Merge tag 'hwmon-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging
Pull hwmon fixes from Guenter Roeck:
"Some more low risk cleanup patches:
- Remove unnecessary pci_set_drvdata in k10temp driver from Jingoo Han
- Fix return values in several drivers from Sachin Kamat
- Remove redundant break in amc6821 driver from Sachin Kamat"
* tag 'hwmon-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging:
hwmon: (k10temp) remove unnecessary pci_set_drvdata()
hwmon: (tmp421) Fix return value
hwmon: (amc6821) Remove redundant break
hwmon: (amc6821) Fix return value
hwmon: (ibmaem) Fix return value
hwmon: (emc2103) Fix return value
diff --git a/Documentation/aoe/udev.txt b/Documentation/aoe/udev.txt
index 8686e78..1f06daf0 100644
--- a/Documentation/aoe/udev.txt
+++ b/Documentation/aoe/udev.txt
@@ -23,4 +23,4 @@
SUBSYSTEM=="aoe", KERNEL=="flush", NAME="etherd/%k", GROUP="disk", MODE="0220"
# aoe block devices
-KERNEL=="etherd*", NAME="%k", GROUP="disk"
+KERNEL=="etherd*", GROUP="disk"
diff --git a/Documentation/block/cmdline-partition.txt b/Documentation/block/cmdline-partition.txt
new file mode 100644
index 0000000..2bbf4cc
--- /dev/null
+++ b/Documentation/block/cmdline-partition.txt
@@ -0,0 +1,39 @@
+Embedded device command line partition
+=====================================================================
+
+Read block device partition table from command line.
+The partition used for fixed block device (eMMC) embedded device.
+It is no MBR, save storage space. Bootloader can be easily accessed
+by absolute address of data on the block device.
+Users can easily change the partition.
+
+The format for the command line is just like mtdparts:
+
+blkdevparts=<blkdev-def>[;<blkdev-def>]
+ <blkdev-def> := <blkdev-id>:<partdef>[,<partdef>]
+ <partdef> := <size>[@<offset>](part-name)
+
+<blkdev-id>
+ block device disk name, embedded device used fixed block device,
+ it's disk name also fixed. such as: mmcblk0, mmcblk1, mmcblk0boot0.
+
+<size>
+ partition size, in bytes, such as: 512, 1m, 1G.
+
+<offset>
+ partition start address, in bytes.
+
+(part-name)
+ partition name, kernel send uevent with "PARTNAME". application can create
+ a link to block device partition with the name "PARTNAME".
+ user space application can access partition by partition name.
+
+Example:
+ eMMC disk name is "mmcblk0" and "mmcblk0boot0"
+
+ bootargs:
+ 'blkdevparts=mmcblk0:1G(data0),1G(data1),-;mmcblk0boot0:1m(boot),-(kernel)'
+
+ dmesg:
+ mmcblk0: p1(data0) p2(data1) p3()
+ mmcblk0boot0: p1(boot) p2(kernel)
diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index 2a33306..8af4ad1 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -490,6 +490,8 @@
pgpgout - # of uncharging events to the memory cgroup. The uncharging
event happens each time a page is unaccounted from the cgroup.
swap - # of bytes of swap usage
+writeback - # of bytes of file/anon cache that are queued for syncing to
+ disk.
inactive_anon - # of bytes of anonymous and swap cache memory on inactive
LRU list.
active_anon - # of bytes of anonymous and swap cache memory on active
diff --git a/Documentation/devicetree/bindings/leds/leds-lp55xx.txt b/Documentation/devicetree/bindings/leds/leds-lp55xx.txt
index d517688..a61727f 100644
--- a/Documentation/devicetree/bindings/leds/leds-lp55xx.txt
+++ b/Documentation/devicetree/bindings/leds/leds-lp55xx.txt
@@ -1,7 +1,7 @@
Binding for TI/National Semiconductor LP55xx Led Drivers
Required properties:
-- compatible: "national,lp5521" or "national,lp5523" or "ti,lp5562"
+- compatible: "national,lp5521" or "national,lp5523" or "ti,lp5562" or "ti,lp8501"
- reg: I2C slave address
- clock-mode: Input clock mode, (0: automode, 1: internal, 2: external)
@@ -11,6 +11,11 @@
Optional properties:
- label: Used for naming LEDs
+- pwr-sel: LP8501 specific property. Power selection for output channels.
+ 0: D1~9 are connected to VDD
+ 1: D1~6 with VDD, D7~9 with VOUT
+ 2: D1~6 with VOUT, D7~9 with VDD
+ 3: D1~9 are connected to VOUT
Alternatively, each child can have specific channel name
- chan-name: Name of each channel name
@@ -145,3 +150,68 @@
max-cur = /bits/ 8 <0x60>;
};
};
+
+example 4) LP8501
+9 channels are defined. The 'pwr-sel' is LP8501 specific property.
+Others are same as LP5523.
+
+lp8501@32 {
+ compatible = "ti,lp8501";
+ reg = <0x32>;
+ clock-mode = /bits/ 8 <2>;
+ pwr-sel = /bits/ 8 <3>; /* D1~9 connected to VOUT */
+
+ chan0 {
+ chan-name = "d1";
+ led-cur = /bits/ 8 <0x14>;
+ max-cur = /bits/ 8 <0x20>;
+ };
+
+ chan1 {
+ chan-name = "d2";
+ led-cur = /bits/ 8 <0x14>;
+ max-cur = /bits/ 8 <0x20>;
+ };
+
+ chan2 {
+ chan-name = "d3";
+ led-cur = /bits/ 8 <0x14>;
+ max-cur = /bits/ 8 <0x20>;
+ };
+
+ chan3 {
+ chan-name = "d4";
+ led-cur = /bits/ 8 <0x14>;
+ max-cur = /bits/ 8 <0x20>;
+ };
+
+ chan4 {
+ chan-name = "d5";
+ led-cur = /bits/ 8 <0x14>;
+ max-cur = /bits/ 8 <0x20>;
+ };
+
+ chan5 {
+ chan-name = "d6";
+ led-cur = /bits/ 8 <0x14>;
+ max-cur = /bits/ 8 <0x20>;
+ };
+
+ chan6 {
+ chan-name = "d7";
+ led-cur = /bits/ 8 <0x14>;
+ max-cur = /bits/ 8 <0x20>;
+ };
+
+ chan7 {
+ chan-name = "d8";
+ led-cur = /bits/ 8 <0x14>;
+ max-cur = /bits/ 8 <0x20>;
+ };
+
+ chan8 {
+ chan-name = "d9";
+ led-cur = /bits/ 8 <0x14>;
+ max-cur = /bits/ 8 <0x20>;
+ };
+};
diff --git a/Documentation/devicetree/bindings/leds/pca963x.txt b/Documentation/devicetree/bindings/leds/pca963x.txt
new file mode 100644
index 0000000..aece3ea
--- /dev/null
+++ b/Documentation/devicetree/bindings/leds/pca963x.txt
@@ -0,0 +1,47 @@
+LEDs connected to pca9632, pca9633 or pca9634
+
+Required properties:
+- compatible : should be : "nxp,pca9632", "nxp,pca9633" or "nxp,pca9634"
+
+Optional properties:
+- nxp,totem-pole : use totem pole (push-pull) instead of default open-drain
+- nxp,hw-blink : use hardware blinking instead of software blinking
+
+Each led is represented as a sub-node of the nxp,pca963x device.
+
+LED sub-node properties:
+- label : (optional) see Documentation/devicetree/bindings/leds/common.txt
+- reg : number of LED line (could be from 0 to 3 in pca9632 or pca9633
+ or 0 to 7 in pca9634)
+- linux,default-trigger : (optional)
+ see Documentation/devicetree/bindings/leds/common.txt
+
+Examples:
+
+pca9632: pca9632 {
+ compatible = "nxp,pca9632";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <0x62>;
+
+ red@0 {
+ label = "red";
+ reg = <0>;
+ linux,default-trigger = "none";
+ };
+ green@1 {
+ label = "green";
+ reg = <1>;
+ linux,default-trigger = "none";
+ };
+ blue@2 {
+ label = "blue";
+ reg = <2>;
+ linux,default-trigger = "none";
+ };
+ unused@3 {
+ label = "unused";
+ reg = <3>;
+ linux,default-trigger = "none";
+ };
+};
diff --git a/Documentation/devicetree/bindings/pci/ralink,rt3883-pci.txt b/Documentation/devicetree/bindings/pci/ralink,rt3883-pci.txt
new file mode 100644
index 0000000..8e0a1eb
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/ralink,rt3883-pci.txt
@@ -0,0 +1,190 @@
+* Mediatek/Ralink RT3883 PCI controller
+
+1) Main node
+
+ Required properties:
+
+ - compatible: must be "ralink,rt3883-pci"
+
+ - reg: specifies the physical base address of the controller and
+ the length of the memory mapped region.
+
+ - #address-cells: specifies the number of cells needed to encode an
+ address. The value must be 1.
+
+ - #size-cells: specifies the number of cells used to represent the size
+ of an address. The value must be 1.
+
+ - ranges: specifies the translation between child address space and parent
+ address space
+
+ Optional properties:
+
+ - status: indicates the operational status of the device.
+ Value must be either "disabled" or "okay".
+
+2) Child nodes
+
+ The main node must have two child nodes which describes the built-in
+ interrupt controller and the PCI host bridge.
+
+ a) Interrupt controller:
+
+ Required properties:
+
+ - interrupt-controller: identifies the node as an interrupt controller
+
+ - #address-cells: specifies the number of cells needed to encode an
+ address. The value must be 0. As such, 'interrupt-map' nodes do not
+ have to specify a parent unit address.
+
+ - #interrupt-cells: specifies the number of cells needed to encode an
+ interrupt source. The value must be 1.
+
+ - interrupt-parent: the phandle for the interrupt controller that
+ services interrupts for this device.
+
+ - interrupts: specifies the interrupt source of the parent interrupt
+ controller. The format of the interrupt specifier depends on the
+ parent interrupt controller.
+
+ b) PCI host bridge:
+
+ Required properties:
+
+ - #address-cells: specifies the number of cells needed to encode an
+ address. The value must be 0.
+
+ - #size-cells: specifies the number of cells used to represent the size
+ of an address. The value must be 2.
+
+ - #interrupt-cells: specifies the number of cells needed to encode an
+ interrupt source. The value must be 1.
+
+ - device_type: must be "pci"
+
+ - bus-range: PCI bus numbers covered
+
+ - ranges: specifies the ranges for the PCI memory and I/O regions
+
+ - interrupt-map-mask,
+ - interrupt-map: standard PCI properties to define the mapping of the
+ PCI interface to interrupt numbers.
+
+ The PCI host bridge node migh have additional sub-nodes representing
+ the onboard PCI devices/PCI slots. Each such sub-node must have the
+ following mandatory properties:
+
+ - reg: used only for interrupt mapping, so only the first four bytes
+ are used to refer to the correct bus number and device number.
+
+ - device_type: must be "pci"
+
+ If a given sub-node represents a PCI bridge it must have following
+ mandatory properties as well:
+
+ - #address-cells: must be set to <3>
+
+ - #size-cells: must set to <2>
+
+ - #interrupt-cells: must be set to <1>
+
+ - interrupt-map-mask,
+ - interrupt-map: standard PCI properties to define the mapping of the
+ PCI interface to interrupt numbers.
+
+ Besides the required properties the sub-nodes may have these optional
+ properties:
+
+ - status: indicates the operational status of the sub-node.
+ Value must be either "disabled" or "okay".
+
+3) Example:
+
+ a) SoC specific dtsi file:
+
+ pci@10140000 {
+ compatible = "ralink,rt3883-pci";
+ reg = <0x10140000 0x20000>;
+ #address-cells = <1>;
+ #size-cells = <1>;
+ ranges; /* direct mapping */
+
+ status = "disabled";
+
+ pciintc: interrupt-controller {
+ interrupt-controller;
+ #address-cells = <0>;
+ #interrupt-cells = <1>;
+
+ interrupt-parent = <&cpuintc>;
+ interrupts = <4>;
+ };
+
+ host-bridge {
+ #address-cells = <3>;
+ #size-cells = <2>;
+ #interrupt-cells = <1>;
+
+ device_type = "pci";
+
+ bus-range = <0 255>;
+ ranges = <
+ 0x02000000 0 0x00000000 0x20000000 0 0x10000000 /* pci memory */
+ 0x01000000 0 0x00000000 0x10160000 0 0x00010000 /* io space */
+ >;
+
+ interrupt-map-mask = <0xf800 0 0 7>;
+ interrupt-map = <
+ /* IDSEL 17 */
+ 0x8800 0 0 1 &pciintc 18
+ 0x8800 0 0 2 &pciintc 18
+ 0x8800 0 0 3 &pciintc 18
+ 0x8800 0 0 4 &pciintc 18
+ /* IDSEL 18 */
+ 0x9000 0 0 1 &pciintc 19
+ 0x9000 0 0 2 &pciintc 19
+ 0x9000 0 0 3 &pciintc 19
+ 0x9000 0 0 4 &pciintc 19
+ >;
+
+ pci-bridge@1 {
+ reg = <0x0800 0 0 0 0>;
+ device_type = "pci";
+ #interrupt-cells = <1>;
+ #address-cells = <3>;
+ #size-cells = <2>;
+
+ interrupt-map-mask = <0x0 0 0 0>;
+ interrupt-map = <0x0 0 0 0 &pciintc 20>;
+
+ status = "disabled";
+ };
+
+ pci-slot@17 {
+ reg = <0x8800 0 0 0 0>;
+ device_type = "pci";
+
+ status = "disabled";
+ };
+
+ pci-slot@18 {
+ reg = <0x9000 0 0 0 0>;
+ device_type = "pci";
+
+ status = "disabled";
+ };
+ };
+ };
+
+ b) Board specific dts file:
+
+ pci@10140000 {
+ status = "okay";
+
+ host-bridge {
+ pci-bridge@1 {
+ status = "okay";
+ };
+ };
+ };
diff --git a/Documentation/devicetree/bindings/rtc/moxa,moxart-rtc.txt b/Documentation/devicetree/bindings/rtc/moxa,moxart-rtc.txt
new file mode 100644
index 0000000..c9d3ac1
--- /dev/null
+++ b/Documentation/devicetree/bindings/rtc/moxa,moxart-rtc.txt
@@ -0,0 +1,17 @@
+MOXA ART real-time clock
+
+Required properties:
+
+- compatible : Should be "moxa,moxart-rtc"
+- gpio-rtc-sclk : RTC sclk gpio, with zero flags
+- gpio-rtc-data : RTC data gpio, with zero flags
+- gpio-rtc-reset : RTC reset gpio, with zero flags
+
+Example:
+
+ rtc: rtc {
+ compatible = "moxa,moxart-rtc";
+ gpio-rtc-sclk = <&gpio 5 0>;
+ gpio-rtc-data = <&gpio 6 0>;
+ gpio-rtc-reset = <&gpio 7 0>;
+ };
diff --git a/Documentation/devicetree/bindings/rtc/rtc-omap.txt b/Documentation/devicetree/bindings/rtc/rtc-omap.txt
index b47aa41..5a0f02d 100644
--- a/Documentation/devicetree/bindings/rtc/rtc-omap.txt
+++ b/Documentation/devicetree/bindings/rtc/rtc-omap.txt
@@ -1,7 +1,11 @@
TI Real Time Clock
Required properties:
-- compatible: "ti,da830-rtc"
+- compatible:
+ - "ti,da830-rtc" - for RTC IP used similar to that on DA8xx SoC family.
+ - "ti,am3352-rtc" - for RTC IP used similar to that on AM335x SoC family.
+ This RTC IP has special WAKE-EN Register to enable
+ Wakeup generation for event Alarm.
- reg: Address range of rtc register set
- interrupts: rtc timer, alarm interrupts in order
- interrupt-parent: phandle for the interrupt controller
diff --git a/Documentation/devicetree/bindings/rtc/rtc-palmas.txt b/Documentation/devicetree/bindings/rtc/rtc-palmas.txt
new file mode 100644
index 0000000..adbccc0
--- /dev/null
+++ b/Documentation/devicetree/bindings/rtc/rtc-palmas.txt
@@ -0,0 +1,33 @@
+Palmas RTC controller bindings
+
+Required properties:
+- compatible:
+ - "ti,palmas-rtc" for palma series of the RTC controller
+- interrupt-parent: Parent interrupt device, must be handle of palmas node.
+- interrupts: Interrupt number of RTC submodule on device.
+
+Optional properties:
+
+- ti,backup-battery-chargeable: The Palmas series device like TPS65913 or
+ TPS80036 supports the backup battery for powering the RTC when main
+ battery is removed or in very low power state. The backup battery
+ can be chargeable or non-chargeable. This flag will tells whether
+ battery is chargeable or not. If charging battery then driver can
+ enable the charging.
+- ti,backup-battery-charge-high-current: Enable high current charging in
+ backup battery. Device supports the < 100mA and > 100mA charging.
+ The high current will be > 100mA. Absence of this property will
+ charge battery to lower current i.e. < 100mA.
+
+Example:
+ palmas: tps65913@58 {
+ ...
+ palmas_rtc: rtc {
+ compatible = "ti,palmas-rtc";
+ interrupt-parent = <&palmas>;
+ interrupts = <8 0>;
+ ti,backup-battery-chargeable;
+ ti,backup-battery-charge-high-current;
+ };
+ ...
+ };
diff --git a/Documentation/devicetree/bindings/sound/mvebu-audio.txt b/Documentation/devicetree/bindings/sound/mvebu-audio.txt
index 7e5fd37..f0062c5 100644
--- a/Documentation/devicetree/bindings/sound/mvebu-audio.txt
+++ b/Documentation/devicetree/bindings/sound/mvebu-audio.txt
@@ -2,13 +2,17 @@
Required properties:
-- compatible: "marvell,mvebu-audio"
+- compatible:
+ "marvell,kirkwood-audio" for Kirkwood platforms
+ "marvell,dove-audio" for Dove platforms
- reg: physical base address of the controller and length of memory mapped
region.
-- interrupts: list of two irq numbers.
- The first irq is used for data flow and the second one is used for errors.
+- interrupts:
+ with "marvell,kirkwood-audio", the audio interrupt
+ with "marvell,dove-audio", a list of two interrupts, the first for
+ the data flow, and the second for errors.
- clocks: one or two phandles.
The first one is mandatory and defines the internal clock.
@@ -21,7 +25,7 @@
Example:
i2s1: audio-controller@b4000 {
- compatible = "marvell,mvebu-audio";
+ compatible = "marvell,dove-audio";
reg = <0xb4000 0x2210>;
interrupts = <21>, <22>;
clocks = <&gate_clk 13>;
diff --git a/Documentation/devicetree/bindings/thermal/exynos-thermal.txt b/Documentation/devicetree/bindings/thermal/exynos-thermal.txt
new file mode 100644
index 0000000..284f530
--- /dev/null
+++ b/Documentation/devicetree/bindings/thermal/exynos-thermal.txt
@@ -0,0 +1,55 @@
+* Exynos Thermal Management Unit (TMU)
+
+** Required properties:
+
+- compatible : One of the following:
+ "samsung,exynos4412-tmu"
+ "samsung,exynos4210-tmu"
+ "samsung,exynos5250-tmu"
+ "samsung,exynos5440-tmu"
+- interrupt-parent : The phandle for the interrupt controller
+- reg : Address range of the thermal registers. For soc's which has multiple
+ instances of TMU and some registers are shared across all TMU's like
+ interrupt related then 2 set of register has to supplied. First set
+ belongs to each instance of TMU and second set belongs to common TMU
+ registers.
+- interrupts : Should contain interrupt for thermal system
+- clocks : The main clock for TMU device
+- clock-names : Thermal system clock name
+- vtmu-supply: This entry is optional and provides the regulator node supplying
+ voltage to TMU. If needed this entry can be placed inside
+ board/platform specific dts file.
+
+Example 1):
+
+ tmu@100C0000 {
+ compatible = "samsung,exynos4412-tmu";
+ interrupt-parent = <&combiner>;
+ reg = <0x100C0000 0x100>;
+ interrupts = <2 4>;
+ clocks = <&clock 383>;
+ clock-names = "tmu_apbif";
+ status = "disabled";
+ vtmu-supply = <&tmu_regulator_node>;
+ };
+
+Example 2):
+
+ tmuctrl_0: tmuctrl@160118 {
+ compatible = "samsung,exynos5440-tmu";
+ reg = <0x160118 0x230>, <0x160368 0x10>;
+ interrupts = <0 58 0>;
+ clocks = <&clock 21>;
+ clock-names = "tmu_apbif";
+ };
+
+Note: For multi-instance tmu each instance should have an alias correctly
+numbered in "aliases" node.
+
+Example:
+
+aliases {
+ tmuctrl0 = &tmuctrl_0;
+ tmuctrl1 = &tmuctrl_1;
+ tmuctrl2 = &tmuctrl_2;
+};
diff --git a/Documentation/devicetree/bindings/thermal/imx-thermal.txt b/Documentation/devicetree/bindings/thermal/imx-thermal.txt
new file mode 100644
index 0000000..541c25e
--- /dev/null
+++ b/Documentation/devicetree/bindings/thermal/imx-thermal.txt
@@ -0,0 +1,17 @@
+* Temperature Monitor (TEMPMON) on Freescale i.MX SoCs
+
+Required properties:
+- compatible : "fsl,imx6q-thermal"
+- fsl,tempmon : phandle pointer to system controller that contains TEMPMON
+ control registers, e.g. ANATOP on imx6q.
+- fsl,tempmon-data : phandle pointer to fuse controller that contains TEMPMON
+ calibration data, e.g. OCOTP on imx6q. The details about calibration data
+ can be found in SoC Reference Manual.
+
+Example:
+
+tempmon {
+ compatible = "fsl,imx6q-tempmon";
+ fsl,tempmon = <&anatop>;
+ fsl,tempmon-data = <&ocotp>;
+};
diff --git a/Documentation/dma-buf-sharing.txt b/Documentation/dma-buf-sharing.txt
index e31a2a9..505e711 100644
--- a/Documentation/dma-buf-sharing.txt
+++ b/Documentation/dma-buf-sharing.txt
@@ -407,6 +407,18 @@
interesting ways depending upong the exporter (if userspace starts depending
upon this implicit synchronization).
+Other Interfaces Exposed to Userspace on the dma-buf FD
+------------------------------------------------------
+
+- Since kernel 3.12 the dma-buf FD supports the llseek system call, but only
+ with offset=0 and whence=SEEK_END|SEEK_SET. SEEK_SET is supported to allow
+ the usual size discover pattern size = SEEK_END(0); SEEK_SET(0). Every other
+ llseek operation will report -EINVAL.
+
+ If llseek on dma-buf FDs isn't support the kernel will report -ESPIPE for all
+ cases. Userspace can use this to detect support for discovering the dma-buf
+ size using llseek.
+
Miscellaneous notes
-------------------
diff --git a/fs/cifs/AUTHORS b/Documentation/filesystems/cifs/AUTHORS
similarity index 98%
rename from fs/cifs/AUTHORS
rename to Documentation/filesystems/cifs/AUTHORS
index ea940b1..ca4a67a 100644
--- a/fs/cifs/AUTHORS
+++ b/Documentation/filesystems/cifs/AUTHORS
@@ -39,6 +39,7 @@
Gunter Kukkukk (testing and suggestions for support of old servers)
Igor Mammedov (DFS support)
Jeff Layton (many, many fixes, as well as great work on the cifs Kerberos code)
+Scott Lovenberg
Test case and Bug Report contributors
-------------------------------------
diff --git a/fs/cifs/CHANGES b/Documentation/filesystems/cifs/CHANGES
similarity index 100%
rename from fs/cifs/CHANGES
rename to Documentation/filesystems/cifs/CHANGES
diff --git a/fs/cifs/README b/Documentation/filesystems/cifs/README
similarity index 100%
rename from fs/cifs/README
rename to Documentation/filesystems/cifs/README
diff --git a/fs/cifs/TODO b/Documentation/filesystems/cifs/TODO
similarity index 100%
rename from fs/cifs/TODO
rename to Documentation/filesystems/cifs/TODO
diff --git a/Documentation/filesystems/cifs.txt b/Documentation/filesystems/cifs/cifs.txt
similarity index 100%
rename from Documentation/filesystems/cifs.txt
rename to Documentation/filesystems/cifs/cifs.txt
diff --git a/Documentation/filesystems/cifs/winucase_convert.pl b/Documentation/filesystems/cifs/winucase_convert.pl
new file mode 100755
index 0000000..322a9c8
--- /dev/null
+++ b/Documentation/filesystems/cifs/winucase_convert.pl
@@ -0,0 +1,62 @@
+#!/usr/bin/perl -w
+#
+# winucase_convert.pl -- convert "Windows 8 Upper Case Mapping Table.txt" to
+# a two-level set of C arrays.
+#
+# Copyright 2013: Jeff Layton <jlayton@redhat.com>
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program. If not, see <http://www.gnu.org/licenses/>.
+#
+
+while(<>) {
+ next if (!/^0x(..)(..)\t0x(....)\t/);
+ $firstchar = hex($1);
+ $secondchar = hex($2);
+ $uppercase = hex($3);
+
+ $top[$firstchar][$secondchar] = $uppercase;
+}
+
+for ($i = 0; $i < 256; $i++) {
+ next if (!$top[$i]);
+
+ printf("static const wchar_t t2_%2.2x[256] = {", $i);
+ for ($j = 0; $j < 256; $j++) {
+ if (($j % 8) == 0) {
+ print "\n\t";
+ } else {
+ print " ";
+ }
+ printf("0x%4.4x,", $top[$i][$j] ? $top[$i][$j] : 0);
+ }
+ print "\n};\n\n";
+}
+
+printf("static const wchar_t *const toplevel[256] = {", $i);
+for ($i = 0; $i < 256; $i++) {
+ if (($i % 8) == 0) {
+ print "\n\t";
+ } elsif ($top[$i]) {
+ print " ";
+ } else {
+ print " ";
+ }
+
+ if ($top[$i]) {
+ printf("t2_%2.2x,", $i);
+ } else {
+ print "NULL,";
+ }
+}
+print "\n};\n\n";
diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index 206a1bd..f089058 100644
--- a/Documentation/filesystems/porting
+++ b/Documentation/filesystems/porting
@@ -451,3 +451,7 @@
--
[mandatory]
->readdir() is gone now; switch to ->iterate()
+[mandatory]
+ vfs_follow_link has been removed. Filesystems must use nd_set_link
+ from ->follow_link for normal symlinks, or nd_jump_link for magic
+ /proc/<pid> style links.
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index fcc22c9..823c95f 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -854,16 +854,15 @@
The committed memory is a sum of all of the memory which
has been allocated by processes, even if it has not been
"used" by them as of yet. A process which malloc()'s 1G
- of memory, but only touches 300M of it will only show up
- as using 300M of memory even if it has the address space
- allocated for the entire 1G. This 1G is memory which has
- been "committed" to by the VM and can be used at any time
- by the allocating application. With strict overcommit
- enabled on the system (mode 2 in 'vm.overcommit_memory'),
- allocations which would exceed the CommitLimit (detailed
- above) will not be permitted. This is useful if one needs
- to guarantee that processes will not fail due to lack of
- memory once that memory has been successfully allocated.
+ of memory, but only touches 300M of it will show up as
+ using 1G. This 1G is memory which has been "committed" to
+ by the VM and can be used at any time by the allocating
+ application. With strict overcommit enabled on the system
+ (mode 2 in 'vm.overcommit_memory'),allocations which would
+ exceed the CommitLimit (detailed above) will not be permitted.
+ This is useful if one needs to guarantee that processes will
+ not fail due to lack of memory once that memory has been
+ successfully allocated.
VmallocTotal: total size of vmalloc memory area
VmallocUsed: amount of vmalloc area which is used
VmallocChunk: largest contiguous block of vmalloc area which is free
diff --git a/Documentation/filesystems/ramfs-rootfs-initramfs.txt b/Documentation/filesystems/ramfs-rootfs-initramfs.txt
index 59b4a096..b176928 100644
--- a/Documentation/filesystems/ramfs-rootfs-initramfs.txt
+++ b/Documentation/filesystems/ramfs-rootfs-initramfs.txt
@@ -79,6 +79,10 @@
Most systems just mount another filesystem over rootfs and ignore it. The
amount of space an empty instance of ramfs takes up is tiny.
+If CONFIG_TMPFS is enabled, rootfs will use tmpfs instead of ramfs by
+default. To force ramfs, add "rootfstype=ramfs" to the kernel command
+line.
+
What is initramfs?
------------------
diff --git a/Documentation/kbuild/kconfig-language.txt b/Documentation/kbuild/kconfig-language.txt
index c858f84..c420676 100644
--- a/Documentation/kbuild/kconfig-language.txt
+++ b/Documentation/kbuild/kconfig-language.txt
@@ -147,6 +147,7 @@
- "modules"
This declares the symbol to be used as the MODULES symbol, which
enables the third modular state for all config symbols.
+ At most one symbol may have the "modules" option set.
- "env"=<value>
This imports the environment variable into Kconfig. It behaves like
diff --git a/Documentation/kbuild/kconfig.txt b/Documentation/kbuild/kconfig.txt
index e349f29..8ef6dbb 100644
--- a/Documentation/kbuild/kconfig.txt
+++ b/Documentation/kbuild/kconfig.txt
@@ -175,11 +175,9 @@
/^hotplug
When searching, symbols are sorted thus:
- - exact match first: an exact match is when the search matches
- the complete symbol name;
- - alphabetical order: when two symbols do not match exactly,
- they are sorted in alphabetical order (in the user's current
- locale).
+ - first, exact matches, sorted alphabetically (an exact match
+ is when the search matches the complete symbol name);
+ - then, other matches, sorted alphabetically.
For example: ^ATH.K matches:
ATH5K ATH9K ATH5K_AHB ATH5K_DEBUG [...] ATH6KL ATH6KL_DEBUG
[...] ATH9K_AHB ATH9K_BTCOEX_SUPPORT ATH9K_COMMON [...]
diff --git a/Documentation/leds/leds-lp5521.txt b/Documentation/leds/leds-lp5521.txt
index 79e4c2e..d08d8c1 100644
--- a/Documentation/leds/leds-lp5521.txt
+++ b/Documentation/leds/leds-lp5521.txt
@@ -18,7 +18,25 @@
More details of the instructions can be found from the public data sheet.
LP5521 has the internal program memory for running various LED patterns.
-For the details, please refer to 'firmware' section in leds-lp55xx.txt
+There are two ways to run LED patterns.
+
+1) Legacy interface - enginex_mode and enginex_load
+ Control interface for the engines:
+ x is 1 .. 3
+ enginex_mode : disabled, load, run
+ enginex_load : store program (visible only in engine load mode)
+
+ Example (start to blink the channel 2 led):
+ cd /sys/class/leds/lp5521:channel2/device
+ echo "load" > engine3_mode
+ echo "037f4d0003ff6000" > engine3_load
+ echo "run" > engine3_mode
+
+ To stop the engine:
+ echo "disabled" > engine3_mode
+
+2) Firmware interface - LP55xx common interface
+ For the details, please refer to 'firmware' section in leds-lp55xx.txt
sysfs contains a selftest entry.
The test communicates with the chip and checks that
diff --git a/Documentation/leds/leds-lp5523.txt b/Documentation/leds/leds-lp5523.txt
index 899fdad..5b3e91d4 100644
--- a/Documentation/leds/leds-lp5523.txt
+++ b/Documentation/leds/leds-lp5523.txt
@@ -28,7 +28,26 @@
/sys/class/leds/lp5523:channelN (N: 0 ~ 8)
LP5523 has the internal program memory for running various LED patterns.
-For the details, please refer to 'firmware' section in leds-lp55xx.txt
+There are two ways to run LED patterns.
+
+1) Legacy interface - enginex_mode, enginex_load and enginex_leds
+ Control interface for the engines:
+ x is 1 .. 3
+ enginex_mode : disabled, load, run
+ enginex_load : microcode load (visible only in load mode)
+ enginex_leds : led mux control (visible only in load mode)
+
+ cd /sys/class/leds/lp5523:channel2/device
+ echo "load" > engine3_mode
+ echo "9d80400004ff05ff437f0000" > engine3_load
+ echo "111111111" > engine3_leds
+ echo "run" > engine3_mode
+
+ To stop the engine:
+ echo "disabled" > engine3_mode
+
+2) Firmware interface - LP55xx common interface
+ For the details, please refer to 'firmware' section in leds-lp55xx.txt
Selftest uses always the current from the platform data.
diff --git a/Documentation/leds/leds-lp55xx.txt b/Documentation/leds/leds-lp55xx.txt
index eec8fa2..82713ff 100644
--- a/Documentation/leds/leds-lp55xx.txt
+++ b/Documentation/leds/leds-lp55xx.txt
@@ -1,11 +1,11 @@
-LP5521/LP5523/LP55231 Common Driver
-===================================
+LP5521/LP5523/LP55231/LP5562/LP8501 Common Driver
+=================================================
Authors: Milo(Woogyom) Kim <milo.kim@ti.com>
Description
-----------
-LP5521, LP5523/55231 and LP5562 have common features as below.
+LP5521, LP5523/55231, LP5562 and LP8501 have common features as below.
Register access via the I2C
Device initialization/deinitialization
@@ -109,6 +109,30 @@
Inside the callback, the selected engine is loaded and memory is updated.
To run programmed pattern, 'run_engine' attribute should be enabled.
+The pattern sqeuence of LP8501 is same as LP5523.
+However pattern data is specific.
+Ex 1) Engine 1 is used
+echo 1 > /sys/bus/i2c/devices/xxxx/select_engine
+echo 1 > /sys/class/firmware/lp8501/loading
+echo "9d0140ff7e0040007e00a001c000" > /sys/class/firmware/lp8501/data
+echo 0 > /sys/class/firmware/lp8501/loading
+echo 1 > /sys/bus/i2c/devices/xxxx/run_engine
+
+Ex 2) Engine 2 and 3 are used at the same time
+echo 2 > /sys/bus/i2c/devices/xxxx/select_engine
+sleep 1
+echo 1 > /sys/class/firmware/lp8501/loading
+echo "9d0140ff7e0040007e00a001c000" > /sys/class/firmware/lp8501/data
+echo 0 > /sys/class/firmware/lp8501/loading
+sleep 1
+echo 3 > /sys/bus/i2c/devices/xxxx/select_engine
+sleep 1
+echo 1 > /sys/class/firmware/lp8501/loading
+echo "9d0340ff7e0040007e00a001c000" > /sys/class/firmware/lp8501/data
+echo 0 > /sys/class/firmware/lp8501/loading
+sleep 1
+echo 1 > /sys/class/leds/d1/device/run_engine
+
( 'run_engine' and 'firmware_cb' )
The sequence of running the program data is common.
But each device has own specific register addresses for commands.
diff --git a/Documentation/networking/00-INDEX b/Documentation/networking/00-INDEX
index 18b64b2..f11580f 100644
--- a/Documentation/networking/00-INDEX
+++ b/Documentation/networking/00-INDEX
@@ -86,6 +86,8 @@
- info on Generic Netlink
gianfar.txt
- Gianfar Ethernet Driver.
+i40e.txt
+ - README for the Intel Ethernet Controller XL710 Driver (i40e).
ieee802154.txt
- Linux IEEE 802.15.4 implementation, API and drivers
igb.txt
diff --git a/Documentation/networking/i40e.txt b/Documentation/networking/i40e.txt
new file mode 100644
index 0000000..f737273
--- /dev/null
+++ b/Documentation/networking/i40e.txt
@@ -0,0 +1,115 @@
+Linux Base Driver for the Intel(R) Ethernet Controller XL710 Family
+===================================================================
+
+Intel i40e Linux driver.
+Copyright(c) 2013 Intel Corporation.
+
+Contents
+========
+
+- Identifying Your Adapter
+- Additional Configurations
+- Performance Tuning
+- Known Issues
+- Support
+
+
+Identifying Your Adapter
+========================
+
+The driver in this release is compatible with the Intel Ethernet
+Controller XL710 Family.
+
+For more information on how to identify your adapter, go to the Adapter &
+Driver ID Guide at:
+
+ http://support.intel.com/support/network/sb/CS-012904.htm
+
+
+Enabling the driver
+===================
+
+The driver is enabled via the standard kernel configuration system,
+using the make command:
+
+ Make oldconfig/silentoldconfig/menuconfig/etc.
+
+The driver is located in the menu structure at:
+
+ -> Device Drivers
+ -> Network device support (NETDEVICES [=y])
+ -> Ethernet driver support
+ -> Intel devices
+ -> Intel(R) Ethernet Controller XL710 Family
+
+Additional Configurations
+=========================
+
+ Generic Receive Offload (GRO)
+ -----------------------------
+ The driver supports the in-kernel software implementation of GRO. GRO has
+ shown that by coalescing Rx traffic into larger chunks of data, CPU
+ utilization can be significantly reduced when under large Rx load. GRO is
+ an evolution of the previously-used LRO interface. GRO is able to coalesce
+ other protocols besides TCP. It's also safe to use with configurations that
+ are problematic for LRO, namely bridging and iSCSI.
+
+ Ethtool
+ -------
+ The driver utilizes the ethtool interface for driver configuration and
+ diagnostics, as well as displaying statistical information. The latest
+ ethtool version is required for this functionality.
+
+ The latest release of ethtool can be found from
+ https://www.kernel.org/pub/software/network/ethtool
+
+ Data Center Bridging (DCB)
+ --------------------------
+ DCB configuration is not currently supported.
+
+ FCoE
+ ----
+ Fiber Channel over Ethernet (FCoE) hardware offload is not currently
+ supported.
+
+ MAC and VLAN anti-spoofing feature
+ ----------------------------------
+ When a malicious driver attempts to send a spoofed packet, it is dropped by
+ the hardware and not transmitted. An interrupt is sent to the PF driver
+ notifying it of the spoof attempt.
+
+ When a spoofed packet is detected the PF driver will send the following
+ message to the system log (displayed by the "dmesg" command):
+
+ Spoof event(s) detected on VF (n)
+
+ Where n=the VF that attempted to do the spoofing.
+
+
+Performance Tuning
+==================
+
+An excellent article on performance tuning can be found at:
+
+http://www.redhat.com/promo/summit/2008/downloads/pdf/Thursday/Mark_Wagner.pdf
+
+
+Known Issues
+============
+
+
+Support
+=======
+
+For general information, go to the Intel support website at:
+
+ http://support.intel.com
+
+or the Intel Wired Networking project hosted by Sourceforge at:
+
+ http://e1000.sourceforge.net
+
+If an issue is identified with the released source code on the supported
+kernel with a supported adapter, email the specific information related
+to the issue to e1000-devel@lists.sourceforge.net and copy
+netdev@vger.kernel.org.
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index ab7d16e..9d4c1d1 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -182,6 +182,7 @@
%<NUL> '%' is dropped
%% output one '%'
%p pid
+ %P global pid (init PID namespace)
%u uid
%g gid
%d dump mode, matches PR_SET_DUMPABLE and
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 36ecc26..79a797e 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -200,17 +200,25 @@
hugepages_treat_as_movable
-This parameter is only useful when kernelcore= is specified at boot time to
-create ZONE_MOVABLE for pages that may be reclaimed or migrated. Huge pages
-are not movable so are not normally allocated from ZONE_MOVABLE. A non-zero
-value written to hugepages_treat_as_movable allows huge pages to be allocated
-from ZONE_MOVABLE.
+This parameter controls whether we can allocate hugepages from ZONE_MOVABLE
+or not. If set to non-zero, hugepages can be allocated from ZONE_MOVABLE.
+ZONE_MOVABLE is created when kernel boot parameter kernelcore= is specified,
+so this parameter has no effect if used without kernelcore=.
-Once enabled, the ZONE_MOVABLE is treated as an area of memory the huge
-pages pool can easily grow or shrink within. Assuming that applications are
-not running that mlock() a lot of memory, it is likely the huge pages pool
-can grow to the size of ZONE_MOVABLE by repeatedly entering the desired value
-into nr_hugepages and triggering page reclaim.
+Hugepage migration is now available in some situations which depend on the
+architecture and/or the hugepage size. If a hugepage supports migration,
+allocation from ZONE_MOVABLE is always enabled for the hugepage regardless
+of the value of this parameter.
+IOW, this parameter affects only non-migratable hugepages.
+
+Assuming that hugepages are not migratable in your system, one usecase of
+this parameter is that users can make hugepage pool more extensible by
+enabling the allocation from ZONE_MOVABLE. This is because on ZONE_MOVABLE
+page reclaim/migration/compaction work more and you can get contiguous
+memory more likely. Note that using ZONE_MOVABLE for non-migratable
+hugepages can do harm to other features like memory hotremove (because
+memory hotremove expects that memory blocks on ZONE_MOVABLE are always
+removable,) so it's a trade-off responsible for the users.
==============================================================
diff --git a/Documentation/thermal/exynos_thermal b/Documentation/thermal/exynos_thermal
index 2b46f67..9010c44 100644
--- a/Documentation/thermal/exynos_thermal
+++ b/Documentation/thermal/exynos_thermal
@@ -1,17 +1,17 @@
-Kernel driver exynos4_tmu
+Kernel driver exynos_tmu
=================
Supported chips:
-* ARM SAMSUNG EXYNOS4 series of SoC
- Prefix: 'exynos4-tmu'
+* ARM SAMSUNG EXYNOS4, EXYNOS5 series of SoC
Datasheet: Not publicly available
Authors: Donggeun Kim <dg77.kim@samsung.com>
+Authors: Amit Daniel <amit.daniel@samsung.com>
-Description
------------
+TMU controller Description:
+---------------------------
-This driver allows to read temperature inside SAMSUNG EXYNOS4 series of SoC.
+This driver allows to read temperature inside SAMSUNG EXYNOS4/5 series of SoC.
The chip only exposes the measured 8-bit temperature code value
through a register.
@@ -34,9 +34,9 @@
TI2: Trimming info for 85 degree Celsius (stored at TRIMINFO register)
Temperature code measured at 85 degree Celsius which is unchanged
-TMU(Thermal Management Unit) in EXYNOS4 generates interrupt
+TMU(Thermal Management Unit) in EXYNOS4/5 generates interrupt
when temperature exceeds pre-defined levels.
-The maximum number of configurable threshold is four.
+The maximum number of configurable threshold is five.
The threshold levels are defined as follows:
Level_0: current temperature > trigger_level_0 + threshold
Level_1: current temperature > trigger_level_1 + threshold
@@ -47,6 +47,31 @@
through the corresponding registers.
When an interrupt occurs, this driver notify kernel thermal framework
-with the function exynos4_report_trigger.
+with the function exynos_report_trigger.
Although an interrupt condition for level_0 can be set,
it can be used to synchronize the cooling action.
+
+TMU driver description:
+-----------------------
+
+The exynos thermal driver is structured as,
+
+ Kernel Core thermal framework
+ (thermal_core.c, step_wise.c, cpu_cooling.c)
+ ^
+ |
+ |
+TMU configuration data -------> TMU Driver <------> Exynos Core thermal wrapper
+(exynos_tmu_data.c) (exynos_tmu.c) (exynos_thermal_common.c)
+(exynos_tmu_data.h) (exynos_tmu.h) (exynos_thermal_common.h)
+
+a) TMU configuration data: This consist of TMU register offsets/bitfields
+ described through structure exynos_tmu_registers. Also several
+ other platform data (struct exynos_tmu_platform_data) members
+ are used to configure the TMU.
+b) TMU driver: This component initialises the TMU controller and sets different
+ thresholds. It invokes core thermal implementation with the call
+ exynos_report_trigger.
+c) Exynos Core thermal wrapper: This provides 3 wrapper function to use the
+ Kernel core thermal framework. They are exynos_unregister_thermal,
+ exynos_register_thermal and exynos_report_trigger.
diff --git a/Documentation/thermal/sysfs-api.txt b/Documentation/thermal/sysfs-api.txt
index a71bd5b..87519cb 100644
--- a/Documentation/thermal/sysfs-api.txt
+++ b/Documentation/thermal/sysfs-api.txt
@@ -134,6 +134,13 @@
this thermal zone and cdev, for a particular trip point.
If nth bit is set, then the cdev and thermal zone are bound
for trip point n.
+ .limits: This is an array of cooling state limits. Must have exactly
+ 2 * thermal_zone.number_of_trip_points. It is an array consisting
+ of tuples <lower-state upper-state> of state limits. Each trip
+ will be associated with one state limit tuple when binding.
+ A NULL pointer means <THERMAL_NO_LIMITS THERMAL_NO_LIMITS>
+ on all trips. These limits are used when binding a cdev to a
+ trip point.
.match: This call back returns success(0) if the 'tz and cdev' need to
be bound, as per platform data.
1.4.2 struct thermal_zone_params
@@ -142,6 +149,11 @@
This is an optional feature where some platforms can choose not to
provide this data.
.governor_name: Name of the thermal governor used for this zone
+ .no_hwmon: a boolean to indicate if the thermal to hwmon sysfs interface
+ is required. when no_hwmon == false, a hwmon sysfs interface
+ will be created. when no_hwmon == true, nothing will be done.
+ In case the thermal_zone_params is NULL, the hwmon interface
+ will be created (for backward compatibility).
.num_tbps: Number of thermal_bind_params entries for this zone
.tbp: thermal_bind_params entries
diff --git a/Documentation/vm/hugetlbpage.txt b/Documentation/vm/hugetlbpage.txt
index 4ac359b..bdd4bb9 100644
--- a/Documentation/vm/hugetlbpage.txt
+++ b/Documentation/vm/hugetlbpage.txt
@@ -165,6 +165,7 @@
Interaction of Task Memory Policy with Huge Page Allocation/Freeing
+===================================================================
Whether huge pages are allocated and freed via the /proc interface or
the /sysfs interface using the nr_hugepages_mempolicy attribute, the NUMA
@@ -229,6 +230,7 @@
of huge pages over all on-lines nodes with memory.
Per Node Hugepages Attributes
+=============================
A subset of the contents of the root huge page control directory in sysfs,
described above, will be replicated under each the system device of each
@@ -258,6 +260,7 @@
Using Huge Pages
+================
If the user applications are going to request huge pages using mmap system
call, then it is required that system administrator mount a file system of
@@ -296,20 +299,16 @@
without MAP_HUGETLB. For an example of how to use mmap with MAP_HUGETLB see
map_hugetlb.c.
-*******************************************************************
+Examples
+========
-/*
- * map_hugetlb: see tools/testing/selftests/vm/map_hugetlb.c
- */
+1) map_hugetlb: see tools/testing/selftests/vm/map_hugetlb.c
-*******************************************************************
+2) hugepage-shm: see tools/testing/selftests/vm/hugepage-shm.c
-/*
- * hugepage-shm: see tools/testing/selftests/vm/hugepage-shm.c
- */
+3) hugepage-mmap: see tools/testing/selftests/vm/hugepage-mmap.c
-*******************************************************************
-
-/*
- * hugepage-mmap: see tools/testing/selftests/vm/hugepage-mmap.c
- */
+4) The libhugetlbfs (http://libhugetlbfs.sourceforge.net) library provides a
+ wide range of userspace tools to help with huge page usability, environment
+ setup, and control. Furthermore it provides useful test cases that should be
+ used when modifying code to ensure no regressions are introduced.
diff --git a/Documentation/vm/soft-dirty.txt b/Documentation/vm/soft-dirty.txt
index 9a12a59..55684d1 100644
--- a/Documentation/vm/soft-dirty.txt
+++ b/Documentation/vm/soft-dirty.txt
@@ -28,6 +28,13 @@
the kernel does is finds this fact out and puts both writable and soft-dirty
bits on the PTE.
+ While in most cases tracking memory changes by #PF-s is more than enough
+there is still a scenario when we can lose soft dirty bits -- a task
+unmaps a previously mapped memory region and then maps a new one at exactly
+the same place. When unmap is called, the kernel internally clears PTE values
+including soft dirty bits. To notify user space application about such
+memory region renewal the kernel always marks new memory regions (and
+expanded regions) as soft dirty.
This feature is actively used by the checkpoint-restore project. You
can find more details about it on http://criu.org
diff --git a/MAINTAINERS b/MAINTAINERS
index d721af1..e61c2e8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1028,7 +1028,7 @@
ARM/MICREL KS8695 ARCHITECTURE
M: Greg Ungerer <gerg@uclinux.org>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-F: arch/arm/mach-ks8695
+F: arch/arm/mach-ks8695/
S: Odd Fixes
ARM/MIOA701 MACHINE SUPPORT
@@ -1048,7 +1048,6 @@
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
F: arch/arm/mach-nomadik/
-F: arch/arm/plat-nomadik/
F: drivers/i2c/busses/i2c-nomadik.c
T: git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-nomadik.git
@@ -1070,7 +1069,7 @@
F: drivers/tty/serial/msm_serial.h
F: drivers/tty/serial/msm_serial.c
F: drivers/*/pm8???-*
-F: drivers/ssbi/
+F: drivers/mfd/ssbi/
F: include/linux/mfd/pm8xxx/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/davidb/linux-msm.git
S: Maintained
@@ -1156,7 +1155,6 @@
W: http://www.fluff.org/ben/linux/
S: Maintained
F: arch/arm/plat-samsung/
-F: arch/arm/plat-s3c24xx/
F: arch/arm/mach-s3c24*/
F: arch/arm/mach-s3c64xx/
F: drivers/*/*s3c2410*
@@ -1179,8 +1177,6 @@
S: Maintained
F: arch/arm/mach-s5pv210/mach-aquila.c
F: arch/arm/mach-s5pv210/mach-goni.c
-F: arch/arm/mach-exynos/mach-universal_c210.c
-F: arch/arm/mach-exynos/mach-nuri.c
ARM/SAMSUNG S5P SERIES 2D GRAPHICS ACCELERATION (G2D) SUPPORT
M: Kyungmin Park <kyungmin.park@samsung.com>
@@ -1325,7 +1321,7 @@
F: drivers/pwm/pwm-vt8500.c
F: drivers/rtc/rtc-vt8500.c
F: drivers/tty/serial/vt8500_serial.c
-F: drivers/usb/host/ehci-vt8500.c
+F: drivers/usb/host/ehci-platform.c
F: drivers/usb/host/uhci-platform.c
F: drivers/video/vt8500lcdfb.*
F: drivers/video/wm8505fb*
@@ -1815,6 +1811,17 @@
S: Supported
F: drivers/net/ethernet/broadcom/bnx2x/
+BROADCOM BCM281XX/BCM11XXX ARM ARCHITECTURE
+M: Christian Daudt <csd@broadcom.com>
+T: git git://git.github.com/broadcom/bcm11351
+S: Maintained
+F: arch/arm/mach-bcm/
+F: arch/arm/boot/dts/bcm113*
+F: arch/arm/boot/dts/bcm281*
+F: arch/arm/configs/bcm_defconfig
+F: drivers/mmc/host/sdhci_bcm_kona.c
+F: drivers/clocksource/bcm_kona_timer.c
+
BROADCOM BCM2835 ARM ARCHICTURE
M: Stephen Warren <swarren@wwwdotorg.org>
L: linux-rpi-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -2035,10 +2042,10 @@
T: git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
S: Supported
F: Documentation/filesystems/ceph.txt
-F: fs/ceph
-F: net/ceph
-F: include/linux/ceph
-F: include/linux/crush
+F: fs/ceph/
+F: net/ceph/
+F: include/linux/ceph/
+F: include/linux/crush/
CERTIFIED WIRELESS USB (WUSB) SUBSYSTEM:
L: linux-usb@vger.kernel.org
@@ -2335,7 +2342,7 @@
M: Dominik Brodowski <linux@dominikbrodowski.net>
M: Thomas Renninger <trenn@suse.de>
S: Maintained
-F: tools/power/cpupower
+F: tools/power/cpupower/
CPUSETS
M: Li Zefan <lizefan@huawei.com>
@@ -2773,7 +2780,7 @@
L: dri-devel@lists.freedesktop.org
T: git git://people.freedesktop.org/~danvet/drm-intel
S: Supported
-F: drivers/gpu/drm/i915
+F: drivers/gpu/drm/i915/
F: include/drm/i915*
F: include/uapi/drm/i915*
@@ -2785,7 +2792,7 @@
L: dri-devel@lists.freedesktop.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/daeinki/drm-exynos.git
S: Supported
-F: drivers/gpu/drm/exynos
+F: drivers/gpu/drm/exynos/
F: include/drm/exynos*
F: include/uapi/drm/exynos*
@@ -3038,7 +3045,7 @@
L: linux-edac@vger.kernel.org
W: bluesmoke.sourceforge.net
S: Maintained
-F: drivers/edac/ghes-edac.c
+F: drivers/edac/ghes_edac.c
EDAC-I82443BXGX
M: Tim Small <tim@buttersideup.com>
@@ -3644,8 +3651,8 @@
L: linux-arch@vger.kernel.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/arnd/asm-generic.git
S: Maintained
-F: include/asm-generic
-F: include/uapi/asm-generic
+F: include/asm-generic/
+F: include/uapi/asm-generic/
GENERIC UIO DRIVER FOR PCI DEVICES
M: "Michael S. Tsirkin" <mst@redhat.com>
@@ -3687,7 +3694,8 @@
M: Dmitry Kozlov <xeb@mail.ru>
L: netdev@vger.kernel.org
S: Maintained
-F: net/ipv4/gre.c
+F: net/ipv4/gre_demux.c
+F: net/ipv4/gre_offload.c
F: include/net/gre.h
GRETH 10/100/1G Ethernet MAC device driver
@@ -3765,7 +3773,7 @@
T: git git://linuxtv.org/media_tree.git
W: http://linuxtv.org
S: Odd Fixes
-F: drivers/media/usb/hdpvr
+F: drivers/media/usb/hdpvr/
HWPOISON MEMORY FAILURE HANDLING
M: Andi Kleen <andi@firstfloor.org>
@@ -4355,7 +4363,7 @@
S: Maintained
F: drivers/char/hw_random/ixp4xx-rng.c
-INTEL ETHERNET DRIVERS (e100/e1000/e1000e/igb/igbvf/ixgb/ixgbe/ixgbevf)
+INTEL ETHERNET DRIVERS (e100/e1000/e1000e/igb/igbvf/ixgb/ixgbe/ixgbevf/i40e)
M: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
M: Jesse Brandeburg <jesse.brandeburg@intel.com>
M: Bruce Allan <bruce.w.allan@intel.com>
@@ -4380,6 +4388,7 @@
F: Documentation/networking/ixgb.txt
F: Documentation/networking/ixgbe.txt
F: Documentation/networking/ixgbevf.txt
+F: Documentation/networking/i40e.txt
F: drivers/net/ethernet/intel/
INTEL PRO/WIRELESS 2100, 2200BG, 2915ABG NETWORK CONNECTION SUPPORT
@@ -4573,7 +4582,7 @@
W: http://www.openfabrics.org
W: www.open-iscsi.org
Q: http://patchwork.kernel.org/project/linux-rdma/list/
-F: drivers/infiniband/ulp/iser
+F: drivers/infiniband/ulp/iser/
ISDN SUBSYSTEM
M: Karsten Keil <isdn@linux-pingi.de>
@@ -4627,7 +4636,7 @@
Q: http://patchwork.linuxtv.org/project/linux-media/list/
T: git git://linuxtv.org/anttip/media_tree.git
S: Maintained
-F: drivers/media/tuners/it913x*
+F: drivers/media/tuners/tuner_it913x*
IVTV VIDEO4LINUX DRIVER
M: Andy Walls <awalls@md.metrocast.net>
@@ -5963,15 +5972,12 @@
F: arch/arm/*omap*/*pm*
F: drivers/cpufreq/omap-cpufreq.c
-OMAP POWERDOMAIN/CLOCKDOMAIN SOC ADAPTATION LAYER SUPPORT
+OMAP POWERDOMAIN SOC ADAPTATION LAYER SUPPORT
M: Rajendra Nayak <rnayak@ti.com>
M: Paul Walmsley <paul@pwsan.com>
L: linux-omap@vger.kernel.org
S: Maintained
-F: arch/arm/mach-omap2/powerdomain2xxx_3xxx.c
-F: arch/arm/mach-omap2/powerdomain44xx.c
-F: arch/arm/mach-omap2/clockdomain2xxx_3xxx.c
-F: arch/arm/mach-omap2/clockdomain44xx.c
+F: arch/arm/mach-omap2/prm*
OMAP AUDIO SUPPORT
M: Peter Ujfalusi <peter.ujfalusi@ti.com>
@@ -6137,7 +6143,7 @@
L: linux@lists.openrisc.net (moderated for non-subscribers)
S: Maintained
T: git git://openrisc.net/~jonas/linux
-F: arch/openrisc
+F: arch/openrisc/
OPENVSWITCH
M: Jesse Gross <jesse@nicira.com>
@@ -6428,7 +6434,7 @@
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
T: git git://github.com/jamieiles/linux-2.6-ji.git
S: Supported
-F: arch/arm/mach-picoxcell
+F: arch/arm/mach-picoxcell/
F: drivers/*/picoxcell*
F: drivers/*/*/picoxcell*
@@ -6701,7 +6707,7 @@
F: drivers/usb/gadget/pxa2*
F: include/sound/pxa2xx-lib.h
F: sound/arm/pxa*
-F: sound/soc/pxa
+F: sound/soc/pxa/
MMP SUPPORT
M: Eric Miao <eric.y.miao@gmail.com>
@@ -7154,7 +7160,7 @@
M: Sangbeom Kim <sbkim73@samsung.com>
L: alsa-devel@alsa-project.org (moderated for non-subscribers)
S: Supported
-F: sound/soc/samsung
+F: sound/soc/samsung/
SAMSUNG FRAMEBUFFER DRIVER
M: Jingoo Han <jg1.han@samsung.com>
@@ -7200,7 +7206,7 @@
M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
L: linux-serial@vger.kernel.org
S: Maintained
-F: drivers/tty/serial
+F: drivers/tty/serial/
SYNOPSYS DESIGNWARE DMAC DRIVER
M: Viresh Kumar <viresh.linux@gmail.com>
@@ -7235,7 +7241,7 @@
M: Huang Shijie <shijie8@gmail.com>
M: Hans Verkuil <hverkuil@xs4all.nl>
S: Odd Fixes
-F: drivers/media/usb/tlg2300
+F: drivers/media/usb/tlg2300/
SC1200 WDT DRIVER
M: Zwane Mwaikambo <zwane@arm.linux.org.uk>
@@ -7496,7 +7502,7 @@
T: git git://linuxtv.org/media_tree.git
W: http://linuxtv.org
S: Odd Fixes
-F: drivers/media/radio/radio-si4713.h
+F: drivers/media/radio/radio-si4713.c
SIANO DVB DRIVER
M: Mauro Carvalho Chehab <m.chehab@samsung.com>
@@ -7505,9 +7511,9 @@
T: git git://linuxtv.org/media_tree.git
S: Odd fixes
F: drivers/media/common/siano/
-F: drivers/media/dvb/siano/
F: drivers/media/usb/siano/
-F: drivers/media/mmc/siano
+F: drivers/media/usb/siano/
+F: drivers/media/mmc/siano/
SH_VEU V4L2 MEM2MEM DRIVER
M: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
@@ -7545,9 +7551,9 @@
M: Simtec Linux Team <linux@simtec.co.uk>
W: http://www.simtec.co.uk/products/EB2410ITX/
S: Supported
-F: arch/arm/mach-s3c2410/mach-bast.c
-F: arch/arm/mach-s3c2410/bast-ide.c
-F: arch/arm/mach-s3c2410/bast-irq.c
+F: arch/arm/mach-s3c24xx/mach-bast.c
+F: arch/arm/mach-s3c24xx/bast-ide.c
+F: arch/arm/mach-s3c24xx/bast-irq.c
TI DAVINCI MACHINE SUPPORT
M: Sekhar Nori <nsekhar@ti.com>
@@ -7556,7 +7562,7 @@
T: git git://gitorious.org/linux-davinci/linux-davinci.git
Q: http://patchwork.kernel.org/project/linux-davinci/list/
S: Supported
-F: arch/arm/mach-davinci
+F: arch/arm/mach-davinci/
F: drivers/i2c/busses/i2c-davinci.c
TI DAVINCI SERIES MEDIA DRIVER
@@ -7641,7 +7647,7 @@
M: Sakari Ailus <sakari.ailus@iki.fi>
L: linux-media@vger.kernel.org
S: Maintained
-F: drivers/media/i2c/smiapp
+F: drivers/media/i2c/smiapp/
F: include/media/smiapp.h
F: drivers/media/i2c/smiapp-pll.c
F: drivers/media/i2c/smiapp-pll.h
@@ -7744,6 +7750,11 @@
S: Maintained
F: drivers/memstick/host/tifm_ms.c
+SONY MEMORYSTICK STANDARD SUPPORT
+M: Maxim Levitsky <maximlevitsky@gmail.com>
+S: Maintained
+F: drivers/memstick/core/ms_block.*
+
SOUND
M: Jaroslav Kysela <perex@perex.cz>
M: Takashi Iwai <tiwai@suse.de>
@@ -7820,35 +7831,7 @@
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
W: http://www.st.com/spear
S: Maintained
-F: arch/arm/plat-spear/
-
-SPEAR13XX MACHINE SUPPORT
-M: Viresh Kumar <viresh.linux@gmail.com>
-M: Shiraz Hashim <shiraz.hashim@st.com>
-L: spear-devel@list.st.com
-L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-W: http://www.st.com/spear
-S: Maintained
-F: arch/arm/mach-spear13xx/
-
-SPEAR3XX MACHINE SUPPORT
-M: Viresh Kumar <viresh.linux@gmail.com>
-M: Shiraz Hashim <shiraz.hashim@st.com>
-L: spear-devel@list.st.com
-L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-W: http://www.st.com/spear
-S: Maintained
-F: arch/arm/mach-spear3xx/
-
-SPEAR6XX MACHINE SUPPORT
-M: Rajeev Kumar <rajeev-dlh.kumar@st.com>
-M: Shiraz Hashim <shiraz.hashim@st.com>
-M: Viresh Kumar <viresh.linux@gmail.com>
-L: spear-devel@list.st.com
-L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-W: http://www.st.com/spear
-S: Maintained
-F: arch/arm/mach-spear6xx/
+F: arch/arm/mach-spear/
SPEAR CLOCK FRAMEWORK SUPPORT
M: Viresh Kumar <viresh.linux@gmail.com>
@@ -8117,7 +8100,7 @@
S: Supported
F: arch/arc/
F: Documentation/devicetree/bindings/arc/
-F: drivers/tty/serial/arc-uart.c
+F: drivers/tty/serial/arc_uart.c
SYSV FILESYSTEM
M: Christoph Hellwig <hch@infradead.org>
@@ -8807,7 +8790,6 @@
T: git git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb.git
S: Maintained
F: drivers/usb/phy/
-F: drivers/usb/otg/
USB PRINTER DRIVER (usblp)
M: Pete Zaitcev <zaitcev@redhat.com>
@@ -9338,7 +9320,7 @@
L: platform-driver-x86@vger.kernel.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/mjg59/platform-drivers-x86.git
S: Maintained
-F: drivers/platform/x86
+F: drivers/platform/x86/
X86 MCE INFRASTRUCTURE
M: Tony Luck <tony.luck@intel.com>
diff --git a/Makefile b/Makefile
index a42f26a..e73f758 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
PATCHLEVEL = 11
SUBLEVEL = 0
EXTRAVERSION =
-NAME = Linux for Workgroups
+NAME = Suicidal Squirrel
# *DOCUMENTATION*
# To see a list of typical targets execute "make help"
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index 082d9b4..35a300d 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -7,7 +7,6 @@
select HAVE_PCSPKR_PLATFORM
select HAVE_PERF_EVENTS
select HAVE_DMA_ATTRS
- select HAVE_GENERIC_HARDIRQS
select VIRT_TO_BUS
select GENERIC_IRQ_PROBE
select AUTO_IRQ_AFFINITY if SMP
diff --git a/arch/alpha/lib/csum_partial_copy.c b/arch/alpha/lib/csum_partial_copy.c
index 40736da..ffb19b7 100644
--- a/arch/alpha/lib/csum_partial_copy.c
+++ b/arch/alpha/lib/csum_partial_copy.c
@@ -338,6 +338,11 @@
unsigned long doff = 7 & (unsigned long) dst;
if (len) {
+ if (!access_ok(VERIFY_READ, src, len)) {
+ *errp = -EFAULT;
+ memset(dst, 0, len);
+ return sum;
+ }
if (!doff) {
if (!soff)
checksum = csum_partial_cfu_aligned(
diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index 0c4132d..98838a0 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -89,8 +89,7 @@
const struct exception_table_entry *fixup;
int fault, si_code = SEGV_MAPERR;
siginfo_t info;
- unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (cause > 0 ? FAULT_FLAG_WRITE : 0));
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
/* As of EV6, a load into $31/$f31 is a prefetch, and never faults
(or is suppressed by the PALcode). Support that for older CPUs
@@ -115,7 +114,8 @@
if (address >= TASK_SIZE)
goto vmalloc_fault;
#endif
-
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
@@ -142,6 +142,7 @@
} else {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
}
/* If for any reason at all we couldn't handle the fault,
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 68fcbb2..91dbb27 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -20,7 +20,6 @@
select GENERIC_SMP_IDLE_THREAD
select HAVE_ARCH_KGDB
select HAVE_ARCH_TRACEHOOK
- select HAVE_GENERIC_HARDIRQS
select HAVE_IOREMAP_PROT
select HAVE_KPROBES
select HAVE_KRETPROBES
diff --git a/arch/arc/include/asm/sections.h b/arch/arc/include/asm/sections.h
index 6fc1159..764f1e3 100644
--- a/arch/arc/include/asm/sections.h
+++ b/arch/arc/include/asm/sections.h
@@ -11,7 +11,6 @@
#include <asm-generic/sections.h>
-extern char _int_vec_base_lds[];
extern char __arc_dccm_base[];
extern char __dtb_start[];
diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S
index 2a913f8..0f944f0 100644
--- a/arch/arc/kernel/head.S
+++ b/arch/arc/kernel/head.S
@@ -34,6 +34,9 @@
; IDENTITY Reg [ 3 2 1 0 ]
; (cpu-id) ^^^ => Zero for UP ARC700
; => #Core-ID if SMP (Master 0)
+ ; Note that non-boot CPUs might not land here if halt-on-reset and
+ ; instead breath life from @first_lines_of_secondary, but we still
+ ; need to make sure only boot cpu takes this path.
GET_CPU_ID r5
cmp r5, 0
jnz arc_platform_smp_wait_to_boot
@@ -98,6 +101,8 @@
first_lines_of_secondary:
+ sr @_int_vec_base_lds, [AUX_INTR_VEC_BASE]
+
; setup per-cpu idle task as "current" on this CPU
ld r0, [@secondary_idle_tsk]
SET_CURR_TASK_ON_CPU r0, r1
diff --git a/arch/arc/kernel/irq.c b/arch/arc/kernel/irq.c
index 305b3f8..5fc9245 100644
--- a/arch/arc/kernel/irq.c
+++ b/arch/arc/kernel/irq.c
@@ -24,7 +24,6 @@
* -Needed for each CPU (hence not foldable into init_IRQ)
*
* what it does ?
- * -setup Vector Table Base Reg - in case Linux not linked at 0x8000_0000
* -Disable all IRQs (on CPU side)
* -Optionally, setup the High priority Interrupts as Level 2 IRQs
*/
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index b011f8c..2c68bc7e 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -47,10 +47,7 @@
READ_BCR(AUX_IDENTITY, cpu->core);
cpu->timers = read_aux_reg(ARC_REG_TIMERS_BCR);
-
cpu->vec_base = read_aux_reg(AUX_INTR_VEC_BASE);
- if (cpu->vec_base == 0)
- cpu->vec_base = (unsigned int)_int_vec_base_lds;
READ_BCR(ARC_REG_D_UNCACH_BCR, uncached_space);
cpu->uncached_base = uncached_space.start << 24;
diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c
index 0fd1f0d..d63f3de 100644
--- a/arch/arc/mm/fault.c
+++ b/arch/arc/mm/fault.c
@@ -60,8 +60,7 @@
siginfo_t info;
int fault, ret;
int write = regs->ecr_cause & ECR_C_PROTV_STORE; /* ST/EX */
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (write ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
/*
* We fault-in kernel-space virtual memory on-demand. The
@@ -89,6 +88,8 @@
if (in_atomic() || !mm)
goto no_context;
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
@@ -117,12 +118,12 @@
if (write) {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
} else {
if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
goto bad_area;
}
-survive:
/*
* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
@@ -201,10 +202,6 @@
die("Oops", regs, address);
out_of_memory:
- if (is_global_init(tsk)) {
- yield();
- goto survive;
- }
up_read(&mm->mmap_sem);
if (user_mode(regs)) {
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index c8a916f..3f7714d 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -3,20 +3,21 @@
default y
select ARCH_BINFMT_ELF_RANDOMIZE_PIE
select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
- select ARCH_HAVE_CUSTOM_GPIO_H
select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
+ select ARCH_HAVE_CUSTOM_GPIO_H
select ARCH_WANT_IPC_PARSE_VERSION
select BUILDTIME_EXTABLE_SORT if MMU
+ select CLONE_BACKWARDS
select CPU_PM if (SUSPEND || CPU_IDLE)
select DCACHE_WORD_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && !CPU_BIG_ENDIAN && MMU
select GENERIC_ATOMIC64 if (CPU_V7M || CPU_V6 || !CPU_32v6K || !AEABI)
select GENERIC_CLOCKEVENTS_BROADCAST if SMP
+ select GENERIC_IDLE_POLL_SETUP
select GENERIC_IRQ_PROBE
select GENERIC_IRQ_SHOW
select GENERIC_PCI_IOMAP
select GENERIC_SCHED_CLOCK
select GENERIC_SMP_IDLE_THREAD
- select GENERIC_IDLE_POLL_SETUP
select GENERIC_STRNCPY_FROM_USER
select GENERIC_STRNLEN_USER
select HARDIRQS_SW_RESEND
@@ -25,6 +26,7 @@
select HAVE_ARCH_SECCOMP_FILTER
select HAVE_ARCH_TRACEHOOK
select HAVE_BPF_JIT
+ select HAVE_CONTEXT_TRACKING
select HAVE_C_RECORDMCOUNT
select HAVE_DEBUG_KMEMLEAK
select HAVE_DMA_API_DEBUG
@@ -35,7 +37,6 @@
select HAVE_FUNCTION_GRAPH_TRACER if (!THUMB2_KERNEL)
select HAVE_FUNCTION_TRACER if (!XIP_KERNEL)
select HAVE_GENERIC_DMA_COHERENT
- select HAVE_GENERIC_HARDIRQS
select HAVE_HW_BREAKPOINT if (PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7))
select HAVE_IDE if PCI || ISA || PCMCIA
select HAVE_IRQ_TIME_ACCOUNTING
@@ -47,6 +48,7 @@
select HAVE_KPROBES if !XIP_KERNEL
select HAVE_KRETPROBES if (HAVE_KPROBES)
select HAVE_MEMBLOCK
+ select HAVE_MOD_ARCH_SPECIFIC if ARM_UNWIND
select HAVE_OPROFILE if (HAVE_PERF_EVENTS)
select HAVE_PERF_EVENTS
select HAVE_REGS_AND_STACK_ACCESS_API
@@ -54,15 +56,14 @@
select HAVE_UID16
select IRQ_FORCED_THREADING
select KTIME_SCALAR
+ select MODULES_USE_ELF_REL
+ select OLD_SIGACTION
+ select OLD_SIGSUSPEND3
select PERF_USE_VMALLOC
select RTC_LIB
select SYS_SUPPORTS_APM_EMULATION
- select HAVE_MOD_ARCH_SPECIFIC if ARM_UNWIND
- select MODULES_USE_ELF_REL
- select CLONE_BACKWARDS
- select OLD_SIGSUSPEND3
- select OLD_SIGACTION
- select HAVE_CONTEXT_TRACKING
+ # Above selects are sorted alphabetically; please add new ones
+ # according to that. Thanks.
help
The ARM series is a line of low-power-consumption RISC chip designs
licensed by ARM Ltd and targeted at embedded applications and
@@ -386,8 +387,8 @@
bool "Cortina Systems Gemini"
select ARCH_REQUIRE_GPIOLIB
select ARCH_USES_GETTIMEOFFSET
- select NEED_MACH_GPIO_H
select CPU_FA526
+ select NEED_MACH_GPIO_H
help
Support for the Cortina Systems Gemini family SoCs
@@ -487,8 +488,8 @@
select GENERIC_CLOCKEVENTS
select MIGHT_HAVE_PCI
select NEED_MACH_IO_H
- select USB_EHCI_BIG_ENDIAN_MMIO
select USB_EHCI_BIG_ENDIAN_DESC
+ select USB_EHCI_BIG_ENDIAN_MMIO
help
Support for Intel's IXP4XX (XScale) family of processors.
@@ -498,11 +499,11 @@
select CPU_PJ4
select GENERIC_CLOCKEVENTS
select MIGHT_HAVE_PCI
+ select MVEBU_MBUS
select PINCTRL
select PINCTRL_DOVE
select PLAT_ORION_LEGACY
select USB_ARCH_HAS_EHCI
- select MVEBU_MBUS
help
Support for the Marvell Dove SoC 88AP510
@@ -512,12 +513,12 @@
select ARCH_REQUIRE_GPIOLIB
select CPU_FEROCEON
select GENERIC_CLOCKEVENTS
+ select MVEBU_MBUS
select PCI
select PCI_QUIRKS
select PINCTRL
select PINCTRL_KIRKWOOD
select PLAT_ORION_LEGACY
- select MVEBU_MBUS
help
Support for the following Marvell Kirkwood series SoCs:
88F6180, 88F6192 and 88F6281.
@@ -527,9 +528,9 @@
select ARCH_REQUIRE_GPIOLIB
select CPU_FEROCEON
select GENERIC_CLOCKEVENTS
+ select MVEBU_MBUS
select PCI
select PLAT_ORION_LEGACY
- select MVEBU_MBUS
help
Support for the following Marvell MV78xx0 series SoCs:
MV781x0, MV782x0.
@@ -540,9 +541,9 @@
select ARCH_REQUIRE_GPIOLIB
select CPU_FEROCEON
select GENERIC_CLOCKEVENTS
+ select MVEBU_MBUS
select PCI
select PLAT_ORION_LEGACY
- select MVEBU_MBUS
help
Support for the following Marvell Orion 5x series SoCs:
Orion-1 (5181), Orion-VoIP (5181L), Orion-NAS (5182),
@@ -758,8 +759,8 @@
select HAVE_S3C2410_WATCHDOG if WATCHDOG
select HAVE_S3C_RTC if RTC_CLASS
select NEED_MACH_GPIO_H
- select SAMSUNG_WDT_RESET
select SAMSUNG_ATAGS
+ select SAMSUNG_WDT_RESET
help
Samsung S5P64X0 CPU based systems, such as the Samsung SMDK6440,
SMDK6450.
@@ -777,8 +778,8 @@
select HAVE_S3C2410_WATCHDOG if WATCHDOG
select HAVE_S3C_RTC if RTC_CLASS
select NEED_MACH_GPIO_H
- select SAMSUNG_WDT_RESET
select SAMSUNG_ATAGS
+ select SAMSUNG_WDT_RESET
help
Samsung S5PC100 series based systems
@@ -1619,9 +1620,10 @@
ARCH_S5PV210 || ARCH_EXYNOS4
default AT91_TIMER_HZ if ARCH_AT91
default SHMOBILE_TIMER_HZ if ARCH_SHMOBILE
+ default 0
choice
- depends on !HZ_FIXED
+ depends on HZ_FIXED = 0
prompt "Timer frequency"
config HZ_100
@@ -1646,7 +1648,7 @@
config HZ
int
- default HZ_FIXED if HZ_FIXED
+ default HZ_FIXED if HZ_FIXED != 0
default 100 if HZ_100
default 200 if HZ_200
default 250 if HZ_250
diff --git a/arch/arm/boot/dts/sun7i-a20-cubieboard2.dts b/arch/arm/boot/dts/sun7i-a20-cubieboard2.dts
index 31b76f0..15e625e 100644
--- a/arch/arm/boot/dts/sun7i-a20-cubieboard2.dts
+++ b/arch/arm/boot/dts/sun7i-a20-cubieboard2.dts
@@ -19,6 +19,21 @@
compatible = "cubietech,cubieboard2", "allwinner,sun7i-a20";
soc@01c00000 {
+ emac: ethernet@01c0b000 {
+ pinctrl-names = "default";
+ pinctrl-0 = <&emac_pins_a>;
+ phy = <&phy1>;
+ status = "okay";
+ };
+
+ mdio@01c0b080 {
+ status = "okay";
+
+ phy1: ethernet-phy@1 {
+ reg = <1>;
+ };
+ };
+
pinctrl@01c20800 {
led_pins_cubieboard2: led_pins@0 {
allwinner,pins = "PH20", "PH21";
diff --git a/arch/arm/boot/dts/sun7i-a20-olinuxino-micro.dts b/arch/arm/boot/dts/sun7i-a20-olinuxino-micro.dts
index 34a6c02..9e77855 100644
--- a/arch/arm/boot/dts/sun7i-a20-olinuxino-micro.dts
+++ b/arch/arm/boot/dts/sun7i-a20-olinuxino-micro.dts
@@ -19,6 +19,21 @@
compatible = "olimex,a20-olinuxino-micro", "allwinner,sun7i-a20";
soc@01c00000 {
+ emac: ethernet@01c0b000 {
+ pinctrl-names = "default";
+ pinctrl-0 = <&emac_pins_a>;
+ phy = <&phy1>;
+ status = "okay";
+ };
+
+ mdio@01c0b080 {
+ status = "okay";
+
+ phy1: ethernet-phy@1 {
+ reg = <1>;
+ };
+ };
+
pinctrl@01c20800 {
led_pins_olinuxino: led_pins@0 {
allwinner,pins = "PH2";
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index 999ff45..80559cb 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -167,6 +167,22 @@
#size-cells = <1>;
ranges;
+ emac: ethernet@01c0b000 {
+ compatible = "allwinner,sun4i-emac";
+ reg = <0x01c0b000 0x1000>;
+ interrupts = <0 55 1>;
+ clocks = <&ahb_gates 17>;
+ status = "disabled";
+ };
+
+ mdio@01c0b080 {
+ compatible = "allwinner,sun4i-mdio";
+ reg = <0x01c0b080 0x14>;
+ status = "disabled";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ };
+
pio: pinctrl@01c20800 {
compatible = "allwinner,sun7i-a20-pinctrl";
reg = <0x01c20800 0x400>;
@@ -198,6 +214,17 @@
allwinner,drive = <0>;
allwinner,pull = <0>;
};
+
+ emac_pins_a: emac0@0 {
+ allwinner,pins = "PA0", "PA1", "PA2",
+ "PA3", "PA4", "PA5", "PA6",
+ "PA7", "PA8", "PA9", "PA10",
+ "PA11", "PA12", "PA13", "PA14",
+ "PA15", "PA16";
+ allwinner,function = "emac";
+ allwinner,drive = <0>;
+ allwinner,pull = <0>;
+ };
};
timer@01c20c00 {
diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index aaf3a87..bd454b0 100644
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile
@@ -49,5 +49,5 @@
ifeq ($(CONFIG_KERNEL_MODE_NEON),y)
NEON_FLAGS := -mfloat-abi=softfp -mfpu=neon
CFLAGS_xor-neon.o += $(NEON_FLAGS)
- lib-$(CONFIG_XOR_BLOCKS) += xor-neon.o
+ obj-$(CONFIG_XOR_BLOCKS) += xor-neon.o
endif
diff --git a/arch/arm/lib/xor-neon.c b/arch/arm/lib/xor-neon.c
index f485e5a..2c40aea 100644
--- a/arch/arm/lib/xor-neon.c
+++ b/arch/arm/lib/xor-neon.c
@@ -9,6 +9,9 @@
*/
#include <linux/raid/xor.h>
+#include <linux/module.h>
+
+MODULE_LICENSE("GPL");
#ifndef __ARM_NEON__
#error You should compile this file with '-mfloat-abi=softfp -mfpu=neon'
@@ -40,3 +43,4 @@
.do_4 = xor_8regs_4,
.do_5 = xor_8regs_5,
};
+EXPORT_SYMBOL(xor_block_neon_inner);
diff --git a/arch/arm/mach-ep93xx/core.c b/arch/arm/mach-ep93xx/core.c
index df8612f..3f12b88 100644
--- a/arch/arm/mach-ep93xx/core.c
+++ b/arch/arm/mach-ep93xx/core.c
@@ -281,7 +281,7 @@
{ IRQ_EP93XX_UART1 }, &ep93xx_uart_data);
static AMBA_APB_DEVICE(uart2, "apb:uart2", 0x00041010, EP93XX_UART2_PHYS_BASE,
- { IRQ_EP93XX_UART2 }, &ep93xx_uart_data);
+ { IRQ_EP93XX_UART2 }, NULL);
static AMBA_APB_DEVICE(uart3, "apb:uart3", 0x00041010, EP93XX_UART3_PHYS_BASE,
{ IRQ_EP93XX_UART3 }, &ep93xx_uart_data);
diff --git a/arch/arm/mach-shmobile/board-lager.c b/arch/arm/mach-shmobile/board-lager.c
index 4872939..ffb6f0a 100644
--- a/arch/arm/mach-shmobile/board-lager.c
+++ b/arch/arm/mach-shmobile/board-lager.c
@@ -96,7 +96,6 @@
static struct sh_eth_plat_data ether_pdata __initdata = {
.phy = 0x1,
.edmac_endian = EDMAC_LITTLE_ENDIAN,
- .register_type = SH_ETH_REG_FAST_RCAR,
.phy_interface = PHY_INTERFACE_MODE_RMII,
.ether_link_active_low = 1,
};
diff --git a/arch/arm/mach-shmobile/setup-r8a7779.c b/arch/arm/mach-shmobile/setup-r8a7779.c
index b5b2f78..ecd0148 100644
--- a/arch/arm/mach-shmobile/setup-r8a7779.c
+++ b/arch/arm/mach-shmobile/setup-r8a7779.c
@@ -691,8 +691,8 @@
void __init r8a7779_earlytimer_init(void)
{
r8a7779_clock_init();
- shmobile_earlytimer_init();
r8a7779_register_twd();
+ shmobile_earlytimer_init();
}
void __init r8a7779_add_early_devices(void)
diff --git a/arch/arm/mach-versatile/include/mach/platform.h b/arch/arm/mach-versatile/include/mach/platform.h
index ec08740..6f938cc 100644
--- a/arch/arm/mach-versatile/include/mach/platform.h
+++ b/arch/arm/mach-versatile/include/mach/platform.h
@@ -231,12 +231,14 @@
/* PCI space */
#define VERSATILE_PCI_BASE 0x41000000 /* PCI Interface */
#define VERSATILE_PCI_CFG_BASE 0x42000000
+#define VERSATILE_PCI_IO_BASE 0x43000000
#define VERSATILE_PCI_MEM_BASE0 0x44000000
#define VERSATILE_PCI_MEM_BASE1 0x50000000
#define VERSATILE_PCI_MEM_BASE2 0x60000000
/* Sizes of above maps */
#define VERSATILE_PCI_BASE_SIZE 0x01000000
#define VERSATILE_PCI_CFG_BASE_SIZE 0x02000000
+#define VERSATILE_PCI_IO_BASE_SIZE 0x01000000
#define VERSATILE_PCI_MEM_BASE0_SIZE 0x0c000000 /* 32Mb */
#define VERSATILE_PCI_MEM_BASE1_SIZE 0x10000000 /* 256Mb */
#define VERSATILE_PCI_MEM_BASE2_SIZE 0x10000000 /* 256Mb */
diff --git a/arch/arm/mach-versatile/pci.c b/arch/arm/mach-versatile/pci.c
index e92e5e0..c97be4e 100644
--- a/arch/arm/mach-versatile/pci.c
+++ b/arch/arm/mach-versatile/pci.c
@@ -43,9 +43,9 @@
#define PCI_IMAP0 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x0)
#define PCI_IMAP1 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x4)
#define PCI_IMAP2 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x8)
-#define PCI_SMAP0 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x10)
-#define PCI_SMAP1 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x14)
-#define PCI_SMAP2 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x18)
+#define PCI_SMAP0 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x14)
+#define PCI_SMAP1 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x18)
+#define PCI_SMAP2 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x1c)
#define PCI_SELFID __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0xc)
#define DEVICE_ID_OFFSET 0x00
@@ -170,8 +170,8 @@
.write = versatile_write_config,
};
-static struct resource io_mem = {
- .name = "PCI I/O space",
+static struct resource unused_mem = {
+ .name = "PCI unused",
.start = VERSATILE_PCI_MEM_BASE0,
.end = VERSATILE_PCI_MEM_BASE0+VERSATILE_PCI_MEM_BASE0_SIZE-1,
.flags = IORESOURCE_MEM,
@@ -195,9 +195,9 @@
{
int ret = 0;
- ret = request_resource(&iomem_resource, &io_mem);
+ ret = request_resource(&iomem_resource, &unused_mem);
if (ret) {
- printk(KERN_ERR "PCI: unable to allocate I/O "
+ printk(KERN_ERR "PCI: unable to allocate unused "
"memory region (%d)\n", ret);
goto out;
}
@@ -205,7 +205,7 @@
if (ret) {
printk(KERN_ERR "PCI: unable to allocate non-prefetchable "
"memory region (%d)\n", ret);
- goto release_io_mem;
+ goto release_unused_mem;
}
ret = request_resource(&iomem_resource, &pre_mem);
if (ret) {
@@ -225,8 +225,8 @@
release_non_mem:
release_resource(&non_mem);
- release_io_mem:
- release_resource(&io_mem);
+ release_unused_mem:
+ release_resource(&unused_mem);
out:
return ret;
}
@@ -246,7 +246,7 @@
goto out;
}
- ret = pci_ioremap_io(0, VERSATILE_PCI_MEM_BASE0);
+ ret = pci_ioremap_io(0, VERSATILE_PCI_IO_BASE);
if (ret)
goto out;
@@ -295,6 +295,19 @@
__raw_writel(PHYS_OFFSET, local_pci_cfg_base + PCI_BASE_ADDRESS_2);
/*
+ * For many years the kernel and QEMU were symbiotically buggy
+ * in that they both assumed the same broken IRQ mapping.
+ * QEMU therefore attempts to auto-detect old broken kernels
+ * so that they still work on newer QEMU as they did on old
+ * QEMU. Since we now use the correct (ie matching-hardware)
+ * IRQ mapping we write a definitely different value to a
+ * PCI_INTERRUPT_LINE register to tell QEMU that we expect
+ * real hardware behaviour and it need not be backwards
+ * compatible for us. This write is harmless on real hardware.
+ */
+ __raw_writel(0, VERSATILE_PCI_VIRT_BASE+PCI_INTERRUPT_LINE);
+
+ /*
* Do not to map Versatile FPGA PCI device into memory space
*/
pci_slot_ignore |= (1 << myslot);
@@ -327,13 +340,13 @@
{
int irq;
- /* slot, pin, irq
- * 24 1 IRQ_SIC_PCI0
- * 25 1 IRQ_SIC_PCI1
- * 26 1 IRQ_SIC_PCI2
- * 27 1 IRQ_SIC_PCI3
+ /*
+ * Slot INTA INTB INTC INTD
+ * 31 PCI1 PCI2 PCI3 PCI0
+ * 30 PCI0 PCI1 PCI2 PCI3
+ * 29 PCI3 PCI0 PCI1 PCI2
*/
- irq = IRQ_SIC_PCI0 + ((slot - 24 + pin - 1) & 3);
+ irq = IRQ_SIC_PCI0 + ((slot + 2 + pin - 1) & 3);
return irq;
}
diff --git a/arch/arm/mach-vexpress/Makefile b/arch/arm/mach-vexpress/Makefile
index 36ea824..505e64a 100644
--- a/arch/arm/mach-vexpress/Makefile
+++ b/arch/arm/mach-vexpress/Makefile
@@ -7,6 +7,8 @@
obj-y := v2m.o
obj-$(CONFIG_ARCH_VEXPRESS_CA9X4) += ct-ca9x4.o
obj-$(CONFIG_ARCH_VEXPRESS_DCSCB) += dcscb.o dcscb_setup.o
+CFLAGS_dcscb.o += -march=armv7-a
obj-$(CONFIG_ARCH_VEXPRESS_TC2_PM) += tc2_pm.o spc.o
+CFLAGS_tc2_pm.o += -march=armv7-a
obj-$(CONFIG_SMP) += platsmp.o
obj-$(CONFIG_HOTPLUG_CPU) += hotplug.o
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index c97f794..eb8830a 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -261,9 +261,7 @@
struct task_struct *tsk;
struct mm_struct *mm;
int fault, sig, code;
- int write = fsr & FSR_WRITE;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (write ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
if (notify_page_fault(regs, fsr))
return 0;
@@ -282,6 +280,11 @@
if (in_atomic() || !mm)
goto no_context;
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
+ if (fsr & FSR_WRITE)
+ flags |= FAULT_FLAG_WRITE;
+
/*
* As per x86, we may deadlock here. However, since the kernel only
* validly references user space from well defined areas of the code,
@@ -349,6 +352,13 @@
if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP | VM_FAULT_BADACCESS))))
return 0;
+ /*
+ * If we are in kernel mode at this point, we
+ * have no context to handle this fault with.
+ */
+ if (!user_mode(regs))
+ goto no_context;
+
if (fault & VM_FAULT_OOM) {
/*
* We ran out of memory, call the OOM killer, and return to
@@ -359,13 +369,6 @@
return 0;
}
- /*
- * If we are in kernel mode at this point, we
- * have no context to handle this fault with.
- */
- if (!user_mode(regs))
- goto no_context;
-
if (fault & VM_FAULT_SIGBUS) {
/*
* We had some memory, but were unable to
diff --git a/arch/arm/mm/hugetlbpage.c b/arch/arm/mm/hugetlbpage.c
index 66781bf3..54ee616 100644
--- a/arch/arm/mm/hugetlbpage.c
+++ b/arch/arm/mm/hugetlbpage.c
@@ -56,3 +56,8 @@
{
return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT);
}
+
+int pmd_huge_support(void)
+{
+ return 1;
+}
diff --git a/arch/arm/plat-pxa/ssp.c b/arch/arm/plat-pxa/ssp.c
index c83f27b..3ea0290 100644
--- a/arch/arm/plat-pxa/ssp.c
+++ b/arch/arm/plat-pxa/ssp.c
@@ -132,6 +132,7 @@
if (dev->of_node) {
struct of_phandle_args dma_spec;
struct device_node *np = dev->of_node;
+ int ret;
/*
* FIXME: we should allocate the DMA channel from this
@@ -140,14 +141,23 @@
*/
/* rx */
- of_parse_phandle_with_args(np, "dmas", "#dma-cells",
- 0, &dma_spec);
+ ret = of_parse_phandle_with_args(np, "dmas", "#dma-cells",
+ 0, &dma_spec);
+
+ if (ret) {
+ dev_err(dev, "Can't parse dmas property\n");
+ return -ENODEV;
+ }
ssp->drcmr_rx = dma_spec.args[0];
of_node_put(dma_spec.np);
/* tx */
- of_parse_phandle_with_args(np, "dmas", "#dma-cells",
- 1, &dma_spec);
+ ret = of_parse_phandle_with_args(np, "dmas", "#dma-cells",
+ 1, &dma_spec);
+ if (ret) {
+ dev_err(dev, "Can't parse dmas property\n");
+ return -ENODEV;
+ }
ssp->drcmr_tx = dma_spec.args[0];
of_node_put(dma_spec.np);
} else {
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index ae323a4..c044548 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -23,7 +23,6 @@
select HAVE_DMA_API_DEBUG
select HAVE_DMA_ATTRS
select HAVE_GENERIC_DMA_COHERENT
- select HAVE_GENERIC_HARDIRQS
select HAVE_HW_BREAKPOINT if PERF_EVENTS
select HAVE_MEMBLOCK
select HAVE_PERF_EVENTS
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 6c8ba25..6d6acf1 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -199,13 +199,6 @@
unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC;
unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
- if (esr & ESR_LNX_EXEC) {
- vm_flags = VM_EXEC;
- } else if ((esr & ESR_WRITE) && !(esr & ESR_CM)) {
- vm_flags = VM_WRITE;
- mm_flags |= FAULT_FLAG_WRITE;
- }
-
tsk = current;
mm = tsk->mm;
@@ -220,6 +213,16 @@
if (in_atomic() || !mm)
goto no_context;
+ if (user_mode(regs))
+ mm_flags |= FAULT_FLAG_USER;
+
+ if (esr & ESR_LNX_EXEC) {
+ vm_flags = VM_EXEC;
+ } else if ((esr & ESR_WRITE) && !(esr & ESR_CM)) {
+ vm_flags = VM_WRITE;
+ mm_flags |= FAULT_FLAG_WRITE;
+ }
+
/*
* As per x86, we may deadlock here. However, since the kernel only
* validly references user space from well defined areas of the code,
@@ -288,6 +291,13 @@
VM_FAULT_BADACCESS))))
return 0;
+ /*
+ * If we are in kernel mode at this point, we have no context to
+ * handle this fault with.
+ */
+ if (!user_mode(regs))
+ goto no_context;
+
if (fault & VM_FAULT_OOM) {
/*
* We ran out of memory, call the OOM killer, and return to
@@ -298,13 +308,6 @@
return 0;
}
- /*
- * If we are in kernel mode at this point, we have no context to
- * handle this fault with.
- */
- if (!user_mode(regs))
- goto no_context;
-
if (fault & VM_FAULT_SIGBUS) {
/*
* We had some memory, but were unable to successfully fix up
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 2fc8258..5e9aec3 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -54,6 +54,11 @@
return !(pud_val(pud) & PUD_TABLE_BIT);
}
+int pmd_huge_support(void)
+{
+ return 1;
+}
+
static __init int setup_hugepagesz(char *opt)
{
unsigned long ps = memparse(opt, &opt);
diff --git a/arch/avr32/Kconfig b/arch/avr32/Kconfig
index 549903c..b6878eb 100644
--- a/arch/avr32/Kconfig
+++ b/arch/avr32/Kconfig
@@ -6,7 +6,6 @@
select HAVE_CLK
select HAVE_OPROFILE
select HAVE_KPROBES
- select HAVE_GENERIC_HARDIRQS
select VIRT_TO_BUS
select GENERIC_IRQ_PROBE
select GENERIC_ATOMIC64
diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c
index b2f2d2d..0eca933 100644
--- a/arch/avr32/mm/fault.c
+++ b/arch/avr32/mm/fault.c
@@ -86,6 +86,8 @@
local_irq_enable();
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
@@ -228,9 +230,9 @@
*/
out_of_memory:
up_read(&mm->mmap_sem);
- pagefault_out_of_memory();
if (!user_mode(regs))
goto no_context;
+ pagefault_out_of_memory();
return;
do_sigbus:
diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig
index 3b6abc5..f78c9a2 100644
--- a/arch/blackfin/Kconfig
+++ b/arch/blackfin/Kconfig
@@ -32,7 +32,6 @@
select HAVE_UNDERSCORE_SYMBOL_PREFIX
select VIRT_TO_BUS
select ARCH_WANT_IPC_PARSE_VERSION
- select HAVE_GENERIC_HARDIRQS
select GENERIC_ATOMIC64
select GENERIC_IRQ_PROBE
select USE_GENERIC_SMP_HELPERS if SMP
diff --git a/arch/blackfin/boot/.gitignore b/arch/blackfin/boot/.gitignore
index 229e508..1287a54 100644
--- a/arch/blackfin/boot/.gitignore
+++ b/arch/blackfin/boot/.gitignore
@@ -1,2 +1,3 @@
vmImage*
vmlinux*
+uImage*
diff --git a/arch/blackfin/include/asm/scb.h b/arch/blackfin/include/asm/scb.h
new file mode 100644
index 0000000..a294cc0
--- /dev/null
+++ b/arch/blackfin/include/asm/scb.h
@@ -0,0 +1,21 @@
+/*
+ * arch/blackfin/mach-common/scb-init.c - reprogram system cross bar priority
+ *
+ * Copyright 2012 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#define SCB_SLOT_OFFSET 24
+#define SCB_MI_MAX_SLOT 32
+
+struct scb_mi_prio {
+ unsigned long scb_mi_arbr;
+ unsigned long scb_mi_arbw;
+ unsigned char scb_mi_slots;
+ unsigned char scb_mi_prio[SCB_MI_MAX_SLOT];
+};
+
+extern struct scb_mi_prio scb_data[];
+
+extern void init_scb(void);
diff --git a/arch/blackfin/kernel/setup.c b/arch/blackfin/kernel/setup.c
index 19ad063..3961930 100644
--- a/arch/blackfin/kernel/setup.c
+++ b/arch/blackfin/kernel/setup.c
@@ -35,6 +35,9 @@
#ifdef CONFIG_BF60x
#include <mach/pm.h>
#endif
+#ifdef CONFIG_SCB_PRIORITY
+#include <asm/scb.h>
+#endif
u16 _bfin_swrst;
EXPORT_SYMBOL(_bfin_swrst);
@@ -1101,6 +1104,9 @@
#endif
init_exception_vectors();
bfin_cache_init(); /* Initialize caches for the boot CPU */
+#ifdef CONFIG_SCB_PRIORITY
+ init_scb();
+#endif
}
static int __init topology_init(void)
diff --git a/arch/blackfin/mach-bf609/Kconfig b/arch/blackfin/mach-bf609/Kconfig
index 95a4f1b..2bcbf94 100644
--- a/arch/blackfin/mach-bf609/Kconfig
+++ b/arch/blackfin/mach-bf609/Kconfig
@@ -59,6 +59,1661 @@
Divide the total number of interrupt priority levels into sub-levels.
There is 2 ^ (SEC_IRQ_PRIORITY_LEVELS + 1) different levels.
+
+comment "System Cross Bar Priority Assignment"
+
+config SCB_PRIORITY
+ bool "Init System Cross Bar Priority"
+ default n
+
+menuconfig SCB0_MI0
+ bool "SCB0 Master Interface 0 (DDR)"
+ default n
+ depends on SCB_PRIORITY
+ help
+ The slave interface id of each slot should be set according following table.
+ Core 0 -- 0
+ Core 1 -- 2
+ SCB1 -- 9
+ SCB2 -- 10
+ SCB3 -- 11
+ SCB4 -- 12
+ SCB5 -- 5
+ SCB6 -- 6
+ SCB7 -- 8
+ SCB8 -- 7
+ SCB9 -- 4
+ USB -- 13
+
+if SCB0_MI0
+
+config SCB0_MI0_SLOT0
+ int "Slot 0 slave interface id"
+ default 0
+ range 0 13
+
+config SCB0_MI0_SLOT1
+ int "Slot 1 slave interface id"
+ default 2
+ range 0 13
+
+config SCB0_MI0_SLOT2
+ int "Slot 2 slave interface id"
+ default 4
+ range 0 13
+
+config SCB0_MI0_SLOT3
+ int "Slot 3 slave interface id"
+ default 5
+ range 0 13
+
+config SCB0_MI0_SLOT4
+ int "Slot 4 slave interface id"
+ default 6
+ range 0 13
+
+config SCB0_MI0_SLOT5
+ int "Slot 5 slave interface id"
+ default 7
+ range 0 13
+
+config SCB0_MI0_SLOT6
+ int "Slot 6 slave interface id"
+ default 8
+ range 0 13
+
+config SCB0_MI0_SLOT7
+ int "Slot 7 slave interface id"
+ default 9
+ range 0 13
+
+config SCB0_MI0_SLOT8
+ int "Slot 8 slave interface id"
+ default 10
+ range 0 13
+
+config SCB0_MI0_SLOT9
+ int "Slot 9 slave interface id"
+ default 11
+ range 0 13
+
+config SCB0_MI0_SLOT10
+ int "Slot 10 slave interface id"
+ default 13
+ range 0 13
+
+config SCB0_MI0_SLOT11
+ int "Slot 11 slave interface id"
+ default 12
+ range 0 13
+
+config SCB0_MI0_SLOT12
+ int "Slot 12 slave interface id"
+ default 0
+ range 0 13
+
+config SCB0_MI0_SLOT13
+ int "Slot 13 slave interface id"
+ default 2
+ range 0 13
+
+config SCB0_MI0_SLOT14
+ int "Slot 14 slave interface id"
+ default 4
+ range 0 13
+
+config SCB0_MI0_SLOT15
+ int "Slot 15 slave interface id"
+ default 5
+ range 0 13
+
+config SCB0_MI0_SLOT16
+ int "Slot 16 slave interface id"
+ default 6
+ range 0 13
+
+config SCB0_MI0_SLOT17
+ int "Slot 17 slave interface id"
+ default 7
+ range 0 13
+
+config SCB0_MI0_SLOT18
+ int "Slot 18 slave interface id"
+ default 8
+ range 0 13
+
+config SCB0_MI0_SLOT19
+ int "Slot 19 slave interface id"
+ default 9
+ range 0 13
+
+config SCB0_MI0_SLOT20
+ int "Slot 20 slave interface id"
+ default 10
+ range 0 13
+
+config SCB0_MI0_SLOT21
+ int "Slot 21 slave interface id"
+ default 11
+ range 0 13
+
+config SCB0_MI0_SLOT22
+ int "Slot 22 slave interface id"
+ default 13
+ range 0 13
+
+config SCB0_MI0_SLOT23
+ int "Slot 23 slave interface id"
+ default 12
+ range 0 13
+
+config SCB0_MI0_SLOT24
+ int "Slot 24 slave interface id"
+ default 0
+ range 0 13
+
+config SCB0_MI0_SLOT25
+ int "Slot 25 slave interface id"
+ default 2
+ range 0 13
+
+config SCB0_MI0_SLOT26
+ int "Slot 26 slave interface id"
+ default 4
+ range 0 13
+
+config SCB0_MI0_SLOT27
+ int "Slot 27 slave interface id"
+ default 5
+ range 0 13
+
+config SCB0_MI0_SLOT28
+ int "Slot 28 slave interface id"
+ default 6
+ range 0 13
+
+config SCB0_MI0_SLOT29
+ int "Slot 29 slave interface id"
+ default 7
+ range 0 13
+
+config SCB0_MI0_SLOT30
+ int "Slot 30 slave interface id"
+ default 8
+ range 0 13
+
+config SCB0_MI0_SLOT31
+ int "Slot 31 slave interface id"
+ default 13
+ range 0 13
+
+endif # SCB0_MI0
+
+menuconfig SCB0_MI1
+ bool "SCB0 Master Interface 1 (SMC)"
+ default n
+ depends on SCB_PRIORITY
+ help
+ The slave interface id of each slot should be set according following table.
+ Core 0 -- 0
+ Core 1 -- 2
+ SCB1 -- 9
+ SCB2 -- 10
+ SCB3 -- 11
+ SCB4 -- 12
+ SCB5 -- 5
+ SCB6 -- 6
+ SCB7 -- 8
+ SCB8 -- 7
+ SCB9 -- 4
+ USB -- 13
+
+if SCB0_MI1
+
+config SCB0_MI1_SLOT0
+ int "Slot 0 slave interface id"
+ default 0
+ range 0 13
+
+config SCB0_MI1_SLOT1
+ int "Slot 1 slave interface id"
+ default 2
+ range 0 13
+
+config SCB0_MI1_SLOT2
+ int "Slot 2 slave interface id"
+ default 4
+ range 0 13
+
+config SCB0_MI1_SLOT3
+ int "Slot 3 slave interface id"
+ default 5
+ range 0 13
+
+config SCB0_MI1_SLOT4
+ int "Slot 4 slave interface id"
+ default 6
+ range 0 13
+
+config SCB0_MI1_SLOT5
+ int "Slot 5 slave interface id"
+ default 7
+ range 0 13
+
+config SCB0_MI1_SLOT6
+ int "Slot 6 slave interface id"
+ default 8
+ range 0 13
+
+config SCB0_MI1_SLOT7
+ int "Slot 7 slave interface id"
+ default 9
+ range 0 13
+
+config SCB0_MI1_SLOT8
+ int "Slot 8 slave interface id"
+ default 10
+ range 0 13
+
+config SCB0_MI1_SLOT9
+ int "Slot 9 slave interface id"
+ default 11
+ range 0 13
+
+config SCB0_MI1_SLOT10
+ int "Slot 10 slave interface id"
+ default 13
+ range 0 13
+
+config SCB0_MI1_SLOT11
+ int "Slot 11 slave interface id"
+ default 12
+ range 0 13
+
+config SCB0_MI1_SLOT12
+ int "Slot 12 slave interface id"
+ default 0
+ range 0 13
+
+config SCB0_MI1_SLOT13
+ int "Slot 13 slave interface id"
+ default 2
+ range 0 13
+
+config SCB0_MI1_SLOT14
+ int "Slot 14 slave interface id"
+ default 4
+ range 0 13
+
+config SCB0_MI1_SLOT15
+ int "Slot 15 slave interface id"
+ default 5
+ range 0 13
+
+config SCB0_MI1_SLOT16
+ int "Slot 16 slave interface id"
+ default 6
+ range 0 13
+
+config SCB0_MI1_SLOT17
+ int "Slot 17 slave interface id"
+ default 7
+ range 0 13
+
+config SCB0_MI1_SLOT18
+ int "Slot 18 slave interface id"
+ default 8
+ range 0 13
+
+config SCB0_MI1_SLOT19
+ int "Slot 19 slave interface id"
+ default 9
+ range 0 13
+
+config SCB0_MI1_SLOT20
+ int "Slot 20 slave interface id"
+ default 10
+ range 0 13
+
+config SCB0_MI1_SLOT21
+ int "Slot 21 slave interface id"
+ default 11
+ range 0 13
+
+config SCB0_MI1_SLOT22
+ int "Slot 22 slave interface id"
+ default 13
+ range 0 13
+
+config SCB0_MI1_SLOT23
+ int "Slot 23 slave interface id"
+ default 12
+ range 0 13
+
+config SCB0_MI1_SLOT24
+ int "Slot 24 slave interface id"
+ default 0
+ range 0 13
+
+config SCB0_MI1_SLOT25
+ int "Slot 25 slave interface id"
+ default 2
+ range 0 13
+
+config SCB0_MI1_SLOT26
+ int "Slot 26 slave interface id"
+ default 4
+ range 0 13
+
+config SCB0_MI1_SLOT27
+ int "Slot 27 slave interface id"
+ default 5
+ range 0 13
+
+config SCB0_MI1_SLOT28
+ int "Slot 28 slave interface id"
+ default 6
+ range 0 13
+
+config SCB0_MI1_SLOT29
+ int "Slot 29 slave interface id"
+ default 7
+ range 0 13
+
+config SCB0_MI1_SLOT30
+ int "Slot 30 slave interface id"
+ default 8
+ range 0 13
+
+config SCB0_MI1_SLOT31
+ int "Slot 31 slave interface id"
+ default 13
+ range 0 13
+
+endif # SCB0_MI1
+
+menuconfig SCB0_MI2
+ bool "SCB0 Master Interface 2 (Data L2)"
+ default n
+ depends on SCB_PRIORITY
+ help
+ The slave interface id of each slot should be set according following table.
+ Core 0 -- 0
+ Core 1 -- 2
+ SCB1 -- 9
+ SCB2 -- 10
+ SCB3 -- 11
+ SCB4 -- 12
+ SCB5 -- 5
+ SCB6 -- 6
+ SCB7 -- 8
+ SCB8 -- 7
+ SCB9 -- 4
+ USB -- 13
+
+if SCB0_MI2
+
+config SCB0_MI2_SLOT0
+ int "Slot 0 slave interface id"
+ default 4
+ range 0 13
+
+config SCB0_MI2_SLOT1
+ int "Slot 1 slave interface id"
+ default 5
+ range 0 13
+
+config SCB0_MI2_SLOT2
+ int "Slot 2 slave interface id"
+ default 6
+ range 0 13
+
+config SCB0_MI2_SLOT3
+ int "Slot 3 slave interface id"
+ default 7
+ range 0 13
+
+config SCB0_MI2_SLOT4
+ int "Slot 4 slave interface id"
+ default 8
+ range 0 13
+
+config SCB0_MI2_SLOT5
+ int "Slot 5 slave interface id"
+ default 9
+ range 0 13
+
+config SCB0_MI2_SLOT6
+ int "Slot 6 slave interface id"
+ default 10
+ range 0 13
+
+config SCB0_MI2_SLOT7
+ int "Slot 7 slave interface id"
+ default 11
+ range 0 13
+
+config SCB0_MI2_SLOT8
+ int "Slot 8 slave interface id"
+ default 13
+ range 0 13
+
+config SCB0_MI2_SLOT9
+ int "Slot 9 slave interface id"
+ default 12
+ range 0 13
+
+config SCB0_MI2_SLOT10
+ int "Slot 10 slave interface id"
+ default 4
+ range 0 13
+
+config SCB0_MI2_SLOT11
+ int "Slot 11 slave interface id"
+ default 5
+ range 0 13
+
+config SCB0_MI2_SLOT12
+ int "Slot 12 slave interface id"
+ default 6
+ range 0 13
+
+config SCB0_MI2_SLOT13
+ int "Slot 13 slave interface id"
+ default 7
+ range 0 13
+
+config SCB0_MI2_SLOT14
+ int "Slot 14 slave interface id"
+ default 8
+ range 0 13
+
+config SCB0_MI2_SLOT15
+ int "Slot 15 slave interface id"
+ default 9
+ range 0 13
+
+config SCB0_MI2_SLOT16
+ int "Slot 16 slave interface id"
+ default 10
+ range 0 13
+
+config SCB0_MI2_SLOT17
+ int "Slot 17 slave interface id"
+ default 11
+ range 0 13
+
+config SCB0_MI2_SLOT18
+ int "Slot 18 slave interface id"
+ default 13
+ range 0 13
+
+config SCB0_MI2_SLOT19
+ int "Slot 19 slave interface id"
+ default 12
+ range 0 13
+
+config SCB0_MI2_SLOT20
+ int "Slot 20 slave interface id"
+ default 4
+ range 0 13
+
+config SCB0_MI2_SLOT21
+ int "Slot 21 slave interface id"
+ default 5
+ range 0 13
+
+config SCB0_MI2_SLOT22
+ int "Slot 22 slave interface id"
+ default 6
+ range 0 13
+
+config SCB0_MI2_SLOT23
+ int "Slot 23 slave interface id"
+ default 7
+ range 0 13
+
+config SCB0_MI2_SLOT24
+ int "Slot 24 slave interface id"
+ default 8
+ range 0 13
+
+config SCB0_MI2_SLOT25
+ int "Slot 25 slave interface id"
+ default 9
+ range 0 13
+
+config SCB0_MI2_SLOT26
+ int "Slot 26 slave interface id"
+ default 10
+ range 0 13
+
+config SCB0_MI2_SLOT27
+ int "Slot 27 slave interface id"
+ default 11
+ range 0 13
+
+config SCB0_MI2_SLOT28
+ int "Slot 28 slave interface id"
+ default 13
+ range 0 13
+
+config SCB0_MI2_SLOT29
+ int "Slot 29 slave interface id"
+ default 12
+ range 0 13
+
+config SCB0_MI2_SLOT30
+ int "Slot 30 slave interface id"
+ default 4
+ range 0 13
+
+config SCB0_MI2_SLOT31
+ int "Slot 31 slave interface id"
+ default 7
+ range 0 13
+
+endif # SCB0_MI2
+
+menuconfig SCB0_MI3
+ bool "SCB0 Master Interface 3 (L1A)"
+ default n
+ depends on SCB_PRIORITY
+ help
+ The slave interface id of each slot should be set according following table.
+ Core 0 -- 0
+ Core 1 -- 2
+ SCB1 -- 9
+ SCB2 -- 10
+ SCB3 -- 11
+ SCB4 -- 12
+ SCB5 -- 5
+ SCB6 -- 6
+ SCB7 -- 8
+ SCB8 -- 7
+ SCB9 -- 4
+ USB -- 13
+
+if SCB0_MI3
+
+config SCB0_MI3_SLOT0
+ int "Slot 0 slave interface id"
+ default 4
+ range 0 13
+
+config SCB0_MI3_SLOT1
+ int "Slot 1 slave interface id"
+ default 5
+ range 0 13
+
+config SCB0_MI3_SLOT2
+ int "Slot 2 slave interface id"
+ default 6
+ range 0 13
+
+config SCB0_MI3_SLOT3
+ int "Slot 3 slave interface id"
+ default 7
+ range 0 13
+
+config SCB0_MI3_SLOT4
+ int "Slot 4 slave interface id"
+ default 8
+ range 0 13
+
+config SCB0_MI3_SLOT5
+ int "Slot 5 slave interface id"
+ default 9
+ range 0 13
+
+config SCB0_MI3_SLOT6
+ int "Slot 6 slave interface id"
+ default 10
+ range 0 13
+
+config SCB0_MI3_SLOT7
+ int "Slot 7 slave interface id"
+ default 11
+ range 0 13
+
+config SCB0_MI3_SLOT8
+ int "Slot 8 slave interface id"
+ default 13
+ range 0 13
+
+config SCB0_MI3_SLOT9
+ int "Slot 9 slave interface id"
+ default 12
+ range 0 13
+
+config SCB0_MI3_SLOT10
+ int "Slot 10 slave interface id"
+ default 4
+ range 0 13
+
+config SCB0_MI3_SLOT11
+ int "Slot 11 slave interface id"
+ default 5
+ range 0 13
+
+config SCB0_MI3_SLOT12
+ int "Slot 12 slave interface id"
+ default 6
+ range 0 13
+
+config SCB0_MI3_SLOT13
+ int "Slot 13 slave interface id"
+ default 7
+ range 0 13
+
+config SCB0_MI3_SLOT14
+ int "Slot 14 slave interface id"
+ default 8
+ range 0 13
+
+config SCB0_MI3_SLOT15
+ int "Slot 15 slave interface id"
+ default 9
+ range 0 13
+
+config SCB0_MI3_SLOT16
+ int "Slot 16 slave interface id"
+ default 10
+ range 0 13
+
+config SCB0_MI3_SLOT17
+ int "Slot 17 slave interface id"
+ default 11
+ range 0 13
+
+config SCB0_MI3_SLOT18
+ int "Slot 18 slave interface id"
+ default 13
+ range 0 13
+
+config SCB0_MI3_SLOT19
+ int "Slot 19 slave interface id"
+ default 12
+ range 0 13
+
+config SCB0_MI3_SLOT20
+ int "Slot 20 slave interface id"
+ default 4
+ range 0 13
+
+config SCB0_MI3_SLOT21
+ int "Slot 21 slave interface id"
+ default 5
+ range 0 13
+
+config SCB0_MI3_SLOT22
+ int "Slot 22 slave interface id"
+ default 6
+ range 0 13
+
+config SCB0_MI3_SLOT23
+ int "Slot 23 slave interface id"
+ default 7
+ range 0 13
+
+config SCB0_MI3_SLOT24
+ int "Slot 24 slave interface id"
+ default 8
+ range 0 13
+
+config SCB0_MI3_SLOT25
+ int "Slot 25 slave interface id"
+ default 9
+ range 0 13
+
+config SCB0_MI3_SLOT26
+ int "Slot 26 slave interface id"
+ default 10
+ range 0 13
+
+config SCB0_MI3_SLOT27
+ int "Slot 27 slave interface id"
+ default 11
+ range 0 13
+
+config SCB0_MI3_SLOT28
+ int "Slot 28 slave interface id"
+ default 13
+ range 0 13
+
+config SCB0_MI3_SLOT29
+ int "Slot 29 slave interface id"
+ default 12
+ range 0 13
+
+config SCB0_MI3_SLOT30
+ int "Slot 30 slave interface id"
+ default 4
+ range 0 13
+
+config SCB0_MI3_SLOT31
+ int "Slot 31 slave interface id"
+ default 7
+ range 0 13
+
+endif # SCB0_MI3
+
+menuconfig SCB0_MI4
+ bool "SCB0 Master Interface 4 (L1B)"
+ default n
+ depends on SCB_PRIORITY
+ help
+ The slave interface id of each slot should be set according following table.
+ Core 0 -- 0
+ Core 1 -- 2
+ SCB1 -- 9
+ SCB2 -- 10
+ SCB3 -- 11
+ SCB4 -- 12
+ SCB5 -- 5
+ SCB6 -- 6
+ SCB7 -- 8
+ SCB8 -- 7
+ SCB9 -- 4
+ USB -- 13
+
+if SCB0_MI4
+
+config SCB0_MI4_SLOT0
+ int "Slot 0 slave interface id"
+ default 4
+ range 0 13
+
+config SCB0_MI4_SLOT1
+ int "Slot 1 slave interface id"
+ default 5
+ range 0 13
+
+config SCB0_MI4_SLOT2
+ int "Slot 2 slave interface id"
+ default 6
+ range 0 13
+
+config SCB0_MI4_SLOT3
+ int "Slot 3 slave interface id"
+ default 7
+ range 0 13
+
+config SCB0_MI4_SLOT4
+ int "Slot 4 slave interface id"
+ default 8
+ range 0 13
+
+config SCB0_MI4_SLOT5
+ int "Slot 5 slave interface id"
+ default 9
+ range 0 13
+
+config SCB0_MI4_SLOT6
+ int "Slot 6 slave interface id"
+ default 10
+ range 0 13
+
+config SCB0_MI4_SLOT7
+ int "Slot 7 slave interface id"
+ default 11
+ range 0 13
+
+config SCB0_MI4_SLOT8
+ int "Slot 8 slave interface id"
+ default 13
+ range 0 13
+
+config SCB0_MI4_SLOT9
+ int "Slot 9 slave interface id"
+ default 12
+ range 0 13
+
+config SCB0_MI4_SLOT10
+ int "Slot 10 slave interface id"
+ default 4
+ range 0 13
+
+config SCB0_MI4_SLOT11
+ int "Slot 11 slave interface id"
+ default 5
+ range 0 13
+
+config SCB0_MI4_SLOT12
+ int "Slot 12 slave interface id"
+ default 6
+ range 0 13
+
+config SCB0_MI4_SLOT13
+ int "Slot 13 slave interface id"
+ default 7
+ range 0 13
+
+config SCB0_MI4_SLOT14
+ int "Slot 14 slave interface id"
+ default 8
+ range 0 13
+
+config SCB0_MI4_SLOT15
+ int "Slot 15 slave interface id"
+ default 9
+ range 0 13
+
+config SCB0_MI4_SLOT16
+ int "Slot 16 slave interface id"
+ default 10
+ range 0 13
+
+config SCB0_MI4_SLOT17
+ int "Slot 17 slave interface id"
+ default 11
+ range 0 13
+
+config SCB0_MI4_SLOT18
+ int "Slot 18 slave interface id"
+ default 13
+ range 0 13
+
+config SCB0_MI4_SLOT19
+ int "Slot 19 slave interface id"
+ default 12
+ range 0 13
+
+config SCB0_MI4_SLOT20
+ int "Slot 20 slave interface id"
+ default 4
+ range 0 13
+
+config SCB0_MI4_SLOT21
+ int "Slot 21 slave interface id"
+ default 5
+ range 0 13
+
+config SCB0_MI4_SLOT22
+ int "Slot 22 slave interface id"
+ default 6
+ range 0 13
+
+config SCB0_MI4_SLOT23
+ int "Slot 23 slave interface id"
+ default 7
+ range 0 13
+
+config SCB0_MI4_SLOT24
+ int "Slot 24 slave interface id"
+ default 8
+ range 0 13
+
+config SCB0_MI4_SLOT25
+ int "Slot 25 slave interface id"
+ default 9
+ range 0 13
+
+config SCB0_MI4_SLOT26
+ int "Slot 26 slave interface id"
+ default 10
+ range 0 13
+
+config SCB0_MI4_SLOT27
+ int "Slot 27 slave interface id"
+ default 11
+ range 0 13
+
+config SCB0_MI4_SLOT28
+ int "Slot 28 slave interface id"
+ default 13
+ range 0 13
+
+config SCB0_MI4_SLOT29
+ int "Slot 29 slave interface id"
+ default 12
+ range 0 13
+
+config SCB0_MI4_SLOT30
+ int "Slot 30 slave interface id"
+ default 4
+ range 0 13
+
+config SCB0_MI4_SLOT31
+ int "Slot 31 slave interface id"
+ default 7
+ range 0 13
+
+endif # SCB0_MI4
+
+menuconfig SCB0_MI5
+ bool "SCB0 Master Interface 5 (SMMR)"
+ default n
+ depends on SCB_PRIORITY
+ help
+ The slave interface id of each slot should be set according following table.
+ MMR0 -- 1
+ MMR1 -- 3
+ SCB2 -- 10
+ SCB4 -- 12
+
+if SCB0_MI5
+
+config SCB0_MI5_SLOT0
+ int "Slot 0 slave interface id"
+ default 1
+ range 0 13
+
+config SCB0_MI5_SLOT1
+ int "Slot 1 slave interface id"
+ default 3
+ range 0 13
+
+config SCB0_MI5_SLOT2
+ int "Slot 2 slave interface id"
+ default 10
+ range 0 13
+
+config SCB0_MI5_SLOT3
+ int "Slot 3 slave interface id"
+ default 12
+ range 0 13
+
+config SCB0_MI5_SLOT4
+ int "Slot 4 slave interface id"
+ default 1
+ range 0 13
+
+config SCB0_MI5_SLOT5
+ int "Slot 5 slave interface id"
+ default 3
+ range 0 13
+
+config SCB0_MI5_SLOT6
+ int "Slot 6 slave interface id"
+ default 10
+ range 0 13
+
+config SCB0_MI5_SLOT7
+ int "Slot 7 slave interface id"
+ default 12
+ range 0 13
+
+config SCB0_MI5_SLOT8
+ int "Slot 8 slave interface id"
+ default 1
+ range 0 13
+
+config SCB0_MI5_SLOT9
+ int "Slot 9 slave interface id"
+ default 3
+ range 0 13
+
+config SCB0_MI5_SLOT10
+ int "Slot 10 slave interface id"
+ default 10
+ range 0 13
+
+config SCB0_MI5_SLOT11
+ int "Slot 11 slave interface id"
+ default 12
+ range 0 13
+
+config SCB0_MI5_SLOT12
+ int "Slot 12 slave interface id"
+ default 1
+ range 0 13
+
+config SCB0_MI5_SLOT13
+ int "Slot 13 slave interface id"
+ default 3
+ range 0 13
+
+config SCB0_MI5_SLOT14
+ int "Slot 14 slave interface id"
+ default 10
+ range 0 13
+
+config SCB0_MI5_SLOT15
+ int "Slot 15 slave interface id"
+ default 12
+ range 0 13
+
+endif # SCB0_MI5
+
+menuconfig SCB1_MI0
+ bool "SCB1 Master Interface 0"
+ default n
+ depends on SCB_PRIORITY
+ help
+ The slave interface id of each slot should be set according following table.
+ SPORT0A -- 0
+ SPORT0B -- 1
+ SPORT1A -- 2
+ SPORT1B -- 3
+ SPORT2A -- 4
+ SPORT2B -- 5
+ SPI0TX -- 6
+ SPI0RX -- 7
+ SPI1TX -- 8
+ SPI1RX -- 9
+
+if SCB1_MI0
+
+config SCB1_MI0_SLOT0
+ int "Slot 0 slave interface id"
+ default 0
+ range 0 9
+
+config SCB1_MI0_SLOT1
+ int "Slot 1 slave interface id"
+ default 1
+ range 0 9
+
+config SCB1_MI0_SLOT2
+ int "Slot 2 slave interface id"
+ default 2
+ range 0 9
+
+config SCB1_MI0_SLOT3
+ int "Slot 3 slave interface id"
+ default 3
+ range 0 9
+
+config SCB1_MI0_SLOT4
+ int "Slot 4 slave interface id"
+ default 4
+ range 0 9
+
+config SCB1_MI0_SLOT5
+ int "Slot 5 slave interface id"
+ default 5
+ range 0 9
+
+config SCB1_MI0_SLOT6
+ int "Slot 6 slave interface id"
+ default 6
+ range 0 9
+
+config SCB1_MI0_SLOT7
+ int "Slot 7 slave interface id"
+ default 7
+ range 0 9
+
+config SCB1_MI0_SLOT8
+ int "Slot 8 slave interface id"
+ default 8
+ range 0 9
+
+config SCB1_MI0_SLOT9
+ int "Slot 9 slave interface id"
+ default 9
+ range 0 9
+
+config SCB1_MI0_SLOT10
+ int "Slot 10 slave interface id"
+ default 0
+ range 0 9
+
+config SCB1_MI0_SLOT11
+ int "Slot 11 slave interface id"
+ default 1
+ range 0 9
+
+config SCB1_MI0_SLOT12
+ int "Slot 12 slave interface id"
+ default 2
+ range 0 9
+
+config SCB1_MI0_SLOT13
+ int "Slot 13 slave interface id"
+ default 3
+ range 0 9
+
+config SCB1_MI0_SLOT14
+ int "Slot 14 slave interface id"
+ default 4
+ range 0 9
+
+config SCB1_MI0_SLOT15
+ int "Slot 15 slave interface id"
+ default 5
+ range 0 9
+
+config SCB1_MI0_SLOT16
+ int "Slot 16 slave interface id"
+ default 6
+ range 0 13
+
+config SCB1_MI0_SLOT17
+ int "Slot 17 slave interface id"
+ default 7
+ range 0 13
+
+config SCB1_MI0_SLOT18
+ int "Slot 18 slave interface id"
+ default 8
+ range 0 13
+
+config SCB1_MI0_SLOT19
+ int "Slot 19 slave interface id"
+ default 9
+ range 0 13
+
+endif # SCB1_MI0
+
+menuconfig SCB2_MI0
+ bool "SCB2 Master Interface 0"
+ default n
+ depends on SCB_PRIORITY
+ help
+ The slave interface id of each slot should be set according following table.
+ RSI -- 0
+ SDU DMA -- 1
+ SDU -- 2
+ EMAC0 -- 3
+ EMAC1 -- 4
+
+if SCB2_MI0
+
+config SCB2_MI0_SLOT0
+ int "Slot 0 slave interface id"
+ default 0
+ range 0 4
+
+config SCB2_MI0_SLOT1
+ int "Slot 1 slave interface id"
+ default 1
+ range 0 4
+
+config SCB2_MI0_SLOT2
+ int "Slot 2 slave interface id"
+ default 2
+ range 0 4
+
+config SCB2_MI0_SLOT3
+ int "Slot 3 slave interface id"
+ default 3
+ range 0 4
+
+config SCB2_MI0_SLOT4
+ int "Slot 4 slave interface id"
+ default 4
+ range 0 4
+
+config SCB2_MI0_SLOT5
+ int "Slot 5 slave interface id"
+ default 0
+ range 0 4
+
+config SCB2_MI0_SLOT6
+ int "Slot 6 slave interface id"
+ default 1
+ range 0 4
+
+config SCB2_MI0_SLOT7
+ int "Slot 7 slave interface id"
+ default 2
+ range 0 4
+
+config SCB2_MI0_SLOT8
+ int "Slot 8 slave interface id"
+ default 3
+ range 0 4
+
+config SCB2_MI0_SLOT9
+ int "Slot 9 slave interface id"
+ default 4
+ range 0 4
+
+endif # SCB2_MI0
+
+menuconfig SCB3_MI0
+ bool "SCB3 Master Interface 0"
+ default n
+ depends on SCB_PRIORITY
+ help
+ The slave interface id of each slot should be set according following table.
+ LP0 -- 0
+ LP1 -- 1
+ LP2 -- 2
+ LP3 -- 3
+ UART0TX -- 4
+ UART0RX -- 5
+ UART1TX -- 4
+ UART1RX -- 5
+
+if SCB3_MI0
+
+config SCB3_MI0_SLOT0
+ int "Slot 0 slave interface id"
+ default 0
+ range 0 7
+
+config SCB3_MI0_SLOT1
+ int "Slot 1 slave interface id"
+ default 1
+ range 0 7
+
+config SCB3_MI0_SLOT2
+ int "Slot 2 slave interface id"
+ default 2
+ range 0 7
+
+config SCB3_MI0_SLOT3
+ int "Slot 3 slave interface id"
+ default 3
+ range 0 7
+
+config SCB3_MI0_SLOT4
+ int "Slot 4 slave interface id"
+ default 4
+ range 0 7
+
+config SCB3_MI0_SLOT5
+ int "Slot 5 slave interface id"
+ default 5
+ range 0 7
+
+config SCB3_MI0_SLOT6
+ int "Slot 6 slave interface id"
+ default 6
+ range 0 7
+
+config SCB3_MI0_SLOT7
+ int "Slot 7 slave interface id"
+ default 7
+ range 0 7
+
+config SCB3_MI0_SLOT8
+ int "Slot 8 slave interface id"
+ default 0
+ range 0 7
+
+config SCB3_MI0_SLOT9
+ int "Slot 9 slave interface id"
+ default 1
+ range 0 7
+
+config SCB3_MI0_SLOT10
+ int "Slot 10 slave interface id"
+ default 2
+ range 0 7
+
+config SCB3_MI0_SLOT11
+ int "Slot 11 slave interface id"
+ default 3
+ range 0 7
+
+config SCB3_MI0_SLOT12
+ int "Slot 12 slave interface id"
+ default 4
+ range 0 7
+
+config SCB3_MI0_SLOT13
+ int "Slot 13 slave interface id"
+ default 5
+ range 0 7
+
+config SCB3_MI0_SLOT14
+ int "Slot 14 slave interface id"
+ default 6
+ range 0 7
+
+config SCB3_MI0_SLOT15
+ int "Slot 15 slave interface id"
+ default 7
+ range 0 7
+
+endif # SCB3_MI0
+
+menuconfig SCB4_MI0
+ bool "SCB4 Master Interface 0"
+ default n
+ depends on SCB_PRIORITY
+ help
+ The slave interface id of each slot should be set according following table.
+ MDA21 -- 0
+ MDA22 -- 1
+ MDA23 -- 2
+ MDA24 -- 3
+ MDA25 -- 4
+ MDA26 -- 5
+ MDA27 -- 6
+ MDA28 -- 7
+
+if SCB4_MI0
+
+config SCB4_MI0_SLOT0
+ int "Slot 0 slave interface id"
+ default 0
+ range 0 7
+
+config SCB4_MI0_SLOT1
+ int "Slot 1 slave interface id"
+ default 1
+ range 0 7
+
+config SCB4_MI0_SLOT2
+ int "Slot 2 slave interface id"
+ default 2
+ range 0 7
+
+config SCB4_MI0_SLOT3
+ int "Slot 3 slave interface id"
+ default 3
+ range 0 7
+
+config SCB4_MI0_SLOT4
+ int "Slot 4 slave interface id"
+ default 4
+ range 0 7
+
+config SCB4_MI0_SLOT5
+ int "Slot 5 slave interface id"
+ default 5
+ range 0 7
+
+config SCB4_MI0_SLOT6
+ int "Slot 6 slave interface id"
+ default 6
+ range 0 7
+
+config SCB4_MI0_SLOT7
+ int "Slot 7 slave interface id"
+ default 7
+ range 0 7
+
+config SCB4_MI0_SLOT8
+ int "Slot 8 slave interface id"
+ default 0
+ range 0 7
+
+config SCB4_MI0_SLOT9
+ int "Slot 9 slave interface id"
+ default 1
+ range 0 7
+
+config SCB4_MI0_SLOT10
+ int "Slot 10 slave interface id"
+ default 2
+ range 0 7
+
+config SCB4_MI0_SLOT11
+ int "Slot 11 slave interface id"
+ default 3
+ range 0 7
+
+config SCB4_MI0_SLOT12
+ int "Slot 12 slave interface id"
+ default 4
+ range 0 7
+
+config SCB4_MI0_SLOT13
+ int "Slot 13 slave interface id"
+ default 5
+ range 0 7
+
+config SCB4_MI0_SLOT14
+ int "Slot 14 slave interface id"
+ default 6
+ range 0 7
+
+config SCB4_MI0_SLOT15
+ int "Slot 15 slave interface id"
+ default 7
+ range 0 7
+
+endif # SCB4_MI0
+
+menuconfig SCB5_MI0
+ bool "SCB5 Master Interface 0"
+ default n
+ depends on SCB_PRIORITY
+ help
+ The slave interface id of each slot should be set according following table.
+ PPI0 MDA29 -- 0
+ PPI0 MDA30 -- 1
+ PPI2 MDA31 -- 2
+ PPI2 MDA32 -- 3
+
+if SCB5_MI0
+
+config SCB5_MI0_SLOT0
+ int "Slot 0 slave interface id"
+ default 0
+ range 0 3
+
+config SCB5_MI0_SLOT1
+ int "Slot 1 slave interface id"
+ default 1
+ range 0 3
+
+config SCB5_MI0_SLOT2
+ int "Slot 2 slave interface id"
+ default 2
+ range 0 3
+
+config SCB5_MI0_SLOT3
+ int "Slot 3 slave interface id"
+ default 3
+ range 0 3
+
+config SCB5_MI0_SLOT4
+ int "Slot 4 slave interface id"
+ default 0
+ range 0 3
+
+config SCB5_MI0_SLOT5
+ int "Slot 5 slave interface id"
+ default 1
+ range 0 3
+
+config SCB5_MI0_SLOT6
+ int "Slot 6 slave interface id"
+ default 2
+ range 0 3
+
+config SCB5_MI0_SLOT7
+ int "Slot 7 slave interface id"
+ default 3
+ range 0 3
+
+endif # SCB5_MI0
+
+menuconfig SCB6_MI0
+ bool "SCB6 Master Interface 0"
+ default n
+ depends on SCB_PRIORITY
+ help
+ The slave interface id of each slot should be set according following table.
+ PPI1 MDA33 -- 0
+ PPI1 MDA34 -- 1
+
+if SCB6_MI0
+
+config SCB6_MI0_SLOT0
+ int "Slot 0 slave interface id"
+ default 0
+ range 0 1
+
+config SCB6_MI0_SLOT1
+ int "Slot 1 slave interface id"
+ default 1
+ range 0 1
+
+config SCB6_MI0_SLOT2
+ int "Slot 2 slave interface id"
+ default 0
+ range 0 1
+
+config SCB6_MI0_SLOT3
+ int "Slot 3 slave interface id"
+ default 1
+ range 0 1
+
+endif # SCB6_MI0
+
+menuconfig SCB7_MI0
+ bool "SCB7 Master Interface 0"
+ default n
+ depends on SCB_PRIORITY
+ help
+ The slave interface id of each slot should be set according following table.
+ PIXC0 -- 0
+ PIXC1 -- 1
+ PIXC2 -- 2
+
+if SCB7_MI0
+
+config SCB7_MI0_SLOT0
+ int "Slot 0 slave interface id"
+ default 0
+ range 0 2
+
+config SCB7_MI0_SLOT1
+ int "Slot 1 slave interface id"
+ default 1
+ range 0 2
+
+config SCB7_MI0_SLOT2
+ int "Slot 2 slave interface id"
+ default 2
+ range 0 2
+
+config SCB7_MI0_SLOT3
+ int "Slot 3 slave interface id"
+ default 0
+ range 0 2
+
+config SCB7_MI0_SLOT4
+ int "Slot 4 slave interface id"
+ default 1
+ range 0 2
+
+config SCB7_MI0_SLOT5
+ int "Slot 5 slave interface id"
+ default 2
+ range 0 2
+
+endif # SCB7_MI0
+
+menuconfig SCB8_MI0
+ bool "SCB8 Master Interface 0"
+ default n
+ depends on SCB_PRIORITY
+ help
+ The slave interface id of each slot should be set according following table.
+ PVP CPDOB -- 0
+ PVP CPDOC -- 1
+ PVP CPCO -- 2
+ PVP CPCI -- 3
+
+if SCB8_MI0
+
+config SCB8_MI0_SLOT0
+ int "Slot 0 slave interface id"
+ default 0
+ range 0 3
+
+config SCB8_MI0_SLOT1
+ int "Slot 1 slave interface id"
+ default 1
+ range 0 3
+
+config SCB8_MI0_SLOT2
+ int "Slot 2 slave interface id"
+ default 2
+ range 0 3
+
+config SCB8_MI0_SLOT3
+ int "Slot 3 slave interface id"
+ default 3
+ range 0 3
+
+config SCB8_MI0_SLOT4
+ int "Slot 4 slave interface id"
+ default 0
+ range 0 3
+
+config SCB8_MI0_SLOT5
+ int "Slot 5 slave interface id"
+ default 1
+ range 0 3
+
+config SCB8_MI0_SLOT6
+ int "Slot 6 slave interface id"
+ default 2
+ range 0 3
+
+config SCB8_MI0_SLOT7
+ int "Slot 7 slave interface id"
+ default 3
+ range 0 3
+
+endif # SCB8_MI0
+
+menuconfig SCB9_MI0
+ bool "SCB9 Master Interface 0"
+ default n
+ depends on SCB_PRIORITY
+ help
+ The slave interface id of each slot should be set according following table.
+ PVP MPDO -- 0
+ PVP MPDI -- 1
+ PVP MPCO -- 2
+ PVP MPCI -- 3
+ PVP CPDOA -- 4
+
+if SCB9_MI0
+
+config SCB9_MI0_SLOT0
+ int "Slot 0 slave interface id"
+ default 0
+ range 0 4
+
+config SCB9_MI0_SLOT1
+ int "Slot 1 slave interface id"
+ default 1
+ range 0 4
+
+config SCB9_MI0_SLOT2
+ int "Slot 2 slave interface id"
+ default 2
+ range 0 4
+
+config SCB9_MI0_SLOT3
+ int "Slot 3 slave interface id"
+ default 3
+ range 0 4
+
+config SCB9_MI0_SLOT4
+ int "Slot 4 slave interface id"
+ default 4
+ range 0 4
+
+config SCB9_MI0_SLOT5
+ int "Slot 5 slave interface id"
+ default 0
+ range 0 4
+
+config SCB9_MI0_SLOT6
+ int "Slot 6 slave interface id"
+ default 1
+ range 0 4
+
+config SCB9_MI0_SLOT7
+ int "Slot 7 slave interface id"
+ default 2
+ range 0 4
+
+config SCB9_MI0_SLOT8
+ int "Slot 8 slave interface id"
+ default 3
+ range 0 4
+
+config SCB9_MI0_SLOT9
+ int "Slot 9 slave interface id"
+ default 4
+ range 0 4
+
+endif # SCB9_MI0
+
endmenu
endif
diff --git a/arch/blackfin/mach-bf609/Makefile b/arch/blackfin/mach-bf609/Makefile
index 234fe1b..60ffaf8 100644
--- a/arch/blackfin/mach-bf609/Makefile
+++ b/arch/blackfin/mach-bf609/Makefile
@@ -4,3 +4,4 @@
obj-y := dma.o clock.o ints-priority.o
obj-$(CONFIG_PM) += pm.o dpm.o
+obj-$(CONFIG_SCB_PRIORITY) += scb.o
diff --git a/arch/blackfin/mach-bf609/boards/ezkit.c b/arch/blackfin/mach-bf609/boards/ezkit.c
index 0bc4723..d56a55a 100644
--- a/arch/blackfin/mach-bf609/boards/ezkit.c
+++ b/arch/blackfin/mach-bf609/boards/ezkit.c
@@ -104,6 +104,7 @@
#if defined(CONFIG_STMMAC_ETH) || defined(CONFIG_STMMAC_ETH_MODULE)
#include <linux/stmmac.h>
+#include <linux/phy.h>
static unsigned short pins[] = P_RMII0;
@@ -111,11 +112,26 @@
.phy_mask = 1,
};
+static struct stmmac_dma_cfg eth_dma_cfg = {
+ .pbl = 2,
+};
+
+int stmmac_ptp_clk_init(struct platform_device *pdev)
+{
+ bfin_write32(PADS0_EMAC_PTP_CLKSEL, 0);
+ return 0;
+}
+
static struct plat_stmmacenet_data eth_private_data = {
+ .has_gmac = 1,
.bus_id = 0,
.enh_desc = 1,
.phy_addr = 1,
.mdio_bus_data = &phy_private_data,
+ .dma_cfg = ð_dma_cfg,
+ .force_thresh_dma_mode = 1,
+ .interface = PHY_INTERFACE_MODE_RMII,
+ .init = stmmac_ptp_clk_init,
};
static struct platform_device bfin_eth_device = {
@@ -1107,6 +1123,81 @@
};
#endif
+#if IS_ENABLED(CONFIG_VIDEO_ADV7343)
+#include <media/adv7343.h>
+
+static struct v4l2_output adv7343_outputs[] = {
+ {
+ .index = 0,
+ .name = "Composite",
+ .type = V4L2_OUTPUT_TYPE_ANALOG,
+ .std = V4L2_STD_ALL,
+ .capabilities = V4L2_OUT_CAP_STD,
+ },
+ {
+ .index = 1,
+ .name = "S-Video",
+ .type = V4L2_OUTPUT_TYPE_ANALOG,
+ .std = V4L2_STD_ALL,
+ .capabilities = V4L2_OUT_CAP_STD,
+ },
+ {
+ .index = 2,
+ .name = "Component",
+ .type = V4L2_OUTPUT_TYPE_ANALOG,
+ .std = V4L2_STD_ALL,
+ .capabilities = V4L2_OUT_CAP_STD,
+ },
+
+};
+
+static struct disp_route adv7343_routes[] = {
+ {
+ .output = ADV7343_COMPOSITE_ID,
+ },
+ {
+ .output = ADV7343_SVIDEO_ID,
+ },
+ {
+ .output = ADV7343_COMPONENT_ID,
+ },
+};
+
+static struct adv7343_platform_data adv7343_data = {
+ .mode_config = {
+ .sleep_mode = false,
+ .pll_control = false,
+ .dac_1 = true,
+ .dac_2 = true,
+ .dac_3 = true,
+ .dac_4 = true,
+ .dac_5 = true,
+ .dac_6 = true,
+ },
+ .sd_config = {
+ .sd_dac_out1 = false,
+ .sd_dac_out2 = false,
+ },
+};
+
+static struct bfin_display_config bfin_display_data = {
+ .card_name = "BF609",
+ .outputs = adv7343_outputs,
+ .num_outputs = ARRAY_SIZE(adv7343_outputs),
+ .routes = adv7343_routes,
+ .i2c_adapter_id = 0,
+ .board_info = {
+ .type = "adv7343",
+ .addr = 0x2b,
+ .platform_data = (void *)&adv7343_data,
+ },
+ .ppi_info = &ppi_info_disp,
+ .ppi_control = (PACK_EN | DLEN_8 | EPPI_CTL_FS1LO_FS2LO
+ | EPPI_CTL_POLC3 | EPPI_CTL_BLANKGEN | EPPI_CTL_SYNC2
+ | EPPI_CTL_NON656 | EPPI_CTL_DIR),
+};
+#endif
+
static struct platform_device bfin_display_device = {
.name = "bfin_display",
.dev = {
diff --git a/arch/blackfin/mach-bf609/clock.c b/arch/blackfin/mach-bf609/clock.c
index 437d56c..dab8849 100644
--- a/arch/blackfin/mach-bf609/clock.c
+++ b/arch/blackfin/mach-bf609/clock.c
@@ -220,6 +220,12 @@
}
}
+unsigned long dummy_get_rate(struct clk *clk)
+{
+ clk->parent->rate = clk_get_rate(clk->parent);
+ return clk->parent->rate;
+}
+
unsigned long sys_clk_round_rate(struct clk *clk, unsigned long rate)
{
unsigned long max_rate;
@@ -283,6 +289,10 @@
.round_rate = sys_clk_round_rate,
};
+static struct clk_ops dummy_clk_ops = {
+ .get_rate = dummy_get_rate,
+};
+
static struct clk sys_clkin = {
.name = "SYS_CLKIN",
.rate = CONFIG_CLKIN_HZ,
@@ -364,6 +374,12 @@
.parent = &pll_clk,
};
+static struct clk ethclk = {
+ .name = "stmmaceth",
+ .parent = &sclk0,
+ .ops = &dummy_clk_ops,
+};
+
static struct clk_lookup bf609_clks[] = {
CLK(sys_clkin, NULL, "SYS_CLKIN"),
CLK(pll_clk, NULL, "PLLCLK"),
@@ -375,6 +391,7 @@
CLK(sclk1, NULL, "SCLK1"),
CLK(dclk, NULL, "DCLK"),
CLK(oclk, NULL, "OCLK"),
+ CLK(ethclk, NULL, "stmmaceth"),
};
int __init clk_init(void)
diff --git a/arch/blackfin/mach-bf609/include/mach/defBF60x_base.h b/arch/blackfin/mach-bf609/include/mach/defBF60x_base.h
index f1a6afa..35caa7b 100644
--- a/arch/blackfin/mach-bf609/include/mach/defBF60x_base.h
+++ b/arch/blackfin/mach-bf609/include/mach/defBF60x_base.h
@@ -839,6 +839,16 @@
#define PORTG_LOCK 0xFFC03344 /* PORTG Port x GPIO Lock Register */
#define PORTG_REVID 0xFFC0337C /* PORTG Port x GPIO Revision ID */
+/* ==================================================
+ Pads Controller Registers
+ ================================================== */
+
+/* =========================
+ PADS0
+ ========================= */
+#define PADS0_EMAC_PTP_CLKSEL 0xFFC03404 /* PADS0 Clock Selection for EMAC and PTP */
+#define PADS0_TWI_VSEL 0xFFC03408 /* PADS0 TWI Voltage Selection */
+#define PADS0_PORTS_HYST 0xFFC03440 /* PADS0 Hysteresis Enable Register */
/* =========================
PINT Registers
diff --git a/arch/blackfin/mach-bf609/scb.c b/arch/blackfin/mach-bf609/scb.c
new file mode 100644
index 0000000..ac1f07c
--- /dev/null
+++ b/arch/blackfin/mach-bf609/scb.c
@@ -0,0 +1,363 @@
+/*
+ * arch/blackfin/mach-common/scb-init.c - reprogram system cross bar priority
+ *
+ * Copyright 2012 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#include <asm/blackfin.h>
+#include <asm/scb.h>
+
+struct scb_mi_prio scb_data[] = {
+#ifdef CONFIG_SCB0_MI0
+ { REG_SCB0_ARBR0, REG_SCB0_ARBW0, 32, {
+ CONFIG_SCB0_MI0_SLOT0,
+ CONFIG_SCB0_MI0_SLOT1,
+ CONFIG_SCB0_MI0_SLOT2,
+ CONFIG_SCB0_MI0_SLOT3,
+ CONFIG_SCB0_MI0_SLOT4,
+ CONFIG_SCB0_MI0_SLOT5,
+ CONFIG_SCB0_MI0_SLOT6,
+ CONFIG_SCB0_MI0_SLOT7,
+ CONFIG_SCB0_MI0_SLOT8,
+ CONFIG_SCB0_MI0_SLOT9,
+ CONFIG_SCB0_MI0_SLOT10,
+ CONFIG_SCB0_MI0_SLOT11,
+ CONFIG_SCB0_MI0_SLOT12,
+ CONFIG_SCB0_MI0_SLOT13,
+ CONFIG_SCB0_MI0_SLOT14,
+ CONFIG_SCB0_MI0_SLOT15,
+ CONFIG_SCB0_MI0_SLOT16,
+ CONFIG_SCB0_MI0_SLOT17,
+ CONFIG_SCB0_MI0_SLOT18,
+ CONFIG_SCB0_MI0_SLOT19,
+ CONFIG_SCB0_MI0_SLOT20,
+ CONFIG_SCB0_MI0_SLOT21,
+ CONFIG_SCB0_MI0_SLOT22,
+ CONFIG_SCB0_MI0_SLOT23,
+ CONFIG_SCB0_MI0_SLOT24,
+ CONFIG_SCB0_MI0_SLOT25,
+ CONFIG_SCB0_MI0_SLOT26,
+ CONFIG_SCB0_MI0_SLOT27,
+ CONFIG_SCB0_MI0_SLOT28,
+ CONFIG_SCB0_MI0_SLOT29,
+ CONFIG_SCB0_MI0_SLOT30,
+ CONFIG_SCB0_MI0_SLOT31
+ },
+ },
+#endif
+#ifdef CONFIG_SCB0_MI1
+ { REG_SCB0_ARBR1, REG_SCB0_ARBW1, 32, {
+ CONFIG_SCB0_MI1_SLOT0,
+ CONFIG_SCB0_MI1_SLOT1,
+ CONFIG_SCB0_MI1_SLOT2,
+ CONFIG_SCB0_MI1_SLOT3,
+ CONFIG_SCB0_MI1_SLOT4,
+ CONFIG_SCB0_MI1_SLOT5,
+ CONFIG_SCB0_MI1_SLOT6,
+ CONFIG_SCB0_MI1_SLOT7,
+ CONFIG_SCB0_MI1_SLOT8,
+ CONFIG_SCB0_MI1_SLOT9,
+ CONFIG_SCB0_MI1_SLOT10,
+ CONFIG_SCB0_MI1_SLOT11,
+ CONFIG_SCB0_MI1_SLOT12,
+ CONFIG_SCB0_MI1_SLOT13,
+ CONFIG_SCB0_MI1_SLOT14,
+ CONFIG_SCB0_MI1_SLOT15,
+ CONFIG_SCB0_MI1_SLOT16,
+ CONFIG_SCB0_MI1_SLOT17,
+ CONFIG_SCB0_MI1_SLOT18,
+ CONFIG_SCB0_MI1_SLOT19,
+ CONFIG_SCB0_MI1_SLOT20,
+ CONFIG_SCB0_MI1_SLOT21,
+ CONFIG_SCB0_MI1_SLOT22,
+ CONFIG_SCB0_MI1_SLOT23,
+ CONFIG_SCB0_MI1_SLOT24,
+ CONFIG_SCB0_MI1_SLOT25,
+ CONFIG_SCB0_MI1_SLOT26,
+ CONFIG_SCB0_MI1_SLOT27,
+ CONFIG_SCB0_MI1_SLOT28,
+ CONFIG_SCB0_MI1_SLOT29,
+ CONFIG_SCB0_MI1_SLOT30,
+ CONFIG_SCB0_MI1_SLOT31
+ },
+ },
+#endif
+#ifdef CONFIG_SCB0_MI2
+ { REG_SCB0_ARBR2, REG_SCB0_ARBW2, 32, {
+ CONFIG_SCB0_MI2_SLOT0,
+ CONFIG_SCB0_MI2_SLOT1,
+ CONFIG_SCB0_MI2_SLOT2,
+ CONFIG_SCB0_MI2_SLOT3,
+ CONFIG_SCB0_MI2_SLOT4,
+ CONFIG_SCB0_MI2_SLOT5,
+ CONFIG_SCB0_MI2_SLOT6,
+ CONFIG_SCB0_MI2_SLOT7,
+ CONFIG_SCB0_MI2_SLOT8,
+ CONFIG_SCB0_MI2_SLOT9,
+ CONFIG_SCB0_MI2_SLOT10,
+ CONFIG_SCB0_MI2_SLOT11,
+ CONFIG_SCB0_MI2_SLOT12,
+ CONFIG_SCB0_MI2_SLOT13,
+ CONFIG_SCB0_MI2_SLOT14,
+ CONFIG_SCB0_MI2_SLOT15,
+ CONFIG_SCB0_MI2_SLOT16,
+ CONFIG_SCB0_MI2_SLOT17,
+ CONFIG_SCB0_MI2_SLOT18,
+ CONFIG_SCB0_MI2_SLOT19,
+ CONFIG_SCB0_MI2_SLOT20,
+ CONFIG_SCB0_MI2_SLOT21,
+ CONFIG_SCB0_MI2_SLOT22,
+ CONFIG_SCB0_MI2_SLOT23,
+ CONFIG_SCB0_MI2_SLOT24,
+ CONFIG_SCB0_MI2_SLOT25,
+ CONFIG_SCB0_MI2_SLOT26,
+ CONFIG_SCB0_MI2_SLOT27,
+ CONFIG_SCB0_MI2_SLOT28,
+ CONFIG_SCB0_MI2_SLOT29,
+ CONFIG_SCB0_MI2_SLOT30,
+ CONFIG_SCB0_MI2_SLOT31
+ },
+ },
+#endif
+#ifdef CONFIG_SCB0_MI3
+ { REG_SCB0_ARBR3, REG_SCB0_ARBW3, 32, {
+ CONFIG_SCB0_MI3_SLOT0,
+ CONFIG_SCB0_MI3_SLOT1,
+ CONFIG_SCB0_MI3_SLOT2,
+ CONFIG_SCB0_MI3_SLOT3,
+ CONFIG_SCB0_MI3_SLOT4,
+ CONFIG_SCB0_MI3_SLOT5,
+ CONFIG_SCB0_MI3_SLOT6,
+ CONFIG_SCB0_MI3_SLOT7,
+ CONFIG_SCB0_MI3_SLOT8,
+ CONFIG_SCB0_MI3_SLOT9,
+ CONFIG_SCB0_MI3_SLOT10,
+ CONFIG_SCB0_MI3_SLOT11,
+ CONFIG_SCB0_MI3_SLOT12,
+ CONFIG_SCB0_MI3_SLOT13,
+ CONFIG_SCB0_MI3_SLOT14,
+ CONFIG_SCB0_MI3_SLOT15,
+ CONFIG_SCB0_MI3_SLOT16,
+ CONFIG_SCB0_MI3_SLOT17,
+ CONFIG_SCB0_MI3_SLOT18,
+ CONFIG_SCB0_MI3_SLOT19,
+ CONFIG_SCB0_MI3_SLOT20,
+ CONFIG_SCB0_MI3_SLOT21,
+ CONFIG_SCB0_MI3_SLOT22,
+ CONFIG_SCB0_MI3_SLOT23,
+ CONFIG_SCB0_MI3_SLOT24,
+ CONFIG_SCB0_MI3_SLOT25,
+ CONFIG_SCB0_MI3_SLOT26,
+ CONFIG_SCB0_MI3_SLOT27,
+ CONFIG_SCB0_MI3_SLOT28,
+ CONFIG_SCB0_MI3_SLOT29,
+ CONFIG_SCB0_MI3_SLOT30,
+ CONFIG_SCB0_MI3_SLOT31
+ },
+ },
+#endif
+#ifdef CONFIG_SCB0_MI4
+ { REG_SCB0_ARBR4, REG_SCB4_ARBW0, 32, {
+ CONFIG_SCB0_MI4_SLOT0,
+ CONFIG_SCB0_MI4_SLOT1,
+ CONFIG_SCB0_MI4_SLOT2,
+ CONFIG_SCB0_MI4_SLOT3,
+ CONFIG_SCB0_MI4_SLOT4,
+ CONFIG_SCB0_MI4_SLOT5,
+ CONFIG_SCB0_MI4_SLOT6,
+ CONFIG_SCB0_MI4_SLOT7,
+ CONFIG_SCB0_MI4_SLOT8,
+ CONFIG_SCB0_MI4_SLOT9,
+ CONFIG_SCB0_MI4_SLOT10,
+ CONFIG_SCB0_MI4_SLOT11,
+ CONFIG_SCB0_MI4_SLOT12,
+ CONFIG_SCB0_MI4_SLOT13,
+ CONFIG_SCB0_MI4_SLOT14,
+ CONFIG_SCB0_MI4_SLOT15,
+ CONFIG_SCB0_MI4_SLOT16,
+ CONFIG_SCB0_MI4_SLOT17,
+ CONFIG_SCB0_MI4_SLOT18,
+ CONFIG_SCB0_MI4_SLOT19,
+ CONFIG_SCB0_MI4_SLOT20,
+ CONFIG_SCB0_MI4_SLOT21,
+ CONFIG_SCB0_MI4_SLOT22,
+ CONFIG_SCB0_MI4_SLOT23,
+ CONFIG_SCB0_MI4_SLOT24,
+ CONFIG_SCB0_MI4_SLOT25,
+ CONFIG_SCB0_MI4_SLOT26,
+ CONFIG_SCB0_MI4_SLOT27,
+ CONFIG_SCB0_MI4_SLOT28,
+ CONFIG_SCB0_MI4_SLOT29,
+ CONFIG_SCB0_MI4_SLOT30,
+ CONFIG_SCB0_MI4_SLOT31
+ },
+ },
+#endif
+#ifdef CONFIG_SCB0_MI5
+ { REG_SCB0_ARBR5, REG_SCB0_ARBW5, 16, {
+ CONFIG_SCB0_MI5_SLOT0,
+ CONFIG_SCB0_MI5_SLOT1,
+ CONFIG_SCB0_MI5_SLOT2,
+ CONFIG_SCB0_MI5_SLOT3,
+ CONFIG_SCB0_MI5_SLOT4,
+ CONFIG_SCB0_MI5_SLOT5,
+ CONFIG_SCB0_MI5_SLOT6,
+ CONFIG_SCB0_MI5_SLOT7,
+ CONFIG_SCB0_MI5_SLOT8,
+ CONFIG_SCB0_MI5_SLOT9,
+ CONFIG_SCB0_MI5_SLOT10,
+ CONFIG_SCB0_MI5_SLOT11,
+ CONFIG_SCB0_MI5_SLOT12,
+ CONFIG_SCB0_MI5_SLOT13,
+ CONFIG_SCB0_MI5_SLOT14,
+ CONFIG_SCB0_MI5_SLOT15
+ },
+ },
+#endif
+#ifdef CONFIG_SCB1_MI0
+ { REG_SCB1_ARBR0, REG_SCB1_ARBW0, 20, {
+ CONFIG_SCB1_MI0_SLOT0,
+ CONFIG_SCB1_MI0_SLOT1,
+ CONFIG_SCB1_MI0_SLOT2,
+ CONFIG_SCB1_MI0_SLOT3,
+ CONFIG_SCB1_MI0_SLOT4,
+ CONFIG_SCB1_MI0_SLOT5,
+ CONFIG_SCB1_MI0_SLOT6,
+ CONFIG_SCB1_MI0_SLOT7,
+ CONFIG_SCB1_MI0_SLOT8,
+ CONFIG_SCB1_MI0_SLOT9,
+ CONFIG_SCB1_MI0_SLOT10,
+ CONFIG_SCB1_MI0_SLOT11,
+ CONFIG_SCB1_MI0_SLOT12,
+ CONFIG_SCB1_MI0_SLOT13,
+ CONFIG_SCB1_MI0_SLOT14,
+ CONFIG_SCB1_MI0_SLOT15,
+ CONFIG_SCB1_MI0_SLOT16,
+ CONFIG_SCB1_MI0_SLOT17,
+ CONFIG_SCB1_MI0_SLOT18,
+ CONFIG_SCB1_MI0_SLOT19
+ },
+ },
+#endif
+#ifdef CONFIG_SCB2_MI0
+ { REG_SCB2_ARBR0, REG_SCB2_ARBW0, 10, {
+ CONFIG_SCB2_MI0_SLOT0,
+ CONFIG_SCB2_MI0_SLOT1,
+ CONFIG_SCB2_MI0_SLOT2,
+ CONFIG_SCB2_MI0_SLOT3,
+ CONFIG_SCB2_MI0_SLOT4,
+ CONFIG_SCB2_MI0_SLOT5,
+ CONFIG_SCB2_MI0_SLOT6,
+ CONFIG_SCB2_MI0_SLOT7,
+ CONFIG_SCB2_MI0_SLOT8,
+ CONFIG_SCB2_MI0_SLOT9
+ },
+ },
+#endif
+#ifdef CONFIG_SCB3_MI0
+ { REG_SCB3_ARBR0, REG_SCB3_ARBW0, 16, {
+ CONFIG_SCB3_MI0_SLOT0,
+ CONFIG_SCB3_MI0_SLOT1,
+ CONFIG_SCB3_MI0_SLOT2,
+ CONFIG_SCB3_MI0_SLOT3,
+ CONFIG_SCB3_MI0_SLOT4,
+ CONFIG_SCB3_MI0_SLOT5,
+ CONFIG_SCB3_MI0_SLOT6,
+ CONFIG_SCB3_MI0_SLOT7,
+ CONFIG_SCB3_MI0_SLOT8,
+ CONFIG_SCB3_MI0_SLOT9,
+ CONFIG_SCB3_MI0_SLOT10,
+ CONFIG_SCB3_MI0_SLOT11,
+ CONFIG_SCB3_MI0_SLOT12,
+ CONFIG_SCB3_MI0_SLOT13,
+ CONFIG_SCB3_MI0_SLOT14,
+ CONFIG_SCB3_MI0_SLOT15
+ },
+ },
+#endif
+#ifdef CONFIG_SCB4_MI0
+ { REG_SCB4_ARBR0, REG_SCB4_ARBW0, 16, {
+ CONFIG_SCB4_MI0_SLOT0,
+ CONFIG_SCB4_MI0_SLOT1,
+ CONFIG_SCB4_MI0_SLOT2,
+ CONFIG_SCB4_MI0_SLOT3,
+ CONFIG_SCB4_MI0_SLOT4,
+ CONFIG_SCB4_MI0_SLOT5,
+ CONFIG_SCB4_MI0_SLOT6,
+ CONFIG_SCB4_MI0_SLOT7,
+ CONFIG_SCB4_MI0_SLOT8,
+ CONFIG_SCB4_MI0_SLOT9,
+ CONFIG_SCB4_MI0_SLOT10,
+ CONFIG_SCB4_MI0_SLOT11,
+ CONFIG_SCB4_MI0_SLOT12,
+ CONFIG_SCB4_MI0_SLOT13,
+ CONFIG_SCB4_MI0_SLOT14,
+ CONFIG_SCB4_MI0_SLOT15
+ },
+ },
+#endif
+#ifdef CONFIG_SCB5_MI0
+ { REG_SCB5_ARBR0, REG_SCB5_ARBW0, 8, {
+ CONFIG_SCB5_MI0_SLOT0,
+ CONFIG_SCB5_MI0_SLOT1,
+ CONFIG_SCB5_MI0_SLOT2,
+ CONFIG_SCB5_MI0_SLOT3,
+ CONFIG_SCB5_MI0_SLOT4,
+ CONFIG_SCB5_MI0_SLOT5,
+ CONFIG_SCB5_MI0_SLOT6,
+ CONFIG_SCB5_MI0_SLOT7
+ },
+ },
+#endif
+#ifdef CONFIG_SCB6_MI0
+ { REG_SCB6_ARBR0, REG_SCB6_ARBW0, 4, {
+ CONFIG_SCB6_MI0_SLOT0,
+ CONFIG_SCB6_MI0_SLOT1,
+ CONFIG_SCB6_MI0_SLOT2,
+ CONFIG_SCB6_MI0_SLOT3
+ },
+ },
+#endif
+#ifdef CONFIG_SCB7_MI0
+ { REG_SCB7_ARBR0, REG_SCB7_ARBW0, 6, {
+ CONFIG_SCB7_MI0_SLOT0,
+ CONFIG_SCB7_MI0_SLOT1,
+ CONFIG_SCB7_MI0_SLOT2,
+ CONFIG_SCB7_MI0_SLOT3,
+ CONFIG_SCB7_MI0_SLOT4,
+ CONFIG_SCB7_MI0_SLOT5
+ },
+ },
+#endif
+#ifdef CONFIG_SCB8_MI0
+ { REG_SCB8_ARBR0, REG_SCB8_ARBW0, 8, {
+ CONFIG_SCB8_MI0_SLOT0,
+ CONFIG_SCB8_MI0_SLOT1,
+ CONFIG_SCB8_MI0_SLOT2,
+ CONFIG_SCB8_MI0_SLOT3,
+ CONFIG_SCB8_MI0_SLOT4,
+ CONFIG_SCB8_MI0_SLOT5,
+ CONFIG_SCB8_MI0_SLOT6,
+ CONFIG_SCB8_MI0_SLOT7
+ },
+ },
+#endif
+#ifdef CONFIG_SCB9_MI0
+ { REG_SCB9_ARBR0, REG_SCB9_ARBW0, 10, {
+ CONFIG_SCB9_MI0_SLOT0,
+ CONFIG_SCB9_MI0_SLOT1,
+ CONFIG_SCB9_MI0_SLOT2,
+ CONFIG_SCB9_MI0_SLOT3,
+ CONFIG_SCB9_MI0_SLOT4,
+ CONFIG_SCB9_MI0_SLOT5,
+ CONFIG_SCB9_MI0_SLOT6,
+ CONFIG_SCB9_MI0_SLOT7,
+ CONFIG_SCB9_MI0_SLOT8,
+ CONFIG_SCB9_MI0_SLOT9
+ },
+ },
+#endif
+ { 0, }
+};
diff --git a/arch/blackfin/mach-common/Makefile b/arch/blackfin/mach-common/Makefile
index 675466d..f099792 100644
--- a/arch/blackfin/mach-common/Makefile
+++ b/arch/blackfin/mach-common/Makefile
@@ -10,6 +10,7 @@
ifneq ($(CONFIG_BF60x),y)
obj-$(CONFIG_PM) += dpmc_modes.o
endif
+obj-$(CONFIG_SCB_PRIORITY) += scb-init.o
obj-$(CONFIG_CPU_VOLTAGE) += dpmc.o
obj-$(CONFIG_SMP) += smp.o
obj-$(CONFIG_BFIN_KERNEL_CLOCK) += clocks-init.o
diff --git a/arch/blackfin/mach-common/scb-init.c b/arch/blackfin/mach-common/scb-init.c
new file mode 100644
index 0000000..2cbfb0b
--- /dev/null
+++ b/arch/blackfin/mach-common/scb-init.c
@@ -0,0 +1,53 @@
+/*
+ * arch/blackfin/mach-common/scb-init.c - reprogram system cross bar priority
+ *
+ * Copyright 2012 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <asm/scb.h>
+
+__attribute__((l1_text))
+inline void scb_mi_write(unsigned long scb_mi_arbw, unsigned int slots,
+ unsigned char *scb_mi_prio)
+{
+ unsigned int i;
+
+ for (i = 0; i < slots; ++i)
+ bfin_write32(scb_mi_arbw, (i << SCB_SLOT_OFFSET) | scb_mi_prio[i]);
+}
+
+__attribute__((l1_text))
+inline void scb_mi_read(unsigned long scb_mi_arbw, unsigned int slots,
+ unsigned char *scb_mi_prio)
+{
+ unsigned int i;
+
+ for (i = 0; i < slots; ++i) {
+ bfin_write32(scb_mi_arbw, (0xFF << SCB_SLOT_OFFSET) | i);
+ scb_mi_prio[i] = bfin_read32(scb_mi_arbw);
+ }
+}
+
+__attribute__((l1_text))
+void init_scb(void)
+{
+ unsigned int i, j;
+ unsigned char scb_tmp_prio[32];
+
+ pr_info("Init System Crossbar\n");
+ for (i = 0; scb_data[i].scb_mi_arbr > 0; ++i) {
+
+ scb_mi_write(scb_data[i].scb_mi_arbw, scb_data[i].scb_mi_slots, scb_data[i].scb_mi_prio);
+
+ pr_debug("scb priority at 0x%lx:\n", scb_data[i].scb_mi_arbr);
+ scb_mi_read(scb_data[i].scb_mi_arbw, scb_data[i].scb_mi_slots, scb_tmp_prio);
+ for (j = 0; j < scb_data[i].scb_mi_slots; ++j)
+ pr_debug("slot %d = %d\n", j, scb_tmp_prio[j]);
+ }
+
+}
diff --git a/arch/c6x/Kconfig b/arch/c6x/Kconfig
index f6a3648..957dd00 100644
--- a/arch/c6x/Kconfig
+++ b/arch/c6x/Kconfig
@@ -10,7 +10,6 @@
select GENERIC_IRQ_SHOW
select HAVE_ARCH_TRACEHOOK
select HAVE_DMA_API_DEBUG
- select HAVE_GENERIC_HARDIRQS
select HAVE_MEMBLOCK
select SPARSE_IRQ
select IRQ_DOMAIN
diff --git a/arch/cris/Kconfig b/arch/cris/Kconfig
index c699d32..02380be 100644
--- a/arch/cris/Kconfig
+++ b/arch/cris/Kconfig
@@ -41,7 +41,6 @@
default y
select HAVE_IDE
select GENERIC_ATOMIC64
- select HAVE_GENERIC_HARDIRQS
select HAVE_UID16
select VIRT_TO_BUS
select ARCH_WANT_IPC_PARSE_VERSION
diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c
index 73312ab..1790f22 100644
--- a/arch/cris/mm/fault.c
+++ b/arch/cris/mm/fault.c
@@ -58,8 +58,7 @@
struct vm_area_struct * vma;
siginfo_t info;
int fault;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- ((writeaccess & 1) ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
D(printk(KERN_DEBUG
"Page fault for %lX on %X at %lX, prot %d write %d\n",
@@ -117,6 +116,8 @@
if (in_atomic() || !mm)
goto no_context;
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
@@ -155,6 +156,7 @@
} else if (writeaccess == 1) {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
} else {
if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
goto bad_area;
diff --git a/arch/frv/Kconfig b/arch/frv/Kconfig
index 4b6628e..34aa193 100644
--- a/arch/frv/Kconfig
+++ b/arch/frv/Kconfig
@@ -5,7 +5,6 @@
select HAVE_ARCH_TRACEHOOK
select HAVE_PERF_EVENTS
select HAVE_UID16
- select HAVE_GENERIC_HARDIRQS
select VIRT_TO_BUS
select GENERIC_IRQ_SHOW
select HAVE_DEBUG_BUGVERBOSE
diff --git a/arch/frv/mm/fault.c b/arch/frv/mm/fault.c
index 331c1e2..9a66372 100644
--- a/arch/frv/mm/fault.c
+++ b/arch/frv/mm/fault.c
@@ -34,11 +34,11 @@
struct vm_area_struct *vma;
struct mm_struct *mm;
unsigned long _pme, lrai, lrad, fixup;
+ unsigned long flags = 0;
siginfo_t info;
pgd_t *pge;
pud_t *pue;
pte_t *pte;
- int write;
int fault;
#if 0
@@ -81,6 +81,9 @@
if (in_atomic() || !mm)
goto no_context;
+ if (user_mode(__frame))
+ flags |= FAULT_FLAG_USER;
+
down_read(&mm->mmap_sem);
vma = find_vma(mm, ear0);
@@ -129,7 +132,6 @@
*/
good_area:
info.si_code = SEGV_ACCERR;
- write = 0;
switch (esr0 & ESR0_ATXC) {
default:
/* handle write to write protected page */
@@ -140,7 +142,7 @@
#endif
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
- write = 1;
+ flags |= FAULT_FLAG_WRITE;
break;
/* handle read from protected page */
@@ -162,7 +164,7 @@
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(mm, vma, ear0, write ? FAULT_FLAG_WRITE : 0);
+ fault = handle_mm_fault(mm, vma, ear0, flags);
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig
index 3d6759e..24b1dc2 100644
--- a/arch/h8300/Kconfig
+++ b/arch/h8300/Kconfig
@@ -2,7 +2,6 @@
bool
default y
select HAVE_IDE
- select HAVE_GENERIC_HARDIRQS
select GENERIC_ATOMIC64
select HAVE_UID16
select VIRT_TO_BUS
diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig
index 77d442a..99041b0 100644
--- a/arch/hexagon/Kconfig
+++ b/arch/hexagon/Kconfig
@@ -15,7 +15,6 @@
# select GENERIC_PENDING_IRQ if SMP
select GENERIC_ATOMIC64
select HAVE_PERF_EVENTS
- select HAVE_GENERIC_HARDIRQS
# GENERIC_ALLOCATOR is used by dma_alloc_coherent()
select GENERIC_ALLOCATOR
select GENERIC_IRQ_SHOW
diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c
index 1bd276d..8704c93 100644
--- a/arch/hexagon/mm/vm_fault.c
+++ b/arch/hexagon/mm/vm_fault.c
@@ -53,8 +53,7 @@
int si_code = SEGV_MAPERR;
int fault;
const struct exception_table_entry *fixup;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (cause > 0 ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
/*
* If we're in an interrupt or have no user context,
@@ -65,6 +64,8 @@
local_irq_enable();
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
@@ -96,6 +97,7 @@
case FLT_STORE:
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
break;
}
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index a86a56d..7740ab1 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -21,7 +21,6 @@
select HAVE_KVM
select HAVE_ARCH_TRACEHOOK
select HAVE_DMA_API_DEBUG
- select HAVE_GENERIC_HARDIRQS
select HAVE_MEMBLOCK
select HAVE_MEMBLOCK_NODE_MAP
select HAVE_VIRT_CPU_ACCOUNTING
diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index 6cf0341..7225dad 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -90,8 +90,6 @@
mask = ((((isr >> IA64_ISR_X_BIT) & 1UL) << VM_EXEC_BIT)
| (((isr >> IA64_ISR_W_BIT) & 1UL) << VM_WRITE_BIT));
- flags |= ((mask & VM_WRITE) ? FAULT_FLAG_WRITE : 0);
-
/* mmap_sem is performance critical.... */
prefetchw(&mm->mmap_sem);
@@ -119,6 +117,10 @@
if (notify_page_fault(regs, TRAP_BRKPT))
return;
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
+ if (mask & VM_WRITE)
+ flags |= FAULT_FLAG_WRITE;
retry:
down_read(&mm->mmap_sem);
diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c
index 76069c1..68232db 100644
--- a/arch/ia64/mm/hugetlbpage.c
+++ b/arch/ia64/mm/hugetlbpage.c
@@ -114,6 +114,11 @@
return 0;
}
+int pmd_huge_support(void)
+{
+ return 0;
+}
+
struct page *
follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write)
{
diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig
index 29a7ef4..75661fb 100644
--- a/arch/m32r/Kconfig
+++ b/arch/m32r/Kconfig
@@ -9,7 +9,6 @@
select HAVE_KERNEL_LZMA
select ARCH_WANT_IPC_PARSE_VERSION
select HAVE_DEBUG_BUGVERBOSE
- select HAVE_GENERIC_HARDIRQS
select VIRT_TO_BUS
select GENERIC_IRQ_PROBE
select GENERIC_IRQ_SHOW
diff --git a/arch/m32r/mm/fault.c b/arch/m32r/mm/fault.c
index 3cdfa9c..e9c6a80 100644
--- a/arch/m32r/mm/fault.c
+++ b/arch/m32r/mm/fault.c
@@ -78,7 +78,7 @@
struct mm_struct *mm;
struct vm_area_struct * vma;
unsigned long page, addr;
- int write;
+ unsigned long flags = 0;
int fault;
siginfo_t info;
@@ -117,6 +117,9 @@
if (in_atomic() || !mm)
goto bad_area_nosemaphore;
+ if (error_code & ACE_USERMODE)
+ flags |= FAULT_FLAG_USER;
+
/* When running in the kernel we expect faults to occur only to
* addresses in user space. All other faults represent errors in the
* kernel and should generate an OOPS. Unfortunately, in the case of an
@@ -166,14 +169,13 @@
*/
good_area:
info.si_code = SEGV_ACCERR;
- write = 0;
switch (error_code & (ACE_WRITE|ACE_PROTECTION)) {
default: /* 3: write, present */
/* fall through */
case ACE_WRITE: /* write, not present */
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
- write++;
+ flags |= FAULT_FLAG_WRITE;
break;
case ACE_PROTECTION: /* read, present */
case 0: /* read, not present */
@@ -194,7 +196,7 @@
*/
addr = (address & PAGE_MASK);
set_thread_fault_code(error_code);
- fault = handle_mm_fault(mm, vma, addr, write ? FAULT_FLAG_WRITE : 0);
+ fault = handle_mm_fault(mm, vma, addr, flags);
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index c3cda41..311a300 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -4,7 +4,6 @@
select HAVE_IDE
select HAVE_AOUT if MMU
select HAVE_DEBUG_BUGVERBOSE
- select HAVE_GENERIC_HARDIRQS
select GENERIC_IRQ_SHOW
select GENERIC_ATOMIC64
select HAVE_UID16
diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index a563727..eb1d61f 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -88,6 +88,8 @@
if (in_atomic() || !mm)
goto no_context;
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
diff --git a/arch/metag/Kconfig b/arch/metag/Kconfig
index cfd831c..36368eb 100644
--- a/arch/metag/Kconfig
+++ b/arch/metag/Kconfig
@@ -13,7 +13,6 @@
select HAVE_FTRACE_MCOUNT_RECORD
select HAVE_FUNCTION_TRACER
select HAVE_FUNCTION_TRACE_MCOUNT_TEST
- select HAVE_GENERIC_HARDIRQS
select HAVE_KERNEL_BZIP2
select HAVE_KERNEL_GZIP
select HAVE_KERNEL_LZO
diff --git a/arch/metag/mm/fault.c b/arch/metag/mm/fault.c
index 8fddf46..332680e 100644
--- a/arch/metag/mm/fault.c
+++ b/arch/metag/mm/fault.c
@@ -53,8 +53,7 @@
struct vm_area_struct *vma, *prev_vma;
siginfo_t info;
int fault;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (write_access ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
tsk = current;
@@ -109,6 +108,8 @@
if (in_atomic() || !mm)
goto no_context;
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
@@ -121,6 +122,7 @@
if (write_access) {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
} else {
if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
goto bad_area;
diff --git a/arch/metag/mm/hugetlbpage.c b/arch/metag/mm/hugetlbpage.c
index 3c52fa6..0424315 100644
--- a/arch/metag/mm/hugetlbpage.c
+++ b/arch/metag/mm/hugetlbpage.c
@@ -110,6 +110,11 @@
return 0;
}
+int pmd_huge_support(void)
+{
+ return 1;
+}
+
struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
pmd_t *pmd, int write)
{
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index 3f6659cb..b82f82b 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -18,7 +18,6 @@
select ARCH_WANT_IPC_PARSE_VERSION
select HAVE_DEBUG_KMEMLEAK
select IRQ_DOMAIN
- select HAVE_GENERIC_HARDIRQS
select VIRT_TO_BUS
select GENERIC_IRQ_PROBE
select GENERIC_IRQ_SHOW
diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c
index 731f739..fa4cf52 100644
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -92,8 +92,7 @@
int code = SEGV_MAPERR;
int is_write = error_code & ESR_S;
int fault;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (is_write ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
regs->ear = address;
regs->esr = error_code;
@@ -121,6 +120,9 @@
die("Weird page fault", regs, SIGSEGV);
}
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
+
/* When running in the kernel we expect faults to occur only to
* addresses in user space. All other faults represent errors in the
* kernel and should generate an OOPS. Unfortunately, in the case of an
@@ -199,6 +201,7 @@
if (unlikely(is_write)) {
if (unlikely(!(vma->vm_flags & VM_WRITE)))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
/* a read */
} else {
/* protection fault */
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 71f15e7..f75ab4a 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -25,7 +25,6 @@
select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
select HAVE_DMA_ATTRS
select HAVE_DMA_API_DEBUG
- select HAVE_GENERIC_HARDIRQS
select GENERIC_IRQ_PROBE
select GENERIC_IRQ_SHOW
select GENERIC_PCI_IOMAP
@@ -95,6 +94,7 @@
select CSRC_R4K
select DMA_NONCOHERENT
select HAVE_CLK
+ select CLKDEV_LOOKUP
select IRQ_CPU
select MIPS_MACHINE
select SYS_HAS_CPU_MIPS32_R2
@@ -131,7 +131,6 @@
select IRQ_CPU
select SYS_HAS_CPU_MIPS32_R1
select SYS_HAS_CPU_BMIPS4350 if !BCM63XX_CPU_6338 && !BCM63XX_CPU_6345 && !BCM63XX_CPU_6348
- select NR_CPUS_DEFAULT_2
select SYS_SUPPORTS_32BIT_KERNEL
select SYS_SUPPORTS_BIG_ENDIAN
select SYS_HAS_EARLY_PRINTK
@@ -445,6 +444,8 @@
select SYS_HAS_EARLY_PRINTK
select HAVE_MACH_CLKDEV
select CLKDEV_LOOKUP
+ select ARCH_HAS_RESET_CONTROLLER
+ select RESET_CONTROLLER
config SGI_IP22
bool "SGI IP22 (Indy/Indigo2)"
@@ -609,7 +610,6 @@
select BOOT_ELF32
select DMA_COHERENT
select HAVE_PATA_PLATFORM
- select NR_CPUS_DEFAULT_2
select SIBYTE_SB1250
select SWAP_IO_SPACE
select SYS_HAS_CPU_SB1
@@ -623,7 +623,6 @@
select BOOT_ELF32
select DMA_COHERENT
select HAVE_PATA_PLATFORM
- select NR_CPUS_DEFAULT_2
select SIBYTE_SB1250
select SWAP_IO_SPACE
select SYS_HAS_CPU_SB1
@@ -635,7 +634,6 @@
bool "Sibyte BCM91250E-Sentosa"
select BOOT_ELF32
select DMA_COHERENT
- select NR_CPUS_DEFAULT_2
select SIBYTE_SB1250
select SWAP_IO_SPACE
select SYS_HAS_CPU_SB1
@@ -731,6 +729,7 @@
select USB_ARCH_HAS_OHCI
select USB_ARCH_HAS_EHCI
select HOLES_IN_ZONE
+ select ARCH_REQUIRE_GPIOLIB
help
This option supports all of the Octeon reference boards from Cavium
Networks. It builds a kernel that dynamically determines the Octeon
@@ -1860,7 +1859,6 @@
select CPU_MIPSR2_IRQ_VI
select CPU_MIPSR2_IRQ_EI
select MIPS_MT
- select NR_CPUS_DEFAULT_2
select SMP
select SYS_SUPPORTS_SCHED_SMT if SMP
select SYS_SUPPORTS_SMP
@@ -2171,12 +2169,6 @@
config SYS_SUPPORTS_SMP
bool
-config NR_CPUS_DEFAULT_1
- bool
-
-config NR_CPUS_DEFAULT_2
- bool
-
config NR_CPUS_DEFAULT_4
bool
@@ -2194,10 +2186,8 @@
config NR_CPUS
int "Maximum number of CPUs (2-64)"
- range 1 64 if NR_CPUS_DEFAULT_1
+ range 2 64
depends on SMP
- default "1" if NR_CPUS_DEFAULT_1
- default "2" if NR_CPUS_DEFAULT_2
default "4" if NR_CPUS_DEFAULT_4
default "8" if NR_CPUS_DEFAULT_8
default "16" if NR_CPUS_DEFAULT_16
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index 37f9ef3..75a36ad 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -194,6 +194,8 @@
ifdef CONFIG_PHYSICAL_START
load-y = $(CONFIG_PHYSICAL_START)
endif
+entry-y = 0x$(shell $(NM) vmlinux 2>/dev/null \
+ | grep "\bkernel_entry\b" | cut -f1 -d \ )
cflags-y += -I$(srctree)/arch/mips/include/asm/mach-generic
drivers-$(CONFIG_PCI) += arch/mips/pci/
@@ -225,6 +227,9 @@
KBUILD_CPPFLAGS += -DVMLINUX_LOAD_ADDRESS=$(load-y)
KBUILD_CPPFLAGS += -DDATAOFFSET=$(if $(dataoffset-y),$(dataoffset-y),0)
+bootvars-y = VMLINUX_LOAD_ADDRESS=$(load-y) \
+ VMLINUX_ENTRY_ADDRESS=$(entry-y)
+
LDFLAGS += -m $(ld-emul)
ifdef CONFIG_CC_STACKPROTECTOR
@@ -254,9 +259,25 @@
# suspend and hibernation support
drivers-$(CONFIG_PM) += arch/mips/power/
+# boot image targets (arch/mips/boot/)
+boot-y := vmlinux.bin
+boot-y += vmlinux.ecoff
+boot-y += vmlinux.srec
+ifeq ($(shell expr $(load-y) \< 0xffffffff80000000 2> /dev/null), 0)
+boot-y += uImage
+boot-y += uImage.gz
+endif
+
+# compressed boot image targets (arch/mips/boot/compressed/)
+bootz-y := vmlinuz
+bootz-y += vmlinuz.bin
+bootz-y += vmlinuz.ecoff
+bootz-y += vmlinuz.srec
+
ifdef CONFIG_LASAT
rom.bin rom.sw: vmlinux
- $(Q)$(MAKE) $(build)=arch/mips/lasat/image $@
+ $(Q)$(MAKE) $(build)=arch/mips/lasat/image \
+ $(bootvars-y) $@
endif
#
@@ -280,13 +301,14 @@
all: $(all-y)
# boot
-vmlinux.bin vmlinux.ecoff vmlinux.srec: $(vmlinux-32) FORCE
- $(Q)$(MAKE) $(build)=arch/mips/boot VMLINUX=$(vmlinux-32) arch/mips/boot/$@
+$(boot-y): $(vmlinux-32) FORCE
+ $(Q)$(MAKE) $(build)=arch/mips/boot VMLINUX=$(vmlinux-32) \
+ $(bootvars-y) arch/mips/boot/$@
# boot/compressed
-vmlinuz vmlinuz.bin vmlinuz.ecoff vmlinuz.srec: $(vmlinux-32) FORCE
+$(bootz-y): $(vmlinux-32) FORCE
$(Q)$(MAKE) $(build)=arch/mips/boot/compressed \
- VMLINUX_LOAD_ADDRESS=$(load-y) 32bit-bfd=$(32bit-bfd) $@
+ $(bootvars-y) 32bit-bfd=$(32bit-bfd) $@
CLEAN_FILES += vmlinux.32 vmlinux.64
@@ -323,6 +345,8 @@
echo ' vmlinuz.ecoff - ECOFF zboot image'
echo ' vmlinuz.bin - Raw binary zboot image'
echo ' vmlinuz.srec - SREC zboot image'
+ echo ' uImage - U-Boot image'
+ echo ' uImage.gz - U-Boot image (gzip)'
echo
echo ' These will be default as appropriate for a configured platform.'
endef
diff --git a/arch/mips/ath79/clock.c b/arch/mips/ath79/clock.c
index 765ef30..26479f4 100644
--- a/arch/mips/ath79/clock.c
+++ b/arch/mips/ath79/clock.c
@@ -16,6 +16,7 @@
#include <linux/init.h>
#include <linux/err.h>
#include <linux/clk.h>
+#include <linux/clkdev.h>
#include <asm/div64.h>
@@ -31,92 +32,132 @@
unsigned long rate;
};
-static struct clk ath79_ref_clk;
-static struct clk ath79_cpu_clk;
-static struct clk ath79_ddr_clk;
-static struct clk ath79_ahb_clk;
-static struct clk ath79_wdt_clk;
-static struct clk ath79_uart_clk;
+static void __init ath79_add_sys_clkdev(const char *id, unsigned long rate)
+{
+ struct clk *clk;
+ int err;
+
+ clk = kzalloc(sizeof(*clk), GFP_KERNEL);
+ if (!clk)
+ panic("failed to allocate %s clock structure", id);
+
+ clk->rate = rate;
+
+ err = clk_register_clkdev(clk, id, NULL);
+ if (err)
+ panic("unable to register %s clock device", id);
+}
static void __init ar71xx_clocks_init(void)
{
+ unsigned long ref_rate;
+ unsigned long cpu_rate;
+ unsigned long ddr_rate;
+ unsigned long ahb_rate;
u32 pll;
u32 freq;
u32 div;
- ath79_ref_clk.rate = AR71XX_BASE_FREQ;
+ ref_rate = AR71XX_BASE_FREQ;
pll = ath79_pll_rr(AR71XX_PLL_REG_CPU_CONFIG);
div = ((pll >> AR71XX_PLL_DIV_SHIFT) & AR71XX_PLL_DIV_MASK) + 1;
- freq = div * ath79_ref_clk.rate;
+ freq = div * ref_rate;
div = ((pll >> AR71XX_CPU_DIV_SHIFT) & AR71XX_CPU_DIV_MASK) + 1;
- ath79_cpu_clk.rate = freq / div;
+ cpu_rate = freq / div;
div = ((pll >> AR71XX_DDR_DIV_SHIFT) & AR71XX_DDR_DIV_MASK) + 1;
- ath79_ddr_clk.rate = freq / div;
+ ddr_rate = freq / div;
div = (((pll >> AR71XX_AHB_DIV_SHIFT) & AR71XX_AHB_DIV_MASK) + 1) * 2;
- ath79_ahb_clk.rate = ath79_cpu_clk.rate / div;
+ ahb_rate = cpu_rate / div;
- ath79_wdt_clk.rate = ath79_ahb_clk.rate;
- ath79_uart_clk.rate = ath79_ahb_clk.rate;
+ ath79_add_sys_clkdev("ref", ref_rate);
+ ath79_add_sys_clkdev("cpu", cpu_rate);
+ ath79_add_sys_clkdev("ddr", ddr_rate);
+ ath79_add_sys_clkdev("ahb", ahb_rate);
+
+ clk_add_alias("wdt", NULL, "ahb", NULL);
+ clk_add_alias("uart", NULL, "ahb", NULL);
}
static void __init ar724x_clocks_init(void)
{
+ unsigned long ref_rate;
+ unsigned long cpu_rate;
+ unsigned long ddr_rate;
+ unsigned long ahb_rate;
u32 pll;
u32 freq;
u32 div;
- ath79_ref_clk.rate = AR724X_BASE_FREQ;
+ ref_rate = AR724X_BASE_FREQ;
pll = ath79_pll_rr(AR724X_PLL_REG_CPU_CONFIG);
div = ((pll >> AR724X_PLL_DIV_SHIFT) & AR724X_PLL_DIV_MASK);
- freq = div * ath79_ref_clk.rate;
+ freq = div * ref_rate;
div = ((pll >> AR724X_PLL_REF_DIV_SHIFT) & AR724X_PLL_REF_DIV_MASK);
freq *= div;
- ath79_cpu_clk.rate = freq;
+ cpu_rate = freq;
div = ((pll >> AR724X_DDR_DIV_SHIFT) & AR724X_DDR_DIV_MASK) + 1;
- ath79_ddr_clk.rate = freq / div;
+ ddr_rate = freq / div;
div = (((pll >> AR724X_AHB_DIV_SHIFT) & AR724X_AHB_DIV_MASK) + 1) * 2;
- ath79_ahb_clk.rate = ath79_cpu_clk.rate / div;
+ ahb_rate = cpu_rate / div;
- ath79_wdt_clk.rate = ath79_ahb_clk.rate;
- ath79_uart_clk.rate = ath79_ahb_clk.rate;
+ ath79_add_sys_clkdev("ref", ref_rate);
+ ath79_add_sys_clkdev("cpu", cpu_rate);
+ ath79_add_sys_clkdev("ddr", ddr_rate);
+ ath79_add_sys_clkdev("ahb", ahb_rate);
+
+ clk_add_alias("wdt", NULL, "ahb", NULL);
+ clk_add_alias("uart", NULL, "ahb", NULL);
}
static void __init ar913x_clocks_init(void)
{
+ unsigned long ref_rate;
+ unsigned long cpu_rate;
+ unsigned long ddr_rate;
+ unsigned long ahb_rate;
u32 pll;
u32 freq;
u32 div;
- ath79_ref_clk.rate = AR913X_BASE_FREQ;
+ ref_rate = AR913X_BASE_FREQ;
pll = ath79_pll_rr(AR913X_PLL_REG_CPU_CONFIG);
div = ((pll >> AR913X_PLL_DIV_SHIFT) & AR913X_PLL_DIV_MASK);
- freq = div * ath79_ref_clk.rate;
+ freq = div * ref_rate;
- ath79_cpu_clk.rate = freq;
+ cpu_rate = freq;
div = ((pll >> AR913X_DDR_DIV_SHIFT) & AR913X_DDR_DIV_MASK) + 1;
- ath79_ddr_clk.rate = freq / div;
+ ddr_rate = freq / div;
div = (((pll >> AR913X_AHB_DIV_SHIFT) & AR913X_AHB_DIV_MASK) + 1) * 2;
- ath79_ahb_clk.rate = ath79_cpu_clk.rate / div;
+ ahb_rate = cpu_rate / div;
- ath79_wdt_clk.rate = ath79_ahb_clk.rate;
- ath79_uart_clk.rate = ath79_ahb_clk.rate;
+ ath79_add_sys_clkdev("ref", ref_rate);
+ ath79_add_sys_clkdev("cpu", cpu_rate);
+ ath79_add_sys_clkdev("ddr", ddr_rate);
+ ath79_add_sys_clkdev("ahb", ahb_rate);
+
+ clk_add_alias("wdt", NULL, "ahb", NULL);
+ clk_add_alias("uart", NULL, "ahb", NULL);
}
static void __init ar933x_clocks_init(void)
{
+ unsigned long ref_rate;
+ unsigned long cpu_rate;
+ unsigned long ddr_rate;
+ unsigned long ahb_rate;
u32 clock_ctrl;
u32 cpu_config;
u32 freq;
@@ -124,21 +165,21 @@
t = ath79_reset_rr(AR933X_RESET_REG_BOOTSTRAP);
if (t & AR933X_BOOTSTRAP_REF_CLK_40)
- ath79_ref_clk.rate = (40 * 1000 * 1000);
+ ref_rate = (40 * 1000 * 1000);
else
- ath79_ref_clk.rate = (25 * 1000 * 1000);
+ ref_rate = (25 * 1000 * 1000);
clock_ctrl = ath79_pll_rr(AR933X_PLL_CLOCK_CTRL_REG);
if (clock_ctrl & AR933X_PLL_CLOCK_CTRL_BYPASS) {
- ath79_cpu_clk.rate = ath79_ref_clk.rate;
- ath79_ahb_clk.rate = ath79_ref_clk.rate;
- ath79_ddr_clk.rate = ath79_ref_clk.rate;
+ cpu_rate = ref_rate;
+ ahb_rate = ref_rate;
+ ddr_rate = ref_rate;
} else {
cpu_config = ath79_pll_rr(AR933X_PLL_CPU_CONFIG_REG);
t = (cpu_config >> AR933X_PLL_CPU_CONFIG_REFDIV_SHIFT) &
AR933X_PLL_CPU_CONFIG_REFDIV_MASK;
- freq = ath79_ref_clk.rate / t;
+ freq = ref_rate / t;
t = (cpu_config >> AR933X_PLL_CPU_CONFIG_NINT_SHIFT) &
AR933X_PLL_CPU_CONFIG_NINT_MASK;
@@ -153,19 +194,24 @@
t = ((clock_ctrl >> AR933X_PLL_CLOCK_CTRL_CPU_DIV_SHIFT) &
AR933X_PLL_CLOCK_CTRL_CPU_DIV_MASK) + 1;
- ath79_cpu_clk.rate = freq / t;
+ cpu_rate = freq / t;
t = ((clock_ctrl >> AR933X_PLL_CLOCK_CTRL_DDR_DIV_SHIFT) &
AR933X_PLL_CLOCK_CTRL_DDR_DIV_MASK) + 1;
- ath79_ddr_clk.rate = freq / t;
+ ddr_rate = freq / t;
t = ((clock_ctrl >> AR933X_PLL_CLOCK_CTRL_AHB_DIV_SHIFT) &
AR933X_PLL_CLOCK_CTRL_AHB_DIV_MASK) + 1;
- ath79_ahb_clk.rate = freq / t;
+ ahb_rate = freq / t;
}
- ath79_wdt_clk.rate = ath79_ref_clk.rate;
- ath79_uart_clk.rate = ath79_ref_clk.rate;
+ ath79_add_sys_clkdev("ref", ref_rate);
+ ath79_add_sys_clkdev("cpu", cpu_rate);
+ ath79_add_sys_clkdev("ddr", ddr_rate);
+ ath79_add_sys_clkdev("ahb", ahb_rate);
+
+ clk_add_alias("wdt", NULL, "ahb", NULL);
+ clk_add_alias("uart", NULL, "ref", NULL);
}
static u32 __init ar934x_get_pll_freq(u32 ref, u32 ref_div, u32 nint, u32 nfrac,
@@ -174,12 +220,12 @@
u64 t;
u32 ret;
- t = ath79_ref_clk.rate;
+ t = ref;
t *= nint;
do_div(t, ref_div);
ret = t;
- t = ath79_ref_clk.rate;
+ t = ref;
t *= nfrac;
do_div(t, ref_div * frac);
ret += t;
@@ -190,6 +236,10 @@
static void __init ar934x_clocks_init(void)
{
+ unsigned long ref_rate;
+ unsigned long cpu_rate;
+ unsigned long ddr_rate;
+ unsigned long ahb_rate;
u32 pll, out_div, ref_div, nint, nfrac, frac, clk_ctrl, postdiv;
u32 cpu_pll, ddr_pll;
u32 bootstrap;
@@ -199,9 +249,9 @@
bootstrap = ath79_reset_rr(AR934X_RESET_REG_BOOTSTRAP);
if (bootstrap & AR934X_BOOTSTRAP_REF_CLK_40)
- ath79_ref_clk.rate = 40 * 1000 * 1000;
+ ref_rate = 40 * 1000 * 1000;
else
- ath79_ref_clk.rate = 25 * 1000 * 1000;
+ ref_rate = 25 * 1000 * 1000;
pll = __raw_readl(dpll_base + AR934X_SRIF_CPU_DPLL2_REG);
if (pll & AR934X_SRIF_DPLL2_LOCAL_PLL) {
@@ -227,7 +277,7 @@
frac = 1 << 6;
}
- cpu_pll = ar934x_get_pll_freq(ath79_ref_clk.rate, ref_div, nint,
+ cpu_pll = ar934x_get_pll_freq(ref_rate, ref_div, nint,
nfrac, frac, out_div);
pll = __raw_readl(dpll_base + AR934X_SRIF_DDR_DPLL2_REG);
@@ -254,7 +304,7 @@
frac = 1 << 10;
}
- ddr_pll = ar934x_get_pll_freq(ath79_ref_clk.rate, ref_div, nint,
+ ddr_pll = ar934x_get_pll_freq(ref_rate, ref_div, nint,
nfrac, frac, out_div);
clk_ctrl = ath79_pll_rr(AR934X_PLL_CPU_DDR_CLK_CTRL_REG);
@@ -263,49 +313,58 @@
AR934X_PLL_CPU_DDR_CLK_CTRL_CPU_POST_DIV_MASK;
if (clk_ctrl & AR934X_PLL_CPU_DDR_CLK_CTRL_CPU_PLL_BYPASS)
- ath79_cpu_clk.rate = ath79_ref_clk.rate;
+ cpu_rate = ref_rate;
else if (clk_ctrl & AR934X_PLL_CPU_DDR_CLK_CTRL_CPUCLK_FROM_CPUPLL)
- ath79_cpu_clk.rate = cpu_pll / (postdiv + 1);
+ cpu_rate = cpu_pll / (postdiv + 1);
else
- ath79_cpu_clk.rate = ddr_pll / (postdiv + 1);
+ cpu_rate = ddr_pll / (postdiv + 1);
postdiv = (clk_ctrl >> AR934X_PLL_CPU_DDR_CLK_CTRL_DDR_POST_DIV_SHIFT) &
AR934X_PLL_CPU_DDR_CLK_CTRL_DDR_POST_DIV_MASK;
if (clk_ctrl & AR934X_PLL_CPU_DDR_CLK_CTRL_DDR_PLL_BYPASS)
- ath79_ddr_clk.rate = ath79_ref_clk.rate;
+ ddr_rate = ref_rate;
else if (clk_ctrl & AR934X_PLL_CPU_DDR_CLK_CTRL_DDRCLK_FROM_DDRPLL)
- ath79_ddr_clk.rate = ddr_pll / (postdiv + 1);
+ ddr_rate = ddr_pll / (postdiv + 1);
else
- ath79_ddr_clk.rate = cpu_pll / (postdiv + 1);
+ ddr_rate = cpu_pll / (postdiv + 1);
postdiv = (clk_ctrl >> AR934X_PLL_CPU_DDR_CLK_CTRL_AHB_POST_DIV_SHIFT) &
AR934X_PLL_CPU_DDR_CLK_CTRL_AHB_POST_DIV_MASK;
if (clk_ctrl & AR934X_PLL_CPU_DDR_CLK_CTRL_AHB_PLL_BYPASS)
- ath79_ahb_clk.rate = ath79_ref_clk.rate;
+ ahb_rate = ref_rate;
else if (clk_ctrl & AR934X_PLL_CPU_DDR_CLK_CTRL_AHBCLK_FROM_DDRPLL)
- ath79_ahb_clk.rate = ddr_pll / (postdiv + 1);
+ ahb_rate = ddr_pll / (postdiv + 1);
else
- ath79_ahb_clk.rate = cpu_pll / (postdiv + 1);
+ ahb_rate = cpu_pll / (postdiv + 1);
- ath79_wdt_clk.rate = ath79_ref_clk.rate;
- ath79_uart_clk.rate = ath79_ref_clk.rate;
+ ath79_add_sys_clkdev("ref", ref_rate);
+ ath79_add_sys_clkdev("cpu", cpu_rate);
+ ath79_add_sys_clkdev("ddr", ddr_rate);
+ ath79_add_sys_clkdev("ahb", ahb_rate);
+
+ clk_add_alias("wdt", NULL, "ref", NULL);
+ clk_add_alias("uart", NULL, "ref", NULL);
iounmap(dpll_base);
}
static void __init qca955x_clocks_init(void)
{
+ unsigned long ref_rate;
+ unsigned long cpu_rate;
+ unsigned long ddr_rate;
+ unsigned long ahb_rate;
u32 pll, out_div, ref_div, nint, frac, clk_ctrl, postdiv;
u32 cpu_pll, ddr_pll;
u32 bootstrap;
bootstrap = ath79_reset_rr(QCA955X_RESET_REG_BOOTSTRAP);
if (bootstrap & QCA955X_BOOTSTRAP_REF_CLK_40)
- ath79_ref_clk.rate = 40 * 1000 * 1000;
+ ref_rate = 40 * 1000 * 1000;
else
- ath79_ref_clk.rate = 25 * 1000 * 1000;
+ ref_rate = 25 * 1000 * 1000;
pll = ath79_pll_rr(QCA955X_PLL_CPU_CONFIG_REG);
out_div = (pll >> QCA955X_PLL_CPU_CONFIG_OUTDIV_SHIFT) &
@@ -317,8 +376,8 @@
frac = (pll >> QCA955X_PLL_CPU_CONFIG_NFRAC_SHIFT) &
QCA955X_PLL_CPU_CONFIG_NFRAC_MASK;
- cpu_pll = nint * ath79_ref_clk.rate / ref_div;
- cpu_pll += frac * ath79_ref_clk.rate / (ref_div * (1 << 6));
+ cpu_pll = nint * ref_rate / ref_div;
+ cpu_pll += frac * ref_rate / (ref_div * (1 << 6));
cpu_pll /= (1 << out_div);
pll = ath79_pll_rr(QCA955X_PLL_DDR_CONFIG_REG);
@@ -331,8 +390,8 @@
frac = (pll >> QCA955X_PLL_DDR_CONFIG_NFRAC_SHIFT) &
QCA955X_PLL_DDR_CONFIG_NFRAC_MASK;
- ddr_pll = nint * ath79_ref_clk.rate / ref_div;
- ddr_pll += frac * ath79_ref_clk.rate / (ref_div * (1 << 10));
+ ddr_pll = nint * ref_rate / ref_div;
+ ddr_pll += frac * ref_rate / (ref_div * (1 << 10));
ddr_pll /= (1 << out_div);
clk_ctrl = ath79_pll_rr(QCA955X_PLL_CLK_CTRL_REG);
@@ -341,34 +400,39 @@
QCA955X_PLL_CLK_CTRL_CPU_POST_DIV_MASK;
if (clk_ctrl & QCA955X_PLL_CLK_CTRL_CPU_PLL_BYPASS)
- ath79_cpu_clk.rate = ath79_ref_clk.rate;
+ cpu_rate = ref_rate;
else if (clk_ctrl & QCA955X_PLL_CLK_CTRL_CPUCLK_FROM_CPUPLL)
- ath79_cpu_clk.rate = ddr_pll / (postdiv + 1);
+ cpu_rate = ddr_pll / (postdiv + 1);
else
- ath79_cpu_clk.rate = cpu_pll / (postdiv + 1);
+ cpu_rate = cpu_pll / (postdiv + 1);
postdiv = (clk_ctrl >> QCA955X_PLL_CLK_CTRL_DDR_POST_DIV_SHIFT) &
QCA955X_PLL_CLK_CTRL_DDR_POST_DIV_MASK;
if (clk_ctrl & QCA955X_PLL_CLK_CTRL_DDR_PLL_BYPASS)
- ath79_ddr_clk.rate = ath79_ref_clk.rate;
+ ddr_rate = ref_rate;
else if (clk_ctrl & QCA955X_PLL_CLK_CTRL_DDRCLK_FROM_DDRPLL)
- ath79_ddr_clk.rate = cpu_pll / (postdiv + 1);
+ ddr_rate = cpu_pll / (postdiv + 1);
else
- ath79_ddr_clk.rate = ddr_pll / (postdiv + 1);
+ ddr_rate = ddr_pll / (postdiv + 1);
postdiv = (clk_ctrl >> QCA955X_PLL_CLK_CTRL_AHB_POST_DIV_SHIFT) &
QCA955X_PLL_CLK_CTRL_AHB_POST_DIV_MASK;
if (clk_ctrl & QCA955X_PLL_CLK_CTRL_AHB_PLL_BYPASS)
- ath79_ahb_clk.rate = ath79_ref_clk.rate;
+ ahb_rate = ref_rate;
else if (clk_ctrl & QCA955X_PLL_CLK_CTRL_AHBCLK_FROM_DDRPLL)
- ath79_ahb_clk.rate = ddr_pll / (postdiv + 1);
+ ahb_rate = ddr_pll / (postdiv + 1);
else
- ath79_ahb_clk.rate = cpu_pll / (postdiv + 1);
+ ahb_rate = cpu_pll / (postdiv + 1);
- ath79_wdt_clk.rate = ath79_ref_clk.rate;
- ath79_uart_clk.rate = ath79_ref_clk.rate;
+ ath79_add_sys_clkdev("ref", ref_rate);
+ ath79_add_sys_clkdev("cpu", cpu_rate);
+ ath79_add_sys_clkdev("ddr", ddr_rate);
+ ath79_add_sys_clkdev("ahb", ahb_rate);
+
+ clk_add_alias("wdt", NULL, "ref", NULL);
+ clk_add_alias("uart", NULL, "ref", NULL);
}
void __init ath79_clocks_init(void)
@@ -387,46 +451,27 @@
qca955x_clocks_init();
else
BUG();
+}
- pr_info("Clocks: CPU:%lu.%03luMHz, DDR:%lu.%03luMHz, AHB:%lu.%03luMHz, "
- "Ref:%lu.%03luMHz",
- ath79_cpu_clk.rate / 1000000,
- (ath79_cpu_clk.rate / 1000) % 1000,
- ath79_ddr_clk.rate / 1000000,
- (ath79_ddr_clk.rate / 1000) % 1000,
- ath79_ahb_clk.rate / 1000000,
- (ath79_ahb_clk.rate / 1000) % 1000,
- ath79_ref_clk.rate / 1000000,
- (ath79_ref_clk.rate / 1000) % 1000);
+unsigned long __init
+ath79_get_sys_clk_rate(const char *id)
+{
+ struct clk *clk;
+ unsigned long rate;
+
+ clk = clk_get(NULL, id);
+ if (IS_ERR(clk))
+ panic("unable to get %s clock, err=%d", id, (int) PTR_ERR(clk));
+
+ rate = clk_get_rate(clk);
+ clk_put(clk);
+
+ return rate;
}
/*
* Linux clock API
*/
-struct clk *clk_get(struct device *dev, const char *id)
-{
- if (!strcmp(id, "ref"))
- return &ath79_ref_clk;
-
- if (!strcmp(id, "cpu"))
- return &ath79_cpu_clk;
-
- if (!strcmp(id, "ddr"))
- return &ath79_ddr_clk;
-
- if (!strcmp(id, "ahb"))
- return &ath79_ahb_clk;
-
- if (!strcmp(id, "wdt"))
- return &ath79_wdt_clk;
-
- if (!strcmp(id, "uart"))
- return &ath79_uart_clk;
-
- return ERR_PTR(-ENOENT);
-}
-EXPORT_SYMBOL(clk_get);
-
int clk_enable(struct clk *clk)
{
return 0;
@@ -443,8 +488,3 @@
return clk->rate;
}
EXPORT_SYMBOL(clk_get_rate);
-
-void clk_put(struct clk *clk)
-{
-}
-EXPORT_SYMBOL(clk_put);
diff --git a/arch/mips/ath79/common.h b/arch/mips/ath79/common.h
index 561906c..648d2da 100644
--- a/arch/mips/ath79/common.h
+++ b/arch/mips/ath79/common.h
@@ -21,6 +21,8 @@
#define ATH79_MEM_SIZE_MAX (128 * 1024 * 1024)
void ath79_clocks_init(void);
+unsigned long ath79_get_sys_clk_rate(const char *id);
+
void ath79_ddr_wb_flush(unsigned int reg);
void ath79_gpio_function_enable(u32 mask);
diff --git a/arch/mips/ath79/dev-common.c b/arch/mips/ath79/dev-common.c
index a3a2741..c3b04c9 100644
--- a/arch/mips/ath79/dev-common.c
+++ b/arch/mips/ath79/dev-common.c
@@ -81,21 +81,19 @@
void __init ath79_register_uart(void)
{
- struct clk *clk;
+ unsigned long uart_clk_rate;
- clk = clk_get(NULL, "uart");
- if (IS_ERR(clk))
- panic("unable to get UART clock, err=%ld", PTR_ERR(clk));
+ uart_clk_rate = ath79_get_sys_clk_rate("uart");
if (soc_is_ar71xx() ||
soc_is_ar724x() ||
soc_is_ar913x() ||
soc_is_ar934x() ||
soc_is_qca955x()) {
- ath79_uart_data[0].uartclk = clk_get_rate(clk);
+ ath79_uart_data[0].uartclk = uart_clk_rate;
platform_device_register(&ath79_uart_device);
} else if (soc_is_ar933x()) {
- ar933x_uart_data.uartclk = clk_get_rate(clk);
+ ar933x_uart_data.uartclk = uart_clk_rate;
platform_device_register(&ar933x_uart_device);
} else {
BUG();
diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c
index 80f4ecd..64807a4 100644
--- a/arch/mips/ath79/setup.c
+++ b/arch/mips/ath79/setup.c
@@ -200,7 +200,6 @@
ath79_detect_sys_type();
detect_memory_region(0, ATH79_MEM_SIZE_MIN, ATH79_MEM_SIZE_MAX);
- ath79_clocks_init();
_machine_restart = ath79_restart;
_machine_halt = ath79_halt;
@@ -209,13 +208,25 @@
void __init plat_time_init(void)
{
- struct clk *clk;
+ unsigned long cpu_clk_rate;
+ unsigned long ahb_clk_rate;
+ unsigned long ddr_clk_rate;
+ unsigned long ref_clk_rate;
- clk = clk_get(NULL, "cpu");
- if (IS_ERR(clk))
- panic("unable to get CPU clock, err=%ld", PTR_ERR(clk));
+ ath79_clocks_init();
- mips_hpt_frequency = clk_get_rate(clk) / 2;
+ cpu_clk_rate = ath79_get_sys_clk_rate("cpu");
+ ahb_clk_rate = ath79_get_sys_clk_rate("ahb");
+ ddr_clk_rate = ath79_get_sys_clk_rate("ddr");
+ ref_clk_rate = ath79_get_sys_clk_rate("ref");
+
+ pr_info("Clocks: CPU:%lu.%03luMHz, DDR:%lu.%03luMHz, AHB:%lu.%03luMHz, Ref:%lu.%03luMHz",
+ cpu_clk_rate / 1000000, (cpu_clk_rate / 1000) % 1000,
+ ddr_clk_rate / 1000000, (ddr_clk_rate / 1000) % 1000,
+ ahb_clk_rate / 1000000, (ahb_clk_rate / 1000) % 1000,
+ ref_clk_rate / 1000000, (ref_clk_rate / 1000) % 1000);
+
+ mips_hpt_frequency = cpu_clk_rate / 2;
}
static int __init ath79_setup(void)
diff --git a/arch/mips/boot/.gitignore b/arch/mips/boot/.gitignore
index f210b09..a73d6e2 100644
--- a/arch/mips/boot/.gitignore
+++ b/arch/mips/boot/.gitignore
@@ -4,3 +4,4 @@
zImage
zImage.tmp
calc_vmlinuz_load_addr
+uImage
diff --git a/arch/mips/boot/Makefile b/arch/mips/boot/Makefile
index 851261e..1466c00 100644
--- a/arch/mips/boot/Makefile
+++ b/arch/mips/boot/Makefile
@@ -40,3 +40,18 @@
cmd_srec = $(OBJCOPY) -S -O srec $(strip-flags) $(VMLINUX) $@
$(obj)/vmlinux.srec: $(VMLINUX) FORCE
$(call if_changed,srec)
+
+UIMAGE_LOADADDR = $(VMLINUX_LOAD_ADDRESS)
+UIMAGE_ENTRYADDR = $(VMLINUX_ENTRY_ADDRESS)
+
+$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
+ $(call if_changed,gzip)
+
+targets += uImage.gz
+$(obj)/uImage.gz: $(obj)/vmlinux.bin.gz FORCE
+ $(call if_changed,uimage,gzip)
+
+targets += uImage
+$(obj)/uImage: $(obj)/uImage.gz FORCE
+ @ln -sf $(notdir $<) $@
+ @echo ' Image $@ is ready'
diff --git a/arch/mips/boot/compressed/Makefile b/arch/mips/boot/compressed/Makefile
index bb1dbf4..0048c08 100644
--- a/arch/mips/boot/compressed/Makefile
+++ b/arch/mips/boot/compressed/Makefile
@@ -25,7 +25,7 @@
KBUILD_AFLAGS := $(LINUXINCLUDE) $(KBUILD_AFLAGS) -D__ASSEMBLY__ \
-DBOOT_HEAP_SIZE=$(BOOT_HEAP_SIZE) \
- -DKERNEL_ENTRY=0x$(shell $(NM) $(objtree)/$(KBUILD_IMAGE) 2>/dev/null | grep " kernel_entry" | cut -f1 -d \ )
+ -DKERNEL_ENTRY=$(VMLINUX_ENTRY_ADDRESS)
targets := head.o decompress.o dbg.o uart-16550.o uart-alchemy.o
diff --git a/arch/mips/boot/dts/include/dt-bindings b/arch/mips/boot/dts/include/dt-bindings
new file mode 120000
index 0000000..68ae388
--- /dev/null
+++ b/arch/mips/boot/dts/include/dt-bindings
@@ -0,0 +1 @@
+../../../../../include/dt-bindings
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index 9d36774..25fbfae 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -1776,7 +1776,7 @@
#ifdef CONFIG_HOTPLUG_CPU
-void fixup_irqs(void)
+void octeon_fixup_irqs(void)
{
irq_cpu_offline();
}
diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c
index 48b08eb..b212ae1 100644
--- a/arch/mips/cavium-octeon/setup.c
+++ b/arch/mips/cavium-octeon/setup.c
@@ -8,6 +8,7 @@
* written by Ralf Baechle <ralf@linux-mips.org>
*/
#include <linux/compiler.h>
+#include <linux/vmalloc.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/console.h>
@@ -1139,3 +1140,30 @@
return err;
}
device_initcall(edac_devinit);
+
+static void __initdata *octeon_dummy_iospace;
+
+static int __init octeon_no_pci_init(void)
+{
+ /*
+ * Initially assume there is no PCI. The PCI/PCIe platform code will
+ * later re-initialize these to correct values if they are present.
+ */
+ octeon_dummy_iospace = vzalloc(IO_SPACE_LIMIT);
+ set_io_port_base((unsigned long)octeon_dummy_iospace);
+ ioport_resource.start = MAX_RESOURCE;
+ ioport_resource.end = 0;
+ return 0;
+}
+core_initcall(octeon_no_pci_init);
+
+static int __init octeon_no_pci_release(void)
+{
+ /*
+ * Release the allocated memory if a real IO space is there.
+ */
+ if ((unsigned long)octeon_dummy_iospace != mips_io_port_base)
+ vfree(octeon_dummy_iospace);
+ return 0;
+}
+late_initcall(octeon_no_pci_release);
diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c
index 138cc80..24a2167 100644
--- a/arch/mips/cavium-octeon/smp.c
+++ b/arch/mips/cavium-octeon/smp.c
@@ -255,8 +255,6 @@
/* State of each CPU. */
DEFINE_PER_CPU(int, cpu_state);
-extern void fixup_irqs(void);
-
static int octeon_cpu_disable(void)
{
unsigned int cpu = smp_processor_id();
@@ -267,7 +265,7 @@
set_cpu_online(cpu, false);
cpu_clear(cpu, cpu_callin_map);
local_irq_disable();
- fixup_irqs();
+ octeon_fixup_irqs();
local_irq_enable();
flush_cache_all();
diff --git a/arch/mips/configs/xway_defconfig b/arch/mips/configs/xway_defconfig
new file mode 100644
index 0000000..8987846
--- /dev/null
+++ b/arch/mips/configs/xway_defconfig
@@ -0,0 +1,159 @@
+CONFIG_LANTIQ=y
+CONFIG_XRX200_PHY_FW=y
+CONFIG_CPU_MIPS32_R2=y
+# CONFIG_COMPACTION is not set
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_HZ_100=y
+# CONFIG_SECCOMP is not set
+# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_SYSVIPC=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_BLK_DEV_INITRD=y
+# CONFIG_RD_GZIP is not set
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+CONFIG_KALLSYMS_ALL=y
+# CONFIG_AIO is not set
+CONFIG_EMBEDDED=y
+# CONFIG_VM_EVENT_COUNTERS is not set
+# CONFIG_SLUB_DEBUG is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+# CONFIG_BLK_DEV_BSG is not set
+CONFIG_PARTITION_ADVANCED=y
+# CONFIG_IOSCHED_CFQ is not set
+# CONFIG_COREDUMP is not set
+# CONFIG_SUSPEND is not set
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_ROUTE_MULTIPATH=y
+CONFIG_IP_ROUTE_VERBOSE=y
+CONFIG_IP_MROUTE=y
+CONFIG_IP_MROUTE_MULTIPLE_TABLES=y
+CONFIG_ARPD=y
+CONFIG_SYN_COOKIES=y
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_BEET is not set
+# CONFIG_INET_LRO is not set
+# CONFIG_INET_DIAG is not set
+CONFIG_TCP_CONG_ADVANCED=y
+# CONFIG_TCP_CONG_BIC is not set
+# CONFIG_TCP_CONG_WESTWOOD is not set
+# CONFIG_TCP_CONG_HTCP is not set
+# CONFIG_IPV6 is not set
+CONFIG_NETFILTER=y
+# CONFIG_BRIDGE_NETFILTER is not set
+CONFIG_NF_CONNTRACK=m
+CONFIG_NF_CONNTRACK_FTP=m
+CONFIG_NF_CONNTRACK_IRC=m
+CONFIG_NETFILTER_XT_TARGET_CT=m
+CONFIG_NETFILTER_XT_TARGET_LOG=m
+CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
+CONFIG_NETFILTER_XT_MATCH_COMMENT=m
+CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
+CONFIG_NETFILTER_XT_MATCH_LIMIT=m
+CONFIG_NETFILTER_XT_MATCH_MAC=m
+CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m
+CONFIG_NETFILTER_XT_MATCH_STATE=m
+CONFIG_NF_CONNTRACK_IPV4=m
+# CONFIG_NF_CONNTRACK_PROC_COMPAT is not set
+CONFIG_IP_NF_IPTABLES=m
+CONFIG_IP_NF_FILTER=m
+CONFIG_IP_NF_TARGET_REJECT=m
+CONFIG_IP_NF_MANGLE=m
+CONFIG_IP_NF_RAW=m
+CONFIG_BRIDGE=y
+# CONFIG_BRIDGE_IGMP_SNOOPING is not set
+CONFIG_VLAN_8021Q=y
+CONFIG_NET_SCHED=y
+CONFIG_HAMRADIO=y
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+# CONFIG_FIRMWARE_IN_KERNEL is not set
+CONFIG_MTD=y
+CONFIG_MTD_CMDLINE_PARTS=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_CFI=y
+CONFIG_MTD_CFI_AMDSTD=y
+CONFIG_MTD_COMPLEX_MAPPINGS=y
+CONFIG_MTD_PHYSMAP=y
+CONFIG_MTD_PHYSMAP_OF=y
+CONFIG_MTD_LANTIQ=y
+CONFIG_EEPROM_93CX6=m
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_NETDEVICES=y
+CONFIG_LANTIQ_ETOP=y
+# CONFIG_NET_VENDOR_WIZNET is not set
+CONFIG_PHYLIB=y
+CONFIG_PPP=m
+CONFIG_PPP_FILTER=y
+CONFIG_PPP_MULTILINK=y
+CONFIG_PPPOE=m
+CONFIG_PPP_ASYNC=m
+CONFIG_ISDN=y
+CONFIG_INPUT=m
+CONFIG_INPUT_POLLDEV=m
+# CONFIG_INPUT_MOUSEDEV is not set
+# CONFIG_KEYBOARD_ATKBD is not set
+# CONFIG_INPUT_MOUSE is not set
+CONFIG_INPUT_MISC=y
+# CONFIG_SERIO is not set
+# CONFIG_VT is not set
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_DEVKMEM is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_RUNTIME_UARTS=2
+CONFIG_SERIAL_OF_PLATFORM=y
+CONFIG_SPI=y
+CONFIG_GPIO_MM_LANTIQ=y
+CONFIG_GPIO_STP_XWAY=y
+# CONFIG_HWMON is not set
+CONFIG_WATCHDOG=y
+# CONFIG_HID is not set
+# CONFIG_USB_HID is not set
+CONFIG_USB=y
+CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
+CONFIG_USB_STORAGE=y
+CONFIG_USB_STORAGE_DEBUG=y
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
+CONFIG_LEDS_TRIGGERS=y
+CONFIG_LEDS_TRIGGER_TIMER=y
+CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
+CONFIG_STAGING=y
+# CONFIG_IOMMU_SUPPORT is not set
+# CONFIG_DNOTIFY is not set
+# CONFIG_PROC_PAGE_MONITOR is not set
+CONFIG_TMPFS=y
+CONFIG_TMPFS_XATTR=y
+CONFIG_JFFS2_FS=y
+CONFIG_JFFS2_SUMMARY=y
+CONFIG_JFFS2_FS_XATTR=y
+# CONFIG_JFFS2_FS_POSIX_ACL is not set
+# CONFIG_JFFS2_FS_SECURITY is not set
+CONFIG_JFFS2_COMPRESSION_OPTIONS=y
+# CONFIG_JFFS2_ZLIB is not set
+CONFIG_SQUASHFS=y
+# CONFIG_SQUASHFS_ZLIB is not set
+CONFIG_SQUASHFS_XZ=y
+CONFIG_PRINTK_TIME=y
+# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_STRIP_ASM_SYMS=y
+CONFIG_DEBUG_FS=y
+CONFIG_MAGIC_SYSRQ=y
+# CONFIG_SCHED_DEBUG is not set
+# CONFIG_FTRACE is not set
+CONFIG_CMDLINE_BOOL=y
+CONFIG_CRYPTO_MANAGER=m
+CONFIG_CRYPTO_ARC4=m
+# CONFIG_CRYPTO_ANSI_CPRNG is not set
+CONFIG_CRC_ITU_T=m
+CONFIG_CRC32_SARWATE=y
+CONFIG_AVERAGE=y
diff --git a/arch/mips/dec/time.c b/arch/mips/dec/time.c
index ea57f39..56ebc7f 100644
--- a/arch/mips/dec/time.c
+++ b/arch/mips/dec/time.c
@@ -126,12 +126,13 @@
void __init plat_time_init(void)
{
u32 start, end;
- int i = HZ / 10;
+ int i = HZ / 8;
/* Set up the rate of periodic DS1287 interrupts. */
ds1287_set_base_clock(HZ);
if (cpu_has_counter) {
+ ds1287_timer_state();
while (!ds1287_timer_state())
;
@@ -143,7 +144,7 @@
end = read_c0_count();
- mips_hpt_frequency = (end - start) * 10;
+ mips_hpt_frequency = (end - start) * 8;
printk(KERN_INFO "MIPS counter frequency %dHz\n",
mips_hpt_frequency);
} else if (IOASIC)
diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild
index 9b54b7a..454ddf9 100644
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -1,2 +1,15 @@
# MIPS headers
+generic-y += cputime.h
+generic-y += current.h
+generic-y += emergency-restart.h
+generic-y += local64.h
+generic-y += mutex.h
+generic-y += parport.h
+generic-y += percpu.h
+generic-y += scatterlist.h
+generic-y += sections.h
+generic-y += segment.h
+generic-y += serial.h
generic-y += trace_clock.h
+generic-y += ucontext.h
+generic-y += xor.h
diff --git a/arch/mips/include/asm/bmips.h b/arch/mips/include/asm/bmips.h
index 552a65a..27bd060 100644
--- a/arch/mips/include/asm/bmips.h
+++ b/arch/mips/include/asm/bmips.h
@@ -65,44 +65,33 @@
{
unsigned long ret;
- __asm__ __volatile__(
- ".set push\n"
- ".set noreorder\n"
- "cache %1, 0(%2)\n"
- "sync\n"
- "_ssnop\n"
- "_ssnop\n"
- "_ssnop\n"
- "_ssnop\n"
- "_ssnop\n"
- "_ssnop\n"
- "_ssnop\n"
- "mfc0 %0, $28, 3\n"
- "_ssnop\n"
- ".set pop\n"
- : "=&r" (ret)
- : "i" (Index_Load_Tag_S), "r" (ZSCM_REG_BASE + offset)
- : "memory");
+ barrier();
+ cache_op(Index_Load_Tag_S, ZSCM_REG_BASE + offset);
+ __sync();
+ _ssnop();
+ _ssnop();
+ _ssnop();
+ _ssnop();
+ _ssnop();
+ _ssnop();
+ _ssnop();
+ ret = read_c0_ddatalo();
+ _ssnop();
+
return ret;
}
static inline void bmips_write_zscm_reg(unsigned int offset, unsigned long data)
{
- __asm__ __volatile__(
- ".set push\n"
- ".set noreorder\n"
- "mtc0 %0, $28, 3\n"
- "_ssnop\n"
- "_ssnop\n"
- "_ssnop\n"
- "cache %1, 0(%2)\n"
- "_ssnop\n"
- "_ssnop\n"
- "_ssnop\n"
- : /* no outputs */
- : "r" (data),
- "i" (Index_Store_Tag_S), "r" (ZSCM_REG_BASE + offset)
- : "memory");
+ write_c0_ddatalo(data);
+ _ssnop();
+ _ssnop();
+ _ssnop();
+ cache_op(Index_Store_Tag_S, ZSCM_REG_BASE + offset);
+ _ssnop();
+ _ssnop();
+ _ssnop();
+ barrier();
}
#endif /* !defined(__ASSEMBLY__) */
diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h
index 632bbe5..71b9f19 100644
--- a/arch/mips/include/asm/cpu.h
+++ b/arch/mips/include/asm/cpu.h
@@ -141,6 +141,9 @@
#define PRID_IMP_CAVIUM_CN68XX 0x9100
#define PRID_IMP_CAVIUM_CN66XX 0x9200
#define PRID_IMP_CAVIUM_CN61XX 0x9300
+#define PRID_IMP_CAVIUM_CNF71XX 0x9400
+#define PRID_IMP_CAVIUM_CN78XX 0x9500
+#define PRID_IMP_CAVIUM_CN70XX 0x9600
/*
* These are the PRID's for when 23:16 == PRID_COMP_INGENIC
@@ -176,6 +179,7 @@
#define PRID_IMP_NETLOGIC_XLP8XX 0x1000
#define PRID_IMP_NETLOGIC_XLP3XX 0x1100
+#define PRID_IMP_NETLOGIC_XLP2XX 0x1200
/*
* Definitions for 7:0 on legacy processors
@@ -272,7 +276,7 @@
*/
CPU_5KC, CPU_5KE, CPU_20KC, CPU_25KF, CPU_SB1, CPU_SB1A, CPU_LOONGSON2,
CPU_CAVIUM_OCTEON, CPU_CAVIUM_OCTEON_PLUS, CPU_CAVIUM_OCTEON2,
- CPU_XLR, CPU_XLP,
+ CPU_CAVIUM_OCTEON3, CPU_XLR, CPU_XLP,
CPU_LAST
};
diff --git a/arch/mips/include/asm/cputime.h b/arch/mips/include/asm/cputime.h
deleted file mode 100644
index c00eacb..0000000
--- a/arch/mips/include/asm/cputime.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __MIPS_CPUTIME_H
-#define __MIPS_CPUTIME_H
-
-#include <asm-generic/cputime.h>
-
-#endif /* __MIPS_CPUTIME_H */
diff --git a/arch/mips/include/asm/current.h b/arch/mips/include/asm/current.h
deleted file mode 100644
index 4c51401..0000000
--- a/arch/mips/include/asm/current.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/current.h>
diff --git a/arch/mips/include/asm/emergency-restart.h b/arch/mips/include/asm/emergency-restart.h
deleted file mode 100644
index 108d8c4..0000000
--- a/arch/mips/include/asm/emergency-restart.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_EMERGENCY_RESTART_H
-#define _ASM_EMERGENCY_RESTART_H
-
-#include <asm-generic/emergency-restart.h>
-
-#endif /* _ASM_EMERGENCY_RESTART_H */
diff --git a/arch/mips/include/asm/local64.h b/arch/mips/include/asm/local64.h
deleted file mode 100644
index 36c93b5..0000000
--- a/arch/mips/include/asm/local64.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/local64.h>
diff --git a/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h b/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h
index ddb947e..0089a74 100644
--- a/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h
+++ b/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h
@@ -42,8 +42,6 @@
#define cpu_has_mips64r1 0
#define cpu_has_mips64r2 0
-#define cpu_has_dsp 0
-#define cpu_has_dsp2 0
#define cpu_has_mipsmt 0
#define cpu_has_64bits 0
diff --git a/arch/mips/include/asm/mach-cavium-octeon/gpio.h b/arch/mips/include/asm/mach-cavium-octeon/gpio.h
new file mode 100644
index 0000000..34e9f7a
--- /dev/null
+++ b/arch/mips/include/asm/mach-cavium-octeon/gpio.h
@@ -0,0 +1,21 @@
+#ifndef __ASM_MACH_CAVIUM_OCTEON_GPIO_H
+#define __ASM_MACH_CAVIUM_OCTEON_GPIO_H
+
+#ifdef CONFIG_GPIOLIB
+#define gpio_get_value __gpio_get_value
+#define gpio_set_value __gpio_set_value
+#define gpio_cansleep __gpio_cansleep
+#else
+int gpio_request(unsigned gpio, const char *label);
+void gpio_free(unsigned gpio);
+int gpio_direction_input(unsigned gpio);
+int gpio_direction_output(unsigned gpio, int value);
+int gpio_get_value(unsigned gpio);
+void gpio_set_value(unsigned gpio, int value);
+#endif
+
+#include <asm-generic/gpio.h>
+
+#define gpio_to_irq __gpio_to_irq
+
+#endif /* __ASM_MACH_GENERIC_GPIO_H */
diff --git a/arch/mips/include/asm/mach-lantiq/falcon/cpu-feature-overrides.h b/arch/mips/include/asm/mach-lantiq/falcon/cpu-feature-overrides.h
new file mode 100644
index 0000000..096a100
--- /dev/null
+++ b/arch/mips/include/asm/mach-lantiq/falcon/cpu-feature-overrides.h
@@ -0,0 +1,58 @@
+/*
+ * Lantiq FALCON specific CPU feature overrides
+ *
+ * Copyright (C) 2013 Thomas Langer, Lantiq Deutschland
+ *
+ * This file was derived from: include/asm-mips/cpu-features.h
+ * Copyright (C) 2003, 2004 Ralf Baechle
+ * Copyright (C) 2004 Maciej W. Rozycki
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ */
+#ifndef __ASM_MACH_FALCON_CPU_FEATURE_OVERRIDES_H
+#define __ASM_MACH_FALCON_CPU_FEATURE_OVERRIDES_H
+
+#define cpu_has_tlb 1
+#define cpu_has_4kex 1
+#define cpu_has_3k_cache 0
+#define cpu_has_4k_cache 1
+#define cpu_has_tx39_cache 0
+#define cpu_has_sb1_cache 0
+#define cpu_has_fpu 0
+#define cpu_has_32fpr 0
+#define cpu_has_counter 1
+#define cpu_has_watch 1
+#define cpu_has_divec 1
+
+#define cpu_has_prefetch 1
+#define cpu_has_ejtag 1
+#define cpu_has_llsc 1
+
+#define cpu_has_mips16 1
+#define cpu_has_mdmx 0
+#define cpu_has_mips3d 0
+#define cpu_has_smartmips 0
+
+#define cpu_has_mips32r1 1
+#define cpu_has_mips32r2 1
+#define cpu_has_mips64r1 0
+#define cpu_has_mips64r2 0
+
+#define cpu_has_dsp 1
+#define cpu_has_mipsmt 1
+
+#define cpu_has_vint 1
+#define cpu_has_veic 1
+
+#define cpu_has_64bits 0
+#define cpu_has_64bit_zero_reg 0
+#define cpu_has_64bit_gp_regs 0
+#define cpu_has_64bit_addresses 0
+
+#define cpu_dcache_line_size() 32
+#define cpu_icache_line_size() 32
+
+#endif /* __ASM_MACH_FALCON_CPU_FEATURE_OVERRIDES_H */
diff --git a/arch/mips/include/asm/mach-ralink/mt7620.h b/arch/mips/include/asm/mach-ralink/mt7620.h
index 9809972..6f9b24f 100644
--- a/arch/mips/include/asm/mach-ralink/mt7620.h
+++ b/arch/mips/include/asm/mach-ralink/mt7620.h
@@ -20,6 +20,8 @@
#define SYSC_REG_CHIP_REV 0x0c
#define SYSC_REG_SYSTEM_CONFIG0 0x10
#define SYSC_REG_SYSTEM_CONFIG1 0x14
+#define SYSC_REG_CLKCFG0 0x2c
+#define SYSC_REG_CPU_SYS_CLKCFG 0x3c
#define SYSC_REG_CPLL_CONFIG0 0x54
#define SYSC_REG_CPLL_CONFIG1 0x58
@@ -29,20 +31,42 @@
#define MT7620A_CHIP_NAME0 0x3637544d
#define MT7620A_CHIP_NAME1 0x20203032
+#define SYSCFG0_XTAL_FREQ_SEL BIT(6)
+
#define CHIP_REV_PKG_MASK 0x1
#define CHIP_REV_PKG_SHIFT 16
#define CHIP_REV_VER_MASK 0xf
#define CHIP_REV_VER_SHIFT 8
#define CHIP_REV_ECO_MASK 0xf
-#define CPLL_SW_CONFIG_SHIFT 31
-#define CPLL_SW_CONFIG_MASK 0x1
-#define CPLL_CPU_CLK_SHIFT 24
-#define CPLL_CPU_CLK_MASK 0x1
-#define CPLL_MULT_RATIO_SHIFT 16
-#define CPLL_MULT_RATIO 0x7
-#define CPLL_DIV_RATIO_SHIFT 10
-#define CPLL_DIV_RATIO 0x3
+#define CLKCFG0_PERI_CLK_SEL BIT(4)
+
+#define CPU_SYS_CLKCFG_OCP_RATIO_SHIFT 16
+#define CPU_SYS_CLKCFG_OCP_RATIO_MASK 0xf
+#define CPU_SYS_CLKCFG_OCP_RATIO_1 0 /* 1:1 (Reserved) */
+#define CPU_SYS_CLKCFG_OCP_RATIO_1_5 1 /* 1:1.5 (Reserved) */
+#define CPU_SYS_CLKCFG_OCP_RATIO_2 2 /* 1:2 */
+#define CPU_SYS_CLKCFG_OCP_RATIO_2_5 3 /* 1:2.5 (Reserved) */
+#define CPU_SYS_CLKCFG_OCP_RATIO_3 4 /* 1:3 */
+#define CPU_SYS_CLKCFG_OCP_RATIO_3_5 5 /* 1:3.5 (Reserved) */
+#define CPU_SYS_CLKCFG_OCP_RATIO_4 6 /* 1:4 */
+#define CPU_SYS_CLKCFG_OCP_RATIO_5 7 /* 1:5 */
+#define CPU_SYS_CLKCFG_OCP_RATIO_10 8 /* 1:10 */
+#define CPU_SYS_CLKCFG_CPU_FDIV_SHIFT 8
+#define CPU_SYS_CLKCFG_CPU_FDIV_MASK 0x1f
+#define CPU_SYS_CLKCFG_CPU_FFRAC_SHIFT 0
+#define CPU_SYS_CLKCFG_CPU_FFRAC_MASK 0x1f
+
+#define CPLL_CFG0_SW_CFG BIT(31)
+#define CPLL_CFG0_PLL_MULT_RATIO_SHIFT 16
+#define CPLL_CFG0_PLL_MULT_RATIO_MASK 0x7
+#define CPLL_CFG0_LC_CURFCK BIT(15)
+#define CPLL_CFG0_BYPASS_REF_CLK BIT(14)
+#define CPLL_CFG0_PLL_DIV_RATIO_SHIFT 10
+#define CPLL_CFG0_PLL_DIV_RATIO_MASK 0x3
+
+#define CPLL_CFG1_CPU_AUX1 BIT(25)
+#define CPLL_CFG1_CPU_AUX0 BIT(24)
#define SYSCFG0_DRAM_TYPE_MASK 0x3
#define SYSCFG0_DRAM_TYPE_SHIFT 4
diff --git a/arch/mips/include/asm/mach-ralink/mt7620/cpu-feature-overrides.h b/arch/mips/include/asm/mach-ralink/mt7620/cpu-feature-overrides.h
new file mode 100644
index 0000000..f7bb8cf
--- /dev/null
+++ b/arch/mips/include/asm/mach-ralink/mt7620/cpu-feature-overrides.h
@@ -0,0 +1,57 @@
+/*
+ * Ralink MT7620 specific CPU feature overrides
+ *
+ * Copyright (C) 2008-2009 Gabor Juhos <juhosg@openwrt.org>
+ * Copyright (C) 2008 Imre Kaloz <kaloz@openwrt.org>
+ *
+ * This file was derived from: include/asm-mips/cpu-features.h
+ * Copyright (C) 2003, 2004 Ralf Baechle
+ * Copyright (C) 2004 Maciej W. Rozycki
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ */
+#ifndef _MT7620_CPU_FEATURE_OVERRIDES_H
+#define _MT7620_CPU_FEATURE_OVERRIDES_H
+
+#define cpu_has_tlb 1
+#define cpu_has_4kex 1
+#define cpu_has_3k_cache 0
+#define cpu_has_4k_cache 1
+#define cpu_has_tx39_cache 0
+#define cpu_has_sb1_cache 0
+#define cpu_has_fpu 0
+#define cpu_has_32fpr 0
+#define cpu_has_counter 1
+#define cpu_has_watch 1
+#define cpu_has_divec 1
+
+#define cpu_has_prefetch 1
+#define cpu_has_ejtag 1
+#define cpu_has_llsc 1
+
+#define cpu_has_mips16 1
+#define cpu_has_mdmx 0
+#define cpu_has_mips3d 0
+#define cpu_has_smartmips 0
+
+#define cpu_has_mips32r1 1
+#define cpu_has_mips32r2 1
+#define cpu_has_mips64r1 0
+#define cpu_has_mips64r2 0
+
+#define cpu_has_dsp 1
+#define cpu_has_dsp2 0
+#define cpu_has_mipsmt 0
+
+#define cpu_has_64bits 0
+#define cpu_has_64bit_zero_reg 0
+#define cpu_has_64bit_gp_regs 0
+#define cpu_has_64bit_addresses 0
+
+#define cpu_dcache_line_size() 32
+#define cpu_icache_line_size() 32
+
+#endif /* _MT7620_CPU_FEATURE_OVERRIDES_H */
diff --git a/arch/mips/include/asm/mutex.h b/arch/mips/include/asm/mutex.h
deleted file mode 100644
index 458c1f7..0000000
--- a/arch/mips/include/asm/mutex.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-
-#include <asm-generic/mutex-dec.h>
diff --git a/arch/mips/include/asm/netlogic/xlp-hal/bridge.h b/arch/mips/include/asm/netlogic/xlp-hal/bridge.h
index 790f0f1..4e8eacb 100644
--- a/arch/mips/include/asm/netlogic/xlp-hal/bridge.h
+++ b/arch/mips/include/asm/netlogic/xlp-hal/bridge.h
@@ -88,6 +88,7 @@
#define BRIDGE_DRAM_LIMIT6 0x22
#define BRIDGE_DRAM_LIMIT7 0x23
+#define BRIDGE_DRAM_NODE_TRANSLN(i) (0x24 + (i))
#define BRIDGE_DRAM_NODE_TRANSLN0 0x24
#define BRIDGE_DRAM_NODE_TRANSLN1 0x25
#define BRIDGE_DRAM_NODE_TRANSLN2 0x26
@@ -96,6 +97,8 @@
#define BRIDGE_DRAM_NODE_TRANSLN5 0x29
#define BRIDGE_DRAM_NODE_TRANSLN6 0x2a
#define BRIDGE_DRAM_NODE_TRANSLN7 0x2b
+
+#define BRIDGE_DRAM_CHNL_TRANSLN(i) (0x2c + (i))
#define BRIDGE_DRAM_CHNL_TRANSLN0 0x2c
#define BRIDGE_DRAM_CHNL_TRANSLN1 0x2d
#define BRIDGE_DRAM_CHNL_TRANSLN2 0x2e
@@ -104,6 +107,7 @@
#define BRIDGE_DRAM_CHNL_TRANSLN5 0x31
#define BRIDGE_DRAM_CHNL_TRANSLN6 0x32
#define BRIDGE_DRAM_CHNL_TRANSLN7 0x33
+
#define BRIDGE_PCIEMEM_BASE0 0x34
#define BRIDGE_PCIEMEM_BASE1 0x35
#define BRIDGE_PCIEMEM_BASE2 0x36
diff --git a/arch/mips/include/asm/netlogic/xlp-hal/iomap.h b/arch/mips/include/asm/netlogic/xlp-hal/iomap.h
index 9fac46f..55eee77 100644
--- a/arch/mips/include/asm/netlogic/xlp-hal/iomap.h
+++ b/arch/mips/include/asm/netlogic/xlp-hal/iomap.h
@@ -72,6 +72,12 @@
#define XLP_IO_USB_OHCI2_OFFSET(node) XLP_HDR_OFFSET(node, 0, 2, 4)
#define XLP_IO_USB_OHCI3_OFFSET(node) XLP_HDR_OFFSET(node, 0, 2, 5)
+/* XLP2xx has an updated USB block */
+#define XLP2XX_IO_USB_OFFSET(node, i) XLP_HDR_OFFSET(node, 0, 4, i)
+#define XLP2XX_IO_USB_XHCI0_OFFSET(node) XLP_HDR_OFFSET(node, 0, 4, 1)
+#define XLP2XX_IO_USB_XHCI1_OFFSET(node) XLP_HDR_OFFSET(node, 0, 4, 2)
+#define XLP2XX_IO_USB_XHCI2_OFFSET(node) XLP_HDR_OFFSET(node, 0, 4, 3)
+
#define XLP_IO_NAE_OFFSET(node) XLP_HDR_OFFSET(node, 0, 3, 0)
#define XLP_IO_POE_OFFSET(node) XLP_HDR_OFFSET(node, 0, 3, 1)
@@ -88,6 +94,9 @@
#define XLP_IO_I2C0_OFFSET(node) XLP_HDR_OFFSET(node, 0, 6, 2)
#define XLP_IO_I2C1_OFFSET(node) XLP_HDR_OFFSET(node, 0, 6, 3)
#define XLP_IO_GPIO_OFFSET(node) XLP_HDR_OFFSET(node, 0, 6, 4)
+/* on 2XX, all I2C busses are on the same block */
+#define XLP2XX_IO_I2C_OFFSET(node) XLP_HDR_OFFSET(node, 0, 6, 7)
+
/* system management */
#define XLP_IO_SYS_OFFSET(node) XLP_HDR_OFFSET(node, 0, 6, 5)
#define XLP_IO_JTAG_OFFSET(node) XLP_HDR_OFFSET(node, 0, 6, 6)
@@ -145,6 +154,7 @@
#define PCI_DEVICE_ID_NLM_NOR 0x1015
#define PCI_DEVICE_ID_NLM_NAND 0x1016
#define PCI_DEVICE_ID_NLM_MMC 0x1018
+#define PCI_DEVICE_ID_NLM_XHCI 0x101d
#ifndef __ASSEMBLY__
diff --git a/arch/mips/include/asm/netlogic/xlp-hal/pic.h b/arch/mips/include/asm/netlogic/xlp-hal/pic.h
index 4b5108d..105389b 100644
--- a/arch/mips/include/asm/netlogic/xlp-hal/pic.h
+++ b/arch/mips/include/asm/netlogic/xlp-hal/pic.h
@@ -208,13 +208,14 @@
#define PIC_LOCAL_SCHEDULING 1
#define PIC_GLOBAL_SCHEDULING 0
-#define PIC_CLK_HZ 133333333
-
#define nlm_read_pic_reg(b, r) nlm_read_reg64(b, r)
#define nlm_write_pic_reg(b, r, v) nlm_write_reg64(b, r, v)
#define nlm_get_pic_pcibase(node) nlm_pcicfg_base(XLP_IO_PIC_OFFSET(node))
#define nlm_get_pic_regbase(node) (nlm_get_pic_pcibase(node) + XLP_IO_PCI_HDRSZ)
+/* We use PIC on node 0 as a timer */
+#define pic_timer_freq() nlm_get_pic_frequency(0)
+
/* IRT and h/w interrupt routines */
static inline int
nlm_pic_read_irt(uint64_t base, int irt_index)
diff --git a/arch/mips/include/asm/netlogic/xlp-hal/sys.h b/arch/mips/include/asm/netlogic/xlp-hal/sys.h
index 470e52b..fcf2833c 100644
--- a/arch/mips/include/asm/netlogic/xlp-hal/sys.h
+++ b/arch/mips/include/asm/netlogic/xlp-hal/sys.h
@@ -117,6 +117,36 @@
#define SYS_SCRTCH2 0x4b
#define SYS_SCRTCH3 0x4c
+/* PLL registers XLP2XX */
+#define SYS_PLL_CTRL0 0x240
+#define SYS_PLL_CTRL1 0x241
+#define SYS_PLL_CTRL2 0x242
+#define SYS_PLL_CTRL3 0x243
+#define SYS_DMC_PLL_CTRL0 0x244
+#define SYS_DMC_PLL_CTRL1 0x245
+#define SYS_DMC_PLL_CTRL2 0x246
+#define SYS_DMC_PLL_CTRL3 0x247
+
+#define SYS_PLL_CTRL0_DEVX(x) (0x248 + (x) * 4)
+#define SYS_PLL_CTRL1_DEVX(x) (0x249 + (x) * 4)
+#define SYS_PLL_CTRL2_DEVX(x) (0x24a + (x) * 4)
+#define SYS_PLL_CTRL3_DEVX(x) (0x24b + (x) * 4)
+
+#define SYS_CPU_PLL_CHG_CTRL 0x288
+#define SYS_PLL_CHG_CTRL 0x289
+#define SYS_CLK_DEV_DIS 0x28a
+#define SYS_CLK_DEV_SEL 0x28b
+#define SYS_CLK_DEV_DIV 0x28c
+#define SYS_CLK_DEV_CHG 0x28d
+#define SYS_CLK_DEV_SEL_REG 0x28e
+#define SYS_CLK_DEV_DIV_REG 0x28f
+#define SYS_CPU_PLL_LOCK 0x29f
+#define SYS_SYS_PLL_LOCK 0x2a0
+#define SYS_PLL_MEM_CMD 0x2a1
+#define SYS_CPU_PLL_MEM_REQ 0x2a2
+#define SYS_SYS_PLL_MEM_REQ 0x2a3
+#define SYS_PLL_MEM_STAT 0x2a4
+
#ifndef __ASSEMBLY__
#define nlm_read_sys_reg(b, r) nlm_read_reg(b, r)
@@ -124,5 +154,6 @@
#define nlm_get_sys_pcibase(node) nlm_pcicfg_base(XLP_IO_SYS_OFFSET(node))
#define nlm_get_sys_regbase(node) (nlm_get_sys_pcibase(node) + XLP_IO_PCI_HDRSZ)
+unsigned int nlm_get_pic_frequency(int node);
#endif
#endif
diff --git a/arch/mips/include/asm/netlogic/xlp-hal/xlp.h b/arch/mips/include/asm/netlogic/xlp-hal/xlp.h
index f4ea0f7..17daffb2 100644
--- a/arch/mips/include/asm/netlogic/xlp-hal/xlp.h
+++ b/arch/mips/include/asm/netlogic/xlp-hal/xlp.h
@@ -41,15 +41,22 @@
#define PIC_PCIE_LINK_1_IRQ 20
#define PIC_PCIE_LINK_2_IRQ 21
#define PIC_PCIE_LINK_3_IRQ 22
+
#define PIC_EHCI_0_IRQ 23
#define PIC_EHCI_1_IRQ 24
#define PIC_OHCI_0_IRQ 25
#define PIC_OHCI_1_IRQ 26
#define PIC_OHCI_2_IRQ 27
#define PIC_OHCI_3_IRQ 28
+#define PIC_2XX_XHCI_0_IRQ 23
+#define PIC_2XX_XHCI_1_IRQ 24
+#define PIC_2XX_XHCI_2_IRQ 25
+
#define PIC_MMC_IRQ 29
#define PIC_I2C_0_IRQ 30
#define PIC_I2C_1_IRQ 31
+#define PIC_I2C_2_IRQ 32
+#define PIC_I2C_3_IRQ 33
#ifndef __ASSEMBLY__
@@ -59,7 +66,17 @@
void xlp_mmu_init(void);
void nlm_hal_init(void);
+int xlp_get_dram_map(int n, uint64_t *dram_map);
+
+/* Device tree related */
void *xlp_dt_init(void *fdtp);
+static inline int cpu_is_xlpii(void)
+{
+ int chip = read_c0_prid() & 0xff00;
+
+ return chip == PRID_IMP_NETLOGIC_XLP2XX;
+}
+
#endif /* !__ASSEMBLY__ */
#endif /* _ASM_NLM_XLP_H */
diff --git a/arch/mips/include/asm/netlogic/xlr/pic.h b/arch/mips/include/asm/netlogic/xlr/pic.h
index 63c9917..3c80a75 100644
--- a/arch/mips/include/asm/netlogic/xlr/pic.h
+++ b/arch/mips/include/asm/netlogic/xlr/pic.h
@@ -36,6 +36,8 @@
#define _ASM_NLM_XLR_PIC_H
#define PIC_CLK_HZ 66666666
+#define pic_timer_freq() PIC_CLK_HZ
+
/* PIC hardware interrupt numbers */
#define PIC_IRT_WD_INDEX 0
#define PIC_IRT_TIMER_0_INDEX 1
diff --git a/arch/mips/include/asm/octeon/octeon.h b/arch/mips/include/asm/octeon/octeon.h
index a2eed23..f5d77b9 100644
--- a/arch/mips/include/asm/octeon/octeon.h
+++ b/arch/mips/include/asm/octeon/octeon.h
@@ -251,4 +251,6 @@
typedef void (*octeon_irq_ip4_handler_t)(void);
void octeon_irq_set_ip4_handler(octeon_irq_ip4_handler_t);
+extern void octeon_fixup_irqs(void);
+
#endif /* __ASM_OCTEON_OCTEON_H */
diff --git a/arch/mips/include/asm/parport.h b/arch/mips/include/asm/parport.h
deleted file mode 100644
index cf252af..0000000
--- a/arch/mips/include/asm/parport.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/parport.h>
diff --git a/arch/mips/include/asm/percpu.h b/arch/mips/include/asm/percpu.h
deleted file mode 100644
index 844e763..0000000
--- a/arch/mips/include/asm/percpu.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_PERCPU_H
-#define __ASM_PERCPU_H
-
-#include <asm-generic/percpu.h>
-
-#endif /* __ASM_PERCPU_H */
diff --git a/arch/mips/include/asm/scatterlist.h b/arch/mips/include/asm/scatterlist.h
deleted file mode 100644
index 7ee0e64..0000000
--- a/arch/mips/include/asm/scatterlist.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_SCATTERLIST_H
-#define __ASM_SCATTERLIST_H
-
-#include <asm-generic/scatterlist.h>
-
-#endif /* __ASM_SCATTERLIST_H */
diff --git a/arch/mips/include/asm/sections.h b/arch/mips/include/asm/sections.h
deleted file mode 100644
index b7e3726..0000000
--- a/arch/mips/include/asm/sections.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_SECTIONS_H
-#define _ASM_SECTIONS_H
-
-#include <asm-generic/sections.h>
-
-#endif /* _ASM_SECTIONS_H */
diff --git a/arch/mips/include/asm/segment.h b/arch/mips/include/asm/segment.h
deleted file mode 100644
index 92ac001..0000000
--- a/arch/mips/include/asm/segment.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_SEGMENT_H
-#define _ASM_SEGMENT_H
-
-/* Only here because we have some old header files that expect it.. */
-
-#endif /* _ASM_SEGMENT_H */
diff --git a/arch/mips/include/asm/serial.h b/arch/mips/include/asm/serial.h
deleted file mode 100644
index a0cb0caf..0000000
--- a/arch/mips/include/asm/serial.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/serial.h>
diff --git a/arch/mips/include/asm/ucontext.h b/arch/mips/include/asm/ucontext.h
deleted file mode 100644
index 9bc07b9..0000000
--- a/arch/mips/include/asm/ucontext.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/ucontext.h>
diff --git a/arch/mips/include/asm/xor.h b/arch/mips/include/asm/xor.h
deleted file mode 100644
index c82eb12..0000000
--- a/arch/mips/include/asm/xor.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/xor.h>
diff --git a/arch/mips/include/uapi/asm/Kbuild b/arch/mips/include/uapi/asm/Kbuild
index 350cccc..be7196e 100644
--- a/arch/mips/include/uapi/asm/Kbuild
+++ b/arch/mips/include/uapi/asm/Kbuild
@@ -1,7 +1,9 @@
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
-header-y += auxvec.h
+generic-y += auxvec.h
+generic-y += ipcbuf.h
+
header-y += bitsperlong.h
header-y += break.h
header-y += byteorder.h
@@ -11,7 +13,6 @@
header-y += inst.h
header-y += ioctl.h
header-y += ioctls.h
-header-y += ipcbuf.h
header-y += kvm_para.h
header-y += mman.h
header-y += msgbuf.h
diff --git a/arch/mips/include/uapi/asm/auxvec.h b/arch/mips/include/uapi/asm/auxvec.h
deleted file mode 100644
index 7cf7f2d..0000000
--- a/arch/mips/include/uapi/asm/auxvec.h
+++ /dev/null
@@ -1,4 +0,0 @@
-#ifndef _ASM_AUXVEC_H
-#define _ASM_AUXVEC_H
-
-#endif /* _ASM_AUXVEC_H */
diff --git a/arch/mips/include/uapi/asm/ipcbuf.h b/arch/mips/include/uapi/asm/ipcbuf.h
deleted file mode 100644
index 84c7e51..0000000
--- a/arch/mips/include/uapi/asm/ipcbuf.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/ipcbuf.h>
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index 4c6167a..37663c7 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -852,10 +852,17 @@
case PRID_IMP_CAVIUM_CN63XX:
case PRID_IMP_CAVIUM_CN66XX:
case PRID_IMP_CAVIUM_CN68XX:
+ case PRID_IMP_CAVIUM_CNF71XX:
c->cputype = CPU_CAVIUM_OCTEON2;
__cpu_name[cpu] = "Cavium Octeon II";
set_elf_platform(cpu, "octeon2");
break;
+ case PRID_IMP_CAVIUM_CN70XX:
+ case PRID_IMP_CAVIUM_CN78XX:
+ c->cputype = CPU_CAVIUM_OCTEON3;
+ __cpu_name[cpu] = "Cavium Octeon III";
+ set_elf_platform(cpu, "octeon3");
+ break;
default:
printk(KERN_INFO "Unknown Octeon chip!\n");
c->cputype = CPU_UNKNOWN;
@@ -899,6 +906,11 @@
MIPS_CPU_LLSC);
switch (c->processor_id & 0xff00) {
+ case PRID_IMP_NETLOGIC_XLP2XX:
+ c->cputype = CPU_XLP;
+ __cpu_name[cpu] = "Broadcom XLPII";
+ break;
+
case PRID_IMP_NETLOGIC_XLP8XX:
case PRID_IMP_NETLOGIC_XLP3XX:
c->cputype = CPU_XLP;
diff --git a/arch/mips/kernel/csrc-ioasic.c b/arch/mips/kernel/csrc-ioasic.c
index 0654bff..87e88fe 100644
--- a/arch/mips/kernel/csrc-ioasic.c
+++ b/arch/mips/kernel/csrc-ioasic.c
@@ -41,9 +41,9 @@
{
unsigned int freq;
u32 start, end;
- int i = HZ / 10;
+ int i = HZ / 8;
-
+ ds1287_timer_state();
while (!ds1287_timer_state())
;
@@ -55,7 +55,7 @@
end = dec_ioasic_hpt_read(&clocksource_dec);
- freq = (end - start) * 10;
+ freq = (end - start) * 8;
printk(KERN_INFO "I/O ASIC clock frequency %dHz\n", freq);
clocksource_dec.rating = 200 + freq / 10000000;
diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c
index 0c655de..42f8875 100644
--- a/arch/mips/kernel/idle.c
+++ b/arch/mips/kernel/idle.c
@@ -166,6 +166,7 @@
case CPU_CAVIUM_OCTEON:
case CPU_CAVIUM_OCTEON_PLUS:
case CPU_CAVIUM_OCTEON2:
+ case CPU_CAVIUM_OCTEON3:
case CPU_JZRISC:
case CPU_LOONGSON1:
case CPU_XLR:
diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S
index a03e93c..539b629 100644
--- a/arch/mips/kernel/mcount.S
+++ b/arch/mips/kernel/mcount.S
@@ -83,7 +83,7 @@
PTR_S MCOUNT_RA_ADDRESS_REG, PT_R12(sp)
#endif
- move a0, ra /* arg1: self return address */
+ PTR_SUBU a0, ra, 8 /* arg1: self address */
.globl ftrace_call
ftrace_call:
nop /* a placeholder for the call to a real tracing function */
diff --git a/arch/mips/kernel/relocate_kernel.S b/arch/mips/kernel/relocate_kernel.S
index 43d2d78..74bab9d 100644
--- a/arch/mips/kernel/relocate_kernel.S
+++ b/arch/mips/kernel/relocate_kernel.S
@@ -26,6 +26,12 @@
PTR_L s2, (s0)
PTR_ADD s0, s0, SZREG
+ /*
+ * In case of a kdump/crash kernel, the indirection page is not
+ * populated as the kernel is directly copied to a reserved location
+ */
+ beqz s2, done
+
/* destination page */
and s3, s2, 0x1
beq s3, zero, 1f
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index c7f9051..c538d6e 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -552,6 +552,52 @@
add_memory_region(mem, size, type);
}
+#ifdef CONFIG_KEXEC
+static inline unsigned long long get_total_mem(void)
+{
+ unsigned long long total;
+
+ total = max_pfn - min_low_pfn;
+ return total << PAGE_SHIFT;
+}
+
+static void __init mips_parse_crashkernel(void)
+{
+ unsigned long long total_mem;
+ unsigned long long crash_size, crash_base;
+ int ret;
+
+ total_mem = get_total_mem();
+ ret = parse_crashkernel(boot_command_line, total_mem,
+ &crash_size, &crash_base);
+ if (ret != 0 || crash_size <= 0)
+ return;
+
+ crashk_res.start = crash_base;
+ crashk_res.end = crash_base + crash_size - 1;
+}
+
+static void __init request_crashkernel(struct resource *res)
+{
+ int ret;
+
+ ret = request_resource(res, &crashk_res);
+ if (!ret)
+ pr_info("Reserving %ldMB of memory at %ldMB for crashkernel\n",
+ (unsigned long)((crashk_res.end -
+ crashk_res.start + 1) >> 20),
+ (unsigned long)(crashk_res.start >> 20));
+}
+#else /* !defined(CONFIG_KEXEC) */
+static void __init mips_parse_crashkernel(void)
+{
+}
+
+static void __init request_crashkernel(struct resource *res)
+{
+}
+#endif /* !defined(CONFIG_KEXEC) */
+
static void __init arch_mem_init(char **cmdline_p)
{
extern void plat_mem_setup(void);
@@ -608,6 +654,8 @@
BOOTMEM_DEFAULT);
}
#endif
+
+ mips_parse_crashkernel();
#ifdef CONFIG_KEXEC
if (crashk_res.start != crashk_res.end)
reserve_bootmem(crashk_res.start,
@@ -620,52 +668,6 @@
paging_init();
}
-#ifdef CONFIG_KEXEC
-static inline unsigned long long get_total_mem(void)
-{
- unsigned long long total;
-
- total = max_pfn - min_low_pfn;
- return total << PAGE_SHIFT;
-}
-
-static void __init mips_parse_crashkernel(void)
-{
- unsigned long long total_mem;
- unsigned long long crash_size, crash_base;
- int ret;
-
- total_mem = get_total_mem();
- ret = parse_crashkernel(boot_command_line, total_mem,
- &crash_size, &crash_base);
- if (ret != 0 || crash_size <= 0)
- return;
-
- crashk_res.start = crash_base;
- crashk_res.end = crash_base + crash_size - 1;
-}
-
-static void __init request_crashkernel(struct resource *res)
-{
- int ret;
-
- ret = request_resource(res, &crashk_res);
- if (!ret)
- pr_info("Reserving %ldMB of memory at %ldMB for crashkernel\n",
- (unsigned long)((crashk_res.end -
- crashk_res.start + 1) >> 20),
- (unsigned long)(crashk_res.start >> 20));
-}
-#else /* !defined(CONFIG_KEXEC) */
-static void __init mips_parse_crashkernel(void)
-{
-}
-
-static void __init request_crashkernel(struct resource *res)
-{
-}
-#endif /* !defined(CONFIG_KEXEC) */
-
static void __init resource_init(void)
{
int i;
@@ -678,11 +680,6 @@
data_resource.start = __pa_symbol(&_etext);
data_resource.end = __pa_symbol(&_edata) - 1;
- /*
- * Request address space for all standard RAM.
- */
- mips_parse_crashkernel();
-
for (i = 0; i < boot_mem_map.nr_map; i++) {
struct resource *res;
unsigned long start, end;
diff --git a/arch/mips/kernel/time.c b/arch/mips/kernel/time.c
index 9d686bf..364d26a 100644
--- a/arch/mips/kernel/time.c
+++ b/arch/mips/kernel/time.c
@@ -121,6 +121,14 @@
{
plat_time_init();
- if (!mips_clockevent_init() || !cpu_has_mfc0_count_bug())
+ /*
+ * The use of the R4k timer as a clock event takes precedence;
+ * if reading the Count register might interfere with the timer
+ * interrupt, then we don't use the timer as a clock source.
+ * We may still use the timer as a clock source though if the
+ * timer interrupt isn't reliable; the interference doesn't
+ * matter then, because we don't use the interrupt.
+ */
+ if (mips_clockevent_init() != 0 || !cpu_has_mfc0_count_bug())
init_mips_clocksource();
}
diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S
index 05826d2..3b46f7c 100644
--- a/arch/mips/kernel/vmlinux.lds.S
+++ b/arch/mips/kernel/vmlinux.lds.S
@@ -179,5 +179,6 @@
*(.options)
*(.pdr)
*(.reginfo)
+ *(.eh_frame)
}
}
diff --git a/arch/mips/lantiq/falcon/sysctrl.c b/arch/mips/lantiq/falcon/sysctrl.c
index ff4894a..8f1866d 100644
--- a/arch/mips/lantiq/falcon/sysctrl.c
+++ b/arch/mips/lantiq/falcon/sysctrl.c
@@ -48,6 +48,7 @@
#define CPU0CC_CPUDIV 0x0001
/* Activation Status Register */
+#define ACTS_ASC0_ACT 0x00001000
#define ACTS_ASC1_ACT 0x00000800
#define ACTS_I2C_ACT 0x00004000
#define ACTS_P0 0x00010000
@@ -108,6 +109,7 @@
static int sysctl_clken(struct clk *clk)
{
sysctl_w32(clk->module, clk->bits, SYSCTL_CLKEN);
+ sysctl_w32(clk->module, clk->bits, SYSCTL_ACT);
sysctl_wait(clk, clk->bits, SYSCTL_CLKS);
return 0;
}
@@ -256,6 +258,7 @@
clkdev_add_sys("1e800400.pad", SYSCTL_SYS1, ACTS_PADCTRL1);
clkdev_add_sys("1e800500.pad", SYSCTL_SYS1, ACTS_PADCTRL3);
clkdev_add_sys("1e800600.pad", SYSCTL_SYS1, ACTS_PADCTRL4);
- clkdev_add_sys("1e100C00.serial", SYSCTL_SYS1, ACTS_ASC1_ACT);
+ clkdev_add_sys("1e100b00.serial", SYSCTL_SYS1, ACTS_ASC1_ACT);
+ clkdev_add_sys("1e100c00.serial", SYSCTL_SYS1, ACTS_ASC0_ACT);
clkdev_add_sys("1e200000.i2c", SYSCTL_SYS1, ACTS_I2C_ACT);
}
diff --git a/arch/mips/lantiq/xway/Makefile b/arch/mips/lantiq/xway/Makefile
index 7a13660..087497d 100644
--- a/arch/mips/lantiq/xway/Makefile
+++ b/arch/mips/lantiq/xway/Makefile
@@ -1,3 +1,3 @@
-obj-y := prom.o sysctrl.o clk.o reset.o dma.o gptu.o
+obj-y := prom.o sysctrl.o clk.o reset.o dma.o gptu.o dcdc.o
obj-$(CONFIG_XRX200_PHY_FW) += xrx200_phy_fw.o
diff --git a/arch/mips/lantiq/xway/dcdc.c b/arch/mips/lantiq/xway/dcdc.c
new file mode 100644
index 0000000..7688ac0
--- /dev/null
+++ b/arch/mips/lantiq/xway/dcdc.c
@@ -0,0 +1,63 @@
+/*
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ * Copyright (C) 2012 John Crispin <blogic@openwrt.org>
+ * Copyright (C) 2010 Sameer Ahmad, Lantiq GmbH
+ */
+
+#include <linux/ioport.h>
+#include <linux/of_platform.h>
+
+#include <lantiq_soc.h>
+
+/* Bias and regulator Setup Register */
+#define DCDC_BIAS_VREG0 0xa
+/* Bias and regulator Setup Register */
+#define DCDC_BIAS_VREG1 0xb
+
+#define dcdc_w8(x, y) ltq_w8((x), dcdc_membase + (y))
+#define dcdc_r8(x) ltq_r8(dcdc_membase + (x))
+
+static void __iomem *dcdc_membase;
+
+static int dcdc_probe(struct platform_device *pdev)
+{
+ struct resource *res;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ dcdc_membase = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(dcdc_membase))
+ return PTR_ERR(dcdc_membase);
+
+ dev_info(&pdev->dev, "Core Voltage : %d mV\n",
+ dcdc_r8(DCDC_BIAS_VREG1) * 8);
+
+ return 0;
+}
+
+static const struct of_device_id dcdc_match[] = {
+ { .compatible = "lantiq,dcdc-xrx200" },
+ {},
+};
+
+static struct platform_driver dcdc_driver = {
+ .probe = dcdc_probe,
+ .driver = {
+ .name = "dcdc-xrx200",
+ .owner = THIS_MODULE,
+ .of_match_table = dcdc_match,
+ },
+};
+
+int __init dcdc_init(void)
+{
+ int ret = platform_driver_register(&dcdc_driver);
+
+ if (ret)
+ pr_info("dcdc: Error registering platform driver\n");
+ return ret;
+}
+
+arch_initcall(dcdc_init);
diff --git a/arch/mips/lasat/image/Makefile b/arch/mips/lasat/image/Makefile
index dfb509d..fd32075 100644
--- a/arch/mips/lasat/image/Makefile
+++ b/arch/mips/lasat/image/Makefile
@@ -13,13 +13,11 @@
MKLASATIMG = mklasatimg
MKLASATIMG_ARCH = mq2,mqpro,sp100,sp200
KERNEL_IMAGE = vmlinux
-KERNEL_START = $(shell $(NM) $(KERNEL_IMAGE) | grep " _text" | cut -f1 -d\ )
-KERNEL_ENTRY = $(shell $(NM) $(KERNEL_IMAGE) | grep kernel_entry | cut -f1 -d\ )
LDSCRIPT= -L$(srctree)/$(src) -Tromscript.normal
-HEAD_DEFINES := -D_kernel_start=0x$(KERNEL_START) \
- -D_kernel_entry=0x$(KERNEL_ENTRY) \
+HEAD_DEFINES := -D_kernel_start=$(VMLINUX_LOAD_ADDRESS) \
+ -D_kernel_entry=$(VMLINUX_ENTRY_ADDRESS) \
-D VERSION="\"$(Version)\"" \
-D TIMESTAMP=$(shell date +%s)
diff --git a/arch/mips/loongson/common/Makefile b/arch/mips/loongson/common/Makefile
index 4c57b3e..9e4484c 100644
--- a/arch/mips/loongson/common/Makefile
+++ b/arch/mips/loongson/common/Makefile
@@ -3,8 +3,9 @@
#
obj-y += setup.o init.o cmdline.o env.o time.o reset.o irq.o \
- pci.o bonito-irq.o mem.o machtype.o platform.o
+ bonito-irq.o mem.o machtype.o platform.o
obj-$(CONFIG_GPIOLIB) += gpio.o
+obj-$(CONFIG_PCI) += pci.o
#
# Serial port support
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index 46048d2..efe0088 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -436,7 +436,6 @@
break;
default:
return SIGILL;
- break;
}
break;
case mm_32f_74_op: /* c.cond.fmt */
@@ -451,12 +450,10 @@
break;
default:
return SIGILL;
- break;
}
break;
default:
return SIGILL;
- break;
}
*insn_ptr = mips32_insn;
@@ -491,7 +488,6 @@
dec_insn.next_pc_inc;
*contpc = regs->regs[insn.mm_i_format.rs];
return 1;
- break;
}
}
break;
@@ -513,7 +509,6 @@
dec_insn.pc_inc +
dec_insn.next_pc_inc;
return 1;
- break;
case mm_bgezals_op:
case mm_bgezal_op:
regs->regs[31] = regs->cp0_epc +
@@ -530,7 +525,6 @@
dec_insn.pc_inc +
dec_insn.next_pc_inc;
return 1;
- break;
case mm_blez_op:
if ((long)regs->regs[insn.mm_i_format.rs] <= 0)
*contpc = regs->cp0_epc +
@@ -541,7 +535,6 @@
dec_insn.pc_inc +
dec_insn.next_pc_inc;
return 1;
- break;
case mm_bgtz_op:
if ((long)regs->regs[insn.mm_i_format.rs] <= 0)
*contpc = regs->cp0_epc +
@@ -552,7 +545,6 @@
dec_insn.pc_inc +
dec_insn.next_pc_inc;
return 1;
- break;
case mm_bc2f_op:
case mm_bc1f_op:
bc_false = 1;
@@ -580,7 +572,6 @@
*contpc = regs->cp0_epc +
dec_insn.pc_inc + dec_insn.next_pc_inc;
return 1;
- break;
}
break;
case mm_pool16c_op:
@@ -593,7 +584,6 @@
case mm_jr16_op:
*contpc = regs->regs[insn.mm_i_format.rs];
return 1;
- break;
}
break;
case mm_beqz16_op:
@@ -605,7 +595,6 @@
*contpc = regs->cp0_epc +
dec_insn.pc_inc + dec_insn.next_pc_inc;
return 1;
- break;
case mm_bnez16_op:
if ((long)regs->regs[reg16to32map[insn.mm_b1_format.rs]] != 0)
*contpc = regs->cp0_epc +
@@ -615,12 +604,10 @@
*contpc = regs->cp0_epc +
dec_insn.pc_inc + dec_insn.next_pc_inc;
return 1;
- break;
case mm_b16_op:
*contpc = regs->cp0_epc + dec_insn.pc_inc +
(insn.mm_b0_format.simmediate << 1);
return 1;
- break;
case mm_beq32_op:
if (regs->regs[insn.mm_i_format.rs] ==
regs->regs[insn.mm_i_format.rt])
@@ -632,7 +619,6 @@
dec_insn.pc_inc +
dec_insn.next_pc_inc;
return 1;
- break;
case mm_bne32_op:
if (regs->regs[insn.mm_i_format.rs] !=
regs->regs[insn.mm_i_format.rt])
@@ -643,7 +629,6 @@
*contpc = regs->cp0_epc +
dec_insn.pc_inc + dec_insn.next_pc_inc;
return 1;
- break;
case mm_jalx32_op:
regs->regs[31] = regs->cp0_epc +
dec_insn.pc_inc + dec_insn.next_pc_inc;
@@ -652,7 +637,6 @@
*contpc <<= 28;
*contpc |= (insn.j_format.target << 2);
return 1;
- break;
case mm_jals32_op:
case mm_jal32_op:
regs->regs[31] = regs->cp0_epc +
@@ -665,7 +649,6 @@
*contpc |= (insn.j_format.target << 1);
set_isa16_mode(*contpc);
return 1;
- break;
}
return 0;
}
@@ -694,7 +677,6 @@
case jr_op:
*contpc = regs->regs[insn.r_format.rs];
return 1;
- break;
}
break;
case bcond_op:
@@ -716,7 +698,6 @@
dec_insn.pc_inc +
dec_insn.next_pc_inc;
return 1;
- break;
case bgezal_op:
case bgezall_op:
regs->regs[31] = regs->cp0_epc +
@@ -734,7 +715,6 @@
dec_insn.pc_inc +
dec_insn.next_pc_inc;
return 1;
- break;
}
break;
case jalx_op:
@@ -752,7 +732,6 @@
/* Set microMIPS mode bit: XOR for jalx. */
*contpc ^= bit;
return 1;
- break;
case beq_op:
case beql_op:
if (regs->regs[insn.i_format.rs] ==
@@ -765,7 +744,6 @@
dec_insn.pc_inc +
dec_insn.next_pc_inc;
return 1;
- break;
case bne_op:
case bnel_op:
if (regs->regs[insn.i_format.rs] !=
@@ -778,7 +756,6 @@
dec_insn.pc_inc +
dec_insn.next_pc_inc;
return 1;
- break;
case blez_op:
case blezl_op:
if ((long)regs->regs[insn.i_format.rs] <= 0)
@@ -790,7 +767,6 @@
dec_insn.pc_inc +
dec_insn.next_pc_inc;
return 1;
- break;
case bgtz_op:
case bgtzl_op:
if ((long)regs->regs[insn.i_format.rs] > 0)
@@ -802,7 +778,6 @@
dec_insn.pc_inc +
dec_insn.next_pc_inc;
return 1;
- break;
#ifdef CONFIG_CPU_CAVIUM_OCTEON
case lwc2_op: /* This is bbit0 on Octeon */
if ((regs->regs[insn.i_format.rs] & (1ull<<insn.i_format.rt)) == 0)
@@ -856,7 +831,6 @@
dec_insn.pc_inc +
dec_insn.next_pc_inc;
return 1;
- break;
case 1: /* bc1t */
case 3: /* bc1tl */
if (fcr31 & (1 << bit))
@@ -868,7 +842,6 @@
dec_insn.pc_inc +
dec_insn.next_pc_inc;
return 1;
- break;
}
}
break;
diff --git a/arch/mips/mm/c-octeon.c b/arch/mips/mm/c-octeon.c
index a0bcdbb..729e770 100644
--- a/arch/mips/mm/c-octeon.c
+++ b/arch/mips/mm/c-octeon.c
@@ -224,6 +224,20 @@
c->options |= MIPS_CPU_PREFETCH;
break;
+ case CPU_CAVIUM_OCTEON3:
+ c->icache.linesz = 128;
+ c->icache.sets = 16;
+ c->icache.ways = 39;
+ c->icache.flags |= MIPS_CACHE_VTAG;
+ icache_size = c->icache.sets * c->icache.ways * c->icache.linesz;
+
+ c->dcache.linesz = 128;
+ c->dcache.ways = 32;
+ c->dcache.sets = 8;
+ dcache_size = c->dcache.sets * c->dcache.ways * c->dcache.linesz;
+ c->options |= MIPS_CPU_PREFETCH;
+ break;
+
default:
panic("Unsupported Cavium Networks CPU type");
break;
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
index aaccf1c..664e5236 100644
--- a/arch/mips/mm/dma-default.c
+++ b/arch/mips/mm/dma-default.c
@@ -50,16 +50,20 @@
}
/*
+ * The affected CPUs below in 'cpu_needs_post_dma_flush()' can
+ * speculatively fill random cachelines with stale data at any time,
+ * requiring an extra flush post-DMA.
+ *
* Warning on the terminology - Linux calls an uncached area coherent;
* MIPS terminology calls memory areas with hardware maintained coherency
* coherent.
*/
-
-static inline int cpu_is_noncoherent_r10000(struct device *dev)
+static inline int cpu_needs_post_dma_flush(struct device *dev)
{
return !plat_device_is_coherent(dev) &&
- (current_cpu_type() == CPU_R10000 ||
- current_cpu_type() == CPU_R12000);
+ (boot_cpu_type() == CPU_R10000 ||
+ boot_cpu_type() == CPU_R12000 ||
+ boot_cpu_type() == CPU_BMIPS5000);
}
static gfp_t massage_gfp_flags(const struct device *dev, gfp_t gfp)
@@ -230,7 +234,7 @@
static void mips_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
size_t size, enum dma_data_direction direction, struct dma_attrs *attrs)
{
- if (cpu_is_noncoherent_r10000(dev))
+ if (cpu_needs_post_dma_flush(dev))
__dma_sync(dma_addr_to_page(dev, dma_addr),
dma_addr & ~PAGE_MASK, size, direction);
@@ -284,7 +288,7 @@
static void mips_dma_sync_single_for_cpu(struct device *dev,
dma_addr_t dma_handle, size_t size, enum dma_data_direction direction)
{
- if (cpu_is_noncoherent_r10000(dev))
+ if (cpu_needs_post_dma_flush(dev))
__dma_sync(dma_addr_to_page(dev, dma_handle),
dma_handle & ~PAGE_MASK, size, direction);
}
@@ -305,7 +309,7 @@
/* Make sure that gcc doesn't leave the empty loop body. */
for (i = 0; i < nelems; i++, sg++) {
- if (cpu_is_noncoherent_r10000(dev))
+ if (cpu_needs_post_dma_flush(dev))
__dma_sync(sg_page(sg), sg->offset, sg->length,
direction);
}
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index 85df1cd..becc42b 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -42,8 +42,7 @@
const int field = sizeof(unsigned long) * 2;
siginfo_t info;
int fault;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (write ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
#if 0
printk("Cpu%d[%s:%d:%0*lx:%ld:%0*lx]\n", raw_smp_processor_id(),
@@ -93,6 +92,8 @@
if (in_atomic() || !mm)
goto bad_area_nosemaphore;
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
@@ -114,6 +115,7 @@
if (write) {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
} else {
if (cpu_has_rixi) {
if (address == regs->cp0_epc && !(vma->vm_flags & VM_EXEC)) {
@@ -241,6 +243,8 @@
* (which will retry the fault, or kill us if we got oom-killed).
*/
up_read(&mm->mmap_sem);
+ if (!user_mode(regs))
+ goto no_context;
pagefault_out_of_memory();
return;
diff --git a/arch/mips/mm/gup.c b/arch/mips/mm/gup.c
index d4ea5c9..06ce17c 100644
--- a/arch/mips/mm/gup.c
+++ b/arch/mips/mm/gup.c
@@ -12,6 +12,7 @@
#include <linux/swap.h>
#include <linux/hugetlb.h>
+#include <asm/cpu-features.h>
#include <asm/pgtable.h>
static inline pte_t gup_get_pte(pte_t *ptep)
@@ -273,7 +274,7 @@
len = (unsigned long) nr_pages << PAGE_SHIFT;
end = start + len;
- if (end < start)
+ if (end < start || cpu_has_dc_aliases)
goto slow_irqon;
/* XXX: batch / limit 'nr' */
diff --git a/arch/mips/mm/hugetlbpage.c b/arch/mips/mm/hugetlbpage.c
index a7fee0d..01fda44 100644
--- a/arch/mips/mm/hugetlbpage.c
+++ b/arch/mips/mm/hugetlbpage.c
@@ -85,6 +85,11 @@
return (pud_val(pud) & _PAGE_HUGE) != 0;
}
+int pmd_huge_support(void)
+{
+ return 1;
+}
+
struct page *
follow_huge_pmd(struct mm_struct *mm, unsigned long address,
pmd_t *pmd, int write)
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index 4e73f10..e205ef5 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -254,6 +254,7 @@
SetPageDcacheDirty(page);
}
}
+EXPORT_SYMBOL_GPL(copy_from_user_page);
void __init fixrange_init(unsigned long start, unsigned long end,
pgd_t *pgd_base)
diff --git a/arch/mips/mm/tlb-funcs.S b/arch/mips/mm/tlb-funcs.S
index 30a494d..79bca31 100644
--- a/arch/mips/mm/tlb-funcs.S
+++ b/arch/mips/mm/tlb-funcs.S
@@ -16,10 +16,12 @@
#define FASTPATH_SIZE 128
+#ifdef CONFIG_MIPS_PGD_C0_CONTEXT
LEAF(tlbmiss_handler_setup_pgd)
.space 16 * 4
END(tlbmiss_handler_setup_pgd)
EXPORT(tlbmiss_handler_setup_pgd_end)
+#endif
LEAF(handle_tlbm)
.space FASTPATH_SIZE * 4
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index 556cb48..821b451 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -85,6 +85,7 @@
case CPU_CAVIUM_OCTEON:
case CPU_CAVIUM_OCTEON_PLUS:
case CPU_CAVIUM_OCTEON2:
+ case CPU_CAVIUM_OCTEON3:
return 1;
default:
return 0;
@@ -95,6 +96,7 @@
{
switch (current_cpu_type()) {
case CPU_CAVIUM_OCTEON2:
+ case CPU_CAVIUM_OCTEON3:
return 1;
default:
return 0;
diff --git a/arch/mips/netlogic/Kconfig b/arch/mips/netlogic/Kconfig
index 2447bf9..852a4ee 100644
--- a/arch/mips/netlogic/Kconfig
+++ b/arch/mips/netlogic/Kconfig
@@ -19,6 +19,15 @@
pointer to the kernel. The corresponding DTS file is at
arch/mips/netlogic/dts/xlp_svp.dts
+config DT_XLP_FVP
+ bool "Built-in device tree for XLP FVP boards"
+ default y
+ help
+ Add an FDT blob for XLP FVP board into the kernel.
+ This DTB will be used if the firmware does not pass in a DTB
+ pointer to the kernel. The corresponding DTS file is at
+ arch/mips/netlogic/dts/xlp_fvp.dts
+
config NLM_MULTINODE
bool "Support for multi-chip boards"
depends on NLM_XLP_BOARD
diff --git a/arch/mips/netlogic/common/smp.c b/arch/mips/netlogic/common/smp.c
index 4e35d9c..6f8feb9 100644
--- a/arch/mips/netlogic/common/smp.c
+++ b/arch/mips/netlogic/common/smp.c
@@ -106,9 +106,7 @@
{
change_c0_config(CONF_CM_CMASK, 0x3);
#ifdef CONFIG_CPU_XLP
- /* mmu init, once per core */
- if (cpu % NLM_THREADS_PER_CORE == 0)
- xlp_mmu_init();
+ xlp_mmu_init();
#endif
write_c0_ebase(nlm_current_node()->ebase);
}
diff --git a/arch/mips/netlogic/common/time.c b/arch/mips/netlogic/common/time.c
index 045a396..13391b8 100644
--- a/arch/mips/netlogic/common/time.c
+++ b/arch/mips/netlogic/common/time.c
@@ -45,6 +45,7 @@
#if defined(CONFIG_CPU_XLP)
#include <asm/netlogic/xlp-hal/iomap.h>
#include <asm/netlogic/xlp-hal/xlp.h>
+#include <asm/netlogic/xlp-hal/sys.h>
#include <asm/netlogic/xlp-hal/pic.h>
#elif defined(CONFIG_CPU_XLR)
#include <asm/netlogic/xlr/iomap.h>
@@ -91,7 +92,7 @@
csrc_pic.read = nlm_get_pic_timer;
}
csrc_pic.rating = 1000;
- clocksource_register_hz(&csrc_pic, PIC_CLK_HZ);
+ clocksource_register_hz(&csrc_pic, pic_timer_freq());
}
void __init plat_time_init(void)
diff --git a/arch/mips/netlogic/dts/Makefile b/arch/mips/netlogic/dts/Makefile
index aecb6fa..0b9be5f 100644
--- a/arch/mips/netlogic/dts/Makefile
+++ b/arch/mips/netlogic/dts/Makefile
@@ -1,2 +1,3 @@
obj-$(CONFIG_DT_XLP_EVP) := xlp_evp.dtb.o
obj-$(CONFIG_DT_XLP_SVP) += xlp_svp.dtb.o
+obj-$(CONFIG_DT_XLP_FVP) += xlp_fvp.dtb.o
diff --git a/arch/mips/netlogic/dts/xlp_evp.dts b/arch/mips/netlogic/dts/xlp_evp.dts
index 0640703..89ad048 100644
--- a/arch/mips/netlogic/dts/xlp_evp.dts
+++ b/arch/mips/netlogic/dts/xlp_evp.dts
@@ -9,19 +9,12 @@
#address-cells = <2>;
#size-cells = <2>;
- memory {
- device_type = "memory";
- reg = <0 0x00100000 0 0x0FF00000 // 255M at 1M
- 0 0x20000000 0 0xa0000000 // 2560M at 512M
- 0 0xe0000000 1 0x00000000>;
- };
-
soc {
#address-cells = <2>;
#size-cells = <1>;
compatible = "simple-bus";
ranges = <0 0 0 0x18000000 0x04000000 // PCIe CFG
- 1 0 0 0x16000000 0x01000000>; // GBU chipselects
+ 1 0 0 0x16000000 0x02000000>; // GBU chipselects
serial0: serial@30000 {
device_type = "serial";
diff --git a/arch/mips/netlogic/dts/xlp_fvp.dts b/arch/mips/netlogic/dts/xlp_fvp.dts
new file mode 100644
index 0000000..63e62b7
--- /dev/null
+++ b/arch/mips/netlogic/dts/xlp_fvp.dts
@@ -0,0 +1,118 @@
+/*
+ * XLP2XX Device Tree Source for FVP boards
+ */
+
+/dts-v1/;
+/ {
+ model = "netlogic,XLP-FVP";
+ compatible = "netlogic,xlp";
+ #address-cells = <2>;
+ #size-cells = <2>;
+
+ soc {
+ #address-cells = <2>;
+ #size-cells = <1>;
+ compatible = "simple-bus";
+ ranges = <0 0 0 0x18000000 0x04000000 // PCIe CFG
+ 1 0 0 0x16000000 0x02000000>; // GBU chipselects
+
+ serial0: serial@30000 {
+ device_type = "serial";
+ compatible = "ns16550";
+ reg = <0 0x30100 0xa00>;
+ reg-shift = <2>;
+ reg-io-width = <4>;
+ clock-frequency = <133333333>;
+ interrupt-parent = <&pic>;
+ interrupts = <17>;
+ };
+ serial1: serial@31000 {
+ device_type = "serial";
+ compatible = "ns16550";
+ reg = <0 0x31100 0xa00>;
+ reg-shift = <2>;
+ reg-io-width = <4>;
+ clock-frequency = <133333333>;
+ interrupt-parent = <&pic>;
+ interrupts = <18>;
+ };
+ i2c0: ocores@37100 {
+ compatible = "opencores,i2c-ocores";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <0 0x37100 0x20>;
+ reg-shift = <2>;
+ reg-io-width = <4>;
+ clock-frequency = <32000000>;
+ interrupt-parent = <&pic>;
+ interrupts = <30>;
+ };
+ i2c1: ocores@37120 {
+ compatible = "opencores,i2c-ocores";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <0 0x37120 0x20>;
+ reg-shift = <2>;
+ reg-io-width = <4>;
+ clock-frequency = <32000000>;
+ interrupt-parent = <&pic>;
+ interrupts = <31>;
+
+ rtc@68 {
+ compatible = "dallas,ds1374";
+ reg = <0x68>;
+ };
+
+ dtt@4c {
+ compatible = "national,lm90";
+ reg = <0x4c>;
+ };
+ };
+ pic: pic@4000 {
+ compatible = "netlogic,xlp-pic";
+ #address-cells = <0>;
+ #interrupt-cells = <1>;
+ reg = <0 0x4000 0x200>;
+ interrupt-controller;
+ };
+
+ nor_flash@1,0 {
+ compatible = "cfi-flash";
+ #address-cells = <1>;
+ #size-cells = <1>;
+ bank-width = <2>;
+ reg = <1 0 0x1000000>;
+
+ partition@0 {
+ label = "x-loader";
+ reg = <0x0 0x100000>; /* 1M */
+ read-only;
+ };
+
+ partition@100000 {
+ label = "u-boot";
+ reg = <0x100000 0x100000>; /* 1M */
+ };
+
+ partition@200000 {
+ label = "kernel";
+ reg = <0x200000 0x500000>; /* 5M */
+ };
+
+ partition@700000 {
+ label = "rootfs";
+ reg = <0x700000 0x800000>; /* 8M */
+ };
+
+ partition@f00000 {
+ label = "env";
+ reg = <0xf00000 0x100000>; /* 1M */
+ read-only;
+ };
+ };
+ };
+
+ chosen {
+ bootargs = "console=ttyS0,115200 rdinit=/sbin/init";
+ };
+};
diff --git a/arch/mips/netlogic/dts/xlp_svp.dts b/arch/mips/netlogic/dts/xlp_svp.dts
index 9c5db10..1ebd00ed 100644
--- a/arch/mips/netlogic/dts/xlp_svp.dts
+++ b/arch/mips/netlogic/dts/xlp_svp.dts
@@ -9,19 +9,12 @@
#address-cells = <2>;
#size-cells = <2>;
- memory {
- device_type = "memory";
- reg = <0 0x00100000 0 0x0FF00000 // 255M at 1M
- 0 0x20000000 0 0xa0000000 // 2560M at 512M
- 0 0xe0000000 0 0x40000000>;
- };
-
soc {
#address-cells = <2>;
#size-cells = <1>;
compatible = "simple-bus";
ranges = <0 0 0 0x18000000 0x04000000 // PCIe CFG
- 1 0 0 0x16000000 0x01000000>; // GBU chipselects
+ 1 0 0 0x16000000 0x02000000>; // GBU chipselects
serial0: serial@30000 {
device_type = "serial";
diff --git a/arch/mips/netlogic/xlp/Makefile b/arch/mips/netlogic/xlp/Makefile
index 85ac4a8..ed9a93c 100644
--- a/arch/mips/netlogic/xlp/Makefile
+++ b/arch/mips/netlogic/xlp/Makefile
@@ -1,3 +1,4 @@
obj-y += setup.o nlm_hal.o cop2-ex.o dt.o
obj-$(CONFIG_SMP) += wakeup.o
obj-$(CONFIG_USB) += usb-init.o
+obj-$(CONFIG_USB) += usb-init-xlp2.o
diff --git a/arch/mips/netlogic/xlp/dt.c b/arch/mips/netlogic/xlp/dt.c
index a15cdbb..88df445 100644
--- a/arch/mips/netlogic/xlp/dt.c
+++ b/arch/mips/netlogic/xlp/dt.c
@@ -39,12 +39,18 @@
#include <linux/of_platform.h>
#include <linux/of_device.h>
-extern u32 __dtb_xlp_evp_begin[], __dtb_xlp_svp_begin[], __dtb_start[];
+extern u32 __dtb_xlp_evp_begin[], __dtb_xlp_svp_begin[],
+ __dtb_xlp_fvp_begin[], __dtb_start[];
void __init *xlp_dt_init(void *fdtp)
{
if (!fdtp) {
switch (current_cpu_data.processor_id & 0xff00) {
+#ifdef CONFIG_DT_XLP_FVP
+ case PRID_IMP_NETLOGIC_XLP2XX:
+ fdtp = __dtb_xlp_fvp_begin;
+ break;
+#endif
#ifdef CONFIG_DT_XLP_SVP
case PRID_IMP_NETLOGIC_XLP3XX:
fdtp = __dtb_xlp_svp_begin;
diff --git a/arch/mips/netlogic/xlp/nlm_hal.c b/arch/mips/netlogic/xlp/nlm_hal.c
index 87560e4..56c50ba 100644
--- a/arch/mips/netlogic/xlp/nlm_hal.c
+++ b/arch/mips/netlogic/xlp/nlm_hal.c
@@ -44,6 +44,7 @@
#include <asm/netlogic/haldefs.h>
#include <asm/netlogic/xlp-hal/iomap.h>
#include <asm/netlogic/xlp-hal/xlp.h>
+#include <asm/netlogic/xlp-hal/bridge.h>
#include <asm/netlogic/xlp-hal/pic.h>
#include <asm/netlogic/xlp-hal/sys.h>
@@ -64,6 +65,7 @@
uint64_t pcibase;
int devoff, irt;
+ devoff = 0;
switch (irq) {
case PIC_UART_0_IRQ:
devoff = XLP_IO_UART0_OFFSET(0);
@@ -71,44 +73,68 @@
case PIC_UART_1_IRQ:
devoff = XLP_IO_UART1_OFFSET(0);
break;
- case PIC_EHCI_0_IRQ:
- devoff = XLP_IO_USB_EHCI0_OFFSET(0);
- break;
- case PIC_EHCI_1_IRQ:
- devoff = XLP_IO_USB_EHCI1_OFFSET(0);
- break;
- case PIC_OHCI_0_IRQ:
- devoff = XLP_IO_USB_OHCI0_OFFSET(0);
- break;
- case PIC_OHCI_1_IRQ:
- devoff = XLP_IO_USB_OHCI1_OFFSET(0);
- break;
- case PIC_OHCI_2_IRQ:
- devoff = XLP_IO_USB_OHCI2_OFFSET(0);
- break;
- case PIC_OHCI_3_IRQ:
- devoff = XLP_IO_USB_OHCI3_OFFSET(0);
- break;
case PIC_MMC_IRQ:
devoff = XLP_IO_SD_OFFSET(0);
break;
- case PIC_I2C_0_IRQ:
- devoff = XLP_IO_I2C0_OFFSET(0);
- break;
+ case PIC_I2C_0_IRQ: /* I2C will be fixed up */
case PIC_I2C_1_IRQ:
- devoff = XLP_IO_I2C1_OFFSET(0);
+ case PIC_I2C_2_IRQ:
+ case PIC_I2C_3_IRQ:
+ if (cpu_is_xlpii())
+ devoff = XLP2XX_IO_I2C_OFFSET(0);
+ else
+ devoff = XLP_IO_I2C0_OFFSET(0);
break;
default:
- devoff = 0;
- break;
+ if (cpu_is_xlpii()) {
+ switch (irq) {
+ /* XLP2XX has three XHCI USB controller */
+ case PIC_2XX_XHCI_0_IRQ:
+ devoff = XLP2XX_IO_USB_XHCI0_OFFSET(0);
+ break;
+ case PIC_2XX_XHCI_1_IRQ:
+ devoff = XLP2XX_IO_USB_XHCI1_OFFSET(0);
+ break;
+ case PIC_2XX_XHCI_2_IRQ:
+ devoff = XLP2XX_IO_USB_XHCI2_OFFSET(0);
+ break;
+ }
+ } else {
+ switch (irq) {
+ case PIC_EHCI_0_IRQ:
+ devoff = XLP_IO_USB_EHCI0_OFFSET(0);
+ break;
+ case PIC_EHCI_1_IRQ:
+ devoff = XLP_IO_USB_EHCI1_OFFSET(0);
+ break;
+ case PIC_OHCI_0_IRQ:
+ devoff = XLP_IO_USB_OHCI0_OFFSET(0);
+ break;
+ case PIC_OHCI_1_IRQ:
+ devoff = XLP_IO_USB_OHCI1_OFFSET(0);
+ break;
+ case PIC_OHCI_2_IRQ:
+ devoff = XLP_IO_USB_OHCI2_OFFSET(0);
+ break;
+ case PIC_OHCI_3_IRQ:
+ devoff = XLP_IO_USB_OHCI3_OFFSET(0);
+ break;
+ }
+ }
}
if (devoff != 0) {
pcibase = nlm_pcicfg_base(devoff);
irt = nlm_read_reg(pcibase, XLP_PCI_IRTINFO_REG) & 0xffff;
- /* HW bug, I2C 1 irt entry is off by one */
- if (irq == PIC_I2C_1_IRQ)
- irt = irt + 1;
+ /* HW weirdness, I2C IRT entry has to be fixed up */
+ switch (irq) {
+ case PIC_I2C_1_IRQ:
+ irt = irt + 1; break;
+ case PIC_I2C_2_IRQ:
+ irt = irt + 2; break;
+ case PIC_I2C_3_IRQ:
+ irt = irt + 3; break;
+ }
} else if (irq >= PIC_PCIE_LINK_0_IRQ && irq <= PIC_PCIE_LINK_3_IRQ) {
/* HW bug, PCI IRT entries are bad on early silicon, fix */
irt = PIC_IRT_PCIE_LINK_INDEX(irq - PIC_PCIE_LINK_0_IRQ);
@@ -126,19 +152,160 @@
sysbase = nlm_get_node(node)->sysbase;
rstval = nlm_read_sys_reg(sysbase, SYS_POWER_ON_RESET_CFG);
- dfsval = nlm_read_sys_reg(sysbase, SYS_CORE_DFS_DIV_VALUE);
- pll_divf = ((rstval >> 10) & 0x7f) + 1;
- pll_divr = ((rstval >> 8) & 0x3) + 1;
- ext_div = ((rstval >> 30) & 0x3) + 1;
- dfs_div = ((dfsval >> (core * 4)) & 0xf) + 1;
+ if (cpu_is_xlpii()) {
+ num = 1000000ULL * (400 * 3 + 100 * (rstval >> 26));
+ denom = 3;
+ } else {
+ dfsval = nlm_read_sys_reg(sysbase, SYS_CORE_DFS_DIV_VALUE);
+ pll_divf = ((rstval >> 10) & 0x7f) + 1;
+ pll_divr = ((rstval >> 8) & 0x3) + 1;
+ ext_div = ((rstval >> 30) & 0x3) + 1;
+ dfs_div = ((dfsval >> (core * 4)) & 0xf) + 1;
- num = 800000000ULL * pll_divf;
- denom = 3 * pll_divr * ext_div * dfs_div;
+ num = 800000000ULL * pll_divf;
+ denom = 3 * pll_divr * ext_div * dfs_div;
+ }
do_div(num, denom);
return (unsigned int)num;
}
+/* Calculate Frequency to the PIC from PLL.
+ * freq_out = ( ref_freq/2 * (6 + ctrl2[7:0]) + ctrl2[20:8]/2^13 ) /
+ * ((2^ctrl0[7:5]) * Table(ctrl0[26:24]))
+ */
+static unsigned int nlm_2xx_get_pic_frequency(int node)
+{
+ u32 ctrl_val0, ctrl_val2, vco_post_div, pll_post_div;
+ u32 mdiv, fdiv, pll_out_freq_den, reg_select, ref_div, pic_div;
+ u64 ref_clk, sysbase, pll_out_freq_num, ref_clk_select;
+
+ sysbase = nlm_get_node(node)->sysbase;
+
+ /* Find ref_clk_base */
+ ref_clk_select =
+ (nlm_read_sys_reg(sysbase, SYS_POWER_ON_RESET_CFG) >> 18) & 0x3;
+ switch (ref_clk_select) {
+ case 0:
+ ref_clk = 200000000ULL;
+ ref_div = 3;
+ break;
+ case 1:
+ ref_clk = 100000000ULL;
+ ref_div = 1;
+ break;
+ case 2:
+ ref_clk = 125000000ULL;
+ ref_div = 1;
+ break;
+ case 3:
+ ref_clk = 400000000ULL;
+ ref_div = 3;
+ break;
+ }
+
+ /* Find the clock source PLL device for PIC */
+ reg_select = (nlm_read_sys_reg(sysbase, SYS_CLK_DEV_SEL) >> 22) & 0x3;
+ switch (reg_select) {
+ case 0:
+ ctrl_val0 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL0);
+ ctrl_val2 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL2);
+ break;
+ case 1:
+ ctrl_val0 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL0_DEVX(0));
+ ctrl_val2 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL2_DEVX(0));
+ break;
+ case 2:
+ ctrl_val0 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL0_DEVX(1));
+ ctrl_val2 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL2_DEVX(1));
+ break;
+ case 3:
+ ctrl_val0 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL0_DEVX(2));
+ ctrl_val2 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL2_DEVX(2));
+ break;
+ }
+
+ vco_post_div = (ctrl_val0 >> 5) & 0x7;
+ pll_post_div = (ctrl_val0 >> 24) & 0x7;
+ mdiv = ctrl_val2 & 0xff;
+ fdiv = (ctrl_val2 >> 8) & 0xfff;
+
+ /* Find PLL post divider value */
+ switch (pll_post_div) {
+ case 1:
+ pll_post_div = 2;
+ break;
+ case 3:
+ pll_post_div = 4;
+ break;
+ case 7:
+ pll_post_div = 8;
+ break;
+ case 6:
+ pll_post_div = 16;
+ break;
+ case 0:
+ default:
+ pll_post_div = 1;
+ break;
+ }
+
+ fdiv = fdiv/(1 << 13);
+ pll_out_freq_num = ((ref_clk >> 1) * (6 + mdiv)) + fdiv;
+ pll_out_freq_den = (1 << vco_post_div) * pll_post_div * 3;
+
+ if (pll_out_freq_den > 0)
+ do_div(pll_out_freq_num, pll_out_freq_den);
+
+ /* PIC post divider, which happens after PLL */
+ pic_div = (nlm_read_sys_reg(sysbase, SYS_CLK_DEV_DIV) >> 22) & 0x3;
+ do_div(pll_out_freq_num, 1 << pic_div);
+
+ return pll_out_freq_num;
+}
+
+unsigned int nlm_get_pic_frequency(int node)
+{
+ if (cpu_is_xlpii())
+ return nlm_2xx_get_pic_frequency(node);
+ else
+ return 133333333;
+}
+
unsigned int nlm_get_cpu_frequency(void)
{
return nlm_get_core_frequency(0, 0);
}
+
+/*
+ * Fills upto 8 pairs of entries containing the DRAM map of a node
+ * if n < 0, get dram map for all nodes
+ */
+int xlp_get_dram_map(int n, uint64_t *dram_map)
+{
+ uint64_t bridgebase, base, lim;
+ uint32_t val;
+ int i, node, rv;
+
+ /* Look only at mapping on Node 0, we don't handle crazy configs */
+ bridgebase = nlm_get_bridge_regbase(0);
+ rv = 0;
+ for (i = 0; i < 8; i++) {
+ val = nlm_read_bridge_reg(bridgebase,
+ BRIDGE_DRAM_NODE_TRANSLN(i));
+ node = (val >> 1) & 0x3;
+ if (n >= 0 && n != node)
+ continue;
+ val = nlm_read_bridge_reg(bridgebase, BRIDGE_DRAM_BAR(i));
+ val = (val >> 12) & 0xfffff;
+ base = (uint64_t) val << 20;
+ val = nlm_read_bridge_reg(bridgebase, BRIDGE_DRAM_LIMIT(i));
+ val = (val >> 12) & 0xfffff;
+ if (val == 0) /* BAR not used */
+ continue;
+ lim = ((uint64_t)val + 1) << 20;
+ dram_map[rv] = base;
+ dram_map[rv + 1] = lim;
+ rv += 2;
+ }
+ return rv;
+}
diff --git a/arch/mips/netlogic/xlp/setup.c b/arch/mips/netlogic/xlp/setup.c
index 7b638f7..76a7131 100644
--- a/arch/mips/netlogic/xlp/setup.c
+++ b/arch/mips/netlogic/xlp/setup.c
@@ -73,6 +73,23 @@
}
}
+static void __init xlp_init_mem_from_bars(void)
+{
+ uint64_t map[16];
+ int i, n;
+
+ n = xlp_get_dram_map(-1, map); /* -1: info for all nodes */
+ for (i = 0; i < n; i += 2) {
+ /* exclude 0x1000_0000-0x2000_0000, u-boot device */
+ if (map[i] <= 0x10000000 && map[i+1] > 0x10000000)
+ map[i+1] = 0x10000000;
+ if (map[i] > 0x10000000 && map[i] < 0x20000000)
+ map[i] = 0x20000000;
+
+ add_memory_region(map[i], map[i+1] - map[i], BOOT_MEM_RAM);
+ }
+}
+
void __init plat_mem_setup(void)
{
panic_timeout = 5;
@@ -82,12 +99,23 @@
/* memory and bootargs from DT */
early_init_devtree(initial_boot_params);
+
+ if (boot_mem_map.nr_map == 0) {
+ pr_info("Using DRAM BARs for memory map.\n");
+ xlp_init_mem_from_bars();
+ }
+ /* Calculate and setup wired entries for mapped kernel */
nlm_fixup_mem();
}
const char *get_system_type(void)
{
- return "Netlogic XLP Series";
+ switch (read_c0_prid() & 0xff00) {
+ case PRID_IMP_NETLOGIC_XLP2XX:
+ return "Broadcom XLPII Series";
+ default:
+ return "Netlogic XLP Series";
+ }
}
void __init prom_free_prom_memory(void)
@@ -97,12 +125,20 @@
void xlp_mmu_init(void)
{
- /* enable extended TLB and Large Fixed TLB */
- write_c0_config6(read_c0_config6() | 0x24);
+ u32 conf4;
- /* set page mask of Fixed TLB in config7 */
- write_c0_config7(PM_DEFAULT_MASK >>
- (13 + (ffz(PM_DEFAULT_MASK >> 13) / 2)));
+ if (cpu_is_xlpii()) {
+ /* XLPII series has extended pagesize in config 4 */
+ conf4 = read_c0_config4() & ~0x1f00u;
+ write_c0_config4(conf4 | ((PAGE_SHIFT - 10) / 2 << 8));
+ } else {
+ /* enable extended TLB and Large Fixed TLB */
+ write_c0_config6(read_c0_config6() | 0x24);
+
+ /* set page mask of extended Fixed TLB in config7 */
+ write_c0_config7(PM_DEFAULT_MASK >>
+ (13 + (ffz(PM_DEFAULT_MASK >> 13) / 2)));
+ }
}
void nlm_percpu_init(int hwcpuid)
diff --git a/arch/mips/netlogic/xlp/usb-init-xlp2.c b/arch/mips/netlogic/xlp/usb-init-xlp2.c
new file mode 100644
index 0000000..36e9c22
--- /dev/null
+++ b/arch/mips/netlogic/xlp/usb-init-xlp2.c
@@ -0,0 +1,218 @@
+/*
+ * Copyright (c) 2003-2013 Broadcom Corporation
+ * All Rights Reserved
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the Broadcom
+ * license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in
+ * the documentation and/or other materials provided with the
+ * distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY BROADCOM ``AS IS'' AND ANY EXPRESS OR
+ * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL BROADCOM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
+ * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
+ * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/dma-mapping.h>
+#include <linux/kernel.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/irq.h>
+
+#include <asm/netlogic/common.h>
+#include <asm/netlogic/haldefs.h>
+#include <asm/netlogic/xlp-hal/iomap.h>
+#include <asm/netlogic/xlp-hal/xlp.h>
+
+#define XLPII_USB3_CTL_0 0xc0
+#define XLPII_VAUXRST BIT(0)
+#define XLPII_VCCRST BIT(1)
+#define XLPII_NUM2PORT 9
+#define XLPII_NUM3PORT 13
+#define XLPII_RTUNEREQ BIT(20)
+#define XLPII_MS_CSYSREQ BIT(21)
+#define XLPII_XS_CSYSREQ BIT(22)
+#define XLPII_RETENABLEN BIT(23)
+#define XLPII_TX2RX BIT(24)
+#define XLPII_XHCIREV BIT(25)
+#define XLPII_ECCDIS BIT(26)
+
+#define XLPII_USB3_INT_REG 0xc2
+#define XLPII_USB3_INT_MASK 0xc3
+
+#define XLPII_USB_PHY_TEST 0xc6
+#define XLPII_PRESET BIT(0)
+#define XLPII_ATERESET BIT(1)
+#define XLPII_LOOPEN BIT(2)
+#define XLPII_TESTPDHSP BIT(3)
+#define XLPII_TESTPDSSP BIT(4)
+#define XLPII_TESTBURNIN BIT(5)
+
+#define XLPII_USB_PHY_LOS_LV 0xc9
+#define XLPII_LOSLEV 0
+#define XLPII_LOSBIAS 5
+#define XLPII_SQRXTX 8
+#define XLPII_TXBOOST 11
+#define XLPII_RSLKSEL 16
+#define XLPII_FSEL 20
+
+#define XLPII_USB_RFCLK_REG 0xcc
+#define XLPII_VVLD 30
+
+#define nlm_read_usb_reg(b, r) nlm_read_reg(b, r)
+#define nlm_write_usb_reg(b, r, v) nlm_write_reg(b, r, v)
+
+#define nlm_xlpii_get_usb_pcibase(node, inst) \
+ nlm_pcicfg_base(XLP2XX_IO_USB_OFFSET(node, inst))
+#define nlm_xlpii_get_usb_regbase(node, inst) \
+ (nlm_xlpii_get_usb_pcibase(node, inst) + XLP_IO_PCI_HDRSZ)
+
+static void xlpii_usb_ack(struct irq_data *data)
+{
+ u64 port_addr;
+
+ switch (data->irq) {
+ case PIC_2XX_XHCI_0_IRQ:
+ port_addr = nlm_xlpii_get_usb_regbase(0, 1);
+ break;
+ case PIC_2XX_XHCI_1_IRQ:
+ port_addr = nlm_xlpii_get_usb_regbase(0, 2);
+ break;
+ case PIC_2XX_XHCI_2_IRQ:
+ port_addr = nlm_xlpii_get_usb_regbase(0, 3);
+ break;
+ default:
+ pr_err("No matching USB irq!\n");
+ return;
+ }
+ nlm_write_usb_reg(port_addr, XLPII_USB3_INT_REG, 0xffffffff);
+}
+
+static void nlm_xlpii_usb_hw_reset(int node, int port)
+{
+ u64 port_addr, xhci_base, pci_base;
+ void __iomem *corebase;
+ u32 val;
+
+ port_addr = nlm_xlpii_get_usb_regbase(node, port);
+
+ /* Set frequency */
+ val = nlm_read_usb_reg(port_addr, XLPII_USB_PHY_LOS_LV);
+ val &= ~(0x3f << XLPII_FSEL);
+ val |= (0x27 << XLPII_FSEL);
+ nlm_write_usb_reg(port_addr, XLPII_USB_PHY_LOS_LV, val);
+
+ val = nlm_read_usb_reg(port_addr, XLPII_USB_RFCLK_REG);
+ val |= (1 << XLPII_VVLD);
+ nlm_write_usb_reg(port_addr, XLPII_USB_RFCLK_REG, val);
+
+ /* PHY reset */
+ val = nlm_read_usb_reg(port_addr, XLPII_USB_PHY_TEST);
+ val &= (XLPII_ATERESET | XLPII_LOOPEN | XLPII_TESTPDHSP
+ | XLPII_TESTPDSSP | XLPII_TESTBURNIN);
+ nlm_write_usb_reg(port_addr, XLPII_USB_PHY_TEST, val);
+
+ /* Setup control register */
+ val = XLPII_VAUXRST | XLPII_VCCRST | (1 << XLPII_NUM2PORT)
+ | (1 << XLPII_NUM3PORT) | XLPII_MS_CSYSREQ | XLPII_XS_CSYSREQ
+ | XLPII_RETENABLEN | XLPII_XHCIREV;
+ nlm_write_usb_reg(port_addr, XLPII_USB3_CTL_0, val);
+
+ /* Enable interrupts */
+ nlm_write_usb_reg(port_addr, XLPII_USB3_INT_MASK, 0x00000001);
+
+ /* Clear all interrupts */
+ nlm_write_usb_reg(port_addr, XLPII_USB3_INT_REG, 0xffffffff);
+
+ udelay(2000);
+
+ /* XHCI configuration at PCI mem */
+ pci_base = nlm_xlpii_get_usb_pcibase(node, port);
+ xhci_base = nlm_read_usb_reg(pci_base, 0x4) & ~0xf;
+ corebase = ioremap(xhci_base, 0x10000);
+ if (!corebase)
+ return;
+
+ writel(0x240002, corebase + 0xc2c0);
+ /* GCTL 0xc110 */
+ val = readl(corebase + 0xc110);
+ val &= ~(0x3 << 12);
+ val |= (1 << 12);
+ writel(val, corebase + 0xc110);
+ udelay(100);
+
+ /* PHYCFG 0xc200 */
+ val = readl(corebase + 0xc200);
+ val &= ~(1 << 6);
+ writel(val, corebase + 0xc200);
+ udelay(100);
+
+ /* PIPECTL 0xc2c0 */
+ val = readl(corebase + 0xc2c0);
+ val &= ~(1 << 17);
+ writel(val, corebase + 0xc2c0);
+
+ iounmap(corebase);
+}
+
+static int __init nlm_platform_xlpii_usb_init(void)
+{
+ if (!cpu_is_xlpii())
+ return 0;
+
+ pr_info("Initializing 2XX USB Interface\n");
+ nlm_xlpii_usb_hw_reset(0, 1);
+ nlm_xlpii_usb_hw_reset(0, 2);
+ nlm_xlpii_usb_hw_reset(0, 3);
+ nlm_set_pic_extra_ack(0, PIC_2XX_XHCI_0_IRQ, xlpii_usb_ack);
+ nlm_set_pic_extra_ack(0, PIC_2XX_XHCI_1_IRQ, xlpii_usb_ack);
+ nlm_set_pic_extra_ack(0, PIC_2XX_XHCI_2_IRQ, xlpii_usb_ack);
+
+ return 0;
+}
+
+arch_initcall(nlm_platform_xlpii_usb_init);
+
+static u64 xlp_usb_dmamask = ~(u32)0;
+
+/* Fixup IRQ for USB devices on XLP the SoC PCIe bus */
+static void nlm_usb_fixup_final(struct pci_dev *dev)
+{
+ dev->dev.dma_mask = &xlp_usb_dmamask;
+ dev->dev.coherent_dma_mask = DMA_BIT_MASK(32);
+ switch (dev->devfn) {
+ case 0x21:
+ dev->irq = PIC_2XX_XHCI_0_IRQ;
+ break;
+ case 0x22:
+ dev->irq = PIC_2XX_XHCI_1_IRQ;
+ break;
+ case 0x23:
+ dev->irq = PIC_2XX_XHCI_2_IRQ;
+ break;
+ }
+}
+
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_NETLOGIC, PCI_DEVICE_ID_NLM_XHCI,
+ nlm_usb_fixup_final);
diff --git a/arch/mips/netlogic/xlp/usb-init.c b/arch/mips/netlogic/xlp/usb-init.c
index ef3897e..f811798 100644
--- a/arch/mips/netlogic/xlp/usb-init.c
+++ b/arch/mips/netlogic/xlp/usb-init.c
@@ -75,8 +75,7 @@
port_addr = nlm_get_usb_regbase(node, port);
val = nlm_read_usb_reg(port_addr, USB_INT_EN);
val = USB_CTRL_INTERRUPT_EN | USB_OHCI_INTERRUPT_EN |
- USB_OHCI_INTERRUPT1_EN | USB_CTRL_INTERRUPT_EN |
- USB_OHCI_INTERRUPT_EN | USB_OHCI_INTERRUPT2_EN;
+ USB_OHCI_INTERRUPT1_EN | USB_OHCI_INTERRUPT2_EN;
nlm_write_usb_reg(port_addr, USB_INT_EN, val);
}
@@ -100,6 +99,9 @@
static int __init nlm_platform_usb_init(void)
{
+ if (cpu_is_xlpii())
+ return 0;
+
pr_info("Initializing USB Interface\n");
nlm_usb_hw_reset(0, 0);
nlm_usb_hw_reset(0, 3);
diff --git a/arch/mips/netlogic/xlp/wakeup.c b/arch/mips/netlogic/xlp/wakeup.c
index 0cce37c..682d563 100644
--- a/arch/mips/netlogic/xlp/wakeup.c
+++ b/arch/mips/netlogic/xlp/wakeup.c
@@ -58,10 +58,12 @@
coremask = (1 << core);
- /* Enable CPU clock */
- value = nlm_read_sys_reg(sysbase, SYS_CORE_DFS_DIS_CTRL);
- value &= ~coremask;
- nlm_write_sys_reg(sysbase, SYS_CORE_DFS_DIS_CTRL, value);
+ /* Enable CPU clock in case of 8xx/3xx */
+ if (!cpu_is_xlpii()) {
+ value = nlm_read_sys_reg(sysbase, SYS_CORE_DFS_DIS_CTRL);
+ value &= ~coremask;
+ nlm_write_sys_reg(sysbase, SYS_CORE_DFS_DIS_CTRL, value);
+ }
/* Remove CPU Reset */
value = nlm_read_sys_reg(sysbase, SYS_CPU_RESET);
diff --git a/arch/mips/pci/Makefile b/arch/mips/pci/Makefile
index c382042..719e455 100644
--- a/arch/mips/pci/Makefile
+++ b/arch/mips/pci/Makefile
@@ -41,6 +41,7 @@
obj-$(CONFIG_SNI_RM) += fixup-sni.o ops-sni.o
obj-$(CONFIG_LANTIQ) += fixup-lantiq.o
obj-$(CONFIG_PCI_LANTIQ) += pci-lantiq.o ops-lantiq.o
+obj-$(CONFIG_SOC_RT3883) += pci-rt3883.o
obj-$(CONFIG_TANBAC_TB0219) += fixup-tb0219.o
obj-$(CONFIG_TANBAC_TB0226) += fixup-tb0226.o
obj-$(CONFIG_TANBAC_TB0287) += fixup-tb0287.o
diff --git a/arch/mips/pci/pci-octeon.c b/arch/mips/pci/pci-octeon.c
index 95c2ea8..59cccd9 100644
--- a/arch/mips/pci/pci-octeon.c
+++ b/arch/mips/pci/pci-octeon.c
@@ -586,15 +586,16 @@
else
octeon_dma_bar_type = OCTEON_DMA_BAR_TYPE_BIG;
- /* PCI I/O and PCI MEM values */
- set_io_port_base(OCTEON_PCI_IOSPACE_BASE);
- ioport_resource.start = 0;
- ioport_resource.end = OCTEON_PCI_IOSPACE_SIZE - 1;
if (!octeon_is_pci_host()) {
pr_notice("Not in host mode, PCI Controller not initialized\n");
return 0;
}
+ /* PCI I/O and PCI MEM values */
+ set_io_port_base(OCTEON_PCI_IOSPACE_BASE);
+ ioport_resource.start = 0;
+ ioport_resource.end = OCTEON_PCI_IOSPACE_SIZE - 1;
+
pr_notice("%s Octeon big bar support\n",
(octeon_dma_bar_type ==
OCTEON_DMA_BAR_TYPE_BIG) ? "Enabling" : "Disabling");
diff --git a/arch/mips/pci/pci-rt3883.c b/arch/mips/pci/pci-rt3883.c
new file mode 100644
index 0000000..95c9d41
--- /dev/null
+++ b/arch/mips/pci/pci-rt3883.c
@@ -0,0 +1,636 @@
+/*
+ * Ralink RT3662/RT3883 SoC PCI support
+ *
+ * Copyright (C) 2011-2013 Gabor Juhos <juhosg@openwrt.org>
+ *
+ * Parts of this file are based on Ralink's 2.6.21 BSP
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include <linux/types.h>
+#include <linux/pci.h>
+#include <linux/io.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/of_pci.h>
+#include <linux/platform_device.h>
+
+#include <asm/mach-ralink/rt3883.h>
+#include <asm/mach-ralink/ralink_regs.h>
+
+#define RT3883_MEMORY_BASE 0x00000000
+#define RT3883_MEMORY_SIZE 0x02000000
+
+#define RT3883_PCI_REG_PCICFG 0x00
+#define RT3883_PCICFG_P2P_BR_DEVNUM_M 0xf
+#define RT3883_PCICFG_P2P_BR_DEVNUM_S 16
+#define RT3883_PCICFG_PCIRST BIT(1)
+#define RT3883_PCI_REG_PCIRAW 0x04
+#define RT3883_PCI_REG_PCIINT 0x08
+#define RT3883_PCI_REG_PCIENA 0x0c
+
+#define RT3883_PCI_REG_CFGADDR 0x20
+#define RT3883_PCI_REG_CFGDATA 0x24
+#define RT3883_PCI_REG_MEMBASE 0x28
+#define RT3883_PCI_REG_IOBASE 0x2c
+#define RT3883_PCI_REG_ARBCTL 0x80
+
+#define RT3883_PCI_REG_BASE(_x) (0x1000 + (_x) * 0x1000)
+#define RT3883_PCI_REG_BAR0SETUP(_x) (RT3883_PCI_REG_BASE((_x)) + 0x10)
+#define RT3883_PCI_REG_IMBASEBAR0(_x) (RT3883_PCI_REG_BASE((_x)) + 0x18)
+#define RT3883_PCI_REG_ID(_x) (RT3883_PCI_REG_BASE((_x)) + 0x30)
+#define RT3883_PCI_REG_CLASS(_x) (RT3883_PCI_REG_BASE((_x)) + 0x34)
+#define RT3883_PCI_REG_SUBID(_x) (RT3883_PCI_REG_BASE((_x)) + 0x38)
+#define RT3883_PCI_REG_STATUS(_x) (RT3883_PCI_REG_BASE((_x)) + 0x50)
+
+#define RT3883_PCI_MODE_NONE 0
+#define RT3883_PCI_MODE_PCI BIT(0)
+#define RT3883_PCI_MODE_PCIE BIT(1)
+#define RT3883_PCI_MODE_BOTH (RT3883_PCI_MODE_PCI | RT3883_PCI_MODE_PCIE)
+
+#define RT3883_PCI_IRQ_COUNT 32
+
+#define RT3883_P2P_BR_DEVNUM 1
+
+struct rt3883_pci_controller {
+ void __iomem *base;
+ spinlock_t lock;
+
+ struct device_node *intc_of_node;
+ struct irq_domain *irq_domain;
+
+ struct pci_controller pci_controller;
+ struct resource io_res;
+ struct resource mem_res;
+
+ bool pcie_ready;
+};
+
+static inline struct rt3883_pci_controller *
+pci_bus_to_rt3883_controller(struct pci_bus *bus)
+{
+ struct pci_controller *hose;
+
+ hose = (struct pci_controller *) bus->sysdata;
+ return container_of(hose, struct rt3883_pci_controller, pci_controller);
+}
+
+static inline u32 rt3883_pci_r32(struct rt3883_pci_controller *rpc,
+ unsigned reg)
+{
+ return ioread32(rpc->base + reg);
+}
+
+static inline void rt3883_pci_w32(struct rt3883_pci_controller *rpc,
+ u32 val, unsigned reg)
+{
+ iowrite32(val, rpc->base + reg);
+}
+
+static inline u32 rt3883_pci_get_cfgaddr(unsigned int bus, unsigned int slot,
+ unsigned int func, unsigned int where)
+{
+ return (bus << 16) | (slot << 11) | (func << 8) | (where & 0xfc) |
+ 0x80000000;
+}
+
+static u32 rt3883_pci_read_cfg32(struct rt3883_pci_controller *rpc,
+ unsigned bus, unsigned slot,
+ unsigned func, unsigned reg)
+{
+ unsigned long flags;
+ u32 address;
+ u32 ret;
+
+ address = rt3883_pci_get_cfgaddr(bus, slot, func, reg);
+
+ spin_lock_irqsave(&rpc->lock, flags);
+ rt3883_pci_w32(rpc, address, RT3883_PCI_REG_CFGADDR);
+ ret = rt3883_pci_r32(rpc, RT3883_PCI_REG_CFGDATA);
+ spin_unlock_irqrestore(&rpc->lock, flags);
+
+ return ret;
+}
+
+static void rt3883_pci_write_cfg32(struct rt3883_pci_controller *rpc,
+ unsigned bus, unsigned slot,
+ unsigned func, unsigned reg, u32 val)
+{
+ unsigned long flags;
+ u32 address;
+
+ address = rt3883_pci_get_cfgaddr(bus, slot, func, reg);
+
+ spin_lock_irqsave(&rpc->lock, flags);
+ rt3883_pci_w32(rpc, address, RT3883_PCI_REG_CFGADDR);
+ rt3883_pci_w32(rpc, val, RT3883_PCI_REG_CFGDATA);
+ spin_unlock_irqrestore(&rpc->lock, flags);
+}
+
+static void rt3883_pci_irq_handler(unsigned int irq, struct irq_desc *desc)
+{
+ struct rt3883_pci_controller *rpc;
+ u32 pending;
+
+ rpc = irq_get_handler_data(irq);
+
+ pending = rt3883_pci_r32(rpc, RT3883_PCI_REG_PCIINT) &
+ rt3883_pci_r32(rpc, RT3883_PCI_REG_PCIENA);
+
+ if (!pending) {
+ spurious_interrupt();
+ return;
+ }
+
+ while (pending) {
+ unsigned bit = __ffs(pending);
+
+ irq = irq_find_mapping(rpc->irq_domain, bit);
+ generic_handle_irq(irq);
+
+ pending &= ~BIT(bit);
+ }
+}
+
+static void rt3883_pci_irq_unmask(struct irq_data *d)
+{
+ struct rt3883_pci_controller *rpc;
+ u32 t;
+
+ rpc = irq_data_get_irq_chip_data(d);
+
+ t = rt3883_pci_r32(rpc, RT3883_PCI_REG_PCIENA);
+ rt3883_pci_w32(rpc, t | BIT(d->hwirq), RT3883_PCI_REG_PCIENA);
+ /* flush write */
+ rt3883_pci_r32(rpc, RT3883_PCI_REG_PCIENA);
+}
+
+static void rt3883_pci_irq_mask(struct irq_data *d)
+{
+ struct rt3883_pci_controller *rpc;
+ u32 t;
+
+ rpc = irq_data_get_irq_chip_data(d);
+
+ t = rt3883_pci_r32(rpc, RT3883_PCI_REG_PCIENA);
+ rt3883_pci_w32(rpc, t & ~BIT(d->hwirq), RT3883_PCI_REG_PCIENA);
+ /* flush write */
+ rt3883_pci_r32(rpc, RT3883_PCI_REG_PCIENA);
+}
+
+static struct irq_chip rt3883_pci_irq_chip = {
+ .name = "RT3883 PCI",
+ .irq_mask = rt3883_pci_irq_mask,
+ .irq_unmask = rt3883_pci_irq_unmask,
+ .irq_mask_ack = rt3883_pci_irq_mask,
+};
+
+static int rt3883_pci_irq_map(struct irq_domain *d, unsigned int irq,
+ irq_hw_number_t hw)
+{
+ irq_set_chip_and_handler(irq, &rt3883_pci_irq_chip, handle_level_irq);
+ irq_set_chip_data(irq, d->host_data);
+
+ return 0;
+}
+
+static const struct irq_domain_ops rt3883_pci_irq_domain_ops = {
+ .map = rt3883_pci_irq_map,
+ .xlate = irq_domain_xlate_onecell,
+};
+
+static int rt3883_pci_irq_init(struct device *dev,
+ struct rt3883_pci_controller *rpc)
+{
+ int irq;
+
+ irq = irq_of_parse_and_map(rpc->intc_of_node, 0);
+ if (irq == 0) {
+ dev_err(dev, "%s has no IRQ",
+ of_node_full_name(rpc->intc_of_node));
+ return -EINVAL;
+ }
+
+ /* disable all interrupts */
+ rt3883_pci_w32(rpc, 0, RT3883_PCI_REG_PCIENA);
+
+ rpc->irq_domain =
+ irq_domain_add_linear(rpc->intc_of_node, RT3883_PCI_IRQ_COUNT,
+ &rt3883_pci_irq_domain_ops,
+ rpc);
+ if (!rpc->irq_domain) {
+ dev_err(dev, "unable to add IRQ domain\n");
+ return -ENODEV;
+ }
+
+ irq_set_handler_data(irq, rpc);
+ irq_set_chained_handler(irq, rt3883_pci_irq_handler);
+
+ return 0;
+}
+
+static int rt3883_pci_config_read(struct pci_bus *bus, unsigned int devfn,
+ int where, int size, u32 *val)
+{
+ struct rt3883_pci_controller *rpc;
+ unsigned long flags;
+ u32 address;
+ u32 data;
+
+ rpc = pci_bus_to_rt3883_controller(bus);
+
+ if (!rpc->pcie_ready && bus->number == 1)
+ return PCIBIOS_DEVICE_NOT_FOUND;
+
+ address = rt3883_pci_get_cfgaddr(bus->number, PCI_SLOT(devfn),
+ PCI_FUNC(devfn), where);
+
+ spin_lock_irqsave(&rpc->lock, flags);
+ rt3883_pci_w32(rpc, address, RT3883_PCI_REG_CFGADDR);
+ data = rt3883_pci_r32(rpc, RT3883_PCI_REG_CFGDATA);
+ spin_unlock_irqrestore(&rpc->lock, flags);
+
+ switch (size) {
+ case 1:
+ *val = (data >> ((where & 3) << 3)) & 0xff;
+ break;
+ case 2:
+ *val = (data >> ((where & 3) << 3)) & 0xffff;
+ break;
+ case 4:
+ *val = data;
+ break;
+ }
+
+ return PCIBIOS_SUCCESSFUL;
+}
+
+static int rt3883_pci_config_write(struct pci_bus *bus, unsigned int devfn,
+ int where, int size, u32 val)
+{
+ struct rt3883_pci_controller *rpc;
+ unsigned long flags;
+ u32 address;
+ u32 data;
+
+ rpc = pci_bus_to_rt3883_controller(bus);
+
+ if (!rpc->pcie_ready && bus->number == 1)
+ return PCIBIOS_DEVICE_NOT_FOUND;
+
+ address = rt3883_pci_get_cfgaddr(bus->number, PCI_SLOT(devfn),
+ PCI_FUNC(devfn), where);
+
+ spin_lock_irqsave(&rpc->lock, flags);
+ rt3883_pci_w32(rpc, address, RT3883_PCI_REG_CFGADDR);
+ data = rt3883_pci_r32(rpc, RT3883_PCI_REG_CFGDATA);
+
+ switch (size) {
+ case 1:
+ data = (data & ~(0xff << ((where & 3) << 3))) |
+ (val << ((where & 3) << 3));
+ break;
+ case 2:
+ data = (data & ~(0xffff << ((where & 3) << 3))) |
+ (val << ((where & 3) << 3));
+ break;
+ case 4:
+ data = val;
+ break;
+ }
+
+ rt3883_pci_w32(rpc, data, RT3883_PCI_REG_CFGDATA);
+ spin_unlock_irqrestore(&rpc->lock, flags);
+
+ return PCIBIOS_SUCCESSFUL;
+}
+
+static struct pci_ops rt3883_pci_ops = {
+ .read = rt3883_pci_config_read,
+ .write = rt3883_pci_config_write,
+};
+
+static void rt3883_pci_preinit(struct rt3883_pci_controller *rpc, unsigned mode)
+{
+ u32 syscfg1;
+ u32 rstctrl;
+ u32 clkcfg1;
+ u32 t;
+
+ rstctrl = rt_sysc_r32(RT3883_SYSC_REG_RSTCTRL);
+ syscfg1 = rt_sysc_r32(RT3883_SYSC_REG_SYSCFG1);
+ clkcfg1 = rt_sysc_r32(RT3883_SYSC_REG_CLKCFG1);
+
+ if (mode & RT3883_PCI_MODE_PCIE) {
+ rstctrl |= RT3883_RSTCTRL_PCIE;
+ rt_sysc_w32(rstctrl, RT3883_SYSC_REG_RSTCTRL);
+
+ /* setup PCI PAD drive mode */
+ syscfg1 &= ~(0x30);
+ syscfg1 |= (2 << 4);
+ rt_sysc_w32(syscfg1, RT3883_SYSC_REG_SYSCFG1);
+
+ t = rt_sysc_r32(RT3883_SYSC_REG_PCIE_CLK_GEN0);
+ t &= ~BIT(31);
+ rt_sysc_w32(t, RT3883_SYSC_REG_PCIE_CLK_GEN0);
+
+ t = rt_sysc_r32(RT3883_SYSC_REG_PCIE_CLK_GEN1);
+ t &= 0x80ffffff;
+ rt_sysc_w32(t, RT3883_SYSC_REG_PCIE_CLK_GEN1);
+
+ t = rt_sysc_r32(RT3883_SYSC_REG_PCIE_CLK_GEN1);
+ t |= 0xa << 24;
+ rt_sysc_w32(t, RT3883_SYSC_REG_PCIE_CLK_GEN1);
+
+ t = rt_sysc_r32(RT3883_SYSC_REG_PCIE_CLK_GEN0);
+ t |= BIT(31);
+ rt_sysc_w32(t, RT3883_SYSC_REG_PCIE_CLK_GEN0);
+
+ msleep(50);
+
+ rstctrl &= ~RT3883_RSTCTRL_PCIE;
+ rt_sysc_w32(rstctrl, RT3883_SYSC_REG_RSTCTRL);
+ }
+
+ syscfg1 |= (RT3883_SYSCFG1_PCIE_RC_MODE | RT3883_SYSCFG1_PCI_HOST_MODE);
+
+ clkcfg1 &= ~(RT3883_CLKCFG1_PCI_CLK_EN | RT3883_CLKCFG1_PCIE_CLK_EN);
+
+ if (mode & RT3883_PCI_MODE_PCI) {
+ clkcfg1 |= RT3883_CLKCFG1_PCI_CLK_EN;
+ rstctrl &= ~RT3883_RSTCTRL_PCI;
+ }
+
+ if (mode & RT3883_PCI_MODE_PCIE) {
+ clkcfg1 |= RT3883_CLKCFG1_PCIE_CLK_EN;
+ rstctrl &= ~RT3883_RSTCTRL_PCIE;
+ }
+
+ rt_sysc_w32(syscfg1, RT3883_SYSC_REG_SYSCFG1);
+ rt_sysc_w32(rstctrl, RT3883_SYSC_REG_RSTCTRL);
+ rt_sysc_w32(clkcfg1, RT3883_SYSC_REG_CLKCFG1);
+
+ msleep(500);
+
+ /*
+ * setup the device number of the P2P bridge
+ * and de-assert the reset line
+ */
+ t = (RT3883_P2P_BR_DEVNUM << RT3883_PCICFG_P2P_BR_DEVNUM_S);
+ rt3883_pci_w32(rpc, t, RT3883_PCI_REG_PCICFG);
+
+ /* flush write */
+ rt3883_pci_r32(rpc, RT3883_PCI_REG_PCICFG);
+ msleep(500);
+
+ if (mode & RT3883_PCI_MODE_PCIE) {
+ msleep(500);
+
+ t = rt3883_pci_r32(rpc, RT3883_PCI_REG_STATUS(1));
+
+ rpc->pcie_ready = t & BIT(0);
+
+ if (!rpc->pcie_ready) {
+ /* reset the PCIe block */
+ t = rt_sysc_r32(RT3883_SYSC_REG_RSTCTRL);
+ t |= RT3883_RSTCTRL_PCIE;
+ rt_sysc_w32(t, RT3883_SYSC_REG_RSTCTRL);
+ t &= ~RT3883_RSTCTRL_PCIE;
+ rt_sysc_w32(t, RT3883_SYSC_REG_RSTCTRL);
+
+ /* turn off PCIe clock */
+ t = rt_sysc_r32(RT3883_SYSC_REG_CLKCFG1);
+ t &= ~RT3883_CLKCFG1_PCIE_CLK_EN;
+ rt_sysc_w32(t, RT3883_SYSC_REG_CLKCFG1);
+
+ t = rt_sysc_r32(RT3883_SYSC_REG_PCIE_CLK_GEN0);
+ t &= ~0xf000c080;
+ rt_sysc_w32(t, RT3883_SYSC_REG_PCIE_CLK_GEN0);
+ }
+ }
+
+ /* enable PCI arbiter */
+ rt3883_pci_w32(rpc, 0x79, RT3883_PCI_REG_ARBCTL);
+}
+
+static int rt3883_pci_probe(struct platform_device *pdev)
+{
+ struct rt3883_pci_controller *rpc;
+ struct device *dev = &pdev->dev;
+ struct device_node *np = dev->of_node;
+ struct resource *res;
+ struct device_node *child;
+ u32 val;
+ int err;
+ int mode;
+
+ rpc = devm_kzalloc(dev, sizeof(*rpc), GFP_KERNEL);
+ if (!rpc)
+ return -ENOMEM;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!res)
+ return -EINVAL;
+
+ rpc->base = devm_ioremap_resource(dev, res);
+ if (IS_ERR(rpc->base))
+ return PTR_ERR(rpc->base);
+
+ /* find the interrupt controller child node */
+ for_each_child_of_node(np, child) {
+ if (of_get_property(child, "interrupt-controller", NULL) &&
+ of_node_get(child)) {
+ rpc->intc_of_node = child;
+ break;
+ }
+ }
+
+ if (!rpc->intc_of_node) {
+ dev_err(dev, "%s has no %s child node",
+ of_node_full_name(rpc->intc_of_node),
+ "interrupt controller");
+ return -EINVAL;
+ }
+
+ /* find the PCI host bridge child node */
+ for_each_child_of_node(np, child) {
+ if (child->type &&
+ of_node_cmp(child->type, "pci") == 0 &&
+ of_node_get(child)) {
+ rpc->pci_controller.of_node = child;
+ break;
+ }
+ }
+
+ if (!rpc->pci_controller.of_node) {
+ dev_err(dev, "%s has no %s child node",
+ of_node_full_name(rpc->intc_of_node),
+ "PCI host bridge");
+ err = -EINVAL;
+ goto err_put_intc_node;
+ }
+
+ mode = RT3883_PCI_MODE_NONE;
+ for_each_available_child_of_node(rpc->pci_controller.of_node, child) {
+ int devfn;
+
+ if (!child->type ||
+ of_node_cmp(child->type, "pci") != 0)
+ continue;
+
+ devfn = of_pci_get_devfn(child);
+ if (devfn < 0)
+ continue;
+
+ switch (PCI_SLOT(devfn)) {
+ case 1:
+ mode |= RT3883_PCI_MODE_PCIE;
+ break;
+
+ case 17:
+ case 18:
+ mode |= RT3883_PCI_MODE_PCI;
+ break;
+ }
+ }
+
+ if (mode == RT3883_PCI_MODE_NONE) {
+ dev_err(dev, "unable to determine PCI mode\n");
+ err = -EINVAL;
+ goto err_put_hb_node;
+ }
+
+ dev_info(dev, "mode:%s%s\n",
+ (mode & RT3883_PCI_MODE_PCI) ? " PCI" : "",
+ (mode & RT3883_PCI_MODE_PCIE) ? " PCIe" : "");
+
+ rt3883_pci_preinit(rpc, mode);
+
+ rpc->pci_controller.pci_ops = &rt3883_pci_ops;
+ rpc->pci_controller.io_resource = &rpc->io_res;
+ rpc->pci_controller.mem_resource = &rpc->mem_res;
+
+ /* Load PCI I/O and memory resources from DT */
+ pci_load_of_ranges(&rpc->pci_controller,
+ rpc->pci_controller.of_node);
+
+ rt3883_pci_w32(rpc, rpc->mem_res.start, RT3883_PCI_REG_MEMBASE);
+ rt3883_pci_w32(rpc, rpc->io_res.start, RT3883_PCI_REG_IOBASE);
+
+ ioport_resource.start = rpc->io_res.start;
+ ioport_resource.end = rpc->io_res.end;
+
+ /* PCI */
+ rt3883_pci_w32(rpc, 0x03ff0000, RT3883_PCI_REG_BAR0SETUP(0));
+ rt3883_pci_w32(rpc, RT3883_MEMORY_BASE, RT3883_PCI_REG_IMBASEBAR0(0));
+ rt3883_pci_w32(rpc, 0x08021814, RT3883_PCI_REG_ID(0));
+ rt3883_pci_w32(rpc, 0x00800001, RT3883_PCI_REG_CLASS(0));
+ rt3883_pci_w32(rpc, 0x28801814, RT3883_PCI_REG_SUBID(0));
+
+ /* PCIe */
+ rt3883_pci_w32(rpc, 0x03ff0000, RT3883_PCI_REG_BAR0SETUP(1));
+ rt3883_pci_w32(rpc, RT3883_MEMORY_BASE, RT3883_PCI_REG_IMBASEBAR0(1));
+ rt3883_pci_w32(rpc, 0x08021814, RT3883_PCI_REG_ID(1));
+ rt3883_pci_w32(rpc, 0x06040001, RT3883_PCI_REG_CLASS(1));
+ rt3883_pci_w32(rpc, 0x28801814, RT3883_PCI_REG_SUBID(1));
+
+ err = rt3883_pci_irq_init(dev, rpc);
+ if (err)
+ goto err_put_hb_node;
+
+ /* PCIe */
+ val = rt3883_pci_read_cfg32(rpc, 0, 0x01, 0, PCI_COMMAND);
+ val |= PCI_COMMAND_IO | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER;
+ rt3883_pci_write_cfg32(rpc, 0, 0x01, 0, PCI_COMMAND, val);
+
+ /* PCI */
+ val = rt3883_pci_read_cfg32(rpc, 0, 0x00, 0, PCI_COMMAND);
+ val |= PCI_COMMAND_IO | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER;
+ rt3883_pci_write_cfg32(rpc, 0, 0x00, 0, PCI_COMMAND, val);
+
+ if (mode == RT3883_PCI_MODE_PCIE) {
+ rt3883_pci_w32(rpc, 0x03ff0001, RT3883_PCI_REG_BAR0SETUP(0));
+ rt3883_pci_w32(rpc, 0x03ff0001, RT3883_PCI_REG_BAR0SETUP(1));
+
+ rt3883_pci_write_cfg32(rpc, 0, RT3883_P2P_BR_DEVNUM, 0,
+ PCI_BASE_ADDRESS_0,
+ RT3883_MEMORY_BASE);
+ /* flush write */
+ rt3883_pci_read_cfg32(rpc, 0, RT3883_P2P_BR_DEVNUM, 0,
+ PCI_BASE_ADDRESS_0);
+ } else {
+ rt3883_pci_write_cfg32(rpc, 0, RT3883_P2P_BR_DEVNUM, 0,
+ PCI_IO_BASE, 0x00000101);
+ }
+
+ register_pci_controller(&rpc->pci_controller);
+
+ return 0;
+
+err_put_hb_node:
+ of_node_put(rpc->pci_controller.of_node);
+err_put_intc_node:
+ of_node_put(rpc->intc_of_node);
+ return err;
+}
+
+int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+{
+ struct of_irq dev_irq;
+ int err;
+ int irq;
+
+ err = of_irq_map_pci(dev, &dev_irq);
+ if (err) {
+ pr_err("pci %s: unable to get irq map, err=%d\n",
+ pci_name((struct pci_dev *) dev), err);
+ return 0;
+ }
+
+ irq = irq_create_of_mapping(dev_irq.controller,
+ dev_irq.specifier,
+ dev_irq.size);
+
+ if (irq == 0)
+ pr_crit("pci %s: no irq found for pin %u\n",
+ pci_name((struct pci_dev *) dev), pin);
+ else
+ pr_info("pci %s: using irq %d for pin %u\n",
+ pci_name((struct pci_dev *) dev), irq, pin);
+
+ return irq;
+}
+
+int pcibios_plat_dev_init(struct pci_dev *dev)
+{
+ return 0;
+}
+
+static const struct of_device_id rt3883_pci_ids[] = {
+ { .compatible = "ralink,rt3883-pci" },
+ {},
+};
+MODULE_DEVICE_TABLE(of, rt3883_pci_ids);
+
+static struct platform_driver rt3883_pci_driver = {
+ .probe = rt3883_pci_probe,
+ .driver = {
+ .name = "rt3883-pci",
+ .owner = THIS_MODULE,
+ .of_match_table = of_match_ptr(rt3883_pci_ids),
+ },
+};
+
+static int __init rt3883_pci_init(void)
+{
+ return platform_driver_register(&rt3883_pci_driver);
+}
+
+postcore_initcall(rt3883_pci_init);
diff --git a/arch/mips/powertv/Kconfig b/arch/mips/powertv/Kconfig
index 1a1b03e..dd91fba 100644
--- a/arch/mips/powertv/Kconfig
+++ b/arch/mips/powertv/Kconfig
@@ -1,14 +1,7 @@
-config BOOTLOADER_DRIVER
- bool "PowerTV Bootloader Driver Support"
- default n
- depends on POWERTV
- help
- Use this option if you want to load bootloader driver.
-
config BOOTLOADER_FAMILY
string "POWERTV Bootloader Family string"
default "85"
- depends on POWERTV && !BOOTLOADER_DRIVER
+ depends on POWERTV
help
This value should be specified when the bootloader driver is disabled
and must be exactly two characters long. Families supported are:
diff --git a/arch/mips/powertv/asic/asic_devices.c b/arch/mips/powertv/asic/asic_devices.c
index 0238af1..8380605 100644
--- a/arch/mips/powertv/asic/asic_devices.c
+++ b/arch/mips/powertv/asic/asic_devices.c
@@ -147,20 +147,10 @@
if (check_forcefamily(forced_family) == 0)
bootldr_family = BOOTLDRFAMILY(forced_family[0],
forced_family[1]);
- else {
-
-#ifdef CONFIG_BOOTLOADER_DRIVER
- bootldr_family = (unsigned short) kbldr_GetSWFamily();
-#else
-#if defined(CONFIG_BOOTLOADER_FAMILY)
+ else
bootldr_family = (unsigned short) BOOTLDRFAMILY(
CONFIG_BOOTLOADER_FAMILY[0],
CONFIG_BOOTLOADER_FAMILY[1]);
-#else
-#error "Unknown Bootloader Family"
-#endif
-#endif
- }
pr_info("Bootloader Family = 0x%04X\n", bootldr_family);
diff --git a/arch/mips/powertv/init.c b/arch/mips/powertv/init.c
index a01baff..4989263 100644
--- a/arch/mips/powertv/init.c
+++ b/arch/mips/powertv/init.c
@@ -87,8 +87,4 @@
configure_platform();
prom_meminit();
-
-#ifndef CONFIG_BOOTLOADER_DRIVER
- pr_info("\nBootloader driver isn't loaded...\n");
-#endif
}
diff --git a/arch/mips/powertv/reset.c b/arch/mips/powertv/reset.c
index 0007652..11c32fb 100644
--- a/arch/mips/powertv/reset.c
+++ b/arch/mips/powertv/reset.c
@@ -21,24 +21,12 @@
#include <linux/io.h>
#include <asm/reboot.h> /* Not included by linux/reboot.h */
-#ifdef CONFIG_BOOTLOADER_DRIVER
-#include <asm/mach-powertv/kbldr.h>
-#endif
-
#include <asm/mach-powertv/asic_regs.h>
#include "reset.h"
static void mips_machine_restart(char *command)
{
-#ifdef CONFIG_BOOTLOADER_DRIVER
- /*
- * Call the bootloader's reset function to ensure
- * that persistent data is flushed before hard reset
- */
- kbldr_SetCauseAndReset();
-#else
writel(0x1, asic_reg_addr(watchdog));
-#endif
}
void mips_reboot_setup(void)
diff --git a/arch/mips/ralink/Kconfig b/arch/mips/ralink/Kconfig
index 026e823..424f034 100644
--- a/arch/mips/ralink/Kconfig
+++ b/arch/mips/ralink/Kconfig
@@ -1,5 +1,12 @@
if RALINK
+config CLKEVT_RT3352
+ bool
+ depends on SOC_RT305X || SOC_MT7620
+ default y
+ select CLKSRC_OF
+ select CLKSRC_MMIO
+
choice
prompt "Ralink SoC selection"
default SOC_RT305X
@@ -19,9 +26,12 @@
bool "RT3883"
select USB_ARCH_HAS_OHCI
select USB_ARCH_HAS_EHCI
+ select HW_HAS_PCI
config SOC_MT7620
bool "MT7620"
+ select USB_ARCH_HAS_OHCI
+ select USB_ARCH_HAS_EHCI
endchoice
diff --git a/arch/mips/ralink/Makefile b/arch/mips/ralink/Makefile
index 38cf1a8..98ae349 100644
--- a/arch/mips/ralink/Makefile
+++ b/arch/mips/ralink/Makefile
@@ -6,7 +6,9 @@
# Copyright (C) 2009-2011 Gabor Juhos <juhosg@openwrt.org>
# Copyright (C) 2013 John Crispin <blogic@openwrt.org>
-obj-y := prom.o of.o reset.o clk.o irq.o
+obj-y := prom.o of.o reset.o clk.o irq.o timer.o
+
+obj-$(CONFIG_CLKEVT_RT3352) += cevt-rt3352.o
obj-$(CONFIG_SOC_RT288X) += rt288x.o
obj-$(CONFIG_SOC_RT305X) += rt305x.o
diff --git a/arch/mips/ralink/Platform b/arch/mips/ralink/Platform
index cda4b66..6d9c8c4 100644
--- a/arch/mips/ralink/Platform
+++ b/arch/mips/ralink/Platform
@@ -26,3 +26,4 @@
# Ralink MT7620
#
load-$(CONFIG_SOC_MT7620) += 0xffffffff80000000
+cflags-$(CONFIG_SOC_MT7620) += -I$(srctree)/arch/mips/include/asm/mach-ralink/mt7620
diff --git a/arch/mips/ralink/cevt-rt3352.c b/arch/mips/ralink/cevt-rt3352.c
new file mode 100644
index 0000000..cc17566
--- /dev/null
+++ b/arch/mips/ralink/cevt-rt3352.c
@@ -0,0 +1,145 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2013 by John Crispin <blogic@openwrt.org>
+ */
+
+#include <linux/clockchips.h>
+#include <linux/clocksource.h>
+#include <linux/interrupt.h>
+#include <linux/reset.h>
+#include <linux/init.h>
+#include <linux/time.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/of_address.h>
+
+#include <asm/mach-ralink/ralink_regs.h>
+
+#define SYSTICK_FREQ (50 * 1000)
+
+#define SYSTICK_CONFIG 0x00
+#define SYSTICK_COMPARE 0x04
+#define SYSTICK_COUNT 0x08
+
+/* route systick irq to mips irq 7 instead of the r4k-timer */
+#define CFG_EXT_STK_EN 0x2
+/* enable the counter */
+#define CFG_CNT_EN 0x1
+
+struct systick_device {
+ void __iomem *membase;
+ struct clock_event_device dev;
+ int irq_requested;
+ int freq_scale;
+};
+
+static void systick_set_clock_mode(enum clock_event_mode mode,
+ struct clock_event_device *evt);
+
+static int systick_next_event(unsigned long delta,
+ struct clock_event_device *evt)
+{
+ struct systick_device *sdev;
+ u32 count;
+
+ sdev = container_of(evt, struct systick_device, dev);
+ count = ioread32(sdev->membase + SYSTICK_COUNT);
+ count = (count + delta) % SYSTICK_FREQ;
+ iowrite32(count + delta, sdev->membase + SYSTICK_COMPARE);
+
+ return 0;
+}
+
+static void systick_event_handler(struct clock_event_device *dev)
+{
+ /* noting to do here */
+}
+
+static irqreturn_t systick_interrupt(int irq, void *dev_id)
+{
+ struct clock_event_device *dev = (struct clock_event_device *) dev_id;
+
+ dev->event_handler(dev);
+
+ return IRQ_HANDLED;
+}
+
+static struct systick_device systick = {
+ .dev = {
+ /*
+ * cevt-r4k uses 300, make sure systick
+ * gets used if available
+ */
+ .rating = 310,
+ .features = CLOCK_EVT_FEAT_ONESHOT,
+ .set_next_event = systick_next_event,
+ .set_mode = systick_set_clock_mode,
+ .event_handler = systick_event_handler,
+ },
+};
+
+static struct irqaction systick_irqaction = {
+ .handler = systick_interrupt,
+ .flags = IRQF_PERCPU | IRQF_TIMER,
+ .dev_id = &systick.dev,
+};
+
+static void systick_set_clock_mode(enum clock_event_mode mode,
+ struct clock_event_device *evt)
+{
+ struct systick_device *sdev;
+
+ sdev = container_of(evt, struct systick_device, dev);
+
+ switch (mode) {
+ case CLOCK_EVT_MODE_ONESHOT:
+ if (!sdev->irq_requested)
+ setup_irq(systick.dev.irq, &systick_irqaction);
+ sdev->irq_requested = 1;
+ iowrite32(CFG_EXT_STK_EN | CFG_CNT_EN,
+ systick.membase + SYSTICK_CONFIG);
+ break;
+
+ case CLOCK_EVT_MODE_SHUTDOWN:
+ if (sdev->irq_requested)
+ free_irq(systick.dev.irq, &systick_irqaction);
+ sdev->irq_requested = 0;
+ iowrite32(0, systick.membase + SYSTICK_CONFIG);
+ break;
+
+ default:
+ pr_err("%s: Unhandeled mips clock_mode\n", systick.dev.name);
+ break;
+ }
+}
+
+static void __init ralink_systick_init(struct device_node *np)
+{
+ systick.membase = of_iomap(np, 0);
+ if (!systick.membase)
+ return;
+
+ systick_irqaction.name = np->name;
+ systick.dev.name = np->name;
+ clockevents_calc_mult_shift(&systick.dev, SYSTICK_FREQ, 60);
+ systick.dev.max_delta_ns = clockevent_delta2ns(0x7fff, &systick.dev);
+ systick.dev.min_delta_ns = clockevent_delta2ns(0x3, &systick.dev);
+ systick.dev.irq = irq_of_parse_and_map(np, 0);
+ if (!systick.dev.irq) {
+ pr_err("%s: request_irq failed", np->name);
+ return;
+ }
+
+ clocksource_mmio_init(systick.membase + SYSTICK_COUNT, np->name,
+ SYSTICK_FREQ, 301, 16, clocksource_mmio_readl_up);
+
+ clockevents_register_device(&systick.dev);
+
+ pr_info("%s: runing - mult: %d, shift: %d\n",
+ np->name, systick.dev.mult, systick.dev.shift);
+}
+
+CLOCKSOURCE_OF_DECLARE(systick, "ralink,cevt-systick", ralink_systick_init);
diff --git a/arch/mips/ralink/clk.c b/arch/mips/ralink/clk.c
index 8dfa22f..bba0cdf 100644
--- a/arch/mips/ralink/clk.c
+++ b/arch/mips/ralink/clk.c
@@ -69,4 +69,5 @@
pr_info("CPU Clock: %ldMHz\n", clk_get_rate(clk) / 1000000);
mips_hpt_frequency = clk_get_rate(clk) / 2;
clk_put(clk);
+ clocksource_of_init();
}
diff --git a/arch/mips/ralink/common.h b/arch/mips/ralink/common.h
index 83144c3f..42dfd61 100644
--- a/arch/mips/ralink/common.h
+++ b/arch/mips/ralink/common.h
@@ -46,6 +46,8 @@
extern void ralink_clk_init(void);
extern void ralink_clk_add(const char *dev, unsigned long rate);
+extern void ralink_rst_init(void);
+
extern void prom_soc_init(struct ralink_soc_info *soc_info);
__iomem void *plat_of_remap_node(const char *node);
diff --git a/arch/mips/ralink/mt7620.c b/arch/mips/ralink/mt7620.c
index 0018b1a..d217509 100644
--- a/arch/mips/ralink/mt7620.c
+++ b/arch/mips/ralink/mt7620.c
@@ -23,9 +23,6 @@
/* does the board have sdram or ddram */
static int dram_type;
-/* the pll dividers */
-static u32 mt7620_clk_divider[] = { 2, 3, 4, 8 };
-
static struct ralink_pinmux_grp mode_mux[] = {
{
.name = "i2c",
@@ -140,34 +137,189 @@
.uart_mask = MT7620_GPIO_MODE_UART0_MASK,
};
+static __init u32
+mt7620_calc_rate(u32 ref_rate, u32 mul, u32 div)
+{
+ u64 t;
+
+ t = ref_rate;
+ t *= mul;
+ do_div(t, div);
+
+ return t;
+}
+
+#define MHZ(x) ((x) * 1000 * 1000)
+
+static __init unsigned long
+mt7620_get_xtal_rate(void)
+{
+ u32 reg;
+
+ reg = rt_sysc_r32(SYSC_REG_SYSTEM_CONFIG0);
+ if (reg & SYSCFG0_XTAL_FREQ_SEL)
+ return MHZ(40);
+
+ return MHZ(20);
+}
+
+static __init unsigned long
+mt7620_get_periph_rate(unsigned long xtal_rate)
+{
+ u32 reg;
+
+ reg = rt_sysc_r32(SYSC_REG_CLKCFG0);
+ if (reg & CLKCFG0_PERI_CLK_SEL)
+ return xtal_rate;
+
+ return MHZ(40);
+}
+
+static const u32 mt7620_clk_divider[] __initconst = { 2, 3, 4, 8 };
+
+static __init unsigned long
+mt7620_get_cpu_pll_rate(unsigned long xtal_rate)
+{
+ u32 reg;
+ u32 mul;
+ u32 div;
+
+ reg = rt_sysc_r32(SYSC_REG_CPLL_CONFIG0);
+ if (reg & CPLL_CFG0_BYPASS_REF_CLK)
+ return xtal_rate;
+
+ if ((reg & CPLL_CFG0_SW_CFG) == 0)
+ return MHZ(600);
+
+ mul = (reg >> CPLL_CFG0_PLL_MULT_RATIO_SHIFT) &
+ CPLL_CFG0_PLL_MULT_RATIO_MASK;
+ mul += 24;
+ if (reg & CPLL_CFG0_LC_CURFCK)
+ mul *= 2;
+
+ div = (reg >> CPLL_CFG0_PLL_DIV_RATIO_SHIFT) &
+ CPLL_CFG0_PLL_DIV_RATIO_MASK;
+
+ WARN_ON(div >= ARRAY_SIZE(mt7620_clk_divider));
+
+ return mt7620_calc_rate(xtal_rate, mul, mt7620_clk_divider[div]);
+}
+
+static __init unsigned long
+mt7620_get_pll_rate(unsigned long xtal_rate, unsigned long cpu_pll_rate)
+{
+ u32 reg;
+
+ reg = rt_sysc_r32(SYSC_REG_CPLL_CONFIG1);
+ if (reg & CPLL_CFG1_CPU_AUX1)
+ return xtal_rate;
+
+ if (reg & CPLL_CFG1_CPU_AUX0)
+ return MHZ(480);
+
+ return cpu_pll_rate;
+}
+
+static __init unsigned long
+mt7620_get_cpu_rate(unsigned long pll_rate)
+{
+ u32 reg;
+ u32 mul;
+ u32 div;
+
+ reg = rt_sysc_r32(SYSC_REG_CPU_SYS_CLKCFG);
+
+ mul = reg & CPU_SYS_CLKCFG_CPU_FFRAC_MASK;
+ div = (reg >> CPU_SYS_CLKCFG_CPU_FDIV_SHIFT) &
+ CPU_SYS_CLKCFG_CPU_FDIV_MASK;
+
+ return mt7620_calc_rate(pll_rate, mul, div);
+}
+
+static const u32 mt7620_ocp_dividers[16] __initconst = {
+ [CPU_SYS_CLKCFG_OCP_RATIO_2] = 2,
+ [CPU_SYS_CLKCFG_OCP_RATIO_3] = 3,
+ [CPU_SYS_CLKCFG_OCP_RATIO_4] = 4,
+ [CPU_SYS_CLKCFG_OCP_RATIO_5] = 5,
+ [CPU_SYS_CLKCFG_OCP_RATIO_10] = 10,
+};
+
+static __init unsigned long
+mt7620_get_dram_rate(unsigned long pll_rate)
+{
+ if (dram_type == SYSCFG0_DRAM_TYPE_SDRAM)
+ return pll_rate / 4;
+
+ return pll_rate / 3;
+}
+
+static __init unsigned long
+mt7620_get_sys_rate(unsigned long cpu_rate)
+{
+ u32 reg;
+ u32 ocp_ratio;
+ u32 div;
+
+ reg = rt_sysc_r32(SYSC_REG_CPU_SYS_CLKCFG);
+
+ ocp_ratio = (reg >> CPU_SYS_CLKCFG_OCP_RATIO_SHIFT) &
+ CPU_SYS_CLKCFG_OCP_RATIO_MASK;
+
+ if (WARN_ON(ocp_ratio >= ARRAY_SIZE(mt7620_ocp_dividers)))
+ return cpu_rate;
+
+ div = mt7620_ocp_dividers[ocp_ratio];
+ if (WARN(!div, "invalid divider for OCP ratio %u", ocp_ratio))
+ return cpu_rate;
+
+ return cpu_rate / div;
+}
+
void __init ralink_clk_init(void)
{
- unsigned long cpu_rate, sys_rate;
- u32 c0 = rt_sysc_r32(SYSC_REG_CPLL_CONFIG0);
- u32 c1 = rt_sysc_r32(SYSC_REG_CPLL_CONFIG1);
- u32 swconfig = (c0 >> CPLL_SW_CONFIG_SHIFT) & CPLL_SW_CONFIG_MASK;
- u32 cpu_clk = (c1 >> CPLL_CPU_CLK_SHIFT) & CPLL_CPU_CLK_MASK;
+ unsigned long xtal_rate;
+ unsigned long cpu_pll_rate;
+ unsigned long pll_rate;
+ unsigned long cpu_rate;
+ unsigned long sys_rate;
+ unsigned long dram_rate;
+ unsigned long periph_rate;
- if (cpu_clk) {
- cpu_rate = 480000000;
- } else if (!swconfig) {
- cpu_rate = 600000000;
- } else {
- u32 m = (c0 >> CPLL_MULT_RATIO_SHIFT) & CPLL_MULT_RATIO;
- u32 d = (c0 >> CPLL_DIV_RATIO_SHIFT) & CPLL_DIV_RATIO;
+ xtal_rate = mt7620_get_xtal_rate();
- cpu_rate = ((40 * (m + 24)) / mt7620_clk_divider[d]) * 1000000;
- }
+ cpu_pll_rate = mt7620_get_cpu_pll_rate(xtal_rate);
+ pll_rate = mt7620_get_pll_rate(xtal_rate, cpu_pll_rate);
- if (dram_type == SYSCFG0_DRAM_TYPE_SDRAM)
- sys_rate = cpu_rate / 4;
- else
- sys_rate = cpu_rate / 3;
+ cpu_rate = mt7620_get_cpu_rate(pll_rate);
+ dram_rate = mt7620_get_dram_rate(pll_rate);
+ sys_rate = mt7620_get_sys_rate(cpu_rate);
+ periph_rate = mt7620_get_periph_rate(xtal_rate);
+
+#define RFMT(label) label ":%lu.%03luMHz "
+#define RINT(x) ((x) / 1000000)
+#define RFRAC(x) (((x) / 1000) % 1000)
+
+ pr_debug(RFMT("XTAL") RFMT("CPU_PLL") RFMT("PLL"),
+ RINT(xtal_rate), RFRAC(xtal_rate),
+ RINT(cpu_pll_rate), RFRAC(cpu_pll_rate),
+ RINT(pll_rate), RFRAC(pll_rate));
+
+ pr_debug(RFMT("CPU") RFMT("DRAM") RFMT("SYS") RFMT("PERIPH"),
+ RINT(cpu_rate), RFRAC(cpu_rate),
+ RINT(dram_rate), RFRAC(dram_rate),
+ RINT(sys_rate), RFRAC(sys_rate),
+ RINT(periph_rate), RFRAC(periph_rate));
+
+#undef RFRAC
+#undef RINT
+#undef RFMT
ralink_clk_add("cpu", cpu_rate);
- ralink_clk_add("10000100.timer", 40000000);
- ralink_clk_add("10000500.uart", 40000000);
- ralink_clk_add("10000c00.uartlite", 40000000);
+ ralink_clk_add("10000100.timer", periph_rate);
+ ralink_clk_add("10000120.watchdog", periph_rate);
+ ralink_clk_add("10000500.uart", periph_rate);
+ ralink_clk_add("10000b00.spi", sys_rate);
+ ralink_clk_add("10000c00.uartlite", periph_rate);
}
void __init ralink_of_remap(void)
@@ -214,16 +366,19 @@
switch (dram_type) {
case SYSCFG0_DRAM_TYPE_SDRAM:
+ pr_info("Board has SDRAM\n");
soc_info->mem_size_min = MT7620_SDRAM_SIZE_MIN;
soc_info->mem_size_max = MT7620_SDRAM_SIZE_MAX;
break;
case SYSCFG0_DRAM_TYPE_DDR1:
+ pr_info("Board has DDR1\n");
soc_info->mem_size_min = MT7620_DDR1_SIZE_MIN;
soc_info->mem_size_max = MT7620_DDR1_SIZE_MAX;
break;
case SYSCFG0_DRAM_TYPE_DDR2:
+ pr_info("Board has DDR2\n");
soc_info->mem_size_min = MT7620_DDR2_SIZE_MIN;
soc_info->mem_size_max = MT7620_DDR2_SIZE_MAX;
break;
diff --git a/arch/mips/ralink/of.c b/arch/mips/ralink/of.c
index f25ea5b..ce38d11 100644
--- a/arch/mips/ralink/of.c
+++ b/arch/mips/ralink/of.c
@@ -110,6 +110,9 @@
if (of_platform_populate(NULL, of_ids, NULL, NULL))
panic("failed to populate DT\n");
+ /* make sure ithat the reset controller is setup early */
+ ralink_rst_init();
+
return 0;
}
diff --git a/arch/mips/ralink/reset.c b/arch/mips/ralink/reset.c
index 22120e5..55c7ec5 100644
--- a/arch/mips/ralink/reset.c
+++ b/arch/mips/ralink/reset.c
@@ -10,6 +10,8 @@
#include <linux/pm.h>
#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/reset-controller.h>
#include <asm/reboot.h>
@@ -19,6 +21,66 @@
#define SYSC_REG_RESET_CTRL 0x034
#define RSTCTL_RESET_SYSTEM BIT(0)
+static int ralink_assert_device(struct reset_controller_dev *rcdev,
+ unsigned long id)
+{
+ u32 val;
+
+ if (id < 8)
+ return -1;
+
+ val = rt_sysc_r32(SYSC_REG_RESET_CTRL);
+ val |= BIT(id);
+ rt_sysc_w32(val, SYSC_REG_RESET_CTRL);
+
+ return 0;
+}
+
+static int ralink_deassert_device(struct reset_controller_dev *rcdev,
+ unsigned long id)
+{
+ u32 val;
+
+ if (id < 8)
+ return -1;
+
+ val = rt_sysc_r32(SYSC_REG_RESET_CTRL);
+ val &= ~BIT(id);
+ rt_sysc_w32(val, SYSC_REG_RESET_CTRL);
+
+ return 0;
+}
+
+static int ralink_reset_device(struct reset_controller_dev *rcdev,
+ unsigned long id)
+{
+ ralink_assert_device(rcdev, id);
+ return ralink_deassert_device(rcdev, id);
+}
+
+static struct reset_control_ops reset_ops = {
+ .reset = ralink_reset_device,
+ .assert = ralink_assert_device,
+ .deassert = ralink_deassert_device,
+};
+
+static struct reset_controller_dev reset_dev = {
+ .ops = &reset_ops,
+ .owner = THIS_MODULE,
+ .nr_resets = 32,
+ .of_reset_n_cells = 1,
+};
+
+void ralink_rst_init(void)
+{
+ reset_dev.of_node = of_find_compatible_node(NULL, NULL,
+ "ralink,rt2880-reset");
+ if (!reset_dev.of_node)
+ pr_err("Failed to find reset controller node");
+ else
+ reset_controller_register(&reset_dev);
+}
+
static void ralink_restart(char *command)
{
local_irq_disable();
diff --git a/arch/mips/ralink/timer.c b/arch/mips/ralink/timer.c
new file mode 100644
index 0000000..e49241a
--- /dev/null
+++ b/arch/mips/ralink/timer.c
@@ -0,0 +1,185 @@
+/*
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ * Copyright (C) 2013 John Crispin <blogic@openwrt.org>
+*/
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/interrupt.h>
+#include <linux/timer.h>
+#include <linux/of_gpio.h>
+#include <linux/clk.h>
+
+#include <asm/mach-ralink/ralink_regs.h>
+
+#define TIMER_REG_TMRSTAT 0x00
+#define TIMER_REG_TMR0LOAD 0x10
+#define TIMER_REG_TMR0CTL 0x18
+
+#define TMRSTAT_TMR0INT BIT(0)
+
+#define TMR0CTL_ENABLE BIT(7)
+#define TMR0CTL_MODE_PERIODIC BIT(4)
+#define TMR0CTL_PRESCALER 1
+#define TMR0CTL_PRESCALE_VAL (0xf - TMR0CTL_PRESCALER)
+#define TMR0CTL_PRESCALE_DIV (65536 / BIT(TMR0CTL_PRESCALER))
+
+struct rt_timer {
+ struct device *dev;
+ void __iomem *membase;
+ int irq;
+ unsigned long timer_freq;
+ unsigned long timer_div;
+};
+
+static inline void rt_timer_w32(struct rt_timer *rt, u8 reg, u32 val)
+{
+ __raw_writel(val, rt->membase + reg);
+}
+
+static inline u32 rt_timer_r32(struct rt_timer *rt, u8 reg)
+{
+ return __raw_readl(rt->membase + reg);
+}
+
+static irqreturn_t rt_timer_irq(int irq, void *_rt)
+{
+ struct rt_timer *rt = (struct rt_timer *) _rt;
+
+ rt_timer_w32(rt, TIMER_REG_TMR0LOAD, rt->timer_freq / rt->timer_div);
+ rt_timer_w32(rt, TIMER_REG_TMRSTAT, TMRSTAT_TMR0INT);
+
+ return IRQ_HANDLED;
+}
+
+
+static int rt_timer_request(struct rt_timer *rt)
+{
+ int err = request_irq(rt->irq, rt_timer_irq, IRQF_DISABLED,
+ dev_name(rt->dev), rt);
+ if (err) {
+ dev_err(rt->dev, "failed to request irq\n");
+ } else {
+ u32 t = TMR0CTL_MODE_PERIODIC | TMR0CTL_PRESCALE_VAL;
+ rt_timer_w32(rt, TIMER_REG_TMR0CTL, t);
+ }
+ return err;
+}
+
+static void rt_timer_free(struct rt_timer *rt)
+{
+ free_irq(rt->irq, rt);
+}
+
+static int rt_timer_config(struct rt_timer *rt, unsigned long divisor)
+{
+ if (rt->timer_freq < divisor)
+ rt->timer_div = rt->timer_freq;
+ else
+ rt->timer_div = divisor;
+
+ rt_timer_w32(rt, TIMER_REG_TMR0LOAD, rt->timer_freq / rt->timer_div);
+
+ return 0;
+}
+
+static int rt_timer_enable(struct rt_timer *rt)
+{
+ u32 t;
+
+ rt_timer_w32(rt, TIMER_REG_TMR0LOAD, rt->timer_freq / rt->timer_div);
+
+ t = rt_timer_r32(rt, TIMER_REG_TMR0CTL);
+ t |= TMR0CTL_ENABLE;
+ rt_timer_w32(rt, TIMER_REG_TMR0CTL, t);
+
+ return 0;
+}
+
+static void rt_timer_disable(struct rt_timer *rt)
+{
+ u32 t;
+
+ t = rt_timer_r32(rt, TIMER_REG_TMR0CTL);
+ t &= ~TMR0CTL_ENABLE;
+ rt_timer_w32(rt, TIMER_REG_TMR0CTL, t);
+}
+
+static int rt_timer_probe(struct platform_device *pdev)
+{
+ struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ struct rt_timer *rt;
+ struct clk *clk;
+
+ rt = devm_kzalloc(&pdev->dev, sizeof(*rt), GFP_KERNEL);
+ if (!rt) {
+ dev_err(&pdev->dev, "failed to allocate memory\n");
+ return -ENOMEM;
+ }
+
+ rt->irq = platform_get_irq(pdev, 0);
+ if (!rt->irq) {
+ dev_err(&pdev->dev, "failed to load irq\n");
+ return -ENOENT;
+ }
+
+ rt->membase = devm_request_and_ioremap(&pdev->dev, res);
+ if (IS_ERR(rt->membase))
+ return PTR_ERR(rt->membase);
+
+ clk = devm_clk_get(&pdev->dev, NULL);
+ if (IS_ERR(clk)) {
+ dev_err(&pdev->dev, "failed get clock rate\n");
+ return PTR_ERR(clk);
+ }
+
+ rt->timer_freq = clk_get_rate(clk) / TMR0CTL_PRESCALE_DIV;
+ if (!rt->timer_freq)
+ return -EINVAL;
+
+ rt->dev = &pdev->dev;
+ platform_set_drvdata(pdev, rt);
+
+ rt_timer_request(rt);
+ rt_timer_config(rt, 2);
+ rt_timer_enable(rt);
+
+ dev_info(&pdev->dev, "maximum frequncy is %luHz\n", rt->timer_freq);
+
+ return 0;
+}
+
+static int rt_timer_remove(struct platform_device *pdev)
+{
+ struct rt_timer *rt = platform_get_drvdata(pdev);
+
+ rt_timer_disable(rt);
+ rt_timer_free(rt);
+
+ return 0;
+}
+
+static const struct of_device_id rt_timer_match[] = {
+ { .compatible = "ralink,rt2880-timer" },
+ {},
+};
+MODULE_DEVICE_TABLE(of, rt_timer_match);
+
+static struct platform_driver rt_timer_driver = {
+ .probe = rt_timer_probe,
+ .remove = rt_timer_remove,
+ .driver = {
+ .name = "rt-timer",
+ .owner = THIS_MODULE,
+ .of_match_table = rt_timer_match
+ },
+};
+
+module_platform_driver(rt_timer_driver);
+
+MODULE_DESCRIPTION("Ralink RT2880 timer");
+MODULE_AUTHOR("John Crispin <blogic@openwrt.org");
+MODULE_LICENSE("GPL");
diff --git a/arch/mips/txx9/generic/setup.c b/arch/mips/txx9/generic/setup.c
index 681e7f8..2b0b83c 100644
--- a/arch/mips/txx9/generic/setup.c
+++ b/arch/mips/txx9/generic/setup.c
@@ -350,7 +350,7 @@
}
/* select "default" board */
-#ifdef CONFIG_CPU_TX39XX
+#ifdef CONFIG_TOSHIBA_JMR3927
txx9_board_vec = &jmr3927_vec;
#endif
#ifdef CONFIG_CPU_TX49XX
diff --git a/arch/mn10300/Kconfig b/arch/mn10300/Kconfig
index 70e4f66..6aaa160 100644
--- a/arch/mn10300/Kconfig
+++ b/arch/mn10300/Kconfig
@@ -1,7 +1,6 @@
config MN10300
def_bool y
select HAVE_OPROFILE
- select HAVE_GENERIC_HARDIRQS
select GENERIC_IRQ_SHOW
select ARCH_WANT_IPC_PARSE_VERSION
select HAVE_ARCH_TRACEHOOK
diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c
index 8a2e6de..3516cbd 100644
--- a/arch/mn10300/mm/fault.c
+++ b/arch/mn10300/mm/fault.c
@@ -171,6 +171,8 @@
if (in_atomic() || !mm)
goto no_context;
+ if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_USR)
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index d60bf98..9488209 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -11,7 +11,6 @@
select HAVE_MEMBLOCK
select ARCH_REQUIRE_GPIOLIB
select HAVE_ARCH_TRACEHOOK
- select HAVE_GENERIC_HARDIRQS
select GENERIC_IRQ_CHIP
select GENERIC_IRQ_PROBE
select GENERIC_IRQ_SHOW
diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c
index 4a41f84..0703acf 100644
--- a/arch/openrisc/mm/fault.c
+++ b/arch/openrisc/mm/fault.c
@@ -86,6 +86,7 @@
if (user_mode(regs)) {
/* Exception was in userspace: reenable interrupts */
local_irq_enable();
+ flags |= FAULT_FLAG_USER;
} else {
/* If exception was in a syscall, then IRQ's may have
* been enabled or disabled. If they were enabled,
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index aa399a5..ad2ce8d 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -14,7 +14,6 @@
select HAVE_PERF_EVENTS
select GENERIC_ATOMIC64 if !64BIT
select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
- select HAVE_GENERIC_HARDIRQS
select BROKEN_RODATA
select GENERIC_IRQ_PROBE
select GENERIC_PCI_IOMAP
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index f247a34..d10d27a 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -180,6 +180,10 @@
if (in_atomic() || !mm)
goto no_context;
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
+ if (acc_type & VM_WRITE)
+ flags |= FAULT_FLAG_WRITE;
retry:
down_read(&mm->mmap_sem);
vma = find_vma_prev(mm, address, &prev_vma);
@@ -203,8 +207,7 @@
* fault.
*/
- fault = handle_mm_fault(mm, vma, address,
- flags | ((acc_type & VM_WRITE) ? FAULT_FLAG_WRITE : 0));
+ fault = handle_mm_fault(mm, vma, address, flags);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return;
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 6b7530f..38f3b7e 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -114,7 +114,6 @@
select HAVE_PERF_EVENTS
select HAVE_REGS_AND_STACK_ACCESS_API
select HAVE_HW_BREAKPOINT if PERF_EVENTS && PPC_BOOK3S_64
- select HAVE_GENERIC_HARDIRQS
select ARCH_WANT_IPC_PARSE_VERSION
select SPARSE_IRQ
select IRQ_DOMAIN
diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h
index 77e97dd..38faede 100644
--- a/arch/powerpc/include/asm/device.h
+++ b/arch/powerpc/include/asm/device.h
@@ -28,6 +28,9 @@
void *iommu_table_base;
} dma_data;
+#ifdef CONFIG_IOMMU_API
+ void *iommu_domain;
+#endif
#ifdef CONFIG_SWIOTLB
dma_addr_t max_direct_dma_addr;
#endif
diff --git a/arch/powerpc/include/asm/fsl_pamu_stash.h b/arch/powerpc/include/asm/fsl_pamu_stash.h
new file mode 100644
index 0000000..caa1b21
--- /dev/null
+++ b/arch/powerpc/include/asm/fsl_pamu_stash.h
@@ -0,0 +1,39 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ *
+ * Copyright (C) 2013 Freescale Semiconductor, Inc.
+ *
+ */
+
+#ifndef __FSL_PAMU_STASH_H
+#define __FSL_PAMU_STASH_H
+
+/* cache stash targets */
+enum pamu_stash_target {
+ PAMU_ATTR_CACHE_L1 = 1,
+ PAMU_ATTR_CACHE_L2,
+ PAMU_ATTR_CACHE_L3,
+};
+
+/*
+ * This attribute allows configuring stashig specific parameters
+ * in the PAMU hardware.
+ */
+
+struct pamu_stash_attribute {
+ u32 cpu; /* cpu number */
+ u32 cache; /* cache to stash to: L1,L2,L3 */
+};
+
+#endif /* __FSL_PAMU_STASH_H */
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 2dd69bf..51ab9e7 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -223,9 +223,6 @@
is_write = error_code & ESR_DST;
#endif /* CONFIG_4xx || CONFIG_BOOKE */
- if (is_write)
- flags |= FAULT_FLAG_WRITE;
-
#ifdef CONFIG_PPC_ICSWX
/*
* we need to do this early because this "data storage
@@ -288,6 +285,9 @@
if (user_mode(regs))
store_update_sp = store_updates_sp(regs);
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
+
/* When running in the kernel we expect faults to occur only to
* addresses in user space. All other faults represent errors in the
* kernel and should generate an OOPS. Unfortunately, in the case of an
@@ -415,6 +415,7 @@
} else if (is_write) {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
/* a read */
} else {
/* protection fault */
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 834ca8e..d67db4b 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -86,6 +86,11 @@
*/
return ((pgd_val(pgd) & 0x3) != 0x0);
}
+
+int pmd_huge_support(void)
+{
+ return 1;
+}
#else
int pmd_huge(pmd_t pmd)
{
@@ -101,6 +106,11 @@
{
return 0;
}
+
+int pmd_huge_support(void)
+{
+ return 0;
+}
#endif
pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
diff --git a/arch/powerpc/sysdev/fsl_pci.h b/arch/powerpc/sysdev/fsl_pci.h
index defc422..8d455df 100644
--- a/arch/powerpc/sysdev/fsl_pci.h
+++ b/arch/powerpc/sysdev/fsl_pci.h
@@ -16,6 +16,11 @@
struct platform_device;
+
+/* FSL PCI controller BRR1 register */
+#define PCI_FSL_BRR1 0xbf8
+#define PCI_FSL_BRR1_VER 0xffff
+
#define PCIE_LTSSM 0x0404 /* PCIE Link Training and Status */
#define PCIE_LTSSM_L0 0x16 /* L0 state */
#define PCIE_IP_REV_2_2 0x02080202 /* PCIE IP block version Rev2.2 */
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index c696ad7d..dcc6ac2 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -62,6 +62,7 @@
def_bool y
select ARCH_DISCARD_MEMBLOCK
select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
+ select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
select ARCH_HAVE_NMI_SAFE_CMPXCHG
select ARCH_INLINE_READ_LOCK
select ARCH_INLINE_READ_LOCK_BH
@@ -91,7 +92,6 @@
select ARCH_INLINE_WRITE_UNLOCK_BH
select ARCH_INLINE_WRITE_UNLOCK_IRQ
select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
- select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
select ARCH_SAVE_PAGE_KEYS if HIBERNATION
select ARCH_WANT_IPC_PARSE_VERSION
select BUILDTIME_EXTABLE_SORT
@@ -116,7 +116,6 @@
select HAVE_FUNCTION_GRAPH_TRACER
select HAVE_FUNCTION_TRACER
select HAVE_FUNCTION_TRACE_MCOUNT_TEST
- select HAVE_GENERIC_HARDIRQS
select HAVE_KERNEL_BZIP2
select HAVE_KERNEL_GZIP
select HAVE_KERNEL_LZ4
@@ -135,15 +134,15 @@
select HAVE_SYSCALL_TRACEPOINTS
select HAVE_UID16 if 32BIT
select HAVE_VIRT_CPU_ACCOUNTING
- select VIRT_TO_BUS
select INIT_ALL_POSSIBLE
select KTIME_SCALAR if 32BIT
select MODULES_USE_ELF_RELA
- select OLD_SIGSUSPEND3
select OLD_SIGACTION
+ select OLD_SIGSUSPEND3
select SYSCTL_EXCEPTION_TRACE
select USE_GENERIC_SMP_HELPERS if SMP
select VIRT_CPU_ACCOUNTING
+ select VIRT_TO_BUS
config SCHED_OMIT_FRAME_POINTER
def_bool y
@@ -526,6 +525,7 @@
bool "kernel crash dumps"
depends on 64BIT && SMP
select KEXEC
+ select ZFCPDUMP
help
Generate crash dump after being started by kexec.
Crash dump kernels are loaded in the main kernel with kexec-tools
@@ -536,7 +536,7 @@
config ZFCPDUMP
def_bool n
prompt "zfcpdump support"
- select SMP
+ depends on SMP
help
Select this option if you want to build an zfcpdump enabled kernel.
Refer to <file:Documentation/s390/zfcpdump.txt> for more details on this.
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index b74400e..d204c65 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -1,14 +1,13 @@
-CONFIG_EXPERIMENTAL=y
CONFIG_SYSVIPC=y
CONFIG_POSIX_MQUEUE=y
CONFIG_FHANDLE=y
+CONFIG_AUDIT=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
CONFIG_TASKSTATS=y
CONFIG_TASK_DELAY_ACCT=y
CONFIG_TASK_XACCT=y
CONFIG_TASK_IO_ACCOUNTING=y
-CONFIG_AUDIT=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
CONFIG_RCU_FAST_NO_HZ=y
CONFIG_IKCONFIG=y
CONFIG_IKCONFIG_PROC=y
@@ -27,6 +26,7 @@
CONFIG_RD_LZMA=y
CONFIG_RD_XZ=y
CONFIG_RD_LZO=y
+CONFIG_RD_LZ4=y
CONFIG_EXPERT=y
# CONFIG_COMPAT_BRK is not set
CONFIG_PROFILING=y
@@ -38,11 +38,13 @@
CONFIG_MODVERSIONS=y
CONFIG_PARTITION_ADVANCED=y
CONFIG_IBM_PARTITION=y
+# CONFIG_EFI_PARTITION is not set
CONFIG_DEFAULT_DEADLINE=y
CONFIG_HZ_100=y
CONFIG_MEMORY_HOTPLUG=y
CONFIG_MEMORY_HOTREMOVE=y
CONFIG_KSM=y
+CONFIG_TRANSPARENT_HUGEPAGE=y
CONFIG_CRASH_DUMP=y
CONFIG_BINFMT_MISC=m
CONFIG_HIBERNATION=y
@@ -92,40 +94,49 @@
CONFIG_SCSI_LOGGING=y
CONFIG_SCSI_SCAN_ASYNC=y
CONFIG_ZFCP=y
+CONFIG_SCSI_VIRTIO=y
CONFIG_NETDEVICES=y
CONFIG_BONDING=m
CONFIG_DUMMY=m
CONFIG_EQUALIZER=m
CONFIG_TUN=m
CONFIG_VIRTIO_NET=y
+# CONFIG_INPUT is not set
+# CONFIG_SERIO is not set
CONFIG_RAW_DRIVER=m
CONFIG_VIRTIO_BALLOON=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
CONFIG_EXT4_FS=y
CONFIG_EXT4_FS_POSIX_ACL=y
CONFIG_EXT4_FS_SECURITY=y
+CONFIG_XFS_FS=y
+CONFIG_XFS_QUOTA=y
+CONFIG_XFS_POSIX_ACL=y
+CONFIG_XFS_RT=y
+CONFIG_BTRFS_FS=y
+CONFIG_BTRFS_FS_POSIX_ACL=y
+CONFIG_FANOTIFY=y
+CONFIG_FUSE_FS=y
CONFIG_PROC_KCORE=y
CONFIG_TMPFS=y
CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_HUGETLBFS=y
# CONFIG_NETWORK_FILESYSTEMS is not set
+CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y
CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_PAGEALLOC=y
CONFIG_TIMER_STATS=y
CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
CONFIG_LOCK_STAT=y
CONFIG_DEBUG_LOCKDEP=y
CONFIG_DEBUG_LIST=y
CONFIG_DEBUG_NOTIFIERS=y
+CONFIG_PROVE_RCU=y
+CONFIG_RCU_CPU_STALL_TIMEOUT=60
CONFIG_RCU_TRACE=y
-CONFIG_KPROBES_SANITY_TEST=y
-CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y
CONFIG_LATENCYTOP=y
-CONFIG_DEBUG_PAGEALLOC=y
CONFIG_BLK_DEV_IO_TRACE=y
+CONFIG_KPROBES_SANITY_TEST=y
# CONFIG_STRICT_DEVMEM is not set
-CONFIG_CRYPTO_NULL=m
CONFIG_CRYPTO_CRYPTD=m
CONFIG_CRYPTO_AUTHENC=m
CONFIG_CRYPTO_TEST=m
@@ -137,8 +148,10 @@
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_XTS=m
+CONFIG_CRYPTO_CMAC=m
CONFIG_CRYPTO_XCBC=m
CONFIG_CRYPTO_VMAC=m
+CONFIG_CRYPTO_CRC32=m
CONFIG_CRYPTO_MD4=m
CONFIG_CRYPTO_MICHAEL_MIC=m
CONFIG_CRYPTO_RMD128=m
@@ -165,6 +178,8 @@
CONFIG_CRYPTO_DEFLATE=m
CONFIG_CRYPTO_ZLIB=m
CONFIG_CRYPTO_LZO=m
+CONFIG_CRYPTO_LZ4=m
+CONFIG_CRYPTO_LZ4HC=m
CONFIG_ZCRYPT=m
CONFIG_CRYPTO_SHA1_S390=m
CONFIG_CRYPTO_SHA256_S390=m
diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h
index 1eaa362..5f8bcc5 100644
--- a/arch/s390/include/asm/irq.h
+++ b/arch/s390/include/asm/irq.h
@@ -78,10 +78,14 @@
int register_external_interrupt(u16 code, ext_int_handler_t handler);
int unregister_external_interrupt(u16 code, ext_int_handler_t handler);
-void service_subclass_irq_register(void);
-void service_subclass_irq_unregister(void);
-void measurement_alert_subclass_register(void);
-void measurement_alert_subclass_unregister(void);
+
+enum irq_subclass {
+ IRQ_SUBCLASS_MEASUREMENT_ALERT = 5,
+ IRQ_SUBCLASS_SERVICE_SIGNAL = 9,
+};
+
+void irq_subclass_register(enum irq_subclass subclass);
+void irq_subclass_unregister(enum irq_subclass subclass);
#define irq_canonicalize(irq) (irq)
diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h
index dcf6948..4176dfe 100644
--- a/arch/s390/include/asm/kprobes.h
+++ b/arch/s390/include/asm/kprobes.h
@@ -31,6 +31,8 @@
#include <linux/ptrace.h>
#include <linux/percpu.h>
+#define __ARCH_WANT_KPROBES_INSN_SLOT
+
struct pt_regs;
struct kprobe;
@@ -57,7 +59,7 @@
/* Architecture specific copy of original instruction */
struct arch_specific_insn {
/* copy of original instruction */
- kprobe_opcode_t insn[MAX_INSN_SIZE];
+ kprobe_opcode_t *insn;
};
struct prev_kprobe {
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index 06a1361..7dc7f9c 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -56,5 +56,6 @@
bool sclp_has_vt220(void);
int sclp_pci_configure(u32 fid);
int sclp_pci_deconfigure(u32 fid);
+int memcpy_hsa(void *dest, unsigned long src, size_t count, int mode);
#endif /* _ASM_S390_SCLP_H */
diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c
index 8b6e4f5..1f1b8c7 100644
--- a/arch/s390/kernel/compat_linux.c
+++ b/arch/s390/kernel/compat_linux.c
@@ -221,25 +221,26 @@
asmlinkage long sys32_getgroups16(int gidsetsize, u16 __user *grouplist)
{
+ const struct cred *cred = current_cred();
int i;
if (gidsetsize < 0)
return -EINVAL;
- get_group_info(current->cred->group_info);
- i = current->cred->group_info->ngroups;
+ get_group_info(cred->group_info);
+ i = cred->group_info->ngroups;
if (gidsetsize) {
if (i > gidsetsize) {
i = -EINVAL;
goto out;
}
- if (groups16_to_user(grouplist, current->cred->group_info)) {
+ if (groups16_to_user(grouplist, cred->group_info)) {
i = -EFAULT;
goto out;
}
}
out:
- put_group_info(current->cred->group_info);
+ put_group_info(cred->group_info);
return i;
}
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index c439ac9..1389b63 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -332,9 +332,9 @@
/* Set up to return from userspace. If provided, use a stub
already in userspace. */
if (ka->sa.sa_flags & SA_RESTORER) {
- regs->gprs[14] = (__u64) ka->sa.sa_restorer | PSW32_ADDR_AMODE;
+ regs->gprs[14] = (__u64 __force) ka->sa.sa_restorer | PSW32_ADDR_AMODE;
} else {
- regs->gprs[14] = (__u64) frame->retcode | PSW32_ADDR_AMODE;
+ regs->gprs[14] = (__u64 __force) frame->retcode | PSW32_ADDR_AMODE;
if (__put_user(S390_SYSCALL_OPCODE | __NR_sigreturn,
(u16 __force __user *)(frame->retcode)))
goto give_sigsegv;
@@ -400,9 +400,9 @@
/* Set up to return from userspace. If provided, use a stub
already in userspace. */
if (ka->sa.sa_flags & SA_RESTORER) {
- regs->gprs[14] = (__u64) ka->sa.sa_restorer | PSW32_ADDR_AMODE;
+ regs->gprs[14] = (__u64 __force) ka->sa.sa_restorer | PSW32_ADDR_AMODE;
} else {
- regs->gprs[14] = (__u64) frame->retcode | PSW32_ADDR_AMODE;
+ regs->gprs[14] = (__u64 __force) frame->retcode | PSW32_ADDR_AMODE;
err |= __put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn,
(u16 __force __user *)(frame->retcode));
}
@@ -417,7 +417,7 @@
regs->psw.mask = PSW_MASK_BA |
(psw_user_bits & PSW_MASK_ASC) |
(regs->psw.mask & ~PSW_MASK_ASC);
- regs->psw.addr = (__u64) ka->sa.sa_handler;
+ regs->psw.addr = (__u64 __force) ka->sa.sa_handler;
regs->gprs[2] = map_signal(sig);
regs->gprs[3] = (__force __u64) &frame->info;
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index d8f3556..c84f33d 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -16,6 +16,7 @@
#include <asm/os_info.h>
#include <asm/elf.h>
#include <asm/ipl.h>
+#include <asm/sclp.h>
#define PTR_ADD(x, y) (((char *) (x)) + ((unsigned long) (y)))
#define PTR_SUB(x, y) (((char *) (x)) - ((unsigned long) (y)))
@@ -64,22 +65,46 @@
}
/*
- * Copy one page from "oldmem"
+ * Pointer to ELF header in new kernel
+ */
+static void *elfcorehdr_newmem;
+
+/*
+ * Copy one page from zfcpdump "oldmem"
+ *
+ * For pages below ZFCPDUMP_HSA_SIZE memory from the HSA is copied. Otherwise
+ * real memory copy is used.
+ */
+static ssize_t copy_oldmem_page_zfcpdump(char *buf, size_t csize,
+ unsigned long src, int userbuf)
+{
+ int rc;
+
+ if (src < ZFCPDUMP_HSA_SIZE) {
+ rc = memcpy_hsa(buf, src, csize, userbuf);
+ } else {
+ if (userbuf)
+ rc = copy_to_user_real((void __force __user *) buf,
+ (void *) src, csize);
+ else
+ rc = memcpy_real(buf, (void *) src, csize);
+ }
+ return rc ? rc : csize;
+}
+
+/*
+ * Copy one page from kdump "oldmem"
*
* For the kdump reserved memory this functions performs a swap operation:
* - [OLDMEM_BASE - OLDMEM_BASE + OLDMEM_SIZE] is mapped to [0 - OLDMEM_SIZE].
* - [0 - OLDMEM_SIZE] is mapped to [OLDMEM_BASE - OLDMEM_BASE + OLDMEM_SIZE]
*/
-ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
- size_t csize, unsigned long offset, int userbuf)
+static ssize_t copy_oldmem_page_kdump(char *buf, size_t csize,
+ unsigned long src, int userbuf)
+
{
- unsigned long src;
int rc;
- if (!csize)
- return 0;
-
- src = (pfn << PAGE_SHIFT) + offset;
if (src < OLDMEM_SIZE)
src += OLDMEM_BASE;
else if (src > OLDMEM_BASE &&
@@ -90,7 +115,88 @@
(void *) src, csize);
else
rc = copy_page_real(buf, (void *) src, csize);
- return (rc == 0) ? csize : rc;
+ return (rc == 0) ? rc : csize;
+}
+
+/*
+ * Copy one page from "oldmem"
+ */
+ssize_t copy_oldmem_page(unsigned long pfn, char *buf, size_t csize,
+ unsigned long offset, int userbuf)
+{
+ unsigned long src;
+
+ if (!csize)
+ return 0;
+ src = (pfn << PAGE_SHIFT) + offset;
+ if (OLDMEM_BASE)
+ return copy_oldmem_page_kdump(buf, csize, src, userbuf);
+ else
+ return copy_oldmem_page_zfcpdump(buf, csize, src, userbuf);
+}
+
+/*
+ * Remap "oldmem" for kdump
+ *
+ * For the kdump reserved memory this functions performs a swap operation:
+ * [0 - OLDMEM_SIZE] is mapped to [OLDMEM_BASE - OLDMEM_BASE + OLDMEM_SIZE]
+ */
+static int remap_oldmem_pfn_range_kdump(struct vm_area_struct *vma,
+ unsigned long from, unsigned long pfn,
+ unsigned long size, pgprot_t prot)
+{
+ unsigned long size_old;
+ int rc;
+
+ if (pfn < OLDMEM_SIZE >> PAGE_SHIFT) {
+ size_old = min(size, OLDMEM_SIZE - (pfn << PAGE_SHIFT));
+ rc = remap_pfn_range(vma, from,
+ pfn + (OLDMEM_BASE >> PAGE_SHIFT),
+ size_old, prot);
+ if (rc || size == size_old)
+ return rc;
+ size -= size_old;
+ from += size_old;
+ pfn += size_old >> PAGE_SHIFT;
+ }
+ return remap_pfn_range(vma, from, pfn, size, prot);
+}
+
+/*
+ * Remap "oldmem" for zfcpdump
+ *
+ * We only map available memory above ZFCPDUMP_HSA_SIZE. Memory below
+ * ZFCPDUMP_HSA_SIZE is read on demand using the copy_oldmem_page() function.
+ */
+static int remap_oldmem_pfn_range_zfcpdump(struct vm_area_struct *vma,
+ unsigned long from,
+ unsigned long pfn,
+ unsigned long size, pgprot_t prot)
+{
+ unsigned long size_hsa;
+
+ if (pfn < ZFCPDUMP_HSA_SIZE >> PAGE_SHIFT) {
+ size_hsa = min(size, ZFCPDUMP_HSA_SIZE - (pfn << PAGE_SHIFT));
+ if (size == size_hsa)
+ return 0;
+ size -= size_hsa;
+ from += size_hsa;
+ pfn += size_hsa >> PAGE_SHIFT;
+ }
+ return remap_pfn_range(vma, from, pfn, size, prot);
+}
+
+/*
+ * Remap "oldmem" for kdump or zfcpdump
+ */
+int remap_oldmem_pfn_range(struct vm_area_struct *vma, unsigned long from,
+ unsigned long pfn, unsigned long size, pgprot_t prot)
+{
+ if (OLDMEM_BASE)
+ return remap_oldmem_pfn_range_kdump(vma, from, pfn, size, prot);
+ else
+ return remap_oldmem_pfn_range_zfcpdump(vma, from, pfn, size,
+ prot);
}
/*
@@ -101,11 +207,21 @@
unsigned long copied = 0;
int rc;
- if ((unsigned long) src < OLDMEM_SIZE) {
- copied = min(count, OLDMEM_SIZE - (unsigned long) src);
- rc = memcpy_real(dest, src + OLDMEM_BASE, copied);
- if (rc)
- return rc;
+ if (OLDMEM_BASE) {
+ if ((unsigned long) src < OLDMEM_SIZE) {
+ copied = min(count, OLDMEM_SIZE - (unsigned long) src);
+ rc = memcpy_real(dest, src + OLDMEM_BASE, copied);
+ if (rc)
+ return rc;
+ }
+ } else {
+ if ((unsigned long) src < ZFCPDUMP_HSA_SIZE) {
+ copied = min(count,
+ ZFCPDUMP_HSA_SIZE - (unsigned long) src);
+ rc = memcpy_hsa(dest, (unsigned long) src, copied, 0);
+ if (rc)
+ return rc;
+ }
}
return memcpy_real(dest + copied, src + copied, count - copied);
}
@@ -368,14 +484,6 @@
}
/*
- * Relocate pointer in order to allow vmcore code access the data
- */
-static inline unsigned long relocate(unsigned long addr)
-{
- return OLDMEM_BASE + addr;
-}
-
-/*
* Initialize ELF loads (new kernel)
*/
static int loads_init(Elf64_Phdr *phdr, u64 loads_offset)
@@ -426,7 +534,7 @@
ptr = nt_vmcoreinfo(ptr);
memset(phdr, 0, sizeof(*phdr));
phdr->p_type = PT_NOTE;
- phdr->p_offset = relocate(notes_offset);
+ phdr->p_offset = notes_offset;
phdr->p_filesz = (unsigned long) PTR_SUB(ptr, ptr_start);
phdr->p_memsz = phdr->p_filesz;
return ptr;
@@ -435,7 +543,7 @@
/*
* Create ELF core header (new kernel)
*/
-static void s390_elf_corehdr_create(char **elfcorebuf, size_t *elfcorebuf_sz)
+int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size)
{
Elf64_Phdr *phdr_notes, *phdr_loads;
int mem_chunk_cnt;
@@ -443,6 +551,12 @@
u32 alloc_size;
u64 hdr_off;
+ /* If we are not in kdump or zfcpdump mode return */
+ if (!OLDMEM_BASE && ipl_info.type != IPL_TYPE_FCP_DUMP)
+ return 0;
+ /* If elfcorehdr= has been passed via cmdline, we use that one */
+ if (elfcorehdr_addr != ELFCORE_ADDR_MAX)
+ return 0;
mem_chunk_cnt = get_mem_chunk_cnt();
alloc_size = 0x1000 + get_cpu_cnt() * 0x300 +
@@ -460,27 +574,52 @@
ptr = notes_init(phdr_notes, ptr, ((unsigned long) hdr) + hdr_off);
/* Init loads */
hdr_off = PTR_DIFF(ptr, hdr);
- loads_init(phdr_loads, ((unsigned long) hdr) + hdr_off);
- *elfcorebuf_sz = hdr_off;
- *elfcorebuf = (void *) relocate((unsigned long) hdr);
- BUG_ON(*elfcorebuf_sz > alloc_size);
-}
-
-/*
- * Create kdump ELF core header in new kernel, if it has not been passed via
- * the "elfcorehdr" kernel parameter
- */
-static int setup_kdump_elfcorehdr(void)
-{
- size_t elfcorebuf_sz;
- char *elfcorebuf;
-
- if (!OLDMEM_BASE || is_kdump_kernel())
- return -EINVAL;
- s390_elf_corehdr_create(&elfcorebuf, &elfcorebuf_sz);
- elfcorehdr_addr = (unsigned long long) elfcorebuf;
- elfcorehdr_size = elfcorebuf_sz;
+ loads_init(phdr_loads, hdr_off);
+ *addr = (unsigned long long) hdr;
+ elfcorehdr_newmem = hdr;
+ *size = (unsigned long long) hdr_off;
+ BUG_ON(elfcorehdr_size > alloc_size);
return 0;
}
-subsys_initcall(setup_kdump_elfcorehdr);
+/*
+ * Free ELF core header (new kernel)
+ */
+void elfcorehdr_free(unsigned long long addr)
+{
+ if (!elfcorehdr_newmem)
+ return;
+ kfree((void *)(unsigned long)addr);
+}
+
+/*
+ * Read from ELF header
+ */
+ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos)
+{
+ void *src = (void *)(unsigned long)*ppos;
+
+ src = elfcorehdr_newmem ? src : src - OLDMEM_BASE;
+ memcpy(buf, src, count);
+ *ppos += count;
+ return count;
+}
+
+/*
+ * Read from ELF notes data
+ */
+ssize_t elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos)
+{
+ void *src = (void *)(unsigned long)*ppos;
+ int rc;
+
+ if (elfcorehdr_newmem) {
+ memcpy(buf, src, count);
+ } else {
+ rc = copy_from_oldmem(buf, src, count);
+ if (rc)
+ return rc;
+ }
+ *ppos += count;
+ return count;
+}
diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c
index 87acc38..99e7f60 100644
--- a/arch/s390/kernel/dumpstack.c
+++ b/arch/s390/kernel/dumpstack.c
@@ -40,14 +40,15 @@
{
struct stack_frame *sf;
struct pt_regs *regs;
+ unsigned long addr;
while (1) {
sp = sp & PSW_ADDR_INSN;
if (sp < low || sp > high - sizeof(*sf))
return sp;
sf = (struct stack_frame *) sp;
- printk("([<%016lx>] ", sf->gprs[8] & PSW_ADDR_INSN);
- print_symbol("%s)\n", sf->gprs[8] & PSW_ADDR_INSN);
+ addr = sf->gprs[8] & PSW_ADDR_INSN;
+ printk("([<%016lx>] %pSR)\n", addr, (void *)addr);
/* Follow the backchain. */
while (1) {
low = sp;
@@ -57,16 +58,16 @@
if (sp <= low || sp > high - sizeof(*sf))
return sp;
sf = (struct stack_frame *) sp;
- printk(" [<%016lx>] ", sf->gprs[8] & PSW_ADDR_INSN);
- print_symbol("%s\n", sf->gprs[8] & PSW_ADDR_INSN);
+ addr = sf->gprs[8] & PSW_ADDR_INSN;
+ printk(" [<%016lx>] %pSR\n", addr, (void *)addr);
}
/* Zero backchain detected, check for interrupt frame. */
sp = (unsigned long) (sf + 1);
if (sp <= low || sp > high - sizeof(*regs))
return sp;
regs = (struct pt_regs *) sp;
- printk(" [<%016lx>] ", regs->psw.addr & PSW_ADDR_INSN);
- print_symbol("%s\n", regs->psw.addr & PSW_ADDR_INSN);
+ addr = regs->psw.addr & PSW_ADDR_INSN;
+ printk(" [<%016lx>] %pSR\n", addr, (void *)addr);
low = sp;
sp = regs->gprs[15];
}
@@ -128,8 +129,7 @@
{
#ifdef CONFIG_64BIT
printk("Last Breaking-Event-Address:\n");
- printk(" [<%016lx>] ", regs->args[0] & PSW_ADDR_INSN);
- print_symbol("%s\n", regs->args[0] & PSW_ADDR_INSN);
+ printk(" [<%016lx>] %pSR\n", regs->args[0], (void *)regs->args[0]);
#endif
}
@@ -143,10 +143,10 @@
char *mode;
mode = user_mode(regs) ? "User" : "Krnl";
- printk("%s PSW : %p %p",
+ printk("%s PSW : %p %p (%pSR)\n",
mode, (void *) regs->psw.mask,
+ (void *) regs->psw.addr,
(void *) regs->psw.addr);
- print_symbol(" (%s)\n", regs->psw.addr & PSW_ADDR_INSN);
printk(" R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x "
"P:%x AS:%x CC:%x PM:%x", mask_bits(regs, PSW_MASK_PER),
mask_bits(regs, PSW_MASK_DAT), mask_bits(regs, PSW_MASK_IO),
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index 3ddbc26..e9b04c3 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -53,27 +53,21 @@
siginfo_t *info, sigset_t *oldset, struct pt_regs *regs);
void do_notify_resume(struct pt_regs *regs);
-struct ext_code;
-void do_extint(struct pt_regs *regs);
+void __init init_IRQ(void);
+void do_IRQ(struct pt_regs *regs, int irq);
void do_restart(void);
void __init startup_init(void);
void die(struct pt_regs *regs, const char *str);
-
+int setup_profiling_timer(unsigned int multiplier);
void __init time_init(void);
+int pfn_is_nosave(unsigned long);
+void s390_early_resume(void);
+unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip);
struct s390_mmap_arg_struct;
struct fadvise64_64_args;
struct old_sigaction;
-long sys_mmap2(struct s390_mmap_arg_struct __user *arg);
-long sys_s390_ipc(uint call, int first, unsigned long second,
- unsigned long third, void __user *ptr);
-long sys_s390_personality(unsigned int personality);
-long sys_s390_fadvise64(int fd, u32 offset_high, u32 offset_low,
- size_t len, int advice);
-long sys_s390_fadvise64_64(struct fadvise64_64_args __user *args);
-long sys_s390_fallocate(int fd, int mode, loff_t offset, u32 len_high,
- u32 len_low);
long sys_sigreturn(void);
long sys_rt_sigreturn(void);
long sys32_sigreturn(void);
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index e3043ae..1014ad5 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -15,6 +15,7 @@
#include <linux/kprobes.h>
#include <trace/syscall.h>
#include <asm/asm-offsets.h>
+#include "entry.h"
#ifdef CONFIG_DYNAMIC_FTRACE
@@ -177,7 +178,7 @@
offset = ((void *) prepare_ftrace_return -
(void *) ftrace_graph_caller) / 2;
- return probe_kernel_write(ftrace_graph_caller + 2,
+ return probe_kernel_write((void *) ftrace_graph_caller + 2,
&offset, sizeof(offset));
}
@@ -185,7 +186,7 @@
{
static unsigned short offset = 0x0002;
- return probe_kernel_write(ftrace_graph_caller + 2,
+ return probe_kernel_write((void *) ftrace_graph_caller + 2,
&offset, sizeof(offset));
}
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index b34ba0e..8ac2097 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -196,21 +196,23 @@
* ext_int_hash[index] is the list head for all external interrupts that hash
* to this index.
*/
-static struct list_head ext_int_hash[256];
+static struct hlist_head ext_int_hash[32] ____cacheline_aligned;
struct ext_int_info {
ext_int_handler_t handler;
- u16 code;
- struct list_head entry;
+ struct hlist_node entry;
struct rcu_head rcu;
+ u16 code;
};
/* ext_int_hash_lock protects the handler lists for external interrupts */
-DEFINE_SPINLOCK(ext_int_hash_lock);
+static DEFINE_SPINLOCK(ext_int_hash_lock);
static inline int ext_hash(u16 code)
{
- return (code + (code >> 9)) & 0xff;
+ BUILD_BUG_ON(!is_power_of_2(ARRAY_SIZE(ext_int_hash)));
+
+ return (code + (code >> 9)) & (ARRAY_SIZE(ext_int_hash) - 1);
}
int register_external_interrupt(u16 code, ext_int_handler_t handler)
@@ -227,7 +229,7 @@
index = ext_hash(code);
spin_lock_irqsave(&ext_int_hash_lock, flags);
- list_add_rcu(&p->entry, &ext_int_hash[index]);
+ hlist_add_head_rcu(&p->entry, &ext_int_hash[index]);
spin_unlock_irqrestore(&ext_int_hash_lock, flags);
return 0;
}
@@ -240,9 +242,9 @@
int index = ext_hash(code);
spin_lock_irqsave(&ext_int_hash_lock, flags);
- list_for_each_entry_rcu(p, &ext_int_hash[index], entry) {
+ hlist_for_each_entry_rcu(p, &ext_int_hash[index], entry) {
if (p->code == code && p->handler == handler) {
- list_del_rcu(&p->entry);
+ hlist_del_rcu(&p->entry);
kfree_rcu(p, rcu);
}
}
@@ -264,12 +266,12 @@
index = ext_hash(ext_code.code);
rcu_read_lock();
- list_for_each_entry_rcu(p, &ext_int_hash[index], entry)
- if (likely(p->code == ext_code.code))
- p->handler(ext_code, regs->int_parm,
- regs->int_parm_long);
+ hlist_for_each_entry_rcu(p, &ext_int_hash[index], entry) {
+ if (unlikely(p->code != ext_code.code))
+ continue;
+ p->handler(ext_code, regs->int_parm, regs->int_parm_long);
+ }
rcu_read_unlock();
-
return IRQ_HANDLED;
}
@@ -283,55 +285,32 @@
int idx;
for (idx = 0; idx < ARRAY_SIZE(ext_int_hash); idx++)
- INIT_LIST_HEAD(&ext_int_hash[idx]);
+ INIT_HLIST_HEAD(&ext_int_hash[idx]);
irq_set_chip_and_handler(EXT_INTERRUPT,
&dummy_irq_chip, handle_percpu_irq);
setup_irq(EXT_INTERRUPT, &external_interrupt);
}
-static DEFINE_SPINLOCK(sc_irq_lock);
-static int sc_irq_refcount;
+static DEFINE_SPINLOCK(irq_subclass_lock);
+static unsigned char irq_subclass_refcount[64];
-void service_subclass_irq_register(void)
+void irq_subclass_register(enum irq_subclass subclass)
{
- spin_lock(&sc_irq_lock);
- if (!sc_irq_refcount)
- ctl_set_bit(0, 9);
- sc_irq_refcount++;
- spin_unlock(&sc_irq_lock);
+ spin_lock(&irq_subclass_lock);
+ if (!irq_subclass_refcount[subclass])
+ ctl_set_bit(0, subclass);
+ irq_subclass_refcount[subclass]++;
+ spin_unlock(&irq_subclass_lock);
}
-EXPORT_SYMBOL(service_subclass_irq_register);
+EXPORT_SYMBOL(irq_subclass_register);
-void service_subclass_irq_unregister(void)
+void irq_subclass_unregister(enum irq_subclass subclass)
{
- spin_lock(&sc_irq_lock);
- sc_irq_refcount--;
- if (!sc_irq_refcount)
- ctl_clear_bit(0, 9);
- spin_unlock(&sc_irq_lock);
+ spin_lock(&irq_subclass_lock);
+ irq_subclass_refcount[subclass]--;
+ if (!irq_subclass_refcount[subclass])
+ ctl_clear_bit(0, subclass);
+ spin_unlock(&irq_subclass_lock);
}
-EXPORT_SYMBOL(service_subclass_irq_unregister);
-
-static DEFINE_SPINLOCK(ma_subclass_lock);
-static int ma_subclass_refcount;
-
-void measurement_alert_subclass_register(void)
-{
- spin_lock(&ma_subclass_lock);
- if (!ma_subclass_refcount)
- ctl_set_bit(0, 5);
- ma_subclass_refcount++;
- spin_unlock(&ma_subclass_lock);
-}
-EXPORT_SYMBOL(measurement_alert_subclass_register);
-
-void measurement_alert_subclass_unregister(void)
-{
- spin_lock(&ma_subclass_lock);
- ma_subclass_refcount--;
- if (!ma_subclass_refcount)
- ctl_clear_bit(0, 5);
- spin_unlock(&ma_subclass_lock);
-}
-EXPORT_SYMBOL(measurement_alert_subclass_unregister);
+EXPORT_SYMBOL(irq_subclass_unregister);
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index adbbe7f..0ce9fb2 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -37,6 +37,26 @@
struct kretprobe_blackpoint kretprobe_blacklist[] = { };
+DEFINE_INSN_CACHE_OPS(dmainsn);
+
+static void *alloc_dmainsn_page(void)
+{
+ return (void *)__get_free_page(GFP_KERNEL | GFP_DMA);
+}
+
+static void free_dmainsn_page(void *page)
+{
+ free_page((unsigned long)page);
+}
+
+struct kprobe_insn_cache kprobe_dmainsn_slots = {
+ .mutex = __MUTEX_INITIALIZER(kprobe_dmainsn_slots.mutex),
+ .alloc = alloc_dmainsn_page,
+ .free = free_dmainsn_page,
+ .pages = LIST_HEAD_INIT(kprobe_dmainsn_slots.pages),
+ .insn_size = MAX_INSN_SIZE,
+};
+
static int __kprobes is_prohibited_opcode(kprobe_opcode_t *insn)
{
switch (insn[0] >> 8) {
@@ -100,9 +120,8 @@
fixup |= FIXUP_RETURN_REGISTER;
break;
case 0xc0:
- if ((insn[0] & 0x0f) == 0x00 || /* larl */
- (insn[0] & 0x0f) == 0x05) /* brasl */
- fixup |= FIXUP_RETURN_REGISTER;
+ if ((insn[0] & 0x0f) == 0x05) /* brasl */
+ fixup |= FIXUP_RETURN_REGISTER;
break;
case 0xeb:
switch (insn[2] & 0xff) {
@@ -134,18 +153,128 @@
return fixup;
}
+static int __kprobes is_insn_relative_long(kprobe_opcode_t *insn)
+{
+ /* Check if we have a RIL-b or RIL-c format instruction which
+ * we need to modify in order to avoid instruction emulation. */
+ switch (insn[0] >> 8) {
+ case 0xc0:
+ if ((insn[0] & 0x0f) == 0x00) /* larl */
+ return true;
+ break;
+ case 0xc4:
+ switch (insn[0] & 0x0f) {
+ case 0x02: /* llhrl */
+ case 0x04: /* lghrl */
+ case 0x05: /* lhrl */
+ case 0x06: /* llghrl */
+ case 0x07: /* sthrl */
+ case 0x08: /* lgrl */
+ case 0x0b: /* stgrl */
+ case 0x0c: /* lgfrl */
+ case 0x0d: /* lrl */
+ case 0x0e: /* llgfrl */
+ case 0x0f: /* strl */
+ return true;
+ }
+ break;
+ case 0xc6:
+ switch (insn[0] & 0x0f) {
+ case 0x00: /* exrl */
+ case 0x02: /* pfdrl */
+ case 0x04: /* cghrl */
+ case 0x05: /* chrl */
+ case 0x06: /* clghrl */
+ case 0x07: /* clhrl */
+ case 0x08: /* cgrl */
+ case 0x0a: /* clgrl */
+ case 0x0c: /* cgfrl */
+ case 0x0d: /* crl */
+ case 0x0e: /* clgfrl */
+ case 0x0f: /* clrl */
+ return true;
+ }
+ break;
+ }
+ return false;
+}
+
+static void __kprobes copy_instruction(struct kprobe *p)
+{
+ s64 disp, new_disp;
+ u64 addr, new_addr;
+
+ memcpy(p->ainsn.insn, p->addr, ((p->opcode >> 14) + 3) & -2);
+ if (!is_insn_relative_long(p->ainsn.insn))
+ return;
+ /*
+ * For pc-relative instructions in RIL-b or RIL-c format patch the
+ * RI2 displacement field. We have already made sure that the insn
+ * slot for the patched instruction is within the same 2GB area
+ * as the original instruction (either kernel image or module area).
+ * Therefore the new displacement will always fit.
+ */
+ disp = *(s32 *)&p->ainsn.insn[1];
+ addr = (u64)(unsigned long)p->addr;
+ new_addr = (u64)(unsigned long)p->ainsn.insn;
+ new_disp = ((addr + (disp * 2)) - new_addr) / 2;
+ *(s32 *)&p->ainsn.insn[1] = new_disp;
+}
+
+static inline int is_kernel_addr(void *addr)
+{
+ return addr < (void *)_end;
+}
+
+static inline int is_module_addr(void *addr)
+{
+#ifdef CONFIG_64BIT
+ BUILD_BUG_ON(MODULES_LEN > (1UL << 31));
+ if (addr < (void *)MODULES_VADDR)
+ return 0;
+ if (addr > (void *)MODULES_END)
+ return 0;
+#endif
+ return 1;
+}
+
+static int __kprobes s390_get_insn_slot(struct kprobe *p)
+{
+ /*
+ * Get an insn slot that is within the same 2GB area like the original
+ * instruction. That way instructions with a 32bit signed displacement
+ * field can be patched and executed within the insn slot.
+ */
+ p->ainsn.insn = NULL;
+ if (is_kernel_addr(p->addr))
+ p->ainsn.insn = get_dmainsn_slot();
+ if (is_module_addr(p->addr))
+ p->ainsn.insn = get_insn_slot();
+ return p->ainsn.insn ? 0 : -ENOMEM;
+}
+
+static void __kprobes s390_free_insn_slot(struct kprobe *p)
+{
+ if (!p->ainsn.insn)
+ return;
+ if (is_kernel_addr(p->addr))
+ free_dmainsn_slot(p->ainsn.insn, 0);
+ else
+ free_insn_slot(p->ainsn.insn, 0);
+ p->ainsn.insn = NULL;
+}
+
int __kprobes arch_prepare_kprobe(struct kprobe *p)
{
if ((unsigned long) p->addr & 0x01)
return -EINVAL;
-
/* Make sure the probe isn't going on a difficult instruction */
if (is_prohibited_opcode(p->addr))
return -EINVAL;
-
+ if (s390_get_insn_slot(p))
+ return -ENOMEM;
p->opcode = *p->addr;
- memcpy(p->ainsn.insn, p->addr, ((p->opcode >> 14) + 3) & -2);
-
+ copy_instruction(p);
return 0;
}
@@ -186,6 +315,7 @@
void __kprobes arch_remove_kprobe(struct kprobe *p)
{
+ s390_free_insn_slot(p);
}
static void __kprobes enable_singlestep(struct kprobe_ctlblk *kcb,
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index ac21781..719e27b 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -50,7 +50,7 @@
/*
* Initialize CPU ELF notes
*/
-void setup_regs(void)
+static void setup_regs(void)
{
unsigned long sa = S390_lowcore.prefixreg_save_area + SAVE_AREA_BASE;
int cpu, this_cpu;
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index fb99c20..1105502 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -274,7 +274,7 @@
int flags = PMC_INIT;
on_each_cpu(setup_pmc_cpu, &flags, 1);
- measurement_alert_subclass_register();
+ irq_subclass_register(IRQ_SUBCLASS_MEASUREMENT_ALERT);
return 0;
}
@@ -285,7 +285,7 @@
int flags = PMC_RELEASE;
on_each_cpu(setup_pmc_cpu, &flags, 1);
- measurement_alert_subclass_unregister();
+ irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT);
}
/* Release the PMU if event is the last perf event */
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index 500aa10..2343c21 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -105,13 +105,10 @@
cpu = smp_processor_id();
memset(&cf_info, 0, sizeof(cf_info));
- if (!qctri(&cf_info)) {
+ if (!qctri(&cf_info))
pr_info("CPU[%i] CPUM_CF: ver=%u.%u A=%04x E=%04x C=%04x\n",
cpu, cf_info.cfvn, cf_info.csvn,
cf_info.auth_ctl, cf_info.enable_ctl, cf_info.act_ctl);
- print_hex_dump_bytes("CPUMF Query: ", DUMP_PREFIX_OFFSET,
- &cf_info, sizeof(cf_info));
- }
local_irq_restore(flags);
}
diff --git a/arch/s390/kernel/runtime_instr.c b/arch/s390/kernel/runtime_instr.c
index 077a993..e1c9d1c 100644
--- a/arch/s390/kernel/runtime_instr.c
+++ b/arch/s390/kernel/runtime_instr.c
@@ -139,10 +139,10 @@
if (!runtime_instr_avail())
return 0;
- measurement_alert_subclass_register();
+ irq_subclass_register(IRQ_SUBCLASS_MEASUREMENT_ALERT);
rc = register_external_interrupt(0x1407, runtime_instr_int_handler);
if (rc)
- measurement_alert_subclass_unregister();
+ irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT);
else
pr_info("Runtime instrumentation facility initialized\n");
return rc;
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index d386c4e..1a4313a 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -362,7 +362,7 @@
* Send cpus emergency shutdown signal. This gives the cpus the
* opportunity to complete outstanding interrupts.
*/
-void smp_emergency_stop(cpumask_t *cpumask)
+static void smp_emergency_stop(cpumask_t *cpumask)
{
u64 end;
int cpu;
diff --git a/arch/s390/kernel/suspend.c b/arch/s390/kernel/suspend.c
index 737bff3..a7a7537 100644
--- a/arch/s390/kernel/suspend.c
+++ b/arch/s390/kernel/suspend.c
@@ -13,6 +13,7 @@
#include <asm/ipl.h>
#include <asm/cio.h>
#include <asm/pci.h>
+#include "entry.h"
/*
* References to section boundaries
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index f00aefb..fc66792 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -302,6 +302,8 @@
address = trans_exc_code & __FAIL_ADDR_MASK;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
if (access == VM_WRITE || (trans_exc_code & store_indication) == 0x400)
flags |= FAULT_FLAG_WRITE;
down_read(&mm->mmap_sem);
@@ -673,7 +675,7 @@
rc = pfault_init() == 0 ? 0 : -EOPNOTSUPP;
if (rc)
goto out_pfault;
- service_subclass_irq_register();
+ irq_subclass_register(IRQ_SUBCLASS_SERVICE_SIGNAL);
hotcpu_notifier(pfault_cpu_notify, 0);
return 0;
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index 248445f..d261c62 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -223,6 +223,11 @@
return 0;
}
+int pmd_huge_support(void)
+{
+ return 1;
+}
+
struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
pmd_t *pmdp, int write)
{
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index 921fa54..d1e0e0c 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -14,6 +14,7 @@
#include <linux/gfp.h>
#include <linux/cpu.h>
#include <asm/ctl_reg.h>
+#include <asm/io.h>
/*
* This function writes to kernel memory bypassing DAT and possible
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index bf7c0dc..de8cbc3 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -245,7 +245,9 @@
* gmap_alloc_table is assumed to be called with mmap_sem held
*/
static int gmap_alloc_table(struct gmap *gmap,
- unsigned long *table, unsigned long init)
+ unsigned long *table, unsigned long init)
+ __releases(&gmap->mm->page_table_lock)
+ __acquires(&gmap->mm->page_table_lock)
{
struct page *page;
unsigned long *new;
@@ -966,7 +968,7 @@
tlb_remove_table(tlb, table);
}
-void __tlb_remove_table(void *_table)
+static void __tlb_remove_table(void *_table)
{
const unsigned long mask = (FRAG_MASK << 4) | FRAG_MASK;
void *table = (void *)((unsigned long) _table & ~mask);
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index d5f10a4..7092392 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -805,7 +805,7 @@
return NULL;
memset(header, 0, sz);
header->pages = sz / PAGE_SIZE;
- hole = sz - bpfsize + sizeof(*header);
+ hole = sz - (bpfsize + sizeof(*header));
/* Insert random number of illegal instructions before BPF code
* and make sure the first instruction starts at an even address.
*/
diff --git a/arch/s390/oprofile/hwsampler.c b/arch/s390/oprofile/hwsampler.c
index b5b2916..231ceca 100644
--- a/arch/s390/oprofile/hwsampler.c
+++ b/arch/s390/oprofile/hwsampler.c
@@ -1001,7 +1001,7 @@
if (hws_state != HWS_STOPPED)
goto deallocate_exit;
- measurement_alert_subclass_unregister();
+ irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT);
deallocate_sdbt();
hws_state = HWS_DEALLOCATED;
@@ -1115,7 +1115,7 @@
mutex_lock(&hws_sem);
if (hws_state == HWS_STOPPED) {
- measurement_alert_subclass_unregister();
+ irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT);
deallocate_sdbt();
}
if (hws_wq) {
@@ -1190,7 +1190,7 @@
hws_oom = 1;
hws_flush_all = 0;
/* now let them in, 1407 CPUMF external interrupts */
- measurement_alert_subclass_register();
+ irq_subclass_register(IRQ_SUBCLASS_MEASUREMENT_ALERT);
return 0;
}
diff --git a/arch/score/Kconfig b/arch/score/Kconfig
index 5fc2375..a1be70d 100644
--- a/arch/score/Kconfig
+++ b/arch/score/Kconfig
@@ -2,7 +2,6 @@
config SCORE
def_bool y
- select HAVE_GENERIC_HARDIRQS
select GENERIC_IRQ_SHOW
select GENERIC_IOMAP
select GENERIC_ATOMIC64
diff --git a/arch/score/mm/fault.c b/arch/score/mm/fault.c
index 6b18fb0..52238983 100644
--- a/arch/score/mm/fault.c
+++ b/arch/score/mm/fault.c
@@ -47,6 +47,7 @@
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
const int field = sizeof(unsigned long) * 2;
+ unsigned long flags = 0;
siginfo_t info;
int fault;
@@ -75,6 +76,9 @@
if (in_atomic() || !mm)
goto bad_area_nosemaphore;
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
+
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
if (!vma)
@@ -95,18 +99,18 @@
if (write) {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
} else {
if (!(vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)))
goto bad_area;
}
-survive:
/*
* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(mm, vma, address, write);
+ fault = handle_mm_fault(mm, vma, address, flags);
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
@@ -167,11 +171,6 @@
*/
out_of_memory:
up_read(&mm->mmap_sem);
- if (is_global_init(tsk)) {
- yield();
- down_read(&mm->mmap_sem);
- goto survive;
- }
if (!user_mode(regs))
goto no_context;
pagefault_out_of_memory();
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 1018ed3..224f4bc 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -26,7 +26,6 @@
select ARCH_WANT_IPC_PARSE_VERSION
select HAVE_SYSCALL_TRACEPOINTS
select HAVE_REGS_AND_STACK_ACCESS_API
- select HAVE_GENERIC_HARDIRQS
select MAY_HAVE_SPARSE_IRQ
select IRQ_FORCED_THREADING
select RTC_LIB
diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c
index 1f49c28a..541dc61 100644
--- a/arch/sh/mm/fault.c
+++ b/arch/sh/mm/fault.c
@@ -400,9 +400,7 @@
struct mm_struct *mm;
struct vm_area_struct * vma;
int fault;
- int write = error_code & FAULT_CODE_WRITE;
- unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (write ? FAULT_FLAG_WRITE : 0));
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
tsk = current;
mm = tsk->mm;
@@ -476,6 +474,11 @@
set_thread_fault_code(error_code);
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
+ if (error_code & FAULT_CODE_WRITE)
+ flags |= FAULT_FLAG_WRITE;
+
/*
* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
diff --git a/arch/sh/mm/hugetlbpage.c b/arch/sh/mm/hugetlbpage.c
index d776234..0d676a4 100644
--- a/arch/sh/mm/hugetlbpage.c
+++ b/arch/sh/mm/hugetlbpage.c
@@ -83,6 +83,11 @@
return 0;
}
+int pmd_huge_support(void)
+{
+ return 0;
+}
+
struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
pmd_t *pmd, int write)
{
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 1570ad2..2137ad6 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -26,7 +26,6 @@
select HAVE_DMA_ATTRS
select HAVE_DMA_API_DEBUG
select HAVE_ARCH_JUMP_LABEL
- select HAVE_GENERIC_HARDIRQS
select GENERIC_IRQ_SHOW
select ARCH_WANT_IPC_PARSE_VERSION
select USE_GENERIC_SMP_HELPERS if SMP
diff --git a/arch/sparc/kernel/sys_sparc32.c b/arch/sparc/kernel/sys_sparc32.c
index 3d0ddbc..7136885 100644
--- a/arch/sparc/kernel/sys_sparc32.c
+++ b/arch/sparc/kernel/sys_sparc32.c
@@ -169,10 +169,10 @@
new_ka.ka_restorer = restorer;
ret = get_user(u_handler, &act->sa_handler);
new_ka.sa.sa_handler = compat_ptr(u_handler);
- ret |= __copy_from_user(&set32, &act->sa_mask, sizeof(compat_sigset_t));
+ ret |= copy_from_user(&set32, &act->sa_mask, sizeof(compat_sigset_t));
sigset_from_compat(&new_ka.sa.sa_mask, &set32);
- ret |= __get_user(new_ka.sa.sa_flags, &act->sa_flags);
- ret |= __get_user(u_restorer, &act->sa_restorer);
+ ret |= get_user(new_ka.sa.sa_flags, &act->sa_flags);
+ ret |= get_user(u_restorer, &act->sa_restorer);
new_ka.sa.sa_restorer = compat_ptr(u_restorer);
if (ret)
return -EFAULT;
@@ -183,9 +183,9 @@
if (!ret && oact) {
sigset_to_compat(&set32, &old_ka.sa.sa_mask);
ret = put_user(ptr_to_compat(old_ka.sa.sa_handler), &oact->sa_handler);
- ret |= __copy_to_user(&oact->sa_mask, &set32, sizeof(compat_sigset_t));
- ret |= __put_user(old_ka.sa.sa_flags, &oact->sa_flags);
- ret |= __put_user(ptr_to_compat(old_ka.sa.sa_restorer), &oact->sa_restorer);
+ ret |= copy_to_user(&oact->sa_mask, &set32, sizeof(compat_sigset_t));
+ ret |= put_user(old_ka.sa.sa_flags, &oact->sa_flags);
+ ret |= put_user(ptr_to_compat(old_ka.sa.sa_restorer), &oact->sa_restorer);
if (ret)
ret = -EFAULT;
}
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index e98bfda..59dbd46 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -177,8 +177,7 @@
unsigned long g2;
int from_user = !(regs->psr & PSR_PS);
int fault, code;
- unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (write ? FAULT_FLAG_WRITE : 0));
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
if (text_fault)
address = regs->pc;
@@ -235,6 +234,11 @@
goto bad_area;
}
+ if (from_user)
+ flags |= FAULT_FLAG_USER;
+ if (write)
+ flags |= FAULT_FLAG_WRITE;
+
/*
* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
@@ -383,6 +387,7 @@
struct vm_area_struct *vma;
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
+ unsigned int flags = FAULT_FLAG_USER;
int code;
code = SEGV_MAPERR;
@@ -402,11 +407,12 @@
if (write) {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
} else {
if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
goto bad_area;
}
- switch (handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0)) {
+ switch (handle_mm_fault(mm, vma, address, flags)) {
case VM_FAULT_SIGBUS:
case VM_FAULT_OOM:
goto do_sigbus;
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 5062ff3..2ebec26 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -315,7 +315,8 @@
bad_kernel_pc(regs, address);
return;
}
- }
+ } else
+ flags |= FAULT_FLAG_USER;
/*
* If we're in an interrupt or have no user
@@ -418,13 +419,14 @@
vma->vm_file != NULL)
set_thread_fault_code(fault_code |
FAULT_CODE_BLKCOMMIT);
+
+ flags |= FAULT_FLAG_WRITE;
} else {
/* Allow reads even for write-only mappings */
if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
goto bad_area;
}
- flags |= ((fault_code & FAULT_CODE_WRITE) ? FAULT_FLAG_WRITE : 0);
fault = handle_mm_fault(mm, vma, address, flags);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index d2b5944..9639964 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -234,6 +234,11 @@
return 0;
}
+int pmd_huge_support(void)
+{
+ return 0;
+}
+
struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
pmd_t *pmd, int write)
{
diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig
index 932fa14..8a7cc66 100644
--- a/arch/tile/Kconfig
+++ b/arch/tile/Kconfig
@@ -11,7 +11,6 @@
select USE_GENERIC_SMP_HELPERS
select CC_OPTIMIZE_FOR_SIZE
select HAVE_DEBUG_KMEMLEAK
- select HAVE_GENERIC_HARDIRQS
select GENERIC_IRQ_PROBE
select GENERIC_PENDING_IRQ if SMP
select GENERIC_IRQ_SHOW
diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c
index 111d5a9..4c288f1 100644
--- a/arch/tile/mm/fault.c
+++ b/arch/tile/mm/fault.c
@@ -280,8 +280,7 @@
if (!is_page_fault)
write = 1;
- flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (write ? FAULT_FLAG_WRITE : 0));
+ flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
is_kernel_mode = !user_mode(regs);
@@ -365,6 +364,9 @@
goto bad_area_nosemaphore;
}
+ if (!is_kernel_mode)
+ flags |= FAULT_FLAG_USER;
+
/*
* When running in the kernel we expect faults to occur only to
* addresses in user space. All other faults represent errors in the
@@ -425,12 +427,12 @@
#endif
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
} else {
if (!is_page_fault || !(vma->vm_flags & VM_READ))
goto bad_area;
}
- survive:
/*
* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
@@ -555,11 +557,6 @@
*/
out_of_memory:
up_read(&mm->mmap_sem);
- if (is_global_init(tsk)) {
- yield();
- down_read(&mm->mmap_sem);
- goto survive;
- }
if (is_kernel_mode)
goto no_context;
pagefault_out_of_memory();
diff --git a/arch/tile/mm/hugetlbpage.c b/arch/tile/mm/hugetlbpage.c
index e514899..0cb3bba 100644
--- a/arch/tile/mm/hugetlbpage.c
+++ b/arch/tile/mm/hugetlbpage.c
@@ -166,6 +166,11 @@
return !!(pud_val(pud) & _PAGE_HUGE_PAGE);
}
+int pmd_huge_support(void)
+{
+ return 1;
+}
+
struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
pmd_t *pmd, int write)
{
diff --git a/arch/um/Kconfig.common b/arch/um/Kconfig.common
index bceee66..8ddea1f 100644
--- a/arch/um/Kconfig.common
+++ b/arch/um/Kconfig.common
@@ -6,7 +6,6 @@
config UML
bool
default y
- select HAVE_GENERIC_HARDIRQS
select HAVE_UID16
select GENERIC_IRQ_SHOW
select GENERIC_CPU_DEVICES
diff --git a/arch/um/defconfig b/arch/um/defconfig
index 08107a7..2665e6b 100644
--- a/arch/um/defconfig
+++ b/arch/um/defconfig
@@ -129,12 +129,10 @@
# CONFIG_FHANDLE is not set
# CONFIG_TASKSTATS is not set
# CONFIG_AUDIT is not set
-CONFIG_HAVE_GENERIC_HARDIRQS=y
#
# IRQ subsystem
#
-CONFIG_GENERIC_HARDIRQS=y
CONFIG_GENERIC_IRQ_SHOW=y
#
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index 089f398..5c3aef7 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -30,8 +30,7 @@
pmd_t *pmd;
pte_t *pte;
int err = -EFAULT;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (is_write ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
*code_out = SEGV_MAPERR;
@@ -42,6 +41,8 @@
if (in_atomic())
goto out_nosemaphore;
+ if (is_user)
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
@@ -58,12 +59,15 @@
good_area:
*code_out = SEGV_ACCERR;
- if (is_write && !(vma->vm_flags & VM_WRITE))
- goto out;
-
- /* Don't require VM_READ|VM_EXEC for write faults! */
- if (!is_write && !(vma->vm_flags & (VM_READ | VM_EXEC)))
- goto out;
+ if (is_write) {
+ if (!(vma->vm_flags & VM_WRITE))
+ goto out;
+ flags |= FAULT_FLAG_WRITE;
+ } else {
+ /* Don't require VM_READ|VM_EXEC for write faults! */
+ if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
+ goto out;
+ }
do {
int fault;
@@ -124,6 +128,8 @@
* (which will retry the fault, or kill us if we got oom-killed).
*/
up_read(&mm->mmap_sem);
+ if (!is_user)
+ goto out_nosemaphore;
pagefault_out_of_memory();
return 0;
}
diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig
index 41bcc00..82cdd89 100644
--- a/arch/unicore32/Kconfig
+++ b/arch/unicore32/Kconfig
@@ -2,7 +2,6 @@
def_bool y
select HAVE_MEMBLOCK
select HAVE_GENERIC_DMA_COHERENT
- select HAVE_GENERIC_HARDIRQS
select HAVE_DMA_ATTRS
select HAVE_KERNEL_GZIP
select HAVE_KERNEL_BZIP2
diff --git a/arch/unicore32/mm/fault.c b/arch/unicore32/mm/fault.c
index f9b5c10..0dc922d 100644
--- a/arch/unicore32/mm/fault.c
+++ b/arch/unicore32/mm/fault.c
@@ -209,8 +209,7 @@
struct task_struct *tsk;
struct mm_struct *mm;
int fault, sig, code;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- ((!(fsr ^ 0x12)) ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
tsk = current;
mm = tsk->mm;
@@ -222,6 +221,11 @@
if (in_atomic() || !mm)
goto no_context;
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
+ if (!(fsr ^ 0x12))
+ flags |= FAULT_FLAG_WRITE;
+
/*
* As per x86, we may deadlock here. However, since the kernel only
* validly references user space from well defined areas of the code,
@@ -278,6 +282,13 @@
(VM_FAULT_ERROR | VM_FAULT_BADMAP | VM_FAULT_BADACCESS))))
return 0;
+ /*
+ * If we are in kernel mode at this point, we
+ * have no context to handle this fault with.
+ */
+ if (!user_mode(regs))
+ goto no_context;
+
if (fault & VM_FAULT_OOM) {
/*
* We ran out of memory, call the OOM killer, and return to
@@ -288,13 +299,6 @@
return 0;
}
- /*
- * If we are in kernel mode at this point, we
- * have no context to handle this fault with.
- */
- if (!user_mode(regs))
- goto no_context;
-
if (fault & VM_FAULT_SIGBUS) {
/*
* We had some memory, but were unable to
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 30c40f0..e241a19 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -82,7 +82,6 @@
select HAVE_USER_RETURN_NOTIFIER
select ARCH_BINFMT_ELF_RANDOMIZE_PIE
select HAVE_ARCH_JUMP_LABEL
- select HAVE_GENERIC_HARDIRQS
select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
select SPARSE_IRQ
select GENERIC_FIND_FIRST_BIT
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 8d16bef..3d19994 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -315,21 +315,6 @@
return pmd_set_flags(pmd, _PAGE_SOFT_DIRTY);
}
-static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
-{
- return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY);
-}
-
-static inline int pte_swp_soft_dirty(pte_t pte)
-{
- return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY;
-}
-
-static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
-{
- return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY);
-}
-
static inline pte_t pte_file_clear_soft_dirty(pte_t pte)
{
return pte_clear_flags(pte, _PAGE_SOFT_DIRTY);
@@ -446,6 +431,7 @@
#ifndef __ASSEMBLY__
#include <linux/mm_types.h>
+#include <linux/mmdebug.h>
#include <linux/log2.h>
static inline int pte_none(pte_t pte)
@@ -864,6 +850,24 @@
{
}
+static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
+{
+ VM_BUG_ON(pte_present(pte));
+ return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY);
+}
+
+static inline int pte_swp_soft_dirty(pte_t pte)
+{
+ VM_BUG_ON(pte_present(pte));
+ return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY;
+}
+
+static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
+{
+ VM_BUG_ON(pte_present(pte));
+ return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY);
+}
+
#include <asm-generic/pgtable.h>
#endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index f4843e0..0ecac25 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -75,6 +75,9 @@
* with swap entry format. On x86 bits 6 and 7 are *not* involved
* into swap entry computation, but bit 6 is used for nonlinear
* file mapping, so we borrow bit 7 for soft dirty tracking.
+ *
+ * Please note that this bit must be treated as swap dirty page
+ * mark if and only if the PTE has present bit clear!
*/
#ifdef CONFIG_MEM_SOFT_DIRTY
#define _PAGE_SWP_SOFT_DIRTY _PAGE_PSE
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index cf51200..e6d90ba 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -62,6 +62,7 @@
static inline void __flush_tlb_one(unsigned long addr)
{
+ count_vm_event(NR_TLB_LOCAL_FLUSH_ONE);
__flush_tlb_single(addr);
}
@@ -84,14 +85,38 @@
#ifndef CONFIG_SMP
-#define flush_tlb() __flush_tlb()
-#define flush_tlb_all() __flush_tlb_all()
-#define local_flush_tlb() __flush_tlb()
+/* "_up" is for UniProcessor.
+ *
+ * This is a helper for other header functions. *Not* intended to be called
+ * directly. All global TLB flushes need to either call this, or to bump the
+ * vm statistics themselves.
+ */
+static inline void __flush_tlb_up(void)
+{
+ count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+ __flush_tlb();
+}
+
+static inline void flush_tlb_all(void)
+{
+ count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+ __flush_tlb_all();
+}
+
+static inline void flush_tlb(void)
+{
+ __flush_tlb_up();
+}
+
+static inline void local_flush_tlb(void)
+{
+ __flush_tlb_up();
+}
static inline void flush_tlb_mm(struct mm_struct *mm)
{
if (mm == current->active_mm)
- __flush_tlb();
+ __flush_tlb_up();
}
static inline void flush_tlb_page(struct vm_area_struct *vma,
@@ -105,14 +130,14 @@
unsigned long start, unsigned long end)
{
if (vma->vm_mm == current->active_mm)
- __flush_tlb();
+ __flush_tlb_up();
}
static inline void flush_tlb_mm_range(struct mm_struct *mm,
unsigned long start, unsigned long end, unsigned long vmflag)
{
if (mm == current->active_mm)
- __flush_tlb();
+ __flush_tlb_up();
}
static inline void native_flush_tlb_others(const struct cpumask *cpumask,
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index d4cdfa6..ce2d0a2 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -683,6 +683,7 @@
}
/* Flush all TLBs via a mov %cr3, %reg; mov %reg, %cr3 */
+ count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
__flush_tlb();
/* Save MTRR state */
@@ -696,6 +697,7 @@
static void post_set(void) __releases(set_atomicity_lock)
{
/* Flush TLBs (no need to flush caches - they are disabled) */
+ count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
__flush_tlb();
/* Intel (P6) standard MTRRs */
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 0abf674..c62d883 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -124,6 +124,7 @@
INTEL_UEVENT_CONSTRAINT(0x0148, 0x4), /* L1D_PEND_MISS.PENDING */
INTEL_UEVENT_CONSTRAINT(0x0279, 0xf), /* IDQ.EMTPY */
INTEL_UEVENT_CONSTRAINT(0x019c, 0xf), /* IDQ_UOPS_NOT_DELIVERED.CORE */
+ INTEL_UEVENT_CONSTRAINT(0x02a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_LDM_PENDING */
INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */
INTEL_UEVENT_CONSTRAINT(0x05a3, 0xf), /* CYCLE_ACTIVITY.STALLS_L2_PENDING */
INTEL_UEVENT_CONSTRAINT(0x06a3, 0xf), /* CYCLE_ACTIVITY.STALLS_LDM_PENDING */
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index fd8011e..8ed4458 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -2808,7 +2808,7 @@
return c;
}
- if (event->hw.config == ~0ULL)
+ if (event->attr.config == UNCORE_FIXED_EVENT)
return &constraint_fixed;
if (type->constraints) {
@@ -3112,7 +3112,9 @@
*/
if (pmu->type->single_fixed && pmu->pmu_idx > 0)
return -EINVAL;
- hwc->config = ~0ULL;
+
+ /* fixed counters have event field hardcoded to zero */
+ hwc->config = 0ULL;
} else {
hwc->config = event->attr.config & pmu->type->event_mask;
if (pmu->type->ops->hw_config) {
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 6e2d2c8..dce0df8 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -4421,13 +4421,12 @@
}
}
-static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc)
+static unsigned long
+mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
{
struct kvm *kvm;
int nr_to_scan = sc->nr_to_scan;
-
- if (nr_to_scan == 0)
- goto out;
+ unsigned long freed = 0;
raw_spin_lock(&kvm_lock);
@@ -4462,25 +4461,37 @@
goto unlock;
}
- prepare_zap_oldest_mmu_page(kvm, &invalid_list);
+ if (prepare_zap_oldest_mmu_page(kvm, &invalid_list))
+ freed++;
kvm_mmu_commit_zap_page(kvm, &invalid_list);
unlock:
spin_unlock(&kvm->mmu_lock);
srcu_read_unlock(&kvm->srcu, idx);
+ /*
+ * unfair on small ones
+ * per-vm shrinkers cry out
+ * sadness comes quickly
+ */
list_move_tail(&kvm->vm_list, &vm_list);
break;
}
raw_spin_unlock(&kvm_lock);
+ return freed;
-out:
+}
+
+static unsigned long
+mmu_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
+{
return percpu_counter_read_positive(&kvm_total_used_mmu_pages);
}
static struct shrinker mmu_shrinker = {
- .shrink = mmu_shrink,
+ .count_objects = mmu_shrink_count,
+ .scan_objects = mmu_shrink_scan,
.seeks = DEFAULT_SEEKS * 10,
};
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 654be4a..3aaeffc 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -842,23 +842,15 @@
force_sig_info_fault(SIGBUS, code, address, tsk, fault);
}
-static noinline int
+static noinline void
mm_fault_error(struct pt_regs *regs, unsigned long error_code,
unsigned long address, unsigned int fault)
{
- /*
- * Pagefault was interrupted by SIGKILL. We have no reason to
- * continue pagefault.
- */
- if (fatal_signal_pending(current)) {
- if (!(fault & VM_FAULT_RETRY))
- up_read(¤t->mm->mmap_sem);
- if (!(error_code & PF_USER))
- no_context(regs, error_code, address, 0, 0);
- return 1;
+ if (fatal_signal_pending(current) && !(error_code & PF_USER)) {
+ up_read(¤t->mm->mmap_sem);
+ no_context(regs, error_code, address, 0, 0);
+ return;
}
- if (!(fault & VM_FAULT_ERROR))
- return 0;
if (fault & VM_FAULT_OOM) {
/* Kernel mode? Handle exceptions or die: */
@@ -866,7 +858,7 @@
up_read(¤t->mm->mmap_sem);
no_context(regs, error_code, address,
SIGSEGV, SEGV_MAPERR);
- return 1;
+ return;
}
up_read(¤t->mm->mmap_sem);
@@ -884,7 +876,6 @@
else
BUG();
}
- return 1;
}
static int spurious_fault_check(unsigned long error_code, pte_t *pte)
@@ -1011,9 +1002,7 @@
unsigned long address;
struct mm_struct *mm;
int fault;
- int write = error_code & PF_WRITE;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (write ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
tsk = current;
mm = tsk->mm;
@@ -1083,6 +1072,7 @@
if (user_mode_vm(regs)) {
local_irq_enable();
error_code |= PF_USER;
+ flags |= FAULT_FLAG_USER;
} else {
if (regs->flags & X86_EFLAGS_IF)
local_irq_enable();
@@ -1109,6 +1099,9 @@
return;
}
+ if (error_code & PF_WRITE)
+ flags |= FAULT_FLAG_WRITE;
+
/*
* When running in the kernel we expect faults to occur only to
* addresses in user space. All other faults represent errors in
@@ -1187,9 +1180,17 @@
*/
fault = handle_mm_fault(mm, vma, address, flags);
- if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) {
- if (mm_fault_error(regs, error_code, address, fault))
- return;
+ /*
+ * If we need to retry but a fatal signal is pending, handle the
+ * signal first. We do not need to release the mmap_sem because it
+ * would already be released in __lock_page_or_retry in mm/filemap.c.
+ */
+ if (unlikely((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)))
+ return;
+
+ if (unlikely(fault & VM_FAULT_ERROR)) {
+ mm_fault_error(regs, error_code, address, fault);
+ return;
}
/*
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 7e73e8c..9d980d8 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -59,6 +59,10 @@
return NULL;
}
+int pmd_huge_support(void)
+{
+ return 0;
+}
#else
struct page *
@@ -77,6 +81,10 @@
return !!(pud_val(pud) & _PAGE_PSE);
}
+int pmd_huge_support(void)
+{
+ return 1;
+}
#endif
/* x86_64 also uses this file */
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 282375f..ae699b3 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -103,6 +103,7 @@
if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm))
return;
+ count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
if (f->flush_end == TLB_FLUSH_ALL)
local_flush_tlb();
@@ -130,6 +131,7 @@
info.flush_start = start;
info.flush_end = end;
+ count_vm_event(NR_TLB_REMOTE_FLUSH);
if (is_uv_system()) {
unsigned int cpu;
@@ -149,6 +151,7 @@
preempt_disable();
+ count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
local_flush_tlb();
if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL);
@@ -211,16 +214,19 @@
act_entries = mm->total_vm > tlb_entries ? tlb_entries : mm->total_vm;
/* tlb_flushall_shift is on balance point, details in commit log */
- if ((end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift)
+ if ((end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift) {
+ count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
local_flush_tlb();
- else {
+ } else {
if (has_large_page(mm, start, end)) {
local_flush_tlb();
goto flush_all;
}
/* flush range by one by one 'invlpg' */
- for (addr = start; addr < end; addr += PAGE_SIZE)
+ for (addr = start; addr < end; addr += PAGE_SIZE) {
+ count_vm_event(NR_TLB_LOCAL_FLUSH_ONE);
__flush_tlb_single(addr);
+ }
if (cpumask_any_but(mm_cpumask(mm),
smp_processor_id()) < nr_cpu_ids)
@@ -256,6 +262,7 @@
static void do_flush_tlb_all(void *info)
{
+ count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
__flush_tlb_all();
if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY)
leave_mm(smp_processor_id());
@@ -263,6 +270,7 @@
void flush_tlb_all(void)
{
+ count_vm_event(NR_TLB_REMOTE_FLUSH);
on_each_cpu(do_flush_tlb_all, NULL, 1);
}
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 7ea6451..8d24dcb 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -7,7 +7,6 @@
select HAVE_IDE
select GENERIC_ATOMIC64
select GENERIC_CLOCKEVENTS
- select HAVE_GENERIC_HARDIRQS
select VIRT_TO_BUS
select GENERIC_IRQ_SHOW
select GENERIC_CPU_DEVICES
diff --git a/arch/xtensa/Makefile b/arch/xtensa/Makefile
index 136224b..81250ec 100644
--- a/arch/xtensa/Makefile
+++ b/arch/xtensa/Makefile
@@ -55,10 +55,10 @@
LDFLAGS := --no-relax
endif
-ifeq ($(shell echo -e __XTENSA_EB__ | $(CC) -E - | grep -v "\#"),1)
+ifeq ($(shell echo __XTENSA_EB__ | $(CC) -E - | grep -v "\#"),1)
CHECKFLAGS += -D__XTENSA_EB__
endif
-ifeq ($(shell echo -e __XTENSA_EL__ | $(CC) -E - | grep -v "\#"),1)
+ifeq ($(shell echo __XTENSA_EL__ | $(CC) -E - | grep -v "\#"),1)
CHECKFLAGS += -D__XTENSA_EL__
endif
diff --git a/arch/xtensa/boot/Makefile b/arch/xtensa/boot/Makefile
index 64ffc4b..ca20a89 100644
--- a/arch/xtensa/boot/Makefile
+++ b/arch/xtensa/boot/Makefile
@@ -12,7 +12,7 @@
KBUILD_CFLAGS += -fno-builtin -Iarch/$(ARCH)/boot/include
HOSTFLAGS += -Iarch/$(ARCH)/boot/include
-BIG_ENDIAN := $(shell echo -e __XTENSA_EB__ | $(CC) -E - | grep -v "\#")
+BIG_ENDIAN := $(shell echo __XTENSA_EB__ | $(CC) -E - | grep -v "\#")
export ccflags-y
export BIG_ENDIAN
diff --git a/arch/xtensa/configs/common_defconfig b/arch/xtensa/configs/common_defconfig
index a182a4e..f6000fe 100644
--- a/arch/xtensa/configs/common_defconfig
+++ b/arch/xtensa/configs/common_defconfig
@@ -8,7 +8,6 @@
# CONFIG_UID16 is not set
CONFIG_RWSEM_XCHGADD_ALGORITHM=y
CONFIG_HAVE_DEC_LOCK=y
-CONFIG_GENERIC_HARDIRQS=y
#
# Code maturity level options
diff --git a/arch/xtensa/configs/iss_defconfig b/arch/xtensa/configs/iss_defconfig
index 77c52f8..4f23320 100644
--- a/arch/xtensa/configs/iss_defconfig
+++ b/arch/xtensa/configs/iss_defconfig
@@ -9,7 +9,6 @@
CONFIG_RWSEM_XCHGADD_ALGORITHM=y
CONFIG_GENERIC_FIND_NEXT_BIT=y
CONFIG_GENERIC_HWEIGHT=y
-CONFIG_GENERIC_HARDIRQS=y
# CONFIG_ARCH_HAS_ILOG2_U32 is not set
# CONFIG_ARCH_HAS_ILOG2_U64 is not set
CONFIG_NO_IOPORT=y
diff --git a/arch/xtensa/configs/s6105_defconfig b/arch/xtensa/configs/s6105_defconfig
index 4799c6a..d929f77 100644
--- a/arch/xtensa/configs/s6105_defconfig
+++ b/arch/xtensa/configs/s6105_defconfig
@@ -9,7 +9,6 @@
CONFIG_RWSEM_XCHGADD_ALGORITHM=y
CONFIG_GENERIC_FIND_NEXT_BIT=y
CONFIG_GENERIC_HWEIGHT=y
-CONFIG_GENERIC_HARDIRQS=y
# CONFIG_ARCH_HAS_ILOG2_U32 is not set
# CONFIG_ARCH_HAS_ILOG2_U64 is not set
CONFIG_NO_IOPORT=y
diff --git a/arch/xtensa/include/asm/regs.h b/arch/xtensa/include/asm/regs.h
index b24de67..4ba9f51 100644
--- a/arch/xtensa/include/asm/regs.h
+++ b/arch/xtensa/include/asm/regs.h
@@ -82,6 +82,7 @@
#define PS_CALLINC_SHIFT 16
#define PS_CALLINC_MASK 0x00030000
#define PS_OWB_SHIFT 8
+#define PS_OWB_WIDTH 4
#define PS_OWB_MASK 0x00000F00
#define PS_RING_SHIFT 6
#define PS_RING_MASK 0x000000C0
diff --git a/arch/xtensa/include/asm/timex.h b/arch/xtensa/include/asm/timex.h
index 69f9017..27fa3c1 100644
--- a/arch/xtensa/include/asm/timex.h
+++ b/arch/xtensa/include/asm/timex.h
@@ -35,13 +35,7 @@
# error "Bad timer number for Linux configurations!"
#endif
-#ifdef CONFIG_XTENSA_CALIBRATE_CCOUNT
extern unsigned long ccount_freq;
-#define CCOUNT_PER_JIFFY (ccount_freq / HZ)
-#else
-#define CCOUNT_PER_JIFFY (CONFIG_XTENSA_CPU_CLOCK*(1000000UL/HZ))
-#endif
-
typedef unsigned long long cycles_t;
diff --git a/arch/xtensa/kernel/align.S b/arch/xtensa/kernel/align.S
index aa2e87b..d4cef60 100644
--- a/arch/xtensa/kernel/align.S
+++ b/arch/xtensa/kernel/align.S
@@ -146,9 +146,9 @@
* a0: trashed, original value saved on stack (PT_AREG0)
* a1: a1
* a2: new stack pointer, original in DEPC
- * a3: dispatch table
+ * a3: a3
* depc: a2, original value saved on stack (PT_DEPC)
- * excsave_1: a3
+ * excsave_1: dispatch table
*
* PT_DEPC >= VALID_DOUBLE_EXCEPTION_ADDRESS: double exception, DEPC
* < VALID_DOUBLE_EXCEPTION_ADDRESS: regular exception
@@ -171,7 +171,6 @@
s32i a8, a2, PT_AREG8
rsr a0, depc
- xsr a3, excsave1
s32i a0, a2, PT_AREG2
s32i a3, a2, PT_AREG3
diff --git a/arch/xtensa/kernel/coprocessor.S b/arch/xtensa/kernel/coprocessor.S
index 6476574..a482df5 100644
--- a/arch/xtensa/kernel/coprocessor.S
+++ b/arch/xtensa/kernel/coprocessor.S
@@ -32,9 +32,9 @@
* a0: trashed, original value saved on stack (PT_AREG0)
* a1: a1
* a2: new stack pointer, original in DEPC
- * a3: dispatch table
+ * a3: a3
* depc: a2, original value saved on stack (PT_DEPC)
- * excsave_1: a3
+ * excsave_1: dispatch table
*
* PT_DEPC >= VALID_DOUBLE_EXCEPTION_ADDRESS: double exception, DEPC
* < VALID_DOUBLE_EXCEPTION_ADDRESS: regular exception
@@ -225,9 +225,9 @@
* a0: trashed, original value saved on stack (PT_AREG0)
* a1: a1
* a2: new stack pointer, original in DEPC
- * a3: dispatch table
+ * a3: a3
* depc: a2, original value saved on stack (PT_DEPC)
- * excsave_1: a3
+ * excsave_1: dispatch table
*
* PT_DEPC >= VALID_DOUBLE_EXCEPTION_ADDRESS: double exception, DEPC
* < VALID_DOUBLE_EXCEPTION_ADDRESS: regular exception
@@ -245,7 +245,6 @@
/* Save remaining registers a1-a3 and SAR */
- xsr a3, excsave1
s32i a3, a2, PT_AREG3
rsr a3, sar
s32i a1, a2, PT_AREG1
diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S
index 9298742..de1dfa1 100644
--- a/arch/xtensa/kernel/entry.S
+++ b/arch/xtensa/kernel/entry.S
@@ -31,8 +31,6 @@
/* Unimplemented features. */
#undef KERNEL_STACK_OVERFLOW_CHECK
-#undef PREEMPTIBLE_KERNEL
-#undef ALLOCA_EXCEPTION_IN_IRAM
/* Not well tested.
*
@@ -92,9 +90,9 @@
* a0: trashed, original value saved on stack (PT_AREG0)
* a1: a1
* a2: new stack pointer, original value in depc
- * a3: dispatch table
+ * a3: a3
* depc: a2, original value saved on stack (PT_DEPC)
- * excsave1: a3
+ * excsave1: dispatch table
*
* PT_DEPC >= VALID_DOUBLE_EXCEPTION_ADDRESS: double exception, DEPC
* < VALID_DOUBLE_EXCEPTION_ADDRESS: regular exception
@@ -110,9 +108,8 @@
ENTRY(user_exception)
- /* Save a2, a3, and depc, restore excsave_1 and set SP. */
+ /* Save a1, a2, a3, and set SP. */
- xsr a3, excsave1
rsr a0, depc
s32i a1, a2, PT_AREG1
s32i a0, a2, PT_AREG2
@@ -238,9 +235,9 @@
* a0: trashed, original value saved on stack (PT_AREG0)
* a1: a1
* a2: new stack pointer, original in DEPC
- * a3: dispatch table
+ * a3: a3
* depc: a2, original value saved on stack (PT_DEPC)
- * excsave_1: a3
+ * excsave_1: dispatch table
*
* PT_DEPC >= VALID_DOUBLE_EXCEPTION_ADDRESS: double exception, DEPC
* < VALID_DOUBLE_EXCEPTION_ADDRESS: regular exception
@@ -256,9 +253,8 @@
ENTRY(kernel_exception)
- /* Save a0, a2, a3, DEPC and set SP. */
+ /* Save a1, a2, a3, and set SP. */
- xsr a3, excsave1 # restore a3, excsave_1
rsr a0, depc # get a2
s32i a1, a2, PT_AREG1
s32i a0, a2, PT_AREG2
@@ -409,7 +405,7 @@
* exception handler and call the exception handler.
*/
- movi a4, exc_table
+ rsr a4, excsave1
mov a6, a1 # pass stack frame
mov a7, a0 # pass EXCCAUSE
addx4 a4, a0, a4
@@ -423,6 +419,67 @@
.global common_exception_return
common_exception_return:
+1:
+ rsil a2, LOCKLEVEL
+
+ /* Jump if we are returning from kernel exceptions. */
+
+ l32i a3, a1, PT_PS
+ GET_THREAD_INFO(a2, a1)
+ l32i a4, a2, TI_FLAGS
+ _bbci.l a3, PS_UM_BIT, 6f
+
+ /* Specific to a user exception exit:
+ * We need to check some flags for signal handling and rescheduling,
+ * and have to restore WB and WS, extra states, and all registers
+ * in the register file that were in use in the user task.
+ * Note that we don't disable interrupts here.
+ */
+
+ _bbsi.l a4, TIF_NEED_RESCHED, 3f
+ _bbsi.l a4, TIF_NOTIFY_RESUME, 2f
+ _bbci.l a4, TIF_SIGPENDING, 5f
+
+2: l32i a4, a1, PT_DEPC
+ bgeui a4, VALID_DOUBLE_EXCEPTION_ADDRESS, 4f
+
+ /* Call do_signal() */
+
+ rsil a2, 0
+ movi a4, do_notify_resume # int do_notify_resume(struct pt_regs*)
+ mov a6, a1
+ callx4 a4
+ j 1b
+
+3: /* Reschedule */
+
+ rsil a2, 0
+ movi a4, schedule # void schedule (void)
+ callx4 a4
+ j 1b
+
+#ifdef CONFIG_PREEMPT
+6:
+ _bbci.l a4, TIF_NEED_RESCHED, 4f
+
+ /* Check current_thread_info->preempt_count */
+
+ l32i a4, a2, TI_PRE_COUNT
+ bnez a4, 4f
+ movi a4, preempt_schedule_irq
+ callx4 a4
+ j 1b
+#endif
+
+5:
+#ifdef CONFIG_DEBUG_TLB_SANITY
+ l32i a4, a1, PT_DEPC
+ bgeui a4, VALID_DOUBLE_EXCEPTION_ADDRESS, 4f
+ movi a4, check_tlb_sanity
+ callx4 a4
+#endif
+6:
+4:
#ifdef CONFIG_TRACE_IRQFLAGS
l32i a4, a1, PT_DEPC
/* Double exception means we came here with an exception
@@ -438,52 +495,7 @@
callx4 a4
1:
#endif
-
- /* Jump if we are returning from kernel exceptions. */
-
-1: l32i a3, a1, PT_PS
- _bbci.l a3, PS_UM_BIT, 4f
-
- rsil a2, 0
-
- /* Specific to a user exception exit:
- * We need to check some flags for signal handling and rescheduling,
- * and have to restore WB and WS, extra states, and all registers
- * in the register file that were in use in the user task.
- * Note that we don't disable interrupts here.
- */
-
- GET_THREAD_INFO(a2,a1)
- l32i a4, a2, TI_FLAGS
-
- _bbsi.l a4, TIF_NEED_RESCHED, 3f
- _bbsi.l a4, TIF_NOTIFY_RESUME, 2f
- _bbci.l a4, TIF_SIGPENDING, 5f
-
-2: l32i a4, a1, PT_DEPC
- bgeui a4, VALID_DOUBLE_EXCEPTION_ADDRESS, 4f
-
- /* Call do_signal() */
-
- movi a4, do_notify_resume # int do_notify_resume(struct pt_regs*)
- mov a6, a1
- callx4 a4
- j 1b
-
-3: /* Reschedule */
-
- movi a4, schedule # void schedule (void)
- callx4 a4
- j 1b
-
-5:
-#ifdef CONFIG_DEBUG_TLB_SANITY
- l32i a4, a1, PT_DEPC
- bgeui a4, VALID_DOUBLE_EXCEPTION_ADDRESS, 4f
- movi a4, check_tlb_sanity
- callx4 a4
-#endif
-4: /* Restore optional registers. */
+ /* Restore optional registers. */
load_xtregs_opt a1 a2 a4 a5 a6 a7 PT_XTREGS_OPT
@@ -570,29 +582,6 @@
kernel_exception_exit:
-#ifdef PREEMPTIBLE_KERNEL
-
-#ifdef CONFIG_PREEMPT
-
- /*
- * Note: We've just returned from a call4, so we have
- * at least 4 addt'l regs.
- */
-
- /* Check current_thread_info->preempt_count */
-
- GET_THREAD_INFO(a2)
- l32i a3, a2, TI_PREEMPT
- bnez a3, 1f
-
- l32i a2, a2, TI_FLAGS
-
-1:
-
-#endif
-
-#endif
-
/* Check if we have to do a movsp.
*
* We only have to do a movsp if the previous window-frame has
@@ -829,176 +818,63 @@
*
* The ALLOCA handler is entered when user code executes the MOVSP
* instruction and the caller's frame is not in the register file.
- * In this case, the caller frame's a0..a3 are on the stack just
- * below sp (a1), and this handler moves them.
*
- * For "MOVSP <ar>,<as>" without destination register a1, this routine
- * simply moves the value from <as> to <ar> without moving the save area.
+ * This algorithm was taken from the Ross Morley's RTOS Porting Layer:
+ *
+ * /home/ross/rtos/porting/XtensaRTOS-PortingLayer-20090507/xtensa_vectors.S
+ *
+ * It leverages the existing window spill/fill routines and their support for
+ * double exceptions. The 'movsp' instruction will only cause an exception if
+ * the next window needs to be loaded. In fact this ALLOCA exception may be
+ * replaced at some point by changing the hardware to do a underflow exception
+ * of the proper size instead.
+ *
+ * This algorithm simply backs out the register changes started by the user
+ * excpetion handler, makes it appear that we have started a window underflow
+ * by rotating the window back and then setting the old window base (OWB) in
+ * the 'ps' register with the rolled back window base. The 'movsp' instruction
+ * will be re-executed and this time since the next window frames is in the
+ * active AR registers it won't cause an exception.
+ *
+ * If the WindowUnderflow code gets a TLB miss the page will get mapped
+ * the the partial windeowUnderflow will be handeled in the double exception
+ * handler.
*
* Entry condition:
*
* a0: trashed, original value saved on stack (PT_AREG0)
* a1: a1
* a2: new stack pointer, original in DEPC
- * a3: dispatch table
+ * a3: a3
* depc: a2, original value saved on stack (PT_DEPC)
- * excsave_1: a3
+ * excsave_1: dispatch table
*
* PT_DEPC >= VALID_DOUBLE_EXCEPTION_ADDRESS: double exception, DEPC
* < VALID_DOUBLE_EXCEPTION_ADDRESS: regular exception
*/
-#if XCHAL_HAVE_BE
-#define _EXTUI_MOVSP_SRC(ar) extui ar, ar, 4, 4
-#define _EXTUI_MOVSP_DST(ar) extui ar, ar, 0, 4
-#else
-#define _EXTUI_MOVSP_SRC(ar) extui ar, ar, 0, 4
-#define _EXTUI_MOVSP_DST(ar) extui ar, ar, 4, 4
-#endif
-
ENTRY(fast_alloca)
+ rsr a0, windowbase
+ rotw -1
+ rsr a2, ps
+ extui a3, a2, PS_OWB_SHIFT, PS_OWB_WIDTH
+ xor a3, a3, a4
+ l32i a4, a6, PT_AREG0
+ l32i a1, a6, PT_DEPC
+ rsr a6, depc
+ wsr a1, depc
+ slli a3, a3, PS_OWB_SHIFT
+ xor a2, a2, a3
+ wsr a2, ps
+ rsync
- /* We shouldn't be in a double exception. */
-
- l32i a0, a2, PT_DEPC
- _bgeui a0, VALID_DOUBLE_EXCEPTION_ADDRESS, .Lunhandled_double
-
- rsr a0, depc # get a2
- s32i a4, a2, PT_AREG4 # save a4 and
- s32i a0, a2, PT_AREG2 # a2 to stack
-
- /* Exit critical section. */
-
- movi a0, 0
- s32i a0, a3, EXC_TABLE_FIXUP
-
- /* Restore a3, excsave_1 */
-
- xsr a3, excsave1 # make sure excsave_1 is valid for dbl.
- rsr a4, epc1 # get exception address
- s32i a3, a2, PT_AREG3 # save a3 to stack
-
-#ifdef ALLOCA_EXCEPTION_IN_IRAM
-#error iram not supported
-#else
- /* Note: l8ui not allowed in IRAM/IROM!! */
- l8ui a0, a4, 1 # read as(src) from MOVSP instruction
-#endif
- movi a3, .Lmovsp_src
- _EXTUI_MOVSP_SRC(a0) # extract source register number
- addx8 a3, a0, a3
- jx a3
-
-.Lunhandled_double:
- wsr a0, excsave1
- movi a0, unrecoverable_exception
- callx0 a0
-
- .align 8
-.Lmovsp_src:
- l32i a3, a2, PT_AREG0; _j 1f; .align 8
- mov a3, a1; _j 1f; .align 8
- l32i a3, a2, PT_AREG2; _j 1f; .align 8
- l32i a3, a2, PT_AREG3; _j 1f; .align 8
- l32i a3, a2, PT_AREG4; _j 1f; .align 8
- mov a3, a5; _j 1f; .align 8
- mov a3, a6; _j 1f; .align 8
- mov a3, a7; _j 1f; .align 8
- mov a3, a8; _j 1f; .align 8
- mov a3, a9; _j 1f; .align 8
- mov a3, a10; _j 1f; .align 8
- mov a3, a11; _j 1f; .align 8
- mov a3, a12; _j 1f; .align 8
- mov a3, a13; _j 1f; .align 8
- mov a3, a14; _j 1f; .align 8
- mov a3, a15; _j 1f; .align 8
-
-1:
-
-#ifdef ALLOCA_EXCEPTION_IN_IRAM
-#error iram not supported
-#else
- l8ui a0, a4, 0 # read ar(dst) from MOVSP instruction
-#endif
- addi a4, a4, 3 # step over movsp
- _EXTUI_MOVSP_DST(a0) # extract destination register
- wsr a4, epc1 # save new epc_1
-
- _bnei a0, 1, 1f # no 'movsp a1, ax': jump
-
- /* Move the save area. This implies the use of the L32E
- * and S32E instructions, because this move must be done with
- * the user's PS.RING privilege levels, not with ring 0
- * (kernel's) privileges currently active with PS.EXCM
- * set. Note that we have stil registered a fixup routine with the
- * double exception vector in case a double exception occurs.
- */
-
- /* a0,a4:avail a1:old user stack a2:exc. stack a3:new user stack. */
-
- l32e a0, a1, -16
- l32e a4, a1, -12
- s32e a0, a3, -16
- s32e a4, a3, -12
- l32e a0, a1, -8
- l32e a4, a1, -4
- s32e a0, a3, -8
- s32e a4, a3, -4
-
- /* Restore stack-pointer and all the other saved registers. */
-
- mov a1, a3
-
- l32i a4, a2, PT_AREG4
- l32i a3, a2, PT_AREG3
- l32i a0, a2, PT_AREG0
- l32i a2, a2, PT_AREG2
- rfe
-
- /* MOVSP <at>,<as> was invoked with <at> != a1.
- * Because the stack pointer is not being modified,
- * we should be able to just modify the pointer
- * without moving any save area.
- * The processor only traps these occurrences if the
- * caller window isn't live, so unfortunately we can't
- * use this as an alternate trap mechanism.
- * So we just do the move. This requires that we
- * resolve the destination register, not just the source,
- * so there's some extra work.
- * (PERHAPS NOT REALLY NEEDED, BUT CLEANER...)
- */
-
- /* a0 dst-reg, a1 user-stack, a2 stack, a3 value of src reg. */
-
-1: movi a4, .Lmovsp_dst
- addx8 a4, a0, a4
- jx a4
-
- .align 8
-.Lmovsp_dst:
- s32i a3, a2, PT_AREG0; _j 1f; .align 8
- mov a1, a3; _j 1f; .align 8
- s32i a3, a2, PT_AREG2; _j 1f; .align 8
- s32i a3, a2, PT_AREG3; _j 1f; .align 8
- s32i a3, a2, PT_AREG4; _j 1f; .align 8
- mov a5, a3; _j 1f; .align 8
- mov a6, a3; _j 1f; .align 8
- mov a7, a3; _j 1f; .align 8
- mov a8, a3; _j 1f; .align 8
- mov a9, a3; _j 1f; .align 8
- mov a10, a3; _j 1f; .align 8
- mov a11, a3; _j 1f; .align 8
- mov a12, a3; _j 1f; .align 8
- mov a13, a3; _j 1f; .align 8
- mov a14, a3; _j 1f; .align 8
- mov a15, a3; _j 1f; .align 8
-
-1: l32i a4, a2, PT_AREG4
- l32i a3, a2, PT_AREG3
- l32i a0, a2, PT_AREG0
- l32i a2, a2, PT_AREG2
- rfe
-
+ _bbci.l a4, 31, 4f
+ rotw -1
+ _bbci.l a8, 30, 8f
+ rotw -1
+ j _WindowUnderflow12
+8: j _WindowUnderflow8
+4: j _WindowUnderflow4
ENDPROC(fast_alloca)
/*
@@ -1015,9 +891,9 @@
* a0: trashed, original value saved on stack (PT_AREG0)
* a1: a1
* a2: new stack pointer, original in DEPC
- * a3: dispatch table
+ * a3: a3
* depc: a2, original value saved on stack (PT_DEPC)
- * excsave_1: a3
+ * excsave_1: dispatch table
*/
ENTRY(fast_syscall_kernel)
@@ -1064,7 +940,6 @@
l32i a0, a2, PT_AREG0 # restore a0
xsr a2, depc # restore a2, depc
- rsr a3, excsave1
wsr a0, excsave1
movi a0, unrecoverable_exception
@@ -1086,10 +961,10 @@
* a0: a2 (syscall-nr), original value saved on stack (PT_AREG0)
* a1: a1
* a2: new stack pointer, original in a0 and DEPC
- * a3: dispatch table, original in excsave_1
+ * a3: a3
* a4..a15: unchanged
* depc: a2, original value saved on stack (PT_DEPC)
- * excsave_1: a3
+ * excsave_1: dispatch table
*
* PT_DEPC >= VALID_DOUBLE_EXCEPTION_ADDRESS: double exception, DEPC
* < VALID_DOUBLE_EXCEPTION_ADDRESS: regular exception
@@ -1122,8 +997,6 @@
ENTRY(fast_syscall_xtensa)
- xsr a3, excsave1 # restore a3, excsave1
-
s32i a7, a2, PT_AREG7 # we need an additional register
movi a7, 4 # sizeof(unsigned int)
access_ok a3, a7, a0, a2, .Leac # a0: scratch reg, a2: sp
@@ -1186,9 +1059,9 @@
* a0: trashed, original value saved on stack (PT_AREG0)
* a1: a1
* a2: new stack pointer, original in DEPC
- * a3: dispatch table
+ * a3: a3
* depc: a2, original value saved on stack (PT_DEPC)
- * excsave_1: a3
+ * excsave_1: dispatch table
*
* Note: We assume the stack pointer is EXC_TABLE_KSTK in the fixup handler.
*/
@@ -1197,15 +1070,16 @@
/* Register a FIXUP handler (pass current wb as a parameter) */
+ xsr a3, excsave1
movi a0, fast_syscall_spill_registers_fixup
s32i a0, a3, EXC_TABLE_FIXUP
rsr a0, windowbase
s32i a0, a3, EXC_TABLE_PARAM
+ xsr a3, excsave1 # restore a3 and excsave_1
- /* Save a3 and SAR on stack. */
+ /* Save a3, a4 and SAR on stack. */
rsr a0, sar
- xsr a3, excsave1 # restore a3 and excsave_1
s32i a3, a2, PT_AREG3
s32i a4, a2, PT_AREG4
s32i a0, a2, PT_AREG5 # store SAR to PT_AREG5
@@ -1259,14 +1133,14 @@
* in WS, so that the exception handlers save them to the task stack.
*/
- rsr a3, excsave1 # get spill-mask
+ xsr a3, excsave1 # get spill-mask
slli a2, a3, 1 # shift left by one
slli a3, a2, 32-WSBITS
src a2, a2, a3 # a1 = xxwww1yyxxxwww1yy......
wsr a2, windowstart # set corrected windowstart
- movi a3, exc_table
+ rsr a3, excsave1
l32i a2, a3, EXC_TABLE_DOUBLE_SAVE # restore a2
l32i a3, a3, EXC_TABLE_PARAM # original WB (in user task)
@@ -1303,7 +1177,7 @@
/* Jump to the exception handler. */
- movi a3, exc_table
+ rsr a3, excsave1
rsr a0, exccause
addx4 a0, a0, a3 # find entry in table
l32i a0, a0, EXC_TABLE_FAST_USER # load handler
@@ -1320,6 +1194,7 @@
xsr a3, excsave1
movi a2, fast_syscall_spill_registers_fixup
s32i a2, a3, EXC_TABLE_FIXUP
+ s32i a0, a3, EXC_TABLE_DOUBLE_SAVE
rsr a2, windowbase
s32i a2, a3, EXC_TABLE_PARAM
l32i a2, a3, EXC_TABLE_KSTK
@@ -1331,11 +1206,6 @@
wsr a3, windowbase
rsync
- /* Restore a3 and return. */
-
- movi a3, exc_table
- xsr a3, excsave1
-
rfde
@@ -1522,9 +1392,8 @@
movi a0, 0
- movi a3, exc_table
+ rsr a3, excsave1
l32i a1, a3, EXC_TABLE_KSTK
- wsr a3, excsave1
movi a4, (1 << PS_WOE_BIT) | LOCKLEVEL
wsr a4, ps
@@ -1568,9 +1437,9 @@
* a0: trashed, original value saved on stack (PT_AREG0)
* a1: a1
* a2: new stack pointer, original in DEPC
- * a3: dispatch table
+ * a3: a3
* depc: a2, original value saved on stack (PT_DEPC)
- * excsave_1: a3
+ * excsave_1: dispatch table
*
* PT_DEPC >= VALID_DOUBLE_EXCEPTION_ADDRESS: double exception, DEPC
* < VALID_DOUBLE_EXCEPTION_ADDRESS: regular exception
@@ -1578,9 +1447,10 @@
ENTRY(fast_second_level_miss)
- /* Save a1. Note: we don't expect a double exception. */
+ /* Save a1 and a3. Note: we don't expect a double exception. */
s32i a1, a2, PT_AREG1
+ s32i a3, a2, PT_AREG3
/* We need to map the page of PTEs for the user task. Find
* the pointer to that page. Also, it's possible for tsk->mm
@@ -1602,9 +1472,6 @@
l32i a0, a1, TASK_MM # tsk->mm
beqz a0, 9f
-
- /* We deliberately destroy a3 that holds the exception table. */
-
8: rsr a3, excvaddr # fault address
_PGD_OFFSET(a0, a3, a1)
l32i a0, a0, 0 # read pmdval
@@ -1655,7 +1522,7 @@
/* Exit critical section. */
-4: movi a3, exc_table # restore a3
+4: rsr a3, excsave1
movi a0, 0
s32i a0, a3, EXC_TABLE_FIXUP
@@ -1663,8 +1530,8 @@
l32i a0, a2, PT_AREG0
l32i a1, a2, PT_AREG1
+ l32i a3, a2, PT_AREG3
l32i a2, a2, PT_DEPC
- xsr a3, excsave1
bgeui a2, VALID_DOUBLE_EXCEPTION_ADDRESS, 1f
@@ -1751,11 +1618,8 @@
2: /* Invalid PGD, default exception handling */
- movi a3, exc_table
rsr a1, depc
- xsr a3, excsave1
s32i a1, a2, PT_AREG2
- s32i a3, a2, PT_AREG3
mov a1, a2
rsr a2, ps
@@ -1775,9 +1639,9 @@
* a0: trashed, original value saved on stack (PT_AREG0)
* a1: a1
* a2: new stack pointer, original in DEPC
- * a3: dispatch table
+ * a3: a3
* depc: a2, original value saved on stack (PT_DEPC)
- * excsave_1: a3
+ * excsave_1: dispatch table
*
* PT_DEPC >= VALID_DOUBLE_EXCEPTION_ADDRESS: double exception, DEPC
* < VALID_DOUBLE_EXCEPTION_ADDRESS: regular exception
@@ -1785,17 +1649,17 @@
ENTRY(fast_store_prohibited)
- /* Save a1 and a4. */
+ /* Save a1 and a3. */
s32i a1, a2, PT_AREG1
- s32i a4, a2, PT_AREG4
+ s32i a3, a2, PT_AREG3
GET_CURRENT(a1,a2)
l32i a0, a1, TASK_MM # tsk->mm
beqz a0, 9f
8: rsr a1, excvaddr # fault address
- _PGD_OFFSET(a0, a1, a4)
+ _PGD_OFFSET(a0, a1, a3)
l32i a0, a0, 0
beqz a0, 2f
@@ -1804,39 +1668,37 @@
* and is not PAGE_NONE. See pgtable.h for possible PTE layouts.
*/
- _PTE_OFFSET(a0, a1, a4)
- l32i a4, a0, 0 # read pteval
+ _PTE_OFFSET(a0, a1, a3)
+ l32i a3, a0, 0 # read pteval
movi a1, _PAGE_CA_INVALID
- ball a4, a1, 2f
- bbci.l a4, _PAGE_WRITABLE_BIT, 2f
+ ball a3, a1, 2f
+ bbci.l a3, _PAGE_WRITABLE_BIT, 2f
movi a1, _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_HW_WRITE
- or a4, a4, a1
+ or a3, a3, a1
rsr a1, excvaddr
- s32i a4, a0, 0
+ s32i a3, a0, 0
/* We need to flush the cache if we have page coloring. */
#if (DCACHE_WAY_SIZE > PAGE_SIZE) && XCHAL_DCACHE_IS_WRITEBACK
dhwb a0, 0
#endif
pdtlb a0, a1
- wdtlb a4, a0
+ wdtlb a3, a0
/* Exit critical section. */
movi a0, 0
+ rsr a3, excsave1
s32i a0, a3, EXC_TABLE_FIXUP
/* Restore the working registers, and return. */
- l32i a4, a2, PT_AREG4
+ l32i a3, a2, PT_AREG3
l32i a1, a2, PT_AREG1
l32i a0, a2, PT_AREG0
l32i a2, a2, PT_DEPC
- /* Restore excsave1 and a3. */
-
- xsr a3, excsave1
bgeui a2, VALID_DOUBLE_EXCEPTION_ADDRESS, 1f
rsr a2, depc
@@ -1853,11 +1715,8 @@
2: /* If there was a problem, handle fault in C */
- rsr a4, depc # still holds a2
- xsr a3, excsave1
- s32i a4, a2, PT_AREG2
- s32i a3, a2, PT_AREG3
- l32i a4, a2, PT_AREG4
+ rsr a3, depc # still holds a2
+ s32i a3, a2, PT_AREG2
mov a1, a2
rsr a2, ps
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index 101012b..946fb8d 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -584,8 +584,8 @@
"bogomips\t: %lu.%02lu\n",
XCHAL_BUILD_UNIQUE_ID,
XCHAL_HAVE_BE ? "big" : "little",
- CCOUNT_PER_JIFFY/(1000000/HZ),
- (CCOUNT_PER_JIFFY/(10000/HZ)) % 100,
+ ccount_freq/1000000,
+ (ccount_freq/10000) % 100,
loops_per_jiffy/(500000/HZ),
(loops_per_jiffy/(5000/HZ)) % 100);
diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c
index 24bb0c17..9af3dd8 100644
--- a/arch/xtensa/kernel/time.c
+++ b/arch/xtensa/kernel/time.c
@@ -29,9 +29,7 @@
#include <asm/timex.h>
#include <asm/platform.h>
-#ifdef CONFIG_XTENSA_CALIBRATE_CCOUNT
unsigned long ccount_freq; /* ccount Hz */
-#endif
static cycle_t ccount_read(struct clocksource *cs)
{
@@ -129,8 +127,10 @@
platform_calibrate_ccount();
printk("%d.%02d MHz\n", (int)ccount_freq/1000000,
(int)(ccount_freq/10000)%100);
+#else
+ ccount_freq = CONFIG_XTENSA_CPU_CLOCK*1000000UL;
#endif
- clocksource_register_hz(&ccount_clocksource, CCOUNT_PER_JIFFY * HZ);
+ clocksource_register_hz(&ccount_clocksource, ccount_freq);
ccount_timer.evt.cpumask = cpumask_of(0);
ccount_timer.evt.irq = irq_create_mapping(NULL, LINUX_TIMER_INT);
@@ -164,7 +164,7 @@
#ifndef CONFIG_GENERIC_CALIBRATE_DELAY
void calibrate_delay(void)
{
- loops_per_jiffy = CCOUNT_PER_JIFFY;
+ loops_per_jiffy = ccount_freq / HZ;
printk("Calibrating delay loop (skipped)... "
"%lu.%02lu BogoMIPS preset\n",
loops_per_jiffy/(1000000/HZ),
diff --git a/arch/xtensa/kernel/vectors.S b/arch/xtensa/kernel/vectors.S
index f9e1753..cb8fd44 100644
--- a/arch/xtensa/kernel/vectors.S
+++ b/arch/xtensa/kernel/vectors.S
@@ -78,6 +78,7 @@
s32i a0, a2, PT_DEPC # mark it as a regular exception
addx4 a0, a0, a3 # find entry in table
l32i a0, a0, EXC_TABLE_FAST_USER # load handler
+ xsr a3, excsave1 # restore a3 and dispatch table
jx a0
ENDPROC(_UserExceptionVector)
@@ -104,6 +105,7 @@
s32i a0, a2, PT_DEPC # mark it as a regular exception
addx4 a0, a0, a3 # find entry in table
l32i a0, a0, EXC_TABLE_FAST_KERNEL # load handler address
+ xsr a3, excsave1 # restore a3 and dispatch table
jx a0
ENDPROC(_KernelExceptionVector)
@@ -168,7 +170,7 @@
*
* a0: DEPC
* a1: a1
- * a2: trashed, original value in EXC_TABLE_DOUBLE_A2
+ * a2: trashed, original value in EXC_TABLE_DOUBLE_SAVE
* a3: exctable
* depc: a0
* excsave_1: a3
@@ -204,47 +206,46 @@
.section .DoubleExceptionVector.text, "ax"
.begin literal_prefix .DoubleExceptionVector
+ .globl _DoubleExceptionVector_WindowUnderflow
+ .globl _DoubleExceptionVector_WindowOverflow
ENTRY(_DoubleExceptionVector)
- /* Deliberately destroy excsave (don't assume it's value was valid). */
-
- wsr a3, excsave1 # save a3
+ xsr a3, excsave1
+ s32i a2, a3, EXC_TABLE_DOUBLE_SAVE
/* Check for kernel double exception (usually fatal). */
- rsr a3, ps
- _bbci.l a3, PS_UM_BIT, .Lksp
+ rsr a2, ps
+ _bbci.l a2, PS_UM_BIT, .Lksp
/* Check if we are currently handling a window exception. */
/* Note: We don't need to indicate that we enter a critical section. */
xsr a0, depc # get DEPC, save a0
- movi a3, WINDOW_VECTORS_VADDR
- _bltu a0, a3, .Lfixup
- addi a3, a3, WINDOW_VECTORS_SIZE
- _bgeu a0, a3, .Lfixup
+ movi a2, WINDOW_VECTORS_VADDR
+ _bltu a0, a2, .Lfixup
+ addi a2, a2, WINDOW_VECTORS_SIZE
+ _bgeu a0, a2, .Lfixup
/* Window overflow/underflow exception. Get stack pointer. */
- mov a3, a2
- /* This explicit literal and the following references to it are made
- * in order to fit DoubleExceptionVector.literals into the available
- * 16-byte gap before DoubleExceptionVector.text in the absence of
- * link time relaxation. See kernel/vmlinux.lds.S
- */
- .literal .Lexc_table, exc_table
- l32r a2, .Lexc_table
- l32i a2, a2, EXC_TABLE_KSTK
+ l32i a2, a3, EXC_TABLE_KSTK
/* Check for overflow/underflow exception, jump if overflow. */
- _bbci.l a0, 6, .Lovfl
+ _bbci.l a0, 6, _DoubleExceptionVector_WindowOverflow
- /* a0: depc, a1: a1, a2: kstk, a3: a2, depc: a0, excsave: a3 */
-
- /* Restart window underflow exception.
+ /*
+ * Restart window underflow exception.
+ * Currently:
+ * depc = orig a0,
+ * a0 = orig DEPC,
+ * a2 = new sp based on KSTK from exc_table
+ * a3 = excsave_1
+ * excsave_1 = orig a3
+ *
* We return to the instruction in user space that caused the window
* underflow exception. Therefore, we change window base to the value
* before we entered the window underflow exception and prepare the
@@ -252,10 +253,11 @@
* by changing depc (in a0).
* Note: We can trash the current window frame (a0...a3) and depc!
*/
-
+_DoubleExceptionVector_WindowUnderflow:
+ xsr a3, excsave1
wsr a2, depc # save stack pointer temporarily
rsr a0, ps
- extui a0, a0, PS_OWB_SHIFT, 4
+ extui a0, a0, PS_OWB_SHIFT, PS_OWB_WIDTH
wsr a0, windowbase
rsync
@@ -263,52 +265,11 @@
xsr a2, depc # save a2 and get stack pointer
s32i a0, a2, PT_AREG0
-
- wsr a3, excsave1 # save a3
- l32r a3, .Lexc_table
-
+ xsr a3, excsave1
rsr a0, exccause
s32i a0, a2, PT_DEPC # mark it as a regular exception
addx4 a0, a0, a3
- l32i a0, a0, EXC_TABLE_FAST_USER
- jx a0
-
-.Lfixup:/* Check for a fixup handler or if we were in a critical section. */
-
- /* a0: depc, a1: a1, a2: a2, a3: trashed, depc: a0, excsave1: a3 */
-
- l32r a3, .Lexc_table
- s32i a2, a3, EXC_TABLE_DOUBLE_SAVE # temporary variable
-
- /* Enter critical section. */
-
- l32i a2, a3, EXC_TABLE_FIXUP
- s32i a3, a3, EXC_TABLE_FIXUP
- beq a2, a3, .Lunrecoverable_fixup # critical!
- beqz a2, .Ldflt # no handler was registered
-
- /* a0: depc, a1: a1, a2: trash, a3: exctable, depc: a0, excsave: a3 */
-
- jx a2
-
-.Ldflt: /* Get stack pointer. */
-
- l32i a3, a3, EXC_TABLE_DOUBLE_SAVE
- addi a2, a3, -PT_USER_SIZE
-
-.Lovfl: /* Jump to default handlers. */
-
- /* a0: depc, a1: a1, a2: kstk, a3: a2, depc: a0, excsave: a3 */
-
- xsr a3, depc
- s32i a0, a2, PT_DEPC
- s32i a3, a2, PT_AREG0
-
- /* a0: avail, a1: a1, a2: kstk, a3: avail, depc: a2, excsave: a3 */
-
- l32r a3, .Lexc_table
- rsr a0, exccause
- addx4 a0, a0, a3
+ xsr a3, excsave1
l32i a0, a0, EXC_TABLE_FAST_USER
jx a0
@@ -346,6 +307,163 @@
movi a0, unrecoverable_exception
callx0 a0
+.Lfixup:/* Check for a fixup handler or if we were in a critical section. */
+
+ /* a0: depc, a1: a1, a2: trash, a3: exctable, depc: a0, excsave1: a3 */
+
+ /* Enter critical section. */
+
+ l32i a2, a3, EXC_TABLE_FIXUP
+ s32i a3, a3, EXC_TABLE_FIXUP
+ beq a2, a3, .Lunrecoverable_fixup # critical section
+ beqz a2, .Ldflt # no handler was registered
+
+ /* a0: depc, a1: a1, a2: trash, a3: exctable, depc: a0, excsave: a3 */
+
+ jx a2
+
+.Ldflt: /* Get stack pointer. */
+
+ l32i a2, a3, EXC_TABLE_DOUBLE_SAVE
+ addi a2, a2, -PT_USER_SIZE
+
+ /* a0: depc, a1: a1, a2: kstk, a3: exctable, depc: a0, excsave: a3 */
+
+ s32i a0, a2, PT_DEPC
+ l32i a0, a3, EXC_TABLE_DOUBLE_SAVE
+ xsr a0, depc
+ s32i a0, a2, PT_AREG0
+
+ /* a0: avail, a1: a1, a2: kstk, a3: exctable, depc: a2, excsave: a3 */
+
+ rsr a0, exccause
+ addx4 a0, a0, a3
+ xsr a3, excsave1
+ l32i a0, a0, EXC_TABLE_FAST_USER
+ jx a0
+
+ /*
+ * Restart window OVERFLOW exception.
+ * Currently:
+ * depc = orig a0,
+ * a0 = orig DEPC,
+ * a2 = new sp based on KSTK from exc_table
+ * a3 = EXCSAVE_1
+ * excsave_1 = orig a3
+ *
+ * We return to the instruction in user space that caused the window
+ * overflow exception. Therefore, we change window base to the value
+ * before we entered the window overflow exception and prepare the
+ * registers to return as if we were coming from a regular exception
+ * by changing DEPC (in a0).
+ *
+ * NOTE: We CANNOT trash the current window frame (a0...a3), but we
+ * can clobber depc.
+ *
+ * The tricky part here is that overflow8 and overflow12 handlers
+ * save a0, then clobber a0. To restart the handler, we have to restore
+ * a0 if the double exception was past the point where a0 was clobbered.
+ *
+ * To keep things simple, we take advantage of the fact all overflow
+ * handlers save a0 in their very first instruction. If DEPC was past
+ * that instruction, we can safely restore a0 from where it was saved
+ * on the stack.
+ *
+ * a0: depc, a1: a1, a2: kstk, a3: exc_table, depc: a0, excsave1: a3
+ */
+_DoubleExceptionVector_WindowOverflow:
+ extui a2, a0, 0, 6 # get offset into 64-byte vector handler
+ beqz a2, 1f # if at start of vector, don't restore
+
+ addi a0, a0, -128
+ bbsi a0, 8, 1f # don't restore except for overflow 8 and 12
+ bbsi a0, 7, 2f
+
+ /*
+ * Restore a0 as saved by _WindowOverflow8().
+ *
+ * FIXME: we really need a fixup handler for this L32E,
+ * for the extremely unlikely case where the overflow handler's
+ * reference thru a0 gets a hardware TLB refill that bumps out
+ * the (distinct, aliasing) TLB entry that mapped its prior
+ * references thru a9, and where our reference now thru a9
+ * gets a 2nd-level miss exception (not hardware TLB refill).
+ */
+
+ l32e a2, a9, -16
+ wsr a2, depc # replace the saved a0
+ j 1f
+
+2:
+ /*
+ * Restore a0 as saved by _WindowOverflow12().
+ *
+ * FIXME: we really need a fixup handler for this L32E,
+ * for the extremely unlikely case where the overflow handler's
+ * reference thru a0 gets a hardware TLB refill that bumps out
+ * the (distinct, aliasing) TLB entry that mapped its prior
+ * references thru a13, and where our reference now thru a13
+ * gets a 2nd-level miss exception (not hardware TLB refill).
+ */
+
+ l32e a2, a13, -16
+ wsr a2, depc # replace the saved a0
+1:
+ /*
+ * Restore WindowBase while leaving all address registers restored.
+ * We have to use ROTW for this, because WSR.WINDOWBASE requires
+ * an address register (which would prevent restore).
+ *
+ * Window Base goes from 0 ... 7 (Module 8)
+ * Window Start is 8 bits; Ex: (0b1010 1010):0x55 from series of call4s
+ */
+
+ rsr a0, ps
+ extui a0, a0, PS_OWB_SHIFT, PS_OWB_WIDTH
+ rsr a2, windowbase
+ sub a0, a2, a0
+ extui a0, a0, 0, 3
+
+ l32i a2, a3, EXC_TABLE_DOUBLE_SAVE
+ xsr a3, excsave1
+ beqi a0, 1, .L1pane
+ beqi a0, 3, .L3pane
+
+ rsr a0, depc
+ rotw -2
+
+ /*
+ * We are now in the user code's original window frame.
+ * Process the exception as a user exception as if it was
+ * taken by the user code.
+ *
+ * This is similar to the user exception vector,
+ * except that PT_DEPC isn't set to EXCCAUSE.
+ */
+1:
+ xsr a3, excsave1
+ wsr a2, depc
+ l32i a2, a3, EXC_TABLE_KSTK
+ s32i a0, a2, PT_AREG0
+ rsr a0, exccause
+
+ s32i a0, a2, PT_DEPC
+
+ addx4 a0, a0, a3
+ l32i a0, a0, EXC_TABLE_FAST_USER
+ xsr a3, excsave1
+ jx a0
+
+.L1pane:
+ rsr a0, depc
+ rotw -1
+ j 1b
+
+.L3pane:
+ rsr a0, depc
+ rotw -3
+ j 1b
+
.end literal_prefix
ENDPROC(_DoubleExceptionVector)
diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c
index d8507f8..74a60c7 100644
--- a/arch/xtensa/kernel/xtensa_ksyms.c
+++ b/arch/xtensa/kernel/xtensa_ksyms.c
@@ -25,6 +25,7 @@
#include <asm/io.h>
#include <asm/page.h>
#include <asm/pgalloc.h>
+#include <asm/ftrace.h>
#ifdef CONFIG_BLK_DEV_FD
#include <asm/floppy.h>
#endif
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index 4b7bc8d..70fa7bc 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -72,6 +72,8 @@
address, exccause, regs->pc, is_write? "w":"", is_exec? "x":"");
#endif
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
diff --git a/block/Kconfig b/block/Kconfig
index a7e40a7..7f38e40 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -99,6 +99,12 @@
See Documentation/cgroups/blkio-controller.txt for more information.
+config CMDLINE_PARSER
+ bool "Block device command line partition parser"
+ default n
+ ---help---
+ Parsing command line, get the partitions information.
+
menu "Partition Types"
source "block/partitions/Kconfig"
diff --git a/block/Makefile b/block/Makefile
index 39b76ba..4fa4be5 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -18,3 +18,4 @@
obj-$(CONFIG_BLOCK_COMPAT) += compat_ioctl.o
obj-$(CONFIG_BLK_DEV_INTEGRITY) += blk-integrity.o
+obj-$(CONFIG_CMDLINE_PARSER) += cmdline-parser.o
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 4464c82..46cd7bd 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -367,7 +367,7 @@
if (!icq)
return NULL;
- if (radix_tree_preload(gfp_mask) < 0) {
+ if (radix_tree_maybe_preload(gfp_mask) < 0) {
kmem_cache_free(et->icq_cache, icq);
return NULL;
}
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 5efc5a6..3aa5b19 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -29,7 +29,7 @@
int err;
unsigned long v;
- err = strict_strtoul(page, 10, &v);
+ err = kstrtoul(page, 10, &v);
if (err || v > UINT_MAX)
return -EINVAL;
diff --git a/block/cmdline-parser.c b/block/cmdline-parser.c
new file mode 100644
index 0000000..cc2637f
--- /dev/null
+++ b/block/cmdline-parser.c
@@ -0,0 +1,250 @@
+/*
+ * Parse command line, get partition information
+ *
+ * Written by Cai Zhiyong <caizhiyong@huawei.com>
+ *
+ */
+#include <linux/buffer_head.h>
+#include <linux/module.h>
+#include <linux/cmdline-parser.h>
+
+static int parse_subpart(struct cmdline_subpart **subpart, char *partdef)
+{
+ int ret = 0;
+ struct cmdline_subpart *new_subpart;
+
+ *subpart = NULL;
+
+ new_subpart = kzalloc(sizeof(struct cmdline_subpart), GFP_KERNEL);
+ if (!new_subpart)
+ return -ENOMEM;
+
+ if (*partdef == '-') {
+ new_subpart->size = (sector_t)(~0ULL);
+ partdef++;
+ } else {
+ new_subpart->size = (sector_t)memparse(partdef, &partdef);
+ if (new_subpart->size < (sector_t)PAGE_SIZE) {
+ pr_warn("cmdline partition size is invalid.");
+ ret = -EINVAL;
+ goto fail;
+ }
+ }
+
+ if (*partdef == '@') {
+ partdef++;
+ new_subpart->from = (sector_t)memparse(partdef, &partdef);
+ } else {
+ new_subpart->from = (sector_t)(~0ULL);
+ }
+
+ if (*partdef == '(') {
+ int length;
+ char *next = strchr(++partdef, ')');
+
+ if (!next) {
+ pr_warn("cmdline partition format is invalid.");
+ ret = -EINVAL;
+ goto fail;
+ }
+
+ length = min_t(int, next - partdef,
+ sizeof(new_subpart->name) - 1);
+ strncpy(new_subpart->name, partdef, length);
+ new_subpart->name[length] = '\0';
+
+ partdef = ++next;
+ } else
+ new_subpart->name[0] = '\0';
+
+ new_subpart->flags = 0;
+
+ if (!strncmp(partdef, "ro", 2)) {
+ new_subpart->flags |= PF_RDONLY;
+ partdef += 2;
+ }
+
+ if (!strncmp(partdef, "lk", 2)) {
+ new_subpart->flags |= PF_POWERUP_LOCK;
+ partdef += 2;
+ }
+
+ *subpart = new_subpart;
+ return 0;
+fail:
+ kfree(new_subpart);
+ return ret;
+}
+
+static void free_subpart(struct cmdline_parts *parts)
+{
+ struct cmdline_subpart *subpart;
+
+ while (parts->subpart) {
+ subpart = parts->subpart;
+ parts->subpart = subpart->next_subpart;
+ kfree(subpart);
+ }
+}
+
+static int parse_parts(struct cmdline_parts **parts, const char *bdevdef)
+{
+ int ret = -EINVAL;
+ char *next;
+ int length;
+ struct cmdline_subpart **next_subpart;
+ struct cmdline_parts *newparts;
+ char buf[BDEVNAME_SIZE + 32 + 4];
+
+ *parts = NULL;
+
+ newparts = kzalloc(sizeof(struct cmdline_parts), GFP_KERNEL);
+ if (!newparts)
+ return -ENOMEM;
+
+ next = strchr(bdevdef, ':');
+ if (!next) {
+ pr_warn("cmdline partition has no block device.");
+ goto fail;
+ }
+
+ length = min_t(int, next - bdevdef, sizeof(newparts->name) - 1);
+ strncpy(newparts->name, bdevdef, length);
+ newparts->name[length] = '\0';
+ newparts->nr_subparts = 0;
+
+ next_subpart = &newparts->subpart;
+
+ while (next && *(++next)) {
+ bdevdef = next;
+ next = strchr(bdevdef, ',');
+
+ length = (!next) ? (sizeof(buf) - 1) :
+ min_t(int, next - bdevdef, sizeof(buf) - 1);
+
+ strncpy(buf, bdevdef, length);
+ buf[length] = '\0';
+
+ ret = parse_subpart(next_subpart, buf);
+ if (ret)
+ goto fail;
+
+ newparts->nr_subparts++;
+ next_subpart = &(*next_subpart)->next_subpart;
+ }
+
+ if (!newparts->subpart) {
+ pr_warn("cmdline partition has no valid partition.");
+ ret = -EINVAL;
+ goto fail;
+ }
+
+ *parts = newparts;
+
+ return 0;
+fail:
+ free_subpart(newparts);
+ kfree(newparts);
+ return ret;
+}
+
+void cmdline_parts_free(struct cmdline_parts **parts)
+{
+ struct cmdline_parts *next_parts;
+
+ while (*parts) {
+ next_parts = (*parts)->next_parts;
+ free_subpart(*parts);
+ kfree(*parts);
+ *parts = next_parts;
+ }
+}
+
+int cmdline_parts_parse(struct cmdline_parts **parts, const char *cmdline)
+{
+ int ret;
+ char *buf;
+ char *pbuf;
+ char *next;
+ struct cmdline_parts **next_parts;
+
+ *parts = NULL;
+
+ next = pbuf = buf = kstrdup(cmdline, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ next_parts = parts;
+
+ while (next && *pbuf) {
+ next = strchr(pbuf, ';');
+ if (next)
+ *next = '\0';
+
+ ret = parse_parts(next_parts, pbuf);
+ if (ret)
+ goto fail;
+
+ if (next)
+ pbuf = ++next;
+
+ next_parts = &(*next_parts)->next_parts;
+ }
+
+ if (!*parts) {
+ pr_warn("cmdline partition has no valid partition.");
+ ret = -EINVAL;
+ goto fail;
+ }
+
+ ret = 0;
+done:
+ kfree(buf);
+ return ret;
+
+fail:
+ cmdline_parts_free(parts);
+ goto done;
+}
+
+struct cmdline_parts *cmdline_parts_find(struct cmdline_parts *parts,
+ const char *bdev)
+{
+ while (parts && strncmp(bdev, parts->name, sizeof(parts->name)))
+ parts = parts->next_parts;
+ return parts;
+}
+
+/*
+ * add_part()
+ * 0 success.
+ * 1 can not add so many partitions.
+ */
+void cmdline_parts_set(struct cmdline_parts *parts, sector_t disk_size,
+ int slot,
+ int (*add_part)(int, struct cmdline_subpart *, void *),
+ void *param)
+
+{
+ sector_t from = 0;
+ struct cmdline_subpart *subpart;
+
+ for (subpart = parts->subpart; subpart;
+ subpart = subpart->next_subpart, slot++) {
+ if (subpart->from == (sector_t)(~0ULL))
+ subpart->from = from;
+ else
+ from = subpart->from;
+
+ if (from >= disk_size)
+ break;
+
+ if (subpart->size > (disk_size - from))
+ subpart->size = disk_size - from;
+
+ from += subpart->size;
+
+ if (add_part(slot, subpart, param))
+ break;
+ }
+}
diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
index 7e5d474d..fbd5a67 100644
--- a/block/compat_ioctl.c
+++ b/block/compat_ioctl.c
@@ -70,7 +70,7 @@
return ret;
ret = copy_to_user(ugeo, &geo, 4);
- ret |= __put_user(geo.start, &ugeo->start);
+ ret |= put_user(geo.start, &ugeo->start);
if (ret)
ret = -EFAULT;
diff --git a/block/partitions/Kconfig b/block/partitions/Kconfig
index 4cebb2f..87a3208 100644
--- a/block/partitions/Kconfig
+++ b/block/partitions/Kconfig
@@ -260,3 +260,10 @@
partition table format used by Motorola Delta machines (using
sysv68).
Otherwise, say N.
+
+config CMDLINE_PARTITION
+ bool "Command line partition support" if PARTITION_ADVANCED
+ select CMDLINE_PARSER
+ help
+ Say Y here if you would read the partitions table from bootargs.
+ The format for the command line is just like mtdparts.
diff --git a/block/partitions/Makefile b/block/partitions/Makefile
index 2be4d7b..37a9527 100644
--- a/block/partitions/Makefile
+++ b/block/partitions/Makefile
@@ -8,6 +8,7 @@
obj-$(CONFIG_AMIGA_PARTITION) += amiga.o
obj-$(CONFIG_ATARI_PARTITION) += atari.o
obj-$(CONFIG_AIX_PARTITION) += aix.o
+obj-$(CONFIG_CMDLINE_PARTITION) += cmdline.o
obj-$(CONFIG_MAC_PARTITION) += mac.o
obj-$(CONFIG_LDM_PARTITION) += ldm.o
obj-$(CONFIG_MSDOS_PARTITION) += msdos.o
diff --git a/block/partitions/check.c b/block/partitions/check.c
index 19ba207..9ac1df7 100644
--- a/block/partitions/check.c
+++ b/block/partitions/check.c
@@ -34,6 +34,7 @@
#include "efi.h"
#include "karma.h"
#include "sysv68.h"
+#include "cmdline.h"
int warn_no_part = 1; /*This is ugly: should make genhd removable media aware*/
@@ -65,6 +66,9 @@
adfspart_check_ADFS,
#endif
+#ifdef CONFIG_CMDLINE_PARTITION
+ cmdline_partition,
+#endif
#ifdef CONFIG_EFI_PARTITION
efi_partition, /* this must come before msdos */
#endif
diff --git a/block/partitions/cmdline.c b/block/partitions/cmdline.c
new file mode 100644
index 0000000..56cf4ff
--- /dev/null
+++ b/block/partitions/cmdline.c
@@ -0,0 +1,99 @@
+/*
+ * Copyright (C) 2013 HUAWEI
+ * Author: Cai Zhiyong <caizhiyong@huawei.com>
+ *
+ * Read block device partition table from command line.
+ * The partition used for fixed block device (eMMC) embedded device.
+ * It is no MBR, save storage space. Bootloader can be easily accessed
+ * by absolute address of data on the block device.
+ * Users can easily change the partition.
+ *
+ * The format for the command line is just like mtdparts.
+ *
+ * Verbose config please reference "Documentation/block/cmdline-partition.txt"
+ *
+ */
+
+#include <linux/cmdline-parser.h>
+
+#include "check.h"
+#include "cmdline.h"
+
+static char *cmdline;
+static struct cmdline_parts *bdev_parts;
+
+static int add_part(int slot, struct cmdline_subpart *subpart, void *param)
+{
+ int label_min;
+ struct partition_meta_info *info;
+ char tmp[sizeof(info->volname) + 4];
+ struct parsed_partitions *state = (struct parsed_partitions *)param;
+
+ if (slot >= state->limit)
+ return 1;
+
+ put_partition(state, slot, subpart->from >> 9,
+ subpart->size >> 9);
+
+ info = &state->parts[slot].info;
+
+ label_min = min_t(int, sizeof(info->volname) - 1,
+ sizeof(subpart->name));
+ strncpy(info->volname, subpart->name, label_min);
+ info->volname[label_min] = '\0';
+
+ snprintf(tmp, sizeof(tmp), "(%s)", info->volname);
+ strlcat(state->pp_buf, tmp, PAGE_SIZE);
+
+ state->parts[slot].has_info = true;
+
+ return 0;
+}
+
+static int __init cmdline_parts_setup(char *s)
+{
+ cmdline = s;
+ return 1;
+}
+__setup("blkdevparts=", cmdline_parts_setup);
+
+/*
+ * Purpose: allocate cmdline partitions.
+ * Returns:
+ * -1 if unable to read the partition table
+ * 0 if this isn't our partition table
+ * 1 if successful
+ */
+int cmdline_partition(struct parsed_partitions *state)
+{
+ sector_t disk_size;
+ char bdev[BDEVNAME_SIZE];
+ struct cmdline_parts *parts;
+
+ if (cmdline) {
+ if (bdev_parts)
+ cmdline_parts_free(&bdev_parts);
+
+ if (cmdline_parts_parse(&bdev_parts, cmdline)) {
+ cmdline = NULL;
+ return -1;
+ }
+ cmdline = NULL;
+ }
+
+ if (!bdev_parts)
+ return 0;
+
+ bdevname(state->bdev, bdev);
+ parts = cmdline_parts_find(bdev_parts, bdev);
+ if (!parts)
+ return 0;
+
+ disk_size = get_capacity(state->bdev->bd_disk) << 9;
+
+ cmdline_parts_set(parts, disk_size, 1, add_part, (void *)state);
+
+ strlcat(state->pp_buf, "\n", PAGE_SIZE);
+
+ return 1;
+}
diff --git a/block/partitions/cmdline.h b/block/partitions/cmdline.h
new file mode 100644
index 0000000..26e0f8d
--- /dev/null
+++ b/block/partitions/cmdline.h
@@ -0,0 +1,2 @@
+
+int cmdline_partition(struct parsed_partitions *state);
diff --git a/block/partitions/efi.c b/block/partitions/efi.c
index c85fc89..1a5ec9a 100644
--- a/block/partitions/efi.c
+++ b/block/partitions/efi.c
@@ -25,6 +25,9 @@
* TODO:
*
* Changelog:
+ * Mon August 5th, 2013 Davidlohr Bueso <davidlohr@hp.com>
+ * - detect hybrid MBRs, tighter pMBR checking & cleanups.
+ *
* Mon Nov 09 2004 Matt Domsch <Matt_Domsch@dell.com>
* - test for valid PMBR and valid PGPT before ever reading
* AGPT, allow override with 'gpt' kernel command line option.
@@ -149,34 +152,80 @@
bdev_logical_block_size(bdev)) - 1ULL;
}
-static inline int
-pmbr_part_valid(struct partition *part)
+static inline int pmbr_part_valid(gpt_mbr_record *part)
{
- if (part->sys_ind == EFI_PMBR_OSTYPE_EFI_GPT &&
- le32_to_cpu(part->start_sect) == 1UL)
- return 1;
- return 0;
+ if (part->os_type != EFI_PMBR_OSTYPE_EFI_GPT)
+ goto invalid;
+
+ /* set to 0x00000001 (i.e., the LBA of the GPT Partition Header) */
+ if (le32_to_cpu(part->starting_lba) != GPT_PRIMARY_PARTITION_TABLE_LBA)
+ goto invalid;
+
+ return GPT_MBR_PROTECTIVE;
+invalid:
+ return 0;
}
/**
* is_pmbr_valid(): test Protective MBR for validity
* @mbr: pointer to a legacy mbr structure
+ * @total_sectors: amount of sectors in the device
*
- * Description: Returns 1 if PMBR is valid, 0 otherwise.
- * Validity depends on two things:
+ * Description: Checks for a valid protective or hybrid
+ * master boot record (MBR). The validity of a pMBR depends
+ * on all of the following properties:
* 1) MSDOS signature is in the last two bytes of the MBR
* 2) One partition of type 0xEE is found
+ *
+ * In addition, a hybrid MBR will have up to three additional
+ * primary partitions, which point to the same space that's
+ * marked out by up to three GPT partitions.
+ *
+ * Returns 0 upon invalid MBR, or GPT_MBR_PROTECTIVE or
+ * GPT_MBR_HYBRID depending on the device layout.
*/
-static int
-is_pmbr_valid(legacy_mbr *mbr)
+static int is_pmbr_valid(legacy_mbr *mbr, sector_t total_sectors)
{
- int i;
+ int i, part = 0, ret = 0; /* invalid by default */
+
if (!mbr || le16_to_cpu(mbr->signature) != MSDOS_MBR_SIGNATURE)
- return 0;
+ goto done;
+
+ for (i = 0; i < 4; i++) {
+ ret = pmbr_part_valid(&mbr->partition_record[i]);
+ if (ret == GPT_MBR_PROTECTIVE) {
+ part = i;
+ /*
+ * Ok, we at least know that there's a protective MBR,
+ * now check if there are other partition types for
+ * hybrid MBR.
+ */
+ goto check_hybrid;
+ }
+ }
+
+ if (ret != GPT_MBR_PROTECTIVE)
+ goto done;
+check_hybrid:
for (i = 0; i < 4; i++)
- if (pmbr_part_valid(&mbr->partition_record[i]))
- return 1;
- return 0;
+ if ((mbr->partition_record[i].os_type !=
+ EFI_PMBR_OSTYPE_EFI_GPT) &&
+ (mbr->partition_record[i].os_type != 0x00))
+ ret = GPT_MBR_HYBRID;
+
+ /*
+ * Protective MBRs take up the lesser of the whole disk
+ * or 2 TiB (32bit LBA), ignoring the rest of the disk.
+ *
+ * Hybrid MBRs do not necessarily comply with this.
+ */
+ if (ret == GPT_MBR_PROTECTIVE) {
+ if (le32_to_cpu(mbr->partition_record[part].size_in_lba) !=
+ min((uint32_t) total_sectors - 1, 0xFFFFFFFF))
+ ret = 0;
+ }
+done:
+ return ret;
}
/**
@@ -243,8 +292,7 @@
return NULL;
if (read_lba(state, le64_to_cpu(gpt->partition_entry_lba),
- (u8 *) pte,
- count) < count) {
+ (u8 *) pte, count) < count) {
kfree(pte);
pte=NULL;
return NULL;
@@ -364,7 +412,12 @@
(unsigned long long)lastlba);
goto fail;
}
-
+ if (le64_to_cpu((*gpt)->last_usable_lba) < le64_to_cpu((*gpt)->first_usable_lba)) {
+ pr_debug("GPT: last_usable_lba incorrect: %lld > %lld\n",
+ (unsigned long long)le64_to_cpu((*gpt)->last_usable_lba),
+ (unsigned long long)le64_to_cpu((*gpt)->first_usable_lba));
+ goto fail;
+ }
/* Check that sizeof_partition_entry has the correct value */
if (le32_to_cpu((*gpt)->sizeof_partition_entry) != sizeof(gpt_entry)) {
pr_debug("GUID Partitition Entry Size check failed.\n");
@@ -429,44 +482,42 @@
if (!pgpt || !agpt)
return;
if (le64_to_cpu(pgpt->my_lba) != le64_to_cpu(agpt->alternate_lba)) {
- printk(KERN_WARNING
- "GPT:Primary header LBA != Alt. header alternate_lba\n");
- printk(KERN_WARNING "GPT:%lld != %lld\n",
+ pr_warn("GPT:Primary header LBA != Alt. header alternate_lba\n");
+ pr_warn("GPT:%lld != %lld\n",
(unsigned long long)le64_to_cpu(pgpt->my_lba),
(unsigned long long)le64_to_cpu(agpt->alternate_lba));
error_found++;
}
if (le64_to_cpu(pgpt->alternate_lba) != le64_to_cpu(agpt->my_lba)) {
- printk(KERN_WARNING
- "GPT:Primary header alternate_lba != Alt. header my_lba\n");
- printk(KERN_WARNING "GPT:%lld != %lld\n",
+ pr_warn("GPT:Primary header alternate_lba != Alt. header my_lba\n");
+ pr_warn("GPT:%lld != %lld\n",
(unsigned long long)le64_to_cpu(pgpt->alternate_lba),
(unsigned long long)le64_to_cpu(agpt->my_lba));
error_found++;
}
if (le64_to_cpu(pgpt->first_usable_lba) !=
le64_to_cpu(agpt->first_usable_lba)) {
- printk(KERN_WARNING "GPT:first_usable_lbas don't match.\n");
- printk(KERN_WARNING "GPT:%lld != %lld\n",
+ pr_warn("GPT:first_usable_lbas don't match.\n");
+ pr_warn("GPT:%lld != %lld\n",
(unsigned long long)le64_to_cpu(pgpt->first_usable_lba),
(unsigned long long)le64_to_cpu(agpt->first_usable_lba));
error_found++;
}
if (le64_to_cpu(pgpt->last_usable_lba) !=
le64_to_cpu(agpt->last_usable_lba)) {
- printk(KERN_WARNING "GPT:last_usable_lbas don't match.\n");
- printk(KERN_WARNING "GPT:%lld != %lld\n",
+ pr_warn("GPT:last_usable_lbas don't match.\n");
+ pr_warn("GPT:%lld != %lld\n",
(unsigned long long)le64_to_cpu(pgpt->last_usable_lba),
(unsigned long long)le64_to_cpu(agpt->last_usable_lba));
error_found++;
}
if (efi_guidcmp(pgpt->disk_guid, agpt->disk_guid)) {
- printk(KERN_WARNING "GPT:disk_guids don't match.\n");
+ pr_warn("GPT:disk_guids don't match.\n");
error_found++;
}
if (le32_to_cpu(pgpt->num_partition_entries) !=
le32_to_cpu(agpt->num_partition_entries)) {
- printk(KERN_WARNING "GPT:num_partition_entries don't match: "
+ pr_warn("GPT:num_partition_entries don't match: "
"0x%x != 0x%x\n",
le32_to_cpu(pgpt->num_partition_entries),
le32_to_cpu(agpt->num_partition_entries));
@@ -474,8 +525,7 @@
}
if (le32_to_cpu(pgpt->sizeof_partition_entry) !=
le32_to_cpu(agpt->sizeof_partition_entry)) {
- printk(KERN_WARNING
- "GPT:sizeof_partition_entry values don't match: "
+ pr_warn("GPT:sizeof_partition_entry values don't match: "
"0x%x != 0x%x\n",
le32_to_cpu(pgpt->sizeof_partition_entry),
le32_to_cpu(agpt->sizeof_partition_entry));
@@ -483,34 +533,30 @@
}
if (le32_to_cpu(pgpt->partition_entry_array_crc32) !=
le32_to_cpu(agpt->partition_entry_array_crc32)) {
- printk(KERN_WARNING
- "GPT:partition_entry_array_crc32 values don't match: "
+ pr_warn("GPT:partition_entry_array_crc32 values don't match: "
"0x%x != 0x%x\n",
le32_to_cpu(pgpt->partition_entry_array_crc32),
le32_to_cpu(agpt->partition_entry_array_crc32));
error_found++;
}
if (le64_to_cpu(pgpt->alternate_lba) != lastlba) {
- printk(KERN_WARNING
- "GPT:Primary header thinks Alt. header is not at the end of the disk.\n");
- printk(KERN_WARNING "GPT:%lld != %lld\n",
+ pr_warn("GPT:Primary header thinks Alt. header is not at the end of the disk.\n");
+ pr_warn("GPT:%lld != %lld\n",
(unsigned long long)le64_to_cpu(pgpt->alternate_lba),
(unsigned long long)lastlba);
error_found++;
}
if (le64_to_cpu(agpt->my_lba) != lastlba) {
- printk(KERN_WARNING
- "GPT:Alternate GPT header not at the end of the disk.\n");
- printk(KERN_WARNING "GPT:%lld != %lld\n",
+ pr_warn("GPT:Alternate GPT header not at the end of the disk.\n");
+ pr_warn("GPT:%lld != %lld\n",
(unsigned long long)le64_to_cpu(agpt->my_lba),
(unsigned long long)lastlba);
error_found++;
}
if (error_found)
- printk(KERN_WARNING
- "GPT: Use GNU Parted to correct GPT errors.\n");
+ pr_warn("GPT: Use GNU Parted to correct GPT errors.\n");
return;
}
@@ -536,6 +582,7 @@
gpt_header *pgpt = NULL, *agpt = NULL;
gpt_entry *pptes = NULL, *aptes = NULL;
legacy_mbr *legacymbr;
+ sector_t total_sectors = i_size_read(state->bdev->bd_inode) >> 9;
u64 lastlba;
if (!ptes)
@@ -543,17 +590,22 @@
lastlba = last_lba(state->bdev);
if (!force_gpt) {
- /* This will be added to the EFI Spec. per Intel after v1.02. */
- legacymbr = kzalloc(sizeof (*legacymbr), GFP_KERNEL);
- if (legacymbr) {
- read_lba(state, 0, (u8 *) legacymbr,
- sizeof (*legacymbr));
- good_pmbr = is_pmbr_valid(legacymbr);
- kfree(legacymbr);
- }
- if (!good_pmbr)
- goto fail;
- }
+ /* This will be added to the EFI Spec. per Intel after v1.02. */
+ legacymbr = kzalloc(sizeof(*legacymbr), GFP_KERNEL);
+ if (!legacymbr)
+ goto fail;
+
+ read_lba(state, 0, (u8 *)legacymbr, sizeof(*legacymbr));
+ good_pmbr = is_pmbr_valid(legacymbr, total_sectors);
+ kfree(legacymbr);
+
+ if (!good_pmbr)
+ goto fail;
+
+ pr_debug("Device has a %s MBR\n",
+ good_pmbr == GPT_MBR_PROTECTIVE ?
+ "protective" : "hybrid");
+ }
good_pgpt = is_gpt_valid(state, GPT_PRIMARY_PARTITION_TABLE_LBA,
&pgpt, &pptes);
@@ -576,11 +628,8 @@
*ptes = pptes;
kfree(agpt);
kfree(aptes);
- if (!good_agpt) {
- printk(KERN_WARNING
- "Alternate GPT is invalid, "
- "using primary GPT.\n");
- }
+ if (!good_agpt)
+ pr_warn("Alternate GPT is invalid, using primary GPT.\n");
return 1;
}
else if (good_agpt) {
@@ -588,8 +637,7 @@
*ptes = aptes;
kfree(pgpt);
kfree(pptes);
- printk(KERN_WARNING
- "Primary GPT is invalid, using alternate GPT.\n");
+ pr_warn("Primary GPT is invalid, using alternate GPT.\n");
return 1;
}
@@ -651,8 +699,7 @@
put_partition(state, i+1, start * ssz, size * ssz);
/* If this is a RAID volume, tell md */
- if (!efi_guidcmp(ptes[i].partition_type_guid,
- PARTITION_LINUX_RAID_GUID))
+ if (!efi_guidcmp(ptes[i].partition_type_guid, PARTITION_LINUX_RAID_GUID))
state->parts[i + 1].flags = ADDPART_FLAG_RAID;
info = &state->parts[i + 1].info;
diff --git a/block/partitions/efi.h b/block/partitions/efi.h
index b69ab72..4efcafb 100644
--- a/block/partitions/efi.h
+++ b/block/partitions/efi.h
@@ -37,6 +37,9 @@
#define EFI_PMBR_OSTYPE_EFI 0xEF
#define EFI_PMBR_OSTYPE_EFI_GPT 0xEE
+#define GPT_MBR_PROTECTIVE 1
+#define GPT_MBR_HYBRID 2
+
#define GPT_HEADER_SIGNATURE 0x5452415020494645ULL
#define GPT_HEADER_REVISION_V1 0x00010000
#define GPT_PRIMARY_PARTITION_TABLE_LBA 1
@@ -101,11 +104,25 @@
efi_char16_t partition_name[72 / sizeof (efi_char16_t)];
} __attribute__ ((packed)) gpt_entry;
+typedef struct _gpt_mbr_record {
+ u8 boot_indicator; /* unused by EFI, set to 0x80 for bootable */
+ u8 start_head; /* unused by EFI, pt start in CHS */
+ u8 start_sector; /* unused by EFI, pt start in CHS */
+ u8 start_track;
+ u8 os_type; /* EFI and legacy non-EFI OS types */
+ u8 end_head; /* unused by EFI, pt end in CHS */
+ u8 end_sector; /* unused by EFI, pt end in CHS */
+ u8 end_track; /* unused by EFI, pt end in CHS */
+ __le32 starting_lba; /* used by EFI - start addr of the on disk pt */
+ __le32 size_in_lba; /* used by EFI - size of pt in LBA */
+} __packed gpt_mbr_record;
+
+
typedef struct _legacy_mbr {
u8 boot_code[440];
__le32 unique_mbr_signature;
__le16 unknown;
- struct partition partition_record[4];
+ gpt_mbr_record partition_record[4];
__le16 signature;
} __attribute__ ((packed)) legacy_mbr;
@@ -113,22 +130,3 @@
extern int efi_partition(struct parsed_partitions *state);
#endif
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * Emacs will notice this stuff at the end of the file and automatically
- * adjust the settings for this buffer only. This must remain at the end
- * of the file.
- * --------------------------------------------------------------------------
- * Local variables:
- * c-indent-level: 4
- * c-brace-imaginary-offset: 0
- * c-brace-offset: -4
- * c-argdecl-indent: 4
- * c-label-offset: -4
- * c-continued-statement-offset: 4
- * c-continued-brace-offset: 0
- * indent-tabs-mode: nil
- * tab-width: 8
- * End:
- */
diff --git a/crypto/Makefile b/crypto/Makefile
index 2d5ed08..80019ba 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -83,7 +83,7 @@
obj-$(CONFIG_CRYPTO_MICHAEL_MIC) += michael_mic.o
obj-$(CONFIG_CRYPTO_CRC32C) += crc32c.o
obj-$(CONFIG_CRYPTO_CRC32) += crc32.o
-obj-$(CONFIG_CRYPTO_CRCT10DIF) += crct10dif.o
+obj-$(CONFIG_CRYPTO_CRCT10DIF) += crct10dif_common.o crct10dif_generic.o
obj-$(CONFIG_CRYPTO_AUTHENC) += authenc.o authencesn.o
obj-$(CONFIG_CRYPTO_LZO) += lzo.o
obj-$(CONFIG_CRYPTO_LZ4) += lz4.o
diff --git a/crypto/api.c b/crypto/api.c
index 320ea4d..a2b39c5 100644
--- a/crypto/api.c
+++ b/crypto/api.c
@@ -34,6 +34,8 @@
BLOCKING_NOTIFIER_HEAD(crypto_chain);
EXPORT_SYMBOL_GPL(crypto_chain);
+static struct crypto_alg *crypto_larval_wait(struct crypto_alg *alg);
+
struct crypto_alg *crypto_mod_get(struct crypto_alg *alg)
{
return try_module_get(alg->cra_module) ? crypto_alg_get(alg) : NULL;
@@ -144,8 +146,11 @@
}
up_write(&crypto_alg_sem);
- if (alg != &larval->alg)
+ if (alg != &larval->alg) {
kfree(larval);
+ if (crypto_is_larval(alg))
+ alg = crypto_larval_wait(alg);
+ }
return alg;
}
diff --git a/crypto/crct10dif.c b/crypto/crct10dif_common.c
similarity index 63%
rename from crypto/crct10dif.c
rename to crypto/crct10dif_common.c
index 92aca96..b2fab36 100644
--- a/crypto/crct10dif.c
+++ b/crypto/crct10dif_common.c
@@ -24,18 +24,10 @@
*
*/
-#include <linux/types.h>
-#include <linux/module.h>
#include <linux/crc-t10dif.h>
-#include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/string.h>
+#include <linux/module.h>
#include <linux/kernel.h>
-struct chksum_desc_ctx {
- __u16 crc;
-};
-
/* Table generated using the following polynomium:
* x^16 + x^15 + x^11 + x^9 + x^8 + x^7 + x^5 + x^4 + x^2 + x + 1
* gt: 0x8bb7
@@ -86,93 +78,5 @@
}
EXPORT_SYMBOL(crc_t10dif_generic);
-/*
- * Steps through buffer one byte at at time, calculates reflected
- * crc using table.
- */
-
-static int chksum_init(struct shash_desc *desc)
-{
- struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
-
- ctx->crc = 0;
-
- return 0;
-}
-
-static int chksum_update(struct shash_desc *desc, const u8 *data,
- unsigned int length)
-{
- struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
-
- ctx->crc = crc_t10dif_generic(ctx->crc, data, length);
- return 0;
-}
-
-static int chksum_final(struct shash_desc *desc, u8 *out)
-{
- struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
-
- *(__u16 *)out = ctx->crc;
- return 0;
-}
-
-static int __chksum_finup(__u16 *crcp, const u8 *data, unsigned int len,
- u8 *out)
-{
- *(__u16 *)out = crc_t10dif_generic(*crcp, data, len);
- return 0;
-}
-
-static int chksum_finup(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out)
-{
- struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
-
- return __chksum_finup(&ctx->crc, data, len, out);
-}
-
-static int chksum_digest(struct shash_desc *desc, const u8 *data,
- unsigned int length, u8 *out)
-{
- struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
-
- return __chksum_finup(&ctx->crc, data, length, out);
-}
-
-static struct shash_alg alg = {
- .digestsize = CRC_T10DIF_DIGEST_SIZE,
- .init = chksum_init,
- .update = chksum_update,
- .final = chksum_final,
- .finup = chksum_finup,
- .digest = chksum_digest,
- .descsize = sizeof(struct chksum_desc_ctx),
- .base = {
- .cra_name = "crct10dif",
- .cra_driver_name = "crct10dif-generic",
- .cra_priority = 100,
- .cra_blocksize = CRC_T10DIF_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- }
-};
-
-static int __init crct10dif_mod_init(void)
-{
- int ret;
-
- ret = crypto_register_shash(&alg);
- return ret;
-}
-
-static void __exit crct10dif_mod_fini(void)
-{
- crypto_unregister_shash(&alg);
-}
-
-module_init(crct10dif_mod_init);
-module_exit(crct10dif_mod_fini);
-
-MODULE_AUTHOR("Tim Chen <tim.c.chen@linux.intel.com>");
-MODULE_DESCRIPTION("T10 DIF CRC calculation.");
+MODULE_DESCRIPTION("T10 DIF CRC calculation common code");
MODULE_LICENSE("GPL");
diff --git a/crypto/crct10dif_generic.c b/crypto/crct10dif_generic.c
new file mode 100644
index 0000000..877e711
--- /dev/null
+++ b/crypto/crct10dif_generic.c
@@ -0,0 +1,127 @@
+/*
+ * Cryptographic API.
+ *
+ * T10 Data Integrity Field CRC16 Crypto Transform
+ *
+ * Copyright (c) 2007 Oracle Corporation. All rights reserved.
+ * Written by Martin K. Petersen <martin.petersen@oracle.com>
+ * Copyright (C) 2013 Intel Corporation
+ * Author: Tim Chen <tim.c.chen@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/crc-t10dif.h>
+#include <crypto/internal/hash.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+
+struct chksum_desc_ctx {
+ __u16 crc;
+};
+
+/*
+ * Steps through buffer one byte at at time, calculates reflected
+ * crc using table.
+ */
+
+static int chksum_init(struct shash_desc *desc)
+{
+ struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+ ctx->crc = 0;
+
+ return 0;
+}
+
+static int chksum_update(struct shash_desc *desc, const u8 *data,
+ unsigned int length)
+{
+ struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+ ctx->crc = crc_t10dif_generic(ctx->crc, data, length);
+ return 0;
+}
+
+static int chksum_final(struct shash_desc *desc, u8 *out)
+{
+ struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+ *(__u16 *)out = ctx->crc;
+ return 0;
+}
+
+static int __chksum_finup(__u16 *crcp, const u8 *data, unsigned int len,
+ u8 *out)
+{
+ *(__u16 *)out = crc_t10dif_generic(*crcp, data, len);
+ return 0;
+}
+
+static int chksum_finup(struct shash_desc *desc, const u8 *data,
+ unsigned int len, u8 *out)
+{
+ struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+ return __chksum_finup(&ctx->crc, data, len, out);
+}
+
+static int chksum_digest(struct shash_desc *desc, const u8 *data,
+ unsigned int length, u8 *out)
+{
+ struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+ return __chksum_finup(&ctx->crc, data, length, out);
+}
+
+static struct shash_alg alg = {
+ .digestsize = CRC_T10DIF_DIGEST_SIZE,
+ .init = chksum_init,
+ .update = chksum_update,
+ .final = chksum_final,
+ .finup = chksum_finup,
+ .digest = chksum_digest,
+ .descsize = sizeof(struct chksum_desc_ctx),
+ .base = {
+ .cra_name = "crct10dif",
+ .cra_driver_name = "crct10dif-generic",
+ .cra_priority = 100,
+ .cra_blocksize = CRC_T10DIF_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+};
+
+static int __init crct10dif_mod_init(void)
+{
+ int ret;
+
+ ret = crypto_register_shash(&alg);
+ return ret;
+}
+
+static void __exit crct10dif_mod_fini(void)
+{
+ crypto_unregister_shash(&alg);
+}
+
+module_init(crct10dif_mod_init);
+module_exit(crct10dif_mod_fini);
+
+MODULE_AUTHOR("Tim Chen <tim.c.chen@linux.intel.com>");
+MODULE_DESCRIPTION("T10 DIF CRC calculation.");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("crct10dif");
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 6a38218..fb78bb9 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -257,12 +257,13 @@
pdata->mmio_size = resource_size(&rentry->res);
pdata->mmio_base = ioremap(rentry->res.start,
pdata->mmio_size);
- pdata->dev_desc = dev_desc;
break;
}
acpi_dev_free_resource_list(&resource_list);
+ pdata->dev_desc = dev_desc;
+
if (dev_desc->clk_required) {
ret = register_device_clock(adev, pdata);
if (ret) {
diff --git a/drivers/acpi/acpica/exstore.c b/drivers/acpi/acpica/exstore.c
index 2bdba6f..f0b09bf 100644
--- a/drivers/acpi/acpica/exstore.c
+++ b/drivers/acpi/acpica/exstore.c
@@ -57,6 +57,11 @@
union acpi_operand_object *dest_desc,
struct acpi_walk_state *walk_state);
+static acpi_status
+acpi_ex_store_direct_to_node(union acpi_operand_object *source_desc,
+ struct acpi_namespace_node *node,
+ struct acpi_walk_state *walk_state);
+
/*******************************************************************************
*
* FUNCTION: acpi_ex_store
@@ -375,7 +380,11 @@
* When storing into an object the data is converted to the
* target object type then stored in the object. This means
* that the target object type (for an initialized target) will
- * not be changed by a store operation.
+ * not be changed by a store operation. A copy_object can change
+ * the target type, however.
+ *
+ * The implicit_conversion flag is set to NO/FALSE only when
+ * storing to an arg_x -- as per the rules of the ACPI spec.
*
* Assumes parameters are already validated.
*
@@ -399,7 +408,7 @@
target_type = acpi_ns_get_type(node);
target_desc = acpi_ns_get_attached_object(node);
- ACPI_DEBUG_PRINT((ACPI_DB_EXEC, "Storing %p(%s) into node %p(%s)\n",
+ ACPI_DEBUG_PRINT((ACPI_DB_EXEC, "Storing %p (%s) to node %p (%s)\n",
source_desc,
acpi_ut_get_object_type_name(source_desc), node,
acpi_ut_get_type_name(target_type)));
@@ -413,45 +422,30 @@
return_ACPI_STATUS(status);
}
- /* If no implicit conversion, drop into the default case below */
-
- if ((!implicit_conversion) ||
- ((walk_state->opcode == AML_COPY_OP) &&
- (target_type != ACPI_TYPE_LOCAL_REGION_FIELD) &&
- (target_type != ACPI_TYPE_LOCAL_BANK_FIELD) &&
- (target_type != ACPI_TYPE_LOCAL_INDEX_FIELD))) {
- /*
- * Force execution of default (no implicit conversion). Note:
- * copy_object does not perform an implicit conversion, as per the ACPI
- * spec -- except in case of region/bank/index fields -- because these
- * objects must retain their original type permanently.
- */
- target_type = ACPI_TYPE_ANY;
- }
-
/* Do the actual store operation */
switch (target_type) {
- case ACPI_TYPE_BUFFER_FIELD:
- case ACPI_TYPE_LOCAL_REGION_FIELD:
- case ACPI_TYPE_LOCAL_BANK_FIELD:
- case ACPI_TYPE_LOCAL_INDEX_FIELD:
-
- /* For fields, copy the source data to the target field. */
-
- status = acpi_ex_write_data_to_field(source_desc, target_desc,
- &walk_state->result_obj);
- break;
-
case ACPI_TYPE_INTEGER:
case ACPI_TYPE_STRING:
case ACPI_TYPE_BUFFER:
/*
- * These target types are all of type Integer/String/Buffer, and
- * therefore support implicit conversion before the store.
- *
- * Copy and/or convert the source object to a new target object
+ * The simple data types all support implicit source operand
+ * conversion before the store.
*/
+
+ if ((walk_state->opcode == AML_COPY_OP) || !implicit_conversion) {
+ /*
+ * However, copy_object and Stores to arg_x do not perform
+ * an implicit conversion, as per the ACPI specification.
+ * A direct store is performed instead.
+ */
+ status = acpi_ex_store_direct_to_node(source_desc, node,
+ walk_state);
+ break;
+ }
+
+ /* Store with implicit source operand conversion support */
+
status =
acpi_ex_store_object_to_object(source_desc, target_desc,
&new_desc, walk_state);
@@ -465,13 +459,12 @@
* the Name's type to that of the value being stored in it.
* source_desc reference count is incremented by attach_object.
*
- * Note: This may change the type of the node if an explicit store
- * has been performed such that the node/object type has been
- * changed.
+ * Note: This may change the type of the node if an explicit
+ * store has been performed such that the node/object type
+ * has been changed.
*/
- status =
- acpi_ns_attach_object(node, new_desc,
- new_desc->common.type);
+ status = acpi_ns_attach_object(node, new_desc,
+ new_desc->common.type);
ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
"Store %s into %s via Convert/Attach\n",
@@ -482,38 +475,83 @@
}
break;
+ case ACPI_TYPE_BUFFER_FIELD:
+ case ACPI_TYPE_LOCAL_REGION_FIELD:
+ case ACPI_TYPE_LOCAL_BANK_FIELD:
+ case ACPI_TYPE_LOCAL_INDEX_FIELD:
+ /*
+ * For all fields, always write the source data to the target
+ * field. Any required implicit source operand conversion is
+ * performed in the function below as necessary. Note, field
+ * objects must retain their original type permanently.
+ */
+ status = acpi_ex_write_data_to_field(source_desc, target_desc,
+ &walk_state->result_obj);
+ break;
+
default:
-
- ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
- "Storing [%s] (%p) directly into node [%s] (%p)"
- " with no implicit conversion\n",
- acpi_ut_get_object_type_name(source_desc),
- source_desc,
- acpi_ut_get_object_type_name(target_desc),
- node));
-
/*
* No conversions for all other types. Directly store a copy of
- * the source object. NOTE: This is a departure from the ACPI
- * spec, which states "If conversion is impossible, abort the
- * running control method".
+ * the source object. This is the ACPI spec-defined behavior for
+ * the copy_object operator.
*
- * This code implements "If conversion is impossible, treat the
- * Store operation as a CopyObject".
+ * NOTE: For the Store operator, this is a departure from the
+ * ACPI spec, which states "If conversion is impossible, abort
+ * the running control method". Instead, this code implements
+ * "If conversion is impossible, treat the Store operation as
+ * a CopyObject".
*/
- status =
- acpi_ut_copy_iobject_to_iobject(source_desc, &new_desc,
- walk_state);
- if (ACPI_FAILURE(status)) {
- return_ACPI_STATUS(status);
- }
-
- status =
- acpi_ns_attach_object(node, new_desc,
- new_desc->common.type);
- acpi_ut_remove_reference(new_desc);
+ status = acpi_ex_store_direct_to_node(source_desc, node,
+ walk_state);
break;
}
return_ACPI_STATUS(status);
}
+
+/*******************************************************************************
+ *
+ * FUNCTION: acpi_ex_store_direct_to_node
+ *
+ * PARAMETERS: source_desc - Value to be stored
+ * node - Named object to receive the value
+ * walk_state - Current walk state
+ *
+ * RETURN: Status
+ *
+ * DESCRIPTION: "Store" an object directly to a node. This involves a copy
+ * and an attach.
+ *
+ ******************************************************************************/
+
+static acpi_status
+acpi_ex_store_direct_to_node(union acpi_operand_object *source_desc,
+ struct acpi_namespace_node *node,
+ struct acpi_walk_state *walk_state)
+{
+ acpi_status status;
+ union acpi_operand_object *new_desc;
+
+ ACPI_FUNCTION_TRACE(ex_store_direct_to_node);
+
+ ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
+ "Storing [%s] (%p) directly into node [%s] (%p)"
+ " with no implicit conversion\n",
+ acpi_ut_get_object_type_name(source_desc),
+ source_desc, acpi_ut_get_type_name(node->type),
+ node));
+
+ /* Copy the source object to a new object */
+
+ status =
+ acpi_ut_copy_iobject_to_iobject(source_desc, &new_desc, walk_state);
+ if (ACPI_FAILURE(status)) {
+ return_ACPI_STATUS(status);
+ }
+
+ /* Attach the new object to the node */
+
+ status = acpi_ns_attach_object(node, new_desc, new_desc->common.type);
+ acpi_ut_remove_reference(new_desc);
+ return_ACPI_STATUS(status);
+}
diff --git a/drivers/acpi/glue.c b/drivers/acpi/glue.c
index 9467229..10f0f40 100644
--- a/drivers/acpi/glue.c
+++ b/drivers/acpi/glue.c
@@ -79,6 +79,9 @@
return ret;
}
+#define FIND_CHILD_MIN_SCORE 1
+#define FIND_CHILD_MAX_SCORE 2
+
static acpi_status acpi_dev_present(acpi_handle handle, u32 lvl_not_used,
void *not_used, void **ret_p)
{
@@ -92,14 +95,17 @@
return AE_OK;
}
-static bool acpi_extra_checks_passed(acpi_handle handle, bool is_bridge)
+static int do_find_child_checks(acpi_handle handle, bool is_bridge)
{
+ bool sta_present = true;
unsigned long long sta;
acpi_status status;
- status = acpi_bus_get_status_handle(handle, &sta);
- if (ACPI_FAILURE(status) || !(sta & ACPI_STA_DEVICE_ENABLED))
- return false;
+ status = acpi_evaluate_integer(handle, "_STA", NULL, &sta);
+ if (status == AE_NOT_FOUND)
+ sta_present = false;
+ else if (ACPI_FAILURE(status) || !(sta & ACPI_STA_DEVICE_ENABLED))
+ return -ENODEV;
if (is_bridge) {
void *test = NULL;
@@ -107,16 +113,17 @@
/* Check if this object has at least one child device. */
acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, 1,
acpi_dev_present, NULL, NULL, &test);
- return !!test;
+ if (!test)
+ return -ENODEV;
}
- return true;
+ return sta_present ? FIND_CHILD_MAX_SCORE : FIND_CHILD_MIN_SCORE;
}
struct find_child_context {
u64 addr;
bool is_bridge;
acpi_handle ret;
- bool ret_checked;
+ int ret_score;
};
static acpi_status do_find_child(acpi_handle handle, u32 lvl_not_used,
@@ -125,6 +132,7 @@
struct find_child_context *context = data;
unsigned long long addr;
acpi_status status;
+ int score;
status = acpi_evaluate_integer(handle, METHOD_NAME__ADR, NULL, &addr);
if (ACPI_FAILURE(status) || addr != context->addr)
@@ -144,15 +152,20 @@
* its handle if so. Second, check the same for the object that we've
* just found.
*/
- if (!context->ret_checked) {
- if (acpi_extra_checks_passed(context->ret, context->is_bridge))
+ if (!context->ret_score) {
+ score = do_find_child_checks(context->ret, context->is_bridge);
+ if (score == FIND_CHILD_MAX_SCORE)
return AE_CTRL_TERMINATE;
else
- context->ret_checked = true;
+ context->ret_score = score;
}
- if (acpi_extra_checks_passed(handle, context->is_bridge)) {
+ score = do_find_child_checks(handle, context->is_bridge);
+ if (score == FIND_CHILD_MAX_SCORE) {
context->ret = handle;
return AE_CTRL_TERMINATE;
+ } else if (score > context->ret_score) {
+ context->ret = handle;
+ context->ret_score = score;
}
return AE_OK;
}
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 61d090b..fbdb82e 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -204,8 +204,6 @@
return -EINVAL;
}
- lock_device_hotplug();
-
/*
* Carry out two passes here and ignore errors in the first pass,
* because if the devices in question are memory blocks and
@@ -236,9 +234,6 @@
ACPI_UINT32_MAX,
acpi_bus_online_companions, NULL,
NULL, NULL);
-
- unlock_device_hotplug();
-
put_device(&device->dev);
return -EBUSY;
}
@@ -249,8 +244,6 @@
acpi_bus_trim(device);
- unlock_device_hotplug();
-
/* Device node has been unregistered. */
put_device(&device->dev);
device = NULL;
@@ -289,6 +282,7 @@
u32 ost_code = ACPI_OST_SC_NON_SPECIFIC_FAILURE;
int error;
+ lock_device_hotplug();
mutex_lock(&acpi_scan_lock);
acpi_bus_get_device(handle, &device);
@@ -312,6 +306,7 @@
out:
mutex_unlock(&acpi_scan_lock);
+ unlock_device_hotplug();
return;
err_out:
@@ -326,8 +321,8 @@
u32 ost_code = ACPI_OST_SC_NON_SPECIFIC_FAILURE;
int error;
- mutex_lock(&acpi_scan_lock);
lock_device_hotplug();
+ mutex_lock(&acpi_scan_lock);
if (ost_source != ACPI_NOTIFY_BUS_CHECK) {
acpi_bus_get_device(handle, &device);
@@ -353,9 +348,9 @@
kobject_uevent(&device->dev.kobj, KOBJ_ONLINE);
out:
- unlock_device_hotplug();
acpi_evaluate_hotplug_ost(handle, ost_source, ost_code, NULL);
mutex_unlock(&acpi_scan_lock);
+ unlock_device_hotplug();
}
static void acpi_scan_bus_check(void *context)
@@ -446,6 +441,7 @@
acpi_handle handle = device->handle;
int error;
+ lock_device_hotplug();
mutex_lock(&acpi_scan_lock);
error = acpi_scan_hot_remove(device);
@@ -455,6 +451,7 @@
NULL);
mutex_unlock(&acpi_scan_lock);
+ unlock_device_hotplug();
kfree(context);
}
EXPORT_SYMBOL(acpi_bus_hot_remove_device);
diff --git a/drivers/base/dma-buf.c b/drivers/base/dma-buf.c
index 1219ab7..1e16cbd 100644
--- a/drivers/base/dma-buf.c
+++ b/drivers/base/dma-buf.c
@@ -77,9 +77,36 @@
return dmabuf->ops->mmap(dmabuf, vma);
}
+static loff_t dma_buf_llseek(struct file *file, loff_t offset, int whence)
+{
+ struct dma_buf *dmabuf;
+ loff_t base;
+
+ if (!is_dma_buf_file(file))
+ return -EBADF;
+
+ dmabuf = file->private_data;
+
+ /* only support discovering the end of the buffer,
+ but also allow SEEK_SET to maintain the idiomatic
+ SEEK_END(0), SEEK_CUR(0) pattern */
+ if (whence == SEEK_END)
+ base = dmabuf->size;
+ else if (whence == SEEK_SET)
+ base = 0;
+ else
+ return -EINVAL;
+
+ if (offset != 0)
+ return -EINVAL;
+
+ return base + offset;
+}
+
static const struct file_operations dma_buf_fops = {
.release = dma_buf_release,
.mmap = dma_buf_mmap_internal,
+ .llseek = dma_buf_llseek,
};
/*
@@ -133,7 +160,12 @@
dmabuf->exp_name = exp_name;
file = anon_inode_getfile("dmabuf", &dma_buf_fops, dmabuf, flags);
+ if (IS_ERR(file)) {
+ kfree(dmabuf);
+ return ERR_CAST(file);
+ }
+ file->f_mode |= FMODE_LSEEK;
dmabuf->file = file;
mutex_init(&dmabuf->lock);
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 7616a77..bc9f43b 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -125,13 +125,7 @@
nid, K(node_page_state(nid, NR_WRITEBACK)),
nid, K(node_page_state(nid, NR_FILE_PAGES)),
nid, K(node_page_state(nid, NR_FILE_MAPPED)),
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- nid, K(node_page_state(nid, NR_ANON_PAGES)
- + node_page_state(nid, NR_ANON_TRANSPARENT_HUGEPAGES) *
- HPAGE_PMD_NR),
-#else
nid, K(node_page_state(nid, NR_ANON_PAGES)),
-#endif
nid, K(node_page_state(nid, NR_SHMEM)),
nid, node_page_state(nid, NR_KERNEL_STACK) *
THREAD_SIZE / 1024,
diff --git a/drivers/block/aoe/aoe.h b/drivers/block/aoe/aoe.h
index 025c41d..14a9d19 100644
--- a/drivers/block/aoe/aoe.h
+++ b/drivers/block/aoe/aoe.h
@@ -1,5 +1,5 @@
/* Copyright (c) 2013 Coraid, Inc. See COPYING for GPL terms. */
-#define VERSION "83"
+#define VERSION "85"
#define AOE_MAJOR 152
#define DEVICE_NAME "aoe"
@@ -169,6 +169,7 @@
ulong ref;
struct work_struct work;/* disk create work struct */
struct gendisk *gd;
+ struct dentry *debugfs;
struct request_queue *blkq;
struct hd_geometry geo;
sector_t ssize;
@@ -206,6 +207,7 @@
int aoeblk_init(void);
void aoeblk_exit(void);
void aoeblk_gdalloc(void *);
+void aoedisk_rm_debugfs(struct aoedev *d);
void aoedisk_rm_sysfs(struct aoedev *d);
int aoechr_init(void);
diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c
index 916d9ed..dd73e1f 100644
--- a/drivers/block/aoe/aoeblk.c
+++ b/drivers/block/aoe/aoeblk.c
@@ -1,4 +1,4 @@
-/* Copyright (c) 2012 Coraid, Inc. See COPYING for GPL terms. */
+/* Copyright (c) 2013 Coraid, Inc. See COPYING for GPL terms. */
/*
* aoeblk.c
* block device routines
@@ -17,11 +17,13 @@
#include <linux/mutex.h>
#include <linux/export.h>
#include <linux/moduleparam.h>
+#include <linux/debugfs.h>
#include <scsi/sg.h>
#include "aoe.h"
static DEFINE_MUTEX(aoeblk_mutex);
static struct kmem_cache *buf_pool_cache;
+static struct dentry *aoe_debugfs_dir;
/* GPFS needs a larger value than the default. */
static int aoe_maxsectors;
@@ -108,6 +110,55 @@
return snprintf(page, PAGE_SIZE, "%lu\n", d->maxbcnt);
}
+static int aoedisk_debugfs_show(struct seq_file *s, void *ignored)
+{
+ struct aoedev *d;
+ struct aoetgt **t, **te;
+ struct aoeif *ifp, *ife;
+ unsigned long flags;
+ char c;
+
+ d = s->private;
+ seq_printf(s, "rttavg: %d rttdev: %d\n",
+ d->rttavg >> RTTSCALE,
+ d->rttdev >> RTTDSCALE);
+ seq_printf(s, "nskbpool: %d\n", skb_queue_len(&d->skbpool));
+ seq_printf(s, "kicked: %ld\n", d->kicked);
+ seq_printf(s, "maxbcnt: %ld\n", d->maxbcnt);
+ seq_printf(s, "ref: %ld\n", d->ref);
+
+ spin_lock_irqsave(&d->lock, flags);
+ t = d->targets;
+ te = t + d->ntargets;
+ for (; t < te && *t; t++) {
+ c = '\t';
+ seq_printf(s, "falloc: %ld\n", (*t)->falloc);
+ seq_printf(s, "ffree: %p\n",
+ list_empty(&(*t)->ffree) ? NULL : (*t)->ffree.next);
+ seq_printf(s, "%pm:%d:%d:%d\n", (*t)->addr, (*t)->nout,
+ (*t)->maxout, (*t)->nframes);
+ seq_printf(s, "\tssthresh:%d\n", (*t)->ssthresh);
+ seq_printf(s, "\ttaint:%d\n", (*t)->taint);
+ seq_printf(s, "\tr:%d\n", (*t)->rpkts);
+ seq_printf(s, "\tw:%d\n", (*t)->wpkts);
+ ifp = (*t)->ifs;
+ ife = ifp + ARRAY_SIZE((*t)->ifs);
+ for (; ifp->nd && ifp < ife; ifp++) {
+ seq_printf(s, "%c%s", c, ifp->nd->name);
+ c = ',';
+ }
+ seq_puts(s, "\n");
+ }
+ spin_unlock_irqrestore(&d->lock, flags);
+
+ return 0;
+}
+
+static int aoe_debugfs_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, aoedisk_debugfs_show, inode->i_private);
+}
+
static DEVICE_ATTR(state, S_IRUGO, aoedisk_show_state, NULL);
static DEVICE_ATTR(mac, S_IRUGO, aoedisk_show_mac, NULL);
static DEVICE_ATTR(netif, S_IRUGO, aoedisk_show_netif, NULL);
@@ -130,6 +181,44 @@
.attrs = aoe_attrs,
};
+static const struct file_operations aoe_debugfs_fops = {
+ .open = aoe_debugfs_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static void
+aoedisk_add_debugfs(struct aoedev *d)
+{
+ struct dentry *entry;
+ char *p;
+
+ if (aoe_debugfs_dir == NULL)
+ return;
+ p = strchr(d->gd->disk_name, '/');
+ if (p == NULL)
+ p = d->gd->disk_name;
+ else
+ p++;
+ BUG_ON(*p == '\0');
+ entry = debugfs_create_file(p, 0444, aoe_debugfs_dir, d,
+ &aoe_debugfs_fops);
+ if (IS_ERR_OR_NULL(entry)) {
+ pr_info("aoe: cannot create debugfs file for %s\n",
+ d->gd->disk_name);
+ return;
+ }
+ BUG_ON(d->debugfs);
+ d->debugfs = entry;
+}
+void
+aoedisk_rm_debugfs(struct aoedev *d)
+{
+ debugfs_remove(d->debugfs);
+ d->debugfs = NULL;
+}
+
static int
aoedisk_add_sysfs(struct aoedev *d)
{
@@ -330,6 +419,7 @@
add_disk(gd);
aoedisk_add_sysfs(d);
+ aoedisk_add_debugfs(d);
spin_lock_irqsave(&d->lock, flags);
WARN_ON(!(d->flags & DEVFL_GD_NOW));
@@ -351,6 +441,8 @@
void
aoeblk_exit(void)
{
+ debugfs_remove_recursive(aoe_debugfs_dir);
+ aoe_debugfs_dir = NULL;
kmem_cache_destroy(buf_pool_cache);
}
@@ -362,7 +454,11 @@
0, 0, NULL);
if (buf_pool_cache == NULL)
return -ENOMEM;
-
+ aoe_debugfs_dir = debugfs_create_dir("aoe", NULL);
+ if (IS_ERR_OR_NULL(aoe_debugfs_dir)) {
+ pr_info("aoe: cannot create debugfs directory\n");
+ aoe_debugfs_dir = NULL;
+ }
return 0;
}
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index 4d45dba..d251543 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -380,7 +380,6 @@
{
struct frame *f;
struct buf *buf;
- struct aoetgt *t;
struct sk_buff *skb;
struct sk_buff_head queue;
ulong bcnt, fbcnt;
@@ -391,7 +390,6 @@
f = newframe(d);
if (f == NULL)
return 0;
- t = *d->tgt;
bcnt = d->maxbcnt;
if (bcnt == 0)
bcnt = DEFAULTBCNT;
@@ -485,7 +483,6 @@
struct sk_buff *skb;
struct sk_buff_head queue;
struct aoe_hdr *h;
- struct aoe_atahdr *ah;
struct aoetgt *t;
char buf[128];
u32 n;
@@ -500,7 +497,6 @@
return;
}
h = (struct aoe_hdr *) skb_mac_header(skb);
- ah = (struct aoe_atahdr *) (h+1);
if (!(f->flags & FFL_PROBE)) {
snprintf(buf, sizeof(buf),
diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c
index 784c92e..e774c50 100644
--- a/drivers/block/aoe/aoedev.c
+++ b/drivers/block/aoe/aoedev.c
@@ -12,6 +12,7 @@
#include <linux/bitmap.h>
#include <linux/kdev_t.h>
#include <linux/moduleparam.h>
+#include <linux/string.h>
#include "aoe.h"
static void dummy_timer(ulong);
@@ -241,16 +242,12 @@
static int
user_req(char *s, size_t slen, struct aoedev *d)
{
- char *p;
+ const char *p;
size_t lim;
if (!d->gd)
return 0;
- p = strrchr(d->gd->disk_name, '/');
- if (!p)
- p = d->gd->disk_name;
- else
- p += 1;
+ p = kbasename(d->gd->disk_name);
lim = sizeof(d->gd->disk_name);
lim -= p - d->gd->disk_name;
if (slen < lim)
@@ -278,6 +275,7 @@
del_timer_sync(&d->timer);
if (d->gd) {
+ aoedisk_rm_debugfs(d);
aoedisk_rm_sysfs(d);
del_gendisk(d->gd);
put_disk(d->gd);
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index 62b6c2c..d2d95ff 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -4258,6 +4258,13 @@
h->nr_cmds = h->max_commands - 4 - cciss_tape_cmds;
h->maxsgentries = readl(&(h->cfgtable->MaxSGElements));
/*
+ * The P600 may exhibit poor performnace under some workloads
+ * if we use the value in the configuration table. Limit this
+ * controller to MAXSGENTRIES (32) instead.
+ */
+ if (h->board_id == 0x3225103C)
+ h->maxsgentries = MAXSGENTRIES;
+ /*
* Limit in-command s/g elements to 32 save dma'able memory.
* Howvever spec says if 0, use 31
*/
diff --git a/drivers/block/mg_disk.c b/drivers/block/mg_disk.c
index a56cfcd..77a60be 100644
--- a/drivers/block/mg_disk.c
+++ b/drivers/block/mg_disk.c
@@ -636,7 +636,7 @@
mg_request(host->breq);
}
-void mg_times_out(unsigned long data)
+static void mg_times_out(unsigned long data)
{
struct mg_host *host = (struct mg_host *)data;
char *name;
diff --git a/drivers/block/mtip32xx/Kconfig b/drivers/block/mtip32xx/Kconfig
index 1fca1f99..0ba837f 100644
--- a/drivers/block/mtip32xx/Kconfig
+++ b/drivers/block/mtip32xx/Kconfig
@@ -4,6 +4,6 @@
config BLK_DEV_PCIESSD_MTIP32XX
tristate "Block Device Driver for Micron PCIe SSDs"
- depends on PCI && GENERIC_HARDIRQS
+ depends on PCI
help
This enables the block driver for Micron PCIe SSDs.
diff --git a/drivers/block/osdblk.c b/drivers/block/osdblk.c
index 1bbc681..79aa179 100644
--- a/drivers/block/osdblk.c
+++ b/drivers/block/osdblk.c
@@ -598,7 +598,7 @@
unsigned long ul;
struct list_head *tmp;
- rc = strict_strtoul(buf, 10, &ul);
+ rc = kstrtoul(buf, 10, &ul);
if (rc)
return rc;
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index f5d0ea1..5618847 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -44,6 +44,8 @@
*
*************************************************************************/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/pktcdvd.h>
#include <linux/module.h>
#include <linux/types.h>
@@ -69,23 +71,24 @@
#define DRIVER_NAME "pktcdvd"
-#if PACKET_DEBUG
-#define DPRINTK(fmt, args...) printk(KERN_NOTICE fmt, ##args)
-#else
-#define DPRINTK(fmt, args...)
-#endif
+#define pkt_err(pd, fmt, ...) \
+ pr_err("%s: " fmt, pd->name, ##__VA_ARGS__)
+#define pkt_notice(pd, fmt, ...) \
+ pr_notice("%s: " fmt, pd->name, ##__VA_ARGS__)
+#define pkt_info(pd, fmt, ...) \
+ pr_info("%s: " fmt, pd->name, ##__VA_ARGS__)
-#if PACKET_DEBUG > 1
-#define VPRINTK(fmt, args...) printk(KERN_NOTICE fmt, ##args)
-#else
-#define VPRINTK(fmt, args...)
-#endif
+#define pkt_dbg(level, pd, fmt, ...) \
+do { \
+ if (level == 2 && PACKET_DEBUG >= 2) \
+ pr_notice("%s: %s():" fmt, \
+ pd->name, __func__, ##__VA_ARGS__); \
+ else if (level == 1 && PACKET_DEBUG >= 1) \
+ pr_notice("%s: " fmt, pd->name, ##__VA_ARGS__); \
+} while (0)
#define MAX_SPEED 0xffff
-#define ZONE(sector, pd) (((sector) + (pd)->offset) & \
- ~(sector_t)((pd)->settings.size - 1))
-
static DEFINE_MUTEX(pktcdvd_mutex);
static struct pktcdvd_device *pkt_devs[MAX_WRITERS];
static struct proc_dir_entry *pkt_proc;
@@ -103,7 +106,10 @@
static int pkt_remove_dev(dev_t pkt_dev);
static int pkt_seq_show(struct seq_file *m, void *p);
-
+static sector_t get_zone(sector_t sector, struct pktcdvd_device *pd)
+{
+ return (sector + pd->offset) & ~(sector_t)(pd->settings.size - 1);
+}
/*
* create and register a pktcdvd kernel object.
@@ -424,7 +430,7 @@
if (ret) {
kfree(class_pktcdvd);
class_pktcdvd = NULL;
- printk(DRIVER_NAME": failed to create class pktcdvd\n");
+ pr_err("failed to create class pktcdvd\n");
return ret;
}
return 0;
@@ -517,7 +523,7 @@
{
BUG_ON(atomic_read(&pd->cdrw.pending_bios) <= 0);
if (atomic_dec_and_test(&pd->cdrw.pending_bios)) {
- VPRINTK(DRIVER_NAME": queue empty\n");
+ pkt_dbg(2, pd, "queue empty\n");
atomic_set(&pd->iosched.attention, 1);
wake_up(&pd->wqueue);
}
@@ -734,36 +740,33 @@
return ret;
}
+static const char *sense_key_string(__u8 index)
+{
+ static const char * const info[] = {
+ "No sense", "Recovered error", "Not ready",
+ "Medium error", "Hardware error", "Illegal request",
+ "Unit attention", "Data protect", "Blank check",
+ };
+
+ return index < ARRAY_SIZE(info) ? info[index] : "INVALID";
+}
+
/*
* A generic sense dump / resolve mechanism should be implemented across
* all ATAPI + SCSI devices.
*/
-static void pkt_dump_sense(struct packet_command *cgc)
+static void pkt_dump_sense(struct pktcdvd_device *pd,
+ struct packet_command *cgc)
{
- static char *info[9] = { "No sense", "Recovered error", "Not ready",
- "Medium error", "Hardware error", "Illegal request",
- "Unit attention", "Data protect", "Blank check" };
- int i;
struct request_sense *sense = cgc->sense;
- printk(DRIVER_NAME":");
- for (i = 0; i < CDROM_PACKET_SIZE; i++)
- printk(" %02x", cgc->cmd[i]);
- printk(" - ");
-
- if (sense == NULL) {
- printk("no sense\n");
- return;
- }
-
- printk("sense %02x.%02x.%02x", sense->sense_key, sense->asc, sense->ascq);
-
- if (sense->sense_key > 8) {
- printk(" (INVALID)\n");
- return;
- }
-
- printk(" (%s)\n", info[sense->sense_key]);
+ if (sense)
+ pkt_err(pd, "%*ph - sense %02x.%02x.%02x (%s)\n",
+ CDROM_PACKET_SIZE, cgc->cmd,
+ sense->sense_key, sense->asc, sense->ascq,
+ sense_key_string(sense->sense_key));
+ else
+ pkt_err(pd, "%*ph - no sense\n", CDROM_PACKET_SIZE, cgc->cmd);
}
/*
@@ -806,7 +809,7 @@
cgc.cmd[5] = write_speed & 0xff;
if ((ret = pkt_generic_packet(pd, &cgc)))
- pkt_dump_sense(&cgc);
+ pkt_dump_sense(pd, &cgc);
return ret;
}
@@ -872,7 +875,7 @@
need_write_seek = 0;
if (need_write_seek && reads_queued) {
if (atomic_read(&pd->cdrw.pending_bios) > 0) {
- VPRINTK(DRIVER_NAME": write, waiting\n");
+ pkt_dbg(2, pd, "write, waiting\n");
break;
}
pkt_flush_cache(pd);
@@ -881,7 +884,7 @@
} else {
if (!reads_queued && writes_queued) {
if (atomic_read(&pd->cdrw.pending_bios) > 0) {
- VPRINTK(DRIVER_NAME": read, waiting\n");
+ pkt_dbg(2, pd, "read, waiting\n");
break;
}
pd->iosched.writing = 1;
@@ -943,7 +946,7 @@
set_bit(PACKET_MERGE_SEGS, &pd->flags);
return 0;
} else {
- printk(DRIVER_NAME": cdrom max_phys_segments too small\n");
+ pkt_err(pd, "cdrom max_phys_segments too small\n");
return -EIO;
}
}
@@ -987,8 +990,9 @@
struct pktcdvd_device *pd = pkt->pd;
BUG_ON(!pd);
- VPRINTK("pkt_end_io_read: bio=%p sec0=%llx sec=%llx err=%d\n", bio,
- (unsigned long long)pkt->sector, (unsigned long long)bio->bi_sector, err);
+ pkt_dbg(2, pd, "bio=%p sec0=%llx sec=%llx err=%d\n",
+ bio, (unsigned long long)pkt->sector,
+ (unsigned long long)bio->bi_sector, err);
if (err)
atomic_inc(&pkt->io_errors);
@@ -1005,7 +1009,7 @@
struct pktcdvd_device *pd = pkt->pd;
BUG_ON(!pd);
- VPRINTK("pkt_end_io_packet_write: id=%d, err=%d\n", pkt->id, err);
+ pkt_dbg(2, pd, "id=%d, err=%d\n", pkt->id, err);
pd->stats.pkt_ended++;
@@ -1047,7 +1051,7 @@
spin_unlock(&pkt->lock);
if (pkt->cache_valid) {
- VPRINTK("pkt_gather_data: zone %llx cached\n",
+ pkt_dbg(2, pd, "zone %llx cached\n",
(unsigned long long)pkt->sector);
goto out_account;
}
@@ -1070,7 +1074,7 @@
p = (f * CD_FRAMESIZE) / PAGE_SIZE;
offset = (f * CD_FRAMESIZE) % PAGE_SIZE;
- VPRINTK("pkt_gather_data: Adding frame %d, page:%p offs:%d\n",
+ pkt_dbg(2, pd, "Adding frame %d, page:%p offs:%d\n",
f, pkt->pages[p], offset);
if (!bio_add_page(bio, pkt->pages[p], CD_FRAMESIZE, offset))
BUG();
@@ -1082,7 +1086,7 @@
}
out_account:
- VPRINTK("pkt_gather_data: need %d frames for zone %llx\n",
+ pkt_dbg(2, pd, "need %d frames for zone %llx\n",
frames_read, (unsigned long long)pkt->sector);
pd->stats.pkt_started++;
pd->stats.secs_rg += frames_read * (CD_FRAMESIZE >> 9);
@@ -1183,7 +1187,8 @@
"IDLE", "WAITING", "READ_WAIT", "WRITE_WAIT", "RECOVERY", "FINISHED"
};
enum packet_data_state old_state = pkt->state;
- VPRINTK("pkt %2d : s=%6llx %s -> %s\n", pkt->id, (unsigned long long)pkt->sector,
+ pkt_dbg(2, pd, "pkt %2d : s=%6llx %s -> %s\n",
+ pkt->id, (unsigned long long)pkt->sector,
state_name[old_state], state_name[state]);
#endif
pkt->state = state;
@@ -1202,12 +1207,10 @@
struct rb_node *n;
int wakeup;
- VPRINTK("handle_queue\n");
-
atomic_set(&pd->scan_queue, 0);
if (list_empty(&pd->cdrw.pkt_free_list)) {
- VPRINTK("handle_queue: no pkt\n");
+ pkt_dbg(2, pd, "no pkt\n");
return 0;
}
@@ -1224,7 +1227,7 @@
node = first_node;
while (node) {
bio = node->bio;
- zone = ZONE(bio->bi_sector, pd);
+ zone = get_zone(bio->bi_sector, pd);
list_for_each_entry(p, &pd->cdrw.pkt_active_list, list) {
if (p->sector == zone) {
bio = NULL;
@@ -1244,7 +1247,7 @@
}
spin_unlock(&pd->lock);
if (!bio) {
- VPRINTK("handle_queue: no bio\n");
+ pkt_dbg(2, pd, "no bio\n");
return 0;
}
@@ -1260,12 +1263,12 @@
* to this packet.
*/
spin_lock(&pd->lock);
- VPRINTK("pkt_handle_queue: looking for zone %llx\n", (unsigned long long)zone);
+ pkt_dbg(2, pd, "looking for zone %llx\n", (unsigned long long)zone);
while ((node = pkt_rbtree_find(pd, zone)) != NULL) {
bio = node->bio;
- VPRINTK("pkt_handle_queue: found zone=%llx\n",
- (unsigned long long)ZONE(bio->bi_sector, pd));
- if (ZONE(bio->bi_sector, pd) != zone)
+ pkt_dbg(2, pd, "found zone=%llx\n",
+ (unsigned long long)get_zone(bio->bi_sector, pd));
+ if (get_zone(bio->bi_sector, pd) != zone)
break;
pkt_rbtree_erase(pd, node);
spin_lock(&pkt->lock);
@@ -1316,7 +1319,7 @@
if (!bio_add_page(pkt->w_bio, bvec[f].bv_page, CD_FRAMESIZE, bvec[f].bv_offset))
BUG();
}
- VPRINTK(DRIVER_NAME": vcnt=%d\n", pkt->w_bio->bi_vcnt);
+ pkt_dbg(2, pd, "vcnt=%d\n", pkt->w_bio->bi_vcnt);
/*
* Fill-in bvec with data from orig_bios.
@@ -1327,7 +1330,7 @@
pkt_set_state(pkt, PACKET_WRITE_WAIT_STATE);
spin_unlock(&pkt->lock);
- VPRINTK("pkt_start_write: Writing %d frames for zone %llx\n",
+ pkt_dbg(2, pd, "Writing %d frames for zone %llx\n",
pkt->write_size, (unsigned long long)pkt->sector);
if (test_bit(PACKET_MERGE_SEGS, &pd->flags) || (pkt->write_size < pkt->frames)) {
@@ -1359,7 +1362,7 @@
{
int uptodate;
- VPRINTK("run_state_machine: pkt %d\n", pkt->id);
+ pkt_dbg(2, pd, "pkt %d\n", pkt->id);
for (;;) {
switch (pkt->state) {
@@ -1398,7 +1401,7 @@
if (pkt_start_recovery(pkt)) {
pkt_start_write(pd, pkt);
} else {
- VPRINTK("No recovery possible\n");
+ pkt_dbg(2, pd, "No recovery possible\n");
pkt_set_state(pkt, PACKET_FINISHED_STATE);
}
break;
@@ -1419,8 +1422,6 @@
{
struct packet_data *pkt, *next;
- VPRINTK("pkt_handle_packets\n");
-
/*
* Run state machine for active packets
*/
@@ -1502,9 +1503,9 @@
if (PACKET_DEBUG > 1) {
int states[PACKET_NUM_STATES];
pkt_count_states(pd, states);
- VPRINTK("kcdrwd: i:%d ow:%d rw:%d ww:%d rec:%d fin:%d\n",
- states[0], states[1], states[2], states[3],
- states[4], states[5]);
+ pkt_dbg(2, pd, "i:%d ow:%d rw:%d ww:%d rec:%d fin:%d\n",
+ states[0], states[1], states[2],
+ states[3], states[4], states[5]);
}
min_sleep_time = MAX_SCHEDULE_TIMEOUT;
@@ -1513,9 +1514,9 @@
min_sleep_time = pkt->sleep_time;
}
- VPRINTK("kcdrwd: sleeping\n");
+ pkt_dbg(2, pd, "sleeping\n");
residue = schedule_timeout(min_sleep_time);
- VPRINTK("kcdrwd: wake up\n");
+ pkt_dbg(2, pd, "wake up\n");
/* make swsusp happy with our thread */
try_to_freeze();
@@ -1563,9 +1564,10 @@
static void pkt_print_settings(struct pktcdvd_device *pd)
{
- printk(DRIVER_NAME": %s packets, ", pd->settings.fp ? "Fixed" : "Variable");
- printk("%u blocks, ", pd->settings.size >> 2);
- printk("Mode-%c disc\n", pd->settings.block_mode == 8 ? '1' : '2');
+ pkt_info(pd, "%s packets, %u blocks, Mode-%c disc\n",
+ pd->settings.fp ? "Fixed" : "Variable",
+ pd->settings.size >> 2,
+ pd->settings.block_mode == 8 ? '1' : '2');
}
static int pkt_mode_sense(struct pktcdvd_device *pd, struct packet_command *cgc, int page_code, int page_control)
@@ -1699,7 +1701,7 @@
init_cdrom_command(&cgc, buffer, sizeof(*wp), CGC_DATA_READ);
cgc.sense = &sense;
if ((ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0))) {
- pkt_dump_sense(&cgc);
+ pkt_dump_sense(pd, &cgc);
return ret;
}
@@ -1714,7 +1716,7 @@
init_cdrom_command(&cgc, buffer, size, CGC_DATA_READ);
cgc.sense = &sense;
if ((ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0))) {
- pkt_dump_sense(&cgc);
+ pkt_dump_sense(pd, &cgc);
return ret;
}
@@ -1749,14 +1751,14 @@
/*
* paranoia
*/
- printk(DRIVER_NAME": write mode wrong %d\n", wp->data_block_type);
+ pkt_err(pd, "write mode wrong %d\n", wp->data_block_type);
return 1;
}
wp->packet_size = cpu_to_be32(pd->settings.size >> 2);
cgc.buflen = cgc.cmd[8] = size;
if ((ret = pkt_mode_select(pd, &cgc))) {
- pkt_dump_sense(&cgc);
+ pkt_dump_sense(pd, &cgc);
return ret;
}
@@ -1793,7 +1795,7 @@
if (ti->rt == 1 && ti->blank == 0)
return 1;
- printk(DRIVER_NAME": bad state %d-%d-%d\n", ti->rt, ti->blank, ti->packet);
+ pkt_err(pd, "bad state %d-%d-%d\n", ti->rt, ti->blank, ti->packet);
return 0;
}
@@ -1811,7 +1813,8 @@
case 0x12: /* DVD-RAM */
return 1;
default:
- VPRINTK(DRIVER_NAME": Wrong disc profile (%x)\n", pd->mmc3_profile);
+ pkt_dbg(2, pd, "Wrong disc profile (%x)\n",
+ pd->mmc3_profile);
return 0;
}
@@ -1820,22 +1823,22 @@
* but i'm not sure, should we leave this to user apps? probably.
*/
if (di->disc_type == 0xff) {
- printk(DRIVER_NAME": Unknown disc. No track?\n");
+ pkt_notice(pd, "unknown disc - no track?\n");
return 0;
}
if (di->disc_type != 0x20 && di->disc_type != 0) {
- printk(DRIVER_NAME": Wrong disc type (%x)\n", di->disc_type);
+ pkt_err(pd, "wrong disc type (%x)\n", di->disc_type);
return 0;
}
if (di->erasable == 0) {
- printk(DRIVER_NAME": Disc not erasable\n");
+ pkt_notice(pd, "disc not erasable\n");
return 0;
}
if (di->border_status == PACKET_SESSION_RESERVED) {
- printk(DRIVER_NAME": Can't write to last track (reserved)\n");
+ pkt_err(pd, "can't write to last track (reserved)\n");
return 0;
}
@@ -1860,7 +1863,7 @@
memset(&ti, 0, sizeof(track_information));
if ((ret = pkt_get_disc_info(pd, &di))) {
- printk("failed get_disc\n");
+ pkt_err(pd, "failed get_disc\n");
return ret;
}
@@ -1871,12 +1874,12 @@
track = 1; /* (di.last_track_msb << 8) | di.last_track_lsb; */
if ((ret = pkt_get_track_info(pd, track, 1, &ti))) {
- printk(DRIVER_NAME": failed get_track\n");
+ pkt_err(pd, "failed get_track\n");
return ret;
}
if (!pkt_writable_track(pd, &ti)) {
- printk(DRIVER_NAME": can't write to this track\n");
+ pkt_err(pd, "can't write to this track\n");
return -EROFS;
}
@@ -1886,11 +1889,11 @@
*/
pd->settings.size = be32_to_cpu(ti.fixed_packet_size) << 2;
if (pd->settings.size == 0) {
- printk(DRIVER_NAME": detected zero packet size!\n");
+ pkt_notice(pd, "detected zero packet size!\n");
return -ENXIO;
}
if (pd->settings.size > PACKET_MAX_SECTORS) {
- printk(DRIVER_NAME": packet size is too big\n");
+ pkt_err(pd, "packet size is too big\n");
return -EROFS;
}
pd->settings.fp = ti.fp;
@@ -1932,7 +1935,7 @@
pd->settings.block_mode = PACKET_BLOCK_MODE2;
break;
default:
- printk(DRIVER_NAME": unknown data mode\n");
+ pkt_err(pd, "unknown data mode\n");
return -EROFS;
}
return 0;
@@ -1966,10 +1969,10 @@
cgc.buflen = cgc.cmd[8] = 2 + ((buf[0] << 8) | (buf[1] & 0xff));
ret = pkt_mode_select(pd, &cgc);
if (ret) {
- printk(DRIVER_NAME": write caching control failed\n");
- pkt_dump_sense(&cgc);
+ pkt_err(pd, "write caching control failed\n");
+ pkt_dump_sense(pd, &cgc);
} else if (!ret && set)
- printk(DRIVER_NAME": enabled write caching on %s\n", pd->name);
+ pkt_notice(pd, "enabled write caching\n");
return ret;
}
@@ -2005,7 +2008,7 @@
sizeof(struct mode_page_header);
ret = pkt_mode_sense(pd, &cgc, GPMODE_CAPABILITIES_PAGE, 0);
if (ret) {
- pkt_dump_sense(&cgc);
+ pkt_dump_sense(pd, &cgc);
return ret;
}
}
@@ -2064,7 +2067,7 @@
cgc.cmd[8] = 2;
ret = pkt_generic_packet(pd, &cgc);
if (ret) {
- pkt_dump_sense(&cgc);
+ pkt_dump_sense(pd, &cgc);
return ret;
}
size = ((unsigned int) buf[0]<<8) + buf[1] + 2;
@@ -2079,16 +2082,16 @@
cgc.cmd[8] = size;
ret = pkt_generic_packet(pd, &cgc);
if (ret) {
- pkt_dump_sense(&cgc);
+ pkt_dump_sense(pd, &cgc);
return ret;
}
if (!(buf[6] & 0x40)) {
- printk(DRIVER_NAME": Disc type is not CD-RW\n");
+ pkt_notice(pd, "disc type is not CD-RW\n");
return 1;
}
if (!(buf[6] & 0x4)) {
- printk(DRIVER_NAME": A1 values on media are not valid, maybe not CDRW?\n");
+ pkt_notice(pd, "A1 values on media are not valid, maybe not CDRW?\n");
return 1;
}
@@ -2108,14 +2111,14 @@
*speed = us_clv_to_speed[sp];
break;
default:
- printk(DRIVER_NAME": Unknown disc sub-type %d\n",st);
+ pkt_notice(pd, "unknown disc sub-type %d\n", st);
return 1;
}
if (*speed) {
- printk(DRIVER_NAME": Max. media speed: %d\n",*speed);
+ pkt_info(pd, "maximum media speed: %d\n", *speed);
return 0;
} else {
- printk(DRIVER_NAME": Unknown speed %d for sub-type %d\n",sp,st);
+ pkt_notice(pd, "unknown speed %d for sub-type %d\n", sp, st);
return 1;
}
}
@@ -2126,7 +2129,7 @@
struct request_sense sense;
int ret;
- VPRINTK(DRIVER_NAME": Performing OPC\n");
+ pkt_dbg(2, pd, "Performing OPC\n");
init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
cgc.sense = &sense;
@@ -2134,7 +2137,7 @@
cgc.cmd[0] = GPCMD_SEND_OPC;
cgc.cmd[1] = 1;
if ((ret = pkt_generic_packet(pd, &cgc)))
- pkt_dump_sense(&cgc);
+ pkt_dump_sense(pd, &cgc);
return ret;
}
@@ -2144,12 +2147,12 @@
unsigned int write_speed, media_write_speed, read_speed;
if ((ret = pkt_probe_settings(pd))) {
- VPRINTK(DRIVER_NAME": %s failed probe\n", pd->name);
+ pkt_dbg(2, pd, "failed probe\n");
return ret;
}
if ((ret = pkt_set_write_settings(pd))) {
- DPRINTK(DRIVER_NAME": %s failed saving write settings\n", pd->name);
+ pkt_dbg(1, pd, "failed saving write settings\n");
return -EIO;
}
@@ -2161,26 +2164,26 @@
case 0x13: /* DVD-RW */
case 0x1a: /* DVD+RW */
case 0x12: /* DVD-RAM */
- DPRINTK(DRIVER_NAME": write speed %ukB/s\n", write_speed);
+ pkt_dbg(1, pd, "write speed %ukB/s\n", write_speed);
break;
default:
if ((ret = pkt_media_speed(pd, &media_write_speed)))
media_write_speed = 16;
write_speed = min(write_speed, media_write_speed * 177);
- DPRINTK(DRIVER_NAME": write speed %ux\n", write_speed / 176);
+ pkt_dbg(1, pd, "write speed %ux\n", write_speed / 176);
break;
}
read_speed = write_speed;
if ((ret = pkt_set_speed(pd, write_speed, read_speed))) {
- DPRINTK(DRIVER_NAME": %s couldn't set write speed\n", pd->name);
+ pkt_dbg(1, pd, "couldn't set write speed\n");
return -EIO;
}
pd->write_speed = write_speed;
pd->read_speed = read_speed;
if ((ret = pkt_perform_opc(pd))) {
- DPRINTK(DRIVER_NAME": %s Optimum Power Calibration failed\n", pd->name);
+ pkt_dbg(1, pd, "Optimum Power Calibration failed\n");
}
return 0;
@@ -2205,7 +2208,7 @@
goto out;
if ((ret = pkt_get_last_written(pd, &lba))) {
- printk(DRIVER_NAME": pkt_get_last_written failed\n");
+ pkt_err(pd, "pkt_get_last_written failed\n");
goto out_putdev;
}
@@ -2235,11 +2238,11 @@
if (write) {
if (!pkt_grow_pktlist(pd, CONFIG_CDROM_PKTCDVD_BUFFERS)) {
- printk(DRIVER_NAME": not enough memory for buffers\n");
+ pkt_err(pd, "not enough memory for buffers\n");
ret = -ENOMEM;
goto out_putdev;
}
- printk(DRIVER_NAME": %lukB available on disc\n", lba << 1);
+ pkt_info(pd, "%lukB available on disc\n", lba << 1);
}
return 0;
@@ -2257,7 +2260,7 @@
static void pkt_release_dev(struct pktcdvd_device *pd, int flush)
{
if (flush && pkt_flush_cache(pd))
- DPRINTK(DRIVER_NAME": %s not flushing cache\n", pd->name);
+ pkt_dbg(1, pd, "not flushing cache\n");
pkt_lock_door(pd, 0);
@@ -2279,8 +2282,6 @@
struct pktcdvd_device *pd = NULL;
int ret;
- VPRINTK(DRIVER_NAME": entering open\n");
-
mutex_lock(&pktcdvd_mutex);
mutex_lock(&ctl_mutex);
pd = pkt_find_dev_from_minor(MINOR(bdev->bd_dev));
@@ -2315,7 +2316,6 @@
out_dec:
pd->refcnt--;
out:
- VPRINTK(DRIVER_NAME": failed open (%d)\n", ret);
mutex_unlock(&ctl_mutex);
mutex_unlock(&pktcdvd_mutex);
return ret;
@@ -2360,7 +2360,8 @@
pd = q->queuedata;
if (!pd) {
- printk(DRIVER_NAME": %s incorrect request queue\n", bdevname(bio->bi_bdev, b));
+ pr_err("%s incorrect request queue\n",
+ bdevname(bio->bi_bdev, b));
goto end_io;
}
@@ -2382,20 +2383,20 @@
}
if (!test_bit(PACKET_WRITABLE, &pd->flags)) {
- printk(DRIVER_NAME": WRITE for ro device %s (%llu)\n",
- pd->name, (unsigned long long)bio->bi_sector);
+ pkt_notice(pd, "WRITE for ro device (%llu)\n",
+ (unsigned long long)bio->bi_sector);
goto end_io;
}
if (!bio->bi_size || (bio->bi_size % CD_FRAMESIZE)) {
- printk(DRIVER_NAME": wrong bio size\n");
+ pkt_err(pd, "wrong bio size\n");
goto end_io;
}
blk_queue_bounce(q, &bio);
- zone = ZONE(bio->bi_sector, pd);
- VPRINTK("pkt_make_request: start = %6llx stop = %6llx\n",
+ zone = get_zone(bio->bi_sector, pd);
+ pkt_dbg(2, pd, "start = %6llx stop = %6llx\n",
(unsigned long long)bio->bi_sector,
(unsigned long long)bio_end_sector(bio));
@@ -2405,7 +2406,7 @@
sector_t last_zone;
int first_sectors;
- last_zone = ZONE(bio_end_sector(bio) - 1, pd);
+ last_zone = get_zone(bio_end_sector(bio) - 1, pd);
if (last_zone != zone) {
BUG_ON(last_zone != zone + pd->settings.size);
first_sectors = last_zone - bio->bi_sector;
@@ -2500,7 +2501,7 @@
struct bio_vec *bvec)
{
struct pktcdvd_device *pd = q->queuedata;
- sector_t zone = ZONE(bmd->bi_sector, pd);
+ sector_t zone = get_zone(bmd->bi_sector, pd);
int used = ((bmd->bi_sector - zone) << 9) + bmd->bi_size;
int remaining = (pd->settings.size << 9) - used;
int remaining2;
@@ -2609,7 +2610,7 @@
struct block_device *bdev;
if (pd->pkt_dev == dev) {
- printk(DRIVER_NAME": Recursive setup not allowed\n");
+ pkt_err(pd, "recursive setup not allowed\n");
return -EBUSY;
}
for (i = 0; i < MAX_WRITERS; i++) {
@@ -2617,11 +2618,12 @@
if (!pd2)
continue;
if (pd2->bdev->bd_dev == dev) {
- printk(DRIVER_NAME": %s already setup\n", bdevname(pd2->bdev, b));
+ pkt_err(pd, "%s already setup\n",
+ bdevname(pd2->bdev, b));
return -EBUSY;
}
if (pd2->pkt_dev == dev) {
- printk(DRIVER_NAME": Can't chain pktcdvd devices\n");
+ pkt_err(pd, "can't chain pktcdvd devices\n");
return -EBUSY;
}
}
@@ -2644,13 +2646,13 @@
atomic_set(&pd->cdrw.pending_bios, 0);
pd->cdrw.thread = kthread_run(kcdrwd, pd, "%s", pd->name);
if (IS_ERR(pd->cdrw.thread)) {
- printk(DRIVER_NAME": can't start kernel thread\n");
+ pkt_err(pd, "can't start kernel thread\n");
ret = -ENOMEM;
goto out_mem;
}
proc_create_data(pd->name, 0, pkt_proc, &pkt_proc_fops, pd);
- DPRINTK(DRIVER_NAME": writer %s mapped to %s\n", pd->name, bdevname(bdev, b));
+ pkt_dbg(1, pd, "writer mapped to %s\n", bdevname(bdev, b));
return 0;
out_mem:
@@ -2665,8 +2667,8 @@
struct pktcdvd_device *pd = bdev->bd_disk->private_data;
int ret;
- VPRINTK("pkt_ioctl: cmd %x, dev %d:%d\n", cmd,
- MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev));
+ pkt_dbg(2, pd, "cmd %x, dev %d:%d\n",
+ cmd, MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev));
mutex_lock(&pktcdvd_mutex);
switch (cmd) {
@@ -2690,7 +2692,7 @@
break;
default:
- VPRINTK(DRIVER_NAME": Unknown ioctl for %s (%x)\n", pd->name, cmd);
+ pkt_dbg(2, pd, "Unknown ioctl (%x)\n", cmd);
ret = -ENOTTY;
}
mutex_unlock(&pktcdvd_mutex);
@@ -2743,7 +2745,7 @@
if (!pkt_devs[idx])
break;
if (idx == MAX_WRITERS) {
- printk(DRIVER_NAME": max %d writers supported\n", MAX_WRITERS);
+ pr_err("max %d writers supported\n", MAX_WRITERS);
ret = -EBUSY;
goto out_mutex;
}
@@ -2818,7 +2820,7 @@
kfree(pd);
out_mutex:
mutex_unlock(&ctl_mutex);
- printk(DRIVER_NAME": setup of pktcdvd device failed\n");
+ pr_err("setup of pktcdvd device failed\n");
return ret;
}
@@ -2839,7 +2841,7 @@
break;
}
if (idx == MAX_WRITERS) {
- DPRINTK(DRIVER_NAME": dev not setup\n");
+ pr_debug("dev not setup\n");
ret = -ENXIO;
goto out;
}
@@ -2859,7 +2861,7 @@
blkdev_put(pd->bdev, FMODE_READ | FMODE_NDELAY);
remove_proc_entry(pd->name, pkt_proc);
- DPRINTK(DRIVER_NAME": writer %s unmapped\n", pd->name);
+ pkt_dbg(1, pd, "writer unmapped\n");
del_gendisk(pd->disk);
blk_cleanup_queue(pd->disk->queue);
@@ -2969,7 +2971,7 @@
ret = register_blkdev(pktdev_major, DRIVER_NAME);
if (ret < 0) {
- printk(DRIVER_NAME": Unable to register block device\n");
+ pr_err("unable to register block device\n");
goto out2;
}
if (!pktdev_major)
@@ -2983,7 +2985,7 @@
ret = misc_register(&pkt_misc);
if (ret) {
- printk(DRIVER_NAME": Unable to register misc device\n");
+ pr_err("unable to register misc device\n");
goto out_misc;
}
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 39c51cc..b22a7d0 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -5132,7 +5132,7 @@
bool already = false;
int ret;
- ret = strict_strtoul(buf, 10, &ul);
+ ret = kstrtoul(buf, 10, &ul);
if (ret)
return ret;
diff --git a/drivers/block/swim.c b/drivers/block/swim.c
index 8ed6ccb..b02d53a 100644
--- a/drivers/block/swim.c
+++ b/drivers/block/swim.c
@@ -924,7 +924,6 @@
return 0;
out_kfree:
- platform_set_drvdata(dev, NULL);
kfree(swd);
out_iounmap:
iounmap(swim_base);
@@ -962,7 +961,6 @@
if (res)
release_mem_region(res->start, resource_size(res));
- platform_set_drvdata(dev, NULL);
kfree(swd);
return 0;
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index fe5c3cd..c2014a0 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -620,7 +620,7 @@
}
/* Front end dir is a number, which is used as the handle. */
- err = strict_strtoul(strrchr(dev->otherend, '/') + 1, 0, &handle);
+ err = kstrtoul(strrchr(dev->otherend, '/') + 1, 0, &handle);
if (err)
return;
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 0d91fe5..7737b5b 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -255,10 +255,7 @@
#include <linux/fips.h>
#include <linux/ptrace.h>
#include <linux/kmemcheck.h>
-
-#ifdef CONFIG_GENERIC_HARDIRQS
-# include <linux/irq.h>
-#endif
+#include <linux/irq.h>
#include <asm/processor.h>
#include <asm/uaccess.h>
diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c
index 4519cb3..5796d01 100644
--- a/drivers/char/tpm/tpm_tis.c
+++ b/drivers/char/tpm/tpm_tis.c
@@ -766,6 +766,25 @@
}
#endif
+#ifdef CONFIG_PM_SLEEP
+static int tpm_tis_resume(struct device *dev)
+{
+ struct tpm_chip *chip = dev_get_drvdata(dev);
+ int ret;
+
+ if (chip->vendor.irq)
+ tpm_tis_reenable_interrupts(chip);
+
+ ret = tpm_pm_resume(dev);
+ if (!ret)
+ tpm_do_selftest(chip);
+
+ return ret;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(tpm_tis_pm, tpm_pm_suspend, tpm_tis_resume);
+
#ifdef CONFIG_PNP
static int tpm_tis_pnp_init(struct pnp_dev *pnp_dev,
const struct pnp_device_id *pnp_id)
@@ -787,26 +806,6 @@
return tpm_tis_init(&pnp_dev->dev, start, len, irq);
}
-static int tpm_tis_pnp_suspend(struct pnp_dev *dev, pm_message_t msg)
-{
- return tpm_pm_suspend(&dev->dev);
-}
-
-static int tpm_tis_pnp_resume(struct pnp_dev *dev)
-{
- struct tpm_chip *chip = pnp_get_drvdata(dev);
- int ret;
-
- if (chip->vendor.irq)
- tpm_tis_reenable_interrupts(chip);
-
- ret = tpm_pm_resume(&dev->dev);
- if (!ret)
- tpm_do_selftest(chip);
-
- return ret;
-}
-
static struct pnp_device_id tpm_pnp_tbl[] = {
{"PNP0C31", 0}, /* TPM */
{"ATM1200", 0}, /* Atmel */
@@ -835,9 +834,12 @@
.name = "tpm_tis",
.id_table = tpm_pnp_tbl,
.probe = tpm_tis_pnp_init,
- .suspend = tpm_tis_pnp_suspend,
- .resume = tpm_tis_pnp_resume,
.remove = tpm_tis_pnp_remove,
+#ifdef CONFIG_PM_SLEEP
+ .driver = {
+ .pm = &tpm_tis_pm,
+ },
+#endif
};
#define TIS_HID_USR_IDX sizeof(tpm_pnp_tbl)/sizeof(struct pnp_device_id) -2
@@ -846,20 +848,6 @@
MODULE_PARM_DESC(hid, "Set additional specific HID for this driver to probe");
#endif
-#ifdef CONFIG_PM_SLEEP
-static int tpm_tis_resume(struct device *dev)
-{
- struct tpm_chip *chip = dev_get_drvdata(dev);
-
- if (chip->vendor.irq)
- tpm_tis_reenable_interrupts(chip);
-
- return tpm_pm_resume(dev);
-}
-#endif
-
-static SIMPLE_DEV_PM_OPS(tpm_tis_pm, tpm_pm_suspend, tpm_tis_resume);
-
static struct platform_driver tis_drv = {
.driver = {
.name = "tpm_tis",
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 5c75e31..43c24aa 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -280,13 +280,6 @@
switch (state) {
case CPUFREQ_PRECHANGE:
- if (WARN(policy->transition_ongoing ==
- cpumask_weight(policy->cpus),
- "In middle of another frequency transition\n"))
- return;
-
- policy->transition_ongoing++;
-
/* detect if the driver reported a value as "old frequency"
* which is not equal to what the cpufreq core thinks is
* "old frequency".
@@ -306,12 +299,6 @@
break;
case CPUFREQ_POSTCHANGE:
- if (WARN(!policy->transition_ongoing,
- "No frequency transition in progress\n"))
- return;
-
- policy->transition_ongoing--;
-
adjust_jiffies(CPUFREQ_POSTCHANGE, freqs);
pr_debug("FREQ: %lu - CPU: %lu", (unsigned long)freqs->new,
(unsigned long)freqs->cpu);
@@ -437,7 +424,7 @@
static ssize_t store_##file_name \
(struct cpufreq_policy *policy, const char *buf, size_t count) \
{ \
- unsigned int ret; \
+ int ret; \
struct cpufreq_policy new_policy; \
\
ret = cpufreq_get_policy(&new_policy, policy->cpu); \
@@ -490,7 +477,7 @@
static ssize_t store_scaling_governor(struct cpufreq_policy *policy,
const char *buf, size_t count)
{
- unsigned int ret;
+ int ret;
char str_governor[16];
struct cpufreq_policy new_policy;
@@ -694,8 +681,13 @@
struct freq_attr *fattr = to_attr(attr);
ssize_t ret = -EINVAL;
+ get_online_cpus();
+
+ if (!cpu_online(policy->cpu))
+ goto unlock;
+
if (!down_read_trylock(&cpufreq_rwsem))
- goto exit;
+ goto unlock;
if (lock_policy_rwsem_write(policy->cpu) < 0)
goto up_read;
@@ -709,7 +701,9 @@
up_read:
up_read(&cpufreq_rwsem);
-exit:
+unlock:
+ put_online_cpus();
+
return ret;
}
@@ -912,11 +906,11 @@
struct cpufreq_policy *policy;
unsigned long flags;
- write_lock_irqsave(&cpufreq_driver_lock, flags);
+ read_lock_irqsave(&cpufreq_driver_lock, flags);
policy = per_cpu(cpufreq_cpu_data_fallback, cpu);
- write_unlock_irqrestore(&cpufreq_driver_lock, flags);
+ read_unlock_irqrestore(&cpufreq_driver_lock, flags);
return policy;
}
@@ -953,6 +947,21 @@
kfree(policy);
}
+static void update_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu)
+{
+ if (cpu == policy->cpu)
+ return;
+
+ policy->last_cpu = policy->cpu;
+ policy->cpu = cpu;
+
+#ifdef CONFIG_CPU_FREQ_TABLE
+ cpufreq_frequency_table_update_policy_cpu(policy);
+#endif
+ blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
+ CPUFREQ_UPDATE_POLICY_CPU, policy);
+}
+
static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif,
bool frozen)
{
@@ -1006,7 +1015,18 @@
if (!policy)
goto nomem_out;
- policy->cpu = cpu;
+
+ /*
+ * In the resume path, since we restore a saved policy, the assignment
+ * to policy->cpu is like an update of the existing policy, rather than
+ * the creation of a brand new one. So we need to perform this update
+ * by invoking update_policy_cpu().
+ */
+ if (frozen && cpu != policy->cpu)
+ update_policy_cpu(policy, cpu);
+ else
+ policy->cpu = cpu;
+
policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
cpumask_copy(policy->cpus, cpumask_of(cpu));
@@ -1098,18 +1118,6 @@
return __cpufreq_add_dev(dev, sif, false);
}
-static void update_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu)
-{
- policy->last_cpu = policy->cpu;
- policy->cpu = cpu;
-
-#ifdef CONFIG_CPU_FREQ_TABLE
- cpufreq_frequency_table_update_policy_cpu(policy);
-#endif
- blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
- CPUFREQ_UPDATE_POLICY_CPU, policy);
-}
-
static int cpufreq_nominate_new_policy_cpu(struct cpufreq_policy *policy,
unsigned int old_cpu, bool frozen)
{
@@ -1141,22 +1149,14 @@
return cpu_dev->id;
}
-/**
- * __cpufreq_remove_dev - remove a CPU device
- *
- * Removes the cpufreq interface for a CPU device.
- * Caller should already have policy_rwsem in write mode for this CPU.
- * This routine frees the rwsem before returning.
- */
-static int __cpufreq_remove_dev(struct device *dev,
- struct subsys_interface *sif, bool frozen)
+static int __cpufreq_remove_dev_prepare(struct device *dev,
+ struct subsys_interface *sif,
+ bool frozen)
{
unsigned int cpu = dev->id, cpus;
int new_cpu, ret;
unsigned long flags;
struct cpufreq_policy *policy;
- struct kobject *kobj;
- struct completion *cmp;
pr_debug("%s: unregistering CPU %u\n", __func__, cpu);
@@ -1196,8 +1196,9 @@
cpumask_clear_cpu(cpu, policy->cpus);
unlock_policy_rwsem_write(cpu);
- if (cpu != policy->cpu && !frozen) {
- sysfs_remove_link(&dev->kobj, "cpufreq");
+ if (cpu != policy->cpu) {
+ if (!frozen)
+ sysfs_remove_link(&dev->kobj, "cpufreq");
} else if (cpus > 1) {
new_cpu = cpufreq_nominate_new_policy_cpu(policy, cpu, frozen);
@@ -1213,6 +1214,33 @@
}
}
+ return 0;
+}
+
+static int __cpufreq_remove_dev_finish(struct device *dev,
+ struct subsys_interface *sif,
+ bool frozen)
+{
+ unsigned int cpu = dev->id, cpus;
+ int ret;
+ unsigned long flags;
+ struct cpufreq_policy *policy;
+ struct kobject *kobj;
+ struct completion *cmp;
+
+ read_lock_irqsave(&cpufreq_driver_lock, flags);
+ policy = per_cpu(cpufreq_cpu_data, cpu);
+ read_unlock_irqrestore(&cpufreq_driver_lock, flags);
+
+ if (!policy) {
+ pr_debug("%s: No cpu_data found\n", __func__);
+ return -EINVAL;
+ }
+
+ lock_policy_rwsem_read(cpu);
+ cpus = cpumask_weight(policy->cpus);
+ unlock_policy_rwsem_read(cpu);
+
/* If cpu is last user of policy, free policy */
if (cpus == 1) {
if (cpufreq_driver->target) {
@@ -1272,6 +1300,27 @@
return 0;
}
+/**
+ * __cpufreq_remove_dev - remove a CPU device
+ *
+ * Removes the cpufreq interface for a CPU device.
+ * Caller should already have policy_rwsem in write mode for this CPU.
+ * This routine frees the rwsem before returning.
+ */
+static inline int __cpufreq_remove_dev(struct device *dev,
+ struct subsys_interface *sif,
+ bool frozen)
+{
+ int ret;
+
+ ret = __cpufreq_remove_dev_prepare(dev, sif, frozen);
+
+ if (!ret)
+ ret = __cpufreq_remove_dev_finish(dev, sif, frozen);
+
+ return ret;
+}
+
static int cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
{
unsigned int cpu = dev->id;
@@ -1610,8 +1659,6 @@
if (cpufreq_disabled())
return -ENODEV;
- if (policy->transition_ongoing)
- return -EBUSY;
/* Make sure that target_freq is within supported range */
if (target_freq > policy->max)
@@ -1692,8 +1739,9 @@
policy->cpu, event);
mutex_lock(&cpufreq_governor_lock);
- if ((!policy->governor_enabled && (event == CPUFREQ_GOV_STOP)) ||
- (policy->governor_enabled && (event == CPUFREQ_GOV_START))) {
+ if ((policy->governor_enabled && event == CPUFREQ_GOV_START)
+ || (!policy->governor_enabled
+ && (event == CPUFREQ_GOV_LIMITS || event == CPUFREQ_GOV_STOP))) {
mutex_unlock(&cpufreq_governor_lock);
return -EBUSY;
}
@@ -1994,7 +2042,11 @@
break;
case CPU_DOWN_PREPARE:
- __cpufreq_remove_dev(dev, NULL, frozen);
+ __cpufreq_remove_dev_prepare(dev, NULL, frozen);
+ break;
+
+ case CPU_POST_DEAD:
+ __cpufreq_remove_dev_finish(dev, NULL, frozen);
break;
case CPU_DOWN_FAILED:
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index 04452f0..4cf0d28 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -74,7 +74,7 @@
for (i = 0; i < stat->state_num; i++) {
len += sprintf(buf + len, "%u %llu\n", stat->freq_table[i],
(unsigned long long)
- cputime64_to_clock_t(stat->time_in_state[i]));
+ jiffies_64_to_clock_t(stat->time_in_state[i]));
}
return len;
}
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 6efd96c..9733f29 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -522,6 +522,11 @@
ICPU(0x2a, default_policy),
ICPU(0x2d, default_policy),
ICPU(0x3a, default_policy),
+ ICPU(0x3c, default_policy),
+ ICPU(0x3e, default_policy),
+ ICPU(0x3f, default_policy),
+ ICPU(0x45, default_policy),
+ ICPU(0x46, default_policy),
{}
};
MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);
diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c
index 3ac499d..6e11701 100644
--- a/drivers/cpuidle/driver.c
+++ b/drivers/cpuidle/driver.c
@@ -331,7 +331,8 @@
spin_lock(&cpuidle_driver_lock);
drv = cpuidle_get_driver();
- drv->refcnt++;
+ if (drv)
+ drv->refcnt++;
spin_unlock(&cpuidle_driver_lock);
return drv;
diff --git a/drivers/dma/dw/Kconfig b/drivers/dma/dw/Kconfig
index dde1324..dcfe964 100644
--- a/drivers/dma/dw/Kconfig
+++ b/drivers/dma/dw/Kconfig
@@ -4,7 +4,6 @@
config DW_DMAC_CORE
tristate "Synopsys DesignWare AHB DMA support"
- depends on GENERIC_HARDIRQS
select DMA_ENGINE
config DW_DMAC
diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c
index 232fa8f..fa0affb 100644
--- a/drivers/firmware/dmi_scan.c
+++ b/drivers/firmware/dmi_scan.c
@@ -14,7 +14,7 @@
* of and an antecedent to, SMBIOS, which stands for System
* Management BIOS. See further: http://www.dmtf.org/standards
*/
-static char dmi_empty_string[] = " ";
+static const char dmi_empty_string[] = " ";
static u16 __initdata dmi_ver;
/*
@@ -49,7 +49,7 @@
return "";
}
-static char * __init dmi_string(const struct dmi_header *dm, u8 s)
+static const char * __init dmi_string(const struct dmi_header *dm, u8 s)
{
const char *bp = dmi_string_nosave(dm, s);
char *str;
@@ -62,8 +62,6 @@
str = dmi_alloc(len);
if (str != NULL)
strcpy(str, bp);
- else
- printk(KERN_ERR "dmi_string: cannot allocate %Zu bytes.\n", len);
return str;
}
@@ -133,17 +131,18 @@
return sum == 0;
}
-static char *dmi_ident[DMI_STRING_MAX];
+static const char *dmi_ident[DMI_STRING_MAX];
static LIST_HEAD(dmi_devices);
int dmi_available;
/*
* Save a DMI string
*/
-static void __init dmi_save_ident(const struct dmi_header *dm, int slot, int string)
+static void __init dmi_save_ident(const struct dmi_header *dm, int slot,
+ int string)
{
- const char *d = (const char*) dm;
- char *p;
+ const char *d = (const char *) dm;
+ const char *p;
if (dmi_ident[slot])
return;
@@ -155,9 +154,10 @@
dmi_ident[slot] = p;
}
-static void __init dmi_save_uuid(const struct dmi_header *dm, int slot, int index)
+static void __init dmi_save_uuid(const struct dmi_header *dm, int slot,
+ int index)
{
- const u8 *d = (u8*) dm + index;
+ const u8 *d = (u8 *) dm + index;
char *s;
int is_ff = 1, is_00 = 1, i;
@@ -188,12 +188,13 @@
else
sprintf(s, "%pUB", d);
- dmi_ident[slot] = s;
+ dmi_ident[slot] = s;
}
-static void __init dmi_save_type(const struct dmi_header *dm, int slot, int index)
+static void __init dmi_save_type(const struct dmi_header *dm, int slot,
+ int index)
{
- const u8 *d = (u8*) dm + index;
+ const u8 *d = (u8 *) dm + index;
char *s;
if (dmi_ident[slot])
@@ -216,10 +217,8 @@
return;
dev = dmi_alloc(sizeof(*dev) + strlen(name) + 1);
- if (!dev) {
- printk(KERN_ERR "dmi_save_one_device: out of memory.\n");
+ if (!dev)
return;
- }
dev->type = type;
strcpy((char *)(dev + 1), name);
@@ -249,17 +248,14 @@
struct dmi_device *dev;
for (i = 1; i <= count; i++) {
- char *devname = dmi_string(dm, i);
+ const char *devname = dmi_string(dm, i);
if (devname == dmi_empty_string)
continue;
dev = dmi_alloc(sizeof(*dev));
- if (!dev) {
- printk(KERN_ERR
- "dmi_save_oem_strings_devices: out of memory.\n");
+ if (!dev)
break;
- }
dev->type = DMI_DEV_TYPE_OEM_STRING;
dev->name = devname;
@@ -272,21 +268,17 @@
static void __init dmi_save_ipmi_device(const struct dmi_header *dm)
{
struct dmi_device *dev;
- void * data;
+ void *data;
data = dmi_alloc(dm->length);
- if (data == NULL) {
- printk(KERN_ERR "dmi_save_ipmi_device: out of memory.\n");
+ if (data == NULL)
return;
- }
memcpy(data, dm, dm->length);
dev = dmi_alloc(sizeof(*dev));
- if (!dev) {
- printk(KERN_ERR "dmi_save_ipmi_device: out of memory.\n");
+ if (!dev)
return;
- }
dev->type = DMI_DEV_TYPE_IPMI;
dev->name = "IPMI controller";
@@ -301,10 +293,9 @@
struct dmi_dev_onboard *onboard_dev;
onboard_dev = dmi_alloc(sizeof(*onboard_dev) + strlen(name) + 1);
- if (!onboard_dev) {
- printk(KERN_ERR "dmi_save_dev_onboard: out of memory.\n");
+ if (!onboard_dev)
return;
- }
+
onboard_dev->instance = instance;
onboard_dev->segment = segment;
onboard_dev->bus = bus;
@@ -320,7 +311,7 @@
static void __init dmi_save_extended_devices(const struct dmi_header *dm)
{
- const u8 *d = (u8*) dm + 5;
+ const u8 *d = (u8 *) dm + 5;
/* Skip disabled device */
if ((*d & 0x80) == 0)
@@ -338,7 +329,7 @@
*/
static void __init dmi_decode(const struct dmi_header *dm, void *dummy)
{
- switch(dm->type) {
+ switch (dm->type) {
case 0: /* BIOS Information */
dmi_save_ident(dm, DMI_BIOS_VENDOR, 4);
dmi_save_ident(dm, DMI_BIOS_VERSION, 5);
@@ -502,13 +493,7 @@
dmi_available = 1;
goto out;
}
- }
- else {
- /*
- * no iounmap() for that ioremap(); it would be a no-op, but
- * it's so early in setup that sucker gets confused into doing
- * what it shouldn't if we actually call it.
- */
+ } else {
p = dmi_ioremap(0xF0000, 0x10000);
if (p == NULL)
goto error;
@@ -533,7 +518,7 @@
dmi_iounmap(p, 0x10000);
}
error:
- printk(KERN_INFO "DMI not present or invalid.\n");
+ pr_info("DMI not present or invalid.\n");
out:
dmi_initialized = 1;
}
@@ -669,7 +654,7 @@
/**
* dmi_name_in_vendors - Check if string is in the DMI system or board vendor name
- * @str: Case sensitive Name
+ * @str: Case sensitive Name
*/
int dmi_name_in_vendors(const char *str)
{
@@ -696,13 +681,13 @@
* A new search is initiated by passing %NULL as the @from argument.
* If @from is not %NULL, searches continue from next device.
*/
-const struct dmi_device * dmi_find_device(int type, const char *name,
+const struct dmi_device *dmi_find_device(int type, const char *name,
const struct dmi_device *from)
{
const struct list_head *head = from ? &from->list : &dmi_devices;
struct list_head *d;
- for(d = head->next; d != &dmi_devices; d = d->next) {
+ for (d = head->next; d != &dmi_devices; d = d->next) {
const struct dmi_device *dev =
list_entry(d, struct dmi_device, list);
diff --git a/drivers/firmware/google/gsmi.c b/drivers/firmware/google/gsmi.c
index acba0b9..6eb535f 100644
--- a/drivers/firmware/google/gsmi.c
+++ b/drivers/firmware/google/gsmi.c
@@ -525,7 +525,7 @@
u32 data_type;
} param;
- rc = strict_strtoul(buf, 0, &val);
+ rc = kstrtoul(buf, 0, &val);
if (rc)
return rc;
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 349b161..b6ed304 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -203,6 +203,14 @@
select GPIO_GENERIC
select GENERIC_IRQ_CHIP
+config GPIO_OCTEON
+ tristate "Cavium OCTEON GPIO"
+ depends on GPIOLIB && CAVIUM_OCTEON_SOC
+ default y
+ help
+ Say yes here to support the on-chip GPIO lines on the OCTEON
+ family of SOCs.
+
config GPIO_PL061
bool "PrimeCell PL061 GPIO support"
depends on ARM && ARM_AMBA
@@ -314,7 +322,7 @@
config GPIO_VX855
tristate "VIA VX855/VX875 GPIO"
- depends on PCI && GENERIC_HARDIRQS
+ depends on PCI
select MFD_CORE
select MFD_VX855
help
@@ -388,7 +396,7 @@
config GPIO_MAX732X_IRQ
bool "Interrupt controller support for MAX732x"
- depends on GPIO_MAX732X=y && GENERIC_HARDIRQS
+ depends on GPIO_MAX732X=y
help
Say yes here to enable the max732x to be used as an interrupt
controller. It requires the driver to be built in the kernel.
@@ -653,7 +661,7 @@
config GPIO_RDC321X
tristate "RDC R-321x GPIO support"
- depends on PCI && GENERIC_HARDIRQS
+ depends on PCI
select MFD_CORE
select MFD_RDC321X
help
diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile
index 97438bf..98e23eb 100644
--- a/drivers/gpio/Makefile
+++ b/drivers/gpio/Makefile
@@ -52,6 +52,7 @@
obj-$(CONFIG_GPIO_MVEBU) += gpio-mvebu.o
obj-$(CONFIG_GPIO_MXC) += gpio-mxc.o
obj-$(CONFIG_GPIO_MXS) += gpio-mxs.o
+obj-$(CONFIG_GPIO_OCTEON) += gpio-octeon.o
obj-$(CONFIG_ARCH_OMAP) += gpio-omap.o
obj-$(CONFIG_GPIO_PCA953X) += gpio-pca953x.o
obj-$(CONFIG_GPIO_PCF857X) += gpio-pcf857x.o
diff --git a/drivers/gpio/gpio-octeon.c b/drivers/gpio/gpio-octeon.c
new file mode 100644
index 0000000..71a4a31
--- /dev/null
+++ b/drivers/gpio/gpio-octeon.c
@@ -0,0 +1,157 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2011, 2012 Cavium Inc.
+ */
+
+#include <linux/platform_device.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/gpio.h>
+#include <linux/io.h>
+
+#include <asm/octeon/octeon.h>
+#include <asm/octeon/cvmx-gpio-defs.h>
+
+#define RX_DAT 0x80
+#define TX_SET 0x88
+#define TX_CLEAR 0x90
+/*
+ * The address offset of the GPIO configuration register for a given
+ * line.
+ */
+static unsigned int bit_cfg_reg(unsigned int offset)
+{
+ /*
+ * The register stride is 8, with a discontinuity after the
+ * first 16.
+ */
+ if (offset < 16)
+ return 8 * offset;
+ else
+ return 8 * (offset - 16) + 0x100;
+}
+
+struct octeon_gpio {
+ struct gpio_chip chip;
+ u64 register_base;
+};
+
+static int octeon_gpio_dir_in(struct gpio_chip *chip, unsigned offset)
+{
+ struct octeon_gpio *gpio = container_of(chip, struct octeon_gpio, chip);
+
+ cvmx_write_csr(gpio->register_base + bit_cfg_reg(offset), 0);
+ return 0;
+}
+
+static void octeon_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
+{
+ struct octeon_gpio *gpio = container_of(chip, struct octeon_gpio, chip);
+ u64 mask = 1ull << offset;
+ u64 reg = gpio->register_base + (value ? TX_SET : TX_CLEAR);
+ cvmx_write_csr(reg, mask);
+}
+
+static int octeon_gpio_dir_out(struct gpio_chip *chip, unsigned offset,
+ int value)
+{
+ struct octeon_gpio *gpio = container_of(chip, struct octeon_gpio, chip);
+ union cvmx_gpio_bit_cfgx cfgx;
+
+ octeon_gpio_set(chip, offset, value);
+
+ cfgx.u64 = 0;
+ cfgx.s.tx_oe = 1;
+
+ cvmx_write_csr(gpio->register_base + bit_cfg_reg(offset), cfgx.u64);
+ return 0;
+}
+
+static int octeon_gpio_get(struct gpio_chip *chip, unsigned offset)
+{
+ struct octeon_gpio *gpio = container_of(chip, struct octeon_gpio, chip);
+ u64 read_bits = cvmx_read_csr(gpio->register_base + RX_DAT);
+
+ return ((1ull << offset) & read_bits) != 0;
+}
+
+static int octeon_gpio_probe(struct platform_device *pdev)
+{
+ struct octeon_gpio *gpio;
+ struct gpio_chip *chip;
+ struct resource *res_mem;
+ int err = 0;
+
+ gpio = devm_kzalloc(&pdev->dev, sizeof(*gpio), GFP_KERNEL);
+ if (!gpio)
+ return -ENOMEM;
+ chip = &gpio->chip;
+
+ res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (res_mem == NULL) {
+ dev_err(&pdev->dev, "found no memory resource\n");
+ err = -ENXIO;
+ goto out;
+ }
+ if (!devm_request_mem_region(&pdev->dev, res_mem->start,
+ resource_size(res_mem),
+ res_mem->name)) {
+ dev_err(&pdev->dev, "request_mem_region failed\n");
+ err = -ENXIO;
+ goto out;
+ }
+ gpio->register_base = (u64)devm_ioremap(&pdev->dev, res_mem->start,
+ resource_size(res_mem));
+
+ pdev->dev.platform_data = chip;
+ chip->label = "octeon-gpio";
+ chip->dev = &pdev->dev;
+ chip->owner = THIS_MODULE;
+ chip->base = 0;
+ chip->can_sleep = 0;
+ chip->ngpio = 20;
+ chip->direction_input = octeon_gpio_dir_in;
+ chip->get = octeon_gpio_get;
+ chip->direction_output = octeon_gpio_dir_out;
+ chip->set = octeon_gpio_set;
+ err = gpiochip_add(chip);
+ if (err)
+ goto out;
+
+ dev_info(&pdev->dev, "OCTEON GPIO driver probed.\n");
+out:
+ return err;
+}
+
+static int octeon_gpio_remove(struct platform_device *pdev)
+{
+ struct gpio_chip *chip = pdev->dev.platform_data;
+ return gpiochip_remove(chip);
+}
+
+static struct of_device_id octeon_gpio_match[] = {
+ {
+ .compatible = "cavium,octeon-3860-gpio",
+ },
+ {},
+};
+MODULE_DEVICE_TABLE(of, octeon_gpio_match);
+
+static struct platform_driver octeon_gpio_driver = {
+ .driver = {
+ .name = "octeon_gpio",
+ .owner = THIS_MODULE,
+ .of_match_table = octeon_gpio_match,
+ },
+ .probe = octeon_gpio_probe,
+ .remove = octeon_gpio_remove,
+};
+
+module_platform_driver(octeon_gpio_driver);
+
+MODULE_DESCRIPTION("Cavium Inc. OCTEON GPIO Driver");
+MODULE_AUTHOR("David Daney");
+MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 9b265a4..c27a210 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1676,7 +1676,7 @@
return 0;
out_gem_unload:
- if (dev_priv->mm.inactive_shrinker.shrink)
+ if (dev_priv->mm.inactive_shrinker.scan_objects)
unregister_shrinker(&dev_priv->mm.inactive_shrinker);
if (dev->pdev->msi_enabled)
@@ -1715,7 +1715,7 @@
i915_teardown_sysfs(dev);
- if (dev_priv->mm.inactive_shrinker.shrink)
+ if (dev_priv->mm.inactive_shrinker.scan_objects)
unregister_shrinker(&dev_priv->mm.inactive_shrinker);
mutex_lock(&dev->struct_mutex);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index d9e337f..8507c6d 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -57,10 +57,12 @@
struct drm_i915_fence_reg *fence,
bool enable);
-static int i915_gem_inactive_shrink(struct shrinker *shrinker,
- struct shrink_control *sc);
+static unsigned long i915_gem_inactive_count(struct shrinker *shrinker,
+ struct shrink_control *sc);
+static unsigned long i915_gem_inactive_scan(struct shrinker *shrinker,
+ struct shrink_control *sc);
static long i915_gem_purge(struct drm_i915_private *dev_priv, long target);
-static void i915_gem_shrink_all(struct drm_i915_private *dev_priv);
+static long i915_gem_shrink_all(struct drm_i915_private *dev_priv);
static void i915_gem_object_truncate(struct drm_i915_gem_object *obj);
static bool cpu_cache_is_coherent(struct drm_device *dev,
@@ -1769,16 +1771,21 @@
return __i915_gem_shrink(dev_priv, target, true);
}
-static void
+static long
i915_gem_shrink_all(struct drm_i915_private *dev_priv)
{
struct drm_i915_gem_object *obj, *next;
+ long freed = 0;
i915_gem_evict_everything(dev_priv->dev);
list_for_each_entry_safe(obj, next, &dev_priv->mm.unbound_list,
- global_list)
+ global_list) {
+ if (obj->pages_pin_count == 0)
+ freed += obj->base.size >> PAGE_SHIFT;
i915_gem_object_put_pages(obj);
+ }
+ return freed;
}
static int
@@ -4558,7 +4565,8 @@
dev_priv->mm.interruptible = true;
- dev_priv->mm.inactive_shrinker.shrink = i915_gem_inactive_shrink;
+ dev_priv->mm.inactive_shrinker.scan_objects = i915_gem_inactive_scan;
+ dev_priv->mm.inactive_shrinker.count_objects = i915_gem_inactive_count;
dev_priv->mm.inactive_shrinker.seeks = DEFAULT_SEEKS;
register_shrinker(&dev_priv->mm.inactive_shrinker);
}
@@ -4781,8 +4789,8 @@
#endif
}
-static int
-i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc)
+static unsigned long
+i915_gem_inactive_count(struct shrinker *shrinker, struct shrink_control *sc)
{
struct drm_i915_private *dev_priv =
container_of(shrinker,
@@ -4790,45 +4798,35 @@
mm.inactive_shrinker);
struct drm_device *dev = dev_priv->dev;
struct drm_i915_gem_object *obj;
- int nr_to_scan = sc->nr_to_scan;
bool unlock = true;
- int cnt;
+ unsigned long count;
if (!mutex_trylock(&dev->struct_mutex)) {
if (!mutex_is_locked_by(&dev->struct_mutex, current))
- return 0;
+ return SHRINK_STOP;
if (dev_priv->mm.shrinker_no_lock_stealing)
- return 0;
+ return SHRINK_STOP;
unlock = false;
}
- if (nr_to_scan) {
- nr_to_scan -= i915_gem_purge(dev_priv, nr_to_scan);
- if (nr_to_scan > 0)
- nr_to_scan -= __i915_gem_shrink(dev_priv, nr_to_scan,
- false);
- if (nr_to_scan > 0)
- i915_gem_shrink_all(dev_priv);
- }
-
- cnt = 0;
+ count = 0;
list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_list)
if (obj->pages_pin_count == 0)
- cnt += obj->base.size >> PAGE_SHIFT;
+ count += obj->base.size >> PAGE_SHIFT;
list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
if (obj->active)
continue;
if (obj->pin_count == 0 && obj->pages_pin_count == 0)
- cnt += obj->base.size >> PAGE_SHIFT;
+ count += obj->base.size >> PAGE_SHIFT;
}
if (unlock)
mutex_unlock(&dev->struct_mutex);
- return cnt;
+ return count;
}
/* All the new VM stuff */
@@ -4892,6 +4890,40 @@
return 0;
}
+static unsigned long
+i915_gem_inactive_scan(struct shrinker *shrinker, struct shrink_control *sc)
+{
+ struct drm_i915_private *dev_priv =
+ container_of(shrinker,
+ struct drm_i915_private,
+ mm.inactive_shrinker);
+ struct drm_device *dev = dev_priv->dev;
+ int nr_to_scan = sc->nr_to_scan;
+ unsigned long freed;
+ bool unlock = true;
+
+ if (!mutex_trylock(&dev->struct_mutex)) {
+ if (!mutex_is_locked_by(&dev->struct_mutex, current))
+ return 0;
+
+ if (dev_priv->mm.shrinker_no_lock_stealing)
+ return 0;
+
+ unlock = false;
+ }
+
+ freed = i915_gem_purge(dev_priv, nr_to_scan);
+ if (freed < nr_to_scan)
+ freed += __i915_gem_shrink(dev_priv, nr_to_scan,
+ false);
+ if (freed < nr_to_scan)
+ freed += i915_gem_shrink_all(dev_priv);
+
+ if (unlock)
+ mutex_unlock(&dev->struct_mutex);
+ return freed;
+}
+
struct i915_vma *i915_gem_obj_to_vma(struct drm_i915_gem_object *obj,
struct i915_address_space *vm)
{
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
index bd2a3b4..863bef9 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
@@ -377,28 +377,26 @@
return nr_free;
}
-/* Get good estimation how many pages are free in pools */
-static int ttm_pool_get_num_unused_pages(void)
-{
- unsigned i;
- int total = 0;
- for (i = 0; i < NUM_POOLS; ++i)
- total += _manager->pools[i].npages;
-
- return total;
-}
-
/**
* Callback for mm to request pool to reduce number of page held.
+ *
+ * XXX: (dchinner) Deadlock warning!
+ *
+ * ttm_page_pool_free() does memory allocation using GFP_KERNEL. that means
+ * this can deadlock when called a sc->gfp_mask that is not equal to
+ * GFP_KERNEL.
+ *
+ * This code is crying out for a shrinker per pool....
*/
-static int ttm_pool_mm_shrink(struct shrinker *shrink,
- struct shrink_control *sc)
+static unsigned long
+ttm_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
{
static atomic_t start_pool = ATOMIC_INIT(0);
unsigned i;
unsigned pool_offset = atomic_add_return(1, &start_pool);
struct ttm_page_pool *pool;
int shrink_pages = sc->nr_to_scan;
+ unsigned long freed = 0;
pool_offset = pool_offset % NUM_POOLS;
/* select start pool in round robin fashion */
@@ -408,14 +406,28 @@
break;
pool = &_manager->pools[(i + pool_offset)%NUM_POOLS];
shrink_pages = ttm_page_pool_free(pool, nr_free);
+ freed += nr_free - shrink_pages;
}
- /* return estimated number of unused pages in pool */
- return ttm_pool_get_num_unused_pages();
+ return freed;
+}
+
+
+static unsigned long
+ttm_pool_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
+{
+ unsigned i;
+ unsigned long count = 0;
+
+ for (i = 0; i < NUM_POOLS; ++i)
+ count += _manager->pools[i].npages;
+
+ return count;
}
static void ttm_pool_mm_shrink_init(struct ttm_pool_manager *manager)
{
- manager->mm_shrink.shrink = &ttm_pool_mm_shrink;
+ manager->mm_shrink.count_objects = ttm_pool_shrink_count;
+ manager->mm_shrink.scan_objects = ttm_pool_shrink_scan;
manager->mm_shrink.seeks = 1;
register_shrinker(&manager->mm_shrink);
}
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
index b8b3943..7957bee 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
@@ -918,19 +918,6 @@
}
EXPORT_SYMBOL_GPL(ttm_dma_populate);
-/* Get good estimation how many pages are free in pools */
-static int ttm_dma_pool_get_num_unused_pages(void)
-{
- struct device_pools *p;
- unsigned total = 0;
-
- mutex_lock(&_manager->lock);
- list_for_each_entry(p, &_manager->pools, pools)
- total += p->pool->npages_free;
- mutex_unlock(&_manager->lock);
- return total;
-}
-
/* Put all pages in pages list to correct pool to wait for reuse */
void ttm_dma_unpopulate(struct ttm_dma_tt *ttm_dma, struct device *dev)
{
@@ -1002,18 +989,29 @@
/**
* Callback for mm to request pool to reduce number of page held.
+ *
+ * XXX: (dchinner) Deadlock warning!
+ *
+ * ttm_dma_page_pool_free() does GFP_KERNEL memory allocation, and so attention
+ * needs to be paid to sc->gfp_mask to determine if this can be done or not.
+ * GFP_KERNEL memory allocation in a GFP_ATOMIC reclaim context woul dbe really
+ * bad.
+ *
+ * I'm getting sadder as I hear more pathetical whimpers about needing per-pool
+ * shrinkers
*/
-static int ttm_dma_pool_mm_shrink(struct shrinker *shrink,
- struct shrink_control *sc)
+static unsigned long
+ttm_dma_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
{
static atomic_t start_pool = ATOMIC_INIT(0);
unsigned idx = 0;
unsigned pool_offset = atomic_add_return(1, &start_pool);
unsigned shrink_pages = sc->nr_to_scan;
struct device_pools *p;
+ unsigned long freed = 0;
if (list_empty(&_manager->pools))
- return 0;
+ return SHRINK_STOP;
mutex_lock(&_manager->lock);
pool_offset = pool_offset % _manager->npools;
@@ -1029,18 +1027,33 @@
continue;
nr_free = shrink_pages;
shrink_pages = ttm_dma_page_pool_free(p->pool, nr_free);
+ freed += nr_free - shrink_pages;
+
pr_debug("%s: (%s:%d) Asked to shrink %d, have %d more to go\n",
p->pool->dev_name, p->pool->name, current->pid,
nr_free, shrink_pages);
}
mutex_unlock(&_manager->lock);
- /* return estimated number of unused pages in pool */
- return ttm_dma_pool_get_num_unused_pages();
+ return freed;
+}
+
+static unsigned long
+ttm_dma_pool_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
+{
+ struct device_pools *p;
+ unsigned long count = 0;
+
+ mutex_lock(&_manager->lock);
+ list_for_each_entry(p, &_manager->pools, pools)
+ count += p->pool->npages_free;
+ mutex_unlock(&_manager->lock);
+ return count;
}
static void ttm_dma_pool_mm_shrink_init(struct ttm_pool_manager *manager)
{
- manager->mm_shrink.shrink = &ttm_dma_pool_mm_shrink;
+ manager->mm_shrink.count_objects = ttm_dma_pool_shrink_count;
+ manager->mm_shrink.scan_objects = &ttm_dma_pool_shrink_scan;
manager->mm_shrink.seeks = 1;
register_shrinker(&manager->mm_shrink);
}
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index 3d7c9f6..71b70e3 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -773,7 +773,7 @@
config HID_SENSOR_HUB
tristate "HID Sensors framework support"
- depends on HID && GENERIC_HARDIRQS
+ depends on HID
select MFD_CORE
default n
---help---
diff --git a/drivers/i2c/Kconfig b/drivers/i2c/Kconfig
index e380c6e..7b7ea32 100644
--- a/drivers/i2c/Kconfig
+++ b/drivers/i2c/Kconfig
@@ -75,7 +75,6 @@
config I2C_SMBUS
tristate "SMBus-specific protocols" if !I2C_HELPER_AUTO
- depends on GENERIC_HARDIRQS
help
Say Y here if you want support for SMBus extensions to the I2C
specification. At the moment, the only supported extension is
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index fcdd321..cdcbd83 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -115,7 +115,7 @@
config I2C_ISCH
tristate "Intel SCH SMBus 1.0"
- depends on PCI && GENERIC_HARDIRQS
+ depends on PCI
select LPC_SCH
help
Say Y here if you want to use SMBus controller on the Intel SCH
@@ -546,7 +546,6 @@
config I2C_OCORES
tristate "OpenCores I2C Controller"
- depends on GENERIC_HARDIRQS
help
If you say yes to this option, support will be included for the
OpenCores I2C controller. For details see
@@ -791,7 +790,7 @@
config I2C_PARPORT
tristate "Parallel port adapter"
- depends on PARPORT && GENERIC_HARDIRQS
+ depends on PARPORT
select I2C_ALGOBIT
select I2C_SMBUS
help
@@ -816,7 +815,6 @@
config I2C_PARPORT_LIGHT
tristate "Parallel port adapter (light)"
- depends on GENERIC_HARDIRQS
select I2C_ALGOBIT
select I2C_SMBUS
help
diff --git a/drivers/i2c/busses/i2c-davinci.c b/drivers/i2c/busses/i2c-davinci.c
index 5747341..132369f 100644
--- a/drivers/i2c/busses/i2c-davinci.c
+++ b/drivers/i2c/busses/i2c-davinci.c
@@ -662,7 +662,7 @@
#endif
dev->dev = &pdev->dev;
dev->irq = irq->start;
- dev->pdata = dev_get_platdata(&dev->dev);
+ dev->pdata = dev_get_platdata(&pdev->dev);
platform_set_drvdata(pdev, dev);
if (!dev->pdata && pdev->dev.of_node) {
diff --git a/drivers/iio/Kconfig b/drivers/iio/Kconfig
index cbea327..90cf0cd 100644
--- a/drivers/iio/Kconfig
+++ b/drivers/iio/Kconfig
@@ -4,7 +4,6 @@
menuconfig IIO
tristate "Industrial I/O support"
- depends on GENERIC_HARDIRQS
help
The industrial I/O subsystem provides a unified framework for
drivers for many different types of embedded sensors using a
diff --git a/drivers/infiniband/hw/qib/Kconfig b/drivers/infiniband/hw/qib/Kconfig
index d03ca4c..495be09 100644
--- a/drivers/infiniband/hw/qib/Kconfig
+++ b/drivers/infiniband/hw/qib/Kconfig
@@ -8,7 +8,7 @@
config INFINIBAND_QIB_DCA
bool "QIB DCA support"
- depends on INFINIBAND_QIB && DCA && SMP && GENERIC_HARDIRQS && !(INFINIBAND_QIB=y && DCA=m)
+ depends on INFINIBAND_QIB && DCA && SMP && !(INFINIBAND_QIB=y && DCA=m)
default y
---help---
Setting this enables DCA support on some Intel chip sets
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 3f62041..3591855 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -1,7 +1,7 @@
/*******************************************************************************
* This file contains iSCSI extentions for RDMA (iSER) Verbs
*
- * (c) Copyright 2013 RisingTide Systems LLC.
+ * (c) Copyright 2013 Datera, Inc.
*
* Nicholas A. Bellinger <nab@linux-iscsi.org>
*
@@ -39,7 +39,17 @@
static LIST_HEAD(device_list);
static struct workqueue_struct *isert_rx_wq;
static struct workqueue_struct *isert_comp_wq;
-static struct kmem_cache *isert_cmd_cache;
+
+static void
+isert_unmap_cmd(struct isert_cmd *isert_cmd, struct isert_conn *isert_conn);
+static int
+isert_map_rdma(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
+ struct isert_rdma_wr *wr);
+static void
+isert_unreg_rdma_frwr(struct isert_cmd *isert_cmd, struct isert_conn *isert_conn);
+static int
+isert_reg_rdma_frwr(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
+ struct isert_rdma_wr *wr);
static void
isert_qp_event_callback(struct ib_event *e, void *context)
@@ -80,14 +90,8 @@
{
struct isert_device *device = isert_conn->conn_device;
struct ib_qp_init_attr attr;
- struct ib_device_attr devattr;
int ret, index, min_index = 0;
- memset(&devattr, 0, sizeof(struct ib_device_attr));
- ret = isert_query_device(cma_id->device, &devattr);
- if (ret)
- return ret;
-
mutex_lock(&device_list_mutex);
for (index = 0; index < device->cqs_used; index++)
if (device->cq_active_qps[index] <
@@ -108,7 +112,7 @@
* FIXME: Use devattr.max_sge - 2 for max_send_sge as
* work-around for RDMA_READ..
*/
- attr.cap.max_send_sge = devattr.max_sge - 2;
+ attr.cap.max_send_sge = device->dev_attr.max_sge - 2;
isert_conn->max_sge = attr.cap.max_send_sge;
attr.cap.max_recv_sge = 1;
@@ -210,14 +214,31 @@
{
struct ib_device *ib_dev = device->ib_device;
struct isert_cq_desc *cq_desc;
+ struct ib_device_attr *dev_attr;
int ret = 0, i, j;
+ dev_attr = &device->dev_attr;
+ ret = isert_query_device(ib_dev, dev_attr);
+ if (ret)
+ return ret;
+
+ /* asign function handlers */
+ if (dev_attr->device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS) {
+ device->use_frwr = 1;
+ device->reg_rdma_mem = isert_reg_rdma_frwr;
+ device->unreg_rdma_mem = isert_unreg_rdma_frwr;
+ } else {
+ device->use_frwr = 0;
+ device->reg_rdma_mem = isert_map_rdma;
+ device->unreg_rdma_mem = isert_unmap_cmd;
+ }
+
device->cqs_used = min_t(int, num_online_cpus(),
device->ib_device->num_comp_vectors);
device->cqs_used = min(ISERT_MAX_CQ, device->cqs_used);
- pr_debug("Using %d CQs, device %s supports %d vectors\n",
+ pr_debug("Using %d CQs, device %s supports %d vectors support FRWR %d\n",
device->cqs_used, device->ib_device->name,
- device->ib_device->num_comp_vectors);
+ device->ib_device->num_comp_vectors, device->use_frwr);
device->cq_desc = kzalloc(sizeof(struct isert_cq_desc) *
device->cqs_used, GFP_KERNEL);
if (!device->cq_desc) {
@@ -363,6 +384,85 @@
return device;
}
+static void
+isert_conn_free_frwr_pool(struct isert_conn *isert_conn)
+{
+ struct fast_reg_descriptor *fr_desc, *tmp;
+ int i = 0;
+
+ if (list_empty(&isert_conn->conn_frwr_pool))
+ return;
+
+ pr_debug("Freeing conn %p frwr pool", isert_conn);
+
+ list_for_each_entry_safe(fr_desc, tmp,
+ &isert_conn->conn_frwr_pool, list) {
+ list_del(&fr_desc->list);
+ ib_free_fast_reg_page_list(fr_desc->data_frpl);
+ ib_dereg_mr(fr_desc->data_mr);
+ kfree(fr_desc);
+ ++i;
+ }
+
+ if (i < isert_conn->conn_frwr_pool_size)
+ pr_warn("Pool still has %d regions registered\n",
+ isert_conn->conn_frwr_pool_size - i);
+}
+
+static int
+isert_conn_create_frwr_pool(struct isert_conn *isert_conn)
+{
+ struct fast_reg_descriptor *fr_desc;
+ struct isert_device *device = isert_conn->conn_device;
+ int i, ret;
+
+ INIT_LIST_HEAD(&isert_conn->conn_frwr_pool);
+ isert_conn->conn_frwr_pool_size = 0;
+ for (i = 0; i < ISCSI_DEF_XMIT_CMDS_MAX; i++) {
+ fr_desc = kzalloc(sizeof(*fr_desc), GFP_KERNEL);
+ if (!fr_desc) {
+ pr_err("Failed to allocate fast_reg descriptor\n");
+ ret = -ENOMEM;
+ goto err;
+ }
+
+ fr_desc->data_frpl =
+ ib_alloc_fast_reg_page_list(device->ib_device,
+ ISCSI_ISER_SG_TABLESIZE);
+ if (IS_ERR(fr_desc->data_frpl)) {
+ pr_err("Failed to allocate fr_pg_list err=%ld\n",
+ PTR_ERR(fr_desc->data_frpl));
+ ret = PTR_ERR(fr_desc->data_frpl);
+ goto err;
+ }
+
+ fr_desc->data_mr = ib_alloc_fast_reg_mr(device->dev_pd,
+ ISCSI_ISER_SG_TABLESIZE);
+ if (IS_ERR(fr_desc->data_mr)) {
+ pr_err("Failed to allocate frmr err=%ld\n",
+ PTR_ERR(fr_desc->data_mr));
+ ret = PTR_ERR(fr_desc->data_mr);
+ ib_free_fast_reg_page_list(fr_desc->data_frpl);
+ goto err;
+ }
+ pr_debug("Create fr_desc %p page_list %p\n",
+ fr_desc, fr_desc->data_frpl->page_list);
+
+ fr_desc->valid = true;
+ list_add_tail(&fr_desc->list, &isert_conn->conn_frwr_pool);
+ isert_conn->conn_frwr_pool_size++;
+ }
+
+ pr_debug("Creating conn %p frwr pool size=%d",
+ isert_conn, isert_conn->conn_frwr_pool_size);
+
+ return 0;
+
+err:
+ isert_conn_free_frwr_pool(isert_conn);
+ return ret;
+}
+
static int
isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
{
@@ -389,6 +489,7 @@
kref_init(&isert_conn->conn_kref);
kref_get(&isert_conn->conn_kref);
mutex_init(&isert_conn->conn_mutex);
+ spin_lock_init(&isert_conn->conn_lock);
cma_id->context = isert_conn;
isert_conn->conn_cm_id = cma_id;
@@ -446,6 +547,14 @@
isert_conn->conn_pd = device->dev_pd;
isert_conn->conn_mr = device->dev_mr;
+ if (device->use_frwr) {
+ ret = isert_conn_create_frwr_pool(isert_conn);
+ if (ret) {
+ pr_err("Conn: %p failed to create frwr_pool\n", isert_conn);
+ goto out_frwr;
+ }
+ }
+
ret = isert_conn_setup_qp(isert_conn, cma_id);
if (ret)
goto out_conn_dev;
@@ -459,6 +568,9 @@
return 0;
out_conn_dev:
+ if (device->use_frwr)
+ isert_conn_free_frwr_pool(isert_conn);
+out_frwr:
isert_device_try_release(device);
out_rsp_dma_map:
ib_dma_unmap_single(ib_dev, isert_conn->login_rsp_dma,
@@ -482,6 +594,9 @@
pr_debug("Entering isert_connect_release(): >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\n");
+ if (device->use_frwr)
+ isert_conn_free_frwr_pool(isert_conn);
+
if (isert_conn->conn_qp) {
cq_index = ((struct isert_cq_desc *)
isert_conn->conn_qp->recv_cq->cq_context)->cq_index;
@@ -869,46 +984,37 @@
size, rx_buflen, MAX_KEY_VALUE_PAIRS);
memcpy(login->req_buf, &rx_desc->data[0], size);
- complete(&isert_conn->conn_login_comp);
-}
-
-static void
-isert_release_cmd(struct iscsi_cmd *cmd)
-{
- struct isert_cmd *isert_cmd = container_of(cmd, struct isert_cmd,
- iscsi_cmd);
-
- pr_debug("Entering isert_release_cmd %p >>>>>>>>>>>>>>>.\n", isert_cmd);
-
- kfree(cmd->buf_ptr);
- kfree(cmd->tmr_req);
-
- kmem_cache_free(isert_cmd_cache, isert_cmd);
+ if (login->first_request) {
+ complete(&isert_conn->conn_login_comp);
+ return;
+ }
+ schedule_delayed_work(&conn->login_work, 0);
}
static struct iscsi_cmd
-*isert_alloc_cmd(struct iscsi_conn *conn, gfp_t gfp)
+*isert_allocate_cmd(struct iscsi_conn *conn, gfp_t gfp)
{
struct isert_conn *isert_conn = (struct isert_conn *)conn->context;
struct isert_cmd *isert_cmd;
+ struct iscsi_cmd *cmd;
- isert_cmd = kmem_cache_zalloc(isert_cmd_cache, gfp);
- if (!isert_cmd) {
- pr_err("Unable to allocate isert_cmd\n");
+ cmd = iscsit_allocate_cmd(conn, gfp);
+ if (!cmd) {
+ pr_err("Unable to allocate iscsi_cmd + isert_cmd\n");
return NULL;
}
+ isert_cmd = iscsit_priv_cmd(cmd);
isert_cmd->conn = isert_conn;
- isert_cmd->iscsi_cmd.release_cmd = &isert_release_cmd;
+ isert_cmd->iscsi_cmd = cmd;
- return &isert_cmd->iscsi_cmd;
+ return cmd;
}
static int
isert_handle_scsi_cmd(struct isert_conn *isert_conn,
- struct isert_cmd *isert_cmd, struct iser_rx_desc *rx_desc,
- unsigned char *buf)
+ struct isert_cmd *isert_cmd, struct iscsi_cmd *cmd,
+ struct iser_rx_desc *rx_desc, unsigned char *buf)
{
- struct iscsi_cmd *cmd = &isert_cmd->iscsi_cmd;
struct iscsi_conn *conn = isert_conn->conn;
struct iscsi_scsi_req *hdr = (struct iscsi_scsi_req *)buf;
struct scatterlist *sg;
@@ -1015,9 +1121,9 @@
static int
isert_handle_nop_out(struct isert_conn *isert_conn, struct isert_cmd *isert_cmd,
- struct iser_rx_desc *rx_desc, unsigned char *buf)
+ struct iscsi_cmd *cmd, struct iser_rx_desc *rx_desc,
+ unsigned char *buf)
{
- struct iscsi_cmd *cmd = &isert_cmd->iscsi_cmd;
struct iscsi_conn *conn = isert_conn->conn;
struct iscsi_nopout *hdr = (struct iscsi_nopout *)buf;
int rc;
@@ -1034,9 +1140,9 @@
static int
isert_handle_text_cmd(struct isert_conn *isert_conn, struct isert_cmd *isert_cmd,
- struct iser_rx_desc *rx_desc, struct iscsi_text *hdr)
+ struct iscsi_cmd *cmd, struct iser_rx_desc *rx_desc,
+ struct iscsi_text *hdr)
{
- struct iscsi_cmd *cmd = &isert_cmd->iscsi_cmd;
struct iscsi_conn *conn = isert_conn->conn;
u32 payload_length = ntoh24(hdr->dlength);
int rc;
@@ -1081,26 +1187,26 @@
switch (opcode) {
case ISCSI_OP_SCSI_CMD:
- cmd = iscsit_allocate_cmd(conn, GFP_KERNEL);
+ cmd = isert_allocate_cmd(conn, GFP_KERNEL);
if (!cmd)
break;
- isert_cmd = container_of(cmd, struct isert_cmd, iscsi_cmd);
+ isert_cmd = iscsit_priv_cmd(cmd);
isert_cmd->read_stag = read_stag;
isert_cmd->read_va = read_va;
isert_cmd->write_stag = write_stag;
isert_cmd->write_va = write_va;
- ret = isert_handle_scsi_cmd(isert_conn, isert_cmd,
+ ret = isert_handle_scsi_cmd(isert_conn, isert_cmd, cmd,
rx_desc, (unsigned char *)hdr);
break;
case ISCSI_OP_NOOP_OUT:
- cmd = iscsit_allocate_cmd(conn, GFP_KERNEL);
+ cmd = isert_allocate_cmd(conn, GFP_KERNEL);
if (!cmd)
break;
- isert_cmd = container_of(cmd, struct isert_cmd, iscsi_cmd);
- ret = isert_handle_nop_out(isert_conn, isert_cmd,
+ isert_cmd = iscsit_priv_cmd(cmd);
+ ret = isert_handle_nop_out(isert_conn, isert_cmd, cmd,
rx_desc, (unsigned char *)hdr);
break;
case ISCSI_OP_SCSI_DATA_OUT:
@@ -1108,7 +1214,7 @@
(unsigned char *)hdr);
break;
case ISCSI_OP_SCSI_TMFUNC:
- cmd = iscsit_allocate_cmd(conn, GFP_KERNEL);
+ cmd = isert_allocate_cmd(conn, GFP_KERNEL);
if (!cmd)
break;
@@ -1116,7 +1222,7 @@
(unsigned char *)hdr);
break;
case ISCSI_OP_LOGOUT:
- cmd = iscsit_allocate_cmd(conn, GFP_KERNEL);
+ cmd = isert_allocate_cmd(conn, GFP_KERNEL);
if (!cmd)
break;
@@ -1127,12 +1233,12 @@
HZ);
break;
case ISCSI_OP_TEXT:
- cmd = iscsit_allocate_cmd(conn, GFP_KERNEL);
+ cmd = isert_allocate_cmd(conn, GFP_KERNEL);
if (!cmd)
break;
- isert_cmd = container_of(cmd, struct isert_cmd, iscsi_cmd);
- ret = isert_handle_text_cmd(isert_conn, isert_cmd,
+ isert_cmd = iscsit_priv_cmd(cmd);
+ ret = isert_handle_text_cmd(isert_conn, isert_cmd, cmd,
rx_desc, (struct iscsi_text *)hdr);
break;
default:
@@ -1243,26 +1349,65 @@
struct isert_rdma_wr *wr = &isert_cmd->rdma_wr;
struct ib_device *ib_dev = isert_conn->conn_cm_id->device;
- pr_debug("isert_unmap_cmd >>>>>>>>>>>>>>>>>>>>>>>\n");
-
+ pr_debug("isert_unmap_cmd: %p\n", isert_cmd);
if (wr->sge) {
- ib_dma_unmap_sg(ib_dev, wr->sge, wr->num_sge, DMA_TO_DEVICE);
+ pr_debug("isert_unmap_cmd: %p unmap_sg op\n", isert_cmd);
+ ib_dma_unmap_sg(ib_dev, wr->sge, wr->num_sge,
+ (wr->iser_ib_op == ISER_IB_RDMA_WRITE) ?
+ DMA_TO_DEVICE : DMA_FROM_DEVICE);
wr->sge = NULL;
}
- kfree(wr->send_wr);
- wr->send_wr = NULL;
+ if (wr->send_wr) {
+ pr_debug("isert_unmap_cmd: %p free send_wr\n", isert_cmd);
+ kfree(wr->send_wr);
+ wr->send_wr = NULL;
+ }
- kfree(isert_cmd->ib_sge);
- isert_cmd->ib_sge = NULL;
+ if (wr->ib_sge) {
+ pr_debug("isert_unmap_cmd: %p free ib_sge\n", isert_cmd);
+ kfree(wr->ib_sge);
+ wr->ib_sge = NULL;
+ }
+}
+
+static void
+isert_unreg_rdma_frwr(struct isert_cmd *isert_cmd, struct isert_conn *isert_conn)
+{
+ struct isert_rdma_wr *wr = &isert_cmd->rdma_wr;
+ struct ib_device *ib_dev = isert_conn->conn_cm_id->device;
+ LIST_HEAD(unmap_list);
+
+ pr_debug("unreg_frwr_cmd: %p\n", isert_cmd);
+
+ if (wr->fr_desc) {
+ pr_debug("unreg_frwr_cmd: %p free fr_desc %p\n",
+ isert_cmd, wr->fr_desc);
+ spin_lock_bh(&isert_conn->conn_lock);
+ list_add_tail(&wr->fr_desc->list, &isert_conn->conn_frwr_pool);
+ spin_unlock_bh(&isert_conn->conn_lock);
+ wr->fr_desc = NULL;
+ }
+
+ if (wr->sge) {
+ pr_debug("unreg_frwr_cmd: %p unmap_sg op\n", isert_cmd);
+ ib_dma_unmap_sg(ib_dev, wr->sge, wr->num_sge,
+ (wr->iser_ib_op == ISER_IB_RDMA_WRITE) ?
+ DMA_TO_DEVICE : DMA_FROM_DEVICE);
+ wr->sge = NULL;
+ }
+
+ wr->ib_sge = NULL;
+ wr->send_wr = NULL;
}
static void
isert_put_cmd(struct isert_cmd *isert_cmd)
{
- struct iscsi_cmd *cmd = &isert_cmd->iscsi_cmd;
+ struct iscsi_cmd *cmd = isert_cmd->iscsi_cmd;
struct isert_conn *isert_conn = isert_cmd->conn;
struct iscsi_conn *conn = isert_conn->conn;
+ struct isert_device *device = isert_conn->conn_device;
pr_debug("Entering isert_put_cmd: %p\n", isert_cmd);
@@ -1276,7 +1421,7 @@
if (cmd->data_direction == DMA_TO_DEVICE)
iscsit_stop_dataout_timer(cmd);
- isert_unmap_cmd(isert_cmd, isert_conn);
+ device->unreg_rdma_mem(isert_cmd, isert_conn);
transport_generic_free_cmd(&cmd->se_cmd, 0);
break;
case ISCSI_OP_SCSI_TMFUNC:
@@ -1311,7 +1456,7 @@
* Fall-through
*/
default:
- isert_release_cmd(cmd);
+ iscsit_release_cmd(cmd);
break;
}
}
@@ -1347,27 +1492,16 @@
struct isert_cmd *isert_cmd)
{
struct isert_rdma_wr *wr = &isert_cmd->rdma_wr;
- struct iscsi_cmd *cmd = &isert_cmd->iscsi_cmd;
+ struct iscsi_cmd *cmd = isert_cmd->iscsi_cmd;
struct se_cmd *se_cmd = &cmd->se_cmd;
- struct ib_device *ib_dev = isert_cmd->conn->conn_cm_id->device;
+ struct isert_conn *isert_conn = isert_cmd->conn;
+ struct isert_device *device = isert_conn->conn_device;
iscsit_stop_dataout_timer(cmd);
+ device->unreg_rdma_mem(isert_cmd, isert_conn);
+ cmd->write_data_done = wr->cur_rdma_length;
- if (wr->sge) {
- pr_debug("isert_do_rdma_read_comp: Unmapping wr->sge from t_data_sg\n");
- ib_dma_unmap_sg(ib_dev, wr->sge, wr->num_sge, DMA_TO_DEVICE);
- wr->sge = NULL;
- }
-
- if (isert_cmd->ib_sge) {
- pr_debug("isert_do_rdma_read_comp: Freeing isert_cmd->ib_sge\n");
- kfree(isert_cmd->ib_sge);
- isert_cmd->ib_sge = NULL;
- }
-
- cmd->write_data_done = se_cmd->data_length;
-
- pr_debug("isert_do_rdma_read_comp, calling target_execute_cmd\n");
+ pr_debug("Cmd: %p RDMA_READ comp calling execute_cmd\n", isert_cmd);
spin_lock_bh(&cmd->istate_lock);
cmd->cmd_flags |= ICF_GOT_LAST_DATAOUT;
cmd->i_state = ISTATE_RECEIVED_LAST_DATAOUT;
@@ -1383,7 +1517,7 @@
struct isert_cmd, comp_work);
struct isert_conn *isert_conn = isert_cmd->conn;
struct ib_device *ib_dev = isert_conn->conn_cm_id->device;
- struct iscsi_cmd *cmd = &isert_cmd->iscsi_cmd;
+ struct iscsi_cmd *cmd = isert_cmd->iscsi_cmd;
switch (cmd->i_state) {
case ISTATE_SEND_TASKMGTRSP:
@@ -1429,7 +1563,7 @@
struct isert_conn *isert_conn,
struct ib_device *ib_dev)
{
- struct iscsi_cmd *cmd = &isert_cmd->iscsi_cmd;
+ struct iscsi_cmd *cmd = isert_cmd->iscsi_cmd;
if (cmd->i_state == ISTATE_SEND_TASKMGTRSP ||
cmd->i_state == ISTATE_SEND_LOGOUTRSP ||
@@ -1621,8 +1755,7 @@
static int
isert_put_response(struct iscsi_conn *conn, struct iscsi_cmd *cmd)
{
- struct isert_cmd *isert_cmd = container_of(cmd,
- struct isert_cmd, iscsi_cmd);
+ struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd);
struct isert_conn *isert_conn = (struct isert_conn *)conn->context;
struct ib_send_wr *send_wr = &isert_cmd->tx_desc.send_wr;
struct iscsi_scsi_rsp *hdr = (struct iscsi_scsi_rsp *)
@@ -1671,8 +1804,7 @@
isert_put_nopin(struct iscsi_cmd *cmd, struct iscsi_conn *conn,
bool nopout_response)
{
- struct isert_cmd *isert_cmd = container_of(cmd,
- struct isert_cmd, iscsi_cmd);
+ struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd);
struct isert_conn *isert_conn = (struct isert_conn *)conn->context;
struct ib_send_wr *send_wr = &isert_cmd->tx_desc.send_wr;
@@ -1691,8 +1823,7 @@
static int
isert_put_logout_rsp(struct iscsi_cmd *cmd, struct iscsi_conn *conn)
{
- struct isert_cmd *isert_cmd = container_of(cmd,
- struct isert_cmd, iscsi_cmd);
+ struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd);
struct isert_conn *isert_conn = (struct isert_conn *)conn->context;
struct ib_send_wr *send_wr = &isert_cmd->tx_desc.send_wr;
@@ -1710,8 +1841,7 @@
static int
isert_put_tm_rsp(struct iscsi_cmd *cmd, struct iscsi_conn *conn)
{
- struct isert_cmd *isert_cmd = container_of(cmd,
- struct isert_cmd, iscsi_cmd);
+ struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd);
struct isert_conn *isert_conn = (struct isert_conn *)conn->context;
struct ib_send_wr *send_wr = &isert_cmd->tx_desc.send_wr;
@@ -1729,8 +1859,7 @@
static int
isert_put_reject(struct iscsi_cmd *cmd, struct iscsi_conn *conn)
{
- struct isert_cmd *isert_cmd = container_of(cmd,
- struct isert_cmd, iscsi_cmd);
+ struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd);
struct isert_conn *isert_conn = (struct isert_conn *)conn->context;
struct ib_send_wr *send_wr = &isert_cmd->tx_desc.send_wr;
struct ib_device *ib_dev = isert_conn->conn_cm_id->device;
@@ -1762,8 +1891,7 @@
static int
isert_put_text_rsp(struct iscsi_cmd *cmd, struct iscsi_conn *conn)
{
- struct isert_cmd *isert_cmd = container_of(cmd,
- struct isert_cmd, iscsi_cmd);
+ struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd);
struct isert_conn *isert_conn = (struct isert_conn *)conn->context;
struct ib_send_wr *send_wr = &isert_cmd->tx_desc.send_wr;
struct iscsi_text_rsp *hdr =
@@ -1805,7 +1933,7 @@
struct ib_sge *ib_sge, struct ib_send_wr *send_wr,
u32 data_left, u32 offset)
{
- struct iscsi_cmd *cmd = &isert_cmd->iscsi_cmd;
+ struct iscsi_cmd *cmd = isert_cmd->iscsi_cmd;
struct scatterlist *sg_start, *tmp_sg;
struct ib_device *ib_dev = isert_conn->conn_cm_id->device;
u32 sg_off, page_off;
@@ -1832,8 +1960,8 @@
ib_sg_dma_len(ib_dev, tmp_sg) - page_off);
ib_sge->lkey = isert_conn->conn_mr->lkey;
- pr_debug("RDMA ib_sge: addr: 0x%16llx length: %u\n",
- ib_sge->addr, ib_sge->length);
+ pr_debug("RDMA ib_sge: addr: 0x%16llx length: %u lkey: %08x\n",
+ ib_sge->addr, ib_sge->length, ib_sge->lkey);
page_off = 0;
data_left -= ib_sge->length;
ib_sge++;
@@ -1847,85 +1975,333 @@
}
static int
-isert_put_datain(struct iscsi_conn *conn, struct iscsi_cmd *cmd)
+isert_map_rdma(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
+ struct isert_rdma_wr *wr)
{
struct se_cmd *se_cmd = &cmd->se_cmd;
- struct isert_cmd *isert_cmd = container_of(cmd,
- struct isert_cmd, iscsi_cmd);
- struct isert_rdma_wr *wr = &isert_cmd->rdma_wr;
+ struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd);
struct isert_conn *isert_conn = (struct isert_conn *)conn->context;
- struct ib_send_wr *wr_failed, *send_wr;
struct ib_device *ib_dev = isert_conn->conn_cm_id->device;
+ struct ib_send_wr *send_wr;
struct ib_sge *ib_sge;
- struct scatterlist *sg;
- u32 offset = 0, data_len, data_left, rdma_write_max;
- int rc, ret = 0, count, sg_nents, i, ib_sge_cnt;
+ struct scatterlist *sg_start;
+ u32 sg_off = 0, sg_nents;
+ u32 offset = 0, data_len, data_left, rdma_write_max, va_offset = 0;
+ int ret = 0, count, i, ib_sge_cnt;
- pr_debug("RDMA_WRITE: data_length: %u\n", se_cmd->data_length);
+ if (wr->iser_ib_op == ISER_IB_RDMA_WRITE) {
+ data_left = se_cmd->data_length;
+ iscsit_increment_maxcmdsn(cmd, conn->sess);
+ cmd->stat_sn = conn->stat_sn++;
+ } else {
+ sg_off = cmd->write_data_done / PAGE_SIZE;
+ data_left = se_cmd->data_length - cmd->write_data_done;
+ offset = cmd->write_data_done;
+ isert_cmd->tx_desc.isert_cmd = isert_cmd;
+ }
- sg = &se_cmd->t_data_sg[0];
- sg_nents = se_cmd->t_data_nents;
+ sg_start = &cmd->se_cmd.t_data_sg[sg_off];
+ sg_nents = se_cmd->t_data_nents - sg_off;
- count = ib_dma_map_sg(ib_dev, sg, sg_nents, DMA_TO_DEVICE);
+ count = ib_dma_map_sg(ib_dev, sg_start, sg_nents,
+ (wr->iser_ib_op == ISER_IB_RDMA_WRITE) ?
+ DMA_TO_DEVICE : DMA_FROM_DEVICE);
if (unlikely(!count)) {
- pr_err("Unable to map put_datain SGs\n");
+ pr_err("Cmd: %p unrable to map SGs\n", isert_cmd);
return -EINVAL;
}
- wr->sge = sg;
+ wr->sge = sg_start;
wr->num_sge = sg_nents;
- pr_debug("Mapped IB count: %u sg: %p sg_nents: %u for RDMA_WRITE\n",
- count, sg, sg_nents);
+ wr->cur_rdma_length = data_left;
+ pr_debug("Mapped cmd: %p count: %u sg: %p sg_nents: %u rdma_len %d\n",
+ isert_cmd, count, sg_start, sg_nents, data_left);
ib_sge = kzalloc(sizeof(struct ib_sge) * sg_nents, GFP_KERNEL);
if (!ib_sge) {
- pr_warn("Unable to allocate datain ib_sge\n");
+ pr_warn("Unable to allocate ib_sge\n");
ret = -ENOMEM;
goto unmap_sg;
}
- isert_cmd->ib_sge = ib_sge;
-
- pr_debug("Allocated ib_sge: %p from t_data_ents: %d for RDMA_WRITE\n",
- ib_sge, se_cmd->t_data_nents);
+ wr->ib_sge = ib_sge;
wr->send_wr_num = DIV_ROUND_UP(sg_nents, isert_conn->max_sge);
wr->send_wr = kzalloc(sizeof(struct ib_send_wr) * wr->send_wr_num,
GFP_KERNEL);
if (!wr->send_wr) {
- pr_err("Unable to allocate wr->send_wr\n");
+ pr_debug("Unable to allocate wr->send_wr\n");
ret = -ENOMEM;
goto unmap_sg;
}
- pr_debug("Allocated wr->send_wr: %p wr->send_wr_num: %u\n",
- wr->send_wr, wr->send_wr_num);
-
- iscsit_increment_maxcmdsn(cmd, conn->sess);
- cmd->stat_sn = conn->stat_sn++;
wr->isert_cmd = isert_cmd;
rdma_write_max = isert_conn->max_sge * PAGE_SIZE;
- data_left = se_cmd->data_length;
for (i = 0; i < wr->send_wr_num; i++) {
send_wr = &isert_cmd->rdma_wr.send_wr[i];
data_len = min(data_left, rdma_write_max);
- send_wr->opcode = IB_WR_RDMA_WRITE;
send_wr->send_flags = 0;
- send_wr->wr.rdma.remote_addr = isert_cmd->read_va + offset;
- send_wr->wr.rdma.rkey = isert_cmd->read_stag;
+ if (wr->iser_ib_op == ISER_IB_RDMA_WRITE) {
+ send_wr->opcode = IB_WR_RDMA_WRITE;
+ send_wr->wr.rdma.remote_addr = isert_cmd->read_va + offset;
+ send_wr->wr.rdma.rkey = isert_cmd->read_stag;
+ if (i + 1 == wr->send_wr_num)
+ send_wr->next = &isert_cmd->tx_desc.send_wr;
+ else
+ send_wr->next = &wr->send_wr[i + 1];
+ } else {
+ send_wr->opcode = IB_WR_RDMA_READ;
+ send_wr->wr.rdma.remote_addr = isert_cmd->write_va + va_offset;
+ send_wr->wr.rdma.rkey = isert_cmd->write_stag;
+ if (i + 1 == wr->send_wr_num)
+ send_wr->send_flags = IB_SEND_SIGNALED;
+ else
+ send_wr->next = &wr->send_wr[i + 1];
+ }
ib_sge_cnt = isert_build_rdma_wr(isert_conn, isert_cmd, ib_sge,
send_wr, data_len, offset);
ib_sge += ib_sge_cnt;
- if (i + 1 == wr->send_wr_num)
- send_wr->next = &isert_cmd->tx_desc.send_wr;
- else
- send_wr->next = &wr->send_wr[i + 1];
-
offset += data_len;
+ va_offset += data_len;
data_left -= data_len;
}
+
+ return 0;
+unmap_sg:
+ ib_dma_unmap_sg(ib_dev, sg_start, sg_nents,
+ (wr->iser_ib_op == ISER_IB_RDMA_WRITE) ?
+ DMA_TO_DEVICE : DMA_FROM_DEVICE);
+ return ret;
+}
+
+static int
+isert_map_fr_pagelist(struct ib_device *ib_dev,
+ struct scatterlist *sg_start, int sg_nents, u64 *fr_pl)
+{
+ u64 start_addr, end_addr, page, chunk_start = 0;
+ struct scatterlist *tmp_sg;
+ int i = 0, new_chunk, last_ent, n_pages;
+
+ n_pages = 0;
+ new_chunk = 1;
+ last_ent = sg_nents - 1;
+ for_each_sg(sg_start, tmp_sg, sg_nents, i) {
+ start_addr = ib_sg_dma_address(ib_dev, tmp_sg);
+ if (new_chunk)
+ chunk_start = start_addr;
+ end_addr = start_addr + ib_sg_dma_len(ib_dev, tmp_sg);
+
+ pr_debug("SGL[%d] dma_addr: 0x%16llx len: %u\n",
+ i, (unsigned long long)tmp_sg->dma_address,
+ tmp_sg->length);
+
+ if ((end_addr & ~PAGE_MASK) && i < last_ent) {
+ new_chunk = 0;
+ continue;
+ }
+ new_chunk = 1;
+
+ page = chunk_start & PAGE_MASK;
+ do {
+ fr_pl[n_pages++] = page;
+ pr_debug("Mapped page_list[%d] page_addr: 0x%16llx\n",
+ n_pages - 1, page);
+ page += PAGE_SIZE;
+ } while (page < end_addr);
+ }
+
+ return n_pages;
+}
+
+static int
+isert_fast_reg_mr(struct fast_reg_descriptor *fr_desc,
+ struct isert_cmd *isert_cmd, struct isert_conn *isert_conn,
+ struct ib_sge *ib_sge, u32 offset, unsigned int data_len)
+{
+ struct iscsi_cmd *cmd = isert_cmd->iscsi_cmd;
+ struct ib_device *ib_dev = isert_conn->conn_cm_id->device;
+ struct scatterlist *sg_start;
+ u32 sg_off, page_off;
+ struct ib_send_wr fr_wr, inv_wr;
+ struct ib_send_wr *bad_wr, *wr = NULL;
+ u8 key;
+ int ret, sg_nents, pagelist_len;
+
+ sg_off = offset / PAGE_SIZE;
+ sg_start = &cmd->se_cmd.t_data_sg[sg_off];
+ sg_nents = min_t(unsigned int, cmd->se_cmd.t_data_nents - sg_off,
+ ISCSI_ISER_SG_TABLESIZE);
+ page_off = offset % PAGE_SIZE;
+
+ pr_debug("Cmd: %p use fr_desc %p sg_nents %d sg_off %d offset %u\n",
+ isert_cmd, fr_desc, sg_nents, sg_off, offset);
+
+ pagelist_len = isert_map_fr_pagelist(ib_dev, sg_start, sg_nents,
+ &fr_desc->data_frpl->page_list[0]);
+
+ if (!fr_desc->valid) {
+ memset(&inv_wr, 0, sizeof(inv_wr));
+ inv_wr.opcode = IB_WR_LOCAL_INV;
+ inv_wr.ex.invalidate_rkey = fr_desc->data_mr->rkey;
+ wr = &inv_wr;
+ /* Bump the key */
+ key = (u8)(fr_desc->data_mr->rkey & 0x000000FF);
+ ib_update_fast_reg_key(fr_desc->data_mr, ++key);
+ }
+
+ /* Prepare FASTREG WR */
+ memset(&fr_wr, 0, sizeof(fr_wr));
+ fr_wr.opcode = IB_WR_FAST_REG_MR;
+ fr_wr.wr.fast_reg.iova_start =
+ fr_desc->data_frpl->page_list[0] + page_off;
+ fr_wr.wr.fast_reg.page_list = fr_desc->data_frpl;
+ fr_wr.wr.fast_reg.page_list_len = pagelist_len;
+ fr_wr.wr.fast_reg.page_shift = PAGE_SHIFT;
+ fr_wr.wr.fast_reg.length = data_len;
+ fr_wr.wr.fast_reg.rkey = fr_desc->data_mr->rkey;
+ fr_wr.wr.fast_reg.access_flags = IB_ACCESS_LOCAL_WRITE;
+
+ if (!wr)
+ wr = &fr_wr;
+ else
+ wr->next = &fr_wr;
+
+ ret = ib_post_send(isert_conn->conn_qp, wr, &bad_wr);
+ if (ret) {
+ pr_err("fast registration failed, ret:%d\n", ret);
+ return ret;
+ }
+ fr_desc->valid = false;
+
+ ib_sge->lkey = fr_desc->data_mr->lkey;
+ ib_sge->addr = fr_desc->data_frpl->page_list[0] + page_off;
+ ib_sge->length = data_len;
+
+ pr_debug("RDMA ib_sge: addr: 0x%16llx length: %u lkey: %08x\n",
+ ib_sge->addr, ib_sge->length, ib_sge->lkey);
+
+ return ret;
+}
+
+static int
+isert_reg_rdma_frwr(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
+ struct isert_rdma_wr *wr)
+{
+ struct se_cmd *se_cmd = &cmd->se_cmd;
+ struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd);
+ struct isert_conn *isert_conn = (struct isert_conn *)conn->context;
+ struct ib_device *ib_dev = isert_conn->conn_cm_id->device;
+ struct ib_send_wr *send_wr;
+ struct ib_sge *ib_sge;
+ struct scatterlist *sg_start;
+ struct fast_reg_descriptor *fr_desc;
+ u32 sg_off = 0, sg_nents;
+ u32 offset = 0, data_len, data_left, rdma_write_max;
+ int ret = 0, count;
+ unsigned long flags;
+
+ if (wr->iser_ib_op == ISER_IB_RDMA_WRITE) {
+ data_left = se_cmd->data_length;
+ iscsit_increment_maxcmdsn(cmd, conn->sess);
+ cmd->stat_sn = conn->stat_sn++;
+ } else {
+ sg_off = cmd->write_data_done / PAGE_SIZE;
+ data_left = se_cmd->data_length - cmd->write_data_done;
+ offset = cmd->write_data_done;
+ isert_cmd->tx_desc.isert_cmd = isert_cmd;
+ }
+
+ sg_start = &cmd->se_cmd.t_data_sg[sg_off];
+ sg_nents = se_cmd->t_data_nents - sg_off;
+
+ count = ib_dma_map_sg(ib_dev, sg_start, sg_nents,
+ (wr->iser_ib_op == ISER_IB_RDMA_WRITE) ?
+ DMA_TO_DEVICE : DMA_FROM_DEVICE);
+ if (unlikely(!count)) {
+ pr_err("Cmd: %p unrable to map SGs\n", isert_cmd);
+ return -EINVAL;
+ }
+ wr->sge = sg_start;
+ wr->num_sge = sg_nents;
+ pr_debug("Mapped cmd: %p count: %u sg: %p sg_nents: %u rdma_len %d\n",
+ isert_cmd, count, sg_start, sg_nents, data_left);
+
+ memset(&wr->s_ib_sge, 0, sizeof(*ib_sge));
+ ib_sge = &wr->s_ib_sge;
+ wr->ib_sge = ib_sge;
+
+ wr->send_wr_num = 1;
+ memset(&wr->s_send_wr, 0, sizeof(*send_wr));
+ wr->send_wr = &wr->s_send_wr;
+
+ wr->isert_cmd = isert_cmd;
+ rdma_write_max = ISCSI_ISER_SG_TABLESIZE * PAGE_SIZE;
+
+ send_wr = &isert_cmd->rdma_wr.s_send_wr;
+ send_wr->sg_list = ib_sge;
+ send_wr->num_sge = 1;
+ send_wr->wr_id = (unsigned long)&isert_cmd->tx_desc;
+ if (wr->iser_ib_op == ISER_IB_RDMA_WRITE) {
+ send_wr->opcode = IB_WR_RDMA_WRITE;
+ send_wr->wr.rdma.remote_addr = isert_cmd->read_va;
+ send_wr->wr.rdma.rkey = isert_cmd->read_stag;
+ send_wr->send_flags = 0;
+ send_wr->next = &isert_cmd->tx_desc.send_wr;
+ } else {
+ send_wr->opcode = IB_WR_RDMA_READ;
+ send_wr->wr.rdma.remote_addr = isert_cmd->write_va;
+ send_wr->wr.rdma.rkey = isert_cmd->write_stag;
+ send_wr->send_flags = IB_SEND_SIGNALED;
+ }
+
+ data_len = min(data_left, rdma_write_max);
+ wr->cur_rdma_length = data_len;
+
+ spin_lock_irqsave(&isert_conn->conn_lock, flags);
+ fr_desc = list_first_entry(&isert_conn->conn_frwr_pool,
+ struct fast_reg_descriptor, list);
+ list_del(&fr_desc->list);
+ spin_unlock_irqrestore(&isert_conn->conn_lock, flags);
+ wr->fr_desc = fr_desc;
+
+ ret = isert_fast_reg_mr(fr_desc, isert_cmd, isert_conn,
+ ib_sge, offset, data_len);
+ if (ret) {
+ list_add_tail(&fr_desc->list, &isert_conn->conn_frwr_pool);
+ goto unmap_sg;
+ }
+
+ return 0;
+
+unmap_sg:
+ ib_dma_unmap_sg(ib_dev, sg_start, sg_nents,
+ (wr->iser_ib_op == ISER_IB_RDMA_WRITE) ?
+ DMA_TO_DEVICE : DMA_FROM_DEVICE);
+ return ret;
+}
+
+static int
+isert_put_datain(struct iscsi_conn *conn, struct iscsi_cmd *cmd)
+{
+ struct se_cmd *se_cmd = &cmd->se_cmd;
+ struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd);
+ struct isert_rdma_wr *wr = &isert_cmd->rdma_wr;
+ struct isert_conn *isert_conn = (struct isert_conn *)conn->context;
+ struct isert_device *device = isert_conn->conn_device;
+ struct ib_send_wr *wr_failed;
+ int rc;
+
+ pr_debug("Cmd: %p RDMA_WRITE data_length: %u\n",
+ isert_cmd, se_cmd->data_length);
+ wr->iser_ib_op = ISER_IB_RDMA_WRITE;
+ rc = device->reg_rdma_mem(conn, cmd, wr);
+ if (rc) {
+ pr_err("Cmd: %p failed to prepare RDMA res\n", isert_cmd);
+ return rc;
+ }
+
/*
* Build isert_conn->tx_desc for iSCSI response PDU and attach
*/
@@ -1942,105 +2318,30 @@
pr_warn("ib_post_send() failed for IB_WR_RDMA_WRITE\n");
atomic_dec(&isert_conn->post_send_buf_count);
}
- pr_debug("Posted RDMA_WRITE + Response for iSER Data READ\n");
- return 1;
+ pr_debug("Cmd: %p posted RDMA_WRITE + Response for iSER Data READ\n",
+ isert_cmd);
-unmap_sg:
- ib_dma_unmap_sg(ib_dev, sg, sg_nents, DMA_TO_DEVICE);
- return ret;
+ return 1;
}
static int
isert_get_dataout(struct iscsi_conn *conn, struct iscsi_cmd *cmd, bool recovery)
{
struct se_cmd *se_cmd = &cmd->se_cmd;
- struct isert_cmd *isert_cmd = container_of(cmd,
- struct isert_cmd, iscsi_cmd);
+ struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd);
struct isert_rdma_wr *wr = &isert_cmd->rdma_wr;
struct isert_conn *isert_conn = (struct isert_conn *)conn->context;
- struct ib_send_wr *wr_failed, *send_wr;
- struct ib_sge *ib_sge;
- struct ib_device *ib_dev = isert_conn->conn_cm_id->device;
- struct scatterlist *sg_start;
- u32 sg_off, sg_nents, page_off, va_offset = 0;
- u32 offset = 0, data_len, data_left, rdma_write_max;
- int rc, ret = 0, count, i, ib_sge_cnt;
+ struct isert_device *device = isert_conn->conn_device;
+ struct ib_send_wr *wr_failed;
+ int rc;
- pr_debug("RDMA_READ: data_length: %u write_data_done: %u\n",
- se_cmd->data_length, cmd->write_data_done);
-
- sg_off = cmd->write_data_done / PAGE_SIZE;
- sg_start = &cmd->se_cmd.t_data_sg[sg_off];
- page_off = cmd->write_data_done % PAGE_SIZE;
-
- pr_debug("RDMA_READ: sg_off: %d, sg_start: %p page_off: %d\n",
- sg_off, sg_start, page_off);
-
- data_left = se_cmd->data_length - cmd->write_data_done;
- sg_nents = se_cmd->t_data_nents - sg_off;
-
- pr_debug("RDMA_READ: data_left: %d, sg_nents: %d\n",
- data_left, sg_nents);
-
- count = ib_dma_map_sg(ib_dev, sg_start, sg_nents, DMA_FROM_DEVICE);
- if (unlikely(!count)) {
- pr_err("Unable to map get_dataout SGs\n");
- return -EINVAL;
- }
- wr->sge = sg_start;
- wr->num_sge = sg_nents;
- pr_debug("Mapped IB count: %u sg_start: %p sg_nents: %u for RDMA_READ\n",
- count, sg_start, sg_nents);
-
- ib_sge = kzalloc(sizeof(struct ib_sge) * sg_nents, GFP_KERNEL);
- if (!ib_sge) {
- pr_warn("Unable to allocate dataout ib_sge\n");
- ret = -ENOMEM;
- goto unmap_sg;
- }
- isert_cmd->ib_sge = ib_sge;
-
- pr_debug("Using ib_sge: %p from sg_ents: %d for RDMA_READ\n",
- ib_sge, sg_nents);
-
- wr->send_wr_num = DIV_ROUND_UP(sg_nents, isert_conn->max_sge);
- wr->send_wr = kzalloc(sizeof(struct ib_send_wr) * wr->send_wr_num,
- GFP_KERNEL);
- if (!wr->send_wr) {
- pr_debug("Unable to allocate wr->send_wr\n");
- ret = -ENOMEM;
- goto unmap_sg;
- }
- pr_debug("Allocated wr->send_wr: %p wr->send_wr_num: %u\n",
- wr->send_wr, wr->send_wr_num);
-
- isert_cmd->tx_desc.isert_cmd = isert_cmd;
-
+ pr_debug("Cmd: %p RDMA_READ data_length: %u write_data_done: %u\n",
+ isert_cmd, se_cmd->data_length, cmd->write_data_done);
wr->iser_ib_op = ISER_IB_RDMA_READ;
- wr->isert_cmd = isert_cmd;
- rdma_write_max = isert_conn->max_sge * PAGE_SIZE;
- offset = cmd->write_data_done;
-
- for (i = 0; i < wr->send_wr_num; i++) {
- send_wr = &isert_cmd->rdma_wr.send_wr[i];
- data_len = min(data_left, rdma_write_max);
-
- send_wr->opcode = IB_WR_RDMA_READ;
- send_wr->wr.rdma.remote_addr = isert_cmd->write_va + va_offset;
- send_wr->wr.rdma.rkey = isert_cmd->write_stag;
-
- ib_sge_cnt = isert_build_rdma_wr(isert_conn, isert_cmd, ib_sge,
- send_wr, data_len, offset);
- ib_sge += ib_sge_cnt;
-
- if (i + 1 == wr->send_wr_num)
- send_wr->send_flags = IB_SEND_SIGNALED;
- else
- send_wr->next = &wr->send_wr[i + 1];
-
- offset += data_len;
- va_offset += data_len;
- data_left -= data_len;
+ rc = device->reg_rdma_mem(conn, cmd, wr);
+ if (rc) {
+ pr_err("Cmd: %p failed to prepare RDMA res\n", isert_cmd);
+ return rc;
}
atomic_inc(&isert_conn->post_send_buf_count);
@@ -2050,12 +2351,10 @@
pr_warn("ib_post_send() failed for IB_WR_RDMA_READ\n");
atomic_dec(&isert_conn->post_send_buf_count);
}
- pr_debug("Posted RDMA_READ memory for ISER Data WRITE\n");
- return 0;
+ pr_debug("Cmd: %p posted RDMA_READ memory for ISER Data WRITE\n",
+ isert_cmd);
-unmap_sg:
- ib_dma_unmap_sg(ib_dev, sg_start, sg_nents, DMA_FROM_DEVICE);
- return ret;
+ return 0;
}
static int
@@ -2224,6 +2523,14 @@
int ret;
pr_debug("isert_get_login_rx before conn_login_comp conn: %p\n", conn);
+ /*
+ * For login requests after the first PDU, isert_rx_login_req() will
+ * kick schedule_delayed_work(&conn->login_work) as the packet is
+ * received, which turns this callback from iscsi_target_do_login_rx()
+ * into a NOP.
+ */
+ if (!login->first_request)
+ return 0;
ret = wait_for_completion_interruptible(&isert_conn->conn_login_comp);
if (ret)
@@ -2393,12 +2700,12 @@
static struct iscsit_transport iser_target_transport = {
.name = "IB/iSER",
.transport_type = ISCSI_INFINIBAND,
+ .priv_size = sizeof(struct isert_cmd),
.owner = THIS_MODULE,
.iscsit_setup_np = isert_setup_np,
.iscsit_accept_np = isert_accept_np,
.iscsit_free_np = isert_free_np,
.iscsit_free_conn = isert_free_conn,
- .iscsit_alloc_cmd = isert_alloc_cmd,
.iscsit_get_login_rx = isert_get_login_rx,
.iscsit_put_login_tx = isert_put_login_tx,
.iscsit_immediate_queue = isert_immediate_queue,
@@ -2425,21 +2732,10 @@
goto destroy_rx_wq;
}
- isert_cmd_cache = kmem_cache_create("isert_cmd_cache",
- sizeof(struct isert_cmd), __alignof__(struct isert_cmd),
- 0, NULL);
- if (!isert_cmd_cache) {
- pr_err("Unable to create isert_cmd_cache\n");
- ret = -ENOMEM;
- goto destroy_tx_cq;
- }
-
iscsit_register_transport(&iser_target_transport);
pr_debug("iSER_TARGET[0] - Loaded iser_target_transport\n");
return 0;
-destroy_tx_cq:
- destroy_workqueue(isert_comp_wq);
destroy_rx_wq:
destroy_workqueue(isert_rx_wq);
return ret;
@@ -2447,7 +2743,6 @@
static void __exit isert_exit(void)
{
- kmem_cache_destroy(isert_cmd_cache);
destroy_workqueue(isert_comp_wq);
destroy_workqueue(isert_rx_wq);
iscsit_unregister_transport(&iser_target_transport);
diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h
index 191117b..631f209 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.h
+++ b/drivers/infiniband/ulp/isert/ib_isert.h
@@ -5,6 +5,7 @@
#include <rdma/rdma_cm.h>
#define ISERT_RDMA_LISTEN_BACKLOG 10
+#define ISCSI_ISER_SG_TABLESIZE 256
enum isert_desc_type {
ISCSI_TX_CONTROL,
@@ -45,15 +46,26 @@
struct ib_send_wr send_wr;
} __packed;
+struct fast_reg_descriptor {
+ struct list_head list;
+ struct ib_mr *data_mr;
+ struct ib_fast_reg_page_list *data_frpl;
+ bool valid;
+};
+
struct isert_rdma_wr {
struct list_head wr_list;
struct isert_cmd *isert_cmd;
enum iser_ib_op_code iser_ib_op;
struct ib_sge *ib_sge;
+ struct ib_sge s_ib_sge;
int num_sge;
struct scatterlist *sge;
int send_wr_num;
struct ib_send_wr *send_wr;
+ struct ib_send_wr s_send_wr;
+ u32 cur_rdma_length;
+ struct fast_reg_descriptor *fr_desc;
};
struct isert_cmd {
@@ -67,8 +79,7 @@
u32 write_va_off;
u32 rdma_wr_num;
struct isert_conn *conn;
- struct iscsi_cmd iscsi_cmd;
- struct ib_sge *ib_sge;
+ struct iscsi_cmd *iscsi_cmd;
struct iser_tx_desc tx_desc;
struct isert_rdma_wr rdma_wr;
struct work_struct comp_work;
@@ -106,6 +117,10 @@
wait_queue_head_t conn_wait;
wait_queue_head_t conn_wait_comp_err;
struct kref conn_kref;
+ struct list_head conn_frwr_pool;
+ int conn_frwr_pool_size;
+ /* lock to protect frwr_pool */
+ spinlock_t conn_lock;
};
#define ISERT_MAX_CQ 64
@@ -118,6 +133,7 @@
};
struct isert_device {
+ int use_frwr;
int cqs_used;
int refcount;
int cq_active_qps[ISERT_MAX_CQ];
@@ -128,6 +144,12 @@
struct ib_cq *dev_tx_cq[ISERT_MAX_CQ];
struct isert_cq_desc *cq_desc;
struct list_head dev_node;
+ struct ib_device_attr dev_attr;
+ int (*reg_rdma_mem)(struct iscsi_conn *conn,
+ struct iscsi_cmd *cmd,
+ struct isert_rdma_wr *wr);
+ void (*unreg_rdma_mem)(struct isert_cmd *isert_cmd,
+ struct isert_conn *isert_conn);
};
struct isert_np {
diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig
index 269d4c3..c1edd39 100644
--- a/drivers/input/keyboard/Kconfig
+++ b/drivers/input/keyboard/Kconfig
@@ -224,7 +224,7 @@
config KEYBOARD_TCA8418
tristate "TCA8418 Keypad Support"
- depends on I2C && GENERIC_HARDIRQS
+ depends on I2C
select INPUT_MATRIXKMAP
help
This driver implements basic keypad functionality
@@ -303,7 +303,7 @@
config KEYBOARD_LM8323
tristate "LM8323 keypad chip"
- depends on I2C && GENERIC_HARDIRQS
+ depends on I2C
depends on LEDS_CLASS
help
If you say yes here you get support for the National Semiconductor
diff --git a/drivers/input/serio/Kconfig b/drivers/input/serio/Kconfig
index 1e691a3..33b3e88 100644
--- a/drivers/input/serio/Kconfig
+++ b/drivers/input/serio/Kconfig
@@ -239,7 +239,6 @@
config SERIO_ARC_PS2
tristate "ARC PS/2 support"
- depends on GENERIC_HARDIRQS
help
Say Y here if you have an ARC FPGA platform with a PS/2
controller in it.
diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig
index 3b9758b..e09ec67 100644
--- a/drivers/input/touchscreen/Kconfig
+++ b/drivers/input/touchscreen/Kconfig
@@ -389,7 +389,7 @@
config TOUCHSCREEN_MMS114
tristate "MELFAS MMS114 touchscreen"
- depends on I2C && GENERIC_HARDIRQS
+ depends on I2C
help
Say Y here if you have the MELFAS MMS114 touchscreen controller
chip in your system.
@@ -845,7 +845,7 @@
config TOUCHSCREEN_TSC2005
tristate "TSC2005 based touchscreens"
- depends on SPI_MASTER && GENERIC_HARDIRQS
+ depends on SPI_MASTER
help
Say Y here if you have a TSC2005 based touchscreen.
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 820d85c..fe302e3 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -17,6 +17,16 @@
def_bool y
depends on OF
+config FSL_PAMU
+ bool "Freescale IOMMU support"
+ depends on PPC_E500MC
+ select IOMMU_API
+ select GENERIC_ALLOCATOR
+ help
+ Freescale PAMU support. PAMU is the IOMMU present on Freescale QorIQ platforms.
+ PAMU can authorize memory access, remap the memory address, and remap I/O
+ transaction types.
+
# MSM IOMMU support
config MSM_IOMMU
bool "MSM IOMMU Support"
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index bbe7041..14c1f47 100644
--- a/drivers/iommu/Makefile
+++ b/drivers/iommu/Makefile
@@ -16,3 +16,4 @@
obj-$(CONFIG_EXYNOS_IOMMU) += exynos-iommu.o
obj-$(CONFIG_SHMOBILE_IOMMU) += shmobile-iommu.o
obj-$(CONFIG_SHMOBILE_IPMMU) += shmobile-ipmmu.o
+obj-$(CONFIG_FSL_PAMU) += fsl_pamu.o fsl_pamu_domain.o
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 6dc6594..72531f0 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -456,8 +456,10 @@
}
ret = init_iommu_group(dev);
- if (ret)
+ if (ret) {
+ free_dev_data(dev_data);
return ret;
+ }
if (pci_iommuv2_capable(pdev)) {
struct amd_iommu *iommu;
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 7acbf35..8f798be 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -1384,7 +1384,7 @@
if (iommu->int_enabled)
goto enable_faults;
- if (pci_find_capability(iommu->dev, PCI_CAP_ID_MSI))
+ if (iommu->dev->msi_cap)
ret = iommu_setup_msi(iommu);
else
ret = -ENODEV;
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index ebd0a4c..f417e89 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -56,9 +56,6 @@
/* Maximum number of mapping groups per SMMU */
#define ARM_SMMU_MAX_SMRS 128
-/* Number of VMIDs per SMMU */
-#define ARM_SMMU_NUM_VMIDS 256
-
/* SMMU global address space */
#define ARM_SMMU_GR0(smmu) ((smmu)->base)
#define ARM_SMMU_GR1(smmu) ((smmu)->base + (smmu)->pagesize)
@@ -87,6 +84,7 @@
#define ARM_SMMU_PTE_AP_UNPRIV (((pteval_t)1) << 6)
#define ARM_SMMU_PTE_AP_RDONLY (((pteval_t)2) << 6)
#define ARM_SMMU_PTE_ATTRINDX_SHIFT 2
+#define ARM_SMMU_PTE_nG (((pteval_t)1) << 11)
/* Stage-2 PTE */
#define ARM_SMMU_PTE_HAP_FAULT (((pteval_t)0) << 6)
@@ -223,6 +221,7 @@
#define ARM_SMMU_CB_FAR_LO 0x60
#define ARM_SMMU_CB_FAR_HI 0x64
#define ARM_SMMU_CB_FSYNR0 0x68
+#define ARM_SMMU_CB_S1_TLBIASID 0x610
#define SCTLR_S1_ASIDPNE (1 << 12)
#define SCTLR_CFCFG (1 << 7)
@@ -282,6 +281,8 @@
#define TTBCR2_ADDR_44 4
#define TTBCR2_ADDR_48 5
+#define TTBRn_HI_ASID_SHIFT 16
+
#define MAIR_ATTR_SHIFT(n) ((n) << 3)
#define MAIR_ATTR_MASK 0xff
#define MAIR_ATTR_DEVICE 0x04
@@ -305,7 +306,7 @@
#define FSR_IGN (FSR_AFF | FSR_ASF | FSR_TLBMCF | \
FSR_TLBLKF)
#define FSR_FAULT (FSR_MULTI | FSR_SS | FSR_UUT | \
- FSR_EF | FSR_PF | FSR_TF)
+ FSR_EF | FSR_PF | FSR_TF | FSR_IGN)
#define FSYNR0_WNR (1 << 4)
@@ -365,21 +366,21 @@
u32 num_context_irqs;
unsigned int *irqs;
- DECLARE_BITMAP(vmid_map, ARM_SMMU_NUM_VMIDS);
-
struct list_head list;
struct rb_root masters;
};
struct arm_smmu_cfg {
struct arm_smmu_device *smmu;
- u8 vmid;
u8 cbndx;
u8 irptndx;
u32 cbar;
pgd_t *pgd;
};
+#define ARM_SMMU_CB_ASID(cfg) ((cfg)->cbndx)
+#define ARM_SMMU_CB_VMID(cfg) ((cfg)->cbndx + 1)
+
struct arm_smmu_domain {
/*
* A domain can span across multiple, chained SMMUs and requires
@@ -533,6 +534,25 @@
}
}
+static void arm_smmu_tlb_inv_context(struct arm_smmu_cfg *cfg)
+{
+ struct arm_smmu_device *smmu = cfg->smmu;
+ void __iomem *base = ARM_SMMU_GR0(smmu);
+ bool stage1 = cfg->cbar != CBAR_TYPE_S2_TRANS;
+
+ if (stage1) {
+ base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
+ writel_relaxed(ARM_SMMU_CB_ASID(cfg),
+ base + ARM_SMMU_CB_S1_TLBIASID);
+ } else {
+ base = ARM_SMMU_GR0(smmu);
+ writel_relaxed(ARM_SMMU_CB_VMID(cfg),
+ base + ARM_SMMU_GR0_TLBIVMID);
+ }
+
+ arm_smmu_tlb_sync(smmu);
+}
+
static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
{
int flags, ret;
@@ -590,6 +610,9 @@
void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
gfsr = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSR);
+ if (!gfsr)
+ return IRQ_NONE;
+
gfsynr0 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSYNR0);
gfsynr1 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSYNR1);
gfsynr2 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSYNR2);
@@ -601,7 +624,7 @@
gfsr, gfsynr0, gfsynr1, gfsynr2);
writel(gfsr, gr0_base + ARM_SMMU_GR0_sGFSR);
- return IRQ_NONE;
+ return IRQ_HANDLED;
}
static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
@@ -618,14 +641,15 @@
cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, root_cfg->cbndx);
/* CBAR */
- reg = root_cfg->cbar |
- (root_cfg->vmid << CBAR_VMID_SHIFT);
+ reg = root_cfg->cbar;
if (smmu->version == 1)
reg |= root_cfg->irptndx << CBAR_IRPTNDX_SHIFT;
/* Use the weakest memory type, so it is overridden by the pte */
if (stage1)
reg |= (CBAR_S1_MEMATTR_WB << CBAR_S1_MEMATTR_SHIFT);
+ else
+ reg |= ARM_SMMU_CB_VMID(root_cfg) << CBAR_VMID_SHIFT;
writel_relaxed(reg, gr1_base + ARM_SMMU_GR1_CBAR(root_cfg->cbndx));
if (smmu->version > 1) {
@@ -687,15 +711,11 @@
/* TTBR0 */
reg = __pa(root_cfg->pgd);
-#ifndef __BIG_ENDIAN
writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_LO);
reg = (phys_addr_t)__pa(root_cfg->pgd) >> 32;
+ if (stage1)
+ reg |= ARM_SMMU_CB_ASID(root_cfg) << TTBRn_HI_ASID_SHIFT;
writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_HI);
-#else
- writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_HI);
- reg = (phys_addr_t)__pa(root_cfg->pgd) >> 32;
- writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_LO);
-#endif
/*
* TTBCR
@@ -750,10 +770,6 @@
writel_relaxed(reg, cb_base + ARM_SMMU_CB_S1_MAIR0);
}
- /* Nuke the TLB */
- writel_relaxed(root_cfg->vmid, gr0_base + ARM_SMMU_GR0_TLBIVMID);
- arm_smmu_tlb_sync(smmu);
-
/* SCTLR */
reg = SCTLR_CFCFG | SCTLR_CFIE | SCTLR_CFRE | SCTLR_M | SCTLR_EAE_SBOP;
if (stage1)
@@ -790,11 +806,6 @@
return -ENODEV;
}
- ret = __arm_smmu_alloc_bitmap(smmu->vmid_map, 0, ARM_SMMU_NUM_VMIDS);
- if (IS_ERR_VALUE(ret))
- return ret;
-
- root_cfg->vmid = ret;
if (smmu->features & ARM_SMMU_FEAT_TRANS_NESTED) {
/*
* We will likely want to change this if/when KVM gets
@@ -813,10 +824,9 @@
ret = __arm_smmu_alloc_bitmap(smmu->context_map, start,
smmu->num_context_banks);
if (IS_ERR_VALUE(ret))
- goto out_free_vmid;
+ return ret;
root_cfg->cbndx = ret;
-
if (smmu->version == 1) {
root_cfg->irptndx = atomic_inc_return(&smmu->irptndx);
root_cfg->irptndx %= smmu->num_context_irqs;
@@ -840,8 +850,6 @@
out_free_context:
__arm_smmu_free_bitmap(smmu->context_map, root_cfg->cbndx);
-out_free_vmid:
- __arm_smmu_free_bitmap(smmu->vmid_map, root_cfg->vmid);
return ret;
}
@@ -850,17 +858,22 @@
struct arm_smmu_domain *smmu_domain = domain->priv;
struct arm_smmu_cfg *root_cfg = &smmu_domain->root_cfg;
struct arm_smmu_device *smmu = root_cfg->smmu;
+ void __iomem *cb_base;
int irq;
if (!smmu)
return;
+ /* Disable the context bank and nuke the TLB before freeing it. */
+ cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, root_cfg->cbndx);
+ writel_relaxed(0, cb_base + ARM_SMMU_CB_SCTLR);
+ arm_smmu_tlb_inv_context(root_cfg);
+
if (root_cfg->irptndx != -1) {
irq = smmu->irqs[smmu->num_global_irqs + root_cfg->irptndx];
free_irq(irq, domain);
}
- __arm_smmu_free_bitmap(smmu->vmid_map, root_cfg->vmid);
__arm_smmu_free_bitmap(smmu->context_map, root_cfg->cbndx);
}
@@ -959,6 +972,11 @@
static void arm_smmu_domain_destroy(struct iommu_domain *domain)
{
struct arm_smmu_domain *smmu_domain = domain->priv;
+
+ /*
+ * Free the domain resources. We assume that all devices have
+ * already been detached.
+ */
arm_smmu_destroy_domain_context(domain);
arm_smmu_free_pgtables(smmu_domain);
kfree(smmu_domain);
@@ -1199,7 +1217,7 @@
}
if (stage == 1) {
- pteval |= ARM_SMMU_PTE_AP_UNPRIV;
+ pteval |= ARM_SMMU_PTE_AP_UNPRIV | ARM_SMMU_PTE_nG;
if (!(flags & IOMMU_WRITE) && (flags & IOMMU_READ))
pteval |= ARM_SMMU_PTE_AP_RDONLY;
@@ -1415,13 +1433,9 @@
{
int ret;
struct arm_smmu_domain *smmu_domain = domain->priv;
- struct arm_smmu_cfg *root_cfg = &smmu_domain->root_cfg;
- struct arm_smmu_device *smmu = root_cfg->smmu;
- void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
ret = arm_smmu_handle_mapping(smmu_domain, iova, 0, size, 0);
- writel_relaxed(root_cfg->vmid, gr0_base + ARM_SMMU_GR0_TLBIVMID);
- arm_smmu_tlb_sync(smmu);
+ arm_smmu_tlb_inv_context(&smmu_domain->root_cfg);
return ret ? ret : size;
}
@@ -1544,6 +1558,7 @@
static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
{
void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
+ void __iomem *sctlr_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB_SCTLR;
int i = 0;
u32 scr0 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sCR0);
@@ -1553,6 +1568,10 @@
writel_relaxed(S2CR_TYPE_BYPASS, gr0_base + ARM_SMMU_GR0_S2CR(i));
}
+ /* Make sure all context banks are disabled */
+ for (i = 0; i < smmu->num_context_banks; ++i)
+ writel_relaxed(0, sctlr_base + ARM_SMMU_CB(smmu, i));
+
/* Invalidate the TLB, just in case */
writel_relaxed(0, gr0_base + ARM_SMMU_GR0_STLBIALL);
writel_relaxed(0, gr0_base + ARM_SMMU_GR0_TLBIALLH);
@@ -1906,7 +1925,7 @@
of_node_put(master->of_node);
}
- if (!bitmap_empty(smmu->vmid_map, ARM_SMMU_NUM_VMIDS))
+ if (!bitmap_empty(smmu->context_map, ARM_SMMU_MAX_CBS))
dev_err(dev, "removing device with active domains!\n");
for (i = 0; i < smmu->num_global_irqs; ++i)
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index 3f32d64..0740189 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -247,50 +247,6 @@
__raw_writel(size - 1 + base, sfrbase + REG_PB0_EADDR + idx * 8);
}
-void exynos_sysmmu_set_prefbuf(struct device *dev,
- unsigned long base0, unsigned long size0,
- unsigned long base1, unsigned long size1)
-{
- struct sysmmu_drvdata *data = dev_get_drvdata(dev->archdata.iommu);
- unsigned long flags;
- int i;
-
- BUG_ON((base0 + size0) <= base0);
- BUG_ON((size1 > 0) && ((base1 + size1) <= base1));
-
- read_lock_irqsave(&data->lock, flags);
- if (!is_sysmmu_active(data))
- goto finish;
-
- for (i = 0; i < data->nsfrs; i++) {
- if ((readl(data->sfrbases[i] + REG_MMU_VERSION) >> 28) == 3) {
- if (!sysmmu_block(data->sfrbases[i]))
- continue;
-
- if (size1 == 0) {
- if (size0 <= SZ_128K) {
- base1 = base0;
- size1 = size0;
- } else {
- size1 = size0 -
- ALIGN(size0 / 2, SZ_64K);
- size0 = size0 - size1;
- base1 = base0 + size0;
- }
- }
-
- __sysmmu_set_prefbuf(
- data->sfrbases[i], base0, size0, 0);
- __sysmmu_set_prefbuf(
- data->sfrbases[i], base1, size1, 1);
-
- sysmmu_unblock(data->sfrbases[i]);
- }
- }
-finish:
- read_unlock_irqrestore(&data->lock, flags);
-}
-
static void __set_fault_handler(struct sysmmu_drvdata *data,
sysmmu_fault_handler_t handler)
{
diff --git a/drivers/iommu/fsl_pamu.c b/drivers/iommu/fsl_pamu.c
new file mode 100644
index 0000000..cba0498
--- /dev/null
+++ b/drivers/iommu/fsl_pamu.c
@@ -0,0 +1,1309 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ *
+ * Copyright (C) 2013 Freescale Semiconductor, Inc.
+ *
+ */
+
+#define pr_fmt(fmt) "fsl-pamu: %s: " fmt, __func__
+
+#include <linux/init.h>
+#include <linux/iommu.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <linux/interrupt.h>
+#include <linux/device.h>
+#include <linux/of_platform.h>
+#include <linux/bootmem.h>
+#include <linux/genalloc.h>
+#include <asm/io.h>
+#include <asm/bitops.h>
+#include <asm/fsl_guts.h>
+
+#include "fsl_pamu.h"
+
+/* define indexes for each operation mapping scenario */
+#define OMI_QMAN 0x00
+#define OMI_FMAN 0x01
+#define OMI_QMAN_PRIV 0x02
+#define OMI_CAAM 0x03
+
+#define make64(high, low) (((u64)(high) << 32) | (low))
+
+struct pamu_isr_data {
+ void __iomem *pamu_reg_base; /* Base address of PAMU regs*/
+ unsigned int count; /* The number of PAMUs */
+};
+
+static struct paace *ppaact;
+static struct paace *spaact;
+static struct ome *omt;
+
+/*
+ * Table for matching compatible strings, for device tree
+ * guts node, for QorIQ SOCs.
+ * "fsl,qoriq-device-config-2.0" corresponds to T4 & B4
+ * SOCs. For the older SOCs "fsl,qoriq-device-config-1.0"
+ * string would be used.
+*/
+static const struct of_device_id guts_device_ids[] = {
+ { .compatible = "fsl,qoriq-device-config-1.0", },
+ { .compatible = "fsl,qoriq-device-config-2.0", },
+ {}
+};
+
+
+/*
+ * Table for matching compatible strings, for device tree
+ * L3 cache controller node.
+ * "fsl,t4240-l3-cache-controller" corresponds to T4,
+ * "fsl,b4860-l3-cache-controller" corresponds to B4 &
+ * "fsl,p4080-l3-cache-controller" corresponds to other,
+ * SOCs.
+*/
+static const struct of_device_id l3_device_ids[] = {
+ { .compatible = "fsl,t4240-l3-cache-controller", },
+ { .compatible = "fsl,b4860-l3-cache-controller", },
+ { .compatible = "fsl,p4080-l3-cache-controller", },
+ {}
+};
+
+/* maximum subwindows permitted per liodn */
+static u32 max_subwindow_count;
+
+/* Pool for fspi allocation */
+struct gen_pool *spaace_pool;
+
+/**
+ * pamu_get_max_subwin_cnt() - Return the maximum supported
+ * subwindow count per liodn.
+ *
+ */
+u32 pamu_get_max_subwin_cnt()
+{
+ return max_subwindow_count;
+}
+
+/**
+ * pamu_get_ppaace() - Return the primary PACCE
+ * @liodn: liodn PAACT index for desired PAACE
+ *
+ * Returns the ppace pointer upon success else return
+ * null.
+ */
+static struct paace *pamu_get_ppaace(int liodn)
+{
+ if (!ppaact || liodn >= PAACE_NUMBER_ENTRIES) {
+ pr_debug("PPAACT doesn't exist\n");
+ return NULL;
+ }
+
+ return &ppaact[liodn];
+}
+
+/**
+ * pamu_enable_liodn() - Set valid bit of PACCE
+ * @liodn: liodn PAACT index for desired PAACE
+ *
+ * Returns 0 upon success else error code < 0 returned
+ */
+int pamu_enable_liodn(int liodn)
+{
+ struct paace *ppaace;
+
+ ppaace = pamu_get_ppaace(liodn);
+ if (!ppaace) {
+ pr_debug("Invalid primary paace entry\n");
+ return -ENOENT;
+ }
+
+ if (!get_bf(ppaace->addr_bitfields, PPAACE_AF_WSE)) {
+ pr_debug("liodn %d not configured\n", liodn);
+ return -EINVAL;
+ }
+
+ /* Ensure that all other stores to the ppaace complete first */
+ mb();
+
+ set_bf(ppaace->addr_bitfields, PAACE_AF_V, PAACE_V_VALID);
+ mb();
+
+ return 0;
+}
+
+/**
+ * pamu_disable_liodn() - Clears valid bit of PACCE
+ * @liodn: liodn PAACT index for desired PAACE
+ *
+ * Returns 0 upon success else error code < 0 returned
+ */
+int pamu_disable_liodn(int liodn)
+{
+ struct paace *ppaace;
+
+ ppaace = pamu_get_ppaace(liodn);
+ if (!ppaace) {
+ pr_debug("Invalid primary paace entry\n");
+ return -ENOENT;
+ }
+
+ set_bf(ppaace->addr_bitfields, PAACE_AF_V, PAACE_V_INVALID);
+ mb();
+
+ return 0;
+}
+
+/* Derive the window size encoding for a particular PAACE entry */
+static unsigned int map_addrspace_size_to_wse(phys_addr_t addrspace_size)
+{
+ /* Bug if not a power of 2 */
+ BUG_ON(!is_power_of_2(addrspace_size));
+
+ /* window size is 2^(WSE+1) bytes */
+ return __ffs(addrspace_size) - 1;
+}
+
+/* Derive the PAACE window count encoding for the subwindow count */
+static unsigned int map_subwindow_cnt_to_wce(u32 subwindow_cnt)
+{
+ /* window count is 2^(WCE+1) bytes */
+ return __ffs(subwindow_cnt) - 1;
+}
+
+/*
+ * Set the PAACE type as primary and set the coherency required domain
+ * attribute
+ */
+static void pamu_init_ppaace(struct paace *ppaace)
+{
+ set_bf(ppaace->addr_bitfields, PAACE_AF_PT, PAACE_PT_PRIMARY);
+
+ set_bf(ppaace->domain_attr.to_host.coherency_required, PAACE_DA_HOST_CR,
+ PAACE_M_COHERENCE_REQ);
+}
+
+/*
+ * Set the PAACE type as secondary and set the coherency required domain
+ * attribute.
+ */
+static void pamu_init_spaace(struct paace *spaace)
+{
+ set_bf(spaace->addr_bitfields, PAACE_AF_PT, PAACE_PT_SECONDARY);
+ set_bf(spaace->domain_attr.to_host.coherency_required, PAACE_DA_HOST_CR,
+ PAACE_M_COHERENCE_REQ);
+}
+
+/*
+ * Return the spaace (corresponding to the secondary window index)
+ * for a particular ppaace.
+ */
+static struct paace *pamu_get_spaace(struct paace *paace, u32 wnum)
+{
+ u32 subwin_cnt;
+ struct paace *spaace = NULL;
+
+ subwin_cnt = 1UL << (get_bf(paace->impl_attr, PAACE_IA_WCE) + 1);
+
+ if (wnum < subwin_cnt)
+ spaace = &spaact[paace->fspi + wnum];
+ else
+ pr_debug("secondary paace out of bounds\n");
+
+ return spaace;
+}
+
+/**
+ * pamu_get_fspi_and_allocate() - Allocates fspi index and reserves subwindows
+ * required for primary PAACE in the secondary
+ * PAACE table.
+ * @subwin_cnt: Number of subwindows to be reserved.
+ *
+ * A PPAACE entry may have a number of associated subwindows. A subwindow
+ * corresponds to a SPAACE entry in the SPAACT table. Each PAACE entry stores
+ * the index (fspi) of the first SPAACE entry in the SPAACT table. This
+ * function returns the index of the first SPAACE entry. The remaining
+ * SPAACE entries are reserved contiguously from that index.
+ *
+ * Returns a valid fspi index in the range of 0 - SPAACE_NUMBER_ENTRIES on success.
+ * If no SPAACE entry is available or the allocator can not reserve the required
+ * number of contiguous entries function returns ULONG_MAX indicating a failure.
+ *
+*/
+static unsigned long pamu_get_fspi_and_allocate(u32 subwin_cnt)
+{
+ unsigned long spaace_addr;
+
+ spaace_addr = gen_pool_alloc(spaace_pool, subwin_cnt * sizeof(struct paace));
+ if (!spaace_addr)
+ return ULONG_MAX;
+
+ return (spaace_addr - (unsigned long)spaact) / (sizeof(struct paace));
+}
+
+/* Release the subwindows reserved for a particular LIODN */
+void pamu_free_subwins(int liodn)
+{
+ struct paace *ppaace;
+ u32 subwin_cnt, size;
+
+ ppaace = pamu_get_ppaace(liodn);
+ if (!ppaace) {
+ pr_debug("Invalid liodn entry\n");
+ return;
+ }
+
+ if (get_bf(ppaace->addr_bitfields, PPAACE_AF_MW)) {
+ subwin_cnt = 1UL << (get_bf(ppaace->impl_attr, PAACE_IA_WCE) + 1);
+ size = (subwin_cnt - 1) * sizeof(struct paace);
+ gen_pool_free(spaace_pool, (unsigned long)&spaact[ppaace->fspi], size);
+ set_bf(ppaace->addr_bitfields, PPAACE_AF_MW, 0);
+ }
+}
+
+/*
+ * Function used for updating stash destination for the coressponding
+ * LIODN.
+ */
+int pamu_update_paace_stash(int liodn, u32 subwin, u32 value)
+{
+ struct paace *paace;
+
+ paace = pamu_get_ppaace(liodn);
+ if (!paace) {
+ pr_debug("Invalid liodn entry\n");
+ return -ENOENT;
+ }
+ if (subwin) {
+ paace = pamu_get_spaace(paace, subwin - 1);
+ if (!paace) {
+ return -ENOENT;
+ }
+ }
+ set_bf(paace->impl_attr, PAACE_IA_CID, value);
+
+ mb();
+
+ return 0;
+}
+
+/* Disable a subwindow corresponding to the LIODN */
+int pamu_disable_spaace(int liodn, u32 subwin)
+{
+ struct paace *paace;
+
+ paace = pamu_get_ppaace(liodn);
+ if (!paace) {
+ pr_debug("Invalid liodn entry\n");
+ return -ENOENT;
+ }
+ if (subwin) {
+ paace = pamu_get_spaace(paace, subwin - 1);
+ if (!paace) {
+ return -ENOENT;
+ }
+ set_bf(paace->addr_bitfields, PAACE_AF_V,
+ PAACE_V_INVALID);
+ } else {
+ set_bf(paace->addr_bitfields, PAACE_AF_AP,
+ PAACE_AP_PERMS_DENIED);
+ }
+
+ mb();
+
+ return 0;
+}
+
+
+/**
+ * pamu_config_paace() - Sets up PPAACE entry for specified liodn
+ *
+ * @liodn: Logical IO device number
+ * @win_addr: starting address of DSA window
+ * @win-size: size of DSA window
+ * @omi: Operation mapping index -- if ~omi == 0 then omi not defined
+ * @rpn: real (true physical) page number
+ * @stashid: cache stash id for associated cpu -- if ~stashid == 0 then
+ * stashid not defined
+ * @snoopid: snoop id for hardware coherency -- if ~snoopid == 0 then
+ * snoopid not defined
+ * @subwin_cnt: number of sub-windows
+ * @prot: window permissions
+ *
+ * Returns 0 upon success else error code < 0 returned
+ */
+int pamu_config_ppaace(int liodn, phys_addr_t win_addr, phys_addr_t win_size,
+ u32 omi, unsigned long rpn, u32 snoopid, u32 stashid,
+ u32 subwin_cnt, int prot)
+{
+ struct paace *ppaace;
+ unsigned long fspi;
+
+ if (!is_power_of_2(win_size) || win_size < PAMU_PAGE_SIZE) {
+ pr_debug("window size too small or not a power of two %llx\n", win_size);
+ return -EINVAL;
+ }
+
+ if (win_addr & (win_size - 1)) {
+ pr_debug("window address is not aligned with window size\n");
+ return -EINVAL;
+ }
+
+ ppaace = pamu_get_ppaace(liodn);
+ if (!ppaace) {
+ return -ENOENT;
+ }
+
+ /* window size is 2^(WSE+1) bytes */
+ set_bf(ppaace->addr_bitfields, PPAACE_AF_WSE,
+ map_addrspace_size_to_wse(win_size));
+
+ pamu_init_ppaace(ppaace);
+
+ ppaace->wbah = win_addr >> (PAMU_PAGE_SHIFT + 20);
+ set_bf(ppaace->addr_bitfields, PPAACE_AF_WBAL,
+ (win_addr >> PAMU_PAGE_SHIFT));
+
+ /* set up operation mapping if it's configured */
+ if (omi < OME_NUMBER_ENTRIES) {
+ set_bf(ppaace->impl_attr, PAACE_IA_OTM, PAACE_OTM_INDEXED);
+ ppaace->op_encode.index_ot.omi = omi;
+ } else if (~omi != 0) {
+ pr_debug("bad operation mapping index: %d\n", omi);
+ return -EINVAL;
+ }
+
+ /* configure stash id */
+ if (~stashid != 0)
+ set_bf(ppaace->impl_attr, PAACE_IA_CID, stashid);
+
+ /* configure snoop id */
+ if (~snoopid != 0)
+ ppaace->domain_attr.to_host.snpid = snoopid;
+
+ if (subwin_cnt) {
+ /* The first entry is in the primary PAACE instead */
+ fspi = pamu_get_fspi_and_allocate(subwin_cnt - 1);
+ if (fspi == ULONG_MAX) {
+ pr_debug("spaace indexes exhausted\n");
+ return -EINVAL;
+ }
+
+ /* window count is 2^(WCE+1) bytes */
+ set_bf(ppaace->impl_attr, PAACE_IA_WCE,
+ map_subwindow_cnt_to_wce(subwin_cnt));
+ set_bf(ppaace->addr_bitfields, PPAACE_AF_MW, 0x1);
+ ppaace->fspi = fspi;
+ } else {
+ set_bf(ppaace->impl_attr, PAACE_IA_ATM, PAACE_ATM_WINDOW_XLATE);
+ ppaace->twbah = rpn >> 20;
+ set_bf(ppaace->win_bitfields, PAACE_WIN_TWBAL, rpn);
+ set_bf(ppaace->addr_bitfields, PAACE_AF_AP, prot);
+ set_bf(ppaace->impl_attr, PAACE_IA_WCE, 0);
+ set_bf(ppaace->addr_bitfields, PPAACE_AF_MW, 0);
+ }
+ mb();
+
+ return 0;
+}
+
+/**
+ * pamu_config_spaace() - Sets up SPAACE entry for specified subwindow
+ *
+ * @liodn: Logical IO device number
+ * @subwin_cnt: number of sub-windows associated with dma-window
+ * @subwin: subwindow index
+ * @subwin_size: size of subwindow
+ * @omi: Operation mapping index
+ * @rpn: real (true physical) page number
+ * @snoopid: snoop id for hardware coherency -- if ~snoopid == 0 then
+ * snoopid not defined
+ * @stashid: cache stash id for associated cpu
+ * @enable: enable/disable subwindow after reconfiguration
+ * @prot: sub window permissions
+ *
+ * Returns 0 upon success else error code < 0 returned
+ */
+int pamu_config_spaace(int liodn, u32 subwin_cnt, u32 subwin,
+ phys_addr_t subwin_size, u32 omi, unsigned long rpn,
+ u32 snoopid, u32 stashid, int enable, int prot)
+{
+ struct paace *paace;
+
+
+ /* setup sub-windows */
+ if (!subwin_cnt) {
+ pr_debug("Invalid subwindow count\n");
+ return -EINVAL;
+ }
+
+ paace = pamu_get_ppaace(liodn);
+ if (subwin > 0 && subwin < subwin_cnt && paace) {
+ paace = pamu_get_spaace(paace, subwin - 1);
+
+ if (paace && !(paace->addr_bitfields & PAACE_V_VALID)) {
+ pamu_init_spaace(paace);
+ set_bf(paace->addr_bitfields, SPAACE_AF_LIODN, liodn);
+ }
+ }
+
+ if (!paace) {
+ pr_debug("Invalid liodn entry\n");
+ return -ENOENT;
+ }
+
+ if (!is_power_of_2(subwin_size) || subwin_size < PAMU_PAGE_SIZE) {
+ pr_debug("subwindow size out of range, or not a power of 2\n");
+ return -EINVAL;
+ }
+
+ if (rpn == ULONG_MAX) {
+ pr_debug("real page number out of range\n");
+ return -EINVAL;
+ }
+
+ /* window size is 2^(WSE+1) bytes */
+ set_bf(paace->win_bitfields, PAACE_WIN_SWSE,
+ map_addrspace_size_to_wse(subwin_size));
+
+ set_bf(paace->impl_attr, PAACE_IA_ATM, PAACE_ATM_WINDOW_XLATE);
+ paace->twbah = rpn >> 20;
+ set_bf(paace->win_bitfields, PAACE_WIN_TWBAL, rpn);
+ set_bf(paace->addr_bitfields, PAACE_AF_AP, prot);
+
+ /* configure snoop id */
+ if (~snoopid != 0)
+ paace->domain_attr.to_host.snpid = snoopid;
+
+ /* set up operation mapping if it's configured */
+ if (omi < OME_NUMBER_ENTRIES) {
+ set_bf(paace->impl_attr, PAACE_IA_OTM, PAACE_OTM_INDEXED);
+ paace->op_encode.index_ot.omi = omi;
+ } else if (~omi != 0) {
+ pr_debug("bad operation mapping index: %d\n", omi);
+ return -EINVAL;
+ }
+
+ if (~stashid != 0)
+ set_bf(paace->impl_attr, PAACE_IA_CID, stashid);
+
+ smp_wmb();
+
+ if (enable)
+ set_bf(paace->addr_bitfields, PAACE_AF_V, PAACE_V_VALID);
+
+ mb();
+
+ return 0;
+}
+
+/**
+* get_ome_index() - Returns the index in the operation mapping table
+* for device.
+* @*omi_index: pointer for storing the index value
+*
+*/
+void get_ome_index(u32 *omi_index, struct device *dev)
+{
+ if (of_device_is_compatible(dev->of_node, "fsl,qman-portal"))
+ *omi_index = OMI_QMAN;
+ if (of_device_is_compatible(dev->of_node, "fsl,qman"))
+ *omi_index = OMI_QMAN_PRIV;
+}
+
+/**
+ * get_stash_id - Returns stash destination id corresponding to a
+ * cache type and vcpu.
+ * @stash_dest_hint: L1, L2 or L3
+ * @vcpu: vpcu target for a particular cache type.
+ *
+ * Returs stash on success or ~(u32)0 on failure.
+ *
+ */
+u32 get_stash_id(u32 stash_dest_hint, u32 vcpu)
+{
+ const u32 *prop;
+ struct device_node *node;
+ u32 cache_level;
+ int len, found = 0;
+ int i;
+
+ /* Fastpath, exit early if L3/CPC cache is target for stashing */
+ if (stash_dest_hint == PAMU_ATTR_CACHE_L3) {
+ node = of_find_matching_node(NULL, l3_device_ids);
+ if (node) {
+ prop = of_get_property(node, "cache-stash-id", 0);
+ if (!prop) {
+ pr_debug("missing cache-stash-id at %s\n", node->full_name);
+ of_node_put(node);
+ return ~(u32)0;
+ }
+ of_node_put(node);
+ return be32_to_cpup(prop);
+ }
+ return ~(u32)0;
+ }
+
+ for_each_node_by_type(node, "cpu") {
+ prop = of_get_property(node, "reg", &len);
+ for (i = 0; i < len / sizeof(u32); i++) {
+ if (be32_to_cpup(&prop[i]) == vcpu) {
+ found = 1;
+ goto found_cpu_node;
+ }
+ }
+ }
+found_cpu_node:
+
+ /* find the hwnode that represents the cache */
+ for (cache_level = PAMU_ATTR_CACHE_L1; (cache_level < PAMU_ATTR_CACHE_L3) && found; cache_level++) {
+ if (stash_dest_hint == cache_level) {
+ prop = of_get_property(node, "cache-stash-id", 0);
+ if (!prop) {
+ pr_debug("missing cache-stash-id at %s\n", node->full_name);
+ of_node_put(node);
+ return ~(u32)0;
+ }
+ of_node_put(node);
+ return be32_to_cpup(prop);
+ }
+
+ prop = of_get_property(node, "next-level-cache", 0);
+ if (!prop) {
+ pr_debug("can't find next-level-cache at %s\n",
+ node->full_name);
+ of_node_put(node);
+ return ~(u32)0; /* can't traverse any further */
+ }
+ of_node_put(node);
+
+ /* advance to next node in cache hierarchy */
+ node = of_find_node_by_phandle(*prop);
+ if (!node) {
+ pr_debug("Invalid node for cache hierarchy %s\n",
+ node->full_name);
+ return ~(u32)0;
+ }
+ }
+
+ pr_debug("stash dest not found for %d on vcpu %d\n",
+ stash_dest_hint, vcpu);
+ return ~(u32)0;
+}
+
+/* Identify if the PAACT table entry belongs to QMAN, BMAN or QMAN Portal */
+#define QMAN_PAACE 1
+#define QMAN_PORTAL_PAACE 2
+#define BMAN_PAACE 3
+
+/**
+ * Setup operation mapping and stash destinations for QMAN and QMAN portal.
+ * Memory accesses to QMAN and BMAN private memory need not be coherent, so
+ * clear the PAACE entry coherency attribute for them.
+ */
+static void setup_qbman_paace(struct paace *ppaace, int paace_type)
+{
+ switch (paace_type) {
+ case QMAN_PAACE:
+ set_bf(ppaace->impl_attr, PAACE_IA_OTM, PAACE_OTM_INDEXED);
+ ppaace->op_encode.index_ot.omi = OMI_QMAN_PRIV;
+ /* setup QMAN Private data stashing for the L3 cache */
+ set_bf(ppaace->impl_attr, PAACE_IA_CID, get_stash_id(PAMU_ATTR_CACHE_L3, 0));
+ set_bf(ppaace->domain_attr.to_host.coherency_required, PAACE_DA_HOST_CR,
+ 0);
+ break;
+ case QMAN_PORTAL_PAACE:
+ set_bf(ppaace->impl_attr, PAACE_IA_OTM, PAACE_OTM_INDEXED);
+ ppaace->op_encode.index_ot.omi = OMI_QMAN;
+ /*Set DQRR and Frame stashing for the L3 cache */
+ set_bf(ppaace->impl_attr, PAACE_IA_CID, get_stash_id(PAMU_ATTR_CACHE_L3, 0));
+ break;
+ case BMAN_PAACE:
+ set_bf(ppaace->domain_attr.to_host.coherency_required, PAACE_DA_HOST_CR,
+ 0);
+ break;
+ }
+}
+
+/**
+ * Setup the operation mapping table for various devices. This is a static
+ * table where each table index corresponds to a particular device. PAMU uses
+ * this table to translate device transaction to appropriate corenet
+ * transaction.
+ */
+static void __init setup_omt(struct ome *omt)
+{
+ struct ome *ome;
+
+ /* Configure OMI_QMAN */
+ ome = &omt[OMI_QMAN];
+
+ ome->moe[IOE_READ_IDX] = EOE_VALID | EOE_READ;
+ ome->moe[IOE_EREAD0_IDX] = EOE_VALID | EOE_RSA;
+ ome->moe[IOE_WRITE_IDX] = EOE_VALID | EOE_WRITE;
+ ome->moe[IOE_EWRITE0_IDX] = EOE_VALID | EOE_WWSAO;
+
+ ome->moe[IOE_DIRECT0_IDX] = EOE_VALID | EOE_LDEC;
+ ome->moe[IOE_DIRECT1_IDX] = EOE_VALID | EOE_LDECPE;
+
+ /* Configure OMI_FMAN */
+ ome = &omt[OMI_FMAN];
+ ome->moe[IOE_READ_IDX] = EOE_VALID | EOE_READI;
+ ome->moe[IOE_WRITE_IDX] = EOE_VALID | EOE_WRITE;
+
+ /* Configure OMI_QMAN private */
+ ome = &omt[OMI_QMAN_PRIV];
+ ome->moe[IOE_READ_IDX] = EOE_VALID | EOE_READ;
+ ome->moe[IOE_WRITE_IDX] = EOE_VALID | EOE_WRITE;
+ ome->moe[IOE_EREAD0_IDX] = EOE_VALID | EOE_RSA;
+ ome->moe[IOE_EWRITE0_IDX] = EOE_VALID | EOE_WWSA;
+
+ /* Configure OMI_CAAM */
+ ome = &omt[OMI_CAAM];
+ ome->moe[IOE_READ_IDX] = EOE_VALID | EOE_READI;
+ ome->moe[IOE_WRITE_IDX] = EOE_VALID | EOE_WRITE;
+}
+
+/*
+ * Get the maximum number of PAACT table entries
+ * and subwindows supported by PAMU
+ */
+static void get_pamu_cap_values(unsigned long pamu_reg_base)
+{
+ u32 pc_val;
+
+ pc_val = in_be32((u32 *)(pamu_reg_base + PAMU_PC3));
+ /* Maximum number of subwindows per liodn */
+ max_subwindow_count = 1 << (1 + PAMU_PC3_MWCE(pc_val));
+}
+
+/* Setup PAMU registers pointing to PAACT, SPAACT and OMT */
+int setup_one_pamu(unsigned long pamu_reg_base, unsigned long pamu_reg_size,
+ phys_addr_t ppaact_phys, phys_addr_t spaact_phys,
+ phys_addr_t omt_phys)
+{
+ u32 *pc;
+ struct pamu_mmap_regs *pamu_regs;
+
+ pc = (u32 *) (pamu_reg_base + PAMU_PC);
+ pamu_regs = (struct pamu_mmap_regs *)
+ (pamu_reg_base + PAMU_MMAP_REGS_BASE);
+
+ /* set up pointers to corenet control blocks */
+
+ out_be32(&pamu_regs->ppbah, upper_32_bits(ppaact_phys));
+ out_be32(&pamu_regs->ppbal, lower_32_bits(ppaact_phys));
+ ppaact_phys = ppaact_phys + PAACT_SIZE;
+ out_be32(&pamu_regs->pplah, upper_32_bits(ppaact_phys));
+ out_be32(&pamu_regs->pplal, lower_32_bits(ppaact_phys));
+
+ out_be32(&pamu_regs->spbah, upper_32_bits(spaact_phys));
+ out_be32(&pamu_regs->spbal, lower_32_bits(spaact_phys));
+ spaact_phys = spaact_phys + SPAACT_SIZE;
+ out_be32(&pamu_regs->splah, upper_32_bits(spaact_phys));
+ out_be32(&pamu_regs->splal, lower_32_bits(spaact_phys));
+
+ out_be32(&pamu_regs->obah, upper_32_bits(omt_phys));
+ out_be32(&pamu_regs->obal, lower_32_bits(omt_phys));
+ omt_phys = omt_phys + OMT_SIZE;
+ out_be32(&pamu_regs->olah, upper_32_bits(omt_phys));
+ out_be32(&pamu_regs->olal, lower_32_bits(omt_phys));
+
+ /*
+ * set PAMU enable bit,
+ * allow ppaact & omt to be cached
+ * & enable PAMU access violation interrupts.
+ */
+
+ out_be32((u32 *)(pamu_reg_base + PAMU_PICS),
+ PAMU_ACCESS_VIOLATION_ENABLE);
+ out_be32(pc, PAMU_PC_PE | PAMU_PC_OCE | PAMU_PC_SPCC | PAMU_PC_PPCC);
+ return 0;
+}
+
+/* Enable all device LIODNS */
+static void __init setup_liodns(void)
+{
+ int i, len;
+ struct paace *ppaace;
+ struct device_node *node = NULL;
+ const u32 *prop;
+
+ for_each_node_with_property(node, "fsl,liodn") {
+ prop = of_get_property(node, "fsl,liodn", &len);
+ for (i = 0; i < len / sizeof(u32); i++) {
+ int liodn;
+
+ liodn = be32_to_cpup(&prop[i]);
+ if (liodn >= PAACE_NUMBER_ENTRIES) {
+ pr_debug("Invalid LIODN value %d\n", liodn);
+ continue;
+ }
+ ppaace = pamu_get_ppaace(liodn);
+ pamu_init_ppaace(ppaace);
+ /* window size is 2^(WSE+1) bytes */
+ set_bf(ppaace->addr_bitfields, PPAACE_AF_WSE, 35);
+ ppaace->wbah = 0;
+ set_bf(ppaace->addr_bitfields, PPAACE_AF_WBAL, 0);
+ set_bf(ppaace->impl_attr, PAACE_IA_ATM,
+ PAACE_ATM_NO_XLATE);
+ set_bf(ppaace->addr_bitfields, PAACE_AF_AP,
+ PAACE_AP_PERMS_ALL);
+ if (of_device_is_compatible(node, "fsl,qman-portal"))
+ setup_qbman_paace(ppaace, QMAN_PORTAL_PAACE);
+ if (of_device_is_compatible(node, "fsl,qman"))
+ setup_qbman_paace(ppaace, QMAN_PAACE);
+ if (of_device_is_compatible(node, "fsl,bman"))
+ setup_qbman_paace(ppaace, BMAN_PAACE);
+ mb();
+ pamu_enable_liodn(liodn);
+ }
+ }
+}
+
+irqreturn_t pamu_av_isr(int irq, void *arg)
+{
+ struct pamu_isr_data *data = arg;
+ phys_addr_t phys;
+ unsigned int i, j, ret;
+
+ pr_emerg("access violation interrupt\n");
+
+ for (i = 0; i < data->count; i++) {
+ void __iomem *p = data->pamu_reg_base + i * PAMU_OFFSET;
+ u32 pics = in_be32(p + PAMU_PICS);
+
+ if (pics & PAMU_ACCESS_VIOLATION_STAT) {
+ u32 avs1 = in_be32(p + PAMU_AVS1);
+ struct paace *paace;
+
+ pr_emerg("POES1=%08x\n", in_be32(p + PAMU_POES1));
+ pr_emerg("POES2=%08x\n", in_be32(p + PAMU_POES2));
+ pr_emerg("AVS1=%08x\n", avs1);
+ pr_emerg("AVS2=%08x\n", in_be32(p + PAMU_AVS2));
+ pr_emerg("AVA=%016llx\n", make64(in_be32(p + PAMU_AVAH),
+ in_be32(p + PAMU_AVAL)));
+ pr_emerg("UDAD=%08x\n", in_be32(p + PAMU_UDAD));
+ pr_emerg("POEA=%016llx\n", make64(in_be32(p + PAMU_POEAH),
+ in_be32(p + PAMU_POEAL)));
+
+ phys = make64(in_be32(p + PAMU_POEAH),
+ in_be32(p + PAMU_POEAL));
+
+ /* Assume that POEA points to a PAACE */
+ if (phys) {
+ u32 *paace = phys_to_virt(phys);
+
+ /* Only the first four words are relevant */
+ for (j = 0; j < 4; j++)
+ pr_emerg("PAACE[%u]=%08x\n", j, in_be32(paace + j));
+ }
+
+ /* clear access violation condition */
+ out_be32((p + PAMU_AVS1), avs1 & PAMU_AV_MASK);
+ paace = pamu_get_ppaace(avs1 >> PAMU_AVS1_LIODN_SHIFT);
+ BUG_ON(!paace);
+ /* check if we got a violation for a disabled LIODN */
+ if (!get_bf(paace->addr_bitfields, PAACE_AF_V)) {
+ /*
+ * As per hardware erratum A-003638, access
+ * violation can be reported for a disabled
+ * LIODN. If we hit that condition, disable
+ * access violation reporting.
+ */
+ pics &= ~PAMU_ACCESS_VIOLATION_ENABLE;
+ } else {
+ /* Disable the LIODN */
+ ret = pamu_disable_liodn(avs1 >> PAMU_AVS1_LIODN_SHIFT);
+ BUG_ON(ret);
+ pr_emerg("Disabling liodn %x\n", avs1 >> PAMU_AVS1_LIODN_SHIFT);
+ }
+ out_be32((p + PAMU_PICS), pics);
+ }
+ }
+
+
+ return IRQ_HANDLED;
+}
+
+#define LAWAR_EN 0x80000000
+#define LAWAR_TARGET_MASK 0x0FF00000
+#define LAWAR_TARGET_SHIFT 20
+#define LAWAR_SIZE_MASK 0x0000003F
+#define LAWAR_CSDID_MASK 0x000FF000
+#define LAWAR_CSDID_SHIFT 12
+
+#define LAW_SIZE_4K 0xb
+
+struct ccsr_law {
+ u32 lawbarh; /* LAWn base address high */
+ u32 lawbarl; /* LAWn base address low */
+ u32 lawar; /* LAWn attributes */
+ u32 reserved;
+};
+
+/*
+ * Create a coherence subdomain for a given memory block.
+ */
+static int __init create_csd(phys_addr_t phys, size_t size, u32 csd_port_id)
+{
+ struct device_node *np;
+ const __be32 *iprop;
+ void __iomem *lac = NULL; /* Local Access Control registers */
+ struct ccsr_law __iomem *law;
+ void __iomem *ccm = NULL;
+ u32 __iomem *csdids;
+ unsigned int i, num_laws, num_csds;
+ u32 law_target = 0;
+ u32 csd_id = 0;
+ int ret = 0;
+
+ np = of_find_compatible_node(NULL, NULL, "fsl,corenet-law");
+ if (!np)
+ return -ENODEV;
+
+ iprop = of_get_property(np, "fsl,num-laws", NULL);
+ if (!iprop) {
+ ret = -ENODEV;
+ goto error;
+ }
+
+ num_laws = be32_to_cpup(iprop);
+ if (!num_laws) {
+ ret = -ENODEV;
+ goto error;
+ }
+
+ lac = of_iomap(np, 0);
+ if (!lac) {
+ ret = -ENODEV;
+ goto error;
+ }
+
+ /* LAW registers are at offset 0xC00 */
+ law = lac + 0xC00;
+
+ of_node_put(np);
+
+ np = of_find_compatible_node(NULL, NULL, "fsl,corenet-cf");
+ if (!np) {
+ ret = -ENODEV;
+ goto error;
+ }
+
+ iprop = of_get_property(np, "fsl,ccf-num-csdids", NULL);
+ if (!iprop) {
+ ret = -ENODEV;
+ goto error;
+ }
+
+ num_csds = be32_to_cpup(iprop);
+ if (!num_csds) {
+ ret = -ENODEV;
+ goto error;
+ }
+
+ ccm = of_iomap(np, 0);
+ if (!ccm) {
+ ret = -ENOMEM;
+ goto error;
+ }
+
+ /* The undocumented CSDID registers are at offset 0x600 */
+ csdids = ccm + 0x600;
+
+ of_node_put(np);
+ np = NULL;
+
+ /* Find an unused coherence subdomain ID */
+ for (csd_id = 0; csd_id < num_csds; csd_id++) {
+ if (!csdids[csd_id])
+ break;
+ }
+
+ /* Store the Port ID in the (undocumented) proper CIDMRxx register */
+ csdids[csd_id] = csd_port_id;
+
+ /* Find the DDR LAW that maps to our buffer. */
+ for (i = 0; i < num_laws; i++) {
+ if (law[i].lawar & LAWAR_EN) {
+ phys_addr_t law_start, law_end;
+
+ law_start = make64(law[i].lawbarh, law[i].lawbarl);
+ law_end = law_start +
+ (2ULL << (law[i].lawar & LAWAR_SIZE_MASK));
+
+ if (law_start <= phys && phys < law_end) {
+ law_target = law[i].lawar & LAWAR_TARGET_MASK;
+ break;
+ }
+ }
+ }
+
+ if (i == 0 || i == num_laws) {
+ /* This should never happen*/
+ ret = -ENOENT;
+ goto error;
+ }
+
+ /* Find a free LAW entry */
+ while (law[--i].lawar & LAWAR_EN) {
+ if (i == 0) {
+ /* No higher priority LAW slots available */
+ ret = -ENOENT;
+ goto error;
+ }
+ }
+
+ law[i].lawbarh = upper_32_bits(phys);
+ law[i].lawbarl = lower_32_bits(phys);
+ wmb();
+ law[i].lawar = LAWAR_EN | law_target | (csd_id << LAWAR_CSDID_SHIFT) |
+ (LAW_SIZE_4K + get_order(size));
+ wmb();
+
+error:
+ if (ccm)
+ iounmap(ccm);
+
+ if (lac)
+ iounmap(lac);
+
+ if (np)
+ of_node_put(np);
+
+ return ret;
+}
+
+/*
+ * Table of SVRs and the corresponding PORT_ID values. Port ID corresponds to a
+ * bit map of snoopers for a given range of memory mapped by a LAW.
+ *
+ * All future CoreNet-enabled SOCs will have this erratum(A-004510) fixed, so this
+ * table should never need to be updated. SVRs are guaranteed to be unique, so
+ * there is no worry that a future SOC will inadvertently have one of these
+ * values.
+ */
+static const struct {
+ u32 svr;
+ u32 port_id;
+} port_id_map[] = {
+ {0x82100010, 0xFF000000}, /* P2040 1.0 */
+ {0x82100011, 0xFF000000}, /* P2040 1.1 */
+ {0x82100110, 0xFF000000}, /* P2041 1.0 */
+ {0x82100111, 0xFF000000}, /* P2041 1.1 */
+ {0x82110310, 0xFF000000}, /* P3041 1.0 */
+ {0x82110311, 0xFF000000}, /* P3041 1.1 */
+ {0x82010020, 0xFFF80000}, /* P4040 2.0 */
+ {0x82000020, 0xFFF80000}, /* P4080 2.0 */
+ {0x82210010, 0xFC000000}, /* P5010 1.0 */
+ {0x82210020, 0xFC000000}, /* P5010 2.0 */
+ {0x82200010, 0xFC000000}, /* P5020 1.0 */
+ {0x82050010, 0xFF800000}, /* P5021 1.0 */
+ {0x82040010, 0xFF800000}, /* P5040 1.0 */
+};
+
+#define SVR_SECURITY 0x80000 /* The Security (E) bit */
+
+static int __init fsl_pamu_probe(struct platform_device *pdev)
+{
+ void __iomem *pamu_regs = NULL;
+ struct ccsr_guts __iomem *guts_regs = NULL;
+ u32 pamubypenr, pamu_counter;
+ unsigned long pamu_reg_off;
+ unsigned long pamu_reg_base;
+ struct pamu_isr_data *data = NULL;
+ struct device_node *guts_node;
+ u64 size;
+ struct page *p;
+ int ret = 0;
+ int irq;
+ phys_addr_t ppaact_phys;
+ phys_addr_t spaact_phys;
+ phys_addr_t omt_phys;
+ size_t mem_size = 0;
+ unsigned int order = 0;
+ u32 csd_port_id = 0;
+ unsigned i;
+ /*
+ * enumerate all PAMUs and allocate and setup PAMU tables
+ * for each of them,
+ * NOTE : All PAMUs share the same LIODN tables.
+ */
+
+ pamu_regs = of_iomap(pdev->dev.of_node, 0);
+ if (!pamu_regs) {
+ dev_err(&pdev->dev, "ioremap of PAMU node failed\n");
+ return -ENOMEM;
+ }
+ of_get_address(pdev->dev.of_node, 0, &size, NULL);
+
+ irq = irq_of_parse_and_map(pdev->dev.of_node, 0);
+ if (irq == NO_IRQ) {
+ dev_warn(&pdev->dev, "no interrupts listed in PAMU node\n");
+ goto error;
+ }
+
+ data = kzalloc(sizeof(struct pamu_isr_data), GFP_KERNEL);
+ if (!data) {
+ dev_err(&pdev->dev, "PAMU isr data memory allocation failed\n");
+ ret = -ENOMEM;
+ goto error;
+ }
+ data->pamu_reg_base = pamu_regs;
+ data->count = size / PAMU_OFFSET;
+
+ /* The ISR needs access to the regs, so we won't iounmap them */
+ ret = request_irq(irq, pamu_av_isr, 0, "pamu", data);
+ if (ret < 0) {
+ dev_err(&pdev->dev, "error %i installing ISR for irq %i\n",
+ ret, irq);
+ goto error;
+ }
+
+ guts_node = of_find_matching_node(NULL, guts_device_ids);
+ if (!guts_node) {
+ dev_err(&pdev->dev, "could not find GUTS node %s\n",
+ pdev->dev.of_node->full_name);
+ ret = -ENODEV;
+ goto error;
+ }
+
+ guts_regs = of_iomap(guts_node, 0);
+ of_node_put(guts_node);
+ if (!guts_regs) {
+ dev_err(&pdev->dev, "ioremap of GUTS node failed\n");
+ ret = -ENODEV;
+ goto error;
+ }
+
+ /* read in the PAMU capability registers */
+ get_pamu_cap_values((unsigned long)pamu_regs);
+ /*
+ * To simplify the allocation of a coherency domain, we allocate the
+ * PAACT and the OMT in the same memory buffer. Unfortunately, this
+ * wastes more memory compared to allocating the buffers separately.
+ */
+ /* Determine how much memory we need */
+ mem_size = (PAGE_SIZE << get_order(PAACT_SIZE)) +
+ (PAGE_SIZE << get_order(SPAACT_SIZE)) +
+ (PAGE_SIZE << get_order(OMT_SIZE));
+ order = get_order(mem_size);
+
+ p = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
+ if (!p) {
+ dev_err(&pdev->dev, "unable to allocate PAACT/SPAACT/OMT block\n");
+ ret = -ENOMEM;
+ goto error;
+ }
+
+ ppaact = page_address(p);
+ ppaact_phys = page_to_phys(p);
+
+ /* Make sure the memory is naturally aligned */
+ if (ppaact_phys & ((PAGE_SIZE << order) - 1)) {
+ dev_err(&pdev->dev, "PAACT/OMT block is unaligned\n");
+ ret = -ENOMEM;
+ goto error;
+ }
+
+ spaact = (void *)ppaact + (PAGE_SIZE << get_order(PAACT_SIZE));
+ omt = (void *)spaact + (PAGE_SIZE << get_order(SPAACT_SIZE));
+
+ dev_dbg(&pdev->dev, "ppaact virt=%p phys=0x%llx\n", ppaact,
+ (unsigned long long) ppaact_phys);
+
+ /* Check to see if we need to implement the work-around on this SOC */
+
+ /* Determine the Port ID for our coherence subdomain */
+ for (i = 0; i < ARRAY_SIZE(port_id_map); i++) {
+ if (port_id_map[i].svr == (mfspr(SPRN_SVR) & ~SVR_SECURITY)) {
+ csd_port_id = port_id_map[i].port_id;
+ dev_dbg(&pdev->dev, "found matching SVR %08x\n",
+ port_id_map[i].svr);
+ break;
+ }
+ }
+
+ if (csd_port_id) {
+ dev_dbg(&pdev->dev, "creating coherency subdomain at address "
+ "0x%llx, size %zu, port id 0x%08x", ppaact_phys,
+ mem_size, csd_port_id);
+
+ ret = create_csd(ppaact_phys, mem_size, csd_port_id);
+ if (ret) {
+ dev_err(&pdev->dev, "could not create coherence "
+ "subdomain\n");
+ return ret;
+ }
+ }
+
+ spaact_phys = virt_to_phys(spaact);
+ omt_phys = virt_to_phys(omt);
+
+ spaace_pool = gen_pool_create(ilog2(sizeof(struct paace)), -1);
+ if (!spaace_pool) {
+ ret = -ENOMEM;
+ dev_err(&pdev->dev, "PAMU : failed to allocate spaace gen pool\n");
+ goto error;
+ }
+
+ ret = gen_pool_add(spaace_pool, (unsigned long)spaact, SPAACT_SIZE, -1);
+ if (ret)
+ goto error_genpool;
+
+ pamubypenr = in_be32(&guts_regs->pamubypenr);
+
+ for (pamu_reg_off = 0, pamu_counter = 0x80000000; pamu_reg_off < size;
+ pamu_reg_off += PAMU_OFFSET, pamu_counter >>= 1) {
+
+ pamu_reg_base = (unsigned long) pamu_regs + pamu_reg_off;
+ setup_one_pamu(pamu_reg_base, pamu_reg_off, ppaact_phys,
+ spaact_phys, omt_phys);
+ /* Disable PAMU bypass for this PAMU */
+ pamubypenr &= ~pamu_counter;
+ }
+
+ setup_omt(omt);
+
+ /* Enable all relevant PAMU(s) */
+ out_be32(&guts_regs->pamubypenr, pamubypenr);
+
+ iounmap(guts_regs);
+
+ /* Enable DMA for the LIODNs in the device tree*/
+
+ setup_liodns();
+
+ return 0;
+
+error_genpool:
+ gen_pool_destroy(spaace_pool);
+
+error:
+ if (irq != NO_IRQ)
+ free_irq(irq, data);
+
+ if (data) {
+ memset(data, 0, sizeof(struct pamu_isr_data));
+ kfree(data);
+ }
+
+ if (pamu_regs)
+ iounmap(pamu_regs);
+
+ if (guts_regs)
+ iounmap(guts_regs);
+
+ if (ppaact)
+ free_pages((unsigned long)ppaact, order);
+
+ ppaact = NULL;
+
+ return ret;
+}
+
+static const struct of_device_id fsl_of_pamu_ids[] = {
+ {
+ .compatible = "fsl,p4080-pamu",
+ },
+ {
+ .compatible = "fsl,pamu",
+ },
+ {},
+};
+
+static struct platform_driver fsl_of_pamu_driver = {
+ .driver = {
+ .name = "fsl-of-pamu",
+ .owner = THIS_MODULE,
+ },
+ .probe = fsl_pamu_probe,
+};
+
+static __init int fsl_pamu_init(void)
+{
+ struct platform_device *pdev = NULL;
+ struct device_node *np;
+ int ret;
+
+ /*
+ * The normal OF process calls the probe function at some
+ * indeterminate later time, after most drivers have loaded. This is
+ * too late for us, because PAMU clients (like the Qman driver)
+ * depend on PAMU being initialized early.
+ *
+ * So instead, we "manually" call our probe function by creating the
+ * platform devices ourselves.
+ */
+
+ /*
+ * We assume that there is only one PAMU node in the device tree. A
+ * single PAMU node represents all of the PAMU devices in the SOC
+ * already. Everything else already makes that assumption, and the
+ * binding for the PAMU nodes doesn't allow for any parent-child
+ * relationships anyway. In other words, support for more than one
+ * PAMU node would require significant changes to a lot of code.
+ */
+
+ np = of_find_compatible_node(NULL, NULL, "fsl,pamu");
+ if (!np) {
+ pr_err("could not find a PAMU node\n");
+ return -ENODEV;
+ }
+
+ ret = platform_driver_register(&fsl_of_pamu_driver);
+ if (ret) {
+ pr_err("could not register driver (err=%i)\n", ret);
+ goto error_driver_register;
+ }
+
+ pdev = platform_device_alloc("fsl-of-pamu", 0);
+ if (!pdev) {
+ pr_err("could not allocate device %s\n",
+ np->full_name);
+ ret = -ENOMEM;
+ goto error_device_alloc;
+ }
+ pdev->dev.of_node = of_node_get(np);
+
+ ret = pamu_domain_init();
+ if (ret)
+ goto error_device_add;
+
+ ret = platform_device_add(pdev);
+ if (ret) {
+ pr_err("could not add device %s (err=%i)\n",
+ np->full_name, ret);
+ goto error_device_add;
+ }
+
+ return 0;
+
+error_device_add:
+ of_node_put(pdev->dev.of_node);
+ pdev->dev.of_node = NULL;
+
+ platform_device_put(pdev);
+
+error_device_alloc:
+ platform_driver_unregister(&fsl_of_pamu_driver);
+
+error_driver_register:
+ of_node_put(np);
+
+ return ret;
+}
+arch_initcall(fsl_pamu_init);
diff --git a/drivers/iommu/fsl_pamu.h b/drivers/iommu/fsl_pamu.h
new file mode 100644
index 0000000..8fc1a12
--- /dev/null
+++ b/drivers/iommu/fsl_pamu.h
@@ -0,0 +1,410 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ *
+ * Copyright (C) 2013 Freescale Semiconductor, Inc.
+ *
+ */
+
+#ifndef __FSL_PAMU_H
+#define __FSL_PAMU_H
+
+#include <asm/fsl_pamu_stash.h>
+
+/* Bit Field macros
+ * v = bit field variable; m = mask, m##_SHIFT = shift, x = value to load
+ */
+#define set_bf(v, m, x) (v = ((v) & ~(m)) | (((x) << (m##_SHIFT)) & (m)))
+#define get_bf(v, m) (((v) & (m)) >> (m##_SHIFT))
+
+/* PAMU CCSR space */
+#define PAMU_PGC 0x00000000 /* Allows all peripheral accesses */
+#define PAMU_PE 0x40000000 /* enable PAMU */
+
+/* PAMU_OFFSET to the next pamu space in ccsr */
+#define PAMU_OFFSET 0x1000
+
+#define PAMU_MMAP_REGS_BASE 0
+
+struct pamu_mmap_regs {
+ u32 ppbah;
+ u32 ppbal;
+ u32 pplah;
+ u32 pplal;
+ u32 spbah;
+ u32 spbal;
+ u32 splah;
+ u32 splal;
+ u32 obah;
+ u32 obal;
+ u32 olah;
+ u32 olal;
+};
+
+/* PAMU Error Registers */
+#define PAMU_POES1 0x0040
+#define PAMU_POES2 0x0044
+#define PAMU_POEAH 0x0048
+#define PAMU_POEAL 0x004C
+#define PAMU_AVS1 0x0050
+#define PAMU_AVS1_AV 0x1
+#define PAMU_AVS1_OTV 0x6
+#define PAMU_AVS1_APV 0x78
+#define PAMU_AVS1_WAV 0x380
+#define PAMU_AVS1_LAV 0x1c00
+#define PAMU_AVS1_GCV 0x2000
+#define PAMU_AVS1_PDV 0x4000
+#define PAMU_AV_MASK (PAMU_AVS1_AV | PAMU_AVS1_OTV | PAMU_AVS1_APV | PAMU_AVS1_WAV \
+ | PAMU_AVS1_LAV | PAMU_AVS1_GCV | PAMU_AVS1_PDV)
+#define PAMU_AVS1_LIODN_SHIFT 16
+#define PAMU_LAV_LIODN_NOT_IN_PPAACT 0x400
+
+#define PAMU_AVS2 0x0054
+#define PAMU_AVAH 0x0058
+#define PAMU_AVAL 0x005C
+#define PAMU_EECTL 0x0060
+#define PAMU_EEDIS 0x0064
+#define PAMU_EEINTEN 0x0068
+#define PAMU_EEDET 0x006C
+#define PAMU_EEATTR 0x0070
+#define PAMU_EEAHI 0x0074
+#define PAMU_EEALO 0x0078
+#define PAMU_EEDHI 0X007C
+#define PAMU_EEDLO 0x0080
+#define PAMU_EECC 0x0084
+#define PAMU_UDAD 0x0090
+
+/* PAMU Revision Registers */
+#define PAMU_PR1 0x0BF8
+#define PAMU_PR2 0x0BFC
+
+/* PAMU version mask */
+#define PAMU_PR1_MASK 0xffff
+
+/* PAMU Capabilities Registers */
+#define PAMU_PC1 0x0C00
+#define PAMU_PC2 0x0C04
+#define PAMU_PC3 0x0C08
+#define PAMU_PC4 0x0C0C
+
+/* PAMU Control Register */
+#define PAMU_PC 0x0C10
+
+/* PAMU control defs */
+#define PAMU_CONTROL 0x0C10
+#define PAMU_PC_PGC 0x80000000 /* PAMU gate closed bit */
+#define PAMU_PC_PE 0x40000000 /* PAMU enable bit */
+#define PAMU_PC_SPCC 0x00000010 /* sPAACE cache enable */
+#define PAMU_PC_PPCC 0x00000001 /* pPAACE cache enable */
+#define PAMU_PC_OCE 0x00001000 /* OMT cache enable */
+
+#define PAMU_PFA1 0x0C14
+#define PAMU_PFA2 0x0C18
+
+#define PAMU_PC2_MLIODN(X) ((X) >> 16)
+#define PAMU_PC3_MWCE(X) (((X) >> 21) & 0xf)
+
+/* PAMU Interrupt control and Status Register */
+#define PAMU_PICS 0x0C1C
+#define PAMU_ACCESS_VIOLATION_STAT 0x8
+#define PAMU_ACCESS_VIOLATION_ENABLE 0x4
+
+/* PAMU Debug Registers */
+#define PAMU_PD1 0x0F00
+#define PAMU_PD2 0x0F04
+#define PAMU_PD3 0x0F08
+#define PAMU_PD4 0x0F0C
+
+#define PAACE_AP_PERMS_DENIED 0x0
+#define PAACE_AP_PERMS_QUERY 0x1
+#define PAACE_AP_PERMS_UPDATE 0x2
+#define PAACE_AP_PERMS_ALL 0x3
+
+#define PAACE_DD_TO_HOST 0x0
+#define PAACE_DD_TO_IO 0x1
+#define PAACE_PT_PRIMARY 0x0
+#define PAACE_PT_SECONDARY 0x1
+#define PAACE_V_INVALID 0x0
+#define PAACE_V_VALID 0x1
+#define PAACE_MW_SUBWINDOWS 0x1
+
+#define PAACE_WSE_4K 0xB
+#define PAACE_WSE_8K 0xC
+#define PAACE_WSE_16K 0xD
+#define PAACE_WSE_32K 0xE
+#define PAACE_WSE_64K 0xF
+#define PAACE_WSE_128K 0x10
+#define PAACE_WSE_256K 0x11
+#define PAACE_WSE_512K 0x12
+#define PAACE_WSE_1M 0x13
+#define PAACE_WSE_2M 0x14
+#define PAACE_WSE_4M 0x15
+#define PAACE_WSE_8M 0x16
+#define PAACE_WSE_16M 0x17
+#define PAACE_WSE_32M 0x18
+#define PAACE_WSE_64M 0x19
+#define PAACE_WSE_128M 0x1A
+#define PAACE_WSE_256M 0x1B
+#define PAACE_WSE_512M 0x1C
+#define PAACE_WSE_1G 0x1D
+#define PAACE_WSE_2G 0x1E
+#define PAACE_WSE_4G 0x1F
+
+#define PAACE_DID_PCI_EXPRESS_1 0x00
+#define PAACE_DID_PCI_EXPRESS_2 0x01
+#define PAACE_DID_PCI_EXPRESS_3 0x02
+#define PAACE_DID_PCI_EXPRESS_4 0x03
+#define PAACE_DID_LOCAL_BUS 0x04
+#define PAACE_DID_SRIO 0x0C
+#define PAACE_DID_MEM_1 0x10
+#define PAACE_DID_MEM_2 0x11
+#define PAACE_DID_MEM_3 0x12
+#define PAACE_DID_MEM_4 0x13
+#define PAACE_DID_MEM_1_2 0x14
+#define PAACE_DID_MEM_3_4 0x15
+#define PAACE_DID_MEM_1_4 0x16
+#define PAACE_DID_BM_SW_PORTAL 0x18
+#define PAACE_DID_PAMU 0x1C
+#define PAACE_DID_CAAM 0x21
+#define PAACE_DID_QM_SW_PORTAL 0x3C
+#define PAACE_DID_CORE0_INST 0x80
+#define PAACE_DID_CORE0_DATA 0x81
+#define PAACE_DID_CORE1_INST 0x82
+#define PAACE_DID_CORE1_DATA 0x83
+#define PAACE_DID_CORE2_INST 0x84
+#define PAACE_DID_CORE2_DATA 0x85
+#define PAACE_DID_CORE3_INST 0x86
+#define PAACE_DID_CORE3_DATA 0x87
+#define PAACE_DID_CORE4_INST 0x88
+#define PAACE_DID_CORE4_DATA 0x89
+#define PAACE_DID_CORE5_INST 0x8A
+#define PAACE_DID_CORE5_DATA 0x8B
+#define PAACE_DID_CORE6_INST 0x8C
+#define PAACE_DID_CORE6_DATA 0x8D
+#define PAACE_DID_CORE7_INST 0x8E
+#define PAACE_DID_CORE7_DATA 0x8F
+#define PAACE_DID_BROADCAST 0xFF
+
+#define PAACE_ATM_NO_XLATE 0x00
+#define PAACE_ATM_WINDOW_XLATE 0x01
+#define PAACE_ATM_PAGE_XLATE 0x02
+#define PAACE_ATM_WIN_PG_XLATE \
+ (PAACE_ATM_WINDOW_XLATE | PAACE_ATM_PAGE_XLATE)
+#define PAACE_OTM_NO_XLATE 0x00
+#define PAACE_OTM_IMMEDIATE 0x01
+#define PAACE_OTM_INDEXED 0x02
+#define PAACE_OTM_RESERVED 0x03
+
+#define PAACE_M_COHERENCE_REQ 0x01
+
+#define PAACE_PID_0 0x0
+#define PAACE_PID_1 0x1
+#define PAACE_PID_2 0x2
+#define PAACE_PID_3 0x3
+#define PAACE_PID_4 0x4
+#define PAACE_PID_5 0x5
+#define PAACE_PID_6 0x6
+#define PAACE_PID_7 0x7
+
+#define PAACE_TCEF_FORMAT0_8B 0x00
+#define PAACE_TCEF_FORMAT1_RSVD 0x01
+/*
+ * Hard coded value for the PAACT size to accomodate
+ * maximum LIODN value generated by u-boot.
+ */
+#define PAACE_NUMBER_ENTRIES 0x500
+/* Hard coded value for the SPAACT size */
+#define SPAACE_NUMBER_ENTRIES 0x800
+
+#define OME_NUMBER_ENTRIES 16
+
+/* PAACE Bit Field Defines */
+#define PPAACE_AF_WBAL 0xfffff000
+#define PPAACE_AF_WBAL_SHIFT 12
+#define PPAACE_AF_WSE 0x00000fc0
+#define PPAACE_AF_WSE_SHIFT 6
+#define PPAACE_AF_MW 0x00000020
+#define PPAACE_AF_MW_SHIFT 5
+
+#define SPAACE_AF_LIODN 0xffff0000
+#define SPAACE_AF_LIODN_SHIFT 16
+
+#define PAACE_AF_AP 0x00000018
+#define PAACE_AF_AP_SHIFT 3
+#define PAACE_AF_DD 0x00000004
+#define PAACE_AF_DD_SHIFT 2
+#define PAACE_AF_PT 0x00000002
+#define PAACE_AF_PT_SHIFT 1
+#define PAACE_AF_V 0x00000001
+#define PAACE_AF_V_SHIFT 0
+
+#define PAACE_DA_HOST_CR 0x80
+#define PAACE_DA_HOST_CR_SHIFT 7
+
+#define PAACE_IA_CID 0x00FF0000
+#define PAACE_IA_CID_SHIFT 16
+#define PAACE_IA_WCE 0x000000F0
+#define PAACE_IA_WCE_SHIFT 4
+#define PAACE_IA_ATM 0x0000000C
+#define PAACE_IA_ATM_SHIFT 2
+#define PAACE_IA_OTM 0x00000003
+#define PAACE_IA_OTM_SHIFT 0
+
+#define PAACE_WIN_TWBAL 0xfffff000
+#define PAACE_WIN_TWBAL_SHIFT 12
+#define PAACE_WIN_SWSE 0x00000fc0
+#define PAACE_WIN_SWSE_SHIFT 6
+
+/* PAMU Data Structures */
+/* primary / secondary paact structure */
+struct paace {
+ /* PAACE Offset 0x00 */
+ u32 wbah; /* only valid for Primary PAACE */
+ u32 addr_bitfields; /* See P/S PAACE_AF_* */
+
+ /* PAACE Offset 0x08 */
+ /* Interpretation of first 32 bits dependent on DD above */
+ union {
+ struct {
+ /* Destination ID, see PAACE_DID_* defines */
+ u8 did;
+ /* Partition ID */
+ u8 pid;
+ /* Snoop ID */
+ u8 snpid;
+ /* coherency_required : 1 reserved : 7 */
+ u8 coherency_required; /* See PAACE_DA_* */
+ } to_host;
+ struct {
+ /* Destination ID, see PAACE_DID_* defines */
+ u8 did;
+ u8 reserved1;
+ u16 reserved2;
+ } to_io;
+ } domain_attr;
+
+ /* Implementation attributes + window count + address & operation translation modes */
+ u32 impl_attr; /* See PAACE_IA_* */
+
+ /* PAACE Offset 0x10 */
+ /* Translated window base address */
+ u32 twbah;
+ u32 win_bitfields; /* See PAACE_WIN_* */
+
+ /* PAACE Offset 0x18 */
+ /* first secondary paace entry */
+ u32 fspi; /* only valid for Primary PAACE */
+ union {
+ struct {
+ u8 ioea;
+ u8 moea;
+ u8 ioeb;
+ u8 moeb;
+ } immed_ot;
+ struct {
+ u16 reserved;
+ u16 omi;
+ } index_ot;
+ } op_encode;
+
+ /* PAACE Offsets 0x20-0x38 */
+ u32 reserved[8]; /* not currently implemented */
+};
+
+/* OME : Operation mapping entry
+ * MOE : Mapped Operation Encodings
+ * The operation mapping table is table containing operation mapping entries (OME).
+ * The index of a particular OME is programmed in the PAACE entry for translation
+ * in bound I/O operations corresponding to an LIODN. The OMT is used for translation
+ * specifically in case of the indexed translation mode. Each OME contains a 128
+ * byte mapped operation encoding (MOE), where each byte represents an MOE.
+ */
+#define NUM_MOE 128
+struct ome {
+ u8 moe[NUM_MOE];
+} __attribute__((packed));
+
+#define PAACT_SIZE (sizeof(struct paace) * PAACE_NUMBER_ENTRIES)
+#define SPAACT_SIZE (sizeof(struct paace) * SPAACE_NUMBER_ENTRIES)
+#define OMT_SIZE (sizeof(struct ome) * OME_NUMBER_ENTRIES)
+
+#define PAMU_PAGE_SHIFT 12
+#define PAMU_PAGE_SIZE 4096ULL
+
+#define IOE_READ 0x00
+#define IOE_READ_IDX 0x00
+#define IOE_WRITE 0x81
+#define IOE_WRITE_IDX 0x01
+#define IOE_EREAD0 0x82 /* Enhanced read type 0 */
+#define IOE_EREAD0_IDX 0x02 /* Enhanced read type 0 */
+#define IOE_EWRITE0 0x83 /* Enhanced write type 0 */
+#define IOE_EWRITE0_IDX 0x03 /* Enhanced write type 0 */
+#define IOE_DIRECT0 0x84 /* Directive type 0 */
+#define IOE_DIRECT0_IDX 0x04 /* Directive type 0 */
+#define IOE_EREAD1 0x85 /* Enhanced read type 1 */
+#define IOE_EREAD1_IDX 0x05 /* Enhanced read type 1 */
+#define IOE_EWRITE1 0x86 /* Enhanced write type 1 */
+#define IOE_EWRITE1_IDX 0x06 /* Enhanced write type 1 */
+#define IOE_DIRECT1 0x87 /* Directive type 1 */
+#define IOE_DIRECT1_IDX 0x07 /* Directive type 1 */
+#define IOE_RAC 0x8c /* Read with Atomic clear */
+#define IOE_RAC_IDX 0x0c /* Read with Atomic clear */
+#define IOE_RAS 0x8d /* Read with Atomic set */
+#define IOE_RAS_IDX 0x0d /* Read with Atomic set */
+#define IOE_RAD 0x8e /* Read with Atomic decrement */
+#define IOE_RAD_IDX 0x0e /* Read with Atomic decrement */
+#define IOE_RAI 0x8f /* Read with Atomic increment */
+#define IOE_RAI_IDX 0x0f /* Read with Atomic increment */
+
+#define EOE_READ 0x00
+#define EOE_WRITE 0x01
+#define EOE_RAC 0x0c /* Read with Atomic clear */
+#define EOE_RAS 0x0d /* Read with Atomic set */
+#define EOE_RAD 0x0e /* Read with Atomic decrement */
+#define EOE_RAI 0x0f /* Read with Atomic increment */
+#define EOE_LDEC 0x10 /* Load external cache */
+#define EOE_LDECL 0x11 /* Load external cache with stash lock */
+#define EOE_LDECPE 0x12 /* Load external cache with preferred exclusive */
+#define EOE_LDECPEL 0x13 /* Load external cache with preferred exclusive and lock */
+#define EOE_LDECFE 0x14 /* Load external cache with forced exclusive */
+#define EOE_LDECFEL 0x15 /* Load external cache with forced exclusive and lock */
+#define EOE_RSA 0x16 /* Read with stash allocate */
+#define EOE_RSAU 0x17 /* Read with stash allocate and unlock */
+#define EOE_READI 0x18 /* Read with invalidate */
+#define EOE_RWNITC 0x19 /* Read with no intention to cache */
+#define EOE_WCI 0x1a /* Write cache inhibited */
+#define EOE_WWSA 0x1b /* Write with stash allocate */
+#define EOE_WWSAL 0x1c /* Write with stash allocate and lock */
+#define EOE_WWSAO 0x1d /* Write with stash allocate only */
+#define EOE_WWSAOL 0x1e /* Write with stash allocate only and lock */
+#define EOE_VALID 0x80
+
+/* Function prototypes */
+int pamu_domain_init(void);
+int pamu_enable_liodn(int liodn);
+int pamu_disable_liodn(int liodn);
+void pamu_free_subwins(int liodn);
+int pamu_config_ppaace(int liodn, phys_addr_t win_addr, phys_addr_t win_size,
+ u32 omi, unsigned long rpn, u32 snoopid, uint32_t stashid,
+ u32 subwin_cnt, int prot);
+int pamu_config_spaace(int liodn, u32 subwin_cnt, u32 subwin_addr,
+ phys_addr_t subwin_size, u32 omi, unsigned long rpn,
+ uint32_t snoopid, u32 stashid, int enable, int prot);
+
+u32 get_stash_id(u32 stash_dest_hint, u32 vcpu);
+void get_ome_index(u32 *omi_index, struct device *dev);
+int pamu_update_paace_stash(int liodn, u32 subwin, u32 value);
+int pamu_disable_spaace(int liodn, u32 subwin);
+u32 pamu_get_max_subwin_cnt(void);
+
+#endif /* __FSL_PAMU_H */
diff --git a/drivers/iommu/fsl_pamu_domain.c b/drivers/iommu/fsl_pamu_domain.c
new file mode 100644
index 0000000..c857c30
--- /dev/null
+++ b/drivers/iommu/fsl_pamu_domain.c
@@ -0,0 +1,1172 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ *
+ * Copyright (C) 2013 Freescale Semiconductor, Inc.
+ * Author: Varun Sethi <varun.sethi@freescale.com>
+ *
+ */
+
+#define pr_fmt(fmt) "fsl-pamu-domain: %s: " fmt, __func__
+
+#include <linux/init.h>
+#include <linux/iommu.h>
+#include <linux/notifier.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <linux/interrupt.h>
+#include <linux/device.h>
+#include <linux/of_platform.h>
+#include <linux/bootmem.h>
+#include <linux/err.h>
+#include <asm/io.h>
+#include <asm/bitops.h>
+
+#include <asm/pci-bridge.h>
+#include <sysdev/fsl_pci.h>
+
+#include "fsl_pamu_domain.h"
+#include "pci.h"
+
+/*
+ * Global spinlock that needs to be held while
+ * configuring PAMU.
+ */
+static DEFINE_SPINLOCK(iommu_lock);
+
+static struct kmem_cache *fsl_pamu_domain_cache;
+static struct kmem_cache *iommu_devinfo_cache;
+static DEFINE_SPINLOCK(device_domain_lock);
+
+static int __init iommu_init_mempool(void)
+{
+
+ fsl_pamu_domain_cache = kmem_cache_create("fsl_pamu_domain",
+ sizeof(struct fsl_dma_domain),
+ 0,
+ SLAB_HWCACHE_ALIGN,
+
+ NULL);
+ if (!fsl_pamu_domain_cache) {
+ pr_debug("Couldn't create fsl iommu_domain cache\n");
+ return -ENOMEM;
+ }
+
+ iommu_devinfo_cache = kmem_cache_create("iommu_devinfo",
+ sizeof(struct device_domain_info),
+ 0,
+ SLAB_HWCACHE_ALIGN,
+ NULL);
+ if (!iommu_devinfo_cache) {
+ pr_debug("Couldn't create devinfo cache\n");
+ kmem_cache_destroy(fsl_pamu_domain_cache);
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static phys_addr_t get_phys_addr(struct fsl_dma_domain *dma_domain, dma_addr_t iova)
+{
+ u32 win_cnt = dma_domain->win_cnt;
+ struct dma_window *win_ptr =
+ &dma_domain->win_arr[0];
+ struct iommu_domain_geometry *geom;
+
+ geom = &dma_domain->iommu_domain->geometry;
+
+ if (!win_cnt || !dma_domain->geom_size) {
+ pr_debug("Number of windows/geometry not configured for the domain\n");
+ return 0;
+ }
+
+ if (win_cnt > 1) {
+ u64 subwin_size;
+ dma_addr_t subwin_iova;
+ u32 wnd;
+
+ subwin_size = dma_domain->geom_size >> ilog2(win_cnt);
+ subwin_iova = iova & ~(subwin_size - 1);
+ wnd = (subwin_iova - geom->aperture_start) >> ilog2(subwin_size);
+ win_ptr = &dma_domain->win_arr[wnd];
+ }
+
+ if (win_ptr->valid)
+ return (win_ptr->paddr + (iova & (win_ptr->size - 1)));
+
+ return 0;
+}
+
+static int map_subwins(int liodn, struct fsl_dma_domain *dma_domain)
+{
+ struct dma_window *sub_win_ptr =
+ &dma_domain->win_arr[0];
+ int i, ret;
+ unsigned long rpn, flags;
+
+ for (i = 0; i < dma_domain->win_cnt; i++) {
+ if (sub_win_ptr[i].valid) {
+ rpn = sub_win_ptr[i].paddr >>
+ PAMU_PAGE_SHIFT;
+ spin_lock_irqsave(&iommu_lock, flags);
+ ret = pamu_config_spaace(liodn, dma_domain->win_cnt, i,
+ sub_win_ptr[i].size,
+ ~(u32)0,
+ rpn,
+ dma_domain->snoop_id,
+ dma_domain->stash_id,
+ (i > 0) ? 1 : 0,
+ sub_win_ptr[i].prot);
+ spin_unlock_irqrestore(&iommu_lock, flags);
+ if (ret) {
+ pr_debug("PAMU SPAACE configuration failed for liodn %d\n",
+ liodn);
+ return ret;
+ }
+ }
+ }
+
+ return ret;
+}
+
+static int map_win(int liodn, struct fsl_dma_domain *dma_domain)
+{
+ int ret;
+ struct dma_window *wnd = &dma_domain->win_arr[0];
+ phys_addr_t wnd_addr = dma_domain->iommu_domain->geometry.aperture_start;
+ unsigned long flags;
+
+ spin_lock_irqsave(&iommu_lock, flags);
+ ret = pamu_config_ppaace(liodn, wnd_addr,
+ wnd->size,
+ ~(u32)0,
+ wnd->paddr >> PAMU_PAGE_SHIFT,
+ dma_domain->snoop_id, dma_domain->stash_id,
+ 0, wnd->prot);
+ spin_unlock_irqrestore(&iommu_lock, flags);
+ if (ret)
+ pr_debug("PAMU PAACE configuration failed for liodn %d\n",
+ liodn);
+
+ return ret;
+}
+
+/* Map the DMA window corresponding to the LIODN */
+static int map_liodn(int liodn, struct fsl_dma_domain *dma_domain)
+{
+ if (dma_domain->win_cnt > 1)
+ return map_subwins(liodn, dma_domain);
+ else
+ return map_win(liodn, dma_domain);
+
+}
+
+/* Update window/subwindow mapping for the LIODN */
+static int update_liodn(int liodn, struct fsl_dma_domain *dma_domain, u32 wnd_nr)
+{
+ int ret;
+ struct dma_window *wnd = &dma_domain->win_arr[wnd_nr];
+ unsigned long flags;
+
+ spin_lock_irqsave(&iommu_lock, flags);
+ if (dma_domain->win_cnt > 1) {
+ ret = pamu_config_spaace(liodn, dma_domain->win_cnt, wnd_nr,
+ wnd->size,
+ ~(u32)0,
+ wnd->paddr >> PAMU_PAGE_SHIFT,
+ dma_domain->snoop_id,
+ dma_domain->stash_id,
+ (wnd_nr > 0) ? 1 : 0,
+ wnd->prot);
+ if (ret)
+ pr_debug("Subwindow reconfiguration failed for liodn %d\n", liodn);
+ } else {
+ phys_addr_t wnd_addr;
+
+ wnd_addr = dma_domain->iommu_domain->geometry.aperture_start;
+
+ ret = pamu_config_ppaace(liodn, wnd_addr,
+ wnd->size,
+ ~(u32)0,
+ wnd->paddr >> PAMU_PAGE_SHIFT,
+ dma_domain->snoop_id, dma_domain->stash_id,
+ 0, wnd->prot);
+ if (ret)
+ pr_debug("Window reconfiguration failed for liodn %d\n", liodn);
+ }
+
+ spin_unlock_irqrestore(&iommu_lock, flags);
+
+ return ret;
+}
+
+static int update_liodn_stash(int liodn, struct fsl_dma_domain *dma_domain,
+ u32 val)
+{
+ int ret = 0, i;
+ unsigned long flags;
+
+ spin_lock_irqsave(&iommu_lock, flags);
+ if (!dma_domain->win_arr) {
+ pr_debug("Windows not configured, stash destination update failed for liodn %d\n", liodn);
+ spin_unlock_irqrestore(&iommu_lock, flags);
+ return -EINVAL;
+ }
+
+ for (i = 0; i < dma_domain->win_cnt; i++) {
+ ret = pamu_update_paace_stash(liodn, i, val);
+ if (ret) {
+ pr_debug("Failed to update SPAACE %d field for liodn %d\n ", i, liodn);
+ spin_unlock_irqrestore(&iommu_lock, flags);
+ return ret;
+ }
+ }
+
+ spin_unlock_irqrestore(&iommu_lock, flags);
+
+ return ret;
+}
+
+/* Set the geometry parameters for a LIODN */
+static int pamu_set_liodn(int liodn, struct device *dev,
+ struct fsl_dma_domain *dma_domain,
+ struct iommu_domain_geometry *geom_attr,
+ u32 win_cnt)
+{
+ phys_addr_t window_addr, window_size;
+ phys_addr_t subwin_size;
+ int ret = 0, i;
+ u32 omi_index = ~(u32)0;
+ unsigned long flags;
+
+ /*
+ * Configure the omi_index at the geometry setup time.
+ * This is a static value which depends on the type of
+ * device and would not change thereafter.
+ */
+ get_ome_index(&omi_index, dev);
+
+ window_addr = geom_attr->aperture_start;
+ window_size = dma_domain->geom_size;
+
+ spin_lock_irqsave(&iommu_lock, flags);
+ ret = pamu_disable_liodn(liodn);
+ if (!ret)
+ ret = pamu_config_ppaace(liodn, window_addr, window_size, omi_index,
+ 0, dma_domain->snoop_id,
+ dma_domain->stash_id, win_cnt, 0);
+ spin_unlock_irqrestore(&iommu_lock, flags);
+ if (ret) {
+ pr_debug("PAMU PAACE configuration failed for liodn %d, win_cnt =%d\n", liodn, win_cnt);
+ return ret;
+ }
+
+ if (win_cnt > 1) {
+ subwin_size = window_size >> ilog2(win_cnt);
+ for (i = 0; i < win_cnt; i++) {
+ spin_lock_irqsave(&iommu_lock, flags);
+ ret = pamu_disable_spaace(liodn, i);
+ if (!ret)
+ ret = pamu_config_spaace(liodn, win_cnt, i,
+ subwin_size, omi_index,
+ 0, dma_domain->snoop_id,
+ dma_domain->stash_id,
+ 0, 0);
+ spin_unlock_irqrestore(&iommu_lock, flags);
+ if (ret) {
+ pr_debug("PAMU SPAACE configuration failed for liodn %d\n", liodn);
+ return ret;
+ }
+ }
+ }
+
+ return ret;
+}
+
+static int check_size(u64 size, dma_addr_t iova)
+{
+ /*
+ * Size must be a power of two and at least be equal
+ * to PAMU page size.
+ */
+ if (!is_power_of_2(size) || size < PAMU_PAGE_SIZE) {
+ pr_debug("%s: size too small or not a power of two\n", __func__);
+ return -EINVAL;
+ }
+
+ /* iova must be page size aligned*/
+ if (iova & (size - 1)) {
+ pr_debug("%s: address is not aligned with window size\n", __func__);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static struct fsl_dma_domain *iommu_alloc_dma_domain(void)
+{
+ struct fsl_dma_domain *domain;
+
+ domain = kmem_cache_zalloc(fsl_pamu_domain_cache, GFP_KERNEL);
+ if (!domain)
+ return NULL;
+
+ domain->stash_id = ~(u32)0;
+ domain->snoop_id = ~(u32)0;
+ domain->win_cnt = pamu_get_max_subwin_cnt();
+ domain->geom_size = 0;
+
+ INIT_LIST_HEAD(&domain->devices);
+
+ spin_lock_init(&domain->domain_lock);
+
+ return domain;
+}
+
+static inline struct device_domain_info *find_domain(struct device *dev)
+{
+ return dev->archdata.iommu_domain;
+}
+
+static void remove_device_ref(struct device_domain_info *info, u32 win_cnt)
+{
+ unsigned long flags;
+
+ list_del(&info->link);
+ spin_lock_irqsave(&iommu_lock, flags);
+ if (win_cnt > 1)
+ pamu_free_subwins(info->liodn);
+ pamu_disable_liodn(info->liodn);
+ spin_unlock_irqrestore(&iommu_lock, flags);
+ spin_lock_irqsave(&device_domain_lock, flags);
+ info->dev->archdata.iommu_domain = NULL;
+ kmem_cache_free(iommu_devinfo_cache, info);
+ spin_unlock_irqrestore(&device_domain_lock, flags);
+}
+
+static void detach_device(struct device *dev, struct fsl_dma_domain *dma_domain)
+{
+ struct device_domain_info *info, *tmp;
+ unsigned long flags;
+
+ spin_lock_irqsave(&dma_domain->domain_lock, flags);
+ /* Remove the device from the domain device list */
+ list_for_each_entry_safe(info, tmp, &dma_domain->devices, link) {
+ if (!dev || (info->dev == dev))
+ remove_device_ref(info, dma_domain->win_cnt);
+ }
+ spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+}
+
+static void attach_device(struct fsl_dma_domain *dma_domain, int liodn, struct device *dev)
+{
+ struct device_domain_info *info, *old_domain_info;
+ unsigned long flags;
+
+ spin_lock_irqsave(&device_domain_lock, flags);
+ /*
+ * Check here if the device is already attached to domain or not.
+ * If the device is already attached to a domain detach it.
+ */
+ old_domain_info = find_domain(dev);
+ if (old_domain_info && old_domain_info->domain != dma_domain) {
+ spin_unlock_irqrestore(&device_domain_lock, flags);
+ detach_device(dev, old_domain_info->domain);
+ spin_lock_irqsave(&device_domain_lock, flags);
+ }
+
+ info = kmem_cache_zalloc(iommu_devinfo_cache, GFP_ATOMIC);
+
+ info->dev = dev;
+ info->liodn = liodn;
+ info->domain = dma_domain;
+
+ list_add(&info->link, &dma_domain->devices);
+ /*
+ * In case of devices with multiple LIODNs just store
+ * the info for the first LIODN as all
+ * LIODNs share the same domain
+ */
+ if (!old_domain_info)
+ dev->archdata.iommu_domain = info;
+ spin_unlock_irqrestore(&device_domain_lock, flags);
+
+}
+
+static phys_addr_t fsl_pamu_iova_to_phys(struct iommu_domain *domain,
+ dma_addr_t iova)
+{
+ struct fsl_dma_domain *dma_domain = domain->priv;
+
+ if ((iova < domain->geometry.aperture_start) ||
+ iova > (domain->geometry.aperture_end))
+ return 0;
+
+ return get_phys_addr(dma_domain, iova);
+}
+
+static int fsl_pamu_domain_has_cap(struct iommu_domain *domain,
+ unsigned long cap)
+{
+ return cap == IOMMU_CAP_CACHE_COHERENCY;
+}
+
+static void fsl_pamu_domain_destroy(struct iommu_domain *domain)
+{
+ struct fsl_dma_domain *dma_domain = domain->priv;
+
+ domain->priv = NULL;
+
+ /* remove all the devices from the device list */
+ detach_device(NULL, dma_domain);
+
+ dma_domain->enabled = 0;
+ dma_domain->mapped = 0;
+
+ kmem_cache_free(fsl_pamu_domain_cache, dma_domain);
+}
+
+static int fsl_pamu_domain_init(struct iommu_domain *domain)
+{
+ struct fsl_dma_domain *dma_domain;
+
+ dma_domain = iommu_alloc_dma_domain();
+ if (!dma_domain) {
+ pr_debug("dma_domain allocation failed\n");
+ return -ENOMEM;
+ }
+ domain->priv = dma_domain;
+ dma_domain->iommu_domain = domain;
+ /* defaul geometry 64 GB i.e. maximum system address */
+ domain->geometry.aperture_start = 0;
+ domain->geometry.aperture_end = (1ULL << 36) - 1;
+ domain->geometry.force_aperture = true;
+
+ return 0;
+}
+
+/* Configure geometry settings for all LIODNs associated with domain */
+static int pamu_set_domain_geometry(struct fsl_dma_domain *dma_domain,
+ struct iommu_domain_geometry *geom_attr,
+ u32 win_cnt)
+{
+ struct device_domain_info *info;
+ int ret = 0;
+
+ list_for_each_entry(info, &dma_domain->devices, link) {
+ ret = pamu_set_liodn(info->liodn, info->dev, dma_domain,
+ geom_attr, win_cnt);
+ if (ret)
+ break;
+ }
+
+ return ret;
+}
+
+/* Update stash destination for all LIODNs associated with the domain */
+static int update_domain_stash(struct fsl_dma_domain *dma_domain, u32 val)
+{
+ struct device_domain_info *info;
+ int ret = 0;
+
+ list_for_each_entry(info, &dma_domain->devices, link) {
+ ret = update_liodn_stash(info->liodn, dma_domain, val);
+ if (ret)
+ break;
+ }
+
+ return ret;
+}
+
+/* Update domain mappings for all LIODNs associated with the domain */
+static int update_domain_mapping(struct fsl_dma_domain *dma_domain, u32 wnd_nr)
+{
+ struct device_domain_info *info;
+ int ret = 0;
+
+ list_for_each_entry(info, &dma_domain->devices, link) {
+ ret = update_liodn(info->liodn, dma_domain, wnd_nr);
+ if (ret)
+ break;
+ }
+ return ret;
+}
+
+static int disable_domain_win(struct fsl_dma_domain *dma_domain, u32 wnd_nr)
+{
+ struct device_domain_info *info;
+ int ret = 0;
+
+ list_for_each_entry(info, &dma_domain->devices, link) {
+ if (dma_domain->win_cnt == 1 && dma_domain->enabled) {
+ ret = pamu_disable_liodn(info->liodn);
+ if (!ret)
+ dma_domain->enabled = 0;
+ } else {
+ ret = pamu_disable_spaace(info->liodn, wnd_nr);
+ }
+ }
+
+ return ret;
+}
+
+static void fsl_pamu_window_disable(struct iommu_domain *domain, u32 wnd_nr)
+{
+ struct fsl_dma_domain *dma_domain = domain->priv;
+ unsigned long flags;
+ int ret;
+
+ spin_lock_irqsave(&dma_domain->domain_lock, flags);
+ if (!dma_domain->win_arr) {
+ pr_debug("Number of windows not configured\n");
+ spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+ return;
+ }
+
+ if (wnd_nr >= dma_domain->win_cnt) {
+ pr_debug("Invalid window index\n");
+ spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+ return;
+ }
+
+ if (dma_domain->win_arr[wnd_nr].valid) {
+ ret = disable_domain_win(dma_domain, wnd_nr);
+ if (!ret) {
+ dma_domain->win_arr[wnd_nr].valid = 0;
+ dma_domain->mapped--;
+ }
+ }
+
+ spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+
+}
+
+static int fsl_pamu_window_enable(struct iommu_domain *domain, u32 wnd_nr,
+ phys_addr_t paddr, u64 size, int prot)
+{
+ struct fsl_dma_domain *dma_domain = domain->priv;
+ struct dma_window *wnd;
+ int pamu_prot = 0;
+ int ret;
+ unsigned long flags;
+ u64 win_size;
+
+ if (prot & IOMMU_READ)
+ pamu_prot |= PAACE_AP_PERMS_QUERY;
+ if (prot & IOMMU_WRITE)
+ pamu_prot |= PAACE_AP_PERMS_UPDATE;
+
+ spin_lock_irqsave(&dma_domain->domain_lock, flags);
+ if (!dma_domain->win_arr) {
+ pr_debug("Number of windows not configured\n");
+ spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+ return -ENODEV;
+ }
+
+ if (wnd_nr >= dma_domain->win_cnt) {
+ pr_debug("Invalid window index\n");
+ spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+ return -EINVAL;
+ }
+
+ win_size = dma_domain->geom_size >> ilog2(dma_domain->win_cnt);
+ if (size > win_size) {
+ pr_debug("Invalid window size \n");
+ spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+ return -EINVAL;
+ }
+
+ if (dma_domain->win_cnt == 1) {
+ if (dma_domain->enabled) {
+ pr_debug("Disable the window before updating the mapping\n");
+ spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+ return -EBUSY;
+ }
+
+ ret = check_size(size, domain->geometry.aperture_start);
+ if (ret) {
+ pr_debug("Aperture start not aligned to the size\n");
+ spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+ return -EINVAL;
+ }
+ }
+
+ wnd = &dma_domain->win_arr[wnd_nr];
+ if (!wnd->valid) {
+ wnd->paddr = paddr;
+ wnd->size = size;
+ wnd->prot = pamu_prot;
+
+ ret = update_domain_mapping(dma_domain, wnd_nr);
+ if (!ret) {
+ wnd->valid = 1;
+ dma_domain->mapped++;
+ }
+ } else {
+ pr_debug("Disable the window before updating the mapping\n");
+ ret = -EBUSY;
+ }
+
+ spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+
+ return ret;
+}
+
+/*
+ * Attach the LIODN to the DMA domain and configure the geometry
+ * and window mappings.
+ */
+static int handle_attach_device(struct fsl_dma_domain *dma_domain,
+ struct device *dev, const u32 *liodn,
+ int num)
+{
+ unsigned long flags;
+ struct iommu_domain *domain = dma_domain->iommu_domain;
+ int ret = 0;
+ int i;
+
+ spin_lock_irqsave(&dma_domain->domain_lock, flags);
+ for (i = 0; i < num; i++) {
+
+ /* Ensure that LIODN value is valid */
+ if (liodn[i] >= PAACE_NUMBER_ENTRIES) {
+ pr_debug("Invalid liodn %d, attach device failed for %s\n",
+ liodn[i], dev->of_node->full_name);
+ ret = -EINVAL;
+ break;
+ }
+
+ attach_device(dma_domain, liodn[i], dev);
+ /*
+ * Check if geometry has already been configured
+ * for the domain. If yes, set the geometry for
+ * the LIODN.
+ */
+ if (dma_domain->win_arr) {
+ u32 win_cnt = dma_domain->win_cnt > 1 ? dma_domain->win_cnt : 0;
+ ret = pamu_set_liodn(liodn[i], dev, dma_domain,
+ &domain->geometry,
+ win_cnt);
+ if (ret)
+ break;
+ if (dma_domain->mapped) {
+ /*
+ * Create window/subwindow mapping for
+ * the LIODN.
+ */
+ ret = map_liodn(liodn[i], dma_domain);
+ if (ret)
+ break;
+ }
+ }
+ }
+ spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+
+ return ret;
+}
+
+static int fsl_pamu_attach_device(struct iommu_domain *domain,
+ struct device *dev)
+{
+ struct fsl_dma_domain *dma_domain = domain->priv;
+ const u32 *liodn;
+ u32 liodn_cnt;
+ int len, ret = 0;
+ struct pci_dev *pdev = NULL;
+ struct pci_controller *pci_ctl;
+
+ /*
+ * Use LIODN of the PCI controller while attaching a
+ * PCI device.
+ */
+ if (dev->bus == &pci_bus_type) {
+ pdev = to_pci_dev(dev);
+ pci_ctl = pci_bus_to_host(pdev->bus);
+ /*
+ * make dev point to pci controller device
+ * so we can get the LIODN programmed by
+ * u-boot.
+ */
+ dev = pci_ctl->parent;
+ }
+
+ liodn = of_get_property(dev->of_node, "fsl,liodn", &len);
+ if (liodn) {
+ liodn_cnt = len / sizeof(u32);
+ ret = handle_attach_device(dma_domain, dev,
+ liodn, liodn_cnt);
+ } else {
+ pr_debug("missing fsl,liodn property at %s\n",
+ dev->of_node->full_name);
+ ret = -EINVAL;
+ }
+
+ return ret;
+}
+
+static void fsl_pamu_detach_device(struct iommu_domain *domain,
+ struct device *dev)
+{
+ struct fsl_dma_domain *dma_domain = domain->priv;
+ const u32 *prop;
+ int len;
+ struct pci_dev *pdev = NULL;
+ struct pci_controller *pci_ctl;
+
+ /*
+ * Use LIODN of the PCI controller while detaching a
+ * PCI device.
+ */
+ if (dev->bus == &pci_bus_type) {
+ pdev = to_pci_dev(dev);
+ pci_ctl = pci_bus_to_host(pdev->bus);
+ /*
+ * make dev point to pci controller device
+ * so we can get the LIODN programmed by
+ * u-boot.
+ */
+ dev = pci_ctl->parent;
+ }
+
+ prop = of_get_property(dev->of_node, "fsl,liodn", &len);
+ if (prop)
+ detach_device(dev, dma_domain);
+ else
+ pr_debug("missing fsl,liodn property at %s\n",
+ dev->of_node->full_name);
+}
+
+static int configure_domain_geometry(struct iommu_domain *domain, void *data)
+{
+ struct iommu_domain_geometry *geom_attr = data;
+ struct fsl_dma_domain *dma_domain = domain->priv;
+ dma_addr_t geom_size;
+ unsigned long flags;
+
+ geom_size = geom_attr->aperture_end - geom_attr->aperture_start + 1;
+ /*
+ * Sanity check the geometry size. Also, we do not support
+ * DMA outside of the geometry.
+ */
+ if (check_size(geom_size, geom_attr->aperture_start) ||
+ !geom_attr->force_aperture) {
+ pr_debug("Invalid PAMU geometry attributes\n");
+ return -EINVAL;
+ }
+
+ spin_lock_irqsave(&dma_domain->domain_lock, flags);
+ if (dma_domain->enabled) {
+ pr_debug("Can't set geometry attributes as domain is active\n");
+ spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+ return -EBUSY;
+ }
+
+ /* Copy the domain geometry information */
+ memcpy(&domain->geometry, geom_attr,
+ sizeof(struct iommu_domain_geometry));
+ dma_domain->geom_size = geom_size;
+
+ spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+
+ return 0;
+}
+
+/* Set the domain stash attribute */
+static int configure_domain_stash(struct fsl_dma_domain *dma_domain, void *data)
+{
+ struct pamu_stash_attribute *stash_attr = data;
+ unsigned long flags;
+ int ret;
+
+ spin_lock_irqsave(&dma_domain->domain_lock, flags);
+
+ memcpy(&dma_domain->dma_stash, stash_attr,
+ sizeof(struct pamu_stash_attribute));
+
+ dma_domain->stash_id = get_stash_id(stash_attr->cache,
+ stash_attr->cpu);
+ if (dma_domain->stash_id == ~(u32)0) {
+ pr_debug("Invalid stash attributes\n");
+ spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+ return -EINVAL;
+ }
+
+ ret = update_domain_stash(dma_domain, dma_domain->stash_id);
+
+ spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+
+ return ret;
+}
+
+/* Configure domain dma state i.e. enable/disable DMA*/
+static int configure_domain_dma_state(struct fsl_dma_domain *dma_domain, bool enable)
+{
+ struct device_domain_info *info;
+ unsigned long flags;
+ int ret;
+
+ spin_lock_irqsave(&dma_domain->domain_lock, flags);
+
+ if (enable && !dma_domain->mapped) {
+ pr_debug("Can't enable DMA domain without valid mapping\n");
+ spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+ return -ENODEV;
+ }
+
+ dma_domain->enabled = enable;
+ list_for_each_entry(info, &dma_domain->devices,
+ link) {
+ ret = (enable) ? pamu_enable_liodn(info->liodn) :
+ pamu_disable_liodn(info->liodn);
+ if (ret)
+ pr_debug("Unable to set dma state for liodn %d",
+ info->liodn);
+ }
+ spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+
+ return 0;
+}
+
+static int fsl_pamu_set_domain_attr(struct iommu_domain *domain,
+ enum iommu_attr attr_type, void *data)
+{
+ struct fsl_dma_domain *dma_domain = domain->priv;
+ int ret = 0;
+
+
+ switch (attr_type) {
+ case DOMAIN_ATTR_GEOMETRY:
+ ret = configure_domain_geometry(domain, data);
+ break;
+ case DOMAIN_ATTR_FSL_PAMU_STASH:
+ ret = configure_domain_stash(dma_domain, data);
+ break;
+ case DOMAIN_ATTR_FSL_PAMU_ENABLE:
+ ret = configure_domain_dma_state(dma_domain, *(int *)data);
+ break;
+ default:
+ pr_debug("Unsupported attribute type\n");
+ ret = -EINVAL;
+ break;
+ };
+
+ return ret;
+}
+
+static int fsl_pamu_get_domain_attr(struct iommu_domain *domain,
+ enum iommu_attr attr_type, void *data)
+{
+ struct fsl_dma_domain *dma_domain = domain->priv;
+ int ret = 0;
+
+
+ switch (attr_type) {
+ case DOMAIN_ATTR_FSL_PAMU_STASH:
+ memcpy((struct pamu_stash_attribute *) data, &dma_domain->dma_stash,
+ sizeof(struct pamu_stash_attribute));
+ break;
+ case DOMAIN_ATTR_FSL_PAMU_ENABLE:
+ *(int *)data = dma_domain->enabled;
+ break;
+ case DOMAIN_ATTR_FSL_PAMUV1:
+ *(int *)data = DOMAIN_ATTR_FSL_PAMUV1;
+ break;
+ default:
+ pr_debug("Unsupported attribute type\n");
+ ret = -EINVAL;
+ break;
+ };
+
+ return ret;
+}
+
+#define REQ_ACS_FLAGS (PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF)
+
+static struct iommu_group *get_device_iommu_group(struct device *dev)
+{
+ struct iommu_group *group;
+
+ group = iommu_group_get(dev);
+ if (!group)
+ group = iommu_group_alloc();
+
+ return group;
+}
+
+static bool check_pci_ctl_endpt_part(struct pci_controller *pci_ctl)
+{
+ u32 version;
+
+ /* Check the PCI controller version number by readding BRR1 register */
+ version = in_be32(pci_ctl->cfg_addr + (PCI_FSL_BRR1 >> 2));
+ version &= PCI_FSL_BRR1_VER;
+ /* If PCI controller version is >= 0x204 we can partition endpoints*/
+ if (version >= 0x204)
+ return 1;
+
+ return 0;
+}
+
+/* Get iommu group information from peer devices or devices on the parent bus */
+static struct iommu_group *get_shared_pci_device_group(struct pci_dev *pdev)
+{
+ struct pci_dev *tmp;
+ struct iommu_group *group;
+ struct pci_bus *bus = pdev->bus;
+
+ /*
+ * Traverese the pci bus device list to get
+ * the shared iommu group.
+ */
+ while (bus) {
+ list_for_each_entry(tmp, &bus->devices, bus_list) {
+ if (tmp == pdev)
+ continue;
+ group = iommu_group_get(&tmp->dev);
+ if (group)
+ return group;
+ }
+
+ bus = bus->parent;
+ }
+
+ return NULL;
+}
+
+static struct iommu_group *get_pci_device_group(struct pci_dev *pdev)
+{
+ struct pci_controller *pci_ctl;
+ bool pci_endpt_partioning;
+ struct iommu_group *group = NULL;
+ struct pci_dev *bridge, *dma_pdev = NULL;
+
+ pci_ctl = pci_bus_to_host(pdev->bus);
+ pci_endpt_partioning = check_pci_ctl_endpt_part(pci_ctl);
+ /* We can partition PCIe devices so assign device group to the device */
+ if (pci_endpt_partioning) {
+ bridge = pci_find_upstream_pcie_bridge(pdev);
+ if (bridge) {
+ if (pci_is_pcie(bridge))
+ dma_pdev = pci_get_domain_bus_and_slot(
+ pci_domain_nr(pdev->bus),
+ bridge->subordinate->number, 0);
+ if (!dma_pdev)
+ dma_pdev = pci_dev_get(bridge);
+ } else
+ dma_pdev = pci_dev_get(pdev);
+
+ /* Account for quirked devices */
+ swap_pci_ref(&dma_pdev, pci_get_dma_source(dma_pdev));
+
+ /*
+ * If it's a multifunction device that does not support our
+ * required ACS flags, add to the same group as lowest numbered
+ * function that also does not suport the required ACS flags.
+ */
+ if (dma_pdev->multifunction &&
+ !pci_acs_enabled(dma_pdev, REQ_ACS_FLAGS)) {
+ u8 i, slot = PCI_SLOT(dma_pdev->devfn);
+
+ for (i = 0; i < 8; i++) {
+ struct pci_dev *tmp;
+
+ tmp = pci_get_slot(dma_pdev->bus, PCI_DEVFN(slot, i));
+ if (!tmp)
+ continue;
+
+ if (!pci_acs_enabled(tmp, REQ_ACS_FLAGS)) {
+ swap_pci_ref(&dma_pdev, tmp);
+ break;
+ }
+ pci_dev_put(tmp);
+ }
+ }
+
+ /*
+ * Devices on the root bus go through the iommu. If that's not us,
+ * find the next upstream device and test ACS up to the root bus.
+ * Finding the next device may require skipping virtual buses.
+ */
+ while (!pci_is_root_bus(dma_pdev->bus)) {
+ struct pci_bus *bus = dma_pdev->bus;
+
+ while (!bus->self) {
+ if (!pci_is_root_bus(bus))
+ bus = bus->parent;
+ else
+ goto root_bus;
+ }
+
+ if (pci_acs_path_enabled(bus->self, NULL, REQ_ACS_FLAGS))
+ break;
+
+ swap_pci_ref(&dma_pdev, pci_dev_get(bus->self));
+ }
+
+root_bus:
+ group = get_device_iommu_group(&dma_pdev->dev);
+ pci_dev_put(dma_pdev);
+ /*
+ * PCIe controller is not a paritionable entity
+ * free the controller device iommu_group.
+ */
+ if (pci_ctl->parent->iommu_group)
+ iommu_group_remove_device(pci_ctl->parent);
+ } else {
+ /*
+ * All devices connected to the controller will share the
+ * PCI controllers device group. If this is the first
+ * device to be probed for the pci controller, copy the
+ * device group information from the PCI controller device
+ * node and remove the PCI controller iommu group.
+ * For subsequent devices, the iommu group information can
+ * be obtained from sibling devices (i.e. from the bus_devices
+ * link list).
+ */
+ if (pci_ctl->parent->iommu_group) {
+ group = get_device_iommu_group(pci_ctl->parent);
+ iommu_group_remove_device(pci_ctl->parent);
+ } else
+ group = get_shared_pci_device_group(pdev);
+ }
+
+ return group;
+}
+
+static int fsl_pamu_add_device(struct device *dev)
+{
+ struct iommu_group *group = NULL;
+ struct pci_dev *pdev;
+ const u32 *prop;
+ int ret, len;
+
+ /*
+ * For platform devices we allocate a separate group for
+ * each of the devices.
+ */
+ if (dev->bus == &pci_bus_type) {
+ pdev = to_pci_dev(dev);
+ /* Don't create device groups for virtual PCI bridges */
+ if (pdev->subordinate)
+ return 0;
+
+ group = get_pci_device_group(pdev);
+
+ } else {
+ prop = of_get_property(dev->of_node, "fsl,liodn", &len);
+ if (prop)
+ group = get_device_iommu_group(dev);
+ }
+
+ if (!group || IS_ERR(group))
+ return PTR_ERR(group);
+
+ ret = iommu_group_add_device(group, dev);
+
+ iommu_group_put(group);
+ return ret;
+}
+
+static void fsl_pamu_remove_device(struct device *dev)
+{
+ iommu_group_remove_device(dev);
+}
+
+static int fsl_pamu_set_windows(struct iommu_domain *domain, u32 w_count)
+{
+ struct fsl_dma_domain *dma_domain = domain->priv;
+ unsigned long flags;
+ int ret;
+
+ spin_lock_irqsave(&dma_domain->domain_lock, flags);
+ /* Ensure domain is inactive i.e. DMA should be disabled for the domain */
+ if (dma_domain->enabled) {
+ pr_debug("Can't set geometry attributes as domain is active\n");
+ spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+ return -EBUSY;
+ }
+
+ /* Ensure that the geometry has been set for the domain */
+ if (!dma_domain->geom_size) {
+ pr_debug("Please configure geometry before setting the number of windows\n");
+ spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+ return -EINVAL;
+ }
+
+ /*
+ * Ensure we have valid window count i.e. it should be less than
+ * maximum permissible limit and should be a power of two.
+ */
+ if (w_count > pamu_get_max_subwin_cnt() || !is_power_of_2(w_count)) {
+ pr_debug("Invalid window count\n");
+ spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+ return -EINVAL;
+ }
+
+ ret = pamu_set_domain_geometry(dma_domain, &domain->geometry,
+ ((w_count > 1) ? w_count : 0));
+ if (!ret) {
+ if (dma_domain->win_arr)
+ kfree(dma_domain->win_arr);
+ dma_domain->win_arr = kzalloc(sizeof(struct dma_window) *
+ w_count, GFP_ATOMIC);
+ if (!dma_domain->win_arr) {
+ spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+ return -ENOMEM;
+ }
+ dma_domain->win_cnt = w_count;
+ }
+ spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+
+ return ret;
+}
+
+static u32 fsl_pamu_get_windows(struct iommu_domain *domain)
+{
+ struct fsl_dma_domain *dma_domain = domain->priv;
+
+ return dma_domain->win_cnt;
+}
+
+static struct iommu_ops fsl_pamu_ops = {
+ .domain_init = fsl_pamu_domain_init,
+ .domain_destroy = fsl_pamu_domain_destroy,
+ .attach_dev = fsl_pamu_attach_device,
+ .detach_dev = fsl_pamu_detach_device,
+ .domain_window_enable = fsl_pamu_window_enable,
+ .domain_window_disable = fsl_pamu_window_disable,
+ .domain_get_windows = fsl_pamu_get_windows,
+ .domain_set_windows = fsl_pamu_set_windows,
+ .iova_to_phys = fsl_pamu_iova_to_phys,
+ .domain_has_cap = fsl_pamu_domain_has_cap,
+ .domain_set_attr = fsl_pamu_set_domain_attr,
+ .domain_get_attr = fsl_pamu_get_domain_attr,
+ .add_device = fsl_pamu_add_device,
+ .remove_device = fsl_pamu_remove_device,
+};
+
+int pamu_domain_init()
+{
+ int ret = 0;
+
+ ret = iommu_init_mempool();
+ if (ret)
+ return ret;
+
+ bus_set_iommu(&platform_bus_type, &fsl_pamu_ops);
+ bus_set_iommu(&pci_bus_type, &fsl_pamu_ops);
+
+ return ret;
+}
diff --git a/drivers/iommu/fsl_pamu_domain.h b/drivers/iommu/fsl_pamu_domain.h
new file mode 100644
index 0000000..c90293f
--- /dev/null
+++ b/drivers/iommu/fsl_pamu_domain.h
@@ -0,0 +1,85 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ *
+ * Copyright (C) 2013 Freescale Semiconductor, Inc.
+ *
+ */
+
+#ifndef __FSL_PAMU_DOMAIN_H
+#define __FSL_PAMU_DOMAIN_H
+
+#include "fsl_pamu.h"
+
+struct dma_window {
+ phys_addr_t paddr;
+ u64 size;
+ int valid;
+ int prot;
+};
+
+struct fsl_dma_domain {
+ /*
+ * Indicates the geometry size for the domain.
+ * This would be set when the geometry is
+ * configured for the domain.
+ */
+ dma_addr_t geom_size;
+ /*
+ * Number of windows assocaited with this domain.
+ * During domain initialization, it is set to the
+ * the maximum number of subwindows allowed for a LIODN.
+ * Minimum value for this is 1 indicating a single PAMU
+ * window, without any sub windows. Value can be set/
+ * queried by set_attr/get_attr API for DOMAIN_ATTR_WINDOWS.
+ * Value can only be set once the geometry has been configured.
+ */
+ u32 win_cnt;
+ /*
+ * win_arr contains information of the configured
+ * windows for a domain. This is allocated only
+ * when the number of windows for the domain are
+ * set.
+ */
+ struct dma_window *win_arr;
+ /* list of devices associated with the domain */
+ struct list_head devices;
+ /* dma_domain states:
+ * mapped - A particular mapping has been created
+ * within the configured geometry.
+ * enabled - DMA has been enabled for the given
+ * domain. This translates to setting of the
+ * valid bit for the primary PAACE in the PAMU
+ * PAACT table. Domain geometry should be set and
+ * it must have a valid mapping before DMA can be
+ * enabled for it.
+ *
+ */
+ int mapped;
+ int enabled;
+ /* stash_id obtained from the stash attribute details */
+ u32 stash_id;
+ struct pamu_stash_attribute dma_stash;
+ u32 snoop_id;
+ struct iommu_domain *iommu_domain;
+ spinlock_t domain_lock;
+};
+
+/* domain-device relationship */
+struct device_domain_info {
+ struct list_head link; /* link to domain siblings */
+ struct device *dev;
+ u32 liodn;
+ struct fsl_dma_domain *domain; /* pointer to domain */
+};
+#endif /* __FSL_PAMU_DOMAIN_H */
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index eec0d3e..15e9b57 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -890,56 +890,54 @@
return order;
}
+static void dma_pte_free_level(struct dmar_domain *domain, int level,
+ struct dma_pte *pte, unsigned long pfn,
+ unsigned long start_pfn, unsigned long last_pfn)
+{
+ pfn = max(start_pfn, pfn);
+ pte = &pte[pfn_level_offset(pfn, level)];
+
+ do {
+ unsigned long level_pfn;
+ struct dma_pte *level_pte;
+
+ if (!dma_pte_present(pte) || dma_pte_superpage(pte))
+ goto next;
+
+ level_pfn = pfn & level_mask(level - 1);
+ level_pte = phys_to_virt(dma_pte_addr(pte));
+
+ if (level > 2)
+ dma_pte_free_level(domain, level - 1, level_pte,
+ level_pfn, start_pfn, last_pfn);
+
+ /* If range covers entire pagetable, free it */
+ if (!(start_pfn > level_pfn ||
+ last_pfn < level_pfn + level_size(level))) {
+ dma_clear_pte(pte);
+ domain_flush_cache(domain, pte, sizeof(*pte));
+ free_pgtable_page(level_pte);
+ }
+next:
+ pfn += level_size(level);
+ } while (!first_pte_in_page(++pte) && pfn <= last_pfn);
+}
+
/* free page table pages. last level pte should already be cleared */
static void dma_pte_free_pagetable(struct dmar_domain *domain,
unsigned long start_pfn,
unsigned long last_pfn)
{
int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
- struct dma_pte *first_pte, *pte;
- int total = agaw_to_level(domain->agaw);
- int level;
- unsigned long tmp;
- int large_page = 2;
BUG_ON(addr_width < BITS_PER_LONG && start_pfn >> addr_width);
BUG_ON(addr_width < BITS_PER_LONG && last_pfn >> addr_width);
BUG_ON(start_pfn > last_pfn);
/* We don't need lock here; nobody else touches the iova range */
- level = 2;
- while (level <= total) {
- tmp = align_to_level(start_pfn, level);
+ dma_pte_free_level(domain, agaw_to_level(domain->agaw),
+ domain->pgd, 0, start_pfn, last_pfn);
- /* If we can't even clear one PTE at this level, we're done */
- if (tmp + level_size(level) - 1 > last_pfn)
- return;
-
- do {
- large_page = level;
- first_pte = pte = dma_pfn_level_pte(domain, tmp, level, &large_page);
- if (large_page > level)
- level = large_page + 1;
- if (!pte) {
- tmp = align_to_level(tmp + 1, level + 1);
- continue;
- }
- do {
- if (dma_pte_present(pte)) {
- free_pgtable_page(phys_to_virt(dma_pte_addr(pte)));
- dma_clear_pte(pte);
- }
- pte++;
- tmp += level_size(level);
- } while (!first_pte_in_page(pte) &&
- tmp + level_size(level) - 1 <= last_pfn);
-
- domain_flush_cache(domain, first_pte,
- (void *)pte - (void *)first_pte);
-
- } while (tmp && tmp + level_size(level) - 1 <= last_pfn);
- level++;
- }
/* free pgd */
if (start_pfn == 0 && last_pfn == DOMAIN_MAX_PFN(domain->gaw)) {
free_pgtable_page(domain->pgd);
diff --git a/drivers/iommu/msm_iommu_dev.c b/drivers/iommu/msm_iommu_dev.c
index 0a1c962..08ba497 100644
--- a/drivers/iommu/msm_iommu_dev.c
+++ b/drivers/iommu/msm_iommu_dev.c
@@ -282,7 +282,6 @@
clk_put(drv->pclk);
memset(drv, 0, sizeof(*drv));
kfree(drv);
- platform_set_drvdata(pdev, NULL);
}
return 0;
}
@@ -366,7 +365,6 @@
if (drv) {
memset(drv, 0, sizeof(struct msm_iommu_ctx_drvdata));
kfree(drv);
- platform_set_drvdata(pdev, NULL);
}
return 0;
}
diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c
index 0ba3766..bcd78a7 100644
--- a/drivers/iommu/omap-iommu.c
+++ b/drivers/iommu/omap-iommu.c
@@ -1008,8 +1008,6 @@
struct resource *res;
struct omap_iommu *obj = platform_get_drvdata(pdev);
- platform_set_drvdata(pdev, NULL);
-
iopgtable_clear_entry_all(obj);
irq = platform_get_irq(pdev, 0);
diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index 074bcb3..875bbe4 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -194,11 +194,11 @@
module will be called leds-lp3944.
config LEDS_LP55XX_COMMON
- tristate "Common Driver for TI/National LP5521, LP5523/55231 and LP5562"
- depends on LEDS_LP5521 || LEDS_LP5523 || LEDS_LP5562
+ tristate "Common Driver for TI/National LP5521/5523/55231/5562/8501"
+ depends on LEDS_LP5521 || LEDS_LP5523 || LEDS_LP5562 || LEDS_LP8501
select FW_LOADER
help
- This option supports common operations for LP5521 and LP5523/55231
+ This option supports common operations for LP5521/5523/55231/5562/8501
devices.
config LEDS_LP5521
@@ -232,6 +232,18 @@
Driver provides direct control via LED class and interface for
programming the engines.
+config LEDS_LP8501
+ tristate "LED Support for TI LP8501 LED driver chip"
+ depends on LEDS_CLASS && I2C
+ select LEDS_LP55XX_COMMON
+ help
+ If you say yes here you get support for TI LP8501 LED driver.
+ It is 9 channel chip with programmable engines.
+ Driver provides direct control via LED class and interface for
+ programming the engines.
+ It is similar as LP5523, but output power selection is available.
+ And register layout and engine program schemes are different.
+
config LEDS_LP8788
tristate "LED support for the TI LP8788 PMIC"
depends on LEDS_CLASS
@@ -279,13 +291,14 @@
LED driver chips accessed via the I2C bus. Supported
devices include PCA9550, PCA9551, PCA9552, and PCA9553.
-config LEDS_PCA9633
- tristate "LED support for PCA9633 I2C chip"
+config LEDS_PCA963X
+ tristate "LED support for PCA963x I2C chip"
depends on LEDS_CLASS
depends on I2C
help
- This option enables support for LEDs connected to the PCA9633
- LED driver chip accessed via the I2C bus.
+ This option enables support for LEDs connected to the PCA963x
+ LED driver chip accessed via the I2C bus. Supported
+ devices include PCA9633 and PCA9634
config LEDS_WM831X_STATUS
tristate "LED support for status LEDs on WM831x PMICs"
@@ -398,10 +411,7 @@
config LEDS_NS2
tristate "LED support for Network Space v2 GPIO LEDs"
depends on LEDS_CLASS
- depends on MACH_NETSPACE_V2 || MACH_INETSPACE_V2 || \
- MACH_NETSPACE_MAX_V2 || MACH_D2NET_V2 || \
- MACH_NETSPACE_V2_DT || MACH_INETSPACE_V2_DT || \
- MACH_NETSPACE_MAX_V2_DT || MACH_NETSPACE_MINI_V2_DT
+ depends on ARCH_KIRKWOOD
default y
help
This option enable support for the dual-GPIO LED found on the
@@ -410,8 +420,8 @@
config LEDS_NETXBIG
tristate "LED support for Big Network series LEDs"
- depends on MACH_NET2BIG_V2 || MACH_NET5BIG_V2
depends on LEDS_CLASS
+ depends on ARCH_KIRKWOOD
default y
help
This option enable support for LEDs found on the LaCie 2Big
diff --git a/drivers/leds/Makefile b/drivers/leds/Makefile
index ae4b613..8979b0b 100644
--- a/drivers/leds/Makefile
+++ b/drivers/leds/Makefile
@@ -27,6 +27,7 @@
obj-$(CONFIG_LEDS_LP5521) += leds-lp5521.o
obj-$(CONFIG_LEDS_LP5523) += leds-lp5523.o
obj-$(CONFIG_LEDS_LP5562) += leds-lp5562.o
+obj-$(CONFIG_LEDS_LP8501) += leds-lp8501.o
obj-$(CONFIG_LEDS_LP8788) += leds-lp8788.o
obj-$(CONFIG_LEDS_TCA6507) += leds-tca6507.o
obj-$(CONFIG_LEDS_CLEVO_MAIL) += leds-clevo-mail.o
@@ -34,7 +35,7 @@
obj-$(CONFIG_LEDS_OT200) += leds-ot200.o
obj-$(CONFIG_LEDS_FSG) += leds-fsg.o
obj-$(CONFIG_LEDS_PCA955X) += leds-pca955x.o
-obj-$(CONFIG_LEDS_PCA9633) += leds-pca9633.o
+obj-$(CONFIG_LEDS_PCA963X) += leds-pca963x.o
obj-$(CONFIG_LEDS_DA903X) += leds-da903x.o
obj-$(CONFIG_LEDS_DA9052) += leds-da9052.o
obj-$(CONFIG_LEDS_WM831X_STATUS) += leds-wm831x-status.o
diff --git a/drivers/leds/leds-88pm860x.c b/drivers/leds/leds-88pm860x.c
index 232b3ce..5f588c0 100644
--- a/drivers/leds/leds-88pm860x.c
+++ b/drivers/leds/leds-88pm860x.c
@@ -157,7 +157,7 @@
static int pm860x_led_probe(struct platform_device *pdev)
{
struct pm860x_chip *chip = dev_get_drvdata(pdev->dev.parent);
- struct pm860x_led_pdata *pdata = pdev->dev.platform_data;
+ struct pm860x_led_pdata *pdata = dev_get_platdata(&pdev->dev);
struct pm860x_led *data;
struct resource *res;
int ret = 0;
diff --git a/drivers/leds/leds-adp5520.c b/drivers/leds/leds-adp5520.c
index e8072ab..7e311a1 100644
--- a/drivers/leds/leds-adp5520.c
+++ b/drivers/leds/leds-adp5520.c
@@ -87,7 +87,7 @@
static int adp5520_led_prepare(struct platform_device *pdev)
{
- struct adp5520_leds_platform_data *pdata = pdev->dev.platform_data;
+ struct adp5520_leds_platform_data *pdata = dev_get_platdata(&pdev->dev);
struct device *dev = pdev->dev.parent;
int ret = 0;
@@ -103,7 +103,7 @@
static int adp5520_led_probe(struct platform_device *pdev)
{
- struct adp5520_leds_platform_data *pdata = pdev->dev.platform_data;
+ struct adp5520_leds_platform_data *pdata = dev_get_platdata(&pdev->dev);
struct adp5520_led *led, *led_dat;
struct led_info *cur_led;
int ret, i;
@@ -185,7 +185,7 @@
static int adp5520_led_remove(struct platform_device *pdev)
{
- struct adp5520_leds_platform_data *pdata = pdev->dev.platform_data;
+ struct adp5520_leds_platform_data *pdata = dev_get_platdata(&pdev->dev);
struct adp5520_led *led;
int i;
diff --git a/drivers/leds/leds-asic3.c b/drivers/leds/leds-asic3.c
index cf9efe4..6de216a 100644
--- a/drivers/leds/leds-asic3.c
+++ b/drivers/leds/leds-asic3.c
@@ -94,7 +94,7 @@
static int asic3_led_probe(struct platform_device *pdev)
{
- struct asic3_led *led = pdev->dev.platform_data;
+ struct asic3_led *led = dev_get_platdata(&pdev->dev);
int ret;
ret = mfd_cell_enable(pdev);
@@ -127,7 +127,7 @@
static int asic3_led_remove(struct platform_device *pdev)
{
- struct asic3_led *led = pdev->dev.platform_data;
+ struct asic3_led *led = dev_get_platdata(&pdev->dev);
led_classdev_unregister(led->cdev);
diff --git a/drivers/leds/leds-atmel-pwm.c b/drivers/leds/leds-atmel-pwm.c
index 90518f8..56cec8d 100644
--- a/drivers/leds/leds-atmel-pwm.c
+++ b/drivers/leds/leds-atmel-pwm.c
@@ -42,7 +42,7 @@
int i;
int status;
- pdata = pdev->dev.platform_data;
+ pdata = dev_get_platdata(&pdev->dev);
if (!pdata || pdata->num_leds < 1)
return -ENODEV;
@@ -119,7 +119,7 @@
struct pwmled *leds;
unsigned i;
- pdata = pdev->dev.platform_data;
+ pdata = dev_get_platdata(&pdev->dev);
leds = platform_get_drvdata(pdev);
for (i = 0; i < pdata->num_leds; i++) {
diff --git a/drivers/leds/leds-bd2802.c b/drivers/leds/leds-bd2802.c
index 2db0423..fb5a347 100644
--- a/drivers/leds/leds-bd2802.c
+++ b/drivers/leds/leds-bd2802.c
@@ -684,7 +684,7 @@
}
led->client = client;
- pdata = led->pdata = client->dev.platform_data;
+ pdata = led->pdata = dev_get_platdata(&client->dev);
i2c_set_clientdata(client, led);
/* Configure RESET GPIO (L: RESET, H: RESET cancel) */
diff --git a/drivers/leds/leds-clevo-mail.c b/drivers/leds/leds-clevo-mail.c
index 6a8405d..d93e245 100644
--- a/drivers/leds/leds-clevo-mail.c
+++ b/drivers/leds/leds-clevo-mail.c
@@ -40,7 +40,7 @@
* detected as working, but in reality it is not) as low as
* possible.
*/
-static struct dmi_system_id __initdata clevo_mail_led_dmi_table[] = {
+static struct dmi_system_id clevo_mail_led_dmi_table[] __initdata = {
{
.callback = clevo_mail_led_dmi_callback,
.ident = "Clevo D410J",
diff --git a/drivers/leds/leds-da903x.c b/drivers/leds/leds-da903x.c
index c263a21..2a4b87f 100644
--- a/drivers/leds/leds-da903x.c
+++ b/drivers/leds/leds-da903x.c
@@ -93,7 +93,7 @@
static int da903x_led_probe(struct platform_device *pdev)
{
- struct led_info *pdata = pdev->dev.platform_data;
+ struct led_info *pdata = dev_get_platdata(&pdev->dev);
struct da903x_led *led;
int id, ret;
diff --git a/drivers/leds/leds-da9052.c b/drivers/leds/leds-da9052.c
index efec433..865d4fa 100644
--- a/drivers/leds/leds-da9052.c
+++ b/drivers/leds/leds-da9052.c
@@ -112,7 +112,7 @@
int i;
da9052 = dev_get_drvdata(pdev->dev.parent);
- pdata = da9052->dev->platform_data;
+ pdata = dev_get_platdata(da9052->dev);
if (pdata == NULL) {
dev_err(&pdev->dev, "No platform data\n");
goto err;
@@ -185,7 +185,7 @@
int i;
da9052 = dev_get_drvdata(pdev->dev.parent);
- pdata = da9052->dev->platform_data;
+ pdata = dev_get_platdata(da9052->dev);
pled = pdata->pled;
for (i = 0; i < pled->num_leds; i++) {
diff --git a/drivers/leds/leds-gpio.c b/drivers/leds/leds-gpio.c
index 84d74c37..e8b01e5 100644
--- a/drivers/leds/leds-gpio.c
+++ b/drivers/leds/leds-gpio.c
@@ -233,7 +233,7 @@
static int gpio_led_probe(struct platform_device *pdev)
{
- struct gpio_led_platform_data *pdata = pdev->dev.platform_data;
+ struct gpio_led_platform_data *pdata = dev_get_platdata(&pdev->dev);
struct gpio_leds_priv *priv;
int i, ret = 0;
diff --git a/drivers/leds/leds-lm3530.c b/drivers/leds/leds-lm3530.c
index a036a19..652368c 100644
--- a/drivers/leds/leds-lm3530.c
+++ b/drivers/leds/leds-lm3530.c
@@ -403,7 +403,7 @@
static int lm3530_probe(struct i2c_client *client,
const struct i2c_device_id *id)
{
- struct lm3530_platform_data *pdata = client->dev.platform_data;
+ struct lm3530_platform_data *pdata = dev_get_platdata(&client->dev);
struct lm3530_data *drvdata;
int err = 0;
diff --git a/drivers/leds/leds-lm3533.c b/drivers/leds/leds-lm3533.c
index bbf24d0..027ede7 100644
--- a/drivers/leds/leds-lm3533.c
+++ b/drivers/leds/leds-lm3533.c
@@ -671,7 +671,7 @@
if (!lm3533)
return -EINVAL;
- pdata = pdev->dev.platform_data;
+ pdata = dev_get_platdata(&pdev->dev);
if (!pdata) {
dev_err(&pdev->dev, "no platform data\n");
return -EINVAL;
diff --git a/drivers/leds/leds-lm355x.c b/drivers/leds/leds-lm355x.c
index d81a8e7..591eb5e 100644
--- a/drivers/leds/leds-lm355x.c
+++ b/drivers/leds/leds-lm355x.c
@@ -423,7 +423,7 @@
static int lm355x_probe(struct i2c_client *client,
const struct i2c_device_id *id)
{
- struct lm355x_platform_data *pdata = client->dev.platform_data;
+ struct lm355x_platform_data *pdata = dev_get_platdata(&client->dev);
struct lm355x_chip_data *chip;
int err;
diff --git a/drivers/leds/leds-lm3642.c b/drivers/leds/leds-lm3642.c
index f361bbe..ceb6b3c 100644
--- a/drivers/leds/leds-lm3642.c
+++ b/drivers/leds/leds-lm3642.c
@@ -316,7 +316,7 @@
static int lm3642_probe(struct i2c_client *client,
const struct i2c_device_id *id)
{
- struct lm3642_platform_data *pdata = client->dev.platform_data;
+ struct lm3642_platform_data *pdata = dev_get_platdata(&client->dev);
struct lm3642_chip_data *chip;
int err;
diff --git a/drivers/leds/leds-lp3944.c b/drivers/leds/leds-lp3944.c
index 0c4386e6..8e1abdc 100644
--- a/drivers/leds/leds-lp3944.c
+++ b/drivers/leds/leds-lp3944.c
@@ -289,7 +289,7 @@
dev_dbg(&led->client->dev, "%s: %s, %d\n",
__func__, led_cdev->name, brightness);
- led->status = brightness;
+ led->status = !!brightness;
schedule_work(&led->work);
}
@@ -377,7 +377,8 @@
static int lp3944_probe(struct i2c_client *client,
const struct i2c_device_id *id)
{
- struct lp3944_platform_data *lp3944_pdata = client->dev.platform_data;
+ struct lp3944_platform_data *lp3944_pdata =
+ dev_get_platdata(&client->dev);
struct lp3944_data *data;
int err;
@@ -413,7 +414,7 @@
static int lp3944_remove(struct i2c_client *client)
{
- struct lp3944_platform_data *pdata = client->dev.platform_data;
+ struct lp3944_platform_data *pdata = dev_get_platdata(&client->dev);
struct lp3944_data *data = i2c_get_clientdata(client);
int i;
diff --git a/drivers/leds/leds-lp5521.c b/drivers/leds/leds-lp5521.c
index 1392feb..0518835 100644
--- a/drivers/leds/leds-lp5521.c
+++ b/drivers/leds/leds-lp5521.c
@@ -220,17 +220,11 @@
};
unsigned cmd;
char c[3];
- int program_size;
int nrchars;
- int offset = 0;
int ret;
- int i;
+ int offset = 0;
+ int i = 0;
- /* clear program memory before updating */
- for (i = 0; i < LP5521_PROGRAM_LENGTH; i++)
- lp55xx_write(chip, addr[idx] + i, 0);
-
- i = 0;
while ((offset < size - 1) && (i < LP5521_PROGRAM_LENGTH)) {
/* separate sscanfs because length is working only for %s */
ret = sscanf(data + offset, "%2s%n ", c, &nrchars);
@@ -250,11 +244,19 @@
if (i % 2)
goto err;
- program_size = i;
- for (i = 0; i < program_size; i++)
- lp55xx_write(chip, addr[idx] + i, pattern[i]);
+ mutex_lock(&chip->lock);
- return 0;
+ for (i = 0; i < LP5521_PROGRAM_LENGTH; i++) {
+ ret = lp55xx_write(chip, addr[idx] + i, pattern[i]);
+ if (ret) {
+ mutex_unlock(&chip->lock);
+ return -EINVAL;
+ }
+ }
+
+ mutex_unlock(&chip->lock);
+
+ return size;
err:
dev_err(&chip->cl->dev, "wrong pattern format\n");
@@ -365,6 +367,80 @@
mutex_unlock(&chip->lock);
}
+static ssize_t show_engine_mode(struct device *dev,
+ struct device_attribute *attr,
+ char *buf, int nr)
+{
+ struct lp55xx_led *led = i2c_get_clientdata(to_i2c_client(dev));
+ struct lp55xx_chip *chip = led->chip;
+ enum lp55xx_engine_mode mode = chip->engines[nr - 1].mode;
+
+ switch (mode) {
+ case LP55XX_ENGINE_RUN:
+ return sprintf(buf, "run\n");
+ case LP55XX_ENGINE_LOAD:
+ return sprintf(buf, "load\n");
+ case LP55XX_ENGINE_DISABLED:
+ default:
+ return sprintf(buf, "disabled\n");
+ }
+}
+show_mode(1)
+show_mode(2)
+show_mode(3)
+
+static ssize_t store_engine_mode(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t len, int nr)
+{
+ struct lp55xx_led *led = i2c_get_clientdata(to_i2c_client(dev));
+ struct lp55xx_chip *chip = led->chip;
+ struct lp55xx_engine *engine = &chip->engines[nr - 1];
+
+ mutex_lock(&chip->lock);
+
+ chip->engine_idx = nr;
+
+ if (!strncmp(buf, "run", 3)) {
+ lp5521_run_engine(chip, true);
+ engine->mode = LP55XX_ENGINE_RUN;
+ } else if (!strncmp(buf, "load", 4)) {
+ lp5521_stop_engine(chip);
+ lp5521_load_engine(chip);
+ engine->mode = LP55XX_ENGINE_LOAD;
+ } else if (!strncmp(buf, "disabled", 8)) {
+ lp5521_stop_engine(chip);
+ engine->mode = LP55XX_ENGINE_DISABLED;
+ }
+
+ mutex_unlock(&chip->lock);
+
+ return len;
+}
+store_mode(1)
+store_mode(2)
+store_mode(3)
+
+static ssize_t store_engine_load(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t len, int nr)
+{
+ struct lp55xx_led *led = i2c_get_clientdata(to_i2c_client(dev));
+ struct lp55xx_chip *chip = led->chip;
+
+ mutex_lock(&chip->lock);
+
+ chip->engine_idx = nr;
+ lp5521_load_engine(chip);
+
+ mutex_unlock(&chip->lock);
+
+ return lp5521_update_program_memory(chip, buf, len);
+}
+store_load(1)
+store_load(2)
+store_load(3)
+
static ssize_t lp5521_selftest(struct device *dev,
struct device_attribute *attr,
char *buf)
@@ -381,9 +457,21 @@
}
/* device attributes */
-static DEVICE_ATTR(selftest, S_IRUGO, lp5521_selftest, NULL);
+static LP55XX_DEV_ATTR_RW(engine1_mode, show_engine1_mode, store_engine1_mode);
+static LP55XX_DEV_ATTR_RW(engine2_mode, show_engine2_mode, store_engine2_mode);
+static LP55XX_DEV_ATTR_RW(engine3_mode, show_engine3_mode, store_engine3_mode);
+static LP55XX_DEV_ATTR_WO(engine1_load, store_engine1_load);
+static LP55XX_DEV_ATTR_WO(engine2_load, store_engine2_load);
+static LP55XX_DEV_ATTR_WO(engine3_load, store_engine3_load);
+static LP55XX_DEV_ATTR_RO(selftest, lp5521_selftest);
static struct attribute *lp5521_attributes[] = {
+ &dev_attr_engine1_mode.attr,
+ &dev_attr_engine2_mode.attr,
+ &dev_attr_engine3_mode.attr,
+ &dev_attr_engine1_load.attr,
+ &dev_attr_engine2_load.attr,
+ &dev_attr_engine3_load.attr,
&dev_attr_selftest.attr,
NULL
};
@@ -420,7 +508,7 @@
struct lp55xx_platform_data *pdata;
struct device_node *np = client->dev.of_node;
- if (!client->dev.platform_data) {
+ if (!dev_get_platdata(&client->dev)) {
if (np) {
ret = lp55xx_of_populate_pdata(&client->dev, np);
if (ret < 0)
@@ -430,7 +518,7 @@
return -EINVAL;
}
}
- pdata = client->dev.platform_data;
+ pdata = dev_get_platdata(&client->dev);
chip = devm_kzalloc(&client->dev, sizeof(*chip), GFP_KERNEL);
if (!chip)
diff --git a/drivers/leds/leds-lp5523.c b/drivers/leds/leds-lp5523.c
index 3979428..fe3bcbb 100644
--- a/drivers/leds/leds-lp5523.c
+++ b/drivers/leds/leds-lp5523.c
@@ -49,6 +49,9 @@
#define LP5523_REG_RESET 0x3D
#define LP5523_REG_LED_TEST_CTRL 0x41
#define LP5523_REG_LED_TEST_ADC 0x42
+#define LP5523_REG_CH1_PROG_START 0x4C
+#define LP5523_REG_CH2_PROG_START 0x4D
+#define LP5523_REG_CH3_PROG_START 0x4E
#define LP5523_REG_PROG_PAGE_SEL 0x4F
#define LP5523_REG_PROG_MEM 0x50
@@ -65,11 +68,15 @@
#define LP5523_RESET 0xFF
#define LP5523_ADC_SHORTCIRC_LIM 80
#define LP5523_EXT_CLK_USED 0x08
+#define LP5523_ENG_STATUS_MASK 0x07
/* Memory Page Selection */
#define LP5523_PAGE_ENG1 0
#define LP5523_PAGE_ENG2 1
#define LP5523_PAGE_ENG3 2
+#define LP5523_PAGE_MUX1 3
+#define LP5523_PAGE_MUX2 4
+#define LP5523_PAGE_MUX3 5
/* Program Memory Operations */
#define LP5523_MODE_ENG1_M 0x30 /* Operation Mode Register */
@@ -94,11 +101,15 @@
#define LP5523_RUN_ENG2 0x08
#define LP5523_RUN_ENG3 0x02
+#define LED_ACTIVE(mux, led) (!!(mux & (0x0001 << led)))
+
enum lp5523_chip_id {
LP5523,
LP55231,
};
+static int lp5523_init_program_engine(struct lp55xx_chip *chip);
+
static inline void lp5523_wait_opmode_done(void)
{
usleep_range(1000, 2000);
@@ -134,7 +145,11 @@
if (ret)
return ret;
- return lp55xx_write(chip, LP5523_REG_ENABLE_LEDS_LSB, 0xff);
+ ret = lp55xx_write(chip, LP5523_REG_ENABLE_LEDS_LSB, 0xff);
+ if (ret)
+ return ret;
+
+ return lp5523_init_program_engine(chip);
}
static void lp5523_load_engine(struct lp55xx_chip *chip)
@@ -152,15 +167,21 @@
[LP55XX_ENGINE_3] = LP5523_LOAD_ENG3,
};
+ lp55xx_update_bits(chip, LP5523_REG_OP_MODE, mask[idx], val[idx]);
+
+ lp5523_wait_opmode_done();
+}
+
+static void lp5523_load_engine_and_select_page(struct lp55xx_chip *chip)
+{
+ enum lp55xx_engine_index idx = chip->engine_idx;
u8 page_sel[] = {
[LP55XX_ENGINE_1] = LP5523_PAGE_ENG1,
[LP55XX_ENGINE_2] = LP5523_PAGE_ENG2,
[LP55XX_ENGINE_3] = LP5523_PAGE_ENG3,
};
- lp55xx_update_bits(chip, LP5523_REG_OP_MODE, mask[idx], val[idx]);
-
- lp5523_wait_opmode_done();
+ lp5523_load_engine(chip);
lp55xx_write(chip, LP5523_REG_PROG_PAGE_SEL, page_sel[idx]);
}
@@ -227,23 +248,75 @@
lp55xx_update_bits(chip, LP5523_REG_ENABLE, LP5523_EXEC_M, exec);
}
+static int lp5523_init_program_engine(struct lp55xx_chip *chip)
+{
+ int i;
+ int j;
+ int ret;
+ u8 status;
+ /* one pattern per engine setting LED MUX start and stop addresses */
+ static const u8 pattern[][LP5523_PROGRAM_LENGTH] = {
+ { 0x9c, 0x30, 0x9c, 0xb0, 0x9d, 0x80, 0xd8, 0x00, 0},
+ { 0x9c, 0x40, 0x9c, 0xc0, 0x9d, 0x80, 0xd8, 0x00, 0},
+ { 0x9c, 0x50, 0x9c, 0xd0, 0x9d, 0x80, 0xd8, 0x00, 0},
+ };
+
+ /* hardcode 32 bytes of memory for each engine from program memory */
+ ret = lp55xx_write(chip, LP5523_REG_CH1_PROG_START, 0x00);
+ if (ret)
+ return ret;
+
+ ret = lp55xx_write(chip, LP5523_REG_CH2_PROG_START, 0x10);
+ if (ret)
+ return ret;
+
+ ret = lp55xx_write(chip, LP5523_REG_CH3_PROG_START, 0x20);
+ if (ret)
+ return ret;
+
+ /* write LED MUX address space for each engine */
+ for (i = LP55XX_ENGINE_1; i <= LP55XX_ENGINE_3; i++) {
+ chip->engine_idx = i;
+ lp5523_load_engine_and_select_page(chip);
+
+ for (j = 0; j < LP5523_PROGRAM_LENGTH; j++) {
+ ret = lp55xx_write(chip, LP5523_REG_PROG_MEM + j,
+ pattern[i - 1][j]);
+ if (ret)
+ goto out;
+ }
+ }
+
+ lp5523_run_engine(chip, true);
+
+ /* Let the programs run for couple of ms and check the engine status */
+ usleep_range(3000, 6000);
+ lp55xx_read(chip, LP5523_REG_STATUS, &status);
+ status &= LP5523_ENG_STATUS_MASK;
+
+ if (status != LP5523_ENG_STATUS_MASK) {
+ dev_err(&chip->cl->dev,
+ "cound not configure LED engine, status = 0x%.2x\n",
+ status);
+ ret = -1;
+ }
+
+out:
+ lp5523_stop_engine(chip);
+ return ret;
+}
+
static int lp5523_update_program_memory(struct lp55xx_chip *chip,
const u8 *data, size_t size)
{
u8 pattern[LP5523_PROGRAM_LENGTH] = {0};
unsigned cmd;
char c[3];
- int update_size;
int nrchars;
- int offset = 0;
int ret;
- int i;
+ int offset = 0;
+ int i = 0;
- /* clear program memory before updating */
- for (i = 0; i < LP5523_PROGRAM_LENGTH; i++)
- lp55xx_write(chip, LP5523_REG_PROG_MEM + i, 0);
-
- i = 0;
while ((offset < size - 1) && (i < LP5523_PROGRAM_LENGTH)) {
/* separate sscanfs because length is working only for %s */
ret = sscanf(data + offset, "%2s%n ", c, &nrchars);
@@ -263,11 +336,19 @@
if (i % 2)
goto err;
- update_size = i;
- for (i = 0; i < update_size; i++)
- lp55xx_write(chip, LP5523_REG_PROG_MEM + i, pattern[i]);
+ mutex_lock(&chip->lock);
- return 0;
+ for (i = 0; i < LP5523_PROGRAM_LENGTH; i++) {
+ ret = lp55xx_write(chip, LP5523_REG_PROG_MEM + i, pattern[i]);
+ if (ret) {
+ mutex_unlock(&chip->lock);
+ return -EINVAL;
+ }
+ }
+
+ mutex_unlock(&chip->lock);
+
+ return size;
err:
dev_err(&chip->cl->dev, "wrong pattern format\n");
@@ -290,10 +371,196 @@
* 2) write firmware data into program memory
*/
- lp5523_load_engine(chip);
+ lp5523_load_engine_and_select_page(chip);
lp5523_update_program_memory(chip, fw->data, fw->size);
}
+static ssize_t show_engine_mode(struct device *dev,
+ struct device_attribute *attr,
+ char *buf, int nr)
+{
+ struct lp55xx_led *led = i2c_get_clientdata(to_i2c_client(dev));
+ struct lp55xx_chip *chip = led->chip;
+ enum lp55xx_engine_mode mode = chip->engines[nr - 1].mode;
+
+ switch (mode) {
+ case LP55XX_ENGINE_RUN:
+ return sprintf(buf, "run\n");
+ case LP55XX_ENGINE_LOAD:
+ return sprintf(buf, "load\n");
+ case LP55XX_ENGINE_DISABLED:
+ default:
+ return sprintf(buf, "disabled\n");
+ }
+}
+show_mode(1)
+show_mode(2)
+show_mode(3)
+
+static ssize_t store_engine_mode(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t len, int nr)
+{
+ struct lp55xx_led *led = i2c_get_clientdata(to_i2c_client(dev));
+ struct lp55xx_chip *chip = led->chip;
+ struct lp55xx_engine *engine = &chip->engines[nr - 1];
+
+ mutex_lock(&chip->lock);
+
+ chip->engine_idx = nr;
+
+ if (!strncmp(buf, "run", 3)) {
+ lp5523_run_engine(chip, true);
+ engine->mode = LP55XX_ENGINE_RUN;
+ } else if (!strncmp(buf, "load", 4)) {
+ lp5523_stop_engine(chip);
+ lp5523_load_engine(chip);
+ engine->mode = LP55XX_ENGINE_LOAD;
+ } else if (!strncmp(buf, "disabled", 8)) {
+ lp5523_stop_engine(chip);
+ engine->mode = LP55XX_ENGINE_DISABLED;
+ }
+
+ mutex_unlock(&chip->lock);
+
+ return len;
+}
+store_mode(1)
+store_mode(2)
+store_mode(3)
+
+static int lp5523_mux_parse(const char *buf, u16 *mux, size_t len)
+{
+ u16 tmp_mux = 0;
+ int i;
+
+ len = min_t(int, len, LP5523_MAX_LEDS);
+
+ for (i = 0; i < len; i++) {
+ switch (buf[i]) {
+ case '1':
+ tmp_mux |= (1 << i);
+ break;
+ case '0':
+ break;
+ case '\n':
+ i = len;
+ break;
+ default:
+ return -1;
+ }
+ }
+ *mux = tmp_mux;
+
+ return 0;
+}
+
+static void lp5523_mux_to_array(u16 led_mux, char *array)
+{
+ int i, pos = 0;
+ for (i = 0; i < LP5523_MAX_LEDS; i++)
+ pos += sprintf(array + pos, "%x", LED_ACTIVE(led_mux, i));
+
+ array[pos] = '\0';
+}
+
+static ssize_t show_engine_leds(struct device *dev,
+ struct device_attribute *attr,
+ char *buf, int nr)
+{
+ struct lp55xx_led *led = i2c_get_clientdata(to_i2c_client(dev));
+ struct lp55xx_chip *chip = led->chip;
+ char mux[LP5523_MAX_LEDS + 1];
+
+ lp5523_mux_to_array(chip->engines[nr - 1].led_mux, mux);
+
+ return sprintf(buf, "%s\n", mux);
+}
+show_leds(1)
+show_leds(2)
+show_leds(3)
+
+static int lp5523_load_mux(struct lp55xx_chip *chip, u16 mux, int nr)
+{
+ struct lp55xx_engine *engine = &chip->engines[nr - 1];
+ int ret;
+ u8 mux_page[] = {
+ [LP55XX_ENGINE_1] = LP5523_PAGE_MUX1,
+ [LP55XX_ENGINE_2] = LP5523_PAGE_MUX2,
+ [LP55XX_ENGINE_3] = LP5523_PAGE_MUX3,
+ };
+
+ lp5523_load_engine(chip);
+
+ ret = lp55xx_write(chip, LP5523_REG_PROG_PAGE_SEL, mux_page[nr]);
+ if (ret)
+ return ret;
+
+ ret = lp55xx_write(chip, LP5523_REG_PROG_MEM , (u8)(mux >> 8));
+ if (ret)
+ return ret;
+
+ ret = lp55xx_write(chip, LP5523_REG_PROG_MEM + 1, (u8)(mux));
+ if (ret)
+ return ret;
+
+ engine->led_mux = mux;
+ return 0;
+}
+
+static ssize_t store_engine_leds(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t len, int nr)
+{
+ struct lp55xx_led *led = i2c_get_clientdata(to_i2c_client(dev));
+ struct lp55xx_chip *chip = led->chip;
+ struct lp55xx_engine *engine = &chip->engines[nr - 1];
+ u16 mux = 0;
+ ssize_t ret;
+
+ if (lp5523_mux_parse(buf, &mux, len))
+ return -EINVAL;
+
+ mutex_lock(&chip->lock);
+
+ chip->engine_idx = nr;
+ ret = -EINVAL;
+
+ if (engine->mode != LP55XX_ENGINE_LOAD)
+ goto leave;
+
+ if (lp5523_load_mux(chip, mux, nr))
+ goto leave;
+
+ ret = len;
+leave:
+ mutex_unlock(&chip->lock);
+ return ret;
+}
+store_leds(1)
+store_leds(2)
+store_leds(3)
+
+static ssize_t store_engine_load(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t len, int nr)
+{
+ struct lp55xx_led *led = i2c_get_clientdata(to_i2c_client(dev));
+ struct lp55xx_chip *chip = led->chip;
+
+ mutex_lock(&chip->lock);
+
+ chip->engine_idx = nr;
+ lp5523_load_engine_and_select_page(chip);
+
+ mutex_unlock(&chip->lock);
+
+ return lp5523_update_program_memory(chip, buf, len);
+}
+store_load(1)
+store_load(2)
+store_load(3)
+
static ssize_t lp5523_selftest(struct device *dev,
struct device_attribute *attr,
char *buf)
@@ -393,9 +660,27 @@
mutex_unlock(&chip->lock);
}
-static DEVICE_ATTR(selftest, S_IRUGO, lp5523_selftest, NULL);
+static LP55XX_DEV_ATTR_RW(engine1_mode, show_engine1_mode, store_engine1_mode);
+static LP55XX_DEV_ATTR_RW(engine2_mode, show_engine2_mode, store_engine2_mode);
+static LP55XX_DEV_ATTR_RW(engine3_mode, show_engine3_mode, store_engine3_mode);
+static LP55XX_DEV_ATTR_RW(engine1_leds, show_engine1_leds, store_engine1_leds);
+static LP55XX_DEV_ATTR_RW(engine2_leds, show_engine2_leds, store_engine2_leds);
+static LP55XX_DEV_ATTR_RW(engine3_leds, show_engine3_leds, store_engine3_leds);
+static LP55XX_DEV_ATTR_WO(engine1_load, store_engine1_load);
+static LP55XX_DEV_ATTR_WO(engine2_load, store_engine2_load);
+static LP55XX_DEV_ATTR_WO(engine3_load, store_engine3_load);
+static LP55XX_DEV_ATTR_RO(selftest, lp5523_selftest);
static struct attribute *lp5523_attributes[] = {
+ &dev_attr_engine1_mode.attr,
+ &dev_attr_engine2_mode.attr,
+ &dev_attr_engine3_mode.attr,
+ &dev_attr_engine1_load.attr,
+ &dev_attr_engine2_load.attr,
+ &dev_attr_engine3_load.attr,
+ &dev_attr_engine1_leds.attr,
+ &dev_attr_engine2_leds.attr,
+ &dev_attr_engine3_leds.attr,
&dev_attr_selftest.attr,
NULL,
};
@@ -432,7 +717,7 @@
struct lp55xx_platform_data *pdata;
struct device_node *np = client->dev.of_node;
- if (!client->dev.platform_data) {
+ if (!dev_get_platdata(&client->dev)) {
if (np) {
ret = lp55xx_of_populate_pdata(&client->dev, np);
if (ret < 0)
@@ -442,7 +727,7 @@
return -EINVAL;
}
}
- pdata = client->dev.platform_data;
+ pdata = dev_get_platdata(&client->dev);
chip = devm_kzalloc(&client->dev, sizeof(*chip), GFP_KERNEL);
if (!chip)
diff --git a/drivers/leds/leds-lp5562.c b/drivers/leds/leds-lp5562.c
index cbd856d..2585cfd 100644
--- a/drivers/leds/leds-lp5562.c
+++ b/drivers/leds/leds-lp5562.c
@@ -477,8 +477,8 @@
return len;
}
-static DEVICE_ATTR(led_pattern, S_IWUSR, NULL, lp5562_store_pattern);
-static DEVICE_ATTR(engine_mux, S_IWUSR, NULL, lp5562_store_engine_mux);
+static LP55XX_DEV_ATTR_WO(led_pattern, lp5562_store_pattern);
+static LP55XX_DEV_ATTR_WO(engine_mux, lp5562_store_engine_mux);
static struct attribute *lp5562_attributes[] = {
&dev_attr_led_pattern.attr,
@@ -518,7 +518,7 @@
struct lp55xx_platform_data *pdata;
struct device_node *np = client->dev.of_node;
- if (!client->dev.platform_data) {
+ if (!dev_get_platdata(&client->dev)) {
if (np) {
ret = lp55xx_of_populate_pdata(&client->dev, np);
if (ret < 0)
@@ -528,7 +528,7 @@
return -EINVAL;
}
}
- pdata = client->dev.platform_data;
+ pdata = dev_get_platdata(&client->dev);
chip = devm_kzalloc(&client->dev, sizeof(*chip), GFP_KERNEL);
if (!chip)
diff --git a/drivers/leds/leds-lp55xx-common.c b/drivers/leds/leds-lp55xx-common.c
index c2fecd4..351825b 100644
--- a/drivers/leds/leds-lp55xx-common.c
+++ b/drivers/leds/leds-lp55xx-common.c
@@ -593,6 +593,9 @@
of_property_read_string(np, "label", &pdata->label);
of_property_read_u8(np, "clock-mode", &pdata->clock_mode);
+ /* LP8501 specific */
+ of_property_read_u8(np, "pwr-sel", (u8 *)&pdata->pwr_sel);
+
dev->platform_data = pdata;
return 0;
diff --git a/drivers/leds/leds-lp55xx-common.h b/drivers/leds/leds-lp55xx-common.h
index dbbf86d..cceab48 100644
--- a/drivers/leds/leds-lp55xx-common.h
+++ b/drivers/leds/leds-lp55xx-common.h
@@ -20,8 +20,62 @@
LP55XX_ENGINE_1,
LP55XX_ENGINE_2,
LP55XX_ENGINE_3,
+ LP55XX_ENGINE_MAX = LP55XX_ENGINE_3,
};
+enum lp55xx_engine_mode {
+ LP55XX_ENGINE_DISABLED,
+ LP55XX_ENGINE_LOAD,
+ LP55XX_ENGINE_RUN,
+};
+
+#define LP55XX_DEV_ATTR_RW(name, show, store) \
+ DEVICE_ATTR(name, S_IRUGO | S_IWUSR, show, store)
+#define LP55XX_DEV_ATTR_RO(name, show) \
+ DEVICE_ATTR(name, S_IRUGO, show, NULL)
+#define LP55XX_DEV_ATTR_WO(name, store) \
+ DEVICE_ATTR(name, S_IWUSR, NULL, store)
+
+#define show_mode(nr) \
+static ssize_t show_engine##nr##_mode(struct device *dev, \
+ struct device_attribute *attr, \
+ char *buf) \
+{ \
+ return show_engine_mode(dev, attr, buf, nr); \
+}
+
+#define store_mode(nr) \
+static ssize_t store_engine##nr##_mode(struct device *dev, \
+ struct device_attribute *attr, \
+ const char *buf, size_t len) \
+{ \
+ return store_engine_mode(dev, attr, buf, len, nr); \
+}
+
+#define show_leds(nr) \
+static ssize_t show_engine##nr##_leds(struct device *dev, \
+ struct device_attribute *attr, \
+ char *buf) \
+{ \
+ return show_engine_leds(dev, attr, buf, nr); \
+}
+
+#define store_leds(nr) \
+static ssize_t store_engine##nr##_leds(struct device *dev, \
+ struct device_attribute *attr, \
+ const char *buf, size_t len) \
+{ \
+ return store_engine_leds(dev, attr, buf, len, nr); \
+}
+
+#define store_load(nr) \
+static ssize_t store_engine##nr##_load(struct device *dev, \
+ struct device_attribute *attr, \
+ const char *buf, size_t len) \
+{ \
+ return store_engine_load(dev, attr, buf, len, nr); \
+}
+
struct lp55xx_led;
struct lp55xx_chip;
@@ -72,6 +126,16 @@
};
/*
+ * struct lp55xx_engine
+ * @mode : Engine mode
+ * @led_mux : Mux bits for LED selection. Only used in LP5523
+ */
+struct lp55xx_engine {
+ enum lp55xx_engine_mode mode;
+ u16 led_mux;
+};
+
+/*
* struct lp55xx_chip
* @cl : I2C communication for access registers
* @pdata : Platform specific data
@@ -79,6 +143,7 @@
* @num_leds : Number of registered LEDs
* @cfg : Device specific configuration data
* @engine_idx : Selected engine number
+ * @engines : Engine structure for the device attribute R/W interface
* @fw : Firmware data for running a LED pattern
*/
struct lp55xx_chip {
@@ -89,6 +154,7 @@
int num_leds;
struct lp55xx_device_config *cfg;
enum lp55xx_engine_index engine_idx;
+ struct lp55xx_engine engines[LP55XX_ENGINE_MAX];
const struct firmware *fw;
};
diff --git a/drivers/leds/leds-lp8501.c b/drivers/leds/leds-lp8501.c
new file mode 100644
index 0000000..8d55a780
--- /dev/null
+++ b/drivers/leds/leds-lp8501.c
@@ -0,0 +1,410 @@
+/*
+ * TI LP8501 9 channel LED Driver
+ *
+ * Copyright (C) 2013 Texas Instruments
+ *
+ * Author: Milo(Woogyom) Kim <milo.kim@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/delay.h>
+#include <linux/firmware.h>
+#include <linux/i2c.h>
+#include <linux/init.h>
+#include <linux/leds.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/platform_data/leds-lp55xx.h>
+#include <linux/slab.h>
+
+#include "leds-lp55xx-common.h"
+
+#define LP8501_PROGRAM_LENGTH 32
+#define LP8501_MAX_LEDS 9
+
+/* Registers */
+#define LP8501_REG_ENABLE 0x00
+#define LP8501_ENABLE BIT(6)
+#define LP8501_EXEC_M 0x3F
+#define LP8501_EXEC_ENG1_M 0x30
+#define LP8501_EXEC_ENG2_M 0x0C
+#define LP8501_EXEC_ENG3_M 0x03
+#define LP8501_RUN_ENG1 0x20
+#define LP8501_RUN_ENG2 0x08
+#define LP8501_RUN_ENG3 0x02
+
+#define LP8501_REG_OP_MODE 0x01
+#define LP8501_MODE_ENG1_M 0x30
+#define LP8501_MODE_ENG2_M 0x0C
+#define LP8501_MODE_ENG3_M 0x03
+#define LP8501_LOAD_ENG1 0x10
+#define LP8501_LOAD_ENG2 0x04
+#define LP8501_LOAD_ENG3 0x01
+
+#define LP8501_REG_PWR_CONFIG 0x05
+#define LP8501_PWR_CONFIG_M 0x03
+
+#define LP8501_REG_LED_PWM_BASE 0x16
+
+#define LP8501_REG_LED_CURRENT_BASE 0x26
+
+#define LP8501_REG_CONFIG 0x36
+#define LP8501_PWM_PSAVE BIT(7)
+#define LP8501_AUTO_INC BIT(6)
+#define LP8501_PWR_SAVE BIT(5)
+#define LP8501_CP_AUTO 0x18
+#define LP8501_INT_CLK BIT(0)
+#define LP8501_DEFAULT_CFG \
+ (LP8501_PWM_PSAVE | LP8501_AUTO_INC | LP8501_PWR_SAVE | LP8501_CP_AUTO)
+
+#define LP8501_REG_RESET 0x3D
+#define LP8501_RESET 0xFF
+
+#define LP8501_REG_PROG_PAGE_SEL 0x4F
+#define LP8501_PAGE_ENG1 0
+#define LP8501_PAGE_ENG2 1
+#define LP8501_PAGE_ENG3 2
+
+#define LP8501_REG_PROG_MEM 0x50
+
+#define LP8501_ENG1_IS_LOADING(mode) \
+ ((mode & LP8501_MODE_ENG1_M) == LP8501_LOAD_ENG1)
+#define LP8501_ENG2_IS_LOADING(mode) \
+ ((mode & LP8501_MODE_ENG2_M) == LP8501_LOAD_ENG2)
+#define LP8501_ENG3_IS_LOADING(mode) \
+ ((mode & LP8501_MODE_ENG3_M) == LP8501_LOAD_ENG3)
+
+static inline void lp8501_wait_opmode_done(void)
+{
+ usleep_range(1000, 2000);
+}
+
+static void lp8501_set_led_current(struct lp55xx_led *led, u8 led_current)
+{
+ led->led_current = led_current;
+ lp55xx_write(led->chip, LP8501_REG_LED_CURRENT_BASE + led->chan_nr,
+ led_current);
+}
+
+static int lp8501_post_init_device(struct lp55xx_chip *chip)
+{
+ int ret;
+ u8 val = LP8501_DEFAULT_CFG;
+
+ ret = lp55xx_write(chip, LP8501_REG_ENABLE, LP8501_ENABLE);
+ if (ret)
+ return ret;
+
+ /* Chip startup time is 500 us, 1 - 2 ms gives some margin */
+ usleep_range(1000, 2000);
+
+ if (chip->pdata->clock_mode != LP55XX_CLOCK_EXT)
+ val |= LP8501_INT_CLK;
+
+ ret = lp55xx_write(chip, LP8501_REG_CONFIG, val);
+ if (ret)
+ return ret;
+
+ /* Power selection for each output */
+ return lp55xx_update_bits(chip, LP8501_REG_PWR_CONFIG,
+ LP8501_PWR_CONFIG_M, chip->pdata->pwr_sel);
+}
+
+static void lp8501_load_engine(struct lp55xx_chip *chip)
+{
+ enum lp55xx_engine_index idx = chip->engine_idx;
+ u8 mask[] = {
+ [LP55XX_ENGINE_1] = LP8501_MODE_ENG1_M,
+ [LP55XX_ENGINE_2] = LP8501_MODE_ENG2_M,
+ [LP55XX_ENGINE_3] = LP8501_MODE_ENG3_M,
+ };
+
+ u8 val[] = {
+ [LP55XX_ENGINE_1] = LP8501_LOAD_ENG1,
+ [LP55XX_ENGINE_2] = LP8501_LOAD_ENG2,
+ [LP55XX_ENGINE_3] = LP8501_LOAD_ENG3,
+ };
+
+ u8 page_sel[] = {
+ [LP55XX_ENGINE_1] = LP8501_PAGE_ENG1,
+ [LP55XX_ENGINE_2] = LP8501_PAGE_ENG2,
+ [LP55XX_ENGINE_3] = LP8501_PAGE_ENG3,
+ };
+
+ lp55xx_update_bits(chip, LP8501_REG_OP_MODE, mask[idx], val[idx]);
+
+ lp8501_wait_opmode_done();
+
+ lp55xx_write(chip, LP8501_REG_PROG_PAGE_SEL, page_sel[idx]);
+}
+
+static void lp8501_stop_engine(struct lp55xx_chip *chip)
+{
+ lp55xx_write(chip, LP8501_REG_OP_MODE, 0);
+ lp8501_wait_opmode_done();
+}
+
+static void lp8501_turn_off_channels(struct lp55xx_chip *chip)
+{
+ int i;
+
+ for (i = 0; i < LP8501_MAX_LEDS; i++)
+ lp55xx_write(chip, LP8501_REG_LED_PWM_BASE + i, 0);
+}
+
+static void lp8501_run_engine(struct lp55xx_chip *chip, bool start)
+{
+ int ret;
+ u8 mode;
+ u8 exec;
+
+ /* stop engine */
+ if (!start) {
+ lp8501_stop_engine(chip);
+ lp8501_turn_off_channels(chip);
+ return;
+ }
+
+ /*
+ * To run the engine,
+ * operation mode and enable register should updated at the same time
+ */
+
+ ret = lp55xx_read(chip, LP8501_REG_OP_MODE, &mode);
+ if (ret)
+ return;
+
+ ret = lp55xx_read(chip, LP8501_REG_ENABLE, &exec);
+ if (ret)
+ return;
+
+ /* change operation mode to RUN only when each engine is loading */
+ if (LP8501_ENG1_IS_LOADING(mode)) {
+ mode = (mode & ~LP8501_MODE_ENG1_M) | LP8501_RUN_ENG1;
+ exec = (exec & ~LP8501_EXEC_ENG1_M) | LP8501_RUN_ENG1;
+ }
+
+ if (LP8501_ENG2_IS_LOADING(mode)) {
+ mode = (mode & ~LP8501_MODE_ENG2_M) | LP8501_RUN_ENG2;
+ exec = (exec & ~LP8501_EXEC_ENG2_M) | LP8501_RUN_ENG2;
+ }
+
+ if (LP8501_ENG3_IS_LOADING(mode)) {
+ mode = (mode & ~LP8501_MODE_ENG3_M) | LP8501_RUN_ENG3;
+ exec = (exec & ~LP8501_EXEC_ENG3_M) | LP8501_RUN_ENG3;
+ }
+
+ lp55xx_write(chip, LP8501_REG_OP_MODE, mode);
+ lp8501_wait_opmode_done();
+
+ lp55xx_update_bits(chip, LP8501_REG_ENABLE, LP8501_EXEC_M, exec);
+}
+
+static int lp8501_update_program_memory(struct lp55xx_chip *chip,
+ const u8 *data, size_t size)
+{
+ u8 pattern[LP8501_PROGRAM_LENGTH] = {0};
+ unsigned cmd;
+ char c[3];
+ int update_size;
+ int nrchars;
+ int offset = 0;
+ int ret;
+ int i;
+
+ /* clear program memory before updating */
+ for (i = 0; i < LP8501_PROGRAM_LENGTH; i++)
+ lp55xx_write(chip, LP8501_REG_PROG_MEM + i, 0);
+
+ i = 0;
+ while ((offset < size - 1) && (i < LP8501_PROGRAM_LENGTH)) {
+ /* separate sscanfs because length is working only for %s */
+ ret = sscanf(data + offset, "%2s%n ", c, &nrchars);
+ if (ret != 1)
+ goto err;
+
+ ret = sscanf(c, "%2x", &cmd);
+ if (ret != 1)
+ goto err;
+
+ pattern[i] = (u8)cmd;
+ offset += nrchars;
+ i++;
+ }
+
+ /* Each instruction is 16bit long. Check that length is even */
+ if (i % 2)
+ goto err;
+
+ update_size = i;
+ for (i = 0; i < update_size; i++)
+ lp55xx_write(chip, LP8501_REG_PROG_MEM + i, pattern[i]);
+
+ return 0;
+
+err:
+ dev_err(&chip->cl->dev, "wrong pattern format\n");
+ return -EINVAL;
+}
+
+static void lp8501_firmware_loaded(struct lp55xx_chip *chip)
+{
+ const struct firmware *fw = chip->fw;
+
+ if (fw->size > LP8501_PROGRAM_LENGTH) {
+ dev_err(&chip->cl->dev, "firmware data size overflow: %zu\n",
+ fw->size);
+ return;
+ }
+
+ /*
+ * Program momery sequence
+ * 1) set engine mode to "LOAD"
+ * 2) write firmware data into program memory
+ */
+
+ lp8501_load_engine(chip);
+ lp8501_update_program_memory(chip, fw->data, fw->size);
+}
+
+static void lp8501_led_brightness_work(struct work_struct *work)
+{
+ struct lp55xx_led *led = container_of(work, struct lp55xx_led,
+ brightness_work);
+ struct lp55xx_chip *chip = led->chip;
+
+ mutex_lock(&chip->lock);
+ lp55xx_write(chip, LP8501_REG_LED_PWM_BASE + led->chan_nr,
+ led->brightness);
+ mutex_unlock(&chip->lock);
+}
+
+/* Chip specific configurations */
+static struct lp55xx_device_config lp8501_cfg = {
+ .reset = {
+ .addr = LP8501_REG_RESET,
+ .val = LP8501_RESET,
+ },
+ .enable = {
+ .addr = LP8501_REG_ENABLE,
+ .val = LP8501_ENABLE,
+ },
+ .max_channel = LP8501_MAX_LEDS,
+ .post_init_device = lp8501_post_init_device,
+ .brightness_work_fn = lp8501_led_brightness_work,
+ .set_led_current = lp8501_set_led_current,
+ .firmware_cb = lp8501_firmware_loaded,
+ .run_engine = lp8501_run_engine,
+};
+
+static int lp8501_probe(struct i2c_client *client,
+ const struct i2c_device_id *id)
+{
+ int ret;
+ struct lp55xx_chip *chip;
+ struct lp55xx_led *led;
+ struct lp55xx_platform_data *pdata;
+ struct device_node *np = client->dev.of_node;
+
+ if (!dev_get_platdata(&client->dev)) {
+ if (np) {
+ ret = lp55xx_of_populate_pdata(&client->dev, np);
+ if (ret < 0)
+ return ret;
+ } else {
+ dev_err(&client->dev, "no platform data\n");
+ return -EINVAL;
+ }
+ }
+ pdata = dev_get_platdata(&client->dev);
+
+ chip = devm_kzalloc(&client->dev, sizeof(*chip), GFP_KERNEL);
+ if (!chip)
+ return -ENOMEM;
+
+ led = devm_kzalloc(&client->dev,
+ sizeof(*led) * pdata->num_channels, GFP_KERNEL);
+ if (!led)
+ return -ENOMEM;
+
+ chip->cl = client;
+ chip->pdata = pdata;
+ chip->cfg = &lp8501_cfg;
+
+ mutex_init(&chip->lock);
+
+ i2c_set_clientdata(client, led);
+
+ ret = lp55xx_init_device(chip);
+ if (ret)
+ goto err_init;
+
+ dev_info(&client->dev, "%s Programmable led chip found\n", id->name);
+
+ ret = lp55xx_register_leds(led, chip);
+ if (ret)
+ goto err_register_leds;
+
+ ret = lp55xx_register_sysfs(chip);
+ if (ret) {
+ dev_err(&client->dev, "registering sysfs failed\n");
+ goto err_register_sysfs;
+ }
+
+ return 0;
+
+err_register_sysfs:
+ lp55xx_unregister_leds(led, chip);
+err_register_leds:
+ lp55xx_deinit_device(chip);
+err_init:
+ return ret;
+}
+
+static int lp8501_remove(struct i2c_client *client)
+{
+ struct lp55xx_led *led = i2c_get_clientdata(client);
+ struct lp55xx_chip *chip = led->chip;
+
+ lp8501_stop_engine(chip);
+ lp55xx_unregister_sysfs(chip);
+ lp55xx_unregister_leds(led, chip);
+ lp55xx_deinit_device(chip);
+
+ return 0;
+}
+
+static const struct i2c_device_id lp8501_id[] = {
+ { "lp8501", 0 },
+ { }
+};
+MODULE_DEVICE_TABLE(i2c, lp8501_id);
+
+#ifdef CONFIG_OF
+static const struct of_device_id of_lp8501_leds_match[] = {
+ { .compatible = "ti,lp8501", },
+ {},
+};
+
+MODULE_DEVICE_TABLE(of, of_lp8501_leds_match);
+#endif
+
+static struct i2c_driver lp8501_driver = {
+ .driver = {
+ .name = "lp8501",
+ .of_match_table = of_match_ptr(of_lp8501_leds_match),
+ },
+ .probe = lp8501_probe,
+ .remove = lp8501_remove,
+ .id_table = lp8501_id,
+};
+
+module_i2c_driver(lp8501_driver);
+
+MODULE_DESCRIPTION("Texas Instruments LP8501 LED drvier");
+MODULE_AUTHOR("Milo Kim");
+MODULE_LICENSE("GPL");
diff --git a/drivers/leds/leds-lt3593.c b/drivers/leds/leds-lt3593.c
index ca48a7d5..3417e5b 100644
--- a/drivers/leds/leds-lt3593.c
+++ b/drivers/leds/leds-lt3593.c
@@ -135,7 +135,7 @@
static int lt3593_led_probe(struct platform_device *pdev)
{
- struct gpio_led_platform_data *pdata = pdev->dev.platform_data;
+ struct gpio_led_platform_data *pdata = dev_get_platdata(&pdev->dev);
struct lt3593_led_data *leds_data;
int i, ret = 0;
@@ -169,7 +169,7 @@
static int lt3593_led_remove(struct platform_device *pdev)
{
int i;
- struct gpio_led_platform_data *pdata = pdev->dev.platform_data;
+ struct gpio_led_platform_data *pdata = dev_get_platdata(&pdev->dev);
struct lt3593_led_data *leds_data;
leds_data = platform_get_drvdata(pdev);
diff --git a/drivers/leds/leds-netxbig.c b/drivers/leds/leds-netxbig.c
index c61c5eb..2f9f141 100644
--- a/drivers/leds/leds-netxbig.c
+++ b/drivers/leds/leds-netxbig.c
@@ -306,7 +306,7 @@
struct netxbig_led_data *led_dat,
const struct netxbig_led *template)
{
- struct netxbig_led_platform_data *pdata = pdev->dev.platform_data;
+ struct netxbig_led_platform_data *pdata = dev_get_platdata(&pdev->dev);
int ret;
spin_lock_init(&led_dat->lock);
@@ -354,7 +354,7 @@
static int netxbig_led_probe(struct platform_device *pdev)
{
- struct netxbig_led_platform_data *pdata = pdev->dev.platform_data;
+ struct netxbig_led_platform_data *pdata = dev_get_platdata(&pdev->dev);
struct netxbig_led_data *leds_data;
int i;
int ret;
@@ -391,7 +391,7 @@
static int netxbig_led_remove(struct platform_device *pdev)
{
- struct netxbig_led_platform_data *pdata = pdev->dev.platform_data;
+ struct netxbig_led_platform_data *pdata = dev_get_platdata(&pdev->dev);
struct netxbig_led_data *leds_data;
int i;
diff --git a/drivers/leds/leds-ns2.c b/drivers/leds/leds-ns2.c
index e7df987..141f134 100644
--- a/drivers/leds/leds-ns2.c
+++ b/drivers/leds/leds-ns2.c
@@ -321,7 +321,7 @@
static int ns2_led_probe(struct platform_device *pdev)
{
- struct ns2_led_platform_data *pdata = pdev->dev.platform_data;
+ struct ns2_led_platform_data *pdata = dev_get_platdata(&pdev->dev);
struct ns2_led_priv *priv;
int i;
int ret;
diff --git a/drivers/leds/leds-pca9532.c b/drivers/leds/leds-pca9532.c
index 0c597bd..4a0e786 100644
--- a/drivers/leds/leds-pca9532.c
+++ b/drivers/leds/leds-pca9532.c
@@ -446,7 +446,8 @@
const struct i2c_device_id *id)
{
struct pca9532_data *data = i2c_get_clientdata(client);
- struct pca9532_platform_data *pca9532_pdata = client->dev.platform_data;
+ struct pca9532_platform_data *pca9532_pdata =
+ dev_get_platdata(&client->dev);
if (!pca9532_pdata)
return -EIO;
diff --git a/drivers/leds/leds-pca955x.c b/drivers/leds/leds-pca955x.c
index edf485b..c3a08b6 100644
--- a/drivers/leds/leds-pca955x.c
+++ b/drivers/leds/leds-pca955x.c
@@ -267,7 +267,7 @@
chip = &pca955x_chipdefs[id->driver_data];
adapter = to_i2c_adapter(client->dev.parent);
- pdata = client->dev.platform_data;
+ pdata = dev_get_platdata(&client->dev);
/* Make sure the slave address / chip type combo given is possible */
if ((client->addr & ~((1 << chip->slv_addr_shift) - 1)) !=
diff --git a/drivers/leds/leds-pca9633.c b/drivers/leds/leds-pca9633.c
deleted file mode 100644
index 9aae567..0000000
--- a/drivers/leds/leds-pca9633.c
+++ /dev/null
@@ -1,194 +0,0 @@
-/*
- * Copyright 2011 bct electronic GmbH
- *
- * Author: Peter Meerwald <p.meerwald@bct-electronic.com>
- *
- * Based on leds-pca955x.c
- *
- * This file is subject to the terms and conditions of version 2 of
- * the GNU General Public License. See the file COPYING in the main
- * directory of this archive for more details.
- *
- * LED driver for the PCA9633 I2C LED driver (7-bit slave address 0x62)
- *
- */
-
-#include <linux/module.h>
-#include <linux/delay.h>
-#include <linux/string.h>
-#include <linux/ctype.h>
-#include <linux/leds.h>
-#include <linux/err.h>
-#include <linux/i2c.h>
-#include <linux/workqueue.h>
-#include <linux/slab.h>
-#include <linux/platform_data/leds-pca9633.h>
-
-/* LED select registers determine the source that drives LED outputs */
-#define PCA9633_LED_OFF 0x0 /* LED driver off */
-#define PCA9633_LED_ON 0x1 /* LED driver on */
-#define PCA9633_LED_PWM 0x2 /* Controlled through PWM */
-#define PCA9633_LED_GRP_PWM 0x3 /* Controlled through PWM/GRPPWM */
-
-#define PCA9633_MODE1 0x00
-#define PCA9633_MODE2 0x01
-#define PCA9633_PWM_BASE 0x02
-#define PCA9633_LEDOUT 0x08
-
-static const struct i2c_device_id pca9633_id[] = {
- { "pca9633", 0 },
- { }
-};
-MODULE_DEVICE_TABLE(i2c, pca9633_id);
-
-struct pca9633_led {
- struct i2c_client *client;
- struct work_struct work;
- enum led_brightness brightness;
- struct led_classdev led_cdev;
- int led_num; /* 0 .. 3 potentially */
- char name[32];
-};
-
-static void pca9633_led_work(struct work_struct *work)
-{
- struct pca9633_led *pca9633 = container_of(work,
- struct pca9633_led, work);
- u8 ledout = i2c_smbus_read_byte_data(pca9633->client, PCA9633_LEDOUT);
- int shift = 2 * pca9633->led_num;
- u8 mask = 0x3 << shift;
-
- switch (pca9633->brightness) {
- case LED_FULL:
- i2c_smbus_write_byte_data(pca9633->client, PCA9633_LEDOUT,
- (ledout & ~mask) | (PCA9633_LED_ON << shift));
- break;
- case LED_OFF:
- i2c_smbus_write_byte_data(pca9633->client, PCA9633_LEDOUT,
- ledout & ~mask);
- break;
- default:
- i2c_smbus_write_byte_data(pca9633->client,
- PCA9633_PWM_BASE + pca9633->led_num,
- pca9633->brightness);
- i2c_smbus_write_byte_data(pca9633->client, PCA9633_LEDOUT,
- (ledout & ~mask) | (PCA9633_LED_PWM << shift));
- break;
- }
-}
-
-static void pca9633_led_set(struct led_classdev *led_cdev,
- enum led_brightness value)
-{
- struct pca9633_led *pca9633;
-
- pca9633 = container_of(led_cdev, struct pca9633_led, led_cdev);
-
- pca9633->brightness = value;
-
- /*
- * Must use workqueue for the actual I/O since I2C operations
- * can sleep.
- */
- schedule_work(&pca9633->work);
-}
-
-static int pca9633_probe(struct i2c_client *client,
- const struct i2c_device_id *id)
-{
- struct pca9633_led *pca9633;
- struct pca9633_platform_data *pdata;
- int i, err;
-
- pdata = client->dev.platform_data;
-
- if (pdata) {
- if (pdata->leds.num_leds <= 0 || pdata->leds.num_leds > 4) {
- dev_err(&client->dev, "board info must claim at most 4 LEDs");
- return -EINVAL;
- }
- }
-
- pca9633 = devm_kzalloc(&client->dev, 4 * sizeof(*pca9633), GFP_KERNEL);
- if (!pca9633)
- return -ENOMEM;
-
- i2c_set_clientdata(client, pca9633);
-
- for (i = 0; i < 4; i++) {
- pca9633[i].client = client;
- pca9633[i].led_num = i;
-
- /* Platform data can specify LED names and default triggers */
- if (pdata && i < pdata->leds.num_leds) {
- if (pdata->leds.leds[i].name)
- snprintf(pca9633[i].name,
- sizeof(pca9633[i].name), "pca9633:%s",
- pdata->leds.leds[i].name);
- if (pdata->leds.leds[i].default_trigger)
- pca9633[i].led_cdev.default_trigger =
- pdata->leds.leds[i].default_trigger;
- } else {
- snprintf(pca9633[i].name, sizeof(pca9633[i].name),
- "pca9633:%d", i);
- }
-
- pca9633[i].led_cdev.name = pca9633[i].name;
- pca9633[i].led_cdev.brightness_set = pca9633_led_set;
-
- INIT_WORK(&pca9633[i].work, pca9633_led_work);
-
- err = led_classdev_register(&client->dev, &pca9633[i].led_cdev);
- if (err < 0)
- goto exit;
- }
-
- /* Disable LED all-call address and set normal mode */
- i2c_smbus_write_byte_data(client, PCA9633_MODE1, 0x00);
-
- /* Configure output: open-drain or totem pole (push-pull) */
- if (pdata && pdata->outdrv == PCA9633_OPEN_DRAIN)
- i2c_smbus_write_byte_data(client, PCA9633_MODE2, 0x01);
-
- /* Turn off LEDs */
- i2c_smbus_write_byte_data(client, PCA9633_LEDOUT, 0x00);
-
- return 0;
-
-exit:
- while (i--) {
- led_classdev_unregister(&pca9633[i].led_cdev);
- cancel_work_sync(&pca9633[i].work);
- }
-
- return err;
-}
-
-static int pca9633_remove(struct i2c_client *client)
-{
- struct pca9633_led *pca9633 = i2c_get_clientdata(client);
- int i;
-
- for (i = 0; i < 4; i++) {
- led_classdev_unregister(&pca9633[i].led_cdev);
- cancel_work_sync(&pca9633[i].work);
- }
-
- return 0;
-}
-
-static struct i2c_driver pca9633_driver = {
- .driver = {
- .name = "leds-pca9633",
- .owner = THIS_MODULE,
- },
- .probe = pca9633_probe,
- .remove = pca9633_remove,
- .id_table = pca9633_id,
-};
-
-module_i2c_driver(pca9633_driver);
-
-MODULE_AUTHOR("Peter Meerwald <p.meerwald@bct-electronic.com>");
-MODULE_DESCRIPTION("PCA9633 LED driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/leds/leds-pca963x.c b/drivers/leds/leds-pca963x.c
new file mode 100644
index 0000000..82589c0
--- /dev/null
+++ b/drivers/leds/leds-pca963x.c
@@ -0,0 +1,461 @@
+/*
+ * Copyright 2011 bct electronic GmbH
+ * Copyright 2013 Qtechnology/AS
+ *
+ * Author: Peter Meerwald <p.meerwald@bct-electronic.com>
+ * Author: Ricardo Ribalda <ricardo.ribalda@gmail.com>
+ *
+ * Based on leds-pca955x.c
+ *
+ * This file is subject to the terms and conditions of version 2 of
+ * the GNU General Public License. See the file COPYING in the main
+ * directory of this archive for more details.
+ *
+ * LED driver for the PCA9633 I2C LED driver (7-bit slave address 0x62)
+ * LED driver for the PCA9634 I2C LED driver (7-bit slave address set by hw.)
+ *
+ * Note that hardware blinking violates the leds infrastructure driver
+ * interface since the hardware only supports blinking all LEDs with the
+ * same delay_on/delay_off rates. That is, only the LEDs that are set to
+ * blink will actually blink but all LEDs that are set to blink will blink
+ * in identical fashion. The delay_on/delay_off values of the last LED
+ * that is set to blink will be used for all of the blinking LEDs.
+ * Hardware blinking is disabled by default but can be enabled by setting
+ * the 'blink_type' member in the platform_data struct to 'PCA963X_HW_BLINK'
+ * or by adding the 'nxp,hw-blink' property to the DTS.
+ */
+
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+#include <linux/leds.h>
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/workqueue.h>
+#include <linux/slab.h>
+#include <linux/of.h>
+#include <linux/platform_data/leds-pca963x.h>
+
+/* LED select registers determine the source that drives LED outputs */
+#define PCA963X_LED_OFF 0x0 /* LED driver off */
+#define PCA963X_LED_ON 0x1 /* LED driver on */
+#define PCA963X_LED_PWM 0x2 /* Controlled through PWM */
+#define PCA963X_LED_GRP_PWM 0x3 /* Controlled through PWM/GRPPWM */
+
+#define PCA963X_MODE2_DMBLNK 0x20 /* Enable blinking */
+
+#define PCA963X_MODE1 0x00
+#define PCA963X_MODE2 0x01
+#define PCA963X_PWM_BASE 0x02
+
+enum pca963x_type {
+ pca9633,
+ pca9634,
+};
+
+struct pca963x_chipdef {
+ u8 grppwm;
+ u8 grpfreq;
+ u8 ledout_base;
+ int n_leds;
+};
+
+static struct pca963x_chipdef pca963x_chipdefs[] = {
+ [pca9633] = {
+ .grppwm = 0x6,
+ .grpfreq = 0x7,
+ .ledout_base = 0x8,
+ .n_leds = 4,
+ },
+ [pca9634] = {
+ .grppwm = 0xa,
+ .grpfreq = 0xb,
+ .ledout_base = 0xc,
+ .n_leds = 8,
+ },
+};
+
+/* Total blink period in milliseconds */
+#define PCA963X_BLINK_PERIOD_MIN 42
+#define PCA963X_BLINK_PERIOD_MAX 10667
+
+static const struct i2c_device_id pca963x_id[] = {
+ { "pca9632", pca9633 },
+ { "pca9633", pca9633 },
+ { "pca9634", pca9634 },
+ { }
+};
+MODULE_DEVICE_TABLE(i2c, pca963x_id);
+
+enum pca963x_cmd {
+ BRIGHTNESS_SET,
+ BLINK_SET,
+};
+
+struct pca963x_led;
+
+struct pca963x {
+ struct pca963x_chipdef *chipdef;
+ struct mutex mutex;
+ struct i2c_client *client;
+ struct pca963x_led *leds;
+};
+
+struct pca963x_led {
+ struct pca963x *chip;
+ struct work_struct work;
+ enum led_brightness brightness;
+ struct led_classdev led_cdev;
+ int led_num; /* 0 .. 7 potentially */
+ enum pca963x_cmd cmd;
+ char name[32];
+ u8 gdc;
+ u8 gfrq;
+};
+
+static void pca963x_brightness_work(struct pca963x_led *pca963x)
+{
+ u8 ledout_addr = pca963x->chip->chipdef->ledout_base
+ + (pca963x->led_num / 4);
+ u8 ledout;
+ int shift = 2 * (pca963x->led_num % 4);
+ u8 mask = 0x3 << shift;
+
+ mutex_lock(&pca963x->chip->mutex);
+ ledout = i2c_smbus_read_byte_data(pca963x->chip->client, ledout_addr);
+ switch (pca963x->brightness) {
+ case LED_FULL:
+ i2c_smbus_write_byte_data(pca963x->chip->client, ledout_addr,
+ (ledout & ~mask) | (PCA963X_LED_ON << shift));
+ break;
+ case LED_OFF:
+ i2c_smbus_write_byte_data(pca963x->chip->client, ledout_addr,
+ ledout & ~mask);
+ break;
+ default:
+ i2c_smbus_write_byte_data(pca963x->chip->client,
+ PCA963X_PWM_BASE + pca963x->led_num,
+ pca963x->brightness);
+ i2c_smbus_write_byte_data(pca963x->chip->client, ledout_addr,
+ (ledout & ~mask) | (PCA963X_LED_PWM << shift));
+ break;
+ }
+ mutex_unlock(&pca963x->chip->mutex);
+}
+
+static void pca963x_blink_work(struct pca963x_led *pca963x)
+{
+ u8 ledout_addr = pca963x->chip->chipdef->ledout_base +
+ (pca963x->led_num / 4);
+ u8 ledout;
+ u8 mode2 = i2c_smbus_read_byte_data(pca963x->chip->client,
+ PCA963X_MODE2);
+ int shift = 2 * (pca963x->led_num % 4);
+ u8 mask = 0x3 << shift;
+
+ i2c_smbus_write_byte_data(pca963x->chip->client,
+ pca963x->chip->chipdef->grppwm, pca963x->gdc);
+
+ i2c_smbus_write_byte_data(pca963x->chip->client,
+ pca963x->chip->chipdef->grpfreq, pca963x->gfrq);
+
+ if (!(mode2 & PCA963X_MODE2_DMBLNK))
+ i2c_smbus_write_byte_data(pca963x->chip->client, PCA963X_MODE2,
+ mode2 | PCA963X_MODE2_DMBLNK);
+
+ mutex_lock(&pca963x->chip->mutex);
+ ledout = i2c_smbus_read_byte_data(pca963x->chip->client, ledout_addr);
+ if ((ledout & mask) != (PCA963X_LED_GRP_PWM << shift))
+ i2c_smbus_write_byte_data(pca963x->chip->client, ledout_addr,
+ (ledout & ~mask) | (PCA963X_LED_GRP_PWM << shift));
+ mutex_unlock(&pca963x->chip->mutex);
+}
+
+static void pca963x_work(struct work_struct *work)
+{
+ struct pca963x_led *pca963x = container_of(work,
+ struct pca963x_led, work);
+
+ switch (pca963x->cmd) {
+ case BRIGHTNESS_SET:
+ pca963x_brightness_work(pca963x);
+ break;
+ case BLINK_SET:
+ pca963x_blink_work(pca963x);
+ break;
+ }
+}
+
+static void pca963x_led_set(struct led_classdev *led_cdev,
+ enum led_brightness value)
+{
+ struct pca963x_led *pca963x;
+
+ pca963x = container_of(led_cdev, struct pca963x_led, led_cdev);
+
+ pca963x->cmd = BRIGHTNESS_SET;
+ pca963x->brightness = value;
+
+ /*
+ * Must use workqueue for the actual I/O since I2C operations
+ * can sleep.
+ */
+ schedule_work(&pca963x->work);
+}
+
+static int pca963x_blink_set(struct led_classdev *led_cdev,
+ unsigned long *delay_on, unsigned long *delay_off)
+{
+ struct pca963x_led *pca963x;
+ unsigned long time_on, time_off, period;
+ u8 gdc, gfrq;
+
+ pca963x = container_of(led_cdev, struct pca963x_led, led_cdev);
+
+ time_on = *delay_on;
+ time_off = *delay_off;
+
+ /* If both zero, pick reasonable defaults of 500ms each */
+ if (!time_on && !time_off) {
+ time_on = 500;
+ time_off = 500;
+ }
+
+ period = time_on + time_off;
+
+ /* If period not supported by hardware, default to someting sane. */
+ if ((period < PCA963X_BLINK_PERIOD_MIN) ||
+ (period > PCA963X_BLINK_PERIOD_MAX)) {
+ time_on = 500;
+ time_off = 500;
+ period = time_on + time_off;
+ }
+
+ /*
+ * From manual: duty cycle = (GDC / 256) ->
+ * (time_on / period) = (GDC / 256) ->
+ * GDC = ((time_on * 256) / period)
+ */
+ gdc = (time_on * 256) / period;
+
+ /*
+ * From manual: period = ((GFRQ + 1) / 24) in seconds.
+ * So, period (in ms) = (((GFRQ + 1) / 24) * 1000) ->
+ * GFRQ = ((period * 24 / 1000) - 1)
+ */
+ gfrq = (period * 24 / 1000) - 1;
+
+ pca963x->cmd = BLINK_SET;
+ pca963x->gdc = gdc;
+ pca963x->gfrq = gfrq;
+
+ /*
+ * Must use workqueue for the actual I/O since I2C operations
+ * can sleep.
+ */
+ schedule_work(&pca963x->work);
+
+ *delay_on = time_on;
+ *delay_off = time_off;
+
+ return 0;
+}
+
+#if IS_ENABLED(CONFIG_OF)
+static struct pca963x_platform_data *
+pca963x_dt_init(struct i2c_client *client, struct pca963x_chipdef *chip)
+{
+ struct device_node *np = client->dev.of_node, *child;
+ struct pca963x_platform_data *pdata;
+ struct led_info *pca963x_leds;
+ int count;
+
+ count = of_get_child_count(np);
+ if (!count || count > chip->n_leds)
+ return ERR_PTR(-ENODEV);
+
+ pca963x_leds = devm_kzalloc(&client->dev,
+ sizeof(struct led_info) * chip->n_leds, GFP_KERNEL);
+ if (!pca963x_leds)
+ return ERR_PTR(-ENOMEM);
+
+ for_each_child_of_node(np, child) {
+ struct led_info led;
+ u32 reg;
+ int res;
+
+ res = of_property_read_u32(child, "reg", ®);
+ if ((res != 0) || (reg >= chip->n_leds))
+ continue;
+ led.name =
+ of_get_property(child, "label", NULL) ? : child->name;
+ led.default_trigger =
+ of_get_property(child, "linux,default-trigger", NULL);
+ pca963x_leds[reg] = led;
+ }
+ pdata = devm_kzalloc(&client->dev,
+ sizeof(struct pca963x_platform_data), GFP_KERNEL);
+ if (!pdata)
+ return ERR_PTR(-ENOMEM);
+
+ pdata->leds.leds = pca963x_leds;
+ pdata->leds.num_leds = chip->n_leds;
+
+ /* default to open-drain unless totem pole (push-pull) is specified */
+ if (of_property_read_bool(np, "nxp,totem-pole"))
+ pdata->outdrv = PCA963X_TOTEM_POLE;
+ else
+ pdata->outdrv = PCA963X_OPEN_DRAIN;
+
+ /* default to software blinking unless hardware blinking is specified */
+ if (of_property_read_bool(np, "nxp,hw-blink"))
+ pdata->blink_type = PCA963X_HW_BLINK;
+ else
+ pdata->blink_type = PCA963X_SW_BLINK;
+
+ return pdata;
+}
+
+static const struct of_device_id of_pca963x_match[] = {
+ { .compatible = "nxp,pca9632", },
+ { .compatible = "nxp,pca9633", },
+ { .compatible = "nxp,pca9634", },
+ {},
+};
+#else
+static struct pca963x_platform_data *
+pca963x_dt_init(struct i2c_client *client, struct pca963x_chipdef *chip)
+{
+ return ERR_PTR(-ENODEV);
+}
+#endif
+
+static int pca963x_probe(struct i2c_client *client,
+ const struct i2c_device_id *id)
+{
+ struct pca963x *pca963x_chip;
+ struct pca963x_led *pca963x;
+ struct pca963x_platform_data *pdata;
+ struct pca963x_chipdef *chip;
+ int i, err;
+
+ chip = &pca963x_chipdefs[id->driver_data];
+ pdata = dev_get_platdata(&client->dev);
+
+ if (!pdata) {
+ pdata = pca963x_dt_init(client, chip);
+ if (IS_ERR(pdata)) {
+ dev_warn(&client->dev, "could not parse configuration\n");
+ pdata = NULL;
+ }
+ }
+
+ if (pdata && (pdata->leds.num_leds < 1 ||
+ pdata->leds.num_leds > chip->n_leds)) {
+ dev_err(&client->dev, "board info must claim 1-%d LEDs",
+ chip->n_leds);
+ return -EINVAL;
+ }
+
+ pca963x_chip = devm_kzalloc(&client->dev, sizeof(*pca963x_chip),
+ GFP_KERNEL);
+ if (!pca963x_chip)
+ return -ENOMEM;
+ pca963x = devm_kzalloc(&client->dev, chip->n_leds * sizeof(*pca963x),
+ GFP_KERNEL);
+ if (!pca963x)
+ return -ENOMEM;
+
+ i2c_set_clientdata(client, pca963x_chip);
+
+ mutex_init(&pca963x_chip->mutex);
+ pca963x_chip->chipdef = chip;
+ pca963x_chip->client = client;
+ pca963x_chip->leds = pca963x;
+
+ /* Turn off LEDs by default*/
+ i2c_smbus_write_byte_data(client, chip->ledout_base, 0x00);
+ if (chip->n_leds > 4)
+ i2c_smbus_write_byte_data(client, chip->ledout_base + 1, 0x00);
+
+ for (i = 0; i < chip->n_leds; i++) {
+ pca963x[i].led_num = i;
+ pca963x[i].chip = pca963x_chip;
+
+ /* Platform data can specify LED names and default triggers */
+ if (pdata && i < pdata->leds.num_leds) {
+ if (pdata->leds.leds[i].name)
+ snprintf(pca963x[i].name,
+ sizeof(pca963x[i].name), "pca963x:%s",
+ pdata->leds.leds[i].name);
+ if (pdata->leds.leds[i].default_trigger)
+ pca963x[i].led_cdev.default_trigger =
+ pdata->leds.leds[i].default_trigger;
+ }
+ if (!pdata || i >= pdata->leds.num_leds ||
+ !pdata->leds.leds[i].name)
+ snprintf(pca963x[i].name, sizeof(pca963x[i].name),
+ "pca963x:%d:%.2x:%d", client->adapter->nr,
+ client->addr, i);
+
+ pca963x[i].led_cdev.name = pca963x[i].name;
+ pca963x[i].led_cdev.brightness_set = pca963x_led_set;
+
+ if (pdata && pdata->blink_type == PCA963X_HW_BLINK)
+ pca963x[i].led_cdev.blink_set = pca963x_blink_set;
+
+ INIT_WORK(&pca963x[i].work, pca963x_work);
+
+ err = led_classdev_register(&client->dev, &pca963x[i].led_cdev);
+ if (err < 0)
+ goto exit;
+ }
+
+ /* Disable LED all-call address and set normal mode */
+ i2c_smbus_write_byte_data(client, PCA963X_MODE1, 0x00);
+
+ /* Configure output: open-drain or totem pole (push-pull) */
+ if (pdata && pdata->outdrv == PCA963X_OPEN_DRAIN)
+ i2c_smbus_write_byte_data(client, PCA963X_MODE2, 0x01);
+
+ return 0;
+
+exit:
+ while (i--) {
+ led_classdev_unregister(&pca963x[i].led_cdev);
+ cancel_work_sync(&pca963x[i].work);
+ }
+
+ return err;
+}
+
+static int pca963x_remove(struct i2c_client *client)
+{
+ struct pca963x *pca963x = i2c_get_clientdata(client);
+ int i;
+
+ for (i = 0; i < pca963x->chipdef->n_leds; i++) {
+ led_classdev_unregister(&pca963x->leds[i].led_cdev);
+ cancel_work_sync(&pca963x->leds[i].work);
+ }
+
+ return 0;
+}
+
+static struct i2c_driver pca963x_driver = {
+ .driver = {
+ .name = "leds-pca963x",
+ .owner = THIS_MODULE,
+ .of_match_table = of_match_ptr(of_pca963x_match),
+ },
+ .probe = pca963x_probe,
+ .remove = pca963x_remove,
+ .id_table = pca963x_id,
+};
+
+module_i2c_driver(pca963x_driver);
+
+MODULE_AUTHOR("Peter Meerwald <p.meerwald@bct-electronic.com>");
+MODULE_DESCRIPTION("PCA963X LED driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/leds/leds-pwm.c b/drivers/leds/leds-pwm.c
index faf52c0..bb6f948 100644
--- a/drivers/leds/leds-pwm.c
+++ b/drivers/leds/leds-pwm.c
@@ -147,7 +147,7 @@
static int led_pwm_probe(struct platform_device *pdev)
{
- struct led_pwm_platform_data *pdata = pdev->dev.platform_data;
+ struct led_pwm_platform_data *pdata = dev_get_platdata(&pdev->dev);
struct led_pwm_priv *priv;
int i, ret = 0;
diff --git a/drivers/leds/leds-regulator.c b/drivers/leds/leds-regulator.c
index 4253a9b..358430d 100644
--- a/drivers/leds/leds-regulator.c
+++ b/drivers/leds/leds-regulator.c
@@ -142,7 +142,8 @@
static int regulator_led_probe(struct platform_device *pdev)
{
- struct led_regulator_platform_data *pdata = pdev->dev.platform_data;
+ struct led_regulator_platform_data *pdata =
+ dev_get_platdata(&pdev->dev);
struct regulator_led *led;
struct regulator *vcc;
int ret = 0;
diff --git a/drivers/leds/leds-s3c24xx.c b/drivers/leds/leds-s3c24xx.c
index e1a0df6..76483fb 100644
--- a/drivers/leds/leds-s3c24xx.c
+++ b/drivers/leds/leds-s3c24xx.c
@@ -71,7 +71,7 @@
static int s3c24xx_led_probe(struct platform_device *dev)
{
- struct s3c24xx_led_platdata *pdata = dev->dev.platform_data;
+ struct s3c24xx_led_platdata *pdata = dev_get_platdata(&dev->dev);
struct s3c24xx_gpio_led *led;
int ret;
diff --git a/drivers/leds/leds-ss4200.c b/drivers/leds/leds-ss4200.c
index 64e204e..5b8f938 100644
--- a/drivers/leds/leds-ss4200.c
+++ b/drivers/leds/leds-ss4200.c
@@ -91,7 +91,7 @@
* detected as working, but in reality it is not) as low as
* possible.
*/
-static struct dmi_system_id __initdata nas_led_whitelist[] = {
+static struct dmi_system_id nas_led_whitelist[] __initdata = {
{
.callback = ss4200_led_dmi_callback,
.ident = "Intel SS4200-E",
@@ -197,7 +197,7 @@
spin_unlock(&nasgpio_gpio_lock);
}
-u32 nasgpio_led_get_attr(struct led_classdev *led_cdev, u32 port)
+static u32 nasgpio_led_get_attr(struct led_classdev *led_cdev, u32 port)
{
struct nasgpio_led *led = led_classdev_to_nasgpio_led(led_cdev);
u32 gpio_in;
diff --git a/drivers/leds/leds-tca6507.c b/drivers/leds/leds-tca6507.c
index 98fe021..8cc304f 100644
--- a/drivers/leds/leds-tca6507.c
+++ b/drivers/leds/leds-tca6507.c
@@ -737,7 +737,7 @@
int i = 0;
adapter = to_i2c_adapter(client->dev.parent);
- pdata = client->dev.platform_data;
+ pdata = dev_get_platdata(&client->dev);
if (!i2c_check_functionality(adapter, I2C_FUNC_I2C))
return -EIO;
diff --git a/drivers/leds/leds-wm831x-status.c b/drivers/leds/leds-wm831x-status.c
index 120815a..0a1a13f 100644
--- a/drivers/leds/leds-wm831x-status.c
+++ b/drivers/leds/leds-wm831x-status.c
@@ -230,9 +230,9 @@
int id = pdev->id % ARRAY_SIZE(chip_pdata->status);
int ret;
- res = platform_get_resource(pdev, IORESOURCE_IO, 0);
+ res = platform_get_resource(pdev, IORESOURCE_REG, 0);
if (res == NULL) {
- dev_err(&pdev->dev, "No I/O resource\n");
+ dev_err(&pdev->dev, "No register resource\n");
ret = -EINVAL;
goto err;
}
@@ -246,8 +246,8 @@
drvdata->wm831x = wm831x;
drvdata->reg = res->start;
- if (wm831x->dev->platform_data)
- chip_pdata = wm831x->dev->platform_data;
+ if (dev_get_platdata(wm831x->dev))
+ chip_pdata = dev_get_platdata(wm831x->dev);
else
chip_pdata = NULL;
diff --git a/drivers/leds/leds-wm8350.c b/drivers/leds/leds-wm8350.c
index 8a181d5..3f75fd2 100644
--- a/drivers/leds/leds-wm8350.c
+++ b/drivers/leds/leds-wm8350.c
@@ -203,7 +203,7 @@
{
struct regulator *isink, *dcdc;
struct wm8350_led *led;
- struct wm8350_led_platform_data *pdata = pdev->dev.platform_data;
+ struct wm8350_led_platform_data *pdata = dev_get_platdata(&pdev->dev);
int i;
if (pdata == NULL) {
diff --git a/drivers/leds/trigger/ledtrig-backlight.c b/drivers/leds/trigger/ledtrig-backlight.c
index 3c9c88a..47e55aa 100644
--- a/drivers/leds/trigger/ledtrig-backlight.c
+++ b/drivers/leds/trigger/ledtrig-backlight.c
@@ -36,26 +36,28 @@
struct bl_trig_notifier, notifier);
struct led_classdev *led = n->led;
struct fb_event *fb_event = data;
- int *blank = fb_event->data;
- int new_status = *blank ? BLANK : UNBLANK;
+ int *blank;
+ int new_status;
- switch (event) {
- case FB_EVENT_BLANK:
- if (new_status == n->old_status)
- break;
+ /* If we aren't interested in this event, skip it immediately ... */
+ if (event != FB_EVENT_BLANK)
+ return 0;
- if ((n->old_status == UNBLANK) ^ n->invert) {
- n->brightness = led->brightness;
- __led_set_brightness(led, LED_OFF);
- } else {
- __led_set_brightness(led, n->brightness);
- }
+ blank = fb_event->data;
+ new_status = *blank ? BLANK : UNBLANK;
- n->old_status = new_status;
+ if (new_status == n->old_status)
+ return 0;
- break;
+ if ((n->old_status == UNBLANK) ^ n->invert) {
+ n->brightness = led->brightness;
+ __led_set_brightness(led, LED_OFF);
+ } else {
+ __led_set_brightness(led, n->brightness);
}
+ n->old_status = new_status;
+
return 0;
}
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index ee37288..f9764e6 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -597,24 +597,19 @@
return 0;
}
-static int bch_mca_shrink(struct shrinker *shrink, struct shrink_control *sc)
+static unsigned long bch_mca_scan(struct shrinker *shrink,
+ struct shrink_control *sc)
{
struct cache_set *c = container_of(shrink, struct cache_set, shrink);
struct btree *b, *t;
unsigned long i, nr = sc->nr_to_scan;
+ unsigned long freed = 0;
if (c->shrinker_disabled)
- return 0;
+ return SHRINK_STOP;
if (c->try_harder)
- return 0;
-
- /*
- * If nr == 0, we're supposed to return the number of items we have
- * cached. Not allowed to return -1.
- */
- if (!nr)
- return mca_can_free(c) * c->btree_pages;
+ return SHRINK_STOP;
/* Return -1 if we can't do anything right now */
if (sc->gfp_mask & __GFP_WAIT)
@@ -634,14 +629,14 @@
i = 0;
list_for_each_entry_safe(b, t, &c->btree_cache_freeable, list) {
- if (!nr)
+ if (freed >= nr)
break;
if (++i > 3 &&
!mca_reap(b, NULL, 0)) {
mca_data_free(b);
rw_unlock(true, b);
- --nr;
+ freed++;
}
}
@@ -652,7 +647,7 @@
if (list_empty(&c->btree_cache))
goto out;
- for (i = 0; nr && i < c->bucket_cache_used; i++) {
+ for (i = 0; (nr--) && i < c->bucket_cache_used; i++) {
b = list_first_entry(&c->btree_cache, struct btree, list);
list_rotate_left(&c->btree_cache);
@@ -661,14 +656,27 @@
mca_bucket_free(b);
mca_data_free(b);
rw_unlock(true, b);
- --nr;
+ freed++;
} else
b->accessed = 0;
}
out:
- nr = mca_can_free(c) * c->btree_pages;
mutex_unlock(&c->bucket_lock);
- return nr;
+ return freed;
+}
+
+static unsigned long bch_mca_count(struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ struct cache_set *c = container_of(shrink, struct cache_set, shrink);
+
+ if (c->shrinker_disabled)
+ return 0;
+
+ if (c->try_harder)
+ return 0;
+
+ return mca_can_free(c) * c->btree_pages;
}
void bch_btree_cache_free(struct cache_set *c)
@@ -737,7 +745,8 @@
c->verify_data = NULL;
#endif
- c->shrink.shrink = bch_mca_shrink;
+ c->shrink.count_objects = bch_mca_count;
+ c->shrink.scan_objects = bch_mca_scan;
c->shrink.seeks = 4;
c->shrink.batch = c->btree_pages * 2;
register_shrinker(&c->shrink);
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 12a2c28..4fe6ab2 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -556,7 +556,7 @@
struct shrink_control sc;
sc.gfp_mask = GFP_KERNEL;
sc.nr_to_scan = strtoul_or_return(buf);
- c->shrink.shrink(&c->shrink, &sc);
+ c->shrink.scan_objects(&c->shrink, &sc);
}
sysfs_strtoul(congested_read_threshold_us,
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 5227e07..173cbb2 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -1425,62 +1425,75 @@
unsigned long max_jiffies)
{
if (jiffies - b->last_accessed < max_jiffies)
- return 1;
+ return 0;
if (!(gfp & __GFP_IO)) {
if (test_bit(B_READING, &b->state) ||
test_bit(B_WRITING, &b->state) ||
test_bit(B_DIRTY, &b->state))
- return 1;
+ return 0;
}
if (b->hold_count)
- return 1;
+ return 0;
__make_buffer_clean(b);
__unlink_buffer(b);
__free_buffer_wake(b);
- return 0;
+ return 1;
}
-static void __scan(struct dm_bufio_client *c, unsigned long nr_to_scan,
- struct shrink_control *sc)
+static long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan,
+ gfp_t gfp_mask)
{
int l;
struct dm_buffer *b, *tmp;
+ long freed = 0;
for (l = 0; l < LIST_SIZE; l++) {
- list_for_each_entry_safe_reverse(b, tmp, &c->lru[l], lru_list)
- if (!__cleanup_old_buffer(b, sc->gfp_mask, 0) &&
- !--nr_to_scan)
- return;
+ list_for_each_entry_safe_reverse(b, tmp, &c->lru[l], lru_list) {
+ freed += __cleanup_old_buffer(b, gfp_mask, 0);
+ if (!--nr_to_scan)
+ break;
+ }
dm_bufio_cond_resched();
}
+ return freed;
}
-static int shrink(struct shrinker *shrinker, struct shrink_control *sc)
+static unsigned long
+dm_bufio_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
{
- struct dm_bufio_client *c =
- container_of(shrinker, struct dm_bufio_client, shrinker);
- unsigned long r;
- unsigned long nr_to_scan = sc->nr_to_scan;
+ struct dm_bufio_client *c;
+ unsigned long freed;
+ c = container_of(shrink, struct dm_bufio_client, shrinker);
if (sc->gfp_mask & __GFP_IO)
dm_bufio_lock(c);
else if (!dm_bufio_trylock(c))
- return !nr_to_scan ? 0 : -1;
+ return SHRINK_STOP;
- if (nr_to_scan)
- __scan(c, nr_to_scan, sc);
-
- r = c->n_buffers[LIST_CLEAN] + c->n_buffers[LIST_DIRTY];
- if (r > INT_MAX)
- r = INT_MAX;
-
+ freed = __scan(c, sc->nr_to_scan, sc->gfp_mask);
dm_bufio_unlock(c);
+ return freed;
+}
- return r;
+static unsigned long
+dm_bufio_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
+{
+ struct dm_bufio_client *c;
+ unsigned long count;
+
+ c = container_of(shrink, struct dm_bufio_client, shrinker);
+ if (sc->gfp_mask & __GFP_IO)
+ dm_bufio_lock(c);
+ else if (!dm_bufio_trylock(c))
+ return 0;
+
+ count = c->n_buffers[LIST_CLEAN] + c->n_buffers[LIST_DIRTY];
+ dm_bufio_unlock(c);
+ return count;
}
/*
@@ -1582,7 +1595,8 @@
__cache_size_refresh();
mutex_unlock(&dm_bufio_clients_lock);
- c->shrinker.shrink = shrink;
+ c->shrinker.count_objects = dm_bufio_shrink_count;
+ c->shrinker.scan_objects = dm_bufio_shrink_scan;
c->shrinker.seeks = 1;
c->shrinker.batch = 0;
register_shrinker(&c->shrinker);
@@ -1669,7 +1683,7 @@
struct dm_buffer *b;
b = list_entry(c->lru[LIST_CLEAN].prev,
struct dm_buffer, lru_list);
- if (__cleanup_old_buffer(b, 0, max_age * HZ))
+ if (!__cleanup_old_buffer(b, 0, max_age * HZ))
break;
dm_bufio_cond_resched();
}
diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig
index 8068d7b..c7caf94 100644
--- a/drivers/media/platform/Kconfig
+++ b/drivers/media/platform/Kconfig
@@ -203,7 +203,7 @@
config VIDEO_SH_VEU
tristate "SuperH VEU mem2mem video processing driver"
- depends on VIDEO_DEV && VIDEO_V4L2 && GENERIC_HARDIRQS && HAS_DMA
+ depends on VIDEO_DEV && VIDEO_V4L2 && HAS_DMA
select VIDEOBUF2_DMA_CONTIG
select V4L2_MEM2MEM_DEV
help
diff --git a/drivers/media/radio/Kconfig b/drivers/media/radio/Kconfig
index 39882dd..6ecdc39 100644
--- a/drivers/media/radio/Kconfig
+++ b/drivers/media/radio/Kconfig
@@ -214,7 +214,7 @@
config RADIO_WL1273
tristate "Texas Instruments WL1273 I2C FM Radio"
- depends on I2C && VIDEO_V4L2 && GENERIC_HARDIRQS
+ depends on I2C && VIDEO_V4L2
select MFD_CORE
select MFD_WL1273_CORE
select FW_LOADER
diff --git a/drivers/memstick/core/Kconfig b/drivers/memstick/core/Kconfig
index 95f1814..1d38949 100644
--- a/drivers/memstick/core/Kconfig
+++ b/drivers/memstick/core/Kconfig
@@ -24,3 +24,15 @@
support. This provides a block device driver, which you can use
to mount the filesystem. Almost everyone wishing MemoryStick
support should say Y or M here.
+
+config MS_BLOCK
+ tristate "MemoryStick Standard device driver"
+ depends on BLOCK
+ help
+ Say Y here to enable the MemoryStick Standard device driver
+ support. This provides a block device driver, which you can use
+ to mount the filesystem.
+ This driver works with old (bulky) MemoryStick and MemoryStick Duo
+ but not PRO. Say Y if you have such card.
+ Driver is new and not yet well tested, thus it can damage your card
+ (even permanently)
diff --git a/drivers/memstick/core/Makefile b/drivers/memstick/core/Makefile
index ecd0299..0d7f90c 100644
--- a/drivers/memstick/core/Makefile
+++ b/drivers/memstick/core/Makefile
@@ -3,5 +3,5 @@
#
obj-$(CONFIG_MEMSTICK) += memstick.o
-
+obj-$(CONFIG_MS_BLOCK) += ms_block.o
obj-$(CONFIG_MSPRO_BLOCK) += mspro_block.o
diff --git a/drivers/memstick/core/ms_block.c b/drivers/memstick/core/ms_block.c
new file mode 100644
index 0000000..08e7023
--- /dev/null
+++ b/drivers/memstick/core/ms_block.c
@@ -0,0 +1,2385 @@
+/*
+ * ms_block.c - Sony MemoryStick (legacy) storage support
+
+ * Copyright (C) 2013 Maxim Levitsky <maximlevitsky@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Minor portions of the driver were copied from mspro_block.c which is
+ * Copyright (C) 2007 Alex Dubov <oakad@yahoo.com>
+ *
+ */
+#define DRIVER_NAME "ms_block"
+#define pr_fmt(fmt) DRIVER_NAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/blkdev.h>
+#include <linux/memstick.h>
+#include <linux/idr.h>
+#include <linux/hdreg.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+#include <linux/random.h>
+#include <linux/bitmap.h>
+#include <linux/scatterlist.h>
+#include <linux/jiffies.h>
+#include <linux/workqueue.h>
+#include <linux/mutex.h>
+#include "ms_block.h"
+
+static int debug;
+static int cache_flush_timeout = 1000;
+static bool verify_writes;
+
+/*
+ * Copies section of 'sg_from' starting from offset 'offset' and with length
+ * 'len' To another scatterlist of to_nents enties
+ */
+static size_t msb_sg_copy(struct scatterlist *sg_from,
+ struct scatterlist *sg_to, int to_nents, size_t offset, size_t len)
+{
+ size_t copied = 0;
+
+ while (offset > 0) {
+ if (offset >= sg_from->length) {
+ if (sg_is_last(sg_from))
+ return 0;
+
+ offset -= sg_from->length;
+ sg_from = sg_next(sg_from);
+ continue;
+ }
+
+ copied = min(len, sg_from->length - offset);
+ sg_set_page(sg_to, sg_page(sg_from),
+ copied, sg_from->offset + offset);
+
+ len -= copied;
+ offset = 0;
+
+ if (sg_is_last(sg_from) || !len)
+ goto out;
+
+ sg_to = sg_next(sg_to);
+ to_nents--;
+ sg_from = sg_next(sg_from);
+ }
+
+ while (len > sg_from->length && to_nents--) {
+ len -= sg_from->length;
+ copied += sg_from->length;
+
+ sg_set_page(sg_to, sg_page(sg_from),
+ sg_from->length, sg_from->offset);
+
+ if (sg_is_last(sg_from) || !len)
+ goto out;
+
+ sg_from = sg_next(sg_from);
+ sg_to = sg_next(sg_to);
+ }
+
+ if (len && to_nents) {
+ sg_set_page(sg_to, sg_page(sg_from), len, sg_from->offset);
+ copied += len;
+ }
+out:
+ sg_mark_end(sg_to);
+ return copied;
+}
+
+/*
+ * Compares section of 'sg' starting from offset 'offset' and with length 'len'
+ * to linear buffer of length 'len' at address 'buffer'
+ * Returns 0 if equal and -1 otherwice
+ */
+static int msb_sg_compare_to_buffer(struct scatterlist *sg,
+ size_t offset, u8 *buffer, size_t len)
+{
+ int retval = 0, cmplen;
+ struct sg_mapping_iter miter;
+
+ sg_miter_start(&miter, sg, sg_nents(sg),
+ SG_MITER_ATOMIC | SG_MITER_FROM_SG);
+
+ while (sg_miter_next(&miter) && len > 0) {
+ if (offset >= miter.length) {
+ offset -= miter.length;
+ continue;
+ }
+
+ cmplen = min(miter.length - offset, len);
+ retval = memcmp(miter.addr + offset, buffer, cmplen) ? -1 : 0;
+ if (retval)
+ break;
+
+ buffer += cmplen;
+ len -= cmplen;
+ offset = 0;
+ }
+
+ if (!retval && len)
+ retval = -1;
+
+ sg_miter_stop(&miter);
+ return retval;
+}
+
+
+/* Get zone at which block with logical address 'lba' lives
+ * Flash is broken into zones.
+ * Each zone consists of 512 eraseblocks, out of which in first
+ * zone 494 are used and 496 are for all following zones.
+ * Therefore zone #0 hosts blocks 0-493, zone #1 blocks 494-988, etc...
+*/
+static int msb_get_zone_from_lba(int lba)
+{
+ if (lba < 494)
+ return 0;
+ return ((lba - 494) / 496) + 1;
+}
+
+/* Get zone of physical block. Trivial */
+static int msb_get_zone_from_pba(int pba)
+{
+ return pba / MS_BLOCKS_IN_ZONE;
+}
+
+/* Debug test to validate free block counts */
+static int msb_validate_used_block_bitmap(struct msb_data *msb)
+{
+ int total_free_blocks = 0;
+ int i;
+
+ if (!debug)
+ return 0;
+
+ for (i = 0; i < msb->zone_count; i++)
+ total_free_blocks += msb->free_block_count[i];
+
+ if (msb->block_count - bitmap_weight(msb->used_blocks_bitmap,
+ msb->block_count) == total_free_blocks)
+ return 0;
+
+ pr_err("BUG: free block counts don't match the bitmap");
+ msb->read_only = true;
+ return -EINVAL;
+}
+
+/* Mark physical block as used */
+static void msb_mark_block_used(struct msb_data *msb, int pba)
+{
+ int zone = msb_get_zone_from_pba(pba);
+
+ if (test_bit(pba, msb->used_blocks_bitmap)) {
+ pr_err(
+ "BUG: attempt to mark already used pba %d as used", pba);
+ msb->read_only = true;
+ return;
+ }
+
+ if (msb_validate_used_block_bitmap(msb))
+ return;
+
+ /* No races because all IO is single threaded */
+ __set_bit(pba, msb->used_blocks_bitmap);
+ msb->free_block_count[zone]--;
+}
+
+/* Mark physical block as free */
+static void msb_mark_block_unused(struct msb_data *msb, int pba)
+{
+ int zone = msb_get_zone_from_pba(pba);
+
+ if (!test_bit(pba, msb->used_blocks_bitmap)) {
+ pr_err("BUG: attempt to mark already unused pba %d as unused" , pba);
+ msb->read_only = true;
+ return;
+ }
+
+ if (msb_validate_used_block_bitmap(msb))
+ return;
+
+ /* No races because all IO is single threaded */
+ __clear_bit(pba, msb->used_blocks_bitmap);
+ msb->free_block_count[zone]++;
+}
+
+/* Invalidate current register window */
+static void msb_invalidate_reg_window(struct msb_data *msb)
+{
+ msb->reg_addr.w_offset = offsetof(struct ms_register, id);
+ msb->reg_addr.w_length = sizeof(struct ms_id_register);
+ msb->reg_addr.r_offset = offsetof(struct ms_register, id);
+ msb->reg_addr.r_length = sizeof(struct ms_id_register);
+ msb->addr_valid = false;
+}
+
+/* Start a state machine */
+static int msb_run_state_machine(struct msb_data *msb, int (*state_func)
+ (struct memstick_dev *card, struct memstick_request **req))
+{
+ struct memstick_dev *card = msb->card;
+
+ WARN_ON(msb->state != -1);
+ msb->int_polling = false;
+ msb->state = 0;
+ msb->exit_error = 0;
+
+ memset(&card->current_mrq, 0, sizeof(card->current_mrq));
+
+ card->next_request = state_func;
+ memstick_new_req(card->host);
+ wait_for_completion(&card->mrq_complete);
+
+ WARN_ON(msb->state != -1);
+ return msb->exit_error;
+}
+
+/* State machines call that to exit */
+static int msb_exit_state_machine(struct msb_data *msb, int error)
+{
+ WARN_ON(msb->state == -1);
+
+ msb->state = -1;
+ msb->exit_error = error;
+ msb->card->next_request = h_msb_default_bad;
+
+ /* Invalidate reg window on errors */
+ if (error)
+ msb_invalidate_reg_window(msb);
+
+ complete(&msb->card->mrq_complete);
+ return -ENXIO;
+}
+
+/* read INT register */
+static int msb_read_int_reg(struct msb_data *msb, long timeout)
+{
+ struct memstick_request *mrq = &msb->card->current_mrq;
+
+ WARN_ON(msb->state == -1);
+
+ if (!msb->int_polling) {
+ msb->int_timeout = jiffies +
+ msecs_to_jiffies(timeout == -1 ? 500 : timeout);
+ msb->int_polling = true;
+ } else if (time_after(jiffies, msb->int_timeout)) {
+ mrq->data[0] = MEMSTICK_INT_CMDNAK;
+ return 0;
+ }
+
+ if ((msb->caps & MEMSTICK_CAP_AUTO_GET_INT) &&
+ mrq->need_card_int && !mrq->error) {
+ mrq->data[0] = mrq->int_reg;
+ mrq->need_card_int = false;
+ return 0;
+ } else {
+ memstick_init_req(mrq, MS_TPC_GET_INT, NULL, 1);
+ return 1;
+ }
+}
+
+/* Read a register */
+static int msb_read_regs(struct msb_data *msb, int offset, int len)
+{
+ struct memstick_request *req = &msb->card->current_mrq;
+
+ if (msb->reg_addr.r_offset != offset ||
+ msb->reg_addr.r_length != len || !msb->addr_valid) {
+
+ msb->reg_addr.r_offset = offset;
+ msb->reg_addr.r_length = len;
+ msb->addr_valid = true;
+
+ memstick_init_req(req, MS_TPC_SET_RW_REG_ADRS,
+ &msb->reg_addr, sizeof(msb->reg_addr));
+ return 0;
+ }
+
+ memstick_init_req(req, MS_TPC_READ_REG, NULL, len);
+ return 1;
+}
+
+/* Write a card register */
+static int msb_write_regs(struct msb_data *msb, int offset, int len, void *buf)
+{
+ struct memstick_request *req = &msb->card->current_mrq;
+
+ if (msb->reg_addr.w_offset != offset ||
+ msb->reg_addr.w_length != len || !msb->addr_valid) {
+
+ msb->reg_addr.w_offset = offset;
+ msb->reg_addr.w_length = len;
+ msb->addr_valid = true;
+
+ memstick_init_req(req, MS_TPC_SET_RW_REG_ADRS,
+ &msb->reg_addr, sizeof(msb->reg_addr));
+ return 0;
+ }
+
+ memstick_init_req(req, MS_TPC_WRITE_REG, buf, len);
+ return 1;
+}
+
+/* Handler for absence of IO */
+static int h_msb_default_bad(struct memstick_dev *card,
+ struct memstick_request **mrq)
+{
+ return -ENXIO;
+}
+
+/*
+ * This function is a handler for reads of one page from device.
+ * Writes output to msb->current_sg, takes sector address from msb->reg.param
+ * Can also be used to read extra data only. Set params accordintly.
+ */
+static int h_msb_read_page(struct memstick_dev *card,
+ struct memstick_request **out_mrq)
+{
+ struct msb_data *msb = memstick_get_drvdata(card);
+ struct memstick_request *mrq = *out_mrq = &card->current_mrq;
+ struct scatterlist sg[2];
+ u8 command, intreg;
+
+ if (mrq->error) {
+ dbg("read_page, unknown error");
+ return msb_exit_state_machine(msb, mrq->error);
+ }
+again:
+ switch (msb->state) {
+ case MSB_RP_SEND_BLOCK_ADDRESS:
+ /* msb_write_regs sometimes "fails" because it needs to update
+ the reg window, and thus it returns request for that.
+ Then we stay in this state and retry */
+ if (!msb_write_regs(msb,
+ offsetof(struct ms_register, param),
+ sizeof(struct ms_param_register),
+ (unsigned char *)&msb->regs.param))
+ return 0;
+
+ msb->state = MSB_RP_SEND_READ_COMMAND;
+ return 0;
+
+ case MSB_RP_SEND_READ_COMMAND:
+ command = MS_CMD_BLOCK_READ;
+ memstick_init_req(mrq, MS_TPC_SET_CMD, &command, 1);
+ msb->state = MSB_RP_SEND_INT_REQ;
+ return 0;
+
+ case MSB_RP_SEND_INT_REQ:
+ msb->state = MSB_RP_RECEIVE_INT_REQ_RESULT;
+ /* If dont actually need to send the int read request (only in
+ serial mode), then just fall through */
+ if (msb_read_int_reg(msb, -1))
+ return 0;
+ /* fallthrough */
+
+ case MSB_RP_RECEIVE_INT_REQ_RESULT:
+ intreg = mrq->data[0];
+ msb->regs.status.interrupt = intreg;
+
+ if (intreg & MEMSTICK_INT_CMDNAK)
+ return msb_exit_state_machine(msb, -EIO);
+
+ if (!(intreg & MEMSTICK_INT_CED)) {
+ msb->state = MSB_RP_SEND_INT_REQ;
+ goto again;
+ }
+
+ msb->int_polling = false;
+ msb->state = (intreg & MEMSTICK_INT_ERR) ?
+ MSB_RP_SEND_READ_STATUS_REG : MSB_RP_SEND_OOB_READ;
+ goto again;
+
+ case MSB_RP_SEND_READ_STATUS_REG:
+ /* read the status register to understand source of the INT_ERR */
+ if (!msb_read_regs(msb,
+ offsetof(struct ms_register, status),
+ sizeof(struct ms_status_register)))
+ return 0;
+
+ msb->state = MSB_RP_RECEIVE_OOB_READ;
+ return 0;
+
+ case MSB_RP_RECIVE_STATUS_REG:
+ msb->regs.status = *(struct ms_status_register *)mrq->data;
+ msb->state = MSB_RP_SEND_OOB_READ;
+ /* fallthrough */
+
+ case MSB_RP_SEND_OOB_READ:
+ if (!msb_read_regs(msb,
+ offsetof(struct ms_register, extra_data),
+ sizeof(struct ms_extra_data_register)))
+ return 0;
+
+ msb->state = MSB_RP_RECEIVE_OOB_READ;
+ return 0;
+
+ case MSB_RP_RECEIVE_OOB_READ:
+ msb->regs.extra_data =
+ *(struct ms_extra_data_register *) mrq->data;
+ msb->state = MSB_RP_SEND_READ_DATA;
+ /* fallthrough */
+
+ case MSB_RP_SEND_READ_DATA:
+ /* Skip that state if we only read the oob */
+ if (msb->regs.param.cp == MEMSTICK_CP_EXTRA) {
+ msb->state = MSB_RP_RECEIVE_READ_DATA;
+ goto again;
+ }
+
+ sg_init_table(sg, ARRAY_SIZE(sg));
+ msb_sg_copy(msb->current_sg, sg, ARRAY_SIZE(sg),
+ msb->current_sg_offset,
+ msb->page_size);
+
+ memstick_init_req_sg(mrq, MS_TPC_READ_LONG_DATA, sg);
+ msb->state = MSB_RP_RECEIVE_READ_DATA;
+ return 0;
+
+ case MSB_RP_RECEIVE_READ_DATA:
+ if (!(msb->regs.status.interrupt & MEMSTICK_INT_ERR)) {
+ msb->current_sg_offset += msb->page_size;
+ return msb_exit_state_machine(msb, 0);
+ }
+
+ if (msb->regs.status.status1 & MEMSTICK_UNCORR_ERROR) {
+ dbg("read_page: uncorrectable error");
+ return msb_exit_state_machine(msb, -EBADMSG);
+ }
+
+ if (msb->regs.status.status1 & MEMSTICK_CORR_ERROR) {
+ dbg("read_page: correctable error");
+ msb->current_sg_offset += msb->page_size;
+ return msb_exit_state_machine(msb, -EUCLEAN);
+ } else {
+ dbg("read_page: INT error, but no status error bits");
+ return msb_exit_state_machine(msb, -EIO);
+ }
+ }
+
+ BUG();
+}
+
+/*
+ * Handler of writes of exactly one block.
+ * Takes address from msb->regs.param.
+ * Writes same extra data to blocks, also taken
+ * from msb->regs.extra
+ * Returns -EBADMSG if write fails due to uncorrectable error, or -EIO if
+ * device refuses to take the command or something else
+ */
+static int h_msb_write_block(struct memstick_dev *card,
+ struct memstick_request **out_mrq)
+{
+ struct msb_data *msb = memstick_get_drvdata(card);
+ struct memstick_request *mrq = *out_mrq = &card->current_mrq;
+ struct scatterlist sg[2];
+ u8 intreg, command;
+
+ if (mrq->error)
+ return msb_exit_state_machine(msb, mrq->error);
+
+again:
+ switch (msb->state) {
+
+ /* HACK: Jmicon handling of TPCs between 8 and
+ * sizeof(memstick_request.data) is broken due to hardware
+ * bug in PIO mode that is used for these TPCs
+ * Therefore split the write
+ */
+
+ case MSB_WB_SEND_WRITE_PARAMS:
+ if (!msb_write_regs(msb,
+ offsetof(struct ms_register, param),
+ sizeof(struct ms_param_register),
+ &msb->regs.param))
+ return 0;
+
+ msb->state = MSB_WB_SEND_WRITE_OOB;
+ return 0;
+
+ case MSB_WB_SEND_WRITE_OOB:
+ if (!msb_write_regs(msb,
+ offsetof(struct ms_register, extra_data),
+ sizeof(struct ms_extra_data_register),
+ &msb->regs.extra_data))
+ return 0;
+ msb->state = MSB_WB_SEND_WRITE_COMMAND;
+ return 0;
+
+
+ case MSB_WB_SEND_WRITE_COMMAND:
+ command = MS_CMD_BLOCK_WRITE;
+ memstick_init_req(mrq, MS_TPC_SET_CMD, &command, 1);
+ msb->state = MSB_WB_SEND_INT_REQ;
+ return 0;
+
+ case MSB_WB_SEND_INT_REQ:
+ msb->state = MSB_WB_RECEIVE_INT_REQ;
+ if (msb_read_int_reg(msb, -1))
+ return 0;
+ /* fallthrough */
+
+ case MSB_WB_RECEIVE_INT_REQ:
+ intreg = mrq->data[0];
+ msb->regs.status.interrupt = intreg;
+
+ /* errors mean out of here, and fast... */
+ if (intreg & (MEMSTICK_INT_CMDNAK))
+ return msb_exit_state_machine(msb, -EIO);
+
+ if (intreg & MEMSTICK_INT_ERR)
+ return msb_exit_state_machine(msb, -EBADMSG);
+
+
+ /* for last page we need to poll CED */
+ if (msb->current_page == msb->pages_in_block) {
+ if (intreg & MEMSTICK_INT_CED)
+ return msb_exit_state_machine(msb, 0);
+ msb->state = MSB_WB_SEND_INT_REQ;
+ goto again;
+
+ }
+
+ /* for non-last page we need BREQ before writing next chunk */
+ if (!(intreg & MEMSTICK_INT_BREQ)) {
+ msb->state = MSB_WB_SEND_INT_REQ;
+ goto again;
+ }
+
+ msb->int_polling = false;
+ msb->state = MSB_WB_SEND_WRITE_DATA;
+ /* fallthrough */
+
+ case MSB_WB_SEND_WRITE_DATA:
+ sg_init_table(sg, ARRAY_SIZE(sg));
+
+ if (msb_sg_copy(msb->current_sg, sg, ARRAY_SIZE(sg),
+ msb->current_sg_offset,
+ msb->page_size) < msb->page_size)
+ return msb_exit_state_machine(msb, -EIO);
+
+ memstick_init_req_sg(mrq, MS_TPC_WRITE_LONG_DATA, sg);
+ mrq->need_card_int = 1;
+ msb->state = MSB_WB_RECEIVE_WRITE_CONFIRMATION;
+ return 0;
+
+ case MSB_WB_RECEIVE_WRITE_CONFIRMATION:
+ msb->current_page++;
+ msb->current_sg_offset += msb->page_size;
+ msb->state = MSB_WB_SEND_INT_REQ;
+ goto again;
+ default:
+ BUG();
+ }
+
+ return 0;
+}
+
+/*
+ * This function is used to send simple IO requests to device that consist
+ * of register write + command
+ */
+static int h_msb_send_command(struct memstick_dev *card,
+ struct memstick_request **out_mrq)
+{
+ struct msb_data *msb = memstick_get_drvdata(card);
+ struct memstick_request *mrq = *out_mrq = &card->current_mrq;
+ u8 intreg;
+
+ if (mrq->error) {
+ dbg("send_command: unknown error");
+ return msb_exit_state_machine(msb, mrq->error);
+ }
+again:
+ switch (msb->state) {
+
+ /* HACK: see h_msb_write_block */
+ case MSB_SC_SEND_WRITE_PARAMS: /* write param register*/
+ if (!msb_write_regs(msb,
+ offsetof(struct ms_register, param),
+ sizeof(struct ms_param_register),
+ &msb->regs.param))
+ return 0;
+ msb->state = MSB_SC_SEND_WRITE_OOB;
+ return 0;
+
+ case MSB_SC_SEND_WRITE_OOB:
+ if (!msb->command_need_oob) {
+ msb->state = MSB_SC_SEND_COMMAND;
+ goto again;
+ }
+
+ if (!msb_write_regs(msb,
+ offsetof(struct ms_register, extra_data),
+ sizeof(struct ms_extra_data_register),
+ &msb->regs.extra_data))
+ return 0;
+
+ msb->state = MSB_SC_SEND_COMMAND;
+ return 0;
+
+ case MSB_SC_SEND_COMMAND:
+ memstick_init_req(mrq, MS_TPC_SET_CMD, &msb->command_value, 1);
+ msb->state = MSB_SC_SEND_INT_REQ;
+ return 0;
+
+ case MSB_SC_SEND_INT_REQ:
+ msb->state = MSB_SC_RECEIVE_INT_REQ;
+ if (msb_read_int_reg(msb, -1))
+ return 0;
+ /* fallthrough */
+
+ case MSB_SC_RECEIVE_INT_REQ:
+ intreg = mrq->data[0];
+
+ if (intreg & MEMSTICK_INT_CMDNAK)
+ return msb_exit_state_machine(msb, -EIO);
+ if (intreg & MEMSTICK_INT_ERR)
+ return msb_exit_state_machine(msb, -EBADMSG);
+
+ if (!(intreg & MEMSTICK_INT_CED)) {
+ msb->state = MSB_SC_SEND_INT_REQ;
+ goto again;
+ }
+
+ return msb_exit_state_machine(msb, 0);
+ }
+
+ BUG();
+}
+
+/* Small handler for card reset */
+static int h_msb_reset(struct memstick_dev *card,
+ struct memstick_request **out_mrq)
+{
+ u8 command = MS_CMD_RESET;
+ struct msb_data *msb = memstick_get_drvdata(card);
+ struct memstick_request *mrq = *out_mrq = &card->current_mrq;
+
+ if (mrq->error)
+ return msb_exit_state_machine(msb, mrq->error);
+
+ switch (msb->state) {
+ case MSB_RS_SEND:
+ memstick_init_req(mrq, MS_TPC_SET_CMD, &command, 1);
+ mrq->need_card_int = 0;
+ msb->state = MSB_RS_CONFIRM;
+ return 0;
+ case MSB_RS_CONFIRM:
+ return msb_exit_state_machine(msb, 0);
+ }
+ BUG();
+}
+
+/* This handler is used to do serial->parallel switch */
+static int h_msb_parallel_switch(struct memstick_dev *card,
+ struct memstick_request **out_mrq)
+{
+ struct msb_data *msb = memstick_get_drvdata(card);
+ struct memstick_request *mrq = *out_mrq = &card->current_mrq;
+ struct memstick_host *host = card->host;
+
+ if (mrq->error) {
+ dbg("parallel_switch: error");
+ msb->regs.param.system &= ~MEMSTICK_SYS_PAM;
+ return msb_exit_state_machine(msb, mrq->error);
+ }
+
+ switch (msb->state) {
+ case MSB_PS_SEND_SWITCH_COMMAND:
+ /* Set the parallel interface on memstick side */
+ msb->regs.param.system |= MEMSTICK_SYS_PAM;
+
+ if (!msb_write_regs(msb,
+ offsetof(struct ms_register, param),
+ 1,
+ (unsigned char *)&msb->regs.param))
+ return 0;
+
+ msb->state = MSB_PS_SWICH_HOST;
+ return 0;
+
+ case MSB_PS_SWICH_HOST:
+ /* Set parallel interface on our side + send a dummy request
+ to see if card responds */
+ host->set_param(host, MEMSTICK_INTERFACE, MEMSTICK_PAR4);
+ memstick_init_req(mrq, MS_TPC_GET_INT, NULL, 1);
+ msb->state = MSB_PS_CONFIRM;
+ return 0;
+
+ case MSB_PS_CONFIRM:
+ return msb_exit_state_machine(msb, 0);
+ }
+
+ BUG();
+}
+
+static int msb_switch_to_parallel(struct msb_data *msb);
+
+/* Reset the card, to guard against hw errors beeing treated as bad blocks */
+static int msb_reset(struct msb_data *msb, bool full)
+{
+
+ bool was_parallel = msb->regs.param.system & MEMSTICK_SYS_PAM;
+ struct memstick_dev *card = msb->card;
+ struct memstick_host *host = card->host;
+ int error;
+
+ /* Reset the card */
+ msb->regs.param.system = MEMSTICK_SYS_BAMD;
+
+ if (full) {
+ error = host->set_param(host,
+ MEMSTICK_POWER, MEMSTICK_POWER_OFF);
+ if (error)
+ goto out_error;
+
+ msb_invalidate_reg_window(msb);
+
+ error = host->set_param(host,
+ MEMSTICK_POWER, MEMSTICK_POWER_ON);
+ if (error)
+ goto out_error;
+
+ error = host->set_param(host,
+ MEMSTICK_INTERFACE, MEMSTICK_SERIAL);
+ if (error) {
+out_error:
+ dbg("Failed to reset the host controller");
+ msb->read_only = true;
+ return -EFAULT;
+ }
+ }
+
+ error = msb_run_state_machine(msb, h_msb_reset);
+ if (error) {
+ dbg("Failed to reset the card");
+ msb->read_only = true;
+ return -ENODEV;
+ }
+
+ /* Set parallel mode */
+ if (was_parallel)
+ msb_switch_to_parallel(msb);
+ return 0;
+}
+
+/* Attempts to switch interface to parallel mode */
+static int msb_switch_to_parallel(struct msb_data *msb)
+{
+ int error;
+
+ error = msb_run_state_machine(msb, h_msb_parallel_switch);
+ if (error) {
+ pr_err("Switch to parallel failed");
+ msb->regs.param.system &= ~MEMSTICK_SYS_PAM;
+ msb_reset(msb, true);
+ return -EFAULT;
+ }
+
+ msb->caps |= MEMSTICK_CAP_AUTO_GET_INT;
+ return 0;
+}
+
+/* Changes overwrite flag on a page */
+static int msb_set_overwrite_flag(struct msb_data *msb,
+ u16 pba, u8 page, u8 flag)
+{
+ if (msb->read_only)
+ return -EROFS;
+
+ msb->regs.param.block_address = cpu_to_be16(pba);
+ msb->regs.param.page_address = page;
+ msb->regs.param.cp = MEMSTICK_CP_OVERWRITE;
+ msb->regs.extra_data.overwrite_flag = flag;
+ msb->command_value = MS_CMD_BLOCK_WRITE;
+ msb->command_need_oob = true;
+
+ dbg_verbose("changing overwrite flag to %02x for sector %d, page %d",
+ flag, pba, page);
+ return msb_run_state_machine(msb, h_msb_send_command);
+}
+
+static int msb_mark_bad(struct msb_data *msb, int pba)
+{
+ pr_notice("marking pba %d as bad", pba);
+ msb_reset(msb, true);
+ return msb_set_overwrite_flag(
+ msb, pba, 0, 0xFF & ~MEMSTICK_OVERWRITE_BKST);
+}
+
+static int msb_mark_page_bad(struct msb_data *msb, int pba, int page)
+{
+ dbg("marking page %d of pba %d as bad", page, pba);
+ msb_reset(msb, true);
+ return msb_set_overwrite_flag(msb,
+ pba, page, ~MEMSTICK_OVERWRITE_PGST0);
+}
+
+/* Erases one physical block */
+static int msb_erase_block(struct msb_data *msb, u16 pba)
+{
+ int error, try;
+ if (msb->read_only)
+ return -EROFS;
+
+ dbg_verbose("erasing pba %d", pba);
+
+ for (try = 1; try < 3; try++) {
+ msb->regs.param.block_address = cpu_to_be16(pba);
+ msb->regs.param.page_address = 0;
+ msb->regs.param.cp = MEMSTICK_CP_BLOCK;
+ msb->command_value = MS_CMD_BLOCK_ERASE;
+ msb->command_need_oob = false;
+
+
+ error = msb_run_state_machine(msb, h_msb_send_command);
+ if (!error || msb_reset(msb, true))
+ break;
+ }
+
+ if (error) {
+ pr_err("erase failed, marking pba %d as bad", pba);
+ msb_mark_bad(msb, pba);
+ }
+
+ dbg_verbose("erase success, marking pba %d as unused", pba);
+ msb_mark_block_unused(msb, pba);
+ __set_bit(pba, msb->erased_blocks_bitmap);
+ return error;
+}
+
+/* Reads one page from device */
+static int msb_read_page(struct msb_data *msb,
+ u16 pba, u8 page, struct ms_extra_data_register *extra,
+ struct scatterlist *sg, int offset)
+{
+ int try, error;
+
+ if (pba == MS_BLOCK_INVALID) {
+ unsigned long flags;
+ struct sg_mapping_iter miter;
+ size_t len = msb->page_size;
+
+ dbg_verbose("read unmapped sector. returning 0xFF");
+
+ local_irq_save(flags);
+ sg_miter_start(&miter, sg, sg_nents(sg),
+ SG_MITER_ATOMIC | SG_MITER_TO_SG);
+
+ while (sg_miter_next(&miter) && len > 0) {
+
+ int chunklen;
+
+ if (offset && offset >= miter.length) {
+ offset -= miter.length;
+ continue;
+ }
+
+ chunklen = min(miter.length - offset, len);
+ memset(miter.addr + offset, 0xFF, chunklen);
+ len -= chunklen;
+ offset = 0;
+ }
+
+ sg_miter_stop(&miter);
+ local_irq_restore(flags);
+
+ if (offset)
+ return -EFAULT;
+
+ if (extra)
+ memset(extra, 0xFF, sizeof(*extra));
+ return 0;
+ }
+
+ if (pba >= msb->block_count) {
+ pr_err("BUG: attempt to read beyond the end of the card at pba %d", pba);
+ return -EINVAL;
+ }
+
+ for (try = 1; try < 3; try++) {
+ msb->regs.param.block_address = cpu_to_be16(pba);
+ msb->regs.param.page_address = page;
+ msb->regs.param.cp = MEMSTICK_CP_PAGE;
+
+ msb->current_sg = sg;
+ msb->current_sg_offset = offset;
+ error = msb_run_state_machine(msb, h_msb_read_page);
+
+
+ if (error == -EUCLEAN) {
+ pr_notice("correctable error on pba %d, page %d",
+ pba, page);
+ error = 0;
+ }
+
+ if (!error && extra)
+ *extra = msb->regs.extra_data;
+
+ if (!error || msb_reset(msb, true))
+ break;
+
+ }
+
+ /* Mark bad pages */
+ if (error == -EBADMSG) {
+ pr_err("uncorrectable error on read of pba %d, page %d",
+ pba, page);
+
+ if (msb->regs.extra_data.overwrite_flag &
+ MEMSTICK_OVERWRITE_PGST0)
+ msb_mark_page_bad(msb, pba, page);
+ return -EBADMSG;
+ }
+
+ if (error)
+ pr_err("read of pba %d, page %d failed with error %d",
+ pba, page, error);
+ return error;
+}
+
+/* Reads oob of page only */
+static int msb_read_oob(struct msb_data *msb, u16 pba, u16 page,
+ struct ms_extra_data_register *extra)
+{
+ int error;
+
+ BUG_ON(!extra);
+ msb->regs.param.block_address = cpu_to_be16(pba);
+ msb->regs.param.page_address = page;
+ msb->regs.param.cp = MEMSTICK_CP_EXTRA;
+
+ if (pba > msb->block_count) {
+ pr_err("BUG: attempt to read beyond the end of card at pba %d", pba);
+ return -EINVAL;
+ }
+
+ error = msb_run_state_machine(msb, h_msb_read_page);
+ *extra = msb->regs.extra_data;
+
+ if (error == -EUCLEAN) {
+ pr_notice("correctable error on pba %d, page %d",
+ pba, page);
+ return 0;
+ }
+
+ return error;
+}
+
+/* Reads a block and compares it with data contained in scatterlist orig_sg */
+static int msb_verify_block(struct msb_data *msb, u16 pba,
+ struct scatterlist *orig_sg, int offset)
+{
+ struct scatterlist sg;
+ int page = 0, error;
+
+ sg_init_one(&sg, msb->block_buffer, msb->block_size);
+
+ while (page < msb->pages_in_block) {
+
+ error = msb_read_page(msb, pba, page,
+ NULL, &sg, page * msb->page_size);
+ if (error)
+ return error;
+ page++;
+ }
+
+ if (msb_sg_compare_to_buffer(orig_sg, offset,
+ msb->block_buffer, msb->block_size))
+ return -EIO;
+ return 0;
+}
+
+/* Writes exectly one block + oob */
+static int msb_write_block(struct msb_data *msb,
+ u16 pba, u32 lba, struct scatterlist *sg, int offset)
+{
+ int error, current_try = 1;
+ BUG_ON(sg->length < msb->page_size);
+
+ if (msb->read_only)
+ return -EROFS;
+
+ if (pba == MS_BLOCK_INVALID) {
+ pr_err(
+ "BUG: write: attempt to write MS_BLOCK_INVALID block");
+ return -EINVAL;
+ }
+
+ if (pba >= msb->block_count || lba >= msb->logical_block_count) {
+ pr_err(
+ "BUG: write: attempt to write beyond the end of device");
+ return -EINVAL;
+ }
+
+ if (msb_get_zone_from_lba(lba) != msb_get_zone_from_pba(pba)) {
+ pr_err("BUG: write: lba zone mismatch");
+ return -EINVAL;
+ }
+
+ if (pba == msb->boot_block_locations[0] ||
+ pba == msb->boot_block_locations[1]) {
+ pr_err("BUG: write: attempt to write to boot blocks!");
+ return -EINVAL;
+ }
+
+ while (1) {
+
+ if (msb->read_only)
+ return -EROFS;
+
+ msb->regs.param.cp = MEMSTICK_CP_BLOCK;
+ msb->regs.param.page_address = 0;
+ msb->regs.param.block_address = cpu_to_be16(pba);
+
+ msb->regs.extra_data.management_flag = 0xFF;
+ msb->regs.extra_data.overwrite_flag = 0xF8;
+ msb->regs.extra_data.logical_address = cpu_to_be16(lba);
+
+ msb->current_sg = sg;
+ msb->current_sg_offset = offset;
+ msb->current_page = 0;
+
+ error = msb_run_state_machine(msb, h_msb_write_block);
+
+ /* Sector we just wrote to is assumed erased since its pba
+ was erased. If it wasn't erased, write will succeed
+ and will just clear the bits that were set in the block
+ thus test that what we have written,
+ matches what we expect.
+ We do trust the blocks that we erased */
+ if (!error && (verify_writes ||
+ !test_bit(pba, msb->erased_blocks_bitmap)))
+ error = msb_verify_block(msb, pba, sg, offset);
+
+ if (!error)
+ break;
+
+ if (current_try > 1 || msb_reset(msb, true))
+ break;
+
+ pr_err("write failed, trying to erase the pba %d", pba);
+ error = msb_erase_block(msb, pba);
+ if (error)
+ break;
+
+ current_try++;
+ }
+ return error;
+}
+
+/* Finds a free block for write replacement */
+static u16 msb_get_free_block(struct msb_data *msb, int zone)
+{
+ u16 pos;
+ int pba = zone * MS_BLOCKS_IN_ZONE;
+ int i;
+
+ get_random_bytes(&pos, sizeof(pos));
+
+ if (!msb->free_block_count[zone]) {
+ pr_err("NO free blocks in the zone %d, to use for a write, (media is WORN out) switching to RO mode", zone);
+ msb->read_only = true;
+ return MS_BLOCK_INVALID;
+ }
+
+ pos %= msb->free_block_count[zone];
+
+ dbg_verbose("have %d choices for a free block, selected randomally: %d",
+ msb->free_block_count[zone], pos);
+
+ pba = find_next_zero_bit(msb->used_blocks_bitmap,
+ msb->block_count, pba);
+ for (i = 0; i < pos; ++i)
+ pba = find_next_zero_bit(msb->used_blocks_bitmap,
+ msb->block_count, pba + 1);
+
+ dbg_verbose("result of the free blocks scan: pba %d", pba);
+
+ if (pba == msb->block_count || (msb_get_zone_from_pba(pba)) != zone) {
+ pr_err("BUG: cant get a free block");
+ msb->read_only = true;
+ return MS_BLOCK_INVALID;
+ }
+
+ msb_mark_block_used(msb, pba);
+ return pba;
+}
+
+static int msb_update_block(struct msb_data *msb, u16 lba,
+ struct scatterlist *sg, int offset)
+{
+ u16 pba, new_pba;
+ int error, try;
+
+ pba = msb->lba_to_pba_table[lba];
+ dbg_verbose("start of a block update at lba %d, pba %d", lba, pba);
+
+ if (pba != MS_BLOCK_INVALID) {
+ dbg_verbose("setting the update flag on the block");
+ msb_set_overwrite_flag(msb, pba, 0,
+ 0xFF & ~MEMSTICK_OVERWRITE_UDST);
+ }
+
+ for (try = 0; try < 3; try++) {
+ new_pba = msb_get_free_block(msb,
+ msb_get_zone_from_lba(lba));
+
+ if (new_pba == MS_BLOCK_INVALID) {
+ error = -EIO;
+ goto out;
+ }
+
+ dbg_verbose("block update: writing updated block to the pba %d",
+ new_pba);
+ error = msb_write_block(msb, new_pba, lba, sg, offset);
+ if (error == -EBADMSG) {
+ msb_mark_bad(msb, new_pba);
+ continue;
+ }
+
+ if (error)
+ goto out;
+
+ dbg_verbose("block update: erasing the old block");
+ msb_erase_block(msb, pba);
+ msb->lba_to_pba_table[lba] = new_pba;
+ return 0;
+ }
+out:
+ if (error) {
+ pr_err("block update error after %d tries, switching to r/o mode", try);
+ msb->read_only = true;
+ }
+ return error;
+}
+
+/* Converts endiannes in the boot block for easy use */
+static void msb_fix_boot_page_endianness(struct ms_boot_page *p)
+{
+ p->header.block_id = be16_to_cpu(p->header.block_id);
+ p->header.format_reserved = be16_to_cpu(p->header.format_reserved);
+ p->entry.disabled_block.start_addr
+ = be32_to_cpu(p->entry.disabled_block.start_addr);
+ p->entry.disabled_block.data_size
+ = be32_to_cpu(p->entry.disabled_block.data_size);
+ p->entry.cis_idi.start_addr
+ = be32_to_cpu(p->entry.cis_idi.start_addr);
+ p->entry.cis_idi.data_size
+ = be32_to_cpu(p->entry.cis_idi.data_size);
+ p->attr.block_size = be16_to_cpu(p->attr.block_size);
+ p->attr.number_of_blocks = be16_to_cpu(p->attr.number_of_blocks);
+ p->attr.number_of_effective_blocks
+ = be16_to_cpu(p->attr.number_of_effective_blocks);
+ p->attr.page_size = be16_to_cpu(p->attr.page_size);
+ p->attr.memory_manufacturer_code
+ = be16_to_cpu(p->attr.memory_manufacturer_code);
+ p->attr.memory_device_code = be16_to_cpu(p->attr.memory_device_code);
+ p->attr.implemented_capacity
+ = be16_to_cpu(p->attr.implemented_capacity);
+ p->attr.controller_number = be16_to_cpu(p->attr.controller_number);
+ p->attr.controller_function = be16_to_cpu(p->attr.controller_function);
+}
+
+static int msb_read_boot_blocks(struct msb_data *msb)
+{
+ int pba = 0;
+ struct scatterlist sg;
+ struct ms_extra_data_register extra;
+ struct ms_boot_page *page;
+
+ msb->boot_block_locations[0] = MS_BLOCK_INVALID;
+ msb->boot_block_locations[1] = MS_BLOCK_INVALID;
+ msb->boot_block_count = 0;
+
+ dbg_verbose("Start of a scan for the boot blocks");
+
+ if (!msb->boot_page) {
+ page = kmalloc(sizeof(struct ms_boot_page)*2, GFP_KERNEL);
+ if (!page)
+ return -ENOMEM;
+
+ msb->boot_page = page;
+ } else
+ page = msb->boot_page;
+
+ msb->block_count = MS_BLOCK_MAX_BOOT_ADDR;
+
+ for (pba = 0; pba < MS_BLOCK_MAX_BOOT_ADDR; pba++) {
+
+ sg_init_one(&sg, page, sizeof(*page));
+ if (msb_read_page(msb, pba, 0, &extra, &sg, 0)) {
+ dbg("boot scan: can't read pba %d", pba);
+ continue;
+ }
+
+ if (extra.management_flag & MEMSTICK_MANAGEMENT_SYSFLG) {
+ dbg("managment flag doesn't indicate boot block %d",
+ pba);
+ continue;
+ }
+
+ if (be16_to_cpu(page->header.block_id) != MS_BLOCK_BOOT_ID) {
+ dbg("the pba at %d doesn' contain boot block ID", pba);
+ continue;
+ }
+
+ msb_fix_boot_page_endianness(page);
+ msb->boot_block_locations[msb->boot_block_count] = pba;
+
+ page++;
+ msb->boot_block_count++;
+
+ if (msb->boot_block_count == 2)
+ break;
+ }
+
+ if (!msb->boot_block_count) {
+ pr_err("media doesn't contain master page, aborting");
+ return -EIO;
+ }
+
+ dbg_verbose("End of scan for boot blocks");
+ return 0;
+}
+
+static int msb_read_bad_block_table(struct msb_data *msb, int block_nr)
+{
+ struct ms_boot_page *boot_block;
+ struct scatterlist sg;
+ u16 *buffer = NULL;
+ int offset = 0;
+ int i, error = 0;
+ int data_size, data_offset, page, page_offset, size_to_read;
+ u16 pba;
+
+ BUG_ON(block_nr > 1);
+ boot_block = &msb->boot_page[block_nr];
+ pba = msb->boot_block_locations[block_nr];
+
+ if (msb->boot_block_locations[block_nr] == MS_BLOCK_INVALID)
+ return -EINVAL;
+
+ data_size = boot_block->entry.disabled_block.data_size;
+ data_offset = sizeof(struct ms_boot_page) +
+ boot_block->entry.disabled_block.start_addr;
+ if (!data_size)
+ return 0;
+
+ page = data_offset / msb->page_size;
+ page_offset = data_offset % msb->page_size;
+ size_to_read =
+ DIV_ROUND_UP(data_size + page_offset, msb->page_size) *
+ msb->page_size;
+
+ dbg("reading bad block of boot block at pba %d, offset %d len %d",
+ pba, data_offset, data_size);
+
+ buffer = kzalloc(size_to_read, GFP_KERNEL);
+ if (!buffer)
+ return -ENOMEM;
+
+ /* Read the buffer */
+ sg_init_one(&sg, buffer, size_to_read);
+
+ while (offset < size_to_read) {
+ error = msb_read_page(msb, pba, page, NULL, &sg, offset);
+ if (error)
+ goto out;
+
+ page++;
+ offset += msb->page_size;
+
+ if (page == msb->pages_in_block) {
+ pr_err(
+ "bad block table extends beyond the boot block");
+ break;
+ }
+ }
+
+ /* Process the bad block table */
+ for (i = page_offset; i < data_size / sizeof(u16); i++) {
+
+ u16 bad_block = be16_to_cpu(buffer[i]);
+
+ if (bad_block >= msb->block_count) {
+ dbg("bad block table contains invalid block %d",
+ bad_block);
+ continue;
+ }
+
+ if (test_bit(bad_block, msb->used_blocks_bitmap)) {
+ dbg("duplicate bad block %d in the table",
+ bad_block);
+ continue;
+ }
+
+ dbg("block %d is marked as factory bad", bad_block);
+ msb_mark_block_used(msb, bad_block);
+ }
+out:
+ kfree(buffer);
+ return error;
+}
+
+static int msb_ftl_initialize(struct msb_data *msb)
+{
+ int i;
+
+ if (msb->ftl_initialized)
+ return 0;
+
+ msb->zone_count = msb->block_count / MS_BLOCKS_IN_ZONE;
+ msb->logical_block_count = msb->zone_count * 496 - 2;
+
+ msb->used_blocks_bitmap = kzalloc(msb->block_count / 8, GFP_KERNEL);
+ msb->erased_blocks_bitmap = kzalloc(msb->block_count / 8, GFP_KERNEL);
+ msb->lba_to_pba_table =
+ kmalloc(msb->logical_block_count * sizeof(u16), GFP_KERNEL);
+
+ if (!msb->used_blocks_bitmap || !msb->lba_to_pba_table ||
+ !msb->erased_blocks_bitmap) {
+ kfree(msb->used_blocks_bitmap);
+ kfree(msb->lba_to_pba_table);
+ kfree(msb->erased_blocks_bitmap);
+ return -ENOMEM;
+ }
+
+ for (i = 0; i < msb->zone_count; i++)
+ msb->free_block_count[i] = MS_BLOCKS_IN_ZONE;
+
+ memset(msb->lba_to_pba_table, MS_BLOCK_INVALID,
+ msb->logical_block_count * sizeof(u16));
+
+ dbg("initial FTL tables created. Zone count = %d, Logical block count = %d",
+ msb->zone_count, msb->logical_block_count);
+
+ msb->ftl_initialized = true;
+ return 0;
+}
+
+static int msb_ftl_scan(struct msb_data *msb)
+{
+ u16 pba, lba, other_block;
+ u8 overwrite_flag, managment_flag, other_overwrite_flag;
+ int error;
+ struct ms_extra_data_register extra;
+ u8 *overwrite_flags = kzalloc(msb->block_count, GFP_KERNEL);
+
+ if (!overwrite_flags)
+ return -ENOMEM;
+
+ dbg("Start of media scanning");
+ for (pba = 0; pba < msb->block_count; pba++) {
+
+ if (pba == msb->boot_block_locations[0] ||
+ pba == msb->boot_block_locations[1]) {
+ dbg_verbose("pba %05d -> [boot block]", pba);
+ msb_mark_block_used(msb, pba);
+ continue;
+ }
+
+ if (test_bit(pba, msb->used_blocks_bitmap)) {
+ dbg_verbose("pba %05d -> [factory bad]", pba);
+ continue;
+ }
+
+ memset(&extra, 0, sizeof(extra));
+ error = msb_read_oob(msb, pba, 0, &extra);
+
+ /* can't trust the page if we can't read the oob */
+ if (error == -EBADMSG) {
+ pr_notice(
+ "oob of pba %d damaged, will try to erase it", pba);
+ msb_mark_block_used(msb, pba);
+ msb_erase_block(msb, pba);
+ continue;
+ } else if (error) {
+ pr_err("unknown error %d on read of oob of pba %d - aborting",
+ error, pba);
+
+ kfree(overwrite_flags);
+ return error;
+ }
+
+ lba = be16_to_cpu(extra.logical_address);
+ managment_flag = extra.management_flag;
+ overwrite_flag = extra.overwrite_flag;
+ overwrite_flags[pba] = overwrite_flag;
+
+ /* Skip bad blocks */
+ if (!(overwrite_flag & MEMSTICK_OVERWRITE_BKST)) {
+ dbg("pba %05d -> [BAD]", pba);
+ msb_mark_block_used(msb, pba);
+ continue;
+ }
+
+ /* Skip system/drm blocks */
+ if ((managment_flag & MEMSTICK_MANAGMENT_FLAG_NORMAL) !=
+ MEMSTICK_MANAGMENT_FLAG_NORMAL) {
+ dbg("pba %05d -> [reserved managment flag %02x]",
+ pba, managment_flag);
+ msb_mark_block_used(msb, pba);
+ continue;
+ }
+
+ /* Erase temporary tables */
+ if (!(managment_flag & MEMSTICK_MANAGEMENT_ATFLG)) {
+ dbg("pba %05d -> [temp table] - will erase", pba);
+
+ msb_mark_block_used(msb, pba);
+ msb_erase_block(msb, pba);
+ continue;
+ }
+
+ if (lba == MS_BLOCK_INVALID) {
+ dbg_verbose("pba %05d -> [free]", pba);
+ continue;
+ }
+
+ msb_mark_block_used(msb, pba);
+
+ /* Block has LBA not according to zoning*/
+ if (msb_get_zone_from_lba(lba) != msb_get_zone_from_pba(pba)) {
+ pr_notice("pba %05d -> [bad lba %05d] - will erase",
+ pba, lba);
+ msb_erase_block(msb, pba);
+ continue;
+ }
+
+ /* No collisions - great */
+ if (msb->lba_to_pba_table[lba] == MS_BLOCK_INVALID) {
+ dbg_verbose("pba %05d -> [lba %05d]", pba, lba);
+ msb->lba_to_pba_table[lba] = pba;
+ continue;
+ }
+
+ other_block = msb->lba_to_pba_table[lba];
+ other_overwrite_flag = overwrite_flags[other_block];
+
+ pr_notice("Collision between pba %d and pba %d",
+ pba, other_block);
+
+ if (!(overwrite_flag & MEMSTICK_OVERWRITE_UDST)) {
+ pr_notice("pba %d is marked as stable, use it", pba);
+ msb_erase_block(msb, other_block);
+ msb->lba_to_pba_table[lba] = pba;
+ continue;
+ }
+
+ if (!(other_overwrite_flag & MEMSTICK_OVERWRITE_UDST)) {
+ pr_notice("pba %d is marked as stable, use it",
+ other_block);
+ msb_erase_block(msb, pba);
+ continue;
+ }
+
+ pr_notice("collision between blocks %d and %d, without stable flag set on both, erasing pba %d",
+ pba, other_block, other_block);
+
+ msb_erase_block(msb, other_block);
+ msb->lba_to_pba_table[lba] = pba;
+ }
+
+ dbg("End of media scanning");
+ kfree(overwrite_flags);
+ return 0;
+}
+
+static void msb_cache_flush_timer(unsigned long data)
+{
+ struct msb_data *msb = (struct msb_data *)data;
+ msb->need_flush_cache = true;
+ queue_work(msb->io_queue, &msb->io_work);
+}
+
+
+static void msb_cache_discard(struct msb_data *msb)
+{
+ if (msb->cache_block_lba == MS_BLOCK_INVALID)
+ return;
+
+ del_timer_sync(&msb->cache_flush_timer);
+
+ dbg_verbose("Discarding the write cache");
+ msb->cache_block_lba = MS_BLOCK_INVALID;
+ bitmap_zero(&msb->valid_cache_bitmap, msb->pages_in_block);
+}
+
+static int msb_cache_init(struct msb_data *msb)
+{
+ setup_timer(&msb->cache_flush_timer, msb_cache_flush_timer,
+ (unsigned long)msb);
+
+ if (!msb->cache)
+ msb->cache = kzalloc(msb->block_size, GFP_KERNEL);
+ if (!msb->cache)
+ return -ENOMEM;
+
+ msb_cache_discard(msb);
+ return 0;
+}
+
+static int msb_cache_flush(struct msb_data *msb)
+{
+ struct scatterlist sg;
+ struct ms_extra_data_register extra;
+ int page, offset, error;
+ u16 pba, lba;
+
+ if (msb->read_only)
+ return -EROFS;
+
+ if (msb->cache_block_lba == MS_BLOCK_INVALID)
+ return 0;
+
+ lba = msb->cache_block_lba;
+ pba = msb->lba_to_pba_table[lba];
+
+ dbg_verbose("Flushing the write cache of pba %d (LBA %d)",
+ pba, msb->cache_block_lba);
+
+ sg_init_one(&sg, msb->cache , msb->block_size);
+
+ /* Read all missing pages in cache */
+ for (page = 0; page < msb->pages_in_block; page++) {
+
+ if (test_bit(page, &msb->valid_cache_bitmap))
+ continue;
+
+ offset = page * msb->page_size;
+
+ dbg_verbose("reading non-present sector %d of cache block %d",
+ page, lba);
+ error = msb_read_page(msb, pba, page, &extra, &sg, offset);
+
+ /* Bad pages are copied with 00 page status */
+ if (error == -EBADMSG) {
+ pr_err("read error on sector %d, contents probably damaged", page);
+ continue;
+ }
+
+ if (error)
+ return error;
+
+ if ((extra.overwrite_flag & MEMSTICK_OV_PG_NORMAL) !=
+ MEMSTICK_OV_PG_NORMAL) {
+ dbg("page %d is marked as bad", page);
+ continue;
+ }
+
+ set_bit(page, &msb->valid_cache_bitmap);
+ }
+
+ /* Write the cache now */
+ error = msb_update_block(msb, msb->cache_block_lba, &sg, 0);
+ pba = msb->lba_to_pba_table[msb->cache_block_lba];
+
+ /* Mark invalid pages */
+ if (!error) {
+ for (page = 0; page < msb->pages_in_block; page++) {
+
+ if (test_bit(page, &msb->valid_cache_bitmap))
+ continue;
+
+ dbg("marking page %d as containing damaged data",
+ page);
+ msb_set_overwrite_flag(msb,
+ pba , page, 0xFF & ~MEMSTICK_OV_PG_NORMAL);
+ }
+ }
+
+ msb_cache_discard(msb);
+ return error;
+}
+
+static int msb_cache_write(struct msb_data *msb, int lba,
+ int page, bool add_to_cache_only, struct scatterlist *sg, int offset)
+{
+ int error;
+ struct scatterlist sg_tmp[10];
+
+ if (msb->read_only)
+ return -EROFS;
+
+ if (msb->cache_block_lba == MS_BLOCK_INVALID ||
+ lba != msb->cache_block_lba)
+ if (add_to_cache_only)
+ return 0;
+
+ /* If we need to write different block */
+ if (msb->cache_block_lba != MS_BLOCK_INVALID &&
+ lba != msb->cache_block_lba) {
+ dbg_verbose("first flush the cache");
+ error = msb_cache_flush(msb);
+ if (error)
+ return error;
+ }
+
+ if (msb->cache_block_lba == MS_BLOCK_INVALID) {
+ msb->cache_block_lba = lba;
+ mod_timer(&msb->cache_flush_timer,
+ jiffies + msecs_to_jiffies(cache_flush_timeout));
+ }
+
+ dbg_verbose("Write of LBA %d page %d to cache ", lba, page);
+
+ sg_init_table(sg_tmp, ARRAY_SIZE(sg_tmp));
+ msb_sg_copy(sg, sg_tmp, ARRAY_SIZE(sg_tmp), offset, msb->page_size);
+
+ sg_copy_to_buffer(sg_tmp, sg_nents(sg_tmp),
+ msb->cache + page * msb->page_size, msb->page_size);
+
+ set_bit(page, &msb->valid_cache_bitmap);
+ return 0;
+}
+
+static int msb_cache_read(struct msb_data *msb, int lba,
+ int page, struct scatterlist *sg, int offset)
+{
+ int pba = msb->lba_to_pba_table[lba];
+ struct scatterlist sg_tmp[10];
+ int error = 0;
+
+ if (lba == msb->cache_block_lba &&
+ test_bit(page, &msb->valid_cache_bitmap)) {
+
+ dbg_verbose("Read of LBA %d (pba %d) sector %d from cache",
+ lba, pba, page);
+
+ sg_init_table(sg_tmp, ARRAY_SIZE(sg_tmp));
+ msb_sg_copy(sg, sg_tmp, ARRAY_SIZE(sg_tmp),
+ offset, msb->page_size);
+ sg_copy_from_buffer(sg_tmp, sg_nents(sg_tmp),
+ msb->cache + msb->page_size * page,
+ msb->page_size);
+ } else {
+ dbg_verbose("Read of LBA %d (pba %d) sector %d from device",
+ lba, pba, page);
+
+ error = msb_read_page(msb, pba, page, NULL, sg, offset);
+ if (error)
+ return error;
+
+ msb_cache_write(msb, lba, page, true, sg, offset);
+ }
+ return error;
+}
+
+/* Emulated geometry table
+ * This table content isn't that importaint,
+ * One could put here different values, providing that they still
+ * cover whole disk.
+ * 64 MB entry is what windows reports for my 64M memstick */
+
+static const struct chs_entry chs_table[] = {
+/* size sectors cylynders heads */
+ { 4, 16, 247, 2 },
+ { 8, 16, 495, 2 },
+ { 16, 16, 495, 4 },
+ { 32, 16, 991, 4 },
+ { 64, 16, 991, 8 },
+ {128, 16, 991, 16 },
+ { 0 }
+};
+
+/* Load information about the card */
+static int msb_init_card(struct memstick_dev *card)
+{
+ struct msb_data *msb = memstick_get_drvdata(card);
+ struct memstick_host *host = card->host;
+ struct ms_boot_page *boot_block;
+ int error = 0, i, raw_size_in_megs;
+
+ msb->caps = 0;
+
+ if (card->id.class >= MEMSTICK_CLASS_ROM &&
+ card->id.class <= MEMSTICK_CLASS_ROM)
+ msb->read_only = true;
+
+ msb->state = -1;
+ error = msb_reset(msb, false);
+ if (error)
+ return error;
+
+ /* Due to a bug in Jmicron driver written by Alex Dubov,
+ its serial mode barely works,
+ so we switch to parallel mode right away */
+ if (host->caps & MEMSTICK_CAP_PAR4)
+ msb_switch_to_parallel(msb);
+
+ msb->page_size = sizeof(struct ms_boot_page);
+
+ /* Read the boot page */
+ error = msb_read_boot_blocks(msb);
+ if (error)
+ return -EIO;
+
+ boot_block = &msb->boot_page[0];
+
+ /* Save intersting attributes from boot page */
+ msb->block_count = boot_block->attr.number_of_blocks;
+ msb->page_size = boot_block->attr.page_size;
+
+ msb->pages_in_block = boot_block->attr.block_size * 2;
+ msb->block_size = msb->page_size * msb->pages_in_block;
+
+ if (msb->page_size > PAGE_SIZE) {
+ /* this isn't supported by linux at all, anyway*/
+ dbg("device page %d size isn't supported", msb->page_size);
+ return -EINVAL;
+ }
+
+ msb->block_buffer = kzalloc(msb->block_size, GFP_KERNEL);
+ if (!msb->block_buffer)
+ return -ENOMEM;
+
+ raw_size_in_megs = (msb->block_size * msb->block_count) >> 20;
+
+ for (i = 0; chs_table[i].size; i++) {
+
+ if (chs_table[i].size != raw_size_in_megs)
+ continue;
+
+ msb->geometry.cylinders = chs_table[i].cyl;
+ msb->geometry.heads = chs_table[i].head;
+ msb->geometry.sectors = chs_table[i].sec;
+ break;
+ }
+
+ if (boot_block->attr.transfer_supporting == 1)
+ msb->caps |= MEMSTICK_CAP_PAR4;
+
+ if (boot_block->attr.device_type & 0x03)
+ msb->read_only = true;
+
+ dbg("Total block count = %d", msb->block_count);
+ dbg("Each block consists of %d pages", msb->pages_in_block);
+ dbg("Page size = %d bytes", msb->page_size);
+ dbg("Parallel mode supported: %d", !!(msb->caps & MEMSTICK_CAP_PAR4));
+ dbg("Read only: %d", msb->read_only);
+
+#if 0
+ /* Now we can switch the interface */
+ if (host->caps & msb->caps & MEMSTICK_CAP_PAR4)
+ msb_switch_to_parallel(msb);
+#endif
+
+ error = msb_cache_init(msb);
+ if (error)
+ return error;
+
+ error = msb_ftl_initialize(msb);
+ if (error)
+ return error;
+
+
+ /* Read the bad block table */
+ error = msb_read_bad_block_table(msb, 0);
+
+ if (error && error != -ENOMEM) {
+ dbg("failed to read bad block table from primary boot block, trying from backup");
+ error = msb_read_bad_block_table(msb, 1);
+ }
+
+ if (error)
+ return error;
+
+ /* *drum roll* Scan the media */
+ error = msb_ftl_scan(msb);
+ if (error) {
+ pr_err("Scan of media failed");
+ return error;
+ }
+
+ return 0;
+
+}
+
+static int msb_do_write_request(struct msb_data *msb, int lba,
+ int page, struct scatterlist *sg, size_t len, int *sucessfuly_written)
+{
+ int error = 0;
+ off_t offset = 0;
+ *sucessfuly_written = 0;
+
+ while (offset < len) {
+ if (page == 0 && len - offset >= msb->block_size) {
+
+ if (msb->cache_block_lba == lba)
+ msb_cache_discard(msb);
+
+ dbg_verbose("Writing whole lba %d", lba);
+ error = msb_update_block(msb, lba, sg, offset);
+ if (error)
+ return error;
+
+ offset += msb->block_size;
+ *sucessfuly_written += msb->block_size;
+ lba++;
+ continue;
+ }
+
+ error = msb_cache_write(msb, lba, page, false, sg, offset);
+ if (error)
+ return error;
+
+ offset += msb->page_size;
+ *sucessfuly_written += msb->page_size;
+
+ page++;
+ if (page == msb->pages_in_block) {
+ page = 0;
+ lba++;
+ }
+ }
+ return 0;
+}
+
+static int msb_do_read_request(struct msb_data *msb, int lba,
+ int page, struct scatterlist *sg, int len, int *sucessfuly_read)
+{
+ int error = 0;
+ int offset = 0;
+ *sucessfuly_read = 0;
+
+ while (offset < len) {
+
+ error = msb_cache_read(msb, lba, page, sg, offset);
+ if (error)
+ return error;
+
+ offset += msb->page_size;
+ *sucessfuly_read += msb->page_size;
+
+ page++;
+ if (page == msb->pages_in_block) {
+ page = 0;
+ lba++;
+ }
+ }
+ return 0;
+}
+
+static void msb_io_work(struct work_struct *work)
+{
+ struct msb_data *msb = container_of(work, struct msb_data, io_work);
+ int page, error, len;
+ sector_t lba;
+ unsigned long flags;
+ struct scatterlist *sg = msb->prealloc_sg;
+
+ dbg_verbose("IO: work started");
+
+ while (1) {
+ spin_lock_irqsave(&msb->q_lock, flags);
+
+ if (msb->need_flush_cache) {
+ msb->need_flush_cache = false;
+ spin_unlock_irqrestore(&msb->q_lock, flags);
+ msb_cache_flush(msb);
+ continue;
+ }
+
+ if (!msb->req) {
+ msb->req = blk_fetch_request(msb->queue);
+ if (!msb->req) {
+ dbg_verbose("IO: no more requests exiting");
+ spin_unlock_irqrestore(&msb->q_lock, flags);
+ return;
+ }
+ }
+
+ spin_unlock_irqrestore(&msb->q_lock, flags);
+
+ /* If card was removed meanwhile */
+ if (!msb->req)
+ return;
+
+ /* process the request */
+ dbg_verbose("IO: processing new request");
+ blk_rq_map_sg(msb->queue, msb->req, sg);
+
+ lba = blk_rq_pos(msb->req);
+
+ sector_div(lba, msb->page_size / 512);
+ page = do_div(lba, msb->pages_in_block);
+
+ if (rq_data_dir(msb->req) == READ)
+ error = msb_do_read_request(msb, lba, page, sg,
+ blk_rq_bytes(msb->req), &len);
+ else
+ error = msb_do_write_request(msb, lba, page, sg,
+ blk_rq_bytes(msb->req), &len);
+
+ spin_lock_irqsave(&msb->q_lock, flags);
+
+ if (len)
+ if (!__blk_end_request(msb->req, 0, len))
+ msb->req = NULL;
+
+ if (error && msb->req) {
+ dbg_verbose("IO: ending one sector of the request with error");
+ if (!__blk_end_request(msb->req, error, msb->page_size))
+ msb->req = NULL;
+ }
+
+ if (msb->req)
+ dbg_verbose("IO: request still pending");
+
+ spin_unlock_irqrestore(&msb->q_lock, flags);
+ }
+}
+
+static DEFINE_IDR(msb_disk_idr); /*set of used disk numbers */
+static DEFINE_MUTEX(msb_disk_lock); /* protects against races in open/release */
+
+static int msb_bd_open(struct block_device *bdev, fmode_t mode)
+{
+ struct gendisk *disk = bdev->bd_disk;
+ struct msb_data *msb = disk->private_data;
+
+ dbg_verbose("block device open");
+
+ mutex_lock(&msb_disk_lock);
+
+ if (msb && msb->card)
+ msb->usage_count++;
+
+ mutex_unlock(&msb_disk_lock);
+ return 0;
+}
+
+static void msb_data_clear(struct msb_data *msb)
+{
+ kfree(msb->boot_page);
+ kfree(msb->used_blocks_bitmap);
+ kfree(msb->lba_to_pba_table);
+ kfree(msb->cache);
+ msb->card = NULL;
+}
+
+static int msb_disk_release(struct gendisk *disk)
+{
+ struct msb_data *msb = disk->private_data;
+
+ dbg_verbose("block device release");
+ mutex_lock(&msb_disk_lock);
+
+ if (msb) {
+ if (msb->usage_count)
+ msb->usage_count--;
+
+ if (!msb->usage_count) {
+ disk->private_data = NULL;
+ idr_remove(&msb_disk_idr, msb->disk_id);
+ put_disk(disk);
+ kfree(msb);
+ }
+ }
+ mutex_unlock(&msb_disk_lock);
+ return 0;
+}
+
+static void msb_bd_release(struct gendisk *disk, fmode_t mode)
+{
+ msb_disk_release(disk);
+}
+
+static int msb_bd_getgeo(struct block_device *bdev,
+ struct hd_geometry *geo)
+{
+ struct msb_data *msb = bdev->bd_disk->private_data;
+ *geo = msb->geometry;
+ return 0;
+}
+
+static int msb_prepare_req(struct request_queue *q, struct request *req)
+{
+ if (req->cmd_type != REQ_TYPE_FS &&
+ req->cmd_type != REQ_TYPE_BLOCK_PC) {
+ blk_dump_rq_flags(req, "MS unsupported request");
+ return BLKPREP_KILL;
+ }
+ req->cmd_flags |= REQ_DONTPREP;
+ return BLKPREP_OK;
+}
+
+static void msb_submit_req(struct request_queue *q)
+{
+ struct memstick_dev *card = q->queuedata;
+ struct msb_data *msb = memstick_get_drvdata(card);
+ struct request *req = NULL;
+
+ dbg_verbose("Submit request");
+
+ if (msb->card_dead) {
+ dbg("Refusing requests on removed card");
+
+ WARN_ON(!msb->io_queue_stopped);
+
+ while ((req = blk_fetch_request(q)) != NULL)
+ __blk_end_request_all(req, -ENODEV);
+ return;
+ }
+
+ if (msb->req)
+ return;
+
+ if (!msb->io_queue_stopped)
+ queue_work(msb->io_queue, &msb->io_work);
+}
+
+static int msb_check_card(struct memstick_dev *card)
+{
+ struct msb_data *msb = memstick_get_drvdata(card);
+ return (msb->card_dead == 0);
+}
+
+static void msb_stop(struct memstick_dev *card)
+{
+ struct msb_data *msb = memstick_get_drvdata(card);
+ unsigned long flags;
+
+ dbg("Stopping all msblock IO");
+
+ spin_lock_irqsave(&msb->q_lock, flags);
+ blk_stop_queue(msb->queue);
+ msb->io_queue_stopped = true;
+ spin_unlock_irqrestore(&msb->q_lock, flags);
+
+ del_timer_sync(&msb->cache_flush_timer);
+ flush_workqueue(msb->io_queue);
+
+ if (msb->req) {
+ spin_lock_irqsave(&msb->q_lock, flags);
+ blk_requeue_request(msb->queue, msb->req);
+ msb->req = NULL;
+ spin_unlock_irqrestore(&msb->q_lock, flags);
+ }
+
+}
+
+static void msb_start(struct memstick_dev *card)
+{
+ struct msb_data *msb = memstick_get_drvdata(card);
+ unsigned long flags;
+
+ dbg("Resuming IO from msblock");
+
+ msb_invalidate_reg_window(msb);
+
+ spin_lock_irqsave(&msb->q_lock, flags);
+ if (!msb->io_queue_stopped || msb->card_dead) {
+ spin_unlock_irqrestore(&msb->q_lock, flags);
+ return;
+ }
+ spin_unlock_irqrestore(&msb->q_lock, flags);
+
+ /* Kick cache flush anyway, its harmless */
+ msb->need_flush_cache = true;
+ msb->io_queue_stopped = false;
+
+ spin_lock_irqsave(&msb->q_lock, flags);
+ blk_start_queue(msb->queue);
+ spin_unlock_irqrestore(&msb->q_lock, flags);
+
+ queue_work(msb->io_queue, &msb->io_work);
+
+}
+
+static const struct block_device_operations msb_bdops = {
+ .open = msb_bd_open,
+ .release = msb_bd_release,
+ .getgeo = msb_bd_getgeo,
+ .owner = THIS_MODULE
+};
+
+/* Registers the block device */
+static int msb_init_disk(struct memstick_dev *card)
+{
+ struct msb_data *msb = memstick_get_drvdata(card);
+ struct memstick_host *host = card->host;
+ int rc;
+ u64 limit = BLK_BOUNCE_HIGH;
+ unsigned long capacity;
+
+ if (host->dev.dma_mask && *(host->dev.dma_mask))
+ limit = *(host->dev.dma_mask);
+
+ mutex_lock(&msb_disk_lock);
+ msb->disk_id = idr_alloc(&msb_disk_idr, card, 0, 256, GFP_KERNEL);
+ mutex_unlock(&msb_disk_lock);
+
+ if (msb->disk_id < 0)
+ return msb->disk_id;
+
+ msb->disk = alloc_disk(0);
+ if (!msb->disk) {
+ rc = -ENOMEM;
+ goto out_release_id;
+ }
+
+ msb->queue = blk_init_queue(msb_submit_req, &msb->q_lock);
+ if (!msb->queue) {
+ rc = -ENOMEM;
+ goto out_put_disk;
+ }
+
+ msb->queue->queuedata = card;
+ blk_queue_prep_rq(msb->queue, msb_prepare_req);
+
+ blk_queue_bounce_limit(msb->queue, limit);
+ blk_queue_max_hw_sectors(msb->queue, MS_BLOCK_MAX_PAGES);
+ blk_queue_max_segments(msb->queue, MS_BLOCK_MAX_SEGS);
+ blk_queue_max_segment_size(msb->queue,
+ MS_BLOCK_MAX_PAGES * msb->page_size);
+ blk_queue_logical_block_size(msb->queue, msb->page_size);
+
+ sprintf(msb->disk->disk_name, "msblk%d", msb->disk_id);
+ msb->disk->fops = &msb_bdops;
+ msb->disk->private_data = msb;
+ msb->disk->queue = msb->queue;
+ msb->disk->driverfs_dev = &card->dev;
+ msb->disk->flags |= GENHD_FL_EXT_DEVT;
+
+ capacity = msb->pages_in_block * msb->logical_block_count;
+ capacity *= (msb->page_size / 512);
+ set_capacity(msb->disk, capacity);
+ dbg("Set total disk size to %lu sectors", capacity);
+
+ msb->usage_count = 1;
+ msb->io_queue = alloc_ordered_workqueue("ms_block", WQ_MEM_RECLAIM);
+ INIT_WORK(&msb->io_work, msb_io_work);
+ sg_init_table(msb->prealloc_sg, MS_BLOCK_MAX_SEGS+1);
+
+ if (msb->read_only)
+ set_disk_ro(msb->disk, 1);
+
+ msb_start(card);
+ add_disk(msb->disk);
+ dbg("Disk added");
+ return 0;
+
+out_put_disk:
+ put_disk(msb->disk);
+out_release_id:
+ mutex_lock(&msb_disk_lock);
+ idr_remove(&msb_disk_idr, msb->disk_id);
+ mutex_unlock(&msb_disk_lock);
+ return rc;
+}
+
+static int msb_probe(struct memstick_dev *card)
+{
+ struct msb_data *msb;
+ int rc = 0;
+
+ msb = kzalloc(sizeof(struct msb_data), GFP_KERNEL);
+ if (!msb)
+ return -ENOMEM;
+ memstick_set_drvdata(card, msb);
+ msb->card = card;
+ spin_lock_init(&msb->q_lock);
+
+ rc = msb_init_card(card);
+ if (rc)
+ goto out_free;
+
+ rc = msb_init_disk(card);
+ if (!rc) {
+ card->check = msb_check_card;
+ card->stop = msb_stop;
+ card->start = msb_start;
+ return 0;
+ }
+out_free:
+ memstick_set_drvdata(card, NULL);
+ msb_data_clear(msb);
+ kfree(msb);
+ return rc;
+}
+
+static void msb_remove(struct memstick_dev *card)
+{
+ struct msb_data *msb = memstick_get_drvdata(card);
+ unsigned long flags;
+
+ if (!msb->io_queue_stopped)
+ msb_stop(card);
+
+ dbg("Removing the disk device");
+
+ /* Take care of unhandled + new requests from now on */
+ spin_lock_irqsave(&msb->q_lock, flags);
+ msb->card_dead = true;
+ blk_start_queue(msb->queue);
+ spin_unlock_irqrestore(&msb->q_lock, flags);
+
+ /* Remove the disk */
+ del_gendisk(msb->disk);
+ blk_cleanup_queue(msb->queue);
+ msb->queue = NULL;
+
+ mutex_lock(&msb_disk_lock);
+ msb_data_clear(msb);
+ mutex_unlock(&msb_disk_lock);
+
+ msb_disk_release(msb->disk);
+ memstick_set_drvdata(card, NULL);
+}
+
+#ifdef CONFIG_PM
+
+static int msb_suspend(struct memstick_dev *card, pm_message_t state)
+{
+ msb_stop(card);
+ return 0;
+}
+
+static int msb_resume(struct memstick_dev *card)
+{
+ struct msb_data *msb = memstick_get_drvdata(card);
+ struct msb_data *new_msb = NULL;
+ bool card_dead = true;
+
+#ifndef CONFIG_MEMSTICK_UNSAFE_RESUME
+ msb->card_dead = true;
+ return 0;
+#endif
+ mutex_lock(&card->host->lock);
+
+ new_msb = kzalloc(sizeof(struct msb_data), GFP_KERNEL);
+ if (!new_msb)
+ goto out;
+
+ new_msb->card = card;
+ memstick_set_drvdata(card, new_msb);
+ spin_lock_init(&new_msb->q_lock);
+ sg_init_table(msb->prealloc_sg, MS_BLOCK_MAX_SEGS+1);
+
+ if (msb_init_card(card))
+ goto out;
+
+ if (msb->block_size != new_msb->block_size)
+ goto out;
+
+ if (memcmp(msb->boot_page, new_msb->boot_page,
+ sizeof(struct ms_boot_page)))
+ goto out;
+
+ if (msb->logical_block_count != new_msb->logical_block_count ||
+ memcmp(msb->lba_to_pba_table, new_msb->lba_to_pba_table,
+ msb->logical_block_count))
+ goto out;
+
+ if (msb->block_count != new_msb->block_count ||
+ memcmp(msb->used_blocks_bitmap, new_msb->used_blocks_bitmap,
+ msb->block_count / 8))
+ goto out;
+
+ card_dead = false;
+out:
+ if (card_dead)
+ dbg("Card was removed/replaced during suspend");
+
+ msb->card_dead = card_dead;
+ memstick_set_drvdata(card, msb);
+
+ if (new_msb) {
+ msb_data_clear(new_msb);
+ kfree(new_msb);
+ }
+
+ msb_start(card);
+ mutex_unlock(&card->host->lock);
+ return 0;
+}
+#else
+
+#define msb_suspend NULL
+#define msb_resume NULL
+
+#endif /* CONFIG_PM */
+
+static struct memstick_device_id msb_id_tbl[] = {
+ {MEMSTICK_MATCH_ALL, MEMSTICK_TYPE_LEGACY, MEMSTICK_CATEGORY_STORAGE,
+ MEMSTICK_CLASS_FLASH},
+
+ {MEMSTICK_MATCH_ALL, MEMSTICK_TYPE_LEGACY, MEMSTICK_CATEGORY_STORAGE,
+ MEMSTICK_CLASS_ROM},
+
+ {MEMSTICK_MATCH_ALL, MEMSTICK_TYPE_LEGACY, MEMSTICK_CATEGORY_STORAGE,
+ MEMSTICK_CLASS_RO},
+
+ {MEMSTICK_MATCH_ALL, MEMSTICK_TYPE_LEGACY, MEMSTICK_CATEGORY_STORAGE,
+ MEMSTICK_CLASS_WP},
+
+ {MEMSTICK_MATCH_ALL, MEMSTICK_TYPE_DUO, MEMSTICK_CATEGORY_STORAGE_DUO,
+ MEMSTICK_CLASS_DUO},
+ {}
+};
+MODULE_DEVICE_TABLE(memstick, msb_id_tbl);
+
+
+static struct memstick_driver msb_driver = {
+ .driver = {
+ .name = DRIVER_NAME,
+ .owner = THIS_MODULE
+ },
+ .id_table = msb_id_tbl,
+ .probe = msb_probe,
+ .remove = msb_remove,
+ .suspend = msb_suspend,
+ .resume = msb_resume
+};
+
+static int major;
+
+static int __init msb_init(void)
+{
+ int rc = register_blkdev(0, DRIVER_NAME);
+
+ if (rc < 0) {
+ pr_err("failed to register major (error %d)\n", rc);
+ return rc;
+ }
+
+ major = rc;
+ rc = memstick_register_driver(&msb_driver);
+ if (rc) {
+ unregister_blkdev(major, DRIVER_NAME);
+ pr_err("failed to register memstick driver (error %d)\n", rc);
+ }
+
+ return rc;
+}
+
+static void __exit msb_exit(void)
+{
+ memstick_unregister_driver(&msb_driver);
+ unregister_blkdev(major, DRIVER_NAME);
+ idr_destroy(&msb_disk_idr);
+}
+
+module_init(msb_init);
+module_exit(msb_exit);
+
+module_param(cache_flush_timeout, int, S_IRUGO);
+MODULE_PARM_DESC(cache_flush_timeout,
+ "Cache flush timeout in msec (1000 default)");
+module_param(debug, int, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(debug, "Debug level (0-2)");
+
+module_param(verify_writes, bool, S_IRUGO);
+MODULE_PARM_DESC(verify_writes, "Read back and check all data that is written");
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Maxim Levitsky");
+MODULE_DESCRIPTION("Sony MemoryStick block device driver");
diff --git a/drivers/memstick/core/ms_block.h b/drivers/memstick/core/ms_block.h
new file mode 100644
index 0000000..96e6375
--- /dev/null
+++ b/drivers/memstick/core/ms_block.h
@@ -0,0 +1,290 @@
+/*
+ * ms_block.h - Sony MemoryStick (legacy) storage support
+
+ * Copyright (C) 2013 Maxim Levitsky <maximlevitsky@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Minor portions of the driver are copied from mspro_block.c which is
+ * Copyright (C) 2007 Alex Dubov <oakad@yahoo.com>
+ *
+ * Also ms structures were copied from old broken driver by same author
+ * These probably come from MS spec
+ *
+ */
+
+#ifndef MS_BLOCK_NEW_H
+#define MS_BLOCK_NEW_H
+
+#define MS_BLOCK_MAX_SEGS 32
+#define MS_BLOCK_MAX_PAGES ((2 << 16) - 1)
+
+#define MS_BLOCK_MAX_BOOT_ADDR 0x000c
+#define MS_BLOCK_BOOT_ID 0x0001
+#define MS_BLOCK_INVALID 0xffff
+#define MS_MAX_ZONES 16
+#define MS_BLOCKS_IN_ZONE 512
+
+#define MS_BLOCK_MAP_LINE_SZ 16
+#define MS_BLOCK_PART_SHIFT 3
+
+
+#define MEMSTICK_UNCORR_ERROR (MEMSTICK_STATUS1_UCFG | \
+ MEMSTICK_STATUS1_UCEX | MEMSTICK_STATUS1_UCDT)
+
+#define MEMSTICK_CORR_ERROR (MEMSTICK_STATUS1_FGER | MEMSTICK_STATUS1_EXER | \
+ MEMSTICK_STATUS1_DTER)
+
+#define MEMSTICK_INT_ERROR (MEMSTICK_INT_CMDNAK | MEMSTICK_INT_ERR)
+
+#define MEMSTICK_OVERWRITE_FLAG_NORMAL \
+ (MEMSTICK_OVERWRITE_PGST1 | \
+ MEMSTICK_OVERWRITE_PGST0 | \
+ MEMSTICK_OVERWRITE_BKST)
+
+#define MEMSTICK_OV_PG_NORMAL \
+ (MEMSTICK_OVERWRITE_PGST1 | MEMSTICK_OVERWRITE_PGST0)
+
+#define MEMSTICK_MANAGMENT_FLAG_NORMAL \
+ (MEMSTICK_MANAGEMENT_SYSFLG | \
+ MEMSTICK_MANAGEMENT_SCMS1 | \
+ MEMSTICK_MANAGEMENT_SCMS0) \
+
+struct ms_boot_header {
+ unsigned short block_id;
+ unsigned short format_reserved;
+ unsigned char reserved0[184];
+ unsigned char data_entry;
+ unsigned char reserved1[179];
+} __packed;
+
+
+struct ms_system_item {
+ unsigned int start_addr;
+ unsigned int data_size;
+ unsigned char data_type_id;
+ unsigned char reserved[3];
+} __packed;
+
+struct ms_system_entry {
+ struct ms_system_item disabled_block;
+ struct ms_system_item cis_idi;
+ unsigned char reserved[24];
+} __packed;
+
+struct ms_boot_attr_info {
+ unsigned char memorystick_class;
+ unsigned char format_unique_value1;
+ unsigned short block_size;
+ unsigned short number_of_blocks;
+ unsigned short number_of_effective_blocks;
+ unsigned short page_size;
+ unsigned char extra_data_size;
+ unsigned char format_unique_value2;
+ unsigned char assembly_time[8];
+ unsigned char format_unique_value3;
+ unsigned char serial_number[3];
+ unsigned char assembly_manufacturer_code;
+ unsigned char assembly_model_code[3];
+ unsigned short memory_manufacturer_code;
+ unsigned short memory_device_code;
+ unsigned short implemented_capacity;
+ unsigned char format_unique_value4[2];
+ unsigned char vcc;
+ unsigned char vpp;
+ unsigned short controller_number;
+ unsigned short controller_function;
+ unsigned char reserved0[9];
+ unsigned char transfer_supporting;
+ unsigned short format_unique_value5;
+ unsigned char format_type;
+ unsigned char memorystick_application;
+ unsigned char device_type;
+ unsigned char reserved1[22];
+ unsigned char format_uniqure_value6[2];
+ unsigned char reserved2[15];
+} __packed;
+
+struct ms_cis_idi {
+ unsigned short general_config;
+ unsigned short logical_cylinders;
+ unsigned short reserved0;
+ unsigned short logical_heads;
+ unsigned short track_size;
+ unsigned short page_size;
+ unsigned short pages_per_track;
+ unsigned short msw;
+ unsigned short lsw;
+ unsigned short reserved1;
+ unsigned char serial_number[20];
+ unsigned short buffer_type;
+ unsigned short buffer_size_increments;
+ unsigned short long_command_ecc;
+ unsigned char firmware_version[28];
+ unsigned char model_name[18];
+ unsigned short reserved2[5];
+ unsigned short pio_mode_number;
+ unsigned short dma_mode_number;
+ unsigned short field_validity;
+ unsigned short current_logical_cylinders;
+ unsigned short current_logical_heads;
+ unsigned short current_pages_per_track;
+ unsigned int current_page_capacity;
+ unsigned short mutiple_page_setting;
+ unsigned int addressable_pages;
+ unsigned short single_word_dma;
+ unsigned short multi_word_dma;
+ unsigned char reserved3[128];
+} __packed;
+
+
+struct ms_boot_page {
+ struct ms_boot_header header;
+ struct ms_system_entry entry;
+ struct ms_boot_attr_info attr;
+} __packed;
+
+struct msb_data {
+ unsigned int usage_count;
+ struct memstick_dev *card;
+ struct gendisk *disk;
+ struct request_queue *queue;
+ spinlock_t q_lock;
+ struct hd_geometry geometry;
+ struct attribute_group attr_group;
+ struct request *req;
+ int caps;
+ int disk_id;
+
+ /* IO */
+ struct workqueue_struct *io_queue;
+ bool io_queue_stopped;
+ struct work_struct io_work;
+ bool card_dead;
+
+ /* Media properties */
+ struct ms_boot_page *boot_page;
+ u16 boot_block_locations[2];
+ int boot_block_count;
+
+ bool read_only;
+ unsigned short page_size;
+ int block_size;
+ int pages_in_block;
+ int zone_count;
+ int block_count;
+ int logical_block_count;
+
+ /* FTL tables */
+ unsigned long *used_blocks_bitmap;
+ unsigned long *erased_blocks_bitmap;
+ u16 *lba_to_pba_table;
+ int free_block_count[MS_MAX_ZONES];
+ bool ftl_initialized;
+
+ /* Cache */
+ unsigned char *cache;
+ unsigned long valid_cache_bitmap;
+ int cache_block_lba;
+ bool need_flush_cache;
+ struct timer_list cache_flush_timer;
+
+ /* Preallocated buffers */
+ unsigned char *block_buffer;
+ struct scatterlist prealloc_sg[MS_BLOCK_MAX_SEGS+1];
+
+
+ /* handler's local data */
+ struct ms_register_addr reg_addr;
+ bool addr_valid;
+
+ u8 command_value;
+ bool command_need_oob;
+ struct scatterlist *current_sg;
+ int current_sg_offset;
+
+ struct ms_register regs;
+ int current_page;
+
+ int state;
+ int exit_error;
+ bool int_polling;
+ unsigned long int_timeout;
+
+};
+
+enum msb_readpage_states {
+ MSB_RP_SEND_BLOCK_ADDRESS = 0,
+ MSB_RP_SEND_READ_COMMAND,
+
+ MSB_RP_SEND_INT_REQ,
+ MSB_RP_RECEIVE_INT_REQ_RESULT,
+
+ MSB_RP_SEND_READ_STATUS_REG,
+ MSB_RP_RECIVE_STATUS_REG,
+
+ MSB_RP_SEND_OOB_READ,
+ MSB_RP_RECEIVE_OOB_READ,
+
+ MSB_RP_SEND_READ_DATA,
+ MSB_RP_RECEIVE_READ_DATA,
+};
+
+enum msb_write_block_states {
+ MSB_WB_SEND_WRITE_PARAMS = 0,
+ MSB_WB_SEND_WRITE_OOB,
+ MSB_WB_SEND_WRITE_COMMAND,
+
+ MSB_WB_SEND_INT_REQ,
+ MSB_WB_RECEIVE_INT_REQ,
+
+ MSB_WB_SEND_WRITE_DATA,
+ MSB_WB_RECEIVE_WRITE_CONFIRMATION,
+};
+
+enum msb_send_command_states {
+ MSB_SC_SEND_WRITE_PARAMS,
+ MSB_SC_SEND_WRITE_OOB,
+ MSB_SC_SEND_COMMAND,
+
+ MSB_SC_SEND_INT_REQ,
+ MSB_SC_RECEIVE_INT_REQ,
+
+};
+
+enum msb_reset_states {
+ MSB_RS_SEND,
+ MSB_RS_CONFIRM,
+};
+
+enum msb_par_switch_states {
+ MSB_PS_SEND_SWITCH_COMMAND,
+ MSB_PS_SWICH_HOST,
+ MSB_PS_CONFIRM,
+};
+
+struct chs_entry {
+ unsigned long size;
+ unsigned char sec;
+ unsigned short cyl;
+ unsigned char head;
+};
+
+static int msb_reset(struct msb_data *msb, bool full);
+
+static int h_msb_default_bad(struct memstick_dev *card,
+ struct memstick_request **mrq);
+
+#define __dbg(level, format, ...) \
+ do { \
+ if (debug >= level) \
+ pr_err(format "\n", ## __VA_ARGS__); \
+ } while (0)
+
+
+#define dbg(format, ...) __dbg(1, format, ## __VA_ARGS__)
+#define dbg_verbose(format, ...) __dbg(2, format, ## __VA_ARGS__)
+
+#endif
diff --git a/drivers/memstick/host/rtsx_pci_ms.c b/drivers/memstick/host/rtsx_pci_ms.c
index cf8bd72..25f8f93 100644
--- a/drivers/memstick/host/rtsx_pci_ms.c
+++ b/drivers/memstick/host/rtsx_pci_ms.c
@@ -612,8 +612,6 @@
memstick_remove_host(msh);
memstick_free_host(msh);
- platform_set_drvdata(pdev, NULL);
-
dev_dbg(&(pdev->dev),
": Realtek PCI-E Memstick controller has been removed\n");
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index e0e46f5..914c3d1 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -23,7 +23,7 @@
select MFD_CORE
select REGMAP_I2C
select REGMAP_IRQ
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
help
Support for the AS3711 PMIC from AMS
@@ -40,7 +40,7 @@
config MFD_AAT2870_CORE
bool "AnalogicTech AAT2870"
select MFD_CORE
- depends on I2C=y && GPIOLIB && GENERIC_HARDIRQS
+ depends on I2C=y && GPIOLIB
help
If you say yes here you get support for the AAT2870.
This driver provides common support for accessing the device,
@@ -78,7 +78,7 @@
config MFD_ASIC3
bool "Compaq ASIC3"
- depends on GENERIC_HARDIRQS && GPIOLIB && ARM
+ depends on GPIOLIB && ARM
select MFD_CORE
---help---
This driver supports the ASIC3 multifunction chip found on many
@@ -104,7 +104,7 @@
select REGMAP_SPI
select REGMAP_IRQ
select PMIC_DA9052
- depends on SPI_MASTER=y && GENERIC_HARDIRQS
+ depends on SPI_MASTER=y
help
Support for the Dialog Semiconductor DA9052 PMIC
when controlled using SPI. This driver provides common support
@@ -116,7 +116,7 @@
select REGMAP_I2C
select REGMAP_IRQ
select PMIC_DA9052
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
help
Support for the Dialog Semiconductor DA9052 PMIC
when controlled using I2C. This driver provides common support
@@ -128,7 +128,7 @@
select REGMAP_I2C
select REGMAP_IRQ
select MFD_CORE
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
help
Say yes here for support of Dialog Semiconductor DA9055. This is
a Power Management IC. This driver provides common support for
@@ -144,7 +144,7 @@
select MFD_CORE
select REGMAP_I2C
select REGMAP_IRQ
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
help
Say yes here for support for the Dialog Semiconductor DA9063 PMIC.
This includes the I2C driver and core APIs.
@@ -156,7 +156,7 @@
config MFD_MC13XXX
tristate
- depends on (SPI_MASTER || I2C) && GENERIC_HARDIRQS
+ depends on (SPI_MASTER || I2C)
select MFD_CORE
select MFD_MC13783
help
@@ -167,7 +167,7 @@
config MFD_MC13XXX_SPI
tristate "Freescale MC13783 and MC13892 SPI interface"
- depends on SPI_MASTER && GENERIC_HARDIRQS
+ depends on SPI_MASTER
select REGMAP_SPI
select MFD_MC13XXX
help
@@ -175,7 +175,7 @@
config MFD_MC13XXX_I2C
tristate "Freescale MC13892 I2C interface"
- depends on I2C && GENERIC_HARDIRQS
+ depends on I2C
select REGMAP_I2C
select MFD_MC13XXX
help
@@ -183,7 +183,7 @@
config HTC_EGPIO
bool "HTC EGPIO support"
- depends on GENERIC_HARDIRQS && GPIOLIB && ARM
+ depends on GPIOLIB && ARM
help
This driver supports the CPLD egpio chip present on
several HTC phones. It provides basic support for input
@@ -192,7 +192,6 @@
config HTC_PASIC3
tristate "HTC PASIC3 LED/DS1WM chip support"
select MFD_CORE
- depends on GENERIC_HARDIRQS
help
This core driver provides register access for the LED/DS1WM
chips labeled "AIC2" and "AIC3", found on HTC Blueangel and
@@ -210,7 +209,7 @@
config LPC_ICH
tristate "Intel ICH LPC"
- depends on PCI && GENERIC_HARDIRQS
+ depends on PCI
select MFD_CORE
help
The LPC bridge function of the Intel ICH provides support for
@@ -220,7 +219,7 @@
config LPC_SCH
tristate "Intel SCH LPC"
- depends on PCI && GENERIC_HARDIRQS
+ depends on PCI
select MFD_CORE
help
LPC bridge function of the Intel SCH provides support for
@@ -238,7 +237,7 @@
config MFD_JANZ_CMODIO
tristate "Janz CMOD-IO PCI MODULbus Carrier Board"
select MFD_CORE
- depends on PCI && GENERIC_HARDIRQS
+ depends on PCI
help
This is the core driver for the Janz CMOD-IO PCI MODULbus
carrier board. This device is a PCI to MODULbus bridge which may
@@ -277,7 +276,7 @@
config MFD_88PM800
tristate "Marvell 88PM800"
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
select REGMAP_I2C
select REGMAP_IRQ
select MFD_CORE
@@ -289,7 +288,7 @@
config MFD_88PM805
tristate "Marvell 88PM805"
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
select REGMAP_I2C
select REGMAP_IRQ
select MFD_CORE
@@ -301,7 +300,7 @@
config MFD_88PM860X
bool "Marvell 88PM8606/88PM8607"
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
select REGMAP_I2C
select MFD_CORE
help
@@ -312,7 +311,7 @@
config MFD_MAX77686
bool "Maxim Semiconductor MAX77686 PMIC Support"
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
select MFD_CORE
select REGMAP_I2C
select IRQ_DOMAIN
@@ -325,7 +324,7 @@
config MFD_MAX77693
bool "Maxim Semiconductor MAX77693 PMIC Support"
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
select MFD_CORE
select REGMAP_I2C
help
@@ -339,7 +338,7 @@
config MFD_MAX8907
tristate "Maxim Semiconductor MAX8907 PMIC Support"
select MFD_CORE
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
select REGMAP_I2C
select REGMAP_IRQ
help
@@ -350,7 +349,7 @@
config MFD_MAX8925
bool "Maxim Semiconductor MAX8925 PMIC Support"
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
select MFD_CORE
help
Say yes here to support for Maxim Semiconductor MAX8925. This is
@@ -360,7 +359,7 @@
config MFD_MAX8997
bool "Maxim Semiconductor MAX8997/8966 PMIC Support"
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
select MFD_CORE
select IRQ_DOMAIN
help
@@ -373,7 +372,7 @@
config MFD_MAX8998
bool "Maxim Semiconductor MAX8998/National LP3974 PMIC Support"
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
select MFD_CORE
select IRQ_DOMAIN
help
@@ -385,7 +384,7 @@
config EZX_PCAP
bool "Motorola EZXPCAP Support"
- depends on GENERIC_HARDIRQS && SPI_MASTER
+ depends on SPI_MASTER
help
This enables the PCAP ASIC present on EZX Phones. This is
needed for MMC, TouchScreen, Sound, USB, etc..
@@ -393,7 +392,7 @@
config MFD_VIPERBOARD
tristate "Nano River Technologies Viperboard"
select MFD_CORE
- depends on USB && GENERIC_HARDIRQS
+ depends on USB
default n
help
Say yes here if you want support for Nano River Technologies
@@ -407,7 +406,7 @@
config MFD_RETU
tristate "Nokia Retu and Tahvo multi-function device"
select MFD_CORE
- depends on I2C && GENERIC_HARDIRQS
+ depends on I2C
select REGMAP_IRQ
help
Retu and Tahvo are a multi-function devices found on Nokia
@@ -480,7 +479,7 @@
config MFD_RDC321X
tristate "RDC R-321x southbridge"
select MFD_CORE
- depends on PCI && GENERIC_HARDIRQS
+ depends on PCI
help
Say yes here if you want to have support for the RDC R-321x SoC
southbridge which provides access to GPIOs and Watchdog using the
@@ -488,7 +487,7 @@
config MFD_RTSX_PCI
tristate "Realtek PCI-E card reader"
- depends on PCI && GENERIC_HARDIRQS
+ depends on PCI
select MFD_CORE
help
This supports for Realtek PCI-Express card reader including rts5209,
@@ -498,7 +497,7 @@
config MFD_RC5T583
bool "Ricoh RC5T583 Power Management system device"
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
select MFD_CORE
select REGMAP_I2C
help
@@ -512,7 +511,7 @@
config MFD_SEC_CORE
bool "SAMSUNG Electronics PMIC Series Support"
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
select MFD_CORE
select REGMAP_I2C
select REGMAP_IRQ
@@ -555,7 +554,7 @@
config MFD_SMSC
bool "SMSC ECE1099 series chips"
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
select MFD_CORE
select REGMAP_I2C
help
@@ -577,7 +576,7 @@
config AB3100_CORE
bool "ST-Ericsson AB3100 Mixed Signal Circuit core functions"
- depends on I2C=y && ABX500_CORE && GENERIC_HARDIRQS
+ depends on I2C=y && ABX500_CORE
select MFD_CORE
default y if ARCH_U300
help
@@ -601,7 +600,7 @@
config AB8500_CORE
bool "ST-Ericsson AB8500 Mixed Signal Power Management chip"
- depends on GENERIC_HARDIRQS && ABX500_CORE && MFD_DB8500_PRCMU
+ depends on ABX500_CORE && MFD_DB8500_PRCMU
select POWER_SUPPLY
select MFD_CORE
select IRQ_DOMAIN
@@ -639,7 +638,7 @@
config MFD_STMPE
bool "STMicroelectronics STMPE"
- depends on (I2C=y || SPI_MASTER=y) && GENERIC_HARDIRQS
+ depends on (I2C=y || SPI_MASTER=y)
select MFD_CORE
help
Support for the STMPE family of I/O Expanders from
@@ -680,7 +679,7 @@
config MFD_STA2X11
bool "STMicroelectronics STA2X11"
- depends on STA2X11 && GENERIC_HARDIRQS
+ depends on STA2X11
select MFD_CORE
select REGMAP_MMIO
@@ -700,7 +699,6 @@
select MFD_CORE
select REGMAP
select REGMAP_MMIO
- depends on GENERIC_HARDIRQS
help
If you say yes here you get support for Texas Instruments series
of Touch Screen /ADC chips.
@@ -717,7 +715,7 @@
config MFD_LP8788
bool "TI LP8788 Power Management Unit Driver"
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
select MFD_CORE
select REGMAP_I2C
select IRQ_DOMAIN
@@ -739,14 +737,14 @@
select MFD_CORE
select REGMAP_I2C
select REGMAP_IRQ
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
help
If you say yes here you get support for the Palmas
series of PMIC chips from Texas Instruments.
config MFD_TI_SSP
tristate "TI Sequencer Serial Port support"
- depends on ARCH_DAVINCI_TNETV107X && GENERIC_HARDIRQS
+ depends on ARCH_DAVINCI_TNETV107X
select MFD_CORE
---help---
Say Y here if you want support for the Sequencer Serial Port
@@ -761,7 +759,6 @@
select REGULATOR
select MFD_CORE
select REGULATOR_FIXED_VOLTAGE
- depends on GENERIC_HARDIRQS
help
This option enables a driver for the TP61050/TPS61052
high-power "white LED driver". This boost converter is
@@ -784,7 +781,7 @@
config TPS6507X
tristate "TI TPS6507x Power Management / Touch Screen chips"
select MFD_CORE
- depends on I2C && GENERIC_HARDIRQS
+ depends on I2C
help
If you say yes here you get support for the TPS6507x series of
Power Management / Touch Screen chips. These include voltage
@@ -798,7 +795,7 @@
config MFD_TPS65090
bool "TI TPS65090 Power Management chips"
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
select MFD_CORE
select REGMAP_I2C
select REGMAP_IRQ
@@ -811,7 +808,7 @@
config MFD_TPS65217
tristate "TI TPS65217 Power Management / White LED chips"
- depends on I2C && GENERIC_HARDIRQS
+ depends on I2C
select MFD_CORE
select REGMAP_I2C
help
@@ -826,7 +823,7 @@
config MFD_TPS6586X
bool "TI TPS6586x Power Management chips"
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
select MFD_CORE
select REGMAP_I2C
help
@@ -841,7 +838,7 @@
config MFD_TPS65910
bool "TI TPS65910 Power Management chip"
- depends on I2C=y && GPIOLIB && GENERIC_HARDIRQS
+ depends on I2C=y && GPIOLIB
select MFD_CORE
select REGMAP_I2C
select REGMAP_IRQ
@@ -862,7 +859,7 @@
bool "TI TPS65912 Power Management chip with I2C"
select MFD_CORE
select MFD_TPS65912
- depends on I2C=y && GPIOLIB && GENERIC_HARDIRQS
+ depends on I2C=y && GPIOLIB
help
If you say yes here you get support for the TPS65912 series of
PM chips with I2C interface.
@@ -871,14 +868,14 @@
bool "TI TPS65912 Power Management chip with SPI"
select MFD_CORE
select MFD_TPS65912
- depends on SPI_MASTER && GPIOLIB && GENERIC_HARDIRQS
+ depends on SPI_MASTER && GPIOLIB
help
If you say yes here you get support for the TPS65912 series of
PM chips with SPI interface.
config MFD_TPS80031
bool "TI TPS80031/TPS80032 Power Management chips"
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
select MFD_CORE
select REGMAP_I2C
select REGMAP_IRQ
@@ -892,7 +889,7 @@
config TWL4030_CORE
bool "TI TWL4030/TWL5030/TWL6030/TPS659x0 Support"
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
select IRQ_DOMAIN
select REGMAP_I2C
help
@@ -931,13 +928,13 @@
config MFD_TWL4030_AUDIO
bool "TI TWL4030 Audio"
- depends on TWL4030_CORE && GENERIC_HARDIRQS
+ depends on TWL4030_CORE
select MFD_CORE
default n
config TWL6040_CORE
bool "TI TWL6040 audio codec"
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
select MFD_CORE
select REGMAP_I2C
select REGMAP_IRQ
@@ -961,7 +958,7 @@
config MFD_WL1273_CORE
tristate "TI WL1273 FM radio"
- depends on I2C && GENERIC_HARDIRQS
+ depends on I2C
select MFD_CORE
default n
help
@@ -974,7 +971,6 @@
depends on I2C
select MFD_CORE
select REGMAP_I2C
- depends on GENERIC_HARDIRQS
help
Say yes here to enable support for National Semiconductor / TI
LM3533 Lighting Power chips.
@@ -996,7 +992,7 @@
config MFD_TC3589X
bool "Toshiba TC35892 and variants"
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
select MFD_CORE
help
Support for the Toshiba TC35892 and variants I/O Expander.
@@ -1011,7 +1007,7 @@
config MFD_T7L66XB
bool "Toshiba T7L66XB"
- depends on ARM && HAVE_CLK && GENERIC_HARDIRQS
+ depends on ARM && HAVE_CLK
select MFD_CORE
select MFD_TMIO
help
@@ -1036,7 +1032,7 @@
config MFD_VX855
tristate "VIA VX855/VX875 integrated south bridge"
- depends on PCI && GENERIC_HARDIRQS
+ depends on PCI
select MFD_CORE
help
Say yes here to enable support for various functions of the
@@ -1054,7 +1050,7 @@
select MFD_ARIZONA
select MFD_CORE
select REGMAP_I2C
- depends on I2C && GENERIC_HARDIRQS
+ depends on I2C
help
Support for the Wolfson Microelectronics Arizona platform audio SoC
core functionality controlled via I2C.
@@ -1064,7 +1060,7 @@
select MFD_ARIZONA
select MFD_CORE
select REGMAP_SPI
- depends on SPI_MASTER && GENERIC_HARDIRQS
+ depends on SPI_MASTER
help
Support for the Wolfson Microelectronics Arizona platform audio SoC
core functionality controlled via I2C.
@@ -1090,7 +1086,7 @@
config MFD_WM8400
bool "Wolfson Microelectronics WM8400"
select MFD_CORE
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
select REGMAP_I2C
help
Support for the Wolfson Microelecronics WM8400 PMIC and audio
@@ -1100,7 +1096,6 @@
config MFD_WM831X
bool
- depends on GENERIC_HARDIRQS
config MFD_WM831X_I2C
bool "Wolfson Microelectronics WM831x/2x PMICs with I2C"
@@ -1108,7 +1103,7 @@
select MFD_WM831X
select REGMAP_I2C
select IRQ_DOMAIN
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
help
Support for the Wolfson Microelecronics WM831x and WM832x PMICs
when controlled using I2C. This driver provides common support
@@ -1121,7 +1116,7 @@
select MFD_WM831X
select REGMAP_SPI
select IRQ_DOMAIN
- depends on SPI_MASTER && GENERIC_HARDIRQS
+ depends on SPI_MASTER
help
Support for the Wolfson Microelecronics WM831x and WM832x PMICs
when controlled using SPI. This driver provides common support
@@ -1130,12 +1125,11 @@
config MFD_WM8350
bool
- depends on GENERIC_HARDIRQS
config MFD_WM8350_I2C
bool "Wolfson Microelectronics WM8350 with I2C"
select MFD_WM8350
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
help
The WM8350 is an integrated audio and power management
subsystem with watchdog and RTC functionality for embedded
@@ -1148,7 +1142,7 @@
select MFD_CORE
select REGMAP_I2C
select REGMAP_IRQ
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
help
The WM8994 is a highly integrated hi-fi CODEC designed for
smartphone applicatiosn. As well as audio functionality it
diff --git a/drivers/misc/cb710/Kconfig b/drivers/misc/cb710/Kconfig
index 5acb9c5..22429b8 100644
--- a/drivers/misc/cb710/Kconfig
+++ b/drivers/misc/cb710/Kconfig
@@ -1,6 +1,6 @@
config CB710_CORE
tristate "ENE CB710/720 Flash memory card reader support"
- depends on PCI && GENERIC_HARDIRQS
+ depends on PCI
help
This option enables support for PCI ENE CB710/720 Flash memory card
reader found in some laptops (ie. some versions of HP Compaq nx9500).
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index b7fd5ab..7fc5099 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -487,7 +487,7 @@
config MMC_CB710
tristate "ENE CB710 MMC/SD Interface support"
- depends on PCI && GENERIC_HARDIRQS
+ depends on PCI
select CB710_CORE
help
This option enables support for MMC/SD part of ENE CB710/720 Flash
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 39e5b1c..72df399 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2404,8 +2404,8 @@
slave->target_last_arp_rx[i] = jiffies;
}
-static int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond,
- struct slave *slave)
+int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond,
+ struct slave *slave)
{
struct arphdr *arp = (struct arphdr *)skb->data;
unsigned char *arp_ptr;
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index ce46776..eeab40b 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -349,6 +349,8 @@
goto out;
}
+ /* don't cache arp_validate between modes */
+ bond->params.arp_validate = BOND_ARP_VALIDATE_NONE;
bond->params.mode = new_value;
bond_set_mode_ops(bond, bond->params.mode);
pr_info("%s: setting mode to %s (%d).\n",
@@ -419,27 +421,39 @@
struct device_attribute *attr,
const char *buf, size_t count)
{
- int new_value;
struct bonding *bond = to_bond(d);
+ int new_value, ret = count;
+ if (!rtnl_trylock())
+ return restart_syscall();
new_value = bond_parse_parm(buf, arp_validate_tbl);
if (new_value < 0) {
pr_err("%s: Ignoring invalid arp_validate value %s\n",
bond->dev->name, buf);
- return -EINVAL;
+ ret = -EINVAL;
+ goto out;
}
- if (new_value && (bond->params.mode != BOND_MODE_ACTIVEBACKUP)) {
+ if (bond->params.mode != BOND_MODE_ACTIVEBACKUP) {
pr_err("%s: arp_validate only supported in active-backup mode.\n",
bond->dev->name);
- return -EINVAL;
+ ret = -EINVAL;
+ goto out;
}
pr_info("%s: setting arp_validate to %s (%d).\n",
bond->dev->name, arp_validate_tbl[new_value].modename,
new_value);
+ if (bond->dev->flags & IFF_UP) {
+ if (!new_value)
+ bond->recv_probe = NULL;
+ else if (bond->params.arp_interval)
+ bond->recv_probe = bond_arp_rcv;
+ }
bond->params.arp_validate = new_value;
+out:
+ rtnl_unlock();
- return count;
+ return ret;
}
static DEVICE_ATTR(arp_validate, S_IRUGO | S_IWUSR, bonding_show_arp_validate,
@@ -555,8 +569,8 @@
struct device_attribute *attr,
const char *buf, size_t count)
{
- int new_value, ret = count;
struct bonding *bond = to_bond(d);
+ int new_value, ret = count;
if (!rtnl_trylock())
return restart_syscall();
@@ -599,8 +613,13 @@
* is called.
*/
if (!new_value) {
+ if (bond->params.arp_validate)
+ bond->recv_probe = NULL;
cancel_delayed_work_sync(&bond->arp_work);
} else {
+ /* arp_validate can be set only in active-backup mode */
+ if (bond->params.arp_validate)
+ bond->recv_probe = bond_arp_rcv;
cancel_delayed_work_sync(&bond->mii_work);
queue_delayed_work(bond->wq, &bond->arp_work, 0);
}
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index f7ab161..7ad8bd5 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -430,6 +430,7 @@
struct bond_net;
+int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave);
struct vlan_entry *bond_next_vlan(struct bonding *bond, struct vlan_entry *curr);
int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev);
void bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb, int slave_id);
diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
index 8ac48fb..b9a5fb6 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
@@ -926,13 +926,13 @@
if (ret)
goto out_phy_disconnect;
- ret = request_irq(priv->irq_rx, bcm_enet_isr_dma, IRQF_DISABLED,
+ ret = request_irq(priv->irq_rx, bcm_enet_isr_dma, 0,
dev->name, dev);
if (ret)
goto out_freeirq;
ret = request_irq(priv->irq_tx, bcm_enet_isr_dma,
- IRQF_DISABLED, dev->name, dev);
+ 0, dev->name, dev);
if (ret)
goto out_freeirq_rx;
@@ -2156,13 +2156,13 @@
enet_dmac_writel(priv, 0, ENETDMAC_IRMASK, priv->tx_chan);
ret = request_irq(priv->irq_rx, bcm_enet_isr_dma,
- IRQF_DISABLED, dev->name, dev);
+ 0, dev->name, dev);
if (ret)
goto out_freeirq;
if (priv->irq_tx != -1) {
ret = request_irq(priv->irq_tx, bcm_enet_isr_dma,
- IRQF_DISABLED, dev->name, dev);
+ 0, dev->name, dev);
if (ret)
goto out_freeirq_rx;
}
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 2361bf2..90045c9 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -490,10 +490,10 @@
NAPI_GRO_CB(skb)->count = num_of_coalesced_segs;
}
-static int bnx2x_alloc_rx_sge(struct bnx2x *bp,
- struct bnx2x_fastpath *fp, u16 index)
+static int bnx2x_alloc_rx_sge(struct bnx2x *bp, struct bnx2x_fastpath *fp,
+ u16 index, gfp_t gfp_mask)
{
- struct page *page = alloc_pages(GFP_ATOMIC, PAGES_PER_SGE_SHIFT);
+ struct page *page = alloc_pages(gfp_mask, PAGES_PER_SGE_SHIFT);
struct sw_rx_page *sw_buf = &fp->rx_page_ring[index];
struct eth_rx_sge *sge = &fp->rx_sge_ring[index];
dma_addr_t mapping;
@@ -572,7 +572,7 @@
/* If we fail to allocate a substitute page, we simply stop
where we are and drop the whole packet */
- err = bnx2x_alloc_rx_sge(bp, fp, sge_idx);
+ err = bnx2x_alloc_rx_sge(bp, fp, sge_idx, GFP_ATOMIC);
if (unlikely(err)) {
bnx2x_fp_qstats(bp, fp)->rx_skb_alloc_failed++;
return err;
@@ -616,12 +616,17 @@
kfree(data);
}
-static void *bnx2x_frag_alloc(const struct bnx2x_fastpath *fp)
+static void *bnx2x_frag_alloc(const struct bnx2x_fastpath *fp, gfp_t gfp_mask)
{
- if (fp->rx_frag_size)
- return netdev_alloc_frag(fp->rx_frag_size);
+ if (fp->rx_frag_size) {
+ /* GFP_KERNEL allocations are used only during initialization */
+ if (unlikely(gfp_mask & __GFP_WAIT))
+ return (void *)__get_free_page(gfp_mask);
- return kmalloc(fp->rx_buf_size + NET_SKB_PAD, GFP_ATOMIC);
+ return netdev_alloc_frag(fp->rx_frag_size);
+ }
+
+ return kmalloc(fp->rx_buf_size + NET_SKB_PAD, gfp_mask);
}
#ifdef CONFIG_INET
@@ -701,7 +706,7 @@
goto drop;
/* Try to allocate the new data */
- new_data = bnx2x_frag_alloc(fp);
+ new_data = bnx2x_frag_alloc(fp, GFP_ATOMIC);
/* Unmap skb in the pool anyway, as we are going to change
pool entry status to BNX2X_TPA_STOP even if new skb allocation
fails. */
@@ -752,15 +757,15 @@
bnx2x_fp_stats(bp, fp)->eth_q_stats.rx_skb_alloc_failed++;
}
-static int bnx2x_alloc_rx_data(struct bnx2x *bp,
- struct bnx2x_fastpath *fp, u16 index)
+static int bnx2x_alloc_rx_data(struct bnx2x *bp, struct bnx2x_fastpath *fp,
+ u16 index, gfp_t gfp_mask)
{
u8 *data;
struct sw_rx_bd *rx_buf = &fp->rx_buf_ring[index];
struct eth_rx_bd *rx_bd = &fp->rx_desc_ring[index];
dma_addr_t mapping;
- data = bnx2x_frag_alloc(fp);
+ data = bnx2x_frag_alloc(fp, gfp_mask);
if (unlikely(data == NULL))
return -ENOMEM;
@@ -953,7 +958,8 @@
memcpy(skb->data, data + pad, len);
bnx2x_reuse_rx_data(fp, bd_cons, bd_prod);
} else {
- if (likely(bnx2x_alloc_rx_data(bp, fp, bd_prod) == 0)) {
+ if (likely(bnx2x_alloc_rx_data(bp, fp, bd_prod,
+ GFP_ATOMIC) == 0)) {
dma_unmap_single(&bp->pdev->dev,
dma_unmap_addr(rx_buf, mapping),
fp->rx_buf_size,
@@ -1313,7 +1319,8 @@
struct sw_rx_bd *first_buf =
&tpa_info->first_buf;
- first_buf->data = bnx2x_frag_alloc(fp);
+ first_buf->data =
+ bnx2x_frag_alloc(fp, GFP_KERNEL);
if (!first_buf->data) {
BNX2X_ERR("Failed to allocate TPA skb pool for queue[%d] - disabling TPA on this queue!\n",
j);
@@ -1335,7 +1342,8 @@
for (i = 0, ring_prod = 0;
i < MAX_RX_SGE_CNT*NUM_RX_SGE_PAGES; i++) {
- if (bnx2x_alloc_rx_sge(bp, fp, ring_prod) < 0) {
+ if (bnx2x_alloc_rx_sge(bp, fp, ring_prod,
+ GFP_KERNEL) < 0) {
BNX2X_ERR("was only able to allocate %d rx sges\n",
i);
BNX2X_ERR("disabling TPA for queue[%d]\n",
@@ -4221,7 +4229,7 @@
* fp->eth_q_stats.rx_skb_alloc_failed = 0
*/
for (i = 0; i < rx_ring_size; i++) {
- if (bnx2x_alloc_rx_data(bp, fp, ring_prod) < 0) {
+ if (bnx2x_alloc_rx_data(bp, fp, ring_prod, GFP_KERNEL) < 0) {
failure_cnt++;
continue;
}
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 634a793..2f8dbbb 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -7645,6 +7645,7 @@
bnx2x_init_block(bp, BLOCK_TM, init_phase);
bnx2x_init_block(bp, BLOCK_DORQ, init_phase);
+ REG_WR(bp, DORQ_REG_MODE_ACT, 1); /* no dpm */
bnx2x_iov_init_dq(bp);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index b26eb83..2604b62 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -1756,9 +1756,6 @@
REG_WR(bp, DORQ_REG_VF_TYPE_MIN_MCID_0, 0);
REG_WR(bp, DORQ_REG_VF_TYPE_MAX_MCID_0, 0x1ffff);
- /* set the number of VF allowed doorbells to the full DQ range */
- REG_WR(bp, DORQ_REG_VF_NORM_MAX_CID_COUNT, 0x20000);
-
/* set the VF doorbell threshold */
REG_WR(bp, DORQ_REG_VF_USAGE_CT_LIMIT, 4);
}
diff --git a/drivers/net/ethernet/cadence/Kconfig b/drivers/net/ethernet/cadence/Kconfig
index 8030cc0..751d5c7 100644
--- a/drivers/net/ethernet/cadence/Kconfig
+++ b/drivers/net/ethernet/cadence/Kconfig
@@ -22,7 +22,7 @@
config ARM_AT91_ETHER
tristate "AT91RM9200 Ethernet support"
- depends on GENERIC_HARDIRQS && HAS_DMA
+ depends on HAS_DMA
select MACB
---help---
If you wish to compile a kernel for the AT91RM9200 and enable
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig
index f0e7ed2..149ac85 100644
--- a/drivers/net/ethernet/intel/Kconfig
+++ b/drivers/net/ethernet/intel/Kconfig
@@ -241,4 +241,22 @@
will be called ixgbevf. MSI-X interrupt support is required
for this driver to work correctly.
+config I40E
+ tristate "Intel(R) Ethernet Controller XL710 Family support"
+ depends on PCI
+ ---help---
+ This driver supports Intel(R) Ethernet Controller XL710 Family of
+ devices. For more information on how to identify your adapter, go
+ to the Adapter & Driver ID Guide at:
+
+ <http://support.intel.com/support/network/adapter/pro100/21397.htm>
+
+ For general information and support, go to the Intel support
+ website at:
+
+ <http://support.intel.com>
+
+ To compile this driver as a module, choose M here. The module
+ will be called i40e.
+
endif # NET_VENDOR_INTEL
diff --git a/drivers/net/ethernet/intel/Makefile b/drivers/net/ethernet/intel/Makefile
index c8210e6..5bae933 100644
--- a/drivers/net/ethernet/intel/Makefile
+++ b/drivers/net/ethernet/intel/Makefile
@@ -9,4 +9,5 @@
obj-$(CONFIG_IGBVF) += igbvf/
obj-$(CONFIG_IXGBE) += ixgbe/
obj-$(CONFIG_IXGBEVF) += ixgbevf/
+obj-$(CONFIG_I40E) += i40e/
obj-$(CONFIG_IXGB) += ixgb/
diff --git a/drivers/net/ethernet/intel/i40e/Makefile b/drivers/net/ethernet/intel/i40e/Makefile
new file mode 100644
index 0000000..479b2c4
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/Makefile
@@ -0,0 +1,44 @@
+################################################################################
+#
+# Intel Ethernet Controller XL710 Family Linux Driver
+# Copyright(c) 2013 Intel Corporation.
+#
+# This program is free software; you can redistribute it and/or modify it
+# under the terms and conditions of the GNU General Public License,
+# version 2, as published by the Free Software Foundation.
+#
+# This program is distributed in the hope it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+# more details.
+#
+# You should have received a copy of the GNU General Public License along with
+# this program; if not, write to the Free Software Foundation, Inc.,
+# 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+#
+# The full GNU General Public License is included in this distribution in
+# the file called "COPYING".
+#
+# Contact Information:
+# e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+# Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+#
+################################################################################
+
+#
+# Makefile for the Intel(R) Ethernet Connection XL710 (i40e.ko) driver
+#
+
+obj-$(CONFIG_I40E) += i40e.o
+
+i40e-objs := i40e_main.o \
+ i40e_ethtool.o \
+ i40e_adminq.o \
+ i40e_common.o \
+ i40e_hmc.o \
+ i40e_lan_hmc.o \
+ i40e_nvm.o \
+ i40e_debugfs.o \
+ i40e_diag.o \
+ i40e_txrx.o \
+ i40e_virtchnl_pf.o
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
new file mode 100644
index 0000000..b5252eb
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -0,0 +1,558 @@
+/*******************************************************************************
+ *
+ * Intel Ethernet Controller XL710 Family Linux Driver
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ ******************************************************************************/
+
+#ifndef _I40E_H_
+#define _I40E_H_
+
+#include <net/tcp.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/aer.h>
+#include <linux/netdevice.h>
+#include <linux/ioport.h>
+#include <linux/slab.h>
+#include <linux/list.h>
+#include <linux/string.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/tcp.h>
+#include <linux/sctp.h>
+#include <linux/pkt_sched.h>
+#include <linux/ipv6.h>
+#include <linux/version.h>
+#include <net/checksum.h>
+#include <net/ip6_checksum.h>
+#include <linux/ethtool.h>
+#include <linux/if_vlan.h>
+#include "i40e_type.h"
+#include "i40e_prototype.h"
+#include "i40e_virtchnl.h"
+#include "i40e_virtchnl_pf.h"
+#include "i40e_txrx.h"
+
+/* Useful i40e defaults */
+#define I40E_BASE_PF_SEID 16
+#define I40E_BASE_VSI_SEID 512
+#define I40E_BASE_VEB_SEID 288
+#define I40E_MAX_VEB 16
+
+#define I40E_MAX_NUM_DESCRIPTORS 4096
+#define I40E_MAX_REGISTER 0x0038FFFF
+#define I40E_DEFAULT_NUM_DESCRIPTORS 512
+#define I40E_REQ_DESCRIPTOR_MULTIPLE 32
+#define I40E_MIN_NUM_DESCRIPTORS 64
+#define I40E_MIN_MSIX 2
+#define I40E_DEFAULT_NUM_VMDQ_VSI 8 /* max 256 VSIs */
+#define I40E_DEFAULT_QUEUES_PER_VMDQ 2 /* max 16 qps */
+#define I40E_DEFAULT_QUEUES_PER_VF 4
+#define I40E_DEFAULT_QUEUES_PER_TC 1 /* should be a power of 2 */
+#define I40E_FDIR_RING 0
+#define I40E_FDIR_RING_COUNT 32
+#define I40E_MAX_AQ_BUF_SIZE 4096
+#define I40E_AQ_LEN 32
+#define I40E_AQ_WORK_LIMIT 16
+#define I40E_MAX_USER_PRIORITY 8
+#define I40E_DEFAULT_MSG_ENABLE 4
+
+#define I40E_NVM_VERSION_LO_SHIFT 0
+#define I40E_NVM_VERSION_LO_MASK (0xf << I40E_NVM_VERSION_LO_SHIFT)
+#define I40E_NVM_VERSION_MID_SHIFT 4
+#define I40E_NVM_VERSION_MID_MASK (0xff << I40E_NVM_VERSION_MID_SHIFT)
+#define I40E_NVM_VERSION_HI_SHIFT 12
+#define I40E_NVM_VERSION_HI_MASK (0xf << I40E_NVM_VERSION_HI_SHIFT)
+
+/* magic for getting defines into strings */
+#define STRINGIFY(foo) #foo
+#define XSTRINGIFY(bar) STRINGIFY(bar)
+
+#ifndef ARCH_HAS_PREFETCH
+#define prefetch(X)
+#endif
+
+#define I40E_RX_DESC(R, i) \
+ ((ring_is_16byte_desc_enabled(R)) \
+ ? (union i40e_32byte_rx_desc *) \
+ (&(((union i40e_16byte_rx_desc *)((R)->desc))[i])) \
+ : (&(((union i40e_32byte_rx_desc *)((R)->desc))[i])))
+#define I40E_TX_DESC(R, i) \
+ (&(((struct i40e_tx_desc *)((R)->desc))[i]))
+#define I40E_TX_CTXTDESC(R, i) \
+ (&(((struct i40e_tx_context_desc *)((R)->desc))[i]))
+#define I40E_TX_FDIRDESC(R, i) \
+ (&(((struct i40e_filter_program_desc *)((R)->desc))[i]))
+
+/* default to trying for four seconds */
+#define I40E_TRY_LINK_TIMEOUT (4 * HZ)
+
+/* driver state flags */
+enum i40e_state_t {
+ __I40E_TESTING,
+ __I40E_CONFIG_BUSY,
+ __I40E_CONFIG_DONE,
+ __I40E_DOWN,
+ __I40E_NEEDS_RESTART,
+ __I40E_SERVICE_SCHED,
+ __I40E_ADMINQ_EVENT_PENDING,
+ __I40E_MDD_EVENT_PENDING,
+ __I40E_VFLR_EVENT_PENDING,
+ __I40E_RESET_RECOVERY_PENDING,
+ __I40E_RESET_INTR_RECEIVED,
+ __I40E_REINIT_REQUESTED,
+ __I40E_PF_RESET_REQUESTED,
+ __I40E_CORE_RESET_REQUESTED,
+ __I40E_GLOBAL_RESET_REQUESTED,
+ __I40E_FILTER_OVERFLOW_PROMISC,
+};
+
+enum i40e_interrupt_policy {
+ I40E_INTERRUPT_BEST_CASE,
+ I40E_INTERRUPT_MEDIUM,
+ I40E_INTERRUPT_LOWEST
+};
+
+struct i40e_lump_tracking {
+ u16 num_entries;
+ u16 search_hint;
+ u16 list[0];
+#define I40E_PILE_VALID_BIT 0x8000
+};
+
+#define I40E_DEFAULT_ATR_SAMPLE_RATE 20
+#define I40E_FDIR_MAX_RAW_PACKET_LOOKUP 512
+struct i40e_fdir_data {
+ u16 q_index;
+ u8 flex_off;
+ u8 pctype;
+ u16 dest_vsi;
+ u8 dest_ctl;
+ u8 fd_status;
+ u16 cnt_index;
+ u32 fd_id;
+ u8 *raw_packet;
+};
+
+#define I40E_DCB_PRIO_TYPE_STRICT 0
+#define I40E_DCB_PRIO_TYPE_ETS 1
+#define I40E_DCB_STRICT_PRIO_CREDITS 127
+#define I40E_MAX_USER_PRIORITY 8
+/* DCB per TC information data structure */
+struct i40e_tc_info {
+ u16 qoffset; /* Queue offset from base queue */
+ u16 qcount; /* Total Queues */
+ u8 netdev_tc; /* Netdev TC index if netdev associated */
+};
+
+/* TC configuration data structure */
+struct i40e_tc_configuration {
+ u8 numtc; /* Total number of enabled TCs */
+ u8 enabled_tc; /* TC map */
+ struct i40e_tc_info tc_info[I40E_MAX_TRAFFIC_CLASS];
+};
+
+/* struct that defines the Ethernet device */
+struct i40e_pf {
+ struct pci_dev *pdev;
+ struct i40e_hw hw;
+ unsigned long state;
+ unsigned long link_check_timeout;
+ struct msix_entry *msix_entries;
+ u16 num_msix_entries;
+ bool fc_autoneg_status;
+
+ u16 eeprom_version;
+ u16 num_vmdq_vsis; /* num vmdq pools this pf has set up */
+ u16 num_vmdq_qps; /* num queue pairs per vmdq pool */
+ u16 num_vmdq_msix; /* num queue vectors per vmdq pool */
+ u16 num_req_vfs; /* num vfs requested for this vf */
+ u16 num_vf_qps; /* num queue pairs per vf */
+ u16 num_tc_qps; /* num queue pairs per TC */
+ u16 num_lan_qps; /* num lan queues this pf has set up */
+ u16 num_lan_msix; /* num queue vectors for the base pf vsi */
+ u16 rss_size; /* num queues in the RSS array */
+ u16 rss_size_max; /* HW defined max RSS queues */
+ u16 fdir_pf_filter_count; /* num of guaranteed filters for this PF */
+ u8 atr_sample_rate;
+
+ enum i40e_interrupt_policy int_policy;
+ u16 rx_itr_default;
+ u16 tx_itr_default;
+ u16 msg_enable;
+ char misc_int_name[IFNAMSIZ + 9];
+ u16 adminq_work_limit; /* num of admin receive queue desc to process */
+ int service_timer_period;
+ struct timer_list service_timer;
+ struct work_struct service_task;
+
+ u64 flags;
+#define I40E_FLAG_RX_CSUM_ENABLED (u64)(1 << 1)
+#define I40E_FLAG_MSI_ENABLED (u64)(1 << 2)
+#define I40E_FLAG_MSIX_ENABLED (u64)(1 << 3)
+#define I40E_FLAG_RX_1BUF_ENABLED (u64)(1 << 4)
+#define I40E_FLAG_RX_PS_ENABLED (u64)(1 << 5)
+#define I40E_FLAG_RSS_ENABLED (u64)(1 << 6)
+#define I40E_FLAG_MQ_ENABLED (u64)(1 << 7)
+#define I40E_FLAG_VMDQ_ENABLED (u64)(1 << 8)
+#define I40E_FLAG_FDIR_REQUIRES_REINIT (u64)(1 << 9)
+#define I40E_FLAG_NEED_LINK_UPDATE (u64)(1 << 10)
+#define I40E_FLAG_IN_NETPOLL (u64)(1 << 13)
+#define I40E_FLAG_16BYTE_RX_DESC_ENABLED (u64)(1 << 14)
+#define I40E_FLAG_CLEAN_ADMINQ (u64)(1 << 15)
+#define I40E_FLAG_FILTER_SYNC (u64)(1 << 16)
+#define I40E_FLAG_PROCESS_MDD_EVENT (u64)(1 << 18)
+#define I40E_FLAG_PROCESS_VFLR_EVENT (u64)(1 << 19)
+#define I40E_FLAG_SRIOV_ENABLED (u64)(1 << 20)
+#define I40E_FLAG_DCB_ENABLED (u64)(1 << 21)
+#define I40E_FLAG_FDIR_ENABLED (u64)(1 << 22)
+#define I40E_FLAG_FDIR_ATR_ENABLED (u64)(1 << 23)
+#define I40E_FLAG_MFP_ENABLED (u64)(1 << 27)
+
+ u16 num_tx_queues;
+ u16 num_rx_queues;
+
+ bool stat_offsets_loaded;
+ struct i40e_hw_port_stats stats;
+ struct i40e_hw_port_stats stats_offsets;
+ u32 tx_timeout_count;
+ u32 tx_timeout_recovery_level;
+ unsigned long tx_timeout_last_recovery;
+ u32 hw_csum_rx_error;
+ u32 led_status;
+ u16 corer_count; /* Core reset count */
+ u16 globr_count; /* Global reset count */
+ u16 empr_count; /* EMP reset count */
+ u16 pfr_count; /* PF reset count */
+
+ struct mutex switch_mutex;
+ u16 lan_vsi; /* our default LAN VSI */
+ u16 lan_veb; /* initial relay, if exists */
+#define I40E_NO_VEB 0xffff
+#define I40E_NO_VSI 0xffff
+ u16 next_vsi; /* Next unallocated VSI - 0-based! */
+ struct i40e_vsi **vsi;
+ struct i40e_veb *veb[I40E_MAX_VEB];
+
+ struct i40e_lump_tracking *qp_pile;
+ struct i40e_lump_tracking *irq_pile;
+
+ /* switch config info */
+ u16 pf_seid;
+ u16 main_vsi_seid;
+ u16 mac_seid;
+ struct i40e_aqc_get_switch_config_data *sw_config;
+ struct kobject *switch_kobj;
+#ifdef CONFIG_DEBUG_FS
+ struct dentry *i40e_dbg_pf;
+#endif /* CONFIG_DEBUG_FS */
+
+ /* sr-iov config info */
+ struct i40e_vf *vf;
+ int num_alloc_vfs; /* actual number of VFs allocated */
+ u32 vf_aq_requests;
+
+ /* DCBx/DCBNL capability for PF that indicates
+ * whether DCBx is managed by firmware or host
+ * based agent (LLDPAD). Also, indicates what
+ * flavor of DCBx protocol (IEEE/CEE) is supported
+ * by the device. For now we're supporting IEEE
+ * mode only.
+ */
+ u16 dcbx_cap;
+
+ u32 fcoe_hmc_filt_num;
+ u32 fcoe_hmc_cntx_num;
+ struct i40e_filter_control_settings filter_settings;
+};
+
+struct i40e_mac_filter {
+ struct list_head list;
+ u8 macaddr[ETH_ALEN];
+#define I40E_VLAN_ANY -1
+ s16 vlan;
+ u8 counter; /* number of instances of this filter */
+ bool is_vf; /* filter belongs to a VF */
+ bool is_netdev; /* filter belongs to a netdev */
+ bool changed; /* filter needs to be sync'd to the HW */
+};
+
+struct i40e_veb {
+ struct i40e_pf *pf;
+ u16 idx;
+ u16 veb_idx; /* index of VEB parent */
+ u16 seid;
+ u16 uplink_seid;
+ u16 stats_idx; /* index of VEB parent */
+ u8 enabled_tc;
+ u16 flags;
+ u16 bw_limit;
+ u8 bw_max_quanta;
+ bool is_abs_credits;
+ u8 bw_tc_share_credits[I40E_MAX_TRAFFIC_CLASS];
+ u16 bw_tc_limit_credits[I40E_MAX_TRAFFIC_CLASS];
+ u8 bw_tc_max_quanta[I40E_MAX_TRAFFIC_CLASS];
+ struct kobject *kobj;
+ bool stat_offsets_loaded;
+ struct i40e_eth_stats stats;
+ struct i40e_eth_stats stats_offsets;
+};
+
+/* struct that defines a VSI, associated with a dev */
+struct i40e_vsi {
+ struct net_device *netdev;
+ unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
+ bool netdev_registered;
+ bool stat_offsets_loaded;
+
+ u32 current_netdev_flags;
+ unsigned long state;
+#define I40E_VSI_FLAG_FILTER_CHANGED (1<<0)
+#define I40E_VSI_FLAG_VEB_OWNER (1<<1)
+ unsigned long flags;
+
+ struct list_head mac_filter_list;
+
+ /* VSI stats */
+ struct rtnl_link_stats64 net_stats;
+ struct rtnl_link_stats64 net_stats_offsets;
+ struct i40e_eth_stats eth_stats;
+ struct i40e_eth_stats eth_stats_offsets;
+ u32 tx_restart;
+ u32 tx_busy;
+ u32 rx_buf_failed;
+ u32 rx_page_failed;
+
+ /* These are arrays of rings, allocated at run-time */
+ struct i40e_ring *rx_rings;
+ struct i40e_ring *tx_rings;
+
+ u16 work_limit;
+ /* high bit set means dynamic, use accessor routines to read/write.
+ * hardware only supports 2us resolution for the ITR registers.
+ * these values always store the USER setting, and must be converted
+ * before programming to a register.
+ */
+ u16 rx_itr_setting;
+ u16 tx_itr_setting;
+
+ u16 max_frame;
+ u16 rx_hdr_len;
+ u16 rx_buf_len;
+ u8 dtype;
+
+ /* List of q_vectors allocated to this VSI */
+ struct i40e_q_vector *q_vectors;
+ int num_q_vectors;
+ int base_vector;
+
+ u16 seid; /* HW index of this VSI (absolute index) */
+ u16 id; /* VSI number */
+ u16 uplink_seid;
+
+ u16 base_queue; /* vsi's first queue in hw array */
+ u16 alloc_queue_pairs; /* Allocated Tx/Rx queues */
+ u16 num_queue_pairs; /* Used tx and rx pairs */
+ u16 num_desc;
+ enum i40e_vsi_type type; /* VSI type, e.g., LAN, FCoE, etc */
+ u16 vf_id; /* Virtual function ID for SRIOV VSIs */
+
+ struct i40e_tc_configuration tc_config;
+ struct i40e_aqc_vsi_properties_data info;
+
+ /* VSI BW limit (absolute across all TCs) */
+ u16 bw_limit; /* VSI BW Limit (0 = disabled) */
+ u8 bw_max_quanta; /* Max Quanta when BW limit is enabled */
+
+ /* Relative TC credits across VSIs */
+ u8 bw_ets_share_credits[I40E_MAX_TRAFFIC_CLASS];
+ /* TC BW limit credits within VSI */
+ u16 bw_ets_limit_credits[I40E_MAX_TRAFFIC_CLASS];
+ /* TC BW limit max quanta within VSI */
+ u8 bw_ets_max_quanta[I40E_MAX_TRAFFIC_CLASS];
+
+ struct i40e_pf *back; /* Backreference to associated PF */
+ u16 idx; /* index in pf->vsi[] */
+ u16 veb_idx; /* index of VEB parent */
+ struct kobject *kobj; /* sysfs object */
+
+ /* VSI specific handlers */
+ irqreturn_t (*irq_handler)(int irq, void *data);
+} ____cacheline_internodealigned_in_smp;
+
+struct i40e_netdev_priv {
+ struct i40e_vsi *vsi;
+};
+
+/* struct that defines an interrupt vector */
+struct i40e_q_vector {
+ struct i40e_vsi *vsi;
+
+ u16 v_idx; /* index in the vsi->q_vector array. */
+ u16 reg_idx; /* register index of the interrupt */
+
+ struct napi_struct napi;
+
+ struct i40e_ring_container rx;
+ struct i40e_ring_container tx;
+
+ u8 num_ringpairs; /* total number of ring pairs in vector */
+
+ char name[IFNAMSIZ + 9];
+ cpumask_t affinity_mask;
+} ____cacheline_internodealigned_in_smp;
+
+/* lan device */
+struct i40e_device {
+ struct list_head list;
+ struct i40e_pf *pf;
+};
+
+/**
+ * i40e_fw_version_str - format the FW and NVM version strings
+ * @hw: ptr to the hardware info
+ **/
+static inline char *i40e_fw_version_str(struct i40e_hw *hw)
+{
+ static char buf[32];
+
+ snprintf(buf, sizeof(buf),
+ "f%d.%d a%d.%d n%02d.%02d.%02d e%08x",
+ hw->aq.fw_maj_ver, hw->aq.fw_min_ver,
+ hw->aq.api_maj_ver, hw->aq.api_min_ver,
+ (hw->nvm.version & I40E_NVM_VERSION_HI_MASK)
+ >> I40E_NVM_VERSION_HI_SHIFT,
+ (hw->nvm.version & I40E_NVM_VERSION_MID_MASK)
+ >> I40E_NVM_VERSION_MID_SHIFT,
+ (hw->nvm.version & I40E_NVM_VERSION_LO_MASK)
+ >> I40E_NVM_VERSION_LO_SHIFT,
+ hw->nvm.eetrack);
+
+ return buf;
+}
+
+/**
+ * i40e_netdev_to_pf: Retrieve the PF struct for given netdev
+ * @netdev: the corresponding netdev
+ *
+ * Return the PF struct for the given netdev
+ **/
+static inline struct i40e_pf *i40e_netdev_to_pf(struct net_device *netdev)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+
+ return vsi->back;
+}
+
+static inline void i40e_vsi_setup_irqhandler(struct i40e_vsi *vsi,
+ irqreturn_t (*irq_handler)(int, void *))
+{
+ vsi->irq_handler = irq_handler;
+}
+
+/**
+ * i40e_rx_is_programming_status - check for programming status descriptor
+ * @qw: the first quad word of the program status descriptor
+ *
+ * The value of in the descriptor length field indicate if this
+ * is a programming status descriptor for flow director or FCoE
+ * by the value of I40E_RX_PROG_STATUS_DESC_LENGTH, otherwise
+ * it is a packet descriptor.
+ **/
+static inline bool i40e_rx_is_programming_status(u64 qw)
+{
+ return I40E_RX_PROG_STATUS_DESC_LENGTH ==
+ (qw >> I40E_RX_PROG_STATUS_DESC_LENGTH_SHIFT);
+}
+
+/* needed by i40e_ethtool.c */
+int i40e_up(struct i40e_vsi *vsi);
+void i40e_down(struct i40e_vsi *vsi);
+extern const char i40e_driver_name[];
+extern const char i40e_driver_version_str[];
+void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags);
+void i40e_update_stats(struct i40e_vsi *vsi);
+void i40e_update_eth_stats(struct i40e_vsi *vsi);
+struct rtnl_link_stats64 *i40e_get_vsi_stats_struct(struct i40e_vsi *vsi);
+int i40e_fetch_switch_configuration(struct i40e_pf *pf,
+ bool printconfig);
+
+/* needed by i40e_main.c */
+void i40e_add_fdir_filter(struct i40e_fdir_data fdir_data,
+ struct i40e_ring *tx_ring);
+void i40e_add_remove_filter(struct i40e_fdir_data fdir_data,
+ struct i40e_ring *tx_ring);
+void i40e_update_fdir_filter(struct i40e_fdir_data fdir_data,
+ struct i40e_ring *tx_ring);
+int i40e_program_fdir_filter(struct i40e_fdir_data *fdir_data,
+ struct i40e_pf *pf, bool add);
+
+void i40e_set_ethtool_ops(struct net_device *netdev);
+struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi,
+ u8 *macaddr, s16 vlan,
+ bool is_vf, bool is_netdev);
+void i40e_del_filter(struct i40e_vsi *vsi, u8 *macaddr, s16 vlan,
+ bool is_vf, bool is_netdev);
+int i40e_sync_vsi_filters(struct i40e_vsi *vsi);
+struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type,
+ u16 uplink, u32 param1);
+int i40e_vsi_release(struct i40e_vsi *vsi);
+struct i40e_vsi *i40e_vsi_lookup(struct i40e_pf *pf, enum i40e_vsi_type type,
+ struct i40e_vsi *start_vsi);
+struct i40e_veb *i40e_veb_setup(struct i40e_pf *pf, u16 flags, u16 uplink_seid,
+ u16 downlink_seid, u8 enabled_tc);
+void i40e_veb_release(struct i40e_veb *veb);
+
+i40e_status i40e_vsi_add_pvid(struct i40e_vsi *vsi, u16 vid);
+void i40e_vsi_remove_pvid(struct i40e_vsi *vsi);
+void i40e_vsi_reset_stats(struct i40e_vsi *vsi);
+void i40e_pf_reset_stats(struct i40e_pf *pf);
+#ifdef CONFIG_DEBUG_FS
+void i40e_dbg_pf_init(struct i40e_pf *pf);
+void i40e_dbg_pf_exit(struct i40e_pf *pf);
+void i40e_dbg_init(void);
+void i40e_dbg_exit(void);
+#else
+static inline void i40e_dbg_pf_init(struct i40e_pf *pf) {}
+static inline void i40e_dbg_pf_exit(struct i40e_pf *pf) {}
+static inline void i40e_dbg_init(void) {}
+static inline void i40e_dbg_exit(void) {}
+#endif /* CONFIG_DEBUG_FS*/
+void i40e_irq_dynamic_enable(struct i40e_vsi *vsi, int vector);
+int i40e_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd);
+void i40e_vlan_stripping_disable(struct i40e_vsi *vsi);
+int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid);
+int i40e_vsi_kill_vlan(struct i40e_vsi *vsi, s16 vid);
+struct i40e_mac_filter *i40e_put_mac_in_vlan(struct i40e_vsi *vsi, u8 *macaddr,
+ bool is_vf, bool is_netdev);
+bool i40e_is_vsi_in_vlan(struct i40e_vsi *vsi);
+struct i40e_mac_filter *i40e_find_mac(struct i40e_vsi *vsi, u8 *macaddr,
+ bool is_vf, bool is_netdev);
+void i40e_vlan_stripping_enable(struct i40e_vsi *vsi);
+
+#endif /* _I40E_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
new file mode 100644
index 0000000..0c524fa
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
@@ -0,0 +1,983 @@
+/*******************************************************************************
+ *
+ * Intel Ethernet Controller XL710 Family Linux Driver
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ ******************************************************************************/
+
+#include "i40e_status.h"
+#include "i40e_type.h"
+#include "i40e_register.h"
+#include "i40e_adminq.h"
+#include "i40e_prototype.h"
+
+/**
+ * i40e_adminq_init_regs - Initialize AdminQ registers
+ * @hw: pointer to the hardware structure
+ *
+ * This assumes the alloc_asq and alloc_arq functions have already been called
+ **/
+static void i40e_adminq_init_regs(struct i40e_hw *hw)
+{
+ /* set head and tail registers in our local struct */
+ if (hw->mac.type == I40E_MAC_VF) {
+ hw->aq.asq.tail = I40E_VF_ATQT1;
+ hw->aq.asq.head = I40E_VF_ATQH1;
+ hw->aq.arq.tail = I40E_VF_ARQT1;
+ hw->aq.arq.head = I40E_VF_ARQH1;
+ } else {
+ hw->aq.asq.tail = I40E_PF_ATQT;
+ hw->aq.asq.head = I40E_PF_ATQH;
+ hw->aq.arq.tail = I40E_PF_ARQT;
+ hw->aq.arq.head = I40E_PF_ARQH;
+ }
+}
+
+/**
+ * i40e_alloc_adminq_asq_ring - Allocate Admin Queue send rings
+ * @hw: pointer to the hardware structure
+ **/
+static i40e_status i40e_alloc_adminq_asq_ring(struct i40e_hw *hw)
+{
+ i40e_status ret_code;
+ struct i40e_virt_mem mem;
+
+ ret_code = i40e_allocate_dma_mem(hw, &hw->aq.asq_mem,
+ i40e_mem_atq_ring,
+ (hw->aq.num_asq_entries *
+ sizeof(struct i40e_aq_desc)),
+ I40E_ADMINQ_DESC_ALIGNMENT);
+ if (ret_code)
+ return ret_code;
+
+ hw->aq.asq.desc = hw->aq.asq_mem.va;
+ hw->aq.asq.dma_addr = hw->aq.asq_mem.pa;
+
+ ret_code = i40e_allocate_virt_mem(hw, &mem,
+ (hw->aq.num_asq_entries *
+ sizeof(struct i40e_asq_cmd_details)));
+ if (ret_code) {
+ i40e_free_dma_mem(hw, &hw->aq.asq_mem);
+ hw->aq.asq_mem.va = NULL;
+ hw->aq.asq_mem.pa = 0;
+ return ret_code;
+ }
+
+ hw->aq.asq.details = mem.va;
+
+ return ret_code;
+}
+
+/**
+ * i40e_alloc_adminq_arq_ring - Allocate Admin Queue receive rings
+ * @hw: pointer to the hardware structure
+ **/
+static i40e_status i40e_alloc_adminq_arq_ring(struct i40e_hw *hw)
+{
+ i40e_status ret_code;
+
+ ret_code = i40e_allocate_dma_mem(hw, &hw->aq.arq_mem,
+ i40e_mem_arq_ring,
+ (hw->aq.num_arq_entries *
+ sizeof(struct i40e_aq_desc)),
+ I40E_ADMINQ_DESC_ALIGNMENT);
+ if (ret_code)
+ return ret_code;
+
+ hw->aq.arq.desc = hw->aq.arq_mem.va;
+ hw->aq.arq.dma_addr = hw->aq.arq_mem.pa;
+
+ return ret_code;
+}
+
+/**
+ * i40e_free_adminq_asq - Free Admin Queue send rings
+ * @hw: pointer to the hardware structure
+ *
+ * This assumes the posted send buffers have already been cleaned
+ * and de-allocated
+ **/
+static void i40e_free_adminq_asq(struct i40e_hw *hw)
+{
+ struct i40e_virt_mem mem;
+
+ i40e_free_dma_mem(hw, &hw->aq.asq_mem);
+ hw->aq.asq_mem.va = NULL;
+ hw->aq.asq_mem.pa = 0;
+ mem.va = hw->aq.asq.details;
+ i40e_free_virt_mem(hw, &mem);
+ hw->aq.asq.details = NULL;
+}
+
+/**
+ * i40e_free_adminq_arq - Free Admin Queue receive rings
+ * @hw: pointer to the hardware structure
+ *
+ * This assumes the posted receive buffers have already been cleaned
+ * and de-allocated
+ **/
+static void i40e_free_adminq_arq(struct i40e_hw *hw)
+{
+ i40e_free_dma_mem(hw, &hw->aq.arq_mem);
+ hw->aq.arq_mem.va = NULL;
+ hw->aq.arq_mem.pa = 0;
+}
+
+/**
+ * i40e_alloc_arq_bufs - Allocate pre-posted buffers for the receive queue
+ * @hw: pointer to the hardware structure
+ **/
+static i40e_status i40e_alloc_arq_bufs(struct i40e_hw *hw)
+{
+ i40e_status ret_code;
+ struct i40e_aq_desc *desc;
+ struct i40e_virt_mem mem;
+ struct i40e_dma_mem *bi;
+ int i;
+
+ /* We'll be allocating the buffer info memory first, then we can
+ * allocate the mapped buffers for the event processing
+ */
+
+ /* buffer_info structures do not need alignment */
+ ret_code = i40e_allocate_virt_mem(hw, &mem, (hw->aq.num_arq_entries *
+ sizeof(struct i40e_dma_mem)));
+ if (ret_code)
+ goto alloc_arq_bufs;
+ hw->aq.arq.r.arq_bi = (struct i40e_dma_mem *)mem.va;
+
+ /* allocate the mapped buffers */
+ for (i = 0; i < hw->aq.num_arq_entries; i++) {
+ bi = &hw->aq.arq.r.arq_bi[i];
+ ret_code = i40e_allocate_dma_mem(hw, bi,
+ i40e_mem_arq_buf,
+ hw->aq.arq_buf_size,
+ I40E_ADMINQ_DESC_ALIGNMENT);
+ if (ret_code)
+ goto unwind_alloc_arq_bufs;
+
+ /* now configure the descriptors for use */
+ desc = I40E_ADMINQ_DESC(hw->aq.arq, i);
+
+ desc->flags = cpu_to_le16(I40E_AQ_FLAG_BUF);
+ if (hw->aq.arq_buf_size > I40E_AQ_LARGE_BUF)
+ desc->flags |= cpu_to_le16(I40E_AQ_FLAG_LB);
+ desc->opcode = 0;
+ /* This is in accordance with Admin queue design, there is no
+ * register for buffer size configuration
+ */
+ desc->datalen = cpu_to_le16((u16)bi->size);
+ desc->retval = 0;
+ desc->cookie_high = 0;
+ desc->cookie_low = 0;
+ desc->params.external.addr_high =
+ cpu_to_le32(upper_32_bits(bi->pa));
+ desc->params.external.addr_low =
+ cpu_to_le32(lower_32_bits(bi->pa));
+ desc->params.external.param0 = 0;
+ desc->params.external.param1 = 0;
+ }
+
+alloc_arq_bufs:
+ return ret_code;
+
+unwind_alloc_arq_bufs:
+ /* don't try to free the one that failed... */
+ i--;
+ for (; i >= 0; i--)
+ i40e_free_dma_mem(hw, &hw->aq.arq.r.arq_bi[i]);
+ mem.va = hw->aq.arq.r.arq_bi;
+ i40e_free_virt_mem(hw, &mem);
+
+ return ret_code;
+}
+
+/**
+ * i40e_alloc_asq_bufs - Allocate empty buffer structs for the send queue
+ * @hw: pointer to the hardware structure
+ **/
+static i40e_status i40e_alloc_asq_bufs(struct i40e_hw *hw)
+{
+ i40e_status ret_code;
+ struct i40e_virt_mem mem;
+ struct i40e_dma_mem *bi;
+ int i;
+
+ /* No mapped memory needed yet, just the buffer info structures */
+ ret_code = i40e_allocate_virt_mem(hw, &mem, (hw->aq.num_asq_entries *
+ sizeof(struct i40e_dma_mem)));
+ if (ret_code)
+ goto alloc_asq_bufs;
+ hw->aq.asq.r.asq_bi = (struct i40e_dma_mem *)mem.va;
+
+ /* allocate the mapped buffers */
+ for (i = 0; i < hw->aq.num_asq_entries; i++) {
+ bi = &hw->aq.asq.r.asq_bi[i];
+ ret_code = i40e_allocate_dma_mem(hw, bi,
+ i40e_mem_asq_buf,
+ hw->aq.asq_buf_size,
+ I40E_ADMINQ_DESC_ALIGNMENT);
+ if (ret_code)
+ goto unwind_alloc_asq_bufs;
+ }
+alloc_asq_bufs:
+ return ret_code;
+
+unwind_alloc_asq_bufs:
+ /* don't try to free the one that failed... */
+ i--;
+ for (; i >= 0; i--)
+ i40e_free_dma_mem(hw, &hw->aq.asq.r.asq_bi[i]);
+ mem.va = hw->aq.asq.r.asq_bi;
+ i40e_free_virt_mem(hw, &mem);
+
+ return ret_code;
+}
+
+/**
+ * i40e_free_arq_bufs - Free receive queue buffer info elements
+ * @hw: pointer to the hardware structure
+ **/
+static void i40e_free_arq_bufs(struct i40e_hw *hw)
+{
+ struct i40e_virt_mem mem;
+ int i;
+
+ for (i = 0; i < hw->aq.num_arq_entries; i++)
+ i40e_free_dma_mem(hw, &hw->aq.arq.r.arq_bi[i]);
+
+ mem.va = hw->aq.arq.r.arq_bi;
+ i40e_free_virt_mem(hw, &mem);
+}
+
+/**
+ * i40e_free_asq_bufs - Free send queue buffer info elements
+ * @hw: pointer to the hardware structure
+ **/
+static void i40e_free_asq_bufs(struct i40e_hw *hw)
+{
+ struct i40e_virt_mem mem;
+ int i;
+
+ /* only unmap if the address is non-NULL */
+ for (i = 0; i < hw->aq.num_asq_entries; i++)
+ if (hw->aq.asq.r.asq_bi[i].pa)
+ i40e_free_dma_mem(hw, &hw->aq.asq.r.asq_bi[i]);
+
+ /* now free the buffer info list */
+ mem.va = hw->aq.asq.r.asq_bi;
+ i40e_free_virt_mem(hw, &mem);
+}
+
+/**
+ * i40e_config_asq_regs - configure ASQ registers
+ * @hw: pointer to the hardware structure
+ *
+ * Configure base address and length registers for the transmit queue
+ **/
+static void i40e_config_asq_regs(struct i40e_hw *hw)
+{
+ if (hw->mac.type == I40E_MAC_VF) {
+ /* configure the transmit queue */
+ wr32(hw, I40E_VF_ATQBAH1, upper_32_bits(hw->aq.asq.dma_addr));
+ wr32(hw, I40E_VF_ATQBAL1, lower_32_bits(hw->aq.asq.dma_addr));
+ wr32(hw, I40E_VF_ATQLEN1, (hw->aq.num_asq_entries |
+ I40E_VF_ATQLEN1_ATQENABLE_MASK));
+ } else {
+ /* configure the transmit queue */
+ wr32(hw, I40E_PF_ATQBAH, upper_32_bits(hw->aq.asq.dma_addr));
+ wr32(hw, I40E_PF_ATQBAL, lower_32_bits(hw->aq.asq.dma_addr));
+ wr32(hw, I40E_PF_ATQLEN, (hw->aq.num_asq_entries |
+ I40E_PF_ATQLEN_ATQENABLE_MASK));
+ }
+}
+
+/**
+ * i40e_config_arq_regs - ARQ register configuration
+ * @hw: pointer to the hardware structure
+ *
+ * Configure base address and length registers for the receive (event queue)
+ **/
+static void i40e_config_arq_regs(struct i40e_hw *hw)
+{
+ if (hw->mac.type == I40E_MAC_VF) {
+ /* configure the receive queue */
+ wr32(hw, I40E_VF_ARQBAH1, upper_32_bits(hw->aq.arq.dma_addr));
+ wr32(hw, I40E_VF_ARQBAL1, lower_32_bits(hw->aq.arq.dma_addr));
+ wr32(hw, I40E_VF_ARQLEN1, (hw->aq.num_arq_entries |
+ I40E_VF_ARQLEN1_ARQENABLE_MASK));
+ } else {
+ /* configure the receive queue */
+ wr32(hw, I40E_PF_ARQBAH, upper_32_bits(hw->aq.arq.dma_addr));
+ wr32(hw, I40E_PF_ARQBAL, lower_32_bits(hw->aq.arq.dma_addr));
+ wr32(hw, I40E_PF_ARQLEN, (hw->aq.num_arq_entries |
+ I40E_PF_ARQLEN_ARQENABLE_MASK));
+ }
+
+ /* Update tail in the HW to post pre-allocated buffers */
+ wr32(hw, hw->aq.arq.tail, hw->aq.num_arq_entries - 1);
+}
+
+/**
+ * i40e_init_asq - main initialization routine for ASQ
+ * @hw: pointer to the hardware structure
+ *
+ * This is the main initialization routine for the Admin Send Queue
+ * Prior to calling this function, drivers *MUST* set the following fields
+ * in the hw->aq structure:
+ * - hw->aq.num_asq_entries
+ * - hw->aq.arq_buf_size
+ *
+ * Do *NOT* hold the lock when calling this as the memory allocation routines
+ * called are not going to be atomic context safe
+ **/
+static i40e_status i40e_init_asq(struct i40e_hw *hw)
+{
+ i40e_status ret_code = 0;
+
+ if (hw->aq.asq.count > 0) {
+ /* queue already initialized */
+ ret_code = I40E_ERR_NOT_READY;
+ goto init_adminq_exit;
+ }
+
+ /* verify input for valid configuration */
+ if ((hw->aq.num_asq_entries == 0) ||
+ (hw->aq.asq_buf_size == 0)) {
+ ret_code = I40E_ERR_CONFIG;
+ goto init_adminq_exit;
+ }
+
+ hw->aq.asq.next_to_use = 0;
+ hw->aq.asq.next_to_clean = 0;
+ hw->aq.asq.count = hw->aq.num_asq_entries;
+
+ /* allocate the ring memory */
+ ret_code = i40e_alloc_adminq_asq_ring(hw);
+ if (ret_code)
+ goto init_adminq_exit;
+
+ /* allocate buffers in the rings */
+ ret_code = i40e_alloc_asq_bufs(hw);
+ if (ret_code)
+ goto init_adminq_free_rings;
+
+ /* initialize base registers */
+ i40e_config_asq_regs(hw);
+
+ /* success! */
+ goto init_adminq_exit;
+
+init_adminq_free_rings:
+ i40e_free_adminq_asq(hw);
+
+init_adminq_exit:
+ return ret_code;
+}
+
+/**
+ * i40e_init_arq - initialize ARQ
+ * @hw: pointer to the hardware structure
+ *
+ * The main initialization routine for the Admin Receive (Event) Queue.
+ * Prior to calling this function, drivers *MUST* set the following fields
+ * in the hw->aq structure:
+ * - hw->aq.num_asq_entries
+ * - hw->aq.arq_buf_size
+ *
+ * Do *NOT* hold the lock when calling this as the memory allocation routines
+ * called are not going to be atomic context safe
+ **/
+static i40e_status i40e_init_arq(struct i40e_hw *hw)
+{
+ i40e_status ret_code = 0;
+
+ if (hw->aq.arq.count > 0) {
+ /* queue already initialized */
+ ret_code = I40E_ERR_NOT_READY;
+ goto init_adminq_exit;
+ }
+
+ /* verify input for valid configuration */
+ if ((hw->aq.num_arq_entries == 0) ||
+ (hw->aq.arq_buf_size == 0)) {
+ ret_code = I40E_ERR_CONFIG;
+ goto init_adminq_exit;
+ }
+
+ hw->aq.arq.next_to_use = 0;
+ hw->aq.arq.next_to_clean = 0;
+ hw->aq.arq.count = hw->aq.num_arq_entries;
+
+ /* allocate the ring memory */
+ ret_code = i40e_alloc_adminq_arq_ring(hw);
+ if (ret_code)
+ goto init_adminq_exit;
+
+ /* allocate buffers in the rings */
+ ret_code = i40e_alloc_arq_bufs(hw);
+ if (ret_code)
+ goto init_adminq_free_rings;
+
+ /* initialize base registers */
+ i40e_config_arq_regs(hw);
+
+ /* success! */
+ goto init_adminq_exit;
+
+init_adminq_free_rings:
+ i40e_free_adminq_arq(hw);
+
+init_adminq_exit:
+ return ret_code;
+}
+
+/**
+ * i40e_shutdown_asq - shutdown the ASQ
+ * @hw: pointer to the hardware structure
+ *
+ * The main shutdown routine for the Admin Send Queue
+ **/
+static i40e_status i40e_shutdown_asq(struct i40e_hw *hw)
+{
+ i40e_status ret_code = 0;
+
+ if (hw->aq.asq.count == 0)
+ return I40E_ERR_NOT_READY;
+
+ /* Stop firmware AdminQ processing */
+ if (hw->mac.type == I40E_MAC_VF)
+ wr32(hw, I40E_VF_ATQLEN1, 0);
+ else
+ wr32(hw, I40E_PF_ATQLEN, 0);
+
+ /* make sure lock is available */
+ mutex_lock(&hw->aq.asq_mutex);
+
+ hw->aq.asq.count = 0; /* to indicate uninitialized queue */
+
+ /* free ring buffers */
+ i40e_free_asq_bufs(hw);
+ /* free the ring descriptors */
+ i40e_free_adminq_asq(hw);
+
+ mutex_unlock(&hw->aq.asq_mutex);
+
+ return ret_code;
+}
+
+/**
+ * i40e_shutdown_arq - shutdown ARQ
+ * @hw: pointer to the hardware structure
+ *
+ * The main shutdown routine for the Admin Receive Queue
+ **/
+static i40e_status i40e_shutdown_arq(struct i40e_hw *hw)
+{
+ i40e_status ret_code = 0;
+
+ if (hw->aq.arq.count == 0)
+ return I40E_ERR_NOT_READY;
+
+ /* Stop firmware AdminQ processing */
+ if (hw->mac.type == I40E_MAC_VF)
+ wr32(hw, I40E_VF_ARQLEN1, 0);
+ else
+ wr32(hw, I40E_PF_ARQLEN, 0);
+
+ /* make sure lock is available */
+ mutex_lock(&hw->aq.arq_mutex);
+
+ hw->aq.arq.count = 0; /* to indicate uninitialized queue */
+
+ /* free ring buffers */
+ i40e_free_arq_bufs(hw);
+ /* free the ring descriptors */
+ i40e_free_adminq_arq(hw);
+
+ mutex_unlock(&hw->aq.arq_mutex);
+
+ return ret_code;
+}
+
+/**
+ * i40e_init_adminq - main initialization routine for Admin Queue
+ * @hw: pointer to the hardware structure
+ *
+ * Prior to calling this function, drivers *MUST* set the following fields
+ * in the hw->aq structure:
+ * - hw->aq.num_asq_entries
+ * - hw->aq.num_arq_entries
+ * - hw->aq.arq_buf_size
+ * - hw->aq.asq_buf_size
+ **/
+i40e_status i40e_init_adminq(struct i40e_hw *hw)
+{
+ u16 eetrack_lo, eetrack_hi;
+ i40e_status ret_code;
+
+ /* verify input for valid configuration */
+ if ((hw->aq.num_arq_entries == 0) ||
+ (hw->aq.num_asq_entries == 0) ||
+ (hw->aq.arq_buf_size == 0) ||
+ (hw->aq.asq_buf_size == 0)) {
+ ret_code = I40E_ERR_CONFIG;
+ goto init_adminq_exit;
+ }
+
+ /* initialize locks */
+ mutex_init(&hw->aq.asq_mutex);
+ mutex_init(&hw->aq.arq_mutex);
+
+ /* Set up register offsets */
+ i40e_adminq_init_regs(hw);
+
+ /* allocate the ASQ */
+ ret_code = i40e_init_asq(hw);
+ if (ret_code)
+ goto init_adminq_destroy_locks;
+
+ /* allocate the ARQ */
+ ret_code = i40e_init_arq(hw);
+ if (ret_code)
+ goto init_adminq_free_asq;
+
+ ret_code = i40e_aq_get_firmware_version(hw,
+ &hw->aq.fw_maj_ver, &hw->aq.fw_min_ver,
+ &hw->aq.api_maj_ver, &hw->aq.api_min_ver,
+ NULL);
+ if (ret_code)
+ goto init_adminq_free_arq;
+
+ if (hw->aq.api_maj_ver != I40E_FW_API_VERSION_MAJOR ||
+ hw->aq.api_min_ver != I40E_FW_API_VERSION_MINOR) {
+ ret_code = I40E_ERR_FIRMWARE_API_VERSION;
+ goto init_adminq_free_arq;
+ }
+ i40e_read_nvm_word(hw, I40E_SR_NVM_IMAGE_VERSION, &hw->nvm.version);
+ i40e_read_nvm_word(hw, I40E_SR_NVM_EETRACK_LO, &eetrack_lo);
+ i40e_read_nvm_word(hw, I40E_SR_NVM_EETRACK_HI, &eetrack_hi);
+ hw->nvm.eetrack = (eetrack_hi << 16) | eetrack_lo;
+
+ ret_code = i40e_aq_set_hmc_resource_profile(hw,
+ I40E_HMC_PROFILE_DEFAULT,
+ 0,
+ NULL);
+ ret_code = 0;
+
+ /* success! */
+ goto init_adminq_exit;
+
+init_adminq_free_arq:
+ i40e_shutdown_arq(hw);
+init_adminq_free_asq:
+ i40e_shutdown_asq(hw);
+init_adminq_destroy_locks:
+
+init_adminq_exit:
+ return ret_code;
+}
+
+/**
+ * i40e_shutdown_adminq - shutdown routine for the Admin Queue
+ * @hw: pointer to the hardware structure
+ **/
+i40e_status i40e_shutdown_adminq(struct i40e_hw *hw)
+{
+ i40e_status ret_code = 0;
+
+ i40e_shutdown_asq(hw);
+ i40e_shutdown_arq(hw);
+
+ /* destroy the locks */
+
+ return ret_code;
+}
+
+/**
+ * i40e_clean_asq - cleans Admin send queue
+ * @asq: pointer to the adminq send ring
+ *
+ * returns the number of free desc
+ **/
+static u16 i40e_clean_asq(struct i40e_hw *hw)
+{
+ struct i40e_adminq_ring *asq = &(hw->aq.asq);
+ struct i40e_asq_cmd_details *details;
+ u16 ntc = asq->next_to_clean;
+ struct i40e_aq_desc desc_cb;
+ struct i40e_aq_desc *desc;
+
+ desc = I40E_ADMINQ_DESC(*asq, ntc);
+ details = I40E_ADMINQ_DETAILS(*asq, ntc);
+ while (rd32(hw, hw->aq.asq.head) != ntc) {
+ if (details->callback) {
+ I40E_ADMINQ_CALLBACK cb_func =
+ (I40E_ADMINQ_CALLBACK)details->callback;
+ desc_cb = *desc;
+ cb_func(hw, &desc_cb);
+ }
+ memset((void *)desc, 0, sizeof(struct i40e_aq_desc));
+ memset((void *)details, 0,
+ sizeof(struct i40e_asq_cmd_details));
+ ntc++;
+ if (ntc == asq->count)
+ ntc = 0;
+ desc = I40E_ADMINQ_DESC(*asq, ntc);
+ details = I40E_ADMINQ_DETAILS(*asq, ntc);
+ }
+
+ asq->next_to_clean = ntc;
+
+ return I40E_DESC_UNUSED(asq);
+}
+
+/**
+ * i40e_asq_done - check if FW has processed the Admin Send Queue
+ * @hw: pointer to the hw struct
+ *
+ * Returns true if the firmware has processed all descriptors on the
+ * admin send queue. Returns false if there are still requests pending.
+ **/
+bool i40e_asq_done(struct i40e_hw *hw)
+{
+ /* AQ designers suggest use of head for better
+ * timing reliability than DD bit
+ */
+ return (rd32(hw, hw->aq.asq.head) == hw->aq.asq.next_to_use);
+
+}
+
+/**
+ * i40e_asq_send_command - send command to Admin Queue
+ * @hw: pointer to the hw struct
+ * @desc: prefilled descriptor describing the command (non DMA mem)
+ * @buff: buffer to use for indirect commands
+ * @buff_size: size of buffer for indirect commands
+ * @opaque: pointer to info to be used in async cleanup
+ *
+ * This is the main send command driver routine for the Admin Queue send
+ * queue. It runs the queue, cleans the queue, etc
+ **/
+i40e_status i40e_asq_send_command(struct i40e_hw *hw,
+ struct i40e_aq_desc *desc,
+ void *buff, /* can be NULL */
+ u16 buff_size,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ i40e_status status = 0;
+ struct i40e_dma_mem *dma_buff = NULL;
+ struct i40e_asq_cmd_details *details;
+ struct i40e_aq_desc *desc_on_ring;
+ bool cmd_completed = false;
+ u16 retval = 0;
+
+ if (hw->aq.asq.count == 0) {
+ i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
+ "AQTX: Admin queue not initialized.\n");
+ status = I40E_ERR_QUEUE_EMPTY;
+ goto asq_send_command_exit;
+ }
+
+ details = I40E_ADMINQ_DETAILS(hw->aq.asq, hw->aq.asq.next_to_use);
+ if (cmd_details) {
+ memcpy(details, cmd_details,
+ sizeof(struct i40e_asq_cmd_details));
+
+ /* If the cmd_details are defined copy the cookie. The
+ * cpu_to_le32 is not needed here because the data is ignored
+ * by the FW, only used by the driver
+ */
+ if (details->cookie) {
+ desc->cookie_high =
+ cpu_to_le32(upper_32_bits(details->cookie));
+ desc->cookie_low =
+ cpu_to_le32(lower_32_bits(details->cookie));
+ }
+ } else {
+ memset(details, 0, sizeof(struct i40e_asq_cmd_details));
+ }
+
+ /* clear requested flags and then set additional flags if defined */
+ desc->flags &= ~cpu_to_le16(details->flags_dis);
+ desc->flags |= cpu_to_le16(details->flags_ena);
+
+ mutex_lock(&hw->aq.asq_mutex);
+
+ if (buff_size > hw->aq.asq_buf_size) {
+ i40e_debug(hw,
+ I40E_DEBUG_AQ_MESSAGE,
+ "AQTX: Invalid buffer size: %d.\n",
+ buff_size);
+ status = I40E_ERR_INVALID_SIZE;
+ goto asq_send_command_error;
+ }
+
+ if (details->postpone && !details->async) {
+ i40e_debug(hw,
+ I40E_DEBUG_AQ_MESSAGE,
+ "AQTX: Async flag not set along with postpone flag");
+ status = I40E_ERR_PARAM;
+ goto asq_send_command_error;
+ }
+
+ /* call clean and check queue available function to reclaim the
+ * descriptors that were processed by FW, the function returns the
+ * number of desc available
+ */
+ /* the clean function called here could be called in a separate thread
+ * in case of asynchronous completions
+ */
+ if (i40e_clean_asq(hw) == 0) {
+ i40e_debug(hw,
+ I40E_DEBUG_AQ_MESSAGE,
+ "AQTX: Error queue is full.\n");
+ status = I40E_ERR_ADMIN_QUEUE_FULL;
+ goto asq_send_command_error;
+ }
+
+ /* initialize the temp desc pointer with the right desc */
+ desc_on_ring = I40E_ADMINQ_DESC(hw->aq.asq, hw->aq.asq.next_to_use);
+
+ /* if the desc is available copy the temp desc to the right place */
+ memcpy(desc_on_ring, desc, sizeof(struct i40e_aq_desc));
+
+ /* if buff is not NULL assume indirect command */
+ if (buff != NULL) {
+ dma_buff = &(hw->aq.asq.r.asq_bi[hw->aq.asq.next_to_use]);
+ /* copy the user buff into the respective DMA buff */
+ memcpy(dma_buff->va, buff, buff_size);
+ desc_on_ring->datalen = cpu_to_le16(buff_size);
+
+ /* Update the address values in the desc with the pa value
+ * for respective buffer
+ */
+ desc_on_ring->params.external.addr_high =
+ cpu_to_le32(upper_32_bits(dma_buff->pa));
+ desc_on_ring->params.external.addr_low =
+ cpu_to_le32(lower_32_bits(dma_buff->pa));
+ }
+
+ /* bump the tail */
+ i40e_debug_aq(hw, I40E_DEBUG_AQ_COMMAND, (void *)desc_on_ring, buff);
+ (hw->aq.asq.next_to_use)++;
+ if (hw->aq.asq.next_to_use == hw->aq.asq.count)
+ hw->aq.asq.next_to_use = 0;
+ if (!details->postpone)
+ wr32(hw, hw->aq.asq.tail, hw->aq.asq.next_to_use);
+
+ /* if cmd_details are not defined or async flag is not set,
+ * we need to wait for desc write back
+ */
+ if (!details->async && !details->postpone) {
+ u32 total_delay = 0;
+ u32 delay_len = 10;
+
+ do {
+ /* AQ designers suggest use of head for better
+ * timing reliability than DD bit
+ */
+ if (i40e_asq_done(hw))
+ break;
+ /* ugh! delay while spin_lock */
+ udelay(delay_len);
+ total_delay += delay_len;
+ } while (total_delay < I40E_ASQ_CMD_TIMEOUT);
+ }
+
+ /* if ready, copy the desc back to temp */
+ if (i40e_asq_done(hw)) {
+ memcpy(desc, desc_on_ring, sizeof(struct i40e_aq_desc));
+ if (buff != NULL)
+ memcpy(buff, dma_buff->va, buff_size);
+ retval = le16_to_cpu(desc->retval);
+ if (retval != 0) {
+ i40e_debug(hw,
+ I40E_DEBUG_AQ_MESSAGE,
+ "AQTX: Command completed with error 0x%X.\n",
+ retval);
+ /* strip off FW internal code */
+ retval &= 0xff;
+ }
+ cmd_completed = true;
+ if ((enum i40e_admin_queue_err)retval == I40E_AQ_RC_OK)
+ status = 0;
+ else
+ status = I40E_ERR_ADMIN_QUEUE_ERROR;
+ hw->aq.asq_last_status = (enum i40e_admin_queue_err)retval;
+ }
+
+ /* update the error if time out occurred */
+ if ((!cmd_completed) &&
+ (!details->async && !details->postpone)) {
+ i40e_debug(hw,
+ I40E_DEBUG_AQ_MESSAGE,
+ "AQTX: Writeback timeout.\n");
+ status = I40E_ERR_ADMIN_QUEUE_TIMEOUT;
+ }
+
+asq_send_command_error:
+ mutex_unlock(&hw->aq.asq_mutex);
+asq_send_command_exit:
+ return status;
+}
+
+/**
+ * i40e_fill_default_direct_cmd_desc - AQ descriptor helper function
+ * @desc: pointer to the temp descriptor (non DMA mem)
+ * @opcode: the opcode can be used to decide which flags to turn off or on
+ *
+ * Fill the desc with default values
+ **/
+void i40e_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc,
+ u16 opcode)
+{
+ /* zero out the desc */
+ memset((void *)desc, 0, sizeof(struct i40e_aq_desc));
+ desc->opcode = cpu_to_le16(opcode);
+ desc->flags = cpu_to_le16(I40E_AQ_FLAG_EI | I40E_AQ_FLAG_SI);
+}
+
+/**
+ * i40e_clean_arq_element
+ * @hw: pointer to the hw struct
+ * @e: event info from the receive descriptor, includes any buffers
+ * @pending: number of events that could be left to process
+ *
+ * This function cleans one Admin Receive Queue element and returns
+ * the contents through e. It can also return how many events are
+ * left to process through 'pending'
+ **/
+i40e_status i40e_clean_arq_element(struct i40e_hw *hw,
+ struct i40e_arq_event_info *e,
+ u16 *pending)
+{
+ i40e_status ret_code = 0;
+ u16 ntc = hw->aq.arq.next_to_clean;
+ struct i40e_aq_desc *desc;
+ struct i40e_dma_mem *bi;
+ u16 desc_idx;
+ u16 datalen;
+ u16 flags;
+ u16 ntu;
+
+ /* take the lock before we start messing with the ring */
+ mutex_lock(&hw->aq.arq_mutex);
+
+ /* set next_to_use to head */
+ ntu = (rd32(hw, hw->aq.arq.head) & I40E_PF_ARQH_ARQH_MASK);
+ if (ntu == ntc) {
+ /* nothing to do - shouldn't need to update ring's values */
+ i40e_debug(hw,
+ I40E_DEBUG_AQ_MESSAGE,
+ "AQRX: Queue is empty.\n");
+ ret_code = I40E_ERR_ADMIN_QUEUE_NO_WORK;
+ goto clean_arq_element_out;
+ }
+
+ /* now clean the next descriptor */
+ desc = I40E_ADMINQ_DESC(hw->aq.arq, ntc);
+ desc_idx = ntc;
+ i40e_debug_aq(hw,
+ I40E_DEBUG_AQ_COMMAND,
+ (void *)desc,
+ hw->aq.arq.r.arq_bi[desc_idx].va);
+
+ flags = le16_to_cpu(desc->flags);
+ if (flags & I40E_AQ_FLAG_ERR) {
+ ret_code = I40E_ERR_ADMIN_QUEUE_ERROR;
+ hw->aq.arq_last_status =
+ (enum i40e_admin_queue_err)le16_to_cpu(desc->retval);
+ i40e_debug(hw,
+ I40E_DEBUG_AQ_MESSAGE,
+ "AQRX: Event received with error 0x%X.\n",
+ hw->aq.arq_last_status);
+ } else {
+ memcpy(&e->desc, desc, sizeof(struct i40e_aq_desc));
+ datalen = le16_to_cpu(desc->datalen);
+ e->msg_size = min(datalen, e->msg_size);
+ if (e->msg_buf != NULL && (e->msg_size != 0))
+ memcpy(e->msg_buf, hw->aq.arq.r.arq_bi[desc_idx].va,
+ e->msg_size);
+ }
+
+ /* Restore the original datalen and buffer address in the desc,
+ * FW updates datalen to indicate the event message
+ * size
+ */
+ bi = &hw->aq.arq.r.arq_bi[ntc];
+ desc->datalen = cpu_to_le16((u16)bi->size);
+ desc->params.external.addr_high = cpu_to_le32(upper_32_bits(bi->pa));
+ desc->params.external.addr_low = cpu_to_le32(lower_32_bits(bi->pa));
+
+ /* set tail = the last cleaned desc index. */
+ wr32(hw, hw->aq.arq.tail, ntc);
+ /* ntc is updated to tail + 1 */
+ ntc++;
+ if (ntc == hw->aq.num_arq_entries)
+ ntc = 0;
+ hw->aq.arq.next_to_clean = ntc;
+ hw->aq.arq.next_to_use = ntu;
+
+clean_arq_element_out:
+ /* Set pending if needed, unlock and return */
+ if (pending != NULL)
+ *pending = (ntc > ntu ? hw->aq.arq.count : 0) + (ntu - ntc);
+ mutex_unlock(&hw->aq.arq_mutex);
+
+ return ret_code;
+}
+
+void i40e_resume_aq(struct i40e_hw *hw)
+{
+ u32 reg = 0;
+
+ /* Registers are reset after PF reset */
+ hw->aq.asq.next_to_use = 0;
+ hw->aq.asq.next_to_clean = 0;
+
+ i40e_config_asq_regs(hw);
+ reg = hw->aq.num_asq_entries;
+
+ if (hw->mac.type == I40E_MAC_VF) {
+ reg |= I40E_VF_ATQLEN_ATQENABLE_MASK;
+ wr32(hw, I40E_VF_ATQLEN1, reg);
+ } else {
+ reg |= I40E_PF_ATQLEN_ATQENABLE_MASK;
+ wr32(hw, I40E_PF_ATQLEN, reg);
+ }
+
+ hw->aq.arq.next_to_use = 0;
+ hw->aq.arq.next_to_clean = 0;
+
+ i40e_config_arq_regs(hw);
+ reg = hw->aq.num_arq_entries;
+
+ if (hw->mac.type == I40E_MAC_VF) {
+ reg |= I40E_VF_ATQLEN_ATQENABLE_MASK;
+ wr32(hw, I40E_VF_ARQLEN1, reg);
+ } else {
+ reg |= I40E_PF_ATQLEN_ATQENABLE_MASK;
+ wr32(hw, I40E_PF_ARQLEN, reg);
+ }
+}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.h b/drivers/net/ethernet/intel/i40e/i40e_adminq.h
new file mode 100644
index 0000000..22e5ed6
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.h
@@ -0,0 +1,112 @@
+/*******************************************************************************
+ *
+ * Intel Ethernet Controller XL710 Family Linux Driver
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ ******************************************************************************/
+
+#ifndef _I40E_ADMINQ_H_
+#define _I40E_ADMINQ_H_
+
+#include "i40e_osdep.h"
+#include "i40e_adminq_cmd.h"
+
+#define I40E_ADMINQ_DESC(R, i) \
+ (&(((struct i40e_aq_desc *)((R).desc))[i]))
+
+#define I40E_ADMINQ_DESC_ALIGNMENT 4096
+
+struct i40e_adminq_ring {
+ void *desc; /* Descriptor ring memory */
+ void *details; /* ASQ details */
+
+ union {
+ struct i40e_dma_mem *asq_bi;
+ struct i40e_dma_mem *arq_bi;
+ } r;
+
+ u64 dma_addr; /* Physical address of the ring */
+ u16 count; /* Number of descriptors */
+ u16 rx_buf_len; /* Admin Receive Queue buffer length */
+
+ /* used for interrupt processing */
+ u16 next_to_use;
+ u16 next_to_clean;
+
+ /* used for queue tracking */
+ u32 head;
+ u32 tail;
+};
+
+/* ASQ transaction details */
+struct i40e_asq_cmd_details {
+ void *callback; /* cast from type I40E_ADMINQ_CALLBACK */
+ u64 cookie;
+ u16 flags_ena;
+ u16 flags_dis;
+ bool async;
+ bool postpone;
+};
+
+#define I40E_ADMINQ_DETAILS(R, i) \
+ (&(((struct i40e_asq_cmd_details *)((R).details))[i]))
+
+/* ARQ event information */
+struct i40e_arq_event_info {
+ struct i40e_aq_desc desc;
+ u16 msg_size;
+ u8 *msg_buf;
+};
+
+/* Admin Queue information */
+struct i40e_adminq_info {
+ struct i40e_adminq_ring arq; /* receive queue */
+ struct i40e_adminq_ring asq; /* send queue */
+ u16 num_arq_entries; /* receive queue depth */
+ u16 num_asq_entries; /* send queue depth */
+ u16 arq_buf_size; /* receive queue buffer size */
+ u16 asq_buf_size; /* send queue buffer size */
+ u16 fw_maj_ver; /* firmware major version */
+ u16 fw_min_ver; /* firmware minor version */
+ u16 api_maj_ver; /* api major version */
+ u16 api_min_ver; /* api minor version */
+
+ struct mutex asq_mutex; /* Send queue lock */
+ struct mutex arq_mutex; /* Receive queue lock */
+
+ struct i40e_dma_mem asq_mem; /* send queue dynamic memory */
+ struct i40e_dma_mem arq_mem; /* receive queue dynamic memory */
+
+ /* last status values on send and receive queues */
+ enum i40e_admin_queue_err asq_last_status;
+ enum i40e_admin_queue_err arq_last_status;
+};
+
+/* general information */
+#define I40E_AQ_LARGE_BUF 512
+#define I40E_ASQ_CMD_TIMEOUT 100000 /* usecs */
+
+void i40e_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc,
+ u16 opcode);
+
+#endif /* _I40E_ADMINQ_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
new file mode 100644
index 0000000..e61ebdd
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -0,0 +1,2076 @@
+/*******************************************************************************
+ *
+ * Intel Ethernet Controller XL710 Family Linux Driver
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ ******************************************************************************/
+
+#ifndef _I40E_ADMINQ_CMD_H_
+#define _I40E_ADMINQ_CMD_H_
+
+/* This header file defines the i40e Admin Queue commands and is shared between
+ * i40e Firmware and Software.
+ *
+ * This file needs to comply with the Linux Kernel coding style.
+ */
+
+#define I40E_FW_API_VERSION_MAJOR 0x0001
+#define I40E_FW_API_VERSION_MINOR 0x0000
+
+struct i40e_aq_desc {
+ __le16 flags;
+ __le16 opcode;
+ __le16 datalen;
+ __le16 retval;
+ __le32 cookie_high;
+ __le32 cookie_low;
+ union {
+ struct {
+ __le32 param0;
+ __le32 param1;
+ __le32 param2;
+ __le32 param3;
+ } internal;
+ struct {
+ __le32 param0;
+ __le32 param1;
+ __le32 addr_high;
+ __le32 addr_low;
+ } external;
+ u8 raw[16];
+ } params;
+};
+
+/* Flags sub-structure
+ * |0 |1 |2 |3 |4 |5 |6 |7 |8 |9 |10 |11 |12 |13 |14 |15 |
+ * |DD |CMP|ERR|VFE| * * RESERVED * * |LB |RD |VFC|BUF|SI |EI |FE |
+ */
+
+/* command flags and offsets*/
+#define I40E_AQ_FLAG_DD_SHIFT 0
+#define I40E_AQ_FLAG_CMP_SHIFT 1
+#define I40E_AQ_FLAG_ERR_SHIFT 2
+#define I40E_AQ_FLAG_VFE_SHIFT 3
+#define I40E_AQ_FLAG_LB_SHIFT 9
+#define I40E_AQ_FLAG_RD_SHIFT 10
+#define I40E_AQ_FLAG_VFC_SHIFT 11
+#define I40E_AQ_FLAG_BUF_SHIFT 12
+#define I40E_AQ_FLAG_SI_SHIFT 13
+#define I40E_AQ_FLAG_EI_SHIFT 14
+#define I40E_AQ_FLAG_FE_SHIFT 15
+
+#define I40E_AQ_FLAG_DD (1 << I40E_AQ_FLAG_DD_SHIFT) /* 0x1 */
+#define I40E_AQ_FLAG_CMP (1 << I40E_AQ_FLAG_CMP_SHIFT) /* 0x2 */
+#define I40E_AQ_FLAG_ERR (1 << I40E_AQ_FLAG_ERR_SHIFT) /* 0x4 */
+#define I40E_AQ_FLAG_VFE (1 << I40E_AQ_FLAG_VFE_SHIFT) /* 0x8 */
+#define I40E_AQ_FLAG_LB (1 << I40E_AQ_FLAG_LB_SHIFT) /* 0x200 */
+#define I40E_AQ_FLAG_RD (1 << I40E_AQ_FLAG_RD_SHIFT) /* 0x400 */
+#define I40E_AQ_FLAG_VFC (1 << I40E_AQ_FLAG_VFC_SHIFT) /* 0x800 */
+#define I40E_AQ_FLAG_BUF (1 << I40E_AQ_FLAG_BUF_SHIFT) /* 0x1000 */
+#define I40E_AQ_FLAG_SI (1 << I40E_AQ_FLAG_SI_SHIFT) /* 0x2000 */
+#define I40E_AQ_FLAG_EI (1 << I40E_AQ_FLAG_EI_SHIFT) /* 0x4000 */
+#define I40E_AQ_FLAG_FE (1 << I40E_AQ_FLAG_FE_SHIFT) /* 0x8000 */
+
+/* error codes */
+enum i40e_admin_queue_err {
+ I40E_AQ_RC_OK = 0, /* success */
+ I40E_AQ_RC_EPERM = 1, /* Operation not permitted */
+ I40E_AQ_RC_ENOENT = 2, /* No such element */
+ I40E_AQ_RC_ESRCH = 3, /* Bad opcode */
+ I40E_AQ_RC_EINTR = 4, /* operation interrupted */
+ I40E_AQ_RC_EIO = 5, /* I/O error */
+ I40E_AQ_RC_ENXIO = 6, /* No such resource */
+ I40E_AQ_RC_E2BIG = 7, /* Arg too long */
+ I40E_AQ_RC_EAGAIN = 8, /* Try again */
+ I40E_AQ_RC_ENOMEM = 9, /* Out of memory */
+ I40E_AQ_RC_EACCES = 10, /* Permission denied */
+ I40E_AQ_RC_EFAULT = 11, /* Bad address */
+ I40E_AQ_RC_EBUSY = 12, /* Device or resource busy */
+ I40E_AQ_RC_EEXIST = 13, /* object already exists */
+ I40E_AQ_RC_EINVAL = 14, /* Invalid argument */
+ I40E_AQ_RC_ENOTTY = 15, /* Not a typewriter */
+ I40E_AQ_RC_ENOSPC = 16, /* No space left or alloc failure */
+ I40E_AQ_RC_ENOSYS = 17, /* Function not implemented */
+ I40E_AQ_RC_ERANGE = 18, /* Parameter out of range */
+ I40E_AQ_RC_EFLUSHED = 19, /* Cmd flushed because of prev cmd error */
+ I40E_AQ_RC_BAD_ADDR = 20, /* Descriptor contains a bad pointer */
+ I40E_AQ_RC_EMODE = 21, /* Op not allowed in current dev mode */
+ I40E_AQ_RC_EFBIG = 22, /* File too large */
+};
+
+/* Admin Queue command opcodes */
+enum i40e_admin_queue_opc {
+ /* aq commands */
+ i40e_aqc_opc_get_version = 0x0001,
+ i40e_aqc_opc_driver_version = 0x0002,
+ i40e_aqc_opc_queue_shutdown = 0x0003,
+
+ /* resource ownership */
+ i40e_aqc_opc_request_resource = 0x0008,
+ i40e_aqc_opc_release_resource = 0x0009,
+
+ i40e_aqc_opc_list_func_capabilities = 0x000A,
+ i40e_aqc_opc_list_dev_capabilities = 0x000B,
+
+ i40e_aqc_opc_set_cppm_configuration = 0x0103,
+ i40e_aqc_opc_set_arp_proxy_entry = 0x0104,
+ i40e_aqc_opc_set_ns_proxy_entry = 0x0105,
+
+ /* LAA */
+ i40e_aqc_opc_mng_laa = 0x0106,
+ i40e_aqc_opc_mac_address_read = 0x0107,
+ i40e_aqc_opc_mac_address_write = 0x0108,
+
+ /* internal switch commands */
+ i40e_aqc_opc_get_switch_config = 0x0200,
+ i40e_aqc_opc_add_statistics = 0x0201,
+ i40e_aqc_opc_remove_statistics = 0x0202,
+ i40e_aqc_opc_set_port_parameters = 0x0203,
+ i40e_aqc_opc_get_switch_resource_alloc = 0x0204,
+
+ i40e_aqc_opc_add_vsi = 0x0210,
+ i40e_aqc_opc_update_vsi_parameters = 0x0211,
+ i40e_aqc_opc_get_vsi_parameters = 0x0212,
+
+ i40e_aqc_opc_add_pv = 0x0220,
+ i40e_aqc_opc_update_pv_parameters = 0x0221,
+ i40e_aqc_opc_get_pv_parameters = 0x0222,
+
+ i40e_aqc_opc_add_veb = 0x0230,
+ i40e_aqc_opc_update_veb_parameters = 0x0231,
+ i40e_aqc_opc_get_veb_parameters = 0x0232,
+
+ i40e_aqc_opc_delete_element = 0x0243,
+
+ i40e_aqc_opc_add_macvlan = 0x0250,
+ i40e_aqc_opc_remove_macvlan = 0x0251,
+ i40e_aqc_opc_add_vlan = 0x0252,
+ i40e_aqc_opc_remove_vlan = 0x0253,
+ i40e_aqc_opc_set_vsi_promiscuous_modes = 0x0254,
+ i40e_aqc_opc_add_tag = 0x0255,
+ i40e_aqc_opc_remove_tag = 0x0256,
+ i40e_aqc_opc_add_multicast_etag = 0x0257,
+ i40e_aqc_opc_remove_multicast_etag = 0x0258,
+ i40e_aqc_opc_update_tag = 0x0259,
+ i40e_aqc_opc_add_control_packet_filter = 0x025A,
+ i40e_aqc_opc_remove_control_packet_filter = 0x025B,
+ i40e_aqc_opc_add_cloud_filters = 0x025C,
+ i40e_aqc_opc_remove_cloud_filters = 0x025D,
+
+ i40e_aqc_opc_add_mirror_rule = 0x0260,
+ i40e_aqc_opc_delete_mirror_rule = 0x0261,
+
+ i40e_aqc_opc_set_storm_control_config = 0x0280,
+ i40e_aqc_opc_get_storm_control_config = 0x0281,
+
+ /* DCB commands */
+ i40e_aqc_opc_dcb_ignore_pfc = 0x0301,
+ i40e_aqc_opc_dcb_updated = 0x0302,
+
+ /* TX scheduler */
+ i40e_aqc_opc_configure_vsi_bw_limit = 0x0400,
+ i40e_aqc_opc_configure_vsi_ets_sla_bw_limit = 0x0406,
+ i40e_aqc_opc_configure_vsi_tc_bw = 0x0407,
+ i40e_aqc_opc_query_vsi_bw_config = 0x0408,
+ i40e_aqc_opc_query_vsi_ets_sla_config = 0x040A,
+ i40e_aqc_opc_configure_switching_comp_bw_limit = 0x0410,
+
+ i40e_aqc_opc_enable_switching_comp_ets = 0x0413,
+ i40e_aqc_opc_modify_switching_comp_ets = 0x0414,
+ i40e_aqc_opc_disable_switching_comp_ets = 0x0415,
+ i40e_aqc_opc_configure_switching_comp_ets_bw_limit = 0x0416,
+ i40e_aqc_opc_configure_switching_comp_bw_config = 0x0417,
+ i40e_aqc_opc_query_switching_comp_ets_config = 0x0418,
+ i40e_aqc_opc_query_port_ets_config = 0x0419,
+ i40e_aqc_opc_query_switching_comp_bw_config = 0x041A,
+ i40e_aqc_opc_suspend_port_tx = 0x041B,
+ i40e_aqc_opc_resume_port_tx = 0x041C,
+
+ /* hmc */
+ i40e_aqc_opc_query_hmc_resource_profile = 0x0500,
+ i40e_aqc_opc_set_hmc_resource_profile = 0x0501,
+
+ /* phy commands*/
+ i40e_aqc_opc_get_phy_abilities = 0x0600,
+ i40e_aqc_opc_set_phy_config = 0x0601,
+ i40e_aqc_opc_set_mac_config = 0x0603,
+ i40e_aqc_opc_set_link_restart_an = 0x0605,
+ i40e_aqc_opc_get_link_status = 0x0607,
+ i40e_aqc_opc_set_phy_int_mask = 0x0613,
+ i40e_aqc_opc_get_local_advt_reg = 0x0614,
+ i40e_aqc_opc_set_local_advt_reg = 0x0615,
+ i40e_aqc_opc_get_partner_advt = 0x0616,
+ i40e_aqc_opc_set_lb_modes = 0x0618,
+ i40e_aqc_opc_get_phy_wol_caps = 0x0621,
+ i40e_aqc_opc_set_phy_reset = 0x0622,
+ i40e_aqc_opc_upload_ext_phy_fm = 0x0625,
+
+ /* NVM commands */
+ i40e_aqc_opc_nvm_read = 0x0701,
+ i40e_aqc_opc_nvm_erase = 0x0702,
+ i40e_aqc_opc_nvm_update = 0x0703,
+
+ /* virtualization commands */
+ i40e_aqc_opc_send_msg_to_pf = 0x0801,
+ i40e_aqc_opc_send_msg_to_vf = 0x0802,
+ i40e_aqc_opc_send_msg_to_peer = 0x0803,
+
+ /* alternate structure */
+ i40e_aqc_opc_alternate_write = 0x0900,
+ i40e_aqc_opc_alternate_write_indirect = 0x0901,
+ i40e_aqc_opc_alternate_read = 0x0902,
+ i40e_aqc_opc_alternate_read_indirect = 0x0903,
+ i40e_aqc_opc_alternate_write_done = 0x0904,
+ i40e_aqc_opc_alternate_set_mode = 0x0905,
+ i40e_aqc_opc_alternate_clear_port = 0x0906,
+
+ /* LLDP commands */
+ i40e_aqc_opc_lldp_get_mib = 0x0A00,
+ i40e_aqc_opc_lldp_update_mib = 0x0A01,
+ i40e_aqc_opc_lldp_add_tlv = 0x0A02,
+ i40e_aqc_opc_lldp_update_tlv = 0x0A03,
+ i40e_aqc_opc_lldp_delete_tlv = 0x0A04,
+ i40e_aqc_opc_lldp_stop = 0x0A05,
+ i40e_aqc_opc_lldp_start = 0x0A06,
+
+ /* Tunnel commands */
+ i40e_aqc_opc_add_udp_tunnel = 0x0B00,
+ i40e_aqc_opc_del_udp_tunnel = 0x0B01,
+ i40e_aqc_opc_tunnel_key_structure = 0x0B10,
+
+ /* Async Events */
+ i40e_aqc_opc_event_lan_overflow = 0x1001,
+
+ /* OEM commands */
+ i40e_aqc_opc_oem_parameter_change = 0xFE00,
+ i40e_aqc_opc_oem_device_status_change = 0xFE01,
+
+ /* debug commands */
+ i40e_aqc_opc_debug_get_deviceid = 0xFF00,
+ i40e_aqc_opc_debug_set_mode = 0xFF01,
+ i40e_aqc_opc_debug_read_reg = 0xFF03,
+ i40e_aqc_opc_debug_write_reg = 0xFF04,
+ i40e_aqc_opc_debug_read_reg_sg = 0xFF05,
+ i40e_aqc_opc_debug_write_reg_sg = 0xFF06,
+ i40e_aqc_opc_debug_modify_reg = 0xFF07,
+ i40e_aqc_opc_debug_dump_internals = 0xFF08,
+ i40e_aqc_opc_debug_modify_internals = 0xFF09,
+};
+
+/* command structures and indirect data structures */
+
+/* Structure naming conventions:
+ * - no suffix for direct command descriptor structures
+ * - _data for indirect sent data
+ * - _resp for indirect return data (data which is both will use _data)
+ * - _completion for direct return data
+ * - _element_ for repeated elements (may also be _data or _resp)
+ *
+ * Command structures are expected to overlay the params.raw member of the basic
+ * descriptor, and as such cannot exceed 16 bytes in length.
+ */
+
+/* This macro is used to generate a compilation error if a structure
+ * is not exactly the correct length. It gives a divide by zero error if the
+ * structure is not of the correct size, otherwise it creates an enum that is
+ * never used.
+ */
+#define I40E_CHECK_STRUCT_LEN(n, X) enum i40e_static_assert_enum_##X \
+ { i40e_static_assert_##X = (n)/((sizeof(struct X) == (n)) ? 1 : 0) }
+
+/* This macro is used extensively to ensure that command structures are 16
+ * bytes in length as they have to map to the raw array of that size.
+ */
+#define I40E_CHECK_CMD_LENGTH(X) I40E_CHECK_STRUCT_LEN(16, X)
+
+/* internal (0x00XX) commands */
+
+/* Get version (direct 0x0001) */
+struct i40e_aqc_get_version {
+ __le32 rom_ver;
+ __le32 fw_build;
+ __le16 fw_major;
+ __le16 fw_minor;
+ __le16 api_major;
+ __le16 api_minor;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_get_version);
+
+/* Send driver version (direct 0x0002) */
+struct i40e_aqc_driver_version {
+ u8 driver_major_ver;
+ u8 driver_minor_ver;
+ u8 driver_build_ver;
+ u8 driver_subbuild_ver;
+ u8 reserved[12];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_driver_version);
+
+/* Queue Shutdown (direct 0x0003) */
+struct i40e_aqc_queue_shutdown {
+ __le32 driver_unloading;
+#define I40E_AQ_DRIVER_UNLOADING 0x1
+ u8 reserved[12];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_queue_shutdown);
+
+/* Request resource ownership (direct 0x0008)
+ * Release resource ownership (direct 0x0009)
+ */
+#define I40E_AQ_RESOURCE_NVM 1
+#define I40E_AQ_RESOURCE_SDP 2
+#define I40E_AQ_RESOURCE_ACCESS_READ 1
+#define I40E_AQ_RESOURCE_ACCESS_WRITE 2
+#define I40E_AQ_RESOURCE_NVM_READ_TIMEOUT 3000
+#define I40E_AQ_RESOURCE_NVM_WRITE_TIMEOUT 180000
+
+struct i40e_aqc_request_resource {
+ __le16 resource_id;
+ __le16 access_type;
+ __le32 timeout;
+ __le32 resource_number;
+ u8 reserved[4];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_request_resource);
+
+/* Get function capabilities (indirect 0x000A)
+ * Get device capabilities (indirect 0x000B)
+ */
+struct i40e_aqc_list_capabilites {
+ u8 command_flags;
+#define I40E_AQ_LIST_CAP_PF_INDEX_EN 1
+ u8 pf_index;
+ u8 reserved[2];
+ __le32 count;
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_list_capabilites);
+
+struct i40e_aqc_list_capabilities_element_resp {
+ __le16 id;
+ u8 major_rev;
+ u8 minor_rev;
+ __le32 number;
+ __le32 logical_id;
+ __le32 phys_id;
+ u8 reserved[16];
+};
+
+/* list of caps */
+
+#define I40E_AQ_CAP_ID_SWITCH_MODE 0x0001
+#define I40E_AQ_CAP_ID_MNG_MODE 0x0002
+#define I40E_AQ_CAP_ID_NPAR_ACTIVE 0x0003
+#define I40E_AQ_CAP_ID_OS2BMC_CAP 0x0004
+#define I40E_AQ_CAP_ID_FUNCTIONS_VALID 0x0005
+#define I40E_AQ_CAP_ID_ALTERNATE_RAM 0x0006
+#define I40E_AQ_CAP_ID_SRIOV 0x0012
+#define I40E_AQ_CAP_ID_VF 0x0013
+#define I40E_AQ_CAP_ID_VMDQ 0x0014
+#define I40E_AQ_CAP_ID_8021QBG 0x0015
+#define I40E_AQ_CAP_ID_8021QBR 0x0016
+#define I40E_AQ_CAP_ID_VSI 0x0017
+#define I40E_AQ_CAP_ID_DCB 0x0018
+#define I40E_AQ_CAP_ID_FCOE 0x0021
+#define I40E_AQ_CAP_ID_RSS 0x0040
+#define I40E_AQ_CAP_ID_RXQ 0x0041
+#define I40E_AQ_CAP_ID_TXQ 0x0042
+#define I40E_AQ_CAP_ID_MSIX 0x0043
+#define I40E_AQ_CAP_ID_VF_MSIX 0x0044
+#define I40E_AQ_CAP_ID_FLOW_DIRECTOR 0x0045
+#define I40E_AQ_CAP_ID_1588 0x0046
+#define I40E_AQ_CAP_ID_IWARP 0x0051
+#define I40E_AQ_CAP_ID_LED 0x0061
+#define I40E_AQ_CAP_ID_SDP 0x0062
+#define I40E_AQ_CAP_ID_MDIO 0x0063
+#define I40E_AQ_CAP_ID_FLEX10 0x00F1
+#define I40E_AQ_CAP_ID_CEM 0x00F2
+
+/* Set CPPM Configuration (direct 0x0103) */
+struct i40e_aqc_cppm_configuration {
+ __le16 command_flags;
+#define I40E_AQ_CPPM_EN_LTRC 0x0800
+#define I40E_AQ_CPPM_EN_DMCTH 0x1000
+#define I40E_AQ_CPPM_EN_DMCTLX 0x2000
+#define I40E_AQ_CPPM_EN_HPTC 0x4000
+#define I40E_AQ_CPPM_EN_DMARC 0x8000
+ __le16 ttlx;
+ __le32 dmacr;
+ __le16 dmcth;
+ u8 hptc;
+ u8 reserved;
+ __le32 pfltrc;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_cppm_configuration);
+
+/* Set ARP Proxy command / response (indirect 0x0104) */
+struct i40e_aqc_arp_proxy_data {
+ __le16 command_flags;
+#define I40E_AQ_ARP_INIT_IPV4 0x0008
+#define I40E_AQ_ARP_UNSUP_CTL 0x0010
+#define I40E_AQ_ARP_ENA 0x0020
+#define I40E_AQ_ARP_ADD_IPV4 0x0040
+#define I40E_AQ_ARP_DEL_IPV4 0x0080
+ __le16 table_id;
+ __le32 pfpm_proxyfc;
+ __le32 ip_addr;
+ u8 mac_addr[6];
+};
+
+/* Set NS Proxy Table Entry Command (indirect 0x0105) */
+struct i40e_aqc_ns_proxy_data {
+ __le16 table_idx_mac_addr_0;
+ __le16 table_idx_mac_addr_1;
+ __le16 table_idx_ipv6_0;
+ __le16 table_idx_ipv6_1;
+ __le16 control;
+#define I40E_AQ_NS_PROXY_ADD_0 0x0100
+#define I40E_AQ_NS_PROXY_DEL_0 0x0200
+#define I40E_AQ_NS_PROXY_ADD_1 0x0400
+#define I40E_AQ_NS_PROXY_DEL_1 0x0800
+#define I40E_AQ_NS_PROXY_ADD_IPV6_0 0x1000
+#define I40E_AQ_NS_PROXY_DEL_IPV6_0 0x2000
+#define I40E_AQ_NS_PROXY_ADD_IPV6_1 0x4000
+#define I40E_AQ_NS_PROXY_DEL_IPV6_1 0x8000
+#define I40E_AQ_NS_PROXY_COMMAND_SEQ 0x0001
+#define I40E_AQ_NS_PROXY_INIT_IPV6_TBL 0x0002
+#define I40E_AQ_NS_PROXY_INIT_MAC_TBL 0x0004
+ u8 mac_addr_0[6];
+ u8 mac_addr_1[6];
+ u8 local_mac_addr[6];
+ u8 ipv6_addr_0[16]; /* Warning! spec specifies BE byte order */
+ u8 ipv6_addr_1[16];
+};
+
+/* Manage LAA Command (0x0106) - obsolete */
+struct i40e_aqc_mng_laa {
+ __le16 command_flags;
+#define I40E_AQ_LAA_FLAG_WR 0x8000
+ u8 reserved[2];
+ __le32 sal;
+ __le16 sah;
+ u8 reserved2[6];
+};
+
+/* Manage MAC Address Read Command (0x0107) */
+struct i40e_aqc_mac_address_read {
+ __le16 command_flags;
+#define I40E_AQC_LAN_ADDR_VALID 0x10
+#define I40E_AQC_SAN_ADDR_VALID 0x20
+#define I40E_AQC_PORT_ADDR_VALID 0x40
+#define I40E_AQC_WOL_ADDR_VALID 0x80
+#define I40E_AQC_ADDR_VALID_MASK 0xf0
+ u8 reserved[6];
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_mac_address_read);
+
+struct i40e_aqc_mac_address_read_data {
+ u8 pf_lan_mac[6];
+ u8 pf_san_mac[6];
+ u8 port_mac[6];
+ u8 pf_wol_mac[6];
+};
+
+I40E_CHECK_STRUCT_LEN(24, i40e_aqc_mac_address_read_data);
+
+/* Manage MAC Address Write Command (0x0108) */
+struct i40e_aqc_mac_address_write {
+ __le16 command_flags;
+#define I40E_AQC_WRITE_TYPE_LAA_ONLY 0x0000
+#define I40E_AQC_WRITE_TYPE_LAA_WOL 0x4000
+#define I40E_AQC_WRITE_TYPE_PORT 0x8000
+#define I40E_AQC_WRITE_TYPE_MASK 0xc000
+ __le16 mac_sah;
+ __le32 mac_sal;
+ u8 reserved[8];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_mac_address_write);
+
+/* Switch configuration commands (0x02xx) */
+
+/* Used by many indirect commands that only pass an seid and a buffer in the
+ * command
+ */
+struct i40e_aqc_switch_seid {
+ __le16 seid;
+ u8 reserved[6];
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_switch_seid);
+
+/* Get Switch Configuration command (indirect 0x0200)
+ * uses i40e_aqc_switch_seid for the descriptor
+ */
+struct i40e_aqc_get_switch_config_header_resp {
+ __le16 num_reported;
+ __le16 num_total;
+ u8 reserved[12];
+};
+
+struct i40e_aqc_switch_config_element_resp {
+ u8 element_type;
+#define I40E_AQ_SW_ELEM_TYPE_MAC 1
+#define I40E_AQ_SW_ELEM_TYPE_PF 2
+#define I40E_AQ_SW_ELEM_TYPE_VF 3
+#define I40E_AQ_SW_ELEM_TYPE_EMP 4
+#define I40E_AQ_SW_ELEM_TYPE_BMC 5
+#define I40E_AQ_SW_ELEM_TYPE_PV 16
+#define I40E_AQ_SW_ELEM_TYPE_VEB 17
+#define I40E_AQ_SW_ELEM_TYPE_PA 18
+#define I40E_AQ_SW_ELEM_TYPE_VSI 19
+ u8 revision;
+#define I40E_AQ_SW_ELEM_REV_1 1
+ __le16 seid;
+ __le16 uplink_seid;
+ __le16 downlink_seid;
+ u8 reserved[3];
+ u8 connection_type;
+#define I40E_AQ_CONN_TYPE_REGULAR 0x1
+#define I40E_AQ_CONN_TYPE_DEFAULT 0x2
+#define I40E_AQ_CONN_TYPE_CASCADED 0x3
+ __le16 scheduler_id;
+ __le16 element_info;
+};
+
+/* Get Switch Configuration (indirect 0x0200)
+ * an array of elements are returned in the response buffer
+ * the first in the array is the header, remainder are elements
+ */
+struct i40e_aqc_get_switch_config_resp {
+ struct i40e_aqc_get_switch_config_header_resp header;
+ struct i40e_aqc_switch_config_element_resp element[1];
+};
+
+/* Add Statistics (direct 0x0201)
+ * Remove Statistics (direct 0x0202)
+ */
+struct i40e_aqc_add_remove_statistics {
+ __le16 seid;
+ __le16 vlan;
+ __le16 stat_index;
+ u8 reserved[10];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_statistics);
+
+/* Set Port Parameters command (direct 0x0203) */
+struct i40e_aqc_set_port_parameters {
+ __le16 command_flags;
+#define I40E_AQ_SET_P_PARAMS_SAVE_BAD_PACKETS 1
+#define I40E_AQ_SET_P_PARAMS_PAD_SHORT_PACKETS 2 /* must set! */
+#define I40E_AQ_SET_P_PARAMS_DOUBLE_VLAN_ENA 4
+ __le16 bad_frame_vsi;
+ __le16 default_seid; /* reserved for command */
+ u8 reserved[10];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_set_port_parameters);
+
+/* Get Switch Resource Allocation (indirect 0x0204) */
+struct i40e_aqc_get_switch_resource_alloc {
+ u8 num_entries; /* reserved for command */
+ u8 reserved[7];
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_get_switch_resource_alloc);
+
+/* expect an array of these structs in the response buffer */
+struct i40e_aqc_switch_resource_alloc_element_resp {
+ u8 resource_type;
+#define I40E_AQ_RESOURCE_TYPE_VEB 0x0
+#define I40E_AQ_RESOURCE_TYPE_VSI 0x1
+#define I40E_AQ_RESOURCE_TYPE_MACADDR 0x2
+#define I40E_AQ_RESOURCE_TYPE_STAG 0x3
+#define I40E_AQ_RESOURCE_TYPE_ETAG 0x4
+#define I40E_AQ_RESOURCE_TYPE_MULTICAST_HASH 0x5
+#define I40E_AQ_RESOURCE_TYPE_UNICAST_HASH 0x6
+#define I40E_AQ_RESOURCE_TYPE_VLAN 0x7
+#define I40E_AQ_RESOURCE_TYPE_VSI_LIST_ENTRY 0x8
+#define I40E_AQ_RESOURCE_TYPE_ETAG_LIST_ENTRY 0x9
+#define I40E_AQ_RESOURCE_TYPE_VLAN_STAT_POOL 0xA
+#define I40E_AQ_RESOURCE_TYPE_MIRROR_RULE 0xB
+#define I40E_AQ_RESOURCE_TYPE_QUEUE_SETS 0xC
+#define I40E_AQ_RESOURCE_TYPE_VLAN_FILTERS 0xD
+#define I40E_AQ_RESOURCE_TYPE_INNER_MAC_FILTERS 0xF
+#define I40E_AQ_RESOURCE_TYPE_IP_FILTERS 0x10
+#define I40E_AQ_RESOURCE_TYPE_GRE_VN_KEYS 0x11
+#define I40E_AQ_RESOURCE_TYPE_VN2_KEYS 0x12
+#define I40E_AQ_RESOURCE_TYPE_TUNNEL_PORTS 0x13
+ u8 reserved1;
+ __le16 guaranteed;
+ __le16 total;
+ __le16 used;
+ __le16 total_unalloced;
+ u8 reserved2[6];
+};
+
+/* Add VSI (indirect 0x210)
+ * this indirect command uses struct i40e_aqc_vsi_properties_data
+ * as the indirect buffer (128 bytes)
+ *
+ * Update VSI (indirect 0x211) Get VSI (indirect 0x0212)
+ * use the generic i40e_aqc_switch_seid descriptor format
+ * use the same completion and data structure as Add VSI
+ */
+struct i40e_aqc_add_get_update_vsi {
+ __le16 uplink_seid;
+ u8 connection_type;
+#define I40E_AQ_VSI_CONN_TYPE_NORMAL 0x1
+#define I40E_AQ_VSI_CONN_TYPE_DEFAULT 0x2
+#define I40E_AQ_VSI_CONN_TYPE_CASCADED 0x3
+ u8 reserved1;
+ u8 vf_id;
+ u8 reserved2;
+ __le16 vsi_flags;
+#define I40E_AQ_VSI_TYPE_SHIFT 0x0
+#define I40E_AQ_VSI_TYPE_MASK (0x3 << I40E_AQ_VSI_TYPE_SHIFT)
+#define I40E_AQ_VSI_TYPE_VF 0x0
+#define I40E_AQ_VSI_TYPE_VMDQ2 0x1
+#define I40E_AQ_VSI_TYPE_PF 0x2
+#define I40E_AQ_VSI_TYPE_EMP_MNG 0x3
+#define I40E_AQ_VSI_FLAG_CASCADED_PV 0x4
+#define I40E_AQ_VSI_FLAG_CLOUD_VSI 0x8
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_add_get_update_vsi);
+
+struct i40e_aqc_add_get_update_vsi_completion {
+ __le16 seid;
+ __le16 vsi_number;
+ __le16 vsi_used;
+ __le16 vsi_free;
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_add_get_update_vsi_completion);
+
+struct i40e_aqc_vsi_properties_data {
+ /* first 96 byte are written by SW */
+ __le16 valid_sections;
+#define I40E_AQ_VSI_PROP_SWITCH_VALID 0x0001
+#define I40E_AQ_VSI_PROP_SECURITY_VALID 0x0002
+#define I40E_AQ_VSI_PROP_VLAN_VALID 0x0004
+#define I40E_AQ_VSI_PROP_CAS_PV_VALID 0x0008
+#define I40E_AQ_VSI_PROP_INGRESS_UP_VALID 0x0010
+#define I40E_AQ_VSI_PROP_EGRESS_UP_VALID 0x0020
+#define I40E_AQ_VSI_PROP_QUEUE_MAP_VALID 0x0040
+#define I40E_AQ_VSI_PROP_QUEUE_OPT_VALID 0x0080
+#define I40E_AQ_VSI_PROP_OUTER_UP_VALID 0x0100
+#define I40E_AQ_VSI_PROP_SCHED_VALID 0x0200
+ /* switch section */
+ __le16 switch_id; /* 12bit id combined with flags below */
+#define I40E_AQ_VSI_SW_ID_SHIFT 0x0000
+#define I40E_AQ_VSI_SW_ID_MASK (0xFFF << I40E_AQ_VSI_SW_ID_SHIFT)
+#define I40E_AQ_VSI_SW_ID_FLAG_NOT_STAG 0x1000
+#define I40E_AQ_VSI_SW_ID_FLAG_ALLOW_LB 0x2000
+#define I40E_AQ_VSI_SW_ID_FLAG_LOCAL_LB 0x4000
+ u8 sw_reserved[2];
+ /* security section */
+ u8 sec_flags;
+#define I40E_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD 0x01
+#define I40E_AQ_VSI_SEC_FLAG_ENABLE_VLAN_CHK 0x02
+#define I40E_AQ_VSI_SEC_FLAG_ENABLE_MAC_CHK 0x04
+ u8 sec_reserved;
+ /* VLAN section */
+ __le16 pvid; /* VLANS include priority bits */
+ __le16 fcoe_pvid;
+ u8 port_vlan_flags;
+#define I40E_AQ_VSI_PVLAN_MODE_SHIFT 0x00
+#define I40E_AQ_VSI_PVLAN_MODE_MASK (0x03 << \
+ I40E_AQ_VSI_PVLAN_MODE_SHIFT)
+#define I40E_AQ_VSI_PVLAN_MODE_TAGGED 0x01
+#define I40E_AQ_VSI_PVLAN_MODE_UNTAGGED 0x02
+#define I40E_AQ_VSI_PVLAN_MODE_ALL 0x03
+#define I40E_AQ_VSI_PVLAN_INSERT_PVID 0x04
+#define I40E_AQ_VSI_PVLAN_EMOD_SHIFT 0x03
+#define I40E_AQ_VSI_PVLAN_EMOD_MASK (0x3 << \
+ I40E_AQ_VSI_PVLAN_EMOD_SHIFT)
+#define I40E_AQ_VSI_PVLAN_EMOD_STR_BOTH 0x0
+#define I40E_AQ_VSI_PVLAN_EMOD_STR_UP 0x08
+#define I40E_AQ_VSI_PVLAN_EMOD_STR 0x10
+#define I40E_AQ_VSI_PVLAN_EMOD_NOTHING 0x18
+ u8 pvlan_reserved[3];
+ /* ingress egress up sections */
+ __le32 ingress_table; /* bitmap, 3 bits per up */
+#define I40E_AQ_VSI_UP_TABLE_UP0_SHIFT 0
+#define I40E_AQ_VSI_UP_TABLE_UP0_MASK (0x7 << \
+ I40E_AQ_VSI_UP_TABLE_UP0_SHIFT)
+#define I40E_AQ_VSI_UP_TABLE_UP1_SHIFT 3
+#define I40E_AQ_VSI_UP_TABLE_UP1_MASK (0x7 << \
+ I40E_AQ_VSI_UP_TABLE_UP1_SHIFT)
+#define I40E_AQ_VSI_UP_TABLE_UP2_SHIFT 6
+#define I40E_AQ_VSI_UP_TABLE_UP2_MASK (0x7 << \
+ I40E_AQ_VSI_UP_TABLE_UP2_SHIFT)
+#define I40E_AQ_VSI_UP_TABLE_UP3_SHIFT 9
+#define I40E_AQ_VSI_UP_TABLE_UP3_MASK (0x7 << \
+ I40E_AQ_VSI_UP_TABLE_UP3_SHIFT)
+#define I40E_AQ_VSI_UP_TABLE_UP4_SHIFT 12
+#define I40E_AQ_VSI_UP_TABLE_UP4_MASK (0x7 << \
+ I40E_AQ_VSI_UP_TABLE_UP4_SHIFT)
+#define I40E_AQ_VSI_UP_TABLE_UP5_SHIFT 15
+#define I40E_AQ_VSI_UP_TABLE_UP5_MASK (0x7 << \
+ I40E_AQ_VSI_UP_TABLE_UP5_SHIFT)
+#define I40E_AQ_VSI_UP_TABLE_UP6_SHIFT 18
+#define I40E_AQ_VSI_UP_TABLE_UP6_MASK (0x7 << \
+ I40E_AQ_VSI_UP_TABLE_UP6_SHIFT)
+#define I40E_AQ_VSI_UP_TABLE_UP7_SHIFT 21
+#define I40E_AQ_VSI_UP_TABLE_UP7_MASK (0x7 << \
+ I40E_AQ_VSI_UP_TABLE_UP7_SHIFT)
+ __le32 egress_table; /* same defines as for ingress table */
+ /* cascaded PV section */
+ __le16 cas_pv_tag;
+ u8 cas_pv_flags;
+#define I40E_AQ_VSI_CAS_PV_TAGX_SHIFT 0x00
+#define I40E_AQ_VSI_CAS_PV_TAGX_MASK (0x03 << \
+ I40E_AQ_VSI_CAS_PV_TAGX_SHIFT)
+#define I40E_AQ_VSI_CAS_PV_TAGX_LEAVE 0x00
+#define I40E_AQ_VSI_CAS_PV_TAGX_REMOVE 0x01
+#define I40E_AQ_VSI_CAS_PV_TAGX_COPY 0x02
+#define I40E_AQ_VSI_CAS_PV_INSERT_TAG 0x10
+#define I40E_AQ_VSI_CAS_PV_ETAG_PRUNE 0x20
+#define I40E_AQ_VSI_CAS_PV_ACCEPT_HOST_TAG 0x40
+ u8 cas_pv_reserved;
+ /* queue mapping section */
+ __le16 mapping_flags;
+#define I40E_AQ_VSI_QUE_MAP_CONTIG 0x0
+#define I40E_AQ_VSI_QUE_MAP_NONCONTIG 0x1
+ __le16 queue_mapping[16];
+#define I40E_AQ_VSI_QUEUE_SHIFT 0x0
+#define I40E_AQ_VSI_QUEUE_MASK (0x7FF << I40E_AQ_VSI_QUEUE_SHIFT)
+ __le16 tc_mapping[8];
+#define I40E_AQ_VSI_TC_QUE_OFFSET_SHIFT 0
+#define I40E_AQ_VSI_TC_QUE_OFFSET_MASK (0x1FF << \
+ I40E_AQ_VSI_TC_QUE_OFFSET_SHIFT)
+#define I40E_AQ_VSI_TC_QUE_NUMBER_SHIFT 9
+#define I40E_AQ_VSI_TC_QUE_NUMBER_MASK (0x7 << \
+ I40E_AQ_VSI_TC_QUE_NUMBER_SHIFT)
+ /* queueing option section */
+ u8 queueing_opt_flags;
+#define I40E_AQ_VSI_QUE_OPT_TCP_ENA 0x10
+#define I40E_AQ_VSI_QUE_OPT_FCOE_ENA 0x20
+ u8 queueing_opt_reserved[3];
+ /* scheduler section */
+ u8 up_enable_bits;
+ u8 sched_reserved;
+ /* outer up section */
+ __le32 outer_up_table; /* same structure and defines as ingress table */
+ u8 cmd_reserved[8];
+ /* last 32 bytes are written by FW */
+ __le16 qs_handle[8];
+#define I40E_AQ_VSI_QS_HANDLE_INVALID 0xFFFF
+ __le16 stat_counter_idx;
+ __le16 sched_id;
+ u8 resp_reserved[12];
+};
+
+I40E_CHECK_STRUCT_LEN(128, i40e_aqc_vsi_properties_data);
+
+/* Add Port Virtualizer (direct 0x0220)
+ * also used for update PV (direct 0x0221) but only flags are used
+ * (IS_CTRL_PORT only works on add PV)
+ */
+struct i40e_aqc_add_update_pv {
+ __le16 command_flags;
+#define I40E_AQC_PV_FLAG_PV_TYPE 0x1
+#define I40E_AQC_PV_FLAG_FWD_UNKNOWN_STAG_EN 0x2
+#define I40E_AQC_PV_FLAG_FWD_UNKNOWN_ETAG_EN 0x4
+#define I40E_AQC_PV_FLAG_IS_CTRL_PORT 0x8
+ __le16 uplink_seid;
+ __le16 connected_seid;
+ u8 reserved[10];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_add_update_pv);
+
+struct i40e_aqc_add_update_pv_completion {
+ /* reserved for update; for add also encodes error if rc == ENOSPC */
+ __le16 pv_seid;
+#define I40E_AQC_PV_ERR_FLAG_NO_PV 0x1
+#define I40E_AQC_PV_ERR_FLAG_NO_SCHED 0x2
+#define I40E_AQC_PV_ERR_FLAG_NO_COUNTER 0x4
+#define I40E_AQC_PV_ERR_FLAG_NO_ENTRY 0x8
+ u8 reserved[14];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_add_update_pv_completion);
+
+/* Get PV Params (direct 0x0222)
+ * uses i40e_aqc_switch_seid for the descriptor
+ */
+
+struct i40e_aqc_get_pv_params_completion {
+ __le16 seid;
+ __le16 default_stag;
+ __le16 pv_flags; /* same flags as add_pv */
+#define I40E_AQC_GET_PV_PV_TYPE 0x1
+#define I40E_AQC_GET_PV_FRWD_UNKNOWN_STAG 0x2
+#define I40E_AQC_GET_PV_FRWD_UNKNOWN_ETAG 0x4
+ u8 reserved[8];
+ __le16 default_port_seid;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_get_pv_params_completion);
+
+/* Add VEB (direct 0x0230) */
+struct i40e_aqc_add_veb {
+ __le16 uplink_seid;
+ __le16 downlink_seid;
+ __le16 veb_flags;
+#define I40E_AQC_ADD_VEB_FLOATING 0x1
+#define I40E_AQC_ADD_VEB_PORT_TYPE_SHIFT 1
+#define I40E_AQC_ADD_VEB_PORT_TYPE_MASK (0x3 << \
+ I40E_AQC_ADD_VEB_PORT_TYPE_SHIFT)
+#define I40E_AQC_ADD_VEB_PORT_TYPE_DEFAULT 0x2
+#define I40E_AQC_ADD_VEB_PORT_TYPE_DATA 0x4
+#define I40E_AQC_ADD_VEB_ENABLE_L2_FILTER 0x8
+ u8 enable_tcs;
+ u8 reserved[9];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_add_veb);
+
+struct i40e_aqc_add_veb_completion {
+ u8 reserved[6];
+ __le16 switch_seid;
+ /* also encodes error if rc == ENOSPC; codes are the same as add_pv */
+ __le16 veb_seid;
+#define I40E_AQC_VEB_ERR_FLAG_NO_VEB 0x1
+#define I40E_AQC_VEB_ERR_FLAG_NO_SCHED 0x2
+#define I40E_AQC_VEB_ERR_FLAG_NO_COUNTER 0x4
+#define I40E_AQC_VEB_ERR_FLAG_NO_ENTRY 0x8
+ __le16 statistic_index;
+ __le16 vebs_used;
+ __le16 vebs_free;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_add_veb_completion);
+
+/* Get VEB Parameters (direct 0x0232)
+ * uses i40e_aqc_switch_seid for the descriptor
+ */
+struct i40e_aqc_get_veb_parameters_completion {
+ __le16 seid;
+ __le16 switch_id;
+ __le16 veb_flags; /* only the first/last flags from 0x0230 is valid */
+ __le16 statistic_index;
+ __le16 vebs_used;
+ __le16 vebs_free;
+ u8 reserved[4];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_get_veb_parameters_completion);
+
+/* Delete Element (direct 0x0243)
+ * uses the generic i40e_aqc_switch_seid
+ */
+
+/* Add MAC-VLAN (indirect 0x0250) */
+
+/* used for the command for most vlan commands */
+struct i40e_aqc_macvlan {
+ __le16 num_addresses;
+ __le16 seid[3];
+#define I40E_AQC_MACVLAN_CMD_SEID_NUM_SHIFT 0
+#define I40E_AQC_MACVLAN_CMD_SEID_NUM_MASK (0x3FF << \
+ I40E_AQC_MACVLAN_CMD_SEID_NUM_SHIFT)
+#define I40E_AQC_MACVLAN_CMD_SEID_VALID 0x8000
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_macvlan);
+
+/* indirect data for command and response */
+struct i40e_aqc_add_macvlan_element_data {
+ u8 mac_addr[6];
+ __le16 vlan_tag;
+ __le16 flags;
+#define I40E_AQC_MACVLAN_ADD_PERFECT_MATCH 0x0001
+#define I40E_AQC_MACVLAN_ADD_HASH_MATCH 0x0002
+#define I40E_AQC_MACVLAN_ADD_IGNORE_VLAN 0x0004
+#define I40E_AQC_MACVLAN_ADD_TO_QUEUE 0x0008
+ __le16 queue_number;
+#define I40E_AQC_MACVLAN_CMD_QUEUE_SHIFT 0
+#define I40E_AQC_MACVLAN_CMD_QUEUE_MASK (0x7FF << \
+ I40E_AQC_MACVLAN_CMD_SEID_NUM_SHIFT)
+ /* response section */
+ u8 match_method;
+#define I40E_AQC_MM_PERFECT_MATCH 0x01
+#define I40E_AQC_MM_HASH_MATCH 0x02
+#define I40E_AQC_MM_ERR_NO_RES 0xFF
+ u8 reserved1[3];
+};
+
+struct i40e_aqc_add_remove_macvlan_completion {
+ __le16 perfect_mac_used;
+ __le16 perfect_mac_free;
+ __le16 unicast_hash_free;
+ __le16 multicast_hash_free;
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_macvlan_completion);
+
+/* Remove MAC-VLAN (indirect 0x0251)
+ * uses i40e_aqc_macvlan for the descriptor
+ * data points to an array of num_addresses of elements
+ */
+
+struct i40e_aqc_remove_macvlan_element_data {
+ u8 mac_addr[6];
+ __le16 vlan_tag;
+ u8 flags;
+#define I40E_AQC_MACVLAN_DEL_PERFECT_MATCH 0x01
+#define I40E_AQC_MACVLAN_DEL_HASH_MATCH 0x02
+#define I40E_AQC_MACVLAN_DEL_IGNORE_VLAN 0x08
+#define I40E_AQC_MACVLAN_DEL_ALL_VSIS 0x10
+ u8 reserved[3];
+ /* reply section */
+ u8 error_code;
+#define I40E_AQC_REMOVE_MACVLAN_SUCCESS 0x0
+#define I40E_AQC_REMOVE_MACVLAN_FAIL 0xFF
+ u8 reply_reserved[3];
+};
+
+/* Add VLAN (indirect 0x0252)
+ * Remove VLAN (indirect 0x0253)
+ * use the generic i40e_aqc_macvlan for the command
+ */
+struct i40e_aqc_add_remove_vlan_element_data {
+ __le16 vlan_tag;
+ u8 vlan_flags;
+/* flags for add VLAN */
+#define I40E_AQC_ADD_VLAN_LOCAL 0x1
+#define I40E_AQC_ADD_PVLAN_TYPE_SHIFT 1
+#define I40E_AQC_ADD_PVLAN_TYPE_MASK (0x3 << \
+ I40E_AQC_ADD_PVLAN_TYPE_SHIFT)
+#define I40E_AQC_ADD_PVLAN_TYPE_REGULAR 0x0
+#define I40E_AQC_ADD_PVLAN_TYPE_PRIMARY 0x2
+#define I40E_AQC_ADD_PVLAN_TYPE_SECONDARY 0x4
+#define I40E_AQC_VLAN_PTYPE_SHIFT 3
+#define I40E_AQC_VLAN_PTYPE_MASK (0x3 << I40E_AQC_VLAN_PTYPE_SHIFT)
+#define I40E_AQC_VLAN_PTYPE_REGULAR_VSI 0x0
+#define I40E_AQC_VLAN_PTYPE_PROMISC_VSI 0x8
+#define I40E_AQC_VLAN_PTYPE_COMMUNITY_VSI 0x10
+#define I40E_AQC_VLAN_PTYPE_ISOLATED_VSI 0x18
+/* flags for remove VLAN */
+#define I40E_AQC_REMOVE_VLAN_ALL 0x1
+ u8 reserved;
+ u8 result;
+/* flags for add VLAN */
+#define I40E_AQC_ADD_VLAN_SUCCESS 0x0
+#define I40E_AQC_ADD_VLAN_FAIL_REQUEST 0xFE
+#define I40E_AQC_ADD_VLAN_FAIL_RESOURCE 0xFF
+/* flags for remove VLAN */
+#define I40E_AQC_REMOVE_VLAN_SUCCESS 0x0
+#define I40E_AQC_REMOVE_VLAN_FAIL 0xFF
+ u8 reserved1[3];
+};
+
+struct i40e_aqc_add_remove_vlan_completion {
+ u8 reserved[4];
+ __le16 vlans_used;
+ __le16 vlans_free;
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+/* Set VSI Promiscuous Modes (direct 0x0254) */
+struct i40e_aqc_set_vsi_promiscuous_modes {
+ __le16 promiscuous_flags;
+ __le16 valid_flags;
+/* flags used for both fields above */
+#define I40E_AQC_SET_VSI_PROMISC_UNICAST 0x01
+#define I40E_AQC_SET_VSI_PROMISC_MULTICAST 0x02
+#define I40E_AQC_SET_VSI_PROMISC_BROADCAST 0x04
+#define I40E_AQC_SET_VSI_DEFAULT 0x08
+#define I40E_AQC_SET_VSI_PROMISC_VLAN 0x10
+ __le16 seid;
+#define I40E_AQC_VSI_PROM_CMD_SEID_MASK 0x3FF
+ u8 reserved[10];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_set_vsi_promiscuous_modes);
+
+/* Add S/E-tag command (direct 0x0255)
+ * Uses generic i40e_aqc_add_remove_tag_completion for completion
+ */
+struct i40e_aqc_add_tag {
+ __le16 flags;
+#define I40E_AQC_ADD_TAG_FLAG_TO_QUEUE 0x0001
+ __le16 seid;
+#define I40E_AQC_ADD_TAG_CMD_SEID_NUM_SHIFT 0
+#define I40E_AQC_ADD_TAG_CMD_SEID_NUM_MASK (0x3FF << \
+ I40E_AQC_ADD_TAG_CMD_SEID_NUM_SHIFT)
+ __le16 tag;
+ __le16 queue_number;
+ u8 reserved[8];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_add_tag);
+
+struct i40e_aqc_add_remove_tag_completion {
+ u8 reserved[12];
+ __le16 tags_used;
+ __le16 tags_free;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_tag_completion);
+
+/* Remove S/E-tag command (direct 0x0256)
+ * Uses generic i40e_aqc_add_remove_tag_completion for completion
+ */
+struct i40e_aqc_remove_tag {
+ __le16 seid;
+#define I40E_AQC_REMOVE_TAG_CMD_SEID_NUM_SHIFT 0
+#define I40E_AQC_REMOVE_TAG_CMD_SEID_NUM_MASK (0x3FF << \
+ I40E_AQC_REMOVE_TAG_CMD_SEID_NUM_SHIFT)
+ __le16 tag;
+ u8 reserved[12];
+};
+
+/* Add multicast E-Tag (direct 0x0257)
+ * del multicast E-Tag (direct 0x0258) only uses pv_seid and etag fields
+ * and no external data
+ */
+struct i40e_aqc_add_remove_mcast_etag {
+ __le16 pv_seid;
+ __le16 etag;
+ u8 num_unicast_etags;
+ u8 reserved[3];
+ __le32 addr_high; /* address of array of 2-byte s-tags */
+ __le32 addr_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_mcast_etag);
+
+struct i40e_aqc_add_remove_mcast_etag_completion {
+ u8 reserved[4];
+ __le16 mcast_etags_used;
+ __le16 mcast_etags_free;
+ __le32 addr_high;
+ __le32 addr_low;
+
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_mcast_etag_completion);
+
+/* Update S/E-Tag (direct 0x0259) */
+struct i40e_aqc_update_tag {
+ __le16 seid;
+#define I40E_AQC_UPDATE_TAG_CMD_SEID_NUM_SHIFT 0
+#define I40E_AQC_UPDATE_TAG_CMD_SEID_NUM_MASK (0x3FF << \
+ I40E_AQC_UPDATE_TAG_CMD_SEID_NUM_SHIFT)
+ __le16 old_tag;
+ __le16 new_tag;
+ u8 reserved[10];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_update_tag);
+
+struct i40e_aqc_update_tag_completion {
+ u8 reserved[12];
+ __le16 tags_used;
+ __le16 tags_free;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_update_tag_completion);
+
+/* Add Control Packet filter (direct 0x025A)
+ * Remove Control Packet filter (direct 0x025B)
+ * uses the i40e_aqc_add_oveb_cloud,
+ * and the generic direct completion structure
+ */
+struct i40e_aqc_add_remove_control_packet_filter {
+ u8 mac[6];
+ __le16 etype;
+ __le16 flags;
+#define I40E_AQC_ADD_CONTROL_PACKET_FLAGS_IGNORE_MAC 0x0001
+#define I40E_AQC_ADD_CONTROL_PACKET_FLAGS_DROP 0x0002
+#define I40E_AQC_ADD_CONTROL_PACKET_FLAGS_TO_QUEUE 0x0004
+#define I40E_AQC_ADD_CONTROL_PACKET_FLAGS_TX 0x0008
+#define I40E_AQC_ADD_CONTROL_PACKET_FLAGS_RX 0x0000
+ __le16 seid;
+#define I40E_AQC_ADD_CONTROL_PACKET_CMD_SEID_NUM_SHIFT 0
+#define I40E_AQC_ADD_CONTROL_PACKET_CMD_SEID_NUM_MASK (0x3FF << \
+ I40E_AQC_ADD_CONTROL_PACKET_CMD_SEID_NUM_SHIFT)
+ __le16 queue;
+ u8 reserved[2];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_control_packet_filter);
+
+struct i40e_aqc_add_remove_control_packet_filter_completion {
+ __le16 mac_etype_used;
+ __le16 etype_used;
+ __le16 mac_etype_free;
+ __le16 etype_free;
+ u8 reserved[8];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_control_packet_filter_completion);
+
+/* Add Cloud filters (indirect 0x025C)
+ * Remove Cloud filters (indirect 0x025D)
+ * uses the i40e_aqc_add_remove_cloud_filters,
+ * and the generic indirect completion structure
+ */
+struct i40e_aqc_add_remove_cloud_filters {
+ u8 num_filters;
+ u8 reserved;
+ __le16 seid;
+#define I40E_AQC_ADD_CLOUD_CMD_SEID_NUM_SHIFT 0
+#define I40E_AQC_ADD_CLOUD_CMD_SEID_NUM_MASK (0x3FF << \
+ I40E_AQC_ADD_CLOUD_CMD_SEID_NUM_SHIFT)
+ u8 reserved2[4];
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_cloud_filters);
+
+struct i40e_aqc_add_remove_cloud_filters_element_data {
+ u8 outer_mac[6];
+ u8 inner_mac[6];
+ __le16 inner_vlan;
+ union {
+ struct {
+ u8 reserved[12];
+ u8 data[4];
+ } v4;
+ struct {
+ u8 data[16];
+ } v6;
+ } ipaddr;
+ __le16 flags;
+#define I40E_AQC_ADD_CLOUD_FILTER_SHIFT 0
+#define I40E_AQC_ADD_CLOUD_FILTER_MASK (0x3F << \
+ I40E_AQC_ADD_CLOUD_FILTER_SHIFT)
+#define I40E_AQC_ADD_CLOUD_FILTER_OIP 0x0001
+#define I40E_AQC_ADD_CLOUD_FILTER_OIP_GRE 0x0002
+#define I40E_AQC_ADD_CLOUD_FILTER_IMAC_IVLAN 0x0003
+#define I40E_AQC_ADD_CLOUD_FILTER_IMAC_IVLAN_GRE 0x0004
+#define I40E_AQC_ADD_CLOUD_FILTER_IMAC_TEN_ID 0x0006
+#define I40E_AQC_ADD_CLOUD_FILTER_IMAC_IVLAN_VNL 0x0007
+/* 0x0008 reserved */
+#define I40E_AQC_ADD_CLOUD_FILTER_OMAC 0x0009
+#define I40E_AQC_ADD_CLOUD_FILTER_IMAC 0x000A
+#define I40E_AQC_ADD_CLOUD_FLAGS_TO_QUEUE 0x0080
+#define I40E_AQC_ADD_CLOUD_VNK_SHIFT 6
+#define I40E_AQC_ADD_CLOUD_VNK_MASK 0x00C0
+#define I40E_AQC_ADD_CLOUD_FLAGS_IPV4 0
+#define I40E_AQC_ADD_CLOUD_FLAGS_IPV6 0x0100
+ __le32 key_low;
+ __le32 key_high;
+ __le16 queue_number;
+#define I40E_AQC_ADD_CLOUD_QUEUE_SHIFT 0
+#define I40E_AQC_ADD_CLOUD_QUEUE_MASK (0x3F << \
+ I40E_AQC_ADD_CLOUD_QUEUE_SHIFT)
+ u8 reserved[14];
+ /* response section */
+ u8 allocation_result;
+#define I40E_AQC_ADD_CLOUD_FILTER_SUCCESS 0x0
+#define I40E_AQC_ADD_CLOUD_FILTER_FAIL 0xFF
+ u8 response_reserved[7];
+};
+
+struct i40e_aqc_remove_cloud_filters_completion {
+ __le16 perfect_ovlan_used;
+ __le16 perfect_ovlan_free;
+ __le16 vlan_used;
+ __le16 vlan_free;
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_remove_cloud_filters_completion);
+
+/* Add Mirror Rule (indirect or direct 0x0260)
+ * Delete Mirror Rule (indirect or direct 0x0261)
+ * note: some rule types (4,5) do not use an external buffer.
+ * take care to set the flags correctly.
+ */
+struct i40e_aqc_add_delete_mirror_rule {
+ __le16 seid;
+ __le16 rule_type;
+#define I40E_AQC_MIRROR_RULE_TYPE_SHIFT 0
+#define I40E_AQC_MIRROR_RULE_TYPE_MASK (0x7 << \
+ I40E_AQC_MIRROR_RULE_TYPE_SHIFT)
+#define I40E_AQC_MIRROR_RULE_TYPE_VPORT_INGRESS 1
+#define I40E_AQC_MIRROR_RULE_TYPE_VPORT_EGRESS 2
+#define I40E_AQC_MIRROR_RULE_TYPE_VLAN 3
+#define I40E_AQC_MIRROR_RULE_TYPE_ALL_INGRESS 4
+#define I40E_AQC_MIRROR_RULE_TYPE_ALL_EGRESS 5
+ __le16 num_entries;
+ __le16 destination; /* VSI for add, rule id for delete */
+ __le32 addr_high; /* address of array of 2-byte VSI or VLAN ids */
+ __le32 addr_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_add_delete_mirror_rule);
+
+struct i40e_aqc_add_delete_mirror_rule_completion {
+ u8 reserved[2];
+ __le16 rule_id; /* only used on add */
+ __le16 mirror_rules_used;
+ __le16 mirror_rules_free;
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_add_delete_mirror_rule_completion);
+
+/* Set Storm Control Configuration (direct 0x0280)
+ * Get Storm Control Configuration (direct 0x0281)
+ * the command and response use the same descriptor structure
+ */
+struct i40e_aqc_set_get_storm_control_config {
+ __le32 broadcast_threshold;
+ __le32 multicast_threshold;
+ __le32 control_flags;
+#define I40E_AQC_STORM_CONTROL_MDIPW 0x01
+#define I40E_AQC_STORM_CONTROL_MDICW 0x02
+#define I40E_AQC_STORM_CONTROL_BDIPW 0x04
+#define I40E_AQC_STORM_CONTROL_BDICW 0x08
+#define I40E_AQC_STORM_CONTROL_BIDU 0x10
+#define I40E_AQC_STORM_CONTROL_INTERVAL_SHIFT 8
+#define I40E_AQC_STORM_CONTROL_INTERVAL_MASK (0x3FF << \
+ I40E_AQC_STORM_CONTROL_INTERVAL_SHIFT)
+ u8 reserved[4];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_set_get_storm_control_config);
+
+/* DCB 0x03xx*/
+
+/* PFC Ignore (direct 0x0301)
+ * the command and response use the same descriptor structure
+ */
+struct i40e_aqc_pfc_ignore {
+ u8 tc_bitmap;
+ u8 command_flags; /* unused on response */
+#define I40E_AQC_PFC_IGNORE_SET 0x80
+#define I40E_AQC_PFC_IGNORE_CLEAR 0x0
+ u8 reserved[14];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_pfc_ignore);
+
+/* DCB Update (direct 0x0302) uses the i40e_aq_desc structure
+ * with no parameters
+ */
+
+/* TX scheduler 0x04xx */
+
+/* Almost all the indirect commands use
+ * this generic struct to pass the SEID in param0
+ */
+struct i40e_aqc_tx_sched_ind {
+ __le16 vsi_seid;
+ u8 reserved[6];
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_tx_sched_ind);
+
+/* Several commands respond with a set of queue set handles */
+struct i40e_aqc_qs_handles_resp {
+ __le16 qs_handles[8];
+};
+
+/* Configure VSI BW limits (direct 0x0400) */
+struct i40e_aqc_configure_vsi_bw_limit {
+ __le16 vsi_seid;
+ u8 reserved[2];
+ __le16 credit;
+ u8 reserved1[2];
+ u8 max_credit; /* 0-3, limit = 2^max */
+ u8 reserved2[7];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_configure_vsi_bw_limit);
+
+/* Configure VSI Bandwidth Limit per Traffic Type (indirect 0x0406)
+ * responds with i40e_aqc_qs_handles_resp
+ */
+struct i40e_aqc_configure_vsi_ets_sla_bw_data {
+ u8 tc_valid_bits;
+ u8 reserved[15];
+ __le16 tc_bw_credits[8]; /* FW writesback QS handles here */
+
+ /* 4 bits per tc 0-7, 4th bit is reserved, limit = 2^max */
+ __le16 tc_bw_max[2];
+ u8 reserved1[28];
+};
+
+/* Configure VSI Bandwidth Allocation per Traffic Type (indirect 0x0407)
+ * responds with i40e_aqc_qs_handles_resp
+ */
+struct i40e_aqc_configure_vsi_tc_bw_data {
+ u8 tc_valid_bits;
+ u8 reserved[3];
+ u8 tc_bw_credits[8];
+ u8 reserved1[4];
+ __le16 qs_handles[8];
+};
+
+/* Query vsi bw configuration (indirect 0x0408) */
+struct i40e_aqc_query_vsi_bw_config_resp {
+ u8 tc_valid_bits;
+ u8 tc_suspended_bits;
+ u8 reserved[14];
+ __le16 qs_handles[8];
+ u8 reserved1[4];
+ __le16 port_bw_limit;
+ u8 reserved2[2];
+ u8 max_bw; /* 0-3, limit = 2^max */
+ u8 reserved3[23];
+};
+
+/* Query VSI Bandwidth Allocation per Traffic Type (indirect 0x040A) */
+struct i40e_aqc_query_vsi_ets_sla_config_resp {
+ u8 tc_valid_bits;
+ u8 reserved[3];
+ u8 share_credits[8];
+ __le16 credits[8];
+
+ /* 4 bits per tc 0-7, 4th bit is reserved, limit = 2^max */
+ __le16 tc_bw_max[2];
+};
+
+/* Configure Switching Component Bandwidth Limit (direct 0x0410) */
+struct i40e_aqc_configure_switching_comp_bw_limit {
+ __le16 seid;
+ u8 reserved[2];
+ __le16 credit;
+ u8 reserved1[2];
+ u8 max_bw; /* 0-3, limit = 2^max */
+ u8 reserved2[7];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_configure_switching_comp_bw_limit);
+
+/* Enable Physical Port ETS (indirect 0x0413)
+ * Modify Physical Port ETS (indirect 0x0414)
+ * Disable Physical Port ETS (indirect 0x0415)
+ */
+struct i40e_aqc_configure_switching_comp_ets_data {
+ u8 reserved[4];
+ u8 tc_valid_bits;
+ u8 reserved1;
+ u8 tc_strict_priority_flags;
+ u8 reserved2[17];
+ u8 tc_bw_share_credits[8];
+ u8 reserved3[96];
+};
+
+/* Configure Switching Component Bandwidth Limits per Tc (indirect 0x0416) */
+struct i40e_aqc_configure_switching_comp_ets_bw_limit_data {
+ u8 tc_valid_bits;
+ u8 reserved[15];
+ __le16 tc_bw_credit[8];
+
+ /* 4 bits per tc 0-7, 4th bit is reserved, limit = 2^max */
+ __le16 tc_bw_max[2];
+ u8 reserved1[28];
+};
+
+/* Configure Switching Component Bandwidth Allocation per Tc
+ * (indirect 0x0417)
+ */
+struct i40e_aqc_configure_switching_comp_bw_config_data {
+ u8 tc_valid_bits;
+ u8 reserved[2];
+ u8 absolute_credits; /* bool */
+ u8 tc_bw_share_credits[8];
+ u8 reserved1[20];
+};
+
+/* Query Switching Component Configuration (indirect 0x0418) */
+struct i40e_aqc_query_switching_comp_ets_config_resp {
+ u8 tc_valid_bits;
+ u8 reserved[35];
+ __le16 port_bw_limit;
+ u8 reserved1[2];
+ u8 tc_bw_max; /* 0-3, limit = 2^max */
+ u8 reserved2[23];
+};
+
+/* Query PhysicalPort ETS Configuration (indirect 0x0419) */
+struct i40e_aqc_query_port_ets_config_resp {
+ u8 reserved[4];
+ u8 tc_valid_bits;
+ u8 reserved1;
+ u8 tc_strict_priority_bits;
+ u8 reserved2;
+ u8 tc_bw_share_credits[8];
+ __le16 tc_bw_limits[8];
+
+ /* 4 bits per tc 0-7, 4th bit reserved, limit = 2^max */
+ __le16 tc_bw_max[2];
+ u8 reserved3[32];
+};
+
+/* Query Switching Component Bandwidth Allocation per Traffic Type
+ * (indirect 0x041A)
+ */
+struct i40e_aqc_query_switching_comp_bw_config_resp {
+ u8 tc_valid_bits;
+ u8 reserved[2];
+ u8 absolute_credits_enable; /* bool */
+ u8 tc_bw_share_credits[8];
+ __le16 tc_bw_limits[8];
+
+ /* 4 bits per tc 0-7, 4th bit is reserved, limit = 2^max */
+ __le16 tc_bw_max[2];
+};
+
+/* Suspend/resume port TX traffic
+ * (direct 0x041B and 0x041C) uses the generic SEID struct
+ */
+
+/* Get and set the active HMC resource profile and status.
+ * (direct 0x0500) and (direct 0x0501)
+ */
+struct i40e_aq_get_set_hmc_resource_profile {
+ u8 pm_profile;
+ u8 pe_vf_enabled;
+ u8 reserved[14];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aq_get_set_hmc_resource_profile);
+
+enum i40e_aq_hmc_profile {
+ /* I40E_HMC_PROFILE_NO_CHANGE = 0, reserved */
+ I40E_HMC_PROFILE_DEFAULT = 1,
+ I40E_HMC_PROFILE_FAVOR_VF = 2,
+ I40E_HMC_PROFILE_EQUAL = 3,
+};
+
+#define I40E_AQ_GET_HMC_RESOURCE_PROFILE_PM_MASK 0xF
+#define I40E_AQ_GET_HMC_RESOURCE_PROFILE_COUNT_MASK 0x3F
+
+/* Get PHY Abilities (indirect 0x0600) uses the generic indirect struct */
+
+/* set in param0 for get phy abilities to report qualified modules */
+#define I40E_AQ_PHY_REPORT_QUALIFIED_MODULES 0x0001
+#define I40E_AQ_PHY_REPORT_INITIAL_VALUES 0x0002
+
+enum i40e_aq_phy_type {
+ I40E_PHY_TYPE_SGMII = 0x0,
+ I40E_PHY_TYPE_1000BASE_KX = 0x1,
+ I40E_PHY_TYPE_10GBASE_KX4 = 0x2,
+ I40E_PHY_TYPE_10GBASE_KR = 0x3,
+ I40E_PHY_TYPE_40GBASE_KR4 = 0x4,
+ I40E_PHY_TYPE_XAUI = 0x5,
+ I40E_PHY_TYPE_XFI = 0x6,
+ I40E_PHY_TYPE_SFI = 0x7,
+ I40E_PHY_TYPE_XLAUI = 0x8,
+ I40E_PHY_TYPE_XLPPI = 0x9,
+ I40E_PHY_TYPE_40GBASE_CR4_CU = 0xA,
+ I40E_PHY_TYPE_10GBASE_CR1_CU = 0xB,
+ I40E_PHY_TYPE_100BASE_TX = 0x11,
+ I40E_PHY_TYPE_1000BASE_T = 0x12,
+ I40E_PHY_TYPE_10GBASE_T = 0x13,
+ I40E_PHY_TYPE_10GBASE_SR = 0x14,
+ I40E_PHY_TYPE_10GBASE_LR = 0x15,
+ I40E_PHY_TYPE_10GBASE_SFPP_CU = 0x16,
+ I40E_PHY_TYPE_10GBASE_CR1 = 0x17,
+ I40E_PHY_TYPE_40GBASE_CR4 = 0x18,
+ I40E_PHY_TYPE_40GBASE_SR4 = 0x19,
+ I40E_PHY_TYPE_40GBASE_LR4 = 0x1A,
+ I40E_PHY_TYPE_20GBASE_KR2 = 0x1B,
+ I40E_PHY_TYPE_MAX
+};
+
+#define I40E_LINK_SPEED_100MB_SHIFT 0x1
+#define I40E_LINK_SPEED_1000MB_SHIFT 0x2
+#define I40E_LINK_SPEED_10GB_SHIFT 0x3
+#define I40E_LINK_SPEED_40GB_SHIFT 0x4
+#define I40E_LINK_SPEED_20GB_SHIFT 0x5
+
+enum i40e_aq_link_speed {
+ I40E_LINK_SPEED_UNKNOWN = 0,
+ I40E_LINK_SPEED_100MB = (1 << I40E_LINK_SPEED_100MB_SHIFT),
+ I40E_LINK_SPEED_1GB = (1 << I40E_LINK_SPEED_1000MB_SHIFT),
+ I40E_LINK_SPEED_10GB = (1 << I40E_LINK_SPEED_10GB_SHIFT),
+ I40E_LINK_SPEED_40GB = (1 << I40E_LINK_SPEED_40GB_SHIFT),
+ I40E_LINK_SPEED_20GB = (1 << I40E_LINK_SPEED_20GB_SHIFT)
+};
+
+struct i40e_aqc_module_desc {
+ u8 oui[3];
+ u8 reserved1;
+ u8 part_number[16];
+ u8 revision[4];
+ u8 reserved2[8];
+};
+
+struct i40e_aq_get_phy_abilities_resp {
+ __le32 phy_type; /* bitmap using the above enum for offsets */
+ u8 link_speed; /* bitmap using the above enum */
+ u8 abilities;
+#define I40E_AQ_PHY_FLAG_PAUSE_TX 0x01
+#define I40E_AQ_PHY_FLAG_PAUSE_RX 0x02
+#define I40E_AQ_PHY_FLAG_LOW_POWER 0x04
+#define I40E_AQ_PHY_FLAG_AN_SHIFT 3
+#define I40E_AQ_PHY_FLAG_AN_MASK (0x3 << I40E_AQ_PHY_FLAG_AN_SHIFT)
+#define I40E_AQ_PHY_FLAG_AN_OFF 0x00 /* link forced on */
+#define I40E_AQ_PHY_FLAG_AN_OFF_LINK_DOWN 0x01
+#define I40E_AQ_PHY_FLAG_AN_ON 0x02
+#define I40E_AQ_PHY_FLAG_MODULE_QUAL 0x20
+ __le16 eee_capability;
+#define I40E_AQ_EEE_100BASE_TX 0x0002
+#define I40E_AQ_EEE_1000BASE_T 0x0004
+#define I40E_AQ_EEE_10GBASE_T 0x0008
+#define I40E_AQ_EEE_1000BASE_KX 0x0010
+#define I40E_AQ_EEE_10GBASE_KX4 0x0020
+#define I40E_AQ_EEE_10GBASE_KR 0x0040
+ __le32 eeer_val;
+ u8 d3_lpan;
+#define I40E_AQ_SET_PHY_D3_LPAN_ENA 0x01
+ u8 reserved[3];
+ u8 phy_id[4];
+ u8 module_type[3];
+ u8 qualified_module_count;
+#define I40E_AQ_PHY_MAX_QMS 16
+ struct i40e_aqc_module_desc qualified_module[I40E_AQ_PHY_MAX_QMS];
+};
+
+/* Set PHY Config (direct 0x0601) */
+struct i40e_aq_set_phy_config { /* same bits as above in all */
+ __le32 phy_type;
+ u8 link_speed;
+ u8 abilities;
+ __le16 eee_capability;
+ __le32 eeer;
+ u8 low_power_ctrl;
+ u8 reserved[3];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aq_set_phy_config);
+
+/* Set MAC Config command data structure (direct 0x0603) */
+struct i40e_aq_set_mac_config {
+ __le16 max_frame_size;
+ u8 params;
+#define I40E_AQ_SET_MAC_CONFIG_CRC_EN 0x04
+#define I40E_AQ_SET_MAC_CONFIG_PACING_MASK 0x78
+#define I40E_AQ_SET_MAC_CONFIG_PACING_SHIFT 3
+#define I40E_AQ_SET_MAC_CONFIG_PACING_NONE 0x0
+#define I40E_AQ_SET_MAC_CONFIG_PACING_1B_13TX 0xF
+#define I40E_AQ_SET_MAC_CONFIG_PACING_1DW_9TX 0x9
+#define I40E_AQ_SET_MAC_CONFIG_PACING_1DW_4TX 0x8
+#define I40E_AQ_SET_MAC_CONFIG_PACING_3DW_7TX 0x7
+#define I40E_AQ_SET_MAC_CONFIG_PACING_2DW_3TX 0x6
+#define I40E_AQ_SET_MAC_CONFIG_PACING_1DW_1TX 0x5
+#define I40E_AQ_SET_MAC_CONFIG_PACING_3DW_2TX 0x4
+#define I40E_AQ_SET_MAC_CONFIG_PACING_7DW_3TX 0x3
+#define I40E_AQ_SET_MAC_CONFIG_PACING_4DW_1TX 0x2
+#define I40E_AQ_SET_MAC_CONFIG_PACING_9DW_1TX 0x1
+ u8 tx_timer_priority; /* bitmap */
+ __le16 tx_timer_value;
+ __le16 fc_refresh_threshold;
+ u8 reserved[8];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aq_set_mac_config);
+
+/* Restart Auto-Negotiation (direct 0x605) */
+struct i40e_aqc_set_link_restart_an {
+ u8 command;
+#define I40E_AQ_PHY_RESTART_AN 0x02
+#define I40E_AQ_PHY_LINK_ENABLE 0x04
+ u8 reserved[15];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_set_link_restart_an);
+
+/* Get Link Status cmd & response data structure (direct 0x0607) */
+struct i40e_aqc_get_link_status {
+ __le16 command_flags; /* only field set on command */
+#define I40E_AQ_LSE_MASK 0x3
+#define I40E_AQ_LSE_NOP 0x0
+#define I40E_AQ_LSE_DISABLE 0x2
+#define I40E_AQ_LSE_ENABLE 0x3
+/* only response uses this flag */
+#define I40E_AQ_LSE_IS_ENABLED 0x1
+ u8 phy_type; /* i40e_aq_phy_type */
+ u8 link_speed; /* i40e_aq_link_speed */
+ u8 link_info;
+#define I40E_AQ_LINK_UP 0x01
+#define I40E_AQ_LINK_FAULT 0x02
+#define I40E_AQ_LINK_FAULT_TX 0x04
+#define I40E_AQ_LINK_FAULT_RX 0x08
+#define I40E_AQ_LINK_FAULT_REMOTE 0x10
+#define I40E_AQ_MEDIA_AVAILABLE 0x40
+#define I40E_AQ_SIGNAL_DETECT 0x80
+ u8 an_info;
+#define I40E_AQ_AN_COMPLETED 0x01
+#define I40E_AQ_LP_AN_ABILITY 0x02
+#define I40E_AQ_PD_FAULT 0x04
+#define I40E_AQ_FEC_EN 0x08
+#define I40E_AQ_PHY_LOW_POWER 0x10
+#define I40E_AQ_LINK_PAUSE_TX 0x20
+#define I40E_AQ_LINK_PAUSE_RX 0x40
+#define I40E_AQ_QUALIFIED_MODULE 0x80
+ u8 ext_info;
+#define I40E_AQ_LINK_PHY_TEMP_ALARM 0x01
+#define I40E_AQ_LINK_XCESSIVE_ERRORS 0x02
+#define I40E_AQ_LINK_TX_SHIFT 0x02
+#define I40E_AQ_LINK_TX_MASK (0x03 << I40E_AQ_LINK_TX_SHIFT)
+#define I40E_AQ_LINK_TX_ACTIVE 0x00
+#define I40E_AQ_LINK_TX_DRAINED 0x01
+#define I40E_AQ_LINK_TX_FLUSHED 0x03
+ u8 loopback; /* use defines from i40e_aqc_set_lb_mode */
+ __le16 max_frame_size;
+ u8 config;
+#define I40E_AQ_CONFIG_CRC_ENA 0x04
+#define I40E_AQ_CONFIG_PACING_MASK 0x78
+ u8 reserved[5];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_get_link_status);
+
+/* Set event mask command (direct 0x613) */
+struct i40e_aqc_set_phy_int_mask {
+ u8 reserved[8];
+ __le16 event_mask;
+#define I40E_AQ_EVENT_LINK_UPDOWN 0x0002
+#define I40E_AQ_EVENT_MEDIA_NA 0x0004
+#define I40E_AQ_EVENT_LINK_FAULT 0x0008
+#define I40E_AQ_EVENT_PHY_TEMP_ALARM 0x0010
+#define I40E_AQ_EVENT_EXCESSIVE_ERRORS 0x0020
+#define I40E_AQ_EVENT_SIGNAL_DETECT 0x0040
+#define I40E_AQ_EVENT_AN_COMPLETED 0x0080
+#define I40E_AQ_EVENT_MODULE_QUAL_FAIL 0x0100
+#define I40E_AQ_EVENT_PORT_TX_SUSPENDED 0x0200
+ u8 reserved1[6];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_set_phy_int_mask);
+
+/* Get Local AN advt register (direct 0x0614)
+ * Set Local AN advt register (direct 0x0615)
+ * Get Link Partner AN advt register (direct 0x0616)
+ */
+struct i40e_aqc_an_advt_reg {
+ __le32 local_an_reg0;
+ __le16 local_an_reg1;
+ u8 reserved[10];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_an_advt_reg);
+
+/* Set Loopback mode (0x0618) */
+struct i40e_aqc_set_lb_mode {
+ __le16 lb_mode;
+#define I40E_AQ_LB_PHY_LOCAL 0x01
+#define I40E_AQ_LB_PHY_REMOTE 0x02
+#define I40E_AQ_LB_MAC_LOCAL 0x04
+ u8 reserved[14];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_set_lb_mode);
+
+/* Set PHY Reset command (0x0622) */
+struct i40e_aqc_set_phy_reset {
+ u8 reset_flags;
+#define I40E_AQ_PHY_RESET_REQUEST 0x02
+ u8 reserved[15];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_set_phy_reset);
+
+enum i40e_aq_phy_reg_type {
+ I40E_AQC_PHY_REG_INTERNAL = 0x1,
+ I40E_AQC_PHY_REG_EXERNAL_BASET = 0x2,
+ I40E_AQC_PHY_REG_EXERNAL_MODULE = 0x3
+};
+
+/* NVM Read command (indirect 0x0701)
+ * NVM Erase commands (direct 0x0702)
+ * NVM Update commands (indirect 0x0703)
+ */
+struct i40e_aqc_nvm_update {
+ u8 command_flags;
+#define I40E_AQ_NVM_LAST_CMD 0x01
+#define I40E_AQ_NVM_FLASH_ONLY 0x80
+ u8 module_pointer;
+ __le16 length;
+ __le32 offset;
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_nvm_update);
+
+/* Send to PF command (indirect 0x0801) id is only used by PF
+ * Send to VF command (indirect 0x0802) id is only used by PF
+ * Send to Peer PF command (indirect 0x0803)
+ */
+struct i40e_aqc_pf_vf_message {
+ __le32 id;
+ u8 reserved[4];
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_pf_vf_message);
+
+/* Alternate structure */
+
+/* Direct write (direct 0x0900)
+ * Direct read (direct 0x0902)
+ */
+struct i40e_aqc_alternate_write {
+ __le32 address0;
+ __le32 data0;
+ __le32 address1;
+ __le32 data1;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_alternate_write);
+
+/* Indirect write (indirect 0x0901)
+ * Indirect read (indirect 0x0903)
+ */
+
+struct i40e_aqc_alternate_ind_write {
+ __le32 address;
+ __le32 length;
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_alternate_ind_write);
+
+/* Done alternate write (direct 0x0904)
+ * uses i40e_aq_desc
+ */
+struct i40e_aqc_alternate_write_done {
+ __le16 cmd_flags;
+#define I40E_AQ_ALTERNATE_MODE_BIOS_MASK 1
+#define I40E_AQ_ALTERNATE_MODE_BIOS_LEGACY 0
+#define I40E_AQ_ALTERNATE_MODE_BIOS_UEFI 1
+#define I40E_AQ_ALTERNATE_RESET_NEEDED 2
+ u8 reserved[14];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_alternate_write_done);
+
+/* Set OEM mode (direct 0x0905) */
+struct i40e_aqc_alternate_set_mode {
+ __le32 mode;
+#define I40E_AQ_ALTERNATE_MODE_NONE 0
+#define I40E_AQ_ALTERNATE_MODE_OEM 1
+ u8 reserved[12];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_alternate_set_mode);
+
+/* Clear port Alternate RAM (direct 0x0906) uses i40e_aq_desc */
+
+/* async events 0x10xx */
+
+/* Lan Queue Overflow Event (direct, 0x1001) */
+struct i40e_aqc_lan_overflow {
+ __le32 prtdcb_rupto;
+ __le32 otx_ctl;
+ u8 reserved[8];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_lan_overflow);
+
+/* Get LLDP MIB (indirect 0x0A00) */
+struct i40e_aqc_lldp_get_mib {
+ u8 type;
+ u8 reserved1;
+#define I40E_AQ_LLDP_MIB_TYPE_MASK 0x3
+#define I40E_AQ_LLDP_MIB_LOCAL 0x0
+#define I40E_AQ_LLDP_MIB_REMOTE 0x1
+#define I40E_AQ_LLDP_MIB_LOCAL_AND_REMOTE 0x2
+#define I40E_AQ_LLDP_BRIDGE_TYPE_MASK 0xC
+#define I40E_AQ_LLDP_BRIDGE_TYPE_SHIFT 0x2
+#define I40E_AQ_LLDP_BRIDGE_TYPE_NEAREST_BRIDGE 0x0
+#define I40E_AQ_LLDP_BRIDGE_TYPE_NON_TPMR 0x1
+#define I40E_AQ_LLDP_TX_SHIFT 0x4
+#define I40E_AQ_LLDP_TX_MASK (0x03 << I40E_AQ_LLDP_TX_SHIFT)
+/* TX pause flags use I40E_AQ_LINK_TX_* above */
+ __le16 local_len;
+ __le16 remote_len;
+ u8 reserved2[2];
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_get_mib);
+
+/* Configure LLDP MIB Change Event (direct 0x0A01)
+ * also used for the event (with type in the command field)
+ */
+struct i40e_aqc_lldp_update_mib {
+ u8 command;
+#define I40E_AQ_LLDP_MIB_UPDATE_ENABLE 0x0
+#define I40E_AQ_LLDP_MIB_UPDATE_DISABLE 0x1
+ u8 reserved[7];
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_update_mib);
+
+/* Add LLDP TLV (indirect 0x0A02)
+ * Delete LLDP TLV (indirect 0x0A04)
+ */
+struct i40e_aqc_lldp_add_tlv {
+ u8 type; /* only nearest bridge and non-TPMR from 0x0A00 */
+ u8 reserved1[1];
+ __le16 len;
+ u8 reserved2[4];
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_add_tlv);
+
+/* Update LLDP TLV (indirect 0x0A03) */
+struct i40e_aqc_lldp_update_tlv {
+ u8 type; /* only nearest bridge and non-TPMR from 0x0A00 */
+ u8 reserved;
+ __le16 old_len;
+ __le16 new_offset;
+ __le16 new_len;
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_update_tlv);
+
+/* Stop LLDP (direct 0x0A05) */
+struct i40e_aqc_lldp_stop {
+ u8 command;
+#define I40E_AQ_LLDP_AGENT_STOP 0x0
+#define I40E_AQ_LLDP_AGENT_SHUTDOWN 0x1
+ u8 reserved[15];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_stop);
+
+/* Start LLDP (direct 0x0A06) */
+
+struct i40e_aqc_lldp_start {
+ u8 command;
+#define I40E_AQ_LLDP_AGENT_START 0x1
+ u8 reserved[15];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_start);
+
+/* Apply MIB changes (0x0A07)
+ * uses the generic struc as it contains no data
+ */
+
+/* Add Udp Tunnel command and completion (direct 0x0B00) */
+struct i40e_aqc_add_udp_tunnel {
+ __le16 udp_port;
+ u8 header_len; /* in DWords, 1 to 15 */
+ u8 protocol_index;
+#define I40E_AQC_TUNNEL_TYPE_MAC 0x0
+#define I40E_AQC_TUNNEL_TYPE_UDP 0x1
+ u8 reserved[12];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_add_udp_tunnel);
+
+/* remove UDP Tunnel command (0x0B01) */
+struct i40e_aqc_remove_udp_tunnel {
+ u8 reserved[2];
+ u8 index; /* 0 to 15 */
+ u8 pf_filters;
+ u8 total_filters;
+ u8 reserved2[11];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_remove_udp_tunnel);
+
+struct i40e_aqc_del_udp_tunnel_completion {
+ __le16 udp_port;
+ u8 index; /* 0 to 15 */
+ u8 multiple_entries;
+ u8 tunnels_used;
+ u8 reserved;
+ u8 tunnels_free;
+ u8 reserved1[9];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_del_udp_tunnel_completion);
+
+/* tunnel key structure 0x0B10 */
+struct i40e_aqc_tunnel_key_structure {
+ __le16 key1_off;
+ __le16 key1_len;
+ __le16 key2_off;
+ __le16 key2_len;
+ __le16 flags;
+#define I40E_AQC_TUNNEL_KEY_STRUCT_OVERRIDE 0x01
+/* response flags */
+#define I40E_AQC_TUNNEL_KEY_STRUCT_SUCCESS 0x01
+#define I40E_AQC_TUNNEL_KEY_STRUCT_MODIFIED 0x02
+#define I40E_AQC_TUNNEL_KEY_STRUCT_OVERRIDDEN 0x03
+ u8 resreved[6];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_tunnel_key_structure);
+
+/* OEM mode commands (direct 0xFE0x) */
+struct i40e_aqc_oem_param_change {
+ __le32 param_type;
+#define I40E_AQ_OEM_PARAM_TYPE_PF_CTL 0
+#define I40E_AQ_OEM_PARAM_TYPE_BW_CTL 1
+#define I40E_AQ_OEM_PARAM_MAC 2
+ __le32 param_value1;
+ u8 param_value2[8];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_oem_param_change);
+
+struct i40e_aqc_oem_state_change {
+ __le32 state;
+#define I40E_AQ_OEM_STATE_LINK_DOWN 0x0
+#define I40E_AQ_OEM_STATE_LINK_UP 0x1
+ u8 reserved[12];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_oem_state_change);
+
+/* debug commands */
+
+/* get device id (0xFF00) uses the generic structure */
+
+/* set test more (0xFF01, internal) */
+
+struct i40e_acq_set_test_mode {
+ u8 mode;
+#define I40E_AQ_TEST_PARTIAL 0
+#define I40E_AQ_TEST_FULL 1
+#define I40E_AQ_TEST_NVM 2
+ u8 reserved[3];
+ u8 command;
+#define I40E_AQ_TEST_OPEN 0
+#define I40E_AQ_TEST_CLOSE 1
+#define I40E_AQ_TEST_INC 2
+ u8 reserved2[3];
+ __le32 address_high;
+ __le32 address_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_acq_set_test_mode);
+
+/* Debug Read Register command (0xFF03)
+ * Debug Write Register command (0xFF04)
+ */
+struct i40e_aqc_debug_reg_read_write {
+ __le32 reserved;
+ __le32 address;
+ __le32 value_high;
+ __le32 value_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_debug_reg_read_write);
+
+/* Scatter/gather Reg Read (indirect 0xFF05)
+ * Scatter/gather Reg Write (indirect 0xFF06)
+ */
+
+/* i40e_aq_desc is used for the command */
+struct i40e_aqc_debug_reg_sg_element_data {
+ __le32 address;
+ __le32 value;
+};
+
+/* Debug Modify register (direct 0xFF07) */
+struct i40e_aqc_debug_modify_reg {
+ __le32 address;
+ __le32 value;
+ __le32 clear_mask;
+ __le32 set_mask;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_debug_modify_reg);
+
+/* dump internal data (0xFF08, indirect) */
+
+#define I40E_AQ_CLUSTER_ID_AUX 0
+#define I40E_AQ_CLUSTER_ID_SWITCH_FLU 1
+#define I40E_AQ_CLUSTER_ID_TXSCHED 2
+#define I40E_AQ_CLUSTER_ID_HMC 3
+#define I40E_AQ_CLUSTER_ID_MAC0 4
+#define I40E_AQ_CLUSTER_ID_MAC1 5
+#define I40E_AQ_CLUSTER_ID_MAC2 6
+#define I40E_AQ_CLUSTER_ID_MAC3 7
+#define I40E_AQ_CLUSTER_ID_DCB 8
+#define I40E_AQ_CLUSTER_ID_EMP_MEM 9
+#define I40E_AQ_CLUSTER_ID_PKT_BUF 10
+
+struct i40e_aqc_debug_dump_internals {
+ u8 cluster_id;
+ u8 table_id;
+ __le16 data_size;
+ __le32 idx;
+ __le32 address_high;
+ __le32 address_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_debug_dump_internals);
+
+struct i40e_aqc_debug_modify_internals {
+ u8 cluster_id;
+ u8 cluster_specific_params[7];
+ __le32 address_high;
+ __le32 address_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_debug_modify_internals);
+
+#endif
diff --git a/drivers/net/ethernet/intel/i40e/i40e_alloc.h b/drivers/net/ethernet/intel/i40e/i40e_alloc.h
new file mode 100644
index 0000000..3b1cc21
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_alloc.h
@@ -0,0 +1,59 @@
+/*******************************************************************************
+ *
+ * Intel Ethernet Controller XL710 Family Linux Driver
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ ******************************************************************************/
+
+#ifndef _I40E_ALLOC_H_
+#define _I40E_ALLOC_H_
+
+struct i40e_hw;
+
+/* Memory allocation types */
+enum i40e_memory_type {
+ i40e_mem_arq_buf = 0, /* ARQ indirect command buffer */
+ i40e_mem_asq_buf = 1,
+ i40e_mem_atq_buf = 2, /* ATQ indirect command buffer */
+ i40e_mem_arq_ring = 3, /* ARQ descriptor ring */
+ i40e_mem_atq_ring = 4, /* ATQ descriptor ring */
+ i40e_mem_pd = 5, /* Page Descriptor */
+ i40e_mem_bp = 6, /* Backing Page - 4KB */
+ i40e_mem_bp_jumbo = 7, /* Backing Page - > 4KB */
+ i40e_mem_reserved
+};
+
+/* prototype for functions used for dynamic memory allocation */
+i40e_status i40e_allocate_dma_mem(struct i40e_hw *hw,
+ struct i40e_dma_mem *mem,
+ enum i40e_memory_type type,
+ u64 size, u32 alignment);
+i40e_status i40e_free_dma_mem(struct i40e_hw *hw,
+ struct i40e_dma_mem *mem);
+i40e_status i40e_allocate_virt_mem(struct i40e_hw *hw,
+ struct i40e_virt_mem *mem,
+ u32 size);
+i40e_status i40e_free_virt_mem(struct i40e_hw *hw,
+ struct i40e_virt_mem *mem);
+
+#endif /* _I40E_ALLOC_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
new file mode 100644
index 0000000..c21df7b
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -0,0 +1,2041 @@
+/*******************************************************************************
+ *
+ * Intel Ethernet Controller XL710 Family Linux Driver
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ ******************************************************************************/
+
+#include "i40e_type.h"
+#include "i40e_adminq.h"
+#include "i40e_prototype.h"
+#include "i40e_virtchnl.h"
+
+/**
+ * i40e_set_mac_type - Sets MAC type
+ * @hw: pointer to the HW structure
+ *
+ * This function sets the mac type of the adapter based on the
+ * vendor ID and device ID stored in the hw structure.
+ **/
+static i40e_status i40e_set_mac_type(struct i40e_hw *hw)
+{
+ i40e_status status = 0;
+
+ if (hw->vendor_id == PCI_VENDOR_ID_INTEL) {
+ switch (hw->device_id) {
+ case I40E_SFP_XL710_DEVICE_ID:
+ case I40E_SFP_X710_DEVICE_ID:
+ case I40E_QEMU_DEVICE_ID:
+ case I40E_KX_A_DEVICE_ID:
+ case I40E_KX_B_DEVICE_ID:
+ case I40E_KX_C_DEVICE_ID:
+ case I40E_KX_D_DEVICE_ID:
+ case I40E_QSFP_A_DEVICE_ID:
+ case I40E_QSFP_B_DEVICE_ID:
+ case I40E_QSFP_C_DEVICE_ID:
+ hw->mac.type = I40E_MAC_XL710;
+ break;
+ case I40E_VF_DEVICE_ID:
+ case I40E_VF_HV_DEVICE_ID:
+ hw->mac.type = I40E_MAC_VF;
+ break;
+ default:
+ hw->mac.type = I40E_MAC_GENERIC;
+ break;
+ }
+ } else {
+ status = I40E_ERR_DEVICE_NOT_SUPPORTED;
+ }
+
+ hw_dbg(hw, "i40e_set_mac_type found mac: %d, returns: %d\n",
+ hw->mac.type, status);
+ return status;
+}
+
+/**
+ * i40e_debug_aq
+ * @hw: debug mask related to admin queue
+ * @cap: pointer to adminq command descriptor
+ * @buffer: pointer to command buffer
+ *
+ * Dumps debug log about adminq command with descriptor contents.
+ **/
+void i40e_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask, void *desc,
+ void *buffer)
+{
+ struct i40e_aq_desc *aq_desc = (struct i40e_aq_desc *)desc;
+ u8 *aq_buffer = (u8 *)buffer;
+ u32 data[4];
+ u32 i = 0;
+
+ if ((!(mask & hw->debug_mask)) || (desc == NULL))
+ return;
+
+ i40e_debug(hw, mask,
+ "AQ CMD: opcode 0x%04X, flags 0x%04X, datalen 0x%04X, retval 0x%04X\n",
+ aq_desc->opcode, aq_desc->flags, aq_desc->datalen,
+ aq_desc->retval);
+ i40e_debug(hw, mask, "\tcookie (h,l) 0x%08X 0x%08X\n",
+ aq_desc->cookie_high, aq_desc->cookie_low);
+ i40e_debug(hw, mask, "\tparam (0,1) 0x%08X 0x%08X\n",
+ aq_desc->params.internal.param0,
+ aq_desc->params.internal.param1);
+ i40e_debug(hw, mask, "\taddr (h,l) 0x%08X 0x%08X\n",
+ aq_desc->params.external.addr_high,
+ aq_desc->params.external.addr_low);
+
+ if ((buffer != NULL) && (aq_desc->datalen != 0)) {
+ memset(data, 0, sizeof(data));
+ i40e_debug(hw, mask, "AQ CMD Buffer:\n");
+ for (i = 0; i < le16_to_cpu(aq_desc->datalen); i++) {
+ data[((i % 16) / 4)] |=
+ ((u32)aq_buffer[i]) << (8 * (i % 4));
+ if ((i % 16) == 15) {
+ i40e_debug(hw, mask,
+ "\t0x%04X %08X %08X %08X %08X\n",
+ i - 15, data[0], data[1], data[2],
+ data[3]);
+ memset(data, 0, sizeof(data));
+ }
+ }
+ if ((i % 16) != 0)
+ i40e_debug(hw, mask, "\t0x%04X %08X %08X %08X %08X\n",
+ i - (i % 16), data[0], data[1], data[2],
+ data[3]);
+ }
+}
+
+/**
+ * i40e_init_shared_code - Initialize the shared code
+ * @hw: pointer to hardware structure
+ *
+ * This assigns the MAC type and PHY code and inits the NVM.
+ * Does not touch the hardware. This function must be called prior to any
+ * other function in the shared code. The i40e_hw structure should be
+ * memset to 0 prior to calling this function. The following fields in
+ * hw structure should be filled in prior to calling this function:
+ * hw_addr, back, device_id, vendor_id, subsystem_device_id,
+ * subsystem_vendor_id, and revision_id
+ **/
+i40e_status i40e_init_shared_code(struct i40e_hw *hw)
+{
+ i40e_status status = 0;
+ u32 reg;
+
+ hw->phy.get_link_info = true;
+
+ /* Determine port number */
+ reg = rd32(hw, I40E_PFGEN_PORTNUM);
+ reg = ((reg & I40E_PFGEN_PORTNUM_PORT_NUM_MASK) >>
+ I40E_PFGEN_PORTNUM_PORT_NUM_SHIFT);
+ hw->port = (u8)reg;
+
+ i40e_set_mac_type(hw);
+
+ switch (hw->mac.type) {
+ case I40E_MAC_XL710:
+ break;
+ default:
+ return I40E_ERR_DEVICE_NOT_SUPPORTED;
+ break;
+ }
+
+ status = i40e_init_nvm(hw);
+ return status;
+}
+
+/**
+ * i40e_aq_mac_address_read - Retrieve the MAC addresses
+ * @hw: pointer to the hw struct
+ * @flags: a return indicator of what addresses were added to the addr store
+ * @addrs: the requestor's mac addr store
+ * @cmd_details: pointer to command details structure or NULL
+ **/
+static i40e_status i40e_aq_mac_address_read(struct i40e_hw *hw,
+ u16 *flags,
+ struct i40e_aqc_mac_address_read_data *addrs,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_mac_address_read *cmd_data =
+ (struct i40e_aqc_mac_address_read *)&desc.params.raw;
+ i40e_status status;
+
+ i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_mac_address_read);
+ desc.flags |= cpu_to_le16(I40E_AQ_FLAG_BUF);
+
+ status = i40e_asq_send_command(hw, &desc, addrs,
+ sizeof(*addrs), cmd_details);
+ *flags = le16_to_cpu(cmd_data->command_flags);
+
+ return status;
+}
+
+/**
+ * i40e_aq_mac_address_write - Change the MAC addresses
+ * @hw: pointer to the hw struct
+ * @flags: indicates which MAC to be written
+ * @mac_addr: address to write
+ * @cmd_details: pointer to command details structure or NULL
+ **/
+i40e_status i40e_aq_mac_address_write(struct i40e_hw *hw,
+ u16 flags, u8 *mac_addr,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_mac_address_write *cmd_data =
+ (struct i40e_aqc_mac_address_write *)&desc.params.raw;
+ i40e_status status;
+
+ i40e_fill_default_direct_cmd_desc(&desc,
+ i40e_aqc_opc_mac_address_write);
+ cmd_data->command_flags = cpu_to_le16(flags);
+ memcpy(&cmd_data->mac_sal, &mac_addr[0], 4);
+ memcpy(&cmd_data->mac_sah, &mac_addr[4], 2);
+
+ status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+ return status;
+}
+
+/**
+ * i40e_get_mac_addr - get MAC address
+ * @hw: pointer to the HW structure
+ * @mac_addr: pointer to MAC address
+ *
+ * Reads the adapter's MAC address from register
+ **/
+i40e_status i40e_get_mac_addr(struct i40e_hw *hw, u8 *mac_addr)
+{
+ struct i40e_aqc_mac_address_read_data addrs;
+ i40e_status status;
+ u16 flags = 0;
+
+ status = i40e_aq_mac_address_read(hw, &flags, &addrs, NULL);
+
+ if (flags & I40E_AQC_LAN_ADDR_VALID)
+ memcpy(mac_addr, &addrs.pf_lan_mac, sizeof(addrs.pf_lan_mac));
+
+ return status;
+}
+
+/**
+ * i40e_validate_mac_addr - Validate MAC address
+ * @mac_addr: pointer to MAC address
+ *
+ * Tests a MAC address to ensure it is a valid Individual Address
+ **/
+i40e_status i40e_validate_mac_addr(u8 *mac_addr)
+{
+ i40e_status status = 0;
+
+ /* Make sure it is not a multicast address */
+ if (I40E_IS_MULTICAST(mac_addr)) {
+ hw_dbg(hw, "MAC address is multicast\n");
+ status = I40E_ERR_INVALID_MAC_ADDR;
+ /* Not a broadcast address */
+ } else if (I40E_IS_BROADCAST(mac_addr)) {
+ hw_dbg(hw, "MAC address is broadcast\n");
+ status = I40E_ERR_INVALID_MAC_ADDR;
+ /* Reject the zero address */
+ } else if (mac_addr[0] == 0 && mac_addr[1] == 0 && mac_addr[2] == 0 &&
+ mac_addr[3] == 0 && mac_addr[4] == 0 && mac_addr[5] == 0) {
+ hw_dbg(hw, "MAC address is all zeros\n");
+ status = I40E_ERR_INVALID_MAC_ADDR;
+ }
+ return status;
+}
+
+/**
+ * i40e_pf_reset - Reset the PF
+ * @hw: pointer to the hardware structure
+ *
+ * Assuming someone else has triggered a global reset,
+ * assure the global reset is complete and then reset the PF
+ **/
+i40e_status i40e_pf_reset(struct i40e_hw *hw)
+{
+ u32 wait_cnt = 0;
+ u32 reg = 0;
+ u32 grst_del;
+
+ /* Poll for Global Reset steady state in case of recent GRST.
+ * The grst delay value is in 100ms units, and we'll wait a
+ * couple counts longer to be sure we don't just miss the end.
+ */
+ grst_del = rd32(hw, I40E_GLGEN_RSTCTL) & I40E_GLGEN_RSTCTL_GRSTDEL_MASK
+ >> I40E_GLGEN_RSTCTL_GRSTDEL_SHIFT;
+ for (wait_cnt = 0; wait_cnt < grst_del + 2; wait_cnt++) {
+ reg = rd32(hw, I40E_GLGEN_RSTAT);
+ if (!(reg & I40E_GLGEN_RSTAT_DEVSTATE_MASK))
+ break;
+ msleep(100);
+ }
+ if (reg & I40E_GLGEN_RSTAT_DEVSTATE_MASK) {
+ hw_dbg(hw, "Global reset polling failed to complete.\n");
+ return I40E_ERR_RESET_FAILED;
+ }
+
+ /* Determine the PF number based on the PCI fn */
+ hw->pf_id = (u8)hw->bus.func;
+
+ /* If there was a Global Reset in progress when we got here,
+ * we don't need to do the PF Reset
+ */
+ if (!wait_cnt) {
+ reg = rd32(hw, I40E_PFGEN_CTRL);
+ wr32(hw, I40E_PFGEN_CTRL,
+ (reg | I40E_PFGEN_CTRL_PFSWR_MASK));
+ for (wait_cnt = 0; wait_cnt < 10; wait_cnt++) {
+ reg = rd32(hw, I40E_PFGEN_CTRL);
+ if (!(reg & I40E_PFGEN_CTRL_PFSWR_MASK))
+ break;
+ usleep_range(1000, 2000);
+ }
+ if (reg & I40E_PFGEN_CTRL_PFSWR_MASK) {
+ hw_dbg(hw, "PF reset polling failed to complete.\n");
+ return I40E_ERR_RESET_FAILED;
+ }
+ }
+
+ i40e_clear_pxe_mode(hw);
+ return 0;
+}
+
+/**
+ * i40e_clear_pxe_mode - clear pxe operations mode
+ * @hw: pointer to the hw struct
+ *
+ * Make sure all PXE mode settings are cleared, including things
+ * like descriptor fetch/write-back mode.
+ **/
+void i40e_clear_pxe_mode(struct i40e_hw *hw)
+{
+ u32 reg;
+
+ /* Clear single descriptor fetch/write-back mode */
+ reg = rd32(hw, I40E_GLLAN_RCTL_0);
+ wr32(hw, I40E_GLLAN_RCTL_0, (reg | I40E_GLLAN_RCTL_0_PXE_MODE_MASK));
+}
+
+/**
+ * i40e_led_get - return current on/off mode
+ * @hw: pointer to the hw struct
+ *
+ * The value returned is the 'mode' field as defined in the
+ * GPIO register definitions: 0x0 = off, 0xf = on, and other
+ * values are variations of possible behaviors relating to
+ * blink, link, and wire.
+ **/
+u32 i40e_led_get(struct i40e_hw *hw)
+{
+ u32 gpio_val = 0;
+ u32 mode = 0;
+ u32 port;
+ int i;
+
+ for (i = 0; i < I40E_HW_CAP_MAX_GPIO; i++) {
+ if (!hw->func_caps.led[i])
+ continue;
+
+ gpio_val = rd32(hw, I40E_GLGEN_GPIO_CTL(i));
+ port = (gpio_val & I40E_GLGEN_GPIO_CTL_PRT_NUM_MASK)
+ >> I40E_GLGEN_GPIO_CTL_PRT_NUM_SHIFT;
+
+ if (port != hw->port)
+ continue;
+
+ mode = (gpio_val & I40E_GLGEN_GPIO_CTL_LED_MODE_MASK)
+ >> I40E_GLGEN_GPIO_CTL_INT_MODE_SHIFT;
+ break;
+ }
+
+ return mode;
+}
+
+/**
+ * i40e_led_set - set new on/off mode
+ * @hw: pointer to the hw struct
+ * @mode: 0=off, else on (see EAS for mode details)
+ **/
+void i40e_led_set(struct i40e_hw *hw, u32 mode)
+{
+ u32 gpio_val = 0;
+ u32 led_mode = 0;
+ u32 port;
+ int i;
+
+ for (i = 0; i < I40E_HW_CAP_MAX_GPIO; i++) {
+ if (!hw->func_caps.led[i])
+ continue;
+
+ gpio_val = rd32(hw, I40E_GLGEN_GPIO_CTL(i));
+ port = (gpio_val & I40E_GLGEN_GPIO_CTL_PRT_NUM_MASK)
+ >> I40E_GLGEN_GPIO_CTL_PRT_NUM_SHIFT;
+
+ if (port != hw->port)
+ continue;
+
+ led_mode = (mode << I40E_GLGEN_GPIO_CTL_LED_MODE_SHIFT) &
+ I40E_GLGEN_GPIO_CTL_LED_MODE_MASK;
+ gpio_val &= ~I40E_GLGEN_GPIO_CTL_LED_MODE_MASK;
+ gpio_val |= led_mode;
+ wr32(hw, I40E_GLGEN_GPIO_CTL(i), gpio_val);
+ }
+}
+
+/* Admin command wrappers */
+/**
+ * i40e_aq_queue_shutdown
+ * @hw: pointer to the hw struct
+ * @unloading: is the driver unloading itself
+ *
+ * Tell the Firmware that we're shutting down the AdminQ and whether
+ * or not the driver is unloading as well.
+ **/
+i40e_status i40e_aq_queue_shutdown(struct i40e_hw *hw,
+ bool unloading)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_queue_shutdown *cmd =
+ (struct i40e_aqc_queue_shutdown *)&desc.params.raw;
+ i40e_status status;
+
+ i40e_fill_default_direct_cmd_desc(&desc,
+ i40e_aqc_opc_queue_shutdown);
+
+ if (unloading)
+ cmd->driver_unloading = cpu_to_le32(I40E_AQ_DRIVER_UNLOADING);
+ status = i40e_asq_send_command(hw, &desc, NULL, 0, NULL);
+
+ return status;
+}
+
+/**
+ * i40e_aq_set_link_restart_an
+ * @hw: pointer to the hw struct
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Sets up the link and restarts the Auto-Negotiation over the link.
+ **/
+i40e_status i40e_aq_set_link_restart_an(struct i40e_hw *hw,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_set_link_restart_an *cmd =
+ (struct i40e_aqc_set_link_restart_an *)&desc.params.raw;
+ i40e_status status;
+
+ i40e_fill_default_direct_cmd_desc(&desc,
+ i40e_aqc_opc_set_link_restart_an);
+
+ cmd->command = I40E_AQ_PHY_RESTART_AN;
+
+ status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+ return status;
+}
+
+/**
+ * i40e_aq_get_link_info
+ * @hw: pointer to the hw struct
+ * @enable_lse: enable/disable LinkStatusEvent reporting
+ * @link: pointer to link status structure - optional
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Returns the link status of the adapter.
+ **/
+i40e_status i40e_aq_get_link_info(struct i40e_hw *hw,
+ bool enable_lse, struct i40e_link_status *link,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_get_link_status *resp =
+ (struct i40e_aqc_get_link_status *)&desc.params.raw;
+ struct i40e_link_status *hw_link_info = &hw->phy.link_info;
+ i40e_status status;
+ u16 command_flags;
+
+ i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_get_link_status);
+
+ if (enable_lse)
+ command_flags = I40E_AQ_LSE_ENABLE;
+ else
+ command_flags = I40E_AQ_LSE_DISABLE;
+ resp->command_flags = cpu_to_le16(command_flags);
+
+ status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+ if (status)
+ goto aq_get_link_info_exit;
+
+ /* save off old link status information */
+ memcpy(&hw->phy.link_info_old, hw_link_info,
+ sizeof(struct i40e_link_status));
+
+ /* update link status */
+ hw_link_info->phy_type = (enum i40e_aq_phy_type)resp->phy_type;
+ hw_link_info->link_speed = (enum i40e_aq_link_speed)resp->link_speed;
+ hw_link_info->link_info = resp->link_info;
+ hw_link_info->an_info = resp->an_info;
+ hw_link_info->ext_info = resp->ext_info;
+
+ if (resp->command_flags & cpu_to_le16(I40E_AQ_LSE_ENABLE))
+ hw_link_info->lse_enable = true;
+ else
+ hw_link_info->lse_enable = false;
+
+ /* save link status information */
+ if (link)
+ memcpy(link, hw_link_info, sizeof(struct i40e_link_status));
+
+ /* flag cleared so helper functions don't call AQ again */
+ hw->phy.get_link_info = false;
+
+aq_get_link_info_exit:
+ return status;
+}
+
+/**
+ * i40e_aq_add_vsi
+ * @hw: pointer to the hw struct
+ * @vsi: pointer to a vsi context struct
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Add a VSI context to the hardware.
+**/
+i40e_status i40e_aq_add_vsi(struct i40e_hw *hw,
+ struct i40e_vsi_context *vsi_ctx,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_add_get_update_vsi *cmd =
+ (struct i40e_aqc_add_get_update_vsi *)&desc.params.raw;
+ struct i40e_aqc_add_get_update_vsi_completion *resp =
+ (struct i40e_aqc_add_get_update_vsi_completion *)
+ &desc.params.raw;
+ i40e_status status;
+
+ i40e_fill_default_direct_cmd_desc(&desc,
+ i40e_aqc_opc_add_vsi);
+
+ cmd->uplink_seid = cpu_to_le16(vsi_ctx->uplink_seid);
+ cmd->connection_type = vsi_ctx->connection_type;
+ cmd->vf_id = vsi_ctx->vf_num;
+ cmd->vsi_flags = cpu_to_le16(vsi_ctx->flags);
+
+ desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+ if (sizeof(vsi_ctx->info) > I40E_AQ_LARGE_BUF)
+ desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+
+ status = i40e_asq_send_command(hw, &desc, &vsi_ctx->info,
+ sizeof(vsi_ctx->info), cmd_details);
+
+ if (status)
+ goto aq_add_vsi_exit;
+
+ vsi_ctx->seid = le16_to_cpu(resp->seid);
+ vsi_ctx->vsi_number = le16_to_cpu(resp->vsi_number);
+ vsi_ctx->vsis_allocated = le16_to_cpu(resp->vsi_used);
+ vsi_ctx->vsis_unallocated = le16_to_cpu(resp->vsi_free);
+
+aq_add_vsi_exit:
+ return status;
+}
+
+/**
+ * i40e_aq_set_vsi_unicast_promiscuous
+ * @hw: pointer to the hw struct
+ * @seid: vsi number
+ * @set: set unicast promiscuous enable/disable
+ * @cmd_details: pointer to command details structure or NULL
+ **/
+i40e_status i40e_aq_set_vsi_unicast_promiscuous(struct i40e_hw *hw,
+ u16 seid, bool set, struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_set_vsi_promiscuous_modes *cmd =
+ (struct i40e_aqc_set_vsi_promiscuous_modes *)&desc.params.raw;
+ i40e_status status;
+ u16 flags = 0;
+
+ i40e_fill_default_direct_cmd_desc(&desc,
+ i40e_aqc_opc_set_vsi_promiscuous_modes);
+
+ if (set)
+ flags |= I40E_AQC_SET_VSI_PROMISC_UNICAST;
+
+ cmd->promiscuous_flags = cpu_to_le16(flags);
+
+ cmd->valid_flags = cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_UNICAST);
+
+ cmd->seid = cpu_to_le16(seid);
+ status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+ return status;
+}
+
+/**
+ * i40e_aq_set_vsi_multicast_promiscuous
+ * @hw: pointer to the hw struct
+ * @seid: vsi number
+ * @set: set multicast promiscuous enable/disable
+ * @cmd_details: pointer to command details structure or NULL
+ **/
+i40e_status i40e_aq_set_vsi_multicast_promiscuous(struct i40e_hw *hw,
+ u16 seid, bool set, struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_set_vsi_promiscuous_modes *cmd =
+ (struct i40e_aqc_set_vsi_promiscuous_modes *)&desc.params.raw;
+ i40e_status status;
+ u16 flags = 0;
+
+ i40e_fill_default_direct_cmd_desc(&desc,
+ i40e_aqc_opc_set_vsi_promiscuous_modes);
+
+ if (set)
+ flags |= I40E_AQC_SET_VSI_PROMISC_MULTICAST;
+
+ cmd->promiscuous_flags = cpu_to_le16(flags);
+
+ cmd->valid_flags = cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_MULTICAST);
+
+ cmd->seid = cpu_to_le16(seid);
+ status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+ return status;
+}
+
+/**
+ * i40e_aq_set_vsi_broadcast
+ * @hw: pointer to the hw struct
+ * @seid: vsi number
+ * @set_filter: true to set filter, false to clear filter
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Set or clear the broadcast promiscuous flag (filter) for a given VSI.
+ **/
+i40e_status i40e_aq_set_vsi_broadcast(struct i40e_hw *hw,
+ u16 seid, bool set_filter,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_set_vsi_promiscuous_modes *cmd =
+ (struct i40e_aqc_set_vsi_promiscuous_modes *)&desc.params.raw;
+ i40e_status status;
+
+ i40e_fill_default_direct_cmd_desc(&desc,
+ i40e_aqc_opc_set_vsi_promiscuous_modes);
+
+ if (set_filter)
+ cmd->promiscuous_flags
+ |= cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_BROADCAST);
+ else
+ cmd->promiscuous_flags
+ &= cpu_to_le16(~I40E_AQC_SET_VSI_PROMISC_BROADCAST);
+
+ cmd->valid_flags = cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_BROADCAST);
+ cmd->seid = cpu_to_le16(seid);
+ status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+ return status;
+}
+
+/**
+ * i40e_get_vsi_params - get VSI configuration info
+ * @hw: pointer to the hw struct
+ * @vsi: pointer to a vsi context struct
+ * @cmd_details: pointer to command details structure or NULL
+ **/
+i40e_status i40e_aq_get_vsi_params(struct i40e_hw *hw,
+ struct i40e_vsi_context *vsi_ctx,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_switch_seid *cmd =
+ (struct i40e_aqc_switch_seid *)&desc.params.raw;
+ struct i40e_aqc_add_get_update_vsi_completion *resp =
+ (struct i40e_aqc_add_get_update_vsi_completion *)
+ &desc.params.raw;
+ i40e_status status;
+
+ i40e_fill_default_direct_cmd_desc(&desc,
+ i40e_aqc_opc_get_vsi_parameters);
+
+ cmd->seid = cpu_to_le16(vsi_ctx->seid);
+
+ desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+ if (sizeof(vsi_ctx->info) > I40E_AQ_LARGE_BUF)
+ desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+
+ status = i40e_asq_send_command(hw, &desc, &vsi_ctx->info,
+ sizeof(vsi_ctx->info), NULL);
+
+ if (status)
+ goto aq_get_vsi_params_exit;
+
+ vsi_ctx->seid = le16_to_cpu(resp->seid);
+ vsi_ctx->vsi_number = le16_to_cpu(resp->vsi_number);
+ vsi_ctx->vsis_allocated = le16_to_cpu(resp->vsi_used);
+ vsi_ctx->vsis_unallocated = le16_to_cpu(resp->vsi_free);
+
+aq_get_vsi_params_exit:
+ return status;
+}
+
+/**
+ * i40e_aq_update_vsi_params
+ * @hw: pointer to the hw struct
+ * @vsi: pointer to a vsi context struct
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Update a VSI context.
+ **/
+i40e_status i40e_aq_update_vsi_params(struct i40e_hw *hw,
+ struct i40e_vsi_context *vsi_ctx,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_switch_seid *cmd =
+ (struct i40e_aqc_switch_seid *)&desc.params.raw;
+ i40e_status status;
+
+ i40e_fill_default_direct_cmd_desc(&desc,
+ i40e_aqc_opc_update_vsi_parameters);
+ cmd->seid = cpu_to_le16(vsi_ctx->seid);
+
+ desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+ if (sizeof(vsi_ctx->info) > I40E_AQ_LARGE_BUF)
+ desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+
+ status = i40e_asq_send_command(hw, &desc, &vsi_ctx->info,
+ sizeof(vsi_ctx->info), cmd_details);
+
+ return status;
+}
+
+/**
+ * i40e_aq_get_switch_config
+ * @hw: pointer to the hardware structure
+ * @buf: pointer to the result buffer
+ * @buf_size: length of input buffer
+ * @start_seid: seid to start for the report, 0 == beginning
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Fill the buf with switch configuration returned from AdminQ command
+ **/
+i40e_status i40e_aq_get_switch_config(struct i40e_hw *hw,
+ struct i40e_aqc_get_switch_config_resp *buf,
+ u16 buf_size, u16 *start_seid,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_switch_seid *scfg =
+ (struct i40e_aqc_switch_seid *)&desc.params.raw;
+ i40e_status status;
+
+ i40e_fill_default_direct_cmd_desc(&desc,
+ i40e_aqc_opc_get_switch_config);
+ desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+ if (buf_size > I40E_AQ_LARGE_BUF)
+ desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+ scfg->seid = cpu_to_le16(*start_seid);
+
+ status = i40e_asq_send_command(hw, &desc, buf, buf_size, cmd_details);
+ *start_seid = le16_to_cpu(scfg->seid);
+
+ return status;
+}
+
+/**
+ * i40e_aq_get_firmware_version
+ * @hw: pointer to the hw struct
+ * @fw_major_version: firmware major version
+ * @fw_minor_version: firmware minor version
+ * @api_major_version: major queue version
+ * @api_minor_version: minor queue version
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Get the firmware version from the admin queue commands
+ **/
+i40e_status i40e_aq_get_firmware_version(struct i40e_hw *hw,
+ u16 *fw_major_version, u16 *fw_minor_version,
+ u16 *api_major_version, u16 *api_minor_version,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_get_version *resp =
+ (struct i40e_aqc_get_version *)&desc.params.raw;
+ i40e_status status;
+
+ i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_get_version);
+
+ status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+ if (!status) {
+ if (fw_major_version != NULL)
+ *fw_major_version = le16_to_cpu(resp->fw_major);
+ if (fw_minor_version != NULL)
+ *fw_minor_version = le16_to_cpu(resp->fw_minor);
+ if (api_major_version != NULL)
+ *api_major_version = le16_to_cpu(resp->api_major);
+ if (api_minor_version != NULL)
+ *api_minor_version = le16_to_cpu(resp->api_minor);
+ }
+
+ return status;
+}
+
+/**
+ * i40e_aq_send_driver_version
+ * @hw: pointer to the hw struct
+ * @event: driver event: driver ok, start or stop
+ * @dv: driver's major, minor version
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Send the driver version to the firmware
+ **/
+i40e_status i40e_aq_send_driver_version(struct i40e_hw *hw,
+ struct i40e_driver_version *dv,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_driver_version *cmd =
+ (struct i40e_aqc_driver_version *)&desc.params.raw;
+ i40e_status status;
+
+ if (dv == NULL)
+ return I40E_ERR_PARAM;
+
+ i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_driver_version);
+
+ desc.flags |= cpu_to_le16(I40E_AQ_FLAG_SI);
+ cmd->driver_major_ver = dv->major_version;
+ cmd->driver_minor_ver = dv->minor_version;
+ cmd->driver_build_ver = dv->build_version;
+ cmd->driver_subbuild_ver = dv->subbuild_version;
+ status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+ return status;
+}
+
+/**
+ * i40e_get_link_status - get status of the HW network link
+ * @hw: pointer to the hw struct
+ *
+ * Returns true if link is up, false if link is down.
+ *
+ * Side effect: LinkStatusEvent reporting becomes enabled
+ **/
+bool i40e_get_link_status(struct i40e_hw *hw)
+{
+ i40e_status status = 0;
+ bool link_status = false;
+
+ if (hw->phy.get_link_info) {
+ status = i40e_aq_get_link_info(hw, true, NULL, NULL);
+
+ if (status)
+ goto i40e_get_link_status_exit;
+ }
+
+ link_status = hw->phy.link_info.link_info & I40E_AQ_LINK_UP;
+
+i40e_get_link_status_exit:
+ return link_status;
+}
+
+/**
+ * i40e_aq_add_veb - Insert a VEB between the VSI and the MAC
+ * @hw: pointer to the hw struct
+ * @uplink_seid: the MAC or other gizmo SEID
+ * @downlink_seid: the VSI SEID
+ * @enabled_tc: bitmap of TCs to be enabled
+ * @default_port: true for default port VSI, false for control port
+ * @veb_seid: pointer to where to put the resulting VEB SEID
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * This asks the FW to add a VEB between the uplink and downlink
+ * elements. If the uplink SEID is 0, this will be a floating VEB.
+ **/
+i40e_status i40e_aq_add_veb(struct i40e_hw *hw, u16 uplink_seid,
+ u16 downlink_seid, u8 enabled_tc,
+ bool default_port, u16 *veb_seid,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_add_veb *cmd =
+ (struct i40e_aqc_add_veb *)&desc.params.raw;
+ struct i40e_aqc_add_veb_completion *resp =
+ (struct i40e_aqc_add_veb_completion *)&desc.params.raw;
+ i40e_status status;
+ u16 veb_flags = 0;
+
+ /* SEIDs need to either both be set or both be 0 for floating VEB */
+ if (!!uplink_seid != !!downlink_seid)
+ return I40E_ERR_PARAM;
+
+ i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_add_veb);
+
+ cmd->uplink_seid = cpu_to_le16(uplink_seid);
+ cmd->downlink_seid = cpu_to_le16(downlink_seid);
+ cmd->enable_tcs = enabled_tc;
+ if (!uplink_seid)
+ veb_flags |= I40E_AQC_ADD_VEB_FLOATING;
+ if (default_port)
+ veb_flags |= I40E_AQC_ADD_VEB_PORT_TYPE_DEFAULT;
+ else
+ veb_flags |= I40E_AQC_ADD_VEB_PORT_TYPE_DATA;
+ cmd->veb_flags = cpu_to_le16(veb_flags);
+
+ status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+ if (!status && veb_seid)
+ *veb_seid = le16_to_cpu(resp->veb_seid);
+
+ return status;
+}
+
+/**
+ * i40e_aq_get_veb_parameters - Retrieve VEB parameters
+ * @hw: pointer to the hw struct
+ * @veb_seid: the SEID of the VEB to query
+ * @switch_id: the uplink switch id
+ * @floating_veb: set to true if the VEB is floating
+ * @statistic_index: index of the stats counter block for this VEB
+ * @vebs_used: number of VEB's used by function
+ * @vebs_unallocated: total VEB's not reserved by any function
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * This retrieves the parameters for a particular VEB, specified by
+ * uplink_seid, and returns them to the caller.
+ **/
+i40e_status i40e_aq_get_veb_parameters(struct i40e_hw *hw,
+ u16 veb_seid, u16 *switch_id,
+ bool *floating, u16 *statistic_index,
+ u16 *vebs_used, u16 *vebs_free,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_get_veb_parameters_completion *cmd_resp =
+ (struct i40e_aqc_get_veb_parameters_completion *)
+ &desc.params.raw;
+ i40e_status status;
+
+ if (veb_seid == 0)
+ return I40E_ERR_PARAM;
+
+ i40e_fill_default_direct_cmd_desc(&desc,
+ i40e_aqc_opc_get_veb_parameters);
+ cmd_resp->seid = cpu_to_le16(veb_seid);
+
+ status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+ if (status)
+ goto get_veb_exit;
+
+ if (switch_id)
+ *switch_id = le16_to_cpu(cmd_resp->switch_id);
+ if (statistic_index)
+ *statistic_index = le16_to_cpu(cmd_resp->statistic_index);
+ if (vebs_used)
+ *vebs_used = le16_to_cpu(cmd_resp->vebs_used);
+ if (vebs_free)
+ *vebs_free = le16_to_cpu(cmd_resp->vebs_free);
+ if (floating) {
+ u16 flags = le16_to_cpu(cmd_resp->veb_flags);
+ if (flags & I40E_AQC_ADD_VEB_FLOATING)
+ *floating = true;
+ else
+ *floating = false;
+ }
+
+get_veb_exit:
+ return status;
+}
+
+/**
+ * i40e_aq_add_macvlan
+ * @hw: pointer to the hw struct
+ * @seid: VSI for the mac address
+ * @mv_list: list of macvlans to be added
+ * @count: length of the list
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Add MAC/VLAN addresses to the HW filtering
+ **/
+i40e_status i40e_aq_add_macvlan(struct i40e_hw *hw, u16 seid,
+ struct i40e_aqc_add_macvlan_element_data *mv_list,
+ u16 count, struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_macvlan *cmd =
+ (struct i40e_aqc_macvlan *)&desc.params.raw;
+ i40e_status status;
+ u16 buf_size;
+
+ if (count == 0 || !mv_list || !hw)
+ return I40E_ERR_PARAM;
+
+ buf_size = count * sizeof(struct i40e_aqc_add_macvlan_element_data);
+
+ /* prep the rest of the request */
+ i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_add_macvlan);
+ cmd->num_addresses = cpu_to_le16(count);
+ cmd->seid[0] = cpu_to_le16(I40E_AQC_MACVLAN_CMD_SEID_VALID | seid);
+ cmd->seid[1] = 0;
+ cmd->seid[2] = 0;
+
+ desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+ if (buf_size > I40E_AQ_LARGE_BUF)
+ desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+
+ status = i40e_asq_send_command(hw, &desc, mv_list, buf_size,
+ cmd_details);
+
+ return status;
+}
+
+/**
+ * i40e_aq_remove_macvlan
+ * @hw: pointer to the hw struct
+ * @seid: VSI for the mac address
+ * @mv_list: list of macvlans to be removed
+ * @count: length of the list
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Remove MAC/VLAN addresses from the HW filtering
+ **/
+i40e_status i40e_aq_remove_macvlan(struct i40e_hw *hw, u16 seid,
+ struct i40e_aqc_remove_macvlan_element_data *mv_list,
+ u16 count, struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_macvlan *cmd =
+ (struct i40e_aqc_macvlan *)&desc.params.raw;
+ i40e_status status;
+ u16 buf_size;
+
+ if (count == 0 || !mv_list || !hw)
+ return I40E_ERR_PARAM;
+
+ buf_size = count * sizeof(struct i40e_aqc_remove_macvlan_element_data);
+
+ /* prep the rest of the request */
+ i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_remove_macvlan);
+ cmd->num_addresses = cpu_to_le16(count);
+ cmd->seid[0] = cpu_to_le16(I40E_AQC_MACVLAN_CMD_SEID_VALID | seid);
+ cmd->seid[1] = 0;
+ cmd->seid[2] = 0;
+
+ desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+ if (buf_size > I40E_AQ_LARGE_BUF)
+ desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+
+ status = i40e_asq_send_command(hw, &desc, mv_list, buf_size,
+ cmd_details);
+
+ return status;
+}
+
+/**
+ * i40e_aq_add_vlan - Add VLAN ids to the HW filtering
+ * @hw: pointer to the hw struct
+ * @seid: VSI for the vlan filters
+ * @v_list: list of vlan filters to be added
+ * @count: length of the list
+ * @cmd_details: pointer to command details structure or NULL
+ **/
+i40e_status i40e_aq_add_vlan(struct i40e_hw *hw, u16 seid,
+ struct i40e_aqc_add_remove_vlan_element_data *v_list,
+ u8 count, struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_macvlan *cmd =
+ (struct i40e_aqc_macvlan *)&desc.params.raw;
+ i40e_status status;
+ u16 buf_size;
+
+ if (count == 0 || !v_list || !hw)
+ return I40E_ERR_PARAM;
+
+ buf_size = count * sizeof(struct i40e_aqc_add_remove_vlan_element_data);
+
+ /* prep the rest of the request */
+ i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_add_vlan);
+ cmd->num_addresses = cpu_to_le16(count);
+ cmd->seid[0] = cpu_to_le16(seid | I40E_AQC_MACVLAN_CMD_SEID_VALID);
+ cmd->seid[1] = 0;
+ cmd->seid[2] = 0;
+
+ desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+ if (buf_size > I40E_AQ_LARGE_BUF)
+ desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+
+ status = i40e_asq_send_command(hw, &desc, v_list, buf_size,
+ cmd_details);
+
+ return status;
+}
+
+/**
+ * i40e_aq_remove_vlan - Remove VLANs from the HW filtering
+ * @hw: pointer to the hw struct
+ * @seid: VSI for the vlan filters
+ * @v_list: list of macvlans to be removed
+ * @count: length of the list
+ * @cmd_details: pointer to command details structure or NULL
+ **/
+i40e_status i40e_aq_remove_vlan(struct i40e_hw *hw, u16 seid,
+ struct i40e_aqc_add_remove_vlan_element_data *v_list,
+ u8 count, struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_macvlan *cmd =
+ (struct i40e_aqc_macvlan *)&desc.params.raw;
+ i40e_status status;
+ u16 buf_size;
+
+ if (count == 0 || !v_list || !hw)
+ return I40E_ERR_PARAM;
+
+ buf_size = count * sizeof(struct i40e_aqc_add_remove_vlan_element_data);
+
+ /* prep the rest of the request */
+ i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_remove_vlan);
+ cmd->num_addresses = cpu_to_le16(count);
+ cmd->seid[0] = cpu_to_le16(seid | I40E_AQC_MACVLAN_CMD_SEID_VALID);
+ cmd->seid[1] = 0;
+ cmd->seid[2] = 0;
+
+ desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+ if (buf_size > I40E_AQ_LARGE_BUF)
+ desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+
+ status = i40e_asq_send_command(hw, &desc, v_list, buf_size,
+ cmd_details);
+
+ return status;
+}
+
+/**
+ * i40e_aq_send_msg_to_vf
+ * @hw: pointer to the hardware structure
+ * @vfid: vf id to send msg
+ * @msg: pointer to the msg buffer
+ * @msglen: msg length
+ * @cmd_details: pointer to command details
+ *
+ * send msg to vf
+ **/
+i40e_status i40e_aq_send_msg_to_vf(struct i40e_hw *hw, u16 vfid,
+ u32 v_opcode, u32 v_retval, u8 *msg, u16 msglen,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_pf_vf_message *cmd =
+ (struct i40e_aqc_pf_vf_message *)&desc.params.raw;
+ i40e_status status;
+
+ i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_send_msg_to_vf);
+ cmd->id = cpu_to_le32(vfid);
+ desc.cookie_high = cpu_to_le32(v_opcode);
+ desc.cookie_low = cpu_to_le32(v_retval);
+ desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_SI);
+ if (msglen) {
+ desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF |
+ I40E_AQ_FLAG_RD));
+ if (msglen > I40E_AQ_LARGE_BUF)
+ desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+ desc.datalen = cpu_to_le16(msglen);
+ }
+ status = i40e_asq_send_command(hw, &desc, msg, msglen, cmd_details);
+
+ return status;
+}
+
+/**
+ * i40e_aq_set_hmc_resource_profile
+ * @hw: pointer to the hw struct
+ * @profile: type of profile the HMC is to be set as
+ * @pe_vf_enabled_count: the number of PE enabled VFs the system has
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * set the HMC profile of the device.
+ **/
+i40e_status i40e_aq_set_hmc_resource_profile(struct i40e_hw *hw,
+ enum i40e_aq_hmc_profile profile,
+ u8 pe_vf_enabled_count,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aq_get_set_hmc_resource_profile *cmd =
+ (struct i40e_aq_get_set_hmc_resource_profile *)&desc.params.raw;
+ i40e_status status;
+
+ i40e_fill_default_direct_cmd_desc(&desc,
+ i40e_aqc_opc_set_hmc_resource_profile);
+
+ cmd->pm_profile = (u8)profile;
+ cmd->pe_vf_enabled = pe_vf_enabled_count;
+
+ status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+ return status;
+}
+
+/**
+ * i40e_aq_request_resource
+ * @hw: pointer to the hw struct
+ * @resource: resource id
+ * @access: access type
+ * @sdp_number: resource number
+ * @timeout: the maximum time in ms that the driver may hold the resource
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * requests common resource using the admin queue commands
+ **/
+i40e_status i40e_aq_request_resource(struct i40e_hw *hw,
+ enum i40e_aq_resources_ids resource,
+ enum i40e_aq_resource_access_type access,
+ u8 sdp_number, u64 *timeout,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_request_resource *cmd_resp =
+ (struct i40e_aqc_request_resource *)&desc.params.raw;
+ i40e_status status;
+
+ i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_request_resource);
+
+ cmd_resp->resource_id = cpu_to_le16(resource);
+ cmd_resp->access_type = cpu_to_le16(access);
+ cmd_resp->resource_number = cpu_to_le32(sdp_number);
+
+ status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+ /* The completion specifies the maximum time in ms that the driver
+ * may hold the resource in the Timeout field.
+ * If the resource is held by someone else, the command completes with
+ * busy return value and the timeout field indicates the maximum time
+ * the current owner of the resource has to free it.
+ */
+ if (!status || hw->aq.asq_last_status == I40E_AQ_RC_EBUSY)
+ *timeout = le32_to_cpu(cmd_resp->timeout);
+
+ return status;
+}
+
+/**
+ * i40e_aq_release_resource
+ * @hw: pointer to the hw struct
+ * @resource: resource id
+ * @sdp_number: resource number
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * release common resource using the admin queue commands
+ **/
+i40e_status i40e_aq_release_resource(struct i40e_hw *hw,
+ enum i40e_aq_resources_ids resource,
+ u8 sdp_number,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_request_resource *cmd =
+ (struct i40e_aqc_request_resource *)&desc.params.raw;
+ i40e_status status;
+
+ i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_release_resource);
+
+ cmd->resource_id = cpu_to_le16(resource);
+ cmd->resource_number = cpu_to_le32(sdp_number);
+
+ status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+ return status;
+}
+
+/**
+ * i40e_aq_read_nvm
+ * @hw: pointer to the hw struct
+ * @module_pointer: module pointer location in words from the NVM beginning
+ * @offset: byte offset from the module beginning
+ * @length: length of the section to be read (in bytes from the offset)
+ * @data: command buffer (size [bytes] = length)
+ * @last_command: tells if this is the last command in a series
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Read the NVM using the admin queue commands
+ **/
+i40e_status i40e_aq_read_nvm(struct i40e_hw *hw, u8 module_pointer,
+ u32 offset, u16 length, void *data,
+ bool last_command,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_nvm_update *cmd =
+ (struct i40e_aqc_nvm_update *)&desc.params.raw;
+ i40e_status status;
+
+ /* In offset the highest byte must be zeroed. */
+ if (offset & 0xFF000000) {
+ status = I40E_ERR_PARAM;
+ goto i40e_aq_read_nvm_exit;
+ }
+
+ i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_nvm_read);
+
+ /* If this is the last command in a series, set the proper flag. */
+ if (last_command)
+ cmd->command_flags |= I40E_AQ_NVM_LAST_CMD;
+ cmd->module_pointer = module_pointer;
+ cmd->offset = cpu_to_le32(offset);
+ cmd->length = cpu_to_le16(length);
+
+ desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+ if (length > I40E_AQ_LARGE_BUF)
+ desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+
+ status = i40e_asq_send_command(hw, &desc, data, length, cmd_details);
+
+i40e_aq_read_nvm_exit:
+ return status;
+}
+
+#define I40E_DEV_FUNC_CAP_SWITCH_MODE 0x01
+#define I40E_DEV_FUNC_CAP_MGMT_MODE 0x02
+#define I40E_DEV_FUNC_CAP_NPAR 0x03
+#define I40E_DEV_FUNC_CAP_OS2BMC 0x04
+#define I40E_DEV_FUNC_CAP_VALID_FUNC 0x05
+#define I40E_DEV_FUNC_CAP_SRIOV_1_1 0x12
+#define I40E_DEV_FUNC_CAP_VF 0x13
+#define I40E_DEV_FUNC_CAP_VMDQ 0x14
+#define I40E_DEV_FUNC_CAP_802_1_QBG 0x15
+#define I40E_DEV_FUNC_CAP_802_1_QBH 0x16
+#define I40E_DEV_FUNC_CAP_VSI 0x17
+#define I40E_DEV_FUNC_CAP_DCB 0x18
+#define I40E_DEV_FUNC_CAP_FCOE 0x21
+#define I40E_DEV_FUNC_CAP_RSS 0x40
+#define I40E_DEV_FUNC_CAP_RX_QUEUES 0x41
+#define I40E_DEV_FUNC_CAP_TX_QUEUES 0x42
+#define I40E_DEV_FUNC_CAP_MSIX 0x43
+#define I40E_DEV_FUNC_CAP_MSIX_VF 0x44
+#define I40E_DEV_FUNC_CAP_FLOW_DIRECTOR 0x45
+#define I40E_DEV_FUNC_CAP_IEEE_1588 0x46
+#define I40E_DEV_FUNC_CAP_MFP_MODE_1 0xF1
+#define I40E_DEV_FUNC_CAP_CEM 0xF2
+#define I40E_DEV_FUNC_CAP_IWARP 0x51
+#define I40E_DEV_FUNC_CAP_LED 0x61
+#define I40E_DEV_FUNC_CAP_SDP 0x62
+#define I40E_DEV_FUNC_CAP_MDIO 0x63
+
+/**
+ * i40e_parse_discover_capabilities
+ * @hw: pointer to the hw struct
+ * @buff: pointer to a buffer containing device/function capability records
+ * @cap_count: number of capability records in the list
+ * @list_type_opc: type of capabilities list to parse
+ *
+ * Parse the device/function capabilities list.
+ **/
+static void i40e_parse_discover_capabilities(struct i40e_hw *hw, void *buff,
+ u32 cap_count,
+ enum i40e_admin_queue_opc list_type_opc)
+{
+ struct i40e_aqc_list_capabilities_element_resp *cap;
+ u32 number, logical_id, phys_id;
+ struct i40e_hw_capabilities *p;
+ u32 reg_val;
+ u32 i = 0;
+ u16 id;
+
+ cap = (struct i40e_aqc_list_capabilities_element_resp *) buff;
+
+ if (list_type_opc == i40e_aqc_opc_list_dev_capabilities)
+ p = (struct i40e_hw_capabilities *)&hw->dev_caps;
+ else if (list_type_opc == i40e_aqc_opc_list_func_capabilities)
+ p = (struct i40e_hw_capabilities *)&hw->func_caps;
+ else
+ return;
+
+ for (i = 0; i < cap_count; i++, cap++) {
+ id = le16_to_cpu(cap->id);
+ number = le32_to_cpu(cap->number);
+ logical_id = le32_to_cpu(cap->logical_id);
+ phys_id = le32_to_cpu(cap->phys_id);
+
+ switch (id) {
+ case I40E_DEV_FUNC_CAP_SWITCH_MODE:
+ p->switch_mode = number;
+ break;
+ case I40E_DEV_FUNC_CAP_MGMT_MODE:
+ p->management_mode = number;
+ break;
+ case I40E_DEV_FUNC_CAP_NPAR:
+ p->npar_enable = number;
+ break;
+ case I40E_DEV_FUNC_CAP_OS2BMC:
+ p->os2bmc = number;
+ break;
+ case I40E_DEV_FUNC_CAP_VALID_FUNC:
+ p->valid_functions = number;
+ break;
+ case I40E_DEV_FUNC_CAP_SRIOV_1_1:
+ if (number == 1)
+ p->sr_iov_1_1 = true;
+ break;
+ case I40E_DEV_FUNC_CAP_VF:
+ p->num_vfs = number;
+ p->vf_base_id = logical_id;
+ break;
+ case I40E_DEV_FUNC_CAP_VMDQ:
+ if (number == 1)
+ p->vmdq = true;
+ break;
+ case I40E_DEV_FUNC_CAP_802_1_QBG:
+ if (number == 1)
+ p->evb_802_1_qbg = true;
+ break;
+ case I40E_DEV_FUNC_CAP_802_1_QBH:
+ if (number == 1)
+ p->evb_802_1_qbh = true;
+ break;
+ case I40E_DEV_FUNC_CAP_VSI:
+ p->num_vsis = number;
+ break;
+ case I40E_DEV_FUNC_CAP_DCB:
+ if (number == 1) {
+ p->dcb = true;
+ p->enabled_tcmap = logical_id;
+ p->maxtc = phys_id;
+ }
+ break;
+ case I40E_DEV_FUNC_CAP_FCOE:
+ if (number == 1)
+ p->fcoe = true;
+ break;
+ case I40E_DEV_FUNC_CAP_RSS:
+ p->rss = true;
+ reg_val = rd32(hw, I40E_PFQF_CTL_0);
+ if (reg_val & I40E_PFQF_CTL_0_HASHLUTSIZE_MASK)
+ p->rss_table_size = number;
+ else
+ p->rss_table_size = 128;
+ p->rss_table_entry_width = logical_id;
+ break;
+ case I40E_DEV_FUNC_CAP_RX_QUEUES:
+ p->num_rx_qp = number;
+ p->base_queue = phys_id;
+ break;
+ case I40E_DEV_FUNC_CAP_TX_QUEUES:
+ p->num_tx_qp = number;
+ p->base_queue = phys_id;
+ break;
+ case I40E_DEV_FUNC_CAP_MSIX:
+ p->num_msix_vectors = number;
+ break;
+ case I40E_DEV_FUNC_CAP_MSIX_VF:
+ p->num_msix_vectors_vf = number;
+ break;
+ case I40E_DEV_FUNC_CAP_MFP_MODE_1:
+ if (number == 1)
+ p->mfp_mode_1 = true;
+ break;
+ case I40E_DEV_FUNC_CAP_CEM:
+ if (number == 1)
+ p->mgmt_cem = true;
+ break;
+ case I40E_DEV_FUNC_CAP_IWARP:
+ if (number == 1)
+ p->iwarp = true;
+ break;
+ case I40E_DEV_FUNC_CAP_LED:
+ if (phys_id < I40E_HW_CAP_MAX_GPIO)
+ p->led[phys_id] = true;
+ break;
+ case I40E_DEV_FUNC_CAP_SDP:
+ if (phys_id < I40E_HW_CAP_MAX_GPIO)
+ p->sdp[phys_id] = true;
+ break;
+ case I40E_DEV_FUNC_CAP_MDIO:
+ if (number == 1) {
+ p->mdio_port_num = phys_id;
+ p->mdio_port_mode = logical_id;
+ }
+ break;
+ case I40E_DEV_FUNC_CAP_IEEE_1588:
+ if (number == 1)
+ p->ieee_1588 = true;
+ break;
+ case I40E_DEV_FUNC_CAP_FLOW_DIRECTOR:
+ p->fd = true;
+ p->fd_filters_guaranteed = number;
+ p->fd_filters_best_effort = logical_id;
+ break;
+ default:
+ break;
+ }
+ }
+
+ /* additional HW specific goodies that might
+ * someday be HW version specific
+ */
+ p->rx_buf_chain_len = I40E_MAX_CHAINED_RX_BUFFERS;
+}
+
+/**
+ * i40e_aq_discover_capabilities
+ * @hw: pointer to the hw struct
+ * @buff: a virtual buffer to hold the capabilities
+ * @buff_size: Size of the virtual buffer
+ * @data_size: Size of the returned data, or buff size needed if AQ err==ENOMEM
+ * @list_type_opc: capabilities type to discover - pass in the command opcode
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Get the device capabilities descriptions from the firmware
+ **/
+i40e_status i40e_aq_discover_capabilities(struct i40e_hw *hw,
+ void *buff, u16 buff_size, u16 *data_size,
+ enum i40e_admin_queue_opc list_type_opc,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aqc_list_capabilites *cmd;
+ i40e_status status = 0;
+ struct i40e_aq_desc desc;
+
+ cmd = (struct i40e_aqc_list_capabilites *)&desc.params.raw;
+
+ if (list_type_opc != i40e_aqc_opc_list_func_capabilities &&
+ list_type_opc != i40e_aqc_opc_list_dev_capabilities) {
+ status = I40E_ERR_PARAM;
+ goto exit;
+ }
+
+ i40e_fill_default_direct_cmd_desc(&desc, list_type_opc);
+
+ desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+ if (buff_size > I40E_AQ_LARGE_BUF)
+ desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+
+ status = i40e_asq_send_command(hw, &desc, buff, buff_size, cmd_details);
+ *data_size = le16_to_cpu(desc.datalen);
+
+ if (status)
+ goto exit;
+
+ i40e_parse_discover_capabilities(hw, buff, le32_to_cpu(cmd->count),
+ list_type_opc);
+
+exit:
+ return status;
+}
+
+/**
+ * i40e_aq_get_lldp_mib
+ * @hw: pointer to the hw struct
+ * @bridge_type: type of bridge requested
+ * @mib_type: Local, Remote or both Local and Remote MIBs
+ * @buff: pointer to a user supplied buffer to store the MIB block
+ * @buff_size: size of the buffer (in bytes)
+ * @local_len : length of the returned Local LLDP MIB
+ * @remote_len: length of the returned Remote LLDP MIB
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Requests the complete LLDP MIB (entire packet).
+ **/
+i40e_status i40e_aq_get_lldp_mib(struct i40e_hw *hw, u8 bridge_type,
+ u8 mib_type, void *buff, u16 buff_size,
+ u16 *local_len, u16 *remote_len,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_lldp_get_mib *cmd =
+ (struct i40e_aqc_lldp_get_mib *)&desc.params.raw;
+ struct i40e_aqc_lldp_get_mib *resp =
+ (struct i40e_aqc_lldp_get_mib *)&desc.params.raw;
+ i40e_status status;
+
+ if (buff_size == 0 || !buff)
+ return I40E_ERR_PARAM;
+
+ i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_lldp_get_mib);
+ /* Indirect Command */
+ desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+
+ cmd->type = mib_type & I40E_AQ_LLDP_MIB_TYPE_MASK;
+ cmd->type |= ((bridge_type << I40E_AQ_LLDP_BRIDGE_TYPE_SHIFT) &
+ I40E_AQ_LLDP_BRIDGE_TYPE_MASK);
+
+ desc.datalen = cpu_to_le16(buff_size);
+
+ desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+ if (buff_size > I40E_AQ_LARGE_BUF)
+ desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+
+ status = i40e_asq_send_command(hw, &desc, buff, buff_size, cmd_details);
+ if (!status) {
+ if (local_len != NULL)
+ *local_len = le16_to_cpu(resp->local_len);
+ if (remote_len != NULL)
+ *remote_len = le16_to_cpu(resp->remote_len);
+ }
+
+ return status;
+}
+
+/**
+ * i40e_aq_cfg_lldp_mib_change_event
+ * @hw: pointer to the hw struct
+ * @enable_update: Enable or Disable event posting
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Enable or Disable posting of an event on ARQ when LLDP MIB
+ * associated with the interface changes
+ **/
+i40e_status i40e_aq_cfg_lldp_mib_change_event(struct i40e_hw *hw,
+ bool enable_update,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_lldp_update_mib *cmd =
+ (struct i40e_aqc_lldp_update_mib *)&desc.params.raw;
+ i40e_status status;
+
+ i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_lldp_update_mib);
+
+ if (!enable_update)
+ cmd->command |= I40E_AQ_LLDP_MIB_UPDATE_DISABLE;
+
+ status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+ return status;
+}
+
+/**
+ * i40e_aq_stop_lldp
+ * @hw: pointer to the hw struct
+ * @shutdown_agent: True if LLDP Agent needs to be Shutdown
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Stop or Shutdown the embedded LLDP Agent
+ **/
+i40e_status i40e_aq_stop_lldp(struct i40e_hw *hw, bool shutdown_agent,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_lldp_stop *cmd =
+ (struct i40e_aqc_lldp_stop *)&desc.params.raw;
+ i40e_status status;
+
+ i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_lldp_stop);
+
+ if (shutdown_agent)
+ cmd->command |= I40E_AQ_LLDP_AGENT_SHUTDOWN;
+
+ status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+ return status;
+}
+
+/**
+ * i40e_aq_start_lldp
+ * @hw: pointer to the hw struct
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Start the embedded LLDP Agent on all ports.
+ **/
+i40e_status i40e_aq_start_lldp(struct i40e_hw *hw,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_lldp_start *cmd =
+ (struct i40e_aqc_lldp_start *)&desc.params.raw;
+ i40e_status status;
+
+ i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_lldp_start);
+
+ cmd->command = I40E_AQ_LLDP_AGENT_START;
+
+ status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+ return status;
+}
+
+/**
+ * i40e_aq_delete_element - Delete switch element
+ * @hw: pointer to the hw struct
+ * @seid: the SEID to delete from the switch
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * This deletes a switch element from the switch.
+ **/
+i40e_status i40e_aq_delete_element(struct i40e_hw *hw, u16 seid,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_switch_seid *cmd =
+ (struct i40e_aqc_switch_seid *)&desc.params.raw;
+ i40e_status status;
+
+ if (seid == 0)
+ return I40E_ERR_PARAM;
+
+ i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_delete_element);
+
+ cmd->seid = cpu_to_le16(seid);
+
+ status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+ return status;
+}
+
+/**
+ * i40e_aq_tx_sched_cmd - generic Tx scheduler AQ command handler
+ * @hw: pointer to the hw struct
+ * @seid: seid for the physical port/switching component/vsi
+ * @buff: Indirect buffer to hold data parameters and response
+ * @buff_size: Indirect buffer size
+ * @opcode: Tx scheduler AQ command opcode
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Generic command handler for Tx scheduler AQ commands
+ **/
+static i40e_status i40e_aq_tx_sched_cmd(struct i40e_hw *hw, u16 seid,
+ void *buff, u16 buff_size,
+ enum i40e_admin_queue_opc opcode,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_tx_sched_ind *cmd =
+ (struct i40e_aqc_tx_sched_ind *)&desc.params.raw;
+ i40e_status status;
+ bool cmd_param_flag = false;
+
+ switch (opcode) {
+ case i40e_aqc_opc_configure_vsi_ets_sla_bw_limit:
+ case i40e_aqc_opc_configure_vsi_tc_bw:
+ case i40e_aqc_opc_enable_switching_comp_ets:
+ case i40e_aqc_opc_modify_switching_comp_ets:
+ case i40e_aqc_opc_disable_switching_comp_ets:
+ case i40e_aqc_opc_configure_switching_comp_ets_bw_limit:
+ case i40e_aqc_opc_configure_switching_comp_bw_config:
+ cmd_param_flag = true;
+ break;
+ case i40e_aqc_opc_query_vsi_bw_config:
+ case i40e_aqc_opc_query_vsi_ets_sla_config:
+ case i40e_aqc_opc_query_switching_comp_ets_config:
+ case i40e_aqc_opc_query_port_ets_config:
+ case i40e_aqc_opc_query_switching_comp_bw_config:
+ cmd_param_flag = false;
+ break;
+ default:
+ return I40E_ERR_PARAM;
+ }
+
+ i40e_fill_default_direct_cmd_desc(&desc, opcode);
+
+ /* Indirect command */
+ desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+ if (cmd_param_flag)
+ desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_RD);
+ if (buff_size > I40E_AQ_LARGE_BUF)
+ desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+
+ desc.datalen = cpu_to_le16(buff_size);
+
+ cmd->vsi_seid = cpu_to_le16(seid);
+
+ status = i40e_asq_send_command(hw, &desc, buff, buff_size, cmd_details);
+
+ return status;
+}
+
+/**
+ * i40e_aq_config_vsi_tc_bw - Config VSI BW Allocation per TC
+ * @hw: pointer to the hw struct
+ * @seid: VSI seid
+ * @bw_data: Buffer holding enabled TCs, relative TC BW limit/credits
+ * @cmd_details: pointer to command details structure or NULL
+ **/
+i40e_status i40e_aq_config_vsi_tc_bw(struct i40e_hw *hw,
+ u16 seid,
+ struct i40e_aqc_configure_vsi_tc_bw_data *bw_data,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ return i40e_aq_tx_sched_cmd(hw, seid, (void *)bw_data, sizeof(*bw_data),
+ i40e_aqc_opc_configure_vsi_tc_bw,
+ cmd_details);
+}
+
+/**
+ * i40e_aq_query_vsi_bw_config - Query VSI BW configuration
+ * @hw: pointer to the hw struct
+ * @seid: seid of the VSI
+ * @bw_data: Buffer to hold VSI BW configuration
+ * @cmd_details: pointer to command details structure or NULL
+ **/
+i40e_status i40e_aq_query_vsi_bw_config(struct i40e_hw *hw,
+ u16 seid,
+ struct i40e_aqc_query_vsi_bw_config_resp *bw_data,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ return i40e_aq_tx_sched_cmd(hw, seid, (void *)bw_data, sizeof(*bw_data),
+ i40e_aqc_opc_query_vsi_bw_config,
+ cmd_details);
+}
+
+/**
+ * i40e_aq_query_vsi_ets_sla_config - Query VSI BW configuration per TC
+ * @hw: pointer to the hw struct
+ * @seid: seid of the VSI
+ * @bw_data: Buffer to hold VSI BW configuration per TC
+ * @cmd_details: pointer to command details structure or NULL
+ **/
+i40e_status i40e_aq_query_vsi_ets_sla_config(struct i40e_hw *hw,
+ u16 seid,
+ struct i40e_aqc_query_vsi_ets_sla_config_resp *bw_data,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ return i40e_aq_tx_sched_cmd(hw, seid, (void *)bw_data, sizeof(*bw_data),
+ i40e_aqc_opc_query_vsi_ets_sla_config,
+ cmd_details);
+}
+
+/**
+ * i40e_aq_query_switch_comp_ets_config - Query Switch comp BW config per TC
+ * @hw: pointer to the hw struct
+ * @seid: seid of the switching component
+ * @bw_data: Buffer to hold switching component's per TC BW config
+ * @cmd_details: pointer to command details structure or NULL
+ **/
+i40e_status i40e_aq_query_switch_comp_ets_config(struct i40e_hw *hw,
+ u16 seid,
+ struct i40e_aqc_query_switching_comp_ets_config_resp *bw_data,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ return i40e_aq_tx_sched_cmd(hw, seid, (void *)bw_data, sizeof(*bw_data),
+ i40e_aqc_opc_query_switching_comp_ets_config,
+ cmd_details);
+}
+
+/**
+ * i40e_aq_query_port_ets_config - Query Physical Port ETS configuration
+ * @hw: pointer to the hw struct
+ * @seid: seid of the VSI or switching component connected to Physical Port
+ * @bw_data: Buffer to hold current ETS configuration for the Physical Port
+ * @cmd_details: pointer to command details structure or NULL
+ **/
+i40e_status i40e_aq_query_port_ets_config(struct i40e_hw *hw,
+ u16 seid,
+ struct i40e_aqc_query_port_ets_config_resp *bw_data,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ return i40e_aq_tx_sched_cmd(hw, seid, (void *)bw_data, sizeof(*bw_data),
+ i40e_aqc_opc_query_port_ets_config,
+ cmd_details);
+}
+
+/**
+ * i40e_aq_query_switch_comp_bw_config - Query Switch comp BW configuration
+ * @hw: pointer to the hw struct
+ * @seid: seid of the switching component
+ * @bw_data: Buffer to hold switching component's BW configuration
+ * @cmd_details: pointer to command details structure or NULL
+ **/
+i40e_status i40e_aq_query_switch_comp_bw_config(struct i40e_hw *hw,
+ u16 seid,
+ struct i40e_aqc_query_switching_comp_bw_config_resp *bw_data,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ return i40e_aq_tx_sched_cmd(hw, seid, (void *)bw_data, sizeof(*bw_data),
+ i40e_aqc_opc_query_switching_comp_bw_config,
+ cmd_details);
+}
+
+/**
+ * i40e_validate_filter_settings
+ * @hw: pointer to the hardware structure
+ * @settings: Filter control settings
+ *
+ * Check and validate the filter control settings passed.
+ * The function checks for the valid filter/context sizes being
+ * passed for FCoE and PE.
+ *
+ * Returns 0 if the values passed are valid and within
+ * range else returns an error.
+ **/
+static i40e_status i40e_validate_filter_settings(struct i40e_hw *hw,
+ struct i40e_filter_control_settings *settings)
+{
+ u32 fcoe_cntx_size, fcoe_filt_size;
+ u32 pe_cntx_size, pe_filt_size;
+ u32 fcoe_fmax, pe_fmax;
+ u32 val;
+
+ /* Validate FCoE settings passed */
+ switch (settings->fcoe_filt_num) {
+ case I40E_HASH_FILTER_SIZE_1K:
+ case I40E_HASH_FILTER_SIZE_2K:
+ case I40E_HASH_FILTER_SIZE_4K:
+ case I40E_HASH_FILTER_SIZE_8K:
+ case I40E_HASH_FILTER_SIZE_16K:
+ case I40E_HASH_FILTER_SIZE_32K:
+ fcoe_filt_size = I40E_HASH_FILTER_BASE_SIZE;
+ fcoe_filt_size <<= (u32)settings->fcoe_filt_num;
+ break;
+ default:
+ return I40E_ERR_PARAM;
+ }
+
+ switch (settings->fcoe_cntx_num) {
+ case I40E_DMA_CNTX_SIZE_512:
+ case I40E_DMA_CNTX_SIZE_1K:
+ case I40E_DMA_CNTX_SIZE_2K:
+ case I40E_DMA_CNTX_SIZE_4K:
+ fcoe_cntx_size = I40E_DMA_CNTX_BASE_SIZE;
+ fcoe_cntx_size <<= (u32)settings->fcoe_cntx_num;
+ break;
+ default:
+ return I40E_ERR_PARAM;
+ }
+
+ /* Validate PE settings passed */
+ switch (settings->pe_filt_num) {
+ case I40E_HASH_FILTER_SIZE_1K:
+ case I40E_HASH_FILTER_SIZE_2K:
+ case I40E_HASH_FILTER_SIZE_4K:
+ case I40E_HASH_FILTER_SIZE_8K:
+ case I40E_HASH_FILTER_SIZE_16K:
+ case I40E_HASH_FILTER_SIZE_32K:
+ case I40E_HASH_FILTER_SIZE_64K:
+ case I40E_HASH_FILTER_SIZE_128K:
+ case I40E_HASH_FILTER_SIZE_256K:
+ case I40E_HASH_FILTER_SIZE_512K:
+ case I40E_HASH_FILTER_SIZE_1M:
+ pe_filt_size = I40E_HASH_FILTER_BASE_SIZE;
+ pe_filt_size <<= (u32)settings->pe_filt_num;
+ break;
+ default:
+ return I40E_ERR_PARAM;
+ }
+
+ switch (settings->pe_cntx_num) {
+ case I40E_DMA_CNTX_SIZE_512:
+ case I40E_DMA_CNTX_SIZE_1K:
+ case I40E_DMA_CNTX_SIZE_2K:
+ case I40E_DMA_CNTX_SIZE_4K:
+ case I40E_DMA_CNTX_SIZE_8K:
+ case I40E_DMA_CNTX_SIZE_16K:
+ case I40E_DMA_CNTX_SIZE_32K:
+ case I40E_DMA_CNTX_SIZE_64K:
+ case I40E_DMA_CNTX_SIZE_128K:
+ case I40E_DMA_CNTX_SIZE_256K:
+ pe_cntx_size = I40E_DMA_CNTX_BASE_SIZE;
+ pe_cntx_size <<= (u32)settings->pe_cntx_num;
+ break;
+ default:
+ return I40E_ERR_PARAM;
+ }
+
+ /* FCHSIZE + FCDSIZE should not be greater than PMFCOEFMAX */
+ val = rd32(hw, I40E_GLHMC_FCOEFMAX);
+ fcoe_fmax = (val & I40E_GLHMC_FCOEFMAX_PMFCOEFMAX_MASK)
+ >> I40E_GLHMC_FCOEFMAX_PMFCOEFMAX_SHIFT;
+ if (fcoe_filt_size + fcoe_cntx_size > fcoe_fmax)
+ return I40E_ERR_INVALID_SIZE;
+
+ /* PEHSIZE + PEDSIZE should not be greater than PMPEXFMAX */
+ val = rd32(hw, I40E_GLHMC_PEXFMAX);
+ pe_fmax = (val & I40E_GLHMC_PEXFMAX_PMPEXFMAX_MASK)
+ >> I40E_GLHMC_PEXFMAX_PMPEXFMAX_SHIFT;
+ if (pe_filt_size + pe_cntx_size > pe_fmax)
+ return I40E_ERR_INVALID_SIZE;
+
+ return 0;
+}
+
+/**
+ * i40e_set_filter_control
+ * @hw: pointer to the hardware structure
+ * @settings: Filter control settings
+ *
+ * Set the Queue Filters for PE/FCoE and enable filters required
+ * for a single PF. It is expected that these settings are programmed
+ * at the driver initialization time.
+ **/
+i40e_status i40e_set_filter_control(struct i40e_hw *hw,
+ struct i40e_filter_control_settings *settings)
+{
+ i40e_status ret = 0;
+ u32 hash_lut_size = 0;
+ u32 val;
+
+ if (!settings)
+ return I40E_ERR_PARAM;
+
+ /* Validate the input settings */
+ ret = i40e_validate_filter_settings(hw, settings);
+ if (ret)
+ return ret;
+
+ /* Read the PF Queue Filter control register */
+ val = rd32(hw, I40E_PFQF_CTL_0);
+
+ /* Program required PE hash buckets for the PF */
+ val &= ~I40E_PFQF_CTL_0_PEHSIZE_MASK;
+ val |= ((u32)settings->pe_filt_num << I40E_PFQF_CTL_0_PEHSIZE_SHIFT) &
+ I40E_PFQF_CTL_0_PEHSIZE_MASK;
+ /* Program required PE contexts for the PF */
+ val &= ~I40E_PFQF_CTL_0_PEDSIZE_MASK;
+ val |= ((u32)settings->pe_cntx_num << I40E_PFQF_CTL_0_PEDSIZE_SHIFT) &
+ I40E_PFQF_CTL_0_PEDSIZE_MASK;
+
+ /* Program required FCoE hash buckets for the PF */
+ val &= ~I40E_PFQF_CTL_0_PFFCHSIZE_MASK;
+ val |= ((u32)settings->fcoe_filt_num <<
+ I40E_PFQF_CTL_0_PFFCHSIZE_SHIFT) &
+ I40E_PFQF_CTL_0_PFFCHSIZE_MASK;
+ /* Program required FCoE DDP contexts for the PF */
+ val &= ~I40E_PFQF_CTL_0_PFFCDSIZE_MASK;
+ val |= ((u32)settings->fcoe_cntx_num <<
+ I40E_PFQF_CTL_0_PFFCDSIZE_SHIFT) &
+ I40E_PFQF_CTL_0_PFFCDSIZE_MASK;
+
+ /* Program Hash LUT size for the PF */
+ val &= ~I40E_PFQF_CTL_0_HASHLUTSIZE_MASK;
+ if (settings->hash_lut_size == I40E_HASH_LUT_SIZE_512)
+ hash_lut_size = 1;
+ val |= (hash_lut_size << I40E_PFQF_CTL_0_HASHLUTSIZE_SHIFT) &
+ I40E_PFQF_CTL_0_HASHLUTSIZE_MASK;
+
+ /* Enable FDIR, Ethertype and MACVLAN filters for PF and VFs */
+ if (settings->enable_fdir)
+ val |= I40E_PFQF_CTL_0_FD_ENA_MASK;
+ if (settings->enable_ethtype)
+ val |= I40E_PFQF_CTL_0_ETYPE_ENA_MASK;
+ if (settings->enable_macvlan)
+ val |= I40E_PFQF_CTL_0_MACVLAN_ENA_MASK;
+
+ wr32(hw, I40E_PFQF_CTL_0, val);
+
+ return 0;
+}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
new file mode 100644
index 0000000..8dbd91f
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
@@ -0,0 +1,2076 @@
+/*******************************************************************************
+ *
+ * Intel Ethernet Controller XL710 Family Linux Driver
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ ******************************************************************************/
+
+#ifdef CONFIG_DEBUG_FS
+
+#include <linux/fs.h>
+#include <linux/debugfs.h>
+
+#include "i40e.h"
+
+static struct dentry *i40e_dbg_root;
+
+/**
+ * i40e_dbg_find_vsi - searches for the vsi with the given seid
+ * @pf - the pf structure to search for the vsi
+ * @seid - seid of the vsi it is searching for
+ **/
+static struct i40e_vsi *i40e_dbg_find_vsi(struct i40e_pf *pf, int seid)
+{
+ int i;
+
+ if (seid < 0)
+ dev_info(&pf->pdev->dev, "%d: bad seid\n", seid);
+ else
+ for (i = 0; i < pf->hw.func_caps.num_vsis; i++)
+ if (pf->vsi[i] && (pf->vsi[i]->seid == seid))
+ return pf->vsi[i];
+
+ return NULL;
+}
+
+/**
+ * i40e_dbg_find_veb - searches for the veb with the given seid
+ * @pf - the pf structure to search for the veb
+ * @seid - seid of the veb it is searching for
+ **/
+static struct i40e_veb *i40e_dbg_find_veb(struct i40e_pf *pf, int seid)
+{
+ int i;
+
+ if ((seid < I40E_BASE_VEB_SEID) ||
+ (seid > (I40E_BASE_VEB_SEID + I40E_MAX_VEB)))
+ dev_info(&pf->pdev->dev, "%d: bad seid\n", seid);
+ else
+ for (i = 0; i < I40E_MAX_VEB; i++)
+ if (pf->veb[i] && pf->veb[i]->seid == seid)
+ return pf->veb[i];
+ return NULL;
+}
+
+/**************************************************************
+ * dump
+ * The dump entry in debugfs is for getting a data snapshow of
+ * the driver's current configuration and runtime details.
+ * When the filesystem entry is written, a snapshot is taken.
+ * When the entry is read, the most recent snapshot data is dumped.
+ **************************************************************/
+static char *i40e_dbg_dump_buf;
+static ssize_t i40e_dbg_dump_data_len;
+static ssize_t i40e_dbg_dump_buffer_len;
+
+/**
+ * i40e_dbg_dump_read - read the dump data
+ * @filp: the opened file
+ * @buffer: where to write the data for the user to read
+ * @count: the size of the user's buffer
+ * @ppos: file position offset
+ **/
+static ssize_t i40e_dbg_dump_read(struct file *filp, char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ int bytes_not_copied;
+ int len;
+
+ /* is *ppos bigger than the available data? */
+ if (*ppos >= i40e_dbg_dump_data_len || !i40e_dbg_dump_buf)
+ return 0;
+
+ /* be sure to not read beyond the end of available data */
+ len = min_t(int, count, (i40e_dbg_dump_data_len - *ppos));
+
+ bytes_not_copied = copy_to_user(buffer, &i40e_dbg_dump_buf[*ppos], len);
+ if (bytes_not_copied < 0)
+ return bytes_not_copied;
+
+ *ppos += len;
+ return len;
+}
+
+/**
+ * i40e_dbg_prep_dump_buf
+ * @pf: the pf we're working with
+ * @buflen: the desired buffer length
+ *
+ * Return positive if success, 0 if failed
+ **/
+static int i40e_dbg_prep_dump_buf(struct i40e_pf *pf, int buflen)
+{
+ /* if not already big enough, prep for re alloc */
+ if (i40e_dbg_dump_buffer_len && i40e_dbg_dump_buffer_len < buflen) {
+ kfree(i40e_dbg_dump_buf);
+ i40e_dbg_dump_buffer_len = 0;
+ i40e_dbg_dump_buf = NULL;
+ }
+
+ /* get a new buffer if needed */
+ if (!i40e_dbg_dump_buf) {
+ i40e_dbg_dump_buf = kzalloc(buflen, GFP_KERNEL);
+ if (i40e_dbg_dump_buf != NULL)
+ i40e_dbg_dump_buffer_len = buflen;
+ }
+
+ return i40e_dbg_dump_buffer_len;
+}
+
+/**
+ * i40e_dbg_dump_write - trigger a datadump snapshot
+ * @filp: the opened file
+ * @buffer: where to find the user's data
+ * @count: the length of the user's data
+ * @ppos: file position offset
+ *
+ * Any write clears the stats
+ **/
+static ssize_t i40e_dbg_dump_write(struct file *filp,
+ const char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ struct i40e_pf *pf = filp->private_data;
+ char dump_request_buf[16];
+ bool seid_found = false;
+ int bytes_not_copied;
+ long seid = -1;
+ int buflen = 0;
+ int i, ret;
+ int len;
+ u8 *p;
+
+ /* don't allow partial writes */
+ if (*ppos != 0)
+ return 0;
+ if (count >= sizeof(dump_request_buf))
+ return -ENOSPC;
+
+ bytes_not_copied = copy_from_user(dump_request_buf, buffer, count);
+ if (bytes_not_copied < 0)
+ return bytes_not_copied;
+ if (bytes_not_copied > 0)
+ count -= bytes_not_copied;
+ dump_request_buf[count] = '\0';
+
+ /* decode the SEID given to be dumped */
+ ret = kstrtol(dump_request_buf, 0, &seid);
+ if (ret < 0) {
+ dev_info(&pf->pdev->dev, "bad seid value '%s'\n",
+ dump_request_buf);
+ } else if (seid == 0) {
+ seid_found = true;
+
+ kfree(i40e_dbg_dump_buf);
+ i40e_dbg_dump_buffer_len = 0;
+ i40e_dbg_dump_data_len = 0;
+ i40e_dbg_dump_buf = NULL;
+ dev_info(&pf->pdev->dev, "debug buffer freed\n");
+
+ } else if (seid == pf->pf_seid || seid == 1) {
+ seid_found = true;
+
+ buflen = sizeof(struct i40e_pf);
+ buflen += (sizeof(struct i40e_aq_desc)
+ * (pf->hw.aq.num_arq_entries + pf->hw.aq.num_asq_entries));
+
+ if (i40e_dbg_prep_dump_buf(pf, buflen)) {
+ p = i40e_dbg_dump_buf;
+
+ len = sizeof(struct i40e_pf);
+ memcpy(p, pf, len);
+ p += len;
+
+ len = (sizeof(struct i40e_aq_desc)
+ * pf->hw.aq.num_asq_entries);
+ memcpy(p, pf->hw.aq.asq.desc, len);
+ p += len;
+
+ len = (sizeof(struct i40e_aq_desc)
+ * pf->hw.aq.num_arq_entries);
+ memcpy(p, pf->hw.aq.arq.desc, len);
+ p += len;
+
+ i40e_dbg_dump_data_len = buflen;
+ dev_info(&pf->pdev->dev,
+ "PF seid %ld dumped %d bytes\n",
+ seid, (int)i40e_dbg_dump_data_len);
+ }
+ } else if (seid >= I40E_BASE_VSI_SEID) {
+ struct i40e_vsi *vsi = NULL;
+ struct i40e_mac_filter *f;
+ int filter_count = 0;
+
+ mutex_lock(&pf->switch_mutex);
+ vsi = i40e_dbg_find_vsi(pf, seid);
+ if (!vsi) {
+ mutex_unlock(&pf->switch_mutex);
+ goto write_exit;
+ }
+
+ buflen = sizeof(struct i40e_vsi);
+ buflen += sizeof(struct i40e_q_vector) * vsi->num_q_vectors;
+ buflen += sizeof(struct i40e_ring) * 2 * vsi->num_queue_pairs;
+ buflen += sizeof(struct i40e_tx_buffer) * vsi->num_queue_pairs;
+ buflen += sizeof(struct i40e_rx_buffer) * vsi->num_queue_pairs;
+ list_for_each_entry(f, &vsi->mac_filter_list, list)
+ filter_count++;
+ buflen += sizeof(struct i40e_mac_filter) * filter_count;
+
+ if (i40e_dbg_prep_dump_buf(pf, buflen)) {
+ p = i40e_dbg_dump_buf;
+ seid_found = true;
+
+ len = sizeof(struct i40e_vsi);
+ memcpy(p, vsi, len);
+ p += len;
+
+ len = (sizeof(struct i40e_q_vector)
+ * vsi->num_q_vectors);
+ memcpy(p, vsi->q_vectors, len);
+ p += len;
+
+ len = (sizeof(struct i40e_ring) * vsi->num_queue_pairs);
+ memcpy(p, vsi->tx_rings, len);
+ p += len;
+ memcpy(p, vsi->rx_rings, len);
+ p += len;
+
+ for (i = 0; i < vsi->num_queue_pairs; i++) {
+ len = sizeof(struct i40e_tx_buffer);
+ memcpy(p, vsi->tx_rings[i].tx_bi, len);
+ p += len;
+ }
+ for (i = 0; i < vsi->num_queue_pairs; i++) {
+ len = sizeof(struct i40e_rx_buffer);
+ memcpy(p, vsi->rx_rings[i].rx_bi, len);
+ p += len;
+ }
+
+ /* macvlan filter list */
+ len = sizeof(struct i40e_mac_filter);
+ list_for_each_entry(f, &vsi->mac_filter_list, list) {
+ memcpy(p, f, len);
+ p += len;
+ }
+
+ i40e_dbg_dump_data_len = buflen;
+ dev_info(&pf->pdev->dev,
+ "VSI seid %ld dumped %d bytes\n",
+ seid, (int)i40e_dbg_dump_data_len);
+ }
+ mutex_unlock(&pf->switch_mutex);
+ } else if (seid >= I40E_BASE_VEB_SEID) {
+ struct i40e_veb *veb = NULL;
+
+ mutex_lock(&pf->switch_mutex);
+ veb = i40e_dbg_find_veb(pf, seid);
+ if (!veb) {
+ mutex_unlock(&pf->switch_mutex);
+ goto write_exit;
+ }
+
+ buflen = sizeof(struct i40e_veb);
+ if (i40e_dbg_prep_dump_buf(pf, buflen)) {
+ seid_found = true;
+ memcpy(i40e_dbg_dump_buf, veb, buflen);
+ i40e_dbg_dump_data_len = buflen;
+ dev_info(&pf->pdev->dev,
+ "VEB seid %ld dumped %d bytes\n",
+ seid, (int)i40e_dbg_dump_data_len);
+ }
+ mutex_unlock(&pf->switch_mutex);
+ }
+
+write_exit:
+ if (!seid_found)
+ dev_info(&pf->pdev->dev, "unknown seid %ld\n", seid);
+
+ return count;
+}
+
+static const struct file_operations i40e_dbg_dump_fops = {
+ .owner = THIS_MODULE,
+ .open = simple_open,
+ .read = i40e_dbg_dump_read,
+ .write = i40e_dbg_dump_write,
+};
+
+/**************************************************************
+ * command
+ * The command entry in debugfs is for giving the driver commands
+ * to be executed - these may be for changing the internal switch
+ * setup, adding or removing filters, or other things. Many of
+ * these will be useful for some forms of unit testing.
+ **************************************************************/
+static char i40e_dbg_command_buf[256] = "hello world";
+
+/**
+ * i40e_dbg_command_read - read for command datum
+ * @filp: the opened file
+ * @buffer: where to write the data for the user to read
+ * @count: the size of the user's buffer
+ * @ppos: file position offset
+ **/
+static ssize_t i40e_dbg_command_read(struct file *filp, char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ struct i40e_pf *pf = filp->private_data;
+ int bytes_not_copied;
+ int buf_size = 256;
+ char *buf;
+ int len;
+
+ /* don't allow partial reads */
+ if (*ppos != 0)
+ return 0;
+ if (count < buf_size)
+ return -ENOSPC;
+
+ buf = kzalloc(buf_size, GFP_KERNEL);
+ if (!buf)
+ return -ENOSPC;
+
+ len = snprintf(buf, buf_size, "%s: %s\n",
+ pf->vsi[pf->lan_vsi]->netdev->name,
+ i40e_dbg_command_buf);
+
+ bytes_not_copied = copy_to_user(buffer, buf, len);
+ kfree(buf);
+
+ if (bytes_not_copied < 0)
+ return bytes_not_copied;
+
+ *ppos = len;
+ return len;
+}
+
+/**
+ * i40e_dbg_dump_vsi_seid - handles dump vsi seid write into pokem datum
+ * @pf: the i40e_pf created in command write
+ * @seid: the seid the user put in
+ **/
+static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid)
+{
+ struct rtnl_link_stats64 *nstat;
+ struct i40e_mac_filter *f;
+ struct i40e_vsi *vsi;
+ int i;
+
+ vsi = i40e_dbg_find_vsi(pf, seid);
+ if (!vsi) {
+ dev_info(&pf->pdev->dev,
+ "dump %d: seid not found\n", seid);
+ return;
+ }
+ dev_info(&pf->pdev->dev, "vsi seid %d\n", seid);
+ if (vsi->netdev)
+ dev_info(&pf->pdev->dev,
+ " netdev: name = %s\n",
+ vsi->netdev->name);
+ if (vsi->active_vlans)
+ dev_info(&pf->pdev->dev,
+ " vlgrp: & = %p\n", vsi->active_vlans);
+ dev_info(&pf->pdev->dev,
+ " netdev_registered = %i, current_netdev_flags = 0x%04x, state = %li flags = 0x%08lx\n",
+ vsi->netdev_registered,
+ vsi->current_netdev_flags, vsi->state, vsi->flags);
+ list_for_each_entry(f, &vsi->mac_filter_list, list) {
+ dev_info(&pf->pdev->dev,
+ " mac_filter_list: %pM vid=%d, is_netdev=%d is_vf=%d counter=%d\n",
+ f->macaddr, f->vlan, f->is_netdev, f->is_vf,
+ f->counter);
+ }
+ nstat = i40e_get_vsi_stats_struct(vsi);
+ dev_info(&pf->pdev->dev,
+ " net_stats: rx_packets = %lu, rx_bytes = %lu, rx_errors = %lu, rx_dropped = %lu\n",
+ (long unsigned int)nstat->rx_packets,
+ (long unsigned int)nstat->rx_bytes,
+ (long unsigned int)nstat->rx_errors,
+ (long unsigned int)nstat->rx_dropped);
+ dev_info(&pf->pdev->dev,
+ " net_stats: tx_packets = %lu, tx_bytes = %lu, tx_errors = %lu, tx_dropped = %lu\n",
+ (long unsigned int)nstat->tx_packets,
+ (long unsigned int)nstat->tx_bytes,
+ (long unsigned int)nstat->tx_errors,
+ (long unsigned int)nstat->tx_dropped);
+ dev_info(&pf->pdev->dev,
+ " net_stats: multicast = %lu, collisions = %lu\n",
+ (long unsigned int)nstat->multicast,
+ (long unsigned int)nstat->collisions);
+ dev_info(&pf->pdev->dev,
+ " net_stats: rx_length_errors = %lu, rx_over_errors = %lu, rx_crc_errors = %lu\n",
+ (long unsigned int)nstat->rx_length_errors,
+ (long unsigned int)nstat->rx_over_errors,
+ (long unsigned int)nstat->rx_crc_errors);
+ dev_info(&pf->pdev->dev,
+ " net_stats: rx_frame_errors = %lu, rx_fifo_errors = %lu, rx_missed_errors = %lu\n",
+ (long unsigned int)nstat->rx_frame_errors,
+ (long unsigned int)nstat->rx_fifo_errors,
+ (long unsigned int)nstat->rx_missed_errors);
+ dev_info(&pf->pdev->dev,
+ " net_stats: tx_aborted_errors = %lu, tx_carrier_errors = %lu, tx_fifo_errors = %lu\n",
+ (long unsigned int)nstat->tx_aborted_errors,
+ (long unsigned int)nstat->tx_carrier_errors,
+ (long unsigned int)nstat->tx_fifo_errors);
+ dev_info(&pf->pdev->dev,
+ " net_stats: tx_heartbeat_errors = %lu, tx_window_errors = %lu\n",
+ (long unsigned int)nstat->tx_heartbeat_errors,
+ (long unsigned int)nstat->tx_window_errors);
+ dev_info(&pf->pdev->dev,
+ " net_stats: rx_compressed = %lu, tx_compressed = %lu\n",
+ (long unsigned int)nstat->rx_compressed,
+ (long unsigned int)nstat->tx_compressed);
+ dev_info(&pf->pdev->dev,
+ " net_stats_offsets: rx_packets = %lu, rx_bytes = %lu, rx_errors = %lu, rx_dropped = %lu\n",
+ (long unsigned int)vsi->net_stats_offsets.rx_packets,
+ (long unsigned int)vsi->net_stats_offsets.rx_bytes,
+ (long unsigned int)vsi->net_stats_offsets.rx_errors,
+ (long unsigned int)vsi->net_stats_offsets.rx_dropped);
+ dev_info(&pf->pdev->dev,
+ " net_stats_offsets: tx_packets = %lu, tx_bytes = %lu, tx_errors = %lu, tx_dropped = %lu\n",
+ (long unsigned int)vsi->net_stats_offsets.tx_packets,
+ (long unsigned int)vsi->net_stats_offsets.tx_bytes,
+ (long unsigned int)vsi->net_stats_offsets.tx_errors,
+ (long unsigned int)vsi->net_stats_offsets.tx_dropped);
+ dev_info(&pf->pdev->dev,
+ " net_stats_offsets: multicast = %lu, collisions = %lu\n",
+ (long unsigned int)vsi->net_stats_offsets.multicast,
+ (long unsigned int)vsi->net_stats_offsets.collisions);
+ dev_info(&pf->pdev->dev,
+ " net_stats_offsets: rx_length_errors = %lu, rx_over_errors = %lu, rx_crc_errors = %lu\n",
+ (long unsigned int)vsi->net_stats_offsets.rx_length_errors,
+ (long unsigned int)vsi->net_stats_offsets.rx_over_errors,
+ (long unsigned int)vsi->net_stats_offsets.rx_crc_errors);
+ dev_info(&pf->pdev->dev,
+ " net_stats_offsets: rx_frame_errors = %lu, rx_fifo_errors = %lu, rx_missed_errors = %lu\n",
+ (long unsigned int)vsi->net_stats_offsets.rx_frame_errors,
+ (long unsigned int)vsi->net_stats_offsets.rx_fifo_errors,
+ (long unsigned int)vsi->net_stats_offsets.rx_missed_errors);
+ dev_info(&pf->pdev->dev,
+ " net_stats_offsets: tx_aborted_errors = %lu, tx_carrier_errors = %lu, tx_fifo_errors = %lu\n",
+ (long unsigned int)vsi->net_stats_offsets.tx_aborted_errors,
+ (long unsigned int)vsi->net_stats_offsets.tx_carrier_errors,
+ (long unsigned int)vsi->net_stats_offsets.tx_fifo_errors);
+ dev_info(&pf->pdev->dev,
+ " net_stats_offsets: tx_heartbeat_errors = %lu, tx_window_errors = %lu\n",
+ (long unsigned int)vsi->net_stats_offsets.tx_heartbeat_errors,
+ (long unsigned int)vsi->net_stats_offsets.tx_window_errors);
+ dev_info(&pf->pdev->dev,
+ " net_stats_offsets: rx_compressed = %lu, tx_compressed = %lu\n",
+ (long unsigned int)vsi->net_stats_offsets.rx_compressed,
+ (long unsigned int)vsi->net_stats_offsets.tx_compressed);
+ dev_info(&pf->pdev->dev,
+ " tx_restart = %d, tx_busy = %d, rx_buf_failed = %d, rx_page_failed = %d\n",
+ vsi->tx_restart, vsi->tx_busy,
+ vsi->rx_buf_failed, vsi->rx_page_failed);
+ if (vsi->rx_rings) {
+ for (i = 0; i < vsi->num_queue_pairs; i++) {
+ dev_info(&pf->pdev->dev,
+ " rx_rings[%i]: desc = %p\n",
+ i, vsi->rx_rings[i].desc);
+ dev_info(&pf->pdev->dev,
+ " rx_rings[%i]: dev = %p, netdev = %p, rx_bi = %p\n",
+ i, vsi->rx_rings[i].dev,
+ vsi->rx_rings[i].netdev,
+ vsi->rx_rings[i].rx_bi);
+ dev_info(&pf->pdev->dev,
+ " rx_rings[%i]: state = %li, queue_index = %d, reg_idx = %d\n",
+ i, vsi->rx_rings[i].state,
+ vsi->rx_rings[i].queue_index,
+ vsi->rx_rings[i].reg_idx);
+ dev_info(&pf->pdev->dev,
+ " rx_rings[%i]: rx_hdr_len = %d, rx_buf_len = %d, dtype = %d\n",
+ i, vsi->rx_rings[i].rx_hdr_len,
+ vsi->rx_rings[i].rx_buf_len,
+ vsi->rx_rings[i].dtype);
+ dev_info(&pf->pdev->dev,
+ " rx_rings[%i]: hsplit = %d, next_to_use = %d, next_to_clean = %d, ring_active = %i\n",
+ i, vsi->rx_rings[i].hsplit,
+ vsi->rx_rings[i].next_to_use,
+ vsi->rx_rings[i].next_to_clean,
+ vsi->rx_rings[i].ring_active);
+ dev_info(&pf->pdev->dev,
+ " rx_rings[%i]: rx_stats: packets = %lld, bytes = %lld, non_eop_descs = %lld\n",
+ i, vsi->rx_rings[i].rx_stats.packets,
+ vsi->rx_rings[i].rx_stats.bytes,
+ vsi->rx_rings[i].rx_stats.non_eop_descs);
+ dev_info(&pf->pdev->dev,
+ " rx_rings[%i]: rx_stats: alloc_rx_page_failed = %lld, alloc_rx_buff_failed = %lld\n",
+ i,
+ vsi->rx_rings[i].rx_stats.alloc_rx_page_failed,
+ vsi->rx_rings[i].rx_stats.alloc_rx_buff_failed);
+ dev_info(&pf->pdev->dev,
+ " rx_rings[%i]: size = %i, dma = 0x%08lx\n",
+ i, vsi->rx_rings[i].size,
+ (long unsigned int)vsi->rx_rings[i].dma);
+ dev_info(&pf->pdev->dev,
+ " rx_rings[%i]: vsi = %p, q_vector = %p\n",
+ i, vsi->rx_rings[i].vsi,
+ vsi->rx_rings[i].q_vector);
+ }
+ }
+ if (vsi->tx_rings) {
+ for (i = 0; i < vsi->num_queue_pairs; i++) {
+ dev_info(&pf->pdev->dev,
+ " tx_rings[%i]: desc = %p\n",
+ i, vsi->tx_rings[i].desc);
+ dev_info(&pf->pdev->dev,
+ " tx_rings[%i]: dev = %p, netdev = %p, tx_bi = %p\n",
+ i, vsi->tx_rings[i].dev,
+ vsi->tx_rings[i].netdev,
+ vsi->tx_rings[i].tx_bi);
+ dev_info(&pf->pdev->dev,
+ " tx_rings[%i]: state = %li, queue_index = %d, reg_idx = %d\n",
+ i, vsi->tx_rings[i].state,
+ vsi->tx_rings[i].queue_index,
+ vsi->tx_rings[i].reg_idx);
+ dev_info(&pf->pdev->dev,
+ " tx_rings[%i]: dtype = %d\n",
+ i, vsi->tx_rings[i].dtype);
+ dev_info(&pf->pdev->dev,
+ " tx_rings[%i]: hsplit = %d, next_to_use = %d, next_to_clean = %d, ring_active = %i\n",
+ i, vsi->tx_rings[i].hsplit,
+ vsi->tx_rings[i].next_to_use,
+ vsi->tx_rings[i].next_to_clean,
+ vsi->tx_rings[i].ring_active);
+ dev_info(&pf->pdev->dev,
+ " tx_rings[%i]: tx_stats: packets = %lld, bytes = %lld, restart_queue = %lld\n",
+ i, vsi->tx_rings[i].tx_stats.packets,
+ vsi->tx_rings[i].tx_stats.bytes,
+ vsi->tx_rings[i].tx_stats.restart_queue);
+ dev_info(&pf->pdev->dev,
+ " tx_rings[%i]: tx_stats: tx_busy = %lld, completed = %lld, tx_done_old = %lld\n",
+ i,
+ vsi->tx_rings[i].tx_stats.tx_busy,
+ vsi->tx_rings[i].tx_stats.completed,
+ vsi->tx_rings[i].tx_stats.tx_done_old);
+ dev_info(&pf->pdev->dev,
+ " tx_rings[%i]: size = %i, dma = 0x%08lx\n",
+ i, vsi->tx_rings[i].size,
+ (long unsigned int)vsi->tx_rings[i].dma);
+ dev_info(&pf->pdev->dev,
+ " tx_rings[%i]: vsi = %p, q_vector = %p\n",
+ i, vsi->tx_rings[i].vsi,
+ vsi->tx_rings[i].q_vector);
+ dev_info(&pf->pdev->dev,
+ " tx_rings[%i]: DCB tc = %d\n",
+ i, vsi->tx_rings[i].dcb_tc);
+ }
+ }
+ dev_info(&pf->pdev->dev,
+ " work_limit = %d, rx_itr_setting = %d (%s), tx_itr_setting = %d (%s)\n",
+ vsi->work_limit, vsi->rx_itr_setting,
+ ITR_IS_DYNAMIC(vsi->rx_itr_setting) ? "dynamic" : "fixed",
+ vsi->tx_itr_setting,
+ ITR_IS_DYNAMIC(vsi->tx_itr_setting) ? "dynamic" : "fixed");
+ dev_info(&pf->pdev->dev,
+ " max_frame = %d, rx_hdr_len = %d, rx_buf_len = %d dtype = %d\n",
+ vsi->max_frame, vsi->rx_hdr_len, vsi->rx_buf_len, vsi->dtype);
+ if (vsi->q_vectors) {
+ for (i = 0; i < vsi->num_q_vectors; i++) {
+ dev_info(&pf->pdev->dev,
+ " q_vectors[%i]: base index = %ld\n",
+ i, ((long int)*vsi->q_vectors[i].rx.ring-
+ (long int)*vsi->q_vectors[0].rx.ring)/
+ sizeof(struct i40e_ring));
+ }
+ }
+ dev_info(&pf->pdev->dev,
+ " num_q_vectors = %i, base_vector = %i\n",
+ vsi->num_q_vectors, vsi->base_vector);
+ dev_info(&pf->pdev->dev,
+ " seid = %d, id = %d, uplink_seid = %d\n",
+ vsi->seid, vsi->id, vsi->uplink_seid);
+ dev_info(&pf->pdev->dev,
+ " base_queue = %d, num_queue_pairs = %d, num_desc = %d\n",
+ vsi->base_queue, vsi->num_queue_pairs, vsi->num_desc);
+ dev_info(&pf->pdev->dev, " type = %i\n", vsi->type);
+ dev_info(&pf->pdev->dev,
+ " info: valid_sections = 0x%04x, switch_id = 0x%04x\n",
+ vsi->info.valid_sections, vsi->info.switch_id);
+ dev_info(&pf->pdev->dev,
+ " info: sw_reserved[] = 0x%02x 0x%02x\n",
+ vsi->info.sw_reserved[0], vsi->info.sw_reserved[1]);
+ dev_info(&pf->pdev->dev,
+ " info: sec_flags = 0x%02x, sec_reserved = 0x%02x\n",
+ vsi->info.sec_flags, vsi->info.sec_reserved);
+ dev_info(&pf->pdev->dev,
+ " info: pvid = 0x%04x, fcoe_pvid = 0x%04x, port_vlan_flags = 0x%02x\n",
+ vsi->info.pvid, vsi->info.fcoe_pvid,
+ vsi->info.port_vlan_flags);
+ dev_info(&pf->pdev->dev,
+ " info: pvlan_reserved[] = 0x%02x 0x%02x 0x%02x\n",
+ vsi->info.pvlan_reserved[0], vsi->info.pvlan_reserved[1],
+ vsi->info.pvlan_reserved[2]);
+ dev_info(&pf->pdev->dev,
+ " info: ingress_table = 0x%08x, egress_table = 0x%08x\n",
+ vsi->info.ingress_table, vsi->info.egress_table);
+ dev_info(&pf->pdev->dev,
+ " info: cas_pv_stag = 0x%04x, cas_pv_flags= 0x%02x, cas_pv_reserved = 0x%02x\n",
+ vsi->info.cas_pv_tag, vsi->info.cas_pv_flags,
+ vsi->info.cas_pv_reserved);
+ dev_info(&pf->pdev->dev,
+ " info: queue_mapping[0..7 ] = 0x%04x 0x%04x 0x%04x 0x%04x 0x%04x 0x%04x 0x%04x 0x%04x\n",
+ vsi->info.queue_mapping[0], vsi->info.queue_mapping[1],
+ vsi->info.queue_mapping[2], vsi->info.queue_mapping[3],
+ vsi->info.queue_mapping[4], vsi->info.queue_mapping[5],
+ vsi->info.queue_mapping[6], vsi->info.queue_mapping[7]);
+ dev_info(&pf->pdev->dev,
+ " info: queue_mapping[8..15] = 0x%04x 0x%04x 0x%04x 0x%04x 0x%04x 0x%04x 0x%04x 0x%04x\n",
+ vsi->info.queue_mapping[8], vsi->info.queue_mapping[9],
+ vsi->info.queue_mapping[10], vsi->info.queue_mapping[11],
+ vsi->info.queue_mapping[12], vsi->info.queue_mapping[13],
+ vsi->info.queue_mapping[14], vsi->info.queue_mapping[15]);
+ dev_info(&pf->pdev->dev,
+ " info: tc_mapping[] = 0x%04x 0x%04x 0x%04x 0x%04x 0x%04x 0x%04x 0x%04x 0x%04x\n",
+ vsi->info.tc_mapping[0], vsi->info.tc_mapping[1],
+ vsi->info.tc_mapping[2], vsi->info.tc_mapping[3],
+ vsi->info.tc_mapping[4], vsi->info.tc_mapping[5],
+ vsi->info.tc_mapping[6], vsi->info.tc_mapping[7]);
+ dev_info(&pf->pdev->dev,
+ " info: queueing_opt_flags = 0x%02x queueing_opt_reserved[0..2] = 0x%02x 0x%02x 0x%02x\n",
+ vsi->info.queueing_opt_flags,
+ vsi->info.queueing_opt_reserved[0],
+ vsi->info.queueing_opt_reserved[1],
+ vsi->info.queueing_opt_reserved[2]);
+ dev_info(&pf->pdev->dev,
+ " info: up_enable_bits = 0x%02x\n",
+ vsi->info.up_enable_bits);
+ dev_info(&pf->pdev->dev,
+ " info: sched_reserved = 0x%02x, outer_up_table = 0x%04x\n",
+ vsi->info.sched_reserved, vsi->info.outer_up_table);
+ dev_info(&pf->pdev->dev,
+ " info: cmd_reserved[] = 0x%02x 0x%02x 0x%02x 0x0%02x 0x%02x 0x%02x 0x%02x 0x0%02x\n",
+ vsi->info.cmd_reserved[0], vsi->info.cmd_reserved[1],
+ vsi->info.cmd_reserved[2], vsi->info.cmd_reserved[3],
+ vsi->info.cmd_reserved[4], vsi->info.cmd_reserved[5],
+ vsi->info.cmd_reserved[6], vsi->info.cmd_reserved[7]);
+ dev_info(&pf->pdev->dev,
+ " info: qs_handle[] = 0x%04x 0x%04x 0x%04x 0x%04x 0x%04x 0x%04x 0x%04x 0x%04x\n",
+ vsi->info.qs_handle[0], vsi->info.qs_handle[1],
+ vsi->info.qs_handle[2], vsi->info.qs_handle[3],
+ vsi->info.qs_handle[4], vsi->info.qs_handle[5],
+ vsi->info.qs_handle[6], vsi->info.qs_handle[7]);
+ dev_info(&pf->pdev->dev,
+ " info: stat_counter_idx = 0x%04x, sched_id = 0x%04x\n",
+ vsi->info.stat_counter_idx, vsi->info.sched_id);
+ dev_info(&pf->pdev->dev,
+ " info: resp_reserved[] = 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x\n",
+ vsi->info.resp_reserved[0], vsi->info.resp_reserved[1],
+ vsi->info.resp_reserved[2], vsi->info.resp_reserved[3],
+ vsi->info.resp_reserved[4], vsi->info.resp_reserved[5],
+ vsi->info.resp_reserved[6], vsi->info.resp_reserved[7],
+ vsi->info.resp_reserved[8], vsi->info.resp_reserved[9],
+ vsi->info.resp_reserved[10], vsi->info.resp_reserved[11]);
+ if (vsi->back)
+ dev_info(&pf->pdev->dev, " pf = %p\n", vsi->back);
+ dev_info(&pf->pdev->dev, " idx = %d\n", vsi->idx);
+ dev_info(&pf->pdev->dev,
+ " tc_config: numtc = %d, enabled_tc = 0x%x\n",
+ vsi->tc_config.numtc, vsi->tc_config.enabled_tc);
+ for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
+ dev_info(&pf->pdev->dev,
+ " tc_config: tc = %d, qoffset = %d, qcount = %d, netdev_tc = %d\n",
+ i, vsi->tc_config.tc_info[i].qoffset,
+ vsi->tc_config.tc_info[i].qcount,
+ vsi->tc_config.tc_info[i].netdev_tc);
+ }
+ dev_info(&pf->pdev->dev,
+ " bw: bw_limit = %d, bw_max_quanta = %d\n",
+ vsi->bw_limit, vsi->bw_max_quanta);
+ for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
+ dev_info(&pf->pdev->dev,
+ " bw[%d]: ets_share_credits = %d, ets_limit_credits = %d, max_quanta = %d\n",
+ i, vsi->bw_ets_share_credits[i],
+ vsi->bw_ets_limit_credits[i],
+ vsi->bw_ets_max_quanta[i]);
+ }
+}
+
+/**
+ * i40e_dbg_dump_aq_desc - handles dump aq_desc write into command datum
+ * @pf: the i40e_pf created in command write
+ **/
+static void i40e_dbg_dump_aq_desc(struct i40e_pf *pf)
+{
+ struct i40e_adminq_ring *ring;
+ struct i40e_hw *hw = &pf->hw;
+ int i;
+
+ /* first the send (command) ring, then the receive (event) ring */
+ dev_info(&pf->pdev->dev, "AdminQ Tx Ring\n");
+ ring = &(hw->aq.asq);
+ for (i = 0; i < ring->count; i++) {
+ struct i40e_aq_desc *d = I40E_ADMINQ_DESC(*ring, i);
+ dev_info(&pf->pdev->dev,
+ " at[%02d] flags=0x%04x op=0x%04x dlen=0x%04x ret=0x%04x cookie_h=0x%08x cookie_l=0x%08x\n",
+ i, d->flags, d->opcode, d->datalen, d->retval,
+ d->cookie_high, d->cookie_low);
+ dev_info(&pf->pdev->dev,
+ " %02x %02x %02x %02x %02x %02x %02x %02x %02x %02x %02x %02x %02x %02x %02x %02x\n",
+ d->params.raw[0], d->params.raw[1], d->params.raw[2],
+ d->params.raw[3], d->params.raw[4], d->params.raw[5],
+ d->params.raw[6], d->params.raw[7], d->params.raw[8],
+ d->params.raw[9], d->params.raw[10], d->params.raw[11],
+ d->params.raw[12], d->params.raw[13],
+ d->params.raw[14], d->params.raw[15]);
+ }
+
+ dev_info(&pf->pdev->dev, "AdminQ Rx Ring\n");
+ ring = &(hw->aq.arq);
+ for (i = 0; i < ring->count; i++) {
+ struct i40e_aq_desc *d = I40E_ADMINQ_DESC(*ring, i);
+ dev_info(&pf->pdev->dev,
+ " ar[%02d] flags=0x%04x op=0x%04x dlen=0x%04x ret=0x%04x cookie_h=0x%08x cookie_l=0x%08x\n",
+ i, d->flags, d->opcode, d->datalen, d->retval,
+ d->cookie_high, d->cookie_low);
+ dev_info(&pf->pdev->dev,
+ " %02x %02x %02x %02x %02x %02x %02x %02x %02x %02x %02x %02x %02x %02x %02x %02x\n",
+ d->params.raw[0], d->params.raw[1], d->params.raw[2],
+ d->params.raw[3], d->params.raw[4], d->params.raw[5],
+ d->params.raw[6], d->params.raw[7], d->params.raw[8],
+ d->params.raw[9], d->params.raw[10], d->params.raw[11],
+ d->params.raw[12], d->params.raw[13],
+ d->params.raw[14], d->params.raw[15]);
+ }
+}
+
+/**
+ * i40e_dbg_dump_desc - handles dump desc write into command datum
+ * @cnt: number of arguments that the user supplied
+ * @vsi_seid: vsi id entered by user
+ * @ring_id: ring id entered by user
+ * @desc_n: descriptor number entered by user
+ * @pf: the i40e_pf created in command write
+ * @is_rx_ring: true if rx, false if tx
+ **/
+static void i40e_dbg_dump_desc(int cnt, int vsi_seid, int ring_id, int desc_n,
+ struct i40e_pf *pf, bool is_rx_ring)
+{
+ union i40e_rx_desc *ds;
+ struct i40e_ring ring;
+ struct i40e_vsi *vsi;
+ int i;
+
+ vsi = i40e_dbg_find_vsi(pf, vsi_seid);
+ if (!vsi) {
+ dev_info(&pf->pdev->dev,
+ "vsi %d not found\n", vsi_seid);
+ if (is_rx_ring)
+ dev_info(&pf->pdev->dev, "dump desc rx <vsi_seid> <ring_id> [<desc_n>]\n");
+ else
+ dev_info(&pf->pdev->dev, "dump desc tx <vsi_seid> <ring_id> [<desc_n>]\n");
+ return;
+ }
+ if (ring_id >= vsi->num_queue_pairs || ring_id < 0) {
+ dev_info(&pf->pdev->dev, "ring %d not found\n", ring_id);
+ if (is_rx_ring)
+ dev_info(&pf->pdev->dev, "dump desc rx <vsi_seid> <ring_id> [<desc_n>]\n");
+ else
+ dev_info(&pf->pdev->dev, "dump desc tx <vsi_seid> <ring_id> [<desc_n>]\n");
+ return;
+ }
+ if (is_rx_ring)
+ ring = vsi->rx_rings[ring_id];
+ else
+ ring = vsi->tx_rings[ring_id];
+ if (cnt == 2) {
+ dev_info(&pf->pdev->dev, "vsi = %02i %s ring = %02i\n",
+ vsi_seid, is_rx_ring ? "rx" : "tx", ring_id);
+ for (i = 0; i < ring.count; i++) {
+ if (is_rx_ring)
+ ds = I40E_RX_DESC(&ring, i);
+ else
+ ds = (union i40e_rx_desc *)
+ I40E_TX_DESC(&ring, i);
+ if ((sizeof(union i40e_rx_desc) ==
+ sizeof(union i40e_16byte_rx_desc)) || (!is_rx_ring))
+ dev_info(&pf->pdev->dev,
+ " d[%03i] = 0x%016llx 0x%016llx\n", i,
+ ds->read.pkt_addr, ds->read.hdr_addr);
+ else
+ dev_info(&pf->pdev->dev,
+ " d[%03i] = 0x%016llx 0x%016llx 0x%016llx 0x%016llx\n",
+ i, ds->read.pkt_addr,
+ ds->read.hdr_addr,
+ ds->read.rsvd1, ds->read.rsvd2);
+ }
+ } else if (cnt == 3) {
+ if (desc_n >= ring.count || desc_n < 0) {
+ dev_info(&pf->pdev->dev,
+ "descriptor %d not found\n", desc_n);
+ return;
+ }
+ if (is_rx_ring)
+ ds = I40E_RX_DESC(&ring, desc_n);
+ else
+ ds = (union i40e_rx_desc *)I40E_TX_DESC(&ring, desc_n);
+ if ((sizeof(union i40e_rx_desc) ==
+ sizeof(union i40e_16byte_rx_desc)) || (!is_rx_ring))
+ dev_info(&pf->pdev->dev,
+ "vsi = %02i %s ring = %02i d[%03i] = 0x%016llx 0x%016llx\n",
+ vsi_seid, is_rx_ring ? "rx" : "tx", ring_id,
+ desc_n, ds->read.pkt_addr, ds->read.hdr_addr);
+ else
+ dev_info(&pf->pdev->dev,
+ "vsi = %02i rx ring = %02i d[%03i] = 0x%016llx 0x%016llx 0x%016llx 0x%016llx\n",
+ vsi_seid, ring_id,
+ desc_n, ds->read.pkt_addr, ds->read.hdr_addr,
+ ds->read.rsvd1, ds->read.rsvd2);
+ } else {
+ if (is_rx_ring)
+ dev_info(&pf->pdev->dev, "dump desc rx <vsi_seid> <ring_id> [<desc_n>]\n");
+ else
+ dev_info(&pf->pdev->dev, "dump desc tx <vsi_seid> <ring_id> [<desc_n>]\n");
+ }
+}
+
+/**
+ * i40e_dbg_dump_vsi_no_seid - handles dump vsi write into command datum
+ * @pf: the i40e_pf created in command write
+ **/
+static void i40e_dbg_dump_vsi_no_seid(struct i40e_pf *pf)
+{
+ int i;
+
+ for (i = 0; i < pf->hw.func_caps.num_vsis; i++)
+ if (pf->vsi[i])
+ dev_info(&pf->pdev->dev, "dump vsi[%d]: %d\n",
+ i, pf->vsi[i]->seid);
+}
+
+/**
+ * i40e_dbg_dump_stats - handles dump stats write into command datum
+ * @pf: the i40e_pf created in command write
+ * @estats: the eth stats structure to be dumped
+ **/
+static void i40e_dbg_dump_eth_stats(struct i40e_pf *pf,
+ struct i40e_eth_stats *estats)
+{
+ dev_info(&pf->pdev->dev, " ethstats:\n");
+ dev_info(&pf->pdev->dev,
+ " rx_bytes = \t%lld \trx_unicast = \t\t%lld \trx_multicast = \t%lld\n",
+ estats->rx_bytes, estats->rx_unicast, estats->rx_multicast);
+ dev_info(&pf->pdev->dev,
+ " rx_broadcast = \t%lld \trx_discards = \t\t%lld \trx_errors = \t%lld\n",
+ estats->rx_broadcast, estats->rx_discards, estats->rx_errors);
+ dev_info(&pf->pdev->dev,
+ " rx_missed = \t%lld \trx_unknown_protocol = \t%lld \ttx_bytes = \t%lld\n",
+ estats->rx_missed, estats->rx_unknown_protocol,
+ estats->tx_bytes);
+ dev_info(&pf->pdev->dev,
+ " tx_unicast = \t%lld \ttx_multicast = \t\t%lld \ttx_broadcast = \t%lld\n",
+ estats->tx_unicast, estats->tx_multicast, estats->tx_broadcast);
+ dev_info(&pf->pdev->dev,
+ " tx_discards = \t%lld \ttx_errors = \t\t%lld\n",
+ estats->tx_discards, estats->tx_errors);
+}
+
+/**
+ * i40e_dbg_dump_stats - handles dump stats write into command datum
+ * @pf: the i40e_pf created in command write
+ * @stats: the stats structure to be dumped
+ **/
+static void i40e_dbg_dump_stats(struct i40e_pf *pf,
+ struct i40e_hw_port_stats *stats)
+{
+ int i;
+
+ dev_info(&pf->pdev->dev, " stats:\n");
+ dev_info(&pf->pdev->dev,
+ " crc_errors = \t\t%lld \tillegal_bytes = \t%lld \terror_bytes = \t\t%lld\n",
+ stats->crc_errors, stats->illegal_bytes, stats->error_bytes);
+ dev_info(&pf->pdev->dev,
+ " mac_local_faults = \t%lld \tmac_remote_faults = \t%lld \trx_length_errors = \t%lld\n",
+ stats->mac_local_faults, stats->mac_remote_faults,
+ stats->rx_length_errors);
+ dev_info(&pf->pdev->dev,
+ " link_xon_rx = \t\t%lld \tlink_xoff_rx = \t\t%lld \tlink_xon_tx = \t\t%lld\n",
+ stats->link_xon_rx, stats->link_xoff_rx, stats->link_xon_tx);
+ dev_info(&pf->pdev->dev,
+ " link_xoff_tx = \t\t%lld \trx_size_64 = \t\t%lld \trx_size_127 = \t\t%lld\n",
+ stats->link_xoff_tx, stats->rx_size_64, stats->rx_size_127);
+ dev_info(&pf->pdev->dev,
+ " rx_size_255 = \t\t%lld \trx_size_511 = \t\t%lld \trx_size_1023 = \t\t%lld\n",
+ stats->rx_size_255, stats->rx_size_511, stats->rx_size_1023);
+ dev_info(&pf->pdev->dev,
+ " rx_size_big = \t\t%lld \trx_undersize = \t\t%lld \trx_jabber = \t\t%lld\n",
+ stats->rx_size_big, stats->rx_undersize, stats->rx_jabber);
+ dev_info(&pf->pdev->dev,
+ " rx_fragments = \t\t%lld \trx_oversize = \t\t%lld \ttx_size_64 = \t\t%lld\n",
+ stats->rx_fragments, stats->rx_oversize, stats->tx_size_64);
+ dev_info(&pf->pdev->dev,
+ " tx_size_127 = \t\t%lld \ttx_size_255 = \t\t%lld \ttx_size_511 = \t\t%lld\n",
+ stats->tx_size_127, stats->tx_size_255, stats->tx_size_511);
+ dev_info(&pf->pdev->dev,
+ " tx_size_1023 = \t\t%lld \ttx_size_big = \t\t%lld \tmac_short_packet_dropped = \t%lld\n",
+ stats->tx_size_1023, stats->tx_size_big,
+ stats->mac_short_packet_dropped);
+ for (i = 0; i < 8; i += 4) {
+ dev_info(&pf->pdev->dev,
+ " priority_xon_rx[%d] = \t%lld \t[%d] = \t%lld \t[%d] = \t%lld \t[%d] = \t%lld\n",
+ i, stats->priority_xon_rx[i],
+ i+1, stats->priority_xon_rx[i+1],
+ i+2, stats->priority_xon_rx[i+2],
+ i+3, stats->priority_xon_rx[i+3]);
+ }
+ for (i = 0; i < 8; i += 4) {
+ dev_info(&pf->pdev->dev,
+ " priority_xoff_rx[%d] = \t%lld \t[%d] = \t%lld \t[%d] = \t%lld \t[%d] = \t%lld\n",
+ i, stats->priority_xoff_rx[i],
+ i+1, stats->priority_xoff_rx[i+1],
+ i+2, stats->priority_xoff_rx[i+2],
+ i+3, stats->priority_xoff_rx[i+3]);
+ }
+ for (i = 0; i < 8; i += 4) {
+ dev_info(&pf->pdev->dev,
+ " priority_xon_tx[%d] = \t%lld \t[%d] = \t%lld \t[%d] = \t%lld \t[%d] = \t%lld\n",
+ i, stats->priority_xon_tx[i],
+ i+1, stats->priority_xon_tx[i+1],
+ i+2, stats->priority_xon_tx[i+2],
+ i+3, stats->priority_xon_rx[i+3]);
+ }
+ for (i = 0; i < 8; i += 4) {
+ dev_info(&pf->pdev->dev,
+ " priority_xoff_tx[%d] = \t%lld \t[%d] = \t%lld \t[%d] = \t%lld \t[%d] = \t%lld\n",
+ i, stats->priority_xoff_tx[i],
+ i+1, stats->priority_xoff_tx[i+1],
+ i+2, stats->priority_xoff_tx[i+2],
+ i+3, stats->priority_xoff_tx[i+3]);
+ }
+ for (i = 0; i < 8; i += 4) {
+ dev_info(&pf->pdev->dev,
+ " priority_xon_2_xoff[%d] = \t%lld \t[%d] = \t%lld \t[%d] = \t%lld \t[%d] = \t%lld\n",
+ i, stats->priority_xon_2_xoff[i],
+ i+1, stats->priority_xon_2_xoff[i+1],
+ i+2, stats->priority_xon_2_xoff[i+2],
+ i+3, stats->priority_xon_2_xoff[i+3]);
+ }
+
+ i40e_dbg_dump_eth_stats(pf, &stats->eth);
+}
+
+/**
+ * i40e_dbg_dump_veb_seid - handles dump stats of a single given veb
+ * @pf: the i40e_pf created in command write
+ * @seid: the seid the user put in
+ **/
+static void i40e_dbg_dump_veb_seid(struct i40e_pf *pf, int seid)
+{
+ struct i40e_veb *veb;
+
+ if ((seid < I40E_BASE_VEB_SEID) ||
+ (seid >= (I40E_MAX_VEB + I40E_BASE_VEB_SEID))) {
+ dev_info(&pf->pdev->dev, "%d: bad seid\n", seid);
+ return;
+ }
+
+ veb = i40e_dbg_find_veb(pf, seid);
+ if (!veb) {
+ dev_info(&pf->pdev->dev,
+ "%d: can't find veb\n", seid);
+ return;
+ }
+ dev_info(&pf->pdev->dev,
+ "veb idx=%d,%d stats_ic=%d seid=%d uplink=%d\n",
+ veb->idx, veb->veb_idx, veb->stats_idx, veb->seid,
+ veb->uplink_seid);
+ i40e_dbg_dump_eth_stats(pf, &veb->stats);
+}
+
+/**
+ * i40e_dbg_dump_veb_all - dumps all known veb's stats
+ * @pf: the i40e_pf created in command write
+ **/
+static void i40e_dbg_dump_veb_all(struct i40e_pf *pf)
+{
+ struct i40e_veb *veb;
+ int i;
+
+ for (i = 0; i < I40E_MAX_VEB; i++) {
+ veb = pf->veb[i];
+ if (veb)
+ i40e_dbg_dump_veb_seid(pf, veb->seid);
+ }
+}
+
+#define I40E_MAX_DEBUG_OUT_BUFFER (4096*4)
+/**
+ * i40e_dbg_command_write - write into command datum
+ * @filp: the opened file
+ * @buffer: where to find the user's data
+ * @count: the length of the user's data
+ * @ppos: file position offset
+ **/
+static ssize_t i40e_dbg_command_write(struct file *filp,
+ const char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ struct i40e_pf *pf = filp->private_data;
+ int bytes_not_copied;
+ struct i40e_vsi *vsi;
+ u8 *print_buf_start;
+ u8 *print_buf;
+ char *cmd_buf;
+ int vsi_seid;
+ int veb_seid;
+ int cnt;
+
+ /* don't allow partial writes */
+ if (*ppos != 0)
+ return 0;
+
+ cmd_buf = kzalloc(count + 1, GFP_KERNEL);
+ if (!cmd_buf)
+ return count;
+ bytes_not_copied = copy_from_user(cmd_buf, buffer, count);
+ if (bytes_not_copied < 0)
+ return bytes_not_copied;
+ if (bytes_not_copied > 0)
+ count -= bytes_not_copied;
+ cmd_buf[count] = '\0';
+
+ print_buf_start = kzalloc(I40E_MAX_DEBUG_OUT_BUFFER, GFP_KERNEL);
+ if (!print_buf_start)
+ goto command_write_done;
+ print_buf = print_buf_start;
+
+ if (strncmp(cmd_buf, "add vsi", 7) == 0) {
+ vsi_seid = -1;
+ cnt = sscanf(&cmd_buf[7], "%i", &vsi_seid);
+ if (cnt == 0) {
+ /* default to PF VSI */
+ vsi_seid = pf->vsi[pf->lan_vsi]->seid;
+ } else if (vsi_seid < 0) {
+ dev_info(&pf->pdev->dev, "add VSI %d: bad vsi seid\n",
+ vsi_seid);
+ goto command_write_done;
+ }
+
+ vsi = i40e_vsi_setup(pf, I40E_VSI_VMDQ2, vsi_seid, 0);
+ if (vsi)
+ dev_info(&pf->pdev->dev, "added VSI %d to relay %d\n",
+ vsi->seid, vsi->uplink_seid);
+ else
+ dev_info(&pf->pdev->dev, "'%s' failed\n", cmd_buf);
+
+ } else if (strncmp(cmd_buf, "del vsi", 7) == 0) {
+ sscanf(&cmd_buf[7], "%i", &vsi_seid);
+ vsi = i40e_dbg_find_vsi(pf, vsi_seid);
+ if (!vsi) {
+ dev_info(&pf->pdev->dev, "del VSI %d: seid not found\n",
+ vsi_seid);
+ goto command_write_done;
+ }
+
+ dev_info(&pf->pdev->dev, "deleting VSI %d\n", vsi_seid);
+ i40e_vsi_release(vsi);
+
+ } else if (strncmp(cmd_buf, "add relay", 9) == 0) {
+ struct i40e_veb *veb;
+ int uplink_seid, i;
+
+ cnt = sscanf(&cmd_buf[9], "%i %i", &uplink_seid, &vsi_seid);
+ if (cnt != 2) {
+ dev_info(&pf->pdev->dev,
+ "add relay: bad command string, cnt=%d\n",
+ cnt);
+ goto command_write_done;
+ } else if (uplink_seid < 0) {
+ dev_info(&pf->pdev->dev,
+ "add relay %d: bad uplink seid\n",
+ uplink_seid);
+ goto command_write_done;
+ }
+
+ vsi = i40e_dbg_find_vsi(pf, vsi_seid);
+ if (!vsi) {
+ dev_info(&pf->pdev->dev,
+ "add relay: vsi VSI %d not found\n", vsi_seid);
+ goto command_write_done;
+ }
+
+ for (i = 0; i < I40E_MAX_VEB; i++)
+ if (pf->veb[i] && pf->veb[i]->seid == uplink_seid)
+ break;
+ if (i >= I40E_MAX_VEB && uplink_seid != 0 &&
+ uplink_seid != pf->mac_seid) {
+ dev_info(&pf->pdev->dev,
+ "add relay: relay uplink %d not found\n",
+ uplink_seid);
+ goto command_write_done;
+ }
+
+ veb = i40e_veb_setup(pf, 0, uplink_seid, vsi_seid,
+ vsi->tc_config.enabled_tc);
+ if (veb)
+ dev_info(&pf->pdev->dev, "added relay %d\n", veb->seid);
+ else
+ dev_info(&pf->pdev->dev, "add relay failed\n");
+
+ } else if (strncmp(cmd_buf, "del relay", 9) == 0) {
+ int i;
+ cnt = sscanf(&cmd_buf[9], "%i", &veb_seid);
+ if (cnt != 1) {
+ dev_info(&pf->pdev->dev,
+ "del relay: bad command string, cnt=%d\n",
+ cnt);
+ goto command_write_done;
+ } else if (veb_seid < 0) {
+ dev_info(&pf->pdev->dev,
+ "del relay %d: bad relay seid\n", veb_seid);
+ goto command_write_done;
+ }
+
+ /* find the veb */
+ for (i = 0; i < I40E_MAX_VEB; i++)
+ if (pf->veb[i] && pf->veb[i]->seid == veb_seid)
+ break;
+ if (i >= I40E_MAX_VEB) {
+ dev_info(&pf->pdev->dev,
+ "del relay: relay %d not found\n", veb_seid);
+ goto command_write_done;
+ }
+
+ dev_info(&pf->pdev->dev, "deleting relay %d\n", veb_seid);
+ i40e_veb_release(pf->veb[i]);
+
+ } else if (strncmp(cmd_buf, "add macaddr", 11) == 0) {
+ u8 ma[6];
+ int vlan = 0;
+ struct i40e_mac_filter *f;
+ int ret;
+
+ cnt = sscanf(&cmd_buf[11],
+ "%i %hhx:%hhx:%hhx:%hhx:%hhx:%hhx %i",
+ &vsi_seid,
+ &ma[0], &ma[1], &ma[2], &ma[3], &ma[4], &ma[5],
+ &vlan);
+ if (cnt == 7) {
+ vlan = 0;
+ } else if (cnt != 8) {
+ dev_info(&pf->pdev->dev,
+ "add macaddr: bad command string, cnt=%d\n",
+ cnt);
+ goto command_write_done;
+ }
+
+ vsi = i40e_dbg_find_vsi(pf, vsi_seid);
+ if (!vsi) {
+ dev_info(&pf->pdev->dev,
+ "add macaddr: VSI %d not found\n", vsi_seid);
+ goto command_write_done;
+ }
+
+ f = i40e_add_filter(vsi, ma, vlan, false, false);
+ ret = i40e_sync_vsi_filters(vsi);
+ if (f && !ret)
+ dev_info(&pf->pdev->dev,
+ "add macaddr: %pM vlan=%d added to VSI %d\n",
+ ma, vlan, vsi_seid);
+ else
+ dev_info(&pf->pdev->dev,
+ "add macaddr: %pM vlan=%d to VSI %d failed, f=%p ret=%d\n",
+ ma, vlan, vsi_seid, f, ret);
+
+ } else if (strncmp(cmd_buf, "del macaddr", 11) == 0) {
+ u8 ma[6];
+ int vlan = 0;
+ int ret;
+
+ cnt = sscanf(&cmd_buf[11],
+ "%i %hhx:%hhx:%hhx:%hhx:%hhx:%hhx %i",
+ &vsi_seid,
+ &ma[0], &ma[1], &ma[2], &ma[3], &ma[4], &ma[5],
+ &vlan);
+ if (cnt == 7) {
+ vlan = 0;
+ } else if (cnt != 8) {
+ dev_info(&pf->pdev->dev,
+ "del macaddr: bad command string, cnt=%d\n",
+ cnt);
+ goto command_write_done;
+ }
+
+ vsi = i40e_dbg_find_vsi(pf, vsi_seid);
+ if (!vsi) {
+ dev_info(&pf->pdev->dev,
+ "del macaddr: VSI %d not found\n", vsi_seid);
+ goto command_write_done;
+ }
+
+ i40e_del_filter(vsi, ma, vlan, false, false);
+ ret = i40e_sync_vsi_filters(vsi);
+ if (!ret)
+ dev_info(&pf->pdev->dev,
+ "del macaddr: %pM vlan=%d removed from VSI %d\n",
+ ma, vlan, vsi_seid);
+ else
+ dev_info(&pf->pdev->dev,
+ "del macaddr: %pM vlan=%d from VSI %d failed, ret=%d\n",
+ ma, vlan, vsi_seid, ret);
+
+ } else if (strncmp(cmd_buf, "add pvid", 8) == 0) {
+ int v;
+ u16 vid;
+ i40e_status ret;
+
+ cnt = sscanf(&cmd_buf[8], "%i %u", &vsi_seid, &v);
+ if (cnt != 2) {
+ dev_info(&pf->pdev->dev,
+ "add pvid: bad command string, cnt=%d\n", cnt);
+ goto command_write_done;
+ }
+
+ vsi = i40e_dbg_find_vsi(pf, vsi_seid);
+ if (!vsi) {
+ dev_info(&pf->pdev->dev, "add pvid: VSI %d not found\n",
+ vsi_seid);
+ goto command_write_done;
+ }
+
+ vid = (unsigned)v;
+ ret = i40e_vsi_add_pvid(vsi, vid);
+ if (!ret)
+ dev_info(&pf->pdev->dev,
+ "add pvid: %d added to VSI %d\n",
+ vid, vsi_seid);
+ else
+ dev_info(&pf->pdev->dev,
+ "add pvid: %d to VSI %d failed, ret=%d\n",
+ vid, vsi_seid, ret);
+
+ } else if (strncmp(cmd_buf, "del pvid", 8) == 0) {
+
+ cnt = sscanf(&cmd_buf[8], "%i", &vsi_seid);
+ if (cnt != 1) {
+ dev_info(&pf->pdev->dev,
+ "del pvid: bad command string, cnt=%d\n",
+ cnt);
+ goto command_write_done;
+ }
+
+ vsi = i40e_dbg_find_vsi(pf, vsi_seid);
+ if (!vsi) {
+ dev_info(&pf->pdev->dev,
+ "del pvid: VSI %d not found\n", vsi_seid);
+ goto command_write_done;
+ }
+
+ i40e_vsi_remove_pvid(vsi);
+ dev_info(&pf->pdev->dev,
+ "del pvid: removed from VSI %d\n", vsi_seid);
+
+ } else if (strncmp(cmd_buf, "dump", 4) == 0) {
+ if (strncmp(&cmd_buf[5], "switch", 6) == 0) {
+ i40e_fetch_switch_configuration(pf, true);
+ } else if (strncmp(&cmd_buf[5], "vsi", 3) == 0) {
+ cnt = sscanf(&cmd_buf[8], "%i", &vsi_seid);
+ if (cnt > 0)
+ i40e_dbg_dump_vsi_seid(pf, vsi_seid);
+ else
+ i40e_dbg_dump_vsi_no_seid(pf);
+ } else if (strncmp(&cmd_buf[5], "veb", 3) == 0) {
+ cnt = sscanf(&cmd_buf[8], "%i", &vsi_seid);
+ if (cnt > 0)
+ i40e_dbg_dump_veb_seid(pf, vsi_seid);
+ else
+ i40e_dbg_dump_veb_all(pf);
+ } else if (strncmp(&cmd_buf[5], "desc", 4) == 0) {
+ int ring_id, desc_n;
+ if (strncmp(&cmd_buf[10], "rx", 2) == 0) {
+ cnt = sscanf(&cmd_buf[12], "%i %i %i",
+ &vsi_seid, &ring_id, &desc_n);
+ i40e_dbg_dump_desc(cnt, vsi_seid, ring_id,
+ desc_n, pf, true);
+ } else if (strncmp(&cmd_buf[10], "tx", 2)
+ == 0) {
+ cnt = sscanf(&cmd_buf[12], "%i %i %i",
+ &vsi_seid, &ring_id, &desc_n);
+ i40e_dbg_dump_desc(cnt, vsi_seid, ring_id,
+ desc_n, pf, false);
+ } else if (strncmp(&cmd_buf[10], "aq", 2) == 0) {
+ i40e_dbg_dump_aq_desc(pf);
+ } else {
+ dev_info(&pf->pdev->dev,
+ "dump desc tx <vsi_seid> <ring_id> [<desc_n>]\n");
+ dev_info(&pf->pdev->dev,
+ "dump desc rx <vsi_seid> <ring_id> [<desc_n>]\n");
+ dev_info(&pf->pdev->dev, "dump desc aq\n");
+ }
+ } else if (strncmp(&cmd_buf[5], "stats", 5) == 0) {
+ dev_info(&pf->pdev->dev, "pf stats:\n");
+ i40e_dbg_dump_stats(pf, &pf->stats);
+ dev_info(&pf->pdev->dev, "pf stats_offsets:\n");
+ i40e_dbg_dump_stats(pf, &pf->stats_offsets);
+ } else if (strncmp(&cmd_buf[5], "reset stats", 11) == 0) {
+ dev_info(&pf->pdev->dev,
+ "core reset count: %d\n", pf->corer_count);
+ dev_info(&pf->pdev->dev,
+ "global reset count: %d\n", pf->globr_count);
+ dev_info(&pf->pdev->dev,
+ "emp reset count: %d\n", pf->empr_count);
+ dev_info(&pf->pdev->dev,
+ "pf reset count: %d\n", pf->pfr_count);
+ } else if (strncmp(&cmd_buf[5], "port", 4) == 0) {
+ struct i40e_aqc_query_port_ets_config_resp *bw_data;
+ struct i40e_dcbx_config *cfg =
+ &pf->hw.local_dcbx_config;
+ struct i40e_dcbx_config *r_cfg =
+ &pf->hw.remote_dcbx_config;
+ int i, ret;
+
+ bw_data = kzalloc(sizeof(
+ struct i40e_aqc_query_port_ets_config_resp),
+ GFP_KERNEL);
+ if (!bw_data) {
+ ret = -ENOMEM;
+ goto command_write_done;
+ }
+
+ ret = i40e_aq_query_port_ets_config(&pf->hw,
+ pf->mac_seid,
+ bw_data, NULL);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "Query Port ETS Config AQ command failed =0x%x\n",
+ pf->hw.aq.asq_last_status);
+ kfree(bw_data);
+ bw_data = NULL;
+ goto command_write_done;
+ }
+ dev_info(&pf->pdev->dev,
+ "port bw: tc_valid=0x%x tc_strict_prio=0x%x, tc_bw_max=0x%04x,0x%04x\n",
+ bw_data->tc_valid_bits,
+ bw_data->tc_strict_priority_bits,
+ le16_to_cpu(bw_data->tc_bw_max[0]),
+ le16_to_cpu(bw_data->tc_bw_max[1]));
+ for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
+ dev_info(&pf->pdev->dev, "port bw: tc_bw_share=%d tc_bw_limit=%d\n",
+ bw_data->tc_bw_share_credits[i],
+ le16_to_cpu(bw_data->tc_bw_limits[i]));
+ }
+
+ kfree(bw_data);
+ bw_data = NULL;
+
+ dev_info(&pf->pdev->dev,
+ "port ets_cfg: willing=%d cbs=%d, maxtcs=%d\n",
+ cfg->etscfg.willing, cfg->etscfg.cbs,
+ cfg->etscfg.maxtcs);
+ for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
+ dev_info(&pf->pdev->dev, "port ets_cfg: %d prio_tc=%d tcbw=%d tctsa=%d\n",
+ i, cfg->etscfg.prioritytable[i],
+ cfg->etscfg.tcbwtable[i],
+ cfg->etscfg.tsatable[i]);
+ }
+ for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
+ dev_info(&pf->pdev->dev, "port ets_rec: %d prio_tc=%d tcbw=%d tctsa=%d\n",
+ i, cfg->etsrec.prioritytable[i],
+ cfg->etsrec.tcbwtable[i],
+ cfg->etsrec.tsatable[i]);
+ }
+ dev_info(&pf->pdev->dev,
+ "port pfc_cfg: willing=%d mbc=%d, pfccap=%d pfcenable=0x%x\n",
+ cfg->pfc.willing, cfg->pfc.mbc,
+ cfg->pfc.pfccap, cfg->pfc.pfcenable);
+ dev_info(&pf->pdev->dev,
+ "port app_table: num_apps=%d\n", cfg->numapps);
+ for (i = 0; i < cfg->numapps; i++) {
+ dev_info(&pf->pdev->dev, "port app_table: %d prio=%d selector=%d protocol=0x%x\n",
+ i, cfg->app[i].priority,
+ cfg->app[i].selector,
+ cfg->app[i].protocolid);
+ }
+ /* Peer TLV DCBX data */
+ dev_info(&pf->pdev->dev,
+ "remote port ets_cfg: willing=%d cbs=%d, maxtcs=%d\n",
+ r_cfg->etscfg.willing,
+ r_cfg->etscfg.cbs, r_cfg->etscfg.maxtcs);
+ for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
+ dev_info(&pf->pdev->dev, "remote port ets_cfg: %d prio_tc=%d tcbw=%d tctsa=%d\n",
+ i, r_cfg->etscfg.prioritytable[i],
+ r_cfg->etscfg.tcbwtable[i],
+ r_cfg->etscfg.tsatable[i]);
+ }
+ for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
+ dev_info(&pf->pdev->dev, "remote port ets_rec: %d prio_tc=%d tcbw=%d tctsa=%d\n",
+ i, r_cfg->etsrec.prioritytable[i],
+ r_cfg->etsrec.tcbwtable[i],
+ r_cfg->etsrec.tsatable[i]);
+ }
+ dev_info(&pf->pdev->dev,
+ "remote port pfc_cfg: willing=%d mbc=%d, pfccap=%d pfcenable=0x%x\n",
+ r_cfg->pfc.willing,
+ r_cfg->pfc.mbc,
+ r_cfg->pfc.pfccap,
+ r_cfg->pfc.pfcenable);
+ dev_info(&pf->pdev->dev,
+ "remote port app_table: num_apps=%d\n",
+ r_cfg->numapps);
+ for (i = 0; i < r_cfg->numapps; i++) {
+ dev_info(&pf->pdev->dev, "remote port app_table: %d prio=%d selector=%d protocol=0x%x\n",
+ i, r_cfg->app[i].priority,
+ r_cfg->app[i].selector,
+ r_cfg->app[i].protocolid);
+ }
+ } else {
+ dev_info(&pf->pdev->dev,
+ "dump desc tx <vsi_seid> <ring_id> [<desc_n>], dump desc rx <vsi_seid> <ring_id> [<desc_n>],\n");
+ dev_info(&pf->pdev->dev, "dump switch, dump vsi [seid] or\n");
+ dev_info(&pf->pdev->dev, "dump stats\n");
+ dev_info(&pf->pdev->dev, "dump reset stats\n");
+ dev_info(&pf->pdev->dev, "dump port\n");
+ dev_info(&pf->pdev->dev,
+ "dump debug fwdata <cluster_id> <table_id> <index>\n");
+ }
+
+ } else if (strncmp(cmd_buf, "msg_enable", 10) == 0) {
+ u32 level;
+ cnt = sscanf(&cmd_buf[10], "%i", &level);
+ if (cnt) {
+ if (I40E_DEBUG_USER & level) {
+ pf->hw.debug_mask = level;
+ dev_info(&pf->pdev->dev,
+ "set hw.debug_mask = 0x%08x\n",
+ pf->hw.debug_mask);
+ }
+ pf->msg_enable = level;
+ dev_info(&pf->pdev->dev, "set msg_enable = 0x%08x\n",
+ pf->msg_enable);
+ } else {
+ dev_info(&pf->pdev->dev, "msg_enable = 0x%08x\n",
+ pf->msg_enable);
+ }
+ } else if (strncmp(cmd_buf, "pfr", 3) == 0) {
+ dev_info(&pf->pdev->dev, "forcing PFR\n");
+ i40e_do_reset(pf, (1 << __I40E_PF_RESET_REQUESTED));
+
+ } else if (strncmp(cmd_buf, "corer", 5) == 0) {
+ dev_info(&pf->pdev->dev, "forcing CoreR\n");
+ i40e_do_reset(pf, (1 << __I40E_CORE_RESET_REQUESTED));
+
+ } else if (strncmp(cmd_buf, "globr", 5) == 0) {
+ dev_info(&pf->pdev->dev, "forcing GlobR\n");
+ i40e_do_reset(pf, (1 << __I40E_GLOBAL_RESET_REQUESTED));
+
+ } else if (strncmp(cmd_buf, "read", 4) == 0) {
+ u32 address;
+ u32 value;
+ cnt = sscanf(&cmd_buf[4], "%x", &address);
+ if (cnt != 1) {
+ dev_info(&pf->pdev->dev, "read <reg>\n");
+ goto command_write_done;
+ }
+
+ /* check the range on address */
+ if (address >= I40E_MAX_REGISTER) {
+ dev_info(&pf->pdev->dev, "read reg address 0x%08x too large\n",
+ address);
+ goto command_write_done;
+ }
+
+ value = rd32(&pf->hw, address);
+ dev_info(&pf->pdev->dev, "read: 0x%08x = 0x%08x\n",
+ address, value);
+
+ } else if (strncmp(cmd_buf, "write", 5) == 0) {
+ u32 address, value;
+ cnt = sscanf(&cmd_buf[5], "%x %x", &address, &value);
+ if (cnt != 2) {
+ dev_info(&pf->pdev->dev, "write <reg> <value>\n");
+ goto command_write_done;
+ }
+
+ /* check the range on address */
+ if (address >= I40E_MAX_REGISTER) {
+ dev_info(&pf->pdev->dev, "write reg address 0x%08x too large\n",
+ address);
+ goto command_write_done;
+ }
+ wr32(&pf->hw, address, value);
+ value = rd32(&pf->hw, address);
+ dev_info(&pf->pdev->dev, "write: 0x%08x = 0x%08x\n",
+ address, value);
+ } else if (strncmp(cmd_buf, "clear_stats", 11) == 0) {
+ if (strncmp(&cmd_buf[12], "vsi", 3) == 0) {
+ cnt = sscanf(&cmd_buf[15], "%d", &vsi_seid);
+ if (cnt == 0) {
+ int i;
+ for (i = 0; i < pf->hw.func_caps.num_vsis; i++)
+ i40e_vsi_reset_stats(pf->vsi[i]);
+ dev_info(&pf->pdev->dev, "vsi clear stats called for all vsi's\n");
+ } else if (cnt == 1) {
+ vsi = i40e_dbg_find_vsi(pf, vsi_seid);
+ if (!vsi) {
+ dev_info(&pf->pdev->dev,
+ "clear_stats vsi: bad vsi %d\n",
+ vsi_seid);
+ goto command_write_done;
+ }
+ i40e_vsi_reset_stats(vsi);
+ dev_info(&pf->pdev->dev,
+ "vsi clear stats called for vsi %d\n",
+ vsi_seid);
+ } else {
+ dev_info(&pf->pdev->dev, "clear_stats vsi [seid]\n");
+ }
+ } else if (strncmp(&cmd_buf[12], "pf", 2) == 0) {
+ i40e_pf_reset_stats(pf);
+ dev_info(&pf->pdev->dev, "pf clear stats called\n");
+ } else {
+ dev_info(&pf->pdev->dev, "clear_stats vsi [seid] or clear_stats pf\n");
+ }
+ } else if ((strncmp(cmd_buf, "add fd_filter", 13) == 0) ||
+ (strncmp(cmd_buf, "rem fd_filter", 13) == 0)) {
+ struct i40e_fdir_data fd_data;
+ int ret;
+ u16 packet_len, i, j = 0;
+ char *asc_packet;
+ bool add = false;
+
+ asc_packet = kzalloc(I40E_FDIR_MAX_RAW_PACKET_LOOKUP,
+ GFP_KERNEL);
+ if (!asc_packet)
+ goto command_write_done;
+
+ fd_data.raw_packet = kzalloc(I40E_FDIR_MAX_RAW_PACKET_LOOKUP,
+ GFP_KERNEL);
+
+ if (!fd_data.raw_packet) {
+ kfree(asc_packet);
+ asc_packet = NULL;
+ goto command_write_done;
+ }
+
+ if (strncmp(cmd_buf, "add", 3) == 0)
+ add = true;
+ cnt = sscanf(&cmd_buf[13],
+ "%hx %2hhx %2hhx %hx %2hhx %2hhx %hx %x %hd %512s",
+ &fd_data.q_index,
+ &fd_data.flex_off, &fd_data.pctype,
+ &fd_data.dest_vsi, &fd_data.dest_ctl,
+ &fd_data.fd_status, &fd_data.cnt_index,
+ &fd_data.fd_id, &packet_len, asc_packet);
+ if (cnt != 10) {
+ dev_info(&pf->pdev->dev,
+ "program fd_filter: bad command string, cnt=%d\n",
+ cnt);
+ kfree(asc_packet);
+ asc_packet = NULL;
+ kfree(fd_data.raw_packet);
+ goto command_write_done;
+ }
+
+ /* fix packet length if user entered 0 */
+ if (packet_len == 0)
+ packet_len = I40E_FDIR_MAX_RAW_PACKET_LOOKUP;
+
+ /* make sure to check the max as well */
+ packet_len = min_t(u16,
+ packet_len, I40E_FDIR_MAX_RAW_PACKET_LOOKUP);
+
+ dev_info(&pf->pdev->dev, "FD raw packet:\n");
+ for (i = 0; i < packet_len; i++) {
+ sscanf(&asc_packet[j], "%2hhx ",
+ &fd_data.raw_packet[i]);
+ j += 3;
+ snprintf(print_buf, 3, "%02x ", fd_data.raw_packet[i]);
+ print_buf += 3;
+ if ((i % 16) == 15) {
+ snprintf(print_buf, 1, "\n");
+ print_buf++;
+ }
+ }
+ dev_info(&pf->pdev->dev, "%s\n", print_buf_start);
+ ret = i40e_program_fdir_filter(&fd_data, pf, add);
+ if (!ret) {
+ dev_info(&pf->pdev->dev, "Filter command send Status : Success\n");
+ } else {
+ dev_info(&pf->pdev->dev,
+ "Filter command send failed %d\n", ret);
+ }
+ kfree(fd_data.raw_packet);
+ fd_data.raw_packet = NULL;
+ kfree(asc_packet);
+ asc_packet = NULL;
+ } else if (strncmp(cmd_buf, "lldp", 4) == 0) {
+ if (strncmp(&cmd_buf[5], "stop", 4) == 0) {
+ int ret;
+ ret = i40e_aq_stop_lldp(&pf->hw, false, NULL);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "Stop LLDP AQ command failed =0x%x\n",
+ pf->hw.aq.asq_last_status);
+ goto command_write_done;
+ }
+ } else if (strncmp(&cmd_buf[5], "start", 5) == 0) {
+ int ret;
+ ret = i40e_aq_start_lldp(&pf->hw, NULL);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "Start LLDP AQ command failed =0x%x\n",
+ pf->hw.aq.asq_last_status);
+ goto command_write_done;
+ }
+ } else if (strncmp(&cmd_buf[5],
+ "get local", 9) == 0) {
+ int ret, i;
+ u8 *buff;
+ u16 llen, rlen;
+ buff = kzalloc(I40E_LLDPDU_SIZE, GFP_KERNEL);
+ if (!buff)
+ goto command_write_done;
+
+ ret = i40e_aq_get_lldp_mib(&pf->hw, 0,
+ I40E_AQ_LLDP_MIB_LOCAL,
+ buff, I40E_LLDPDU_SIZE,
+ &llen, &rlen, NULL);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "Get LLDP MIB (local) AQ command failed =0x%x\n",
+ pf->hw.aq.asq_last_status);
+ kfree(buff);
+ buff = NULL;
+ goto command_write_done;
+ }
+ dev_info(&pf->pdev->dev,
+ "Get LLDP MIB (local) AQ buffer written back:\n");
+ for (i = 0; i < I40E_LLDPDU_SIZE; i++) {
+ snprintf(print_buf, 3, "%02x ", buff[i]);
+ print_buf += 3;
+ if ((i % 16) == 15) {
+ snprintf(print_buf, 1, "\n");
+ print_buf++;
+ }
+ }
+ dev_info(&pf->pdev->dev, "%s\n", print_buf_start);
+ kfree(buff);
+ buff = NULL;
+ } else if (strncmp(&cmd_buf[5], "get remote", 10) == 0) {
+ int ret, i;
+ u8 *buff;
+ u16 llen, rlen;
+ buff = kzalloc(I40E_LLDPDU_SIZE, GFP_KERNEL);
+ if (!buff)
+ goto command_write_done;
+
+ ret = i40e_aq_get_lldp_mib(&pf->hw,
+ I40E_AQ_LLDP_BRIDGE_TYPE_NEAREST_BRIDGE,
+ I40E_AQ_LLDP_MIB_LOCAL,
+ buff, I40E_LLDPDU_SIZE,
+ &llen, &rlen, NULL);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "Get LLDP MIB (remote) AQ command failed =0x%x\n",
+ pf->hw.aq.asq_last_status);
+ kfree(buff);
+ buff = NULL;
+ goto command_write_done;
+ }
+ dev_info(&pf->pdev->dev,
+ "Get LLDP MIB (remote) AQ buffer written back:\n");
+ for (i = 0; i < I40E_LLDPDU_SIZE; i++) {
+ snprintf(print_buf, 3, "%02x ", buff[i]);
+ print_buf += 3;
+ if ((i % 16) == 15) {
+ snprintf(print_buf, 1, "\n");
+ print_buf++;
+ }
+ }
+ dev_info(&pf->pdev->dev, "%s\n", print_buf_start);
+ kfree(buff);
+ buff = NULL;
+ } else if (strncmp(&cmd_buf[5], "event on", 8) == 0) {
+ int ret;
+ ret = i40e_aq_cfg_lldp_mib_change_event(&pf->hw,
+ true, NULL);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "Config LLDP MIB Change Event (on) AQ command failed =0x%x\n",
+ pf->hw.aq.asq_last_status);
+ goto command_write_done;
+ }
+ } else if (strncmp(&cmd_buf[5], "event off", 9) == 0) {
+ int ret;
+ ret = i40e_aq_cfg_lldp_mib_change_event(&pf->hw,
+ false, NULL);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "Config LLDP MIB Change Event (off) AQ command failed =0x%x\n",
+ pf->hw.aq.asq_last_status);
+ goto command_write_done;
+ }
+ }
+ } else if (strncmp(cmd_buf, "nvm read", 8) == 0) {
+ u16 buffer_len, i, bytes;
+ u16 module;
+ u32 offset;
+ u16 *buff;
+ int ret;
+
+ cnt = sscanf(&cmd_buf[8], "%hx %x %hx",
+ &module, &offset, &buffer_len);
+ if (cnt == 0) {
+ module = 0;
+ offset = 0;
+ buffer_len = 0;
+ } else if (cnt == 1) {
+ offset = 0;
+ buffer_len = 0;
+ } else if (cnt == 2) {
+ buffer_len = 0;
+ } else if (cnt > 3) {
+ dev_info(&pf->pdev->dev,
+ "nvm read: bad command string, cnt=%d\n", cnt);
+ goto command_write_done;
+ }
+
+ /* Read at least 512 words */
+ if (buffer_len == 0)
+ buffer_len = 512;
+
+ bytes = 2 * buffer_len;
+ buff = kzalloc(bytes, GFP_KERNEL);
+ if (!buff)
+ goto command_write_done;
+
+ ret = i40e_acquire_nvm(&pf->hw, I40E_RESOURCE_READ);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "Failed Acquiring NVM resource for read err=%d status=0x%x\n",
+ ret, pf->hw.aq.asq_last_status);
+ kfree(buff);
+ goto command_write_done;
+ }
+
+ ret = i40e_aq_read_nvm(&pf->hw, module, (2 * offset),
+ bytes, (u8 *)buff, true, NULL);
+ i40e_release_nvm(&pf->hw);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "Read NVM AQ failed err=%d status=0x%x\n",
+ ret, pf->hw.aq.asq_last_status);
+ } else {
+ dev_info(&pf->pdev->dev,
+ "Read NVM module=0x%x offset=0x%x words=%d\n",
+ module, offset, buffer_len);
+ for (i = 0; i < buffer_len; i++) {
+ if ((i % 16) == 0) {
+ snprintf(print_buf, 11, "\n0x%08x: ",
+ offset + i);
+ print_buf += 11;
+ }
+ snprintf(print_buf, 5, "%04x ", buff[i]);
+ print_buf += 5;
+ }
+ dev_info(&pf->pdev->dev, "%s\n", print_buf_start);
+ }
+ kfree(buff);
+ buff = NULL;
+ } else {
+ dev_info(&pf->pdev->dev, "unknown command '%s'\n", cmd_buf);
+ dev_info(&pf->pdev->dev, "available commands\n");
+ dev_info(&pf->pdev->dev, " add vsi [relay_seid]\n");
+ dev_info(&pf->pdev->dev, " del vsi [vsi_seid]\n");
+ dev_info(&pf->pdev->dev, " add relay <uplink_seid> <vsi_seid>\n");
+ dev_info(&pf->pdev->dev, " del relay <relay_seid>\n");
+ dev_info(&pf->pdev->dev, " add macaddr <vsi_seid> <aa:bb:cc:dd:ee:ff> [vlan]\n");
+ dev_info(&pf->pdev->dev, " del macaddr <vsi_seid> <aa:bb:cc:dd:ee:ff> [vlan]\n");
+ dev_info(&pf->pdev->dev, " add pvid <vsi_seid> <vid>\n");
+ dev_info(&pf->pdev->dev, " del pvid <vsi_seid>\n");
+ dev_info(&pf->pdev->dev, " dump switch\n");
+ dev_info(&pf->pdev->dev, " dump vsi [seid]\n");
+ dev_info(&pf->pdev->dev, " dump desc tx <vsi_seid> <ring_id> [<desc_n>]\n");
+ dev_info(&pf->pdev->dev, " dump desc rx <vsi_seid> <ring_id> [<desc_n>]\n");
+ dev_info(&pf->pdev->dev, " dump desc aq\n");
+ dev_info(&pf->pdev->dev, " dump stats\n");
+ dev_info(&pf->pdev->dev, " dump reset stats\n");
+ dev_info(&pf->pdev->dev, " msg_enable [level]\n");
+ dev_info(&pf->pdev->dev, " read <reg>\n");
+ dev_info(&pf->pdev->dev, " write <reg> <value>\n");
+ dev_info(&pf->pdev->dev, " clear_stats vsi [seid]\n");
+ dev_info(&pf->pdev->dev, " clear_stats pf\n");
+ dev_info(&pf->pdev->dev, " pfr\n");
+ dev_info(&pf->pdev->dev, " corer\n");
+ dev_info(&pf->pdev->dev, " globr\n");
+ dev_info(&pf->pdev->dev, " add fd_filter <dest q_index> <flex_off> <pctype> <dest_vsi> <dest_ctl> <fd_status> <cnt_index> <fd_id> <packet_len> <packet>\n");
+ dev_info(&pf->pdev->dev, " rem fd_filter <dest q_index> <flex_off> <pctype> <dest_vsi> <dest_ctl> <fd_status> <cnt_index> <fd_id> <packet_len> <packet>\n");
+ dev_info(&pf->pdev->dev, " lldp start\n");
+ dev_info(&pf->pdev->dev, " lldp stop\n");
+ dev_info(&pf->pdev->dev, " lldp get local\n");
+ dev_info(&pf->pdev->dev, " lldp get remote\n");
+ dev_info(&pf->pdev->dev, " lldp event on\n");
+ dev_info(&pf->pdev->dev, " lldp event off\n");
+ dev_info(&pf->pdev->dev, " nvm read [module] [word_offset] [word_count]\n");
+ }
+
+command_write_done:
+ kfree(cmd_buf);
+ cmd_buf = NULL;
+ kfree(print_buf_start);
+ print_buf = NULL;
+ print_buf_start = NULL;
+ return count;
+}
+
+static const struct file_operations i40e_dbg_command_fops = {
+ .owner = THIS_MODULE,
+ .open = simple_open,
+ .read = i40e_dbg_command_read,
+ .write = i40e_dbg_command_write,
+};
+
+/**************************************************************
+ * netdev_ops
+ * The netdev_ops entry in debugfs is for giving the driver commands
+ * to be executed from the netdev operations.
+ **************************************************************/
+static char i40e_dbg_netdev_ops_buf[256] = "hello world";
+
+/**
+ * i40e_dbg_netdev_ops - read for netdev_ops datum
+ * @filp: the opened file
+ * @buffer: where to write the data for the user to read
+ * @count: the size of the user's buffer
+ * @ppos: file position offset
+ **/
+static ssize_t i40e_dbg_netdev_ops_read(struct file *filp, char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ struct i40e_pf *pf = filp->private_data;
+ int bytes_not_copied;
+ int buf_size = 256;
+ char *buf;
+ int len;
+
+ /* don't allow partal reads */
+ if (*ppos != 0)
+ return 0;
+ if (count < buf_size)
+ return -ENOSPC;
+
+ buf = kzalloc(buf_size, GFP_KERNEL);
+ if (!buf)
+ return -ENOSPC;
+
+ len = snprintf(buf, buf_size, "%s: %s\n",
+ pf->vsi[pf->lan_vsi]->netdev->name,
+ i40e_dbg_netdev_ops_buf);
+
+ bytes_not_copied = copy_to_user(buffer, buf, len);
+ kfree(buf);
+
+ if (bytes_not_copied < 0)
+ return bytes_not_copied;
+
+ *ppos = len;
+ return len;
+}
+
+/**
+ * i40e_dbg_netdev_ops_write - write into netdev_ops datum
+ * @filp: the opened file
+ * @buffer: where to find the user's data
+ * @count: the length of the user's data
+ * @ppos: file position offset
+ **/
+static ssize_t i40e_dbg_netdev_ops_write(struct file *filp,
+ const char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ struct i40e_pf *pf = filp->private_data;
+ int bytes_not_copied;
+ struct i40e_vsi *vsi;
+ int vsi_seid;
+ int i, cnt;
+
+ /* don't allow partial writes */
+ if (*ppos != 0)
+ return 0;
+ if (count >= sizeof(i40e_dbg_netdev_ops_buf))
+ return -ENOSPC;
+
+ memset(i40e_dbg_netdev_ops_buf, 0, sizeof(i40e_dbg_netdev_ops_buf));
+ bytes_not_copied = copy_from_user(i40e_dbg_netdev_ops_buf,
+ buffer, count);
+ if (bytes_not_copied < 0)
+ return bytes_not_copied;
+ else if (bytes_not_copied > 0)
+ count -= bytes_not_copied;
+ i40e_dbg_netdev_ops_buf[count] = '\0';
+
+ if (strncmp(i40e_dbg_netdev_ops_buf, "tx_timeout", 10) == 0) {
+ cnt = sscanf(&i40e_dbg_netdev_ops_buf[11], "%i", &vsi_seid);
+ if (cnt != 1) {
+ dev_info(&pf->pdev->dev, "tx_timeout <vsi_seid>\n");
+ goto netdev_ops_write_done;
+ }
+ vsi = i40e_dbg_find_vsi(pf, vsi_seid);
+ if (!vsi) {
+ dev_info(&pf->pdev->dev,
+ "tx_timeout: VSI %d not found\n", vsi_seid);
+ goto netdev_ops_write_done;
+ }
+ if (rtnl_trylock()) {
+ vsi->netdev->netdev_ops->ndo_tx_timeout(vsi->netdev);
+ rtnl_unlock();
+ dev_info(&pf->pdev->dev, "tx_timeout called\n");
+ } else {
+ dev_info(&pf->pdev->dev, "Could not acquire RTNL - please try again\n");
+ }
+ } else if (strncmp(i40e_dbg_netdev_ops_buf, "change_mtu", 10) == 0) {
+ int mtu;
+ cnt = sscanf(&i40e_dbg_netdev_ops_buf[11], "%i %i",
+ &vsi_seid, &mtu);
+ if (cnt != 2) {
+ dev_info(&pf->pdev->dev, "change_mtu <vsi_seid> <mtu>\n");
+ goto netdev_ops_write_done;
+ }
+ vsi = i40e_dbg_find_vsi(pf, vsi_seid);
+ if (!vsi) {
+ dev_info(&pf->pdev->dev,
+ "change_mtu: VSI %d not found\n", vsi_seid);
+ goto netdev_ops_write_done;
+ }
+ if (rtnl_trylock()) {
+ vsi->netdev->netdev_ops->ndo_change_mtu(vsi->netdev,
+ mtu);
+ rtnl_unlock();
+ dev_info(&pf->pdev->dev, "change_mtu called\n");
+ } else {
+ dev_info(&pf->pdev->dev, "Could not acquire RTNL - please try again\n");
+ }
+
+ } else if (strncmp(i40e_dbg_netdev_ops_buf, "set_rx_mode", 11) == 0) {
+ cnt = sscanf(&i40e_dbg_netdev_ops_buf[11], "%i", &vsi_seid);
+ if (cnt != 1) {
+ dev_info(&pf->pdev->dev, "set_rx_mode <vsi_seid>\n");
+ goto netdev_ops_write_done;
+ }
+ vsi = i40e_dbg_find_vsi(pf, vsi_seid);
+ if (!vsi) {
+ dev_info(&pf->pdev->dev,
+ "set_rx_mode: VSI %d not found\n", vsi_seid);
+ goto netdev_ops_write_done;
+ }
+ if (rtnl_trylock()) {
+ vsi->netdev->netdev_ops->ndo_set_rx_mode(vsi->netdev);
+ rtnl_unlock();
+ dev_info(&pf->pdev->dev, "set_rx_mode called\n");
+ } else {
+ dev_info(&pf->pdev->dev, "Could not acquire RTNL - please try again\n");
+ }
+
+ } else if (strncmp(i40e_dbg_netdev_ops_buf, "napi", 4) == 0) {
+ cnt = sscanf(&i40e_dbg_netdev_ops_buf[4], "%i", &vsi_seid);
+ if (cnt != 1) {
+ dev_info(&pf->pdev->dev, "napi <vsi_seid>\n");
+ goto netdev_ops_write_done;
+ }
+ vsi = i40e_dbg_find_vsi(pf, vsi_seid);
+ if (!vsi) {
+ dev_info(&pf->pdev->dev, "napi: VSI %d not found\n",
+ vsi_seid);
+ goto netdev_ops_write_done;
+ }
+ for (i = 0; i < vsi->num_q_vectors; i++)
+ napi_schedule(&vsi->q_vectors[i].napi);
+ dev_info(&pf->pdev->dev, "napi called\n");
+ } else {
+ dev_info(&pf->pdev->dev, "unknown command '%s'\n",
+ i40e_dbg_netdev_ops_buf);
+ dev_info(&pf->pdev->dev, "available commands\n");
+ dev_info(&pf->pdev->dev, " tx_timeout <vsi_seid>\n");
+ dev_info(&pf->pdev->dev, " change_mtu <vsi_seid> <mtu>\n");
+ dev_info(&pf->pdev->dev, " set_rx_mode <vsi_seid>\n");
+ dev_info(&pf->pdev->dev, " napi <vsi_seid>\n");
+ }
+netdev_ops_write_done:
+ return count;
+}
+
+static const struct file_operations i40e_dbg_netdev_ops_fops = {
+ .owner = THIS_MODULE,
+ .open = simple_open,
+ .read = i40e_dbg_netdev_ops_read,
+ .write = i40e_dbg_netdev_ops_write,
+};
+
+/**
+ * i40e_dbg_pf_init - setup the debugfs directory for the pf
+ * @pf: the pf that is starting up
+ **/
+void i40e_dbg_pf_init(struct i40e_pf *pf)
+{
+ struct dentry *pfile __attribute__((unused));
+ const char *name = pci_name(pf->pdev);
+
+ pf->i40e_dbg_pf = debugfs_create_dir(name, i40e_dbg_root);
+ if (pf->i40e_dbg_pf) {
+ pfile = debugfs_create_file("command", 0600, pf->i40e_dbg_pf,
+ pf, &i40e_dbg_command_fops);
+ pfile = debugfs_create_file("dump", 0600, pf->i40e_dbg_pf, pf,
+ &i40e_dbg_dump_fops);
+ pfile = debugfs_create_file("netdev_ops", 0600, pf->i40e_dbg_pf,
+ pf, &i40e_dbg_netdev_ops_fops);
+ } else {
+ dev_info(&pf->pdev->dev,
+ "debugfs entry for %s failed\n", name);
+ }
+}
+
+/**
+ * i40e_dbg_pf_exit - clear out the pf's debugfs entries
+ * @pf: the pf that is stopping
+ **/
+void i40e_dbg_pf_exit(struct i40e_pf *pf)
+{
+ debugfs_remove_recursive(pf->i40e_dbg_pf);
+ pf->i40e_dbg_pf = NULL;
+
+ kfree(i40e_dbg_dump_buf);
+ i40e_dbg_dump_buf = NULL;
+}
+
+/**
+ * i40e_dbg_init - start up debugfs for the driver
+ **/
+void i40e_dbg_init(void)
+{
+ i40e_dbg_root = debugfs_create_dir(i40e_driver_name, NULL);
+ if (!i40e_dbg_root)
+ pr_info("init of debugfs failed\n");
+}
+
+/**
+ * i40e_dbg_exit - clean out the driver's debugfs entries
+ **/
+void i40e_dbg_exit(void)
+{
+ debugfs_remove_recursive(i40e_dbg_root);
+ i40e_dbg_root = NULL;
+}
+
+#endif /* CONFIG_DEBUG_FS */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_diag.c b/drivers/net/ethernet/intel/i40e/i40e_diag.c
new file mode 100644
index 0000000..de25514
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_diag.c
@@ -0,0 +1,131 @@
+/*******************************************************************************
+ *
+ * Intel Ethernet Controller XL710 Family Linux Driver
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ ******************************************************************************/
+
+#include "i40e_diag.h"
+#include "i40e_prototype.h"
+
+/**
+ * i40e_diag_reg_pattern_test
+ * @hw: pointer to the hw struct
+ * @reg: reg to be tested
+ * @mask: bits to be touched
+ **/
+static i40e_status i40e_diag_reg_pattern_test(struct i40e_hw *hw,
+ u32 reg, u32 mask)
+{
+ const u32 patterns[] = {0x5A5A5A5A, 0xA5A5A5A5, 0x00000000, 0xFFFFFFFF};
+ u32 pat, val, orig_val;
+ int i;
+
+ orig_val = rd32(hw, reg);
+ for (i = 0; i < ARRAY_SIZE(patterns); i++) {
+ pat = patterns[i];
+ wr32(hw, reg, (pat & mask));
+ val = rd32(hw, reg);
+ if ((val & mask) != (pat & mask)) {
+ i40e_debug(hw, I40E_DEBUG_DIAG,
+ "%s: reg pattern test failed - reg 0x%08x pat 0x%08x val 0x%08x\n",
+ __func__, reg, pat, val);
+ return I40E_ERR_DIAG_TEST_FAILED;
+ }
+ }
+
+ wr32(hw, reg, orig_val);
+ val = rd32(hw, reg);
+ if (val != orig_val) {
+ i40e_debug(hw, I40E_DEBUG_DIAG,
+ "%s: reg restore test failed - reg 0x%08x orig_val 0x%08x val 0x%08x\n",
+ __func__, reg, orig_val, val);
+ return I40E_ERR_DIAG_TEST_FAILED;
+ }
+
+ return 0;
+}
+
+struct i40e_diag_reg_test_info i40e_reg_list[] = {
+ /* offset mask elements stride */
+ {I40E_QTX_CTL(0), 0x0000FFBF, 64, I40E_QTX_CTL(1) - I40E_QTX_CTL(0)},
+ {I40E_PFINT_ITR0(0), 0x00000FFF, 3, I40E_PFINT_ITR0(1) - I40E_PFINT_ITR0(0)},
+ {I40E_PFINT_ITRN(0, 0), 0x00000FFF, 64, I40E_PFINT_ITRN(0, 1) - I40E_PFINT_ITRN(0, 0)},
+ {I40E_PFINT_ITRN(1, 0), 0x00000FFF, 64, I40E_PFINT_ITRN(1, 1) - I40E_PFINT_ITRN(1, 0)},
+ {I40E_PFINT_ITRN(2, 0), 0x00000FFF, 64, I40E_PFINT_ITRN(2, 1) - I40E_PFINT_ITRN(2, 0)},
+ {I40E_PFINT_STAT_CTL0, 0x0000000C, 1, 0},
+ {I40E_PFINT_LNKLST0, 0x00001FFF, 1, 0},
+ {I40E_PFINT_LNKLSTN(0), 0x000007FF, 511, I40E_PFINT_LNKLSTN(1) - I40E_PFINT_LNKLSTN(0)},
+ {I40E_QINT_TQCTL(0), 0x000000FF, I40E_QINT_TQCTL_MAX_INDEX + 1, I40E_QINT_TQCTL(1) - I40E_QINT_TQCTL(0)},
+ {I40E_QINT_RQCTL(0), 0x000000FF, I40E_QINT_RQCTL_MAX_INDEX + 1, I40E_QINT_RQCTL(1) - I40E_QINT_RQCTL(0)},
+ {I40E_PFINT_ICR0_ENA, 0xF7F20000, 1, 0},
+ { 0 }
+};
+
+/**
+ * i40e_diag_reg_test
+ * @hw: pointer to the hw struct
+ *
+ * Perform registers diagnostic test
+ **/
+i40e_status i40e_diag_reg_test(struct i40e_hw *hw)
+{
+ i40e_status ret_code = 0;
+ u32 reg, mask;
+ u32 i, j;
+
+ for (i = 0; (i40e_reg_list[i].offset != 0) && !ret_code; i++) {
+ mask = i40e_reg_list[i].mask;
+ for (j = 0; (j < i40e_reg_list[i].elements) && !ret_code; j++) {
+ reg = i40e_reg_list[i].offset +
+ (j * i40e_reg_list[i].stride);
+ ret_code = i40e_diag_reg_pattern_test(hw, reg, mask);
+ }
+ }
+
+ return ret_code;
+}
+
+/**
+ * i40e_diag_eeprom_test
+ * @hw: pointer to the hw struct
+ *
+ * Perform EEPROM diagnostic test
+ **/
+i40e_status i40e_diag_eeprom_test(struct i40e_hw *hw)
+{
+ i40e_status ret_code;
+ u16 reg_val;
+
+ /* read NVM control word and if NVM valid, validate EEPROM checksum*/
+ ret_code = i40e_read_nvm_word(hw, I40E_SR_NVM_CONTROL_WORD, ®_val);
+ if ((!ret_code) &&
+ ((reg_val & I40E_SR_CONTROL_WORD_1_MASK) ==
+ (0x01 << I40E_SR_CONTROL_WORD_1_SHIFT))) {
+ ret_code = i40e_validate_nvm_checksum(hw, NULL);
+ } else {
+ ret_code = I40E_ERR_DIAG_TEST_FAILED;
+ }
+
+ return ret_code;
+}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_diag.h b/drivers/net/ethernet/intel/i40e/i40e_diag.h
new file mode 100644
index 0000000..3d98277
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_diag.h
@@ -0,0 +1,52 @@
+/*******************************************************************************
+ *
+ * Intel Ethernet Controller XL710 Family Linux Driver
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ ******************************************************************************/
+
+#ifndef _I40E_DIAG_H_
+#define _I40E_DIAG_H_
+
+#include "i40e_type.h"
+
+enum i40e_lb_mode {
+ I40E_LB_MODE_NONE = 0,
+ I40E_LB_MODE_PHY_LOCAL,
+ I40E_LB_MODE_PHY_REMOTE,
+ I40E_LB_MODE_MAC_LOCAL,
+};
+
+struct i40e_diag_reg_test_info {
+ u32 offset; /* the base register */
+ u32 mask; /* bits that can be tested */
+ u32 elements; /* number of elements if array */
+ u32 stride; /* bytes between each element */
+};
+
+extern struct i40e_diag_reg_test_info i40e_reg_list[];
+
+i40e_status i40e_diag_reg_test(struct i40e_hw *hw);
+i40e_status i40e_diag_eeprom_test(struct i40e_hw *hw);
+
+#endif /* _I40E_DIAG_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
new file mode 100644
index 0000000..9a76b8c
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -0,0 +1,1449 @@
+/*******************************************************************************
+ *
+ * Intel Ethernet Controller XL710 Family Linux Driver
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ ******************************************************************************/
+
+/* ethtool support for i40e */
+
+#include "i40e.h"
+#include "i40e_diag.h"
+
+struct i40e_stats {
+ char stat_string[ETH_GSTRING_LEN];
+ int sizeof_stat;
+ int stat_offset;
+};
+
+#define I40E_STAT(_type, _name, _stat) { \
+ .stat_string = _name, \
+ .sizeof_stat = FIELD_SIZEOF(_type, _stat), \
+ .stat_offset = offsetof(_type, _stat) \
+}
+#define I40E_NETDEV_STAT(_net_stat) \
+ I40E_STAT(struct net_device_stats, #_net_stat, _net_stat)
+#define I40E_PF_STAT(_name, _stat) \
+ I40E_STAT(struct i40e_pf, _name, _stat)
+#define I40E_VSI_STAT(_name, _stat) \
+ I40E_STAT(struct i40e_vsi, _name, _stat)
+
+static const struct i40e_stats i40e_gstrings_net_stats[] = {
+ I40E_NETDEV_STAT(rx_packets),
+ I40E_NETDEV_STAT(tx_packets),
+ I40E_NETDEV_STAT(rx_bytes),
+ I40E_NETDEV_STAT(tx_bytes),
+ I40E_NETDEV_STAT(rx_errors),
+ I40E_NETDEV_STAT(tx_errors),
+ I40E_NETDEV_STAT(rx_dropped),
+ I40E_NETDEV_STAT(tx_dropped),
+ I40E_NETDEV_STAT(multicast),
+ I40E_NETDEV_STAT(collisions),
+ I40E_NETDEV_STAT(rx_length_errors),
+ I40E_NETDEV_STAT(rx_crc_errors),
+};
+
+/* These PF_STATs might look like duplicates of some NETDEV_STATs,
+ * but they are separate. This device supports Virtualization, and
+ * as such might have several netdevs supporting VMDq and FCoE going
+ * through a single port. The NETDEV_STATs are for individual netdevs
+ * seen at the top of the stack, and the PF_STATs are for the physical
+ * function at the bottom of the stack hosting those netdevs.
+ *
+ * The PF_STATs are appended to the netdev stats only when ethtool -S
+ * is queried on the base PF netdev, not on the VMDq or FCoE netdev.
+ */
+static struct i40e_stats i40e_gstrings_stats[] = {
+ I40E_PF_STAT("rx_bytes", stats.eth.rx_bytes),
+ I40E_PF_STAT("tx_bytes", stats.eth.tx_bytes),
+ I40E_PF_STAT("rx_errors", stats.eth.rx_errors),
+ I40E_PF_STAT("tx_errors", stats.eth.tx_errors),
+ I40E_PF_STAT("rx_dropped", stats.eth.rx_discards),
+ I40E_PF_STAT("tx_dropped", stats.eth.tx_discards),
+ I40E_PF_STAT("tx_dropped_link_down", stats.tx_dropped_link_down),
+ I40E_PF_STAT("crc_errors", stats.crc_errors),
+ I40E_PF_STAT("illegal_bytes", stats.illegal_bytes),
+ I40E_PF_STAT("mac_local_faults", stats.mac_local_faults),
+ I40E_PF_STAT("mac_remote_faults", stats.mac_remote_faults),
+ I40E_PF_STAT("rx_length_errors", stats.rx_length_errors),
+ I40E_PF_STAT("link_xon_rx", stats.link_xon_rx),
+ I40E_PF_STAT("link_xoff_rx", stats.link_xoff_rx),
+ I40E_PF_STAT("link_xon_tx", stats.link_xon_tx),
+ I40E_PF_STAT("link_xoff_tx", stats.link_xoff_tx),
+ I40E_PF_STAT("rx_size_64", stats.rx_size_64),
+ I40E_PF_STAT("rx_size_127", stats.rx_size_127),
+ I40E_PF_STAT("rx_size_255", stats.rx_size_255),
+ I40E_PF_STAT("rx_size_511", stats.rx_size_511),
+ I40E_PF_STAT("rx_size_1023", stats.rx_size_1023),
+ I40E_PF_STAT("rx_size_1522", stats.rx_size_1522),
+ I40E_PF_STAT("rx_size_big", stats.rx_size_big),
+ I40E_PF_STAT("tx_size_64", stats.tx_size_64),
+ I40E_PF_STAT("tx_size_127", stats.tx_size_127),
+ I40E_PF_STAT("tx_size_255", stats.tx_size_255),
+ I40E_PF_STAT("tx_size_511", stats.tx_size_511),
+ I40E_PF_STAT("tx_size_1023", stats.tx_size_1023),
+ I40E_PF_STAT("tx_size_1522", stats.tx_size_1522),
+ I40E_PF_STAT("tx_size_big", stats.tx_size_big),
+ I40E_PF_STAT("rx_undersize", stats.rx_undersize),
+ I40E_PF_STAT("rx_fragments", stats.rx_fragments),
+ I40E_PF_STAT("rx_oversize", stats.rx_oversize),
+ I40E_PF_STAT("rx_jabber", stats.rx_jabber),
+ I40E_PF_STAT("VF_admin_queue_requests", vf_aq_requests),
+};
+
+#define I40E_QUEUE_STATS_LEN(n) \
+ ((((struct i40e_netdev_priv *)netdev_priv((n)))->vsi->num_queue_pairs + \
+ ((struct i40e_netdev_priv *)netdev_priv((n)))->vsi->num_queue_pairs) * 2)
+#define I40E_GLOBAL_STATS_LEN ARRAY_SIZE(i40e_gstrings_stats)
+#define I40E_NETDEV_STATS_LEN ARRAY_SIZE(i40e_gstrings_net_stats)
+#define I40E_VSI_STATS_LEN(n) (I40E_NETDEV_STATS_LEN + \
+ I40E_QUEUE_STATS_LEN((n)))
+#define I40E_PFC_STATS_LEN ( \
+ (FIELD_SIZEOF(struct i40e_pf, stats.priority_xoff_rx) + \
+ FIELD_SIZEOF(struct i40e_pf, stats.priority_xon_rx) + \
+ FIELD_SIZEOF(struct i40e_pf, stats.priority_xoff_tx) + \
+ FIELD_SIZEOF(struct i40e_pf, stats.priority_xon_tx) + \
+ FIELD_SIZEOF(struct i40e_pf, stats.priority_xon_2_xoff)) \
+ / sizeof(u64))
+#define I40E_PF_STATS_LEN(n) (I40E_GLOBAL_STATS_LEN + \
+ I40E_PFC_STATS_LEN + \
+ I40E_VSI_STATS_LEN((n)))
+
+enum i40e_ethtool_test_id {
+ I40E_ETH_TEST_REG = 0,
+ I40E_ETH_TEST_EEPROM,
+ I40E_ETH_TEST_INTR,
+ I40E_ETH_TEST_LOOPBACK,
+ I40E_ETH_TEST_LINK,
+};
+
+static const char i40e_gstrings_test[][ETH_GSTRING_LEN] = {
+ "Register test (offline)",
+ "Eeprom test (offline)",
+ "Interrupt test (offline)",
+ "Loopback test (offline)",
+ "Link test (on/offline)"
+};
+
+#define I40E_TEST_LEN (sizeof(i40e_gstrings_test) / ETH_GSTRING_LEN)
+
+/**
+ * i40e_get_settings - Get Link Speed and Duplex settings
+ * @netdev: network interface device structure
+ * @ecmd: ethtool command
+ *
+ * Reports speed/duplex settings based on media_type
+ **/
+static int i40e_get_settings(struct net_device *netdev,
+ struct ethtool_cmd *ecmd)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_pf *pf = np->vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+ struct i40e_link_status *hw_link_info = &hw->phy.link_info;
+ bool link_up = hw_link_info->link_info & I40E_AQ_LINK_UP;
+ u32 link_speed = hw_link_info->link_speed;
+
+ /* hardware is either in 40G mode or 10G mode
+ * NOTE: this section initializes supported and advertising
+ */
+ switch (hw_link_info->phy_type) {
+ case I40E_PHY_TYPE_40GBASE_CR4:
+ case I40E_PHY_TYPE_40GBASE_CR4_CU:
+ ecmd->supported = SUPPORTED_40000baseCR4_Full;
+ ecmd->advertising = ADVERTISED_40000baseCR4_Full;
+ break;
+ case I40E_PHY_TYPE_40GBASE_KR4:
+ ecmd->supported = SUPPORTED_40000baseKR4_Full;
+ ecmd->advertising = ADVERTISED_40000baseKR4_Full;
+ break;
+ case I40E_PHY_TYPE_40GBASE_SR4:
+ ecmd->supported = SUPPORTED_40000baseSR4_Full;
+ ecmd->advertising = ADVERTISED_40000baseSR4_Full;
+ break;
+ case I40E_PHY_TYPE_40GBASE_LR4:
+ ecmd->supported = SUPPORTED_40000baseLR4_Full;
+ ecmd->advertising = ADVERTISED_40000baseLR4_Full;
+ break;
+ case I40E_PHY_TYPE_10GBASE_KX4:
+ ecmd->supported = SUPPORTED_10000baseKX4_Full;
+ ecmd->advertising = ADVERTISED_10000baseKX4_Full;
+ break;
+ case I40E_PHY_TYPE_10GBASE_KR:
+ ecmd->supported = SUPPORTED_10000baseKR_Full;
+ ecmd->advertising = ADVERTISED_10000baseKR_Full;
+ break;
+ case I40E_PHY_TYPE_10GBASE_T:
+ default:
+ ecmd->supported = SUPPORTED_10000baseT_Full;
+ ecmd->advertising = ADVERTISED_10000baseT_Full;
+ break;
+ }
+
+ /* for now just say autoneg all the time */
+ ecmd->supported |= SUPPORTED_Autoneg;
+
+ if (hw->phy.media_type == I40E_MEDIA_TYPE_BACKPLANE) {
+ ecmd->supported |= SUPPORTED_Backplane;
+ ecmd->advertising |= ADVERTISED_Backplane;
+ ecmd->port = PORT_NONE;
+ } else if (hw->phy.media_type == I40E_MEDIA_TYPE_BASET) {
+ ecmd->supported |= SUPPORTED_TP;
+ ecmd->advertising |= ADVERTISED_TP;
+ ecmd->port = PORT_TP;
+ } else {
+ ecmd->supported |= SUPPORTED_FIBRE;
+ ecmd->advertising |= ADVERTISED_FIBRE;
+ ecmd->port = PORT_FIBRE;
+ }
+
+ ecmd->transceiver = XCVR_EXTERNAL;
+
+ if (link_up) {
+ switch (link_speed) {
+ case I40E_LINK_SPEED_40GB:
+ /* need a SPEED_40000 in ethtool.h */
+ ethtool_cmd_speed_set(ecmd, 40000);
+ break;
+ case I40E_LINK_SPEED_10GB:
+ ethtool_cmd_speed_set(ecmd, SPEED_10000);
+ break;
+ default:
+ break;
+ }
+ ecmd->duplex = DUPLEX_FULL;
+ } else {
+ ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
+ ecmd->duplex = DUPLEX_UNKNOWN;
+ }
+
+ return 0;
+}
+
+/**
+ * i40e_get_pauseparam - Get Flow Control status
+ * Return tx/rx-pause status
+ **/
+static void i40e_get_pauseparam(struct net_device *netdev,
+ struct ethtool_pauseparam *pause)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_pf *pf = np->vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+ struct i40e_link_status *hw_link_info = &hw->phy.link_info;
+
+ pause->autoneg =
+ ((hw_link_info->an_info & I40E_AQ_AN_COMPLETED) ?
+ AUTONEG_ENABLE : AUTONEG_DISABLE);
+
+ pause->rx_pause = 0;
+ pause->tx_pause = 0;
+ if (hw_link_info->an_info & I40E_AQ_LINK_PAUSE_RX)
+ pause->rx_pause = 1;
+ if (hw_link_info->an_info & I40E_AQ_LINK_PAUSE_TX)
+ pause->tx_pause = 1;
+}
+
+static u32 i40e_get_msglevel(struct net_device *netdev)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_pf *pf = np->vsi->back;
+
+ return pf->msg_enable;
+}
+
+static void i40e_set_msglevel(struct net_device *netdev, u32 data)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_pf *pf = np->vsi->back;
+
+ if (I40E_DEBUG_USER & data)
+ pf->hw.debug_mask = data;
+ pf->msg_enable = data;
+}
+
+static int i40e_get_regs_len(struct net_device *netdev)
+{
+ int reg_count = 0;
+ int i;
+
+ for (i = 0; i40e_reg_list[i].offset != 0; i++)
+ reg_count += i40e_reg_list[i].elements;
+
+ return reg_count * sizeof(u32);
+}
+
+static void i40e_get_regs(struct net_device *netdev, struct ethtool_regs *regs,
+ void *p)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_pf *pf = np->vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+ u32 *reg_buf = p;
+ int i, j, ri;
+ u32 reg;
+
+ /* Tell ethtool which driver-version-specific regs output we have.
+ *
+ * At some point, if we have ethtool doing special formatting of
+ * this data, it will rely on this version number to know how to
+ * interpret things. Hence, this needs to be updated if/when the
+ * diags register table is changed.
+ */
+ regs->version = 1;
+
+ /* loop through the diags reg table for what to print */
+ ri = 0;
+ for (i = 0; i40e_reg_list[i].offset != 0; i++) {
+ for (j = 0; j < i40e_reg_list[i].elements; j++) {
+ reg = i40e_reg_list[i].offset
+ + (j * i40e_reg_list[i].stride);
+ reg_buf[ri++] = rd32(hw, reg);
+ }
+ }
+
+}
+
+static int i40e_get_eeprom(struct net_device *netdev,
+ struct ethtool_eeprom *eeprom, u8 *bytes)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_hw *hw = &np->vsi->back->hw;
+ int first_word, last_word;
+ u16 i, eeprom_len;
+ u16 *eeprom_buff;
+ int ret_val = 0;
+
+ if (eeprom->len == 0)
+ return -EINVAL;
+
+ eeprom->magic = hw->vendor_id | (hw->device_id << 16);
+
+ first_word = eeprom->offset >> 1;
+ last_word = (eeprom->offset + eeprom->len - 1) >> 1;
+ eeprom_len = last_word - first_word + 1;
+
+ eeprom_buff = kmalloc(sizeof(u16) * eeprom_len, GFP_KERNEL);
+ if (!eeprom_buff)
+ return -ENOMEM;
+
+ ret_val = i40e_read_nvm_buffer(hw, first_word, &eeprom_len,
+ eeprom_buff);
+ if (eeprom_len == 0) {
+ kfree(eeprom_buff);
+ return -EACCES;
+ }
+
+ /* Device's eeprom is always little-endian, word addressable */
+ for (i = 0; i < eeprom_len; i++)
+ le16_to_cpus(&eeprom_buff[i]);
+
+ memcpy(bytes, (u8 *)eeprom_buff + (eeprom->offset & 1), eeprom->len);
+ kfree(eeprom_buff);
+
+ return ret_val;
+}
+
+static int i40e_get_eeprom_len(struct net_device *netdev)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_hw *hw = &np->vsi->back->hw;
+
+ return hw->nvm.sr_size * 2;
+}
+
+static void i40e_get_drvinfo(struct net_device *netdev,
+ struct ethtool_drvinfo *drvinfo)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+ struct i40e_pf *pf = vsi->back;
+
+ strlcpy(drvinfo->driver, i40e_driver_name, sizeof(drvinfo->driver));
+ strlcpy(drvinfo->version, i40e_driver_version_str,
+ sizeof(drvinfo->version));
+ strlcpy(drvinfo->fw_version, i40e_fw_version_str(&pf->hw),
+ sizeof(drvinfo->fw_version));
+ strlcpy(drvinfo->bus_info, pci_name(pf->pdev),
+ sizeof(drvinfo->bus_info));
+}
+
+static void i40e_get_ringparam(struct net_device *netdev,
+ struct ethtool_ringparam *ring)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_pf *pf = np->vsi->back;
+ struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
+
+ ring->rx_max_pending = I40E_MAX_NUM_DESCRIPTORS;
+ ring->tx_max_pending = I40E_MAX_NUM_DESCRIPTORS;
+ ring->rx_mini_max_pending = 0;
+ ring->rx_jumbo_max_pending = 0;
+ ring->rx_pending = vsi->rx_rings[0].count;
+ ring->tx_pending = vsi->tx_rings[0].count;
+ ring->rx_mini_pending = 0;
+ ring->rx_jumbo_pending = 0;
+}
+
+static int i40e_set_ringparam(struct net_device *netdev,
+ struct ethtool_ringparam *ring)
+{
+ struct i40e_ring *tx_rings = NULL, *rx_rings = NULL;
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+ struct i40e_pf *pf = vsi->back;
+ u32 new_rx_count, new_tx_count;
+ int i, err = 0;
+
+ if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending))
+ return -EINVAL;
+
+ new_tx_count = clamp_t(u32, ring->tx_pending,
+ I40E_MIN_NUM_DESCRIPTORS,
+ I40E_MAX_NUM_DESCRIPTORS);
+ new_tx_count = ALIGN(new_tx_count, I40E_REQ_DESCRIPTOR_MULTIPLE);
+
+ new_rx_count = clamp_t(u32, ring->rx_pending,
+ I40E_MIN_NUM_DESCRIPTORS,
+ I40E_MAX_NUM_DESCRIPTORS);
+ new_rx_count = ALIGN(new_rx_count, I40E_REQ_DESCRIPTOR_MULTIPLE);
+
+ /* if nothing to do return success */
+ if ((new_tx_count == vsi->tx_rings[0].count) &&
+ (new_rx_count == vsi->rx_rings[0].count))
+ return 0;
+
+ while (test_and_set_bit(__I40E_CONFIG_BUSY, &pf->state))
+ usleep_range(1000, 2000);
+
+ if (!netif_running(vsi->netdev)) {
+ /* simple case - set for the next time the netdev is started */
+ for (i = 0; i < vsi->num_queue_pairs; i++) {
+ vsi->tx_rings[i].count = new_tx_count;
+ vsi->rx_rings[i].count = new_rx_count;
+ }
+ goto done;
+ }
+
+ /* We can't just free everything and then setup again,
+ * because the ISRs in MSI-X mode get passed pointers
+ * to the Tx and Rx ring structs.
+ */
+
+ /* alloc updated Tx resources */
+ if (new_tx_count != vsi->tx_rings[0].count) {
+ netdev_info(netdev,
+ "Changing Tx descriptor count from %d to %d.\n",
+ vsi->tx_rings[0].count, new_tx_count);
+ tx_rings = kcalloc(vsi->alloc_queue_pairs,
+ sizeof(struct i40e_ring), GFP_KERNEL);
+ if (!tx_rings) {
+ err = -ENOMEM;
+ goto done;
+ }
+
+ for (i = 0; i < vsi->num_queue_pairs; i++) {
+ /* clone ring and setup updated count */
+ tx_rings[i] = vsi->tx_rings[i];
+ tx_rings[i].count = new_tx_count;
+ err = i40e_setup_tx_descriptors(&tx_rings[i]);
+ if (err) {
+ while (i) {
+ i--;
+ i40e_free_tx_resources(&tx_rings[i]);
+ }
+ kfree(tx_rings);
+ tx_rings = NULL;
+
+ goto done;
+ }
+ }
+ }
+
+ /* alloc updated Rx resources */
+ if (new_rx_count != vsi->rx_rings[0].count) {
+ netdev_info(netdev,
+ "Changing Rx descriptor count from %d to %d\n",
+ vsi->rx_rings[0].count, new_rx_count);
+ rx_rings = kcalloc(vsi->alloc_queue_pairs,
+ sizeof(struct i40e_ring), GFP_KERNEL);
+ if (!rx_rings) {
+ err = -ENOMEM;
+ goto free_tx;
+ }
+
+ for (i = 0; i < vsi->num_queue_pairs; i++) {
+ /* clone ring and setup updated count */
+ rx_rings[i] = vsi->rx_rings[i];
+ rx_rings[i].count = new_rx_count;
+ err = i40e_setup_rx_descriptors(&rx_rings[i]);
+ if (err) {
+ while (i) {
+ i--;
+ i40e_free_rx_resources(&rx_rings[i]);
+ }
+ kfree(rx_rings);
+ rx_rings = NULL;
+
+ goto free_tx;
+ }
+ }
+ }
+
+ /* Bring interface down, copy in the new ring info,
+ * then restore the interface
+ */
+ i40e_down(vsi);
+
+ if (tx_rings) {
+ for (i = 0; i < vsi->num_queue_pairs; i++) {
+ i40e_free_tx_resources(&vsi->tx_rings[i]);
+ vsi->tx_rings[i] = tx_rings[i];
+ }
+ kfree(tx_rings);
+ tx_rings = NULL;
+ }
+
+ if (rx_rings) {
+ for (i = 0; i < vsi->num_queue_pairs; i++) {
+ i40e_free_rx_resources(&vsi->rx_rings[i]);
+ vsi->rx_rings[i] = rx_rings[i];
+ }
+ kfree(rx_rings);
+ rx_rings = NULL;
+ }
+
+ i40e_up(vsi);
+
+free_tx:
+ /* error cleanup if the Rx allocations failed after getting Tx */
+ if (tx_rings) {
+ for (i = 0; i < vsi->num_queue_pairs; i++)
+ i40e_free_tx_resources(&tx_rings[i]);
+ kfree(tx_rings);
+ tx_rings = NULL;
+ }
+
+done:
+ clear_bit(__I40E_CONFIG_BUSY, &pf->state);
+
+ return err;
+}
+
+static int i40e_get_sset_count(struct net_device *netdev, int sset)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+ struct i40e_pf *pf = vsi->back;
+
+ switch (sset) {
+ case ETH_SS_TEST:
+ return I40E_TEST_LEN;
+ case ETH_SS_STATS:
+ if (vsi == pf->vsi[pf->lan_vsi])
+ return I40E_PF_STATS_LEN(netdev);
+ else
+ return I40E_VSI_STATS_LEN(netdev);
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+static void i40e_get_ethtool_stats(struct net_device *netdev,
+ struct ethtool_stats *stats, u64 *data)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+ struct i40e_pf *pf = vsi->back;
+ int i = 0;
+ char *p;
+ int j;
+ struct rtnl_link_stats64 *net_stats = i40e_get_vsi_stats_struct(vsi);
+
+ i40e_update_stats(vsi);
+
+ for (j = 0; j < I40E_NETDEV_STATS_LEN; j++) {
+ p = (char *)net_stats + i40e_gstrings_net_stats[j].stat_offset;
+ data[i++] = (i40e_gstrings_net_stats[j].sizeof_stat ==
+ sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
+ }
+ for (j = 0; j < vsi->num_queue_pairs; j++) {
+ data[i++] = vsi->tx_rings[j].tx_stats.packets;
+ data[i++] = vsi->tx_rings[j].tx_stats.bytes;
+ }
+ for (j = 0; j < vsi->num_queue_pairs; j++) {
+ data[i++] = vsi->rx_rings[j].rx_stats.packets;
+ data[i++] = vsi->rx_rings[j].rx_stats.bytes;
+ }
+ if (vsi == pf->vsi[pf->lan_vsi]) {
+ for (j = 0; j < I40E_GLOBAL_STATS_LEN; j++) {
+ p = (char *)pf + i40e_gstrings_stats[j].stat_offset;
+ data[i++] = (i40e_gstrings_stats[j].sizeof_stat ==
+ sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
+ }
+ for (j = 0; j < I40E_MAX_USER_PRIORITY; j++) {
+ data[i++] = pf->stats.priority_xon_tx[j];
+ data[i++] = pf->stats.priority_xoff_tx[j];
+ }
+ for (j = 0; j < I40E_MAX_USER_PRIORITY; j++) {
+ data[i++] = pf->stats.priority_xon_rx[j];
+ data[i++] = pf->stats.priority_xoff_rx[j];
+ }
+ for (j = 0; j < I40E_MAX_USER_PRIORITY; j++)
+ data[i++] = pf->stats.priority_xon_2_xoff[j];
+ }
+}
+
+static void i40e_get_strings(struct net_device *netdev, u32 stringset,
+ u8 *data)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+ struct i40e_pf *pf = vsi->back;
+ char *p = (char *)data;
+ int i;
+
+ switch (stringset) {
+ case ETH_SS_TEST:
+ for (i = 0; i < I40E_TEST_LEN; i++) {
+ memcpy(data, i40e_gstrings_test[i], ETH_GSTRING_LEN);
+ data += ETH_GSTRING_LEN;
+ }
+ break;
+ case ETH_SS_STATS:
+ for (i = 0; i < I40E_NETDEV_STATS_LEN; i++) {
+ snprintf(p, ETH_GSTRING_LEN, "%s",
+ i40e_gstrings_net_stats[i].stat_string);
+ p += ETH_GSTRING_LEN;
+ }
+ for (i = 0; i < vsi->num_queue_pairs; i++) {
+ snprintf(p, ETH_GSTRING_LEN, "tx-%u.tx_packets", i);
+ p += ETH_GSTRING_LEN;
+ snprintf(p, ETH_GSTRING_LEN, "tx-%u.tx_bytes", i);
+ p += ETH_GSTRING_LEN;
+ }
+ for (i = 0; i < vsi->num_queue_pairs; i++) {
+ snprintf(p, ETH_GSTRING_LEN, "rx-%u.rx_packets", i);
+ p += ETH_GSTRING_LEN;
+ snprintf(p, ETH_GSTRING_LEN, "rx-%u.rx_bytes", i);
+ p += ETH_GSTRING_LEN;
+ }
+ if (vsi == pf->vsi[pf->lan_vsi]) {
+ for (i = 0; i < I40E_GLOBAL_STATS_LEN; i++) {
+ snprintf(p, ETH_GSTRING_LEN, "port.%s",
+ i40e_gstrings_stats[i].stat_string);
+ p += ETH_GSTRING_LEN;
+ }
+ for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
+ snprintf(p, ETH_GSTRING_LEN,
+ "port.tx_priority_%u_xon", i);
+ p += ETH_GSTRING_LEN;
+ snprintf(p, ETH_GSTRING_LEN,
+ "port.tx_priority_%u_xoff", i);
+ p += ETH_GSTRING_LEN;
+ }
+ for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
+ snprintf(p, ETH_GSTRING_LEN,
+ "port.rx_priority_%u_xon", i);
+ p += ETH_GSTRING_LEN;
+ snprintf(p, ETH_GSTRING_LEN,
+ "port.rx_priority_%u_xoff", i);
+ p += ETH_GSTRING_LEN;
+ }
+ for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
+ snprintf(p, ETH_GSTRING_LEN,
+ "port.rx_priority_%u_xon_2_xoff", i);
+ p += ETH_GSTRING_LEN;
+ }
+ }
+ /* BUG_ON(p - data != I40E_STATS_LEN * ETH_GSTRING_LEN); */
+ break;
+ }
+}
+
+static int i40e_get_ts_info(struct net_device *dev,
+ struct ethtool_ts_info *info)
+{
+ return ethtool_op_get_ts_info(dev, info);
+}
+
+static int i40e_link_test(struct i40e_pf *pf, u64 *data)
+{
+ if (i40e_get_link_status(&pf->hw))
+ *data = 0;
+ else
+ *data = 1;
+
+ return *data;
+}
+
+static int i40e_reg_test(struct i40e_pf *pf, u64 *data)
+{
+ i40e_status ret;
+
+ ret = i40e_diag_reg_test(&pf->hw);
+ *data = ret;
+
+ return ret;
+}
+
+static int i40e_eeprom_test(struct i40e_pf *pf, u64 *data)
+{
+ i40e_status ret;
+
+ ret = i40e_diag_eeprom_test(&pf->hw);
+ *data = ret;
+
+ return ret;
+}
+
+static int i40e_intr_test(struct i40e_pf *pf, u64 *data)
+{
+ *data = -ENOSYS;
+
+ return *data;
+}
+
+static int i40e_loopback_test(struct i40e_pf *pf, u64 *data)
+{
+ *data = -ENOSYS;
+
+ return *data;
+}
+
+static void i40e_diag_test(struct net_device *netdev,
+ struct ethtool_test *eth_test, u64 *data)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_pf *pf = np->vsi->back;
+
+ set_bit(__I40E_TESTING, &pf->state);
+ if (eth_test->flags == ETH_TEST_FL_OFFLINE) {
+ /* Offline tests */
+
+ netdev_info(netdev, "offline testing starting\n");
+
+ /* Link test performed before hardware reset
+ * so autoneg doesn't interfere with test result
+ */
+ netdev_info(netdev, "link test starting\n");
+ if (i40e_link_test(pf, &data[I40E_ETH_TEST_LINK]))
+ eth_test->flags |= ETH_TEST_FL_FAILED;
+
+ netdev_info(netdev, "register test starting\n");
+ if (i40e_reg_test(pf, &data[I40E_ETH_TEST_REG]))
+ eth_test->flags |= ETH_TEST_FL_FAILED;
+
+ i40e_do_reset(pf, (1 << __I40E_PF_RESET_REQUESTED));
+ netdev_info(netdev, "eeprom test starting\n");
+ if (i40e_eeprom_test(pf, &data[I40E_ETH_TEST_EEPROM]))
+ eth_test->flags |= ETH_TEST_FL_FAILED;
+
+ i40e_do_reset(pf, (1 << __I40E_PF_RESET_REQUESTED));
+ netdev_info(netdev, "interrupt test starting\n");
+ if (i40e_intr_test(pf, &data[I40E_ETH_TEST_INTR]))
+ eth_test->flags |= ETH_TEST_FL_FAILED;
+
+ i40e_do_reset(pf, (1 << __I40E_PF_RESET_REQUESTED));
+ netdev_info(netdev, "loopback test starting\n");
+ if (i40e_loopback_test(pf, &data[I40E_ETH_TEST_LOOPBACK]))
+ eth_test->flags |= ETH_TEST_FL_FAILED;
+
+ } else {
+ netdev_info(netdev, "online test starting\n");
+ /* Online tests */
+ if (i40e_link_test(pf, &data[I40E_ETH_TEST_LINK]))
+ eth_test->flags |= ETH_TEST_FL_FAILED;
+
+ /* Offline only tests, not run in online; pass by default */
+ data[I40E_ETH_TEST_REG] = 0;
+ data[I40E_ETH_TEST_EEPROM] = 0;
+ data[I40E_ETH_TEST_INTR] = 0;
+ data[I40E_ETH_TEST_LOOPBACK] = 0;
+
+ clear_bit(__I40E_TESTING, &pf->state);
+ }
+}
+
+static void i40e_get_wol(struct net_device *netdev,
+ struct ethtool_wolinfo *wol)
+{
+ wol->supported = 0;
+ wol->wolopts = 0;
+}
+
+static int i40e_nway_reset(struct net_device *netdev)
+{
+ /* restart autonegotiation */
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_pf *pf = np->vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+ i40e_status ret = 0;
+
+ ret = i40e_aq_set_link_restart_an(hw, NULL);
+ if (ret) {
+ netdev_info(netdev, "link restart failed, aq_err=%d\n",
+ pf->hw.aq.asq_last_status);
+ return -EIO;
+ }
+
+ return 0;
+}
+
+static int i40e_set_phys_id(struct net_device *netdev,
+ enum ethtool_phys_id_state state)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_pf *pf = np->vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+ int blink_freq = 2;
+
+ switch (state) {
+ case ETHTOOL_ID_ACTIVE:
+ pf->led_status = i40e_led_get(hw);
+ return blink_freq;
+ case ETHTOOL_ID_ON:
+ i40e_led_set(hw, 0xF);
+ break;
+ case ETHTOOL_ID_OFF:
+ i40e_led_set(hw, 0x0);
+ break;
+ case ETHTOOL_ID_INACTIVE:
+ i40e_led_set(hw, pf->led_status);
+ break;
+ }
+
+ return 0;
+}
+
+/* NOTE: i40e hardware uses a conversion factor of 2 for Interrupt
+ * Throttle Rate (ITR) ie. ITR(1) = 2us ITR(10) = 20 us, and also
+ * 125us (8000 interrupts per second) == ITR(62)
+ */
+
+static int i40e_get_coalesce(struct net_device *netdev,
+ struct ethtool_coalesce *ec)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+
+ ec->tx_max_coalesced_frames_irq = vsi->work_limit;
+ ec->rx_max_coalesced_frames_irq = vsi->work_limit;
+
+ if (ITR_IS_DYNAMIC(vsi->rx_itr_setting))
+ ec->rx_coalesce_usecs = 1;
+ else
+ ec->rx_coalesce_usecs = vsi->rx_itr_setting;
+
+ if (ITR_IS_DYNAMIC(vsi->tx_itr_setting))
+ ec->tx_coalesce_usecs = 1;
+ else
+ ec->tx_coalesce_usecs = vsi->tx_itr_setting;
+
+ return 0;
+}
+
+static int i40e_set_coalesce(struct net_device *netdev,
+ struct ethtool_coalesce *ec)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_q_vector *q_vector;
+ struct i40e_vsi *vsi = np->vsi;
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+ u16 vector;
+ int i;
+
+ if (ec->tx_max_coalesced_frames_irq || ec->rx_max_coalesced_frames_irq)
+ vsi->work_limit = ec->tx_max_coalesced_frames_irq;
+
+ switch (ec->rx_coalesce_usecs) {
+ case 0:
+ vsi->rx_itr_setting = 0;
+ break;
+ case 1:
+ vsi->rx_itr_setting = (I40E_ITR_DYNAMIC |
+ ITR_REG_TO_USEC(I40E_ITR_RX_DEF));
+ break;
+ default:
+ if ((ec->rx_coalesce_usecs < (I40E_MIN_ITR << 1)) ||
+ (ec->rx_coalesce_usecs > (I40E_MAX_ITR << 1)))
+ return -EINVAL;
+ vsi->rx_itr_setting = ec->rx_coalesce_usecs;
+ break;
+ }
+
+ switch (ec->tx_coalesce_usecs) {
+ case 0:
+ vsi->tx_itr_setting = 0;
+ break;
+ case 1:
+ vsi->tx_itr_setting = (I40E_ITR_DYNAMIC |
+ ITR_REG_TO_USEC(I40E_ITR_TX_DEF));
+ break;
+ default:
+ if ((ec->tx_coalesce_usecs < (I40E_MIN_ITR << 1)) ||
+ (ec->tx_coalesce_usecs > (I40E_MAX_ITR << 1)))
+ return -EINVAL;
+ vsi->tx_itr_setting = ec->tx_coalesce_usecs;
+ break;
+ }
+
+ vector = vsi->base_vector;
+ q_vector = vsi->q_vectors;
+ for (i = 0; i < vsi->num_q_vectors; i++, vector++, q_vector++) {
+ q_vector->rx.itr = ITR_TO_REG(vsi->rx_itr_setting);
+ wr32(hw, I40E_PFINT_ITRN(0, vector - 1), q_vector->rx.itr);
+ q_vector->tx.itr = ITR_TO_REG(vsi->tx_itr_setting);
+ wr32(hw, I40E_PFINT_ITRN(1, vector - 1), q_vector->tx.itr);
+ i40e_flush(hw);
+ }
+
+ return 0;
+}
+
+/**
+ * i40e_get_rss_hash_opts - Get RSS hash Input Set for each flow type
+ * @pf: pointer to the physical function struct
+ * @cmd: ethtool rxnfc command
+ *
+ * Returns Success if the flow is supported, else Invalid Input.
+ **/
+static int i40e_get_rss_hash_opts(struct i40e_pf *pf, struct ethtool_rxnfc *cmd)
+{
+ cmd->data = 0;
+
+ /* Report default options for RSS on i40e */
+ switch (cmd->flow_type) {
+ case TCP_V4_FLOW:
+ case UDP_V4_FLOW:
+ cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+ /* fall through to add IP fields */
+ case SCTP_V4_FLOW:
+ case AH_ESP_V4_FLOW:
+ case AH_V4_FLOW:
+ case ESP_V4_FLOW:
+ case IPV4_FLOW:
+ cmd->data |= RXH_IP_SRC | RXH_IP_DST;
+ break;
+ case TCP_V6_FLOW:
+ case UDP_V6_FLOW:
+ cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+ /* fall through to add IP fields */
+ case SCTP_V6_FLOW:
+ case AH_ESP_V6_FLOW:
+ case AH_V6_FLOW:
+ case ESP_V6_FLOW:
+ case IPV6_FLOW:
+ cmd->data |= RXH_IP_SRC | RXH_IP_DST;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+/**
+ * i40e_get_rxnfc - command to get RX flow classification rules
+ * @netdev: network interface device structure
+ * @cmd: ethtool rxnfc command
+ *
+ * Returns Success if the command is supported.
+ **/
+static int i40e_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
+ u32 *rule_locs)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+ struct i40e_pf *pf = vsi->back;
+ int ret = -EOPNOTSUPP;
+
+ switch (cmd->cmd) {
+ case ETHTOOL_GRXRINGS:
+ cmd->data = vsi->alloc_queue_pairs;
+ ret = 0;
+ break;
+ case ETHTOOL_GRXFH:
+ ret = i40e_get_rss_hash_opts(pf, cmd);
+ break;
+ case ETHTOOL_GRXCLSRLCNT:
+ ret = 0;
+ break;
+ case ETHTOOL_GRXCLSRULE:
+ ret = 0;
+ break;
+ case ETHTOOL_GRXCLSRLALL:
+ cmd->data = 500;
+ ret = 0;
+ default:
+ break;
+ }
+
+ return ret;
+}
+
+/**
+ * i40e_set_rss_hash_opt - Enable/Disable flow types for RSS hash
+ * @pf: pointer to the physical function struct
+ * @cmd: ethtool rxnfc command
+ *
+ * Returns Success if the flow input set is supported.
+ **/
+static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
+{
+ struct i40e_hw *hw = &pf->hw;
+ u64 hena = (u64)rd32(hw, I40E_PFQF_HENA(0)) |
+ ((u64)rd32(hw, I40E_PFQF_HENA(1)) << 32);
+
+ /* RSS does not support anything other than hashing
+ * to queues on src and dst IPs and ports
+ */
+ if (nfc->data & ~(RXH_IP_SRC | RXH_IP_DST |
+ RXH_L4_B_0_1 | RXH_L4_B_2_3))
+ return -EINVAL;
+
+ /* We need at least the IP SRC and DEST fields for hashing */
+ if (!(nfc->data & RXH_IP_SRC) ||
+ !(nfc->data & RXH_IP_DST))
+ return -EINVAL;
+
+ switch (nfc->flow_type) {
+ case TCP_V4_FLOW:
+ switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
+ case 0:
+ hena &= ~((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV4_TCP);
+ break;
+ case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+ hena |= ((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV4_TCP);
+ break;
+ default:
+ return -EINVAL;
+ }
+ break;
+ case TCP_V6_FLOW:
+ switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
+ case 0:
+ hena &= ~((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV6_TCP);
+ break;
+ case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+ hena |= ((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV6_TCP);
+ break;
+ default:
+ return -EINVAL;
+ }
+ break;
+ case UDP_V4_FLOW:
+ switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
+ case 0:
+ hena &=
+ ~(((u64)1 << I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) |
+ ((u64)1 << I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) |
+ ((u64)1 << I40E_FILTER_PCTYPE_FRAG_IPV4));
+ break;
+ case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+ hena |=
+ (((u64)1 << I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) |
+ ((u64)1 << I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) |
+ ((u64)1 << I40E_FILTER_PCTYPE_FRAG_IPV4));
+ break;
+ default:
+ return -EINVAL;
+ }
+ break;
+ case UDP_V6_FLOW:
+ switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
+ case 0:
+ hena &=
+ ~(((u64)1 << I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) |
+ ((u64)1 << I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP) |
+ ((u64)1 << I40E_FILTER_PCTYPE_FRAG_IPV6));
+ break;
+ case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+ hena |=
+ (((u64)1 << I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) |
+ ((u64)1 << I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP) |
+ ((u64)1 << I40E_FILTER_PCTYPE_FRAG_IPV6));
+ break;
+ default:
+ return -EINVAL;
+ }
+ break;
+ case AH_ESP_V4_FLOW:
+ case AH_V4_FLOW:
+ case ESP_V4_FLOW:
+ case SCTP_V4_FLOW:
+ if ((nfc->data & RXH_L4_B_0_1) ||
+ (nfc->data & RXH_L4_B_2_3))
+ return -EINVAL;
+ hena |= ((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV4_OTHER);
+ break;
+ case AH_ESP_V6_FLOW:
+ case AH_V6_FLOW:
+ case ESP_V6_FLOW:
+ case SCTP_V6_FLOW:
+ if ((nfc->data & RXH_L4_B_0_1) ||
+ (nfc->data & RXH_L4_B_2_3))
+ return -EINVAL;
+ hena |= ((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV6_OTHER);
+ break;
+ case IPV4_FLOW:
+ hena |= ((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV4_OTHER) |
+ ((u64)1 << I40E_FILTER_PCTYPE_FRAG_IPV4);
+ break;
+ case IPV6_FLOW:
+ hena |= ((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV6_OTHER) |
+ ((u64)1 << I40E_FILTER_PCTYPE_FRAG_IPV6);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ wr32(hw, I40E_PFQF_HENA(0), (u32)hena);
+ wr32(hw, I40E_PFQF_HENA(1), (u32)(hena >> 32));
+ i40e_flush(hw);
+
+ return 0;
+}
+
+#define IP_HEADER_OFFSET 14
+/**
+ * i40e_add_del_fdir_udpv4 - Add/Remove UDPv4 Flow Director filters for
+ * a specific flow spec
+ * @vsi: pointer to the targeted VSI
+ * @fd_data: the flow director data required from the FDir descriptor
+ * @ethtool_rx_flow_spec: the flow spec
+ * @add: true adds a filter, false removes it
+ *
+ * Returns 0 if the filters were successfully added or removed
+ **/
+static int i40e_add_del_fdir_udpv4(struct i40e_vsi *vsi,
+ struct i40e_fdir_data *fd_data,
+ struct ethtool_rx_flow_spec *fsp, bool add)
+{
+ struct i40e_pf *pf = vsi->back;
+ struct udphdr *udp;
+ struct iphdr *ip;
+ bool err = false;
+ int ret;
+ int i;
+
+ ip = (struct iphdr *)(fd_data->raw_packet + IP_HEADER_OFFSET);
+ udp = (struct udphdr *)(fd_data->raw_packet + IP_HEADER_OFFSET
+ + sizeof(struct iphdr));
+
+ ip->saddr = fsp->h_u.tcp_ip4_spec.ip4src;
+ ip->daddr = fsp->h_u.tcp_ip4_spec.ip4dst;
+ udp->source = fsp->h_u.tcp_ip4_spec.psrc;
+ udp->dest = fsp->h_u.tcp_ip4_spec.pdst;
+
+ for (i = I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP;
+ i <= I40E_FILTER_PCTYPE_NONF_IPV4_UDP; i++) {
+ fd_data->pctype = i;
+ ret = i40e_program_fdir_filter(fd_data, pf, add);
+
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "Filter command send failed for PCTYPE %d (ret = %d)\n",
+ fd_data->pctype, ret);
+ err = true;
+ } else {
+ dev_info(&pf->pdev->dev,
+ "Filter OK for PCTYPE %d (ret = %d)\n",
+ fd_data->pctype, ret);
+ }
+ }
+
+ return err ? -EOPNOTSUPP : 0;
+}
+
+/**
+ * i40e_add_del_fdir_tcpv4 - Add/Remove TCPv4 Flow Director filters for
+ * a specific flow spec
+ * @vsi: pointer to the targeted VSI
+ * @fd_data: the flow director data required from the FDir descriptor
+ * @ethtool_rx_flow_spec: the flow spec
+ * @add: true adds a filter, false removes it
+ *
+ * Returns 0 if the filters were successfully added or removed
+ **/
+static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi,
+ struct i40e_fdir_data *fd_data,
+ struct ethtool_rx_flow_spec *fsp, bool add)
+{
+ struct i40e_pf *pf = vsi->back;
+ struct tcphdr *tcp;
+ struct iphdr *ip;
+ bool err = false;
+ int ret;
+
+ ip = (struct iphdr *)(fd_data->raw_packet + IP_HEADER_OFFSET);
+ tcp = (struct tcphdr *)(fd_data->raw_packet + IP_HEADER_OFFSET
+ + sizeof(struct iphdr));
+
+ ip->daddr = fsp->h_u.tcp_ip4_spec.ip4dst;
+ tcp->dest = fsp->h_u.tcp_ip4_spec.pdst;
+
+ fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN;
+ ret = i40e_program_fdir_filter(fd_data, pf, add);
+
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "Filter command send failed for PCTYPE %d (ret = %d)\n",
+ fd_data->pctype, ret);
+ err = true;
+ } else {
+ dev_info(&pf->pdev->dev, "Filter OK for PCTYPE %d (ret = %d)\n",
+ fd_data->pctype, ret);
+ }
+
+ ip->saddr = fsp->h_u.tcp_ip4_spec.ip4src;
+ tcp->source = fsp->h_u.tcp_ip4_spec.psrc;
+
+ fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_TCP;
+
+ ret = i40e_program_fdir_filter(fd_data, pf, add);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "Filter command send failed for PCTYPE %d (ret = %d)\n",
+ fd_data->pctype, ret);
+ err = true;
+ } else {
+ dev_info(&pf->pdev->dev, "Filter OK for PCTYPE %d (ret = %d)\n",
+ fd_data->pctype, ret);
+ }
+
+ return err ? -EOPNOTSUPP : 0;
+}
+
+/**
+ * i40e_add_del_fdir_sctpv4 - Add/Remove SCTPv4 Flow Director filters for
+ * a specific flow spec
+ * @vsi: pointer to the targeted VSI
+ * @fd_data: the flow director data required from the FDir descriptor
+ * @ethtool_rx_flow_spec: the flow spec
+ * @add: true adds a filter, false removes it
+ *
+ * Returns 0 if the filters were successfully added or removed
+ **/
+static int i40e_add_del_fdir_sctpv4(struct i40e_vsi *vsi,
+ struct i40e_fdir_data *fd_data,
+ struct ethtool_rx_flow_spec *fsp, bool add)
+{
+ return -EOPNOTSUPP;
+}
+
+/**
+ * i40e_add_del_fdir_ipv4 - Add/Remove IPv4 Flow Director filters for
+ * a specific flow spec
+ * @vsi: pointer to the targeted VSI
+ * @fd_data: the flow director data required for the FDir descriptor
+ * @fsp: the ethtool flow spec
+ * @add: true adds a filter, false removes it
+ *
+ * Returns 0 if the filters were successfully added or removed
+ **/
+static int i40e_add_del_fdir_ipv4(struct i40e_vsi *vsi,
+ struct i40e_fdir_data *fd_data,
+ struct ethtool_rx_flow_spec *fsp, bool add)
+{
+ struct i40e_pf *pf = vsi->back;
+ struct iphdr *ip;
+ bool err = false;
+ int ret;
+ int i;
+
+ ip = (struct iphdr *)(fd_data->raw_packet + IP_HEADER_OFFSET);
+
+ ip->saddr = fsp->h_u.usr_ip4_spec.ip4src;
+ ip->daddr = fsp->h_u.usr_ip4_spec.ip4dst;
+ ip->protocol = fsp->h_u.usr_ip4_spec.proto;
+
+ for (i = I40E_FILTER_PCTYPE_NONF_IPV4_OTHER;
+ i <= I40E_FILTER_PCTYPE_FRAG_IPV4; i++) {
+ fd_data->pctype = i;
+ ret = i40e_program_fdir_filter(fd_data, pf, add);
+
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "Filter command send failed for PCTYPE %d (ret = %d)\n",
+ fd_data->pctype, ret);
+ err = true;
+ } else {
+ dev_info(&pf->pdev->dev,
+ "Filter OK for PCTYPE %d (ret = %d)\n",
+ fd_data->pctype, ret);
+ }
+ }
+
+ return err ? -EOPNOTSUPP : 0;
+}
+
+/**
+ * i40e_add_del_fdir_ethtool - Add/Remove Flow Director filters for
+ * a specific flow spec based on their protocol
+ * @vsi: pointer to the targeted VSI
+ * @cmd: command to get or set RX flow classification rules
+ * @add: true adds a filter, false removes it
+ *
+ * Returns 0 if the filters were successfully added or removed
+ **/
+static int i40e_add_del_fdir_ethtool(struct i40e_vsi *vsi,
+ struct ethtool_rxnfc *cmd, bool add)
+{
+ struct i40e_fdir_data fd_data;
+ int ret = -EINVAL;
+ struct i40e_pf *pf;
+ struct ethtool_rx_flow_spec *fsp =
+ (struct ethtool_rx_flow_spec *)&cmd->fs;
+
+ if (!vsi)
+ return -EINVAL;
+
+ pf = vsi->back;
+
+ if ((fsp->ring_cookie != RX_CLS_FLOW_DISC) &&
+ (fsp->ring_cookie >= vsi->num_queue_pairs))
+ return -EINVAL;
+
+ /* Populate the Flow Director that we have at the moment
+ * and allocate the raw packet buffer for the calling functions
+ */
+ fd_data.raw_packet = kzalloc(I40E_FDIR_MAX_RAW_PACKET_LOOKUP,
+ GFP_KERNEL);
+
+ if (!fd_data.raw_packet) {
+ dev_info(&pf->pdev->dev, "Could not allocate memory\n");
+ return -ENOMEM;
+ }
+
+ fd_data.q_index = fsp->ring_cookie;
+ fd_data.flex_off = 0;
+ fd_data.pctype = 0;
+ fd_data.dest_vsi = vsi->id;
+ fd_data.dest_ctl = 0;
+ fd_data.fd_status = 0;
+ fd_data.cnt_index = 0;
+ fd_data.fd_id = 0;
+
+ switch (fsp->flow_type & ~FLOW_EXT) {
+ case TCP_V4_FLOW:
+ ret = i40e_add_del_fdir_tcpv4(vsi, &fd_data, fsp, add);
+ break;
+ case UDP_V4_FLOW:
+ ret = i40e_add_del_fdir_udpv4(vsi, &fd_data, fsp, add);
+ break;
+ case SCTP_V4_FLOW:
+ ret = i40e_add_del_fdir_sctpv4(vsi, &fd_data, fsp, add);
+ break;
+ case IPV4_FLOW:
+ ret = i40e_add_del_fdir_ipv4(vsi, &fd_data, fsp, add);
+ break;
+ case IP_USER_FLOW:
+ switch (fsp->h_u.usr_ip4_spec.proto) {
+ case IPPROTO_TCP:
+ ret = i40e_add_del_fdir_tcpv4(vsi, &fd_data, fsp, add);
+ break;
+ case IPPROTO_UDP:
+ ret = i40e_add_del_fdir_udpv4(vsi, &fd_data, fsp, add);
+ break;
+ case IPPROTO_SCTP:
+ ret = i40e_add_del_fdir_sctpv4(vsi, &fd_data, fsp, add);
+ break;
+ default:
+ ret = i40e_add_del_fdir_ipv4(vsi, &fd_data, fsp, add);
+ break;
+ }
+ break;
+ default:
+ dev_info(&pf->pdev->dev, "Could not specify spec type\n");
+ ret = -EINVAL;
+ }
+
+ kfree(fd_data.raw_packet);
+ fd_data.raw_packet = NULL;
+
+ return ret;
+}
+/**
+ * i40e_set_rxnfc - command to set RX flow classification rules
+ * @netdev: network interface device structure
+ * @cmd: ethtool rxnfc command
+ *
+ * Returns Success if the command is supported.
+ **/
+static int i40e_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+ struct i40e_pf *pf = vsi->back;
+ int ret = -EOPNOTSUPP;
+
+ switch (cmd->cmd) {
+ case ETHTOOL_SRXFH:
+ ret = i40e_set_rss_hash_opt(pf, cmd);
+ break;
+ case ETHTOOL_SRXCLSRLINS:
+ ret = i40e_add_del_fdir_ethtool(vsi, cmd, true);
+ break;
+ case ETHTOOL_SRXCLSRLDEL:
+ ret = i40e_add_del_fdir_ethtool(vsi, cmd, false);
+ break;
+ default:
+ break;
+ }
+
+ return ret;
+}
+
+static const struct ethtool_ops i40e_ethtool_ops = {
+ .get_settings = i40e_get_settings,
+ .get_drvinfo = i40e_get_drvinfo,
+ .get_regs_len = i40e_get_regs_len,
+ .get_regs = i40e_get_regs,
+ .nway_reset = i40e_nway_reset,
+ .get_link = ethtool_op_get_link,
+ .get_wol = i40e_get_wol,
+ .get_eeprom_len = i40e_get_eeprom_len,
+ .get_eeprom = i40e_get_eeprom,
+ .get_ringparam = i40e_get_ringparam,
+ .set_ringparam = i40e_set_ringparam,
+ .get_pauseparam = i40e_get_pauseparam,
+ .get_msglevel = i40e_get_msglevel,
+ .set_msglevel = i40e_set_msglevel,
+ .get_rxnfc = i40e_get_rxnfc,
+ .set_rxnfc = i40e_set_rxnfc,
+ .self_test = i40e_diag_test,
+ .get_strings = i40e_get_strings,
+ .set_phys_id = i40e_set_phys_id,
+ .get_sset_count = i40e_get_sset_count,
+ .get_ethtool_stats = i40e_get_ethtool_stats,
+ .get_coalesce = i40e_get_coalesce,
+ .set_coalesce = i40e_set_coalesce,
+ .get_ts_info = i40e_get_ts_info,
+};
+
+void i40e_set_ethtool_ops(struct net_device *netdev)
+{
+ SET_ETHTOOL_OPS(netdev, &i40e_ethtool_ops);
+}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_hmc.c b/drivers/net/ethernet/intel/i40e/i40e_hmc.c
new file mode 100644
index 0000000..901804a
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_hmc.c
@@ -0,0 +1,366 @@
+/*******************************************************************************
+ *
+ * Intel Ethernet Controller XL710 Family Linux Driver
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ ******************************************************************************/
+
+#include "i40e_osdep.h"
+#include "i40e_register.h"
+#include "i40e_status.h"
+#include "i40e_alloc.h"
+#include "i40e_hmc.h"
+#include "i40e_type.h"
+
+/**
+ * i40e_add_sd_table_entry - Adds a segment descriptor to the table
+ * @hw: pointer to our hw struct
+ * @hmc_info: pointer to the HMC configuration information struct
+ * @sd_index: segment descriptor index to manipulate
+ * @type: what type of segment descriptor we're manipulating
+ * @direct_mode_sz: size to alloc in direct mode
+ **/
+i40e_status i40e_add_sd_table_entry(struct i40e_hw *hw,
+ struct i40e_hmc_info *hmc_info,
+ u32 sd_index,
+ enum i40e_sd_entry_type type,
+ u64 direct_mode_sz)
+{
+ enum i40e_memory_type mem_type __attribute__((unused));
+ i40e_status ret_code = 0;
+ struct i40e_hmc_sd_entry *sd_entry;
+ bool dma_mem_alloc_done = false;
+ struct i40e_dma_mem mem;
+ u64 alloc_len;
+
+ if (NULL == hmc_info->sd_table.sd_entry) {
+ ret_code = I40E_ERR_BAD_PTR;
+ hw_dbg(hw, "i40e_add_sd_table_entry: bad sd_entry\n");
+ goto exit;
+ }
+
+ if (sd_index >= hmc_info->sd_table.sd_cnt) {
+ ret_code = I40E_ERR_INVALID_SD_INDEX;
+ hw_dbg(hw, "i40e_add_sd_table_entry: bad sd_index\n");
+ goto exit;
+ }
+
+ sd_entry = &hmc_info->sd_table.sd_entry[sd_index];
+ if (!sd_entry->valid) {
+ if (I40E_SD_TYPE_PAGED == type) {
+ mem_type = i40e_mem_pd;
+ alloc_len = I40E_HMC_PAGED_BP_SIZE;
+ } else {
+ mem_type = i40e_mem_bp_jumbo;
+ alloc_len = direct_mode_sz;
+ }
+
+ /* allocate a 4K pd page or 2M backing page */
+ ret_code = i40e_allocate_dma_mem(hw, &mem, mem_type, alloc_len,
+ I40E_HMC_PD_BP_BUF_ALIGNMENT);
+ if (ret_code)
+ goto exit;
+ dma_mem_alloc_done = true;
+ if (I40E_SD_TYPE_PAGED == type) {
+ ret_code = i40e_allocate_virt_mem(hw,
+ &sd_entry->u.pd_table.pd_entry_virt_mem,
+ sizeof(struct i40e_hmc_pd_entry) * 512);
+ if (ret_code)
+ goto exit;
+ sd_entry->u.pd_table.pd_entry =
+ (struct i40e_hmc_pd_entry *)
+ sd_entry->u.pd_table.pd_entry_virt_mem.va;
+ memcpy(&sd_entry->u.pd_table.pd_page_addr, &mem,
+ sizeof(struct i40e_dma_mem));
+ } else {
+ memcpy(&sd_entry->u.bp.addr, &mem,
+ sizeof(struct i40e_dma_mem));
+ sd_entry->u.bp.sd_pd_index = sd_index;
+ }
+ /* initialize the sd entry */
+ hmc_info->sd_table.sd_entry[sd_index].entry_type = type;
+
+ /* increment the ref count */
+ I40E_INC_SD_REFCNT(&hmc_info->sd_table);
+ }
+ /* Increment backing page reference count */
+ if (I40E_SD_TYPE_DIRECT == sd_entry->entry_type)
+ I40E_INC_BP_REFCNT(&sd_entry->u.bp);
+exit:
+ if (ret_code)
+ if (dma_mem_alloc_done)
+ i40e_free_dma_mem(hw, &mem);
+
+ return ret_code;
+}
+
+/**
+ * i40e_add_pd_table_entry - Adds page descriptor to the specified table
+ * @hw: pointer to our HW structure
+ * @hmc_info: pointer to the HMC configuration information structure
+ * @pd_index: which page descriptor index to manipulate
+ *
+ * This function:
+ * 1. Initializes the pd entry
+ * 2. Adds pd_entry in the pd_table
+ * 3. Mark the entry valid in i40e_hmc_pd_entry structure
+ * 4. Initializes the pd_entry's ref count to 1
+ * assumptions:
+ * 1. The memory for pd should be pinned down, physically contiguous and
+ * aligned on 4K boundary and zeroed memory.
+ * 2. It should be 4K in size.
+ **/
+i40e_status i40e_add_pd_table_entry(struct i40e_hw *hw,
+ struct i40e_hmc_info *hmc_info,
+ u32 pd_index)
+{
+ i40e_status ret_code = 0;
+ struct i40e_hmc_pd_table *pd_table;
+ struct i40e_hmc_pd_entry *pd_entry;
+ struct i40e_dma_mem mem;
+ u32 sd_idx, rel_pd_idx;
+ u64 *pd_addr;
+ u64 page_desc;
+
+ if (pd_index / I40E_HMC_PD_CNT_IN_SD >= hmc_info->sd_table.sd_cnt) {
+ ret_code = I40E_ERR_INVALID_PAGE_DESC_INDEX;
+ hw_dbg(hw, "i40e_add_pd_table_entry: bad pd_index\n");
+ goto exit;
+ }
+
+ /* find corresponding sd */
+ sd_idx = (pd_index / I40E_HMC_PD_CNT_IN_SD);
+ if (I40E_SD_TYPE_PAGED !=
+ hmc_info->sd_table.sd_entry[sd_idx].entry_type)
+ goto exit;
+
+ rel_pd_idx = (pd_index % I40E_HMC_PD_CNT_IN_SD);
+ pd_table = &hmc_info->sd_table.sd_entry[sd_idx].u.pd_table;
+ pd_entry = &pd_table->pd_entry[rel_pd_idx];
+ if (!pd_entry->valid) {
+ /* allocate a 4K backing page */
+ ret_code = i40e_allocate_dma_mem(hw, &mem, i40e_mem_bp,
+ I40E_HMC_PAGED_BP_SIZE,
+ I40E_HMC_PD_BP_BUF_ALIGNMENT);
+ if (ret_code)
+ goto exit;
+
+ memcpy(&pd_entry->bp.addr, &mem, sizeof(struct i40e_dma_mem));
+ pd_entry->bp.sd_pd_index = pd_index;
+ pd_entry->bp.entry_type = I40E_SD_TYPE_PAGED;
+ /* Set page address and valid bit */
+ page_desc = mem.pa | 0x1;
+
+ pd_addr = (u64 *)pd_table->pd_page_addr.va;
+ pd_addr += rel_pd_idx;
+
+ /* Add the backing page physical address in the pd entry */
+ memcpy(pd_addr, &page_desc, sizeof(u64));
+
+ pd_entry->sd_index = sd_idx;
+ pd_entry->valid = true;
+ I40E_INC_PD_REFCNT(pd_table);
+ }
+ I40E_INC_BP_REFCNT(&pd_entry->bp);
+exit:
+ return ret_code;
+}
+
+/**
+ * i40e_remove_pd_bp - remove a backing page from a page descriptor
+ * @hw: pointer to our HW structure
+ * @hmc_info: pointer to the HMC configuration information structure
+ * @idx: the page index
+ * @is_pf: distinguishes a VF from a PF
+ *
+ * This function:
+ * 1. Marks the entry in pd tabe (for paged address mode) or in sd table
+ * (for direct address mode) invalid.
+ * 2. Write to register PMPDINV to invalidate the backing page in FV cache
+ * 3. Decrement the ref count for the pd _entry
+ * assumptions:
+ * 1. Caller can deallocate the memory used by backing storage after this
+ * function returns.
+ **/
+i40e_status i40e_remove_pd_bp(struct i40e_hw *hw,
+ struct i40e_hmc_info *hmc_info,
+ u32 idx, bool is_pf)
+{
+ i40e_status ret_code = 0;
+ struct i40e_hmc_pd_entry *pd_entry;
+ struct i40e_hmc_pd_table *pd_table;
+ struct i40e_hmc_sd_entry *sd_entry;
+ u32 sd_idx, rel_pd_idx;
+ u64 *pd_addr;
+
+ /* calculate index */
+ sd_idx = idx / I40E_HMC_PD_CNT_IN_SD;
+ rel_pd_idx = idx % I40E_HMC_PD_CNT_IN_SD;
+ if (sd_idx >= hmc_info->sd_table.sd_cnt) {
+ ret_code = I40E_ERR_INVALID_PAGE_DESC_INDEX;
+ hw_dbg(hw, "i40e_remove_pd_bp: bad idx\n");
+ goto exit;
+ }
+ sd_entry = &hmc_info->sd_table.sd_entry[sd_idx];
+ if (I40E_SD_TYPE_PAGED != sd_entry->entry_type) {
+ ret_code = I40E_ERR_INVALID_SD_TYPE;
+ hw_dbg(hw, "i40e_remove_pd_bp: wrong sd_entry type\n");
+ goto exit;
+ }
+ /* get the entry and decrease its ref counter */
+ pd_table = &hmc_info->sd_table.sd_entry[sd_idx].u.pd_table;
+ pd_entry = &pd_table->pd_entry[rel_pd_idx];
+ I40E_DEC_BP_REFCNT(&pd_entry->bp);
+ if (pd_entry->bp.ref_cnt)
+ goto exit;
+
+ /* mark the entry invalid */
+ pd_entry->valid = false;
+ I40E_DEC_PD_REFCNT(pd_table);
+ pd_addr = (u64 *)pd_table->pd_page_addr.va;
+ pd_addr += rel_pd_idx;
+ memset(pd_addr, 0, sizeof(u64));
+ if (is_pf)
+ I40E_INVALIDATE_PF_HMC_PD(hw, sd_idx, idx);
+ else
+ I40E_INVALIDATE_VF_HMC_PD(hw, sd_idx, idx, hmc_info->hmc_fn_id);
+
+ /* free memory here */
+ ret_code = i40e_free_dma_mem(hw, &(pd_entry->bp.addr));
+ if (ret_code)
+ goto exit;
+ if (!pd_table->ref_cnt)
+ i40e_free_virt_mem(hw, &pd_table->pd_entry_virt_mem);
+exit:
+ return ret_code;
+}
+
+/**
+ * i40e_prep_remove_sd_bp - Prepares to remove a backing page from a sd entry
+ * @hmc_info: pointer to the HMC configuration information structure
+ * @idx: the page index
+ **/
+i40e_status i40e_prep_remove_sd_bp(struct i40e_hmc_info *hmc_info,
+ u32 idx)
+{
+ i40e_status ret_code = 0;
+ struct i40e_hmc_sd_entry *sd_entry;
+
+ /* get the entry and decrease its ref counter */
+ sd_entry = &hmc_info->sd_table.sd_entry[idx];
+ I40E_DEC_BP_REFCNT(&sd_entry->u.bp);
+ if (sd_entry->u.bp.ref_cnt) {
+ ret_code = I40E_ERR_NOT_READY;
+ goto exit;
+ }
+ I40E_DEC_SD_REFCNT(&hmc_info->sd_table);
+
+ /* mark the entry invalid */
+ sd_entry->valid = false;
+exit:
+ return ret_code;
+}
+
+/**
+ * i40e_remove_sd_bp_new - Removes a backing page from a segment descriptor
+ * @hw: pointer to our hw struct
+ * @hmc_info: pointer to the HMC configuration information structure
+ * @idx: the page index
+ * @is_pf: used to distinguish between VF and PF
+ **/
+i40e_status i40e_remove_sd_bp_new(struct i40e_hw *hw,
+ struct i40e_hmc_info *hmc_info,
+ u32 idx, bool is_pf)
+{
+ struct i40e_hmc_sd_entry *sd_entry;
+ i40e_status ret_code = 0;
+
+ /* get the entry and decrease its ref counter */
+ sd_entry = &hmc_info->sd_table.sd_entry[idx];
+ if (is_pf) {
+ I40E_CLEAR_PF_SD_ENTRY(hw, idx, I40E_SD_TYPE_DIRECT);
+ } else {
+ ret_code = I40E_NOT_SUPPORTED;
+ goto exit;
+ }
+ ret_code = i40e_free_dma_mem(hw, &(sd_entry->u.bp.addr));
+ if (ret_code)
+ goto exit;
+exit:
+ return ret_code;
+}
+
+/**
+ * i40e_prep_remove_pd_page - Prepares to remove a PD page from sd entry.
+ * @hmc_info: pointer to the HMC configuration information structure
+ * @idx: segment descriptor index to find the relevant page descriptor
+ **/
+i40e_status i40e_prep_remove_pd_page(struct i40e_hmc_info *hmc_info,
+ u32 idx)
+{
+ i40e_status ret_code = 0;
+ struct i40e_hmc_sd_entry *sd_entry;
+
+ sd_entry = &hmc_info->sd_table.sd_entry[idx];
+
+ if (sd_entry->u.pd_table.ref_cnt) {
+ ret_code = I40E_ERR_NOT_READY;
+ goto exit;
+ }
+
+ /* mark the entry invalid */
+ sd_entry->valid = false;
+
+ I40E_DEC_SD_REFCNT(&hmc_info->sd_table);
+exit:
+ return ret_code;
+}
+
+/**
+ * i40e_remove_pd_page_new - Removes a PD page from sd entry.
+ * @hw: pointer to our hw struct
+ * @hmc_info: pointer to the HMC configuration information structure
+ * @idx: segment descriptor index to find the relevant page descriptor
+ * @is_pf: used to distinguish between VF and PF
+ **/
+i40e_status i40e_remove_pd_page_new(struct i40e_hw *hw,
+ struct i40e_hmc_info *hmc_info,
+ u32 idx, bool is_pf)
+{
+ i40e_status ret_code = 0;
+ struct i40e_hmc_sd_entry *sd_entry;
+
+ sd_entry = &hmc_info->sd_table.sd_entry[idx];
+ if (is_pf) {
+ I40E_CLEAR_PF_SD_ENTRY(hw, idx, I40E_SD_TYPE_PAGED);
+ } else {
+ ret_code = I40E_NOT_SUPPORTED;
+ goto exit;
+ }
+ /* free memory here */
+ ret_code = i40e_free_dma_mem(hw, &(sd_entry->u.pd_table.pd_page_addr));
+ if (ret_code)
+ goto exit;
+exit:
+ return ret_code;
+}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_hmc.h b/drivers/net/ethernet/intel/i40e/i40e_hmc.h
new file mode 100644
index 0000000..aacd42a
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_hmc.h
@@ -0,0 +1,245 @@
+/*******************************************************************************
+ *
+ * Intel Ethernet Controller XL710 Family Linux Driver
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ ******************************************************************************/
+
+#ifndef _I40E_HMC_H_
+#define _I40E_HMC_H_
+
+#define I40E_HMC_MAX_BP_COUNT 512
+
+/* forward-declare the HW struct for the compiler */
+struct i40e_hw;
+
+#define I40E_HMC_INFO_SIGNATURE 0x484D5347 /* HMSG */
+#define I40E_HMC_PD_CNT_IN_SD 512
+#define I40E_HMC_DIRECT_BP_SIZE 0x200000 /* 2M */
+#define I40E_HMC_PAGED_BP_SIZE 4096
+#define I40E_HMC_PD_BP_BUF_ALIGNMENT 4096
+#define I40E_FIRST_VF_FPM_ID 16
+
+struct i40e_hmc_obj_info {
+ u64 base; /* base addr in FPM */
+ u32 max_cnt; /* max count available for this hmc func */
+ u32 cnt; /* count of objects driver actually wants to create */
+ u64 size; /* size in bytes of one object */
+};
+
+enum i40e_sd_entry_type {
+ I40E_SD_TYPE_INVALID = 0,
+ I40E_SD_TYPE_PAGED = 1,
+ I40E_SD_TYPE_DIRECT = 2
+};
+
+struct i40e_hmc_bp {
+ enum i40e_sd_entry_type entry_type;
+ struct i40e_dma_mem addr; /* populate to be used by hw */
+ u32 sd_pd_index;
+ u32 ref_cnt;
+};
+
+struct i40e_hmc_pd_entry {
+ struct i40e_hmc_bp bp;
+ u32 sd_index;
+ bool valid;
+};
+
+struct i40e_hmc_pd_table {
+ struct i40e_dma_mem pd_page_addr; /* populate to be used by hw */
+ struct i40e_hmc_pd_entry *pd_entry; /* [512] for sw book keeping */
+ struct i40e_virt_mem pd_entry_virt_mem; /* virt mem for pd_entry */
+
+ u32 ref_cnt;
+ u32 sd_index;
+};
+
+struct i40e_hmc_sd_entry {
+ enum i40e_sd_entry_type entry_type;
+ bool valid;
+
+ union {
+ struct i40e_hmc_pd_table pd_table;
+ struct i40e_hmc_bp bp;
+ } u;
+};
+
+struct i40e_hmc_sd_table {
+ struct i40e_virt_mem addr; /* used to track sd_entry allocations */
+ u32 sd_cnt;
+ u32 ref_cnt;
+ struct i40e_hmc_sd_entry *sd_entry; /* (sd_cnt*512) entries max */
+};
+
+struct i40e_hmc_info {
+ u32 signature;
+ /* equals to pci func num for PF and dynamically allocated for VFs */
+ u8 hmc_fn_id;
+ u16 first_sd_index; /* index of the first available SD */
+
+ /* hmc objects */
+ struct i40e_hmc_obj_info *hmc_obj;
+ struct i40e_virt_mem hmc_obj_virt_mem;
+ struct i40e_hmc_sd_table sd_table;
+};
+
+#define I40E_INC_SD_REFCNT(sd_table) ((sd_table)->ref_cnt++)
+#define I40E_INC_PD_REFCNT(pd_table) ((pd_table)->ref_cnt++)
+#define I40E_INC_BP_REFCNT(bp) ((bp)->ref_cnt++)
+
+#define I40E_DEC_SD_REFCNT(sd_table) ((sd_table)->ref_cnt--)
+#define I40E_DEC_PD_REFCNT(pd_table) ((pd_table)->ref_cnt--)
+#define I40E_DEC_BP_REFCNT(bp) ((bp)->ref_cnt--)
+
+/**
+ * I40E_SET_PF_SD_ENTRY - marks the sd entry as valid in the hardware
+ * @hw: pointer to our hw struct
+ * @pa: pointer to physical address
+ * @sd_index: segment descriptor index
+ * @hmc_fn_id: hmc function id
+ * @type: if sd entry is direct or paged
+ **/
+#define I40E_SET_PF_SD_ENTRY(hw, pa, sd_index, type) \
+{ \
+ u32 val1, val2, val3; \
+ val1 = (u32)(upper_32_bits(pa)); \
+ val2 = (u32)(pa) | (I40E_HMC_MAX_BP_COUNT << \
+ I40E_PFHMC_SDDATALOW_PMSDBPCOUNT_SHIFT) | \
+ ((((type) == I40E_SD_TYPE_PAGED) ? 0 : 1) << \
+ I40E_PFHMC_SDDATALOW_PMSDTYPE_SHIFT) | \
+ (1 << I40E_PFHMC_SDDATALOW_PMSDVALID_SHIFT); \
+ val3 = (sd_index) | (1 << I40E_PFHMC_SDCMD_PMSDWR_SHIFT); \
+ wr32((hw), I40E_PFHMC_SDDATAHIGH, val1); \
+ wr32((hw), I40E_PFHMC_SDDATALOW, val2); \
+ wr32((hw), I40E_PFHMC_SDCMD, val3); \
+}
+
+/**
+ * I40E_CLEAR_PF_SD_ENTRY - marks the sd entry as invalid in the hardware
+ * @hw: pointer to our hw struct
+ * @sd_index: segment descriptor index
+ * @hmc_fn_id: hmc function id
+ * @type: if sd entry is direct or paged
+ **/
+#define I40E_CLEAR_PF_SD_ENTRY(hw, sd_index, type) \
+{ \
+ u32 val2, val3; \
+ val2 = (I40E_HMC_MAX_BP_COUNT << \
+ I40E_PFHMC_SDDATALOW_PMSDBPCOUNT_SHIFT) | \
+ ((((type) == I40E_SD_TYPE_PAGED) ? 0 : 1) << \
+ I40E_PFHMC_SDDATALOW_PMSDTYPE_SHIFT); \
+ val3 = (sd_index) | (1 << I40E_PFHMC_SDCMD_PMSDWR_SHIFT); \
+ wr32((hw), I40E_PFHMC_SDDATAHIGH, 0); \
+ wr32((hw), I40E_PFHMC_SDDATALOW, val2); \
+ wr32((hw), I40E_PFHMC_SDCMD, val3); \
+}
+
+/**
+ * I40E_INVALIDATE_PF_HMC_PD - Invalidates the pd cache in the hardware
+ * @hw: pointer to our hw struct
+ * @sd_idx: segment descriptor index
+ * @pd_idx: page descriptor index
+ * @hmc_fn_id: hmc function id
+ **/
+#define I40E_INVALIDATE_PF_HMC_PD(hw, sd_idx, pd_idx) \
+ wr32((hw), I40E_PFHMC_PDINV, \
+ (((sd_idx) << I40E_PFHMC_PDINV_PMSDIDX_SHIFT) | \
+ ((pd_idx) << I40E_PFHMC_PDINV_PMPDIDX_SHIFT)))
+
+#define I40E_INVALIDATE_VF_HMC_PD(hw, sd_idx, pd_idx, hmc_fn_id) \
+ wr32((hw), I40E_GLHMC_VFPDINV((hmc_fn_id) - I40E_FIRST_VF_FPM_ID), \
+ (((sd_idx) << I40E_PFHMC_PDINV_PMSDIDX_SHIFT) | \
+ ((pd_idx) << I40E_PFHMC_PDINV_PMPDIDX_SHIFT)))
+
+/**
+ * I40E_FIND_SD_INDEX_LIMIT - finds segment descriptor index limit
+ * @hmc_info: pointer to the HMC configuration information structure
+ * @type: type of HMC resources we're searching
+ * @index: starting index for the object
+ * @cnt: number of objects we're trying to create
+ * @sd_idx: pointer to return index of the segment descriptor in question
+ * @sd_limit: pointer to return the maximum number of segment descriptors
+ *
+ * This function calculates the segment descriptor index and index limit
+ * for the resource defined by i40e_hmc_rsrc_type.
+ **/
+#define I40E_FIND_SD_INDEX_LIMIT(hmc_info, type, index, cnt, sd_idx, sd_limit)\
+{ \
+ u64 fpm_addr, fpm_limit; \
+ fpm_addr = (hmc_info)->hmc_obj[(type)].base + \
+ (hmc_info)->hmc_obj[(type)].size * (index); \
+ fpm_limit = fpm_addr + (hmc_info)->hmc_obj[(type)].size * (cnt);\
+ *(sd_idx) = (u32)(fpm_addr / I40E_HMC_DIRECT_BP_SIZE); \
+ *(sd_limit) = (u32)((fpm_limit - 1) / I40E_HMC_DIRECT_BP_SIZE); \
+ /* add one more to the limit to correct our range */ \
+ *(sd_limit) += 1; \
+}
+
+/**
+ * I40E_FIND_PD_INDEX_LIMIT - finds page descriptor index limit
+ * @hmc_info: pointer to the HMC configuration information struct
+ * @type: HMC resource type we're examining
+ * @idx: starting index for the object
+ * @cnt: number of objects we're trying to create
+ * @pd_index: pointer to return page descriptor index
+ * @pd_limit: pointer to return page descriptor index limit
+ *
+ * Calculates the page descriptor index and index limit for the resource
+ * defined by i40e_hmc_rsrc_type.
+ **/
+#define I40E_FIND_PD_INDEX_LIMIT(hmc_info, type, idx, cnt, pd_index, pd_limit)\
+{ \
+ u64 fpm_adr, fpm_limit; \
+ fpm_adr = (hmc_info)->hmc_obj[(type)].base + \
+ (hmc_info)->hmc_obj[(type)].size * (idx); \
+ fpm_limit = fpm_adr + (hmc_info)->hmc_obj[(type)].size * (cnt); \
+ *(pd_index) = (u32)(fpm_adr / I40E_HMC_PAGED_BP_SIZE); \
+ *(pd_limit) = (u32)((fpm_limit - 1) / I40E_HMC_PAGED_BP_SIZE); \
+ /* add one more to the limit to correct our range */ \
+ *(pd_limit) += 1; \
+}
+i40e_status i40e_add_sd_table_entry(struct i40e_hw *hw,
+ struct i40e_hmc_info *hmc_info,
+ u32 sd_index,
+ enum i40e_sd_entry_type type,
+ u64 direct_mode_sz);
+
+i40e_status i40e_add_pd_table_entry(struct i40e_hw *hw,
+ struct i40e_hmc_info *hmc_info,
+ u32 pd_index);
+i40e_status i40e_remove_pd_bp(struct i40e_hw *hw,
+ struct i40e_hmc_info *hmc_info,
+ u32 idx, bool is_pf);
+i40e_status i40e_prep_remove_sd_bp(struct i40e_hmc_info *hmc_info,
+ u32 idx);
+i40e_status i40e_remove_sd_bp_new(struct i40e_hw *hw,
+ struct i40e_hmc_info *hmc_info,
+ u32 idx, bool is_pf);
+i40e_status i40e_prep_remove_pd_page(struct i40e_hmc_info *hmc_info,
+ u32 idx);
+i40e_status i40e_remove_pd_page_new(struct i40e_hw *hw,
+ struct i40e_hmc_info *hmc_info,
+ u32 idx, bool is_pf);
+
+#endif /* _I40E_HMC_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c
new file mode 100644
index 0000000..a695b91
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c
@@ -0,0 +1,1006 @@
+/*******************************************************************************
+ *
+ * Intel Ethernet Controller XL710 Family Linux Driver
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ ******************************************************************************/
+
+#include "i40e_osdep.h"
+#include "i40e_register.h"
+#include "i40e_type.h"
+#include "i40e_hmc.h"
+#include "i40e_lan_hmc.h"
+#include "i40e_prototype.h"
+
+/* lan specific interface functions */
+
+/**
+ * i40e_align_l2obj_base - aligns base object pointer to 512 bytes
+ * @offset: base address offset needing alignment
+ *
+ * Aligns the layer 2 function private memory so it's 512-byte aligned.
+ **/
+static u64 i40e_align_l2obj_base(u64 offset)
+{
+ u64 aligned_offset = offset;
+
+ if ((offset % I40E_HMC_L2OBJ_BASE_ALIGNMENT) > 0)
+ aligned_offset += (I40E_HMC_L2OBJ_BASE_ALIGNMENT -
+ (offset % I40E_HMC_L2OBJ_BASE_ALIGNMENT));
+
+ return aligned_offset;
+}
+
+/**
+ * i40e_calculate_l2fpm_size - calculates layer 2 FPM memory size
+ * @txq_num: number of Tx queues needing backing context
+ * @rxq_num: number of Rx queues needing backing context
+ * @fcoe_cntx_num: amount of FCoE statefull contexts needing backing context
+ * @fcoe_filt_num: number of FCoE filters needing backing context
+ *
+ * Calculates the maximum amount of memory for the function required, based
+ * on the number of resources it must provide context for.
+ **/
+static u64 i40e_calculate_l2fpm_size(u32 txq_num, u32 rxq_num,
+ u32 fcoe_cntx_num, u32 fcoe_filt_num)
+{
+ u64 fpm_size = 0;
+
+ fpm_size = txq_num * I40E_HMC_OBJ_SIZE_TXQ;
+ fpm_size = i40e_align_l2obj_base(fpm_size);
+
+ fpm_size += (rxq_num * I40E_HMC_OBJ_SIZE_RXQ);
+ fpm_size = i40e_align_l2obj_base(fpm_size);
+
+ fpm_size += (fcoe_cntx_num * I40E_HMC_OBJ_SIZE_FCOE_CNTX);
+ fpm_size = i40e_align_l2obj_base(fpm_size);
+
+ fpm_size += (fcoe_filt_num * I40E_HMC_OBJ_SIZE_FCOE_FILT);
+ fpm_size = i40e_align_l2obj_base(fpm_size);
+
+ return fpm_size;
+}
+
+/**
+ * i40e_init_lan_hmc - initialize i40e_hmc_info struct
+ * @hw: pointer to the HW structure
+ * @txq_num: number of Tx queues needing backing context
+ * @rxq_num: number of Rx queues needing backing context
+ * @fcoe_cntx_num: amount of FCoE statefull contexts needing backing context
+ * @fcoe_filt_num: number of FCoE filters needing backing context
+ *
+ * This function will be called once per physical function initialization.
+ * It will fill out the i40e_hmc_obj_info structure for LAN objects based on
+ * the driver's provided input, as well as information from the HMC itself
+ * loaded from NVRAM.
+ *
+ * Assumptions:
+ * - HMC Resource Profile has been selected before calling this function.
+ **/
+i40e_status i40e_init_lan_hmc(struct i40e_hw *hw, u32 txq_num,
+ u32 rxq_num, u32 fcoe_cntx_num,
+ u32 fcoe_filt_num)
+{
+ struct i40e_hmc_obj_info *obj, *full_obj;
+ i40e_status ret_code = 0;
+ u64 l2fpm_size;
+ u32 size_exp;
+
+ hw->hmc.signature = I40E_HMC_INFO_SIGNATURE;
+ hw->hmc.hmc_fn_id = hw->pf_id;
+
+ /* allocate memory for hmc_obj */
+ ret_code = i40e_allocate_virt_mem(hw, &hw->hmc.hmc_obj_virt_mem,
+ sizeof(struct i40e_hmc_obj_info) * I40E_HMC_LAN_MAX);
+ if (ret_code)
+ goto init_lan_hmc_out;
+ hw->hmc.hmc_obj = (struct i40e_hmc_obj_info *)
+ hw->hmc.hmc_obj_virt_mem.va;
+
+ /* The full object will be used to create the LAN HMC SD */
+ full_obj = &hw->hmc.hmc_obj[I40E_HMC_LAN_FULL];
+ full_obj->max_cnt = 0;
+ full_obj->cnt = 0;
+ full_obj->base = 0;
+ full_obj->size = 0;
+
+ /* Tx queue context information */
+ obj = &hw->hmc.hmc_obj[I40E_HMC_LAN_TX];
+ obj->max_cnt = rd32(hw, I40E_GLHMC_LANQMAX);
+ obj->cnt = txq_num;
+ obj->base = 0;
+ size_exp = rd32(hw, I40E_GLHMC_LANTXOBJSZ);
+ obj->size = (u64)1 << size_exp;
+
+ /* validate values requested by driver don't exceed HMC capacity */
+ if (txq_num > obj->max_cnt) {
+ ret_code = I40E_ERR_INVALID_HMC_OBJ_COUNT;
+ hw_dbg(hw, "i40e_init_lan_hmc: Tx context: asks for 0x%x but max allowed is 0x%x, returns error %d\n",
+ txq_num, obj->max_cnt, ret_code);
+ goto init_lan_hmc_out;
+ }
+
+ /* aggregate values into the full LAN object for later */
+ full_obj->max_cnt += obj->max_cnt;
+ full_obj->cnt += obj->cnt;
+
+ /* Rx queue context information */
+ obj = &hw->hmc.hmc_obj[I40E_HMC_LAN_RX];
+ obj->max_cnt = rd32(hw, I40E_GLHMC_LANQMAX);
+ obj->cnt = rxq_num;
+ obj->base = hw->hmc.hmc_obj[I40E_HMC_LAN_TX].base +
+ (hw->hmc.hmc_obj[I40E_HMC_LAN_TX].cnt *
+ hw->hmc.hmc_obj[I40E_HMC_LAN_TX].size);
+ obj->base = i40e_align_l2obj_base(obj->base);
+ size_exp = rd32(hw, I40E_GLHMC_LANRXOBJSZ);
+ obj->size = (u64)1 << size_exp;
+
+ /* validate values requested by driver don't exceed HMC capacity */
+ if (rxq_num > obj->max_cnt) {
+ ret_code = I40E_ERR_INVALID_HMC_OBJ_COUNT;
+ hw_dbg(hw, "i40e_init_lan_hmc: Rx context: asks for 0x%x but max allowed is 0x%x, returns error %d\n",
+ rxq_num, obj->max_cnt, ret_code);
+ goto init_lan_hmc_out;
+ }
+
+ /* aggregate values into the full LAN object for later */
+ full_obj->max_cnt += obj->max_cnt;
+ full_obj->cnt += obj->cnt;
+
+ /* FCoE context information */
+ obj = &hw->hmc.hmc_obj[I40E_HMC_FCOE_CTX];
+ obj->max_cnt = rd32(hw, I40E_GLHMC_FCOEMAX);
+ obj->cnt = fcoe_cntx_num;
+ obj->base = hw->hmc.hmc_obj[I40E_HMC_LAN_RX].base +
+ (hw->hmc.hmc_obj[I40E_HMC_LAN_RX].cnt *
+ hw->hmc.hmc_obj[I40E_HMC_LAN_RX].size);
+ obj->base = i40e_align_l2obj_base(obj->base);
+ size_exp = rd32(hw, I40E_GLHMC_FCOEDDPOBJSZ);
+ obj->size = (u64)1 << size_exp;
+
+ /* validate values requested by driver don't exceed HMC capacity */
+ if (fcoe_cntx_num > obj->max_cnt) {
+ ret_code = I40E_ERR_INVALID_HMC_OBJ_COUNT;
+ hw_dbg(hw, "i40e_init_lan_hmc: FCoE context: asks for 0x%x but max allowed is 0x%x, returns error %d\n",
+ fcoe_cntx_num, obj->max_cnt, ret_code);
+ goto init_lan_hmc_out;
+ }
+
+ /* aggregate values into the full LAN object for later */
+ full_obj->max_cnt += obj->max_cnt;
+ full_obj->cnt += obj->cnt;
+
+ /* FCoE filter information */
+ obj = &hw->hmc.hmc_obj[I40E_HMC_FCOE_FILT];
+ obj->max_cnt = rd32(hw, I40E_GLHMC_FCOEFMAX);
+ obj->cnt = fcoe_filt_num;
+ obj->base = hw->hmc.hmc_obj[I40E_HMC_FCOE_CTX].base +
+ (hw->hmc.hmc_obj[I40E_HMC_FCOE_CTX].cnt *
+ hw->hmc.hmc_obj[I40E_HMC_FCOE_CTX].size);
+ obj->base = i40e_align_l2obj_base(obj->base);
+ size_exp = rd32(hw, I40E_GLHMC_FCOEFOBJSZ);
+ obj->size = (u64)1 << size_exp;
+
+ /* validate values requested by driver don't exceed HMC capacity */
+ if (fcoe_filt_num > obj->max_cnt) {
+ ret_code = I40E_ERR_INVALID_HMC_OBJ_COUNT;
+ hw_dbg(hw, "i40e_init_lan_hmc: FCoE filter: asks for 0x%x but max allowed is 0x%x, returns error %d\n",
+ fcoe_filt_num, obj->max_cnt, ret_code);
+ goto init_lan_hmc_out;
+ }
+
+ /* aggregate values into the full LAN object for later */
+ full_obj->max_cnt += obj->max_cnt;
+ full_obj->cnt += obj->cnt;
+
+ hw->hmc.first_sd_index = 0;
+ hw->hmc.sd_table.ref_cnt = 0;
+ l2fpm_size = i40e_calculate_l2fpm_size(txq_num, rxq_num, fcoe_cntx_num,
+ fcoe_filt_num);
+ if (NULL == hw->hmc.sd_table.sd_entry) {
+ hw->hmc.sd_table.sd_cnt = (u32)
+ (l2fpm_size + I40E_HMC_DIRECT_BP_SIZE - 1) /
+ I40E_HMC_DIRECT_BP_SIZE;
+
+ /* allocate the sd_entry members in the sd_table */
+ ret_code = i40e_allocate_virt_mem(hw, &hw->hmc.sd_table.addr,
+ (sizeof(struct i40e_hmc_sd_entry) *
+ hw->hmc.sd_table.sd_cnt));
+ if (ret_code)
+ goto init_lan_hmc_out;
+ hw->hmc.sd_table.sd_entry =
+ (struct i40e_hmc_sd_entry *)hw->hmc.sd_table.addr.va;
+ }
+ /* store in the LAN full object for later */
+ full_obj->size = l2fpm_size;
+
+init_lan_hmc_out:
+ return ret_code;
+}
+
+/**
+ * i40e_remove_pd_page - Remove a page from the page descriptor table
+ * @hw: pointer to the HW structure
+ * @hmc_info: pointer to the HMC configuration information structure
+ * @idx: segment descriptor index to find the relevant page descriptor
+ *
+ * This function:
+ * 1. Marks the entry in pd table (for paged address mode) invalid
+ * 2. write to register PMPDINV to invalidate the backing page in FV cache
+ * 3. Decrement the ref count for pd_entry
+ * assumptions:
+ * 1. caller can deallocate the memory used by pd after this function
+ * returns.
+ **/
+static i40e_status i40e_remove_pd_page(struct i40e_hw *hw,
+ struct i40e_hmc_info *hmc_info,
+ u32 idx)
+{
+ i40e_status ret_code = 0;
+
+ if (!i40e_prep_remove_pd_page(hmc_info, idx))
+ ret_code = i40e_remove_pd_page_new(hw, hmc_info, idx, true);
+
+ return ret_code;
+}
+
+/**
+ * i40e_remove_sd_bp - remove a backing page from a segment descriptor
+ * @hw: pointer to our HW structure
+ * @hmc_info: pointer to the HMC configuration information structure
+ * @idx: the page index
+ *
+ * This function:
+ * 1. Marks the entry in sd table (for direct address mode) invalid
+ * 2. write to register PMSDCMD, PMSDDATALOW(PMSDDATALOW.PMSDVALID set
+ * to 0) and PMSDDATAHIGH to invalidate the sd page
+ * 3. Decrement the ref count for the sd_entry
+ * assumptions:
+ * 1. caller can deallocate the memory used by backing storage after this
+ * function returns.
+ **/
+static i40e_status i40e_remove_sd_bp(struct i40e_hw *hw,
+ struct i40e_hmc_info *hmc_info,
+ u32 idx)
+{
+ i40e_status ret_code = 0;
+
+ if (!i40e_prep_remove_sd_bp(hmc_info, idx))
+ ret_code = i40e_remove_sd_bp_new(hw, hmc_info, idx, true);
+
+ return ret_code;
+}
+
+/**
+ * i40e_create_lan_hmc_object - allocate backing store for hmc objects
+ * @hw: pointer to the HW structure
+ * @info: pointer to i40e_hmc_create_obj_info struct
+ *
+ * This will allocate memory for PDs and backing pages and populate
+ * the sd and pd entries.
+ **/
+static i40e_status i40e_create_lan_hmc_object(struct i40e_hw *hw,
+ struct i40e_hmc_lan_create_obj_info *info)
+{
+ i40e_status ret_code = 0;
+ struct i40e_hmc_sd_entry *sd_entry;
+ u32 pd_idx1 = 0, pd_lmt1 = 0;
+ u32 pd_idx = 0, pd_lmt = 0;
+ bool pd_error = false;
+ u32 sd_idx, sd_lmt;
+ u64 sd_size;
+ u32 i, j;
+
+ if (NULL == info) {
+ ret_code = I40E_ERR_BAD_PTR;
+ hw_dbg(hw, "i40e_create_lan_hmc_object: bad info ptr\n");
+ goto exit;
+ }
+ if (NULL == info->hmc_info) {
+ ret_code = I40E_ERR_BAD_PTR;
+ hw_dbg(hw, "i40e_create_lan_hmc_object: bad hmc_info ptr\n");
+ goto exit;
+ }
+ if (I40E_HMC_INFO_SIGNATURE != info->hmc_info->signature) {
+ ret_code = I40E_ERR_BAD_PTR;
+ hw_dbg(hw, "i40e_create_lan_hmc_object: bad signature\n");
+ goto exit;
+ }
+
+ if (info->start_idx >= info->hmc_info->hmc_obj[info->rsrc_type].cnt) {
+ ret_code = I40E_ERR_INVALID_HMC_OBJ_INDEX;
+ hw_dbg(hw, "i40e_create_lan_hmc_object: returns error %d\n",
+ ret_code);
+ goto exit;
+ }
+ if ((info->start_idx + info->count) >
+ info->hmc_info->hmc_obj[info->rsrc_type].cnt) {
+ ret_code = I40E_ERR_INVALID_HMC_OBJ_COUNT;
+ hw_dbg(hw, "i40e_create_lan_hmc_object: returns error %d\n",
+ ret_code);
+ goto exit;
+ }
+
+ /* find sd index and limit */
+ I40E_FIND_SD_INDEX_LIMIT(info->hmc_info, info->rsrc_type,
+ info->start_idx, info->count,
+ &sd_idx, &sd_lmt);
+ if (sd_idx >= info->hmc_info->sd_table.sd_cnt ||
+ sd_lmt > info->hmc_info->sd_table.sd_cnt) {
+ ret_code = I40E_ERR_INVALID_SD_INDEX;
+ goto exit;
+ }
+ /* find pd index */
+ I40E_FIND_PD_INDEX_LIMIT(info->hmc_info, info->rsrc_type,
+ info->start_idx, info->count, &pd_idx,
+ &pd_lmt);
+
+ /* This is to cover for cases where you may not want to have an SD with
+ * the full 2M memory but something smaller. By not filling out any
+ * size, the function will default the SD size to be 2M.
+ */
+ if (info->direct_mode_sz == 0)
+ sd_size = I40E_HMC_DIRECT_BP_SIZE;
+ else
+ sd_size = info->direct_mode_sz;
+
+ /* check if all the sds are valid. If not, allocate a page and
+ * initialize it.
+ */
+ for (j = sd_idx; j < sd_lmt; j++) {
+ /* update the sd table entry */
+ ret_code = i40e_add_sd_table_entry(hw, info->hmc_info, j,
+ info->entry_type,
+ sd_size);
+ if (ret_code)
+ goto exit_sd_error;
+ sd_entry = &info->hmc_info->sd_table.sd_entry[j];
+ if (I40E_SD_TYPE_PAGED == sd_entry->entry_type) {
+ /* check if all the pds in this sd are valid. If not,
+ * allocate a page and initialize it.
+ */
+
+ /* find pd_idx and pd_lmt in this sd */
+ pd_idx1 = max(pd_idx, (j * I40E_HMC_MAX_BP_COUNT));
+ pd_lmt1 = min(pd_lmt,
+ ((j + 1) * I40E_HMC_MAX_BP_COUNT));
+ for (i = pd_idx1; i < pd_lmt1; i++) {
+ /* update the pd table entry */
+ ret_code = i40e_add_pd_table_entry(hw,
+ info->hmc_info,
+ i);
+ if (ret_code) {
+ pd_error = true;
+ break;
+ }
+ }
+ if (pd_error) {
+ /* remove the backing pages from pd_idx1 to i */
+ while (i && (i > pd_idx1)) {
+ i40e_remove_pd_bp(hw, info->hmc_info,
+ (i - 1), true);
+ i--;
+ }
+ }
+ }
+ if (!sd_entry->valid) {
+ sd_entry->valid = true;
+ switch (sd_entry->entry_type) {
+ case I40E_SD_TYPE_PAGED:
+ I40E_SET_PF_SD_ENTRY(hw,
+ sd_entry->u.pd_table.pd_page_addr.pa,
+ j, sd_entry->entry_type);
+ break;
+ case I40E_SD_TYPE_DIRECT:
+ I40E_SET_PF_SD_ENTRY(hw, sd_entry->u.bp.addr.pa,
+ j, sd_entry->entry_type);
+ break;
+ default:
+ ret_code = I40E_ERR_INVALID_SD_TYPE;
+ goto exit;
+ break;
+ }
+ }
+ }
+ goto exit;
+
+exit_sd_error:
+ /* cleanup for sd entries from j to sd_idx */
+ while (j && (j > sd_idx)) {
+ sd_entry = &info->hmc_info->sd_table.sd_entry[j - 1];
+ switch (sd_entry->entry_type) {
+ case I40E_SD_TYPE_PAGED:
+ pd_idx1 = max(pd_idx,
+ ((j - 1) * I40E_HMC_MAX_BP_COUNT));
+ pd_lmt1 = min(pd_lmt, (j * I40E_HMC_MAX_BP_COUNT));
+ for (i = pd_idx1; i < pd_lmt1; i++) {
+ i40e_remove_pd_bp(
+ hw,
+ info->hmc_info,
+ i,
+ true);
+ }
+ i40e_remove_pd_page(hw, info->hmc_info, (j - 1));
+ break;
+ case I40E_SD_TYPE_DIRECT:
+ i40e_remove_sd_bp(hw, info->hmc_info, (j - 1));
+ break;
+ default:
+ ret_code = I40E_ERR_INVALID_SD_TYPE;
+ break;
+ }
+ j--;
+ }
+exit:
+ return ret_code;
+}
+
+/**
+ * i40e_configure_lan_hmc - prepare the HMC backing store
+ * @hw: pointer to the hw structure
+ * @model: the model for the layout of the SD/PD tables
+ *
+ * - This function will be called once per physical function initialization.
+ * - This function will be called after i40e_init_lan_hmc() and before
+ * any LAN/FCoE HMC objects can be created.
+ **/
+i40e_status i40e_configure_lan_hmc(struct i40e_hw *hw,
+ enum i40e_hmc_model model)
+{
+ struct i40e_hmc_lan_create_obj_info info;
+ i40e_status ret_code = 0;
+ u8 hmc_fn_id = hw->hmc.hmc_fn_id;
+ struct i40e_hmc_obj_info *obj;
+
+ /* Initialize part of the create object info struct */
+ info.hmc_info = &hw->hmc;
+ info.rsrc_type = I40E_HMC_LAN_FULL;
+ info.start_idx = 0;
+ info.direct_mode_sz = hw->hmc.hmc_obj[I40E_HMC_LAN_FULL].size;
+
+ /* Build the SD entry for the LAN objects */
+ switch (model) {
+ case I40E_HMC_MODEL_DIRECT_PREFERRED:
+ case I40E_HMC_MODEL_DIRECT_ONLY:
+ info.entry_type = I40E_SD_TYPE_DIRECT;
+ /* Make one big object, a single SD */
+ info.count = 1;
+ ret_code = i40e_create_lan_hmc_object(hw, &info);
+ if ((ret_code) &&
+ (model == I40E_HMC_MODEL_DIRECT_PREFERRED))
+ goto try_type_paged;
+ else if (ret_code)
+ goto configure_lan_hmc_out;
+ /* else clause falls through the break */
+ break;
+ case I40E_HMC_MODEL_PAGED_ONLY:
+try_type_paged:
+ info.entry_type = I40E_SD_TYPE_PAGED;
+ /* Make one big object in the PD table */
+ info.count = 1;
+ ret_code = i40e_create_lan_hmc_object(hw, &info);
+ if (ret_code)
+ goto configure_lan_hmc_out;
+ break;
+ default:
+ /* unsupported type */
+ ret_code = I40E_ERR_INVALID_SD_TYPE;
+ hw_dbg(hw, "i40e_configure_lan_hmc: Unknown SD type: %d\n",
+ ret_code);
+ goto configure_lan_hmc_out;
+ break;
+ }
+
+ /* Configure and program the FPM registers so objects can be created */
+
+ /* Tx contexts */
+ obj = &hw->hmc.hmc_obj[I40E_HMC_LAN_TX];
+ wr32(hw, I40E_GLHMC_LANTXBASE(hmc_fn_id),
+ (u32)((obj->base & I40E_GLHMC_LANTXBASE_FPMLANTXBASE_MASK) / 512));
+ wr32(hw, I40E_GLHMC_LANTXCNT(hmc_fn_id), obj->cnt);
+
+ /* Rx contexts */
+ obj = &hw->hmc.hmc_obj[I40E_HMC_LAN_RX];
+ wr32(hw, I40E_GLHMC_LANRXBASE(hmc_fn_id),
+ (u32)((obj->base & I40E_GLHMC_LANRXBASE_FPMLANRXBASE_MASK) / 512));
+ wr32(hw, I40E_GLHMC_LANRXCNT(hmc_fn_id), obj->cnt);
+
+ /* FCoE contexts */
+ obj = &hw->hmc.hmc_obj[I40E_HMC_FCOE_CTX];
+ wr32(hw, I40E_GLHMC_FCOEDDPBASE(hmc_fn_id),
+ (u32)((obj->base & I40E_GLHMC_FCOEDDPBASE_FPMFCOEDDPBASE_MASK) / 512));
+ wr32(hw, I40E_GLHMC_FCOEDDPCNT(hmc_fn_id), obj->cnt);
+
+ /* FCoE filters */
+ obj = &hw->hmc.hmc_obj[I40E_HMC_FCOE_FILT];
+ wr32(hw, I40E_GLHMC_FCOEFBASE(hmc_fn_id),
+ (u32)((obj->base & I40E_GLHMC_FCOEFBASE_FPMFCOEFBASE_MASK) / 512));
+ wr32(hw, I40E_GLHMC_FCOEFCNT(hmc_fn_id), obj->cnt);
+
+configure_lan_hmc_out:
+ return ret_code;
+}
+
+/**
+ * i40e_delete_hmc_object - remove hmc objects
+ * @hw: pointer to the HW structure
+ * @info: pointer to i40e_hmc_delete_obj_info struct
+ *
+ * This will de-populate the SDs and PDs. It frees
+ * the memory for PDS and backing storage. After this function is returned,
+ * caller should deallocate memory allocated previously for
+ * book-keeping information about PDs and backing storage.
+ **/
+static i40e_status i40e_delete_lan_hmc_object(struct i40e_hw *hw,
+ struct i40e_hmc_lan_delete_obj_info *info)
+{
+ i40e_status ret_code = 0;
+ struct i40e_hmc_pd_table *pd_table;
+ u32 pd_idx, pd_lmt, rel_pd_idx;
+ u32 sd_idx, sd_lmt;
+ u32 i, j;
+
+ if (NULL == info) {
+ ret_code = I40E_ERR_BAD_PTR;
+ hw_dbg(hw, "i40e_delete_hmc_object: bad info ptr\n");
+ goto exit;
+ }
+ if (NULL == info->hmc_info) {
+ ret_code = I40E_ERR_BAD_PTR;
+ hw_dbg(hw, "i40e_delete_hmc_object: bad info->hmc_info ptr\n");
+ goto exit;
+ }
+ if (I40E_HMC_INFO_SIGNATURE != info->hmc_info->signature) {
+ ret_code = I40E_ERR_BAD_PTR;
+ hw_dbg(hw, "i40e_delete_hmc_object: bad hmc_info->signature\n");
+ goto exit;
+ }
+
+ if (NULL == info->hmc_info->sd_table.sd_entry) {
+ ret_code = I40E_ERR_BAD_PTR;
+ hw_dbg(hw, "i40e_delete_hmc_object: bad sd_entry\n");
+ goto exit;
+ }
+
+ if (NULL == info->hmc_info->hmc_obj) {
+ ret_code = I40E_ERR_BAD_PTR;
+ hw_dbg(hw, "i40e_delete_hmc_object: bad hmc_info->hmc_obj\n");
+ goto exit;
+ }
+ if (info->start_idx >= info->hmc_info->hmc_obj[info->rsrc_type].cnt) {
+ ret_code = I40E_ERR_INVALID_HMC_OBJ_INDEX;
+ hw_dbg(hw, "i40e_delete_hmc_object: returns error %d\n",
+ ret_code);
+ goto exit;
+ }
+
+ if ((info->start_idx + info->count) >
+ info->hmc_info->hmc_obj[info->rsrc_type].cnt) {
+ ret_code = I40E_ERR_INVALID_HMC_OBJ_COUNT;
+ hw_dbg(hw, "i40e_delete_hmc_object: returns error %d\n",
+ ret_code);
+ goto exit;
+ }
+
+ I40E_FIND_PD_INDEX_LIMIT(info->hmc_info, info->rsrc_type,
+ info->start_idx, info->count, &pd_idx,
+ &pd_lmt);
+
+ for (j = pd_idx; j < pd_lmt; j++) {
+ sd_idx = j / I40E_HMC_PD_CNT_IN_SD;
+
+ if (I40E_SD_TYPE_PAGED !=
+ info->hmc_info->sd_table.sd_entry[sd_idx].entry_type)
+ continue;
+
+ rel_pd_idx = j % I40E_HMC_PD_CNT_IN_SD;
+
+ pd_table =
+ &info->hmc_info->sd_table.sd_entry[sd_idx].u.pd_table;
+ if (pd_table->pd_entry[rel_pd_idx].valid) {
+ ret_code = i40e_remove_pd_bp(hw, info->hmc_info,
+ j, true);
+ if (ret_code)
+ goto exit;
+ }
+ }
+
+ /* find sd index and limit */
+ I40E_FIND_SD_INDEX_LIMIT(info->hmc_info, info->rsrc_type,
+ info->start_idx, info->count,
+ &sd_idx, &sd_lmt);
+ if (sd_idx >= info->hmc_info->sd_table.sd_cnt ||
+ sd_lmt > info->hmc_info->sd_table.sd_cnt) {
+ ret_code = I40E_ERR_INVALID_SD_INDEX;
+ goto exit;
+ }
+
+ for (i = sd_idx; i < sd_lmt; i++) {
+ if (!info->hmc_info->sd_table.sd_entry[i].valid)
+ continue;
+ switch (info->hmc_info->sd_table.sd_entry[i].entry_type) {
+ case I40E_SD_TYPE_DIRECT:
+ ret_code = i40e_remove_sd_bp(hw, info->hmc_info, i);
+ if (ret_code)
+ goto exit;
+ break;
+ case I40E_SD_TYPE_PAGED:
+ ret_code = i40e_remove_pd_page(hw, info->hmc_info, i);
+ if (ret_code)
+ goto exit;
+ break;
+ default:
+ break;
+ }
+ }
+exit:
+ return ret_code;
+}
+
+/**
+ * i40e_shutdown_lan_hmc - Remove HMC backing store, free allocated memory
+ * @hw: pointer to the hw structure
+ *
+ * This must be called by drivers as they are shutting down and being
+ * removed from the OS.
+ **/
+i40e_status i40e_shutdown_lan_hmc(struct i40e_hw *hw)
+{
+ struct i40e_hmc_lan_delete_obj_info info;
+ i40e_status ret_code;
+
+ info.hmc_info = &hw->hmc;
+ info.rsrc_type = I40E_HMC_LAN_FULL;
+ info.start_idx = 0;
+ info.count = 1;
+
+ /* delete the object */
+ ret_code = i40e_delete_lan_hmc_object(hw, &info);
+
+ /* free the SD table entry for LAN */
+ i40e_free_virt_mem(hw, &hw->hmc.sd_table.addr);
+ hw->hmc.sd_table.sd_cnt = 0;
+ hw->hmc.sd_table.sd_entry = NULL;
+
+ /* free memory used for hmc_obj */
+ i40e_free_virt_mem(hw, &hw->hmc.hmc_obj_virt_mem);
+ hw->hmc.hmc_obj = NULL;
+
+ return ret_code;
+}
+
+#define I40E_HMC_STORE(_struct, _ele) \
+ offsetof(struct _struct, _ele), \
+ FIELD_SIZEOF(struct _struct, _ele)
+
+struct i40e_context_ele {
+ u16 offset;
+ u16 size_of;
+ u16 width;
+ u16 lsb;
+};
+
+/* LAN Tx Queue Context */
+static struct i40e_context_ele i40e_hmc_txq_ce_info[] = {
+ /* Field Width LSB */
+ {I40E_HMC_STORE(i40e_hmc_obj_txq, head), 13, 0 },
+ {I40E_HMC_STORE(i40e_hmc_obj_txq, new_context), 1, 30 },
+ {I40E_HMC_STORE(i40e_hmc_obj_txq, base), 57, 32 },
+ {I40E_HMC_STORE(i40e_hmc_obj_txq, fc_ena), 1, 89 },
+ {I40E_HMC_STORE(i40e_hmc_obj_txq, timesync_ena), 1, 90 },
+ {I40E_HMC_STORE(i40e_hmc_obj_txq, fd_ena), 1, 91 },
+ {I40E_HMC_STORE(i40e_hmc_obj_txq, alt_vlan_ena), 1, 92 },
+ {I40E_HMC_STORE(i40e_hmc_obj_txq, cpuid), 8, 96 },
+/* line 1 */
+ {I40E_HMC_STORE(i40e_hmc_obj_txq, thead_wb), 13, 0 + 128 },
+ {I40E_HMC_STORE(i40e_hmc_obj_txq, head_wb_ena), 1, 32 + 128 },
+ {I40E_HMC_STORE(i40e_hmc_obj_txq, qlen), 13, 33 + 128 },
+ {I40E_HMC_STORE(i40e_hmc_obj_txq, tphrdesc_ena), 1, 46 + 128 },
+ {I40E_HMC_STORE(i40e_hmc_obj_txq, tphrpacket_ena), 1, 47 + 128 },
+ {I40E_HMC_STORE(i40e_hmc_obj_txq, tphwdesc_ena), 1, 48 + 128 },
+ {I40E_HMC_STORE(i40e_hmc_obj_txq, head_wb_addr), 64, 64 + 128 },
+/* line 7 */
+ {I40E_HMC_STORE(i40e_hmc_obj_txq, crc), 32, 0 + (7 * 128) },
+ {I40E_HMC_STORE(i40e_hmc_obj_txq, rdylist), 10, 84 + (7 * 128) },
+ {I40E_HMC_STORE(i40e_hmc_obj_txq, rdylist_act), 1, 94 + (7 * 128) },
+ { 0 }
+};
+
+/* LAN Rx Queue Context */
+static struct i40e_context_ele i40e_hmc_rxq_ce_info[] = {
+ /* Field Width LSB */
+ { I40E_HMC_STORE(i40e_hmc_obj_rxq, head), 13, 0 },
+ { I40E_HMC_STORE(i40e_hmc_obj_rxq, cpuid), 8, 13 },
+ { I40E_HMC_STORE(i40e_hmc_obj_rxq, base), 57, 32 },
+ { I40E_HMC_STORE(i40e_hmc_obj_rxq, qlen), 13, 89 },
+ { I40E_HMC_STORE(i40e_hmc_obj_rxq, dbuff), 7, 102 },
+ { I40E_HMC_STORE(i40e_hmc_obj_rxq, hbuff), 5, 109 },
+ { I40E_HMC_STORE(i40e_hmc_obj_rxq, dtype), 2, 114 },
+ { I40E_HMC_STORE(i40e_hmc_obj_rxq, dsize), 1, 116 },
+ { I40E_HMC_STORE(i40e_hmc_obj_rxq, crcstrip), 1, 117 },
+ { I40E_HMC_STORE(i40e_hmc_obj_rxq, fc_ena), 1, 118 },
+ { I40E_HMC_STORE(i40e_hmc_obj_rxq, l2tsel), 1, 119 },
+ { I40E_HMC_STORE(i40e_hmc_obj_rxq, hsplit_0), 4, 120 },
+ { I40E_HMC_STORE(i40e_hmc_obj_rxq, hsplit_1), 2, 124 },
+ { I40E_HMC_STORE(i40e_hmc_obj_rxq, showiv), 1, 127 },
+ { I40E_HMC_STORE(i40e_hmc_obj_rxq, rxmax), 14, 174 },
+ { I40E_HMC_STORE(i40e_hmc_obj_rxq, tphrdesc_ena), 1, 193 },
+ { I40E_HMC_STORE(i40e_hmc_obj_rxq, tphwdesc_ena), 1, 194 },
+ { I40E_HMC_STORE(i40e_hmc_obj_rxq, tphdata_ena), 1, 195 },
+ { I40E_HMC_STORE(i40e_hmc_obj_rxq, tphhead_ena), 1, 196 },
+ { I40E_HMC_STORE(i40e_hmc_obj_rxq, lrxqthresh), 3, 198 },
+ { 0 }
+};
+
+/**
+ * i40e_clear_hmc_context - zero out the HMC context bits
+ * @hw: the hardware struct
+ * @context_bytes: pointer to the context bit array (DMA memory)
+ * @hmc_type: the type of HMC resource
+ **/
+static i40e_status i40e_clear_hmc_context(struct i40e_hw *hw,
+ u8 *context_bytes,
+ enum i40e_hmc_lan_rsrc_type hmc_type)
+{
+ /* clean the bit array */
+ memset(context_bytes, 0, (u32)hw->hmc.hmc_obj[hmc_type].size);
+
+ return 0;
+}
+
+/**
+ * i40e_set_hmc_context - replace HMC context bits
+ * @context_bytes: pointer to the context bit array
+ * @ce_info: a description of the struct to be filled
+ * @dest: the struct to be filled
+ **/
+static i40e_status i40e_set_hmc_context(u8 *context_bytes,
+ struct i40e_context_ele *ce_info,
+ u8 *dest)
+{
+ u16 shift_width;
+ u64 bitfield;
+ u8 hi_byte;
+ u8 hi_mask;
+ u64 t_bits;
+ u64 mask;
+ u8 *p;
+ int f;
+
+ for (f = 0; ce_info[f].width != 0; f++) {
+ /* clear out the field */
+ bitfield = 0;
+
+ /* copy from the next struct field */
+ p = dest + ce_info[f].offset;
+ switch (ce_info[f].size_of) {
+ case 1:
+ bitfield = *p;
+ break;
+ case 2:
+ bitfield = cpu_to_le16(*(u16 *)p);
+ break;
+ case 4:
+ bitfield = cpu_to_le32(*(u32 *)p);
+ break;
+ case 8:
+ bitfield = cpu_to_le64(*(u64 *)p);
+ break;
+ }
+
+ /* prepare the bits and mask */
+ shift_width = ce_info[f].lsb % 8;
+ mask = ((u64)1 << ce_info[f].width) - 1;
+
+ /* save upper bytes for special case */
+ hi_mask = (u8)((mask >> 56) & 0xff);
+ hi_byte = (u8)((bitfield >> 56) & 0xff);
+
+ /* shift to correct alignment */
+ mask <<= shift_width;
+ bitfield <<= shift_width;
+
+ /* get the current bits from the target bit string */
+ p = context_bytes + (ce_info[f].lsb / 8);
+ memcpy(&t_bits, p, sizeof(u64));
+
+ t_bits &= ~mask; /* get the bits not changing */
+ t_bits |= bitfield; /* add in the new bits */
+
+ /* put it all back */
+ memcpy(p, &t_bits, sizeof(u64));
+
+ /* deal with the special case if needed
+ * example: 62 bit field that starts in bit 5 of first byte
+ * will overlap 3 bits into byte 9
+ */
+ if ((shift_width + ce_info[f].width) > 64) {
+ u8 byte;
+
+ hi_mask >>= (8 - shift_width);
+ hi_byte >>= (8 - shift_width);
+ byte = p[8] & ~hi_mask; /* get the bits not changing */
+ byte |= hi_byte; /* add in the new bits */
+ p[8] = byte; /* put it back */
+ }
+ }
+
+ return 0;
+}
+
+/**
+ * i40e_hmc_get_object_va - retrieves an object's virtual address
+ * @hmc_info: pointer to i40e_hmc_info struct
+ * @object_base: pointer to u64 to get the va
+ * @rsrc_type: the hmc resource type
+ * @obj_idx: hmc object index
+ *
+ * This function retrieves the object's virtual address from the object
+ * base pointer. This function is used for LAN Queue contexts.
+ **/
+static
+i40e_status i40e_hmc_get_object_va(struct i40e_hmc_info *hmc_info,
+ u8 **object_base,
+ enum i40e_hmc_lan_rsrc_type rsrc_type,
+ u32 obj_idx)
+{
+ u32 obj_offset_in_sd, obj_offset_in_pd;
+ i40e_status ret_code = 0;
+ struct i40e_hmc_sd_entry *sd_entry;
+ struct i40e_hmc_pd_entry *pd_entry;
+ u32 pd_idx, pd_lmt, rel_pd_idx;
+ u64 obj_offset_in_fpm;
+ u32 sd_idx, sd_lmt;
+
+ if (NULL == hmc_info) {
+ ret_code = I40E_ERR_BAD_PTR;
+ hw_dbg(hw, "i40e_hmc_get_object_va: bad hmc_info ptr\n");
+ goto exit;
+ }
+ if (NULL == hmc_info->hmc_obj) {
+ ret_code = I40E_ERR_BAD_PTR;
+ hw_dbg(hw, "i40e_hmc_get_object_va: bad hmc_info->hmc_obj ptr\n");
+ goto exit;
+ }
+ if (NULL == object_base) {
+ ret_code = I40E_ERR_BAD_PTR;
+ hw_dbg(hw, "i40e_hmc_get_object_va: bad object_base ptr\n");
+ goto exit;
+ }
+ if (I40E_HMC_INFO_SIGNATURE != hmc_info->signature) {
+ ret_code = I40E_ERR_BAD_PTR;
+ hw_dbg(hw, "i40e_hmc_get_object_va: bad hmc_info->signature\n");
+ goto exit;
+ }
+ if (obj_idx >= hmc_info->hmc_obj[rsrc_type].cnt) {
+ hw_dbg(hw, "i40e_hmc_get_object_va: returns error %d\n",
+ ret_code);
+ ret_code = I40E_ERR_INVALID_HMC_OBJ_INDEX;
+ goto exit;
+ }
+ /* find sd index and limit */
+ I40E_FIND_SD_INDEX_LIMIT(hmc_info, rsrc_type, obj_idx, 1,
+ &sd_idx, &sd_lmt);
+
+ sd_entry = &hmc_info->sd_table.sd_entry[sd_idx];
+ obj_offset_in_fpm = hmc_info->hmc_obj[rsrc_type].base +
+ hmc_info->hmc_obj[rsrc_type].size * obj_idx;
+
+ if (I40E_SD_TYPE_PAGED == sd_entry->entry_type) {
+ I40E_FIND_PD_INDEX_LIMIT(hmc_info, rsrc_type, obj_idx, 1,
+ &pd_idx, &pd_lmt);
+ rel_pd_idx = pd_idx % I40E_HMC_PD_CNT_IN_SD;
+ pd_entry = &sd_entry->u.pd_table.pd_entry[rel_pd_idx];
+ obj_offset_in_pd = (u32)(obj_offset_in_fpm %
+ I40E_HMC_PAGED_BP_SIZE);
+ *object_base = (u8 *)pd_entry->bp.addr.va + obj_offset_in_pd;
+ } else {
+ obj_offset_in_sd = (u32)(obj_offset_in_fpm %
+ I40E_HMC_DIRECT_BP_SIZE);
+ *object_base = (u8 *)sd_entry->u.bp.addr.va + obj_offset_in_sd;
+ }
+exit:
+ return ret_code;
+}
+
+/**
+ * i40e_clear_lan_tx_queue_context - clear the HMC context for the queue
+ * @hw: the hardware struct
+ * @queue: the queue we care about
+ **/
+i40e_status i40e_clear_lan_tx_queue_context(struct i40e_hw *hw,
+ u16 queue)
+{
+ i40e_status err;
+ u8 *context_bytes;
+
+ err = i40e_hmc_get_object_va(&hw->hmc, &context_bytes,
+ I40E_HMC_LAN_TX, queue);
+ if (err < 0)
+ return err;
+
+ return i40e_clear_hmc_context(hw, context_bytes, I40E_HMC_LAN_TX);
+}
+
+/**
+ * i40e_set_lan_tx_queue_context - set the HMC context for the queue
+ * @hw: the hardware struct
+ * @queue: the queue we care about
+ * @s: the struct to be filled
+ **/
+i40e_status i40e_set_lan_tx_queue_context(struct i40e_hw *hw,
+ u16 queue,
+ struct i40e_hmc_obj_txq *s)
+{
+ i40e_status err;
+ u8 *context_bytes;
+
+ err = i40e_hmc_get_object_va(&hw->hmc, &context_bytes,
+ I40E_HMC_LAN_TX, queue);
+ if (err < 0)
+ return err;
+
+ return i40e_set_hmc_context(context_bytes,
+ i40e_hmc_txq_ce_info, (u8 *)s);
+}
+
+/**
+ * i40e_clear_lan_rx_queue_context - clear the HMC context for the queue
+ * @hw: the hardware struct
+ * @queue: the queue we care about
+ **/
+i40e_status i40e_clear_lan_rx_queue_context(struct i40e_hw *hw,
+ u16 queue)
+{
+ i40e_status err;
+ u8 *context_bytes;
+
+ err = i40e_hmc_get_object_va(&hw->hmc, &context_bytes,
+ I40E_HMC_LAN_RX, queue);
+ if (err < 0)
+ return err;
+
+ return i40e_clear_hmc_context(hw, context_bytes, I40E_HMC_LAN_RX);
+}
+
+/**
+ * i40e_set_lan_rx_queue_context - set the HMC context for the queue
+ * @hw: the hardware struct
+ * @queue: the queue we care about
+ * @s: the struct to be filled
+ **/
+i40e_status i40e_set_lan_rx_queue_context(struct i40e_hw *hw,
+ u16 queue,
+ struct i40e_hmc_obj_rxq *s)
+{
+ i40e_status err;
+ u8 *context_bytes;
+
+ err = i40e_hmc_get_object_va(&hw->hmc, &context_bytes,
+ I40E_HMC_LAN_RX, queue);
+ if (err < 0)
+ return err;
+
+ return i40e_set_hmc_context(context_bytes,
+ i40e_hmc_rxq_ce_info, (u8 *)s);
+}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.h b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.h
new file mode 100644
index 0000000..00ff35006
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.h
@@ -0,0 +1,169 @@
+/*******************************************************************************
+ *
+ * Intel Ethernet Controller XL710 Family Linux Driver
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ ******************************************************************************/
+
+#ifndef _I40E_LAN_HMC_H_
+#define _I40E_LAN_HMC_H_
+
+/* forward-declare the HW struct for the compiler */
+struct i40e_hw;
+
+/* HMC element context information */
+
+/* Rx queue context data */
+struct i40e_hmc_obj_rxq {
+ u16 head;
+ u8 cpuid;
+ u64 base;
+ u16 qlen;
+#define I40E_RXQ_CTX_DBUFF_SHIFT 7
+ u8 dbuff;
+#define I40E_RXQ_CTX_HBUFF_SHIFT 6
+ u8 hbuff;
+ u8 dtype;
+ u8 dsize;
+ u8 crcstrip;
+ u8 fc_ena;
+ u8 l2tsel;
+ u8 hsplit_0;
+ u8 hsplit_1;
+ u8 showiv;
+ u16 rxmax;
+ u8 tphrdesc_ena;
+ u8 tphwdesc_ena;
+ u8 tphdata_ena;
+ u8 tphhead_ena;
+ u8 lrxqthresh;
+};
+
+/* Tx queue context data */
+struct i40e_hmc_obj_txq {
+ u16 head;
+ u8 new_context;
+ u64 base;
+ u8 fc_ena;
+ u8 timesync_ena;
+ u8 fd_ena;
+ u8 alt_vlan_ena;
+ u16 thead_wb;
+ u16 cpuid;
+ u8 head_wb_ena;
+ u16 qlen;
+ u8 tphrdesc_ena;
+ u8 tphrpacket_ena;
+ u8 tphwdesc_ena;
+ u64 head_wb_addr;
+ u32 crc;
+ u16 rdylist;
+ u8 rdylist_act;
+};
+
+/* for hsplit_0 field of Rx HMC context */
+enum i40e_hmc_obj_rx_hsplit_0 {
+ I40E_HMC_OBJ_RX_HSPLIT_0_NO_SPLIT = 0,
+ I40E_HMC_OBJ_RX_HSPLIT_0_SPLIT_L2 = 1,
+ I40E_HMC_OBJ_RX_HSPLIT_0_SPLIT_IP = 2,
+ I40E_HMC_OBJ_RX_HSPLIT_0_SPLIT_TCP_UDP = 4,
+ I40E_HMC_OBJ_RX_HSPLIT_0_SPLIT_SCTP = 8,
+};
+
+/* fcoe_cntx and fcoe_filt are for debugging purpose only */
+struct i40e_hmc_obj_fcoe_cntx {
+ u32 rsv[32];
+};
+
+struct i40e_hmc_obj_fcoe_filt {
+ u32 rsv[8];
+};
+
+/* Context sizes for LAN objects */
+enum i40e_hmc_lan_object_size {
+ I40E_HMC_LAN_OBJ_SZ_8 = 0x3,
+ I40E_HMC_LAN_OBJ_SZ_16 = 0x4,
+ I40E_HMC_LAN_OBJ_SZ_32 = 0x5,
+ I40E_HMC_LAN_OBJ_SZ_64 = 0x6,
+ I40E_HMC_LAN_OBJ_SZ_128 = 0x7,
+ I40E_HMC_LAN_OBJ_SZ_256 = 0x8,
+ I40E_HMC_LAN_OBJ_SZ_512 = 0x9,
+};
+
+#define I40E_HMC_L2OBJ_BASE_ALIGNMENT 512
+#define I40E_HMC_OBJ_SIZE_TXQ 128
+#define I40E_HMC_OBJ_SIZE_RXQ 32
+#define I40E_HMC_OBJ_SIZE_FCOE_CNTX 128
+#define I40E_HMC_OBJ_SIZE_FCOE_FILT 32
+
+enum i40e_hmc_lan_rsrc_type {
+ I40E_HMC_LAN_FULL = 0,
+ I40E_HMC_LAN_TX = 1,
+ I40E_HMC_LAN_RX = 2,
+ I40E_HMC_FCOE_CTX = 3,
+ I40E_HMC_FCOE_FILT = 4,
+ I40E_HMC_LAN_MAX = 5
+};
+
+enum i40e_hmc_model {
+ I40E_HMC_MODEL_DIRECT_PREFERRED = 0,
+ I40E_HMC_MODEL_DIRECT_ONLY = 1,
+ I40E_HMC_MODEL_PAGED_ONLY = 2,
+ I40E_HMC_MODEL_UNKNOWN,
+};
+
+struct i40e_hmc_lan_create_obj_info {
+ struct i40e_hmc_info *hmc_info;
+ u32 rsrc_type;
+ u32 start_idx;
+ u32 count;
+ enum i40e_sd_entry_type entry_type;
+ u64 direct_mode_sz;
+};
+
+struct i40e_hmc_lan_delete_obj_info {
+ struct i40e_hmc_info *hmc_info;
+ u32 rsrc_type;
+ u32 start_idx;
+ u32 count;
+};
+
+i40e_status i40e_init_lan_hmc(struct i40e_hw *hw, u32 txq_num,
+ u32 rxq_num, u32 fcoe_cntx_num,
+ u32 fcoe_filt_num);
+i40e_status i40e_configure_lan_hmc(struct i40e_hw *hw,
+ enum i40e_hmc_model model);
+i40e_status i40e_shutdown_lan_hmc(struct i40e_hw *hw);
+
+i40e_status i40e_clear_lan_tx_queue_context(struct i40e_hw *hw,
+ u16 queue);
+i40e_status i40e_set_lan_tx_queue_context(struct i40e_hw *hw,
+ u16 queue,
+ struct i40e_hmc_obj_txq *s);
+i40e_status i40e_clear_lan_rx_queue_context(struct i40e_hw *hw,
+ u16 queue);
+i40e_status i40e_set_lan_rx_queue_context(struct i40e_hw *hw,
+ u16 queue,
+ struct i40e_hmc_obj_rxq *s);
+
+#endif /* _I40E_LAN_HMC_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
new file mode 100644
index 0000000..601d482
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -0,0 +1,7375 @@
+/*******************************************************************************
+ *
+ * Intel Ethernet Controller XL710 Family Linux Driver
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ ******************************************************************************/
+
+/* Local includes */
+#include "i40e.h"
+
+const char i40e_driver_name[] = "i40e";
+static const char i40e_driver_string[] =
+ "Intel(R) Ethernet Connection XL710 Network Driver";
+
+#define DRV_KERN "-k"
+
+#define DRV_VERSION_MAJOR 0
+#define DRV_VERSION_MINOR 3
+#define DRV_VERSION_BUILD 9
+#define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
+ __stringify(DRV_VERSION_MINOR) "." \
+ __stringify(DRV_VERSION_BUILD) DRV_KERN
+const char i40e_driver_version_str[] = DRV_VERSION;
+static const char i40e_copyright[] = "Copyright (c) 2013 Intel Corporation.";
+
+/* a bit of forward declarations */
+static void i40e_vsi_reinit_locked(struct i40e_vsi *vsi);
+static void i40e_handle_reset_warning(struct i40e_pf *pf);
+static int i40e_add_vsi(struct i40e_vsi *vsi);
+static int i40e_add_veb(struct i40e_veb *veb, struct i40e_vsi *vsi);
+static int i40e_setup_pf_switch(struct i40e_pf *pf);
+static int i40e_setup_misc_vector(struct i40e_pf *pf);
+static void i40e_determine_queue_usage(struct i40e_pf *pf);
+static int i40e_setup_pf_filter_control(struct i40e_pf *pf);
+
+/* i40e_pci_tbl - PCI Device ID Table
+ *
+ * Last entry must be all 0s
+ *
+ * { Vendor ID, Device ID, SubVendor ID, SubDevice ID,
+ * Class, Class Mask, private data (not used) }
+ */
+static DEFINE_PCI_DEVICE_TABLE(i40e_pci_tbl) = {
+ {PCI_VDEVICE(INTEL, I40E_SFP_XL710_DEVICE_ID), 0},
+ {PCI_VDEVICE(INTEL, I40E_SFP_X710_DEVICE_ID), 0},
+ {PCI_VDEVICE(INTEL, I40E_QEMU_DEVICE_ID), 0},
+ {PCI_VDEVICE(INTEL, I40E_KX_A_DEVICE_ID), 0},
+ {PCI_VDEVICE(INTEL, I40E_KX_B_DEVICE_ID), 0},
+ {PCI_VDEVICE(INTEL, I40E_KX_C_DEVICE_ID), 0},
+ {PCI_VDEVICE(INTEL, I40E_KX_D_DEVICE_ID), 0},
+ {PCI_VDEVICE(INTEL, I40E_QSFP_A_DEVICE_ID), 0},
+ {PCI_VDEVICE(INTEL, I40E_QSFP_B_DEVICE_ID), 0},
+ {PCI_VDEVICE(INTEL, I40E_QSFP_C_DEVICE_ID), 0},
+ /* required last entry */
+ {0, }
+};
+MODULE_DEVICE_TABLE(pci, i40e_pci_tbl);
+
+#define I40E_MAX_VF_COUNT 128
+static int debug = -1;
+module_param(debug, int, 0);
+MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");
+
+MODULE_AUTHOR("Intel Corporation, <e1000-devel@lists.sourceforge.net>");
+MODULE_DESCRIPTION("Intel(R) Ethernet Connection XL710 Network Driver");
+MODULE_LICENSE("GPL");
+MODULE_VERSION(DRV_VERSION);
+
+/**
+ * i40e_allocate_dma_mem_d - OS specific memory alloc for shared code
+ * @hw: pointer to the HW structure
+ * @mem: ptr to mem struct to fill out
+ * @size: size of memory requested
+ * @alignment: what to align the allocation to
+ **/
+int i40e_allocate_dma_mem_d(struct i40e_hw *hw, struct i40e_dma_mem *mem,
+ u64 size, u32 alignment)
+{
+ struct i40e_pf *pf = (struct i40e_pf *)hw->back;
+
+ mem->size = ALIGN(size, alignment);
+ mem->va = dma_zalloc_coherent(&pf->pdev->dev, mem->size,
+ &mem->pa, GFP_KERNEL);
+ if (mem->va)
+ return 0;
+
+ return -ENOMEM;
+}
+
+/**
+ * i40e_free_dma_mem_d - OS specific memory free for shared code
+ * @hw: pointer to the HW structure
+ * @mem: ptr to mem struct to free
+ **/
+int i40e_free_dma_mem_d(struct i40e_hw *hw, struct i40e_dma_mem *mem)
+{
+ struct i40e_pf *pf = (struct i40e_pf *)hw->back;
+
+ dma_free_coherent(&pf->pdev->dev, mem->size, mem->va, mem->pa);
+ mem->va = NULL;
+ mem->pa = 0;
+ mem->size = 0;
+
+ return 0;
+}
+
+/**
+ * i40e_allocate_virt_mem_d - OS specific memory alloc for shared code
+ * @hw: pointer to the HW structure
+ * @mem: ptr to mem struct to fill out
+ * @size: size of memory requested
+ **/
+int i40e_allocate_virt_mem_d(struct i40e_hw *hw, struct i40e_virt_mem *mem,
+ u32 size)
+{
+ mem->size = size;
+ mem->va = kzalloc(size, GFP_KERNEL);
+
+ if (mem->va)
+ return 0;
+
+ return -ENOMEM;
+}
+
+/**
+ * i40e_free_virt_mem_d - OS specific memory free for shared code
+ * @hw: pointer to the HW structure
+ * @mem: ptr to mem struct to free
+ **/
+int i40e_free_virt_mem_d(struct i40e_hw *hw, struct i40e_virt_mem *mem)
+{
+ /* it's ok to kfree a NULL pointer */
+ kfree(mem->va);
+ mem->va = NULL;
+ mem->size = 0;
+
+ return 0;
+}
+
+/**
+ * i40e_get_lump - find a lump of free generic resource
+ * @pf: board private structure
+ * @pile: the pile of resource to search
+ * @needed: the number of items needed
+ * @id: an owner id to stick on the items assigned
+ *
+ * Returns the base item index of the lump, or negative for error
+ *
+ * The search_hint trick and lack of advanced fit-finding only work
+ * because we're highly likely to have all the same size lump requests.
+ * Linear search time and any fragmentation should be minimal.
+ **/
+static int i40e_get_lump(struct i40e_pf *pf, struct i40e_lump_tracking *pile,
+ u16 needed, u16 id)
+{
+ int ret = -ENOMEM;
+ int i = 0;
+ int j = 0;
+
+ if (!pile || needed == 0 || id >= I40E_PILE_VALID_BIT) {
+ dev_info(&pf->pdev->dev,
+ "param err: pile=%p needed=%d id=0x%04x\n",
+ pile, needed, id);
+ return -EINVAL;
+ }
+
+ /* start the linear search with an imperfect hint */
+ i = pile->search_hint;
+ while (i < pile->num_entries && ret < 0) {
+ /* skip already allocated entries */
+ if (pile->list[i] & I40E_PILE_VALID_BIT) {
+ i++;
+ continue;
+ }
+
+ /* do we have enough in this lump? */
+ for (j = 0; (j < needed) && ((i+j) < pile->num_entries); j++) {
+ if (pile->list[i+j] & I40E_PILE_VALID_BIT)
+ break;
+ }
+
+ if (j == needed) {
+ /* there was enough, so assign it to the requestor */
+ for (j = 0; j < needed; j++)
+ pile->list[i+j] = id | I40E_PILE_VALID_BIT;
+ ret = i;
+ pile->search_hint = i + j;
+ } else {
+ /* not enough, so skip over it and continue looking */
+ i += j;
+ }
+ }
+
+ return ret;
+}
+
+/**
+ * i40e_put_lump - return a lump of generic resource
+ * @pile: the pile of resource to search
+ * @index: the base item index
+ * @id: the owner id of the items assigned
+ *
+ * Returns the count of items in the lump
+ **/
+static int i40e_put_lump(struct i40e_lump_tracking *pile, u16 index, u16 id)
+{
+ int valid_id = (id | I40E_PILE_VALID_BIT);
+ int count = 0;
+ int i;
+
+ if (!pile || index >= pile->num_entries)
+ return -EINVAL;
+
+ for (i = index;
+ i < pile->num_entries && pile->list[i] == valid_id;
+ i++) {
+ pile->list[i] = 0;
+ count++;
+ }
+
+ if (count && index < pile->search_hint)
+ pile->search_hint = index;
+
+ return count;
+}
+
+/**
+ * i40e_service_event_schedule - Schedule the service task to wake up
+ * @pf: board private structure
+ *
+ * If not already scheduled, this puts the task into the work queue
+ **/
+static void i40e_service_event_schedule(struct i40e_pf *pf)
+{
+ if (!test_bit(__I40E_DOWN, &pf->state) &&
+ !test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state) &&
+ !test_and_set_bit(__I40E_SERVICE_SCHED, &pf->state))
+ schedule_work(&pf->service_task);
+}
+
+/**
+ * i40e_tx_timeout - Respond to a Tx Hang
+ * @netdev: network interface device structure
+ *
+ * If any port has noticed a Tx timeout, it is likely that the whole
+ * device is munged, not just the one netdev port, so go for the full
+ * reset.
+ **/
+static void i40e_tx_timeout(struct net_device *netdev)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+ struct i40e_pf *pf = vsi->back;
+
+ pf->tx_timeout_count++;
+
+ if (time_after(jiffies, (pf->tx_timeout_last_recovery + HZ*20)))
+ pf->tx_timeout_recovery_level = 0;
+ pf->tx_timeout_last_recovery = jiffies;
+ netdev_info(netdev, "tx_timeout recovery level %d\n",
+ pf->tx_timeout_recovery_level);
+
+ switch (pf->tx_timeout_recovery_level) {
+ case 0:
+ /* disable and re-enable queues for the VSI */
+ if (in_interrupt()) {
+ set_bit(__I40E_REINIT_REQUESTED, &pf->state);
+ set_bit(__I40E_REINIT_REQUESTED, &vsi->state);
+ } else {
+ i40e_vsi_reinit_locked(vsi);
+ }
+ break;
+ case 1:
+ set_bit(__I40E_PF_RESET_REQUESTED, &pf->state);
+ break;
+ case 2:
+ set_bit(__I40E_CORE_RESET_REQUESTED, &pf->state);
+ break;
+ case 3:
+ set_bit(__I40E_GLOBAL_RESET_REQUESTED, &pf->state);
+ break;
+ default:
+ netdev_err(netdev, "tx_timeout recovery unsuccessful\n");
+ i40e_down(vsi);
+ break;
+ }
+ i40e_service_event_schedule(pf);
+ pf->tx_timeout_recovery_level++;
+}
+
+/**
+ * i40e_release_rx_desc - Store the new tail and head values
+ * @rx_ring: ring to bump
+ * @val: new head index
+ **/
+static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val)
+{
+ rx_ring->next_to_use = val;
+
+ /* Force memory writes to complete before letting h/w
+ * know there are new descriptors to fetch. (Only
+ * applicable for weak-ordered memory model archs,
+ * such as IA-64).
+ */
+ wmb();
+ writel(val, rx_ring->tail);
+}
+
+/**
+ * i40e_get_vsi_stats_struct - Get System Network Statistics
+ * @vsi: the VSI we care about
+ *
+ * Returns the address of the device statistics structure.
+ * The statistics are actually updated from the service task.
+ **/
+struct rtnl_link_stats64 *i40e_get_vsi_stats_struct(struct i40e_vsi *vsi)
+{
+ return &vsi->net_stats;
+}
+
+/**
+ * i40e_get_netdev_stats_struct - Get statistics for netdev interface
+ * @netdev: network interface device structure
+ *
+ * Returns the address of the device statistics structure.
+ * The statistics are actually updated from the service task.
+ **/
+static struct rtnl_link_stats64 *i40e_get_netdev_stats_struct(
+ struct net_device *netdev,
+ struct rtnl_link_stats64 *storage)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+
+ *storage = *i40e_get_vsi_stats_struct(vsi);
+
+ return storage;
+}
+
+/**
+ * i40e_vsi_reset_stats - Resets all stats of the given vsi
+ * @vsi: the VSI to have its stats reset
+ **/
+void i40e_vsi_reset_stats(struct i40e_vsi *vsi)
+{
+ struct rtnl_link_stats64 *ns;
+ int i;
+
+ if (!vsi)
+ return;
+
+ ns = i40e_get_vsi_stats_struct(vsi);
+ memset(ns, 0, sizeof(*ns));
+ memset(&vsi->net_stats_offsets, 0, sizeof(vsi->net_stats_offsets));
+ memset(&vsi->eth_stats, 0, sizeof(vsi->eth_stats));
+ memset(&vsi->eth_stats_offsets, 0, sizeof(vsi->eth_stats_offsets));
+ if (vsi->rx_rings)
+ for (i = 0; i < vsi->num_queue_pairs; i++) {
+ memset(&vsi->rx_rings[i].rx_stats, 0 ,
+ sizeof(vsi->rx_rings[i].rx_stats));
+ memset(&vsi->tx_rings[i].tx_stats, 0,
+ sizeof(vsi->tx_rings[i].tx_stats));
+ }
+ vsi->stat_offsets_loaded = false;
+}
+
+/**
+ * i40e_pf_reset_stats - Reset all of the stats for the given pf
+ * @pf: the PF to be reset
+ **/
+void i40e_pf_reset_stats(struct i40e_pf *pf)
+{
+ memset(&pf->stats, 0, sizeof(pf->stats));
+ memset(&pf->stats_offsets, 0, sizeof(pf->stats_offsets));
+ pf->stat_offsets_loaded = false;
+}
+
+/**
+ * i40e_stat_update48 - read and update a 48 bit stat from the chip
+ * @hw: ptr to the hardware info
+ * @hireg: the high 32 bit reg to read
+ * @loreg: the low 32 bit reg to read
+ * @offset_loaded: has the initial offset been loaded yet
+ * @offset: ptr to current offset value
+ * @stat: ptr to the stat
+ *
+ * Since the device stats are not reset at PFReset, they likely will not
+ * be zeroed when the driver starts. We'll save the first values read
+ * and use them as offsets to be subtracted from the raw values in order
+ * to report stats that count from zero. In the process, we also manage
+ * the potential roll-over.
+ **/
+static void i40e_stat_update48(struct i40e_hw *hw, u32 hireg, u32 loreg,
+ bool offset_loaded, u64 *offset, u64 *stat)
+{
+ u64 new_data;
+
+ if (hw->device_id == I40E_QEMU_DEVICE_ID) {
+ new_data = rd32(hw, loreg);
+ new_data |= ((u64)(rd32(hw, hireg) & 0xFFFF)) << 32;
+ } else {
+ new_data = rd64(hw, loreg);
+ }
+ if (!offset_loaded)
+ *offset = new_data;
+ if (likely(new_data >= *offset))
+ *stat = new_data - *offset;
+ else
+ *stat = (new_data + ((u64)1 << 48)) - *offset;
+ *stat &= 0xFFFFFFFFFFFFULL;
+}
+
+/**
+ * i40e_stat_update32 - read and update a 32 bit stat from the chip
+ * @hw: ptr to the hardware info
+ * @reg: the hw reg to read
+ * @offset_loaded: has the initial offset been loaded yet
+ * @offset: ptr to current offset value
+ * @stat: ptr to the stat
+ **/
+static void i40e_stat_update32(struct i40e_hw *hw, u32 reg,
+ bool offset_loaded, u64 *offset, u64 *stat)
+{
+ u32 new_data;
+
+ new_data = rd32(hw, reg);
+ if (!offset_loaded)
+ *offset = new_data;
+ if (likely(new_data >= *offset))
+ *stat = (u32)(new_data - *offset);
+ else
+ *stat = (u32)((new_data + ((u64)1 << 32)) - *offset);
+}
+
+/**
+ * i40e_update_eth_stats - Update VSI-specific ethernet statistics counters.
+ * @vsi: the VSI to be updated
+ **/
+void i40e_update_eth_stats(struct i40e_vsi *vsi)
+{
+ int stat_idx = le16_to_cpu(vsi->info.stat_counter_idx);
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+ struct i40e_eth_stats *oes;
+ struct i40e_eth_stats *es; /* device's eth stats */
+
+ es = &vsi->eth_stats;
+ oes = &vsi->eth_stats_offsets;
+
+ /* Gather up the stats that the hw collects */
+ i40e_stat_update32(hw, I40E_GLV_TEPC(stat_idx),
+ vsi->stat_offsets_loaded,
+ &oes->tx_errors, &es->tx_errors);
+ i40e_stat_update32(hw, I40E_GLV_RDPC(stat_idx),
+ vsi->stat_offsets_loaded,
+ &oes->rx_discards, &es->rx_discards);
+
+ i40e_stat_update48(hw, I40E_GLV_GORCH(stat_idx),
+ I40E_GLV_GORCL(stat_idx),
+ vsi->stat_offsets_loaded,
+ &oes->rx_bytes, &es->rx_bytes);
+ i40e_stat_update48(hw, I40E_GLV_UPRCH(stat_idx),
+ I40E_GLV_UPRCL(stat_idx),
+ vsi->stat_offsets_loaded,
+ &oes->rx_unicast, &es->rx_unicast);
+ i40e_stat_update48(hw, I40E_GLV_MPRCH(stat_idx),
+ I40E_GLV_MPRCL(stat_idx),
+ vsi->stat_offsets_loaded,
+ &oes->rx_multicast, &es->rx_multicast);
+ i40e_stat_update48(hw, I40E_GLV_BPRCH(stat_idx),
+ I40E_GLV_BPRCL(stat_idx),
+ vsi->stat_offsets_loaded,
+ &oes->rx_broadcast, &es->rx_broadcast);
+
+ i40e_stat_update48(hw, I40E_GLV_GOTCH(stat_idx),
+ I40E_GLV_GOTCL(stat_idx),
+ vsi->stat_offsets_loaded,
+ &oes->tx_bytes, &es->tx_bytes);
+ i40e_stat_update48(hw, I40E_GLV_UPTCH(stat_idx),
+ I40E_GLV_UPTCL(stat_idx),
+ vsi->stat_offsets_loaded,
+ &oes->tx_unicast, &es->tx_unicast);
+ i40e_stat_update48(hw, I40E_GLV_MPTCH(stat_idx),
+ I40E_GLV_MPTCL(stat_idx),
+ vsi->stat_offsets_loaded,
+ &oes->tx_multicast, &es->tx_multicast);
+ i40e_stat_update48(hw, I40E_GLV_BPTCH(stat_idx),
+ I40E_GLV_BPTCL(stat_idx),
+ vsi->stat_offsets_loaded,
+ &oes->tx_broadcast, &es->tx_broadcast);
+ vsi->stat_offsets_loaded = true;
+}
+
+/**
+ * i40e_update_veb_stats - Update Switch component statistics
+ * @veb: the VEB being updated
+ **/
+static void i40e_update_veb_stats(struct i40e_veb *veb)
+{
+ struct i40e_pf *pf = veb->pf;
+ struct i40e_hw *hw = &pf->hw;
+ struct i40e_eth_stats *oes;
+ struct i40e_eth_stats *es; /* device's eth stats */
+ int idx = 0;
+
+ idx = veb->stats_idx;
+ es = &veb->stats;
+ oes = &veb->stats_offsets;
+
+ /* Gather up the stats that the hw collects */
+ i40e_stat_update32(hw, I40E_GLSW_TDPC(idx),
+ veb->stat_offsets_loaded,
+ &oes->tx_discards, &es->tx_discards);
+ i40e_stat_update32(hw, I40E_GLSW_RUPP(idx),
+ veb->stat_offsets_loaded,
+ &oes->rx_unknown_protocol, &es->rx_unknown_protocol);
+
+ i40e_stat_update48(hw, I40E_GLSW_GORCH(idx), I40E_GLSW_GORCL(idx),
+ veb->stat_offsets_loaded,
+ &oes->rx_bytes, &es->rx_bytes);
+ i40e_stat_update48(hw, I40E_GLSW_UPRCH(idx), I40E_GLSW_UPRCL(idx),
+ veb->stat_offsets_loaded,
+ &oes->rx_unicast, &es->rx_unicast);
+ i40e_stat_update48(hw, I40E_GLSW_MPRCH(idx), I40E_GLSW_MPRCL(idx),
+ veb->stat_offsets_loaded,
+ &oes->rx_multicast, &es->rx_multicast);
+ i40e_stat_update48(hw, I40E_GLSW_BPRCH(idx), I40E_GLSW_BPRCL(idx),
+ veb->stat_offsets_loaded,
+ &oes->rx_broadcast, &es->rx_broadcast);
+
+ i40e_stat_update48(hw, I40E_GLSW_GOTCH(idx), I40E_GLSW_GOTCL(idx),
+ veb->stat_offsets_loaded,
+ &oes->tx_bytes, &es->tx_bytes);
+ i40e_stat_update48(hw, I40E_GLSW_UPTCH(idx), I40E_GLSW_UPTCL(idx),
+ veb->stat_offsets_loaded,
+ &oes->tx_unicast, &es->tx_unicast);
+ i40e_stat_update48(hw, I40E_GLSW_MPTCH(idx), I40E_GLSW_MPTCL(idx),
+ veb->stat_offsets_loaded,
+ &oes->tx_multicast, &es->tx_multicast);
+ i40e_stat_update48(hw, I40E_GLSW_BPTCH(idx), I40E_GLSW_BPTCL(idx),
+ veb->stat_offsets_loaded,
+ &oes->tx_broadcast, &es->tx_broadcast);
+ veb->stat_offsets_loaded = true;
+}
+
+/**
+ * i40e_update_link_xoff_rx - Update XOFF received in link flow control mode
+ * @pf: the corresponding PF
+ *
+ * Update the Rx XOFF counter (PAUSE frames) in link flow control mode
+ **/
+static void i40e_update_link_xoff_rx(struct i40e_pf *pf)
+{
+ struct i40e_hw_port_stats *osd = &pf->stats_offsets;
+ struct i40e_hw_port_stats *nsd = &pf->stats;
+ struct i40e_hw *hw = &pf->hw;
+ u64 xoff = 0;
+ u16 i, v;
+
+ if ((hw->fc.current_mode != I40E_FC_FULL) &&
+ (hw->fc.current_mode != I40E_FC_RX_PAUSE))
+ return;
+
+ xoff = nsd->link_xoff_rx;
+ i40e_stat_update32(hw, I40E_GLPRT_LXOFFRXC(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->link_xoff_rx, &nsd->link_xoff_rx);
+
+ /* No new LFC xoff rx */
+ if (!(nsd->link_xoff_rx - xoff))
+ return;
+
+ /* Clear the __I40E_HANG_CHECK_ARMED bit for all Tx rings */
+ for (v = 0; v < pf->hw.func_caps.num_vsis; v++) {
+ struct i40e_vsi *vsi = pf->vsi[v];
+
+ if (!vsi)
+ continue;
+
+ for (i = 0; i < vsi->num_queue_pairs; i++) {
+ struct i40e_ring *ring = &vsi->tx_rings[i];
+ clear_bit(__I40E_HANG_CHECK_ARMED, &ring->state);
+ }
+ }
+}
+
+/**
+ * i40e_update_prio_xoff_rx - Update XOFF received in PFC mode
+ * @pf: the corresponding PF
+ *
+ * Update the Rx XOFF counter (PAUSE frames) in PFC mode
+ **/
+static void i40e_update_prio_xoff_rx(struct i40e_pf *pf)
+{
+ struct i40e_hw_port_stats *osd = &pf->stats_offsets;
+ struct i40e_hw_port_stats *nsd = &pf->stats;
+ bool xoff[I40E_MAX_TRAFFIC_CLASS] = {false};
+ struct i40e_dcbx_config *dcb_cfg;
+ struct i40e_hw *hw = &pf->hw;
+ u16 i, v;
+ u8 tc;
+
+ dcb_cfg = &hw->local_dcbx_config;
+
+ /* See if DCB enabled with PFC TC */
+ if (!(pf->flags & I40E_FLAG_DCB_ENABLED) ||
+ !(dcb_cfg->pfc.pfcenable)) {
+ i40e_update_link_xoff_rx(pf);
+ return;
+ }
+
+ for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
+ u64 prio_xoff = nsd->priority_xoff_rx[i];
+ i40e_stat_update32(hw, I40E_GLPRT_PXOFFRXC(hw->port, i),
+ pf->stat_offsets_loaded,
+ &osd->priority_xoff_rx[i],
+ &nsd->priority_xoff_rx[i]);
+
+ /* No new PFC xoff rx */
+ if (!(nsd->priority_xoff_rx[i] - prio_xoff))
+ continue;
+ /* Get the TC for given priority */
+ tc = dcb_cfg->etscfg.prioritytable[i];
+ xoff[tc] = true;
+ }
+
+ /* Clear the __I40E_HANG_CHECK_ARMED bit for Tx rings */
+ for (v = 0; v < pf->hw.func_caps.num_vsis; v++) {
+ struct i40e_vsi *vsi = pf->vsi[v];
+
+ if (!vsi)
+ continue;
+
+ for (i = 0; i < vsi->num_queue_pairs; i++) {
+ struct i40e_ring *ring = &vsi->tx_rings[i];
+
+ tc = ring->dcb_tc;
+ if (xoff[tc])
+ clear_bit(__I40E_HANG_CHECK_ARMED,
+ &ring->state);
+ }
+ }
+}
+
+/**
+ * i40e_update_stats - Update the board statistics counters.
+ * @vsi: the VSI to be updated
+ *
+ * There are a few instances where we store the same stat in a
+ * couple of different structs. This is partly because we have
+ * the netdev stats that need to be filled out, which is slightly
+ * different from the "eth_stats" defined by the chip and used in
+ * VF communications. We sort it all out here in a central place.
+ **/
+void i40e_update_stats(struct i40e_vsi *vsi)
+{
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+ struct rtnl_link_stats64 *ons;
+ struct rtnl_link_stats64 *ns; /* netdev stats */
+ struct i40e_eth_stats *oes;
+ struct i40e_eth_stats *es; /* device's eth stats */
+ u32 tx_restart, tx_busy;
+ u32 rx_page, rx_buf;
+ u64 rx_p, rx_b;
+ u64 tx_p, tx_b;
+ int i;
+ u16 q;
+
+ if (test_bit(__I40E_DOWN, &vsi->state) ||
+ test_bit(__I40E_CONFIG_BUSY, &pf->state))
+ return;
+
+ ns = i40e_get_vsi_stats_struct(vsi);
+ ons = &vsi->net_stats_offsets;
+ es = &vsi->eth_stats;
+ oes = &vsi->eth_stats_offsets;
+
+ /* Gather up the netdev and vsi stats that the driver collects
+ * on the fly during packet processing
+ */
+ rx_b = rx_p = 0;
+ tx_b = tx_p = 0;
+ tx_restart = tx_busy = 0;
+ rx_page = 0;
+ rx_buf = 0;
+ for (q = 0; q < vsi->num_queue_pairs; q++) {
+ struct i40e_ring *p;
+
+ p = &vsi->rx_rings[q];
+ rx_b += p->rx_stats.bytes;
+ rx_p += p->rx_stats.packets;
+ rx_buf += p->rx_stats.alloc_rx_buff_failed;
+ rx_page += p->rx_stats.alloc_rx_page_failed;
+
+ p = &vsi->tx_rings[q];
+ tx_b += p->tx_stats.bytes;
+ tx_p += p->tx_stats.packets;
+ tx_restart += p->tx_stats.restart_queue;
+ tx_busy += p->tx_stats.tx_busy;
+ }
+ vsi->tx_restart = tx_restart;
+ vsi->tx_busy = tx_busy;
+ vsi->rx_page_failed = rx_page;
+ vsi->rx_buf_failed = rx_buf;
+
+ ns->rx_packets = rx_p;
+ ns->rx_bytes = rx_b;
+ ns->tx_packets = tx_p;
+ ns->tx_bytes = tx_b;
+
+ i40e_update_eth_stats(vsi);
+ /* update netdev stats from eth stats */
+ ons->rx_errors = oes->rx_errors;
+ ns->rx_errors = es->rx_errors;
+ ons->tx_errors = oes->tx_errors;
+ ns->tx_errors = es->tx_errors;
+ ons->multicast = oes->rx_multicast;
+ ns->multicast = es->rx_multicast;
+ ons->tx_dropped = oes->tx_discards;
+ ns->tx_dropped = es->tx_discards;
+
+ /* Get the port data only if this is the main PF VSI */
+ if (vsi == pf->vsi[pf->lan_vsi]) {
+ struct i40e_hw_port_stats *nsd = &pf->stats;
+ struct i40e_hw_port_stats *osd = &pf->stats_offsets;
+
+ i40e_stat_update48(hw, I40E_GLPRT_GORCH(hw->port),
+ I40E_GLPRT_GORCL(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->eth.rx_bytes, &nsd->eth.rx_bytes);
+ i40e_stat_update48(hw, I40E_GLPRT_GOTCH(hw->port),
+ I40E_GLPRT_GOTCL(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->eth.tx_bytes, &nsd->eth.tx_bytes);
+ i40e_stat_update32(hw, I40E_GLPRT_RDPC(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->eth.rx_discards,
+ &nsd->eth.rx_discards);
+ i40e_stat_update32(hw, I40E_GLPRT_TDPC(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->eth.tx_discards,
+ &nsd->eth.tx_discards);
+ i40e_stat_update48(hw, I40E_GLPRT_MPRCH(hw->port),
+ I40E_GLPRT_MPRCL(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->eth.rx_multicast,
+ &nsd->eth.rx_multicast);
+
+ i40e_stat_update32(hw, I40E_GLPRT_TDOLD(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->tx_dropped_link_down,
+ &nsd->tx_dropped_link_down);
+
+ i40e_stat_update32(hw, I40E_GLPRT_CRCERRS(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->crc_errors, &nsd->crc_errors);
+ ns->rx_crc_errors = nsd->crc_errors;
+
+ i40e_stat_update32(hw, I40E_GLPRT_ILLERRC(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->illegal_bytes, &nsd->illegal_bytes);
+ ns->rx_errors = nsd->crc_errors
+ + nsd->illegal_bytes;
+
+ i40e_stat_update32(hw, I40E_GLPRT_MLFC(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->mac_local_faults,
+ &nsd->mac_local_faults);
+ i40e_stat_update32(hw, I40E_GLPRT_MRFC(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->mac_remote_faults,
+ &nsd->mac_remote_faults);
+
+ i40e_stat_update32(hw, I40E_GLPRT_RLEC(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->rx_length_errors,
+ &nsd->rx_length_errors);
+ ns->rx_length_errors = nsd->rx_length_errors;
+
+ i40e_stat_update32(hw, I40E_GLPRT_LXONRXC(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->link_xon_rx, &nsd->link_xon_rx);
+ i40e_stat_update32(hw, I40E_GLPRT_LXONTXC(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->link_xon_tx, &nsd->link_xon_tx);
+ i40e_update_prio_xoff_rx(pf); /* handles I40E_GLPRT_LXOFFRXC */
+ i40e_stat_update32(hw, I40E_GLPRT_LXOFFTXC(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->link_xoff_tx, &nsd->link_xoff_tx);
+
+ for (i = 0; i < 8; i++) {
+ i40e_stat_update32(hw, I40E_GLPRT_PXONRXC(hw->port, i),
+ pf->stat_offsets_loaded,
+ &osd->priority_xon_rx[i],
+ &nsd->priority_xon_rx[i]);
+ i40e_stat_update32(hw, I40E_GLPRT_PXONTXC(hw->port, i),
+ pf->stat_offsets_loaded,
+ &osd->priority_xon_tx[i],
+ &nsd->priority_xon_tx[i]);
+ i40e_stat_update32(hw, I40E_GLPRT_PXOFFTXC(hw->port, i),
+ pf->stat_offsets_loaded,
+ &osd->priority_xoff_tx[i],
+ &nsd->priority_xoff_tx[i]);
+ i40e_stat_update32(hw,
+ I40E_GLPRT_RXON2OFFCNT(hw->port, i),
+ pf->stat_offsets_loaded,
+ &osd->priority_xon_2_xoff[i],
+ &nsd->priority_xon_2_xoff[i]);
+ }
+
+ i40e_stat_update48(hw, I40E_GLPRT_PRC64H(hw->port),
+ I40E_GLPRT_PRC64L(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->rx_size_64, &nsd->rx_size_64);
+ i40e_stat_update48(hw, I40E_GLPRT_PRC127H(hw->port),
+ I40E_GLPRT_PRC127L(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->rx_size_127, &nsd->rx_size_127);
+ i40e_stat_update48(hw, I40E_GLPRT_PRC255H(hw->port),
+ I40E_GLPRT_PRC255L(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->rx_size_255, &nsd->rx_size_255);
+ i40e_stat_update48(hw, I40E_GLPRT_PRC511H(hw->port),
+ I40E_GLPRT_PRC511L(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->rx_size_511, &nsd->rx_size_511);
+ i40e_stat_update48(hw, I40E_GLPRT_PRC1023H(hw->port),
+ I40E_GLPRT_PRC1023L(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->rx_size_1023, &nsd->rx_size_1023);
+ i40e_stat_update48(hw, I40E_GLPRT_PRC1522H(hw->port),
+ I40E_GLPRT_PRC1522L(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->rx_size_1522, &nsd->rx_size_1522);
+ i40e_stat_update48(hw, I40E_GLPRT_PRC9522H(hw->port),
+ I40E_GLPRT_PRC9522L(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->rx_size_big, &nsd->rx_size_big);
+
+ i40e_stat_update48(hw, I40E_GLPRT_PTC64H(hw->port),
+ I40E_GLPRT_PTC64L(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->tx_size_64, &nsd->tx_size_64);
+ i40e_stat_update48(hw, I40E_GLPRT_PTC127H(hw->port),
+ I40E_GLPRT_PTC127L(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->tx_size_127, &nsd->tx_size_127);
+ i40e_stat_update48(hw, I40E_GLPRT_PTC255H(hw->port),
+ I40E_GLPRT_PTC255L(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->tx_size_255, &nsd->tx_size_255);
+ i40e_stat_update48(hw, I40E_GLPRT_PTC511H(hw->port),
+ I40E_GLPRT_PTC511L(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->tx_size_511, &nsd->tx_size_511);
+ i40e_stat_update48(hw, I40E_GLPRT_PTC1023H(hw->port),
+ I40E_GLPRT_PTC1023L(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->tx_size_1023, &nsd->tx_size_1023);
+ i40e_stat_update48(hw, I40E_GLPRT_PTC1522H(hw->port),
+ I40E_GLPRT_PTC1522L(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->tx_size_1522, &nsd->tx_size_1522);
+ i40e_stat_update48(hw, I40E_GLPRT_PTC9522H(hw->port),
+ I40E_GLPRT_PTC9522L(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->tx_size_big, &nsd->tx_size_big);
+
+ i40e_stat_update32(hw, I40E_GLPRT_RUC(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->rx_undersize, &nsd->rx_undersize);
+ i40e_stat_update32(hw, I40E_GLPRT_RFC(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->rx_fragments, &nsd->rx_fragments);
+ i40e_stat_update32(hw, I40E_GLPRT_ROC(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->rx_oversize, &nsd->rx_oversize);
+ i40e_stat_update32(hw, I40E_GLPRT_RJC(hw->port),
+ pf->stat_offsets_loaded,
+ &osd->rx_jabber, &nsd->rx_jabber);
+ }
+
+ pf->stat_offsets_loaded = true;
+}
+
+/**
+ * i40e_find_filter - Search VSI filter list for specific mac/vlan filter
+ * @vsi: the VSI to be searched
+ * @macaddr: the MAC address
+ * @vlan: the vlan
+ * @is_vf: make sure its a vf filter, else doesn't matter
+ * @is_netdev: make sure its a netdev filter, else doesn't matter
+ *
+ * Returns ptr to the filter object or NULL
+ **/
+static struct i40e_mac_filter *i40e_find_filter(struct i40e_vsi *vsi,
+ u8 *macaddr, s16 vlan,
+ bool is_vf, bool is_netdev)
+{
+ struct i40e_mac_filter *f;
+
+ if (!vsi || !macaddr)
+ return NULL;
+
+ list_for_each_entry(f, &vsi->mac_filter_list, list) {
+ if ((ether_addr_equal(macaddr, f->macaddr)) &&
+ (vlan == f->vlan) &&
+ (!is_vf || f->is_vf) &&
+ (!is_netdev || f->is_netdev))
+ return f;
+ }
+ return NULL;
+}
+
+/**
+ * i40e_find_mac - Find a mac addr in the macvlan filters list
+ * @vsi: the VSI to be searched
+ * @macaddr: the MAC address we are searching for
+ * @is_vf: make sure its a vf filter, else doesn't matter
+ * @is_netdev: make sure its a netdev filter, else doesn't matter
+ *
+ * Returns the first filter with the provided MAC address or NULL if
+ * MAC address was not found
+ **/
+struct i40e_mac_filter *i40e_find_mac(struct i40e_vsi *vsi, u8 *macaddr,
+ bool is_vf, bool is_netdev)
+{
+ struct i40e_mac_filter *f;
+
+ if (!vsi || !macaddr)
+ return NULL;
+
+ list_for_each_entry(f, &vsi->mac_filter_list, list) {
+ if ((ether_addr_equal(macaddr, f->macaddr)) &&
+ (!is_vf || f->is_vf) &&
+ (!is_netdev || f->is_netdev))
+ return f;
+ }
+ return NULL;
+}
+
+/**
+ * i40e_is_vsi_in_vlan - Check if VSI is in vlan mode
+ * @vsi: the VSI to be searched
+ *
+ * Returns true if VSI is in vlan mode or false otherwise
+ **/
+bool i40e_is_vsi_in_vlan(struct i40e_vsi *vsi)
+{
+ struct i40e_mac_filter *f;
+
+ /* Only -1 for all the filters denotes not in vlan mode
+ * so we have to go through all the list in order to make sure
+ */
+ list_for_each_entry(f, &vsi->mac_filter_list, list) {
+ if (f->vlan >= 0)
+ return true;
+ }
+
+ return false;
+}
+
+/**
+ * i40e_put_mac_in_vlan - Make macvlan filters from macaddrs and vlans
+ * @vsi: the VSI to be searched
+ * @macaddr: the mac address to be filtered
+ * @is_vf: true if it is a vf
+ * @is_netdev: true if it is a netdev
+ *
+ * Goes through all the macvlan filters and adds a
+ * macvlan filter for each unique vlan that already exists
+ *
+ * Returns first filter found on success, else NULL
+ **/
+struct i40e_mac_filter *i40e_put_mac_in_vlan(struct i40e_vsi *vsi, u8 *macaddr,
+ bool is_vf, bool is_netdev)
+{
+ struct i40e_mac_filter *f;
+
+ list_for_each_entry(f, &vsi->mac_filter_list, list) {
+ if (!i40e_find_filter(vsi, macaddr, f->vlan,
+ is_vf, is_netdev)) {
+ if (!i40e_add_filter(vsi, macaddr, f->vlan,
+ is_vf, is_netdev))
+ return NULL;
+ }
+ }
+
+ return list_first_entry_or_null(&vsi->mac_filter_list,
+ struct i40e_mac_filter, list);
+}
+
+/**
+ * i40e_add_filter - Add a mac/vlan filter to the VSI
+ * @vsi: the VSI to be searched
+ * @macaddr: the MAC address
+ * @vlan: the vlan
+ * @is_vf: make sure its a vf filter, else doesn't matter
+ * @is_netdev: make sure its a netdev filter, else doesn't matter
+ *
+ * Returns ptr to the filter object or NULL when no memory available.
+ **/
+struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi,
+ u8 *macaddr, s16 vlan,
+ bool is_vf, bool is_netdev)
+{
+ struct i40e_mac_filter *f;
+
+ if (!vsi || !macaddr)
+ return NULL;
+
+ f = i40e_find_filter(vsi, macaddr, vlan, is_vf, is_netdev);
+ if (!f) {
+ f = kzalloc(sizeof(*f), GFP_ATOMIC);
+ if (!f)
+ goto add_filter_out;
+
+ memcpy(f->macaddr, macaddr, ETH_ALEN);
+ f->vlan = vlan;
+ f->changed = true;
+
+ INIT_LIST_HEAD(&f->list);
+ list_add(&f->list, &vsi->mac_filter_list);
+ }
+
+ /* increment counter and add a new flag if needed */
+ if (is_vf) {
+ if (!f->is_vf) {
+ f->is_vf = true;
+ f->counter++;
+ }
+ } else if (is_netdev) {
+ if (!f->is_netdev) {
+ f->is_netdev = true;
+ f->counter++;
+ }
+ } else {
+ f->counter++;
+ }
+
+ /* changed tells sync_filters_subtask to
+ * push the filter down to the firmware
+ */
+ if (f->changed) {
+ vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED;
+ vsi->back->flags |= I40E_FLAG_FILTER_SYNC;
+ }
+
+add_filter_out:
+ return f;
+}
+
+/**
+ * i40e_del_filter - Remove a mac/vlan filter from the VSI
+ * @vsi: the VSI to be searched
+ * @macaddr: the MAC address
+ * @vlan: the vlan
+ * @is_vf: make sure it's a vf filter, else doesn't matter
+ * @is_netdev: make sure it's a netdev filter, else doesn't matter
+ **/
+void i40e_del_filter(struct i40e_vsi *vsi,
+ u8 *macaddr, s16 vlan,
+ bool is_vf, bool is_netdev)
+{
+ struct i40e_mac_filter *f;
+
+ if (!vsi || !macaddr)
+ return;
+
+ f = i40e_find_filter(vsi, macaddr, vlan, is_vf, is_netdev);
+ if (!f || f->counter == 0)
+ return;
+
+ if (is_vf) {
+ if (f->is_vf) {
+ f->is_vf = false;
+ f->counter--;
+ }
+ } else if (is_netdev) {
+ if (f->is_netdev) {
+ f->is_netdev = false;
+ f->counter--;
+ }
+ } else {
+ /* make sure we don't remove a filter in use by vf or netdev */
+ int min_f = 0;
+ min_f += (f->is_vf ? 1 : 0);
+ min_f += (f->is_netdev ? 1 : 0);
+
+ if (f->counter > min_f)
+ f->counter--;
+ }
+
+ /* counter == 0 tells sync_filters_subtask to
+ * remove the filter from the firmware's list
+ */
+ if (f->counter == 0) {
+ f->changed = true;
+ vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED;
+ vsi->back->flags |= I40E_FLAG_FILTER_SYNC;
+ }
+}
+
+/**
+ * i40e_set_mac - NDO callback to set mac address
+ * @netdev: network interface device structure
+ * @p: pointer to an address structure
+ *
+ * Returns 0 on success, negative on failure
+ **/
+static int i40e_set_mac(struct net_device *netdev, void *p)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+ struct sockaddr *addr = p;
+ struct i40e_mac_filter *f;
+
+ if (!is_valid_ether_addr(addr->sa_data))
+ return -EADDRNOTAVAIL;
+
+ netdev_info(netdev, "set mac address=%pM\n", addr->sa_data);
+
+ if (ether_addr_equal(netdev->dev_addr, addr->sa_data))
+ return 0;
+
+ if (vsi->type == I40E_VSI_MAIN) {
+ i40e_status ret;
+ ret = i40e_aq_mac_address_write(&vsi->back->hw,
+ I40E_AQC_WRITE_TYPE_LAA_ONLY,
+ addr->sa_data, NULL);
+ if (ret) {
+ netdev_info(netdev,
+ "Addr change for Main VSI failed: %d\n",
+ ret);
+ return -EADDRNOTAVAIL;
+ }
+
+ memcpy(vsi->back->hw.mac.addr, addr->sa_data, netdev->addr_len);
+ }
+
+ /* In order to be sure to not drop any packets, add the new address
+ * then delete the old one.
+ */
+ f = i40e_add_filter(vsi, addr->sa_data, I40E_VLAN_ANY, false, false);
+ if (!f)
+ return -ENOMEM;
+
+ i40e_sync_vsi_filters(vsi);
+ i40e_del_filter(vsi, netdev->dev_addr, I40E_VLAN_ANY, false, false);
+ i40e_sync_vsi_filters(vsi);
+
+ memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
+
+ return 0;
+}
+
+/**
+ * i40e_vsi_setup_queue_map - Setup a VSI queue map based on enabled_tc
+ * @vsi: the VSI being setup
+ * @ctxt: VSI context structure
+ * @enabled_tc: Enabled TCs bitmap
+ * @is_add: True if called before Add VSI
+ *
+ * Setup VSI queue mapping for enabled traffic classes.
+ **/
+static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
+ struct i40e_vsi_context *ctxt,
+ u8 enabled_tc,
+ bool is_add)
+{
+ struct i40e_pf *pf = vsi->back;
+ u16 sections = 0;
+ u8 netdev_tc = 0;
+ u16 numtc = 0;
+ u16 qcount;
+ u8 offset;
+ u16 qmap;
+ int i;
+
+ sections = I40E_AQ_VSI_PROP_QUEUE_MAP_VALID;
+ offset = 0;
+
+ if (enabled_tc && (vsi->back->flags & I40E_FLAG_DCB_ENABLED)) {
+ /* Find numtc from enabled TC bitmap */
+ for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
+ if (enabled_tc & (1 << i)) /* TC is enabled */
+ numtc++;
+ }
+ if (!numtc) {
+ dev_warn(&pf->pdev->dev, "DCB is enabled but no TC enabled, forcing TC0\n");
+ numtc = 1;
+ }
+ } else {
+ /* At least TC0 is enabled in case of non-DCB case */
+ numtc = 1;
+ }
+
+ vsi->tc_config.numtc = numtc;
+ vsi->tc_config.enabled_tc = enabled_tc ? enabled_tc : 1;
+
+ /* Setup queue offset/count for all TCs for given VSI */
+ for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
+ /* See if the given TC is enabled for the given VSI */
+ if (vsi->tc_config.enabled_tc & (1 << i)) { /* TC is enabled */
+ int pow, num_qps;
+
+ vsi->tc_config.tc_info[i].qoffset = offset;
+ switch (vsi->type) {
+ case I40E_VSI_MAIN:
+ if (i == 0)
+ qcount = pf->rss_size;
+ else
+ qcount = pf->num_tc_qps;
+ vsi->tc_config.tc_info[i].qcount = qcount;
+ break;
+ case I40E_VSI_FDIR:
+ case I40E_VSI_SRIOV:
+ case I40E_VSI_VMDQ2:
+ default:
+ qcount = vsi->alloc_queue_pairs;
+ vsi->tc_config.tc_info[i].qcount = qcount;
+ WARN_ON(i != 0);
+ break;
+ }
+
+ /* find the power-of-2 of the number of queue pairs */
+ num_qps = vsi->tc_config.tc_info[i].qcount;
+ pow = 0;
+ while (num_qps &&
+ ((1 << pow) < vsi->tc_config.tc_info[i].qcount)) {
+ pow++;
+ num_qps >>= 1;
+ }
+
+ vsi->tc_config.tc_info[i].netdev_tc = netdev_tc++;
+ qmap =
+ (offset << I40E_AQ_VSI_TC_QUE_OFFSET_SHIFT) |
+ (pow << I40E_AQ_VSI_TC_QUE_NUMBER_SHIFT);
+
+ offset += vsi->tc_config.tc_info[i].qcount;
+ } else {
+ /* TC is not enabled so set the offset to
+ * default queue and allocate one queue
+ * for the given TC.
+ */
+ vsi->tc_config.tc_info[i].qoffset = 0;
+ vsi->tc_config.tc_info[i].qcount = 1;
+ vsi->tc_config.tc_info[i].netdev_tc = 0;
+
+ qmap = 0;
+ }
+ ctxt->info.tc_mapping[i] = cpu_to_le16(qmap);
+ }
+
+ /* Set actual Tx/Rx queue pairs */
+ vsi->num_queue_pairs = offset;
+
+ /* Scheduler section valid can only be set for ADD VSI */
+ if (is_add) {
+ sections |= I40E_AQ_VSI_PROP_SCHED_VALID;
+
+ ctxt->info.up_enable_bits = enabled_tc;
+ }
+ if (vsi->type == I40E_VSI_SRIOV) {
+ ctxt->info.mapping_flags |=
+ cpu_to_le16(I40E_AQ_VSI_QUE_MAP_NONCONTIG);
+ for (i = 0; i < vsi->num_queue_pairs; i++)
+ ctxt->info.queue_mapping[i] =
+ cpu_to_le16(vsi->base_queue + i);
+ } else {
+ ctxt->info.mapping_flags |=
+ cpu_to_le16(I40E_AQ_VSI_QUE_MAP_CONTIG);
+ ctxt->info.queue_mapping[0] = cpu_to_le16(vsi->base_queue);
+ }
+ ctxt->info.valid_sections |= cpu_to_le16(sections);
+}
+
+/**
+ * i40e_set_rx_mode - NDO callback to set the netdev filters
+ * @netdev: network interface device structure
+ **/
+static void i40e_set_rx_mode(struct net_device *netdev)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_mac_filter *f, *ftmp;
+ struct i40e_vsi *vsi = np->vsi;
+ struct netdev_hw_addr *uca;
+ struct netdev_hw_addr *mca;
+ struct netdev_hw_addr *ha;
+
+ /* add addr if not already in the filter list */
+ netdev_for_each_uc_addr(uca, netdev) {
+ if (!i40e_find_mac(vsi, uca->addr, false, true)) {
+ if (i40e_is_vsi_in_vlan(vsi))
+ i40e_put_mac_in_vlan(vsi, uca->addr,
+ false, true);
+ else
+ i40e_add_filter(vsi, uca->addr, I40E_VLAN_ANY,
+ false, true);
+ }
+ }
+
+ netdev_for_each_mc_addr(mca, netdev) {
+ if (!i40e_find_mac(vsi, mca->addr, false, true)) {
+ if (i40e_is_vsi_in_vlan(vsi))
+ i40e_put_mac_in_vlan(vsi, mca->addr,
+ false, true);
+ else
+ i40e_add_filter(vsi, mca->addr, I40E_VLAN_ANY,
+ false, true);
+ }
+ }
+
+ /* remove filter if not in netdev list */
+ list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) {
+ bool found = false;
+
+ if (!f->is_netdev)
+ continue;
+
+ if (is_multicast_ether_addr(f->macaddr)) {
+ netdev_for_each_mc_addr(mca, netdev) {
+ if (ether_addr_equal(mca->addr, f->macaddr)) {
+ found = true;
+ break;
+ }
+ }
+ } else {
+ netdev_for_each_uc_addr(uca, netdev) {
+ if (ether_addr_equal(uca->addr, f->macaddr)) {
+ found = true;
+ break;
+ }
+ }
+
+ for_each_dev_addr(netdev, ha) {
+ if (ether_addr_equal(ha->addr, f->macaddr)) {
+ found = true;
+ break;
+ }
+ }
+ }
+ if (!found)
+ i40e_del_filter(
+ vsi, f->macaddr, I40E_VLAN_ANY, false, true);
+ }
+
+ /* check for other flag changes */
+ if (vsi->current_netdev_flags != vsi->netdev->flags) {
+ vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED;
+ vsi->back->flags |= I40E_FLAG_FILTER_SYNC;
+ }
+}
+
+/**
+ * i40e_sync_vsi_filters - Update the VSI filter list to the HW
+ * @vsi: ptr to the VSI
+ *
+ * Push any outstanding VSI filter changes through the AdminQ.
+ *
+ * Returns 0 or error value
+ **/
+int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
+{
+ struct i40e_mac_filter *f, *ftmp;
+ bool promisc_forced_on = false;
+ bool add_happened = false;
+ int filter_list_len = 0;
+ u32 changed_flags = 0;
+ i40e_status ret = 0;
+ struct i40e_pf *pf;
+ int num_add = 0;
+ int num_del = 0;
+ u16 cmd_flags;
+
+ /* empty array typed pointers, kcalloc later */
+ struct i40e_aqc_add_macvlan_element_data *add_list;
+ struct i40e_aqc_remove_macvlan_element_data *del_list;
+
+ while (test_and_set_bit(__I40E_CONFIG_BUSY, &vsi->state))
+ usleep_range(1000, 2000);
+ pf = vsi->back;
+
+ if (vsi->netdev) {
+ changed_flags = vsi->current_netdev_flags ^ vsi->netdev->flags;
+ vsi->current_netdev_flags = vsi->netdev->flags;
+ }
+
+ if (vsi->flags & I40E_VSI_FLAG_FILTER_CHANGED) {
+ vsi->flags &= ~I40E_VSI_FLAG_FILTER_CHANGED;
+
+ filter_list_len = pf->hw.aq.asq_buf_size /
+ sizeof(struct i40e_aqc_remove_macvlan_element_data);
+ del_list = kcalloc(filter_list_len,
+ sizeof(struct i40e_aqc_remove_macvlan_element_data),
+ GFP_KERNEL);
+ if (!del_list)
+ return -ENOMEM;
+
+ list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) {
+ if (!f->changed)
+ continue;
+
+ if (f->counter != 0)
+ continue;
+ f->changed = false;
+ cmd_flags = 0;
+
+ /* add to delete list */
+ memcpy(del_list[num_del].mac_addr,
+ f->macaddr, ETH_ALEN);
+ del_list[num_del].vlan_tag =
+ cpu_to_le16((u16)(f->vlan ==
+ I40E_VLAN_ANY ? 0 : f->vlan));
+
+ /* vlan0 as wild card to allow packets from all vlans */
+ if (f->vlan == I40E_VLAN_ANY ||
+ (vsi->netdev && !(vsi->netdev->features &
+ NETIF_F_HW_VLAN_CTAG_FILTER)))
+ cmd_flags |= I40E_AQC_MACVLAN_DEL_IGNORE_VLAN;
+ cmd_flags |= I40E_AQC_MACVLAN_DEL_PERFECT_MATCH;
+ del_list[num_del].flags = cmd_flags;
+ num_del++;
+
+ /* unlink from filter list */
+ list_del(&f->list);
+ kfree(f);
+
+ /* flush a full buffer */
+ if (num_del == filter_list_len) {
+ ret = i40e_aq_remove_macvlan(&pf->hw,
+ vsi->seid, del_list, num_del,
+ NULL);
+ num_del = 0;
+ memset(del_list, 0, sizeof(*del_list));
+
+ if (ret)
+ dev_info(&pf->pdev->dev,
+ "ignoring delete macvlan error, err %d, aq_err %d while flushing a full buffer\n",
+ ret,
+ pf->hw.aq.asq_last_status);
+ }
+ }
+ if (num_del) {
+ ret = i40e_aq_remove_macvlan(&pf->hw, vsi->seid,
+ del_list, num_del, NULL);
+ num_del = 0;
+
+ if (ret)
+ dev_info(&pf->pdev->dev,
+ "ignoring delete macvlan error, err %d, aq_err %d\n",
+ ret, pf->hw.aq.asq_last_status);
+ }
+
+ kfree(del_list);
+ del_list = NULL;
+
+ /* do all the adds now */
+ filter_list_len = pf->hw.aq.asq_buf_size /
+ sizeof(struct i40e_aqc_add_macvlan_element_data),
+ add_list = kcalloc(filter_list_len,
+ sizeof(struct i40e_aqc_add_macvlan_element_data),
+ GFP_KERNEL);
+ if (!add_list)
+ return -ENOMEM;
+
+ list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) {
+ if (!f->changed)
+ continue;
+
+ if (f->counter == 0)
+ continue;
+ f->changed = false;
+ add_happened = true;
+ cmd_flags = 0;
+
+ /* add to add array */
+ memcpy(add_list[num_add].mac_addr,
+ f->macaddr, ETH_ALEN);
+ add_list[num_add].vlan_tag =
+ cpu_to_le16(
+ (u16)(f->vlan == I40E_VLAN_ANY ? 0 : f->vlan));
+ add_list[num_add].queue_number = 0;
+
+ cmd_flags |= I40E_AQC_MACVLAN_ADD_PERFECT_MATCH;
+
+ /* vlan0 as wild card to allow packets from all vlans */
+ if (f->vlan == I40E_VLAN_ANY || (vsi->netdev &&
+ !(vsi->netdev->features &
+ NETIF_F_HW_VLAN_CTAG_FILTER)))
+ cmd_flags |= I40E_AQC_MACVLAN_ADD_IGNORE_VLAN;
+ add_list[num_add].flags = cpu_to_le16(cmd_flags);
+ num_add++;
+
+ /* flush a full buffer */
+ if (num_add == filter_list_len) {
+ ret = i40e_aq_add_macvlan(&pf->hw,
+ vsi->seid,
+ add_list,
+ num_add,
+ NULL);
+ num_add = 0;
+
+ if (ret)
+ break;
+ memset(add_list, 0, sizeof(*add_list));
+ }
+ }
+ if (num_add) {
+ ret = i40e_aq_add_macvlan(&pf->hw, vsi->seid,
+ add_list, num_add, NULL);
+ num_add = 0;
+ }
+ kfree(add_list);
+ add_list = NULL;
+
+ if (add_happened && (!ret)) {
+ /* do nothing */;
+ } else if (add_happened && (ret)) {
+ dev_info(&pf->pdev->dev,
+ "add filter failed, err %d, aq_err %d\n",
+ ret, pf->hw.aq.asq_last_status);
+ if ((pf->hw.aq.asq_last_status == I40E_AQ_RC_ENOSPC) &&
+ !test_bit(__I40E_FILTER_OVERFLOW_PROMISC,
+ &vsi->state)) {
+ promisc_forced_on = true;
+ set_bit(__I40E_FILTER_OVERFLOW_PROMISC,
+ &vsi->state);
+ dev_info(&pf->pdev->dev, "promiscuous mode forced on\n");
+ }
+ }
+ }
+
+ /* check for changes in promiscuous modes */
+ if (changed_flags & IFF_ALLMULTI) {
+ bool cur_multipromisc;
+ cur_multipromisc = !!(vsi->current_netdev_flags & IFF_ALLMULTI);
+ ret = i40e_aq_set_vsi_multicast_promiscuous(&vsi->back->hw,
+ vsi->seid,
+ cur_multipromisc,
+ NULL);
+ if (ret)
+ dev_info(&pf->pdev->dev,
+ "set multi promisc failed, err %d, aq_err %d\n",
+ ret, pf->hw.aq.asq_last_status);
+ }
+ if ((changed_flags & IFF_PROMISC) || promisc_forced_on) {
+ bool cur_promisc;
+ cur_promisc = (!!(vsi->current_netdev_flags & IFF_PROMISC) ||
+ test_bit(__I40E_FILTER_OVERFLOW_PROMISC,
+ &vsi->state));
+ ret = i40e_aq_set_vsi_unicast_promiscuous(&vsi->back->hw,
+ vsi->seid,
+ cur_promisc,
+ NULL);
+ if (ret)
+ dev_info(&pf->pdev->dev,
+ "set uni promisc failed, err %d, aq_err %d\n",
+ ret, pf->hw.aq.asq_last_status);
+ }
+
+ clear_bit(__I40E_CONFIG_BUSY, &vsi->state);
+ return 0;
+}
+
+/**
+ * i40e_sync_filters_subtask - Sync the VSI filter list with HW
+ * @pf: board private structure
+ **/
+static void i40e_sync_filters_subtask(struct i40e_pf *pf)
+{
+ int v;
+
+ if (!pf || !(pf->flags & I40E_FLAG_FILTER_SYNC))
+ return;
+ pf->flags &= ~I40E_FLAG_FILTER_SYNC;
+
+ for (v = 0; v < pf->hw.func_caps.num_vsis; v++) {
+ if (pf->vsi[v] &&
+ (pf->vsi[v]->flags & I40E_VSI_FLAG_FILTER_CHANGED))
+ i40e_sync_vsi_filters(pf->vsi[v]);
+ }
+}
+
+/**
+ * i40e_change_mtu - NDO callback to change the Maximum Transfer Unit
+ * @netdev: network interface device structure
+ * @new_mtu: new value for maximum frame size
+ *
+ * Returns 0 on success, negative on failure
+ **/
+static int i40e_change_mtu(struct net_device *netdev, int new_mtu)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN;
+ struct i40e_vsi *vsi = np->vsi;
+
+ /* MTU < 68 is an error and causes problems on some kernels */
+ if ((new_mtu < 68) || (max_frame > I40E_MAX_RXBUFFER))
+ return -EINVAL;
+
+ netdev_info(netdev, "changing MTU from %d to %d\n",
+ netdev->mtu, new_mtu);
+ netdev->mtu = new_mtu;
+ if (netif_running(netdev))
+ i40e_vsi_reinit_locked(vsi);
+
+ return 0;
+}
+
+/**
+ * i40e_vlan_stripping_enable - Turn on vlan stripping for the VSI
+ * @vsi: the vsi being adjusted
+ **/
+void i40e_vlan_stripping_enable(struct i40e_vsi *vsi)
+{
+ struct i40e_vsi_context ctxt;
+ i40e_status ret;
+
+ if ((vsi->info.valid_sections &
+ cpu_to_le16(I40E_AQ_VSI_PROP_VLAN_VALID)) &&
+ ((vsi->info.port_vlan_flags & I40E_AQ_VSI_PVLAN_MODE_MASK) == 0))
+ return; /* already enabled */
+
+ vsi->info.valid_sections = cpu_to_le16(I40E_AQ_VSI_PROP_VLAN_VALID);
+ vsi->info.port_vlan_flags = I40E_AQ_VSI_PVLAN_MODE_ALL |
+ I40E_AQ_VSI_PVLAN_EMOD_STR_BOTH;
+
+ ctxt.seid = vsi->seid;
+ memcpy(&ctxt.info, &vsi->info, sizeof(vsi->info));
+ ret = i40e_aq_update_vsi_params(&vsi->back->hw, &ctxt, NULL);
+ if (ret) {
+ dev_info(&vsi->back->pdev->dev,
+ "%s: update vsi failed, aq_err=%d\n",
+ __func__, vsi->back->hw.aq.asq_last_status);
+ }
+}
+
+/**
+ * i40e_vlan_stripping_disable - Turn off vlan stripping for the VSI
+ * @vsi: the vsi being adjusted
+ **/
+void i40e_vlan_stripping_disable(struct i40e_vsi *vsi)
+{
+ struct i40e_vsi_context ctxt;
+ i40e_status ret;
+
+ if ((vsi->info.valid_sections &
+ cpu_to_le16(I40E_AQ_VSI_PROP_VLAN_VALID)) &&
+ ((vsi->info.port_vlan_flags & I40E_AQ_VSI_PVLAN_EMOD_MASK) ==
+ I40E_AQ_VSI_PVLAN_EMOD_MASK))
+ return; /* already disabled */
+
+ vsi->info.valid_sections = cpu_to_le16(I40E_AQ_VSI_PROP_VLAN_VALID);
+ vsi->info.port_vlan_flags = I40E_AQ_VSI_PVLAN_MODE_ALL |
+ I40E_AQ_VSI_PVLAN_EMOD_NOTHING;
+
+ ctxt.seid = vsi->seid;
+ memcpy(&ctxt.info, &vsi->info, sizeof(vsi->info));
+ ret = i40e_aq_update_vsi_params(&vsi->back->hw, &ctxt, NULL);
+ if (ret) {
+ dev_info(&vsi->back->pdev->dev,
+ "%s: update vsi failed, aq_err=%d\n",
+ __func__, vsi->back->hw.aq.asq_last_status);
+ }
+}
+
+/**
+ * i40e_vlan_rx_register - Setup or shutdown vlan offload
+ * @netdev: network interface to be adjusted
+ * @features: netdev features to test if VLAN offload is enabled or not
+ **/
+static void i40e_vlan_rx_register(struct net_device *netdev, u32 features)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+
+ if (features & NETIF_F_HW_VLAN_CTAG_RX)
+ i40e_vlan_stripping_enable(vsi);
+ else
+ i40e_vlan_stripping_disable(vsi);
+}
+
+/**
+ * i40e_vsi_add_vlan - Add vsi membership for given vlan
+ * @vsi: the vsi being configured
+ * @vid: vlan id to be added (0 = untagged only , -1 = any)
+ **/
+int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid)
+{
+ struct i40e_mac_filter *f, *add_f;
+ bool is_netdev, is_vf;
+ int ret;
+
+ is_vf = (vsi->type == I40E_VSI_SRIOV);
+ is_netdev = !!(vsi->netdev);
+
+ if (is_netdev) {
+ add_f = i40e_add_filter(vsi, vsi->netdev->dev_addr, vid,
+ is_vf, is_netdev);
+ if (!add_f) {
+ dev_info(&vsi->back->pdev->dev,
+ "Could not add vlan filter %d for %pM\n",
+ vid, vsi->netdev->dev_addr);
+ return -ENOMEM;
+ }
+ }
+
+ list_for_each_entry(f, &vsi->mac_filter_list, list) {
+ add_f = i40e_add_filter(vsi, f->macaddr, vid, is_vf, is_netdev);
+ if (!add_f) {
+ dev_info(&vsi->back->pdev->dev,
+ "Could not add vlan filter %d for %pM\n",
+ vid, f->macaddr);
+ return -ENOMEM;
+ }
+ }
+
+ ret = i40e_sync_vsi_filters(vsi);
+ if (ret) {
+ dev_info(&vsi->back->pdev->dev,
+ "Could not sync filters for vid %d\n", vid);
+ return ret;
+ }
+
+ /* Now if we add a vlan tag, make sure to check if it is the first
+ * tag (i.e. a "tag" -1 does exist) and if so replace the -1 "tag"
+ * with 0, so we now accept untagged and specified tagged traffic
+ * (and not any taged and untagged)
+ */
+ if (vid > 0) {
+ if (is_netdev && i40e_find_filter(vsi, vsi->netdev->dev_addr,
+ I40E_VLAN_ANY,
+ is_vf, is_netdev)) {
+ i40e_del_filter(vsi, vsi->netdev->dev_addr,
+ I40E_VLAN_ANY, is_vf, is_netdev);
+ add_f = i40e_add_filter(vsi, vsi->netdev->dev_addr, 0,
+ is_vf, is_netdev);
+ if (!add_f) {
+ dev_info(&vsi->back->pdev->dev,
+ "Could not add filter 0 for %pM\n",
+ vsi->netdev->dev_addr);
+ return -ENOMEM;
+ }
+ }
+
+ list_for_each_entry(f, &vsi->mac_filter_list, list) {
+ if (i40e_find_filter(vsi, f->macaddr, I40E_VLAN_ANY,
+ is_vf, is_netdev)) {
+ i40e_del_filter(vsi, f->macaddr, I40E_VLAN_ANY,
+ is_vf, is_netdev);
+ add_f = i40e_add_filter(vsi, f->macaddr,
+ 0, is_vf, is_netdev);
+ if (!add_f) {
+ dev_info(&vsi->back->pdev->dev,
+ "Could not add filter 0 for %pM\n",
+ f->macaddr);
+ return -ENOMEM;
+ }
+ }
+ }
+ ret = i40e_sync_vsi_filters(vsi);
+ }
+
+ return ret;
+}
+
+/**
+ * i40e_vsi_kill_vlan - Remove vsi membership for given vlan
+ * @vsi: the vsi being configured
+ * @vid: vlan id to be removed (0 = untagged only , -1 = any)
+ **/
+int i40e_vsi_kill_vlan(struct i40e_vsi *vsi, s16 vid)
+{
+ struct net_device *netdev = vsi->netdev;
+ struct i40e_mac_filter *f, *add_f;
+ bool is_vf, is_netdev;
+ int filter_count = 0;
+ int ret;
+
+ is_vf = (vsi->type == I40E_VSI_SRIOV);
+ is_netdev = !!(netdev);
+
+ if (is_netdev)
+ i40e_del_filter(vsi, netdev->dev_addr, vid, is_vf, is_netdev);
+
+ list_for_each_entry(f, &vsi->mac_filter_list, list)
+ i40e_del_filter(vsi, f->macaddr, vid, is_vf, is_netdev);
+
+ ret = i40e_sync_vsi_filters(vsi);
+ if (ret) {
+ dev_info(&vsi->back->pdev->dev, "Could not sync filters\n");
+ return ret;
+ }
+
+ /* go through all the filters for this VSI and if there is only
+ * vid == 0 it means there are no other filters, so vid 0 must
+ * be replaced with -1. This signifies that we should from now
+ * on accept any traffic (with any tag present, or untagged)
+ */
+ list_for_each_entry(f, &vsi->mac_filter_list, list) {
+ if (is_netdev) {
+ if (f->vlan &&
+ ether_addr_equal(netdev->dev_addr, f->macaddr))
+ filter_count++;
+ }
+
+ if (f->vlan)
+ filter_count++;
+ }
+
+ if (!filter_count && is_netdev) {
+ i40e_del_filter(vsi, netdev->dev_addr, 0, is_vf, is_netdev);
+ f = i40e_add_filter(vsi, netdev->dev_addr, I40E_VLAN_ANY,
+ is_vf, is_netdev);
+ if (!f) {
+ dev_info(&vsi->back->pdev->dev,
+ "Could not add filter %d for %pM\n",
+ I40E_VLAN_ANY, netdev->dev_addr);
+ return -ENOMEM;
+ }
+ }
+
+ if (!filter_count) {
+ list_for_each_entry(f, &vsi->mac_filter_list, list) {
+ i40e_del_filter(vsi, f->macaddr, 0, is_vf, is_netdev);
+ add_f = i40e_add_filter(vsi, f->macaddr, I40E_VLAN_ANY,
+ is_vf, is_netdev);
+ if (!add_f) {
+ dev_info(&vsi->back->pdev->dev,
+ "Could not add filter %d for %pM\n",
+ I40E_VLAN_ANY, f->macaddr);
+ return -ENOMEM;
+ }
+ }
+ }
+
+ return i40e_sync_vsi_filters(vsi);
+}
+
+/**
+ * i40e_vlan_rx_add_vid - Add a vlan id filter to HW offload
+ * @netdev: network interface to be adjusted
+ * @vid: vlan id to be added
+ **/
+static int i40e_vlan_rx_add_vid(struct net_device *netdev,
+ __always_unused __be16 proto, u16 vid)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+ int ret;
+
+ if (vid > 4095)
+ return 0;
+
+ netdev_info(vsi->netdev, "adding %pM vid=%d\n",
+ netdev->dev_addr, vid);
+ /* If the network stack called us with vid = 0, we should
+ * indicate to i40e_vsi_add_vlan() that we want to receive
+ * any traffic (i.e. with any vlan tag, or untagged)
+ */
+ ret = i40e_vsi_add_vlan(vsi, vid ? vid : I40E_VLAN_ANY);
+
+ if (!ret) {
+ if (vid < VLAN_N_VID)
+ set_bit(vid, vsi->active_vlans);
+ }
+
+ return 0;
+}
+
+/**
+ * i40e_vlan_rx_kill_vid - Remove a vlan id filter from HW offload
+ * @netdev: network interface to be adjusted
+ * @vid: vlan id to be removed
+ **/
+static int i40e_vlan_rx_kill_vid(struct net_device *netdev,
+ __always_unused __be16 proto, u16 vid)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+
+ netdev_info(vsi->netdev, "removing %pM vid=%d\n",
+ netdev->dev_addr, vid);
+ /* return code is ignored as there is nothing a user
+ * can do about failure to remove and a log message was
+ * already printed from another function
+ */
+ i40e_vsi_kill_vlan(vsi, vid);
+
+ clear_bit(vid, vsi->active_vlans);
+ return 0;
+}
+
+/**
+ * i40e_restore_vlan - Reinstate vlans when vsi/netdev comes back up
+ * @vsi: the vsi being brought back up
+ **/
+static void i40e_restore_vlan(struct i40e_vsi *vsi)
+{
+ u16 vid;
+
+ if (!vsi->netdev)
+ return;
+
+ i40e_vlan_rx_register(vsi->netdev, vsi->netdev->features);
+
+ for_each_set_bit(vid, vsi->active_vlans, VLAN_N_VID)
+ i40e_vlan_rx_add_vid(vsi->netdev, htons(ETH_P_8021Q),
+ vid);
+}
+
+/**
+ * i40e_vsi_add_pvid - Add pvid for the VSI
+ * @vsi: the vsi being adjusted
+ * @vid: the vlan id to set as a PVID
+ **/
+i40e_status i40e_vsi_add_pvid(struct i40e_vsi *vsi, u16 vid)
+{
+ struct i40e_vsi_context ctxt;
+ i40e_status ret;
+
+ vsi->info.valid_sections = cpu_to_le16(I40E_AQ_VSI_PROP_VLAN_VALID);
+ vsi->info.pvid = cpu_to_le16(vid);
+ vsi->info.port_vlan_flags |= I40E_AQ_VSI_PVLAN_INSERT_PVID;
+ vsi->info.port_vlan_flags |= I40E_AQ_VSI_PVLAN_MODE_UNTAGGED;
+
+ ctxt.seid = vsi->seid;
+ memcpy(&ctxt.info, &vsi->info, sizeof(vsi->info));
+ ret = i40e_aq_update_vsi_params(&vsi->back->hw, &ctxt, NULL);
+ if (ret) {
+ dev_info(&vsi->back->pdev->dev,
+ "%s: update vsi failed, aq_err=%d\n",
+ __func__, vsi->back->hw.aq.asq_last_status);
+ }
+
+ return ret;
+}
+
+/**
+ * i40e_vsi_remove_pvid - Remove the pvid from the VSI
+ * @vsi: the vsi being adjusted
+ *
+ * Just use the vlan_rx_register() service to put it back to normal
+ **/
+void i40e_vsi_remove_pvid(struct i40e_vsi *vsi)
+{
+ vsi->info.pvid = 0;
+ i40e_vlan_rx_register(vsi->netdev, vsi->netdev->features);
+}
+
+/**
+ * i40e_vsi_setup_tx_resources - Allocate VSI Tx queue resources
+ * @vsi: ptr to the VSI
+ *
+ * If this function returns with an error, then it's possible one or
+ * more of the rings is populated (while the rest are not). It is the
+ * callers duty to clean those orphaned rings.
+ *
+ * Return 0 on success, negative on failure
+ **/
+static int i40e_vsi_setup_tx_resources(struct i40e_vsi *vsi)
+{
+ int i, err = 0;
+
+ for (i = 0; i < vsi->num_queue_pairs && !err; i++)
+ err = i40e_setup_tx_descriptors(&vsi->tx_rings[i]);
+
+ return err;
+}
+
+/**
+ * i40e_vsi_free_tx_resources - Free Tx resources for VSI queues
+ * @vsi: ptr to the VSI
+ *
+ * Free VSI's transmit software resources
+ **/
+static void i40e_vsi_free_tx_resources(struct i40e_vsi *vsi)
+{
+ int i;
+
+ for (i = 0; i < vsi->num_queue_pairs; i++)
+ if (vsi->tx_rings[i].desc)
+ i40e_free_tx_resources(&vsi->tx_rings[i]);
+}
+
+/**
+ * i40e_vsi_setup_rx_resources - Allocate VSI queues Rx resources
+ * @vsi: ptr to the VSI
+ *
+ * If this function returns with an error, then it's possible one or
+ * more of the rings is populated (while the rest are not). It is the
+ * callers duty to clean those orphaned rings.
+ *
+ * Return 0 on success, negative on failure
+ **/
+static int i40e_vsi_setup_rx_resources(struct i40e_vsi *vsi)
+{
+ int i, err = 0;
+
+ for (i = 0; i < vsi->num_queue_pairs && !err; i++)
+ err = i40e_setup_rx_descriptors(&vsi->rx_rings[i]);
+ return err;
+}
+
+/**
+ * i40e_vsi_free_rx_resources - Free Rx Resources for VSI queues
+ * @vsi: ptr to the VSI
+ *
+ * Free all receive software resources
+ **/
+static void i40e_vsi_free_rx_resources(struct i40e_vsi *vsi)
+{
+ int i;
+
+ for (i = 0; i < vsi->num_queue_pairs; i++)
+ if (vsi->rx_rings[i].desc)
+ i40e_free_rx_resources(&vsi->rx_rings[i]);
+}
+
+/**
+ * i40e_configure_tx_ring - Configure a transmit ring context and rest
+ * @ring: The Tx ring to configure
+ *
+ * Configure the Tx descriptor ring in the HMC context.
+ **/
+static int i40e_configure_tx_ring(struct i40e_ring *ring)
+{
+ struct i40e_vsi *vsi = ring->vsi;
+ u16 pf_q = vsi->base_queue + ring->queue_index;
+ struct i40e_hw *hw = &vsi->back->hw;
+ struct i40e_hmc_obj_txq tx_ctx;
+ i40e_status err = 0;
+ u32 qtx_ctl = 0;
+
+ /* some ATR related tx ring init */
+ if (vsi->back->flags & I40E_FLAG_FDIR_ATR_ENABLED) {
+ ring->atr_sample_rate = vsi->back->atr_sample_rate;
+ ring->atr_count = 0;
+ } else {
+ ring->atr_sample_rate = 0;
+ }
+
+ /* initialize XPS */
+ if (ring->q_vector && ring->netdev &&
+ !test_and_set_bit(__I40E_TX_XPS_INIT_DONE, &ring->state))
+ netif_set_xps_queue(ring->netdev,
+ &ring->q_vector->affinity_mask,
+ ring->queue_index);
+
+ /* clear the context structure first */
+ memset(&tx_ctx, 0, sizeof(tx_ctx));
+
+ tx_ctx.new_context = 1;
+ tx_ctx.base = (ring->dma / 128);
+ tx_ctx.qlen = ring->count;
+ tx_ctx.fd_ena = !!(vsi->back->flags & (I40E_FLAG_FDIR_ENABLED |
+ I40E_FLAG_FDIR_ATR_ENABLED));
+
+ /* As part of VSI creation/update, FW allocates certain
+ * Tx arbitration queue sets for each TC enabled for
+ * the VSI. The FW returns the handles to these queue
+ * sets as part of the response buffer to Add VSI,
+ * Update VSI, etc. AQ commands. It is expected that
+ * these queue set handles be associated with the Tx
+ * queues by the driver as part of the TX queue context
+ * initialization. This has to be done regardless of
+ * DCB as by default everything is mapped to TC0.
+ */
+ tx_ctx.rdylist = le16_to_cpu(vsi->info.qs_handle[ring->dcb_tc]);
+ tx_ctx.rdylist_act = 0;
+
+ /* clear the context in the HMC */
+ err = i40e_clear_lan_tx_queue_context(hw, pf_q);
+ if (err) {
+ dev_info(&vsi->back->pdev->dev,
+ "Failed to clear LAN Tx queue context on Tx ring %d (pf_q %d), error: %d\n",
+ ring->queue_index, pf_q, err);
+ return -ENOMEM;
+ }
+
+ /* set the context in the HMC */
+ err = i40e_set_lan_tx_queue_context(hw, pf_q, &tx_ctx);
+ if (err) {
+ dev_info(&vsi->back->pdev->dev,
+ "Failed to set LAN Tx queue context on Tx ring %d (pf_q %d, error: %d\n",
+ ring->queue_index, pf_q, err);
+ return -ENOMEM;
+ }
+
+ /* Now associate this queue with this PCI function */
+ qtx_ctl = I40E_QTX_CTL_PF_QUEUE;
+ qtx_ctl |= ((hw->hmc.hmc_fn_id << I40E_QTX_CTL_PF_INDX_SHIFT)
+ & I40E_QTX_CTL_PF_INDX_MASK);
+ wr32(hw, I40E_QTX_CTL(pf_q), qtx_ctl);
+ i40e_flush(hw);
+
+ clear_bit(__I40E_HANG_CHECK_ARMED, &ring->state);
+
+ /* cache tail off for easier writes later */
+ ring->tail = hw->hw_addr + I40E_QTX_TAIL(pf_q);
+
+ return 0;
+}
+
+/**
+ * i40e_configure_rx_ring - Configure a receive ring context
+ * @ring: The Rx ring to configure
+ *
+ * Configure the Rx descriptor ring in the HMC context.
+ **/
+static int i40e_configure_rx_ring(struct i40e_ring *ring)
+{
+ struct i40e_vsi *vsi = ring->vsi;
+ u32 chain_len = vsi->back->hw.func_caps.rx_buf_chain_len;
+ u16 pf_q = vsi->base_queue + ring->queue_index;
+ struct i40e_hw *hw = &vsi->back->hw;
+ struct i40e_hmc_obj_rxq rx_ctx;
+ i40e_status err = 0;
+
+ ring->state = 0;
+
+ /* clear the context structure first */
+ memset(&rx_ctx, 0, sizeof(rx_ctx));
+
+ ring->rx_buf_len = vsi->rx_buf_len;
+ ring->rx_hdr_len = vsi->rx_hdr_len;
+
+ rx_ctx.dbuff = ring->rx_buf_len >> I40E_RXQ_CTX_DBUFF_SHIFT;
+ rx_ctx.hbuff = ring->rx_hdr_len >> I40E_RXQ_CTX_HBUFF_SHIFT;
+
+ rx_ctx.base = (ring->dma / 128);
+ rx_ctx.qlen = ring->count;
+
+ if (vsi->back->flags & I40E_FLAG_16BYTE_RX_DESC_ENABLED) {
+ set_ring_16byte_desc_enabled(ring);
+ rx_ctx.dsize = 0;
+ } else {
+ rx_ctx.dsize = 1;
+ }
+
+ rx_ctx.dtype = vsi->dtype;
+ if (vsi->dtype) {
+ set_ring_ps_enabled(ring);
+ rx_ctx.hsplit_0 = I40E_RX_SPLIT_L2 |
+ I40E_RX_SPLIT_IP |
+ I40E_RX_SPLIT_TCP_UDP |
+ I40E_RX_SPLIT_SCTP;
+ } else {
+ rx_ctx.hsplit_0 = 0;
+ }
+
+ rx_ctx.rxmax = min_t(u16, vsi->max_frame,
+ (chain_len * ring->rx_buf_len));
+ rx_ctx.tphrdesc_ena = 1;
+ rx_ctx.tphwdesc_ena = 1;
+ rx_ctx.tphdata_ena = 1;
+ rx_ctx.tphhead_ena = 1;
+ rx_ctx.lrxqthresh = 2;
+ rx_ctx.crcstrip = 1;
+ rx_ctx.l2tsel = 1;
+ rx_ctx.showiv = 1;
+
+ /* clear the context in the HMC */
+ err = i40e_clear_lan_rx_queue_context(hw, pf_q);
+ if (err) {
+ dev_info(&vsi->back->pdev->dev,
+ "Failed to clear LAN Rx queue context on Rx ring %d (pf_q %d), error: %d\n",
+ ring->queue_index, pf_q, err);
+ return -ENOMEM;
+ }
+
+ /* set the context in the HMC */
+ err = i40e_set_lan_rx_queue_context(hw, pf_q, &rx_ctx);
+ if (err) {
+ dev_info(&vsi->back->pdev->dev,
+ "Failed to set LAN Rx queue context on Rx ring %d (pf_q %d), error: %d\n",
+ ring->queue_index, pf_q, err);
+ return -ENOMEM;
+ }
+
+ /* cache tail for quicker writes, and clear the reg before use */
+ ring->tail = hw->hw_addr + I40E_QRX_TAIL(pf_q);
+ writel(0, ring->tail);
+
+ i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring));
+
+ return 0;
+}
+
+/**
+ * i40e_vsi_configure_tx - Configure the VSI for Tx
+ * @vsi: VSI structure describing this set of rings and resources
+ *
+ * Configure the Tx VSI for operation.
+ **/
+static int i40e_vsi_configure_tx(struct i40e_vsi *vsi)
+{
+ int err = 0;
+ u16 i;
+
+ for (i = 0; (i < vsi->num_queue_pairs) && (!err); i++)
+ err = i40e_configure_tx_ring(&vsi->tx_rings[i]);
+
+ return err;
+}
+
+/**
+ * i40e_vsi_configure_rx - Configure the VSI for Rx
+ * @vsi: the VSI being configured
+ *
+ * Configure the Rx VSI for operation.
+ **/
+static int i40e_vsi_configure_rx(struct i40e_vsi *vsi)
+{
+ int err = 0;
+ u16 i;
+
+ if (vsi->netdev && (vsi->netdev->mtu > ETH_DATA_LEN))
+ vsi->max_frame = vsi->netdev->mtu + ETH_HLEN
+ + ETH_FCS_LEN + VLAN_HLEN;
+ else
+ vsi->max_frame = I40E_RXBUFFER_2048;
+
+ /* figure out correct receive buffer length */
+ switch (vsi->back->flags & (I40E_FLAG_RX_1BUF_ENABLED |
+ I40E_FLAG_RX_PS_ENABLED)) {
+ case I40E_FLAG_RX_1BUF_ENABLED:
+ vsi->rx_hdr_len = 0;
+ vsi->rx_buf_len = vsi->max_frame;
+ vsi->dtype = I40E_RX_DTYPE_NO_SPLIT;
+ break;
+ case I40E_FLAG_RX_PS_ENABLED:
+ vsi->rx_hdr_len = I40E_RX_HDR_SIZE;
+ vsi->rx_buf_len = I40E_RXBUFFER_2048;
+ vsi->dtype = I40E_RX_DTYPE_HEADER_SPLIT;
+ break;
+ default:
+ vsi->rx_hdr_len = I40E_RX_HDR_SIZE;
+ vsi->rx_buf_len = I40E_RXBUFFER_2048;
+ vsi->dtype = I40E_RX_DTYPE_SPLIT_ALWAYS;
+ break;
+ }
+
+ /* round up for the chip's needs */
+ vsi->rx_hdr_len = ALIGN(vsi->rx_hdr_len,
+ (1 << I40E_RXQ_CTX_HBUFF_SHIFT));
+ vsi->rx_buf_len = ALIGN(vsi->rx_buf_len,
+ (1 << I40E_RXQ_CTX_DBUFF_SHIFT));
+
+ /* set up individual rings */
+ for (i = 0; i < vsi->num_queue_pairs && !err; i++)
+ err = i40e_configure_rx_ring(&vsi->rx_rings[i]);
+
+ return err;
+}
+
+/**
+ * i40e_vsi_config_dcb_rings - Update rings to reflect DCB TC
+ * @vsi: ptr to the VSI
+ **/
+static void i40e_vsi_config_dcb_rings(struct i40e_vsi *vsi)
+{
+ u16 qoffset, qcount;
+ int i, n;
+
+ if (!(vsi->back->flags & I40E_FLAG_DCB_ENABLED))
+ return;
+
+ for (n = 0; n < I40E_MAX_TRAFFIC_CLASS; n++) {
+ if (!(vsi->tc_config.enabled_tc & (1 << n)))
+ continue;
+
+ qoffset = vsi->tc_config.tc_info[n].qoffset;
+ qcount = vsi->tc_config.tc_info[n].qcount;
+ for (i = qoffset; i < (qoffset + qcount); i++) {
+ struct i40e_ring *rx_ring = &vsi->rx_rings[i];
+ struct i40e_ring *tx_ring = &vsi->tx_rings[i];
+ rx_ring->dcb_tc = n;
+ tx_ring->dcb_tc = n;
+ }
+ }
+}
+
+/**
+ * i40e_set_vsi_rx_mode - Call set_rx_mode on a VSI
+ * @vsi: ptr to the VSI
+ **/
+static void i40e_set_vsi_rx_mode(struct i40e_vsi *vsi)
+{
+ if (vsi->netdev)
+ i40e_set_rx_mode(vsi->netdev);
+}
+
+/**
+ * i40e_vsi_configure - Set up the VSI for action
+ * @vsi: the VSI being configured
+ **/
+static int i40e_vsi_configure(struct i40e_vsi *vsi)
+{
+ int err;
+
+ i40e_set_vsi_rx_mode(vsi);
+ i40e_restore_vlan(vsi);
+ i40e_vsi_config_dcb_rings(vsi);
+ err = i40e_vsi_configure_tx(vsi);
+ if (!err)
+ err = i40e_vsi_configure_rx(vsi);
+
+ return err;
+}
+
+/**
+ * i40e_vsi_configure_msix - MSIX mode Interrupt Config in the HW
+ * @vsi: the VSI being configured
+ **/
+static void i40e_vsi_configure_msix(struct i40e_vsi *vsi)
+{
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_q_vector *q_vector;
+ struct i40e_hw *hw = &pf->hw;
+ u16 vector;
+ int i, q;
+ u32 val;
+ u32 qp;
+
+ /* The interrupt indexing is offset by 1 in the PFINT_ITRn
+ * and PFINT_LNKLSTn registers, e.g.:
+ * PFINT_ITRn[0..n-1] gets msix-1..msix-n (qpair interrupts)
+ */
+ qp = vsi->base_queue;
+ vector = vsi->base_vector;
+ q_vector = vsi->q_vectors;
+ for (i = 0; i < vsi->num_q_vectors; i++, q_vector++, vector++) {
+ q_vector->rx.itr = ITR_TO_REG(vsi->rx_itr_setting);
+ q_vector->rx.latency_range = I40E_LOW_LATENCY;
+ wr32(hw, I40E_PFINT_ITRN(I40E_RX_ITR, vector - 1),
+ q_vector->rx.itr);
+ q_vector->tx.itr = ITR_TO_REG(vsi->tx_itr_setting);
+ q_vector->tx.latency_range = I40E_LOW_LATENCY;
+ wr32(hw, I40E_PFINT_ITRN(I40E_TX_ITR, vector - 1),
+ q_vector->tx.itr);
+
+ /* Linked list for the queuepairs assigned to this vector */
+ wr32(hw, I40E_PFINT_LNKLSTN(vector - 1), qp);
+ for (q = 0; q < q_vector->num_ringpairs; q++) {
+ val = I40E_QINT_RQCTL_CAUSE_ENA_MASK |
+ (I40E_RX_ITR << I40E_QINT_RQCTL_ITR_INDX_SHIFT) |
+ (vector << I40E_QINT_RQCTL_MSIX_INDX_SHIFT) |
+ (qp << I40E_QINT_RQCTL_NEXTQ_INDX_SHIFT)|
+ (I40E_QUEUE_TYPE_TX
+ << I40E_QINT_RQCTL_NEXTQ_TYPE_SHIFT);
+
+ wr32(hw, I40E_QINT_RQCTL(qp), val);
+
+ val = I40E_QINT_TQCTL_CAUSE_ENA_MASK |
+ (I40E_TX_ITR << I40E_QINT_TQCTL_ITR_INDX_SHIFT) |
+ (vector << I40E_QINT_TQCTL_MSIX_INDX_SHIFT) |
+ ((qp+1) << I40E_QINT_TQCTL_NEXTQ_INDX_SHIFT)|
+ (I40E_QUEUE_TYPE_RX
+ << I40E_QINT_TQCTL_NEXTQ_TYPE_SHIFT);
+
+ /* Terminate the linked list */
+ if (q == (q_vector->num_ringpairs - 1))
+ val |= (I40E_QUEUE_END_OF_LIST
+ << I40E_QINT_TQCTL_NEXTQ_INDX_SHIFT);
+
+ wr32(hw, I40E_QINT_TQCTL(qp), val);
+ qp++;
+ }
+ }
+
+ i40e_flush(hw);
+}
+
+/**
+ * i40e_enable_misc_int_causes - enable the non-queue interrupts
+ * @hw: ptr to the hardware info
+ **/
+static void i40e_enable_misc_int_causes(struct i40e_hw *hw)
+{
+ u32 val;
+
+ /* clear things first */
+ wr32(hw, I40E_PFINT_ICR0_ENA, 0); /* disable all */
+ rd32(hw, I40E_PFINT_ICR0); /* read to clear */
+
+ val = I40E_PFINT_ICR0_ENA_ECC_ERR_MASK |
+ I40E_PFINT_ICR0_ENA_MAL_DETECT_MASK |
+ I40E_PFINT_ICR0_ENA_GRST_MASK |
+ I40E_PFINT_ICR0_ENA_PCI_EXCEPTION_MASK |
+ I40E_PFINT_ICR0_ENA_GPIO_MASK |
+ I40E_PFINT_ICR0_ENA_STORM_DETECT_MASK |
+ I40E_PFINT_ICR0_ENA_HMC_ERR_MASK |
+ I40E_PFINT_ICR0_ENA_VFLR_MASK |
+ I40E_PFINT_ICR0_ENA_ADMINQ_MASK;
+
+ wr32(hw, I40E_PFINT_ICR0_ENA, val);
+
+ /* SW_ITR_IDX = 0, but don't change INTENA */
+ wr32(hw, I40E_PFINT_DYN_CTL0, I40E_PFINT_DYN_CTLN_SW_ITR_INDX_MASK |
+ I40E_PFINT_DYN_CTLN_INTENA_MSK_MASK);
+
+ /* OTHER_ITR_IDX = 0 */
+ wr32(hw, I40E_PFINT_STAT_CTL0, 0);
+}
+
+/**
+ * i40e_configure_msi_and_legacy - Legacy mode interrupt config in the HW
+ * @vsi: the VSI being configured
+ **/
+static void i40e_configure_msi_and_legacy(struct i40e_vsi *vsi)
+{
+ struct i40e_q_vector *q_vector = vsi->q_vectors;
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+ u32 val;
+
+ /* set the ITR configuration */
+ q_vector->rx.itr = ITR_TO_REG(vsi->rx_itr_setting);
+ q_vector->rx.latency_range = I40E_LOW_LATENCY;
+ wr32(hw, I40E_PFINT_ITR0(I40E_RX_ITR), q_vector->rx.itr);
+ q_vector->tx.itr = ITR_TO_REG(vsi->tx_itr_setting);
+ q_vector->tx.latency_range = I40E_LOW_LATENCY;
+ wr32(hw, I40E_PFINT_ITR0(I40E_TX_ITR), q_vector->tx.itr);
+
+ i40e_enable_misc_int_causes(hw);
+
+ /* FIRSTQ_INDX = 0, FIRSTQ_TYPE = 0 (rx) */
+ wr32(hw, I40E_PFINT_LNKLST0, 0);
+
+ /* Associate the queue pair to the vector and enable the q int */
+ val = I40E_QINT_RQCTL_CAUSE_ENA_MASK |
+ (I40E_RX_ITR << I40E_QINT_RQCTL_ITR_INDX_SHIFT) |
+ (I40E_QUEUE_TYPE_TX << I40E_QINT_TQCTL_NEXTQ_TYPE_SHIFT);
+
+ wr32(hw, I40E_QINT_RQCTL(0), val);
+
+ val = I40E_QINT_TQCTL_CAUSE_ENA_MASK |
+ (I40E_TX_ITR << I40E_QINT_TQCTL_ITR_INDX_SHIFT) |
+ (I40E_QUEUE_END_OF_LIST << I40E_QINT_TQCTL_NEXTQ_INDX_SHIFT);
+
+ wr32(hw, I40E_QINT_TQCTL(0), val);
+ i40e_flush(hw);
+}
+
+/**
+ * i40e_irq_dynamic_enable_icr0 - Enable default interrupt generation for icr0
+ * @pf: board private structure
+ **/
+static void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf)
+{
+ struct i40e_hw *hw = &pf->hw;
+ u32 val;
+
+ val = I40E_PFINT_DYN_CTL0_INTENA_MASK |
+ I40E_PFINT_DYN_CTL0_CLEARPBA_MASK |
+ (I40E_ITR_NONE << I40E_PFINT_DYN_CTL0_ITR_INDX_SHIFT);
+
+ wr32(hw, I40E_PFINT_DYN_CTL0, val);
+ i40e_flush(hw);
+}
+
+/**
+ * i40e_irq_dynamic_enable - Enable default interrupt generation settings
+ * @vsi: pointer to a vsi
+ * @vector: enable a particular Hw Interrupt vector
+ **/
+void i40e_irq_dynamic_enable(struct i40e_vsi *vsi, int vector)
+{
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+ u32 val;
+
+ val = I40E_PFINT_DYN_CTLN_INTENA_MASK |
+ I40E_PFINT_DYN_CTLN_CLEARPBA_MASK |
+ (I40E_ITR_NONE << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT);
+ wr32(hw, I40E_PFINT_DYN_CTLN(vector - 1), val);
+ i40e_flush(hw);
+}
+
+/**
+ * i40e_msix_clean_rings - MSIX mode Interrupt Handler
+ * @irq: interrupt number
+ * @data: pointer to a q_vector
+ **/
+static irqreturn_t i40e_msix_clean_rings(int irq, void *data)
+{
+ struct i40e_q_vector *q_vector = data;
+
+ if (!q_vector->tx.ring[0] && !q_vector->rx.ring[0])
+ return IRQ_HANDLED;
+
+ napi_schedule(&q_vector->napi);
+
+ return IRQ_HANDLED;
+}
+
+/**
+ * i40e_fdir_clean_rings - Interrupt Handler for FDIR rings
+ * @irq: interrupt number
+ * @data: pointer to a q_vector
+ **/
+static irqreturn_t i40e_fdir_clean_rings(int irq, void *data)
+{
+ struct i40e_q_vector *q_vector = data;
+
+ if (!q_vector->tx.ring[0] && !q_vector->rx.ring[0])
+ return IRQ_HANDLED;
+
+ pr_info("fdir ring cleaning needed\n");
+
+ return IRQ_HANDLED;
+}
+
+/**
+ * i40e_vsi_request_irq_msix - Initialize MSI-X interrupts
+ * @vsi: the VSI being configured
+ * @basename: name for the vector
+ *
+ * Allocates MSI-X vectors and requests interrupts from the kernel.
+ **/
+static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename)
+{
+ int q_vectors = vsi->num_q_vectors;
+ struct i40e_pf *pf = vsi->back;
+ int base = vsi->base_vector;
+ int rx_int_idx = 0;
+ int tx_int_idx = 0;
+ int vector, err;
+
+ for (vector = 0; vector < q_vectors; vector++) {
+ struct i40e_q_vector *q_vector = &(vsi->q_vectors[vector]);
+
+ if (q_vector->tx.ring[0] && q_vector->rx.ring[0]) {
+ snprintf(q_vector->name, sizeof(q_vector->name) - 1,
+ "%s-%s-%d", basename, "TxRx", rx_int_idx++);
+ tx_int_idx++;
+ } else if (q_vector->rx.ring[0]) {
+ snprintf(q_vector->name, sizeof(q_vector->name) - 1,
+ "%s-%s-%d", basename, "rx", rx_int_idx++);
+ } else if (q_vector->tx.ring[0]) {
+ snprintf(q_vector->name, sizeof(q_vector->name) - 1,
+ "%s-%s-%d", basename, "tx", tx_int_idx++);
+ } else {
+ /* skip this unused q_vector */
+ continue;
+ }
+ err = request_irq(pf->msix_entries[base + vector].vector,
+ vsi->irq_handler,
+ 0,
+ q_vector->name,
+ q_vector);
+ if (err) {
+ dev_info(&pf->pdev->dev,
+ "%s: request_irq failed, error: %d\n",
+ __func__, err);
+ goto free_queue_irqs;
+ }
+ /* assign the mask for this irq */
+ irq_set_affinity_hint(pf->msix_entries[base + vector].vector,
+ &q_vector->affinity_mask);
+ }
+
+ return 0;
+
+free_queue_irqs:
+ while (vector) {
+ vector--;
+ irq_set_affinity_hint(pf->msix_entries[base + vector].vector,
+ NULL);
+ free_irq(pf->msix_entries[base + vector].vector,
+ &(vsi->q_vectors[vector]));
+ }
+ return err;
+}
+
+/**
+ * i40e_vsi_disable_irq - Mask off queue interrupt generation on the VSI
+ * @vsi: the VSI being un-configured
+ **/
+static void i40e_vsi_disable_irq(struct i40e_vsi *vsi)
+{
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+ int base = vsi->base_vector;
+ int i;
+
+ for (i = 0; i < vsi->num_queue_pairs; i++) {
+ wr32(hw, I40E_QINT_TQCTL(vsi->tx_rings[i].reg_idx), 0);
+ wr32(hw, I40E_QINT_RQCTL(vsi->rx_rings[i].reg_idx), 0);
+ }
+
+ if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
+ for (i = vsi->base_vector;
+ i < (vsi->num_q_vectors + vsi->base_vector); i++)
+ wr32(hw, I40E_PFINT_DYN_CTLN(i - 1), 0);
+
+ i40e_flush(hw);
+ for (i = 0; i < vsi->num_q_vectors; i++)
+ synchronize_irq(pf->msix_entries[i + base].vector);
+ } else {
+ /* Legacy and MSI mode - this stops all interrupt handling */
+ wr32(hw, I40E_PFINT_ICR0_ENA, 0);
+ wr32(hw, I40E_PFINT_DYN_CTL0, 0);
+ i40e_flush(hw);
+ synchronize_irq(pf->pdev->irq);
+ }
+}
+
+/**
+ * i40e_vsi_enable_irq - Enable IRQ for the given VSI
+ * @vsi: the VSI being configured
+ **/
+static int i40e_vsi_enable_irq(struct i40e_vsi *vsi)
+{
+ struct i40e_pf *pf = vsi->back;
+ int i;
+
+ if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
+ for (i = vsi->base_vector;
+ i < (vsi->num_q_vectors + vsi->base_vector); i++)
+ i40e_irq_dynamic_enable(vsi, i);
+ } else {
+ i40e_irq_dynamic_enable_icr0(pf);
+ }
+
+ return 0;
+}
+
+/**
+ * i40e_stop_misc_vector - Stop the vector that handles non-queue events
+ * @pf: board private structure
+ **/
+static void i40e_stop_misc_vector(struct i40e_pf *pf)
+{
+ /* Disable ICR 0 */
+ wr32(&pf->hw, I40E_PFINT_ICR0_ENA, 0);
+ i40e_flush(&pf->hw);
+}
+
+/**
+ * i40e_intr - MSI/Legacy and non-queue interrupt handler
+ * @irq: interrupt number
+ * @data: pointer to a q_vector
+ *
+ * This is the handler used for all MSI/Legacy interrupts, and deals
+ * with both queue and non-queue interrupts. This is also used in
+ * MSIX mode to handle the non-queue interrupts.
+ **/
+static irqreturn_t i40e_intr(int irq, void *data)
+{
+ struct i40e_pf *pf = (struct i40e_pf *)data;
+ struct i40e_hw *hw = &pf->hw;
+ u32 icr0, icr0_remaining;
+ u32 val, ena_mask;
+
+ icr0 = rd32(hw, I40E_PFINT_ICR0);
+
+ /* if sharing a legacy IRQ, we might get called w/o an intr pending */
+ if ((icr0 & I40E_PFINT_ICR0_INTEVENT_MASK) == 0)
+ return IRQ_NONE;
+
+ val = rd32(hw, I40E_PFINT_DYN_CTL0);
+ val = val | I40E_PFINT_DYN_CTL0_CLEARPBA_MASK;
+ wr32(hw, I40E_PFINT_DYN_CTL0, val);
+
+ ena_mask = rd32(hw, I40E_PFINT_ICR0_ENA);
+
+ /* only q0 is used in MSI/Legacy mode, and none are used in MSIX */
+ if (icr0 & I40E_PFINT_ICR0_QUEUE_0_MASK) {
+
+ /* temporarily disable queue cause for NAPI processing */
+ u32 qval = rd32(hw, I40E_QINT_RQCTL(0));
+ qval &= ~I40E_QINT_RQCTL_CAUSE_ENA_MASK;
+ wr32(hw, I40E_QINT_RQCTL(0), qval);
+
+ qval = rd32(hw, I40E_QINT_TQCTL(0));
+ qval &= ~I40E_QINT_TQCTL_CAUSE_ENA_MASK;
+ wr32(hw, I40E_QINT_TQCTL(0), qval);
+ i40e_flush(hw);
+
+ if (!test_bit(__I40E_DOWN, &pf->state))
+ napi_schedule(&pf->vsi[pf->lan_vsi]->q_vectors[0].napi);
+ }
+
+ if (icr0 & I40E_PFINT_ICR0_ADMINQ_MASK) {
+ ena_mask &= ~I40E_PFINT_ICR0_ENA_ADMINQ_MASK;
+ set_bit(__I40E_ADMINQ_EVENT_PENDING, &pf->state);
+ }
+
+ if (icr0 & I40E_PFINT_ICR0_MAL_DETECT_MASK) {
+ ena_mask &= ~I40E_PFINT_ICR0_ENA_MAL_DETECT_MASK;
+ set_bit(__I40E_MDD_EVENT_PENDING, &pf->state);
+ }
+
+ if (icr0 & I40E_PFINT_ICR0_VFLR_MASK) {
+ ena_mask &= ~I40E_PFINT_ICR0_ENA_VFLR_MASK;
+ set_bit(__I40E_VFLR_EVENT_PENDING, &pf->state);
+ }
+
+ if (icr0 & I40E_PFINT_ICR0_GRST_MASK) {
+ if (!test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state))
+ set_bit(__I40E_RESET_INTR_RECEIVED, &pf->state);
+ ena_mask &= ~I40E_PFINT_ICR0_ENA_GRST_MASK;
+ val = rd32(hw, I40E_GLGEN_RSTAT);
+ val = (val & I40E_GLGEN_RSTAT_RESET_TYPE_MASK)
+ >> I40E_GLGEN_RSTAT_RESET_TYPE_SHIFT;
+ if (val & I40E_RESET_CORER)
+ pf->corer_count++;
+ else if (val & I40E_RESET_GLOBR)
+ pf->globr_count++;
+ else if (val & I40E_RESET_EMPR)
+ pf->empr_count++;
+ }
+
+ /* If a critical error is pending we have no choice but to reset the
+ * device.
+ * Report and mask out any remaining unexpected interrupts.
+ */
+ icr0_remaining = icr0 & ena_mask;
+ if (icr0_remaining) {
+ dev_info(&pf->pdev->dev, "unhandled interrupt icr0=0x%08x\n",
+ icr0_remaining);
+ if ((icr0_remaining & I40E_PFINT_ICR0_HMC_ERR_MASK) ||
+ (icr0_remaining & I40E_PFINT_ICR0_PE_CRITERR_MASK) ||
+ (icr0_remaining & I40E_PFINT_ICR0_PCI_EXCEPTION_MASK) ||
+ (icr0_remaining & I40E_PFINT_ICR0_ECC_ERR_MASK) ||
+ (icr0_remaining & I40E_PFINT_ICR0_MAL_DETECT_MASK)) {
+ if (icr0 & I40E_PFINT_ICR0_HMC_ERR_MASK) {
+ dev_info(&pf->pdev->dev, "HMC error interrupt\n");
+ } else {
+ dev_info(&pf->pdev->dev, "device will be reset\n");
+ set_bit(__I40E_PF_RESET_REQUESTED, &pf->state);
+ i40e_service_event_schedule(pf);
+ }
+ }
+ ena_mask &= ~icr0_remaining;
+ }
+
+ /* re-enable interrupt causes */
+ wr32(hw, I40E_PFINT_ICR0_ENA, ena_mask);
+ i40e_flush(hw);
+ if (!test_bit(__I40E_DOWN, &pf->state)) {
+ i40e_service_event_schedule(pf);
+ i40e_irq_dynamic_enable_icr0(pf);
+ }
+
+ return IRQ_HANDLED;
+}
+
+/**
+ * i40e_map_vector_to_rxq - Assigns the Rx queue to the vector
+ * @vsi: the VSI being configured
+ * @v_idx: vector index
+ * @r_idx: rx queue index
+ **/
+static void map_vector_to_rxq(struct i40e_vsi *vsi, int v_idx, int r_idx)
+{
+ struct i40e_q_vector *q_vector = &(vsi->q_vectors[v_idx]);
+ struct i40e_ring *rx_ring = &(vsi->rx_rings[r_idx]);
+
+ rx_ring->q_vector = q_vector;
+ q_vector->rx.ring[q_vector->rx.count] = rx_ring;
+ q_vector->rx.count++;
+ q_vector->rx.latency_range = I40E_LOW_LATENCY;
+ q_vector->vsi = vsi;
+}
+
+/**
+ * i40e_map_vector_to_txq - Assigns the Tx queue to the vector
+ * @vsi: the VSI being configured
+ * @v_idx: vector index
+ * @t_idx: tx queue index
+ **/
+static void map_vector_to_txq(struct i40e_vsi *vsi, int v_idx, int t_idx)
+{
+ struct i40e_q_vector *q_vector = &(vsi->q_vectors[v_idx]);
+ struct i40e_ring *tx_ring = &(vsi->tx_rings[t_idx]);
+
+ tx_ring->q_vector = q_vector;
+ q_vector->tx.ring[q_vector->tx.count] = tx_ring;
+ q_vector->tx.count++;
+ q_vector->tx.latency_range = I40E_LOW_LATENCY;
+ q_vector->num_ringpairs++;
+ q_vector->vsi = vsi;
+}
+
+/**
+ * i40e_vsi_map_rings_to_vectors - Maps descriptor rings to vectors
+ * @vsi: the VSI being configured
+ *
+ * This function maps descriptor rings to the queue-specific vectors
+ * we were allotted through the MSI-X enabling code. Ideally, we'd have
+ * one vector per queue pair, but on a constrained vector budget, we
+ * group the queue pairs as "efficiently" as possible.
+ **/
+static void i40e_vsi_map_rings_to_vectors(struct i40e_vsi *vsi)
+{
+ int qp_remaining = vsi->num_queue_pairs;
+ int q_vectors = vsi->num_q_vectors;
+ int qp_per_vector;
+ int v_start = 0;
+ int qp_idx = 0;
+
+ /* If we don't have enough vectors for a 1-to-1 mapping, we'll have to
+ * group them so there are multiple queues per vector.
+ */
+ for (; v_start < q_vectors && qp_remaining; v_start++) {
+ qp_per_vector = DIV_ROUND_UP(qp_remaining, q_vectors - v_start);
+ for (; qp_per_vector;
+ qp_per_vector--, qp_idx++, qp_remaining--) {
+ map_vector_to_rxq(vsi, v_start, qp_idx);
+ map_vector_to_txq(vsi, v_start, qp_idx);
+ }
+ }
+}
+
+/**
+ * i40e_vsi_request_irq - Request IRQ from the OS
+ * @vsi: the VSI being configured
+ * @basename: name for the vector
+ **/
+static int i40e_vsi_request_irq(struct i40e_vsi *vsi, char *basename)
+{
+ struct i40e_pf *pf = vsi->back;
+ int err;
+
+ if (pf->flags & I40E_FLAG_MSIX_ENABLED)
+ err = i40e_vsi_request_irq_msix(vsi, basename);
+ else if (pf->flags & I40E_FLAG_MSI_ENABLED)
+ err = request_irq(pf->pdev->irq, i40e_intr, 0,
+ pf->misc_int_name, pf);
+ else
+ err = request_irq(pf->pdev->irq, i40e_intr, IRQF_SHARED,
+ pf->misc_int_name, pf);
+
+ if (err)
+ dev_info(&pf->pdev->dev, "request_irq failed, Error %d\n", err);
+
+ return err;
+}
+
+#ifdef CONFIG_NET_POLL_CONTROLLER
+/**
+ * i40e_netpoll - A Polling 'interrupt'handler
+ * @netdev: network interface device structure
+ *
+ * This is used by netconsole to send skbs without having to re-enable
+ * interrupts. It's not called while the normal interrupt routine is executing.
+ **/
+static void i40e_netpoll(struct net_device *netdev)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+ struct i40e_pf *pf = vsi->back;
+ int i;
+
+ /* if interface is down do nothing */
+ if (test_bit(__I40E_DOWN, &vsi->state))
+ return;
+
+ pf->flags |= I40E_FLAG_IN_NETPOLL;
+ if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
+ for (i = 0; i < vsi->num_q_vectors; i++)
+ i40e_msix_clean_rings(0, &vsi->q_vectors[i]);
+ } else {
+ i40e_intr(pf->pdev->irq, netdev);
+ }
+ pf->flags &= ~I40E_FLAG_IN_NETPOLL;
+}
+#endif
+
+/**
+ * i40e_vsi_control_tx - Start or stop a VSI's rings
+ * @vsi: the VSI being configured
+ * @enable: start or stop the rings
+ **/
+static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable)
+{
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+ int i, j, pf_q;
+ u32 tx_reg;
+
+ pf_q = vsi->base_queue;
+ for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) {
+ j = 1000;
+ do {
+ usleep_range(1000, 2000);
+ tx_reg = rd32(hw, I40E_QTX_ENA(pf_q));
+ } while (j-- && ((tx_reg >> I40E_QTX_ENA_QENA_REQ_SHIFT)
+ ^ (tx_reg >> I40E_QTX_ENA_QENA_STAT_SHIFT)) & 1);
+
+ if (enable) {
+ /* is STAT set ? */
+ if ((tx_reg & I40E_QTX_ENA_QENA_STAT_MASK)) {
+ dev_info(&pf->pdev->dev,
+ "Tx %d already enabled\n", i);
+ continue;
+ }
+ } else {
+ /* is !STAT set ? */
+ if (!(tx_reg & I40E_QTX_ENA_QENA_STAT_MASK)) {
+ dev_info(&pf->pdev->dev,
+ "Tx %d already disabled\n", i);
+ continue;
+ }
+ }
+
+ /* turn on/off the queue */
+ if (enable)
+ tx_reg |= I40E_QTX_ENA_QENA_REQ_MASK |
+ I40E_QTX_ENA_QENA_STAT_MASK;
+ else
+ tx_reg &= ~I40E_QTX_ENA_QENA_REQ_MASK;
+
+ wr32(hw, I40E_QTX_ENA(pf_q), tx_reg);
+
+ /* wait for the change to finish */
+ for (j = 0; j < 10; j++) {
+ tx_reg = rd32(hw, I40E_QTX_ENA(pf_q));
+ if (enable) {
+ if ((tx_reg & I40E_QTX_ENA_QENA_STAT_MASK))
+ break;
+ } else {
+ if (!(tx_reg & I40E_QTX_ENA_QENA_STAT_MASK))
+ break;
+ }
+
+ udelay(10);
+ }
+ if (j >= 10) {
+ dev_info(&pf->pdev->dev, "Tx ring %d %sable timeout\n",
+ pf_q, (enable ? "en" : "dis"));
+ return -ETIMEDOUT;
+ }
+ }
+
+ return 0;
+}
+
+/**
+ * i40e_vsi_control_rx - Start or stop a VSI's rings
+ * @vsi: the VSI being configured
+ * @enable: start or stop the rings
+ **/
+static int i40e_vsi_control_rx(struct i40e_vsi *vsi, bool enable)
+{
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+ int i, j, pf_q;
+ u32 rx_reg;
+
+ pf_q = vsi->base_queue;
+ for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) {
+ j = 1000;
+ do {
+ usleep_range(1000, 2000);
+ rx_reg = rd32(hw, I40E_QRX_ENA(pf_q));
+ } while (j-- && ((rx_reg >> I40E_QRX_ENA_QENA_REQ_SHIFT)
+ ^ (rx_reg >> I40E_QRX_ENA_QENA_STAT_SHIFT)) & 1);
+
+ if (enable) {
+ /* is STAT set ? */
+ if ((rx_reg & I40E_QRX_ENA_QENA_STAT_MASK))
+ continue;
+ } else {
+ /* is !STAT set ? */
+ if (!(rx_reg & I40E_QRX_ENA_QENA_STAT_MASK))
+ continue;
+ }
+
+ /* turn on/off the queue */
+ if (enable)
+ rx_reg |= I40E_QRX_ENA_QENA_REQ_MASK |
+ I40E_QRX_ENA_QENA_STAT_MASK;
+ else
+ rx_reg &= ~(I40E_QRX_ENA_QENA_REQ_MASK |
+ I40E_QRX_ENA_QENA_STAT_MASK);
+ wr32(hw, I40E_QRX_ENA(pf_q), rx_reg);
+
+ /* wait for the change to finish */
+ for (j = 0; j < 10; j++) {
+ rx_reg = rd32(hw, I40E_QRX_ENA(pf_q));
+
+ if (enable) {
+ if ((rx_reg & I40E_QRX_ENA_QENA_STAT_MASK))
+ break;
+ } else {
+ if (!(rx_reg & I40E_QRX_ENA_QENA_STAT_MASK))
+ break;
+ }
+
+ udelay(10);
+ }
+ if (j >= 10) {
+ dev_info(&pf->pdev->dev, "Rx ring %d %sable timeout\n",
+ pf_q, (enable ? "en" : "dis"));
+ return -ETIMEDOUT;
+ }
+ }
+
+ return 0;
+}
+
+/**
+ * i40e_vsi_control_rings - Start or stop a VSI's rings
+ * @vsi: the VSI being configured
+ * @enable: start or stop the rings
+ **/
+static int i40e_vsi_control_rings(struct i40e_vsi *vsi, bool request)
+{
+ int ret;
+
+ /* do rx first for enable and last for disable */
+ if (request) {
+ ret = i40e_vsi_control_rx(vsi, request);
+ if (ret)
+ return ret;
+ ret = i40e_vsi_control_tx(vsi, request);
+ } else {
+ ret = i40e_vsi_control_tx(vsi, request);
+ if (ret)
+ return ret;
+ ret = i40e_vsi_control_rx(vsi, request);
+ }
+
+ return ret;
+}
+
+/**
+ * i40e_vsi_free_irq - Free the irq association with the OS
+ * @vsi: the VSI being configured
+ **/
+static void i40e_vsi_free_irq(struct i40e_vsi *vsi)
+{
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+ int base = vsi->base_vector;
+ u32 val, qp;
+ int i;
+
+ if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
+ if (!vsi->q_vectors)
+ return;
+
+ for (i = 0; i < vsi->num_q_vectors; i++) {
+ u16 vector = i + base;
+
+ /* free only the irqs that were actually requested */
+ if (vsi->q_vectors[i].num_ringpairs == 0)
+ continue;
+
+ /* clear the affinity_mask in the IRQ descriptor */
+ irq_set_affinity_hint(pf->msix_entries[vector].vector,
+ NULL);
+ free_irq(pf->msix_entries[vector].vector,
+ &vsi->q_vectors[i]);
+
+ /* Tear down the interrupt queue link list
+ *
+ * We know that they come in pairs and always
+ * the Rx first, then the Tx. To clear the
+ * link list, stick the EOL value into the
+ * next_q field of the registers.
+ */
+ val = rd32(hw, I40E_PFINT_LNKLSTN(vector - 1));
+ qp = (val & I40E_PFINT_LNKLSTN_FIRSTQ_INDX_MASK)
+ >> I40E_PFINT_LNKLSTN_FIRSTQ_INDX_SHIFT;
+ val |= I40E_QUEUE_END_OF_LIST
+ << I40E_PFINT_LNKLSTN_FIRSTQ_INDX_SHIFT;
+ wr32(hw, I40E_PFINT_LNKLSTN(vector - 1), val);
+
+ while (qp != I40E_QUEUE_END_OF_LIST) {
+ u32 next;
+
+ val = rd32(hw, I40E_QINT_RQCTL(qp));
+
+ val &= ~(I40E_QINT_RQCTL_MSIX_INDX_MASK |
+ I40E_QINT_RQCTL_MSIX0_INDX_MASK |
+ I40E_QINT_RQCTL_CAUSE_ENA_MASK |
+ I40E_QINT_RQCTL_INTEVENT_MASK);
+
+ val |= (I40E_QINT_RQCTL_ITR_INDX_MASK |
+ I40E_QINT_RQCTL_NEXTQ_INDX_MASK);
+
+ wr32(hw, I40E_QINT_RQCTL(qp), val);
+
+ val = rd32(hw, I40E_QINT_TQCTL(qp));
+
+ next = (val & I40E_QINT_TQCTL_NEXTQ_INDX_MASK)
+ >> I40E_QINT_TQCTL_NEXTQ_INDX_SHIFT;
+
+ val &= ~(I40E_QINT_TQCTL_MSIX_INDX_MASK |
+ I40E_QINT_TQCTL_MSIX0_INDX_MASK |
+ I40E_QINT_TQCTL_CAUSE_ENA_MASK |
+ I40E_QINT_TQCTL_INTEVENT_MASK);
+
+ val |= (I40E_QINT_TQCTL_ITR_INDX_MASK |
+ I40E_QINT_TQCTL_NEXTQ_INDX_MASK);
+
+ wr32(hw, I40E_QINT_TQCTL(qp), val);
+ qp = next;
+ }
+ }
+ } else {
+ free_irq(pf->pdev->irq, pf);
+
+ val = rd32(hw, I40E_PFINT_LNKLST0);
+ qp = (val & I40E_PFINT_LNKLSTN_FIRSTQ_INDX_MASK)
+ >> I40E_PFINT_LNKLSTN_FIRSTQ_INDX_SHIFT;
+ val |= I40E_QUEUE_END_OF_LIST
+ << I40E_PFINT_LNKLST0_FIRSTQ_INDX_SHIFT;
+ wr32(hw, I40E_PFINT_LNKLST0, val);
+
+ val = rd32(hw, I40E_QINT_RQCTL(qp));
+ val &= ~(I40E_QINT_RQCTL_MSIX_INDX_MASK |
+ I40E_QINT_RQCTL_MSIX0_INDX_MASK |
+ I40E_QINT_RQCTL_CAUSE_ENA_MASK |
+ I40E_QINT_RQCTL_INTEVENT_MASK);
+
+ val |= (I40E_QINT_RQCTL_ITR_INDX_MASK |
+ I40E_QINT_RQCTL_NEXTQ_INDX_MASK);
+
+ wr32(hw, I40E_QINT_RQCTL(qp), val);
+
+ val = rd32(hw, I40E_QINT_TQCTL(qp));
+
+ val &= ~(I40E_QINT_TQCTL_MSIX_INDX_MASK |
+ I40E_QINT_TQCTL_MSIX0_INDX_MASK |
+ I40E_QINT_TQCTL_CAUSE_ENA_MASK |
+ I40E_QINT_TQCTL_INTEVENT_MASK);
+
+ val |= (I40E_QINT_TQCTL_ITR_INDX_MASK |
+ I40E_QINT_TQCTL_NEXTQ_INDX_MASK);
+
+ wr32(hw, I40E_QINT_TQCTL(qp), val);
+ }
+}
+
+/**
+ * i40e_vsi_free_q_vectors - Free memory allocated for interrupt vectors
+ * @vsi: the VSI being un-configured
+ *
+ * This frees the memory allocated to the q_vectors and
+ * deletes references to the NAPI struct.
+ **/
+static void i40e_vsi_free_q_vectors(struct i40e_vsi *vsi)
+{
+ int v_idx;
+
+ for (v_idx = 0; v_idx < vsi->num_q_vectors; v_idx++) {
+ struct i40e_q_vector *q_vector = &vsi->q_vectors[v_idx];
+ int r_idx;
+
+ if (!q_vector)
+ continue;
+
+ /* disassociate q_vector from rings */
+ for (r_idx = 0; r_idx < q_vector->tx.count; r_idx++)
+ q_vector->tx.ring[r_idx]->q_vector = NULL;
+ for (r_idx = 0; r_idx < q_vector->rx.count; r_idx++)
+ q_vector->rx.ring[r_idx]->q_vector = NULL;
+
+ /* only VSI w/ an associated netdev is set up w/ NAPI */
+ if (vsi->netdev)
+ netif_napi_del(&q_vector->napi);
+ }
+ kfree(vsi->q_vectors);
+}
+
+/**
+ * i40e_reset_interrupt_capability - Disable interrupt setup in OS
+ * @pf: board private structure
+ **/
+static void i40e_reset_interrupt_capability(struct i40e_pf *pf)
+{
+ /* If we're in Legacy mode, the interrupt was cleaned in vsi_close */
+ if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
+ pci_disable_msix(pf->pdev);
+ kfree(pf->msix_entries);
+ pf->msix_entries = NULL;
+ } else if (pf->flags & I40E_FLAG_MSI_ENABLED) {
+ pci_disable_msi(pf->pdev);
+ }
+ pf->flags &= ~(I40E_FLAG_MSIX_ENABLED | I40E_FLAG_MSI_ENABLED);
+}
+
+/**
+ * i40e_clear_interrupt_scheme - Clear the current interrupt scheme settings
+ * @pf: board private structure
+ *
+ * We go through and clear interrupt specific resources and reset the structure
+ * to pre-load conditions
+ **/
+static void i40e_clear_interrupt_scheme(struct i40e_pf *pf)
+{
+ int i;
+
+ i40e_put_lump(pf->irq_pile, 0, I40E_PILE_VALID_BIT-1);
+ for (i = 0; i < pf->hw.func_caps.num_vsis; i++)
+ if (pf->vsi[i])
+ i40e_vsi_free_q_vectors(pf->vsi[i]);
+ i40e_reset_interrupt_capability(pf);
+}
+
+/**
+ * i40e_napi_enable_all - Enable NAPI for all q_vectors in the VSI
+ * @vsi: the VSI being configured
+ **/
+static void i40e_napi_enable_all(struct i40e_vsi *vsi)
+{
+ int q_idx;
+
+ if (!vsi->netdev)
+ return;
+
+ for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++)
+ napi_enable(&vsi->q_vectors[q_idx].napi);
+}
+
+/**
+ * i40e_napi_disable_all - Disable NAPI for all q_vectors in the VSI
+ * @vsi: the VSI being configured
+ **/
+static void i40e_napi_disable_all(struct i40e_vsi *vsi)
+{
+ int q_idx;
+
+ if (!vsi->netdev)
+ return;
+
+ for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++)
+ napi_disable(&vsi->q_vectors[q_idx].napi);
+}
+
+/**
+ * i40e_quiesce_vsi - Pause a given VSI
+ * @vsi: the VSI being paused
+ **/
+static void i40e_quiesce_vsi(struct i40e_vsi *vsi)
+{
+ if (test_bit(__I40E_DOWN, &vsi->state))
+ return;
+
+ set_bit(__I40E_NEEDS_RESTART, &vsi->state);
+ if (vsi->netdev && netif_running(vsi->netdev)) {
+ vsi->netdev->netdev_ops->ndo_stop(vsi->netdev);
+ } else {
+ set_bit(__I40E_DOWN, &vsi->state);
+ i40e_down(vsi);
+ }
+}
+
+/**
+ * i40e_unquiesce_vsi - Resume a given VSI
+ * @vsi: the VSI being resumed
+ **/
+static void i40e_unquiesce_vsi(struct i40e_vsi *vsi)
+{
+ if (!test_bit(__I40E_NEEDS_RESTART, &vsi->state))
+ return;
+
+ clear_bit(__I40E_NEEDS_RESTART, &vsi->state);
+ if (vsi->netdev && netif_running(vsi->netdev))
+ vsi->netdev->netdev_ops->ndo_open(vsi->netdev);
+ else
+ i40e_up(vsi); /* this clears the DOWN bit */
+}
+
+/**
+ * i40e_pf_quiesce_all_vsi - Pause all VSIs on a PF
+ * @pf: the PF
+ **/
+static void i40e_pf_quiesce_all_vsi(struct i40e_pf *pf)
+{
+ int v;
+
+ for (v = 0; v < pf->hw.func_caps.num_vsis; v++) {
+ if (pf->vsi[v])
+ i40e_quiesce_vsi(pf->vsi[v]);
+ }
+}
+
+/**
+ * i40e_pf_unquiesce_all_vsi - Resume all VSIs on a PF
+ * @pf: the PF
+ **/
+static void i40e_pf_unquiesce_all_vsi(struct i40e_pf *pf)
+{
+ int v;
+
+ for (v = 0; v < pf->hw.func_caps.num_vsis; v++) {
+ if (pf->vsi[v])
+ i40e_unquiesce_vsi(pf->vsi[v]);
+ }
+}
+
+/**
+ * i40e_dcb_get_num_tc - Get the number of TCs from DCBx config
+ * @dcbcfg: the corresponding DCBx configuration structure
+ *
+ * Return the number of TCs from given DCBx configuration
+ **/
+static u8 i40e_dcb_get_num_tc(struct i40e_dcbx_config *dcbcfg)
+{
+ int num_tc = 0, i;
+
+ /* Scan the ETS Config Priority Table to find
+ * traffic class enabled for a given priority
+ * and use the traffic class index to get the
+ * number of traffic classes enabled
+ */
+ for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
+ if (dcbcfg->etscfg.prioritytable[i] > num_tc)
+ num_tc = dcbcfg->etscfg.prioritytable[i];
+ }
+
+ /* Traffic class index starts from zero so
+ * increment to return the actual count
+ */
+ num_tc++;
+
+ return num_tc;
+}
+
+/**
+ * i40e_dcb_get_enabled_tc - Get enabled traffic classes
+ * @dcbcfg: the corresponding DCBx configuration structure
+ *
+ * Query the current DCB configuration and return the number of
+ * traffic classes enabled from the given DCBX config
+ **/
+static u8 i40e_dcb_get_enabled_tc(struct i40e_dcbx_config *dcbcfg)
+{
+ u8 num_tc = i40e_dcb_get_num_tc(dcbcfg);
+ u8 enabled_tc = 1;
+ u8 i;
+
+ for (i = 0; i < num_tc; i++)
+ enabled_tc |= 1 << i;
+
+ return enabled_tc;
+}
+
+/**
+ * i40e_pf_get_num_tc - Get enabled traffic classes for PF
+ * @pf: PF being queried
+ *
+ * Return number of traffic classes enabled for the given PF
+ **/
+static u8 i40e_pf_get_num_tc(struct i40e_pf *pf)
+{
+ struct i40e_hw *hw = &pf->hw;
+ u8 i, enabled_tc;
+ u8 num_tc = 0;
+ struct i40e_dcbx_config *dcbcfg = &hw->local_dcbx_config;
+
+ /* If DCB is not enabled then always in single TC */
+ if (!(pf->flags & I40E_FLAG_DCB_ENABLED))
+ return 1;
+
+ /* MFP mode return count of enabled TCs for this PF */
+ if (pf->flags & I40E_FLAG_MFP_ENABLED) {
+ enabled_tc = pf->hw.func_caps.enabled_tcmap;
+ for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
+ if (enabled_tc & (1 << i))
+ num_tc++;
+ }
+ return num_tc;
+ }
+
+ /* SFP mode will be enabled for all TCs on port */
+ return i40e_dcb_get_num_tc(dcbcfg);
+}
+
+/**
+ * i40e_pf_get_default_tc - Get bitmap for first enabled TC
+ * @pf: PF being queried
+ *
+ * Return a bitmap for first enabled traffic class for this PF.
+ **/
+static u8 i40e_pf_get_default_tc(struct i40e_pf *pf)
+{
+ u8 enabled_tc = pf->hw.func_caps.enabled_tcmap;
+ u8 i = 0;
+
+ if (!enabled_tc)
+ return 0x1; /* TC0 */
+
+ /* Find the first enabled TC */
+ for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
+ if (enabled_tc & (1 << i))
+ break;
+ }
+
+ return 1 << i;
+}
+
+/**
+ * i40e_pf_get_pf_tc_map - Get bitmap for enabled traffic classes
+ * @pf: PF being queried
+ *
+ * Return a bitmap for enabled traffic classes for this PF.
+ **/
+static u8 i40e_pf_get_tc_map(struct i40e_pf *pf)
+{
+ /* If DCB is not enabled for this PF then just return default TC */
+ if (!(pf->flags & I40E_FLAG_DCB_ENABLED))
+ return i40e_pf_get_default_tc(pf);
+
+ /* MFP mode will have enabled TCs set by FW */
+ if (pf->flags & I40E_FLAG_MFP_ENABLED)
+ return pf->hw.func_caps.enabled_tcmap;
+
+ /* SFP mode we want PF to be enabled for all TCs */
+ return i40e_dcb_get_enabled_tc(&pf->hw.local_dcbx_config);
+}
+
+/**
+ * i40e_vsi_get_bw_info - Query VSI BW Information
+ * @vsi: the VSI being queried
+ *
+ * Returns 0 on success, negative value on failure
+ **/
+static int i40e_vsi_get_bw_info(struct i40e_vsi *vsi)
+{
+ struct i40e_aqc_query_vsi_ets_sla_config_resp bw_ets_config = {0};
+ struct i40e_aqc_query_vsi_bw_config_resp bw_config = {0};
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+ u32 tc_bw_max;
+ int ret;
+ int i;
+
+ /* Get the VSI level BW configuration */
+ ret = i40e_aq_query_vsi_bw_config(hw, vsi->seid, &bw_config, NULL);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "couldn't get pf vsi bw config, err %d, aq_err %d\n",
+ ret, pf->hw.aq.asq_last_status);
+ return ret;
+ }
+
+ /* Get the VSI level BW configuration per TC */
+ ret = i40e_aq_query_vsi_ets_sla_config(hw, vsi->seid,
+ &bw_ets_config,
+ NULL);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "couldn't get pf vsi ets bw config, err %d, aq_err %d\n",
+ ret, pf->hw.aq.asq_last_status);
+ return ret;
+ }
+
+ if (bw_config.tc_valid_bits != bw_ets_config.tc_valid_bits) {
+ dev_info(&pf->pdev->dev,
+ "Enabled TCs mismatch from querying VSI BW info 0x%08x 0x%08x\n",
+ bw_config.tc_valid_bits,
+ bw_ets_config.tc_valid_bits);
+ /* Still continuing */
+ }
+
+ vsi->bw_limit = le16_to_cpu(bw_config.port_bw_limit);
+ vsi->bw_max_quanta = bw_config.max_bw;
+ tc_bw_max = le16_to_cpu(bw_ets_config.tc_bw_max[0]) |
+ (le16_to_cpu(bw_ets_config.tc_bw_max[1]) << 16);
+ for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
+ vsi->bw_ets_share_credits[i] = bw_ets_config.share_credits[i];
+ vsi->bw_ets_limit_credits[i] =
+ le16_to_cpu(bw_ets_config.credits[i]);
+ /* 3 bits out of 4 for each TC */
+ vsi->bw_ets_max_quanta[i] = (u8)((tc_bw_max >> (i*4)) & 0x7);
+ }
+ return ret;
+}
+
+/**
+ * i40e_vsi_configure_bw_alloc - Configure VSI BW allocation per TC
+ * @vsi: the VSI being configured
+ * @enabled_tc: TC bitmap
+ * @bw_credits: BW shared credits per TC
+ *
+ * Returns 0 on success, negative value on failure
+ **/
+static int i40e_vsi_configure_bw_alloc(struct i40e_vsi *vsi,
+ u8 enabled_tc,
+ u8 *bw_share)
+{
+ struct i40e_aqc_configure_vsi_tc_bw_data bw_data;
+ int i, ret = 0;
+
+ bw_data.tc_valid_bits = enabled_tc;
+ for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++)
+ bw_data.tc_bw_credits[i] = bw_share[i];
+
+ ret = i40e_aq_config_vsi_tc_bw(&vsi->back->hw, vsi->seid,
+ &bw_data, NULL);
+ if (ret) {
+ dev_info(&vsi->back->pdev->dev,
+ "%s: AQ command Config VSI BW allocation per TC failed = %d\n",
+ __func__, vsi->back->hw.aq.asq_last_status);
+ return ret;
+ }
+
+ for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++)
+ vsi->info.qs_handle[i] = bw_data.qs_handles[i];
+
+ return ret;
+}
+
+/**
+ * i40e_vsi_config_netdev_tc - Setup the netdev TC configuration
+ * @vsi: the VSI being configured
+ * @enabled_tc: TC map to be enabled
+ *
+ **/
+static void i40e_vsi_config_netdev_tc(struct i40e_vsi *vsi, u8 enabled_tc)
+{
+ struct net_device *netdev = vsi->netdev;
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+ u8 netdev_tc = 0;
+ int i;
+ struct i40e_dcbx_config *dcbcfg = &hw->local_dcbx_config;
+
+ if (!netdev)
+ return;
+
+ if (!enabled_tc) {
+ netdev_reset_tc(netdev);
+ return;
+ }
+
+ /* Set up actual enabled TCs on the VSI */
+ if (netdev_set_num_tc(netdev, vsi->tc_config.numtc))
+ return;
+
+ /* set per TC queues for the VSI */
+ for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
+ /* Only set TC queues for enabled tcs
+ *
+ * e.g. For a VSI that has TC0 and TC3 enabled the
+ * enabled_tc bitmap would be 0x00001001; the driver
+ * will set the numtc for netdev as 2 that will be
+ * referenced by the netdev layer as TC 0 and 1.
+ */
+ if (vsi->tc_config.enabled_tc & (1 << i))
+ netdev_set_tc_queue(netdev,
+ vsi->tc_config.tc_info[i].netdev_tc,
+ vsi->tc_config.tc_info[i].qcount,
+ vsi->tc_config.tc_info[i].qoffset);
+ }
+
+ /* Assign UP2TC map for the VSI */
+ for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
+ /* Get the actual TC# for the UP */
+ u8 ets_tc = dcbcfg->etscfg.prioritytable[i];
+ /* Get the mapped netdev TC# for the UP */
+ netdev_tc = vsi->tc_config.tc_info[ets_tc].netdev_tc;
+ netdev_set_prio_tc_map(netdev, i, netdev_tc);
+ }
+}
+
+/**
+ * i40e_vsi_update_queue_map - Update our copy of VSi info with new queue map
+ * @vsi: the VSI being configured
+ * @ctxt: the ctxt buffer returned from AQ VSI update param command
+ **/
+static void i40e_vsi_update_queue_map(struct i40e_vsi *vsi,
+ struct i40e_vsi_context *ctxt)
+{
+ /* copy just the sections touched not the entire info
+ * since not all sections are valid as returned by
+ * update vsi params
+ */
+ vsi->info.mapping_flags = ctxt->info.mapping_flags;
+ memcpy(&vsi->info.queue_mapping,
+ &ctxt->info.queue_mapping, sizeof(vsi->info.queue_mapping));
+ memcpy(&vsi->info.tc_mapping, ctxt->info.tc_mapping,
+ sizeof(vsi->info.tc_mapping));
+}
+
+/**
+ * i40e_vsi_config_tc - Configure VSI Tx Scheduler for given TC map
+ * @vsi: VSI to be configured
+ * @enabled_tc: TC bitmap
+ *
+ * This configures a particular VSI for TCs that are mapped to the
+ * given TC bitmap. It uses default bandwidth share for TCs across
+ * VSIs to configure TC for a particular VSI.
+ *
+ * NOTE:
+ * It is expected that the VSI queues have been quisced before calling
+ * this function.
+ **/
+static int i40e_vsi_config_tc(struct i40e_vsi *vsi, u8 enabled_tc)
+{
+ u8 bw_share[I40E_MAX_TRAFFIC_CLASS] = {0};
+ struct i40e_vsi_context ctxt;
+ int ret = 0;
+ int i;
+
+ /* Check if enabled_tc is same as existing or new TCs */
+ if (vsi->tc_config.enabled_tc == enabled_tc)
+ return ret;
+
+ /* Enable ETS TCs with equal BW Share for now across all VSIs */
+ for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
+ if (enabled_tc & (1 << i))
+ bw_share[i] = 1;
+ }
+
+ ret = i40e_vsi_configure_bw_alloc(vsi, enabled_tc, bw_share);
+ if (ret) {
+ dev_info(&vsi->back->pdev->dev,
+ "Failed configuring TC map %d for VSI %d\n",
+ enabled_tc, vsi->seid);
+ goto out;
+ }
+
+ /* Update Queue Pairs Mapping for currently enabled UPs */
+ ctxt.seid = vsi->seid;
+ ctxt.pf_num = vsi->back->hw.pf_id;
+ ctxt.vf_num = 0;
+ ctxt.uplink_seid = vsi->uplink_seid;
+ memcpy(&ctxt.info, &vsi->info, sizeof(vsi->info));
+ i40e_vsi_setup_queue_map(vsi, &ctxt, enabled_tc, false);
+
+ /* Update the VSI after updating the VSI queue-mapping information */
+ ret = i40e_aq_update_vsi_params(&vsi->back->hw, &ctxt, NULL);
+ if (ret) {
+ dev_info(&vsi->back->pdev->dev,
+ "update vsi failed, aq_err=%d\n",
+ vsi->back->hw.aq.asq_last_status);
+ goto out;
+ }
+ /* update the local VSI info with updated queue map */
+ i40e_vsi_update_queue_map(vsi, &ctxt);
+ vsi->info.valid_sections = 0;
+
+ /* Update current VSI BW information */
+ ret = i40e_vsi_get_bw_info(vsi);
+ if (ret) {
+ dev_info(&vsi->back->pdev->dev,
+ "Failed updating vsi bw info, aq_err=%d\n",
+ vsi->back->hw.aq.asq_last_status);
+ goto out;
+ }
+
+ /* Update the netdev TC setup */
+ i40e_vsi_config_netdev_tc(vsi, enabled_tc);
+out:
+ return ret;
+}
+
+/**
+ * i40e_up_complete - Finish the last steps of bringing up a connection
+ * @vsi: the VSI being configured
+ **/
+static int i40e_up_complete(struct i40e_vsi *vsi)
+{
+ struct i40e_pf *pf = vsi->back;
+ int err;
+
+ if (pf->flags & I40E_FLAG_MSIX_ENABLED)
+ i40e_vsi_configure_msix(vsi);
+ else
+ i40e_configure_msi_and_legacy(vsi);
+
+ /* start rings */
+ err = i40e_vsi_control_rings(vsi, true);
+ if (err)
+ return err;
+
+ clear_bit(__I40E_DOWN, &vsi->state);
+ i40e_napi_enable_all(vsi);
+ i40e_vsi_enable_irq(vsi);
+
+ if ((pf->hw.phy.link_info.link_info & I40E_AQ_LINK_UP) &&
+ (vsi->netdev)) {
+ netif_tx_start_all_queues(vsi->netdev);
+ netif_carrier_on(vsi->netdev);
+ }
+ i40e_service_event_schedule(pf);
+
+ return 0;
+}
+
+/**
+ * i40e_vsi_reinit_locked - Reset the VSI
+ * @vsi: the VSI being configured
+ *
+ * Rebuild the ring structs after some configuration
+ * has changed, e.g. MTU size.
+ **/
+static void i40e_vsi_reinit_locked(struct i40e_vsi *vsi)
+{
+ struct i40e_pf *pf = vsi->back;
+
+ WARN_ON(in_interrupt());
+ while (test_and_set_bit(__I40E_CONFIG_BUSY, &pf->state))
+ usleep_range(1000, 2000);
+ i40e_down(vsi);
+
+ /* Give a VF some time to respond to the reset. The
+ * two second wait is based upon the watchdog cycle in
+ * the VF driver.
+ */
+ if (vsi->type == I40E_VSI_SRIOV)
+ msleep(2000);
+ i40e_up(vsi);
+ clear_bit(__I40E_CONFIG_BUSY, &pf->state);
+}
+
+/**
+ * i40e_up - Bring the connection back up after being down
+ * @vsi: the VSI being configured
+ **/
+int i40e_up(struct i40e_vsi *vsi)
+{
+ int err;
+
+ err = i40e_vsi_configure(vsi);
+ if (!err)
+ err = i40e_up_complete(vsi);
+
+ return err;
+}
+
+/**
+ * i40e_down - Shutdown the connection processing
+ * @vsi: the VSI being stopped
+ **/
+void i40e_down(struct i40e_vsi *vsi)
+{
+ int i;
+
+ /* It is assumed that the caller of this function
+ * sets the vsi->state __I40E_DOWN bit.
+ */
+ if (vsi->netdev) {
+ netif_carrier_off(vsi->netdev);
+ netif_tx_disable(vsi->netdev);
+ }
+ i40e_vsi_disable_irq(vsi);
+ i40e_vsi_control_rings(vsi, false);
+ i40e_napi_disable_all(vsi);
+
+ for (i = 0; i < vsi->num_queue_pairs; i++) {
+ i40e_clean_tx_ring(&vsi->tx_rings[i]);
+ i40e_clean_rx_ring(&vsi->rx_rings[i]);
+ }
+}
+
+/**
+ * i40e_setup_tc - configure multiple traffic classes
+ * @netdev: net device to configure
+ * @tc: number of traffic classes to enable
+ **/
+static int i40e_setup_tc(struct net_device *netdev, u8 tc)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+ struct i40e_pf *pf = vsi->back;
+ u8 enabled_tc = 0;
+ int ret = -EINVAL;
+ int i;
+
+ /* Check if DCB enabled to continue */
+ if (!(pf->flags & I40E_FLAG_DCB_ENABLED)) {
+ netdev_info(netdev, "DCB is not enabled for adapter\n");
+ goto exit;
+ }
+
+ /* Check if MFP enabled */
+ if (pf->flags & I40E_FLAG_MFP_ENABLED) {
+ netdev_info(netdev, "Configuring TC not supported in MFP mode\n");
+ goto exit;
+ }
+
+ /* Check whether tc count is within enabled limit */
+ if (tc > i40e_pf_get_num_tc(pf)) {
+ netdev_info(netdev, "TC count greater than enabled on link for adapter\n");
+ goto exit;
+ }
+
+ /* Generate TC map for number of tc requested */
+ for (i = 0; i < tc; i++)
+ enabled_tc |= (1 << i);
+
+ /* Requesting same TC configuration as already enabled */
+ if (enabled_tc == vsi->tc_config.enabled_tc)
+ return 0;
+
+ /* Quiesce VSI queues */
+ i40e_quiesce_vsi(vsi);
+
+ /* Configure VSI for enabled TCs */
+ ret = i40e_vsi_config_tc(vsi, enabled_tc);
+ if (ret) {
+ netdev_info(netdev, "Failed configuring TC for VSI seid=%d\n",
+ vsi->seid);
+ goto exit;
+ }
+
+ /* Unquiesce VSI */
+ i40e_unquiesce_vsi(vsi);
+
+exit:
+ return ret;
+}
+
+/**
+ * i40e_open - Called when a network interface is made active
+ * @netdev: network interface device structure
+ *
+ * The open entry point is called when a network interface is made
+ * active by the system (IFF_UP). At this point all resources needed
+ * for transmit and receive operations are allocated, the interrupt
+ * handler is registered with the OS, the netdev watchdog subtask is
+ * enabled, and the stack is notified that the interface is ready.
+ *
+ * Returns 0 on success, negative value on failure
+ **/
+static int i40e_open(struct net_device *netdev)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+ struct i40e_pf *pf = vsi->back;
+ char int_name[IFNAMSIZ];
+ int err;
+
+ /* disallow open during test */
+ if (test_bit(__I40E_TESTING, &pf->state))
+ return -EBUSY;
+
+ netif_carrier_off(netdev);
+
+ /* allocate descriptors */
+ err = i40e_vsi_setup_tx_resources(vsi);
+ if (err)
+ goto err_setup_tx;
+ err = i40e_vsi_setup_rx_resources(vsi);
+ if (err)
+ goto err_setup_rx;
+
+ err = i40e_vsi_configure(vsi);
+ if (err)
+ goto err_setup_rx;
+
+ snprintf(int_name, sizeof(int_name) - 1, "%s-%s",
+ dev_driver_string(&pf->pdev->dev), netdev->name);
+ err = i40e_vsi_request_irq(vsi, int_name);
+ if (err)
+ goto err_setup_rx;
+
+ err = i40e_up_complete(vsi);
+ if (err)
+ goto err_up_complete;
+
+ if ((vsi->type == I40E_VSI_MAIN) || (vsi->type == I40E_VSI_VMDQ2)) {
+ err = i40e_aq_set_vsi_broadcast(&pf->hw, vsi->seid, true, NULL);
+ if (err)
+ netdev_info(netdev,
+ "couldn't set broadcast err %d aq_err %d\n",
+ err, pf->hw.aq.asq_last_status);
+ }
+
+ return 0;
+
+err_up_complete:
+ i40e_down(vsi);
+ i40e_vsi_free_irq(vsi);
+err_setup_rx:
+ i40e_vsi_free_rx_resources(vsi);
+err_setup_tx:
+ i40e_vsi_free_tx_resources(vsi);
+ if (vsi == pf->vsi[pf->lan_vsi])
+ i40e_do_reset(pf, (1 << __I40E_PF_RESET_REQUESTED));
+
+ return err;
+}
+
+/**
+ * i40e_close - Disables a network interface
+ * @netdev: network interface device structure
+ *
+ * The close entry point is called when an interface is de-activated
+ * by the OS. The hardware is still under the driver's control, but
+ * this netdev interface is disabled.
+ *
+ * Returns 0, this is not allowed to fail
+ **/
+static int i40e_close(struct net_device *netdev)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+
+ if (test_and_set_bit(__I40E_DOWN, &vsi->state))
+ return 0;
+
+ i40e_down(vsi);
+ i40e_vsi_free_irq(vsi);
+
+ i40e_vsi_free_tx_resources(vsi);
+ i40e_vsi_free_rx_resources(vsi);
+
+ return 0;
+}
+
+/**
+ * i40e_do_reset - Start a PF or Core Reset sequence
+ * @pf: board private structure
+ * @reset_flags: which reset is requested
+ *
+ * The essential difference in resets is that the PF Reset
+ * doesn't clear the packet buffers, doesn't reset the PE
+ * firmware, and doesn't bother the other PFs on the chip.
+ **/
+void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags)
+{
+ u32 val;
+
+ WARN_ON(in_interrupt());
+
+ /* do the biggest reset indicated */
+ if (reset_flags & (1 << __I40E_GLOBAL_RESET_REQUESTED)) {
+
+ /* Request a Global Reset
+ *
+ * This will start the chip's countdown to the actual full
+ * chip reset event, and a warning interrupt to be sent
+ * to all PFs, including the requestor. Our handler
+ * for the warning interrupt will deal with the shutdown
+ * and recovery of the switch setup.
+ */
+ dev_info(&pf->pdev->dev, "GlobalR requested\n");
+ val = rd32(&pf->hw, I40E_GLGEN_RTRIG);
+ val |= I40E_GLGEN_RTRIG_GLOBR_MASK;
+ wr32(&pf->hw, I40E_GLGEN_RTRIG, val);
+
+ } else if (reset_flags & (1 << __I40E_CORE_RESET_REQUESTED)) {
+
+ /* Request a Core Reset
+ *
+ * Same as Global Reset, except does *not* include the MAC/PHY
+ */
+ dev_info(&pf->pdev->dev, "CoreR requested\n");
+ val = rd32(&pf->hw, I40E_GLGEN_RTRIG);
+ val |= I40E_GLGEN_RTRIG_CORER_MASK;
+ wr32(&pf->hw, I40E_GLGEN_RTRIG, val);
+ i40e_flush(&pf->hw);
+
+ } else if (reset_flags & (1 << __I40E_PF_RESET_REQUESTED)) {
+
+ /* Request a PF Reset
+ *
+ * Resets only the PF-specific registers
+ *
+ * This goes directly to the tear-down and rebuild of
+ * the switch, since we need to do all the recovery as
+ * for the Core Reset.
+ */
+ dev_info(&pf->pdev->dev, "PFR requested\n");
+ i40e_handle_reset_warning(pf);
+
+ } else if (reset_flags & (1 << __I40E_REINIT_REQUESTED)) {
+ int v;
+
+ /* Find the VSI(s) that requested a re-init */
+ dev_info(&pf->pdev->dev,
+ "VSI reinit requested\n");
+ for (v = 0; v < pf->hw.func_caps.num_vsis; v++) {
+ struct i40e_vsi *vsi = pf->vsi[v];
+ if (vsi != NULL &&
+ test_bit(__I40E_REINIT_REQUESTED, &vsi->state)) {
+ i40e_vsi_reinit_locked(pf->vsi[v]);
+ clear_bit(__I40E_REINIT_REQUESTED, &vsi->state);
+ }
+ }
+
+ /* no further action needed, so return now */
+ return;
+ } else {
+ dev_info(&pf->pdev->dev,
+ "bad reset request 0x%08x\n", reset_flags);
+ return;
+ }
+}
+
+/**
+ * i40e_handle_lan_overflow_event - Handler for LAN queue overflow event
+ * @pf: board private structure
+ * @e: event info posted on ARQ
+ *
+ * Handler for LAN Queue Overflow Event generated by the firmware for PF
+ * and VF queues
+ **/
+static void i40e_handle_lan_overflow_event(struct i40e_pf *pf,
+ struct i40e_arq_event_info *e)
+{
+ struct i40e_aqc_lan_overflow *data =
+ (struct i40e_aqc_lan_overflow *)&e->desc.params.raw;
+ u32 queue = le32_to_cpu(data->prtdcb_rupto);
+ u32 qtx_ctl = le32_to_cpu(data->otx_ctl);
+ struct i40e_hw *hw = &pf->hw;
+ struct i40e_vf *vf;
+ u16 vf_id;
+
+ dev_info(&pf->pdev->dev, "%s: Rx Queue Number = %d QTX_CTL=0x%08x\n",
+ __func__, queue, qtx_ctl);
+
+ /* Queue belongs to VF, find the VF and issue VF reset */
+ if (((qtx_ctl & I40E_QTX_CTL_PFVF_Q_MASK)
+ >> I40E_QTX_CTL_PFVF_Q_SHIFT) == I40E_QTX_CTL_VF_QUEUE) {
+ vf_id = (u16)((qtx_ctl & I40E_QTX_CTL_VFVM_INDX_MASK)
+ >> I40E_QTX_CTL_VFVM_INDX_SHIFT);
+ vf_id -= hw->func_caps.vf_base_id;
+ vf = &pf->vf[vf_id];
+ i40e_vc_notify_vf_reset(vf);
+ /* Allow VF to process pending reset notification */
+ msleep(20);
+ i40e_reset_vf(vf, false);
+ }
+}
+
+/**
+ * i40e_service_event_complete - Finish up the service event
+ * @pf: board private structure
+ **/
+static void i40e_service_event_complete(struct i40e_pf *pf)
+{
+ BUG_ON(!test_bit(__I40E_SERVICE_SCHED, &pf->state));
+
+ /* flush memory to make sure state is correct before next watchog */
+ smp_mb__before_clear_bit();
+ clear_bit(__I40E_SERVICE_SCHED, &pf->state);
+}
+
+/**
+ * i40e_fdir_reinit_subtask - Worker thread to reinit FDIR filter table
+ * @pf: board private structure
+ **/
+static void i40e_fdir_reinit_subtask(struct i40e_pf *pf)
+{
+ if (!(pf->flags & I40E_FLAG_FDIR_REQUIRES_REINIT))
+ return;
+
+ pf->flags &= ~I40E_FLAG_FDIR_REQUIRES_REINIT;
+
+ /* if interface is down do nothing */
+ if (test_bit(__I40E_DOWN, &pf->state))
+ return;
+}
+
+/**
+ * i40e_vsi_link_event - notify VSI of a link event
+ * @vsi: vsi to be notified
+ * @link_up: link up or down
+ **/
+static void i40e_vsi_link_event(struct i40e_vsi *vsi, bool link_up)
+{
+ if (!vsi)
+ return;
+
+ switch (vsi->type) {
+ case I40E_VSI_MAIN:
+ if (!vsi->netdev || !vsi->netdev_registered)
+ break;
+
+ if (link_up) {
+ netif_carrier_on(vsi->netdev);
+ netif_tx_wake_all_queues(vsi->netdev);
+ } else {
+ netif_carrier_off(vsi->netdev);
+ netif_tx_stop_all_queues(vsi->netdev);
+ }
+ break;
+
+ case I40E_VSI_SRIOV:
+ break;
+
+ case I40E_VSI_VMDQ2:
+ case I40E_VSI_CTRL:
+ case I40E_VSI_MIRROR:
+ default:
+ /* there is no notification for other VSIs */
+ break;
+ }
+}
+
+/**
+ * i40e_veb_link_event - notify elements on the veb of a link event
+ * @veb: veb to be notified
+ * @link_up: link up or down
+ **/
+static void i40e_veb_link_event(struct i40e_veb *veb, bool link_up)
+{
+ struct i40e_pf *pf;
+ int i;
+
+ if (!veb || !veb->pf)
+ return;
+ pf = veb->pf;
+
+ /* depth first... */
+ for (i = 0; i < I40E_MAX_VEB; i++)
+ if (pf->veb[i] && (pf->veb[i]->uplink_seid == veb->seid))
+ i40e_veb_link_event(pf->veb[i], link_up);
+
+ /* ... now the local VSIs */
+ for (i = 0; i < pf->hw.func_caps.num_vsis; i++)
+ if (pf->vsi[i] && (pf->vsi[i]->uplink_seid == veb->seid))
+ i40e_vsi_link_event(pf->vsi[i], link_up);
+}
+
+/**
+ * i40e_link_event - Update netif_carrier status
+ * @pf: board private structure
+ **/
+static void i40e_link_event(struct i40e_pf *pf)
+{
+ bool new_link, old_link;
+
+ new_link = (pf->hw.phy.link_info.link_info & I40E_AQ_LINK_UP);
+ old_link = (pf->hw.phy.link_info_old.link_info & I40E_AQ_LINK_UP);
+
+ if (new_link == old_link)
+ return;
+
+ netdev_info(pf->vsi[pf->lan_vsi]->netdev,
+ "NIC Link is %s\n", (new_link ? "Up" : "Down"));
+
+ /* Notify the base of the switch tree connected to
+ * the link. Floating VEBs are not notified.
+ */
+ if (pf->lan_veb != I40E_NO_VEB && pf->veb[pf->lan_veb])
+ i40e_veb_link_event(pf->veb[pf->lan_veb], new_link);
+ else
+ i40e_vsi_link_event(pf->vsi[pf->lan_vsi], new_link);
+
+ if (pf->vf)
+ i40e_vc_notify_link_state(pf);
+}
+
+/**
+ * i40e_check_hang_subtask - Check for hung queues and dropped interrupts
+ * @pf: board private structure
+ *
+ * Set the per-queue flags to request a check for stuck queues in the irq
+ * clean functions, then force interrupts to be sure the irq clean is called.
+ **/
+static void i40e_check_hang_subtask(struct i40e_pf *pf)
+{
+ int i, v;
+
+ /* If we're down or resetting, just bail */
+ if (test_bit(__I40E_CONFIG_BUSY, &pf->state))
+ return;
+
+ /* for each VSI/netdev
+ * for each Tx queue
+ * set the check flag
+ * for each q_vector
+ * force an interrupt
+ */
+ for (v = 0; v < pf->hw.func_caps.num_vsis; v++) {
+ struct i40e_vsi *vsi = pf->vsi[v];
+ int armed = 0;
+
+ if (!pf->vsi[v] ||
+ test_bit(__I40E_DOWN, &vsi->state) ||
+ (vsi->netdev && !netif_carrier_ok(vsi->netdev)))
+ continue;
+
+ for (i = 0; i < vsi->num_queue_pairs; i++) {
+ set_check_for_tx_hang(&vsi->tx_rings[i]);
+ if (test_bit(__I40E_HANG_CHECK_ARMED,
+ &vsi->tx_rings[i].state))
+ armed++;
+ }
+
+ if (armed) {
+ if (!(pf->flags & I40E_FLAG_MSIX_ENABLED)) {
+ wr32(&vsi->back->hw, I40E_PFINT_DYN_CTL0,
+ (I40E_PFINT_DYN_CTL0_INTENA_MASK |
+ I40E_PFINT_DYN_CTL0_SWINT_TRIG_MASK));
+ } else {
+ u16 vec = vsi->base_vector - 1;
+ u32 val = (I40E_PFINT_DYN_CTLN_INTENA_MASK |
+ I40E_PFINT_DYN_CTLN_SWINT_TRIG_MASK);
+ for (i = 0; i < vsi->num_q_vectors; i++, vec++)
+ wr32(&vsi->back->hw,
+ I40E_PFINT_DYN_CTLN(vec), val);
+ }
+ i40e_flush(&vsi->back->hw);
+ }
+ }
+}
+
+/**
+ * i40e_watchdog_subtask - Check and bring link up
+ * @pf: board private structure
+ **/
+static void i40e_watchdog_subtask(struct i40e_pf *pf)
+{
+ int i;
+
+ /* if interface is down do nothing */
+ if (test_bit(__I40E_DOWN, &pf->state) ||
+ test_bit(__I40E_CONFIG_BUSY, &pf->state))
+ return;
+
+ /* Update the stats for active netdevs so the network stack
+ * can look at updated numbers whenever it cares to
+ */
+ for (i = 0; i < pf->hw.func_caps.num_vsis; i++)
+ if (pf->vsi[i] && pf->vsi[i]->netdev)
+ i40e_update_stats(pf->vsi[i]);
+
+ /* Update the stats for the active switching components */
+ for (i = 0; i < I40E_MAX_VEB; i++)
+ if (pf->veb[i])
+ i40e_update_veb_stats(pf->veb[i]);
+}
+
+/**
+ * i40e_reset_subtask - Set up for resetting the device and driver
+ * @pf: board private structure
+ **/
+static void i40e_reset_subtask(struct i40e_pf *pf)
+{
+ u32 reset_flags = 0;
+
+ if (test_bit(__I40E_REINIT_REQUESTED, &pf->state)) {
+ reset_flags |= (1 << __I40E_REINIT_REQUESTED);
+ clear_bit(__I40E_REINIT_REQUESTED, &pf->state);
+ }
+ if (test_bit(__I40E_PF_RESET_REQUESTED, &pf->state)) {
+ reset_flags |= (1 << __I40E_PF_RESET_REQUESTED);
+ clear_bit(__I40E_PF_RESET_REQUESTED, &pf->state);
+ }
+ if (test_bit(__I40E_CORE_RESET_REQUESTED, &pf->state)) {
+ reset_flags |= (1 << __I40E_CORE_RESET_REQUESTED);
+ clear_bit(__I40E_CORE_RESET_REQUESTED, &pf->state);
+ }
+ if (test_bit(__I40E_GLOBAL_RESET_REQUESTED, &pf->state)) {
+ reset_flags |= (1 << __I40E_GLOBAL_RESET_REQUESTED);
+ clear_bit(__I40E_GLOBAL_RESET_REQUESTED, &pf->state);
+ }
+
+ /* If there's a recovery already waiting, it takes
+ * precedence before starting a new reset sequence.
+ */
+ if (test_bit(__I40E_RESET_INTR_RECEIVED, &pf->state)) {
+ i40e_handle_reset_warning(pf);
+ return;
+ }
+
+ /* If we're already down or resetting, just bail */
+ if (reset_flags &&
+ !test_bit(__I40E_DOWN, &pf->state) &&
+ !test_bit(__I40E_CONFIG_BUSY, &pf->state))
+ i40e_do_reset(pf, reset_flags);
+}
+
+/**
+ * i40e_handle_link_event - Handle link event
+ * @pf: board private structure
+ * @e: event info posted on ARQ
+ **/
+static void i40e_handle_link_event(struct i40e_pf *pf,
+ struct i40e_arq_event_info *e)
+{
+ struct i40e_hw *hw = &pf->hw;
+ struct i40e_aqc_get_link_status *status =
+ (struct i40e_aqc_get_link_status *)&e->desc.params.raw;
+ struct i40e_link_status *hw_link_info = &hw->phy.link_info;
+
+ /* save off old link status information */
+ memcpy(&pf->hw.phy.link_info_old, hw_link_info,
+ sizeof(pf->hw.phy.link_info_old));
+
+ /* update link status */
+ hw_link_info->phy_type = (enum i40e_aq_phy_type)status->phy_type;
+ hw_link_info->link_speed = (enum i40e_aq_link_speed)status->link_speed;
+ hw_link_info->link_info = status->link_info;
+ hw_link_info->an_info = status->an_info;
+ hw_link_info->ext_info = status->ext_info;
+ hw_link_info->lse_enable =
+ le16_to_cpu(status->command_flags) &
+ I40E_AQ_LSE_ENABLE;
+
+ /* process the event */
+ i40e_link_event(pf);
+
+ /* Do a new status request to re-enable LSE reporting
+ * and load new status information into the hw struct,
+ * then see if the status changed while processing the
+ * initial event.
+ */
+ i40e_aq_get_link_info(&pf->hw, true, NULL, NULL);
+ i40e_link_event(pf);
+}
+
+/**
+ * i40e_clean_adminq_subtask - Clean the AdminQ rings
+ * @pf: board private structure
+ **/
+static void i40e_clean_adminq_subtask(struct i40e_pf *pf)
+{
+ struct i40e_arq_event_info event;
+ struct i40e_hw *hw = &pf->hw;
+ u16 pending, i = 0;
+ i40e_status ret;
+ u16 opcode;
+ u32 val;
+
+ if (!test_bit(__I40E_ADMINQ_EVENT_PENDING, &pf->state))
+ return;
+
+ event.msg_size = I40E_MAX_AQ_BUF_SIZE;
+ event.msg_buf = kzalloc(event.msg_size, GFP_KERNEL);
+ if (!event.msg_buf)
+ return;
+
+ do {
+ ret = i40e_clean_arq_element(hw, &event, &pending);
+ if (ret == I40E_ERR_ADMIN_QUEUE_NO_WORK) {
+ dev_info(&pf->pdev->dev, "No ARQ event found\n");
+ break;
+ } else if (ret) {
+ dev_info(&pf->pdev->dev, "ARQ event error %d\n", ret);
+ break;
+ }
+
+ opcode = le16_to_cpu(event.desc.opcode);
+ switch (opcode) {
+
+ case i40e_aqc_opc_get_link_status:
+ i40e_handle_link_event(pf, &event);
+ break;
+ case i40e_aqc_opc_send_msg_to_pf:
+ ret = i40e_vc_process_vf_msg(pf,
+ le16_to_cpu(event.desc.retval),
+ le32_to_cpu(event.desc.cookie_high),
+ le32_to_cpu(event.desc.cookie_low),
+ event.msg_buf,
+ event.msg_size);
+ break;
+ case i40e_aqc_opc_lldp_update_mib:
+ dev_info(&pf->pdev->dev, "ARQ: Update LLDP MIB event received\n");
+ break;
+ case i40e_aqc_opc_event_lan_overflow:
+ dev_info(&pf->pdev->dev, "ARQ LAN queue overflow event received\n");
+ i40e_handle_lan_overflow_event(pf, &event);
+ break;
+ default:
+ dev_info(&pf->pdev->dev,
+ "ARQ Error: Unknown event %d received\n",
+ event.desc.opcode);
+ break;
+ }
+ } while (pending && (i++ < pf->adminq_work_limit));
+
+ clear_bit(__I40E_ADMINQ_EVENT_PENDING, &pf->state);
+ /* re-enable Admin queue interrupt cause */
+ val = rd32(hw, I40E_PFINT_ICR0_ENA);
+ val |= I40E_PFINT_ICR0_ENA_ADMINQ_MASK;
+ wr32(hw, I40E_PFINT_ICR0_ENA, val);
+ i40e_flush(hw);
+
+ kfree(event.msg_buf);
+}
+
+/**
+ * i40e_reconstitute_veb - rebuild the VEB and anything connected to it
+ * @veb: pointer to the VEB instance
+ *
+ * This is a recursive function that first builds the attached VSIs then
+ * recurses in to build the next layer of VEB. We track the connections
+ * through our own index numbers because the seid's from the HW could
+ * change across the reset.
+ **/
+static int i40e_reconstitute_veb(struct i40e_veb *veb)
+{
+ struct i40e_vsi *ctl_vsi = NULL;
+ struct i40e_pf *pf = veb->pf;
+ int v, veb_idx;
+ int ret;
+
+ /* build VSI that owns this VEB, temporarily attached to base VEB */
+ for (v = 0; v < pf->hw.func_caps.num_vsis && !ctl_vsi; v++) {
+ if (pf->vsi[v] &&
+ pf->vsi[v]->veb_idx == veb->idx &&
+ pf->vsi[v]->flags & I40E_VSI_FLAG_VEB_OWNER) {
+ ctl_vsi = pf->vsi[v];
+ break;
+ }
+ }
+ if (!ctl_vsi) {
+ dev_info(&pf->pdev->dev,
+ "missing owner VSI for veb_idx %d\n", veb->idx);
+ ret = -ENOENT;
+ goto end_reconstitute;
+ }
+ if (ctl_vsi != pf->vsi[pf->lan_vsi])
+ ctl_vsi->uplink_seid = pf->vsi[pf->lan_vsi]->uplink_seid;
+ ret = i40e_add_vsi(ctl_vsi);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "rebuild of owner VSI failed: %d\n", ret);
+ goto end_reconstitute;
+ }
+ i40e_vsi_reset_stats(ctl_vsi);
+
+ /* create the VEB in the switch and move the VSI onto the VEB */
+ ret = i40e_add_veb(veb, ctl_vsi);
+ if (ret)
+ goto end_reconstitute;
+
+ /* create the remaining VSIs attached to this VEB */
+ for (v = 0; v < pf->hw.func_caps.num_vsis; v++) {
+ if (!pf->vsi[v] || pf->vsi[v] == ctl_vsi)
+ continue;
+
+ if (pf->vsi[v]->veb_idx == veb->idx) {
+ struct i40e_vsi *vsi = pf->vsi[v];
+ vsi->uplink_seid = veb->seid;
+ ret = i40e_add_vsi(vsi);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "rebuild of vsi_idx %d failed: %d\n",
+ v, ret);
+ goto end_reconstitute;
+ }
+ i40e_vsi_reset_stats(vsi);
+ }
+ }
+
+ /* create any VEBs attached to this VEB - RECURSION */
+ for (veb_idx = 0; veb_idx < I40E_MAX_VEB; veb_idx++) {
+ if (pf->veb[veb_idx] && pf->veb[veb_idx]->veb_idx == veb->idx) {
+ pf->veb[veb_idx]->uplink_seid = veb->seid;
+ ret = i40e_reconstitute_veb(pf->veb[veb_idx]);
+ if (ret)
+ break;
+ }
+ }
+
+end_reconstitute:
+ return ret;
+}
+
+/**
+ * i40e_get_capabilities - get info about the HW
+ * @pf: the PF struct
+ **/
+static int i40e_get_capabilities(struct i40e_pf *pf)
+{
+ struct i40e_aqc_list_capabilities_element_resp *cap_buf;
+ u16 data_size;
+ int buf_len;
+ int err;
+
+ buf_len = 40 * sizeof(struct i40e_aqc_list_capabilities_element_resp);
+ do {
+ cap_buf = kzalloc(buf_len, GFP_KERNEL);
+ if (!cap_buf)
+ return -ENOMEM;
+
+ /* this loads the data into the hw struct for us */
+ err = i40e_aq_discover_capabilities(&pf->hw, cap_buf, buf_len,
+ &data_size,
+ i40e_aqc_opc_list_func_capabilities,
+ NULL);
+ /* data loaded, buffer no longer needed */
+ kfree(cap_buf);
+
+ if (pf->hw.aq.asq_last_status == I40E_AQ_RC_ENOMEM) {
+ /* retry with a larger buffer */
+ buf_len = data_size;
+ } else if (pf->hw.aq.asq_last_status != I40E_AQ_RC_OK) {
+ dev_info(&pf->pdev->dev,
+ "capability discovery failed: aq=%d\n",
+ pf->hw.aq.asq_last_status);
+ return -ENODEV;
+ }
+ } while (err);
+
+ if (pf->hw.debug_mask & I40E_DEBUG_USER)
+ dev_info(&pf->pdev->dev,
+ "pf=%d, num_vfs=%d, msix_pf=%d, msix_vf=%d, fd_g=%d, fd_b=%d, pf_max_q=%d num_vsi=%d\n",
+ pf->hw.pf_id, pf->hw.func_caps.num_vfs,
+ pf->hw.func_caps.num_msix_vectors,
+ pf->hw.func_caps.num_msix_vectors_vf,
+ pf->hw.func_caps.fd_filters_guaranteed,
+ pf->hw.func_caps.fd_filters_best_effort,
+ pf->hw.func_caps.num_tx_qp,
+ pf->hw.func_caps.num_vsis);
+
+ return 0;
+}
+
+/**
+ * i40e_fdir_setup - initialize the Flow Director resources
+ * @pf: board private structure
+ **/
+static void i40e_fdir_setup(struct i40e_pf *pf)
+{
+ struct i40e_vsi *vsi;
+ bool new_vsi = false;
+ int err, i;
+
+ if (!(pf->flags & (I40E_FLAG_FDIR_ENABLED|I40E_FLAG_FDIR_ATR_ENABLED)))
+ return;
+
+ pf->atr_sample_rate = I40E_DEFAULT_ATR_SAMPLE_RATE;
+
+ /* find existing or make new FDIR VSI */
+ vsi = NULL;
+ for (i = 0; i < pf->hw.func_caps.num_vsis; i++)
+ if (pf->vsi[i] && pf->vsi[i]->type == I40E_VSI_FDIR)
+ vsi = pf->vsi[i];
+ if (!vsi) {
+ vsi = i40e_vsi_setup(pf, I40E_VSI_FDIR, pf->mac_seid, 0);
+ if (!vsi) {
+ dev_info(&pf->pdev->dev, "Couldn't create FDir VSI\n");
+ pf->flags &= ~I40E_FLAG_FDIR_ENABLED;
+ return;
+ }
+ new_vsi = true;
+ }
+ WARN_ON(vsi->base_queue != I40E_FDIR_RING);
+ i40e_vsi_setup_irqhandler(vsi, i40e_fdir_clean_rings);
+
+ err = i40e_vsi_setup_tx_resources(vsi);
+ if (!err)
+ err = i40e_vsi_setup_rx_resources(vsi);
+ if (!err)
+ err = i40e_vsi_configure(vsi);
+ if (!err && new_vsi) {
+ char int_name[IFNAMSIZ + 9];
+ snprintf(int_name, sizeof(int_name) - 1, "%s-fdir",
+ dev_driver_string(&pf->pdev->dev));
+ err = i40e_vsi_request_irq(vsi, int_name);
+ }
+ if (!err)
+ err = i40e_up_complete(vsi);
+
+ clear_bit(__I40E_NEEDS_RESTART, &vsi->state);
+}
+
+/**
+ * i40e_fdir_teardown - release the Flow Director resources
+ * @pf: board private structure
+ **/
+static void i40e_fdir_teardown(struct i40e_pf *pf)
+{
+ int i;
+
+ for (i = 0; i < pf->hw.func_caps.num_vsis; i++) {
+ if (pf->vsi[i] && pf->vsi[i]->type == I40E_VSI_FDIR) {
+ i40e_vsi_release(pf->vsi[i]);
+ break;
+ }
+ }
+}
+
+/**
+ * i40e_handle_reset_warning - prep for the core to reset
+ * @pf: board private structure
+ *
+ * Close up the VFs and other things in prep for a Core Reset,
+ * then get ready to rebuild the world.
+ **/
+static void i40e_handle_reset_warning(struct i40e_pf *pf)
+{
+ struct i40e_driver_version dv;
+ struct i40e_hw *hw = &pf->hw;
+ i40e_status ret;
+ u32 v;
+
+ clear_bit(__I40E_RESET_INTR_RECEIVED, &pf->state);
+ if (test_and_set_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state))
+ return;
+
+ dev_info(&pf->pdev->dev, "Tearing down internal switch for reset\n");
+
+ i40e_vc_notify_reset(pf);
+
+ /* quiesce the VSIs and their queues that are not already DOWN */
+ i40e_pf_quiesce_all_vsi(pf);
+
+ for (v = 0; v < pf->hw.func_caps.num_vsis; v++) {
+ if (pf->vsi[v])
+ pf->vsi[v]->seid = 0;
+ }
+
+ i40e_shutdown_adminq(&pf->hw);
+
+ /* Now we wait for GRST to settle out.
+ * We don't have to delete the VEBs or VSIs from the hw switch
+ * because the reset will make them disappear.
+ */
+ ret = i40e_pf_reset(hw);
+ if (ret)
+ dev_info(&pf->pdev->dev, "PF reset failed, %d\n", ret);
+ pf->pfr_count++;
+
+ if (test_bit(__I40E_DOWN, &pf->state))
+ goto end_core_reset;
+ dev_info(&pf->pdev->dev, "Rebuilding internal switch\n");
+
+ /* rebuild the basics for the AdminQ, HMC, and initial HW switch */
+ ret = i40e_init_adminq(&pf->hw);
+ if (ret) {
+ dev_info(&pf->pdev->dev, "Rebuild AdminQ failed, %d\n", ret);
+ goto end_core_reset;
+ }
+
+ ret = i40e_get_capabilities(pf);
+ if (ret) {
+ dev_info(&pf->pdev->dev, "i40e_get_capabilities failed, %d\n",
+ ret);
+ goto end_core_reset;
+ }
+
+ /* call shutdown HMC */
+ ret = i40e_shutdown_lan_hmc(hw);
+ if (ret) {
+ dev_info(&pf->pdev->dev, "shutdown_lan_hmc failed: %d\n", ret);
+ goto end_core_reset;
+ }
+
+ ret = i40e_init_lan_hmc(hw, hw->func_caps.num_tx_qp,
+ hw->func_caps.num_rx_qp,
+ pf->fcoe_hmc_cntx_num, pf->fcoe_hmc_filt_num);
+ if (ret) {
+ dev_info(&pf->pdev->dev, "init_lan_hmc failed: %d\n", ret);
+ goto end_core_reset;
+ }
+ ret = i40e_configure_lan_hmc(hw, I40E_HMC_MODEL_DIRECT_ONLY);
+ if (ret) {
+ dev_info(&pf->pdev->dev, "configure_lan_hmc failed: %d\n", ret);
+ goto end_core_reset;
+ }
+
+ /* do basic switch setup */
+ ret = i40e_setup_pf_switch(pf);
+ if (ret)
+ goto end_core_reset;
+
+ /* Rebuild the VSIs and VEBs that existed before reset.
+ * They are still in our local switch element arrays, so only
+ * need to rebuild the switch model in the HW.
+ *
+ * If there were VEBs but the reconstitution failed, we'll try
+ * try to recover minimal use by getting the basic PF VSI working.
+ */
+ if (pf->vsi[pf->lan_vsi]->uplink_seid != pf->mac_seid) {
+ dev_info(&pf->pdev->dev, "attempting to rebuild switch\n");
+ /* find the one VEB connected to the MAC, and find orphans */
+ for (v = 0; v < I40E_MAX_VEB; v++) {
+ if (!pf->veb[v])
+ continue;
+
+ if (pf->veb[v]->uplink_seid == pf->mac_seid ||
+ pf->veb[v]->uplink_seid == 0) {
+ ret = i40e_reconstitute_veb(pf->veb[v]);
+
+ if (!ret)
+ continue;
+
+ /* If Main VEB failed, we're in deep doodoo,
+ * so give up rebuilding the switch and set up
+ * for minimal rebuild of PF VSI.
+ * If orphan failed, we'll report the error
+ * but try to keep going.
+ */
+ if (pf->veb[v]->uplink_seid == pf->mac_seid) {
+ dev_info(&pf->pdev->dev,
+ "rebuild of switch failed: %d, will try to set up simple PF connection\n",
+ ret);
+ pf->vsi[pf->lan_vsi]->uplink_seid
+ = pf->mac_seid;
+ break;
+ } else if (pf->veb[v]->uplink_seid == 0) {
+ dev_info(&pf->pdev->dev,
+ "rebuild of orphan VEB failed: %d\n",
+ ret);
+ }
+ }
+ }
+ }
+
+ if (pf->vsi[pf->lan_vsi]->uplink_seid == pf->mac_seid) {
+ dev_info(&pf->pdev->dev, "attempting to rebuild PF VSI\n");
+ /* no VEB, so rebuild only the Main VSI */
+ ret = i40e_add_vsi(pf->vsi[pf->lan_vsi]);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "rebuild of Main VSI failed: %d\n", ret);
+ goto end_core_reset;
+ }
+ }
+
+ /* reinit the misc interrupt */
+ if (pf->flags & I40E_FLAG_MSIX_ENABLED)
+ ret = i40e_setup_misc_vector(pf);
+
+ /* restart the VSIs that were rebuilt and running before the reset */
+ i40e_pf_unquiesce_all_vsi(pf);
+
+ /* tell the firmware that we're starting */
+ dv.major_version = DRV_VERSION_MAJOR;
+ dv.minor_version = DRV_VERSION_MINOR;
+ dv.build_version = DRV_VERSION_BUILD;
+ dv.subbuild_version = 0;
+ i40e_aq_send_driver_version(&pf->hw, &dv, NULL);
+
+ dev_info(&pf->pdev->dev, "PF reset done\n");
+
+end_core_reset:
+ clear_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state);
+}
+
+/**
+ * i40e_handle_mdd_event
+ * @pf: pointer to the pf structure
+ *
+ * Called from the MDD irq handler to identify possibly malicious vfs
+ **/
+static void i40e_handle_mdd_event(struct i40e_pf *pf)
+{
+ struct i40e_hw *hw = &pf->hw;
+ bool mdd_detected = false;
+ struct i40e_vf *vf;
+ u32 reg;
+ int i;
+
+ if (!test_bit(__I40E_MDD_EVENT_PENDING, &pf->state))
+ return;
+
+ /* find what triggered the MDD event */
+ reg = rd32(hw, I40E_GL_MDET_TX);
+ if (reg & I40E_GL_MDET_TX_VALID_MASK) {
+ u8 func = (reg & I40E_GL_MDET_TX_FUNCTION_MASK)
+ >> I40E_GL_MDET_TX_FUNCTION_SHIFT;
+ u8 event = (reg & I40E_GL_MDET_TX_EVENT_SHIFT)
+ >> I40E_GL_MDET_TX_EVENT_SHIFT;
+ u8 queue = (reg & I40E_GL_MDET_TX_QUEUE_MASK)
+ >> I40E_GL_MDET_TX_QUEUE_SHIFT;
+ dev_info(&pf->pdev->dev,
+ "Malicious Driver Detection TX event 0x%02x on q %d of function 0x%02x\n",
+ event, queue, func);
+ wr32(hw, I40E_GL_MDET_TX, 0xffffffff);
+ mdd_detected = true;
+ }
+ reg = rd32(hw, I40E_GL_MDET_RX);
+ if (reg & I40E_GL_MDET_RX_VALID_MASK) {
+ u8 func = (reg & I40E_GL_MDET_RX_FUNCTION_MASK)
+ >> I40E_GL_MDET_RX_FUNCTION_SHIFT;
+ u8 event = (reg & I40E_GL_MDET_RX_EVENT_SHIFT)
+ >> I40E_GL_MDET_RX_EVENT_SHIFT;
+ u8 queue = (reg & I40E_GL_MDET_RX_QUEUE_MASK)
+ >> I40E_GL_MDET_RX_QUEUE_SHIFT;
+ dev_info(&pf->pdev->dev,
+ "Malicious Driver Detection RX event 0x%02x on q %d of function 0x%02x\n",
+ event, queue, func);
+ wr32(hw, I40E_GL_MDET_RX, 0xffffffff);
+ mdd_detected = true;
+ }
+
+ /* see if one of the VFs needs its hand slapped */
+ for (i = 0; i < pf->num_alloc_vfs && mdd_detected; i++) {
+ vf = &(pf->vf[i]);
+ reg = rd32(hw, I40E_VP_MDET_TX(i));
+ if (reg & I40E_VP_MDET_TX_VALID_MASK) {
+ wr32(hw, I40E_VP_MDET_TX(i), 0xFFFF);
+ vf->num_mdd_events++;
+ dev_info(&pf->pdev->dev, "MDD TX event on VF %d\n", i);
+ }
+
+ reg = rd32(hw, I40E_VP_MDET_RX(i));
+ if (reg & I40E_VP_MDET_RX_VALID_MASK) {
+ wr32(hw, I40E_VP_MDET_RX(i), 0xFFFF);
+ vf->num_mdd_events++;
+ dev_info(&pf->pdev->dev, "MDD RX event on VF %d\n", i);
+ }
+
+ if (vf->num_mdd_events > I40E_DEFAULT_NUM_MDD_EVENTS_ALLOWED) {
+ dev_info(&pf->pdev->dev,
+ "Too many MDD events on VF %d, disabled\n", i);
+ dev_info(&pf->pdev->dev,
+ "Use PF Control I/F to re-enable the VF\n");
+ set_bit(I40E_VF_STAT_DISABLED, &vf->vf_states);
+ }
+ }
+
+ /* re-enable mdd interrupt cause */
+ clear_bit(__I40E_MDD_EVENT_PENDING, &pf->state);
+ reg = rd32(hw, I40E_PFINT_ICR0_ENA);
+ reg |= I40E_PFINT_ICR0_ENA_MAL_DETECT_MASK;
+ wr32(hw, I40E_PFINT_ICR0_ENA, reg);
+ i40e_flush(hw);
+}
+
+/**
+ * i40e_service_task - Run the driver's async subtasks
+ * @work: pointer to work_struct containing our data
+ **/
+static void i40e_service_task(struct work_struct *work)
+{
+ struct i40e_pf *pf = container_of(work,
+ struct i40e_pf,
+ service_task);
+ unsigned long start_time = jiffies;
+
+ i40e_reset_subtask(pf);
+ i40e_handle_mdd_event(pf);
+ i40e_vc_process_vflr_event(pf);
+ i40e_watchdog_subtask(pf);
+ i40e_fdir_reinit_subtask(pf);
+ i40e_check_hang_subtask(pf);
+ i40e_sync_filters_subtask(pf);
+ i40e_clean_adminq_subtask(pf);
+
+ i40e_service_event_complete(pf);
+
+ /* If the tasks have taken longer than one timer cycle or there
+ * is more work to be done, reschedule the service task now
+ * rather than wait for the timer to tick again.
+ */
+ if (time_after(jiffies, (start_time + pf->service_timer_period)) ||
+ test_bit(__I40E_ADMINQ_EVENT_PENDING, &pf->state) ||
+ test_bit(__I40E_MDD_EVENT_PENDING, &pf->state) ||
+ test_bit(__I40E_VFLR_EVENT_PENDING, &pf->state))
+ i40e_service_event_schedule(pf);
+}
+
+/**
+ * i40e_service_timer - timer callback
+ * @data: pointer to PF struct
+ **/
+static void i40e_service_timer(unsigned long data)
+{
+ struct i40e_pf *pf = (struct i40e_pf *)data;
+
+ mod_timer(&pf->service_timer,
+ round_jiffies(jiffies + pf->service_timer_period));
+ i40e_service_event_schedule(pf);
+}
+
+/**
+ * i40e_set_num_rings_in_vsi - Determine number of rings in the VSI
+ * @vsi: the VSI being configured
+ **/
+static int i40e_set_num_rings_in_vsi(struct i40e_vsi *vsi)
+{
+ struct i40e_pf *pf = vsi->back;
+
+ switch (vsi->type) {
+ case I40E_VSI_MAIN:
+ vsi->alloc_queue_pairs = pf->num_lan_qps;
+ vsi->num_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
+ I40E_REQ_DESCRIPTOR_MULTIPLE);
+ if (pf->flags & I40E_FLAG_MSIX_ENABLED)
+ vsi->num_q_vectors = pf->num_lan_msix;
+ else
+ vsi->num_q_vectors = 1;
+
+ break;
+
+ case I40E_VSI_FDIR:
+ vsi->alloc_queue_pairs = 1;
+ vsi->num_desc = ALIGN(I40E_FDIR_RING_COUNT,
+ I40E_REQ_DESCRIPTOR_MULTIPLE);
+ vsi->num_q_vectors = 1;
+ break;
+
+ case I40E_VSI_VMDQ2:
+ vsi->alloc_queue_pairs = pf->num_vmdq_qps;
+ vsi->num_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
+ I40E_REQ_DESCRIPTOR_MULTIPLE);
+ vsi->num_q_vectors = pf->num_vmdq_msix;
+ break;
+
+ case I40E_VSI_SRIOV:
+ vsi->alloc_queue_pairs = pf->num_vf_qps;
+ vsi->num_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
+ I40E_REQ_DESCRIPTOR_MULTIPLE);
+ break;
+
+ default:
+ WARN_ON(1);
+ return -ENODATA;
+ }
+
+ return 0;
+}
+
+/**
+ * i40e_vsi_mem_alloc - Allocates the next available struct vsi in the PF
+ * @pf: board private structure
+ * @type: type of VSI
+ *
+ * On error: returns error code (negative)
+ * On success: returns vsi index in PF (positive)
+ **/
+static int i40e_vsi_mem_alloc(struct i40e_pf *pf, enum i40e_vsi_type type)
+{
+ int ret = -ENODEV;
+ struct i40e_vsi *vsi;
+ int vsi_idx;
+ int i;
+
+ /* Need to protect the allocation of the VSIs at the PF level */
+ mutex_lock(&pf->switch_mutex);
+
+ /* VSI list may be fragmented if VSI creation/destruction has
+ * been happening. We can afford to do a quick scan to look
+ * for any free VSIs in the list.
+ *
+ * find next empty vsi slot, looping back around if necessary
+ */
+ i = pf->next_vsi;
+ while (i < pf->hw.func_caps.num_vsis && pf->vsi[i])
+ i++;
+ if (i >= pf->hw.func_caps.num_vsis) {
+ i = 0;
+ while (i < pf->next_vsi && pf->vsi[i])
+ i++;
+ }
+
+ if (i < pf->hw.func_caps.num_vsis && !pf->vsi[i]) {
+ vsi_idx = i; /* Found one! */
+ } else {
+ ret = -ENODEV;
+ goto err_alloc_vsi; /* out of VSI slots! */
+ }
+ pf->next_vsi = ++i;
+
+ vsi = kzalloc(sizeof(*vsi), GFP_KERNEL);
+ if (!vsi) {
+ ret = -ENOMEM;
+ goto err_alloc_vsi;
+ }
+ vsi->type = type;
+ vsi->back = pf;
+ set_bit(__I40E_DOWN, &vsi->state);
+ vsi->flags = 0;
+ vsi->idx = vsi_idx;
+ vsi->rx_itr_setting = pf->rx_itr_default;
+ vsi->tx_itr_setting = pf->tx_itr_default;
+ vsi->netdev_registered = false;
+ vsi->work_limit = I40E_DEFAULT_IRQ_WORK;
+ INIT_LIST_HEAD(&vsi->mac_filter_list);
+
+ i40e_set_num_rings_in_vsi(vsi);
+
+ /* Setup default MSIX irq handler for VSI */
+ i40e_vsi_setup_irqhandler(vsi, i40e_msix_clean_rings);
+
+ pf->vsi[vsi_idx] = vsi;
+ ret = vsi_idx;
+err_alloc_vsi:
+ mutex_unlock(&pf->switch_mutex);
+ return ret;
+}
+
+/**
+ * i40e_vsi_clear - Deallocate the VSI provided
+ * @vsi: the VSI being un-configured
+ **/
+static int i40e_vsi_clear(struct i40e_vsi *vsi)
+{
+ struct i40e_pf *pf;
+
+ if (!vsi)
+ return 0;
+
+ if (!vsi->back)
+ goto free_vsi;
+ pf = vsi->back;
+
+ mutex_lock(&pf->switch_mutex);
+ if (!pf->vsi[vsi->idx]) {
+ dev_err(&pf->pdev->dev, "pf->vsi[%d] is NULL, just free vsi[%d](%p,type %d)\n",
+ vsi->idx, vsi->idx, vsi, vsi->type);
+ goto unlock_vsi;
+ }
+
+ if (pf->vsi[vsi->idx] != vsi) {
+ dev_err(&pf->pdev->dev,
+ "pf->vsi[%d](%p, type %d) != vsi[%d](%p,type %d): no free!\n",
+ pf->vsi[vsi->idx]->idx,
+ pf->vsi[vsi->idx],
+ pf->vsi[vsi->idx]->type,
+ vsi->idx, vsi, vsi->type);
+ goto unlock_vsi;
+ }
+
+ /* updates the pf for this cleared vsi */
+ i40e_put_lump(pf->qp_pile, vsi->base_queue, vsi->idx);
+ i40e_put_lump(pf->irq_pile, vsi->base_vector, vsi->idx);
+
+ pf->vsi[vsi->idx] = NULL;
+ if (vsi->idx < pf->next_vsi)
+ pf->next_vsi = vsi->idx;
+
+unlock_vsi:
+ mutex_unlock(&pf->switch_mutex);
+free_vsi:
+ kfree(vsi);
+
+ return 0;
+}
+
+/**
+ * i40e_alloc_rings - Allocates the Rx and Tx rings for the provided VSI
+ * @vsi: the VSI being configured
+ **/
+static int i40e_alloc_rings(struct i40e_vsi *vsi)
+{
+ struct i40e_pf *pf = vsi->back;
+ int ret = 0;
+ int i;
+
+ vsi->rx_rings = kcalloc(vsi->alloc_queue_pairs,
+ sizeof(struct i40e_ring), GFP_KERNEL);
+ if (!vsi->rx_rings) {
+ ret = -ENOMEM;
+ goto err_alloc_rings;
+ }
+
+ vsi->tx_rings = kcalloc(vsi->alloc_queue_pairs,
+ sizeof(struct i40e_ring), GFP_KERNEL);
+ if (!vsi->tx_rings) {
+ ret = -ENOMEM;
+ kfree(vsi->rx_rings);
+ goto err_alloc_rings;
+ }
+
+ /* Set basic values in the rings to be used later during open() */
+ for (i = 0; i < vsi->alloc_queue_pairs; i++) {
+ struct i40e_ring *rx_ring = &vsi->rx_rings[i];
+ struct i40e_ring *tx_ring = &vsi->tx_rings[i];
+
+ tx_ring->queue_index = i;
+ tx_ring->reg_idx = vsi->base_queue + i;
+ tx_ring->ring_active = false;
+ tx_ring->vsi = vsi;
+ tx_ring->netdev = vsi->netdev;
+ tx_ring->dev = &pf->pdev->dev;
+ tx_ring->count = vsi->num_desc;
+ tx_ring->size = 0;
+ tx_ring->dcb_tc = 0;
+
+ rx_ring->queue_index = i;
+ rx_ring->reg_idx = vsi->base_queue + i;
+ rx_ring->ring_active = false;
+ rx_ring->vsi = vsi;
+ rx_ring->netdev = vsi->netdev;
+ rx_ring->dev = &pf->pdev->dev;
+ rx_ring->count = vsi->num_desc;
+ rx_ring->size = 0;
+ rx_ring->dcb_tc = 0;
+ if (pf->flags & I40E_FLAG_16BYTE_RX_DESC_ENABLED)
+ set_ring_16byte_desc_enabled(rx_ring);
+ else
+ clear_ring_16byte_desc_enabled(rx_ring);
+ }
+
+err_alloc_rings:
+ return ret;
+}
+
+/**
+ * i40e_vsi_clear_rings - Deallocates the Rx and Tx rings for the provided VSI
+ * @vsi: the VSI being cleaned
+ **/
+static int i40e_vsi_clear_rings(struct i40e_vsi *vsi)
+{
+ if (vsi) {
+ kfree(vsi->rx_rings);
+ kfree(vsi->tx_rings);
+ }
+
+ return 0;
+}
+
+/**
+ * i40e_reserve_msix_vectors - Reserve MSI-X vectors in the kernel
+ * @pf: board private structure
+ * @vectors: the number of MSI-X vectors to request
+ *
+ * Returns the number of vectors reserved, or error
+ **/
+static int i40e_reserve_msix_vectors(struct i40e_pf *pf, int vectors)
+{
+ int err = 0;
+
+ pf->num_msix_entries = 0;
+ while (vectors >= I40E_MIN_MSIX) {
+ err = pci_enable_msix(pf->pdev, pf->msix_entries, vectors);
+ if (err == 0) {
+ /* good to go */
+ pf->num_msix_entries = vectors;
+ break;
+ } else if (err < 0) {
+ /* total failure */
+ dev_info(&pf->pdev->dev,
+ "MSI-X vector reservation failed: %d\n", err);
+ vectors = 0;
+ break;
+ } else {
+ /* err > 0 is the hint for retry */
+ dev_info(&pf->pdev->dev,
+ "MSI-X vectors wanted %d, retrying with %d\n",
+ vectors, err);
+ vectors = err;
+ }
+ }
+
+ if (vectors > 0 && vectors < I40E_MIN_MSIX) {
+ dev_info(&pf->pdev->dev,
+ "Couldn't get enough vectors, only %d available\n",
+ vectors);
+ vectors = 0;
+ }
+
+ return vectors;
+}
+
+/**
+ * i40e_init_msix - Setup the MSIX capability
+ * @pf: board private structure
+ *
+ * Work with the OS to set up the MSIX vectors needed.
+ *
+ * Returns 0 on success, negative on failure
+ **/
+static int i40e_init_msix(struct i40e_pf *pf)
+{
+ i40e_status err = 0;
+ struct i40e_hw *hw = &pf->hw;
+ int v_budget, i;
+ int vec;
+
+ if (!(pf->flags & I40E_FLAG_MSIX_ENABLED))
+ return -ENODEV;
+
+ /* The number of vectors we'll request will be comprised of:
+ * - Add 1 for "other" cause for Admin Queue events, etc.
+ * - The number of LAN queue pairs
+ * already adjusted for the NUMA node
+ * assumes symmetric Tx/Rx pairing
+ * - The number of VMDq pairs
+ * Once we count this up, try the request.
+ *
+ * If we can't get what we want, we'll simplify to nearly nothing
+ * and try again. If that still fails, we punt.
+ */
+ pf->num_lan_msix = pf->num_lan_qps;
+ pf->num_vmdq_msix = pf->num_vmdq_qps;
+ v_budget = 1 + pf->num_lan_msix;
+ v_budget += (pf->num_vmdq_vsis * pf->num_vmdq_msix);
+ if (pf->flags & I40E_FLAG_FDIR_ENABLED)
+ v_budget++;
+
+ /* Scale down if necessary, and the rings will share vectors */
+ v_budget = min_t(int, v_budget, hw->func_caps.num_msix_vectors);
+
+ pf->msix_entries = kcalloc(v_budget, sizeof(struct msix_entry),
+ GFP_KERNEL);
+ if (!pf->msix_entries)
+ return -ENOMEM;
+
+ for (i = 0; i < v_budget; i++)
+ pf->msix_entries[i].entry = i;
+ vec = i40e_reserve_msix_vectors(pf, v_budget);
+ if (vec < I40E_MIN_MSIX) {
+ pf->flags &= ~I40E_FLAG_MSIX_ENABLED;
+ kfree(pf->msix_entries);
+ pf->msix_entries = NULL;
+ return -ENODEV;
+
+ } else if (vec == I40E_MIN_MSIX) {
+ /* Adjust for minimal MSIX use */
+ dev_info(&pf->pdev->dev, "Features disabled, not enough MSIX vectors\n");
+ pf->flags &= ~I40E_FLAG_VMDQ_ENABLED;
+ pf->num_vmdq_vsis = 0;
+ pf->num_vmdq_qps = 0;
+ pf->num_vmdq_msix = 0;
+ pf->num_lan_qps = 1;
+ pf->num_lan_msix = 1;
+
+ } else if (vec != v_budget) {
+ /* Scale vector usage down */
+ pf->num_vmdq_msix = 1; /* force VMDqs to only one vector */
+ vec--; /* reserve the misc vector */
+
+ /* partition out the remaining vectors */
+ switch (vec) {
+ case 2:
+ pf->num_vmdq_vsis = 1;
+ pf->num_lan_msix = 1;
+ break;
+ case 3:
+ pf->num_vmdq_vsis = 1;
+ pf->num_lan_msix = 2;
+ break;
+ default:
+ pf->num_lan_msix = min_t(int, (vec / 2),
+ pf->num_lan_qps);
+ pf->num_vmdq_vsis = min_t(int, (vec - pf->num_lan_msix),
+ I40E_DEFAULT_NUM_VMDQ_VSI);
+ break;
+ }
+ }
+
+ return err;
+}
+
+/**
+ * i40e_alloc_q_vectors - Allocate memory for interrupt vectors
+ * @vsi: the VSI being configured
+ *
+ * We allocate one q_vector per queue interrupt. If allocation fails we
+ * return -ENOMEM.
+ **/
+static int i40e_alloc_q_vectors(struct i40e_vsi *vsi)
+{
+ struct i40e_pf *pf = vsi->back;
+ int v_idx, num_q_vectors;
+
+ /* if not MSIX, give the one vector only to the LAN VSI */
+ if (pf->flags & I40E_FLAG_MSIX_ENABLED)
+ num_q_vectors = vsi->num_q_vectors;
+ else if (vsi == pf->vsi[pf->lan_vsi])
+ num_q_vectors = 1;
+ else
+ return -EINVAL;
+
+ vsi->q_vectors = kcalloc(num_q_vectors,
+ sizeof(struct i40e_q_vector),
+ GFP_KERNEL);
+ if (!vsi->q_vectors)
+ return -ENOMEM;
+
+ for (v_idx = 0; v_idx < num_q_vectors; v_idx++) {
+ vsi->q_vectors[v_idx].vsi = vsi;
+ vsi->q_vectors[v_idx].v_idx = v_idx;
+ cpumask_set_cpu(v_idx, &vsi->q_vectors[v_idx].affinity_mask);
+ if (vsi->netdev)
+ netif_napi_add(vsi->netdev, &vsi->q_vectors[v_idx].napi,
+ i40e_napi_poll, vsi->work_limit);
+ }
+
+ return 0;
+}
+
+/**
+ * i40e_init_interrupt_scheme - Determine proper interrupt scheme
+ * @pf: board private structure to initialize
+ **/
+static void i40e_init_interrupt_scheme(struct i40e_pf *pf)
+{
+ int err = 0;
+
+ if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
+ err = i40e_init_msix(pf);
+ if (err) {
+ pf->flags &= ~(I40E_FLAG_RSS_ENABLED |
+ I40E_FLAG_MQ_ENABLED |
+ I40E_FLAG_DCB_ENABLED |
+ I40E_FLAG_SRIOV_ENABLED |
+ I40E_FLAG_FDIR_ENABLED |
+ I40E_FLAG_FDIR_ATR_ENABLED |
+ I40E_FLAG_VMDQ_ENABLED);
+
+ /* rework the queue expectations without MSIX */
+ i40e_determine_queue_usage(pf);
+ }
+ }
+
+ if (!(pf->flags & I40E_FLAG_MSIX_ENABLED) &&
+ (pf->flags & I40E_FLAG_MSI_ENABLED)) {
+ err = pci_enable_msi(pf->pdev);
+ if (err) {
+ dev_info(&pf->pdev->dev,
+ "MSI init failed (%d), trying legacy.\n", err);
+ pf->flags &= ~I40E_FLAG_MSI_ENABLED;
+ }
+ }
+
+ /* track first vector for misc interrupts */
+ err = i40e_get_lump(pf, pf->irq_pile, 1, I40E_PILE_VALID_BIT-1);
+}
+
+/**
+ * i40e_setup_misc_vector - Setup the misc vector to handle non queue events
+ * @pf: board private structure
+ *
+ * This sets up the handler for MSIX 0, which is used to manage the
+ * non-queue interrupts, e.g. AdminQ and errors. This is not used
+ * when in MSI or Legacy interrupt mode.
+ **/
+static int i40e_setup_misc_vector(struct i40e_pf *pf)
+{
+ struct i40e_hw *hw = &pf->hw;
+ int err = 0;
+
+ /* Only request the irq if this is the first time through, and
+ * not when we're rebuilding after a Reset
+ */
+ if (!test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state)) {
+ err = request_irq(pf->msix_entries[0].vector,
+ i40e_intr, 0, pf->misc_int_name, pf);
+ if (err) {
+ dev_info(&pf->pdev->dev,
+ "request_irq for msix_misc failed: %d\n", err);
+ return -EFAULT;
+ }
+ }
+
+ i40e_enable_misc_int_causes(hw);
+
+ /* associate no queues to the misc vector */
+ wr32(hw, I40E_PFINT_LNKLST0, I40E_QUEUE_END_OF_LIST);
+ wr32(hw, I40E_PFINT_ITR0(I40E_RX_ITR), I40E_ITR_8K);
+
+ i40e_flush(hw);
+
+ i40e_irq_dynamic_enable_icr0(pf);
+
+ return err;
+}
+
+/**
+ * i40e_config_rss - Prepare for RSS if used
+ * @pf: board private structure
+ **/
+static int i40e_config_rss(struct i40e_pf *pf)
+{
+ struct i40e_hw *hw = &pf->hw;
+ u32 lut = 0;
+ int i, j;
+ u64 hena;
+ /* Set of random keys generated using kernel random number generator */
+ static const u32 seed[I40E_PFQF_HKEY_MAX_INDEX + 1] = {0x41b01687,
+ 0x183cfd8c, 0xce880440, 0x580cbc3c, 0x35897377,
+ 0x328b25e1, 0x4fa98922, 0xb7d90c14, 0xd5bad70d,
+ 0xcd15a2c1, 0xe8580225, 0x4a1e9d11, 0xfe5731be};
+
+ /* Fill out hash function seed */
+ for (i = 0; i <= I40E_PFQF_HKEY_MAX_INDEX; i++)
+ wr32(hw, I40E_PFQF_HKEY(i), seed[i]);
+
+ /* By default we enable TCP/UDP with IPv4/IPv6 ptypes */
+ hena = (u64)rd32(hw, I40E_PFQF_HENA(0)) |
+ ((u64)rd32(hw, I40E_PFQF_HENA(1)) << 32);
+ hena |= ((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV4_UDP) |
+ ((u64)1 << I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) |
+ ((u64)1 << I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) |
+ ((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV4_TCP) |
+ ((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV6_TCP) |
+ ((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV6_UDP) |
+ ((u64)1 << I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) |
+ ((u64)1 << I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP) |
+ ((u64)1 << I40E_FILTER_PCTYPE_FRAG_IPV4)|
+ ((u64)1 << I40E_FILTER_PCTYPE_FRAG_IPV6);
+ wr32(hw, I40E_PFQF_HENA(0), (u32)hena);
+ wr32(hw, I40E_PFQF_HENA(1), (u32)(hena >> 32));
+
+ /* Populate the LUT with max no. of queues in round robin fashion */
+ for (i = 0, j = 0; i < pf->hw.func_caps.rss_table_size; i++, j++) {
+
+ /* The assumption is that lan qp count will be the highest
+ * qp count for any PF VSI that needs RSS.
+ * If multiple VSIs need RSS support, all the qp counts
+ * for those VSIs should be a power of 2 for RSS to work.
+ * If LAN VSI is the only consumer for RSS then this requirement
+ * is not necessary.
+ */
+ if (j == pf->rss_size)
+ j = 0;
+ /* lut = 4-byte sliding window of 4 lut entries */
+ lut = (lut << 8) | (j &
+ ((0x1 << pf->hw.func_caps.rss_table_entry_width) - 1));
+ /* On i = 3, we have 4 entries in lut; write to the register */
+ if ((i & 3) == 3)
+ wr32(hw, I40E_PFQF_HLUT(i >> 2), lut);
+ }
+ i40e_flush(hw);
+
+ return 0;
+}
+
+/**
+ * i40e_sw_init - Initialize general software structures (struct i40e_pf)
+ * @pf: board private structure to initialize
+ *
+ * i40e_sw_init initializes the Adapter private data structure.
+ * Fields are initialized based on PCI device information and
+ * OS network device settings (MTU size).
+ **/
+static int i40e_sw_init(struct i40e_pf *pf)
+{
+ int err = 0;
+ int size;
+
+ pf->msg_enable = netif_msg_init(I40E_DEFAULT_MSG_ENABLE,
+ (NETIF_MSG_DRV|NETIF_MSG_PROBE|NETIF_MSG_LINK));
+ if (debug != -1 && debug != I40E_DEFAULT_MSG_ENABLE) {
+ if (I40E_DEBUG_USER & debug)
+ pf->hw.debug_mask = debug;
+ pf->msg_enable = netif_msg_init((debug & ~I40E_DEBUG_USER),
+ I40E_DEFAULT_MSG_ENABLE);
+ }
+
+ /* Set default capability flags */
+ pf->flags = I40E_FLAG_RX_CSUM_ENABLED |
+ I40E_FLAG_MSI_ENABLED |
+ I40E_FLAG_MSIX_ENABLED |
+ I40E_FLAG_RX_PS_ENABLED |
+ I40E_FLAG_MQ_ENABLED |
+ I40E_FLAG_RX_1BUF_ENABLED;
+
+ pf->rss_size_max = 0x1 << pf->hw.func_caps.rss_table_entry_width;
+ if (pf->hw.func_caps.rss) {
+ pf->flags |= I40E_FLAG_RSS_ENABLED;
+ pf->rss_size = min_t(int, pf->rss_size_max,
+ nr_cpus_node(numa_node_id()));
+ } else {
+ pf->rss_size = 1;
+ }
+
+ if (pf->hw.func_caps.dcb)
+ pf->num_tc_qps = I40E_DEFAULT_QUEUES_PER_TC;
+ else
+ pf->num_tc_qps = 0;
+
+ if (pf->hw.func_caps.fd) {
+ /* FW/NVM is not yet fixed in this regard */
+ if ((pf->hw.func_caps.fd_filters_guaranteed > 0) ||
+ (pf->hw.func_caps.fd_filters_best_effort > 0)) {
+ pf->flags |= I40E_FLAG_FDIR_ATR_ENABLED;
+ dev_info(&pf->pdev->dev,
+ "Flow Director ATR mode Enabled\n");
+ pf->flags |= I40E_FLAG_FDIR_ENABLED;
+ dev_info(&pf->pdev->dev,
+ "Flow Director Side Band mode Enabled\n");
+ pf->fdir_pf_filter_count =
+ pf->hw.func_caps.fd_filters_guaranteed;
+ }
+ } else {
+ pf->fdir_pf_filter_count = 0;
+ }
+
+ if (pf->hw.func_caps.vmdq) {
+ pf->flags |= I40E_FLAG_VMDQ_ENABLED;
+ pf->num_vmdq_vsis = I40E_DEFAULT_NUM_VMDQ_VSI;
+ pf->num_vmdq_qps = I40E_DEFAULT_QUEUES_PER_VMDQ;
+ }
+
+ /* MFP mode enabled */
+ if (pf->hw.func_caps.npar_enable || pf->hw.func_caps.mfp_mode_1) {
+ pf->flags |= I40E_FLAG_MFP_ENABLED;
+ dev_info(&pf->pdev->dev, "MFP mode Enabled\n");
+ }
+
+#ifdef CONFIG_PCI_IOV
+ if (pf->hw.func_caps.num_vfs) {
+ pf->num_vf_qps = I40E_DEFAULT_QUEUES_PER_VF;
+ pf->flags |= I40E_FLAG_SRIOV_ENABLED;
+ pf->num_req_vfs = min_t(int,
+ pf->hw.func_caps.num_vfs,
+ I40E_MAX_VF_COUNT);
+ }
+#endif /* CONFIG_PCI_IOV */
+ pf->eeprom_version = 0xDEAD;
+ pf->lan_veb = I40E_NO_VEB;
+ pf->lan_vsi = I40E_NO_VSI;
+
+ /* set up queue assignment tracking */
+ size = sizeof(struct i40e_lump_tracking)
+ + (sizeof(u16) * pf->hw.func_caps.num_tx_qp);
+ pf->qp_pile = kzalloc(size, GFP_KERNEL);
+ if (!pf->qp_pile) {
+ err = -ENOMEM;
+ goto sw_init_done;
+ }
+ pf->qp_pile->num_entries = pf->hw.func_caps.num_tx_qp;
+ pf->qp_pile->search_hint = 0;
+
+ /* set up vector assignment tracking */
+ size = sizeof(struct i40e_lump_tracking)
+ + (sizeof(u16) * pf->hw.func_caps.num_msix_vectors);
+ pf->irq_pile = kzalloc(size, GFP_KERNEL);
+ if (!pf->irq_pile) {
+ kfree(pf->qp_pile);
+ err = -ENOMEM;
+ goto sw_init_done;
+ }
+ pf->irq_pile->num_entries = pf->hw.func_caps.num_msix_vectors;
+ pf->irq_pile->search_hint = 0;
+
+ mutex_init(&pf->switch_mutex);
+
+sw_init_done:
+ return err;
+}
+
+/**
+ * i40e_set_features - set the netdev feature flags
+ * @netdev: ptr to the netdev being adjusted
+ * @features: the feature set that the stack is suggesting
+ **/
+static int i40e_set_features(struct net_device *netdev,
+ netdev_features_t features)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+
+ if (features & NETIF_F_HW_VLAN_CTAG_RX)
+ i40e_vlan_stripping_enable(vsi);
+ else
+ i40e_vlan_stripping_disable(vsi);
+
+ return 0;
+}
+
+static const struct net_device_ops i40e_netdev_ops = {
+ .ndo_open = i40e_open,
+ .ndo_stop = i40e_close,
+ .ndo_start_xmit = i40e_lan_xmit_frame,
+ .ndo_get_stats64 = i40e_get_netdev_stats_struct,
+ .ndo_set_rx_mode = i40e_set_rx_mode,
+ .ndo_validate_addr = eth_validate_addr,
+ .ndo_set_mac_address = i40e_set_mac,
+ .ndo_change_mtu = i40e_change_mtu,
+ .ndo_tx_timeout = i40e_tx_timeout,
+ .ndo_vlan_rx_add_vid = i40e_vlan_rx_add_vid,
+ .ndo_vlan_rx_kill_vid = i40e_vlan_rx_kill_vid,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+ .ndo_poll_controller = i40e_netpoll,
+#endif
+ .ndo_setup_tc = i40e_setup_tc,
+ .ndo_set_features = i40e_set_features,
+ .ndo_set_vf_mac = i40e_ndo_set_vf_mac,
+ .ndo_set_vf_vlan = i40e_ndo_set_vf_port_vlan,
+ .ndo_set_vf_tx_rate = i40e_ndo_set_vf_bw,
+ .ndo_get_vf_config = i40e_ndo_get_vf_config,
+};
+
+/**
+ * i40e_config_netdev - Setup the netdev flags
+ * @vsi: the VSI being configured
+ *
+ * Returns 0 on success, negative value on failure
+ **/
+static int i40e_config_netdev(struct i40e_vsi *vsi)
+{
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+ struct i40e_netdev_priv *np;
+ struct net_device *netdev;
+ u8 mac_addr[ETH_ALEN];
+ int etherdev_size;
+
+ etherdev_size = sizeof(struct i40e_netdev_priv);
+ netdev = alloc_etherdev_mq(etherdev_size, vsi->alloc_queue_pairs);
+ if (!netdev)
+ return -ENOMEM;
+
+ vsi->netdev = netdev;
+ np = netdev_priv(netdev);
+ np->vsi = vsi;
+
+ netdev->hw_enc_features = NETIF_F_IP_CSUM |
+ NETIF_F_GSO_UDP_TUNNEL |
+ NETIF_F_TSO |
+ NETIF_F_SG;
+
+ netdev->features = NETIF_F_SG |
+ NETIF_F_IP_CSUM |
+ NETIF_F_SCTP_CSUM |
+ NETIF_F_HIGHDMA |
+ NETIF_F_GSO_UDP_TUNNEL |
+ NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_CTAG_RX |
+ NETIF_F_HW_VLAN_CTAG_FILTER |
+ NETIF_F_IPV6_CSUM |
+ NETIF_F_TSO |
+ NETIF_F_TSO6 |
+ NETIF_F_RXCSUM |
+ NETIF_F_RXHASH |
+ 0;
+
+ /* copy netdev features into list of user selectable features */
+ netdev->hw_features |= netdev->features;
+
+ if (vsi->type == I40E_VSI_MAIN) {
+ SET_NETDEV_DEV(netdev, &pf->pdev->dev);
+ memcpy(mac_addr, hw->mac.perm_addr, ETH_ALEN);
+ } else {
+ /* relate the VSI_VMDQ name to the VSI_MAIN name */
+ snprintf(netdev->name, IFNAMSIZ, "%sv%%d",
+ pf->vsi[pf->lan_vsi]->netdev->name);
+ random_ether_addr(mac_addr);
+ i40e_add_filter(vsi, mac_addr, I40E_VLAN_ANY, false, false);
+ }
+
+ memcpy(netdev->dev_addr, mac_addr, ETH_ALEN);
+ memcpy(netdev->perm_addr, mac_addr, ETH_ALEN);
+ /* vlan gets same features (except vlan offload)
+ * after any tweaks for specific VSI types
+ */
+ netdev->vlan_features = netdev->features & ~(NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_CTAG_RX |
+ NETIF_F_HW_VLAN_CTAG_FILTER);
+ netdev->priv_flags |= IFF_UNICAST_FLT;
+ netdev->priv_flags |= IFF_SUPP_NOFCS;
+ /* Setup netdev TC information */
+ i40e_vsi_config_netdev_tc(vsi, vsi->tc_config.enabled_tc);
+
+ netdev->netdev_ops = &i40e_netdev_ops;
+ netdev->watchdog_timeo = 5 * HZ;
+ i40e_set_ethtool_ops(netdev);
+
+ return 0;
+}
+
+/**
+ * i40e_vsi_delete - Delete a VSI from the switch
+ * @vsi: the VSI being removed
+ *
+ * Returns 0 on success, negative value on failure
+ **/
+static void i40e_vsi_delete(struct i40e_vsi *vsi)
+{
+ /* remove default VSI is not allowed */
+ if (vsi == vsi->back->vsi[vsi->back->lan_vsi])
+ return;
+
+ /* there is no HW VSI for FDIR */
+ if (vsi->type == I40E_VSI_FDIR)
+ return;
+
+ i40e_aq_delete_element(&vsi->back->hw, vsi->seid, NULL);
+ return;
+}
+
+/**
+ * i40e_add_vsi - Add a VSI to the switch
+ * @vsi: the VSI being configured
+ *
+ * This initializes a VSI context depending on the VSI type to be added and
+ * passes it down to the add_vsi aq command.
+ **/
+static int i40e_add_vsi(struct i40e_vsi *vsi)
+{
+ int ret = -ENODEV;
+ struct i40e_mac_filter *f, *ftmp;
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+ struct i40e_vsi_context ctxt;
+ u8 enabled_tc = 0x1; /* TC0 enabled */
+ int f_count = 0;
+
+ memset(&ctxt, 0, sizeof(ctxt));
+ switch (vsi->type) {
+ case I40E_VSI_MAIN:
+ /* The PF's main VSI is already setup as part of the
+ * device initialization, so we'll not bother with
+ * the add_vsi call, but we will retrieve the current
+ * VSI context.
+ */
+ ctxt.seid = pf->main_vsi_seid;
+ ctxt.pf_num = pf->hw.pf_id;
+ ctxt.vf_num = 0;
+ ret = i40e_aq_get_vsi_params(&pf->hw, &ctxt, NULL);
+ ctxt.flags = I40E_AQ_VSI_TYPE_PF;
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "couldn't get pf vsi config, err %d, aq_err %d\n",
+ ret, pf->hw.aq.asq_last_status);
+ return -ENOENT;
+ }
+ memcpy(&vsi->info, &ctxt.info, sizeof(ctxt.info));
+ vsi->info.valid_sections = 0;
+
+ vsi->seid = ctxt.seid;
+ vsi->id = ctxt.vsi_number;
+
+ enabled_tc = i40e_pf_get_tc_map(pf);
+
+ /* MFP mode setup queue map and update VSI */
+ if (pf->flags & I40E_FLAG_MFP_ENABLED) {
+ memset(&ctxt, 0, sizeof(ctxt));
+ ctxt.seid = pf->main_vsi_seid;
+ ctxt.pf_num = pf->hw.pf_id;
+ ctxt.vf_num = 0;
+ i40e_vsi_setup_queue_map(vsi, &ctxt, enabled_tc, false);
+ ret = i40e_aq_update_vsi_params(hw, &ctxt, NULL);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "update vsi failed, aq_err=%d\n",
+ pf->hw.aq.asq_last_status);
+ ret = -ENOENT;
+ goto err;
+ }
+ /* update the local VSI info queue map */
+ i40e_vsi_update_queue_map(vsi, &ctxt);
+ vsi->info.valid_sections = 0;
+ } else {
+ /* Default/Main VSI is only enabled for TC0
+ * reconfigure it to enable all TCs that are
+ * available on the port in SFP mode.
+ */
+ ret = i40e_vsi_config_tc(vsi, enabled_tc);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "failed to configure TCs for main VSI tc_map 0x%08x, err %d, aq_err %d\n",
+ enabled_tc, ret,
+ pf->hw.aq.asq_last_status);
+ ret = -ENOENT;
+ }
+ }
+ break;
+
+ case I40E_VSI_FDIR:
+ /* no queue mapping or actual HW VSI needed */
+ vsi->info.valid_sections = 0;
+ vsi->seid = 0;
+ vsi->id = 0;
+ i40e_vsi_setup_queue_map(vsi, &ctxt, enabled_tc, true);
+ return 0;
+ break;
+
+ case I40E_VSI_VMDQ2:
+ ctxt.pf_num = hw->pf_id;
+ ctxt.vf_num = 0;
+ ctxt.uplink_seid = vsi->uplink_seid;
+ ctxt.connection_type = 0x1; /* regular data port */
+ ctxt.flags = I40E_AQ_VSI_TYPE_VMDQ2;
+
+ ctxt.info.valid_sections |= cpu_to_le16(I40E_AQ_VSI_PROP_SWITCH_VALID);
+
+ /* This VSI is connected to VEB so the switch_id
+ * should be set to zero by default.
+ */
+ ctxt.info.switch_id = 0;
+ ctxt.info.switch_id |= cpu_to_le16(I40E_AQ_VSI_SW_ID_FLAG_LOCAL_LB);
+ ctxt.info.switch_id |= cpu_to_le16(I40E_AQ_VSI_SW_ID_FLAG_ALLOW_LB);
+
+ /* Setup the VSI tx/rx queue map for TC0 only for now */
+ i40e_vsi_setup_queue_map(vsi, &ctxt, enabled_tc, true);
+ break;
+
+ case I40E_VSI_SRIOV:
+ ctxt.pf_num = hw->pf_id;
+ ctxt.vf_num = vsi->vf_id + hw->func_caps.vf_base_id;
+ ctxt.uplink_seid = vsi->uplink_seid;
+ ctxt.connection_type = 0x1; /* regular data port */
+ ctxt.flags = I40E_AQ_VSI_TYPE_VF;
+
+ ctxt.info.valid_sections |= cpu_to_le16(I40E_AQ_VSI_PROP_SWITCH_VALID);
+
+ /* This VSI is connected to VEB so the switch_id
+ * should be set to zero by default.
+ */
+ ctxt.info.switch_id = cpu_to_le16(I40E_AQ_VSI_SW_ID_FLAG_ALLOW_LB);
+
+ ctxt.info.valid_sections |= cpu_to_le16(I40E_AQ_VSI_PROP_VLAN_VALID);
+ ctxt.info.port_vlan_flags |= I40E_AQ_VSI_PVLAN_MODE_ALL;
+ /* Setup the VSI tx/rx queue map for TC0 only for now */
+ i40e_vsi_setup_queue_map(vsi, &ctxt, enabled_tc, true);
+ break;
+
+ default:
+ return -ENODEV;
+ }
+
+ if (vsi->type != I40E_VSI_MAIN) {
+ ret = i40e_aq_add_vsi(hw, &ctxt, NULL);
+ if (ret) {
+ dev_info(&vsi->back->pdev->dev,
+ "add vsi failed, aq_err=%d\n",
+ vsi->back->hw.aq.asq_last_status);
+ ret = -ENOENT;
+ goto err;
+ }
+ memcpy(&vsi->info, &ctxt.info, sizeof(ctxt.info));
+ vsi->info.valid_sections = 0;
+ vsi->seid = ctxt.seid;
+ vsi->id = ctxt.vsi_number;
+ }
+
+ /* If macvlan filters already exist, force them to get loaded */
+ list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) {
+ f->changed = true;
+ f_count++;
+ }
+ if (f_count) {
+ vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED;
+ pf->flags |= I40E_FLAG_FILTER_SYNC;
+ }
+
+ /* Update VSI BW information */
+ ret = i40e_vsi_get_bw_info(vsi);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "couldn't get vsi bw info, err %d, aq_err %d\n",
+ ret, pf->hw.aq.asq_last_status);
+ /* VSI is already added so not tearing that up */
+ ret = 0;
+ }
+
+err:
+ return ret;
+}
+
+/**
+ * i40e_vsi_release - Delete a VSI and free its resources
+ * @vsi: the VSI being removed
+ *
+ * Returns 0 on success or < 0 on error
+ **/
+int i40e_vsi_release(struct i40e_vsi *vsi)
+{
+ struct i40e_mac_filter *f, *ftmp;
+ struct i40e_veb *veb = NULL;
+ struct i40e_pf *pf;
+ u16 uplink_seid;
+ int i, n;
+
+ pf = vsi->back;
+
+ /* release of a VEB-owner or last VSI is not allowed */
+ if (vsi->flags & I40E_VSI_FLAG_VEB_OWNER) {
+ dev_info(&pf->pdev->dev, "VSI %d has existing VEB %d\n",
+ vsi->seid, vsi->uplink_seid);
+ return -ENODEV;
+ }
+ if (vsi == pf->vsi[pf->lan_vsi] &&
+ !test_bit(__I40E_DOWN, &pf->state)) {
+ dev_info(&pf->pdev->dev, "Can't remove PF VSI\n");
+ return -ENODEV;
+ }
+
+ uplink_seid = vsi->uplink_seid;
+ if (vsi->type != I40E_VSI_SRIOV) {
+ if (vsi->netdev_registered) {
+ vsi->netdev_registered = false;
+ if (vsi->netdev) {
+ /* results in a call to i40e_close() */
+ unregister_netdev(vsi->netdev);
+ free_netdev(vsi->netdev);
+ vsi->netdev = NULL;
+ }
+ } else {
+ if (!test_and_set_bit(__I40E_DOWN, &vsi->state))
+ i40e_down(vsi);
+ i40e_vsi_free_irq(vsi);
+ i40e_vsi_free_tx_resources(vsi);
+ i40e_vsi_free_rx_resources(vsi);
+ }
+ i40e_vsi_disable_irq(vsi);
+ }
+
+ list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list)
+ i40e_del_filter(vsi, f->macaddr, f->vlan,
+ f->is_vf, f->is_netdev);
+ i40e_sync_vsi_filters(vsi);
+
+ i40e_vsi_delete(vsi);
+ i40e_vsi_free_q_vectors(vsi);
+ i40e_vsi_clear_rings(vsi);
+ i40e_vsi_clear(vsi);
+
+ /* If this was the last thing on the VEB, except for the
+ * controlling VSI, remove the VEB, which puts the controlling
+ * VSI onto the next level down in the switch.
+ *
+ * Well, okay, there's one more exception here: don't remove
+ * the orphan VEBs yet. We'll wait for an explicit remove request
+ * from up the network stack.
+ */
+ for (n = 0, i = 0; i < pf->hw.func_caps.num_vsis; i++) {
+ if (pf->vsi[i] &&
+ pf->vsi[i]->uplink_seid == uplink_seid &&
+ (pf->vsi[i]->flags & I40E_VSI_FLAG_VEB_OWNER) == 0) {
+ n++; /* count the VSIs */
+ }
+ }
+ for (i = 0; i < I40E_MAX_VEB; i++) {
+ if (!pf->veb[i])
+ continue;
+ if (pf->veb[i]->uplink_seid == uplink_seid)
+ n++; /* count the VEBs */
+ if (pf->veb[i]->seid == uplink_seid)
+ veb = pf->veb[i];
+ }
+ if (n == 0 && veb && veb->uplink_seid != 0)
+ i40e_veb_release(veb);
+
+ return 0;
+}
+
+/**
+ * i40e_vsi_setup_vectors - Set up the q_vectors for the given VSI
+ * @vsi: ptr to the VSI
+ *
+ * This should only be called after i40e_vsi_mem_alloc() which allocates the
+ * corresponding SW VSI structure and initializes num_queue_pairs for the
+ * newly allocated VSI.
+ *
+ * Returns 0 on success or negative on failure
+ **/
+static int i40e_vsi_setup_vectors(struct i40e_vsi *vsi)
+{
+ int ret = -ENOENT;
+ struct i40e_pf *pf = vsi->back;
+
+ if (vsi->q_vectors) {
+ dev_info(&pf->pdev->dev, "VSI %d has existing q_vectors\n",
+ vsi->seid);
+ return -EEXIST;
+ }
+
+ if (vsi->base_vector) {
+ dev_info(&pf->pdev->dev,
+ "VSI %d has non-zero base vector %d\n",
+ vsi->seid, vsi->base_vector);
+ return -EEXIST;
+ }
+
+ ret = i40e_alloc_q_vectors(vsi);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "failed to allocate %d q_vector for VSI %d, ret=%d\n",
+ vsi->num_q_vectors, vsi->seid, ret);
+ vsi->num_q_vectors = 0;
+ goto vector_setup_out;
+ }
+
+ vsi->base_vector = i40e_get_lump(pf, pf->irq_pile,
+ vsi->num_q_vectors, vsi->idx);
+ if (vsi->base_vector < 0) {
+ dev_info(&pf->pdev->dev,
+ "failed to get q tracking for VSI %d, err=%d\n",
+ vsi->seid, vsi->base_vector);
+ i40e_vsi_free_q_vectors(vsi);
+ ret = -ENOENT;
+ goto vector_setup_out;
+ }
+
+vector_setup_out:
+ return ret;
+}
+
+/**
+ * i40e_vsi_setup - Set up a VSI by a given type
+ * @pf: board private structure
+ * @type: VSI type
+ * @uplink_seid: the switch element to link to
+ * @param1: usage depends upon VSI type. For VF types, indicates VF id
+ *
+ * This allocates the sw VSI structure and its queue resources, then add a VSI
+ * to the identified VEB.
+ *
+ * Returns pointer to the successfully allocated and configure VSI sw struct on
+ * success, otherwise returns NULL on failure.
+ **/
+struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type,
+ u16 uplink_seid, u32 param1)
+{
+ struct i40e_vsi *vsi = NULL;
+ struct i40e_veb *veb = NULL;
+ int ret, i;
+ int v_idx;
+
+ /* The requested uplink_seid must be either
+ * - the PF's port seid
+ * no VEB is needed because this is the PF
+ * or this is a Flow Director special case VSI
+ * - seid of an existing VEB
+ * - seid of a VSI that owns an existing VEB
+ * - seid of a VSI that doesn't own a VEB
+ * a new VEB is created and the VSI becomes the owner
+ * - seid of the PF VSI, which is what creates the first VEB
+ * this is a special case of the previous
+ *
+ * Find which uplink_seid we were given and create a new VEB if needed
+ */
+ for (i = 0; i < I40E_MAX_VEB; i++) {
+ if (pf->veb[i] && pf->veb[i]->seid == uplink_seid) {
+ veb = pf->veb[i];
+ break;
+ }
+ }
+
+ if (!veb && uplink_seid != pf->mac_seid) {
+
+ for (i = 0; i < pf->hw.func_caps.num_vsis; i++) {
+ if (pf->vsi[i] && pf->vsi[i]->seid == uplink_seid) {
+ vsi = pf->vsi[i];
+ break;
+ }
+ }
+ if (!vsi) {
+ dev_info(&pf->pdev->dev, "no such uplink_seid %d\n",
+ uplink_seid);
+ return NULL;
+ }
+
+ if (vsi->uplink_seid == pf->mac_seid)
+ veb = i40e_veb_setup(pf, 0, pf->mac_seid, vsi->seid,
+ vsi->tc_config.enabled_tc);
+ else if ((vsi->flags & I40E_VSI_FLAG_VEB_OWNER) == 0)
+ veb = i40e_veb_setup(pf, 0, vsi->uplink_seid, vsi->seid,
+ vsi->tc_config.enabled_tc);
+
+ for (i = 0; i < I40E_MAX_VEB && !veb; i++) {
+ if (pf->veb[i] && pf->veb[i]->seid == vsi->uplink_seid)
+ veb = pf->veb[i];
+ }
+ if (!veb) {
+ dev_info(&pf->pdev->dev, "couldn't add VEB\n");
+ return NULL;
+ }
+
+ vsi->flags |= I40E_VSI_FLAG_VEB_OWNER;
+ uplink_seid = veb->seid;
+ }
+
+ /* get vsi sw struct */
+ v_idx = i40e_vsi_mem_alloc(pf, type);
+ if (v_idx < 0)
+ goto err_alloc;
+ vsi = pf->vsi[v_idx];
+ vsi->type = type;
+ vsi->veb_idx = (veb ? veb->idx : I40E_NO_VEB);
+
+ if (type == I40E_VSI_MAIN)
+ pf->lan_vsi = v_idx;
+ else if (type == I40E_VSI_SRIOV)
+ vsi->vf_id = param1;
+ /* assign it some queues */
+ ret = i40e_get_lump(pf, pf->qp_pile, vsi->alloc_queue_pairs, vsi->idx);
+ if (ret < 0) {
+ dev_info(&pf->pdev->dev, "VSI %d get_lump failed %d\n",
+ vsi->seid, ret);
+ goto err_vsi;
+ }
+ vsi->base_queue = ret;
+
+ /* get a VSI from the hardware */
+ vsi->uplink_seid = uplink_seid;
+ ret = i40e_add_vsi(vsi);
+ if (ret)
+ goto err_vsi;
+
+ switch (vsi->type) {
+ /* setup the netdev if needed */
+ case I40E_VSI_MAIN:
+ case I40E_VSI_VMDQ2:
+ ret = i40e_config_netdev(vsi);
+ if (ret)
+ goto err_netdev;
+ ret = register_netdev(vsi->netdev);
+ if (ret)
+ goto err_netdev;
+ vsi->netdev_registered = true;
+ netif_carrier_off(vsi->netdev);
+ /* fall through */
+
+ case I40E_VSI_FDIR:
+ /* set up vectors and rings if needed */
+ ret = i40e_vsi_setup_vectors(vsi);
+ if (ret)
+ goto err_msix;
+
+ ret = i40e_alloc_rings(vsi);
+ if (ret)
+ goto err_rings;
+
+ /* map all of the rings to the q_vectors */
+ i40e_vsi_map_rings_to_vectors(vsi);
+
+ i40e_vsi_reset_stats(vsi);
+ break;
+
+ default:
+ /* no netdev or rings for the other VSI types */
+ break;
+ }
+
+ return vsi;
+
+err_rings:
+ i40e_vsi_free_q_vectors(vsi);
+err_msix:
+ if (vsi->netdev_registered) {
+ vsi->netdev_registered = false;
+ unregister_netdev(vsi->netdev);
+ free_netdev(vsi->netdev);
+ vsi->netdev = NULL;
+ }
+err_netdev:
+ i40e_aq_delete_element(&pf->hw, vsi->seid, NULL);
+err_vsi:
+ i40e_vsi_clear(vsi);
+err_alloc:
+ return NULL;
+}
+
+/**
+ * i40e_veb_get_bw_info - Query VEB BW information
+ * @veb: the veb to query
+ *
+ * Query the Tx scheduler BW configuration data for given VEB
+ **/
+static int i40e_veb_get_bw_info(struct i40e_veb *veb)
+{
+ struct i40e_aqc_query_switching_comp_ets_config_resp ets_data;
+ struct i40e_aqc_query_switching_comp_bw_config_resp bw_data;
+ struct i40e_pf *pf = veb->pf;
+ struct i40e_hw *hw = &pf->hw;
+ u32 tc_bw_max;
+ int ret = 0;
+ int i;
+
+ ret = i40e_aq_query_switch_comp_bw_config(hw, veb->seid,
+ &bw_data, NULL);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "query veb bw config failed, aq_err=%d\n",
+ hw->aq.asq_last_status);
+ goto out;
+ }
+
+ ret = i40e_aq_query_switch_comp_ets_config(hw, veb->seid,
+ &ets_data, NULL);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "query veb bw ets config failed, aq_err=%d\n",
+ hw->aq.asq_last_status);
+ goto out;
+ }
+
+ veb->bw_limit = le16_to_cpu(ets_data.port_bw_limit);
+ veb->bw_max_quanta = ets_data.tc_bw_max;
+ veb->is_abs_credits = bw_data.absolute_credits_enable;
+ tc_bw_max = le16_to_cpu(bw_data.tc_bw_max[0]) |
+ (le16_to_cpu(bw_data.tc_bw_max[1]) << 16);
+ for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
+ veb->bw_tc_share_credits[i] = bw_data.tc_bw_share_credits[i];
+ veb->bw_tc_limit_credits[i] =
+ le16_to_cpu(bw_data.tc_bw_limits[i]);
+ veb->bw_tc_max_quanta[i] = ((tc_bw_max >> (i*4)) & 0x7);
+ }
+
+out:
+ return ret;
+}
+
+/**
+ * i40e_veb_mem_alloc - Allocates the next available struct veb in the PF
+ * @pf: board private structure
+ *
+ * On error: returns error code (negative)
+ * On success: returns vsi index in PF (positive)
+ **/
+static int i40e_veb_mem_alloc(struct i40e_pf *pf)
+{
+ int ret = -ENOENT;
+ struct i40e_veb *veb;
+ int i;
+
+ /* Need to protect the allocation of switch elements at the PF level */
+ mutex_lock(&pf->switch_mutex);
+
+ /* VEB list may be fragmented if VEB creation/destruction has
+ * been happening. We can afford to do a quick scan to look
+ * for any free slots in the list.
+ *
+ * find next empty veb slot, looping back around if necessary
+ */
+ i = 0;
+ while ((i < I40E_MAX_VEB) && (pf->veb[i] != NULL))
+ i++;
+ if (i >= I40E_MAX_VEB) {
+ ret = -ENOMEM;
+ goto err_alloc_veb; /* out of VEB slots! */
+ }
+
+ veb = kzalloc(sizeof(*veb), GFP_KERNEL);
+ if (!veb) {
+ ret = -ENOMEM;
+ goto err_alloc_veb;
+ }
+ veb->pf = pf;
+ veb->idx = i;
+ veb->enabled_tc = 1;
+
+ pf->veb[i] = veb;
+ ret = i;
+err_alloc_veb:
+ mutex_unlock(&pf->switch_mutex);
+ return ret;
+}
+
+/**
+ * i40e_switch_branch_release - Delete a branch of the switch tree
+ * @branch: where to start deleting
+ *
+ * This uses recursion to find the tips of the branch to be
+ * removed, deleting until we get back to and can delete this VEB.
+ **/
+static void i40e_switch_branch_release(struct i40e_veb *branch)
+{
+ struct i40e_pf *pf = branch->pf;
+ u16 branch_seid = branch->seid;
+ u16 veb_idx = branch->idx;
+ int i;
+
+ /* release any VEBs on this VEB - RECURSION */
+ for (i = 0; i < I40E_MAX_VEB; i++) {
+ if (!pf->veb[i])
+ continue;
+ if (pf->veb[i]->uplink_seid == branch->seid)
+ i40e_switch_branch_release(pf->veb[i]);
+ }
+
+ /* Release the VSIs on this VEB, but not the owner VSI.
+ *
+ * NOTE: Removing the last VSI on a VEB has the SIDE EFFECT of removing
+ * the VEB itself, so don't use (*branch) after this loop.
+ */
+ for (i = 0; i < pf->hw.func_caps.num_vsis; i++) {
+ if (!pf->vsi[i])
+ continue;
+ if (pf->vsi[i]->uplink_seid == branch_seid &&
+ (pf->vsi[i]->flags & I40E_VSI_FLAG_VEB_OWNER) == 0) {
+ i40e_vsi_release(pf->vsi[i]);
+ }
+ }
+
+ /* There's one corner case where the VEB might not have been
+ * removed, so double check it here and remove it if needed.
+ * This case happens if the veb was created from the debugfs
+ * commands and no VSIs were added to it.
+ */
+ if (pf->veb[veb_idx])
+ i40e_veb_release(pf->veb[veb_idx]);
+}
+
+/**
+ * i40e_veb_clear - remove veb struct
+ * @veb: the veb to remove
+ **/
+static void i40e_veb_clear(struct i40e_veb *veb)
+{
+ if (!veb)
+ return;
+
+ if (veb->pf) {
+ struct i40e_pf *pf = veb->pf;
+
+ mutex_lock(&pf->switch_mutex);
+ if (pf->veb[veb->idx] == veb)
+ pf->veb[veb->idx] = NULL;
+ mutex_unlock(&pf->switch_mutex);
+ }
+
+ kfree(veb);
+}
+
+/**
+ * i40e_veb_release - Delete a VEB and free its resources
+ * @veb: the VEB being removed
+ **/
+void i40e_veb_release(struct i40e_veb *veb)
+{
+ struct i40e_vsi *vsi = NULL;
+ struct i40e_pf *pf;
+ int i, n = 0;
+
+ pf = veb->pf;
+
+ /* find the remaining VSI and check for extras */
+ for (i = 0; i < pf->hw.func_caps.num_vsis; i++) {
+ if (pf->vsi[i] && pf->vsi[i]->uplink_seid == veb->seid) {
+ n++;
+ vsi = pf->vsi[i];
+ }
+ }
+ if (n != 1) {
+ dev_info(&pf->pdev->dev,
+ "can't remove VEB %d with %d VSIs left\n",
+ veb->seid, n);
+ return;
+ }
+
+ /* move the remaining VSI to uplink veb */
+ vsi->flags &= ~I40E_VSI_FLAG_VEB_OWNER;
+ if (veb->uplink_seid) {
+ vsi->uplink_seid = veb->uplink_seid;
+ if (veb->uplink_seid == pf->mac_seid)
+ vsi->veb_idx = I40E_NO_VEB;
+ else
+ vsi->veb_idx = veb->veb_idx;
+ } else {
+ /* floating VEB */
+ vsi->uplink_seid = pf->vsi[pf->lan_vsi]->uplink_seid;
+ vsi->veb_idx = pf->vsi[pf->lan_vsi]->veb_idx;
+ }
+
+ i40e_aq_delete_element(&pf->hw, veb->seid, NULL);
+ i40e_veb_clear(veb);
+
+ return;
+}
+
+/**
+ * i40e_add_veb - create the VEB in the switch
+ * @veb: the VEB to be instantiated
+ * @vsi: the controlling VSI
+ **/
+static int i40e_add_veb(struct i40e_veb *veb, struct i40e_vsi *vsi)
+{
+ bool is_default = (vsi->idx == vsi->back->lan_vsi);
+ int ret;
+
+ /* get a VEB from the hardware */
+ ret = i40e_aq_add_veb(&veb->pf->hw, veb->uplink_seid, vsi->seid,
+ veb->enabled_tc, is_default, &veb->seid, NULL);
+ if (ret) {
+ dev_info(&veb->pf->pdev->dev,
+ "couldn't add VEB, err %d, aq_err %d\n",
+ ret, veb->pf->hw.aq.asq_last_status);
+ return -EPERM;
+ }
+
+ /* get statistics counter */
+ ret = i40e_aq_get_veb_parameters(&veb->pf->hw, veb->seid, NULL, NULL,
+ &veb->stats_idx, NULL, NULL, NULL);
+ if (ret) {
+ dev_info(&veb->pf->pdev->dev,
+ "couldn't get VEB statistics idx, err %d, aq_err %d\n",
+ ret, veb->pf->hw.aq.asq_last_status);
+ return -EPERM;
+ }
+ ret = i40e_veb_get_bw_info(veb);
+ if (ret) {
+ dev_info(&veb->pf->pdev->dev,
+ "couldn't get VEB bw info, err %d, aq_err %d\n",
+ ret, veb->pf->hw.aq.asq_last_status);
+ i40e_aq_delete_element(&veb->pf->hw, veb->seid, NULL);
+ return -ENOENT;
+ }
+
+ vsi->uplink_seid = veb->seid;
+ vsi->veb_idx = veb->idx;
+ vsi->flags |= I40E_VSI_FLAG_VEB_OWNER;
+
+ return 0;
+}
+
+/**
+ * i40e_veb_setup - Set up a VEB
+ * @pf: board private structure
+ * @flags: VEB setup flags
+ * @uplink_seid: the switch element to link to
+ * @vsi_seid: the initial VSI seid
+ * @enabled_tc: Enabled TC bit-map
+ *
+ * This allocates the sw VEB structure and links it into the switch
+ * It is possible and legal for this to be a duplicate of an already
+ * existing VEB. It is also possible for both uplink and vsi seids
+ * to be zero, in order to create a floating VEB.
+ *
+ * Returns pointer to the successfully allocated VEB sw struct on
+ * success, otherwise returns NULL on failure.
+ **/
+struct i40e_veb *i40e_veb_setup(struct i40e_pf *pf, u16 flags,
+ u16 uplink_seid, u16 vsi_seid,
+ u8 enabled_tc)
+{
+ struct i40e_veb *veb, *uplink_veb = NULL;
+ int vsi_idx, veb_idx;
+ int ret;
+
+ /* if one seid is 0, the other must be 0 to create a floating relay */
+ if ((uplink_seid == 0 || vsi_seid == 0) &&
+ (uplink_seid + vsi_seid != 0)) {
+ dev_info(&pf->pdev->dev,
+ "one, not both seid's are 0: uplink=%d vsi=%d\n",
+ uplink_seid, vsi_seid);
+ return NULL;
+ }
+
+ /* make sure there is such a vsi and uplink */
+ for (vsi_idx = 0; vsi_idx < pf->hw.func_caps.num_vsis; vsi_idx++)
+ if (pf->vsi[vsi_idx] && pf->vsi[vsi_idx]->seid == vsi_seid)
+ break;
+ if (vsi_idx >= pf->hw.func_caps.num_vsis && vsi_seid != 0) {
+ dev_info(&pf->pdev->dev, "vsi seid %d not found\n",
+ vsi_seid);
+ return NULL;
+ }
+
+ if (uplink_seid && uplink_seid != pf->mac_seid) {
+ for (veb_idx = 0; veb_idx < I40E_MAX_VEB; veb_idx++) {
+ if (pf->veb[veb_idx] &&
+ pf->veb[veb_idx]->seid == uplink_seid) {
+ uplink_veb = pf->veb[veb_idx];
+ break;
+ }
+ }
+ if (!uplink_veb) {
+ dev_info(&pf->pdev->dev,
+ "uplink seid %d not found\n", uplink_seid);
+ return NULL;
+ }
+ }
+
+ /* get veb sw struct */
+ veb_idx = i40e_veb_mem_alloc(pf);
+ if (veb_idx < 0)
+ goto err_alloc;
+ veb = pf->veb[veb_idx];
+ veb->flags = flags;
+ veb->uplink_seid = uplink_seid;
+ veb->veb_idx = (uplink_veb ? uplink_veb->idx : I40E_NO_VEB);
+ veb->enabled_tc = (enabled_tc ? enabled_tc : 0x1);
+
+ /* create the VEB in the switch */
+ ret = i40e_add_veb(veb, pf->vsi[vsi_idx]);
+ if (ret)
+ goto err_veb;
+
+ return veb;
+
+err_veb:
+ i40e_veb_clear(veb);
+err_alloc:
+ return NULL;
+}
+
+/**
+ * i40e_setup_pf_switch_element - set pf vars based on switch type
+ * @pf: board private structure
+ * @ele: element we are building info from
+ * @num_reported: total number of elements
+ * @printconfig: should we print the contents
+ *
+ * helper function to assist in extracting a few useful SEID values.
+ **/
+static void i40e_setup_pf_switch_element(struct i40e_pf *pf,
+ struct i40e_aqc_switch_config_element_resp *ele,
+ u16 num_reported, bool printconfig)
+{
+ u16 downlink_seid = le16_to_cpu(ele->downlink_seid);
+ u16 uplink_seid = le16_to_cpu(ele->uplink_seid);
+ u8 element_type = ele->element_type;
+ u16 seid = le16_to_cpu(ele->seid);
+
+ if (printconfig)
+ dev_info(&pf->pdev->dev,
+ "type=%d seid=%d uplink=%d downlink=%d\n",
+ element_type, seid, uplink_seid, downlink_seid);
+
+ switch (element_type) {
+ case I40E_SWITCH_ELEMENT_TYPE_MAC:
+ pf->mac_seid = seid;
+ break;
+ case I40E_SWITCH_ELEMENT_TYPE_VEB:
+ /* Main VEB? */
+ if (uplink_seid != pf->mac_seid)
+ break;
+ if (pf->lan_veb == I40E_NO_VEB) {
+ int v;
+
+ /* find existing or else empty VEB */
+ for (v = 0; v < I40E_MAX_VEB; v++) {
+ if (pf->veb[v] && (pf->veb[v]->seid == seid)) {
+ pf->lan_veb = v;
+ break;
+ }
+ }
+ if (pf->lan_veb == I40E_NO_VEB) {
+ v = i40e_veb_mem_alloc(pf);
+ if (v < 0)
+ break;
+ pf->lan_veb = v;
+ }
+ }
+
+ pf->veb[pf->lan_veb]->seid = seid;
+ pf->veb[pf->lan_veb]->uplink_seid = pf->mac_seid;
+ pf->veb[pf->lan_veb]->pf = pf;
+ pf->veb[pf->lan_veb]->veb_idx = I40E_NO_VEB;
+ break;
+ case I40E_SWITCH_ELEMENT_TYPE_VSI:
+ if (num_reported != 1)
+ break;
+ /* This is immediately after a reset so we can assume this is
+ * the PF's VSI
+ */
+ pf->mac_seid = uplink_seid;
+ pf->pf_seid = downlink_seid;
+ pf->main_vsi_seid = seid;
+ if (printconfig)
+ dev_info(&pf->pdev->dev,
+ "pf_seid=%d main_vsi_seid=%d\n",
+ pf->pf_seid, pf->main_vsi_seid);
+ break;
+ case I40E_SWITCH_ELEMENT_TYPE_PF:
+ case I40E_SWITCH_ELEMENT_TYPE_VF:
+ case I40E_SWITCH_ELEMENT_TYPE_EMP:
+ case I40E_SWITCH_ELEMENT_TYPE_BMC:
+ case I40E_SWITCH_ELEMENT_TYPE_PE:
+ case I40E_SWITCH_ELEMENT_TYPE_PA:
+ /* ignore these for now */
+ break;
+ default:
+ dev_info(&pf->pdev->dev, "unknown element type=%d seid=%d\n",
+ element_type, seid);
+ break;
+ }
+}
+
+/**
+ * i40e_fetch_switch_configuration - Get switch config from firmware
+ * @pf: board private structure
+ * @printconfig: should we print the contents
+ *
+ * Get the current switch configuration from the device and
+ * extract a few useful SEID values.
+ **/
+int i40e_fetch_switch_configuration(struct i40e_pf *pf, bool printconfig)
+{
+ struct i40e_aqc_get_switch_config_resp *sw_config;
+ u16 next_seid = 0;
+ int ret = 0;
+ u8 *aq_buf;
+ int i;
+
+ aq_buf = kzalloc(I40E_AQ_LARGE_BUF, GFP_KERNEL);
+ if (!aq_buf)
+ return -ENOMEM;
+
+ sw_config = (struct i40e_aqc_get_switch_config_resp *)aq_buf;
+ do {
+ u16 num_reported, num_total;
+
+ ret = i40e_aq_get_switch_config(&pf->hw, sw_config,
+ I40E_AQ_LARGE_BUF,
+ &next_seid, NULL);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "get switch config failed %d aq_err=%x\n",
+ ret, pf->hw.aq.asq_last_status);
+ kfree(aq_buf);
+ return -ENOENT;
+ }
+
+ num_reported = le16_to_cpu(sw_config->header.num_reported);
+ num_total = le16_to_cpu(sw_config->header.num_total);
+
+ if (printconfig)
+ dev_info(&pf->pdev->dev,
+ "header: %d reported %d total\n",
+ num_reported, num_total);
+
+ if (num_reported) {
+ int sz = sizeof(*sw_config) * num_reported;
+
+ kfree(pf->sw_config);
+ pf->sw_config = kzalloc(sz, GFP_KERNEL);
+ if (pf->sw_config)
+ memcpy(pf->sw_config, sw_config, sz);
+ }
+
+ for (i = 0; i < num_reported; i++) {
+ struct i40e_aqc_switch_config_element_resp *ele =
+ &sw_config->element[i];
+
+ i40e_setup_pf_switch_element(pf, ele, num_reported,
+ printconfig);
+ }
+ } while (next_seid != 0);
+
+ kfree(aq_buf);
+ return ret;
+}
+
+/**
+ * i40e_setup_pf_switch - Setup the HW switch on startup or after reset
+ * @pf: board private structure
+ *
+ * Returns 0 on success, negative value on failure
+ **/
+static int i40e_setup_pf_switch(struct i40e_pf *pf)
+{
+ int ret;
+
+ /* find out what's out there already */
+ ret = i40e_fetch_switch_configuration(pf, false);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "couldn't fetch switch config, err %d, aq_err %d\n",
+ ret, pf->hw.aq.asq_last_status);
+ return ret;
+ }
+ i40e_pf_reset_stats(pf);
+
+ /* fdir VSI must happen first to be sure it gets queue 0, but only
+ * if there is enough room for the fdir VSI
+ */
+ if (pf->num_lan_qps > 1)
+ i40e_fdir_setup(pf);
+
+ /* first time setup */
+ if (pf->lan_vsi == I40E_NO_VSI) {
+ struct i40e_vsi *vsi = NULL;
+ u16 uplink_seid;
+
+ /* Set up the PF VSI associated with the PF's main VSI
+ * that is already in the HW switch
+ */
+ if (pf->lan_veb != I40E_NO_VEB && pf->veb[pf->lan_veb])
+ uplink_seid = pf->veb[pf->lan_veb]->seid;
+ else
+ uplink_seid = pf->mac_seid;
+
+ vsi = i40e_vsi_setup(pf, I40E_VSI_MAIN, uplink_seid, 0);
+ if (!vsi) {
+ dev_info(&pf->pdev->dev, "setup of MAIN VSI failed\n");
+ i40e_fdir_teardown(pf);
+ return -EAGAIN;
+ }
+ /* accommodate kcompat by copying the main VSI queue count
+ * into the pf, since this newer code pushes the pf queue
+ * info down a level into a VSI
+ */
+ pf->num_rx_queues = vsi->alloc_queue_pairs;
+ pf->num_tx_queues = vsi->alloc_queue_pairs;
+ } else {
+ /* force a reset of TC and queue layout configurations */
+ u8 enabled_tc = pf->vsi[pf->lan_vsi]->tc_config.enabled_tc;
+ pf->vsi[pf->lan_vsi]->tc_config.enabled_tc = 0;
+ pf->vsi[pf->lan_vsi]->seid = pf->main_vsi_seid;
+ i40e_vsi_config_tc(pf->vsi[pf->lan_vsi], enabled_tc);
+ }
+ i40e_vlan_stripping_disable(pf->vsi[pf->lan_vsi]);
+
+ /* Setup static PF queue filter control settings */
+ ret = i40e_setup_pf_filter_control(pf);
+ if (ret) {
+ dev_info(&pf->pdev->dev, "setup_pf_filter_control failed: %d\n",
+ ret);
+ /* Failure here should not stop continuing other steps */
+ }
+
+ /* enable RSS in the HW, even for only one queue, as the stack can use
+ * the hash
+ */
+ if ((pf->flags & I40E_FLAG_RSS_ENABLED))
+ i40e_config_rss(pf);
+
+ /* fill in link information and enable LSE reporting */
+ i40e_aq_get_link_info(&pf->hw, true, NULL, NULL);
+ i40e_link_event(pf);
+
+ /* Initialize user-specifics link properties */
+ pf->fc_autoneg_status = ((pf->hw.phy.link_info.an_info &
+ I40E_AQ_AN_COMPLETED) ? true : false);
+ pf->hw.fc.requested_mode = I40E_FC_DEFAULT;
+ if (pf->hw.phy.link_info.an_info &
+ (I40E_AQ_LINK_PAUSE_TX | I40E_AQ_LINK_PAUSE_RX))
+ pf->hw.fc.current_mode = I40E_FC_FULL;
+ else if (pf->hw.phy.link_info.an_info & I40E_AQ_LINK_PAUSE_TX)
+ pf->hw.fc.current_mode = I40E_FC_TX_PAUSE;
+ else if (pf->hw.phy.link_info.an_info & I40E_AQ_LINK_PAUSE_RX)
+ pf->hw.fc.current_mode = I40E_FC_RX_PAUSE;
+ else
+ pf->hw.fc.current_mode = I40E_FC_DEFAULT;
+
+ return ret;
+}
+
+/**
+ * i40e_set_rss_size - helper to set rss_size
+ * @pf: board private structure
+ * @queues_left: how many queues
+ */
+static u16 i40e_set_rss_size(struct i40e_pf *pf, int queues_left)
+{
+ int num_tc0;
+
+ num_tc0 = min_t(int, queues_left, pf->rss_size_max);
+ num_tc0 = min_t(int, num_tc0, nr_cpus_node(numa_node_id()));
+ num_tc0 = rounddown_pow_of_two(num_tc0);
+
+ return num_tc0;
+}
+
+/**
+ * i40e_determine_queue_usage - Work out queue distribution
+ * @pf: board private structure
+ **/
+static void i40e_determine_queue_usage(struct i40e_pf *pf)
+{
+ int accum_tc_size;
+ int queues_left;
+
+ pf->num_lan_qps = 0;
+ pf->num_tc_qps = rounddown_pow_of_two(pf->num_tc_qps);
+ accum_tc_size = (I40E_MAX_TRAFFIC_CLASS - 1) * pf->num_tc_qps;
+
+ /* Find the max queues to be put into basic use. We'll always be
+ * using TC0, whether or not DCB is running, and TC0 will get the
+ * big RSS set.
+ */
+ queues_left = pf->hw.func_caps.num_tx_qp;
+
+ if (!((pf->flags & I40E_FLAG_MSIX_ENABLED) &&
+ (pf->flags & I40E_FLAG_MQ_ENABLED)) ||
+ !(pf->flags & (I40E_FLAG_RSS_ENABLED |
+ I40E_FLAG_FDIR_ENABLED | I40E_FLAG_DCB_ENABLED)) ||
+ (queues_left == 1)) {
+
+ /* one qp for PF, no queues for anything else */
+ queues_left = 0;
+ pf->rss_size = pf->num_lan_qps = 1;
+
+ /* make sure all the fancies are disabled */
+ pf->flags &= ~(I40E_FLAG_RSS_ENABLED |
+ I40E_FLAG_MQ_ENABLED |
+ I40E_FLAG_FDIR_ENABLED |
+ I40E_FLAG_FDIR_ATR_ENABLED |
+ I40E_FLAG_DCB_ENABLED |
+ I40E_FLAG_SRIOV_ENABLED |
+ I40E_FLAG_VMDQ_ENABLED);
+
+ } else if (pf->flags & I40E_FLAG_RSS_ENABLED &&
+ !(pf->flags & I40E_FLAG_FDIR_ENABLED) &&
+ !(pf->flags & I40E_FLAG_DCB_ENABLED)) {
+
+ pf->rss_size = i40e_set_rss_size(pf, queues_left);
+
+ queues_left -= pf->rss_size;
+ pf->num_lan_qps = pf->rss_size;
+
+ } else if (pf->flags & I40E_FLAG_RSS_ENABLED &&
+ !(pf->flags & I40E_FLAG_FDIR_ENABLED) &&
+ (pf->flags & I40E_FLAG_DCB_ENABLED)) {
+
+ /* save num_tc_qps queues for TCs 1 thru 7 and the rest
+ * are set up for RSS in TC0
+ */
+ queues_left -= accum_tc_size;
+
+ pf->rss_size = i40e_set_rss_size(pf, queues_left);
+
+ queues_left -= pf->rss_size;
+ if (queues_left < 0) {
+ dev_info(&pf->pdev->dev, "not enough queues for DCB\n");
+ return;
+ }
+
+ pf->num_lan_qps = pf->rss_size + accum_tc_size;
+
+ } else if (pf->flags & I40E_FLAG_RSS_ENABLED &&
+ (pf->flags & I40E_FLAG_FDIR_ENABLED) &&
+ !(pf->flags & I40E_FLAG_DCB_ENABLED)) {
+
+ queues_left -= 1; /* save 1 queue for FD */
+
+ pf->rss_size = i40e_set_rss_size(pf, queues_left);
+
+ queues_left -= pf->rss_size;
+ if (queues_left < 0) {
+ dev_info(&pf->pdev->dev, "not enough queues for Flow Director\n");
+ return;
+ }
+
+ pf->num_lan_qps = pf->rss_size;
+
+ } else if (pf->flags & I40E_FLAG_RSS_ENABLED &&
+ (pf->flags & I40E_FLAG_FDIR_ENABLED) &&
+ (pf->flags & I40E_FLAG_DCB_ENABLED)) {
+
+ /* save 1 queue for TCs 1 thru 7,
+ * 1 queue for flow director,
+ * and the rest are set up for RSS in TC0
+ */
+ queues_left -= 1;
+ queues_left -= accum_tc_size;
+
+ pf->rss_size = i40e_set_rss_size(pf, queues_left);
+ queues_left -= pf->rss_size;
+ if (queues_left < 0) {
+ dev_info(&pf->pdev->dev, "not enough queues for DCB and Flow Director\n");
+ return;
+ }
+
+ pf->num_lan_qps = pf->rss_size + accum_tc_size;
+
+ } else {
+ dev_info(&pf->pdev->dev,
+ "Invalid configuration, flags=0x%08llx\n", pf->flags);
+ return;
+ }
+
+ if ((pf->flags & I40E_FLAG_SRIOV_ENABLED) &&
+ pf->num_vf_qps && pf->num_req_vfs && queues_left) {
+ pf->num_req_vfs = min_t(int, pf->num_req_vfs, (queues_left /
+ pf->num_vf_qps));
+ queues_left -= (pf->num_req_vfs * pf->num_vf_qps);
+ }
+
+ if ((pf->flags & I40E_FLAG_VMDQ_ENABLED) &&
+ pf->num_vmdq_vsis && pf->num_vmdq_qps && queues_left) {
+ pf->num_vmdq_vsis = min_t(int, pf->num_vmdq_vsis,
+ (queues_left / pf->num_vmdq_qps));
+ queues_left -= (pf->num_vmdq_vsis * pf->num_vmdq_qps);
+ }
+
+ return;
+}
+
+/**
+ * i40e_setup_pf_filter_control - Setup PF static filter control
+ * @pf: PF to be setup
+ *
+ * i40e_setup_pf_filter_control sets up a pf's initial filter control
+ * settings. If PE/FCoE are enabled then it will also set the per PF
+ * based filter sizes required for them. It also enables Flow director,
+ * ethertype and macvlan type filter settings for the pf.
+ *
+ * Returns 0 on success, negative on failure
+ **/
+static int i40e_setup_pf_filter_control(struct i40e_pf *pf)
+{
+ struct i40e_filter_control_settings *settings = &pf->filter_settings;
+
+ settings->hash_lut_size = I40E_HASH_LUT_SIZE_128;
+
+ /* Flow Director is enabled */
+ if (pf->flags & (I40E_FLAG_FDIR_ENABLED | I40E_FLAG_FDIR_ATR_ENABLED))
+ settings->enable_fdir = true;
+
+ /* Ethtype and MACVLAN filters enabled for PF */
+ settings->enable_ethtype = true;
+ settings->enable_macvlan = true;
+
+ if (i40e_set_filter_control(&pf->hw, settings))
+ return -ENOENT;
+
+ return 0;
+}
+
+/**
+ * i40e_probe - Device initialization routine
+ * @pdev: PCI device information struct
+ * @ent: entry in i40e_pci_tbl
+ *
+ * i40e_probe initializes a pf identified by a pci_dev structure.
+ * The OS initialization, configuring of the pf private structure,
+ * and a hardware reset occur.
+ *
+ * Returns 0 on success, negative on failure
+ **/
+static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+ struct i40e_driver_version dv;
+ struct i40e_pf *pf;
+ struct i40e_hw *hw;
+ int err = 0;
+ u32 len;
+
+ err = pci_enable_device_mem(pdev);
+ if (err)
+ return err;
+
+ /* set up for high or low dma */
+ if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(64))) {
+ /* coherent mask for the same size will always succeed if
+ * dma_set_mask does
+ */
+ dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64));
+ } else if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(32))) {
+ dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32));
+ } else {
+ dev_err(&pdev->dev, "DMA configuration failed: %d\n", err);
+ err = -EIO;
+ goto err_dma;
+ }
+
+ /* set up pci connections */
+ err = pci_request_selected_regions(pdev, pci_select_bars(pdev,
+ IORESOURCE_MEM), i40e_driver_name);
+ if (err) {
+ dev_info(&pdev->dev,
+ "pci_request_selected_regions failed %d\n", err);
+ goto err_pci_reg;
+ }
+
+ pci_enable_pcie_error_reporting(pdev);
+ pci_set_master(pdev);
+
+ /* Now that we have a PCI connection, we need to do the
+ * low level device setup. This is primarily setting up
+ * the Admin Queue structures and then querying for the
+ * device's current profile information.
+ */
+ pf = kzalloc(sizeof(*pf), GFP_KERNEL);
+ if (!pf) {
+ err = -ENOMEM;
+ goto err_pf_alloc;
+ }
+ pf->next_vsi = 0;
+ pf->pdev = pdev;
+ set_bit(__I40E_DOWN, &pf->state);
+
+ hw = &pf->hw;
+ hw->back = pf;
+ hw->hw_addr = ioremap(pci_resource_start(pdev, 0),
+ pci_resource_len(pdev, 0));
+ if (!hw->hw_addr) {
+ err = -EIO;
+ dev_info(&pdev->dev, "ioremap(0x%04x, 0x%04x) failed: 0x%x\n",
+ (unsigned int)pci_resource_start(pdev, 0),
+ (unsigned int)pci_resource_len(pdev, 0), err);
+ goto err_ioremap;
+ }
+ hw->vendor_id = pdev->vendor;
+ hw->device_id = pdev->device;
+ pci_read_config_byte(pdev, PCI_REVISION_ID, &hw->revision_id);
+ hw->subsystem_vendor_id = pdev->subsystem_vendor;
+ hw->subsystem_device_id = pdev->subsystem_device;
+ hw->bus.device = PCI_SLOT(pdev->devfn);
+ hw->bus.func = PCI_FUNC(pdev->devfn);
+
+ /* Reset here to make sure all is clean and to define PF 'n' */
+ err = i40e_pf_reset(hw);
+ if (err) {
+ dev_info(&pdev->dev, "Initial pf_reset failed: %d\n", err);
+ goto err_pf_reset;
+ }
+ pf->pfr_count++;
+
+ hw->aq.num_arq_entries = I40E_AQ_LEN;
+ hw->aq.num_asq_entries = I40E_AQ_LEN;
+ hw->aq.arq_buf_size = I40E_MAX_AQ_BUF_SIZE;
+ hw->aq.asq_buf_size = I40E_MAX_AQ_BUF_SIZE;
+ pf->adminq_work_limit = I40E_AQ_WORK_LIMIT;
+ snprintf(pf->misc_int_name, sizeof(pf->misc_int_name) - 1,
+ "%s-pf%d:misc",
+ dev_driver_string(&pf->pdev->dev), pf->hw.pf_id);
+
+ err = i40e_init_shared_code(hw);
+ if (err) {
+ dev_info(&pdev->dev, "init_shared_code failed: %d\n", err);
+ goto err_pf_reset;
+ }
+
+ err = i40e_init_adminq(hw);
+ dev_info(&pdev->dev, "%s\n", i40e_fw_version_str(hw));
+ if (err) {
+ dev_info(&pdev->dev,
+ "init_adminq failed: %d expecting API %02x.%02x\n",
+ err,
+ I40E_FW_API_VERSION_MAJOR, I40E_FW_API_VERSION_MINOR);
+ goto err_pf_reset;
+ }
+
+ err = i40e_get_capabilities(pf);
+ if (err)
+ goto err_adminq_setup;
+
+ err = i40e_sw_init(pf);
+ if (err) {
+ dev_info(&pdev->dev, "sw_init failed: %d\n", err);
+ goto err_sw_init;
+ }
+
+ err = i40e_init_lan_hmc(hw, hw->func_caps.num_tx_qp,
+ hw->func_caps.num_rx_qp,
+ pf->fcoe_hmc_cntx_num, pf->fcoe_hmc_filt_num);
+ if (err) {
+ dev_info(&pdev->dev, "init_lan_hmc failed: %d\n", err);
+ goto err_init_lan_hmc;
+ }
+
+ err = i40e_configure_lan_hmc(hw, I40E_HMC_MODEL_DIRECT_ONLY);
+ if (err) {
+ dev_info(&pdev->dev, "configure_lan_hmc failed: %d\n", err);
+ err = -ENOENT;
+ goto err_configure_lan_hmc;
+ }
+
+ i40e_get_mac_addr(hw, hw->mac.addr);
+ if (i40e_validate_mac_addr(hw->mac.addr)) {
+ dev_info(&pdev->dev, "invalid MAC address %pM\n", hw->mac.addr);
+ err = -EIO;
+ goto err_mac_addr;
+ }
+ dev_info(&pdev->dev, "MAC address: %pM\n", hw->mac.addr);
+ memcpy(hw->mac.perm_addr, hw->mac.addr, ETH_ALEN);
+
+ pci_set_drvdata(pdev, pf);
+ pci_save_state(pdev);
+
+ /* set up periodic task facility */
+ setup_timer(&pf->service_timer, i40e_service_timer, (unsigned long)pf);
+ pf->service_timer_period = HZ;
+
+ INIT_WORK(&pf->service_task, i40e_service_task);
+ clear_bit(__I40E_SERVICE_SCHED, &pf->state);
+ pf->flags |= I40E_FLAG_NEED_LINK_UPDATE;
+ pf->link_check_timeout = jiffies;
+
+ /* set up the main switch operations */
+ i40e_determine_queue_usage(pf);
+ i40e_init_interrupt_scheme(pf);
+
+ /* Set up the *vsi struct based on the number of VSIs in the HW,
+ * and set up our local tracking of the MAIN PF vsi.
+ */
+ len = sizeof(struct i40e_vsi *) * pf->hw.func_caps.num_vsis;
+ pf->vsi = kzalloc(len, GFP_KERNEL);
+ if (!pf->vsi)
+ goto err_switch_setup;
+
+ err = i40e_setup_pf_switch(pf);
+ if (err) {
+ dev_info(&pdev->dev, "setup_pf_switch failed: %d\n", err);
+ goto err_vsis;
+ }
+
+ /* The main driver is (mostly) up and happy. We need to set this state
+ * before setting up the misc vector or we get a race and the vector
+ * ends up disabled forever.
+ */
+ clear_bit(__I40E_DOWN, &pf->state);
+
+ /* In case of MSIX we are going to setup the misc vector right here
+ * to handle admin queue events etc. In case of legacy and MSI
+ * the misc functionality and queue processing is combined in
+ * the same vector and that gets setup at open.
+ */
+ if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
+ err = i40e_setup_misc_vector(pf);
+ if (err) {
+ dev_info(&pdev->dev,
+ "setup of misc vector failed: %d\n", err);
+ goto err_vsis;
+ }
+ }
+
+ /* prep for VF support */
+ if ((pf->flags & I40E_FLAG_SRIOV_ENABLED) &&
+ (pf->flags & I40E_FLAG_MSIX_ENABLED)) {
+ u32 val;
+
+ /* disable link interrupts for VFs */
+ val = rd32(hw, I40E_PFGEN_PORTMDIO_NUM);
+ val &= ~I40E_PFGEN_PORTMDIO_NUM_VFLINK_STAT_ENA_MASK;
+ wr32(hw, I40E_PFGEN_PORTMDIO_NUM, val);
+ i40e_flush(hw);
+ }
+
+ i40e_dbg_pf_init(pf);
+
+ /* tell the firmware that we're starting */
+ dv.major_version = DRV_VERSION_MAJOR;
+ dv.minor_version = DRV_VERSION_MINOR;
+ dv.build_version = DRV_VERSION_BUILD;
+ dv.subbuild_version = 0;
+ i40e_aq_send_driver_version(&pf->hw, &dv, NULL);
+
+ /* since everything's happy, start the service_task timer */
+ mod_timer(&pf->service_timer,
+ round_jiffies(jiffies + pf->service_timer_period));
+
+ return 0;
+
+ /* Unwind what we've done if something failed in the setup */
+err_vsis:
+ set_bit(__I40E_DOWN, &pf->state);
+err_switch_setup:
+ i40e_clear_interrupt_scheme(pf);
+ kfree(pf->vsi);
+ del_timer_sync(&pf->service_timer);
+err_mac_addr:
+err_configure_lan_hmc:
+ (void)i40e_shutdown_lan_hmc(hw);
+err_init_lan_hmc:
+ kfree(pf->qp_pile);
+ kfree(pf->irq_pile);
+err_sw_init:
+err_adminq_setup:
+ (void)i40e_shutdown_adminq(hw);
+err_pf_reset:
+ iounmap(hw->hw_addr);
+err_ioremap:
+ kfree(pf);
+err_pf_alloc:
+ pci_disable_pcie_error_reporting(pdev);
+ pci_release_selected_regions(pdev,
+ pci_select_bars(pdev, IORESOURCE_MEM));
+err_pci_reg:
+err_dma:
+ pci_disable_device(pdev);
+ return err;
+}
+
+/**
+ * i40e_remove - Device removal routine
+ * @pdev: PCI device information struct
+ *
+ * i40e_remove is called by the PCI subsystem to alert the driver
+ * that is should release a PCI device. This could be caused by a
+ * Hot-Plug event, or because the driver is going to be removed from
+ * memory.
+ **/
+static void i40e_remove(struct pci_dev *pdev)
+{
+ struct i40e_pf *pf = pci_get_drvdata(pdev);
+ i40e_status ret_code;
+ u32 reg;
+ int i;
+
+ i40e_dbg_pf_exit(pf);
+
+ if (pf->flags & I40E_FLAG_SRIOV_ENABLED) {
+ i40e_free_vfs(pf);
+ pf->flags &= ~I40E_FLAG_SRIOV_ENABLED;
+ }
+
+ /* no more scheduling of any task */
+ set_bit(__I40E_DOWN, &pf->state);
+ del_timer_sync(&pf->service_timer);
+ cancel_work_sync(&pf->service_task);
+
+ i40e_fdir_teardown(pf);
+
+ /* If there is a switch structure or any orphans, remove them.
+ * This will leave only the PF's VSI remaining.
+ */
+ for (i = 0; i < I40E_MAX_VEB; i++) {
+ if (!pf->veb[i])
+ continue;
+
+ if (pf->veb[i]->uplink_seid == pf->mac_seid ||
+ pf->veb[i]->uplink_seid == 0)
+ i40e_switch_branch_release(pf->veb[i]);
+ }
+
+ /* Now we can shutdown the PF's VSI, just before we kill
+ * adminq and hmc.
+ */
+ if (pf->vsi[pf->lan_vsi])
+ i40e_vsi_release(pf->vsi[pf->lan_vsi]);
+
+ i40e_stop_misc_vector(pf);
+ if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
+ synchronize_irq(pf->msix_entries[0].vector);
+ free_irq(pf->msix_entries[0].vector, pf);
+ }
+
+ /* shutdown and destroy the HMC */
+ ret_code = i40e_shutdown_lan_hmc(&pf->hw);
+ if (ret_code)
+ dev_warn(&pdev->dev,
+ "Failed to destroy the HMC resources: %d\n", ret_code);
+
+ /* shutdown the adminq */
+ i40e_aq_queue_shutdown(&pf->hw, true);
+ ret_code = i40e_shutdown_adminq(&pf->hw);
+ if (ret_code)
+ dev_warn(&pdev->dev,
+ "Failed to destroy the Admin Queue resources: %d\n",
+ ret_code);
+
+ /* Clear all dynamic memory lists of rings, q_vectors, and VSIs */
+ i40e_clear_interrupt_scheme(pf);
+ for (i = 0; i < pf->hw.func_caps.num_vsis; i++) {
+ if (pf->vsi[i]) {
+ i40e_vsi_clear_rings(pf->vsi[i]);
+ i40e_vsi_clear(pf->vsi[i]);
+ pf->vsi[i] = NULL;
+ }
+ }
+
+ for (i = 0; i < I40E_MAX_VEB; i++) {
+ kfree(pf->veb[i]);
+ pf->veb[i] = NULL;
+ }
+
+ kfree(pf->qp_pile);
+ kfree(pf->irq_pile);
+ kfree(pf->sw_config);
+ kfree(pf->vsi);
+
+ /* force a PF reset to clean anything leftover */
+ reg = rd32(&pf->hw, I40E_PFGEN_CTRL);
+ wr32(&pf->hw, I40E_PFGEN_CTRL, (reg | I40E_PFGEN_CTRL_PFSWR_MASK));
+ i40e_flush(&pf->hw);
+
+ iounmap(pf->hw.hw_addr);
+ kfree(pf);
+ pci_release_selected_regions(pdev,
+ pci_select_bars(pdev, IORESOURCE_MEM));
+
+ pci_disable_pcie_error_reporting(pdev);
+ pci_disable_device(pdev);
+}
+
+/**
+ * i40e_pci_error_detected - warning that something funky happened in PCI land
+ * @pdev: PCI device information struct
+ *
+ * Called to warn that something happened and the error handling steps
+ * are in progress. Allows the driver to quiesce things, be ready for
+ * remediation.
+ **/
+static pci_ers_result_t i40e_pci_error_detected(struct pci_dev *pdev,
+ enum pci_channel_state error)
+{
+ struct i40e_pf *pf = pci_get_drvdata(pdev);
+
+ dev_info(&pdev->dev, "%s: error %d\n", __func__, error);
+
+ /* shutdown all operations */
+ i40e_pf_quiesce_all_vsi(pf);
+
+ /* Request a slot reset */
+ return PCI_ERS_RESULT_NEED_RESET;
+}
+
+/**
+ * i40e_pci_error_slot_reset - a PCI slot reset just happened
+ * @pdev: PCI device information struct
+ *
+ * Called to find if the driver can work with the device now that
+ * the pci slot has been reset. If a basic connection seems good
+ * (registers are readable and have sane content) then return a
+ * happy little PCI_ERS_RESULT_xxx.
+ **/
+static pci_ers_result_t i40e_pci_error_slot_reset(struct pci_dev *pdev)
+{
+ struct i40e_pf *pf = pci_get_drvdata(pdev);
+ pci_ers_result_t result;
+ int err;
+ u32 reg;
+
+ dev_info(&pdev->dev, "%s\n", __func__);
+ if (pci_enable_device_mem(pdev)) {
+ dev_info(&pdev->dev,
+ "Cannot re-enable PCI device after reset.\n");
+ result = PCI_ERS_RESULT_DISCONNECT;
+ } else {
+ pci_set_master(pdev);
+ pci_restore_state(pdev);
+ pci_save_state(pdev);
+ pci_wake_from_d3(pdev, false);
+
+ reg = rd32(&pf->hw, I40E_GLGEN_RTRIG);
+ if (reg == 0)
+ result = PCI_ERS_RESULT_RECOVERED;
+ else
+ result = PCI_ERS_RESULT_DISCONNECT;
+ }
+
+ err = pci_cleanup_aer_uncorrect_error_status(pdev);
+ if (err) {
+ dev_info(&pdev->dev,
+ "pci_cleanup_aer_uncorrect_error_status failed 0x%0x\n",
+ err);
+ /* non-fatal, continue */
+ }
+
+ return result;
+}
+
+/**
+ * i40e_pci_error_resume - restart operations after PCI error recovery
+ * @pdev: PCI device information struct
+ *
+ * Called to allow the driver to bring things back up after PCI error
+ * and/or reset recovery has finished.
+ **/
+static void i40e_pci_error_resume(struct pci_dev *pdev)
+{
+ struct i40e_pf *pf = pci_get_drvdata(pdev);
+
+ dev_info(&pdev->dev, "%s\n", __func__);
+ i40e_handle_reset_warning(pf);
+}
+
+static const struct pci_error_handlers i40e_err_handler = {
+ .error_detected = i40e_pci_error_detected,
+ .slot_reset = i40e_pci_error_slot_reset,
+ .resume = i40e_pci_error_resume,
+};
+
+static struct pci_driver i40e_driver = {
+ .name = i40e_driver_name,
+ .id_table = i40e_pci_tbl,
+ .probe = i40e_probe,
+ .remove = i40e_remove,
+ .err_handler = &i40e_err_handler,
+ .sriov_configure = i40e_pci_sriov_configure,
+};
+
+/**
+ * i40e_init_module - Driver registration routine
+ *
+ * i40e_init_module is the first routine called when the driver is
+ * loaded. All it does is register with the PCI subsystem.
+ **/
+static int __init i40e_init_module(void)
+{
+ pr_info("%s: %s - version %s\n", i40e_driver_name,
+ i40e_driver_string, i40e_driver_version_str);
+ pr_info("%s: %s\n", i40e_driver_name, i40e_copyright);
+ i40e_dbg_init();
+ return pci_register_driver(&i40e_driver);
+}
+module_init(i40e_init_module);
+
+/**
+ * i40e_exit_module - Driver exit cleanup routine
+ *
+ * i40e_exit_module is called just before the driver is removed
+ * from memory.
+ **/
+static void __exit i40e_exit_module(void)
+{
+ pci_unregister_driver(&i40e_driver);
+ i40e_dbg_exit();
+}
+module_exit(i40e_exit_module);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
new file mode 100644
index 0000000..97e1bb3
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
@@ -0,0 +1,391 @@
+/*******************************************************************************
+ *
+ * Intel Ethernet Controller XL710 Family Linux Driver
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ ******************************************************************************/
+
+#include "i40e_prototype.h"
+
+/**
+ * i40e_init_nvm_ops - Initialize NVM function pointers.
+ * @hw: pointer to the HW structure.
+ *
+ * Setups the function pointers and the NVM info structure. Should be called
+ * once per NVM initialization, e.g. inside the i40e_init_shared_code().
+ * Please notice that the NVM term is used here (& in all methods covered
+ * in this file) as an equivalent of the FLASH part mapped into the SR.
+ * We are accessing FLASH always thru the Shadow RAM.
+ **/
+i40e_status i40e_init_nvm(struct i40e_hw *hw)
+{
+ struct i40e_nvm_info *nvm = &hw->nvm;
+ i40e_status ret_code = 0;
+ u32 fla, gens;
+ u8 sr_size;
+
+ /* The SR size is stored regardless of the nvm programming mode
+ * as the blank mode may be used in the factory line.
+ */
+ gens = rd32(hw, I40E_GLNVM_GENS);
+ sr_size = ((gens & I40E_GLNVM_GENS_SR_SIZE_MASK) >>
+ I40E_GLNVM_GENS_SR_SIZE_SHIFT);
+ /* Switching to words (sr_size contains power of 2KB). */
+ nvm->sr_size = (1 << sr_size) * I40E_SR_WORDS_IN_1KB;
+
+ /* Check if we are in the normal or blank NVM programming mode. */
+ fla = rd32(hw, I40E_GLNVM_FLA);
+ if (fla & I40E_GLNVM_FLA_LOCKED_MASK) { /* Normal programming mode. */
+ /* Max NVM timeout. */
+ nvm->timeout = I40E_MAX_NVM_TIMEOUT;
+ nvm->blank_nvm_mode = false;
+ } else { /* Blank programming mode. */
+ nvm->blank_nvm_mode = true;
+ ret_code = I40E_ERR_NVM_BLANK_MODE;
+ hw_dbg(hw, "NVM init error: unsupported blank mode.\n");
+ }
+
+ return ret_code;
+}
+
+/**
+ * i40e_acquire_nvm - Generic request for acquiring the NVM ownership.
+ * @hw: pointer to the HW structure.
+ * @access: NVM access type (read or write).
+ *
+ * This function will request NVM ownership for reading
+ * via the proper Admin Command.
+ **/
+i40e_status i40e_acquire_nvm(struct i40e_hw *hw,
+ enum i40e_aq_resource_access_type access)
+{
+ i40e_status ret_code = 0;
+ u64 gtime, timeout;
+ u64 time = 0;
+
+ if (hw->nvm.blank_nvm_mode)
+ goto i40e_i40e_acquire_nvm_exit;
+
+ ret_code = i40e_aq_request_resource(hw, I40E_NVM_RESOURCE_ID, access,
+ 0, &time, NULL);
+ /* Reading the Global Device Timer. */
+ gtime = rd32(hw, I40E_GLVFGEN_TIMER);
+
+ /* Store the timeout. */
+ hw->nvm.hw_semaphore_timeout = I40E_MS_TO_GTIME(time) + gtime;
+
+ if (ret_code) {
+ /* Set the polling timeout. */
+ if (time > I40E_MAX_NVM_TIMEOUT)
+ timeout = I40E_MS_TO_GTIME(I40E_MAX_NVM_TIMEOUT)
+ + gtime;
+ else
+ timeout = hw->nvm.hw_semaphore_timeout;
+ /* Poll until the current NVM owner timeouts. */
+ while (gtime < timeout) {
+ usleep_range(10000, 20000);
+ ret_code = i40e_aq_request_resource(hw,
+ I40E_NVM_RESOURCE_ID,
+ access, 0, &time,
+ NULL);
+ if (!ret_code) {
+ hw->nvm.hw_semaphore_timeout =
+ I40E_MS_TO_GTIME(time) + gtime;
+ break;
+ }
+ gtime = rd32(hw, I40E_GLVFGEN_TIMER);
+ }
+ if (ret_code) {
+ hw->nvm.hw_semaphore_timeout = 0;
+ hw->nvm.hw_semaphore_wait =
+ I40E_MS_TO_GTIME(time) + gtime;
+ hw_dbg(hw, "NVM acquire timed out, wait %llu ms before trying again.\n",
+ time);
+ }
+ }
+
+i40e_i40e_acquire_nvm_exit:
+ return ret_code;
+}
+
+/**
+ * i40e_release_nvm - Generic request for releasing the NVM ownership.
+ * @hw: pointer to the HW structure.
+ *
+ * This function will release NVM resource via the proper Admin Command.
+ **/
+void i40e_release_nvm(struct i40e_hw *hw)
+{
+ if (!hw->nvm.blank_nvm_mode)
+ i40e_aq_release_resource(hw, I40E_NVM_RESOURCE_ID, 0, NULL);
+}
+
+/**
+ * i40e_poll_sr_srctl_done_bit - Polls the GLNVM_SRCTL done bit.
+ * @hw: pointer to the HW structure.
+ *
+ * Polls the SRCTL Shadow RAM register done bit.
+ **/
+static i40e_status i40e_poll_sr_srctl_done_bit(struct i40e_hw *hw)
+{
+ i40e_status ret_code = I40E_ERR_TIMEOUT;
+ u32 srctl, wait_cnt;
+
+ /* Poll the I40E_GLNVM_SRCTL until the done bit is set. */
+ for (wait_cnt = 0; wait_cnt < I40E_SRRD_SRCTL_ATTEMPTS; wait_cnt++) {
+ srctl = rd32(hw, I40E_GLNVM_SRCTL);
+ if (srctl & I40E_GLNVM_SRCTL_DONE_MASK) {
+ ret_code = 0;
+ break;
+ }
+ udelay(5);
+ }
+ if (ret_code == I40E_ERR_TIMEOUT)
+ hw_dbg(hw, "Done bit in GLNVM_SRCTL not set");
+ return ret_code;
+}
+
+/**
+ * i40e_read_nvm_srctl - Reads Shadow RAM.
+ * @hw: pointer to the HW structure.
+ * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF).
+ * @data: word read from the Shadow RAM.
+ *
+ * Reads 16 bit word from the Shadow RAM using the GLNVM_SRCTL register.
+ **/
+static i40e_status i40e_read_nvm_srctl(struct i40e_hw *hw, u16 offset,
+ u16 *data)
+{
+ i40e_status ret_code = I40E_ERR_TIMEOUT;
+ u32 sr_reg;
+
+ if (offset >= hw->nvm.sr_size) {
+ hw_dbg(hw, "NVM read error: Offset beyond Shadow RAM limit.\n");
+ ret_code = I40E_ERR_PARAM;
+ goto read_nvm_exit;
+ }
+
+ /* Poll the done bit first. */
+ ret_code = i40e_poll_sr_srctl_done_bit(hw);
+ if (!ret_code) {
+ /* Write the address and start reading. */
+ sr_reg = (u32)(offset << I40E_GLNVM_SRCTL_ADDR_SHIFT) |
+ (1 << I40E_GLNVM_SRCTL_START_SHIFT);
+ wr32(hw, I40E_GLNVM_SRCTL, sr_reg);
+
+ /* Poll I40E_GLNVM_SRCTL until the done bit is set. */
+ ret_code = i40e_poll_sr_srctl_done_bit(hw);
+ if (!ret_code) {
+ sr_reg = rd32(hw, I40E_GLNVM_SRDATA);
+ *data = (u16)((sr_reg &
+ I40E_GLNVM_SRDATA_RDDATA_MASK)
+ >> I40E_GLNVM_SRDATA_RDDATA_SHIFT);
+ }
+ }
+ if (ret_code)
+ hw_dbg(hw, "NVM read error: Couldn't access Shadow RAM address: 0x%x\n",
+ offset);
+
+read_nvm_exit:
+ return ret_code;
+}
+
+/**
+ * i40e_read_nvm_word - Reads Shadow RAM word.
+ * @hw: pointer to the HW structure.
+ * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF).
+ * @data: word read from the Shadow RAM.
+ *
+ * Reads 16 bit word from the Shadow RAM. Each read is preceded
+ * with the NVM ownership taking and followed by the release.
+ **/
+i40e_status i40e_read_nvm_word(struct i40e_hw *hw, u16 offset,
+ u16 *data)
+{
+ i40e_status ret_code = 0;
+
+ ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ);
+ if (!ret_code) {
+ ret_code = i40e_read_nvm_srctl(hw, offset, data);
+ i40e_release_nvm(hw);
+ }
+
+ return ret_code;
+}
+
+/**
+ * i40e_read_nvm_buffer - Reads Shadow RAM buffer.
+ * @hw: pointer to the HW structure.
+ * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF).
+ * @words: number of words to read (in) &
+ * number of words read before the NVM ownership timeout (out).
+ * @data: words read from the Shadow RAM.
+ *
+ * Reads 16 bit words (data buffer) from the SR using the i40e_read_nvm_srrd()
+ * method. The buffer read is preceded by the NVM ownership take
+ * and followed by the release.
+ **/
+i40e_status i40e_read_nvm_buffer(struct i40e_hw *hw, u16 offset,
+ u16 *words, u16 *data)
+{
+ i40e_status ret_code = 0;
+ u16 index, word;
+ u32 time;
+
+ ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ);
+ if (!ret_code) {
+ /* Loop thru the selected region. */
+ for (word = 0; word < *words; word++) {
+ index = offset + word;
+ ret_code = i40e_read_nvm_srctl(hw, index, &data[word]);
+ if (ret_code)
+ break;
+ /* Check if we didn't exceeded the semaphore timeout. */
+ time = rd32(hw, I40E_GLVFGEN_TIMER);
+ if (time >= hw->nvm.hw_semaphore_timeout) {
+ ret_code = I40E_ERR_TIMEOUT;
+ hw_dbg(hw, "NVM read error: timeout.\n");
+ break;
+ }
+ }
+ /* Update the number of words read from the Shadow RAM. */
+ *words = word;
+ /* Release the NVM ownership. */
+ i40e_release_nvm(hw);
+ }
+
+ return ret_code;
+}
+
+/**
+ * i40e_calc_nvm_checksum - Calculates and returns the checksum
+ * @hw: pointer to hardware structure
+ *
+ * This function calculate SW Checksum that covers the whole 64kB shadow RAM
+ * except the VPD and PCIe ALT Auto-load modules. The structure and size of VPD
+ * is customer specific and unknown. Therefore, this function skips all maximum
+ * possible size of VPD (1kB).
+ **/
+static i40e_status i40e_calc_nvm_checksum(struct i40e_hw *hw,
+ u16 *checksum)
+{
+ i40e_status ret_code = 0;
+ u16 pcie_alt_module = 0;
+ u16 checksum_local = 0;
+ u16 vpd_module = 0;
+ u16 word = 0;
+ u32 i = 0;
+
+ /* read pointer to VPD area */
+ ret_code = i40e_read_nvm_srctl(hw, I40E_SR_VPD_PTR, &vpd_module);
+ if (ret_code) {
+ ret_code = I40E_ERR_NVM_CHECKSUM;
+ goto i40e_calc_nvm_checksum_exit;
+ }
+
+ /* read pointer to PCIe Alt Auto-load module */
+ ret_code = i40e_read_nvm_srctl(hw, I40E_SR_PCIE_ALT_AUTO_LOAD_PTR,
+ &pcie_alt_module);
+ if (ret_code) {
+ ret_code = I40E_ERR_NVM_CHECKSUM;
+ goto i40e_calc_nvm_checksum_exit;
+ }
+
+ /* Calculate SW checksum that covers the whole 64kB shadow RAM
+ * except the VPD and PCIe ALT Auto-load modules
+ */
+ for (i = 0; i < hw->nvm.sr_size; i++) {
+ /* Skip Checksum word */
+ if (i == I40E_SR_SW_CHECKSUM_WORD)
+ i++;
+ /* Skip VPD module (convert byte size to word count) */
+ if (i == (u32)vpd_module) {
+ i += (I40E_SR_VPD_MODULE_MAX_SIZE / 2);
+ if (i >= hw->nvm.sr_size)
+ break;
+ }
+ /* Skip PCIe ALT module (convert byte size to word count) */
+ if (i == (u32)pcie_alt_module) {
+ i += (I40E_SR_PCIE_ALT_MODULE_MAX_SIZE / 2);
+ if (i >= hw->nvm.sr_size)
+ break;
+ }
+
+ ret_code = i40e_read_nvm_srctl(hw, (u16)i, &word);
+ if (ret_code) {
+ ret_code = I40E_ERR_NVM_CHECKSUM;
+ goto i40e_calc_nvm_checksum_exit;
+ }
+ checksum_local += word;
+ }
+
+ *checksum = (u16)I40E_SR_SW_CHECKSUM_BASE - checksum_local;
+
+i40e_calc_nvm_checksum_exit:
+ return ret_code;
+}
+
+/**
+ * i40e_validate_nvm_checksum - Validate EEPROM checksum
+ * @hw: pointer to hardware structure
+ * @checksum: calculated checksum
+ *
+ * Performs checksum calculation and validates the NVM SW checksum. If the
+ * caller does not need checksum, the value can be NULL.
+ **/
+i40e_status i40e_validate_nvm_checksum(struct i40e_hw *hw,
+ u16 *checksum)
+{
+ i40e_status ret_code = 0;
+ u16 checksum_sr = 0;
+ u16 checksum_local;
+
+ ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ);
+ if (ret_code)
+ goto i40e_validate_nvm_checksum_exit;
+
+ ret_code = i40e_calc_nvm_checksum(hw, &checksum_local);
+ if (ret_code)
+ goto i40e_validate_nvm_checksum_free;
+
+ /* Do not use i40e_read_nvm_word() because we do not want to take
+ * the synchronization semaphores twice here.
+ */
+ i40e_read_nvm_srctl(hw, I40E_SR_SW_CHECKSUM_WORD, &checksum_sr);
+
+ /* Verify read checksum from EEPROM is the same as
+ * calculated checksum
+ */
+ if (checksum_local != checksum_sr)
+ ret_code = I40E_ERR_NVM_CHECKSUM;
+
+ /* If the user cares, return the calculated checksum */
+ if (checksum)
+ *checksum = checksum_local;
+
+i40e_validate_nvm_checksum_free:
+ i40e_release_nvm(hw);
+
+i40e_validate_nvm_checksum_exit:
+ return ret_code;
+}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_osdep.h b/drivers/net/ethernet/intel/i40e/i40e_osdep.h
new file mode 100644
index 0000000..702c81b
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_osdep.h
@@ -0,0 +1,82 @@
+/*******************************************************************************
+ *
+ * Intel Ethernet Controller XL710 Family Linux Driver
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ ******************************************************************************/
+
+#ifndef _I40E_OSDEP_H_
+#define _I40E_OSDEP_H_
+
+#include <linux/types.h>
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <linux/tcp.h>
+#include <linux/pci.h>
+#include <linux/highuid.h>
+
+/* get readq/writeq support for 32 bit kernels, use the low-first version */
+#include <asm-generic/io-64-nonatomic-lo-hi.h>
+
+/* File to be the magic between shared code and
+ * actual OS primitives
+ */
+
+#define hw_dbg(hw, S, A...) do {} while (0)
+
+#define wr32(a, reg, value) writel((value), ((a)->hw_addr + (reg)))
+#define rd32(a, reg) readl((a)->hw_addr + (reg))
+
+#define wr64(a, reg, value) writeq((value), ((a)->hw_addr + (reg)))
+#define rd64(a, reg) readq((a)->hw_addr + (reg))
+#define i40e_flush(a) readl((a)->hw_addr + I40E_GLGEN_STAT)
+
+/* memory allocation tracking */
+struct i40e_dma_mem {
+ void *va;
+ dma_addr_t pa;
+ u32 size;
+} __packed;
+
+#define i40e_allocate_dma_mem(h, m, unused, s, a) \
+ i40e_allocate_dma_mem_d(h, m, s, a)
+#define i40e_free_dma_mem(h, m) i40e_free_dma_mem_d(h, m)
+
+struct i40e_virt_mem {
+ void *va;
+ u32 size;
+} __packed;
+
+#define i40e_allocate_virt_mem(h, m, s) i40e_allocate_virt_mem_d(h, m, s)
+#define i40e_free_virt_mem(h, m) i40e_free_virt_mem_d(h, m)
+
+#define i40e_debug(h, m, s, ...) \
+do { \
+ if (((m) & (h)->debug_mask)) \
+ pr_info("i40e %02x.%x " s, \
+ (h)->bus.device, (h)->bus.func, \
+ ##__VA_ARGS__); \
+} while (0)
+
+typedef enum i40e_status_code i40e_status;
+#endif /* _I40E_OSDEP_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
new file mode 100644
index 0000000..f75bb9c
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
@@ -0,0 +1,239 @@
+/*******************************************************************************
+ *
+ * Intel Ethernet Controller XL710 Family Linux Driver
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ ******************************************************************************/
+
+#ifndef _I40E_PROTOTYPE_H_
+#define _I40E_PROTOTYPE_H_
+
+#include "i40e_type.h"
+#include "i40e_alloc.h"
+#include "i40e_virtchnl.h"
+
+/* Prototypes for shared code functions that are not in
+ * the standard function pointer structures. These are
+ * mostly because they are needed even before the init
+ * has happened and will assist in the early SW and FW
+ * setup.
+ */
+
+/* adminq functions */
+i40e_status i40e_init_adminq(struct i40e_hw *hw);
+i40e_status i40e_shutdown_adminq(struct i40e_hw *hw);
+void i40e_adminq_init_ring_data(struct i40e_hw *hw);
+i40e_status i40e_clean_arq_element(struct i40e_hw *hw,
+ struct i40e_arq_event_info *e,
+ u16 *events_pending);
+i40e_status i40e_asq_send_command(struct i40e_hw *hw,
+ struct i40e_aq_desc *desc,
+ void *buff, /* can be NULL */
+ u16 buff_size,
+ struct i40e_asq_cmd_details *cmd_details);
+bool i40e_asq_done(struct i40e_hw *hw);
+
+/* debug function for adminq */
+void i40e_debug_aq(struct i40e_hw *hw,
+ enum i40e_debug_mask mask,
+ void *desc,
+ void *buffer);
+
+void i40e_idle_aq(struct i40e_hw *hw);
+void i40e_resume_aq(struct i40e_hw *hw);
+
+u32 i40e_led_get(struct i40e_hw *hw);
+void i40e_led_set(struct i40e_hw *hw, u32 mode);
+
+/* admin send queue commands */
+
+i40e_status i40e_aq_get_firmware_version(struct i40e_hw *hw,
+ u16 *fw_major_version, u16 *fw_minor_version,
+ u16 *api_major_version, u16 *api_minor_version,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_queue_shutdown(struct i40e_hw *hw,
+ bool unloading);
+i40e_status i40e_aq_set_phy_reset(struct i40e_hw *hw,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_set_default_vsi(struct i40e_hw *hw, u16 vsi_id,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_set_link_restart_an(struct i40e_hw *hw,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_get_link_info(struct i40e_hw *hw,
+ bool enable_lse, struct i40e_link_status *link,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_set_local_advt_reg(struct i40e_hw *hw,
+ u64 advt_reg,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_send_driver_version(struct i40e_hw *hw,
+ struct i40e_driver_version *dv,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_add_vsi(struct i40e_hw *hw,
+ struct i40e_vsi_context *vsi_ctx,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_set_vsi_broadcast(struct i40e_hw *hw,
+ u16 vsi_id, bool set_filter,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_set_vsi_unicast_promiscuous(struct i40e_hw *hw,
+ u16 vsi_id, bool set, struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_set_vsi_multicast_promiscuous(struct i40e_hw *hw,
+ u16 vsi_id, bool set, struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_get_vsi_params(struct i40e_hw *hw,
+ struct i40e_vsi_context *vsi_ctx,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_update_vsi_params(struct i40e_hw *hw,
+ struct i40e_vsi_context *vsi_ctx,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_add_veb(struct i40e_hw *hw, u16 uplink_seid,
+ u16 downlink_seid, u8 enabled_tc,
+ bool default_port, u16 *pveb_seid,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_get_veb_parameters(struct i40e_hw *hw,
+ u16 veb_seid, u16 *switch_id, bool *floating,
+ u16 *statistic_index, u16 *vebs_used,
+ u16 *vebs_free,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_add_macvlan(struct i40e_hw *hw, u16 vsi_id,
+ struct i40e_aqc_add_macvlan_element_data *mv_list,
+ u16 count, struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_remove_macvlan(struct i40e_hw *hw, u16 vsi_id,
+ struct i40e_aqc_remove_macvlan_element_data *mv_list,
+ u16 count, struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_add_vlan(struct i40e_hw *hw, u16 vsi_id,
+ struct i40e_aqc_add_remove_vlan_element_data *v_list,
+ u8 count, struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_remove_vlan(struct i40e_hw *hw, u16 vsi_id,
+ struct i40e_aqc_add_remove_vlan_element_data *v_list,
+ u8 count, struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_send_msg_to_vf(struct i40e_hw *hw, u16 vfid,
+ u32 v_opcode, u32 v_retval, u8 *msg, u16 msglen,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_get_switch_config(struct i40e_hw *hw,
+ struct i40e_aqc_get_switch_config_resp *buf,
+ u16 buf_size, u16 *start_seid,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_request_resource(struct i40e_hw *hw,
+ enum i40e_aq_resources_ids resource,
+ enum i40e_aq_resource_access_type access,
+ u8 sdp_number, u64 *timeout,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_release_resource(struct i40e_hw *hw,
+ enum i40e_aq_resources_ids resource,
+ u8 sdp_number,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_read_nvm(struct i40e_hw *hw, u8 module_pointer,
+ u32 offset, u16 length, void *data,
+ bool last_command,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_discover_capabilities(struct i40e_hw *hw,
+ void *buff, u16 buff_size, u16 *data_size,
+ enum i40e_admin_queue_opc list_type_opc,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_update_nvm(struct i40e_hw *hw, u8 module_pointer,
+ u32 offset, u16 length, void *data,
+ bool last_command,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_get_lldp_mib(struct i40e_hw *hw, u8 bridge_type,
+ u8 mib_type, void *buff, u16 buff_size,
+ u16 *local_len, u16 *remote_len,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_cfg_lldp_mib_change_event(struct i40e_hw *hw,
+ bool enable_update,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_stop_lldp(struct i40e_hw *hw, bool shutdown_agent,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_start_lldp(struct i40e_hw *hw,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_delete_element(struct i40e_hw *hw, u16 seid,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_mac_address_write(struct i40e_hw *hw,
+ u16 flags, u8 *mac_addr,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_set_hmc_resource_profile(struct i40e_hw *hw,
+ enum i40e_aq_hmc_profile profile,
+ u8 pe_vf_enabled_count,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_config_switch_comp_bw_limit(struct i40e_hw *hw,
+ u16 seid, u16 credit, u8 max_bw,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_config_vsi_tc_bw(struct i40e_hw *hw, u16 seid,
+ struct i40e_aqc_configure_vsi_tc_bw_data *bw_data,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_query_vsi_bw_config(struct i40e_hw *hw,
+ u16 seid,
+ struct i40e_aqc_query_vsi_bw_config_resp *bw_data,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_query_vsi_ets_sla_config(struct i40e_hw *hw,
+ u16 seid,
+ struct i40e_aqc_query_vsi_ets_sla_config_resp *bw_data,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_query_switch_comp_ets_config(struct i40e_hw *hw,
+ u16 seid,
+ struct i40e_aqc_query_switching_comp_ets_config_resp *bw_data,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_query_port_ets_config(struct i40e_hw *hw,
+ u16 seid,
+ struct i40e_aqc_query_port_ets_config_resp *bw_data,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_query_switch_comp_bw_config(struct i40e_hw *hw,
+ u16 seid,
+ struct i40e_aqc_query_switching_comp_bw_config_resp *bw_data,
+ struct i40e_asq_cmd_details *cmd_details);
+/* i40e_common */
+i40e_status i40e_init_shared_code(struct i40e_hw *hw);
+i40e_status i40e_pf_reset(struct i40e_hw *hw);
+void i40e_clear_pxe_mode(struct i40e_hw *hw);
+bool i40e_get_link_status(struct i40e_hw *hw);
+i40e_status i40e_get_mac_addr(struct i40e_hw *hw,
+ u8 *mac_addr);
+i40e_status i40e_validate_mac_addr(u8 *mac_addr);
+i40e_status i40e_read_lldp_cfg(struct i40e_hw *hw,
+ struct i40e_lldp_variables *lldp_cfg);
+/* prototype for functions used for NVM access */
+i40e_status i40e_init_nvm(struct i40e_hw *hw);
+i40e_status i40e_acquire_nvm(struct i40e_hw *hw,
+ enum i40e_aq_resource_access_type access);
+void i40e_release_nvm(struct i40e_hw *hw);
+i40e_status i40e_read_nvm_srrd(struct i40e_hw *hw, u16 offset,
+ u16 *data);
+i40e_status i40e_read_nvm_word(struct i40e_hw *hw, u16 offset,
+ u16 *data);
+i40e_status i40e_read_nvm_buffer(struct i40e_hw *hw, u16 offset,
+ u16 *words, u16 *data);
+i40e_status i40e_validate_nvm_checksum(struct i40e_hw *hw,
+ u16 *checksum);
+
+/* prototype for functions used for SW locks */
+
+/* i40e_common for VF drivers*/
+void i40e_vf_parse_hw_config(struct i40e_hw *hw,
+ struct i40e_virtchnl_vf_resource *msg);
+i40e_status i40e_vf_reset(struct i40e_hw *hw);
+i40e_status i40e_aq_send_msg_to_pf(struct i40e_hw *hw,
+ enum i40e_virtchnl_ops v_opcode,
+ i40e_status v_retval,
+ u8 *msg, u16 msglen,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_set_filter_control(struct i40e_hw *hw,
+ struct i40e_filter_control_settings *settings);
+#endif /* _I40E_PROTOTYPE_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_register.h b/drivers/net/ethernet/intel/i40e/i40e_register.h
new file mode 100644
index 0000000..6bd333c
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_register.h
@@ -0,0 +1,4688 @@
+/*******************************************************************************
+ *
+ * Intel Ethernet Controller XL710 Family Linux Driver
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ ******************************************************************************/
+
+#ifndef _I40E_REGISTER_H_
+#define _I40E_REGISTER_H_
+
+#define I40E_GLPCI_PM_MUX_NPQ 0x0009C4F4
+#define I40E_GLPCI_PM_MUX_NPQ_NPQ_NUM_PORT_SEL_SHIFT 0
+#define I40E_GLPCI_PM_MUX_NPQ_NPQ_NUM_PORT_SEL_MASK (0x7 << I40E_GLPCI_PM_MUX_NPQ_NPQ_NUM_PORT_SEL_SHIFT)
+#define I40E_GLPCI_PM_MUX_NPQ_INNER_NPQ_SEL_SHIFT 16
+#define I40E_GLPCI_PM_MUX_NPQ_INNER_NPQ_SEL_MASK (0x1F << I40E_GLPCI_PM_MUX_NPQ_INNER_NPQ_SEL_SHIFT)
+#define I40E_GLPCI_PM_MUX_PFB 0x0009C4F0
+#define I40E_GLPCI_PM_MUX_PFB_PFB_PORT_SEL_SHIFT 0
+#define I40E_GLPCI_PM_MUX_PFB_PFB_PORT_SEL_MASK (0x1F << I40E_GLPCI_PM_MUX_PFB_PFB_PORT_SEL_SHIFT)
+#define I40E_GLPCI_PM_MUX_PFB_INNER_PORT_SEL_SHIFT 16
+#define I40E_GLPCI_PM_MUX_PFB_INNER_PORT_SEL_MASK (0x7 << I40E_GLPCI_PM_MUX_PFB_INNER_PORT_SEL_SHIFT)
+#define I40E_GLPCI_SPARE_BITS_0 0x0009C4F8
+#define I40E_GLPCI_SPARE_BITS_0_SPARE_BITS_SHIFT 0
+#define I40E_GLPCI_SPARE_BITS_0_SPARE_BITS_MASK (0xFFFFFFFF << I40E_GLPCI_SPARE_BITS_0_SPARE_BITS_SHIFT)
+#define I40E_GLPCI_SPARE_BITS_1 0x0009C4FC
+#define I40E_GLPCI_SPARE_BITS_1_SPARE_BITS_SHIFT 0
+#define I40E_GLPCI_SPARE_BITS_1_SPARE_BITS_MASK (0xFFFFFFFF << I40E_GLPCI_SPARE_BITS_1_SPARE_BITS_SHIFT)
+#define I40E_PFPCI_PF_FLUSH_DONE 0x0009C800
+#define I40E_PFPCI_PF_FLUSH_DONE_FLUSH_DONE_SHIFT 0
+#define I40E_PFPCI_PF_FLUSH_DONE_FLUSH_DONE_MASK (0x1 << I40E_PFPCI_PF_FLUSH_DONE_FLUSH_DONE_SHIFT)
+#define I40E_PFPCI_VF_FLUSH_DONE 0x0009C600
+#define I40E_PFPCI_VF_FLUSH_DONE_FLUSH_DONE_SHIFT 0
+#define I40E_PFPCI_VF_FLUSH_DONE_FLUSH_DONE_MASK (0x1 << I40E_PFPCI_VF_FLUSH_DONE_FLUSH_DONE_SHIFT)
+#define I40E_PFPCI_VM_FLUSH_DONE 0x0009C880
+#define I40E_PFPCI_VM_FLUSH_DONE_FLUSH_DONE_SHIFT 0
+#define I40E_PFPCI_VM_FLUSH_DONE_FLUSH_DONE_MASK (0x1 << I40E_PFPCI_VM_FLUSH_DONE_FLUSH_DONE_SHIFT)
+#define I40E_PF_ARQBAH 0x00080180
+#define I40E_PF_ARQBAH_ARQBAH_SHIFT 0
+#define I40E_PF_ARQBAH_ARQBAH_MASK (0xFFFFFFFF << I40E_PF_ARQBAH_ARQBAH_SHIFT)
+#define I40E_PF_ARQBAL 0x00080080
+#define I40E_PF_ARQBAL_ARQBAL_SHIFT 0
+#define I40E_PF_ARQBAL_ARQBAL_MASK (0xFFFFFFFF << I40E_PF_ARQBAL_ARQBAL_SHIFT)
+#define I40E_PF_ARQH 0x00080380
+#define I40E_PF_ARQH_ARQH_SHIFT 0
+#define I40E_PF_ARQH_ARQH_MASK (0x3FF << I40E_PF_ARQH_ARQH_SHIFT)
+#define I40E_PF_ARQLEN 0x00080280
+#define I40E_PF_ARQLEN_ARQLEN_SHIFT 0
+#define I40E_PF_ARQLEN_ARQLEN_MASK (0x3FF << I40E_PF_ARQLEN_ARQLEN_SHIFT)
+#define I40E_PF_ARQLEN_ARQVFE_SHIFT 28
+#define I40E_PF_ARQLEN_ARQVFE_MASK (0x1 << I40E_PF_ARQLEN_ARQVFE_SHIFT)
+#define I40E_PF_ARQLEN_ARQOVFL_SHIFT 29
+#define I40E_PF_ARQLEN_ARQOVFL_MASK (0x1 << I40E_PF_ARQLEN_ARQOVFL_SHIFT)
+#define I40E_PF_ARQLEN_ARQCRIT_SHIFT 30
+#define I40E_PF_ARQLEN_ARQCRIT_MASK (0x1 << I40E_PF_ARQLEN_ARQCRIT_SHIFT)
+#define I40E_PF_ARQLEN_ARQENABLE_SHIFT 31
+#define I40E_PF_ARQLEN_ARQENABLE_MASK (0x1 << I40E_PF_ARQLEN_ARQENABLE_SHIFT)
+#define I40E_PF_ARQT 0x00080480
+#define I40E_PF_ARQT_ARQT_SHIFT 0
+#define I40E_PF_ARQT_ARQT_MASK (0x3FF << I40E_PF_ARQT_ARQT_SHIFT)
+#define I40E_PF_ATQBAH 0x00080100
+#define I40E_PF_ATQBAH_ATQBAH_SHIFT 0
+#define I40E_PF_ATQBAH_ATQBAH_MASK (0xFFFFFFFF << I40E_PF_ATQBAH_ATQBAH_SHIFT)
+#define I40E_PF_ATQBAL 0x00080000
+#define I40E_PF_ATQBAL_ATQBAL_SHIFT 0
+#define I40E_PF_ATQBAL_ATQBAL_MASK (0xFFFFFFFF << I40E_PF_ATQBAL_ATQBAL_SHIFT)
+#define I40E_PF_ATQH 0x00080300
+#define I40E_PF_ATQH_ATQH_SHIFT 0
+#define I40E_PF_ATQH_ATQH_MASK (0x3FF << I40E_PF_ATQH_ATQH_SHIFT)
+#define I40E_PF_ATQLEN 0x00080200
+#define I40E_PF_ATQLEN_ATQLEN_SHIFT 0
+#define I40E_PF_ATQLEN_ATQLEN_MASK (0x3FF << I40E_PF_ATQLEN_ATQLEN_SHIFT)
+#define I40E_PF_ATQLEN_ATQVFE_SHIFT 28
+#define I40E_PF_ATQLEN_ATQVFE_MASK (0x1 << I40E_PF_ATQLEN_ATQVFE_SHIFT)
+#define I40E_PF_ATQLEN_ATQOVFL_SHIFT 29
+#define I40E_PF_ATQLEN_ATQOVFL_MASK (0x1 << I40E_PF_ATQLEN_ATQOVFL_SHIFT)
+#define I40E_PF_ATQLEN_ATQCRIT_SHIFT 30
+#define I40E_PF_ATQLEN_ATQCRIT_MASK (0x1 << I40E_PF_ATQLEN_ATQCRIT_SHIFT)
+#define I40E_PF_ATQLEN_ATQENABLE_SHIFT 31
+#define I40E_PF_ATQLEN_ATQENABLE_MASK (0x1 << I40E_PF_ATQLEN_ATQENABLE_SHIFT)
+#define I40E_PF_ATQT 0x00080400
+#define I40E_PF_ATQT_ATQT_SHIFT 0
+#define I40E_PF_ATQT_ATQT_MASK (0x3FF << I40E_PF_ATQT_ATQT_SHIFT)
+#define I40E_VF_ARQBAH(_VF) (0x00081400 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VF_ARQBAH_MAX_INDEX 127
+#define I40E_VF_ARQBAH_ARQBAH_SHIFT 0
+#define I40E_VF_ARQBAH_ARQBAH_MASK (0xFFFFFFFF << I40E_VF_ARQBAH_ARQBAH_SHIFT)
+#define I40E_VF_ARQBAL(_VF) (0x00080C00 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VF_ARQBAL_MAX_INDEX 127
+#define I40E_VF_ARQBAL_ARQBAL_SHIFT 0
+#define I40E_VF_ARQBAL_ARQBAL_MASK (0xFFFFFFFF << I40E_VF_ARQBAL_ARQBAL_SHIFT)
+#define I40E_VF_ARQH(_VF) (0x00082400 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VF_ARQH_MAX_INDEX 127
+#define I40E_VF_ARQH_ARQH_SHIFT 0
+#define I40E_VF_ARQH_ARQH_MASK (0x3FF << I40E_VF_ARQH_ARQH_SHIFT)
+#define I40E_VF_ARQLEN(_VF) (0x00081C00 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VF_ARQLEN_MAX_INDEX 127
+#define I40E_VF_ARQLEN_ARQLEN_SHIFT 0
+#define I40E_VF_ARQLEN_ARQLEN_MASK (0x3FF << I40E_VF_ARQLEN_ARQLEN_SHIFT)
+#define I40E_VF_ARQLEN_ARQVFE_SHIFT 28
+#define I40E_VF_ARQLEN_ARQVFE_MASK (0x1 << I40E_VF_ARQLEN_ARQVFE_SHIFT)
+#define I40E_VF_ARQLEN_ARQOVFL_SHIFT 29
+#define I40E_VF_ARQLEN_ARQOVFL_MASK (0x1 << I40E_VF_ARQLEN_ARQOVFL_SHIFT)
+#define I40E_VF_ARQLEN_ARQCRIT_SHIFT 30
+#define I40E_VF_ARQLEN_ARQCRIT_MASK (0x1 << I40E_VF_ARQLEN_ARQCRIT_SHIFT)
+#define I40E_VF_ARQLEN_ARQENABLE_SHIFT 31
+#define I40E_VF_ARQLEN_ARQENABLE_MASK (0x1 << I40E_VF_ARQLEN_ARQENABLE_SHIFT)
+#define I40E_VF_ARQT(_VF) (0x00082C00 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VF_ARQT_MAX_INDEX 127
+#define I40E_VF_ARQT_ARQT_SHIFT 0
+#define I40E_VF_ARQT_ARQT_MASK (0x3FF << I40E_VF_ARQT_ARQT_SHIFT)
+#define I40E_VF_ATQBAH(_VF) (0x00081000 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VF_ATQBAH_MAX_INDEX 127
+#define I40E_VF_ATQBAH_ATQBAH_SHIFT 0
+#define I40E_VF_ATQBAH_ATQBAH_MASK (0xFFFFFFFF << I40E_VF_ATQBAH_ATQBAH_SHIFT)
+#define I40E_VF_ATQBAL(_VF) (0x00080800 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VF_ATQBAL_MAX_INDEX 127
+#define I40E_VF_ATQBAL_ATQBAL_SHIFT 0
+#define I40E_VF_ATQBAL_ATQBAL_MASK (0xFFFFFFFF << I40E_VF_ATQBAL_ATQBAL_SHIFT)
+#define I40E_VF_ATQH(_VF) (0x00082000 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VF_ATQH_MAX_INDEX 127
+#define I40E_VF_ATQH_ATQH_SHIFT 0
+#define I40E_VF_ATQH_ATQH_MASK (0x3FF << I40E_VF_ATQH_ATQH_SHIFT)
+#define I40E_VF_ATQLEN(_VF) (0x00081800 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VF_ATQLEN_MAX_INDEX 127
+#define I40E_VF_ATQLEN_ATQLEN_SHIFT 0
+#define I40E_VF_ATQLEN_ATQLEN_MASK (0x3FF << I40E_VF_ATQLEN_ATQLEN_SHIFT)
+#define I40E_VF_ATQLEN_ATQVFE_SHIFT 28
+#define I40E_VF_ATQLEN_ATQVFE_MASK (0x1 << I40E_VF_ATQLEN_ATQVFE_SHIFT)
+#define I40E_VF_ATQLEN_ATQOVFL_SHIFT 29
+#define I40E_VF_ATQLEN_ATQOVFL_MASK (0x1 << I40E_VF_ATQLEN_ATQOVFL_SHIFT)
+#define I40E_VF_ATQLEN_ATQCRIT_SHIFT 30
+#define I40E_VF_ATQLEN_ATQCRIT_MASK (0x1 << I40E_VF_ATQLEN_ATQCRIT_SHIFT)
+#define I40E_VF_ATQLEN_ATQENABLE_SHIFT 31
+#define I40E_VF_ATQLEN_ATQENABLE_MASK (0x1 << I40E_VF_ATQLEN_ATQENABLE_SHIFT)
+#define I40E_VF_ATQT(_VF) (0x00082800 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VF_ATQT_MAX_INDEX 127
+#define I40E_VF_ATQT_ATQT_SHIFT 0
+#define I40E_VF_ATQT_ATQT_MASK (0x3FF << I40E_VF_ATQT_ATQT_SHIFT)
+#define I40E_PRT_L2TAGSEN 0x001C0B20
+#define I40E_PRT_L2TAGSEN_ENABLE_SHIFT 0
+#define I40E_PRT_L2TAGSEN_ENABLE_MASK (0xFF << I40E_PRT_L2TAGSEN_ENABLE_SHIFT)
+#define I40E_PFCM_LAN_ERRDATA 0x0010C080
+#define I40E_PFCM_LAN_ERRDATA_ERROR_CODE_SHIFT 0
+#define I40E_PFCM_LAN_ERRDATA_ERROR_CODE_MASK (0xF << I40E_PFCM_LAN_ERRDATA_ERROR_CODE_SHIFT)
+#define I40E_PFCM_LAN_ERRDATA_Q_TYPE_SHIFT 4
+#define I40E_PFCM_LAN_ERRDATA_Q_TYPE_MASK (0x7 << I40E_PFCM_LAN_ERRDATA_Q_TYPE_SHIFT)
+#define I40E_PFCM_LAN_ERRDATA_Q_NUM_SHIFT 8
+#define I40E_PFCM_LAN_ERRDATA_Q_NUM_MASK (0xFFF << I40E_PFCM_LAN_ERRDATA_Q_NUM_SHIFT)
+#define I40E_PFCM_LAN_ERRINFO 0x0010C000
+#define I40E_PFCM_LAN_ERRINFO_ERROR_VALID_SHIFT 0
+#define I40E_PFCM_LAN_ERRINFO_ERROR_VALID_MASK (0x1 << I40E_PFCM_LAN_ERRINFO_ERROR_VALID_SHIFT)
+#define I40E_PFCM_LAN_ERRINFO_ERROR_INST_SHIFT 4
+#define I40E_PFCM_LAN_ERRINFO_ERROR_INST_MASK (0x7 << I40E_PFCM_LAN_ERRINFO_ERROR_INST_SHIFT)
+#define I40E_PFCM_LAN_ERRINFO_DBL_ERROR_CNT_SHIFT 8
+#define I40E_PFCM_LAN_ERRINFO_DBL_ERROR_CNT_MASK (0xFF << I40E_PFCM_LAN_ERRINFO_DBL_ERROR_CNT_SHIFT)
+#define I40E_PFCM_LAN_ERRINFO_RLU_ERROR_CNT_SHIFT 16
+#define I40E_PFCM_LAN_ERRINFO_RLU_ERROR_CNT_MASK (0xFF << I40E_PFCM_LAN_ERRINFO_RLU_ERROR_CNT_SHIFT)
+#define I40E_PFCM_LAN_ERRINFO_RLS_ERROR_CNT_SHIFT 24
+#define I40E_PFCM_LAN_ERRINFO_RLS_ERROR_CNT_MASK (0xFF << I40E_PFCM_LAN_ERRINFO_RLS_ERROR_CNT_SHIFT)
+#define I40E_PFCM_LANCTXCTL 0x0010C300
+#define I40E_PFCM_LANCTXCTL_QUEUE_NUM_SHIFT 0
+#define I40E_PFCM_LANCTXCTL_QUEUE_NUM_MASK (0xFFF << I40E_PFCM_LANCTXCTL_QUEUE_NUM_SHIFT)
+#define I40E_PFCM_LANCTXCTL_SUB_LINE_SHIFT 12
+#define I40E_PFCM_LANCTXCTL_SUB_LINE_MASK (0x7 << I40E_PFCM_LANCTXCTL_SUB_LINE_SHIFT)
+#define I40E_PFCM_LANCTXCTL_QUEUE_TYPE_SHIFT 15
+#define I40E_PFCM_LANCTXCTL_QUEUE_TYPE_MASK (0x3 << I40E_PFCM_LANCTXCTL_QUEUE_TYPE_SHIFT)
+#define I40E_PFCM_LANCTXCTL_OP_CODE_SHIFT 17
+#define I40E_PFCM_LANCTXCTL_OP_CODE_MASK (0x3 << I40E_PFCM_LANCTXCTL_OP_CODE_SHIFT)
+#define I40E_PFCM_LANCTXDATA(_i) (0x0010C100 + ((_i) * 128)) /* _i=0...3 */
+#define I40E_PFCM_LANCTXDATA_MAX_INDEX 3
+#define I40E_PFCM_LANCTXDATA_DATA_SHIFT 0
+#define I40E_PFCM_LANCTXDATA_DATA_MASK (0xFFFFFFFF << I40E_PFCM_LANCTXDATA_DATA_SHIFT)
+#define I40E_PFCM_LANCTXSTAT 0x0010C380
+#define I40E_PFCM_LANCTXSTAT_CTX_DONE_SHIFT 0
+#define I40E_PFCM_LANCTXSTAT_CTX_DONE_MASK (0x1 << I40E_PFCM_LANCTXSTAT_CTX_DONE_SHIFT)
+#define I40E_PFCM_LANCTXSTAT_CTX_MISS_SHIFT 1
+#define I40E_PFCM_LANCTXSTAT_CTX_MISS_MASK (0x1 << I40E_PFCM_LANCTXSTAT_CTX_MISS_SHIFT)
+#define I40E_PFCM_PE_ERRDATA 0x00138D00
+#define I40E_PFCM_PE_ERRDATA_ERROR_CODE_SHIFT 0
+#define I40E_PFCM_PE_ERRDATA_ERROR_CODE_MASK (0xF << I40E_PFCM_PE_ERRDATA_ERROR_CODE_SHIFT)
+#define I40E_PFCM_PE_ERRDATA_Q_TYPE_SHIFT 4
+#define I40E_PFCM_PE_ERRDATA_Q_TYPE_MASK (0x7 << I40E_PFCM_PE_ERRDATA_Q_TYPE_SHIFT)
+#define I40E_PFCM_PE_ERRDATA_Q_NUM_SHIFT 8
+#define I40E_PFCM_PE_ERRDATA_Q_NUM_MASK (0x3FFFF << I40E_PFCM_PE_ERRDATA_Q_NUM_SHIFT)
+#define I40E_PFCM_PE_ERRINFO 0x00138C80
+#define I40E_PFCM_PE_ERRINFO_ERROR_VALID_SHIFT 0
+#define I40E_PFCM_PE_ERRINFO_ERROR_VALID_MASK (0x1 << I40E_PFCM_PE_ERRINFO_ERROR_VALID_SHIFT)
+#define I40E_PFCM_PE_ERRINFO_ERROR_INST_SHIFT 4
+#define I40E_PFCM_PE_ERRINFO_ERROR_INST_MASK (0x7 << I40E_PFCM_PE_ERRINFO_ERROR_INST_SHIFT)
+#define I40E_PFCM_PE_ERRINFO_DBL_ERROR_CNT_SHIFT 8
+#define I40E_PFCM_PE_ERRINFO_DBL_ERROR_CNT_MASK (0xFF << I40E_PFCM_PE_ERRINFO_DBL_ERROR_CNT_SHIFT)
+#define I40E_PFCM_PE_ERRINFO_RLU_ERROR_CNT_SHIFT 16
+#define I40E_PFCM_PE_ERRINFO_RLU_ERROR_CNT_MASK (0xFF << I40E_PFCM_PE_ERRINFO_RLU_ERROR_CNT_SHIFT)
+#define I40E_PFCM_PE_ERRINFO_RLS_ERROR_CNT_SHIFT 24
+#define I40E_PFCM_PE_ERRINFO_RLS_ERROR_CNT_MASK (0xFF << I40E_PFCM_PE_ERRINFO_RLS_ERROR_CNT_SHIFT)
+#define I40E_VFCM_PE_ERRDATA1(_VF) (0x00138800 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VFCM_PE_ERRDATA1_MAX_INDEX 127
+#define I40E_VFCM_PE_ERRDATA1_ERROR_CODE_SHIFT 0
+#define I40E_VFCM_PE_ERRDATA1_ERROR_CODE_MASK (0xF << I40E_VFCM_PE_ERRDATA1_ERROR_CODE_SHIFT)
+#define I40E_VFCM_PE_ERRDATA1_Q_TYPE_SHIFT 4
+#define I40E_VFCM_PE_ERRDATA1_Q_TYPE_MASK (0x7 << I40E_VFCM_PE_ERRDATA1_Q_TYPE_SHIFT)
+#define I40E_VFCM_PE_ERRDATA1_Q_NUM_SHIFT 8
+#define I40E_VFCM_PE_ERRDATA1_Q_NUM_MASK (0x3FFFF << I40E_VFCM_PE_ERRDATA1_Q_NUM_SHIFT)
+#define I40E_VFCM_PE_ERRINFO1(_VF) (0x00138400 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VFCM_PE_ERRINFO1_MAX_INDEX 127
+#define I40E_VFCM_PE_ERRINFO1_ERROR_VALID_SHIFT 0
+#define I40E_VFCM_PE_ERRINFO1_ERROR_VALID_MASK (0x1 << I40E_VFCM_PE_ERRINFO1_ERROR_VALID_SHIFT)
+#define I40E_VFCM_PE_ERRINFO1_ERROR_INST_SHIFT 4
+#define I40E_VFCM_PE_ERRINFO1_ERROR_INST_MASK (0x7 << I40E_VFCM_PE_ERRINFO1_ERROR_INST_SHIFT)
+#define I40E_VFCM_PE_ERRINFO1_DBL_ERROR_CNT_SHIFT 8
+#define I40E_VFCM_PE_ERRINFO1_DBL_ERROR_CNT_MASK (0xFF << I40E_VFCM_PE_ERRINFO1_DBL_ERROR_CNT_SHIFT)
+#define I40E_VFCM_PE_ERRINFO1_RLU_ERROR_CNT_SHIFT 16
+#define I40E_VFCM_PE_ERRINFO1_RLU_ERROR_CNT_MASK (0xFF << I40E_VFCM_PE_ERRINFO1_RLU_ERROR_CNT_SHIFT)
+#define I40E_VFCM_PE_ERRINFO1_RLS_ERROR_CNT_SHIFT 24
+#define I40E_VFCM_PE_ERRINFO1_RLS_ERROR_CNT_MASK (0xFF << I40E_VFCM_PE_ERRINFO1_RLS_ERROR_CNT_SHIFT)
+#define I40E_GLDCB_GENC 0x00083044
+#define I40E_GLDCB_GENC_PCIRTT_SHIFT 0
+#define I40E_GLDCB_GENC_PCIRTT_MASK (0xFFFF << I40E_GLDCB_GENC_PCIRTT_SHIFT)
+#define I40E_GLDCB_RUPTI 0x00122618
+#define I40E_GLDCB_RUPTI_PFCTIMEOUT_UP_SHIFT 0
+#define I40E_GLDCB_RUPTI_PFCTIMEOUT_UP_MASK (0xFFFFFFFF << I40E_GLDCB_RUPTI_PFCTIMEOUT_UP_SHIFT)
+#define I40E_PRTDCB_FCCFG 0x001E4640
+#define I40E_PRTDCB_FCCFG_TFCE_SHIFT 3
+#define I40E_PRTDCB_FCCFG_TFCE_MASK (0x3 << I40E_PRTDCB_FCCFG_TFCE_SHIFT)
+#define I40E_PRTDCB_FCRTV 0x001E4600
+#define I40E_PRTDCB_FCRTV_FC_REFRESH_TH_SHIFT 0
+#define I40E_PRTDCB_FCRTV_FC_REFRESH_TH_MASK (0xFFFF << I40E_PRTDCB_FCRTV_FC_REFRESH_TH_SHIFT)
+#define I40E_PRTDCB_FCTTVN(_i) (0x001E4580 + ((_i) * 32)) /* _i=0...3 */
+#define I40E_PRTDCB_FCTTVN_MAX_INDEX 3
+#define I40E_PRTDCB_FCTTVN_TTV_2N_SHIFT 0
+#define I40E_PRTDCB_FCTTVN_TTV_2N_MASK (0xFFFF << I40E_PRTDCB_FCTTVN_TTV_2N_SHIFT)
+#define I40E_PRTDCB_FCTTVN_TTV_2N_P1_SHIFT 16
+#define I40E_PRTDCB_FCTTVN_TTV_2N_P1_MASK (0xFFFF << I40E_PRTDCB_FCTTVN_TTV_2N_P1_SHIFT)
+#define I40E_PRTDCB_GENC 0x00083000
+#define I40E_PRTDCB_GENC_RESERVED_1_SHIFT 0
+#define I40E_PRTDCB_GENC_RESERVED_1_MASK (0x3 << I40E_PRTDCB_GENC_RESERVED_1_SHIFT)
+#define I40E_PRTDCB_GENC_NUMTC_SHIFT 2
+#define I40E_PRTDCB_GENC_NUMTC_MASK (0xF << I40E_PRTDCB_GENC_NUMTC_SHIFT)
+#define I40E_PRTDCB_GENC_FCOEUP_SHIFT 6
+#define I40E_PRTDCB_GENC_FCOEUP_MASK (0x7 << I40E_PRTDCB_GENC_FCOEUP_SHIFT)
+#define I40E_PRTDCB_GENC_FCOEUP_VALID_SHIFT 9
+#define I40E_PRTDCB_GENC_FCOEUP_VALID_MASK (0x1 << I40E_PRTDCB_GENC_FCOEUP_VALID_SHIFT)
+#define I40E_PRTDCB_GENC_PFCLDA_SHIFT 16
+#define I40E_PRTDCB_GENC_PFCLDA_MASK (0xFFFF << I40E_PRTDCB_GENC_PFCLDA_SHIFT)
+#define I40E_PRTDCB_GENS 0x00083020
+#define I40E_PRTDCB_GENS_DCBX_STATUS_SHIFT 0
+#define I40E_PRTDCB_GENS_DCBX_STATUS_MASK (0x7 << I40E_PRTDCB_GENS_DCBX_STATUS_SHIFT)
+#define I40E_PRTDCB_MFLCN 0x001E2400
+#define I40E_PRTDCB_MFLCN_PMCF_SHIFT 0
+#define I40E_PRTDCB_MFLCN_PMCF_MASK (0x1 << I40E_PRTDCB_MFLCN_PMCF_SHIFT)
+#define I40E_PRTDCB_MFLCN_DPF_SHIFT 1
+#define I40E_PRTDCB_MFLCN_DPF_MASK (0x1 << I40E_PRTDCB_MFLCN_DPF_SHIFT)
+#define I40E_PRTDCB_MFLCN_RPFCM_SHIFT 2
+#define I40E_PRTDCB_MFLCN_RPFCM_MASK (0x1 << I40E_PRTDCB_MFLCN_RPFCM_SHIFT)
+#define I40E_PRTDCB_MFLCN_RFCE_SHIFT 3
+#define I40E_PRTDCB_MFLCN_RFCE_MASK (0x1 << I40E_PRTDCB_MFLCN_RFCE_SHIFT)
+#define I40E_PRTDCB_MFLCN_RPFCE_SHIFT 4
+#define I40E_PRTDCB_MFLCN_RPFCE_MASK (0xFF << I40E_PRTDCB_MFLCN_RPFCE_SHIFT)
+#define I40E_PRTDCB_RETSC 0x001223E0
+#define I40E_PRTDCB_RETSC_ETS_MODE_SHIFT 0
+#define I40E_PRTDCB_RETSC_ETS_MODE_MASK (0x1 << I40E_PRTDCB_RETSC_ETS_MODE_SHIFT)
+#define I40E_PRTDCB_RETSC_NON_ETS_MODE_SHIFT 1
+#define I40E_PRTDCB_RETSC_NON_ETS_MODE_MASK (0x1 << I40E_PRTDCB_RETSC_NON_ETS_MODE_SHIFT)
+#define I40E_PRTDCB_RETSC_ETS_MAX_EXP_SHIFT 2
+#define I40E_PRTDCB_RETSC_ETS_MAX_EXP_MASK (0xF << I40E_PRTDCB_RETSC_ETS_MAX_EXP_SHIFT)
+#define I40E_PRTDCB_RETSC_LLTC_SHIFT 8
+#define I40E_PRTDCB_RETSC_LLTC_MASK (0xFF << I40E_PRTDCB_RETSC_LLTC_SHIFT)
+#define I40E_PRTDCB_RETSTCC(_i) (0x00122180 + ((_i) * 32)) /* _i=0...7 */
+#define I40E_PRTDCB_RETSTCC_MAX_INDEX 7
+#define I40E_PRTDCB_RETSTCC_BWSHARE_SHIFT 0
+#define I40E_PRTDCB_RETSTCC_BWSHARE_MASK (0x7F << I40E_PRTDCB_RETSTCC_BWSHARE_SHIFT)
+#define I40E_PRTDCB_RETSTCC_UPINTC_MODE_SHIFT 30
+#define I40E_PRTDCB_RETSTCC_UPINTC_MODE_MASK (0x1 << I40E_PRTDCB_RETSTCC_UPINTC_MODE_SHIFT)
+#define I40E_PRTDCB_RETSTCC_ETSTC_SHIFT 31
+#define I40E_PRTDCB_RETSTCC_ETSTC_MASK (0x1 << I40E_PRTDCB_RETSTCC_ETSTC_SHIFT)
+#define I40E_PRTDCB_RPPMC 0x001223A0
+#define I40E_PRTDCB_RPPMC_LANRPPM_SHIFT 0
+#define I40E_PRTDCB_RPPMC_LANRPPM_MASK (0xFF << I40E_PRTDCB_RPPMC_LANRPPM_SHIFT)
+#define I40E_PRTDCB_RPPMC_RDMARPPM_SHIFT 8
+#define I40E_PRTDCB_RPPMC_RDMARPPM_MASK (0xFF << I40E_PRTDCB_RPPMC_RDMARPPM_SHIFT)
+#define I40E_PRTDCB_RPPMC_RX_FIFO_SIZE_SHIFT 16
+#define I40E_PRTDCB_RPPMC_RX_FIFO_SIZE_MASK (0xFF << I40E_PRTDCB_RPPMC_RX_FIFO_SIZE_SHIFT)
+#define I40E_PRTDCB_RUP 0x001C0B00
+#define I40E_PRTDCB_RUP_NOVLANUP_SHIFT 0
+#define I40E_PRTDCB_RUP_NOVLANUP_MASK (0x7 << I40E_PRTDCB_RUP_NOVLANUP_SHIFT)
+#define I40E_PRTDCB_RUP2TC 0x001C09A0
+#define I40E_PRTDCB_RUP2TC_UP0TC_SHIFT 0
+#define I40E_PRTDCB_RUP2TC_UP0TC_MASK (0x7 << I40E_PRTDCB_RUP2TC_UP0TC_SHIFT)
+#define I40E_PRTDCB_RUP2TC_UP1TC_SHIFT 3
+#define I40E_PRTDCB_RUP2TC_UP1TC_MASK (0x7 << I40E_PRTDCB_RUP2TC_UP1TC_SHIFT)
+#define I40E_PRTDCB_RUP2TC_UP2TC_SHIFT 6
+#define I40E_PRTDCB_RUP2TC_UP2TC_MASK (0x7 << I40E_PRTDCB_RUP2TC_UP2TC_SHIFT)
+#define I40E_PRTDCB_RUP2TC_UP3TC_SHIFT 9
+#define I40E_PRTDCB_RUP2TC_UP3TC_MASK (0x7 << I40E_PRTDCB_RUP2TC_UP3TC_SHIFT)
+#define I40E_PRTDCB_RUP2TC_UP4TC_SHIFT 12
+#define I40E_PRTDCB_RUP2TC_UP4TC_MASK (0x7 << I40E_PRTDCB_RUP2TC_UP4TC_SHIFT)
+#define I40E_PRTDCB_RUP2TC_UP5TC_SHIFT 15
+#define I40E_PRTDCB_RUP2TC_UP5TC_MASK (0x7 << I40E_PRTDCB_RUP2TC_UP5TC_SHIFT)
+#define I40E_PRTDCB_RUP2TC_UP6TC_SHIFT 18
+#define I40E_PRTDCB_RUP2TC_UP6TC_MASK (0x7 << I40E_PRTDCB_RUP2TC_UP6TC_SHIFT)
+#define I40E_PRTDCB_RUP2TC_UP7TC_SHIFT 21
+#define I40E_PRTDCB_RUP2TC_UP7TC_MASK (0x7 << I40E_PRTDCB_RUP2TC_UP7TC_SHIFT)
+#define I40E_PRTDCB_TC2PFC 0x001C0980
+#define I40E_PRTDCB_TC2PFC_TC2PFC_SHIFT 0
+#define I40E_PRTDCB_TC2PFC_TC2PFC_MASK (0xFF << I40E_PRTDCB_TC2PFC_TC2PFC_SHIFT)
+#define I40E_PRTDCB_TCPMC 0x000A21A0
+#define I40E_PRTDCB_TCPMC_CPM_SHIFT 0
+#define I40E_PRTDCB_TCPMC_CPM_MASK (0x1FFF << I40E_PRTDCB_TCPMC_CPM_SHIFT)
+#define I40E_PRTDCB_TCPMC_LLTC_SHIFT 13
+#define I40E_PRTDCB_TCPMC_LLTC_MASK (0xFF << I40E_PRTDCB_TCPMC_LLTC_SHIFT)
+#define I40E_PRTDCB_TCPMC_TCPM_MODE_SHIFT 30
+#define I40E_PRTDCB_TCPMC_TCPM_MODE_MASK (0x1 << I40E_PRTDCB_TCPMC_TCPM_MODE_SHIFT)
+#define I40E_PRTDCB_TCWSTC(_i) (0x000A2040 + ((_i) * 32)) /* _i=0...7 */
+#define I40E_PRTDCB_TCWSTC_MAX_INDEX 7
+#define I40E_PRTDCB_TCWSTC_MSTC_SHIFT 0
+#define I40E_PRTDCB_TCWSTC_MSTC_MASK (0xFFFFF << I40E_PRTDCB_TCWSTC_MSTC_SHIFT)
+#define I40E_PRTDCB_TDPMC 0x000A0180
+#define I40E_PRTDCB_TDPMC_DPM_SHIFT 0
+#define I40E_PRTDCB_TDPMC_DPM_MASK (0xFF << I40E_PRTDCB_TDPMC_DPM_SHIFT)
+#define I40E_PRTDCB_TDPMC_TCPM_MODE_SHIFT 30
+#define I40E_PRTDCB_TDPMC_TCPM_MODE_MASK (0x1 << I40E_PRTDCB_TDPMC_TCPM_MODE_SHIFT)
+#define I40E_PRTDCB_TDPUC 0x00044100
+#define I40E_PRTDCB_TDPUC_MAX_TXFRAME_SHIFT 0
+#define I40E_PRTDCB_TDPUC_MAX_TXFRAME_MASK (0xFFFF << I40E_PRTDCB_TDPUC_MAX_TXFRAME_SHIFT)
+#define I40E_PRTDCB_TETSC_TCB 0x000AE060
+#define I40E_PRTDCB_TETSC_TCB_EN_LL_STRICT_PRIORITY_SHIFT 0
+#define I40E_PRTDCB_TETSC_TCB_EN_LL_STRICT_PRIORITY_MASK (0x1 << I40E_PRTDCB_TETSC_TCB_EN_LL_STRICT_PRIORITY_SHIFT)
+#define I40E_PRTDCB_TETSC_TCB_LLTC_SHIFT 8
+#define I40E_PRTDCB_TETSC_TCB_LLTC_MASK (0xFF << I40E_PRTDCB_TETSC_TCB_LLTC_SHIFT)
+#define I40E_PRTDCB_TETSC_TPB 0x00098060
+#define I40E_PRTDCB_TETSC_TPB_EN_LL_STRICT_PRIORITY_SHIFT 0
+#define I40E_PRTDCB_TETSC_TPB_EN_LL_STRICT_PRIORITY_MASK (0x1 << I40E_PRTDCB_TETSC_TPB_EN_LL_STRICT_PRIORITY_SHIFT)
+#define I40E_PRTDCB_TETSC_TPB_LLTC_SHIFT 8
+#define I40E_PRTDCB_TETSC_TPB_LLTC_MASK (0xFF << I40E_PRTDCB_TETSC_TPB_LLTC_SHIFT)
+#define I40E_PRTDCB_TFCS 0x001E4560
+#define I40E_PRTDCB_TFCS_TXOFF_SHIFT 0
+#define I40E_PRTDCB_TFCS_TXOFF_MASK (0x1 << I40E_PRTDCB_TFCS_TXOFF_SHIFT)
+#define I40E_PRTDCB_TFCS_TXOFF0_SHIFT 8
+#define I40E_PRTDCB_TFCS_TXOFF0_MASK (0x1 << I40E_PRTDCB_TFCS_TXOFF0_SHIFT)
+#define I40E_PRTDCB_TFCS_TXOFF1_SHIFT 9
+#define I40E_PRTDCB_TFCS_TXOFF1_MASK (0x1 << I40E_PRTDCB_TFCS_TXOFF1_SHIFT)
+#define I40E_PRTDCB_TFCS_TXOFF2_SHIFT 10
+#define I40E_PRTDCB_TFCS_TXOFF2_MASK (0x1 << I40E_PRTDCB_TFCS_TXOFF2_SHIFT)
+#define I40E_PRTDCB_TFCS_TXOFF3_SHIFT 11
+#define I40E_PRTDCB_TFCS_TXOFF3_MASK (0x1 << I40E_PRTDCB_TFCS_TXOFF3_SHIFT)
+#define I40E_PRTDCB_TFCS_TXOFF4_SHIFT 12
+#define I40E_PRTDCB_TFCS_TXOFF4_MASK (0x1 << I40E_PRTDCB_TFCS_TXOFF4_SHIFT)
+#define I40E_PRTDCB_TFCS_TXOFF5_SHIFT 13
+#define I40E_PRTDCB_TFCS_TXOFF5_MASK (0x1 << I40E_PRTDCB_TFCS_TXOFF5_SHIFT)
+#define I40E_PRTDCB_TFCS_TXOFF6_SHIFT 14
+#define I40E_PRTDCB_TFCS_TXOFF6_MASK (0x1 << I40E_PRTDCB_TFCS_TXOFF6_SHIFT)
+#define I40E_PRTDCB_TFCS_TXOFF7_SHIFT 15
+#define I40E_PRTDCB_TFCS_TXOFF7_MASK (0x1 << I40E_PRTDCB_TFCS_TXOFF7_SHIFT)
+#define I40E_PRTDCB_TFWSTC(_i) (0x000A0040 + ((_i) * 32)) /* _i=0...7 */
+#define I40E_PRTDCB_TFWSTC_MAX_INDEX 7
+#define I40E_PRTDCB_TFWSTC_MSTC_SHIFT 0
+#define I40E_PRTDCB_TFWSTC_MSTC_MASK (0xFFFFF << I40E_PRTDCB_TFWSTC_MSTC_SHIFT)
+#define I40E_PRTDCB_TPFCTS(_i) (0x001E4660 + ((_i) * 32)) /* _i=0...7 */
+#define I40E_PRTDCB_TPFCTS_MAX_INDEX 7
+#define I40E_PRTDCB_TPFCTS_PFCTIMER_SHIFT 0
+#define I40E_PRTDCB_TPFCTS_PFCTIMER_MASK (0x3FFF << I40E_PRTDCB_TPFCTS_PFCTIMER_SHIFT)
+#define I40E_GLFCOE_RCTL 0x00269B94
+#define I40E_GLFCOE_RCTL_FCOEVER_SHIFT 0
+#define I40E_GLFCOE_RCTL_FCOEVER_MASK (0xF << I40E_GLFCOE_RCTL_FCOEVER_SHIFT)
+#define I40E_GLFCOE_RCTL_SAVBAD_SHIFT 4
+#define I40E_GLFCOE_RCTL_SAVBAD_MASK (0x1 << I40E_GLFCOE_RCTL_SAVBAD_SHIFT)
+#define I40E_GLFCOE_RCTL_ICRC_SHIFT 5
+#define I40E_GLFCOE_RCTL_ICRC_MASK (0x1 << I40E_GLFCOE_RCTL_ICRC_SHIFT)
+#define I40E_GLFCOE_RCTL_MAX_SIZE_SHIFT 16
+#define I40E_GLFCOE_RCTL_MAX_SIZE_MASK (0x3FFF << I40E_GLFCOE_RCTL_MAX_SIZE_SHIFT)
+#define I40E_GL_FWSTS 0x00083048
+#define I40E_GL_FWSTS_FWS0B_SHIFT 0
+#define I40E_GL_FWSTS_FWS0B_MASK (0xFF << I40E_GL_FWSTS_FWS0B_SHIFT)
+#define I40E_GL_FWSTS_FWRI_SHIFT 9
+#define I40E_GL_FWSTS_FWRI_MASK (0x1 << I40E_GL_FWSTS_FWRI_SHIFT)
+#define I40E_GL_FWSTS_FWS1B_SHIFT 16
+#define I40E_GL_FWSTS_FWS1B_MASK (0xFF << I40E_GL_FWSTS_FWS1B_SHIFT)
+#define I40E_GLGEN_CLKSTAT 0x000B8184
+#define I40E_GLGEN_CLKSTAT_CLKMODE_SHIFT 0
+#define I40E_GLGEN_CLKSTAT_CLKMODE_MASK (0x1 << I40E_GLGEN_CLKSTAT_CLKMODE_SHIFT)
+#define I40E_GLGEN_CLKSTAT_U_CLK_SPEED_SHIFT 4
+#define I40E_GLGEN_CLKSTAT_U_CLK_SPEED_MASK (0x3 << I40E_GLGEN_CLKSTAT_U_CLK_SPEED_SHIFT)
+#define I40E_GLGEN_CLKSTAT_P0_CLK_SPEED_SHIFT 8
+#define I40E_GLGEN_CLKSTAT_P0_CLK_SPEED_MASK (0x7 << I40E_GLGEN_CLKSTAT_P0_CLK_SPEED_SHIFT)
+#define I40E_GLGEN_CLKSTAT_P1_CLK_SPEED_SHIFT 12
+#define I40E_GLGEN_CLKSTAT_P1_CLK_SPEED_MASK (0x7 << I40E_GLGEN_CLKSTAT_P1_CLK_SPEED_SHIFT)
+#define I40E_GLGEN_CLKSTAT_P2_CLK_SPEED_SHIFT 16
+#define I40E_GLGEN_CLKSTAT_P2_CLK_SPEED_MASK (0x7 << I40E_GLGEN_CLKSTAT_P2_CLK_SPEED_SHIFT)
+#define I40E_GLGEN_CLKSTAT_P3_CLK_SPEED_SHIFT 20
+#define I40E_GLGEN_CLKSTAT_P3_CLK_SPEED_MASK (0x7 << I40E_GLGEN_CLKSTAT_P3_CLK_SPEED_SHIFT)
+#define I40E_GLGEN_GPIO_CTL(_i) (0x00088100 + ((_i) * 4)) /* _i=0...29 */
+#define I40E_GLGEN_GPIO_CTL_MAX_INDEX 29
+#define I40E_GLGEN_GPIO_CTL_PRT_NUM_SHIFT 0
+#define I40E_GLGEN_GPIO_CTL_PRT_NUM_MASK (0x3 << I40E_GLGEN_GPIO_CTL_PRT_NUM_SHIFT)
+#define I40E_GLGEN_GPIO_CTL_PRT_NUM_NA_SHIFT 3
+#define I40E_GLGEN_GPIO_CTL_PRT_NUM_NA_MASK (0x1 << I40E_GLGEN_GPIO_CTL_PRT_NUM_NA_SHIFT)
+#define I40E_GLGEN_GPIO_CTL_PIN_DIR_SHIFT 4
+#define I40E_GLGEN_GPIO_CTL_PIN_DIR_MASK (0x1 << I40E_GLGEN_GPIO_CTL_PIN_DIR_SHIFT)
+#define I40E_GLGEN_GPIO_CTL_TRI_CTL_SHIFT 5
+#define I40E_GLGEN_GPIO_CTL_TRI_CTL_MASK (0x1 << I40E_GLGEN_GPIO_CTL_TRI_CTL_SHIFT)
+#define I40E_GLGEN_GPIO_CTL_OUT_CTL_SHIFT 6
+#define I40E_GLGEN_GPIO_CTL_OUT_CTL_MASK (0x1 << I40E_GLGEN_GPIO_CTL_OUT_CTL_SHIFT)
+#define I40E_GLGEN_GPIO_CTL_PIN_FUNC_SHIFT 7
+#define I40E_GLGEN_GPIO_CTL_PIN_FUNC_MASK (0x7 << I40E_GLGEN_GPIO_CTL_PIN_FUNC_SHIFT)
+#define I40E_GLGEN_GPIO_CTL_LED_INVRT_SHIFT 10
+#define I40E_GLGEN_GPIO_CTL_LED_INVRT_MASK (0x1 << I40E_GLGEN_GPIO_CTL_LED_INVRT_SHIFT)
+#define I40E_GLGEN_GPIO_CTL_LED_BLINK_SHIFT 11
+#define I40E_GLGEN_GPIO_CTL_LED_BLINK_MASK (0x1 << I40E_GLGEN_GPIO_CTL_LED_BLINK_SHIFT)
+#define I40E_GLGEN_GPIO_CTL_LED_MODE_SHIFT 12
+#define I40E_GLGEN_GPIO_CTL_LED_MODE_MASK (0xF << I40E_GLGEN_GPIO_CTL_LED_MODE_SHIFT)
+#define I40E_GLGEN_GPIO_CTL_INT_MODE_SHIFT 17
+#define I40E_GLGEN_GPIO_CTL_INT_MODE_MASK (0x3 << I40E_GLGEN_GPIO_CTL_INT_MODE_SHIFT)
+#define I40E_GLGEN_GPIO_CTL_OUT_DEFAULT_SHIFT 19
+#define I40E_GLGEN_GPIO_CTL_OUT_DEFAULT_MASK (0x1 << I40E_GLGEN_GPIO_CTL_OUT_DEFAULT_SHIFT)
+#define I40E_GLGEN_GPIO_CTL_PHY_PIN_NAME_SHIFT 20
+#define I40E_GLGEN_GPIO_CTL_PHY_PIN_NAME_MASK (0x3F << I40E_GLGEN_GPIO_CTL_PHY_PIN_NAME_SHIFT)
+#define I40E_GLGEN_GPIO_SET 0x00088184
+#define I40E_GLGEN_GPIO_SET_GPIO_INDX_SHIFT 0
+#define I40E_GLGEN_GPIO_SET_GPIO_INDX_MASK (0x1F << I40E_GLGEN_GPIO_SET_GPIO_INDX_SHIFT)
+#define I40E_GLGEN_GPIO_SET_SDP_DATA_SHIFT 5
+#define I40E_GLGEN_GPIO_SET_SDP_DATA_MASK (0x1 << I40E_GLGEN_GPIO_SET_SDP_DATA_SHIFT)
+#define I40E_GLGEN_GPIO_SET_DRIVE_SDP_SHIFT 6
+#define I40E_GLGEN_GPIO_SET_DRIVE_SDP_MASK (0x1 << I40E_GLGEN_GPIO_SET_DRIVE_SDP_SHIFT)
+#define I40E_GLGEN_GPIO_STAT 0x0008817C
+#define I40E_GLGEN_GPIO_STAT_GPIO_VALUE_SHIFT 0
+#define I40E_GLGEN_GPIO_STAT_GPIO_VALUE_MASK (0x3FFFFFFF << I40E_GLGEN_GPIO_STAT_GPIO_VALUE_SHIFT)
+#define I40E_GLGEN_GPIO_TRANSIT 0x00088180
+#define I40E_GLGEN_GPIO_TRANSIT_GPIO_TRANSITION_SHIFT 0
+#define I40E_GLGEN_GPIO_TRANSIT_GPIO_TRANSITION_MASK (0x3FFFFFFF << I40E_GLGEN_GPIO_TRANSIT_GPIO_TRANSITION_SHIFT)
+#define I40E_GLGEN_I2CCMD(_i) (0x000881E0 + ((_i) * 4)) /* _i=0...3 */
+#define I40E_GLGEN_I2CCMD_MAX_INDEX 3
+#define I40E_GLGEN_I2CCMD_DATA_SHIFT 0
+#define I40E_GLGEN_I2CCMD_DATA_MASK (0xFFFF << I40E_GLGEN_I2CCMD_DATA_SHIFT)
+#define I40E_GLGEN_I2CCMD_REGADD_SHIFT 16
+#define I40E_GLGEN_I2CCMD_REGADD_MASK (0xFF << I40E_GLGEN_I2CCMD_REGADD_SHIFT)
+#define I40E_GLGEN_I2CCMD_PHYADD_SHIFT 24
+#define I40E_GLGEN_I2CCMD_PHYADD_MASK (0x7 << I40E_GLGEN_I2CCMD_PHYADD_SHIFT)
+#define I40E_GLGEN_I2CCMD_OP_SHIFT 27
+#define I40E_GLGEN_I2CCMD_OP_MASK (0x1 << I40E_GLGEN_I2CCMD_OP_SHIFT)
+#define I40E_GLGEN_I2CCMD_RESET_SHIFT 28
+#define I40E_GLGEN_I2CCMD_RESET_MASK (0x1 << I40E_GLGEN_I2CCMD_RESET_SHIFT)
+#define I40E_GLGEN_I2CCMD_R_SHIFT 29
+#define I40E_GLGEN_I2CCMD_R_MASK (0x1 << I40E_GLGEN_I2CCMD_R_SHIFT)
+#define I40E_GLGEN_I2CCMD_E_SHIFT 31
+#define I40E_GLGEN_I2CCMD_E_MASK (0x1 << I40E_GLGEN_I2CCMD_E_SHIFT)
+#define I40E_GLGEN_I2CPARAMS(_i) (0x000881AC + ((_i) * 4)) /* _i=0...3 */
+#define I40E_GLGEN_I2CPARAMS_MAX_INDEX 3
+#define I40E_GLGEN_I2CPARAMS_WRITE_TIME_SHIFT 0
+#define I40E_GLGEN_I2CPARAMS_WRITE_TIME_MASK (0x1F << I40E_GLGEN_I2CPARAMS_WRITE_TIME_SHIFT)
+#define I40E_GLGEN_I2CPARAMS_READ_TIME_SHIFT 5
+#define I40E_GLGEN_I2CPARAMS_READ_TIME_MASK (0x7 << I40E_GLGEN_I2CPARAMS_READ_TIME_SHIFT)
+#define I40E_GLGEN_I2CPARAMS_I2CBB_EN_SHIFT 8
+#define I40E_GLGEN_I2CPARAMS_I2CBB_EN_MASK (0x1 << I40E_GLGEN_I2CPARAMS_I2CBB_EN_SHIFT)
+#define I40E_GLGEN_I2CPARAMS_CLK_SHIFT 9
+#define I40E_GLGEN_I2CPARAMS_CLK_MASK (0x1 << I40E_GLGEN_I2CPARAMS_CLK_SHIFT)
+#define I40E_GLGEN_I2CPARAMS_DATA_OUT_SHIFT 10
+#define I40E_GLGEN_I2CPARAMS_DATA_OUT_MASK (0x1 << I40E_GLGEN_I2CPARAMS_DATA_OUT_SHIFT)
+#define I40E_GLGEN_I2CPARAMS_DATA_OE_N_SHIFT 11
+#define I40E_GLGEN_I2CPARAMS_DATA_OE_N_MASK (0x1 << I40E_GLGEN_I2CPARAMS_DATA_OE_N_SHIFT)
+#define I40E_GLGEN_I2CPARAMS_DATA_IN_SHIFT 12
+#define I40E_GLGEN_I2CPARAMS_DATA_IN_MASK (0x1 << I40E_GLGEN_I2CPARAMS_DATA_IN_SHIFT)
+#define I40E_GLGEN_I2CPARAMS_CLK_OE_N_SHIFT 13
+#define I40E_GLGEN_I2CPARAMS_CLK_OE_N_MASK (0x1 << I40E_GLGEN_I2CPARAMS_CLK_OE_N_SHIFT)
+#define I40E_GLGEN_I2CPARAMS_CLK_IN_SHIFT 14
+#define I40E_GLGEN_I2CPARAMS_CLK_IN_MASK (0x1 << I40E_GLGEN_I2CPARAMS_CLK_IN_SHIFT)
+#define I40E_GLGEN_I2CPARAMS_CLK_STRETCH_DIS_SHIFT 15
+#define I40E_GLGEN_I2CPARAMS_CLK_STRETCH_DIS_MASK (0x1 << I40E_GLGEN_I2CPARAMS_CLK_STRETCH_DIS_SHIFT)
+#define I40E_GLGEN_I2CPARAMS_I2C_DATA_ORDER_SHIFT 31
+#define I40E_GLGEN_I2CPARAMS_I2C_DATA_ORDER_MASK (0x1 << I40E_GLGEN_I2CPARAMS_I2C_DATA_ORDER_SHIFT)
+#define I40E_GLGEN_LED_CTL 0x00088178
+#define I40E_GLGEN_LED_CTL_GLOBAL_BLINK_MODE_SHIFT 0
+#define I40E_GLGEN_LED_CTL_GLOBAL_BLINK_MODE_MASK (0x1 << I40E_GLGEN_LED_CTL_GLOBAL_BLINK_MODE_SHIFT)
+#define I40E_GLGEN_MDIO_CTRL(_i) (0x000881D0 + ((_i) * 4)) /* _i=0...3 */
+#define I40E_GLGEN_MDIO_CTRL_MAX_INDEX 3
+#define I40E_GLGEN_MDIO_CTRL_LEGACY_RSVD2_SHIFT 0
+#define I40E_GLGEN_MDIO_CTRL_LEGACY_RSVD2_MASK (0x1FFFF << I40E_GLGEN_MDIO_CTRL_LEGACY_RSVD2_SHIFT)
+#define I40E_GLGEN_MDIO_CTRL_CONTMDC_SHIFT 17
+#define I40E_GLGEN_MDIO_CTRL_CONTMDC_MASK (0x1 << I40E_GLGEN_MDIO_CTRL_CONTMDC_SHIFT)
+#define I40E_GLGEN_MDIO_CTRL_LEGACY_RSVD1_SHIFT 18
+#define I40E_GLGEN_MDIO_CTRL_LEGACY_RSVD1_MASK (0x3FFF << I40E_GLGEN_MDIO_CTRL_LEGACY_RSVD1_SHIFT)
+#define I40E_GLGEN_MDIO_I2C_SEL(_i) (0x000881C0 + ((_i) * 4)) /* _i=0...3 */
+#define I40E_GLGEN_MDIO_I2C_SEL_MAX_INDEX 3
+#define I40E_GLGEN_MDIO_I2C_SEL_MDIO_I2C_SEL_SHIFT 0
+#define I40E_GLGEN_MDIO_I2C_SEL_MDIO_I2C_SEL_MASK (0x1 << I40E_GLGEN_MDIO_I2C_SEL_MDIO_I2C_SEL_SHIFT)
+#define I40E_GLGEN_MDIO_I2C_SEL_PHY_PORT_NUM_SHIFT 1
+#define I40E_GLGEN_MDIO_I2C_SEL_PHY_PORT_NUM_MASK (0xF << I40E_GLGEN_MDIO_I2C_SEL_PHY_PORT_NUM_SHIFT)
+#define I40E_GLGEN_MDIO_I2C_SEL_PHY0_ADDRESS_SHIFT 5
+#define I40E_GLGEN_MDIO_I2C_SEL_PHY0_ADDRESS_MASK (0x1F << I40E_GLGEN_MDIO_I2C_SEL_PHY0_ADDRESS_SHIFT)
+#define I40E_GLGEN_MDIO_I2C_SEL_PHY1_ADDRESS_SHIFT 10
+#define I40E_GLGEN_MDIO_I2C_SEL_PHY1_ADDRESS_MASK (0x1F << I40E_GLGEN_MDIO_I2C_SEL_PHY1_ADDRESS_SHIFT)
+#define I40E_GLGEN_MDIO_I2C_SEL_PHY2_ADDRESS_SHIFT 15
+#define I40E_GLGEN_MDIO_I2C_SEL_PHY2_ADDRESS_MASK (0x1F << I40E_GLGEN_MDIO_I2C_SEL_PHY2_ADDRESS_SHIFT)
+#define I40E_GLGEN_MDIO_I2C_SEL_PHY3_ADDRESS_SHIFT 20
+#define I40E_GLGEN_MDIO_I2C_SEL_PHY3_ADDRESS_MASK (0x1F << I40E_GLGEN_MDIO_I2C_SEL_PHY3_ADDRESS_SHIFT)
+#define I40E_GLGEN_MDIO_I2C_SEL_MDIO_IF_MODE_SHIFT 25
+#define I40E_GLGEN_MDIO_I2C_SEL_MDIO_IF_MODE_MASK (0xF << I40E_GLGEN_MDIO_I2C_SEL_MDIO_IF_MODE_SHIFT)
+#define I40E_GLGEN_MDIO_I2C_SEL_EN_FAST_MODE_SHIFT 31
+#define I40E_GLGEN_MDIO_I2C_SEL_EN_FAST_MODE_MASK (0x1 << I40E_GLGEN_MDIO_I2C_SEL_EN_FAST_MODE_SHIFT)
+#define I40E_GLGEN_MSCA(_i) (0x0008818C + ((_i) * 4)) /* _i=0...3 */
+#define I40E_GLGEN_MSCA_MAX_INDEX 3
+#define I40E_GLGEN_MSCA_MDIADD_SHIFT 0
+#define I40E_GLGEN_MSCA_MDIADD_MASK (0xFFFF << I40E_GLGEN_MSCA_MDIADD_SHIFT)
+#define I40E_GLGEN_MSCA_DEVADD_SHIFT 16
+#define I40E_GLGEN_MSCA_DEVADD_MASK (0x1F << I40E_GLGEN_MSCA_DEVADD_SHIFT)
+#define I40E_GLGEN_MSCA_PHYADD_SHIFT 21
+#define I40E_GLGEN_MSCA_PHYADD_MASK (0x1F << I40E_GLGEN_MSCA_PHYADD_SHIFT)
+#define I40E_GLGEN_MSCA_OPCODE_SHIFT 26
+#define I40E_GLGEN_MSCA_OPCODE_MASK (0x3 << I40E_GLGEN_MSCA_OPCODE_SHIFT)
+#define I40E_GLGEN_MSCA_STCODE_SHIFT 28
+#define I40E_GLGEN_MSCA_STCODE_MASK (0x3 << I40E_GLGEN_MSCA_STCODE_SHIFT)
+#define I40E_GLGEN_MSCA_MDICMD_SHIFT 30
+#define I40E_GLGEN_MSCA_MDICMD_MASK (0x1 << I40E_GLGEN_MSCA_MDICMD_SHIFT)
+#define I40E_GLGEN_MSCA_MDIINPROGEN_SHIFT 31
+#define I40E_GLGEN_MSCA_MDIINPROGEN_MASK (0x1 << I40E_GLGEN_MSCA_MDIINPROGEN_SHIFT)
+#define I40E_GLGEN_MSRWD(_i) (0x0008819C + ((_i) * 4)) /* _i=0...3 */
+#define I40E_GLGEN_MSRWD_MAX_INDEX 3
+#define I40E_GLGEN_MSRWD_MDIWRDATA_SHIFT 0
+#define I40E_GLGEN_MSRWD_MDIWRDATA_MASK (0xFFFF << I40E_GLGEN_MSRWD_MDIWRDATA_SHIFT)
+#define I40E_GLGEN_MSRWD_MDIRDDATA_SHIFT 16
+#define I40E_GLGEN_MSRWD_MDIRDDATA_MASK (0xFFFF << I40E_GLGEN_MSRWD_MDIRDDATA_SHIFT)
+#define I40E_GLGEN_PCIFCNCNT 0x001C0AB4
+#define I40E_GLGEN_PCIFCNCNT_PCIPFCNT_SHIFT 0
+#define I40E_GLGEN_PCIFCNCNT_PCIPFCNT_MASK (0x1F << I40E_GLGEN_PCIFCNCNT_PCIPFCNT_SHIFT)
+#define I40E_GLGEN_PCIFCNCNT_PCIVFCNT_SHIFT 16
+#define I40E_GLGEN_PCIFCNCNT_PCIVFCNT_MASK (0xFF << I40E_GLGEN_PCIFCNCNT_PCIVFCNT_SHIFT)
+#define I40E_GLGEN_PE_ENA 0x000B81A0
+#define I40E_GLGEN_PE_ENA_PE_ENA_SHIFT 0
+#define I40E_GLGEN_PE_ENA_PE_ENA_MASK (0x1 << I40E_GLGEN_PE_ENA_PE_ENA_SHIFT)
+#define I40E_GLGEN_PE_ENA_PE_CLK_SRC_SEL_SHIFT 1
+#define I40E_GLGEN_PE_ENA_PE_CLK_SRC_SEL_MASK (0x3 << I40E_GLGEN_PE_ENA_PE_CLK_SRC_SEL_SHIFT)
+#define I40E_GLGEN_RSTAT 0x000B8188
+#define I40E_GLGEN_RSTAT_DEVSTATE_SHIFT 0
+#define I40E_GLGEN_RSTAT_DEVSTATE_MASK (0x3 << I40E_GLGEN_RSTAT_DEVSTATE_SHIFT)
+#define I40E_GLGEN_RSTAT_RESET_TYPE_SHIFT 2
+#define I40E_GLGEN_RSTAT_RESET_TYPE_MASK (0x3 << I40E_GLGEN_RSTAT_RESET_TYPE_SHIFT)
+#define I40E_GLGEN_RSTAT_CORERCNT_SHIFT 4
+#define I40E_GLGEN_RSTAT_CORERCNT_MASK (0x3 << I40E_GLGEN_RSTAT_CORERCNT_SHIFT)
+#define I40E_GLGEN_RSTAT_GLOBRCNT_SHIFT 6
+#define I40E_GLGEN_RSTAT_GLOBRCNT_MASK (0x3 << I40E_GLGEN_RSTAT_GLOBRCNT_SHIFT)
+#define I40E_GLGEN_RSTAT_EMPRCNT_SHIFT 8
+#define I40E_GLGEN_RSTAT_EMPRCNT_MASK (0x3 << I40E_GLGEN_RSTAT_EMPRCNT_SHIFT)
+#define I40E_GLGEN_RSTAT_TIME_TO_RST_SHIFT 10
+#define I40E_GLGEN_RSTAT_TIME_TO_RST_MASK (0x3F << I40E_GLGEN_RSTAT_TIME_TO_RST_SHIFT)
+#define I40E_GLGEN_RSTCTL 0x000B8180
+#define I40E_GLGEN_RSTCTL_GRSTDEL_SHIFT 0
+#define I40E_GLGEN_RSTCTL_GRSTDEL_MASK (0x3F << I40E_GLGEN_RSTCTL_GRSTDEL_SHIFT)
+#define I40E_GLGEN_RSTCTL_ECC_RST_ENA_SHIFT 8
+#define I40E_GLGEN_RSTCTL_ECC_RST_ENA_MASK (0x1 << I40E_GLGEN_RSTCTL_ECC_RST_ENA_SHIFT)
+#define I40E_GLGEN_RSTENA_EMP 0x000B818C
+#define I40E_GLGEN_RSTENA_EMP_EMP_RST_ENA_SHIFT 0
+#define I40E_GLGEN_RSTENA_EMP_EMP_RST_ENA_MASK (0x1 << I40E_GLGEN_RSTENA_EMP_EMP_RST_ENA_SHIFT)
+#define I40E_GLGEN_RTRIG 0x000B8190
+#define I40E_GLGEN_RTRIG_CORER_SHIFT 0
+#define I40E_GLGEN_RTRIG_CORER_MASK (0x1 << I40E_GLGEN_RTRIG_CORER_SHIFT)
+#define I40E_GLGEN_RTRIG_GLOBR_SHIFT 1
+#define I40E_GLGEN_RTRIG_GLOBR_MASK (0x1 << I40E_GLGEN_RTRIG_GLOBR_SHIFT)
+#define I40E_GLGEN_RTRIG_EMPFWR_SHIFT 2
+#define I40E_GLGEN_RTRIG_EMPFWR_MASK (0x1 << I40E_GLGEN_RTRIG_EMPFWR_SHIFT)
+#define I40E_GLGEN_STAT 0x000B612C
+#define I40E_GLGEN_STAT_HWRSVD0_SHIFT 0
+#define I40E_GLGEN_STAT_HWRSVD0_MASK (0x3 << I40E_GLGEN_STAT_HWRSVD0_SHIFT)
+#define I40E_GLGEN_STAT_DCBEN_SHIFT 2
+#define I40E_GLGEN_STAT_DCBEN_MASK (0x1 << I40E_GLGEN_STAT_DCBEN_SHIFT)
+#define I40E_GLGEN_STAT_VTEN_SHIFT 3
+#define I40E_GLGEN_STAT_VTEN_MASK (0x1 << I40E_GLGEN_STAT_VTEN_SHIFT)
+#define I40E_GLGEN_STAT_FCOEN_SHIFT 4
+#define I40E_GLGEN_STAT_FCOEN_MASK (0x1 << I40E_GLGEN_STAT_FCOEN_SHIFT)
+#define I40E_GLGEN_STAT_EVBEN_SHIFT 5
+#define I40E_GLGEN_STAT_EVBEN_MASK (0x1 << I40E_GLGEN_STAT_EVBEN_SHIFT)
+#define I40E_GLGEN_STAT_HWRSVD1_SHIFT 6
+#define I40E_GLGEN_STAT_HWRSVD1_MASK (0x3 << I40E_GLGEN_STAT_HWRSVD1_SHIFT)
+#define I40E_GLGEN_VFLRSTAT(_i) (0x00092600 + ((_i) * 4)) /* _i=0...3 */
+#define I40E_GLGEN_VFLRSTAT_MAX_INDEX 3
+#define I40E_GLGEN_VFLRSTAT_VFLRE_SHIFT 0
+#define I40E_GLGEN_VFLRSTAT_VFLRE_MASK (0xFFFFFFFF << I40E_GLGEN_VFLRSTAT_VFLRE_SHIFT)
+#define I40E_GLVFGEN_TIMER 0x000881BC
+#define I40E_GLVFGEN_TIMER_GTIME_SHIFT 0
+#define I40E_GLVFGEN_TIMER_GTIME_MASK (0xFFFFFFFF << I40E_GLVFGEN_TIMER_GTIME_SHIFT)
+#define I40E_PFGEN_CTRL 0x00092400
+#define I40E_PFGEN_CTRL_PFSWR_SHIFT 0
+#define I40E_PFGEN_CTRL_PFSWR_MASK (0x1 << I40E_PFGEN_CTRL_PFSWR_SHIFT)
+#define I40E_PFGEN_DRUN 0x00092500
+#define I40E_PFGEN_DRUN_DRVUNLD_SHIFT 0
+#define I40E_PFGEN_DRUN_DRVUNLD_MASK (0x1 << I40E_PFGEN_DRUN_DRVUNLD_SHIFT)
+#define I40E_PFGEN_PORTNUM 0x001C0480
+#define I40E_PFGEN_PORTNUM_PORT_NUM_SHIFT 0
+#define I40E_PFGEN_PORTNUM_PORT_NUM_MASK (0x3 << I40E_PFGEN_PORTNUM_PORT_NUM_SHIFT)
+#define I40E_PFGEN_STATE 0x00088000
+#define I40E_PFGEN_STATE_PFPEEN_SHIFT 0
+#define I40E_PFGEN_STATE_PFPEEN_MASK (0x1 << I40E_PFGEN_STATE_PFPEEN_SHIFT)
+#define I40E_PFGEN_STATE_PFFCEN_SHIFT 1
+#define I40E_PFGEN_STATE_PFFCEN_MASK (0x1 << I40E_PFGEN_STATE_PFFCEN_SHIFT)
+#define I40E_PFGEN_STATE_PFLINKEN_SHIFT 2
+#define I40E_PFGEN_STATE_PFLINKEN_MASK (0x1 << I40E_PFGEN_STATE_PFLINKEN_SHIFT)
+#define I40E_PFGEN_STATE_PFSCEN_SHIFT 3
+#define I40E_PFGEN_STATE_PFSCEN_MASK (0x1 << I40E_PFGEN_STATE_PFSCEN_SHIFT)
+#define I40E_PRTGEN_CNF 0x000B8120
+#define I40E_PRTGEN_CNF_PORT_DIS_SHIFT 0
+#define I40E_PRTGEN_CNF_PORT_DIS_MASK (0x1 << I40E_PRTGEN_CNF_PORT_DIS_SHIFT)
+#define I40E_PRTGEN_CNF_ALLOW_PORT_DIS_SHIFT 1
+#define I40E_PRTGEN_CNF_ALLOW_PORT_DIS_MASK (0x1 << I40E_PRTGEN_CNF_ALLOW_PORT_DIS_SHIFT)
+#define I40E_PRTGEN_CNF_EMP_PORT_DIS_SHIFT 2
+#define I40E_PRTGEN_CNF_EMP_PORT_DIS_MASK (0x1 << I40E_PRTGEN_CNF_EMP_PORT_DIS_SHIFT)
+#define I40E_PRTGEN_CNF2 0x000B8160
+#define I40E_PRTGEN_CNF2_ACTIVATE_PORT_LINK_SHIFT 0
+#define I40E_PRTGEN_CNF2_ACTIVATE_PORT_LINK_MASK (0x1 << I40E_PRTGEN_CNF2_ACTIVATE_PORT_LINK_SHIFT)
+#define I40E_PRTGEN_STATUS 0x000B8100
+#define I40E_PRTGEN_STATUS_PORT_VALID_SHIFT 0
+#define I40E_PRTGEN_STATUS_PORT_VALID_MASK (0x1 << I40E_PRTGEN_STATUS_PORT_VALID_SHIFT)
+#define I40E_PRTGEN_STATUS_PORT_ACTIVE_SHIFT 1
+#define I40E_PRTGEN_STATUS_PORT_ACTIVE_MASK (0x1 << I40E_PRTGEN_STATUS_PORT_ACTIVE_SHIFT)
+#define I40E_VFGEN_RSTAT1(_VF) (0x00074400 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VFGEN_RSTAT1_MAX_INDEX 127
+#define I40E_VFGEN_RSTAT1_VFR_STATE_SHIFT 0
+#define I40E_VFGEN_RSTAT1_VFR_STATE_MASK (0x3 << I40E_VFGEN_RSTAT1_VFR_STATE_SHIFT)
+#define I40E_VPGEN_VFRSTAT(_VF) (0x00091C00 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VPGEN_VFRSTAT_MAX_INDEX 127
+#define I40E_VPGEN_VFRSTAT_VFRD_SHIFT 0
+#define I40E_VPGEN_VFRSTAT_VFRD_MASK (0x1 << I40E_VPGEN_VFRSTAT_VFRD_SHIFT)
+#define I40E_VPGEN_VFRTRIG(_VF) (0x00091800 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VPGEN_VFRTRIG_MAX_INDEX 127
+#define I40E_VPGEN_VFRTRIG_VFSWR_SHIFT 0
+#define I40E_VPGEN_VFRTRIG_VFSWR_MASK (0x1 << I40E_VPGEN_VFRTRIG_VFSWR_SHIFT)
+#define I40E_VSIGEN_RSTAT(_VSI) (0x00090800 + ((_VSI) * 4)) /* _i=0...383 */
+#define I40E_VSIGEN_RSTAT_MAX_INDEX 383
+#define I40E_VSIGEN_RSTAT_VMRD_SHIFT 0
+#define I40E_VSIGEN_RSTAT_VMRD_MASK (0x1 << I40E_VSIGEN_RSTAT_VMRD_SHIFT)
+#define I40E_VSIGEN_RTRIG(_VSI) (0x00090000 + ((_VSI) * 4)) /* _i=0...383 */
+#define I40E_VSIGEN_RTRIG_MAX_INDEX 383
+#define I40E_VSIGEN_RTRIG_VMSWR_SHIFT 0
+#define I40E_VSIGEN_RTRIG_VMSWR_MASK (0x1 << I40E_VSIGEN_RTRIG_VMSWR_SHIFT)
+#define I40E_GLHMC_APBVTINUSEBASE(_i) (0x000C4a00 + ((_i) * 4))
+#define I40E_GLHMC_APBVTINUSEBASE_MAX_INDEX 15
+#define I40E_GLHMC_APBVTINUSEBASE_FPMAPBINUSEBASE_SHIFT 0
+#define I40E_GLHMC_APBVTINUSEBASE_FPMAPBINUSEBASE_MASK (0xFFFFFF << I40E_GLHMC_APBVTINUSEBASE_FPMAPBINUSEBASE_SHIFT)
+#define I40E_GLHMC_CEQPART(_i) (0x001312C0 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_CEQPART_MAX_INDEX 15
+#define I40E_GLHMC_CEQPART_PMCEQBASE_SHIFT 0
+#define I40E_GLHMC_CEQPART_PMCEQBASE_MASK (0xFF << I40E_GLHMC_CEQPART_PMCEQBASE_SHIFT)
+#define I40E_GLHMC_CEQPART_PMCEQSIZE_SHIFT 16
+#define I40E_GLHMC_CEQPART_PMCEQSIZE_MASK (0x1FF << I40E_GLHMC_CEQPART_PMCEQSIZE_SHIFT)
+#define I40E_GLHMC_DBCQPART(_i) (0x00131240 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_DBCQPART_MAX_INDEX 15
+#define I40E_GLHMC_DBCQPART_PMDBCQBASE_SHIFT 0
+#define I40E_GLHMC_DBCQPART_PMDBCQBASE_MASK (0x3FFF << I40E_GLHMC_DBCQPART_PMDBCQBASE_SHIFT)
+#define I40E_GLHMC_DBCQPART_PMDBCQSIZE_SHIFT 16
+#define I40E_GLHMC_DBCQPART_PMDBCQSIZE_MASK (0x7FFF << I40E_GLHMC_DBCQPART_PMDBCQSIZE_SHIFT)
+#define I40E_GLHMC_DBQPPART(_i) (0x00138D80 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_DBQPPART_MAX_INDEX 15
+#define I40E_GLHMC_DBQPPART_PMDBQPBASE_SHIFT 0
+#define I40E_GLHMC_DBQPPART_PMDBQPBASE_MASK (0x3FFF << I40E_GLHMC_DBQPPART_PMDBQPBASE_SHIFT)
+#define I40E_GLHMC_DBQPPART_PMDBQPSIZE_SHIFT 16
+#define I40E_GLHMC_DBQPPART_PMDBQPSIZE_MASK (0x7FFF << I40E_GLHMC_DBQPPART_PMDBQPSIZE_SHIFT)
+#define I40E_GLHMC_FCOEDDPBASE(_i) (0x000C6600 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_FCOEDDPBASE_MAX_INDEX 15
+#define I40E_GLHMC_FCOEDDPBASE_FPMFCOEDDPBASE_SHIFT 0
+#define I40E_GLHMC_FCOEDDPBASE_FPMFCOEDDPBASE_MASK (0xFFFFFF << I40E_GLHMC_FCOEDDPBASE_FPMFCOEDDPBASE_SHIFT)
+#define I40E_GLHMC_FCOEDDPCNT(_i) (0x000C6700 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_FCOEDDPCNT_MAX_INDEX 15
+#define I40E_GLHMC_FCOEDDPCNT_FPMFCOEDDPCNT_SHIFT 0
+#define I40E_GLHMC_FCOEDDPCNT_FPMFCOEDDPCNT_MASK (0xFFFFF << I40E_GLHMC_FCOEDDPCNT_FPMFCOEDDPCNT_SHIFT)
+#define I40E_GLHMC_FCOEDDPOBJSZ 0x000C2010
+#define I40E_GLHMC_FCOEDDPOBJSZ_PMFCOEDDPOBJSZ_SHIFT 0
+#define I40E_GLHMC_FCOEDDPOBJSZ_PMFCOEDDPOBJSZ_MASK (0xF << I40E_GLHMC_FCOEDDPOBJSZ_PMFCOEDDPOBJSZ_SHIFT)
+#define I40E_GLHMC_FCOEFBASE(_i) (0x000C6800 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_FCOEFBASE_MAX_INDEX 15
+#define I40E_GLHMC_FCOEFBASE_FPMFCOEFBASE_SHIFT 0
+#define I40E_GLHMC_FCOEFBASE_FPMFCOEFBASE_MASK (0xFFFFFF << I40E_GLHMC_FCOEFBASE_FPMFCOEFBASE_SHIFT)
+#define I40E_GLHMC_FCOEFCNT(_i) (0x000C6900 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_FCOEFCNT_MAX_INDEX 15
+#define I40E_GLHMC_FCOEFCNT_FPMFCOEFCNT_SHIFT 0
+#define I40E_GLHMC_FCOEFCNT_FPMFCOEFCNT_MASK (0x7FFFFF << I40E_GLHMC_FCOEFCNT_FPMFCOEFCNT_SHIFT)
+#define I40E_GLHMC_FCOEFMAX 0x000C20D0
+#define I40E_GLHMC_FCOEFMAX_PMFCOEFMAX_SHIFT 0
+#define I40E_GLHMC_FCOEFMAX_PMFCOEFMAX_MASK (0xFFFF << I40E_GLHMC_FCOEFMAX_PMFCOEFMAX_SHIFT)
+#define I40E_GLHMC_FCOEFOBJSZ 0x000C2018
+#define I40E_GLHMC_FCOEFOBJSZ_PMFCOEFOBJSZ_SHIFT 0
+#define I40E_GLHMC_FCOEFOBJSZ_PMFCOEFOBJSZ_MASK (0xF << I40E_GLHMC_FCOEFOBJSZ_PMFCOEFOBJSZ_SHIFT)
+#define I40E_GLHMC_FCOEMAX 0x000C2014
+#define I40E_GLHMC_FCOEMAX_PMFCOEMAX_SHIFT 0
+#define I40E_GLHMC_FCOEMAX_PMFCOEMAX_MASK (0x1FFF << I40E_GLHMC_FCOEMAX_PMFCOEMAX_SHIFT)
+#define I40E_GLHMC_FSIAVBASE(_i) (0x000C5600 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_FSIAVBASE_MAX_INDEX 15
+#define I40E_GLHMC_FSIAVBASE_FPMFSIAVBASE_SHIFT 0
+#define I40E_GLHMC_FSIAVBASE_FPMFSIAVBASE_MASK (0xFFFFFF << I40E_GLHMC_FSIAVBASE_FPMFSIAVBASE_SHIFT)
+#define I40E_GLHMC_FSIAVCNT(_i) (0x000C5700 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_FSIAVCNT_MAX_INDEX 15
+#define I40E_GLHMC_FSIAVCNT_FPMFSIAVCNT_SHIFT 0
+#define I40E_GLHMC_FSIAVCNT_FPMFSIAVCNT_MASK (0x1FFFFFFF << I40E_GLHMC_FSIAVCNT_FPMFSIAVCNT_SHIFT)
+#define I40E_GLHMC_FSIAVCNT_RSVD_SHIFT 29
+#define I40E_GLHMC_FSIAVCNT_RSVD_MASK (0x7 << I40E_GLHMC_FSIAVCNT_RSVD_SHIFT)
+#define I40E_GLHMC_FSIAVMAX 0x000C2068
+#define I40E_GLHMC_FSIAVMAX_PMFSIAVMAX_SHIFT 0
+#define I40E_GLHMC_FSIAVMAX_PMFSIAVMAX_MASK (0x1FFFF << I40E_GLHMC_FSIAVMAX_PMFSIAVMAX_SHIFT)
+#define I40E_GLHMC_FSIAVOBJSZ 0x000C2064
+#define I40E_GLHMC_FSIAVOBJSZ_PMFSIAVOBJSZ_SHIFT 0
+#define I40E_GLHMC_FSIAVOBJSZ_PMFSIAVOBJSZ_MASK (0xF << I40E_GLHMC_FSIAVOBJSZ_PMFSIAVOBJSZ_SHIFT)
+#define I40E_GLHMC_FSIMCBASE(_i) (0x000C6000 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_FSIMCBASE_MAX_INDEX 15
+#define I40E_GLHMC_FSIMCBASE_FPMFSIMCBASE_SHIFT 0
+#define I40E_GLHMC_FSIMCBASE_FPMFSIMCBASE_MASK (0xFFFFFF << I40E_GLHMC_FSIMCBASE_FPMFSIMCBASE_SHIFT)
+#define I40E_GLHMC_FSIMCCNT(_i) (0x000C6100 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_FSIMCCNT_MAX_INDEX 15
+#define I40E_GLHMC_FSIMCCNT_FPMFSIMCSZ_SHIFT 0
+#define I40E_GLHMC_FSIMCCNT_FPMFSIMCSZ_MASK (0x1FFFFFFF << I40E_GLHMC_FSIMCCNT_FPMFSIMCSZ_SHIFT)
+#define I40E_GLHMC_FSIMCMAX 0x000C2060
+#define I40E_GLHMC_FSIMCMAX_PMFSIMCMAX_SHIFT 0
+#define I40E_GLHMC_FSIMCMAX_PMFSIMCMAX_MASK (0x3FFF << I40E_GLHMC_FSIMCMAX_PMFSIMCMAX_SHIFT)
+#define I40E_GLHMC_FSIMCOBJSZ 0x000C205c
+#define I40E_GLHMC_FSIMCOBJSZ_PMFSIMCOBJSZ_SHIFT 0
+#define I40E_GLHMC_FSIMCOBJSZ_PMFSIMCOBJSZ_MASK (0xF << I40E_GLHMC_FSIMCOBJSZ_PMFSIMCOBJSZ_SHIFT)
+#define I40E_GLHMC_LANQMAX 0x000C2008
+#define I40E_GLHMC_LANQMAX_PMLANQMAX_SHIFT 0
+#define I40E_GLHMC_LANQMAX_PMLANQMAX_MASK (0x7FF << I40E_GLHMC_LANQMAX_PMLANQMAX_SHIFT)
+#define I40E_GLHMC_LANRXBASE(_i) (0x000C6400 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_LANRXBASE_MAX_INDEX 15
+#define I40E_GLHMC_LANRXBASE_FPMLANRXBASE_SHIFT 0
+#define I40E_GLHMC_LANRXBASE_FPMLANRXBASE_MASK (0xFFFFFF << I40E_GLHMC_LANRXBASE_FPMLANRXBASE_SHIFT)
+#define I40E_GLHMC_LANRXCNT(_i) (0x000C6500 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_LANRXCNT_MAX_INDEX 15
+#define I40E_GLHMC_LANRXCNT_FPMLANRXCNT_SHIFT 0
+#define I40E_GLHMC_LANRXCNT_FPMLANRXCNT_MASK (0x7FF << I40E_GLHMC_LANRXCNT_FPMLANRXCNT_SHIFT)
+#define I40E_GLHMC_LANRXOBJSZ 0x000C200c
+#define I40E_GLHMC_LANRXOBJSZ_PMLANRXOBJSZ_SHIFT 0
+#define I40E_GLHMC_LANRXOBJSZ_PMLANRXOBJSZ_MASK (0xF << I40E_GLHMC_LANRXOBJSZ_PMLANRXOBJSZ_SHIFT)
+#define I40E_GLHMC_LANTXBASE(_i) (0x000C6200 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_LANTXBASE_MAX_INDEX 15
+#define I40E_GLHMC_LANTXBASE_FPMLANTXBASE_SHIFT 0
+#define I40E_GLHMC_LANTXBASE_FPMLANTXBASE_MASK (0xFFFFFF << I40E_GLHMC_LANTXBASE_FPMLANTXBASE_SHIFT)
+#define I40E_GLHMC_LANTXBASE_RSVD_SHIFT 24
+#define I40E_GLHMC_LANTXBASE_RSVD_MASK (0xFF << I40E_GLHMC_LANTXBASE_RSVD_SHIFT)
+#define I40E_GLHMC_LANTXCNT(_i) (0x000C6300 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_LANTXCNT_MAX_INDEX 15
+#define I40E_GLHMC_LANTXCNT_FPMLANTXCNT_SHIFT 0
+#define I40E_GLHMC_LANTXCNT_FPMLANTXCNT_MASK (0x7FF << I40E_GLHMC_LANTXCNT_FPMLANTXCNT_SHIFT)
+#define I40E_GLHMC_LANTXOBJSZ 0x000C2004
+#define I40E_GLHMC_LANTXOBJSZ_PMLANTXOBJSZ_SHIFT 0
+#define I40E_GLHMC_LANTXOBJSZ_PMLANTXOBJSZ_MASK (0xF << I40E_GLHMC_LANTXOBJSZ_PMLANTXOBJSZ_SHIFT)
+#define I40E_GLHMC_PEARPBASE(_i) (0x000C4800 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_PEARPBASE_MAX_INDEX 15
+#define I40E_GLHMC_PEARPBASE_FPMPEARPBASE_SHIFT 0
+#define I40E_GLHMC_PEARPBASE_FPMPEARPBASE_MASK (0xFFFFFF << I40E_GLHMC_PEARPBASE_FPMPEARPBASE_SHIFT)
+#define I40E_GLHMC_PEARPCNT(_i) (0x000C4900 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_PEARPCNT_MAX_INDEX 15
+#define I40E_GLHMC_PEARPCNT_FPMPEARPCNT_SHIFT 0
+#define I40E_GLHMC_PEARPCNT_FPMPEARPCNT_MASK (0x1FFFFFFF << I40E_GLHMC_PEARPCNT_FPMPEARPCNT_SHIFT)
+#define I40E_GLHMC_PEARPMAX 0x000C2038
+#define I40E_GLHMC_PEARPMAX_PMPEARPMAX_SHIFT 0
+#define I40E_GLHMC_PEARPMAX_PMPEARPMAX_MASK (0x1FFFF << I40E_GLHMC_PEARPMAX_PMPEARPMAX_SHIFT)
+#define I40E_GLHMC_PEARPOBJSZ 0x000C2034
+#define I40E_GLHMC_PEARPOBJSZ_PMPEARPOBJSZ_SHIFT 0
+#define I40E_GLHMC_PEARPOBJSZ_PMPEARPOBJSZ_MASK (0x7 << I40E_GLHMC_PEARPOBJSZ_PMPEARPOBJSZ_SHIFT)
+#define I40E_GLHMC_PECQBASE(_i) (0x000C4200 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_PECQBASE_MAX_INDEX 15
+#define I40E_GLHMC_PECQBASE_FPMPECQBASE_SHIFT 0
+#define I40E_GLHMC_PECQBASE_FPMPECQBASE_MASK (0xFFFFFF << I40E_GLHMC_PECQBASE_FPMPECQBASE_SHIFT)
+#define I40E_GLHMC_PECQCNT(_i) (0x000C4300 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_PECQCNT_MAX_INDEX 15
+#define I40E_GLHMC_PECQCNT_FPMPECQCNT_SHIFT 0
+#define I40E_GLHMC_PECQCNT_FPMPECQCNT_MASK (0x1FFFFFFF << I40E_GLHMC_PECQCNT_FPMPECQCNT_SHIFT)
+#define I40E_GLHMC_PECQOBJSZ 0x000C2020
+#define I40E_GLHMC_PECQOBJSZ_PMPECQOBJSZ_SHIFT 0
+#define I40E_GLHMC_PECQOBJSZ_PMPECQOBJSZ_MASK (0xF << I40E_GLHMC_PECQOBJSZ_PMPECQOBJSZ_SHIFT)
+#define I40E_GLHMC_PEHTCNT(_i) (0x000C4700 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_PEHTCNT_MAX_INDEX 15
+#define I40E_GLHMC_PEHTCNT_FPMPEHTCNT_SHIFT 0
+#define I40E_GLHMC_PEHTCNT_FPMPEHTCNT_MASK (0x1FFFFFFF << I40E_GLHMC_PEHTCNT_FPMPEHTCNT_SHIFT)
+#define I40E_GLHMC_PEHTEBASE(_i) (0x000C4600 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_PEHTEBASE_MAX_INDEX 15
+#define I40E_GLHMC_PEHTEBASE_FPMPEHTEBASE_SHIFT 0
+#define I40E_GLHMC_PEHTEBASE_FPMPEHTEBASE_MASK (0xFFFFFF << I40E_GLHMC_PEHTEBASE_FPMPEHTEBASE_SHIFT)
+#define I40E_GLHMC_PEHTEOBJSZ 0x000C202c
+#define I40E_GLHMC_PEHTEOBJSZ_PMPEHTEOBJSZ_SHIFT 0
+#define I40E_GLHMC_PEHTEOBJSZ_PMPEHTEOBJSZ_MASK (0xF << I40E_GLHMC_PEHTEOBJSZ_PMPEHTEOBJSZ_SHIFT)
+#define I40E_GLHMC_PEHTMAX 0x000C2030
+#define I40E_GLHMC_PEHTMAX_PMPEHTMAX_SHIFT 0
+#define I40E_GLHMC_PEHTMAX_PMPEHTMAX_MASK (0x1FFFFF << I40E_GLHMC_PEHTMAX_PMPEHTMAX_SHIFT)
+#define I40E_GLHMC_PEMRBASE(_i) (0x000C4c00 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_PEMRBASE_MAX_INDEX 15
+#define I40E_GLHMC_PEMRBASE_FPMPEMRBASE_SHIFT 0
+#define I40E_GLHMC_PEMRBASE_FPMPEMRBASE_MASK (0xFFFFFF << I40E_GLHMC_PEMRBASE_FPMPEMRBASE_SHIFT)
+#define I40E_GLHMC_PEMRCNT(_i) (0x000C4d00 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_PEMRCNT_MAX_INDEX 15
+#define I40E_GLHMC_PEMRCNT_FPMPEMRSZ_SHIFT 0
+#define I40E_GLHMC_PEMRCNT_FPMPEMRSZ_MASK (0x1FFFFFFF << I40E_GLHMC_PEMRCNT_FPMPEMRSZ_SHIFT)
+#define I40E_GLHMC_PEMRMAX 0x000C2040
+#define I40E_GLHMC_PEMRMAX_PMPEMRMAX_SHIFT 0
+#define I40E_GLHMC_PEMRMAX_PMPEMRMAX_MASK (0x7FFFFF << I40E_GLHMC_PEMRMAX_PMPEMRMAX_SHIFT)
+#define I40E_GLHMC_PEMROBJSZ 0x000C203c
+#define I40E_GLHMC_PEMROBJSZ_PMPEMROBJSZ_SHIFT 0
+#define I40E_GLHMC_PEMROBJSZ_PMPEMROBJSZ_MASK (0xF << I40E_GLHMC_PEMROBJSZ_PMPEMROBJSZ_SHIFT)
+#define I40E_GLHMC_PEPBLBASE(_i) (0x000C5800 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_PEPBLBASE_MAX_INDEX 15
+#define I40E_GLHMC_PEPBLBASE_FPMPEPBLBASE_SHIFT 0
+#define I40E_GLHMC_PEPBLBASE_FPMPEPBLBASE_MASK (0xFFFFFF << I40E_GLHMC_PEPBLBASE_FPMPEPBLBASE_SHIFT)
+#define I40E_GLHMC_PEPBLCNT(_i) (0x000C5900 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_PEPBLCNT_MAX_INDEX 15
+#define I40E_GLHMC_PEPBLCNT_FPMPEPBLCNT_SHIFT 0
+#define I40E_GLHMC_PEPBLCNT_FPMPEPBLCNT_MASK (0x1FFFFFFF << I40E_GLHMC_PEPBLCNT_FPMPEPBLCNT_SHIFT)
+#define I40E_GLHMC_PEPBLMAX 0x000C206c
+#define I40E_GLHMC_PEPBLMAX_PMPEPBLMAX_SHIFT 0
+#define I40E_GLHMC_PEPBLMAX_PMPEPBLMAX_MASK (0x1FFFFFFF << I40E_GLHMC_PEPBLMAX_PMPEPBLMAX_SHIFT)
+#define I40E_GLHMC_PEQ1BASE(_i) (0x000C5200 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_PEQ1BASE_MAX_INDEX 15
+#define I40E_GLHMC_PEQ1BASE_FPMPEQ1BASE_SHIFT 0
+#define I40E_GLHMC_PEQ1BASE_FPMPEQ1BASE_MASK (0xFFFFFF << I40E_GLHMC_PEQ1BASE_FPMPEQ1BASE_SHIFT)
+#define I40E_GLHMC_PEQ1CNT(_i) (0x000C5300 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_PEQ1CNT_MAX_INDEX 15
+#define I40E_GLHMC_PEQ1CNT_FPMPEQ1CNT_SHIFT 0
+#define I40E_GLHMC_PEQ1CNT_FPMPEQ1CNT_MASK (0x1FFFFFFF << I40E_GLHMC_PEQ1CNT_FPMPEQ1CNT_SHIFT)
+#define I40E_GLHMC_PEQ1FLBASE(_i) (0x000C5400 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_PEQ1FLBASE_MAX_INDEX 15
+#define I40E_GLHMC_PEQ1FLBASE_FPMPEQ1FLBASE_SHIFT 0
+#define I40E_GLHMC_PEQ1FLBASE_FPMPEQ1FLBASE_MASK (0xFFFFFF << I40E_GLHMC_PEQ1FLBASE_FPMPEQ1FLBASE_SHIFT)
+#define I40E_GLHMC_PEQ1FLCNT(_i) (0x000C5500 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_PEQ1FLCNT_MAX_INDEX 15
+#define I40E_GLHMC_PEQ1FLCNT_FPMPEQ1FLCNT_SHIFT 0
+#define I40E_GLHMC_PEQ1FLCNT_FPMPEQ1FLCNT_MASK (0x1FFFFFFF << I40E_GLHMC_PEQ1FLCNT_FPMPEQ1FLCNT_SHIFT)
+#define I40E_GLHMC_PEQ1FLMAX 0x000C2058
+#define I40E_GLHMC_PEQ1FLMAX_PMPEQ1FLMAX_SHIFT 0
+#define I40E_GLHMC_PEQ1FLMAX_PMPEQ1FLMAX_MASK (0x3FFFFF << I40E_GLHMC_PEQ1FLMAX_PMPEQ1FLMAX_SHIFT)
+#define I40E_GLHMC_PEQ1MAX 0x000C2054
+#define I40E_GLHMC_PEQ1MAX_PMPEQ1MAX_SHIFT 0
+#define I40E_GLHMC_PEQ1MAX_PMPEQ1MAX_MASK (0x3FFFFFF << I40E_GLHMC_PEQ1MAX_PMPEQ1MAX_SHIFT)
+#define I40E_GLHMC_PEQ1OBJSZ 0x000C2050
+#define I40E_GLHMC_PEQ1OBJSZ_PMPEQ1OBJSZ_SHIFT 0
+#define I40E_GLHMC_PEQ1OBJSZ_PMPEQ1OBJSZ_MASK (0xF << I40E_GLHMC_PEQ1OBJSZ_PMPEQ1OBJSZ_SHIFT)
+#define I40E_GLHMC_PEQPBASE(_i) (0x000C4000 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_PEQPBASE_MAX_INDEX 15
+#define I40E_GLHMC_PEQPBASE_FPMPEQPBASE_SHIFT 0
+#define I40E_GLHMC_PEQPBASE_FPMPEQPBASE_MASK (0xFFFFFF << I40E_GLHMC_PEQPBASE_FPMPEQPBASE_SHIFT)
+#define I40E_GLHMC_PEQPCNT(_i) (0x000C4100 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_PEQPCNT_MAX_INDEX 15
+#define I40E_GLHMC_PEQPCNT_FPMPEQPCNT_SHIFT 0
+#define I40E_GLHMC_PEQPCNT_FPMPEQPCNT_MASK (0x1FFFFFFF << I40E_GLHMC_PEQPCNT_FPMPEQPCNT_SHIFT)
+#define I40E_GLHMC_PEQPOBJSZ 0x000C201c
+#define I40E_GLHMC_PEQPOBJSZ_PMPEQPOBJSZ_SHIFT 0
+#define I40E_GLHMC_PEQPOBJSZ_PMPEQPOBJSZ_MASK (0xF << I40E_GLHMC_PEQPOBJSZ_PMPEQPOBJSZ_SHIFT)
+#define I40E_GLHMC_PESRQBASE(_i) (0x000C4400 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_PESRQBASE_MAX_INDEX 15
+#define I40E_GLHMC_PESRQBASE_FPMPESRQBASE_SHIFT 0
+#define I40E_GLHMC_PESRQBASE_FPMPESRQBASE_MASK (0xFFFFFF << I40E_GLHMC_PESRQBASE_FPMPESRQBASE_SHIFT)
+#define I40E_GLHMC_PESRQCNT(_i) (0x000C4500 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_PESRQCNT_MAX_INDEX 15
+#define I40E_GLHMC_PESRQCNT_FPMPESRQCNT_SHIFT 0
+#define I40E_GLHMC_PESRQCNT_FPMPESRQCNT_MASK (0x1FFFFFFF << I40E_GLHMC_PESRQCNT_FPMPESRQCNT_SHIFT)
+#define I40E_GLHMC_PESRQMAX 0x000C2028
+#define I40E_GLHMC_PESRQMAX_PMPESRQMAX_SHIFT 0
+#define I40E_GLHMC_PESRQMAX_PMPESRQMAX_MASK (0xFFFF << I40E_GLHMC_PESRQMAX_PMPESRQMAX_SHIFT)
+#define I40E_GLHMC_PESRQOBJSZ 0x000C2024
+#define I40E_GLHMC_PESRQOBJSZ_PMPESRQOBJSZ_SHIFT 0
+#define I40E_GLHMC_PESRQOBJSZ_PMPESRQOBJSZ_MASK (0xF << I40E_GLHMC_PESRQOBJSZ_PMPESRQOBJSZ_SHIFT)
+#define I40E_GLHMC_PESRQOBJSZ_RSVD_SHIFT 4
+#define I40E_GLHMC_PESRQOBJSZ_RSVD_MASK (0xFFFFFFF << I40E_GLHMC_PESRQOBJSZ_RSVD_SHIFT)
+#define I40E_GLHMC_PETIMERBASE(_i) (0x000C5A00 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_PETIMERBASE_MAX_INDEX 15
+#define I40E_GLHMC_PETIMERBASE_FPMPETIMERBASE_SHIFT 0
+#define I40E_GLHMC_PETIMERBASE_FPMPETIMERBASE_MASK (0xFFFFFF << I40E_GLHMC_PETIMERBASE_FPMPETIMERBASE_SHIFT)
+#define I40E_GLHMC_PETIMERCNT(_i) (0x000C5B00 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_PETIMERCNT_MAX_INDEX 15
+#define I40E_GLHMC_PETIMERCNT_FPMPETIMERCNT_SHIFT 0
+#define I40E_GLHMC_PETIMERCNT_FPMPETIMERCNT_MASK (0x1FFFFFFF << I40E_GLHMC_PETIMERCNT_FPMPETIMERCNT_SHIFT)
+#define I40E_GLHMC_PETIMERMAX 0x000C2084
+#define I40E_GLHMC_PETIMERMAX_PMPETIMERMAX_SHIFT 0
+#define I40E_GLHMC_PETIMERMAX_PMPETIMERMAX_MASK (0x1FFFFFFF << I40E_GLHMC_PETIMERMAX_PMPETIMERMAX_SHIFT)
+#define I40E_GLHMC_PETIMEROBJSZ 0x000C2080
+#define I40E_GLHMC_PETIMEROBJSZ_PMPETIMEROBJSZ_SHIFT 0
+#define I40E_GLHMC_PETIMEROBJSZ_PMPETIMEROBJSZ_MASK (0xF << I40E_GLHMC_PETIMEROBJSZ_PMPETIMEROBJSZ_SHIFT)
+#define I40E_GLHMC_PEXFBASE(_i) (0x000C4e00 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_PEXFBASE_MAX_INDEX 15
+#define I40E_GLHMC_PEXFBASE_FPMPEXFBASE_SHIFT 0
+#define I40E_GLHMC_PEXFBASE_FPMPEXFBASE_MASK (0xFFFFFF << I40E_GLHMC_PEXFBASE_FPMPEXFBASE_SHIFT)
+#define I40E_GLHMC_PEXFCNT(_i) (0x000C4f00 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_PEXFCNT_MAX_INDEX 15
+#define I40E_GLHMC_PEXFCNT_FPMPEXFCNT_SHIFT 0
+#define I40E_GLHMC_PEXFCNT_FPMPEXFCNT_MASK (0x1FFFFFFF << I40E_GLHMC_PEXFCNT_FPMPEXFCNT_SHIFT)
+#define I40E_GLHMC_PEXFFLBASE(_i) (0x000C5000 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_PEXFFLBASE_MAX_INDEX 15
+#define I40E_GLHMC_PEXFFLBASE_FPMPEXFFLBASE_SHIFT 0
+#define I40E_GLHMC_PEXFFLBASE_FPMPEXFFLBASE_MASK (0xFFFFFF << I40E_GLHMC_PEXFFLBASE_FPMPEXFFLBASE_SHIFT)
+#define I40E_GLHMC_PEXFFLCNT(_i) (0x000C5100 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_PEXFFLCNT_MAX_INDEX 15
+#define I40E_GLHMC_PEXFFLCNT_FPMPEXFFLCNT_SHIFT 0
+#define I40E_GLHMC_PEXFFLCNT_FPMPEXFFLCNT_MASK (0x1FFFFFFF << I40E_GLHMC_PEXFFLCNT_FPMPEXFFLCNT_SHIFT)
+#define I40E_GLHMC_PEXFFLMAX 0x000C204c
+#define I40E_GLHMC_PEXFFLMAX_PMPEXFFLMAX_SHIFT 0
+#define I40E_GLHMC_PEXFFLMAX_PMPEXFFLMAX_MASK (0x3FFFFF << I40E_GLHMC_PEXFFLMAX_PMPEXFFLMAX_SHIFT)
+#define I40E_GLHMC_PEXFMAX 0x000C2048
+#define I40E_GLHMC_PEXFMAX_PMPEXFMAX_SHIFT 0
+#define I40E_GLHMC_PEXFMAX_PMPEXFMAX_MASK (0x3FFFFFF << I40E_GLHMC_PEXFMAX_PMPEXFMAX_SHIFT)
+#define I40E_GLHMC_PEXFOBJSZ 0x000C2044
+#define I40E_GLHMC_PEXFOBJSZ_PMPEXFOBJSZ_SHIFT 0
+#define I40E_GLHMC_PEXFOBJSZ_PMPEXFOBJSZ_MASK (0xF << I40E_GLHMC_PEXFOBJSZ_PMPEXFOBJSZ_SHIFT)
+#define I40E_GLHMC_PEXFOBJSZ_RSVD_SHIFT 4
+#define I40E_GLHMC_PEXFOBJSZ_RSVD_MASK (0xFFFFFFF << I40E_GLHMC_PEXFOBJSZ_RSVD_SHIFT)
+#define I40E_GLHMC_PFASSIGN(_i) (0x000C0c00 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_PFASSIGN_MAX_INDEX 15
+#define I40E_GLHMC_PFASSIGN_PMFCNPFASSIGN_SHIFT 0
+#define I40E_GLHMC_PFASSIGN_PMFCNPFASSIGN_MASK (0xF << I40E_GLHMC_PFASSIGN_PMFCNPFASSIGN_SHIFT)
+#define I40E_GLHMC_SDPART(_i) (0x000C0800 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLHMC_SDPART_MAX_INDEX 15
+#define I40E_GLHMC_SDPART_PMSDBASE_SHIFT 0
+#define I40E_GLHMC_SDPART_PMSDBASE_MASK (0xFFF << I40E_GLHMC_SDPART_PMSDBASE_SHIFT)
+#define I40E_GLHMC_SDPART_PMSDSIZE_SHIFT 16
+#define I40E_GLHMC_SDPART_PMSDSIZE_MASK (0x1FFF << I40E_GLHMC_SDPART_PMSDSIZE_SHIFT)
+#define I40E_GLHMC_VFAPBVTINUSEBASE(_i) (0x000Cca00 + ((_i) * 4))
+#define I40E_GLHMC_VFAPBVTINUSEBASE_MAX_INDEX 31
+#define I40E_GLHMC_VFAPBVTINUSEBASE_FPMAPBINUSEBASE_SHIFT 0
+#define I40E_GLHMC_VFAPBVTINUSEBASE_FPMAPBINUSEBASE_MASK (0xFFFFFF << I40E_GLHMC_VFAPBVTINUSEBASE_FPMAPBINUSEBASE_SHIFT)
+#define I40E_GLHMC_VFCEQPART(_i) (0x00132240 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFCEQPART_MAX_INDEX 31
+#define I40E_GLHMC_VFCEQPART_PMCEQBASE_SHIFT 0
+#define I40E_GLHMC_VFCEQPART_PMCEQBASE_MASK (0xFF << I40E_GLHMC_VFCEQPART_PMCEQBASE_SHIFT)
+#define I40E_GLHMC_VFCEQPART_PMCEQSIZE_SHIFT 16
+#define I40E_GLHMC_VFCEQPART_PMCEQSIZE_MASK (0x1FF << I40E_GLHMC_VFCEQPART_PMCEQSIZE_SHIFT)
+#define I40E_GLHMC_VFDBCQPART(_i) (0x00132140 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFDBCQPART_MAX_INDEX 31
+#define I40E_GLHMC_VFDBCQPART_PMDBCQBASE_SHIFT 0
+#define I40E_GLHMC_VFDBCQPART_PMDBCQBASE_MASK (0x3FFF << I40E_GLHMC_VFDBCQPART_PMDBCQBASE_SHIFT)
+#define I40E_GLHMC_VFDBCQPART_PMDBCQSIZE_SHIFT 16
+#define I40E_GLHMC_VFDBCQPART_PMDBCQSIZE_MASK (0x7FFF << I40E_GLHMC_VFDBCQPART_PMDBCQSIZE_SHIFT)
+#define I40E_GLHMC_VFDBQPPART(_i) (0x00138E00 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFDBQPPART_MAX_INDEX 31
+#define I40E_GLHMC_VFDBQPPART_PMDBQPBASE_SHIFT 0
+#define I40E_GLHMC_VFDBQPPART_PMDBQPBASE_MASK (0x3FFF << I40E_GLHMC_VFDBQPPART_PMDBQPBASE_SHIFT)
+#define I40E_GLHMC_VFDBQPPART_PMDBQPSIZE_SHIFT 16
+#define I40E_GLHMC_VFDBQPPART_PMDBQPSIZE_MASK (0x7FFF << I40E_GLHMC_VFDBQPPART_PMDBQPSIZE_SHIFT)
+#define I40E_GLHMC_VFFSIAVBASE(_i) (0x000Cd600 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFFSIAVBASE_MAX_INDEX 31
+#define I40E_GLHMC_VFFSIAVBASE_FPMFSIAVBASE_SHIFT 0
+#define I40E_GLHMC_VFFSIAVBASE_FPMFSIAVBASE_MASK (0xFFFFFF << I40E_GLHMC_VFFSIAVBASE_FPMFSIAVBASE_SHIFT)
+#define I40E_GLHMC_VFFSIAVCNT(_i) (0x000Cd700 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFFSIAVCNT_MAX_INDEX 31
+#define I40E_GLHMC_VFFSIAVCNT_FPMFSIAVCNT_SHIFT 0
+#define I40E_GLHMC_VFFSIAVCNT_FPMFSIAVCNT_MASK (0x1FFFFFFF << I40E_GLHMC_VFFSIAVCNT_FPMFSIAVCNT_SHIFT)
+#define I40E_GLHMC_VFFSIAVCNT_RSVD_SHIFT 29
+#define I40E_GLHMC_VFFSIAVCNT_RSVD_MASK (0x7 << I40E_GLHMC_VFFSIAVCNT_RSVD_SHIFT)
+#define I40E_GLHMC_VFPDINV(_i) (0x000C8300 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFPDINV_MAX_INDEX 31
+#define I40E_GLHMC_VFPDINV_PMSDIDX_SHIFT 0
+#define I40E_GLHMC_VFPDINV_PMSDIDX_MASK (0xFFF << I40E_GLHMC_VFPDINV_PMSDIDX_SHIFT)
+#define I40E_GLHMC_VFPDINV_PMPDIDX_SHIFT 16
+#define I40E_GLHMC_VFPDINV_PMPDIDX_MASK (0x1FF << I40E_GLHMC_VFPDINV_PMPDIDX_SHIFT)
+#define I40E_GLHMC_VFPEARPBASE(_i) (0x000Cc800 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFPEARPBASE_MAX_INDEX 31
+#define I40E_GLHMC_VFPEARPBASE_FPMPEARPBASE_SHIFT 0
+#define I40E_GLHMC_VFPEARPBASE_FPMPEARPBASE_MASK (0xFFFFFF << I40E_GLHMC_VFPEARPBASE_FPMPEARPBASE_SHIFT)
+#define I40E_GLHMC_VFPEARPCNT(_i) (0x000Cc900 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFPEARPCNT_MAX_INDEX 31
+#define I40E_GLHMC_VFPEARPCNT_FPMPEARPCNT_SHIFT 0
+#define I40E_GLHMC_VFPEARPCNT_FPMPEARPCNT_MASK (0x1FFFFFFF << I40E_GLHMC_VFPEARPCNT_FPMPEARPCNT_SHIFT)
+#define I40E_GLHMC_VFPECQBASE(_i) (0x000Cc200 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFPECQBASE_MAX_INDEX 31
+#define I40E_GLHMC_VFPECQBASE_FPMPECQBASE_SHIFT 0
+#define I40E_GLHMC_VFPECQBASE_FPMPECQBASE_MASK (0xFFFFFF << I40E_GLHMC_VFPECQBASE_FPMPECQBASE_SHIFT)
+#define I40E_GLHMC_VFPECQCNT(_i) (0x000Cc300 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFPECQCNT_MAX_INDEX 31
+#define I40E_GLHMC_VFPECQCNT_FPMPECQCNT_SHIFT 0
+#define I40E_GLHMC_VFPECQCNT_FPMPECQCNT_MASK (0x1FFFFFFF << I40E_GLHMC_VFPECQCNT_FPMPECQCNT_SHIFT)
+#define I40E_GLHMC_VFPEHTCNT(_i) (0x000Cc700 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFPEHTCNT_MAX_INDEX 31
+#define I40E_GLHMC_VFPEHTCNT_FPMPEHTCNT_SHIFT 0
+#define I40E_GLHMC_VFPEHTCNT_FPMPEHTCNT_MASK (0x1FFFFFFF << I40E_GLHMC_VFPEHTCNT_FPMPEHTCNT_SHIFT)
+#define I40E_GLHMC_VFPEHTEBASE(_i) (0x000Cc600 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFPEHTEBASE_MAX_INDEX 31
+#define I40E_GLHMC_VFPEHTEBASE_FPMPEHTEBASE_SHIFT 0
+#define I40E_GLHMC_VFPEHTEBASE_FPMPEHTEBASE_MASK (0xFFFFFF << I40E_GLHMC_VFPEHTEBASE_FPMPEHTEBASE_SHIFT)
+#define I40E_GLHMC_VFPEMRBASE(_i) (0x000Ccc00 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFPEMRBASE_MAX_INDEX 31
+#define I40E_GLHMC_VFPEMRBASE_FPMPEMRBASE_SHIFT 0
+#define I40E_GLHMC_VFPEMRBASE_FPMPEMRBASE_MASK (0xFFFFFF << I40E_GLHMC_VFPEMRBASE_FPMPEMRBASE_SHIFT)
+#define I40E_GLHMC_VFPEMRCNT(_i) (0x000Ccd00 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFPEMRCNT_MAX_INDEX 31
+#define I40E_GLHMC_VFPEMRCNT_FPMPEMRSZ_SHIFT 0
+#define I40E_GLHMC_VFPEMRCNT_FPMPEMRSZ_MASK (0x1FFFFFFF << I40E_GLHMC_VFPEMRCNT_FPMPEMRSZ_SHIFT)
+#define I40E_GLHMC_VFPEPBLBASE(_i) (0x000Cd800 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFPEPBLBASE_MAX_INDEX 31
+#define I40E_GLHMC_VFPEPBLBASE_FPMPEPBLBASE_SHIFT 0
+#define I40E_GLHMC_VFPEPBLBASE_FPMPEPBLBASE_MASK (0xFFFFFF << I40E_GLHMC_VFPEPBLBASE_FPMPEPBLBASE_SHIFT)
+#define I40E_GLHMC_VFPEPBLCNT(_i) (0x000Cd900 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFPEPBLCNT_MAX_INDEX 31
+#define I40E_GLHMC_VFPEPBLCNT_FPMPEPBLCNT_SHIFT 0
+#define I40E_GLHMC_VFPEPBLCNT_FPMPEPBLCNT_MASK (0x1FFFFFFF << I40E_GLHMC_VFPEPBLCNT_FPMPEPBLCNT_SHIFT)
+#define I40E_GLHMC_VFPEQ1BASE(_i) (0x000Cd200 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFPEQ1BASE_MAX_INDEX 31
+#define I40E_GLHMC_VFPEQ1BASE_FPMPEQ1BASE_SHIFT 0
+#define I40E_GLHMC_VFPEQ1BASE_FPMPEQ1BASE_MASK (0xFFFFFF << I40E_GLHMC_VFPEQ1BASE_FPMPEQ1BASE_SHIFT)
+#define I40E_GLHMC_VFPEQ1CNT(_i) (0x000Cd300 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFPEQ1CNT_MAX_INDEX 31
+#define I40E_GLHMC_VFPEQ1CNT_FPMPEQ1CNT_SHIFT 0
+#define I40E_GLHMC_VFPEQ1CNT_FPMPEQ1CNT_MASK (0x1FFFFFFF << I40E_GLHMC_VFPEQ1CNT_FPMPEQ1CNT_SHIFT)
+#define I40E_GLHMC_VFPEQ1FLBASE(_i) (0x000Cd400 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFPEQ1FLBASE_MAX_INDEX 31
+#define I40E_GLHMC_VFPEQ1FLBASE_FPMPEQ1FLBASE_SHIFT 0
+#define I40E_GLHMC_VFPEQ1FLBASE_FPMPEQ1FLBASE_MASK (0xFFFFFF << I40E_GLHMC_VFPEQ1FLBASE_FPMPEQ1FLBASE_SHIFT)
+#define I40E_GLHMC_VFPEQ1FLCNT(_i) (0x000Cd500 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFPEQ1FLCNT_MAX_INDEX 31
+#define I40E_GLHMC_VFPEQ1FLCNT_FPMPEQ1FLCNT_SHIFT 0
+#define I40E_GLHMC_VFPEQ1FLCNT_FPMPEQ1FLCNT_MASK (0x1FFFFFFF << I40E_GLHMC_VFPEQ1FLCNT_FPMPEQ1FLCNT_SHIFT)
+#define I40E_GLHMC_VFPEQPBASE(_i) (0x000Cc000 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFPEQPBASE_MAX_INDEX 31
+#define I40E_GLHMC_VFPEQPBASE_FPMPEQPBASE_SHIFT 0
+#define I40E_GLHMC_VFPEQPBASE_FPMPEQPBASE_MASK (0xFFFFFF << I40E_GLHMC_VFPEQPBASE_FPMPEQPBASE_SHIFT)
+#define I40E_GLHMC_VFPEQPCNT(_i) (0x000Cc100 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFPEQPCNT_MAX_INDEX 31
+#define I40E_GLHMC_VFPEQPCNT_FPMPEQPCNT_SHIFT 0
+#define I40E_GLHMC_VFPEQPCNT_FPMPEQPCNT_MASK (0x1FFFFFFF << I40E_GLHMC_VFPEQPCNT_FPMPEQPCNT_SHIFT)
+#define I40E_GLHMC_VFPESRQBASE(_i) (0x000Cc400 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFPESRQBASE_MAX_INDEX 31
+#define I40E_GLHMC_VFPESRQBASE_FPMPESRQBASE_SHIFT 0
+#define I40E_GLHMC_VFPESRQBASE_FPMPESRQBASE_MASK (0xFFFFFF << I40E_GLHMC_VFPESRQBASE_FPMPESRQBASE_SHIFT)
+#define I40E_GLHMC_VFPESRQCNT(_i) (0x000Cc500 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFPESRQCNT_MAX_INDEX 31
+#define I40E_GLHMC_VFPESRQCNT_FPMPESRQCNT_SHIFT 0
+#define I40E_GLHMC_VFPESRQCNT_FPMPESRQCNT_MASK (0x1FFFFFFF << I40E_GLHMC_VFPESRQCNT_FPMPESRQCNT_SHIFT)
+#define I40E_GLHMC_VFPETIMERBASE(_i) (0x000CDA00 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFPETIMERBASE_MAX_INDEX 31
+#define I40E_GLHMC_VFPETIMERBASE_FPMPETIMERBASE_SHIFT 0
+#define I40E_GLHMC_VFPETIMERBASE_FPMPETIMERBASE_MASK (0xFFFFFF << I40E_GLHMC_VFPETIMERBASE_FPMPETIMERBASE_SHIFT)
+#define I40E_GLHMC_VFPETIMERCNT(_i) (0x000CDB00 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFPETIMERCNT_MAX_INDEX 31
+#define I40E_GLHMC_VFPETIMERCNT_FPMPETIMERCNT_SHIFT 0
+#define I40E_GLHMC_VFPETIMERCNT_FPMPETIMERCNT_MASK (0x1FFFFFFF << I40E_GLHMC_VFPETIMERCNT_FPMPETIMERCNT_SHIFT)
+#define I40E_GLHMC_VFPEXFBASE(_i) (0x000Cce00 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFPEXFBASE_MAX_INDEX 31
+#define I40E_GLHMC_VFPEXFBASE_FPMPEXFBASE_SHIFT 0
+#define I40E_GLHMC_VFPEXFBASE_FPMPEXFBASE_MASK (0xFFFFFF << I40E_GLHMC_VFPEXFBASE_FPMPEXFBASE_SHIFT)
+#define I40E_GLHMC_VFPEXFCNT(_i) (0x000Ccf00 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFPEXFCNT_MAX_INDEX 31
+#define I40E_GLHMC_VFPEXFCNT_FPMPEXFCNT_SHIFT 0
+#define I40E_GLHMC_VFPEXFCNT_FPMPEXFCNT_MASK (0x1FFFFFFF << I40E_GLHMC_VFPEXFCNT_FPMPEXFCNT_SHIFT)
+#define I40E_GLHMC_VFPEXFFLBASE(_i) (0x000Cd000 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFPEXFFLBASE_MAX_INDEX 31
+#define I40E_GLHMC_VFPEXFFLBASE_FPMPEXFFLBASE_SHIFT 0
+#define I40E_GLHMC_VFPEXFFLBASE_FPMPEXFFLBASE_MASK (0xFFFFFF << I40E_GLHMC_VFPEXFFLBASE_FPMPEXFFLBASE_SHIFT)
+#define I40E_GLHMC_VFPEXFFLCNT(_i) (0x000Cd100 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFPEXFFLCNT_MAX_INDEX 31
+#define I40E_GLHMC_VFPEXFFLCNT_FPMPEXFFLCNT_SHIFT 0
+#define I40E_GLHMC_VFPEXFFLCNT_FPMPEXFFLCNT_MASK (0x1FFFFFFF << I40E_GLHMC_VFPEXFFLCNT_FPMPEXFFLCNT_SHIFT)
+#define I40E_GLHMC_VFSDPART(_i) (0x000C8800 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLHMC_VFSDPART_MAX_INDEX 31
+#define I40E_GLHMC_VFSDPART_PMSDBASE_SHIFT 0
+#define I40E_GLHMC_VFSDPART_PMSDBASE_MASK (0xFFF << I40E_GLHMC_VFSDPART_PMSDBASE_SHIFT)
+#define I40E_GLHMC_VFSDPART_PMSDSIZE_SHIFT 16
+#define I40E_GLHMC_VFSDPART_PMSDSIZE_MASK (0x1FFF << I40E_GLHMC_VFSDPART_PMSDSIZE_SHIFT)
+#define I40E_PFHMC_ERRORDATA 0x000C0500
+#define I40E_PFHMC_ERRORDATA_HMC_ERROR_DATA_SHIFT 0
+#define I40E_PFHMC_ERRORDATA_HMC_ERROR_DATA_MASK (0x3FFFFFFF << I40E_PFHMC_ERRORDATA_HMC_ERROR_DATA_SHIFT)
+#define I40E_PFHMC_ERRORINFO 0x000C0400
+#define I40E_PFHMC_ERRORINFO_PMF_INDEX_SHIFT 0
+#define I40E_PFHMC_ERRORINFO_PMF_INDEX_MASK (0x1F << I40E_PFHMC_ERRORINFO_PMF_INDEX_SHIFT)
+#define I40E_PFHMC_ERRORINFO_PMF_ISVF_SHIFT 7
+#define I40E_PFHMC_ERRORINFO_PMF_ISVF_MASK (0x1 << I40E_PFHMC_ERRORINFO_PMF_ISVF_SHIFT)
+#define I40E_PFHMC_ERRORINFO_HMC_ERROR_TYPE_SHIFT 8
+#define I40E_PFHMC_ERRORINFO_HMC_ERROR_TYPE_MASK (0xF << I40E_PFHMC_ERRORINFO_HMC_ERROR_TYPE_SHIFT)
+#define I40E_PFHMC_ERRORINFO_HMC_OBJECT_TYPE_SHIFT 16
+#define I40E_PFHMC_ERRORINFO_HMC_OBJECT_TYPE_MASK (0x1F << I40E_PFHMC_ERRORINFO_HMC_OBJECT_TYPE_SHIFT)
+#define I40E_PFHMC_ERRORINFO_ERROR_DETECTED_SHIFT 31
+#define I40E_PFHMC_ERRORINFO_ERROR_DETECTED_MASK (0x1 << I40E_PFHMC_ERRORINFO_ERROR_DETECTED_SHIFT)
+#define I40E_PFHMC_PDINV 0x000C0300
+#define I40E_PFHMC_PDINV_PMSDIDX_SHIFT 0
+#define I40E_PFHMC_PDINV_PMSDIDX_MASK (0xFFF << I40E_PFHMC_PDINV_PMSDIDX_SHIFT)
+#define I40E_PFHMC_PDINV_PMPDIDX_SHIFT 16
+#define I40E_PFHMC_PDINV_PMPDIDX_MASK (0x1FF << I40E_PFHMC_PDINV_PMPDIDX_SHIFT)
+#define I40E_PFHMC_SDCMD 0x000C0000
+#define I40E_PFHMC_SDCMD_PMSDIDX_SHIFT 0
+#define I40E_PFHMC_SDCMD_PMSDIDX_MASK (0xFFF << I40E_PFHMC_SDCMD_PMSDIDX_SHIFT)
+#define I40E_PFHMC_SDCMD_PMSDWR_SHIFT 31
+#define I40E_PFHMC_SDCMD_PMSDWR_MASK (0x1 << I40E_PFHMC_SDCMD_PMSDWR_SHIFT)
+#define I40E_PFHMC_SDDATAHIGH 0x000C0200
+#define I40E_PFHMC_SDDATAHIGH_PMSDDATAHIGH_SHIFT 0
+#define I40E_PFHMC_SDDATAHIGH_PMSDDATAHIGH_MASK (0xFFFFFFFF << I40E_PFHMC_SDDATAHIGH_PMSDDATAHIGH_SHIFT)
+#define I40E_PFHMC_SDDATALOW 0x000C0100
+#define I40E_PFHMC_SDDATALOW_PMSDVALID_SHIFT 0
+#define I40E_PFHMC_SDDATALOW_PMSDVALID_MASK (0x1 << I40E_PFHMC_SDDATALOW_PMSDVALID_SHIFT)
+#define I40E_PFHMC_SDDATALOW_PMSDTYPE_SHIFT 1
+#define I40E_PFHMC_SDDATALOW_PMSDTYPE_MASK (0x1 << I40E_PFHMC_SDDATALOW_PMSDTYPE_SHIFT)
+#define I40E_PFHMC_SDDATALOW_PMSDBPCOUNT_SHIFT 2
+#define I40E_PFHMC_SDDATALOW_PMSDBPCOUNT_MASK (0x3FF << I40E_PFHMC_SDDATALOW_PMSDBPCOUNT_SHIFT)
+#define I40E_PFHMC_SDDATALOW_PMSDDATALOW_SHIFT 12
+#define I40E_PFHMC_SDDATALOW_PMSDDATALOW_MASK (0xFFFFF << I40E_PFHMC_SDDATALOW_PMSDDATALOW_SHIFT)
+#define I40E_GL_UFUSE 0x00094008
+#define I40E_GL_UFUSE_FOUR_PORT_ENABLE_SHIFT 1
+#define I40E_GL_UFUSE_FOUR_PORT_ENABLE_MASK (0x1 << I40E_GL_UFUSE_FOUR_PORT_ENABLE_SHIFT)
+#define I40E_GL_UFUSE_NIC_ID_SHIFT 2
+#define I40E_GL_UFUSE_NIC_ID_MASK (0x1 << I40E_GL_UFUSE_NIC_ID_SHIFT)
+#define I40E_GL_UFUSE_ULT_LOCKOUT_SHIFT 10
+#define I40E_GL_UFUSE_ULT_LOCKOUT_MASK (0x1 << I40E_GL_UFUSE_ULT_LOCKOUT_SHIFT)
+#define I40E_GL_UFUSE_CLS_LOCKOUT_SHIFT 11
+#define I40E_GL_UFUSE_CLS_LOCKOUT_MASK (0x1 << I40E_GL_UFUSE_CLS_LOCKOUT_SHIFT)
+#define I40E_EMPINT_GPIO_ENA 0x00088188
+#define I40E_EMPINT_GPIO_ENA_GPIO0_ENA_SHIFT 0
+#define I40E_EMPINT_GPIO_ENA_GPIO0_ENA_MASK (0x1 << I40E_EMPINT_GPIO_ENA_GPIO0_ENA_SHIFT)
+#define I40E_EMPINT_GPIO_ENA_GPIO1_ENA_SHIFT 1
+#define I40E_EMPINT_GPIO_ENA_GPIO1_ENA_MASK (0x1 << I40E_EMPINT_GPIO_ENA_GPIO1_ENA_SHIFT)
+#define I40E_EMPINT_GPIO_ENA_GPIO2_ENA_SHIFT 2
+#define I40E_EMPINT_GPIO_ENA_GPIO2_ENA_MASK (0x1 << I40E_EMPINT_GPIO_ENA_GPIO2_ENA_SHIFT)
+#define I40E_EMPINT_GPIO_ENA_GPIO3_ENA_SHIFT 3
+#define I40E_EMPINT_GPIO_ENA_GPIO3_ENA_MASK (0x1 << I40E_EMPINT_GPIO_ENA_GPIO3_ENA_SHIFT)
+#define I40E_EMPINT_GPIO_ENA_GPIO4_ENA_SHIFT 4
+#define I40E_EMPINT_GPIO_ENA_GPIO4_ENA_MASK (0x1 << I40E_EMPINT_GPIO_ENA_GPIO4_ENA_SHIFT)
+#define I40E_EMPINT_GPIO_ENA_GPIO5_ENA_SHIFT 5
+#define I40E_EMPINT_GPIO_ENA_GPIO5_ENA_MASK (0x1 << I40E_EMPINT_GPIO_ENA_GPIO5_ENA_SHIFT)
+#define I40E_EMPINT_GPIO_ENA_GPIO6_ENA_SHIFT 6
+#define I40E_EMPINT_GPIO_ENA_GPIO6_ENA_MASK (0x1 << I40E_EMPINT_GPIO_ENA_GPIO6_ENA_SHIFT)
+#define I40E_EMPINT_GPIO_ENA_GPIO7_ENA_SHIFT 7
+#define I40E_EMPINT_GPIO_ENA_GPIO7_ENA_MASK (0x1 << I40E_EMPINT_GPIO_ENA_GPIO7_ENA_SHIFT)
+#define I40E_EMPINT_GPIO_ENA_GPIO8_ENA_SHIFT 8
+#define I40E_EMPINT_GPIO_ENA_GPIO8_ENA_MASK (0x1 << I40E_EMPINT_GPIO_ENA_GPIO8_ENA_SHIFT)
+#define I40E_EMPINT_GPIO_ENA_GPIO9_ENA_SHIFT 9
+#define I40E_EMPINT_GPIO_ENA_GPIO9_ENA_MASK (0x1 << I40E_EMPINT_GPIO_ENA_GPIO9_ENA_SHIFT)
+#define I40E_EMPINT_GPIO_ENA_GPIO10_ENA_SHIFT 10
+#define I40E_EMPINT_GPIO_ENA_GPIO10_ENA_MASK (0x1 << I40E_EMPINT_GPIO_ENA_GPIO10_ENA_SHIFT)
+#define I40E_EMPINT_GPIO_ENA_GPIO11_ENA_SHIFT 11
+#define I40E_EMPINT_GPIO_ENA_GPIO11_ENA_MASK (0x1 << I40E_EMPINT_GPIO_ENA_GPIO11_ENA_SHIFT)
+#define I40E_EMPINT_GPIO_ENA_GPIO12_ENA_SHIFT 12
+#define I40E_EMPINT_GPIO_ENA_GPIO12_ENA_MASK (0x1 << I40E_EMPINT_GPIO_ENA_GPIO12_ENA_SHIFT)
+#define I40E_EMPINT_GPIO_ENA_GPIO13_ENA_SHIFT 13
+#define I40E_EMPINT_GPIO_ENA_GPIO13_ENA_MASK (0x1 << I40E_EMPINT_GPIO_ENA_GPIO13_ENA_SHIFT)
+#define I40E_EMPINT_GPIO_ENA_GPIO14_ENA_SHIFT 14
+#define I40E_EMPINT_GPIO_ENA_GPIO14_ENA_MASK (0x1 << I40E_EMPINT_GPIO_ENA_GPIO14_ENA_SHIFT)
+#define I40E_EMPINT_GPIO_ENA_GPIO15_ENA_SHIFT 15
+#define I40E_EMPINT_GPIO_ENA_GPIO15_ENA_MASK (0x1 << I40E_EMPINT_GPIO_ENA_GPIO15_ENA_SHIFT)
+#define I40E_EMPINT_GPIO_ENA_GPIO16_ENA_SHIFT 16
+#define I40E_EMPINT_GPIO_ENA_GPIO16_ENA_MASK (0x1 << I40E_EMPINT_GPIO_ENA_GPIO16_ENA_SHIFT)
+#define I40E_EMPINT_GPIO_ENA_GPIO17_ENA_SHIFT 17
+#define I40E_EMPINT_GPIO_ENA_GPIO17_ENA_MASK (0x1 << I40E_EMPINT_GPIO_ENA_GPIO17_ENA_SHIFT)
+#define I40E_EMPINT_GPIO_ENA_GPIO18_ENA_SHIFT 18
+#define I40E_EMPINT_GPIO_ENA_GPIO18_ENA_MASK (0x1 << I40E_EMPINT_GPIO_ENA_GPIO18_ENA_SHIFT)
+#define I40E_EMPINT_GPIO_ENA_GPIO19_ENA_SHIFT 19
+#define I40E_EMPINT_GPIO_ENA_GPIO19_ENA_MASK (0x1 << I40E_EMPINT_GPIO_ENA_GPIO19_ENA_SHIFT)
+#define I40E_EMPINT_GPIO_ENA_GPIO20_ENA_SHIFT 20
+#define I40E_EMPINT_GPIO_ENA_GPIO20_ENA_MASK (0x1 << I40E_EMPINT_GPIO_ENA_GPIO20_ENA_SHIFT)
+#define I40E_EMPINT_GPIO_ENA_GPIO21_ENA_SHIFT 21
+#define I40E_EMPINT_GPIO_ENA_GPIO21_ENA_MASK (0x1 << I40E_EMPINT_GPIO_ENA_GPIO21_ENA_SHIFT)
+#define I40E_EMPINT_GPIO_ENA_GPIO22_ENA_SHIFT 22
+#define I40E_EMPINT_GPIO_ENA_GPIO22_ENA_MASK (0x1 << I40E_EMPINT_GPIO_ENA_GPIO22_ENA_SHIFT)
+#define I40E_EMPINT_GPIO_ENA_GPIO23_ENA_SHIFT 23
+#define I40E_EMPINT_GPIO_ENA_GPIO23_ENA_MASK (0x1 << I40E_EMPINT_GPIO_ENA_GPIO23_ENA_SHIFT)
+#define I40E_EMPINT_GPIO_ENA_GPIO24_ENA_SHIFT 24
+#define I40E_EMPINT_GPIO_ENA_GPIO24_ENA_MASK (0x1 << I40E_EMPINT_GPIO_ENA_GPIO24_ENA_SHIFT)
+#define I40E_EMPINT_GPIO_ENA_GPIO25_ENA_SHIFT 25
+#define I40E_EMPINT_GPIO_ENA_GPIO25_ENA_MASK (0x1 << I40E_EMPINT_GPIO_ENA_GPIO25_ENA_SHIFT)
+#define I40E_EMPINT_GPIO_ENA_GPIO26_ENA_SHIFT 26
+#define I40E_EMPINT_GPIO_ENA_GPIO26_ENA_MASK (0x1 << I40E_EMPINT_GPIO_ENA_GPIO26_ENA_SHIFT)
+#define I40E_EMPINT_GPIO_ENA_GPIO27_ENA_SHIFT 27
+#define I40E_EMPINT_GPIO_ENA_GPIO27_ENA_MASK (0x1 << I40E_EMPINT_GPIO_ENA_GPIO27_ENA_SHIFT)
+#define I40E_EMPINT_GPIO_ENA_GPIO28_ENA_SHIFT 28
+#define I40E_EMPINT_GPIO_ENA_GPIO28_ENA_MASK (0x1 << I40E_EMPINT_GPIO_ENA_GPIO28_ENA_SHIFT)
+#define I40E_EMPINT_GPIO_ENA_GPIO29_ENA_SHIFT 29
+#define I40E_EMPINT_GPIO_ENA_GPIO29_ENA_MASK (0x1 << I40E_EMPINT_GPIO_ENA_GPIO29_ENA_SHIFT)
+#define I40E_PFGEN_PORTMDIO_NUM 0x0003F100
+#define I40E_PFGEN_PORTMDIO_NUM_PORT_NUM_SHIFT 0
+#define I40E_PFGEN_PORTMDIO_NUM_PORT_NUM_MASK (0x3 << I40E_PFGEN_PORTMDIO_NUM_PORT_NUM_SHIFT)
+#define I40E_PFGEN_PORTMDIO_NUM_VFLINK_STAT_ENA_SHIFT 4
+#define I40E_PFGEN_PORTMDIO_NUM_VFLINK_STAT_ENA_MASK (0x1 << I40E_PFGEN_PORTMDIO_NUM_VFLINK_STAT_ENA_SHIFT)
+#define I40E_PFINT_AEQCTL 0x00038700
+#define I40E_PFINT_AEQCTL_MSIX_INDX_SHIFT 0
+#define I40E_PFINT_AEQCTL_MSIX_INDX_MASK (0xFF << I40E_PFINT_AEQCTL_MSIX_INDX_SHIFT)
+#define I40E_PFINT_AEQCTL_ITR_INDX_SHIFT 11
+#define I40E_PFINT_AEQCTL_ITR_INDX_MASK (0x3 << I40E_PFINT_AEQCTL_ITR_INDX_SHIFT)
+#define I40E_PFINT_AEQCTL_MSIX0_INDX_SHIFT 13
+#define I40E_PFINT_AEQCTL_MSIX0_INDX_MASK (0x7 << I40E_PFINT_AEQCTL_MSIX0_INDX_SHIFT)
+#define I40E_PFINT_AEQCTL_CAUSE_ENA_SHIFT 30
+#define I40E_PFINT_AEQCTL_CAUSE_ENA_MASK (0x1 << I40E_PFINT_AEQCTL_CAUSE_ENA_SHIFT)
+#define I40E_PFINT_AEQCTL_INTEVENT_SHIFT 31
+#define I40E_PFINT_AEQCTL_INTEVENT_MASK (0x1 << I40E_PFINT_AEQCTL_INTEVENT_SHIFT)
+#define I40E_PFINT_CEQCTL(_INTPF) (0x00036800 + ((_INTPF) * 4)) /* _i=0...511 */
+#define I40E_PFINT_CEQCTL_MAX_INDEX 511
+#define I40E_PFINT_CEQCTL_MSIX_INDX_SHIFT 0
+#define I40E_PFINT_CEQCTL_MSIX_INDX_MASK (0xFF << I40E_PFINT_CEQCTL_MSIX_INDX_SHIFT)
+#define I40E_PFINT_CEQCTL_ITR_INDX_SHIFT 11
+#define I40E_PFINT_CEQCTL_ITR_INDX_MASK (0x3 << I40E_PFINT_CEQCTL_ITR_INDX_SHIFT)
+#define I40E_PFINT_CEQCTL_MSIX0_INDX_SHIFT 13
+#define I40E_PFINT_CEQCTL_MSIX0_INDX_MASK (0x7 << I40E_PFINT_CEQCTL_MSIX0_INDX_SHIFT)
+#define I40E_PFINT_CEQCTL_NEXTQ_INDX_SHIFT 16
+#define I40E_PFINT_CEQCTL_NEXTQ_INDX_MASK (0x7FF << I40E_PFINT_CEQCTL_NEXTQ_INDX_SHIFT)
+#define I40E_PFINT_CEQCTL_NEXTQ_TYPE_SHIFT 27
+#define I40E_PFINT_CEQCTL_NEXTQ_TYPE_MASK (0x3 << I40E_PFINT_CEQCTL_NEXTQ_TYPE_SHIFT)
+#define I40E_PFINT_CEQCTL_CAUSE_ENA_SHIFT 30
+#define I40E_PFINT_CEQCTL_CAUSE_ENA_MASK (0x1 << I40E_PFINT_CEQCTL_CAUSE_ENA_SHIFT)
+#define I40E_PFINT_CEQCTL_INTEVENT_SHIFT 31
+#define I40E_PFINT_CEQCTL_INTEVENT_MASK (0x1 << I40E_PFINT_CEQCTL_INTEVENT_SHIFT)
+#define I40E_PFINT_DYN_CTL0 0x00038480
+#define I40E_PFINT_DYN_CTL0_INTENA_SHIFT 0
+#define I40E_PFINT_DYN_CTL0_INTENA_MASK (0x1 << I40E_PFINT_DYN_CTL0_INTENA_SHIFT)
+#define I40E_PFINT_DYN_CTL0_CLEARPBA_SHIFT 1
+#define I40E_PFINT_DYN_CTL0_CLEARPBA_MASK (0x1 << I40E_PFINT_DYN_CTL0_CLEARPBA_SHIFT)
+#define I40E_PFINT_DYN_CTL0_SWINT_TRIG_SHIFT 2
+#define I40E_PFINT_DYN_CTL0_SWINT_TRIG_MASK (0x1 << I40E_PFINT_DYN_CTL0_SWINT_TRIG_SHIFT)
+#define I40E_PFINT_DYN_CTL0_ITR_INDX_SHIFT 3
+#define I40E_PFINT_DYN_CTL0_ITR_INDX_MASK (0x3 << I40E_PFINT_DYN_CTL0_ITR_INDX_SHIFT)
+#define I40E_PFINT_DYN_CTL0_INTERVAL_SHIFT 5
+#define I40E_PFINT_DYN_CTL0_INTERVAL_MASK (0xFFF << I40E_PFINT_DYN_CTL0_INTERVAL_SHIFT)
+#define I40E_PFINT_DYN_CTL0_SW_ITR_INDX_ENA_SHIFT 24
+#define I40E_PFINT_DYN_CTL0_SW_ITR_INDX_ENA_MASK (0x1 << I40E_PFINT_DYN_CTL0_SW_ITR_INDX_ENA_SHIFT)
+#define I40E_PFINT_DYN_CTL0_SW_ITR_INDX_SHIFT 25
+#define I40E_PFINT_DYN_CTL0_SW_ITR_INDX_MASK (0x3 << I40E_PFINT_DYN_CTL0_SW_ITR_INDX_SHIFT)
+#define I40E_PFINT_DYN_CTL0_INTENA_MSK_SHIFT 31
+#define I40E_PFINT_DYN_CTL0_INTENA_MSK_MASK (0x1 << I40E_PFINT_DYN_CTL0_INTENA_MSK_SHIFT)
+#define I40E_PFINT_DYN_CTLN(_INTPF) (0x00034800 + ((_INTPF) * 4)) /* _i=0...511 */
+#define I40E_PFINT_DYN_CTLN_MAX_INDEX 511
+#define I40E_PFINT_DYN_CTLN_INTENA_SHIFT 0
+#define I40E_PFINT_DYN_CTLN_INTENA_MASK (0x1 << I40E_PFINT_DYN_CTLN_INTENA_SHIFT)
+#define I40E_PFINT_DYN_CTLN_CLEARPBA_SHIFT 1
+#define I40E_PFINT_DYN_CTLN_CLEARPBA_MASK (0x1 << I40E_PFINT_DYN_CTLN_CLEARPBA_SHIFT)
+#define I40E_PFINT_DYN_CTLN_SWINT_TRIG_SHIFT 2
+#define I40E_PFINT_DYN_CTLN_SWINT_TRIG_MASK (0x1 << I40E_PFINT_DYN_CTLN_SWINT_TRIG_SHIFT)
+#define I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT 3
+#define I40E_PFINT_DYN_CTLN_ITR_INDX_MASK (0x3 << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT)
+#define I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT 5
+#define I40E_PFINT_DYN_CTLN_INTERVAL_MASK (0xFFF << I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT)
+#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_SHIFT 24
+#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK (0x1 << I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_SHIFT)
+#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_SHIFT 25
+#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_MASK (0x3 << I40E_PFINT_DYN_CTLN_SW_ITR_INDX_SHIFT)
+#define I40E_PFINT_DYN_CTLN_INTENA_MSK_SHIFT 31
+#define I40E_PFINT_DYN_CTLN_INTENA_MSK_MASK (0x1 << I40E_PFINT_DYN_CTLN_INTENA_MSK_SHIFT)
+#define I40E_PFINT_GPIO_ENA 0x00088080
+#define I40E_PFINT_GPIO_ENA_GPIO0_ENA_SHIFT 0
+#define I40E_PFINT_GPIO_ENA_GPIO0_ENA_MASK (0x1 << I40E_PFINT_GPIO_ENA_GPIO0_ENA_SHIFT)
+#define I40E_PFINT_GPIO_ENA_GPIO1_ENA_SHIFT 1
+#define I40E_PFINT_GPIO_ENA_GPIO1_ENA_MASK (0x1 << I40E_PFINT_GPIO_ENA_GPIO1_ENA_SHIFT)
+#define I40E_PFINT_GPIO_ENA_GPIO2_ENA_SHIFT 2
+#define I40E_PFINT_GPIO_ENA_GPIO2_ENA_MASK (0x1 << I40E_PFINT_GPIO_ENA_GPIO2_ENA_SHIFT)
+#define I40E_PFINT_GPIO_ENA_GPIO3_ENA_SHIFT 3
+#define I40E_PFINT_GPIO_ENA_GPIO3_ENA_MASK (0x1 << I40E_PFINT_GPIO_ENA_GPIO3_ENA_SHIFT)
+#define I40E_PFINT_GPIO_ENA_GPIO4_ENA_SHIFT 4
+#define I40E_PFINT_GPIO_ENA_GPIO4_ENA_MASK (0x1 << I40E_PFINT_GPIO_ENA_GPIO4_ENA_SHIFT)
+#define I40E_PFINT_GPIO_ENA_GPIO5_ENA_SHIFT 5
+#define I40E_PFINT_GPIO_ENA_GPIO5_ENA_MASK (0x1 << I40E_PFINT_GPIO_ENA_GPIO5_ENA_SHIFT)
+#define I40E_PFINT_GPIO_ENA_GPIO6_ENA_SHIFT 6
+#define I40E_PFINT_GPIO_ENA_GPIO6_ENA_MASK (0x1 << I40E_PFINT_GPIO_ENA_GPIO6_ENA_SHIFT)
+#define I40E_PFINT_GPIO_ENA_GPIO7_ENA_SHIFT 7
+#define I40E_PFINT_GPIO_ENA_GPIO7_ENA_MASK (0x1 << I40E_PFINT_GPIO_ENA_GPIO7_ENA_SHIFT)
+#define I40E_PFINT_GPIO_ENA_GPIO8_ENA_SHIFT 8
+#define I40E_PFINT_GPIO_ENA_GPIO8_ENA_MASK (0x1 << I40E_PFINT_GPIO_ENA_GPIO8_ENA_SHIFT)
+#define I40E_PFINT_GPIO_ENA_GPIO9_ENA_SHIFT 9
+#define I40E_PFINT_GPIO_ENA_GPIO9_ENA_MASK (0x1 << I40E_PFINT_GPIO_ENA_GPIO9_ENA_SHIFT)
+#define I40E_PFINT_GPIO_ENA_GPIO10_ENA_SHIFT 10
+#define I40E_PFINT_GPIO_ENA_GPIO10_ENA_MASK (0x1 << I40E_PFINT_GPIO_ENA_GPIO10_ENA_SHIFT)
+#define I40E_PFINT_GPIO_ENA_GPIO11_ENA_SHIFT 11
+#define I40E_PFINT_GPIO_ENA_GPIO11_ENA_MASK (0x1 << I40E_PFINT_GPIO_ENA_GPIO11_ENA_SHIFT)
+#define I40E_PFINT_GPIO_ENA_GPIO12_ENA_SHIFT 12
+#define I40E_PFINT_GPIO_ENA_GPIO12_ENA_MASK (0x1 << I40E_PFINT_GPIO_ENA_GPIO12_ENA_SHIFT)
+#define I40E_PFINT_GPIO_ENA_GPIO13_ENA_SHIFT 13
+#define I40E_PFINT_GPIO_ENA_GPIO13_ENA_MASK (0x1 << I40E_PFINT_GPIO_ENA_GPIO13_ENA_SHIFT)
+#define I40E_PFINT_GPIO_ENA_GPIO14_ENA_SHIFT 14
+#define I40E_PFINT_GPIO_ENA_GPIO14_ENA_MASK (0x1 << I40E_PFINT_GPIO_ENA_GPIO14_ENA_SHIFT)
+#define I40E_PFINT_GPIO_ENA_GPIO15_ENA_SHIFT 15
+#define I40E_PFINT_GPIO_ENA_GPIO15_ENA_MASK (0x1 << I40E_PFINT_GPIO_ENA_GPIO15_ENA_SHIFT)
+#define I40E_PFINT_GPIO_ENA_GPIO16_ENA_SHIFT 16
+#define I40E_PFINT_GPIO_ENA_GPIO16_ENA_MASK (0x1 << I40E_PFINT_GPIO_ENA_GPIO16_ENA_SHIFT)
+#define I40E_PFINT_GPIO_ENA_GPIO17_ENA_SHIFT 17
+#define I40E_PFINT_GPIO_ENA_GPIO17_ENA_MASK (0x1 << I40E_PFINT_GPIO_ENA_GPIO17_ENA_SHIFT)
+#define I40E_PFINT_GPIO_ENA_GPIO18_ENA_SHIFT 18
+#define I40E_PFINT_GPIO_ENA_GPIO18_ENA_MASK (0x1 << I40E_PFINT_GPIO_ENA_GPIO18_ENA_SHIFT)
+#define I40E_PFINT_GPIO_ENA_GPIO19_ENA_SHIFT 19
+#define I40E_PFINT_GPIO_ENA_GPIO19_ENA_MASK (0x1 << I40E_PFINT_GPIO_ENA_GPIO19_ENA_SHIFT)
+#define I40E_PFINT_GPIO_ENA_GPIO20_ENA_SHIFT 20
+#define I40E_PFINT_GPIO_ENA_GPIO20_ENA_MASK (0x1 << I40E_PFINT_GPIO_ENA_GPIO20_ENA_SHIFT)
+#define I40E_PFINT_GPIO_ENA_GPIO21_ENA_SHIFT 21
+#define I40E_PFINT_GPIO_ENA_GPIO21_ENA_MASK (0x1 << I40E_PFINT_GPIO_ENA_GPIO21_ENA_SHIFT)
+#define I40E_PFINT_GPIO_ENA_GPIO22_ENA_SHIFT 22
+#define I40E_PFINT_GPIO_ENA_GPIO22_ENA_MASK (0x1 << I40E_PFINT_GPIO_ENA_GPIO22_ENA_SHIFT)
+#define I40E_PFINT_GPIO_ENA_GPIO23_ENA_SHIFT 23
+#define I40E_PFINT_GPIO_ENA_GPIO23_ENA_MASK (0x1 << I40E_PFINT_GPIO_ENA_GPIO23_ENA_SHIFT)
+#define I40E_PFINT_GPIO_ENA_GPIO24_ENA_SHIFT 24
+#define I40E_PFINT_GPIO_ENA_GPIO24_ENA_MASK (0x1 << I40E_PFINT_GPIO_ENA_GPIO24_ENA_SHIFT)
+#define I40E_PFINT_GPIO_ENA_GPIO25_ENA_SHIFT 25
+#define I40E_PFINT_GPIO_ENA_GPIO25_ENA_MASK (0x1 << I40E_PFINT_GPIO_ENA_GPIO25_ENA_SHIFT)
+#define I40E_PFINT_GPIO_ENA_GPIO26_ENA_SHIFT 26
+#define I40E_PFINT_GPIO_ENA_GPIO26_ENA_MASK (0x1 << I40E_PFINT_GPIO_ENA_GPIO26_ENA_SHIFT)
+#define I40E_PFINT_GPIO_ENA_GPIO27_ENA_SHIFT 27
+#define I40E_PFINT_GPIO_ENA_GPIO27_ENA_MASK (0x1 << I40E_PFINT_GPIO_ENA_GPIO27_ENA_SHIFT)
+#define I40E_PFINT_GPIO_ENA_GPIO28_ENA_SHIFT 28
+#define I40E_PFINT_GPIO_ENA_GPIO28_ENA_MASK (0x1 << I40E_PFINT_GPIO_ENA_GPIO28_ENA_SHIFT)
+#define I40E_PFINT_GPIO_ENA_GPIO29_ENA_SHIFT 29
+#define I40E_PFINT_GPIO_ENA_GPIO29_ENA_MASK (0x1 << I40E_PFINT_GPIO_ENA_GPIO29_ENA_SHIFT)
+#define I40E_PFINT_ICR0 0x00038780
+#define I40E_PFINT_ICR0_INTEVENT_SHIFT 0
+#define I40E_PFINT_ICR0_INTEVENT_MASK (0x1 << I40E_PFINT_ICR0_INTEVENT_SHIFT)
+#define I40E_PFINT_ICR0_QUEUE_0_SHIFT 1
+#define I40E_PFINT_ICR0_QUEUE_0_MASK (0x1 << I40E_PFINT_ICR0_QUEUE_0_SHIFT)
+#define I40E_PFINT_ICR0_QUEUE_1_SHIFT 2
+#define I40E_PFINT_ICR0_QUEUE_1_MASK (0x1 << I40E_PFINT_ICR0_QUEUE_1_SHIFT)
+#define I40E_PFINT_ICR0_QUEUE_2_SHIFT 3
+#define I40E_PFINT_ICR0_QUEUE_2_MASK (0x1 << I40E_PFINT_ICR0_QUEUE_2_SHIFT)
+#define I40E_PFINT_ICR0_QUEUE_3_SHIFT 4
+#define I40E_PFINT_ICR0_QUEUE_3_MASK (0x1 << I40E_PFINT_ICR0_QUEUE_3_SHIFT)
+#define I40E_PFINT_ICR0_QUEUE_4_SHIFT 5
+#define I40E_PFINT_ICR0_QUEUE_4_MASK (0x1 << I40E_PFINT_ICR0_QUEUE_4_SHIFT)
+#define I40E_PFINT_ICR0_QUEUE_5_SHIFT 6
+#define I40E_PFINT_ICR0_QUEUE_5_MASK (0x1 << I40E_PFINT_ICR0_QUEUE_5_SHIFT)
+#define I40E_PFINT_ICR0_QUEUE_6_SHIFT 7
+#define I40E_PFINT_ICR0_QUEUE_6_MASK (0x1 << I40E_PFINT_ICR0_QUEUE_6_SHIFT)
+#define I40E_PFINT_ICR0_QUEUE_7_SHIFT 8
+#define I40E_PFINT_ICR0_QUEUE_7_MASK (0x1 << I40E_PFINT_ICR0_QUEUE_7_SHIFT)
+#define I40E_PFINT_ICR0_ECC_ERR_SHIFT 16
+#define I40E_PFINT_ICR0_ECC_ERR_MASK (0x1 << I40E_PFINT_ICR0_ECC_ERR_SHIFT)
+#define I40E_PFINT_ICR0_MAL_DETECT_SHIFT 19
+#define I40E_PFINT_ICR0_MAL_DETECT_MASK (0x1 << I40E_PFINT_ICR0_MAL_DETECT_SHIFT)
+#define I40E_PFINT_ICR0_GRST_SHIFT 20
+#define I40E_PFINT_ICR0_GRST_MASK (0x1 << I40E_PFINT_ICR0_GRST_SHIFT)
+#define I40E_PFINT_ICR0_PCI_EXCEPTION_SHIFT 21
+#define I40E_PFINT_ICR0_PCI_EXCEPTION_MASK (0x1 << I40E_PFINT_ICR0_PCI_EXCEPTION_SHIFT)
+#define I40E_PFINT_ICR0_GPIO_SHIFT 22
+#define I40E_PFINT_ICR0_GPIO_MASK (0x1 << I40E_PFINT_ICR0_GPIO_SHIFT)
+#define I40E_PFINT_ICR0_TIMESYNC_SHIFT 23
+#define I40E_PFINT_ICR0_TIMESYNC_MASK (0x1 << I40E_PFINT_ICR0_TIMESYNC_SHIFT)
+#define I40E_PFINT_ICR0_STORM_DETECT_SHIFT 24
+#define I40E_PFINT_ICR0_STORM_DETECT_MASK (0x1 << I40E_PFINT_ICR0_STORM_DETECT_SHIFT)
+#define I40E_PFINT_ICR0_LINK_STAT_CHANGE_SHIFT 25
+#define I40E_PFINT_ICR0_LINK_STAT_CHANGE_MASK (0x1 << I40E_PFINT_ICR0_LINK_STAT_CHANGE_SHIFT)
+#define I40E_PFINT_ICR0_HMC_ERR_SHIFT 26
+#define I40E_PFINT_ICR0_HMC_ERR_MASK (0x1 << I40E_PFINT_ICR0_HMC_ERR_SHIFT)
+#define I40E_PFINT_ICR0_PE_CRITERR_SHIFT 28
+#define I40E_PFINT_ICR0_PE_CRITERR_MASK (0x1 << I40E_PFINT_ICR0_PE_CRITERR_SHIFT)
+#define I40E_PFINT_ICR0_VFLR_SHIFT 29
+#define I40E_PFINT_ICR0_VFLR_MASK (0x1 << I40E_PFINT_ICR0_VFLR_SHIFT)
+#define I40E_PFINT_ICR0_ADMINQ_SHIFT 30
+#define I40E_PFINT_ICR0_ADMINQ_MASK (0x1 << I40E_PFINT_ICR0_ADMINQ_SHIFT)
+#define I40E_PFINT_ICR0_SWINT_SHIFT 31
+#define I40E_PFINT_ICR0_SWINT_MASK (0x1 << I40E_PFINT_ICR0_SWINT_SHIFT)
+#define I40E_PFINT_ICR0_ENA 0x00038800
+#define I40E_PFINT_ICR0_ENA_ECC_ERR_SHIFT 16
+#define I40E_PFINT_ICR0_ENA_ECC_ERR_MASK (0x1 << I40E_PFINT_ICR0_ENA_ECC_ERR_SHIFT)
+#define I40E_PFINT_ICR0_ENA_MAL_DETECT_SHIFT 19
+#define I40E_PFINT_ICR0_ENA_MAL_DETECT_MASK (0x1 << I40E_PFINT_ICR0_ENA_MAL_DETECT_SHIFT)
+#define I40E_PFINT_ICR0_ENA_GRST_SHIFT 20
+#define I40E_PFINT_ICR0_ENA_GRST_MASK (0x1 << I40E_PFINT_ICR0_ENA_GRST_SHIFT)
+#define I40E_PFINT_ICR0_ENA_PCI_EXCEPTION_SHIFT 21
+#define I40E_PFINT_ICR0_ENA_PCI_EXCEPTION_MASK (0x1 << I40E_PFINT_ICR0_ENA_PCI_EXCEPTION_SHIFT)
+#define I40E_PFINT_ICR0_ENA_GPIO_SHIFT 22
+#define I40E_PFINT_ICR0_ENA_GPIO_MASK (0x1 << I40E_PFINT_ICR0_ENA_GPIO_SHIFT)
+#define I40E_PFINT_ICR0_ENA_TIMESYNC_SHIFT 23
+#define I40E_PFINT_ICR0_ENA_TIMESYNC_MASK (0x1 << I40E_PFINT_ICR0_ENA_TIMESYNC_SHIFT)
+#define I40E_PFINT_ICR0_ENA_STORM_DETECT_SHIFT 24
+#define I40E_PFINT_ICR0_ENA_STORM_DETECT_MASK (0x1 << I40E_PFINT_ICR0_ENA_STORM_DETECT_SHIFT)
+#define I40E_PFINT_ICR0_ENA_LINK_STAT_CHANGE_SHIFT 25
+#define I40E_PFINT_ICR0_ENA_LINK_STAT_CHANGE_MASK (0x1 << I40E_PFINT_ICR0_ENA_LINK_STAT_CHANGE_SHIFT)
+#define I40E_PFINT_ICR0_ENA_HMC_ERR_SHIFT 26
+#define I40E_PFINT_ICR0_ENA_HMC_ERR_MASK (0x1 << I40E_PFINT_ICR0_ENA_HMC_ERR_SHIFT)
+#define I40E_PFINT_ICR0_ENA_PE_CRITERR_SHIFT 28
+#define I40E_PFINT_ICR0_ENA_PE_CRITERR_MASK (0x1 << I40E_PFINT_ICR0_ENA_PE_CRITERR_SHIFT)
+#define I40E_PFINT_ICR0_ENA_VFLR_SHIFT 29
+#define I40E_PFINT_ICR0_ENA_VFLR_MASK (0x1 << I40E_PFINT_ICR0_ENA_VFLR_SHIFT)
+#define I40E_PFINT_ICR0_ENA_ADMINQ_SHIFT 30
+#define I40E_PFINT_ICR0_ENA_ADMINQ_MASK (0x1 << I40E_PFINT_ICR0_ENA_ADMINQ_SHIFT)
+#define I40E_PFINT_ICR0_ENA_RSVD_SHIFT 31
+#define I40E_PFINT_ICR0_ENA_RSVD_MASK (0x1 << I40E_PFINT_ICR0_ENA_RSVD_SHIFT)
+#define I40E_PFINT_ITR0(_i) (0x00038000 + ((_i) * 128)) /* _i=0...2 */
+#define I40E_PFINT_ITR0_MAX_INDEX 2
+#define I40E_PFINT_ITR0_INTERVAL_SHIFT 0
+#define I40E_PFINT_ITR0_INTERVAL_MASK (0xFFF << I40E_PFINT_ITR0_INTERVAL_SHIFT)
+#define I40E_PFINT_ITRN(_i, _INTPF) (0x00030000 + ((_i) * 2048 + (_INTPF) * 4))
+#define I40E_PFINT_ITRN_MAX_INDEX 2
+#define I40E_PFINT_ITRN_INTERVAL_SHIFT 0
+#define I40E_PFINT_ITRN_INTERVAL_MASK (0xFFF << I40E_PFINT_ITRN_INTERVAL_SHIFT)
+#define I40E_PFINT_LNKLST0 0x00038500
+#define I40E_PFINT_LNKLST0_FIRSTQ_INDX_SHIFT 0
+#define I40E_PFINT_LNKLST0_FIRSTQ_INDX_MASK (0x7FF << I40E_PFINT_LNKLST0_FIRSTQ_INDX_SHIFT)
+#define I40E_PFINT_LNKLST0_FIRSTQ_TYPE_SHIFT 11
+#define I40E_PFINT_LNKLST0_FIRSTQ_TYPE_MASK (0x3 << I40E_PFINT_LNKLST0_FIRSTQ_TYPE_SHIFT)
+#define I40E_PFINT_LNKLSTN(_INTPF) (0x00035000 + ((_INTPF) * 4)) /* _i=0...511 */
+#define I40E_PFINT_LNKLSTN_MAX_INDEX 511
+#define I40E_PFINT_LNKLSTN_FIRSTQ_INDX_SHIFT 0
+#define I40E_PFINT_LNKLSTN_FIRSTQ_INDX_MASK (0x7FF << I40E_PFINT_LNKLSTN_FIRSTQ_INDX_SHIFT)
+#define I40E_PFINT_LNKLSTN_FIRSTQ_TYPE_SHIFT 11
+#define I40E_PFINT_LNKLSTN_FIRSTQ_TYPE_MASK (0x3 << I40E_PFINT_LNKLSTN_FIRSTQ_TYPE_SHIFT)
+#define I40E_PFINT_RATE0 0x00038580
+#define I40E_PFINT_RATE0_INTERVAL_SHIFT 0
+#define I40E_PFINT_RATE0_INTERVAL_MASK (0x3F << I40E_PFINT_RATE0_INTERVAL_SHIFT)
+#define I40E_PFINT_RATE0_INTRL_ENA_SHIFT 6
+#define I40E_PFINT_RATE0_INTRL_ENA_MASK (0x1 << I40E_PFINT_RATE0_INTRL_ENA_SHIFT)
+#define I40E_PFINT_RATEN(_INTPF) (0x00035800 + ((_INTPF) * 4)) /* _i=0...511 */
+#define I40E_PFINT_RATEN_MAX_INDEX 511
+#define I40E_PFINT_RATEN_INTERVAL_SHIFT 0
+#define I40E_PFINT_RATEN_INTERVAL_MASK (0x3F << I40E_PFINT_RATEN_INTERVAL_SHIFT)
+#define I40E_PFINT_RATEN_INTRL_ENA_SHIFT 6
+#define I40E_PFINT_RATEN_INTRL_ENA_MASK (0x1 << I40E_PFINT_RATEN_INTRL_ENA_SHIFT)
+#define I40E_PFINT_STAT_CTL0 0x00038400
+#define I40E_PFINT_STAT_CTL0_OTHER_ITR_INDX_SHIFT 2
+#define I40E_PFINT_STAT_CTL0_OTHER_ITR_INDX_MASK (0x3 << I40E_PFINT_STAT_CTL0_OTHER_ITR_INDX_SHIFT)
+#define I40E_QINT_RQCTL(_Q) (0x0003A000 + ((_Q) * 4)) /* _i=0...1535 */
+#define I40E_QINT_RQCTL_MAX_INDEX 1535
+#define I40E_QINT_RQCTL_MSIX_INDX_SHIFT 0
+#define I40E_QINT_RQCTL_MSIX_INDX_MASK (0xFF << I40E_QINT_RQCTL_MSIX_INDX_SHIFT)
+#define I40E_QINT_RQCTL_ITR_INDX_SHIFT 11
+#define I40E_QINT_RQCTL_ITR_INDX_MASK (0x3 << I40E_QINT_RQCTL_ITR_INDX_SHIFT)
+#define I40E_QINT_RQCTL_MSIX0_INDX_SHIFT 13
+#define I40E_QINT_RQCTL_MSIX0_INDX_MASK (0x7 << I40E_QINT_RQCTL_MSIX0_INDX_SHIFT)
+#define I40E_QINT_RQCTL_NEXTQ_INDX_SHIFT 16
+#define I40E_QINT_RQCTL_NEXTQ_INDX_MASK (0x7FF << I40E_QINT_RQCTL_NEXTQ_INDX_SHIFT)
+#define I40E_QINT_RQCTL_NEXTQ_TYPE_SHIFT 27
+#define I40E_QINT_RQCTL_NEXTQ_TYPE_MASK (0x3 << I40E_QINT_RQCTL_NEXTQ_TYPE_SHIFT)
+#define I40E_QINT_RQCTL_CAUSE_ENA_SHIFT 30
+#define I40E_QINT_RQCTL_CAUSE_ENA_MASK (0x1 << I40E_QINT_RQCTL_CAUSE_ENA_SHIFT)
+#define I40E_QINT_RQCTL_INTEVENT_SHIFT 31
+#define I40E_QINT_RQCTL_INTEVENT_MASK (0x1 << I40E_QINT_RQCTL_INTEVENT_SHIFT)
+#define I40E_QINT_TQCTL(_Q) (0x0003C000 + ((_Q) * 4)) /* _i=0...1535 */
+#define I40E_QINT_TQCTL_MAX_INDEX 1535
+#define I40E_QINT_TQCTL_MSIX_INDX_SHIFT 0
+#define I40E_QINT_TQCTL_MSIX_INDX_MASK (0xFF << I40E_QINT_TQCTL_MSIX_INDX_SHIFT)
+#define I40E_QINT_TQCTL_ITR_INDX_SHIFT 11
+#define I40E_QINT_TQCTL_ITR_INDX_MASK (0x3 << I40E_QINT_TQCTL_ITR_INDX_SHIFT)
+#define I40E_QINT_TQCTL_MSIX0_INDX_SHIFT 13
+#define I40E_QINT_TQCTL_MSIX0_INDX_MASK (0x7 << I40E_QINT_TQCTL_MSIX0_INDX_SHIFT)
+#define I40E_QINT_TQCTL_NEXTQ_INDX_SHIFT 16
+#define I40E_QINT_TQCTL_NEXTQ_INDX_MASK (0x7FF << I40E_QINT_TQCTL_NEXTQ_INDX_SHIFT)
+#define I40E_QINT_TQCTL_NEXTQ_TYPE_SHIFT 27
+#define I40E_QINT_TQCTL_NEXTQ_TYPE_MASK (0x3 << I40E_QINT_TQCTL_NEXTQ_TYPE_SHIFT)
+#define I40E_QINT_TQCTL_CAUSE_ENA_SHIFT 30
+#define I40E_QINT_TQCTL_CAUSE_ENA_MASK (0x1 << I40E_QINT_TQCTL_CAUSE_ENA_SHIFT)
+#define I40E_QINT_TQCTL_INTEVENT_SHIFT 31
+#define I40E_QINT_TQCTL_INTEVENT_MASK (0x1 << I40E_QINT_TQCTL_INTEVENT_SHIFT)
+#define I40E_VFINT_DYN_CTL0(_VF) (0x0002A400 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VFINT_DYN_CTL0_MAX_INDEX 127
+#define I40E_VFINT_DYN_CTL0_INTENA_SHIFT 0
+#define I40E_VFINT_DYN_CTL0_INTENA_MASK (0x1 << I40E_VFINT_DYN_CTL0_INTENA_SHIFT)
+#define I40E_VFINT_DYN_CTL0_CLEARPBA_SHIFT 1
+#define I40E_VFINT_DYN_CTL0_CLEARPBA_MASK (0x1 << I40E_VFINT_DYN_CTL0_CLEARPBA_SHIFT)
+#define I40E_VFINT_DYN_CTL0_SWINT_TRIG_SHIFT 2
+#define I40E_VFINT_DYN_CTL0_SWINT_TRIG_MASK (0x1 << I40E_VFINT_DYN_CTL0_SWINT_TRIG_SHIFT)
+#define I40E_VFINT_DYN_CTL0_ITR_INDX_SHIFT 3
+#define I40E_VFINT_DYN_CTL0_ITR_INDX_MASK (0x3 << I40E_VFINT_DYN_CTL0_ITR_INDX_SHIFT)
+#define I40E_VFINT_DYN_CTL0_INTERVAL_SHIFT 5
+#define I40E_VFINT_DYN_CTL0_INTERVAL_MASK (0xFFF << I40E_VFINT_DYN_CTL0_INTERVAL_SHIFT)
+#define I40E_VFINT_DYN_CTL0_SW_ITR_INDX_ENA_SHIFT 24
+#define I40E_VFINT_DYN_CTL0_SW_ITR_INDX_ENA_MASK (0x1 << I40E_VFINT_DYN_CTL0_SW_ITR_INDX_ENA_SHIFT)
+#define I40E_VFINT_DYN_CTL0_SW_ITR_INDX_SHIFT 25
+#define I40E_VFINT_DYN_CTL0_SW_ITR_INDX_MASK (0x3 << I40E_VFINT_DYN_CTL0_SW_ITR_INDX_SHIFT)
+#define I40E_VFINT_DYN_CTL0_INTENA_MSK_SHIFT 31
+#define I40E_VFINT_DYN_CTL0_INTENA_MSK_MASK (0x1 << I40E_VFINT_DYN_CTL0_INTENA_MSK_SHIFT)
+#define I40E_VFINT_DYN_CTLN(_INTVF) (0x00024800 + ((_INTVF) * 4)) /* _i=0...511 */
+#define I40E_VFINT_DYN_CTLN_MAX_INDEX 511
+#define I40E_VFINT_DYN_CTLN_INTENA_SHIFT 0
+#define I40E_VFINT_DYN_CTLN_INTENA_MASK (0x1 << I40E_VFINT_DYN_CTLN_INTENA_SHIFT)
+#define I40E_VFINT_DYN_CTLN_CLEARPBA_SHIFT 1
+#define I40E_VFINT_DYN_CTLN_CLEARPBA_MASK (0x1 << I40E_VFINT_DYN_CTLN_CLEARPBA_SHIFT)
+#define I40E_VFINT_DYN_CTLN_SWINT_TRIG_SHIFT 2
+#define I40E_VFINT_DYN_CTLN_SWINT_TRIG_MASK (0x1 << I40E_VFINT_DYN_CTLN_SWINT_TRIG_SHIFT)
+#define I40E_VFINT_DYN_CTLN_ITR_INDX_SHIFT 3
+#define I40E_VFINT_DYN_CTLN_ITR_INDX_MASK (0x3 << I40E_VFINT_DYN_CTLN_ITR_INDX_SHIFT)
+#define I40E_VFINT_DYN_CTLN_INTERVAL_SHIFT 5
+#define I40E_VFINT_DYN_CTLN_INTERVAL_MASK (0xFFF << I40E_VFINT_DYN_CTLN_INTERVAL_SHIFT)
+#define I40E_VFINT_DYN_CTLN_SW_ITR_INDX_ENA_SHIFT 24
+#define I40E_VFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK (0x1 << I40E_VFINT_DYN_CTLN_SW_ITR_INDX_ENA_SHIFT)
+#define I40E_VFINT_DYN_CTLN_SW_ITR_INDX_SHIFT 25
+#define I40E_VFINT_DYN_CTLN_SW_ITR_INDX_MASK (0x3 << I40E_VFINT_DYN_CTLN_SW_ITR_INDX_SHIFT)
+#define I40E_VFINT_DYN_CTLN_INTENA_MSK_SHIFT 31
+#define I40E_VFINT_DYN_CTLN_INTENA_MSK_MASK (0x1 << I40E_VFINT_DYN_CTLN_INTENA_MSK_SHIFT)
+#define I40E_VFINT_ICR0(_VF) (0x0002BC00 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VFINT_ICR0_MAX_INDEX 127
+#define I40E_VFINT_ICR0_INTEVENT_SHIFT 0
+#define I40E_VFINT_ICR0_INTEVENT_MASK (0x1 << I40E_VFINT_ICR0_INTEVENT_SHIFT)
+#define I40E_VFINT_ICR0_QUEUE_0_SHIFT 1
+#define I40E_VFINT_ICR0_QUEUE_0_MASK (0x1 << I40E_VFINT_ICR0_QUEUE_0_SHIFT)
+#define I40E_VFINT_ICR0_QUEUE_1_SHIFT 2
+#define I40E_VFINT_ICR0_QUEUE_1_MASK (0x1 << I40E_VFINT_ICR0_QUEUE_1_SHIFT)
+#define I40E_VFINT_ICR0_QUEUE_2_SHIFT 3
+#define I40E_VFINT_ICR0_QUEUE_2_MASK (0x1 << I40E_VFINT_ICR0_QUEUE_2_SHIFT)
+#define I40E_VFINT_ICR0_QUEUE_3_SHIFT 4
+#define I40E_VFINT_ICR0_QUEUE_3_MASK (0x1 << I40E_VFINT_ICR0_QUEUE_3_SHIFT)
+#define I40E_VFINT_ICR0_LINK_STAT_CHANGE_SHIFT 25
+#define I40E_VFINT_ICR0_LINK_STAT_CHANGE_MASK (0x1 << I40E_VFINT_ICR0_LINK_STAT_CHANGE_SHIFT)
+#define I40E_VFINT_ICR0_ADMINQ_SHIFT 30
+#define I40E_VFINT_ICR0_ADMINQ_MASK (0x1 << I40E_VFINT_ICR0_ADMINQ_SHIFT)
+#define I40E_VFINT_ICR0_SWINT_SHIFT 31
+#define I40E_VFINT_ICR0_SWINT_MASK (0x1 << I40E_VFINT_ICR0_SWINT_SHIFT)
+#define I40E_VFINT_ICR0_ENA(_VF) (0x0002C000 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VFINT_ICR0_ENA_MAX_INDEX 127
+#define I40E_VFINT_ICR0_ENA_LINK_STAT_CHANGE_SHIFT 25
+#define I40E_VFINT_ICR0_ENA_LINK_STAT_CHANGE_MASK (0x1 << I40E_VFINT_ICR0_ENA_LINK_STAT_CHANGE_SHIFT)
+#define I40E_VFINT_ICR0_ENA_ADMINQ_SHIFT 30
+#define I40E_VFINT_ICR0_ENA_ADMINQ_MASK (0x1 << I40E_VFINT_ICR0_ENA_ADMINQ_SHIFT)
+#define I40E_VFINT_ICR0_ENA_RSVD_SHIFT 31
+#define I40E_VFINT_ICR0_ENA_RSVD_MASK (0x1 << I40E_VFINT_ICR0_ENA_RSVD_SHIFT)
+#define I40E_VFINT_ITR0(_i, _VF) (0x00028000 + ((_i) * 1024 + (_VF) * 4)) /* _i=0...2, _VF=0...127 */
+#define I40E_VFINT_ITR0_MAX_INDEX 2
+#define I40E_VFINT_ITR0_INTERVAL_SHIFT 0
+#define I40E_VFINT_ITR0_INTERVAL_MASK (0xFFF << I40E_VFINT_ITR0_INTERVAL_SHIFT)
+#define I40E_VFINT_ITRN(_i, _INTVF) (0x00020000 + ((_i) * 2048 + (_INTVF) * 4))
+#define I40E_VFINT_ITRN_MAX_INDEX 2
+#define I40E_VFINT_ITRN_INTERVAL_SHIFT 0
+#define I40E_VFINT_ITRN_INTERVAL_MASK (0xFFF << I40E_VFINT_ITRN_INTERVAL_SHIFT)
+#define I40E_VFINT_STAT_CTL0(_VF) (0x0002A000 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VFINT_STAT_CTL0_MAX_INDEX 127
+#define I40E_VFINT_STAT_CTL0_OTHER_ITR_INDX_SHIFT 2
+#define I40E_VFINT_STAT_CTL0_OTHER_ITR_INDX_MASK (0x3 << I40E_VFINT_STAT_CTL0_OTHER_ITR_INDX_SHIFT)
+#define I40E_VPINT_AEQCTL(_VF) (0x0002B800 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VPINT_AEQCTL_MAX_INDEX 127
+#define I40E_VPINT_AEQCTL_MSIX_INDX_SHIFT 0
+#define I40E_VPINT_AEQCTL_MSIX_INDX_MASK (0xFF << I40E_VPINT_AEQCTL_MSIX_INDX_SHIFT)
+#define I40E_VPINT_AEQCTL_ITR_INDX_SHIFT 11
+#define I40E_VPINT_AEQCTL_ITR_INDX_MASK (0x3 << I40E_VPINT_AEQCTL_ITR_INDX_SHIFT)
+#define I40E_VPINT_AEQCTL_MSIX0_INDX_SHIFT 13
+#define I40E_VPINT_AEQCTL_MSIX0_INDX_MASK (0x7 << I40E_VPINT_AEQCTL_MSIX0_INDX_SHIFT)
+#define I40E_VPINT_AEQCTL_CAUSE_ENA_SHIFT 30
+#define I40E_VPINT_AEQCTL_CAUSE_ENA_MASK (0x1 << I40E_VPINT_AEQCTL_CAUSE_ENA_SHIFT)
+#define I40E_VPINT_AEQCTL_INTEVENT_SHIFT 31
+#define I40E_VPINT_AEQCTL_INTEVENT_MASK (0x1 << I40E_VPINT_AEQCTL_INTEVENT_SHIFT)
+#define I40E_VPINT_CEQCTL(_INTVF) (0x00026800 + ((_INTVF) * 4)) /* _i=0...511 */
+#define I40E_VPINT_CEQCTL_MAX_INDEX 511
+#define I40E_VPINT_CEQCTL_MSIX_INDX_SHIFT 0
+#define I40E_VPINT_CEQCTL_MSIX_INDX_MASK (0xFF << I40E_VPINT_CEQCTL_MSIX_INDX_SHIFT)
+#define I40E_VPINT_CEQCTL_ITR_INDX_SHIFT 11
+#define I40E_VPINT_CEQCTL_ITR_INDX_MASK (0x3 << I40E_VPINT_CEQCTL_ITR_INDX_SHIFT)
+#define I40E_VPINT_CEQCTL_MSIX0_INDX_SHIFT 13
+#define I40E_VPINT_CEQCTL_MSIX0_INDX_MASK (0x7 << I40E_VPINT_CEQCTL_MSIX0_INDX_SHIFT)
+#define I40E_VPINT_CEQCTL_NEXTQ_INDX_SHIFT 16
+#define I40E_VPINT_CEQCTL_NEXTQ_INDX_MASK (0x7FF << I40E_VPINT_CEQCTL_NEXTQ_INDX_SHIFT)
+#define I40E_VPINT_CEQCTL_NEXTQ_TYPE_SHIFT 27
+#define I40E_VPINT_CEQCTL_NEXTQ_TYPE_MASK (0x3 << I40E_VPINT_CEQCTL_NEXTQ_TYPE_SHIFT)
+#define I40E_VPINT_CEQCTL_CAUSE_ENA_SHIFT 30
+#define I40E_VPINT_CEQCTL_CAUSE_ENA_MASK (0x1 << I40E_VPINT_CEQCTL_CAUSE_ENA_SHIFT)
+#define I40E_VPINT_CEQCTL_INTEVENT_SHIFT 31
+#define I40E_VPINT_CEQCTL_INTEVENT_MASK (0x1 << I40E_VPINT_CEQCTL_INTEVENT_SHIFT)
+#define I40E_VPINT_LNKLST0(_VF) (0x0002A800 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VPINT_LNKLST0_MAX_INDEX 127
+#define I40E_VPINT_LNKLST0_FIRSTQ_INDX_SHIFT 0
+#define I40E_VPINT_LNKLST0_FIRSTQ_INDX_MASK (0x7FF << I40E_VPINT_LNKLST0_FIRSTQ_INDX_SHIFT)
+#define I40E_VPINT_LNKLST0_FIRSTQ_TYPE_SHIFT 11
+#define I40E_VPINT_LNKLST0_FIRSTQ_TYPE_MASK (0x3 << I40E_VPINT_LNKLST0_FIRSTQ_TYPE_SHIFT)
+#define I40E_VPINT_LNKLSTN(_INTVF) (0x00025000 + ((_INTVF) * 4)) /* _i=0...511 */
+#define I40E_VPINT_LNKLSTN_MAX_INDEX 511
+#define I40E_VPINT_LNKLSTN_FIRSTQ_INDX_SHIFT 0
+#define I40E_VPINT_LNKLSTN_FIRSTQ_INDX_MASK (0x7FF << I40E_VPINT_LNKLSTN_FIRSTQ_INDX_SHIFT)
+#define I40E_VPINT_LNKLSTN_FIRSTQ_TYPE_SHIFT 11
+#define I40E_VPINT_LNKLSTN_FIRSTQ_TYPE_MASK (0x3 << I40E_VPINT_LNKLSTN_FIRSTQ_TYPE_SHIFT)
+#define I40E_VPINT_RATE0(_VF) (0x0002AC00 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VPINT_RATE0_MAX_INDEX 127
+#define I40E_VPINT_RATE0_INTERVAL_SHIFT 0
+#define I40E_VPINT_RATE0_INTERVAL_MASK (0x3F << I40E_VPINT_RATE0_INTERVAL_SHIFT)
+#define I40E_VPINT_RATE0_INTRL_ENA_SHIFT 6
+#define I40E_VPINT_RATE0_INTRL_ENA_MASK (0x1 << I40E_VPINT_RATE0_INTRL_ENA_SHIFT)
+#define I40E_VPINT_RATEN(_INTVF) (0x00025800 + ((_INTVF) * 4)) /* _i=0...511 */
+#define I40E_VPINT_RATEN_MAX_INDEX 511
+#define I40E_VPINT_RATEN_INTERVAL_SHIFT 0
+#define I40E_VPINT_RATEN_INTERVAL_MASK (0x3F << I40E_VPINT_RATEN_INTERVAL_SHIFT)
+#define I40E_VPINT_RATEN_INTRL_ENA_SHIFT 6
+#define I40E_VPINT_RATEN_INTRL_ENA_MASK (0x1 << I40E_VPINT_RATEN_INTRL_ENA_SHIFT)
+#define I40E_GL_RDPU_CNTRL 0x00051060
+#define I40E_GL_RDPU_CNTRL_RX_PAD_EN_SHIFT 0
+#define I40E_GL_RDPU_CNTRL_RX_PAD_EN_MASK (0x1 << I40E_GL_RDPU_CNTRL_RX_PAD_EN_SHIFT)
+#define I40E_GL_RDPU_CNTRL_ECO_SHIFT 1
+#define I40E_GL_RDPU_CNTRL_ECO_MASK (0x7FFFFFFF << I40E_GL_RDPU_CNTRL_ECO_SHIFT)
+#define I40E_GLLAN_RCTL_0 0x0012A500
+#define I40E_GLLAN_RCTL_0_PXE_MODE_SHIFT 0
+#define I40E_GLLAN_RCTL_0_PXE_MODE_MASK (0x1 << I40E_GLLAN_RCTL_0_PXE_MODE_SHIFT)
+#define I40E_GLLAN_TSOMSK_F 0x000442D8
+#define I40E_GLLAN_TSOMSK_F_TCPMSKF_SHIFT 0
+#define I40E_GLLAN_TSOMSK_F_TCPMSKF_MASK (0xFFF << I40E_GLLAN_TSOMSK_F_TCPMSKF_SHIFT)
+#define I40E_GLLAN_TSOMSK_L 0x000442E0
+#define I40E_GLLAN_TSOMSK_L_TCPMSKL_SHIFT 0
+#define I40E_GLLAN_TSOMSK_L_TCPMSKL_MASK (0xFFF << I40E_GLLAN_TSOMSK_L_TCPMSKL_SHIFT)
+#define I40E_GLLAN_TSOMSK_M 0x000442DC
+#define I40E_GLLAN_TSOMSK_M_TCPMSKM_SHIFT 0
+#define I40E_GLLAN_TSOMSK_M_TCPMSKM_MASK (0xFFF << I40E_GLLAN_TSOMSK_M_TCPMSKM_SHIFT)
+#define I40E_PFLAN_QALLOC 0x001C0400
+#define I40E_PFLAN_QALLOC_FIRSTQ_SHIFT 0
+#define I40E_PFLAN_QALLOC_FIRSTQ_MASK (0x7FF << I40E_PFLAN_QALLOC_FIRSTQ_SHIFT)
+#define I40E_PFLAN_QALLOC_LASTQ_SHIFT 16
+#define I40E_PFLAN_QALLOC_LASTQ_MASK (0x7FF << I40E_PFLAN_QALLOC_LASTQ_SHIFT)
+#define I40E_PFLAN_QALLOC_VALID_SHIFT 31
+#define I40E_PFLAN_QALLOC_VALID_MASK (0x1 << I40E_PFLAN_QALLOC_VALID_SHIFT)
+#define I40E_QRX_ENA(_Q) (0x00120000 + ((_Q) * 4)) /* _i=0...1535 */
+#define I40E_QRX_ENA_MAX_INDEX 1535
+#define I40E_QRX_ENA_QENA_REQ_SHIFT 0
+#define I40E_QRX_ENA_QENA_REQ_MASK (0x1 << I40E_QRX_ENA_QENA_REQ_SHIFT)
+#define I40E_QRX_ENA_FAST_QDIS_SHIFT 1
+#define I40E_QRX_ENA_FAST_QDIS_MASK (0x1 << I40E_QRX_ENA_FAST_QDIS_SHIFT)
+#define I40E_QRX_ENA_QENA_STAT_SHIFT 2
+#define I40E_QRX_ENA_QENA_STAT_MASK (0x1 << I40E_QRX_ENA_QENA_STAT_SHIFT)
+#define I40E_QRX_TAIL(_Q) (0x00128000 + ((_Q) * 4)) /* _i=0...1535 */
+#define I40E_QRX_TAIL_MAX_INDEX 1535
+#define I40E_QRX_TAIL_TAIL_SHIFT 0
+#define I40E_QRX_TAIL_TAIL_MASK (0x1FFF << I40E_QRX_TAIL_TAIL_SHIFT)
+#define I40E_QTX_CTL(_Q) (0x00104000 + ((_Q) * 4)) /* _i=0...1535 */
+#define I40E_QTX_CTL_MAX_INDEX 1535
+#define I40E_QTX_CTL_PFVF_Q_SHIFT 0
+#define I40E_QTX_CTL_PFVF_Q_MASK (0x3 << I40E_QTX_CTL_PFVF_Q_SHIFT)
+#define I40E_QTX_CTL_PF_INDX_SHIFT 2
+#define I40E_QTX_CTL_PF_INDX_MASK (0xF << I40E_QTX_CTL_PF_INDX_SHIFT)
+#define I40E_QTX_CTL_VFVM_INDX_SHIFT 7
+#define I40E_QTX_CTL_VFVM_INDX_MASK (0x1FF << I40E_QTX_CTL_VFVM_INDX_SHIFT)
+#define I40E_QTX_ENA(_Q) (0x00100000 + ((_Q) * 4)) /* _i=0...1535 */
+#define I40E_QTX_ENA_MAX_INDEX 1535
+#define I40E_QTX_ENA_QENA_REQ_SHIFT 0
+#define I40E_QTX_ENA_QENA_REQ_MASK (0x1 << I40E_QTX_ENA_QENA_REQ_SHIFT)
+#define I40E_QTX_ENA_FAST_QDIS_SHIFT 1
+#define I40E_QTX_ENA_FAST_QDIS_MASK (0x1 << I40E_QTX_ENA_FAST_QDIS_SHIFT)
+#define I40E_QTX_ENA_QENA_STAT_SHIFT 2
+#define I40E_QTX_ENA_QENA_STAT_MASK (0x1 << I40E_QTX_ENA_QENA_STAT_SHIFT)
+#define I40E_QTX_HEAD(_Q) (0x000E4000 + ((_Q) * 4)) /* _i=0...1535 */
+#define I40E_QTX_HEAD_MAX_INDEX 1535
+#define I40E_QTX_HEAD_HEAD_SHIFT 0
+#define I40E_QTX_HEAD_HEAD_MASK (0x1FFF << I40E_QTX_HEAD_HEAD_SHIFT)
+#define I40E_QTX_HEAD_RS_PENDING_SHIFT 16
+#define I40E_QTX_HEAD_RS_PENDING_MASK (0x1 << I40E_QTX_HEAD_RS_PENDING_SHIFT)
+#define I40E_QTX_TAIL(_Q) (0x00108000 + ((_Q) * 4)) /* _i=0...1535 */
+#define I40E_QTX_TAIL_MAX_INDEX 1535
+#define I40E_QTX_TAIL_TAIL_SHIFT 0
+#define I40E_QTX_TAIL_TAIL_MASK (0x1FFF << I40E_QTX_TAIL_TAIL_SHIFT)
+#define I40E_VPLAN_MAPENA(_VF) (0x00074000 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VPLAN_MAPENA_MAX_INDEX 127
+#define I40E_VPLAN_MAPENA_TXRX_ENA_SHIFT 0
+#define I40E_VPLAN_MAPENA_TXRX_ENA_MASK (0x1 << I40E_VPLAN_MAPENA_TXRX_ENA_SHIFT)
+#define I40E_VPLAN_QTABLE(_i, _VF) (0x00070000 + ((_i) * 1024 + (_VF) * 4)) /* _i=0...15, _VF=0...127 */
+#define I40E_VPLAN_QTABLE_MAX_INDEX 15
+#define I40E_VPLAN_QTABLE_QINDEX_SHIFT 0
+#define I40E_VPLAN_QTABLE_QINDEX_MASK (0x7FF << I40E_VPLAN_QTABLE_QINDEX_SHIFT)
+#define I40E_VSILAN_QBASE(_VSI) (0x0020C800 + ((_VSI) * 4)) /* _i=0...383 */
+#define I40E_VSILAN_QBASE_MAX_INDEX 383
+#define I40E_VSILAN_QBASE_VSIBASE_SHIFT 0
+#define I40E_VSILAN_QBASE_VSIBASE_MASK (0x7FF << I40E_VSILAN_QBASE_VSIBASE_SHIFT)
+#define I40E_VSILAN_QBASE_VSIQTABLE_ENA_SHIFT 11
+#define I40E_VSILAN_QBASE_VSIQTABLE_ENA_MASK (0x1 << I40E_VSILAN_QBASE_VSIQTABLE_ENA_SHIFT)
+#define I40E_VSILAN_QTABLE(_i, _VSI) (0x00200000 + ((_i) * 2048 + (_VSI) * 4))
+#define I40E_VSILAN_QTABLE_MAX_INDEX 15
+#define I40E_VSILAN_QTABLE_QINDEX_0_SHIFT 0
+#define I40E_VSILAN_QTABLE_QINDEX_0_MASK (0x7FF << I40E_VSILAN_QTABLE_QINDEX_0_SHIFT)
+#define I40E_VSILAN_QTABLE_QINDEX_1_SHIFT 16
+#define I40E_VSILAN_QTABLE_QINDEX_1_MASK (0x7FF << I40E_VSILAN_QTABLE_QINDEX_1_SHIFT)
+#define I40E_PRTGL_SAH 0x001E2140
+#define I40E_PRTGL_SAH_FC_SAH_SHIFT 0
+#define I40E_PRTGL_SAH_FC_SAH_MASK (0xFFFF << I40E_PRTGL_SAH_FC_SAH_SHIFT)
+#define I40E_PRTGL_SAH_MFS_SHIFT 16
+#define I40E_PRTGL_SAH_MFS_MASK (0xFFFF << I40E_PRTGL_SAH_MFS_SHIFT)
+#define I40E_PRTGL_SAL 0x001E2120
+#define I40E_PRTGL_SAL_FC_SAL_SHIFT 0
+#define I40E_PRTGL_SAL_FC_SAL_MASK (0xFFFFFFFF << I40E_PRTGL_SAL_FC_SAL_SHIFT)
+#define I40E_PRTMAC_HLCTLA 0x001E4760
+#define I40E_PRTMAC_HLCTLA_DROP_US_PKTS_SHIFT 0
+#define I40E_PRTMAC_HLCTLA_DROP_US_PKTS_MASK (0x1 << I40E_PRTMAC_HLCTLA_DROP_US_PKTS_SHIFT)
+#define I40E_PRTMAC_HLCTLA_RX_FWRD_CTRL_SHIFT 1
+#define I40E_PRTMAC_HLCTLA_RX_FWRD_CTRL_MASK (0x1 << I40E_PRTMAC_HLCTLA_RX_FWRD_CTRL_SHIFT)
+#define I40E_PRTMAC_HLCTLA_CHOP_OS_PKT_SHIFT 2
+#define I40E_PRTMAC_HLCTLA_CHOP_OS_PKT_MASK (0x1 << I40E_PRTMAC_HLCTLA_CHOP_OS_PKT_SHIFT)
+#define I40E_PRTMAC_HLCTLA_TX_HYSTERESIS_SHIFT 4
+#define I40E_PRTMAC_HLCTLA_TX_HYSTERESIS_MASK (0x7 << I40E_PRTMAC_HLCTLA_TX_HYSTERESIS_SHIFT)
+#define I40E_PRTMAC_HLCTLA_HYS_FLUSH_PKT_SHIFT 7
+#define I40E_PRTMAC_HLCTLA_HYS_FLUSH_PKT_MASK (0x1 << I40E_PRTMAC_HLCTLA_HYS_FLUSH_PKT_SHIFT)
+#define I40E_PRTMAC_HSEC_CTL_RX_CHECK_SA_GCP 0x001E3130
+#define I40E_PRTMAC_HSEC_CTL_RX_CHECK_SA_GCP_HSEC_CTL_RX_CHECK_SA_GCP_SHIFT 0
+#define I40E_PRTMAC_HSEC_CTL_RX_CHECK_SA_GCP_HSEC_CTL_RX_CHECK_SA_GCP_MASK (0x1 << I40E_PRTMAC_HSEC_CTL_RX_CHECK_SA_GCP_HSEC_CTL_RX_CHECK_SA_GCP_SHIFT)
+#define I40E_PRTMAC_HSEC_CTL_RX_CHECK_SA_GPP 0x001E3290
+#define I40E_PRTMAC_HSEC_CTL_RX_CHECK_SA_GPP_HSEC_CTL_RX_CHECK_SA_GPP_SHIFT 0
+#define I40E_PRTMAC_HSEC_CTL_RX_CHECK_SA_GPP_HSEC_CTL_RX_CHECK_SA_GPP_MASK (0x1 << I40E_PRTMAC_HSEC_CTL_RX_CHECK_SA_GPP_HSEC_CTL_RX_CHECK_SA_GPP_SHIFT)
+#define I40E_PRTMAC_HSEC_CTL_RX_CHECK_SA_PPP 0x001E3310
+#define I40E_PRTMAC_HSEC_CTL_RX_CHECK_SA_PPP_HSEC_CTL_RX_CHECK_SA_PPP_SHIFT 0
+#define I40E_PRTMAC_HSEC_CTL_RX_CHECK_SA_PPP_HSEC_CTL_RX_CHECK_SA_PPP_MASK (0x1 << I40E_PRTMAC_HSEC_CTL_RX_CHECK_SA_PPP_HSEC_CTL_RX_CHECK_SA_PPP_SHIFT)
+#define I40E_PRTMAC_HSEC_CTL_RX_CHECK_UCAST_GCP 0x001E3100
+#define I40E_PRTMAC_HSEC_CTL_RX_CHECK_UCAST_GCP_HSEC_CTL_RX_CHECK_UCAST_GCP_SHIFT 0
+#define I40E_PRTMAC_HSEC_CTL_RX_CHECK_UCAST_GCP_HSEC_CTL_RX_CHECK_UCAST_GCP_MASK (0x1 << I40E_PRTMAC_HSEC_CTL_RX_CHECK_UCAST_GCP_HSEC_CTL_RX_CHECK_UCAST_GCP_SHIFT)
+#define I40E_PRTMAC_HSEC_CTL_RX_CHECK_UCAST_GPP 0x001E3280
+#define I40E_PRTMAC_HSEC_CTL_RX_CHECK_UCAST_GPP_HSEC_CTL_RX_CHECK_UCAST_GPP_SHIFT 0
+#define I40E_PRTMAC_HSEC_CTL_RX_CHECK_UCAST_GPP_HSEC_CTL_RX_CHECK_UCAST_GPP_MASK (0x1 << I40E_PRTMAC_HSEC_CTL_RX_CHECK_UCAST_GPP_HSEC_CTL_RX_CHECK_UCAST_GPP_SHIFT)
+#define I40E_PRTMAC_HSEC_CTL_RX_CHECK_UCAST_PPP 0x001E3300
+#define I40E_PRTMAC_HSEC_CTL_RX_CHECK_UCAST_PPP_HSEC_CTL_RX_CHECK_UCAST_PPP_SHIFT 0
+#define I40E_PRTMAC_HSEC_CTL_RX_CHECK_UCAST_PPP_HSEC_CTL_RX_CHECK_UCAST_PPP_MASK (0x1 << I40E_PRTMAC_HSEC_CTL_RX_CHECK_UCAST_PPP_HSEC_CTL_RX_CHECK_UCAST_PPP_SHIFT)
+#define I40E_PRTMAC_HSEC_CTL_RX_ENABLE_GCP 0x001E30E0
+#define I40E_PRTMAC_HSEC_CTL_RX_ENABLE_GCP_HSEC_CTL_RX_ENABLE_GCP_SHIFT 0
+#define I40E_PRTMAC_HSEC_CTL_RX_ENABLE_GCP_HSEC_CTL_RX_ENABLE_GCP_MASK (0x1 << I40E_PRTMAC_HSEC_CTL_RX_ENABLE_GCP_HSEC_CTL_RX_ENABLE_GCP_SHIFT)
+#define I40E_PRTMAC_HSEC_CTL_RX_ENABLE_GPP 0x001E3260
+#define I40E_PRTMAC_HSEC_CTL_RX_ENABLE_GPP_HSEC_CTL_RX_ENABLE_GPP_SHIFT 0
+#define I40E_PRTMAC_HSEC_CTL_RX_ENABLE_GPP_HSEC_CTL_RX_ENABLE_GPP_MASK (0x1 << I40E_PRTMAC_HSEC_CTL_RX_ENABLE_GPP_HSEC_CTL_RX_ENABLE_GPP_SHIFT)
+#define I40E_PRTMAC_HSEC_CTL_RX_ENABLE_PPP 0x001E32E0
+#define I40E_PRTMAC_HSEC_CTL_RX_ENABLE_PPP_HSEC_CTL_RX_ENABLE_PPP_SHIFT 0
+#define I40E_PRTMAC_HSEC_CTL_RX_ENABLE_PPP_HSEC_CTL_RX_ENABLE_PPP_MASK (0x1 << I40E_PRTMAC_HSEC_CTL_RX_ENABLE_PPP_HSEC_CTL_RX_ENABLE_PPP_SHIFT)
+#define I40E_PRTMAC_HSEC_CTL_RX_FORWARD_CONTROL 0x001E3360
+#define I40E_PRTMAC_HSEC_CTL_RX_FORWARD_CONTROL_HSEC_CTL_RX_FORWARD_CONTROL_SHIFT 0
+#define I40E_PRTMAC_HSEC_CTL_RX_FORWARD_CONTROL_HSEC_CTL_RX_FORWARD_CONTROL_MASK (0x1 << I40E_PRTMAC_HSEC_CTL_RX_FORWARD_CONTROL_HSEC_CTL_RX_FORWARD_CONTROL_SHIFT)
+#define I40E_PRTMAC_HSEC_CTL_RX_PAUSE_DA_UCAST_PART1 0x001E3110
+#define I40E_PRTMAC_HSEC_CTL_RX_PAUSE_DA_UCAST_PART1_HSEC_CTL_RX_PAUSE_DA_UCAST_PART1_SHIFT 0
+#define I40E_PRTMAC_HSEC_CTL_RX_PAUSE_DA_UCAST_PART1_HSEC_CTL_RX_PAUSE_DA_UCAST_PART1_MASK (0xFFFFFFFF << I40E_PRTMAC_HSEC_CTL_RX_PAUSE_DA_UCAST_PART1_HSEC_CTL_RX_PAUSE_DA_UCAST_PART1_SHIFT)
+#define I40E_PRTMAC_HSEC_CTL_RX_PAUSE_DA_UCAST_PART2 0x001E3120
+#define I40E_PRTMAC_HSEC_CTL_RX_PAUSE_DA_UCAST_PART2_HSEC_CTL_RX_PAUSE_DA_UCAST_PART2_SHIFT 0
+#define I40E_PRTMAC_HSEC_CTL_RX_PAUSE_DA_UCAST_PART2_HSEC_CTL_RX_PAUSE_DA_UCAST_PART2_MASK (0xFFFF << I40E_PRTMAC_HSEC_CTL_RX_PAUSE_DA_UCAST_PART2_HSEC_CTL_RX_PAUSE_DA_UCAST_PART2_SHIFT)
+#define I40E_PRTMAC_HSEC_CTL_RX_PAUSE_ENABLE 0x001E30C0
+#define I40E_PRTMAC_HSEC_CTL_RX_PAUSE_ENABLE_HSEC_CTL_RX_PAUSE_ENABLE_SHIFT 0
+#define I40E_PRTMAC_HSEC_CTL_RX_PAUSE_ENABLE_HSEC_CTL_RX_PAUSE_ENABLE_MASK (0x1FF << I40E_PRTMAC_HSEC_CTL_RX_PAUSE_ENABLE_HSEC_CTL_RX_PAUSE_ENABLE_SHIFT)
+#define I40E_PRTMAC_HSEC_CTL_RX_PAUSE_SA_PART1 0x001E3140
+#define I40E_PRTMAC_HSEC_CTL_RX_PAUSE_SA_PART1_HSEC_CTL_RX_PAUSE_SA_PART1_SHIFT 0
+#define I40E_PRTMAC_HSEC_CTL_RX_PAUSE_SA_PART1_HSEC_CTL_RX_PAUSE_SA_PART1_MASK (0xFFFFFFFF << I40E_PRTMAC_HSEC_CTL_RX_PAUSE_SA_PART1_HSEC_CTL_RX_PAUSE_SA_PART1_SHIFT)
+#define I40E_PRTMAC_HSEC_CTL_RX_PAUSE_SA_PART2 0x001E3150
+#define I40E_PRTMAC_HSEC_CTL_RX_PAUSE_SA_PART2_HSEC_CTL_RX_PAUSE_SA_PART2_SHIFT 0
+#define I40E_PRTMAC_HSEC_CTL_RX_PAUSE_SA_PART2_HSEC_CTL_RX_PAUSE_SA_PART2_MASK (0xFFFF << I40E_PRTMAC_HSEC_CTL_RX_PAUSE_SA_PART2_HSEC_CTL_RX_PAUSE_SA_PART2_SHIFT)
+#define I40E_PRTMAC_HSEC_CTL_TX_ENABLE 0x001E3000
+#define I40E_PRTMAC_HSEC_CTL_TX_ENABLE_HSEC_CTL_TX_ENABLE_SHIFT 0
+#define I40E_PRTMAC_HSEC_CTL_TX_ENABLE_HSEC_CTL_TX_ENABLE_MASK (0x1 << I40E_PRTMAC_HSEC_CTL_TX_ENABLE_HSEC_CTL_TX_ENABLE_SHIFT)
+#define I40E_PRTMAC_HSEC_CTL_TX_PAUSE_ENABLE 0x001E30D0
+#define I40E_PRTMAC_HSEC_CTL_TX_PAUSE_ENABLE_HSEC_CTL_TX_PAUSE_ENABLE_SHIFT 0
+#define I40E_PRTMAC_HSEC_CTL_TX_PAUSE_ENABLE_HSEC_CTL_TX_PAUSE_ENABLE_MASK (0x1FF << I40E_PRTMAC_HSEC_CTL_TX_PAUSE_ENABLE_HSEC_CTL_TX_PAUSE_ENABLE_SHIFT)
+#define I40E_PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA(_i) (0x001E3370 + ((_i) * 16))
+#define I40E_PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA_MAX_INDEX 8
+#define I40E_PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA_HSEC_CTL_TX_PAUSE_QUANTA_SHIFT 0
+#define I40E_PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA_HSEC_CTL_TX_PAUSE_QUANTA_MASK (0xFFFF << I40E_PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA_HSEC_CTL_TX_PAUSE_QUANTA_SHIFT)
+#define I40E_PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER(_i) (0x001E3400 + ((_i) * 16))
+#define I40E_PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_MAX_INDEX 8
+#define I40E_PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_SHIFT 0
+#define I40E_PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_MASK (0xFFFF << I40E_PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_SHIFT)
+#define I40E_PRTMAC_HSEC_CTL_TX_SA_PART1 0x001E34B0
+#define I40E_PRTMAC_HSEC_CTL_TX_SA_PART1_HSEC_CTL_TX_SA_PART1_SHIFT 0
+#define I40E_PRTMAC_HSEC_CTL_TX_SA_PART1_HSEC_CTL_TX_SA_PART1_MASK (0xFFFFFFFF << I40E_PRTMAC_HSEC_CTL_TX_SA_PART1_HSEC_CTL_TX_SA_PART1_SHIFT)
+#define I40E_PRTMAC_HSEC_CTL_TX_SA_PART2 0x001E34C0
+#define I40E_PRTMAC_HSEC_CTL_TX_SA_PART2_HSEC_CTL_TX_SA_PART2_SHIFT 0
+#define I40E_PRTMAC_HSEC_CTL_TX_SA_PART2_HSEC_CTL_TX_SA_PART2_MASK (0xFFFF << I40E_PRTMAC_HSEC_CTL_TX_SA_PART2_HSEC_CTL_TX_SA_PART2_SHIFT)
+#define I40E_PRTMAC_HSECTL1 0x001E3560
+#define I40E_PRTMAC_HSECTL1_DROP_US_PKTS_SHIFT 0
+#define I40E_PRTMAC_HSECTL1_DROP_US_PKTS_MASK (0x1 << I40E_PRTMAC_HSECTL1_DROP_US_PKTS_SHIFT)
+#define I40E_PRTMAC_HSECTL1_PAD_US_PKT_SHIFT 3
+#define I40E_PRTMAC_HSECTL1_PAD_US_PKT_MASK (0x1 << I40E_PRTMAC_HSECTL1_PAD_US_PKT_SHIFT)
+#define I40E_PRTMAC_HSECTL1_TX_HYSTERESIS_SHIFT 4
+#define I40E_PRTMAC_HSECTL1_TX_HYSTERESIS_MASK (0x7 << I40E_PRTMAC_HSECTL1_TX_HYSTERESIS_SHIFT)
+#define I40E_PRTMAC_HSECTL1_HYS_FLUSH_PKT_SHIFT 7
+#define I40E_PRTMAC_HSECTL1_HYS_FLUSH_PKT_MASK (0x1 << I40E_PRTMAC_HSECTL1_HYS_FLUSH_PKT_SHIFT)
+#define I40E_PRTMAC_HSECTL1_EN_SFD_CHECK_SHIFT 30
+#define I40E_PRTMAC_HSECTL1_EN_SFD_CHECK_MASK (0x1 << I40E_PRTMAC_HSECTL1_EN_SFD_CHECK_SHIFT)
+#define I40E_PRTMAC_HSECTL1_EN_PREAMBLE_CHECK_SHIFT 31
+#define I40E_PRTMAC_HSECTL1_EN_PREAMBLE_CHECK_MASK (0x1 << I40E_PRTMAC_HSECTL1_EN_PREAMBLE_CHECK_SHIFT)
+#define I40E_PRTMAC_PCS_XAUI_SWAP_A 0x0008C480
+#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_TX_LANE3_SHIFT 0
+#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_TX_LANE3_MASK (0x3 << I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_TX_LANE3_SHIFT)
+#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_TX_LANE2_SHIFT 2
+#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_TX_LANE2_MASK (0x3 << I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_TX_LANE2_SHIFT)
+#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_TX_LANE1_SHIFT 4
+#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_TX_LANE1_MASK (0x3 << I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_TX_LANE1_SHIFT)
+#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_TX_LANE0_SHIFT 6
+#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_TX_LANE0_MASK (0x3 << I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_TX_LANE0_SHIFT)
+#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_RX_LANE3_SHIFT 8
+#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_RX_LANE3_MASK (0x3 << I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_RX_LANE3_SHIFT)
+#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_RX_LANE2_SHIFT 10
+#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_RX_LANE2_MASK (0x3 << I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_RX_LANE2_SHIFT)
+#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_RX_LANE1_SHIFT 12
+#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_RX_LANE1_MASK (0x3 << I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_RX_LANE1_SHIFT)
+#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_RX_LANE0_SHIFT 14
+#define I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_RX_LANE0_MASK (0x3 << I40E_PRTMAC_PCS_XAUI_SWAP_A_SWAP_RX_LANE0_SHIFT)
+#define I40E_PRTMAC_PCS_XAUI_SWAP_B 0x0008C484
+#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_TX_LANE3_SHIFT 0
+#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_TX_LANE3_MASK (0x3 << I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_TX_LANE3_SHIFT)
+#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_TX_LANE2_SHIFT 2
+#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_TX_LANE2_MASK (0x3 << I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_TX_LANE2_SHIFT)
+#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_TX_LANE1_SHIFT 4
+#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_TX_LANE1_MASK (0x3 << I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_TX_LANE1_SHIFT)
+#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_TX_LANE0_SHIFT 6
+#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_TX_LANE0_MASK (0x3 << I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_TX_LANE0_SHIFT)
+#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_RX_LANE3_SHIFT 8
+#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_RX_LANE3_MASK (0x3 << I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_RX_LANE3_SHIFT)
+#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_RX_LANE2_SHIFT 10
+#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_RX_LANE2_MASK (0x3 << I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_RX_LANE2_SHIFT)
+#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_RX_LANE1_SHIFT 12
+#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_RX_LANE1_MASK (0x3 << I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_RX_LANE1_SHIFT)
+#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_RX_LANE0_SHIFT 14
+#define I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_RX_LANE0_MASK (0x3 << I40E_PRTMAC_PCS_XAUI_SWAP_B_SWAP_RX_LANE0_SHIFT)
+#define I40E_GL_MNG_FWSM 0x000B6134
+#define I40E_GL_MNG_FWSM_FW_MODES_SHIFT 0
+#define I40E_GL_MNG_FWSM_FW_MODES_MASK (0x3FF << I40E_GL_MNG_FWSM_FW_MODES_SHIFT)
+#define I40E_GL_MNG_FWSM_EEP_RELOAD_IND_SHIFT 10
+#define I40E_GL_MNG_FWSM_EEP_RELOAD_IND_MASK (0x1 << I40E_GL_MNG_FWSM_EEP_RELOAD_IND_SHIFT)
+#define I40E_GL_MNG_FWSM_CRC_ERROR_MODULE_SHIFT 11
+#define I40E_GL_MNG_FWSM_CRC_ERROR_MODULE_MASK (0xF << I40E_GL_MNG_FWSM_CRC_ERROR_MODULE_SHIFT)
+#define I40E_GL_MNG_FWSM_FW_STATUS_VALID_SHIFT 15
+#define I40E_GL_MNG_FWSM_FW_STATUS_VALID_MASK (0x1 << I40E_GL_MNG_FWSM_FW_STATUS_VALID_SHIFT)
+#define I40E_GL_MNG_FWSM_EXT_ERR_IND_SHIFT 19
+#define I40E_GL_MNG_FWSM_EXT_ERR_IND_MASK (0x3F << I40E_GL_MNG_FWSM_EXT_ERR_IND_SHIFT)
+#define I40E_GL_MNG_FWSM_PHY_SERDES0_CONFIG_ERR_SHIFT 26
+#define I40E_GL_MNG_FWSM_PHY_SERDES0_CONFIG_ERR_MASK (0x1 << I40E_GL_MNG_FWSM_PHY_SERDES0_CONFIG_ERR_SHIFT)
+#define I40E_GL_MNG_FWSM_PHY_SERDES1_CONFIG_ERR_SHIFT 27
+#define I40E_GL_MNG_FWSM_PHY_SERDES1_CONFIG_ERR_MASK (0x1 << I40E_GL_MNG_FWSM_PHY_SERDES1_CONFIG_ERR_SHIFT)
+#define I40E_GL_MNG_FWSM_PHY_SERDES2_CONFIG_ERR_SHIFT 28
+#define I40E_GL_MNG_FWSM_PHY_SERDES2_CONFIG_ERR_MASK (0x1 << I40E_GL_MNG_FWSM_PHY_SERDES2_CONFIG_ERR_SHIFT)
+#define I40E_GL_MNG_FWSM_PHY_SERDES3_CONFIG_ERR_SHIFT 29
+#define I40E_GL_MNG_FWSM_PHY_SERDES3_CONFIG_ERR_MASK (0x1 << I40E_GL_MNG_FWSM_PHY_SERDES3_CONFIG_ERR_SHIFT)
+#define I40E_GL_MNG_HWARB_CTRL 0x000B6130
+#define I40E_GL_MNG_HWARB_CTRL_NCSI_ARB_EN_SHIFT 0
+#define I40E_GL_MNG_HWARB_CTRL_NCSI_ARB_EN_MASK (0x1 << I40E_GL_MNG_HWARB_CTRL_NCSI_ARB_EN_SHIFT)
+#define I40E_PRT_MNG_FTFT_DATA(_i) (0x000852A0 + ((_i) * 32)) /* _i=0...31 */
+#define I40E_PRT_MNG_FTFT_DATA_MAX_INDEX 31
+#define I40E_PRT_MNG_FTFT_DATA_DWORD_SHIFT 0
+#define I40E_PRT_MNG_FTFT_DATA_DWORD_MASK (0xFFFFFFFF << I40E_PRT_MNG_FTFT_DATA_DWORD_SHIFT)
+#define I40E_PRT_MNG_FTFT_LENGTH 0x00085260
+#define I40E_PRT_MNG_FTFT_LENGTH_LENGTH_SHIFT 0
+#define I40E_PRT_MNG_FTFT_LENGTH_LENGTH_MASK (0xFF << I40E_PRT_MNG_FTFT_LENGTH_LENGTH_SHIFT)
+#define I40E_PRT_MNG_FTFT_MASK(_i) (0x00085160 + ((_i) * 32)) /* _i=0...7 */
+#define I40E_PRT_MNG_FTFT_MASK_MAX_INDEX 7
+#define I40E_PRT_MNG_FTFT_MASK_MASK_SHIFT 0
+#define I40E_PRT_MNG_FTFT_MASK_MASK_MASK (0xFFFF << I40E_PRT_MNG_FTFT_MASK_MASK_SHIFT)
+#define I40E_PRT_MNG_MANC 0x00256A20
+#define I40E_PRT_MNG_MANC_FLOW_CONTROL_DISCARD_SHIFT 0
+#define I40E_PRT_MNG_MANC_FLOW_CONTROL_DISCARD_MASK (0x1 << I40E_PRT_MNG_MANC_FLOW_CONTROL_DISCARD_SHIFT)
+#define I40E_PRT_MNG_MANC_NCSI_DISCARD_SHIFT 1
+#define I40E_PRT_MNG_MANC_NCSI_DISCARD_MASK (0x1 << I40E_PRT_MNG_MANC_NCSI_DISCARD_SHIFT)
+#define I40E_PRT_MNG_MANC_RCV_TCO_EN_SHIFT 17
+#define I40E_PRT_MNG_MANC_RCV_TCO_EN_MASK (0x1 << I40E_PRT_MNG_MANC_RCV_TCO_EN_SHIFT)
+#define I40E_PRT_MNG_MANC_RCV_ALL_SHIFT 19
+#define I40E_PRT_MNG_MANC_RCV_ALL_MASK (0x1 << I40E_PRT_MNG_MANC_RCV_ALL_SHIFT)
+#define I40E_PRT_MNG_MANC_FIXED_NET_TYPE_SHIFT 25
+#define I40E_PRT_MNG_MANC_FIXED_NET_TYPE_MASK (0x1 << I40E_PRT_MNG_MANC_FIXED_NET_TYPE_SHIFT)
+#define I40E_PRT_MNG_MANC_NET_TYPE_SHIFT 26
+#define I40E_PRT_MNG_MANC_NET_TYPE_MASK (0x1 << I40E_PRT_MNG_MANC_NET_TYPE_SHIFT)
+#define I40E_PRT_MNG_MANC_EN_BMC2OS_SHIFT 28
+#define I40E_PRT_MNG_MANC_EN_BMC2OS_MASK (0x1 << I40E_PRT_MNG_MANC_EN_BMC2OS_SHIFT)
+#define I40E_PRT_MNG_MANC_EN_BMC2NET_SHIFT 29
+#define I40E_PRT_MNG_MANC_EN_BMC2NET_MASK (0x1 << I40E_PRT_MNG_MANC_EN_BMC2NET_SHIFT)
+#define I40E_PRT_MNG_MAVTV(_i) (0x00255900 + ((_i) * 32)) /* _i=0...7 */
+#define I40E_PRT_MNG_MAVTV_MAX_INDEX 7
+#define I40E_PRT_MNG_MAVTV_VID_SHIFT 0
+#define I40E_PRT_MNG_MAVTV_VID_MASK (0xFFF << I40E_PRT_MNG_MAVTV_VID_SHIFT)
+#define I40E_PRT_MNG_MDEF(_i) (0x00255D00 + ((_i) * 32))
+#define I40E_PRT_MNG_MDEF_MAX_INDEX 7
+#define I40E_PRT_MNG_MDEF_MAC_EXACT_AND_SHIFT 0
+#define I40E_PRT_MNG_MDEF_MAC_EXACT_AND_MASK (0xF << I40E_PRT_MNG_MDEF_MAC_EXACT_AND_SHIFT)
+#define I40E_PRT_MNG_MDEF_BROADCAST_AND_SHIFT 4
+#define I40E_PRT_MNG_MDEF_BROADCAST_AND_MASK (0x1 << I40E_PRT_MNG_MDEF_BROADCAST_AND_SHIFT)
+#define I40E_PRT_MNG_MDEF_VLAN_AND_SHIFT 5
+#define I40E_PRT_MNG_MDEF_VLAN_AND_MASK (0xFF << I40E_PRT_MNG_MDEF_VLAN_AND_SHIFT)
+#define I40E_PRT_MNG_MDEF_IPV4_ADDRESS_AND_SHIFT 13
+#define I40E_PRT_MNG_MDEF_IPV4_ADDRESS_AND_MASK (0xF << I40E_PRT_MNG_MDEF_IPV4_ADDRESS_AND_SHIFT)
+#define I40E_PRT_MNG_MDEF_IPV6_ADDRESS_AND_SHIFT 17
+#define I40E_PRT_MNG_MDEF_IPV6_ADDRESS_AND_MASK (0xF << I40E_PRT_MNG_MDEF_IPV6_ADDRESS_AND_SHIFT)
+#define I40E_PRT_MNG_MDEF_MAC_EXACT_OR_SHIFT 21
+#define I40E_PRT_MNG_MDEF_MAC_EXACT_OR_MASK (0xF << I40E_PRT_MNG_MDEF_MAC_EXACT_OR_SHIFT)
+#define I40E_PRT_MNG_MDEF_BROADCAST_OR_SHIFT 25
+#define I40E_PRT_MNG_MDEF_BROADCAST_OR_MASK (0x1 << I40E_PRT_MNG_MDEF_BROADCAST_OR_SHIFT)
+#define I40E_PRT_MNG_MDEF_MULTICAST_AND_SHIFT 26
+#define I40E_PRT_MNG_MDEF_MULTICAST_AND_MASK (0x1 << I40E_PRT_MNG_MDEF_MULTICAST_AND_SHIFT)
+#define I40E_PRT_MNG_MDEF_ARP_REQUEST_OR_SHIFT 27
+#define I40E_PRT_MNG_MDEF_ARP_REQUEST_OR_MASK (0x1 << I40E_PRT_MNG_MDEF_ARP_REQUEST_OR_SHIFT)
+#define I40E_PRT_MNG_MDEF_ARP_RESPONSE_OR_SHIFT 28
+#define I40E_PRT_MNG_MDEF_ARP_RESPONSE_OR_MASK (0x1 << I40E_PRT_MNG_MDEF_ARP_RESPONSE_OR_SHIFT)
+#define I40E_PRT_MNG_MDEF_NEIGHBOR_DISCOVERY_134_OR_SHIFT 29
+#define I40E_PRT_MNG_MDEF_NEIGHBOR_DISCOVERY_134_OR_MASK (0x1 << I40E_PRT_MNG_MDEF_NEIGHBOR_DISCOVERY_134_OR_SHIFT)
+#define I40E_PRT_MNG_MDEF_PORT_0X298_OR_SHIFT 30
+#define I40E_PRT_MNG_MDEF_PORT_0X298_OR_MASK (0x1 << I40E_PRT_MNG_MDEF_PORT_0X298_OR_SHIFT)
+#define I40E_PRT_MNG_MDEF_PORT_0X26F_OR_SHIFT 31
+#define I40E_PRT_MNG_MDEF_PORT_0X26F_OR_MASK (0x1 << I40E_PRT_MNG_MDEF_PORT_0X26F_OR_SHIFT)
+#define I40E_PRT_MNG_MDEF_EXT(_i) (0x00255F00 + ((_i) * 32))
+#define I40E_PRT_MNG_MDEF_EXT_MAX_INDEX 7
+#define I40E_PRT_MNG_MDEF_EXT_L2_ETHERTYPE_AND_SHIFT 0
+#define I40E_PRT_MNG_MDEF_EXT_L2_ETHERTYPE_AND_MASK (0xF << I40E_PRT_MNG_MDEF_EXT_L2_ETHERTYPE_AND_SHIFT)
+#define I40E_PRT_MNG_MDEF_EXT_L2_ETHERTYPE_OR_SHIFT 4
+#define I40E_PRT_MNG_MDEF_EXT_L2_ETHERTYPE_OR_MASK (0xF << I40E_PRT_MNG_MDEF_EXT_L2_ETHERTYPE_OR_SHIFT)
+#define I40E_PRT_MNG_MDEF_EXT_FLEX_PORT_OR_SHIFT 8
+#define I40E_PRT_MNG_MDEF_EXT_FLEX_PORT_OR_MASK (0xFFFF << I40E_PRT_MNG_MDEF_EXT_FLEX_PORT_OR_SHIFT)
+#define I40E_PRT_MNG_MDEF_EXT_FLEX_TCO_SHIFT 24
+#define I40E_PRT_MNG_MDEF_EXT_FLEX_TCO_MASK (0x1 << I40E_PRT_MNG_MDEF_EXT_FLEX_TCO_SHIFT)
+#define I40E_PRT_MNG_MDEF_EXT_NEIGHBOR_DISCOVERY_135_OR_SHIFT 25
+#define I40E_PRT_MNG_MDEF_EXT_NEIGHBOR_DISCOVERY_135_OR_MASK (0x1 << I40E_PRT_MNG_MDEF_EXT_NEIGHBOR_DISCOVERY_135_OR_SHIFT)
+#define I40E_PRT_MNG_MDEF_EXT_NEIGHBOR_DISCOVERY_136_OR_SHIFT 26
+#define I40E_PRT_MNG_MDEF_EXT_NEIGHBOR_DISCOVERY_136_OR_MASK (0x1 << I40E_PRT_MNG_MDEF_EXT_NEIGHBOR_DISCOVERY_136_OR_SHIFT)
+#define I40E_PRT_MNG_MDEF_EXT_NEIGHBOR_DISCOVERY_137_OR_SHIFT 27
+#define I40E_PRT_MNG_MDEF_EXT_NEIGHBOR_DISCOVERY_137_OR_MASK (0x1 << I40E_PRT_MNG_MDEF_EXT_NEIGHBOR_DISCOVERY_137_OR_SHIFT)
+#define I40E_PRT_MNG_MDEF_EXT_ICMP_OR_SHIFT 28
+#define I40E_PRT_MNG_MDEF_EXT_ICMP_OR_MASK (0x1 << I40E_PRT_MNG_MDEF_EXT_ICMP_OR_SHIFT)
+#define I40E_PRT_MNG_MDEF_EXT_MLD_SHIFT 29
+#define I40E_PRT_MNG_MDEF_EXT_MLD_MASK (0x1 << I40E_PRT_MNG_MDEF_EXT_MLD_SHIFT)
+#define I40E_PRT_MNG_MDEF_EXT_APPLY_TO_NETWORK_TRAFFIC_SHIFT 30
+#define I40E_PRT_MNG_MDEF_EXT_APPLY_TO_NETWORK_TRAFFIC_MASK (0x1 << I40E_PRT_MNG_MDEF_EXT_APPLY_TO_NETWORK_TRAFFIC_SHIFT)
+#define I40E_PRT_MNG_MDEF_EXT_APPLY_TO_HOST_TRAFFIC_SHIFT 31
+#define I40E_PRT_MNG_MDEF_EXT_APPLY_TO_HOST_TRAFFIC_MASK (0x1 << I40E_PRT_MNG_MDEF_EXT_APPLY_TO_HOST_TRAFFIC_SHIFT)
+#define I40E_PRT_MNG_MDEFVSI(_i) (0x00256580 + ((_i) * 32)) /* _i=0...3 */
+#define I40E_PRT_MNG_MDEFVSI_MAX_INDEX 3
+#define I40E_PRT_MNG_MDEFVSI_MDEFVSI_2N_SHIFT 0
+#define I40E_PRT_MNG_MDEFVSI_MDEFVSI_2N_MASK (0xFFFF << I40E_PRT_MNG_MDEFVSI_MDEFVSI_2N_SHIFT)
+#define I40E_PRT_MNG_MDEFVSI_MDEFVSI_2NP1_SHIFT 16
+#define I40E_PRT_MNG_MDEFVSI_MDEFVSI_2NP1_MASK (0xFFFF << I40E_PRT_MNG_MDEFVSI_MDEFVSI_2NP1_SHIFT)
+#define I40E_PRT_MNG_METF(_i) (0x00256780 + ((_i) * 32)) /* _i=0...3 */
+#define I40E_PRT_MNG_METF_MAX_INDEX 3
+#define I40E_PRT_MNG_METF_ETYPE_SHIFT 0
+#define I40E_PRT_MNG_METF_ETYPE_MASK (0xFFFF << I40E_PRT_MNG_METF_ETYPE_SHIFT)
+#define I40E_PRT_MNG_METF_POLARITY_SHIFT 30
+#define I40E_PRT_MNG_METF_POLARITY_MASK (0x1 << I40E_PRT_MNG_METF_POLARITY_SHIFT)
+#define I40E_PRT_MNG_MFUTP(_i) (0x00254E00 + ((_i) * 32)) /* _i=0...15 */
+#define I40E_PRT_MNG_MFUTP_MAX_INDEX 15
+#define I40E_PRT_MNG_MFUTP_MFUTP_N_SHIFT 0
+#define I40E_PRT_MNG_MFUTP_MFUTP_N_MASK (0xFFFF << I40E_PRT_MNG_MFUTP_MFUTP_N_SHIFT)
+#define I40E_PRT_MNG_MFUTP_UDP_SHIFT 16
+#define I40E_PRT_MNG_MFUTP_UDP_MASK (0x1 << I40E_PRT_MNG_MFUTP_UDP_SHIFT)
+#define I40E_PRT_MNG_MFUTP_TCP_SHIFT 17
+#define I40E_PRT_MNG_MFUTP_TCP_MASK (0x1 << I40E_PRT_MNG_MFUTP_TCP_SHIFT)
+#define I40E_PRT_MNG_MFUTP_SOURCE_DESTINATION_SHIFT 18
+#define I40E_PRT_MNG_MFUTP_SOURCE_DESTINATION_MASK (0x1 << I40E_PRT_MNG_MFUTP_SOURCE_DESTINATION_SHIFT)
+#define I40E_PRT_MNG_MIPAF4(_i) (0x00256280 + ((_i) * 32)) /* _i=0...3 */
+#define I40E_PRT_MNG_MIPAF4_MAX_INDEX 3
+#define I40E_PRT_MNG_MIPAF4_MIPAF_SHIFT 0
+#define I40E_PRT_MNG_MIPAF4_MIPAF_MASK (0xFFFFFFFF << I40E_PRT_MNG_MIPAF4_MIPAF_SHIFT)
+#define I40E_PRT_MNG_MIPAF6(_i) (0x00254200 + ((_i) * 32)) /* _i=0...15 */
+#define I40E_PRT_MNG_MIPAF6_MAX_INDEX 15
+#define I40E_PRT_MNG_MIPAF6_MIPAF_SHIFT 0
+#define I40E_PRT_MNG_MIPAF6_MIPAF_MASK (0xFFFFFFFF << I40E_PRT_MNG_MIPAF6_MIPAF_SHIFT)
+#define I40E_PRT_MNG_MMAH(_i) (0x00256380 + ((_i) * 32)) /* _i=0...3 */
+#define I40E_PRT_MNG_MMAH_MAX_INDEX 3
+#define I40E_PRT_MNG_MMAH_MMAH_SHIFT 0
+#define I40E_PRT_MNG_MMAH_MMAH_MASK (0xFFFF << I40E_PRT_MNG_MMAH_MMAH_SHIFT)
+#define I40E_PRT_MNG_MMAL(_i) (0x00256480 + ((_i) * 32)) /* _i=0...3 */
+#define I40E_PRT_MNG_MMAL_MAX_INDEX 3
+#define I40E_PRT_MNG_MMAL_MMAL_SHIFT 0
+#define I40E_PRT_MNG_MMAL_MMAL_MASK (0xFFFFFFFF << I40E_PRT_MNG_MMAL_MMAL_SHIFT)
+#define I40E_PRT_MNG_MNGONLY 0x00256A60
+#define I40E_PRT_MNG_MNGONLY_EXCLUSIVE_TO_MANAGEABILITY_SHIFT 0
+#define I40E_PRT_MNG_MNGONLY_EXCLUSIVE_TO_MANAGEABILITY_MASK (0xFF << I40E_PRT_MNG_MNGONLY_EXCLUSIVE_TO_MANAGEABILITY_SHIFT)
+#define I40E_PRT_MNG_MSFM 0x00256AA0
+#define I40E_PRT_MNG_MSFM_PORT_26F_UDP_SHIFT 0
+#define I40E_PRT_MNG_MSFM_PORT_26F_UDP_MASK (0x1 << I40E_PRT_MNG_MSFM_PORT_26F_UDP_SHIFT)
+#define I40E_PRT_MNG_MSFM_PORT_26F_TCP_SHIFT 1
+#define I40E_PRT_MNG_MSFM_PORT_26F_TCP_MASK (0x1 << I40E_PRT_MNG_MSFM_PORT_26F_TCP_SHIFT)
+#define I40E_PRT_MNG_MSFM_PORT_298_UDP_SHIFT 2
+#define I40E_PRT_MNG_MSFM_PORT_298_UDP_MASK (0x1 << I40E_PRT_MNG_MSFM_PORT_298_UDP_SHIFT)
+#define I40E_PRT_MNG_MSFM_PORT_298_TCP_SHIFT 3
+#define I40E_PRT_MNG_MSFM_PORT_298_TCP_MASK (0x1 << I40E_PRT_MNG_MSFM_PORT_298_TCP_SHIFT)
+#define I40E_PRT_MNG_MSFM_IPV6_0_MASK_SHIFT 4
+#define I40E_PRT_MNG_MSFM_IPV6_0_MASK_MASK (0x1 << I40E_PRT_MNG_MSFM_IPV6_0_MASK_SHIFT)
+#define I40E_PRT_MNG_MSFM_IPV6_1_MASK_SHIFT 5
+#define I40E_PRT_MNG_MSFM_IPV6_1_MASK_MASK (0x1 << I40E_PRT_MNG_MSFM_IPV6_1_MASK_SHIFT)
+#define I40E_PRT_MNG_MSFM_IPV6_2_MASK_SHIFT 6
+#define I40E_PRT_MNG_MSFM_IPV6_2_MASK_MASK (0x1 << I40E_PRT_MNG_MSFM_IPV6_2_MASK_SHIFT)
+#define I40E_PRT_MNG_MSFM_IPV6_3_MASK_SHIFT 7
+#define I40E_PRT_MNG_MSFM_IPV6_3_MASK_MASK (0x1 << I40E_PRT_MNG_MSFM_IPV6_3_MASK_SHIFT)
+#define I40E_MSIX_PBA(_i) (0x00004900 + ((_i) * 4)) /* _i=0...5 */
+#define I40E_MSIX_PBA_MAX_INDEX 5
+#define I40E_MSIX_PBA_PENBIT_SHIFT 0
+#define I40E_MSIX_PBA_PENBIT_MASK (0xFFFFFFFF << I40E_MSIX_PBA_PENBIT_SHIFT)
+#define I40E_MSIX_TADD(_i) (0x00000000 + ((_i) * 16)) /* _i=0...128 */
+#define I40E_MSIX_TADD_MAX_INDEX 128
+#define I40E_MSIX_TADD_MSIXTADD10_SHIFT 0
+#define I40E_MSIX_TADD_MSIXTADD10_MASK (0x3 << I40E_MSIX_TADD_MSIXTADD10_SHIFT)
+#define I40E_MSIX_TADD_MSIXTADD_SHIFT 2
+#define I40E_MSIX_TADD_MSIXTADD_MASK (0x3FFFFFFF << I40E_MSIX_TADD_MSIXTADD_SHIFT)
+#define I40E_MSIX_TMSG(_i) (0x00000008 + ((_i) * 16)) /* _i=0...128 */
+#define I40E_MSIX_TMSG_MAX_INDEX 128
+#define I40E_MSIX_TMSG_MSIXTMSG_SHIFT 0
+#define I40E_MSIX_TMSG_MSIXTMSG_MASK (0xFFFFFFFF << I40E_MSIX_TMSG_MSIXTMSG_SHIFT)
+#define I40E_MSIX_TUADD(_i) (0x00000004 + ((_i) * 16)) /* _i=0...128 */
+#define I40E_MSIX_TUADD_MAX_INDEX 128
+#define I40E_MSIX_TUADD_MSIXTUADD_SHIFT 0
+#define I40E_MSIX_TUADD_MSIXTUADD_MASK (0xFFFFFFFF << I40E_MSIX_TUADD_MSIXTUADD_SHIFT)
+#define I40E_MSIX_TVCTRL(_i) (0x0000000C + ((_i) * 16)) /* _i=0...128 */
+#define I40E_MSIX_TVCTRL_MAX_INDEX 128
+#define I40E_MSIX_TVCTRL_MASK_SHIFT 0
+#define I40E_MSIX_TVCTRL_MASK_MASK (0x1 << I40E_MSIX_TVCTRL_MASK_SHIFT)
+#define I40E_VFMSIX_PBA1(_i) (0x00004944 + ((_i) * 4)) /* _i=0...19 */
+#define I40E_VFMSIX_PBA1_MAX_INDEX 19
+#define I40E_VFMSIX_PBA1_PENBIT_SHIFT 0
+#define I40E_VFMSIX_PBA1_PENBIT_MASK (0xFFFFFFFF << I40E_VFMSIX_PBA1_PENBIT_SHIFT)
+#define I40E_VFMSIX_TADD1(_i) (0x00002100 + ((_i) * 16)) /* _i=0...639 */
+#define I40E_VFMSIX_TADD1_MAX_INDEX 639
+#define I40E_VFMSIX_TADD1_MSIXTADD10_SHIFT 0
+#define I40E_VFMSIX_TADD1_MSIXTADD10_MASK (0x3 << I40E_VFMSIX_TADD1_MSIXTADD10_SHIFT)
+#define I40E_VFMSIX_TADD1_MSIXTADD_SHIFT 2
+#define I40E_VFMSIX_TADD1_MSIXTADD_MASK (0x3FFFFFFF << I40E_VFMSIX_TADD1_MSIXTADD_SHIFT)
+#define I40E_VFMSIX_TMSG1(_i) (0x00002108 + ((_i) * 16)) /* _i=0...639 */
+#define I40E_VFMSIX_TMSG1_MAX_INDEX 639
+#define I40E_VFMSIX_TMSG1_MSIXTMSG_SHIFT 0
+#define I40E_VFMSIX_TMSG1_MSIXTMSG_MASK (0xFFFFFFFF << I40E_VFMSIX_TMSG1_MSIXTMSG_SHIFT)
+#define I40E_VFMSIX_TUADD1(_i) (0x00002104 + ((_i) * 16)) /* _i=0...639 */
+#define I40E_VFMSIX_TUADD1_MAX_INDEX 639
+#define I40E_VFMSIX_TUADD1_MSIXTUADD_SHIFT 0
+#define I40E_VFMSIX_TUADD1_MSIXTUADD_MASK (0xFFFFFFFF << I40E_VFMSIX_TUADD1_MSIXTUADD_SHIFT)
+#define I40E_VFMSIX_TVCTRL1(_i) (0x0000210C + ((_i) * 16)) /* _i=0...639 */
+#define I40E_VFMSIX_TVCTRL1_MAX_INDEX 639
+#define I40E_VFMSIX_TVCTRL1_MASK_SHIFT 0
+#define I40E_VFMSIX_TVCTRL1_MASK_MASK (0x1 << I40E_VFMSIX_TVCTRL1_MASK_SHIFT)
+#define I40E_GLNVM_FLA 0x000B6108
+#define I40E_GLNVM_FLA_FL_SCK_SHIFT 0
+#define I40E_GLNVM_FLA_FL_SCK_MASK (0x1 << I40E_GLNVM_FLA_FL_SCK_SHIFT)
+#define I40E_GLNVM_FLA_FL_CE_SHIFT 1
+#define I40E_GLNVM_FLA_FL_CE_MASK (0x1 << I40E_GLNVM_FLA_FL_CE_SHIFT)
+#define I40E_GLNVM_FLA_FL_SI_SHIFT 2
+#define I40E_GLNVM_FLA_FL_SI_MASK (0x1 << I40E_GLNVM_FLA_FL_SI_SHIFT)
+#define I40E_GLNVM_FLA_FL_SO_SHIFT 3
+#define I40E_GLNVM_FLA_FL_SO_MASK (0x1 << I40E_GLNVM_FLA_FL_SO_SHIFT)
+#define I40E_GLNVM_FLA_FL_REQ_SHIFT 4
+#define I40E_GLNVM_FLA_FL_REQ_MASK (0x1 << I40E_GLNVM_FLA_FL_REQ_SHIFT)
+#define I40E_GLNVM_FLA_FL_GNT_SHIFT 5
+#define I40E_GLNVM_FLA_FL_GNT_MASK (0x1 << I40E_GLNVM_FLA_FL_GNT_SHIFT)
+#define I40E_GLNVM_FLA_LOCKED_SHIFT 6
+#define I40E_GLNVM_FLA_LOCKED_MASK (0x1 << I40E_GLNVM_FLA_LOCKED_SHIFT)
+#define I40E_GLNVM_FLA_FL_SADDR_SHIFT 18
+#define I40E_GLNVM_FLA_FL_SADDR_MASK (0x7FF << I40E_GLNVM_FLA_FL_SADDR_SHIFT)
+#define I40E_GLNVM_FLA_FL_BUSY_SHIFT 30
+#define I40E_GLNVM_FLA_FL_BUSY_MASK (0x1 << I40E_GLNVM_FLA_FL_BUSY_SHIFT)
+#define I40E_GLNVM_FLA_FL_DER_SHIFT 31
+#define I40E_GLNVM_FLA_FL_DER_MASK (0x1 << I40E_GLNVM_FLA_FL_DER_SHIFT)
+#define I40E_GLNVM_FLASHID 0x000B6104
+#define I40E_GLNVM_FLASHID_FLASHID_SHIFT 0
+#define I40E_GLNVM_FLASHID_FLASHID_MASK (0xFFFFFF << I40E_GLNVM_FLASHID_FLASHID_SHIFT)
+#define I40E_GLNVM_GENS 0x000B6100
+#define I40E_GLNVM_GENS_NVM_PRES_SHIFT 0
+#define I40E_GLNVM_GENS_NVM_PRES_MASK (0x1 << I40E_GLNVM_GENS_NVM_PRES_SHIFT)
+#define I40E_GLNVM_GENS_SR_SIZE_SHIFT 5
+#define I40E_GLNVM_GENS_SR_SIZE_MASK (0x7 << I40E_GLNVM_GENS_SR_SIZE_SHIFT)
+#define I40E_GLNVM_GENS_BANK1VAL_SHIFT 8
+#define I40E_GLNVM_GENS_BANK1VAL_MASK (0x1 << I40E_GLNVM_GENS_BANK1VAL_SHIFT)
+#define I40E_GLNVM_GENS_ALT_PRST_SHIFT 23
+#define I40E_GLNVM_GENS_ALT_PRST_MASK (0x1 << I40E_GLNVM_GENS_ALT_PRST_SHIFT)
+#define I40E_GLNVM_GENS_FL_AUTO_RD_SHIFT 25
+#define I40E_GLNVM_GENS_FL_AUTO_RD_MASK (0x1 << I40E_GLNVM_GENS_FL_AUTO_RD_SHIFT)
+#define I40E_GLNVM_PROTCSR(_i) (0x000B6010 + ((_i) * 4)) /* _i=0...59 */
+#define I40E_GLNVM_PROTCSR_MAX_INDEX 59
+#define I40E_GLNVM_PROTCSR_ADDR_BLOCK_SHIFT 0
+#define I40E_GLNVM_PROTCSR_ADDR_BLOCK_MASK (0xFFFFFF << I40E_GLNVM_PROTCSR_ADDR_BLOCK_SHIFT)
+#define I40E_GLNVM_SRCTL 0x000B6110
+#define I40E_GLNVM_SRCTL_SRBUSY_SHIFT 0
+#define I40E_GLNVM_SRCTL_SRBUSY_MASK (0x1 << I40E_GLNVM_SRCTL_SRBUSY_SHIFT)
+#define I40E_GLNVM_SRCTL_ADDR_SHIFT 14
+#define I40E_GLNVM_SRCTL_ADDR_MASK (0x7FFF << I40E_GLNVM_SRCTL_ADDR_SHIFT)
+#define I40E_GLNVM_SRCTL_WRITE_SHIFT 29
+#define I40E_GLNVM_SRCTL_WRITE_MASK (0x1 << I40E_GLNVM_SRCTL_WRITE_SHIFT)
+#define I40E_GLNVM_SRCTL_START_SHIFT 30
+#define I40E_GLNVM_SRCTL_START_MASK (0x1 << I40E_GLNVM_SRCTL_START_SHIFT)
+#define I40E_GLNVM_SRCTL_DONE_SHIFT 31
+#define I40E_GLNVM_SRCTL_DONE_MASK (0x1 << I40E_GLNVM_SRCTL_DONE_SHIFT)
+#define I40E_GLNVM_SRDATA 0x000B6114
+#define I40E_GLNVM_SRDATA_WRDATA_SHIFT 0
+#define I40E_GLNVM_SRDATA_WRDATA_MASK (0xFFFF << I40E_GLNVM_SRDATA_WRDATA_SHIFT)
+#define I40E_GLNVM_SRDATA_RDDATA_SHIFT 16
+#define I40E_GLNVM_SRDATA_RDDATA_MASK (0xFFFF << I40E_GLNVM_SRDATA_RDDATA_SHIFT)
+#define I40E_GLPCI_BYTCTH 0x0009C484
+#define I40E_GLPCI_BYTCTH_PCI_COUNT_BW_BCT_SHIFT 0
+#define I40E_GLPCI_BYTCTH_PCI_COUNT_BW_BCT_MASK (0xFFFFFFFF << I40E_GLPCI_BYTCTH_PCI_COUNT_BW_BCT_SHIFT)
+#define I40E_GLPCI_BYTCTL 0x0009C488
+#define I40E_GLPCI_BYTCTL_PCI_COUNT_BW_BCT_SHIFT 0
+#define I40E_GLPCI_BYTCTL_PCI_COUNT_BW_BCT_MASK (0xFFFFFFFF << I40E_GLPCI_BYTCTL_PCI_COUNT_BW_BCT_SHIFT)
+#define I40E_GLPCI_CAPCTRL 0x000BE4A4
+#define I40E_GLPCI_CAPCTRL_VPD_EN_SHIFT 0
+#define I40E_GLPCI_CAPCTRL_VPD_EN_MASK (0x1 << I40E_GLPCI_CAPCTRL_VPD_EN_SHIFT)
+#define I40E_GLPCI_CAPSUP 0x000BE4A8
+#define I40E_GLPCI_CAPSUP_PCIE_VER_SHIFT 0
+#define I40E_GLPCI_CAPSUP_PCIE_VER_MASK (0x1 << I40E_GLPCI_CAPSUP_PCIE_VER_SHIFT)
+#define I40E_GLPCI_CAPSUP_LTR_EN_SHIFT 2
+#define I40E_GLPCI_CAPSUP_LTR_EN_MASK (0x1 << I40E_GLPCI_CAPSUP_LTR_EN_SHIFT)
+#define I40E_GLPCI_CAPSUP_TPH_EN_SHIFT 3
+#define I40E_GLPCI_CAPSUP_TPH_EN_MASK (0x1 << I40E_GLPCI_CAPSUP_TPH_EN_SHIFT)
+#define I40E_GLPCI_CAPSUP_ARI_EN_SHIFT 4
+#define I40E_GLPCI_CAPSUP_ARI_EN_MASK (0x1 << I40E_GLPCI_CAPSUP_ARI_EN_SHIFT)
+#define I40E_GLPCI_CAPSUP_IOV_EN_SHIFT 5
+#define I40E_GLPCI_CAPSUP_IOV_EN_MASK (0x1 << I40E_GLPCI_CAPSUP_IOV_EN_SHIFT)
+#define I40E_GLPCI_CAPSUP_ACS_EN_SHIFT 6
+#define I40E_GLPCI_CAPSUP_ACS_EN_MASK (0x1 << I40E_GLPCI_CAPSUP_ACS_EN_SHIFT)
+#define I40E_GLPCI_CAPSUP_SEC_EN_SHIFT 7
+#define I40E_GLPCI_CAPSUP_SEC_EN_MASK (0x1 << I40E_GLPCI_CAPSUP_SEC_EN_SHIFT)
+#define I40E_GLPCI_CAPSUP_ECRC_GEN_EN_SHIFT 16
+#define I40E_GLPCI_CAPSUP_ECRC_GEN_EN_MASK (0x1 << I40E_GLPCI_CAPSUP_ECRC_GEN_EN_SHIFT)
+#define I40E_GLPCI_CAPSUP_ECRC_CHK_EN_SHIFT 17
+#define I40E_GLPCI_CAPSUP_ECRC_CHK_EN_MASK (0x1 << I40E_GLPCI_CAPSUP_ECRC_CHK_EN_SHIFT)
+#define I40E_GLPCI_CAPSUP_IDO_EN_SHIFT 18
+#define I40E_GLPCI_CAPSUP_IDO_EN_MASK (0x1 << I40E_GLPCI_CAPSUP_IDO_EN_SHIFT)
+#define I40E_GLPCI_CAPSUP_MSI_MASK_SHIFT 19
+#define I40E_GLPCI_CAPSUP_MSI_MASK_MASK (0x1 << I40E_GLPCI_CAPSUP_MSI_MASK_SHIFT)
+#define I40E_GLPCI_CAPSUP_CSR_CONF_EN_SHIFT 20
+#define I40E_GLPCI_CAPSUP_CSR_CONF_EN_MASK (0x1 << I40E_GLPCI_CAPSUP_CSR_CONF_EN_SHIFT)
+#define I40E_GLPCI_CAPSUP_LOAD_SUBSYS_ID_SHIFT 30
+#define I40E_GLPCI_CAPSUP_LOAD_SUBSYS_ID_MASK (0x1 << I40E_GLPCI_CAPSUP_LOAD_SUBSYS_ID_SHIFT)
+#define I40E_GLPCI_CAPSUP_LOAD_DEV_ID_SHIFT 31
+#define I40E_GLPCI_CAPSUP_LOAD_DEV_ID_MASK (0x1 << I40E_GLPCI_CAPSUP_LOAD_DEV_ID_SHIFT)
+#define I40E_GLPCI_CNF 0x000BE4C0
+#define I40E_GLPCI_CNF_FLEX10_SHIFT 1
+#define I40E_GLPCI_CNF_FLEX10_MASK (0x1 << I40E_GLPCI_CNF_FLEX10_SHIFT)
+#define I40E_GLPCI_CNF_WAKE_PIN_EN_SHIFT 2
+#define I40E_GLPCI_CNF_WAKE_PIN_EN_MASK (0x1 << I40E_GLPCI_CNF_WAKE_PIN_EN_SHIFT)
+#define I40E_GLPCI_CNF2 0x000BE494
+#define I40E_GLPCI_CNF2_RO_DIS_SHIFT 0
+#define I40E_GLPCI_CNF2_RO_DIS_MASK (0x1 << I40E_GLPCI_CNF2_RO_DIS_SHIFT)
+#define I40E_GLPCI_CNF2_CACHELINE_SIZE_SHIFT 1
+#define I40E_GLPCI_CNF2_CACHELINE_SIZE_MASK (0x1 << I40E_GLPCI_CNF2_CACHELINE_SIZE_SHIFT)
+#define I40E_GLPCI_CNF2_MSI_X_PF_N_SHIFT 2
+#define I40E_GLPCI_CNF2_MSI_X_PF_N_MASK (0x7FF << I40E_GLPCI_CNF2_MSI_X_PF_N_SHIFT)
+#define I40E_GLPCI_CNF2_MSI_X_VF_N_SHIFT 13
+#define I40E_GLPCI_CNF2_MSI_X_VF_N_MASK (0x7FF << I40E_GLPCI_CNF2_MSI_X_VF_N_SHIFT)
+#define I40E_GLPCI_DREVID 0x0009C480
+#define I40E_GLPCI_DREVID_DEFAULT_REVID_SHIFT 0
+#define I40E_GLPCI_DREVID_DEFAULT_REVID_MASK (0xFF << I40E_GLPCI_DREVID_DEFAULT_REVID_SHIFT)
+#define I40E_GLPCI_GSCL_1 0x0009C48C
+#define I40E_GLPCI_GSCL_1_GIO_COUNT_EN_0_SHIFT 0
+#define I40E_GLPCI_GSCL_1_GIO_COUNT_EN_0_MASK (0x1 << I40E_GLPCI_GSCL_1_GIO_COUNT_EN_0_SHIFT)
+#define I40E_GLPCI_GSCL_1_GIO_COUNT_EN_1_SHIFT 1
+#define I40E_GLPCI_GSCL_1_GIO_COUNT_EN_1_MASK (0x1 << I40E_GLPCI_GSCL_1_GIO_COUNT_EN_1_SHIFT)
+#define I40E_GLPCI_GSCL_1_GIO_COUNT_EN_2_SHIFT 2
+#define I40E_GLPCI_GSCL_1_GIO_COUNT_EN_2_MASK (0x1 << I40E_GLPCI_GSCL_1_GIO_COUNT_EN_2_SHIFT)
+#define I40E_GLPCI_GSCL_1_GIO_COUNT_EN_3_SHIFT 3
+#define I40E_GLPCI_GSCL_1_GIO_COUNT_EN_3_MASK (0x1 << I40E_GLPCI_GSCL_1_GIO_COUNT_EN_3_SHIFT)
+#define I40E_GLPCI_GSCL_1_LBC_ENABLE_0_SHIFT 4
+#define I40E_GLPCI_GSCL_1_LBC_ENABLE_0_MASK (0x1 << I40E_GLPCI_GSCL_1_LBC_ENABLE_0_SHIFT)
+#define I40E_GLPCI_GSCL_1_LBC_ENABLE_1_SHIFT 5
+#define I40E_GLPCI_GSCL_1_LBC_ENABLE_1_MASK (0x1 << I40E_GLPCI_GSCL_1_LBC_ENABLE_1_SHIFT)
+#define I40E_GLPCI_GSCL_1_LBC_ENABLE_2_SHIFT 6
+#define I40E_GLPCI_GSCL_1_LBC_ENABLE_2_MASK (0x1 << I40E_GLPCI_GSCL_1_LBC_ENABLE_2_SHIFT)
+#define I40E_GLPCI_GSCL_1_LBC_ENABLE_3_SHIFT 7
+#define I40E_GLPCI_GSCL_1_LBC_ENABLE_3_MASK (0x1 << I40E_GLPCI_GSCL_1_LBC_ENABLE_3_SHIFT)
+#define I40E_GLPCI_GSCL_1_PCI_COUNT_LAT_EN_SHIFT 8
+#define I40E_GLPCI_GSCL_1_PCI_COUNT_LAT_EN_MASK (0x1 << I40E_GLPCI_GSCL_1_PCI_COUNT_LAT_EN_SHIFT)
+#define I40E_GLPCI_GSCL_1_PCI_COUNT_LAT_EV_SHIFT 9
+#define I40E_GLPCI_GSCL_1_PCI_COUNT_LAT_EV_MASK (0x1F << I40E_GLPCI_GSCL_1_PCI_COUNT_LAT_EV_SHIFT)
+#define I40E_GLPCI_GSCL_1_PCI_COUNT_BW_EN_SHIFT 14
+#define I40E_GLPCI_GSCL_1_PCI_COUNT_BW_EN_MASK (0x1 << I40E_GLPCI_GSCL_1_PCI_COUNT_BW_EN_SHIFT)
+#define I40E_GLPCI_GSCL_1_PCI_COUNT_BW_EV_SHIFT 15
+#define I40E_GLPCI_GSCL_1_PCI_COUNT_BW_EV_MASK (0x1F << I40E_GLPCI_GSCL_1_PCI_COUNT_BW_EV_SHIFT)
+#define I40E_GLPCI_GSCL_1_GIO_64_BIT_EN_SHIFT 28
+#define I40E_GLPCI_GSCL_1_GIO_64_BIT_EN_MASK (0x1 << I40E_GLPCI_GSCL_1_GIO_64_BIT_EN_SHIFT)
+#define I40E_GLPCI_GSCL_1_GIO_COUNT_RESET_SHIFT 29
+#define I40E_GLPCI_GSCL_1_GIO_COUNT_RESET_MASK (0x1 << I40E_GLPCI_GSCL_1_GIO_COUNT_RESET_SHIFT)
+#define I40E_GLPCI_GSCL_1_GIO_COUNT_STOP_SHIFT 30
+#define I40E_GLPCI_GSCL_1_GIO_COUNT_STOP_MASK (0x1 << I40E_GLPCI_GSCL_1_GIO_COUNT_STOP_SHIFT)
+#define I40E_GLPCI_GSCL_1_GIO_COUNT_START_SHIFT 31
+#define I40E_GLPCI_GSCL_1_GIO_COUNT_START_MASK (0x1 << I40E_GLPCI_GSCL_1_GIO_COUNT_START_SHIFT)
+#define I40E_GLPCI_GSCL_2 0x0009C490
+#define I40E_GLPCI_GSCL_2_GIO_EVENT_NUM_0_SHIFT 0
+#define I40E_GLPCI_GSCL_2_GIO_EVENT_NUM_0_MASK (0xFF << I40E_GLPCI_GSCL_2_GIO_EVENT_NUM_0_SHIFT)
+#define I40E_GLPCI_GSCL_2_GIO_EVENT_NUM_1_SHIFT 8
+#define I40E_GLPCI_GSCL_2_GIO_EVENT_NUM_1_MASK (0xFF << I40E_GLPCI_GSCL_2_GIO_EVENT_NUM_1_SHIFT)
+#define I40E_GLPCI_GSCL_2_GIO_EVENT_NUM_2_SHIFT 16
+#define I40E_GLPCI_GSCL_2_GIO_EVENT_NUM_2_MASK (0xFF << I40E_GLPCI_GSCL_2_GIO_EVENT_NUM_2_SHIFT)
+#define I40E_GLPCI_GSCL_2_GIO_EVENT_NUM_3_SHIFT 24
+#define I40E_GLPCI_GSCL_2_GIO_EVENT_NUM_3_MASK (0xFF << I40E_GLPCI_GSCL_2_GIO_EVENT_NUM_3_SHIFT)
+#define I40E_GLPCI_GSCL_5_8(_i) (0x0009C494 + ((_i) * 4)) /* _i=0...3 */
+#define I40E_GLPCI_GSCL_5_8_MAX_INDEX 3
+#define I40E_GLPCI_GSCL_5_8_LBC_THRESHOLD_N_SHIFT 0
+#define I40E_GLPCI_GSCL_5_8_LBC_THRESHOLD_N_MASK (0xFFFF << I40E_GLPCI_GSCL_5_8_LBC_THRESHOLD_N_SHIFT)
+#define I40E_GLPCI_GSCL_5_8_LBC_TIMER_N_SHIFT 16
+#define I40E_GLPCI_GSCL_5_8_LBC_TIMER_N_MASK (0xFFFF << I40E_GLPCI_GSCL_5_8_LBC_TIMER_N_SHIFT)
+#define I40E_GLPCI_GSCN_0_3(_i) (0x0009C4A4 + ((_i) * 4)) /* _i=0...3 */
+#define I40E_GLPCI_GSCN_0_3_MAX_INDEX 3
+#define I40E_GLPCI_GSCN_0_3_EVENT_COUNTER_SHIFT 0
+#define I40E_GLPCI_GSCN_0_3_EVENT_COUNTER_MASK (0xFFFFFFFF << I40E_GLPCI_GSCN_0_3_EVENT_COUNTER_SHIFT)
+#define I40E_GLPCI_LATCT 0x0009C4B4
+#define I40E_GLPCI_LATCT_PCI_COUNT_LAT_CT_SHIFT 0
+#define I40E_GLPCI_LATCT_PCI_COUNT_LAT_CT_MASK (0xFFFFFFFF << I40E_GLPCI_LATCT_PCI_COUNT_LAT_CT_SHIFT)
+#define I40E_GLPCI_LBARCTRL 0x000BE484
+#define I40E_GLPCI_LBARCTRL_PREFBAR_SHIFT 0
+#define I40E_GLPCI_LBARCTRL_PREFBAR_MASK (0x1 << I40E_GLPCI_LBARCTRL_PREFBAR_SHIFT)
+#define I40E_GLPCI_LBARCTRL_BAR32_SHIFT 1
+#define I40E_GLPCI_LBARCTRL_BAR32_MASK (0x1 << I40E_GLPCI_LBARCTRL_BAR32_SHIFT)
+#define I40E_GLPCI_LBARCTRL_FLASH_EXPOSE_SHIFT 3
+#define I40E_GLPCI_LBARCTRL_FLASH_EXPOSE_MASK (0x1 << I40E_GLPCI_LBARCTRL_FLASH_EXPOSE_SHIFT)
+#define I40E_GLPCI_LBARCTRL_PE_DB_SIZE_SHIFT 4
+#define I40E_GLPCI_LBARCTRL_PE_DB_SIZE_MASK (0x3 << I40E_GLPCI_LBARCTRL_PE_DB_SIZE_SHIFT)
+#define I40E_GLPCI_LBARCTRL_FL_SIZE_SHIFT 6
+#define I40E_GLPCI_LBARCTRL_FL_SIZE_MASK (0x7 << I40E_GLPCI_LBARCTRL_FL_SIZE_SHIFT)
+#define I40E_GLPCI_LBARCTRL_VF_PE_DB_SIZE_SHIFT 10
+#define I40E_GLPCI_LBARCTRL_VF_PE_DB_SIZE_MASK (0x1 << I40E_GLPCI_LBARCTRL_VF_PE_DB_SIZE_SHIFT)
+#define I40E_GLPCI_LBARCTRL_EXROM_SIZE_SHIFT 11
+#define I40E_GLPCI_LBARCTRL_EXROM_SIZE_MASK (0x7 << I40E_GLPCI_LBARCTRL_EXROM_SIZE_SHIFT)
+#define I40E_GLPCI_LINKCAP 0x000BE4AC
+#define I40E_GLPCI_LINKCAP_LINK_SPEEDS_VECTOR_SHIFT 0
+#define I40E_GLPCI_LINKCAP_LINK_SPEEDS_VECTOR_MASK (0x3F << I40E_GLPCI_LINKCAP_LINK_SPEEDS_VECTOR_SHIFT)
+#define I40E_GLPCI_LINKCAP_MAX_PAYLOAD_SHIFT 6
+#define I40E_GLPCI_LINKCAP_MAX_PAYLOAD_MASK (0x7 << I40E_GLPCI_LINKCAP_MAX_PAYLOAD_SHIFT)
+#define I40E_GLPCI_LINKCAP_MAX_LINK_WIDTH_SHIFT 9
+#define I40E_GLPCI_LINKCAP_MAX_LINK_WIDTH_MASK (0xF << I40E_GLPCI_LINKCAP_MAX_LINK_WIDTH_SHIFT)
+#define I40E_GLPCI_PCIERR 0x000BE4FC
+#define I40E_GLPCI_PCIERR_PCIE_ERR_REP_SHIFT 0
+#define I40E_GLPCI_PCIERR_PCIE_ERR_REP_MASK (0xFFFFFFFF << I40E_GLPCI_PCIERR_PCIE_ERR_REP_SHIFT)
+#define I40E_GLPCI_PKTCT 0x0009C4BC
+#define I40E_GLPCI_PKTCT_PCI_COUNT_BW_PCT_SHIFT 0
+#define I40E_GLPCI_PKTCT_PCI_COUNT_BW_PCT_MASK (0xFFFFFFFF << I40E_GLPCI_PKTCT_PCI_COUNT_BW_PCT_SHIFT)
+#define I40E_GLPCI_PMSUP 0x000BE4B0
+#define I40E_GLPCI_PMSUP_ASPM_SUP_SHIFT 0
+#define I40E_GLPCI_PMSUP_ASPM_SUP_MASK (0x3 << I40E_GLPCI_PMSUP_ASPM_SUP_SHIFT)
+#define I40E_GLPCI_PMSUP_L0S_EXIT_LAT_SHIFT 2
+#define I40E_GLPCI_PMSUP_L0S_EXIT_LAT_MASK (0x7 << I40E_GLPCI_PMSUP_L0S_EXIT_LAT_SHIFT)
+#define I40E_GLPCI_PMSUP_L1_EXIT_LAT_SHIFT 5
+#define I40E_GLPCI_PMSUP_L1_EXIT_LAT_MASK (0x7 << I40E_GLPCI_PMSUP_L1_EXIT_LAT_SHIFT)
+#define I40E_GLPCI_PMSUP_L0S_ACC_LAT_SHIFT 8
+#define I40E_GLPCI_PMSUP_L0S_ACC_LAT_MASK (0x7 << I40E_GLPCI_PMSUP_L0S_ACC_LAT_SHIFT)
+#define I40E_GLPCI_PMSUP_L1_ACC_LAT_SHIFT 11
+#define I40E_GLPCI_PMSUP_L1_ACC_LAT_MASK (0x7 << I40E_GLPCI_PMSUP_L1_ACC_LAT_SHIFT)
+#define I40E_GLPCI_PMSUP_SLOT_CLK_SHIFT 14
+#define I40E_GLPCI_PMSUP_SLOT_CLK_MASK (0x1 << I40E_GLPCI_PMSUP_SLOT_CLK_SHIFT)
+#define I40E_GLPCI_PMSUP_OBFF_SUP_SHIFT 15
+#define I40E_GLPCI_PMSUP_OBFF_SUP_MASK (0x3 << I40E_GLPCI_PMSUP_OBFF_SUP_SHIFT)
+#define I40E_GLPCI_PWRDATA 0x000BE490
+#define I40E_GLPCI_PWRDATA_D0_POWER_SHIFT 0
+#define I40E_GLPCI_PWRDATA_D0_POWER_MASK (0xFF << I40E_GLPCI_PWRDATA_D0_POWER_SHIFT)
+#define I40E_GLPCI_PWRDATA_COMM_POWER_SHIFT 8
+#define I40E_GLPCI_PWRDATA_COMM_POWER_MASK (0xFF << I40E_GLPCI_PWRDATA_COMM_POWER_SHIFT)
+#define I40E_GLPCI_PWRDATA_D3_POWER_SHIFT 16
+#define I40E_GLPCI_PWRDATA_D3_POWER_MASK (0xFF << I40E_GLPCI_PWRDATA_D3_POWER_SHIFT)
+#define I40E_GLPCI_PWRDATA_DATA_SCALE_SHIFT 24
+#define I40E_GLPCI_PWRDATA_DATA_SCALE_MASK (0x3 << I40E_GLPCI_PWRDATA_DATA_SCALE_SHIFT)
+#define I40E_GLPCI_REVID 0x000BE4B4
+#define I40E_GLPCI_REVID_NVM_REVID_SHIFT 0
+#define I40E_GLPCI_REVID_NVM_REVID_MASK (0xFF << I40E_GLPCI_REVID_NVM_REVID_SHIFT)
+#define I40E_GLPCI_SERH 0x000BE49C
+#define I40E_GLPCI_SERH_SER_NUM_H_SHIFT 0
+#define I40E_GLPCI_SERH_SER_NUM_H_MASK (0xFFFF << I40E_GLPCI_SERH_SER_NUM_H_SHIFT)
+#define I40E_GLPCI_SERL 0x000BE498
+#define I40E_GLPCI_SERL_SER_NUM_L_SHIFT 0
+#define I40E_GLPCI_SERL_SER_NUM_L_MASK (0xFFFFFFFF << I40E_GLPCI_SERL_SER_NUM_L_SHIFT)
+#define I40E_GLPCI_SUBSYSID 0x000BE48C
+#define I40E_GLPCI_SUBSYSID_SUB_VEN_ID_SHIFT 0
+#define I40E_GLPCI_SUBSYSID_SUB_VEN_ID_MASK (0xFFFF << I40E_GLPCI_SUBSYSID_SUB_VEN_ID_SHIFT)
+#define I40E_GLPCI_SUBSYSID_SUB_ID_SHIFT 16
+#define I40E_GLPCI_SUBSYSID_SUB_ID_MASK (0xFFFF << I40E_GLPCI_SUBSYSID_SUB_ID_SHIFT)
+#define I40E_GLPCI_UPADD 0x000BE4F8
+#define I40E_GLPCI_UPADD_ADDRESS_SHIFT 1
+#define I40E_GLPCI_UPADD_ADDRESS_MASK (0x7FFFFFFF << I40E_GLPCI_UPADD_ADDRESS_SHIFT)
+#define I40E_GLPCI_VFSUP 0x000BE4B8
+#define I40E_GLPCI_VFSUP_VF_PREFETCH_SHIFT 0
+#define I40E_GLPCI_VFSUP_VF_PREFETCH_MASK (0x1 << I40E_GLPCI_VFSUP_VF_PREFETCH_SHIFT)
+#define I40E_GLPCI_VFSUP_VR_BAR_TYPE_SHIFT 1
+#define I40E_GLPCI_VFSUP_VR_BAR_TYPE_MASK (0x1 << I40E_GLPCI_VFSUP_VR_BAR_TYPE_SHIFT)
+#define I40E_PF_FUNC_RID 0x0009C000
+#define I40E_PF_FUNC_RID_FUNCTION_NUMBER_SHIFT 0
+#define I40E_PF_FUNC_RID_FUNCTION_NUMBER_MASK (0x7 << I40E_PF_FUNC_RID_FUNCTION_NUMBER_SHIFT)
+#define I40E_PF_FUNC_RID_DEVICE_NUMBER_SHIFT 3
+#define I40E_PF_FUNC_RID_DEVICE_NUMBER_MASK (0x1F << I40E_PF_FUNC_RID_DEVICE_NUMBER_SHIFT)
+#define I40E_PF_FUNC_RID_BUS_NUMBER_SHIFT 8
+#define I40E_PF_FUNC_RID_BUS_NUMBER_MASK (0xFF << I40E_PF_FUNC_RID_BUS_NUMBER_SHIFT)
+#define I40E_PF_PCI_CIAA 0x0009C080
+#define I40E_PF_PCI_CIAA_ADDRESS_SHIFT 0
+#define I40E_PF_PCI_CIAA_ADDRESS_MASK (0xFFF << I40E_PF_PCI_CIAA_ADDRESS_SHIFT)
+#define I40E_PF_PCI_CIAA_VF_NUM_SHIFT 12
+#define I40E_PF_PCI_CIAA_VF_NUM_MASK (0x7F << I40E_PF_PCI_CIAA_VF_NUM_SHIFT)
+#define I40E_PF_PCI_CIAD 0x0009C100
+#define I40E_PF_PCI_CIAD_DATA_SHIFT 0
+#define I40E_PF_PCI_CIAD_DATA_MASK (0xFFFFFFFF << I40E_PF_PCI_CIAD_DATA_SHIFT)
+#define I40E_PFPCI_CLASS 0x000BE400
+#define I40E_PFPCI_CLASS_STORAGE_CLASS_SHIFT 0
+#define I40E_PFPCI_CLASS_STORAGE_CLASS_MASK (0x1 << I40E_PFPCI_CLASS_STORAGE_CLASS_SHIFT)
+#define I40E_PFPCI_CNF 0x000BE000
+#define I40E_PFPCI_CNF_MSI_EN_SHIFT 2
+#define I40E_PFPCI_CNF_MSI_EN_MASK (0x1 << I40E_PFPCI_CNF_MSI_EN_SHIFT)
+#define I40E_PFPCI_CNF_EXROM_DIS_SHIFT 3
+#define I40E_PFPCI_CNF_EXROM_DIS_MASK (0x1 << I40E_PFPCI_CNF_EXROM_DIS_SHIFT)
+#define I40E_PFPCI_CNF_IO_BAR_SHIFT 4
+#define I40E_PFPCI_CNF_IO_BAR_MASK (0x1 << I40E_PFPCI_CNF_IO_BAR_SHIFT)
+#define I40E_PFPCI_CNF_INT_PIN_SHIFT 5
+#define I40E_PFPCI_CNF_INT_PIN_MASK (0x3 << I40E_PFPCI_CNF_INT_PIN_SHIFT)
+#define I40E_PFPCI_FACTPS 0x0009C180
+#define I40E_PFPCI_FACTPS_FUNC_POWER_STATE_SHIFT 0
+#define I40E_PFPCI_FACTPS_FUNC_POWER_STATE_MASK (0x3 << I40E_PFPCI_FACTPS_FUNC_POWER_STATE_SHIFT)
+#define I40E_PFPCI_FACTPS_FUNC_AUX_EN_SHIFT 3
+#define I40E_PFPCI_FACTPS_FUNC_AUX_EN_MASK (0x1 << I40E_PFPCI_FACTPS_FUNC_AUX_EN_SHIFT)
+#define I40E_PFPCI_FUNC 0x000BE200
+#define I40E_PFPCI_FUNC_FUNC_DIS_SHIFT 0
+#define I40E_PFPCI_FUNC_FUNC_DIS_MASK (0x1 << I40E_PFPCI_FUNC_FUNC_DIS_SHIFT)
+#define I40E_PFPCI_FUNC_ALLOW_FUNC_DIS_SHIFT 1
+#define I40E_PFPCI_FUNC_ALLOW_FUNC_DIS_MASK (0x1 << I40E_PFPCI_FUNC_ALLOW_FUNC_DIS_SHIFT)
+#define I40E_PFPCI_FUNC_DIS_FUNC_ON_PORT_DIS_SHIFT 2
+#define I40E_PFPCI_FUNC_DIS_FUNC_ON_PORT_DIS_MASK (0x1 << I40E_PFPCI_FUNC_DIS_FUNC_ON_PORT_DIS_SHIFT)
+#define I40E_PFPCI_FUNC2 0x000BE180
+#define I40E_PFPCI_FUNC2_EMP_FUNC_DIS_SHIFT 0
+#define I40E_PFPCI_FUNC2_EMP_FUNC_DIS_MASK (0x1 << I40E_PFPCI_FUNC2_EMP_FUNC_DIS_SHIFT)
+#define I40E_PFPCI_ICAUSE 0x0009C200
+#define I40E_PFPCI_ICAUSE_PCIE_ERR_CAUSE_SHIFT 0
+#define I40E_PFPCI_ICAUSE_PCIE_ERR_CAUSE_MASK (0xFFFFFFFF << I40E_PFPCI_ICAUSE_PCIE_ERR_CAUSE_SHIFT)
+#define I40E_PFPCI_IENA 0x0009C280
+#define I40E_PFPCI_IENA_PCIE_ERR_EN_SHIFT 0
+#define I40E_PFPCI_IENA_PCIE_ERR_EN_MASK (0xFFFFFFFF << I40E_PFPCI_IENA_PCIE_ERR_EN_SHIFT)
+#define I40E_PFPCI_PFDEVID 0x000BE080
+#define I40E_PFPCI_PFDEVID_PF_DEV_ID_LAN_SHIFT 0
+#define I40E_PFPCI_PFDEVID_PF_DEV_ID_LAN_MASK (0xFFFF << I40E_PFPCI_PFDEVID_PF_DEV_ID_LAN_SHIFT)
+#define I40E_PFPCI_PFDEVID_PF_DEV_ID_SAN_SHIFT 16
+#define I40E_PFPCI_PFDEVID_PF_DEV_ID_SAN_MASK (0xFFFF << I40E_PFPCI_PFDEVID_PF_DEV_ID_SAN_SHIFT)
+#define I40E_PFPCI_PM 0x000BE300
+#define I40E_PFPCI_PM_PME_EN_SHIFT 0
+#define I40E_PFPCI_PM_PME_EN_MASK (0x1 << I40E_PFPCI_PM_PME_EN_SHIFT)
+#define I40E_PFPCI_STATUS1 0x000BE280
+#define I40E_PFPCI_STATUS1_FUNC_VALID_SHIFT 0
+#define I40E_PFPCI_STATUS1_FUNC_VALID_MASK (0x1 << I40E_PFPCI_STATUS1_FUNC_VALID_SHIFT)
+#define I40E_PFPCI_VFDEVID 0x000BE100
+#define I40E_PFPCI_VFDEVID_VF_DEV_ID_LAN_SHIFT 0
+#define I40E_PFPCI_VFDEVID_VF_DEV_ID_LAN_MASK (0xFFFF << I40E_PFPCI_VFDEVID_VF_DEV_ID_LAN_SHIFT)
+#define I40E_PFPCI_VFDEVID_VF_DEV_ID_SAN_SHIFT 16
+#define I40E_PFPCI_VFDEVID_VF_DEV_ID_SAN_MASK (0xFFFF << I40E_PFPCI_VFDEVID_VF_DEV_ID_SAN_SHIFT)
+#define I40E_PFPCI_VMINDEX 0x0009C300
+#define I40E_PFPCI_VMINDEX_VMINDEX_SHIFT 0
+#define I40E_PFPCI_VMINDEX_VMINDEX_MASK (0x1FF << I40E_PFPCI_VMINDEX_VMINDEX_SHIFT)
+#define I40E_PFPCI_VMPEND 0x0009C380
+#define I40E_PFPCI_VMPEND_PENDING_SHIFT 0
+#define I40E_PFPCI_VMPEND_PENDING_MASK (0x1 << I40E_PFPCI_VMPEND_PENDING_SHIFT)
+#define I40E_GLPE_CPUSTATUS0 0x0000D040
+#define I40E_GLPE_CPUSTATUS0_PECPUSTATUS0_SHIFT 0
+#define I40E_GLPE_CPUSTATUS0_PECPUSTATUS0_MASK (0xFFFFFFFF << I40E_GLPE_CPUSTATUS0_PECPUSTATUS0_SHIFT)
+#define I40E_GLPE_CPUSTATUS1 0x0000D044
+#define I40E_GLPE_CPUSTATUS1_PECPUSTATUS1_SHIFT 0
+#define I40E_GLPE_CPUSTATUS1_PECPUSTATUS1_MASK (0xFFFFFFFF << I40E_GLPE_CPUSTATUS1_PECPUSTATUS1_SHIFT)
+#define I40E_GLPE_CPUSTATUS2 0x0000D048
+#define I40E_GLPE_CPUSTATUS2_PECPUSTATUS2_SHIFT 0
+#define I40E_GLPE_CPUSTATUS2_PECPUSTATUS2_MASK (0xFFFFFFFF << I40E_GLPE_CPUSTATUS2_PECPUSTATUS2_SHIFT)
+#define I40E_GLPE_PFFLMOBJCTRL(_i) (0x0000D480 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLPE_PFFLMOBJCTRL_MAX_INDEX 15
+#define I40E_GLPE_PFFLMOBJCTRL_XMIT_BLOCKSIZE_SHIFT 0
+#define I40E_GLPE_PFFLMOBJCTRL_XMIT_BLOCKSIZE_MASK (0x7 << I40E_GLPE_PFFLMOBJCTRL_XMIT_BLOCKSIZE_SHIFT)
+#define I40E_GLPE_PFFLMOBJCTRL_Q1_BLOCKSIZE_SHIFT 8
+#define I40E_GLPE_PFFLMOBJCTRL_Q1_BLOCKSIZE_MASK (0x7 << I40E_GLPE_PFFLMOBJCTRL_Q1_BLOCKSIZE_SHIFT)
+#define I40E_GLPE_VFFLMOBJCTRL(_i) (0x0000D400 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPE_VFFLMOBJCTRL_MAX_INDEX 31
+#define I40E_GLPE_VFFLMOBJCTRL_XMIT_BLOCKSIZE_SHIFT 0
+#define I40E_GLPE_VFFLMOBJCTRL_XMIT_BLOCKSIZE_MASK (0x7 << I40E_GLPE_VFFLMOBJCTRL_XMIT_BLOCKSIZE_SHIFT)
+#define I40E_GLPE_VFFLMOBJCTRL_Q1_BLOCKSIZE_SHIFT 8
+#define I40E_GLPE_VFFLMOBJCTRL_Q1_BLOCKSIZE_MASK (0x7 << I40E_GLPE_VFFLMOBJCTRL_Q1_BLOCKSIZE_SHIFT)
+#define I40E_GLPE_VFFLMQ1ALLOCERR(_i) (0x0000C700 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPE_VFFLMQ1ALLOCERR_MAX_INDEX 31
+#define I40E_GLPE_VFFLMQ1ALLOCERR_ERROR_COUNT_SHIFT 0
+#define I40E_GLPE_VFFLMQ1ALLOCERR_ERROR_COUNT_MASK (0xFFFF << I40E_GLPE_VFFLMQ1ALLOCERR_ERROR_COUNT_SHIFT)
+#define I40E_GLPE_VFFLMXMITALLOCERR(_i) (0x0000C600 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPE_VFFLMXMITALLOCERR_MAX_INDEX 31
+#define I40E_GLPE_VFFLMXMITALLOCERR_ERROR_COUNT_SHIFT 0
+#define I40E_GLPE_VFFLMXMITALLOCERR_ERROR_COUNT_MASK (0xFFFF << I40E_GLPE_VFFLMXMITALLOCERR_ERROR_COUNT_SHIFT)
+#define I40E_GLPE_VFUDACTRL(_i) (0x0000C000 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPE_VFUDACTRL_MAX_INDEX 31
+#define I40E_GLPE_VFUDACTRL_IPV4MCFRAGRESBP_SHIFT 0
+#define I40E_GLPE_VFUDACTRL_IPV4MCFRAGRESBP_MASK (0x1 << I40E_GLPE_VFUDACTRL_IPV4MCFRAGRESBP_SHIFT)
+#define I40E_GLPE_VFUDACTRL_IPV4UCFRAGRESBP_SHIFT 1
+#define I40E_GLPE_VFUDACTRL_IPV4UCFRAGRESBP_MASK (0x1 << I40E_GLPE_VFUDACTRL_IPV4UCFRAGRESBP_SHIFT)
+#define I40E_GLPE_VFUDACTRL_IPV6MCFRAGRESBP_SHIFT 2
+#define I40E_GLPE_VFUDACTRL_IPV6MCFRAGRESBP_MASK (0x1 << I40E_GLPE_VFUDACTRL_IPV6MCFRAGRESBP_SHIFT)
+#define I40E_GLPE_VFUDACTRL_IPV6UCFRAGRESBP_SHIFT 3
+#define I40E_GLPE_VFUDACTRL_IPV6UCFRAGRESBP_MASK (0x1 << I40E_GLPE_VFUDACTRL_IPV6UCFRAGRESBP_SHIFT)
+#define I40E_GLPE_VFUDACTRL_UDPMCFRAGRESFAIL_SHIFT 4
+#define I40E_GLPE_VFUDACTRL_UDPMCFRAGRESFAIL_MASK (0x1 << I40E_GLPE_VFUDACTRL_UDPMCFRAGRESFAIL_SHIFT)
+#define I40E_GLPE_VFUDAUCFBQPN(_i) (0x0000C100 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPE_VFUDAUCFBQPN_MAX_INDEX 31
+#define I40E_GLPE_VFUDAUCFBQPN_QPN_SHIFT 0
+#define I40E_GLPE_VFUDAUCFBQPN_QPN_MASK (0x3FFFF << I40E_GLPE_VFUDAUCFBQPN_QPN_SHIFT)
+#define I40E_GLPE_VFUDAUCFBQPN_VALID_SHIFT 31
+#define I40E_GLPE_VFUDAUCFBQPN_VALID_MASK (0x1 << I40E_GLPE_VFUDAUCFBQPN_VALID_SHIFT)
+#define I40E_PFPE_AEQALLOC 0x00131180
+#define I40E_PFPE_AEQALLOC_AECOUNT_SHIFT 0
+#define I40E_PFPE_AEQALLOC_AECOUNT_MASK (0xFFFFFFFF << I40E_PFPE_AEQALLOC_AECOUNT_SHIFT)
+#define I40E_PFPE_CCQPHIGH 0x00008200
+#define I40E_PFPE_CCQPHIGH_PECCQPHIGH_SHIFT 0
+#define I40E_PFPE_CCQPHIGH_PECCQPHIGH_MASK (0xFFFFFFFF << I40E_PFPE_CCQPHIGH_PECCQPHIGH_SHIFT)
+#define I40E_PFPE_CCQPLOW 0x00008180
+#define I40E_PFPE_CCQPLOW_PECCQPLOW_SHIFT 0
+#define I40E_PFPE_CCQPLOW_PECCQPLOW_MASK (0xFFFFFFFF << I40E_PFPE_CCQPLOW_PECCQPLOW_SHIFT)
+#define I40E_PFPE_CCQPSTATUS 0x00008100
+#define I40E_PFPE_CCQPSTATUS_CCQP_DONE_SHIFT 0
+#define I40E_PFPE_CCQPSTATUS_CCQP_DONE_MASK (0x1 << I40E_PFPE_CCQPSTATUS_CCQP_DONE_SHIFT)
+#define I40E_PFPE_CCQPSTATUS_CCQP_ERR_SHIFT 31
+#define I40E_PFPE_CCQPSTATUS_CCQP_ERR_MASK (0x1 << I40E_PFPE_CCQPSTATUS_CCQP_ERR_SHIFT)
+#define I40E_PFPE_CQACK 0x00131100
+#define I40E_PFPE_CQACK_PECQID_SHIFT 0
+#define I40E_PFPE_CQACK_PECQID_MASK (0x1FFFF << I40E_PFPE_CQACK_PECQID_SHIFT)
+#define I40E_PFPE_CQARM 0x00131080
+#define I40E_PFPE_CQARM_PECQID_SHIFT 0
+#define I40E_PFPE_CQARM_PECQID_MASK (0x1FFFF << I40E_PFPE_CQARM_PECQID_SHIFT)
+#define I40E_PFPE_CQPDB 0x00008000
+#define I40E_PFPE_CQPDB_WQHEAD_SHIFT 0
+#define I40E_PFPE_CQPDB_WQHEAD_MASK (0x7FF << I40E_PFPE_CQPDB_WQHEAD_SHIFT)
+#define I40E_PFPE_CQPERRCODES 0x00008880
+#define I40E_PFPE_CQPERRCODES_CQP_MINOR_CODE_SHIFT 0
+#define I40E_PFPE_CQPERRCODES_CQP_MINOR_CODE_MASK (0xFFFF << I40E_PFPE_CQPERRCODES_CQP_MINOR_CODE_SHIFT)
+#define I40E_PFPE_CQPERRCODES_CQP_MAJOR_CODE_SHIFT 16
+#define I40E_PFPE_CQPERRCODES_CQP_MAJOR_CODE_MASK (0xFFFF << I40E_PFPE_CQPERRCODES_CQP_MAJOR_CODE_SHIFT)
+#define I40E_PFPE_CQPTAIL 0x00008080
+#define I40E_PFPE_CQPTAIL_WQTAIL_SHIFT 0
+#define I40E_PFPE_CQPTAIL_WQTAIL_MASK (0x7FF << I40E_PFPE_CQPTAIL_WQTAIL_SHIFT)
+#define I40E_PFPE_CQPTAIL_CQP_OP_ERR_SHIFT 31
+#define I40E_PFPE_CQPTAIL_CQP_OP_ERR_MASK (0x1 << I40E_PFPE_CQPTAIL_CQP_OP_ERR_SHIFT)
+#define I40E_PFPE_FLMQ1ALLOCERR 0x00008980
+#define I40E_PFPE_FLMQ1ALLOCERR_ERROR_COUNT_SHIFT 0
+#define I40E_PFPE_FLMQ1ALLOCERR_ERROR_COUNT_MASK (0xFFFF << I40E_PFPE_FLMQ1ALLOCERR_ERROR_COUNT_SHIFT)
+#define I40E_PFPE_FLMXMITALLOCERR 0x00008900
+#define I40E_PFPE_FLMXMITALLOCERR_ERROR_COUNT_SHIFT 0
+#define I40E_PFPE_FLMXMITALLOCERR_ERROR_COUNT_MASK (0xFFFF << I40E_PFPE_FLMXMITALLOCERR_ERROR_COUNT_SHIFT)
+#define I40E_PFPE_IPCONFIG0 0x00008280
+#define I40E_PFPE_IPCONFIG0_PEIPID_SHIFT 0
+#define I40E_PFPE_IPCONFIG0_PEIPID_MASK (0xFFFF << I40E_PFPE_IPCONFIG0_PEIPID_SHIFT)
+#define I40E_PFPE_IPCONFIG0_USEENTIREIDRANGE_SHIFT 16
+#define I40E_PFPE_IPCONFIG0_USEENTIREIDRANGE_MASK (0x1 << I40E_PFPE_IPCONFIG0_USEENTIREIDRANGE_SHIFT)
+#define I40E_PFPE_IPCONFIG0_USEUPPERIDRANGE_SHIFT 17
+#define I40E_PFPE_IPCONFIG0_USEUPPERIDRANGE_MASK (0x1 << I40E_PFPE_IPCONFIG0_USEUPPERIDRANGE_SHIFT)
+#define I40E_PFPE_MRTEIDXMASK 0x00008600
+#define I40E_PFPE_MRTEIDXMASK_MRTEIDXMASKBITS_SHIFT 0
+#define I40E_PFPE_MRTEIDXMASK_MRTEIDXMASKBITS_MASK (0x1F << I40E_PFPE_MRTEIDXMASK_MRTEIDXMASKBITS_SHIFT)
+#define I40E_PFPE_RCVUNEXPECTEDERROR 0x00008680
+#define I40E_PFPE_RCVUNEXPECTEDERROR_TCP_RX_UNEXP_ERR_SHIFT 0
+#define I40E_PFPE_RCVUNEXPECTEDERROR_TCP_RX_UNEXP_ERR_MASK (0xFFFFFF << I40E_PFPE_RCVUNEXPECTEDERROR_TCP_RX_UNEXP_ERR_SHIFT)
+#define I40E_PFPE_TCPNOWTIMER 0x00008580
+#define I40E_PFPE_TCPNOWTIMER_TCP_NOW_SHIFT 0
+#define I40E_PFPE_TCPNOWTIMER_TCP_NOW_MASK (0xFFFFFFFF << I40E_PFPE_TCPNOWTIMER_TCP_NOW_SHIFT)
+#define I40E_PFPE_UDACTRL 0x00008700
+#define I40E_PFPE_UDACTRL_IPV4MCFRAGRESBP_SHIFT 0
+#define I40E_PFPE_UDACTRL_IPV4MCFRAGRESBP_MASK (0x1 << I40E_PFPE_UDACTRL_IPV4MCFRAGRESBP_SHIFT)
+#define I40E_PFPE_UDACTRL_IPV4UCFRAGRESBP_SHIFT 1
+#define I40E_PFPE_UDACTRL_IPV4UCFRAGRESBP_MASK (0x1 << I40E_PFPE_UDACTRL_IPV4UCFRAGRESBP_SHIFT)
+#define I40E_PFPE_UDACTRL_IPV6MCFRAGRESBP_SHIFT 2
+#define I40E_PFPE_UDACTRL_IPV6MCFRAGRESBP_MASK (0x1 << I40E_PFPE_UDACTRL_IPV6MCFRAGRESBP_SHIFT)
+#define I40E_PFPE_UDACTRL_IPV6UCFRAGRESBP_SHIFT 3
+#define I40E_PFPE_UDACTRL_IPV6UCFRAGRESBP_MASK (0x1 << I40E_PFPE_UDACTRL_IPV6UCFRAGRESBP_SHIFT)
+#define I40E_PFPE_UDACTRL_UDPMCFRAGRESFAIL_SHIFT 4
+#define I40E_PFPE_UDACTRL_UDPMCFRAGRESFAIL_MASK (0x1 << I40E_PFPE_UDACTRL_UDPMCFRAGRESFAIL_SHIFT)
+#define I40E_PFPE_UDAUCFBQPN 0x00008780
+#define I40E_PFPE_UDAUCFBQPN_QPN_SHIFT 0
+#define I40E_PFPE_UDAUCFBQPN_QPN_MASK (0x3FFFF << I40E_PFPE_UDAUCFBQPN_QPN_SHIFT)
+#define I40E_PFPE_UDAUCFBQPN_VALID_SHIFT 31
+#define I40E_PFPE_UDAUCFBQPN_VALID_MASK (0x1 << I40E_PFPE_UDAUCFBQPN_VALID_SHIFT)
+#define I40E_PFPE_WQEALLOC 0x00138C00
+#define I40E_PFPE_WQEALLOC_PEQPID_SHIFT 0
+#define I40E_PFPE_WQEALLOC_PEQPID_MASK (0x3FFFF << I40E_PFPE_WQEALLOC_PEQPID_SHIFT)
+#define I40E_PFPE_WQEALLOC_WQE_DESC_INDEX_SHIFT 20
+#define I40E_PFPE_WQEALLOC_WQE_DESC_INDEX_MASK (0xFFF << I40E_PFPE_WQEALLOC_WQE_DESC_INDEX_SHIFT)
+#define I40E_VFPE_AEQALLOC(_VF) (0x00130C00 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VFPE_AEQALLOC_MAX_INDEX 127
+#define I40E_VFPE_AEQALLOC_AECOUNT_SHIFT 0
+#define I40E_VFPE_AEQALLOC_AECOUNT_MASK (0xFFFFFFFF << I40E_VFPE_AEQALLOC_AECOUNT_SHIFT)
+#define I40E_VFPE_CCQPHIGH(_VF) (0x00001000 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VFPE_CCQPHIGH_MAX_INDEX 127
+#define I40E_VFPE_CCQPHIGH_PECCQPHIGH_SHIFT 0
+#define I40E_VFPE_CCQPHIGH_PECCQPHIGH_MASK (0xFFFFFFFF << I40E_VFPE_CCQPHIGH_PECCQPHIGH_SHIFT)
+#define I40E_VFPE_CCQPLOW(_VF) (0x00000C00 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VFPE_CCQPLOW_MAX_INDEX 127
+#define I40E_VFPE_CCQPLOW_PECCQPLOW_SHIFT 0
+#define I40E_VFPE_CCQPLOW_PECCQPLOW_MASK (0xFFFFFFFF << I40E_VFPE_CCQPLOW_PECCQPLOW_SHIFT)
+#define I40E_VFPE_CCQPSTATUS(_VF) (0x00000800 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VFPE_CCQPSTATUS_MAX_INDEX 127
+#define I40E_VFPE_CCQPSTATUS_CCQP_DONE_SHIFT 0
+#define I40E_VFPE_CCQPSTATUS_CCQP_DONE_MASK (0x1 << I40E_VFPE_CCQPSTATUS_CCQP_DONE_SHIFT)
+#define I40E_VFPE_CCQPSTATUS_CCQP_ERR_SHIFT 31
+#define I40E_VFPE_CCQPSTATUS_CCQP_ERR_MASK (0x1 << I40E_VFPE_CCQPSTATUS_CCQP_ERR_SHIFT)
+#define I40E_VFPE_CQACK(_VF) (0x00130800 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VFPE_CQACK_MAX_INDEX 127
+#define I40E_VFPE_CQACK_PECQID_SHIFT 0
+#define I40E_VFPE_CQACK_PECQID_MASK (0x1FFFF << I40E_VFPE_CQACK_PECQID_SHIFT)
+#define I40E_VFPE_CQARM(_VF) (0x00130400 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VFPE_CQARM_MAX_INDEX 127
+#define I40E_VFPE_CQARM_PECQID_SHIFT 0
+#define I40E_VFPE_CQARM_PECQID_MASK (0x1FFFF << I40E_VFPE_CQARM_PECQID_SHIFT)
+#define I40E_VFPE_CQPDB(_VF) (0x00000000 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VFPE_CQPDB_MAX_INDEX 127
+#define I40E_VFPE_CQPDB_WQHEAD_SHIFT 0
+#define I40E_VFPE_CQPDB_WQHEAD_MASK (0x7FF << I40E_VFPE_CQPDB_WQHEAD_SHIFT)
+#define I40E_VFPE_CQPERRCODES(_VF) (0x00001800 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VFPE_CQPERRCODES_MAX_INDEX 127
+#define I40E_VFPE_CQPERRCODES_CQP_MINOR_CODE_SHIFT 0
+#define I40E_VFPE_CQPERRCODES_CQP_MINOR_CODE_MASK (0xFFFF << I40E_VFPE_CQPERRCODES_CQP_MINOR_CODE_SHIFT)
+#define I40E_VFPE_CQPERRCODES_CQP_MAJOR_CODE_SHIFT 16
+#define I40E_VFPE_CQPERRCODES_CQP_MAJOR_CODE_MASK (0xFFFF << I40E_VFPE_CQPERRCODES_CQP_MAJOR_CODE_SHIFT)
+#define I40E_VFPE_CQPTAIL(_VF) (0x00000400 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VFPE_CQPTAIL_MAX_INDEX 127
+#define I40E_VFPE_CQPTAIL_WQTAIL_SHIFT 0
+#define I40E_VFPE_CQPTAIL_WQTAIL_MASK (0x7FF << I40E_VFPE_CQPTAIL_WQTAIL_SHIFT)
+#define I40E_VFPE_CQPTAIL_CQP_OP_ERR_SHIFT 31
+#define I40E_VFPE_CQPTAIL_CQP_OP_ERR_MASK (0x1 << I40E_VFPE_CQPTAIL_CQP_OP_ERR_SHIFT)
+#define I40E_VFPE_IPCONFIG0(_VF) (0x00001400 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VFPE_IPCONFIG0_MAX_INDEX 127
+#define I40E_VFPE_IPCONFIG0_PEIPID_SHIFT 0
+#define I40E_VFPE_IPCONFIG0_PEIPID_MASK (0xFFFF << I40E_VFPE_IPCONFIG0_PEIPID_SHIFT)
+#define I40E_VFPE_IPCONFIG0_USEENTIREIDRANGE_SHIFT 16
+#define I40E_VFPE_IPCONFIG0_USEENTIREIDRANGE_MASK (0x1 << I40E_VFPE_IPCONFIG0_USEENTIREIDRANGE_SHIFT)
+#define I40E_VFPE_IPCONFIG0_USEUPPERIDRANGE_SHIFT 17
+#define I40E_VFPE_IPCONFIG0_USEUPPERIDRANGE_MASK (0x1 << I40E_VFPE_IPCONFIG0_USEUPPERIDRANGE_SHIFT)
+#define I40E_VFPE_MRTEIDXMASK(_VF) (0x00003000 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VFPE_MRTEIDXMASK_MAX_INDEX 127
+#define I40E_VFPE_MRTEIDXMASK_MRTEIDXMASKBITS_SHIFT 0
+#define I40E_VFPE_MRTEIDXMASK_MRTEIDXMASKBITS_MASK (0x1F << I40E_VFPE_MRTEIDXMASK_MRTEIDXMASKBITS_SHIFT)
+#define I40E_VFPE_RCVUNEXPECTEDERROR(_VF) (0x00003400 + ((_VF) * 4))
+#define I40E_VFPE_RCVUNEXPECTEDERROR_MAX_INDEX 127
+#define I40E_VFPE_RCVUNEXPECTEDERROR_TCP_RX_UNEXP_ERR_SHIFT 0
+#define I40E_VFPE_RCVUNEXPECTEDERROR_TCP_RX_UNEXP_ERR_MASK (0xFFFFFF << I40E_VFPE_RCVUNEXPECTEDERROR_TCP_RX_UNEXP_ERR_SHIFT)
+#define I40E_VFPE_TCPNOWTIMER(_VF) (0x00002C00 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VFPE_TCPNOWTIMER_MAX_INDEX 127
+#define I40E_VFPE_TCPNOWTIMER_TCP_NOW_SHIFT 0
+#define I40E_VFPE_TCPNOWTIMER_TCP_NOW_MASK (0xFFFFFFFF << I40E_VFPE_TCPNOWTIMER_TCP_NOW_SHIFT)
+#define I40E_VFPE_WQEALLOC(_VF) (0x00138000 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VFPE_WQEALLOC_MAX_INDEX 127
+#define I40E_VFPE_WQEALLOC_PEQPID_SHIFT 0
+#define I40E_VFPE_WQEALLOC_PEQPID_MASK (0x3FFFF << I40E_VFPE_WQEALLOC_PEQPID_SHIFT)
+#define I40E_VFPE_WQEALLOC_WQE_DESC_INDEX_SHIFT 20
+#define I40E_VFPE_WQEALLOC_WQE_DESC_INDEX_MASK (0xFFF << I40E_VFPE_WQEALLOC_WQE_DESC_INDEX_SHIFT)
+#define I40E_GLPES_PFIP4RXDISCARD(_i) (0x00010600 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLPES_PFIP4RXDISCARD_MAX_INDEX 15
+#define I40E_GLPES_PFIP4RXDISCARD_IP4RXDISCARD_SHIFT 0
+#define I40E_GLPES_PFIP4RXDISCARD_IP4RXDISCARD_MASK (0xFFFFFFFF << I40E_GLPES_PFIP4RXDISCARD_IP4RXDISCARD_SHIFT)
+#define I40E_GLPES_PFIP4RXFRAGSHI(_i) (0x00010804 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFIP4RXFRAGSHI_MAX_INDEX 15
+#define I40E_GLPES_PFIP4RXFRAGSHI_IP4RXFRAGSHI_SHIFT 0
+#define I40E_GLPES_PFIP4RXFRAGSHI_IP4RXFRAGSHI_MASK (0xFFFF << I40E_GLPES_PFIP4RXFRAGSHI_IP4RXFRAGSHI_SHIFT)
+#define I40E_GLPES_PFIP4RXFRAGSLO(_i) (0x00010800 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFIP4RXFRAGSLO_MAX_INDEX 15
+#define I40E_GLPES_PFIP4RXFRAGSLO_IP4RXFRAGSLO_SHIFT 0
+#define I40E_GLPES_PFIP4RXFRAGSLO_IP4RXFRAGSLO_MASK (0xFFFFFFFF << I40E_GLPES_PFIP4RXFRAGSLO_IP4RXFRAGSLO_SHIFT)
+#define I40E_GLPES_PFIP4RXMCOCTSHI(_i) (0x00010A04 + ((_i) * 8))
+#define I40E_GLPES_PFIP4RXMCOCTSHI_MAX_INDEX 15
+#define I40E_GLPES_PFIP4RXMCOCTSHI_IP4RXMCOCTSHI_SHIFT 0
+#define I40E_GLPES_PFIP4RXMCOCTSHI_IP4RXMCOCTSHI_MASK (0xFFFF << I40E_GLPES_PFIP4RXMCOCTSHI_IP4RXMCOCTSHI_SHIFT)
+#define I40E_GLPES_PFIP4RXMCOCTSLO(_i) (0x00010A00 + ((_i) * 8))
+#define I40E_GLPES_PFIP4RXMCOCTSLO_MAX_INDEX 15
+#define I40E_GLPES_PFIP4RXMCOCTSLO_IP4RXMCOCTSLO_SHIFT 0
+#define I40E_GLPES_PFIP4RXMCOCTSLO_IP4RXMCOCTSLO_MASK (0xFFFFFFFF << I40E_GLPES_PFIP4RXMCOCTSLO_IP4RXMCOCTSLO_SHIFT)
+#define I40E_GLPES_PFIP4RXMCPKTSHI(_i) (0x00010C04 + ((_i) * 8))
+#define I40E_GLPES_PFIP4RXMCPKTSHI_MAX_INDEX 15
+#define I40E_GLPES_PFIP4RXMCPKTSHI_IP4RXMCPKTSHI_SHIFT 0
+#define I40E_GLPES_PFIP4RXMCPKTSHI_IP4RXMCPKTSHI_MASK (0xFFFF << I40E_GLPES_PFIP4RXMCPKTSHI_IP4RXMCPKTSHI_SHIFT)
+#define I40E_GLPES_PFIP4RXMCPKTSLO(_i) (0x00010C00 + ((_i) * 8))
+#define I40E_GLPES_PFIP4RXMCPKTSLO_MAX_INDEX 15
+#define I40E_GLPES_PFIP4RXMCPKTSLO_IP4RXMCPKTSLO_SHIFT 0
+#define I40E_GLPES_PFIP4RXMCPKTSLO_IP4RXMCPKTSLO_MASK (0xFFFFFFFF << I40E_GLPES_PFIP4RXMCPKTSLO_IP4RXMCPKTSLO_SHIFT)
+#define I40E_GLPES_PFIP4RXOCTSHI(_i) (0x00010204 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFIP4RXOCTSHI_MAX_INDEX 15
+#define I40E_GLPES_PFIP4RXOCTSHI_IP4RXOCTSHI_SHIFT 0
+#define I40E_GLPES_PFIP4RXOCTSHI_IP4RXOCTSHI_MASK (0xFFFF << I40E_GLPES_PFIP4RXOCTSHI_IP4RXOCTSHI_SHIFT)
+#define I40E_GLPES_PFIP4RXOCTSLO(_i) (0x00010200 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFIP4RXOCTSLO_MAX_INDEX 15
+#define I40E_GLPES_PFIP4RXOCTSLO_IP4RXOCTSLO_SHIFT 0
+#define I40E_GLPES_PFIP4RXOCTSLO_IP4RXOCTSLO_MASK (0xFFFFFFFF << I40E_GLPES_PFIP4RXOCTSLO_IP4RXOCTSLO_SHIFT)
+#define I40E_GLPES_PFIP4RXPKTSHI(_i) (0x00010404 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFIP4RXPKTSHI_MAX_INDEX 15
+#define I40E_GLPES_PFIP4RXPKTSHI_IP4RXPKTSHI_SHIFT 0
+#define I40E_GLPES_PFIP4RXPKTSHI_IP4RXPKTSHI_MASK (0xFFFF << I40E_GLPES_PFIP4RXPKTSHI_IP4RXPKTSHI_SHIFT)
+#define I40E_GLPES_PFIP4RXPKTSLO(_i) (0x00010400 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFIP4RXPKTSLO_MAX_INDEX 15
+#define I40E_GLPES_PFIP4RXPKTSLO_IP4RXPKTSLO_SHIFT 0
+#define I40E_GLPES_PFIP4RXPKTSLO_IP4RXPKTSLO_MASK (0xFFFFFFFF << I40E_GLPES_PFIP4RXPKTSLO_IP4RXPKTSLO_SHIFT)
+#define I40E_GLPES_PFIP4RXTRUNC(_i) (0x00010700 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLPES_PFIP4RXTRUNC_MAX_INDEX 15
+#define I40E_GLPES_PFIP4RXTRUNC_IP4RXTRUNC_SHIFT 0
+#define I40E_GLPES_PFIP4RXTRUNC_IP4RXTRUNC_MASK (0xFFFFFFFF << I40E_GLPES_PFIP4RXTRUNC_IP4RXTRUNC_SHIFT)
+#define I40E_GLPES_PFIP4TXFRAGSHI(_i) (0x00011E04 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFIP4TXFRAGSHI_MAX_INDEX 15
+#define I40E_GLPES_PFIP4TXFRAGSHI_IP4TXFRAGSHI_SHIFT 0
+#define I40E_GLPES_PFIP4TXFRAGSHI_IP4TXFRAGSHI_MASK (0xFFFF << I40E_GLPES_PFIP4TXFRAGSHI_IP4TXFRAGSHI_SHIFT)
+#define I40E_GLPES_PFIP4TXFRAGSLO(_i) (0x00011E00 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFIP4TXFRAGSLO_MAX_INDEX 15
+#define I40E_GLPES_PFIP4TXFRAGSLO_IP4TXFRAGSLO_SHIFT 0
+#define I40E_GLPES_PFIP4TXFRAGSLO_IP4TXFRAGSLO_MASK (0xFFFFFFFF << I40E_GLPES_PFIP4TXFRAGSLO_IP4TXFRAGSLO_SHIFT)
+#define I40E_GLPES_PFIP4TXMCOCTSHI(_i) (0x00012004 + ((_i) * 8))
+#define I40E_GLPES_PFIP4TXMCOCTSHI_MAX_INDEX 15
+#define I40E_GLPES_PFIP4TXMCOCTSHI_IP4TXMCOCTSHI_SHIFT 0
+#define I40E_GLPES_PFIP4TXMCOCTSHI_IP4TXMCOCTSHI_MASK (0xFFFF << I40E_GLPES_PFIP4TXMCOCTSHI_IP4TXMCOCTSHI_SHIFT)
+#define I40E_GLPES_PFIP4TXMCOCTSLO(_i) (0x00012000 + ((_i) * 8))
+#define I40E_GLPES_PFIP4TXMCOCTSLO_MAX_INDEX 15
+#define I40E_GLPES_PFIP4TXMCOCTSLO_IP4TXMCOCTSLO_SHIFT 0
+#define I40E_GLPES_PFIP4TXMCOCTSLO_IP4TXMCOCTSLO_MASK (0xFFFFFFFF << I40E_GLPES_PFIP4TXMCOCTSLO_IP4TXMCOCTSLO_SHIFT)
+#define I40E_GLPES_PFIP4TXMCPKTSHI(_i) (0x00012204 + ((_i) * 8))
+#define I40E_GLPES_PFIP4TXMCPKTSHI_MAX_INDEX 15
+#define I40E_GLPES_PFIP4TXMCPKTSHI_IP4TXMCPKTSHI_SHIFT 0
+#define I40E_GLPES_PFIP4TXMCPKTSHI_IP4TXMCPKTSHI_MASK (0xFFFF << I40E_GLPES_PFIP4TXMCPKTSHI_IP4TXMCPKTSHI_SHIFT)
+#define I40E_GLPES_PFIP4TXMCPKTSLO(_i) (0x00012200 + ((_i) * 8))
+#define I40E_GLPES_PFIP4TXMCPKTSLO_MAX_INDEX 15
+#define I40E_GLPES_PFIP4TXMCPKTSLO_IP4TXMCPKTSLO_SHIFT 0
+#define I40E_GLPES_PFIP4TXMCPKTSLO_IP4TXMCPKTSLO_MASK (0xFFFFFFFF << I40E_GLPES_PFIP4TXMCPKTSLO_IP4TXMCPKTSLO_SHIFT)
+#define I40E_GLPES_PFIP4TXNOROUTE(_i) (0x00012E00 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLPES_PFIP4TXNOROUTE_MAX_INDEX 15
+#define I40E_GLPES_PFIP4TXNOROUTE_IP4TXNOROUTE_SHIFT 0
+#define I40E_GLPES_PFIP4TXNOROUTE_IP4TXNOROUTE_MASK (0xFFFFFF << I40E_GLPES_PFIP4TXNOROUTE_IP4TXNOROUTE_SHIFT)
+#define I40E_GLPES_PFIP4TXOCTSHI(_i) (0x00011A04 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFIP4TXOCTSHI_MAX_INDEX 15
+#define I40E_GLPES_PFIP4TXOCTSHI_IP4TXOCTSHI_SHIFT 0
+#define I40E_GLPES_PFIP4TXOCTSHI_IP4TXOCTSHI_MASK (0xFFFF << I40E_GLPES_PFIP4TXOCTSHI_IP4TXOCTSHI_SHIFT)
+#define I40E_GLPES_PFIP4TXOCTSLO(_i) (0x00011A00 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFIP4TXOCTSLO_MAX_INDEX 15
+#define I40E_GLPES_PFIP4TXOCTSLO_IP4TXOCTSLO_SHIFT 0
+#define I40E_GLPES_PFIP4TXOCTSLO_IP4TXOCTSLO_MASK (0xFFFFFFFF << I40E_GLPES_PFIP4TXOCTSLO_IP4TXOCTSLO_SHIFT)
+#define I40E_GLPES_PFIP4TXPKTSHI(_i) (0x00011C04 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFIP4TXPKTSHI_MAX_INDEX 15
+#define I40E_GLPES_PFIP4TXPKTSHI_IP4TXPKTSHI_SHIFT 0
+#define I40E_GLPES_PFIP4TXPKTSHI_IP4TXPKTSHI_MASK (0xFFFF << I40E_GLPES_PFIP4TXPKTSHI_IP4TXPKTSHI_SHIFT)
+#define I40E_GLPES_PFIP4TXPKTSLO(_i) (0x00011C00 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFIP4TXPKTSLO_MAX_INDEX 15
+#define I40E_GLPES_PFIP4TXPKTSLO_IP4TXPKTSLO_SHIFT 0
+#define I40E_GLPES_PFIP4TXPKTSLO_IP4TXPKTSLO_MASK (0xFFFFFFFF << I40E_GLPES_PFIP4TXPKTSLO_IP4TXPKTSLO_SHIFT)
+#define I40E_GLPES_PFIP6RXDISCARD(_i) (0x00011200 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLPES_PFIP6RXDISCARD_MAX_INDEX 15
+#define I40E_GLPES_PFIP6RXDISCARD_IP6RXDISCARD_SHIFT 0
+#define I40E_GLPES_PFIP6RXDISCARD_IP6RXDISCARD_MASK (0xFFFFFFFF << I40E_GLPES_PFIP6RXDISCARD_IP6RXDISCARD_SHIFT)
+#define I40E_GLPES_PFIP6RXFRAGSHI(_i) (0x00011404 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFIP6RXFRAGSHI_MAX_INDEX 15
+#define I40E_GLPES_PFIP6RXFRAGSHI_IP6RXFRAGSHI_SHIFT 0
+#define I40E_GLPES_PFIP6RXFRAGSHI_IP6RXFRAGSHI_MASK (0xFFFF << I40E_GLPES_PFIP6RXFRAGSHI_IP6RXFRAGSHI_SHIFT)
+#define I40E_GLPES_PFIP6RXFRAGSLO(_i) (0x00011400 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFIP6RXFRAGSLO_MAX_INDEX 15
+#define I40E_GLPES_PFIP6RXFRAGSLO_IP6RXFRAGSLO_SHIFT 0
+#define I40E_GLPES_PFIP6RXFRAGSLO_IP6RXFRAGSLO_MASK (0xFFFFFFFF << I40E_GLPES_PFIP6RXFRAGSLO_IP6RXFRAGSLO_SHIFT)
+#define I40E_GLPES_PFIP6RXMCOCTSHI(_i) (0x00011604 + ((_i) * 8))
+#define I40E_GLPES_PFIP6RXMCOCTSHI_MAX_INDEX 15
+#define I40E_GLPES_PFIP6RXMCOCTSHI_IP6RXMCOCTSHI_SHIFT 0
+#define I40E_GLPES_PFIP6RXMCOCTSHI_IP6RXMCOCTSHI_MASK (0xFFFF << I40E_GLPES_PFIP6RXMCOCTSHI_IP6RXMCOCTSHI_SHIFT)
+#define I40E_GLPES_PFIP6RXMCOCTSLO(_i) (0x00011600 + ((_i) * 8))
+#define I40E_GLPES_PFIP6RXMCOCTSLO_MAX_INDEX 15
+#define I40E_GLPES_PFIP6RXMCOCTSLO_IP6RXMCOCTSLO_SHIFT 0
+#define I40E_GLPES_PFIP6RXMCOCTSLO_IP6RXMCOCTSLO_MASK (0xFFFFFFFF << I40E_GLPES_PFIP6RXMCOCTSLO_IP6RXMCOCTSLO_SHIFT)
+#define I40E_GLPES_PFIP6RXMCPKTSHI(_i) (0x00011804 + ((_i) * 8))
+#define I40E_GLPES_PFIP6RXMCPKTSHI_MAX_INDEX 15
+#define I40E_GLPES_PFIP6RXMCPKTSHI_IP6RXMCPKTSHI_SHIFT 0
+#define I40E_GLPES_PFIP6RXMCPKTSHI_IP6RXMCPKTSHI_MASK (0xFFFF << I40E_GLPES_PFIP6RXMCPKTSHI_IP6RXMCPKTSHI_SHIFT)
+#define I40E_GLPES_PFIP6RXMCPKTSLO(_i) (0x00011800 + ((_i) * 8))
+#define I40E_GLPES_PFIP6RXMCPKTSLO_MAX_INDEX 15
+#define I40E_GLPES_PFIP6RXMCPKTSLO_IP6RXMCPKTSLO_SHIFT 0
+#define I40E_GLPES_PFIP6RXMCPKTSLO_IP6RXMCPKTSLO_MASK (0xFFFFFFFF << I40E_GLPES_PFIP6RXMCPKTSLO_IP6RXMCPKTSLO_SHIFT)
+#define I40E_GLPES_PFIP6RXOCTSHI(_i) (0x00010E04 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFIP6RXOCTSHI_MAX_INDEX 15
+#define I40E_GLPES_PFIP6RXOCTSHI_IP6RXOCTSHI_SHIFT 0
+#define I40E_GLPES_PFIP6RXOCTSHI_IP6RXOCTSHI_MASK (0xFFFF << I40E_GLPES_PFIP6RXOCTSHI_IP6RXOCTSHI_SHIFT)
+#define I40E_GLPES_PFIP6RXOCTSLO(_i) (0x00010E00 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFIP6RXOCTSLO_MAX_INDEX 15
+#define I40E_GLPES_PFIP6RXOCTSLO_IP6RXOCTSLO_SHIFT 0
+#define I40E_GLPES_PFIP6RXOCTSLO_IP6RXOCTSLO_MASK (0xFFFFFFFF << I40E_GLPES_PFIP6RXOCTSLO_IP6RXOCTSLO_SHIFT)
+#define I40E_GLPES_PFIP6RXPKTSHI(_i) (0x00011004 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFIP6RXPKTSHI_MAX_INDEX 15
+#define I40E_GLPES_PFIP6RXPKTSHI_IP6RXPKTSHI_SHIFT 0
+#define I40E_GLPES_PFIP6RXPKTSHI_IP6RXPKTSHI_MASK (0xFFFF << I40E_GLPES_PFIP6RXPKTSHI_IP6RXPKTSHI_SHIFT)
+#define I40E_GLPES_PFIP6RXPKTSLO(_i) (0x00011000 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFIP6RXPKTSLO_MAX_INDEX 15
+#define I40E_GLPES_PFIP6RXPKTSLO_IP6RXPKTSLO_SHIFT 0
+#define I40E_GLPES_PFIP6RXPKTSLO_IP6RXPKTSLO_MASK (0xFFFFFFFF << I40E_GLPES_PFIP6RXPKTSLO_IP6RXPKTSLO_SHIFT)
+#define I40E_GLPES_PFIP6RXTRUNC(_i) (0x00011300 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLPES_PFIP6RXTRUNC_MAX_INDEX 15
+#define I40E_GLPES_PFIP6RXTRUNC_IP6RXTRUNC_SHIFT 0
+#define I40E_GLPES_PFIP6RXTRUNC_IP6RXTRUNC_MASK (0xFFFFFFFF << I40E_GLPES_PFIP6RXTRUNC_IP6RXTRUNC_SHIFT)
+#define I40E_GLPES_PFIP6TXFRAGSHI(_i) (0x00012804 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFIP6TXFRAGSHI_MAX_INDEX 15
+#define I40E_GLPES_PFIP6TXFRAGSHI_IP6TXFRAGSHI_SHIFT 0
+#define I40E_GLPES_PFIP6TXFRAGSHI_IP6TXFRAGSHI_MASK (0xFFFF << I40E_GLPES_PFIP6TXFRAGSHI_IP6TXFRAGSHI_SHIFT)
+#define I40E_GLPES_PFIP6TXFRAGSLO(_i) (0x00012800 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFIP6TXFRAGSLO_MAX_INDEX 15
+#define I40E_GLPES_PFIP6TXFRAGSLO_IP6TXFRAGSLO_SHIFT 0
+#define I40E_GLPES_PFIP6TXFRAGSLO_IP6TXFRAGSLO_MASK (0xFFFFFFFF << I40E_GLPES_PFIP6TXFRAGSLO_IP6TXFRAGSLO_SHIFT)
+#define I40E_GLPES_PFIP6TXMCOCTSHI(_i) (0x00012A04 + ((_i) * 8))
+#define I40E_GLPES_PFIP6TXMCOCTSHI_MAX_INDEX 15
+#define I40E_GLPES_PFIP6TXMCOCTSHI_IP6TXMCOCTSHI_SHIFT 0
+#define I40E_GLPES_PFIP6TXMCOCTSHI_IP6TXMCOCTSHI_MASK (0xFFFF << I40E_GLPES_PFIP6TXMCOCTSHI_IP6TXMCOCTSHI_SHIFT)
+#define I40E_GLPES_PFIP6TXMCOCTSLO(_i) (0x00012A00 + ((_i) * 8))
+#define I40E_GLPES_PFIP6TXMCOCTSLO_MAX_INDEX 15
+#define I40E_GLPES_PFIP6TXMCOCTSLO_IP6TXMCOCTSLO_SHIFT 0
+#define I40E_GLPES_PFIP6TXMCOCTSLO_IP6TXMCOCTSLO_MASK (0xFFFFFFFF << I40E_GLPES_PFIP6TXMCOCTSLO_IP6TXMCOCTSLO_SHIFT)
+#define I40E_GLPES_PFIP6TXMCPKTSHI(_i) (0x00012C04 + ((_i) * 8))
+#define I40E_GLPES_PFIP6TXMCPKTSHI_MAX_INDEX 15
+#define I40E_GLPES_PFIP6TXMCPKTSHI_IP6TXMCPKTSHI_SHIFT 0
+#define I40E_GLPES_PFIP6TXMCPKTSHI_IP6TXMCPKTSHI_MASK (0xFFFF << I40E_GLPES_PFIP6TXMCPKTSHI_IP6TXMCPKTSHI_SHIFT)
+#define I40E_GLPES_PFIP6TXMCPKTSLO(_i) (0x00012C00 + ((_i) * 8))
+#define I40E_GLPES_PFIP6TXMCPKTSLO_MAX_INDEX 15
+#define I40E_GLPES_PFIP6TXMCPKTSLO_IP6TXMCPKTSLO_SHIFT 0
+#define I40E_GLPES_PFIP6TXMCPKTSLO_IP6TXMCPKTSLO_MASK (0xFFFFFFFF << I40E_GLPES_PFIP6TXMCPKTSLO_IP6TXMCPKTSLO_SHIFT)
+#define I40E_GLPES_PFIP6TXNOROUTE(_i) (0x00012F00 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLPES_PFIP6TXNOROUTE_MAX_INDEX 15
+#define I40E_GLPES_PFIP6TXNOROUTE_IP6TXNOROUTE_SHIFT 0
+#define I40E_GLPES_PFIP6TXNOROUTE_IP6TXNOROUTE_MASK (0xFFFFFF << I40E_GLPES_PFIP6TXNOROUTE_IP6TXNOROUTE_SHIFT)
+#define I40E_GLPES_PFIP6TXOCTSHI(_i) (0x00012404 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFIP6TXOCTSHI_MAX_INDEX 15
+#define I40E_GLPES_PFIP6TXOCTSHI_IP6TXOCTSHI_SHIFT 0
+#define I40E_GLPES_PFIP6TXOCTSHI_IP6TXOCTSHI_MASK (0xFFFF << I40E_GLPES_PFIP6TXOCTSHI_IP6TXOCTSHI_SHIFT)
+#define I40E_GLPES_PFIP6TXOCTSLO(_i) (0x00012400 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFIP6TXOCTSLO_MAX_INDEX 15
+#define I40E_GLPES_PFIP6TXOCTSLO_IP6TXOCTSLO_SHIFT 0
+#define I40E_GLPES_PFIP6TXOCTSLO_IP6TXOCTSLO_MASK (0xFFFFFFFF << I40E_GLPES_PFIP6TXOCTSLO_IP6TXOCTSLO_SHIFT)
+#define I40E_GLPES_PFIP6TXPKTSHI(_i) (0x00012604 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFIP6TXPKTSHI_MAX_INDEX 15
+#define I40E_GLPES_PFIP6TXPKTSHI_IP6TXPKTSHI_SHIFT 0
+#define I40E_GLPES_PFIP6TXPKTSHI_IP6TXPKTSHI_MASK (0xFFFF << I40E_GLPES_PFIP6TXPKTSHI_IP6TXPKTSHI_SHIFT)
+#define I40E_GLPES_PFIP6TXPKTSLO(_i) (0x00012600 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFIP6TXPKTSLO_MAX_INDEX 15
+#define I40E_GLPES_PFIP6TXPKTSLO_IP6TXPKTSLO_SHIFT 0
+#define I40E_GLPES_PFIP6TXPKTSLO_IP6TXPKTSLO_MASK (0xFFFFFFFF << I40E_GLPES_PFIP6TXPKTSLO_IP6TXPKTSLO_SHIFT)
+#define I40E_GLPES_PFRDMARXRDSHI(_i) (0x00013E04 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFRDMARXRDSHI_MAX_INDEX 15
+#define I40E_GLPES_PFRDMARXRDSHI_RDMARXRDSHI_SHIFT 0
+#define I40E_GLPES_PFRDMARXRDSHI_RDMARXRDSHI_MASK (0xFFFF << I40E_GLPES_PFRDMARXRDSHI_RDMARXRDSHI_SHIFT)
+#define I40E_GLPES_PFRDMARXRDSLO(_i) (0x00013E00 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFRDMARXRDSLO_MAX_INDEX 15
+#define I40E_GLPES_PFRDMARXRDSLO_RDMARXRDSLO_SHIFT 0
+#define I40E_GLPES_PFRDMARXRDSLO_RDMARXRDSLO_MASK (0xFFFFFFFF << I40E_GLPES_PFRDMARXRDSLO_RDMARXRDSLO_SHIFT)
+#define I40E_GLPES_PFRDMARXSNDSHI(_i) (0x00014004 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFRDMARXSNDSHI_MAX_INDEX 15
+#define I40E_GLPES_PFRDMARXSNDSHI_RDMARXSNDSHI_SHIFT 0
+#define I40E_GLPES_PFRDMARXSNDSHI_RDMARXSNDSHI_MASK (0xFFFF << I40E_GLPES_PFRDMARXSNDSHI_RDMARXSNDSHI_SHIFT)
+#define I40E_GLPES_PFRDMARXSNDSLO(_i) (0x00014000 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFRDMARXSNDSLO_MAX_INDEX 15
+#define I40E_GLPES_PFRDMARXSNDSLO_RDMARXSNDSLO_SHIFT 0
+#define I40E_GLPES_PFRDMARXSNDSLO_RDMARXSNDSLO_MASK (0xFFFFFFFF << I40E_GLPES_PFRDMARXSNDSLO_RDMARXSNDSLO_SHIFT)
+#define I40E_GLPES_PFRDMARXWRSHI(_i) (0x00013C04 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFRDMARXWRSHI_MAX_INDEX 15
+#define I40E_GLPES_PFRDMARXWRSHI_RDMARXWRSHI_SHIFT 0
+#define I40E_GLPES_PFRDMARXWRSHI_RDMARXWRSHI_MASK (0xFFFF << I40E_GLPES_PFRDMARXWRSHI_RDMARXWRSHI_SHIFT)
+#define I40E_GLPES_PFRDMARXWRSLO(_i) (0x00013C00 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFRDMARXWRSLO_MAX_INDEX 15
+#define I40E_GLPES_PFRDMARXWRSLO_RDMARXWRSLO_SHIFT 0
+#define I40E_GLPES_PFRDMARXWRSLO_RDMARXWRSLO_MASK (0xFFFFFFFF << I40E_GLPES_PFRDMARXWRSLO_RDMARXWRSLO_SHIFT)
+#define I40E_GLPES_PFRDMATXRDSHI(_i) (0x00014404 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFRDMATXRDSHI_MAX_INDEX 15
+#define I40E_GLPES_PFRDMATXRDSHI_RDMARXRDSHI_SHIFT 0
+#define I40E_GLPES_PFRDMATXRDSHI_RDMARXRDSHI_MASK (0xFFFF << I40E_GLPES_PFRDMATXRDSHI_RDMARXRDSHI_SHIFT)
+#define I40E_GLPES_PFRDMATXRDSLO(_i) (0x00014400 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFRDMATXRDSLO_MAX_INDEX 15
+#define I40E_GLPES_PFRDMATXRDSLO_RDMARXRDSLO_SHIFT 0
+#define I40E_GLPES_PFRDMATXRDSLO_RDMARXRDSLO_MASK (0xFFFFFFFF << I40E_GLPES_PFRDMATXRDSLO_RDMARXRDSLO_SHIFT)
+#define I40E_GLPES_PFRDMATXSNDSHI(_i) (0x00014604 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFRDMATXSNDSHI_MAX_INDEX 15
+#define I40E_GLPES_PFRDMATXSNDSHI_RDMARXSNDSHI_SHIFT 0
+#define I40E_GLPES_PFRDMATXSNDSHI_RDMARXSNDSHI_MASK (0xFFFF << I40E_GLPES_PFRDMATXSNDSHI_RDMARXSNDSHI_SHIFT)
+#define I40E_GLPES_PFRDMATXSNDSLO(_i) (0x00014600 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFRDMATXSNDSLO_MAX_INDEX 15
+#define I40E_GLPES_PFRDMATXSNDSLO_RDMARXSNDSLO_SHIFT 0
+#define I40E_GLPES_PFRDMATXSNDSLO_RDMARXSNDSLO_MASK (0xFFFFFFFF << I40E_GLPES_PFRDMATXSNDSLO_RDMARXSNDSLO_SHIFT)
+#define I40E_GLPES_PFRDMATXWRSHI(_i) (0x00014204 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFRDMATXWRSHI_MAX_INDEX 15
+#define I40E_GLPES_PFRDMATXWRSHI_RDMARXWRSHI_SHIFT 0
+#define I40E_GLPES_PFRDMATXWRSHI_RDMARXWRSHI_MASK (0xFFFF << I40E_GLPES_PFRDMATXWRSHI_RDMARXWRSHI_SHIFT)
+#define I40E_GLPES_PFRDMATXWRSLO(_i) (0x00014200 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFRDMATXWRSLO_MAX_INDEX 15
+#define I40E_GLPES_PFRDMATXWRSLO_RDMARXWRSLO_SHIFT 0
+#define I40E_GLPES_PFRDMATXWRSLO_RDMARXWRSLO_MASK (0xFFFFFFFF << I40E_GLPES_PFRDMATXWRSLO_RDMARXWRSLO_SHIFT)
+#define I40E_GLPES_PFRDMAVBNDHI(_i) (0x00014804 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFRDMAVBNDHI_MAX_INDEX 15
+#define I40E_GLPES_PFRDMAVBNDHI_RDMAVBNDHI_SHIFT 0
+#define I40E_GLPES_PFRDMAVBNDHI_RDMAVBNDHI_MASK (0xFFFFFFFF << I40E_GLPES_PFRDMAVBNDHI_RDMAVBNDHI_SHIFT)
+#define I40E_GLPES_PFRDMAVBNDLO(_i) (0x00014800 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFRDMAVBNDLO_MAX_INDEX 15
+#define I40E_GLPES_PFRDMAVBNDLO_RDMAVBNDLO_SHIFT 0
+#define I40E_GLPES_PFRDMAVBNDLO_RDMAVBNDLO_MASK (0xFFFFFFFF << I40E_GLPES_PFRDMAVBNDLO_RDMAVBNDLO_SHIFT)
+#define I40E_GLPES_PFRDMAVINVHI(_i) (0x00014A04 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFRDMAVINVHI_MAX_INDEX 15
+#define I40E_GLPES_PFRDMAVINVHI_RDMAVINVHI_SHIFT 0
+#define I40E_GLPES_PFRDMAVINVHI_RDMAVINVHI_MASK (0xFFFFFFFF << I40E_GLPES_PFRDMAVINVHI_RDMAVINVHI_SHIFT)
+#define I40E_GLPES_PFRDMAVINVLO(_i) (0x00014A00 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFRDMAVINVLO_MAX_INDEX 15
+#define I40E_GLPES_PFRDMAVINVLO_RDMAVINVLO_SHIFT 0
+#define I40E_GLPES_PFRDMAVINVLO_RDMAVINVLO_MASK (0xFFFFFFFF << I40E_GLPES_PFRDMAVINVLO_RDMAVINVLO_SHIFT)
+#define I40E_GLPES_PFRXVLANERR(_i) (0x00010000 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLPES_PFRXVLANERR_MAX_INDEX 15
+#define I40E_GLPES_PFRXVLANERR_RXVLANERR_SHIFT 0
+#define I40E_GLPES_PFRXVLANERR_RXVLANERR_MASK (0xFFFFFF << I40E_GLPES_PFRXVLANERR_RXVLANERR_SHIFT)
+#define I40E_GLPES_PFTCPRTXSEG(_i) (0x00013600 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLPES_PFTCPRTXSEG_MAX_INDEX 15
+#define I40E_GLPES_PFTCPRTXSEG_TCPRTXSEG_SHIFT 0
+#define I40E_GLPES_PFTCPRTXSEG_TCPRTXSEG_MASK (0xFFFFFFFF << I40E_GLPES_PFTCPRTXSEG_TCPRTXSEG_SHIFT)
+#define I40E_GLPES_PFTCPRXOPTERR(_i) (0x00013200 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_GLPES_PFTCPRXOPTERR_MAX_INDEX 15
+#define I40E_GLPES_PFTCPRXOPTERR_TCPRXOPTERR_SHIFT 0
+#define I40E_GLPES_PFTCPRXOPTERR_TCPRXOPTERR_MASK (0xFFFFFF << I40E_GLPES_PFTCPRXOPTERR_TCPRXOPTERR_SHIFT)
+#define I40E_GLPES_PFTCPRXPROTOERR(_i) (0x00013300 + ((_i) * 4))
+#define I40E_GLPES_PFTCPRXPROTOERR_MAX_INDEX 15
+#define I40E_GLPES_PFTCPRXPROTOERR_TCPRXPROTOERR_SHIFT 0
+#define I40E_GLPES_PFTCPRXPROTOERR_TCPRXPROTOERR_MASK (0xFFFFFF << I40E_GLPES_PFTCPRXPROTOERR_TCPRXPROTOERR_SHIFT)
+#define I40E_GLPES_PFTCPRXSEGSHI(_i) (0x00013004 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFTCPRXSEGSHI_MAX_INDEX 15
+#define I40E_GLPES_PFTCPRXSEGSHI_TCPRXSEGSHI_SHIFT 0
+#define I40E_GLPES_PFTCPRXSEGSHI_TCPRXSEGSHI_MASK (0xFFFF << I40E_GLPES_PFTCPRXSEGSHI_TCPRXSEGSHI_SHIFT)
+#define I40E_GLPES_PFTCPRXSEGSLO(_i) (0x00013000 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFTCPRXSEGSLO_MAX_INDEX 15
+#define I40E_GLPES_PFTCPRXSEGSLO_TCPRXSEGSLO_SHIFT 0
+#define I40E_GLPES_PFTCPRXSEGSLO_TCPRXSEGSLO_MASK (0xFFFFFFFF << I40E_GLPES_PFTCPRXSEGSLO_TCPRXSEGSLO_SHIFT)
+#define I40E_GLPES_PFTCPTXSEGHI(_i) (0x00013404 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFTCPTXSEGHI_MAX_INDEX 15
+#define I40E_GLPES_PFTCPTXSEGHI_TCPTXSEGHI_SHIFT 0
+#define I40E_GLPES_PFTCPTXSEGHI_TCPTXSEGHI_MASK (0xFFFF << I40E_GLPES_PFTCPTXSEGHI_TCPTXSEGHI_SHIFT)
+#define I40E_GLPES_PFTCPTXSEGLO(_i) (0x00013400 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFTCPTXSEGLO_MAX_INDEX 15
+#define I40E_GLPES_PFTCPTXSEGLO_TCPTXSEGLO_SHIFT 0
+#define I40E_GLPES_PFTCPTXSEGLO_TCPTXSEGLO_MASK (0xFFFFFFFF << I40E_GLPES_PFTCPTXSEGLO_TCPTXSEGLO_SHIFT)
+#define I40E_GLPES_PFUDPRXPKTSHI(_i) (0x00013804 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFUDPRXPKTSHI_MAX_INDEX 15
+#define I40E_GLPES_PFUDPRXPKTSHI_UDPRXPKTSHI_SHIFT 0
+#define I40E_GLPES_PFUDPRXPKTSHI_UDPRXPKTSHI_MASK (0xFFFF << I40E_GLPES_PFUDPRXPKTSHI_UDPRXPKTSHI_SHIFT)
+#define I40E_GLPES_PFUDPRXPKTSLO(_i) (0x00013800 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFUDPRXPKTSLO_MAX_INDEX 15
+#define I40E_GLPES_PFUDPRXPKTSLO_UDPRXPKTSLO_SHIFT 0
+#define I40E_GLPES_PFUDPRXPKTSLO_UDPRXPKTSLO_MASK (0xFFFFFFFF << I40E_GLPES_PFUDPRXPKTSLO_UDPRXPKTSLO_SHIFT)
+#define I40E_GLPES_PFUDPTXPKTSHI(_i) (0x00013A04 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFUDPTXPKTSHI_MAX_INDEX 15
+#define I40E_GLPES_PFUDPTXPKTSHI_UDPTXPKTSHI_SHIFT 0
+#define I40E_GLPES_PFUDPTXPKTSHI_UDPTXPKTSHI_MASK (0xFFFF << I40E_GLPES_PFUDPTXPKTSHI_UDPTXPKTSHI_SHIFT)
+#define I40E_GLPES_PFUDPTXPKTSLO(_i) (0x00013A00 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLPES_PFUDPTXPKTSLO_MAX_INDEX 15
+#define I40E_GLPES_PFUDPTXPKTSLO_UDPTXPKTSLO_SHIFT 0
+#define I40E_GLPES_PFUDPTXPKTSLO_UDPTXPKTSLO_MASK (0xFFFFFFFF << I40E_GLPES_PFUDPTXPKTSLO_UDPTXPKTSLO_SHIFT)
+#define I40E_GLPES_RDMARXMULTFPDUSHI 0x0001E014
+#define I40E_GLPES_RDMARXMULTFPDUSHI_RDMARXMULTFPDUSHI_SHIFT 0
+#define I40E_GLPES_RDMARXMULTFPDUSHI_RDMARXMULTFPDUSHI_MASK (0xFFFFFF << I40E_GLPES_RDMARXMULTFPDUSHI_RDMARXMULTFPDUSHI_SHIFT)
+#define I40E_GLPES_RDMARXMULTFPDUSLO 0x0001E010
+#define I40E_GLPES_RDMARXMULTFPDUSLO_RDMARXMULTFPDUSLO_SHIFT 0
+#define I40E_GLPES_RDMARXMULTFPDUSLO_RDMARXMULTFPDUSLO_MASK (0xFFFFFFFF << I40E_GLPES_RDMARXMULTFPDUSLO_RDMARXMULTFPDUSLO_SHIFT)
+#define I40E_GLPES_RDMARXOOODDPHI 0x0001E01C
+#define I40E_GLPES_RDMARXOOODDPHI_RDMARXOOODDPHI_SHIFT 0
+#define I40E_GLPES_RDMARXOOODDPHI_RDMARXOOODDPHI_MASK (0xFFFFFF << I40E_GLPES_RDMARXOOODDPHI_RDMARXOOODDPHI_SHIFT)
+#define I40E_GLPES_RDMARXOOODDPLO 0x0001E018
+#define I40E_GLPES_RDMARXOOODDPLO_RDMARXOOODDPLO_SHIFT 0
+#define I40E_GLPES_RDMARXOOODDPLO_RDMARXOOODDPLO_MASK (0xFFFFFFFF << I40E_GLPES_RDMARXOOODDPLO_RDMARXOOODDPLO_SHIFT)
+#define I40E_GLPES_RDMARXOOONOMARK 0x0001E004
+#define I40E_GLPES_RDMARXOOONOMARK_RDMAOOONOMARK_SHIFT 0
+#define I40E_GLPES_RDMARXOOONOMARK_RDMAOOONOMARK_MASK (0xFFFFFFFF << I40E_GLPES_RDMARXOOONOMARK_RDMAOOONOMARK_SHIFT)
+#define I40E_GLPES_RDMARXUNALIGN 0x0001E000
+#define I40E_GLPES_RDMARXUNALIGN_RDMRXAUNALIGN_SHIFT 0
+#define I40E_GLPES_RDMARXUNALIGN_RDMRXAUNALIGN_MASK (0xFFFFFFFF << I40E_GLPES_RDMARXUNALIGN_RDMRXAUNALIGN_SHIFT)
+#define I40E_GLPES_TCPRXFOURHOLEHI 0x0001E044
+#define I40E_GLPES_TCPRXFOURHOLEHI_TCPRXFOURHOLEHI_SHIFT 0
+#define I40E_GLPES_TCPRXFOURHOLEHI_TCPRXFOURHOLEHI_MASK (0xFFFFFF << I40E_GLPES_TCPRXFOURHOLEHI_TCPRXFOURHOLEHI_SHIFT)
+#define I40E_GLPES_TCPRXFOURHOLELO 0x0001E040
+#define I40E_GLPES_TCPRXFOURHOLELO_TCPRXFOURHOLELO_SHIFT 0
+#define I40E_GLPES_TCPRXFOURHOLELO_TCPRXFOURHOLELO_MASK (0xFFFFFFFF << I40E_GLPES_TCPRXFOURHOLELO_TCPRXFOURHOLELO_SHIFT)
+#define I40E_GLPES_TCPRXONEHOLEHI 0x0001E02C
+#define I40E_GLPES_TCPRXONEHOLEHI_TCPRXONEHOLEHI_SHIFT 0
+#define I40E_GLPES_TCPRXONEHOLEHI_TCPRXONEHOLEHI_MASK (0xFFFFFF << I40E_GLPES_TCPRXONEHOLEHI_TCPRXONEHOLEHI_SHIFT)
+#define I40E_GLPES_TCPRXONEHOLELO 0x0001E028
+#define I40E_GLPES_TCPRXONEHOLELO_TCPRXONEHOLELO_SHIFT 0
+#define I40E_GLPES_TCPRXONEHOLELO_TCPRXONEHOLELO_MASK (0xFFFFFFFF << I40E_GLPES_TCPRXONEHOLELO_TCPRXONEHOLELO_SHIFT)
+#define I40E_GLPES_TCPRXPUREACKHI 0x0001E024
+#define I40E_GLPES_TCPRXPUREACKHI_TCPRXPUREACKSHI_SHIFT 0
+#define I40E_GLPES_TCPRXPUREACKHI_TCPRXPUREACKSHI_MASK (0xFFFFFF << I40E_GLPES_TCPRXPUREACKHI_TCPRXPUREACKSHI_SHIFT)
+#define I40E_GLPES_TCPRXPUREACKSLO 0x0001E020
+#define I40E_GLPES_TCPRXPUREACKSLO_TCPRXPUREACKLO_SHIFT 0
+#define I40E_GLPES_TCPRXPUREACKSLO_TCPRXPUREACKLO_MASK (0xFFFFFFFF << I40E_GLPES_TCPRXPUREACKSLO_TCPRXPUREACKLO_SHIFT)
+#define I40E_GLPES_TCPRXTHREEHOLEHI 0x0001E03C
+#define I40E_GLPES_TCPRXTHREEHOLEHI_TCPRXTHREEHOLEHI_SHIFT 0
+#define I40E_GLPES_TCPRXTHREEHOLEHI_TCPRXTHREEHOLEHI_MASK (0xFFFFFF << I40E_GLPES_TCPRXTHREEHOLEHI_TCPRXTHREEHOLEHI_SHIFT)
+#define I40E_GLPES_TCPRXTHREEHOLELO 0x0001E038
+#define I40E_GLPES_TCPRXTHREEHOLELO_TCPRXTHREEHOLELO_SHIFT 0
+#define I40E_GLPES_TCPRXTHREEHOLELO_TCPRXTHREEHOLELO_MASK (0xFFFFFFFF << I40E_GLPES_TCPRXTHREEHOLELO_TCPRXTHREEHOLELO_SHIFT)
+#define I40E_GLPES_TCPRXTWOHOLEHI 0x0001E034
+#define I40E_GLPES_TCPRXTWOHOLEHI_TCPRXTWOHOLEHI_SHIFT 0
+#define I40E_GLPES_TCPRXTWOHOLEHI_TCPRXTWOHOLEHI_MASK (0xFFFFFF << I40E_GLPES_TCPRXTWOHOLEHI_TCPRXTWOHOLEHI_SHIFT)
+#define I40E_GLPES_TCPRXTWOHOLELO 0x0001E030
+#define I40E_GLPES_TCPRXTWOHOLELO_TCPRXTWOHOLELO_SHIFT 0
+#define I40E_GLPES_TCPRXTWOHOLELO_TCPRXTWOHOLELO_MASK (0xFFFFFFFF << I40E_GLPES_TCPRXTWOHOLELO_TCPRXTWOHOLELO_SHIFT)
+#define I40E_GLPES_TCPRXUNEXPERR 0x0001E008
+#define I40E_GLPES_TCPRXUNEXPERR_TCPRXUNEXPERR_SHIFT 0
+#define I40E_GLPES_TCPRXUNEXPERR_TCPRXUNEXPERR_MASK (0xFFFFFF << I40E_GLPES_TCPRXUNEXPERR_TCPRXUNEXPERR_SHIFT)
+#define I40E_GLPES_TCPTXRETRANSFASTHI 0x0001E04C
+#define I40E_GLPES_TCPTXRETRANSFASTHI_TCPTXRETRANSFASTHI_SHIFT 0
+#define I40E_GLPES_TCPTXRETRANSFASTHI_TCPTXRETRANSFASTHI_MASK (0xFFFFFF << I40E_GLPES_TCPTXRETRANSFASTHI_TCPTXRETRANSFASTHI_SHIFT)
+#define I40E_GLPES_TCPTXRETRANSFASTLO 0x0001E048
+#define I40E_GLPES_TCPTXRETRANSFASTLO_TCPTXRETRANSFASTLO_SHIFT 0
+#define I40E_GLPES_TCPTXRETRANSFASTLO_TCPTXRETRANSFASTLO_MASK (0xFFFFFFFF << I40E_GLPES_TCPTXRETRANSFASTLO_TCPTXRETRANSFASTLO_SHIFT)
+#define I40E_GLPES_TCPTXTOUTSFASTHI 0x0001E054
+#define I40E_GLPES_TCPTXTOUTSFASTHI_TCPTXTOUTSFASTHI_SHIFT 0
+#define I40E_GLPES_TCPTXTOUTSFASTHI_TCPTXTOUTSFASTHI_MASK (0xFFFFFF << I40E_GLPES_TCPTXTOUTSFASTHI_TCPTXTOUTSFASTHI_SHIFT)
+#define I40E_GLPES_TCPTXTOUTSFASTLO 0x0001E050
+#define I40E_GLPES_TCPTXTOUTSFASTLO_TCPTXTOUTSFASTLO_SHIFT 0
+#define I40E_GLPES_TCPTXTOUTSFASTLO_TCPTXTOUTSFASTLO_MASK (0xFFFFFFFF << I40E_GLPES_TCPTXTOUTSFASTLO_TCPTXTOUTSFASTLO_SHIFT)
+#define I40E_GLPES_TCPTXTOUTSHI 0x0001E05C
+#define I40E_GLPES_TCPTXTOUTSHI_TCPTXTOUTSHI_SHIFT 0
+#define I40E_GLPES_TCPTXTOUTSHI_TCPTXTOUTSHI_MASK (0xFFFFFF << I40E_GLPES_TCPTXTOUTSHI_TCPTXTOUTSHI_SHIFT)
+#define I40E_GLPES_TCPTXTOUTSLO 0x0001E058
+#define I40E_GLPES_TCPTXTOUTSLO_TCPTXTOUTSLO_SHIFT 0
+#define I40E_GLPES_TCPTXTOUTSLO_TCPTXTOUTSLO_MASK (0xFFFFFFFF << I40E_GLPES_TCPTXTOUTSLO_TCPTXTOUTSLO_SHIFT)
+#define I40E_GLPES_VFIP4RXDISCARD(_i) (0x00018600 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFIP4RXDISCARD_MAX_INDEX 31
+#define I40E_GLPES_VFIP4RXDISCARD_IP4RXDISCARD_SHIFT 0
+#define I40E_GLPES_VFIP4RXDISCARD_IP4RXDISCARD_MASK (0xFFFFFFFF << I40E_GLPES_VFIP4RXDISCARD_IP4RXDISCARD_SHIFT)
+#define I40E_GLPES_VFIP4RXFRAGSHI(_i) (0x00018804 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFIP4RXFRAGSHI_MAX_INDEX 31
+#define I40E_GLPES_VFIP4RXFRAGSHI_IP4RXFRAGSHI_SHIFT 0
+#define I40E_GLPES_VFIP4RXFRAGSHI_IP4RXFRAGSHI_MASK (0xFFFF << I40E_GLPES_VFIP4RXFRAGSHI_IP4RXFRAGSHI_SHIFT)
+#define I40E_GLPES_VFIP4RXFRAGSLO(_i) (0x00018800 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFIP4RXFRAGSLO_MAX_INDEX 31
+#define I40E_GLPES_VFIP4RXFRAGSLO_IP4RXFRAGSLO_SHIFT 0
+#define I40E_GLPES_VFIP4RXFRAGSLO_IP4RXFRAGSLO_MASK (0xFFFFFFFF << I40E_GLPES_VFIP4RXFRAGSLO_IP4RXFRAGSLO_SHIFT)
+#define I40E_GLPES_VFIP4RXMCOCTSHI(_i) (0x00018A04 + ((_i) * 4))
+#define I40E_GLPES_VFIP4RXMCOCTSHI_MAX_INDEX 31
+#define I40E_GLPES_VFIP4RXMCOCTSHI_IP4RXMCOCTSHI_SHIFT 0
+#define I40E_GLPES_VFIP4RXMCOCTSHI_IP4RXMCOCTSHI_MASK (0xFFFF << I40E_GLPES_VFIP4RXMCOCTSHI_IP4RXMCOCTSHI_SHIFT)
+#define I40E_GLPES_VFIP4RXMCOCTSLO(_i) (0x00018A00 + ((_i) * 4))
+#define I40E_GLPES_VFIP4RXMCOCTSLO_MAX_INDEX 31
+#define I40E_GLPES_VFIP4RXMCOCTSLO_IP4RXMCOCTSLO_SHIFT 0
+#define I40E_GLPES_VFIP4RXMCOCTSLO_IP4RXMCOCTSLO_MASK (0xFFFFFFFF << I40E_GLPES_VFIP4RXMCOCTSLO_IP4RXMCOCTSLO_SHIFT)
+#define I40E_GLPES_VFIP4RXMCPKTSHI(_i) (0x00018C04 + ((_i) * 4))
+#define I40E_GLPES_VFIP4RXMCPKTSHI_MAX_INDEX 31
+#define I40E_GLPES_VFIP4RXMCPKTSHI_IP4RXMCPKTSHI_SHIFT 0
+#define I40E_GLPES_VFIP4RXMCPKTSHI_IP4RXMCPKTSHI_MASK (0xFFFF << I40E_GLPES_VFIP4RXMCPKTSHI_IP4RXMCPKTSHI_SHIFT)
+#define I40E_GLPES_VFIP4RXMCPKTSLO(_i) (0x00018C00 + ((_i) * 4))
+#define I40E_GLPES_VFIP4RXMCPKTSLO_MAX_INDEX 31
+#define I40E_GLPES_VFIP4RXMCPKTSLO_IP4RXMCPKTSLO_SHIFT 0
+#define I40E_GLPES_VFIP4RXMCPKTSLO_IP4RXMCPKTSLO_MASK (0xFFFFFFFF << I40E_GLPES_VFIP4RXMCPKTSLO_IP4RXMCPKTSLO_SHIFT)
+#define I40E_GLPES_VFIP4RXOCTSHI(_i) (0x00018204 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFIP4RXOCTSHI_MAX_INDEX 31
+#define I40E_GLPES_VFIP4RXOCTSHI_IP4RXOCTSHI_SHIFT 0
+#define I40E_GLPES_VFIP4RXOCTSHI_IP4RXOCTSHI_MASK (0xFFFF << I40E_GLPES_VFIP4RXOCTSHI_IP4RXOCTSHI_SHIFT)
+#define I40E_GLPES_VFIP4RXOCTSLO(_i) (0x00018200 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFIP4RXOCTSLO_MAX_INDEX 31
+#define I40E_GLPES_VFIP4RXOCTSLO_IP4RXOCTSLO_SHIFT 0
+#define I40E_GLPES_VFIP4RXOCTSLO_IP4RXOCTSLO_MASK (0xFFFFFFFF << I40E_GLPES_VFIP4RXOCTSLO_IP4RXOCTSLO_SHIFT)
+#define I40E_GLPES_VFIP4RXPKTSHI(_i) (0x00018404 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFIP4RXPKTSHI_MAX_INDEX 31
+#define I40E_GLPES_VFIP4RXPKTSHI_IP4RXPKTSHI_SHIFT 0
+#define I40E_GLPES_VFIP4RXPKTSHI_IP4RXPKTSHI_MASK (0xFFFF << I40E_GLPES_VFIP4RXPKTSHI_IP4RXPKTSHI_SHIFT)
+#define I40E_GLPES_VFIP4RXPKTSLO(_i) (0x00018400 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFIP4RXPKTSLO_MAX_INDEX 31
+#define I40E_GLPES_VFIP4RXPKTSLO_IP4RXPKTSLO_SHIFT 0
+#define I40E_GLPES_VFIP4RXPKTSLO_IP4RXPKTSLO_MASK (0xFFFFFFFF << I40E_GLPES_VFIP4RXPKTSLO_IP4RXPKTSLO_SHIFT)
+#define I40E_GLPES_VFIP4RXTRUNC(_i) (0x00018700 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFIP4RXTRUNC_MAX_INDEX 31
+#define I40E_GLPES_VFIP4RXTRUNC_IP4RXTRUNC_SHIFT 0
+#define I40E_GLPES_VFIP4RXTRUNC_IP4RXTRUNC_MASK (0xFFFFFFFF << I40E_GLPES_VFIP4RXTRUNC_IP4RXTRUNC_SHIFT)
+#define I40E_GLPES_VFIP4TXFRAGSHI(_i) (0x00019E04 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFIP4TXFRAGSHI_MAX_INDEX 31
+#define I40E_GLPES_VFIP4TXFRAGSHI_IP4TXFRAGSHI_SHIFT 0
+#define I40E_GLPES_VFIP4TXFRAGSHI_IP4TXFRAGSHI_MASK (0xFFFF << I40E_GLPES_VFIP4TXFRAGSHI_IP4TXFRAGSHI_SHIFT)
+#define I40E_GLPES_VFIP4TXFRAGSLO(_i) (0x00019E00 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFIP4TXFRAGSLO_MAX_INDEX 31
+#define I40E_GLPES_VFIP4TXFRAGSLO_IP4TXFRAGSLO_SHIFT 0
+#define I40E_GLPES_VFIP4TXFRAGSLO_IP4TXFRAGSLO_MASK (0xFFFFFFFF << I40E_GLPES_VFIP4TXFRAGSLO_IP4TXFRAGSLO_SHIFT)
+#define I40E_GLPES_VFIP4TXMCOCTSHI(_i) (0x0001A004 + ((_i) * 4))
+#define I40E_GLPES_VFIP4TXMCOCTSHI_MAX_INDEX 31
+#define I40E_GLPES_VFIP4TXMCOCTSHI_IP4TXMCOCTSHI_SHIFT 0
+#define I40E_GLPES_VFIP4TXMCOCTSHI_IP4TXMCOCTSHI_MASK (0xFFFF << I40E_GLPES_VFIP4TXMCOCTSHI_IP4TXMCOCTSHI_SHIFT)
+#define I40E_GLPES_VFIP4TXMCOCTSLO(_i) (0x0001A000 + ((_i) * 4))
+#define I40E_GLPES_VFIP4TXMCOCTSLO_MAX_INDEX 31
+#define I40E_GLPES_VFIP4TXMCOCTSLO_IP4TXMCOCTSLO_SHIFT 0
+#define I40E_GLPES_VFIP4TXMCOCTSLO_IP4TXMCOCTSLO_MASK (0xFFFFFFFF << I40E_GLPES_VFIP4TXMCOCTSLO_IP4TXMCOCTSLO_SHIFT)
+#define I40E_GLPES_VFIP4TXMCPKTSHI(_i) (0x0001A204 + ((_i) * 4))
+#define I40E_GLPES_VFIP4TXMCPKTSHI_MAX_INDEX 31
+#define I40E_GLPES_VFIP4TXMCPKTSHI_IP4TXMCPKTSHI_SHIFT 0
+#define I40E_GLPES_VFIP4TXMCPKTSHI_IP4TXMCPKTSHI_MASK (0xFFFF << I40E_GLPES_VFIP4TXMCPKTSHI_IP4TXMCPKTSHI_SHIFT)
+#define I40E_GLPES_VFIP4TXMCPKTSLO(_i) (0x0001A200 + ((_i) * 4))
+#define I40E_GLPES_VFIP4TXMCPKTSLO_MAX_INDEX 31
+#define I40E_GLPES_VFIP4TXMCPKTSLO_IP4TXMCPKTSLO_SHIFT 0
+#define I40E_GLPES_VFIP4TXMCPKTSLO_IP4TXMCPKTSLO_MASK (0xFFFFFFFF << I40E_GLPES_VFIP4TXMCPKTSLO_IP4TXMCPKTSLO_SHIFT)
+#define I40E_GLPES_VFIP4TXNOROUTE(_i) (0x0001AE00 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFIP4TXNOROUTE_MAX_INDEX 31
+#define I40E_GLPES_VFIP4TXNOROUTE_IP4TXNOROUTE_SHIFT 0
+#define I40E_GLPES_VFIP4TXNOROUTE_IP4TXNOROUTE_MASK (0xFFFFFF << I40E_GLPES_VFIP4TXNOROUTE_IP4TXNOROUTE_SHIFT)
+#define I40E_GLPES_VFIP4TXOCTSHI(_i) (0x00019A04 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFIP4TXOCTSHI_MAX_INDEX 31
+#define I40E_GLPES_VFIP4TXOCTSHI_IP4TXOCTSHI_SHIFT 0
+#define I40E_GLPES_VFIP4TXOCTSHI_IP4TXOCTSHI_MASK (0xFFFF << I40E_GLPES_VFIP4TXOCTSHI_IP4TXOCTSHI_SHIFT)
+#define I40E_GLPES_VFIP4TXOCTSLO(_i) (0x00019A00 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFIP4TXOCTSLO_MAX_INDEX 31
+#define I40E_GLPES_VFIP4TXOCTSLO_IP4TXOCTSLO_SHIFT 0
+#define I40E_GLPES_VFIP4TXOCTSLO_IP4TXOCTSLO_MASK (0xFFFFFFFF << I40E_GLPES_VFIP4TXOCTSLO_IP4TXOCTSLO_SHIFT)
+#define I40E_GLPES_VFIP4TXPKTSHI(_i) (0x00019C04 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFIP4TXPKTSHI_MAX_INDEX 31
+#define I40E_GLPES_VFIP4TXPKTSHI_IP4TXPKTSHI_SHIFT 0
+#define I40E_GLPES_VFIP4TXPKTSHI_IP4TXPKTSHI_MASK (0xFFFF << I40E_GLPES_VFIP4TXPKTSHI_IP4TXPKTSHI_SHIFT)
+#define I40E_GLPES_VFIP4TXPKTSLO(_i) (0x00019C00 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFIP4TXPKTSLO_MAX_INDEX 31
+#define I40E_GLPES_VFIP4TXPKTSLO_IP4TXPKTSLO_SHIFT 0
+#define I40E_GLPES_VFIP4TXPKTSLO_IP4TXPKTSLO_MASK (0xFFFFFFFF << I40E_GLPES_VFIP4TXPKTSLO_IP4TXPKTSLO_SHIFT)
+#define I40E_GLPES_VFIP6RXDISCARD(_i) (0x00019200 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFIP6RXDISCARD_MAX_INDEX 31
+#define I40E_GLPES_VFIP6RXDISCARD_IP6RXDISCARD_SHIFT 0
+#define I40E_GLPES_VFIP6RXDISCARD_IP6RXDISCARD_MASK (0xFFFFFFFF << I40E_GLPES_VFIP6RXDISCARD_IP6RXDISCARD_SHIFT)
+#define I40E_GLPES_VFIP6RXFRAGSHI(_i) (0x00019404 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFIP6RXFRAGSHI_MAX_INDEX 31
+#define I40E_GLPES_VFIP6RXFRAGSHI_IP6RXFRAGSHI_SHIFT 0
+#define I40E_GLPES_VFIP6RXFRAGSHI_IP6RXFRAGSHI_MASK (0xFFFF << I40E_GLPES_VFIP6RXFRAGSHI_IP6RXFRAGSHI_SHIFT)
+#define I40E_GLPES_VFIP6RXFRAGSLO(_i) (0x00019400 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFIP6RXFRAGSLO_MAX_INDEX 31
+#define I40E_GLPES_VFIP6RXFRAGSLO_IP6RXFRAGSLO_SHIFT 0
+#define I40E_GLPES_VFIP6RXFRAGSLO_IP6RXFRAGSLO_MASK (0xFFFFFFFF << I40E_GLPES_VFIP6RXFRAGSLO_IP6RXFRAGSLO_SHIFT)
+#define I40E_GLPES_VFIP6RXMCOCTSHI(_i) (0x00019604 + ((_i) * 4))
+#define I40E_GLPES_VFIP6RXMCOCTSHI_MAX_INDEX 31
+#define I40E_GLPES_VFIP6RXMCOCTSHI_IP6RXMCOCTSHI_SHIFT 0
+#define I40E_GLPES_VFIP6RXMCOCTSHI_IP6RXMCOCTSHI_MASK (0xFFFF << I40E_GLPES_VFIP6RXMCOCTSHI_IP6RXMCOCTSHI_SHIFT)
+#define I40E_GLPES_VFIP6RXMCOCTSLO(_i) (0x00019600 + ((_i) * 4))
+#define I40E_GLPES_VFIP6RXMCOCTSLO_MAX_INDEX 31
+#define I40E_GLPES_VFIP6RXMCOCTSLO_IP6RXMCOCTSLO_SHIFT 0
+#define I40E_GLPES_VFIP6RXMCOCTSLO_IP6RXMCOCTSLO_MASK (0xFFFFFFFF << I40E_GLPES_VFIP6RXMCOCTSLO_IP6RXMCOCTSLO_SHIFT)
+#define I40E_GLPES_VFIP6RXMCPKTSHI(_i) (0x00019804 + ((_i) * 4))
+#define I40E_GLPES_VFIP6RXMCPKTSHI_MAX_INDEX 31
+#define I40E_GLPES_VFIP6RXMCPKTSHI_IP6RXMCPKTSHI_SHIFT 0
+#define I40E_GLPES_VFIP6RXMCPKTSHI_IP6RXMCPKTSHI_MASK (0xFFFF << I40E_GLPES_VFIP6RXMCPKTSHI_IP6RXMCPKTSHI_SHIFT)
+#define I40E_GLPES_VFIP6RXMCPKTSLO(_i) (0x00019800 + ((_i) * 4))
+#define I40E_GLPES_VFIP6RXMCPKTSLO_MAX_INDEX 31
+#define I40E_GLPES_VFIP6RXMCPKTSLO_IP6RXMCPKTSLO_SHIFT 0
+#define I40E_GLPES_VFIP6RXMCPKTSLO_IP6RXMCPKTSLO_MASK (0xFFFFFFFF << I40E_GLPES_VFIP6RXMCPKTSLO_IP6RXMCPKTSLO_SHIFT)
+#define I40E_GLPES_VFIP6RXOCTSHI(_i) (0x00018E04 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFIP6RXOCTSHI_MAX_INDEX 31
+#define I40E_GLPES_VFIP6RXOCTSHI_IP6RXOCTSHI_SHIFT 0
+#define I40E_GLPES_VFIP6RXOCTSHI_IP6RXOCTSHI_MASK (0xFFFF << I40E_GLPES_VFIP6RXOCTSHI_IP6RXOCTSHI_SHIFT)
+#define I40E_GLPES_VFIP6RXOCTSLO(_i) (0x00018E00 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFIP6RXOCTSLO_MAX_INDEX 31
+#define I40E_GLPES_VFIP6RXOCTSLO_IP6RXOCTSLO_SHIFT 0
+#define I40E_GLPES_VFIP6RXOCTSLO_IP6RXOCTSLO_MASK (0xFFFFFFFF << I40E_GLPES_VFIP6RXOCTSLO_IP6RXOCTSLO_SHIFT)
+#define I40E_GLPES_VFIP6RXPKTSHI(_i) (0x00019004 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFIP6RXPKTSHI_MAX_INDEX 31
+#define I40E_GLPES_VFIP6RXPKTSHI_IP6RXPKTSHI_SHIFT 0
+#define I40E_GLPES_VFIP6RXPKTSHI_IP6RXPKTSHI_MASK (0xFFFF << I40E_GLPES_VFIP6RXPKTSHI_IP6RXPKTSHI_SHIFT)
+#define I40E_GLPES_VFIP6RXPKTSLO(_i) (0x00019000 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFIP6RXPKTSLO_MAX_INDEX 31
+#define I40E_GLPES_VFIP6RXPKTSLO_IP6RXPKTSLO_SHIFT 0
+#define I40E_GLPES_VFIP6RXPKTSLO_IP6RXPKTSLO_MASK (0xFFFFFFFF << I40E_GLPES_VFIP6RXPKTSLO_IP6RXPKTSLO_SHIFT)
+#define I40E_GLPES_VFIP6RXTRUNC(_i) (0x00019300 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFIP6RXTRUNC_MAX_INDEX 31
+#define I40E_GLPES_VFIP6RXTRUNC_IP6RXTRUNC_SHIFT 0
+#define I40E_GLPES_VFIP6RXTRUNC_IP6RXTRUNC_MASK (0xFFFFFFFF << I40E_GLPES_VFIP6RXTRUNC_IP6RXTRUNC_SHIFT)
+#define I40E_GLPES_VFIP6TXFRAGSHI(_i) (0x0001A804 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFIP6TXFRAGSHI_MAX_INDEX 31
+#define I40E_GLPES_VFIP6TXFRAGSHI_IP6TXFRAGSHI_SHIFT 0
+#define I40E_GLPES_VFIP6TXFRAGSHI_IP6TXFRAGSHI_MASK (0xFFFF << I40E_GLPES_VFIP6TXFRAGSHI_IP6TXFRAGSHI_SHIFT)
+#define I40E_GLPES_VFIP6TXFRAGSLO(_i) (0x0001A800 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFIP6TXFRAGSLO_MAX_INDEX 31
+#define I40E_GLPES_VFIP6TXFRAGSLO_IP6TXFRAGSLO_SHIFT 0
+#define I40E_GLPES_VFIP6TXFRAGSLO_IP6TXFRAGSLO_MASK (0xFFFFFFFF << I40E_GLPES_VFIP6TXFRAGSLO_IP6TXFRAGSLO_SHIFT)
+#define I40E_GLPES_VFIP6TXMCOCTSHI(_i) (0x0001AA04 + ((_i) * 4))
+#define I40E_GLPES_VFIP6TXMCOCTSHI_MAX_INDEX 31
+#define I40E_GLPES_VFIP6TXMCOCTSHI_IP6TXMCOCTSHI_SHIFT 0
+#define I40E_GLPES_VFIP6TXMCOCTSHI_IP6TXMCOCTSHI_MASK (0xFFFF << I40E_GLPES_VFIP6TXMCOCTSHI_IP6TXMCOCTSHI_SHIFT)
+#define I40E_GLPES_VFIP6TXMCOCTSLO(_i) (0x0001AA00 + ((_i) * 4))
+#define I40E_GLPES_VFIP6TXMCOCTSLO_MAX_INDEX 31
+#define I40E_GLPES_VFIP6TXMCOCTSLO_IP6TXMCOCTSLO_SHIFT 0
+#define I40E_GLPES_VFIP6TXMCOCTSLO_IP6TXMCOCTSLO_MASK (0xFFFFFFFF << I40E_GLPES_VFIP6TXMCOCTSLO_IP6TXMCOCTSLO_SHIFT)
+#define I40E_GLPES_VFIP6TXMCPKTSHI(_i) (0x0001AC04 + ((_i) * 4))
+#define I40E_GLPES_VFIP6TXMCPKTSHI_MAX_INDEX 31
+#define I40E_GLPES_VFIP6TXMCPKTSHI_IP6TXMCPKTSHI_SHIFT 0
+#define I40E_GLPES_VFIP6TXMCPKTSHI_IP6TXMCPKTSHI_MASK (0xFFFF << I40E_GLPES_VFIP6TXMCPKTSHI_IP6TXMCPKTSHI_SHIFT)
+#define I40E_GLPES_VFIP6TXMCPKTSLO(_i) (0x0001AC00 + ((_i) * 4))
+#define I40E_GLPES_VFIP6TXMCPKTSLO_MAX_INDEX 31
+#define I40E_GLPES_VFIP6TXMCPKTSLO_IP6TXMCPKTSLO_SHIFT 0
+#define I40E_GLPES_VFIP6TXMCPKTSLO_IP6TXMCPKTSLO_MASK (0xFFFFFFFF << I40E_GLPES_VFIP6TXMCPKTSLO_IP6TXMCPKTSLO_SHIFT)
+#define I40E_GLPES_VFIP6TXNOROUTE(_i) (0x0001AF00 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFIP6TXNOROUTE_MAX_INDEX 31
+#define I40E_GLPES_VFIP6TXNOROUTE_IP6TXNOROUTE_SHIFT 0
+#define I40E_GLPES_VFIP6TXNOROUTE_IP6TXNOROUTE_MASK (0xFFFFFF << I40E_GLPES_VFIP6TXNOROUTE_IP6TXNOROUTE_SHIFT)
+#define I40E_GLPES_VFIP6TXOCTSHI(_i) (0x0001A404 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFIP6TXOCTSHI_MAX_INDEX 31
+#define I40E_GLPES_VFIP6TXOCTSHI_IP6TXOCTSHI_SHIFT 0
+#define I40E_GLPES_VFIP6TXOCTSHI_IP6TXOCTSHI_MASK (0xFFFF << I40E_GLPES_VFIP6TXOCTSHI_IP6TXOCTSHI_SHIFT)
+#define I40E_GLPES_VFIP6TXOCTSLO(_i) (0x0001A400 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFIP6TXOCTSLO_MAX_INDEX 31
+#define I40E_GLPES_VFIP6TXOCTSLO_IP6TXOCTSLO_SHIFT 0
+#define I40E_GLPES_VFIP6TXOCTSLO_IP6TXOCTSLO_MASK (0xFFFFFFFF << I40E_GLPES_VFIP6TXOCTSLO_IP6TXOCTSLO_SHIFT)
+#define I40E_GLPES_VFIP6TXPKTSHI(_i) (0x0001A604 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFIP6TXPKTSHI_MAX_INDEX 31
+#define I40E_GLPES_VFIP6TXPKTSHI_IP6TXPKTSHI_SHIFT 0
+#define I40E_GLPES_VFIP6TXPKTSHI_IP6TXPKTSHI_MASK (0xFFFF << I40E_GLPES_VFIP6TXPKTSHI_IP6TXPKTSHI_SHIFT)
+#define I40E_GLPES_VFIP6TXPKTSLO(_i) (0x0001A600 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFIP6TXPKTSLO_MAX_INDEX 31
+#define I40E_GLPES_VFIP6TXPKTSLO_IP6TXPKTSLO_SHIFT 0
+#define I40E_GLPES_VFIP6TXPKTSLO_IP6TXPKTSLO_MASK (0xFFFFFFFF << I40E_GLPES_VFIP6TXPKTSLO_IP6TXPKTSLO_SHIFT)
+#define I40E_GLPES_VFRDMARXRDSHI(_i) (0x0001BE04 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFRDMARXRDSHI_MAX_INDEX 31
+#define I40E_GLPES_VFRDMARXRDSHI_RDMARXRDSHI_SHIFT 0
+#define I40E_GLPES_VFRDMARXRDSHI_RDMARXRDSHI_MASK (0xFFFF << I40E_GLPES_VFRDMARXRDSHI_RDMARXRDSHI_SHIFT)
+#define I40E_GLPES_VFRDMARXRDSLO(_i) (0x0001BE00 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFRDMARXRDSLO_MAX_INDEX 31
+#define I40E_GLPES_VFRDMARXRDSLO_RDMARXRDSLO_SHIFT 0
+#define I40E_GLPES_VFRDMARXRDSLO_RDMARXRDSLO_MASK (0xFFFFFFFF << I40E_GLPES_VFRDMARXRDSLO_RDMARXRDSLO_SHIFT)
+#define I40E_GLPES_VFRDMARXSNDSHI(_i) (0x0001C004 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFRDMARXSNDSHI_MAX_INDEX 31
+#define I40E_GLPES_VFRDMARXSNDSHI_RDMARXSNDSHI_SHIFT 0
+#define I40E_GLPES_VFRDMARXSNDSHI_RDMARXSNDSHI_MASK (0xFFFF << I40E_GLPES_VFRDMARXSNDSHI_RDMARXSNDSHI_SHIFT)
+#define I40E_GLPES_VFRDMARXSNDSLO(_i) (0x0001C000 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFRDMARXSNDSLO_MAX_INDEX 31
+#define I40E_GLPES_VFRDMARXSNDSLO_RDMARXSNDSLO_SHIFT 0
+#define I40E_GLPES_VFRDMARXSNDSLO_RDMARXSNDSLO_MASK (0xFFFFFFFF << I40E_GLPES_VFRDMARXSNDSLO_RDMARXSNDSLO_SHIFT)
+#define I40E_GLPES_VFRDMARXWRSHI(_i) (0x0001BC04 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFRDMARXWRSHI_MAX_INDEX 31
+#define I40E_GLPES_VFRDMARXWRSHI_RDMARXWRSHI_SHIFT 0
+#define I40E_GLPES_VFRDMARXWRSHI_RDMARXWRSHI_MASK (0xFFFF << I40E_GLPES_VFRDMARXWRSHI_RDMARXWRSHI_SHIFT)
+#define I40E_GLPES_VFRDMARXWRSLO(_i) (0x0001BC00 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFRDMARXWRSLO_MAX_INDEX 31
+#define I40E_GLPES_VFRDMARXWRSLO_RDMARXWRSLO_SHIFT 0
+#define I40E_GLPES_VFRDMARXWRSLO_RDMARXWRSLO_MASK (0xFFFFFFFF << I40E_GLPES_VFRDMARXWRSLO_RDMARXWRSLO_SHIFT)
+#define I40E_GLPES_VFRDMATXRDSHI(_i) (0x0001C404 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFRDMATXRDSHI_MAX_INDEX 31
+#define I40E_GLPES_VFRDMATXRDSHI_RDMARXRDSHI_SHIFT 0
+#define I40E_GLPES_VFRDMATXRDSHI_RDMARXRDSHI_MASK (0xFFFF << I40E_GLPES_VFRDMATXRDSHI_RDMARXRDSHI_SHIFT)
+#define I40E_GLPES_VFRDMATXRDSLO(_i) (0x0001C400 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFRDMATXRDSLO_MAX_INDEX 31
+#define I40E_GLPES_VFRDMATXRDSLO_RDMARXRDSLO_SHIFT 0
+#define I40E_GLPES_VFRDMATXRDSLO_RDMARXRDSLO_MASK (0xFFFFFFFF << I40E_GLPES_VFRDMATXRDSLO_RDMARXRDSLO_SHIFT)
+#define I40E_GLPES_VFRDMATXSNDSHI(_i) (0x0001C604 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFRDMATXSNDSHI_MAX_INDEX 31
+#define I40E_GLPES_VFRDMATXSNDSHI_RDMARXSNDSHI_SHIFT 0
+#define I40E_GLPES_VFRDMATXSNDSHI_RDMARXSNDSHI_MASK (0xFFFF << I40E_GLPES_VFRDMATXSNDSHI_RDMARXSNDSHI_SHIFT)
+#define I40E_GLPES_VFRDMATXSNDSLO(_i) (0x0001C600 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFRDMATXSNDSLO_MAX_INDEX 31
+#define I40E_GLPES_VFRDMATXSNDSLO_RDMARXSNDSLO_SHIFT 0
+#define I40E_GLPES_VFRDMATXSNDSLO_RDMARXSNDSLO_MASK (0xFFFFFFFF << I40E_GLPES_VFRDMATXSNDSLO_RDMARXSNDSLO_SHIFT)
+#define I40E_GLPES_VFRDMATXWRSHI(_i) (0x0001C204 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFRDMATXWRSHI_MAX_INDEX 31
+#define I40E_GLPES_VFRDMATXWRSHI_RDMARXWRSHI_SHIFT 0
+#define I40E_GLPES_VFRDMATXWRSHI_RDMARXWRSHI_MASK (0xFFFF << I40E_GLPES_VFRDMATXWRSHI_RDMARXWRSHI_SHIFT)
+#define I40E_GLPES_VFRDMATXWRSLO(_i) (0x0001C200 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFRDMATXWRSLO_MAX_INDEX 31
+#define I40E_GLPES_VFRDMATXWRSLO_RDMARXWRSLO_SHIFT 0
+#define I40E_GLPES_VFRDMATXWRSLO_RDMARXWRSLO_MASK (0xFFFFFFFF << I40E_GLPES_VFRDMATXWRSLO_RDMARXWRSLO_SHIFT)
+#define I40E_GLPES_VFRDMAVBNDHI(_i) (0x0001C804 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFRDMAVBNDHI_MAX_INDEX 31
+#define I40E_GLPES_VFRDMAVBNDHI_RDMAVBNDHI_SHIFT 0
+#define I40E_GLPES_VFRDMAVBNDHI_RDMAVBNDHI_MASK (0xFFFFFFFF << I40E_GLPES_VFRDMAVBNDHI_RDMAVBNDHI_SHIFT)
+#define I40E_GLPES_VFRDMAVBNDLO(_i) (0x0001C800 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFRDMAVBNDLO_MAX_INDEX 31
+#define I40E_GLPES_VFRDMAVBNDLO_RDMAVBNDLO_SHIFT 0
+#define I40E_GLPES_VFRDMAVBNDLO_RDMAVBNDLO_MASK (0xFFFFFFFF << I40E_GLPES_VFRDMAVBNDLO_RDMAVBNDLO_SHIFT)
+#define I40E_GLPES_VFRDMAVINVHI(_i) (0x0001CA04 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFRDMAVINVHI_MAX_INDEX 31
+#define I40E_GLPES_VFRDMAVINVHI_RDMAVINVHI_SHIFT 0
+#define I40E_GLPES_VFRDMAVINVHI_RDMAVINVHI_MASK (0xFFFFFFFF << I40E_GLPES_VFRDMAVINVHI_RDMAVINVHI_SHIFT)
+#define I40E_GLPES_VFRDMAVINVLO(_i) (0x0001CA00 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFRDMAVINVLO_MAX_INDEX 31
+#define I40E_GLPES_VFRDMAVINVLO_RDMAVINVLO_SHIFT 0
+#define I40E_GLPES_VFRDMAVINVLO_RDMAVINVLO_MASK (0xFFFFFFFF << I40E_GLPES_VFRDMAVINVLO_RDMAVINVLO_SHIFT)
+#define I40E_GLPES_VFRXVLANERR(_i) (0x00018000 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFRXVLANERR_MAX_INDEX 31
+#define I40E_GLPES_VFRXVLANERR_RXVLANERR_SHIFT 0
+#define I40E_GLPES_VFRXVLANERR_RXVLANERR_MASK (0xFFFFFF << I40E_GLPES_VFRXVLANERR_RXVLANERR_SHIFT)
+#define I40E_GLPES_VFTCPRTXSEG(_i) (0x0001B600 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFTCPRTXSEG_MAX_INDEX 31
+#define I40E_GLPES_VFTCPRTXSEG_TCPRTXSEG_SHIFT 0
+#define I40E_GLPES_VFTCPRTXSEG_TCPRTXSEG_MASK (0xFFFFFFFF << I40E_GLPES_VFTCPRTXSEG_TCPRTXSEG_SHIFT)
+#define I40E_GLPES_VFTCPRXOPTERR(_i) (0x0001B200 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFTCPRXOPTERR_MAX_INDEX 31
+#define I40E_GLPES_VFTCPRXOPTERR_TCPRXOPTERR_SHIFT 0
+#define I40E_GLPES_VFTCPRXOPTERR_TCPRXOPTERR_MASK (0xFFFFFF << I40E_GLPES_VFTCPRXOPTERR_TCPRXOPTERR_SHIFT)
+#define I40E_GLPES_VFTCPRXPROTOERR(_i) (0x0001B300 + ((_i) * 4))
+#define I40E_GLPES_VFTCPRXPROTOERR_MAX_INDEX 31
+#define I40E_GLPES_VFTCPRXPROTOERR_TCPRXPROTOERR_SHIFT 0
+#define I40E_GLPES_VFTCPRXPROTOERR_TCPRXPROTOERR_MASK (0xFFFFFF << I40E_GLPES_VFTCPRXPROTOERR_TCPRXPROTOERR_SHIFT)
+#define I40E_GLPES_VFTCPRXSEGSHI(_i) (0x0001B004 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFTCPRXSEGSHI_MAX_INDEX 31
+#define I40E_GLPES_VFTCPRXSEGSHI_TCPRXSEGSHI_SHIFT 0
+#define I40E_GLPES_VFTCPRXSEGSHI_TCPRXSEGSHI_MASK (0xFFFF << I40E_GLPES_VFTCPRXSEGSHI_TCPRXSEGSHI_SHIFT)
+#define I40E_GLPES_VFTCPRXSEGSLO(_i) (0x0001B000 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFTCPRXSEGSLO_MAX_INDEX 31
+#define I40E_GLPES_VFTCPRXSEGSLO_TCPRXSEGSLO_SHIFT 0
+#define I40E_GLPES_VFTCPRXSEGSLO_TCPRXSEGSLO_MASK (0xFFFFFFFF << I40E_GLPES_VFTCPRXSEGSLO_TCPRXSEGSLO_SHIFT)
+#define I40E_GLPES_VFTCPTXSEGHI(_i) (0x0001B404 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFTCPTXSEGHI_MAX_INDEX 31
+#define I40E_GLPES_VFTCPTXSEGHI_TCPTXSEGHI_SHIFT 0
+#define I40E_GLPES_VFTCPTXSEGHI_TCPTXSEGHI_MASK (0xFFFF << I40E_GLPES_VFTCPTXSEGHI_TCPTXSEGHI_SHIFT)
+#define I40E_GLPES_VFTCPTXSEGLO(_i) (0x0001B400 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFTCPTXSEGLO_MAX_INDEX 31
+#define I40E_GLPES_VFTCPTXSEGLO_TCPTXSEGLO_SHIFT 0
+#define I40E_GLPES_VFTCPTXSEGLO_TCPTXSEGLO_MASK (0xFFFFFFFF << I40E_GLPES_VFTCPTXSEGLO_TCPTXSEGLO_SHIFT)
+#define I40E_GLPES_VFUDPRXPKTSHI(_i) (0x0001B804 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFUDPRXPKTSHI_MAX_INDEX 31
+#define I40E_GLPES_VFUDPRXPKTSHI_UDPRXPKTSHI_SHIFT 0
+#define I40E_GLPES_VFUDPRXPKTSHI_UDPRXPKTSHI_MASK (0xFFFF << I40E_GLPES_VFUDPRXPKTSHI_UDPRXPKTSHI_SHIFT)
+#define I40E_GLPES_VFUDPRXPKTSLO(_i) (0x0001B800 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFUDPRXPKTSLO_MAX_INDEX 31
+#define I40E_GLPES_VFUDPRXPKTSLO_UDPRXPKTSLO_SHIFT 0
+#define I40E_GLPES_VFUDPRXPKTSLO_UDPRXPKTSLO_MASK (0xFFFFFFFF << I40E_GLPES_VFUDPRXPKTSLO_UDPRXPKTSLO_SHIFT)
+#define I40E_GLPES_VFUDPTXPKTSHI(_i) (0x0001BA04 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFUDPTXPKTSHI_MAX_INDEX 31
+#define I40E_GLPES_VFUDPTXPKTSHI_UDPTXPKTSHI_SHIFT 0
+#define I40E_GLPES_VFUDPTXPKTSHI_UDPTXPKTSHI_MASK (0xFFFF << I40E_GLPES_VFUDPTXPKTSHI_UDPTXPKTSHI_SHIFT)
+#define I40E_GLPES_VFUDPTXPKTSLO(_i) (0x0001BA00 + ((_i) * 4)) /* _i=0...31 */
+#define I40E_GLPES_VFUDPTXPKTSLO_MAX_INDEX 31
+#define I40E_GLPES_VFUDPTXPKTSLO_UDPTXPKTSLO_SHIFT 0
+#define I40E_GLPES_VFUDPTXPKTSLO_UDPTXPKTSLO_MASK (0xFFFFFFFF << I40E_GLPES_VFUDPTXPKTSLO_UDPTXPKTSLO_SHIFT)
+#define I40E_GLPM_DMACR 0x000881F4
+#define I40E_GLPM_DMACR_DMACWT_SHIFT 0
+#define I40E_GLPM_DMACR_DMACWT_MASK (0xFFFF << I40E_GLPM_DMACR_DMACWT_SHIFT)
+#define I40E_GLPM_DMACR_EXIT_DC_SHIFT 29
+#define I40E_GLPM_DMACR_EXIT_DC_MASK (0x1 << I40E_GLPM_DMACR_EXIT_DC_SHIFT)
+#define I40E_GLPM_DMACR_LX_COALESCING_INDICATION_SHIFT 30
+#define I40E_GLPM_DMACR_LX_COALESCING_INDICATION_MASK (0x1 << I40E_GLPM_DMACR_LX_COALESCING_INDICATION_SHIFT)
+#define I40E_GLPM_DMACR_DMAC_EN_SHIFT 31
+#define I40E_GLPM_DMACR_DMAC_EN_MASK (0x1 << I40E_GLPM_DMACR_DMAC_EN_SHIFT)
+#define I40E_GLPM_LTRC 0x000BE500
+#define I40E_GLPM_LTRC_SLTRV_SHIFT 0
+#define I40E_GLPM_LTRC_SLTRV_MASK (0x3FF << I40E_GLPM_LTRC_SLTRV_SHIFT)
+#define I40E_GLPM_LTRC_SSCALE_SHIFT 10
+#define I40E_GLPM_LTRC_SSCALE_MASK (0x7 << I40E_GLPM_LTRC_SSCALE_SHIFT)
+#define I40E_GLPM_LTRC_LTRS_REQUIREMENT_SHIFT 15
+#define I40E_GLPM_LTRC_LTRS_REQUIREMENT_MASK (0x1 << I40E_GLPM_LTRC_LTRS_REQUIREMENT_SHIFT)
+#define I40E_GLPM_LTRC_NSLTRV_SHIFT 16
+#define I40E_GLPM_LTRC_NSLTRV_MASK (0x3FF << I40E_GLPM_LTRC_NSLTRV_SHIFT)
+#define I40E_GLPM_LTRC_NSSCALE_SHIFT 26
+#define I40E_GLPM_LTRC_NSSCALE_MASK (0x7 << I40E_GLPM_LTRC_NSSCALE_SHIFT)
+#define I40E_GLPM_LTRC_LTR_SEND_SHIFT 30
+#define I40E_GLPM_LTRC_LTR_SEND_MASK (0x1 << I40E_GLPM_LTRC_LTR_SEND_SHIFT)
+#define I40E_GLPM_LTRC_LTRNS_REQUIREMENT_SHIFT 31
+#define I40E_GLPM_LTRC_LTRNS_REQUIREMENT_MASK (0x1 << I40E_GLPM_LTRC_LTRNS_REQUIREMENT_SHIFT)
+#define I40E_PRTPM_EEE_STAT 0x001E4320
+#define I40E_PRTPM_EEE_STAT_EEE_NEG_SHIFT 29
+#define I40E_PRTPM_EEE_STAT_EEE_NEG_MASK (0x1 << I40E_PRTPM_EEE_STAT_EEE_NEG_SHIFT)
+#define I40E_PRTPM_EEE_STAT_RX_LPI_STATUS_SHIFT 30
+#define I40E_PRTPM_EEE_STAT_RX_LPI_STATUS_MASK (0x1 << I40E_PRTPM_EEE_STAT_RX_LPI_STATUS_SHIFT)
+#define I40E_PRTPM_EEE_STAT_TX_LPI_STATUS_SHIFT 31
+#define I40E_PRTPM_EEE_STAT_TX_LPI_STATUS_MASK (0x1 << I40E_PRTPM_EEE_STAT_TX_LPI_STATUS_SHIFT)
+#define I40E_PRTPM_EEEC 0x001E4380
+#define I40E_PRTPM_EEEC_TW_WAKE_MIN_SHIFT 16
+#define I40E_PRTPM_EEEC_TW_WAKE_MIN_MASK (0x3F << I40E_PRTPM_EEEC_TW_WAKE_MIN_SHIFT)
+#define I40E_PRTPM_EEEC_TX_LU_LPI_DLY_SHIFT 24
+#define I40E_PRTPM_EEEC_TX_LU_LPI_DLY_MASK (0x3 << I40E_PRTPM_EEEC_TX_LU_LPI_DLY_SHIFT)
+#define I40E_PRTPM_EEEC_TEEE_DLY_SHIFT 26
+#define I40E_PRTPM_EEEC_TEEE_DLY_MASK (0x3F << I40E_PRTPM_EEEC_TEEE_DLY_SHIFT)
+#define I40E_PRTPM_EEEFWD 0x001E4400
+#define I40E_PRTPM_EEEFWD_EEE_FW_CONFIG_DONE_SHIFT 31
+#define I40E_PRTPM_EEEFWD_EEE_FW_CONFIG_DONE_MASK (0x1 << I40E_PRTPM_EEEFWD_EEE_FW_CONFIG_DONE_SHIFT)
+#define I40E_PRTPM_EEER 0x001E4360
+#define I40E_PRTPM_EEER_TW_SYSTEM_SHIFT 0
+#define I40E_PRTPM_EEER_TW_SYSTEM_MASK (0xFFFF << I40E_PRTPM_EEER_TW_SYSTEM_SHIFT)
+#define I40E_PRTPM_EEER_TX_LPI_EN_SHIFT 16
+#define I40E_PRTPM_EEER_TX_LPI_EN_MASK (0x1 << I40E_PRTPM_EEER_TX_LPI_EN_SHIFT)
+#define I40E_PRTPM_EEETXC 0x001E43E0
+#define I40E_PRTPM_EEETXC_TW_PHY_SHIFT 0
+#define I40E_PRTPM_EEETXC_TW_PHY_MASK (0xFFFF << I40E_PRTPM_EEETXC_TW_PHY_SHIFT)
+#define I40E_PRTPM_GC 0x000B8140
+#define I40E_PRTPM_GC_EMP_LINK_ON_SHIFT 0
+#define I40E_PRTPM_GC_EMP_LINK_ON_MASK (0x1 << I40E_PRTPM_GC_EMP_LINK_ON_SHIFT)
+#define I40E_PRTPM_GC_MNG_VETO_SHIFT 1
+#define I40E_PRTPM_GC_MNG_VETO_MASK (0x1 << I40E_PRTPM_GC_MNG_VETO_SHIFT)
+#define I40E_PRTPM_GC_RATD_SHIFT 2
+#define I40E_PRTPM_GC_RATD_MASK (0x1 << I40E_PRTPM_GC_RATD_SHIFT)
+#define I40E_PRTPM_GC_LCDMP_SHIFT 3
+#define I40E_PRTPM_GC_LCDMP_MASK (0x1 << I40E_PRTPM_GC_LCDMP_SHIFT)
+#define I40E_PRTPM_GC_LPLU_ASSERTED_SHIFT 31
+#define I40E_PRTPM_GC_LPLU_ASSERTED_MASK (0x1 << I40E_PRTPM_GC_LPLU_ASSERTED_SHIFT)
+#define I40E_PRTPM_HPTC 0x000AC800
+#define I40E_PRTPM_HPTC_HIGH_PRI_TC_SHIFT 0
+#define I40E_PRTPM_HPTC_HIGH_PRI_TC_MASK (0xFF << I40E_PRTPM_HPTC_HIGH_PRI_TC_SHIFT)
+#define I40E_PRTPM_RLPIC 0x001E43A0
+#define I40E_PRTPM_RLPIC_ERLPIC_SHIFT 0
+#define I40E_PRTPM_RLPIC_ERLPIC_MASK (0xFFFFFFFF << I40E_PRTPM_RLPIC_ERLPIC_SHIFT)
+#define I40E_PRTPM_TLPIC 0x001E43C0
+#define I40E_PRTPM_TLPIC_ETLPIC_SHIFT 0
+#define I40E_PRTPM_TLPIC_ETLPIC_MASK (0xFFFFFFFF << I40E_PRTPM_TLPIC_ETLPIC_SHIFT)
+#define I40E_GLRPB_DPSS 0x000AC828
+#define I40E_GLRPB_DPSS_DPS_TCN_SHIFT 0
+#define I40E_GLRPB_DPSS_DPS_TCN_MASK (0xFFFFF << I40E_GLRPB_DPSS_DPS_TCN_SHIFT)
+#define I40E_GLRPB_GHW 0x000AC830
+#define I40E_GLRPB_GHW_GHW_SHIFT 0
+#define I40E_GLRPB_GHW_GHW_MASK (0xFFFFF << I40E_GLRPB_GHW_GHW_SHIFT)
+#define I40E_GLRPB_GLW 0x000AC834
+#define I40E_GLRPB_GLW_GLW_SHIFT 0
+#define I40E_GLRPB_GLW_GLW_MASK (0xFFFFF << I40E_GLRPB_GLW_GLW_SHIFT)
+#define I40E_GLRPB_PHW 0x000AC844
+#define I40E_GLRPB_PHW_PHW_SHIFT 0
+#define I40E_GLRPB_PHW_PHW_MASK (0xFFFFF << I40E_GLRPB_PHW_PHW_SHIFT)
+#define I40E_GLRPB_PLW 0x000AC848
+#define I40E_GLRPB_PLW_PLW_SHIFT 0
+#define I40E_GLRPB_PLW_PLW_MASK (0xFFFFF << I40E_GLRPB_PLW_PLW_SHIFT)
+#define I40E_PRTRPB_DHW(_i) (0x000AC100 + ((_i) * 32)) /* _i=0...7 */
+#define I40E_PRTRPB_DHW_MAX_INDEX 7
+#define I40E_PRTRPB_DHW_DHW_TCN_SHIFT 0
+#define I40E_PRTRPB_DHW_DHW_TCN_MASK (0xFFFFF << I40E_PRTRPB_DHW_DHW_TCN_SHIFT)
+#define I40E_PRTRPB_DLW(_i) (0x000AC220 + ((_i) * 32)) /* _i=0...7 */
+#define I40E_PRTRPB_DLW_MAX_INDEX 7
+#define I40E_PRTRPB_DLW_DLW_TCN_SHIFT 0
+#define I40E_PRTRPB_DLW_DLW_TCN_MASK (0xFFFFF << I40E_PRTRPB_DLW_DLW_TCN_SHIFT)
+#define I40E_PRTRPB_DPS(_i) (0x000AC320 + ((_i) * 32)) /* _i=0...7 */
+#define I40E_PRTRPB_DPS_MAX_INDEX 7
+#define I40E_PRTRPB_DPS_DPS_TCN_SHIFT 0
+#define I40E_PRTRPB_DPS_DPS_TCN_MASK (0xFFFFF << I40E_PRTRPB_DPS_DPS_TCN_SHIFT)
+#define I40E_PRTRPB_SHT(_i) (0x000AC480 + ((_i) * 32)) /* _i=0...7 */
+#define I40E_PRTRPB_SHT_MAX_INDEX 7
+#define I40E_PRTRPB_SHT_SHT_TCN_SHIFT 0
+#define I40E_PRTRPB_SHT_SHT_TCN_MASK (0xFFFFF << I40E_PRTRPB_SHT_SHT_TCN_SHIFT)
+#define I40E_PRTRPB_SHW 0x000AC580
+#define I40E_PRTRPB_SHW_SHW_SHIFT 0
+#define I40E_PRTRPB_SHW_SHW_MASK (0xFFFFF << I40E_PRTRPB_SHW_SHW_SHIFT)
+#define I40E_PRTRPB_SLT(_i) (0x000AC5A0 + ((_i) * 32)) /* _i=0...7 */
+#define I40E_PRTRPB_SLT_MAX_INDEX 7
+#define I40E_PRTRPB_SLT_SLT_TCN_SHIFT 0
+#define I40E_PRTRPB_SLT_SLT_TCN_MASK (0xFFFFF << I40E_PRTRPB_SLT_SLT_TCN_SHIFT)
+#define I40E_PRTRPB_SLW 0x000AC6A0
+#define I40E_PRTRPB_SLW_SLW_SHIFT 0
+#define I40E_PRTRPB_SLW_SLW_MASK (0xFFFFF << I40E_PRTRPB_SLW_SLW_SHIFT)
+#define I40E_PRTRPB_SPS 0x000AC7C0
+#define I40E_PRTRPB_SPS_SPS_SHIFT 0
+#define I40E_PRTRPB_SPS_SPS_MASK (0xFFFFF << I40E_PRTRPB_SPS_SPS_SHIFT)
+#define I40E_GLQF_APBVT(_i) (0x00260000 + ((_i) * 4)) /* _i=0...2047 */
+#define I40E_GLQF_APBVT_MAX_INDEX 2047
+#define I40E_GLQF_APBVT_APBVT_SHIFT 0
+#define I40E_GLQF_APBVT_APBVT_MASK (0xFFFFFFFF << I40E_GLQF_APBVT_APBVT_SHIFT)
+#define I40E_GLQF_CTL 0x00269BA4
+#define I40E_GLQF_CTL_HTOEP_SHIFT 1
+#define I40E_GLQF_CTL_HTOEP_MASK (0x1 << I40E_GLQF_CTL_HTOEP_SHIFT)
+#define I40E_GLQF_CTL_HTOEP_FCOE_SHIFT 2
+#define I40E_GLQF_CTL_HTOEP_FCOE_MASK (0x1 << I40E_GLQF_CTL_HTOEP_FCOE_SHIFT)
+#define I40E_GLQF_CTL_PCNT_ALLOC_SHIFT 3
+#define I40E_GLQF_CTL_PCNT_ALLOC_MASK (0x7 << I40E_GLQF_CTL_PCNT_ALLOC_SHIFT)
+#define I40E_GLQF_CTL_DDPLPEN_SHIFT 7
+#define I40E_GLQF_CTL_DDPLPEN_MASK (0x1 << I40E_GLQF_CTL_DDPLPEN_SHIFT)
+#define I40E_GLQF_CTL_MAXPEBLEN_SHIFT 8
+#define I40E_GLQF_CTL_MAXPEBLEN_MASK (0x7 << I40E_GLQF_CTL_MAXPEBLEN_SHIFT)
+#define I40E_GLQF_CTL_MAXFCBLEN_SHIFT 11
+#define I40E_GLQF_CTL_MAXFCBLEN_MASK (0x7 << I40E_GLQF_CTL_MAXFCBLEN_SHIFT)
+#define I40E_GLQF_CTL_MAXFDBLEN_SHIFT 14
+#define I40E_GLQF_CTL_MAXFDBLEN_MASK (0x7 << I40E_GLQF_CTL_MAXFDBLEN_SHIFT)
+#define I40E_GLQF_CTL_FDBEST_SHIFT 17
+#define I40E_GLQF_CTL_FDBEST_MASK (0xFF << I40E_GLQF_CTL_FDBEST_SHIFT)
+#define I40E_GLQF_CTL_PROGPRIO_SHIFT 25
+#define I40E_GLQF_CTL_PROGPRIO_MASK (0x1 << I40E_GLQF_CTL_PROGPRIO_SHIFT)
+#define I40E_GLQF_CTL_INVALPRIO_SHIFT 26
+#define I40E_GLQF_CTL_INVALPRIO_MASK (0x1 << I40E_GLQF_CTL_INVALPRIO_SHIFT)
+#define I40E_GLQF_CTL_IGNORE_IP_SHIFT 27
+#define I40E_GLQF_CTL_IGNORE_IP_MASK (0x1 << I40E_GLQF_CTL_IGNORE_IP_SHIFT)
+#define I40E_GLQF_FDCNT_0 0x00269BAC
+#define I40E_GLQF_FDCNT_0_GUARANT_CNT_SHIFT 0
+#define I40E_GLQF_FDCNT_0_GUARANT_CNT_MASK (0x1FFF << I40E_GLQF_FDCNT_0_GUARANT_CNT_SHIFT)
+#define I40E_GLQF_FDCNT_0_BESTCNT_SHIFT 13
+#define I40E_GLQF_FDCNT_0_BESTCNT_MASK (0x1FFF << I40E_GLQF_FDCNT_0_BESTCNT_SHIFT)
+#define I40E_GLQF_HSYM(_i) (0x00269D00 + ((_i) * 4)) /* _i=0...63 */
+#define I40E_GLQF_HSYM_MAX_INDEX 63
+#define I40E_GLQF_HSYM_SYMH_ENA_SHIFT 0
+#define I40E_GLQF_HSYM_SYMH_ENA_MASK (0x1 << I40E_GLQF_HSYM_SYMH_ENA_SHIFT)
+#define I40E_GLQF_PCNT(_i) (0x00266800 + ((_i) * 4)) /* _i=0...511 */
+#define I40E_GLQF_PCNT_MAX_INDEX 511
+#define I40E_GLQF_PCNT_PCNT_SHIFT 0
+#define I40E_GLQF_PCNT_PCNT_MASK (0xFFFFFFFF << I40E_GLQF_PCNT_PCNT_SHIFT)
+#define I40E_GLQF_SWAP(_i, _j) (0x00267E00 + ((_i) * 4 + (_j) * 8)) /* _i=0...1, _j=0...63 */
+#define I40E_GLQF_SWAP_MAX_INDEX 1
+#define I40E_GLQF_SWAP_OFF0_SRC0_SHIFT 0
+#define I40E_GLQF_SWAP_OFF0_SRC0_MASK (0x3F << I40E_GLQF_SWAP_OFF0_SRC0_SHIFT)
+#define I40E_GLQF_SWAP_OFF0_SRC1_SHIFT 6
+#define I40E_GLQF_SWAP_OFF0_SRC1_MASK (0x3F << I40E_GLQF_SWAP_OFF0_SRC1_SHIFT)
+#define I40E_GLQF_SWAP_FLEN0_SHIFT 12
+#define I40E_GLQF_SWAP_FLEN0_MASK (0xF << I40E_GLQF_SWAP_FLEN0_SHIFT)
+#define I40E_GLQF_SWAP_OFF1_SRC0_SHIFT 16
+#define I40E_GLQF_SWAP_OFF1_SRC0_MASK (0x3F << I40E_GLQF_SWAP_OFF1_SRC0_SHIFT)
+#define I40E_GLQF_SWAP_OFF1_SRC1_SHIFT 22
+#define I40E_GLQF_SWAP_OFF1_SRC1_MASK (0x3F << I40E_GLQF_SWAP_OFF1_SRC1_SHIFT)
+#define I40E_GLQF_SWAP_FLEN1_SHIFT 28
+#define I40E_GLQF_SWAP_FLEN1_MASK (0xF << I40E_GLQF_SWAP_FLEN1_SHIFT)
+#define I40E_PFQF_CTL_0 0x001C0AC0
+#define I40E_PFQF_CTL_0_PEHSIZE_SHIFT 0
+#define I40E_PFQF_CTL_0_PEHSIZE_MASK (0x1F << I40E_PFQF_CTL_0_PEHSIZE_SHIFT)
+#define I40E_PFQF_CTL_0_PEDSIZE_SHIFT 5
+#define I40E_PFQF_CTL_0_PEDSIZE_MASK (0x1F << I40E_PFQF_CTL_0_PEDSIZE_SHIFT)
+#define I40E_PFQF_CTL_0_PFFCHSIZE_SHIFT 10
+#define I40E_PFQF_CTL_0_PFFCHSIZE_MASK (0xF << I40E_PFQF_CTL_0_PFFCHSIZE_SHIFT)
+#define I40E_PFQF_CTL_0_PFFCDSIZE_SHIFT 14
+#define I40E_PFQF_CTL_0_PFFCDSIZE_MASK (0x3 << I40E_PFQF_CTL_0_PFFCDSIZE_SHIFT)
+#define I40E_PFQF_CTL_0_HASHLUTSIZE_SHIFT 16
+#define I40E_PFQF_CTL_0_HASHLUTSIZE_MASK (0x1 << I40E_PFQF_CTL_0_HASHLUTSIZE_SHIFT)
+#define I40E_PFQF_CTL_0_FD_ENA_SHIFT 17
+#define I40E_PFQF_CTL_0_FD_ENA_MASK (0x1 << I40E_PFQF_CTL_0_FD_ENA_SHIFT)
+#define I40E_PFQF_CTL_0_ETYPE_ENA_SHIFT 18
+#define I40E_PFQF_CTL_0_ETYPE_ENA_MASK (0x1 << I40E_PFQF_CTL_0_ETYPE_ENA_SHIFT)
+#define I40E_PFQF_CTL_0_MACVLAN_ENA_SHIFT 19
+#define I40E_PFQF_CTL_0_MACVLAN_ENA_MASK (0x1 << I40E_PFQF_CTL_0_MACVLAN_ENA_SHIFT)
+#define I40E_PFQF_CTL_0_VFFCHSIZE_SHIFT 20
+#define I40E_PFQF_CTL_0_VFFCHSIZE_MASK (0xF << I40E_PFQF_CTL_0_VFFCHSIZE_SHIFT)
+#define I40E_PFQF_CTL_0_VFFCDSIZE_SHIFT 24
+#define I40E_PFQF_CTL_0_VFFCDSIZE_MASK (0x3 << I40E_PFQF_CTL_0_VFFCDSIZE_SHIFT)
+#define I40E_PFQF_CTL_1 0x00245D80
+#define I40E_PFQF_CTL_1_CLEARFDTABLE_SHIFT 0
+#define I40E_PFQF_CTL_1_CLEARFDTABLE_MASK (0x1 << I40E_PFQF_CTL_1_CLEARFDTABLE_SHIFT)
+#define I40E_PFQF_FDALLOC 0x00246280
+#define I40E_PFQF_FDALLOC_FDALLOC_SHIFT 0
+#define I40E_PFQF_FDALLOC_FDALLOC_MASK (0xFF << I40E_PFQF_FDALLOC_FDALLOC_SHIFT)
+#define I40E_PFQF_FDALLOC_FDBEST_SHIFT 8
+#define I40E_PFQF_FDALLOC_FDBEST_MASK (0xFF << I40E_PFQF_FDALLOC_FDBEST_SHIFT)
+#define I40E_PFQF_FDSTAT 0x00246380
+#define I40E_PFQF_FDSTAT_GUARANT_CNT_SHIFT 0
+#define I40E_PFQF_FDSTAT_GUARANT_CNT_MASK (0x1FFF << I40E_PFQF_FDSTAT_GUARANT_CNT_SHIFT)
+#define I40E_PFQF_FDSTAT_BEST_CNT_SHIFT 16
+#define I40E_PFQF_FDSTAT_BEST_CNT_MASK (0x1FFF << I40E_PFQF_FDSTAT_BEST_CNT_SHIFT)
+#define I40E_PFQF_HENA(_i) (0x00245900 + ((_i) * 128)) /* _i=0...1 */
+#define I40E_PFQF_HENA_MAX_INDEX 1
+#define I40E_PFQF_HENA_PTYPE_ENA_SHIFT 0
+#define I40E_PFQF_HENA_PTYPE_ENA_MASK (0xFFFFFFFF << I40E_PFQF_HENA_PTYPE_ENA_SHIFT)
+#define I40E_PFQF_HKEY(_i) (0x00244800 + ((_i) * 128)) /* _i=0...12 */
+#define I40E_PFQF_HKEY_MAX_INDEX 12
+#define I40E_PFQF_HKEY_KEY_0_SHIFT 0
+#define I40E_PFQF_HKEY_KEY_0_MASK (0xFF << I40E_PFQF_HKEY_KEY_0_SHIFT)
+#define I40E_PFQF_HKEY_KEY_1_SHIFT 8
+#define I40E_PFQF_HKEY_KEY_1_MASK (0xFF << I40E_PFQF_HKEY_KEY_1_SHIFT)
+#define I40E_PFQF_HKEY_KEY_2_SHIFT 16
+#define I40E_PFQF_HKEY_KEY_2_MASK (0xFF << I40E_PFQF_HKEY_KEY_2_SHIFT)
+#define I40E_PFQF_HKEY_KEY_3_SHIFT 24
+#define I40E_PFQF_HKEY_KEY_3_MASK (0xFF << I40E_PFQF_HKEY_KEY_3_SHIFT)
+#define I40E_PFQF_HLUT(_i) (0x00240000 + ((_i) * 128)) /* _i=0...127 */
+#define I40E_PFQF_HLUT_MAX_INDEX 127
+#define I40E_PFQF_HLUT_LUT0_SHIFT 0
+#define I40E_PFQF_HLUT_LUT0_MASK (0x3F << I40E_PFQF_HLUT_LUT0_SHIFT)
+#define I40E_PFQF_HLUT_LUT1_SHIFT 8
+#define I40E_PFQF_HLUT_LUT1_MASK (0x3F << I40E_PFQF_HLUT_LUT1_SHIFT)
+#define I40E_PFQF_HLUT_LUT2_SHIFT 16
+#define I40E_PFQF_HLUT_LUT2_MASK (0x3F << I40E_PFQF_HLUT_LUT2_SHIFT)
+#define I40E_PFQF_HLUT_LUT3_SHIFT 24
+#define I40E_PFQF_HLUT_LUT3_MASK (0x3F << I40E_PFQF_HLUT_LUT3_SHIFT)
+#define I40E_PFQF_HREGION(_i) (0x00245400 + ((_i) * 128)) /* _i=0...7 */
+#define I40E_PFQF_HREGION_MAX_INDEX 7
+#define I40E_PFQF_HREGION_OVERRIDE_ENA_0_SHIFT 0
+#define I40E_PFQF_HREGION_OVERRIDE_ENA_0_MASK (0x1 << I40E_PFQF_HREGION_OVERRIDE_ENA_0_SHIFT)
+#define I40E_PFQF_HREGION_REGION_0_SHIFT 1
+#define I40E_PFQF_HREGION_REGION_0_MASK (0x7 << I40E_PFQF_HREGION_REGION_0_SHIFT)
+#define I40E_PFQF_HREGION_OVERRIDE_ENA_1_SHIFT 4
+#define I40E_PFQF_HREGION_OVERRIDE_ENA_1_MASK (0x1 << I40E_PFQF_HREGION_OVERRIDE_ENA_1_SHIFT)
+#define I40E_PFQF_HREGION_REGION_1_SHIFT 5
+#define I40E_PFQF_HREGION_REGION_1_MASK (0x7 << I40E_PFQF_HREGION_REGION_1_SHIFT)
+#define I40E_PFQF_HREGION_OVERRIDE_ENA_2_SHIFT 8
+#define I40E_PFQF_HREGION_OVERRIDE_ENA_2_MASK (0x1 << I40E_PFQF_HREGION_OVERRIDE_ENA_2_SHIFT)
+#define I40E_PFQF_HREGION_REGION_2_SHIFT 9
+#define I40E_PFQF_HREGION_REGION_2_MASK (0x7 << I40E_PFQF_HREGION_REGION_2_SHIFT)
+#define I40E_PFQF_HREGION_OVERRIDE_ENA_3_SHIFT 12
+#define I40E_PFQF_HREGION_OVERRIDE_ENA_3_MASK (0x1 << I40E_PFQF_HREGION_OVERRIDE_ENA_3_SHIFT)
+#define I40E_PFQF_HREGION_REGION_3_SHIFT 13
+#define I40E_PFQF_HREGION_REGION_3_MASK (0x7 << I40E_PFQF_HREGION_REGION_3_SHIFT)
+#define I40E_PFQF_HREGION_OVERRIDE_ENA_4_SHIFT 16
+#define I40E_PFQF_HREGION_OVERRIDE_ENA_4_MASK (0x1 << I40E_PFQF_HREGION_OVERRIDE_ENA_4_SHIFT)
+#define I40E_PFQF_HREGION_REGION_4_SHIFT 17
+#define I40E_PFQF_HREGION_REGION_4_MASK (0x7 << I40E_PFQF_HREGION_REGION_4_SHIFT)
+#define I40E_PFQF_HREGION_OVERRIDE_ENA_5_SHIFT 20
+#define I40E_PFQF_HREGION_OVERRIDE_ENA_5_MASK (0x1 << I40E_PFQF_HREGION_OVERRIDE_ENA_5_SHIFT)
+#define I40E_PFQF_HREGION_REGION_5_SHIFT 21
+#define I40E_PFQF_HREGION_REGION_5_MASK (0x7 << I40E_PFQF_HREGION_REGION_5_SHIFT)
+#define I40E_PFQF_HREGION_OVERRIDE_ENA_6_SHIFT 24
+#define I40E_PFQF_HREGION_OVERRIDE_ENA_6_MASK (0x1 << I40E_PFQF_HREGION_OVERRIDE_ENA_6_SHIFT)
+#define I40E_PFQF_HREGION_REGION_6_SHIFT 25
+#define I40E_PFQF_HREGION_REGION_6_MASK (0x7 << I40E_PFQF_HREGION_REGION_6_SHIFT)
+#define I40E_PFQF_HREGION_OVERRIDE_ENA_7_SHIFT 28
+#define I40E_PFQF_HREGION_OVERRIDE_ENA_7_MASK (0x1 << I40E_PFQF_HREGION_OVERRIDE_ENA_7_SHIFT)
+#define I40E_PFQF_HREGION_REGION_7_SHIFT 29
+#define I40E_PFQF_HREGION_REGION_7_MASK (0x7 << I40E_PFQF_HREGION_REGION_7_SHIFT)
+#define I40E_PRTQF_CTL_0 0x00256E60
+#define I40E_PRTQF_CTL_0_HSYM_ENA_SHIFT 0
+#define I40E_PRTQF_CTL_0_HSYM_ENA_MASK (0x1 << I40E_PRTQF_CTL_0_HSYM_ENA_SHIFT)
+#define I40E_PRTQF_FD_FLXINSET(_i) (0x00253800 + ((_i) * 32)) /* _i=0...63 */
+#define I40E_PRTQF_FD_FLXINSET_MAX_INDEX 63
+#define I40E_PRTQF_FD_FLXINSET_INSET_SHIFT 0
+#define I40E_PRTQF_FD_FLXINSET_INSET_MASK (0xFF << I40E_PRTQF_FD_FLXINSET_INSET_SHIFT)
+#define I40E_PRTQF_FD_MSK(_i, _j) (0x00252000 + ((_i) * 64 + (_j) * 32)) /* _i=0...63, _j=0...1 */
+#define I40E_PRTQF_FD_MSK_MAX_INDEX 63
+#define I40E_PRTQF_FD_MSK_MASK_SHIFT 0
+#define I40E_PRTQF_FD_MSK_MASK_MASK (0xFFFF << I40E_PRTQF_FD_MSK_MASK_SHIFT)
+#define I40E_PRTQF_FD_MSK_OFFSET_SHIFT 16
+#define I40E_PRTQF_FD_MSK_OFFSET_MASK (0x3F << I40E_PRTQF_FD_MSK_OFFSET_SHIFT)
+#define I40E_PRTQF_FLX_PIT(_i) (0x00255200 + ((_i) * 32)) /* _i=0...8 */
+#define I40E_PRTQF_FLX_PIT_MAX_INDEX 8
+#define I40E_PRTQF_FLX_PIT_SOURCE_OFF_SHIFT 0
+#define I40E_PRTQF_FLX_PIT_SOURCE_OFF_MASK (0x3F << I40E_PRTQF_FLX_PIT_SOURCE_OFF_SHIFT)
+#define I40E_PRTQF_FLX_PIT_FSIZE_SHIFT 6
+#define I40E_PRTQF_FLX_PIT_FSIZE_MASK (0xF << I40E_PRTQF_FLX_PIT_FSIZE_SHIFT)
+#define I40E_PRTQF_FLX_PIT_DEST_OFF_SHIFT 10
+#define I40E_PRTQF_FLX_PIT_DEST_OFF_MASK (0x3F << I40E_PRTQF_FLX_PIT_DEST_OFF_SHIFT)
+#define I40E_VFQF_HENA1(_i, _VF) (0x00230800 + ((_i) * 1024 + (_VF) * 4))
+#define I40E_VFQF_HENA1_MAX_INDEX 1
+#define I40E_VFQF_HENA1_PTYPE_ENA_SHIFT 0
+#define I40E_VFQF_HENA1_PTYPE_ENA_MASK (0xFFFFFFFF << I40E_VFQF_HENA1_PTYPE_ENA_SHIFT)
+#define I40E_VFQF_HKEY1(_i, _VF) (0x00228000 + ((_i) * 1024 + (_VF) * 4)) /* _i=0...12, _VF=0...127 */
+#define I40E_VFQF_HKEY1_MAX_INDEX 12
+#define I40E_VFQF_HKEY1_KEY_0_SHIFT 0
+#define I40E_VFQF_HKEY1_KEY_0_MASK (0xFF << I40E_VFQF_HKEY1_KEY_0_SHIFT)
+#define I40E_VFQF_HKEY1_KEY_1_SHIFT 8
+#define I40E_VFQF_HKEY1_KEY_1_MASK (0xFF << I40E_VFQF_HKEY1_KEY_1_SHIFT)
+#define I40E_VFQF_HKEY1_KEY_2_SHIFT 16
+#define I40E_VFQF_HKEY1_KEY_2_MASK (0xFF << I40E_VFQF_HKEY1_KEY_2_SHIFT)
+#define I40E_VFQF_HKEY1_KEY_3_SHIFT 24
+#define I40E_VFQF_HKEY1_KEY_3_MASK (0xFF << I40E_VFQF_HKEY1_KEY_3_SHIFT)
+#define I40E_VFQF_HLUT1(_i, _VF) (0x00220000 + ((_i) * 1024 + (_VF) * 4)) /* _i=0...15, _VF=0...127 */
+#define I40E_VFQF_HLUT1_MAX_INDEX 15
+#define I40E_VFQF_HLUT1_LUT0_SHIFT 0
+#define I40E_VFQF_HLUT1_LUT0_MASK (0xF << I40E_VFQF_HLUT1_LUT0_SHIFT)
+#define I40E_VFQF_HLUT1_LUT1_SHIFT 8
+#define I40E_VFQF_HLUT1_LUT1_MASK (0xF << I40E_VFQF_HLUT1_LUT1_SHIFT)
+#define I40E_VFQF_HLUT1_LUT2_SHIFT 16
+#define I40E_VFQF_HLUT1_LUT2_MASK (0xF << I40E_VFQF_HLUT1_LUT2_SHIFT)
+#define I40E_VFQF_HLUT1_LUT3_SHIFT 24
+#define I40E_VFQF_HLUT1_LUT3_MASK (0xF << I40E_VFQF_HLUT1_LUT3_SHIFT)
+#define I40E_VFQF_HREGION1(_i, _VF) (0x0022E000 + ((_i) * 1024 + (_VF) * 4))
+#define I40E_VFQF_HREGION1_MAX_INDEX 7
+#define I40E_VFQF_HREGION1_OVERRIDE_ENA_0_SHIFT 0
+#define I40E_VFQF_HREGION1_OVERRIDE_ENA_0_MASK (0x1 << I40E_VFQF_HREGION1_OVERRIDE_ENA_0_SHIFT)
+#define I40E_VFQF_HREGION1_REGION_0_SHIFT 1
+#define I40E_VFQF_HREGION1_REGION_0_MASK (0x7 << I40E_VFQF_HREGION1_REGION_0_SHIFT)
+#define I40E_VFQF_HREGION1_OVERRIDE_ENA_1_SHIFT 4
+#define I40E_VFQF_HREGION1_OVERRIDE_ENA_1_MASK (0x1 << I40E_VFQF_HREGION1_OVERRIDE_ENA_1_SHIFT)
+#define I40E_VFQF_HREGION1_REGION_1_SHIFT 5
+#define I40E_VFQF_HREGION1_REGION_1_MASK (0x7 << I40E_VFQF_HREGION1_REGION_1_SHIFT)
+#define I40E_VFQF_HREGION1_OVERRIDE_ENA_2_SHIFT 8
+#define I40E_VFQF_HREGION1_OVERRIDE_ENA_2_MASK (0x1 << I40E_VFQF_HREGION1_OVERRIDE_ENA_2_SHIFT)
+#define I40E_VFQF_HREGION1_REGION_2_SHIFT 9
+#define I40E_VFQF_HREGION1_REGION_2_MASK (0x7 << I40E_VFQF_HREGION1_REGION_2_SHIFT)
+#define I40E_VFQF_HREGION1_OVERRIDE_ENA_3_SHIFT 12
+#define I40E_VFQF_HREGION1_OVERRIDE_ENA_3_MASK (0x1 << I40E_VFQF_HREGION1_OVERRIDE_ENA_3_SHIFT)
+#define I40E_VFQF_HREGION1_REGION_3_SHIFT 13
+#define I40E_VFQF_HREGION1_REGION_3_MASK (0x7 << I40E_VFQF_HREGION1_REGION_3_SHIFT)
+#define I40E_VFQF_HREGION1_OVERRIDE_ENA_4_SHIFT 16
+#define I40E_VFQF_HREGION1_OVERRIDE_ENA_4_MASK (0x1 << I40E_VFQF_HREGION1_OVERRIDE_ENA_4_SHIFT)
+#define I40E_VFQF_HREGION1_REGION_4_SHIFT 17
+#define I40E_VFQF_HREGION1_REGION_4_MASK (0x7 << I40E_VFQF_HREGION1_REGION_4_SHIFT)
+#define I40E_VFQF_HREGION1_OVERRIDE_ENA_5_SHIFT 20
+#define I40E_VFQF_HREGION1_OVERRIDE_ENA_5_MASK (0x1 << I40E_VFQF_HREGION1_OVERRIDE_ENA_5_SHIFT)
+#define I40E_VFQF_HREGION1_REGION_5_SHIFT 21
+#define I40E_VFQF_HREGION1_REGION_5_MASK (0x7 << I40E_VFQF_HREGION1_REGION_5_SHIFT)
+#define I40E_VFQF_HREGION1_OVERRIDE_ENA_6_SHIFT 24
+#define I40E_VFQF_HREGION1_OVERRIDE_ENA_6_MASK (0x1 << I40E_VFQF_HREGION1_OVERRIDE_ENA_6_SHIFT)
+#define I40E_VFQF_HREGION1_REGION_6_SHIFT 25
+#define I40E_VFQF_HREGION1_REGION_6_MASK (0x7 << I40E_VFQF_HREGION1_REGION_6_SHIFT)
+#define I40E_VFQF_HREGION1_OVERRIDE_ENA_7_SHIFT 28
+#define I40E_VFQF_HREGION1_OVERRIDE_ENA_7_MASK (0x1 << I40E_VFQF_HREGION1_OVERRIDE_ENA_7_SHIFT)
+#define I40E_VFQF_HREGION1_REGION_7_SHIFT 29
+#define I40E_VFQF_HREGION1_REGION_7_MASK (0x7 << I40E_VFQF_HREGION1_REGION_7_SHIFT)
+#define I40E_VPQF_CTL(_VF) (0x001C0000 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VPQF_CTL_MAX_INDEX 127
+#define I40E_VPQF_CTL_PEHSIZE_SHIFT 0
+#define I40E_VPQF_CTL_PEHSIZE_MASK (0x1F << I40E_VPQF_CTL_PEHSIZE_SHIFT)
+#define I40E_VPQF_CTL_PEDSIZE_SHIFT 5
+#define I40E_VPQF_CTL_PEDSIZE_MASK (0x1F << I40E_VPQF_CTL_PEDSIZE_SHIFT)
+#define I40E_VPQF_CTL_FCHSIZE_SHIFT 10
+#define I40E_VPQF_CTL_FCHSIZE_MASK (0xF << I40E_VPQF_CTL_FCHSIZE_SHIFT)
+#define I40E_VPQF_CTL_FCDSIZE_SHIFT 14
+#define I40E_VPQF_CTL_FCDSIZE_MASK (0x3 << I40E_VPQF_CTL_FCDSIZE_SHIFT)
+#define I40E_VSIQF_CTL(_VSI) (0x0020D800 + ((_VSI) * 4)) /* _i=0...383 */
+#define I40E_VSIQF_CTL_MAX_INDEX 383
+#define I40E_VSIQF_CTL_FCOE_ENA_SHIFT 0
+#define I40E_VSIQF_CTL_FCOE_ENA_MASK (0x1 << I40E_VSIQF_CTL_FCOE_ENA_SHIFT)
+#define I40E_VSIQF_CTL_PETCP_ENA_SHIFT 1
+#define I40E_VSIQF_CTL_PETCP_ENA_MASK (0x1 << I40E_VSIQF_CTL_PETCP_ENA_SHIFT)
+#define I40E_VSIQF_CTL_PEUUDP_ENA_SHIFT 2
+#define I40E_VSIQF_CTL_PEUUDP_ENA_MASK (0x1 << I40E_VSIQF_CTL_PEUUDP_ENA_SHIFT)
+#define I40E_VSIQF_CTL_PEMUDP_ENA_SHIFT 3
+#define I40E_VSIQF_CTL_PEMUDP_ENA_MASK (0x1 << I40E_VSIQF_CTL_PEMUDP_ENA_SHIFT)
+#define I40E_VSIQF_CTL_PEUFRAG_ENA_SHIFT 4
+#define I40E_VSIQF_CTL_PEUFRAG_ENA_MASK (0x1 << I40E_VSIQF_CTL_PEUFRAG_ENA_SHIFT)
+#define I40E_VSIQF_CTL_PEMFRAG_ENA_SHIFT 5
+#define I40E_VSIQF_CTL_PEMFRAG_ENA_MASK (0x1 << I40E_VSIQF_CTL_PEMFRAG_ENA_SHIFT)
+#define I40E_VSIQF_TCREGION(_i, _VSI) (0x00206000 + ((_i) * 2048 + (_VSI) * 4))
+#define I40E_VSIQF_TCREGION_MAX_INDEX 7
+#define I40E_VSIQF_TCREGION_TC_OFFSET_SHIFT 0
+#define I40E_VSIQF_TCREGION_TC_OFFSET_MASK (0x1FF << I40E_VSIQF_TCREGION_TC_OFFSET_SHIFT)
+#define I40E_VSIQF_TCREGION_TC_SIZE_SHIFT 9
+#define I40E_VSIQF_TCREGION_TC_SIZE_MASK (0x7 << I40E_VSIQF_TCREGION_TC_SIZE_SHIFT)
+#define I40E_VSIQF_TCREGION_TC_OFFSET2_SHIFT 16
+#define I40E_VSIQF_TCREGION_TC_OFFSET2_MASK (0x1FF << I40E_VSIQF_TCREGION_TC_OFFSET2_SHIFT)
+#define I40E_VSIQF_TCREGION_TC_SIZE2_SHIFT 25
+#define I40E_VSIQF_TCREGION_TC_SIZE2_MASK (0x7 << I40E_VSIQF_TCREGION_TC_SIZE2_SHIFT)
+#define I40E_GL_FCOECRC(_i) (0x00314d80 + ((_i) * 8)) /* _i=0...143 */
+#define I40E_GL_FCOECRC_MAX_INDEX 143
+#define I40E_GL_FCOECRC_FCOECRC_SHIFT 0
+#define I40E_GL_FCOECRC_FCOECRC_MASK (0xFFFFFFFF << I40E_GL_FCOECRC_FCOECRC_SHIFT)
+#define I40E_GL_FCOEDDPC(_i) (0x00314480 + ((_i) * 8)) /* _i=0...143 */
+#define I40E_GL_FCOEDDPC_MAX_INDEX 143
+#define I40E_GL_FCOEDDPC_FCOEDDPC_SHIFT 0
+#define I40E_GL_FCOEDDPC_FCOEDDPC_MASK (0xFFFFFFFF << I40E_GL_FCOEDDPC_FCOEDDPC_SHIFT)
+#define I40E_GL_FCOEDDPEC(_i) (0x00314900 + ((_i) * 8)) /* _i=0...143 */
+#define I40E_GL_FCOEDDPEC_MAX_INDEX 143
+#define I40E_GL_FCOEDDPEC_CFOEDDPEC_SHIFT 0
+#define I40E_GL_FCOEDDPEC_CFOEDDPEC_MASK (0xFFFFFFFF << I40E_GL_FCOEDDPEC_CFOEDDPEC_SHIFT)
+#define I40E_GL_FCOEDIFEC(_i) (0x00318480 + ((_i) * 8)) /* _i=0...143 */
+#define I40E_GL_FCOEDIFEC_MAX_INDEX 143
+#define I40E_GL_FCOEDIFEC_FCOEDIFRC_SHIFT 0
+#define I40E_GL_FCOEDIFEC_FCOEDIFRC_MASK (0xFFFFFFFF << I40E_GL_FCOEDIFEC_FCOEDIFRC_SHIFT)
+#define I40E_GL_FCOEDIFRC(_i) (0x00318000 + ((_i) * 8)) /* _i=0...143 */
+#define I40E_GL_FCOEDIFRC_MAX_INDEX 143
+#define I40E_GL_FCOEDIFRC_FCOEDIFRC_SHIFT 0
+#define I40E_GL_FCOEDIFRC_FCOEDIFRC_MASK (0xFFFFFFFF << I40E_GL_FCOEDIFRC_FCOEDIFRC_SHIFT)
+#define I40E_GL_FCOEDIFTCL(_i) (0x00354000 + ((_i) * 8)) /* _i=0...143 */
+#define I40E_GL_FCOEDIFTCL_MAX_INDEX 143
+#define I40E_GL_FCOEDIFTCL_FCOEDIFTC_SHIFT 0
+#define I40E_GL_FCOEDIFTCL_FCOEDIFTC_MASK (0xFFFFFFFF << I40E_GL_FCOEDIFTCL_FCOEDIFTC_SHIFT)
+#define I40E_GL_FCOEDIXAC(_i) (0x0031c000 + ((_i) * 8)) /* _i=0...143 */
+#define I40E_GL_FCOEDIXAC_MAX_INDEX 143
+#define I40E_GL_FCOEDIXAC_FCOEDIXAC_SHIFT 0
+#define I40E_GL_FCOEDIXAC_FCOEDIXAC_MASK (0xFFFFFFFF << I40E_GL_FCOEDIXAC_FCOEDIXAC_SHIFT)
+#define I40E_GL_FCOEDIXEC(_i) (0x0034c000 + ((_i) * 8)) /* _i=0...143 */
+#define I40E_GL_FCOEDIXEC_MAX_INDEX 143
+#define I40E_GL_FCOEDIXEC_FCOEDIXEC_SHIFT 0
+#define I40E_GL_FCOEDIXEC_FCOEDIXEC_MASK (0xFFFFFFFF << I40E_GL_FCOEDIXEC_FCOEDIXEC_SHIFT)
+#define I40E_GL_FCOEDIXVC(_i) (0x00350000 + ((_i) * 8)) /* _i=0...143 */
+#define I40E_GL_FCOEDIXVC_MAX_INDEX 143
+#define I40E_GL_FCOEDIXVC_FCOEDIXVC_SHIFT 0
+#define I40E_GL_FCOEDIXVC_FCOEDIXVC_MASK (0xFFFFFFFF << I40E_GL_FCOEDIXVC_FCOEDIXVC_SHIFT)
+#define I40E_GL_FCOEDWRCH(_i) (0x00320004 + ((_i) * 8)) /* _i=0...143 */
+#define I40E_GL_FCOEDWRCH_MAX_INDEX 143
+#define I40E_GL_FCOEDWRCH_FCOEDWRCH_SHIFT 0
+#define I40E_GL_FCOEDWRCH_FCOEDWRCH_MASK (0xFFFF << I40E_GL_FCOEDWRCH_FCOEDWRCH_SHIFT)
+#define I40E_GL_FCOEDWRCL(_i) (0x00320000 + ((_i) * 8)) /* _i=0...143 */
+#define I40E_GL_FCOEDWRCL_MAX_INDEX 143
+#define I40E_GL_FCOEDWRCL_FCOEDWRCL_SHIFT 0
+#define I40E_GL_FCOEDWRCL_FCOEDWRCL_MASK (0xFFFFFFFF << I40E_GL_FCOEDWRCL_FCOEDWRCL_SHIFT)
+#define I40E_GL_FCOEDWTCH(_i) (0x00348084 + ((_i) * 8)) /* _i=0...143 */
+#define I40E_GL_FCOEDWTCH_MAX_INDEX 143
+#define I40E_GL_FCOEDWTCH_FCOEDWTCH_SHIFT 0
+#define I40E_GL_FCOEDWTCH_FCOEDWTCH_MASK (0xFFFF << I40E_GL_FCOEDWTCH_FCOEDWTCH_SHIFT)
+#define I40E_GL_FCOEDWTCL(_i) (0x00348080 + ((_i) * 8)) /* _i=0...143 */
+#define I40E_GL_FCOEDWTCL_MAX_INDEX 143
+#define I40E_GL_FCOEDWTCL_FCOEDWTCL_SHIFT 0
+#define I40E_GL_FCOEDWTCL_FCOEDWTCL_MASK (0xFFFFFFFF << I40E_GL_FCOEDWTCL_FCOEDWTCL_SHIFT)
+#define I40E_GL_FCOELAST(_i) (0x00314000 + ((_i) * 8)) /* _i=0...143 */
+#define I40E_GL_FCOELAST_MAX_INDEX 143
+#define I40E_GL_FCOELAST_FCOELAST_SHIFT 0
+#define I40E_GL_FCOELAST_FCOELAST_MASK (0xFFFFFFFF << I40E_GL_FCOELAST_FCOELAST_SHIFT)
+#define I40E_GL_FCOEPRC(_i) (0x00315200 + ((_i) * 8)) /* _i=0...143 */
+#define I40E_GL_FCOEPRC_MAX_INDEX 143
+#define I40E_GL_FCOEPRC_FCOEPRC_SHIFT 0
+#define I40E_GL_FCOEPRC_FCOEPRC_MASK (0xFFFFFFFF << I40E_GL_FCOEPRC_FCOEPRC_SHIFT)
+#define I40E_GL_FCOEPTC(_i) (0x00344C00 + ((_i) * 8)) /* _i=0...143 */
+#define I40E_GL_FCOEPTC_MAX_INDEX 143
+#define I40E_GL_FCOEPTC_FCOEPTC_SHIFT 0
+#define I40E_GL_FCOEPTC_FCOEPTC_MASK (0xFFFFFFFF << I40E_GL_FCOEPTC_FCOEPTC_SHIFT)
+#define I40E_GL_FCOERPDC(_i) (0x00324000 + ((_i) * 8)) /* _i=0...143 */
+#define I40E_GL_FCOERPDC_MAX_INDEX 143
+#define I40E_GL_FCOERPDC_FCOERPDC_SHIFT 0
+#define I40E_GL_FCOERPDC_FCOERPDC_MASK (0xFFFFFFFF << I40E_GL_FCOERPDC_FCOERPDC_SHIFT)
+#define I40E_GLPRT_BPRCH(_i) (0x003005E4 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_BPRCH_MAX_INDEX 3
+#define I40E_GLPRT_BPRCH_UPRCH_SHIFT 0
+#define I40E_GLPRT_BPRCH_UPRCH_MASK (0xFFFF << I40E_GLPRT_BPRCH_UPRCH_SHIFT)
+#define I40E_GLPRT_BPRCL(_i) (0x003005E0 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_BPRCL_MAX_INDEX 3
+#define I40E_GLPRT_BPRCL_UPRCH_SHIFT 0
+#define I40E_GLPRT_BPRCL_UPRCH_MASK (0xFFFFFFFF << I40E_GLPRT_BPRCL_UPRCH_SHIFT)
+#define I40E_GLPRT_BPTCH(_i) (0x00300A04 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_BPTCH_MAX_INDEX 3
+#define I40E_GLPRT_BPTCH_UPRCH_SHIFT 0
+#define I40E_GLPRT_BPTCH_UPRCH_MASK (0xFFFF << I40E_GLPRT_BPTCH_UPRCH_SHIFT)
+#define I40E_GLPRT_BPTCL(_i) (0x00300A00 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_BPTCL_MAX_INDEX 3
+#define I40E_GLPRT_BPTCL_UPRCH_SHIFT 0
+#define I40E_GLPRT_BPTCL_UPRCH_MASK (0xFFFFFFFF << I40E_GLPRT_BPTCL_UPRCH_SHIFT)
+#define I40E_GLPRT_CRCERRS(_i) (0x00300080 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_CRCERRS_MAX_INDEX 3
+#define I40E_GLPRT_CRCERRS_CRCERRS_SHIFT 0
+#define I40E_GLPRT_CRCERRS_CRCERRS_MASK (0xFFFFFFFF << I40E_GLPRT_CRCERRS_CRCERRS_SHIFT)
+#define I40E_GLPRT_GORCH(_i) (0x00300004 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_GORCH_MAX_INDEX 3
+#define I40E_GLPRT_GORCH_GORCH_SHIFT 0
+#define I40E_GLPRT_GORCH_GORCH_MASK (0xFFFF << I40E_GLPRT_GORCH_GORCH_SHIFT)
+#define I40E_GLPRT_GORCL(_i) (0x00300000 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_GORCL_MAX_INDEX 3
+#define I40E_GLPRT_GORCL_GORCL_SHIFT 0
+#define I40E_GLPRT_GORCL_GORCL_MASK (0xFFFFFFFF << I40E_GLPRT_GORCL_GORCL_SHIFT)
+#define I40E_GLPRT_GOTCH(_i) (0x00300684 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_GOTCH_MAX_INDEX 3
+#define I40E_GLPRT_GOTCH_GOTCH_SHIFT 0
+#define I40E_GLPRT_GOTCH_GOTCH_MASK (0xFFFF << I40E_GLPRT_GOTCH_GOTCH_SHIFT)
+#define I40E_GLPRT_GOTCL(_i) (0x00300680 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_GOTCL_MAX_INDEX 3
+#define I40E_GLPRT_GOTCL_GOTCL_SHIFT 0
+#define I40E_GLPRT_GOTCL_GOTCL_MASK (0xFFFFFFFF << I40E_GLPRT_GOTCL_GOTCL_SHIFT)
+#define I40E_GLPRT_ILLERRC(_i) (0x003000E0 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_ILLERRC_MAX_INDEX 3
+#define I40E_GLPRT_ILLERRC_ILLERRC_SHIFT 0
+#define I40E_GLPRT_ILLERRC_ILLERRC_MASK (0xFFFFFFFF << I40E_GLPRT_ILLERRC_ILLERRC_SHIFT)
+#define I40E_GLPRT_LDPC(_i) (0x00300620 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_LDPC_MAX_INDEX 3
+#define I40E_GLPRT_LDPC_LDPC_SHIFT 0
+#define I40E_GLPRT_LDPC_LDPC_MASK (0xFFFFFFFF << I40E_GLPRT_LDPC_LDPC_SHIFT)
+#define I40E_GLPRT_LXOFFRXC(_i) (0x00300160 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_LXOFFRXC_MAX_INDEX 3
+#define I40E_GLPRT_LXOFFRXC_LXOFFRXCNT_SHIFT 0
+#define I40E_GLPRT_LXOFFRXC_LXOFFRXCNT_MASK (0xFFFFFFFF << I40E_GLPRT_LXOFFRXC_LXOFFRXCNT_SHIFT)
+#define I40E_GLPRT_LXOFFTXC(_i) (0x003009A0 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_LXOFFTXC_MAX_INDEX 3
+#define I40E_GLPRT_LXOFFTXC_LXOFFTXC_SHIFT 0
+#define I40E_GLPRT_LXOFFTXC_LXOFFTXC_MASK (0xFFFFFFFF << I40E_GLPRT_LXOFFTXC_LXOFFTXC_SHIFT)
+#define I40E_GLPRT_LXONRXC(_i) (0x00300140 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_LXONRXC_MAX_INDEX 3
+#define I40E_GLPRT_LXONRXC_LXONRXCNT_SHIFT 0
+#define I40E_GLPRT_LXONRXC_LXONRXCNT_MASK (0xFFFFFFFF << I40E_GLPRT_LXONRXC_LXONRXCNT_SHIFT)
+#define I40E_GLPRT_LXONTXC(_i) (0x00300980 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_LXONTXC_MAX_INDEX 3
+#define I40E_GLPRT_LXONTXC_LXONTXC_SHIFT 0
+#define I40E_GLPRT_LXONTXC_LXONTXC_MASK (0xFFFFFFFF << I40E_GLPRT_LXONTXC_LXONTXC_SHIFT)
+#define I40E_GLPRT_MLFC(_i) (0x00300020 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_MLFC_MAX_INDEX 3
+#define I40E_GLPRT_MLFC_MLFC_SHIFT 0
+#define I40E_GLPRT_MLFC_MLFC_MASK (0xFFFFFFFF << I40E_GLPRT_MLFC_MLFC_SHIFT)
+#define I40E_GLPRT_MPRCH(_i) (0x003005C4 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_MPRCH_MAX_INDEX 3
+#define I40E_GLPRT_MPRCH_MPRCH_SHIFT 0
+#define I40E_GLPRT_MPRCH_MPRCH_MASK (0xFFFF << I40E_GLPRT_MPRCH_MPRCH_SHIFT)
+#define I40E_GLPRT_MPRCL(_i) (0x003005C0 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_MPRCL_MAX_INDEX 3
+#define I40E_GLPRT_MPRCL_MPRCL_SHIFT 0
+#define I40E_GLPRT_MPRCL_MPRCL_MASK (0xFFFFFFFF << I40E_GLPRT_MPRCL_MPRCL_SHIFT)
+#define I40E_GLPRT_MPTCH(_i) (0x003009E4 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_MPTCH_MAX_INDEX 3
+#define I40E_GLPRT_MPTCH_MPTCH_SHIFT 0
+#define I40E_GLPRT_MPTCH_MPTCH_MASK (0xFFFF << I40E_GLPRT_MPTCH_MPTCH_SHIFT)
+#define I40E_GLPRT_MPTCL(_i) (0x003009E0 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_MPTCL_MAX_INDEX 3
+#define I40E_GLPRT_MPTCL_MPTCL_SHIFT 0
+#define I40E_GLPRT_MPTCL_MPTCL_MASK (0xFFFFFFFF << I40E_GLPRT_MPTCL_MPTCL_SHIFT)
+#define I40E_GLPRT_MRFC(_i) (0x00300040 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_MRFC_MAX_INDEX 3
+#define I40E_GLPRT_MRFC_MRFC_SHIFT 0
+#define I40E_GLPRT_MRFC_MRFC_MASK (0xFFFFFFFF << I40E_GLPRT_MRFC_MRFC_SHIFT)
+#define I40E_GLPRT_PRC1023H(_i) (0x00300504 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_PRC1023H_MAX_INDEX 3
+#define I40E_GLPRT_PRC1023H_PRC1023H_SHIFT 0
+#define I40E_GLPRT_PRC1023H_PRC1023H_MASK (0xFFFF << I40E_GLPRT_PRC1023H_PRC1023H_SHIFT)
+#define I40E_GLPRT_PRC1023L(_i) (0x00300500 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_PRC1023L_MAX_INDEX 3
+#define I40E_GLPRT_PRC1023L_PRC1023L_SHIFT 0
+#define I40E_GLPRT_PRC1023L_PRC1023L_MASK (0xFFFFFFFF << I40E_GLPRT_PRC1023L_PRC1023L_SHIFT)
+#define I40E_GLPRT_PRC127H(_i) (0x003004A4 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_PRC127H_MAX_INDEX 3
+#define I40E_GLPRT_PRC127H_PRC127H_SHIFT 0
+#define I40E_GLPRT_PRC127H_PRC127H_MASK (0xFFFF << I40E_GLPRT_PRC127H_PRC127H_SHIFT)
+#define I40E_GLPRT_PRC127L(_i) (0x003004A0 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_PRC127L_MAX_INDEX 3
+#define I40E_GLPRT_PRC127L_PRC127L_SHIFT 0
+#define I40E_GLPRT_PRC127L_PRC127L_MASK (0xFFFFFFFF << I40E_GLPRT_PRC127L_PRC127L_SHIFT)
+#define I40E_GLPRT_PRC1522H(_i) (0x00300524 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_PRC1522H_MAX_INDEX 3
+#define I40E_GLPRT_PRC1522H_PRC1522H_SHIFT 0
+#define I40E_GLPRT_PRC1522H_PRC1522H_MASK (0xFFFF << I40E_GLPRT_PRC1522H_PRC1522H_SHIFT)
+#define I40E_GLPRT_PRC1522L(_i) (0x00300520 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_PRC1522L_MAX_INDEX 3
+#define I40E_GLPRT_PRC1522L_PRC1522L_SHIFT 0
+#define I40E_GLPRT_PRC1522L_PRC1522L_MASK (0xFFFFFFFF << I40E_GLPRT_PRC1522L_PRC1522L_SHIFT)
+#define I40E_GLPRT_PRC255H(_i) (0x003004C4 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_PRC255H_MAX_INDEX 3
+#define I40E_GLPRT_PRC255H_PRTPRC255H_SHIFT 0
+#define I40E_GLPRT_PRC255H_PRTPRC255H_MASK (0xFFFF << I40E_GLPRT_PRC255H_PRTPRC255H_SHIFT)
+#define I40E_GLPRT_PRC255L(_i) (0x003004C0 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_PRC255L_MAX_INDEX 3
+#define I40E_GLPRT_PRC255L_PRC255L_SHIFT 0
+#define I40E_GLPRT_PRC255L_PRC255L_MASK (0xFFFFFFFF << I40E_GLPRT_PRC255L_PRC255L_SHIFT)
+#define I40E_GLPRT_PRC511H(_i) (0x003004E4 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_PRC511H_MAX_INDEX 3
+#define I40E_GLPRT_PRC511H_PRC511H_SHIFT 0
+#define I40E_GLPRT_PRC511H_PRC511H_MASK (0xFFFF << I40E_GLPRT_PRC511H_PRC511H_SHIFT)
+#define I40E_GLPRT_PRC511L(_i) (0x003004E0 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_PRC511L_MAX_INDEX 3
+#define I40E_GLPRT_PRC511L_PRC511L_SHIFT 0
+#define I40E_GLPRT_PRC511L_PRC511L_MASK (0xFFFFFFFF << I40E_GLPRT_PRC511L_PRC511L_SHIFT)
+#define I40E_GLPRT_PRC64H(_i) (0x00300484 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_PRC64H_MAX_INDEX 3
+#define I40E_GLPRT_PRC64H_PRC64H_SHIFT 0
+#define I40E_GLPRT_PRC64H_PRC64H_MASK (0xFFFF << I40E_GLPRT_PRC64H_PRC64H_SHIFT)
+#define I40E_GLPRT_PRC64L(_i) (0x00300480 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_PRC64L_MAX_INDEX 3
+#define I40E_GLPRT_PRC64L_PRC64L_SHIFT 0
+#define I40E_GLPRT_PRC64L_PRC64L_MASK (0xFFFFFFFF << I40E_GLPRT_PRC64L_PRC64L_SHIFT)
+#define I40E_GLPRT_PRC9522H(_i) (0x00300544 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_PRC9522H_MAX_INDEX 3
+#define I40E_GLPRT_PRC9522H_PRC1522H_SHIFT 0
+#define I40E_GLPRT_PRC9522H_PRC1522H_MASK (0xFFFF << I40E_GLPRT_PRC9522H_PRC1522H_SHIFT)
+#define I40E_GLPRT_PRC9522L(_i) (0x00300540 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_PRC9522L_MAX_INDEX 3
+#define I40E_GLPRT_PRC9522L_PRC1522L_SHIFT 0
+#define I40E_GLPRT_PRC9522L_PRC1522L_MASK (0xFFFFFFFF << I40E_GLPRT_PRC9522L_PRC1522L_SHIFT)
+#define I40E_GLPRT_PTC1023H(_i) (0x00300724 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_PTC1023H_MAX_INDEX 3
+#define I40E_GLPRT_PTC1023H_PTC1023H_SHIFT 0
+#define I40E_GLPRT_PTC1023H_PTC1023H_MASK (0xFFFF << I40E_GLPRT_PTC1023H_PTC1023H_SHIFT)
+#define I40E_GLPRT_PTC1023L(_i) (0x00300720 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_PTC1023L_MAX_INDEX 3
+#define I40E_GLPRT_PTC1023L_PTC1023L_SHIFT 0
+#define I40E_GLPRT_PTC1023L_PTC1023L_MASK (0xFFFFFFFF << I40E_GLPRT_PTC1023L_PTC1023L_SHIFT)
+#define I40E_GLPRT_PTC127H(_i) (0x003006C4 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_PTC127H_MAX_INDEX 3
+#define I40E_GLPRT_PTC127H_PTC127H_SHIFT 0
+#define I40E_GLPRT_PTC127H_PTC127H_MASK (0xFFFF << I40E_GLPRT_PTC127H_PTC127H_SHIFT)
+#define I40E_GLPRT_PTC127L(_i) (0x003006C0 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_PTC127L_MAX_INDEX 3
+#define I40E_GLPRT_PTC127L_PTC127L_SHIFT 0
+#define I40E_GLPRT_PTC127L_PTC127L_MASK (0xFFFFFFFF << I40E_GLPRT_PTC127L_PTC127L_SHIFT)
+#define I40E_GLPRT_PTC1522H(_i) (0x00300744 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_PTC1522H_MAX_INDEX 3
+#define I40E_GLPRT_PTC1522H_PTC1522H_SHIFT 0
+#define I40E_GLPRT_PTC1522H_PTC1522H_MASK (0xFFFF << I40E_GLPRT_PTC1522H_PTC1522H_SHIFT)
+#define I40E_GLPRT_PTC1522L(_i) (0x00300740 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_PTC1522L_MAX_INDEX 3
+#define I40E_GLPRT_PTC1522L_PTC1522L_SHIFT 0
+#define I40E_GLPRT_PTC1522L_PTC1522L_MASK (0xFFFFFFFF << I40E_GLPRT_PTC1522L_PTC1522L_SHIFT)
+#define I40E_GLPRT_PTC255H(_i) (0x003006E4 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_PTC255H_MAX_INDEX 3
+#define I40E_GLPRT_PTC255H_PTC255H_SHIFT 0
+#define I40E_GLPRT_PTC255H_PTC255H_MASK (0xFFFF << I40E_GLPRT_PTC255H_PTC255H_SHIFT)
+#define I40E_GLPRT_PTC255L(_i) (0x003006E0 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_PTC255L_MAX_INDEX 3
+#define I40E_GLPRT_PTC255L_PTC255L_SHIFT 0
+#define I40E_GLPRT_PTC255L_PTC255L_MASK (0xFFFFFFFF << I40E_GLPRT_PTC255L_PTC255L_SHIFT)
+#define I40E_GLPRT_PTC511H(_i) (0x00300704 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_PTC511H_MAX_INDEX 3
+#define I40E_GLPRT_PTC511H_PTC511H_SHIFT 0
+#define I40E_GLPRT_PTC511H_PTC511H_MASK (0xFFFF << I40E_GLPRT_PTC511H_PTC511H_SHIFT)
+#define I40E_GLPRT_PTC511L(_i) (0x00300700 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_PTC511L_MAX_INDEX 3
+#define I40E_GLPRT_PTC511L_PTC511L_SHIFT 0
+#define I40E_GLPRT_PTC511L_PTC511L_MASK (0xFFFFFFFF << I40E_GLPRT_PTC511L_PTC511L_SHIFT)
+#define I40E_GLPRT_PTC64H(_i) (0x003006A4 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_PTC64H_MAX_INDEX 3
+#define I40E_GLPRT_PTC64H_PTC64H_SHIFT 0
+#define I40E_GLPRT_PTC64H_PTC64H_MASK (0xFFFF << I40E_GLPRT_PTC64H_PTC64H_SHIFT)
+#define I40E_GLPRT_PTC64L(_i) (0x003006A0 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_PTC64L_MAX_INDEX 3
+#define I40E_GLPRT_PTC64L_PTC64L_SHIFT 0
+#define I40E_GLPRT_PTC64L_PTC64L_MASK (0xFFFFFFFF << I40E_GLPRT_PTC64L_PTC64L_SHIFT)
+#define I40E_GLPRT_PTC9522H(_i) (0x00300764 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_PTC9522H_MAX_INDEX 3
+#define I40E_GLPRT_PTC9522H_PTC9522H_SHIFT 0
+#define I40E_GLPRT_PTC9522H_PTC9522H_MASK (0xFFFF << I40E_GLPRT_PTC9522H_PTC9522H_SHIFT)
+#define I40E_GLPRT_PTC9522L(_i) (0x00300760 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_PTC9522L_MAX_INDEX 3
+#define I40E_GLPRT_PTC9522L_PTC9522L_SHIFT 0
+#define I40E_GLPRT_PTC9522L_PTC9522L_MASK (0xFFFFFFFF << I40E_GLPRT_PTC9522L_PTC9522L_SHIFT)
+#define I40E_GLPRT_PXOFFRXC(_i, _j) (0x00300280 + ((_i) * 8 + (_j) * 32))
+#define I40E_GLPRT_PXOFFRXC_MAX_INDEX 3
+#define I40E_GLPRT_PXOFFRXC_PRPXOFFRXCNT_SHIFT 0
+#define I40E_GLPRT_PXOFFRXC_PRPXOFFRXCNT_MASK (0xFFFFFFFF << I40E_GLPRT_PXOFFRXC_PRPXOFFRXCNT_SHIFT)
+#define I40E_GLPRT_PXOFFTXC(_i, _j) (0x00300880 + ((_i) * 8 + (_j) * 32))
+#define I40E_GLPRT_PXOFFTXC_MAX_INDEX 3
+#define I40E_GLPRT_PXOFFTXC_PRPXOFFTXCNT_SHIFT 0
+#define I40E_GLPRT_PXOFFTXC_PRPXOFFTXCNT_MASK (0xFFFFFFFF << I40E_GLPRT_PXOFFTXC_PRPXOFFTXCNT_SHIFT)
+#define I40E_GLPRT_PXONRXC(_i, _j) (0x00300180 + ((_i) * 8 + (_j) * 32))
+#define I40E_GLPRT_PXONRXC_MAX_INDEX 3
+#define I40E_GLPRT_PXONRXC_PRPXONRXCNT_SHIFT 0
+#define I40E_GLPRT_PXONRXC_PRPXONRXCNT_MASK (0xFFFFFFFF << I40E_GLPRT_PXONRXC_PRPXONRXCNT_SHIFT)
+#define I40E_GLPRT_PXONTXC(_i, _j) (0x00300780 + ((_i) * 8 + (_j) * 32))
+#define I40E_GLPRT_PXONTXC_MAX_INDEX 3
+#define I40E_GLPRT_PXONTXC_PRPXONTXC_SHIFT 0
+#define I40E_GLPRT_PXONTXC_PRPXONTXC_MASK (0xFFFFFFFF << I40E_GLPRT_PXONTXC_PRPXONTXC_SHIFT)
+#define I40E_GLPRT_RDPC(_i) (0x00300600 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_RDPC_MAX_INDEX 3
+#define I40E_GLPRT_RDPC_RDPC_SHIFT 0
+#define I40E_GLPRT_RDPC_RDPC_MASK (0xFFFFFFFF << I40E_GLPRT_RDPC_RDPC_SHIFT)
+#define I40E_GLPRT_RFC(_i) (0x00300560 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_RFC_MAX_INDEX 3
+#define I40E_GLPRT_RFC_RFC_SHIFT 0
+#define I40E_GLPRT_RFC_RFC_MASK (0xFFFFFFFF << I40E_GLPRT_RFC_RFC_SHIFT)
+#define I40E_GLPRT_RJC(_i) (0x00300580 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_RJC_MAX_INDEX 3
+#define I40E_GLPRT_RJC_RJC_SHIFT 0
+#define I40E_GLPRT_RJC_RJC_MASK (0xFFFFFFFF << I40E_GLPRT_RJC_RJC_SHIFT)
+#define I40E_GLPRT_RLEC(_i) (0x003000A0 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_RLEC_MAX_INDEX 3
+#define I40E_GLPRT_RLEC_RLEC_SHIFT 0
+#define I40E_GLPRT_RLEC_RLEC_MASK (0xFFFFFFFF << I40E_GLPRT_RLEC_RLEC_SHIFT)
+#define I40E_GLPRT_ROC(_i) (0x00300120 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_ROC_MAX_INDEX 3
+#define I40E_GLPRT_ROC_ROC_SHIFT 0
+#define I40E_GLPRT_ROC_ROC_MASK (0xFFFFFFFF << I40E_GLPRT_ROC_ROC_SHIFT)
+#define I40E_GLPRT_RUC(_i) (0x00300100 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_RUC_MAX_INDEX 3
+#define I40E_GLPRT_RUC_RUC_SHIFT 0
+#define I40E_GLPRT_RUC_RUC_MASK (0xFFFFFFFF << I40E_GLPRT_RUC_RUC_SHIFT)
+#define I40E_GLPRT_RUPP(_i) (0x00300660 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_RUPP_MAX_INDEX 3
+#define I40E_GLPRT_RUPP_RUPP_SHIFT 0
+#define I40E_GLPRT_RUPP_RUPP_MASK (0xFFFFFFFF << I40E_GLPRT_RUPP_RUPP_SHIFT)
+#define I40E_GLPRT_RXON2OFFCNT(_i, _j) (0x00300380 + ((_i) * 8 + (_j) * 32))
+#define I40E_GLPRT_RXON2OFFCNT_MAX_INDEX 3
+#define I40E_GLPRT_RXON2OFFCNT_PRRXON2OFFCNT_SHIFT 0
+#define I40E_GLPRT_RXON2OFFCNT_PRRXON2OFFCNT_MASK (0xFFFFFFFF << I40E_GLPRT_RXON2OFFCNT_PRRXON2OFFCNT_SHIFT)
+#define I40E_GLPRT_STDC(_i) (0x00300640 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_STDC_MAX_INDEX 3
+#define I40E_GLPRT_STDC_STDC_SHIFT 0
+#define I40E_GLPRT_STDC_STDC_MASK (0xFFFFFFFF << I40E_GLPRT_STDC_STDC_SHIFT)
+#define I40E_GLPRT_TDOLD(_i) (0x00300A20 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_TDOLD_MAX_INDEX 3
+#define I40E_GLPRT_TDOLD_GLPRT_TDOLD_SHIFT 0
+#define I40E_GLPRT_TDOLD_GLPRT_TDOLD_MASK (0xFFFFFFFF << I40E_GLPRT_TDOLD_GLPRT_TDOLD_SHIFT)
+#define I40E_GLPRT_TDPC(_i) (0x00375400 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_TDPC_MAX_INDEX 3
+#define I40E_GLPRT_TDPC_TDPC_SHIFT 0
+#define I40E_GLPRT_TDPC_TDPC_MASK (0xFFFFFFFF << I40E_GLPRT_TDPC_TDPC_SHIFT)
+#define I40E_GLPRT_UPRCH(_i) (0x003005A4 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_UPRCH_MAX_INDEX 3
+#define I40E_GLPRT_UPRCH_UPRCH_SHIFT 0
+#define I40E_GLPRT_UPRCH_UPRCH_MASK (0xFFFF << I40E_GLPRT_UPRCH_UPRCH_SHIFT)
+#define I40E_GLPRT_UPRCL(_i) (0x003005A0 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_UPRCL_MAX_INDEX 3
+#define I40E_GLPRT_UPRCL_UPRCL_SHIFT 0
+#define I40E_GLPRT_UPRCL_UPRCL_MASK (0xFFFFFFFF << I40E_GLPRT_UPRCL_UPRCL_SHIFT)
+#define I40E_GLPRT_UPTCH(_i) (0x003009C4 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_UPTCH_MAX_INDEX 3
+#define I40E_GLPRT_UPTCH_UPTCH_SHIFT 0
+#define I40E_GLPRT_UPTCH_UPTCH_MASK (0xFFFF << I40E_GLPRT_UPTCH_UPTCH_SHIFT)
+#define I40E_GLPRT_UPTCL(_i) (0x003009C0 + ((_i) * 8)) /* _i=0...3 */
+#define I40E_GLPRT_UPTCL_MAX_INDEX 3
+#define I40E_GLPRT_UPTCL_VUPTCH_SHIFT 0
+#define I40E_GLPRT_UPTCL_VUPTCH_MASK (0xFFFFFFFF << I40E_GLPRT_UPTCL_VUPTCH_SHIFT)
+#define I40E_GLSW_BPRCH(_i) (0x00370104 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLSW_BPRCH_MAX_INDEX 15
+#define I40E_GLSW_BPRCH_BPRCH_SHIFT 0
+#define I40E_GLSW_BPRCH_BPRCH_MASK (0xFFFF << I40E_GLSW_BPRCH_BPRCH_SHIFT)
+#define I40E_GLSW_BPRCL(_i) (0x00370100 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLSW_BPRCL_MAX_INDEX 15
+#define I40E_GLSW_BPRCL_BPRCL_SHIFT 0
+#define I40E_GLSW_BPRCL_BPRCL_MASK (0xFFFFFFFF << I40E_GLSW_BPRCL_BPRCL_SHIFT)
+#define I40E_GLSW_BPTCH(_i) (0x00340104 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLSW_BPTCH_MAX_INDEX 15
+#define I40E_GLSW_BPTCH_BPTCH_SHIFT 0
+#define I40E_GLSW_BPTCH_BPTCH_MASK (0xFFFF << I40E_GLSW_BPTCH_BPTCH_SHIFT)
+#define I40E_GLSW_BPTCL(_i) (0x00340100 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLSW_BPTCL_MAX_INDEX 15
+#define I40E_GLSW_BPTCL_BPTCL_SHIFT 0
+#define I40E_GLSW_BPTCL_BPTCL_MASK (0xFFFFFFFF << I40E_GLSW_BPTCL_BPTCL_SHIFT)
+#define I40E_GLSW_GORCH(_i) (0x0035C004 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLSW_GORCH_MAX_INDEX 15
+#define I40E_GLSW_GORCH_GORCH_SHIFT 0
+#define I40E_GLSW_GORCH_GORCH_MASK (0xFFFF << I40E_GLSW_GORCH_GORCH_SHIFT)
+#define I40E_GLSW_GORCL(_i) (0x0035c000 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLSW_GORCL_MAX_INDEX 15
+#define I40E_GLSW_GORCL_GORCL_SHIFT 0
+#define I40E_GLSW_GORCL_GORCL_MASK (0xFFFFFFFF << I40E_GLSW_GORCL_GORCL_SHIFT)
+#define I40E_GLSW_GOTCH(_i) (0x0032C004 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLSW_GOTCH_MAX_INDEX 15
+#define I40E_GLSW_GOTCH_GOTCH_SHIFT 0
+#define I40E_GLSW_GOTCH_GOTCH_MASK (0xFFFF << I40E_GLSW_GOTCH_GOTCH_SHIFT)
+#define I40E_GLSW_GOTCL(_i) (0x0032c000 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLSW_GOTCL_MAX_INDEX 15
+#define I40E_GLSW_GOTCL_GOTCL_SHIFT 0
+#define I40E_GLSW_GOTCL_GOTCL_MASK (0xFFFFFFFF << I40E_GLSW_GOTCL_GOTCL_SHIFT)
+#define I40E_GLSW_MPRCH(_i) (0x00370084 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLSW_MPRCH_MAX_INDEX 15
+#define I40E_GLSW_MPRCH_MPRCH_SHIFT 0
+#define I40E_GLSW_MPRCH_MPRCH_MASK (0xFFFF << I40E_GLSW_MPRCH_MPRCH_SHIFT)
+#define I40E_GLSW_MPRCL(_i) (0x00370080 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLSW_MPRCL_MAX_INDEX 15
+#define I40E_GLSW_MPRCL_MPRCL_SHIFT 0
+#define I40E_GLSW_MPRCL_MPRCL_MASK (0xFFFFFFFF << I40E_GLSW_MPRCL_MPRCL_SHIFT)
+#define I40E_GLSW_MPTCH(_i) (0x00340084 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLSW_MPTCH_MAX_INDEX 15
+#define I40E_GLSW_MPTCH_MPTCH_SHIFT 0
+#define I40E_GLSW_MPTCH_MPTCH_MASK (0xFFFF << I40E_GLSW_MPTCH_MPTCH_SHIFT)
+#define I40E_GLSW_MPTCL(_i) (0x00340080 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLSW_MPTCL_MAX_INDEX 15
+#define I40E_GLSW_MPTCL_MPTCL_SHIFT 0
+#define I40E_GLSW_MPTCL_MPTCL_MASK (0xFFFFFFFF << I40E_GLSW_MPTCL_MPTCL_SHIFT)
+#define I40E_GLSW_RUPP(_i) (0x00370180 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLSW_RUPP_MAX_INDEX 15
+#define I40E_GLSW_RUPP_RUPP_SHIFT 0
+#define I40E_GLSW_RUPP_RUPP_MASK (0xFFFFFFFF << I40E_GLSW_RUPP_RUPP_SHIFT)
+#define I40E_GLSW_TDPC(_i) (0x00348000 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLSW_TDPC_MAX_INDEX 15
+#define I40E_GLSW_TDPC_TDPC_SHIFT 0
+#define I40E_GLSW_TDPC_TDPC_MASK (0xFFFFFFFF << I40E_GLSW_TDPC_TDPC_SHIFT)
+#define I40E_GLSW_UPRCH(_i) (0x00370004 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLSW_UPRCH_MAX_INDEX 15
+#define I40E_GLSW_UPRCH_UPRCH_SHIFT 0
+#define I40E_GLSW_UPRCH_UPRCH_MASK (0xFFFF << I40E_GLSW_UPRCH_UPRCH_SHIFT)
+#define I40E_GLSW_UPRCL(_i) (0x00370000 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLSW_UPRCL_MAX_INDEX 15
+#define I40E_GLSW_UPRCL_UPRCL_SHIFT 0
+#define I40E_GLSW_UPRCL_UPRCL_MASK (0xFFFFFFFF << I40E_GLSW_UPRCL_UPRCL_SHIFT)
+#define I40E_GLSW_UPTCH(_i) (0x00340004 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLSW_UPTCH_MAX_INDEX 15
+#define I40E_GLSW_UPTCH_UPTCH_SHIFT 0
+#define I40E_GLSW_UPTCH_UPTCH_MASK (0xFFFF << I40E_GLSW_UPTCH_UPTCH_SHIFT)
+#define I40E_GLSW_UPTCL(_i) (0x00340000 + ((_i) * 8)) /* _i=0...15 */
+#define I40E_GLSW_UPTCL_MAX_INDEX 15
+#define I40E_GLSW_UPTCL_UPTCL_SHIFT 0
+#define I40E_GLSW_UPTCL_UPTCL_MASK (0xFFFFFFFF << I40E_GLSW_UPTCL_UPTCL_SHIFT)
+#define I40E_GLV_BPRCH(_i) (0x0036D804 + ((_i) * 8)) /* _i=0...383 */
+#define I40E_GLV_BPRCH_MAX_INDEX 383
+#define I40E_GLV_BPRCH_BPRCH_SHIFT 0
+#define I40E_GLV_BPRCH_BPRCH_MASK (0xFFFF << I40E_GLV_BPRCH_BPRCH_SHIFT)
+#define I40E_GLV_BPRCL(_i) (0x0036d800 + ((_i) * 8)) /* _i=0...383 */
+#define I40E_GLV_BPRCL_MAX_INDEX 383
+#define I40E_GLV_BPRCL_BPRCL_SHIFT 0
+#define I40E_GLV_BPRCL_BPRCL_MASK (0xFFFFFFFF << I40E_GLV_BPRCL_BPRCL_SHIFT)
+#define I40E_GLV_BPTCH(_i) (0x0033D804 + ((_i) * 8)) /* _i=0...383 */
+#define I40E_GLV_BPTCH_MAX_INDEX 383
+#define I40E_GLV_BPTCH_BPTCH_SHIFT 0
+#define I40E_GLV_BPTCH_BPTCH_MASK (0xFFFF << I40E_GLV_BPTCH_BPTCH_SHIFT)
+#define I40E_GLV_BPTCL(_i) (0x0033d800 + ((_i) * 8)) /* _i=0...383 */
+#define I40E_GLV_BPTCL_MAX_INDEX 383
+#define I40E_GLV_BPTCL_BPTCL_SHIFT 0
+#define I40E_GLV_BPTCL_BPTCL_MASK (0xFFFFFFFF << I40E_GLV_BPTCL_BPTCL_SHIFT)
+#define I40E_GLV_GORCH(_i) (0x00358004 + ((_i) * 8)) /* _i=0...383 */
+#define I40E_GLV_GORCH_MAX_INDEX 383
+#define I40E_GLV_GORCH_GORCH_SHIFT 0
+#define I40E_GLV_GORCH_GORCH_MASK (0xFFFF << I40E_GLV_GORCH_GORCH_SHIFT)
+#define I40E_GLV_GORCL(_i) (0x00358000 + ((_i) * 8)) /* _i=0...383 */
+#define I40E_GLV_GORCL_MAX_INDEX 383
+#define I40E_GLV_GORCL_GORCL_SHIFT 0
+#define I40E_GLV_GORCL_GORCL_MASK (0xFFFFFFFF << I40E_GLV_GORCL_GORCL_SHIFT)
+#define I40E_GLV_GOTCH(_i) (0x00328004 + ((_i) * 8)) /* _i=0...383 */
+#define I40E_GLV_GOTCH_MAX_INDEX 383
+#define I40E_GLV_GOTCH_GOTCH_SHIFT 0
+#define I40E_GLV_GOTCH_GOTCH_MASK (0xFFFF << I40E_GLV_GOTCH_GOTCH_SHIFT)
+#define I40E_GLV_GOTCL(_i) (0x00328000 + ((_i) * 8)) /* _i=0...383 */
+#define I40E_GLV_GOTCL_MAX_INDEX 383
+#define I40E_GLV_GOTCL_GOTCL_SHIFT 0
+#define I40E_GLV_GOTCL_GOTCL_MASK (0xFFFFFFFF << I40E_GLV_GOTCL_GOTCL_SHIFT)
+#define I40E_GLV_MPRCH(_i) (0x0036CC04 + ((_i) * 8)) /* _i=0...383 */
+#define I40E_GLV_MPRCH_MAX_INDEX 383
+#define I40E_GLV_MPRCH_MPRCH_SHIFT 0
+#define I40E_GLV_MPRCH_MPRCH_MASK (0xFFFF << I40E_GLV_MPRCH_MPRCH_SHIFT)
+#define I40E_GLV_MPRCL(_i) (0x0036cc00 + ((_i) * 8)) /* _i=0...383 */
+#define I40E_GLV_MPRCL_MAX_INDEX 383
+#define I40E_GLV_MPRCL_MPRCL_SHIFT 0
+#define I40E_GLV_MPRCL_MPRCL_MASK (0xFFFFFFFF << I40E_GLV_MPRCL_MPRCL_SHIFT)
+#define I40E_GLV_MPTCH(_i) (0x0033CC04 + ((_i) * 8)) /* _i=0...383 */
+#define I40E_GLV_MPTCH_MAX_INDEX 383
+#define I40E_GLV_MPTCH_MPTCH_SHIFT 0
+#define I40E_GLV_MPTCH_MPTCH_MASK (0xFFFF << I40E_GLV_MPTCH_MPTCH_SHIFT)
+#define I40E_GLV_MPTCL(_i) (0x0033cc00 + ((_i) * 8)) /* _i=0...383 */
+#define I40E_GLV_MPTCL_MAX_INDEX 383
+#define I40E_GLV_MPTCL_MPTCL_SHIFT 0
+#define I40E_GLV_MPTCL_MPTCL_MASK (0xFFFFFFFF << I40E_GLV_MPTCL_MPTCL_SHIFT)
+#define I40E_GLV_RDPC(_i) (0x00310000 + ((_i) * 8)) /* _i=0...383 */
+#define I40E_GLV_RDPC_MAX_INDEX 383
+#define I40E_GLV_RDPC_RDPC_SHIFT 0
+#define I40E_GLV_RDPC_RDPC_MASK (0xFFFFFFFF << I40E_GLV_RDPC_RDPC_SHIFT)
+#define I40E_GLV_RUPP(_i) (0x0036E400 + ((_i) * 8)) /* _i=0...383 */
+#define I40E_GLV_RUPP_MAX_INDEX 383
+#define I40E_GLV_RUPP_RUPP_SHIFT 0
+#define I40E_GLV_RUPP_RUPP_MASK (0xFFFFFFFF << I40E_GLV_RUPP_RUPP_SHIFT)
+#define I40E_GLV_TEPC(_VSI) (0x00344000 + ((_VSI) * 8)) /* _i=0...383 */
+#define I40E_GLV_TEPC_MAX_INDEX 383
+#define I40E_GLV_TEPC_TEPC_SHIFT 0
+#define I40E_GLV_TEPC_TEPC_MASK (0xFFFFFFFF << I40E_GLV_TEPC_TEPC_SHIFT)
+#define I40E_GLV_UPRCH(_i) (0x0036C004 + ((_i) * 8)) /* _i=0...383 */
+#define I40E_GLV_UPRCH_MAX_INDEX 383
+#define I40E_GLV_UPRCH_UPRCH_SHIFT 0
+#define I40E_GLV_UPRCH_UPRCH_MASK (0xFFFF << I40E_GLV_UPRCH_UPRCH_SHIFT)
+#define I40E_GLV_UPRCL(_i) (0x0036c000 + ((_i) * 8)) /* _i=0...383 */
+#define I40E_GLV_UPRCL_MAX_INDEX 383
+#define I40E_GLV_UPRCL_UPRCL_SHIFT 0
+#define I40E_GLV_UPRCL_UPRCL_MASK (0xFFFFFFFF << I40E_GLV_UPRCL_UPRCL_SHIFT)
+#define I40E_GLV_UPTCH(_i) (0x0033C004 + ((_i) * 8)) /* _i=0...383 */
+#define I40E_GLV_UPTCH_MAX_INDEX 383
+#define I40E_GLV_UPTCH_GLVUPTCH_SHIFT 0
+#define I40E_GLV_UPTCH_GLVUPTCH_MASK (0xFFFF << I40E_GLV_UPTCH_GLVUPTCH_SHIFT)
+#define I40E_GLV_UPTCL(_i) (0x0033c000 + ((_i) * 8)) /* _i=0...383 */
+#define I40E_GLV_UPTCL_MAX_INDEX 383
+#define I40E_GLV_UPTCL_UPTCL_SHIFT 0
+#define I40E_GLV_UPTCL_UPTCL_MASK (0xFFFFFFFF << I40E_GLV_UPTCL_UPTCL_SHIFT)
+#define I40E_GLVEBTC_RBCH(_i, _j) (0x00364004 + ((_i) * 8 + (_j) * 64)) /* _i=0...7, _j=0...15 */
+#define I40E_GLVEBTC_RBCH_MAX_INDEX 7
+#define I40E_GLVEBTC_RBCH_TCBCH_SHIFT 0
+#define I40E_GLVEBTC_RBCH_TCBCH_MASK (0xFFFF << I40E_GLVEBTC_RBCH_TCBCH_SHIFT)
+#define I40E_GLVEBTC_RBCL(_i, _j) (0x00364000 + ((_i) * 8 + (_j) * 64)) /* _i=0...7, _j=0...15 */
+#define I40E_GLVEBTC_RBCL_MAX_INDEX 7
+#define I40E_GLVEBTC_RBCL_TCBCL_SHIFT 0
+#define I40E_GLVEBTC_RBCL_TCBCL_MASK (0xFFFFFFFF << I40E_GLVEBTC_RBCL_TCBCL_SHIFT)
+#define I40E_GLVEBTC_RPCH(_i, _j) (0x00368004 + ((_i) * 8 + (_j) * 64)) /* _i=0...7, _j=0...15 */
+#define I40E_GLVEBTC_RPCH_MAX_INDEX 7
+#define I40E_GLVEBTC_RPCH_TCPCH_SHIFT 0
+#define I40E_GLVEBTC_RPCH_TCPCH_MASK (0xFFFF << I40E_GLVEBTC_RPCH_TCPCH_SHIFT)
+#define I40E_GLVEBTC_RPCL(_i, _j) (0x00368000 + ((_i) * 8 + (_j) * 64)) /* _i=0...7, _j=0...15 */
+#define I40E_GLVEBTC_RPCL_MAX_INDEX 7
+#define I40E_GLVEBTC_RPCL_TCPCL_SHIFT 0
+#define I40E_GLVEBTC_RPCL_TCPCL_MASK (0xFFFFFFFF << I40E_GLVEBTC_RPCL_TCPCL_SHIFT)
+#define I40E_GLVEBTC_TBCH(_i, _j) (0x00334004 + ((_i) * 8 + (_j) * 64)) /* _i=0...7, _j=0...15 */
+#define I40E_GLVEBTC_TBCH_MAX_INDEX 7
+#define I40E_GLVEBTC_TBCH_TCBCH_SHIFT 0
+#define I40E_GLVEBTC_TBCH_TCBCH_MASK (0xFFFF << I40E_GLVEBTC_TBCH_TCBCH_SHIFT)
+#define I40E_GLVEBTC_TBCL(_i, _j) (0x00334000 + ((_i) * 8 + (_j) * 64)) /* _i=0...7, _j=0...15 */
+#define I40E_GLVEBTC_TBCL_MAX_INDEX 7
+#define I40E_GLVEBTC_TBCL_TCBCL_SHIFT 0
+#define I40E_GLVEBTC_TBCL_TCBCL_MASK (0xFFFFFFFF << I40E_GLVEBTC_TBCL_TCBCL_SHIFT)
+#define I40E_GLVEBTC_TPCH(_i, _j) (0x00338004 + ((_i) * 8 + (_j) * 64)) /* _i=0...7, _j=0...15 */
+#define I40E_GLVEBTC_TPCH_MAX_INDEX 7
+#define I40E_GLVEBTC_TPCH_TCPCH_SHIFT 0
+#define I40E_GLVEBTC_TPCH_TCPCH_MASK (0xFFFF << I40E_GLVEBTC_TPCH_TCPCH_SHIFT)
+#define I40E_GLVEBTC_TPCL(_i, _j) (0x00338000 + ((_i) * 8 + (_j) * 64)) /* _i=0...7, _j=0...15 */
+#define I40E_GLVEBTC_TPCL_MAX_INDEX 7
+#define I40E_GLVEBTC_TPCL_TCPCL_SHIFT 0
+#define I40E_GLVEBTC_TPCL_TCPCL_MASK (0xFFFFFFFF << I40E_GLVEBTC_TPCL_TCPCL_SHIFT)
+#define I40E_GLVEBVL_BPCH(_i) (0x00374804 + ((_i) * 8)) /* _i=0...127 */
+#define I40E_GLVEBVL_BPCH_MAX_INDEX 127
+#define I40E_GLVEBVL_BPCH_VLBPCH_SHIFT 0
+#define I40E_GLVEBVL_BPCH_VLBPCH_MASK (0xFFFF << I40E_GLVEBVL_BPCH_VLBPCH_SHIFT)
+#define I40E_GLVEBVL_BPCL(_i) (0x00374800 + ((_i) * 8)) /* _i=0...127 */
+#define I40E_GLVEBVL_BPCL_MAX_INDEX 127
+#define I40E_GLVEBVL_BPCL_VLBPCL_SHIFT 0
+#define I40E_GLVEBVL_BPCL_VLBPCL_MASK (0xFFFFFFFF << I40E_GLVEBVL_BPCL_VLBPCL_SHIFT)
+#define I40E_GLVEBVL_GORCH(_i) (0x00360004 + ((_i) * 8)) /* _i=0...127 */
+#define I40E_GLVEBVL_GORCH_MAX_INDEX 127
+#define I40E_GLVEBVL_GORCH_VLBCH_SHIFT 0
+#define I40E_GLVEBVL_GORCH_VLBCH_MASK (0xFFFF << I40E_GLVEBVL_GORCH_VLBCH_SHIFT)
+#define I40E_GLVEBVL_GORCL(_i) (0x00360000 + ((_i) * 8)) /* _i=0...127 */
+#define I40E_GLVEBVL_GORCL_MAX_INDEX 127
+#define I40E_GLVEBVL_GORCL_VLBCL_SHIFT 0
+#define I40E_GLVEBVL_GORCL_VLBCL_MASK (0xFFFFFFFF << I40E_GLVEBVL_GORCL_VLBCL_SHIFT)
+#define I40E_GLVEBVL_GOTCH(_i) (0x00330004 + ((_i) * 8)) /* _i=0...127 */
+#define I40E_GLVEBVL_GOTCH_MAX_INDEX 127
+#define I40E_GLVEBVL_GOTCH_VLBCH_SHIFT 0
+#define I40E_GLVEBVL_GOTCH_VLBCH_MASK (0xFFFF << I40E_GLVEBVL_GOTCH_VLBCH_SHIFT)
+#define I40E_GLVEBVL_GOTCL(_i) (0x00330000 + ((_i) * 8)) /* _i=0...127 */
+#define I40E_GLVEBVL_GOTCL_MAX_INDEX 127
+#define I40E_GLVEBVL_GOTCL_VLBCL_SHIFT 0
+#define I40E_GLVEBVL_GOTCL_VLBCL_MASK (0xFFFFFFFF << I40E_GLVEBVL_GOTCL_VLBCL_SHIFT)
+#define I40E_GLVEBVL_MPCH(_i) (0x00374404 + ((_i) * 8)) /* _i=0...127 */
+#define I40E_GLVEBVL_MPCH_MAX_INDEX 127
+#define I40E_GLVEBVL_MPCH_VLMPCH_SHIFT 0
+#define I40E_GLVEBVL_MPCH_VLMPCH_MASK (0xFFFF << I40E_GLVEBVL_MPCH_VLMPCH_SHIFT)
+#define I40E_GLVEBVL_MPCL(_i) (0x00374400 + ((_i) * 8)) /* _i=0...127 */
+#define I40E_GLVEBVL_MPCL_MAX_INDEX 127
+#define I40E_GLVEBVL_MPCL_VLMPCL_SHIFT 0
+#define I40E_GLVEBVL_MPCL_VLMPCL_MASK (0xFFFFFFFF << I40E_GLVEBVL_MPCL_VLMPCL_SHIFT)
+#define I40E_GLVEBVL_UPCH(_i) (0x00374004 + ((_i) * 8)) /* _i=0...127 */
+#define I40E_GLVEBVL_UPCH_MAX_INDEX 127
+#define I40E_GLVEBVL_UPCH_VLUPCH_SHIFT 0
+#define I40E_GLVEBVL_UPCH_VLUPCH_MASK (0xFFFF << I40E_GLVEBVL_UPCH_VLUPCH_SHIFT)
+#define I40E_GLVEBVL_UPCL(_i) (0x00374000 + ((_i) * 8)) /* _i=0...127 */
+#define I40E_GLVEBVL_UPCL_MAX_INDEX 127
+#define I40E_GLVEBVL_UPCL_VLUPCL_SHIFT 0
+#define I40E_GLVEBVL_UPCL_VLUPCL_MASK (0xFFFFFFFF << I40E_GLVEBVL_UPCL_VLUPCL_SHIFT)
+#define I40E_GL_MTG_FLU_MSK_H 0x00269F4C
+#define I40E_GL_MTG_FLU_MSK_H_MASK_HIGH_SHIFT 0
+#define I40E_GL_MTG_FLU_MSK_H_MASK_HIGH_MASK (0xFFFF << I40E_GL_MTG_FLU_MSK_H_MASK_HIGH_SHIFT)
+#define I40E_GL_MTG_FLU_MSK_L 0x00269F44
+#define I40E_GL_MTG_FLU_MSK_L_MASK_LOW_SHIFT 0
+#define I40E_GL_MTG_FLU_MSK_L_MASK_LOW_MASK (0xFFFFFFFF << I40E_GL_MTG_FLU_MSK_L_MASK_LOW_SHIFT)
+#define I40E_GL_SWR_DEF_ACT(_i) (0x0026CF00 + ((_i) * 4)) /* _i=0...25 */
+#define I40E_GL_SWR_DEF_ACT_MAX_INDEX 25
+#define I40E_GL_SWR_DEF_ACT_DEF_ACTION_SHIFT 0
+#define I40E_GL_SWR_DEF_ACT_DEF_ACTION_MASK (0xFFFFFFFF << I40E_GL_SWR_DEF_ACT_DEF_ACTION_SHIFT)
+#define I40E_GL_SWR_DEF_ACT_EN 0x0026CF84
+#define I40E_GL_SWR_DEF_ACT_EN_DEF_ACT_EN_BITMAP_SHIFT 0
+#define I40E_GL_SWR_DEF_ACT_EN_DEF_ACT_EN_BITMAP_MASK (0xFFFFFFFF << I40E_GL_SWR_DEF_ACT_EN_DEF_ACT_EN_BITMAP_SHIFT)
+#define I40E_PRT_MSCCNT 0x00256BA0
+#define I40E_PRT_MSCCNT_CCOUNT_SHIFT 0
+#define I40E_PRT_MSCCNT_CCOUNT_MASK (0x1FFFFFF << I40E_PRT_MSCCNT_CCOUNT_SHIFT)
+#define I40E_PRT_SCSTS 0x00256C20
+#define I40E_PRT_SCSTS_BSCA_SHIFT 0
+#define I40E_PRT_SCSTS_BSCA_MASK (0x1 << I40E_PRT_SCSTS_BSCA_SHIFT)
+#define I40E_PRT_SCSTS_BSCAP_SHIFT 1
+#define I40E_PRT_SCSTS_BSCAP_MASK (0x1 << I40E_PRT_SCSTS_BSCAP_SHIFT)
+#define I40E_PRT_SCSTS_MSCA_SHIFT 2
+#define I40E_PRT_SCSTS_MSCA_MASK (0x1 << I40E_PRT_SCSTS_MSCA_SHIFT)
+#define I40E_PRT_SCSTS_MSCAP_SHIFT 3
+#define I40E_PRT_SCSTS_MSCAP_MASK (0x1 << I40E_PRT_SCSTS_MSCAP_SHIFT)
+#define I40E_PRT_SWT_BSCCNT 0x00256C60
+#define I40E_PRT_SWT_BSCCNT_CCOUNT_SHIFT 0
+#define I40E_PRT_SWT_BSCCNT_CCOUNT_MASK (0x1FFFFFF << I40E_PRT_SWT_BSCCNT_CCOUNT_SHIFT)
+#define I40E_PRTTSYN_ADJ 0x001E4280
+#define I40E_PRTTSYN_ADJ_TSYNADJ_SHIFT 0
+#define I40E_PRTTSYN_ADJ_TSYNADJ_MASK (0x7FFFFFFF << I40E_PRTTSYN_ADJ_TSYNADJ_SHIFT)
+#define I40E_PRTTSYN_ADJ_SIGN_SHIFT 31
+#define I40E_PRTTSYN_ADJ_SIGN_MASK (0x1 << I40E_PRTTSYN_ADJ_SIGN_SHIFT)
+#define I40E_PRTTSYN_AUX_0(_i) (0x001E42A0 + ((_i) * 32)) /* _i=0...1 */
+#define I40E_PRTTSYN_AUX_0_MAX_INDEX 1
+#define I40E_PRTTSYN_AUX_0_OUT_ENA_SHIFT 0
+#define I40E_PRTTSYN_AUX_0_OUT_ENA_MASK (0x1 << I40E_PRTTSYN_AUX_0_OUT_ENA_SHIFT)
+#define I40E_PRTTSYN_AUX_0_OUTMOD_SHIFT 1
+#define I40E_PRTTSYN_AUX_0_OUTMOD_MASK (0x3 << I40E_PRTTSYN_AUX_0_OUTMOD_SHIFT)
+#define I40E_PRTTSYN_AUX_0_OUTLVL_SHIFT 3
+#define I40E_PRTTSYN_AUX_0_OUTLVL_MASK (0x1 << I40E_PRTTSYN_AUX_0_OUTLVL_SHIFT)
+#define I40E_PRTTSYN_AUX_0_PULSEW_SHIFT 8
+#define I40E_PRTTSYN_AUX_0_PULSEW_MASK (0xF << I40E_PRTTSYN_AUX_0_PULSEW_SHIFT)
+#define I40E_PRTTSYN_AUX_0_EVNTLVL_SHIFT 16
+#define I40E_PRTTSYN_AUX_0_EVNTLVL_MASK (0x3 << I40E_PRTTSYN_AUX_0_EVNTLVL_SHIFT)
+#define I40E_PRTTSYN_AUX_1(_i) (0x001E42E0 + ((_i) * 32)) /* _i=0...1 */
+#define I40E_PRTTSYN_AUX_1_MAX_INDEX 1
+#define I40E_PRTTSYN_AUX_1_INSTNT_SHIFT 0
+#define I40E_PRTTSYN_AUX_1_INSTNT_MASK (0x1 << I40E_PRTTSYN_AUX_1_INSTNT_SHIFT)
+#define I40E_PRTTSYN_AUX_1_SAMPLE_TIME_SHIFT 1
+#define I40E_PRTTSYN_AUX_1_SAMPLE_TIME_MASK (0x1 << I40E_PRTTSYN_AUX_1_SAMPLE_TIME_SHIFT)
+#define I40E_PRTTSYN_CLKO(_i) (0x001E4240 + ((_i) * 32)) /* _i=0...1 */
+#define I40E_PRTTSYN_CLKO_MAX_INDEX 1
+#define I40E_PRTTSYN_CLKO_TSYNCLKO_SHIFT 0
+#define I40E_PRTTSYN_CLKO_TSYNCLKO_MASK (0xFFFFFFFF << I40E_PRTTSYN_CLKO_TSYNCLKO_SHIFT)
+#define I40E_PRTTSYN_CTL0 0x001E4200
+#define I40E_PRTTSYN_CTL0_CLEAR_TSYNTIMER_SHIFT 0
+#define I40E_PRTTSYN_CTL0_CLEAR_TSYNTIMER_MASK (0x1 << I40E_PRTTSYN_CTL0_CLEAR_TSYNTIMER_SHIFT)
+#define I40E_PRTTSYN_CTL0_TXTIME_INT_ENA_SHIFT 1
+#define I40E_PRTTSYN_CTL0_TXTIME_INT_ENA_MASK (0x1 << I40E_PRTTSYN_CTL0_TXTIME_INT_ENA_SHIFT)
+#define I40E_PRTTSYN_CTL0_EVENT_INT_ENA_SHIFT 2
+#define I40E_PRTTSYN_CTL0_EVENT_INT_ENA_MASK (0x1 << I40E_PRTTSYN_CTL0_EVENT_INT_ENA_SHIFT)
+#define I40E_PRTTSYN_CTL0_TGT_INT_ENA_SHIFT 3
+#define I40E_PRTTSYN_CTL0_TGT_INT_ENA_MASK (0x1 << I40E_PRTTSYN_CTL0_TGT_INT_ENA_SHIFT)
+#define I40E_PRTTSYN_CTL0_PF_ID_SHIFT 8
+#define I40E_PRTTSYN_CTL0_PF_ID_MASK (0xF << I40E_PRTTSYN_CTL0_PF_ID_SHIFT)
+#define I40E_PRTTSYN_CTL0_TSYNACT_SHIFT 12
+#define I40E_PRTTSYN_CTL0_TSYNACT_MASK (0x3 << I40E_PRTTSYN_CTL0_TSYNACT_SHIFT)
+#define I40E_PRTTSYN_CTL0_TSYNENA_SHIFT 31
+#define I40E_PRTTSYN_CTL0_TSYNENA_MASK (0x1 << I40E_PRTTSYN_CTL0_TSYNENA_SHIFT)
+#define I40E_PRTTSYN_CTL1 0x00085020
+#define I40E_PRTTSYN_CTL1_V1MESSTYPE0_SHIFT 0
+#define I40E_PRTTSYN_CTL1_V1MESSTYPE0_MASK (0xFF << I40E_PRTTSYN_CTL1_V1MESSTYPE0_SHIFT)
+#define I40E_PRTTSYN_CTL1_V1MESSTYPE1_SHIFT 8
+#define I40E_PRTTSYN_CTL1_V1MESSTYPE1_MASK (0xFF << I40E_PRTTSYN_CTL1_V1MESSTYPE1_SHIFT)
+#define I40E_PRTTSYN_CTL1_V2MESSTYPE0_SHIFT 16
+#define I40E_PRTTSYN_CTL1_V2MESSTYPE0_MASK (0xF << I40E_PRTTSYN_CTL1_V2MESSTYPE0_SHIFT)
+#define I40E_PRTTSYN_CTL1_V2MESSTYPE1_SHIFT 20
+#define I40E_PRTTSYN_CTL1_V2MESSTYPE1_MASK (0xF << I40E_PRTTSYN_CTL1_V2MESSTYPE1_SHIFT)
+#define I40E_PRTTSYN_CTL1_TSYNTYPE_SHIFT 24
+#define I40E_PRTTSYN_CTL1_TSYNTYPE_MASK (0x3 << I40E_PRTTSYN_CTL1_TSYNTYPE_SHIFT)
+#define I40E_PRTTSYN_CTL1_UDP_ENA_SHIFT 26
+#define I40E_PRTTSYN_CTL1_UDP_ENA_MASK (0x3 << I40E_PRTTSYN_CTL1_UDP_ENA_SHIFT)
+#define I40E_PRTTSYN_CTL1_TSYNENA_SHIFT 31
+#define I40E_PRTTSYN_CTL1_TSYNENA_MASK (0x1 << I40E_PRTTSYN_CTL1_TSYNENA_SHIFT)
+#define I40E_PRTTSYN_EVNT_H(_i) (0x001E40C0 + ((_i) * 32)) /* _i=0...1 */
+#define I40E_PRTTSYN_EVNT_H_MAX_INDEX 1
+#define I40E_PRTTSYN_EVNT_H_TSYNEVNT_H_SHIFT 0
+#define I40E_PRTTSYN_EVNT_H_TSYNEVNT_H_MASK (0xFFFFFFFF << I40E_PRTTSYN_EVNT_H_TSYNEVNT_H_SHIFT)
+#define I40E_PRTTSYN_EVNT_L(_i) (0x001E4080 + ((_i) * 32)) /* _i=0...1 */
+#define I40E_PRTTSYN_EVNT_L_MAX_INDEX 1
+#define I40E_PRTTSYN_EVNT_L_TSYNEVNT_L_SHIFT 0
+#define I40E_PRTTSYN_EVNT_L_TSYNEVNT_L_MASK (0xFFFFFFFF << I40E_PRTTSYN_EVNT_L_TSYNEVNT_L_SHIFT)
+#define I40E_PRTTSYN_INC_H 0x001E4060
+#define I40E_PRTTSYN_INC_H_TSYNINC_H_SHIFT 0
+#define I40E_PRTTSYN_INC_H_TSYNINC_H_MASK (0x3F << I40E_PRTTSYN_INC_H_TSYNINC_H_SHIFT)
+#define I40E_PRTTSYN_INC_L 0x001E4040
+#define I40E_PRTTSYN_INC_L_TSYNINC_L_SHIFT 0
+#define I40E_PRTTSYN_INC_L_TSYNINC_L_MASK (0xFFFFFFFF << I40E_PRTTSYN_INC_L_TSYNINC_L_SHIFT)
+#define I40E_PRTTSYN_RXTIME_H(_i) (0x00085040 + ((_i) * 32)) /* _i=0...3 */
+#define I40E_PRTTSYN_RXTIME_H_MAX_INDEX 3
+#define I40E_PRTTSYN_RXTIME_H_RXTIEM_H_SHIFT 0
+#define I40E_PRTTSYN_RXTIME_H_RXTIEM_H_MASK (0xFFFFFFFF << I40E_PRTTSYN_RXTIME_H_RXTIEM_H_SHIFT)
+#define I40E_PRTTSYN_RXTIME_L(_i) (0x000850C0 + ((_i) * 32)) /* _i=0...3 */
+#define I40E_PRTTSYN_RXTIME_L_MAX_INDEX 3
+#define I40E_PRTTSYN_RXTIME_L_RXTIEM_L_SHIFT 0
+#define I40E_PRTTSYN_RXTIME_L_RXTIEM_L_MASK (0xFFFFFFFF << I40E_PRTTSYN_RXTIME_L_RXTIEM_L_SHIFT)
+#define I40E_PRTTSYN_STAT_0 0x001E4220
+#define I40E_PRTTSYN_STAT_0_EVENT0_SHIFT 0
+#define I40E_PRTTSYN_STAT_0_EVENT0_MASK (0x1 << I40E_PRTTSYN_STAT_0_EVENT0_SHIFT)
+#define I40E_PRTTSYN_STAT_0_EVENT1_SHIFT 1
+#define I40E_PRTTSYN_STAT_0_EVENT1_MASK (0x1 << I40E_PRTTSYN_STAT_0_EVENT1_SHIFT)
+#define I40E_PRTTSYN_STAT_0_TGT0_SHIFT 2
+#define I40E_PRTTSYN_STAT_0_TGT0_MASK (0x1 << I40E_PRTTSYN_STAT_0_TGT0_SHIFT)
+#define I40E_PRTTSYN_STAT_0_TGT1_SHIFT 3
+#define I40E_PRTTSYN_STAT_0_TGT1_MASK (0x1 << I40E_PRTTSYN_STAT_0_TGT1_SHIFT)
+#define I40E_PRTTSYN_STAT_0_TXTIME_SHIFT 4
+#define I40E_PRTTSYN_STAT_0_TXTIME_MASK (0x1 << I40E_PRTTSYN_STAT_0_TXTIME_SHIFT)
+#define I40E_PRTTSYN_STAT_1 0x00085140
+#define I40E_PRTTSYN_STAT_1_RXT0_SHIFT 0
+#define I40E_PRTTSYN_STAT_1_RXT0_MASK (0x1 << I40E_PRTTSYN_STAT_1_RXT0_SHIFT)
+#define I40E_PRTTSYN_STAT_1_RXT1_SHIFT 1
+#define I40E_PRTTSYN_STAT_1_RXT1_MASK (0x1 << I40E_PRTTSYN_STAT_1_RXT1_SHIFT)
+#define I40E_PRTTSYN_STAT_1_RXT2_SHIFT 2
+#define I40E_PRTTSYN_STAT_1_RXT2_MASK (0x1 << I40E_PRTTSYN_STAT_1_RXT2_SHIFT)
+#define I40E_PRTTSYN_STAT_1_RXT3_SHIFT 3
+#define I40E_PRTTSYN_STAT_1_RXT3_MASK (0x1 << I40E_PRTTSYN_STAT_1_RXT3_SHIFT)
+#define I40E_PRTTSYN_TGT_H(_i) (0x001E4180 + ((_i) * 32)) /* _i=0...1 */
+#define I40E_PRTTSYN_TGT_H_MAX_INDEX 1
+#define I40E_PRTTSYN_TGT_H_TSYNTGTT_H_SHIFT 0
+#define I40E_PRTTSYN_TGT_H_TSYNTGTT_H_MASK (0xFFFFFFFF << I40E_PRTTSYN_TGT_H_TSYNTGTT_H_SHIFT)
+#define I40E_PRTTSYN_TGT_L(_i) (0x001E4140 + ((_i) * 32)) /* _i=0...1 */
+#define I40E_PRTTSYN_TGT_L_MAX_INDEX 1
+#define I40E_PRTTSYN_TGT_L_TSYNTGTT_L_SHIFT 0
+#define I40E_PRTTSYN_TGT_L_TSYNTGTT_L_MASK (0xFFFFFFFF << I40E_PRTTSYN_TGT_L_TSYNTGTT_L_SHIFT)
+#define I40E_PRTTSYN_TIME_H 0x001E4120
+#define I40E_PRTTSYN_TIME_H_TSYNTIME_H_SHIFT 0
+#define I40E_PRTTSYN_TIME_H_TSYNTIME_H_MASK (0xFFFFFFFF << I40E_PRTTSYN_TIME_H_TSYNTIME_H_SHIFT)
+#define I40E_PRTTSYN_TIME_L 0x001E4100
+#define I40E_PRTTSYN_TIME_L_TSYNTIME_L_SHIFT 0
+#define I40E_PRTTSYN_TIME_L_TSYNTIME_L_MASK (0xFFFFFFFF << I40E_PRTTSYN_TIME_L_TSYNTIME_L_SHIFT)
+#define I40E_PRTTSYN_TXTIME_H 0x001E41E0
+#define I40E_PRTTSYN_TXTIME_H_TXTIEM_H_SHIFT 0
+#define I40E_PRTTSYN_TXTIME_H_TXTIEM_H_MASK (0xFFFFFFFF << I40E_PRTTSYN_TXTIME_H_TXTIEM_H_SHIFT)
+#define I40E_PRTTSYN_TXTIME_L 0x001E41C0
+#define I40E_PRTTSYN_TXTIME_L_TXTIEM_L_SHIFT 0
+#define I40E_PRTTSYN_TXTIME_L_TXTIEM_L_MASK (0xFFFFFFFF << I40E_PRTTSYN_TXTIME_L_TXTIEM_L_SHIFT)
+#define I40E_GLSCD_QUANTA 0x000B2080
+#define I40E_GLSCD_QUANTA_TSCDQUANTA_SHIFT 0
+#define I40E_GLSCD_QUANTA_TSCDQUANTA_MASK (0x7 << I40E_GLSCD_QUANTA_TSCDQUANTA_SHIFT)
+#define I40E_GL_MDET_RX 0x0012A510
+#define I40E_GL_MDET_RX_FUNCTION_SHIFT 0
+#define I40E_GL_MDET_RX_FUNCTION_MASK (0xFF << I40E_GL_MDET_RX_FUNCTION_SHIFT)
+#define I40E_GL_MDET_RX_EVENT_SHIFT 8
+#define I40E_GL_MDET_RX_EVENT_MASK (0x1FF << I40E_GL_MDET_RX_EVENT_SHIFT)
+#define I40E_GL_MDET_RX_QUEUE_SHIFT 17
+#define I40E_GL_MDET_RX_QUEUE_MASK (0x3FFF << I40E_GL_MDET_RX_QUEUE_SHIFT)
+#define I40E_GL_MDET_RX_VALID_SHIFT 31
+#define I40E_GL_MDET_RX_VALID_MASK (0x1 << I40E_GL_MDET_RX_VALID_SHIFT)
+#define I40E_GL_MDET_TX 0x000E6480
+#define I40E_GL_MDET_TX_FUNCTION_SHIFT 0
+#define I40E_GL_MDET_TX_FUNCTION_MASK (0xFF << I40E_GL_MDET_TX_FUNCTION_SHIFT)
+#define I40E_GL_MDET_TX_EVENT_SHIFT 8
+#define I40E_GL_MDET_TX_EVENT_MASK (0x1FF << I40E_GL_MDET_TX_EVENT_SHIFT)
+#define I40E_GL_MDET_TX_QUEUE_SHIFT 17
+#define I40E_GL_MDET_TX_QUEUE_MASK (0x3FFF << I40E_GL_MDET_TX_QUEUE_SHIFT)
+#define I40E_GL_MDET_TX_VALID_SHIFT 31
+#define I40E_GL_MDET_TX_VALID_MASK (0x1 << I40E_GL_MDET_TX_VALID_SHIFT)
+#define I40E_PF_MDET_RX 0x0012A400
+#define I40E_PF_MDET_RX_VALID_SHIFT 0
+#define I40E_PF_MDET_RX_VALID_MASK (0x1 << I40E_PF_MDET_RX_VALID_SHIFT)
+#define I40E_PF_MDET_TX 0x000E6400
+#define I40E_PF_MDET_TX_VALID_SHIFT 0
+#define I40E_PF_MDET_TX_VALID_MASK (0x1 << I40E_PF_MDET_TX_VALID_SHIFT)
+#define I40E_PF_VT_PFALLOC 0x001C0500
+#define I40E_PF_VT_PFALLOC_FIRSTVF_SHIFT 0
+#define I40E_PF_VT_PFALLOC_FIRSTVF_MASK (0xFF << I40E_PF_VT_PFALLOC_FIRSTVF_SHIFT)
+#define I40E_PF_VT_PFALLOC_LASTVF_SHIFT 8
+#define I40E_PF_VT_PFALLOC_LASTVF_MASK (0xFF << I40E_PF_VT_PFALLOC_LASTVF_SHIFT)
+#define I40E_PF_VT_PFALLOC_VALID_SHIFT 31
+#define I40E_PF_VT_PFALLOC_VALID_MASK (0x1 << I40E_PF_VT_PFALLOC_VALID_SHIFT)
+#define I40E_VP_MDET_RX(_VF) (0x0012A000 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VP_MDET_RX_MAX_INDEX 127
+#define I40E_VP_MDET_RX_VALID_SHIFT 0
+#define I40E_VP_MDET_RX_VALID_MASK (0x1 << I40E_VP_MDET_RX_VALID_SHIFT)
+#define I40E_VP_MDET_TX(_VF) (0x000E6000 + ((_VF) * 4)) /* _i=0...127 */
+#define I40E_VP_MDET_TX_MAX_INDEX 127
+#define I40E_VP_MDET_TX_VALID_SHIFT 0
+#define I40E_VP_MDET_TX_VALID_MASK (0x1 << I40E_VP_MDET_TX_VALID_SHIFT)
+#define I40E_GLPM_WUMC 0x0006C800
+#define I40E_GLPM_WUMC_NOTCO_SHIFT 0
+#define I40E_GLPM_WUMC_NOTCO_MASK (0x1 << I40E_GLPM_WUMC_NOTCO_SHIFT)
+#define I40E_GLPM_WUMC_SRST_PIN_VAL_SHIFT 1
+#define I40E_GLPM_WUMC_SRST_PIN_VAL_MASK (0x1 << I40E_GLPM_WUMC_SRST_PIN_VAL_SHIFT)
+#define I40E_GLPM_WUMC_ROL_MODE_SHIFT 2
+#define I40E_GLPM_WUMC_ROL_MODE_MASK (0x1 << I40E_GLPM_WUMC_ROL_MODE_SHIFT)
+#define I40E_GLPM_WUMC_RESERVED_4_SHIFT 3
+#define I40E_GLPM_WUMC_RESERVED_4_MASK (0x1FFF << I40E_GLPM_WUMC_RESERVED_4_SHIFT)
+#define I40E_GLPM_WUMC_MNG_WU_PF_SHIFT 16
+#define I40E_GLPM_WUMC_MNG_WU_PF_MASK (0xFFFF << I40E_GLPM_WUMC_MNG_WU_PF_SHIFT)
+#define I40E_PFPM_APM 0x000B8080
+#define I40E_PFPM_APM_APME_SHIFT 0
+#define I40E_PFPM_APM_APME_MASK (0x1 << I40E_PFPM_APM_APME_SHIFT)
+#define I40E_PFPM_FHFT_DATA(_i, _j) (0x00060000 + ((_i) * 4096 + (_j) * 128))
+#define I40E_PFPM_FHFT_DATA_MAX_INDEX 7
+#define I40E_PFPM_FHFT_DATA_DWORD_SHIFT 0
+#define I40E_PFPM_FHFT_DATA_DWORD_MASK (0xFFFFFFFF << I40E_PFPM_FHFT_DATA_DWORD_SHIFT)
+#define I40E_PFPM_FHFT_LENGTH(_i) (0x0006A000 + ((_i) * 128)) /* _i=0...7 */
+#define I40E_PFPM_FHFT_LENGTH_MAX_INDEX 7
+#define I40E_PFPM_FHFT_LENGTH_LENGTH_SHIFT 0
+#define I40E_PFPM_FHFT_LENGTH_LENGTH_MASK (0xFF << I40E_PFPM_FHFT_LENGTH_LENGTH_SHIFT)
+#define I40E_PFPM_FHFT_MASK(_i, _j) (0x00068000 + ((_i) * 1024 + (_j) * 128))
+#define I40E_PFPM_FHFT_MASK_MAX_INDEX 7
+#define I40E_PFPM_FHFT_MASK_MASK_SHIFT 0
+#define I40E_PFPM_FHFT_MASK_MASK_MASK (0xFFFF << I40E_PFPM_FHFT_MASK_MASK_SHIFT)
+#define I40E_PFPM_PROXYFC 0x00245A80
+#define I40E_PFPM_PROXYFC_PPROXYE_SHIFT 0
+#define I40E_PFPM_PROXYFC_PPROXYE_MASK (0x1 << I40E_PFPM_PROXYFC_PPROXYE_SHIFT)
+#define I40E_PFPM_PROXYFC_EX_SHIFT 1
+#define I40E_PFPM_PROXYFC_EX_MASK (0x1 << I40E_PFPM_PROXYFC_EX_SHIFT)
+#define I40E_PFPM_PROXYFC_ARP_SHIFT 4
+#define I40E_PFPM_PROXYFC_ARP_MASK (0x1 << I40E_PFPM_PROXYFC_ARP_SHIFT)
+#define I40E_PFPM_PROXYFC_ARP_DIRECTED_SHIFT 5
+#define I40E_PFPM_PROXYFC_ARP_DIRECTED_MASK (0x1 << I40E_PFPM_PROXYFC_ARP_DIRECTED_SHIFT)
+#define I40E_PFPM_PROXYFC_NS_SHIFT 9
+#define I40E_PFPM_PROXYFC_NS_MASK (0x1 << I40E_PFPM_PROXYFC_NS_SHIFT)
+#define I40E_PFPM_PROXYFC_NS_DIRECTED_SHIFT 10
+#define I40E_PFPM_PROXYFC_NS_DIRECTED_MASK (0x1 << I40E_PFPM_PROXYFC_NS_DIRECTED_SHIFT)
+#define I40E_PFPM_PROXYFC_MLD_SHIFT 12
+#define I40E_PFPM_PROXYFC_MLD_MASK (0x1 << I40E_PFPM_PROXYFC_MLD_SHIFT)
+#define I40E_PFPM_PROXYS 0x00245B80
+#define I40E_PFPM_PROXYS_EX_SHIFT 1
+#define I40E_PFPM_PROXYS_EX_MASK (0x1 << I40E_PFPM_PROXYS_EX_SHIFT)
+#define I40E_PFPM_PROXYS_ARP_SHIFT 4
+#define I40E_PFPM_PROXYS_ARP_MASK (0x1 << I40E_PFPM_PROXYS_ARP_SHIFT)
+#define I40E_PFPM_PROXYS_ARP_DIRECTED_SHIFT 5
+#define I40E_PFPM_PROXYS_ARP_DIRECTED_MASK (0x1 << I40E_PFPM_PROXYS_ARP_DIRECTED_SHIFT)
+#define I40E_PFPM_PROXYS_NS_SHIFT 9
+#define I40E_PFPM_PROXYS_NS_MASK (0x1 << I40E_PFPM_PROXYS_NS_SHIFT)
+#define I40E_PFPM_PROXYS_NS_DIRECTED_SHIFT 10
+#define I40E_PFPM_PROXYS_NS_DIRECTED_MASK (0x1 << I40E_PFPM_PROXYS_NS_DIRECTED_SHIFT)
+#define I40E_PFPM_PROXYS_MLD_SHIFT 12
+#define I40E_PFPM_PROXYS_MLD_MASK (0x1 << I40E_PFPM_PROXYS_MLD_SHIFT)
+#define I40E_PFPM_WUC 0x0006B200
+#define I40E_PFPM_WUC_EN_APM_D0_SHIFT 5
+#define I40E_PFPM_WUC_EN_APM_D0_MASK (0x1 << I40E_PFPM_WUC_EN_APM_D0_SHIFT)
+#define I40E_PFPM_WUFC 0x0006B400
+#define I40E_PFPM_WUFC_LNKC_SHIFT 0
+#define I40E_PFPM_WUFC_LNKC_MASK (0x1 << I40E_PFPM_WUFC_LNKC_SHIFT)
+#define I40E_PFPM_WUFC_MAG_SHIFT 1
+#define I40E_PFPM_WUFC_MAG_MASK (0x1 << I40E_PFPM_WUFC_MAG_SHIFT)
+#define I40E_PFPM_WUFC_MNG_SHIFT 3
+#define I40E_PFPM_WUFC_MNG_MASK (0x1 << I40E_PFPM_WUFC_MNG_SHIFT)
+#define I40E_PFPM_WUFC_FLX0_ACT_SHIFT 4
+#define I40E_PFPM_WUFC_FLX0_ACT_MASK (0x1 << I40E_PFPM_WUFC_FLX0_ACT_SHIFT)
+#define I40E_PFPM_WUFC_FLX1_ACT_SHIFT 5
+#define I40E_PFPM_WUFC_FLX1_ACT_MASK (0x1 << I40E_PFPM_WUFC_FLX1_ACT_SHIFT)
+#define I40E_PFPM_WUFC_FLX2_ACT_SHIFT 6
+#define I40E_PFPM_WUFC_FLX2_ACT_MASK (0x1 << I40E_PFPM_WUFC_FLX2_ACT_SHIFT)
+#define I40E_PFPM_WUFC_FLX3_ACT_SHIFT 7
+#define I40E_PFPM_WUFC_FLX3_ACT_MASK (0x1 << I40E_PFPM_WUFC_FLX3_ACT_SHIFT)
+#define I40E_PFPM_WUFC_FLX4_ACT_SHIFT 8
+#define I40E_PFPM_WUFC_FLX4_ACT_MASK (0x1 << I40E_PFPM_WUFC_FLX4_ACT_SHIFT)
+#define I40E_PFPM_WUFC_FLX5_ACT_SHIFT 9
+#define I40E_PFPM_WUFC_FLX5_ACT_MASK (0x1 << I40E_PFPM_WUFC_FLX5_ACT_SHIFT)
+#define I40E_PFPM_WUFC_FLX6_ACT_SHIFT 10
+#define I40E_PFPM_WUFC_FLX6_ACT_MASK (0x1 << I40E_PFPM_WUFC_FLX6_ACT_SHIFT)
+#define I40E_PFPM_WUFC_FLX7_ACT_SHIFT 11
+#define I40E_PFPM_WUFC_FLX7_ACT_MASK (0x1 << I40E_PFPM_WUFC_FLX7_ACT_SHIFT)
+#define I40E_PFPM_WUFC_FLX0_SHIFT 16
+#define I40E_PFPM_WUFC_FLX0_MASK (0x1 << I40E_PFPM_WUFC_FLX0_SHIFT)
+#define I40E_PFPM_WUFC_FLX1_SHIFT 17
+#define I40E_PFPM_WUFC_FLX1_MASK (0x1 << I40E_PFPM_WUFC_FLX1_SHIFT)
+#define I40E_PFPM_WUFC_FLX2_SHIFT 18
+#define I40E_PFPM_WUFC_FLX2_MASK (0x1 << I40E_PFPM_WUFC_FLX2_SHIFT)
+#define I40E_PFPM_WUFC_FLX3_SHIFT 19
+#define I40E_PFPM_WUFC_FLX3_MASK (0x1 << I40E_PFPM_WUFC_FLX3_SHIFT)
+#define I40E_PFPM_WUFC_FLX4_SHIFT 20
+#define I40E_PFPM_WUFC_FLX4_MASK (0x1 << I40E_PFPM_WUFC_FLX4_SHIFT)
+#define I40E_PFPM_WUFC_FLX5_SHIFT 21
+#define I40E_PFPM_WUFC_FLX5_MASK (0x1 << I40E_PFPM_WUFC_FLX5_SHIFT)
+#define I40E_PFPM_WUFC_FLX6_SHIFT 22
+#define I40E_PFPM_WUFC_FLX6_MASK (0x1 << I40E_PFPM_WUFC_FLX6_SHIFT)
+#define I40E_PFPM_WUFC_FLX7_SHIFT 23
+#define I40E_PFPM_WUFC_FLX7_MASK (0x1 << I40E_PFPM_WUFC_FLX7_SHIFT)
+#define I40E_PFPM_WUFC_FW_RST_WK_SHIFT 31
+#define I40E_PFPM_WUFC_FW_RST_WK_MASK (0x1 << I40E_PFPM_WUFC_FW_RST_WK_SHIFT)
+#define I40E_PFPM_WUS 0x0006B600
+#define I40E_PFPM_WUS_LNKC_SHIFT 0
+#define I40E_PFPM_WUS_LNKC_MASK (0x1 << I40E_PFPM_WUS_LNKC_SHIFT)
+#define I40E_PFPM_WUS_MAG_SHIFT 1
+#define I40E_PFPM_WUS_MAG_MASK (0x1 << I40E_PFPM_WUS_MAG_SHIFT)
+#define I40E_PFPM_WUS_PME_STATUS_SHIFT 2
+#define I40E_PFPM_WUS_PME_STATUS_MASK (0x1 << I40E_PFPM_WUS_PME_STATUS_SHIFT)
+#define I40E_PFPM_WUS_MNG_SHIFT 3
+#define I40E_PFPM_WUS_MNG_MASK (0x1 << I40E_PFPM_WUS_MNG_SHIFT)
+#define I40E_PFPM_WUS_FLX0_SHIFT 16
+#define I40E_PFPM_WUS_FLX0_MASK (0x1 << I40E_PFPM_WUS_FLX0_SHIFT)
+#define I40E_PFPM_WUS_FLX1_SHIFT 17
+#define I40E_PFPM_WUS_FLX1_MASK (0x1 << I40E_PFPM_WUS_FLX1_SHIFT)
+#define I40E_PFPM_WUS_FLX2_SHIFT 18
+#define I40E_PFPM_WUS_FLX2_MASK (0x1 << I40E_PFPM_WUS_FLX2_SHIFT)
+#define I40E_PFPM_WUS_FLX3_SHIFT 19
+#define I40E_PFPM_WUS_FLX3_MASK (0x1 << I40E_PFPM_WUS_FLX3_SHIFT)
+#define I40E_PFPM_WUS_FLX4_SHIFT 20
+#define I40E_PFPM_WUS_FLX4_MASK (0x1 << I40E_PFPM_WUS_FLX4_SHIFT)
+#define I40E_PFPM_WUS_FLX5_SHIFT 21
+#define I40E_PFPM_WUS_FLX5_MASK (0x1 << I40E_PFPM_WUS_FLX5_SHIFT)
+#define I40E_PFPM_WUS_FLX6_SHIFT 22
+#define I40E_PFPM_WUS_FLX6_MASK (0x1 << I40E_PFPM_WUS_FLX6_SHIFT)
+#define I40E_PFPM_WUS_FLX7_SHIFT 23
+#define I40E_PFPM_WUS_FLX7_MASK (0x1 << I40E_PFPM_WUS_FLX7_SHIFT)
+#define I40E_PFPM_WUS_FW_RST_WK_SHIFT 31
+#define I40E_PFPM_WUS_FW_RST_WK_MASK (0x1 << I40E_PFPM_WUS_FW_RST_WK_SHIFT)
+#define I40E_PRTPM_FHFHR 0x0006C000
+#define I40E_PRTPM_FHFHR_UNICAST_SHIFT 0
+#define I40E_PRTPM_FHFHR_UNICAST_MASK (0x1 << I40E_PRTPM_FHFHR_UNICAST_SHIFT)
+#define I40E_PRTPM_FHFHR_MULTICAST_SHIFT 1
+#define I40E_PRTPM_FHFHR_MULTICAST_MASK (0x1 << I40E_PRTPM_FHFHR_MULTICAST_SHIFT)
+#define I40E_PRTPM_SAH(_i) (0x001E44C0 + ((_i) * 32)) /* _i=0...3 */
+#define I40E_PRTPM_SAH_MAX_INDEX 3
+#define I40E_PRTPM_SAH_PFPM_SAH_SHIFT 0
+#define I40E_PRTPM_SAH_PFPM_SAH_MASK (0xFFFF << I40E_PRTPM_SAH_PFPM_SAH_SHIFT)
+#define I40E_PRTPM_SAH_PF_NUM_SHIFT 26
+#define I40E_PRTPM_SAH_PF_NUM_MASK (0xF << I40E_PRTPM_SAH_PF_NUM_SHIFT)
+#define I40E_PRTPM_SAH_MC_MAG_EN_SHIFT 30
+#define I40E_PRTPM_SAH_MC_MAG_EN_MASK (0x1 << I40E_PRTPM_SAH_MC_MAG_EN_SHIFT)
+#define I40E_PRTPM_SAH_AV_SHIFT 31
+#define I40E_PRTPM_SAH_AV_MASK (0x1 << I40E_PRTPM_SAH_AV_SHIFT)
+#define I40E_PRTPM_SAL(_i) (0x001E4440 + ((_i) * 32)) /* _i=0...3 */
+#define I40E_PRTPM_SAL_MAX_INDEX 3
+#define I40E_PRTPM_SAL_PFPM_SAL_SHIFT 0
+#define I40E_PRTPM_SAL_PFPM_SAL_MASK (0xFFFFFFFF << I40E_PRTPM_SAL_PFPM_SAL_SHIFT)
+#define I40E_VF_ARQBAH1 0x00006000
+#define I40E_VF_ARQBAH1_ARQBAH_SHIFT 0
+#define I40E_VF_ARQBAH1_ARQBAH_MASK (0xFFFFFFFF << I40E_VF_ARQBAH1_ARQBAH_SHIFT)
+#define I40E_VF_ARQBAL1 0x00006C00
+#define I40E_VF_ARQBAL1_ARQBAL_SHIFT 0
+#define I40E_VF_ARQBAL1_ARQBAL_MASK (0xFFFFFFFF << I40E_VF_ARQBAL1_ARQBAL_SHIFT)
+#define I40E_VF_ARQH1 0x00007400
+#define I40E_VF_ARQH1_ARQH_SHIFT 0
+#define I40E_VF_ARQH1_ARQH_MASK (0x3FF << I40E_VF_ARQH1_ARQH_SHIFT)
+#define I40E_VF_ARQLEN1 0x00008000
+#define I40E_VF_ARQLEN1_ARQLEN_SHIFT 0
+#define I40E_VF_ARQLEN1_ARQLEN_MASK (0x3FF << I40E_VF_ARQLEN1_ARQLEN_SHIFT)
+#define I40E_VF_ARQLEN1_ARQVFE_SHIFT 28
+#define I40E_VF_ARQLEN1_ARQVFE_MASK (0x1 << I40E_VF_ARQLEN1_ARQVFE_SHIFT)
+#define I40E_VF_ARQLEN1_ARQOVFL_SHIFT 29
+#define I40E_VF_ARQLEN1_ARQOVFL_MASK (0x1 << I40E_VF_ARQLEN1_ARQOVFL_SHIFT)
+#define I40E_VF_ARQLEN1_ARQCRIT_SHIFT 30
+#define I40E_VF_ARQLEN1_ARQCRIT_MASK (0x1 << I40E_VF_ARQLEN1_ARQCRIT_SHIFT)
+#define I40E_VF_ARQLEN1_ARQENABLE_SHIFT 31
+#define I40E_VF_ARQLEN1_ARQENABLE_MASK (0x1 << I40E_VF_ARQLEN1_ARQENABLE_SHIFT)
+#define I40E_VF_ARQT1 0x00007000
+#define I40E_VF_ARQT1_ARQT_SHIFT 0
+#define I40E_VF_ARQT1_ARQT_MASK (0x3FF << I40E_VF_ARQT1_ARQT_SHIFT)
+#define I40E_VF_ATQBAH1 0x00007800
+#define I40E_VF_ATQBAH1_ATQBAH_SHIFT 0
+#define I40E_VF_ATQBAH1_ATQBAH_MASK (0xFFFFFFFF << I40E_VF_ATQBAH1_ATQBAH_SHIFT)
+#define I40E_VF_ATQBAL1 0x00007C00
+#define I40E_VF_ATQBAL1_ATQBAL_SHIFT 0
+#define I40E_VF_ATQBAL1_ATQBAL_MASK (0xFFFFFFFF << I40E_VF_ATQBAL1_ATQBAL_SHIFT)
+#define I40E_VF_ATQH1 0x00006400
+#define I40E_VF_ATQH1_ATQH_SHIFT 0
+#define I40E_VF_ATQH1_ATQH_MASK (0x3FF << I40E_VF_ATQH1_ATQH_SHIFT)
+#define I40E_VF_ATQLEN1 0x00006800
+#define I40E_VF_ATQLEN1_ATQLEN_SHIFT 0
+#define I40E_VF_ATQLEN1_ATQLEN_MASK (0x3FF << I40E_VF_ATQLEN1_ATQLEN_SHIFT)
+#define I40E_VF_ATQLEN1_ATQVFE_SHIFT 28
+#define I40E_VF_ATQLEN1_ATQVFE_MASK (0x1 << I40E_VF_ATQLEN1_ATQVFE_SHIFT)
+#define I40E_VF_ATQLEN1_ATQOVFL_SHIFT 29
+#define I40E_VF_ATQLEN1_ATQOVFL_MASK (0x1 << I40E_VF_ATQLEN1_ATQOVFL_SHIFT)
+#define I40E_VF_ATQLEN1_ATQCRIT_SHIFT 30
+#define I40E_VF_ATQLEN1_ATQCRIT_MASK (0x1 << I40E_VF_ATQLEN1_ATQCRIT_SHIFT)
+#define I40E_VF_ATQLEN1_ATQENABLE_SHIFT 31
+#define I40E_VF_ATQLEN1_ATQENABLE_MASK (0x1 << I40E_VF_ATQLEN1_ATQENABLE_SHIFT)
+#define I40E_VF_ATQT1 0x00008400
+#define I40E_VF_ATQT1_ATQT_SHIFT 0
+#define I40E_VF_ATQT1_ATQT_MASK (0x3FF << I40E_VF_ATQT1_ATQT_SHIFT)
+#define I40E_VFGEN_RSTAT 0x00008800
+#define I40E_VFGEN_RSTAT_VFR_STATE_SHIFT 0
+#define I40E_VFGEN_RSTAT_VFR_STATE_MASK (0x3 << I40E_VFGEN_RSTAT_VFR_STATE_SHIFT)
+#define I40E_VFINT_DYN_CTL01 0x00005C00
+#define I40E_VFINT_DYN_CTL01_INTENA_SHIFT 0
+#define I40E_VFINT_DYN_CTL01_INTENA_MASK (0x1 << I40E_VFINT_DYN_CTL01_INTENA_SHIFT)
+#define I40E_VFINT_DYN_CTL01_CLEARPBA_SHIFT 1
+#define I40E_VFINT_DYN_CTL01_CLEARPBA_MASK (0x1 << I40E_VFINT_DYN_CTL01_CLEARPBA_SHIFT)
+#define I40E_VFINT_DYN_CTL01_SWINT_TRIG_SHIFT 2
+#define I40E_VFINT_DYN_CTL01_SWINT_TRIG_MASK (0x1 << I40E_VFINT_DYN_CTL01_SWINT_TRIG_SHIFT)
+#define I40E_VFINT_DYN_CTL01_ITR_INDX_SHIFT 3
+#define I40E_VFINT_DYN_CTL01_ITR_INDX_MASK (0x3 << I40E_VFINT_DYN_CTL01_ITR_INDX_SHIFT)
+#define I40E_VFINT_DYN_CTL01_INTERVAL_SHIFT 5
+#define I40E_VFINT_DYN_CTL01_INTERVAL_MASK (0xFFF << I40E_VFINT_DYN_CTL01_INTERVAL_SHIFT)
+#define I40E_VFINT_DYN_CTL01_SW_ITR_INDX_ENA_SHIFT 24
+#define I40E_VFINT_DYN_CTL01_SW_ITR_INDX_ENA_MASK (0x1 << I40E_VFINT_DYN_CTL01_SW_ITR_INDX_ENA_SHIFT)
+#define I40E_VFINT_DYN_CTL01_SW_ITR_INDX_SHIFT 25
+#define I40E_VFINT_DYN_CTL01_SW_ITR_INDX_MASK (0x3 << I40E_VFINT_DYN_CTL01_SW_ITR_INDX_SHIFT)
+#define I40E_VFINT_DYN_CTL01_INTENA_MSK_SHIFT 31
+#define I40E_VFINT_DYN_CTL01_INTENA_MSK_MASK (0x1 << I40E_VFINT_DYN_CTL01_INTENA_MSK_SHIFT)
+#define I40E_VFINT_DYN_CTLN1(_INTVF) (0x00003800 + ((_INTVF) * 4))
+#define I40E_VFINT_DYN_CTLN1_MAX_INDEX 15
+#define I40E_VFINT_DYN_CTLN1_INTENA_SHIFT 0
+#define I40E_VFINT_DYN_CTLN1_INTENA_MASK (0x1 << I40E_VFINT_DYN_CTLN1_INTENA_SHIFT)
+#define I40E_VFINT_DYN_CTLN1_CLEARPBA_SHIFT 1
+#define I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK (0x1 << I40E_VFINT_DYN_CTLN1_CLEARPBA_SHIFT)
+#define I40E_VFINT_DYN_CTLN1_SWINT_TRIG_SHIFT 2
+#define I40E_VFINT_DYN_CTLN1_SWINT_TRIG_MASK (0x1 << I40E_VFINT_DYN_CTLN1_SWINT_TRIG_SHIFT)
+#define I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT 3
+#define I40E_VFINT_DYN_CTLN1_ITR_INDX_MASK (0x3 << I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT)
+#define I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT 5
+#define I40E_VFINT_DYN_CTLN1_INTERVAL_MASK (0xFFF << I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT)
+#define I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_SHIFT 24
+#define I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_MASK (0x1 << I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_SHIFT)
+#define I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_SHIFT 25
+#define I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_MASK (0x3 << I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_SHIFT)
+#define I40E_VFINT_DYN_CTLN1_INTENA_MSK_SHIFT 31
+#define I40E_VFINT_DYN_CTLN1_INTENA_MSK_MASK (0x1 << I40E_VFINT_DYN_CTLN1_INTENA_MSK_SHIFT)
+#define I40E_VFINT_ICR0_ENA1 0x00005000
+#define I40E_VFINT_ICR0_ENA1_LINK_STAT_CHANGE_SHIFT 25
+#define I40E_VFINT_ICR0_ENA1_LINK_STAT_CHANGE_MASK (0x1 << I40E_VFINT_ICR0_ENA1_LINK_STAT_CHANGE_SHIFT)
+#define I40E_VFINT_ICR0_ENA1_ADMINQ_SHIFT 30
+#define I40E_VFINT_ICR0_ENA1_ADMINQ_MASK (0x1 << I40E_VFINT_ICR0_ENA1_ADMINQ_SHIFT)
+#define I40E_VFINT_ICR0_ENA1_RSVD_SHIFT 31
+#define I40E_VFINT_ICR0_ENA1_RSVD_MASK (0x1 << I40E_VFINT_ICR0_ENA1_RSVD_SHIFT)
+#define I40E_VFINT_ICR01 0x00004800
+#define I40E_VFINT_ICR01_INTEVENT_SHIFT 0
+#define I40E_VFINT_ICR01_INTEVENT_MASK (0x1 << I40E_VFINT_ICR01_INTEVENT_SHIFT)
+#define I40E_VFINT_ICR01_QUEUE_0_SHIFT 1
+#define I40E_VFINT_ICR01_QUEUE_0_MASK (0x1 << I40E_VFINT_ICR01_QUEUE_0_SHIFT)
+#define I40E_VFINT_ICR01_QUEUE_1_SHIFT 2
+#define I40E_VFINT_ICR01_QUEUE_1_MASK (0x1 << I40E_VFINT_ICR01_QUEUE_1_SHIFT)
+#define I40E_VFINT_ICR01_QUEUE_2_SHIFT 3
+#define I40E_VFINT_ICR01_QUEUE_2_MASK (0x1 << I40E_VFINT_ICR01_QUEUE_2_SHIFT)
+#define I40E_VFINT_ICR01_QUEUE_3_SHIFT 4
+#define I40E_VFINT_ICR01_QUEUE_3_MASK (0x1 << I40E_VFINT_ICR01_QUEUE_3_SHIFT)
+#define I40E_VFINT_ICR01_LINK_STAT_CHANGE_SHIFT 25
+#define I40E_VFINT_ICR01_LINK_STAT_CHANGE_MASK (0x1 << I40E_VFINT_ICR01_LINK_STAT_CHANGE_SHIFT)
+#define I40E_VFINT_ICR01_ADMINQ_SHIFT 30
+#define I40E_VFINT_ICR01_ADMINQ_MASK (0x1 << I40E_VFINT_ICR01_ADMINQ_SHIFT)
+#define I40E_VFINT_ICR01_SWINT_SHIFT 31
+#define I40E_VFINT_ICR01_SWINT_MASK (0x1 << I40E_VFINT_ICR01_SWINT_SHIFT)
+#define I40E_VFINT_ITR01(_i) (0x00004C00 + ((_i) * 4)) /* _i=0...2 */
+#define I40E_VFINT_ITR01_MAX_INDEX 2
+#define I40E_VFINT_ITR01_INTERVAL_SHIFT 0
+#define I40E_VFINT_ITR01_INTERVAL_MASK (0xFFF << I40E_VFINT_ITR01_INTERVAL_SHIFT)
+#define I40E_VFINT_ITRN1(_i, _INTVF) (0x00002800 + ((_i) * 64 + (_INTVF) * 4))
+#define I40E_VFINT_ITRN1_MAX_INDEX 2
+#define I40E_VFINT_ITRN1_INTERVAL_SHIFT 0
+#define I40E_VFINT_ITRN1_INTERVAL_MASK (0xFFF << I40E_VFINT_ITRN1_INTERVAL_SHIFT)
+#define I40E_VFINT_STAT_CTL01 0x00005400
+#define I40E_VFINT_STAT_CTL01_OTHER_ITR_INDX_SHIFT 2
+#define I40E_VFINT_STAT_CTL01_OTHER_ITR_INDX_MASK (0x3 << I40E_VFINT_STAT_CTL01_OTHER_ITR_INDX_SHIFT)
+#define I40E_QRX_TAIL1(_Q) (0x00002000 + ((_Q) * 4)) /* _i=0...15 */
+#define I40E_QRX_TAIL1_MAX_INDEX 15
+#define I40E_QRX_TAIL1_TAIL_SHIFT 0
+#define I40E_QRX_TAIL1_TAIL_MASK (0x1FFF << I40E_QRX_TAIL1_TAIL_SHIFT)
+#define I40E_QTX_TAIL1(_Q) (0x00000000 + ((_Q) * 4)) /* _i=0...15 */
+#define I40E_QTX_TAIL1_MAX_INDEX 15
+#define I40E_QTX_TAIL1_TAIL_SHIFT 0
+#define I40E_QTX_TAIL1_TAIL_MASK (0x1FFF << I40E_QTX_TAIL1_TAIL_SHIFT)
+#define I40E_VFMSIX_PBA 0x00002000
+#define I40E_VFMSIX_PBA_PENBIT_SHIFT 0
+#define I40E_VFMSIX_PBA_PENBIT_MASK (0xFFFFFFFF << I40E_VFMSIX_PBA_PENBIT_SHIFT)
+#define I40E_VFMSIX_TADD(_i) (0x00000008 + ((_i) * 16)) /* _i=0...16 */
+#define I40E_VFMSIX_TADD_MAX_INDEX 16
+#define I40E_VFMSIX_TADD_MSIXTADD10_SHIFT 0
+#define I40E_VFMSIX_TADD_MSIXTADD10_MASK (0x3 << I40E_VFMSIX_TADD_MSIXTADD10_SHIFT)
+#define I40E_VFMSIX_TADD_MSIXTADD_SHIFT 2
+#define I40E_VFMSIX_TADD_MSIXTADD_MASK (0x3FFFFFFF << I40E_VFMSIX_TADD_MSIXTADD_SHIFT)
+#define I40E_VFMSIX_TMSG(_i) (0x0000000C + ((_i) * 16)) /* _i=0...16 */
+#define I40E_VFMSIX_TMSG_MAX_INDEX 16
+#define I40E_VFMSIX_TMSG_MSIXTMSG_SHIFT 0
+#define I40E_VFMSIX_TMSG_MSIXTMSG_MASK (0xFFFFFFFF << I40E_VFMSIX_TMSG_MSIXTMSG_SHIFT)
+#define I40E_VFMSIX_TUADD(_i) (0x00000000 + ((_i) * 16)) /* _i=0...16 */
+#define I40E_VFMSIX_TUADD_MAX_INDEX 16
+#define I40E_VFMSIX_TUADD_MSIXTUADD_SHIFT 0
+#define I40E_VFMSIX_TUADD_MSIXTUADD_MASK (0xFFFFFFFF << I40E_VFMSIX_TUADD_MSIXTUADD_SHIFT)
+#define I40E_VFMSIX_TVCTRL(_i) (0x00000004 + ((_i) * 16)) /* _i=0...16 */
+#define I40E_VFMSIX_TVCTRL_MAX_INDEX 16
+#define I40E_VFMSIX_TVCTRL_MASK_SHIFT 0
+#define I40E_VFMSIX_TVCTRL_MASK_MASK (0x1 << I40E_VFMSIX_TVCTRL_MASK_SHIFT)
+#define I40E_VFCM_PE_ERRDATA 0x0000DC00
+#define I40E_VFCM_PE_ERRDATA_ERROR_CODE_SHIFT 0
+#define I40E_VFCM_PE_ERRDATA_ERROR_CODE_MASK (0xF << I40E_VFCM_PE_ERRDATA_ERROR_CODE_SHIFT)
+#define I40E_VFCM_PE_ERRDATA_Q_TYPE_SHIFT 4
+#define I40E_VFCM_PE_ERRDATA_Q_TYPE_MASK (0x7 << I40E_VFCM_PE_ERRDATA_Q_TYPE_SHIFT)
+#define I40E_VFCM_PE_ERRDATA_Q_NUM_SHIFT 8
+#define I40E_VFCM_PE_ERRDATA_Q_NUM_MASK (0x3FFFF << I40E_VFCM_PE_ERRDATA_Q_NUM_SHIFT)
+#define I40E_VFCM_PE_ERRINFO 0x0000D800
+#define I40E_VFCM_PE_ERRINFO_ERROR_VALID_SHIFT 0
+#define I40E_VFCM_PE_ERRINFO_ERROR_VALID_MASK (0x1 << I40E_VFCM_PE_ERRINFO_ERROR_VALID_SHIFT)
+#define I40E_VFCM_PE_ERRINFO_ERROR_INST_SHIFT 4
+#define I40E_VFCM_PE_ERRINFO_ERROR_INST_MASK (0x7 << I40E_VFCM_PE_ERRINFO_ERROR_INST_SHIFT)
+#define I40E_VFCM_PE_ERRINFO_DBL_ERROR_CNT_SHIFT 8
+#define I40E_VFCM_PE_ERRINFO_DBL_ERROR_CNT_MASK (0xFF << I40E_VFCM_PE_ERRINFO_DBL_ERROR_CNT_SHIFT)
+#define I40E_VFCM_PE_ERRINFO_RLU_ERROR_CNT_SHIFT 16
+#define I40E_VFCM_PE_ERRINFO_RLU_ERROR_CNT_MASK (0xFF << I40E_VFCM_PE_ERRINFO_RLU_ERROR_CNT_SHIFT)
+#define I40E_VFCM_PE_ERRINFO_RLS_ERROR_CNT_SHIFT 24
+#define I40E_VFCM_PE_ERRINFO_RLS_ERROR_CNT_MASK (0xFF << I40E_VFCM_PE_ERRINFO_RLS_ERROR_CNT_SHIFT)
+#define I40E_VFPE_AEQALLOC1 0x0000A400
+#define I40E_VFPE_AEQALLOC1_AECOUNT_SHIFT 0
+#define I40E_VFPE_AEQALLOC1_AECOUNT_MASK (0xFFFFFFFF << I40E_VFPE_AEQALLOC1_AECOUNT_SHIFT)
+#define I40E_VFPE_CCQPHIGH1 0x00009800
+#define I40E_VFPE_CCQPHIGH1_PECCQPHIGH_SHIFT 0
+#define I40E_VFPE_CCQPHIGH1_PECCQPHIGH_MASK (0xFFFFFFFF << I40E_VFPE_CCQPHIGH1_PECCQPHIGH_SHIFT)
+#define I40E_VFPE_CCQPLOW1 0x0000AC00
+#define I40E_VFPE_CCQPLOW1_PECCQPLOW_SHIFT 0
+#define I40E_VFPE_CCQPLOW1_PECCQPLOW_MASK (0xFFFFFFFF << I40E_VFPE_CCQPLOW1_PECCQPLOW_SHIFT)
+#define I40E_VFPE_CCQPSTATUS1 0x0000B800
+#define I40E_VFPE_CCQPSTATUS1_CCQP_DONE_SHIFT 0
+#define I40E_VFPE_CCQPSTATUS1_CCQP_DONE_MASK (0x1 << I40E_VFPE_CCQPSTATUS1_CCQP_DONE_SHIFT)
+#define I40E_VFPE_CCQPSTATUS1_CCQP_ERR_SHIFT 31
+#define I40E_VFPE_CCQPSTATUS1_CCQP_ERR_MASK (0x1 << I40E_VFPE_CCQPSTATUS1_CCQP_ERR_SHIFT)
+#define I40E_VFPE_CQACK1 0x0000B000
+#define I40E_VFPE_CQACK1_PECQID_SHIFT 0
+#define I40E_VFPE_CQACK1_PECQID_MASK (0x1FFFF << I40E_VFPE_CQACK1_PECQID_SHIFT)
+#define I40E_VFPE_CQARM1 0x0000B400
+#define I40E_VFPE_CQARM1_PECQID_SHIFT 0
+#define I40E_VFPE_CQARM1_PECQID_MASK (0x1FFFF << I40E_VFPE_CQARM1_PECQID_SHIFT)
+#define I40E_VFPE_CQPDB1 0x0000BC00
+#define I40E_VFPE_CQPDB1_WQHEAD_SHIFT 0
+#define I40E_VFPE_CQPDB1_WQHEAD_MASK (0x7FF << I40E_VFPE_CQPDB1_WQHEAD_SHIFT)
+#define I40E_VFPE_CQPERRCODES1 0x00009C00
+#define I40E_VFPE_CQPERRCODES1_CQP_MINOR_CODE_SHIFT 0
+#define I40E_VFPE_CQPERRCODES1_CQP_MINOR_CODE_MASK (0xFFFF << I40E_VFPE_CQPERRCODES1_CQP_MINOR_CODE_SHIFT)
+#define I40E_VFPE_CQPERRCODES1_CQP_MAJOR_CODE_SHIFT 16
+#define I40E_VFPE_CQPERRCODES1_CQP_MAJOR_CODE_MASK (0xFFFF << I40E_VFPE_CQPERRCODES1_CQP_MAJOR_CODE_SHIFT)
+#define I40E_VFPE_CQPTAIL1 0x0000A000
+#define I40E_VFPE_CQPTAIL1_WQTAIL_SHIFT 0
+#define I40E_VFPE_CQPTAIL1_WQTAIL_MASK (0x7FF << I40E_VFPE_CQPTAIL1_WQTAIL_SHIFT)
+#define I40E_VFPE_CQPTAIL1_CQP_OP_ERR_SHIFT 31
+#define I40E_VFPE_CQPTAIL1_CQP_OP_ERR_MASK (0x1 << I40E_VFPE_CQPTAIL1_CQP_OP_ERR_SHIFT)
+#define I40E_VFPE_IPCONFIG01 0x00008C00
+#define I40E_VFPE_IPCONFIG01_PEIPID_SHIFT 0
+#define I40E_VFPE_IPCONFIG01_PEIPID_MASK (0xFFFF << I40E_VFPE_IPCONFIG01_PEIPID_SHIFT)
+#define I40E_VFPE_IPCONFIG01_USEENTIREIDRANGE_SHIFT 16
+#define I40E_VFPE_IPCONFIG01_USEENTIREIDRANGE_MASK (0x1 << I40E_VFPE_IPCONFIG01_USEENTIREIDRANGE_SHIFT)
+#define I40E_VFPE_IPCONFIG01_USEUPPERIDRANGE_SHIFT 17
+#define I40E_VFPE_IPCONFIG01_USEUPPERIDRANGE_MASK (0x1 << I40E_VFPE_IPCONFIG01_USEUPPERIDRANGE_SHIFT)
+#define I40E_VFPE_MRTEIDXMASK1 0x00009000
+#define I40E_VFPE_MRTEIDXMASK1_MRTEIDXMASKBITS_SHIFT 0
+#define I40E_VFPE_MRTEIDXMASK1_MRTEIDXMASKBITS_MASK (0x1F << I40E_VFPE_MRTEIDXMASK1_MRTEIDXMASKBITS_SHIFT)
+#define I40E_VFPE_RCVUNEXPECTEDERROR1 0x00009400
+#define I40E_VFPE_RCVUNEXPECTEDERROR1_TCP_RX_UNEXP_ERR_SHIFT 0
+#define I40E_VFPE_RCVUNEXPECTEDERROR1_TCP_RX_UNEXP_ERR_MASK (0xFFFFFF << I40E_VFPE_RCVUNEXPECTEDERROR1_TCP_RX_UNEXP_ERR_SHIFT)
+#define I40E_VFPE_TCPNOWTIMER1 0x0000A800
+#define I40E_VFPE_TCPNOWTIMER1_TCP_NOW_SHIFT 0
+#define I40E_VFPE_TCPNOWTIMER1_TCP_NOW_MASK (0xFFFFFFFF << I40E_VFPE_TCPNOWTIMER1_TCP_NOW_SHIFT)
+#define I40E_VFPE_WQEALLOC1 0x0000C000
+#define I40E_VFPE_WQEALLOC1_PEQPID_SHIFT 0
+#define I40E_VFPE_WQEALLOC1_PEQPID_MASK (0x3FFFF << I40E_VFPE_WQEALLOC1_PEQPID_SHIFT)
+#define I40E_VFPE_WQEALLOC1_WQE_DESC_INDEX_SHIFT 20
+#define I40E_VFPE_WQEALLOC1_WQE_DESC_INDEX_MASK (0xFFF << I40E_VFPE_WQEALLOC1_WQE_DESC_INDEX_SHIFT)
+#define I40E_VFQF_HENA(_i) (0x0000C400 + ((_i) * 4)) /* _i=0...1 */
+#define I40E_VFQF_HENA_MAX_INDEX 1
+#define I40E_VFQF_HENA_PTYPE_ENA_SHIFT 0
+#define I40E_VFQF_HENA_PTYPE_ENA_MASK (0xFFFFFFFF << I40E_VFQF_HENA_PTYPE_ENA_SHIFT)
+#define I40E_VFQF_HKEY(_i) (0x0000CC00 + ((_i) * 4)) /* _i=0...12 */
+#define I40E_VFQF_HKEY_MAX_INDEX 12
+#define I40E_VFQF_HKEY_KEY_0_SHIFT 0
+#define I40E_VFQF_HKEY_KEY_0_MASK (0xFF << I40E_VFQF_HKEY_KEY_0_SHIFT)
+#define I40E_VFQF_HKEY_KEY_1_SHIFT 8
+#define I40E_VFQF_HKEY_KEY_1_MASK (0xFF << I40E_VFQF_HKEY_KEY_1_SHIFT)
+#define I40E_VFQF_HKEY_KEY_2_SHIFT 16
+#define I40E_VFQF_HKEY_KEY_2_MASK (0xFF << I40E_VFQF_HKEY_KEY_2_SHIFT)
+#define I40E_VFQF_HKEY_KEY_3_SHIFT 24
+#define I40E_VFQF_HKEY_KEY_3_MASK (0xFF << I40E_VFQF_HKEY_KEY_3_SHIFT)
+#define I40E_VFQF_HLUT(_i) (0x0000D000 + ((_i) * 4)) /* _i=0...15 */
+#define I40E_VFQF_HLUT_MAX_INDEX 15
+#define I40E_VFQF_HLUT_LUT0_SHIFT 0
+#define I40E_VFQF_HLUT_LUT0_MASK (0xF << I40E_VFQF_HLUT_LUT0_SHIFT)
+#define I40E_VFQF_HLUT_LUT1_SHIFT 8
+#define I40E_VFQF_HLUT_LUT1_MASK (0xF << I40E_VFQF_HLUT_LUT1_SHIFT)
+#define I40E_VFQF_HLUT_LUT2_SHIFT 16
+#define I40E_VFQF_HLUT_LUT2_MASK (0xF << I40E_VFQF_HLUT_LUT2_SHIFT)
+#define I40E_VFQF_HLUT_LUT3_SHIFT 24
+#define I40E_VFQF_HLUT_LUT3_MASK (0xF << I40E_VFQF_HLUT_LUT3_SHIFT)
+#define I40E_VFQF_HREGION(_i) (0x0000D400 + ((_i) * 4)) /* _i=0...7 */
+#define I40E_VFQF_HREGION_MAX_INDEX 7
+#define I40E_VFQF_HREGION_OVERRIDE_ENA_0_SHIFT 0
+#define I40E_VFQF_HREGION_OVERRIDE_ENA_0_MASK (0x1 << I40E_VFQF_HREGION_OVERRIDE_ENA_0_SHIFT)
+#define I40E_VFQF_HREGION_REGION_0_SHIFT 1
+#define I40E_VFQF_HREGION_REGION_0_MASK (0x7 << I40E_VFQF_HREGION_REGION_0_SHIFT)
+#define I40E_VFQF_HREGION_OVERRIDE_ENA_1_SHIFT 4
+#define I40E_VFQF_HREGION_OVERRIDE_ENA_1_MASK (0x1 << I40E_VFQF_HREGION_OVERRIDE_ENA_1_SHIFT)
+#define I40E_VFQF_HREGION_REGION_1_SHIFT 5
+#define I40E_VFQF_HREGION_REGION_1_MASK (0x7 << I40E_VFQF_HREGION_REGION_1_SHIFT)
+#define I40E_VFQF_HREGION_OVERRIDE_ENA_2_SHIFT 8
+#define I40E_VFQF_HREGION_OVERRIDE_ENA_2_MASK (0x1 << I40E_VFQF_HREGION_OVERRIDE_ENA_2_SHIFT)
+#define I40E_VFQF_HREGION_REGION_2_SHIFT 9
+#define I40E_VFQF_HREGION_REGION_2_MASK (0x7 << I40E_VFQF_HREGION_REGION_2_SHIFT)
+#define I40E_VFQF_HREGION_OVERRIDE_ENA_3_SHIFT 12
+#define I40E_VFQF_HREGION_OVERRIDE_ENA_3_MASK (0x1 << I40E_VFQF_HREGION_OVERRIDE_ENA_3_SHIFT)
+#define I40E_VFQF_HREGION_REGION_3_SHIFT 13
+#define I40E_VFQF_HREGION_REGION_3_MASK (0x7 << I40E_VFQF_HREGION_REGION_3_SHIFT)
+#define I40E_VFQF_HREGION_OVERRIDE_ENA_4_SHIFT 16
+#define I40E_VFQF_HREGION_OVERRIDE_ENA_4_MASK (0x1 << I40E_VFQF_HREGION_OVERRIDE_ENA_4_SHIFT)
+#define I40E_VFQF_HREGION_REGION_4_SHIFT 17
+#define I40E_VFQF_HREGION_REGION_4_MASK (0x7 << I40E_VFQF_HREGION_REGION_4_SHIFT)
+#define I40E_VFQF_HREGION_OVERRIDE_ENA_5_SHIFT 20
+#define I40E_VFQF_HREGION_OVERRIDE_ENA_5_MASK (0x1 << I40E_VFQF_HREGION_OVERRIDE_ENA_5_SHIFT)
+#define I40E_VFQF_HREGION_REGION_5_SHIFT 21
+#define I40E_VFQF_HREGION_REGION_5_MASK (0x7 << I40E_VFQF_HREGION_REGION_5_SHIFT)
+#define I40E_VFQF_HREGION_OVERRIDE_ENA_6_SHIFT 24
+#define I40E_VFQF_HREGION_OVERRIDE_ENA_6_MASK (0x1 << I40E_VFQF_HREGION_OVERRIDE_ENA_6_SHIFT)
+#define I40E_VFQF_HREGION_REGION_6_SHIFT 25
+#define I40E_VFQF_HREGION_REGION_6_MASK (0x7 << I40E_VFQF_HREGION_REGION_6_SHIFT)
+#define I40E_VFQF_HREGION_OVERRIDE_ENA_7_SHIFT 28
+#define I40E_VFQF_HREGION_OVERRIDE_ENA_7_MASK (0x1 << I40E_VFQF_HREGION_OVERRIDE_ENA_7_SHIFT)
+#define I40E_VFQF_HREGION_REGION_7_SHIFT 29
+#define I40E_VFQF_HREGION_REGION_7_MASK (0x7 << I40E_VFQF_HREGION_REGION_7_SHIFT)
+
+#endif
diff --git a/drivers/net/ethernet/intel/i40e/i40e_status.h b/drivers/net/ethernet/intel/i40e/i40e_status.h
new file mode 100644
index 0000000..5e5bcdd
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_status.h
@@ -0,0 +1,101 @@
+/*******************************************************************************
+ *
+ * Intel Ethernet Controller XL710 Family Linux Driver
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ ******************************************************************************/
+
+#ifndef _I40E_STATUS_H_
+#define _I40E_STATUS_H_
+
+/* Error Codes */
+enum i40e_status_code {
+ I40E_SUCCESS = 0,
+ I40E_ERR_NVM = -1,
+ I40E_ERR_NVM_CHECKSUM = -2,
+ I40E_ERR_PHY = -3,
+ I40E_ERR_CONFIG = -4,
+ I40E_ERR_PARAM = -5,
+ I40E_ERR_MAC_TYPE = -6,
+ I40E_ERR_UNKNOWN_PHY = -7,
+ I40E_ERR_LINK_SETUP = -8,
+ I40E_ERR_ADAPTER_STOPPED = -9,
+ I40E_ERR_INVALID_MAC_ADDR = -10,
+ I40E_ERR_DEVICE_NOT_SUPPORTED = -11,
+ I40E_ERR_MASTER_REQUESTS_PENDING = -12,
+ I40E_ERR_INVALID_LINK_SETTINGS = -13,
+ I40E_ERR_AUTONEG_NOT_COMPLETE = -14,
+ I40E_ERR_RESET_FAILED = -15,
+ I40E_ERR_SWFW_SYNC = -16,
+ I40E_ERR_NO_AVAILABLE_VSI = -17,
+ I40E_ERR_NO_MEMORY = -18,
+ I40E_ERR_BAD_PTR = -19,
+ I40E_ERR_RING_FULL = -20,
+ I40E_ERR_INVALID_PD_ID = -21,
+ I40E_ERR_INVALID_QP_ID = -22,
+ I40E_ERR_INVALID_CQ_ID = -23,
+ I40E_ERR_INVALID_CEQ_ID = -24,
+ I40E_ERR_INVALID_AEQ_ID = -25,
+ I40E_ERR_INVALID_SIZE = -26,
+ I40E_ERR_INVALID_ARP_INDEX = -27,
+ I40E_ERR_INVALID_FPM_FUNC_ID = -28,
+ I40E_ERR_QP_INVALID_MSG_SIZE = -29,
+ I40E_ERR_QP_TOOMANY_WRS_POSTED = -30,
+ I40E_ERR_INVALID_FRAG_COUNT = -31,
+ I40E_ERR_QUEUE_EMPTY = -32,
+ I40E_ERR_INVALID_ALIGNMENT = -33,
+ I40E_ERR_FLUSHED_QUEUE = -34,
+ I40E_ERR_INVALID_PUSH_PAGE_INDEX = -35,
+ I40E_ERR_INVALID_IMM_DATA_SIZE = -36,
+ I40E_ERR_TIMEOUT = -37,
+ I40E_ERR_OPCODE_MISMATCH = -38,
+ I40E_ERR_CQP_COMPL_ERROR = -39,
+ I40E_ERR_INVALID_VF_ID = -40,
+ I40E_ERR_INVALID_HMCFN_ID = -41,
+ I40E_ERR_BACKING_PAGE_ERROR = -42,
+ I40E_ERR_NO_PBLCHUNKS_AVAILABLE = -43,
+ I40E_ERR_INVALID_PBLE_INDEX = -44,
+ I40E_ERR_INVALID_SD_INDEX = -45,
+ I40E_ERR_INVALID_PAGE_DESC_INDEX = -46,
+ I40E_ERR_INVALID_SD_TYPE = -47,
+ I40E_ERR_MEMCPY_FAILED = -48,
+ I40E_ERR_INVALID_HMC_OBJ_INDEX = -49,
+ I40E_ERR_INVALID_HMC_OBJ_COUNT = -50,
+ I40E_ERR_INVALID_SRQ_ARM_LIMIT = -51,
+ I40E_ERR_SRQ_ENABLED = -52,
+ I40E_ERR_ADMIN_QUEUE_ERROR = -53,
+ I40E_ERR_ADMIN_QUEUE_TIMEOUT = -54,
+ I40E_ERR_BUF_TOO_SHORT = -55,
+ I40E_ERR_ADMIN_QUEUE_FULL = -56,
+ I40E_ERR_ADMIN_QUEUE_NO_WORK = -57,
+ I40E_ERR_BAD_IWARP_CQE = -58,
+ I40E_ERR_NVM_BLANK_MODE = -59,
+ I40E_ERR_NOT_IMPLEMENTED = -60,
+ I40E_ERR_PE_DOORBELL_NOT_ENABLED = -61,
+ I40E_ERR_DIAG_TEST_FAILED = -62,
+ I40E_ERR_NOT_READY = -63,
+ I40E_NOT_SUPPORTED = -64,
+ I40E_ERR_FIRMWARE_API_VERSION = -65,
+};
+
+#endif /* _I40E_STATUS_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
new file mode 100644
index 0000000..49d2cfa
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -0,0 +1,1817 @@
+/*******************************************************************************
+ *
+ * Intel Ethernet Controller XL710 Family Linux Driver
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ ******************************************************************************/
+
+#include "i40e.h"
+
+static inline __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size,
+ u32 td_tag)
+{
+ return cpu_to_le64(I40E_TX_DESC_DTYPE_DATA |
+ ((u64)td_cmd << I40E_TXD_QW1_CMD_SHIFT) |
+ ((u64)td_offset << I40E_TXD_QW1_OFFSET_SHIFT) |
+ ((u64)size << I40E_TXD_QW1_TX_BUF_SZ_SHIFT) |
+ ((u64)td_tag << I40E_TXD_QW1_L2TAG1_SHIFT));
+}
+
+/**
+ * i40e_program_fdir_filter - Program a Flow Director filter
+ * @fdir_input: Packet data that will be filter parameters
+ * @pf: The pf pointer
+ * @add: True for add/update, False for remove
+ **/
+int i40e_program_fdir_filter(struct i40e_fdir_data *fdir_data,
+ struct i40e_pf *pf, bool add)
+{
+ struct i40e_filter_program_desc *fdir_desc;
+ struct i40e_tx_buffer *tx_buf;
+ struct i40e_tx_desc *tx_desc;
+ struct i40e_ring *tx_ring;
+ struct i40e_vsi *vsi;
+ struct device *dev;
+ dma_addr_t dma;
+ u32 td_cmd = 0;
+ u16 i;
+
+ /* find existing FDIR VSI */
+ vsi = NULL;
+ for (i = 0; i < pf->hw.func_caps.num_vsis; i++)
+ if (pf->vsi[i] && pf->vsi[i]->type == I40E_VSI_FDIR)
+ vsi = pf->vsi[i];
+ if (!vsi)
+ return -ENOENT;
+
+ tx_ring = &vsi->tx_rings[0];
+ dev = tx_ring->dev;
+
+ dma = dma_map_single(dev, fdir_data->raw_packet,
+ I40E_FDIR_MAX_RAW_PACKET_LOOKUP, DMA_TO_DEVICE);
+ if (dma_mapping_error(dev, dma))
+ goto dma_fail;
+
+ /* grab the next descriptor */
+ fdir_desc = I40E_TX_FDIRDESC(tx_ring, tx_ring->next_to_use);
+ tx_buf = &tx_ring->tx_bi[tx_ring->next_to_use];
+ tx_ring->next_to_use++;
+ if (tx_ring->next_to_use == tx_ring->count)
+ tx_ring->next_to_use = 0;
+
+ fdir_desc->qindex_flex_ptype_vsi = cpu_to_le32((fdir_data->q_index
+ << I40E_TXD_FLTR_QW0_QINDEX_SHIFT)
+ & I40E_TXD_FLTR_QW0_QINDEX_MASK);
+
+ fdir_desc->qindex_flex_ptype_vsi |= cpu_to_le32((fdir_data->flex_off
+ << I40E_TXD_FLTR_QW0_FLEXOFF_SHIFT)
+ & I40E_TXD_FLTR_QW0_FLEXOFF_MASK);
+
+ fdir_desc->qindex_flex_ptype_vsi |= cpu_to_le32((fdir_data->pctype
+ << I40E_TXD_FLTR_QW0_PCTYPE_SHIFT)
+ & I40E_TXD_FLTR_QW0_PCTYPE_MASK);
+
+ /* Use LAN VSI Id if not programmed by user */
+ if (fdir_data->dest_vsi == 0)
+ fdir_desc->qindex_flex_ptype_vsi |=
+ cpu_to_le32((pf->vsi[pf->lan_vsi]->id)
+ << I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT);
+ else
+ fdir_desc->qindex_flex_ptype_vsi |=
+ cpu_to_le32((fdir_data->dest_vsi
+ << I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT)
+ & I40E_TXD_FLTR_QW0_DEST_VSI_MASK);
+
+ fdir_desc->dtype_cmd_cntindex =
+ cpu_to_le32(I40E_TX_DESC_DTYPE_FILTER_PROG);
+
+ if (add)
+ fdir_desc->dtype_cmd_cntindex |= cpu_to_le32(
+ I40E_FILTER_PROGRAM_DESC_PCMD_ADD_UPDATE
+ << I40E_TXD_FLTR_QW1_PCMD_SHIFT);
+ else
+ fdir_desc->dtype_cmd_cntindex |= cpu_to_le32(
+ I40E_FILTER_PROGRAM_DESC_PCMD_REMOVE
+ << I40E_TXD_FLTR_QW1_PCMD_SHIFT);
+
+ fdir_desc->dtype_cmd_cntindex |= cpu_to_le32((fdir_data->dest_ctl
+ << I40E_TXD_FLTR_QW1_DEST_SHIFT)
+ & I40E_TXD_FLTR_QW1_DEST_MASK);
+
+ fdir_desc->dtype_cmd_cntindex |= cpu_to_le32(
+ (fdir_data->fd_status << I40E_TXD_FLTR_QW1_FD_STATUS_SHIFT)
+ & I40E_TXD_FLTR_QW1_FD_STATUS_MASK);
+
+ if (fdir_data->cnt_index != 0) {
+ fdir_desc->dtype_cmd_cntindex |=
+ cpu_to_le32(I40E_TXD_FLTR_QW1_CNT_ENA_MASK);
+ fdir_desc->dtype_cmd_cntindex |=
+ cpu_to_le32((fdir_data->cnt_index
+ << I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT)
+ & I40E_TXD_FLTR_QW1_CNTINDEX_MASK);
+ }
+
+ fdir_desc->fd_id = cpu_to_le32(fdir_data->fd_id);
+
+ /* Now program a dummy descriptor */
+ tx_desc = I40E_TX_DESC(tx_ring, tx_ring->next_to_use);
+ tx_buf = &tx_ring->tx_bi[tx_ring->next_to_use];
+ tx_ring->next_to_use++;
+ if (tx_ring->next_to_use == tx_ring->count)
+ tx_ring->next_to_use = 0;
+
+ tx_desc->buffer_addr = cpu_to_le64(dma);
+ td_cmd = I40E_TX_DESC_CMD_EOP |
+ I40E_TX_DESC_CMD_RS |
+ I40E_TX_DESC_CMD_DUMMY;
+
+ tx_desc->cmd_type_offset_bsz =
+ build_ctob(td_cmd, 0, I40E_FDIR_MAX_RAW_PACKET_LOOKUP, 0);
+
+ /* Mark the data descriptor to be watched */
+ tx_buf->next_to_watch = tx_desc;
+
+ /* Force memory writes to complete before letting h/w
+ * know there are new descriptors to fetch. (Only
+ * applicable for weak-ordered memory model archs,
+ * such as IA-64).
+ */
+ wmb();
+
+ writel(tx_ring->next_to_use, tx_ring->tail);
+ return 0;
+
+dma_fail:
+ return -1;
+}
+
+/**
+ * i40e_fd_handle_status - check the Programming Status for FD
+ * @rx_ring: the Rx ring for this descriptor
+ * @qw: the descriptor data
+ * @prog_id: the id originally used for programming
+ *
+ * This is used to verify if the FD programming or invalidation
+ * requested by SW to the HW is successful or not and take actions accordingly.
+ **/
+static void i40e_fd_handle_status(struct i40e_ring *rx_ring, u32 qw, u8 prog_id)
+{
+ struct pci_dev *pdev = rx_ring->vsi->back->pdev;
+ u32 error;
+
+ error = (qw & I40E_RX_PROG_STATUS_DESC_QW1_ERROR_MASK) >>
+ I40E_RX_PROG_STATUS_DESC_QW1_ERROR_SHIFT;
+
+ /* for now just print the Status */
+ dev_info(&pdev->dev, "FD programming id %02x, Status %08x\n",
+ prog_id, error);
+}
+
+/**
+ * i40e_unmap_tx_resource - Release a Tx buffer
+ * @ring: the ring that owns the buffer
+ * @tx_buffer: the buffer to free
+ **/
+static inline void i40e_unmap_tx_resource(struct i40e_ring *ring,
+ struct i40e_tx_buffer *tx_buffer)
+{
+ if (tx_buffer->dma) {
+ if (tx_buffer->tx_flags & I40E_TX_FLAGS_MAPPED_AS_PAGE)
+ dma_unmap_page(ring->dev,
+ tx_buffer->dma,
+ tx_buffer->length,
+ DMA_TO_DEVICE);
+ else
+ dma_unmap_single(ring->dev,
+ tx_buffer->dma,
+ tx_buffer->length,
+ DMA_TO_DEVICE);
+ }
+ tx_buffer->dma = 0;
+ tx_buffer->time_stamp = 0;
+}
+
+/**
+ * i40e_clean_tx_ring - Free any empty Tx buffers
+ * @tx_ring: ring to be cleaned
+ **/
+void i40e_clean_tx_ring(struct i40e_ring *tx_ring)
+{
+ struct i40e_tx_buffer *tx_buffer;
+ unsigned long bi_size;
+ u16 i;
+
+ /* ring already cleared, nothing to do */
+ if (!tx_ring->tx_bi)
+ return;
+
+ /* Free all the Tx ring sk_buffs */
+ for (i = 0; i < tx_ring->count; i++) {
+ tx_buffer = &tx_ring->tx_bi[i];
+ i40e_unmap_tx_resource(tx_ring, tx_buffer);
+ if (tx_buffer->skb)
+ dev_kfree_skb_any(tx_buffer->skb);
+ tx_buffer->skb = NULL;
+ }
+
+ bi_size = sizeof(struct i40e_tx_buffer) * tx_ring->count;
+ memset(tx_ring->tx_bi, 0, bi_size);
+
+ /* Zero out the descriptor ring */
+ memset(tx_ring->desc, 0, tx_ring->size);
+
+ tx_ring->next_to_use = 0;
+ tx_ring->next_to_clean = 0;
+}
+
+/**
+ * i40e_free_tx_resources - Free Tx resources per queue
+ * @tx_ring: Tx descriptor ring for a specific queue
+ *
+ * Free all transmit software resources
+ **/
+void i40e_free_tx_resources(struct i40e_ring *tx_ring)
+{
+ i40e_clean_tx_ring(tx_ring);
+ kfree(tx_ring->tx_bi);
+ tx_ring->tx_bi = NULL;
+
+ if (tx_ring->desc) {
+ dma_free_coherent(tx_ring->dev, tx_ring->size,
+ tx_ring->desc, tx_ring->dma);
+ tx_ring->desc = NULL;
+ }
+}
+
+/**
+ * i40e_get_tx_pending - how many tx descriptors not processed
+ * @tx_ring: the ring of descriptors
+ *
+ * Since there is no access to the ring head register
+ * in XL710, we need to use our local copies
+ **/
+static u32 i40e_get_tx_pending(struct i40e_ring *ring)
+{
+ u32 ntu = ((ring->next_to_clean <= ring->next_to_use)
+ ? ring->next_to_use
+ : ring->next_to_use + ring->count);
+ return ntu - ring->next_to_clean;
+}
+
+/**
+ * i40e_check_tx_hang - Is there a hang in the Tx queue
+ * @tx_ring: the ring of descriptors
+ **/
+static bool i40e_check_tx_hang(struct i40e_ring *tx_ring)
+{
+ u32 tx_pending = i40e_get_tx_pending(tx_ring);
+ bool ret = false;
+
+ clear_check_for_tx_hang(tx_ring);
+
+ /* Check for a hung queue, but be thorough. This verifies
+ * that a transmit has been completed since the previous
+ * check AND there is at least one packet pending. The
+ * ARMED bit is set to indicate a potential hang. The
+ * bit is cleared if a pause frame is received to remove
+ * false hang detection due to PFC or 802.3x frames. By
+ * requiring this to fail twice we avoid races with
+ * PFC clearing the ARMED bit and conditions where we
+ * run the check_tx_hang logic with a transmit completion
+ * pending but without time to complete it yet.
+ */
+ if ((tx_ring->tx_stats.tx_done_old == tx_ring->tx_stats.packets) &&
+ tx_pending) {
+ /* make sure it is true for two checks in a row */
+ ret = test_and_set_bit(__I40E_HANG_CHECK_ARMED,
+ &tx_ring->state);
+ } else {
+ /* update completed stats and disarm the hang check */
+ tx_ring->tx_stats.tx_done_old = tx_ring->tx_stats.packets;
+ clear_bit(__I40E_HANG_CHECK_ARMED, &tx_ring->state);
+ }
+
+ return ret;
+}
+
+/**
+ * i40e_clean_tx_irq - Reclaim resources after transmit completes
+ * @tx_ring: tx ring to clean
+ * @budget: how many cleans we're allowed
+ *
+ * Returns true if there's any budget left (e.g. the clean is finished)
+ **/
+static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget)
+{
+ u16 i = tx_ring->next_to_clean;
+ struct i40e_tx_buffer *tx_buf;
+ struct i40e_tx_desc *tx_desc;
+ unsigned int total_packets = 0;
+ unsigned int total_bytes = 0;
+
+ tx_buf = &tx_ring->tx_bi[i];
+ tx_desc = I40E_TX_DESC(tx_ring, i);
+
+ for (; budget; budget--) {
+ struct i40e_tx_desc *eop_desc;
+
+ eop_desc = tx_buf->next_to_watch;
+
+ /* if next_to_watch is not set then there is no work pending */
+ if (!eop_desc)
+ break;
+
+ /* if the descriptor isn't done, no work yet to do */
+ if (!(eop_desc->cmd_type_offset_bsz &
+ cpu_to_le64(I40E_TX_DESC_DTYPE_DESC_DONE)))
+ break;
+
+ /* count the packet as being completed */
+ tx_ring->tx_stats.completed++;
+ tx_buf->next_to_watch = NULL;
+ tx_buf->time_stamp = 0;
+
+ /* set memory barrier before eop_desc is verified */
+ rmb();
+
+ do {
+ i40e_unmap_tx_resource(tx_ring, tx_buf);
+
+ /* clear dtype status */
+ tx_desc->cmd_type_offset_bsz &=
+ ~cpu_to_le64(I40E_TXD_QW1_DTYPE_MASK);
+
+ if (likely(tx_desc == eop_desc)) {
+ eop_desc = NULL;
+
+ dev_kfree_skb_any(tx_buf->skb);
+ tx_buf->skb = NULL;
+
+ total_bytes += tx_buf->bytecount;
+ total_packets += tx_buf->gso_segs;
+ }
+
+ tx_buf++;
+ tx_desc++;
+ i++;
+ if (unlikely(i == tx_ring->count)) {
+ i = 0;
+ tx_buf = tx_ring->tx_bi;
+ tx_desc = I40E_TX_DESC(tx_ring, 0);
+ }
+ } while (eop_desc);
+ }
+
+ tx_ring->next_to_clean = i;
+ tx_ring->tx_stats.bytes += total_bytes;
+ tx_ring->tx_stats.packets += total_packets;
+ tx_ring->q_vector->tx.total_bytes += total_bytes;
+ tx_ring->q_vector->tx.total_packets += total_packets;
+ if (check_for_tx_hang(tx_ring) && i40e_check_tx_hang(tx_ring)) {
+ /* schedule immediate reset if we believe we hung */
+ dev_info(tx_ring->dev, "Detected Tx Unit Hang\n"
+ " VSI <%d>\n"
+ " Tx Queue <%d>\n"
+ " next_to_use <%x>\n"
+ " next_to_clean <%x>\n",
+ tx_ring->vsi->seid,
+ tx_ring->queue_index,
+ tx_ring->next_to_use, i);
+ dev_info(tx_ring->dev, "tx_bi[next_to_clean]\n"
+ " time_stamp <%lx>\n"
+ " jiffies <%lx>\n",
+ tx_ring->tx_bi[i].time_stamp, jiffies);
+
+ netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);
+
+ dev_info(tx_ring->dev,
+ "tx hang detected on queue %d, resetting adapter\n",
+ tx_ring->queue_index);
+
+ tx_ring->netdev->netdev_ops->ndo_tx_timeout(tx_ring->netdev);
+
+ /* the adapter is about to reset, no point in enabling stuff */
+ return true;
+ }
+
+#define TX_WAKE_THRESHOLD (DESC_NEEDED * 2)
+ if (unlikely(total_packets && netif_carrier_ok(tx_ring->netdev) &&
+ (I40E_DESC_UNUSED(tx_ring) >= TX_WAKE_THRESHOLD))) {
+ /* Make sure that anybody stopping the queue after this
+ * sees the new next_to_clean.
+ */
+ smp_mb();
+ if (__netif_subqueue_stopped(tx_ring->netdev,
+ tx_ring->queue_index) &&
+ !test_bit(__I40E_DOWN, &tx_ring->vsi->state)) {
+ netif_wake_subqueue(tx_ring->netdev,
+ tx_ring->queue_index);
+ ++tx_ring->tx_stats.restart_queue;
+ }
+ }
+
+ return budget > 0;
+}
+
+/**
+ * i40e_set_new_dynamic_itr - Find new ITR level
+ * @rc: structure containing ring performance data
+ *
+ * Stores a new ITR value based on packets and byte counts during
+ * the last interrupt. The advantage of per interrupt computation
+ * is faster updates and more accurate ITR for the current traffic
+ * pattern. Constants in this function were computed based on
+ * theoretical maximum wire speed and thresholds were set based on
+ * testing data as well as attempting to minimize response time
+ * while increasing bulk throughput.
+ **/
+static void i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
+{
+ enum i40e_latency_range new_latency_range = rc->latency_range;
+ u32 new_itr = rc->itr;
+ int bytes_per_int;
+
+ if (rc->total_packets == 0 || !rc->itr)
+ return;
+
+ /* simple throttlerate management
+ * 0-10MB/s lowest (100000 ints/s)
+ * 10-20MB/s low (20000 ints/s)
+ * 20-1249MB/s bulk (8000 ints/s)
+ */
+ bytes_per_int = rc->total_bytes / rc->itr;
+ switch (rc->itr) {
+ case I40E_LOWEST_LATENCY:
+ if (bytes_per_int > 10)
+ new_latency_range = I40E_LOW_LATENCY;
+ break;
+ case I40E_LOW_LATENCY:
+ if (bytes_per_int > 20)
+ new_latency_range = I40E_BULK_LATENCY;
+ else if (bytes_per_int <= 10)
+ new_latency_range = I40E_LOWEST_LATENCY;
+ break;
+ case I40E_BULK_LATENCY:
+ if (bytes_per_int <= 20)
+ rc->latency_range = I40E_LOW_LATENCY;
+ break;
+ }
+
+ switch (new_latency_range) {
+ case I40E_LOWEST_LATENCY:
+ new_itr = I40E_ITR_100K;
+ break;
+ case I40E_LOW_LATENCY:
+ new_itr = I40E_ITR_20K;
+ break;
+ case I40E_BULK_LATENCY:
+ new_itr = I40E_ITR_8K;
+ break;
+ default:
+ break;
+ }
+
+ if (new_itr != rc->itr) {
+ /* do an exponential smoothing */
+ new_itr = (10 * new_itr * rc->itr) /
+ ((9 * new_itr) + rc->itr);
+ rc->itr = new_itr & I40E_MAX_ITR;
+ }
+
+ rc->total_bytes = 0;
+ rc->total_packets = 0;
+}
+
+/**
+ * i40e_update_dynamic_itr - Adjust ITR based on bytes per int
+ * @q_vector: the vector to adjust
+ **/
+static void i40e_update_dynamic_itr(struct i40e_q_vector *q_vector)
+{
+ u16 vector = q_vector->vsi->base_vector + q_vector->v_idx;
+ struct i40e_hw *hw = &q_vector->vsi->back->hw;
+ u32 reg_addr;
+ u16 old_itr;
+
+ reg_addr = I40E_PFINT_ITRN(I40E_RX_ITR, vector - 1);
+ old_itr = q_vector->rx.itr;
+ i40e_set_new_dynamic_itr(&q_vector->rx);
+ if (old_itr != q_vector->rx.itr)
+ wr32(hw, reg_addr, q_vector->rx.itr);
+
+ reg_addr = I40E_PFINT_ITRN(I40E_TX_ITR, vector - 1);
+ old_itr = q_vector->tx.itr;
+ i40e_set_new_dynamic_itr(&q_vector->tx);
+ if (old_itr != q_vector->tx.itr)
+ wr32(hw, reg_addr, q_vector->tx.itr);
+
+ i40e_flush(hw);
+}
+
+/**
+ * i40e_clean_programming_status - clean the programming status descriptor
+ * @rx_ring: the rx ring that has this descriptor
+ * @rx_desc: the rx descriptor written back by HW
+ *
+ * Flow director should handle FD_FILTER_STATUS to check its filter programming
+ * status being successful or not and take actions accordingly. FCoE should
+ * handle its context/filter programming/invalidation status and take actions.
+ *
+ **/
+static void i40e_clean_programming_status(struct i40e_ring *rx_ring,
+ union i40e_rx_desc *rx_desc)
+{
+ u64 qw;
+ u8 id;
+
+ qw = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
+ id = (qw & I40E_RX_PROG_STATUS_DESC_QW1_PROGID_MASK) >>
+ I40E_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT;
+
+ if (id == I40E_RX_PROG_STATUS_DESC_FD_FILTER_STATUS)
+ i40e_fd_handle_status(rx_ring, qw, id);
+}
+
+/**
+ * i40e_setup_tx_descriptors - Allocate the Tx descriptors
+ * @tx_ring: the tx ring to set up
+ *
+ * Return 0 on success, negative on error
+ **/
+int i40e_setup_tx_descriptors(struct i40e_ring *tx_ring)
+{
+ struct device *dev = tx_ring->dev;
+ int bi_size;
+
+ if (!dev)
+ return -ENOMEM;
+
+ bi_size = sizeof(struct i40e_tx_buffer) * tx_ring->count;
+ tx_ring->tx_bi = kzalloc(bi_size, GFP_KERNEL);
+ if (!tx_ring->tx_bi)
+ goto err;
+
+ /* round up to nearest 4K */
+ tx_ring->size = tx_ring->count * sizeof(struct i40e_tx_desc);
+ tx_ring->size = ALIGN(tx_ring->size, 4096);
+ tx_ring->desc = dma_alloc_coherent(dev, tx_ring->size,
+ &tx_ring->dma, GFP_KERNEL);
+ if (!tx_ring->desc) {
+ dev_info(dev, "Unable to allocate memory for the Tx descriptor ring, size=%d\n",
+ tx_ring->size);
+ goto err;
+ }
+
+ tx_ring->next_to_use = 0;
+ tx_ring->next_to_clean = 0;
+ return 0;
+
+err:
+ kfree(tx_ring->tx_bi);
+ tx_ring->tx_bi = NULL;
+ return -ENOMEM;
+}
+
+/**
+ * i40e_clean_rx_ring - Free Rx buffers
+ * @rx_ring: ring to be cleaned
+ **/
+void i40e_clean_rx_ring(struct i40e_ring *rx_ring)
+{
+ struct device *dev = rx_ring->dev;
+ struct i40e_rx_buffer *rx_bi;
+ unsigned long bi_size;
+ u16 i;
+
+ /* ring already cleared, nothing to do */
+ if (!rx_ring->rx_bi)
+ return;
+
+ /* Free all the Rx ring sk_buffs */
+ for (i = 0; i < rx_ring->count; i++) {
+ rx_bi = &rx_ring->rx_bi[i];
+ if (rx_bi->dma) {
+ dma_unmap_single(dev,
+ rx_bi->dma,
+ rx_ring->rx_buf_len,
+ DMA_FROM_DEVICE);
+ rx_bi->dma = 0;
+ }
+ if (rx_bi->skb) {
+ dev_kfree_skb(rx_bi->skb);
+ rx_bi->skb = NULL;
+ }
+ if (rx_bi->page) {
+ if (rx_bi->page_dma) {
+ dma_unmap_page(dev,
+ rx_bi->page_dma,
+ PAGE_SIZE / 2,
+ DMA_FROM_DEVICE);
+ rx_bi->page_dma = 0;
+ }
+ __free_page(rx_bi->page);
+ rx_bi->page = NULL;
+ rx_bi->page_offset = 0;
+ }
+ }
+
+ bi_size = sizeof(struct i40e_rx_buffer) * rx_ring->count;
+ memset(rx_ring->rx_bi, 0, bi_size);
+
+ /* Zero out the descriptor ring */
+ memset(rx_ring->desc, 0, rx_ring->size);
+
+ rx_ring->next_to_clean = 0;
+ rx_ring->next_to_use = 0;
+}
+
+/**
+ * i40e_free_rx_resources - Free Rx resources
+ * @rx_ring: ring to clean the resources from
+ *
+ * Free all receive software resources
+ **/
+void i40e_free_rx_resources(struct i40e_ring *rx_ring)
+{
+ i40e_clean_rx_ring(rx_ring);
+ kfree(rx_ring->rx_bi);
+ rx_ring->rx_bi = NULL;
+
+ if (rx_ring->desc) {
+ dma_free_coherent(rx_ring->dev, rx_ring->size,
+ rx_ring->desc, rx_ring->dma);
+ rx_ring->desc = NULL;
+ }
+}
+
+/**
+ * i40e_setup_rx_descriptors - Allocate Rx descriptors
+ * @rx_ring: Rx descriptor ring (for a specific queue) to setup
+ *
+ * Returns 0 on success, negative on failure
+ **/
+int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring)
+{
+ struct device *dev = rx_ring->dev;
+ int bi_size;
+
+ bi_size = sizeof(struct i40e_rx_buffer) * rx_ring->count;
+ rx_ring->rx_bi = kzalloc(bi_size, GFP_KERNEL);
+ if (!rx_ring->rx_bi)
+ goto err;
+
+ /* Round up to nearest 4K */
+ rx_ring->size = ring_is_16byte_desc_enabled(rx_ring)
+ ? rx_ring->count * sizeof(union i40e_16byte_rx_desc)
+ : rx_ring->count * sizeof(union i40e_32byte_rx_desc);
+ rx_ring->size = ALIGN(rx_ring->size, 4096);
+ rx_ring->desc = dma_alloc_coherent(dev, rx_ring->size,
+ &rx_ring->dma, GFP_KERNEL);
+
+ if (!rx_ring->desc) {
+ dev_info(dev, "Unable to allocate memory for the Rx descriptor ring, size=%d\n",
+ rx_ring->size);
+ goto err;
+ }
+
+ rx_ring->next_to_clean = 0;
+ rx_ring->next_to_use = 0;
+
+ return 0;
+err:
+ kfree(rx_ring->rx_bi);
+ rx_ring->rx_bi = NULL;
+ return -ENOMEM;
+}
+
+/**
+ * i40e_release_rx_desc - Store the new tail and head values
+ * @rx_ring: ring to bump
+ * @val: new head index
+ **/
+static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val)
+{
+ rx_ring->next_to_use = val;
+ /* Force memory writes to complete before letting h/w
+ * know there are new descriptors to fetch. (Only
+ * applicable for weak-ordered memory model archs,
+ * such as IA-64).
+ */
+ wmb();
+ writel(val, rx_ring->tail);
+}
+
+/**
+ * i40e_alloc_rx_buffers - Replace used receive buffers; packet split
+ * @rx_ring: ring to place buffers on
+ * @cleaned_count: number of buffers to replace
+ **/
+void i40e_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count)
+{
+ u16 i = rx_ring->next_to_use;
+ union i40e_rx_desc *rx_desc;
+ struct i40e_rx_buffer *bi;
+ struct sk_buff *skb;
+
+ /* do nothing if no valid netdev defined */
+ if (!rx_ring->netdev || !cleaned_count)
+ return;
+
+ while (cleaned_count--) {
+ rx_desc = I40E_RX_DESC(rx_ring, i);
+ bi = &rx_ring->rx_bi[i];
+ skb = bi->skb;
+
+ if (!skb) {
+ skb = netdev_alloc_skb_ip_align(rx_ring->netdev,
+ rx_ring->rx_buf_len);
+ if (!skb) {
+ rx_ring->rx_stats.alloc_rx_buff_failed++;
+ goto no_buffers;
+ }
+ /* initialize queue mapping */
+ skb_record_rx_queue(skb, rx_ring->queue_index);
+ bi->skb = skb;
+ }
+
+ if (!bi->dma) {
+ bi->dma = dma_map_single(rx_ring->dev,
+ skb->data,
+ rx_ring->rx_buf_len,
+ DMA_FROM_DEVICE);
+ if (dma_mapping_error(rx_ring->dev, bi->dma)) {
+ rx_ring->rx_stats.alloc_rx_buff_failed++;
+ bi->dma = 0;
+ goto no_buffers;
+ }
+ }
+
+ if (ring_is_ps_enabled(rx_ring)) {
+ if (!bi->page) {
+ bi->page = alloc_page(GFP_ATOMIC);
+ if (!bi->page) {
+ rx_ring->rx_stats.alloc_rx_page_failed++;
+ goto no_buffers;
+ }
+ }
+
+ if (!bi->page_dma) {
+ /* use a half page if we're re-using */
+ bi->page_offset ^= PAGE_SIZE / 2;
+ bi->page_dma = dma_map_page(rx_ring->dev,
+ bi->page,
+ bi->page_offset,
+ PAGE_SIZE / 2,
+ DMA_FROM_DEVICE);
+ if (dma_mapping_error(rx_ring->dev,
+ bi->page_dma)) {
+ rx_ring->rx_stats.alloc_rx_page_failed++;
+ bi->page_dma = 0;
+ goto no_buffers;
+ }
+ }
+
+ /* Refresh the desc even if buffer_addrs didn't change
+ * because each write-back erases this info.
+ */
+ rx_desc->read.pkt_addr = cpu_to_le64(bi->page_dma);
+ rx_desc->read.hdr_addr = cpu_to_le64(bi->dma);
+ } else {
+ rx_desc->read.pkt_addr = cpu_to_le64(bi->dma);
+ rx_desc->read.hdr_addr = 0;
+ }
+ i++;
+ if (i == rx_ring->count)
+ i = 0;
+ }
+
+no_buffers:
+ if (rx_ring->next_to_use != i)
+ i40e_release_rx_desc(rx_ring, i);
+}
+
+/**
+ * i40e_receive_skb - Send a completed packet up the stack
+ * @rx_ring: rx ring in play
+ * @skb: packet to send up
+ * @vlan_tag: vlan tag for packet
+ **/
+static void i40e_receive_skb(struct i40e_ring *rx_ring,
+ struct sk_buff *skb, u16 vlan_tag)
+{
+ struct i40e_q_vector *q_vector = rx_ring->q_vector;
+ struct i40e_vsi *vsi = rx_ring->vsi;
+ u64 flags = vsi->back->flags;
+
+ if (vlan_tag & VLAN_VID_MASK)
+ __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tag);
+
+ if (flags & I40E_FLAG_IN_NETPOLL)
+ netif_rx(skb);
+ else
+ napi_gro_receive(&q_vector->napi, skb);
+}
+
+/**
+ * i40e_rx_checksum - Indicate in skb if hw indicated a good cksum
+ * @vsi: the VSI we care about
+ * @skb: skb currently being received and modified
+ * @rx_status: status value of last descriptor in packet
+ * @rx_error: error value of last descriptor in packet
+ **/
+static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
+ struct sk_buff *skb,
+ u32 rx_status,
+ u32 rx_error)
+{
+ skb->ip_summed = CHECKSUM_NONE;
+
+ /* Rx csum enabled and ip headers found? */
+ if (!(vsi->netdev->features & NETIF_F_RXCSUM &&
+ rx_status & (1 << I40E_RX_DESC_STATUS_L3L4P_SHIFT)))
+ return;
+
+ /* IP or L4 checksum error */
+ if (rx_error & ((1 << I40E_RX_DESC_ERROR_IPE_SHIFT) |
+ (1 << I40E_RX_DESC_ERROR_L4E_SHIFT))) {
+ vsi->back->hw_csum_rx_error++;
+ return;
+ }
+
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+}
+
+/**
+ * i40e_rx_hash - returns the hash value from the Rx descriptor
+ * @ring: descriptor ring
+ * @rx_desc: specific descriptor
+ **/
+static inline u32 i40e_rx_hash(struct i40e_ring *ring,
+ union i40e_rx_desc *rx_desc)
+{
+ if (ring->netdev->features & NETIF_F_RXHASH) {
+ if ((le64_to_cpu(rx_desc->wb.qword1.status_error_len) >>
+ I40E_RX_DESC_STATUS_FLTSTAT_SHIFT) &
+ I40E_RX_DESC_FLTSTAT_RSS_HASH)
+ return le32_to_cpu(rx_desc->wb.qword0.hi_dword.rss);
+ }
+ return 0;
+}
+
+/**
+ * i40e_clean_rx_irq - Reclaim resources after receive completes
+ * @rx_ring: rx ring to clean
+ * @budget: how many cleans we're allowed
+ *
+ * Returns true if there's any budget left (e.g. the clean is finished)
+ **/
+static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
+{
+ unsigned int total_rx_bytes = 0, total_rx_packets = 0;
+ u16 rx_packet_len, rx_header_len, rx_sph, rx_hbo;
+ u16 cleaned_count = I40E_DESC_UNUSED(rx_ring);
+ const int current_node = numa_node_id();
+ struct i40e_vsi *vsi = rx_ring->vsi;
+ u16 i = rx_ring->next_to_clean;
+ union i40e_rx_desc *rx_desc;
+ u32 rx_error, rx_status;
+ u64 qword;
+
+ rx_desc = I40E_RX_DESC(rx_ring, i);
+ qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
+ rx_status = (qword & I40E_RXD_QW1_STATUS_MASK)
+ >> I40E_RXD_QW1_STATUS_SHIFT;
+
+ while (rx_status & (1 << I40E_RX_DESC_STATUS_DD_SHIFT)) {
+ union i40e_rx_desc *next_rxd;
+ struct i40e_rx_buffer *rx_bi;
+ struct sk_buff *skb;
+ u16 vlan_tag;
+ if (i40e_rx_is_programming_status(qword)) {
+ i40e_clean_programming_status(rx_ring, rx_desc);
+ I40E_RX_NEXT_DESC_PREFETCH(rx_ring, i, next_rxd);
+ goto next_desc;
+ }
+ rx_bi = &rx_ring->rx_bi[i];
+ skb = rx_bi->skb;
+ prefetch(skb->data);
+
+ rx_packet_len = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK)
+ >> I40E_RXD_QW1_LENGTH_PBUF_SHIFT;
+ rx_header_len = (qword & I40E_RXD_QW1_LENGTH_HBUF_MASK)
+ >> I40E_RXD_QW1_LENGTH_HBUF_SHIFT;
+ rx_sph = (qword & I40E_RXD_QW1_LENGTH_SPH_MASK)
+ >> I40E_RXD_QW1_LENGTH_SPH_SHIFT;
+
+ rx_error = (qword & I40E_RXD_QW1_ERROR_MASK)
+ >> I40E_RXD_QW1_ERROR_SHIFT;
+ rx_hbo = rx_error & (1 << I40E_RX_DESC_ERROR_HBO_SHIFT);
+ rx_error &= ~(1 << I40E_RX_DESC_ERROR_HBO_SHIFT);
+
+ rx_bi->skb = NULL;
+
+ /* This memory barrier is needed to keep us from reading
+ * any other fields out of the rx_desc until we know the
+ * STATUS_DD bit is set
+ */
+ rmb();
+
+ /* Get the header and possibly the whole packet
+ * If this is an skb from previous receive dma will be 0
+ */
+ if (rx_bi->dma) {
+ u16 len;
+
+ if (rx_hbo)
+ len = I40E_RX_HDR_SIZE;
+ else if (rx_sph)
+ len = rx_header_len;
+ else if (rx_packet_len)
+ len = rx_packet_len; /* 1buf/no split found */
+ else
+ len = rx_header_len; /* split always mode */
+
+ skb_put(skb, len);
+ dma_unmap_single(rx_ring->dev,
+ rx_bi->dma,
+ rx_ring->rx_buf_len,
+ DMA_FROM_DEVICE);
+ rx_bi->dma = 0;
+ }
+
+ /* Get the rest of the data if this was a header split */
+ if (ring_is_ps_enabled(rx_ring) && rx_packet_len) {
+
+ skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags,
+ rx_bi->page,
+ rx_bi->page_offset,
+ rx_packet_len);
+
+ skb->len += rx_packet_len;
+ skb->data_len += rx_packet_len;
+ skb->truesize += rx_packet_len;
+
+ if ((page_count(rx_bi->page) == 1) &&
+ (page_to_nid(rx_bi->page) == current_node))
+ get_page(rx_bi->page);
+ else
+ rx_bi->page = NULL;
+
+ dma_unmap_page(rx_ring->dev,
+ rx_bi->page_dma,
+ PAGE_SIZE / 2,
+ DMA_FROM_DEVICE);
+ rx_bi->page_dma = 0;
+ }
+ I40E_RX_NEXT_DESC_PREFETCH(rx_ring, i, next_rxd);
+
+ if (unlikely(
+ !(rx_status & (1 << I40E_RX_DESC_STATUS_EOF_SHIFT)))) {
+ struct i40e_rx_buffer *next_buffer;
+
+ next_buffer = &rx_ring->rx_bi[i];
+
+ if (ring_is_ps_enabled(rx_ring)) {
+ rx_bi->skb = next_buffer->skb;
+ rx_bi->dma = next_buffer->dma;
+ next_buffer->skb = skb;
+ next_buffer->dma = 0;
+ }
+ rx_ring->rx_stats.non_eop_descs++;
+ goto next_desc;
+ }
+
+ /* ERR_MASK will only have valid bits if EOP set */
+ if (unlikely(rx_error & (1 << I40E_RX_DESC_ERROR_RXE_SHIFT))) {
+ dev_kfree_skb_any(skb);
+ goto next_desc;
+ }
+
+ skb->rxhash = i40e_rx_hash(rx_ring, rx_desc);
+ i40e_rx_checksum(vsi, skb, rx_status, rx_error);
+
+ /* probably a little skewed due to removing CRC */
+ total_rx_bytes += skb->len;
+ total_rx_packets++;
+
+ skb->protocol = eth_type_trans(skb, rx_ring->netdev);
+ vlan_tag = rx_status & (1 << I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)
+ ? le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1)
+ : 0;
+ i40e_receive_skb(rx_ring, skb, vlan_tag);
+
+ rx_ring->netdev->last_rx = jiffies;
+ budget--;
+next_desc:
+ rx_desc->wb.qword1.status_error_len = 0;
+ if (!budget)
+ break;
+
+ cleaned_count++;
+ /* return some buffers to hardware, one at a time is too slow */
+ if (cleaned_count >= I40E_RX_BUFFER_WRITE) {
+ i40e_alloc_rx_buffers(rx_ring, cleaned_count);
+ cleaned_count = 0;
+ }
+
+ /* use prefetched values */
+ rx_desc = next_rxd;
+ qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
+ rx_status = (qword & I40E_RXD_QW1_STATUS_MASK)
+ >> I40E_RXD_QW1_STATUS_SHIFT;
+ }
+
+ rx_ring->next_to_clean = i;
+ rx_ring->rx_stats.packets += total_rx_packets;
+ rx_ring->rx_stats.bytes += total_rx_bytes;
+ rx_ring->q_vector->rx.total_packets += total_rx_packets;
+ rx_ring->q_vector->rx.total_bytes += total_rx_bytes;
+
+ if (cleaned_count)
+ i40e_alloc_rx_buffers(rx_ring, cleaned_count);
+
+ return budget > 0;
+}
+
+/**
+ * i40e_napi_poll - NAPI polling Rx/Tx cleanup routine
+ * @napi: napi struct with our devices info in it
+ * @budget: amount of work driver is allowed to do this pass, in packets
+ *
+ * This function will clean all queues associated with a q_vector.
+ *
+ * Returns the amount of work done
+ **/
+int i40e_napi_poll(struct napi_struct *napi, int budget)
+{
+ struct i40e_q_vector *q_vector =
+ container_of(napi, struct i40e_q_vector, napi);
+ struct i40e_vsi *vsi = q_vector->vsi;
+ bool clean_complete = true;
+ int budget_per_ring;
+ int i;
+
+ if (test_bit(__I40E_DOWN, &vsi->state)) {
+ napi_complete(napi);
+ return 0;
+ }
+
+ /* We attempt to distribute budget to each Rx queue fairly, but don't
+ * allow the budget to go below 1 because that would exit polling early.
+ * Since the actual Tx work is minimal, we can give the Tx a larger
+ * budget and be more aggressive about cleaning up the Tx descriptors.
+ */
+ budget_per_ring = max(budget/q_vector->num_ringpairs, 1);
+ for (i = 0; i < q_vector->num_ringpairs; i++) {
+ clean_complete &= i40e_clean_tx_irq(q_vector->tx.ring[i],
+ vsi->work_limit);
+ clean_complete &= i40e_clean_rx_irq(q_vector->rx.ring[i],
+ budget_per_ring);
+ }
+
+ /* If work not completed, return budget and polling will return */
+ if (!clean_complete)
+ return budget;
+
+ /* Work is done so exit the polling mode and re-enable the interrupt */
+ napi_complete(napi);
+ if (ITR_IS_DYNAMIC(vsi->rx_itr_setting) ||
+ ITR_IS_DYNAMIC(vsi->tx_itr_setting))
+ i40e_update_dynamic_itr(q_vector);
+
+ if (!test_bit(__I40E_DOWN, &vsi->state)) {
+ if (vsi->back->flags & I40E_FLAG_MSIX_ENABLED) {
+ i40e_irq_dynamic_enable(vsi,
+ q_vector->v_idx + vsi->base_vector);
+ } else {
+ struct i40e_hw *hw = &vsi->back->hw;
+ /* We re-enable the queue 0 cause, but
+ * don't worry about dynamic_enable
+ * because we left it on for the other
+ * possible interrupts during napi
+ */
+ u32 qval = rd32(hw, I40E_QINT_RQCTL(0));
+ qval |= I40E_QINT_RQCTL_CAUSE_ENA_MASK;
+ wr32(hw, I40E_QINT_RQCTL(0), qval);
+
+ qval = rd32(hw, I40E_QINT_TQCTL(0));
+ qval |= I40E_QINT_TQCTL_CAUSE_ENA_MASK;
+ wr32(hw, I40E_QINT_TQCTL(0), qval);
+ i40e_flush(hw);
+ }
+ }
+
+ return 0;
+}
+
+/**
+ * i40e_atr - Add a Flow Director ATR filter
+ * @tx_ring: ring to add programming descriptor to
+ * @skb: send buffer
+ * @flags: send flags
+ * @protocol: wire protocol
+ **/
+static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
+ u32 flags, __be16 protocol)
+{
+ struct i40e_filter_program_desc *fdir_desc;
+ struct i40e_pf *pf = tx_ring->vsi->back;
+ union {
+ unsigned char *network;
+ struct iphdr *ipv4;
+ struct ipv6hdr *ipv6;
+ } hdr;
+ struct tcphdr *th;
+ unsigned int hlen;
+ u32 flex_ptype, dtype_cmd;
+
+ /* make sure ATR is enabled */
+ if (!(pf->flags & I40E_FLAG_FDIR_ATR_ENABLED))
+ return;
+
+ /* if sampling is disabled do nothing */
+ if (!tx_ring->atr_sample_rate)
+ return;
+
+ tx_ring->atr_count++;
+
+ /* snag network header to get L4 type and address */
+ hdr.network = skb_network_header(skb);
+
+ /* Currently only IPv4/IPv6 with TCP is supported */
+ if (protocol == htons(ETH_P_IP)) {
+ if (hdr.ipv4->protocol != IPPROTO_TCP)
+ return;
+
+ /* access ihl as a u8 to avoid unaligned access on ia64 */
+ hlen = (hdr.network[0] & 0x0F) << 2;
+ } else if (protocol == htons(ETH_P_IPV6)) {
+ if (hdr.ipv6->nexthdr != IPPROTO_TCP)
+ return;
+
+ hlen = sizeof(struct ipv6hdr);
+ } else {
+ return;
+ }
+
+ th = (struct tcphdr *)(hdr.network + hlen);
+
+ /* sample on all syn/fin packets or once every atr sample rate */
+ if (!th->fin && !th->syn && (tx_ring->atr_count < tx_ring->atr_sample_rate))
+ return;
+
+ tx_ring->atr_count = 0;
+
+ /* grab the next descriptor */
+ fdir_desc = I40E_TX_FDIRDESC(tx_ring, tx_ring->next_to_use);
+ tx_ring->next_to_use++;
+ if (tx_ring->next_to_use == tx_ring->count)
+ tx_ring->next_to_use = 0;
+
+ flex_ptype = (tx_ring->queue_index << I40E_TXD_FLTR_QW0_QINDEX_SHIFT) &
+ I40E_TXD_FLTR_QW0_QINDEX_MASK;
+ flex_ptype |= (protocol == htons(ETH_P_IP)) ?
+ (I40E_FILTER_PCTYPE_NONF_IPV4_TCP <<
+ I40E_TXD_FLTR_QW0_PCTYPE_SHIFT) :
+ (I40E_FILTER_PCTYPE_NONF_IPV6_TCP <<
+ I40E_TXD_FLTR_QW0_PCTYPE_SHIFT);
+
+ flex_ptype |= tx_ring->vsi->id << I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT;
+
+ dtype_cmd = I40E_TX_DESC_DTYPE_FILTER_PROG;
+
+ dtype_cmd |= th->fin ?
+ (I40E_FILTER_PROGRAM_DESC_PCMD_REMOVE <<
+ I40E_TXD_FLTR_QW1_PCMD_SHIFT) :
+ (I40E_FILTER_PROGRAM_DESC_PCMD_ADD_UPDATE <<
+ I40E_TXD_FLTR_QW1_PCMD_SHIFT);
+
+ dtype_cmd |= I40E_FILTER_PROGRAM_DESC_DEST_DIRECT_PACKET_QINDEX <<
+ I40E_TXD_FLTR_QW1_DEST_SHIFT;
+
+ dtype_cmd |= I40E_FILTER_PROGRAM_DESC_FD_STATUS_FD_ID <<
+ I40E_TXD_FLTR_QW1_FD_STATUS_SHIFT;
+
+ fdir_desc->qindex_flex_ptype_vsi = cpu_to_le32(flex_ptype);
+ fdir_desc->dtype_cmd_cntindex = cpu_to_le32(dtype_cmd);
+}
+
+#define I40E_TXD_CMD (I40E_TX_DESC_CMD_EOP | I40E_TX_DESC_CMD_RS)
+/**
+ * i40e_tx_prepare_vlan_flags - prepare generic TX VLAN tagging flags for HW
+ * @skb: send buffer
+ * @tx_ring: ring to send buffer on
+ * @flags: the tx flags to be set
+ *
+ * Checks the skb and set up correspondingly several generic transmit flags
+ * related to VLAN tagging for the HW, such as VLAN, DCB, etc.
+ *
+ * Returns error code indicate the frame should be dropped upon error and the
+ * otherwise returns 0 to indicate the flags has been set properly.
+ **/
+static int i40e_tx_prepare_vlan_flags(struct sk_buff *skb,
+ struct i40e_ring *tx_ring,
+ u32 *flags)
+{
+ __be16 protocol = skb->protocol;
+ u32 tx_flags = 0;
+
+ /* if we have a HW VLAN tag being added, default to the HW one */
+ if (vlan_tx_tag_present(skb)) {
+ tx_flags |= vlan_tx_tag_get(skb) << I40E_TX_FLAGS_VLAN_SHIFT;
+ tx_flags |= I40E_TX_FLAGS_HW_VLAN;
+ /* else if it is a SW VLAN, check the next protocol and store the tag */
+ } else if (protocol == __constant_htons(ETH_P_8021Q)) {
+ struct vlan_hdr *vhdr, _vhdr;
+ vhdr = skb_header_pointer(skb, ETH_HLEN, sizeof(_vhdr), &_vhdr);
+ if (!vhdr)
+ return -EINVAL;
+
+ protocol = vhdr->h_vlan_encapsulated_proto;
+ tx_flags |= ntohs(vhdr->h_vlan_TCI) << I40E_TX_FLAGS_VLAN_SHIFT;
+ tx_flags |= I40E_TX_FLAGS_SW_VLAN;
+ }
+
+ /* Insert 802.1p priority into VLAN header */
+ if ((tx_ring->vsi->back->flags & I40E_FLAG_DCB_ENABLED) &&
+ ((tx_flags & (I40E_TX_FLAGS_HW_VLAN | I40E_TX_FLAGS_SW_VLAN)) ||
+ (skb->priority != TC_PRIO_CONTROL))) {
+ tx_flags &= ~I40E_TX_FLAGS_VLAN_PRIO_MASK;
+ tx_flags |= (skb->priority & 0x7) <<
+ I40E_TX_FLAGS_VLAN_PRIO_SHIFT;
+ if (tx_flags & I40E_TX_FLAGS_SW_VLAN) {
+ struct vlan_ethhdr *vhdr;
+ if (skb_header_cloned(skb) &&
+ pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+ return -ENOMEM;
+ vhdr = (struct vlan_ethhdr *)skb->data;
+ vhdr->h_vlan_TCI = htons(tx_flags >>
+ I40E_TX_FLAGS_VLAN_SHIFT);
+ } else {
+ tx_flags |= I40E_TX_FLAGS_HW_VLAN;
+ }
+ }
+ *flags = tx_flags;
+ return 0;
+}
+
+/**
+ * i40e_tx_csum - is checksum offload requested
+ * @tx_ring: ptr to the ring to send
+ * @skb: ptr to the skb we're sending
+ * @tx_flags: the collected send information
+ * @protocol: the send protocol
+ *
+ * Returns true if checksum offload is requested
+ **/
+static bool i40e_tx_csum(struct i40e_ring *tx_ring, struct sk_buff *skb,
+ u32 tx_flags, __be16 protocol)
+{
+ if ((skb->ip_summed != CHECKSUM_PARTIAL) &&
+ !(tx_flags & I40E_TX_FLAGS_TXSW)) {
+ if (!(tx_flags & I40E_TX_FLAGS_HW_VLAN))
+ return false;
+ }
+
+ return skb->ip_summed == CHECKSUM_PARTIAL;
+}
+
+/**
+ * i40e_tso - set up the tso context descriptor
+ * @tx_ring: ptr to the ring to send
+ * @skb: ptr to the skb we're sending
+ * @tx_flags: the collected send information
+ * @protocol: the send protocol
+ * @hdr_len: ptr to the size of the packet header
+ * @cd_tunneling: ptr to context descriptor bits
+ *
+ * Returns 0 if no TSO can happen, 1 if tso is going, or error
+ **/
+static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
+ u32 tx_flags, __be16 protocol, u8 *hdr_len,
+ u64 *cd_type_cmd_tso_mss, u32 *cd_tunneling)
+{
+ u32 cd_cmd, cd_tso_len, cd_mss;
+ struct tcphdr *tcph;
+ struct iphdr *iph;
+ u32 l4len;
+ int err;
+ struct ipv6hdr *ipv6h;
+
+ if (!skb_is_gso(skb))
+ return 0;
+
+ if (skb_header_cloned(skb)) {
+ err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
+ if (err)
+ return err;
+ }
+
+ if (protocol == __constant_htons(ETH_P_IP)) {
+ iph = skb->encapsulation ? inner_ip_hdr(skb) : ip_hdr(skb);
+ tcph = skb->encapsulation ? inner_tcp_hdr(skb) : tcp_hdr(skb);
+ iph->tot_len = 0;
+ iph->check = 0;
+ tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
+ 0, IPPROTO_TCP, 0);
+ } else if (skb_is_gso_v6(skb)) {
+
+ ipv6h = skb->encapsulation ? inner_ipv6_hdr(skb)
+ : ipv6_hdr(skb);
+ tcph = skb->encapsulation ? inner_tcp_hdr(skb) : tcp_hdr(skb);
+ ipv6h->payload_len = 0;
+ tcph->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr,
+ 0, IPPROTO_TCP, 0);
+ }
+
+ l4len = skb->encapsulation ? inner_tcp_hdrlen(skb) : tcp_hdrlen(skb);
+ *hdr_len = (skb->encapsulation
+ ? (skb_inner_transport_header(skb) - skb->data)
+ : skb_transport_offset(skb)) + l4len;
+
+ /* find the field values */
+ cd_cmd = I40E_TX_CTX_DESC_TSO;
+ cd_tso_len = skb->len - *hdr_len;
+ cd_mss = skb_shinfo(skb)->gso_size;
+ *cd_type_cmd_tso_mss |= ((u64)cd_cmd << I40E_TXD_CTX_QW1_CMD_SHIFT)
+ | ((u64)cd_tso_len
+ << I40E_TXD_CTX_QW1_TSO_LEN_SHIFT)
+ | ((u64)cd_mss << I40E_TXD_CTX_QW1_MSS_SHIFT);
+ return 1;
+}
+
+/**
+ * i40e_tx_enable_csum - Enable Tx checksum offloads
+ * @skb: send buffer
+ * @tx_flags: Tx flags currently set
+ * @td_cmd: Tx descriptor command bits to set
+ * @td_offset: Tx descriptor header offsets to set
+ * @cd_tunneling: ptr to context desc bits
+ **/
+static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
+ u32 *td_cmd, u32 *td_offset,
+ struct i40e_ring *tx_ring,
+ u32 *cd_tunneling)
+{
+ struct ipv6hdr *this_ipv6_hdr;
+ unsigned int this_tcp_hdrlen;
+ struct iphdr *this_ip_hdr;
+ u32 network_hdr_len;
+ u8 l4_hdr = 0;
+
+ if (skb->encapsulation) {
+ network_hdr_len = skb_inner_network_header_len(skb);
+ this_ip_hdr = inner_ip_hdr(skb);
+ this_ipv6_hdr = inner_ipv6_hdr(skb);
+ this_tcp_hdrlen = inner_tcp_hdrlen(skb);
+
+ if (tx_flags & I40E_TX_FLAGS_IPV4) {
+
+ if (tx_flags & I40E_TX_FLAGS_TSO) {
+ *cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV4;
+ ip_hdr(skb)->check = 0;
+ } else {
+ *cd_tunneling |=
+ I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM;
+ }
+ } else if (tx_flags & I40E_TX_FLAGS_IPV6) {
+ if (tx_flags & I40E_TX_FLAGS_TSO) {
+ *cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV6;
+ ip_hdr(skb)->check = 0;
+ } else {
+ *cd_tunneling |=
+ I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM;
+ }
+ }
+
+ /* Now set the ctx descriptor fields */
+ *cd_tunneling |= (skb_network_header_len(skb) >> 2) <<
+ I40E_TXD_CTX_QW0_EXT_IPLEN_SHIFT |
+ I40E_TXD_CTX_UDP_TUNNELING |
+ ((skb_inner_network_offset(skb) -
+ skb_transport_offset(skb)) >> 1) <<
+ I40E_TXD_CTX_QW0_NATLEN_SHIFT;
+
+ } else {
+ network_hdr_len = skb_network_header_len(skb);
+ this_ip_hdr = ip_hdr(skb);
+ this_ipv6_hdr = ipv6_hdr(skb);
+ this_tcp_hdrlen = tcp_hdrlen(skb);
+ }
+
+ /* Enable IP checksum offloads */
+ if (tx_flags & I40E_TX_FLAGS_IPV4) {
+ l4_hdr = this_ip_hdr->protocol;
+ /* the stack computes the IP header already, the only time we
+ * need the hardware to recompute it is in the case of TSO.
+ */
+ if (tx_flags & I40E_TX_FLAGS_TSO) {
+ *td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV4_CSUM;
+ this_ip_hdr->check = 0;
+ } else {
+ *td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV4;
+ }
+ /* Now set the td_offset for IP header length */
+ *td_offset = (network_hdr_len >> 2) <<
+ I40E_TX_DESC_LENGTH_IPLEN_SHIFT;
+ } else if (tx_flags & I40E_TX_FLAGS_IPV6) {
+ l4_hdr = this_ipv6_hdr->nexthdr;
+ *td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV6;
+ /* Now set the td_offset for IP header length */
+ *td_offset = (network_hdr_len >> 2) <<
+ I40E_TX_DESC_LENGTH_IPLEN_SHIFT;
+ }
+ /* words in MACLEN + dwords in IPLEN + dwords in L4Len */
+ *td_offset |= (skb_network_offset(skb) >> 1) <<
+ I40E_TX_DESC_LENGTH_MACLEN_SHIFT;
+
+ /* Enable L4 checksum offloads */
+ switch (l4_hdr) {
+ case IPPROTO_TCP:
+ /* enable checksum offloads */
+ *td_cmd |= I40E_TX_DESC_CMD_L4T_EOFT_TCP;
+ *td_offset |= (this_tcp_hdrlen >> 2) <<
+ I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
+ break;
+ case IPPROTO_SCTP:
+ /* enable SCTP checksum offload */
+ *td_cmd |= I40E_TX_DESC_CMD_L4T_EOFT_SCTP;
+ *td_offset |= (sizeof(struct sctphdr) >> 2) <<
+ I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
+ break;
+ case IPPROTO_UDP:
+ /* enable UDP checksum offload */
+ *td_cmd |= I40E_TX_DESC_CMD_L4T_EOFT_UDP;
+ *td_offset |= (sizeof(struct udphdr) >> 2) <<
+ I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
+ break;
+ default:
+ break;
+ }
+}
+
+/**
+ * i40e_create_tx_ctx Build the Tx context descriptor
+ * @tx_ring: ring to create the descriptor on
+ * @cd_type_cmd_tso_mss: Quad Word 1
+ * @cd_tunneling: Quad Word 0 - bits 0-31
+ * @cd_l2tag2: Quad Word 0 - bits 32-63
+ **/
+static void i40e_create_tx_ctx(struct i40e_ring *tx_ring,
+ const u64 cd_type_cmd_tso_mss,
+ const u32 cd_tunneling, const u32 cd_l2tag2)
+{
+ struct i40e_tx_context_desc *context_desc;
+
+ if (!cd_type_cmd_tso_mss && !cd_tunneling && !cd_l2tag2)
+ return;
+
+ /* grab the next descriptor */
+ context_desc = I40E_TX_CTXTDESC(tx_ring, tx_ring->next_to_use);
+ tx_ring->next_to_use++;
+ if (tx_ring->next_to_use == tx_ring->count)
+ tx_ring->next_to_use = 0;
+
+ /* cpu_to_le32 and assign to struct fields */
+ context_desc->tunneling_params = cpu_to_le32(cd_tunneling);
+ context_desc->l2tag2 = cpu_to_le16(cd_l2tag2);
+ context_desc->type_cmd_tso_mss = cpu_to_le64(cd_type_cmd_tso_mss);
+}
+
+/**
+ * i40e_tx_map - Build the Tx descriptor
+ * @tx_ring: ring to send buffer on
+ * @skb: send buffer
+ * @first: first buffer info buffer to use
+ * @tx_flags: collected send information
+ * @hdr_len: size of the packet header
+ * @td_cmd: the command field in the descriptor
+ * @td_offset: offset for checksum or crc
+ **/
+static void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
+ struct i40e_tx_buffer *first, u32 tx_flags,
+ const u8 hdr_len, u32 td_cmd, u32 td_offset)
+{
+ struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];
+ unsigned int data_len = skb->data_len;
+ unsigned int size = skb_headlen(skb);
+ struct device *dev = tx_ring->dev;
+ u32 paylen = skb->len - hdr_len;
+ u16 i = tx_ring->next_to_use;
+ struct i40e_tx_buffer *tx_bi;
+ struct i40e_tx_desc *tx_desc;
+ u32 buf_offset = 0;
+ u32 td_tag = 0;
+ dma_addr_t dma;
+ u16 gso_segs;
+
+ dma = dma_map_single(dev, skb->data, size, DMA_TO_DEVICE);
+ if (dma_mapping_error(dev, dma))
+ goto dma_error;
+
+ if (tx_flags & I40E_TX_FLAGS_HW_VLAN) {
+ td_cmd |= I40E_TX_DESC_CMD_IL2TAG1;
+ td_tag = (tx_flags & I40E_TX_FLAGS_VLAN_MASK) >>
+ I40E_TX_FLAGS_VLAN_SHIFT;
+ }
+
+ tx_desc = I40E_TX_DESC(tx_ring, i);
+ for (;;) {
+ while (size > I40E_MAX_DATA_PER_TXD) {
+ tx_desc->buffer_addr = cpu_to_le64(dma + buf_offset);
+ tx_desc->cmd_type_offset_bsz =
+ build_ctob(td_cmd, td_offset,
+ I40E_MAX_DATA_PER_TXD, td_tag);
+
+ buf_offset += I40E_MAX_DATA_PER_TXD;
+ size -= I40E_MAX_DATA_PER_TXD;
+
+ tx_desc++;
+ i++;
+ if (i == tx_ring->count) {
+ tx_desc = I40E_TX_DESC(tx_ring, 0);
+ i = 0;
+ }
+ }
+
+ tx_bi = &tx_ring->tx_bi[i];
+ tx_bi->length = buf_offset + size;
+ tx_bi->tx_flags = tx_flags;
+ tx_bi->dma = dma;
+
+ tx_desc->buffer_addr = cpu_to_le64(dma + buf_offset);
+ tx_desc->cmd_type_offset_bsz = build_ctob(td_cmd, td_offset,
+ size, td_tag);
+
+ if (likely(!data_len))
+ break;
+
+ size = skb_frag_size(frag);
+ data_len -= size;
+ buf_offset = 0;
+ tx_flags |= I40E_TX_FLAGS_MAPPED_AS_PAGE;
+
+ dma = skb_frag_dma_map(dev, frag, 0, size, DMA_TO_DEVICE);
+ if (dma_mapping_error(dev, dma))
+ goto dma_error;
+
+ tx_desc++;
+ i++;
+ if (i == tx_ring->count) {
+ tx_desc = I40E_TX_DESC(tx_ring, 0);
+ i = 0;
+ }
+
+ frag++;
+ }
+
+ tx_desc->cmd_type_offset_bsz |=
+ cpu_to_le64((u64)I40E_TXD_CMD << I40E_TXD_QW1_CMD_SHIFT);
+
+ i++;
+ if (i == tx_ring->count)
+ i = 0;
+
+ tx_ring->next_to_use = i;
+
+ if (tx_flags & (I40E_TX_FLAGS_TSO | I40E_TX_FLAGS_FSO))
+ gso_segs = skb_shinfo(skb)->gso_segs;
+ else
+ gso_segs = 1;
+
+ /* multiply data chunks by size of headers */
+ tx_bi->bytecount = paylen + (gso_segs * hdr_len);
+ tx_bi->gso_segs = gso_segs;
+ tx_bi->skb = skb;
+
+ /* set the timestamp and next to watch values */
+ first->time_stamp = jiffies;
+ first->next_to_watch = tx_desc;
+
+ /* Force memory writes to complete before letting h/w
+ * know there are new descriptors to fetch. (Only
+ * applicable for weak-ordered memory model archs,
+ * such as IA-64).
+ */
+ wmb();
+
+ writel(i, tx_ring->tail);
+ return;
+
+dma_error:
+ dev_info(dev, "TX DMA map failed\n");
+
+ /* clear dma mappings for failed tx_bi map */
+ for (;;) {
+ tx_bi = &tx_ring->tx_bi[i];
+ i40e_unmap_tx_resource(tx_ring, tx_bi);
+ if (tx_bi == first)
+ break;
+ if (i == 0)
+ i = tx_ring->count;
+ i--;
+ }
+
+ dev_kfree_skb_any(skb);
+
+ tx_ring->next_to_use = i;
+}
+
+/**
+ * __i40e_maybe_stop_tx - 2nd level check for tx stop conditions
+ * @tx_ring: the ring to be checked
+ * @size: the size buffer we want to assure is available
+ *
+ * Returns -EBUSY if a stop is needed, else 0
+ **/
+static inline int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
+{
+ netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);
+ smp_mb();
+
+ /* Check again in a case another CPU has just made room available. */
+ if (likely(I40E_DESC_UNUSED(tx_ring) < size))
+ return -EBUSY;
+
+ /* A reprieve! - use start_queue because it doesn't call schedule */
+ netif_start_subqueue(tx_ring->netdev, tx_ring->queue_index);
+ ++tx_ring->tx_stats.restart_queue;
+ return 0;
+}
+
+/**
+ * i40e_maybe_stop_tx - 1st level check for tx stop conditions
+ * @tx_ring: the ring to be checked
+ * @size: the size buffer we want to assure is available
+ *
+ * Returns 0 if stop is not needed
+ **/
+static int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
+{
+ if (likely(I40E_DESC_UNUSED(tx_ring) >= size))
+ return 0;
+ return __i40e_maybe_stop_tx(tx_ring, size);
+}
+
+/**
+ * i40e_xmit_descriptor_count - calculate number of tx descriptors needed
+ * @skb: send buffer
+ * @tx_ring: ring to send buffer on
+ *
+ * Returns number of data descriptors needed for this skb. Returns 0 to indicate
+ * there is not enough descriptors available in this ring since we need at least
+ * one descriptor.
+ **/
+static int i40e_xmit_descriptor_count(struct sk_buff *skb,
+ struct i40e_ring *tx_ring)
+{
+#if PAGE_SIZE > I40E_MAX_DATA_PER_TXD
+ unsigned int f;
+#endif
+ int count = 0;
+
+ /* need: 1 descriptor per page * PAGE_SIZE/I40E_MAX_DATA_PER_TXD,
+ * + 1 desc for skb_head_len/I40E_MAX_DATA_PER_TXD,
+ * + 2 desc gap to keep tail from touching head,
+ * + 1 desc for context descriptor,
+ * otherwise try next time
+ */
+#if PAGE_SIZE > I40E_MAX_DATA_PER_TXD
+ for (f = 0; f < skb_shinfo(skb)->nr_frags; f++)
+ count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size);
+#else
+ count += skb_shinfo(skb)->nr_frags;
+#endif
+ count += TXD_USE_COUNT(skb_headlen(skb));
+ if (i40e_maybe_stop_tx(tx_ring, count + 3)) {
+ tx_ring->tx_stats.tx_busy++;
+ return 0;
+ }
+ return count;
+}
+
+/**
+ * i40e_xmit_frame_ring - Sends buffer on Tx ring
+ * @skb: send buffer
+ * @tx_ring: ring to send buffer on
+ *
+ * Returns NETDEV_TX_OK if sent, else an error code
+ **/
+static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
+ struct i40e_ring *tx_ring)
+{
+ u64 cd_type_cmd_tso_mss = I40E_TX_DESC_DTYPE_CONTEXT;
+ u32 cd_tunneling = 0, cd_l2tag2 = 0;
+ struct i40e_tx_buffer *first;
+ u32 td_offset = 0;
+ u32 tx_flags = 0;
+ __be16 protocol;
+ u32 td_cmd = 0;
+ u8 hdr_len = 0;
+ int tso;
+ if (0 == i40e_xmit_descriptor_count(skb, tx_ring))
+ return NETDEV_TX_BUSY;
+
+ /* prepare the xmit flags */
+ if (i40e_tx_prepare_vlan_flags(skb, tx_ring, &tx_flags))
+ goto out_drop;
+
+ /* obtain protocol of skb */
+ protocol = skb->protocol;
+
+ /* record the location of the first descriptor for this packet */
+ first = &tx_ring->tx_bi[tx_ring->next_to_use];
+
+ /* setup IPv4/IPv6 offloads */
+ if (protocol == __constant_htons(ETH_P_IP))
+ tx_flags |= I40E_TX_FLAGS_IPV4;
+ else if (protocol == __constant_htons(ETH_P_IPV6))
+ tx_flags |= I40E_TX_FLAGS_IPV6;
+
+ tso = i40e_tso(tx_ring, skb, tx_flags, protocol, &hdr_len,
+ &cd_type_cmd_tso_mss, &cd_tunneling);
+
+ if (tso < 0)
+ goto out_drop;
+ else if (tso)
+ tx_flags |= I40E_TX_FLAGS_TSO;
+
+ skb_tx_timestamp(skb);
+
+ /* Always offload the checksum, since it's in the data descriptor */
+ if (i40e_tx_csum(tx_ring, skb, tx_flags, protocol))
+ tx_flags |= I40E_TX_FLAGS_CSUM;
+
+ /* always enable offload insertion */
+ td_cmd |= I40E_TX_DESC_CMD_ICRC;
+
+ if (tx_flags & I40E_TX_FLAGS_CSUM)
+ i40e_tx_enable_csum(skb, tx_flags, &td_cmd, &td_offset,
+ tx_ring, &cd_tunneling);
+
+ i40e_create_tx_ctx(tx_ring, cd_type_cmd_tso_mss,
+ cd_tunneling, cd_l2tag2);
+
+ /* Add Flow Director ATR if it's enabled.
+ *
+ * NOTE: this must always be directly before the data descriptor.
+ */
+ i40e_atr(tx_ring, skb, tx_flags, protocol);
+
+ i40e_tx_map(tx_ring, skb, first, tx_flags, hdr_len,
+ td_cmd, td_offset);
+
+ i40e_maybe_stop_tx(tx_ring, DESC_NEEDED);
+
+ return NETDEV_TX_OK;
+
+out_drop:
+ dev_kfree_skb_any(skb);
+ return NETDEV_TX_OK;
+}
+
+/**
+ * i40e_lan_xmit_frame - Selects the correct VSI and Tx queue to send buffer
+ * @skb: send buffer
+ * @netdev: network interface device structure
+ *
+ * Returns NETDEV_TX_OK if sent, else an error code
+ **/
+netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+ struct i40e_ring *tx_ring = &vsi->tx_rings[skb->queue_mapping];
+
+ /* hardware can't handle really short frames, hardware padding works
+ * beyond this point
+ */
+ if (unlikely(skb->len < I40E_MIN_TX_LEN)) {
+ if (skb_pad(skb, I40E_MIN_TX_LEN - skb->len))
+ return NETDEV_TX_OK;
+ skb->len = I40E_MIN_TX_LEN;
+ skb_set_tail_pointer(skb, I40E_MIN_TX_LEN);
+ }
+
+ return i40e_xmit_frame_ring(skb, tx_ring);
+}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
new file mode 100644
index 0000000..b1d7722
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -0,0 +1,259 @@
+/*******************************************************************************
+ *
+ * Intel Ethernet Controller XL710 Family Linux Driver
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ ******************************************************************************/
+
+/* Interrupt Throttling and Rate Limiting (storm control) Goodies */
+
+#define I40E_MAX_ITR 0x07FF
+#define I40E_MIN_ITR 0x0001
+#define I40E_ITR_USEC_RESOLUTION 2
+#define I40E_MAX_IRATE 0x03F
+#define I40E_MIN_IRATE 0x001
+#define I40E_IRATE_USEC_RESOLUTION 4
+#define I40E_ITR_100K 0x0005
+#define I40E_ITR_20K 0x0019
+#define I40E_ITR_8K 0x003E
+#define I40E_ITR_4K 0x007A
+#define I40E_ITR_RX_DEF I40E_ITR_8K
+#define I40E_ITR_TX_DEF I40E_ITR_4K
+#define I40E_ITR_DYNAMIC 0x8000 /* use top bit as a flag */
+#define I40E_MIN_INT_RATE 250 /* ~= 1000000 / (I40E_MAX_ITR * 2) */
+#define I40E_MAX_INT_RATE 500000 /* == 1000000 / (I40E_MIN_ITR * 2) */
+#define I40E_DEFAULT_IRQ_WORK 256
+#define ITR_TO_REG(setting) ((setting & ~I40E_ITR_DYNAMIC) >> 1)
+#define ITR_IS_DYNAMIC(setting) (!!(setting & I40E_ITR_DYNAMIC))
+#define ITR_REG_TO_USEC(itr_reg) (itr_reg << 1)
+
+#define I40E_QUEUE_END_OF_LIST 0x7FF
+
+#define I40E_ITR_NONE 3
+#define I40E_RX_ITR 0
+#define I40E_TX_ITR 1
+#define I40E_PE_ITR 2
+/* Supported Rx Buffer Sizes */
+#define I40E_RXBUFFER_512 512 /* Used for packet split */
+#define I40E_RXBUFFER_2048 2048
+#define I40E_RXBUFFER_3072 3072 /* For FCoE MTU of 2158 */
+#define I40E_RXBUFFER_4096 4096
+#define I40E_RXBUFFER_8192 8192
+#define I40E_MAX_RXBUFFER 9728 /* largest size for single descriptor */
+
+/* NOTE: netdev_alloc_skb reserves up to 64 bytes, NET_IP_ALIGN means we
+ * reserve 2 more, and skb_shared_info adds an additional 384 bytes more,
+ * this adds up to 512 bytes of extra data meaning the smallest allocation
+ * we could have is 1K.
+ * i.e. RXBUFFER_512 --> size-1024 slab
+ */
+#define I40E_RX_HDR_SIZE I40E_RXBUFFER_512
+
+/* How many Rx Buffers do we bundle into one write to the hardware ? */
+#define I40E_RX_BUFFER_WRITE 16 /* Must be power of 2 */
+#define I40E_RX_NEXT_DESC(r, i, n) \
+ do { \
+ (i)++; \
+ if ((i) == (r)->count) \
+ i = 0; \
+ (n) = I40E_RX_DESC((r), (i)); \
+ } while (0)
+
+#define I40E_RX_NEXT_DESC_PREFETCH(r, i, n) \
+ do { \
+ I40E_RX_NEXT_DESC((r), (i), (n)); \
+ prefetch((n)); \
+ } while (0)
+
+#define i40e_rx_desc i40e_32byte_rx_desc
+
+#define I40E_MIN_TX_LEN 17
+#define I40E_MAX_DATA_PER_TXD 16383 /* aka 16kB - 1 */
+
+/* Tx Descriptors needed, worst case */
+#define TXD_USE_COUNT(S) DIV_ROUND_UP((S), I40E_MAX_DATA_PER_TXD)
+#define DESC_NEEDED ((MAX_SKB_FRAGS * TXD_USE_COUNT(PAGE_SIZE)) + 4)
+
+#define I40E_TX_FLAGS_CSUM (u32)(1)
+#define I40E_TX_FLAGS_HW_VLAN (u32)(1 << 1)
+#define I40E_TX_FLAGS_SW_VLAN (u32)(1 << 2)
+#define I40E_TX_FLAGS_TSO (u32)(1 << 3)
+#define I40E_TX_FLAGS_IPV4 (u32)(1 << 4)
+#define I40E_TX_FLAGS_IPV6 (u32)(1 << 5)
+#define I40E_TX_FLAGS_FCCRC (u32)(1 << 6)
+#define I40E_TX_FLAGS_FSO (u32)(1 << 7)
+#define I40E_TX_FLAGS_TXSW (u32)(1 << 8)
+#define I40E_TX_FLAGS_MAPPED_AS_PAGE (u32)(1 << 9)
+#define I40E_TX_FLAGS_VLAN_MASK 0xffff0000
+#define I40E_TX_FLAGS_VLAN_PRIO_MASK 0xe0000000
+#define I40E_TX_FLAGS_VLAN_PRIO_SHIFT 29
+#define I40E_TX_FLAGS_VLAN_SHIFT 16
+
+struct i40e_tx_buffer {
+ struct sk_buff *skb;
+ dma_addr_t dma;
+ unsigned long time_stamp;
+ u16 length;
+ u32 tx_flags;
+ struct i40e_tx_desc *next_to_watch;
+ unsigned int bytecount;
+ u16 gso_segs;
+ u8 mapped_as_page;
+};
+
+struct i40e_rx_buffer {
+ struct sk_buff *skb;
+ dma_addr_t dma;
+ struct page *page;
+ dma_addr_t page_dma;
+ unsigned int page_offset;
+};
+
+struct i40e_tx_queue_stats {
+ u64 packets;
+ u64 bytes;
+ u64 restart_queue;
+ u64 tx_busy;
+ u64 completed;
+ u64 tx_done_old;
+};
+
+struct i40e_rx_queue_stats {
+ u64 packets;
+ u64 bytes;
+ u64 non_eop_descs;
+ u64 alloc_rx_page_failed;
+ u64 alloc_rx_buff_failed;
+};
+
+enum i40e_ring_state_t {
+ __I40E_TX_FDIR_INIT_DONE,
+ __I40E_TX_XPS_INIT_DONE,
+ __I40E_TX_DETECT_HANG,
+ __I40E_HANG_CHECK_ARMED,
+ __I40E_RX_PS_ENABLED,
+ __I40E_RX_LRO_ENABLED,
+ __I40E_RX_16BYTE_DESC_ENABLED,
+};
+
+#define ring_is_ps_enabled(ring) \
+ test_bit(__I40E_RX_PS_ENABLED, &(ring)->state)
+#define set_ring_ps_enabled(ring) \
+ set_bit(__I40E_RX_PS_ENABLED, &(ring)->state)
+#define clear_ring_ps_enabled(ring) \
+ clear_bit(__I40E_RX_PS_ENABLED, &(ring)->state)
+#define check_for_tx_hang(ring) \
+ test_bit(__I40E_TX_DETECT_HANG, &(ring)->state)
+#define set_check_for_tx_hang(ring) \
+ set_bit(__I40E_TX_DETECT_HANG, &(ring)->state)
+#define clear_check_for_tx_hang(ring) \
+ clear_bit(__I40E_TX_DETECT_HANG, &(ring)->state)
+#define ring_is_lro_enabled(ring) \
+ test_bit(__I40E_RX_LRO_ENABLED, &(ring)->state)
+#define set_ring_lro_enabled(ring) \
+ set_bit(__I40E_RX_LRO_ENABLED, &(ring)->state)
+#define clear_ring_lro_enabled(ring) \
+ clear_bit(__I40E_RX_LRO_ENABLED, &(ring)->state)
+#define ring_is_16byte_desc_enabled(ring) \
+ test_bit(__I40E_RX_16BYTE_DESC_ENABLED, &(ring)->state)
+#define set_ring_16byte_desc_enabled(ring) \
+ set_bit(__I40E_RX_16BYTE_DESC_ENABLED, &(ring)->state)
+#define clear_ring_16byte_desc_enabled(ring) \
+ clear_bit(__I40E_RX_16BYTE_DESC_ENABLED, &(ring)->state)
+
+/* struct that defines a descriptor ring, associated with a VSI */
+struct i40e_ring {
+ void *desc; /* Descriptor ring memory */
+ struct device *dev; /* Used for DMA mapping */
+ struct net_device *netdev; /* netdev ring maps to */
+ union {
+ struct i40e_tx_buffer *tx_bi;
+ struct i40e_rx_buffer *rx_bi;
+ };
+ unsigned long state;
+ u16 queue_index; /* Queue number of ring */
+ u8 dcb_tc; /* Traffic class of ring */
+ u8 __iomem *tail;
+
+ u16 count; /* Number of descriptors */
+ u16 reg_idx; /* HW register index of the ring */
+ u16 rx_hdr_len;
+ u16 rx_buf_len;
+ u8 dtype;
+#define I40E_RX_DTYPE_NO_SPLIT 0
+#define I40E_RX_DTYPE_SPLIT_ALWAYS 1
+#define I40E_RX_DTYPE_HEADER_SPLIT 2
+ u8 hsplit;
+#define I40E_RX_SPLIT_L2 0x1
+#define I40E_RX_SPLIT_IP 0x2
+#define I40E_RX_SPLIT_TCP_UDP 0x4
+#define I40E_RX_SPLIT_SCTP 0x8
+
+ /* used in interrupt processing */
+ u16 next_to_use;
+ u16 next_to_clean;
+
+ u8 atr_sample_rate;
+ u8 atr_count;
+
+ bool ring_active; /* is ring online or not */
+
+ /* stats structs */
+ union {
+ struct i40e_tx_queue_stats tx_stats;
+ struct i40e_rx_queue_stats rx_stats;
+ };
+
+ unsigned int size; /* length of descriptor ring in bytes */
+ dma_addr_t dma; /* physical address of ring */
+
+ struct i40e_vsi *vsi; /* Backreference to associated VSI */
+ struct i40e_q_vector *q_vector; /* Backreference to associated vector */
+} ____cacheline_internodealigned_in_smp;
+
+enum i40e_latency_range {
+ I40E_LOWEST_LATENCY = 0,
+ I40E_LOW_LATENCY = 1,
+ I40E_BULK_LATENCY = 2,
+};
+
+struct i40e_ring_container {
+#define I40E_MAX_RINGPAIR_PER_VECTOR 8
+ /* array of pointers to rings */
+ struct i40e_ring *ring[I40E_MAX_RINGPAIR_PER_VECTOR];
+ unsigned int total_bytes; /* total bytes processed this int */
+ unsigned int total_packets; /* total packets processed this int */
+ u16 count;
+ enum i40e_latency_range latency_range;
+ u16 itr;
+};
+
+void i40e_alloc_rx_buffers(struct i40e_ring *rxr, u16 cleaned_count);
+netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev);
+void i40e_clean_tx_ring(struct i40e_ring *tx_ring);
+void i40e_clean_rx_ring(struct i40e_ring *rx_ring);
+int i40e_setup_tx_descriptors(struct i40e_ring *tx_ring);
+int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring);
+void i40e_free_tx_resources(struct i40e_ring *tx_ring);
+void i40e_free_rx_resources(struct i40e_ring *rx_ring);
+int i40e_napi_poll(struct napi_struct *napi, int budget);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
new file mode 100644
index 0000000..f3f22b2
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -0,0 +1,1154 @@
+/*******************************************************************************
+ *
+ * Intel Ethernet Controller XL710 Family Linux Driver
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ ******************************************************************************/
+
+#ifndef _I40E_TYPE_H_
+#define _I40E_TYPE_H_
+
+#include "i40e_status.h"
+#include "i40e_osdep.h"
+#include "i40e_register.h"
+#include "i40e_adminq.h"
+#include "i40e_hmc.h"
+#include "i40e_lan_hmc.h"
+
+/* Device IDs */
+#define I40E_SFP_XL710_DEVICE_ID 0x1572
+#define I40E_SFP_X710_DEVICE_ID 0x1573
+#define I40E_QEMU_DEVICE_ID 0x1574
+#define I40E_KX_A_DEVICE_ID 0x157F
+#define I40E_KX_B_DEVICE_ID 0x1580
+#define I40E_KX_C_DEVICE_ID 0x1581
+#define I40E_KX_D_DEVICE_ID 0x1582
+#define I40E_QSFP_A_DEVICE_ID 0x1583
+#define I40E_QSFP_B_DEVICE_ID 0x1584
+#define I40E_QSFP_C_DEVICE_ID 0x1585
+#define I40E_VF_DEVICE_ID 0x154C
+#define I40E_VF_HV_DEVICE_ID 0x1571
+
+#define I40E_FW_API_VERSION_MAJOR 0x0001
+#define I40E_FW_API_VERSION_MINOR 0x0000
+
+#define I40E_MAX_VSI_QP 16
+#define I40E_MAX_VF_VSI 3
+#define I40E_MAX_CHAINED_RX_BUFFERS 5
+
+/* Max default timeout in ms, */
+#define I40E_MAX_NVM_TIMEOUT 18000
+
+/* Check whether address is multicast. This is little-endian specific check.*/
+#define I40E_IS_MULTICAST(address) \
+ (bool)(((u8 *)(address))[0] & ((u8)0x01))
+
+/* Check whether an address is broadcast. */
+#define I40E_IS_BROADCAST(address) \
+ ((((u8 *)(address))[0] == ((u8)0xff)) && \
+ (((u8 *)(address))[1] == ((u8)0xff)))
+
+/* Switch from mc to the 2usec global time (this is the GTIME resolution) */
+#define I40E_MS_TO_GTIME(time) (((time) * 1000) / 2)
+
+/* forward declaration */
+struct i40e_hw;
+typedef void (*I40E_ADMINQ_CALLBACK)(struct i40e_hw *, struct i40e_aq_desc *);
+
+#define I40E_ETH_LENGTH_OF_ADDRESS 6
+
+/* Data type manipulation macros. */
+
+#define I40E_DESC_UNUSED(R) \
+ ((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \
+ (R)->next_to_clean - (R)->next_to_use - 1)
+
+/* bitfields for Tx queue mapping in QTX_CTL */
+#define I40E_QTX_CTL_VF_QUEUE 0x0
+#define I40E_QTX_CTL_PF_QUEUE 0x2
+
+/* debug masks */
+enum i40e_debug_mask {
+ I40E_DEBUG_INIT = 0x00000001,
+ I40E_DEBUG_RELEASE = 0x00000002,
+
+ I40E_DEBUG_LINK = 0x00000010,
+ I40E_DEBUG_PHY = 0x00000020,
+ I40E_DEBUG_HMC = 0x00000040,
+ I40E_DEBUG_NVM = 0x00000080,
+ I40E_DEBUG_LAN = 0x00000100,
+ I40E_DEBUG_FLOW = 0x00000200,
+ I40E_DEBUG_DCB = 0x00000400,
+ I40E_DEBUG_DIAG = 0x00000800,
+
+ I40E_DEBUG_AQ_MESSAGE = 0x01000000, /* for i40e_debug() */
+ I40E_DEBUG_AQ_DESCRIPTOR = 0x02000000,
+ I40E_DEBUG_AQ_DESC_BUFFER = 0x04000000,
+ I40E_DEBUG_AQ_COMMAND = 0x06000000, /* for i40e_debug_aq() */
+ I40E_DEBUG_AQ = 0x0F000000,
+
+ I40E_DEBUG_USER = 0xF0000000,
+
+ I40E_DEBUG_ALL = 0xFFFFFFFF
+};
+
+/* These are structs for managing the hardware information and the operations.
+ * The structures of function pointers are filled out at init time when we
+ * know for sure exactly which hardware we're working with. This gives us the
+ * flexibility of using the same main driver code but adapting to slightly
+ * different hardware needs as new parts are developed. For this architecture,
+ * the Firmware and AdminQ are intended to insulate the driver from most of the
+ * future changes, but these structures will also do part of the job.
+ */
+enum i40e_mac_type {
+ I40E_MAC_UNKNOWN = 0,
+ I40E_MAC_X710,
+ I40E_MAC_XL710,
+ I40E_MAC_VF,
+ I40E_MAC_GENERIC,
+};
+
+enum i40e_media_type {
+ I40E_MEDIA_TYPE_UNKNOWN = 0,
+ I40E_MEDIA_TYPE_FIBER,
+ I40E_MEDIA_TYPE_BASET,
+ I40E_MEDIA_TYPE_BACKPLANE,
+ I40E_MEDIA_TYPE_CX4,
+ I40E_MEDIA_TYPE_VIRTUAL
+};
+
+enum i40e_fc_mode {
+ I40E_FC_NONE = 0,
+ I40E_FC_RX_PAUSE,
+ I40E_FC_TX_PAUSE,
+ I40E_FC_FULL,
+ I40E_FC_PFC,
+ I40E_FC_DEFAULT
+};
+
+enum i40e_vsi_type {
+ I40E_VSI_MAIN = 0,
+ I40E_VSI_VMDQ1,
+ I40E_VSI_VMDQ2,
+ I40E_VSI_CTRL,
+ I40E_VSI_FCOE,
+ I40E_VSI_MIRROR,
+ I40E_VSI_SRIOV,
+ I40E_VSI_FDIR,
+ I40E_VSI_TYPE_UNKNOWN
+};
+
+enum i40e_queue_type {
+ I40E_QUEUE_TYPE_RX = 0,
+ I40E_QUEUE_TYPE_TX,
+ I40E_QUEUE_TYPE_PE_CEQ,
+ I40E_QUEUE_TYPE_UNKNOWN
+};
+
+struct i40e_link_status {
+ enum i40e_aq_phy_type phy_type;
+ enum i40e_aq_link_speed link_speed;
+ u8 link_info;
+ u8 an_info;
+ u8 ext_info;
+ /* is Link Status Event notification to SW enabled */
+ bool lse_enable;
+};
+
+struct i40e_phy_info {
+ struct i40e_link_status link_info;
+ struct i40e_link_status link_info_old;
+ u32 autoneg_advertised;
+ u32 phy_id;
+ u32 module_type;
+ bool get_link_info;
+ enum i40e_media_type media_type;
+};
+
+#define I40E_HW_CAP_MAX_GPIO 30
+/* Capabilities of a PF or a VF or the whole device */
+struct i40e_hw_capabilities {
+ u32 switch_mode;
+#define I40E_NVM_IMAGE_TYPE_EVB 0x0
+#define I40E_NVM_IMAGE_TYPE_CLOUD 0x2
+#define I40E_NVM_IMAGE_TYPE_UDP_CLOUD 0x3
+
+ u32 management_mode;
+ u32 npar_enable;
+ u32 os2bmc;
+ u32 valid_functions;
+ bool sr_iov_1_1;
+ bool vmdq;
+ bool evb_802_1_qbg; /* Edge Virtual Bridging */
+ bool evb_802_1_qbh; /* Bridge Port Extension */
+ bool dcb;
+ bool fcoe;
+ bool mfp_mode_1;
+ bool mgmt_cem;
+ bool ieee_1588;
+ bool iwarp;
+ bool fd;
+ u32 fd_filters_guaranteed;
+ u32 fd_filters_best_effort;
+ bool rss;
+ u32 rss_table_size;
+ u32 rss_table_entry_width;
+ bool led[I40E_HW_CAP_MAX_GPIO];
+ bool sdp[I40E_HW_CAP_MAX_GPIO];
+ u32 nvm_image_type;
+ u32 num_flow_director_filters;
+ u32 num_vfs;
+ u32 vf_base_id;
+ u32 num_vsis;
+ u32 num_rx_qp;
+ u32 num_tx_qp;
+ u32 base_queue;
+ u32 num_msix_vectors;
+ u32 num_msix_vectors_vf;
+ u32 led_pin_num;
+ u32 sdp_pin_num;
+ u32 mdio_port_num;
+ u32 mdio_port_mode;
+ u8 rx_buf_chain_len;
+ u32 enabled_tcmap;
+ u32 maxtc;
+};
+
+struct i40e_mac_info {
+ enum i40e_mac_type type;
+ u8 addr[I40E_ETH_LENGTH_OF_ADDRESS];
+ u8 perm_addr[I40E_ETH_LENGTH_OF_ADDRESS];
+ u8 san_addr[I40E_ETH_LENGTH_OF_ADDRESS];
+ u16 max_fcoeq;
+};
+
+enum i40e_aq_resources_ids {
+ I40E_NVM_RESOURCE_ID = 1
+};
+
+enum i40e_aq_resource_access_type {
+ I40E_RESOURCE_READ = 1,
+ I40E_RESOURCE_WRITE
+};
+
+struct i40e_nvm_info {
+ u64 hw_semaphore_timeout; /* 2usec global time (GTIME resolution) */
+ u64 hw_semaphore_wait; /* - || - */
+ u32 timeout; /* [ms] */
+ u16 sr_size; /* Shadow RAM size in words */
+ bool blank_nvm_mode; /* is NVM empty (no FW present)*/
+ u16 version; /* NVM package version */
+ u32 eetrack; /* NVM data version */
+};
+
+/* PCI bus types */
+enum i40e_bus_type {
+ i40e_bus_type_unknown = 0,
+ i40e_bus_type_pci,
+ i40e_bus_type_pcix,
+ i40e_bus_type_pci_express,
+ i40e_bus_type_reserved
+};
+
+/* PCI bus speeds */
+enum i40e_bus_speed {
+ i40e_bus_speed_unknown = 0,
+ i40e_bus_speed_33 = 33,
+ i40e_bus_speed_66 = 66,
+ i40e_bus_speed_100 = 100,
+ i40e_bus_speed_120 = 120,
+ i40e_bus_speed_133 = 133,
+ i40e_bus_speed_2500 = 2500,
+ i40e_bus_speed_5000 = 5000,
+ i40e_bus_speed_8000 = 8000,
+ i40e_bus_speed_reserved
+};
+
+/* PCI bus widths */
+enum i40e_bus_width {
+ i40e_bus_width_unknown = 0,
+ i40e_bus_width_pcie_x1 = 1,
+ i40e_bus_width_pcie_x2 = 2,
+ i40e_bus_width_pcie_x4 = 4,
+ i40e_bus_width_pcie_x8 = 8,
+ i40e_bus_width_32 = 32,
+ i40e_bus_width_64 = 64,
+ i40e_bus_width_reserved
+};
+
+/* Bus parameters */
+struct i40e_bus_info {
+ enum i40e_bus_speed speed;
+ enum i40e_bus_width width;
+ enum i40e_bus_type type;
+
+ u16 func;
+ u16 device;
+ u16 lan_id;
+};
+
+/* Flow control (FC) parameters */
+struct i40e_fc_info {
+ enum i40e_fc_mode current_mode; /* FC mode in effect */
+ enum i40e_fc_mode requested_mode; /* FC mode requested by caller */
+};
+
+#define I40E_MAX_TRAFFIC_CLASS 8
+#define I40E_MAX_USER_PRIORITY 8
+#define I40E_DCBX_MAX_APPS 32
+#define I40E_LLDPDU_SIZE 1500
+
+/* IEEE 802.1Qaz ETS Configuration data */
+struct i40e_ieee_ets_config {
+ u8 willing;
+ u8 cbs;
+ u8 maxtcs;
+ u8 prioritytable[I40E_MAX_TRAFFIC_CLASS];
+ u8 tcbwtable[I40E_MAX_TRAFFIC_CLASS];
+ u8 tsatable[I40E_MAX_TRAFFIC_CLASS];
+};
+
+/* IEEE 802.1Qaz ETS Recommendation data */
+struct i40e_ieee_ets_recommend {
+ u8 prioritytable[I40E_MAX_TRAFFIC_CLASS];
+ u8 tcbwtable[I40E_MAX_TRAFFIC_CLASS];
+ u8 tsatable[I40E_MAX_TRAFFIC_CLASS];
+};
+
+/* IEEE 802.1Qaz PFC Configuration data */
+struct i40e_ieee_pfc_config {
+ u8 willing;
+ u8 mbc;
+ u8 pfccap;
+ u8 pfcenable;
+};
+
+/* IEEE 802.1Qaz Application Priority data */
+struct i40e_ieee_app_priority_table {
+ u8 priority;
+ u8 selector;
+ u16 protocolid;
+};
+
+struct i40e_dcbx_config {
+ u32 numapps;
+ struct i40e_ieee_ets_config etscfg;
+ struct i40e_ieee_ets_recommend etsrec;
+ struct i40e_ieee_pfc_config pfc;
+ struct i40e_ieee_app_priority_table app[I40E_DCBX_MAX_APPS];
+};
+
+/* Port hardware description */
+struct i40e_hw {
+ u8 __iomem *hw_addr;
+ void *back;
+
+ /* function pointer structs */
+ struct i40e_phy_info phy;
+ struct i40e_mac_info mac;
+ struct i40e_bus_info bus;
+ struct i40e_nvm_info nvm;
+ struct i40e_fc_info fc;
+
+ /* pci info */
+ u16 device_id;
+ u16 vendor_id;
+ u16 subsystem_device_id;
+ u16 subsystem_vendor_id;
+ u8 revision_id;
+ u8 port;
+ bool adapter_stopped;
+
+ /* capabilities for entire device and PCI func */
+ struct i40e_hw_capabilities dev_caps;
+ struct i40e_hw_capabilities func_caps;
+
+ /* Flow Director shared filter space */
+ u16 fdir_shared_filter_count;
+
+ /* device profile info */
+ u8 pf_id;
+ u16 main_vsi_seid;
+
+ /* Closest numa node to the device */
+ u16 numa_node;
+
+ /* Admin Queue info */
+ struct i40e_adminq_info aq;
+
+ /* HMC info */
+ struct i40e_hmc_info hmc; /* HMC info struct */
+
+ /* LLDP/DCBX Status */
+ u16 dcbx_status;
+
+ /* DCBX info */
+ struct i40e_dcbx_config local_dcbx_config;
+ struct i40e_dcbx_config remote_dcbx_config;
+
+ /* debug mask */
+ u32 debug_mask;
+};
+
+struct i40e_driver_version {
+ u8 major_version;
+ u8 minor_version;
+ u8 build_version;
+ u8 subbuild_version;
+};
+
+/* RX Descriptors */
+union i40e_16byte_rx_desc {
+ struct {
+ __le64 pkt_addr; /* Packet buffer address */
+ __le64 hdr_addr; /* Header buffer address */
+ } read;
+ struct {
+ struct {
+ struct {
+ union {
+ __le16 mirroring_status;
+ __le16 fcoe_ctx_id;
+ } mirr_fcoe;
+ __le16 l2tag1;
+ } lo_dword;
+ union {
+ __le32 rss; /* RSS Hash */
+ __le32 fd_id; /* Flow director filter id */
+ __le32 fcoe_param; /* FCoE DDP Context id */
+ } hi_dword;
+ } qword0;
+ struct {
+ /* ext status/error/pktype/length */
+ __le64 status_error_len;
+ } qword1;
+ } wb; /* writeback */
+};
+
+union i40e_32byte_rx_desc {
+ struct {
+ __le64 pkt_addr; /* Packet buffer address */
+ __le64 hdr_addr; /* Header buffer address */
+ /* bit 0 of hdr_buffer_addr is DD bit */
+ __le64 rsvd1;
+ __le64 rsvd2;
+ } read;
+ struct {
+ struct {
+ struct {
+ union {
+ __le16 mirroring_status;
+ __le16 fcoe_ctx_id;
+ } mirr_fcoe;
+ __le16 l2tag1;
+ } lo_dword;
+ union {
+ __le32 rss; /* RSS Hash */
+ __le32 fcoe_param; /* FCoE DDP Context id */
+ } hi_dword;
+ } qword0;
+ struct {
+ /* status/error/pktype/length */
+ __le64 status_error_len;
+ } qword1;
+ struct {
+ __le16 ext_status; /* extended status */
+ __le16 rsvd;
+ __le16 l2tag2_1;
+ __le16 l2tag2_2;
+ } qword2;
+ struct {
+ union {
+ __le32 flex_bytes_lo;
+ __le32 pe_status;
+ } lo_dword;
+ union {
+ __le32 flex_bytes_hi;
+ __le32 fd_id;
+ } hi_dword;
+ } qword3;
+ } wb; /* writeback */
+};
+
+#define I40E_RXD_QW1_STATUS_SHIFT 0
+#define I40E_RXD_QW1_STATUS_MASK (0x7FFFUL << I40E_RXD_QW1_STATUS_SHIFT)
+
+enum i40e_rx_desc_status_bits {
+ /* Note: These are predefined bit offsets */
+ I40E_RX_DESC_STATUS_DD_SHIFT = 0,
+ I40E_RX_DESC_STATUS_EOF_SHIFT = 1,
+ I40E_RX_DESC_STATUS_L2TAG1P_SHIFT = 2,
+ I40E_RX_DESC_STATUS_L3L4P_SHIFT = 3,
+ I40E_RX_DESC_STATUS_CRCP_SHIFT = 4,
+ I40E_RX_DESC_STATUS_TSYNINDX_SHIFT = 5, /* 3 BITS */
+ I40E_RX_DESC_STATUS_PIF_SHIFT = 8,
+ I40E_RX_DESC_STATUS_UMBCAST_SHIFT = 9, /* 2 BITS */
+ I40E_RX_DESC_STATUS_FLM_SHIFT = 11,
+ I40E_RX_DESC_STATUS_FLTSTAT_SHIFT = 12, /* 2 BITS */
+ I40E_RX_DESC_STATUS_LPBK_SHIFT = 14
+};
+
+#define I40E_RXD_QW1_STATUS_TSYNINDX_SHIFT I40E_RX_DESC_STATUS_TSYNINDX_SHIFT
+#define I40E_RXD_QW1_STATUS_TSYNINDX_MASK (0x7UL << \
+ I40E_RXD_QW1_STATUS_TSYNINDX_SHIFT)
+
+enum i40e_rx_desc_fltstat_values {
+ I40E_RX_DESC_FLTSTAT_NO_DATA = 0,
+ I40E_RX_DESC_FLTSTAT_RSV_FD_ID = 1, /* 16byte desc? FD_ID : RSV */
+ I40E_RX_DESC_FLTSTAT_RSV = 2,
+ I40E_RX_DESC_FLTSTAT_RSS_HASH = 3,
+};
+
+#define I40E_RXD_QW1_ERROR_SHIFT 19
+#define I40E_RXD_QW1_ERROR_MASK (0xFFUL << I40E_RXD_QW1_ERROR_SHIFT)
+
+enum i40e_rx_desc_error_bits {
+ /* Note: These are predefined bit offsets */
+ I40E_RX_DESC_ERROR_RXE_SHIFT = 0,
+ I40E_RX_DESC_ERROR_RECIPE_SHIFT = 1,
+ I40E_RX_DESC_ERROR_HBO_SHIFT = 2,
+ I40E_RX_DESC_ERROR_L3L4E_SHIFT = 3, /* 3 BITS */
+ I40E_RX_DESC_ERROR_IPE_SHIFT = 3,
+ I40E_RX_DESC_ERROR_L4E_SHIFT = 4,
+ I40E_RX_DESC_ERROR_EIPE_SHIFT = 5,
+ I40E_RX_DESC_ERROR_OVERSIZE_SHIFT = 6
+};
+
+enum i40e_rx_desc_error_l3l4e_fcoe_masks {
+ I40E_RX_DESC_ERROR_L3L4E_NONE = 0,
+ I40E_RX_DESC_ERROR_L3L4E_PROT = 1,
+ I40E_RX_DESC_ERROR_L3L4E_FC = 2,
+ I40E_RX_DESC_ERROR_L3L4E_DMAC_ERR = 3,
+ I40E_RX_DESC_ERROR_L3L4E_DMAC_WARN = 4
+};
+
+#define I40E_RXD_QW1_PTYPE_SHIFT 30
+#define I40E_RXD_QW1_PTYPE_MASK (0xFFULL << I40E_RXD_QW1_PTYPE_SHIFT)
+
+/* Packet type non-ip values */
+enum i40e_rx_l2_ptype {
+ I40E_RX_PTYPE_L2_RESERVED = 0,
+ I40E_RX_PTYPE_L2_MAC_PAY2 = 1,
+ I40E_RX_PTYPE_L2_TIMESYNC_PAY2 = 2,
+ I40E_RX_PTYPE_L2_FIP_PAY2 = 3,
+ I40E_RX_PTYPE_L2_OUI_PAY2 = 4,
+ I40E_RX_PTYPE_L2_MACCNTRL_PAY2 = 5,
+ I40E_RX_PTYPE_L2_LLDP_PAY2 = 6,
+ I40E_RX_PTYPE_L2_ECP_PAY2 = 7,
+ I40E_RX_PTYPE_L2_EVB_PAY2 = 8,
+ I40E_RX_PTYPE_L2_QCN_PAY2 = 9,
+ I40E_RX_PTYPE_L2_EAPOL_PAY2 = 10,
+ I40E_RX_PTYPE_L2_ARP = 11,
+ I40E_RX_PTYPE_L2_FCOE_PAY3 = 12,
+ I40E_RX_PTYPE_L2_FCOE_FCDATA_PAY3 = 13,
+ I40E_RX_PTYPE_L2_FCOE_FCRDY_PAY3 = 14,
+ I40E_RX_PTYPE_L2_FCOE_FCRSP_PAY3 = 15,
+ I40E_RX_PTYPE_L2_FCOE_FCOTHER_PA = 16,
+ I40E_RX_PTYPE_L2_FCOE_VFT_PAY3 = 17,
+ I40E_RX_PTYPE_L2_FCOE_VFT_FCDATA = 18,
+ I40E_RX_PTYPE_L2_FCOE_VFT_FCRDY = 19,
+ I40E_RX_PTYPE_L2_FCOE_VFT_FCRSP = 20,
+ I40E_RX_PTYPE_L2_FCOE_VFT_FCOTHER = 21
+};
+
+struct i40e_rx_ptype_decoded {
+ u32 ptype:8;
+ u32 known:1;
+ u32 outer_ip:1;
+ u32 outer_ip_ver:1;
+ u32 outer_frag:1;
+ u32 tunnel_type:3;
+ u32 tunnel_end_prot:2;
+ u32 tunnel_end_frag:1;
+ u32 inner_prot:4;
+ u32 payload_layer:3;
+};
+
+enum i40e_rx_ptype_outer_ip {
+ I40E_RX_PTYPE_OUTER_L2 = 0,
+ I40E_RX_PTYPE_OUTER_IP = 1
+};
+
+enum i40e_rx_ptype_outer_ip_ver {
+ I40E_RX_PTYPE_OUTER_NONE = 0,
+ I40E_RX_PTYPE_OUTER_IPV4 = 0,
+ I40E_RX_PTYPE_OUTER_IPV6 = 1
+};
+
+enum i40e_rx_ptype_outer_fragmented {
+ I40E_RX_PTYPE_NOT_FRAG = 0,
+ I40E_RX_PTYPE_FRAG = 1
+};
+
+enum i40e_rx_ptype_tunnel_type {
+ I40E_RX_PTYPE_TUNNEL_NONE = 0,
+ I40E_RX_PTYPE_TUNNEL_IP_IP = 1,
+ I40E_RX_PTYPE_TUNNEL_IP_GRENAT = 2,
+ I40E_RX_PTYPE_TUNNEL_IP_GRENAT_MAC = 3,
+ I40E_RX_PTYPE_TUNNEL_IP_GRENAT_MAC_VLAN = 4,
+};
+
+enum i40e_rx_ptype_tunnel_end_prot {
+ I40E_RX_PTYPE_TUNNEL_END_NONE = 0,
+ I40E_RX_PTYPE_TUNNEL_END_IPV4 = 1,
+ I40E_RX_PTYPE_TUNNEL_END_IPV6 = 2,
+};
+
+enum i40e_rx_ptype_inner_prot {
+ I40E_RX_PTYPE_INNER_PROT_NONE = 0,
+ I40E_RX_PTYPE_INNER_PROT_UDP = 1,
+ I40E_RX_PTYPE_INNER_PROT_TCP = 2,
+ I40E_RX_PTYPE_INNER_PROT_SCTP = 3,
+ I40E_RX_PTYPE_INNER_PROT_ICMP = 4,
+ I40E_RX_PTYPE_INNER_PROT_TIMESYNC = 5
+};
+
+enum i40e_rx_ptype_payload_layer {
+ I40E_RX_PTYPE_PAYLOAD_LAYER_NONE = 0,
+ I40E_RX_PTYPE_PAYLOAD_LAYER_PAY2 = 1,
+ I40E_RX_PTYPE_PAYLOAD_LAYER_PAY3 = 2,
+ I40E_RX_PTYPE_PAYLOAD_LAYER_PAY4 = 3,
+};
+
+#define I40E_RXD_QW1_LENGTH_PBUF_SHIFT 38
+#define I40E_RXD_QW1_LENGTH_PBUF_MASK (0x3FFFULL << \
+ I40E_RXD_QW1_LENGTH_PBUF_SHIFT)
+
+#define I40E_RXD_QW1_LENGTH_HBUF_SHIFT 52
+#define I40E_RXD_QW1_LENGTH_HBUF_MASK (0x7FFULL << \
+ I40E_RXD_QW1_LENGTH_HBUF_SHIFT)
+
+#define I40E_RXD_QW1_LENGTH_SPH_SHIFT 63
+#define I40E_RXD_QW1_LENGTH_SPH_MASK (0x1ULL << \
+ I40E_RXD_QW1_LENGTH_SPH_SHIFT)
+
+enum i40e_rx_desc_ext_status_bits {
+ /* Note: These are predefined bit offsets */
+ I40E_RX_DESC_EXT_STATUS_L2TAG2P_SHIFT = 0,
+ I40E_RX_DESC_EXT_STATUS_L2TAG3P_SHIFT = 1,
+ I40E_RX_DESC_EXT_STATUS_FLEXBL_SHIFT = 2, /* 2 BITS */
+ I40E_RX_DESC_EXT_STATUS_FLEXBH_SHIFT = 4, /* 2 BITS */
+ I40E_RX_DESC_EXT_STATUS_FTYPE_SHIFT = 6, /* 3 BITS */
+ I40E_RX_DESC_EXT_STATUS_FDLONGB_SHIFT = 9,
+ I40E_RX_DESC_EXT_STATUS_FCOELONGB_SHIFT = 10,
+ I40E_RX_DESC_EXT_STATUS_PELONGB_SHIFT = 11,
+};
+
+enum i40e_rx_desc_pe_status_bits {
+ /* Note: These are predefined bit offsets */
+ I40E_RX_DESC_PE_STATUS_QPID_SHIFT = 0, /* 18 BITS */
+ I40E_RX_DESC_PE_STATUS_L4PORT_SHIFT = 0, /* 16 BITS */
+ I40E_RX_DESC_PE_STATUS_IPINDEX_SHIFT = 16, /* 8 BITS */
+ I40E_RX_DESC_PE_STATUS_QPIDHIT_SHIFT = 24,
+ I40E_RX_DESC_PE_STATUS_APBVTHIT_SHIFT = 25,
+ I40E_RX_DESC_PE_STATUS_PORTV_SHIFT = 26,
+ I40E_RX_DESC_PE_STATUS_URG_SHIFT = 27,
+ I40E_RX_DESC_PE_STATUS_IPFRAG_SHIFT = 28,
+ I40E_RX_DESC_PE_STATUS_IPOPT_SHIFT = 29
+};
+
+#define I40E_RX_PROG_STATUS_DESC_LENGTH_SHIFT 38
+#define I40E_RX_PROG_STATUS_DESC_LENGTH 0x2000000
+
+#define I40E_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT 2
+#define I40E_RX_PROG_STATUS_DESC_QW1_PROGID_MASK (0x7UL << \
+ I40E_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT)
+
+#define I40E_RX_PROG_STATUS_DESC_QW1_ERROR_SHIFT 19
+#define I40E_RX_PROG_STATUS_DESC_QW1_ERROR_MASK (0x3FUL << \
+ I40E_RX_PROG_STATUS_DESC_QW1_ERROR_SHIFT)
+
+enum i40e_rx_prog_status_desc_status_bits {
+ /* Note: These are predefined bit offsets */
+ I40E_RX_PROG_STATUS_DESC_DD_SHIFT = 0,
+ I40E_RX_PROG_STATUS_DESC_PROG_ID_SHIFT = 2 /* 3 BITS */
+};
+
+enum i40e_rx_prog_status_desc_prog_id_masks {
+ I40E_RX_PROG_STATUS_DESC_FD_FILTER_STATUS = 1,
+ I40E_RX_PROG_STATUS_DESC_FCOE_CTXT_PROG_STATUS = 2,
+ I40E_RX_PROG_STATUS_DESC_FCOE_CTXT_INVL_STATUS = 4,
+};
+
+enum i40e_rx_prog_status_desc_error_bits {
+ /* Note: These are predefined bit offsets */
+ I40E_RX_PROG_STATUS_DESC_FD_TBL_FULL_SHIFT = 0,
+ I40E_RX_PROG_STATUS_DESC_NO_FD_QUOTA_SHIFT = 1,
+ I40E_RX_PROG_STATUS_DESC_FCOE_TBL_FULL_SHIFT = 2,
+ I40E_RX_PROG_STATUS_DESC_FCOE_CONFLICT_SHIFT = 3
+};
+
+/* TX Descriptor */
+struct i40e_tx_desc {
+ __le64 buffer_addr; /* Address of descriptor's data buf */
+ __le64 cmd_type_offset_bsz;
+};
+
+#define I40E_TXD_QW1_DTYPE_SHIFT 0
+#define I40E_TXD_QW1_DTYPE_MASK (0xFUL << I40E_TXD_QW1_DTYPE_SHIFT)
+
+enum i40e_tx_desc_dtype_value {
+ I40E_TX_DESC_DTYPE_DATA = 0x0,
+ I40E_TX_DESC_DTYPE_NOP = 0x1, /* same as Context desc */
+ I40E_TX_DESC_DTYPE_CONTEXT = 0x1,
+ I40E_TX_DESC_DTYPE_FCOE_CTX = 0x2,
+ I40E_TX_DESC_DTYPE_FILTER_PROG = 0x8,
+ I40E_TX_DESC_DTYPE_DDP_CTX = 0x9,
+ I40E_TX_DESC_DTYPE_FLEX_DATA = 0xB,
+ I40E_TX_DESC_DTYPE_FLEX_CTX_1 = 0xC,
+ I40E_TX_DESC_DTYPE_FLEX_CTX_2 = 0xD,
+ I40E_TX_DESC_DTYPE_DESC_DONE = 0xF
+};
+
+#define I40E_TXD_QW1_CMD_SHIFT 4
+#define I40E_TXD_QW1_CMD_MASK (0x3FFUL << I40E_TXD_QW1_CMD_SHIFT)
+
+enum i40e_tx_desc_cmd_bits {
+ I40E_TX_DESC_CMD_EOP = 0x0001,
+ I40E_TX_DESC_CMD_RS = 0x0002,
+ I40E_TX_DESC_CMD_ICRC = 0x0004,
+ I40E_TX_DESC_CMD_IL2TAG1 = 0x0008,
+ I40E_TX_DESC_CMD_DUMMY = 0x0010,
+ I40E_TX_DESC_CMD_IIPT_NONIP = 0x0000, /* 2 BITS */
+ I40E_TX_DESC_CMD_IIPT_IPV6 = 0x0020, /* 2 BITS */
+ I40E_TX_DESC_CMD_IIPT_IPV4 = 0x0040, /* 2 BITS */
+ I40E_TX_DESC_CMD_IIPT_IPV4_CSUM = 0x0060, /* 2 BITS */
+ I40E_TX_DESC_CMD_FCOET = 0x0080,
+ I40E_TX_DESC_CMD_L4T_EOFT_UNK = 0x0000, /* 2 BITS */
+ I40E_TX_DESC_CMD_L4T_EOFT_TCP = 0x0100, /* 2 BITS */
+ I40E_TX_DESC_CMD_L4T_EOFT_SCTP = 0x0200, /* 2 BITS */
+ I40E_TX_DESC_CMD_L4T_EOFT_UDP = 0x0300, /* 2 BITS */
+ I40E_TX_DESC_CMD_L4T_EOFT_EOF_N = 0x0000, /* 2 BITS */
+ I40E_TX_DESC_CMD_L4T_EOFT_EOF_T = 0x0100, /* 2 BITS */
+ I40E_TX_DESC_CMD_L4T_EOFT_EOF_NI = 0x0200, /* 2 BITS */
+ I40E_TX_DESC_CMD_L4T_EOFT_EOF_A = 0x0300, /* 2 BITS */
+};
+
+#define I40E_TXD_QW1_OFFSET_SHIFT 16
+#define I40E_TXD_QW1_OFFSET_MASK (0x3FFFFULL << \
+ I40E_TXD_QW1_OFFSET_SHIFT)
+
+enum i40e_tx_desc_length_fields {
+ /* Note: These are predefined bit offsets */
+ I40E_TX_DESC_LENGTH_MACLEN_SHIFT = 0, /* 7 BITS */
+ I40E_TX_DESC_LENGTH_IPLEN_SHIFT = 7, /* 7 BITS */
+ I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT = 14 /* 4 BITS */
+};
+
+#define I40E_TXD_QW1_TX_BUF_SZ_SHIFT 34
+#define I40E_TXD_QW1_TX_BUF_SZ_MASK (0x3FFFULL << \
+ I40E_TXD_QW1_TX_BUF_SZ_SHIFT)
+
+#define I40E_TXD_QW1_L2TAG1_SHIFT 48
+#define I40E_TXD_QW1_L2TAG1_MASK (0xFFFFULL << I40E_TXD_QW1_L2TAG1_SHIFT)
+
+/* Context descriptors */
+struct i40e_tx_context_desc {
+ __le32 tunneling_params;
+ __le16 l2tag2;
+ __le16 rsvd;
+ __le64 type_cmd_tso_mss;
+};
+
+#define I40E_TXD_CTX_QW1_DTYPE_SHIFT 0
+#define I40E_TXD_CTX_QW1_DTYPE_MASK (0xFUL << I40E_TXD_CTX_QW1_DTYPE_SHIFT)
+
+#define I40E_TXD_CTX_QW1_CMD_SHIFT 4
+#define I40E_TXD_CTX_QW1_CMD_MASK (0xFFFFUL << I40E_TXD_CTX_QW1_CMD_SHIFT)
+
+enum i40e_tx_ctx_desc_cmd_bits {
+ I40E_TX_CTX_DESC_TSO = 0x01,
+ I40E_TX_CTX_DESC_TSYN = 0x02,
+ I40E_TX_CTX_DESC_IL2TAG2 = 0x04,
+ I40E_TX_CTX_DESC_IL2TAG2_IL2H = 0x08,
+ I40E_TX_CTX_DESC_SWTCH_NOTAG = 0x00,
+ I40E_TX_CTX_DESC_SWTCH_UPLINK = 0x10,
+ I40E_TX_CTX_DESC_SWTCH_LOCAL = 0x20,
+ I40E_TX_CTX_DESC_SWTCH_VSI = 0x30,
+ I40E_TX_CTX_DESC_SWPE = 0x40
+};
+
+#define I40E_TXD_CTX_QW1_TSO_LEN_SHIFT 30
+#define I40E_TXD_CTX_QW1_TSO_LEN_MASK (0x3FFFFULL << \
+ I40E_TXD_CTX_QW1_TSO_LEN_SHIFT)
+
+#define I40E_TXD_CTX_QW1_MSS_SHIFT 50
+#define I40E_TXD_CTX_QW1_MSS_MASK (0x3FFFULL << \
+ I40E_TXD_CTX_QW1_MSS_SHIFT)
+
+#define I40E_TXD_CTX_QW1_VSI_SHIFT 50
+#define I40E_TXD_CTX_QW1_VSI_MASK (0x1FFULL << I40E_TXD_CTX_QW1_VSI_SHIFT)
+
+#define I40E_TXD_CTX_QW0_EXT_IP_SHIFT 0
+#define I40E_TXD_CTX_QW0_EXT_IP_MASK (0x3ULL << \
+ I40E_TXD_CTX_QW0_EXT_IP_SHIFT)
+
+enum i40e_tx_ctx_desc_eipt_offload {
+ I40E_TX_CTX_EXT_IP_NONE = 0x0,
+ I40E_TX_CTX_EXT_IP_IPV6 = 0x1,
+ I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM = 0x2,
+ I40E_TX_CTX_EXT_IP_IPV4 = 0x3
+};
+
+#define I40E_TXD_CTX_QW0_EXT_IPLEN_SHIFT 2
+#define I40E_TXD_CTX_QW0_EXT_IPLEN_MASK (0x3FULL << \
+ I40E_TXD_CTX_QW0_EXT_IPLEN_SHIFT)
+
+#define I40E_TXD_CTX_QW0_NATT_SHIFT 9
+#define I40E_TXD_CTX_QW0_NATT_MASK (0x3ULL << I40E_TXD_CTX_QW0_NATT_SHIFT)
+
+#define I40E_TXD_CTX_UDP_TUNNELING (0x1ULL << I40E_TXD_CTX_QW0_NATT_SHIFT)
+#define I40E_TXD_CTX_GRE_TUNNELING (0x2ULL << I40E_TXD_CTX_QW0_NATT_SHIFT)
+
+#define I40E_TXD_CTX_QW0_EIP_NOINC_SHIFT 11
+#define I40E_TXD_CTX_QW0_EIP_NOINC_MASK (0x1ULL << \
+ I40E_TXD_CTX_QW0_EIP_NOINC_SHIFT)
+
+#define I40E_TXD_CTX_EIP_NOINC_IPID_CONST I40E_TXD_CTX_QW0_EIP_NOINC_MASK
+
+#define I40E_TXD_CTX_QW0_NATLEN_SHIFT 12
+#define I40E_TXD_CTX_QW0_NATLEN_MASK (0X7FULL << \
+ I40E_TXD_CTX_QW0_NATLEN_SHIFT)
+
+#define I40E_TXD_CTX_QW0_DECTTL_SHIFT 19
+#define I40E_TXD_CTX_QW0_DECTTL_MASK (0xFULL << \
+ I40E_TXD_CTX_QW0_DECTTL_SHIFT)
+
+struct i40e_filter_program_desc {
+ __le32 qindex_flex_ptype_vsi;
+ __le32 rsvd;
+ __le32 dtype_cmd_cntindex;
+ __le32 fd_id;
+};
+#define I40E_TXD_FLTR_QW0_QINDEX_SHIFT 0
+#define I40E_TXD_FLTR_QW0_QINDEX_MASK (0x7FFUL << \
+ I40E_TXD_FLTR_QW0_QINDEX_SHIFT)
+#define I40E_TXD_FLTR_QW0_FLEXOFF_SHIFT 11
+#define I40E_TXD_FLTR_QW0_FLEXOFF_MASK (0x7UL << \
+ I40E_TXD_FLTR_QW0_FLEXOFF_SHIFT)
+#define I40E_TXD_FLTR_QW0_PCTYPE_SHIFT 17
+#define I40E_TXD_FLTR_QW0_PCTYPE_MASK (0x3FUL << \
+ I40E_TXD_FLTR_QW0_PCTYPE_SHIFT)
+
+/* Packet Classifier Types for filters */
+enum i40e_filter_pctype {
+ /* Note: Value 0-25 are reserved for future use */
+ I40E_FILTER_PCTYPE_IPV4_TEREDO_UDP = 26,
+ I40E_FILTER_PCTYPE_IPV6_TEREDO_UDP = 27,
+ I40E_FILTER_PCTYPE_NONF_IPV4_1588_UDP = 28,
+ I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP = 29,
+ I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP = 30,
+ I40E_FILTER_PCTYPE_NONF_IPV4_UDP = 31,
+ I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN = 32,
+ I40E_FILTER_PCTYPE_NONF_IPV4_TCP = 33,
+ I40E_FILTER_PCTYPE_NONF_IPV4_SCTP = 34,
+ I40E_FILTER_PCTYPE_NONF_IPV4_OTHER = 35,
+ I40E_FILTER_PCTYPE_FRAG_IPV4 = 36,
+ /* Note: Value 37 is reserved for future use */
+ I40E_FILTER_PCTYPE_NONF_IPV6_1588_UDP = 38,
+ I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP = 39,
+ I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP = 40,
+ I40E_FILTER_PCTYPE_NONF_IPV6_UDP = 41,
+ I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN = 42,
+ I40E_FILTER_PCTYPE_NONF_IPV6_TCP = 43,
+ I40E_FILTER_PCTYPE_NONF_IPV6_SCTP = 44,
+ I40E_FILTER_PCTYPE_NONF_IPV6_OTHER = 45,
+ I40E_FILTER_PCTYPE_FRAG_IPV6 = 46,
+ /* Note: Value 47 is reserved for future use */
+ I40E_FILTER_PCTYPE_FCOE_OX = 48,
+ I40E_FILTER_PCTYPE_FCOE_RX = 49,
+ /* Note: Value 50-62 are reserved for future use */
+ I40E_FILTER_PCTYPE_L2_PAYLOAD = 63,
+};
+
+enum i40e_filter_program_desc_dest {
+ I40E_FILTER_PROGRAM_DESC_DEST_DROP_PACKET = 0x0,
+ I40E_FILTER_PROGRAM_DESC_DEST_DIRECT_PACKET_QINDEX = 0x1,
+ I40E_FILTER_PROGRAM_DESC_DEST_DIRECT_PACKET_OTHER = 0x2,
+};
+
+enum i40e_filter_program_desc_fd_status {
+ I40E_FILTER_PROGRAM_DESC_FD_STATUS_NONE = 0x0,
+ I40E_FILTER_PROGRAM_DESC_FD_STATUS_FD_ID = 0x1,
+ I40E_FILTER_PROGRAM_DESC_FD_STATUS_FD_ID_4FLEX_BYTES = 0x2,
+ I40E_FILTER_PROGRAM_DESC_FD_STATUS_8FLEX_BYTES = 0x3,
+};
+
+#define I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT 23
+#define I40E_TXD_FLTR_QW0_DEST_VSI_MASK (0x1FFUL << \
+ I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT)
+
+#define I40E_TXD_FLTR_QW1_CMD_SHIFT 4
+#define I40E_TXD_FLTR_QW1_CMD_MASK (0xFFFFULL << \
+ I40E_TXD_FLTR_QW1_CMD_SHIFT)
+
+#define I40E_TXD_FLTR_QW1_PCMD_SHIFT (0x0ULL + I40E_TXD_FLTR_QW1_CMD_SHIFT)
+#define I40E_TXD_FLTR_QW1_PCMD_MASK (0x7ULL << I40E_TXD_FLTR_QW1_PCMD_SHIFT)
+
+enum i40e_filter_program_desc_pcmd {
+ I40E_FILTER_PROGRAM_DESC_PCMD_ADD_UPDATE = 0x1,
+ I40E_FILTER_PROGRAM_DESC_PCMD_REMOVE = 0x2,
+};
+
+#define I40E_TXD_FLTR_QW1_DEST_SHIFT (0x3ULL + I40E_TXD_FLTR_QW1_CMD_SHIFT)
+#define I40E_TXD_FLTR_QW1_DEST_MASK (0x3ULL << I40E_TXD_FLTR_QW1_DEST_SHIFT)
+
+#define I40E_TXD_FLTR_QW1_CNT_ENA_SHIFT (0x7ULL + I40E_TXD_FLTR_QW1_CMD_SHIFT)
+#define I40E_TXD_FLTR_QW1_CNT_ENA_MASK (0x1ULL << \
+ I40E_TXD_FLTR_QW1_CNT_ENA_SHIFT)
+
+#define I40E_TXD_FLTR_QW1_FD_STATUS_SHIFT (0x9ULL + \
+ I40E_TXD_FLTR_QW1_CMD_SHIFT)
+#define I40E_TXD_FLTR_QW1_FD_STATUS_MASK (0x3ULL << \
+ I40E_TXD_FLTR_QW1_FD_STATUS_SHIFT)
+
+#define I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT 20
+#define I40E_TXD_FLTR_QW1_CNTINDEX_MASK (0x1FFUL << \
+ I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT)
+
+enum i40e_filter_type {
+ I40E_FLOW_DIRECTOR_FLTR = 0,
+ I40E_PE_QUAD_HASH_FLTR = 1,
+ I40E_ETHERTYPE_FLTR,
+ I40E_FCOE_CTX_FLTR,
+ I40E_MAC_VLAN_FLTR,
+ I40E_HASH_FLTR
+};
+
+struct i40e_vsi_context {
+ u16 seid;
+ u16 uplink_seid;
+ u16 vsi_number;
+ u16 vsis_allocated;
+ u16 vsis_unallocated;
+ u16 flags;
+ u8 pf_num;
+ u8 vf_num;
+ u8 connection_type;
+ struct i40e_aqc_vsi_properties_data info;
+};
+
+/* Statistics collected by each port, VSI, VEB, and S-channel */
+struct i40e_eth_stats {
+ u64 rx_bytes; /* gorc */
+ u64 rx_unicast; /* uprc */
+ u64 rx_multicast; /* mprc */
+ u64 rx_broadcast; /* bprc */
+ u64 rx_discards; /* rdpc */
+ u64 rx_errors; /* repc */
+ u64 rx_missed; /* rmpc */
+ u64 rx_unknown_protocol; /* rupp */
+ u64 tx_bytes; /* gotc */
+ u64 tx_unicast; /* uptc */
+ u64 tx_multicast; /* mptc */
+ u64 tx_broadcast; /* bptc */
+ u64 tx_discards; /* tdpc */
+ u64 tx_errors; /* tepc */
+};
+
+/* Statistics collected by the MAC */
+struct i40e_hw_port_stats {
+ /* eth stats collected by the port */
+ struct i40e_eth_stats eth;
+
+ /* additional port specific stats */
+ u64 tx_dropped_link_down; /* tdold */
+ u64 crc_errors; /* crcerrs */
+ u64 illegal_bytes; /* illerrc */
+ u64 error_bytes; /* errbc */
+ u64 mac_local_faults; /* mlfc */
+ u64 mac_remote_faults; /* mrfc */
+ u64 rx_length_errors; /* rlec */
+ u64 link_xon_rx; /* lxonrxc */
+ u64 link_xoff_rx; /* lxoffrxc */
+ u64 priority_xon_rx[8]; /* pxonrxc[8] */
+ u64 priority_xoff_rx[8]; /* pxoffrxc[8] */
+ u64 link_xon_tx; /* lxontxc */
+ u64 link_xoff_tx; /* lxofftxc */
+ u64 priority_xon_tx[8]; /* pxontxc[8] */
+ u64 priority_xoff_tx[8]; /* pxofftxc[8] */
+ u64 priority_xon_2_xoff[8]; /* pxon2offc[8] */
+ u64 rx_size_64; /* prc64 */
+ u64 rx_size_127; /* prc127 */
+ u64 rx_size_255; /* prc255 */
+ u64 rx_size_511; /* prc511 */
+ u64 rx_size_1023; /* prc1023 */
+ u64 rx_size_1522; /* prc1522 */
+ u64 rx_size_big; /* prc9522 */
+ u64 rx_undersize; /* ruc */
+ u64 rx_fragments; /* rfc */
+ u64 rx_oversize; /* roc */
+ u64 rx_jabber; /* rjc */
+ u64 tx_size_64; /* ptc64 */
+ u64 tx_size_127; /* ptc127 */
+ u64 tx_size_255; /* ptc255 */
+ u64 tx_size_511; /* ptc511 */
+ u64 tx_size_1023; /* ptc1023 */
+ u64 tx_size_1522; /* ptc1522 */
+ u64 tx_size_big; /* ptc9522 */
+ u64 mac_short_packet_dropped; /* mspdc */
+ u64 checksum_error; /* xec */
+};
+
+/* Checksum and Shadow RAM pointers */
+#define I40E_SR_NVM_CONTROL_WORD 0x00
+#define I40E_SR_EMP_MODULE_PTR 0x0F
+#define I40E_SR_NVM_IMAGE_VERSION 0x18
+#define I40E_SR_ALTERNATE_SAN_MAC_ADDRESS_PTR 0x27
+#define I40E_SR_NVM_EETRACK_LO 0x2D
+#define I40E_SR_NVM_EETRACK_HI 0x2E
+#define I40E_SR_VPD_PTR 0x2F
+#define I40E_SR_PCIE_ALT_AUTO_LOAD_PTR 0x3E
+#define I40E_SR_SW_CHECKSUM_WORD 0x3F
+
+/* Auxiliary field, mask and shift definition for Shadow RAM and NVM Flash */
+#define I40E_SR_VPD_MODULE_MAX_SIZE 1024
+#define I40E_SR_PCIE_ALT_MODULE_MAX_SIZE 1024
+#define I40E_SR_CONTROL_WORD_1_SHIFT 0x06
+#define I40E_SR_CONTROL_WORD_1_MASK (0x03 << I40E_SR_CONTROL_WORD_1_SHIFT)
+
+/* Shadow RAM related */
+#define I40E_SR_SECTOR_SIZE_IN_WORDS 0x800
+#define I40E_SR_WORDS_IN_1KB 512
+/* Checksum should be calculated such that after adding all the words,
+ * including the checksum word itself, the sum should be 0xBABA.
+ */
+#define I40E_SR_SW_CHECKSUM_BASE 0xBABA
+
+#define I40E_SRRD_SRCTL_ATTEMPTS 100000
+
+enum i40e_switch_element_types {
+ I40E_SWITCH_ELEMENT_TYPE_MAC = 1,
+ I40E_SWITCH_ELEMENT_TYPE_PF = 2,
+ I40E_SWITCH_ELEMENT_TYPE_VF = 3,
+ I40E_SWITCH_ELEMENT_TYPE_EMP = 4,
+ I40E_SWITCH_ELEMENT_TYPE_BMC = 6,
+ I40E_SWITCH_ELEMENT_TYPE_PE = 16,
+ I40E_SWITCH_ELEMENT_TYPE_VEB = 17,
+ I40E_SWITCH_ELEMENT_TYPE_PA = 18,
+ I40E_SWITCH_ELEMENT_TYPE_VSI = 19,
+};
+
+/* Supported EtherType filters */
+enum i40e_ether_type_index {
+ I40E_ETHER_TYPE_1588 = 0,
+ I40E_ETHER_TYPE_FIP = 1,
+ I40E_ETHER_TYPE_OUI_EXTENDED = 2,
+ I40E_ETHER_TYPE_MAC_CONTROL = 3,
+ I40E_ETHER_TYPE_LLDP = 4,
+ I40E_ETHER_TYPE_EVB_PROTOCOL1 = 5,
+ I40E_ETHER_TYPE_EVB_PROTOCOL2 = 6,
+ I40E_ETHER_TYPE_QCN_CNM = 7,
+ I40E_ETHER_TYPE_8021X = 8,
+ I40E_ETHER_TYPE_ARP = 9,
+ I40E_ETHER_TYPE_RSV1 = 10,
+ I40E_ETHER_TYPE_RSV2 = 11,
+};
+
+/* Filter context base size is 1K */
+#define I40E_HASH_FILTER_BASE_SIZE 1024
+/* Supported Hash filter values */
+enum i40e_hash_filter_size {
+ I40E_HASH_FILTER_SIZE_1K = 0,
+ I40E_HASH_FILTER_SIZE_2K = 1,
+ I40E_HASH_FILTER_SIZE_4K = 2,
+ I40E_HASH_FILTER_SIZE_8K = 3,
+ I40E_HASH_FILTER_SIZE_16K = 4,
+ I40E_HASH_FILTER_SIZE_32K = 5,
+ I40E_HASH_FILTER_SIZE_64K = 6,
+ I40E_HASH_FILTER_SIZE_128K = 7,
+ I40E_HASH_FILTER_SIZE_256K = 8,
+ I40E_HASH_FILTER_SIZE_512K = 9,
+ I40E_HASH_FILTER_SIZE_1M = 10,
+};
+
+/* DMA context base size is 0.5K */
+#define I40E_DMA_CNTX_BASE_SIZE 512
+/* Supported DMA context values */
+enum i40e_dma_cntx_size {
+ I40E_DMA_CNTX_SIZE_512 = 0,
+ I40E_DMA_CNTX_SIZE_1K = 1,
+ I40E_DMA_CNTX_SIZE_2K = 2,
+ I40E_DMA_CNTX_SIZE_4K = 3,
+ I40E_DMA_CNTX_SIZE_8K = 4,
+ I40E_DMA_CNTX_SIZE_16K = 5,
+ I40E_DMA_CNTX_SIZE_32K = 6,
+ I40E_DMA_CNTX_SIZE_64K = 7,
+ I40E_DMA_CNTX_SIZE_128K = 8,
+ I40E_DMA_CNTX_SIZE_256K = 9,
+};
+
+/* Supported Hash look up table (LUT) sizes */
+enum i40e_hash_lut_size {
+ I40E_HASH_LUT_SIZE_128 = 0,
+ I40E_HASH_LUT_SIZE_512 = 1,
+};
+
+/* Structure to hold a per PF filter control settings */
+struct i40e_filter_control_settings {
+ /* number of PE Quad Hash filter buckets */
+ enum i40e_hash_filter_size pe_filt_num;
+ /* number of PE Quad Hash contexts */
+ enum i40e_dma_cntx_size pe_cntx_num;
+ /* number of FCoE filter buckets */
+ enum i40e_hash_filter_size fcoe_filt_num;
+ /* number of FCoE DDP contexts */
+ enum i40e_dma_cntx_size fcoe_cntx_num;
+ /* size of the Hash LUT */
+ enum i40e_hash_lut_size hash_lut_size;
+ /* enable FDIR filters for PF and its VFs */
+ bool enable_fdir;
+ /* enable Ethertype filters for PF and its VFs */
+ bool enable_ethtype;
+ /* enable MAC/VLAN filters for PF and its VFs */
+ bool enable_macvlan;
+};
+
+/* Structure to hold device level control filter counts */
+struct i40e_control_filter_stats {
+ u16 mac_etype_used; /* Used perfect match MAC/EtherType filters */
+ u16 etype_used; /* Used perfect EtherType filters */
+ u16 mac_etype_free; /* Un-used perfect match MAC/EtherType filters */
+ u16 etype_free; /* Un-used perfect EtherType filters */
+};
+
+enum i40e_reset_type {
+ I40E_RESET_POR = 0,
+ I40E_RESET_CORER = 1,
+ I40E_RESET_GLOBR = 2,
+ I40E_RESET_EMPR = 3,
+};
+
+/* IEEE 802.1AB LLDP Agent Variables from NVM */
+#define I40E_NVM_LLDP_CFG_PTR 0xF
+struct i40e_lldp_variables {
+ u16 length;
+ u16 adminstatus;
+ u16 msgfasttx;
+ u16 msgtxinterval;
+ u16 txparams;
+ u16 timers;
+ u16 crc8;
+};
+
+#endif /* _I40E_TYPE_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h
new file mode 100644
index 0000000..cc6654f
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h
@@ -0,0 +1,368 @@
+/*******************************************************************************
+ *
+ * Intel Ethernet Controller XL710 Family Linux Driver
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ ******************************************************************************/
+
+#ifndef _I40E_VIRTCHNL_H_
+#define _I40E_VIRTCHNL_H_
+
+#include "i40e_type.h"
+
+/* Description:
+ * This header file describes the VF-PF communication protocol used
+ * by the various i40e drivers.
+ *
+ * Admin queue buffer usage:
+ * desc->opcode is always i40e_aqc_opc_send_msg_to_pf
+ * flags, retval, datalen, and data addr are all used normally.
+ * Firmware copies the cookie fields when sending messages between the PF and
+ * VF, but uses all other fields internally. Due to this limitation, we
+ * must send all messages as "indirect", i.e. using an external buffer.
+ *
+ * All the vsi indexes are relative to the VF. Each VF can have maximum of
+ * three VSIs. All the queue indexes are relative to the VSI. Each VF can
+ * have a maximum of sixteen queues for all of its VSIs.
+ *
+ * The PF is required to return a status code in v_retval for all messages
+ * except RESET_VF, which does not require any response. The return value is of
+ * i40e_status_code type, defined in the i40e_type.h.
+ *
+ * In general, VF driver initialization should roughly follow the order of these
+ * opcodes. The VF driver must first validate the API version of the PF driver,
+ * then request a reset, then get resources, then configure queues and
+ * interrupts. After these operations are complete, the VF driver may start
+ * its queues, optionally add MAC and VLAN filters, and process traffic.
+ */
+
+/* Opcodes for VF-PF communication. These are placed in the v_opcode field
+ * of the virtchnl_msg structure.
+ */
+enum i40e_virtchnl_ops {
+/* VF sends req. to pf for the following
+ * ops.
+ */
+ I40E_VIRTCHNL_OP_UNKNOWN = 0,
+ I40E_VIRTCHNL_OP_VERSION = 1, /* must ALWAYS be 1 */
+ I40E_VIRTCHNL_OP_RESET_VF,
+ I40E_VIRTCHNL_OP_GET_VF_RESOURCES,
+ I40E_VIRTCHNL_OP_CONFIG_TX_QUEUE,
+ I40E_VIRTCHNL_OP_CONFIG_RX_QUEUE,
+ I40E_VIRTCHNL_OP_CONFIG_VSI_QUEUES,
+ I40E_VIRTCHNL_OP_CONFIG_IRQ_MAP,
+ I40E_VIRTCHNL_OP_ENABLE_QUEUES,
+ I40E_VIRTCHNL_OP_DISABLE_QUEUES,
+ I40E_VIRTCHNL_OP_ADD_ETHER_ADDRESS,
+ I40E_VIRTCHNL_OP_DEL_ETHER_ADDRESS,
+ I40E_VIRTCHNL_OP_ADD_VLAN,
+ I40E_VIRTCHNL_OP_DEL_VLAN,
+ I40E_VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE,
+ I40E_VIRTCHNL_OP_GET_STATS,
+ I40E_VIRTCHNL_OP_FCOE,
+/* PF sends status change events to vfs using
+ * the following op.
+ */
+ I40E_VIRTCHNL_OP_EVENT,
+};
+
+/* Virtual channel message descriptor. This overlays the admin queue
+ * descriptor. All other data is passed in external buffers.
+ */
+
+struct i40e_virtchnl_msg {
+ u8 pad[8]; /* AQ flags/opcode/len/retval fields */
+ enum i40e_virtchnl_ops v_opcode; /* avoid confusion with desc->opcode */
+ i40e_status v_retval; /* ditto for desc->retval */
+ u32 vfid; /* used by PF when sending to VF */
+};
+
+/* Message descriptions and data structures.*/
+
+/* I40E_VIRTCHNL_OP_VERSION
+ * VF posts its version number to the PF. PF responds with its version number
+ * in the same format, along with a return code.
+ * Reply from PF has its major/minor versions also in param0 and param1.
+ * If there is a major version mismatch, then the VF cannot operate.
+ * If there is a minor version mismatch, then the VF can operate but should
+ * add a warning to the system log.
+ *
+ * This enum element MUST always be specified as == 1, regardless of other
+ * changes in the API. The PF must always respond to this message without
+ * error regardless of version mismatch.
+ */
+#define I40E_VIRTCHNL_VERSION_MAJOR 1
+#define I40E_VIRTCHNL_VERSION_MINOR 0
+struct i40e_virtchnl_version_info {
+ u32 major;
+ u32 minor;
+};
+
+/* I40E_VIRTCHNL_OP_RESET_VF
+ * VF sends this request to PF with no parameters
+ * PF does NOT respond! VF driver must delay then poll VFGEN_RSTAT register
+ * until reset completion is indicated. The admin queue must be reinitialized
+ * after this operation.
+ *
+ * When reset is complete, PF must ensure that all queues in all VSIs associated
+ * with the VF are stopped, all queue configurations in the HMC are set to 0,
+ * and all MAC and VLAN filters (except the default MAC address) on all VSIs
+ * are cleared.
+ */
+
+/* I40E_VIRTCHNL_OP_GET_VF_RESOURCES
+ * VF sends this request to PF with no parameters
+ * PF responds with an indirect message containing
+ * i40e_virtchnl_vf_resource and one or more
+ * i40e_virtchnl_vsi_resource structures.
+ */
+
+struct i40e_virtchnl_vsi_resource {
+ u16 vsi_id;
+ u16 num_queue_pairs;
+ enum i40e_vsi_type vsi_type;
+ u16 qset_handle;
+ u8 default_mac_addr[I40E_ETH_LENGTH_OF_ADDRESS];
+};
+/* VF offload flags */
+#define I40E_VIRTCHNL_VF_OFFLOAD_L2 0x00000001
+#define I40E_VIRTCHNL_VF_OFFLOAD_FCOE 0x00000004
+#define I40E_VIRTCHNL_VF_OFFLOAD_VLAN 0x00010000
+
+struct i40e_virtchnl_vf_resource {
+ u16 num_vsis;
+ u16 num_queue_pairs;
+ u16 max_vectors;
+ u16 max_mtu;
+
+ u32 vf_offload_flags;
+ u32 max_fcoe_contexts;
+ u32 max_fcoe_filters;
+
+ struct i40e_virtchnl_vsi_resource vsi_res[1];
+};
+
+/* I40E_VIRTCHNL_OP_CONFIG_TX_QUEUE
+ * VF sends this message to set up parameters for one TX queue.
+ * External data buffer contains one instance of i40e_virtchnl_txq_info.
+ * PF configures requested queue and returns a status code.
+ */
+
+/* Tx queue config info */
+struct i40e_virtchnl_txq_info {
+ u16 vsi_id;
+ u16 queue_id;
+ u16 ring_len; /* number of descriptors, multiple of 8 */
+ u16 headwb_enabled;
+ u64 dma_ring_addr;
+ u64 dma_headwb_addr;
+};
+
+/* I40E_VIRTCHNL_OP_CONFIG_RX_QUEUE
+ * VF sends this message to set up parameters for one RX queue.
+ * External data buffer contains one instance of i40e_virtchnl_rxq_info.
+ * PF configures requested queue and returns a status code.
+ */
+
+/* Rx queue config info */
+struct i40e_virtchnl_rxq_info {
+ u16 vsi_id;
+ u16 queue_id;
+ u32 ring_len; /* number of descriptors, multiple of 32 */
+ u16 hdr_size;
+ u16 splithdr_enabled;
+ u32 databuffer_size;
+ u32 max_pkt_size;
+ u64 dma_ring_addr;
+ enum i40e_hmc_obj_rx_hsplit_0 rx_split_pos;
+};
+
+/* I40E_VIRTCHNL_OP_CONFIG_VSI_QUEUES
+ * VF sends this message to set parameters for all active TX and RX queues
+ * associated with the specified VSI.
+ * PF configures queues and returns status.
+ * If the number of queues specified is greater than the number of queues
+ * associated with the VSI, an error is returned and no queues are configured.
+ */
+struct i40e_virtchnl_queue_pair_info {
+ /* NOTE: vsi_id and queue_id should be identical for both queues. */
+ struct i40e_virtchnl_txq_info txq;
+ struct i40e_virtchnl_rxq_info rxq;
+};
+
+struct i40e_virtchnl_vsi_queue_config_info {
+ u16 vsi_id;
+ u16 num_queue_pairs;
+ struct i40e_virtchnl_queue_pair_info qpair[1];
+};
+
+/* I40E_VIRTCHNL_OP_CONFIG_IRQ_MAP
+ * VF uses this message to map vectors to queues.
+ * The rxq_map and txq_map fields are bitmaps used to indicate which queues
+ * are to be associated with the specified vector.
+ * The "other" causes are always mapped to vector 0.
+ * PF configures interrupt mapping and returns status.
+ */
+struct i40e_virtchnl_vector_map {
+ u16 vsi_id;
+ u16 vector_id;
+ u16 rxq_map;
+ u16 txq_map;
+ u16 rxitr_idx;
+ u16 txitr_idx;
+};
+
+struct i40e_virtchnl_irq_map_info {
+ u16 num_vectors;
+ struct i40e_virtchnl_vector_map vecmap[1];
+};
+
+/* I40E_VIRTCHNL_OP_ENABLE_QUEUES
+ * I40E_VIRTCHNL_OP_DISABLE_QUEUES
+ * VF sends these message to enable or disable TX/RX queue pairs.
+ * The queues fields are bitmaps indicating which queues to act upon.
+ * (Currently, we only support 16 queues per VF, but we make the field
+ * u32 to allow for expansion.)
+ * PF performs requested action and returns status.
+ */
+struct i40e_virtchnl_queue_select {
+ u16 vsi_id;
+ u16 pad;
+ u32 rx_queues;
+ u32 tx_queues;
+};
+
+/* I40E_VIRTCHNL_OP_ADD_ETHER_ADDRESS
+ * VF sends this message in order to add one or more unicast or multicast
+ * address filters for the specified VSI.
+ * PF adds the filters and returns status.
+ */
+
+/* I40E_VIRTCHNL_OP_DEL_ETHER_ADDRESS
+ * VF sends this message in order to remove one or more unicast or multicast
+ * filters for the specified VSI.
+ * PF removes the filters and returns status.
+ */
+
+struct i40e_virtchnl_ether_addr {
+ u8 addr[I40E_ETH_LENGTH_OF_ADDRESS];
+ u8 pad[2];
+};
+
+struct i40e_virtchnl_ether_addr_list {
+ u16 vsi_id;
+ u16 num_elements;
+ struct i40e_virtchnl_ether_addr list[1];
+};
+
+/* I40E_VIRTCHNL_OP_ADD_VLAN
+ * VF sends this message to add one or more VLAN tag filters for receives.
+ * PF adds the filters and returns status.
+ * If a port VLAN is configured by the PF, this operation will return an
+ * error to the VF.
+ */
+
+/* I40E_VIRTCHNL_OP_DEL_VLAN
+ * VF sends this message to remove one or more VLAN tag filters for receives.
+ * PF removes the filters and returns status.
+ * If a port VLAN is configured by the PF, this operation will return an
+ * error to the VF.
+ */
+
+struct i40e_virtchnl_vlan_filter_list {
+ u16 vsi_id;
+ u16 num_elements;
+ u16 vlan_id[1];
+};
+
+/* I40E_VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE
+ * VF sends VSI id and flags.
+ * PF returns status code in retval.
+ * Note: we assume that broadcast accept mode is always enabled.
+ */
+struct i40e_virtchnl_promisc_info {
+ u16 vsi_id;
+ u16 flags;
+};
+
+#define I40E_FLAG_VF_UNICAST_PROMISC 0x00000001
+#define I40E_FLAG_VF_MULTICAST_PROMISC 0x00000002
+
+/* I40E_VIRTCHNL_OP_GET_STATS
+ * VF sends this message to request stats for the selected VSI. VF uses
+ * the i40e_virtchnl_queue_select struct to specify the VSI. The queue_id
+ * field is ignored by the PF.
+ *
+ * PF replies with struct i40e_eth_stats in an external buffer.
+ */
+
+/* I40E_VIRTCHNL_OP_EVENT
+ * PF sends this message to inform the VF driver of events that may affect it.
+ * No direct response is expected from the VF, though it may generate other
+ * messages in response to this one.
+ */
+enum i40e_virtchnl_event_codes {
+ I40E_VIRTCHNL_EVENT_UNKNOWN = 0,
+ I40E_VIRTCHNL_EVENT_LINK_CHANGE,
+ I40E_VIRTCHNL_EVENT_RESET_IMPENDING,
+ I40E_VIRTCHNL_EVENT_PF_DRIVER_CLOSE,
+};
+#define I40E_PF_EVENT_SEVERITY_INFO 0
+#define I40E_PF_EVENT_SEVERITY_CERTAIN_DOOM 255
+
+struct i40e_virtchnl_pf_event {
+ enum i40e_virtchnl_event_codes event;
+ union {
+ struct {
+ enum i40e_aq_link_speed link_speed;
+ bool link_status;
+ } link_event;
+ } event_data;
+
+ int severity;
+};
+
+/* The following are TBD, not necessary for LAN functionality.
+ * I40E_VIRTCHNL_OP_FCOE
+ */
+
+/* VF reset states - these are written into the RSTAT register:
+ * I40E_VFGEN_RSTAT1 on the PF
+ * I40E_VFGEN_RSTAT on the VF
+ * When the PF initiates a reset, it writes 0
+ * When the reset is complete, it writes 1
+ * When the PF detects that the VF has recovered, it writes 2
+ * VF checks this register periodically to determine if a reset has occurred,
+ * then polls it to know when the reset is complete.
+ * If either the PF or VF reads the register while the hardware
+ * is in a reset state, it will return DEADBEEF, which, when masked
+ * will result in 3.
+ */
+enum i40e_vfr_states {
+ I40E_VFR_INPROGRESS = 0,
+ I40E_VFR_COMPLETED,
+ I40E_VFR_VFACTIVE,
+ I40E_VFR_UNKNOWN,
+};
+
+#endif /* _I40E_VIRTCHNL_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
new file mode 100644
index 0000000..8967e58
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -0,0 +1,2335 @@
+/*******************************************************************************
+ *
+ * Intel Ethernet Controller XL710 Family Linux Driver
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ ******************************************************************************/
+
+#include "i40e.h"
+
+/***********************misc routines*****************************/
+
+/**
+ * i40e_vc_isvalid_vsi_id
+ * @vf: pointer to the vf info
+ * @vsi_id: vf relative vsi id
+ *
+ * check for the valid vsi id
+ **/
+static inline bool i40e_vc_isvalid_vsi_id(struct i40e_vf *vf, u8 vsi_id)
+{
+ struct i40e_pf *pf = vf->pf;
+
+ return pf->vsi[vsi_id]->vf_id == vf->vf_id;
+}
+
+/**
+ * i40e_vc_isvalid_queue_id
+ * @vf: pointer to the vf info
+ * @vsi_id: vsi id
+ * @qid: vsi relative queue id
+ *
+ * check for the valid queue id
+ **/
+static inline bool i40e_vc_isvalid_queue_id(struct i40e_vf *vf, u8 vsi_id,
+ u8 qid)
+{
+ struct i40e_pf *pf = vf->pf;
+
+ return qid < pf->vsi[vsi_id]->num_queue_pairs;
+}
+
+/**
+ * i40e_vc_isvalid_vector_id
+ * @vf: pointer to the vf info
+ * @vector_id: vf relative vector id
+ *
+ * check for the valid vector id
+ **/
+static inline bool i40e_vc_isvalid_vector_id(struct i40e_vf *vf, u8 vector_id)
+{
+ struct i40e_pf *pf = vf->pf;
+
+ return vector_id < pf->hw.func_caps.num_msix_vectors_vf;
+}
+
+/***********************vf resource mgmt routines*****************/
+
+/**
+ * i40e_vc_get_pf_queue_id
+ * @vf: pointer to the vf info
+ * @vsi_idx: index of VSI in PF struct
+ * @vsi_queue_id: vsi relative queue id
+ *
+ * return pf relative queue id
+ **/
+static u16 i40e_vc_get_pf_queue_id(struct i40e_vf *vf, u8 vsi_idx,
+ u8 vsi_queue_id)
+{
+ struct i40e_pf *pf = vf->pf;
+ struct i40e_vsi *vsi = pf->vsi[vsi_idx];
+ u16 pf_queue_id = I40E_QUEUE_END_OF_LIST;
+
+ if (le16_to_cpu(vsi->info.mapping_flags) &
+ I40E_AQ_VSI_QUE_MAP_NONCONTIG)
+ pf_queue_id =
+ le16_to_cpu(vsi->info.queue_mapping[vsi_queue_id]);
+ else
+ pf_queue_id = le16_to_cpu(vsi->info.queue_mapping[0]) +
+ vsi_queue_id;
+
+ return pf_queue_id;
+}
+
+/**
+ * i40e_ctrl_vsi_tx_queue
+ * @vf: pointer to the vf info
+ * @vsi_idx: index of VSI in PF struct
+ * @vsi_queue_id: vsi relative queue index
+ * @ctrl: control flags
+ *
+ * enable/disable/enable check/disable check
+ **/
+static int i40e_ctrl_vsi_tx_queue(struct i40e_vf *vf, u16 vsi_idx,
+ u16 vsi_queue_id,
+ enum i40e_queue_ctrl ctrl)
+{
+ struct i40e_pf *pf = vf->pf;
+ struct i40e_hw *hw = &pf->hw;
+ bool writeback = false;
+ u16 pf_queue_id;
+ int ret = 0;
+ u32 reg;
+
+ pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_idx, vsi_queue_id);
+ reg = rd32(hw, I40E_QTX_ENA(pf_queue_id));
+
+ switch (ctrl) {
+ case I40E_QUEUE_CTRL_ENABLE:
+ reg |= I40E_QTX_ENA_QENA_REQ_MASK;
+ writeback = true;
+ break;
+ case I40E_QUEUE_CTRL_ENABLECHECK:
+ ret = (reg & I40E_QTX_ENA_QENA_STAT_MASK) ? 0 : -EPERM;
+ break;
+ case I40E_QUEUE_CTRL_DISABLE:
+ reg &= ~I40E_QTX_ENA_QENA_REQ_MASK;
+ writeback = true;
+ break;
+ case I40E_QUEUE_CTRL_DISABLECHECK:
+ ret = (reg & I40E_QTX_ENA_QENA_STAT_MASK) ? -EPERM : 0;
+ break;
+ case I40E_QUEUE_CTRL_FASTDISABLE:
+ reg |= I40E_QTX_ENA_FAST_QDIS_MASK;
+ writeback = true;
+ break;
+ case I40E_QUEUE_CTRL_FASTDISABLECHECK:
+ ret = (reg & I40E_QTX_ENA_QENA_STAT_MASK) ? -EPERM : 0;
+ if (!ret) {
+ reg &= ~I40E_QTX_ENA_FAST_QDIS_MASK;
+ writeback = true;
+ }
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+ if (writeback) {
+ wr32(hw, I40E_QTX_ENA(pf_queue_id), reg);
+ i40e_flush(hw);
+ }
+
+ return ret;
+}
+
+/**
+ * i40e_ctrl_vsi_rx_queue
+ * @vf: pointer to the vf info
+ * @vsi_idx: index of VSI in PF struct
+ * @vsi_queue_id: vsi relative queue index
+ * @ctrl: control flags
+ *
+ * enable/disable/enable check/disable check
+ **/
+static int i40e_ctrl_vsi_rx_queue(struct i40e_vf *vf, u16 vsi_idx,
+ u16 vsi_queue_id,
+ enum i40e_queue_ctrl ctrl)
+{
+ struct i40e_pf *pf = vf->pf;
+ struct i40e_hw *hw = &pf->hw;
+ bool writeback = false;
+ u16 pf_queue_id;
+ int ret = 0;
+ u32 reg;
+
+ pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_idx, vsi_queue_id);
+ reg = rd32(hw, I40E_QRX_ENA(pf_queue_id));
+
+ switch (ctrl) {
+ case I40E_QUEUE_CTRL_ENABLE:
+ reg |= I40E_QRX_ENA_QENA_REQ_MASK;
+ writeback = true;
+ break;
+ case I40E_QUEUE_CTRL_ENABLECHECK:
+ ret = (reg & I40E_QRX_ENA_QENA_STAT_MASK) ? 0 : -EPERM;
+ break;
+ case I40E_QUEUE_CTRL_DISABLE:
+ reg &= ~I40E_QRX_ENA_QENA_REQ_MASK;
+ writeback = true;
+ break;
+ case I40E_QUEUE_CTRL_DISABLECHECK:
+ ret = (reg & I40E_QRX_ENA_QENA_STAT_MASK) ? -EPERM : 0;
+ break;
+ case I40E_QUEUE_CTRL_FASTDISABLE:
+ reg |= I40E_QRX_ENA_FAST_QDIS_MASK;
+ writeback = true;
+ break;
+ case I40E_QUEUE_CTRL_FASTDISABLECHECK:
+ ret = (reg & I40E_QRX_ENA_QENA_STAT_MASK) ? -EPERM : 0;
+ if (!ret) {
+ reg &= ~I40E_QRX_ENA_FAST_QDIS_MASK;
+ writeback = true;
+ }
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+ if (writeback) {
+ wr32(hw, I40E_QRX_ENA(pf_queue_id), reg);
+ i40e_flush(hw);
+ }
+
+ return ret;
+}
+
+/**
+ * i40e_config_irq_link_list
+ * @vf: pointer to the vf info
+ * @vsi_idx: index of VSI in PF struct
+ * @vecmap: irq map info
+ *
+ * configure irq link list from the map
+ **/
+static void i40e_config_irq_link_list(struct i40e_vf *vf, u16 vsi_idx,
+ struct i40e_virtchnl_vector_map *vecmap)
+{
+ unsigned long linklistmap = 0, tempmap;
+ struct i40e_pf *pf = vf->pf;
+ struct i40e_hw *hw = &pf->hw;
+ u16 vsi_queue_id, pf_queue_id;
+ enum i40e_queue_type qtype;
+ u16 next_q, vector_id;
+ u32 reg, reg_idx;
+ u16 itr_idx = 0;
+
+ vector_id = vecmap->vector_id;
+ /* setup the head */
+ if (0 == vector_id)
+ reg_idx = I40E_VPINT_LNKLST0(vf->vf_id);
+ else
+ reg_idx = I40E_VPINT_LNKLSTN(
+ ((pf->hw.func_caps.num_msix_vectors_vf - 1)
+ * vf->vf_id) + (vector_id - 1));
+
+ if (vecmap->rxq_map == 0 && vecmap->txq_map == 0) {
+ /* Special case - No queues mapped on this vector */
+ wr32(hw, reg_idx, I40E_VPINT_LNKLST0_FIRSTQ_INDX_MASK);
+ goto irq_list_done;
+ }
+ tempmap = vecmap->rxq_map;
+ vsi_queue_id = find_first_bit(&tempmap, I40E_MAX_VSI_QP);
+ while (vsi_queue_id < I40E_MAX_VSI_QP) {
+ linklistmap |= (1 <<
+ (I40E_VIRTCHNL_SUPPORTED_QTYPES *
+ vsi_queue_id));
+ vsi_queue_id =
+ find_next_bit(&tempmap, I40E_MAX_VSI_QP, vsi_queue_id + 1);
+ }
+
+ tempmap = vecmap->txq_map;
+ vsi_queue_id = find_first_bit(&tempmap, I40E_MAX_VSI_QP);
+ while (vsi_queue_id < I40E_MAX_VSI_QP) {
+ linklistmap |= (1 <<
+ (I40E_VIRTCHNL_SUPPORTED_QTYPES * vsi_queue_id
+ + 1));
+ vsi_queue_id = find_next_bit(&tempmap, I40E_MAX_VSI_QP,
+ vsi_queue_id + 1);
+ }
+
+ next_q = find_first_bit(&linklistmap,
+ (I40E_MAX_VSI_QP *
+ I40E_VIRTCHNL_SUPPORTED_QTYPES));
+ vsi_queue_id = next_q/I40E_VIRTCHNL_SUPPORTED_QTYPES;
+ qtype = next_q%I40E_VIRTCHNL_SUPPORTED_QTYPES;
+ pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_idx, vsi_queue_id);
+ reg = ((qtype << I40E_VPINT_LNKLSTN_FIRSTQ_TYPE_SHIFT) | pf_queue_id);
+
+ wr32(hw, reg_idx, reg);
+
+ while (next_q < (I40E_MAX_VSI_QP * I40E_VIRTCHNL_SUPPORTED_QTYPES)) {
+ switch (qtype) {
+ case I40E_QUEUE_TYPE_RX:
+ reg_idx = I40E_QINT_RQCTL(pf_queue_id);
+ itr_idx = vecmap->rxitr_idx;
+ break;
+ case I40E_QUEUE_TYPE_TX:
+ reg_idx = I40E_QINT_TQCTL(pf_queue_id);
+ itr_idx = vecmap->txitr_idx;
+ break;
+ default:
+ break;
+ }
+
+ next_q = find_next_bit(&linklistmap,
+ (I40E_MAX_VSI_QP *
+ I40E_VIRTCHNL_SUPPORTED_QTYPES),
+ next_q + 1);
+ if (next_q < (I40E_MAX_VSI_QP * I40E_VIRTCHNL_SUPPORTED_QTYPES)) {
+ vsi_queue_id = next_q / I40E_VIRTCHNL_SUPPORTED_QTYPES;
+ qtype = next_q % I40E_VIRTCHNL_SUPPORTED_QTYPES;
+ pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_idx,
+ vsi_queue_id);
+ } else {
+ pf_queue_id = I40E_QUEUE_END_OF_LIST;
+ qtype = 0;
+ }
+
+ /* format for the RQCTL & TQCTL regs is same */
+ reg = (vector_id) |
+ (qtype << I40E_QINT_RQCTL_NEXTQ_TYPE_SHIFT) |
+ (pf_queue_id << I40E_QINT_RQCTL_NEXTQ_INDX_SHIFT) |
+ (1 << I40E_QINT_RQCTL_CAUSE_ENA_SHIFT) |
+ (itr_idx << I40E_QINT_RQCTL_ITR_INDX_SHIFT);
+ wr32(hw, reg_idx, reg);
+ }
+
+irq_list_done:
+ i40e_flush(hw);
+}
+
+/**
+ * i40e_config_vsi_tx_queue
+ * @vf: pointer to the vf info
+ * @vsi_idx: index of VSI in PF struct
+ * @vsi_queue_id: vsi relative queue index
+ * @info: config. info
+ *
+ * configure tx queue
+ **/
+static int i40e_config_vsi_tx_queue(struct i40e_vf *vf, u16 vsi_idx,
+ u16 vsi_queue_id,
+ struct i40e_virtchnl_txq_info *info)
+{
+ struct i40e_pf *pf = vf->pf;
+ struct i40e_hw *hw = &pf->hw;
+ struct i40e_hmc_obj_txq tx_ctx;
+ u16 pf_queue_id;
+ u32 qtx_ctl;
+ int ret = 0;
+
+ pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_idx, vsi_queue_id);
+
+ /* clear the context structure first */
+ memset(&tx_ctx, 0, sizeof(struct i40e_hmc_obj_txq));
+
+ /* only set the required fields */
+ tx_ctx.base = info->dma_ring_addr / 128;
+ tx_ctx.qlen = info->ring_len;
+ tx_ctx.rdylist = le16_to_cpu(pf->vsi[vsi_idx]->info.qs_handle[0]);
+ tx_ctx.rdylist_act = 0;
+
+ /* clear the context in the HMC */
+ ret = i40e_clear_lan_tx_queue_context(hw, pf_queue_id);
+ if (ret) {
+ dev_err(&pf->pdev->dev,
+ "Failed to clear VF LAN Tx queue context %d, error: %d\n",
+ pf_queue_id, ret);
+ ret = -ENOENT;
+ goto error_context;
+ }
+
+ /* set the context in the HMC */
+ ret = i40e_set_lan_tx_queue_context(hw, pf_queue_id, &tx_ctx);
+ if (ret) {
+ dev_err(&pf->pdev->dev,
+ "Failed to set VF LAN Tx queue context %d error: %d\n",
+ pf_queue_id, ret);
+ ret = -ENOENT;
+ goto error_context;
+ }
+
+ /* associate this queue with the PCI VF function */
+ qtx_ctl = I40E_QTX_CTL_VF_QUEUE;
+ qtx_ctl |= ((hw->hmc.hmc_fn_id << I40E_QTX_CTL_PF_INDX_SHIFT)
+ & I40E_QTX_CTL_PF_INDX_MASK);
+ qtx_ctl |= (((vf->vf_id + hw->func_caps.vf_base_id)
+ << I40E_QTX_CTL_VFVM_INDX_SHIFT)
+ & I40E_QTX_CTL_VFVM_INDX_MASK);
+ wr32(hw, I40E_QTX_CTL(pf_queue_id), qtx_ctl);
+ i40e_flush(hw);
+
+error_context:
+ return ret;
+}
+
+/**
+ * i40e_config_vsi_rx_queue
+ * @vf: pointer to the vf info
+ * @vsi_idx: index of VSI in PF struct
+ * @vsi_queue_id: vsi relative queue index
+ * @info: config. info
+ *
+ * configure rx queue
+ **/
+static int i40e_config_vsi_rx_queue(struct i40e_vf *vf, u16 vsi_idx,
+ u16 vsi_queue_id,
+ struct i40e_virtchnl_rxq_info *info)
+{
+ struct i40e_pf *pf = vf->pf;
+ struct i40e_hw *hw = &pf->hw;
+ struct i40e_hmc_obj_rxq rx_ctx;
+ u16 pf_queue_id;
+ int ret = 0;
+
+ pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_idx, vsi_queue_id);
+
+ /* clear the context structure first */
+ memset(&rx_ctx, 0, sizeof(struct i40e_hmc_obj_rxq));
+
+ /* only set the required fields */
+ rx_ctx.base = info->dma_ring_addr / 128;
+ rx_ctx.qlen = info->ring_len;
+
+ if (info->splithdr_enabled) {
+ rx_ctx.hsplit_0 = I40E_RX_SPLIT_L2 |
+ I40E_RX_SPLIT_IP |
+ I40E_RX_SPLIT_TCP_UDP |
+ I40E_RX_SPLIT_SCTP;
+ /* header length validation */
+ if (info->hdr_size > ((2 * 1024) - 64)) {
+ ret = -EINVAL;
+ goto error_param;
+ }
+ rx_ctx.hbuff = info->hdr_size >> I40E_RXQ_CTX_HBUFF_SHIFT;
+
+ /* set splitalways mode 10b */
+ rx_ctx.dtype = 0x2;
+ }
+
+ /* databuffer length validation */
+ if (info->databuffer_size > ((16 * 1024) - 128)) {
+ ret = -EINVAL;
+ goto error_param;
+ }
+ rx_ctx.dbuff = info->databuffer_size >> I40E_RXQ_CTX_DBUFF_SHIFT;
+
+ /* max pkt. length validation */
+ if (info->max_pkt_size >= (16 * 1024) || info->max_pkt_size < 64) {
+ ret = -EINVAL;
+ goto error_param;
+ }
+ rx_ctx.rxmax = info->max_pkt_size;
+
+ /* enable 32bytes desc always */
+ rx_ctx.dsize = 1;
+
+ /* default values */
+ rx_ctx.tphrdesc_ena = 1;
+ rx_ctx.tphwdesc_ena = 1;
+ rx_ctx.tphdata_ena = 1;
+ rx_ctx.tphhead_ena = 1;
+ rx_ctx.lrxqthresh = 2;
+ rx_ctx.crcstrip = 1;
+
+ /* clear the context in the HMC */
+ ret = i40e_clear_lan_rx_queue_context(hw, pf_queue_id);
+ if (ret) {
+ dev_err(&pf->pdev->dev,
+ "Failed to clear VF LAN Rx queue context %d, error: %d\n",
+ pf_queue_id, ret);
+ ret = -ENOENT;
+ goto error_param;
+ }
+
+ /* set the context in the HMC */
+ ret = i40e_set_lan_rx_queue_context(hw, pf_queue_id, &rx_ctx);
+ if (ret) {
+ dev_err(&pf->pdev->dev,
+ "Failed to set VF LAN Rx queue context %d error: %d\n",
+ pf_queue_id, ret);
+ ret = -ENOENT;
+ goto error_param;
+ }
+
+error_param:
+ return ret;
+}
+
+/**
+ * i40e_alloc_vsi_res
+ * @vf: pointer to the vf info
+ * @type: type of VSI to allocate
+ *
+ * alloc vf vsi context & resources
+ **/
+static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type)
+{
+ struct i40e_mac_filter *f = NULL;
+ struct i40e_pf *pf = vf->pf;
+ struct i40e_hw *hw = &pf->hw;
+ struct i40e_vsi *vsi;
+ int ret = 0;
+
+ vsi = i40e_vsi_setup(pf, type, pf->vsi[pf->lan_vsi]->seid, vf->vf_id);
+
+ if (!vsi) {
+ dev_err(&pf->pdev->dev,
+ "add vsi failed for vf %d, aq_err %d\n",
+ vf->vf_id, pf->hw.aq.asq_last_status);
+ ret = -ENOENT;
+ goto error_alloc_vsi_res;
+ }
+ if (type == I40E_VSI_SRIOV) {
+ vf->lan_vsi_index = vsi->idx;
+ vf->lan_vsi_id = vsi->id;
+ dev_info(&pf->pdev->dev,
+ "LAN VSI index %d, VSI id %d\n",
+ vsi->idx, vsi->id);
+ f = i40e_add_filter(vsi, vf->default_lan_addr.addr,
+ 0, true, false);
+ }
+ if (!f) {
+ dev_err(&pf->pdev->dev, "Unable to add ucast filter\n");
+ ret = -ENOMEM;
+ goto error_alloc_vsi_res;
+ }
+
+ /* program mac filter */
+ ret = i40e_sync_vsi_filters(vsi);
+ if (ret) {
+ dev_err(&pf->pdev->dev, "Unable to program ucast filters\n");
+ goto error_alloc_vsi_res;
+ }
+
+ /* accept bcast pkts. by default */
+ ret = i40e_aq_set_vsi_broadcast(hw, vsi->seid, true, NULL);
+ if (ret) {
+ dev_err(&pf->pdev->dev,
+ "set vsi bcast failed for vf %d, vsi %d, aq_err %d\n",
+ vf->vf_id, vsi->idx, pf->hw.aq.asq_last_status);
+ ret = -EINVAL;
+ }
+
+error_alloc_vsi_res:
+ return ret;
+}
+
+/**
+ * i40e_reset_vf
+ * @vf: pointer to the vf structure
+ * @flr: VFLR was issued or not
+ *
+ * reset the vf
+ **/
+int i40e_reset_vf(struct i40e_vf *vf, bool flr)
+{
+ int ret = -ENOENT;
+ struct i40e_pf *pf = vf->pf;
+ struct i40e_hw *hw = &pf->hw;
+ u32 reg, reg_idx, msix_vf;
+ bool rsd = false;
+ u16 pf_queue_id;
+ int i, j;
+
+ /* warn the VF */
+ wr32(hw, I40E_VFGEN_RSTAT1(vf->vf_id), I40E_VFR_INPROGRESS);
+
+ clear_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states);
+
+ /* PF triggers VFR only when VF requests, in case of
+ * VFLR, HW triggers VFR
+ */
+ if (!flr) {
+ /* reset vf using VPGEN_VFRTRIG reg */
+ reg = I40E_VPGEN_VFRTRIG_VFSWR_MASK;
+ wr32(hw, I40E_VPGEN_VFRTRIG(vf->vf_id), reg);
+ i40e_flush(hw);
+ }
+
+ /* poll VPGEN_VFRSTAT reg to make sure
+ * that reset is complete
+ */
+ for (i = 0; i < 4; i++) {
+ /* vf reset requires driver to first reset the
+ * vf & than poll the status register to make sure
+ * that the requested op was completed
+ * successfully
+ */
+ udelay(10);
+ reg = rd32(hw, I40E_VPGEN_VFRSTAT(vf->vf_id));
+ if (reg & I40E_VPGEN_VFRSTAT_VFRD_MASK) {
+ rsd = true;
+ break;
+ }
+ }
+
+ if (!rsd)
+ dev_err(&pf->pdev->dev, "VF reset check timeout %d\n",
+ vf->vf_id);
+
+ /* fast disable qps */
+ for (j = 0; j < pf->vsi[vf->lan_vsi_index]->num_queue_pairs; j++) {
+ ret = i40e_ctrl_vsi_tx_queue(vf, vf->lan_vsi_index, j,
+ I40E_QUEUE_CTRL_FASTDISABLE);
+ ret = i40e_ctrl_vsi_rx_queue(vf, vf->lan_vsi_index, j,
+ I40E_QUEUE_CTRL_FASTDISABLE);
+ }
+
+ /* Queue enable/disable requires driver to
+ * first reset the vf & than poll the status register
+ * to make sure that the requested op was completed
+ * successfully
+ */
+ udelay(10);
+ for (j = 0; j < pf->vsi[vf->lan_vsi_index]->num_queue_pairs; j++) {
+ ret = i40e_ctrl_vsi_tx_queue(vf, vf->lan_vsi_index, j,
+ I40E_QUEUE_CTRL_FASTDISABLECHECK);
+ if (ret)
+ dev_info(&pf->pdev->dev,
+ "Queue control check failed on Tx queue %d of VSI %d VF %d\n",
+ vf->lan_vsi_index, j, vf->vf_id);
+ ret = i40e_ctrl_vsi_rx_queue(vf, vf->lan_vsi_index, j,
+ I40E_QUEUE_CTRL_FASTDISABLECHECK);
+ if (ret)
+ dev_info(&pf->pdev->dev,
+ "Queue control check failed on Rx queue %d of VSI %d VF %d\n",
+ vf->lan_vsi_index, j, vf->vf_id);
+ }
+
+ /* clear the irq settings */
+ msix_vf = pf->hw.func_caps.num_msix_vectors_vf;
+ for (i = 0; i < msix_vf; i++) {
+ /* format is same for both registers */
+ if (0 == i)
+ reg_idx = I40E_VPINT_LNKLST0(vf->vf_id);
+ else
+ reg_idx = I40E_VPINT_LNKLSTN(((msix_vf - 1) *
+ (vf->vf_id))
+ + (i - 1));
+ reg = (I40E_VPINT_LNKLSTN_FIRSTQ_TYPE_MASK |
+ I40E_VPINT_LNKLSTN_FIRSTQ_INDX_MASK);
+ wr32(hw, reg_idx, reg);
+ i40e_flush(hw);
+ }
+ /* disable interrupts so the VF starts in a known state */
+ for (i = 0; i < msix_vf; i++) {
+ /* format is same for both registers */
+ if (0 == i)
+ reg_idx = I40E_VFINT_DYN_CTL0(vf->vf_id);
+ else
+ reg_idx = I40E_VFINT_DYN_CTLN(((msix_vf - 1) *
+ (vf->vf_id))
+ + (i - 1));
+ wr32(hw, reg_idx, I40E_VFINT_DYN_CTLN_CLEARPBA_MASK);
+ i40e_flush(hw);
+ }
+
+ /* set the defaults for the rqctl & tqctl registers */
+ reg = (I40E_QINT_RQCTL_NEXTQ_INDX_MASK | I40E_QINT_RQCTL_ITR_INDX_MASK |
+ I40E_QINT_RQCTL_NEXTQ_TYPE_MASK);
+ for (j = 0; j < pf->vsi[vf->lan_vsi_index]->num_queue_pairs; j++) {
+ pf_queue_id = i40e_vc_get_pf_queue_id(vf, vf->lan_vsi_index, j);
+ wr32(hw, I40E_QINT_RQCTL(pf_queue_id), reg);
+ wr32(hw, I40E_QINT_TQCTL(pf_queue_id), reg);
+ }
+
+ /* clear the reset bit in the VPGEN_VFRTRIG reg */
+ reg = rd32(hw, I40E_VPGEN_VFRTRIG(vf->vf_id));
+ reg &= ~I40E_VPGEN_VFRTRIG_VFSWR_MASK;
+ wr32(hw, I40E_VPGEN_VFRTRIG(vf->vf_id), reg);
+ /* tell the VF the reset is done */
+ wr32(hw, I40E_VFGEN_RSTAT1(vf->vf_id), I40E_VFR_COMPLETED);
+ i40e_flush(hw);
+
+ return ret;
+}
+
+/**
+ * i40e_enable_vf_mappings
+ * @vf: pointer to the vf info
+ *
+ * enable vf mappings
+ **/
+static void i40e_enable_vf_mappings(struct i40e_vf *vf)
+{
+ struct i40e_pf *pf = vf->pf;
+ struct i40e_hw *hw = &pf->hw;
+ u32 reg, total_queue_pairs = 0;
+ int j;
+
+ /* Tell the hardware we're using noncontiguous mapping. HW requires
+ * that VF queues be mapped using this method, even when they are
+ * contiguous in real life
+ */
+ wr32(hw, I40E_VSILAN_QBASE(vf->lan_vsi_id),
+ I40E_VSILAN_QBASE_VSIQTABLE_ENA_MASK);
+
+ /* enable VF vplan_qtable mappings */
+ reg = I40E_VPLAN_MAPENA_TXRX_ENA_MASK;
+ wr32(hw, I40E_VPLAN_MAPENA(vf->vf_id), reg);
+
+ /* map PF queues to VF queues */
+ for (j = 0; j < pf->vsi[vf->lan_vsi_index]->num_queue_pairs; j++) {
+ u16 qid = i40e_vc_get_pf_queue_id(vf, vf->lan_vsi_index, j);
+ reg = (qid & I40E_VPLAN_QTABLE_QINDEX_MASK);
+ wr32(hw, I40E_VPLAN_QTABLE(total_queue_pairs, vf->vf_id), reg);
+ total_queue_pairs++;
+ }
+
+ /* map PF queues to VSI */
+ for (j = 0; j < 7; j++) {
+ if (j * 2 >= pf->vsi[vf->lan_vsi_index]->num_queue_pairs) {
+ reg = 0x07FF07FF; /* unused */
+ } else {
+ u16 qid = i40e_vc_get_pf_queue_id(vf, vf->lan_vsi_index,
+ j * 2);
+ reg = qid;
+ qid = i40e_vc_get_pf_queue_id(vf, vf->lan_vsi_index,
+ (j * 2) + 1);
+ reg |= qid << 16;
+ }
+ wr32(hw, I40E_VSILAN_QTABLE(j, vf->lan_vsi_id), reg);
+ }
+
+ i40e_flush(hw);
+}
+
+/**
+ * i40e_disable_vf_mappings
+ * @vf: pointer to the vf info
+ *
+ * disable vf mappings
+ **/
+static void i40e_disable_vf_mappings(struct i40e_vf *vf)
+{
+ struct i40e_pf *pf = vf->pf;
+ struct i40e_hw *hw = &pf->hw;
+ int i;
+
+ /* disable qp mappings */
+ wr32(hw, I40E_VPLAN_MAPENA(vf->vf_id), 0);
+ for (i = 0; i < I40E_MAX_VSI_QP; i++)
+ wr32(hw, I40E_VPLAN_QTABLE(i, vf->vf_id),
+ I40E_QUEUE_END_OF_LIST);
+ i40e_flush(hw);
+}
+
+/**
+ * i40e_free_vf_res
+ * @vf: pointer to the vf info
+ *
+ * free vf resources
+ **/
+static void i40e_free_vf_res(struct i40e_vf *vf)
+{
+ struct i40e_pf *pf = vf->pf;
+
+ /* free vsi & disconnect it from the parent uplink */
+ if (vf->lan_vsi_index) {
+ i40e_vsi_release(pf->vsi[vf->lan_vsi_index]);
+ vf->lan_vsi_index = 0;
+ vf->lan_vsi_id = 0;
+ }
+ /* reset some of the state varibles keeping
+ * track of the resources
+ */
+ vf->num_queue_pairs = 0;
+ vf->vf_states = 0;
+}
+
+/**
+ * i40e_alloc_vf_res
+ * @vf: pointer to the vf info
+ *
+ * allocate vf resources
+ **/
+static int i40e_alloc_vf_res(struct i40e_vf *vf)
+{
+ struct i40e_pf *pf = vf->pf;
+ int total_queue_pairs = 0;
+ int ret;
+
+ /* allocate hw vsi context & associated resources */
+ ret = i40e_alloc_vsi_res(vf, I40E_VSI_SRIOV);
+ if (ret)
+ goto error_alloc;
+ total_queue_pairs += pf->vsi[vf->lan_vsi_index]->num_queue_pairs;
+ set_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps);
+
+ /* store the total qps number for the runtime
+ * vf req validation
+ */
+ vf->num_queue_pairs = total_queue_pairs;
+
+ /* vf is now completely initialized */
+ set_bit(I40E_VF_STAT_INIT, &vf->vf_states);
+
+error_alloc:
+ if (ret)
+ i40e_free_vf_res(vf);
+
+ return ret;
+}
+
+/**
+ * i40e_vfs_are_assigned
+ * @pf: pointer to the pf structure
+ *
+ * Determine if any VFs are assigned to VMs
+ **/
+static bool i40e_vfs_are_assigned(struct i40e_pf *pf)
+{
+ struct pci_dev *pdev = pf->pdev;
+ struct pci_dev *vfdev;
+
+ /* loop through all the VFs to see if we own any that are assigned */
+ vfdev = pci_get_device(PCI_VENDOR_ID_INTEL, I40E_VF_DEVICE_ID , NULL);
+ while (vfdev) {
+ /* if we don't own it we don't care */
+ if (vfdev->is_virtfn && pci_physfn(vfdev) == pdev) {
+ /* if it is assigned we cannot release it */
+ if (vfdev->dev_flags & PCI_DEV_FLAGS_ASSIGNED)
+ return true;
+ }
+
+ vfdev = pci_get_device(PCI_VENDOR_ID_INTEL,
+ I40E_VF_DEVICE_ID,
+ vfdev);
+ }
+
+ return false;
+}
+
+/**
+ * i40e_free_vfs
+ * @pf: pointer to the pf structure
+ *
+ * free vf resources
+ **/
+void i40e_free_vfs(struct i40e_pf *pf)
+{
+ struct i40e_hw *hw = &pf->hw;
+ int i;
+
+ if (!pf->vf)
+ return;
+
+ /* Disable interrupt 0 so we don't try to handle the VFLR. */
+ wr32(hw, I40E_PFINT_DYN_CTL0, 0);
+ i40e_flush(hw);
+
+ /* free up vf resources */
+ for (i = 0; i < pf->num_alloc_vfs; i++) {
+ if (test_bit(I40E_VF_STAT_INIT, &pf->vf[i].vf_states))
+ i40e_free_vf_res(&pf->vf[i]);
+ /* disable qp mappings */
+ i40e_disable_vf_mappings(&pf->vf[i]);
+ }
+
+ kfree(pf->vf);
+ pf->vf = NULL;
+ pf->num_alloc_vfs = 0;
+
+ if (!i40e_vfs_are_assigned(pf))
+ pci_disable_sriov(pf->pdev);
+ else
+ dev_warn(&pf->pdev->dev,
+ "unable to disable SR-IOV because VFs are assigned.\n");
+
+ /* Re-enable interrupt 0. */
+ wr32(hw, I40E_PFINT_DYN_CTL0,
+ I40E_PFINT_DYN_CTL0_INTENA_MASK |
+ I40E_PFINT_DYN_CTL0_CLEARPBA_MASK |
+ (I40E_ITR_NONE << I40E_PFINT_DYN_CTL0_ITR_INDX_SHIFT));
+ i40e_flush(hw);
+}
+
+#ifdef CONFIG_PCI_IOV
+/**
+ * i40e_alloc_vfs
+ * @pf: pointer to the pf structure
+ * @num_alloc_vfs: number of vfs to allocate
+ *
+ * allocate vf resources
+ **/
+static int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs)
+{
+ struct i40e_vf *vfs;
+ int i, ret = 0;
+
+ ret = pci_enable_sriov(pf->pdev, num_alloc_vfs);
+ if (ret) {
+ dev_err(&pf->pdev->dev,
+ "pci_enable_sriov failed with error %d!\n", ret);
+ pf->num_alloc_vfs = 0;
+ goto err_iov;
+ }
+
+ /* allocate memory */
+ vfs = kzalloc(num_alloc_vfs * sizeof(struct i40e_vf), GFP_KERNEL);
+ if (!vfs) {
+ ret = -ENOMEM;
+ goto err_alloc;
+ }
+
+ /* apply default profile */
+ for (i = 0; i < num_alloc_vfs; i++) {
+ vfs[i].pf = pf;
+ vfs[i].parent_type = I40E_SWITCH_ELEMENT_TYPE_VEB;
+ vfs[i].vf_id = i;
+
+ /* assign default capabilities */
+ set_bit(I40E_VIRTCHNL_VF_CAP_L2, &vfs[i].vf_caps);
+
+ ret = i40e_alloc_vf_res(&vfs[i]);
+ i40e_reset_vf(&vfs[i], true);
+ if (ret)
+ break;
+
+ /* enable vf vplan_qtable mappings */
+ i40e_enable_vf_mappings(&vfs[i]);
+ }
+ pf->vf = vfs;
+ pf->num_alloc_vfs = num_alloc_vfs;
+
+err_alloc:
+ if (ret)
+ i40e_free_vfs(pf);
+err_iov:
+ return ret;
+}
+
+#endif
+/**
+ * i40e_pci_sriov_enable
+ * @pdev: pointer to a pci_dev structure
+ * @num_vfs: number of vfs to allocate
+ *
+ * Enable or change the number of VFs
+ **/
+static int i40e_pci_sriov_enable(struct pci_dev *pdev, int num_vfs)
+{
+#ifdef CONFIG_PCI_IOV
+ struct i40e_pf *pf = pci_get_drvdata(pdev);
+ int pre_existing_vfs = pci_num_vf(pdev);
+ int err = 0;
+
+ dev_info(&pdev->dev, "Allocating %d VFs.\n", num_vfs);
+ if (pre_existing_vfs && pre_existing_vfs != num_vfs)
+ i40e_free_vfs(pf);
+ else if (pre_existing_vfs && pre_existing_vfs == num_vfs)
+ goto out;
+
+ if (num_vfs > pf->num_req_vfs) {
+ err = -EPERM;
+ goto err_out;
+ }
+
+ err = i40e_alloc_vfs(pf, num_vfs);
+ if (err) {
+ dev_warn(&pdev->dev, "Failed to enable SR-IOV: %d\n", err);
+ goto err_out;
+ }
+
+out:
+ return num_vfs;
+
+err_out:
+ return err;
+#endif
+ return 0;
+}
+
+/**
+ * i40e_pci_sriov_configure
+ * @pdev: pointer to a pci_dev structure
+ * @num_vfs: number of vfs to allocate
+ *
+ * Enable or change the number of VFs. Called when the user updates the number
+ * of VFs in sysfs.
+ **/
+int i40e_pci_sriov_configure(struct pci_dev *pdev, int num_vfs)
+{
+ struct i40e_pf *pf = pci_get_drvdata(pdev);
+
+ if (num_vfs)
+ return i40e_pci_sriov_enable(pdev, num_vfs);
+
+ i40e_free_vfs(pf);
+ return 0;
+}
+
+/***********************virtual channel routines******************/
+
+/**
+ * i40e_vc_send_msg_to_vf
+ * @vf: pointer to the vf info
+ * @v_opcode: virtual channel opcode
+ * @v_retval: virtual channel return value
+ * @msg: pointer to the msg buffer
+ * @msglen: msg length
+ *
+ * send msg to vf
+ **/
+static int i40e_vc_send_msg_to_vf(struct i40e_vf *vf, u32 v_opcode,
+ u32 v_retval, u8 *msg, u16 msglen)
+{
+ struct i40e_pf *pf = vf->pf;
+ struct i40e_hw *hw = &pf->hw;
+ i40e_status aq_ret;
+
+ /* single place to detect unsuccessful return values */
+ if (v_retval) {
+ vf->num_invalid_msgs++;
+ dev_err(&pf->pdev->dev, "Failed opcode %d Error: %d\n",
+ v_opcode, v_retval);
+ if (vf->num_invalid_msgs >
+ I40E_DEFAULT_NUM_INVALID_MSGS_ALLOWED) {
+ dev_err(&pf->pdev->dev,
+ "Number of invalid messages exceeded for VF %d\n",
+ vf->vf_id);
+ dev_err(&pf->pdev->dev, "Use PF Control I/F to enable the VF\n");
+ set_bit(I40E_VF_STAT_DISABLED, &vf->vf_states);
+ }
+ } else {
+ vf->num_valid_msgs++;
+ }
+
+ aq_ret = i40e_aq_send_msg_to_vf(hw, vf->vf_id, v_opcode, v_retval,
+ msg, msglen, NULL);
+ if (aq_ret) {
+ dev_err(&pf->pdev->dev,
+ "Unable to send the message to VF %d aq_err %d\n",
+ vf->vf_id, pf->hw.aq.asq_last_status);
+ return -EIO;
+ }
+
+ return 0;
+}
+
+/**
+ * i40e_vc_send_resp_to_vf
+ * @vf: pointer to the vf info
+ * @opcode: operation code
+ * @retval: return value
+ *
+ * send resp msg to vf
+ **/
+static int i40e_vc_send_resp_to_vf(struct i40e_vf *vf,
+ enum i40e_virtchnl_ops opcode,
+ i40e_status retval)
+{
+ return i40e_vc_send_msg_to_vf(vf, opcode, retval, NULL, 0);
+}
+
+/**
+ * i40e_vc_get_version_msg
+ * @vf: pointer to the vf info
+ *
+ * called from the vf to request the API version used by the PF
+ **/
+static int i40e_vc_get_version_msg(struct i40e_vf *vf)
+{
+ struct i40e_virtchnl_version_info info = {
+ I40E_VIRTCHNL_VERSION_MAJOR, I40E_VIRTCHNL_VERSION_MINOR
+ };
+
+ return i40e_vc_send_msg_to_vf(vf, I40E_VIRTCHNL_OP_VERSION,
+ I40E_SUCCESS, (u8 *)&info,
+ sizeof(struct
+ i40e_virtchnl_version_info));
+}
+
+/**
+ * i40e_vc_get_vf_resources_msg
+ * @vf: pointer to the vf info
+ * @msg: pointer to the msg buffer
+ * @msglen: msg length
+ *
+ * called from the vf to request its resources
+ **/
+static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf)
+{
+ struct i40e_virtchnl_vf_resource *vfres = NULL;
+ struct i40e_pf *pf = vf->pf;
+ i40e_status aq_ret = 0;
+ struct i40e_vsi *vsi;
+ int i = 0, len = 0;
+ int num_vsis = 1;
+ int ret;
+
+ if (!test_bit(I40E_VF_STAT_INIT, &vf->vf_states)) {
+ aq_ret = I40E_ERR_PARAM;
+ goto err;
+ }
+
+ len = (sizeof(struct i40e_virtchnl_vf_resource) +
+ sizeof(struct i40e_virtchnl_vsi_resource) * num_vsis);
+
+ vfres = kzalloc(len, GFP_KERNEL);
+ if (!vfres) {
+ aq_ret = I40E_ERR_NO_MEMORY;
+ len = 0;
+ goto err;
+ }
+
+ vfres->vf_offload_flags = I40E_VIRTCHNL_VF_OFFLOAD_L2;
+ vsi = pf->vsi[vf->lan_vsi_index];
+ if (!vsi->info.pvid)
+ vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_VLAN;
+
+ vfres->num_vsis = num_vsis;
+ vfres->num_queue_pairs = vf->num_queue_pairs;
+ vfres->max_vectors = pf->hw.func_caps.num_msix_vectors_vf;
+ if (vf->lan_vsi_index) {
+ vfres->vsi_res[i].vsi_id = vf->lan_vsi_index;
+ vfres->vsi_res[i].vsi_type = I40E_VSI_SRIOV;
+ vfres->vsi_res[i].num_queue_pairs =
+ pf->vsi[vf->lan_vsi_index]->num_queue_pairs;
+ memcpy(vfres->vsi_res[i].default_mac_addr,
+ vf->default_lan_addr.addr, ETH_ALEN);
+ i++;
+ }
+ set_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states);
+
+err:
+ /* send the response back to the vf */
+ ret = i40e_vc_send_msg_to_vf(vf, I40E_VIRTCHNL_OP_GET_VF_RESOURCES,
+ aq_ret, (u8 *)vfres, len);
+
+ kfree(vfres);
+ return ret;
+}
+
+/**
+ * i40e_vc_reset_vf_msg
+ * @vf: pointer to the vf info
+ * @msg: pointer to the msg buffer
+ * @msglen: msg length
+ *
+ * called from the vf to reset itself,
+ * unlike other virtchnl messages, pf driver
+ * doesn't send the response back to the vf
+ **/
+static int i40e_vc_reset_vf_msg(struct i40e_vf *vf)
+{
+ if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states))
+ return -ENOENT;
+
+ return i40e_reset_vf(vf, false);
+}
+
+/**
+ * i40e_vc_config_promiscuous_mode_msg
+ * @vf: pointer to the vf info
+ * @msg: pointer to the msg buffer
+ * @msglen: msg length
+ *
+ * called from the vf to configure the promiscuous mode of
+ * vf vsis
+ **/
+static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf,
+ u8 *msg, u16 msglen)
+{
+ struct i40e_virtchnl_promisc_info *info =
+ (struct i40e_virtchnl_promisc_info *)msg;
+ struct i40e_pf *pf = vf->pf;
+ struct i40e_hw *hw = &pf->hw;
+ bool allmulti = false;
+ bool promisc = false;
+ i40e_status aq_ret;
+
+ if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states) ||
+ !test_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps) ||
+ !i40e_vc_isvalid_vsi_id(vf, info->vsi_id) ||
+ (pf->vsi[info->vsi_id]->type != I40E_VSI_FCOE)) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+
+ if (info->flags & I40E_FLAG_VF_UNICAST_PROMISC)
+ promisc = true;
+ aq_ret = i40e_aq_set_vsi_unicast_promiscuous(hw, info->vsi_id,
+ promisc, NULL);
+ if (aq_ret)
+ goto error_param;
+
+ if (info->flags & I40E_FLAG_VF_MULTICAST_PROMISC)
+ allmulti = true;
+ aq_ret = i40e_aq_set_vsi_multicast_promiscuous(hw, info->vsi_id,
+ allmulti, NULL);
+
+error_param:
+ /* send the response to the vf */
+ return i40e_vc_send_resp_to_vf(vf,
+ I40E_VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE,
+ aq_ret);
+}
+
+/**
+ * i40e_vc_config_queues_msg
+ * @vf: pointer to the vf info
+ * @msg: pointer to the msg buffer
+ * @msglen: msg length
+ *
+ * called from the vf to configure the rx/tx
+ * queues
+ **/
+static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
+{
+ struct i40e_virtchnl_vsi_queue_config_info *qci =
+ (struct i40e_virtchnl_vsi_queue_config_info *)msg;
+ struct i40e_virtchnl_queue_pair_info *qpi;
+ u16 vsi_id, vsi_queue_id;
+ i40e_status aq_ret = 0;
+ int i;
+
+ if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states)) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+
+ vsi_id = qci->vsi_id;
+ if (!i40e_vc_isvalid_vsi_id(vf, vsi_id)) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+ for (i = 0; i < qci->num_queue_pairs; i++) {
+ qpi = &qci->qpair[i];
+ vsi_queue_id = qpi->txq.queue_id;
+ if ((qpi->txq.vsi_id != vsi_id) ||
+ (qpi->rxq.vsi_id != vsi_id) ||
+ (qpi->rxq.queue_id != vsi_queue_id) ||
+ !i40e_vc_isvalid_queue_id(vf, vsi_id, vsi_queue_id)) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+
+ if (i40e_config_vsi_rx_queue(vf, vsi_id, vsi_queue_id,
+ &qpi->rxq) ||
+ i40e_config_vsi_tx_queue(vf, vsi_id, vsi_queue_id,
+ &qpi->txq)) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+ }
+
+error_param:
+ /* send the response to the vf */
+ return i40e_vc_send_resp_to_vf(vf, I40E_VIRTCHNL_OP_CONFIG_VSI_QUEUES,
+ aq_ret);
+}
+
+/**
+ * i40e_vc_config_irq_map_msg
+ * @vf: pointer to the vf info
+ * @msg: pointer to the msg buffer
+ * @msglen: msg length
+ *
+ * called from the vf to configure the irq to
+ * queue map
+ **/
+static int i40e_vc_config_irq_map_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
+{
+ struct i40e_virtchnl_irq_map_info *irqmap_info =
+ (struct i40e_virtchnl_irq_map_info *)msg;
+ struct i40e_virtchnl_vector_map *map;
+ u16 vsi_id, vsi_queue_id, vector_id;
+ i40e_status aq_ret = 0;
+ unsigned long tempmap;
+ int i;
+
+ if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states)) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+
+ for (i = 0; i < irqmap_info->num_vectors; i++) {
+ map = &irqmap_info->vecmap[i];
+
+ vector_id = map->vector_id;
+ vsi_id = map->vsi_id;
+ /* validate msg params */
+ if (!i40e_vc_isvalid_vector_id(vf, vector_id) ||
+ !i40e_vc_isvalid_vsi_id(vf, vsi_id)) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+
+ /* lookout for the invalid queue index */
+ tempmap = map->rxq_map;
+ vsi_queue_id = find_first_bit(&tempmap, I40E_MAX_VSI_QP);
+ while (vsi_queue_id < I40E_MAX_VSI_QP) {
+ if (!i40e_vc_isvalid_queue_id(vf, vsi_id,
+ vsi_queue_id)) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+ vsi_queue_id = find_next_bit(&tempmap, I40E_MAX_VSI_QP,
+ vsi_queue_id + 1);
+ }
+
+ tempmap = map->txq_map;
+ vsi_queue_id = find_first_bit(&tempmap, I40E_MAX_VSI_QP);
+ while (vsi_queue_id < I40E_MAX_VSI_QP) {
+ if (!i40e_vc_isvalid_queue_id(vf, vsi_id,
+ vsi_queue_id)) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+ vsi_queue_id = find_next_bit(&tempmap, I40E_MAX_VSI_QP,
+ vsi_queue_id + 1);
+ }
+
+ i40e_config_irq_link_list(vf, vsi_id, map);
+ }
+error_param:
+ /* send the response to the vf */
+ return i40e_vc_send_resp_to_vf(vf, I40E_VIRTCHNL_OP_CONFIG_IRQ_MAP,
+ aq_ret);
+}
+
+/**
+ * i40e_vc_enable_queues_msg
+ * @vf: pointer to the vf info
+ * @msg: pointer to the msg buffer
+ * @msglen: msg length
+ *
+ * called from the vf to enable all or specific queue(s)
+ **/
+static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
+{
+ struct i40e_virtchnl_queue_select *vqs =
+ (struct i40e_virtchnl_queue_select *)msg;
+ struct i40e_pf *pf = vf->pf;
+ u16 vsi_id = vqs->vsi_id;
+ i40e_status aq_ret = 0;
+ unsigned long tempmap;
+ u16 queue_id;
+
+ if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states)) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+
+ if (!i40e_vc_isvalid_vsi_id(vf, vsi_id)) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+
+ if ((0 == vqs->rx_queues) && (0 == vqs->tx_queues)) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+
+ tempmap = vqs->rx_queues;
+ queue_id = find_first_bit(&tempmap, I40E_MAX_VSI_QP);
+ while (queue_id < I40E_MAX_VSI_QP) {
+ if (!i40e_vc_isvalid_queue_id(vf, vsi_id, queue_id)) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+ i40e_ctrl_vsi_rx_queue(vf, vsi_id, queue_id,
+ I40E_QUEUE_CTRL_ENABLE);
+
+ queue_id = find_next_bit(&tempmap, I40E_MAX_VSI_QP,
+ queue_id + 1);
+ }
+
+ tempmap = vqs->tx_queues;
+ queue_id = find_first_bit(&tempmap, I40E_MAX_VSI_QP);
+ while (queue_id < I40E_MAX_VSI_QP) {
+ if (!i40e_vc_isvalid_queue_id(vf, vsi_id, queue_id)) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+ i40e_ctrl_vsi_tx_queue(vf, vsi_id, queue_id,
+ I40E_QUEUE_CTRL_ENABLE);
+
+ queue_id = find_next_bit(&tempmap, I40E_MAX_VSI_QP,
+ queue_id + 1);
+ }
+
+ /* Poll the status register to make sure that the
+ * requested op was completed successfully
+ */
+ udelay(10);
+
+ tempmap = vqs->rx_queues;
+ queue_id = find_first_bit(&tempmap, I40E_MAX_VSI_QP);
+ while (queue_id < I40E_MAX_VSI_QP) {
+ if (i40e_ctrl_vsi_rx_queue(vf, vsi_id, queue_id,
+ I40E_QUEUE_CTRL_ENABLECHECK)) {
+ dev_err(&pf->pdev->dev,
+ "Queue control check failed on RX queue %d of VSI %d VF %d\n",
+ queue_id, vsi_id, vf->vf_id);
+ }
+ queue_id = find_next_bit(&tempmap, I40E_MAX_VSI_QP,
+ queue_id + 1);
+ }
+
+ tempmap = vqs->tx_queues;
+ queue_id = find_first_bit(&tempmap, I40E_MAX_VSI_QP);
+ while (queue_id < I40E_MAX_VSI_QP) {
+ if (i40e_ctrl_vsi_tx_queue(vf, vsi_id, queue_id,
+ I40E_QUEUE_CTRL_ENABLECHECK)) {
+ dev_err(&pf->pdev->dev,
+ "Queue control check failed on TX queue %d of VSI %d VF %d\n",
+ queue_id, vsi_id, vf->vf_id);
+ }
+ queue_id = find_next_bit(&tempmap, I40E_MAX_VSI_QP,
+ queue_id + 1);
+ }
+
+error_param:
+ /* send the response to the vf */
+ return i40e_vc_send_resp_to_vf(vf, I40E_VIRTCHNL_OP_ENABLE_QUEUES,
+ aq_ret);
+}
+
+/**
+ * i40e_vc_disable_queues_msg
+ * @vf: pointer to the vf info
+ * @msg: pointer to the msg buffer
+ * @msglen: msg length
+ *
+ * called from the vf to disable all or specific
+ * queue(s)
+ **/
+static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
+{
+ struct i40e_virtchnl_queue_select *vqs =
+ (struct i40e_virtchnl_queue_select *)msg;
+ struct i40e_pf *pf = vf->pf;
+ u16 vsi_id = vqs->vsi_id;
+ i40e_status aq_ret = 0;
+ unsigned long tempmap;
+ u16 queue_id;
+
+ if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states)) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+
+ if (!i40e_vc_isvalid_vsi_id(vf, vqs->vsi_id)) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+
+ if ((0 == vqs->rx_queues) && (0 == vqs->tx_queues)) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+
+ tempmap = vqs->rx_queues;
+ queue_id = find_first_bit(&tempmap, I40E_MAX_VSI_QP);
+ while (queue_id < I40E_MAX_VSI_QP) {
+ if (!i40e_vc_isvalid_queue_id(vf, vsi_id, queue_id)) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+ i40e_ctrl_vsi_rx_queue(vf, vsi_id, queue_id,
+ I40E_QUEUE_CTRL_DISABLE);
+
+ queue_id = find_next_bit(&tempmap, I40E_MAX_VSI_QP,
+ queue_id + 1);
+ }
+
+ tempmap = vqs->tx_queues;
+ queue_id = find_first_bit(&tempmap, I40E_MAX_VSI_QP);
+ while (queue_id < I40E_MAX_VSI_QP) {
+ if (!i40e_vc_isvalid_queue_id(vf, vsi_id, queue_id)) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+ i40e_ctrl_vsi_tx_queue(vf, vsi_id, queue_id,
+ I40E_QUEUE_CTRL_DISABLE);
+
+ queue_id = find_next_bit(&tempmap, I40E_MAX_VSI_QP,
+ queue_id + 1);
+ }
+
+ /* Poll the status register to make sure that the
+ * requested op was completed successfully
+ */
+ udelay(10);
+
+ tempmap = vqs->rx_queues;
+ queue_id = find_first_bit(&tempmap, I40E_MAX_VSI_QP);
+ while (queue_id < I40E_MAX_VSI_QP) {
+ if (i40e_ctrl_vsi_rx_queue(vf, vsi_id, queue_id,
+ I40E_QUEUE_CTRL_DISABLECHECK)) {
+ dev_err(&pf->pdev->dev,
+ "Queue control check failed on RX queue %d of VSI %d VF %d\n",
+ queue_id, vsi_id, vf->vf_id);
+ }
+ queue_id = find_next_bit(&tempmap, I40E_MAX_VSI_QP,
+ queue_id + 1);
+ }
+
+ tempmap = vqs->tx_queues;
+ queue_id = find_first_bit(&tempmap, I40E_MAX_VSI_QP);
+ while (queue_id < I40E_MAX_VSI_QP) {
+ if (i40e_ctrl_vsi_tx_queue(vf, vsi_id, queue_id,
+ I40E_QUEUE_CTRL_DISABLECHECK)) {
+ dev_err(&pf->pdev->dev,
+ "Queue control check failed on TX queue %d of VSI %d VF %d\n",
+ queue_id, vsi_id, vf->vf_id);
+ }
+ queue_id = find_next_bit(&tempmap, I40E_MAX_VSI_QP,
+ queue_id + 1);
+ }
+
+error_param:
+ /* send the response to the vf */
+ return i40e_vc_send_resp_to_vf(vf, I40E_VIRTCHNL_OP_DISABLE_QUEUES,
+ aq_ret);
+}
+
+/**
+ * i40e_vc_get_stats_msg
+ * @vf: pointer to the vf info
+ * @msg: pointer to the msg buffer
+ * @msglen: msg length
+ *
+ * called from the vf to get vsi stats
+ **/
+static int i40e_vc_get_stats_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
+{
+ struct i40e_virtchnl_queue_select *vqs =
+ (struct i40e_virtchnl_queue_select *)msg;
+ struct i40e_pf *pf = vf->pf;
+ struct i40e_eth_stats stats;
+ i40e_status aq_ret = 0;
+ struct i40e_vsi *vsi;
+
+ memset(&stats, 0, sizeof(struct i40e_eth_stats));
+
+ if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states)) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+
+ if (!i40e_vc_isvalid_vsi_id(vf, vqs->vsi_id)) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+
+ vsi = pf->vsi[vqs->vsi_id];
+ if (!vsi) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+ i40e_update_eth_stats(vsi);
+ memcpy(&stats, &vsi->eth_stats, sizeof(struct i40e_eth_stats));
+
+error_param:
+ /* send the response back to the vf */
+ return i40e_vc_send_msg_to_vf(vf, I40E_VIRTCHNL_OP_GET_STATS, aq_ret,
+ (u8 *)&stats, sizeof(stats));
+}
+
+/**
+ * i40e_vc_add_mac_addr_msg
+ * @vf: pointer to the vf info
+ * @msg: pointer to the msg buffer
+ * @msglen: msg length
+ *
+ * add guest mac address filter
+ **/
+static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
+{
+ struct i40e_virtchnl_ether_addr_list *al =
+ (struct i40e_virtchnl_ether_addr_list *)msg;
+ struct i40e_pf *pf = vf->pf;
+ struct i40e_vsi *vsi = NULL;
+ u16 vsi_id = al->vsi_id;
+ i40e_status aq_ret = 0;
+ int i;
+
+ if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states) ||
+ !test_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps) ||
+ !i40e_vc_isvalid_vsi_id(vf, vsi_id)) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+
+ for (i = 0; i < al->num_elements; i++) {
+ if (is_broadcast_ether_addr(al->list[i].addr) ||
+ is_zero_ether_addr(al->list[i].addr)) {
+ dev_err(&pf->pdev->dev, "invalid VF MAC addr %pMAC\n",
+ al->list[i].addr);
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+ }
+ vsi = pf->vsi[vsi_id];
+
+ /* add new addresses to the list */
+ for (i = 0; i < al->num_elements; i++) {
+ struct i40e_mac_filter *f;
+
+ f = i40e_find_mac(vsi, al->list[i].addr, true, false);
+ if (f) {
+ if (i40e_is_vsi_in_vlan(vsi))
+ f = i40e_put_mac_in_vlan(vsi, al->list[i].addr,
+ true, false);
+ else
+ f = i40e_add_filter(vsi, al->list[i].addr, -1,
+ true, false);
+ }
+
+ if (!f) {
+ dev_err(&pf->pdev->dev,
+ "Unable to add VF MAC filter\n");
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+ }
+
+ /* program the updated filter list */
+ if (i40e_sync_vsi_filters(vsi))
+ dev_err(&pf->pdev->dev, "Unable to program VF MAC filters\n");
+
+error_param:
+ /* send the response to the vf */
+ return i40e_vc_send_resp_to_vf(vf, I40E_VIRTCHNL_OP_ADD_ETHER_ADDRESS,
+ aq_ret);
+}
+
+/**
+ * i40e_vc_del_mac_addr_msg
+ * @vf: pointer to the vf info
+ * @msg: pointer to the msg buffer
+ * @msglen: msg length
+ *
+ * remove guest mac address filter
+ **/
+static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
+{
+ struct i40e_virtchnl_ether_addr_list *al =
+ (struct i40e_virtchnl_ether_addr_list *)msg;
+ struct i40e_pf *pf = vf->pf;
+ struct i40e_vsi *vsi = NULL;
+ u16 vsi_id = al->vsi_id;
+ i40e_status aq_ret = 0;
+ int i;
+
+ if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states) ||
+ !test_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps) ||
+ !i40e_vc_isvalid_vsi_id(vf, vsi_id)) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+ vsi = pf->vsi[vsi_id];
+
+ /* delete addresses from the list */
+ for (i = 0; i < al->num_elements; i++)
+ i40e_del_filter(vsi, al->list[i].addr,
+ I40E_VLAN_ANY, true, false);
+
+ /* program the updated filter list */
+ if (i40e_sync_vsi_filters(vsi))
+ dev_err(&pf->pdev->dev, "Unable to program VF MAC filters\n");
+
+error_param:
+ /* send the response to the vf */
+ return i40e_vc_send_resp_to_vf(vf, I40E_VIRTCHNL_OP_DEL_ETHER_ADDRESS,
+ aq_ret);
+}
+
+/**
+ * i40e_vc_add_vlan_msg
+ * @vf: pointer to the vf info
+ * @msg: pointer to the msg buffer
+ * @msglen: msg length
+ *
+ * program guest vlan id
+ **/
+static int i40e_vc_add_vlan_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
+{
+ struct i40e_virtchnl_vlan_filter_list *vfl =
+ (struct i40e_virtchnl_vlan_filter_list *)msg;
+ struct i40e_pf *pf = vf->pf;
+ struct i40e_vsi *vsi = NULL;
+ u16 vsi_id = vfl->vsi_id;
+ i40e_status aq_ret = 0;
+ int i;
+
+ if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states) ||
+ !test_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps) ||
+ !i40e_vc_isvalid_vsi_id(vf, vsi_id)) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+
+ for (i = 0; i < vfl->num_elements; i++) {
+ if (vfl->vlan_id[i] > I40E_MAX_VLANID) {
+ aq_ret = I40E_ERR_PARAM;
+ dev_err(&pf->pdev->dev,
+ "invalid VF VLAN id %d\n", vfl->vlan_id[i]);
+ goto error_param;
+ }
+ }
+ vsi = pf->vsi[vsi_id];
+ if (vsi->info.pvid) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+
+ i40e_vlan_stripping_enable(vsi);
+ for (i = 0; i < vfl->num_elements; i++) {
+ /* add new VLAN filter */
+ int ret = i40e_vsi_add_vlan(vsi, vfl->vlan_id[i]);
+ if (ret)
+ dev_err(&pf->pdev->dev,
+ "Unable to add VF vlan filter %d, error %d\n",
+ vfl->vlan_id[i], ret);
+ }
+
+error_param:
+ /* send the response to the vf */
+ return i40e_vc_send_resp_to_vf(vf, I40E_VIRTCHNL_OP_ADD_VLAN, aq_ret);
+}
+
+/**
+ * i40e_vc_remove_vlan_msg
+ * @vf: pointer to the vf info
+ * @msg: pointer to the msg buffer
+ * @msglen: msg length
+ *
+ * remove programmed guest vlan id
+ **/
+static int i40e_vc_remove_vlan_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
+{
+ struct i40e_virtchnl_vlan_filter_list *vfl =
+ (struct i40e_virtchnl_vlan_filter_list *)msg;
+ struct i40e_pf *pf = vf->pf;
+ struct i40e_vsi *vsi = NULL;
+ u16 vsi_id = vfl->vsi_id;
+ i40e_status aq_ret = 0;
+ int i;
+
+ if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states) ||
+ !test_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps) ||
+ !i40e_vc_isvalid_vsi_id(vf, vsi_id)) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+
+ for (i = 0; i < vfl->num_elements; i++) {
+ if (vfl->vlan_id[i] > I40E_MAX_VLANID) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+ }
+
+ vsi = pf->vsi[vsi_id];
+ if (vsi->info.pvid) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+
+ for (i = 0; i < vfl->num_elements; i++) {
+ int ret = i40e_vsi_kill_vlan(vsi, vfl->vlan_id[i]);
+ if (ret)
+ dev_err(&pf->pdev->dev,
+ "Unable to delete VF vlan filter %d, error %d\n",
+ vfl->vlan_id[i], ret);
+ }
+
+error_param:
+ /* send the response to the vf */
+ return i40e_vc_send_resp_to_vf(vf, I40E_VIRTCHNL_OP_DEL_VLAN, aq_ret);
+}
+
+/**
+ * i40e_vc_fcoe_msg
+ * @vf: pointer to the vf info
+ * @msg: pointer to the msg buffer
+ * @msglen: msg length
+ *
+ * called from the vf for the fcoe msgs
+ **/
+static int i40e_vc_fcoe_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
+{
+ i40e_status aq_ret = 0;
+
+ if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states) ||
+ !test_bit(I40E_VF_STAT_FCOEENA, &vf->vf_states)) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+ aq_ret = I40E_ERR_NOT_IMPLEMENTED;
+
+error_param:
+ /* send the response to the vf */
+ return i40e_vc_send_resp_to_vf(vf, I40E_VIRTCHNL_OP_FCOE, aq_ret);
+}
+
+/**
+ * i40e_vc_validate_vf_msg
+ * @vf: pointer to the vf info
+ * @msg: pointer to the msg buffer
+ * @msglen: msg length
+ * @msghndl: msg handle
+ *
+ * validate msg
+ **/
+static int i40e_vc_validate_vf_msg(struct i40e_vf *vf, u32 v_opcode,
+ u32 v_retval, u8 *msg, u16 msglen)
+{
+ bool err_msg_format = false;
+ int valid_len;
+
+ /* Check if VF is disabled. */
+ if (test_bit(I40E_VF_STAT_DISABLED, &vf->vf_states))
+ return I40E_ERR_PARAM;
+
+ /* Validate message length. */
+ switch (v_opcode) {
+ case I40E_VIRTCHNL_OP_VERSION:
+ valid_len = sizeof(struct i40e_virtchnl_version_info);
+ break;
+ case I40E_VIRTCHNL_OP_RESET_VF:
+ case I40E_VIRTCHNL_OP_GET_VF_RESOURCES:
+ valid_len = 0;
+ break;
+ case I40E_VIRTCHNL_OP_CONFIG_TX_QUEUE:
+ valid_len = sizeof(struct i40e_virtchnl_txq_info);
+ break;
+ case I40E_VIRTCHNL_OP_CONFIG_RX_QUEUE:
+ valid_len = sizeof(struct i40e_virtchnl_rxq_info);
+ break;
+ case I40E_VIRTCHNL_OP_CONFIG_VSI_QUEUES:
+ valid_len = sizeof(struct i40e_virtchnl_vsi_queue_config_info);
+ if (msglen >= valid_len) {
+ struct i40e_virtchnl_vsi_queue_config_info *vqc =
+ (struct i40e_virtchnl_vsi_queue_config_info *)msg;
+ valid_len += (vqc->num_queue_pairs *
+ sizeof(struct
+ i40e_virtchnl_queue_pair_info));
+ if (vqc->num_queue_pairs == 0)
+ err_msg_format = true;
+ }
+ break;
+ case I40E_VIRTCHNL_OP_CONFIG_IRQ_MAP:
+ valid_len = sizeof(struct i40e_virtchnl_irq_map_info);
+ if (msglen >= valid_len) {
+ struct i40e_virtchnl_irq_map_info *vimi =
+ (struct i40e_virtchnl_irq_map_info *)msg;
+ valid_len += (vimi->num_vectors *
+ sizeof(struct i40e_virtchnl_vector_map));
+ if (vimi->num_vectors == 0)
+ err_msg_format = true;
+ }
+ break;
+ case I40E_VIRTCHNL_OP_ENABLE_QUEUES:
+ case I40E_VIRTCHNL_OP_DISABLE_QUEUES:
+ valid_len = sizeof(struct i40e_virtchnl_queue_select);
+ break;
+ case I40E_VIRTCHNL_OP_ADD_ETHER_ADDRESS:
+ case I40E_VIRTCHNL_OP_DEL_ETHER_ADDRESS:
+ valid_len = sizeof(struct i40e_virtchnl_ether_addr_list);
+ if (msglen >= valid_len) {
+ struct i40e_virtchnl_ether_addr_list *veal =
+ (struct i40e_virtchnl_ether_addr_list *)msg;
+ valid_len += veal->num_elements *
+ sizeof(struct i40e_virtchnl_ether_addr);
+ if (veal->num_elements == 0)
+ err_msg_format = true;
+ }
+ break;
+ case I40E_VIRTCHNL_OP_ADD_VLAN:
+ case I40E_VIRTCHNL_OP_DEL_VLAN:
+ valid_len = sizeof(struct i40e_virtchnl_vlan_filter_list);
+ if (msglen >= valid_len) {
+ struct i40e_virtchnl_vlan_filter_list *vfl =
+ (struct i40e_virtchnl_vlan_filter_list *)msg;
+ valid_len += vfl->num_elements * sizeof(u16);
+ if (vfl->num_elements == 0)
+ err_msg_format = true;
+ }
+ break;
+ case I40E_VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE:
+ valid_len = sizeof(struct i40e_virtchnl_promisc_info);
+ break;
+ case I40E_VIRTCHNL_OP_GET_STATS:
+ valid_len = sizeof(struct i40e_virtchnl_queue_select);
+ break;
+ /* These are always errors coming from the VF. */
+ case I40E_VIRTCHNL_OP_EVENT:
+ case I40E_VIRTCHNL_OP_UNKNOWN:
+ default:
+ return -EPERM;
+ break;
+ }
+ /* few more checks */
+ if ((valid_len != msglen) || (err_msg_format)) {
+ i40e_vc_send_resp_to_vf(vf, v_opcode, I40E_ERR_PARAM);
+ return -EINVAL;
+ } else {
+ return 0;
+ }
+}
+
+/**
+ * i40e_vc_process_vf_msg
+ * @pf: pointer to the pf structure
+ * @vf_id: source vf id
+ * @msg: pointer to the msg buffer
+ * @msglen: msg length
+ * @msghndl: msg handle
+ *
+ * called from the common aeq/arq handler to
+ * process request from vf
+ **/
+int i40e_vc_process_vf_msg(struct i40e_pf *pf, u16 vf_id, u32 v_opcode,
+ u32 v_retval, u8 *msg, u16 msglen)
+{
+ struct i40e_vf *vf = &(pf->vf[vf_id]);
+ struct i40e_hw *hw = &pf->hw;
+ int ret;
+
+ pf->vf_aq_requests++;
+ /* perform basic checks on the msg */
+ ret = i40e_vc_validate_vf_msg(vf, v_opcode, v_retval, msg, msglen);
+
+ if (ret) {
+ dev_err(&pf->pdev->dev, "invalid message from vf %d\n", vf_id);
+ return ret;
+ }
+ wr32(hw, I40E_VFGEN_RSTAT1(vf_id), I40E_VFR_VFACTIVE);
+ switch (v_opcode) {
+ case I40E_VIRTCHNL_OP_VERSION:
+ ret = i40e_vc_get_version_msg(vf);
+ break;
+ case I40E_VIRTCHNL_OP_GET_VF_RESOURCES:
+ ret = i40e_vc_get_vf_resources_msg(vf);
+ break;
+ case I40E_VIRTCHNL_OP_RESET_VF:
+ ret = i40e_vc_reset_vf_msg(vf);
+ break;
+ case I40E_VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE:
+ ret = i40e_vc_config_promiscuous_mode_msg(vf, msg, msglen);
+ break;
+ case I40E_VIRTCHNL_OP_CONFIG_VSI_QUEUES:
+ ret = i40e_vc_config_queues_msg(vf, msg, msglen);
+ break;
+ case I40E_VIRTCHNL_OP_CONFIG_IRQ_MAP:
+ ret = i40e_vc_config_irq_map_msg(vf, msg, msglen);
+ break;
+ case I40E_VIRTCHNL_OP_ENABLE_QUEUES:
+ ret = i40e_vc_enable_queues_msg(vf, msg, msglen);
+ break;
+ case I40E_VIRTCHNL_OP_DISABLE_QUEUES:
+ ret = i40e_vc_disable_queues_msg(vf, msg, msglen);
+ break;
+ case I40E_VIRTCHNL_OP_ADD_ETHER_ADDRESS:
+ ret = i40e_vc_add_mac_addr_msg(vf, msg, msglen);
+ break;
+ case I40E_VIRTCHNL_OP_DEL_ETHER_ADDRESS:
+ ret = i40e_vc_del_mac_addr_msg(vf, msg, msglen);
+ break;
+ case I40E_VIRTCHNL_OP_ADD_VLAN:
+ ret = i40e_vc_add_vlan_msg(vf, msg, msglen);
+ break;
+ case I40E_VIRTCHNL_OP_DEL_VLAN:
+ ret = i40e_vc_remove_vlan_msg(vf, msg, msglen);
+ break;
+ case I40E_VIRTCHNL_OP_GET_STATS:
+ ret = i40e_vc_get_stats_msg(vf, msg, msglen);
+ break;
+ case I40E_VIRTCHNL_OP_FCOE:
+ ret = i40e_vc_fcoe_msg(vf, msg, msglen);
+ break;
+ case I40E_VIRTCHNL_OP_UNKNOWN:
+ default:
+ dev_err(&pf->pdev->dev,
+ "Unsupported opcode %d from vf %d\n", v_opcode, vf_id);
+ ret = i40e_vc_send_resp_to_vf(vf, v_opcode,
+ I40E_ERR_NOT_IMPLEMENTED);
+ break;
+ }
+
+ return ret;
+}
+
+/**
+ * i40e_vc_process_vflr_event
+ * @pf: pointer to the pf structure
+ *
+ * called from the vlfr irq handler to
+ * free up vf resources and state variables
+ **/
+int i40e_vc_process_vflr_event(struct i40e_pf *pf)
+{
+ u32 reg, reg_idx, bit_idx, vf_id;
+ struct i40e_hw *hw = &pf->hw;
+ struct i40e_vf *vf;
+
+ if (!test_bit(__I40E_VFLR_EVENT_PENDING, &pf->state))
+ return 0;
+
+ clear_bit(__I40E_VFLR_EVENT_PENDING, &pf->state);
+ for (vf_id = 0; vf_id < pf->num_alloc_vfs; vf_id++) {
+ reg_idx = (hw->func_caps.vf_base_id + vf_id) / 32;
+ bit_idx = (hw->func_caps.vf_base_id + vf_id) % 32;
+ /* read GLGEN_VFLRSTAT register to find out the flr vfs */
+ vf = &pf->vf[vf_id];
+ reg = rd32(hw, I40E_GLGEN_VFLRSTAT(reg_idx));
+ if (reg & (1 << bit_idx)) {
+ /* clear the bit in GLGEN_VFLRSTAT */
+ wr32(hw, I40E_GLGEN_VFLRSTAT(reg_idx), (1 << bit_idx));
+
+ if (i40e_reset_vf(vf, true))
+ dev_err(&pf->pdev->dev,
+ "Unable to reset the VF %d\n", vf_id);
+ /* free up vf resources to destroy vsi state */
+ i40e_free_vf_res(vf);
+
+ /* allocate new vf resources with the default state */
+ if (i40e_alloc_vf_res(vf))
+ dev_err(&pf->pdev->dev,
+ "Unable to allocate VF resources %d\n",
+ vf_id);
+
+ i40e_enable_vf_mappings(vf);
+ }
+ }
+
+ /* re-enable vflr interrupt cause */
+ reg = rd32(hw, I40E_PFINT_ICR0_ENA);
+ reg |= I40E_PFINT_ICR0_ENA_VFLR_MASK;
+ wr32(hw, I40E_PFINT_ICR0_ENA, reg);
+ i40e_flush(hw);
+
+ return 0;
+}
+
+/**
+ * i40e_vc_vf_broadcast
+ * @pf: pointer to the pf structure
+ * @opcode: operation code
+ * @retval: return value
+ * @msg: pointer to the msg buffer
+ * @msglen: msg length
+ *
+ * send a message to all VFs on a given PF
+ **/
+static void i40e_vc_vf_broadcast(struct i40e_pf *pf,
+ enum i40e_virtchnl_ops v_opcode,
+ i40e_status v_retval, u8 *msg,
+ u16 msglen)
+{
+ struct i40e_hw *hw = &pf->hw;
+ struct i40e_vf *vf = pf->vf;
+ int i;
+
+ for (i = 0; i < pf->num_alloc_vfs; i++) {
+ /* Ignore return value on purpose - a given VF may fail, but
+ * we need to keep going and send to all of them
+ */
+ i40e_aq_send_msg_to_vf(hw, vf->vf_id, v_opcode, v_retval,
+ msg, msglen, NULL);
+ vf++;
+ }
+}
+
+/**
+ * i40e_vc_notify_link_state
+ * @pf: pointer to the pf structure
+ *
+ * send a link status message to all VFs on a given PF
+ **/
+void i40e_vc_notify_link_state(struct i40e_pf *pf)
+{
+ struct i40e_virtchnl_pf_event pfe;
+
+ pfe.event = I40E_VIRTCHNL_EVENT_LINK_CHANGE;
+ pfe.severity = I40E_PF_EVENT_SEVERITY_INFO;
+ pfe.event_data.link_event.link_status =
+ pf->hw.phy.link_info.link_info & I40E_AQ_LINK_UP;
+ pfe.event_data.link_event.link_speed = pf->hw.phy.link_info.link_speed;
+
+ i40e_vc_vf_broadcast(pf, I40E_VIRTCHNL_OP_EVENT, I40E_SUCCESS,
+ (u8 *)&pfe, sizeof(struct i40e_virtchnl_pf_event));
+}
+
+/**
+ * i40e_vc_notify_reset
+ * @pf: pointer to the pf structure
+ *
+ * indicate a pending reset to all VFs on a given PF
+ **/
+void i40e_vc_notify_reset(struct i40e_pf *pf)
+{
+ struct i40e_virtchnl_pf_event pfe;
+
+ pfe.event = I40E_VIRTCHNL_EVENT_RESET_IMPENDING;
+ pfe.severity = I40E_PF_EVENT_SEVERITY_CERTAIN_DOOM;
+ i40e_vc_vf_broadcast(pf, I40E_VIRTCHNL_OP_EVENT, I40E_SUCCESS,
+ (u8 *)&pfe, sizeof(struct i40e_virtchnl_pf_event));
+}
+
+/**
+ * i40e_vc_notify_vf_reset
+ * @vf: pointer to the vf structure
+ *
+ * indicate a pending reset to the given VF
+ **/
+void i40e_vc_notify_vf_reset(struct i40e_vf *vf)
+{
+ struct i40e_virtchnl_pf_event pfe;
+
+ pfe.event = I40E_VIRTCHNL_EVENT_RESET_IMPENDING;
+ pfe.severity = I40E_PF_EVENT_SEVERITY_CERTAIN_DOOM;
+ i40e_aq_send_msg_to_vf(&vf->pf->hw, vf->vf_id, I40E_VIRTCHNL_OP_EVENT,
+ I40E_SUCCESS, (u8 *)&pfe,
+ sizeof(struct i40e_virtchnl_pf_event), NULL);
+}
+
+/**
+ * i40e_ndo_set_vf_mac
+ * @netdev: network interface device structure
+ * @vf_id: vf identifier
+ * @mac: mac address
+ *
+ * program vf mac address
+ **/
+int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_mac_filter *f;
+ struct i40e_vf *vf;
+ int ret = 0;
+
+ /* validate the request */
+ if (vf_id >= pf->num_alloc_vfs) {
+ dev_err(&pf->pdev->dev,
+ "Invalid VF Identifier %d\n", vf_id);
+ ret = -EINVAL;
+ goto error_param;
+ }
+
+ vf = &(pf->vf[vf_id]);
+ vsi = pf->vsi[vf->lan_vsi_index];
+ if (!test_bit(I40E_VF_STAT_INIT, &vf->vf_states)) {
+ dev_err(&pf->pdev->dev,
+ "Uninitialized VF %d\n", vf_id);
+ ret = -EINVAL;
+ goto error_param;
+ }
+
+ if (!is_valid_ether_addr(mac)) {
+ dev_err(&pf->pdev->dev,
+ "Invalid VF ethernet address\n");
+ ret = -EINVAL;
+ goto error_param;
+ }
+
+ /* delete the temporary mac address */
+ i40e_del_filter(vsi, vf->default_lan_addr.addr, 0, true, false);
+
+ /* add the new mac address */
+ f = i40e_add_filter(vsi, mac, 0, true, false);
+ if (!f) {
+ dev_err(&pf->pdev->dev,
+ "Unable to add VF ucast filter\n");
+ ret = -ENOMEM;
+ goto error_param;
+ }
+
+ dev_info(&pf->pdev->dev, "Setting MAC %pM on VF %d\n", mac, vf_id);
+ /* program mac filter */
+ if (i40e_sync_vsi_filters(vsi)) {
+ dev_err(&pf->pdev->dev, "Unable to program ucast filters\n");
+ ret = -EIO;
+ goto error_param;
+ }
+ memcpy(vf->default_lan_addr.addr, mac, ETH_ALEN);
+ dev_info(&pf->pdev->dev, "Reload the VF driver to make this change effective.\n");
+ ret = 0;
+
+error_param:
+ return ret;
+}
+
+/**
+ * i40e_ndo_set_vf_port_vlan
+ * @netdev: network interface device structure
+ * @vf_id: vf identifier
+ * @vlan_id: mac address
+ * @qos: priority setting
+ *
+ * program vf vlan id and/or qos
+ **/
+int i40e_ndo_set_vf_port_vlan(struct net_device *netdev,
+ int vf_id, u16 vlan_id, u8 qos)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_pf *pf = np->vsi->back;
+ struct i40e_vsi *vsi;
+ struct i40e_vf *vf;
+ int ret = 0;
+
+ /* validate the request */
+ if (vf_id >= pf->num_alloc_vfs) {
+ dev_err(&pf->pdev->dev, "Invalid VF Identifier %d\n", vf_id);
+ ret = -EINVAL;
+ goto error_pvid;
+ }
+
+ if ((vlan_id > I40E_MAX_VLANID) || (qos > 7)) {
+ dev_err(&pf->pdev->dev, "Invalid VF Parameters\n");
+ ret = -EINVAL;
+ goto error_pvid;
+ }
+
+ vf = &(pf->vf[vf_id]);
+ vsi = pf->vsi[vf->lan_vsi_index];
+ if (!test_bit(I40E_VF_STAT_INIT, &vf->vf_states)) {
+ dev_err(&pf->pdev->dev, "Uninitialized VF %d\n", vf_id);
+ ret = -EINVAL;
+ goto error_pvid;
+ }
+
+ if (vsi->info.pvid) {
+ /* kill old VLAN */
+ ret = i40e_vsi_kill_vlan(vsi, (le16_to_cpu(vsi->info.pvid) &
+ VLAN_VID_MASK));
+ if (ret) {
+ dev_info(&vsi->back->pdev->dev,
+ "remove VLAN failed, ret=%d, aq_err=%d\n",
+ ret, pf->hw.aq.asq_last_status);
+ }
+ }
+ if (vlan_id || qos)
+ ret = i40e_vsi_add_pvid(vsi,
+ vlan_id | (qos << I40E_VLAN_PRIORITY_SHIFT));
+ else
+ i40e_vlan_stripping_disable(vsi);
+
+ if (vlan_id) {
+ dev_info(&pf->pdev->dev, "Setting VLAN %d, QOS 0x%x on VF %d\n",
+ vlan_id, qos, vf_id);
+
+ /* add new VLAN filter */
+ ret = i40e_vsi_add_vlan(vsi, vlan_id);
+ if (ret) {
+ dev_info(&vsi->back->pdev->dev,
+ "add VF VLAN failed, ret=%d aq_err=%d\n", ret,
+ vsi->back->hw.aq.asq_last_status);
+ goto error_pvid;
+ }
+ }
+
+ if (ret) {
+ dev_err(&pf->pdev->dev, "Unable to update VF vsi context\n");
+ goto error_pvid;
+ }
+ ret = 0;
+
+error_pvid:
+ return ret;
+}
+
+/**
+ * i40e_ndo_set_vf_bw
+ * @netdev: network interface device structure
+ * @vf_id: vf identifier
+ * @tx_rate: tx rate
+ *
+ * configure vf tx rate
+ **/
+int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int tx_rate)
+{
+ return -EOPNOTSUPP;
+}
+
+/**
+ * i40e_ndo_get_vf_config
+ * @netdev: network interface device structure
+ * @vf_id: vf identifier
+ * @ivi: vf configuration structure
+ *
+ * return vf configuration
+ **/
+int i40e_ndo_get_vf_config(struct net_device *netdev,
+ int vf_id, struct ifla_vf_info *ivi)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_mac_filter *f, *ftmp;
+ struct i40e_vsi *vsi = np->vsi;
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_vf *vf;
+ int ret = 0;
+
+ /* validate the request */
+ if (vf_id >= pf->num_alloc_vfs) {
+ dev_err(&pf->pdev->dev, "Invalid VF Identifier %d\n", vf_id);
+ ret = -EINVAL;
+ goto error_param;
+ }
+
+ vf = &(pf->vf[vf_id]);
+ /* first vsi is always the LAN vsi */
+ vsi = pf->vsi[vf->lan_vsi_index];
+ if (!test_bit(I40E_VF_STAT_INIT, &vf->vf_states)) {
+ dev_err(&pf->pdev->dev, "Uninitialized VF %d\n", vf_id);
+ ret = -EINVAL;
+ goto error_param;
+ }
+
+ ivi->vf = vf_id;
+
+ /* first entry of the list is the default ethernet address */
+ list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) {
+ memcpy(&ivi->mac, f->macaddr, I40E_ETH_LENGTH_OF_ADDRESS);
+ break;
+ }
+
+ ivi->tx_rate = 0;
+ ivi->vlan = le16_to_cpu(vsi->info.pvid) & I40E_VLAN_MASK;
+ ivi->qos = (le16_to_cpu(vsi->info.pvid) & I40E_PRIORITY_MASK) >>
+ I40E_VLAN_PRIORITY_SHIFT;
+ ret = 0;
+
+error_param:
+ return ret;
+}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
new file mode 100644
index 0000000..360382c
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
@@ -0,0 +1,120 @@
+/*******************************************************************************
+ *
+ * Intel Ethernet Controller XL710 Family Linux Driver
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ ******************************************************************************/
+
+#ifndef _I40E_VIRTCHNL_PF_H_
+#define _I40E_VIRTCHNL_PF_H_
+
+#include "i40e.h"
+
+#define I40E_MAX_MACVLAN_FILTERS 256
+#define I40E_MAX_VLAN_FILTERS 256
+#define I40E_MAX_VLANID 4095
+
+#define I40E_VIRTCHNL_SUPPORTED_QTYPES 2
+
+#define I40E_DEFAULT_NUM_MDD_EVENTS_ALLOWED 3
+#define I40E_DEFAULT_NUM_INVALID_MSGS_ALLOWED 10
+
+#define I40E_VLAN_PRIORITY_SHIFT 12
+#define I40E_VLAN_MASK 0xFFF
+#define I40E_PRIORITY_MASK 0x7000
+
+/* Various queue ctrls */
+enum i40e_queue_ctrl {
+ I40E_QUEUE_CTRL_UNKNOWN = 0,
+ I40E_QUEUE_CTRL_ENABLE,
+ I40E_QUEUE_CTRL_ENABLECHECK,
+ I40E_QUEUE_CTRL_DISABLE,
+ I40E_QUEUE_CTRL_DISABLECHECK,
+ I40E_QUEUE_CTRL_FASTDISABLE,
+ I40E_QUEUE_CTRL_FASTDISABLECHECK,
+};
+
+/* VF states */
+enum i40e_vf_states {
+ I40E_VF_STAT_INIT = 0,
+ I40E_VF_STAT_ACTIVE,
+ I40E_VF_STAT_FCOEENA,
+ I40E_VF_STAT_DISABLED,
+};
+
+/* VF capabilities */
+enum i40e_vf_capabilities {
+ I40E_VIRTCHNL_VF_CAP_PRIVILEGE = 0,
+ I40E_VIRTCHNL_VF_CAP_L2,
+};
+
+/* VF information structure */
+struct i40e_vf {
+ struct i40e_pf *pf;
+
+ /* vf id in the pf space */
+ u16 vf_id;
+ /* all vf vsis connect to the same parent */
+ enum i40e_switch_element_types parent_type;
+
+ /* vf Port Extender (PE) stag if used */
+ u16 stag;
+
+ struct i40e_virtchnl_ether_addr default_lan_addr;
+ struct i40e_virtchnl_ether_addr default_fcoe_addr;
+
+ /* VSI indices - actual VSI pointers are maintained in the PF structure
+ * When assigned, these will be non-zero, because VSI 0 is always
+ * the main LAN VSI for the PF.
+ */
+ u8 lan_vsi_index; /* index into PF struct */
+ u8 lan_vsi_id; /* ID as used by firmware */
+
+ u8 num_queue_pairs; /* num of qps assigned to vf vsis */
+ u64 num_mdd_events; /* num of mdd events detected */
+ u64 num_invalid_msgs; /* num of malformed or invalid msgs detected */
+ u64 num_valid_msgs; /* num of valid msgs detected */
+
+ unsigned long vf_caps; /* vf's adv. capabilities */
+ unsigned long vf_states; /* vf's runtime states */
+};
+
+void i40e_free_vfs(struct i40e_pf *pf);
+int i40e_pci_sriov_configure(struct pci_dev *dev, int num_vfs);
+int i40e_vc_process_vf_msg(struct i40e_pf *pf, u16 vf_id, u32 v_opcode,
+ u32 v_retval, u8 *msg, u16 msglen);
+int i40e_vc_process_vflr_event(struct i40e_pf *pf);
+int i40e_reset_vf(struct i40e_vf *vf, bool flr);
+void i40e_vc_notify_vf_reset(struct i40e_vf *vf);
+
+/* vf configuration related iplink handlers */
+int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac);
+int i40e_ndo_set_vf_port_vlan(struct net_device *netdev,
+ int vf_id, u16 vlan_id, u8 qos);
+int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int tx_rate);
+int i40e_ndo_get_vf_config(struct net_device *netdev,
+ int vf_id, struct ifla_vf_info *ivi);
+void i40e_vc_notify_link_state(struct i40e_pf *pf);
+void i40e_vc_notify_reset(struct i40e_pf *pf);
+
+#endif /* _I40E_VIRTCHNL_PF_H_ */
diff --git a/drivers/net/ethernet/korina.c b/drivers/net/ethernet/korina.c
index 270e65f..a36fa80 100644
--- a/drivers/net/ethernet/korina.c
+++ b/drivers/net/ethernet/korina.c
@@ -996,14 +996,14 @@
* that handles the Done Finished
* Ovr and Und Events */
ret = request_irq(lp->rx_irq, korina_rx_dma_interrupt,
- IRQF_DISABLED, "Korina ethernet Rx", dev);
+ 0, "Korina ethernet Rx", dev);
if (ret < 0) {
printk(KERN_ERR "%s: unable to get Rx DMA IRQ %d\n",
dev->name, lp->rx_irq);
goto err_release;
}
ret = request_irq(lp->tx_irq, korina_tx_dma_interrupt,
- IRQF_DISABLED, "Korina ethernet Tx", dev);
+ 0, "Korina ethernet Tx", dev);
if (ret < 0) {
printk(KERN_ERR "%s: unable to get Tx DMA IRQ %d\n",
dev->name, lp->tx_irq);
@@ -1012,7 +1012,7 @@
/* Install handler for overrun error. */
ret = request_irq(lp->ovr_irq, korina_ovr_interrupt,
- IRQF_DISABLED, "Ethernet Overflow", dev);
+ 0, "Ethernet Overflow", dev);
if (ret < 0) {
printk(KERN_ERR "%s: unable to get OVR IRQ %d\n",
dev->name, lp->ovr_irq);
@@ -1021,7 +1021,7 @@
/* Install handler for underflow error. */
ret = request_irq(lp->und_irq, korina_und_interrupt,
- IRQF_DISABLED, "Ethernet Underflow", dev);
+ 0, "Ethernet Underflow", dev);
if (ret < 0) {
printk(KERN_ERR "%s: unable to get UND IRQ %d\n",
dev->name, lp->und_irq);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index 88349b8..81bf836 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -430,7 +430,7 @@
u8 diag_test;
u8 num_msix;
u8 nic_mode;
- char diag_cnt;
+ int diag_cnt;
u16 max_uc_count;
u16 port_type;
diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c
index 949076f..13e6fff 100644
--- a/drivers/net/ethernet/tile/tilegx.c
+++ b/drivers/net/ethernet/tile/tilegx.c
@@ -1734,7 +1734,8 @@
unsigned int data_len = skb->len - sh_len;
unsigned char *data = skb->data;
unsigned int ih_off, th_off, p_len;
- unsigned int isum_seed, tsum_seed, id, seq;
+ unsigned int isum_seed, tsum_seed, seq;
+ unsigned int uninitialized_var(id);
int is_ipv6;
long f_id = -1; /* id of the current fragment */
long f_size = skb_headlen(skb) - sh_len; /* current fragment size */
@@ -1781,7 +1782,7 @@
} else {
ih = (struct iphdr *)(buf + ih_off);
ih->tot_len = htons(sh_len + p_len - ih_off);
- ih->id = htons(id);
+ ih->id = htons(id++);
ih->check = csum_long(isum_seed + ih->tot_len +
ih->id) ^ 0xffff;
}
@@ -1818,7 +1819,6 @@
slot++;
}
- id++;
seq += p_len;
/* The last segment may be less than gso_size. */
diff --git a/drivers/net/irda/donauboe.c b/drivers/net/irda/donauboe.c
index 510b9c8..31bcb98 100644
--- a/drivers/net/irda/donauboe.c
+++ b/drivers/net/irda/donauboe.c
@@ -1488,7 +1488,7 @@
toshoboe_close (struct pci_dev *pci_dev)
{
int i;
- struct toshoboe_cb *self = (struct toshoboe_cb*)pci_get_drvdata(pci_dev);
+ struct toshoboe_cb *self = pci_get_drvdata(pci_dev);
IRDA_DEBUG (4, "%s()\n", __func__);
@@ -1696,7 +1696,7 @@
static int
toshoboe_gotosleep (struct pci_dev *pci_dev, pm_message_t crap)
{
- struct toshoboe_cb *self = (struct toshoboe_cb*)pci_get_drvdata(pci_dev);
+ struct toshoboe_cb *self = pci_get_drvdata(pci_dev);
unsigned long flags;
int i = 10;
@@ -1725,7 +1725,7 @@
static int
toshoboe_wakeup (struct pci_dev *pci_dev)
{
- struct toshoboe_cb *self = (struct toshoboe_cb*)pci_get_drvdata(pci_dev);
+ struct toshoboe_cb *self = pci_get_drvdata(pci_dev);
unsigned long flags;
IRDA_DEBUG (4, "%s()\n", __func__);
diff --git a/drivers/net/irda/vlsi_ir.c b/drivers/net/irda/vlsi_ir.c
index 5f47584..c5bd58b 100644
--- a/drivers/net/irda/vlsi_ir.c
+++ b/drivers/net/irda/vlsi_ir.c
@@ -543,7 +543,7 @@
int crclen, len = 0;
struct sk_buff *skb;
int ret = 0;
- struct net_device *ndev = (struct net_device *)pci_get_drvdata(r->pdev);
+ struct net_device *ndev = pci_get_drvdata(r->pdev);
vlsi_irda_dev_t *idev = netdev_priv(ndev);
pci_dma_sync_single_for_cpu(r->pdev, rd_get_addr(rd), r->len, r->dir);
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 64dfaa3..9bf46bd 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -118,8 +118,6 @@
const struct ethhdr *eth, bool local)
{
struct net_device *dev = vlan->dev;
- if (!skb)
- return NET_RX_DROP;
if (local)
return vlan->forward(dev, skb);
@@ -171,9 +169,13 @@
hash = mc_hash(vlan, eth->h_dest);
if (!test_bit(hash, vlan->mc_filter))
continue;
+
+ err = NET_RX_DROP;
nskb = skb_clone(skb, GFP_ATOMIC);
- err = macvlan_broadcast_one(nskb, vlan, eth,
- mode == MACVLAN_MODE_BRIDGE);
+ if (likely(nskb))
+ err = macvlan_broadcast_one(
+ nskb, vlan, eth,
+ mode == MACVLAN_MODE_BRIDGE);
macvlan_count_rx(vlan, skb->len + ETH_HLEN,
err == NET_RX_SUCCESS, 1);
}
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 3a81315..6312332 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -518,6 +518,135 @@
/* 3. Combined interface devices matching on interface number */
{QMI_FIXED_INTF(0x0408, 0xea42, 4)}, /* Yota / Megafon M100-1 */
+ {QMI_FIXED_INTF(0x05c6, 0x7000, 0)},
+ {QMI_FIXED_INTF(0x05c6, 0x7001, 1)},
+ {QMI_FIXED_INTF(0x05c6, 0x7002, 1)},
+ {QMI_FIXED_INTF(0x05c6, 0x7101, 1)},
+ {QMI_FIXED_INTF(0x05c6, 0x7101, 2)},
+ {QMI_FIXED_INTF(0x05c6, 0x7101, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x7102, 1)},
+ {QMI_FIXED_INTF(0x05c6, 0x7102, 2)},
+ {QMI_FIXED_INTF(0x05c6, 0x7102, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x8000, 7)},
+ {QMI_FIXED_INTF(0x05c6, 0x8001, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9000, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9003, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9005, 2)},
+ {QMI_FIXED_INTF(0x05c6, 0x900a, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x900b, 2)},
+ {QMI_FIXED_INTF(0x05c6, 0x900c, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x900c, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x900c, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x900d, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x900f, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x900f, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x900f, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9010, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9010, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9011, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9011, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9021, 1)},
+ {QMI_FIXED_INTF(0x05c6, 0x9022, 2)},
+ {QMI_FIXED_INTF(0x05c6, 0x9025, 4)}, /* Alcatel-sbell ASB TL131 TDD LTE (China Mobile) */
+ {QMI_FIXED_INTF(0x05c6, 0x9026, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x902e, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9031, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9032, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9033, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9033, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9033, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9033, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9034, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9034, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9034, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9034, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9034, 7)},
+ {QMI_FIXED_INTF(0x05c6, 0x9035, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9036, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9037, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9038, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x903b, 7)},
+ {QMI_FIXED_INTF(0x05c6, 0x903c, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x903d, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x903e, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9043, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9046, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9046, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9046, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9047, 2)},
+ {QMI_FIXED_INTF(0x05c6, 0x9047, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9047, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9048, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9048, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9048, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9048, 7)},
+ {QMI_FIXED_INTF(0x05c6, 0x9048, 8)},
+ {QMI_FIXED_INTF(0x05c6, 0x904c, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x904c, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x904c, 7)},
+ {QMI_FIXED_INTF(0x05c6, 0x904c, 8)},
+ {QMI_FIXED_INTF(0x05c6, 0x9050, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9052, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9053, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9053, 7)},
+ {QMI_FIXED_INTF(0x05c6, 0x9054, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9054, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9055, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9055, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9055, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9055, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9055, 7)},
+ {QMI_FIXED_INTF(0x05c6, 0x9056, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9062, 2)},
+ {QMI_FIXED_INTF(0x05c6, 0x9062, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9062, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9062, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9062, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9062, 7)},
+ {QMI_FIXED_INTF(0x05c6, 0x9062, 8)},
+ {QMI_FIXED_INTF(0x05c6, 0x9062, 9)},
+ {QMI_FIXED_INTF(0x05c6, 0x9064, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9065, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9065, 7)},
+ {QMI_FIXED_INTF(0x05c6, 0x9066, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9066, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9067, 1)},
+ {QMI_FIXED_INTF(0x05c6, 0x9068, 2)},
+ {QMI_FIXED_INTF(0x05c6, 0x9068, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9068, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9068, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9068, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9068, 7)},
+ {QMI_FIXED_INTF(0x05c6, 0x9069, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9069, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9069, 7)},
+ {QMI_FIXED_INTF(0x05c6, 0x9069, 8)},
+ {QMI_FIXED_INTF(0x05c6, 0x9070, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9070, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9075, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9076, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9076, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9076, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9076, 7)},
+ {QMI_FIXED_INTF(0x05c6, 0x9076, 8)},
+ {QMI_FIXED_INTF(0x05c6, 0x9077, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9077, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9077, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9077, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9078, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9079, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9079, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9079, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9079, 7)},
+ {QMI_FIXED_INTF(0x05c6, 0x9079, 8)},
+ {QMI_FIXED_INTF(0x05c6, 0x9080, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9080, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9080, 7)},
+ {QMI_FIXED_INTF(0x05c6, 0x9080, 8)},
+ {QMI_FIXED_INTF(0x05c6, 0x9083, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9084, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x920d, 0)},
+ {QMI_FIXED_INTF(0x05c6, 0x920d, 5)},
{QMI_FIXED_INTF(0x12d1, 0x140c, 1)}, /* Huawei E173 */
{QMI_FIXED_INTF(0x12d1, 0x14ac, 1)}, /* Huawei E1820 */
{QMI_FIXED_INTF(0x19d2, 0x0002, 1)},
@@ -612,7 +741,6 @@
{QMI_GOBI_DEVICE(0x413c, 0x8186)}, /* Dell Gobi 2000 Modem device (N0218, VU936) */
{QMI_GOBI_DEVICE(0x413c, 0x8194)}, /* Dell Gobi 3000 Composite */
{QMI_GOBI_DEVICE(0x05c6, 0x920b)}, /* Generic Gobi 2000 Modem device */
- {QMI_GOBI_DEVICE(0x05c6, 0x920d)}, /* Gobi 3000 Composite */
{QMI_GOBI_DEVICE(0x05c6, 0x9225)}, /* Sony Gobi 2000 Modem device (N0279, VU730) */
{QMI_GOBI_DEVICE(0x05c6, 0x9245)}, /* Samsung Gobi 2000 Modem device (VL176) */
{QMI_GOBI_DEVICE(0x03f0, 0x251d)}, /* HP Gobi 2000 Modem device (VP412) */
diff --git a/drivers/net/wireless/p54/Kconfig b/drivers/net/wireless/p54/Kconfig
index 15ea36b..cdafb8c 100644
--- a/drivers/net/wireless/p54/Kconfig
+++ b/drivers/net/wireless/p54/Kconfig
@@ -41,7 +41,7 @@
config P54_SPI
tristate "Prism54 SPI (stlc45xx) support"
- depends on P54_COMMON && SPI_MASTER && GENERIC_HARDIRQS
+ depends on P54_COMMON && SPI_MASTER
---help---
This driver is for stlc4550 or stlc4560 based wireless chips
such as Nokia's N800/N810 Portable Internet Tablet.
diff --git a/drivers/net/wireless/ti/wl1251/Kconfig b/drivers/net/wireless/ti/wl1251/Kconfig
index 8fec4ed..477a206 100644
--- a/drivers/net/wireless/ti/wl1251/Kconfig
+++ b/drivers/net/wireless/ti/wl1251/Kconfig
@@ -1,6 +1,6 @@
menuconfig WL1251
tristate "TI wl1251 driver support"
- depends on MAC80211 && GENERIC_HARDIRQS
+ depends on MAC80211
select FW_LOADER
select CRC7
---help---
diff --git a/drivers/net/wireless/ti/wlcore/Kconfig b/drivers/net/wireless/ti/wlcore/Kconfig
index 2b83282..7c09954 100644
--- a/drivers/net/wireless/ti/wlcore/Kconfig
+++ b/drivers/net/wireless/ti/wlcore/Kconfig
@@ -1,6 +1,6 @@
config WLCORE
tristate "TI wlcore support"
- depends on WL_TI && GENERIC_HARDIRQS && MAC80211
+ depends on WL_TI && MAC80211
select FW_LOADER
---help---
This module contains the main code for TI WLAN chips. It abstracts
diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
index a754b84..0fe40c7 100644
--- a/drivers/of/of_reserved_mem.c
+++ b/drivers/of/of_reserved_mem.c
@@ -11,8 +11,6 @@
* License or (at your optional) any later version of the license.
*/
-#include <asm/dma-contiguous.h>
-
#include <linux/memblock.h>
#include <linux/err.h>
#include <linux/of.h>
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index f6488ad..0b7d23b 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -487,7 +487,6 @@
{
struct acpi_device *adev = NULL;
- acpiphp_bus_trim(handle);
acpi_bus_scan(handle);
acpi_bus_get_device(handle, &adev);
if (adev)
@@ -529,6 +528,16 @@
}
}
+static int acpiphp_rescan_slot(struct acpiphp_slot *slot)
+{
+ struct acpiphp_func *func;
+
+ list_for_each_entry(func, &slot->funcs, sibling)
+ acpiphp_bus_add(func_to_handle(func));
+
+ return pci_scan_slot(slot->bus, PCI_DEVFN(slot->device, 0));
+}
+
/**
* enable_slot - enable, configure a slot
* @slot: slot to be enabled
@@ -543,12 +552,9 @@
struct acpiphp_func *func;
int max, pass;
LIST_HEAD(add_list);
+ int nr_found;
- list_for_each_entry(func, &slot->funcs, sibling)
- acpiphp_bus_add(func_to_handle(func));
-
- pci_scan_slot(bus, PCI_DEVFN(slot->device, 0));
-
+ nr_found = acpiphp_rescan_slot(slot);
max = acpiphp_max_busnr(bus);
for (pass = 0; pass < 2; pass++) {
list_for_each_entry(dev, &bus->devices, bus_list) {
@@ -567,8 +573,11 @@
}
}
}
-
__pci_bus_assign_resources(bus, &add_list, NULL);
+ /* Nothing more to do here if there are no new devices on this bus. */
+ if (!nr_found && (slot->flags & SLOT_ENABLED))
+ return;
+
acpiphp_sanitize_bus(bus);
acpiphp_set_hpp_values(bus);
acpiphp_set_acpi_region(slot);
@@ -837,11 +846,22 @@
case ACPI_NOTIFY_DEVICE_CHECK:
/* device check */
dbg("%s: Device check notify on %s\n", __func__, objname);
- if (bridge)
+ if (bridge) {
acpiphp_check_bridge(bridge);
- else
- acpiphp_check_bridge(func->parent);
+ } else {
+ struct acpiphp_slot *slot = func->slot;
+ int ret;
+ /*
+ * Check if anything has changed in the slot and rescan
+ * from the parent if that's the case.
+ */
+ mutex_lock(&slot->crit_sect);
+ ret = acpiphp_rescan_slot(slot);
+ mutex_unlock(&slot->crit_sect);
+ if (ret)
+ acpiphp_check_bridge(func->parent);
+ }
break;
case ACPI_NOTIFY_EJECT_REQUEST:
@@ -867,6 +887,8 @@
hotplug_event(hp_work->handle, hp_work->type, context);
acpi_scan_lock_release();
+ acpi_evaluate_hotplug_ost(hp_work->handle, hp_work->type,
+ ACPI_OST_SC_SUCCESS, NULL);
kfree(hp_work); /* allocated in handle_hotplug_event() */
put_bridge(context->func.parent);
}
@@ -882,11 +904,15 @@
static void handle_hotplug_event(acpi_handle handle, u32 type, void *data)
{
struct acpiphp_context *context;
+ u32 ost_code = ACPI_OST_SC_SUCCESS;
switch (type) {
case ACPI_NOTIFY_BUS_CHECK:
case ACPI_NOTIFY_DEVICE_CHECK:
+ break;
case ACPI_NOTIFY_EJECT_REQUEST:
+ ost_code = ACPI_OST_SC_EJECT_IN_PROGRESS;
+ acpi_evaluate_hotplug_ost(handle, type, ost_code, NULL);
break;
case ACPI_NOTIFY_DEVICE_WAKE:
@@ -895,20 +921,21 @@
case ACPI_NOTIFY_FREQUENCY_MISMATCH:
acpi_handle_err(handle, "Device cannot be configured due "
"to a frequency mismatch\n");
- return;
+ goto out;
case ACPI_NOTIFY_BUS_MODE_MISMATCH:
acpi_handle_err(handle, "Device cannot be configured due "
"to a bus mode mismatch\n");
- return;
+ goto out;
case ACPI_NOTIFY_POWER_FAULT:
acpi_handle_err(handle, "Device has suffered a power fault\n");
- return;
+ goto out;
default:
acpi_handle_warn(handle, "Unsupported event type 0x%x\n", type);
- return;
+ ost_code = ACPI_OST_SC_UNRECOGNIZED_NOTIFY;
+ goto out;
}
mutex_lock(&acpiphp_context_lock);
@@ -917,8 +944,14 @@
get_bridge(context->func.parent);
acpiphp_put_context(context);
alloc_acpi_hp_work(handle, type, context, hotplug_event_work);
+ mutex_unlock(&acpiphp_context_lock);
+ return;
}
mutex_unlock(&acpiphp_context_lock);
+ ost_code = ACPI_OST_SC_NON_SPECIFIC_FAILURE;
+
+ out:
+ acpi_evaluate_hotplug_ost(handle, type, ost_code, NULL);
}
/*
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index b35f93c..d5f90d6 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -30,7 +30,6 @@
/* Arch hooks */
-#if defined(CONFIG_GENERIC_HARDIRQS)
int __weak arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc)
{
struct msi_chip *chip = dev->bus->msi;
@@ -67,21 +66,6 @@
return chip->check_device(chip, dev, nvec, type);
}
-#else
-int __weak arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc)
-{
- return -ENOSYS;
-}
-
-void __weak arch_teardown_msi_irq(unsigned int irq)
-{
-}
-
-int __weak arch_msi_check_device(struct pci_dev *dev, int nvec, int type)
-{
- return 0;
-}
-#endif /* CONFIG_GENERIC_HARDIRQS */
int __weak arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
{
@@ -245,8 +229,6 @@
desc->masked = __msix_mask_irq(desc, flag);
}
-#ifdef CONFIG_GENERIC_HARDIRQS
-
static void msi_set_mask_bit(struct irq_data *data, u32 flag)
{
struct msi_desc *desc = irq_data_get_msi(data);
@@ -270,8 +252,6 @@
msi_set_mask_bit(data, 0);
}
-#endif /* CONFIG_GENERIC_HARDIRQS */
-
void __read_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
{
BUG_ON(entry->dev->current_state != PCI_D0);
@@ -382,10 +362,8 @@
nvec = entry->nvec_used;
else
nvec = 1 << entry->msi_attrib.multiple;
-#ifdef CONFIG_GENERIC_HARDIRQS
for (i = 0; i < nvec; i++)
BUG_ON(irq_has_action(entry->irq + i));
-#endif
}
arch_teardown_msi_irqs(dev);
diff --git a/drivers/platform/x86/apple-gmux.c b/drivers/platform/x86/apple-gmux.c
index f74bfcb..8eea2ef 100644
--- a/drivers/platform/x86/apple-gmux.c
+++ b/drivers/platform/x86/apple-gmux.c
@@ -393,17 +393,21 @@
complete(&gmux_data->powerchange_done);
}
-static int gmux_suspend(struct pnp_dev *pnp, pm_message_t state)
+static int gmux_suspend(struct device *dev)
{
+ struct pnp_dev *pnp = to_pnp_dev(dev);
struct apple_gmux_data *gmux_data = pnp_get_drvdata(pnp);
+
gmux_data->resume_client_id = gmux_active_client(gmux_data);
gmux_disable_interrupts(gmux_data);
return 0;
}
-static int gmux_resume(struct pnp_dev *pnp)
+static int gmux_resume(struct device *dev)
{
+ struct pnp_dev *pnp = to_pnp_dev(dev);
struct apple_gmux_data *gmux_data = pnp_get_drvdata(pnp);
+
gmux_enable_interrupts(gmux_data);
gmux_switchto(gmux_data->resume_client_id);
if (gmux_data->power_state == VGA_SWITCHEROO_OFF)
@@ -605,13 +609,19 @@
{"", 0}
};
+static const struct dev_pm_ops gmux_dev_pm_ops = {
+ .suspend = gmux_suspend,
+ .resume = gmux_resume,
+};
+
static struct pnp_driver gmux_pnp_driver = {
.name = "apple-gmux",
.probe = gmux_probe,
.remove = gmux_remove,
.id_table = gmux_device_ids,
- .suspend = gmux_suspend,
- .resume = gmux_resume
+ .driver = {
+ .pm = &gmux_dev_pm_ops,
+ },
};
static int __init apple_gmux_init(void)
diff --git a/drivers/pnp/driver.c b/drivers/pnp/driver.c
index 12adb43..a39ee38 100644
--- a/drivers/pnp/driver.c
+++ b/drivers/pnp/driver.c
@@ -163,6 +163,13 @@
if (!pnp_drv)
return 0;
+ if (pnp_drv->driver.pm && pnp_drv->driver.pm->suspend) {
+ error = pnp_drv->driver.pm->suspend(dev);
+ suspend_report_result(pnp_drv->driver.pm->suspend, error);
+ if (error)
+ return error;
+ }
+
if (pnp_drv->suspend) {
error = pnp_drv->suspend(pnp_dev, state);
if (error)
@@ -211,6 +218,12 @@
return error;
}
+ if (pnp_drv->driver.pm && pnp_drv->driver.pm->resume) {
+ error = pnp_drv->driver.pm->resume(dev);
+ if (error)
+ return error;
+ }
+
if (pnp_drv->resume) {
error = pnp_drv->resume(pnp_dev);
if (error)
diff --git a/drivers/power/Kconfig b/drivers/power/Kconfig
index bb49ab6..e6f92b4 100644
--- a/drivers/power/Kconfig
+++ b/drivers/power/Kconfig
@@ -269,7 +269,6 @@
config CHARGER_MAX8903
tristate "MAX8903 Battery DC-DC Charger for USB and Adapter Power"
- depends on GENERIC_HARDIRQS
help
Say Y to enable support for the MAX8903 DC-DC charger and sysfs.
The driver supports controlling charger-enable and current-limit
@@ -370,7 +369,7 @@
config BATTERY_GOLDFISH
tristate "Goldfish battery driver"
- depends on GENERIC_HARDIRQS && (GOLDFISH || COMPILE_TEST)
+ depends on GOLDFISH || COMPILE_TEST
help
Say Y to enable support for the battery and AC power in the
Goldfish emulator.
diff --git a/drivers/pps/clients/Kconfig b/drivers/pps/clients/Kconfig
index 6efd9b6..0c9f280 100644
--- a/drivers/pps/clients/Kconfig
+++ b/drivers/pps/clients/Kconfig
@@ -31,7 +31,7 @@
config PPS_CLIENT_GPIO
tristate "PPS client using GPIO"
- depends on PPS && GENERIC_HARDIRQS
+ depends on PPS
help
If you say yes here you get support for a PPS source using
GPIO. To be useful you must also register a platform device
diff --git a/drivers/pps/clients/pps-gpio.c b/drivers/pps/clients/pps-gpio.c
index eae0eda..9966124 100644
--- a/drivers/pps/clients/pps-gpio.c
+++ b/drivers/pps/clients/pps-gpio.c
@@ -184,7 +184,6 @@
{
struct pps_gpio_device_data *data = platform_get_drvdata(pdev);
- platform_set_drvdata(pdev, NULL);
pps_unregister_source(data->pps);
dev_info(&pdev->dev, "removed IRQ %d as PPS source\n", data->irq);
return 0;
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index 9e3498b..9654aa3 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -1249,6 +1249,15 @@
Say "yes" here to support the real time clock on SiRF SOC chips.
This driver can also be built as a module called rtc-sirfsoc.
+config RTC_DRV_MOXART
+ tristate "MOXA ART RTC"
+ help
+ If you say yes here you get support for the MOXA ART
+ RTC module.
+
+ This driver can also be built as a module. If so, the module
+ will be called rtc-moxart
+
comment "HID Sensor RTC drivers"
config RTC_DRV_HID_SENSOR_TIME
diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile
index d3b4488..2dff3d2 100644
--- a/drivers/rtc/Makefile
+++ b/drivers/rtc/Makefile
@@ -130,3 +130,4 @@
obj-$(CONFIG_RTC_DRV_WM8350) += rtc-wm8350.o
obj-$(CONFIG_RTC_DRV_X1205) += rtc-x1205.o
obj-$(CONFIG_RTC_DRV_SIRFSOC) += rtc-sirfsoc.o
+obj-$(CONFIG_RTC_DRV_MOXART) += rtc-moxart.o
diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index be06d71..24e733c 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -1018,23 +1018,6 @@
cmos_do_remove(&pnp->dev);
}
-#ifdef CONFIG_PM
-
-static int cmos_pnp_suspend(struct pnp_dev *pnp, pm_message_t mesg)
-{
- return cmos_suspend(&pnp->dev);
-}
-
-static int cmos_pnp_resume(struct pnp_dev *pnp)
-{
- return cmos_resume(&pnp->dev);
-}
-
-#else
-#define cmos_pnp_suspend NULL
-#define cmos_pnp_resume NULL
-#endif
-
static void cmos_pnp_shutdown(struct pnp_dev *pnp)
{
if (system_state == SYSTEM_POWER_OFF && !cmos_poweroff(&pnp->dev))
@@ -1060,8 +1043,11 @@
/* flag ensures resume() gets called, and stops syslog spam */
.flags = PNP_DRIVER_RES_DO_NOT_CHANGE,
- .suspend = cmos_pnp_suspend,
- .resume = cmos_pnp_resume,
+#ifdef CONFIG_PM_SLEEP
+ .driver = {
+ .pm = &cmos_pm_ops,
+ },
+#endif
};
#endif /* CONFIG_PNP */
diff --git a/drivers/rtc/rtc-ds1511.c b/drivers/rtc/rtc-ds1511.c
index 308a8fe..bc7b4fc 100644
--- a/drivers/rtc/rtc-ds1511.c
+++ b/drivers/rtc/rtc-ds1511.c
@@ -89,7 +89,6 @@
struct rtc_plat_data {
struct rtc_device *rtc;
void __iomem *ioaddr; /* virtual base address */
- int size; /* amount of memory mapped */
int irq;
unsigned int irqen;
int alrm_sec;
@@ -479,20 +478,14 @@
struct rtc_plat_data *pdata;
int ret = 0;
- res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!res)
- return -ENODEV;
-
pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
if (!pdata)
return -ENOMEM;
- pdata->size = resource_size(res);
- if (!devm_request_mem_region(&pdev->dev, res->start, pdata->size,
- pdev->name))
- return -EBUSY;
- ds1511_base = devm_ioremap(&pdev->dev, res->start, pdata->size);
- if (!ds1511_base)
- return -ENOMEM;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ ds1511_base = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(ds1511_base))
+ return PTR_ERR(ds1511_base);
pdata->ioaddr = ds1511_base;
pdata->irq = platform_get_irq(pdev, 0);
diff --git a/drivers/rtc/rtc-ds1553.c b/drivers/rtc/rtc-ds1553.c
index 8c6c952..fd31571 100644
--- a/drivers/rtc/rtc-ds1553.c
+++ b/drivers/rtc/rtc-ds1553.c
@@ -285,19 +285,14 @@
void __iomem *ioaddr;
int ret = 0;
- res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!res)
- return -ENODEV;
pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
if (!pdata)
return -ENOMEM;
- if (!devm_request_mem_region(&pdev->dev, res->start, RTC_REG_SIZE,
- pdev->name))
- return -EBUSY;
- ioaddr = devm_ioremap(&pdev->dev, res->start, RTC_REG_SIZE);
- if (!ioaddr)
- return -ENOMEM;
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ ioaddr = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(ioaddr))
+ return PTR_ERR(ioaddr);
pdata->ioaddr = ioaddr;
pdata->irq = platform_get_irq(pdev, 0);
diff --git a/drivers/rtc/rtc-ds1742.c b/drivers/rtc/rtc-ds1742.c
index eccdc62..17b73fd 100644
--- a/drivers/rtc/rtc-ds1742.c
+++ b/drivers/rtc/rtc-ds1742.c
@@ -52,11 +52,9 @@
#define RTC_BATT_FLAG 0x80
struct rtc_plat_data {
- struct rtc_device *rtc;
void __iomem *ioaddr_nvram;
void __iomem *ioaddr_rtc;
size_t size_nvram;
- size_t size;
unsigned long last_jiffies;
struct bin_attribute nvram_attr;
};
@@ -117,11 +115,7 @@
/* year is 1900 + tm->tm_year */
tm->tm_year = bcd2bin(year) + bcd2bin(century) * 100 - 1900;
- if (rtc_valid_tm(tm) < 0) {
- dev_err(dev, "retrieved date/time is not valid.\n");
- rtc_time_to_tm(0, tm);
- }
- return 0;
+ return rtc_valid_tm(tm);
}
static const struct rtc_class_ops ds1742_rtc_ops = {
@@ -168,22 +162,17 @@
void __iomem *ioaddr;
int ret = 0;
- res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!res)
- return -ENODEV;
pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
if (!pdata)
return -ENOMEM;
- pdata->size = resource_size(res);
- if (!devm_request_mem_region(&pdev->dev, res->start, pdata->size,
- pdev->name))
- return -EBUSY;
- ioaddr = devm_ioremap(&pdev->dev, res->start, pdata->size);
- if (!ioaddr)
- return -ENOMEM;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ ioaddr = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(ioaddr))
+ return PTR_ERR(ioaddr);
pdata->ioaddr_nvram = ioaddr;
- pdata->size_nvram = pdata->size - RTC_SIZE;
+ pdata->size_nvram = resource_size(res) - RTC_SIZE;
pdata->ioaddr_rtc = ioaddr + pdata->size_nvram;
sysfs_bin_attr_init(&pdata->nvram_attr);
@@ -212,7 +201,6 @@
&ds1742_rtc_ops, THIS_MODULE);
if (IS_ERR(rtc))
return PTR_ERR(rtc);
- pdata->rtc = rtc;
ret = sysfs_create_bin_file(&pdev->dev.kobj, &pdata->nvram_attr);
diff --git a/drivers/rtc/rtc-ep93xx.c b/drivers/rtc/rtc-ep93xx.c
index 549b3c3..580e7b5 100644
--- a/drivers/rtc/rtc-ep93xx.c
+++ b/drivers/rtc/rtc-ep93xx.c
@@ -138,17 +138,9 @@
return -ENOMEM;
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!res)
- return -ENXIO;
-
- if (!devm_request_mem_region(&pdev->dev, res->start,
- resource_size(res), pdev->name))
- return -EBUSY;
-
- ep93xx_rtc->mmio_base = devm_ioremap(&pdev->dev, res->start,
- resource_size(res));
- if (!ep93xx_rtc->mmio_base)
- return -ENXIO;
+ ep93xx_rtc->mmio_base = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(ep93xx_rtc->mmio_base))
+ return PTR_ERR(ep93xx_rtc->mmio_base);
pdev->dev.platform_data = ep93xx_rtc;
platform_set_drvdata(pdev, ep93xx_rtc);
diff --git a/drivers/rtc/rtc-hid-sensor-time.c b/drivers/rtc/rtc-hid-sensor-time.c
index 7273b01..4e2a818 100644
--- a/drivers/rtc/rtc-hid-sensor-time.c
+++ b/drivers/rtc/rtc-hid-sensor-time.c
@@ -23,10 +23,6 @@
#include <linux/iio/iio.h>
#include <linux/rtc.h>
-/* Format: HID-SENSOR-usage_id_in_hex */
-/* Usage ID from spec for Time: 0x2000A0 */
-#define DRIVER_NAME "HID-SENSOR-2000a0" /* must be lowercase */
-
enum hid_time_channel {
CHANNEL_SCAN_INDEX_YEAR,
CHANNEL_SCAN_INDEX_MONTH,
@@ -283,9 +279,11 @@
"hid-sensor-time", &hid_time_rtc_ops,
THIS_MODULE);
- if (IS_ERR(time_state->rtc)) {
+ if (IS_ERR_OR_NULL(time_state->rtc)) {
+ ret = time_state->rtc ? PTR_ERR(time_state->rtc) : -ENODEV;
+ time_state->rtc = NULL;
+ sensor_hub_remove_callback(hsdev, HID_USAGE_SENSOR_TIME);
dev_err(&pdev->dev, "rtc device register failed!\n");
- return PTR_ERR(time_state->rtc);
}
return ret;
@@ -300,9 +298,19 @@
return 0;
}
+static struct platform_device_id hid_time_ids[] = {
+ {
+ /* Format: HID-SENSOR-usage_id_in_hex_lowercase */
+ .name = "HID-SENSOR-2000a0",
+ },
+ { /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(platform, hid_time_ids);
+
static struct platform_driver hid_time_platform_driver = {
+ .id_table = hid_time_ids,
.driver = {
- .name = DRIVER_NAME,
+ .name = KBUILD_MODNAME,
.owner = THIS_MODULE,
},
.probe = hid_time_probe,
diff --git a/drivers/rtc/rtc-imxdi.c b/drivers/rtc/rtc-imxdi.c
index d3a8c8e..abd7f90 100644
--- a/drivers/rtc/rtc-imxdi.c
+++ b/drivers/rtc/rtc-imxdi.c
@@ -375,24 +375,16 @@
struct imxdi_dev *imxdi;
int rc;
- res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!res)
- return -ENODEV;
-
imxdi = devm_kzalloc(&pdev->dev, sizeof(*imxdi), GFP_KERNEL);
if (!imxdi)
return -ENOMEM;
imxdi->pdev = pdev;
- if (!devm_request_mem_region(&pdev->dev, res->start, resource_size(res),
- pdev->name))
- return -EBUSY;
-
- imxdi->ioaddr = devm_ioremap(&pdev->dev, res->start,
- resource_size(res));
- if (imxdi->ioaddr == NULL)
- return -ENOMEM;
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ imxdi->ioaddr = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(imxdi->ioaddr))
+ return PTR_ERR(imxdi->ioaddr);
spin_lock_init(&imxdi->irq_lock);
diff --git a/drivers/rtc/rtc-lpc32xx.c b/drivers/rtc/rtc-lpc32xx.c
index 8276ae9..bfdbcb8 100644
--- a/drivers/rtc/rtc-lpc32xx.c
+++ b/drivers/rtc/rtc-lpc32xx.c
@@ -201,16 +201,9 @@
{
struct resource *res;
struct lpc32xx_rtc *rtc;
- resource_size_t size;
int rtcirq;
u32 tmp;
- res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!res) {
- dev_err(&pdev->dev, "Can't get memory resource\n");
- return -ENOENT;
- }
-
rtcirq = platform_get_irq(pdev, 0);
if (rtcirq < 0 || rtcirq >= NR_IRQS) {
dev_warn(&pdev->dev, "Can't get interrupt resource\n");
@@ -224,19 +217,10 @@
}
rtc->irq = rtcirq;
- size = resource_size(res);
-
- if (!devm_request_mem_region(&pdev->dev, res->start, size,
- pdev->name)) {
- dev_err(&pdev->dev, "RTC registers are not free\n");
- return -EBUSY;
- }
-
- rtc->rtc_base = devm_ioremap(&pdev->dev, res->start, size);
- if (!rtc->rtc_base) {
- dev_err(&pdev->dev, "Can't map memory\n");
- return -ENOMEM;
- }
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ rtc->rtc_base = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(rtc->rtc_base))
+ return PTR_ERR(rtc->rtc_base);
spin_lock_init(&rtc->lock);
diff --git a/drivers/rtc/rtc-max77686.c b/drivers/rtc/rtc-max77686.c
index 9915cb9..9efe118 100644
--- a/drivers/rtc/rtc-max77686.c
+++ b/drivers/rtc/rtc-max77686.c
@@ -240,9 +240,9 @@
}
alrm->pending = 0;
- ret = regmap_read(info->max77686->regmap, MAX77686_REG_STATUS1, &val);
+ ret = regmap_read(info->max77686->regmap, MAX77686_REG_STATUS2, &val);
if (ret < 0) {
- dev_err(info->dev, "%s:%d fail to read status1 reg(%d)\n",
+ dev_err(info->dev, "%s:%d fail to read status2 reg(%d)\n",
__func__, __LINE__, ret);
goto out;
}
diff --git a/drivers/rtc/rtc-moxart.c b/drivers/rtc/rtc-moxart.c
new file mode 100644
index 0000000..c29dee0
--- /dev/null
+++ b/drivers/rtc/rtc-moxart.c
@@ -0,0 +1,330 @@
+/*
+ * MOXA ART RTC driver.
+ *
+ * Copyright (C) 2013 Jonas Jensen
+ *
+ * Jonas Jensen <jonas.jensen@gmail.com>
+ *
+ * Based on code from
+ * Moxa Technology Co., Ltd. <www.moxa.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/delay.h>
+#include <linux/rtc.h>
+#include <linux/platform_device.h>
+#include <linux/module.h>
+#include <linux/gpio.h>
+#include <linux/of_gpio.h>
+
+#define GPIO_RTC_RESERVED 0x0C
+#define GPIO_RTC_DATA_SET 0x10
+#define GPIO_RTC_DATA_CLEAR 0x14
+#define GPIO_RTC_PIN_PULL_ENABLE 0x18
+#define GPIO_RTC_PIN_PULL_TYPE 0x1C
+#define GPIO_RTC_INT_ENABLE 0x20
+#define GPIO_RTC_INT_RAW_STATE 0x24
+#define GPIO_RTC_INT_MASKED_STATE 0x28
+#define GPIO_RTC_INT_MASK 0x2C
+#define GPIO_RTC_INT_CLEAR 0x30
+#define GPIO_RTC_INT_TRIGGER 0x34
+#define GPIO_RTC_INT_BOTH 0x38
+#define GPIO_RTC_INT_RISE_NEG 0x3C
+#define GPIO_RTC_BOUNCE_ENABLE 0x40
+#define GPIO_RTC_BOUNCE_PRE_SCALE 0x44
+#define GPIO_RTC_PROTECT_W 0x8E
+#define GPIO_RTC_PROTECT_R 0x8F
+#define GPIO_RTC_YEAR_W 0x8C
+#define GPIO_RTC_YEAR_R 0x8D
+#define GPIO_RTC_DAY_W 0x8A
+#define GPIO_RTC_DAY_R 0x8B
+#define GPIO_RTC_MONTH_W 0x88
+#define GPIO_RTC_MONTH_R 0x89
+#define GPIO_RTC_DATE_W 0x86
+#define GPIO_RTC_DATE_R 0x87
+#define GPIO_RTC_HOURS_W 0x84
+#define GPIO_RTC_HOURS_R 0x85
+#define GPIO_RTC_MINUTES_W 0x82
+#define GPIO_RTC_MINUTES_R 0x83
+#define GPIO_RTC_SECONDS_W 0x80
+#define GPIO_RTC_SECONDS_R 0x81
+#define GPIO_RTC_DELAY_TIME 8
+
+struct moxart_rtc {
+ struct rtc_device *rtc;
+ spinlock_t rtc_lock;
+ int gpio_data, gpio_sclk, gpio_reset;
+};
+
+static int day_of_year[12] = { 0, 31, 59, 90, 120, 151, 181,
+ 212, 243, 273, 304, 334 };
+
+static void moxart_rtc_write_byte(struct device *dev, u8 data)
+{
+ struct moxart_rtc *moxart_rtc = dev_get_drvdata(dev);
+ int i;
+
+ for (i = 0; i < 8; i++, data >>= 1) {
+ gpio_set_value(moxart_rtc->gpio_sclk, 0);
+ gpio_set_value(moxart_rtc->gpio_data, ((data & 1) == 1));
+ udelay(GPIO_RTC_DELAY_TIME);
+ gpio_set_value(moxart_rtc->gpio_sclk, 1);
+ udelay(GPIO_RTC_DELAY_TIME);
+ }
+}
+
+static u8 moxart_rtc_read_byte(struct device *dev)
+{
+ struct moxart_rtc *moxart_rtc = dev_get_drvdata(dev);
+ int i;
+ u8 data = 0;
+
+ for (i = 0; i < 8; i++) {
+ gpio_set_value(moxart_rtc->gpio_sclk, 0);
+ udelay(GPIO_RTC_DELAY_TIME);
+ gpio_set_value(moxart_rtc->gpio_sclk, 1);
+ udelay(GPIO_RTC_DELAY_TIME);
+ if (gpio_get_value(moxart_rtc->gpio_data))
+ data |= (1 << i);
+ udelay(GPIO_RTC_DELAY_TIME);
+ }
+ return data;
+}
+
+static u8 moxart_rtc_read_register(struct device *dev, u8 cmd)
+{
+ struct moxart_rtc *moxart_rtc = dev_get_drvdata(dev);
+ u8 data;
+ unsigned long flags;
+
+ local_irq_save(flags);
+
+ gpio_direction_output(moxart_rtc->gpio_data, 0);
+ gpio_set_value(moxart_rtc->gpio_reset, 1);
+ udelay(GPIO_RTC_DELAY_TIME);
+ moxart_rtc_write_byte(dev, cmd);
+ gpio_direction_input(moxart_rtc->gpio_data);
+ udelay(GPIO_RTC_DELAY_TIME);
+ data = moxart_rtc_read_byte(dev);
+ gpio_set_value(moxart_rtc->gpio_sclk, 0);
+ gpio_set_value(moxart_rtc->gpio_reset, 0);
+ udelay(GPIO_RTC_DELAY_TIME);
+
+ local_irq_restore(flags);
+
+ return data;
+}
+
+static void moxart_rtc_write_register(struct device *dev, u8 cmd, u8 data)
+{
+ struct moxart_rtc *moxart_rtc = dev_get_drvdata(dev);
+ unsigned long flags;
+
+ local_irq_save(flags);
+
+ gpio_direction_output(moxart_rtc->gpio_data, 0);
+ gpio_set_value(moxart_rtc->gpio_reset, 1);
+ udelay(GPIO_RTC_DELAY_TIME);
+ moxart_rtc_write_byte(dev, cmd);
+ moxart_rtc_write_byte(dev, data);
+ gpio_set_value(moxart_rtc->gpio_sclk, 0);
+ gpio_set_value(moxart_rtc->gpio_reset, 0);
+ udelay(GPIO_RTC_DELAY_TIME);
+
+ local_irq_restore(flags);
+}
+
+static int moxart_rtc_set_time(struct device *dev, struct rtc_time *tm)
+{
+ struct moxart_rtc *moxart_rtc = dev_get_drvdata(dev);
+
+ spin_lock_irq(&moxart_rtc->rtc_lock);
+
+ moxart_rtc_write_register(dev, GPIO_RTC_PROTECT_W, 0);
+ moxart_rtc_write_register(dev, GPIO_RTC_YEAR_W,
+ (((tm->tm_year - 100) / 10) << 4) |
+ ((tm->tm_year - 100) % 10));
+
+ moxart_rtc_write_register(dev, GPIO_RTC_MONTH_W,
+ (((tm->tm_mon + 1) / 10) << 4) |
+ ((tm->tm_mon + 1) % 10));
+
+ moxart_rtc_write_register(dev, GPIO_RTC_DATE_W,
+ ((tm->tm_mday / 10) << 4) |
+ (tm->tm_mday % 10));
+
+ moxart_rtc_write_register(dev, GPIO_RTC_HOURS_W,
+ ((tm->tm_hour / 10) << 4) |
+ (tm->tm_hour % 10));
+
+ moxart_rtc_write_register(dev, GPIO_RTC_MINUTES_W,
+ ((tm->tm_min / 10) << 4) |
+ (tm->tm_min % 10));
+
+ moxart_rtc_write_register(dev, GPIO_RTC_SECONDS_W,
+ ((tm->tm_sec / 10) << 4) |
+ (tm->tm_sec % 10));
+
+ moxart_rtc_write_register(dev, GPIO_RTC_PROTECT_W, 0x80);
+
+ spin_unlock_irq(&moxart_rtc->rtc_lock);
+
+ dev_dbg(dev, "%s: success tm_year=%d tm_mon=%d\n"
+ "tm_mday=%d tm_hour=%d tm_min=%d tm_sec=%d\n",
+ __func__, tm->tm_year, tm->tm_mon, tm->tm_mday,
+ tm->tm_hour, tm->tm_min, tm->tm_sec);
+
+ return 0;
+}
+
+static int moxart_rtc_read_time(struct device *dev, struct rtc_time *tm)
+{
+ struct moxart_rtc *moxart_rtc = dev_get_drvdata(dev);
+ unsigned char v;
+
+ spin_lock_irq(&moxart_rtc->rtc_lock);
+
+ v = moxart_rtc_read_register(dev, GPIO_RTC_SECONDS_R);
+ tm->tm_sec = (((v & 0x70) >> 4) * 10) + (v & 0x0F);
+
+ v = moxart_rtc_read_register(dev, GPIO_RTC_MINUTES_R);
+ tm->tm_min = (((v & 0x70) >> 4) * 10) + (v & 0x0F);
+
+ v = moxart_rtc_read_register(dev, GPIO_RTC_HOURS_R);
+ if (v & 0x80) { /* 12-hour mode */
+ tm->tm_hour = (((v & 0x10) >> 4) * 10) + (v & 0x0F);
+ if (v & 0x20) { /* PM mode */
+ tm->tm_hour += 12;
+ if (tm->tm_hour >= 24)
+ tm->tm_hour = 0;
+ }
+ } else { /* 24-hour mode */
+ tm->tm_hour = (((v & 0x30) >> 4) * 10) + (v & 0x0F);
+ }
+
+ v = moxart_rtc_read_register(dev, GPIO_RTC_DATE_R);
+ tm->tm_mday = (((v & 0x30) >> 4) * 10) + (v & 0x0F);
+
+ v = moxart_rtc_read_register(dev, GPIO_RTC_MONTH_R);
+ tm->tm_mon = (((v & 0x10) >> 4) * 10) + (v & 0x0F);
+ tm->tm_mon--;
+
+ v = moxart_rtc_read_register(dev, GPIO_RTC_YEAR_R);
+ tm->tm_year = (((v & 0xF0) >> 4) * 10) + (v & 0x0F);
+ tm->tm_year += 100;
+ if (tm->tm_year <= 69)
+ tm->tm_year += 100;
+
+ v = moxart_rtc_read_register(dev, GPIO_RTC_DAY_R);
+ tm->tm_wday = (v & 0x0f) - 1;
+ tm->tm_yday = day_of_year[tm->tm_mon];
+ tm->tm_yday += (tm->tm_mday - 1);
+ if (tm->tm_mon >= 2) {
+ if (!(tm->tm_year % 4) && (tm->tm_year % 100))
+ tm->tm_yday++;
+ }
+
+ tm->tm_isdst = 0;
+
+ spin_unlock_irq(&moxart_rtc->rtc_lock);
+
+ return 0;
+}
+
+static const struct rtc_class_ops moxart_rtc_ops = {
+ .read_time = moxart_rtc_read_time,
+ .set_time = moxart_rtc_set_time,
+};
+
+static int moxart_rtc_probe(struct platform_device *pdev)
+{
+ struct moxart_rtc *moxart_rtc;
+ int ret = 0;
+
+ moxart_rtc = devm_kzalloc(&pdev->dev, sizeof(*moxart_rtc), GFP_KERNEL);
+ if (!moxart_rtc) {
+ dev_err(&pdev->dev, "devm_kzalloc failed\n");
+ return -ENOMEM;
+ }
+
+ moxart_rtc->gpio_data = of_get_named_gpio(pdev->dev.of_node,
+ "gpio-rtc-data", 0);
+ if (!gpio_is_valid(moxart_rtc->gpio_data)) {
+ dev_err(&pdev->dev, "invalid gpio (data): %d\n",
+ moxart_rtc->gpio_data);
+ return moxart_rtc->gpio_data;
+ }
+
+ moxart_rtc->gpio_sclk = of_get_named_gpio(pdev->dev.of_node,
+ "gpio-rtc-sclk", 0);
+ if (!gpio_is_valid(moxart_rtc->gpio_sclk)) {
+ dev_err(&pdev->dev, "invalid gpio (sclk): %d\n",
+ moxart_rtc->gpio_sclk);
+ return moxart_rtc->gpio_sclk;
+ }
+
+ moxart_rtc->gpio_reset = of_get_named_gpio(pdev->dev.of_node,
+ "gpio-rtc-reset", 0);
+ if (!gpio_is_valid(moxart_rtc->gpio_reset)) {
+ dev_err(&pdev->dev, "invalid gpio (reset): %d\n",
+ moxart_rtc->gpio_reset);
+ return moxart_rtc->gpio_reset;
+ }
+
+ spin_lock_init(&moxart_rtc->rtc_lock);
+ platform_set_drvdata(pdev, moxart_rtc);
+
+ ret = devm_gpio_request(&pdev->dev, moxart_rtc->gpio_data, "rtc_data");
+ if (ret) {
+ dev_err(&pdev->dev, "can't get rtc_data gpio\n");
+ return ret;
+ }
+
+ ret = devm_gpio_request_one(&pdev->dev, moxart_rtc->gpio_sclk,
+ GPIOF_DIR_OUT, "rtc_sclk");
+ if (ret) {
+ dev_err(&pdev->dev, "can't get rtc_sclk gpio\n");
+ return ret;
+ }
+
+ ret = devm_gpio_request_one(&pdev->dev, moxart_rtc->gpio_reset,
+ GPIOF_DIR_OUT, "rtc_reset");
+ if (ret) {
+ dev_err(&pdev->dev, "can't get rtc_reset gpio\n");
+ return ret;
+ }
+
+ moxart_rtc->rtc = devm_rtc_device_register(&pdev->dev, pdev->name,
+ &moxart_rtc_ops,
+ THIS_MODULE);
+ if (IS_ERR(moxart_rtc->rtc)) {
+ dev_err(&pdev->dev, "devm_rtc_device_register failed\n");
+ return PTR_ERR(moxart_rtc->rtc);
+ }
+
+ return 0;
+}
+
+static const struct of_device_id moxart_rtc_match[] = {
+ { .compatible = "moxa,moxart-rtc" },
+ { },
+};
+
+static struct platform_driver moxart_rtc_driver = {
+ .probe = moxart_rtc_probe,
+ .driver = {
+ .name = "moxart-rtc",
+ .owner = THIS_MODULE,
+ .of_match_table = moxart_rtc_match,
+ },
+};
+module_platform_driver(moxart_rtc_driver);
+
+MODULE_DESCRIPTION("MOXART RTC driver");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Jonas Jensen <jonas.jensen@gmail.com>");
diff --git a/drivers/rtc/rtc-mv.c b/drivers/rtc/rtc-mv.c
index baab802..d536c59 100644
--- a/drivers/rtc/rtc-mv.c
+++ b/drivers/rtc/rtc-mv.c
@@ -221,26 +221,17 @@
{
struct resource *res;
struct rtc_plat_data *pdata;
- resource_size_t size;
u32 rtc_time;
int ret = 0;
- res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!res)
- return -ENODEV;
-
pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
if (!pdata)
return -ENOMEM;
- size = resource_size(res);
- if (!devm_request_mem_region(&pdev->dev, res->start, size,
- pdev->name))
- return -EBUSY;
-
- pdata->ioaddr = devm_ioremap(&pdev->dev, res->start, size);
- if (!pdata->ioaddr)
- return -ENOMEM;
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ pdata->ioaddr = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(pdata->ioaddr))
+ return PTR_ERR(pdata->ioaddr);
pdata->clk = devm_clk_get(&pdev->dev, NULL);
/* Not all SoCs require a clock.*/
diff --git a/drivers/rtc/rtc-mxc.c b/drivers/rtc/rtc-mxc.c
index ab87bac..50c5726 100644
--- a/drivers/rtc/rtc-mxc.c
+++ b/drivers/rtc/rtc-mxc.c
@@ -377,22 +377,16 @@
unsigned long rate;
int ret;
- res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!res)
- return -ENODEV;
-
pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
if (!pdata)
return -ENOMEM;
pdata->devtype = pdev->id_entry->driver_data;
- if (!devm_request_mem_region(&pdev->dev, res->start,
- resource_size(res), pdev->name))
- return -EBUSY;
-
- pdata->ioaddr = devm_ioremap(&pdev->dev, res->start,
- resource_size(res));
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ pdata->ioaddr = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(pdata->ioaddr))
+ return PTR_ERR(pdata->ioaddr);
pdata->clk = devm_clk_get(&pdev->dev, NULL);
if (IS_ERR(pdata->clk)) {
diff --git a/drivers/rtc/rtc-nuc900.c b/drivers/rtc/rtc-nuc900.c
index 22861c5..248653c 100644
--- a/drivers/rtc/rtc-nuc900.c
+++ b/drivers/rtc/rtc-nuc900.c
@@ -99,7 +99,7 @@
if (!timeout)
return ERR_PTR(-EPERM);
- return 0;
+ return NULL;
}
static int nuc900_rtc_bcd2bin(unsigned int timereg,
diff --git a/drivers/rtc/rtc-omap.c b/drivers/rtc/rtc-omap.c
index c6ffbae..c7d97ee 100644
--- a/drivers/rtc/rtc-omap.c
+++ b/drivers/rtc/rtc-omap.c
@@ -70,6 +70,8 @@
#define OMAP_RTC_KICK0_REG 0x6c
#define OMAP_RTC_KICK1_REG 0x70
+#define OMAP_RTC_IRQWAKEEN 0x7c
+
/* OMAP_RTC_CTRL_REG bit fields: */
#define OMAP_RTC_CTRL_SPLIT (1<<7)
#define OMAP_RTC_CTRL_DISABLE (1<<6)
@@ -94,12 +96,21 @@
#define OMAP_RTC_INTERRUPTS_IT_ALARM (1<<3)
#define OMAP_RTC_INTERRUPTS_IT_TIMER (1<<2)
+/* OMAP_RTC_IRQWAKEEN bit fields: */
+#define OMAP_RTC_IRQWAKEEN_ALARM_WAKEEN (1<<1)
+
/* OMAP_RTC_KICKER values */
#define KICK0_VALUE 0x83e70b13
#define KICK1_VALUE 0x95a4f1e0
#define OMAP_RTC_HAS_KICKER 0x1
+/*
+ * Few RTC IP revisions has special WAKE-EN Register to enable Wakeup
+ * generation for event Alarm.
+ */
+#define OMAP_RTC_HAS_IRQWAKEEN 0x2
+
static void __iomem *rtc_base;
#define rtc_read(addr) readb(rtc_base + (addr))
@@ -299,12 +310,18 @@
static int omap_rtc_alarm;
static int omap_rtc_timer;
-#define OMAP_RTC_DATA_DA830_IDX 1
+#define OMAP_RTC_DATA_AM3352_IDX 1
+#define OMAP_RTC_DATA_DA830_IDX 2
static struct platform_device_id omap_rtc_devtype[] = {
{
.name = DRIVER_NAME,
- }, {
+ },
+ [OMAP_RTC_DATA_AM3352_IDX] = {
+ .name = "am3352-rtc",
+ .driver_data = OMAP_RTC_HAS_KICKER | OMAP_RTC_HAS_IRQWAKEEN,
+ },
+ [OMAP_RTC_DATA_DA830_IDX] = {
.name = "da830-rtc",
.driver_data = OMAP_RTC_HAS_KICKER,
},
@@ -316,6 +333,9 @@
{ .compatible = "ti,da830-rtc",
.data = &omap_rtc_devtype[OMAP_RTC_DATA_DA830_IDX],
},
+ { .compatible = "ti,am3352-rtc",
+ .data = &omap_rtc_devtype[OMAP_RTC_DATA_AM3352_IDX],
+ },
{},
};
MODULE_DEVICE_TABLE(of, omap_rtc_of_match);
@@ -464,16 +484,28 @@
static int omap_rtc_suspend(struct device *dev)
{
+ u8 irqwake_stat;
+ struct platform_device *pdev = to_platform_device(dev);
+ const struct platform_device_id *id_entry =
+ platform_get_device_id(pdev);
+
irqstat = rtc_read(OMAP_RTC_INTERRUPTS_REG);
/* FIXME the RTC alarm is not currently acting as a wakeup event
- * source, and in fact this enable() call is just saving a flag
- * that's never used...
+ * source on some platforms, and in fact this enable() call is just
+ * saving a flag that's never used...
*/
- if (device_may_wakeup(dev))
+ if (device_may_wakeup(dev)) {
enable_irq_wake(omap_rtc_alarm);
- else
+
+ if (id_entry->driver_data & OMAP_RTC_HAS_IRQWAKEEN) {
+ irqwake_stat = rtc_read(OMAP_RTC_IRQWAKEEN);
+ irqwake_stat |= OMAP_RTC_IRQWAKEEN_ALARM_WAKEEN;
+ rtc_write(irqwake_stat, OMAP_RTC_IRQWAKEEN);
+ }
+ } else {
rtc_write(0, OMAP_RTC_INTERRUPTS_REG);
+ }
/* Disable the clock/module */
pm_runtime_put_sync(dev);
@@ -483,13 +515,25 @@
static int omap_rtc_resume(struct device *dev)
{
+ u8 irqwake_stat;
+ struct platform_device *pdev = to_platform_device(dev);
+ const struct platform_device_id *id_entry =
+ platform_get_device_id(pdev);
+
/* Enable the clock/module so that we can access the registers */
pm_runtime_get_sync(dev);
- if (device_may_wakeup(dev))
+ if (device_may_wakeup(dev)) {
disable_irq_wake(omap_rtc_alarm);
- else
+
+ if (id_entry->driver_data & OMAP_RTC_HAS_IRQWAKEEN) {
+ irqwake_stat = rtc_read(OMAP_RTC_IRQWAKEEN);
+ irqwake_stat &= ~OMAP_RTC_IRQWAKEEN_ALARM_WAKEEN;
+ rtc_write(irqwake_stat, OMAP_RTC_IRQWAKEEN);
+ }
+ } else {
rtc_write(irqstat, OMAP_RTC_INTERRUPTS_REG);
+ }
return 0;
}
#endif
diff --git a/drivers/rtc/rtc-palmas.c b/drivers/rtc/rtc-palmas.c
index a1fecc8..fffb7d3 100644
--- a/drivers/rtc/rtc-palmas.c
+++ b/drivers/rtc/rtc-palmas.c
@@ -238,6 +238,15 @@
struct palmas *palmas = dev_get_drvdata(pdev->dev.parent);
struct palmas_rtc *palmas_rtc = NULL;
int ret;
+ bool enable_bb_charging = false;
+ bool high_bb_charging;
+
+ if (pdev->dev.of_node) {
+ enable_bb_charging = of_property_read_bool(pdev->dev.of_node,
+ "ti,backup-battery-chargeable");
+ high_bb_charging = of_property_read_bool(pdev->dev.of_node,
+ "ti,backup-battery-charge-high-current");
+ }
palmas_rtc = devm_kzalloc(&pdev->dev, sizeof(struct palmas_rtc),
GFP_KERNEL);
@@ -254,6 +263,32 @@
palmas_rtc->dev = &pdev->dev;
platform_set_drvdata(pdev, palmas_rtc);
+ if (enable_bb_charging) {
+ unsigned reg = PALMAS_BACKUP_BATTERY_CTRL_BBS_BBC_LOW_ICHRG;
+
+ if (high_bb_charging)
+ reg = 0;
+
+ ret = palmas_update_bits(palmas, PALMAS_PMU_CONTROL_BASE,
+ PALMAS_BACKUP_BATTERY_CTRL,
+ PALMAS_BACKUP_BATTERY_CTRL_BBS_BBC_LOW_ICHRG, reg);
+ if (ret < 0) {
+ dev_err(&pdev->dev,
+ "BACKUP_BATTERY_CTRL update failed, %d\n", ret);
+ return ret;
+ }
+
+ ret = palmas_update_bits(palmas, PALMAS_PMU_CONTROL_BASE,
+ PALMAS_BACKUP_BATTERY_CTRL,
+ PALMAS_BACKUP_BATTERY_CTRL_BB_CHG_EN,
+ PALMAS_BACKUP_BATTERY_CTRL_BB_CHG_EN);
+ if (ret < 0) {
+ dev_err(&pdev->dev,
+ "BACKUP_BATTERY_CTRL update failed, %d\n", ret);
+ return ret;
+ }
+ }
+
/* Start RTC */
ret = palmas_update_bits(palmas, PALMAS_RTC_BASE, PALMAS_RTC_CTRL_REG,
PALMAS_RTC_CTRL_REG_STOP_RTC,
diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index 205b9f7..1ee514a 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -203,11 +203,6 @@
return 0;
}
-static int pcf2127_remove(struct i2c_client *client)
-{
- return 0;
-}
-
static const struct i2c_device_id pcf2127_id[] = {
{ "pcf2127", 0 },
{ }
@@ -229,7 +224,6 @@
.of_match_table = of_match_ptr(pcf2127_of_match),
},
.probe = pcf2127_probe,
- .remove = pcf2127_remove,
.id_table = pcf2127_id,
};
diff --git a/drivers/rtc/rtc-sirfsoc.c b/drivers/rtc/rtc-sirfsoc.c
index aa7ed4b..63460cf 100644
--- a/drivers/rtc/rtc-sirfsoc.c
+++ b/drivers/rtc/rtc-sirfsoc.c
@@ -44,6 +44,7 @@
struct rtc_device *rtc;
u32 rtc_base;
u32 irq;
+ unsigned irq_wake;
/* Overflow for every 8 years extra time */
u32 overflow_rtc;
#ifdef CONFIG_PM
@@ -355,8 +356,8 @@
rtcdrv->saved_counter =
sirfsoc_rtc_iobrg_readl(rtcdrv->rtc_base + RTC_CN);
rtcdrv->saved_overflow_rtc = rtcdrv->overflow_rtc;
- if (device_may_wakeup(&pdev->dev))
- enable_irq_wake(rtcdrv->irq);
+ if (device_may_wakeup(&pdev->dev) && !enable_irq_wake(rtcdrv->irq))
+ rtcdrv->irq_wake = 1;
return 0;
}
@@ -423,8 +424,10 @@
struct platform_device *pdev = to_platform_device(dev);
struct sirfsoc_rtc_drv *rtcdrv = platform_get_drvdata(pdev);
sirfsoc_rtc_thaw(dev);
- if (device_may_wakeup(&pdev->dev))
+ if (device_may_wakeup(&pdev->dev) && rtcdrv->irq_wake) {
disable_irq_wake(rtcdrv->irq);
+ rtcdrv->irq_wake = 0;
+ }
return 0;
}
@@ -434,8 +437,10 @@
struct platform_device *pdev = to_platform_device(dev);
struct sirfsoc_rtc_drv *rtcdrv = platform_get_drvdata(pdev);
- if (device_may_wakeup(&pdev->dev))
+ if (device_may_wakeup(&pdev->dev) && rtcdrv->irq_wake) {
disable_irq_wake(rtcdrv->irq);
+ rtcdrv->irq_wake = 0;
+ }
return 0;
}
diff --git a/drivers/rtc/rtc-stk17ta8.c b/drivers/rtc/rtc-stk17ta8.c
index af5e97e..a176ba6 100644
--- a/drivers/rtc/rtc-stk17ta8.c
+++ b/drivers/rtc/rtc-stk17ta8.c
@@ -294,19 +294,14 @@
void __iomem *ioaddr;
int ret = 0;
- res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!res)
- return -ENODEV;
-
pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
if (!pdata)
return -ENOMEM;
- if (!devm_request_mem_region(&pdev->dev, res->start, RTC_REG_SIZE,
- pdev->name))
- return -EBUSY;
- ioaddr = devm_ioremap(&pdev->dev, res->start, RTC_REG_SIZE);
- if (!ioaddr)
- return -ENOMEM;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ ioaddr = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(ioaddr))
+ return PTR_ERR(ioaddr);
pdata->ioaddr = ioaddr;
pdata->irq = platform_get_irq(pdev, 0);
diff --git a/drivers/rtc/rtc-tx4939.c b/drivers/rtc/rtc-tx4939.c
index f9a0677..4f87234 100644
--- a/drivers/rtc/rtc-tx4939.c
+++ b/drivers/rtc/rtc-tx4939.c
@@ -244,9 +244,6 @@
struct resource *res;
int irq, ret;
- res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!res)
- return -ENODEV;
irq = platform_get_irq(pdev, 0);
if (irq < 0)
return -ENODEV;
@@ -255,13 +252,10 @@
return -ENOMEM;
platform_set_drvdata(pdev, pdata);
- if (!devm_request_mem_region(&pdev->dev, res->start,
- resource_size(res), pdev->name))
- return -EBUSY;
- pdata->rtcreg = devm_ioremap(&pdev->dev, res->start,
- resource_size(res));
- if (!pdata->rtcreg)
- return -EBUSY;
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ pdata->rtcreg = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(pdata->rtcreg))
+ return PTR_ERR(pdata->rtcreg);
spin_lock_init(&pdata->lock);
tx4939_rtc_cmd(pdata->rtcreg, TX4939_RTCCTL_COMMAND_NOP);
diff --git a/drivers/s390/block/dasd_diag.c b/drivers/s390/block/dasd_diag.c
index feca317..92bd22c 100644
--- a/drivers/s390/block/dasd_diag.c
+++ b/drivers/s390/block/dasd_diag.c
@@ -645,7 +645,7 @@
}
ASCEBC(dasd_diag_discipline.ebcname, 4);
- service_subclass_irq_register();
+ irq_subclass_register(IRQ_SUBCLASS_SERVICE_SIGNAL);
register_external_interrupt(0x2603, dasd_ext_handler);
dasd_diag_discipline_pointer = &dasd_diag_discipline;
return 0;
@@ -655,7 +655,7 @@
dasd_diag_cleanup(void)
{
unregister_external_interrupt(0x2603, dasd_ext_handler);
- service_subclass_irq_unregister();
+ irq_subclass_unregister(IRQ_SUBCLASS_SERVICE_SIGNAL);
dasd_diag_discipline_pointer = NULL;
}
diff --git a/drivers/s390/char/fs3270.c b/drivers/s390/char/fs3270.c
index 96e52bf..f93cc32 100644
--- a/drivers/s390/char/fs3270.c
+++ b/drivers/s390/char/fs3270.c
@@ -524,20 +524,20 @@
.llseek = no_llseek,
};
-void fs3270_create_cb(int minor)
+static void fs3270_create_cb(int minor)
{
__register_chrdev(IBM_FS3270_MAJOR, minor, 1, "tub", &fs3270_fops);
device_create(class3270, NULL, MKDEV(IBM_FS3270_MAJOR, minor),
NULL, "3270/tub%d", minor);
}
-void fs3270_destroy_cb(int minor)
+static void fs3270_destroy_cb(int minor)
{
device_destroy(class3270, MKDEV(IBM_FS3270_MAJOR, minor));
__unregister_chrdev(IBM_FS3270_MAJOR, minor, 1, "tub");
}
-struct raw3270_notifier fs3270_notifier =
+static struct raw3270_notifier fs3270_notifier =
{
.create = fs3270_create_cb,
.destroy = fs3270_destroy_cb,
diff --git a/drivers/s390/char/sclp.c b/drivers/s390/char/sclp.c
index 3e4fb4e..a3aa374 100644
--- a/drivers/s390/char/sclp.c
+++ b/drivers/s390/char/sclp.c
@@ -910,12 +910,12 @@
spin_unlock_irqrestore(&sclp_lock, flags);
/* Enable service-signal interruption - needs to happen
* with IRQs enabled. */
- service_subclass_irq_register();
+ irq_subclass_register(IRQ_SUBCLASS_SERVICE_SIGNAL);
/* Wait for signal from interrupt or timeout */
sclp_sync_wait();
/* Disable service-signal interruption - needs to happen
* with IRQs enabled. */
- service_subclass_irq_unregister();
+ irq_subclass_unregister(IRQ_SUBCLASS_SERVICE_SIGNAL);
spin_lock_irqsave(&sclp_lock, flags);
del_timer(&sclp_request_timer);
if (sclp_init_req.status == SCLP_REQ_DONE &&
@@ -1131,7 +1131,7 @@
spin_unlock_irqrestore(&sclp_lock, flags);
/* Enable service-signal external interruption - needs to happen with
* IRQs enabled. */
- service_subclass_irq_register();
+ irq_subclass_register(IRQ_SUBCLASS_SERVICE_SIGNAL);
sclp_init_mask(1);
return 0;
diff --git a/drivers/s390/char/tty3270.c b/drivers/s390/char/tty3270.c
index cee69da..a0f47c8 100644
--- a/drivers/s390/char/tty3270.c
+++ b/drivers/s390/char/tty3270.c
@@ -1845,17 +1845,17 @@
.set_termios = tty3270_set_termios
};
-void tty3270_create_cb(int minor)
+static void tty3270_create_cb(int minor)
{
tty_register_device(tty3270_driver, minor - RAW3270_FIRSTMINOR, NULL);
}
-void tty3270_destroy_cb(int minor)
+static void tty3270_destroy_cb(int minor)
{
tty_unregister_device(tty3270_driver, minor - RAW3270_FIRSTMINOR);
}
-struct raw3270_notifier tty3270_notifier =
+static struct raw3270_notifier tty3270_notifier =
{
.create = tty3270_create_cb,
.destroy = tty3270_destroy_cb,
diff --git a/drivers/s390/char/zcore.c b/drivers/s390/char/zcore.c
index 9e5e146..794820a 100644
--- a/drivers/s390/char/zcore.c
+++ b/drivers/s390/char/zcore.c
@@ -30,8 +30,8 @@
#define TRACE(x...) debug_sprintf_event(zcore_dbf, 1, x)
-#define TO_USER 0
-#define TO_KERNEL 1
+#define TO_USER 1
+#define TO_KERNEL 0
#define CHUNK_INFO_SIZE 34 /* 2 16-byte char, each followed by blank */
enum arch_id {
@@ -73,7 +73,7 @@
* @count: Size of buffer, which should be copied
* @mode: Either TO_KERNEL or TO_USER
*/
-static int memcpy_hsa(void *dest, unsigned long src, size_t count, int mode)
+int memcpy_hsa(void *dest, unsigned long src, size_t count, int mode)
{
int offs, blk_num;
static char buf[PAGE_SIZE] __attribute__((__aligned__(PAGE_SIZE)));
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index d4174b8..02300dc 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -413,7 +413,7 @@
register unsigned long reg2 asm ("2") = (unsigned long) msg;
register unsigned long reg3 asm ("3") = (unsigned long) length;
register unsigned long reg4 asm ("4") = (unsigned int) (psmid >> 32);
- register unsigned long reg5 asm ("5") = (unsigned int) psmid;
+ register unsigned long reg5 asm ("5") = psmid & 0xffffffff;
if (special == 1)
reg0 |= 0x400000UL;
diff --git a/drivers/s390/kvm/kvm_virtio.c b/drivers/s390/kvm/kvm_virtio.c
index 2ea6165..af2166f 100644
--- a/drivers/s390/kvm/kvm_virtio.c
+++ b/drivers/s390/kvm/kvm_virtio.c
@@ -472,7 +472,7 @@
INIT_WORK(&hotplug_work, hotplug_devices);
- service_subclass_irq_register();
+ irq_subclass_register(IRQ_SUBCLASS_SERVICE_SIGNAL);
register_external_interrupt(0x2603, kvm_extint_handler);
scan_devices();
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index ff12d46..5964800 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -10,7 +10,7 @@
*
* Forward port and refactoring to modern qla2xxx and target/configfs
*
- * Copyright (C) 2010-2011 Nicholas A. Bellinger <nab@kernel.org>
+ * Copyright (C) 2010-2013 Nicholas A. Bellinger <nab@kernel.org>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index a6da313..f85b9e5 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -2,12 +2,9 @@
* This file contains tcm implementation using v4 configfs fabric infrastructure
* for QLogic target mode HBAs
*
- * ?? Copyright 2010-2011 RisingTide Systems LLC.
+ * (c) Copyright 2010-2013 Datera, Inc.
*
- * Licensed to the Linux Foundation under the General Public License (GPL)
- * version 2.
- *
- * Author: Nicholas A. Bellinger <nab@risingtidesystems.com>
+ * Author: Nicholas A. Bellinger <nab@daterainc.com>
*
* tcm_qla2xxx_parse_wwn() and tcm_qla2xxx_format_wwn() contains code from
* the TCM_FC / Open-FCoE.org fabric module.
@@ -360,6 +357,14 @@
return QLA_TPG_ATTRIB(tpg)->prod_mode_write_protect;
}
+static int tcm_qla2xxx_check_demo_mode_login_only(struct se_portal_group *se_tpg)
+{
+ struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg,
+ struct tcm_qla2xxx_tpg, se_tpg);
+
+ return QLA_TPG_ATTRIB(tpg)->demo_mode_login_only;
+}
+
static struct se_node_acl *tcm_qla2xxx_alloc_fabric_acl(
struct se_portal_group *se_tpg)
{
@@ -489,38 +494,13 @@
return 0;
}
-/*
- * The LIO target core uses DMA_TO_DEVICE to mean that data is going
- * to the target (eg handling a WRITE) and DMA_FROM_DEVICE to mean
- * that data is coming from the target (eg handling a READ). However,
- * this is just the opposite of what we have to tell the DMA mapping
- * layer -- eg when handling a READ, the HBA will have to DMA the data
- * out of memory so it can send it to the initiator, which means we
- * need to use DMA_TO_DEVICE when we map the data.
- */
-static enum dma_data_direction tcm_qla2xxx_mapping_dir(struct se_cmd *se_cmd)
-{
- if (se_cmd->se_cmd_flags & SCF_BIDI)
- return DMA_BIDIRECTIONAL;
-
- switch (se_cmd->data_direction) {
- case DMA_TO_DEVICE:
- return DMA_FROM_DEVICE;
- case DMA_FROM_DEVICE:
- return DMA_TO_DEVICE;
- case DMA_NONE:
- default:
- return DMA_NONE;
- }
-}
-
static int tcm_qla2xxx_write_pending(struct se_cmd *se_cmd)
{
struct qla_tgt_cmd *cmd = container_of(se_cmd,
struct qla_tgt_cmd, se_cmd);
cmd->bufflen = se_cmd->data_length;
- cmd->dma_data_direction = tcm_qla2xxx_mapping_dir(se_cmd);
+ cmd->dma_data_direction = target_reverse_dma_direction(se_cmd);
cmd->sg_cnt = se_cmd->t_data_nents;
cmd->sg = se_cmd->t_data_sg;
@@ -656,7 +636,7 @@
struct qla_tgt_cmd, se_cmd);
cmd->bufflen = se_cmd->data_length;
- cmd->dma_data_direction = tcm_qla2xxx_mapping_dir(se_cmd);
+ cmd->dma_data_direction = target_reverse_dma_direction(se_cmd);
cmd->aborted = (se_cmd->transport_state & CMD_T_ABORTED);
cmd->sg_cnt = se_cmd->t_data_nents;
@@ -680,7 +660,7 @@
cmd->sg = NULL;
cmd->sg_cnt = 0;
cmd->offset = 0;
- cmd->dma_data_direction = tcm_qla2xxx_mapping_dir(se_cmd);
+ cmd->dma_data_direction = target_reverse_dma_direction(se_cmd);
cmd->aborted = (se_cmd->transport_state & CMD_T_ABORTED);
if (se_cmd->data_direction == DMA_FROM_DEVICE) {
@@ -939,11 +919,19 @@
DEF_QLA_TPG_ATTRIB(prod_mode_write_protect);
QLA_TPG_ATTR(prod_mode_write_protect, S_IRUGO | S_IWUSR);
+/*
+ * Define tcm_qla2xxx_tpg_attrib_s_demo_mode_login_only
+ */
+DEF_QLA_TPG_ATTR_BOOL(demo_mode_login_only);
+DEF_QLA_TPG_ATTRIB(demo_mode_login_only);
+QLA_TPG_ATTR(demo_mode_login_only, S_IRUGO | S_IWUSR);
+
static struct configfs_attribute *tcm_qla2xxx_tpg_attrib_attrs[] = {
&tcm_qla2xxx_tpg_attrib_generate_node_acls.attr,
&tcm_qla2xxx_tpg_attrib_cache_dynamic_acls.attr,
&tcm_qla2xxx_tpg_attrib_demo_mode_write_protect.attr,
&tcm_qla2xxx_tpg_attrib_prod_mode_write_protect.attr,
+ &tcm_qla2xxx_tpg_attrib_demo_mode_login_only.attr,
NULL,
};
@@ -1042,6 +1030,7 @@
QLA_TPG_ATTRIB(tpg)->generate_node_acls = 1;
QLA_TPG_ATTRIB(tpg)->demo_mode_write_protect = 1;
QLA_TPG_ATTRIB(tpg)->cache_dynamic_acls = 1;
+ QLA_TPG_ATTRIB(tpg)->demo_mode_login_only = 1;
ret = core_tpg_register(&tcm_qla2xxx_fabric_configfs->tf_ops, wwn,
&tpg->se_tpg, tpg, TRANSPORT_TPG_TYPE_NORMAL);
@@ -1736,7 +1725,7 @@
tcm_qla2xxx_check_demo_write_protect,
.tpg_check_prod_mode_write_protect =
tcm_qla2xxx_check_prod_write_protect,
- .tpg_check_demo_mode_login_only = tcm_qla2xxx_check_true,
+ .tpg_check_demo_mode_login_only = tcm_qla2xxx_check_demo_mode_login_only,
.tpg_alloc_fabric_acl = tcm_qla2xxx_alloc_fabric_acl,
.tpg_release_fabric_acl = tcm_qla2xxx_release_fabric_acl,
.tpg_get_inst_index = tcm_qla2xxx_tpg_get_inst_index,
@@ -1784,7 +1773,7 @@
.tpg_check_demo_mode_cache = tcm_qla2xxx_check_true,
.tpg_check_demo_mode_write_protect = tcm_qla2xxx_check_true,
.tpg_check_prod_mode_write_protect = tcm_qla2xxx_check_false,
- .tpg_check_demo_mode_login_only = tcm_qla2xxx_check_true,
+ .tpg_check_demo_mode_login_only = tcm_qla2xxx_check_demo_mode_login_only,
.tpg_alloc_fabric_acl = tcm_qla2xxx_alloc_fabric_acl,
.tpg_release_fabric_acl = tcm_qla2xxx_release_fabric_acl,
.tpg_get_inst_index = tcm_qla2xxx_tpg_get_inst_index,
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.h b/drivers/scsi/qla2xxx/tcm_qla2xxx.h
index 9ba075f..3293275 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.h
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.h
@@ -29,6 +29,7 @@
int cache_dynamic_acls;
int demo_mode_write_protect;
int prod_mode_write_protect;
+ int demo_mode_login_only;
};
struct tcm_qla2xxx_tpg {
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index 0170d4c..b9c53cc 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -55,7 +55,6 @@
config SPI_ALTERA
tristate "Altera SPI Controller"
- depends on GENERIC_HARDIRQS
select SPI_BITBANG
help
This is the driver for the Altera SPI Controller.
@@ -358,7 +357,7 @@
config SPI_PXA2XX
tristate "PXA2xx SSP SPI master"
- depends on (ARCH_PXA || PCI || ACPI) && GENERIC_HARDIRQS
+ depends on (ARCH_PXA || PCI || ACPI)
select PXA_SSP if ARCH_PXA
help
This enables using a PXA2xx or Sodaville SSP port as a SPI master
diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c
index 21a3f72..8e76ddc 100644
--- a/drivers/staging/android/ashmem.c
+++ b/drivers/staging/android/ashmem.c
@@ -341,27 +341,26 @@
/*
* ashmem_shrink - our cache shrinker, called from mm/vmscan.c :: shrink_slab
*
- * 'nr_to_scan' is the number of objects (pages) to prune, or 0 to query how
- * many objects (pages) we have in total.
+ * 'nr_to_scan' is the number of objects to scan for freeing.
*
* 'gfp_mask' is the mask of the allocation that got us into this mess.
*
- * Return value is the number of objects (pages) remaining, or -1 if we cannot
+ * Return value is the number of objects freed or -1 if we cannot
* proceed without risk of deadlock (due to gfp_mask).
*
* We approximate LRU via least-recently-unpinned, jettisoning unpinned partial
* chunks of ashmem regions LRU-wise one-at-a-time until we hit 'nr_to_scan'
* pages freed.
*/
-static int ashmem_shrink(struct shrinker *s, struct shrink_control *sc)
+static unsigned long
+ashmem_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
{
struct ashmem_range *range, *next;
+ unsigned long freed = 0;
/* We might recurse into filesystem code, so bail out if necessary */
- if (sc->nr_to_scan && !(sc->gfp_mask & __GFP_FS))
- return -1;
- if (!sc->nr_to_scan)
- return lru_count;
+ if (!(sc->gfp_mask & __GFP_FS))
+ return SHRINK_STOP;
mutex_lock(&ashmem_mutex);
list_for_each_entry_safe(range, next, &ashmem_lru_list, lru) {
@@ -374,17 +373,32 @@
range->purged = ASHMEM_WAS_PURGED;
lru_del(range);
- sc->nr_to_scan -= range_size(range);
- if (sc->nr_to_scan <= 0)
+ freed += range_size(range);
+ if (--sc->nr_to_scan <= 0)
break;
}
mutex_unlock(&ashmem_mutex);
+ return freed;
+}
+static unsigned long
+ashmem_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
+{
+ /*
+ * note that lru_count is count of pages on the lru, not a count of
+ * objects on the list. This means the scan function needs to return the
+ * number of pages freed, not the number of objects scanned.
+ */
return lru_count;
}
static struct shrinker ashmem_shrinker = {
- .shrink = ashmem_shrink,
+ .count_objects = ashmem_shrink_count,
+ .scan_objects = ashmem_shrink_scan,
+ /*
+ * XXX (dchinner): I wish people would comment on why they need on
+ * significant changes to the default value here
+ */
.seeks = DEFAULT_SEEKS * 4,
};
@@ -690,11 +704,11 @@
if (capable(CAP_SYS_ADMIN)) {
struct shrink_control sc = {
.gfp_mask = GFP_KERNEL,
- .nr_to_scan = 0,
+ .nr_to_scan = LONG_MAX,
};
- ret = ashmem_shrink(&ashmem_shrinker, &sc);
- sc.nr_to_scan = ret;
- ashmem_shrink(&ashmem_shrinker, &sc);
+
+ nodes_setall(sc.nodes_to_scan);
+ ashmem_shrink_scan(&ashmem_shrinker, &sc);
}
break;
}
diff --git a/drivers/staging/android/logger.c b/drivers/staging/android/logger.c
index a8c3444..d42f5785 100644
--- a/drivers/staging/android/logger.c
+++ b/drivers/staging/android/logger.c
@@ -481,7 +481,7 @@
header.sec = now.tv_sec;
header.nsec = now.tv_nsec;
header.euid = current_euid();
- header.len = min_t(size_t, iocb->ki_left, LOGGER_ENTRY_MAX_PAYLOAD);
+ header.len = min_t(size_t, iocb->ki_nbytes, LOGGER_ENTRY_MAX_PAYLOAD);
header.hdr_size = sizeof(struct logger_entry);
/* null writes succeed, return zero */
diff --git a/drivers/staging/android/lowmemorykiller.c b/drivers/staging/android/lowmemorykiller.c
index fe74494..6f094b3 100644
--- a/drivers/staging/android/lowmemorykiller.c
+++ b/drivers/staging/android/lowmemorykiller.c
@@ -66,11 +66,20 @@
pr_info(x); \
} while (0)
-static int lowmem_shrink(struct shrinker *s, struct shrink_control *sc)
+static unsigned long lowmem_count(struct shrinker *s,
+ struct shrink_control *sc)
+{
+ return global_page_state(NR_ACTIVE_ANON) +
+ global_page_state(NR_ACTIVE_FILE) +
+ global_page_state(NR_INACTIVE_ANON) +
+ global_page_state(NR_INACTIVE_FILE);
+}
+
+static unsigned long lowmem_scan(struct shrinker *s, struct shrink_control *sc)
{
struct task_struct *tsk;
struct task_struct *selected = NULL;
- int rem = 0;
+ unsigned long rem = 0;
int tasksize;
int i;
short min_score_adj = OOM_SCORE_ADJ_MAX + 1;
@@ -92,19 +101,17 @@
break;
}
}
- if (sc->nr_to_scan > 0)
- lowmem_print(3, "lowmem_shrink %lu, %x, ofree %d %d, ma %hd\n",
- sc->nr_to_scan, sc->gfp_mask, other_free,
- other_file, min_score_adj);
- rem = global_page_state(NR_ACTIVE_ANON) +
- global_page_state(NR_ACTIVE_FILE) +
- global_page_state(NR_INACTIVE_ANON) +
- global_page_state(NR_INACTIVE_FILE);
- if (sc->nr_to_scan <= 0 || min_score_adj == OOM_SCORE_ADJ_MAX + 1) {
- lowmem_print(5, "lowmem_shrink %lu, %x, return %d\n",
- sc->nr_to_scan, sc->gfp_mask, rem);
- return rem;
+
+ lowmem_print(3, "lowmem_scan %lu, %x, ofree %d %d, ma %hd\n",
+ sc->nr_to_scan, sc->gfp_mask, other_free,
+ other_file, min_score_adj);
+
+ if (min_score_adj == OOM_SCORE_ADJ_MAX + 1) {
+ lowmem_print(5, "lowmem_scan %lu, %x, return 0\n",
+ sc->nr_to_scan, sc->gfp_mask);
+ return 0;
}
+
selected_oom_score_adj = min_score_adj;
rcu_read_lock();
@@ -154,16 +161,18 @@
lowmem_deathpending_timeout = jiffies + HZ;
send_sig(SIGKILL, selected, 0);
set_tsk_thread_flag(selected, TIF_MEMDIE);
- rem -= selected_tasksize;
+ rem += selected_tasksize;
}
- lowmem_print(4, "lowmem_shrink %lu, %x, return %d\n",
+
+ lowmem_print(4, "lowmem_scan %lu, %x, return %lu\n",
sc->nr_to_scan, sc->gfp_mask, rem);
rcu_read_unlock();
return rem;
}
static struct shrinker lowmem_shrinker = {
- .shrink = lowmem_shrink,
+ .scan_objects = lowmem_scan,
+ .count_objects = lowmem_count,
.seeks = DEFAULT_SEEKS * 16
};
diff --git a/drivers/staging/lustre/include/linux/libcfs/linux/linux-mem.h b/drivers/staging/lustre/include/linux/libcfs/linux/linux-mem.h
index 63efb7b..2af15d4 100644
--- a/drivers/staging/lustre/include/linux/libcfs/linux/linux-mem.h
+++ b/drivers/staging/lustre/include/linux/libcfs/linux/linux-mem.h
@@ -79,42 +79,4 @@
do { __oldfs = get_fs(); set_fs(get_ds());} while(0)
#define MMSPACE_CLOSE set_fs(__oldfs)
-/*
- * Shrinker
- */
-
-# define SHRINKER_ARGS(sc, nr_to_scan, gfp_mask) \
- struct shrinker *shrinker, \
- struct shrink_control *sc
-# define shrink_param(sc, var) ((sc)->var)
-
-typedef int (*shrinker_t)(SHRINKER_ARGS(sc, nr_to_scan, gfp_mask));
-
-static inline
-struct shrinker *set_shrinker(int seek, shrinker_t func)
-{
- struct shrinker *s;
-
- s = kmalloc(sizeof(*s), GFP_KERNEL);
- if (s == NULL)
- return (NULL);
-
- s->shrink = func;
- s->seeks = seek;
-
- register_shrinker(s);
-
- return s;
-}
-
-static inline
-void remove_shrinker(struct shrinker *shrinker)
-{
- if (shrinker == NULL)
- return;
-
- unregister_shrinker(shrinker);
- kfree(shrinker);
-}
-
#endif /* __LINUX_CFS_MEM_H__ */
diff --git a/drivers/staging/lustre/lustre/ldlm/ldlm_pool.c b/drivers/staging/lustre/lustre/ldlm/ldlm_pool.c
index 454027d..0025ee6 100644
--- a/drivers/staging/lustre/lustre/ldlm/ldlm_pool.c
+++ b/drivers/staging/lustre/lustre/ldlm/ldlm_pool.c
@@ -521,7 +521,7 @@
int nr, unsigned int gfp_mask)
{
struct ldlm_namespace *ns;
- int canceled = 0, unused;
+ int unused;
ns = ldlm_pl2ns(pl);
@@ -540,14 +540,10 @@
unused = ns->ns_nr_unused;
spin_unlock(&ns->ns_lock);
- if (nr) {
- canceled = ldlm_cancel_lru(ns, nr, LCF_ASYNC,
- LDLM_CANCEL_SHRINK);
- }
- /*
- * Return the number of potentially reclaimable locks.
- */
- return ((unused - canceled) / 100) * sysctl_vfs_cache_pressure;
+ if (nr == 0)
+ return (unused / 100) * sysctl_vfs_cache_pressure;
+ else
+ return ldlm_cancel_lru(ns, nr, LCF_ASYNC, LDLM_CANCEL_SHRINK);
}
struct ldlm_pool_ops ldlm_srv_pool_ops = {
@@ -601,9 +597,10 @@
return recalc_interval_sec;
}
-/**
+/*
* Pool shrink wrapper. Will call either client or server pool recalc callback
- * depending what pool \a pl is used.
+ * depending what pool pl is used. When nr == 0, just return the number of
+ * freeable locks. Otherwise, return the number of canceled locks.
*/
int ldlm_pool_shrink(struct ldlm_pool *pl, int nr,
unsigned int gfp_mask)
@@ -1017,29 +1014,24 @@
}
static struct ptlrpc_thread *ldlm_pools_thread;
-static struct shrinker *ldlm_pools_srv_shrinker;
-static struct shrinker *ldlm_pools_cli_shrinker;
static struct completion ldlm_pools_comp;
/*
- * Cancel \a nr locks from all namespaces (if possible). Returns number of
- * cached locks after shrink is finished. All namespaces are asked to
- * cancel approximately equal amount of locks to keep balancing.
+ * count locks from all namespaces (if possible). Returns number of
+ * cached locks.
*/
-static int ldlm_pools_shrink(ldlm_side_t client, int nr,
- unsigned int gfp_mask)
+static unsigned long ldlm_pools_count(ldlm_side_t client, unsigned int gfp_mask)
{
- int total = 0, cached = 0, nr_ns;
+ int total = 0, nr_ns;
struct ldlm_namespace *ns;
struct ldlm_namespace *ns_old = NULL; /* loop detection */
void *cookie;
- if (client == LDLM_NAMESPACE_CLIENT && nr != 0 &&
- !(gfp_mask & __GFP_FS))
- return -1;
+ if (client == LDLM_NAMESPACE_CLIENT && !(gfp_mask & __GFP_FS))
+ return 0;
- CDEBUG(D_DLMTRACE, "Request to shrink %d %s locks from all pools\n",
- nr, client == LDLM_NAMESPACE_CLIENT ? "client" : "server");
+ CDEBUG(D_DLMTRACE, "Request to count %s locks from all pools\n",
+ client == LDLM_NAMESPACE_CLIENT ? "client" : "server");
cookie = cl_env_reenter();
@@ -1047,8 +1039,7 @@
* Find out how many resources we may release.
*/
for (nr_ns = ldlm_namespace_nr_read(client);
- nr_ns > 0; nr_ns--)
- {
+ nr_ns > 0; nr_ns--) {
mutex_lock(ldlm_namespace_lock(client));
if (list_empty(ldlm_namespace_list(client))) {
mutex_unlock(ldlm_namespace_lock(client));
@@ -1078,17 +1069,27 @@
ldlm_namespace_put(ns);
}
- if (nr == 0 || total == 0) {
- cl_env_reexit(cookie);
- return total;
- }
+ cl_env_reexit(cookie);
+ return total;
+}
+
+static unsigned long ldlm_pools_scan(ldlm_side_t client, int nr, unsigned int gfp_mask)
+{
+ unsigned long freed = 0;
+ int tmp, nr_ns;
+ struct ldlm_namespace *ns;
+ void *cookie;
+
+ if (client == LDLM_NAMESPACE_CLIENT && !(gfp_mask & __GFP_FS))
+ return -1;
+
+ cookie = cl_env_reenter();
/*
- * Shrink at least ldlm_namespace_nr(client) namespaces.
+ * Shrink at least ldlm_namespace_nr_read(client) namespaces.
*/
- for (nr_ns = ldlm_namespace_nr_read(client) - nr_ns;
- nr_ns > 0; nr_ns--)
- {
+ for (tmp = nr_ns = ldlm_namespace_nr_read(client);
+ tmp > 0; tmp--) {
int cancel, nr_locks;
/*
@@ -1097,12 +1098,6 @@
mutex_lock(ldlm_namespace_lock(client));
if (list_empty(ldlm_namespace_list(client))) {
mutex_unlock(ldlm_namespace_lock(client));
- /*
- * If list is empty, we can't return any @cached > 0,
- * that probably would cause needless shrinker
- * call.
- */
- cached = 0;
break;
}
ns = ldlm_namespace_first_locked(client);
@@ -1111,29 +1106,42 @@
mutex_unlock(ldlm_namespace_lock(client));
nr_locks = ldlm_pool_granted(&ns->ns_pool);
- cancel = 1 + nr_locks * nr / total;
- ldlm_pool_shrink(&ns->ns_pool, cancel, gfp_mask);
- cached += ldlm_pool_granted(&ns->ns_pool);
+ /*
+ * We use to shrink propotionally but with new shrinker API,
+ * we lost the total number of freeable locks.
+ */
+ cancel = 1 + min_t(int, nr_locks, nr / nr_ns);
+ freed += ldlm_pool_shrink(&ns->ns_pool, cancel, gfp_mask);
ldlm_namespace_put(ns);
}
cl_env_reexit(cookie);
- /* we only decrease the SLV in server pools shrinker, return -1 to
- * kernel to avoid needless loop. LU-1128 */
- return (client == LDLM_NAMESPACE_SERVER) ? -1 : cached;
+ /*
+ * we only decrease the SLV in server pools shrinker, return
+ * SHRINK_STOP to kernel to avoid needless loop. LU-1128
+ */
+ return (client == LDLM_NAMESPACE_SERVER) ? SHRINK_STOP : freed;
}
-static int ldlm_pools_srv_shrink(SHRINKER_ARGS(sc, nr_to_scan, gfp_mask))
+static unsigned long ldlm_pools_srv_count(struct shrinker *s, struct shrink_control *sc)
{
- return ldlm_pools_shrink(LDLM_NAMESPACE_SERVER,
- shrink_param(sc, nr_to_scan),
- shrink_param(sc, gfp_mask));
+ return ldlm_pools_count(LDLM_NAMESPACE_SERVER, sc->gfp_mask);
}
-static int ldlm_pools_cli_shrink(SHRINKER_ARGS(sc, nr_to_scan, gfp_mask))
+static unsigned long ldlm_pools_srv_scan(struct shrinker *s, struct shrink_control *sc)
{
- return ldlm_pools_shrink(LDLM_NAMESPACE_CLIENT,
- shrink_param(sc, nr_to_scan),
- shrink_param(sc, gfp_mask));
+ return ldlm_pools_scan(LDLM_NAMESPACE_SERVER, sc->nr_to_scan,
+ sc->gfp_mask);
+}
+
+static unsigned long ldlm_pools_cli_count(struct shrinker *s, struct shrink_control *sc)
+{
+ return ldlm_pools_count(LDLM_NAMESPACE_CLIENT, sc->gfp_mask);
+}
+
+static unsigned long ldlm_pools_cli_scan(struct shrinker *s, struct shrink_control *sc)
+{
+ return ldlm_pools_scan(LDLM_NAMESPACE_CLIENT, sc->nr_to_scan,
+ sc->gfp_mask);
}
int ldlm_pools_recalc(ldlm_side_t client)
@@ -1216,7 +1224,7 @@
}
/*
- * Recalc at least ldlm_namespace_nr(client) namespaces.
+ * Recalc at least ldlm_namespace_nr_read(client) namespaces.
*/
for (nr = ldlm_namespace_nr_read(client); nr > 0; nr--) {
int skip;
@@ -1383,18 +1391,26 @@
ldlm_pools_thread = NULL;
}
+static struct shrinker ldlm_pools_srv_shrinker = {
+ .count_objects = ldlm_pools_srv_count,
+ .scan_objects = ldlm_pools_srv_scan,
+ .seeks = DEFAULT_SEEKS,
+};
+
+static struct shrinker ldlm_pools_cli_shrinker = {
+ .count_objects = ldlm_pools_cli_count,
+ .scan_objects = ldlm_pools_cli_scan,
+ .seeks = DEFAULT_SEEKS,
+};
+
int ldlm_pools_init(void)
{
int rc;
rc = ldlm_pools_thread_start();
if (rc == 0) {
- ldlm_pools_srv_shrinker =
- set_shrinker(DEFAULT_SEEKS,
- ldlm_pools_srv_shrink);
- ldlm_pools_cli_shrinker =
- set_shrinker(DEFAULT_SEEKS,
- ldlm_pools_cli_shrink);
+ register_shrinker(&ldlm_pools_srv_shrinker);
+ register_shrinker(&ldlm_pools_cli_shrinker);
}
return rc;
}
@@ -1402,14 +1418,8 @@
void ldlm_pools_fini(void)
{
- if (ldlm_pools_srv_shrinker != NULL) {
- remove_shrinker(ldlm_pools_srv_shrinker);
- ldlm_pools_srv_shrinker = NULL;
- }
- if (ldlm_pools_cli_shrinker != NULL) {
- remove_shrinker(ldlm_pools_cli_shrinker);
- ldlm_pools_cli_shrinker = NULL;
- }
+ unregister_shrinker(&ldlm_pools_srv_shrinker);
+ unregister_shrinker(&ldlm_pools_cli_shrinker);
ldlm_pools_thread_stop();
}
EXPORT_SYMBOL(ldlm_pools_fini);
diff --git a/drivers/staging/lustre/lustre/llite/file.c b/drivers/staging/lustre/lustre/llite/file.c
index 253f026..bc534db 100644
--- a/drivers/staging/lustre/lustre/llite/file.c
+++ b/drivers/staging/lustre/lustre/llite/file.c
@@ -1009,7 +1009,7 @@
local_iov->iov_len = count;
init_sync_kiocb(kiocb, file);
kiocb->ki_pos = *ppos;
- kiocb->ki_left = count;
+ kiocb->ki_nbytes = count;
result = ll_file_aio_read(kiocb, local_iov, 1, kiocb->ki_pos);
*ppos = kiocb->ki_pos;
@@ -1068,7 +1068,7 @@
local_iov->iov_len = count;
init_sync_kiocb(kiocb, file);
kiocb->ki_pos = *ppos;
- kiocb->ki_left = count;
+ kiocb->ki_nbytes = count;
result = ll_file_aio_write(kiocb, local_iov, 1, kiocb->ki_pos);
*ppos = kiocb->ki_pos;
diff --git a/drivers/staging/lustre/lustre/obdclass/lu_object.c b/drivers/staging/lustre/lustre/obdclass/lu_object.c
index c29ac1c..3a3d5bc 100644
--- a/drivers/staging/lustre/lustre/obdclass/lu_object.c
+++ b/drivers/staging/lustre/lustre/obdclass/lu_object.c
@@ -1779,7 +1779,6 @@
}
EXPORT_SYMBOL(lu_env_refill_by_tags);
-static struct shrinker *lu_site_shrinker = NULL;
typedef struct lu_site_stats{
unsigned lss_populated;
@@ -1835,59 +1834,66 @@
* objects without taking the lu_sites_guard lock, but this is not
* possible in the current implementation.
*/
-static int lu_cache_shrink(SHRINKER_ARGS(sc, nr_to_scan, gfp_mask))
+static unsigned long lu_cache_shrink_count(struct shrinker *sk,
+ struct shrink_control *sc)
{
lu_site_stats_t stats;
struct lu_site *s;
struct lu_site *tmp;
- int cached = 0;
- int remain = shrink_param(sc, nr_to_scan);
- LIST_HEAD(splice);
+ unsigned long cached = 0;
- if (!(shrink_param(sc, gfp_mask) & __GFP_FS)) {
- if (remain != 0)
- return -1;
- else
- /* We must not take the lu_sites_guard lock when
- * __GFP_FS is *not* set because of the deadlock
- * possibility detailed above. Additionally,
- * since we cannot determine the number of
- * objects in the cache without taking this
- * lock, we're in a particularly tough spot. As
- * a result, we'll just lie and say our cache is
- * empty. This _should_ be ok, as we can't
- * reclaim objects when __GFP_FS is *not* set
- * anyways.
- */
- return 0;
- }
-
- CDEBUG(D_INODE, "Shrink %d objects\n", remain);
+ if (!(sc->gfp_mask & __GFP_FS))
+ return 0;
mutex_lock(&lu_sites_guard);
list_for_each_entry_safe(s, tmp, &lu_sites, ls_linkage) {
- if (shrink_param(sc, nr_to_scan) != 0) {
- remain = lu_site_purge(&lu_shrink_env, s, remain);
- /*
- * Move just shrunk site to the tail of site list to
- * assure shrinking fairness.
- */
- list_move_tail(&s->ls_linkage, &splice);
- }
-
memset(&stats, 0, sizeof(stats));
lu_site_stats_get(s->ls_obj_hash, &stats, 0);
cached += stats.lss_total - stats.lss_busy;
- if (shrink_param(sc, nr_to_scan) && remain <= 0)
- break;
+ }
+ mutex_unlock(&lu_sites_guard);
+
+ cached = (cached / 100) * sysctl_vfs_cache_pressure;
+ CDEBUG(D_INODE, "%ld objects cached\n", cached);
+ return cached;
+}
+
+static unsigned long lu_cache_shrink_scan(struct shrinker *sk,
+ struct shrink_control *sc)
+{
+ struct lu_site *s;
+ struct lu_site *tmp;
+ unsigned long remain = sc->nr_to_scan, freed = 0;
+ LIST_HEAD(splice);
+
+ if (!(sc->gfp_mask & __GFP_FS))
+ /* We must not take the lu_sites_guard lock when
+ * __GFP_FS is *not* set because of the deadlock
+ * possibility detailed above. Additionally,
+ * since we cannot determine the number of
+ * objects in the cache without taking this
+ * lock, we're in a particularly tough spot. As
+ * a result, we'll just lie and say our cache is
+ * empty. This _should_ be ok, as we can't
+ * reclaim objects when __GFP_FS is *not* set
+ * anyways.
+ */
+ return SHRINK_STOP;
+
+ mutex_lock(&lu_sites_guard);
+ list_for_each_entry_safe(s, tmp, &lu_sites, ls_linkage) {
+ freed = lu_site_purge(&lu_shrink_env, s, remain);
+ remain -= freed;
+ /*
+ * Move just shrunk site to the tail of site list to
+ * assure shrinking fairness.
+ */
+ list_move_tail(&s->ls_linkage, &splice);
}
list_splice(&splice, lu_sites.prev);
mutex_unlock(&lu_sites_guard);
- cached = (cached / 100) * sysctl_vfs_cache_pressure;
- if (shrink_param(sc, nr_to_scan) == 0)
- CDEBUG(D_INODE, "%d objects cached\n", cached);
- return cached;
+ return sc->nr_to_scan - remain;
}
/*
@@ -1913,6 +1919,12 @@
return 0;
}
+static struct shrinker lu_site_shrinker = {
+ .count_objects = lu_cache_shrink_count,
+ .scan_objects = lu_cache_shrink_scan,
+ .seeks = DEFAULT_SEEKS,
+};
+
/**
* Initialization of global lu_* data.
*/
@@ -1947,9 +1959,7 @@
* inode, one for ea. Unfortunately setting this high value results in
* lu_object/inode cache consuming all the memory.
*/
- lu_site_shrinker = set_shrinker(DEFAULT_SEEKS, lu_cache_shrink);
- if (lu_site_shrinker == NULL)
- return -ENOMEM;
+ register_shrinker(&lu_site_shrinker);
return result;
}
@@ -1959,11 +1969,7 @@
*/
void lu_global_fini(void)
{
- if (lu_site_shrinker != NULL) {
- remove_shrinker(lu_site_shrinker);
- lu_site_shrinker = NULL;
- }
-
+ unregister_shrinker(&lu_site_shrinker);
lu_context_key_degister(&lu_global_key);
/*
diff --git a/drivers/staging/lustre/lustre/ptlrpc/sec_bulk.c b/drivers/staging/lustre/lustre/ptlrpc/sec_bulk.c
index 9013745..e90c8fb 100644
--- a/drivers/staging/lustre/lustre/ptlrpc/sec_bulk.c
+++ b/drivers/staging/lustre/lustre/ptlrpc/sec_bulk.c
@@ -121,13 +121,6 @@
} page_pools;
/*
- * memory shrinker
- */
-const int pools_shrinker_seeks = DEFAULT_SEEKS;
-static struct shrinker *pools_shrinker = NULL;
-
-
-/*
* /proc/fs/lustre/sptlrpc/encrypt_page_pools
*/
int sptlrpc_proc_enc_pool_seq_show(struct seq_file *m, void *v)
@@ -226,30 +219,11 @@
}
/*
- * could be called frequently for query (@nr_to_scan == 0).
* we try to keep at least PTLRPC_MAX_BRW_PAGES pages in the pool.
*/
-static int enc_pools_shrink(SHRINKER_ARGS(sc, nr_to_scan, gfp_mask))
+static unsigned long enc_pools_shrink_count(struct shrinker *s,
+ struct shrink_control *sc)
{
- if (unlikely(shrink_param(sc, nr_to_scan) != 0)) {
- spin_lock(&page_pools.epp_lock);
- shrink_param(sc, nr_to_scan) = min_t(unsigned long,
- shrink_param(sc, nr_to_scan),
- page_pools.epp_free_pages -
- PTLRPC_MAX_BRW_PAGES);
- if (shrink_param(sc, nr_to_scan) > 0) {
- enc_pools_release_free_pages(shrink_param(sc,
- nr_to_scan));
- CDEBUG(D_SEC, "released %ld pages, %ld left\n",
- (long)shrink_param(sc, nr_to_scan),
- page_pools.epp_free_pages);
-
- page_pools.epp_st_shrinks++;
- page_pools.epp_last_shrink = cfs_time_current_sec();
- }
- spin_unlock(&page_pools.epp_lock);
- }
-
/*
* if no pool access for a long time, we consider it's fully idle.
* a little race here is fine.
@@ -266,6 +240,40 @@
(IDLE_IDX_MAX - page_pools.epp_idle_idx) / IDLE_IDX_MAX;
}
+/*
+ * we try to keep at least PTLRPC_MAX_BRW_PAGES pages in the pool.
+ */
+static unsigned long enc_pools_shrink_scan(struct shrinker *s,
+ struct shrink_control *sc)
+{
+ spin_lock(&page_pools.epp_lock);
+ sc->nr_to_scan = min_t(unsigned long, sc->nr_to_scan,
+ page_pools.epp_free_pages - PTLRPC_MAX_BRW_PAGES);
+ if (sc->nr_to_scan > 0) {
+ enc_pools_release_free_pages(sc->nr_to_scan);
+ CDEBUG(D_SEC, "released %ld pages, %ld left\n",
+ (long)sc->nr_to_scan, page_pools.epp_free_pages);
+
+ page_pools.epp_st_shrinks++;
+ page_pools.epp_last_shrink = cfs_time_current_sec();
+ }
+ spin_unlock(&page_pools.epp_lock);
+
+ /*
+ * if no pool access for a long time, we consider it's fully idle.
+ * a little race here is fine.
+ */
+ if (unlikely(cfs_time_current_sec() - page_pools.epp_last_access >
+ CACHE_QUIESCENT_PERIOD)) {
+ spin_lock(&page_pools.epp_lock);
+ page_pools.epp_idle_idx = IDLE_IDX_MAX;
+ spin_unlock(&page_pools.epp_lock);
+ }
+
+ LASSERT(page_pools.epp_idle_idx <= IDLE_IDX_MAX);
+ return sc->nr_to_scan;
+}
+
static inline
int npages_to_npools(unsigned long npages)
{
@@ -699,6 +707,12 @@
sizeof(*page_pools.epp_pools));
}
+static struct shrinker pools_shrinker = {
+ .count_objects = enc_pools_shrink_count,
+ .scan_objects = enc_pools_shrink_scan,
+ .seeks = DEFAULT_SEEKS,
+};
+
int sptlrpc_enc_pool_init(void)
{
/*
@@ -736,12 +750,7 @@
if (page_pools.epp_pools == NULL)
return -ENOMEM;
- pools_shrinker = set_shrinker(pools_shrinker_seeks,
- enc_pools_shrink);
- if (pools_shrinker == NULL) {
- enc_pools_free();
- return -ENOMEM;
- }
+ register_shrinker(&pools_shrinker);
return 0;
}
@@ -750,11 +759,10 @@
{
unsigned long cleaned, npools;
- LASSERT(pools_shrinker);
LASSERT(page_pools.epp_pools);
LASSERT(page_pools.epp_total_pages == page_pools.epp_free_pages);
- remove_shrinker(pools_shrinker);
+ unregister_shrinker(&pools_shrinker);
npools = npages_to_npools(page_pools.epp_total_pages);
cleaned = enc_pools_cleanup(page_pools.epp_pools, npools);
diff --git a/drivers/target/Makefile b/drivers/target/Makefile
index 9fdcb56..85b012d 100644
--- a/drivers/target/Makefile
+++ b/drivers/target/Makefile
@@ -13,7 +13,8 @@
target_core_spc.o \
target_core_ua.o \
target_core_rd.o \
- target_core_stat.o
+ target_core_stat.o \
+ target_core_xcopy.o
obj-$(CONFIG_TARGET_CORE) += target_core_mod.o
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 3a17930..35b61f7 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -1,9 +1,7 @@
/*******************************************************************************
* This file contains main functions related to the iSCSI Target Core Driver.
*
- * \u00a9 Copyright 2007-2011 RisingTide Systems LLC.
- *
- * Licensed to the Linux Foundation under the General Public License (GPL) version 2.
+ * (c) Copyright 2007-2013 Datera, Inc.
*
* Author: Nicholas A. Bellinger <nab@linux-iscsi.org>
*
@@ -63,7 +61,6 @@
struct iscsit_global *iscsit_global;
-struct kmem_cache *lio_cmd_cache;
struct kmem_cache *lio_qr_cache;
struct kmem_cache *lio_dr_cache;
struct kmem_cache *lio_ooo_cache;
@@ -220,11 +217,6 @@
spin_unlock_bh(&np->np_thread_lock);
return -1;
}
- if (np->np_login_tpg) {
- pr_err("np->np_login_tpg() is not NULL!\n");
- spin_unlock_bh(&np->np_thread_lock);
- return -1;
- }
spin_unlock_bh(&np->np_thread_lock);
/*
* Determine if the portal group is accepting storage traffic.
@@ -239,26 +231,38 @@
/*
* Here we serialize access across the TIQN+TPG Tuple.
*/
- ret = mutex_lock_interruptible(&tpg->np_login_lock);
+ ret = down_interruptible(&tpg->np_login_sem);
if ((ret != 0) || signal_pending(current))
return -1;
- spin_lock_bh(&np->np_thread_lock);
- np->np_login_tpg = tpg;
- spin_unlock_bh(&np->np_thread_lock);
+ spin_lock_bh(&tpg->tpg_state_lock);
+ if (tpg->tpg_state != TPG_STATE_ACTIVE) {
+ spin_unlock_bh(&tpg->tpg_state_lock);
+ up(&tpg->np_login_sem);
+ return -1;
+ }
+ spin_unlock_bh(&tpg->tpg_state_lock);
return 0;
}
-int iscsit_deaccess_np(struct iscsi_np *np, struct iscsi_portal_group *tpg)
+void iscsit_login_kref_put(struct kref *kref)
+{
+ struct iscsi_tpg_np *tpg_np = container_of(kref,
+ struct iscsi_tpg_np, tpg_np_kref);
+
+ complete(&tpg_np->tpg_np_comp);
+}
+
+int iscsit_deaccess_np(struct iscsi_np *np, struct iscsi_portal_group *tpg,
+ struct iscsi_tpg_np *tpg_np)
{
struct iscsi_tiqn *tiqn = tpg->tpg_tiqn;
- spin_lock_bh(&np->np_thread_lock);
- np->np_login_tpg = NULL;
- spin_unlock_bh(&np->np_thread_lock);
+ up(&tpg->np_login_sem);
- mutex_unlock(&tpg->np_login_lock);
+ if (tpg_np)
+ kref_put(&tpg_np->tpg_np_kref, iscsit_login_kref_put);
if (tiqn)
iscsit_put_tiqn_for_login(tiqn);
@@ -410,20 +414,10 @@
int iscsit_reset_np_thread(
struct iscsi_np *np,
struct iscsi_tpg_np *tpg_np,
- struct iscsi_portal_group *tpg)
+ struct iscsi_portal_group *tpg,
+ bool shutdown)
{
spin_lock_bh(&np->np_thread_lock);
- if (tpg && tpg_np) {
- /*
- * The reset operation need only be performed when the
- * passed struct iscsi_portal_group has a login in progress
- * to one of the network portals.
- */
- if (tpg_np->tpg_np->np_login_tpg != tpg) {
- spin_unlock_bh(&np->np_thread_lock);
- return 0;
- }
- }
if (np->np_thread_state == ISCSI_NP_THREAD_INACTIVE) {
spin_unlock_bh(&np->np_thread_lock);
return 0;
@@ -438,6 +432,12 @@
}
spin_unlock_bh(&np->np_thread_lock);
+ if (tpg_np && shutdown) {
+ kref_put(&tpg_np->tpg_np_kref, iscsit_login_kref_put);
+
+ wait_for_completion(&tpg_np->tpg_np_comp);
+ }
+
return 0;
}
@@ -497,7 +497,6 @@
.iscsit_setup_np = iscsit_setup_np,
.iscsit_accept_np = iscsit_accept_np,
.iscsit_free_np = iscsit_free_np,
- .iscsit_alloc_cmd = iscsit_alloc_cmd,
.iscsit_get_login_rx = iscsit_get_login_rx,
.iscsit_put_login_tx = iscsit_put_login_tx,
.iscsit_get_dataout = iscsit_build_r2ts_for_cmd,
@@ -538,22 +537,13 @@
goto ts_out1;
}
- lio_cmd_cache = kmem_cache_create("lio_cmd_cache",
- sizeof(struct iscsi_cmd), __alignof__(struct iscsi_cmd),
- 0, NULL);
- if (!lio_cmd_cache) {
- pr_err("Unable to kmem_cache_create() for"
- " lio_cmd_cache\n");
- goto ts_out2;
- }
-
lio_qr_cache = kmem_cache_create("lio_qr_cache",
sizeof(struct iscsi_queue_req),
__alignof__(struct iscsi_queue_req), 0, NULL);
if (!lio_qr_cache) {
pr_err("nable to kmem_cache_create() for"
" lio_qr_cache\n");
- goto cmd_out;
+ goto ts_out2;
}
lio_dr_cache = kmem_cache_create("lio_dr_cache",
@@ -597,8 +587,6 @@
kmem_cache_destroy(lio_dr_cache);
qr_out:
kmem_cache_destroy(lio_qr_cache);
-cmd_out:
- kmem_cache_destroy(lio_cmd_cache);
ts_out2:
iscsi_deallocate_thread_sets();
ts_out1:
@@ -616,7 +604,6 @@
iscsi_thread_set_free();
iscsit_release_discovery_tpg();
iscsit_unregister_transport(&iscsi_target_transport);
- kmem_cache_destroy(lio_cmd_cache);
kmem_cache_destroy(lio_qr_cache);
kmem_cache_destroy(lio_dr_cache);
kmem_cache_destroy(lio_ooo_cache);
@@ -3447,12 +3434,10 @@
bool inaddr_any = iscsit_check_inaddr_any(np);
len = sprintf(buf, "TargetAddress="
- "%s%s%s:%hu,%hu",
- (np->np_sockaddr.ss_family == AF_INET6) ?
- "[" : "", (inaddr_any == false) ?
+ "%s:%hu,%hu",
+ (inaddr_any == false) ?
np->np_ip : conn->local_ip,
- (np->np_sockaddr.ss_family == AF_INET6) ?
- "]" : "", (inaddr_any == false) ?
+ (inaddr_any == false) ?
np->np_port : conn->local_port,
tpg->tpgt);
len += 1;
diff --git a/drivers/target/iscsi/iscsi_target.h b/drivers/target/iscsi/iscsi_target.h
index 2c437cb..e936d56 100644
--- a/drivers/target/iscsi/iscsi_target.h
+++ b/drivers/target/iscsi/iscsi_target.h
@@ -7,13 +7,15 @@
extern struct iscsi_tiqn *iscsit_add_tiqn(unsigned char *);
extern void iscsit_del_tiqn(struct iscsi_tiqn *);
extern int iscsit_access_np(struct iscsi_np *, struct iscsi_portal_group *);
-extern int iscsit_deaccess_np(struct iscsi_np *, struct iscsi_portal_group *);
+extern void iscsit_login_kref_put(struct kref *);
+extern int iscsit_deaccess_np(struct iscsi_np *, struct iscsi_portal_group *,
+ struct iscsi_tpg_np *);
extern bool iscsit_check_np_match(struct __kernel_sockaddr_storage *,
struct iscsi_np *, int);
extern struct iscsi_np *iscsit_add_np(struct __kernel_sockaddr_storage *,
char *, int);
extern int iscsit_reset_np_thread(struct iscsi_np *, struct iscsi_tpg_np *,
- struct iscsi_portal_group *);
+ struct iscsi_portal_group *, bool);
extern int iscsit_del_np(struct iscsi_np *);
extern int iscsit_reject_cmd(struct iscsi_cmd *cmd, u8, unsigned char *);
extern void iscsit_set_unsoliticed_dataout(struct iscsi_cmd *);
@@ -37,7 +39,6 @@
extern struct kmem_cache *lio_dr_cache;
extern struct kmem_cache *lio_ooo_cache;
-extern struct kmem_cache *lio_cmd_cache;
extern struct kmem_cache *lio_qr_cache;
extern struct kmem_cache *lio_r2t_cache;
diff --git a/drivers/target/iscsi/iscsi_target_auth.c b/drivers/target/iscsi/iscsi_target_auth.c
index cee1754..7505fdd 100644
--- a/drivers/target/iscsi/iscsi_target_auth.c
+++ b/drivers/target/iscsi/iscsi_target_auth.c
@@ -1,9 +1,7 @@
/*******************************************************************************
* This file houses the main functions for the iSCSI CHAP support
*
- * \u00a9 Copyright 2007-2011 RisingTide Systems LLC.
- *
- * Licensed to the Linux Foundation under the General Public License (GPL) version 2.
+ * (c) Copyright 2007-2013 Datera, Inc.
*
* Author: Nicholas A. Bellinger <nab@linux-iscsi.org>
*
diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c
index bbfd288..fd14525 100644
--- a/drivers/target/iscsi/iscsi_target_configfs.c
+++ b/drivers/target/iscsi/iscsi_target_configfs.c
@@ -2,9 +2,7 @@
* This file contains the configfs implementation for iSCSI Target mode
* from the LIO-Target Project.
*
- * \u00a9 Copyright 2007-2011 RisingTide Systems LLC.
- *
- * Licensed to the Linux Foundation under the General Public License (GPL) version 2.
+ * (c) Copyright 2007-2013 Datera, Inc.
*
* Author: Nicholas A. Bellinger <nab@linux-iscsi.org>
*
@@ -265,9 +263,9 @@
*port_str = '\0'; /* Terminate string for IP */
port_str++; /* Skip over ":" */
- ret = strict_strtoul(port_str, 0, &port);
+ ret = kstrtoul(port_str, 0, &port);
if (ret < 0) {
- pr_err("strict_strtoul() failed for port_str: %d\n", ret);
+ pr_err("kstrtoul() failed for port_str: %d\n", ret);
return ERR_PTR(ret);
}
sock_in6 = (struct sockaddr_in6 *)&sockaddr;
@@ -290,9 +288,9 @@
*port_str = '\0'; /* Terminate string for IP */
port_str++; /* Skip over ":" */
- ret = strict_strtoul(port_str, 0, &port);
+ ret = kstrtoul(port_str, 0, &port);
if (ret < 0) {
- pr_err("strict_strtoul() failed for port_str: %d\n", ret);
+ pr_err("kstrtoul() failed for port_str: %d\n", ret);
return ERR_PTR(ret);
}
sock_in = (struct sockaddr_in *)&sockaddr;
@@ -1481,7 +1479,7 @@
struct target_fabric_configfs *tf,
char *page)
{
- return sprintf(page, "RisingTide Systems Linux-iSCSI Target "ISCSIT_VERSION"\n");
+ return sprintf(page, "Datera Inc. iSCSI Target "ISCSIT_VERSION"\n");
}
TF_WWN_ATTR_RO(lio_target, lio_version);
@@ -1925,7 +1923,7 @@
struct iscsi_cmd *cmd = container_of(se_cmd, struct iscsi_cmd, se_cmd);
pr_debug("Entering lio_release_cmd for se_cmd: %p\n", se_cmd);
- cmd->release_cmd(cmd);
+ iscsit_release_cmd(cmd);
}
/* End functions for target_core_fabric_ops */
diff --git a/drivers/target/iscsi/iscsi_target_core.h b/drivers/target/iscsi/iscsi_target_core.h
index 4f77a78..9a5721b 100644
--- a/drivers/target/iscsi/iscsi_target_core.h
+++ b/drivers/target/iscsi/iscsi_target_core.h
@@ -9,7 +9,7 @@
#include <scsi/iscsi_proto.h>
#include <target/target_core_base.h>
-#define ISCSIT_VERSION "v4.1.0-rc2"
+#define ISCSIT_VERSION "v4.1.0"
#define ISCSI_MAX_DATASN_MISSING_COUNT 16
#define ISCSI_TX_THREAD_TCP_TIMEOUT 2
#define ISCSI_RX_THREAD_TCP_TIMEOUT 2
@@ -17,6 +17,9 @@
#define SECONDS_FOR_ASYNC_TEXT 10
#define SECONDS_FOR_LOGOUT_COMP 15
#define WHITE_SPACE " \t\v\f\n\r"
+#define ISCSIT_MIN_TAGS 16
+#define ISCSIT_EXTRA_TAGS 8
+#define ISCSIT_TCP_BACKLOG 256
/* struct iscsi_node_attrib sanity values */
#define NA_DATAOUT_TIMEOUT 3
@@ -47,7 +50,7 @@
#define TA_NETIF_TIMEOUT_MAX 15
#define TA_NETIF_TIMEOUT_MIN 2
#define TA_GENERATE_NODE_ACLS 0
-#define TA_DEFAULT_CMDSN_DEPTH 16
+#define TA_DEFAULT_CMDSN_DEPTH 64
#define TA_DEFAULT_CMDSN_DEPTH_MAX 512
#define TA_DEFAULT_CMDSN_DEPTH_MIN 1
#define TA_CACHE_DYNAMIC_ACLS 0
@@ -489,7 +492,6 @@
u32 first_data_sg_off;
u32 kmapped_nents;
sense_reason_t sense_reason;
- void (*release_cmd)(struct iscsi_cmd *);
} ____cacheline_aligned;
struct iscsi_tmr_req {
@@ -554,9 +556,19 @@
struct completion rx_half_close_comp;
/* socket used by this connection */
struct socket *sock;
+ void (*orig_data_ready)(struct sock *, int);
+ void (*orig_state_change)(struct sock *);
+#define LOGIN_FLAGS_READ_ACTIVE 1
+#define LOGIN_FLAGS_CLOSED 2
+#define LOGIN_FLAGS_READY 4
+ unsigned long login_flags;
+ struct delayed_work login_work;
+ struct delayed_work login_cleanup_work;
+ struct iscsi_login *login;
struct timer_list nopin_timer;
struct timer_list nopin_response_timer;
struct timer_list transport_timer;
+ struct task_struct *login_kworker;
/* Spinlock used for add/deleting cmd's from conn_cmd_list */
spinlock_t cmd_lock;
spinlock_t conn_usage_lock;
@@ -584,6 +596,7 @@
void *context;
struct iscsi_login_thread_s *login_thread;
struct iscsi_portal_group *tpg;
+ struct iscsi_tpg_np *tpg_np;
/* Pointer to parent session */
struct iscsi_session *sess;
/* Pointer to thread_set in use for this conn's threads */
@@ -682,6 +695,7 @@
u8 version_max;
u8 login_complete;
u8 login_failed;
+ bool zero_tsih;
char isid[6];
u32 cmd_sn;
itt_t init_task_tag;
@@ -694,6 +708,7 @@
char *req_buf;
char *rsp_buf;
struct iscsi_conn *conn;
+ struct iscsi_np *np;
} ____cacheline_aligned;
struct iscsi_node_attrib {
@@ -773,7 +788,6 @@
struct __kernel_sockaddr_storage np_sockaddr;
struct task_struct *np_thread;
struct timer_list np_login_timer;
- struct iscsi_portal_group *np_login_tpg;
void *np_context;
struct iscsit_transport *np_transport;
struct list_head np_list;
@@ -788,6 +802,8 @@
struct list_head tpg_np_parent_list;
struct se_tpg_np se_tpg_np;
spinlock_t tpg_np_parent_lock;
+ struct completion tpg_np_comp;
+ struct kref tpg_np_kref;
};
struct iscsi_portal_group {
@@ -809,7 +825,7 @@
spinlock_t tpg_state_lock;
struct se_portal_group tpg_se_tpg;
struct mutex tpg_access_lock;
- struct mutex np_login_lock;
+ struct semaphore np_login_sem;
struct iscsi_tpg_attrib tpg_attrib;
struct iscsi_node_auth tpg_demo_auth;
/* Pointer to default list of iSCSI parameters for TPG */
diff --git a/drivers/target/iscsi/iscsi_target_datain_values.c b/drivers/target/iscsi/iscsi_target_datain_values.c
index 848fee7..e93d5a7 100644
--- a/drivers/target/iscsi/iscsi_target_datain_values.c
+++ b/drivers/target/iscsi/iscsi_target_datain_values.c
@@ -1,9 +1,7 @@
/*******************************************************************************
* This file contains the iSCSI Target DataIN value generation functions.
*
- * \u00a9 Copyright 2007-2011 RisingTide Systems LLC.
- *
- * Licensed to the Linux Foundation under the General Public License (GPL) version 2.
+ * (c) Copyright 2007-2013 Datera, Inc.
*
* Author: Nicholas A. Bellinger <nab@linux-iscsi.org>
*
diff --git a/drivers/target/iscsi/iscsi_target_device.c b/drivers/target/iscsi/iscsi_target_device.c
index 1b74033..6c7a510 100644
--- a/drivers/target/iscsi/iscsi_target_device.c
+++ b/drivers/target/iscsi/iscsi_target_device.c
@@ -2,9 +2,7 @@
* This file contains the iSCSI Virtual Device and Disk Transport
* agnostic related functions.
*
- \u00a9 Copyright 2007-2011 RisingTide Systems LLC.
- *
- * Licensed to the Linux Foundation under the General Public License (GPL) version 2.
+ * (c) Copyright 2007-2013 Datera, Inc.
*
* Author: Nicholas A. Bellinger <nab@linux-iscsi.org>
*
diff --git a/drivers/target/iscsi/iscsi_target_erl0.c b/drivers/target/iscsi/iscsi_target_erl0.c
index 08bd878..41052e5 100644
--- a/drivers/target/iscsi/iscsi_target_erl0.c
+++ b/drivers/target/iscsi/iscsi_target_erl0.c
@@ -2,9 +2,7 @@
* This file contains error recovery level zero functions used by
* the iSCSI Target driver.
*
- * \u00a9 Copyright 2007-2011 RisingTide Systems LLC.
- *
- * Licensed to the Linux Foundation under the General Public License (GPL) version 2.
+ * (c) Copyright 2007-2013 Datera, Inc.
*
* Author: Nicholas A. Bellinger <nab@linux-iscsi.org>
*
diff --git a/drivers/target/iscsi/iscsi_target_erl1.c b/drivers/target/iscsi/iscsi_target_erl1.c
index 586c268..e048d64 100644
--- a/drivers/target/iscsi/iscsi_target_erl1.c
+++ b/drivers/target/iscsi/iscsi_target_erl1.c
@@ -1,9 +1,7 @@
/*******************************************************************************
* This file contains error recovery level one used by the iSCSI Target driver.
*
- * \u00a9 Copyright 2007-2011 RisingTide Systems LLC.
- *
- * Licensed to the Linux Foundation under the General Public License (GPL) version 2.
+ * (c) Copyright 2007-2013 Datera, Inc.
*
* Author: Nicholas A. Bellinger <nab@linux-iscsi.org>
*
diff --git a/drivers/target/iscsi/iscsi_target_erl2.c b/drivers/target/iscsi/iscsi_target_erl2.c
index 45a5afd..33be1fb 100644
--- a/drivers/target/iscsi/iscsi_target_erl2.c
+++ b/drivers/target/iscsi/iscsi_target_erl2.c
@@ -2,9 +2,7 @@
* This file contains error recovery level two functions used by
* the iSCSI Target driver.
*
- * \u00a9 Copyright 2007-2011 RisingTide Systems LLC.
- *
- * Licensed to the Linux Foundation under the General Public License (GPL) version 2.
+ * (c) Copyright 2007-2013 Datera, Inc.
*
* Author: Nicholas A. Bellinger <nab@linux-iscsi.org>
*
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index bc788c5..1794c75 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -1,9 +1,7 @@
/*******************************************************************************
* This file contains the login functions used by the iSCSI Target driver.
*
- * \u00a9 Copyright 2007-2011 RisingTide Systems LLC.
- *
- * Licensed to the Linux Foundation under the General Public License (GPL) version 2.
+ * (c) Copyright 2007-2013 Datera, Inc.
*
* Author: Nicholas A. Bellinger <nab@linux-iscsi.org>
*
@@ -50,6 +48,7 @@
pr_err("Unable to allocate memory for struct iscsi_login.\n");
return NULL;
}
+ conn->login = login;
login->conn = conn;
login->first_request = 1;
@@ -428,7 +427,7 @@
ISCSI_LOGIN_STATUS_NO_RESOURCES);
return -1;
}
- rc = strict_strtoul(param->value, 0, &mrdsl);
+ rc = kstrtoul(param->value, 0, &mrdsl);
if (rc < 0) {
iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
ISCSI_LOGIN_STATUS_NO_RESOURCES);
@@ -684,7 +683,7 @@
iscsit_start_nopin_timer(conn);
}
-static int iscsi_post_login_handler(
+int iscsi_post_login_handler(
struct iscsi_np *np,
struct iscsi_conn *conn,
u8 zero_tsih)
@@ -872,7 +871,7 @@
struct __kernel_sockaddr_storage *sockaddr)
{
struct socket *sock = NULL;
- int backlog = 5, ret, opt = 0, len;
+ int backlog = ISCSIT_TCP_BACKLOG, ret, opt = 0, len;
switch (np->np_network_transport) {
case ISCSI_TCP:
@@ -1007,16 +1006,24 @@
rc = conn->sock->ops->getname(conn->sock,
(struct sockaddr *)&sock_in6, &err, 1);
if (!rc) {
- snprintf(conn->login_ip, sizeof(conn->login_ip), "%pI6c",
- &sock_in6.sin6_addr.in6_u);
+ if (!ipv6_addr_v4mapped(&sock_in6.sin6_addr))
+ snprintf(conn->login_ip, sizeof(conn->login_ip), "[%pI6c]",
+ &sock_in6.sin6_addr.in6_u);
+ else
+ snprintf(conn->login_ip, sizeof(conn->login_ip), "%pI4",
+ &sock_in6.sin6_addr.s6_addr32[3]);
conn->login_port = ntohs(sock_in6.sin6_port);
}
rc = conn->sock->ops->getname(conn->sock,
(struct sockaddr *)&sock_in6, &err, 0);
if (!rc) {
- snprintf(conn->local_ip, sizeof(conn->local_ip), "%pI6c",
- &sock_in6.sin6_addr.in6_u);
+ if (!ipv6_addr_v4mapped(&sock_in6.sin6_addr))
+ snprintf(conn->local_ip, sizeof(conn->local_ip), "[%pI6c]",
+ &sock_in6.sin6_addr.in6_u);
+ else
+ snprintf(conn->local_ip, sizeof(conn->local_ip), "%pI4",
+ &sock_in6.sin6_addr.s6_addr32[3]);
conn->local_port = ntohs(sock_in6.sin6_port);
}
} else {
@@ -1116,6 +1123,77 @@
return 0;
}
+void iscsi_target_login_sess_out(struct iscsi_conn *conn,
+ struct iscsi_np *np, bool zero_tsih, bool new_sess)
+{
+ if (new_sess == false)
+ goto old_sess_out;
+
+ pr_err("iSCSI Login negotiation failed.\n");
+ iscsit_collect_login_stats(conn, ISCSI_STATUS_CLS_INITIATOR_ERR,
+ ISCSI_LOGIN_STATUS_INIT_ERR);
+ if (!zero_tsih || !conn->sess)
+ goto old_sess_out;
+ if (conn->sess->se_sess)
+ transport_free_session(conn->sess->se_sess);
+ if (conn->sess->session_index != 0) {
+ spin_lock_bh(&sess_idr_lock);
+ idr_remove(&sess_idr, conn->sess->session_index);
+ spin_unlock_bh(&sess_idr_lock);
+ }
+ kfree(conn->sess->sess_ops);
+ kfree(conn->sess);
+
+old_sess_out:
+ iscsi_stop_login_thread_timer(np);
+ /*
+ * If login negotiation fails check if the Time2Retain timer
+ * needs to be restarted.
+ */
+ if (!zero_tsih && conn->sess) {
+ spin_lock_bh(&conn->sess->conn_lock);
+ if (conn->sess->session_state == TARG_SESS_STATE_FAILED) {
+ struct se_portal_group *se_tpg =
+ &ISCSI_TPG_C(conn)->tpg_se_tpg;
+
+ atomic_set(&conn->sess->session_continuation, 0);
+ spin_unlock_bh(&conn->sess->conn_lock);
+ spin_lock_bh(&se_tpg->session_lock);
+ iscsit_start_time2retain_handler(conn->sess);
+ spin_unlock_bh(&se_tpg->session_lock);
+ } else
+ spin_unlock_bh(&conn->sess->conn_lock);
+ iscsit_dec_session_usage_count(conn->sess);
+ }
+
+ if (!IS_ERR(conn->conn_rx_hash.tfm))
+ crypto_free_hash(conn->conn_rx_hash.tfm);
+ if (!IS_ERR(conn->conn_tx_hash.tfm))
+ crypto_free_hash(conn->conn_tx_hash.tfm);
+
+ if (conn->conn_cpumask)
+ free_cpumask_var(conn->conn_cpumask);
+
+ kfree(conn->conn_ops);
+
+ if (conn->param_list) {
+ iscsi_release_param_list(conn->param_list);
+ conn->param_list = NULL;
+ }
+ iscsi_target_nego_release(conn);
+
+ if (conn->sock) {
+ sock_release(conn->sock);
+ conn->sock = NULL;
+ }
+
+ if (conn->conn_transport->iscsit_free_conn)
+ conn->conn_transport->iscsit_free_conn(conn);
+
+ iscsit_put_transport(conn->conn_transport);
+ kfree(conn);
+}
+
static int __iscsi_target_login_thread(struct iscsi_np *np)
{
u8 *buffer, zero_tsih = 0;
@@ -1124,6 +1202,8 @@
struct iscsi_login *login;
struct iscsi_portal_group *tpg = NULL;
struct iscsi_login_req *pdu;
+ struct iscsi_tpg_np *tpg_np;
+ bool new_sess = false;
flush_signals(current);
@@ -1264,6 +1344,7 @@
tpg = conn->tpg;
goto new_sess_out;
}
+ login->zero_tsih = zero_tsih;
tpg = conn->tpg;
if (!tpg) {
@@ -1279,7 +1360,8 @@
goto old_sess_out;
}
- if (iscsi_target_start_negotiation(login, conn) < 0)
+ ret = iscsi_target_start_negotiation(login, conn);
+ if (ret < 0)
goto new_sess_out;
if (!conn->sess) {
@@ -1292,84 +1374,32 @@
if (signal_pending(current))
goto new_sess_out;
- ret = iscsi_post_login_handler(np, conn, zero_tsih);
+ if (ret == 1) {
+ tpg_np = conn->tpg_np;
- if (ret < 0)
- goto new_sess_out;
+ ret = iscsi_post_login_handler(np, conn, zero_tsih);
+ if (ret < 0)
+ goto new_sess_out;
- iscsit_deaccess_np(np, tpg);
+ iscsit_deaccess_np(np, tpg, tpg_np);
+ }
+
tpg = NULL;
+ tpg_np = NULL;
/* Get another socket */
return 1;
new_sess_out:
- pr_err("iSCSI Login negotiation failed.\n");
- iscsit_collect_login_stats(conn, ISCSI_STATUS_CLS_INITIATOR_ERR,
- ISCSI_LOGIN_STATUS_INIT_ERR);
- if (!zero_tsih || !conn->sess)
- goto old_sess_out;
- if (conn->sess->se_sess)
- transport_free_session(conn->sess->se_sess);
- if (conn->sess->session_index != 0) {
- spin_lock_bh(&sess_idr_lock);
- idr_remove(&sess_idr, conn->sess->session_index);
- spin_unlock_bh(&sess_idr_lock);
- }
- kfree(conn->sess->sess_ops);
- kfree(conn->sess);
+ new_sess = true;
old_sess_out:
- iscsi_stop_login_thread_timer(np);
- /*
- * If login negotiation fails check if the Time2Retain timer
- * needs to be restarted.
- */
- if (!zero_tsih && conn->sess) {
- spin_lock_bh(&conn->sess->conn_lock);
- if (conn->sess->session_state == TARG_SESS_STATE_FAILED) {
- struct se_portal_group *se_tpg =
- &ISCSI_TPG_C(conn)->tpg_se_tpg;
-
- atomic_set(&conn->sess->session_continuation, 0);
- spin_unlock_bh(&conn->sess->conn_lock);
- spin_lock_bh(&se_tpg->session_lock);
- iscsit_start_time2retain_handler(conn->sess);
- spin_unlock_bh(&se_tpg->session_lock);
- } else
- spin_unlock_bh(&conn->sess->conn_lock);
- iscsit_dec_session_usage_count(conn->sess);
- }
-
- if (!IS_ERR(conn->conn_rx_hash.tfm))
- crypto_free_hash(conn->conn_rx_hash.tfm);
- if (!IS_ERR(conn->conn_tx_hash.tfm))
- crypto_free_hash(conn->conn_tx_hash.tfm);
-
- if (conn->conn_cpumask)
- free_cpumask_var(conn->conn_cpumask);
-
- kfree(conn->conn_ops);
-
- if (conn->param_list) {
- iscsi_release_param_list(conn->param_list);
- conn->param_list = NULL;
- }
- iscsi_target_nego_release(conn);
-
- if (conn->sock) {
- sock_release(conn->sock);
- conn->sock = NULL;
- }
-
- if (conn->conn_transport->iscsit_free_conn)
- conn->conn_transport->iscsit_free_conn(conn);
-
- iscsit_put_transport(conn->conn_transport);
-
- kfree(conn);
+ tpg_np = conn->tpg_np;
+ iscsi_target_login_sess_out(conn, np, zero_tsih, new_sess);
+ new_sess = false;
if (tpg) {
- iscsit_deaccess_np(np, tpg);
+ iscsit_deaccess_np(np, tpg, tpg_np);
tpg = NULL;
+ tpg_np = NULL;
}
out:
diff --git a/drivers/target/iscsi/iscsi_target_login.h b/drivers/target/iscsi/iscsi_target_login.h
index 63efd28..29d0983 100644
--- a/drivers/target/iscsi/iscsi_target_login.h
+++ b/drivers/target/iscsi/iscsi_target_login.h
@@ -12,6 +12,9 @@
extern int iscsit_get_login_rx(struct iscsi_conn *, struct iscsi_login *);
extern int iscsit_put_login_tx(struct iscsi_conn *, struct iscsi_login *, u32);
extern void iscsit_free_conn(struct iscsi_np *, struct iscsi_conn *);
+extern int iscsi_post_login_handler(struct iscsi_np *, struct iscsi_conn *, u8);
+extern void iscsi_target_login_sess_out(struct iscsi_conn *, struct iscsi_np *,
+ bool, bool);
extern int iscsi_target_login_thread(void *);
extern int iscsi_login_disable_FIM_keys(struct iscsi_param_list *, struct iscsi_conn *);
diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c
index c4675b4..14d1aed5 100644
--- a/drivers/target/iscsi/iscsi_target_nego.c
+++ b/drivers/target/iscsi/iscsi_target_nego.c
@@ -1,9 +1,7 @@
/*******************************************************************************
* This file contains main functions related to iSCSI Parameter negotiation.
*
- * \u00a9 Copyright 2007-2011 RisingTide Systems LLC.
- *
- * Licensed to the Linux Foundation under the General Public License (GPL) version 2.
+ * (c) Copyright 2007-2013 Datera, Inc.
*
* Author: Nicholas A. Bellinger <nab@linux-iscsi.org>
*
@@ -377,15 +375,284 @@
return 0;
}
-static int iscsi_target_do_login_io(struct iscsi_conn *conn, struct iscsi_login *login)
+static void iscsi_target_sk_data_ready(struct sock *sk, int count)
{
- if (iscsi_target_do_tx_login_io(conn, login) < 0)
- return -1;
+ struct iscsi_conn *conn = sk->sk_user_data;
+ bool rc;
- if (conn->conn_transport->iscsit_get_login_rx(conn, login) < 0)
- return -1;
+ pr_debug("Entering iscsi_target_sk_data_ready: conn: %p\n", conn);
- return 0;
+ write_lock_bh(&sk->sk_callback_lock);
+ if (!sk->sk_user_data) {
+ write_unlock_bh(&sk->sk_callback_lock);
+ return;
+ }
+ if (!test_bit(LOGIN_FLAGS_READY, &conn->login_flags)) {
+ write_unlock_bh(&sk->sk_callback_lock);
+ pr_debug("Got LOGIN_FLAGS_READY=0, conn: %p >>>>\n", conn);
+ return;
+ }
+ if (test_bit(LOGIN_FLAGS_CLOSED, &conn->login_flags)) {
+ write_unlock_bh(&sk->sk_callback_lock);
+ pr_debug("Got LOGIN_FLAGS_CLOSED=1, conn: %p >>>>\n", conn);
+ return;
+ }
+ if (test_and_set_bit(LOGIN_FLAGS_READ_ACTIVE, &conn->login_flags)) {
+ write_unlock_bh(&sk->sk_callback_lock);
+ pr_debug("Got LOGIN_FLAGS_READ_ACTIVE=1, conn: %p >>>>\n", conn);
+ return;
+ }
+
+ rc = schedule_delayed_work(&conn->login_work, 0);
+ if (rc == false) {
+ pr_debug("iscsi_target_sk_data_ready, schedule_delayed_work"
+ " got false\n");
+ }
+ write_unlock_bh(&sk->sk_callback_lock);
+}
+
+static void iscsi_target_sk_state_change(struct sock *);
+
+static void iscsi_target_set_sock_callbacks(struct iscsi_conn *conn)
+{
+ struct sock *sk;
+
+ if (!conn->sock)
+ return;
+
+ sk = conn->sock->sk;
+ pr_debug("Entering iscsi_target_set_sock_callbacks: conn: %p\n", conn);
+
+ write_lock_bh(&sk->sk_callback_lock);
+ sk->sk_user_data = conn;
+ conn->orig_data_ready = sk->sk_data_ready;
+ conn->orig_state_change = sk->sk_state_change;
+ sk->sk_data_ready = iscsi_target_sk_data_ready;
+ sk->sk_state_change = iscsi_target_sk_state_change;
+ write_unlock_bh(&sk->sk_callback_lock);
+
+ sk->sk_sndtimeo = TA_LOGIN_TIMEOUT * HZ;
+ sk->sk_rcvtimeo = TA_LOGIN_TIMEOUT * HZ;
+}
+
+static void iscsi_target_restore_sock_callbacks(struct iscsi_conn *conn)
+{
+ struct sock *sk;
+
+ if (!conn->sock)
+ return;
+
+ sk = conn->sock->sk;
+ pr_debug("Entering iscsi_target_restore_sock_callbacks: conn: %p\n", conn);
+
+ write_lock_bh(&sk->sk_callback_lock);
+ if (!sk->sk_user_data) {
+ write_unlock_bh(&sk->sk_callback_lock);
+ return;
+ }
+ sk->sk_user_data = NULL;
+ sk->sk_data_ready = conn->orig_data_ready;
+ sk->sk_state_change = conn->orig_state_change;
+ write_unlock_bh(&sk->sk_callback_lock);
+
+ sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT;
+ sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT;
+}
+
+static int iscsi_target_do_login(struct iscsi_conn *, struct iscsi_login *);
+
+static bool iscsi_target_sk_state_check(struct sock *sk)
+{
+ if (sk->sk_state == TCP_CLOSE_WAIT || sk->sk_state == TCP_CLOSE) {
+ pr_debug("iscsi_target_sk_state_check: TCP_CLOSE_WAIT|TCP_CLOSE,"
+ "returning FALSE\n");
+ return false;
+ }
+ return true;
+}
+
+static void iscsi_target_login_drop(struct iscsi_conn *conn, struct iscsi_login *login)
+{
+ struct iscsi_np *np = login->np;
+ bool zero_tsih = login->zero_tsih;
+
+ iscsi_remove_failed_auth_entry(conn);
+ iscsi_target_nego_release(conn);
+ iscsi_target_login_sess_out(conn, np, zero_tsih, true);
+}
+
+static void iscsi_target_login_timeout(unsigned long data)
+{
+ struct iscsi_conn *conn = (struct iscsi_conn *)data;
+
+ pr_debug("Entering iscsi_target_login_timeout >>>>>>>>>>>>>>>>>>>\n");
+
+ if (conn->login_kworker) {
+ pr_debug("Sending SIGINT to conn->login_kworker %s/%d\n",
+ conn->login_kworker->comm, conn->login_kworker->pid);
+ send_sig(SIGINT, conn->login_kworker, 1);
+ }
+}
+
+static void iscsi_target_do_login_rx(struct work_struct *work)
+{
+ struct iscsi_conn *conn = container_of(work,
+ struct iscsi_conn, login_work.work);
+ struct iscsi_login *login = conn->login;
+ struct iscsi_np *np = login->np;
+ struct iscsi_portal_group *tpg = conn->tpg;
+ struct iscsi_tpg_np *tpg_np = conn->tpg_np;
+ struct timer_list login_timer;
+ int rc, zero_tsih = login->zero_tsih;
+ bool state;
+
+ pr_debug("entering iscsi_target_do_login_rx, conn: %p, %s:%d\n",
+ conn, current->comm, current->pid);
+
+ spin_lock(&tpg->tpg_state_lock);
+ state = (tpg->tpg_state == TPG_STATE_ACTIVE);
+ spin_unlock(&tpg->tpg_state_lock);
+
+ if (state == false) {
+ pr_debug("iscsi_target_do_login_rx: tpg_state != TPG_STATE_ACTIVE\n");
+ iscsi_target_restore_sock_callbacks(conn);
+ iscsi_target_login_drop(conn, login);
+ iscsit_deaccess_np(np, tpg, tpg_np);
+ return;
+ }
+
+ if (conn->sock) {
+ struct sock *sk = conn->sock->sk;
+
+ read_lock_bh(&sk->sk_callback_lock);
+ state = iscsi_target_sk_state_check(sk);
+ read_unlock_bh(&sk->sk_callback_lock);
+
+ if (state == false) {
+ pr_debug("iscsi_target_do_login_rx, TCP state CLOSE\n");
+ iscsi_target_restore_sock_callbacks(conn);
+ iscsi_target_login_drop(conn, login);
+ iscsit_deaccess_np(np, tpg, tpg_np);
+ return;
+ }
+ }
+
+ conn->login_kworker = current;
+ allow_signal(SIGINT);
+
+ init_timer(&login_timer);
+ login_timer.expires = (get_jiffies_64() + TA_LOGIN_TIMEOUT * HZ);
+ login_timer.data = (unsigned long)conn;
+ login_timer.function = iscsi_target_login_timeout;
+ add_timer(&login_timer);
+ pr_debug("Starting login_timer for %s/%d\n", current->comm, current->pid);
+
+ rc = conn->conn_transport->iscsit_get_login_rx(conn, login);
+ del_timer_sync(&login_timer);
+ flush_signals(current);
+ conn->login_kworker = NULL;
+
+ if (rc < 0) {
+ iscsi_target_restore_sock_callbacks(conn);
+ iscsi_target_login_drop(conn, login);
+ iscsit_deaccess_np(np, tpg, tpg_np);
+ return;
+ }
+
+ pr_debug("iscsi_target_do_login_rx after rx_login_io, %p, %s:%d\n",
+ conn, current->comm, current->pid);
+
+ rc = iscsi_target_do_login(conn, login);
+ if (rc < 0) {
+ iscsi_target_restore_sock_callbacks(conn);
+ iscsi_target_login_drop(conn, login);
+ iscsit_deaccess_np(np, tpg, tpg_np);
+ } else if (!rc) {
+ if (conn->sock) {
+ struct sock *sk = conn->sock->sk;
+
+ write_lock_bh(&sk->sk_callback_lock);
+ clear_bit(LOGIN_FLAGS_READ_ACTIVE, &conn->login_flags);
+ write_unlock_bh(&sk->sk_callback_lock);
+ }
+ } else if (rc == 1) {
+ iscsi_target_nego_release(conn);
+ iscsi_post_login_handler(np, conn, zero_tsih);
+ iscsit_deaccess_np(np, tpg, tpg_np);
+ }
+}
+
+static void iscsi_target_do_cleanup(struct work_struct *work)
+{
+ struct iscsi_conn *conn = container_of(work,
+ struct iscsi_conn, login_cleanup_work.work);
+ struct sock *sk = conn->sock->sk;
+ struct iscsi_login *login = conn->login;
+ struct iscsi_np *np = login->np;
+ struct iscsi_portal_group *tpg = conn->tpg;
+ struct iscsi_tpg_np *tpg_np = conn->tpg_np;
+
+ pr_debug("Entering iscsi_target_do_cleanup\n");
+
+ cancel_delayed_work_sync(&conn->login_work);
+ conn->orig_state_change(sk);
+
+ iscsi_target_restore_sock_callbacks(conn);
+ iscsi_target_login_drop(conn, login);
+ iscsit_deaccess_np(np, tpg, tpg_np);
+
+ pr_debug("iscsi_target_do_cleanup done()\n");
+}
+
+static void iscsi_target_sk_state_change(struct sock *sk)
+{
+ struct iscsi_conn *conn;
+ void (*orig_state_change)(struct sock *);
+ bool state;
+
+ pr_debug("Entering iscsi_target_sk_state_change\n");
+
+ write_lock_bh(&sk->sk_callback_lock);
+ conn = sk->sk_user_data;
+ if (!conn) {
+ write_unlock_bh(&sk->sk_callback_lock);
+ return;
+ }
+ orig_state_change = conn->orig_state_change;
+
+ if (!test_bit(LOGIN_FLAGS_READY, &conn->login_flags)) {
+ pr_debug("Got LOGIN_FLAGS_READY=0 sk_state_change conn: %p\n",
+ conn);
+ write_unlock_bh(&sk->sk_callback_lock);
+ orig_state_change(sk);
+ return;
+ }
+ if (test_bit(LOGIN_FLAGS_READ_ACTIVE, &conn->login_flags)) {
+ pr_debug("Got LOGIN_FLAGS_READ_ACTIVE=1 sk_state_change"
+ " conn: %p\n", conn);
+ write_unlock_bh(&sk->sk_callback_lock);
+ orig_state_change(sk);
+ return;
+ }
+ if (test_and_set_bit(LOGIN_FLAGS_CLOSED, &conn->login_flags)) {
+ pr_debug("Got LOGIN_FLAGS_CLOSED=1 sk_state_change conn: %p\n",
+ conn);
+ write_unlock_bh(&sk->sk_callback_lock);
+ orig_state_change(sk);
+ return;
+ }
+
+ state = iscsi_target_sk_state_check(sk);
+ write_unlock_bh(&sk->sk_callback_lock);
+
+ pr_debug("iscsi_target_sk_state_change: state: %d\n", state);
+
+ if (!state) {
+ pr_debug("iscsi_target_sk_state_change got failed state\n");
+ schedule_delayed_work(&conn->login_cleanup_work, 0);
+ return;
+ }
+ orig_state_change(sk);
}
/*
@@ -643,10 +910,11 @@
if (login_rsp->flags & ISCSI_FLAG_LOGIN_TRANSIT) {
login->tsih = conn->sess->tsih;
login->login_complete = 1;
+ iscsi_target_restore_sock_callbacks(conn);
if (iscsi_target_do_tx_login_io(conn,
login) < 0)
return -1;
- return 0;
+ return 1;
}
break;
default:
@@ -656,13 +924,29 @@
break;
}
- if (iscsi_target_do_login_io(conn, login) < 0)
+ if (iscsi_target_do_tx_login_io(conn, login) < 0)
return -1;
if (login_rsp->flags & ISCSI_FLAG_LOGIN_TRANSIT) {
login_rsp->flags &= ~ISCSI_FLAG_LOGIN_TRANSIT;
login_rsp->flags &= ~ISCSI_FLAG_LOGIN_NEXT_STAGE_MASK;
}
+ break;
+ }
+
+ if (conn->sock) {
+ struct sock *sk = conn->sock->sk;
+ bool state;
+
+ read_lock_bh(&sk->sk_callback_lock);
+ state = iscsi_target_sk_state_check(sk);
+ read_unlock_bh(&sk->sk_callback_lock);
+
+ if (!state) {
+ pr_debug("iscsi_target_do_login() failed state for"
+ " conn: %p\n", conn);
+ return -1;
+ }
}
return 0;
@@ -695,9 +979,17 @@
char *tmpbuf, *start = NULL, *end = NULL, *key, *value;
struct iscsi_session *sess = conn->sess;
struct iscsi_tiqn *tiqn;
+ struct iscsi_tpg_np *tpg_np = NULL;
struct iscsi_login_req *login_req;
- u32 payload_length;
- int sessiontype = 0, ret = 0;
+ struct se_node_acl *se_nacl;
+ u32 payload_length, queue_depth = 0;
+ int sessiontype = 0, ret = 0, tag_num, tag_size;
+
+ INIT_DELAYED_WORK(&conn->login_work, iscsi_target_do_login_rx);
+ INIT_DELAYED_WORK(&conn->login_cleanup_work, iscsi_target_do_cleanup);
+ iscsi_target_set_sock_callbacks(conn);
+
+ login->np = np;
login_req = (struct iscsi_login_req *) login->req;
payload_length = ntoh24(login_req->dlength);
@@ -791,7 +1083,7 @@
goto out;
}
ret = 0;
- goto out;
+ goto alloc_tags;
}
get_target:
@@ -822,7 +1114,7 @@
/*
* Locate Target Portal Group from Storage Node.
*/
- conn->tpg = iscsit_get_tpg_from_np(tiqn, np);
+ conn->tpg = iscsit_get_tpg_from_np(tiqn, np, &tpg_np);
if (!conn->tpg) {
pr_err("Unable to locate Target Portal Group"
" on %s\n", tiqn->tiqn);
@@ -832,12 +1124,16 @@
ret = -1;
goto out;
}
+ conn->tpg_np = tpg_np;
pr_debug("Located Portal Group Object: %hu\n", conn->tpg->tpgt);
/*
* Setup crc32c modules from libcrypto
*/
if (iscsi_login_setup_crypto(conn) < 0) {
pr_err("iscsi_login_setup_crypto() failed\n");
+ kref_put(&tpg_np->tpg_np_kref, iscsit_login_kref_put);
+ iscsit_put_tiqn_for_login(tiqn);
+ conn->tpg = NULL;
ret = -1;
goto out;
}
@@ -846,11 +1142,12 @@
* process login attempt.
*/
if (iscsit_access_np(np, conn->tpg) < 0) {
+ kref_put(&tpg_np->tpg_np_kref, iscsit_login_kref_put);
iscsit_put_tiqn_for_login(tiqn);
iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
ISCSI_LOGIN_STATUS_SVC_UNAVAILABLE);
- ret = -1;
conn->tpg = NULL;
+ ret = -1;
goto out;
}
@@ -883,8 +1180,27 @@
ret = -1;
goto out;
}
+ se_nacl = sess->se_sess->se_node_acl;
+ queue_depth = se_nacl->queue_depth;
+ /*
+ * Setup pre-allocated tags based upon allowed per NodeACL CmdSN
+ * depth for non immediate commands, plus extra tags for immediate
+ * commands.
+ *
+ * Also enforce a ISCSIT_MIN_TAGS to prevent unnecessary contention
+ * in per-cpu-ida tag allocation logic + small queue_depth.
+ */
+alloc_tags:
+ tag_num = max_t(u32, ISCSIT_MIN_TAGS, queue_depth);
+ tag_num += ISCSIT_EXTRA_TAGS;
+ tag_size = sizeof(struct iscsi_cmd) + conn->conn_transport->priv_size;
- ret = 0;
+ ret = transport_alloc_session_tags(sess->se_sess, tag_num, tag_size);
+ if (ret < 0) {
+ iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
+ ISCSI_LOGIN_STATUS_NO_RESOURCES);
+ ret = -1;
+ }
out:
kfree(tmpbuf);
return ret;
@@ -897,10 +1213,23 @@
int ret;
ret = iscsi_target_do_login(conn, login);
- if (ret != 0)
- iscsi_remove_failed_auth_entry(conn);
+ if (!ret) {
+ if (conn->sock) {
+ struct sock *sk = conn->sock->sk;
- iscsi_target_nego_release(conn);
+ write_lock_bh(&sk->sk_callback_lock);
+ set_bit(LOGIN_FLAGS_READY, &conn->login_flags);
+ write_unlock_bh(&sk->sk_callback_lock);
+ }
+ } else if (ret < 0) {
+ cancel_delayed_work_sync(&conn->login_work);
+ cancel_delayed_work_sync(&conn->login_cleanup_work);
+ iscsi_target_restore_sock_callbacks(conn);
+ iscsi_remove_failed_auth_entry(conn);
+ }
+ if (ret != 0)
+ iscsi_target_nego_release(conn);
+
return ret;
}
diff --git a/drivers/target/iscsi/iscsi_target_nodeattrib.c b/drivers/target/iscsi/iscsi_target_nodeattrib.c
index 11dc293..93bdc47 100644
--- a/drivers/target/iscsi/iscsi_target_nodeattrib.c
+++ b/drivers/target/iscsi/iscsi_target_nodeattrib.c
@@ -1,9 +1,7 @@
/*******************************************************************************
* This file contains the main functions related to Initiator Node Attributes.
*
- * \u00a9 Copyright 2007-2011 RisingTide Systems LLC.
- *
- * Licensed to the Linux Foundation under the General Public License (GPL) version 2.
+ * (c) Copyright 2007-2013 Datera, Inc.
*
* Author: Nicholas A. Bellinger <nab@linux-iscsi.org>
*
diff --git a/drivers/target/iscsi/iscsi_target_parameters.c b/drivers/target/iscsi/iscsi_target_parameters.c
index 35fd643..4d2e23f 100644
--- a/drivers/target/iscsi/iscsi_target_parameters.c
+++ b/drivers/target/iscsi/iscsi_target_parameters.c
@@ -1,9 +1,7 @@
/*******************************************************************************
* This file contains main functions related to iSCSI Parameter negotiation.
*
- * \u00a9 Copyright 2007-2011 RisingTide Systems LLC.
- *
- * Licensed to the Linux Foundation under the General Public License (GPL) version 2.
+ * (c) Copyright 2007-2013 Datera, Inc.
*
* Author: Nicholas A. Bellinger <nab@linux-iscsi.org>
*
@@ -1182,7 +1180,7 @@
unsigned long long tmp;
int rc;
- rc = strict_strtoull(param->value, 0, &tmp);
+ rc = kstrtoull(param->value, 0, &tmp);
if (rc < 0)
return -1;
diff --git a/drivers/target/iscsi/iscsi_target_seq_pdu_list.c b/drivers/target/iscsi/iscsi_target_seq_pdu_list.c
index edb592a..ca41b58 100644
--- a/drivers/target/iscsi/iscsi_target_seq_pdu_list.c
+++ b/drivers/target/iscsi/iscsi_target_seq_pdu_list.c
@@ -2,9 +2,7 @@
* This file contains main functions related to iSCSI DataSequenceInOrder=No
* and DataPDUInOrder=No.
*
- \u00a9 Copyright 2007-2011 RisingTide Systems LLC.
- *
- * Licensed to the Linux Foundation under the General Public License (GPL) version 2.
+ * (c) Copyright 2007-2013 Datera, Inc.
*
* Author: Nicholas A. Bellinger <nab@linux-iscsi.org>
*
diff --git a/drivers/target/iscsi/iscsi_target_stat.c b/drivers/target/iscsi/iscsi_target_stat.c
index 464b420..f788e8b 100644
--- a/drivers/target/iscsi/iscsi_target_stat.c
+++ b/drivers/target/iscsi/iscsi_target_stat.c
@@ -2,9 +2,7 @@
* Modern ConfigFS group context specific iSCSI statistics based on original
* iscsi_target_mib.c code
*
- * Copyright (c) 2011 Rising Tide Systems
- *
- * Licensed to the Linux Foundation under the General Public License (GPL) version 2.
+ * Copyright (c) 2011-2013 Datera, Inc.
*
* Author: Nicholas A. Bellinger <nab@linux-iscsi.org>
*
@@ -177,7 +175,7 @@
static ssize_t iscsi_stat_instance_show_attr_vendor(
struct iscsi_wwn_stat_grps *igrps, char *page)
{
- return snprintf(page, PAGE_SIZE, "RisingTide Systems iSCSI-Target\n");
+ return snprintf(page, PAGE_SIZE, "Datera, Inc. iSCSI-Target\n");
}
ISCSI_STAT_INSTANCE_ATTR_RO(vendor);
@@ -432,13 +430,7 @@
int ret;
spin_lock(&lstat->lock);
- if (lstat->last_intr_fail_ip_family == AF_INET6) {
- ret = snprintf(page, PAGE_SIZE, "[%s]\n",
- lstat->last_intr_fail_ip_addr);
- } else {
- ret = snprintf(page, PAGE_SIZE, "%s\n",
- lstat->last_intr_fail_ip_addr);
- }
+ ret = snprintf(page, PAGE_SIZE, "%s\n", lstat->last_intr_fail_ip_addr);
spin_unlock(&lstat->lock);
return ret;
diff --git a/drivers/target/iscsi/iscsi_target_tmr.c b/drivers/target/iscsi/iscsi_target_tmr.c
index b997e5d..78404b1 100644
--- a/drivers/target/iscsi/iscsi_target_tmr.c
+++ b/drivers/target/iscsi/iscsi_target_tmr.c
@@ -1,9 +1,7 @@
/*******************************************************************************
* This file contains the iSCSI Target specific Task Management functions.
*
- * \u00a9 Copyright 2007-2011 RisingTide Systems LLC.
- *
- * Licensed to the Linux Foundation under the General Public License (GPL) version 2.
+ * (c) Copyright 2007-2013 Datera, Inc.
*
* Author: Nicholas A. Bellinger <nab@linux-iscsi.org>
*
diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c
index 439260b..4faeb47 100644
--- a/drivers/target/iscsi/iscsi_target_tpg.c
+++ b/drivers/target/iscsi/iscsi_target_tpg.c
@@ -1,9 +1,7 @@
/*******************************************************************************
* This file contains iSCSI Target Portal Group related functions.
*
- * \u00a9 Copyright 2007-2011 RisingTide Systems LLC.
- *
- * Licensed to the Linux Foundation under the General Public License (GPL) version 2.
+ * (c) Copyright 2007-2013 Datera, Inc.
*
* Author: Nicholas A. Bellinger <nab@linux-iscsi.org>
*
@@ -49,7 +47,7 @@
INIT_LIST_HEAD(&tpg->tpg_gnp_list);
INIT_LIST_HEAD(&tpg->tpg_list);
mutex_init(&tpg->tpg_access_lock);
- mutex_init(&tpg->np_login_lock);
+ sema_init(&tpg->np_login_sem, 1);
spin_lock_init(&tpg->tpg_state_lock);
spin_lock_init(&tpg->tpg_np_lock);
@@ -129,7 +127,8 @@
struct iscsi_portal_group *iscsit_get_tpg_from_np(
struct iscsi_tiqn *tiqn,
- struct iscsi_np *np)
+ struct iscsi_np *np,
+ struct iscsi_tpg_np **tpg_np_out)
{
struct iscsi_portal_group *tpg = NULL;
struct iscsi_tpg_np *tpg_np;
@@ -147,6 +146,8 @@
spin_lock(&tpg->tpg_np_lock);
list_for_each_entry(tpg_np, &tpg->tpg_gnp_list, tpg_np_list) {
if (tpg_np->tpg_np == np) {
+ *tpg_np_out = tpg_np;
+ kref_get(&tpg_np->tpg_np_kref);
spin_unlock(&tpg->tpg_np_lock);
spin_unlock(&tiqn->tiqn_tpg_lock);
return tpg;
@@ -175,18 +176,20 @@
static void iscsit_clear_tpg_np_login_thread(
struct iscsi_tpg_np *tpg_np,
- struct iscsi_portal_group *tpg)
+ struct iscsi_portal_group *tpg,
+ bool shutdown)
{
if (!tpg_np->tpg_np) {
pr_err("struct iscsi_tpg_np->tpg_np is NULL!\n");
return;
}
- iscsit_reset_np_thread(tpg_np->tpg_np, tpg_np, tpg);
+ iscsit_reset_np_thread(tpg_np->tpg_np, tpg_np, tpg, shutdown);
}
void iscsit_clear_tpg_np_login_threads(
- struct iscsi_portal_group *tpg)
+ struct iscsi_portal_group *tpg,
+ bool shutdown)
{
struct iscsi_tpg_np *tpg_np;
@@ -197,7 +200,7 @@
continue;
}
spin_unlock(&tpg->tpg_np_lock);
- iscsit_clear_tpg_np_login_thread(tpg_np, tpg);
+ iscsit_clear_tpg_np_login_thread(tpg_np, tpg, shutdown);
spin_lock(&tpg->tpg_np_lock);
}
spin_unlock(&tpg->tpg_np_lock);
@@ -268,6 +271,8 @@
tpg->tpg_state = TPG_STATE_INACTIVE;
spin_unlock(&tpg->tpg_state_lock);
+ iscsit_clear_tpg_np_login_threads(tpg, true);
+
if (iscsit_release_sessions_for_tpg(tpg, force) < 0) {
pr_err("Unable to delete iSCSI Target Portal Group:"
" %hu while active sessions exist, and force=0\n",
@@ -368,7 +373,7 @@
tpg->tpg_state = TPG_STATE_INACTIVE;
spin_unlock(&tpg->tpg_state_lock);
- iscsit_clear_tpg_np_login_threads(tpg);
+ iscsit_clear_tpg_np_login_threads(tpg, false);
if (iscsit_release_sessions_for_tpg(tpg, force) < 0) {
spin_lock(&tpg->tpg_state_lock);
@@ -490,6 +495,8 @@
INIT_LIST_HEAD(&tpg_np->tpg_np_child_list);
INIT_LIST_HEAD(&tpg_np->tpg_np_parent_list);
spin_lock_init(&tpg_np->tpg_np_parent_lock);
+ init_completion(&tpg_np->tpg_np_comp);
+ kref_init(&tpg_np->tpg_np_kref);
tpg_np->tpg_np = np;
tpg_np->tpg = tpg;
@@ -520,7 +527,7 @@
struct iscsi_portal_group *tpg,
struct iscsi_np *np)
{
- iscsit_clear_tpg_np_login_thread(tpg_np, tpg);
+ iscsit_clear_tpg_np_login_thread(tpg_np, tpg, true);
pr_debug("CORE[%s] - Removed Network Portal: %s:%hu,%hu on %s\n",
tpg->tpg_tiqn->tiqn, np->np_ip, np->np_port, tpg->tpgt,
diff --git a/drivers/target/iscsi/iscsi_target_tpg.h b/drivers/target/iscsi/iscsi_target_tpg.h
index dda48c1..b77693e 100644
--- a/drivers/target/iscsi/iscsi_target_tpg.h
+++ b/drivers/target/iscsi/iscsi_target_tpg.h
@@ -5,10 +5,10 @@
extern int iscsit_load_discovery_tpg(void);
extern void iscsit_release_discovery_tpg(void);
extern struct iscsi_portal_group *iscsit_get_tpg_from_np(struct iscsi_tiqn *,
- struct iscsi_np *);
+ struct iscsi_np *, struct iscsi_tpg_np **);
extern int iscsit_get_tpg(struct iscsi_portal_group *);
extern void iscsit_put_tpg(struct iscsi_portal_group *);
-extern void iscsit_clear_tpg_np_login_threads(struct iscsi_portal_group *);
+extern void iscsit_clear_tpg_np_login_threads(struct iscsi_portal_group *, bool);
extern void iscsit_tpg_dump_params(struct iscsi_portal_group *);
extern int iscsit_tpg_add_portal_group(struct iscsi_tiqn *, struct iscsi_portal_group *);
extern int iscsit_tpg_del_portal_group(struct iscsi_tiqn *, struct iscsi_portal_group *,
diff --git a/drivers/target/iscsi/iscsi_target_tq.c b/drivers/target/iscsi/iscsi_target_tq.c
index 8128952..601e9cc 100644
--- a/drivers/target/iscsi/iscsi_target_tq.c
+++ b/drivers/target/iscsi/iscsi_target_tq.c
@@ -1,9 +1,7 @@
/*******************************************************************************
* This file contains the iSCSI Login Thread and Thread Queue functions.
*
- * \u00a9 Copyright 2007-2011 RisingTide Systems LLC.
- *
- * Licensed to the Linux Foundation under the General Public License (GPL) version 2.
+ * (c) Copyright 2007-2013 Datera, Inc.
*
* Author: Nicholas A. Bellinger <nab@linux-iscsi.org>
*
@@ -105,12 +103,11 @@
ts->status = ISCSI_THREAD_SET_FREE;
INIT_LIST_HEAD(&ts->ts_list);
spin_lock_init(&ts->ts_state_lock);
- init_completion(&ts->rx_post_start_comp);
- init_completion(&ts->tx_post_start_comp);
init_completion(&ts->rx_restart_comp);
init_completion(&ts->tx_restart_comp);
init_completion(&ts->rx_start_comp);
init_completion(&ts->tx_start_comp);
+ sema_init(&ts->ts_activate_sem, 0);
ts->create_threads = 1;
ts->tx_thread = kthread_run(iscsi_target_tx_thread, ts, "%s",
@@ -139,35 +136,44 @@
return allocated_thread_pair_count;
}
+static void iscsi_deallocate_thread_one(struct iscsi_thread_set *ts)
+{
+ spin_lock_bh(&ts->ts_state_lock);
+ ts->status = ISCSI_THREAD_SET_DIE;
+
+ if (ts->rx_thread) {
+ complete(&ts->rx_start_comp);
+ spin_unlock_bh(&ts->ts_state_lock);
+ kthread_stop(ts->rx_thread);
+ spin_lock_bh(&ts->ts_state_lock);
+ }
+ if (ts->tx_thread) {
+ complete(&ts->tx_start_comp);
+ spin_unlock_bh(&ts->ts_state_lock);
+ kthread_stop(ts->tx_thread);
+ spin_lock_bh(&ts->ts_state_lock);
+ }
+ spin_unlock_bh(&ts->ts_state_lock);
+ /*
+ * Release this thread_id in the thread_set_bitmap
+ */
+ spin_lock(&ts_bitmap_lock);
+ bitmap_release_region(iscsit_global->ts_bitmap,
+ ts->thread_id, get_order(1));
+ spin_unlock(&ts_bitmap_lock);
+
+ kfree(ts);
+}
+
void iscsi_deallocate_thread_sets(void)
{
- u32 released_count = 0;
struct iscsi_thread_set *ts = NULL;
+ u32 released_count = 0;
while ((ts = iscsi_get_ts_from_inactive_list())) {
- spin_lock_bh(&ts->ts_state_lock);
- ts->status = ISCSI_THREAD_SET_DIE;
- spin_unlock_bh(&ts->ts_state_lock);
-
- if (ts->rx_thread) {
- send_sig(SIGINT, ts->rx_thread, 1);
- kthread_stop(ts->rx_thread);
- }
- if (ts->tx_thread) {
- send_sig(SIGINT, ts->tx_thread, 1);
- kthread_stop(ts->tx_thread);
- }
- /*
- * Release this thread_id in the thread_set_bitmap
- */
- spin_lock(&ts_bitmap_lock);
- bitmap_release_region(iscsit_global->ts_bitmap,
- ts->thread_id, get_order(1));
- spin_unlock(&ts_bitmap_lock);
-
+ iscsi_deallocate_thread_one(ts);
released_count++;
- kfree(ts);
}
if (released_count)
@@ -187,34 +193,13 @@
if (!ts)
break;
- spin_lock_bh(&ts->ts_state_lock);
- ts->status = ISCSI_THREAD_SET_DIE;
- spin_unlock_bh(&ts->ts_state_lock);
-
- if (ts->rx_thread) {
- send_sig(SIGINT, ts->rx_thread, 1);
- kthread_stop(ts->rx_thread);
- }
- if (ts->tx_thread) {
- send_sig(SIGINT, ts->tx_thread, 1);
- kthread_stop(ts->tx_thread);
- }
- /*
- * Release this thread_id in the thread_set_bitmap
- */
- spin_lock(&ts_bitmap_lock);
- bitmap_release_region(iscsit_global->ts_bitmap,
- ts->thread_id, get_order(1));
- spin_unlock(&ts_bitmap_lock);
-
+ iscsi_deallocate_thread_one(ts);
released_count++;
- kfree(ts);
}
- if (released_count) {
+ if (released_count)
pr_debug("Stopped %d thread set(s) (%d total threads)."
"\n", released_count, released_count * 2);
- }
}
void iscsi_activate_thread_set(struct iscsi_conn *conn, struct iscsi_thread_set *ts)
@@ -224,37 +209,23 @@
spin_lock_bh(&ts->ts_state_lock);
conn->thread_set = ts;
ts->conn = conn;
+ ts->status = ISCSI_THREAD_SET_ACTIVE;
spin_unlock_bh(&ts->ts_state_lock);
- /*
- * Start up the RX thread and wait on rx_post_start_comp. The RX
- * Thread will then do the same for the TX Thread in
- * iscsi_rx_thread_pre_handler().
- */
+
complete(&ts->rx_start_comp);
- wait_for_completion(&ts->rx_post_start_comp);
+ complete(&ts->tx_start_comp);
+
+ down(&ts->ts_activate_sem);
}
struct iscsi_thread_set *iscsi_get_thread_set(void)
{
- int allocate_ts = 0;
- struct completion comp;
- struct iscsi_thread_set *ts = NULL;
- /*
- * If no inactive thread set is available on the first call to
- * iscsi_get_ts_from_inactive_list(), sleep for a second and
- * try again. If still none are available after two attempts,
- * allocate a set ourselves.
- */
+ struct iscsi_thread_set *ts;
+
get_set:
ts = iscsi_get_ts_from_inactive_list();
if (!ts) {
- if (allocate_ts == 2)
- iscsi_allocate_thread_sets(1);
-
- init_completion(&comp);
- wait_for_completion_timeout(&comp, 1 * HZ);
-
- allocate_ts++;
+ iscsi_allocate_thread_sets(1);
goto get_set;
}
@@ -263,6 +234,7 @@
ts->thread_count = 2;
init_completion(&ts->rx_restart_comp);
init_completion(&ts->tx_restart_comp);
+ sema_init(&ts->ts_activate_sem, 0);
return ts;
}
@@ -400,7 +372,8 @@
static int iscsi_signal_thread_pre_handler(struct iscsi_thread_set *ts)
{
spin_lock_bh(&ts->ts_state_lock);
- if ((ts->status == ISCSI_THREAD_SET_DIE) || signal_pending(current)) {
+ if (ts->status == ISCSI_THREAD_SET_DIE || kthread_should_stop() ||
+ signal_pending(current)) {
spin_unlock_bh(&ts->ts_state_lock);
return -1;
}
@@ -419,7 +392,8 @@
goto sleep;
}
- flush_signals(current);
+ if (ts->status != ISCSI_THREAD_SET_DIE)
+ flush_signals(current);
if (ts->delay_inactive && (--ts->thread_count == 0)) {
spin_unlock_bh(&ts->ts_state_lock);
@@ -446,18 +420,19 @@
if (iscsi_signal_thread_pre_handler(ts) < 0)
return NULL;
+ iscsi_check_to_add_additional_sets();
+
+ spin_lock_bh(&ts->ts_state_lock);
if (!ts->conn) {
pr_err("struct iscsi_thread_set->conn is NULL for"
- " thread_id: %d, going back to sleep\n", ts->thread_id);
- goto sleep;
+ " RX thread_id: %s/%d\n", current->comm, current->pid);
+ spin_unlock_bh(&ts->ts_state_lock);
+ return NULL;
}
- iscsi_check_to_add_additional_sets();
- /*
- * The RX Thread starts up the TX Thread and sleeps.
- */
ts->thread_clear |= ISCSI_CLEAR_RX_THREAD;
- complete(&ts->tx_start_comp);
- wait_for_completion(&ts->tx_post_start_comp);
+ spin_unlock_bh(&ts->ts_state_lock);
+
+ up(&ts->ts_activate_sem);
return ts->conn;
}
@@ -472,7 +447,8 @@
goto sleep;
}
- flush_signals(current);
+ if (ts->status != ISCSI_THREAD_SET_DIE)
+ flush_signals(current);
if (ts->delay_inactive && (--ts->thread_count == 0)) {
spin_unlock_bh(&ts->ts_state_lock);
@@ -498,27 +474,20 @@
if (iscsi_signal_thread_pre_handler(ts) < 0)
return NULL;
- if (!ts->conn) {
- pr_err("struct iscsi_thread_set->conn is NULL for "
- " thread_id: %d, going back to sleep\n",
- ts->thread_id);
- goto sleep;
- }
-
iscsi_check_to_add_additional_sets();
- /*
- * From the TX thread, up the tx_post_start_comp that the RX Thread is
- * sleeping on in iscsi_rx_thread_pre_handler(), then up the
- * rx_post_start_comp that iscsi_activate_thread_set() is sleeping on.
- */
- ts->thread_clear |= ISCSI_CLEAR_TX_THREAD;
- complete(&ts->tx_post_start_comp);
- complete(&ts->rx_post_start_comp);
spin_lock_bh(&ts->ts_state_lock);
- ts->status = ISCSI_THREAD_SET_ACTIVE;
+ if (!ts->conn) {
+ pr_err("struct iscsi_thread_set->conn is NULL for"
+ " TX thread_id: %s/%d\n", current->comm, current->pid);
+ spin_unlock_bh(&ts->ts_state_lock);
+ return NULL;
+ }
+ ts->thread_clear |= ISCSI_CLEAR_TX_THREAD;
spin_unlock_bh(&ts->ts_state_lock);
+ up(&ts->ts_activate_sem);
+
return ts->conn;
}
diff --git a/drivers/target/iscsi/iscsi_target_tq.h b/drivers/target/iscsi/iscsi_target_tq.h
index 547d118..cc1eede 100644
--- a/drivers/target/iscsi/iscsi_target_tq.h
+++ b/drivers/target/iscsi/iscsi_target_tq.h
@@ -64,10 +64,6 @@
struct iscsi_conn *conn;
/* used for controlling ts state accesses */
spinlock_t ts_state_lock;
- /* Used for rx side post startup */
- struct completion rx_post_start_comp;
- /* Used for tx side post startup */
- struct completion tx_post_start_comp;
/* used for restarting thread queue */
struct completion rx_restart_comp;
/* used for restarting thread queue */
@@ -82,6 +78,7 @@
struct task_struct *tx_thread;
/* struct iscsi_thread_set in list list head*/
struct list_head ts_list;
+ struct semaphore ts_activate_sem;
};
#endif /*** ISCSI_THREAD_QUEUE_H ***/
diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c
index 1df06d5..f2de28e 100644
--- a/drivers/target/iscsi/iscsi_target_util.c
+++ b/drivers/target/iscsi/iscsi_target_util.c
@@ -1,9 +1,7 @@
/*******************************************************************************
* This file contains the iSCSI Target specific utility functions.
*
- * \u00a9 Copyright 2007-2011 RisingTide Systems LLC.
- *
- * Licensed to the Linux Foundation under the General Public License (GPL) version 2.
+ * (c) Copyright 2007-2013 Datera, Inc.
*
* Author: Nicholas A. Bellinger <nab@linux-iscsi.org>
*
@@ -19,6 +17,7 @@
******************************************************************************/
#include <linux/list.h>
+#include <linux/percpu_ida.h>
#include <scsi/scsi_tcq.h>
#include <scsi/iscsi_proto.h>
#include <target/target_core_base.h>
@@ -149,18 +148,6 @@
spin_unlock_bh(&cmd->r2t_lock);
}
-struct iscsi_cmd *iscsit_alloc_cmd(struct iscsi_conn *conn, gfp_t gfp_mask)
-{
- struct iscsi_cmd *cmd;
-
- cmd = kmem_cache_zalloc(lio_cmd_cache, gfp_mask);
- if (!cmd)
- return NULL;
-
- cmd->release_cmd = &iscsit_release_cmd;
- return cmd;
-}
-
/*
* May be called from software interrupt (timer) context for allocating
* iSCSI NopINs.
@@ -168,12 +155,15 @@
struct iscsi_cmd *iscsit_allocate_cmd(struct iscsi_conn *conn, gfp_t gfp_mask)
{
struct iscsi_cmd *cmd;
+ struct se_session *se_sess = conn->sess->se_sess;
+ int size, tag;
- cmd = conn->conn_transport->iscsit_alloc_cmd(conn, gfp_mask);
- if (!cmd) {
- pr_err("Unable to allocate memory for struct iscsi_cmd.\n");
- return NULL;
- }
+ tag = percpu_ida_alloc(&se_sess->sess_tag_pool, gfp_mask);
+ size = sizeof(struct iscsi_cmd) + conn->conn_transport->priv_size;
+ cmd = (struct iscsi_cmd *)(se_sess->sess_cmd_map + (tag * size));
+ memset(cmd, 0, size);
+
+ cmd->se_cmd.map_tag = tag;
cmd->conn = conn;
INIT_LIST_HEAD(&cmd->i_conn_node);
INIT_LIST_HEAD(&cmd->datain_list);
@@ -689,6 +679,16 @@
void iscsit_release_cmd(struct iscsi_cmd *cmd)
{
+ struct iscsi_session *sess;
+ struct se_cmd *se_cmd = &cmd->se_cmd;
+
+ if (cmd->conn)
+ sess = cmd->conn->sess;
+ else
+ sess = cmd->sess;
+
+ BUG_ON(!sess || !sess->se_sess);
+
kfree(cmd->buf_ptr);
kfree(cmd->pdu_list);
kfree(cmd->seq_list);
@@ -696,8 +696,9 @@
kfree(cmd->iov_data);
kfree(cmd->text_in_ptr);
- kmem_cache_free(lio_cmd_cache, cmd);
+ percpu_ida_free(&sess->se_sess->sess_tag_pool, se_cmd->map_tag);
}
+EXPORT_SYMBOL(iscsit_release_cmd);
static void __iscsit_free_cmd(struct iscsi_cmd *cmd, bool scsi_cmd,
bool check_queues)
@@ -761,7 +762,7 @@
/* Fall-through */
default:
__iscsit_free_cmd(cmd, false, shutdown);
- cmd->release_cmd(cmd);
+ iscsit_release_cmd(cmd);
break;
}
}
diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c
index 568ad25..0f6d69d 100644
--- a/drivers/target/loopback/tcm_loop.c
+++ b/drivers/target/loopback/tcm_loop.c
@@ -3,7 +3,7 @@
* This file contains the Linux/SCSI LLD virtual SCSI initiator driver
* for emulated SAS initiator ports
*
- * © Copyright 2011 RisingTide Systems LLC.
+ * © Copyright 2011-2013 Datera, Inc.
*
* Licensed to the Linux Foundation under the General Public License (GPL) version 2.
*
diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c
index cbe48ab..47244102 100644
--- a/drivers/target/target_core_alua.c
+++ b/drivers/target/target_core_alua.c
@@ -3,7 +3,7 @@
*
* This file contains SPC-3 compliant asymmetric logical unit assigntment (ALUA)
*
- * (c) Copyright 2009-2012 RisingTide Systems LLC.
+ * (c) Copyright 2009-2013 Datera, Inc.
*
* Nicholas A. Bellinger <nab@kernel.org>
*
@@ -557,6 +557,9 @@
* a ALUA logical unit group.
*/
tg_pt_gp_mem = port->sep_alua_tg_pt_gp_mem;
+ if (!tg_pt_gp_mem)
+ return 0;
+
spin_lock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
tg_pt_gp = tg_pt_gp_mem->tg_pt_gp;
out_alua_state = atomic_read(&tg_pt_gp->tg_pt_gp_alua_access_state);
@@ -730,7 +733,7 @@
if (ret < 0)
pr_err("Error writing ALUA metadata file: %s\n", path);
fput(file);
- return ret ? -EIO : 0;
+ return (ret < 0) ? -EIO : 0;
}
/*
@@ -1756,10 +1759,10 @@
unsigned long tmp;
int ret;
- ret = strict_strtoul(page, 0, &tmp);
+ ret = kstrtoul(page, 0, &tmp);
if (ret < 0) {
pr_err("Unable to extract alua_access_type\n");
- return -EINVAL;
+ return ret;
}
if ((tmp != 0) && (tmp != 1) && (tmp != 2) && (tmp != 3)) {
pr_err("Illegal value for alua_access_type:"
@@ -1794,10 +1797,10 @@
unsigned long tmp;
int ret;
- ret = strict_strtoul(page, 0, &tmp);
+ ret = kstrtoul(page, 0, &tmp);
if (ret < 0) {
pr_err("Unable to extract nonop_delay_msecs\n");
- return -EINVAL;
+ return ret;
}
if (tmp > ALUA_MAX_NONOP_DELAY_MSECS) {
pr_err("Passed nonop_delay_msecs: %lu, exceeds"
@@ -1825,10 +1828,10 @@
unsigned long tmp;
int ret;
- ret = strict_strtoul(page, 0, &tmp);
+ ret = kstrtoul(page, 0, &tmp);
if (ret < 0) {
pr_err("Unable to extract trans_delay_msecs\n");
- return -EINVAL;
+ return ret;
}
if (tmp > ALUA_MAX_TRANS_DELAY_MSECS) {
pr_err("Passed trans_delay_msecs: %lu, exceeds"
@@ -1856,10 +1859,10 @@
unsigned long tmp;
int ret;
- ret = strict_strtoul(page, 0, &tmp);
+ ret = kstrtoul(page, 0, &tmp);
if (ret < 0) {
pr_err("Unable to extract implict_trans_secs\n");
- return -EINVAL;
+ return ret;
}
if (tmp > ALUA_MAX_IMPLICT_TRANS_SECS) {
pr_err("Passed implict_trans_secs: %lu, exceeds"
@@ -1887,10 +1890,10 @@
unsigned long tmp;
int ret;
- ret = strict_strtoul(page, 0, &tmp);
+ ret = kstrtoul(page, 0, &tmp);
if (ret < 0) {
pr_err("Unable to extract preferred ALUA value\n");
- return -EINVAL;
+ return ret;
}
if ((tmp != 0) && (tmp != 1)) {
pr_err("Illegal value for preferred ALUA: %lu\n", tmp);
@@ -1922,10 +1925,10 @@
if (!lun->lun_sep)
return -ENODEV;
- ret = strict_strtoul(page, 0, &tmp);
+ ret = kstrtoul(page, 0, &tmp);
if (ret < 0) {
pr_err("Unable to extract alua_tg_pt_offline value\n");
- return -EINVAL;
+ return ret;
}
if ((tmp != 0) && (tmp != 1)) {
pr_err("Illegal value for alua_tg_pt_offline: %lu\n",
@@ -1961,10 +1964,10 @@
unsigned long tmp;
int ret;
- ret = strict_strtoul(page, 0, &tmp);
+ ret = kstrtoul(page, 0, &tmp);
if (ret < 0) {
pr_err("Unable to extract alua_tg_pt_status\n");
- return -EINVAL;
+ return ret;
}
if ((tmp != ALUA_STATUS_NONE) &&
(tmp != ALUA_STATUS_ALTERED_BY_EXPLICT_STPG) &&
@@ -1994,10 +1997,10 @@
unsigned long tmp;
int ret;
- ret = strict_strtoul(page, 0, &tmp);
+ ret = kstrtoul(page, 0, &tmp);
if (ret < 0) {
pr_err("Unable to extract alua_tg_pt_write_md\n");
- return -EINVAL;
+ return ret;
}
if ((tmp != 0) && (tmp != 1)) {
pr_err("Illegal value for alua_tg_pt_write_md:"
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index e4d2293..82e81c5 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -3,7 +3,7 @@
*
* This file contains ConfigFS logic for the Generic Target Engine project.
*
- * (c) Copyright 2008-2012 RisingTide Systems LLC.
+ * (c) Copyright 2008-2013 Datera, Inc.
*
* Nicholas A. Bellinger <nab@kernel.org>
*
@@ -48,6 +48,7 @@
#include "target_core_alua.h"
#include "target_core_pr.h"
#include "target_core_rd.h"
+#include "target_core_xcopy.h"
extern struct t10_alua_lu_gp *default_lu_gp;
@@ -268,7 +269,7 @@
},
};
-static struct configfs_subsystem *target_core_subsystem[] = {
+struct configfs_subsystem *target_core_subsystem[] = {
&target_core_fabrics,
NULL,
};
@@ -577,9 +578,9 @@
unsigned long val; \
int ret; \
\
- ret = strict_strtoul(page, 0, &val); \
+ ret = kstrtoul(page, 0, &val); \
if (ret < 0) { \
- pr_err("strict_strtoul() failed with" \
+ pr_err("kstrtoul() failed with" \
" ret: %d\n", ret); \
return -EINVAL; \
} \
@@ -636,6 +637,12 @@
DEF_DEV_ATTRIB(emulate_tpws);
SE_DEV_ATTR(emulate_tpws, S_IRUGO | S_IWUSR);
+DEF_DEV_ATTRIB(emulate_caw);
+SE_DEV_ATTR(emulate_caw, S_IRUGO | S_IWUSR);
+
+DEF_DEV_ATTRIB(emulate_3pc);
+SE_DEV_ATTR(emulate_3pc, S_IRUGO | S_IWUSR);
+
DEF_DEV_ATTRIB(enforce_pr_isids);
SE_DEV_ATTR(enforce_pr_isids, S_IRUGO | S_IWUSR);
@@ -693,6 +700,8 @@
&target_core_dev_attrib_emulate_tas.attr,
&target_core_dev_attrib_emulate_tpu.attr,
&target_core_dev_attrib_emulate_tpws.attr,
+ &target_core_dev_attrib_emulate_caw.attr,
+ &target_core_dev_attrib_emulate_3pc.attr,
&target_core_dev_attrib_enforce_pr_isids.attr,
&target_core_dev_attrib_is_nonrot.attr,
&target_core_dev_attrib_emulate_rest_reord.attr,
@@ -1310,9 +1319,9 @@
ret = -ENOMEM;
goto out;
}
- ret = strict_strtoull(arg_p, 0, &tmp_ll);
+ ret = kstrtoull(arg_p, 0, &tmp_ll);
if (ret < 0) {
- pr_err("strict_strtoull() failed for"
+ pr_err("kstrtoull() failed for"
" sa_res_key=\n");
goto out;
}
@@ -1836,11 +1845,11 @@
unsigned long lu_gp_id;
int ret;
- ret = strict_strtoul(page, 0, &lu_gp_id);
+ ret = kstrtoul(page, 0, &lu_gp_id);
if (ret < 0) {
- pr_err("strict_strtoul() returned %d for"
+ pr_err("kstrtoul() returned %d for"
" lu_gp_id\n", ret);
- return -EINVAL;
+ return ret;
}
if (lu_gp_id > 0x0000ffff) {
pr_err("ALUA lu_gp_id: %lu exceeds maximum:"
@@ -2032,11 +2041,11 @@
return -EINVAL;
}
- ret = strict_strtoul(page, 0, &tmp);
+ ret = kstrtoul(page, 0, &tmp);
if (ret < 0) {
pr_err("Unable to extract new ALUA access state from"
" %s\n", page);
- return -EINVAL;
+ return ret;
}
new_state = (int)tmp;
@@ -2079,11 +2088,11 @@
return -EINVAL;
}
- ret = strict_strtoul(page, 0, &tmp);
+ ret = kstrtoul(page, 0, &tmp);
if (ret < 0) {
pr_err("Unable to extract new ALUA access status"
" from %s\n", page);
- return -EINVAL;
+ return ret;
}
new_status = (int)tmp;
@@ -2139,10 +2148,10 @@
unsigned long tmp;
int ret;
- ret = strict_strtoul(page, 0, &tmp);
+ ret = kstrtoul(page, 0, &tmp);
if (ret < 0) {
pr_err("Unable to extract alua_write_metadata\n");
- return -EINVAL;
+ return ret;
}
if ((tmp != 0) && (tmp != 1)) {
@@ -2263,11 +2272,11 @@
unsigned long tg_pt_gp_id;
int ret;
- ret = strict_strtoul(page, 0, &tg_pt_gp_id);
+ ret = kstrtoul(page, 0, &tg_pt_gp_id);
if (ret < 0) {
- pr_err("strict_strtoul() returned %d for"
+ pr_err("kstrtoul() returned %d for"
" tg_pt_gp_id\n", ret);
- return -EINVAL;
+ return ret;
}
if (tg_pt_gp_id > 0x0000ffff) {
pr_err("ALUA tg_pt_gp_id: %lu exceeds maximum:"
@@ -2676,10 +2685,10 @@
if (transport->pmode_enable_hba == NULL)
return -EINVAL;
- ret = strict_strtoul(page, 0, &mode_flag);
+ ret = kstrtoul(page, 0, &mode_flag);
if (ret < 0) {
pr_err("Unable to extract hba mode flag: %d\n", ret);
- return -EINVAL;
+ return ret;
}
if (hba->dev_count) {
@@ -2767,11 +2776,11 @@
str++; /* Skip to start of plugin dependent ID */
}
- ret = strict_strtoul(str, 0, &plugin_dep_id);
+ ret = kstrtoul(str, 0, &plugin_dep_id);
if (ret < 0) {
- pr_err("strict_strtoul() returned %d for"
+ pr_err("kstrtoul() returned %d for"
" plugin_dep_id\n", ret);
- return ERR_PTR(-EINVAL);
+ return ERR_PTR(ret);
}
/*
* Load up TCM subsystem plugins if they have not already been loaded.
@@ -2927,6 +2936,10 @@
if (ret < 0)
goto out;
+ ret = target_xcopy_setup_pt();
+ if (ret < 0)
+ goto out;
+
return 0;
out:
@@ -2999,6 +3012,7 @@
core_dev_release_virtual_lun0();
rd_module_exit();
+ target_xcopy_release_pt();
release_se_kmem_caches();
}
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 8f4142f..d90dbb0 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -4,7 +4,7 @@
* This file contains the TCM Virtual Device and Disk Transport
* agnostic related functions.
*
- * (c) Copyright 2003-2012 RisingTide Systems LLC.
+ * (c) Copyright 2003-2013 Datera, Inc.
*
* Nicholas A. Bellinger <nab@kernel.org>
*
@@ -47,6 +47,9 @@
#include "target_core_pr.h"
#include "target_core_ua.h"
+DEFINE_MUTEX(g_device_mutex);
+LIST_HEAD(g_device_list);
+
static struct se_hba *lun0_hba;
/* not static, needed by tpg.c */
struct se_device *g_lun0_dev;
@@ -890,6 +893,32 @@
return 0;
}
+int se_dev_set_emulate_caw(struct se_device *dev, int flag)
+{
+ if (flag != 0 && flag != 1) {
+ pr_err("Illegal value %d\n", flag);
+ return -EINVAL;
+ }
+ dev->dev_attrib.emulate_caw = flag;
+ pr_debug("dev[%p]: SE Device CompareAndWrite (AtomicTestandSet): %d\n",
+ dev, flag);
+
+ return 0;
+}
+
+int se_dev_set_emulate_3pc(struct se_device *dev, int flag)
+{
+ if (flag != 0 && flag != 1) {
+ pr_err("Illegal value %d\n", flag);
+ return -EINVAL;
+ }
+ dev->dev_attrib.emulate_3pc = flag;
+ pr_debug("dev[%p]: SE Device 3rd Party Copy (EXTENDED_COPY): %d\n",
+ dev, flag);
+
+ return 0;
+}
+
int se_dev_set_enforce_pr_isids(struct se_device *dev, int flag)
{
if ((flag != 0) && (flag != 1)) {
@@ -1393,6 +1422,7 @@
INIT_LIST_HEAD(&dev->delayed_cmd_list);
INIT_LIST_HEAD(&dev->state_list);
INIT_LIST_HEAD(&dev->qf_cmd_list);
+ INIT_LIST_HEAD(&dev->g_dev_node);
spin_lock_init(&dev->stats_lock);
spin_lock_init(&dev->execute_task_lock);
spin_lock_init(&dev->delayed_cmd_lock);
@@ -1400,6 +1430,7 @@
spin_lock_init(&dev->se_port_lock);
spin_lock_init(&dev->se_tmr_lock);
spin_lock_init(&dev->qf_cmd_lock);
+ sema_init(&dev->caw_sem, 1);
atomic_set(&dev->dev_ordered_id, 0);
INIT_LIST_HEAD(&dev->t10_wwn.t10_vpd_list);
spin_lock_init(&dev->t10_wwn.t10_vpd_lock);
@@ -1423,6 +1454,8 @@
dev->dev_attrib.emulate_tas = DA_EMULATE_TAS;
dev->dev_attrib.emulate_tpu = DA_EMULATE_TPU;
dev->dev_attrib.emulate_tpws = DA_EMULATE_TPWS;
+ dev->dev_attrib.emulate_caw = DA_EMULATE_CAW;
+ dev->dev_attrib.emulate_3pc = DA_EMULATE_3PC;
dev->dev_attrib.enforce_pr_isids = DA_ENFORCE_PR_ISIDS;
dev->dev_attrib.is_nonrot = DA_IS_NONROT;
dev->dev_attrib.emulate_rest_reord = DA_EMULATE_REST_REORD;
@@ -1510,6 +1543,11 @@
spin_lock(&hba->device_lock);
hba->dev_count++;
spin_unlock(&hba->device_lock);
+
+ mutex_lock(&g_device_mutex);
+ list_add_tail(&dev->g_dev_node, &g_device_list);
+ mutex_unlock(&g_device_mutex);
+
return 0;
out_free_alua:
@@ -1528,6 +1566,10 @@
if (dev->dev_flags & DF_CONFIGURED) {
destroy_workqueue(dev->tmr_wq);
+ mutex_lock(&g_device_mutex);
+ list_del(&dev->g_dev_node);
+ mutex_unlock(&g_device_mutex);
+
spin_lock(&hba->device_lock);
hba->dev_count--;
spin_unlock(&hba->device_lock);
diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c
index eb56eb1..3503996 100644
--- a/drivers/target/target_core_fabric_configfs.c
+++ b/drivers/target/target_core_fabric_configfs.c
@@ -4,7 +4,7 @@
* This file contains generic fabric module configfs infrastructure for
* TCM v4.x code
*
- * (c) Copyright 2010-2012 RisingTide Systems LLC.
+ * (c) Copyright 2010-2013 Datera, Inc.
*
* Nicholas A. Bellinger <nab@linux-iscsi.org>
*
@@ -189,9 +189,11 @@
struct se_node_acl *se_nacl = lacl->se_lun_nacl;
struct se_portal_group *se_tpg = se_nacl->se_tpg;
unsigned long op;
+ int ret;
- if (strict_strtoul(page, 0, &op))
- return -EINVAL;
+ ret = kstrtoul(page, 0, &op);
+ if (ret)
+ return ret;
if ((op != 1) && (op != 0))
return -EINVAL;
@@ -350,7 +352,10 @@
* Determine the Mapped LUN value. This is what the SCSI Initiator
* Port will actually see.
*/
- if (strict_strtoul(buf + 4, 0, &mapped_lun) || mapped_lun > UINT_MAX) {
+ ret = kstrtoul(buf + 4, 0, &mapped_lun);
+ if (ret)
+ goto out;
+ if (mapped_lun > UINT_MAX) {
ret = -EINVAL;
goto out;
}
@@ -875,7 +880,10 @@
" \"lun_$LUN_NUMBER\"\n");
return ERR_PTR(-EINVAL);
}
- if (strict_strtoul(name + 4, 0, &unpacked_lun) || unpacked_lun > UINT_MAX)
+ errno = kstrtoul(name + 4, 0, &unpacked_lun);
+ if (errno)
+ return ERR_PTR(errno);
+ if (unpacked_lun > UINT_MAX)
return ERR_PTR(-EINVAL);
lun = core_get_lun_from_tpg(se_tpg, unpacked_lun);
diff --git a/drivers/target/target_core_fabric_lib.c b/drivers/target/target_core_fabric_lib.c
index 687b0b0..0d1cf8b 100644
--- a/drivers/target/target_core_fabric_lib.c
+++ b/drivers/target/target_core_fabric_lib.c
@@ -4,7 +4,7 @@
* This file contains generic high level protocol identifier and PR
* handlers for TCM fabric modules
*
- * (c) Copyright 2010-2012 RisingTide Systems LLC.
+ * (c) Copyright 2010-2013 Datera, Inc.
*
* Nicholas A. Bellinger <nab@linux-iscsi.org>
*
diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c
index b11890d..b662f89 100644
--- a/drivers/target/target_core_file.c
+++ b/drivers/target/target_core_file.c
@@ -3,7 +3,7 @@
*
* This file contains the Storage Engine <-> FILEIO transport specific functions
*
- * (c) Copyright 2005-2012 RisingTide Systems LLC.
+ * (c) Copyright 2005-2013 Datera, Inc.
*
* Nicholas A. Bellinger <nab@kernel.org>
*
@@ -547,11 +547,9 @@
}
static sense_reason_t
-fd_execute_rw(struct se_cmd *cmd)
+fd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
+ enum dma_data_direction data_direction)
{
- struct scatterlist *sgl = cmd->t_data_sg;
- u32 sgl_nents = cmd->t_data_nents;
- enum dma_data_direction data_direction = cmd->data_direction;
struct se_device *dev = cmd->se_dev;
int ret = 0;
@@ -635,10 +633,10 @@
ret = -ENOMEM;
break;
}
- ret = strict_strtoull(arg_p, 0, &fd_dev->fd_dev_size);
+ ret = kstrtoull(arg_p, 0, &fd_dev->fd_dev_size);
kfree(arg_p);
if (ret < 0) {
- pr_err("strict_strtoull() failed for"
+ pr_err("kstrtoull() failed for"
" fd_dev_size=\n");
goto out;
}
diff --git a/drivers/target/target_core_hba.c b/drivers/target/target_core_hba.c
index d2616cd..a25051a 100644
--- a/drivers/target/target_core_hba.c
+++ b/drivers/target/target_core_hba.c
@@ -3,7 +3,7 @@
*
* This file contains the TCM HBA Transport related functions.
*
- * (c) Copyright 2003-2012 RisingTide Systems LLC.
+ * (c) Copyright 2003-2013 Datera, Inc.
*
* Nicholas A. Bellinger <nab@kernel.org>
*
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index aa1620a..b9a3394 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -4,7 +4,7 @@
* This file contains the Storage Engine <-> Linux BlockIO transport
* specific functions.
*
- * (c) Copyright 2003-2012 RisingTide Systems LLC.
+ * (c) Copyright 2003-2013 Datera, Inc.
*
* Nicholas A. Bellinger <nab@kernel.org>
*
@@ -536,10 +536,10 @@
ret = -ENOMEM;
break;
}
- ret = strict_strtoul(arg_p, 0, &tmp_readonly);
+ ret = kstrtoul(arg_p, 0, &tmp_readonly);
kfree(arg_p);
if (ret < 0) {
- pr_err("strict_strtoul() failed for"
+ pr_err("kstrtoul() failed for"
" readonly=\n");
goto out;
}
@@ -587,11 +587,9 @@
}
static sense_reason_t
-iblock_execute_rw(struct se_cmd *cmd)
+iblock_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
+ enum dma_data_direction data_direction)
{
- struct scatterlist *sgl = cmd->t_data_sg;
- u32 sgl_nents = cmd->t_data_nents;
- enum dma_data_direction data_direction = cmd->data_direction;
struct se_device *dev = cmd->se_dev;
struct iblock_req *ibr;
struct bio *bio;
diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h
index 18d49df..579128a 100644
--- a/drivers/target/target_core_internal.h
+++ b/drivers/target/target_core_internal.h
@@ -33,6 +33,8 @@
int se_dev_set_emulate_tas(struct se_device *, int);
int se_dev_set_emulate_tpu(struct se_device *, int);
int se_dev_set_emulate_tpws(struct se_device *, int);
+int se_dev_set_emulate_caw(struct se_device *, int);
+int se_dev_set_emulate_3pc(struct se_device *, int);
int se_dev_set_enforce_pr_isids(struct se_device *, int);
int se_dev_set_is_nonrot(struct se_device *, int);
int se_dev_set_emulate_rest_reord(struct se_device *dev, int);
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index bd78faf..d1ae4c5 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -4,7 +4,7 @@
* This file contains SPC-3 compliant persistent reservations and
* legacy SPC-2 reservations with compatible reservation handling (CRH=1)
*
- * (c) Copyright 2009-2012 RisingTide Systems LLC.
+ * (c) Copyright 2009-2013 Datera, Inc.
*
* Nicholas A. Bellinger <nab@kernel.org>
*
@@ -1949,7 +1949,7 @@
pr_debug("Error writing APTPL metadata file: %s\n", path);
fput(file);
- return ret ? -EIO : 0;
+ return (ret < 0) ? -EIO : 0;
}
/*
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index e992b27..551c96c 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -3,7 +3,7 @@
*
* This file contains the generic target mode <-> Linux SCSI subsystem plugin.
*
- * (c) Copyright 2003-2012 RisingTide Systems LLC.
+ * (c) Copyright 2003-2013 Datera, Inc.
*
* Nicholas A. Bellinger <nab@kernel.org>
*
@@ -1050,9 +1050,8 @@
req = blk_get_request(pdv->pdv_sd->request_queue,
(data_direction == DMA_TO_DEVICE),
GFP_KERNEL);
- if (!req || IS_ERR(req)) {
- pr_err("PSCSI: blk_get_request() failed: %ld\n",
- req ? IS_ERR(req) : -ENOMEM);
+ if (!req) {
+ pr_err("PSCSI: blk_get_request() failed\n");
ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
goto fail;
}
diff --git a/drivers/target/target_core_rd.c b/drivers/target/target_core_rd.c
index 51127d1..131327a 100644
--- a/drivers/target/target_core_rd.c
+++ b/drivers/target/target_core_rd.c
@@ -4,7 +4,7 @@
* This file contains the Storage Engine <-> Ramdisk transport
* specific functions.
*
- * (c) Copyright 2003-2012 RisingTide Systems LLC.
+ * (c) Copyright 2003-2013 Datera, Inc.
*
* Nicholas A. Bellinger <nab@kernel.org>
*
@@ -280,11 +280,9 @@
}
static sense_reason_t
-rd_execute_rw(struct se_cmd *cmd)
+rd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
+ enum dma_data_direction data_direction)
{
- struct scatterlist *sgl = cmd->t_data_sg;
- u32 sgl_nents = cmd->t_data_nents;
- enum dma_data_direction data_direction = cmd->data_direction;
struct se_device *se_dev = cmd->se_dev;
struct rd_dev *dev = RD_DEV(se_dev);
struct rd_dev_sg_table *table;
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index 8a46277..6c17295 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -1,7 +1,7 @@
/*
* SCSI Block Commands (SBC) parsing and emulation.
*
- * (c) Copyright 2002-2012 RisingTide Systems LLC.
+ * (c) Copyright 2002-2013 Datera, Inc.
*
* Nicholas A. Bellinger <nab@kernel.org>
*
@@ -25,6 +25,7 @@
#include <linux/ratelimit.h>
#include <asm/unaligned.h>
#include <scsi/scsi.h>
+#include <scsi/scsi_tcq.h>
#include <target/target_core_base.h>
#include <target/target_core_backend.h>
@@ -280,13 +281,13 @@
return 0;
}
-static void xdreadwrite_callback(struct se_cmd *cmd)
+static sense_reason_t xdreadwrite_callback(struct se_cmd *cmd)
{
unsigned char *buf, *addr;
struct scatterlist *sg;
unsigned int offset;
- int i;
- int count;
+ sense_reason_t ret = TCM_NO_SENSE;
+ int i, count;
/*
* From sbc3r22.pdf section 5.48 XDWRITEREAD (10) command
*
@@ -301,7 +302,7 @@
buf = kmalloc(cmd->data_length, GFP_KERNEL);
if (!buf) {
pr_err("Unable to allocate xor_callback buf\n");
- return;
+ return TCM_OUT_OF_RESOURCES;
}
/*
* Copy the scatterlist WRITE buffer located at cmd->t_data_sg
@@ -320,8 +321,10 @@
offset = 0;
for_each_sg(cmd->t_bidi_data_sg, sg, cmd->t_bidi_data_nents, count) {
addr = kmap_atomic(sg_page(sg));
- if (!addr)
+ if (!addr) {
+ ret = TCM_OUT_OF_RESOURCES;
goto out;
+ }
for (i = 0; i < sg->length; i++)
*(addr + sg->offset + i) ^= *(buf + offset + i);
@@ -332,6 +335,193 @@
out:
kfree(buf);
+ return ret;
+}
+
+static sense_reason_t
+sbc_execute_rw(struct se_cmd *cmd)
+{
+ return cmd->execute_rw(cmd, cmd->t_data_sg, cmd->t_data_nents,
+ cmd->data_direction);
+}
+
+static sense_reason_t compare_and_write_post(struct se_cmd *cmd)
+{
+ struct se_device *dev = cmd->se_dev;
+
+ cmd->se_cmd_flags |= SCF_COMPARE_AND_WRITE_POST;
+ /*
+ * Unlock ->caw_sem originally obtained during sbc_compare_and_write()
+ * before the original READ I/O submission.
+ */
+ up(&dev->caw_sem);
+
+ return TCM_NO_SENSE;
+}
+
+static sense_reason_t compare_and_write_callback(struct se_cmd *cmd)
+{
+ struct se_device *dev = cmd->se_dev;
+ struct scatterlist *write_sg = NULL, *sg;
+ unsigned char *buf, *addr;
+ struct sg_mapping_iter m;
+ unsigned int offset = 0, len;
+ unsigned int nlbas = cmd->t_task_nolb;
+ unsigned int block_size = dev->dev_attrib.block_size;
+ unsigned int compare_len = (nlbas * block_size);
+ sense_reason_t ret = TCM_NO_SENSE;
+ int rc, i;
+
+ /*
+ * Handle early failure in transport_generic_request_failure(),
+ * which will not have taken ->caw_mutex yet..
+ */
+ if (!cmd->t_data_sg || !cmd->t_bidi_data_sg)
+ return TCM_NO_SENSE;
+
+ buf = kzalloc(cmd->data_length, GFP_KERNEL);
+ if (!buf) {
+ pr_err("Unable to allocate compare_and_write buf\n");
+ ret = TCM_OUT_OF_RESOURCES;
+ goto out;
+ }
+
+ write_sg = kzalloc(sizeof(struct scatterlist) * cmd->t_data_nents,
+ GFP_KERNEL);
+ if (!write_sg) {
+ pr_err("Unable to allocate compare_and_write sg\n");
+ ret = TCM_OUT_OF_RESOURCES;
+ goto out;
+ }
+ /*
+ * Setup verify and write data payloads from total NumberLBAs.
+ */
+ rc = sg_copy_to_buffer(cmd->t_data_sg, cmd->t_data_nents, buf,
+ cmd->data_length);
+ if (!rc) {
+ pr_err("sg_copy_to_buffer() failed for compare_and_write\n");
+ ret = TCM_OUT_OF_RESOURCES;
+ goto out;
+ }
+ /*
+ * Compare against SCSI READ payload against verify payload
+ */
+ for_each_sg(cmd->t_bidi_data_sg, sg, cmd->t_bidi_data_nents, i) {
+ addr = (unsigned char *)kmap_atomic(sg_page(sg));
+ if (!addr) {
+ ret = TCM_OUT_OF_RESOURCES;
+ goto out;
+ }
+
+ len = min(sg->length, compare_len);
+
+ if (memcmp(addr, buf + offset, len)) {
+ pr_warn("Detected MISCOMPARE for addr: %p buf: %p\n",
+ addr, buf + offset);
+ kunmap_atomic(addr);
+ goto miscompare;
+ }
+ kunmap_atomic(addr);
+
+ offset += len;
+ compare_len -= len;
+ if (!compare_len)
+ break;
+ }
+
+ i = 0;
+ len = cmd->t_task_nolb * block_size;
+ sg_miter_start(&m, cmd->t_data_sg, cmd->t_data_nents, SG_MITER_TO_SG);
+ /*
+ * Currently assumes NoLB=1 and SGLs are PAGE_SIZE..
+ */
+ while (len) {
+ sg_miter_next(&m);
+
+ if (block_size < PAGE_SIZE) {
+ sg_set_page(&write_sg[i], m.page, block_size,
+ block_size);
+ } else {
+ sg_miter_next(&m);
+ sg_set_page(&write_sg[i], m.page, block_size,
+ 0);
+ }
+ len -= block_size;
+ i++;
+ }
+ sg_miter_stop(&m);
+ /*
+ * Save the original SGL + nents values before updating to new
+ * assignments, to be released in transport_free_pages() ->
+ * transport_reset_sgl_orig()
+ */
+ cmd->t_data_sg_orig = cmd->t_data_sg;
+ cmd->t_data_sg = write_sg;
+ cmd->t_data_nents_orig = cmd->t_data_nents;
+ cmd->t_data_nents = 1;
+
+ cmd->sam_task_attr = MSG_HEAD_TAG;
+ cmd->transport_complete_callback = compare_and_write_post;
+ /*
+ * Now reset ->execute_cmd() to the normal sbc_execute_rw() handler
+ * for submitting the adjusted SGL to write instance user-data.
+ */
+ cmd->execute_cmd = sbc_execute_rw;
+
+ spin_lock_irq(&cmd->t_state_lock);
+ cmd->t_state = TRANSPORT_PROCESSING;
+ cmd->transport_state |= CMD_T_ACTIVE|CMD_T_BUSY|CMD_T_SENT;
+ spin_unlock_irq(&cmd->t_state_lock);
+
+ __target_execute_cmd(cmd);
+
+ kfree(buf);
+ return ret;
+
+miscompare:
+ pr_warn("Target/%s: Send MISCOMPARE check condition and sense\n",
+ dev->transport->name);
+ ret = TCM_MISCOMPARE_VERIFY;
+out:
+ /*
+ * In the MISCOMPARE or failure case, unlock ->caw_sem obtained in
+ * sbc_compare_and_write() before the original READ I/O submission.
+ */
+ up(&dev->caw_sem);
+ kfree(write_sg);
+ kfree(buf);
+ return ret;
+}
+
+static sense_reason_t
+sbc_compare_and_write(struct se_cmd *cmd)
+{
+ struct se_device *dev = cmd->se_dev;
+ sense_reason_t ret;
+ int rc;
+ /*
+ * Submit the READ first for COMPARE_AND_WRITE to perform the
+ * comparision using SGLs at cmd->t_bidi_data_sg..
+ */
+ rc = down_interruptible(&dev->caw_sem);
+ if ((rc != 0) || signal_pending(current)) {
+ cmd->transport_complete_callback = NULL;
+ return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ }
+
+ ret = cmd->execute_rw(cmd, cmd->t_bidi_data_sg, cmd->t_bidi_data_nents,
+ DMA_FROM_DEVICE);
+ if (ret) {
+ cmd->transport_complete_callback = NULL;
+ up(&dev->caw_sem);
+ return ret;
+ }
+ /*
+ * Unlock of dev->caw_sem to occur in compare_and_write_callback()
+ * upon MISCOMPARE, or in compare_and_write_done() upon completion
+ * of WRITE instance user-data.
+ */
+ return TCM_NO_SENSE;
}
sense_reason_t
@@ -348,31 +538,36 @@
sectors = transport_get_sectors_6(cdb);
cmd->t_task_lba = transport_lba_21(cdb);
cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
- cmd->execute_cmd = ops->execute_rw;
+ cmd->execute_rw = ops->execute_rw;
+ cmd->execute_cmd = sbc_execute_rw;
break;
case READ_10:
sectors = transport_get_sectors_10(cdb);
cmd->t_task_lba = transport_lba_32(cdb);
cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
- cmd->execute_cmd = ops->execute_rw;
+ cmd->execute_rw = ops->execute_rw;
+ cmd->execute_cmd = sbc_execute_rw;
break;
case READ_12:
sectors = transport_get_sectors_12(cdb);
cmd->t_task_lba = transport_lba_32(cdb);
cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
- cmd->execute_cmd = ops->execute_rw;
+ cmd->execute_rw = ops->execute_rw;
+ cmd->execute_cmd = sbc_execute_rw;
break;
case READ_16:
sectors = transport_get_sectors_16(cdb);
cmd->t_task_lba = transport_lba_64(cdb);
cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
- cmd->execute_cmd = ops->execute_rw;
+ cmd->execute_rw = ops->execute_rw;
+ cmd->execute_cmd = sbc_execute_rw;
break;
case WRITE_6:
sectors = transport_get_sectors_6(cdb);
cmd->t_task_lba = transport_lba_21(cdb);
cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
- cmd->execute_cmd = ops->execute_rw;
+ cmd->execute_rw = ops->execute_rw;
+ cmd->execute_cmd = sbc_execute_rw;
break;
case WRITE_10:
case WRITE_VERIFY:
@@ -381,7 +576,8 @@
if (cdb[1] & 0x8)
cmd->se_cmd_flags |= SCF_FUA;
cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
- cmd->execute_cmd = ops->execute_rw;
+ cmd->execute_rw = ops->execute_rw;
+ cmd->execute_cmd = sbc_execute_rw;
break;
case WRITE_12:
sectors = transport_get_sectors_12(cdb);
@@ -389,7 +585,8 @@
if (cdb[1] & 0x8)
cmd->se_cmd_flags |= SCF_FUA;
cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
- cmd->execute_cmd = ops->execute_rw;
+ cmd->execute_rw = ops->execute_rw;
+ cmd->execute_cmd = sbc_execute_rw;
break;
case WRITE_16:
sectors = transport_get_sectors_16(cdb);
@@ -397,7 +594,8 @@
if (cdb[1] & 0x8)
cmd->se_cmd_flags |= SCF_FUA;
cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
- cmd->execute_cmd = ops->execute_rw;
+ cmd->execute_rw = ops->execute_rw;
+ cmd->execute_cmd = sbc_execute_rw;
break;
case XDWRITEREAD_10:
if (cmd->data_direction != DMA_TO_DEVICE ||
@@ -411,7 +609,8 @@
/*
* Setup BIDI XOR callback to be run after I/O completion.
*/
- cmd->execute_cmd = ops->execute_rw;
+ cmd->execute_rw = ops->execute_rw;
+ cmd->execute_cmd = sbc_execute_rw;
cmd->transport_complete_callback = &xdreadwrite_callback;
if (cdb[1] & 0x8)
cmd->se_cmd_flags |= SCF_FUA;
@@ -434,7 +633,8 @@
* Setup BIDI XOR callback to be run during after I/O
* completion.
*/
- cmd->execute_cmd = ops->execute_rw;
+ cmd->execute_rw = ops->execute_rw;
+ cmd->execute_cmd = sbc_execute_rw;
cmd->transport_complete_callback = &xdreadwrite_callback;
if (cdb[1] & 0x8)
cmd->se_cmd_flags |= SCF_FUA;
@@ -461,6 +661,28 @@
}
break;
}
+ case COMPARE_AND_WRITE:
+ sectors = cdb[13];
+ /*
+ * Currently enforce COMPARE_AND_WRITE for a single sector
+ */
+ if (sectors > 1) {
+ pr_err("COMPARE_AND_WRITE contains NoLB: %u greater"
+ " than 1\n", sectors);
+ return TCM_INVALID_CDB_FIELD;
+ }
+ /*
+ * Double size because we have two buffers, note that
+ * zero is not an error..
+ */
+ size = 2 * sbc_get_size(cmd, sectors);
+ cmd->t_task_lba = get_unaligned_be64(&cdb[2]);
+ cmd->t_task_nolb = sectors;
+ cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB | SCF_COMPARE_AND_WRITE;
+ cmd->execute_rw = ops->execute_rw;
+ cmd->execute_cmd = sbc_compare_and_write;
+ cmd->transport_complete_callback = compare_and_write_callback;
+ break;
case READ_CAPACITY:
size = READ_CAP_LEN;
cmd->execute_cmd = sbc_emulate_readcapacity;
@@ -600,7 +822,8 @@
return TCM_ADDRESS_OUT_OF_RANGE;
}
- size = sbc_get_size(cmd, sectors);
+ if (!(cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE))
+ size = sbc_get_size(cmd, sectors);
}
return target_cmd_size_check(cmd, size);
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index 9fabbf7..0745395 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -1,7 +1,7 @@
/*
* SCSI Primary Commands (SPC) parsing and emulation.
*
- * (c) Copyright 2002-2012 RisingTide Systems LLC.
+ * (c) Copyright 2002-2013 Datera, Inc.
*
* Nicholas A. Bellinger <nab@kernel.org>
*
@@ -35,7 +35,7 @@
#include "target_core_alua.h"
#include "target_core_pr.h"
#include "target_core_ua.h"
-
+#include "target_core_xcopy.h"
static void spc_fill_alua_data(struct se_port *port, unsigned char *buf)
{
@@ -95,6 +95,12 @@
*/
spc_fill_alua_data(lun->lun_sep, buf);
+ /*
+ * Set Third-Party Copy (3PC) bit to indicate support for EXTENDED_COPY
+ */
+ if (dev->dev_attrib.emulate_3pc)
+ buf[5] |= 0x8;
+
buf[7] = 0x2; /* CmdQue=1 */
memcpy(&buf[8], "LIO-ORG ", 8);
@@ -129,8 +135,8 @@
return 0;
}
-static void spc_parse_naa_6h_vendor_specific(struct se_device *dev,
- unsigned char *buf)
+void spc_parse_naa_6h_vendor_specific(struct se_device *dev,
+ unsigned char *buf)
{
unsigned char *p = &dev->t10_wwn.unit_serial[0];
int cnt;
@@ -460,6 +466,11 @@
/* Set WSNZ to 1 */
buf[4] = 0x01;
+ /*
+ * Set MAXIMUM COMPARE AND WRITE LENGTH
+ */
+ if (dev->dev_attrib.emulate_caw)
+ buf[5] = 0x01;
/*
* Set OPTIMAL TRANSFER LENGTH GRANULARITY
@@ -1250,8 +1261,14 @@
*size = (cdb[6] << 24) | (cdb[7] << 16) | (cdb[8] << 8) | cdb[9];
break;
case EXTENDED_COPY:
- case READ_ATTRIBUTE:
+ *size = get_unaligned_be32(&cdb[10]);
+ cmd->execute_cmd = target_do_xcopy;
+ break;
case RECEIVE_COPY_RESULTS:
+ *size = get_unaligned_be32(&cdb[10]);
+ cmd->execute_cmd = target_do_receive_copy_results;
+ break;
+ case READ_ATTRIBUTE:
case WRITE_ATTRIBUTE:
*size = (cdb[10] << 24) | (cdb[11] << 16) |
(cdb[12] << 8) | cdb[13];
diff --git a/drivers/target/target_core_stat.c b/drivers/target/target_core_stat.c
index d154ce7..9c642e0 100644
--- a/drivers/target/target_core_stat.c
+++ b/drivers/target/target_core_stat.c
@@ -4,7 +4,7 @@
* Modern ConfigFS group context specific statistics based on original
* target_core_mib.c code
*
- * (c) Copyright 2006-2012 RisingTide Systems LLC.
+ * (c) Copyright 2006-2013 Datera, Inc.
*
* Nicholas A. Bellinger <nab@linux-iscsi.org>
*
diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c
index 0d7cacb..2500099 100644
--- a/drivers/target/target_core_tmr.c
+++ b/drivers/target/target_core_tmr.c
@@ -3,7 +3,7 @@
*
* This file contains SPC-3 task management infrastructure
*
- * (c) Copyright 2009-2012 RisingTide Systems LLC.
+ * (c) Copyright 2009-2013 Datera, Inc.
*
* Nicholas A. Bellinger <nab@kernel.org>
*
diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c
index aac9d27..b9a6ec0 100644
--- a/drivers/target/target_core_tpg.c
+++ b/drivers/target/target_core_tpg.c
@@ -3,7 +3,7 @@
*
* This file contains generic Target Portal Group related functions.
*
- * (c) Copyright 2002-2012 RisingTide Systems LLC.
+ * (c) Copyright 2002-2013 Datera, Inc.
*
* Nicholas A. Bellinger <nab@kernel.org>
*
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index d8e49d7..84747cc 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -3,7 +3,7 @@
*
* This file contains the Generic Target Engine Core.
*
- * (c) Copyright 2002-2012 RisingTide Systems LLC.
+ * (c) Copyright 2002-2013 Datera, Inc.
*
* Nicholas A. Bellinger <nab@kernel.org>
*
@@ -67,7 +67,6 @@
static void transport_complete_task_attr(struct se_cmd *cmd);
static void transport_handle_queue_full(struct se_cmd *cmd,
struct se_device *dev);
-static int transport_generic_get_mem(struct se_cmd *cmd);
static int transport_put_cmd(struct se_cmd *cmd);
static void target_complete_ok_work(struct work_struct *work);
@@ -232,6 +231,50 @@
}
EXPORT_SYMBOL(transport_init_session);
+int transport_alloc_session_tags(struct se_session *se_sess,
+ unsigned int tag_num, unsigned int tag_size)
+{
+ int rc;
+
+ se_sess->sess_cmd_map = kzalloc(tag_num * tag_size, GFP_KERNEL);
+ if (!se_sess->sess_cmd_map) {
+ pr_err("Unable to allocate se_sess->sess_cmd_map\n");
+ return -ENOMEM;
+ }
+
+ rc = percpu_ida_init(&se_sess->sess_tag_pool, tag_num);
+ if (rc < 0) {
+ pr_err("Unable to init se_sess->sess_tag_pool,"
+ " tag_num: %u\n", tag_num);
+ kfree(se_sess->sess_cmd_map);
+ se_sess->sess_cmd_map = NULL;
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(transport_alloc_session_tags);
+
+struct se_session *transport_init_session_tags(unsigned int tag_num,
+ unsigned int tag_size)
+{
+ struct se_session *se_sess;
+ int rc;
+
+ se_sess = transport_init_session();
+ if (IS_ERR(se_sess))
+ return se_sess;
+
+ rc = transport_alloc_session_tags(se_sess, tag_num, tag_size);
+ if (rc < 0) {
+ transport_free_session(se_sess);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ return se_sess;
+}
+EXPORT_SYMBOL(transport_init_session_tags);
+
/*
* Called with spin_lock_irqsave(&struct se_portal_group->session_lock called.
*/
@@ -367,6 +410,10 @@
void transport_free_session(struct se_session *se_sess)
{
+ if (se_sess->sess_cmd_map) {
+ percpu_ida_destroy(&se_sess->sess_tag_pool);
+ kfree(se_sess->sess_cmd_map);
+ }
kmem_cache_free(se_sess_cache, se_sess);
}
EXPORT_SYMBOL(transport_free_session);
@@ -1206,7 +1253,7 @@
}
EXPORT_SYMBOL(transport_handle_cdb_direct);
-static sense_reason_t
+sense_reason_t
transport_generic_map_mem_to_cmd(struct se_cmd *cmd, struct scatterlist *sgl,
u32 sgl_count, struct scatterlist *sgl_bidi, u32 sgl_bidi_count)
{
@@ -1512,6 +1559,13 @@
* For SAM Task Attribute emulation for failed struct se_cmd
*/
transport_complete_task_attr(cmd);
+ /*
+ * Handle special case for COMPARE_AND_WRITE failure, where the
+ * callback is expected to drop the per device ->caw_mutex.
+ */
+ if ((cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE) &&
+ cmd->transport_complete_callback)
+ cmd->transport_complete_callback(cmd);
switch (sense_reason) {
case TCM_NON_EXISTENT_LUN:
@@ -1579,7 +1633,7 @@
}
EXPORT_SYMBOL(transport_generic_request_failure);
-static void __target_execute_cmd(struct se_cmd *cmd)
+void __target_execute_cmd(struct se_cmd *cmd)
{
sense_reason_t ret;
@@ -1784,7 +1838,7 @@
ret = cmd->se_tfo->queue_data_in(cmd);
break;
case DMA_TO_DEVICE:
- if (cmd->t_bidi_data_sg) {
+ if (cmd->se_cmd_flags & SCF_BIDI) {
ret = cmd->se_tfo->queue_data_in(cmd);
if (ret < 0)
break;
@@ -1856,10 +1910,25 @@
}
/*
* Check for a callback, used by amongst other things
- * XDWRITE_READ_10 emulation.
+ * XDWRITE_READ_10 and COMPARE_AND_WRITE emulation.
*/
- if (cmd->transport_complete_callback)
- cmd->transport_complete_callback(cmd);
+ if (cmd->transport_complete_callback) {
+ sense_reason_t rc;
+
+ rc = cmd->transport_complete_callback(cmd);
+ if (!rc && !(cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE_POST)) {
+ return;
+ } else if (rc) {
+ ret = transport_send_check_condition_and_sense(cmd,
+ rc, 0);
+ if (ret == -EAGAIN || ret == -ENOMEM)
+ goto queue_full;
+
+ transport_lun_remove_cmd(cmd);
+ transport_cmd_check_stop_to_fabric(cmd);
+ return;
+ }
+ }
switch (cmd->data_direction) {
case DMA_FROM_DEVICE:
@@ -1885,7 +1954,7 @@
/*
* Check if we need to send READ payload for BIDI-COMMAND
*/
- if (cmd->t_bidi_data_sg) {
+ if (cmd->se_cmd_flags & SCF_BIDI) {
spin_lock(&cmd->se_lun->lun_sep_lock);
if (cmd->se_lun->lun_sep) {
cmd->se_lun->lun_sep->sep_stats.tx_data_octets +=
@@ -1930,10 +1999,29 @@
kfree(sgl);
}
+static inline void transport_reset_sgl_orig(struct se_cmd *cmd)
+{
+ /*
+ * Check for saved t_data_sg that may be used for COMPARE_AND_WRITE
+ * emulation, and free + reset pointers if necessary..
+ */
+ if (!cmd->t_data_sg_orig)
+ return;
+
+ kfree(cmd->t_data_sg);
+ cmd->t_data_sg = cmd->t_data_sg_orig;
+ cmd->t_data_sg_orig = NULL;
+ cmd->t_data_nents = cmd->t_data_nents_orig;
+ cmd->t_data_nents_orig = 0;
+}
+
static inline void transport_free_pages(struct se_cmd *cmd)
{
- if (cmd->se_cmd_flags & SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC)
+ if (cmd->se_cmd_flags & SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC) {
+ transport_reset_sgl_orig(cmd);
return;
+ }
+ transport_reset_sgl_orig(cmd);
transport_free_sgl(cmd->t_data_sg, cmd->t_data_nents);
cmd->t_data_sg = NULL;
@@ -2029,24 +2117,22 @@
}
EXPORT_SYMBOL(transport_kunmap_data_sg);
-static int
-transport_generic_get_mem(struct se_cmd *cmd)
+int
+target_alloc_sgl(struct scatterlist **sgl, unsigned int *nents, u32 length,
+ bool zero_page)
{
- u32 length = cmd->data_length;
- unsigned int nents;
+ struct scatterlist *sg;
struct page *page;
- gfp_t zero_flag;
+ gfp_t zero_flag = (zero_page) ? __GFP_ZERO : 0;
+ unsigned int nent;
int i = 0;
- nents = DIV_ROUND_UP(length, PAGE_SIZE);
- cmd->t_data_sg = kmalloc(sizeof(struct scatterlist) * nents, GFP_KERNEL);
- if (!cmd->t_data_sg)
+ nent = DIV_ROUND_UP(length, PAGE_SIZE);
+ sg = kmalloc(sizeof(struct scatterlist) * nent, GFP_KERNEL);
+ if (!sg)
return -ENOMEM;
- cmd->t_data_nents = nents;
- sg_init_table(cmd->t_data_sg, nents);
-
- zero_flag = cmd->se_cmd_flags & SCF_SCSI_DATA_CDB ? 0 : __GFP_ZERO;
+ sg_init_table(sg, nent);
while (length) {
u32 page_len = min_t(u32, length, PAGE_SIZE);
@@ -2054,19 +2140,20 @@
if (!page)
goto out;
- sg_set_page(&cmd->t_data_sg[i], page, page_len, 0);
+ sg_set_page(&sg[i], page, page_len, 0);
length -= page_len;
i++;
}
+ *sgl = sg;
+ *nents = nent;
return 0;
out:
while (i > 0) {
i--;
- __free_page(sg_page(&cmd->t_data_sg[i]));
+ __free_page(sg_page(&sg[i]));
}
- kfree(cmd->t_data_sg);
- cmd->t_data_sg = NULL;
+ kfree(sg);
return -ENOMEM;
}
@@ -2087,7 +2174,27 @@
*/
if (!(cmd->se_cmd_flags & SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC) &&
cmd->data_length) {
- ret = transport_generic_get_mem(cmd);
+ bool zero_flag = !(cmd->se_cmd_flags & SCF_SCSI_DATA_CDB);
+
+ if ((cmd->se_cmd_flags & SCF_BIDI) ||
+ (cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE)) {
+ u32 bidi_length;
+
+ if (cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE)
+ bidi_length = cmd->t_task_nolb *
+ cmd->se_dev->dev_attrib.block_size;
+ else
+ bidi_length = cmd->data_length;
+
+ ret = target_alloc_sgl(&cmd->t_bidi_data_sg,
+ &cmd->t_bidi_data_nents,
+ bidi_length, zero_flag);
+ if (ret < 0)
+ return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ }
+
+ ret = target_alloc_sgl(&cmd->t_data_sg, &cmd->t_data_nents,
+ cmd->data_length, zero_flag);
if (ret < 0)
return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
}
@@ -2740,6 +2847,15 @@
buffer[SPC_ASC_KEY_OFFSET] = asc;
buffer[SPC_ASCQ_KEY_OFFSET] = ascq;
break;
+ case TCM_MISCOMPARE_VERIFY:
+ /* CURRENT ERROR */
+ buffer[0] = 0x70;
+ buffer[SPC_ADD_SENSE_LEN_OFFSET] = 10;
+ buffer[SPC_SENSE_KEY_OFFSET] = MISCOMPARE;
+ /* MISCOMPARE DURING VERIFY OPERATION */
+ buffer[SPC_ASC_KEY_OFFSET] = 0x1d;
+ buffer[SPC_ASCQ_KEY_OFFSET] = 0x00;
+ break;
case TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE:
default:
/* CURRENT ERROR */
diff --git a/drivers/target/target_core_ua.c b/drivers/target/target_core_ua.c
index bf0e390..b04467e 100644
--- a/drivers/target/target_core_ua.c
+++ b/drivers/target/target_core_ua.c
@@ -3,7 +3,7 @@
*
* This file contains logic for SPC-3 Unit Attention emulation
*
- * (c) Copyright 2009-2012 RisingTide Systems LLC.
+ * (c) Copyright 2009-2013 Datera, Inc.
*
* Nicholas A. Bellinger <nab@kernel.org>
*
diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c
new file mode 100644
index 0000000..4d22e7d
--- /dev/null
+++ b/drivers/target/target_core_xcopy.c
@@ -0,0 +1,1081 @@
+/*******************************************************************************
+ * Filename: target_core_xcopy.c
+ *
+ * This file contains support for SPC-4 Extended-Copy offload with generic
+ * TCM backends.
+ *
+ * Copyright (c) 2011-2013 Datera, Inc. All rights reserved.
+ *
+ * Author:
+ * Nicholas A. Bellinger <nab@daterainc.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ ******************************************************************************/
+
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/list.h>
+#include <linux/configfs.h>
+#include <scsi/scsi.h>
+#include <scsi/scsi_cmnd.h>
+#include <asm/unaligned.h>
+
+#include <target/target_core_base.h>
+#include <target/target_core_backend.h>
+#include <target/target_core_fabric.h>
+#include <target/target_core_configfs.h>
+
+#include "target_core_pr.h"
+#include "target_core_ua.h"
+#include "target_core_xcopy.h"
+
+static struct workqueue_struct *xcopy_wq = NULL;
+/*
+ * From target_core_spc.c
+ */
+extern void spc_parse_naa_6h_vendor_specific(struct se_device *, unsigned char *);
+/*
+ * From target_core_device.c
+ */
+extern struct mutex g_device_mutex;
+extern struct list_head g_device_list;
+/*
+ * From target_core_configfs.c
+ */
+extern struct configfs_subsystem *target_core_subsystem[];
+
+static int target_xcopy_gen_naa_ieee(struct se_device *dev, unsigned char *buf)
+{
+ int off = 0;
+
+ buf[off++] = (0x6 << 4);
+ buf[off++] = 0x01;
+ buf[off++] = 0x40;
+ buf[off] = (0x5 << 4);
+
+ spc_parse_naa_6h_vendor_specific(dev, &buf[off]);
+ return 0;
+}
+
+static int target_xcopy_locate_se_dev_e4(struct se_cmd *se_cmd, struct xcopy_op *xop,
+ bool src)
+{
+ struct se_device *se_dev;
+ struct configfs_subsystem *subsys = target_core_subsystem[0];
+ unsigned char tmp_dev_wwn[XCOPY_NAA_IEEE_REGEX_LEN], *dev_wwn;
+ int rc;
+
+ if (src == true)
+ dev_wwn = &xop->dst_tid_wwn[0];
+ else
+ dev_wwn = &xop->src_tid_wwn[0];
+
+ mutex_lock(&g_device_mutex);
+ list_for_each_entry(se_dev, &g_device_list, g_dev_node) {
+
+ memset(&tmp_dev_wwn[0], 0, XCOPY_NAA_IEEE_REGEX_LEN);
+ target_xcopy_gen_naa_ieee(se_dev, &tmp_dev_wwn[0]);
+
+ rc = memcmp(&tmp_dev_wwn[0], dev_wwn, XCOPY_NAA_IEEE_REGEX_LEN);
+ if (rc != 0)
+ continue;
+
+ if (src == true) {
+ xop->dst_dev = se_dev;
+ pr_debug("XCOPY 0xe4: Setting xop->dst_dev: %p from located"
+ " se_dev\n", xop->dst_dev);
+ } else {
+ xop->src_dev = se_dev;
+ pr_debug("XCOPY 0xe4: Setting xop->src_dev: %p from located"
+ " se_dev\n", xop->src_dev);
+ }
+
+ rc = configfs_depend_item(subsys,
+ &se_dev->dev_group.cg_item);
+ if (rc != 0) {
+ pr_err("configfs_depend_item attempt failed:"
+ " %d for se_dev: %p\n", rc, se_dev);
+ mutex_unlock(&g_device_mutex);
+ return rc;
+ }
+
+ pr_debug("Called configfs_depend_item for subsys: %p se_dev: %p"
+ " se_dev->se_dev_group: %p\n", subsys, se_dev,
+ &se_dev->dev_group);
+
+ mutex_unlock(&g_device_mutex);
+ return 0;
+ }
+ mutex_unlock(&g_device_mutex);
+
+ pr_err("Unable to locate 0xe4 descriptor for EXTENDED_COPY\n");
+ return -EINVAL;
+}
+
+static int target_xcopy_parse_tiddesc_e4(struct se_cmd *se_cmd, struct xcopy_op *xop,
+ unsigned char *p, bool src)
+{
+ unsigned char *desc = p;
+ unsigned short ript;
+ u8 desig_len;
+ /*
+ * Extract RELATIVE INITIATOR PORT IDENTIFIER
+ */
+ ript = get_unaligned_be16(&desc[2]);
+ pr_debug("XCOPY 0xe4: RELATIVE INITIATOR PORT IDENTIFIER: %hu\n", ript);
+ /*
+ * Check for supported code set, association, and designator type
+ */
+ if ((desc[4] & 0x0f) != 0x1) {
+ pr_err("XCOPY 0xe4: code set of non binary type not supported\n");
+ return -EINVAL;
+ }
+ if ((desc[5] & 0x30) != 0x00) {
+ pr_err("XCOPY 0xe4: association other than LUN not supported\n");
+ return -EINVAL;
+ }
+ if ((desc[5] & 0x0f) != 0x3) {
+ pr_err("XCOPY 0xe4: designator type unsupported: 0x%02x\n",
+ (desc[5] & 0x0f));
+ return -EINVAL;
+ }
+ /*
+ * Check for matching 16 byte length for NAA IEEE Registered Extended
+ * Assigned designator
+ */
+ desig_len = desc[7];
+ if (desig_len != 16) {
+ pr_err("XCOPY 0xe4: invalid desig_len: %d\n", (int)desig_len);
+ return -EINVAL;
+ }
+ pr_debug("XCOPY 0xe4: desig_len: %d\n", (int)desig_len);
+ /*
+ * Check for NAA IEEE Registered Extended Assigned header..
+ */
+ if ((desc[8] & 0xf0) != 0x60) {
+ pr_err("XCOPY 0xe4: Unsupported DESIGNATOR TYPE: 0x%02x\n",
+ (desc[8] & 0xf0));
+ return -EINVAL;
+ }
+
+ if (src == true) {
+ memcpy(&xop->src_tid_wwn[0], &desc[8], XCOPY_NAA_IEEE_REGEX_LEN);
+ /*
+ * Determine if the source designator matches the local device
+ */
+ if (!memcmp(&xop->local_dev_wwn[0], &xop->src_tid_wwn[0],
+ XCOPY_NAA_IEEE_REGEX_LEN)) {
+ xop->op_origin = XCOL_SOURCE_RECV_OP;
+ xop->src_dev = se_cmd->se_dev;
+ pr_debug("XCOPY 0xe4: Set xop->src_dev %p from source"
+ " received xop\n", xop->src_dev);
+ }
+ } else {
+ memcpy(&xop->dst_tid_wwn[0], &desc[8], XCOPY_NAA_IEEE_REGEX_LEN);
+ /*
+ * Determine if the destination designator matches the local device
+ */
+ if (!memcmp(&xop->local_dev_wwn[0], &xop->dst_tid_wwn[0],
+ XCOPY_NAA_IEEE_REGEX_LEN)) {
+ xop->op_origin = XCOL_DEST_RECV_OP;
+ xop->dst_dev = se_cmd->se_dev;
+ pr_debug("XCOPY 0xe4: Set xop->dst_dev: %p from destination"
+ " received xop\n", xop->dst_dev);
+ }
+ }
+
+ return 0;
+}
+
+static int target_xcopy_parse_target_descriptors(struct se_cmd *se_cmd,
+ struct xcopy_op *xop, unsigned char *p,
+ unsigned short tdll)
+{
+ struct se_device *local_dev = se_cmd->se_dev;
+ unsigned char *desc = p;
+ int offset = tdll % XCOPY_TARGET_DESC_LEN, rc, ret = 0;
+ unsigned short start = 0;
+ bool src = true;
+
+ if (offset != 0) {
+ pr_err("XCOPY target descriptor list length is not"
+ " multiple of %d\n", XCOPY_TARGET_DESC_LEN);
+ return -EINVAL;
+ }
+ if (tdll > 64) {
+ pr_err("XCOPY target descriptor supports a maximum"
+ " two src/dest descriptors, tdll: %hu too large..\n", tdll);
+ return -EINVAL;
+ }
+ /*
+ * Generate an IEEE Registered Extended designator based upon the
+ * se_device the XCOPY was received upon..
+ */
+ memset(&xop->local_dev_wwn[0], 0, XCOPY_NAA_IEEE_REGEX_LEN);
+ target_xcopy_gen_naa_ieee(local_dev, &xop->local_dev_wwn[0]);
+
+ while (start < tdll) {
+ /*
+ * Check target descriptor identification with 0xE4 type with
+ * use VPD 0x83 WWPN matching ..
+ */
+ switch (desc[0]) {
+ case 0xe4:
+ rc = target_xcopy_parse_tiddesc_e4(se_cmd, xop,
+ &desc[0], src);
+ if (rc != 0)
+ goto out;
+ /*
+ * Assume target descriptors are in source -> destination order..
+ */
+ if (src == true)
+ src = false;
+ else
+ src = true;
+ start += XCOPY_TARGET_DESC_LEN;
+ desc += XCOPY_TARGET_DESC_LEN;
+ ret++;
+ break;
+ default:
+ pr_err("XCOPY unsupported descriptor type code:"
+ " 0x%02x\n", desc[0]);
+ goto out;
+ }
+ }
+
+ if (xop->op_origin == XCOL_SOURCE_RECV_OP)
+ rc = target_xcopy_locate_se_dev_e4(se_cmd, xop, true);
+ else
+ rc = target_xcopy_locate_se_dev_e4(se_cmd, xop, false);
+
+ if (rc < 0)
+ goto out;
+
+ pr_debug("XCOPY TGT desc: Source dev: %p NAA IEEE WWN: 0x%16phN\n",
+ xop->src_dev, &xop->src_tid_wwn[0]);
+ pr_debug("XCOPY TGT desc: Dest dev: %p NAA IEEE WWN: 0x%16phN\n",
+ xop->dst_dev, &xop->dst_tid_wwn[0]);
+
+ return ret;
+
+out:
+ return -EINVAL;
+}
+
+static int target_xcopy_parse_segdesc_02(struct se_cmd *se_cmd, struct xcopy_op *xop,
+ unsigned char *p)
+{
+ unsigned char *desc = p;
+ int dc = (desc[1] & 0x02);
+ unsigned short desc_len;
+
+ desc_len = get_unaligned_be16(&desc[2]);
+ if (desc_len != 0x18) {
+ pr_err("XCOPY segment desc 0x02: Illegal desc_len:"
+ " %hu\n", desc_len);
+ return -EINVAL;
+ }
+
+ xop->stdi = get_unaligned_be16(&desc[4]);
+ xop->dtdi = get_unaligned_be16(&desc[6]);
+ pr_debug("XCOPY seg desc 0x02: desc_len: %hu stdi: %hu dtdi: %hu, DC: %d\n",
+ desc_len, xop->stdi, xop->dtdi, dc);
+
+ xop->nolb = get_unaligned_be16(&desc[10]);
+ xop->src_lba = get_unaligned_be64(&desc[12]);
+ xop->dst_lba = get_unaligned_be64(&desc[20]);
+ pr_debug("XCOPY seg desc 0x02: nolb: %hu src_lba: %llu dst_lba: %llu\n",
+ xop->nolb, (unsigned long long)xop->src_lba,
+ (unsigned long long)xop->dst_lba);
+
+ if (dc != 0) {
+ xop->dbl = (desc[29] << 16) & 0xff;
+ xop->dbl |= (desc[30] << 8) & 0xff;
+ xop->dbl |= desc[31] & 0xff;
+
+ pr_debug("XCOPY seg desc 0x02: DC=1 w/ dbl: %u\n", xop->dbl);
+ }
+ return 0;
+}
+
+static int target_xcopy_parse_segment_descriptors(struct se_cmd *se_cmd,
+ struct xcopy_op *xop, unsigned char *p,
+ unsigned int sdll)
+{
+ unsigned char *desc = p;
+ unsigned int start = 0;
+ int offset = sdll % XCOPY_SEGMENT_DESC_LEN, rc, ret = 0;
+
+ if (offset != 0) {
+ pr_err("XCOPY segment descriptor list length is not"
+ " multiple of %d\n", XCOPY_SEGMENT_DESC_LEN);
+ return -EINVAL;
+ }
+
+ while (start < sdll) {
+ /*
+ * Check segment descriptor type code for block -> block
+ */
+ switch (desc[0]) {
+ case 0x02:
+ rc = target_xcopy_parse_segdesc_02(se_cmd, xop, desc);
+ if (rc < 0)
+ goto out;
+
+ ret++;
+ start += XCOPY_SEGMENT_DESC_LEN;
+ desc += XCOPY_SEGMENT_DESC_LEN;
+ break;
+ default:
+ pr_err("XCOPY unspported segment descriptor"
+ "type: 0x%02x\n", desc[0]);
+ goto out;
+ }
+ }
+
+ return ret;
+
+out:
+ return -EINVAL;
+}
+
+/*
+ * Start xcopy_pt ops
+ */
+
+struct xcopy_pt_cmd {
+ bool remote_port;
+ struct se_cmd se_cmd;
+ struct xcopy_op *xcopy_op;
+ struct completion xpt_passthrough_sem;
+};
+
+static struct se_port xcopy_pt_port;
+static struct se_portal_group xcopy_pt_tpg;
+static struct se_session xcopy_pt_sess;
+static struct se_node_acl xcopy_pt_nacl;
+
+static char *xcopy_pt_get_fabric_name(void)
+{
+ return "xcopy-pt";
+}
+
+static u32 xcopy_pt_get_tag(struct se_cmd *se_cmd)
+{
+ return 0;
+}
+
+static int xcopy_pt_get_cmd_state(struct se_cmd *se_cmd)
+{
+ return 0;
+}
+
+static void xcopy_pt_undepend_remotedev(struct xcopy_op *xop)
+{
+ struct configfs_subsystem *subsys = target_core_subsystem[0];
+ struct se_device *remote_dev;
+
+ if (xop->op_origin == XCOL_SOURCE_RECV_OP)
+ remote_dev = xop->dst_dev;
+ else
+ remote_dev = xop->src_dev;
+
+ pr_debug("Calling configfs_undepend_item for subsys: %p"
+ " remote_dev: %p remote_dev->dev_group: %p\n",
+ subsys, remote_dev, &remote_dev->dev_group.cg_item);
+
+ configfs_undepend_item(subsys, &remote_dev->dev_group.cg_item);
+}
+
+static void xcopy_pt_release_cmd(struct se_cmd *se_cmd)
+{
+ struct xcopy_pt_cmd *xpt_cmd = container_of(se_cmd,
+ struct xcopy_pt_cmd, se_cmd);
+
+ if (xpt_cmd->remote_port)
+ kfree(se_cmd->se_lun);
+
+ kfree(xpt_cmd);
+}
+
+static int xcopy_pt_check_stop_free(struct se_cmd *se_cmd)
+{
+ struct xcopy_pt_cmd *xpt_cmd = container_of(se_cmd,
+ struct xcopy_pt_cmd, se_cmd);
+
+ complete(&xpt_cmd->xpt_passthrough_sem);
+ return 0;
+}
+
+static int xcopy_pt_write_pending(struct se_cmd *se_cmd)
+{
+ return 0;
+}
+
+static int xcopy_pt_write_pending_status(struct se_cmd *se_cmd)
+{
+ return 0;
+}
+
+static int xcopy_pt_queue_data_in(struct se_cmd *se_cmd)
+{
+ return 0;
+}
+
+static int xcopy_pt_queue_status(struct se_cmd *se_cmd)
+{
+ return 0;
+}
+
+static struct target_core_fabric_ops xcopy_pt_tfo = {
+ .get_fabric_name = xcopy_pt_get_fabric_name,
+ .get_task_tag = xcopy_pt_get_tag,
+ .get_cmd_state = xcopy_pt_get_cmd_state,
+ .release_cmd = xcopy_pt_release_cmd,
+ .check_stop_free = xcopy_pt_check_stop_free,
+ .write_pending = xcopy_pt_write_pending,
+ .write_pending_status = xcopy_pt_write_pending_status,
+ .queue_data_in = xcopy_pt_queue_data_in,
+ .queue_status = xcopy_pt_queue_status,
+};
+
+/*
+ * End xcopy_pt_ops
+ */
+
+int target_xcopy_setup_pt(void)
+{
+ xcopy_wq = alloc_workqueue("xcopy_wq", WQ_MEM_RECLAIM, 0);
+ if (!xcopy_wq) {
+ pr_err("Unable to allocate xcopy_wq\n");
+ return -ENOMEM;
+ }
+
+ memset(&xcopy_pt_port, 0, sizeof(struct se_port));
+ INIT_LIST_HEAD(&xcopy_pt_port.sep_alua_list);
+ INIT_LIST_HEAD(&xcopy_pt_port.sep_list);
+ mutex_init(&xcopy_pt_port.sep_tg_pt_md_mutex);
+
+ memset(&xcopy_pt_tpg, 0, sizeof(struct se_portal_group));
+ INIT_LIST_HEAD(&xcopy_pt_tpg.se_tpg_node);
+ INIT_LIST_HEAD(&xcopy_pt_tpg.acl_node_list);
+ INIT_LIST_HEAD(&xcopy_pt_tpg.tpg_sess_list);
+
+ xcopy_pt_port.sep_tpg = &xcopy_pt_tpg;
+ xcopy_pt_tpg.se_tpg_tfo = &xcopy_pt_tfo;
+
+ memset(&xcopy_pt_nacl, 0, sizeof(struct se_node_acl));
+ INIT_LIST_HEAD(&xcopy_pt_nacl.acl_list);
+ INIT_LIST_HEAD(&xcopy_pt_nacl.acl_sess_list);
+ memset(&xcopy_pt_sess, 0, sizeof(struct se_session));
+ INIT_LIST_HEAD(&xcopy_pt_sess.sess_list);
+ INIT_LIST_HEAD(&xcopy_pt_sess.sess_acl_list);
+
+ xcopy_pt_nacl.se_tpg = &xcopy_pt_tpg;
+ xcopy_pt_nacl.nacl_sess = &xcopy_pt_sess;
+
+ xcopy_pt_sess.se_tpg = &xcopy_pt_tpg;
+ xcopy_pt_sess.se_node_acl = &xcopy_pt_nacl;
+
+ return 0;
+}
+
+void target_xcopy_release_pt(void)
+{
+ if (xcopy_wq)
+ destroy_workqueue(xcopy_wq);
+}
+
+static void target_xcopy_setup_pt_port(
+ struct xcopy_pt_cmd *xpt_cmd,
+ struct xcopy_op *xop,
+ bool remote_port)
+{
+ struct se_cmd *ec_cmd = xop->xop_se_cmd;
+ struct se_cmd *pt_cmd = &xpt_cmd->se_cmd;
+
+ if (xop->op_origin == XCOL_SOURCE_RECV_OP) {
+ /*
+ * Honor destination port reservations for X-COPY PUSH emulation
+ * when CDB is received on local source port, and READs blocks to
+ * WRITE on remote destination port.
+ */
+ if (remote_port) {
+ xpt_cmd->remote_port = remote_port;
+ pt_cmd->se_lun->lun_sep = &xcopy_pt_port;
+ pr_debug("Setup emulated remote DEST xcopy_pt_port: %p to"
+ " cmd->se_lun->lun_sep for X-COPY data PUSH\n",
+ pt_cmd->se_lun->lun_sep);
+ } else {
+ pt_cmd->se_lun = ec_cmd->se_lun;
+ pt_cmd->se_dev = ec_cmd->se_dev;
+
+ pr_debug("Honoring local SRC port from ec_cmd->se_dev:"
+ " %p\n", pt_cmd->se_dev);
+ pt_cmd->se_lun = ec_cmd->se_lun;
+ pr_debug("Honoring local SRC port from ec_cmd->se_lun: %p\n",
+ pt_cmd->se_lun);
+ }
+ } else {
+ /*
+ * Honor source port reservation for X-COPY PULL emulation
+ * when CDB is received on local desintation port, and READs
+ * blocks from the remote source port to WRITE on local
+ * destination port.
+ */
+ if (remote_port) {
+ xpt_cmd->remote_port = remote_port;
+ pt_cmd->se_lun->lun_sep = &xcopy_pt_port;
+ pr_debug("Setup emulated remote SRC xcopy_pt_port: %p to"
+ " cmd->se_lun->lun_sep for X-COPY data PULL\n",
+ pt_cmd->se_lun->lun_sep);
+ } else {
+ pt_cmd->se_lun = ec_cmd->se_lun;
+ pt_cmd->se_dev = ec_cmd->se_dev;
+
+ pr_debug("Honoring local DST port from ec_cmd->se_dev:"
+ " %p\n", pt_cmd->se_dev);
+ pt_cmd->se_lun = ec_cmd->se_lun;
+ pr_debug("Honoring local DST port from ec_cmd->se_lun: %p\n",
+ pt_cmd->se_lun);
+ }
+ }
+}
+
+static int target_xcopy_init_pt_lun(
+ struct xcopy_pt_cmd *xpt_cmd,
+ struct xcopy_op *xop,
+ struct se_device *se_dev,
+ struct se_cmd *pt_cmd,
+ bool remote_port)
+{
+ /*
+ * Don't allocate + init an pt_cmd->se_lun if honoring local port for
+ * reservations. The pt_cmd->se_lun pointer will be setup from within
+ * target_xcopy_setup_pt_port()
+ */
+ if (remote_port == false) {
+ pt_cmd->se_cmd_flags |= SCF_SE_LUN_CMD | SCF_CMD_XCOPY_PASSTHROUGH;
+ return 0;
+ }
+
+ pt_cmd->se_lun = kzalloc(sizeof(struct se_lun), GFP_KERNEL);
+ if (!pt_cmd->se_lun) {
+ pr_err("Unable to allocate pt_cmd->se_lun\n");
+ return -ENOMEM;
+ }
+ init_completion(&pt_cmd->se_lun->lun_shutdown_comp);
+ INIT_LIST_HEAD(&pt_cmd->se_lun->lun_cmd_list);
+ INIT_LIST_HEAD(&pt_cmd->se_lun->lun_acl_list);
+ spin_lock_init(&pt_cmd->se_lun->lun_acl_lock);
+ spin_lock_init(&pt_cmd->se_lun->lun_cmd_lock);
+ spin_lock_init(&pt_cmd->se_lun->lun_sep_lock);
+
+ pt_cmd->se_dev = se_dev;
+
+ pr_debug("Setup emulated se_dev: %p from se_dev\n", pt_cmd->se_dev);
+ pt_cmd->se_lun->lun_se_dev = se_dev;
+ pt_cmd->se_cmd_flags |= SCF_SE_LUN_CMD | SCF_CMD_XCOPY_PASSTHROUGH;
+
+ pr_debug("Setup emulated se_dev: %p to pt_cmd->se_lun->lun_se_dev\n",
+ pt_cmd->se_lun->lun_se_dev);
+
+ return 0;
+}
+
+static int target_xcopy_setup_pt_cmd(
+ struct xcopy_pt_cmd *xpt_cmd,
+ struct xcopy_op *xop,
+ struct se_device *se_dev,
+ unsigned char *cdb,
+ bool remote_port,
+ bool alloc_mem)
+{
+ struct se_cmd *cmd = &xpt_cmd->se_cmd;
+ sense_reason_t sense_rc;
+ int ret = 0, rc;
+ /*
+ * Setup LUN+port to honor reservations based upon xop->op_origin for
+ * X-COPY PUSH or X-COPY PULL based upon where the CDB was received.
+ */
+ rc = target_xcopy_init_pt_lun(xpt_cmd, xop, se_dev, cmd, remote_port);
+ if (rc < 0) {
+ ret = rc;
+ goto out;
+ }
+ xpt_cmd->xcopy_op = xop;
+ target_xcopy_setup_pt_port(xpt_cmd, xop, remote_port);
+
+ sense_rc = target_setup_cmd_from_cdb(cmd, cdb);
+ if (sense_rc) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (alloc_mem) {
+ rc = target_alloc_sgl(&cmd->t_data_sg, &cmd->t_data_nents,
+ cmd->data_length, false);
+ if (rc < 0) {
+ ret = rc;
+ goto out;
+ }
+ /*
+ * Set this bit so that transport_free_pages() allows the
+ * caller to release SGLs + physical memory allocated by
+ * transport_generic_get_mem()..
+ */
+ cmd->se_cmd_flags |= SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC;
+ } else {
+ /*
+ * Here the previously allocated SGLs for the internal READ
+ * are mapped zero-copy to the internal WRITE.
+ */
+ sense_rc = transport_generic_map_mem_to_cmd(cmd,
+ xop->xop_data_sg, xop->xop_data_nents,
+ NULL, 0);
+ if (sense_rc) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ pr_debug("Setup PASSTHROUGH_NOALLOC t_data_sg: %p t_data_nents:"
+ " %u\n", cmd->t_data_sg, cmd->t_data_nents);
+ }
+
+ return 0;
+
+out:
+ if (remote_port == true)
+ kfree(cmd->se_lun);
+ return ret;
+}
+
+static int target_xcopy_issue_pt_cmd(struct xcopy_pt_cmd *xpt_cmd)
+{
+ struct se_cmd *se_cmd = &xpt_cmd->se_cmd;
+ sense_reason_t sense_rc;
+
+ sense_rc = transport_generic_new_cmd(se_cmd);
+ if (sense_rc)
+ return -EINVAL;
+
+ if (se_cmd->data_direction == DMA_TO_DEVICE)
+ target_execute_cmd(se_cmd);
+
+ wait_for_completion_interruptible(&xpt_cmd->xpt_passthrough_sem);
+
+ pr_debug("target_xcopy_issue_pt_cmd(): SCSI status: 0x%02x\n",
+ se_cmd->scsi_status);
+ return 0;
+}
+
+static int target_xcopy_read_source(
+ struct se_cmd *ec_cmd,
+ struct xcopy_op *xop,
+ struct se_device *src_dev,
+ sector_t src_lba,
+ u32 src_sectors)
+{
+ struct xcopy_pt_cmd *xpt_cmd;
+ struct se_cmd *se_cmd;
+ u32 length = (src_sectors * src_dev->dev_attrib.block_size);
+ int rc;
+ unsigned char cdb[16];
+ bool remote_port = (xop->op_origin == XCOL_DEST_RECV_OP);
+
+ xpt_cmd = kzalloc(sizeof(struct xcopy_pt_cmd), GFP_KERNEL);
+ if (!xpt_cmd) {
+ pr_err("Unable to allocate xcopy_pt_cmd\n");
+ return -ENOMEM;
+ }
+ init_completion(&xpt_cmd->xpt_passthrough_sem);
+ se_cmd = &xpt_cmd->se_cmd;
+
+ memset(&cdb[0], 0, 16);
+ cdb[0] = READ_16;
+ put_unaligned_be64(src_lba, &cdb[2]);
+ put_unaligned_be32(src_sectors, &cdb[10]);
+ pr_debug("XCOPY: Built READ_16: LBA: %llu Sectors: %u Length: %u\n",
+ (unsigned long long)src_lba, src_sectors, length);
+
+ transport_init_se_cmd(se_cmd, &xcopy_pt_tfo, NULL, length,
+ DMA_FROM_DEVICE, 0, NULL);
+ xop->src_pt_cmd = xpt_cmd;
+
+ rc = target_xcopy_setup_pt_cmd(xpt_cmd, xop, src_dev, &cdb[0],
+ remote_port, true);
+ if (rc < 0) {
+ transport_generic_free_cmd(se_cmd, 0);
+ return rc;
+ }
+
+ xop->xop_data_sg = se_cmd->t_data_sg;
+ xop->xop_data_nents = se_cmd->t_data_nents;
+ pr_debug("XCOPY-READ: Saved xop->xop_data_sg: %p, num: %u for READ"
+ " memory\n", xop->xop_data_sg, xop->xop_data_nents);
+
+ rc = target_xcopy_issue_pt_cmd(xpt_cmd);
+ if (rc < 0) {
+ transport_generic_free_cmd(se_cmd, 0);
+ return rc;
+ }
+ /*
+ * Clear off the allocated t_data_sg, that has been saved for
+ * zero-copy WRITE submission reuse in struct xcopy_op..
+ */
+ se_cmd->t_data_sg = NULL;
+ se_cmd->t_data_nents = 0;
+
+ return 0;
+}
+
+static int target_xcopy_write_destination(
+ struct se_cmd *ec_cmd,
+ struct xcopy_op *xop,
+ struct se_device *dst_dev,
+ sector_t dst_lba,
+ u32 dst_sectors)
+{
+ struct xcopy_pt_cmd *xpt_cmd;
+ struct se_cmd *se_cmd;
+ u32 length = (dst_sectors * dst_dev->dev_attrib.block_size);
+ int rc;
+ unsigned char cdb[16];
+ bool remote_port = (xop->op_origin == XCOL_SOURCE_RECV_OP);
+
+ xpt_cmd = kzalloc(sizeof(struct xcopy_pt_cmd), GFP_KERNEL);
+ if (!xpt_cmd) {
+ pr_err("Unable to allocate xcopy_pt_cmd\n");
+ return -ENOMEM;
+ }
+ init_completion(&xpt_cmd->xpt_passthrough_sem);
+ se_cmd = &xpt_cmd->se_cmd;
+
+ memset(&cdb[0], 0, 16);
+ cdb[0] = WRITE_16;
+ put_unaligned_be64(dst_lba, &cdb[2]);
+ put_unaligned_be32(dst_sectors, &cdb[10]);
+ pr_debug("XCOPY: Built WRITE_16: LBA: %llu Sectors: %u Length: %u\n",
+ (unsigned long long)dst_lba, dst_sectors, length);
+
+ transport_init_se_cmd(se_cmd, &xcopy_pt_tfo, NULL, length,
+ DMA_TO_DEVICE, 0, NULL);
+ xop->dst_pt_cmd = xpt_cmd;
+
+ rc = target_xcopy_setup_pt_cmd(xpt_cmd, xop, dst_dev, &cdb[0],
+ remote_port, false);
+ if (rc < 0) {
+ struct se_cmd *src_cmd = &xop->src_pt_cmd->se_cmd;
+ /*
+ * If the failure happened before the t_mem_list hand-off in
+ * target_xcopy_setup_pt_cmd(), Reset memory + clear flag so that
+ * core releases this memory on error during X-COPY WRITE I/O.
+ */
+ src_cmd->se_cmd_flags &= ~SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC;
+ src_cmd->t_data_sg = xop->xop_data_sg;
+ src_cmd->t_data_nents = xop->xop_data_nents;
+
+ transport_generic_free_cmd(se_cmd, 0);
+ return rc;
+ }
+
+ rc = target_xcopy_issue_pt_cmd(xpt_cmd);
+ if (rc < 0) {
+ se_cmd->se_cmd_flags &= ~SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC;
+ transport_generic_free_cmd(se_cmd, 0);
+ return rc;
+ }
+
+ return 0;
+}
+
+static void target_xcopy_do_work(struct work_struct *work)
+{
+ struct xcopy_op *xop = container_of(work, struct xcopy_op, xop_work);
+ struct se_device *src_dev = xop->src_dev, *dst_dev = xop->dst_dev;
+ struct se_cmd *ec_cmd = xop->xop_se_cmd;
+ sector_t src_lba = xop->src_lba, dst_lba = xop->dst_lba, end_lba;
+ unsigned int max_sectors;
+ int rc;
+ unsigned short nolb = xop->nolb, cur_nolb, max_nolb, copied_nolb = 0;
+
+ end_lba = src_lba + nolb;
+ /*
+ * Break up XCOPY I/O into hw_max_sectors sized I/O based on the
+ * smallest max_sectors between src_dev + dev_dev, or
+ */
+ max_sectors = min(src_dev->dev_attrib.hw_max_sectors,
+ dst_dev->dev_attrib.hw_max_sectors);
+ max_sectors = min_t(u32, max_sectors, XCOPY_MAX_SECTORS);
+
+ max_nolb = min_t(u16, max_sectors, ((u16)(~0U)));
+
+ pr_debug("target_xcopy_do_work: nolb: %hu, max_nolb: %hu end_lba: %llu\n",
+ nolb, max_nolb, (unsigned long long)end_lba);
+ pr_debug("target_xcopy_do_work: Starting src_lba: %llu, dst_lba: %llu\n",
+ (unsigned long long)src_lba, (unsigned long long)dst_lba);
+
+ while (src_lba < end_lba) {
+ cur_nolb = min(nolb, max_nolb);
+
+ pr_debug("target_xcopy_do_work: Calling read src_dev: %p src_lba: %llu,"
+ " cur_nolb: %hu\n", src_dev, (unsigned long long)src_lba, cur_nolb);
+
+ rc = target_xcopy_read_source(ec_cmd, xop, src_dev, src_lba, cur_nolb);
+ if (rc < 0)
+ goto out;
+
+ src_lba += cur_nolb;
+ pr_debug("target_xcopy_do_work: Incremented READ src_lba to %llu\n",
+ (unsigned long long)src_lba);
+
+ pr_debug("target_xcopy_do_work: Calling write dst_dev: %p dst_lba: %llu,"
+ " cur_nolb: %hu\n", dst_dev, (unsigned long long)dst_lba, cur_nolb);
+
+ rc = target_xcopy_write_destination(ec_cmd, xop, dst_dev,
+ dst_lba, cur_nolb);
+ if (rc < 0) {
+ transport_generic_free_cmd(&xop->src_pt_cmd->se_cmd, 0);
+ goto out;
+ }
+
+ dst_lba += cur_nolb;
+ pr_debug("target_xcopy_do_work: Incremented WRITE dst_lba to %llu\n",
+ (unsigned long long)dst_lba);
+
+ copied_nolb += cur_nolb;
+ nolb -= cur_nolb;
+
+ transport_generic_free_cmd(&xop->src_pt_cmd->se_cmd, 0);
+ xop->dst_pt_cmd->se_cmd.se_cmd_flags &= ~SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC;
+
+ transport_generic_free_cmd(&xop->dst_pt_cmd->se_cmd, 0);
+ }
+
+ xcopy_pt_undepend_remotedev(xop);
+ kfree(xop);
+
+ pr_debug("target_xcopy_do_work: Final src_lba: %llu, dst_lba: %llu\n",
+ (unsigned long long)src_lba, (unsigned long long)dst_lba);
+ pr_debug("target_xcopy_do_work: Blocks copied: %hu, Bytes Copied: %u\n",
+ copied_nolb, copied_nolb * dst_dev->dev_attrib.block_size);
+
+ pr_debug("target_xcopy_do_work: Setting X-COPY GOOD status -> sending response\n");
+ target_complete_cmd(ec_cmd, SAM_STAT_GOOD);
+ return;
+
+out:
+ xcopy_pt_undepend_remotedev(xop);
+ kfree(xop);
+
+ pr_warn("target_xcopy_do_work: Setting X-COPY CHECK_CONDITION -> sending response\n");
+ ec_cmd->scsi_status = SAM_STAT_CHECK_CONDITION;
+ target_complete_cmd(ec_cmd, SAM_STAT_CHECK_CONDITION);
+}
+
+sense_reason_t target_do_xcopy(struct se_cmd *se_cmd)
+{
+ struct xcopy_op *xop = NULL;
+ unsigned char *p = NULL, *seg_desc;
+ unsigned int list_id, list_id_usage, sdll, inline_dl, sa;
+ int rc;
+ unsigned short tdll;
+
+ sa = se_cmd->t_task_cdb[1] & 0x1f;
+ if (sa != 0x00) {
+ pr_err("EXTENDED_COPY(LID4) not supported\n");
+ return TCM_UNSUPPORTED_SCSI_OPCODE;
+ }
+
+ p = transport_kmap_data_sg(se_cmd);
+ if (!p) {
+ pr_err("transport_kmap_data_sg() failed in target_do_xcopy\n");
+ return TCM_OUT_OF_RESOURCES;
+ }
+
+ list_id = p[0];
+ if (list_id != 0x00) {
+ pr_err("XCOPY with non zero list_id: 0x%02x\n", list_id);
+ goto out;
+ }
+ list_id_usage = (p[1] & 0x18);
+ /*
+ * Determine TARGET DESCRIPTOR LIST LENGTH + SEGMENT DESCRIPTOR LIST LENGTH
+ */
+ tdll = get_unaligned_be16(&p[2]);
+ sdll = get_unaligned_be32(&p[8]);
+
+ inline_dl = get_unaligned_be32(&p[12]);
+ if (inline_dl != 0) {
+ pr_err("XCOPY with non zero inline data length\n");
+ goto out;
+ }
+
+ xop = kzalloc(sizeof(struct xcopy_op), GFP_KERNEL);
+ if (!xop) {
+ pr_err("Unable to allocate xcopy_op\n");
+ goto out;
+ }
+ xop->xop_se_cmd = se_cmd;
+
+ pr_debug("Processing XCOPY with list_id: 0x%02x list_id_usage: 0x%02x"
+ " tdll: %hu sdll: %u inline_dl: %u\n", list_id, list_id_usage,
+ tdll, sdll, inline_dl);
+
+ rc = target_xcopy_parse_target_descriptors(se_cmd, xop, &p[16], tdll);
+ if (rc <= 0)
+ goto out;
+
+ pr_debug("XCOPY: Processed %d target descriptors, length: %u\n", rc,
+ rc * XCOPY_TARGET_DESC_LEN);
+ seg_desc = &p[16];
+ seg_desc += (rc * XCOPY_TARGET_DESC_LEN);
+
+ rc = target_xcopy_parse_segment_descriptors(se_cmd, xop, seg_desc, sdll);
+ if (rc <= 0) {
+ xcopy_pt_undepend_remotedev(xop);
+ goto out;
+ }
+ transport_kunmap_data_sg(se_cmd);
+
+ pr_debug("XCOPY: Processed %d segment descriptors, length: %u\n", rc,
+ rc * XCOPY_SEGMENT_DESC_LEN);
+ INIT_WORK(&xop->xop_work, target_xcopy_do_work);
+ queue_work(xcopy_wq, &xop->xop_work);
+ return TCM_NO_SENSE;
+
+out:
+ if (p)
+ transport_kunmap_data_sg(se_cmd);
+ kfree(xop);
+ return TCM_INVALID_CDB_FIELD;
+}
+
+static sense_reason_t target_rcr_operating_parameters(struct se_cmd *se_cmd)
+{
+ unsigned char *p;
+
+ p = transport_kmap_data_sg(se_cmd);
+ if (!p) {
+ pr_err("transport_kmap_data_sg failed in"
+ " target_rcr_operating_parameters\n");
+ return TCM_OUT_OF_RESOURCES;
+ }
+
+ if (se_cmd->data_length < 54) {
+ pr_err("Receive Copy Results Op Parameters length"
+ " too small: %u\n", se_cmd->data_length);
+ transport_kunmap_data_sg(se_cmd);
+ return TCM_INVALID_CDB_FIELD;
+ }
+ /*
+ * Set SNLID=1 (Supports no List ID)
+ */
+ p[4] = 0x1;
+ /*
+ * MAXIMUM TARGET DESCRIPTOR COUNT
+ */
+ put_unaligned_be16(RCR_OP_MAX_TARGET_DESC_COUNT, &p[8]);
+ /*
+ * MAXIMUM SEGMENT DESCRIPTOR COUNT
+ */
+ put_unaligned_be16(RCR_OP_MAX_SG_DESC_COUNT, &p[10]);
+ /*
+ * MAXIMUM DESCRIPTOR LIST LENGTH
+ */
+ put_unaligned_be32(RCR_OP_MAX_DESC_LIST_LEN, &p[12]);
+ /*
+ * MAXIMUM SEGMENT LENGTH
+ */
+ put_unaligned_be32(RCR_OP_MAX_SEGMENT_LEN, &p[16]);
+ /*
+ * MAXIMUM INLINE DATA LENGTH for SA 0x04 (NOT SUPPORTED)
+ */
+ put_unaligned_be32(0x0, &p[20]);
+ /*
+ * HELD DATA LIMIT
+ */
+ put_unaligned_be32(0x0, &p[24]);
+ /*
+ * MAXIMUM STREAM DEVICE TRANSFER SIZE
+ */
+ put_unaligned_be32(0x0, &p[28]);
+ /*
+ * TOTAL CONCURRENT COPIES
+ */
+ put_unaligned_be16(RCR_OP_TOTAL_CONCURR_COPIES, &p[34]);
+ /*
+ * MAXIMUM CONCURRENT COPIES
+ */
+ p[36] = RCR_OP_MAX_CONCURR_COPIES;
+ /*
+ * DATA SEGMENT GRANULARITY (log 2)
+ */
+ p[37] = RCR_OP_DATA_SEG_GRAN_LOG2;
+ /*
+ * INLINE DATA GRANULARITY log 2)
+ */
+ p[38] = RCR_OP_INLINE_DATA_GRAN_LOG2;
+ /*
+ * HELD DATA GRANULARITY
+ */
+ p[39] = RCR_OP_HELD_DATA_GRAN_LOG2;
+ /*
+ * IMPLEMENTED DESCRIPTOR LIST LENGTH
+ */
+ p[43] = 0x2;
+ /*
+ * List of implemented descriptor type codes (ordered)
+ */
+ p[44] = 0x02; /* Copy Block to Block device */
+ p[45] = 0xe4; /* Identification descriptor target descriptor */
+
+ /*
+ * AVAILABLE DATA (n-3)
+ */
+ put_unaligned_be32(42, &p[0]);
+
+ transport_kunmap_data_sg(se_cmd);
+ target_complete_cmd(se_cmd, GOOD);
+
+ return TCM_NO_SENSE;
+}
+
+sense_reason_t target_do_receive_copy_results(struct se_cmd *se_cmd)
+{
+ unsigned char *cdb = &se_cmd->t_task_cdb[0];
+ int sa = (cdb[1] & 0x1f), list_id = cdb[2];
+ sense_reason_t rc = TCM_NO_SENSE;
+
+ pr_debug("Entering target_do_receive_copy_results: SA: 0x%02x, List ID:"
+ " 0x%02x, AL: %u\n", sa, list_id, se_cmd->data_length);
+
+ if (list_id != 0) {
+ pr_err("Receive Copy Results with non zero list identifier"
+ " not supported\n");
+ return TCM_INVALID_CDB_FIELD;
+ }
+
+ switch (sa) {
+ case RCR_SA_OPERATING_PARAMETERS:
+ rc = target_rcr_operating_parameters(se_cmd);
+ break;
+ case RCR_SA_COPY_STATUS:
+ case RCR_SA_RECEIVE_DATA:
+ case RCR_SA_FAILED_SEGMENT_DETAILS:
+ default:
+ pr_err("Unsupported SA for receive copy results: 0x%02x\n", sa);
+ return TCM_INVALID_CDB_FIELD;
+ }
+
+ return rc;
+}
diff --git a/drivers/target/target_core_xcopy.h b/drivers/target/target_core_xcopy.h
new file mode 100644
index 0000000..700a981
--- /dev/null
+++ b/drivers/target/target_core_xcopy.h
@@ -0,0 +1,62 @@
+#define XCOPY_TARGET_DESC_LEN 32
+#define XCOPY_SEGMENT_DESC_LEN 28
+#define XCOPY_NAA_IEEE_REGEX_LEN 16
+#define XCOPY_MAX_SECTORS 1024
+
+enum xcopy_origin_list {
+ XCOL_SOURCE_RECV_OP = 0x01,
+ XCOL_DEST_RECV_OP = 0x02,
+};
+
+struct xcopy_pt_cmd;
+
+struct xcopy_op {
+ int op_origin;
+
+ struct se_cmd *xop_se_cmd;
+ struct se_device *src_dev;
+ unsigned char src_tid_wwn[XCOPY_NAA_IEEE_REGEX_LEN];
+ struct se_device *dst_dev;
+ unsigned char dst_tid_wwn[XCOPY_NAA_IEEE_REGEX_LEN];
+ unsigned char local_dev_wwn[XCOPY_NAA_IEEE_REGEX_LEN];
+
+ sector_t src_lba;
+ sector_t dst_lba;
+ unsigned short stdi;
+ unsigned short dtdi;
+ unsigned short nolb;
+ unsigned int dbl;
+
+ struct xcopy_pt_cmd *src_pt_cmd;
+ struct xcopy_pt_cmd *dst_pt_cmd;
+
+ u32 xop_data_nents;
+ struct scatterlist *xop_data_sg;
+ struct work_struct xop_work;
+};
+
+/*
+ * Receive Copy Results Sevice Actions
+ */
+#define RCR_SA_COPY_STATUS 0x00
+#define RCR_SA_RECEIVE_DATA 0x01
+#define RCR_SA_OPERATING_PARAMETERS 0x03
+#define RCR_SA_FAILED_SEGMENT_DETAILS 0x04
+
+/*
+ * Receive Copy Results defs for Operating Parameters
+ */
+#define RCR_OP_MAX_TARGET_DESC_COUNT 0x2
+#define RCR_OP_MAX_SG_DESC_COUNT 0x1
+#define RCR_OP_MAX_DESC_LIST_LEN 1024
+#define RCR_OP_MAX_SEGMENT_LEN 268435456 /* 256 MB */
+#define RCR_OP_TOTAL_CONCURR_COPIES 0x1 /* Must be <= 16384 */
+#define RCR_OP_MAX_CONCURR_COPIES 0x1 /* Must be <= 255 */
+#define RCR_OP_DATA_SEG_GRAN_LOG2 9 /* 512 bytes in log 2 */
+#define RCR_OP_INLINE_DATA_GRAN_LOG2 9 /* 512 bytes in log 2 */
+#define RCR_OP_HELD_DATA_GRAN_LOG2 9 /* 512 bytes in log 2 */
+
+extern int target_xcopy_setup_pt(void);
+extern void target_xcopy_release_pt(void);
+extern sense_reason_t target_do_xcopy(struct se_cmd *);
+extern sense_reason_t target_do_receive_copy_results(struct se_cmd *);
diff --git a/drivers/target/tcm_fc/tfc_conf.c b/drivers/target/tcm_fc/tfc_conf.c
index b74feb0..4e00508 100644
--- a/drivers/target/tcm_fc/tfc_conf.c
+++ b/drivers/target/tcm_fc/tfc_conf.c
@@ -311,7 +311,11 @@
*/
if (strstr(name, "tpgt_") != name)
return NULL;
- if (strict_strtoul(name + 5, 10, &index) || index > UINT_MAX)
+
+ ret = kstrtoul(name + 5, 10, &index);
+ if (ret)
+ return NULL;
+ if (index > UINT_MAX)
return NULL;
lacl = container_of(wwn, struct ft_lport_acl, fc_lport_wwn);
diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index e988c81..dbfc390 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -17,8 +17,17 @@
config THERMAL_HWMON
bool
+ prompt "Expose thermal sensors as hwmon device"
depends on HWMON=y || HWMON=THERMAL
default y
+ help
+ In case a sensor is registered with the thermal
+ framework, this option will also register it
+ as a hwmon. The sensor will then have the common
+ hwmon sysfs interface.
+
+ Say 'Y' here if you want all thermal sensors to
+ have hwmon sysfs interface too.
choice
prompt "Default Thermal governor"
@@ -91,6 +100,17 @@
because userland can easily disable the thermal policy by simply
flooding this sysfs node with low temperature values.
+config IMX_THERMAL
+ tristate "Temperature sensor driver for Freescale i.MX SoCs"
+ depends on CPU_THERMAL
+ depends on MFD_SYSCON
+ depends on OF
+ help
+ Support for Temperature Monitor (TEMPMON) found on Freescale i.MX SoCs.
+ It supports one critical trip point and one passive trip point. The
+ cpufreq is used as the cooling device to throttle CPUs when the
+ passive trip is crossed.
+
config SPEAR_THERMAL
bool "SPEAr thermal sensor driver"
depends on PLAT_SPEAR
@@ -114,14 +134,6 @@
Support for the Kirkwood thermal sensor driver into the Linux thermal
framework. Only kirkwood 88F6282 and 88F6283 have this sensor.
-config EXYNOS_THERMAL
- tristate "Temperature sensor on Samsung EXYNOS"
- depends on (ARCH_EXYNOS4 || ARCH_EXYNOS5)
- depends on CPU_THERMAL
- help
- If you say yes here you get support for TMU (Thermal Management
- Unit) on SAMSUNG EXYNOS series of SoC.
-
config DOVE_THERMAL
tristate "Temperature sensor on Marvell Dove SoCs"
depends on ARCH_DOVE
@@ -184,4 +196,9 @@
source "drivers/thermal/ti-soc-thermal/Kconfig"
endmenu
+menu "Samsung thermal drivers"
+depends on PLAT_SAMSUNG
+source "drivers/thermal/samsung/Kconfig"
+endmenu
+
endif
diff --git a/drivers/thermal/Makefile b/drivers/thermal/Makefile
index 67184a2..584b363 100644
--- a/drivers/thermal/Makefile
+++ b/drivers/thermal/Makefile
@@ -5,6 +5,9 @@
obj-$(CONFIG_THERMAL) += thermal_sys.o
thermal_sys-y += thermal_core.o
+# interface to/from other layers providing sensors
+thermal_sys-$(CONFIG_THERMAL_HWMON) += thermal_hwmon.o
+
# governors
thermal_sys-$(CONFIG_THERMAL_GOV_FAIR_SHARE) += fair_share.o
thermal_sys-$(CONFIG_THERMAL_GOV_STEP_WISE) += step_wise.o
@@ -17,10 +20,11 @@
obj-$(CONFIG_SPEAR_THERMAL) += spear_thermal.o
obj-$(CONFIG_RCAR_THERMAL) += rcar_thermal.o
obj-$(CONFIG_KIRKWOOD_THERMAL) += kirkwood_thermal.o
-obj-$(CONFIG_EXYNOS_THERMAL) += exynos_thermal.o
+obj-y += samsung/
obj-$(CONFIG_DOVE_THERMAL) += dove_thermal.o
obj-$(CONFIG_DB8500_THERMAL) += db8500_thermal.o
obj-$(CONFIG_ARMADA_THERMAL) += armada_thermal.o
+obj-$(CONFIG_IMX_THERMAL) += imx_thermal.o
obj-$(CONFIG_DB8500_CPUFREQ_COOLING) += db8500_cpufreq_cooling.o
obj-$(CONFIG_INTEL_POWERCLAMP) += intel_powerclamp.o
obj-$(CONFIG_X86_PKG_TEMP_THERMAL) += x86_pkg_temp_thermal.o
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index 82e15db..d179028 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -322,6 +322,8 @@
if (cpumask_test_cpu(policy->cpu, ¬ify_device->allowed_cpus))
max_freq = notify_device->cpufreq_val;
+ else
+ return 0;
/* Never exceed user_policy.max */
if (max_freq > policy->user_policy.max)
@@ -496,8 +498,12 @@
*/
void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
{
- struct cpufreq_cooling_device *cpufreq_dev = cdev->devdata;
+ struct cpufreq_cooling_device *cpufreq_dev;
+ if (!cdev)
+ return;
+
+ cpufreq_dev = cdev->devdata;
mutex_lock(&cooling_cpufreq_lock);
cpufreq_dev_count--;
diff --git a/drivers/thermal/exynos_thermal.c b/drivers/thermal/exynos_thermal.c
deleted file mode 100644
index 9af4b93..0000000
--- a/drivers/thermal/exynos_thermal.c
+++ /dev/null
@@ -1,1059 +0,0 @@
-/*
- * exynos_thermal.c - Samsung EXYNOS TMU (Thermal Management Unit)
- *
- * Copyright (C) 2011 Samsung Electronics
- * Donggeun Kim <dg77.kim@samsung.com>
- * Amit Daniel Kachhap <amit.kachhap@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- *
- */
-
-#include <linux/module.h>
-#include <linux/err.h>
-#include <linux/kernel.h>
-#include <linux/slab.h>
-#include <linux/platform_device.h>
-#include <linux/interrupt.h>
-#include <linux/clk.h>
-#include <linux/workqueue.h>
-#include <linux/sysfs.h>
-#include <linux/kobject.h>
-#include <linux/io.h>
-#include <linux/mutex.h>
-#include <linux/platform_data/exynos_thermal.h>
-#include <linux/thermal.h>
-#include <linux/cpufreq.h>
-#include <linux/cpu_cooling.h>
-#include <linux/of.h>
-
-/* Exynos generic registers */
-#define EXYNOS_TMU_REG_TRIMINFO 0x0
-#define EXYNOS_TMU_REG_CONTROL 0x20
-#define EXYNOS_TMU_REG_STATUS 0x28
-#define EXYNOS_TMU_REG_CURRENT_TEMP 0x40
-#define EXYNOS_TMU_REG_INTEN 0x70
-#define EXYNOS_TMU_REG_INTSTAT 0x74
-#define EXYNOS_TMU_REG_INTCLEAR 0x78
-
-#define EXYNOS_TMU_TRIM_TEMP_MASK 0xff
-#define EXYNOS_TMU_GAIN_SHIFT 8
-#define EXYNOS_TMU_REF_VOLTAGE_SHIFT 24
-#define EXYNOS_TMU_CORE_ON 3
-#define EXYNOS_TMU_CORE_OFF 2
-#define EXYNOS_TMU_DEF_CODE_TO_TEMP_OFFSET 50
-
-/* Exynos4210 specific registers */
-#define EXYNOS4210_TMU_REG_THRESHOLD_TEMP 0x44
-#define EXYNOS4210_TMU_REG_TRIG_LEVEL0 0x50
-#define EXYNOS4210_TMU_REG_TRIG_LEVEL1 0x54
-#define EXYNOS4210_TMU_REG_TRIG_LEVEL2 0x58
-#define EXYNOS4210_TMU_REG_TRIG_LEVEL3 0x5C
-#define EXYNOS4210_TMU_REG_PAST_TEMP0 0x60
-#define EXYNOS4210_TMU_REG_PAST_TEMP1 0x64
-#define EXYNOS4210_TMU_REG_PAST_TEMP2 0x68
-#define EXYNOS4210_TMU_REG_PAST_TEMP3 0x6C
-
-#define EXYNOS4210_TMU_TRIG_LEVEL0_MASK 0x1
-#define EXYNOS4210_TMU_TRIG_LEVEL1_MASK 0x10
-#define EXYNOS4210_TMU_TRIG_LEVEL2_MASK 0x100
-#define EXYNOS4210_TMU_TRIG_LEVEL3_MASK 0x1000
-#define EXYNOS4210_TMU_INTCLEAR_VAL 0x1111
-
-/* Exynos5250 and Exynos4412 specific registers */
-#define EXYNOS_TMU_TRIMINFO_CON 0x14
-#define EXYNOS_THD_TEMP_RISE 0x50
-#define EXYNOS_THD_TEMP_FALL 0x54
-#define EXYNOS_EMUL_CON 0x80
-
-#define EXYNOS_TRIMINFO_RELOAD 0x1
-#define EXYNOS_TMU_CLEAR_RISE_INT 0x111
-#define EXYNOS_TMU_CLEAR_FALL_INT (0x111 << 12)
-#define EXYNOS_MUX_ADDR_VALUE 6
-#define EXYNOS_MUX_ADDR_SHIFT 20
-#define EXYNOS_TMU_TRIP_MODE_SHIFT 13
-
-#define EFUSE_MIN_VALUE 40
-#define EFUSE_MAX_VALUE 100
-
-/* In-kernel thermal framework related macros & definations */
-#define SENSOR_NAME_LEN 16
-#define MAX_TRIP_COUNT 8
-#define MAX_COOLING_DEVICE 4
-#define MAX_THRESHOLD_LEVS 4
-
-#define ACTIVE_INTERVAL 500
-#define IDLE_INTERVAL 10000
-#define MCELSIUS 1000
-
-#ifdef CONFIG_THERMAL_EMULATION
-#define EXYNOS_EMUL_TIME 0x57F0
-#define EXYNOS_EMUL_TIME_SHIFT 16
-#define EXYNOS_EMUL_DATA_SHIFT 8
-#define EXYNOS_EMUL_DATA_MASK 0xFF
-#define EXYNOS_EMUL_ENABLE 0x1
-#endif /* CONFIG_THERMAL_EMULATION */
-
-/* CPU Zone information */
-#define PANIC_ZONE 4
-#define WARN_ZONE 3
-#define MONITOR_ZONE 2
-#define SAFE_ZONE 1
-
-#define GET_ZONE(trip) (trip + 2)
-#define GET_TRIP(zone) (zone - 2)
-
-#define EXYNOS_ZONE_COUNT 3
-
-struct exynos_tmu_data {
- struct exynos_tmu_platform_data *pdata;
- struct resource *mem;
- void __iomem *base;
- int irq;
- enum soc_type soc;
- struct work_struct irq_work;
- struct mutex lock;
- struct clk *clk;
- u8 temp_error1, temp_error2;
-};
-
-struct thermal_trip_point_conf {
- int trip_val[MAX_TRIP_COUNT];
- int trip_count;
- u8 trigger_falling;
-};
-
-struct thermal_cooling_conf {
- struct freq_clip_table freq_data[MAX_TRIP_COUNT];
- int freq_clip_count;
-};
-
-struct thermal_sensor_conf {
- char name[SENSOR_NAME_LEN];
- int (*read_temperature)(void *data);
- int (*write_emul_temp)(void *drv_data, unsigned long temp);
- struct thermal_trip_point_conf trip_data;
- struct thermal_cooling_conf cooling_data;
- void *private_data;
-};
-
-struct exynos_thermal_zone {
- enum thermal_device_mode mode;
- struct thermal_zone_device *therm_dev;
- struct thermal_cooling_device *cool_dev[MAX_COOLING_DEVICE];
- unsigned int cool_dev_size;
- struct platform_device *exynos4_dev;
- struct thermal_sensor_conf *sensor_conf;
- bool bind;
-};
-
-static struct exynos_thermal_zone *th_zone;
-static void exynos_unregister_thermal(void);
-static int exynos_register_thermal(struct thermal_sensor_conf *sensor_conf);
-
-/* Get mode callback functions for thermal zone */
-static int exynos_get_mode(struct thermal_zone_device *thermal,
- enum thermal_device_mode *mode)
-{
- if (th_zone)
- *mode = th_zone->mode;
- return 0;
-}
-
-/* Set mode callback functions for thermal zone */
-static int exynos_set_mode(struct thermal_zone_device *thermal,
- enum thermal_device_mode mode)
-{
- if (!th_zone->therm_dev) {
- pr_notice("thermal zone not registered\n");
- return 0;
- }
-
- mutex_lock(&th_zone->therm_dev->lock);
-
- if (mode == THERMAL_DEVICE_ENABLED &&
- !th_zone->sensor_conf->trip_data.trigger_falling)
- th_zone->therm_dev->polling_delay = IDLE_INTERVAL;
- else
- th_zone->therm_dev->polling_delay = 0;
-
- mutex_unlock(&th_zone->therm_dev->lock);
-
- th_zone->mode = mode;
- thermal_zone_device_update(th_zone->therm_dev);
- pr_info("thermal polling set for duration=%d msec\n",
- th_zone->therm_dev->polling_delay);
- return 0;
-}
-
-
-/* Get trip type callback functions for thermal zone */
-static int exynos_get_trip_type(struct thermal_zone_device *thermal, int trip,
- enum thermal_trip_type *type)
-{
- switch (GET_ZONE(trip)) {
- case MONITOR_ZONE:
- case WARN_ZONE:
- *type = THERMAL_TRIP_ACTIVE;
- break;
- case PANIC_ZONE:
- *type = THERMAL_TRIP_CRITICAL;
- break;
- default:
- return -EINVAL;
- }
- return 0;
-}
-
-/* Get trip temperature callback functions for thermal zone */
-static int exynos_get_trip_temp(struct thermal_zone_device *thermal, int trip,
- unsigned long *temp)
-{
- if (trip < GET_TRIP(MONITOR_ZONE) || trip > GET_TRIP(PANIC_ZONE))
- return -EINVAL;
-
- *temp = th_zone->sensor_conf->trip_data.trip_val[trip];
- /* convert the temperature into millicelsius */
- *temp = *temp * MCELSIUS;
-
- return 0;
-}
-
-/* Get critical temperature callback functions for thermal zone */
-static int exynos_get_crit_temp(struct thermal_zone_device *thermal,
- unsigned long *temp)
-{
- int ret;
- /* Panic zone */
- ret = exynos_get_trip_temp(thermal, GET_TRIP(PANIC_ZONE), temp);
- return ret;
-}
-
-/* Bind callback functions for thermal zone */
-static int exynos_bind(struct thermal_zone_device *thermal,
- struct thermal_cooling_device *cdev)
-{
- int ret = 0, i, tab_size, level;
- struct freq_clip_table *tab_ptr, *clip_data;
- struct thermal_sensor_conf *data = th_zone->sensor_conf;
-
- tab_ptr = (struct freq_clip_table *)data->cooling_data.freq_data;
- tab_size = data->cooling_data.freq_clip_count;
-
- if (tab_ptr == NULL || tab_size == 0)
- return -EINVAL;
-
- /* find the cooling device registered*/
- for (i = 0; i < th_zone->cool_dev_size; i++)
- if (cdev == th_zone->cool_dev[i])
- break;
-
- /* No matching cooling device */
- if (i == th_zone->cool_dev_size)
- return 0;
-
- /* Bind the thermal zone to the cpufreq cooling device */
- for (i = 0; i < tab_size; i++) {
- clip_data = (struct freq_clip_table *)&(tab_ptr[i]);
- level = cpufreq_cooling_get_level(0, clip_data->freq_clip_max);
- if (level == THERMAL_CSTATE_INVALID)
- return 0;
- switch (GET_ZONE(i)) {
- case MONITOR_ZONE:
- case WARN_ZONE:
- if (thermal_zone_bind_cooling_device(thermal, i, cdev,
- level, 0)) {
- pr_err("error binding cdev inst %d\n", i);
- ret = -EINVAL;
- }
- th_zone->bind = true;
- break;
- default:
- ret = -EINVAL;
- }
- }
-
- return ret;
-}
-
-/* Unbind callback functions for thermal zone */
-static int exynos_unbind(struct thermal_zone_device *thermal,
- struct thermal_cooling_device *cdev)
-{
- int ret = 0, i, tab_size;
- struct thermal_sensor_conf *data = th_zone->sensor_conf;
-
- if (th_zone->bind == false)
- return 0;
-
- tab_size = data->cooling_data.freq_clip_count;
-
- if (tab_size == 0)
- return -EINVAL;
-
- /* find the cooling device registered*/
- for (i = 0; i < th_zone->cool_dev_size; i++)
- if (cdev == th_zone->cool_dev[i])
- break;
-
- /* No matching cooling device */
- if (i == th_zone->cool_dev_size)
- return 0;
-
- /* Bind the thermal zone to the cpufreq cooling device */
- for (i = 0; i < tab_size; i++) {
- switch (GET_ZONE(i)) {
- case MONITOR_ZONE:
- case WARN_ZONE:
- if (thermal_zone_unbind_cooling_device(thermal, i,
- cdev)) {
- pr_err("error unbinding cdev inst=%d\n", i);
- ret = -EINVAL;
- }
- th_zone->bind = false;
- break;
- default:
- ret = -EINVAL;
- }
- }
- return ret;
-}
-
-/* Get temperature callback functions for thermal zone */
-static int exynos_get_temp(struct thermal_zone_device *thermal,
- unsigned long *temp)
-{
- void *data;
-
- if (!th_zone->sensor_conf) {
- pr_info("Temperature sensor not initialised\n");
- return -EINVAL;
- }
- data = th_zone->sensor_conf->private_data;
- *temp = th_zone->sensor_conf->read_temperature(data);
- /* convert the temperature into millicelsius */
- *temp = *temp * MCELSIUS;
- return 0;
-}
-
-/* Get temperature callback functions for thermal zone */
-static int exynos_set_emul_temp(struct thermal_zone_device *thermal,
- unsigned long temp)
-{
- void *data;
- int ret = -EINVAL;
-
- if (!th_zone->sensor_conf) {
- pr_info("Temperature sensor not initialised\n");
- return -EINVAL;
- }
- data = th_zone->sensor_conf->private_data;
- if (th_zone->sensor_conf->write_emul_temp)
- ret = th_zone->sensor_conf->write_emul_temp(data, temp);
- return ret;
-}
-
-/* Get the temperature trend */
-static int exynos_get_trend(struct thermal_zone_device *thermal,
- int trip, enum thermal_trend *trend)
-{
- int ret;
- unsigned long trip_temp;
-
- ret = exynos_get_trip_temp(thermal, trip, &trip_temp);
- if (ret < 0)
- return ret;
-
- if (thermal->temperature >= trip_temp)
- *trend = THERMAL_TREND_RAISE_FULL;
- else
- *trend = THERMAL_TREND_DROP_FULL;
-
- return 0;
-}
-/* Operation callback functions for thermal zone */
-static struct thermal_zone_device_ops const exynos_dev_ops = {
- .bind = exynos_bind,
- .unbind = exynos_unbind,
- .get_temp = exynos_get_temp,
- .set_emul_temp = exynos_set_emul_temp,
- .get_trend = exynos_get_trend,
- .get_mode = exynos_get_mode,
- .set_mode = exynos_set_mode,
- .get_trip_type = exynos_get_trip_type,
- .get_trip_temp = exynos_get_trip_temp,
- .get_crit_temp = exynos_get_crit_temp,
-};
-
-/*
- * This function may be called from interrupt based temperature sensor
- * when threshold is changed.
- */
-static void exynos_report_trigger(void)
-{
- unsigned int i;
- char data[10];
- char *envp[] = { data, NULL };
-
- if (!th_zone || !th_zone->therm_dev)
- return;
- if (th_zone->bind == false) {
- for (i = 0; i < th_zone->cool_dev_size; i++) {
- if (!th_zone->cool_dev[i])
- continue;
- exynos_bind(th_zone->therm_dev,
- th_zone->cool_dev[i]);
- }
- }
-
- thermal_zone_device_update(th_zone->therm_dev);
-
- mutex_lock(&th_zone->therm_dev->lock);
- /* Find the level for which trip happened */
- for (i = 0; i < th_zone->sensor_conf->trip_data.trip_count; i++) {
- if (th_zone->therm_dev->last_temperature <
- th_zone->sensor_conf->trip_data.trip_val[i] * MCELSIUS)
- break;
- }
-
- if (th_zone->mode == THERMAL_DEVICE_ENABLED &&
- !th_zone->sensor_conf->trip_data.trigger_falling) {
- if (i > 0)
- th_zone->therm_dev->polling_delay = ACTIVE_INTERVAL;
- else
- th_zone->therm_dev->polling_delay = IDLE_INTERVAL;
- }
-
- snprintf(data, sizeof(data), "%u", i);
- kobject_uevent_env(&th_zone->therm_dev->device.kobj, KOBJ_CHANGE, envp);
- mutex_unlock(&th_zone->therm_dev->lock);
-}
-
-/* Register with the in-kernel thermal management */
-static int exynos_register_thermal(struct thermal_sensor_conf *sensor_conf)
-{
- int ret;
- struct cpumask mask_val;
-
- if (!sensor_conf || !sensor_conf->read_temperature) {
- pr_err("Temperature sensor not initialised\n");
- return -EINVAL;
- }
-
- th_zone = kzalloc(sizeof(struct exynos_thermal_zone), GFP_KERNEL);
- if (!th_zone)
- return -ENOMEM;
-
- th_zone->sensor_conf = sensor_conf;
- cpumask_set_cpu(0, &mask_val);
- th_zone->cool_dev[0] = cpufreq_cooling_register(&mask_val);
- if (IS_ERR(th_zone->cool_dev[0])) {
- pr_err("Failed to register cpufreq cooling device\n");
- ret = -EINVAL;
- goto err_unregister;
- }
- th_zone->cool_dev_size++;
-
- th_zone->therm_dev = thermal_zone_device_register(sensor_conf->name,
- EXYNOS_ZONE_COUNT, 0, NULL, &exynos_dev_ops, NULL, 0,
- sensor_conf->trip_data.trigger_falling ?
- 0 : IDLE_INTERVAL);
-
- if (IS_ERR(th_zone->therm_dev)) {
- pr_err("Failed to register thermal zone device\n");
- ret = PTR_ERR(th_zone->therm_dev);
- goto err_unregister;
- }
- th_zone->mode = THERMAL_DEVICE_ENABLED;
-
- pr_info("Exynos: Kernel Thermal management registered\n");
-
- return 0;
-
-err_unregister:
- exynos_unregister_thermal();
- return ret;
-}
-
-/* Un-Register with the in-kernel thermal management */
-static void exynos_unregister_thermal(void)
-{
- int i;
-
- if (!th_zone)
- return;
-
- if (th_zone->therm_dev)
- thermal_zone_device_unregister(th_zone->therm_dev);
-
- for (i = 0; i < th_zone->cool_dev_size; i++) {
- if (th_zone->cool_dev[i])
- cpufreq_cooling_unregister(th_zone->cool_dev[i]);
- }
-
- kfree(th_zone);
- pr_info("Exynos: Kernel Thermal management unregistered\n");
-}
-
-/*
- * TMU treats temperature as a mapped temperature code.
- * The temperature is converted differently depending on the calibration type.
- */
-static int temp_to_code(struct exynos_tmu_data *data, u8 temp)
-{
- struct exynos_tmu_platform_data *pdata = data->pdata;
- int temp_code;
-
- if (data->soc == SOC_ARCH_EXYNOS4210)
- /* temp should range between 25 and 125 */
- if (temp < 25 || temp > 125) {
- temp_code = -EINVAL;
- goto out;
- }
-
- switch (pdata->cal_type) {
- case TYPE_TWO_POINT_TRIMMING:
- temp_code = (temp - 25) *
- (data->temp_error2 - data->temp_error1) /
- (85 - 25) + data->temp_error1;
- break;
- case TYPE_ONE_POINT_TRIMMING:
- temp_code = temp + data->temp_error1 - 25;
- break;
- default:
- temp_code = temp + EXYNOS_TMU_DEF_CODE_TO_TEMP_OFFSET;
- break;
- }
-out:
- return temp_code;
-}
-
-/*
- * Calculate a temperature value from a temperature code.
- * The unit of the temperature is degree Celsius.
- */
-static int code_to_temp(struct exynos_tmu_data *data, u8 temp_code)
-{
- struct exynos_tmu_platform_data *pdata = data->pdata;
- int temp;
-
- if (data->soc == SOC_ARCH_EXYNOS4210)
- /* temp_code should range between 75 and 175 */
- if (temp_code < 75 || temp_code > 175) {
- temp = -ENODATA;
- goto out;
- }
-
- switch (pdata->cal_type) {
- case TYPE_TWO_POINT_TRIMMING:
- temp = (temp_code - data->temp_error1) * (85 - 25) /
- (data->temp_error2 - data->temp_error1) + 25;
- break;
- case TYPE_ONE_POINT_TRIMMING:
- temp = temp_code - data->temp_error1 + 25;
- break;
- default:
- temp = temp_code - EXYNOS_TMU_DEF_CODE_TO_TEMP_OFFSET;
- break;
- }
-out:
- return temp;
-}
-
-static int exynos_tmu_initialize(struct platform_device *pdev)
-{
- struct exynos_tmu_data *data = platform_get_drvdata(pdev);
- struct exynos_tmu_platform_data *pdata = data->pdata;
- unsigned int status, trim_info;
- unsigned int rising_threshold = 0, falling_threshold = 0;
- int ret = 0, threshold_code, i, trigger_levs = 0;
-
- mutex_lock(&data->lock);
- clk_enable(data->clk);
-
- status = readb(data->base + EXYNOS_TMU_REG_STATUS);
- if (!status) {
- ret = -EBUSY;
- goto out;
- }
-
- if (data->soc == SOC_ARCH_EXYNOS) {
- __raw_writel(EXYNOS_TRIMINFO_RELOAD,
- data->base + EXYNOS_TMU_TRIMINFO_CON);
- }
- /* Save trimming info in order to perform calibration */
- trim_info = readl(data->base + EXYNOS_TMU_REG_TRIMINFO);
- data->temp_error1 = trim_info & EXYNOS_TMU_TRIM_TEMP_MASK;
- data->temp_error2 = ((trim_info >> 8) & EXYNOS_TMU_TRIM_TEMP_MASK);
-
- if ((EFUSE_MIN_VALUE > data->temp_error1) ||
- (data->temp_error1 > EFUSE_MAX_VALUE) ||
- (data->temp_error2 != 0))
- data->temp_error1 = pdata->efuse_value;
-
- /* Count trigger levels to be enabled */
- for (i = 0; i < MAX_THRESHOLD_LEVS; i++)
- if (pdata->trigger_levels[i])
- trigger_levs++;
-
- if (data->soc == SOC_ARCH_EXYNOS4210) {
- /* Write temperature code for threshold */
- threshold_code = temp_to_code(data, pdata->threshold);
- if (threshold_code < 0) {
- ret = threshold_code;
- goto out;
- }
- writeb(threshold_code,
- data->base + EXYNOS4210_TMU_REG_THRESHOLD_TEMP);
- for (i = 0; i < trigger_levs; i++)
- writeb(pdata->trigger_levels[i],
- data->base + EXYNOS4210_TMU_REG_TRIG_LEVEL0 + i * 4);
-
- writel(EXYNOS4210_TMU_INTCLEAR_VAL,
- data->base + EXYNOS_TMU_REG_INTCLEAR);
- } else if (data->soc == SOC_ARCH_EXYNOS) {
- /* Write temperature code for rising and falling threshold */
- for (i = 0; i < trigger_levs; i++) {
- threshold_code = temp_to_code(data,
- pdata->trigger_levels[i]);
- if (threshold_code < 0) {
- ret = threshold_code;
- goto out;
- }
- rising_threshold |= threshold_code << 8 * i;
- if (pdata->threshold_falling) {
- threshold_code = temp_to_code(data,
- pdata->trigger_levels[i] -
- pdata->threshold_falling);
- if (threshold_code > 0)
- falling_threshold |=
- threshold_code << 8 * i;
- }
- }
-
- writel(rising_threshold,
- data->base + EXYNOS_THD_TEMP_RISE);
- writel(falling_threshold,
- data->base + EXYNOS_THD_TEMP_FALL);
-
- writel(EXYNOS_TMU_CLEAR_RISE_INT | EXYNOS_TMU_CLEAR_FALL_INT,
- data->base + EXYNOS_TMU_REG_INTCLEAR);
- }
-out:
- clk_disable(data->clk);
- mutex_unlock(&data->lock);
-
- return ret;
-}
-
-static void exynos_tmu_control(struct platform_device *pdev, bool on)
-{
- struct exynos_tmu_data *data = platform_get_drvdata(pdev);
- struct exynos_tmu_platform_data *pdata = data->pdata;
- unsigned int con, interrupt_en;
-
- mutex_lock(&data->lock);
- clk_enable(data->clk);
-
- con = pdata->reference_voltage << EXYNOS_TMU_REF_VOLTAGE_SHIFT |
- pdata->gain << EXYNOS_TMU_GAIN_SHIFT;
-
- if (data->soc == SOC_ARCH_EXYNOS) {
- con |= pdata->noise_cancel_mode << EXYNOS_TMU_TRIP_MODE_SHIFT;
- con |= (EXYNOS_MUX_ADDR_VALUE << EXYNOS_MUX_ADDR_SHIFT);
- }
-
- if (on) {
- con |= EXYNOS_TMU_CORE_ON;
- interrupt_en = pdata->trigger_level3_en << 12 |
- pdata->trigger_level2_en << 8 |
- pdata->trigger_level1_en << 4 |
- pdata->trigger_level0_en;
- if (pdata->threshold_falling)
- interrupt_en |= interrupt_en << 16;
- } else {
- con |= EXYNOS_TMU_CORE_OFF;
- interrupt_en = 0; /* Disable all interrupts */
- }
- writel(interrupt_en, data->base + EXYNOS_TMU_REG_INTEN);
- writel(con, data->base + EXYNOS_TMU_REG_CONTROL);
-
- clk_disable(data->clk);
- mutex_unlock(&data->lock);
-}
-
-static int exynos_tmu_read(struct exynos_tmu_data *data)
-{
- u8 temp_code;
- int temp;
-
- mutex_lock(&data->lock);
- clk_enable(data->clk);
-
- temp_code = readb(data->base + EXYNOS_TMU_REG_CURRENT_TEMP);
- temp = code_to_temp(data, temp_code);
-
- clk_disable(data->clk);
- mutex_unlock(&data->lock);
-
- return temp;
-}
-
-#ifdef CONFIG_THERMAL_EMULATION
-static int exynos_tmu_set_emulation(void *drv_data, unsigned long temp)
-{
- struct exynos_tmu_data *data = drv_data;
- unsigned int reg;
- int ret = -EINVAL;
-
- if (data->soc == SOC_ARCH_EXYNOS4210)
- goto out;
-
- if (temp && temp < MCELSIUS)
- goto out;
-
- mutex_lock(&data->lock);
- clk_enable(data->clk);
-
- reg = readl(data->base + EXYNOS_EMUL_CON);
-
- if (temp) {
- temp /= MCELSIUS;
-
- reg = (EXYNOS_EMUL_TIME << EXYNOS_EMUL_TIME_SHIFT) |
- (temp_to_code(data, temp)
- << EXYNOS_EMUL_DATA_SHIFT) | EXYNOS_EMUL_ENABLE;
- } else {
- reg &= ~EXYNOS_EMUL_ENABLE;
- }
-
- writel(reg, data->base + EXYNOS_EMUL_CON);
-
- clk_disable(data->clk);
- mutex_unlock(&data->lock);
- return 0;
-out:
- return ret;
-}
-#else
-static int exynos_tmu_set_emulation(void *drv_data, unsigned long temp)
- { return -EINVAL; }
-#endif/*CONFIG_THERMAL_EMULATION*/
-
-static void exynos_tmu_work(struct work_struct *work)
-{
- struct exynos_tmu_data *data = container_of(work,
- struct exynos_tmu_data, irq_work);
-
- exynos_report_trigger();
- mutex_lock(&data->lock);
- clk_enable(data->clk);
- if (data->soc == SOC_ARCH_EXYNOS)
- writel(EXYNOS_TMU_CLEAR_RISE_INT |
- EXYNOS_TMU_CLEAR_FALL_INT,
- data->base + EXYNOS_TMU_REG_INTCLEAR);
- else
- writel(EXYNOS4210_TMU_INTCLEAR_VAL,
- data->base + EXYNOS_TMU_REG_INTCLEAR);
- clk_disable(data->clk);
- mutex_unlock(&data->lock);
-
- enable_irq(data->irq);
-}
-
-static irqreturn_t exynos_tmu_irq(int irq, void *id)
-{
- struct exynos_tmu_data *data = id;
-
- disable_irq_nosync(irq);
- schedule_work(&data->irq_work);
-
- return IRQ_HANDLED;
-}
-static struct thermal_sensor_conf exynos_sensor_conf = {
- .name = "exynos-therm",
- .read_temperature = (int (*)(void *))exynos_tmu_read,
- .write_emul_temp = exynos_tmu_set_emulation,
-};
-
-#if defined(CONFIG_CPU_EXYNOS4210)
-static struct exynos_tmu_platform_data const exynos4210_default_tmu_data = {
- .threshold = 80,
- .trigger_levels[0] = 5,
- .trigger_levels[1] = 20,
- .trigger_levels[2] = 30,
- .trigger_level0_en = 1,
- .trigger_level1_en = 1,
- .trigger_level2_en = 1,
- .trigger_level3_en = 0,
- .gain = 15,
- .reference_voltage = 7,
- .cal_type = TYPE_ONE_POINT_TRIMMING,
- .freq_tab[0] = {
- .freq_clip_max = 800 * 1000,
- .temp_level = 85,
- },
- .freq_tab[1] = {
- .freq_clip_max = 200 * 1000,
- .temp_level = 100,
- },
- .freq_tab_count = 2,
- .type = SOC_ARCH_EXYNOS4210,
-};
-#define EXYNOS4210_TMU_DRV_DATA (&exynos4210_default_tmu_data)
-#else
-#define EXYNOS4210_TMU_DRV_DATA (NULL)
-#endif
-
-#if defined(CONFIG_SOC_EXYNOS5250) || defined(CONFIG_SOC_EXYNOS4412) || \
- defined(CONFIG_SOC_EXYNOS4212)
-static struct exynos_tmu_platform_data const exynos_default_tmu_data = {
- .threshold_falling = 10,
- .trigger_levels[0] = 85,
- .trigger_levels[1] = 103,
- .trigger_levels[2] = 110,
- .trigger_level0_en = 1,
- .trigger_level1_en = 1,
- .trigger_level2_en = 1,
- .trigger_level3_en = 0,
- .gain = 8,
- .reference_voltage = 16,
- .noise_cancel_mode = 4,
- .cal_type = TYPE_ONE_POINT_TRIMMING,
- .efuse_value = 55,
- .freq_tab[0] = {
- .freq_clip_max = 800 * 1000,
- .temp_level = 85,
- },
- .freq_tab[1] = {
- .freq_clip_max = 200 * 1000,
- .temp_level = 103,
- },
- .freq_tab_count = 2,
- .type = SOC_ARCH_EXYNOS,
-};
-#define EXYNOS_TMU_DRV_DATA (&exynos_default_tmu_data)
-#else
-#define EXYNOS_TMU_DRV_DATA (NULL)
-#endif
-
-#ifdef CONFIG_OF
-static const struct of_device_id exynos_tmu_match[] = {
- {
- .compatible = "samsung,exynos4210-tmu",
- .data = (void *)EXYNOS4210_TMU_DRV_DATA,
- },
- {
- .compatible = "samsung,exynos4412-tmu",
- .data = (void *)EXYNOS_TMU_DRV_DATA,
- },
- {
- .compatible = "samsung,exynos5250-tmu",
- .data = (void *)EXYNOS_TMU_DRV_DATA,
- },
- {},
-};
-MODULE_DEVICE_TABLE(of, exynos_tmu_match);
-#endif
-
-static struct platform_device_id exynos_tmu_driver_ids[] = {
- {
- .name = "exynos4210-tmu",
- .driver_data = (kernel_ulong_t)EXYNOS4210_TMU_DRV_DATA,
- },
- {
- .name = "exynos5250-tmu",
- .driver_data = (kernel_ulong_t)EXYNOS_TMU_DRV_DATA,
- },
- { },
-};
-MODULE_DEVICE_TABLE(platform, exynos_tmu_driver_ids);
-
-static inline struct exynos_tmu_platform_data *exynos_get_driver_data(
- struct platform_device *pdev)
-{
-#ifdef CONFIG_OF
- if (pdev->dev.of_node) {
- const struct of_device_id *match;
- match = of_match_node(exynos_tmu_match, pdev->dev.of_node);
- if (!match)
- return NULL;
- return (struct exynos_tmu_platform_data *) match->data;
- }
-#endif
- return (struct exynos_tmu_platform_data *)
- platform_get_device_id(pdev)->driver_data;
-}
-
-static int exynos_tmu_probe(struct platform_device *pdev)
-{
- struct exynos_tmu_data *data;
- struct exynos_tmu_platform_data *pdata = pdev->dev.platform_data;
- int ret, i;
-
- if (!pdata)
- pdata = exynos_get_driver_data(pdev);
-
- if (!pdata) {
- dev_err(&pdev->dev, "No platform init data supplied.\n");
- return -ENODEV;
- }
- data = devm_kzalloc(&pdev->dev, sizeof(struct exynos_tmu_data),
- GFP_KERNEL);
- if (!data) {
- dev_err(&pdev->dev, "Failed to allocate driver structure\n");
- return -ENOMEM;
- }
-
- data->irq = platform_get_irq(pdev, 0);
- if (data->irq < 0) {
- dev_err(&pdev->dev, "Failed to get platform irq\n");
- return data->irq;
- }
-
- INIT_WORK(&data->irq_work, exynos_tmu_work);
-
- data->mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- data->base = devm_ioremap_resource(&pdev->dev, data->mem);
- if (IS_ERR(data->base))
- return PTR_ERR(data->base);
-
- ret = devm_request_irq(&pdev->dev, data->irq, exynos_tmu_irq,
- IRQF_TRIGGER_RISING, "exynos-tmu", data);
- if (ret) {
- dev_err(&pdev->dev, "Failed to request irq: %d\n", data->irq);
- return ret;
- }
-
- data->clk = devm_clk_get(&pdev->dev, "tmu_apbif");
- if (IS_ERR(data->clk)) {
- dev_err(&pdev->dev, "Failed to get clock\n");
- return PTR_ERR(data->clk);
- }
-
- ret = clk_prepare(data->clk);
- if (ret)
- return ret;
-
- if (pdata->type == SOC_ARCH_EXYNOS ||
- pdata->type == SOC_ARCH_EXYNOS4210)
- data->soc = pdata->type;
- else {
- ret = -EINVAL;
- dev_err(&pdev->dev, "Platform not supported\n");
- goto err_clk;
- }
-
- data->pdata = pdata;
- platform_set_drvdata(pdev, data);
- mutex_init(&data->lock);
-
- ret = exynos_tmu_initialize(pdev);
- if (ret) {
- dev_err(&pdev->dev, "Failed to initialize TMU\n");
- goto err_clk;
- }
-
- exynos_tmu_control(pdev, true);
-
- /* Register the sensor with thermal management interface */
- (&exynos_sensor_conf)->private_data = data;
- exynos_sensor_conf.trip_data.trip_count = pdata->trigger_level0_en +
- pdata->trigger_level1_en + pdata->trigger_level2_en +
- pdata->trigger_level3_en;
-
- for (i = 0; i < exynos_sensor_conf.trip_data.trip_count; i++)
- exynos_sensor_conf.trip_data.trip_val[i] =
- pdata->threshold + pdata->trigger_levels[i];
-
- exynos_sensor_conf.trip_data.trigger_falling = pdata->threshold_falling;
-
- exynos_sensor_conf.cooling_data.freq_clip_count =
- pdata->freq_tab_count;
- for (i = 0; i < pdata->freq_tab_count; i++) {
- exynos_sensor_conf.cooling_data.freq_data[i].freq_clip_max =
- pdata->freq_tab[i].freq_clip_max;
- exynos_sensor_conf.cooling_data.freq_data[i].temp_level =
- pdata->freq_tab[i].temp_level;
- }
-
- ret = exynos_register_thermal(&exynos_sensor_conf);
- if (ret) {
- dev_err(&pdev->dev, "Failed to register thermal interface\n");
- goto err_clk;
- }
-
- return 0;
-err_clk:
- clk_unprepare(data->clk);
- return ret;
-}
-
-static int exynos_tmu_remove(struct platform_device *pdev)
-{
- struct exynos_tmu_data *data = platform_get_drvdata(pdev);
-
- exynos_tmu_control(pdev, false);
-
- exynos_unregister_thermal();
-
- clk_unprepare(data->clk);
-
- return 0;
-}
-
-#ifdef CONFIG_PM_SLEEP
-static int exynos_tmu_suspend(struct device *dev)
-{
- exynos_tmu_control(to_platform_device(dev), false);
-
- return 0;
-}
-
-static int exynos_tmu_resume(struct device *dev)
-{
- struct platform_device *pdev = to_platform_device(dev);
-
- exynos_tmu_initialize(pdev);
- exynos_tmu_control(pdev, true);
-
- return 0;
-}
-
-static SIMPLE_DEV_PM_OPS(exynos_tmu_pm,
- exynos_tmu_suspend, exynos_tmu_resume);
-#define EXYNOS_TMU_PM (&exynos_tmu_pm)
-#else
-#define EXYNOS_TMU_PM NULL
-#endif
-
-static struct platform_driver exynos_tmu_driver = {
- .driver = {
- .name = "exynos-tmu",
- .owner = THIS_MODULE,
- .pm = EXYNOS_TMU_PM,
- .of_match_table = of_match_ptr(exynos_tmu_match),
- },
- .probe = exynos_tmu_probe,
- .remove = exynos_tmu_remove,
- .id_table = exynos_tmu_driver_ids,
-};
-
-module_platform_driver(exynos_tmu_driver);
-
-MODULE_DESCRIPTION("EXYNOS TMU Driver");
-MODULE_AUTHOR("Donggeun Kim <dg77.kim@samsung.com>");
-MODULE_LICENSE("GPL");
-MODULE_ALIAS("platform:exynos-tmu");
diff --git a/drivers/thermal/imx_thermal.c b/drivers/thermal/imx_thermal.c
new file mode 100644
index 0000000..1d6c801
--- /dev/null
+++ b/drivers/thermal/imx_thermal.c
@@ -0,0 +1,541 @@
+/*
+ * Copyright 2013 Freescale Semiconductor, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/cpu_cooling.h>
+#include <linux/cpufreq.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include <linux/thermal.h>
+#include <linux/types.h>
+
+#define REG_SET 0x4
+#define REG_CLR 0x8
+#define REG_TOG 0xc
+
+#define MISC0 0x0150
+#define MISC0_REFTOP_SELBIASOFF (1 << 3)
+
+#define TEMPSENSE0 0x0180
+#define TEMPSENSE0_ALARM_VALUE_SHIFT 20
+#define TEMPSENSE0_ALARM_VALUE_MASK (0xfff << TEMPSENSE0_ALARM_VALUE_SHIFT)
+#define TEMPSENSE0_TEMP_CNT_SHIFT 8
+#define TEMPSENSE0_TEMP_CNT_MASK (0xfff << TEMPSENSE0_TEMP_CNT_SHIFT)
+#define TEMPSENSE0_FINISHED (1 << 2)
+#define TEMPSENSE0_MEASURE_TEMP (1 << 1)
+#define TEMPSENSE0_POWER_DOWN (1 << 0)
+
+#define TEMPSENSE1 0x0190
+#define TEMPSENSE1_MEASURE_FREQ 0xffff
+
+#define OCOTP_ANA1 0x04e0
+
+/* The driver supports 1 passive trip point and 1 critical trip point */
+enum imx_thermal_trip {
+ IMX_TRIP_PASSIVE,
+ IMX_TRIP_CRITICAL,
+ IMX_TRIP_NUM,
+};
+
+/*
+ * It defines the temperature in millicelsius for passive trip point
+ * that will trigger cooling action when crossed.
+ */
+#define IMX_TEMP_PASSIVE 85000
+
+#define IMX_POLLING_DELAY 2000 /* millisecond */
+#define IMX_PASSIVE_DELAY 1000
+
+struct imx_thermal_data {
+ struct thermal_zone_device *tz;
+ struct thermal_cooling_device *cdev;
+ enum thermal_device_mode mode;
+ struct regmap *tempmon;
+ int c1, c2; /* See formula in imx_get_sensor_data() */
+ unsigned long temp_passive;
+ unsigned long temp_critical;
+ unsigned long alarm_temp;
+ unsigned long last_temp;
+ bool irq_enabled;
+ int irq;
+};
+
+static void imx_set_alarm_temp(struct imx_thermal_data *data,
+ signed long alarm_temp)
+{
+ struct regmap *map = data->tempmon;
+ int alarm_value;
+
+ data->alarm_temp = alarm_temp;
+ alarm_value = (alarm_temp - data->c2) / data->c1;
+ regmap_write(map, TEMPSENSE0 + REG_CLR, TEMPSENSE0_ALARM_VALUE_MASK);
+ regmap_write(map, TEMPSENSE0 + REG_SET, alarm_value <<
+ TEMPSENSE0_ALARM_VALUE_SHIFT);
+}
+
+static int imx_get_temp(struct thermal_zone_device *tz, unsigned long *temp)
+{
+ struct imx_thermal_data *data = tz->devdata;
+ struct regmap *map = data->tempmon;
+ unsigned int n_meas;
+ bool wait;
+ u32 val;
+
+ if (data->mode == THERMAL_DEVICE_ENABLED) {
+ /* Check if a measurement is currently in progress */
+ regmap_read(map, TEMPSENSE0, &val);
+ wait = !(val & TEMPSENSE0_FINISHED);
+ } else {
+ /*
+ * Every time we measure the temperature, we will power on the
+ * temperature sensor, enable measurements, take a reading,
+ * disable measurements, power off the temperature sensor.
+ */
+ regmap_write(map, TEMPSENSE0 + REG_CLR, TEMPSENSE0_POWER_DOWN);
+ regmap_write(map, TEMPSENSE0 + REG_SET, TEMPSENSE0_MEASURE_TEMP);
+
+ wait = true;
+ }
+
+ /*
+ * According to the temp sensor designers, it may require up to ~17us
+ * to complete a measurement.
+ */
+ if (wait)
+ usleep_range(20, 50);
+
+ regmap_read(map, TEMPSENSE0, &val);
+
+ if (data->mode != THERMAL_DEVICE_ENABLED) {
+ regmap_write(map, TEMPSENSE0 + REG_CLR, TEMPSENSE0_MEASURE_TEMP);
+ regmap_write(map, TEMPSENSE0 + REG_SET, TEMPSENSE0_POWER_DOWN);
+ }
+
+ if ((val & TEMPSENSE0_FINISHED) == 0) {
+ dev_dbg(&tz->device, "temp measurement never finished\n");
+ return -EAGAIN;
+ }
+
+ n_meas = (val & TEMPSENSE0_TEMP_CNT_MASK) >> TEMPSENSE0_TEMP_CNT_SHIFT;
+
+ /* See imx_get_sensor_data() for formula derivation */
+ *temp = data->c2 + data->c1 * n_meas;
+
+ /* Update alarm value to next higher trip point */
+ if (data->alarm_temp == data->temp_passive && *temp >= data->temp_passive)
+ imx_set_alarm_temp(data, data->temp_critical);
+ if (data->alarm_temp == data->temp_critical && *temp < data->temp_passive) {
+ imx_set_alarm_temp(data, data->temp_passive);
+ dev_dbg(&tz->device, "thermal alarm off: T < %lu\n",
+ data->alarm_temp / 1000);
+ }
+
+ if (*temp != data->last_temp) {
+ dev_dbg(&tz->device, "millicelsius: %ld\n", *temp);
+ data->last_temp = *temp;
+ }
+
+ /* Reenable alarm IRQ if temperature below alarm temperature */
+ if (!data->irq_enabled && *temp < data->alarm_temp) {
+ data->irq_enabled = true;
+ enable_irq(data->irq);
+ }
+
+ return 0;
+}
+
+static int imx_get_mode(struct thermal_zone_device *tz,
+ enum thermal_device_mode *mode)
+{
+ struct imx_thermal_data *data = tz->devdata;
+
+ *mode = data->mode;
+
+ return 0;
+}
+
+static int imx_set_mode(struct thermal_zone_device *tz,
+ enum thermal_device_mode mode)
+{
+ struct imx_thermal_data *data = tz->devdata;
+ struct regmap *map = data->tempmon;
+
+ if (mode == THERMAL_DEVICE_ENABLED) {
+ tz->polling_delay = IMX_POLLING_DELAY;
+ tz->passive_delay = IMX_PASSIVE_DELAY;
+
+ regmap_write(map, TEMPSENSE0 + REG_CLR, TEMPSENSE0_POWER_DOWN);
+ regmap_write(map, TEMPSENSE0 + REG_SET, TEMPSENSE0_MEASURE_TEMP);
+
+ if (!data->irq_enabled) {
+ data->irq_enabled = true;
+ enable_irq(data->irq);
+ }
+ } else {
+ regmap_write(map, TEMPSENSE0 + REG_CLR, TEMPSENSE0_MEASURE_TEMP);
+ regmap_write(map, TEMPSENSE0 + REG_SET, TEMPSENSE0_POWER_DOWN);
+
+ tz->polling_delay = 0;
+ tz->passive_delay = 0;
+
+ if (data->irq_enabled) {
+ disable_irq(data->irq);
+ data->irq_enabled = false;
+ }
+ }
+
+ data->mode = mode;
+ thermal_zone_device_update(tz);
+
+ return 0;
+}
+
+static int imx_get_trip_type(struct thermal_zone_device *tz, int trip,
+ enum thermal_trip_type *type)
+{
+ *type = (trip == IMX_TRIP_PASSIVE) ? THERMAL_TRIP_PASSIVE :
+ THERMAL_TRIP_CRITICAL;
+ return 0;
+}
+
+static int imx_get_crit_temp(struct thermal_zone_device *tz,
+ unsigned long *temp)
+{
+ struct imx_thermal_data *data = tz->devdata;
+
+ *temp = data->temp_critical;
+ return 0;
+}
+
+static int imx_get_trip_temp(struct thermal_zone_device *tz, int trip,
+ unsigned long *temp)
+{
+ struct imx_thermal_data *data = tz->devdata;
+
+ *temp = (trip == IMX_TRIP_PASSIVE) ? data->temp_passive :
+ data->temp_critical;
+ return 0;
+}
+
+static int imx_set_trip_temp(struct thermal_zone_device *tz, int trip,
+ unsigned long temp)
+{
+ struct imx_thermal_data *data = tz->devdata;
+
+ if (trip == IMX_TRIP_CRITICAL)
+ return -EPERM;
+
+ if (temp > IMX_TEMP_PASSIVE)
+ return -EINVAL;
+
+ data->temp_passive = temp;
+
+ imx_set_alarm_temp(data, temp);
+
+ return 0;
+}
+
+static int imx_bind(struct thermal_zone_device *tz,
+ struct thermal_cooling_device *cdev)
+{
+ int ret;
+
+ ret = thermal_zone_bind_cooling_device(tz, IMX_TRIP_PASSIVE, cdev,
+ THERMAL_NO_LIMIT,
+ THERMAL_NO_LIMIT);
+ if (ret) {
+ dev_err(&tz->device,
+ "binding zone %s with cdev %s failed:%d\n",
+ tz->type, cdev->type, ret);
+ return ret;
+ }
+
+ return 0;
+}
+
+static int imx_unbind(struct thermal_zone_device *tz,
+ struct thermal_cooling_device *cdev)
+{
+ int ret;
+
+ ret = thermal_zone_unbind_cooling_device(tz, IMX_TRIP_PASSIVE, cdev);
+ if (ret) {
+ dev_err(&tz->device,
+ "unbinding zone %s with cdev %s failed:%d\n",
+ tz->type, cdev->type, ret);
+ return ret;
+ }
+
+ return 0;
+}
+
+static const struct thermal_zone_device_ops imx_tz_ops = {
+ .bind = imx_bind,
+ .unbind = imx_unbind,
+ .get_temp = imx_get_temp,
+ .get_mode = imx_get_mode,
+ .set_mode = imx_set_mode,
+ .get_trip_type = imx_get_trip_type,
+ .get_trip_temp = imx_get_trip_temp,
+ .get_crit_temp = imx_get_crit_temp,
+ .set_trip_temp = imx_set_trip_temp,
+};
+
+static int imx_get_sensor_data(struct platform_device *pdev)
+{
+ struct imx_thermal_data *data = platform_get_drvdata(pdev);
+ struct regmap *map;
+ int t1, t2, n1, n2;
+ int ret;
+ u32 val;
+
+ map = syscon_regmap_lookup_by_phandle(pdev->dev.of_node,
+ "fsl,tempmon-data");
+ if (IS_ERR(map)) {
+ ret = PTR_ERR(map);
+ dev_err(&pdev->dev, "failed to get sensor regmap: %d\n", ret);
+ return ret;
+ }
+
+ ret = regmap_read(map, OCOTP_ANA1, &val);
+ if (ret) {
+ dev_err(&pdev->dev, "failed to read sensor data: %d\n", ret);
+ return ret;
+ }
+
+ if (val == 0 || val == ~0) {
+ dev_err(&pdev->dev, "invalid sensor calibration data\n");
+ return -EINVAL;
+ }
+
+ /*
+ * Sensor data layout:
+ * [31:20] - sensor value @ 25C
+ * [19:8] - sensor value of hot
+ * [7:0] - hot temperature value
+ */
+ n1 = val >> 20;
+ n2 = (val & 0xfff00) >> 8;
+ t2 = val & 0xff;
+ t1 = 25; /* t1 always 25C */
+
+ /*
+ * Derived from linear interpolation,
+ * Tmeas = T2 + (Nmeas - N2) * (T1 - T2) / (N1 - N2)
+ * We want to reduce this down to the minimum computation necessary
+ * for each temperature read. Also, we want Tmeas in millicelsius
+ * and we don't want to lose precision from integer division. So...
+ * milli_Tmeas = 1000 * T2 + 1000 * (Nmeas - N2) * (T1 - T2) / (N1 - N2)
+ * Let constant c1 = 1000 * (T1 - T2) / (N1 - N2)
+ * milli_Tmeas = (1000 * T2) + c1 * (Nmeas - N2)
+ * milli_Tmeas = (1000 * T2) + (c1 * Nmeas) - (c1 * N2)
+ * Let constant c2 = (1000 * T2) - (c1 * N2)
+ * milli_Tmeas = c2 + (c1 * Nmeas)
+ */
+ data->c1 = 1000 * (t1 - t2) / (n1 - n2);
+ data->c2 = 1000 * t2 - data->c1 * n2;
+
+ /*
+ * Set the default passive cooling trip point to 20 °C below the
+ * maximum die temperature. Can be changed from userspace.
+ */
+ data->temp_passive = 1000 * (t2 - 20);
+
+ /*
+ * The maximum die temperature is t2, let's give 5 °C cushion
+ * for noise and possible temperature rise between measurements.
+ */
+ data->temp_critical = 1000 * (t2 - 5);
+
+ return 0;
+}
+
+static irqreturn_t imx_thermal_alarm_irq(int irq, void *dev)
+{
+ struct imx_thermal_data *data = dev;
+
+ disable_irq_nosync(irq);
+ data->irq_enabled = false;
+
+ return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t imx_thermal_alarm_irq_thread(int irq, void *dev)
+{
+ struct imx_thermal_data *data = dev;
+
+ dev_dbg(&data->tz->device, "THERMAL ALARM: T > %lu\n",
+ data->alarm_temp / 1000);
+
+ thermal_zone_device_update(data->tz);
+
+ return IRQ_HANDLED;
+}
+
+static int imx_thermal_probe(struct platform_device *pdev)
+{
+ struct imx_thermal_data *data;
+ struct cpumask clip_cpus;
+ struct regmap *map;
+ int measure_freq;
+ int ret;
+
+ data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ map = syscon_regmap_lookup_by_phandle(pdev->dev.of_node, "fsl,tempmon");
+ if (IS_ERR(map)) {
+ ret = PTR_ERR(map);
+ dev_err(&pdev->dev, "failed to get tempmon regmap: %d\n", ret);
+ return ret;
+ }
+ data->tempmon = map;
+
+ data->irq = platform_get_irq(pdev, 0);
+ if (data->irq < 0)
+ return data->irq;
+
+ ret = devm_request_threaded_irq(&pdev->dev, data->irq,
+ imx_thermal_alarm_irq, imx_thermal_alarm_irq_thread,
+ 0, "imx_thermal", data);
+ if (ret < 0) {
+ dev_err(&pdev->dev, "failed to request alarm irq: %d\n", ret);
+ return ret;
+ }
+
+ platform_set_drvdata(pdev, data);
+
+ ret = imx_get_sensor_data(pdev);
+ if (ret) {
+ dev_err(&pdev->dev, "failed to get sensor data\n");
+ return ret;
+ }
+
+ /* Make sure sensor is in known good state for measurements */
+ regmap_write(map, TEMPSENSE0 + REG_CLR, TEMPSENSE0_POWER_DOWN);
+ regmap_write(map, TEMPSENSE0 + REG_CLR, TEMPSENSE0_MEASURE_TEMP);
+ regmap_write(map, TEMPSENSE1 + REG_CLR, TEMPSENSE1_MEASURE_FREQ);
+ regmap_write(map, MISC0 + REG_SET, MISC0_REFTOP_SELBIASOFF);
+ regmap_write(map, TEMPSENSE0 + REG_SET, TEMPSENSE0_POWER_DOWN);
+
+ cpumask_set_cpu(0, &clip_cpus);
+ data->cdev = cpufreq_cooling_register(&clip_cpus);
+ if (IS_ERR(data->cdev)) {
+ ret = PTR_ERR(data->cdev);
+ dev_err(&pdev->dev,
+ "failed to register cpufreq cooling device: %d\n", ret);
+ return ret;
+ }
+
+ data->tz = thermal_zone_device_register("imx_thermal_zone",
+ IMX_TRIP_NUM,
+ BIT(IMX_TRIP_PASSIVE), data,
+ &imx_tz_ops, NULL,
+ IMX_PASSIVE_DELAY,
+ IMX_POLLING_DELAY);
+ if (IS_ERR(data->tz)) {
+ ret = PTR_ERR(data->tz);
+ dev_err(&pdev->dev,
+ "failed to register thermal zone device %d\n", ret);
+ cpufreq_cooling_unregister(data->cdev);
+ return ret;
+ }
+
+ /* Enable measurements at ~ 10 Hz */
+ regmap_write(map, TEMPSENSE1 + REG_CLR, TEMPSENSE1_MEASURE_FREQ);
+ measure_freq = DIV_ROUND_UP(32768, 10); /* 10 Hz */
+ regmap_write(map, TEMPSENSE1 + REG_SET, measure_freq);
+ imx_set_alarm_temp(data, data->temp_passive);
+ regmap_write(map, TEMPSENSE0 + REG_CLR, TEMPSENSE0_POWER_DOWN);
+ regmap_write(map, TEMPSENSE0 + REG_SET, TEMPSENSE0_MEASURE_TEMP);
+
+ data->irq_enabled = true;
+ data->mode = THERMAL_DEVICE_ENABLED;
+
+ return 0;
+}
+
+static int imx_thermal_remove(struct platform_device *pdev)
+{
+ struct imx_thermal_data *data = platform_get_drvdata(pdev);
+ struct regmap *map = data->tempmon;
+
+ /* Disable measurements */
+ regmap_write(map, TEMPSENSE0 + REG_SET, TEMPSENSE0_POWER_DOWN);
+
+ thermal_zone_device_unregister(data->tz);
+ cpufreq_cooling_unregister(data->cdev);
+
+ return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int imx_thermal_suspend(struct device *dev)
+{
+ struct imx_thermal_data *data = dev_get_drvdata(dev);
+ struct regmap *map = data->tempmon;
+ u32 val;
+
+ regmap_read(map, TEMPSENSE0, &val);
+ if ((val & TEMPSENSE0_POWER_DOWN) == 0) {
+ /*
+ * If a measurement is taking place, wait for a long enough
+ * time for it to finish, and then check again. If it still
+ * does not finish, something must go wrong.
+ */
+ udelay(50);
+ regmap_read(map, TEMPSENSE0, &val);
+ if ((val & TEMPSENSE0_POWER_DOWN) == 0)
+ return -ETIMEDOUT;
+ }
+
+ return 0;
+}
+
+static int imx_thermal_resume(struct device *dev)
+{
+ /* Nothing to do for now */
+ return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(imx_thermal_pm_ops,
+ imx_thermal_suspend, imx_thermal_resume);
+
+static const struct of_device_id of_imx_thermal_match[] = {
+ { .compatible = "fsl,imx6q-tempmon", },
+ { /* end */ }
+};
+
+static struct platform_driver imx_thermal = {
+ .driver = {
+ .name = "imx_thermal",
+ .owner = THIS_MODULE,
+ .pm = &imx_thermal_pm_ops,
+ .of_match_table = of_imx_thermal_match,
+ },
+ .probe = imx_thermal_probe,
+ .remove = imx_thermal_remove,
+};
+module_platform_driver(imx_thermal);
+
+MODULE_AUTHOR("Freescale Semiconductor, Inc.");
+MODULE_DESCRIPTION("Thermal driver for Freescale i.MX SoCs");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:imx-thermal");
diff --git a/drivers/thermal/samsung/Kconfig b/drivers/thermal/samsung/Kconfig
new file mode 100644
index 0000000..f760389
--- /dev/null
+++ b/drivers/thermal/samsung/Kconfig
@@ -0,0 +1,18 @@
+config EXYNOS_THERMAL
+ tristate "Exynos thermal management unit driver"
+ depends on ARCH_HAS_BANDGAP && OF
+ help
+ If you say yes here you get support for the TMU (Thermal Management
+ Unit) driver for SAMSUNG EXYNOS series of SoCs. This driver initialises
+ the TMU, reports temperature and handles cooling action if defined.
+ This driver uses the Exynos core thermal APIs and TMU configuration
+ data from the supported SoCs.
+
+config EXYNOS_THERMAL_CORE
+ bool "Core thermal framework support for EXYNOS SOCs"
+ depends on EXYNOS_THERMAL
+ help
+ If you say yes here you get support for EXYNOS TMU
+ (Thermal Management Unit) common registration/unregistration
+ functions to the core thermal layer and also to use the generic
+ CPU cooling APIs.
diff --git a/drivers/thermal/samsung/Makefile b/drivers/thermal/samsung/Makefile
new file mode 100644
index 0000000..c09d830
--- /dev/null
+++ b/drivers/thermal/samsung/Makefile
@@ -0,0 +1,7 @@
+#
+# Samsung thermal specific Makefile
+#
+obj-$(CONFIG_EXYNOS_THERMAL) += exynos_thermal.o
+exynos_thermal-y := exynos_tmu.o
+exynos_thermal-y += exynos_tmu_data.o
+exynos_thermal-$(CONFIG_EXYNOS_THERMAL_CORE) += exynos_thermal_common.o
diff --git a/drivers/thermal/samsung/exynos_thermal_common.c b/drivers/thermal/samsung/exynos_thermal_common.c
new file mode 100644
index 0000000..f10a6ad
--- /dev/null
+++ b/drivers/thermal/samsung/exynos_thermal_common.c
@@ -0,0 +1,432 @@
+/*
+ * exynos_thermal_common.c - Samsung EXYNOS common thermal file
+ *
+ * Copyright (C) 2013 Samsung Electronics
+ * Amit Daniel Kachhap <amit.daniel@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ *
+ */
+
+#include <linux/cpu_cooling.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/thermal.h>
+
+#include "exynos_thermal_common.h"
+
+struct exynos_thermal_zone {
+ enum thermal_device_mode mode;
+ struct thermal_zone_device *therm_dev;
+ struct thermal_cooling_device *cool_dev[MAX_COOLING_DEVICE];
+ unsigned int cool_dev_size;
+ struct platform_device *exynos4_dev;
+ struct thermal_sensor_conf *sensor_conf;
+ bool bind;
+};
+
+/* Get mode callback functions for thermal zone */
+static int exynos_get_mode(struct thermal_zone_device *thermal,
+ enum thermal_device_mode *mode)
+{
+ struct exynos_thermal_zone *th_zone = thermal->devdata;
+ if (th_zone)
+ *mode = th_zone->mode;
+ return 0;
+}
+
+/* Set mode callback functions for thermal zone */
+static int exynos_set_mode(struct thermal_zone_device *thermal,
+ enum thermal_device_mode mode)
+{
+ struct exynos_thermal_zone *th_zone = thermal->devdata;
+ if (!th_zone) {
+ dev_err(&thermal->device,
+ "thermal zone not registered\n");
+ return 0;
+ }
+
+ mutex_lock(&thermal->lock);
+
+ if (mode == THERMAL_DEVICE_ENABLED &&
+ !th_zone->sensor_conf->trip_data.trigger_falling)
+ thermal->polling_delay = IDLE_INTERVAL;
+ else
+ thermal->polling_delay = 0;
+
+ mutex_unlock(&thermal->lock);
+
+ th_zone->mode = mode;
+ thermal_zone_device_update(thermal);
+ dev_dbg(th_zone->sensor_conf->dev,
+ "thermal polling set for duration=%d msec\n",
+ thermal->polling_delay);
+ return 0;
+}
+
+
+/* Get trip type callback functions for thermal zone */
+static int exynos_get_trip_type(struct thermal_zone_device *thermal, int trip,
+ enum thermal_trip_type *type)
+{
+ struct exynos_thermal_zone *th_zone = thermal->devdata;
+ int max_trip = th_zone->sensor_conf->trip_data.trip_count;
+ int trip_type;
+
+ if (trip < 0 || trip >= max_trip)
+ return -EINVAL;
+
+ trip_type = th_zone->sensor_conf->trip_data.trip_type[trip];
+
+ if (trip_type == SW_TRIP)
+ *type = THERMAL_TRIP_CRITICAL;
+ else if (trip_type == THROTTLE_ACTIVE)
+ *type = THERMAL_TRIP_ACTIVE;
+ else if (trip_type == THROTTLE_PASSIVE)
+ *type = THERMAL_TRIP_PASSIVE;
+ else
+ return -EINVAL;
+
+ return 0;
+}
+
+/* Get trip temperature callback functions for thermal zone */
+static int exynos_get_trip_temp(struct thermal_zone_device *thermal, int trip,
+ unsigned long *temp)
+{
+ struct exynos_thermal_zone *th_zone = thermal->devdata;
+ int max_trip = th_zone->sensor_conf->trip_data.trip_count;
+
+ if (trip < 0 || trip >= max_trip)
+ return -EINVAL;
+
+ *temp = th_zone->sensor_conf->trip_data.trip_val[trip];
+ /* convert the temperature into millicelsius */
+ *temp = *temp * MCELSIUS;
+
+ return 0;
+}
+
+/* Get critical temperature callback functions for thermal zone */
+static int exynos_get_crit_temp(struct thermal_zone_device *thermal,
+ unsigned long *temp)
+{
+ struct exynos_thermal_zone *th_zone = thermal->devdata;
+ int max_trip = th_zone->sensor_conf->trip_data.trip_count;
+ /* Get the temp of highest trip*/
+ return exynos_get_trip_temp(thermal, max_trip - 1, temp);
+}
+
+/* Bind callback functions for thermal zone */
+static int exynos_bind(struct thermal_zone_device *thermal,
+ struct thermal_cooling_device *cdev)
+{
+ int ret = 0, i, tab_size, level;
+ struct freq_clip_table *tab_ptr, *clip_data;
+ struct exynos_thermal_zone *th_zone = thermal->devdata;
+ struct thermal_sensor_conf *data = th_zone->sensor_conf;
+
+ tab_ptr = (struct freq_clip_table *)data->cooling_data.freq_data;
+ tab_size = data->cooling_data.freq_clip_count;
+
+ if (tab_ptr == NULL || tab_size == 0)
+ return 0;
+
+ /* find the cooling device registered*/
+ for (i = 0; i < th_zone->cool_dev_size; i++)
+ if (cdev == th_zone->cool_dev[i])
+ break;
+
+ /* No matching cooling device */
+ if (i == th_zone->cool_dev_size)
+ return 0;
+
+ /* Bind the thermal zone to the cpufreq cooling device */
+ for (i = 0; i < tab_size; i++) {
+ clip_data = (struct freq_clip_table *)&(tab_ptr[i]);
+ level = cpufreq_cooling_get_level(0, clip_data->freq_clip_max);
+ if (level == THERMAL_CSTATE_INVALID)
+ return 0;
+ switch (GET_ZONE(i)) {
+ case MONITOR_ZONE:
+ case WARN_ZONE:
+ if (thermal_zone_bind_cooling_device(thermal, i, cdev,
+ level, 0)) {
+ dev_err(data->dev,
+ "error unbinding cdev inst=%d\n", i);
+ ret = -EINVAL;
+ }
+ th_zone->bind = true;
+ break;
+ default:
+ ret = -EINVAL;
+ }
+ }
+
+ return ret;
+}
+
+/* Unbind callback functions for thermal zone */
+static int exynos_unbind(struct thermal_zone_device *thermal,
+ struct thermal_cooling_device *cdev)
+{
+ int ret = 0, i, tab_size;
+ struct exynos_thermal_zone *th_zone = thermal->devdata;
+ struct thermal_sensor_conf *data = th_zone->sensor_conf;
+
+ if (th_zone->bind == false)
+ return 0;
+
+ tab_size = data->cooling_data.freq_clip_count;
+
+ if (tab_size == 0)
+ return 0;
+
+ /* find the cooling device registered*/
+ for (i = 0; i < th_zone->cool_dev_size; i++)
+ if (cdev == th_zone->cool_dev[i])
+ break;
+
+ /* No matching cooling device */
+ if (i == th_zone->cool_dev_size)
+ return 0;
+
+ /* Bind the thermal zone to the cpufreq cooling device */
+ for (i = 0; i < tab_size; i++) {
+ switch (GET_ZONE(i)) {
+ case MONITOR_ZONE:
+ case WARN_ZONE:
+ if (thermal_zone_unbind_cooling_device(thermal, i,
+ cdev)) {
+ dev_err(data->dev,
+ "error unbinding cdev inst=%d\n", i);
+ ret = -EINVAL;
+ }
+ th_zone->bind = false;
+ break;
+ default:
+ ret = -EINVAL;
+ }
+ }
+ return ret;
+}
+
+/* Get temperature callback functions for thermal zone */
+static int exynos_get_temp(struct thermal_zone_device *thermal,
+ unsigned long *temp)
+{
+ struct exynos_thermal_zone *th_zone = thermal->devdata;
+ void *data;
+
+ if (!th_zone->sensor_conf) {
+ dev_err(&thermal->device,
+ "Temperature sensor not initialised\n");
+ return -EINVAL;
+ }
+ data = th_zone->sensor_conf->driver_data;
+ *temp = th_zone->sensor_conf->read_temperature(data);
+ /* convert the temperature into millicelsius */
+ *temp = *temp * MCELSIUS;
+ return 0;
+}
+
+/* Get temperature callback functions for thermal zone */
+static int exynos_set_emul_temp(struct thermal_zone_device *thermal,
+ unsigned long temp)
+{
+ void *data;
+ int ret = -EINVAL;
+ struct exynos_thermal_zone *th_zone = thermal->devdata;
+
+ if (!th_zone->sensor_conf) {
+ dev_err(&thermal->device,
+ "Temperature sensor not initialised\n");
+ return -EINVAL;
+ }
+ data = th_zone->sensor_conf->driver_data;
+ if (th_zone->sensor_conf->write_emul_temp)
+ ret = th_zone->sensor_conf->write_emul_temp(data, temp);
+ return ret;
+}
+
+/* Get the temperature trend */
+static int exynos_get_trend(struct thermal_zone_device *thermal,
+ int trip, enum thermal_trend *trend)
+{
+ int ret;
+ unsigned long trip_temp;
+
+ ret = exynos_get_trip_temp(thermal, trip, &trip_temp);
+ if (ret < 0)
+ return ret;
+
+ if (thermal->temperature >= trip_temp)
+ *trend = THERMAL_TREND_RAISE_FULL;
+ else
+ *trend = THERMAL_TREND_DROP_FULL;
+
+ return 0;
+}
+/* Operation callback functions for thermal zone */
+static struct thermal_zone_device_ops const exynos_dev_ops = {
+ .bind = exynos_bind,
+ .unbind = exynos_unbind,
+ .get_temp = exynos_get_temp,
+ .set_emul_temp = exynos_set_emul_temp,
+ .get_trend = exynos_get_trend,
+ .get_mode = exynos_get_mode,
+ .set_mode = exynos_set_mode,
+ .get_trip_type = exynos_get_trip_type,
+ .get_trip_temp = exynos_get_trip_temp,
+ .get_crit_temp = exynos_get_crit_temp,
+};
+
+/*
+ * This function may be called from interrupt based temperature sensor
+ * when threshold is changed.
+ */
+void exynos_report_trigger(struct thermal_sensor_conf *conf)
+{
+ unsigned int i;
+ char data[10];
+ char *envp[] = { data, NULL };
+ struct exynos_thermal_zone *th_zone;
+
+ if (!conf || !conf->pzone_data) {
+ pr_err("Invalid temperature sensor configuration data\n");
+ return;
+ }
+
+ th_zone = conf->pzone_data;
+ if (th_zone->therm_dev)
+ return;
+
+ if (th_zone->bind == false) {
+ for (i = 0; i < th_zone->cool_dev_size; i++) {
+ if (!th_zone->cool_dev[i])
+ continue;
+ exynos_bind(th_zone->therm_dev,
+ th_zone->cool_dev[i]);
+ }
+ }
+
+ thermal_zone_device_update(th_zone->therm_dev);
+
+ mutex_lock(&th_zone->therm_dev->lock);
+ /* Find the level for which trip happened */
+ for (i = 0; i < th_zone->sensor_conf->trip_data.trip_count; i++) {
+ if (th_zone->therm_dev->last_temperature <
+ th_zone->sensor_conf->trip_data.trip_val[i] * MCELSIUS)
+ break;
+ }
+
+ if (th_zone->mode == THERMAL_DEVICE_ENABLED &&
+ !th_zone->sensor_conf->trip_data.trigger_falling) {
+ if (i > 0)
+ th_zone->therm_dev->polling_delay = ACTIVE_INTERVAL;
+ else
+ th_zone->therm_dev->polling_delay = IDLE_INTERVAL;
+ }
+
+ snprintf(data, sizeof(data), "%u", i);
+ kobject_uevent_env(&th_zone->therm_dev->device.kobj, KOBJ_CHANGE, envp);
+ mutex_unlock(&th_zone->therm_dev->lock);
+}
+
+/* Register with the in-kernel thermal management */
+int exynos_register_thermal(struct thermal_sensor_conf *sensor_conf)
+{
+ int ret;
+ struct cpumask mask_val;
+ struct exynos_thermal_zone *th_zone;
+
+ if (!sensor_conf || !sensor_conf->read_temperature) {
+ pr_err("Temperature sensor not initialised\n");
+ return -EINVAL;
+ }
+
+ th_zone = devm_kzalloc(sensor_conf->dev,
+ sizeof(struct exynos_thermal_zone), GFP_KERNEL);
+ if (!th_zone)
+ return -ENOMEM;
+
+ th_zone->sensor_conf = sensor_conf;
+ /*
+ * TODO: 1) Handle multiple cooling devices in a thermal zone
+ * 2) Add a flag/name in cooling info to map to specific
+ * sensor
+ */
+ if (sensor_conf->cooling_data.freq_clip_count > 0) {
+ cpumask_set_cpu(0, &mask_val);
+ th_zone->cool_dev[th_zone->cool_dev_size] =
+ cpufreq_cooling_register(&mask_val);
+ if (IS_ERR(th_zone->cool_dev[th_zone->cool_dev_size])) {
+ dev_err(sensor_conf->dev,
+ "Failed to register cpufreq cooling device\n");
+ ret = -EINVAL;
+ goto err_unregister;
+ }
+ th_zone->cool_dev_size++;
+ }
+
+ th_zone->therm_dev = thermal_zone_device_register(
+ sensor_conf->name, sensor_conf->trip_data.trip_count,
+ 0, th_zone, &exynos_dev_ops, NULL, 0,
+ sensor_conf->trip_data.trigger_falling ? 0 :
+ IDLE_INTERVAL);
+
+ if (IS_ERR(th_zone->therm_dev)) {
+ dev_err(sensor_conf->dev,
+ "Failed to register thermal zone device\n");
+ ret = PTR_ERR(th_zone->therm_dev);
+ goto err_unregister;
+ }
+ th_zone->mode = THERMAL_DEVICE_ENABLED;
+ sensor_conf->pzone_data = th_zone;
+
+ dev_info(sensor_conf->dev,
+ "Exynos: Thermal zone(%s) registered\n", sensor_conf->name);
+
+ return 0;
+
+err_unregister:
+ exynos_unregister_thermal(sensor_conf);
+ return ret;
+}
+
+/* Un-Register with the in-kernel thermal management */
+void exynos_unregister_thermal(struct thermal_sensor_conf *sensor_conf)
+{
+ int i;
+ struct exynos_thermal_zone *th_zone;
+
+ if (!sensor_conf || !sensor_conf->pzone_data) {
+ pr_err("Invalid temperature sensor configuration data\n");
+ return;
+ }
+
+ th_zone = sensor_conf->pzone_data;
+
+ if (th_zone->therm_dev)
+ thermal_zone_device_unregister(th_zone->therm_dev);
+
+ for (i = 0; i < th_zone->cool_dev_size; i++) {
+ if (th_zone->cool_dev[i])
+ cpufreq_cooling_unregister(th_zone->cool_dev[i]);
+ }
+
+ dev_info(sensor_conf->dev,
+ "Exynos: Kernel Thermal management unregistered\n");
+}
diff --git a/drivers/thermal/samsung/exynos_thermal_common.h b/drivers/thermal/samsung/exynos_thermal_common.h
new file mode 100644
index 0000000..3eb2ed9
--- /dev/null
+++ b/drivers/thermal/samsung/exynos_thermal_common.h
@@ -0,0 +1,107 @@
+/*
+ * exynos_thermal_common.h - Samsung EXYNOS common header file
+ *
+ * Copyright (C) 2013 Samsung Electronics
+ * Amit Daniel Kachhap <amit.daniel@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ *
+ */
+
+#ifndef _EXYNOS_THERMAL_COMMON_H
+#define _EXYNOS_THERMAL_COMMON_H
+
+/* In-kernel thermal framework related macros & definations */
+#define SENSOR_NAME_LEN 16
+#define MAX_TRIP_COUNT 8
+#define MAX_COOLING_DEVICE 4
+#define MAX_THRESHOLD_LEVS 5
+
+#define ACTIVE_INTERVAL 500
+#define IDLE_INTERVAL 10000
+#define MCELSIUS 1000
+
+/* CPU Zone information */
+#define PANIC_ZONE 4
+#define WARN_ZONE 3
+#define MONITOR_ZONE 2
+#define SAFE_ZONE 1
+
+#define GET_ZONE(trip) (trip + 2)
+#define GET_TRIP(zone) (zone - 2)
+
+enum trigger_type {
+ THROTTLE_ACTIVE = 1,
+ THROTTLE_PASSIVE,
+ SW_TRIP,
+ HW_TRIP,
+};
+
+/**
+ * struct freq_clip_table
+ * @freq_clip_max: maximum frequency allowed for this cooling state.
+ * @temp_level: Temperature level at which the temperature clipping will
+ * happen.
+ * @mask_val: cpumask of the allowed cpu's where the clipping will take place.
+ *
+ * This structure is required to be filled and passed to the
+ * cpufreq_cooling_unregister function.
+ */
+struct freq_clip_table {
+ unsigned int freq_clip_max;
+ unsigned int temp_level;
+ const struct cpumask *mask_val;
+};
+
+struct thermal_trip_point_conf {
+ int trip_val[MAX_TRIP_COUNT];
+ int trip_type[MAX_TRIP_COUNT];
+ int trip_count;
+ unsigned char trigger_falling;
+};
+
+struct thermal_cooling_conf {
+ struct freq_clip_table freq_data[MAX_TRIP_COUNT];
+ int freq_clip_count;
+};
+
+struct thermal_sensor_conf {
+ char name[SENSOR_NAME_LEN];
+ int (*read_temperature)(void *data);
+ int (*write_emul_temp)(void *drv_data, unsigned long temp);
+ struct thermal_trip_point_conf trip_data;
+ struct thermal_cooling_conf cooling_data;
+ void *driver_data;
+ void *pzone_data;
+ struct device *dev;
+};
+
+/*Functions used exynos based thermal sensor driver*/
+#ifdef CONFIG_EXYNOS_THERMAL_CORE
+void exynos_unregister_thermal(struct thermal_sensor_conf *sensor_conf);
+int exynos_register_thermal(struct thermal_sensor_conf *sensor_conf);
+void exynos_report_trigger(struct thermal_sensor_conf *sensor_conf);
+#else
+static inline void
+exynos_unregister_thermal(struct thermal_sensor_conf *sensor_conf) { return; }
+
+static inline int
+exynos_register_thermal(struct thermal_sensor_conf *sensor_conf) { return 0; }
+
+static inline void
+exynos_report_trigger(struct thermal_sensor_conf *sensor_conf) { return; }
+
+#endif /* CONFIG_EXYNOS_THERMAL_CORE */
+#endif /* _EXYNOS_THERMAL_COMMON_H */
diff --git a/drivers/thermal/samsung/exynos_tmu.c b/drivers/thermal/samsung/exynos_tmu.c
new file mode 100644
index 0000000..b43afda
--- /dev/null
+++ b/drivers/thermal/samsung/exynos_tmu.c
@@ -0,0 +1,762 @@
+/*
+ * exynos_tmu.c - Samsung EXYNOS TMU (Thermal Management Unit)
+ *
+ * Copyright (C) 2011 Samsung Electronics
+ * Donggeun Kim <dg77.kim@samsung.com>
+ * Amit Daniel Kachhap <amit.kachhap@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ *
+ */
+
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/platform_device.h>
+#include <linux/regulator/consumer.h>
+
+#include "exynos_thermal_common.h"
+#include "exynos_tmu.h"
+#include "exynos_tmu_data.h"
+
+/**
+ * struct exynos_tmu_data : A structure to hold the private data of the TMU
+ driver
+ * @id: identifier of the one instance of the TMU controller.
+ * @pdata: pointer to the tmu platform/configuration data
+ * @base: base address of the single instance of the TMU controller.
+ * @base_common: base address of the common registers of the TMU controller.
+ * @irq: irq number of the TMU controller.
+ * @soc: id of the SOC type.
+ * @irq_work: pointer to the irq work structure.
+ * @lock: lock to implement synchronization.
+ * @clk: pointer to the clock structure.
+ * @temp_error1: fused value of the first point trim.
+ * @temp_error2: fused value of the second point trim.
+ * @regulator: pointer to the TMU regulator structure.
+ * @reg_conf: pointer to structure to register with core thermal.
+ */
+struct exynos_tmu_data {
+ int id;
+ struct exynos_tmu_platform_data *pdata;
+ void __iomem *base;
+ void __iomem *base_common;
+ int irq;
+ enum soc_type soc;
+ struct work_struct irq_work;
+ struct mutex lock;
+ struct clk *clk;
+ u8 temp_error1, temp_error2;
+ struct regulator *regulator;
+ struct thermal_sensor_conf *reg_conf;
+};
+
+/*
+ * TMU treats temperature as a mapped temperature code.
+ * The temperature is converted differently depending on the calibration type.
+ */
+static int temp_to_code(struct exynos_tmu_data *data, u8 temp)
+{
+ struct exynos_tmu_platform_data *pdata = data->pdata;
+ int temp_code;
+
+ if (pdata->cal_mode == HW_MODE)
+ return temp;
+
+ if (data->soc == SOC_ARCH_EXYNOS4210)
+ /* temp should range between 25 and 125 */
+ if (temp < 25 || temp > 125) {
+ temp_code = -EINVAL;
+ goto out;
+ }
+
+ switch (pdata->cal_type) {
+ case TYPE_TWO_POINT_TRIMMING:
+ temp_code = (temp - pdata->first_point_trim) *
+ (data->temp_error2 - data->temp_error1) /
+ (pdata->second_point_trim - pdata->first_point_trim) +
+ data->temp_error1;
+ break;
+ case TYPE_ONE_POINT_TRIMMING:
+ temp_code = temp + data->temp_error1 - pdata->first_point_trim;
+ break;
+ default:
+ temp_code = temp + pdata->default_temp_offset;
+ break;
+ }
+out:
+ return temp_code;
+}
+
+/*
+ * Calculate a temperature value from a temperature code.
+ * The unit of the temperature is degree Celsius.
+ */
+static int code_to_temp(struct exynos_tmu_data *data, u8 temp_code)
+{
+ struct exynos_tmu_platform_data *pdata = data->pdata;
+ int temp;
+
+ if (pdata->cal_mode == HW_MODE)
+ return temp_code;
+
+ if (data->soc == SOC_ARCH_EXYNOS4210)
+ /* temp_code should range between 75 and 175 */
+ if (temp_code < 75 || temp_code > 175) {
+ temp = -ENODATA;
+ goto out;
+ }
+
+ switch (pdata->cal_type) {
+ case TYPE_TWO_POINT_TRIMMING:
+ temp = (temp_code - data->temp_error1) *
+ (pdata->second_point_trim - pdata->first_point_trim) /
+ (data->temp_error2 - data->temp_error1) +
+ pdata->first_point_trim;
+ break;
+ case TYPE_ONE_POINT_TRIMMING:
+ temp = temp_code - data->temp_error1 + pdata->first_point_trim;
+ break;
+ default:
+ temp = temp_code - pdata->default_temp_offset;
+ break;
+ }
+out:
+ return temp;
+}
+
+static int exynos_tmu_initialize(struct platform_device *pdev)
+{
+ struct exynos_tmu_data *data = platform_get_drvdata(pdev);
+ struct exynos_tmu_platform_data *pdata = data->pdata;
+ const struct exynos_tmu_registers *reg = pdata->registers;
+ unsigned int status, trim_info = 0, con;
+ unsigned int rising_threshold = 0, falling_threshold = 0;
+ int ret = 0, threshold_code, i, trigger_levs = 0;
+
+ mutex_lock(&data->lock);
+ clk_enable(data->clk);
+
+ if (TMU_SUPPORTS(pdata, READY_STATUS)) {
+ status = readb(data->base + reg->tmu_status);
+ if (!status) {
+ ret = -EBUSY;
+ goto out;
+ }
+ }
+
+ if (TMU_SUPPORTS(pdata, TRIM_RELOAD))
+ __raw_writel(1, data->base + reg->triminfo_ctrl);
+
+ if (pdata->cal_mode == HW_MODE)
+ goto skip_calib_data;
+
+ /* Save trimming info in order to perform calibration */
+ if (data->soc == SOC_ARCH_EXYNOS5440) {
+ /*
+ * For exynos5440 soc triminfo value is swapped between TMU0 and
+ * TMU2, so the below logic is needed.
+ */
+ switch (data->id) {
+ case 0:
+ trim_info = readl(data->base +
+ EXYNOS5440_EFUSE_SWAP_OFFSET + reg->triminfo_data);
+ break;
+ case 1:
+ trim_info = readl(data->base + reg->triminfo_data);
+ break;
+ case 2:
+ trim_info = readl(data->base -
+ EXYNOS5440_EFUSE_SWAP_OFFSET + reg->triminfo_data);
+ }
+ } else {
+ trim_info = readl(data->base + reg->triminfo_data);
+ }
+ data->temp_error1 = trim_info & EXYNOS_TMU_TEMP_MASK;
+ data->temp_error2 = ((trim_info >> reg->triminfo_85_shift) &
+ EXYNOS_TMU_TEMP_MASK);
+
+ if (!data->temp_error1 ||
+ (pdata->min_efuse_value > data->temp_error1) ||
+ (data->temp_error1 > pdata->max_efuse_value))
+ data->temp_error1 = pdata->efuse_value & EXYNOS_TMU_TEMP_MASK;
+
+ if (!data->temp_error2)
+ data->temp_error2 =
+ (pdata->efuse_value >> reg->triminfo_85_shift) &
+ EXYNOS_TMU_TEMP_MASK;
+
+skip_calib_data:
+ if (pdata->max_trigger_level > MAX_THRESHOLD_LEVS) {
+ dev_err(&pdev->dev, "Invalid max trigger level\n");
+ goto out;
+ }
+
+ for (i = 0; i < pdata->max_trigger_level; i++) {
+ if (!pdata->trigger_levels[i])
+ continue;
+
+ if ((pdata->trigger_type[i] == HW_TRIP) &&
+ (!pdata->trigger_levels[pdata->max_trigger_level - 1])) {
+ dev_err(&pdev->dev, "Invalid hw trigger level\n");
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /* Count trigger levels except the HW trip*/
+ if (!(pdata->trigger_type[i] == HW_TRIP))
+ trigger_levs++;
+ }
+
+ if (data->soc == SOC_ARCH_EXYNOS4210) {
+ /* Write temperature code for threshold */
+ threshold_code = temp_to_code(data, pdata->threshold);
+ if (threshold_code < 0) {
+ ret = threshold_code;
+ goto out;
+ }
+ writeb(threshold_code,
+ data->base + reg->threshold_temp);
+ for (i = 0; i < trigger_levs; i++)
+ writeb(pdata->trigger_levels[i], data->base +
+ reg->threshold_th0 + i * sizeof(reg->threshold_th0));
+
+ writel(reg->inten_rise_mask, data->base + reg->tmu_intclear);
+ } else {
+ /* Write temperature code for rising and falling threshold */
+ for (i = 0;
+ i < trigger_levs && i < EXYNOS_MAX_TRIGGER_PER_REG; i++) {
+ threshold_code = temp_to_code(data,
+ pdata->trigger_levels[i]);
+ if (threshold_code < 0) {
+ ret = threshold_code;
+ goto out;
+ }
+ rising_threshold |= threshold_code << 8 * i;
+ if (pdata->threshold_falling) {
+ threshold_code = temp_to_code(data,
+ pdata->trigger_levels[i] -
+ pdata->threshold_falling);
+ if (threshold_code > 0)
+ falling_threshold |=
+ threshold_code << 8 * i;
+ }
+ }
+
+ writel(rising_threshold,
+ data->base + reg->threshold_th0);
+ writel(falling_threshold,
+ data->base + reg->threshold_th1);
+
+ writel((reg->inten_rise_mask << reg->inten_rise_shift) |
+ (reg->inten_fall_mask << reg->inten_fall_shift),
+ data->base + reg->tmu_intclear);
+
+ /* if last threshold limit is also present */
+ i = pdata->max_trigger_level - 1;
+ if (pdata->trigger_levels[i] &&
+ (pdata->trigger_type[i] == HW_TRIP)) {
+ threshold_code = temp_to_code(data,
+ pdata->trigger_levels[i]);
+ if (threshold_code < 0) {
+ ret = threshold_code;
+ goto out;
+ }
+ if (i == EXYNOS_MAX_TRIGGER_PER_REG - 1) {
+ /* 1-4 level to be assigned in th0 reg */
+ rising_threshold |= threshold_code << 8 * i;
+ writel(rising_threshold,
+ data->base + reg->threshold_th0);
+ } else if (i == EXYNOS_MAX_TRIGGER_PER_REG) {
+ /* 5th level to be assigned in th2 reg */
+ rising_threshold =
+ threshold_code << reg->threshold_th3_l0_shift;
+ writel(rising_threshold,
+ data->base + reg->threshold_th2);
+ }
+ con = readl(data->base + reg->tmu_ctrl);
+ con |= (1 << reg->therm_trip_en_shift);
+ writel(con, data->base + reg->tmu_ctrl);
+ }
+ }
+ /*Clear the PMIN in the common TMU register*/
+ if (reg->tmu_pmin && !data->id)
+ writel(0, data->base_common + reg->tmu_pmin);
+out:
+ clk_disable(data->clk);
+ mutex_unlock(&data->lock);
+
+ return ret;
+}
+
+static void exynos_tmu_control(struct platform_device *pdev, bool on)
+{
+ struct exynos_tmu_data *data = platform_get_drvdata(pdev);
+ struct exynos_tmu_platform_data *pdata = data->pdata;
+ const struct exynos_tmu_registers *reg = pdata->registers;
+ unsigned int con, interrupt_en, cal_val;
+
+ mutex_lock(&data->lock);
+ clk_enable(data->clk);
+
+ con = readl(data->base + reg->tmu_ctrl);
+
+ if (pdata->reference_voltage) {
+ con &= ~(reg->buf_vref_sel_mask << reg->buf_vref_sel_shift);
+ con |= pdata->reference_voltage << reg->buf_vref_sel_shift;
+ }
+
+ if (pdata->gain) {
+ con &= ~(reg->buf_slope_sel_mask << reg->buf_slope_sel_shift);
+ con |= (pdata->gain << reg->buf_slope_sel_shift);
+ }
+
+ if (pdata->noise_cancel_mode) {
+ con &= ~(reg->therm_trip_mode_mask <<
+ reg->therm_trip_mode_shift);
+ con |= (pdata->noise_cancel_mode << reg->therm_trip_mode_shift);
+ }
+
+ if (pdata->cal_mode == HW_MODE) {
+ con &= ~(reg->calib_mode_mask << reg->calib_mode_shift);
+ cal_val = 0;
+ switch (pdata->cal_type) {
+ case TYPE_TWO_POINT_TRIMMING:
+ cal_val = 3;
+ break;
+ case TYPE_ONE_POINT_TRIMMING_85:
+ cal_val = 2;
+ break;
+ case TYPE_ONE_POINT_TRIMMING_25:
+ cal_val = 1;
+ break;
+ case TYPE_NONE:
+ break;
+ default:
+ dev_err(&pdev->dev, "Invalid calibration type, using none\n");
+ }
+ con |= cal_val << reg->calib_mode_shift;
+ }
+
+ if (on) {
+ con |= (1 << reg->core_en_shift);
+ interrupt_en =
+ pdata->trigger_enable[3] << reg->inten_rise3_shift |
+ pdata->trigger_enable[2] << reg->inten_rise2_shift |
+ pdata->trigger_enable[1] << reg->inten_rise1_shift |
+ pdata->trigger_enable[0] << reg->inten_rise0_shift;
+ if (TMU_SUPPORTS(pdata, FALLING_TRIP))
+ interrupt_en |=
+ interrupt_en << reg->inten_fall0_shift;
+ } else {
+ con &= ~(1 << reg->core_en_shift);
+ interrupt_en = 0; /* Disable all interrupts */
+ }
+ writel(interrupt_en, data->base + reg->tmu_inten);
+ writel(con, data->base + reg->tmu_ctrl);
+
+ clk_disable(data->clk);
+ mutex_unlock(&data->lock);
+}
+
+static int exynos_tmu_read(struct exynos_tmu_data *data)
+{
+ struct exynos_tmu_platform_data *pdata = data->pdata;
+ const struct exynos_tmu_registers *reg = pdata->registers;
+ u8 temp_code;
+ int temp;
+
+ mutex_lock(&data->lock);
+ clk_enable(data->clk);
+
+ temp_code = readb(data->base + reg->tmu_cur_temp);
+ temp = code_to_temp(data, temp_code);
+
+ clk_disable(data->clk);
+ mutex_unlock(&data->lock);
+
+ return temp;
+}
+
+#ifdef CONFIG_THERMAL_EMULATION
+static int exynos_tmu_set_emulation(void *drv_data, unsigned long temp)
+{
+ struct exynos_tmu_data *data = drv_data;
+ struct exynos_tmu_platform_data *pdata = data->pdata;
+ const struct exynos_tmu_registers *reg = pdata->registers;
+ unsigned int val;
+ int ret = -EINVAL;
+
+ if (!TMU_SUPPORTS(pdata, EMULATION))
+ goto out;
+
+ if (temp && temp < MCELSIUS)
+ goto out;
+
+ mutex_lock(&data->lock);
+ clk_enable(data->clk);
+
+ val = readl(data->base + reg->emul_con);
+
+ if (temp) {
+ temp /= MCELSIUS;
+
+ if (TMU_SUPPORTS(pdata, EMUL_TIME)) {
+ val &= ~(EXYNOS_EMUL_TIME_MASK << reg->emul_time_shift);
+ val |= (EXYNOS_EMUL_TIME << reg->emul_time_shift);
+ }
+ val &= ~(EXYNOS_EMUL_DATA_MASK << reg->emul_temp_shift);
+ val |= (temp_to_code(data, temp) << reg->emul_temp_shift) |
+ EXYNOS_EMUL_ENABLE;
+ } else {
+ val &= ~EXYNOS_EMUL_ENABLE;
+ }
+
+ writel(val, data->base + reg->emul_con);
+
+ clk_disable(data->clk);
+ mutex_unlock(&data->lock);
+ return 0;
+out:
+ return ret;
+}
+#else
+static int exynos_tmu_set_emulation(void *drv_data, unsigned long temp)
+ { return -EINVAL; }
+#endif/*CONFIG_THERMAL_EMULATION*/
+
+static void exynos_tmu_work(struct work_struct *work)
+{
+ struct exynos_tmu_data *data = container_of(work,
+ struct exynos_tmu_data, irq_work);
+ struct exynos_tmu_platform_data *pdata = data->pdata;
+ const struct exynos_tmu_registers *reg = pdata->registers;
+ unsigned int val_irq, val_type;
+
+ /* Find which sensor generated this interrupt */
+ if (reg->tmu_irqstatus) {
+ val_type = readl(data->base_common + reg->tmu_irqstatus);
+ if (!((val_type >> data->id) & 0x1))
+ goto out;
+ }
+
+ exynos_report_trigger(data->reg_conf);
+ mutex_lock(&data->lock);
+ clk_enable(data->clk);
+
+ /* TODO: take action based on particular interrupt */
+ val_irq = readl(data->base + reg->tmu_intstat);
+ /* clear the interrupts */
+ writel(val_irq, data->base + reg->tmu_intclear);
+
+ clk_disable(data->clk);
+ mutex_unlock(&data->lock);
+out:
+ enable_irq(data->irq);
+}
+
+static irqreturn_t exynos_tmu_irq(int irq, void *id)
+{
+ struct exynos_tmu_data *data = id;
+
+ disable_irq_nosync(irq);
+ schedule_work(&data->irq_work);
+
+ return IRQ_HANDLED;
+}
+
+static const struct of_device_id exynos_tmu_match[] = {
+ {
+ .compatible = "samsung,exynos4210-tmu",
+ .data = (void *)EXYNOS4210_TMU_DRV_DATA,
+ },
+ {
+ .compatible = "samsung,exynos4412-tmu",
+ .data = (void *)EXYNOS5250_TMU_DRV_DATA,
+ },
+ {
+ .compatible = "samsung,exynos5250-tmu",
+ .data = (void *)EXYNOS5250_TMU_DRV_DATA,
+ },
+ {
+ .compatible = "samsung,exynos5440-tmu",
+ .data = (void *)EXYNOS5440_TMU_DRV_DATA,
+ },
+ {},
+};
+MODULE_DEVICE_TABLE(of, exynos_tmu_match);
+
+static inline struct exynos_tmu_platform_data *exynos_get_driver_data(
+ struct platform_device *pdev, int id)
+{
+ struct exynos_tmu_init_data *data_table;
+ struct exynos_tmu_platform_data *tmu_data;
+ const struct of_device_id *match;
+
+ match = of_match_node(exynos_tmu_match, pdev->dev.of_node);
+ if (!match)
+ return NULL;
+ data_table = (struct exynos_tmu_init_data *) match->data;
+ if (!data_table || id >= data_table->tmu_count)
+ return NULL;
+ tmu_data = data_table->tmu_data;
+ return (struct exynos_tmu_platform_data *) (tmu_data + id);
+}
+
+static int exynos_map_dt_data(struct platform_device *pdev)
+{
+ struct exynos_tmu_data *data = platform_get_drvdata(pdev);
+ struct exynos_tmu_platform_data *pdata;
+ struct resource res;
+ int ret;
+
+ if (!data || !pdev->dev.of_node)
+ return -ENODEV;
+
+ /*
+ * Try enabling the regulator if found
+ * TODO: Add regulator as an SOC feature, so that regulator enable
+ * is a compulsory call.
+ */
+ data->regulator = devm_regulator_get(&pdev->dev, "vtmu");
+ if (!IS_ERR(data->regulator)) {
+ ret = regulator_enable(data->regulator);
+ if (ret) {
+ dev_err(&pdev->dev, "failed to enable vtmu\n");
+ return ret;
+ }
+ } else {
+ dev_info(&pdev->dev, "Regulator node (vtmu) not found\n");
+ }
+
+ data->id = of_alias_get_id(pdev->dev.of_node, "tmuctrl");
+ if (data->id < 0)
+ data->id = 0;
+
+ data->irq = irq_of_parse_and_map(pdev->dev.of_node, 0);
+ if (data->irq <= 0) {
+ dev_err(&pdev->dev, "failed to get IRQ\n");
+ return -ENODEV;
+ }
+
+ if (of_address_to_resource(pdev->dev.of_node, 0, &res)) {
+ dev_err(&pdev->dev, "failed to get Resource 0\n");
+ return -ENODEV;
+ }
+
+ data->base = devm_ioremap(&pdev->dev, res.start, resource_size(&res));
+ if (!data->base) {
+ dev_err(&pdev->dev, "Failed to ioremap memory\n");
+ return -EADDRNOTAVAIL;
+ }
+
+ pdata = exynos_get_driver_data(pdev, data->id);
+ if (!pdata) {
+ dev_err(&pdev->dev, "No platform init data supplied.\n");
+ return -ENODEV;
+ }
+ data->pdata = pdata;
+ /*
+ * Check if the TMU shares some registers and then try to map the
+ * memory of common registers.
+ */
+ if (!TMU_SUPPORTS(pdata, SHARED_MEMORY))
+ return 0;
+
+ if (of_address_to_resource(pdev->dev.of_node, 1, &res)) {
+ dev_err(&pdev->dev, "failed to get Resource 1\n");
+ return -ENODEV;
+ }
+
+ data->base_common = devm_ioremap(&pdev->dev, res.start,
+ resource_size(&res));
+ if (!data->base_common) {
+ dev_err(&pdev->dev, "Failed to ioremap memory\n");
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static int exynos_tmu_probe(struct platform_device *pdev)
+{
+ struct exynos_tmu_data *data;
+ struct exynos_tmu_platform_data *pdata;
+ struct thermal_sensor_conf *sensor_conf;
+ int ret, i;
+
+ data = devm_kzalloc(&pdev->dev, sizeof(struct exynos_tmu_data),
+ GFP_KERNEL);
+ if (!data) {
+ dev_err(&pdev->dev, "Failed to allocate driver structure\n");
+ return -ENOMEM;
+ }
+
+ platform_set_drvdata(pdev, data);
+ mutex_init(&data->lock);
+
+ ret = exynos_map_dt_data(pdev);
+ if (ret)
+ return ret;
+
+ pdata = data->pdata;
+
+ INIT_WORK(&data->irq_work, exynos_tmu_work);
+
+ data->clk = devm_clk_get(&pdev->dev, "tmu_apbif");
+ if (IS_ERR(data->clk)) {
+ dev_err(&pdev->dev, "Failed to get clock\n");
+ return PTR_ERR(data->clk);
+ }
+
+ ret = clk_prepare(data->clk);
+ if (ret)
+ return ret;
+
+ if (pdata->type == SOC_ARCH_EXYNOS ||
+ pdata->type == SOC_ARCH_EXYNOS4210 ||
+ pdata->type == SOC_ARCH_EXYNOS5440)
+ data->soc = pdata->type;
+ else {
+ ret = -EINVAL;
+ dev_err(&pdev->dev, "Platform not supported\n");
+ goto err_clk;
+ }
+
+ ret = exynos_tmu_initialize(pdev);
+ if (ret) {
+ dev_err(&pdev->dev, "Failed to initialize TMU\n");
+ goto err_clk;
+ }
+
+ exynos_tmu_control(pdev, true);
+
+ /* Allocate a structure to register with the exynos core thermal */
+ sensor_conf = devm_kzalloc(&pdev->dev,
+ sizeof(struct thermal_sensor_conf), GFP_KERNEL);
+ if (!sensor_conf) {
+ dev_err(&pdev->dev, "Failed to allocate registration struct\n");
+ ret = -ENOMEM;
+ goto err_clk;
+ }
+ sprintf(sensor_conf->name, "therm_zone%d", data->id);
+ sensor_conf->read_temperature = (int (*)(void *))exynos_tmu_read;
+ sensor_conf->write_emul_temp =
+ (int (*)(void *, unsigned long))exynos_tmu_set_emulation;
+ sensor_conf->driver_data = data;
+ sensor_conf->trip_data.trip_count = pdata->trigger_enable[0] +
+ pdata->trigger_enable[1] + pdata->trigger_enable[2]+
+ pdata->trigger_enable[3];
+
+ for (i = 0; i < sensor_conf->trip_data.trip_count; i++) {
+ sensor_conf->trip_data.trip_val[i] =
+ pdata->threshold + pdata->trigger_levels[i];
+ sensor_conf->trip_data.trip_type[i] =
+ pdata->trigger_type[i];
+ }
+
+ sensor_conf->trip_data.trigger_falling = pdata->threshold_falling;
+
+ sensor_conf->cooling_data.freq_clip_count = pdata->freq_tab_count;
+ for (i = 0; i < pdata->freq_tab_count; i++) {
+ sensor_conf->cooling_data.freq_data[i].freq_clip_max =
+ pdata->freq_tab[i].freq_clip_max;
+ sensor_conf->cooling_data.freq_data[i].temp_level =
+ pdata->freq_tab[i].temp_level;
+ }
+ sensor_conf->dev = &pdev->dev;
+ /* Register the sensor with thermal management interface */
+ ret = exynos_register_thermal(sensor_conf);
+ if (ret) {
+ dev_err(&pdev->dev, "Failed to register thermal interface\n");
+ goto err_clk;
+ }
+ data->reg_conf = sensor_conf;
+
+ ret = devm_request_irq(&pdev->dev, data->irq, exynos_tmu_irq,
+ IRQF_TRIGGER_RISING | IRQF_SHARED, dev_name(&pdev->dev), data);
+ if (ret) {
+ dev_err(&pdev->dev, "Failed to request irq: %d\n", data->irq);
+ goto err_clk;
+ }
+
+ return 0;
+err_clk:
+ clk_unprepare(data->clk);
+ return ret;
+}
+
+static int exynos_tmu_remove(struct platform_device *pdev)
+{
+ struct exynos_tmu_data *data = platform_get_drvdata(pdev);
+
+ exynos_tmu_control(pdev, false);
+
+ exynos_unregister_thermal(data->reg_conf);
+
+ clk_unprepare(data->clk);
+
+ if (!IS_ERR(data->regulator))
+ regulator_disable(data->regulator);
+
+ return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int exynos_tmu_suspend(struct device *dev)
+{
+ exynos_tmu_control(to_platform_device(dev), false);
+
+ return 0;
+}
+
+static int exynos_tmu_resume(struct device *dev)
+{
+ struct platform_device *pdev = to_platform_device(dev);
+
+ exynos_tmu_initialize(pdev);
+ exynos_tmu_control(pdev, true);
+
+ return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(exynos_tmu_pm,
+ exynos_tmu_suspend, exynos_tmu_resume);
+#define EXYNOS_TMU_PM (&exynos_tmu_pm)
+#else
+#define EXYNOS_TMU_PM NULL
+#endif
+
+static struct platform_driver exynos_tmu_driver = {
+ .driver = {
+ .name = "exynos-tmu",
+ .owner = THIS_MODULE,
+ .pm = EXYNOS_TMU_PM,
+ .of_match_table = exynos_tmu_match,
+ },
+ .probe = exynos_tmu_probe,
+ .remove = exynos_tmu_remove,
+};
+
+module_platform_driver(exynos_tmu_driver);
+
+MODULE_DESCRIPTION("EXYNOS TMU Driver");
+MODULE_AUTHOR("Donggeun Kim <dg77.kim@samsung.com>");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:exynos-tmu");
diff --git a/drivers/thermal/samsung/exynos_tmu.h b/drivers/thermal/samsung/exynos_tmu.h
new file mode 100644
index 0000000..b364c9e
--- /dev/null
+++ b/drivers/thermal/samsung/exynos_tmu.h
@@ -0,0 +1,311 @@
+/*
+ * exynos_tmu.h - Samsung EXYNOS TMU (Thermal Management Unit)
+ *
+ * Copyright (C) 2011 Samsung Electronics
+ * Donggeun Kim <dg77.kim@samsung.com>
+ * Amit Daniel Kachhap <amit.daniel@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef _EXYNOS_TMU_H
+#define _EXYNOS_TMU_H
+#include <linux/cpu_cooling.h>
+
+#include "exynos_thermal_common.h"
+
+enum calibration_type {
+ TYPE_ONE_POINT_TRIMMING,
+ TYPE_ONE_POINT_TRIMMING_25,
+ TYPE_ONE_POINT_TRIMMING_85,
+ TYPE_TWO_POINT_TRIMMING,
+ TYPE_NONE,
+};
+
+enum calibration_mode {
+ SW_MODE,
+ HW_MODE,
+};
+
+enum soc_type {
+ SOC_ARCH_EXYNOS4210 = 1,
+ SOC_ARCH_EXYNOS,
+ SOC_ARCH_EXYNOS5440,
+};
+
+/**
+ * EXYNOS TMU supported features.
+ * TMU_SUPPORT_EMULATION - This features is used to set user defined
+ * temperature to the TMU controller.
+ * TMU_SUPPORT_MULTI_INST - This features denotes that the soc
+ * has many instances of TMU.
+ * TMU_SUPPORT_TRIM_RELOAD - This features shows that trimming can
+ * be reloaded.
+ * TMU_SUPPORT_FALLING_TRIP - This features shows that interrupt can
+ * be registered for falling trips also.
+ * TMU_SUPPORT_READY_STATUS - This feature tells that the TMU current
+ * state(active/idle) can be checked.
+ * TMU_SUPPORT_EMUL_TIME - This features allows to set next temp emulation
+ * sample time.
+ * TMU_SUPPORT_SHARED_MEMORY - This feature tells that the different TMU
+ * sensors shares some common registers.
+ * TMU_SUPPORT - macro to compare the above features with the supplied.
+ */
+#define TMU_SUPPORT_EMULATION BIT(0)
+#define TMU_SUPPORT_MULTI_INST BIT(1)
+#define TMU_SUPPORT_TRIM_RELOAD BIT(2)
+#define TMU_SUPPORT_FALLING_TRIP BIT(3)
+#define TMU_SUPPORT_READY_STATUS BIT(4)
+#define TMU_SUPPORT_EMUL_TIME BIT(5)
+#define TMU_SUPPORT_SHARED_MEMORY BIT(6)
+
+#define TMU_SUPPORTS(a, b) (a->features & TMU_SUPPORT_ ## b)
+
+/**
+ * struct exynos_tmu_register - register descriptors to access registers and
+ * bitfields. The register validity, offsets and bitfield values may vary
+ * slightly across different exynos SOC's.
+ * @triminfo_data: register containing 2 pont trimming data
+ * @triminfo_25_shift: shift bit of the 25 C trim value in triminfo_data reg.
+ * @triminfo_85_shift: shift bit of the 85 C trim value in triminfo_data reg.
+ * @triminfo_ctrl: trim info controller register.
+ * @triminfo_reload_shift: shift of triminfo reload enable bit in triminfo_ctrl
+ reg.
+ * @tmu_ctrl: TMU main controller register.
+ * @buf_vref_sel_shift: shift bits of reference voltage in tmu_ctrl register.
+ * @buf_vref_sel_mask: mask bits of reference voltage in tmu_ctrl register.
+ * @therm_trip_mode_shift: shift bits of tripping mode in tmu_ctrl register.
+ * @therm_trip_mode_mask: mask bits of tripping mode in tmu_ctrl register.
+ * @therm_trip_en_shift: shift bits of tripping enable in tmu_ctrl register.
+ * @buf_slope_sel_shift: shift bits of amplifier gain value in tmu_ctrl
+ register.
+ * @buf_slope_sel_mask: mask bits of amplifier gain value in tmu_ctrl register.
+ * @calib_mode_shift: shift bits of calibration mode value in tmu_ctrl
+ register.
+ * @calib_mode_mask: mask bits of calibration mode value in tmu_ctrl
+ register.
+ * @therm_trip_tq_en_shift: shift bits of thermal trip enable by TQ pin in
+ tmu_ctrl register.
+ * @core_en_shift: shift bits of TMU core enable bit in tmu_ctrl register.
+ * @tmu_status: register drescribing the TMU status.
+ * @tmu_cur_temp: register containing the current temperature of the TMU.
+ * @tmu_cur_temp_shift: shift bits of current temp value in tmu_cur_temp
+ register.
+ * @threshold_temp: register containing the base threshold level.
+ * @threshold_th0: Register containing first set of rising levels.
+ * @threshold_th0_l0_shift: shift bits of level0 threshold temperature.
+ * @threshold_th0_l1_shift: shift bits of level1 threshold temperature.
+ * @threshold_th0_l2_shift: shift bits of level2 threshold temperature.
+ * @threshold_th0_l3_shift: shift bits of level3 threshold temperature.
+ * @threshold_th1: Register containing second set of rising levels.
+ * @threshold_th1_l0_shift: shift bits of level0 threshold temperature.
+ * @threshold_th1_l1_shift: shift bits of level1 threshold temperature.
+ * @threshold_th1_l2_shift: shift bits of level2 threshold temperature.
+ * @threshold_th1_l3_shift: shift bits of level3 threshold temperature.
+ * @threshold_th2: Register containing third set of rising levels.
+ * @threshold_th2_l0_shift: shift bits of level0 threshold temperature.
+ * @threshold_th3: Register containing fourth set of rising levels.
+ * @threshold_th3_l0_shift: shift bits of level0 threshold temperature.
+ * @tmu_inten: register containing the different threshold interrupt
+ enable bits.
+ * @inten_rise_shift: shift bits of all rising interrupt bits.
+ * @inten_rise_mask: mask bits of all rising interrupt bits.
+ * @inten_fall_shift: shift bits of all rising interrupt bits.
+ * @inten_fall_mask: mask bits of all rising interrupt bits.
+ * @inten_rise0_shift: shift bits of rising 0 interrupt bits.
+ * @inten_rise1_shift: shift bits of rising 1 interrupt bits.
+ * @inten_rise2_shift: shift bits of rising 2 interrupt bits.
+ * @inten_rise3_shift: shift bits of rising 3 interrupt bits.
+ * @inten_fall0_shift: shift bits of falling 0 interrupt bits.
+ * @inten_fall1_shift: shift bits of falling 1 interrupt bits.
+ * @inten_fall2_shift: shift bits of falling 2 interrupt bits.
+ * @inten_fall3_shift: shift bits of falling 3 interrupt bits.
+ * @tmu_intstat: Register containing the interrupt status values.
+ * @tmu_intclear: Register for clearing the raised interrupt status.
+ * @emul_con: TMU emulation controller register.
+ * @emul_temp_shift: shift bits of emulation temperature.
+ * @emul_time_shift: shift bits of emulation time.
+ * @emul_time_mask: mask bits of emulation time.
+ * @tmu_irqstatus: register to find which TMU generated interrupts.
+ * @tmu_pmin: register to get/set the Pmin value.
+ */
+struct exynos_tmu_registers {
+ u32 triminfo_data;
+ u32 triminfo_25_shift;
+ u32 triminfo_85_shift;
+
+ u32 triminfo_ctrl;
+ u32 triminfo_reload_shift;
+
+ u32 tmu_ctrl;
+ u32 buf_vref_sel_shift;
+ u32 buf_vref_sel_mask;
+ u32 therm_trip_mode_shift;
+ u32 therm_trip_mode_mask;
+ u32 therm_trip_en_shift;
+ u32 buf_slope_sel_shift;
+ u32 buf_slope_sel_mask;
+ u32 calib_mode_shift;
+ u32 calib_mode_mask;
+ u32 therm_trip_tq_en_shift;
+ u32 core_en_shift;
+
+ u32 tmu_status;
+
+ u32 tmu_cur_temp;
+ u32 tmu_cur_temp_shift;
+
+ u32 threshold_temp;
+
+ u32 threshold_th0;
+ u32 threshold_th0_l0_shift;
+ u32 threshold_th0_l1_shift;
+ u32 threshold_th0_l2_shift;
+ u32 threshold_th0_l3_shift;
+
+ u32 threshold_th1;
+ u32 threshold_th1_l0_shift;
+ u32 threshold_th1_l1_shift;
+ u32 threshold_th1_l2_shift;
+ u32 threshold_th1_l3_shift;
+
+ u32 threshold_th2;
+ u32 threshold_th2_l0_shift;
+
+ u32 threshold_th3;
+ u32 threshold_th3_l0_shift;
+
+ u32 tmu_inten;
+ u32 inten_rise_shift;
+ u32 inten_rise_mask;
+ u32 inten_fall_shift;
+ u32 inten_fall_mask;
+ u32 inten_rise0_shift;
+ u32 inten_rise1_shift;
+ u32 inten_rise2_shift;
+ u32 inten_rise3_shift;
+ u32 inten_fall0_shift;
+ u32 inten_fall1_shift;
+ u32 inten_fall2_shift;
+ u32 inten_fall3_shift;
+
+ u32 tmu_intstat;
+
+ u32 tmu_intclear;
+
+ u32 emul_con;
+ u32 emul_temp_shift;
+ u32 emul_time_shift;
+ u32 emul_time_mask;
+
+ u32 tmu_irqstatus;
+ u32 tmu_pmin;
+};
+
+/**
+ * struct exynos_tmu_platform_data
+ * @threshold: basic temperature for generating interrupt
+ * 25 <= threshold <= 125 [unit: degree Celsius]
+ * @threshold_falling: differntial value for setting threshold
+ * of temperature falling interrupt.
+ * @trigger_levels: array for each interrupt levels
+ * [unit: degree Celsius]
+ * 0: temperature for trigger_level0 interrupt
+ * condition for trigger_level0 interrupt:
+ * current temperature > threshold + trigger_levels[0]
+ * 1: temperature for trigger_level1 interrupt
+ * condition for trigger_level1 interrupt:
+ * current temperature > threshold + trigger_levels[1]
+ * 2: temperature for trigger_level2 interrupt
+ * condition for trigger_level2 interrupt:
+ * current temperature > threshold + trigger_levels[2]
+ * 3: temperature for trigger_level3 interrupt
+ * condition for trigger_level3 interrupt:
+ * current temperature > threshold + trigger_levels[3]
+ * @trigger_type: defines the type of trigger. Possible values are,
+ * THROTTLE_ACTIVE trigger type
+ * THROTTLE_PASSIVE trigger type
+ * SW_TRIP trigger type
+ * HW_TRIP
+ * @trigger_enable[]: array to denote which trigger levels are enabled.
+ * 1 = enable trigger_level[] interrupt,
+ * 0 = disable trigger_level[] interrupt
+ * @max_trigger_level: max trigger level supported by the TMU
+ * @gain: gain of amplifier in the positive-TC generator block
+ * 0 <= gain <= 15
+ * @reference_voltage: reference voltage of amplifier
+ * in the positive-TC generator block
+ * 0 <= reference_voltage <= 31
+ * @noise_cancel_mode: noise cancellation mode
+ * 000, 100, 101, 110 and 111 can be different modes
+ * @type: determines the type of SOC
+ * @efuse_value: platform defined fuse value
+ * @min_efuse_value: minimum valid trimming data
+ * @max_efuse_value: maximum valid trimming data
+ * @first_point_trim: temp value of the first point trimming
+ * @second_point_trim: temp value of the second point trimming
+ * @default_temp_offset: default temperature offset in case of no trimming
+ * @cal_type: calibration type for temperature
+ * @cal_mode: calibration mode for temperature
+ * @freq_clip_table: Table representing frequency reduction percentage.
+ * @freq_tab_count: Count of the above table as frequency reduction may
+ * applicable to only some of the trigger levels.
+ * @registers: Pointer to structure containing all the TMU controller registers
+ * and bitfields shifts and masks.
+ * @features: a bitfield value indicating the features supported in SOC like
+ * emulation, multi instance etc
+ *
+ * This structure is required for configuration of exynos_tmu driver.
+ */
+struct exynos_tmu_platform_data {
+ u8 threshold;
+ u8 threshold_falling;
+ u8 trigger_levels[MAX_TRIP_COUNT];
+ enum trigger_type trigger_type[MAX_TRIP_COUNT];
+ bool trigger_enable[MAX_TRIP_COUNT];
+ u8 max_trigger_level;
+ u8 gain;
+ u8 reference_voltage;
+ u8 noise_cancel_mode;
+
+ u32 efuse_value;
+ u32 min_efuse_value;
+ u32 max_efuse_value;
+ u8 first_point_trim;
+ u8 second_point_trim;
+ u8 default_temp_offset;
+
+ enum calibration_type cal_type;
+ enum calibration_mode cal_mode;
+ enum soc_type type;
+ struct freq_clip_table freq_tab[4];
+ unsigned int freq_tab_count;
+ const struct exynos_tmu_registers *registers;
+ unsigned int features;
+};
+
+/**
+ * struct exynos_tmu_init_data
+ * @tmu_count: number of TMU instances.
+ * @tmu_data: platform data of all TMU instances.
+ * This structure is required to store data for multi-instance exynos tmu
+ * driver.
+ */
+struct exynos_tmu_init_data {
+ int tmu_count;
+ struct exynos_tmu_platform_data tmu_data[];
+};
+
+#endif /* _EXYNOS_TMU_H */
diff --git a/drivers/thermal/samsung/exynos_tmu_data.c b/drivers/thermal/samsung/exynos_tmu_data.c
new file mode 100644
index 0000000..9002499
--- /dev/null
+++ b/drivers/thermal/samsung/exynos_tmu_data.c
@@ -0,0 +1,250 @@
+/*
+ * exynos_tmu_data.c - Samsung EXYNOS tmu data file
+ *
+ * Copyright (C) 2013 Samsung Electronics
+ * Amit Daniel Kachhap <amit.daniel@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ *
+ */
+
+#include "exynos_thermal_common.h"
+#include "exynos_tmu.h"
+#include "exynos_tmu_data.h"
+
+#if defined(CONFIG_CPU_EXYNOS4210)
+static const struct exynos_tmu_registers exynos4210_tmu_registers = {
+ .triminfo_data = EXYNOS_TMU_REG_TRIMINFO,
+ .triminfo_25_shift = EXYNOS_TRIMINFO_25_SHIFT,
+ .triminfo_85_shift = EXYNOS_TRIMINFO_85_SHIFT,
+ .tmu_ctrl = EXYNOS_TMU_REG_CONTROL,
+ .buf_vref_sel_shift = EXYNOS_TMU_REF_VOLTAGE_SHIFT,
+ .buf_vref_sel_mask = EXYNOS_TMU_REF_VOLTAGE_MASK,
+ .buf_slope_sel_shift = EXYNOS_TMU_BUF_SLOPE_SEL_SHIFT,
+ .buf_slope_sel_mask = EXYNOS_TMU_BUF_SLOPE_SEL_MASK,
+ .core_en_shift = EXYNOS_TMU_CORE_EN_SHIFT,
+ .tmu_status = EXYNOS_TMU_REG_STATUS,
+ .tmu_cur_temp = EXYNOS_TMU_REG_CURRENT_TEMP,
+ .threshold_temp = EXYNOS4210_TMU_REG_THRESHOLD_TEMP,
+ .threshold_th0 = EXYNOS4210_TMU_REG_TRIG_LEVEL0,
+ .tmu_inten = EXYNOS_TMU_REG_INTEN,
+ .inten_rise_mask = EXYNOS4210_TMU_TRIG_LEVEL_MASK,
+ .inten_rise0_shift = EXYNOS_TMU_INTEN_RISE0_SHIFT,
+ .inten_rise1_shift = EXYNOS_TMU_INTEN_RISE1_SHIFT,
+ .inten_rise2_shift = EXYNOS_TMU_INTEN_RISE2_SHIFT,
+ .inten_rise3_shift = EXYNOS_TMU_INTEN_RISE3_SHIFT,
+ .tmu_intstat = EXYNOS_TMU_REG_INTSTAT,
+ .tmu_intclear = EXYNOS_TMU_REG_INTCLEAR,
+};
+
+struct exynos_tmu_init_data const exynos4210_default_tmu_data = {
+ .tmu_data = {
+ {
+ .threshold = 80,
+ .trigger_levels[0] = 5,
+ .trigger_levels[1] = 20,
+ .trigger_levels[2] = 30,
+ .trigger_enable[0] = true,
+ .trigger_enable[1] = true,
+ .trigger_enable[2] = true,
+ .trigger_enable[3] = false,
+ .trigger_type[0] = THROTTLE_ACTIVE,
+ .trigger_type[1] = THROTTLE_ACTIVE,
+ .trigger_type[2] = SW_TRIP,
+ .max_trigger_level = 4,
+ .gain = 15,
+ .reference_voltage = 7,
+ .cal_type = TYPE_ONE_POINT_TRIMMING,
+ .min_efuse_value = 40,
+ .max_efuse_value = 100,
+ .first_point_trim = 25,
+ .second_point_trim = 85,
+ .default_temp_offset = 50,
+ .freq_tab[0] = {
+ .freq_clip_max = 800 * 1000,
+ .temp_level = 85,
+ },
+ .freq_tab[1] = {
+ .freq_clip_max = 200 * 1000,
+ .temp_level = 100,
+ },
+ .freq_tab_count = 2,
+ .type = SOC_ARCH_EXYNOS4210,
+ .registers = &exynos4210_tmu_registers,
+ .features = TMU_SUPPORT_READY_STATUS,
+ },
+ },
+ .tmu_count = 1,
+};
+#endif
+
+#if defined(CONFIG_SOC_EXYNOS5250) || defined(CONFIG_SOC_EXYNOS4412)
+static const struct exynos_tmu_registers exynos5250_tmu_registers = {
+ .triminfo_data = EXYNOS_TMU_REG_TRIMINFO,
+ .triminfo_25_shift = EXYNOS_TRIMINFO_25_SHIFT,
+ .triminfo_85_shift = EXYNOS_TRIMINFO_85_SHIFT,
+ .triminfo_ctrl = EXYNOS_TMU_TRIMINFO_CON,
+ .triminfo_reload_shift = EXYNOS_TRIMINFO_RELOAD_SHIFT,
+ .tmu_ctrl = EXYNOS_TMU_REG_CONTROL,
+ .buf_vref_sel_shift = EXYNOS_TMU_REF_VOLTAGE_SHIFT,
+ .buf_vref_sel_mask = EXYNOS_TMU_REF_VOLTAGE_MASK,
+ .therm_trip_mode_shift = EXYNOS_TMU_TRIP_MODE_SHIFT,
+ .therm_trip_mode_mask = EXYNOS_TMU_TRIP_MODE_MASK,
+ .therm_trip_en_shift = EXYNOS_TMU_THERM_TRIP_EN_SHIFT,
+ .buf_slope_sel_shift = EXYNOS_TMU_BUF_SLOPE_SEL_SHIFT,
+ .buf_slope_sel_mask = EXYNOS_TMU_BUF_SLOPE_SEL_MASK,
+ .core_en_shift = EXYNOS_TMU_CORE_EN_SHIFT,
+ .tmu_status = EXYNOS_TMU_REG_STATUS,
+ .tmu_cur_temp = EXYNOS_TMU_REG_CURRENT_TEMP,
+ .threshold_th0 = EXYNOS_THD_TEMP_RISE,
+ .threshold_th1 = EXYNOS_THD_TEMP_FALL,
+ .tmu_inten = EXYNOS_TMU_REG_INTEN,
+ .inten_rise_mask = EXYNOS_TMU_RISE_INT_MASK,
+ .inten_rise_shift = EXYNOS_TMU_RISE_INT_SHIFT,
+ .inten_fall_mask = EXYNOS_TMU_FALL_INT_MASK,
+ .inten_fall_shift = EXYNOS_TMU_FALL_INT_SHIFT,
+ .inten_rise0_shift = EXYNOS_TMU_INTEN_RISE0_SHIFT,
+ .inten_rise1_shift = EXYNOS_TMU_INTEN_RISE1_SHIFT,
+ .inten_rise2_shift = EXYNOS_TMU_INTEN_RISE2_SHIFT,
+ .inten_rise3_shift = EXYNOS_TMU_INTEN_RISE3_SHIFT,
+ .inten_fall0_shift = EXYNOS_TMU_INTEN_FALL0_SHIFT,
+ .tmu_intstat = EXYNOS_TMU_REG_INTSTAT,
+ .tmu_intclear = EXYNOS_TMU_REG_INTCLEAR,
+ .emul_con = EXYNOS_EMUL_CON,
+ .emul_temp_shift = EXYNOS_EMUL_DATA_SHIFT,
+ .emul_time_shift = EXYNOS_EMUL_TIME_SHIFT,
+ .emul_time_mask = EXYNOS_EMUL_TIME_MASK,
+};
+
+#define EXYNOS5250_TMU_DATA \
+ .threshold_falling = 10, \
+ .trigger_levels[0] = 85, \
+ .trigger_levels[1] = 103, \
+ .trigger_levels[2] = 110, \
+ .trigger_levels[3] = 120, \
+ .trigger_enable[0] = true, \
+ .trigger_enable[1] = true, \
+ .trigger_enable[2] = true, \
+ .trigger_enable[3] = false, \
+ .trigger_type[0] = THROTTLE_ACTIVE, \
+ .trigger_type[1] = THROTTLE_ACTIVE, \
+ .trigger_type[2] = SW_TRIP, \
+ .trigger_type[3] = HW_TRIP, \
+ .max_trigger_level = 4, \
+ .gain = 8, \
+ .reference_voltage = 16, \
+ .noise_cancel_mode = 4, \
+ .cal_type = TYPE_ONE_POINT_TRIMMING, \
+ .efuse_value = 55, \
+ .min_efuse_value = 40, \
+ .max_efuse_value = 100, \
+ .first_point_trim = 25, \
+ .second_point_trim = 85, \
+ .default_temp_offset = 50, \
+ .freq_tab[0] = { \
+ .freq_clip_max = 800 * 1000, \
+ .temp_level = 85, \
+ }, \
+ .freq_tab[1] = { \
+ .freq_clip_max = 200 * 1000, \
+ .temp_level = 103, \
+ }, \
+ .freq_tab_count = 2, \
+ .type = SOC_ARCH_EXYNOS, \
+ .registers = &exynos5250_tmu_registers, \
+ .features = (TMU_SUPPORT_EMULATION | TMU_SUPPORT_TRIM_RELOAD | \
+ TMU_SUPPORT_FALLING_TRIP | TMU_SUPPORT_READY_STATUS | \
+ TMU_SUPPORT_EMUL_TIME)
+
+struct exynos_tmu_init_data const exynos5250_default_tmu_data = {
+ .tmu_data = {
+ { EXYNOS5250_TMU_DATA },
+ },
+ .tmu_count = 1,
+};
+#endif
+
+#if defined(CONFIG_SOC_EXYNOS5440)
+static const struct exynos_tmu_registers exynos5440_tmu_registers = {
+ .triminfo_data = EXYNOS5440_TMU_S0_7_TRIM,
+ .triminfo_25_shift = EXYNOS_TRIMINFO_25_SHIFT,
+ .triminfo_85_shift = EXYNOS_TRIMINFO_85_SHIFT,
+ .tmu_ctrl = EXYNOS5440_TMU_S0_7_CTRL,
+ .buf_vref_sel_shift = EXYNOS_TMU_REF_VOLTAGE_SHIFT,
+ .buf_vref_sel_mask = EXYNOS_TMU_REF_VOLTAGE_MASK,
+ .therm_trip_mode_shift = EXYNOS_TMU_TRIP_MODE_SHIFT,
+ .therm_trip_mode_mask = EXYNOS_TMU_TRIP_MODE_MASK,
+ .therm_trip_en_shift = EXYNOS_TMU_THERM_TRIP_EN_SHIFT,
+ .buf_slope_sel_shift = EXYNOS_TMU_BUF_SLOPE_SEL_SHIFT,
+ .buf_slope_sel_mask = EXYNOS_TMU_BUF_SLOPE_SEL_MASK,
+ .calib_mode_shift = EXYNOS_TMU_CALIB_MODE_SHIFT,
+ .calib_mode_mask = EXYNOS_TMU_CALIB_MODE_MASK,
+ .core_en_shift = EXYNOS_TMU_CORE_EN_SHIFT,
+ .tmu_status = EXYNOS5440_TMU_S0_7_STATUS,
+ .tmu_cur_temp = EXYNOS5440_TMU_S0_7_TEMP,
+ .threshold_th0 = EXYNOS5440_TMU_S0_7_TH0,
+ .threshold_th1 = EXYNOS5440_TMU_S0_7_TH1,
+ .threshold_th2 = EXYNOS5440_TMU_S0_7_TH2,
+ .threshold_th3_l0_shift = EXYNOS5440_TMU_TH_RISE4_SHIFT,
+ .tmu_inten = EXYNOS5440_TMU_S0_7_IRQEN,
+ .inten_rise_mask = EXYNOS5440_TMU_RISE_INT_MASK,
+ .inten_rise_shift = EXYNOS5440_TMU_RISE_INT_SHIFT,
+ .inten_fall_mask = EXYNOS5440_TMU_FALL_INT_MASK,
+ .inten_fall_shift = EXYNOS5440_TMU_FALL_INT_SHIFT,
+ .inten_rise0_shift = EXYNOS5440_TMU_INTEN_RISE0_SHIFT,
+ .inten_rise1_shift = EXYNOS5440_TMU_INTEN_RISE1_SHIFT,
+ .inten_rise2_shift = EXYNOS5440_TMU_INTEN_RISE2_SHIFT,
+ .inten_rise3_shift = EXYNOS5440_TMU_INTEN_RISE3_SHIFT,
+ .inten_fall0_shift = EXYNOS5440_TMU_INTEN_FALL0_SHIFT,
+ .tmu_intstat = EXYNOS5440_TMU_S0_7_IRQ,
+ .tmu_intclear = EXYNOS5440_TMU_S0_7_IRQ,
+ .tmu_irqstatus = EXYNOS5440_TMU_IRQ_STATUS,
+ .emul_con = EXYNOS5440_TMU_S0_7_DEBUG,
+ .emul_temp_shift = EXYNOS_EMUL_DATA_SHIFT,
+ .tmu_pmin = EXYNOS5440_TMU_PMIN,
+};
+
+#define EXYNOS5440_TMU_DATA \
+ .trigger_levels[0] = 100, \
+ .trigger_levels[4] = 105, \
+ .trigger_enable[0] = 1, \
+ .trigger_type[0] = SW_TRIP, \
+ .trigger_type[4] = HW_TRIP, \
+ .max_trigger_level = 5, \
+ .gain = 5, \
+ .reference_voltage = 16, \
+ .noise_cancel_mode = 4, \
+ .cal_type = TYPE_ONE_POINT_TRIMMING, \
+ .cal_mode = 0, \
+ .efuse_value = 0x5b2d, \
+ .min_efuse_value = 16, \
+ .max_efuse_value = 76, \
+ .first_point_trim = 25, \
+ .second_point_trim = 70, \
+ .default_temp_offset = 25, \
+ .type = SOC_ARCH_EXYNOS5440, \
+ .registers = &exynos5440_tmu_registers, \
+ .features = (TMU_SUPPORT_EMULATION | TMU_SUPPORT_FALLING_TRIP | \
+ TMU_SUPPORT_MULTI_INST | TMU_SUPPORT_SHARED_MEMORY),
+
+struct exynos_tmu_init_data const exynos5440_default_tmu_data = {
+ .tmu_data = {
+ { EXYNOS5440_TMU_DATA } ,
+ { EXYNOS5440_TMU_DATA } ,
+ { EXYNOS5440_TMU_DATA } ,
+ },
+ .tmu_count = 3,
+};
+#endif
diff --git a/drivers/thermal/samsung/exynos_tmu_data.h b/drivers/thermal/samsung/exynos_tmu_data.h
new file mode 100644
index 0000000..dc7feb5
--- /dev/null
+++ b/drivers/thermal/samsung/exynos_tmu_data.h
@@ -0,0 +1,155 @@
+/*
+ * exynos_tmu_data.h - Samsung EXYNOS tmu data header file
+ *
+ * Copyright (C) 2013 Samsung Electronics
+ * Amit Daniel Kachhap <amit.daniel@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ *
+ */
+
+#ifndef _EXYNOS_TMU_DATA_H
+#define _EXYNOS_TMU_DATA_H
+
+/* Exynos generic registers */
+#define EXYNOS_TMU_REG_TRIMINFO 0x0
+#define EXYNOS_TMU_REG_CONTROL 0x20
+#define EXYNOS_TMU_REG_STATUS 0x28
+#define EXYNOS_TMU_REG_CURRENT_TEMP 0x40
+#define EXYNOS_TMU_REG_INTEN 0x70
+#define EXYNOS_TMU_REG_INTSTAT 0x74
+#define EXYNOS_TMU_REG_INTCLEAR 0x78
+
+#define EXYNOS_TMU_TEMP_MASK 0xff
+#define EXYNOS_TMU_REF_VOLTAGE_SHIFT 24
+#define EXYNOS_TMU_REF_VOLTAGE_MASK 0x1f
+#define EXYNOS_TMU_BUF_SLOPE_SEL_MASK 0xf
+#define EXYNOS_TMU_BUF_SLOPE_SEL_SHIFT 8
+#define EXYNOS_TMU_CORE_EN_SHIFT 0
+
+/* Exynos4210 specific registers */
+#define EXYNOS4210_TMU_REG_THRESHOLD_TEMP 0x44
+#define EXYNOS4210_TMU_REG_TRIG_LEVEL0 0x50
+#define EXYNOS4210_TMU_REG_TRIG_LEVEL1 0x54
+#define EXYNOS4210_TMU_REG_TRIG_LEVEL2 0x58
+#define EXYNOS4210_TMU_REG_TRIG_LEVEL3 0x5C
+#define EXYNOS4210_TMU_REG_PAST_TEMP0 0x60
+#define EXYNOS4210_TMU_REG_PAST_TEMP1 0x64
+#define EXYNOS4210_TMU_REG_PAST_TEMP2 0x68
+#define EXYNOS4210_TMU_REG_PAST_TEMP3 0x6C
+
+#define EXYNOS4210_TMU_TRIG_LEVEL0_MASK 0x1
+#define EXYNOS4210_TMU_TRIG_LEVEL1_MASK 0x10
+#define EXYNOS4210_TMU_TRIG_LEVEL2_MASK 0x100
+#define EXYNOS4210_TMU_TRIG_LEVEL3_MASK 0x1000
+#define EXYNOS4210_TMU_TRIG_LEVEL_MASK 0x1111
+#define EXYNOS4210_TMU_INTCLEAR_VAL 0x1111
+
+/* Exynos5250 and Exynos4412 specific registers */
+#define EXYNOS_TMU_TRIMINFO_CON 0x14
+#define EXYNOS_THD_TEMP_RISE 0x50
+#define EXYNOS_THD_TEMP_FALL 0x54
+#define EXYNOS_EMUL_CON 0x80
+
+#define EXYNOS_TRIMINFO_RELOAD_SHIFT 1
+#define EXYNOS_TRIMINFO_25_SHIFT 0
+#define EXYNOS_TRIMINFO_85_SHIFT 8
+#define EXYNOS_TMU_RISE_INT_MASK 0x111
+#define EXYNOS_TMU_RISE_INT_SHIFT 0
+#define EXYNOS_TMU_FALL_INT_MASK 0x111
+#define EXYNOS_TMU_FALL_INT_SHIFT 12
+#define EXYNOS_TMU_CLEAR_RISE_INT 0x111
+#define EXYNOS_TMU_CLEAR_FALL_INT (0x111 << 12)
+#define EXYNOS_TMU_TRIP_MODE_SHIFT 13
+#define EXYNOS_TMU_TRIP_MODE_MASK 0x7
+#define EXYNOS_TMU_THERM_TRIP_EN_SHIFT 12
+#define EXYNOS_TMU_CALIB_MODE_SHIFT 4
+#define EXYNOS_TMU_CALIB_MODE_MASK 0x3
+
+#define EXYNOS_TMU_INTEN_RISE0_SHIFT 0
+#define EXYNOS_TMU_INTEN_RISE1_SHIFT 4
+#define EXYNOS_TMU_INTEN_RISE2_SHIFT 8
+#define EXYNOS_TMU_INTEN_RISE3_SHIFT 12
+#define EXYNOS_TMU_INTEN_FALL0_SHIFT 16
+#define EXYNOS_TMU_INTEN_FALL1_SHIFT 20
+#define EXYNOS_TMU_INTEN_FALL2_SHIFT 24
+
+#define EXYNOS_EMUL_TIME 0x57F0
+#define EXYNOS_EMUL_TIME_MASK 0xffff
+#define EXYNOS_EMUL_TIME_SHIFT 16
+#define EXYNOS_EMUL_DATA_SHIFT 8
+#define EXYNOS_EMUL_DATA_MASK 0xFF
+#define EXYNOS_EMUL_ENABLE 0x1
+
+#define EXYNOS_MAX_TRIGGER_PER_REG 4
+
+/*exynos5440 specific registers*/
+#define EXYNOS5440_TMU_S0_7_TRIM 0x000
+#define EXYNOS5440_TMU_S0_7_CTRL 0x020
+#define EXYNOS5440_TMU_S0_7_DEBUG 0x040
+#define EXYNOS5440_TMU_S0_7_STATUS 0x060
+#define EXYNOS5440_TMU_S0_7_TEMP 0x0f0
+#define EXYNOS5440_TMU_S0_7_TH0 0x110
+#define EXYNOS5440_TMU_S0_7_TH1 0x130
+#define EXYNOS5440_TMU_S0_7_TH2 0x150
+#define EXYNOS5440_TMU_S0_7_EVTEN 0x1F0
+#define EXYNOS5440_TMU_S0_7_IRQEN 0x210
+#define EXYNOS5440_TMU_S0_7_IRQ 0x230
+/* exynos5440 common registers */
+#define EXYNOS5440_TMU_IRQ_STATUS 0x000
+#define EXYNOS5440_TMU_PMIN 0x004
+#define EXYNOS5440_TMU_TEMP 0x008
+
+#define EXYNOS5440_TMU_RISE_INT_MASK 0xf
+#define EXYNOS5440_TMU_RISE_INT_SHIFT 0
+#define EXYNOS5440_TMU_FALL_INT_MASK 0xf
+#define EXYNOS5440_TMU_FALL_INT_SHIFT 4
+#define EXYNOS5440_TMU_INTEN_RISE0_SHIFT 0
+#define EXYNOS5440_TMU_INTEN_RISE1_SHIFT 1
+#define EXYNOS5440_TMU_INTEN_RISE2_SHIFT 2
+#define EXYNOS5440_TMU_INTEN_RISE3_SHIFT 3
+#define EXYNOS5440_TMU_INTEN_FALL0_SHIFT 4
+#define EXYNOS5440_TMU_INTEN_FALL1_SHIFT 5
+#define EXYNOS5440_TMU_INTEN_FALL2_SHIFT 6
+#define EXYNOS5440_TMU_INTEN_FALL3_SHIFT 7
+#define EXYNOS5440_TMU_TH_RISE0_SHIFT 0
+#define EXYNOS5440_TMU_TH_RISE1_SHIFT 8
+#define EXYNOS5440_TMU_TH_RISE2_SHIFT 16
+#define EXYNOS5440_TMU_TH_RISE3_SHIFT 24
+#define EXYNOS5440_TMU_TH_RISE4_SHIFT 24
+#define EXYNOS5440_EFUSE_SWAP_OFFSET 8
+
+#if defined(CONFIG_CPU_EXYNOS4210)
+extern struct exynos_tmu_init_data const exynos4210_default_tmu_data;
+#define EXYNOS4210_TMU_DRV_DATA (&exynos4210_default_tmu_data)
+#else
+#define EXYNOS4210_TMU_DRV_DATA (NULL)
+#endif
+
+#if (defined(CONFIG_SOC_EXYNOS5250) || defined(CONFIG_SOC_EXYNOS4412))
+extern struct exynos_tmu_init_data const exynos5250_default_tmu_data;
+#define EXYNOS5250_TMU_DRV_DATA (&exynos5250_default_tmu_data)
+#else
+#define EXYNOS5250_TMU_DRV_DATA (NULL)
+#endif
+
+#if defined(CONFIG_SOC_EXYNOS5440)
+extern struct exynos_tmu_init_data const exynos5440_default_tmu_data;
+#define EXYNOS5440_TMU_DRV_DATA (&exynos5440_default_tmu_data)
+#else
+#define EXYNOS5440_TMU_DRV_DATA (NULL)
+#endif
+
+#endif /*_EXYNOS_TMU_DATA_H*/
diff --git a/drivers/thermal/step_wise.c b/drivers/thermal/step_wise.c
index 4d4ddae..d89e781 100644
--- a/drivers/thermal/step_wise.c
+++ b/drivers/thermal/step_wise.c
@@ -51,44 +51,51 @@
{
struct thermal_cooling_device *cdev = instance->cdev;
unsigned long cur_state;
+ unsigned long next_target;
+ /*
+ * We keep this instance the way it is by default.
+ * Otherwise, we use the current state of the
+ * cdev in use to determine the next_target.
+ */
cdev->ops->get_cur_state(cdev, &cur_state);
+ next_target = instance->target;
switch (trend) {
case THERMAL_TREND_RAISING:
if (throttle) {
- cur_state = cur_state < instance->upper ?
+ next_target = cur_state < instance->upper ?
(cur_state + 1) : instance->upper;
- if (cur_state < instance->lower)
- cur_state = instance->lower;
+ if (next_target < instance->lower)
+ next_target = instance->lower;
}
break;
case THERMAL_TREND_RAISE_FULL:
if (throttle)
- cur_state = instance->upper;
+ next_target = instance->upper;
break;
case THERMAL_TREND_DROPPING:
if (cur_state == instance->lower) {
if (!throttle)
- cur_state = -1;
+ next_target = THERMAL_NO_TARGET;
} else {
- cur_state -= 1;
- if (cur_state > instance->upper)
- cur_state = instance->upper;
+ next_target = cur_state - 1;
+ if (next_target > instance->upper)
+ next_target = instance->upper;
}
break;
case THERMAL_TREND_DROP_FULL:
if (cur_state == instance->lower) {
if (!throttle)
- cur_state = -1;
+ next_target = THERMAL_NO_TARGET;
} else
- cur_state = instance->lower;
+ next_target = instance->lower;
break;
default:
break;
}
- return cur_state;
+ return next_target;
}
static void update_passive_instance(struct thermal_zone_device *tz,
@@ -133,6 +140,9 @@
old_target = instance->target;
instance->target = get_target_state(instance, trend, throttle);
+ if (old_target == instance->target)
+ continue;
+
/* Activate a passive thermal instance */
if (old_target == THERMAL_NO_TARGET &&
instance->target != THERMAL_NO_TARGET)
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 1f02e8e..4962a6a 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -38,6 +38,7 @@
#include <net/genetlink.h>
#include "thermal_core.h"
+#include "thermal_hwmon.h"
MODULE_AUTHOR("Zhang Rui");
MODULE_DESCRIPTION("Generic thermal management sysfs support");
@@ -201,14 +202,23 @@
}
static void __bind(struct thermal_zone_device *tz, int mask,
- struct thermal_cooling_device *cdev)
+ struct thermal_cooling_device *cdev,
+ unsigned long *limits)
{
int i, ret;
for (i = 0; i < tz->trips; i++) {
if (mask & (1 << i)) {
+ unsigned long upper, lower;
+
+ upper = THERMAL_NO_LIMIT;
+ lower = THERMAL_NO_LIMIT;
+ if (limits) {
+ lower = limits[i * 2];
+ upper = limits[i * 2 + 1];
+ }
ret = thermal_zone_bind_cooling_device(tz, i, cdev,
- THERMAL_NO_LIMIT, THERMAL_NO_LIMIT);
+ upper, lower);
if (ret)
print_bind_err_msg(tz, cdev, ret);
}
@@ -253,7 +263,8 @@
if (tzp->tbp[i].match(pos, cdev))
continue;
tzp->tbp[i].cdev = cdev;
- __bind(pos, tzp->tbp[i].trip_mask, cdev);
+ __bind(pos, tzp->tbp[i].trip_mask, cdev,
+ tzp->tbp[i].binding_limits);
}
}
@@ -291,7 +302,8 @@
if (tzp->tbp[i].match(tz, pos))
continue;
tzp->tbp[i].cdev = pos;
- __bind(tz, tzp->tbp[i].trip_mask, pos);
+ __bind(tz, tzp->tbp[i].trip_mask, pos,
+ tzp->tbp[i].binding_limits);
}
}
exit:
@@ -859,260 +871,6 @@
/* Device management */
-#if defined(CONFIG_THERMAL_HWMON)
-
-/* hwmon sys I/F */
-#include <linux/hwmon.h>
-
-/* thermal zone devices with the same type share one hwmon device */
-struct thermal_hwmon_device {
- char type[THERMAL_NAME_LENGTH];
- struct device *device;
- int count;
- struct list_head tz_list;
- struct list_head node;
-};
-
-struct thermal_hwmon_attr {
- struct device_attribute attr;
- char name[16];
-};
-
-/* one temperature input for each thermal zone */
-struct thermal_hwmon_temp {
- struct list_head hwmon_node;
- struct thermal_zone_device *tz;
- struct thermal_hwmon_attr temp_input; /* hwmon sys attr */
- struct thermal_hwmon_attr temp_crit; /* hwmon sys attr */
-};
-
-static LIST_HEAD(thermal_hwmon_list);
-
-static ssize_t
-name_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
- struct thermal_hwmon_device *hwmon = dev_get_drvdata(dev);
- return sprintf(buf, "%s\n", hwmon->type);
-}
-static DEVICE_ATTR(name, 0444, name_show, NULL);
-
-static ssize_t
-temp_input_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
- long temperature;
- int ret;
- struct thermal_hwmon_attr *hwmon_attr
- = container_of(attr, struct thermal_hwmon_attr, attr);
- struct thermal_hwmon_temp *temp
- = container_of(hwmon_attr, struct thermal_hwmon_temp,
- temp_input);
- struct thermal_zone_device *tz = temp->tz;
-
- ret = thermal_zone_get_temp(tz, &temperature);
-
- if (ret)
- return ret;
-
- return sprintf(buf, "%ld\n", temperature);
-}
-
-static ssize_t
-temp_crit_show(struct device *dev, struct device_attribute *attr,
- char *buf)
-{
- struct thermal_hwmon_attr *hwmon_attr
- = container_of(attr, struct thermal_hwmon_attr, attr);
- struct thermal_hwmon_temp *temp
- = container_of(hwmon_attr, struct thermal_hwmon_temp,
- temp_crit);
- struct thermal_zone_device *tz = temp->tz;
- long temperature;
- int ret;
-
- ret = tz->ops->get_trip_temp(tz, 0, &temperature);
- if (ret)
- return ret;
-
- return sprintf(buf, "%ld\n", temperature);
-}
-
-
-static struct thermal_hwmon_device *
-thermal_hwmon_lookup_by_type(const struct thermal_zone_device *tz)
-{
- struct thermal_hwmon_device *hwmon;
-
- mutex_lock(&thermal_list_lock);
- list_for_each_entry(hwmon, &thermal_hwmon_list, node)
- if (!strcmp(hwmon->type, tz->type)) {
- mutex_unlock(&thermal_list_lock);
- return hwmon;
- }
- mutex_unlock(&thermal_list_lock);
-
- return NULL;
-}
-
-/* Find the temperature input matching a given thermal zone */
-static struct thermal_hwmon_temp *
-thermal_hwmon_lookup_temp(const struct thermal_hwmon_device *hwmon,
- const struct thermal_zone_device *tz)
-{
- struct thermal_hwmon_temp *temp;
-
- mutex_lock(&thermal_list_lock);
- list_for_each_entry(temp, &hwmon->tz_list, hwmon_node)
- if (temp->tz == tz) {
- mutex_unlock(&thermal_list_lock);
- return temp;
- }
- mutex_unlock(&thermal_list_lock);
-
- return NULL;
-}
-
-static int
-thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
-{
- struct thermal_hwmon_device *hwmon;
- struct thermal_hwmon_temp *temp;
- int new_hwmon_device = 1;
- int result;
-
- hwmon = thermal_hwmon_lookup_by_type(tz);
- if (hwmon) {
- new_hwmon_device = 0;
- goto register_sys_interface;
- }
-
- hwmon = kzalloc(sizeof(struct thermal_hwmon_device), GFP_KERNEL);
- if (!hwmon)
- return -ENOMEM;
-
- INIT_LIST_HEAD(&hwmon->tz_list);
- strlcpy(hwmon->type, tz->type, THERMAL_NAME_LENGTH);
- hwmon->device = hwmon_device_register(NULL);
- if (IS_ERR(hwmon->device)) {
- result = PTR_ERR(hwmon->device);
- goto free_mem;
- }
- dev_set_drvdata(hwmon->device, hwmon);
- result = device_create_file(hwmon->device, &dev_attr_name);
- if (result)
- goto free_mem;
-
- register_sys_interface:
- temp = kzalloc(sizeof(struct thermal_hwmon_temp), GFP_KERNEL);
- if (!temp) {
- result = -ENOMEM;
- goto unregister_name;
- }
-
- temp->tz = tz;
- hwmon->count++;
-
- snprintf(temp->temp_input.name, sizeof(temp->temp_input.name),
- "temp%d_input", hwmon->count);
- temp->temp_input.attr.attr.name = temp->temp_input.name;
- temp->temp_input.attr.attr.mode = 0444;
- temp->temp_input.attr.show = temp_input_show;
- sysfs_attr_init(&temp->temp_input.attr.attr);
- result = device_create_file(hwmon->device, &temp->temp_input.attr);
- if (result)
- goto free_temp_mem;
-
- if (tz->ops->get_crit_temp) {
- unsigned long temperature;
- if (!tz->ops->get_crit_temp(tz, &temperature)) {
- snprintf(temp->temp_crit.name,
- sizeof(temp->temp_crit.name),
- "temp%d_crit", hwmon->count);
- temp->temp_crit.attr.attr.name = temp->temp_crit.name;
- temp->temp_crit.attr.attr.mode = 0444;
- temp->temp_crit.attr.show = temp_crit_show;
- sysfs_attr_init(&temp->temp_crit.attr.attr);
- result = device_create_file(hwmon->device,
- &temp->temp_crit.attr);
- if (result)
- goto unregister_input;
- }
- }
-
- mutex_lock(&thermal_list_lock);
- if (new_hwmon_device)
- list_add_tail(&hwmon->node, &thermal_hwmon_list);
- list_add_tail(&temp->hwmon_node, &hwmon->tz_list);
- mutex_unlock(&thermal_list_lock);
-
- return 0;
-
- unregister_input:
- device_remove_file(hwmon->device, &temp->temp_input.attr);
- free_temp_mem:
- kfree(temp);
- unregister_name:
- if (new_hwmon_device) {
- device_remove_file(hwmon->device, &dev_attr_name);
- hwmon_device_unregister(hwmon->device);
- }
- free_mem:
- if (new_hwmon_device)
- kfree(hwmon);
-
- return result;
-}
-
-static void
-thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz)
-{
- struct thermal_hwmon_device *hwmon;
- struct thermal_hwmon_temp *temp;
-
- hwmon = thermal_hwmon_lookup_by_type(tz);
- if (unlikely(!hwmon)) {
- /* Should never happen... */
- dev_dbg(&tz->device, "hwmon device lookup failed!\n");
- return;
- }
-
- temp = thermal_hwmon_lookup_temp(hwmon, tz);
- if (unlikely(!temp)) {
- /* Should never happen... */
- dev_dbg(&tz->device, "temperature input lookup failed!\n");
- return;
- }
-
- device_remove_file(hwmon->device, &temp->temp_input.attr);
- if (tz->ops->get_crit_temp)
- device_remove_file(hwmon->device, &temp->temp_crit.attr);
-
- mutex_lock(&thermal_list_lock);
- list_del(&temp->hwmon_node);
- kfree(temp);
- if (!list_empty(&hwmon->tz_list)) {
- mutex_unlock(&thermal_list_lock);
- return;
- }
- list_del(&hwmon->node);
- mutex_unlock(&thermal_list_lock);
-
- device_remove_file(hwmon->device, &dev_attr_name);
- hwmon_device_unregister(hwmon->device);
- kfree(hwmon);
-}
-#else
-static int
-thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
-{
- return 0;
-}
-
-static void
-thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz)
-{
-}
-#endif
-
/**
* thermal_zone_bind_cooling_device() - bind a cooling device to a thermal zone
* @tz: pointer to struct thermal_zone_device
@@ -1715,9 +1473,11 @@
mutex_unlock(&thermal_governor_lock);
- result = thermal_add_hwmon_sysfs(tz);
- if (result)
- goto unregister;
+ if (!tz->tzp || !tz->tzp->no_hwmon) {
+ result = thermal_add_hwmon_sysfs(tz);
+ if (result)
+ goto unregister;
+ }
mutex_lock(&thermal_list_lock);
list_add_tail(&tz->node, &thermal_tz_list);
diff --git a/drivers/thermal/thermal_hwmon.c b/drivers/thermal/thermal_hwmon.c
new file mode 100644
index 0000000..eeef0e2
--- /dev/null
+++ b/drivers/thermal/thermal_hwmon.c
@@ -0,0 +1,269 @@
+/*
+ * thermal_hwmon.c - Generic Thermal Management hwmon support.
+ *
+ * Code based on Intel thermal_core.c. Copyrights of the original code:
+ * Copyright (C) 2008 Intel Corp
+ * Copyright (C) 2008 Zhang Rui <rui.zhang@intel.com>
+ * Copyright (C) 2008 Sujith Thomas <sujith.thomas@intel.com>
+ *
+ * Copyright (C) 2013 Texas Instruments
+ * Copyright (C) 2013 Eduardo Valentin <eduardo.valentin@ti.com>
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#include <linux/hwmon.h>
+#include <linux/thermal.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include "thermal_hwmon.h"
+
+/* hwmon sys I/F */
+/* thermal zone devices with the same type share one hwmon device */
+struct thermal_hwmon_device {
+ char type[THERMAL_NAME_LENGTH];
+ struct device *device;
+ int count;
+ struct list_head tz_list;
+ struct list_head node;
+};
+
+struct thermal_hwmon_attr {
+ struct device_attribute attr;
+ char name[16];
+};
+
+/* one temperature input for each thermal zone */
+struct thermal_hwmon_temp {
+ struct list_head hwmon_node;
+ struct thermal_zone_device *tz;
+ struct thermal_hwmon_attr temp_input; /* hwmon sys attr */
+ struct thermal_hwmon_attr temp_crit; /* hwmon sys attr */
+};
+
+static LIST_HEAD(thermal_hwmon_list);
+
+static DEFINE_MUTEX(thermal_hwmon_list_lock);
+
+static ssize_t
+name_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ struct thermal_hwmon_device *hwmon = dev_get_drvdata(dev);
+ return sprintf(buf, "%s\n", hwmon->type);
+}
+static DEVICE_ATTR(name, 0444, name_show, NULL);
+
+static ssize_t
+temp_input_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ long temperature;
+ int ret;
+ struct thermal_hwmon_attr *hwmon_attr
+ = container_of(attr, struct thermal_hwmon_attr, attr);
+ struct thermal_hwmon_temp *temp
+ = container_of(hwmon_attr, struct thermal_hwmon_temp,
+ temp_input);
+ struct thermal_zone_device *tz = temp->tz;
+
+ ret = thermal_zone_get_temp(tz, &temperature);
+
+ if (ret)
+ return ret;
+
+ return sprintf(buf, "%ld\n", temperature);
+}
+
+static ssize_t
+temp_crit_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ struct thermal_hwmon_attr *hwmon_attr
+ = container_of(attr, struct thermal_hwmon_attr, attr);
+ struct thermal_hwmon_temp *temp
+ = container_of(hwmon_attr, struct thermal_hwmon_temp,
+ temp_crit);
+ struct thermal_zone_device *tz = temp->tz;
+ long temperature;
+ int ret;
+
+ ret = tz->ops->get_trip_temp(tz, 0, &temperature);
+ if (ret)
+ return ret;
+
+ return sprintf(buf, "%ld\n", temperature);
+}
+
+
+static struct thermal_hwmon_device *
+thermal_hwmon_lookup_by_type(const struct thermal_zone_device *tz)
+{
+ struct thermal_hwmon_device *hwmon;
+
+ mutex_lock(&thermal_hwmon_list_lock);
+ list_for_each_entry(hwmon, &thermal_hwmon_list, node)
+ if (!strcmp(hwmon->type, tz->type)) {
+ mutex_unlock(&thermal_hwmon_list_lock);
+ return hwmon;
+ }
+ mutex_unlock(&thermal_hwmon_list_lock);
+
+ return NULL;
+}
+
+/* Find the temperature input matching a given thermal zone */
+static struct thermal_hwmon_temp *
+thermal_hwmon_lookup_temp(const struct thermal_hwmon_device *hwmon,
+ const struct thermal_zone_device *tz)
+{
+ struct thermal_hwmon_temp *temp;
+
+ mutex_lock(&thermal_hwmon_list_lock);
+ list_for_each_entry(temp, &hwmon->tz_list, hwmon_node)
+ if (temp->tz == tz) {
+ mutex_unlock(&thermal_hwmon_list_lock);
+ return temp;
+ }
+ mutex_unlock(&thermal_hwmon_list_lock);
+
+ return NULL;
+}
+
+int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
+{
+ struct thermal_hwmon_device *hwmon;
+ struct thermal_hwmon_temp *temp;
+ int new_hwmon_device = 1;
+ int result;
+
+ hwmon = thermal_hwmon_lookup_by_type(tz);
+ if (hwmon) {
+ new_hwmon_device = 0;
+ goto register_sys_interface;
+ }
+
+ hwmon = kzalloc(sizeof(*hwmon), GFP_KERNEL);
+ if (!hwmon)
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(&hwmon->tz_list);
+ strlcpy(hwmon->type, tz->type, THERMAL_NAME_LENGTH);
+ hwmon->device = hwmon_device_register(&tz->device);
+ if (IS_ERR(hwmon->device)) {
+ result = PTR_ERR(hwmon->device);
+ goto free_mem;
+ }
+ dev_set_drvdata(hwmon->device, hwmon);
+ result = device_create_file(hwmon->device, &dev_attr_name);
+ if (result)
+ goto free_mem;
+
+ register_sys_interface:
+ temp = kzalloc(sizeof(*temp), GFP_KERNEL);
+ if (!temp) {
+ result = -ENOMEM;
+ goto unregister_name;
+ }
+
+ temp->tz = tz;
+ hwmon->count++;
+
+ snprintf(temp->temp_input.name, sizeof(temp->temp_input.name),
+ "temp%d_input", hwmon->count);
+ temp->temp_input.attr.attr.name = temp->temp_input.name;
+ temp->temp_input.attr.attr.mode = 0444;
+ temp->temp_input.attr.show = temp_input_show;
+ sysfs_attr_init(&temp->temp_input.attr.attr);
+ result = device_create_file(hwmon->device, &temp->temp_input.attr);
+ if (result)
+ goto free_temp_mem;
+
+ if (tz->ops->get_crit_temp) {
+ unsigned long temperature;
+ if (!tz->ops->get_crit_temp(tz, &temperature)) {
+ snprintf(temp->temp_crit.name,
+ sizeof(temp->temp_crit.name),
+ "temp%d_crit", hwmon->count);
+ temp->temp_crit.attr.attr.name = temp->temp_crit.name;
+ temp->temp_crit.attr.attr.mode = 0444;
+ temp->temp_crit.attr.show = temp_crit_show;
+ sysfs_attr_init(&temp->temp_crit.attr.attr);
+ result = device_create_file(hwmon->device,
+ &temp->temp_crit.attr);
+ if (result)
+ goto unregister_input;
+ }
+ }
+
+ mutex_lock(&thermal_hwmon_list_lock);
+ if (new_hwmon_device)
+ list_add_tail(&hwmon->node, &thermal_hwmon_list);
+ list_add_tail(&temp->hwmon_node, &hwmon->tz_list);
+ mutex_unlock(&thermal_hwmon_list_lock);
+
+ return 0;
+
+ unregister_input:
+ device_remove_file(hwmon->device, &temp->temp_input.attr);
+ free_temp_mem:
+ kfree(temp);
+ unregister_name:
+ if (new_hwmon_device) {
+ device_remove_file(hwmon->device, &dev_attr_name);
+ hwmon_device_unregister(hwmon->device);
+ }
+ free_mem:
+ if (new_hwmon_device)
+ kfree(hwmon);
+
+ return result;
+}
+
+void thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz)
+{
+ struct thermal_hwmon_device *hwmon;
+ struct thermal_hwmon_temp *temp;
+
+ hwmon = thermal_hwmon_lookup_by_type(tz);
+ if (unlikely(!hwmon)) {
+ /* Should never happen... */
+ dev_dbg(&tz->device, "hwmon device lookup failed!\n");
+ return;
+ }
+
+ temp = thermal_hwmon_lookup_temp(hwmon, tz);
+ if (unlikely(!temp)) {
+ /* Should never happen... */
+ dev_dbg(&tz->device, "temperature input lookup failed!\n");
+ return;
+ }
+
+ device_remove_file(hwmon->device, &temp->temp_input.attr);
+ if (tz->ops->get_crit_temp)
+ device_remove_file(hwmon->device, &temp->temp_crit.attr);
+
+ mutex_lock(&thermal_hwmon_list_lock);
+ list_del(&temp->hwmon_node);
+ kfree(temp);
+ if (!list_empty(&hwmon->tz_list)) {
+ mutex_unlock(&thermal_hwmon_list_lock);
+ return;
+ }
+ list_del(&hwmon->node);
+ mutex_unlock(&thermal_hwmon_list_lock);
+
+ device_remove_file(hwmon->device, &dev_attr_name);
+ hwmon_device_unregister(hwmon->device);
+ kfree(hwmon);
+}
diff --git a/drivers/thermal/thermal_hwmon.h b/drivers/thermal/thermal_hwmon.h
new file mode 100644
index 0000000..c798fdb
--- /dev/null
+++ b/drivers/thermal/thermal_hwmon.h
@@ -0,0 +1,49 @@
+/*
+ * thermal_hwmon.h - Generic Thermal Management hwmon support.
+ *
+ * Code based on Intel thermal_core.c. Copyrights of the original code:
+ * Copyright (C) 2008 Intel Corp
+ * Copyright (C) 2008 Zhang Rui <rui.zhang@intel.com>
+ * Copyright (C) 2008 Sujith Thomas <sujith.thomas@intel.com>
+ *
+ * Copyright (C) 2013 Texas Instruments
+ * Copyright (C) 2013 Eduardo Valentin <eduardo.valentin@ti.com>
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#ifndef __THERMAL_HWMON_H__
+#define __THERMAL_HWMON_H__
+
+#include <linux/thermal.h>
+
+#ifdef CONFIG_THERMAL_HWMON
+int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz);
+void thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz);
+#else
+static int
+thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
+{
+ return 0;
+}
+
+static void
+thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz)
+{
+}
+#endif
+
+#endif /* __THERMAL_HWMON_H__ */
diff --git a/drivers/thermal/ti-soc-thermal/dra752-thermal-data.c b/drivers/thermal/ti-soc-thermal/dra752-thermal-data.c
index e5d8326..a492927 100644
--- a/drivers/thermal/ti-soc-thermal/dra752-thermal-data.c
+++ b/drivers/thermal/ti-soc-thermal/dra752-thermal-data.c
@@ -42,6 +42,7 @@
.mask_hot_mask = DRA752_BANDGAP_CTRL_1_MASK_HOT_CORE_MASK,
.mask_cold_mask = DRA752_BANDGAP_CTRL_1_MASK_COLD_CORE_MASK,
.mask_sidlemode_mask = DRA752_BANDGAP_CTRL_1_SIDLEMODE_MASK,
+ .mask_counter_delay_mask = DRA752_BANDGAP_CTRL_1_COUNTER_DELAY_MASK,
.mask_freeze_mask = DRA752_BANDGAP_CTRL_1_FREEZE_CORE_MASK,
.mask_clear_mask = DRA752_BANDGAP_CTRL_1_CLEAR_CORE_MASK,
.mask_clear_accum_mask = DRA752_BANDGAP_CTRL_1_CLEAR_ACCUM_CORE_MASK,
@@ -77,6 +78,7 @@
.mask_hot_mask = DRA752_BANDGAP_CTRL_2_MASK_HOT_IVA_MASK,
.mask_cold_mask = DRA752_BANDGAP_CTRL_2_MASK_COLD_IVA_MASK,
.mask_sidlemode_mask = DRA752_BANDGAP_CTRL_1_SIDLEMODE_MASK,
+ .mask_counter_delay_mask = DRA752_BANDGAP_CTRL_1_COUNTER_DELAY_MASK,
.mask_freeze_mask = DRA752_BANDGAP_CTRL_2_FREEZE_IVA_MASK,
.mask_clear_mask = DRA752_BANDGAP_CTRL_2_CLEAR_IVA_MASK,
.mask_clear_accum_mask = DRA752_BANDGAP_CTRL_2_CLEAR_ACCUM_IVA_MASK,
@@ -112,6 +114,7 @@
.mask_hot_mask = DRA752_BANDGAP_CTRL_1_MASK_HOT_MPU_MASK,
.mask_cold_mask = DRA752_BANDGAP_CTRL_1_MASK_COLD_MPU_MASK,
.mask_sidlemode_mask = DRA752_BANDGAP_CTRL_1_SIDLEMODE_MASK,
+ .mask_counter_delay_mask = DRA752_BANDGAP_CTRL_1_COUNTER_DELAY_MASK,
.mask_freeze_mask = DRA752_BANDGAP_CTRL_1_FREEZE_MPU_MASK,
.mask_clear_mask = DRA752_BANDGAP_CTRL_1_CLEAR_MPU_MASK,
.mask_clear_accum_mask = DRA752_BANDGAP_CTRL_1_CLEAR_ACCUM_MPU_MASK,
@@ -147,6 +150,7 @@
.mask_hot_mask = DRA752_BANDGAP_CTRL_2_MASK_HOT_DSPEVE_MASK,
.mask_cold_mask = DRA752_BANDGAP_CTRL_2_MASK_COLD_DSPEVE_MASK,
.mask_sidlemode_mask = DRA752_BANDGAP_CTRL_1_SIDLEMODE_MASK,
+ .mask_counter_delay_mask = DRA752_BANDGAP_CTRL_1_COUNTER_DELAY_MASK,
.mask_freeze_mask = DRA752_BANDGAP_CTRL_2_FREEZE_DSPEVE_MASK,
.mask_clear_mask = DRA752_BANDGAP_CTRL_2_CLEAR_DSPEVE_MASK,
.mask_clear_accum_mask = DRA752_BANDGAP_CTRL_2_CLEAR_ACCUM_DSPEVE_MASK,
@@ -182,6 +186,7 @@
.mask_hot_mask = DRA752_BANDGAP_CTRL_1_MASK_HOT_GPU_MASK,
.mask_cold_mask = DRA752_BANDGAP_CTRL_1_MASK_COLD_GPU_MASK,
.mask_sidlemode_mask = DRA752_BANDGAP_CTRL_1_SIDLEMODE_MASK,
+ .mask_counter_delay_mask = DRA752_BANDGAP_CTRL_1_COUNTER_DELAY_MASK,
.mask_freeze_mask = DRA752_BANDGAP_CTRL_1_FREEZE_GPU_MASK,
.mask_clear_mask = DRA752_BANDGAP_CTRL_1_CLEAR_GPU_MASK,
.mask_clear_accum_mask = DRA752_BANDGAP_CTRL_1_CLEAR_ACCUM_GPU_MASK,
diff --git a/drivers/thermal/ti-soc-thermal/ti-bandgap.c b/drivers/thermal/ti-soc-thermal/ti-bandgap.c
index 9dfd471..74c0e34 100644
--- a/drivers/thermal/ti-soc-thermal/ti-bandgap.c
+++ b/drivers/thermal/ti-soc-thermal/ti-bandgap.c
@@ -1020,9 +1020,13 @@
/* Fetch the update interval */
ret = ti_bandgap_read_update_interval(bgp, id, &interval);
- if (ret || !interval)
+ if (ret)
goto unfreeze;
+ /* Set the interval to 1 ms if bandgap counter delay is not set */
+ if (interval == 0)
+ interval = 1;
+
*trend = (t1 - t2) / interval;
dev_dbg(bgp->dev, "The temperatures are t1 = %d and t2 = %d and trend =%d\n",
diff --git a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c
index 4c5f55c37..4f8b9af 100644
--- a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c
+++ b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c
@@ -174,6 +174,9 @@
enum thermal_device_mode mode)
{
struct ti_thermal_data *data = thermal->devdata;
+ struct ti_bandgap *bgp;
+
+ bgp = data->bgp;
if (!data->ti_thermal) {
dev_notice(&thermal->device, "thermal zone not registered\n");
@@ -190,6 +193,8 @@
mutex_unlock(&data->ti_thermal->lock);
data->mode = mode;
+ ti_bandgap_write_update_interval(bgp, data->sensor_id,
+ data->ti_thermal->polling_delay);
thermal_zone_device_update(data->ti_thermal);
dev_dbg(&thermal->device, "thermal polling set for duration=%d msec\n",
data->ti_thermal->polling_delay);
@@ -313,6 +318,8 @@
}
data->ti_thermal->polling_delay = FAST_TEMP_MONITORING_RATE;
ti_bandgap_set_sensor_data(bgp, id, data);
+ ti_bandgap_write_update_interval(bgp, data->sensor_id,
+ data->ti_thermal->polling_delay);
return 0;
}
diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig
index 47c6e7b..febd45c 100644
--- a/drivers/tty/serial/Kconfig
+++ b/drivers/tty/serial/Kconfig
@@ -5,7 +5,7 @@
if TTY
menu "Serial drivers"
- depends on HAS_IOMEM && GENERIC_HARDIRQS
+ depends on HAS_IOMEM
source "drivers/tty/serial/8250/Kconfig"
diff --git a/drivers/usb/dwc3/Kconfig b/drivers/usb/dwc3/Kconfig
index f969ea2..b870872 100644
--- a/drivers/usb/dwc3/Kconfig
+++ b/drivers/usb/dwc3/Kconfig
@@ -1,6 +1,6 @@
config USB_DWC3
tristate "DesignWare USB3 DRD Core Support"
- depends on (USB || USB_GADGET) && GENERIC_HARDIRQS && HAS_DMA
+ depends on (USB || USB_GADGET) && HAS_DMA
depends on EXTCON
select USB_XHCI_PLATFORM if USB_SUPPORT && USB_XHCI_HCD
help
diff --git a/drivers/usb/gadget/Kconfig b/drivers/usb/gadget/Kconfig
index 30e2dd8..48cddf3 100644
--- a/drivers/usb/gadget/Kconfig
+++ b/drivers/usb/gadget/Kconfig
@@ -313,7 +313,7 @@
config USB_MV_UDC
tristate "Marvell USB2.0 Device Controller"
- depends on GENERIC_HARDIRQS && HAS_DMA
+ depends on HAS_DMA
help
Marvell Socs (including PXA and MMP series) include a high speed
USB2.0 OTG controller, which can be configured as high speed or
@@ -425,7 +425,7 @@
config USB_EG20T
tristate "Intel EG20T PCH/LAPIS Semiconductor IOH(ML7213/ML7831) UDC"
- depends on PCI && GENERIC_HARDIRQS
+ depends on PCI
help
This is a USB device driver for EG20T PCH.
EG20T PCH is the platform controller hub that is used in Intel's
diff --git a/drivers/usb/gadget/inode.c b/drivers/usb/gadget/inode.c
index 465ef8e..b94c049 100644
--- a/drivers/usb/gadget/inode.c
+++ b/drivers/usb/gadget/inode.c
@@ -524,7 +524,7 @@
unsigned actual;
};
-static int ep_aio_cancel(struct kiocb *iocb, struct io_event *e)
+static int ep_aio_cancel(struct kiocb *iocb)
{
struct kiocb_priv *priv = iocb->private;
struct ep_data *epdata;
@@ -540,7 +540,6 @@
// spin_unlock(&epdata->dev->lock);
local_irq_enable();
- aio_put_req(iocb);
return value;
}
@@ -709,11 +708,11 @@
if (unlikely(usb_endpoint_dir_in(&epdata->desc)))
return -EINVAL;
- buf = kmalloc(iocb->ki_left, GFP_KERNEL);
+ buf = kmalloc(iocb->ki_nbytes, GFP_KERNEL);
if (unlikely(!buf))
return -ENOMEM;
- return ep_aio_rwtail(iocb, buf, iocb->ki_left, epdata, iov, nr_segs);
+ return ep_aio_rwtail(iocb, buf, iocb->ki_nbytes, epdata, iov, nr_segs);
}
static ssize_t
@@ -728,7 +727,7 @@
if (unlikely(!usb_endpoint_dir_in(&epdata->desc)))
return -EINVAL;
- buf = kmalloc(iocb->ki_left, GFP_KERNEL);
+ buf = kmalloc(iocb->ki_nbytes, GFP_KERNEL);
if (unlikely(!buf))
return -ENOMEM;
diff --git a/drivers/usb/host/Kconfig b/drivers/usb/host/Kconfig
index 5be0326..b3f20d7 100644
--- a/drivers/usb/host/Kconfig
+++ b/drivers/usb/host/Kconfig
@@ -278,7 +278,6 @@
config USB_OXU210HP_HCD
tristate "OXU210HP HCD support"
- depends on GENERIC_HARDIRQS
---help---
The OXU210HP is an USB host/OTG/device controller. Enable this
option if your board has this chip. If unsure, say N.
diff --git a/drivers/usb/musb/Kconfig b/drivers/usb/musb/Kconfig
index c64ee09a7..c258a97 100644
--- a/drivers/usb/musb/Kconfig
+++ b/drivers/usb/musb/Kconfig
@@ -71,7 +71,6 @@
config USB_MUSB_TUSB6010
tristate "TUSB6010"
- depends on GENERIC_HARDIRQS
config USB_MUSB_OMAP2PLUS
tristate "OMAP2430 and onwards"
diff --git a/drivers/usb/renesas_usbhs/Kconfig b/drivers/usb/renesas_usbhs/Kconfig
index 019bf7e..1c4195a 100644
--- a/drivers/usb/renesas_usbhs/Kconfig
+++ b/drivers/usb/renesas_usbhs/Kconfig
@@ -4,7 +4,7 @@
config USB_RENESAS_USBHS
tristate 'Renesas USBHS controller'
- depends on USB_GADGET && GENERIC_HARDIRQS
+ depends on USB_GADGET
default n
help
Renesas USBHS is a discrete USB host and peripheral controller chip
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 0c27c7d..4b79a1f 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -1,12 +1,12 @@
/*******************************************************************************
* Vhost kernel TCM fabric driver for virtio SCSI initiators
*
- * (C) Copyright 2010-2012 RisingTide Systems LLC.
+ * (C) Copyright 2010-2013 Datera, Inc.
* (C) Copyright 2010-2012 IBM Corp.
*
* Licensed to the Linux Foundation under the General Public License (GPL) version 2.
*
- * Authors: Nicholas A. Bellinger <nab@risingtidesystems.com>
+ * Authors: Nicholas A. Bellinger <nab@daterainc.com>
* Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
*
* This program is free software; you can redistribute it and/or modify
@@ -48,12 +48,16 @@
#include <linux/virtio_scsi.h>
#include <linux/llist.h>
#include <linux/bitmap.h>
+#include <linux/percpu_ida.h>
#include "vhost.h"
#define TCM_VHOST_VERSION "v0.1"
#define TCM_VHOST_NAMELEN 256
#define TCM_VHOST_MAX_CDB_SIZE 32
+#define TCM_VHOST_DEFAULT_TAGS 256
+#define TCM_VHOST_PREALLOC_SGLS 2048
+#define TCM_VHOST_PREALLOC_PAGES 2048
struct vhost_scsi_inflight {
/* Wait for the flush operation to finish */
@@ -79,6 +83,7 @@
u32 tvc_lun;
/* Pointer to the SGL formatted memory from virtio-scsi */
struct scatterlist *tvc_sgl;
+ struct page **tvc_upages;
/* Pointer to response */
struct virtio_scsi_cmd_resp __user *tvc_resp;
/* Pointer to vhost_scsi for our device */
@@ -450,17 +455,16 @@
{
struct tcm_vhost_cmd *tv_cmd = container_of(se_cmd,
struct tcm_vhost_cmd, tvc_se_cmd);
+ struct se_session *se_sess = se_cmd->se_sess;
if (tv_cmd->tvc_sgl_count) {
u32 i;
for (i = 0; i < tv_cmd->tvc_sgl_count; i++)
put_page(sg_page(&tv_cmd->tvc_sgl[i]));
-
- kfree(tv_cmd->tvc_sgl);
}
tcm_vhost_put_inflight(tv_cmd->inflight);
- kfree(tv_cmd);
+ percpu_ida_free(&se_sess->sess_tag_pool, se_cmd->map_tag);
}
static int tcm_vhost_shutdown_session(struct se_session *se_sess)
@@ -704,7 +708,7 @@
}
static struct tcm_vhost_cmd *
-vhost_scsi_allocate_cmd(struct vhost_virtqueue *vq,
+vhost_scsi_get_tag(struct vhost_virtqueue *vq,
struct tcm_vhost_tpg *tpg,
struct virtio_scsi_cmd_req *v_req,
u32 exp_data_len,
@@ -712,18 +716,27 @@
{
struct tcm_vhost_cmd *cmd;
struct tcm_vhost_nexus *tv_nexus;
+ struct se_session *se_sess;
+ struct scatterlist *sg;
+ struct page **pages;
+ int tag;
tv_nexus = tpg->tpg_nexus;
if (!tv_nexus) {
pr_err("Unable to locate active struct tcm_vhost_nexus\n");
return ERR_PTR(-EIO);
}
+ se_sess = tv_nexus->tvn_se_sess;
- cmd = kzalloc(sizeof(struct tcm_vhost_cmd), GFP_ATOMIC);
- if (!cmd) {
- pr_err("Unable to allocate struct tcm_vhost_cmd\n");
- return ERR_PTR(-ENOMEM);
- }
+ tag = percpu_ida_alloc(&se_sess->sess_tag_pool, GFP_KERNEL);
+ cmd = &((struct tcm_vhost_cmd *)se_sess->sess_cmd_map)[tag];
+ sg = cmd->tvc_sgl;
+ pages = cmd->tvc_upages;
+ memset(cmd, 0, sizeof(struct tcm_vhost_cmd));
+
+ cmd->tvc_sgl = sg;
+ cmd->tvc_upages = pages;
+ cmd->tvc_se_cmd.map_tag = tag;
cmd->tvc_tag = v_req->tag;
cmd->tvc_task_attr = v_req->task_attr;
cmd->tvc_exp_data_len = exp_data_len;
@@ -740,7 +753,8 @@
* Returns the number of scatterlist entries used or -errno on error.
*/
static int
-vhost_scsi_map_to_sgl(struct scatterlist *sgl,
+vhost_scsi_map_to_sgl(struct tcm_vhost_cmd *tv_cmd,
+ struct scatterlist *sgl,
unsigned int sgl_count,
struct iovec *iov,
int write)
@@ -752,13 +766,25 @@
struct page **pages;
int ret, i;
+ if (sgl_count > TCM_VHOST_PREALLOC_SGLS) {
+ pr_err("vhost_scsi_map_to_sgl() psgl_count: %u greater than"
+ " preallocated TCM_VHOST_PREALLOC_SGLS: %u\n",
+ sgl_count, TCM_VHOST_PREALLOC_SGLS);
+ return -ENOBUFS;
+ }
+
pages_nr = iov_num_pages(iov);
if (pages_nr > sgl_count)
return -ENOBUFS;
- pages = kmalloc(pages_nr * sizeof(struct page *), GFP_KERNEL);
- if (!pages)
- return -ENOMEM;
+ if (pages_nr > TCM_VHOST_PREALLOC_PAGES) {
+ pr_err("vhost_scsi_map_to_sgl() pages_nr: %u greater than"
+ " preallocated TCM_VHOST_PREALLOC_PAGES: %u\n",
+ pages_nr, TCM_VHOST_PREALLOC_PAGES);
+ return -ENOBUFS;
+ }
+
+ pages = tv_cmd->tvc_upages;
ret = get_user_pages_fast((unsigned long)ptr, pages_nr, write, pages);
/* No pages were pinned */
@@ -783,7 +809,6 @@
}
out:
- kfree(pages);
return ret;
}
@@ -807,24 +832,20 @@
/* TODO overflow checking */
- sg = kmalloc(sizeof(cmd->tvc_sgl[0]) * sgl_count, GFP_ATOMIC);
- if (!sg)
- return -ENOMEM;
- pr_debug("%s sg %p sgl_count %u is_err %d\n", __func__,
- sg, sgl_count, !sg);
+ sg = cmd->tvc_sgl;
+ pr_debug("%s sg %p sgl_count %u\n", __func__, sg, sgl_count);
sg_init_table(sg, sgl_count);
- cmd->tvc_sgl = sg;
cmd->tvc_sgl_count = sgl_count;
pr_debug("Mapping %u iovecs for %u pages\n", niov, sgl_count);
for (i = 0; i < niov; i++) {
- ret = vhost_scsi_map_to_sgl(sg, sgl_count, &iov[i], write);
+ ret = vhost_scsi_map_to_sgl(cmd, sg, sgl_count, &iov[i],
+ write);
if (ret < 0) {
for (i = 0; i < cmd->tvc_sgl_count; i++)
put_page(sg_page(&cmd->tvc_sgl[i]));
- kfree(cmd->tvc_sgl);
- cmd->tvc_sgl = NULL;
+
cmd->tvc_sgl_count = 0;
return ret;
}
@@ -989,10 +1010,10 @@
for (i = 0; i < data_num; i++)
exp_data_len += vq->iov[data_first + i].iov_len;
- cmd = vhost_scsi_allocate_cmd(vq, tpg, &v_req,
- exp_data_len, data_direction);
+ cmd = vhost_scsi_get_tag(vq, tpg, &v_req,
+ exp_data_len, data_direction);
if (IS_ERR(cmd)) {
- vq_err(vq, "vhost_scsi_allocate_cmd failed %ld\n",
+ vq_err(vq, "vhost_scsi_get_tag failed %ld\n",
PTR_ERR(cmd));
goto err_cmd;
}
@@ -1654,11 +1675,31 @@
kfree(nacl);
}
+static void tcm_vhost_free_cmd_map_res(struct tcm_vhost_nexus *nexus,
+ struct se_session *se_sess)
+{
+ struct tcm_vhost_cmd *tv_cmd;
+ unsigned int i;
+
+ if (!se_sess->sess_cmd_map)
+ return;
+
+ for (i = 0; i < TCM_VHOST_DEFAULT_TAGS; i++) {
+ tv_cmd = &((struct tcm_vhost_cmd *)se_sess->sess_cmd_map)[i];
+
+ kfree(tv_cmd->tvc_sgl);
+ kfree(tv_cmd->tvc_upages);
+ }
+}
+
static int tcm_vhost_make_nexus(struct tcm_vhost_tpg *tpg,
const char *name)
{
struct se_portal_group *se_tpg;
+ struct se_session *se_sess;
struct tcm_vhost_nexus *tv_nexus;
+ struct tcm_vhost_cmd *tv_cmd;
+ unsigned int i;
mutex_lock(&tpg->tv_tpg_mutex);
if (tpg->tpg_nexus) {
@@ -1675,14 +1716,37 @@
return -ENOMEM;
}
/*
- * Initialize the struct se_session pointer
+ * Initialize the struct se_session pointer and setup tagpool
+ * for struct tcm_vhost_cmd descriptors
*/
- tv_nexus->tvn_se_sess = transport_init_session();
+ tv_nexus->tvn_se_sess = transport_init_session_tags(
+ TCM_VHOST_DEFAULT_TAGS,
+ sizeof(struct tcm_vhost_cmd));
if (IS_ERR(tv_nexus->tvn_se_sess)) {
mutex_unlock(&tpg->tv_tpg_mutex);
kfree(tv_nexus);
return -ENOMEM;
}
+ se_sess = tv_nexus->tvn_se_sess;
+ for (i = 0; i < TCM_VHOST_DEFAULT_TAGS; i++) {
+ tv_cmd = &((struct tcm_vhost_cmd *)se_sess->sess_cmd_map)[i];
+
+ tv_cmd->tvc_sgl = kzalloc(sizeof(struct scatterlist) *
+ TCM_VHOST_PREALLOC_SGLS, GFP_KERNEL);
+ if (!tv_cmd->tvc_sgl) {
+ mutex_unlock(&tpg->tv_tpg_mutex);
+ pr_err("Unable to allocate tv_cmd->tvc_sgl\n");
+ goto out;
+ }
+
+ tv_cmd->tvc_upages = kzalloc(sizeof(struct page *) *
+ TCM_VHOST_PREALLOC_PAGES, GFP_KERNEL);
+ if (!tv_cmd->tvc_upages) {
+ mutex_unlock(&tpg->tv_tpg_mutex);
+ pr_err("Unable to allocate tv_cmd->tvc_upages\n");
+ goto out;
+ }
+ }
/*
* Since we are running in 'demo mode' this call with generate a
* struct se_node_acl for the tcm_vhost struct se_portal_group with
@@ -1694,9 +1758,7 @@
mutex_unlock(&tpg->tv_tpg_mutex);
pr_debug("core_tpg_check_initiator_node_acl() failed"
" for %s\n", name);
- transport_free_session(tv_nexus->tvn_se_sess);
- kfree(tv_nexus);
- return -ENOMEM;
+ goto out;
}
/*
* Now register the TCM vhost virtual I_T Nexus as active with the
@@ -1708,6 +1770,12 @@
mutex_unlock(&tpg->tv_tpg_mutex);
return 0;
+
+out:
+ tcm_vhost_free_cmd_map_res(tv_nexus, se_sess);
+ transport_free_session(se_sess);
+ kfree(tv_nexus);
+ return -ENOMEM;
}
static int tcm_vhost_drop_nexus(struct tcm_vhost_tpg *tpg)
@@ -1747,6 +1815,8 @@
pr_debug("TCM_vhost_ConfigFS: Removing I_T Nexus to emulated"
" %s Initiator Port: %s\n", tcm_vhost_dump_proto_id(tpg->tport),
tv_nexus->tvn_se_sess->se_node_acl->initiatorname);
+
+ tcm_vhost_free_cmd_map_res(tv_nexus, se_sess);
/*
* Release the SCSI I_T Nexus to the emulated vhost Target Port
*/
diff --git a/drivers/video/acornfb.c b/drivers/video/acornfb.c
index 6488a73..7e8346e 100644
--- a/drivers/video/acornfb.c
+++ b/drivers/video/acornfb.c
@@ -38,14 +38,6 @@
#include "acornfb.h"
/*
- * VIDC machines can't do 16 or 32BPP modes.
- */
-#ifdef HAS_VIDC
-#undef FBCON_HAS_CFB16
-#undef FBCON_HAS_CFB32
-#endif
-
-/*
* Default resolution.
* NOTE that it has to be supported in the table towards
* the end of this file.
@@ -106,238 +98,6 @@
extern unsigned int vram_size; /* set by setup.c */
-#ifdef HAS_VIDC
-
-#define MAX_SIZE 480*1024
-
-/* CTL VIDC Actual
- * 24.000 0 8.000
- * 25.175 0 8.392
- * 36.000 0 12.000
- * 24.000 1 12.000
- * 25.175 1 12.588
- * 24.000 2 16.000
- * 25.175 2 16.783
- * 36.000 1 18.000
- * 24.000 3 24.000
- * 36.000 2 24.000
- * 25.175 3 25.175
- * 36.000 3 36.000
- */
-struct pixclock {
- u_long min_clock;
- u_long max_clock;
- u_int vidc_ctl;
- u_int vid_ctl;
-};
-
-static struct pixclock arc_clocks[] = {
- /* we allow +/-1% on these */
- { 123750, 126250, VIDC_CTRL_DIV3, VID_CTL_24MHz }, /* 8.000MHz */
- { 82500, 84167, VIDC_CTRL_DIV2, VID_CTL_24MHz }, /* 12.000MHz */
- { 61875, 63125, VIDC_CTRL_DIV1_5, VID_CTL_24MHz }, /* 16.000MHz */
- { 41250, 42083, VIDC_CTRL_DIV1, VID_CTL_24MHz }, /* 24.000MHz */
-};
-
-static struct pixclock *
-acornfb_valid_pixrate(struct fb_var_screeninfo *var)
-{
- u_long pixclock = var->pixclock;
- u_int i;
-
- if (!var->pixclock)
- return NULL;
-
- for (i = 0; i < ARRAY_SIZE(arc_clocks); i++)
- if (pixclock > arc_clocks[i].min_clock &&
- pixclock < arc_clocks[i].max_clock)
- return arc_clocks + i;
-
- return NULL;
-}
-
-/* VIDC Rules:
- * hcr : must be even (interlace, hcr/2 must be even)
- * hswr : must be even
- * hdsr : must be odd
- * hder : must be odd
- *
- * vcr : must be odd
- * vswr : >= 1
- * vdsr : >= 1
- * vder : >= vdsr
- * if interlaced, then hcr/2 must be even
- */
-static void
-acornfb_set_timing(struct fb_var_screeninfo *var)
-{
- struct pixclock *pclk;
- struct vidc_timing vidc;
- u_int horiz_correction;
- u_int sync_len, display_start, display_end, cycle;
- u_int is_interlaced;
- u_int vid_ctl, vidc_ctl;
- u_int bandwidth;
-
- memset(&vidc, 0, sizeof(vidc));
-
- pclk = acornfb_valid_pixrate(var);
- vidc_ctl = pclk->vidc_ctl;
- vid_ctl = pclk->vid_ctl;
-
- bandwidth = var->pixclock * 8 / var->bits_per_pixel;
- /* 25.175, 4bpp = 79.444ns per byte, 317.776ns per word: fifo = 2,6 */
- if (bandwidth > 143500)
- vidc_ctl |= VIDC_CTRL_FIFO_3_7;
- else if (bandwidth > 71750)
- vidc_ctl |= VIDC_CTRL_FIFO_2_6;
- else if (bandwidth > 35875)
- vidc_ctl |= VIDC_CTRL_FIFO_1_5;
- else
- vidc_ctl |= VIDC_CTRL_FIFO_0_4;
-
- switch (var->bits_per_pixel) {
- case 1:
- horiz_correction = 19;
- vidc_ctl |= VIDC_CTRL_1BPP;
- break;
-
- case 2:
- horiz_correction = 11;
- vidc_ctl |= VIDC_CTRL_2BPP;
- break;
-
- case 4:
- horiz_correction = 7;
- vidc_ctl |= VIDC_CTRL_4BPP;
- break;
-
- default:
- case 8:
- horiz_correction = 5;
- vidc_ctl |= VIDC_CTRL_8BPP;
- break;
- }
-
- if (var->sync & FB_SYNC_COMP_HIGH_ACT) /* should be FB_SYNC_COMP */
- vidc_ctl |= VIDC_CTRL_CSYNC;
- else {
- if (!(var->sync & FB_SYNC_HOR_HIGH_ACT))
- vid_ctl |= VID_CTL_HS_NHSYNC;
-
- if (!(var->sync & FB_SYNC_VERT_HIGH_ACT))
- vid_ctl |= VID_CTL_VS_NVSYNC;
- }
-
- sync_len = var->hsync_len;
- display_start = sync_len + var->left_margin;
- display_end = display_start + var->xres;
- cycle = display_end + var->right_margin;
-
- /* if interlaced, then hcr/2 must be even */
- is_interlaced = (var->vmode & FB_VMODE_MASK) == FB_VMODE_INTERLACED;
-
- if (is_interlaced) {
- vidc_ctl |= VIDC_CTRL_INTERLACE;
- if (cycle & 2) {
- cycle += 2;
- var->right_margin += 2;
- }
- }
-
- vidc.h_cycle = (cycle - 2) / 2;
- vidc.h_sync_width = (sync_len - 2) / 2;
- vidc.h_border_start = (display_start - 1) / 2;
- vidc.h_display_start = (display_start - horiz_correction) / 2;
- vidc.h_display_end = (display_end - horiz_correction) / 2;
- vidc.h_border_end = (display_end - 1) / 2;
- vidc.h_interlace = (vidc.h_cycle + 1) / 2;
-
- sync_len = var->vsync_len;
- display_start = sync_len + var->upper_margin;
- display_end = display_start + var->yres;
- cycle = display_end + var->lower_margin;
-
- if (is_interlaced)
- cycle = (cycle - 3) / 2;
- else
- cycle = cycle - 1;
-
- vidc.v_cycle = cycle;
- vidc.v_sync_width = sync_len - 1;
- vidc.v_border_start = display_start - 1;
- vidc.v_display_start = vidc.v_border_start;
- vidc.v_display_end = display_end - 1;
- vidc.v_border_end = vidc.v_display_end;
-
- if (machine_is_a5k())
- __raw_writeb(vid_ctl, IOEB_VID_CTL);
-
- if (memcmp(¤t_vidc, &vidc, sizeof(vidc))) {
- current_vidc = vidc;
-
- vidc_writel(0xe0000000 | vidc_ctl);
- vidc_writel(0x80000000 | (vidc.h_cycle << 14));
- vidc_writel(0x84000000 | (vidc.h_sync_width << 14));
- vidc_writel(0x88000000 | (vidc.h_border_start << 14));
- vidc_writel(0x8c000000 | (vidc.h_display_start << 14));
- vidc_writel(0x90000000 | (vidc.h_display_end << 14));
- vidc_writel(0x94000000 | (vidc.h_border_end << 14));
- vidc_writel(0x98000000);
- vidc_writel(0x9c000000 | (vidc.h_interlace << 14));
- vidc_writel(0xa0000000 | (vidc.v_cycle << 14));
- vidc_writel(0xa4000000 | (vidc.v_sync_width << 14));
- vidc_writel(0xa8000000 | (vidc.v_border_start << 14));
- vidc_writel(0xac000000 | (vidc.v_display_start << 14));
- vidc_writel(0xb0000000 | (vidc.v_display_end << 14));
- vidc_writel(0xb4000000 | (vidc.v_border_end << 14));
- vidc_writel(0xb8000000);
- vidc_writel(0xbc000000);
- }
-#ifdef DEBUG_MODE_SELECTION
- printk(KERN_DEBUG "VIDC registers for %dx%dx%d:\n", var->xres,
- var->yres, var->bits_per_pixel);
- printk(KERN_DEBUG " H-cycle : %d\n", vidc.h_cycle);
- printk(KERN_DEBUG " H-sync-width : %d\n", vidc.h_sync_width);
- printk(KERN_DEBUG " H-border-start : %d\n", vidc.h_border_start);
- printk(KERN_DEBUG " H-display-start : %d\n", vidc.h_display_start);
- printk(KERN_DEBUG " H-display-end : %d\n", vidc.h_display_end);
- printk(KERN_DEBUG " H-border-end : %d\n", vidc.h_border_end);
- printk(KERN_DEBUG " H-interlace : %d\n", vidc.h_interlace);
- printk(KERN_DEBUG " V-cycle : %d\n", vidc.v_cycle);
- printk(KERN_DEBUG " V-sync-width : %d\n", vidc.v_sync_width);
- printk(KERN_DEBUG " V-border-start : %d\n", vidc.v_border_start);
- printk(KERN_DEBUG " V-display-start : %d\n", vidc.v_display_start);
- printk(KERN_DEBUG " V-display-end : %d\n", vidc.v_display_end);
- printk(KERN_DEBUG " V-border-end : %d\n", vidc.v_border_end);
- printk(KERN_DEBUG " VIDC Ctrl (E) : 0x%08X\n", vidc_ctl);
- printk(KERN_DEBUG " IOEB Ctrl : 0x%08X\n", vid_ctl);
-#endif
-}
-
-static int
-acornfb_setcolreg(u_int regno, u_int red, u_int green, u_int blue,
- u_int trans, struct fb_info *info)
-{
- union palette pal;
-
- if (regno >= current_par.palette_size)
- return 1;
-
- pal.p = 0;
- pal.vidc.reg = regno;
- pal.vidc.red = red >> 12;
- pal.vidc.green = green >> 12;
- pal.vidc.blue = blue >> 12;
-
- current_par.palette[regno] = pal;
-
- vidc_writel(pal.p);
-
- return 0;
-}
-#endif
-
#ifdef HAS_VIDC20
#include <mach/acornfb.h>
@@ -634,16 +394,7 @@
/* hsync_len must be even */
var->hsync_len = (var->hsync_len + 1) & ~1;
-#ifdef HAS_VIDC
- /* left_margin must be odd */
- if ((var->left_margin & 1) == 0) {
- var->left_margin -= 1;
- var->right_margin += 1;
- }
-
- /* right_margin must be odd */
- var->right_margin |= 1;
-#elif defined(HAS_VIDC20)
+#if defined(HAS_VIDC20)
/* left_margin must be even */
if (var->left_margin & 1) {
var->left_margin += 1;
@@ -787,11 +538,7 @@
break;
case 8:
current_par.palette_size = VIDC_PALETTE_SIZE;
-#ifdef HAS_VIDC
- info->fix.visual = FB_VISUAL_STATIC_PSEUDOCOLOR;
-#else
info->fix.visual = FB_VISUAL_PSEUDOCOLOR;
-#endif
break;
#ifdef HAS_VIDC20
case 16:
@@ -971,9 +718,6 @@
#if defined(HAS_VIDC20)
fb_info.var.red.length = 8;
fb_info.var.transp.length = 4;
-#elif defined(HAS_VIDC)
- fb_info.var.red.length = 4;
- fb_info.var.transp.length = 1;
#endif
fb_info.var.green = fb_info.var.red;
fb_info.var.blue = fb_info.var.red;
@@ -1310,14 +1054,6 @@
fb_info.fix.smem_start = handle;
}
#endif
-#if defined(HAS_VIDC)
- /*
- * Archimedes/A5000 machines use a fixed address for their
- * framebuffers. Free unused pages
- */
- free_unused_pages(PAGE_OFFSET + size, PAGE_OFFSET + MAX_SIZE);
-#endif
-
fb_info.fix.smem_len = size;
current_par.palette_size = VIDC_PALETTE_SIZE;
diff --git a/drivers/video/acornfb.h b/drivers/video/acornfb.h
index fb2a7ff..175c8ff 100644
--- a/drivers/video/acornfb.h
+++ b/drivers/video/acornfb.h
@@ -13,10 +13,6 @@
#include <asm/hardware/iomd.h>
#define VIDC_PALETTE_SIZE 256
#define VIDC_NAME "VIDC20"
-#elif defined(HAS_VIDC)
-#include <asm/hardware/memc.h>
-#define VIDC_PALETTE_SIZE 16
-#define VIDC_NAME "VIDC"
#endif
#define EXTEND8(x) ((x)|(x)<<8)
@@ -101,31 +97,6 @@
const struct modey_params *modey;
};
-#ifdef HAS_VIDC
-
-#define VID_CTL_VS_NVSYNC (1 << 3)
-#define VID_CTL_HS_NHSYNC (1 << 2)
-#define VID_CTL_24MHz (0)
-#define VID_CTL_25MHz (1)
-#define VID_CTL_36MHz (2)
-
-#define VIDC_CTRL_CSYNC (1 << 7)
-#define VIDC_CTRL_INTERLACE (1 << 6)
-#define VIDC_CTRL_FIFO_0_4 (0 << 4)
-#define VIDC_CTRL_FIFO_1_5 (1 << 4)
-#define VIDC_CTRL_FIFO_2_6 (2 << 4)
-#define VIDC_CTRL_FIFO_3_7 (3 << 4)
-#define VIDC_CTRL_1BPP (0 << 2)
-#define VIDC_CTRL_2BPP (1 << 2)
-#define VIDC_CTRL_4BPP (2 << 2)
-#define VIDC_CTRL_8BPP (3 << 2)
-#define VIDC_CTRL_DIV3 (0 << 0)
-#define VIDC_CTRL_DIV2 (1 << 0)
-#define VIDC_CTRL_DIV1_5 (2 << 0)
-#define VIDC_CTRL_DIV1 (3 << 0)
-
-#endif
-
#ifdef HAS_VIDC20
/*
* VIDC20 registers
diff --git a/drivers/video/logo/logo_linux_clut224.ppm b/drivers/video/logo/logo_linux_clut224.ppm
index 285d552..3c14e43 100644
--- a/drivers/video/logo/logo_linux_clut224.ppm
+++ b/drivers/video/logo/logo_linux_clut224.ppm
@@ -1,883 +1,1604 @@
P3
+# Standard 224-color Linux logo
80 80
255
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 11 15 17 33 49 54 59 85 92 73 97 106
-83 116 129 105 131 142 115 114 122 74 88 93 20 29 31 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 6 6 6 6 6 6 10 10 10 10 10 10
-10 10 10 6 6 6 6 6 6 6 6 6 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 2 3 3 17 23 26 50 67 72 73 97 106 59 85 92 73 97 106
-105 131 142 124 127 131 105 131 142 105 131 142 53 75 83 6 8 8 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 6 6 6 10 10 10 14 14 14 22 22 22 26 26 26 30 30 30 34 34 34
-30 30 30 30 30 30 26 26 26 18 18 18 14 14 14 10 10 10 6 6 6 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 0 0 0
-0 0 0 1 1 1 26 35 39 59 85 92 59 85 92 59 85 92 29 43 47 53 75 83
-108 122 132 132 98 104 108 122 132 105 131 142 101 101 101 43 45 48 6 8 8 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-6 6 6 14 14 14 26 26 26 42 42 42 54 54 54 66 66 66 78 78 78 78 78 78
-78 78 78 74 74 74 66 66 66 54 54 54 42 42 42 26 26 26 18 18 18 10 10 10
-6 6 6 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 1 1 1 0 0 0 0 0 0 0 0 0
-11 15 17 27 40 45 59 85 92 59 85 92 27 40 45 31 45 49 73 97 106 93 121 133
-108 122 132 108 122 132 105 131 142 108 122 132 105 131 142 73 97 106 26 35 39 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 10 10 10
-22 22 22 42 42 42 66 66 66 86 86 86 66 66 66 38 38 38 38 38 38 22 22 22
-26 26 26 34 34 34 54 54 54 66 66 66 86 86 86 70 70 70 46 46 46 26 26 26
-14 14 14 6 6 6 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 1 1 1 7 12 13 21 31 35 42 59 64
-53 75 83 53 75 83 50 67 72 42 59 64 32 40 45 42 59 64 73 97 106 116 116 116
-132 98 104 116 116 116 108 122 132 117 104 110 105 131 142 83 116 129 50 67 72 7 12 13
-1 1 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 10 10 10 26 26 26
-50 50 50 82 82 82 58 58 58 6 6 6 2 2 6 2 2 6 2 2 6 2 2 6
-2 2 6 2 2 6 2 2 6 2 2 6 6 6 6 54 54 54 86 86 86 66 66 66
-38 38 38 18 18 18 6 6 6 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 1 1 1 6 8 8 15 22 25 26 35 39 36 54 60 53 75 83 59 85 92
-59 85 92 48 63 69 15 22 25 12 17 20 52 67 79 94 94 94 132 98 104 132 98 104
-117 104 110 108 122 132 108 122 132 115 114 122 105 131 142 77 105 114 59 85 92 36 54 60
-7 12 13 0 0 0 0 0 0 0 0 0 0 0 0 6 6 6 22 22 22 50 50 50
-78 78 78 34 34 34 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6
-2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 6 6 6 70 70 70
-78 78 78 46 46 46 22 22 22 6 6 6 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 15 22 25 29 43 47 36 54 60 42 59 64 42 59 64 48 63 69 21 31 35
-6 8 8 29 43 47 36 50 56 43 45 48 79 78 84 132 98 104 165 78 79 132 98 104
-108 122 132 117 104 110 117 104 110 108 122 132 77 105 114 73 97 106 95 131 149 78 102 129
-36 50 56 0 0 0 0 0 0 0 0 0 6 6 6 18 18 18 42 42 42 82 82 82
-26 26 26 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6
-2 2 6 2 2 6 2 2 6 14 14 14 46 46 46 34 34 34 6 6 6 2 2 6
-42 42 42 78 78 78 42 42 42 18 18 18 6 6 6 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-27 40 45 53 75 83 48 63 69 24 31 37 6 8 12 0 0 0 18 25 28 26 35 39
-12 17 20 26 35 39 65 78 84 112 81 86 152 81 83 137 83 86 132 98 104 117 104 110
-117 104 110 132 98 104 132 98 104 115 114 122 73 97 106 53 75 83 95 131 149 93 124 152
-68 78 128 15 22 25 0 0 0 0 0 0 10 10 10 30 30 30 66 66 66 58 58 58
-2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6
-2 2 6 2 2 6 2 2 6 26 26 26 86 86 86 101 101 101 46 46 46 10 10 10
-2 2 6 58 58 58 70 70 70 34 34 34 10 10 10 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-36 50 56 21 30 33 4 7 7 0 0 0 1 1 1 17 12 12 69 31 31 68 59 64
-57 59 63 21 31 35 32 40 45 86 73 69 152 81 83 152 81 83 117 104 110 132 98 104
-152 81 83 132 98 104 108 122 132 77 105 114 77 105 114 93 121 133 95 131 149 93 124 152
-95 131 149 53 75 83 11 15 17 0 0 0 14 14 14 42 42 42 86 86 86 10 10 10
-2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6
-2 2 6 2 2 6 2 2 6 30 30 30 94 94 94 94 94 94 58 58 58 26 26 26
-2 2 6 6 6 6 78 78 78 54 54 54 22 22 22 6 6 6 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-17 23 26 2 3 3 0 0 0 17 12 12 69 31 31 123 55 55 123 55 55 152 81 83
-86 73 69 17 23 26 7 12 13 45 54 57 101 101 101 137 83 86 132 98 104 132 98 104
-137 83 86 117 104 110 77 105 114 42 59 64 50 67 72 78 102 129 91 117 157 91 117 157
-95 131 149 83 116 129 40 48 73 6 6 6 22 22 22 62 62 62 62 62 62 2 2 6
-2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6
-2 2 6 2 2 6 2 2 6 26 26 26 54 54 54 38 38 38 18 18 18 10 10 10
-2 2 6 2 2 6 34 34 34 82 82 82 38 38 38 14 14 14 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-1 1 1 1 2 2 2 3 3 28 12 12 123 55 55 174 79 79 174 79 79 174 79 79
-152 81 83 68 59 64 26 35 39 27 40 45 79 78 84 137 83 86 165 78 79 137 83 86
-94 94 94 48 63 69 36 50 56 50 67 72 73 97 106 93 121 133 93 124 152 93 124 152
-95 131 149 91 118 149 78 102 129 27 40 45 30 30 30 78 78 78 30 30 30 2 2 6
-2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6
-2 2 6 2 2 6 2 2 6 10 10 10 10 10 10 2 2 6 2 2 6 2 2 6
-2 2 6 2 2 6 2 2 6 78 78 78 50 50 50 18 18 18 6 6 6 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-4 5 3 24 53 24 19 31 15 8 7 3 90 61 47 165 78 79 174 79 79 174 79 79
-174 79 79 137 83 86 60 52 57 7 12 13 17 23 26 70 70 70 132 98 104 112 81 86
-79 78 84 31 45 49 15 22 25 53 75 83 91 118 149 86 106 160 91 117 157 93 124 152
-91 117 157 93 124 152 95 131 149 53 75 83 50 50 50 86 86 86 14 14 14 2 2 6
-2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6
-2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6
-2 2 6 2 2 6 2 2 6 54 54 54 66 66 66 26 26 26 6 6 6 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-19 31 15 34 76 34 34 76 34 19 31 15 28 12 12 123 55 55 174 79 79 174 79 79
-174 79 79 165 78 79 112 81 86 32 40 45 15 22 25 38 53 58 65 78 84 29 31 32
-21 30 33 42 59 64 60 80 103 78 102 129 87 112 149 84 96 162 91 117 157 93 124 152
-91 117 157 93 124 152 93 121 133 59 85 92 57 68 71 82 85 86 2 2 6 2 2 6
-2 2 6 6 6 6 10 10 10 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6
-2 2 6 2 2 6 2 2 6 6 6 6 14 14 14 10 10 10 2 2 6 2 2 6
-2 2 6 2 2 6 2 2 6 18 18 18 82 82 82 34 34 34 10 10 10 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-34 76 34 40 89 40 40 89 40 34 76 34 8 15 6 48 26 18 123 55 55 174 79 79
-174 79 79 174 79 79 137 83 86 68 59 64 32 40 45 21 30 33 31 45 49 21 31 35
-12 17 20 48 63 69 78 102 129 81 88 166 84 96 162 91 117 157 93 124 152 91 117 157
-93 124 152 95 131 149 83 116 129 59 85 92 57 68 71 86 86 86 2 2 6 2 2 6
-6 6 6 6 6 6 22 22 22 34 34 34 6 6 6 2 2 6 2 2 6 2 2 6
-2 2 6 2 2 6 18 18 18 34 34 34 10 10 10 50 50 50 22 22 22 2 2 6
-2 2 6 2 2 6 2 2 6 10 10 10 86 86 86 42 42 42 14 14 14 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-40 89 40 40 89 40 40 89 40 40 89 40 24 53 24 6 6 6 69 31 31 123 55 55
-123 55 55 90 61 47 69 31 31 36 32 33 21 31 35 7 12 13 18 25 28 48 63 69
-60 80 103 68 78 128 84 101 153 84 96 162 84 96 162 91 117 157 91 117 157 84 96 162
-91 117 157 73 97 106 48 63 69 50 67 72 57 59 63 86 86 86 2 2 6 2 2 6
-38 38 38 116 116 116 94 94 94 22 22 22 22 22 22 2 2 6 2 2 6 2 2 6
-14 14 14 86 86 86 124 131 137 170 170 170 151 151 151 38 38 38 26 26 26 6 6 6
-2 2 6 2 2 6 2 2 6 2 2 6 86 86 86 46 46 46 14 14 14 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-34 76 34 40 89 40 40 89 40 40 89 40 34 76 34 19 31 15 17 12 12 48 26 18
-48 26 18 8 7 3 10 10 22 23 29 47 51 61 92 42 59 64 21 30 33 34 45 54
-68 78 128 81 88 166 81 82 173 86 106 160 86 106 160 84 96 162 86 106 160 87 112 149
-91 118 149 77 105 114 52 67 79 32 40 45 50 50 50 86 86 86 2 2 6 14 14 14
-124 131 137 198 198 198 195 195 195 116 116 116 10 10 10 2 2 6 2 2 6 6 6 6
-101 98 89 187 187 187 210 210 210 218 218 218 214 214 214 124 131 137 14 14 14 6 6 6
-2 2 6 2 2 6 2 2 6 2 2 6 86 86 86 50 50 50 18 18 18 6 6 6
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-19 31 15 34 76 34 40 89 40 40 89 40 40 89 40 24 53 24 8 7 3 0 0 0
-6 8 12 28 32 52 51 61 92 54 54 122 74 77 160 68 78 128 26 35 39 6 8 8
-34 45 54 68 78 128 84 96 162 86 106 160 86 106 160 81 88 166 84 96 162 87 112 149
-73 97 106 36 50 56 33 49 54 18 18 18 46 46 46 86 86 86 2 2 6 54 54 54
-218 218 218 195 195 195 226 226 226 246 246 246 58 58 58 2 2 6 2 2 6 30 30 30
-210 210 210 253 253 253 170 170 170 124 127 131 221 221 221 234 234 234 74 74 74 2 2 6
-2 2 6 2 2 6 2 2 6 2 2 6 70 70 70 58 58 58 22 22 22 6 6 6
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-4 5 3 24 53 24 40 89 40 40 89 40 34 76 34 12 22 15 4 5 3 4 5 3
-13 17 26 54 54 122 78 78 174 78 78 174 78 78 174 74 77 160 51 61 92 21 31 35
-26 35 39 53 75 83 84 101 153 81 82 173 81 88 166 84 101 153 60 80 103 60 80 103
-53 75 83 38 53 58 42 59 64 22 22 22 46 46 46 82 82 82 2 2 6 106 106 106
-170 170 170 26 26 26 86 86 86 226 226 226 124 127 131 10 10 10 14 14 14 46 46 46
-231 231 231 190 190 190 6 6 6 70 70 70 90 90 90 238 238 238 151 151 151 2 2 6
-2 2 6 2 2 6 2 2 6 2 2 6 70 70 70 58 58 58 22 22 22 6 6 6
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-1 2 2 8 15 6 24 53 24 34 76 34 19 31 15 8 15 6 63 55 20 63 55 20
-18 18 18 40 48 73 74 77 160 78 78 174 78 78 174 81 82 173 74 77 160 52 67 79
-17 23 26 21 31 35 60 80 103 81 88 166 74 77 160 78 102 129 36 54 60 12 17 20
-42 59 64 48 63 69 21 31 35 18 18 18 42 42 42 86 86 86 6 6 6 116 116 116
-106 106 106 6 6 6 70 70 70 151 151 151 124 127 131 18 18 18 38 38 38 54 54 54
-221 221 221 106 106 106 2 2 6 14 14 14 46 46 46 190 190 190 198 198 198 2 2 6
-2 2 6 2 2 6 2 2 6 2 2 6 74 74 74 62 62 62 22 22 22 6 6 6
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-11 15 17 0 0 0 12 22 15 19 31 15 8 15 6 63 55 20 149 139 69 149 139 69
-63 55 20 10 10 22 54 54 122 78 78 174 78 78 174 78 78 174 81 82 173 68 78 128
-24 31 37 6 6 6 36 50 56 60 80 103 51 61 92 42 59 64 36 50 56 31 45 49
-29 43 47 27 40 45 6 8 8 14 14 14 42 42 42 94 94 94 14 14 14 101 101 101
-124 127 131 2 2 6 18 18 18 116 116 116 106 107 48 121 92 8 121 92 8 98 70 6
-170 170 170 106 106 106 2 2 6 2 2 6 2 2 6 195 195 195 195 195 195 6 6 6
-2 2 6 2 2 6 2 2 6 2 2 6 74 74 74 62 62 62 22 22 22 6 6 6
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-26 35 39 3 5 6 1 1 1 2 3 3 35 31 12 133 118 54 175 176 80 175 176 80
-133 118 54 35 31 12 23 29 47 54 54 122 78 78 174 78 78 174 74 77 160 68 78 128
-51 61 92 31 45 49 26 35 39 36 50 56 29 43 47 7 12 13 21 30 33 42 59 64
-18 25 28 7 12 13 1 1 1 10 10 10 38 38 38 90 90 90 14 14 14 58 58 58
-210 210 210 26 26 26 62 42 6 154 114 10 226 170 11 237 188 10 220 174 15 184 138 11
-220 174 15 174 140 55 35 31 12 2 2 6 70 70 70 246 246 246 124 131 137 2 2 6
-2 2 6 2 2 6 2 2 6 2 2 6 70 70 70 66 66 66 26 26 26 6 6 6
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-27 40 45 17 23 26 2 3 3 1 1 1 56 77 35 165 152 80 175 176 80 175 176 80
-175 176 80 106 107 48 22 22 22 28 32 52 54 54 122 54 54 122 51 61 92 28 32 52
-20 27 34 31 45 49 11 15 17 7 12 13 36 50 56 31 45 49 29 43 47 36 50 56
-6 8 8 0 0 0 0 0 0 10 10 10 38 38 38 86 86 86 14 14 14 10 10 10
-195 195 195 198 179 130 192 133 9 220 174 15 239 182 13 237 188 10 232 195 16 239 207 25
-237 201 50 241 208 19 232 195 16 184 138 11 198 179 130 208 206 196 42 42 42 2 2 6
-2 2 6 2 2 6 2 2 6 2 2 6 50 50 50 74 74 74 30 30 30 6 6 6
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-15 22 25 26 35 39 15 22 25 0 0 0 35 31 12 133 118 54 175 176 80 175 176 80
-175 176 80 165 152 80 56 77 35 6 8 12 23 29 47 13 17 26 2 2 6 0 0 0
-1 2 2 26 35 39 26 35 39 26 35 39 42 59 64 42 59 64 20 29 31 6 8 8
-0 0 0 0 0 0 0 0 0 10 10 10 34 34 34 86 86 86 14 14 14 2 2 6
-121 92 8 192 133 9 219 162 10 239 182 13 237 188 10 232 195 16 241 208 19 237 201 50
-237 201 50 239 207 25 241 208 19 241 208 19 241 208 19 230 187 11 121 92 8 2 2 6
-2 2 6 2 2 6 2 2 6 2 2 6 50 50 50 82 82 82 34 34 34 10 10 10
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-1 2 2 15 22 25 31 45 49 6 8 12 4 5 3 63 55 20 149 139 69 175 176 80
-175 176 80 175 176 80 106 107 48 20 16 6 1 1 1 0 0 0 2 3 3 11 15 17
-21 30 33 36 50 56 36 50 56 24 31 37 15 22 25 6 8 8 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 10 10 10 34 34 34 82 82 82 30 30 30 62 42 6
-180 123 7 206 145 10 230 174 11 239 182 13 237 188 10 238 202 15 241 208 19 237 201 50
-239 207 25 241 208 19 241 208 19 241 208 19 230 187 11 220 174 15 184 138 11 6 6 6
-2 2 6 2 2 6 2 2 6 2 2 6 26 26 26 94 94 94 42 42 42 14 14 14
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 1 2 2 29 43 47 26 35 39 3 5 6 8 7 3 106 107 48 165 152 80
-175 176 80 149 139 69 63 55 20 4 5 3 2 3 3 12 17 20 26 35 39 26 35 39
-17 23 26 7 12 13 6 8 8 3 5 6 1 2 2 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 10 10 10 30 30 30 78 78 78 50 50 50 104 69 6
-192 133 9 216 158 10 236 178 12 237 188 10 232 195 16 241 208 19 237 201 50 237 201 50
-241 208 19 241 208 19 241 208 19 204 160 10 200 144 11 216 158 10 156 118 10 2 2 6
-2 2 6 2 2 6 2 2 6 2 2 6 6 6 6 90 90 90 54 54 54 18 18 18
-6 6 6 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 12 17 20 27 40 45 18 25 28 1 1 1 35 31 12 106 107 48
-149 139 69 56 77 35 8 7 3 1 2 2 12 17 20 26 35 39 21 31 35 11 15 17
-3 5 6 1 1 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 10 10 10 30 30 30 78 78 78 46 46 46 22 22 22
-137 92 6 204 160 10 239 182 13 237 188 10 238 202 15 241 208 19 241 208 19 241 208 19
-241 208 19 204 160 10 184 138 11 210 150 10 216 158 10 210 150 10 98 70 6 2 2 6
-6 6 6 54 54 54 14 14 14 2 2 6 2 2 6 62 62 62 74 74 74 30 30 30
-10 10 10 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 1 1 1 15 22 25 33 49 54 12 17 20 2 3 3 35 31 12
-56 77 35 20 16 6 1 1 1 18 25 28 21 31 35 11 15 17 1 1 1 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 10 10 10 34 34 34 78 78 78 50 50 50 6 6 6
-88 55 22 139 102 15 190 146 13 230 187 11 239 207 25 232 195 16 220 174 15 190 146 13
-171 120 8 192 133 9 210 150 10 213 154 11 185 146 40 165 152 80 101 98 89 2 2 6
-2 2 6 78 78 78 116 116 116 58 58 58 2 2 6 22 22 22 90 90 90 46 46 46
-18 18 18 6 6 6 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 1 1 1 27 40 45 29 43 47 3 5 6 2 3 3
-8 7 3 1 1 1 17 23 26 31 45 49 15 22 25 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 10 10 10 38 38 38 86 86 86 50 50 50 6 6 6
-124 127 131 168 158 138 156 107 11 171 120 8 204 160 10 184 138 11 197 138 11 200 144 11
-206 145 10 206 145 10 197 138 11 198 179 130 195 195 195 198 198 198 170 170 170 14 14 14
-2 2 6 22 22 22 116 116 116 116 116 116 22 22 22 2 2 6 74 74 74 70 70 70
-30 30 30 10 10 10 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 11 15 17 31 45 49 26 35 39 3 5 6
-0 0 0 7 12 13 27 40 45 18 25 28 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 6 6 6 18 18 18 50 50 50 101 101 101 26 26 26 10 10 10
-124 131 137 190 190 190 168 158 138 156 107 11 197 138 11 200 144 11 197 138 11 192 133 9
-180 123 7 185 146 40 198 179 130 187 187 187 202 202 202 221 221 221 214 214 214 66 66 66
-2 2 6 2 2 6 50 50 50 62 62 62 6 6 6 2 2 6 10 10 10 90 90 90
-50 50 50 18 18 18 6 6 6 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 1 1 1 15 22 25 36 54 60 18 25 28
-0 0 0 21 30 33 27 40 45 2 3 3 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 10 10 10 34 34 34 74 74 74 74 74 74 2 2 6 6 6 6
-151 151 151 198 198 198 190 190 190 168 158 138 148 132 55 156 107 11 156 107 11 169 125 40
-168 158 138 187 187 187 190 190 190 210 210 210 246 246 246 253 253 253 253 253 253 180 180 180
-6 6 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 62 62 62
-74 74 74 34 34 34 14 14 14 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 1 27 40 45 35 52 58
-18 25 28 35 52 58 17 23 26 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 10 10 10 22 22 22 54 54 54 94 94 94 18 18 18 2 2 6 46 46 46
-234 234 234 221 221 221 190 190 190 190 190 190 190 190 190 187 187 187 187 187 187 190 190 190
-190 190 190 195 195 195 214 214 214 242 242 242 253 253 253 253 253 253 253 253 253 253 253 253
-82 82 82 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 14 14 14
-86 86 86 54 54 54 22 22 22 6 6 6 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 7 12 13 33 49 54
-52 72 81 36 54 60 6 8 8 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-6 6 6 18 18 18 46 46 46 90 90 90 46 46 46 18 18 18 6 6 6 180 180 180
-253 253 253 246 246 246 202 202 202 190 190 190 190 190 190 190 190 190 190 190 190 190 190 190
-202 202 202 231 231 231 250 250 250 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-202 202 202 14 14 14 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6
-42 42 42 86 86 86 42 42 42 18 18 18 6 6 6 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 12 17 20
-36 54 60 29 43 47 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 6 6 6
-14 14 14 38 38 38 74 74 74 66 66 66 2 2 6 6 6 6 90 90 90 250 250 250
-253 253 253 253 253 253 238 238 238 198 198 198 190 190 190 190 190 190 195 195 195 221 221 221
-246 246 246 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 82 82 82 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6
-2 2 6 78 78 78 70 70 70 34 34 34 14 14 14 6 6 6 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-21 30 33 35 52 58 6 8 12 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 14 14 14
-34 34 34 66 66 66 78 78 78 6 6 6 2 2 6 18 18 18 218 218 218 253 253 253
-253 253 253 253 253 253 253 253 253 246 246 246 226 226 226 231 231 231 246 246 246 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 180 180 180 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6
-2 2 6 18 18 18 90 90 90 62 62 62 30 30 30 10 10 10 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-12 17 20 36 54 60 29 43 47 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 10 10 10 26 26 26
-58 58 58 90 90 90 18 18 18 2 2 6 2 2 6 106 106 106 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 250 250 250 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 231 231 231 18 18 18 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6
-2 2 6 2 2 6 18 18 18 94 94 94 54 54 54 26 26 26 10 10 10 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 21 30 33 35 52 58 6 8 12 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 6 6 6 22 22 22 50 50 50
-90 90 90 26 26 26 2 2 6 2 2 6 14 14 14 195 195 195 250 250 250 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-250 250 250 242 242 242 54 54 54 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6
-2 2 6 2 2 6 2 2 6 38 38 38 86 86 86 50 50 50 22 22 22 6 6 6
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 12 17 20 36 54 60 29 43 47 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 6 6 6 14 14 14 38 38 38 82 82 82
-34 34 34 2 2 6 2 2 6 2 2 6 42 42 42 195 195 195 246 246 246 253 253 253
-253 253 253 253 253 253 253 253 253 250 250 250 242 242 242 242 242 242 250 250 250 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 250 250 250 246 246 246 238 238 238
-226 226 226 231 231 231 101 101 101 6 6 6 2 2 6 2 2 6 2 2 6 2 2 6
-2 2 6 2 2 6 2 2 6 2 2 6 38 38 38 82 82 82 42 42 42 14 14 14
-6 6 6 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 21 30 33 35 52 58 6 8 12 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 10 10 10 26 26 26 62 62 62 66 66 66
-2 2 6 2 2 6 2 2 6 6 6 6 70 70 70 170 170 170 202 202 202 234 234 234
-246 246 246 250 250 250 250 250 250 238 238 238 226 226 226 231 231 231 238 238 238 250 250 250
-250 250 250 250 250 250 246 246 246 231 231 231 214 214 214 202 202 202 202 202 202 202 202 202
-198 198 198 202 202 202 180 180 180 18 18 18 2 2 6 2 2 6 2 2 6 2 2 6
-2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 62 62 62 66 66 66 30 30 30
-10 10 10 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 12 17 20 36 54 60 29 43 47 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 14 14 14 42 42 42 82 82 82 18 18 18
-2 2 6 2 2 6 2 2 6 10 10 10 94 94 94 180 180 180 218 218 218 242 242 242
-250 250 250 253 253 253 253 253 253 250 250 250 234 234 234 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 246 246 246 238 238 238 226 226 226 210 210 210 202 202 202
-195 195 195 195 195 195 210 210 210 151 151 151 6 6 6 14 14 14 50 50 50 14 14 14
-2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 6 6 6 86 86 86 46 46 46
-18 18 18 6 6 6 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 21 30 33 35 52 58 6 8 12 0 0 0
-0 0 0 0 0 0 0 0 0 6 6 6 22 22 22 54 54 54 70 70 70 2 2 6
-2 2 6 10 10 10 2 2 6 22 22 22 170 170 170 231 231 231 250 250 250 253 253 253
-253 253 253 253 253 253 253 253 253 250 250 250 242 242 242 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 246 246 246
-231 231 231 202 202 202 198 198 198 226 226 226 94 94 94 2 2 6 6 6 6 38 38 38
-30 30 30 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 62 62 62 66 66 66
-26 26 26 10 10 10 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 6 8 8 33 49 54 29 43 47 6 8 12
-0 0 0 0 0 0 0 0 0 10 10 10 30 30 30 74 74 74 50 50 50 2 2 6
-26 26 26 26 26 26 2 2 6 106 106 106 238 238 238 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 246 246 246 218 218 218 202 202 202 210 210 210 14 14 14 2 2 6 2 2 6
-30 30 30 22 22 22 2 2 6 2 2 6 2 2 6 2 2 6 18 18 18 86 86 86
-42 42 42 14 14 14 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 12 17 20 33 49 54 17 23 26
-0 0 0 0 0 0 0 0 0 14 14 14 42 42 42 90 90 90 22 22 22 2 2 6
-42 42 42 2 2 6 18 18 18 218 218 218 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 250 250 250 221 221 221 218 218 218 101 101 101 2 2 6 14 14 14
-18 18 18 38 38 38 10 10 10 2 2 6 2 2 6 2 2 6 2 2 6 78 78 78
-58 58 58 22 22 22 6 6 6 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 15 22 25 36 54 60
-0 0 0 0 0 0 0 0 0 18 18 18 54 54 54 82 82 82 2 2 6 26 26 26
-22 22 22 2 2 6 124 127 131 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 250 250 250 238 238 238 198 198 198 6 6 6 38 38 38
-58 58 58 26 26 26 38 38 38 2 2 6 2 2 6 2 2 6 2 2 6 46 46 46
-78 78 78 30 30 30 10 10 10 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 21 30 33
-36 54 60 0 0 0 0 0 0 30 30 30 74 74 74 58 58 58 2 2 6 42 42 42
-2 2 6 22 22 22 231 231 231 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 250 250 250 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 246 246 246 46 46 46 38 38 38
-42 42 42 14 14 14 38 38 38 14 14 14 2 2 6 2 2 6 2 2 6 6 6 6
-86 86 86 46 46 46 14 14 14 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-36 54 60 0 0 0 0 0 0 42 42 42 90 90 90 18 18 18 18 18 18 26 26 26
-2 2 6 116 116 116 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 250 250 250 238 238 238 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 94 94 94 6 6 6
-2 2 6 2 2 6 10 10 10 34 34 34 2 2 6 2 2 6 2 2 6 2 2 6
-74 74 74 58 58 58 22 22 22 6 6 6 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 36 54 60 26 26 26 66 66 66 82 82 82 2 2 6 38 38 38 6 6 6
-14 14 14 210 210 210 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 246 246 246 242 242 242 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 151 151 151 2 2 6
-2 2 6 2 2 6 2 2 6 46 46 46 2 2 6 2 2 6 2 2 6 2 2 6
-42 42 42 74 74 74 30 30 30 10 10 10 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-6 6 6 36 54 60 21 30 33 90 90 90 26 26 26 6 6 6 42 42 42 2 2 6
-74 74 74 250 250 250 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 242 242 242 242 242 242 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 180 180 180 2 2 6
-2 2 6 2 2 6 2 2 6 46 46 46 2 2 6 2 2 6 2 2 6 2 2 6
-10 10 10 86 86 86 38 38 38 10 10 10 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-10 10 10 26 26 26 36 54 60 82 82 82 2 2 6 22 22 22 18 18 18 2 2 6
-151 151 151 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 234 234 234 242 242 242 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 202 202 202 2 2 6
-2 2 6 2 2 6 2 2 6 38 38 38 2 2 6 2 2 6 2 2 6 2 2 6
-6 6 6 86 86 86 46 46 46 14 14 14 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 6 6 6
-18 18 18 46 46 46 86 86 86 36 54 60 2 2 6 34 34 34 10 10 10 6 6 6
-210 210 210 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 234 234 234 242 242 242 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 221 221 221 6 6 6
-2 2 6 2 2 6 6 6 6 30 30 30 2 2 6 2 2 6 2 2 6 2 2 6
-2 2 6 82 82 82 54 54 54 18 18 18 6 6 6 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 10 10 10
-26 26 26 66 66 66 62 62 62 2 2 6 2 2 6 38 38 38 10 10 10 26 26 26
-238 238 238 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 231 231 231 238 238 238 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 231 231 231 6 6 6
-2 2 6 2 2 6 10 10 10 30 30 30 2 2 6 2 2 6 2 2 6 2 2 6
-2 2 6 66 66 66 58 58 58 22 22 22 6 6 6 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 10 10 10
-38 38 38 78 78 78 6 6 6 2 2 6 2 2 6 46 46 46 14 14 14 42 42 42
-246 246 246 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 231 231 231 242 242 242 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 234 234 234 10 10 10
-2 2 6 2 2 6 22 22 22 14 14 14 2 2 6 2 2 6 2 2 6 2 2 6
-2 2 6 66 66 66 62 62 62 22 22 22 6 6 6 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 6 6 6 18 18 18
-50 50 50 74 74 74 2 2 6 2 2 6 14 14 14 70 70 70 34 34 34 62 62 62
-250 250 250 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 231 231 231 246 246 246 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 234 234 234 14 14 14
-2 2 6 2 2 6 30 30 30 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6
-2 2 6 66 66 66 62 62 62 22 22 22 6 6 6 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 6 6 6 18 18 18
-54 54 54 62 62 62 2 2 6 2 2 6 2 2 6 30 30 30 46 46 46 70 70 70
-250 250 250 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 231 231 231 246 246 246 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 226 226 226 10 10 10
-2 2 6 6 6 6 30 30 30 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6
-2 2 6 66 66 66 58 58 58 22 22 22 6 6 6 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 6 6 6 22 22 22
-58 58 58 62 62 62 2 2 6 2 2 6 2 2 6 2 2 6 30 30 30 78 78 78
-250 250 250 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 231 231 231 246 246 246 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 202 202 202 2 2 6
-22 22 22 34 34 34 20 16 6 22 22 22 26 26 26 18 18 18 6 6 6 2 2 6
-2 2 6 82 82 82 54 54 54 18 18 18 6 6 6 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 6 6 6 26 26 26
-62 62 62 106 106 106 63 55 20 184 138 11 204 160 10 121 92 8 6 6 6 62 62 62
-238 238 238 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 231 231 231 246 246 246 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 151 151 151 18 18 18
-14 14 14 2 2 6 2 2 6 2 2 6 6 6 6 18 18 18 66 66 66 38 38 38
-6 6 6 94 94 94 50 50 50 18 18 18 6 6 6 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 6 6 6 10 10 10 10 10 10 18 18 18 38 38 38
-78 78 78 138 132 106 216 158 10 242 186 14 246 190 14 246 190 14 156 118 10 10 10 10
-90 90 90 238 238 238 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 231 231 231 250 250 250 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 246 230 190 214 187 87 214 187 87 185 146 40 35 31 12
-2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 38 38 38 46 46 46
-26 26 26 106 106 106 54 54 54 18 18 18 6 6 6 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 6 6 6 14 14 14 22 22 22 30 30 30 38 38 38 50 50 50 70 70 70
-106 106 106 185 146 40 226 170 11 242 186 14 246 190 14 246 190 14 246 190 14 154 114 10
-6 6 6 74 74 74 226 226 226 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 231 231 231 250 250 250 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 237 201 50 241 196 14 241 208 19 232 195 16 35 31 12
-2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 6 6 6 30 30 30 26 26 26
-204 160 10 165 152 80 66 66 66 26 26 26 6 6 6 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-6 6 6 18 18 18 38 38 38 58 58 58 78 78 78 86 86 86 101 101 101 124 127 131
-174 140 55 210 150 10 234 174 13 246 186 14 246 190 14 246 190 14 246 190 14 237 188 10
-98 70 6 2 2 6 46 46 46 198 198 198 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 234 234 234 242 242 242 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 214 187 87 242 186 14 241 196 14 204 160 10 20 16 6
-2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 6 6 6 121 92 8
-238 202 15 232 195 16 82 82 82 34 34 34 10 10 10 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-14 14 14 38 38 38 70 70 70 148 132 55 185 146 40 200 144 11 197 138 11 197 138 11
-213 154 11 226 170 11 242 186 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14
-220 174 15 35 31 12 2 2 6 22 22 22 151 151 151 250 250 250 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 250 250 250 242 242 242 214 187 87 239 182 13 237 188 10 213 154 11 35 31 12
-2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 62 42 6 220 174 15
-237 188 10 237 188 10 113 101 86 42 42 42 14 14 14 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 6 6 6
-22 22 22 54 54 54 148 132 55 213 154 11 226 170 11 230 174 11 226 170 11 226 170 11
-236 178 12 242 186 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14
-241 196 14 184 138 11 10 10 10 2 2 6 6 6 6 116 116 116 242 242 242 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 231 231 231 198 198 198 213 164 39 236 178 12 236 178 12 210 150 10 137 92 6
-20 16 6 2 2 6 2 2 6 2 2 6 6 6 6 62 42 6 200 144 11 236 178 12
-239 182 13 239 182 13 124 112 88 58 58 58 22 22 22 6 6 6 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 10 10 10
-30 30 30 70 70 70 169 125 40 226 170 11 239 182 13 242 186 14 242 186 14 246 186 14
-246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14
-246 190 14 232 195 16 98 70 6 2 2 6 2 2 6 2 2 6 66 66 66 221 221 221
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 202 202 202 198 198 198 213 164 39 230 174 11 230 174 11 216 158 10 192 133 9
-163 110 8 120 80 7 98 70 6 120 80 7 167 114 7 197 138 11 226 170 11 239 182 13
-242 186 14 242 186 14 165 152 80 78 78 78 34 34 34 14 14 14 6 6 6 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 6 6 6
-30 30 30 78 78 78 185 146 40 226 170 11 239 182 13 246 190 14 246 190 14 246 190 14
-246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14
-246 190 14 241 196 14 204 160 10 20 16 6 2 2 6 2 2 6 2 2 6 38 38 38
-218 218 218 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-250 250 250 202 202 202 198 198 198 213 164 39 226 170 11 236 178 12 224 166 10 210 150 10
-200 144 11 197 138 11 192 133 9 197 138 11 210 150 10 226 170 11 242 186 14 246 190 14
-246 190 14 246 186 14 220 174 15 124 112 88 62 62 62 30 30 30 14 14 14 6 6 6
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 10 10 10
-30 30 30 78 78 78 174 140 55 224 166 10 239 182 13 246 190 14 246 190 14 246 190 14
-246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14
-246 190 14 246 190 14 241 196 14 139 102 15 2 2 6 2 2 6 2 2 6 2 2 6
-78 78 78 250 250 250 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-250 250 250 214 214 214 198 198 198 185 146 40 219 162 10 236 178 12 234 174 13 224 166 10
-216 158 10 213 154 11 213 154 11 216 158 10 226 170 11 239 182 13 246 190 14 246 190 14
-246 190 14 246 190 14 242 186 14 213 164 39 101 101 101 58 58 58 30 30 30 14 14 14
-6 6 6 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 10 10 10
-30 30 30 74 74 74 174 140 55 216 158 10 236 178 12 246 190 14 246 190 14 246 190 14
-246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14
-246 190 14 246 190 14 241 196 14 230 187 11 62 42 6 2 2 6 2 2 6 2 2 6
-22 22 22 238 238 238 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 226 226 226 187 187 187 169 125 40 216 158 10 236 178 12 239 182 13 236 178 12
-230 174 11 226 170 11 226 170 11 230 174 11 236 178 12 242 186 14 246 190 14 246 190 14
-246 190 14 246 190 14 246 186 14 239 182 13 213 164 39 106 106 106 66 66 66 34 34 34
-14 14 14 6 6 6 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 6 6 6
-26 26 26 70 70 70 149 139 69 213 154 11 236 178 12 246 190 14 246 190 14 246 190 14
-246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14
-246 190 14 246 190 14 246 190 14 241 196 14 190 146 13 20 16 6 2 2 6 2 2 6
-46 46 46 246 246 246 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 221 221 221 86 86 86 156 107 11 216 158 10 236 178 12 242 186 14 246 186 14
-242 186 14 239 182 13 239 182 13 242 186 14 242 186 14 246 186 14 246 190 14 246 190 14
-246 190 14 246 190 14 246 190 14 246 190 14 242 186 14 220 174 15 149 139 69 66 66 66
-30 30 30 10 10 10 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 6 6 6
-26 26 26 70 70 70 149 139 69 210 150 10 236 178 12 246 190 14 246 190 14 246 190 14
-246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14
-246 190 14 246 190 14 246 190 14 246 190 14 232 195 16 121 92 8 34 34 34 106 106 106
-221 221 221 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-242 242 242 82 82 82 20 16 6 163 110 8 216 158 10 236 178 12 242 186 14 246 190 14
-246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14
-246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 242 186 14 149 139 69
-46 46 46 18 18 18 6 6 6 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 10 10 10
-30 30 30 78 78 78 149 139 69 210 150 10 236 178 12 246 186 14 246 190 14 246 190 14
-246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14
-246 190 14 246 190 14 246 190 14 246 190 14 241 196 14 220 174 15 198 179 130 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 218 218 218
-58 58 58 2 2 6 20 16 6 167 114 7 216 158 10 236 178 12 246 186 14 246 190 14
-246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14
-246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 186 14 242 186 14 185 146 40
-54 54 54 22 22 22 6 6 6 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 14 14 14
-38 38 38 86 86 86 169 125 40 213 154 11 236 178 12 246 186 14 246 190 14 246 190 14
-246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14
-246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 232 195 16 190 146 13 214 214 214
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 250 250 250 170 170 170 26 26 26
-2 2 6 2 2 6 35 31 12 163 110 8 219 162 10 239 182 13 246 186 14 246 190 14
-246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14
-246 190 14 246 190 14 246 190 14 246 190 14 246 186 14 236 178 12 224 166 10 149 139 69
-46 46 46 18 18 18 6 6 6 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 6 6 6 18 18 18
-50 50 50 113 101 86 192 133 9 224 166 10 242 186 14 246 190 14 246 190 14 246 190 14
-246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14
-246 190 14 246 190 14 246 190 14 246 190 14 242 186 14 230 187 11 204 160 10 133 118 54
-226 226 226 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253 253
-253 253 253 253 253 253 253 253 253 253 253 253 198 198 198 66 66 66 2 2 6 2 2 6
-2 2 6 2 2 6 62 42 6 156 107 11 219 162 10 239 182 13 246 186 14 246 190 14
-246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14
-246 190 14 246 190 14 246 190 14 242 186 14 234 174 13 213 154 11 148 132 55 66 66 66
-30 30 30 10 10 10 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 6 6 6 22 22 22
-58 58 58 148 132 55 206 145 10 234 174 13 242 186 14 246 186 14 246 190 14 246 190 14
-246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14
-246 190 14 246 190 14 246 190 14 246 190 14 246 186 14 236 178 12 204 160 10 163 110 8
-62 42 6 124 131 137 218 218 218 250 250 250 253 253 253 253 253 253 253 253 253 250 250 250
-242 242 242 210 210 210 151 151 151 66 66 66 6 6 6 2 2 6 2 2 6 2 2 6
-2 2 6 2 2 6 62 42 6 163 110 8 216 158 10 236 178 12 246 190 14 246 190 14
-246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14
-246 190 14 239 182 13 230 174 11 216 158 10 185 146 40 124 112 88 70 70 70 38 38 38
-18 18 18 6 6 6 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 6 6 6 22 22 22
-62 62 62 169 125 40 206 145 10 224 166 10 236 178 12 239 182 13 242 186 14 242 186 14
-246 186 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 246 190 14
-246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 236 178 12 216 158 10 171 120 8
-85 57 6 2 2 6 6 6 6 30 30 30 54 54 54 62 62 62 50 50 50 38 38 38
-14 14 14 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6
-2 2 6 6 6 6 85 57 6 167 114 7 213 154 11 236 178 12 246 190 14 246 190 14
-246 190 14 246 190 14 246 190 14 246 190 14 246 190 14 242 186 14 239 182 13 239 182 13
-230 174 11 210 150 10 174 140 55 124 112 88 82 82 82 54 54 54 34 34 34 18 18 18
-6 6 6 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 6 6 6 18 18 18
-50 50 50 169 125 40 192 133 9 200 144 11 216 158 10 219 162 10 224 166 10 226 170 11
-230 174 11 236 178 12 239 182 13 239 182 13 242 186 14 246 186 14 246 190 14 246 190 14
-246 190 14 246 190 14 246 190 14 246 190 14 246 186 14 230 174 11 210 150 10 163 110 8
-104 69 6 10 10 10 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6
-2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6
-2 2 6 6 6 6 85 57 6 167 114 7 206 145 10 230 174 11 242 186 14 246 190 14
-246 190 14 246 190 14 246 186 14 242 186 14 239 182 13 230 174 11 224 166 10 213 154 11
-169 125 40 124 112 88 86 86 86 58 58 58 38 38 38 22 22 22 10 10 10 6 6 6
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 14 14 14
-34 34 34 70 70 70 133 118 54 169 125 40 167 114 7 180 123 7 192 133 9 197 138 11
-200 144 11 206 145 10 213 154 11 219 162 10 224 166 10 230 174 11 239 182 13 242 186 14
-246 186 14 246 186 14 246 186 14 246 186 14 239 182 13 216 158 10 184 138 11 152 99 6
-104 69 6 20 16 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6
-2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6 2 2 6
-2 2 6 6 6 6 85 57 6 152 99 6 192 133 9 219 162 10 236 178 12 239 182 13
-246 186 14 242 186 14 239 182 13 236 178 12 224 166 10 206 145 10 192 133 9 148 132 55
-94 94 94 62 62 62 42 42 42 22 22 22 14 14 14 6 6 6 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 6 6 6
-18 18 18 34 34 34 58 58 58 78 78 78 101 98 89 124 112 88 133 118 54 156 107 11
-163 110 8 167 114 7 171 120 8 180 123 7 184 138 11 197 138 11 210 150 10 219 162 10
-226 170 11 236 178 12 236 178 12 234 174 13 219 162 10 197 138 11 163 110 8 134 84 6
-85 57 6 10 10 10 2 2 6 2 2 6 18 18 18 38 38 38 38 38 38 38 38 38
-38 38 38 38 38 38 38 38 38 38 38 38 38 38 38 38 38 38 26 26 26 2 2 6
-2 2 6 6 6 6 62 42 6 137 92 6 171 120 8 200 144 11 219 162 10 230 174 11
-234 174 13 230 174 11 219 162 10 210 150 10 192 133 9 163 110 8 124 112 88 82 82 82
-50 50 50 30 30 30 14 14 14 6 6 6 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-6 6 6 14 14 14 22 22 22 34 34 34 42 42 42 58 58 58 74 74 74 86 86 86
-101 98 89 113 101 86 133 118 54 121 92 8 137 92 6 152 99 6 163 110 8 180 123 7
-184 138 11 197 138 11 206 145 10 200 144 11 180 123 7 156 107 11 134 84 6 104 69 6
-62 42 6 54 54 54 106 106 106 101 98 89 86 86 86 82 82 82 78 78 78 78 78 78
-78 78 78 78 78 78 78 78 78 78 78 78 78 78 78 82 82 82 86 86 86 94 94 94
-106 106 106 101 101 101 90 61 47 120 80 7 156 107 11 180 123 7 192 133 9 200 144 11
-206 145 10 200 144 11 192 133 9 171 120 8 139 102 15 113 101 86 70 70 70 42 42 42
-22 22 22 10 10 10 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 6 6 6 10 10 10 14 14 14 22 22 22 30 30 30 38 38 38
-50 50 50 62 62 62 74 74 74 90 90 90 101 98 89 113 101 86 121 92 8 120 80 7
-137 92 6 152 99 6 152 99 6 152 99 6 134 84 6 120 80 7 98 70 6 88 55 22
-101 98 89 82 82 82 58 58 58 46 46 46 38 38 38 34 34 34 34 34 34 34 34 34
-34 34 34 34 34 34 34 34 34 34 34 34 34 34 34 34 34 34 38 38 38 42 42 42
-54 54 54 82 82 82 94 86 71 85 57 6 134 84 6 156 107 11 167 114 7 171 120 8
-171 120 8 167 114 7 152 99 6 121 92 8 101 98 89 62 62 62 34 34 34 18 18 18
-6 6 6 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 6 6 6 6 6 6 10 10 10
-18 18 18 22 22 22 30 30 30 42 42 42 50 50 50 66 66 66 86 86 86 101 98 89
-94 86 71 98 70 6 104 69 6 104 69 6 104 69 6 85 57 6 88 55 22 90 90 90
-62 62 62 38 38 38 22 22 22 14 14 14 10 10 10 10 10 10 10 10 10 10 10 10
-10 10 10 10 10 10 6 6 6 10 10 10 10 10 10 10 10 10 10 10 10 14 14 14
-22 22 22 42 42 42 70 70 70 94 86 71 85 57 6 104 69 6 120 80 7 137 92 6
-134 84 6 120 80 7 94 86 71 86 86 86 58 58 58 30 30 30 14 14 14 6 6 6
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 6 6 6 10 10 10 14 14 14 18 18 18 26 26 26 38 38 38 54 54 54
-70 70 70 86 86 86 94 86 71 94 86 71 94 86 71 86 86 86 74 74 74 50 50 50
-30 30 30 14 14 14 6 6 6 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-6 6 6 18 18 18 34 34 34 58 58 58 82 82 82 94 86 71 94 86 71 94 86 71
-94 86 71 94 86 71 74 74 74 50 50 50 26 26 26 14 14 14 6 6 6 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 6 6 6 6 6 6 14 14 14 18 18 18
-30 30 30 38 38 38 46 46 46 54 54 54 50 50 50 42 42 42 30 30 30 18 18 18
-10 10 10 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 6 6 6 14 14 14 26 26 26 38 38 38 50 50 50 58 58 58 58 58 58
-54 54 54 42 42 42 30 30 30 18 18 18 10 10 10 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 6 6 6
-6 6 6 10 10 10 14 14 14 18 18 18 18 18 18 14 14 14 10 10 10 6 6 6
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 6 6 6 14 14 14 18 18 18 22 22 22 22 22 22
-18 18 18 14 14 14 10 10 10 6 6 6 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
-
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 6 6 6 6 6 6 10 10 10 10 10 10
+ 10 10 10 6 6 6 6 6 6 6 6 6
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 6 6 6 10 10 10 14 14 14
+ 22 22 22 26 26 26 30 30 30 34 34 34
+ 30 30 30 30 30 30 26 26 26 18 18 18
+ 14 14 14 10 10 10 6 6 6 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 1 0 0 1 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 6 6 6 14 14 14 26 26 26 42 42 42
+ 54 54 54 66 66 66 78 78 78 78 78 78
+ 78 78 78 74 74 74 66 66 66 54 54 54
+ 42 42 42 26 26 26 18 18 18 10 10 10
+ 6 6 6 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 1 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 10 10 10
+ 22 22 22 42 42 42 66 66 66 86 86 86
+ 66 66 66 38 38 38 38 38 38 22 22 22
+ 26 26 26 34 34 34 54 54 54 66 66 66
+ 86 86 86 70 70 70 46 46 46 26 26 26
+ 14 14 14 6 6 6 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 1 0 0 1 0 0 1 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 10 10 10 26 26 26
+ 50 50 50 82 82 82 58 58 58 6 6 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 6 6 6 54 54 54 86 86 86 66 66 66
+ 38 38 38 18 18 18 6 6 6 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 6 6 6 22 22 22 50 50 50
+ 78 78 78 34 34 34 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 6 6 6 70 70 70
+ 78 78 78 46 46 46 22 22 22 6 6 6
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 1 0 0 1 0 0 1 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 6 6 6 18 18 18 42 42 42 82 82 82
+ 26 26 26 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 14 14 14
+ 46 46 46 34 34 34 6 6 6 2 2 6
+ 42 42 42 78 78 78 42 42 42 18 18 18
+ 6 6 6 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 1 0 0 0 0 0 1 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 10 10 10 30 30 30 66 66 66 58 58 58
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 26 26 26
+ 86 86 86 101 101 101 46 46 46 10 10 10
+ 2 2 6 58 58 58 70 70 70 34 34 34
+ 10 10 10 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 1 0 0 1 0 0 1 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 14 14 14 42 42 42 86 86 86 10 10 10
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 30 30 30
+ 94 94 94 94 94 94 58 58 58 26 26 26
+ 2 2 6 6 6 6 78 78 78 54 54 54
+ 22 22 22 6 6 6 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 6 6 6
+ 22 22 22 62 62 62 62 62 62 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 26 26 26
+ 54 54 54 38 38 38 18 18 18 10 10 10
+ 2 2 6 2 2 6 34 34 34 82 82 82
+ 38 38 38 14 14 14 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 1 0 0 1 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 6 6 6
+ 30 30 30 78 78 78 30 30 30 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 10 10 10
+ 10 10 10 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 78 78 78
+ 50 50 50 18 18 18 6 6 6 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 1 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 10 10 10
+ 38 38 38 86 86 86 14 14 14 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 54 54 54
+ 66 66 66 26 26 26 6 6 6 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 1 0 0 1 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 14 14 14
+ 42 42 42 82 82 82 2 2 6 2 2 6
+ 2 2 6 6 6 6 10 10 10 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 6 6 6
+ 14 14 14 10 10 10 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 18 18 18
+ 82 82 82 34 34 34 10 10 10 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 1 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 14 14 14
+ 46 46 46 86 86 86 2 2 6 2 2 6
+ 6 6 6 6 6 6 22 22 22 34 34 34
+ 6 6 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 18 18 18 34 34 34
+ 10 10 10 50 50 50 22 22 22 2 2 6
+ 2 2 6 2 2 6 2 2 6 10 10 10
+ 86 86 86 42 42 42 14 14 14 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 1 0 0 1 0 0 1 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 14 14 14
+ 46 46 46 86 86 86 2 2 6 2 2 6
+ 38 38 38 116 116 116 94 94 94 22 22 22
+ 22 22 22 2 2 6 2 2 6 2 2 6
+ 14 14 14 86 86 86 138 138 138 162 162 162
+154 154 154 38 38 38 26 26 26 6 6 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 86 86 86 46 46 46 14 14 14 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 14 14 14
+ 46 46 46 86 86 86 2 2 6 14 14 14
+134 134 134 198 198 198 195 195 195 116 116 116
+ 10 10 10 2 2 6 2 2 6 6 6 6
+101 98 89 187 187 187 210 210 210 218 218 218
+214 214 214 134 134 134 14 14 14 6 6 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 86 86 86 50 50 50 18 18 18 6 6 6
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 1 0 0 0
+ 0 0 1 0 0 1 0 0 1 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 14 14 14
+ 46 46 46 86 86 86 2 2 6 54 54 54
+218 218 218 195 195 195 226 226 226 246 246 246
+ 58 58 58 2 2 6 2 2 6 30 30 30
+210 210 210 253 253 253 174 174 174 123 123 123
+221 221 221 234 234 234 74 74 74 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 70 70 70 58 58 58 22 22 22 6 6 6
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 14 14 14
+ 46 46 46 82 82 82 2 2 6 106 106 106
+170 170 170 26 26 26 86 86 86 226 226 226
+123 123 123 10 10 10 14 14 14 46 46 46
+231 231 231 190 190 190 6 6 6 70 70 70
+ 90 90 90 238 238 238 158 158 158 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 70 70 70 58 58 58 22 22 22 6 6 6
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 1 0 0 0
+ 0 0 1 0 0 1 0 0 1 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 14 14 14
+ 42 42 42 86 86 86 6 6 6 116 116 116
+106 106 106 6 6 6 70 70 70 149 149 149
+128 128 128 18 18 18 38 38 38 54 54 54
+221 221 221 106 106 106 2 2 6 14 14 14
+ 46 46 46 190 190 190 198 198 198 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 74 74 74 62 62 62 22 22 22 6 6 6
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 1 0 0 0
+ 0 0 1 0 0 0 0 0 1 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 14 14 14
+ 42 42 42 94 94 94 14 14 14 101 101 101
+128 128 128 2 2 6 18 18 18 116 116 116
+118 98 46 121 92 8 121 92 8 98 78 10
+162 162 162 106 106 106 2 2 6 2 2 6
+ 2 2 6 195 195 195 195 195 195 6 6 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 74 74 74 62 62 62 22 22 22 6 6 6
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 1 0 0 1
+ 0 0 1 0 0 0 0 0 1 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 10 10 10
+ 38 38 38 90 90 90 14 14 14 58 58 58
+210 210 210 26 26 26 54 38 6 154 114 10
+226 170 11 236 186 11 225 175 15 184 144 12
+215 174 15 175 146 61 37 26 9 2 2 6
+ 70 70 70 246 246 246 138 138 138 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 70 70 70 66 66 66 26 26 26 6 6 6
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 10 10 10
+ 38 38 38 86 86 86 14 14 14 10 10 10
+195 195 195 188 164 115 192 133 9 225 175 15
+239 182 13 234 190 10 232 195 16 232 200 30
+245 207 45 241 208 19 232 195 16 184 144 12
+218 194 134 211 206 186 42 42 42 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 50 50 50 74 74 74 30 30 30 6 6 6
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 10 10 10
+ 34 34 34 86 86 86 14 14 14 2 2 6
+121 87 25 192 133 9 219 162 10 239 182 13
+236 186 11 232 195 16 241 208 19 244 214 54
+246 218 60 246 218 38 246 215 20 241 208 19
+241 208 19 226 184 13 121 87 25 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 50 50 50 82 82 82 34 34 34 10 10 10
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 10 10 10
+ 34 34 34 82 82 82 30 30 30 61 42 6
+180 123 7 206 145 10 230 174 11 239 182 13
+234 190 10 238 202 15 241 208 19 246 218 74
+246 218 38 246 215 20 246 215 20 246 215 20
+226 184 13 215 174 15 184 144 12 6 6 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 26 26 26 94 94 94 42 42 42 14 14 14
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 10 10 10
+ 30 30 30 78 78 78 50 50 50 104 69 6
+192 133 9 216 158 10 236 178 12 236 186 11
+232 195 16 241 208 19 244 214 54 245 215 43
+246 215 20 246 215 20 241 208 19 198 155 10
+200 144 11 216 158 10 156 118 10 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 6 6 6 90 90 90 54 54 54 18 18 18
+ 6 6 6 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 10 10 10
+ 30 30 30 78 78 78 46 46 46 22 22 22
+137 92 6 210 162 10 239 182 13 238 190 10
+238 202 15 241 208 19 246 215 20 246 215 20
+241 208 19 203 166 17 185 133 11 210 150 10
+216 158 10 210 150 10 102 78 10 2 2 6
+ 6 6 6 54 54 54 14 14 14 2 2 6
+ 2 2 6 62 62 62 74 74 74 30 30 30
+ 10 10 10 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 10 10 10
+ 34 34 34 78 78 78 50 50 50 6 6 6
+ 94 70 30 139 102 15 190 146 13 226 184 13
+232 200 30 232 195 16 215 174 15 190 146 13
+168 122 10 192 133 9 210 150 10 213 154 11
+202 150 34 182 157 106 101 98 89 2 2 6
+ 2 2 6 78 78 78 116 116 116 58 58 58
+ 2 2 6 22 22 22 90 90 90 46 46 46
+ 18 18 18 6 6 6 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 10 10 10
+ 38 38 38 86 86 86 50 50 50 6 6 6
+128 128 128 174 154 114 156 107 11 168 122 10
+198 155 10 184 144 12 197 138 11 200 144 11
+206 145 10 206 145 10 197 138 11 188 164 115
+195 195 195 198 198 198 174 174 174 14 14 14
+ 2 2 6 22 22 22 116 116 116 116 116 116
+ 22 22 22 2 2 6 74 74 74 70 70 70
+ 30 30 30 10 10 10 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 6 6 6 18 18 18
+ 50 50 50 101 101 101 26 26 26 10 10 10
+138 138 138 190 190 190 174 154 114 156 107 11
+197 138 11 200 144 11 197 138 11 192 133 9
+180 123 7 190 142 34 190 178 144 187 187 187
+202 202 202 221 221 221 214 214 214 66 66 66
+ 2 2 6 2 2 6 50 50 50 62 62 62
+ 6 6 6 2 2 6 10 10 10 90 90 90
+ 50 50 50 18 18 18 6 6 6 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 10 10 10 34 34 34
+ 74 74 74 74 74 74 2 2 6 6 6 6
+144 144 144 198 198 198 190 190 190 178 166 146
+154 121 60 156 107 11 156 107 11 168 124 44
+174 154 114 187 187 187 190 190 190 210 210 210
+246 246 246 253 253 253 253 253 253 182 182 182
+ 6 6 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 62 62 62
+ 74 74 74 34 34 34 14 14 14 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 10 10 10 22 22 22 54 54 54
+ 94 94 94 18 18 18 2 2 6 46 46 46
+234 234 234 221 221 221 190 190 190 190 190 190
+190 190 190 187 187 187 187 187 187 190 190 190
+190 190 190 195 195 195 214 214 214 242 242 242
+253 253 253 253 253 253 253 253 253 253 253 253
+ 82 82 82 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 14 14 14
+ 86 86 86 54 54 54 22 22 22 6 6 6
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 6 6 6 18 18 18 46 46 46 90 90 90
+ 46 46 46 18 18 18 6 6 6 182 182 182
+253 253 253 246 246 246 206 206 206 190 190 190
+190 190 190 190 190 190 190 190 190 190 190 190
+206 206 206 231 231 231 250 250 250 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+202 202 202 14 14 14 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 42 42 42 86 86 86 42 42 42 18 18 18
+ 6 6 6 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 6 6 6
+ 14 14 14 38 38 38 74 74 74 66 66 66
+ 2 2 6 6 6 6 90 90 90 250 250 250
+253 253 253 253 253 253 238 238 238 198 198 198
+190 190 190 190 190 190 195 195 195 221 221 221
+246 246 246 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 82 82 82 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 78 78 78 70 70 70 34 34 34
+ 14 14 14 6 6 6 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 14 14 14
+ 34 34 34 66 66 66 78 78 78 6 6 6
+ 2 2 6 18 18 18 218 218 218 253 253 253
+253 253 253 253 253 253 253 253 253 246 246 246
+226 226 226 231 231 231 246 246 246 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 178 178 178 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 18 18 18 90 90 90 62 62 62
+ 30 30 30 10 10 10 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 10 10 10 26 26 26
+ 58 58 58 90 90 90 18 18 18 2 2 6
+ 2 2 6 110 110 110 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+250 250 250 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 231 231 231 18 18 18 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 18 18 18 94 94 94
+ 54 54 54 26 26 26 10 10 10 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 6 6 6 22 22 22 50 50 50
+ 90 90 90 26 26 26 2 2 6 2 2 6
+ 14 14 14 195 195 195 250 250 250 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+250 250 250 242 242 242 54 54 54 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 38 38 38
+ 86 86 86 50 50 50 22 22 22 6 6 6
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 6 6 6 14 14 14 38 38 38 82 82 82
+ 34 34 34 2 2 6 2 2 6 2 2 6
+ 42 42 42 195 195 195 246 246 246 253 253 253
+253 253 253 253 253 253 253 253 253 250 250 250
+242 242 242 242 242 242 250 250 250 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 250 250 250 246 246 246 238 238 238
+226 226 226 231 231 231 101 101 101 6 6 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 38 38 38 82 82 82 42 42 42 14 14 14
+ 6 6 6 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 10 10 10 26 26 26 62 62 62 66 66 66
+ 2 2 6 2 2 6 2 2 6 6 6 6
+ 70 70 70 170 170 170 206 206 206 234 234 234
+246 246 246 250 250 250 250 250 250 238 238 238
+226 226 226 231 231 231 238 238 238 250 250 250
+250 250 250 250 250 250 246 246 246 231 231 231
+214 214 214 206 206 206 202 202 202 202 202 202
+198 198 198 202 202 202 182 182 182 18 18 18
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 62 62 62 66 66 66 30 30 30
+ 10 10 10 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 14 14 14 42 42 42 82 82 82 18 18 18
+ 2 2 6 2 2 6 2 2 6 10 10 10
+ 94 94 94 182 182 182 218 218 218 242 242 242
+250 250 250 253 253 253 253 253 253 250 250 250
+234 234 234 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 246 246 246
+238 238 238 226 226 226 210 210 210 202 202 202
+195 195 195 195 195 195 210 210 210 158 158 158
+ 6 6 6 14 14 14 50 50 50 14 14 14
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 6 6 6 86 86 86 46 46 46
+ 18 18 18 6 6 6 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 6 6 6
+ 22 22 22 54 54 54 70 70 70 2 2 6
+ 2 2 6 10 10 10 2 2 6 22 22 22
+166 166 166 231 231 231 250 250 250 253 253 253
+253 253 253 253 253 253 253 253 253 250 250 250
+242 242 242 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 246 246 246
+231 231 231 206 206 206 198 198 198 226 226 226
+ 94 94 94 2 2 6 6 6 6 38 38 38
+ 30 30 30 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 62 62 62 66 66 66
+ 26 26 26 10 10 10 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 10 10 10
+ 30 30 30 74 74 74 50 50 50 2 2 6
+ 26 26 26 26 26 26 2 2 6 106 106 106
+238 238 238 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 246 246 246 218 218 218 202 202 202
+210 210 210 14 14 14 2 2 6 2 2 6
+ 30 30 30 22 22 22 2 2 6 2 2 6
+ 2 2 6 2 2 6 18 18 18 86 86 86
+ 42 42 42 14 14 14 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 14 14 14
+ 42 42 42 90 90 90 22 22 22 2 2 6
+ 42 42 42 2 2 6 18 18 18 218 218 218
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 250 250 250 221 221 221
+218 218 218 101 101 101 2 2 6 14 14 14
+ 18 18 18 38 38 38 10 10 10 2 2 6
+ 2 2 6 2 2 6 2 2 6 78 78 78
+ 58 58 58 22 22 22 6 6 6 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 6 6 6 18 18 18
+ 54 54 54 82 82 82 2 2 6 26 26 26
+ 22 22 22 2 2 6 123 123 123 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 250 250 250
+238 238 238 198 198 198 6 6 6 38 38 38
+ 58 58 58 26 26 26 38 38 38 2 2 6
+ 2 2 6 2 2 6 2 2 6 46 46 46
+ 78 78 78 30 30 30 10 10 10 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 10 10 10 30 30 30
+ 74 74 74 58 58 58 2 2 6 42 42 42
+ 2 2 6 22 22 22 231 231 231 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 250 250 250
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 246 246 246 46 46 46 38 38 38
+ 42 42 42 14 14 14 38 38 38 14 14 14
+ 2 2 6 2 2 6 2 2 6 6 6 6
+ 86 86 86 46 46 46 14 14 14 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 6 6 6 14 14 14 42 42 42
+ 90 90 90 18 18 18 18 18 18 26 26 26
+ 2 2 6 116 116 116 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 250 250 250 238 238 238
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 94 94 94 6 6 6
+ 2 2 6 2 2 6 10 10 10 34 34 34
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 74 74 74 58 58 58 22 22 22 6 6 6
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 10 10 10 26 26 26 66 66 66
+ 82 82 82 2 2 6 38 38 38 6 6 6
+ 14 14 14 210 210 210 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 246 246 246 242 242 242
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 144 144 144 2 2 6
+ 2 2 6 2 2 6 2 2 6 46 46 46
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 42 42 42 74 74 74 30 30 30 10 10 10
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 6 6 6 14 14 14 42 42 42 90 90 90
+ 26 26 26 6 6 6 42 42 42 2 2 6
+ 74 74 74 250 250 250 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 242 242 242 242 242 242
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 182 182 182 2 2 6
+ 2 2 6 2 2 6 2 2 6 46 46 46
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 10 10 10 86 86 86 38 38 38 10 10 10
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 10 10 10 26 26 26 66 66 66 82 82 82
+ 2 2 6 22 22 22 18 18 18 2 2 6
+149 149 149 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 234 234 234 242 242 242
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 206 206 206 2 2 6
+ 2 2 6 2 2 6 2 2 6 38 38 38
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 6 6 6 86 86 86 46 46 46 14 14 14
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 6 6 6
+ 18 18 18 46 46 46 86 86 86 18 18 18
+ 2 2 6 34 34 34 10 10 10 6 6 6
+210 210 210 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 234 234 234 242 242 242
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 221 221 221 6 6 6
+ 2 2 6 2 2 6 6 6 6 30 30 30
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 82 82 82 54 54 54 18 18 18
+ 6 6 6 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 10 10 10
+ 26 26 26 66 66 66 62 62 62 2 2 6
+ 2 2 6 38 38 38 10 10 10 26 26 26
+238 238 238 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 231 231 231 238 238 238
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 231 231 231 6 6 6
+ 2 2 6 2 2 6 10 10 10 30 30 30
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 66 66 66 58 58 58 22 22 22
+ 6 6 6 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 10 10 10
+ 38 38 38 78 78 78 6 6 6 2 2 6
+ 2 2 6 46 46 46 14 14 14 42 42 42
+246 246 246 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 231 231 231 242 242 242
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 234 234 234 10 10 10
+ 2 2 6 2 2 6 22 22 22 14 14 14
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 66 66 66 62 62 62 22 22 22
+ 6 6 6 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 6 6 6 18 18 18
+ 50 50 50 74 74 74 2 2 6 2 2 6
+ 14 14 14 70 70 70 34 34 34 62 62 62
+250 250 250 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 231 231 231 246 246 246
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 234 234 234 14 14 14
+ 2 2 6 2 2 6 30 30 30 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 66 66 66 62 62 62 22 22 22
+ 6 6 6 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 6 6 6 18 18 18
+ 54 54 54 62 62 62 2 2 6 2 2 6
+ 2 2 6 30 30 30 46 46 46 70 70 70
+250 250 250 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 231 231 231 246 246 246
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 226 226 226 10 10 10
+ 2 2 6 6 6 6 30 30 30 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 66 66 66 58 58 58 22 22 22
+ 6 6 6 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 6 6 6 22 22 22
+ 58 58 58 62 62 62 2 2 6 2 2 6
+ 2 2 6 2 2 6 30 30 30 78 78 78
+250 250 250 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 231 231 231 246 246 246
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 206 206 206 2 2 6
+ 22 22 22 34 34 34 18 14 6 22 22 22
+ 26 26 26 18 18 18 6 6 6 2 2 6
+ 2 2 6 82 82 82 54 54 54 18 18 18
+ 6 6 6 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 6 6 6 26 26 26
+ 62 62 62 106 106 106 74 54 14 185 133 11
+210 162 10 121 92 8 6 6 6 62 62 62
+238 238 238 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 231 231 231 246 246 246
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 158 158 158 18 18 18
+ 14 14 14 2 2 6 2 2 6 2 2 6
+ 6 6 6 18 18 18 66 66 66 38 38 38
+ 6 6 6 94 94 94 50 50 50 18 18 18
+ 6 6 6 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 6 6 6
+ 10 10 10 10 10 10 18 18 18 38 38 38
+ 78 78 78 142 134 106 216 158 10 242 186 14
+246 190 14 246 190 14 156 118 10 10 10 10
+ 90 90 90 238 238 238 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 231 231 231 250 250 250
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 246 230 190
+238 204 91 238 204 91 181 142 44 37 26 9
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 38 38 38 46 46 46
+ 26 26 26 106 106 106 54 54 54 18 18 18
+ 6 6 6 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 6 6 6 14 14 14 22 22 22
+ 30 30 30 38 38 38 50 50 50 70 70 70
+106 106 106 190 142 34 226 170 11 242 186 14
+246 190 14 246 190 14 246 190 14 154 114 10
+ 6 6 6 74 74 74 226 226 226 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 231 231 231 250 250 250
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 228 184 62
+241 196 14 241 208 19 232 195 16 38 30 10
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 6 6 6 30 30 30 26 26 26
+203 166 17 154 142 90 66 66 66 26 26 26
+ 6 6 6 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 6 6 6 18 18 18 38 38 38 58 58 58
+ 78 78 78 86 86 86 101 101 101 123 123 123
+175 146 61 210 150 10 234 174 13 246 186 14
+246 190 14 246 190 14 246 190 14 238 190 10
+102 78 10 2 2 6 46 46 46 198 198 198
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 234 234 234 242 242 242
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 224 178 62
+242 186 14 241 196 14 210 166 10 22 18 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 6 6 6 121 92 8
+238 202 15 232 195 16 82 82 82 34 34 34
+ 10 10 10 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 14 14 14 38 38 38 70 70 70 154 122 46
+190 142 34 200 144 11 197 138 11 197 138 11
+213 154 11 226 170 11 242 186 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+225 175 15 46 32 6 2 2 6 22 22 22
+158 158 158 250 250 250 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 250 250 250 242 242 242 224 178 62
+239 182 13 236 186 11 213 154 11 46 32 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 61 42 6 225 175 15
+238 190 10 236 186 11 112 100 78 42 42 42
+ 14 14 14 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 6 6 6
+ 22 22 22 54 54 54 154 122 46 213 154 11
+226 170 11 230 174 11 226 170 11 226 170 11
+236 178 12 242 186 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+241 196 14 184 144 12 10 10 10 2 2 6
+ 6 6 6 116 116 116 242 242 242 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 231 231 231 198 198 198 214 170 54
+236 178 12 236 178 12 210 150 10 137 92 6
+ 18 14 6 2 2 6 2 2 6 2 2 6
+ 6 6 6 70 47 6 200 144 11 236 178 12
+239 182 13 239 182 13 124 112 88 58 58 58
+ 22 22 22 6 6 6 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 10 10 10
+ 30 30 30 70 70 70 180 133 36 226 170 11
+239 182 13 242 186 14 242 186 14 246 186 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 232 195 16 98 70 6 2 2 6
+ 2 2 6 2 2 6 66 66 66 221 221 221
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 206 206 206 198 198 198 214 166 58
+230 174 11 230 174 11 216 158 10 192 133 9
+163 110 8 116 81 8 102 78 10 116 81 8
+167 114 7 197 138 11 226 170 11 239 182 13
+242 186 14 242 186 14 162 146 94 78 78 78
+ 34 34 34 14 14 14 6 6 6 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 6 6 6
+ 30 30 30 78 78 78 190 142 34 226 170 11
+239 182 13 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 241 196 14 203 166 17 22 18 6
+ 2 2 6 2 2 6 2 2 6 38 38 38
+218 218 218 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+250 250 250 206 206 206 198 198 198 202 162 69
+226 170 11 236 178 12 224 166 10 210 150 10
+200 144 11 197 138 11 192 133 9 197 138 11
+210 150 10 226 170 11 242 186 14 246 190 14
+246 190 14 246 186 14 225 175 15 124 112 88
+ 62 62 62 30 30 30 14 14 14 6 6 6
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 10 10 10
+ 30 30 30 78 78 78 174 135 50 224 166 10
+239 182 13 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 241 196 14 139 102 15
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 78 78 78 250 250 250 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+250 250 250 214 214 214 198 198 198 190 150 46
+219 162 10 236 178 12 234 174 13 224 166 10
+216 158 10 213 154 11 213 154 11 216 158 10
+226 170 11 239 182 13 246 190 14 246 190 14
+246 190 14 246 190 14 242 186 14 206 162 42
+101 101 101 58 58 58 30 30 30 14 14 14
+ 6 6 6 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 10 10 10
+ 30 30 30 74 74 74 174 135 50 216 158 10
+236 178 12 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 241 196 14 226 184 13
+ 61 42 6 2 2 6 2 2 6 2 2 6
+ 22 22 22 238 238 238 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 226 226 226 187 187 187 180 133 36
+216 158 10 236 178 12 239 182 13 236 178 12
+230 174 11 226 170 11 226 170 11 230 174 11
+236 178 12 242 186 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 186 14 239 182 13
+206 162 42 106 106 106 66 66 66 34 34 34
+ 14 14 14 6 6 6 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 6 6 6
+ 26 26 26 70 70 70 163 133 67 213 154 11
+236 178 12 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 241 196 14
+190 146 13 18 14 6 2 2 6 2 2 6
+ 46 46 46 246 246 246 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 221 221 221 86 86 86 156 107 11
+216 158 10 236 178 12 242 186 14 246 186 14
+242 186 14 239 182 13 239 182 13 242 186 14
+242 186 14 246 186 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+242 186 14 225 175 15 142 122 72 66 66 66
+ 30 30 30 10 10 10 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 6 6 6
+ 26 26 26 70 70 70 163 133 67 210 150 10
+236 178 12 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+232 195 16 121 92 8 34 34 34 106 106 106
+221 221 221 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+242 242 242 82 82 82 18 14 6 163 110 8
+216 158 10 236 178 12 242 186 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 242 186 14 163 133 67
+ 46 46 46 18 18 18 6 6 6 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 10 10 10
+ 30 30 30 78 78 78 163 133 67 210 150 10
+236 178 12 246 186 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+241 196 14 215 174 15 190 178 144 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 218 218 218
+ 58 58 58 2 2 6 22 18 6 167 114 7
+216 158 10 236 178 12 246 186 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 186 14 242 186 14 190 150 46
+ 54 54 54 22 22 22 6 6 6 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 14 14 14
+ 38 38 38 86 86 86 180 133 36 213 154 11
+236 178 12 246 186 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 232 195 16 190 146 13 214 214 214
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 250 250 250 170 170 170 26 26 26
+ 2 2 6 2 2 6 37 26 9 163 110 8
+219 162 10 239 182 13 246 186 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 186 14 236 178 12 224 166 10 142 122 72
+ 46 46 46 18 18 18 6 6 6 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 6 6 6 18 18 18
+ 50 50 50 109 106 95 192 133 9 224 166 10
+242 186 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+242 186 14 226 184 13 210 162 10 142 110 46
+226 226 226 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+253 253 253 253 253 253 253 253 253 253 253 253
+198 198 198 66 66 66 2 2 6 2 2 6
+ 2 2 6 2 2 6 50 34 6 156 107 11
+219 162 10 239 182 13 246 186 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 242 186 14
+234 174 13 213 154 11 154 122 46 66 66 66
+ 30 30 30 10 10 10 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 6 6 6 22 22 22
+ 58 58 58 154 121 60 206 145 10 234 174 13
+242 186 14 246 186 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 186 14 236 178 12 210 162 10 163 110 8
+ 61 42 6 138 138 138 218 218 218 250 250 250
+253 253 253 253 253 253 253 253 253 250 250 250
+242 242 242 210 210 210 144 144 144 66 66 66
+ 6 6 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 61 42 6 163 110 8
+216 158 10 236 178 12 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 239 182 13 230 174 11 216 158 10
+190 142 34 124 112 88 70 70 70 38 38 38
+ 18 18 18 6 6 6 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 6 6 6 22 22 22
+ 62 62 62 168 124 44 206 145 10 224 166 10
+236 178 12 239 182 13 242 186 14 242 186 14
+246 186 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 236 178 12 216 158 10 175 118 6
+ 80 54 7 2 2 6 6 6 6 30 30 30
+ 54 54 54 62 62 62 50 50 50 38 38 38
+ 14 14 14 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 6 6 6 80 54 7 167 114 7
+213 154 11 236 178 12 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 190 14 242 186 14 239 182 13 239 182 13
+230 174 11 210 150 10 174 135 50 124 112 88
+ 82 82 82 54 54 54 34 34 34 18 18 18
+ 6 6 6 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 6 6 6 18 18 18
+ 50 50 50 158 118 36 192 133 9 200 144 11
+216 158 10 219 162 10 224 166 10 226 170 11
+230 174 11 236 178 12 239 182 13 239 182 13
+242 186 14 246 186 14 246 190 14 246 190 14
+246 190 14 246 190 14 246 190 14 246 190 14
+246 186 14 230 174 11 210 150 10 163 110 8
+104 69 6 10 10 10 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 6 6 6 91 60 6 167 114 7
+206 145 10 230 174 11 242 186 14 246 190 14
+246 190 14 246 190 14 246 186 14 242 186 14
+239 182 13 230 174 11 224 166 10 213 154 11
+180 133 36 124 112 88 86 86 86 58 58 58
+ 38 38 38 22 22 22 10 10 10 6 6 6
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 14 14 14
+ 34 34 34 70 70 70 138 110 50 158 118 36
+167 114 7 180 123 7 192 133 9 197 138 11
+200 144 11 206 145 10 213 154 11 219 162 10
+224 166 10 230 174 11 239 182 13 242 186 14
+246 186 14 246 186 14 246 186 14 246 186 14
+239 182 13 216 158 10 185 133 11 152 99 6
+104 69 6 18 14 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 2 2 6 2 2 6 2 2 6
+ 2 2 6 6 6 6 80 54 7 152 99 6
+192 133 9 219 162 10 236 178 12 239 182 13
+246 186 14 242 186 14 239 182 13 236 178 12
+224 166 10 206 145 10 192 133 9 154 121 60
+ 94 94 94 62 62 62 42 42 42 22 22 22
+ 14 14 14 6 6 6 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 6 6 6
+ 18 18 18 34 34 34 58 58 58 78 78 78
+101 98 89 124 112 88 142 110 46 156 107 11
+163 110 8 167 114 7 175 118 6 180 123 7
+185 133 11 197 138 11 210 150 10 219 162 10
+226 170 11 236 178 12 236 178 12 234 174 13
+219 162 10 197 138 11 163 110 8 130 83 6
+ 91 60 6 10 10 10 2 2 6 2 2 6
+ 18 18 18 38 38 38 38 38 38 38 38 38
+ 38 38 38 38 38 38 38 38 38 38 38 38
+ 38 38 38 38 38 38 26 26 26 2 2 6
+ 2 2 6 6 6 6 70 47 6 137 92 6
+175 118 6 200 144 11 219 162 10 230 174 11
+234 174 13 230 174 11 219 162 10 210 150 10
+192 133 9 163 110 8 124 112 88 82 82 82
+ 50 50 50 30 30 30 14 14 14 6 6 6
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 6 6 6 14 14 14 22 22 22 34 34 34
+ 42 42 42 58 58 58 74 74 74 86 86 86
+101 98 89 122 102 70 130 98 46 121 87 25
+137 92 6 152 99 6 163 110 8 180 123 7
+185 133 11 197 138 11 206 145 10 200 144 11
+180 123 7 156 107 11 130 83 6 104 69 6
+ 50 34 6 54 54 54 110 110 110 101 98 89
+ 86 86 86 82 82 82 78 78 78 78 78 78
+ 78 78 78 78 78 78 78 78 78 78 78 78
+ 78 78 78 82 82 82 86 86 86 94 94 94
+106 106 106 101 101 101 86 66 34 124 80 6
+156 107 11 180 123 7 192 133 9 200 144 11
+206 145 10 200 144 11 192 133 9 175 118 6
+139 102 15 109 106 95 70 70 70 42 42 42
+ 22 22 22 10 10 10 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 6 6 6 10 10 10
+ 14 14 14 22 22 22 30 30 30 38 38 38
+ 50 50 50 62 62 62 74 74 74 90 90 90
+101 98 89 112 100 78 121 87 25 124 80 6
+137 92 6 152 99 6 152 99 6 152 99 6
+138 86 6 124 80 6 98 70 6 86 66 30
+101 98 89 82 82 82 58 58 58 46 46 46
+ 38 38 38 34 34 34 34 34 34 34 34 34
+ 34 34 34 34 34 34 34 34 34 34 34 34
+ 34 34 34 34 34 34 38 38 38 42 42 42
+ 54 54 54 82 82 82 94 86 76 91 60 6
+134 86 6 156 107 11 167 114 7 175 118 6
+175 118 6 167 114 7 152 99 6 121 87 25
+101 98 89 62 62 62 34 34 34 18 18 18
+ 6 6 6 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 6 6 6 6 6 6 10 10 10
+ 18 18 18 22 22 22 30 30 30 42 42 42
+ 50 50 50 66 66 66 86 86 86 101 98 89
+106 86 58 98 70 6 104 69 6 104 69 6
+104 69 6 91 60 6 82 62 34 90 90 90
+ 62 62 62 38 38 38 22 22 22 14 14 14
+ 10 10 10 10 10 10 10 10 10 10 10 10
+ 10 10 10 10 10 10 6 6 6 10 10 10
+ 10 10 10 10 10 10 10 10 10 14 14 14
+ 22 22 22 42 42 42 70 70 70 89 81 66
+ 80 54 7 104 69 6 124 80 6 137 92 6
+134 86 6 116 81 8 100 82 52 86 86 86
+ 58 58 58 30 30 30 14 14 14 6 6 6
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 6 6 6 10 10 10 14 14 14
+ 18 18 18 26 26 26 38 38 38 54 54 54
+ 70 70 70 86 86 86 94 86 76 89 81 66
+ 89 81 66 86 86 86 74 74 74 50 50 50
+ 30 30 30 14 14 14 6 6 6 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 6 6 6 18 18 18 34 34 34 58 58 58
+ 82 82 82 89 81 66 89 81 66 89 81 66
+ 94 86 66 94 86 76 74 74 74 50 50 50
+ 26 26 26 14 14 14 6 6 6 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 6 6 6 6 6 6 14 14 14 18 18 18
+ 30 30 30 38 38 38 46 46 46 54 54 54
+ 50 50 50 42 42 42 30 30 30 18 18 18
+ 10 10 10 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 6 6 6 14 14 14 26 26 26
+ 38 38 38 50 50 50 58 58 58 58 58 58
+ 54 54 54 42 42 42 30 30 30 18 18 18
+ 10 10 10 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 6 6 6
+ 6 6 6 10 10 10 14 14 14 18 18 18
+ 18 18 18 14 14 14 10 10 10 6 6 6
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 6 6 6
+ 14 14 14 18 18 18 22 22 22 22 22 22
+ 18 18 18 14 14 14 10 10 10 6 6 6
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
+ 0 0 0 0 0 0 0 0 0 0 0 0
diff --git a/drivers/w1/masters/Kconfig b/drivers/w1/masters/Kconfig
index 2bd1257..efc7f07 100644
--- a/drivers/w1/masters/Kconfig
+++ b/drivers/w1/masters/Kconfig
@@ -42,7 +42,7 @@
config W1_MASTER_DS1WM
tristate "Maxim DS1WM 1-wire busmaster"
- depends on W1 && GENERIC_HARDIRQS
+ depends on W1
help
Say Y here to enable the DS1WM 1-wire driver, such as that
in HP iPAQ devices like h5xxx, h2200, and ASIC3-based like
diff --git a/drivers/w1/masters/mxc_w1.c b/drivers/w1/masters/mxc_w1.c
index 47e12cf..15c7251 100644
--- a/drivers/w1/masters/mxc_w1.c
+++ b/drivers/w1/masters/mxc_w1.c
@@ -152,8 +152,6 @@
clk_disable_unprepare(mdev->clk);
- platform_set_drvdata(pdev, NULL);
-
return 0;
}
diff --git a/drivers/w1/w1.c b/drivers/w1/w1.c
index 22013ca..c7c64f1 100644
--- a/drivers/w1/w1.c
+++ b/drivers/w1/w1.c
@@ -234,9 +234,11 @@
{
long tmp;
struct w1_master *md = dev_to_w1_master(dev);
+ int ret;
- if (strict_strtol(buf, 0, &tmp) == -EINVAL)
- return -EINVAL;
+ ret = kstrtol(buf, 0, &tmp);
+ if (ret)
+ return ret;
mutex_lock(&md->mutex);
md->search_count = tmp;
@@ -266,9 +268,11 @@
{
long tmp;
struct w1_master *md = dev_to_w1_master(dev);
+ int ret;
- if (strict_strtol(buf, 0, &tmp) == -EINVAL)
- return -EINVAL;
+ ret = kstrtol(buf, 0, &tmp);
+ if (ret)
+ return ret;
mutex_lock(&md->mutex);
md->enable_pullup = tmp;
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 362085d..d1d53f3 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -290,6 +290,16 @@
To compile this driver as a module, choose M here: the
module will be called orion_wdt.
+config SUNXI_WATCHDOG
+ tristate "Allwinner SoCs watchdog support"
+ depends on ARCH_SUNXI
+ select WATCHDOG_CORE
+ help
+ Say Y here to include support for the watchdog timer
+ in Allwinner SoCs.
+ To compile this driver as a module, choose M here: the
+ module will be called sunxi_wdt.
+
config COH901327_WATCHDOG
bool "ST-Ericsson COH 901 327 watchdog"
depends on ARCH_U300
diff --git a/drivers/watchdog/Makefile b/drivers/watchdog/Makefile
index 2f26a0b..6c5bb27 100644
--- a/drivers/watchdog/Makefile
+++ b/drivers/watchdog/Makefile
@@ -46,6 +46,7 @@
obj-$(CONFIG_IOP_WATCHDOG) += iop_wdt.o
obj-$(CONFIG_DAVINCI_WATCHDOG) += davinci_wdt.o
obj-$(CONFIG_ORION_WATCHDOG) += orion_wdt.o
+obj-$(CONFIG_SUNXI_WATCHDOG) += sunxi_wdt.o
obj-$(CONFIG_COH901327_WATCHDOG) += coh901327_wdt.o
obj-$(CONFIG_STMP3XXX_RTC_WATCHDOG) += stmp3xxx_rtc_wdt.o
obj-$(CONFIG_NUC900_WATCHDOG) += nuc900_wdt.o
diff --git a/drivers/watchdog/ar7_wdt.c b/drivers/watchdog/ar7_wdt.c
index 2f3cc8f..b3709f9 100644
--- a/drivers/watchdog/ar7_wdt.c
+++ b/drivers/watchdog/ar7_wdt.c
@@ -280,11 +280,6 @@
ar7_regs_wdt =
platform_get_resource_byname(pdev, IORESOURCE_MEM, "regs");
- if (!ar7_regs_wdt) {
- pr_err("could not get registers resource\n");
- return -ENODEV;
- }
-
ar7_wdt = devm_ioremap_resource(&pdev->dev, ar7_regs_wdt);
if (IS_ERR(ar7_wdt))
return PTR_ERR(ar7_wdt);
diff --git a/drivers/watchdog/hpwdt.c b/drivers/watchdog/hpwdt.c
index de7e4f4..5be5e3d 100644
--- a/drivers/watchdog/hpwdt.c
+++ b/drivers/watchdog/hpwdt.c
@@ -162,7 +162,8 @@
#define HPWDT_ARCH 32
asm(".text \n\t"
- ".align 4 \n"
+ ".align 4 \n\t"
+ ".globl asminline_call \n"
"asminline_call: \n\t"
"pushl %ebp \n\t"
"movl %esp, %ebp \n\t"
@@ -352,7 +353,8 @@
#define HPWDT_ARCH 64
asm(".text \n\t"
- ".align 4 \n"
+ ".align 4 \n\t"
+ ".globl asminline_call \n"
"asminline_call: \n\t"
"pushq %rbp \n\t"
"movq %rsp, %rbp \n\t"
diff --git a/drivers/watchdog/nuc900_wdt.c b/drivers/watchdog/nuc900_wdt.c
index e2b6d2c..b15b6ef 100644
--- a/drivers/watchdog/nuc900_wdt.c
+++ b/drivers/watchdog/nuc900_wdt.c
@@ -256,11 +256,6 @@
spin_lock_init(&nuc900_wdt->wdt_lock);
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (res == NULL) {
- dev_err(&pdev->dev, "no memory resource specified\n");
- return -ENOENT;
- }
-
nuc900_wdt->wdt_base = devm_ioremap_resource(&pdev->dev, res);
if (IS_ERR(nuc900_wdt->wdt_base))
return PTR_ERR(nuc900_wdt->wdt_base);
diff --git a/drivers/watchdog/s3c2410_wdt.c b/drivers/watchdog/s3c2410_wdt.c
index 6a22cf5..23aad7c 100644
--- a/drivers/watchdog/s3c2410_wdt.c
+++ b/drivers/watchdog/s3c2410_wdt.c
@@ -84,13 +84,17 @@
"0 to reboot (default 0)");
MODULE_PARM_DESC(debug, "Watchdog debug, set to >1 for debug (default 0)");
-static struct device *wdt_dev; /* platform device attached to */
-static struct resource *wdt_mem;
-static struct resource *wdt_irq;
-static struct clk *wdt_clock;
-static void __iomem *wdt_base;
-static unsigned int wdt_count;
-static DEFINE_SPINLOCK(wdt_lock);
+struct s3c2410_wdt {
+ struct device *dev;
+ struct clk *clock;
+ void __iomem *reg_base;
+ unsigned int count;
+ spinlock_t lock;
+ unsigned long wtcon_save;
+ unsigned long wtdat_save;
+ struct watchdog_device wdt_device;
+ struct notifier_block freq_transition;
+};
/* watchdog control routines */
@@ -102,29 +106,38 @@
/* functions */
+static inline struct s3c2410_wdt *freq_to_wdt(struct notifier_block *nb)
+{
+ return container_of(nb, struct s3c2410_wdt, freq_transition);
+}
+
static int s3c2410wdt_keepalive(struct watchdog_device *wdd)
{
- spin_lock(&wdt_lock);
- writel(wdt_count, wdt_base + S3C2410_WTCNT);
- spin_unlock(&wdt_lock);
+ struct s3c2410_wdt *wdt = watchdog_get_drvdata(wdd);
+
+ spin_lock(&wdt->lock);
+ writel(wdt->count, wdt->reg_base + S3C2410_WTCNT);
+ spin_unlock(&wdt->lock);
return 0;
}
-static void __s3c2410wdt_stop(void)
+static void __s3c2410wdt_stop(struct s3c2410_wdt *wdt)
{
unsigned long wtcon;
- wtcon = readl(wdt_base + S3C2410_WTCON);
+ wtcon = readl(wdt->reg_base + S3C2410_WTCON);
wtcon &= ~(S3C2410_WTCON_ENABLE | S3C2410_WTCON_RSTEN);
- writel(wtcon, wdt_base + S3C2410_WTCON);
+ writel(wtcon, wdt->reg_base + S3C2410_WTCON);
}
static int s3c2410wdt_stop(struct watchdog_device *wdd)
{
- spin_lock(&wdt_lock);
- __s3c2410wdt_stop();
- spin_unlock(&wdt_lock);
+ struct s3c2410_wdt *wdt = watchdog_get_drvdata(wdd);
+
+ spin_lock(&wdt->lock);
+ __s3c2410wdt_stop(wdt);
+ spin_unlock(&wdt->lock);
return 0;
}
@@ -132,12 +145,13 @@
static int s3c2410wdt_start(struct watchdog_device *wdd)
{
unsigned long wtcon;
+ struct s3c2410_wdt *wdt = watchdog_get_drvdata(wdd);
- spin_lock(&wdt_lock);
+ spin_lock(&wdt->lock);
- __s3c2410wdt_stop();
+ __s3c2410wdt_stop(wdt);
- wtcon = readl(wdt_base + S3C2410_WTCON);
+ wtcon = readl(wdt->reg_base + S3C2410_WTCON);
wtcon |= S3C2410_WTCON_ENABLE | S3C2410_WTCON_DIV128;
if (soft_noboot) {
@@ -148,25 +162,26 @@
wtcon |= S3C2410_WTCON_RSTEN;
}
- DBG("%s: wdt_count=0x%08x, wtcon=%08lx\n",
- __func__, wdt_count, wtcon);
+ DBG("%s: count=0x%08x, wtcon=%08lx\n",
+ __func__, wdt->count, wtcon);
- writel(wdt_count, wdt_base + S3C2410_WTDAT);
- writel(wdt_count, wdt_base + S3C2410_WTCNT);
- writel(wtcon, wdt_base + S3C2410_WTCON);
- spin_unlock(&wdt_lock);
+ writel(wdt->count, wdt->reg_base + S3C2410_WTDAT);
+ writel(wdt->count, wdt->reg_base + S3C2410_WTCNT);
+ writel(wtcon, wdt->reg_base + S3C2410_WTCON);
+ spin_unlock(&wdt->lock);
return 0;
}
-static inline int s3c2410wdt_is_running(void)
+static inline int s3c2410wdt_is_running(struct s3c2410_wdt *wdt)
{
- return readl(wdt_base + S3C2410_WTCON) & S3C2410_WTCON_ENABLE;
+ return readl(wdt->reg_base + S3C2410_WTCON) & S3C2410_WTCON_ENABLE;
}
static int s3c2410wdt_set_heartbeat(struct watchdog_device *wdd, unsigned timeout)
{
- unsigned long freq = clk_get_rate(wdt_clock);
+ struct s3c2410_wdt *wdt = watchdog_get_drvdata(wdd);
+ unsigned long freq = clk_get_rate(wdt->clock);
unsigned int count;
unsigned int divisor = 1;
unsigned long wtcon;
@@ -192,7 +207,7 @@
}
if ((count / divisor) >= 0x10000) {
- dev_err(wdt_dev, "timeout %d too big\n", timeout);
+ dev_err(wdt->dev, "timeout %d too big\n", timeout);
return -EINVAL;
}
}
@@ -201,15 +216,15 @@
__func__, timeout, divisor, count, count/divisor);
count /= divisor;
- wdt_count = count;
+ wdt->count = count;
/* update the pre-scaler */
- wtcon = readl(wdt_base + S3C2410_WTCON);
+ wtcon = readl(wdt->reg_base + S3C2410_WTCON);
wtcon &= ~S3C2410_WTCON_PRESCALE_MASK;
wtcon |= S3C2410_WTCON_PRESCALE(divisor-1);
- writel(count, wdt_base + S3C2410_WTDAT);
- writel(wtcon, wdt_base + S3C2410_WTCON);
+ writel(count, wdt->reg_base + S3C2410_WTDAT);
+ writel(wtcon, wdt->reg_base + S3C2410_WTCON);
wdd->timeout = (count * divisor) / freq;
@@ -242,21 +257,23 @@
static irqreturn_t s3c2410wdt_irq(int irqno, void *param)
{
- dev_info(wdt_dev, "watchdog timer expired (irq)\n");
+ struct s3c2410_wdt *wdt = platform_get_drvdata(param);
- s3c2410wdt_keepalive(&s3c2410_wdd);
+ dev_info(wdt->dev, "watchdog timer expired (irq)\n");
+
+ s3c2410wdt_keepalive(&wdt->wdt_device);
return IRQ_HANDLED;
}
-
#ifdef CONFIG_CPU_FREQ
static int s3c2410wdt_cpufreq_transition(struct notifier_block *nb,
unsigned long val, void *data)
{
int ret;
+ struct s3c2410_wdt *wdt = freq_to_wdt(nb);
- if (!s3c2410wdt_is_running())
+ if (!s3c2410wdt_is_running(wdt))
goto done;
if (val == CPUFREQ_PRECHANGE) {
@@ -265,14 +282,15 @@
* the watchdog is running.
*/
- s3c2410wdt_keepalive(&s3c2410_wdd);
+ s3c2410wdt_keepalive(&wdt->wdt_device);
} else if (val == CPUFREQ_POSTCHANGE) {
- s3c2410wdt_stop(&s3c2410_wdd);
+ s3c2410wdt_stop(&wdt->wdt_device);
- ret = s3c2410wdt_set_heartbeat(&s3c2410_wdd, s3c2410_wdd.timeout);
+ ret = s3c2410wdt_set_heartbeat(&wdt->wdt_device,
+ wdt->wdt_device.timeout);
if (ret >= 0)
- s3c2410wdt_start(&s3c2410_wdd);
+ s3c2410wdt_start(&wdt->wdt_device);
else
goto err;
}
@@ -281,34 +299,35 @@
return 0;
err:
- dev_err(wdt_dev, "cannot set new value for timeout %d\n",
- s3c2410_wdd.timeout);
+ dev_err(wdt->dev, "cannot set new value for timeout %d\n",
+ wdt->wdt_device.timeout);
return ret;
}
-static struct notifier_block s3c2410wdt_cpufreq_transition_nb = {
- .notifier_call = s3c2410wdt_cpufreq_transition,
-};
-
-static inline int s3c2410wdt_cpufreq_register(void)
+static inline int s3c2410wdt_cpufreq_register(struct s3c2410_wdt *wdt)
{
- return cpufreq_register_notifier(&s3c2410wdt_cpufreq_transition_nb,
+ wdt->freq_transition.notifier_call = s3c2410wdt_cpufreq_transition;
+
+ return cpufreq_register_notifier(&wdt->freq_transition,
CPUFREQ_TRANSITION_NOTIFIER);
}
-static inline void s3c2410wdt_cpufreq_deregister(void)
+static inline void s3c2410wdt_cpufreq_deregister(struct s3c2410_wdt *wdt)
{
- cpufreq_unregister_notifier(&s3c2410wdt_cpufreq_transition_nb,
+ wdt->freq_transition.notifier_call = s3c2410wdt_cpufreq_transition;
+
+ cpufreq_unregister_notifier(&wdt->freq_transition,
CPUFREQ_TRANSITION_NOTIFIER);
}
#else
-static inline int s3c2410wdt_cpufreq_register(void)
+
+static inline int s3c2410wdt_cpufreq_register(struct s3c2410_wdt *wdt)
{
return 0;
}
-static inline void s3c2410wdt_cpufreq_deregister(void)
+static inline void s3c2410wdt_cpufreq_deregister(struct s3c2410_wdt *wdt)
{
}
#endif
@@ -316,6 +335,9 @@
static int s3c2410wdt_probe(struct platform_device *pdev)
{
struct device *dev;
+ struct s3c2410_wdt *wdt;
+ struct resource *wdt_mem;
+ struct resource *wdt_irq;
unsigned int wtcon;
int started = 0;
int ret;
@@ -323,13 +345,14 @@
DBG("%s: probe=%p\n", __func__, pdev);
dev = &pdev->dev;
- wdt_dev = &pdev->dev;
- wdt_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (wdt_mem == NULL) {
- dev_err(dev, "no memory resource specified\n");
- return -ENOENT;
- }
+ wdt = devm_kzalloc(dev, sizeof(*wdt), GFP_KERNEL);
+ if (!wdt)
+ return -ENOMEM;
+
+ wdt->dev = &pdev->dev;
+ spin_lock_init(&wdt->lock);
+ wdt->wdt_device = s3c2410_wdd;
wdt_irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
if (wdt_irq == NULL) {
@@ -339,35 +362,40 @@
}
/* get the memory region for the watchdog timer */
- wdt_base = devm_ioremap_resource(dev, wdt_mem);
- if (IS_ERR(wdt_base)) {
- ret = PTR_ERR(wdt_base);
+ wdt_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ wdt->reg_base = devm_ioremap_resource(dev, wdt_mem);
+ if (IS_ERR(wdt->reg_base)) {
+ ret = PTR_ERR(wdt->reg_base);
goto err;
}
- DBG("probe: mapped wdt_base=%p\n", wdt_base);
+ DBG("probe: mapped reg_base=%p\n", wdt->reg_base);
- wdt_clock = devm_clk_get(dev, "watchdog");
- if (IS_ERR(wdt_clock)) {
+ wdt->clock = devm_clk_get(dev, "watchdog");
+ if (IS_ERR(wdt->clock)) {
dev_err(dev, "failed to find watchdog clock source\n");
- ret = PTR_ERR(wdt_clock);
+ ret = PTR_ERR(wdt->clock);
goto err;
}
- clk_prepare_enable(wdt_clock);
+ clk_prepare_enable(wdt->clock);
- ret = s3c2410wdt_cpufreq_register();
+ ret = s3c2410wdt_cpufreq_register(wdt);
if (ret < 0) {
dev_err(dev, "failed to register cpufreq\n");
goto err_clk;
}
+ watchdog_set_drvdata(&wdt->wdt_device, wdt);
+
/* see if we can actually set the requested timer margin, and if
* not, try the default value */
- watchdog_init_timeout(&s3c2410_wdd, tmr_margin, &pdev->dev);
- if (s3c2410wdt_set_heartbeat(&s3c2410_wdd, s3c2410_wdd.timeout)) {
- started = s3c2410wdt_set_heartbeat(&s3c2410_wdd,
+ watchdog_init_timeout(&wdt->wdt_device, tmr_margin, &pdev->dev);
+ ret = s3c2410wdt_set_heartbeat(&wdt->wdt_device,
+ wdt->wdt_device.timeout);
+ if (ret) {
+ started = s3c2410wdt_set_heartbeat(&wdt->wdt_device,
CONFIG_S3C2410_WATCHDOG_DEFAULT_TIME);
if (started == 0)
@@ -386,9 +414,9 @@
goto err_cpufreq;
}
- watchdog_set_nowayout(&s3c2410_wdd, nowayout);
+ watchdog_set_nowayout(&wdt->wdt_device, nowayout);
- ret = watchdog_register_device(&s3c2410_wdd);
+ ret = watchdog_register_device(&wdt->wdt_device);
if (ret) {
dev_err(dev, "cannot register watchdog (%d)\n", ret);
goto err_cpufreq;
@@ -396,18 +424,20 @@
if (tmr_atboot && started == 0) {
dev_info(dev, "starting watchdog timer\n");
- s3c2410wdt_start(&s3c2410_wdd);
+ s3c2410wdt_start(&wdt->wdt_device);
} else if (!tmr_atboot) {
/* if we're not enabling the watchdog, then ensure it is
* disabled if it has been left running from the bootloader
* or other source */
- s3c2410wdt_stop(&s3c2410_wdd);
+ s3c2410wdt_stop(&wdt->wdt_device);
}
+ platform_set_drvdata(pdev, wdt);
+
/* print out a statement of readiness */
- wtcon = readl(wdt_base + S3C2410_WTCON);
+ wtcon = readl(wdt->reg_base + S3C2410_WTCON);
dev_info(dev, "watchdog %sactive, reset %sabled, irq %sabled\n",
(wtcon & S3C2410_WTCON_ENABLE) ? "" : "in",
@@ -417,64 +447,64 @@
return 0;
err_cpufreq:
- s3c2410wdt_cpufreq_deregister();
+ s3c2410wdt_cpufreq_deregister(wdt);
err_clk:
- clk_disable_unprepare(wdt_clock);
- wdt_clock = NULL;
+ clk_disable_unprepare(wdt->clock);
+ wdt->clock = NULL;
err:
- wdt_irq = NULL;
- wdt_mem = NULL;
return ret;
}
static int s3c2410wdt_remove(struct platform_device *dev)
{
- watchdog_unregister_device(&s3c2410_wdd);
+ struct s3c2410_wdt *wdt = platform_get_drvdata(dev);
- s3c2410wdt_cpufreq_deregister();
+ watchdog_unregister_device(&wdt->wdt_device);
- clk_disable_unprepare(wdt_clock);
- wdt_clock = NULL;
+ s3c2410wdt_cpufreq_deregister(wdt);
- wdt_irq = NULL;
- wdt_mem = NULL;
+ clk_disable_unprepare(wdt->clock);
+ wdt->clock = NULL;
+
return 0;
}
static void s3c2410wdt_shutdown(struct platform_device *dev)
{
- s3c2410wdt_stop(&s3c2410_wdd);
+ struct s3c2410_wdt *wdt = platform_get_drvdata(dev);
+
+ s3c2410wdt_stop(&wdt->wdt_device);
}
#ifdef CONFIG_PM_SLEEP
-static unsigned long wtcon_save;
-static unsigned long wtdat_save;
-
static int s3c2410wdt_suspend(struct device *dev)
{
+ struct s3c2410_wdt *wdt = dev_get_drvdata(dev);
+
/* Save watchdog state, and turn it off. */
- wtcon_save = readl(wdt_base + S3C2410_WTCON);
- wtdat_save = readl(wdt_base + S3C2410_WTDAT);
+ wdt->wtcon_save = readl(wdt->reg_base + S3C2410_WTCON);
+ wdt->wtdat_save = readl(wdt->reg_base + S3C2410_WTDAT);
/* Note that WTCNT doesn't need to be saved. */
- s3c2410wdt_stop(&s3c2410_wdd);
+ s3c2410wdt_stop(&wdt->wdt_device);
return 0;
}
static int s3c2410wdt_resume(struct device *dev)
{
- /* Restore watchdog state. */
+ struct s3c2410_wdt *wdt = dev_get_drvdata(dev);
- writel(wtdat_save, wdt_base + S3C2410_WTDAT);
- writel(wtdat_save, wdt_base + S3C2410_WTCNT); /* Reset count */
- writel(wtcon_save, wdt_base + S3C2410_WTCON);
+ /* Restore watchdog state. */
+ writel(wdt->wtdat_save, wdt->reg_base + S3C2410_WTDAT);
+ writel(wdt->wtdat_save, wdt->reg_base + S3C2410_WTCNT);/* Reset count */
+ writel(wdt->wtcon_save, wdt->reg_base + S3C2410_WTCON);
dev_info(dev, "watchdog %sabled\n",
- (wtcon_save & S3C2410_WTCON_ENABLE) ? "en" : "dis");
+ (wdt->wtcon_save & S3C2410_WTCON_ENABLE) ? "en" : "dis");
return 0;
}
diff --git a/drivers/watchdog/sunxi_wdt.c b/drivers/watchdog/sunxi_wdt.c
new file mode 100644
index 0000000..1f94b42
--- /dev/null
+++ b/drivers/watchdog/sunxi_wdt.c
@@ -0,0 +1,237 @@
+/*
+ * sunxi Watchdog Driver
+ *
+ * Copyright (c) 2013 Carlo Caione
+ * 2012 Henrik Nordstrom
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Based on xen_wdt.c
+ * (c) Copyright 2010 Novell, Inc.
+ */
+
+#include <linux/clk.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/types.h>
+#include <linux/watchdog.h>
+
+#define WDT_MAX_TIMEOUT 16
+#define WDT_MIN_TIMEOUT 1
+#define WDT_MODE_TIMEOUT(n) ((n) << 3)
+#define WDT_TIMEOUT_MASK WDT_MODE_TIMEOUT(0x0F)
+
+#define WDT_CTRL 0x00
+#define WDT_CTRL_RELOAD ((1 << 0) | (0x0a57 << 1))
+
+#define WDT_MODE 0x04
+#define WDT_MODE_EN (1 << 0)
+#define WDT_MODE_RST_EN (1 << 1)
+
+#define DRV_NAME "sunxi-wdt"
+#define DRV_VERSION "1.0"
+
+static bool nowayout = WATCHDOG_NOWAYOUT;
+static unsigned int timeout = WDT_MAX_TIMEOUT;
+
+struct sunxi_wdt_dev {
+ struct watchdog_device wdt_dev;
+ void __iomem *wdt_base;
+};
+
+/*
+ * wdt_timeout_map maps the watchdog timer interval value in seconds to
+ * the value of the register WDT_MODE bit 3:6
+ *
+ * [timeout seconds] = register value
+ *
+ */
+
+static const int wdt_timeout_map[] = {
+ [1] = 0b0001, /* 1s */
+ [2] = 0b0010, /* 2s */
+ [3] = 0b0011, /* 3s */
+ [4] = 0b0100, /* 4s */
+ [5] = 0b0101, /* 5s */
+ [6] = 0b0110, /* 6s */
+ [8] = 0b0111, /* 8s */
+ [10] = 0b1000, /* 10s */
+ [12] = 0b1001, /* 12s */
+ [14] = 0b1010, /* 14s */
+ [16] = 0b1011, /* 16s */
+};
+
+static int sunxi_wdt_ping(struct watchdog_device *wdt_dev)
+{
+ struct sunxi_wdt_dev *sunxi_wdt = watchdog_get_drvdata(wdt_dev);
+ void __iomem *wdt_base = sunxi_wdt->wdt_base;
+
+ iowrite32(WDT_CTRL_RELOAD, wdt_base + WDT_CTRL);
+
+ return 0;
+}
+
+static int sunxi_wdt_set_timeout(struct watchdog_device *wdt_dev,
+ unsigned int timeout)
+{
+ struct sunxi_wdt_dev *sunxi_wdt = watchdog_get_drvdata(wdt_dev);
+ void __iomem *wdt_base = sunxi_wdt->wdt_base;
+ u32 reg;
+
+ if (wdt_timeout_map[timeout] == 0)
+ timeout++;
+
+ sunxi_wdt->wdt_dev.timeout = timeout;
+
+ reg = ioread32(wdt_base + WDT_MODE);
+ reg &= ~WDT_TIMEOUT_MASK;
+ reg |= WDT_MODE_TIMEOUT(wdt_timeout_map[timeout]);
+ iowrite32(reg, wdt_base + WDT_MODE);
+
+ sunxi_wdt_ping(wdt_dev);
+
+ return 0;
+}
+
+static int sunxi_wdt_stop(struct watchdog_device *wdt_dev)
+{
+ struct sunxi_wdt_dev *sunxi_wdt = watchdog_get_drvdata(wdt_dev);
+ void __iomem *wdt_base = sunxi_wdt->wdt_base;
+
+ iowrite32(0, wdt_base + WDT_MODE);
+
+ return 0;
+}
+
+static int sunxi_wdt_start(struct watchdog_device *wdt_dev)
+{
+ u32 reg;
+ struct sunxi_wdt_dev *sunxi_wdt = watchdog_get_drvdata(wdt_dev);
+ void __iomem *wdt_base = sunxi_wdt->wdt_base;
+ int ret;
+
+ ret = sunxi_wdt_set_timeout(&sunxi_wdt->wdt_dev,
+ sunxi_wdt->wdt_dev.timeout);
+ if (ret < 0)
+ return ret;
+
+ reg = ioread32(wdt_base + WDT_MODE);
+ reg |= (WDT_MODE_RST_EN | WDT_MODE_EN);
+ iowrite32(reg, wdt_base + WDT_MODE);
+
+ return 0;
+}
+
+static const struct watchdog_info sunxi_wdt_info = {
+ .identity = DRV_NAME,
+ .options = WDIOF_SETTIMEOUT |
+ WDIOF_KEEPALIVEPING |
+ WDIOF_MAGICCLOSE,
+};
+
+static const struct watchdog_ops sunxi_wdt_ops = {
+ .owner = THIS_MODULE,
+ .start = sunxi_wdt_start,
+ .stop = sunxi_wdt_stop,
+ .ping = sunxi_wdt_ping,
+ .set_timeout = sunxi_wdt_set_timeout,
+};
+
+static int __init sunxi_wdt_probe(struct platform_device *pdev)
+{
+ struct sunxi_wdt_dev *sunxi_wdt;
+ struct resource *res;
+ int err;
+
+ sunxi_wdt = devm_kzalloc(&pdev->dev, sizeof(*sunxi_wdt), GFP_KERNEL);
+ if (!sunxi_wdt)
+ return -EINVAL;
+
+ platform_set_drvdata(pdev, sunxi_wdt);
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ sunxi_wdt->wdt_base = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(sunxi_wdt->wdt_base))
+ return PTR_ERR(sunxi_wdt->wdt_base);
+
+ sunxi_wdt->wdt_dev.info = &sunxi_wdt_info;
+ sunxi_wdt->wdt_dev.ops = &sunxi_wdt_ops;
+ sunxi_wdt->wdt_dev.timeout = WDT_MAX_TIMEOUT;
+ sunxi_wdt->wdt_dev.max_timeout = WDT_MAX_TIMEOUT;
+ sunxi_wdt->wdt_dev.min_timeout = WDT_MIN_TIMEOUT;
+ sunxi_wdt->wdt_dev.parent = &pdev->dev;
+
+ watchdog_init_timeout(&sunxi_wdt->wdt_dev, timeout, &pdev->dev);
+ watchdog_set_nowayout(&sunxi_wdt->wdt_dev, nowayout);
+
+ watchdog_set_drvdata(&sunxi_wdt->wdt_dev, sunxi_wdt);
+
+ sunxi_wdt_stop(&sunxi_wdt->wdt_dev);
+
+ err = watchdog_register_device(&sunxi_wdt->wdt_dev);
+ if (unlikely(err))
+ return err;
+
+ dev_info(&pdev->dev, "Watchdog enabled (timeout=%d sec, nowayout=%d)",
+ sunxi_wdt->wdt_dev.timeout, nowayout);
+
+ return 0;
+}
+
+static int __exit sunxi_wdt_remove(struct platform_device *pdev)
+{
+ struct sunxi_wdt_dev *sunxi_wdt = platform_get_drvdata(pdev);
+
+ watchdog_unregister_device(&sunxi_wdt->wdt_dev);
+ watchdog_set_drvdata(&sunxi_wdt->wdt_dev, NULL);
+
+ return 0;
+}
+
+static void sunxi_wdt_shutdown(struct platform_device *pdev)
+{
+ struct sunxi_wdt_dev *sunxi_wdt = platform_get_drvdata(pdev);
+
+ sunxi_wdt_stop(&sunxi_wdt->wdt_dev);
+}
+
+static const struct of_device_id sunxi_wdt_dt_ids[] = {
+ { .compatible = "allwinner,sun4i-wdt" },
+ { /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, sunxi_wdt_dt_ids);
+
+static struct platform_driver sunxi_wdt_driver = {
+ .probe = sunxi_wdt_probe,
+ .remove = sunxi_wdt_remove,
+ .shutdown = sunxi_wdt_shutdown,
+ .driver = {
+ .owner = THIS_MODULE,
+ .name = DRV_NAME,
+ .of_match_table = of_match_ptr(sunxi_wdt_dt_ids)
+ },
+};
+
+module_platform_driver(sunxi_wdt_driver);
+
+module_param(timeout, uint, 0);
+MODULE_PARM_DESC(timeout, "Watchdog heartbeat in seconds");
+
+module_param(nowayout, bool, 0);
+MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started "
+ "(default=" __MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Carlo Caione <carlo.caione@gmail.com>");
+MODULE_AUTHOR("Henrik Nordstrom <henrik@henriknordstrom.net>");
+MODULE_DESCRIPTION("sunxi WatchDog Timer Driver");
+MODULE_VERSION(DRV_VERSION);
diff --git a/drivers/watchdog/ts72xx_wdt.c b/drivers/watchdog/ts72xx_wdt.c
index 4da59b4..42913f1 100644
--- a/drivers/watchdog/ts72xx_wdt.c
+++ b/drivers/watchdog/ts72xx_wdt.c
@@ -403,21 +403,11 @@
}
r1 = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!r1) {
- dev_err(&pdev->dev, "failed to get memory resource\n");
- return -ENODEV;
- }
-
wdt->control_reg = devm_ioremap_resource(&pdev->dev, r1);
if (IS_ERR(wdt->control_reg))
return PTR_ERR(wdt->control_reg);
r2 = platform_get_resource(pdev, IORESOURCE_MEM, 1);
- if (!r2) {
- dev_err(&pdev->dev, "failed to get memory resource\n");
- return -ENODEV;
- }
-
wdt->feed_reg = devm_ioremap_resource(&pdev->dev, r2);
if (IS_ERR(wdt->feed_reg))
return PTR_ERR(wdt->feed_reg);
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 3101cf6..a50c6e3 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -349,8 +349,6 @@
BUG_ON(page == NULL);
pfn = page_to_pfn(page);
- BUG_ON(!xen_feature(XENFEAT_auto_translated_physmap) &&
- phys_to_machine_mapping_valid(pfn));
set_phys_to_machine(pfn, frame_list[i]);
@@ -380,6 +378,7 @@
enum bp_state state = BP_DONE;
unsigned long pfn, i;
struct page *page;
+ struct page *scratch_page;
int ret;
struct xen_memory_reservation reservation = {
.address_bits = 0,
@@ -399,6 +398,8 @@
if (nr_pages > ARRAY_SIZE(frame_list))
nr_pages = ARRAY_SIZE(frame_list);
+ scratch_page = get_balloon_scratch_page();
+
for (i = 0; i < nr_pages; i++) {
page = alloc_page(gfp);
if (page == NULL) {
@@ -416,7 +417,7 @@
if (xen_pv_domain() && !PageHighMem(page)) {
ret = HYPERVISOR_update_va_mapping(
(unsigned long)__va(pfn << PAGE_SHIFT),
- pfn_pte(page_to_pfn(__get_cpu_var(balloon_scratch_page)),
+ pfn_pte(page_to_pfn(scratch_page),
PAGE_KERNEL_RO), 0);
BUG_ON(ret);
}
@@ -432,14 +433,14 @@
pfn = mfn_to_pfn(frame_list[i]);
if (!xen_feature(XENFEAT_auto_translated_physmap)) {
unsigned long p;
- struct page *pg;
- pg = __get_cpu_var(balloon_scratch_page);
- p = page_to_pfn(pg);
+ p = page_to_pfn(scratch_page);
__set_phys_to_machine(pfn, pfn_to_mfn(p));
}
balloon_append(pfn_to_page(pfn));
}
+ put_balloon_scratch_page();
+
set_xen_guest_handle(reservation.extent_start, frame_list);
reservation.nr_extents = nr_pages;
ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation, &reservation);
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index d384a8b..aa5ecf4 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -183,7 +183,7 @@
else
flock.length = fl->fl_end - fl->fl_start + 1;
flock.proc_id = fl->fl_pid;
- flock.client_id = utsname()->nodename;
+ flock.client_id = fid->clnt->name;
if (IS_SETLKW(cmd))
flock.flags = P9_LOCK_FLAGS_BLOCK;
@@ -260,7 +260,7 @@
else
glock.length = fl->fl_end - fl->fl_start + 1;
glock.proc_id = fl->fl_pid;
- glock.client_id = utsname()->nodename;
+ glock.client_id = fid->clnt->name;
res = p9_client_getlock_dotl(fid, &glock);
if (res < 0)
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 25b018e..94de6d1 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -146,7 +146,7 @@
char type = 0, ext[32];
int major = -1, minor = -1;
- strncpy(ext, stat->extension, sizeof(ext));
+ strlcpy(ext, stat->extension, sizeof(ext));
sscanf(ext, "%c %u %u", &type, &major, &minor);
switch (type) {
case 'c':
@@ -1186,7 +1186,7 @@
* this even with .u extension. So check
* for non NULL stat->extension
*/
- strncpy(ext, stat->extension, sizeof(ext));
+ strlcpy(ext, stat->extension, sizeof(ext));
/* HARDLINKCOUNT %u */
sscanf(ext, "%13s %u", tag_name, &i_nlink);
if (!strncmp(tag_name, "HARDLINKCOUNT", 13))
diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c
index 5f95d1e..b9acada 100644
--- a/fs/adfs/inode.c
+++ b/fs/adfs/inode.c
@@ -50,7 +50,7 @@
struct inode *inode = mapping->host;
if (to > inode->i_size)
- truncate_pagecache(inode, to, inode->i_size);
+ truncate_pagecache(inode, inode->i_size);
}
static int adfs_write_begin(struct file *file, struct address_space *mapping,
diff --git a/fs/affs/file.c b/fs/affs/file.c
index af3261b..8669b6e 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -406,7 +406,7 @@
struct inode *inode = mapping->host;
if (to > inode->i_size) {
- truncate_pagecache(inode, to, inode->i_size);
+ truncate_pagecache(inode, inode->i_size);
affs_truncate(inode);
}
}
@@ -836,7 +836,7 @@
struct address_space *mapping = inode->i_mapping;
struct page *page;
void *fsdata;
- u32 size = inode->i_size;
+ loff_t size = inode->i_size;
int res;
res = mapping->a_ops->write_begin(NULL, mapping, size, 0, 0, &page, &fsdata);
diff --git a/fs/aio.c b/fs/aio.c
index 9b5ca11..6b868f0 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -26,6 +26,7 @@
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/mmu_context.h>
+#include <linux/percpu.h>
#include <linux/slab.h>
#include <linux/timer.h>
#include <linux/aio.h>
@@ -35,6 +36,10 @@
#include <linux/eventfd.h>
#include <linux/blkdev.h>
#include <linux/compat.h>
+#include <linux/anon_inodes.h>
+#include <linux/migrate.h>
+#include <linux/ramfs.h>
+#include <linux/percpu-refcount.h>
#include <asm/kmap_types.h>
#include <asm/uaccess.h>
@@ -61,14 +66,29 @@
#define AIO_RING_PAGES 8
+struct kioctx_table {
+ struct rcu_head rcu;
+ unsigned nr;
+ struct kioctx *table[];
+};
+
+struct kioctx_cpu {
+ unsigned reqs_available;
+};
+
struct kioctx {
- atomic_t users;
+ struct percpu_ref users;
atomic_t dead;
- /* This needs improving */
unsigned long user_id;
- struct hlist_node list;
+ struct __percpu kioctx_cpu *cpu;
+
+ /*
+ * For percpu reqs_available, number of slots we move to/from global
+ * counter at a time:
+ */
+ unsigned req_batch;
/*
* This is what userspace passed to io_setup(), it's not used for
* anything but counting against the global max_reqs quota.
@@ -88,10 +108,18 @@
long nr_pages;
struct rcu_head rcu_head;
- struct work_struct rcu_work;
+ struct work_struct free_work;
struct {
- atomic_t reqs_active;
+ /*
+ * This counts the number of available slots in the ringbuffer,
+ * so we avoid overflowing it: it's decremented (if positive)
+ * when allocating a kiocb and incremented when the resulting
+ * io_event is pulled off the ringbuffer.
+ *
+ * We batch accesses to it with a percpu version.
+ */
+ atomic_t reqs_available;
} ____cacheline_aligned_in_smp;
struct {
@@ -110,6 +138,9 @@
} ____cacheline_aligned_in_smp;
struct page *internal_pages[AIO_RING_PAGES];
+ struct file *aio_ring_file;
+
+ unsigned id;
};
/*------ sysctl variables----*/
@@ -138,15 +169,77 @@
static void aio_free_ring(struct kioctx *ctx)
{
- long i;
+ int i;
+ struct file *aio_ring_file = ctx->aio_ring_file;
- for (i = 0; i < ctx->nr_pages; i++)
+ for (i = 0; i < ctx->nr_pages; i++) {
+ pr_debug("pid(%d) [%d] page->count=%d\n", current->pid, i,
+ page_count(ctx->ring_pages[i]));
put_page(ctx->ring_pages[i]);
+ }
if (ctx->ring_pages && ctx->ring_pages != ctx->internal_pages)
kfree(ctx->ring_pages);
+
+ if (aio_ring_file) {
+ truncate_setsize(aio_ring_file->f_inode, 0);
+ fput(aio_ring_file);
+ ctx->aio_ring_file = NULL;
+ }
}
+static int aio_ring_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ vma->vm_ops = &generic_file_vm_ops;
+ return 0;
+}
+
+static const struct file_operations aio_ring_fops = {
+ .mmap = aio_ring_mmap,
+};
+
+static int aio_set_page_dirty(struct page *page)
+{
+ return 0;
+}
+
+#if IS_ENABLED(CONFIG_MIGRATION)
+static int aio_migratepage(struct address_space *mapping, struct page *new,
+ struct page *old, enum migrate_mode mode)
+{
+ struct kioctx *ctx = mapping->private_data;
+ unsigned long flags;
+ unsigned idx = old->index;
+ int rc;
+
+ /* Writeback must be complete */
+ BUG_ON(PageWriteback(old));
+ put_page(old);
+
+ rc = migrate_page_move_mapping(mapping, new, old, NULL, mode);
+ if (rc != MIGRATEPAGE_SUCCESS) {
+ get_page(old);
+ return rc;
+ }
+
+ get_page(new);
+
+ spin_lock_irqsave(&ctx->completion_lock, flags);
+ migrate_page_copy(new, old);
+ ctx->ring_pages[idx] = new;
+ spin_unlock_irqrestore(&ctx->completion_lock, flags);
+
+ return rc;
+}
+#endif
+
+static const struct address_space_operations aio_ctx_aops = {
+ .set_page_dirty = aio_set_page_dirty,
+#if IS_ENABLED(CONFIG_MIGRATION)
+ .migratepage = aio_migratepage,
+#endif
+};
+
static int aio_setup_ring(struct kioctx *ctx)
{
struct aio_ring *ring;
@@ -154,20 +247,45 @@
struct mm_struct *mm = current->mm;
unsigned long size, populate;
int nr_pages;
+ int i;
+ struct file *file;
/* Compensate for the ring buffer's head/tail overlap entry */
nr_events += 2; /* 1 is required, 2 for good luck */
size = sizeof(struct aio_ring);
size += sizeof(struct io_event) * nr_events;
- nr_pages = (size + PAGE_SIZE-1) >> PAGE_SHIFT;
+ nr_pages = PFN_UP(size);
if (nr_pages < 0)
return -EINVAL;
- nr_events = (PAGE_SIZE * nr_pages - sizeof(struct aio_ring)) / sizeof(struct io_event);
+ file = anon_inode_getfile_private("[aio]", &aio_ring_fops, ctx, O_RDWR);
+ if (IS_ERR(file)) {
+ ctx->aio_ring_file = NULL;
+ return -EAGAIN;
+ }
- ctx->nr_events = 0;
+ file->f_inode->i_mapping->a_ops = &aio_ctx_aops;
+ file->f_inode->i_mapping->private_data = ctx;
+ file->f_inode->i_size = PAGE_SIZE * (loff_t)nr_pages;
+
+ for (i = 0; i < nr_pages; i++) {
+ struct page *page;
+ page = find_or_create_page(file->f_inode->i_mapping,
+ i, GFP_HIGHUSER | __GFP_ZERO);
+ if (!page)
+ break;
+ pr_debug("pid(%d) page[%d]->count=%d\n",
+ current->pid, i, page_count(page));
+ SetPageUptodate(page);
+ SetPageDirty(page);
+ unlock_page(page);
+ }
+ ctx->aio_ring_file = file;
+ nr_events = (PAGE_SIZE * nr_pages - sizeof(struct aio_ring))
+ / sizeof(struct io_event);
+
ctx->ring_pages = ctx->internal_pages;
if (nr_pages > AIO_RING_PAGES) {
ctx->ring_pages = kcalloc(nr_pages, sizeof(struct page *),
@@ -178,10 +296,11 @@
ctx->mmap_size = nr_pages * PAGE_SIZE;
pr_debug("attempting mmap of %lu bytes\n", ctx->mmap_size);
+
down_write(&mm->mmap_sem);
- ctx->mmap_base = do_mmap_pgoff(NULL, 0, ctx->mmap_size,
- PROT_READ|PROT_WRITE,
- MAP_ANONYMOUS|MAP_PRIVATE, 0, &populate);
+ ctx->mmap_base = do_mmap_pgoff(ctx->aio_ring_file, 0, ctx->mmap_size,
+ PROT_READ | PROT_WRITE,
+ MAP_SHARED | MAP_POPULATE, 0, &populate);
if (IS_ERR((void *)ctx->mmap_base)) {
up_write(&mm->mmap_sem);
ctx->mmap_size = 0;
@@ -190,23 +309,34 @@
}
pr_debug("mmap address: 0x%08lx\n", ctx->mmap_base);
+
+ /* We must do this while still holding mmap_sem for write, as we
+ * need to be protected against userspace attempting to mremap()
+ * or munmap() the ring buffer.
+ */
ctx->nr_pages = get_user_pages(current, mm, ctx->mmap_base, nr_pages,
1, 0, ctx->ring_pages, NULL);
+
+ /* Dropping the reference here is safe as the page cache will hold
+ * onto the pages for us. It is also required so that page migration
+ * can unmap the pages and get the right reference count.
+ */
+ for (i = 0; i < ctx->nr_pages; i++)
+ put_page(ctx->ring_pages[i]);
+
up_write(&mm->mmap_sem);
if (unlikely(ctx->nr_pages != nr_pages)) {
aio_free_ring(ctx);
return -EAGAIN;
}
- if (populate)
- mm_populate(ctx->mmap_base, populate);
ctx->user_id = ctx->mmap_base;
ctx->nr_events = nr_events; /* trusted copy */
ring = kmap_atomic(ctx->ring_pages[0]);
ring->nr = nr_events; /* user copy */
- ring->id = ctx->user_id;
+ ring->id = ~0U;
ring->head = ring->tail = 0;
ring->magic = AIO_RING_MAGIC;
ring->compat_features = AIO_RING_COMPAT_FEATURES;
@@ -238,11 +368,9 @@
}
EXPORT_SYMBOL(kiocb_set_cancel_fn);
-static int kiocb_cancel(struct kioctx *ctx, struct kiocb *kiocb,
- struct io_event *res)
+static int kiocb_cancel(struct kioctx *ctx, struct kiocb *kiocb)
{
kiocb_cancel_fn *old, *cancel;
- int ret = -EINVAL;
/*
* Don't want to set kiocb->ki_cancel = KIOCB_CANCELLED unless it
@@ -252,28 +380,20 @@
cancel = ACCESS_ONCE(kiocb->ki_cancel);
do {
if (!cancel || cancel == KIOCB_CANCELLED)
- return ret;
+ return -EINVAL;
old = cancel;
cancel = cmpxchg(&kiocb->ki_cancel, old, KIOCB_CANCELLED);
} while (cancel != old);
- atomic_inc(&kiocb->ki_users);
- spin_unlock_irq(&ctx->ctx_lock);
-
- memset(res, 0, sizeof(*res));
- res->obj = (u64)(unsigned long)kiocb->ki_obj.user;
- res->data = kiocb->ki_user_data;
- ret = cancel(kiocb, res);
-
- spin_lock_irq(&ctx->ctx_lock);
-
- return ret;
+ return cancel(kiocb);
}
static void free_ioctx_rcu(struct rcu_head *head)
{
struct kioctx *ctx = container_of(head, struct kioctx, rcu_head);
+
+ free_percpu(ctx->cpu);
kmem_cache_free(kioctx_cachep, ctx);
}
@@ -282,12 +402,13 @@
* and ctx->users has dropped to 0, so we know no more kiocbs can be submitted -
* now it's safe to cancel any that need to be.
*/
-static void free_ioctx(struct kioctx *ctx)
+static void free_ioctx(struct work_struct *work)
{
+ struct kioctx *ctx = container_of(work, struct kioctx, free_work);
struct aio_ring *ring;
- struct io_event res;
struct kiocb *req;
- unsigned head, avail;
+ unsigned cpu, avail;
+ DEFINE_WAIT(wait);
spin_lock_irq(&ctx->ctx_lock);
@@ -296,28 +417,38 @@
struct kiocb, ki_list);
list_del_init(&req->ki_list);
- kiocb_cancel(ctx, req, &res);
+ kiocb_cancel(ctx, req);
}
spin_unlock_irq(&ctx->ctx_lock);
- ring = kmap_atomic(ctx->ring_pages[0]);
- head = ring->head;
- kunmap_atomic(ring);
+ for_each_possible_cpu(cpu) {
+ struct kioctx_cpu *kcpu = per_cpu_ptr(ctx->cpu, cpu);
- while (atomic_read(&ctx->reqs_active) > 0) {
- wait_event(ctx->wait,
- head != ctx->tail ||
- atomic_read(&ctx->reqs_active) <= 0);
-
- avail = (head <= ctx->tail ? ctx->tail : ctx->nr_events) - head;
-
- atomic_sub(avail, &ctx->reqs_active);
- head += avail;
- head %= ctx->nr_events;
+ atomic_add(kcpu->reqs_available, &ctx->reqs_available);
+ kcpu->reqs_available = 0;
}
- WARN_ON(atomic_read(&ctx->reqs_active) < 0);
+ while (1) {
+ prepare_to_wait(&ctx->wait, &wait, TASK_UNINTERRUPTIBLE);
+
+ ring = kmap_atomic(ctx->ring_pages[0]);
+ avail = (ring->head <= ring->tail)
+ ? ring->tail - ring->head
+ : ctx->nr_events - ring->head + ring->tail;
+
+ atomic_add(avail, &ctx->reqs_available);
+ ring->head = ring->tail;
+ kunmap_atomic(ring);
+
+ if (atomic_read(&ctx->reqs_available) >= ctx->nr_events - 1)
+ break;
+
+ schedule();
+ }
+ finish_wait(&ctx->wait, &wait);
+
+ WARN_ON(atomic_read(&ctx->reqs_available) > ctx->nr_events - 1);
aio_free_ring(ctx);
@@ -333,10 +464,68 @@
call_rcu(&ctx->rcu_head, free_ioctx_rcu);
}
-static void put_ioctx(struct kioctx *ctx)
+static void free_ioctx_ref(struct percpu_ref *ref)
{
- if (unlikely(atomic_dec_and_test(&ctx->users)))
- free_ioctx(ctx);
+ struct kioctx *ctx = container_of(ref, struct kioctx, users);
+
+ INIT_WORK(&ctx->free_work, free_ioctx);
+ schedule_work(&ctx->free_work);
+}
+
+static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm)
+{
+ unsigned i, new_nr;
+ struct kioctx_table *table, *old;
+ struct aio_ring *ring;
+
+ spin_lock(&mm->ioctx_lock);
+ rcu_read_lock();
+ table = rcu_dereference(mm->ioctx_table);
+
+ while (1) {
+ if (table)
+ for (i = 0; i < table->nr; i++)
+ if (!table->table[i]) {
+ ctx->id = i;
+ table->table[i] = ctx;
+ rcu_read_unlock();
+ spin_unlock(&mm->ioctx_lock);
+
+ ring = kmap_atomic(ctx->ring_pages[0]);
+ ring->id = ctx->id;
+ kunmap_atomic(ring);
+ return 0;
+ }
+
+ new_nr = (table ? table->nr : 1) * 4;
+
+ rcu_read_unlock();
+ spin_unlock(&mm->ioctx_lock);
+
+ table = kzalloc(sizeof(*table) + sizeof(struct kioctx *) *
+ new_nr, GFP_KERNEL);
+ if (!table)
+ return -ENOMEM;
+
+ table->nr = new_nr;
+
+ spin_lock(&mm->ioctx_lock);
+ rcu_read_lock();
+ old = rcu_dereference(mm->ioctx_table);
+
+ if (!old) {
+ rcu_assign_pointer(mm->ioctx_table, table);
+ } else if (table->nr > old->nr) {
+ memcpy(table->table, old->table,
+ old->nr * sizeof(struct kioctx *));
+
+ rcu_assign_pointer(mm->ioctx_table, table);
+ kfree_rcu(old, rcu);
+ } else {
+ kfree(table);
+ table = old;
+ }
+ }
}
/* ioctx_alloc
@@ -348,6 +537,18 @@
struct kioctx *ctx;
int err = -ENOMEM;
+ /*
+ * We keep track of the number of available ringbuffer slots, to prevent
+ * overflow (reqs_available), and we also use percpu counters for this.
+ *
+ * So since up to half the slots might be on other cpu's percpu counters
+ * and unavailable, double nr_events so userspace sees what they
+ * expected: additionally, we move req_batch slots to/from percpu
+ * counters at a time, so make sure that isn't 0:
+ */
+ nr_events = max(nr_events, num_possible_cpus() * 4);
+ nr_events *= 2;
+
/* Prevent overflows */
if ((nr_events > (0x10000000U / sizeof(struct io_event))) ||
(nr_events > (0x10000000U / sizeof(struct kiocb)))) {
@@ -355,7 +556,7 @@
return ERR_PTR(-EINVAL);
}
- if (!nr_events || (unsigned long)nr_events > aio_max_nr)
+ if (!nr_events || (unsigned long)nr_events > (aio_max_nr * 2UL))
return ERR_PTR(-EAGAIN);
ctx = kmem_cache_zalloc(kioctx_cachep, GFP_KERNEL);
@@ -364,8 +565,9 @@
ctx->max_reqs = nr_events;
- atomic_set(&ctx->users, 2);
- atomic_set(&ctx->dead, 0);
+ if (percpu_ref_init(&ctx->users, free_ioctx_ref))
+ goto out_freectx;
+
spin_lock_init(&ctx->ctx_lock);
spin_lock_init(&ctx->completion_lock);
mutex_init(&ctx->ring_lock);
@@ -373,12 +575,21 @@
INIT_LIST_HEAD(&ctx->active_reqs);
+ ctx->cpu = alloc_percpu(struct kioctx_cpu);
+ if (!ctx->cpu)
+ goto out_freeref;
+
if (aio_setup_ring(ctx) < 0)
- goto out_freectx;
+ goto out_freepcpu;
+
+ atomic_set(&ctx->reqs_available, ctx->nr_events - 1);
+ ctx->req_batch = (ctx->nr_events - 1) / (num_possible_cpus() * 4);
+ if (ctx->req_batch < 1)
+ ctx->req_batch = 1;
/* limit the number of system wide aios */
spin_lock(&aio_nr_lock);
- if (aio_nr + nr_events > aio_max_nr ||
+ if (aio_nr + nr_events > (aio_max_nr * 2UL) ||
aio_nr + nr_events < aio_nr) {
spin_unlock(&aio_nr_lock);
goto out_cleanup;
@@ -386,49 +597,54 @@
aio_nr += ctx->max_reqs;
spin_unlock(&aio_nr_lock);
- /* now link into global list. */
- spin_lock(&mm->ioctx_lock);
- hlist_add_head_rcu(&ctx->list, &mm->ioctx_list);
- spin_unlock(&mm->ioctx_lock);
+ percpu_ref_get(&ctx->users); /* io_setup() will drop this ref */
+
+ err = ioctx_add_table(ctx, mm);
+ if (err)
+ goto out_cleanup_put;
pr_debug("allocated ioctx %p[%ld]: mm=%p mask=0x%x\n",
ctx, ctx->user_id, mm, ctx->nr_events);
return ctx;
+out_cleanup_put:
+ percpu_ref_put(&ctx->users);
out_cleanup:
err = -EAGAIN;
aio_free_ring(ctx);
+out_freepcpu:
+ free_percpu(ctx->cpu);
+out_freeref:
+ free_percpu(ctx->users.pcpu_count);
out_freectx:
+ if (ctx->aio_ring_file)
+ fput(ctx->aio_ring_file);
kmem_cache_free(kioctx_cachep, ctx);
pr_debug("error allocating ioctx %d\n", err);
return ERR_PTR(err);
}
-static void kill_ioctx_work(struct work_struct *work)
-{
- struct kioctx *ctx = container_of(work, struct kioctx, rcu_work);
-
- wake_up_all(&ctx->wait);
- put_ioctx(ctx);
-}
-
-static void kill_ioctx_rcu(struct rcu_head *head)
-{
- struct kioctx *ctx = container_of(head, struct kioctx, rcu_head);
-
- INIT_WORK(&ctx->rcu_work, kill_ioctx_work);
- schedule_work(&ctx->rcu_work);
-}
-
/* kill_ioctx
* Cancels all outstanding aio requests on an aio context. Used
* when the processes owning a context have all exited to encourage
* the rapid destruction of the kioctx.
*/
-static void kill_ioctx(struct kioctx *ctx)
+static void kill_ioctx(struct mm_struct *mm, struct kioctx *ctx)
{
if (!atomic_xchg(&ctx->dead, 1)) {
- hlist_del_rcu(&ctx->list);
+ struct kioctx_table *table;
+
+ spin_lock(&mm->ioctx_lock);
+ rcu_read_lock();
+ table = rcu_dereference(mm->ioctx_table);
+
+ WARN_ON(ctx != table->table[ctx->id]);
+ table->table[ctx->id] = NULL;
+ rcu_read_unlock();
+ spin_unlock(&mm->ioctx_lock);
+
+ /* percpu_ref_kill() will do the necessary call_rcu() */
+ wake_up_all(&ctx->wait);
/*
* It'd be more correct to do this in free_ioctx(), after all
@@ -445,24 +661,23 @@
if (ctx->mmap_size)
vm_munmap(ctx->mmap_base, ctx->mmap_size);
- /* Between hlist_del_rcu() and dropping the initial ref */
- call_rcu(&ctx->rcu_head, kill_ioctx_rcu);
+ percpu_ref_kill(&ctx->users);
}
}
/* wait_on_sync_kiocb:
* Waits on the given sync kiocb to complete.
*/
-ssize_t wait_on_sync_kiocb(struct kiocb *iocb)
+ssize_t wait_on_sync_kiocb(struct kiocb *req)
{
- while (atomic_read(&iocb->ki_users)) {
+ while (!req->ki_ctx) {
set_current_state(TASK_UNINTERRUPTIBLE);
- if (!atomic_read(&iocb->ki_users))
+ if (req->ki_ctx)
break;
io_schedule();
}
__set_current_state(TASK_RUNNING);
- return iocb->ki_user_data;
+ return req->ki_user_data;
}
EXPORT_SYMBOL(wait_on_sync_kiocb);
@@ -476,16 +691,28 @@
*/
void exit_aio(struct mm_struct *mm)
{
+ struct kioctx_table *table;
struct kioctx *ctx;
- struct hlist_node *n;
+ unsigned i = 0;
- hlist_for_each_entry_safe(ctx, n, &mm->ioctx_list, list) {
- if (1 != atomic_read(&ctx->users))
- printk(KERN_DEBUG
- "exit_aio:ioctx still alive: %d %d %d\n",
- atomic_read(&ctx->users),
- atomic_read(&ctx->dead),
- atomic_read(&ctx->reqs_active));
+ while (1) {
+ rcu_read_lock();
+ table = rcu_dereference(mm->ioctx_table);
+
+ do {
+ if (!table || i >= table->nr) {
+ rcu_read_unlock();
+ rcu_assign_pointer(mm->ioctx_table, NULL);
+ if (table)
+ kfree(table);
+ return;
+ }
+
+ ctx = table->table[i++];
+ } while (!ctx);
+
+ rcu_read_unlock();
+
/*
* We don't need to bother with munmap() here -
* exit_mmap(mm) is coming and it'll unmap everything.
@@ -496,40 +723,75 @@
*/
ctx->mmap_size = 0;
- kill_ioctx(ctx);
+ kill_ioctx(mm, ctx);
}
}
+static void put_reqs_available(struct kioctx *ctx, unsigned nr)
+{
+ struct kioctx_cpu *kcpu;
+
+ preempt_disable();
+ kcpu = this_cpu_ptr(ctx->cpu);
+
+ kcpu->reqs_available += nr;
+ while (kcpu->reqs_available >= ctx->req_batch * 2) {
+ kcpu->reqs_available -= ctx->req_batch;
+ atomic_add(ctx->req_batch, &ctx->reqs_available);
+ }
+
+ preempt_enable();
+}
+
+static bool get_reqs_available(struct kioctx *ctx)
+{
+ struct kioctx_cpu *kcpu;
+ bool ret = false;
+
+ preempt_disable();
+ kcpu = this_cpu_ptr(ctx->cpu);
+
+ if (!kcpu->reqs_available) {
+ int old, avail = atomic_read(&ctx->reqs_available);
+
+ do {
+ if (avail < ctx->req_batch)
+ goto out;
+
+ old = avail;
+ avail = atomic_cmpxchg(&ctx->reqs_available,
+ avail, avail - ctx->req_batch);
+ } while (avail != old);
+
+ kcpu->reqs_available += ctx->req_batch;
+ }
+
+ ret = true;
+ kcpu->reqs_available--;
+out:
+ preempt_enable();
+ return ret;
+}
+
/* aio_get_req
- * Allocate a slot for an aio request. Increments the ki_users count
- * of the kioctx so that the kioctx stays around until all requests are
- * complete. Returns NULL if no requests are free.
- *
- * Returns with kiocb->ki_users set to 2. The io submit code path holds
- * an extra reference while submitting the i/o.
- * This prevents races between the aio code path referencing the
- * req (after submitting it) and aio_complete() freeing the req.
+ * Allocate a slot for an aio request.
+ * Returns NULL if no requests are free.
*/
static inline struct kiocb *aio_get_req(struct kioctx *ctx)
{
struct kiocb *req;
- if (atomic_read(&ctx->reqs_active) >= ctx->nr_events)
+ if (!get_reqs_available(ctx))
return NULL;
- if (atomic_inc_return(&ctx->reqs_active) > ctx->nr_events - 1)
- goto out_put;
-
req = kmem_cache_alloc(kiocb_cachep, GFP_KERNEL|__GFP_ZERO);
if (unlikely(!req))
goto out_put;
- atomic_set(&req->ki_users, 2);
req->ki_ctx = ctx;
-
return req;
out_put:
- atomic_dec(&ctx->reqs_active);
+ put_reqs_available(ctx, 1);
return NULL;
}
@@ -539,35 +801,32 @@
fput(req->ki_filp);
if (req->ki_eventfd != NULL)
eventfd_ctx_put(req->ki_eventfd);
- if (req->ki_dtor)
- req->ki_dtor(req);
- if (req->ki_iovec != &req->ki_inline_vec)
- kfree(req->ki_iovec);
kmem_cache_free(kiocb_cachep, req);
}
-void aio_put_req(struct kiocb *req)
-{
- if (atomic_dec_and_test(&req->ki_users))
- kiocb_free(req);
-}
-EXPORT_SYMBOL(aio_put_req);
-
static struct kioctx *lookup_ioctx(unsigned long ctx_id)
{
+ struct aio_ring __user *ring = (void __user *)ctx_id;
struct mm_struct *mm = current->mm;
struct kioctx *ctx, *ret = NULL;
+ struct kioctx_table *table;
+ unsigned id;
+
+ if (get_user(id, &ring->id))
+ return NULL;
rcu_read_lock();
+ table = rcu_dereference(mm->ioctx_table);
- hlist_for_each_entry_rcu(ctx, &mm->ioctx_list, list) {
- if (ctx->user_id == ctx_id) {
- atomic_inc(&ctx->users);
- ret = ctx;
- break;
- }
+ if (!table || id >= table->nr)
+ goto out;
+
+ ctx = table->table[id];
+ if (ctx && ctx->user_id == ctx_id) {
+ percpu_ref_get(&ctx->users);
+ ret = ctx;
}
-
+out:
rcu_read_unlock();
return ret;
}
@@ -591,16 +850,16 @@
* - the sync task helpfully left a reference to itself in the iocb
*/
if (is_sync_kiocb(iocb)) {
- BUG_ON(atomic_read(&iocb->ki_users) != 1);
iocb->ki_user_data = res;
- atomic_set(&iocb->ki_users, 0);
+ smp_wmb();
+ iocb->ki_ctx = ERR_PTR(-EXDEV);
wake_up_process(iocb->ki_obj.tsk);
return;
}
/*
* Take rcu_read_lock() in case the kioctx is being destroyed, as we
- * need to issue a wakeup after decrementing reqs_active.
+ * need to issue a wakeup after incrementing reqs_available.
*/
rcu_read_lock();
@@ -613,17 +872,6 @@
}
/*
- * cancelled requests don't get events, userland was given one
- * when the event got cancelled.
- */
- if (unlikely(xchg(&iocb->ki_cancel,
- KIOCB_CANCELLED) == KIOCB_CANCELLED)) {
- atomic_dec(&ctx->reqs_active);
- /* Still need the wake_up in case free_ioctx is waiting */
- goto put_rq;
- }
-
- /*
* Add a completion event to the ring buffer. Must be done holding
* ctx->completion_lock to prevent other code from messing with the tail
* pointer since we might be called from irq context.
@@ -675,9 +923,8 @@
if (iocb->ki_eventfd != NULL)
eventfd_signal(iocb->ki_eventfd, 1);
-put_rq:
/* everything turned out well, dispose of the aiocb. */
- aio_put_req(iocb);
+ kiocb_free(iocb);
/*
* We have to order our ring_info tail store above and test
@@ -702,7 +949,7 @@
struct io_event __user *event, long nr)
{
struct aio_ring *ring;
- unsigned head, pos;
+ unsigned head, tail, pos;
long ret = 0;
int copy_ret;
@@ -710,11 +957,12 @@
ring = kmap_atomic(ctx->ring_pages[0]);
head = ring->head;
+ tail = ring->tail;
kunmap_atomic(ring);
- pr_debug("h%u t%u m%u\n", head, ctx->tail, ctx->nr_events);
+ pr_debug("h%u t%u m%u\n", head, tail, ctx->nr_events);
- if (head == ctx->tail)
+ if (head == tail)
goto out;
while (ret < nr) {
@@ -722,8 +970,8 @@
struct io_event *ev;
struct page *page;
- avail = (head <= ctx->tail ? ctx->tail : ctx->nr_events) - head;
- if (head == ctx->tail)
+ avail = (head <= tail ? tail : ctx->nr_events) - head;
+ if (head == tail)
break;
avail = min(avail, nr - ret);
@@ -754,9 +1002,9 @@
kunmap_atomic(ring);
flush_dcache_page(ctx->ring_pages[0]);
- pr_debug("%li h%u t%u\n", ret, head, ctx->tail);
+ pr_debug("%li h%u t%u\n", ret, head, tail);
- atomic_sub(ret, &ctx->reqs_active);
+ put_reqs_available(ctx, ret);
out:
mutex_unlock(&ctx->ring_lock);
@@ -854,8 +1102,8 @@
if (!IS_ERR(ioctx)) {
ret = put_user(ioctx->user_id, ctxp);
if (ret)
- kill_ioctx(ioctx);
- put_ioctx(ioctx);
+ kill_ioctx(current->mm, ioctx);
+ percpu_ref_put(&ioctx->users);
}
out:
@@ -872,101 +1120,37 @@
{
struct kioctx *ioctx = lookup_ioctx(ctx);
if (likely(NULL != ioctx)) {
- kill_ioctx(ioctx);
- put_ioctx(ioctx);
+ kill_ioctx(current->mm, ioctx);
+ percpu_ref_put(&ioctx->users);
return 0;
}
pr_debug("EINVAL: io_destroy: invalid context id\n");
return -EINVAL;
}
-static void aio_advance_iovec(struct kiocb *iocb, ssize_t ret)
-{
- struct iovec *iov = &iocb->ki_iovec[iocb->ki_cur_seg];
-
- BUG_ON(ret <= 0);
-
- while (iocb->ki_cur_seg < iocb->ki_nr_segs && ret > 0) {
- ssize_t this = min((ssize_t)iov->iov_len, ret);
- iov->iov_base += this;
- iov->iov_len -= this;
- iocb->ki_left -= this;
- ret -= this;
- if (iov->iov_len == 0) {
- iocb->ki_cur_seg++;
- iov++;
- }
- }
-
- /* the caller should not have done more io than what fit in
- * the remaining iovecs */
- BUG_ON(ret > 0 && iocb->ki_left == 0);
-}
-
typedef ssize_t (aio_rw_op)(struct kiocb *, const struct iovec *,
unsigned long, loff_t);
-static ssize_t aio_rw_vect_retry(struct kiocb *iocb, int rw, aio_rw_op *rw_op)
-{
- struct file *file = iocb->ki_filp;
- struct address_space *mapping = file->f_mapping;
- struct inode *inode = mapping->host;
- ssize_t ret = 0;
-
- /* This matches the pread()/pwrite() logic */
- if (iocb->ki_pos < 0)
- return -EINVAL;
-
- if (rw == WRITE)
- file_start_write(file);
- do {
- ret = rw_op(iocb, &iocb->ki_iovec[iocb->ki_cur_seg],
- iocb->ki_nr_segs - iocb->ki_cur_seg,
- iocb->ki_pos);
- if (ret > 0)
- aio_advance_iovec(iocb, ret);
-
- /* retry all partial writes. retry partial reads as long as its a
- * regular file. */
- } while (ret > 0 && iocb->ki_left > 0 &&
- (rw == WRITE ||
- (!S_ISFIFO(inode->i_mode) && !S_ISSOCK(inode->i_mode))));
- if (rw == WRITE)
- file_end_write(file);
-
- /* This means we must have transferred all that we could */
- /* No need to retry anymore */
- if ((ret == 0) || (iocb->ki_left == 0))
- ret = iocb->ki_nbytes - iocb->ki_left;
-
- /* If we managed to write some out we return that, rather than
- * the eventual error. */
- if (rw == WRITE
- && ret < 0 && ret != -EIOCBQUEUED
- && iocb->ki_nbytes - iocb->ki_left)
- ret = iocb->ki_nbytes - iocb->ki_left;
-
- return ret;
-}
-
-static ssize_t aio_setup_vectored_rw(int rw, struct kiocb *kiocb, bool compat)
+static ssize_t aio_setup_vectored_rw(struct kiocb *kiocb,
+ int rw, char __user *buf,
+ unsigned long *nr_segs,
+ struct iovec **iovec,
+ bool compat)
{
ssize_t ret;
- kiocb->ki_nr_segs = kiocb->ki_nbytes;
+ *nr_segs = kiocb->ki_nbytes;
#ifdef CONFIG_COMPAT
if (compat)
ret = compat_rw_copy_check_uvector(rw,
- (struct compat_iovec __user *)kiocb->ki_buf,
- kiocb->ki_nr_segs, 1, &kiocb->ki_inline_vec,
- &kiocb->ki_iovec);
+ (struct compat_iovec __user *)buf,
+ *nr_segs, 1, *iovec, iovec);
else
#endif
ret = rw_copy_check_uvector(rw,
- (struct iovec __user *)kiocb->ki_buf,
- kiocb->ki_nr_segs, 1, &kiocb->ki_inline_vec,
- &kiocb->ki_iovec);
+ (struct iovec __user *)buf,
+ *nr_segs, 1, *iovec, iovec);
if (ret < 0)
return ret;
@@ -975,15 +1159,17 @@
return 0;
}
-static ssize_t aio_setup_single_vector(int rw, struct kiocb *kiocb)
+static ssize_t aio_setup_single_vector(struct kiocb *kiocb,
+ int rw, char __user *buf,
+ unsigned long *nr_segs,
+ struct iovec *iovec)
{
- if (unlikely(!access_ok(!rw, kiocb->ki_buf, kiocb->ki_nbytes)))
+ if (unlikely(!access_ok(!rw, buf, kiocb->ki_nbytes)))
return -EFAULT;
- kiocb->ki_iovec = &kiocb->ki_inline_vec;
- kiocb->ki_iovec->iov_base = kiocb->ki_buf;
- kiocb->ki_iovec->iov_len = kiocb->ki_nbytes;
- kiocb->ki_nr_segs = 1;
+ iovec->iov_base = buf;
+ iovec->iov_len = kiocb->ki_nbytes;
+ *nr_segs = 1;
return 0;
}
@@ -992,15 +1178,18 @@
* Performs the initial checks and aio retry method
* setup for the kiocb at the time of io submission.
*/
-static ssize_t aio_run_iocb(struct kiocb *req, bool compat)
+static ssize_t aio_run_iocb(struct kiocb *req, unsigned opcode,
+ char __user *buf, bool compat)
{
struct file *file = req->ki_filp;
ssize_t ret;
+ unsigned long nr_segs;
int rw;
fmode_t mode;
aio_rw_op *rw_op;
+ struct iovec inline_vec, *iovec = &inline_vec;
- switch (req->ki_opcode) {
+ switch (opcode) {
case IOCB_CMD_PREAD:
case IOCB_CMD_PREADV:
mode = FMODE_READ;
@@ -1021,21 +1210,38 @@
if (!rw_op)
return -EINVAL;
- ret = (req->ki_opcode == IOCB_CMD_PREADV ||
- req->ki_opcode == IOCB_CMD_PWRITEV)
- ? aio_setup_vectored_rw(rw, req, compat)
- : aio_setup_single_vector(rw, req);
+ ret = (opcode == IOCB_CMD_PREADV ||
+ opcode == IOCB_CMD_PWRITEV)
+ ? aio_setup_vectored_rw(req, rw, buf, &nr_segs,
+ &iovec, compat)
+ : aio_setup_single_vector(req, rw, buf, &nr_segs,
+ iovec);
if (ret)
return ret;
ret = rw_verify_area(rw, file, &req->ki_pos, req->ki_nbytes);
- if (ret < 0)
+ if (ret < 0) {
+ if (iovec != &inline_vec)
+ kfree(iovec);
return ret;
+ }
req->ki_nbytes = ret;
- req->ki_left = ret;
- ret = aio_rw_vect_retry(req, rw, rw_op);
+ /* XXX: move/kill - rw_verify_area()? */
+ /* This matches the pread()/pwrite() logic */
+ if (req->ki_pos < 0) {
+ ret = -EINVAL;
+ break;
+ }
+
+ if (rw == WRITE)
+ file_start_write(file);
+
+ ret = rw_op(req, iovec, nr_segs, req->ki_pos);
+
+ if (rw == WRITE)
+ file_end_write(file);
break;
case IOCB_CMD_FDSYNC:
@@ -1057,6 +1263,9 @@
return -EINVAL;
}
+ if (iovec != &inline_vec)
+ kfree(iovec);
+
if (ret != -EIOCBQUEUED) {
/*
* There's no easy way to restart the syscall since other AIO's
@@ -1128,21 +1337,18 @@
req->ki_obj.user = user_iocb;
req->ki_user_data = iocb->aio_data;
req->ki_pos = iocb->aio_offset;
+ req->ki_nbytes = iocb->aio_nbytes;
- req->ki_buf = (char __user *)(unsigned long)iocb->aio_buf;
- req->ki_left = req->ki_nbytes = iocb->aio_nbytes;
- req->ki_opcode = iocb->aio_lio_opcode;
-
- ret = aio_run_iocb(req, compat);
+ ret = aio_run_iocb(req, iocb->aio_lio_opcode,
+ (char __user *)(unsigned long)iocb->aio_buf,
+ compat);
if (ret)
goto out_put_req;
- aio_put_req(req); /* drop extra ref to req */
return 0;
out_put_req:
- atomic_dec(&ctx->reqs_active);
- aio_put_req(req); /* drop extra ref to req */
- aio_put_req(req); /* drop i/o ref to req */
+ put_reqs_available(ctx, 1);
+ kiocb_free(req);
return ret;
}
@@ -1195,7 +1401,7 @@
}
blk_finish_plug(&plug);
- put_ioctx(ctx);
+ percpu_ref_put(&ctx->users);
return i ? i : ret;
}
@@ -1252,7 +1458,6 @@
SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb,
struct io_event __user *, result)
{
- struct io_event res;
struct kioctx *ctx;
struct kiocb *kiocb;
u32 key;
@@ -1270,21 +1475,22 @@
kiocb = lookup_kiocb(ctx, iocb, key);
if (kiocb)
- ret = kiocb_cancel(ctx, kiocb, &res);
+ ret = kiocb_cancel(ctx, kiocb);
else
ret = -EINVAL;
spin_unlock_irq(&ctx->ctx_lock);
if (!ret) {
- /* Cancellation succeeded -- copy the result
- * into the user's buffer.
+ /*
+ * The result argument is no longer used - the io_event is
+ * always delivered via the ring buffer. -EINPROGRESS indicates
+ * cancellation is progress:
*/
- if (copy_to_user(result, &res, sizeof(res)))
- ret = -EFAULT;
+ ret = -EINPROGRESS;
}
- put_ioctx(ctx);
+ percpu_ref_put(&ctx->users);
return ret;
}
@@ -1313,7 +1519,7 @@
if (likely(ioctx)) {
if (likely(min_nr <= nr && min_nr >= 0))
ret = read_events(ioctx, min_nr, nr, events, timeout);
- put_ioctx(ioctx);
+ percpu_ref_put(&ioctx->users);
}
return ret;
}
diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index 47a65df..85c9618 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -109,6 +109,72 @@
};
/**
+ * anon_inode_getfile_private - creates a new file instance by hooking it up to an
+ * anonymous inode, and a dentry that describe the "class"
+ * of the file
+ *
+ * @name: [in] name of the "class" of the new file
+ * @fops: [in] file operations for the new file
+ * @priv: [in] private data for the new file (will be file's private_data)
+ * @flags: [in] flags
+ *
+ *
+ * Similar to anon_inode_getfile, but each file holds a single inode.
+ *
+ */
+struct file *anon_inode_getfile_private(const char *name,
+ const struct file_operations *fops,
+ void *priv, int flags)
+{
+ struct qstr this;
+ struct path path;
+ struct file *file;
+ struct inode *inode;
+
+ if (fops->owner && !try_module_get(fops->owner))
+ return ERR_PTR(-ENOENT);
+
+ inode = anon_inode_mkinode(anon_inode_mnt->mnt_sb);
+ if (IS_ERR(inode)) {
+ file = ERR_PTR(-ENOMEM);
+ goto err_module;
+ }
+
+ /*
+ * Link the inode to a directory entry by creating a unique name
+ * using the inode sequence number.
+ */
+ file = ERR_PTR(-ENOMEM);
+ this.name = name;
+ this.len = strlen(name);
+ this.hash = 0;
+ path.dentry = d_alloc_pseudo(anon_inode_mnt->mnt_sb, &this);
+ if (!path.dentry)
+ goto err_module;
+
+ path.mnt = mntget(anon_inode_mnt);
+
+ d_instantiate(path.dentry, inode);
+
+ file = alloc_file(&path, OPEN_FMODE(flags), fops);
+ if (IS_ERR(file))
+ goto err_dput;
+
+ file->f_mapping = inode->i_mapping;
+ file->f_flags = flags & (O_ACCMODE | O_NONBLOCK);
+ file->private_data = priv;
+
+ return file;
+
+err_dput:
+ path_put(&path);
+err_module:
+ module_put(fops->owner);
+ return file;
+}
+EXPORT_SYMBOL_GPL(anon_inode_getfile_private);
+
+/**
* anon_inode_getfile - creates a new file instance by hooking it up to an
* anonymous inode, and a dentry that describe the "class"
* of the file
diff --git a/fs/bfs/file.c b/fs/bfs/file.c
index ad3ea14..ae28922 100644
--- a/fs/bfs/file.c
+++ b/fs/bfs/file.c
@@ -166,7 +166,7 @@
struct inode *inode = mapping->host;
if (to > inode->i_size)
- truncate_pagecache(inode, to, inode->i_size);
+ truncate_pagecache(inode, inode->i_size);
}
static int bfs_write_begin(struct file *file, struct address_space *mapping,
diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c
index 8fb42916..6025084 100644
--- a/fs/bio-integrity.c
+++ b/fs/bio-integrity.c
@@ -716,14 +716,15 @@
return 0;
bs->bio_integrity_pool = mempool_create_slab_pool(pool_size, bip_slab);
-
- bs->bvec_integrity_pool = biovec_create_pool(bs, pool_size);
- if (!bs->bvec_integrity_pool)
- return -1;
-
if (!bs->bio_integrity_pool)
return -1;
+ bs->bvec_integrity_pool = biovec_create_pool(bs, pool_size);
+ if (!bs->bvec_integrity_pool) {
+ mempool_destroy(bs->bio_integrity_pool);
+ return -1;
+ }
+
return 0;
}
EXPORT_SYMBOL(bioset_integrity_create);
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 1173a4e..c3549ed 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1542,7 +1542,7 @@
return 0;
size -= pos;
- if (size < iocb->ki_left)
+ if (size < iocb->ki_nbytes)
nr_segs = iov_shorten((struct iovec *)iov, nr_segs, size);
return generic_file_aio_read(iocb, iov, nr_segs, pos);
}
diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig
index 2b3b832..398cbd5 100644
--- a/fs/btrfs/Kconfig
+++ b/fs/btrfs/Kconfig
@@ -72,3 +72,12 @@
performance, or export extra information via sysfs.
If unsure, say N.
+
+config BTRFS_ASSERT
+ bool "Btrfs assert support"
+ depends on BTRFS_FS
+ help
+ Enable run-time assertion checking. This will result in panics if
+ any of the assertions trip. This is meant for btrfs developers only.
+
+ If unsure, say N.
diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile
index 3932224..a91a6a3 100644
--- a/fs/btrfs/Makefile
+++ b/fs/btrfs/Makefile
@@ -8,7 +8,10 @@
extent_io.o volumes.o async-thread.o ioctl.o locking.o orphan.o \
export.o tree-log.o free-space-cache.o zlib.o lzo.o \
compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o \
- reada.o backref.o ulist.o qgroup.o send.o dev-replace.o raid56.o
+ reada.o backref.o ulist.o qgroup.o send.o dev-replace.o raid56.o \
+ uuid-tree.o
btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o
btrfs-$(CONFIG_BTRFS_FS_CHECK_INTEGRITY) += check-integrity.o
+
+btrfs-$(CONFIG_BTRFS_FS_RUN_SANITY_TESTS) += tests/free-space-tests.o
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 8bc5e8c..0552a59 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -119,6 +119,26 @@
u64 wanted_disk_byte;
};
+static struct kmem_cache *btrfs_prelim_ref_cache;
+
+int __init btrfs_prelim_ref_init(void)
+{
+ btrfs_prelim_ref_cache = kmem_cache_create("btrfs_prelim_ref",
+ sizeof(struct __prelim_ref),
+ 0,
+ SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD,
+ NULL);
+ if (!btrfs_prelim_ref_cache)
+ return -ENOMEM;
+ return 0;
+}
+
+void btrfs_prelim_ref_exit(void)
+{
+ if (btrfs_prelim_ref_cache)
+ kmem_cache_destroy(btrfs_prelim_ref_cache);
+}
+
/*
* the rules for all callers of this function are:
* - obtaining the parent is the goal
@@ -160,12 +180,12 @@
static int __add_prelim_ref(struct list_head *head, u64 root_id,
struct btrfs_key *key, int level,
- u64 parent, u64 wanted_disk_byte, int count)
+ u64 parent, u64 wanted_disk_byte, int count,
+ gfp_t gfp_mask)
{
struct __prelim_ref *ref;
- /* in case we're adding delayed refs, we're holding the refs spinlock */
- ref = kmalloc(sizeof(*ref), GFP_ATOMIC);
+ ref = kmem_cache_alloc(btrfs_prelim_ref_cache, gfp_mask);
if (!ref)
return -ENOMEM;
@@ -295,10 +315,9 @@
ret = btrfs_search_old_slot(root, &ref->key_for_search, path, time_seq);
pr_debug("search slot in root %llu (level %d, ref count %d) returned "
"%d for key (%llu %u %llu)\n",
- (unsigned long long)ref->root_id, level, ref->count, ret,
- (unsigned long long)ref->key_for_search.objectid,
- ref->key_for_search.type,
- (unsigned long long)ref->key_for_search.offset);
+ ref->root_id, level, ref->count, ret,
+ ref->key_for_search.objectid, ref->key_for_search.type,
+ ref->key_for_search.offset);
if (ret < 0)
goto out;
@@ -365,11 +384,12 @@
node = ulist_next(parents, &uiter);
ref->parent = node ? node->val : 0;
ref->inode_list = node ?
- (struct extent_inode_elem *)(uintptr_t)node->aux : 0;
+ (struct extent_inode_elem *)(uintptr_t)node->aux : NULL;
/* additional parents require new refs being added here */
while ((node = ulist_next(parents, &uiter))) {
- new_ref = kmalloc(sizeof(*new_ref), GFP_NOFS);
+ new_ref = kmem_cache_alloc(btrfs_prelim_ref_cache,
+ GFP_NOFS);
if (!new_ref) {
ret = -ENOMEM;
goto out;
@@ -493,7 +513,7 @@
ref1->count += ref2->count;
list_del(&ref2->list);
- kfree(ref2);
+ kmem_cache_free(btrfs_prelim_ref_cache, ref2);
}
}
@@ -548,7 +568,7 @@
ref = btrfs_delayed_node_to_tree_ref(node);
ret = __add_prelim_ref(prefs, ref->root, &op_key,
ref->level + 1, 0, node->bytenr,
- node->ref_mod * sgn);
+ node->ref_mod * sgn, GFP_ATOMIC);
break;
}
case BTRFS_SHARED_BLOCK_REF_KEY: {
@@ -558,7 +578,7 @@
ret = __add_prelim_ref(prefs, ref->root, NULL,
ref->level + 1, ref->parent,
node->bytenr,
- node->ref_mod * sgn);
+ node->ref_mod * sgn, GFP_ATOMIC);
break;
}
case BTRFS_EXTENT_DATA_REF_KEY: {
@@ -570,7 +590,7 @@
key.offset = ref->offset;
ret = __add_prelim_ref(prefs, ref->root, &key, 0, 0,
node->bytenr,
- node->ref_mod * sgn);
+ node->ref_mod * sgn, GFP_ATOMIC);
break;
}
case BTRFS_SHARED_DATA_REF_KEY: {
@@ -583,7 +603,7 @@
key.offset = ref->offset;
ret = __add_prelim_ref(prefs, ref->root, &key, 0,
ref->parent, node->bytenr,
- node->ref_mod * sgn);
+ node->ref_mod * sgn, GFP_ATOMIC);
break;
}
default:
@@ -657,7 +677,7 @@
case BTRFS_SHARED_BLOCK_REF_KEY:
ret = __add_prelim_ref(prefs, 0, NULL,
*info_level + 1, offset,
- bytenr, 1);
+ bytenr, 1, GFP_NOFS);
break;
case BTRFS_SHARED_DATA_REF_KEY: {
struct btrfs_shared_data_ref *sdref;
@@ -666,13 +686,13 @@
sdref = (struct btrfs_shared_data_ref *)(iref + 1);
count = btrfs_shared_data_ref_count(leaf, sdref);
ret = __add_prelim_ref(prefs, 0, NULL, 0, offset,
- bytenr, count);
+ bytenr, count, GFP_NOFS);
break;
}
case BTRFS_TREE_BLOCK_REF_KEY:
ret = __add_prelim_ref(prefs, offset, NULL,
*info_level + 1, 0,
- bytenr, 1);
+ bytenr, 1, GFP_NOFS);
break;
case BTRFS_EXTENT_DATA_REF_KEY: {
struct btrfs_extent_data_ref *dref;
@@ -687,7 +707,7 @@
key.offset = btrfs_extent_data_ref_offset(leaf, dref);
root = btrfs_extent_data_ref_root(leaf, dref);
ret = __add_prelim_ref(prefs, root, &key, 0, 0,
- bytenr, count);
+ bytenr, count, GFP_NOFS);
break;
}
default:
@@ -738,7 +758,7 @@
case BTRFS_SHARED_BLOCK_REF_KEY:
ret = __add_prelim_ref(prefs, 0, NULL,
info_level + 1, key.offset,
- bytenr, 1);
+ bytenr, 1, GFP_NOFS);
break;
case BTRFS_SHARED_DATA_REF_KEY: {
struct btrfs_shared_data_ref *sdref;
@@ -748,13 +768,13 @@
struct btrfs_shared_data_ref);
count = btrfs_shared_data_ref_count(leaf, sdref);
ret = __add_prelim_ref(prefs, 0, NULL, 0, key.offset,
- bytenr, count);
+ bytenr, count, GFP_NOFS);
break;
}
case BTRFS_TREE_BLOCK_REF_KEY:
ret = __add_prelim_ref(prefs, key.offset, NULL,
info_level + 1, 0,
- bytenr, 1);
+ bytenr, 1, GFP_NOFS);
break;
case BTRFS_EXTENT_DATA_REF_KEY: {
struct btrfs_extent_data_ref *dref;
@@ -770,7 +790,7 @@
key.offset = btrfs_extent_data_ref_offset(leaf, dref);
root = btrfs_extent_data_ref_root(leaf, dref);
ret = __add_prelim_ref(prefs, root, &key, 0, 0,
- bytenr, count);
+ bytenr, count, GFP_NOFS);
break;
}
default:
@@ -911,7 +931,6 @@
while (!list_empty(&prefs)) {
ref = list_first_entry(&prefs, struct __prelim_ref, list);
- list_del(&ref->list);
WARN_ON(ref->count < 0);
if (ref->count && ref->root_id && ref->parent == 0) {
/* no parent == root of tree */
@@ -935,8 +954,10 @@
}
ret = find_extent_in_eb(eb, bytenr,
*extent_item_pos, &eie);
- ref->inode_list = eie;
free_extent_buffer(eb);
+ if (ret < 0)
+ goto out;
+ ref->inode_list = eie;
}
ret = ulist_add_merge(refs, ref->parent,
(uintptr_t)ref->inode_list,
@@ -954,7 +975,8 @@
eie->next = ref->inode_list;
}
}
- kfree(ref);
+ list_del(&ref->list);
+ kmem_cache_free(btrfs_prelim_ref_cache, ref);
}
out:
@@ -962,13 +984,13 @@
while (!list_empty(&prefs)) {
ref = list_first_entry(&prefs, struct __prelim_ref, list);
list_del(&ref->list);
- kfree(ref);
+ kmem_cache_free(btrfs_prelim_ref_cache, ref);
}
while (!list_empty(&prefs_delayed)) {
ref = list_first_entry(&prefs_delayed, struct __prelim_ref,
list);
list_del(&ref->list);
- kfree(ref);
+ kmem_cache_free(btrfs_prelim_ref_cache, ref);
}
return ret;
@@ -1326,8 +1348,7 @@
found_key->type != BTRFS_METADATA_ITEM_KEY) ||
found_key->objectid > logical ||
found_key->objectid + size <= logical) {
- pr_debug("logical %llu is not within any extent\n",
- (unsigned long long)logical);
+ pr_debug("logical %llu is not within any extent\n", logical);
return -ENOENT;
}
@@ -1340,11 +1361,8 @@
pr_debug("logical %llu is at position %llu within the extent (%llu "
"EXTENT_ITEM %llu) flags %#llx size %u\n",
- (unsigned long long)logical,
- (unsigned long long)(logical - found_key->objectid),
- (unsigned long long)found_key->objectid,
- (unsigned long long)found_key->offset,
- (unsigned long long)flags, item_size);
+ logical, logical - found_key->objectid, found_key->objectid,
+ found_key->offset, flags, item_size);
WARN_ON(!flags_ret);
if (flags_ret) {
@@ -1516,7 +1534,7 @@
while (!ret && (root_node = ulist_next(roots, &root_uiter))) {
pr_debug("root %llu references leaf %llu, data list "
"%#llx\n", root_node->val, ref_node->val,
- (long long)ref_node->aux);
+ ref_node->aux);
ret = iterate_leaf_refs((struct extent_inode_elem *)
(uintptr_t)ref_node->aux,
root_node->val,
@@ -1608,9 +1626,8 @@
name_len = btrfs_inode_ref_name_len(eb, iref);
/* path must be released before calling iterate()! */
pr_debug("following ref at offset %u for inode %llu in "
- "tree %llu\n", cur,
- (unsigned long long)found_key.objectid,
- (unsigned long long)fs_root->objectid);
+ "tree %llu\n", cur, found_key.objectid,
+ fs_root->objectid);
ret = iterate(parent, name_len,
(unsigned long)(iref + 1), eb, ctx);
if (ret)
diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h
index 8f2e767..a910b27 100644
--- a/fs/btrfs/backref.h
+++ b/fs/btrfs/backref.h
@@ -72,4 +72,6 @@
struct btrfs_inode_extref **ret_extref,
u64 *found_off);
+int __init btrfs_prelim_ref_init(void);
+void btrfs_prelim_ref_exit(void);
#endif
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 08b286b..d0ae226 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -218,6 +218,27 @@
return 0;
}
+struct btrfs_dio_private {
+ struct inode *inode;
+ u64 logical_offset;
+ u64 disk_bytenr;
+ u64 bytes;
+ void *private;
+
+ /* number of bios pending for this dio */
+ atomic_t pending_bios;
+
+ /* IO errors */
+ int errors;
+
+ /* orig_bio is our btrfs_io_bio */
+ struct bio *orig_bio;
+
+ /* dio_bio came from fs/direct-io.c */
+ struct bio *dio_bio;
+ u8 csum[0];
+};
+
/*
* Disable DIO read nolock optimization, so new dio readers will be forced
* to grab i_mutex. It is used to avoid the endless truncate due to
diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index 1431a69..1c47be1 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -701,15 +701,13 @@
next_bytenr = btrfs_super_root(selected_super);
if (state->print_mask &
BTRFSIC_PRINT_MASK_ROOT_CHUNK_LOG_TREE_LOCATION)
- printk(KERN_INFO "root@%llu\n",
- (unsigned long long)next_bytenr);
+ printk(KERN_INFO "root@%llu\n", next_bytenr);
break;
case 1:
next_bytenr = btrfs_super_chunk_root(selected_super);
if (state->print_mask &
BTRFSIC_PRINT_MASK_ROOT_CHUNK_LOG_TREE_LOCATION)
- printk(KERN_INFO "chunk@%llu\n",
- (unsigned long long)next_bytenr);
+ printk(KERN_INFO "chunk@%llu\n", next_bytenr);
break;
case 2:
next_bytenr = btrfs_super_log_root(selected_super);
@@ -717,8 +715,7 @@
continue;
if (state->print_mask &
BTRFSIC_PRINT_MASK_ROOT_CHUNK_LOG_TREE_LOCATION)
- printk(KERN_INFO "log@%llu\n",
- (unsigned long long)next_bytenr);
+ printk(KERN_INFO "log@%llu\n", next_bytenr);
break;
}
@@ -727,7 +724,7 @@
next_bytenr, state->metablock_size);
if (state->print_mask & BTRFSIC_PRINT_MASK_NUM_COPIES)
printk(KERN_INFO "num_copies(log_bytenr=%llu) = %d\n",
- (unsigned long long)next_bytenr, num_copies);
+ next_bytenr, num_copies);
for (mirror_num = 1; mirror_num <= num_copies; mirror_num++) {
struct btrfsic_block *next_block;
@@ -742,8 +739,7 @@
printk(KERN_INFO "btrfsic:"
" btrfsic_map_block(root @%llu,"
" mirror %d) failed!\n",
- (unsigned long long)next_bytenr,
- mirror_num);
+ next_bytenr, mirror_num);
kfree(selected_super);
return -1;
}
@@ -767,7 +763,6 @@
if (ret < (int)PAGE_CACHE_SIZE) {
printk(KERN_INFO
"btrfsic: read @logical %llu failed!\n",
- (unsigned long long)
tmp_next_block_ctx.start);
btrfsic_release_block_ctx(&tmp_next_block_ctx);
kfree(selected_super);
@@ -813,7 +808,7 @@
(bh->b_data + (dev_bytenr & 4095));
if (btrfs_super_bytenr(super_tmp) != dev_bytenr ||
- super_tmp->magic != cpu_to_le64(BTRFS_MAGIC) ||
+ btrfs_super_magic(super_tmp) != BTRFS_MAGIC ||
memcmp(device->uuid, super_tmp->dev_item.uuid, BTRFS_UUID_SIZE) ||
btrfs_super_nodesize(super_tmp) != state->metablock_size ||
btrfs_super_leafsize(super_tmp) != state->metablock_size ||
@@ -847,10 +842,8 @@
printk_in_rcu(KERN_INFO "New initial S-block (bdev %p, %s)"
" @%llu (%s/%llu/%d)\n",
superblock_bdev,
- rcu_str_deref(device->name),
- (unsigned long long)dev_bytenr,
- dev_state->name,
- (unsigned long long)dev_bytenr,
+ rcu_str_deref(device->name), dev_bytenr,
+ dev_state->name, dev_bytenr,
superblock_mirror_num);
list_add(&superblock_tmp->all_blocks_node,
&state->all_blocks_list);
@@ -880,20 +873,20 @@
tmp_disk_key.offset = 0;
switch (pass) {
case 0:
- tmp_disk_key.objectid =
- cpu_to_le64(BTRFS_ROOT_TREE_OBJECTID);
+ btrfs_set_disk_key_objectid(&tmp_disk_key,
+ BTRFS_ROOT_TREE_OBJECTID);
additional_string = "initial root ";
next_bytenr = btrfs_super_root(super_tmp);
break;
case 1:
- tmp_disk_key.objectid =
- cpu_to_le64(BTRFS_CHUNK_TREE_OBJECTID);
+ btrfs_set_disk_key_objectid(&tmp_disk_key,
+ BTRFS_CHUNK_TREE_OBJECTID);
additional_string = "initial chunk ";
next_bytenr = btrfs_super_chunk_root(super_tmp);
break;
case 2:
- tmp_disk_key.objectid =
- cpu_to_le64(BTRFS_TREE_LOG_OBJECTID);
+ btrfs_set_disk_key_objectid(&tmp_disk_key,
+ BTRFS_TREE_LOG_OBJECTID);
additional_string = "initial log ";
next_bytenr = btrfs_super_log_root(super_tmp);
if (0 == next_bytenr)
@@ -906,7 +899,7 @@
next_bytenr, state->metablock_size);
if (state->print_mask & BTRFSIC_PRINT_MASK_NUM_COPIES)
printk(KERN_INFO "num_copies(log_bytenr=%llu) = %d\n",
- (unsigned long long)next_bytenr, num_copies);
+ next_bytenr, num_copies);
for (mirror_num = 1; mirror_num <= num_copies; mirror_num++) {
struct btrfsic_block *next_block;
struct btrfsic_block_data_ctx tmp_next_block_ctx;
@@ -918,8 +911,7 @@
mirror_num)) {
printk(KERN_INFO "btrfsic: btrfsic_map_block("
"bytenr @%llu, mirror %d) failed!\n",
- (unsigned long long)next_bytenr,
- mirror_num);
+ next_bytenr, mirror_num);
brelse(bh);
return -1;
}
@@ -1003,19 +995,17 @@
(struct btrfs_leaf *)sf->hdr;
if (-1 == sf->i) {
- sf->nr = le32_to_cpu(leafhdr->header.nritems);
+ sf->nr = btrfs_stack_header_nritems(&leafhdr->header);
if (state->print_mask & BTRFSIC_PRINT_MASK_VERBOSE)
printk(KERN_INFO
"leaf %llu items %d generation %llu"
" owner %llu\n",
- (unsigned long long)
- sf->block_ctx->start,
- sf->nr,
- (unsigned long long)
- le64_to_cpu(leafhdr->header.generation),
- (unsigned long long)
- le64_to_cpu(leafhdr->header.owner));
+ sf->block_ctx->start, sf->nr,
+ btrfs_stack_header_generation(
+ &leafhdr->header),
+ btrfs_stack_header_owner(
+ &leafhdr->header));
}
continue_with_current_leaf_stack_frame:
@@ -1047,10 +1037,10 @@
&disk_item,
disk_item_offset,
sizeof(struct btrfs_item));
- item_offset = le32_to_cpu(disk_item.offset);
- item_size = le32_to_cpu(disk_item.size);
+ item_offset = btrfs_stack_item_offset(&disk_item);
+ item_size = btrfs_stack_item_offset(&disk_item);
disk_key = &disk_item.key;
- type = disk_key->type;
+ type = btrfs_disk_key_type(disk_key);
if (BTRFS_ROOT_ITEM_KEY == type) {
struct btrfs_root_item root_item;
@@ -1066,7 +1056,7 @@
sf->block_ctx, &root_item,
root_item_offset,
item_size);
- next_bytenr = le64_to_cpu(root_item.bytenr);
+ next_bytenr = btrfs_root_bytenr(&root_item);
sf->error =
btrfsic_create_link_to_next_block(
@@ -1081,8 +1071,8 @@
&sf->num_copies,
&sf->mirror_num,
disk_key,
- le64_to_cpu(root_item.
- generation));
+ btrfs_root_generation(
+ &root_item));
if (sf->error)
goto one_stack_frame_backwards;
@@ -1130,18 +1120,17 @@
struct btrfs_node *const nodehdr = (struct btrfs_node *)sf->hdr;
if (-1 == sf->i) {
- sf->nr = le32_to_cpu(nodehdr->header.nritems);
+ sf->nr = btrfs_stack_header_nritems(&nodehdr->header);
if (state->print_mask & BTRFSIC_PRINT_MASK_VERBOSE)
printk(KERN_INFO "node %llu level %d items %d"
" generation %llu owner %llu\n",
- (unsigned long long)
sf->block_ctx->start,
nodehdr->header.level, sf->nr,
- (unsigned long long)
- le64_to_cpu(nodehdr->header.generation),
- (unsigned long long)
- le64_to_cpu(nodehdr->header.owner));
+ btrfs_stack_header_generation(
+ &nodehdr->header),
+ btrfs_stack_header_owner(
+ &nodehdr->header));
}
continue_with_current_node_stack_frame:
@@ -1168,7 +1157,7 @@
btrfsic_read_from_block_data(
sf->block_ctx, &key_ptr, key_ptr_offset,
sizeof(struct btrfs_key_ptr));
- next_bytenr = le64_to_cpu(key_ptr.blockptr);
+ next_bytenr = btrfs_stack_key_blockptr(&key_ptr);
sf->error = btrfsic_create_link_to_next_block(
state,
@@ -1182,7 +1171,7 @@
&sf->num_copies,
&sf->mirror_num,
&key_ptr.key,
- le64_to_cpu(key_ptr.generation));
+ btrfs_stack_key_generation(&key_ptr));
if (sf->error)
goto one_stack_frame_backwards;
@@ -1247,8 +1236,7 @@
unsigned long i = (start_offset + offset) >> PAGE_CACHE_SHIFT;
WARN_ON(offset + len > block_ctx->len);
- offset_in_page = (start_offset + offset) &
- ((unsigned long)PAGE_CACHE_SIZE - 1);
+ offset_in_page = (start_offset + offset) & (PAGE_CACHE_SIZE - 1);
while (len > 0) {
cur = min(len, ((size_t)PAGE_CACHE_SIZE - offset_in_page));
@@ -1290,7 +1278,7 @@
next_bytenr, state->metablock_size);
if (state->print_mask & BTRFSIC_PRINT_MASK_NUM_COPIES)
printk(KERN_INFO "num_copies(log_bytenr=%llu) = %d\n",
- (unsigned long long)next_bytenr, *num_copiesp);
+ next_bytenr, *num_copiesp);
*mirror_nump = 1;
}
@@ -1307,7 +1295,7 @@
if (ret) {
printk(KERN_INFO
"btrfsic: btrfsic_map_block(@%llu, mirror=%d) failed!\n",
- (unsigned long long)next_bytenr, *mirror_nump);
+ next_bytenr, *mirror_nump);
btrfsic_release_block_ctx(next_block_ctx);
*next_blockp = NULL;
return -1;
@@ -1335,20 +1323,16 @@
"Referenced block @%llu (%s/%llu/%d)"
" found in hash table, %c,"
" bytenr mismatch (!= stored %llu).\n",
- (unsigned long long)next_bytenr,
- next_block_ctx->dev->name,
- (unsigned long long)next_block_ctx->dev_bytenr,
- *mirror_nump,
+ next_bytenr, next_block_ctx->dev->name,
+ next_block_ctx->dev_bytenr, *mirror_nump,
btrfsic_get_block_type(state, next_block),
- (unsigned long long)next_block->logical_bytenr);
+ next_block->logical_bytenr);
} else if (state->print_mask & BTRFSIC_PRINT_MASK_VERBOSE)
printk(KERN_INFO
"Referenced block @%llu (%s/%llu/%d)"
" found in hash table, %c.\n",
- (unsigned long long)next_bytenr,
- next_block_ctx->dev->name,
- (unsigned long long)next_block_ctx->dev_bytenr,
- *mirror_nump,
+ next_bytenr, next_block_ctx->dev->name,
+ next_block_ctx->dev_bytenr, *mirror_nump,
btrfsic_get_block_type(state, next_block));
next_block->logical_bytenr = next_bytenr;
@@ -1400,7 +1384,7 @@
if (ret < (int)next_block_ctx->len) {
printk(KERN_INFO
"btrfsic: read block @logical %llu failed!\n",
- (unsigned long long)next_bytenr);
+ next_bytenr);
btrfsic_release_block_ctx(next_block_ctx);
*next_blockp = NULL;
return -1;
@@ -1444,12 +1428,12 @@
file_extent_item_offset,
offsetof(struct btrfs_file_extent_item, disk_num_bytes));
if (BTRFS_FILE_EXTENT_REG != file_extent_item.type ||
- ((u64)0) == le64_to_cpu(file_extent_item.disk_bytenr)) {
+ btrfs_stack_file_extent_disk_bytenr(&file_extent_item) == 0) {
if (state->print_mask & BTRFSIC_PRINT_MASK_VERY_VERBOSE)
printk(KERN_INFO "extent_data: type %u, disk_bytenr = %llu\n",
file_extent_item.type,
- (unsigned long long)
- le64_to_cpu(file_extent_item.disk_bytenr));
+ btrfs_stack_file_extent_disk_bytenr(
+ &file_extent_item));
return 0;
}
@@ -1463,20 +1447,19 @@
btrfsic_read_from_block_data(block_ctx, &file_extent_item,
file_extent_item_offset,
sizeof(struct btrfs_file_extent_item));
- next_bytenr = le64_to_cpu(file_extent_item.disk_bytenr) +
- le64_to_cpu(file_extent_item.offset);
- generation = le64_to_cpu(file_extent_item.generation);
- num_bytes = le64_to_cpu(file_extent_item.num_bytes);
- generation = le64_to_cpu(file_extent_item.generation);
+ next_bytenr = btrfs_stack_file_extent_disk_bytenr(&file_extent_item) +
+ btrfs_stack_file_extent_offset(&file_extent_item);
+ generation = btrfs_stack_file_extent_generation(&file_extent_item);
+ num_bytes = btrfs_stack_file_extent_num_bytes(&file_extent_item);
+ generation = btrfs_stack_file_extent_generation(&file_extent_item);
if (state->print_mask & BTRFSIC_PRINT_MASK_VERY_VERBOSE)
printk(KERN_INFO "extent_data: type %u, disk_bytenr = %llu,"
" offset = %llu, num_bytes = %llu\n",
file_extent_item.type,
- (unsigned long long)
- le64_to_cpu(file_extent_item.disk_bytenr),
- (unsigned long long)le64_to_cpu(file_extent_item.offset),
- (unsigned long long)num_bytes);
+ btrfs_stack_file_extent_disk_bytenr(&file_extent_item),
+ btrfs_stack_file_extent_offset(&file_extent_item),
+ num_bytes);
while (num_bytes > 0) {
u32 chunk_len;
int num_copies;
@@ -1492,7 +1475,7 @@
next_bytenr, state->datablock_size);
if (state->print_mask & BTRFSIC_PRINT_MASK_NUM_COPIES)
printk(KERN_INFO "num_copies(log_bytenr=%llu) = %d\n",
- (unsigned long long)next_bytenr, num_copies);
+ next_bytenr, num_copies);
for (mirror_num = 1; mirror_num <= num_copies; mirror_num++) {
struct btrfsic_block_data_ctx next_block_ctx;
struct btrfsic_block *next_block;
@@ -1504,8 +1487,7 @@
if (state->print_mask & BTRFSIC_PRINT_MASK_VERY_VERBOSE)
printk(KERN_INFO
"\tdisk_bytenr = %llu, num_bytes %u\n",
- (unsigned long long)next_bytenr,
- chunk_len);
+ next_bytenr, chunk_len);
ret = btrfsic_map_block(state, next_bytenr,
chunk_len, &next_block_ctx,
mirror_num);
@@ -1513,8 +1495,7 @@
printk(KERN_INFO
"btrfsic: btrfsic_map_block(@%llu,"
" mirror=%d) failed!\n",
- (unsigned long long)next_bytenr,
- mirror_num);
+ next_bytenr, mirror_num);
return -1;
}
@@ -1543,12 +1524,10 @@
" found in hash table, D,"
" bytenr mismatch"
" (!= stored %llu).\n",
- (unsigned long long)next_bytenr,
+ next_bytenr,
next_block_ctx.dev->name,
- (unsigned long long)
next_block_ctx.dev_bytenr,
mirror_num,
- (unsigned long long)
next_block->logical_bytenr);
}
next_block->logical_bytenr = next_bytenr;
@@ -1675,7 +1654,7 @@
if (block_ctx->dev_bytenr & ((u64)PAGE_CACHE_SIZE - 1)) {
printk(KERN_INFO
"btrfsic: read_block() with unaligned bytenr %llu\n",
- (unsigned long long)block_ctx->dev_bytenr);
+ block_ctx->dev_bytenr);
return -1;
}
@@ -1772,10 +1751,8 @@
printk(KERN_INFO "%c-block @%llu (%s/%llu/%d)\n",
btrfsic_get_block_type(state, b_all),
- (unsigned long long)b_all->logical_bytenr,
- b_all->dev_state->name,
- (unsigned long long)b_all->dev_bytenr,
- b_all->mirror_num);
+ b_all->logical_bytenr, b_all->dev_state->name,
+ b_all->dev_bytenr, b_all->mirror_num);
list_for_each(elem_ref_to, &b_all->ref_to_list) {
const struct btrfsic_block_link *const l =
@@ -1787,16 +1764,13 @@
" refers %u* to"
" %c @%llu (%s/%llu/%d)\n",
btrfsic_get_block_type(state, b_all),
- (unsigned long long)b_all->logical_bytenr,
- b_all->dev_state->name,
- (unsigned long long)b_all->dev_bytenr,
- b_all->mirror_num,
+ b_all->logical_bytenr, b_all->dev_state->name,
+ b_all->dev_bytenr, b_all->mirror_num,
l->ref_cnt,
btrfsic_get_block_type(state, l->block_ref_to),
- (unsigned long long)
l->block_ref_to->logical_bytenr,
l->block_ref_to->dev_state->name,
- (unsigned long long)l->block_ref_to->dev_bytenr,
+ l->block_ref_to->dev_bytenr,
l->block_ref_to->mirror_num);
}
@@ -1810,16 +1784,12 @@
" is ref %u* from"
" %c @%llu (%s/%llu/%d)\n",
btrfsic_get_block_type(state, b_all),
- (unsigned long long)b_all->logical_bytenr,
- b_all->dev_state->name,
- (unsigned long long)b_all->dev_bytenr,
- b_all->mirror_num,
+ b_all->logical_bytenr, b_all->dev_state->name,
+ b_all->dev_bytenr, b_all->mirror_num,
l->ref_cnt,
btrfsic_get_block_type(state, l->block_ref_from),
- (unsigned long long)
l->block_ref_from->logical_bytenr,
l->block_ref_from->dev_state->name,
- (unsigned long long)
l->block_ref_from->dev_bytenr,
l->block_ref_from->mirror_num);
}
@@ -1896,8 +1866,8 @@
struct list_head *tmp_ref_to;
if (block->is_superblock) {
- bytenr = le64_to_cpu(((struct btrfs_super_block *)
- mapped_datav[0])->bytenr);
+ bytenr = btrfs_super_bytenr((struct btrfs_super_block *)
+ mapped_datav[0]);
if (num_pages * PAGE_CACHE_SIZE <
BTRFS_SUPER_INFO_SIZE) {
printk(KERN_INFO
@@ -1923,8 +1893,9 @@
return;
}
processed_len = state->metablock_size;
- bytenr = le64_to_cpu(((struct btrfs_header *)
- mapped_datav[0])->bytenr);
+ bytenr = btrfs_stack_header_bytenr(
+ (struct btrfs_header *)
+ mapped_datav[0]);
btrfsic_cmp_log_and_dev_bytenr(state, bytenr,
dev_state,
dev_bytenr);
@@ -1935,12 +1906,9 @@
" found in hash table, %c,"
" bytenr mismatch"
" (!= stored %llu).\n",
- (unsigned long long)bytenr,
- dev_state->name,
- (unsigned long long)dev_bytenr,
+ bytenr, dev_state->name, dev_bytenr,
block->mirror_num,
btrfsic_get_block_type(state, block),
- (unsigned long long)
block->logical_bytenr);
block->logical_bytenr = bytenr;
} else if (state->print_mask &
@@ -1948,9 +1916,7 @@
printk(KERN_INFO
"Written block @%llu (%s/%llu/%d)"
" found in hash table, %c.\n",
- (unsigned long long)bytenr,
- dev_state->name,
- (unsigned long long)dev_bytenr,
+ bytenr, dev_state->name, dev_bytenr,
block->mirror_num,
btrfsic_get_block_type(state, block));
} else {
@@ -1966,9 +1932,7 @@
printk(KERN_INFO
"Written block @%llu (%s/%llu/%d)"
" found in hash table, %c.\n",
- (unsigned long long)bytenr,
- dev_state->name,
- (unsigned long long)dev_bytenr,
+ bytenr, dev_state->name, dev_bytenr,
block->mirror_num,
btrfsic_get_block_type(state, block));
}
@@ -1985,21 +1949,14 @@
" new(gen=%llu),"
" which is referenced by most recent superblock"
" (superblockgen=%llu)!\n",
- btrfsic_get_block_type(state, block),
- (unsigned long long)bytenr,
- dev_state->name,
- (unsigned long long)dev_bytenr,
- block->mirror_num,
- (unsigned long long)block->generation,
- (unsigned long long)
- le64_to_cpu(block->disk_key.objectid),
+ btrfsic_get_block_type(state, block), bytenr,
+ dev_state->name, dev_bytenr, block->mirror_num,
+ block->generation,
+ btrfs_disk_key_objectid(&block->disk_key),
block->disk_key.type,
- (unsigned long long)
- le64_to_cpu(block->disk_key.offset),
- (unsigned long long)
- le64_to_cpu(((struct btrfs_header *)
- mapped_datav[0])->generation),
- (unsigned long long)
+ btrfs_disk_key_offset(&block->disk_key),
+ btrfs_stack_header_generation(
+ (struct btrfs_header *) mapped_datav[0]),
state->max_superblock_generation);
btrfsic_dump_tree(state);
}
@@ -2008,15 +1965,12 @@
printk(KERN_INFO "btrfs: attempt to overwrite %c-block"
" @%llu (%s/%llu/%d), oldgen=%llu, newgen=%llu,"
" which is not yet iodone!\n",
- btrfsic_get_block_type(state, block),
- (unsigned long long)bytenr,
- dev_state->name,
- (unsigned long long)dev_bytenr,
- block->mirror_num,
- (unsigned long long)block->generation,
- (unsigned long long)
- le64_to_cpu(((struct btrfs_header *)
- mapped_datav[0])->generation));
+ btrfsic_get_block_type(state, block), bytenr,
+ dev_state->name, dev_bytenr, block->mirror_num,
+ block->generation,
+ btrfs_stack_header_generation(
+ (struct btrfs_header *)
+ mapped_datav[0]));
/* it would not be safe to go on */
btrfsic_dump_tree(state);
goto continue_loop;
@@ -2056,7 +2010,7 @@
if (ret) {
printk(KERN_INFO
"btrfsic: btrfsic_map_block(root @%llu)"
- " failed!\n", (unsigned long long)bytenr);
+ " failed!\n", bytenr);
goto continue_loop;
}
block_ctx.datav = mapped_datav;
@@ -2140,7 +2094,7 @@
printk(KERN_INFO
"btrfsic: btrfsic_process_metablock"
"(root @%llu) failed!\n",
- (unsigned long long)dev_bytenr);
+ dev_bytenr);
} else {
block->is_metadata = 0;
block->mirror_num = 0; /* unknown */
@@ -2168,8 +2122,7 @@
if (state->print_mask & BTRFSIC_PRINT_MASK_VERBOSE)
printk(KERN_INFO "Written block (%s/%llu/?)"
" !found in hash table, D.\n",
- dev_state->name,
- (unsigned long long)dev_bytenr);
+ dev_state->name, dev_bytenr);
if (!state->include_extent_data) {
/* ignore that written D block */
goto continue_loop;
@@ -2184,17 +2137,16 @@
block_ctx.pagev = NULL;
} else {
processed_len = state->metablock_size;
- bytenr = le64_to_cpu(((struct btrfs_header *)
- mapped_datav[0])->bytenr);
+ bytenr = btrfs_stack_header_bytenr(
+ (struct btrfs_header *)
+ mapped_datav[0]);
btrfsic_cmp_log_and_dev_bytenr(state, bytenr, dev_state,
dev_bytenr);
if (state->print_mask & BTRFSIC_PRINT_MASK_VERBOSE)
printk(KERN_INFO
"Written block @%llu (%s/%llu/?)"
" !found in hash table, M.\n",
- (unsigned long long)bytenr,
- dev_state->name,
- (unsigned long long)dev_bytenr);
+ bytenr, dev_state->name, dev_bytenr);
ret = btrfsic_map_block(state, bytenr, processed_len,
&block_ctx, 0);
@@ -2202,7 +2154,7 @@
printk(KERN_INFO
"btrfsic: btrfsic_map_block(root @%llu)"
" failed!\n",
- (unsigned long long)dev_bytenr);
+ dev_bytenr);
goto continue_loop;
}
}
@@ -2267,10 +2219,8 @@
printk(KERN_INFO
"New written %c-block @%llu (%s/%llu/%d)\n",
is_metadata ? 'M' : 'D',
- (unsigned long long)block->logical_bytenr,
- block->dev_state->name,
- (unsigned long long)block->dev_bytenr,
- block->mirror_num);
+ block->logical_bytenr, block->dev_state->name,
+ block->dev_bytenr, block->mirror_num);
list_add(&block->all_blocks_node, &state->all_blocks_list);
btrfsic_block_hashtable_add(block, &state->block_hashtable);
@@ -2281,7 +2231,7 @@
printk(KERN_INFO
"btrfsic: process_metablock(root @%llu)"
" failed!\n",
- (unsigned long long)dev_bytenr);
+ dev_bytenr);
}
btrfsic_release_block_ctx(&block_ctx);
}
@@ -2319,10 +2269,8 @@
"bio_end_io(err=%d) for %c @%llu (%s/%llu/%d)\n",
bio_error_status,
btrfsic_get_block_type(dev_state->state, block),
- (unsigned long long)block->logical_bytenr,
- dev_state->name,
- (unsigned long long)block->dev_bytenr,
- block->mirror_num);
+ block->logical_bytenr, dev_state->name,
+ block->dev_bytenr, block->mirror_num);
next_block = block->next_in_same_bio;
block->iodone_w_error = iodone_w_error;
if (block->submit_bio_bh_rw & REQ_FLUSH) {
@@ -2332,7 +2280,6 @@
printk(KERN_INFO
"bio_end_io() new %s flush_gen=%llu\n",
dev_state->name,
- (unsigned long long)
dev_state->last_flush_gen);
}
if (block->submit_bio_bh_rw & REQ_FUA)
@@ -2358,10 +2305,8 @@
"bh_end_io(error=%d) for %c @%llu (%s/%llu/%d)\n",
iodone_w_error,
btrfsic_get_block_type(dev_state->state, block),
- (unsigned long long)block->logical_bytenr,
- block->dev_state->name,
- (unsigned long long)block->dev_bytenr,
- block->mirror_num);
+ block->logical_bytenr, block->dev_state->name,
+ block->dev_bytenr, block->mirror_num);
block->iodone_w_error = iodone_w_error;
if (block->submit_bio_bh_rw & REQ_FLUSH) {
@@ -2370,8 +2315,7 @@
BTRFSIC_PRINT_MASK_END_IO_BIO_BH))
printk(KERN_INFO
"bh_end_io() new %s flush_gen=%llu\n",
- dev_state->name,
- (unsigned long long)dev_state->last_flush_gen);
+ dev_state->name, dev_state->last_flush_gen);
}
if (block->submit_bio_bh_rw & REQ_FUA)
block->flush_gen = 0; /* FUA completed means block is on disk */
@@ -2396,26 +2340,20 @@
printk(KERN_INFO
"btrfsic: superblock @%llu (%s/%llu/%d)"
" with old gen %llu <= %llu\n",
- (unsigned long long)superblock->logical_bytenr,
+ superblock->logical_bytenr,
superblock->dev_state->name,
- (unsigned long long)superblock->dev_bytenr,
- superblock->mirror_num,
- (unsigned long long)
+ superblock->dev_bytenr, superblock->mirror_num,
btrfs_super_generation(super_hdr),
- (unsigned long long)
state->max_superblock_generation);
} else {
if (state->print_mask & BTRFSIC_PRINT_MASK_SUPERBLOCK_WRITE)
printk(KERN_INFO
"btrfsic: got new superblock @%llu (%s/%llu/%d)"
" with new gen %llu > %llu\n",
- (unsigned long long)superblock->logical_bytenr,
+ superblock->logical_bytenr,
superblock->dev_state->name,
- (unsigned long long)superblock->dev_bytenr,
- superblock->mirror_num,
- (unsigned long long)
+ superblock->dev_bytenr, superblock->mirror_num,
btrfs_super_generation(super_hdr),
- (unsigned long long)
state->max_superblock_generation);
state->max_superblock_generation =
@@ -2432,43 +2370,41 @@
int num_copies;
int mirror_num;
const char *additional_string = NULL;
- struct btrfs_disk_key tmp_disk_key;
+ struct btrfs_disk_key tmp_disk_key = {0};
- tmp_disk_key.type = BTRFS_ROOT_ITEM_KEY;
- tmp_disk_key.offset = 0;
+ btrfs_set_disk_key_objectid(&tmp_disk_key,
+ BTRFS_ROOT_ITEM_KEY);
+ btrfs_set_disk_key_objectid(&tmp_disk_key, 0);
switch (pass) {
case 0:
- tmp_disk_key.objectid =
- cpu_to_le64(BTRFS_ROOT_TREE_OBJECTID);
+ btrfs_set_disk_key_objectid(&tmp_disk_key,
+ BTRFS_ROOT_TREE_OBJECTID);
additional_string = "root ";
next_bytenr = btrfs_super_root(super_hdr);
if (state->print_mask &
BTRFSIC_PRINT_MASK_ROOT_CHUNK_LOG_TREE_LOCATION)
- printk(KERN_INFO "root@%llu\n",
- (unsigned long long)next_bytenr);
+ printk(KERN_INFO "root@%llu\n", next_bytenr);
break;
case 1:
- tmp_disk_key.objectid =
- cpu_to_le64(BTRFS_CHUNK_TREE_OBJECTID);
+ btrfs_set_disk_key_objectid(&tmp_disk_key,
+ BTRFS_CHUNK_TREE_OBJECTID);
additional_string = "chunk ";
next_bytenr = btrfs_super_chunk_root(super_hdr);
if (state->print_mask &
BTRFSIC_PRINT_MASK_ROOT_CHUNK_LOG_TREE_LOCATION)
- printk(KERN_INFO "chunk@%llu\n",
- (unsigned long long)next_bytenr);
+ printk(KERN_INFO "chunk@%llu\n", next_bytenr);
break;
case 2:
- tmp_disk_key.objectid =
- cpu_to_le64(BTRFS_TREE_LOG_OBJECTID);
+ btrfs_set_disk_key_objectid(&tmp_disk_key,
+ BTRFS_TREE_LOG_OBJECTID);
additional_string = "log ";
next_bytenr = btrfs_super_log_root(super_hdr);
if (0 == next_bytenr)
continue;
if (state->print_mask &
BTRFSIC_PRINT_MASK_ROOT_CHUNK_LOG_TREE_LOCATION)
- printk(KERN_INFO "log@%llu\n",
- (unsigned long long)next_bytenr);
+ printk(KERN_INFO "log@%llu\n", next_bytenr);
break;
}
@@ -2477,7 +2413,7 @@
next_bytenr, BTRFS_SUPER_INFO_SIZE);
if (state->print_mask & BTRFSIC_PRINT_MASK_NUM_COPIES)
printk(KERN_INFO "num_copies(log_bytenr=%llu) = %d\n",
- (unsigned long long)next_bytenr, num_copies);
+ next_bytenr, num_copies);
for (mirror_num = 1; mirror_num <= num_copies; mirror_num++) {
int was_created;
@@ -2493,8 +2429,7 @@
printk(KERN_INFO
"btrfsic: btrfsic_map_block(@%llu,"
" mirror=%d) failed!\n",
- (unsigned long long)next_bytenr,
- mirror_num);
+ next_bytenr, mirror_num);
return -1;
}
@@ -2579,26 +2514,22 @@
" %u* refers to %c @%llu (%s/%llu/%d)\n",
recursion_level,
btrfsic_get_block_type(state, block),
- (unsigned long long)block->logical_bytenr,
- block->dev_state->name,
- (unsigned long long)block->dev_bytenr,
- block->mirror_num,
+ block->logical_bytenr, block->dev_state->name,
+ block->dev_bytenr, block->mirror_num,
l->ref_cnt,
btrfsic_get_block_type(state, l->block_ref_to),
- (unsigned long long)
l->block_ref_to->logical_bytenr,
l->block_ref_to->dev_state->name,
- (unsigned long long)l->block_ref_to->dev_bytenr,
+ l->block_ref_to->dev_bytenr,
l->block_ref_to->mirror_num);
if (l->block_ref_to->never_written) {
printk(KERN_INFO "btrfs: attempt to write superblock"
" which references block %c @%llu (%s/%llu/%d)"
" which is never written!\n",
btrfsic_get_block_type(state, l->block_ref_to),
- (unsigned long long)
l->block_ref_to->logical_bytenr,
l->block_ref_to->dev_state->name,
- (unsigned long long)l->block_ref_to->dev_bytenr,
+ l->block_ref_to->dev_bytenr,
l->block_ref_to->mirror_num);
ret = -1;
} else if (!l->block_ref_to->is_iodone) {
@@ -2606,10 +2537,9 @@
" which references block %c @%llu (%s/%llu/%d)"
" which is not yet iodone!\n",
btrfsic_get_block_type(state, l->block_ref_to),
- (unsigned long long)
l->block_ref_to->logical_bytenr,
l->block_ref_to->dev_state->name,
- (unsigned long long)l->block_ref_to->dev_bytenr,
+ l->block_ref_to->dev_bytenr,
l->block_ref_to->mirror_num);
ret = -1;
} else if (l->block_ref_to->iodone_w_error) {
@@ -2617,10 +2547,9 @@
" which references block %c @%llu (%s/%llu/%d)"
" which has write error!\n",
btrfsic_get_block_type(state, l->block_ref_to),
- (unsigned long long)
l->block_ref_to->logical_bytenr,
l->block_ref_to->dev_state->name,
- (unsigned long long)l->block_ref_to->dev_bytenr,
+ l->block_ref_to->dev_bytenr,
l->block_ref_to->mirror_num);
ret = -1;
} else if (l->parent_generation !=
@@ -2634,13 +2563,12 @@
" with generation %llu !="
" parent generation %llu!\n",
btrfsic_get_block_type(state, l->block_ref_to),
- (unsigned long long)
l->block_ref_to->logical_bytenr,
l->block_ref_to->dev_state->name,
- (unsigned long long)l->block_ref_to->dev_bytenr,
+ l->block_ref_to->dev_bytenr,
l->block_ref_to->mirror_num,
- (unsigned long long)l->block_ref_to->generation,
- (unsigned long long)l->parent_generation);
+ l->block_ref_to->generation,
+ l->parent_generation);
ret = -1;
} else if (l->block_ref_to->flush_gen >
l->block_ref_to->dev_state->last_flush_gen) {
@@ -2650,13 +2578,10 @@
" (block flush_gen=%llu,"
" dev->flush_gen=%llu)!\n",
btrfsic_get_block_type(state, l->block_ref_to),
- (unsigned long long)
l->block_ref_to->logical_bytenr,
l->block_ref_to->dev_state->name,
- (unsigned long long)l->block_ref_to->dev_bytenr,
- l->block_ref_to->mirror_num,
- (unsigned long long)block->flush_gen,
- (unsigned long long)
+ l->block_ref_to->dev_bytenr,
+ l->block_ref_to->mirror_num, block->flush_gen,
l->block_ref_to->dev_state->last_flush_gen);
ret = -1;
} else if (-1 == btrfsic_check_all_ref_blocks(state,
@@ -2701,16 +2626,12 @@
" is ref %u* from %c @%llu (%s/%llu/%d)\n",
recursion_level,
btrfsic_get_block_type(state, block),
- (unsigned long long)block->logical_bytenr,
- block->dev_state->name,
- (unsigned long long)block->dev_bytenr,
- block->mirror_num,
+ block->logical_bytenr, block->dev_state->name,
+ block->dev_bytenr, block->mirror_num,
l->ref_cnt,
btrfsic_get_block_type(state, l->block_ref_from),
- (unsigned long long)
l->block_ref_from->logical_bytenr,
l->block_ref_from->dev_state->name,
- (unsigned long long)
l->block_ref_from->dev_bytenr,
l->block_ref_from->mirror_num);
if (l->block_ref_from->is_superblock &&
@@ -2737,14 +2658,12 @@
" to %c @%llu (%s/%llu/%d).\n",
l->ref_cnt,
btrfsic_get_block_type(state, l->block_ref_from),
- (unsigned long long)l->block_ref_from->logical_bytenr,
+ l->block_ref_from->logical_bytenr,
l->block_ref_from->dev_state->name,
- (unsigned long long)l->block_ref_from->dev_bytenr,
- l->block_ref_from->mirror_num,
+ l->block_ref_from->dev_bytenr, l->block_ref_from->mirror_num,
btrfsic_get_block_type(state, l->block_ref_to),
- (unsigned long long)l->block_ref_to->logical_bytenr,
- l->block_ref_to->dev_state->name,
- (unsigned long long)l->block_ref_to->dev_bytenr,
+ l->block_ref_to->logical_bytenr,
+ l->block_ref_to->dev_state->name, l->block_ref_to->dev_bytenr,
l->block_ref_to->mirror_num);
}
@@ -2756,14 +2675,12 @@
" to %c @%llu (%s/%llu/%d).\n",
l->ref_cnt,
btrfsic_get_block_type(state, l->block_ref_from),
- (unsigned long long)l->block_ref_from->logical_bytenr,
+ l->block_ref_from->logical_bytenr,
l->block_ref_from->dev_state->name,
- (unsigned long long)l->block_ref_from->dev_bytenr,
- l->block_ref_from->mirror_num,
+ l->block_ref_from->dev_bytenr, l->block_ref_from->mirror_num,
btrfsic_get_block_type(state, l->block_ref_to),
- (unsigned long long)l->block_ref_to->logical_bytenr,
- l->block_ref_to->dev_state->name,
- (unsigned long long)l->block_ref_to->dev_bytenr,
+ l->block_ref_to->logical_bytenr,
+ l->block_ref_to->dev_state->name, l->block_ref_to->dev_bytenr,
l->block_ref_to->mirror_num);
}
@@ -2807,10 +2724,8 @@
*/
indent_add = sprintf(buf, "%c-%llu(%s/%llu/%d)",
btrfsic_get_block_type(state, block),
- (unsigned long long)block->logical_bytenr,
- block->dev_state->name,
- (unsigned long long)block->dev_bytenr,
- block->mirror_num);
+ block->logical_bytenr, block->dev_state->name,
+ block->dev_bytenr, block->mirror_num);
if (indent_level + indent_add > BTRFSIC_TREE_DUMP_MAX_INDENT_LEVEL) {
printk("[...]\n");
return;
@@ -2943,10 +2858,8 @@
"New %s%c-block @%llu (%s/%llu/%d)\n",
additional_string,
btrfsic_get_block_type(state, block),
- (unsigned long long)block->logical_bytenr,
- dev_state->name,
- (unsigned long long)block->dev_bytenr,
- mirror_num);
+ block->logical_bytenr, dev_state->name,
+ block->dev_bytenr, mirror_num);
list_add(&block->all_blocks_node, &state->all_blocks_list);
btrfsic_block_hashtable_add(block, &state->block_hashtable);
if (NULL != was_created)
@@ -2980,7 +2893,7 @@
printk(KERN_INFO "btrfsic:"
" btrfsic_map_block(logical @%llu,"
" mirror %d) failed!\n",
- (unsigned long long)bytenr, mirror_num);
+ bytenr, mirror_num);
continue;
}
@@ -2997,8 +2910,7 @@
printk(KERN_INFO "btrfs: attempt to write M-block which contains logical bytenr that doesn't map to dev+physical bytenr of submit_bio,"
" buffer->log_bytenr=%llu, submit_bio(bdev=%s,"
" phys_bytenr=%llu)!\n",
- (unsigned long long)bytenr, dev_state->name,
- (unsigned long long)dev_bytenr);
+ bytenr, dev_state->name, dev_bytenr);
for (mirror_num = 1; mirror_num <= num_copies; mirror_num++) {
ret = btrfsic_map_block(state, bytenr,
state->metablock_size,
@@ -3008,10 +2920,8 @@
printk(KERN_INFO "Read logical bytenr @%llu maps to"
" (%s/%llu/%d)\n",
- (unsigned long long)bytenr,
- block_ctx.dev->name,
- (unsigned long long)block_ctx.dev_bytenr,
- mirror_num);
+ bytenr, block_ctx.dev->name,
+ block_ctx.dev_bytenr, mirror_num);
}
WARN_ON(1);
}
@@ -3048,12 +2958,10 @@
if (dev_state->state->print_mask &
BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH)
printk(KERN_INFO
- "submit_bh(rw=0x%x, blocknr=%lu (bytenr %llu),"
- " size=%lu, data=%p, bdev=%p)\n",
- rw, (unsigned long)bh->b_blocknr,
- (unsigned long long)dev_bytenr,
- (unsigned long)bh->b_size, bh->b_data,
- bh->b_bdev);
+ "submit_bh(rw=0x%x, blocknr=%llu (bytenr %llu),"
+ " size=%zu, data=%p, bdev=%p)\n",
+ rw, (unsigned long long)bh->b_blocknr,
+ dev_bytenr, bh->b_size, bh->b_data, bh->b_bdev);
btrfsic_process_written_block(dev_state, dev_bytenr,
&bh->b_data, 1, NULL,
NULL, bh, rw);
@@ -3118,9 +3026,9 @@
BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH)
printk(KERN_INFO
"submit_bio(rw=0x%x, bi_vcnt=%u,"
- " bi_sector=%lu (bytenr %llu), bi_bdev=%p)\n",
- rw, bio->bi_vcnt, (unsigned long)bio->bi_sector,
- (unsigned long long)dev_bytenr,
+ " bi_sector=%llu (bytenr %llu), bi_bdev=%p)\n",
+ rw, bio->bi_vcnt,
+ (unsigned long long)bio->bi_sector, dev_bytenr,
bio->bi_bdev);
mapped_datav = kmalloc(sizeof(*mapped_datav) * bio->bi_vcnt,
@@ -3213,19 +3121,19 @@
if (root->nodesize & ((u64)PAGE_CACHE_SIZE - 1)) {
printk(KERN_INFO
"btrfsic: cannot handle nodesize %d not being a multiple of PAGE_CACHE_SIZE %ld!\n",
- root->nodesize, (unsigned long)PAGE_CACHE_SIZE);
+ root->nodesize, PAGE_CACHE_SIZE);
return -1;
}
if (root->leafsize & ((u64)PAGE_CACHE_SIZE - 1)) {
printk(KERN_INFO
"btrfsic: cannot handle leafsize %d not being a multiple of PAGE_CACHE_SIZE %ld!\n",
- root->leafsize, (unsigned long)PAGE_CACHE_SIZE);
+ root->leafsize, PAGE_CACHE_SIZE);
return -1;
}
if (root->sectorsize & ((u64)PAGE_CACHE_SIZE - 1)) {
printk(KERN_INFO
"btrfsic: cannot handle sectorsize %d not being a multiple of PAGE_CACHE_SIZE %ld!\n",
- root->sectorsize, (unsigned long)PAGE_CACHE_SIZE);
+ root->sectorsize, PAGE_CACHE_SIZE);
return -1;
}
state = kzalloc(sizeof(*state), GFP_NOFS);
@@ -3369,10 +3277,8 @@
" @%llu (%s/%llu/%d) on umount which is"
" not yet iodone!\n",
btrfsic_get_block_type(state, b_all),
- (unsigned long long)b_all->logical_bytenr,
- b_all->dev_state->name,
- (unsigned long long)b_all->dev_bytenr,
- b_all->mirror_num);
+ b_all->logical_bytenr, b_all->dev_state->name,
+ b_all->dev_bytenr, b_all->mirror_num);
}
mutex_unlock(&btrfsic_mutex);
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index b189bd1..6aad98c 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -132,9 +132,8 @@
printk(KERN_INFO "btrfs csum failed ino %llu "
"extent %llu csum %u "
"wanted %u mirror %d\n",
- (unsigned long long)btrfs_ino(inode),
- (unsigned long long)disk_start,
- csum, *cb_sum, cb->mirror_num);
+ btrfs_ino(inode), disk_start, csum, *cb_sum,
+ cb->mirror_num);
ret = -EIO;
goto fail;
}
@@ -639,7 +638,11 @@
faili = nr_pages - 1;
cb->nr_pages = nr_pages;
- add_ra_bio_pages(inode, em_start + em_len, cb);
+ /* In the parent-locked case, we only locked the range we are
+ * interested in. In all other cases, we can opportunistically
+ * cache decompressed data that goes beyond the requested range. */
+ if (!(bio_flags & EXTENT_BIO_PARENT_LOCKED))
+ add_ra_bio_pages(inode, em_start + em_len, cb);
/* include any pages we added in add_ra-bio_pages */
uncompressed_len = bio->bi_vcnt * PAGE_CACHE_SIZE;
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index ed50460..6434672 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -274,8 +274,7 @@
else
btrfs_set_header_owner(cow, new_root_objectid);
- write_extent_buffer(cow, root->fs_info->fsid,
- (unsigned long)btrfs_header_fsid(cow),
+ write_extent_buffer(cow, root->fs_info->fsid, btrfs_header_fsid(cow),
BTRFS_FSID_SIZE);
WARN_ON(btrfs_header_generation(buf) > trans->transid);
@@ -484,8 +483,27 @@
struct rb_node **new;
struct rb_node *parent = NULL;
struct tree_mod_elem *cur;
+ int ret = 0;
- BUG_ON(!tm || !tm->seq);
+ BUG_ON(!tm);
+
+ tree_mod_log_write_lock(fs_info);
+ if (list_empty(&fs_info->tree_mod_seq_list)) {
+ tree_mod_log_write_unlock(fs_info);
+ /*
+ * Ok we no longer care about logging modifications, free up tm
+ * and return 0. Any callers shouldn't be using tm after
+ * calling tree_mod_log_insert, but if they do we can just
+ * change this to return a special error code to let the callers
+ * do their own thing.
+ */
+ kfree(tm);
+ return 0;
+ }
+
+ spin_lock(&fs_info->tree_mod_seq_lock);
+ tm->seq = btrfs_inc_tree_mod_seq_minor(fs_info);
+ spin_unlock(&fs_info->tree_mod_seq_lock);
tm_root = &fs_info->tree_mod_log;
new = &tm_root->rb_node;
@@ -501,14 +519,17 @@
else if (cur->seq > tm->seq)
new = &((*new)->rb_right);
else {
+ ret = -EEXIST;
kfree(tm);
- return -EEXIST;
+ goto out;
}
}
rb_link_node(&tm->node, parent, new);
rb_insert_color(&tm->node, tm_root);
- return 0;
+out:
+ tree_mod_log_write_unlock(fs_info);
+ return ret;
}
/*
@@ -524,57 +545,19 @@
return 1;
if (eb && btrfs_header_level(eb) == 0)
return 1;
-
- tree_mod_log_write_lock(fs_info);
- if (list_empty(&fs_info->tree_mod_seq_list)) {
- /*
- * someone emptied the list while we were waiting for the lock.
- * we must not add to the list when no blocker exists.
- */
- tree_mod_log_write_unlock(fs_info);
- return 1;
- }
-
return 0;
}
-/*
- * This allocates memory and gets a tree modification sequence number.
- *
- * Returns <0 on error.
- * Returns >0 (the added sequence number) on success.
- */
-static inline int tree_mod_alloc(struct btrfs_fs_info *fs_info, gfp_t flags,
- struct tree_mod_elem **tm_ret)
-{
- struct tree_mod_elem *tm;
-
- /*
- * once we switch from spin locks to something different, we should
- * honor the flags parameter here.
- */
- tm = *tm_ret = kzalloc(sizeof(*tm), GFP_ATOMIC);
- if (!tm)
- return -ENOMEM;
-
- spin_lock(&fs_info->tree_mod_seq_lock);
- tm->seq = btrfs_inc_tree_mod_seq_minor(fs_info);
- spin_unlock(&fs_info->tree_mod_seq_lock);
-
- return tm->seq;
-}
-
static inline int
__tree_mod_log_insert_key(struct btrfs_fs_info *fs_info,
struct extent_buffer *eb, int slot,
enum mod_log_op op, gfp_t flags)
{
- int ret;
struct tree_mod_elem *tm;
- ret = tree_mod_alloc(fs_info, flags, &tm);
- if (ret < 0)
- return ret;
+ tm = kzalloc(sizeof(*tm), flags);
+ if (!tm)
+ return -ENOMEM;
tm->index = eb->start >> PAGE_CACHE_SHIFT;
if (op != MOD_LOG_KEY_ADD) {
@@ -589,34 +572,14 @@
}
static noinline int
-tree_mod_log_insert_key_mask(struct btrfs_fs_info *fs_info,
- struct extent_buffer *eb, int slot,
- enum mod_log_op op, gfp_t flags)
+tree_mod_log_insert_key(struct btrfs_fs_info *fs_info,
+ struct extent_buffer *eb, int slot,
+ enum mod_log_op op, gfp_t flags)
{
- int ret;
-
if (tree_mod_dont_log(fs_info, eb))
return 0;
- ret = __tree_mod_log_insert_key(fs_info, eb, slot, op, flags);
-
- tree_mod_log_write_unlock(fs_info);
- return ret;
-}
-
-static noinline int
-tree_mod_log_insert_key(struct btrfs_fs_info *fs_info, struct extent_buffer *eb,
- int slot, enum mod_log_op op)
-{
- return tree_mod_log_insert_key_mask(fs_info, eb, slot, op, GFP_NOFS);
-}
-
-static noinline int
-tree_mod_log_insert_key_locked(struct btrfs_fs_info *fs_info,
- struct extent_buffer *eb, int slot,
- enum mod_log_op op)
-{
- return __tree_mod_log_insert_key(fs_info, eb, slot, op, GFP_NOFS);
+ return __tree_mod_log_insert_key(fs_info, eb, slot, op, flags);
}
static noinline int
@@ -637,14 +600,14 @@
* buffer, i.e. dst_slot < src_slot.
*/
for (i = 0; i + dst_slot < src_slot && i < nr_items; i++) {
- ret = tree_mod_log_insert_key_locked(fs_info, eb, i + dst_slot,
- MOD_LOG_KEY_REMOVE_WHILE_MOVING);
+ ret = __tree_mod_log_insert_key(fs_info, eb, i + dst_slot,
+ MOD_LOG_KEY_REMOVE_WHILE_MOVING, GFP_NOFS);
BUG_ON(ret < 0);
}
- ret = tree_mod_alloc(fs_info, flags, &tm);
- if (ret < 0)
- goto out;
+ tm = kzalloc(sizeof(*tm), flags);
+ if (!tm)
+ return -ENOMEM;
tm->index = eb->start >> PAGE_CACHE_SHIFT;
tm->slot = src_slot;
@@ -652,10 +615,7 @@
tm->move.nr_items = nr_items;
tm->op = MOD_LOG_MOVE_KEYS;
- ret = __tree_mod_log_insert(fs_info, tm);
-out:
- tree_mod_log_write_unlock(fs_info);
- return ret;
+ return __tree_mod_log_insert(fs_info, tm);
}
static inline void
@@ -670,8 +630,8 @@
nritems = btrfs_header_nritems(eb);
for (i = nritems - 1; i >= 0; i--) {
- ret = tree_mod_log_insert_key_locked(fs_info, eb, i,
- MOD_LOG_KEY_REMOVE_WHILE_FREEING);
+ ret = __tree_mod_log_insert_key(fs_info, eb, i,
+ MOD_LOG_KEY_REMOVE_WHILE_FREEING, GFP_NOFS);
BUG_ON(ret < 0);
}
}
@@ -683,7 +643,6 @@
int log_removal)
{
struct tree_mod_elem *tm;
- int ret;
if (tree_mod_dont_log(fs_info, NULL))
return 0;
@@ -691,9 +650,9 @@
if (log_removal)
__tree_mod_log_free_eb(fs_info, old_root);
- ret = tree_mod_alloc(fs_info, flags, &tm);
- if (ret < 0)
- goto out;
+ tm = kzalloc(sizeof(*tm), flags);
+ if (!tm)
+ return -ENOMEM;
tm->index = new_root->start >> PAGE_CACHE_SHIFT;
tm->old_root.logical = old_root->start;
@@ -701,10 +660,7 @@
tm->generation = btrfs_header_generation(old_root);
tm->op = MOD_LOG_ROOT_REPLACE;
- ret = __tree_mod_log_insert(fs_info, tm);
-out:
- tree_mod_log_write_unlock(fs_info);
- return ret;
+ return __tree_mod_log_insert(fs_info, tm);
}
static struct tree_mod_elem *
@@ -784,23 +740,20 @@
if (tree_mod_dont_log(fs_info, NULL))
return;
- if (btrfs_header_level(dst) == 0 && btrfs_header_level(src) == 0) {
- tree_mod_log_write_unlock(fs_info);
+ if (btrfs_header_level(dst) == 0 && btrfs_header_level(src) == 0)
return;
- }
for (i = 0; i < nr_items; i++) {
- ret = tree_mod_log_insert_key_locked(fs_info, src,
+ ret = __tree_mod_log_insert_key(fs_info, src,
i + src_offset,
- MOD_LOG_KEY_REMOVE);
+ MOD_LOG_KEY_REMOVE, GFP_NOFS);
BUG_ON(ret < 0);
- ret = tree_mod_log_insert_key_locked(fs_info, dst,
+ ret = __tree_mod_log_insert_key(fs_info, dst,
i + dst_offset,
- MOD_LOG_KEY_ADD);
+ MOD_LOG_KEY_ADD,
+ GFP_NOFS);
BUG_ON(ret < 0);
}
-
- tree_mod_log_write_unlock(fs_info);
}
static inline void
@@ -819,9 +772,9 @@
{
int ret;
- ret = tree_mod_log_insert_key_mask(fs_info, eb, slot,
- MOD_LOG_KEY_REPLACE,
- atomic ? GFP_ATOMIC : GFP_NOFS);
+ ret = __tree_mod_log_insert_key(fs_info, eb, slot,
+ MOD_LOG_KEY_REPLACE,
+ atomic ? GFP_ATOMIC : GFP_NOFS);
BUG_ON(ret < 0);
}
@@ -830,10 +783,7 @@
{
if (tree_mod_dont_log(fs_info, eb))
return;
-
__tree_mod_log_free_eb(fs_info, eb);
-
- tree_mod_log_write_unlock(fs_info);
}
static noinline void
@@ -1046,8 +996,7 @@
else
btrfs_set_header_owner(cow, root->root_key.objectid);
- write_extent_buffer(cow, root->fs_info->fsid,
- (unsigned long)btrfs_header_fsid(cow),
+ write_extent_buffer(cow, root->fs_info->fsid, btrfs_header_fsid(cow),
BTRFS_FSID_SIZE);
ret = update_ref_for_cow(trans, root, buf, cow, &last_ref);
@@ -1083,7 +1032,7 @@
WARN_ON(trans->transid != btrfs_header_generation(parent));
tree_mod_log_insert_key(root->fs_info, parent, parent_slot,
- MOD_LOG_KEY_REPLACE);
+ MOD_LOG_KEY_REPLACE, GFP_NOFS);
btrfs_set_node_blockptr(parent, parent_slot,
cow->start);
btrfs_set_node_ptr_generation(parent, parent_slot,
@@ -1116,7 +1065,7 @@
int looped = 0;
if (!time_seq)
- return 0;
+ return NULL;
/*
* the very last operation that's logged for a root is the replacement
@@ -1127,7 +1076,7 @@
tm = tree_mod_log_search_oldest(fs_info, root_logical,
time_seq);
if (!looped && !tm)
- return 0;
+ return NULL;
/*
* if there are no tree operation for the oldest root, we simply
* return it. this should only happen if that (old) root is at
@@ -1240,8 +1189,8 @@
* is freed (its refcount is decremented).
*/
static struct extent_buffer *
-tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb,
- u64 time_seq)
+tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
+ struct extent_buffer *eb, u64 time_seq)
{
struct extent_buffer *eb_rewin;
struct tree_mod_elem *tm;
@@ -1256,11 +1205,18 @@
if (!tm)
return eb;
+ btrfs_set_path_blocking(path);
+ btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+
if (tm->op == MOD_LOG_KEY_REMOVE_WHILE_FREEING) {
BUG_ON(tm->slot != 0);
eb_rewin = alloc_dummy_extent_buffer(eb->start,
fs_info->tree_root->nodesize);
- BUG_ON(!eb_rewin);
+ if (!eb_rewin) {
+ btrfs_tree_read_unlock_blocking(eb);
+ free_extent_buffer(eb);
+ return NULL;
+ }
btrfs_set_header_bytenr(eb_rewin, eb->start);
btrfs_set_header_backref_rev(eb_rewin,
btrfs_header_backref_rev(eb));
@@ -1268,10 +1224,15 @@
btrfs_set_header_level(eb_rewin, btrfs_header_level(eb));
} else {
eb_rewin = btrfs_clone_extent_buffer(eb);
- BUG_ON(!eb_rewin);
+ if (!eb_rewin) {
+ btrfs_tree_read_unlock_blocking(eb);
+ free_extent_buffer(eb);
+ return NULL;
+ }
}
- btrfs_tree_read_unlock(eb);
+ btrfs_clear_path_blocking(path, NULL, BTRFS_READ_LOCK);
+ btrfs_tree_read_unlock_blocking(eb);
free_extent_buffer(eb);
extent_buffer_get(eb_rewin);
@@ -1335,8 +1296,9 @@
free_extent_buffer(eb_root);
eb = alloc_dummy_extent_buffer(logical, root->nodesize);
} else {
+ btrfs_set_lock_blocking_rw(eb_root, BTRFS_READ_LOCK);
eb = btrfs_clone_extent_buffer(eb_root);
- btrfs_tree_read_unlock(eb_root);
+ btrfs_tree_read_unlock_blocking(eb_root);
free_extent_buffer(eb_root);
}
@@ -1419,14 +1381,12 @@
if (trans->transaction != root->fs_info->running_transaction)
WARN(1, KERN_CRIT "trans %llu running %llu\n",
- (unsigned long long)trans->transid,
- (unsigned long long)
+ trans->transid,
root->fs_info->running_transaction->transid);
if (trans->transid != root->fs_info->generation)
WARN(1, KERN_CRIT "trans %llu running %llu\n",
- (unsigned long long)trans->transid,
- (unsigned long long)root->fs_info->generation);
+ trans->transid, root->fs_info->generation);
if (!should_cow_block(trans, root, buf)) {
*cow_ret = buf;
@@ -2466,6 +2426,40 @@
return ret;
}
+static void key_search_validate(struct extent_buffer *b,
+ struct btrfs_key *key,
+ int level)
+{
+#ifdef CONFIG_BTRFS_ASSERT
+ struct btrfs_disk_key disk_key;
+
+ btrfs_cpu_key_to_disk(&disk_key, key);
+
+ if (level == 0)
+ ASSERT(!memcmp_extent_buffer(b, &disk_key,
+ offsetof(struct btrfs_leaf, items[0].key),
+ sizeof(disk_key)));
+ else
+ ASSERT(!memcmp_extent_buffer(b, &disk_key,
+ offsetof(struct btrfs_node, ptrs[0].key),
+ sizeof(disk_key)));
+#endif
+}
+
+static int key_search(struct extent_buffer *b, struct btrfs_key *key,
+ int level, int *prev_cmp, int *slot)
+{
+ if (*prev_cmp != 0) {
+ *prev_cmp = bin_search(b, key, level, slot);
+ return *prev_cmp;
+ }
+
+ key_search_validate(b, key, level);
+ *slot = 0;
+
+ return 0;
+}
+
/*
* look for key in the tree. path is filled in with nodes along the way
* if key is found, we return zero and you can find the item in the leaf
@@ -2494,6 +2488,7 @@
int write_lock_level = 0;
u8 lowest_level = 0;
int min_write_lock_level;
+ int prev_cmp;
lowest_level = p->lowest_level;
WARN_ON(lowest_level && ins_len > 0);
@@ -2524,6 +2519,7 @@
min_write_lock_level = write_lock_level;
again:
+ prev_cmp = -1;
/*
* we try very hard to do read locks on the root
*/
@@ -2624,7 +2620,7 @@
if (!cow)
btrfs_unlock_up_safe(p, level + 1);
- ret = bin_search(b, key, level, &slot);
+ ret = key_search(b, key, level, &prev_cmp, &slot);
if (level != 0) {
int dec = 0;
@@ -2759,6 +2755,7 @@
int level;
int lowest_unlock = 1;
u8 lowest_level = 0;
+ int prev_cmp;
lowest_level = p->lowest_level;
WARN_ON(p->nodes[0] != NULL);
@@ -2769,6 +2766,7 @@
}
again:
+ prev_cmp = -1;
b = get_old_root(root, time_seq);
level = btrfs_header_level(b);
p->locks[level] = BTRFS_READ_LOCK;
@@ -2786,7 +2784,7 @@
*/
btrfs_unlock_up_safe(p, level + 1);
- ret = bin_search(b, key, level, &slot);
+ ret = key_search(b, key, level, &prev_cmp, &slot);
if (level != 0) {
int dec = 0;
@@ -2820,7 +2818,11 @@
btrfs_clear_path_blocking(p, b,
BTRFS_READ_LOCK);
}
- b = tree_mod_log_rewind(root->fs_info, b, time_seq);
+ b = tree_mod_log_rewind(root->fs_info, p, b, time_seq);
+ if (!b) {
+ ret = -ENOMEM;
+ goto done;
+ }
p->locks[level] = BTRFS_READ_LOCK;
p->nodes[level] = b;
} else {
@@ -3143,13 +3145,11 @@
btrfs_set_header_backref_rev(c, BTRFS_MIXED_BACKREF_REV);
btrfs_set_header_owner(c, root->root_key.objectid);
- write_extent_buffer(c, root->fs_info->fsid,
- (unsigned long)btrfs_header_fsid(c),
+ write_extent_buffer(c, root->fs_info->fsid, btrfs_header_fsid(c),
BTRFS_FSID_SIZE);
write_extent_buffer(c, root->fs_info->chunk_tree_uuid,
- (unsigned long)btrfs_header_chunk_tree_uuid(c),
- BTRFS_UUID_SIZE);
+ btrfs_header_chunk_tree_uuid(c), BTRFS_UUID_SIZE);
btrfs_set_node_key(c, &lower_key, 0);
btrfs_set_node_blockptr(c, 0, lower->start);
@@ -3208,7 +3208,7 @@
}
if (level) {
ret = tree_mod_log_insert_key(root->fs_info, lower, slot,
- MOD_LOG_KEY_ADD);
+ MOD_LOG_KEY_ADD, GFP_NOFS);
BUG_ON(ret < 0);
}
btrfs_set_node_key(lower, key, slot);
@@ -3284,10 +3284,9 @@
btrfs_set_header_backref_rev(split, BTRFS_MIXED_BACKREF_REV);
btrfs_set_header_owner(split, root->root_key.objectid);
write_extent_buffer(split, root->fs_info->fsid,
- (unsigned long)btrfs_header_fsid(split),
- BTRFS_FSID_SIZE);
+ btrfs_header_fsid(split), BTRFS_FSID_SIZE);
write_extent_buffer(split, root->fs_info->chunk_tree_uuid,
- (unsigned long)btrfs_header_chunk_tree_uuid(split),
+ btrfs_header_chunk_tree_uuid(split),
BTRFS_UUID_SIZE);
tree_mod_log_eb_copy(root->fs_info, split, c, 0, mid, c_nritems - mid);
@@ -4040,11 +4039,10 @@
btrfs_set_header_owner(right, root->root_key.objectid);
btrfs_set_header_level(right, 0);
write_extent_buffer(right, root->fs_info->fsid,
- (unsigned long)btrfs_header_fsid(right),
- BTRFS_FSID_SIZE);
+ btrfs_header_fsid(right), BTRFS_FSID_SIZE);
write_extent_buffer(right, root->fs_info->chunk_tree_uuid,
- (unsigned long)btrfs_header_chunk_tree_uuid(right),
+ btrfs_header_chunk_tree_uuid(right),
BTRFS_UUID_SIZE);
if (split == 0) {
@@ -4642,7 +4640,7 @@
(nritems - slot - 1));
} else if (level) {
ret = tree_mod_log_insert_key(root->fs_info, parent, slot,
- MOD_LOG_KEY_REMOVE);
+ MOD_LOG_KEY_REMOVE, GFP_NOFS);
BUG_ON(ret < 0);
}
@@ -4814,7 +4812,7 @@
* This may release the path, and so you may lose any locks held at the
* time you call it.
*/
-int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path)
+static int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path)
{
struct btrfs_key key;
struct btrfs_disk_key found_key;
@@ -5329,19 +5327,20 @@
goto out;
advance_right = ADVANCE;
} else {
+ enum btrfs_compare_tree_result cmp;
+
WARN_ON(!extent_buffer_uptodate(left_path->nodes[0]));
ret = tree_compare_item(left_root, left_path,
right_path, tmp_buf);
- if (ret) {
- WARN_ON(!extent_buffer_uptodate(left_path->nodes[0]));
- ret = changed_cb(left_root, right_root,
- left_path, right_path,
- &left_key,
- BTRFS_COMPARE_TREE_CHANGED,
- ctx);
- if (ret < 0)
- goto out;
- }
+ if (ret)
+ cmp = BTRFS_COMPARE_TREE_CHANGED;
+ else
+ cmp = BTRFS_COMPARE_TREE_SAME;
+ ret = changed_cb(left_root, right_root,
+ left_path, right_path,
+ &left_key, cmp, ctx);
+ if (ret < 0)
+ goto out;
advance_left = ADVANCE;
advance_right = ADVANCE;
}
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index e795bf1..3c1da6f 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -23,6 +23,7 @@
#include <linux/highmem.h>
#include <linux/fs.h>
#include <linux/rwsem.h>
+#include <linux/semaphore.h>
#include <linux/completion.h>
#include <linux/backing-dev.h>
#include <linux/wait.h>
@@ -91,6 +92,9 @@
/* holds quota configuration and tracking */
#define BTRFS_QUOTA_TREE_OBJECTID 8ULL
+/* for storing items that use the BTRFS_UUID_KEY* types */
+#define BTRFS_UUID_TREE_OBJECTID 9ULL
+
/* for storing balance parameters in the root tree */
#define BTRFS_BALANCE_OBJECTID -4ULL
@@ -142,7 +146,7 @@
#define BTRFS_EMPTY_SUBVOL_DIR_OBJECTID 2
-#define BTRFS_DEV_REPLACE_DEVID 0
+#define BTRFS_DEV_REPLACE_DEVID 0ULL
/*
* the max metadata block size. This limit is somewhat artificial,
@@ -478,9 +482,10 @@
char label[BTRFS_LABEL_SIZE];
__le64 cache_generation;
+ __le64 uuid_tree_generation;
/* future expansion */
- __le64 reserved[31];
+ __le64 reserved[30];
u8 sys_chunk_array[BTRFS_SYSTEM_CHUNK_ARRAY_SIZE];
struct btrfs_root_backup super_roots[BTRFS_NUM_BACKUP_ROOTS];
} __attribute__ ((__packed__));
@@ -1188,6 +1193,7 @@
BTRFS_CACHE_STARTED = 1,
BTRFS_CACHE_FAST = 2,
BTRFS_CACHE_FINISHED = 3,
+ BTRFS_CACHE_ERROR = 4,
};
enum btrfs_disk_cache_state {
@@ -1302,6 +1308,7 @@
struct btrfs_root *fs_root;
struct btrfs_root *csum_root;
struct btrfs_root *quota_root;
+ struct btrfs_root *uuid_root;
/* the log root tree is a directory of all the other log roots */
struct btrfs_root *log_root_tree;
@@ -1350,6 +1357,7 @@
u64 last_trans_log_full_commit;
unsigned long mount_opt;
unsigned long compress_type:4;
+ int commit_interval;
/*
* It is a suggestive number, the read side is safe even it gets a
* wrong number because we will write out the data into a regular
@@ -1411,6 +1419,13 @@
* before jumping into the main commit.
*/
struct mutex ordered_operations_mutex;
+
+ /*
+ * Same as ordered_operations_mutex except this is for ordered extents
+ * and not the operations.
+ */
+ struct mutex ordered_extent_flush_mutex;
+
struct rw_semaphore extent_commit_sem;
struct rw_semaphore cleanup_work_sem;
@@ -1641,6 +1656,9 @@
struct btrfs_dev_replace dev_replace;
atomic_t mutually_exclusive_operation_running;
+
+ struct semaphore uuid_tree_rescan_sem;
+ unsigned int update_uuid_tree_gen:1;
};
/*
@@ -1934,6 +1952,19 @@
#define BTRFS_DEV_REPLACE_KEY 250
/*
+ * Stores items that allow to quickly map UUIDs to something else.
+ * These items are part of the filesystem UUID tree.
+ * The key is built like this:
+ * (UUID_upper_64_bits, BTRFS_UUID_KEY*, UUID_lower_64_bits).
+ */
+#if BTRFS_UUID_SIZE != 16
+#error "UUID items require BTRFS_UUID_SIZE == 16!"
+#endif
+#define BTRFS_UUID_KEY_SUBVOL 251 /* for UUIDs assigned to subvols */
+#define BTRFS_UUID_KEY_RECEIVED_SUBVOL 252 /* for UUIDs assigned to
+ * received subvols */
+
+/*
* string items are for debugging. They just store a short string of
* data in the FS
*/
@@ -1967,6 +1998,9 @@
#define BTRFS_MOUNT_CHECK_INTEGRITY (1 << 20)
#define BTRFS_MOUNT_CHECK_INTEGRITY_INCLUDING_EXTENT_DATA (1 << 21)
#define BTRFS_MOUNT_PANIC_ON_FATAL_ERROR (1 << 22)
+#define BTRFS_MOUNT_RESCAN_UUID_TREE (1 << 23)
+
+#define BTRFS_DEFAULT_COMMIT_INTERVAL (30)
#define btrfs_clear_opt(o, opt) ((o) &= ~BTRFS_MOUNT_##opt)
#define btrfs_set_opt(o, opt) ((o) |= BTRFS_MOUNT_##opt)
@@ -2130,14 +2164,14 @@
BTRFS_SETGET_STACK_FUNCS(stack_device_generation, struct btrfs_dev_item,
generation, 64);
-static inline char *btrfs_device_uuid(struct btrfs_dev_item *d)
+static inline unsigned long btrfs_device_uuid(struct btrfs_dev_item *d)
{
- return (char *)d + offsetof(struct btrfs_dev_item, uuid);
+ return (unsigned long)d + offsetof(struct btrfs_dev_item, uuid);
}
-static inline char *btrfs_device_fsid(struct btrfs_dev_item *d)
+static inline unsigned long btrfs_device_fsid(struct btrfs_dev_item *d)
{
- return (char *)d + offsetof(struct btrfs_dev_item, fsid);
+ return (unsigned long)d + offsetof(struct btrfs_dev_item, fsid);
}
BTRFS_SETGET_FUNCS(chunk_length, struct btrfs_chunk, length, 64);
@@ -2240,6 +2274,23 @@
BTRFS_SETGET_FUNCS(inode_mode, struct btrfs_inode_item, mode, 32);
BTRFS_SETGET_FUNCS(inode_rdev, struct btrfs_inode_item, rdev, 64);
BTRFS_SETGET_FUNCS(inode_flags, struct btrfs_inode_item, flags, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_inode_generation, struct btrfs_inode_item,
+ generation, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_inode_sequence, struct btrfs_inode_item,
+ sequence, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_inode_transid, struct btrfs_inode_item,
+ transid, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_inode_size, struct btrfs_inode_item, size, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_inode_nbytes, struct btrfs_inode_item,
+ nbytes, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_inode_block_group, struct btrfs_inode_item,
+ block_group, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_inode_nlink, struct btrfs_inode_item, nlink, 32);
+BTRFS_SETGET_STACK_FUNCS(stack_inode_uid, struct btrfs_inode_item, uid, 32);
+BTRFS_SETGET_STACK_FUNCS(stack_inode_gid, struct btrfs_inode_item, gid, 32);
+BTRFS_SETGET_STACK_FUNCS(stack_inode_mode, struct btrfs_inode_item, mode, 32);
+BTRFS_SETGET_STACK_FUNCS(stack_inode_rdev, struct btrfs_inode_item, rdev, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_inode_flags, struct btrfs_inode_item, flags, 64);
static inline struct btrfs_timespec *
btrfs_inode_atime(struct btrfs_inode_item *inode_item)
@@ -2267,6 +2318,8 @@
BTRFS_SETGET_FUNCS(timespec_sec, struct btrfs_timespec, sec, 64);
BTRFS_SETGET_FUNCS(timespec_nsec, struct btrfs_timespec, nsec, 32);
+BTRFS_SETGET_STACK_FUNCS(stack_timespec_sec, struct btrfs_timespec, sec, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_timespec_nsec, struct btrfs_timespec, nsec, 32);
/* struct btrfs_dev_extent */
BTRFS_SETGET_FUNCS(dev_extent_chunk_tree, struct btrfs_dev_extent,
@@ -2277,10 +2330,10 @@
chunk_offset, 64);
BTRFS_SETGET_FUNCS(dev_extent_length, struct btrfs_dev_extent, length, 64);
-static inline u8 *btrfs_dev_extent_chunk_tree_uuid(struct btrfs_dev_extent *dev)
+static inline unsigned long btrfs_dev_extent_chunk_tree_uuid(struct btrfs_dev_extent *dev)
{
unsigned long ptr = offsetof(struct btrfs_dev_extent, chunk_tree_uuid);
- return (u8 *)((unsigned long)dev + ptr);
+ return (unsigned long)dev + ptr;
}
BTRFS_SETGET_FUNCS(extent_refs, struct btrfs_extent_item, refs, 64);
@@ -2348,6 +2401,10 @@
/* struct btrfs_node */
BTRFS_SETGET_FUNCS(key_blockptr, struct btrfs_key_ptr, blockptr, 64);
BTRFS_SETGET_FUNCS(key_generation, struct btrfs_key_ptr, generation, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_key_blockptr, struct btrfs_key_ptr,
+ blockptr, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_key_generation, struct btrfs_key_ptr,
+ generation, 64);
static inline u64 btrfs_node_blockptr(struct extent_buffer *eb, int nr)
{
@@ -2404,6 +2461,8 @@
/* struct btrfs_item */
BTRFS_SETGET_FUNCS(item_offset, struct btrfs_item, offset, 32);
BTRFS_SETGET_FUNCS(item_size, struct btrfs_item, size, 32);
+BTRFS_SETGET_STACK_FUNCS(stack_item_offset, struct btrfs_item, offset, 32);
+BTRFS_SETGET_STACK_FUNCS(stack_item_size, struct btrfs_item, size, 32);
static inline unsigned long btrfs_item_nr_offset(int nr)
{
@@ -2466,6 +2525,13 @@
BTRFS_SETGET_FUNCS(dir_type, struct btrfs_dir_item, type, 8);
BTRFS_SETGET_FUNCS(dir_name_len, struct btrfs_dir_item, name_len, 16);
BTRFS_SETGET_FUNCS(dir_transid, struct btrfs_dir_item, transid, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_dir_type, struct btrfs_dir_item, type, 8);
+BTRFS_SETGET_STACK_FUNCS(stack_dir_data_len, struct btrfs_dir_item,
+ data_len, 16);
+BTRFS_SETGET_STACK_FUNCS(stack_dir_name_len, struct btrfs_dir_item,
+ name_len, 16);
+BTRFS_SETGET_STACK_FUNCS(stack_dir_transid, struct btrfs_dir_item,
+ transid, 64);
static inline void btrfs_dir_item_key(struct extent_buffer *eb,
struct btrfs_dir_item *item,
@@ -2568,6 +2634,12 @@
BTRFS_SETGET_HEADER_FUNCS(header_nritems, struct btrfs_header, nritems, 32);
BTRFS_SETGET_HEADER_FUNCS(header_flags, struct btrfs_header, flags, 64);
BTRFS_SETGET_HEADER_FUNCS(header_level, struct btrfs_header, level, 8);
+BTRFS_SETGET_STACK_FUNCS(stack_header_generation, struct btrfs_header,
+ generation, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_header_owner, struct btrfs_header, owner, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_header_nritems, struct btrfs_header,
+ nritems, 32);
+BTRFS_SETGET_STACK_FUNCS(stack_header_bytenr, struct btrfs_header, bytenr, 64);
static inline int btrfs_header_flag(struct extent_buffer *eb, u64 flag)
{
@@ -2603,16 +2675,14 @@
btrfs_set_header_flags(eb, flags);
}
-static inline u8 *btrfs_header_fsid(struct extent_buffer *eb)
+static inline unsigned long btrfs_header_fsid(struct extent_buffer *eb)
{
- unsigned long ptr = offsetof(struct btrfs_header, fsid);
- return (u8 *)ptr;
+ return offsetof(struct btrfs_header, fsid);
}
-static inline u8 *btrfs_header_chunk_tree_uuid(struct extent_buffer *eb)
+static inline unsigned long btrfs_header_chunk_tree_uuid(struct extent_buffer *eb)
{
- unsigned long ptr = offsetof(struct btrfs_header, chunk_tree_uuid);
- return (u8 *)ptr;
+ return offsetof(struct btrfs_header, chunk_tree_uuid);
}
static inline int btrfs_is_leaf(struct extent_buffer *eb)
@@ -2830,6 +2900,9 @@
csum_type, 16);
BTRFS_SETGET_STACK_FUNCS(super_cache_generation, struct btrfs_super_block,
cache_generation, 64);
+BTRFS_SETGET_STACK_FUNCS(super_magic, struct btrfs_super_block, magic, 64);
+BTRFS_SETGET_STACK_FUNCS(super_uuid_tree_generation, struct btrfs_super_block,
+ uuid_tree_generation, 64);
static inline int btrfs_super_csum_size(struct btrfs_super_block *s)
{
@@ -2847,6 +2920,14 @@
/* struct btrfs_file_extent_item */
BTRFS_SETGET_FUNCS(file_extent_type, struct btrfs_file_extent_item, type, 8);
+BTRFS_SETGET_STACK_FUNCS(stack_file_extent_disk_bytenr,
+ struct btrfs_file_extent_item, disk_bytenr, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_file_extent_offset,
+ struct btrfs_file_extent_item, offset, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_file_extent_generation,
+ struct btrfs_file_extent_item, generation, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_file_extent_num_bytes,
+ struct btrfs_file_extent_item, num_bytes, 64);
static inline unsigned long
btrfs_file_extent_inline_start(struct btrfs_file_extent_item *e)
@@ -3107,11 +3188,9 @@
struct btrfs_root *root,
u64 root_objectid, u64 owner, u64 offset,
struct btrfs_key *ins);
-int btrfs_reserve_extent(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
- u64 num_bytes, u64 min_alloc_size,
- u64 empty_size, u64 hint_byte,
- struct btrfs_key *ins, int is_data);
+int btrfs_reserve_extent(struct btrfs_root *root, u64 num_bytes,
+ u64 min_alloc_size, u64 empty_size, u64 hint_byte,
+ struct btrfs_key *ins, int is_data);
int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
struct extent_buffer *buf, int full_backref, int for_cow);
int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
@@ -3175,7 +3254,7 @@
int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
struct btrfs_block_rsv *rsv,
int nitems,
- u64 *qgroup_reserved);
+ u64 *qgroup_reserved, bool use_global_rsv);
void btrfs_subvolume_release_metadata(struct btrfs_root *root,
struct btrfs_block_rsv *rsv,
u64 qgroup_reserved);
@@ -3245,6 +3324,7 @@
BTRFS_COMPARE_TREE_NEW,
BTRFS_COMPARE_TREE_DELETED,
BTRFS_COMPARE_TREE_CHANGED,
+ BTRFS_COMPARE_TREE_SAME,
};
typedef int (*btrfs_changed_cb_t)(struct btrfs_root *left_root,
struct btrfs_root *right_root,
@@ -3380,6 +3460,7 @@
kfree(fs_info->dev_root);
kfree(fs_info->csum_root);
kfree(fs_info->quota_root);
+ kfree(fs_info->uuid_root);
kfree(fs_info->super_copy);
kfree(fs_info->super_for_commit);
kfree(fs_info);
@@ -3414,8 +3495,6 @@
struct btrfs_root *root,
struct btrfs_key *key,
struct btrfs_root_item *item);
-void btrfs_read_root_item(struct extent_buffer *eb, int slot,
- struct btrfs_root_item *item);
int btrfs_find_root(struct btrfs_root *root, struct btrfs_key *search_key,
struct btrfs_path *path, struct btrfs_root_item *root_item,
struct btrfs_key *root_key);
@@ -3426,6 +3505,17 @@
void btrfs_update_root_times(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
+/* uuid-tree.c */
+int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans,
+ struct btrfs_root *uuid_root, u8 *uuid, u8 type,
+ u64 subid);
+int btrfs_uuid_tree_rem(struct btrfs_trans_handle *trans,
+ struct btrfs_root *uuid_root, u8 *uuid, u8 type,
+ u64 subid);
+int btrfs_uuid_tree_iterate(struct btrfs_fs_info *fs_info,
+ int (*check_func)(struct btrfs_fs_info *, u8 *, u8,
+ u64));
+
/* dir-item.c */
int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir,
const char *name, int name_len);
@@ -3509,12 +3599,14 @@
struct btrfs_inode_extref **extref_ret);
/* file-item.c */
+struct btrfs_dio_private;
int btrfs_del_csums(struct btrfs_trans_handle *trans,
struct btrfs_root *root, u64 bytenr, u64 len);
int btrfs_lookup_bio_sums(struct btrfs_root *root, struct inode *inode,
struct bio *bio, u32 *dst);
int btrfs_lookup_bio_sums_dio(struct btrfs_root *root, struct inode *inode,
- struct bio *bio, u64 logical_offset);
+ struct btrfs_dio_private *dip, struct bio *bio,
+ u64 logical_offset);
int btrfs_insert_file_extent(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
u64 objectid, u64 pos,
@@ -3552,8 +3644,7 @@
struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *page,
size_t pg_offset, u64 start, u64 len,
int create);
-noinline int can_nocow_extent(struct btrfs_trans_handle *trans,
- struct inode *inode, u64 offset, u64 *len,
+noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
u64 *orig_start, u64 *orig_block_len,
u64 *ram_bytes);
@@ -3643,11 +3734,15 @@
long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
void btrfs_update_iflags(struct inode *inode);
void btrfs_inherit_iflags(struct inode *inode, struct inode *dir);
+int btrfs_is_empty_uuid(u8 *uuid);
int btrfs_defrag_file(struct inode *inode, struct file *file,
struct btrfs_ioctl_defrag_range_args *range,
u64 newer_than, unsigned long max_pages);
void btrfs_get_block_group_info(struct list_head *groups_list,
struct btrfs_ioctl_space_info *space);
+void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock,
+ struct btrfs_ioctl_balance_args *bargs);
+
/* file.c */
int btrfs_auto_defrag_init(void);
@@ -3720,6 +3815,22 @@
#define btrfs_debug(fs_info, fmt, args...) \
btrfs_printk(fs_info, KERN_DEBUG fmt, ##args)
+#ifdef CONFIG_BTRFS_ASSERT
+
+static inline void assfail(char *expr, char *file, int line)
+{
+ printk(KERN_ERR "BTRFS assertion failed: %s, file: %s, line: %d",
+ expr, file, line);
+ BUG();
+}
+
+#define ASSERT(expr) \
+ (likely(expr) ? (void)0 : assfail(#expr, __FILE__, __LINE__))
+#else
+#define ASSERT(expr) ((void)0)
+#endif
+
+#define btrfs_assert()
__printf(5, 6)
void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function,
unsigned int line, int errno, const char *fmt, ...);
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 3755109..cbd9523 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -21,6 +21,7 @@
#include "delayed-inode.h"
#include "disk-io.h"
#include "transaction.h"
+#include "ctree.h"
#define BTRFS_DELAYED_WRITEBACK 512
#define BTRFS_DELAYED_BACKGROUND 128
@@ -1453,10 +1454,10 @@
dir_item = (struct btrfs_dir_item *)delayed_item->data;
dir_item->location = *disk_key;
- dir_item->transid = cpu_to_le64(trans->transid);
- dir_item->data_len = 0;
- dir_item->name_len = cpu_to_le16(name_len);
- dir_item->type = type;
+ btrfs_set_stack_dir_transid(dir_item, trans->transid);
+ btrfs_set_stack_dir_data_len(dir_item, 0);
+ btrfs_set_stack_dir_name_len(dir_item, name_len);
+ btrfs_set_stack_dir_type(dir_item, type);
memcpy((char *)(dir_item + 1), name, name_len);
ret = btrfs_delayed_item_reserve_metadata(trans, root, delayed_item);
@@ -1470,13 +1471,11 @@
mutex_lock(&delayed_node->mutex);
ret = __btrfs_add_delayed_insertion_item(delayed_node, delayed_item);
if (unlikely(ret)) {
- printk(KERN_ERR "err add delayed dir index item(name: %s) into "
- "the insertion tree of the delayed node"
+ printk(KERN_ERR "err add delayed dir index item(name: %.*s) "
+ "into the insertion tree of the delayed node"
"(root id: %llu, inode id: %llu, errno: %d)\n",
- name,
- (unsigned long long)delayed_node->root->objectid,
- (unsigned long long)delayed_node->inode_id,
- ret);
+ name_len, name, delayed_node->root->objectid,
+ delayed_node->inode_id, ret);
BUG();
}
mutex_unlock(&delayed_node->mutex);
@@ -1547,9 +1546,7 @@
printk(KERN_ERR "err add delayed dir index item(index: %llu) "
"into the deletion tree of the delayed node"
"(root id: %llu, inode id: %llu, errno: %d)\n",
- (unsigned long long)index,
- (unsigned long long)node->root->objectid,
- (unsigned long long)node->inode_id,
+ index, node->root->objectid, node->inode_id,
ret);
BUG();
}
@@ -1699,7 +1696,7 @@
di = (struct btrfs_dir_item *)curr->data;
name = (char *)(di + 1);
- name_len = le16_to_cpu(di->name_len);
+ name_len = btrfs_stack_dir_name_len(di);
d_type = btrfs_filetype_table[di->type];
btrfs_disk_key_to_cpu(&location, &di->location);
@@ -1716,27 +1713,6 @@
return 0;
}
-BTRFS_SETGET_STACK_FUNCS(stack_inode_generation, struct btrfs_inode_item,
- generation, 64);
-BTRFS_SETGET_STACK_FUNCS(stack_inode_sequence, struct btrfs_inode_item,
- sequence, 64);
-BTRFS_SETGET_STACK_FUNCS(stack_inode_transid, struct btrfs_inode_item,
- transid, 64);
-BTRFS_SETGET_STACK_FUNCS(stack_inode_size, struct btrfs_inode_item, size, 64);
-BTRFS_SETGET_STACK_FUNCS(stack_inode_nbytes, struct btrfs_inode_item,
- nbytes, 64);
-BTRFS_SETGET_STACK_FUNCS(stack_inode_block_group, struct btrfs_inode_item,
- block_group, 64);
-BTRFS_SETGET_STACK_FUNCS(stack_inode_nlink, struct btrfs_inode_item, nlink, 32);
-BTRFS_SETGET_STACK_FUNCS(stack_inode_uid, struct btrfs_inode_item, uid, 32);
-BTRFS_SETGET_STACK_FUNCS(stack_inode_gid, struct btrfs_inode_item, gid, 32);
-BTRFS_SETGET_STACK_FUNCS(stack_inode_mode, struct btrfs_inode_item, mode, 32);
-BTRFS_SETGET_STACK_FUNCS(stack_inode_rdev, struct btrfs_inode_item, rdev, 64);
-BTRFS_SETGET_STACK_FUNCS(stack_inode_flags, struct btrfs_inode_item, flags, 64);
-
-BTRFS_SETGET_STACK_FUNCS(stack_timespec_sec, struct btrfs_timespec, sec, 64);
-BTRFS_SETGET_STACK_FUNCS(stack_timespec_nsec, struct btrfs_timespec, nsec, 32);
-
static void fill_stack_inode_item(struct btrfs_trans_handle *trans,
struct btrfs_inode_item *inode_item,
struct inode *inode)
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index c219463..e4d467b 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -241,7 +241,7 @@
return 0;
}
-static void inline drop_delayed_ref(struct btrfs_trans_handle *trans,
+static inline void drop_delayed_ref(struct btrfs_trans_handle *trans,
struct btrfs_delayed_ref_root *delayed_refs,
struct btrfs_delayed_ref_node *ref)
{
@@ -600,7 +600,7 @@
INIT_LIST_HEAD(&head_ref->cluster);
mutex_init(&head_ref->mutex);
- trace_btrfs_delayed_ref_head(ref, head_ref, action);
+ trace_add_delayed_ref_head(ref, head_ref, action);
existing = tree_insert(&delayed_refs->root, &ref->rb_node);
@@ -661,7 +661,7 @@
ref->type = BTRFS_TREE_BLOCK_REF_KEY;
full_ref->level = level;
- trace_btrfs_delayed_tree_ref(ref, full_ref, action);
+ trace_add_delayed_tree_ref(ref, full_ref, action);
existing = tree_insert(&delayed_refs->root, &ref->rb_node);
@@ -722,7 +722,7 @@
full_ref->objectid = owner;
full_ref->offset = offset;
- trace_btrfs_delayed_data_ref(ref, full_ref, action);
+ trace_add_delayed_data_ref(ref, full_ref, action);
existing = tree_insert(&delayed_refs->root, &ref->rb_node);
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 5f8f334..a644353 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -148,13 +148,13 @@
!btrfs_test_opt(dev_root, DEGRADED)) {
ret = -EIO;
pr_warn("btrfs: cannot mount because device replace operation is ongoing and\n" "srcdev (devid %llu) is missing, need to run 'btrfs dev scan'?\n",
- (unsigned long long)src_devid);
+ src_devid);
}
if (!dev_replace->tgtdev &&
!btrfs_test_opt(dev_root, DEGRADED)) {
ret = -EIO;
pr_warn("btrfs: cannot mount because device replace operation is ongoing and\n" "tgtdev (devid %llu) is missing, need to run btrfs dev scan?\n",
- (unsigned long long)BTRFS_DEV_REPLACE_DEVID);
+ BTRFS_DEV_REPLACE_DEVID);
}
if (dev_replace->tgtdev) {
if (dev_replace->srcdev) {
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 6b092a1..4cbb00a 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -31,6 +31,7 @@
#include <linux/migrate.h>
#include <linux/ratelimit.h>
#include <linux/uuid.h>
+#include <linux/semaphore.h>
#include <asm/unaligned.h>
#include "compat.h"
#include "ctree.h"
@@ -302,9 +303,8 @@
printk_ratelimited(KERN_INFO "btrfs: %s checksum verify "
"failed on %llu wanted %X found %X "
"level %d\n",
- root->fs_info->sb->s_id,
- (unsigned long long)buf->start, val, found,
- btrfs_header_level(buf));
+ root->fs_info->sb->s_id, buf->start,
+ val, found, btrfs_header_level(buf));
if (result != (char *)&inline_result)
kfree(result);
return 1;
@@ -345,9 +345,7 @@
}
printk_ratelimited("parent transid verify failed on %llu wanted %llu "
"found %llu\n",
- (unsigned long long)eb->start,
- (unsigned long long)parent_transid,
- (unsigned long long)btrfs_header_generation(eb));
+ eb->start, parent_transid, btrfs_header_generation(eb));
ret = 1;
clear_extent_buffer_uptodate(eb);
out:
@@ -497,8 +495,7 @@
u8 fsid[BTRFS_UUID_SIZE];
int ret = 1;
- read_extent_buffer(eb, fsid, (unsigned long)btrfs_header_fsid(eb),
- BTRFS_FSID_SIZE);
+ read_extent_buffer(eb, fsid, btrfs_header_fsid(eb), BTRFS_FSID_SIZE);
while (fs_devices) {
if (!memcmp(fsid, fs_devices->fsid, BTRFS_FSID_SIZE)) {
ret = 0;
@@ -512,8 +509,7 @@
#define CORRUPT(reason, eb, root, slot) \
printk(KERN_CRIT "btrfs: corrupt leaf, %s: block=%llu," \
"root=%llu, slot=%d\n", reason, \
- (unsigned long long)btrfs_header_bytenr(eb), \
- (unsigned long long)root->objectid, slot)
+ btrfs_header_bytenr(eb), root->objectid, slot)
static noinline int check_leaf(struct btrfs_root *root,
struct extent_buffer *leaf)
@@ -576,8 +572,9 @@
return 0;
}
-static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end,
- struct extent_state *state, int mirror)
+static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
+ u64 phy_offset, struct page *page,
+ u64 start, u64 end, int mirror)
{
struct extent_io_tree *tree;
u64 found_start;
@@ -612,14 +609,13 @@
if (found_start != eb->start) {
printk_ratelimited(KERN_INFO "btrfs bad tree block start "
"%llu %llu\n",
- (unsigned long long)found_start,
- (unsigned long long)eb->start);
+ found_start, eb->start);
ret = -EIO;
goto err;
}
if (check_tree_block_fsid(root, eb)) {
printk_ratelimited(KERN_INFO "btrfs bad fsid on block %llu\n",
- (unsigned long long)eb->start);
+ eb->start);
ret = -EIO;
goto err;
}
@@ -1148,6 +1144,10 @@
return NULL;
ret = btree_read_extent_buffer_pages(root, buf, 0, parent_transid);
+ if (ret) {
+ free_extent_buffer(buf);
+ return NULL;
+ }
return buf;
}
@@ -1291,11 +1291,10 @@
btrfs_set_header_owner(leaf, objectid);
root->node = leaf;
- write_extent_buffer(leaf, fs_info->fsid,
- (unsigned long)btrfs_header_fsid(leaf),
+ write_extent_buffer(leaf, fs_info->fsid, btrfs_header_fsid(leaf),
BTRFS_FSID_SIZE);
write_extent_buffer(leaf, fs_info->chunk_tree_uuid,
- (unsigned long)btrfs_header_chunk_tree_uuid(leaf),
+ btrfs_header_chunk_tree_uuid(leaf),
BTRFS_UUID_SIZE);
btrfs_mark_buffer_dirty(leaf);
@@ -1379,8 +1378,7 @@
root->node = leaf;
write_extent_buffer(root->node, root->fs_info->fsid,
- (unsigned long)btrfs_header_fsid(root->node),
- BTRFS_FSID_SIZE);
+ btrfs_header_fsid(root->node), BTRFS_FSID_SIZE);
btrfs_mark_buffer_dirty(root->node);
btrfs_tree_unlock(root->node);
return root;
@@ -1413,11 +1411,11 @@
log_root->root_key.offset = root->root_key.objectid;
inode_item = &log_root->root_item.inode;
- inode_item->generation = cpu_to_le64(1);
- inode_item->size = cpu_to_le64(3);
- inode_item->nlink = cpu_to_le32(1);
- inode_item->nbytes = cpu_to_le64(root->leafsize);
- inode_item->mode = cpu_to_le32(S_IFDIR | 0755);
+ btrfs_set_stack_inode_generation(inode_item, 1);
+ btrfs_set_stack_inode_size(inode_item, 3);
+ btrfs_set_stack_inode_nlink(inode_item, 1);
+ btrfs_set_stack_inode_nbytes(inode_item, root->leafsize);
+ btrfs_set_stack_inode_mode(inode_item, S_IFDIR | 0755);
btrfs_set_root_node(&log_root->root_item, log_root->node);
@@ -1428,8 +1426,8 @@
return 0;
}
-struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root,
- struct btrfs_key *key)
+static struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root,
+ struct btrfs_key *key)
{
struct btrfs_root *root;
struct btrfs_fs_info *fs_info = tree_root->fs_info;
@@ -1529,8 +1527,8 @@
return ret;
}
-struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,
- u64 root_id)
+static struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,
+ u64 root_id)
{
struct btrfs_root *root;
@@ -1581,10 +1579,16 @@
if (location->objectid == BTRFS_QUOTA_TREE_OBJECTID)
return fs_info->quota_root ? fs_info->quota_root :
ERR_PTR(-ENOENT);
+ if (location->objectid == BTRFS_UUID_TREE_OBJECTID)
+ return fs_info->uuid_root ? fs_info->uuid_root :
+ ERR_PTR(-ENOENT);
again:
root = btrfs_lookup_fs_root(fs_info, location->objectid);
- if (root)
+ if (root) {
+ if (btrfs_root_refs(&root->root_item) == 0)
+ return ERR_PTR(-ENOENT);
return root;
+ }
root = btrfs_read_fs_root(fs_info->tree_root, location);
if (IS_ERR(root))
@@ -1737,7 +1741,7 @@
do {
cannot_commit = false;
- delay = HZ * 30;
+ delay = HZ * root->fs_info->commit_interval;
mutex_lock(&root->fs_info->transaction_kthread_mutex);
spin_lock(&root->fs_info->trans_lock);
@@ -1749,7 +1753,8 @@
now = get_seconds();
if (cur->state < TRANS_STATE_BLOCKED &&
- (now < cur->start_time || now - cur->start_time < 30)) {
+ (now < cur->start_time ||
+ now - cur->start_time < root->fs_info->commit_interval)) {
spin_unlock(&root->fs_info->trans_lock);
delay = HZ * 5;
goto sleep;
@@ -2038,6 +2043,12 @@
info->quota_root->node = NULL;
info->quota_root->commit_root = NULL;
}
+ if (info->uuid_root) {
+ free_extent_buffer(info->uuid_root->node);
+ free_extent_buffer(info->uuid_root->commit_root);
+ info->uuid_root->node = NULL;
+ info->uuid_root->commit_root = NULL;
+ }
if (chunk_root) {
free_extent_buffer(info->chunk_root->node);
free_extent_buffer(info->chunk_root->commit_root);
@@ -2098,11 +2109,14 @@
struct btrfs_root *chunk_root;
struct btrfs_root *dev_root;
struct btrfs_root *quota_root;
+ struct btrfs_root *uuid_root;
struct btrfs_root *log_tree_root;
int ret;
int err = -EINVAL;
int num_backups_tried = 0;
int backup_index = 0;
+ bool create_uuid_tree;
+ bool check_uuid_tree;
tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info);
chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info);
@@ -2189,6 +2203,7 @@
fs_info->defrag_inodes = RB_ROOT;
fs_info->free_chunk_space = 0;
fs_info->tree_mod_log = RB_ROOT;
+ fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL;
/* readahead state */
INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_WAIT);
@@ -2270,6 +2285,7 @@
mutex_init(&fs_info->ordered_operations_mutex);
+ mutex_init(&fs_info->ordered_extent_flush_mutex);
mutex_init(&fs_info->tree_log_mutex);
mutex_init(&fs_info->chunk_mutex);
mutex_init(&fs_info->transaction_kthread_mutex);
@@ -2278,6 +2294,7 @@
init_rwsem(&fs_info->extent_commit_sem);
init_rwsem(&fs_info->cleanup_work_sem);
init_rwsem(&fs_info->subvol_sem);
+ sema_init(&fs_info->uuid_tree_rescan_sem, 1);
fs_info->dev_replace.lock_owner = 0;
atomic_set(&fs_info->dev_replace.nesting_level, 0);
mutex_init(&fs_info->dev_replace.lock_finishing_cancel_unmount);
@@ -2383,7 +2400,7 @@
if (features) {
printk(KERN_ERR "BTRFS: couldn't mount because of "
"unsupported optional features (%Lx).\n",
- (unsigned long long)features);
+ features);
err = -EINVAL;
goto fail_alloc;
}
@@ -2453,7 +2470,7 @@
if (!(sb->s_flags & MS_RDONLY) && features) {
printk(KERN_ERR "BTRFS: couldn't mount RDWR because of "
"unsupported option features (%Lx).\n",
- (unsigned long long)features);
+ features);
err = -EINVAL;
goto fail_alloc;
}
@@ -2466,20 +2483,17 @@
&fs_info->generic_worker);
btrfs_init_workers(&fs_info->delalloc_workers, "delalloc",
- fs_info->thread_pool_size,
- &fs_info->generic_worker);
+ fs_info->thread_pool_size, NULL);
btrfs_init_workers(&fs_info->flush_workers, "flush_delalloc",
- fs_info->thread_pool_size,
- &fs_info->generic_worker);
+ fs_info->thread_pool_size, NULL);
btrfs_init_workers(&fs_info->submit_workers, "submit",
min_t(u64, fs_devices->num_devices,
- fs_info->thread_pool_size),
- &fs_info->generic_worker);
+ fs_info->thread_pool_size), NULL);
btrfs_init_workers(&fs_info->caching_workers, "cache",
- 2, &fs_info->generic_worker);
+ fs_info->thread_pool_size, NULL);
/* a higher idle thresh on the submit workers makes it much more
* likely that bios will be send down in a sane order to the
@@ -2575,7 +2589,7 @@
sb->s_blocksize = sectorsize;
sb->s_blocksize_bits = blksize_bits(sectorsize);
- if (disk_super->magic != cpu_to_le64(BTRFS_MAGIC)) {
+ if (btrfs_super_magic(disk_super) != BTRFS_MAGIC) {
printk(KERN_INFO "btrfs: valid FS not found on %s\n", sb->s_id);
goto fail_sb_buffer;
}
@@ -2615,8 +2629,7 @@
chunk_root->commit_root = btrfs_root_node(chunk_root);
read_extent_buffer(chunk_root->node, fs_info->chunk_tree_uuid,
- (unsigned long)btrfs_header_chunk_tree_uuid(chunk_root->node),
- BTRFS_UUID_SIZE);
+ btrfs_header_chunk_tree_uuid(chunk_root->node), BTRFS_UUID_SIZE);
ret = btrfs_read_chunk_tree(chunk_root);
if (ret) {
@@ -2696,6 +2709,22 @@
fs_info->quota_root = quota_root;
}
+ location.objectid = BTRFS_UUID_TREE_OBJECTID;
+ uuid_root = btrfs_read_tree_root(tree_root, &location);
+ if (IS_ERR(uuid_root)) {
+ ret = PTR_ERR(uuid_root);
+ if (ret != -ENOENT)
+ goto recovery_tree_root;
+ create_uuid_tree = true;
+ check_uuid_tree = false;
+ } else {
+ uuid_root->track_dirty = 1;
+ fs_info->uuid_root = uuid_root;
+ create_uuid_tree = false;
+ check_uuid_tree =
+ generation != btrfs_super_uuid_tree_generation(disk_super);
+ }
+
fs_info->generation = generation;
fs_info->last_trans_committed = generation;
@@ -2882,6 +2911,29 @@
btrfs_qgroup_rescan_resume(fs_info);
+ if (create_uuid_tree) {
+ pr_info("btrfs: creating UUID tree\n");
+ ret = btrfs_create_uuid_tree(fs_info);
+ if (ret) {
+ pr_warn("btrfs: failed to create the UUID tree %d\n",
+ ret);
+ close_ctree(tree_root);
+ return ret;
+ }
+ } else if (check_uuid_tree ||
+ btrfs_test_opt(tree_root, RESCAN_UUID_TREE)) {
+ pr_info("btrfs: checking UUID tree\n");
+ ret = btrfs_check_uuid_tree(fs_info);
+ if (ret) {
+ pr_warn("btrfs: failed to check the UUID tree %d\n",
+ ret);
+ close_ctree(tree_root);
+ return ret;
+ }
+ } else {
+ fs_info->update_uuid_tree_gen = 1;
+ }
+
return 0;
fail_qgroup:
@@ -2983,15 +3035,17 @@
*/
for (i = 0; i < 1; i++) {
bytenr = btrfs_sb_offset(i);
- if (bytenr + 4096 >= i_size_read(bdev->bd_inode))
+ if (bytenr + BTRFS_SUPER_INFO_SIZE >=
+ i_size_read(bdev->bd_inode))
break;
- bh = __bread(bdev, bytenr / 4096, 4096);
+ bh = __bread(bdev, bytenr / 4096,
+ BTRFS_SUPER_INFO_SIZE);
if (!bh)
continue;
super = (struct btrfs_super_block *)bh->b_data;
if (btrfs_super_bytenr(super) != bytenr ||
- super->magic != cpu_to_le64(BTRFS_MAGIC)) {
+ btrfs_super_magic(super) != BTRFS_MAGIC) {
brelse(bh);
continue;
}
@@ -3311,7 +3365,6 @@
int total_errors = 0;
u64 flags;
- max_errors = btrfs_super_num_devices(root->fs_info->super_copy) - 1;
do_barriers = !btrfs_test_opt(root, NOBARRIER);
backup_super_roots(root->fs_info);
@@ -3320,6 +3373,7 @@
mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
head = &root->fs_info->fs_devices->devices;
+ max_errors = btrfs_super_num_devices(root->fs_info->super_copy) - 1;
if (do_barriers) {
ret = barrier_all_devices(root->fs_info);
@@ -3362,8 +3416,10 @@
printk(KERN_ERR "btrfs: %d errors while writing supers\n",
total_errors);
- /* This shouldn't happen. FUA is masked off if unsupported */
- BUG();
+ /* FUA is masked off if unsupported and can't be the reason */
+ btrfs_error(root->fs_info, -EIO,
+ "%d errors while writing supers", total_errors);
+ return -EIO;
}
total_errors = 0;
@@ -3421,6 +3477,8 @@
{
iput(root->cache_inode);
WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree));
+ btrfs_free_block_rsv(root, root->orphan_block_rsv);
+ root->orphan_block_rsv = NULL;
if (root->anon_dev)
free_anon_bdev(root->anon_dev);
free_extent_buffer(root->node);
@@ -3510,6 +3568,11 @@
fs_info->closing = 1;
smp_mb();
+ /* wait for the uuid_scan task to finish */
+ down(&fs_info->uuid_tree_rescan_sem);
+ /* avoid complains from lockdep et al., set sem back to initial state */
+ up(&fs_info->uuid_tree_rescan_sem);
+
/* pause restriper - we want to resume on mount */
btrfs_pause_balance(fs_info);
@@ -3573,6 +3636,9 @@
btrfs_free_stripe_hash_table(fs_info);
+ btrfs_free_block_rsv(root, root->orphan_block_rsv);
+ root->orphan_block_rsv = NULL;
+
return 0;
}
@@ -3608,9 +3674,7 @@
if (transid != root->fs_info->generation)
WARN(1, KERN_CRIT "btrfs transid mismatch buffer %llu, "
"found %llu running %llu\n",
- (unsigned long long)buf->start,
- (unsigned long long)transid,
- (unsigned long long)root->fs_info->generation);
+ buf->start, transid, root->fs_info->generation);
was_dirty = set_extent_buffer_dirty(buf);
if (!was_dirty)
__percpu_counter_add(&root->fs_info->dirty_metadata_bytes,
@@ -3744,8 +3808,8 @@
spin_unlock(&fs_info->ordered_root_lock);
}
-int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
- struct btrfs_root *root)
+static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
+ struct btrfs_root *root)
{
struct rb_node *node;
struct btrfs_delayed_ref_root *delayed_refs;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 1204c8e..cfb3cf7 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -113,7 +113,8 @@
block_group_cache_done(struct btrfs_block_group_cache *cache)
{
smp_mb();
- return cache->cached == BTRFS_CACHE_FINISHED;
+ return cache->cached == BTRFS_CACHE_FINISHED ||
+ cache->cached == BTRFS_CACHE_ERROR;
}
static int block_group_bits(struct btrfs_block_group_cache *cache, u64 bits)
@@ -389,7 +390,7 @@
u64 total_found = 0;
u64 last = 0;
u32 nritems;
- int ret = 0;
+ int ret = -ENOMEM;
caching_ctl = container_of(work, struct btrfs_caching_control, work);
block_group = caching_ctl->block_group;
@@ -420,6 +421,7 @@
/* need to make sure the commit_root doesn't disappear */
down_read(&fs_info->extent_commit_sem);
+next:
ret = btrfs_search_slot(NULL, extent_root, &key, path, 0, 0);
if (ret < 0)
goto err;
@@ -459,6 +461,16 @@
continue;
}
+ if (key.objectid < last) {
+ key.objectid = last;
+ key.offset = 0;
+ key.type = BTRFS_EXTENT_ITEM_KEY;
+
+ caching_ctl->progress = last;
+ btrfs_release_path(path);
+ goto next;
+ }
+
if (key.objectid < block_group->key.objectid) {
path->slots[0]++;
continue;
@@ -506,6 +518,12 @@
mutex_unlock(&caching_ctl->mutex);
out:
+ if (ret) {
+ spin_lock(&block_group->lock);
+ block_group->caching_ctl = NULL;
+ block_group->cached = BTRFS_CACHE_ERROR;
+ spin_unlock(&block_group->lock);
+ }
wake_up(&caching_ctl->wait);
put_caching_control(caching_ctl);
@@ -771,10 +789,23 @@
goto out_free;
if (ret > 0 && metadata && key.type == BTRFS_METADATA_ITEM_KEY) {
- key.type = BTRFS_EXTENT_ITEM_KEY;
- key.offset = root->leafsize;
- btrfs_release_path(path);
- goto again;
+ metadata = 0;
+ if (path->slots[0]) {
+ path->slots[0]--;
+ btrfs_item_key_to_cpu(path->nodes[0], &key,
+ path->slots[0]);
+ if (key.objectid == bytenr &&
+ key.type == BTRFS_EXTENT_ITEM_KEY &&
+ key.offset == root->leafsize)
+ ret = 0;
+ }
+ if (ret) {
+ key.objectid = bytenr;
+ key.type = BTRFS_EXTENT_ITEM_KEY;
+ key.offset = root->leafsize;
+ btrfs_release_path(path);
+ goto again;
+ }
}
if (ret == 0) {
@@ -2011,6 +2042,8 @@
ins.type = BTRFS_EXTENT_ITEM_KEY;
ref = btrfs_delayed_node_to_data_ref(node);
+ trace_run_delayed_data_ref(node, ref, node->action);
+
if (node->type == BTRFS_SHARED_DATA_REF_KEY)
parent = ref->parent;
else
@@ -2154,6 +2187,8 @@
SKINNY_METADATA);
ref = btrfs_delayed_node_to_tree_ref(node);
+ trace_run_delayed_tree_ref(node, ref, node->action);
+
if (node->type == BTRFS_SHARED_BLOCK_REF_KEY)
parent = ref->parent;
else
@@ -2212,6 +2247,8 @@
*/
BUG_ON(extent_op);
head = btrfs_delayed_node_to_head(node);
+ trace_run_delayed_ref_head(node, head, node->action);
+
if (insert_reserved) {
btrfs_pin_extent(root, node->bytenr,
node->num_bytes, 1);
@@ -2403,6 +2440,8 @@
default:
WARN_ON(1);
}
+ } else {
+ list_del_init(&locked_ref->cluster);
}
spin_unlock(&delayed_refs->lock);
@@ -2425,7 +2464,6 @@
* list before we release it.
*/
if (btrfs_delayed_ref_is_head(ref)) {
- list_del_init(&locked_ref->cluster);
btrfs_delayed_ref_unlock(locked_ref);
locked_ref = NULL;
}
@@ -3799,8 +3837,12 @@
if (force < space_info->force_alloc)
force = space_info->force_alloc;
if (space_info->full) {
+ if (should_alloc_chunk(extent_root, space_info, force))
+ ret = -ENOSPC;
+ else
+ ret = 0;
spin_unlock(&space_info->lock);
- return 0;
+ return ret;
}
if (!should_alloc_chunk(extent_root, space_info, force)) {
@@ -4320,6 +4362,9 @@
if (root == root->fs_info->csum_root && trans->adding_csums)
block_rsv = trans->block_rsv;
+ if (root == root->fs_info->uuid_root)
+ block_rsv = trans->block_rsv;
+
if (!block_rsv)
block_rsv = root->block_rsv;
@@ -4729,10 +4774,12 @@
int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
struct btrfs_block_rsv *rsv,
int items,
- u64 *qgroup_reserved)
+ u64 *qgroup_reserved,
+ bool use_global_rsv)
{
u64 num_bytes;
int ret;
+ struct btrfs_block_rsv *global_rsv = &root->fs_info->global_block_rsv;
if (root->fs_info->quota_enabled) {
/* One for parent inode, two for dir entries */
@@ -4751,6 +4798,10 @@
BTRFS_BLOCK_GROUP_METADATA);
ret = btrfs_block_rsv_add(root, rsv, num_bytes,
BTRFS_RESERVE_FLUSH_ALL);
+
+ if (ret == -ENOSPC && use_global_rsv)
+ ret = btrfs_block_rsv_migrate(global_rsv, rsv, num_bytes);
+
if (ret) {
if (*qgroup_reserved)
btrfs_qgroup_free(root, *qgroup_reserved);
@@ -5668,7 +5719,7 @@
if (ret) {
btrfs_err(info, "umm, got %d back from search, was looking for %llu",
- ret, (unsigned long long)bytenr);
+ ret, bytenr);
if (ret > 0)
btrfs_print_leaf(extent_root,
path->nodes[0]);
@@ -5684,11 +5735,8 @@
WARN_ON(1);
btrfs_err(info,
"unable to find ref byte nr %llu parent %llu root %llu owner %llu offset %llu",
- (unsigned long long)bytenr,
- (unsigned long long)parent,
- (unsigned long long)root_objectid,
- (unsigned long long)owner_objectid,
- (unsigned long long)owner_offset);
+ bytenr, parent, root_objectid, owner_objectid,
+ owner_offset);
} else {
btrfs_abort_transaction(trans, extent_root, ret);
goto out;
@@ -5717,7 +5765,7 @@
-1, 1);
if (ret) {
btrfs_err(info, "umm, got %d back from search, was looking for %llu",
- ret, (unsigned long long)bytenr);
+ ret, bytenr);
btrfs_print_leaf(extent_root, path->nodes[0]);
}
if (ret < 0) {
@@ -5999,8 +6047,11 @@
* for our min num_bytes. Another option is to have it go ahead
* and look in the rbtree for a free extent of a given size, but this
* is a good start.
+ *
+ * Callers of this must check if cache->cached == BTRFS_CACHE_ERROR before using
+ * any of the information in this block group.
*/
-static noinline int
+static noinline void
wait_block_group_cache_progress(struct btrfs_block_group_cache *cache,
u64 num_bytes)
{
@@ -6008,28 +6059,29 @@
caching_ctl = get_caching_control(cache);
if (!caching_ctl)
- return 0;
+ return;
wait_event(caching_ctl->wait, block_group_cache_done(cache) ||
(cache->free_space_ctl->free_space >= num_bytes));
put_caching_control(caching_ctl);
- return 0;
}
static noinline int
wait_block_group_cache_done(struct btrfs_block_group_cache *cache)
{
struct btrfs_caching_control *caching_ctl;
+ int ret = 0;
caching_ctl = get_caching_control(cache);
if (!caching_ctl)
- return 0;
+ return (cache->cached == BTRFS_CACHE_ERROR) ? -EIO : 0;
wait_event(caching_ctl->wait, block_group_cache_done(cache));
-
+ if (cache->cached == BTRFS_CACHE_ERROR)
+ ret = -EIO;
put_caching_control(caching_ctl);
- return 0;
+ return ret;
}
int __get_raid_index(u64 flags)
@@ -6070,8 +6122,7 @@
* ins->offset == number of blocks
* Any available blocks before search_start are skipped.
*/
-static noinline int find_free_extent(struct btrfs_trans_handle *trans,
- struct btrfs_root *orig_root,
+static noinline int find_free_extent(struct btrfs_root *orig_root,
u64 num_bytes, u64 empty_size,
u64 hint_byte, struct btrfs_key *ins,
u64 flags)
@@ -6212,6 +6263,8 @@
ret = 0;
}
+ if (unlikely(block_group->cached == BTRFS_CACHE_ERROR))
+ goto loop;
if (unlikely(block_group->ro))
goto loop;
@@ -6292,10 +6345,10 @@
block_group->full_stripe_len);
/* allocate a cluster in this block group */
- ret = btrfs_find_space_cluster(trans, root,
- block_group, last_ptr,
- search_start, num_bytes,
- aligned_cluster);
+ ret = btrfs_find_space_cluster(root, block_group,
+ last_ptr, search_start,
+ num_bytes,
+ aligned_cluster);
if (ret == 0) {
/*
* now pull our allocation out of this
@@ -6426,17 +6479,28 @@
index = 0;
loop++;
if (loop == LOOP_ALLOC_CHUNK) {
+ struct btrfs_trans_handle *trans;
+
+ trans = btrfs_join_transaction(root);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ goto out;
+ }
+
ret = do_chunk_alloc(trans, root, flags,
CHUNK_ALLOC_FORCE);
/*
* Do not bail out on ENOSPC since we
* can do more things.
*/
- if (ret < 0 && ret != -ENOSPC) {
+ if (ret < 0 && ret != -ENOSPC)
btrfs_abort_transaction(trans,
root, ret);
+ else
+ ret = 0;
+ btrfs_end_transaction(trans, root);
+ if (ret)
goto out;
- }
}
if (loop == LOOP_NO_EMPTY_SIZE) {
@@ -6463,19 +6527,15 @@
spin_lock(&info->lock);
printk(KERN_INFO "space_info %llu has %llu free, is %sfull\n",
- (unsigned long long)info->flags,
- (unsigned long long)(info->total_bytes - info->bytes_used -
- info->bytes_pinned - info->bytes_reserved -
- info->bytes_readonly),
+ info->flags,
+ info->total_bytes - info->bytes_used - info->bytes_pinned -
+ info->bytes_reserved - info->bytes_readonly,
(info->full) ? "" : "not ");
printk(KERN_INFO "space_info total=%llu, used=%llu, pinned=%llu, "
"reserved=%llu, may_use=%llu, readonly=%llu\n",
- (unsigned long long)info->total_bytes,
- (unsigned long long)info->bytes_used,
- (unsigned long long)info->bytes_pinned,
- (unsigned long long)info->bytes_reserved,
- (unsigned long long)info->bytes_may_use,
- (unsigned long long)info->bytes_readonly);
+ info->total_bytes, info->bytes_used, info->bytes_pinned,
+ info->bytes_reserved, info->bytes_may_use,
+ info->bytes_readonly);
spin_unlock(&info->lock);
if (!dump_block_groups)
@@ -6486,12 +6546,9 @@
list_for_each_entry(cache, &info->block_groups[index], list) {
spin_lock(&cache->lock);
printk(KERN_INFO "block group %llu has %llu bytes, %llu used %llu pinned %llu reserved %s\n",
- (unsigned long long)cache->key.objectid,
- (unsigned long long)cache->key.offset,
- (unsigned long long)btrfs_block_group_used(&cache->item),
- (unsigned long long)cache->pinned,
- (unsigned long long)cache->reserved,
- cache->ro ? "[readonly]" : "");
+ cache->key.objectid, cache->key.offset,
+ btrfs_block_group_used(&cache->item), cache->pinned,
+ cache->reserved, cache->ro ? "[readonly]" : "");
btrfs_dump_free_space(cache, bytes);
spin_unlock(&cache->lock);
}
@@ -6500,8 +6557,7 @@
up_read(&info->groups_sem);
}
-int btrfs_reserve_extent(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
+int btrfs_reserve_extent(struct btrfs_root *root,
u64 num_bytes, u64 min_alloc_size,
u64 empty_size, u64 hint_byte,
struct btrfs_key *ins, int is_data)
@@ -6513,8 +6569,8 @@
flags = btrfs_get_alloc_profile(root, is_data);
again:
WARN_ON(num_bytes < root->sectorsize);
- ret = find_free_extent(trans, root, num_bytes, empty_size,
- hint_byte, ins, flags);
+ ret = find_free_extent(root, num_bytes, empty_size, hint_byte, ins,
+ flags);
if (ret == -ENOSPC) {
if (!final_tried) {
@@ -6529,8 +6585,7 @@
sinfo = __find_space_info(root->fs_info, flags);
btrfs_err(root->fs_info, "allocation failed flags %llu, wanted %llu",
- (unsigned long long)flags,
- (unsigned long long)num_bytes);
+ flags, num_bytes);
if (sinfo)
dump_space_info(sinfo, num_bytes, 1);
}
@@ -6550,7 +6605,7 @@
cache = btrfs_lookup_block_group(root->fs_info, start);
if (!cache) {
btrfs_err(root->fs_info, "Unable to find block group for %llu",
- (unsigned long long)start);
+ start);
return -ENOSPC;
}
@@ -6646,8 +6701,7 @@
ret = update_block_group(root, ins->objectid, ins->offset, 1);
if (ret) { /* -ENOENT, logic error */
btrfs_err(fs_info, "update block group failed for %llu %llu",
- (unsigned long long)ins->objectid,
- (unsigned long long)ins->offset);
+ ins->objectid, ins->offset);
BUG();
}
return ret;
@@ -6719,8 +6773,7 @@
ret = update_block_group(root, ins->objectid, root->leafsize, 1);
if (ret) { /* -ENOENT, logic error */
btrfs_err(fs_info, "update block group failed for %llu %llu",
- (unsigned long long)ins->objectid,
- (unsigned long long)ins->offset);
+ ins->objectid, ins->offset);
BUG();
}
return ret;
@@ -6902,7 +6955,7 @@
if (IS_ERR(block_rsv))
return ERR_CAST(block_rsv);
- ret = btrfs_reserve_extent(trans, root, blocksize, blocksize,
+ ret = btrfs_reserve_extent(root, blocksize, blocksize,
empty_size, hint, &ins, 0);
if (ret) {
unuse_block_rsv(root->fs_info, block_rsv, blocksize);
@@ -7173,6 +7226,8 @@
next = btrfs_find_create_tree_block(root, bytenr, blocksize);
if (!next)
return -ENOMEM;
+ btrfs_set_buffer_lockdep_class(root->root_key.objectid, next,
+ level - 1);
reada = 1;
}
btrfs_tree_lock(next);
@@ -7658,7 +7713,7 @@
* don't have it in the radix (like when we recover after a power fail
* or unmount) so we don't leak memory.
*/
- if (root_dropped == false)
+ if (!for_reloc && root_dropped == false)
btrfs_add_dead_root(root);
if (err)
btrfs_std_error(root->fs_info, err);
@@ -8192,7 +8247,8 @@
* We haven't cached this block group, which means we could
* possibly have excluded extents on this block group.
*/
- if (block_group->cached == BTRFS_CACHE_NO)
+ if (block_group->cached == BTRFS_CACHE_NO ||
+ block_group->cached == BTRFS_CACHE_ERROR)
free_excluded_extents(info->extent_root, block_group);
btrfs_remove_free_space_cache(block_group);
@@ -8409,9 +8465,13 @@
* avoid allocating from un-mirrored block group if there are
* mirrored block groups.
*/
- list_for_each_entry(cache, &space_info->block_groups[3], list)
+ list_for_each_entry(cache,
+ &space_info->block_groups[BTRFS_RAID_RAID0],
+ list)
set_block_group_ro(cache, 1);
- list_for_each_entry(cache, &space_info->block_groups[4], list)
+ list_for_each_entry(cache,
+ &space_info->block_groups[BTRFS_RAID_SINGLE],
+ list)
set_block_group_ro(cache, 1);
}
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index fe443fe..09582b8 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -61,9 +61,8 @@
state = list_entry(states.next, struct extent_state, leak_list);
printk(KERN_ERR "btrfs state leak: start %llu end %llu "
"state %lu in tree %p refs %d\n",
- (unsigned long long)state->start,
- (unsigned long long)state->end,
- state->state, state->tree, atomic_read(&state->refs));
+ state->start, state->end, state->state, state->tree,
+ atomic_read(&state->refs));
list_del(&state->leak_list);
kmem_cache_free(extent_state_cache, state);
}
@@ -71,8 +70,8 @@
while (!list_empty(&buffers)) {
eb = list_entry(buffers.next, struct extent_buffer, leak_list);
printk(KERN_ERR "btrfs buffer leak start %llu len %lu "
- "refs %d\n", (unsigned long long)eb->start,
- eb->len, atomic_read(&eb->refs));
+ "refs %d\n",
+ eb->start, eb->len, atomic_read(&eb->refs));
list_del(&eb->leak_list);
kmem_cache_free(extent_buffer_cache, eb);
}
@@ -88,11 +87,7 @@
if (end >= PAGE_SIZE && (end % 2) == 0 && end != isize - 1) {
printk_ratelimited(KERN_DEBUG
"btrfs: %s: ino %llu isize %llu odd range [%llu,%llu]\n",
- caller,
- (unsigned long long)btrfs_ino(inode),
- (unsigned long long)isize,
- (unsigned long long)start,
- (unsigned long long)end);
+ caller, btrfs_ino(inode), isize, start, end);
}
}
#else
@@ -388,8 +383,7 @@
if (end < start)
WARN(1, KERN_ERR "btrfs end < start %llu %llu\n",
- (unsigned long long)end,
- (unsigned long long)start);
+ end, start);
state->start = start;
state->end = end;
@@ -400,9 +394,8 @@
struct extent_state *found;
found = rb_entry(node, struct extent_state, rb_node);
printk(KERN_ERR "btrfs found node %llu %llu on insert of "
- "%llu %llu\n", (unsigned long long)found->start,
- (unsigned long long)found->end,
- (unsigned long long)start, (unsigned long long)end);
+ "%llu %llu\n",
+ found->start, found->end, start, end);
return -EEXIST;
}
state->tree = tree;
@@ -762,15 +755,6 @@
}
}
-static void uncache_state(struct extent_state **cached_ptr)
-{
- if (cached_ptr && (*cached_ptr)) {
- struct extent_state *state = *cached_ptr;
- *cached_ptr = NULL;
- free_extent_state(state);
- }
-}
-
/*
* set some bits on a range in the tree. This may require allocations or
* sleeping, so the gfp mask is used to indicate what is allowed.
@@ -1687,31 +1671,21 @@
return found;
}
-int extent_clear_unlock_delalloc(struct inode *inode,
- struct extent_io_tree *tree,
- u64 start, u64 end, struct page *locked_page,
- unsigned long op)
+int extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
+ struct page *locked_page,
+ unsigned long clear_bits,
+ unsigned long page_ops)
{
+ struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
int ret;
struct page *pages[16];
unsigned long index = start >> PAGE_CACHE_SHIFT;
unsigned long end_index = end >> PAGE_CACHE_SHIFT;
unsigned long nr_pages = end_index - index + 1;
int i;
- unsigned long clear_bits = 0;
-
- if (op & EXTENT_CLEAR_UNLOCK)
- clear_bits |= EXTENT_LOCKED;
- if (op & EXTENT_CLEAR_DIRTY)
- clear_bits |= EXTENT_DIRTY;
-
- if (op & EXTENT_CLEAR_DELALLOC)
- clear_bits |= EXTENT_DELALLOC;
clear_extent_bit(tree, start, end, clear_bits, 1, 0, NULL, GFP_NOFS);
- if (!(op & (EXTENT_CLEAR_UNLOCK_PAGE | EXTENT_CLEAR_DIRTY |
- EXTENT_SET_WRITEBACK | EXTENT_END_WRITEBACK |
- EXTENT_SET_PRIVATE2)))
+ if (page_ops == 0)
return 0;
while (nr_pages > 0) {
@@ -1720,20 +1694,20 @@
nr_pages, ARRAY_SIZE(pages)), pages);
for (i = 0; i < ret; i++) {
- if (op & EXTENT_SET_PRIVATE2)
+ if (page_ops & PAGE_SET_PRIVATE2)
SetPagePrivate2(pages[i]);
if (pages[i] == locked_page) {
page_cache_release(pages[i]);
continue;
}
- if (op & EXTENT_CLEAR_DIRTY)
+ if (page_ops & PAGE_CLEAR_DIRTY)
clear_page_dirty_for_io(pages[i]);
- if (op & EXTENT_SET_WRITEBACK)
+ if (page_ops & PAGE_SET_WRITEBACK)
set_page_writeback(pages[i]);
- if (op & EXTENT_END_WRITEBACK)
+ if (page_ops & PAGE_END_WRITEBACK)
end_page_writeback(pages[i]);
- if (op & EXTENT_CLEAR_UNLOCK_PAGE)
+ if (page_ops & PAGE_UNLOCK)
unlock_page(pages[i]);
page_cache_release(pages[i]);
}
@@ -1810,7 +1784,7 @@
* set the private field for a given byte offset in the tree. If there isn't
* an extent_state there already, this does nothing.
*/
-int set_state_private(struct extent_io_tree *tree, u64 start, u64 private)
+static int set_state_private(struct extent_io_tree *tree, u64 start, u64 private)
{
struct rb_node *node;
struct extent_state *state;
@@ -1837,64 +1811,6 @@
return ret;
}
-void extent_cache_csums_dio(struct extent_io_tree *tree, u64 start, u32 csums[],
- int count)
-{
- struct rb_node *node;
- struct extent_state *state;
-
- spin_lock(&tree->lock);
- /*
- * this search will find all the extents that end after
- * our range starts.
- */
- node = tree_search(tree, start);
- BUG_ON(!node);
-
- state = rb_entry(node, struct extent_state, rb_node);
- BUG_ON(state->start != start);
-
- while (count) {
- state->private = *csums++;
- count--;
- state = next_state(state);
- }
- spin_unlock(&tree->lock);
-}
-
-static inline u64 __btrfs_get_bio_offset(struct bio *bio, int bio_index)
-{
- struct bio_vec *bvec = bio->bi_io_vec + bio_index;
-
- return page_offset(bvec->bv_page) + bvec->bv_offset;
-}
-
-void extent_cache_csums(struct extent_io_tree *tree, struct bio *bio, int bio_index,
- u32 csums[], int count)
-{
- struct rb_node *node;
- struct extent_state *state = NULL;
- u64 start;
-
- spin_lock(&tree->lock);
- do {
- start = __btrfs_get_bio_offset(bio, bio_index);
- if (state == NULL || state->start != start) {
- node = tree_search(tree, start);
- BUG_ON(!node);
-
- state = rb_entry(node, struct extent_state, rb_node);
- BUG_ON(state->start != start);
- }
- state->private = *csums++;
- count--;
- bio_index++;
-
- state = next_state(state);
- } while (count);
- spin_unlock(&tree->lock);
-}
-
int get_state_private(struct extent_io_tree *tree, u64 start, u64 *private)
{
struct rb_node *node;
@@ -2173,7 +2089,8 @@
EXTENT_LOCKED);
spin_unlock(&BTRFS_I(inode)->io_tree.lock);
- if (state && state->start == failrec->start) {
+ if (state && state->start <= failrec->start &&
+ state->end >= failrec->start + failrec->len - 1) {
fs_info = BTRFS_I(inode)->root->fs_info;
num_copies = btrfs_num_copies(fs_info, failrec->logical,
failrec->len);
@@ -2201,9 +2118,9 @@
* needed
*/
-static int bio_readpage_error(struct bio *failed_bio, struct page *page,
- u64 start, u64 end, int failed_mirror,
- struct extent_state *state)
+static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
+ struct page *page, u64 start, u64 end,
+ int failed_mirror)
{
struct io_failure_record *failrec = NULL;
u64 private;
@@ -2213,6 +2130,8 @@
struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
struct bio *bio;
+ struct btrfs_io_bio *btrfs_failed_bio;
+ struct btrfs_io_bio *btrfs_bio;
int num_copies;
int ret;
int read_mode;
@@ -2296,23 +2215,12 @@
* all the retry and error correction code that follows. no
* matter what the error is, it is very likely to persist.
*/
- pr_debug("bio_readpage_error: cannot repair, num_copies == 1. "
- "state=%p, num_copies=%d, next_mirror %d, "
- "failed_mirror %d\n", state, num_copies,
- failrec->this_mirror, failed_mirror);
+ pr_debug("bio_readpage_error: cannot repair, num_copies=%d, next_mirror %d, failed_mirror %d\n",
+ num_copies, failrec->this_mirror, failed_mirror);
free_io_failure(inode, failrec, 0);
return -EIO;
}
- if (!state) {
- spin_lock(&tree->lock);
- state = find_first_extent_bit_state(tree, failrec->start,
- EXTENT_LOCKED);
- if (state && state->start != failrec->start)
- state = NULL;
- spin_unlock(&tree->lock);
- }
-
/*
* there are two premises:
* a) deliver good data to the caller
@@ -2349,9 +2257,8 @@
read_mode = READ_SYNC;
}
- if (!state || failrec->this_mirror > num_copies) {
- pr_debug("bio_readpage_error: (fail) state=%p, num_copies=%d, "
- "next_mirror %d, failed_mirror %d\n", state,
+ if (failrec->this_mirror > num_copies) {
+ pr_debug("bio_readpage_error: (fail) num_copies=%d, next_mirror %d, failed_mirror %d\n",
num_copies, failrec->this_mirror, failed_mirror);
free_io_failure(inode, failrec, 0);
return -EIO;
@@ -2362,12 +2269,24 @@
free_io_failure(inode, failrec, 0);
return -EIO;
}
- bio->bi_private = state;
bio->bi_end_io = failed_bio->bi_end_io;
bio->bi_sector = failrec->logical >> 9;
bio->bi_bdev = BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev;
bio->bi_size = 0;
+ btrfs_failed_bio = btrfs_io_bio(failed_bio);
+ if (btrfs_failed_bio->csum) {
+ struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
+ u16 csum_size = btrfs_super_csum_size(fs_info->super_copy);
+
+ btrfs_bio = btrfs_io_bio(bio);
+ btrfs_bio->csum = btrfs_bio->csum_inline;
+ phy_offset >>= inode->i_sb->s_blocksize_bits;
+ phy_offset *= csum_size;
+ memcpy(btrfs_bio->csum, btrfs_failed_bio->csum + phy_offset,
+ csum_size);
+ }
+
bio_add_page(bio, page, failrec->len, start - page_offset(page));
pr_debug("bio_readpage_error: submitting new read[%#x] to "
@@ -2450,6 +2369,18 @@
bio_put(bio);
}
+static void
+endio_readpage_release_extent(struct extent_io_tree *tree, u64 start, u64 len,
+ int uptodate)
+{
+ struct extent_state *cached = NULL;
+ u64 end = start + len - 1;
+
+ if (uptodate && tree->track_uptodate)
+ set_extent_uptodate(tree, start, end, &cached, GFP_ATOMIC);
+ unlock_extent_cached(tree, start, end, &cached, GFP_ATOMIC);
+}
+
/*
* after a readpage IO is done, we need to:
* clear the uptodate bits on error
@@ -2466,9 +2397,14 @@
int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
struct bio_vec *bvec_end = bio->bi_io_vec + bio->bi_vcnt - 1;
struct bio_vec *bvec = bio->bi_io_vec;
+ struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
struct extent_io_tree *tree;
+ u64 offset = 0;
u64 start;
u64 end;
+ u64 len;
+ u64 extent_start = 0;
+ u64 extent_len = 0;
int mirror;
int ret;
@@ -2477,9 +2413,6 @@
do {
struct page *page = bvec->bv_page;
- struct extent_state *cached = NULL;
- struct extent_state *state;
- struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
struct inode *inode = page->mapping->host;
pr_debug("end_bio_extent_readpage: bi_sector=%llu, err=%d, "
@@ -2500,37 +2433,32 @@
start = page_offset(page);
end = start + bvec->bv_offset + bvec->bv_len - 1;
+ len = bvec->bv_len;
if (++bvec <= bvec_end)
prefetchw(&bvec->bv_page->flags);
- spin_lock(&tree->lock);
- state = find_first_extent_bit_state(tree, start, EXTENT_LOCKED);
- if (state && state->start == start) {
- /*
- * take a reference on the state, unlock will drop
- * the ref
- */
- cache_state(state, &cached);
- }
- spin_unlock(&tree->lock);
-
mirror = io_bio->mirror_num;
- if (uptodate && tree->ops && tree->ops->readpage_end_io_hook) {
- ret = tree->ops->readpage_end_io_hook(page, start, end,
- state, mirror);
+ if (likely(uptodate && tree->ops &&
+ tree->ops->readpage_end_io_hook)) {
+ ret = tree->ops->readpage_end_io_hook(io_bio, offset,
+ page, start, end,
+ mirror);
if (ret)
uptodate = 0;
else
clean_io_failure(start, page);
}
- if (!uptodate && tree->ops && tree->ops->readpage_io_failed_hook) {
+ if (likely(uptodate))
+ goto readpage_ok;
+
+ if (tree->ops && tree->ops->readpage_io_failed_hook) {
ret = tree->ops->readpage_io_failed_hook(page, mirror);
if (!ret && !err &&
test_bit(BIO_UPTODATE, &bio->bi_flags))
uptodate = 1;
- } else if (!uptodate) {
+ } else {
/*
* The generic bio_readpage_error handles errors the
* following way: If possible, new read requests are
@@ -2541,24 +2469,18 @@
* can't handle the error it will return -EIO and we
* remain responsible for that page.
*/
- ret = bio_readpage_error(bio, page, start, end, mirror, NULL);
+ ret = bio_readpage_error(bio, offset, page, start, end,
+ mirror);
if (ret == 0) {
uptodate =
test_bit(BIO_UPTODATE, &bio->bi_flags);
if (err)
uptodate = 0;
- uncache_state(&cached);
continue;
}
}
-
- if (uptodate && tree->track_uptodate) {
- set_extent_uptodate(tree, start, end, &cached,
- GFP_ATOMIC);
- }
- unlock_extent_cached(tree, start, end, &cached, GFP_ATOMIC);
-
- if (uptodate) {
+readpage_ok:
+ if (likely(uptodate)) {
loff_t i_size = i_size_read(inode);
pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
unsigned offset;
@@ -2573,8 +2495,36 @@
SetPageError(page);
}
unlock_page(page);
+ offset += len;
+
+ if (unlikely(!uptodate)) {
+ if (extent_len) {
+ endio_readpage_release_extent(tree,
+ extent_start,
+ extent_len, 1);
+ extent_start = 0;
+ extent_len = 0;
+ }
+ endio_readpage_release_extent(tree, start,
+ end - start + 1, 0);
+ } else if (!extent_len) {
+ extent_start = start;
+ extent_len = end + 1 - start;
+ } else if (extent_start + extent_len == start) {
+ extent_len += end + 1 - start;
+ } else {
+ endio_readpage_release_extent(tree, extent_start,
+ extent_len, uptodate);
+ extent_start = start;
+ extent_len = end + 1 - start;
+ }
} while (bvec <= bvec_end);
+ if (extent_len)
+ endio_readpage_release_extent(tree, extent_start, extent_len,
+ uptodate);
+ if (io_bio->end_io)
+ io_bio->end_io(io_bio, err);
bio_put(bio);
}
@@ -2586,6 +2536,7 @@
btrfs_bio_alloc(struct block_device *bdev, u64 first_sector, int nr_vecs,
gfp_t gfp_flags)
{
+ struct btrfs_io_bio *btrfs_bio;
struct bio *bio;
bio = bio_alloc_bioset(gfp_flags, nr_vecs, btrfs_bioset);
@@ -2601,6 +2552,10 @@
bio->bi_size = 0;
bio->bi_bdev = bdev;
bio->bi_sector = first_sector;
+ btrfs_bio = btrfs_io_bio(bio);
+ btrfs_bio->csum = NULL;
+ btrfs_bio->csum_allocated = NULL;
+ btrfs_bio->end_io = NULL;
}
return bio;
}
@@ -2614,7 +2569,17 @@
/* this also allocates from the btrfs_bioset */
struct bio *btrfs_io_bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs)
{
- return bio_alloc_bioset(gfp_mask, nr_iovecs, btrfs_bioset);
+ struct btrfs_io_bio *btrfs_bio;
+ struct bio *bio;
+
+ bio = bio_alloc_bioset(gfp_mask, nr_iovecs, btrfs_bioset);
+ if (bio) {
+ btrfs_bio = btrfs_io_bio(bio);
+ btrfs_bio->csum = NULL;
+ btrfs_bio->csum_allocated = NULL;
+ btrfs_bio->end_io = NULL;
+ }
+ return bio;
}
@@ -2738,17 +2703,45 @@
}
}
+static struct extent_map *
+__get_extent_map(struct inode *inode, struct page *page, size_t pg_offset,
+ u64 start, u64 len, get_extent_t *get_extent,
+ struct extent_map **em_cached)
+{
+ struct extent_map *em;
+
+ if (em_cached && *em_cached) {
+ em = *em_cached;
+ if (em->in_tree && start >= em->start &&
+ start < extent_map_end(em)) {
+ atomic_inc(&em->refs);
+ return em;
+ }
+
+ free_extent_map(em);
+ *em_cached = NULL;
+ }
+
+ em = get_extent(inode, page, pg_offset, start, len, 0);
+ if (em_cached && !IS_ERR_OR_NULL(em)) {
+ BUG_ON(*em_cached);
+ atomic_inc(&em->refs);
+ *em_cached = em;
+ }
+ return em;
+}
/*
* basic readpage implementation. Locked extent state structs are inserted
* into the tree that are removed when the IO is done (by the end_io
* handlers)
* XXX JDM: This needs looking at to ensure proper page locking
*/
-static int __extent_read_full_page(struct extent_io_tree *tree,
- struct page *page,
- get_extent_t *get_extent,
- struct bio **bio, int mirror_num,
- unsigned long *bio_flags, int rw)
+static int __do_readpage(struct extent_io_tree *tree,
+ struct page *page,
+ get_extent_t *get_extent,
+ struct extent_map **em_cached,
+ struct bio **bio, int mirror_num,
+ unsigned long *bio_flags, int rw)
{
struct inode *inode = page->mapping->host;
u64 start = page_offset(page);
@@ -2762,35 +2755,26 @@
sector_t sector;
struct extent_map *em;
struct block_device *bdev;
- struct btrfs_ordered_extent *ordered;
int ret;
int nr = 0;
+ int parent_locked = *bio_flags & EXTENT_BIO_PARENT_LOCKED;
size_t pg_offset = 0;
size_t iosize;
size_t disk_io_size;
size_t blocksize = inode->i_sb->s_blocksize;
- unsigned long this_bio_flag = 0;
+ unsigned long this_bio_flag = *bio_flags & EXTENT_BIO_PARENT_LOCKED;
set_page_extent_mapped(page);
+ end = page_end;
if (!PageUptodate(page)) {
if (cleancache_get_page(page) == 0) {
BUG_ON(blocksize != PAGE_SIZE);
+ unlock_extent(tree, start, end);
goto out;
}
}
- end = page_end;
- while (1) {
- lock_extent(tree, start, end);
- ordered = btrfs_lookup_ordered_extent(inode, start);
- if (!ordered)
- break;
- unlock_extent(tree, start, end);
- btrfs_start_ordered_extent(inode, ordered, 1);
- btrfs_put_ordered_extent(ordered);
- }
-
if (page->index == last_byte >> PAGE_CACHE_SHIFT) {
char *userpage;
size_t zero_offset = last_byte & (PAGE_CACHE_SIZE - 1);
@@ -2817,15 +2801,18 @@
kunmap_atomic(userpage);
set_extent_uptodate(tree, cur, cur + iosize - 1,
&cached, GFP_NOFS);
- unlock_extent_cached(tree, cur, cur + iosize - 1,
- &cached, GFP_NOFS);
+ if (!parent_locked)
+ unlock_extent_cached(tree, cur,
+ cur + iosize - 1,
+ &cached, GFP_NOFS);
break;
}
- em = get_extent(inode, page, pg_offset, cur,
- end - cur + 1, 0);
+ em = __get_extent_map(inode, page, pg_offset, cur,
+ end - cur + 1, get_extent, em_cached);
if (IS_ERR_OR_NULL(em)) {
SetPageError(page);
- unlock_extent(tree, cur, end);
+ if (!parent_locked)
+ unlock_extent(tree, cur, end);
break;
}
extent_offset = cur - em->start;
@@ -2833,7 +2820,7 @@
BUG_ON(end < cur);
if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) {
- this_bio_flag = EXTENT_BIO_COMPRESSED;
+ this_bio_flag |= EXTENT_BIO_COMPRESSED;
extent_set_compress_type(&this_bio_flag,
em->compress_type);
}
@@ -2877,7 +2864,8 @@
if (test_range_bit(tree, cur, cur_end,
EXTENT_UPTODATE, 1, NULL)) {
check_page_uptodate(tree, page);
- unlock_extent(tree, cur, cur + iosize - 1);
+ if (!parent_locked)
+ unlock_extent(tree, cur, cur + iosize - 1);
cur = cur + iosize;
pg_offset += iosize;
continue;
@@ -2887,7 +2875,8 @@
*/
if (block_start == EXTENT_MAP_INLINE) {
SetPageError(page);
- unlock_extent(tree, cur, cur + iosize - 1);
+ if (!parent_locked)
+ unlock_extent(tree, cur, cur + iosize - 1);
cur = cur + iosize;
pg_offset += iosize;
continue;
@@ -2905,7 +2894,8 @@
*bio_flags = this_bio_flag;
} else {
SetPageError(page);
- unlock_extent(tree, cur, cur + iosize - 1);
+ if (!parent_locked)
+ unlock_extent(tree, cur, cur + iosize - 1);
}
cur = cur + iosize;
pg_offset += iosize;
@@ -2919,6 +2909,104 @@
return 0;
}
+static inline void __do_contiguous_readpages(struct extent_io_tree *tree,
+ struct page *pages[], int nr_pages,
+ u64 start, u64 end,
+ get_extent_t *get_extent,
+ struct extent_map **em_cached,
+ struct bio **bio, int mirror_num,
+ unsigned long *bio_flags, int rw)
+{
+ struct inode *inode;
+ struct btrfs_ordered_extent *ordered;
+ int index;
+
+ inode = pages[0]->mapping->host;
+ while (1) {
+ lock_extent(tree, start, end);
+ ordered = btrfs_lookup_ordered_range(inode, start,
+ end - start + 1);
+ if (!ordered)
+ break;
+ unlock_extent(tree, start, end);
+ btrfs_start_ordered_extent(inode, ordered, 1);
+ btrfs_put_ordered_extent(ordered);
+ }
+
+ for (index = 0; index < nr_pages; index++) {
+ __do_readpage(tree, pages[index], get_extent, em_cached, bio,
+ mirror_num, bio_flags, rw);
+ page_cache_release(pages[index]);
+ }
+}
+
+static void __extent_readpages(struct extent_io_tree *tree,
+ struct page *pages[],
+ int nr_pages, get_extent_t *get_extent,
+ struct extent_map **em_cached,
+ struct bio **bio, int mirror_num,
+ unsigned long *bio_flags, int rw)
+{
+ u64 start = 0;
+ u64 end = 0;
+ u64 page_start;
+ int index;
+ int first_index = 0;
+
+ for (index = 0; index < nr_pages; index++) {
+ page_start = page_offset(pages[index]);
+ if (!end) {
+ start = page_start;
+ end = start + PAGE_CACHE_SIZE - 1;
+ first_index = index;
+ } else if (end + 1 == page_start) {
+ end += PAGE_CACHE_SIZE;
+ } else {
+ __do_contiguous_readpages(tree, &pages[first_index],
+ index - first_index, start,
+ end, get_extent, em_cached,
+ bio, mirror_num, bio_flags,
+ rw);
+ start = page_start;
+ end = start + PAGE_CACHE_SIZE - 1;
+ first_index = index;
+ }
+ }
+
+ if (end)
+ __do_contiguous_readpages(tree, &pages[first_index],
+ index - first_index, start,
+ end, get_extent, em_cached, bio,
+ mirror_num, bio_flags, rw);
+}
+
+static int __extent_read_full_page(struct extent_io_tree *tree,
+ struct page *page,
+ get_extent_t *get_extent,
+ struct bio **bio, int mirror_num,
+ unsigned long *bio_flags, int rw)
+{
+ struct inode *inode = page->mapping->host;
+ struct btrfs_ordered_extent *ordered;
+ u64 start = page_offset(page);
+ u64 end = start + PAGE_CACHE_SIZE - 1;
+ int ret;
+
+ while (1) {
+ lock_extent(tree, start, end);
+ ordered = btrfs_lookup_ordered_extent(inode, start);
+ if (!ordered)
+ break;
+ unlock_extent(tree, start, end);
+ btrfs_start_ordered_extent(inode, ordered, 1);
+ btrfs_put_ordered_extent(ordered);
+ }
+
+ ret = __do_readpage(tree, page, get_extent, NULL, bio, mirror_num,
+ bio_flags, rw);
+ return ret;
+}
+
int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
get_extent_t *get_extent, int mirror_num)
{
@@ -2933,6 +3021,20 @@
return ret;
}
+int extent_read_full_page_nolock(struct extent_io_tree *tree, struct page *page,
+ get_extent_t *get_extent, int mirror_num)
+{
+ struct bio *bio = NULL;
+ unsigned long bio_flags = EXTENT_BIO_PARENT_LOCKED;
+ int ret;
+
+ ret = __do_readpage(tree, page, get_extent, NULL, &bio, mirror_num,
+ &bio_flags, READ);
+ if (bio)
+ ret = submit_one_bio(READ, bio, mirror_num, bio_flags);
+ return ret;
+}
+
static noinline void update_nr_written(struct page *page,
struct writeback_control *wbc,
unsigned long nr_written)
@@ -3189,8 +3291,7 @@
if (!PageWriteback(page)) {
printk(KERN_ERR "btrfs warning page %lu not "
"writeback, cur %llu end %llu\n",
- page->index, (unsigned long long)cur,
- (unsigned long long)end);
+ page->index, cur, end);
}
ret = submit_extent_page(write_flags, tree, page,
@@ -3769,7 +3870,7 @@
unsigned long bio_flags = 0;
struct page *pagepool[16];
struct page *page;
- int i = 0;
+ struct extent_map *em_cached = NULL;
int nr = 0;
for (page_idx = 0; page_idx < nr_pages; page_idx++) {
@@ -3786,18 +3887,16 @@
pagepool[nr++] = page;
if (nr < ARRAY_SIZE(pagepool))
continue;
- for (i = 0; i < nr; i++) {
- __extent_read_full_page(tree, pagepool[i], get_extent,
- &bio, 0, &bio_flags, READ);
- page_cache_release(pagepool[i]);
- }
+ __extent_readpages(tree, pagepool, nr, get_extent, &em_cached,
+ &bio, 0, &bio_flags, READ);
nr = 0;
}
- for (i = 0; i < nr; i++) {
- __extent_read_full_page(tree, pagepool[i], get_extent,
- &bio, 0, &bio_flags, READ);
- page_cache_release(pagepool[i]);
- }
+ if (nr)
+ __extent_readpages(tree, pagepool, nr, get_extent, &em_cached,
+ &bio, 0, &bio_flags, READ);
+
+ if (em_cached)
+ free_extent_map(em_cached);
BUG_ON(!list_empty(pages));
if (bio)
@@ -4136,101 +4235,6 @@
kmem_cache_free(extent_buffer_cache, eb);
}
-static struct extent_buffer *__alloc_extent_buffer(struct extent_io_tree *tree,
- u64 start,
- unsigned long len,
- gfp_t mask)
-{
- struct extent_buffer *eb = NULL;
-
- eb = kmem_cache_zalloc(extent_buffer_cache, mask);
- if (eb == NULL)
- return NULL;
- eb->start = start;
- eb->len = len;
- eb->tree = tree;
- eb->bflags = 0;
- rwlock_init(&eb->lock);
- atomic_set(&eb->write_locks, 0);
- atomic_set(&eb->read_locks, 0);
- atomic_set(&eb->blocking_readers, 0);
- atomic_set(&eb->blocking_writers, 0);
- atomic_set(&eb->spinning_readers, 0);
- atomic_set(&eb->spinning_writers, 0);
- eb->lock_nested = 0;
- init_waitqueue_head(&eb->write_lock_wq);
- init_waitqueue_head(&eb->read_lock_wq);
-
- btrfs_leak_debug_add(&eb->leak_list, &buffers);
-
- spin_lock_init(&eb->refs_lock);
- atomic_set(&eb->refs, 1);
- atomic_set(&eb->io_pages, 0);
-
- /*
- * Sanity checks, currently the maximum is 64k covered by 16x 4k pages
- */
- BUILD_BUG_ON(BTRFS_MAX_METADATA_BLOCKSIZE
- > MAX_INLINE_EXTENT_BUFFER_SIZE);
- BUG_ON(len > MAX_INLINE_EXTENT_BUFFER_SIZE);
-
- return eb;
-}
-
-struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src)
-{
- unsigned long i;
- struct page *p;
- struct extent_buffer *new;
- unsigned long num_pages = num_extent_pages(src->start, src->len);
-
- new = __alloc_extent_buffer(NULL, src->start, src->len, GFP_ATOMIC);
- if (new == NULL)
- return NULL;
-
- for (i = 0; i < num_pages; i++) {
- p = alloc_page(GFP_ATOMIC);
- BUG_ON(!p);
- attach_extent_buffer_page(new, p);
- WARN_ON(PageDirty(p));
- SetPageUptodate(p);
- new->pages[i] = p;
- }
-
- copy_extent_buffer(new, src, 0, 0, src->len);
- set_bit(EXTENT_BUFFER_UPTODATE, &new->bflags);
- set_bit(EXTENT_BUFFER_DUMMY, &new->bflags);
-
- return new;
-}
-
-struct extent_buffer *alloc_dummy_extent_buffer(u64 start, unsigned long len)
-{
- struct extent_buffer *eb;
- unsigned long num_pages = num_extent_pages(0, len);
- unsigned long i;
-
- eb = __alloc_extent_buffer(NULL, start, len, GFP_ATOMIC);
- if (!eb)
- return NULL;
-
- for (i = 0; i < num_pages; i++) {
- eb->pages[i] = alloc_page(GFP_ATOMIC);
- if (!eb->pages[i])
- goto err;
- }
- set_extent_buffer_uptodate(eb);
- btrfs_set_header_nritems(eb, 0);
- set_bit(EXTENT_BUFFER_DUMMY, &eb->bflags);
-
- return eb;
-err:
- for (; i > 0; i--)
- __free_page(eb->pages[i - 1]);
- __free_extent_buffer(eb);
- return NULL;
-}
-
static int extent_buffer_under_io(struct extent_buffer *eb)
{
return (atomic_read(&eb->io_pages) ||
@@ -4301,6 +4305,104 @@
__free_extent_buffer(eb);
}
+static struct extent_buffer *__alloc_extent_buffer(struct extent_io_tree *tree,
+ u64 start,
+ unsigned long len,
+ gfp_t mask)
+{
+ struct extent_buffer *eb = NULL;
+
+ eb = kmem_cache_zalloc(extent_buffer_cache, mask);
+ if (eb == NULL)
+ return NULL;
+ eb->start = start;
+ eb->len = len;
+ eb->tree = tree;
+ eb->bflags = 0;
+ rwlock_init(&eb->lock);
+ atomic_set(&eb->write_locks, 0);
+ atomic_set(&eb->read_locks, 0);
+ atomic_set(&eb->blocking_readers, 0);
+ atomic_set(&eb->blocking_writers, 0);
+ atomic_set(&eb->spinning_readers, 0);
+ atomic_set(&eb->spinning_writers, 0);
+ eb->lock_nested = 0;
+ init_waitqueue_head(&eb->write_lock_wq);
+ init_waitqueue_head(&eb->read_lock_wq);
+
+ btrfs_leak_debug_add(&eb->leak_list, &buffers);
+
+ spin_lock_init(&eb->refs_lock);
+ atomic_set(&eb->refs, 1);
+ atomic_set(&eb->io_pages, 0);
+
+ /*
+ * Sanity checks, currently the maximum is 64k covered by 16x 4k pages
+ */
+ BUILD_BUG_ON(BTRFS_MAX_METADATA_BLOCKSIZE
+ > MAX_INLINE_EXTENT_BUFFER_SIZE);
+ BUG_ON(len > MAX_INLINE_EXTENT_BUFFER_SIZE);
+
+ return eb;
+}
+
+struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src)
+{
+ unsigned long i;
+ struct page *p;
+ struct extent_buffer *new;
+ unsigned long num_pages = num_extent_pages(src->start, src->len);
+
+ new = __alloc_extent_buffer(NULL, src->start, src->len, GFP_NOFS);
+ if (new == NULL)
+ return NULL;
+
+ for (i = 0; i < num_pages; i++) {
+ p = alloc_page(GFP_NOFS);
+ if (!p) {
+ btrfs_release_extent_buffer(new);
+ return NULL;
+ }
+ attach_extent_buffer_page(new, p);
+ WARN_ON(PageDirty(p));
+ SetPageUptodate(p);
+ new->pages[i] = p;
+ }
+
+ copy_extent_buffer(new, src, 0, 0, src->len);
+ set_bit(EXTENT_BUFFER_UPTODATE, &new->bflags);
+ set_bit(EXTENT_BUFFER_DUMMY, &new->bflags);
+
+ return new;
+}
+
+struct extent_buffer *alloc_dummy_extent_buffer(u64 start, unsigned long len)
+{
+ struct extent_buffer *eb;
+ unsigned long num_pages = num_extent_pages(0, len);
+ unsigned long i;
+
+ eb = __alloc_extent_buffer(NULL, start, len, GFP_NOFS);
+ if (!eb)
+ return NULL;
+
+ for (i = 0; i < num_pages; i++) {
+ eb->pages[i] = alloc_page(GFP_NOFS);
+ if (!eb->pages[i])
+ goto err;
+ }
+ set_extent_buffer_uptodate(eb);
+ btrfs_set_header_nritems(eb, 0);
+ set_bit(EXTENT_BUFFER_DUMMY, &eb->bflags);
+
+ return eb;
+err:
+ for (; i > 0; i--)
+ __free_page(eb->pages[i - 1]);
+ __free_extent_buffer(eb);
+ return NULL;
+}
+
static void check_buffer_tree_ref(struct extent_buffer *eb)
{
int refs;
@@ -4771,7 +4873,7 @@
WARN_ON(start > eb->len);
WARN_ON(start + len > eb->start + eb->len);
- offset = (start_offset + start) & ((unsigned long)PAGE_CACHE_SIZE - 1);
+ offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
while (len > 0) {
page = extent_buffer_page(eb, i);
@@ -4813,8 +4915,8 @@
if (start + min_len > eb->len) {
WARN(1, KERN_ERR "btrfs bad mapping eb start %llu len %lu, "
- "wanted %lu %lu\n", (unsigned long long)eb->start,
- eb->len, start, min_len);
+ "wanted %lu %lu\n",
+ eb->start, eb->len, start, min_len);
return -EINVAL;
}
@@ -4841,7 +4943,7 @@
WARN_ON(start > eb->len);
WARN_ON(start + len > eb->start + eb->len);
- offset = (start_offset + start) & ((unsigned long)PAGE_CACHE_SIZE - 1);
+ offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
while (len > 0) {
page = extent_buffer_page(eb, i);
@@ -4875,7 +4977,7 @@
WARN_ON(start > eb->len);
WARN_ON(start + len > eb->start + eb->len);
- offset = (start_offset + start) & ((unsigned long)PAGE_CACHE_SIZE - 1);
+ offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
while (len > 0) {
page = extent_buffer_page(eb, i);
@@ -4905,7 +5007,7 @@
WARN_ON(start > eb->len);
WARN_ON(start + len > eb->start + eb->len);
- offset = (start_offset + start) & ((unsigned long)PAGE_CACHE_SIZE - 1);
+ offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
while (len > 0) {
page = extent_buffer_page(eb, i);
@@ -4936,7 +5038,7 @@
WARN_ON(src->len != dst_len);
offset = (start_offset + dst_offset) &
- ((unsigned long)PAGE_CACHE_SIZE - 1);
+ (PAGE_CACHE_SIZE - 1);
while (len > 0) {
page = extent_buffer_page(dst, i);
@@ -5022,9 +5124,9 @@
while (len > 0) {
dst_off_in_page = (start_offset + dst_offset) &
- ((unsigned long)PAGE_CACHE_SIZE - 1);
+ (PAGE_CACHE_SIZE - 1);
src_off_in_page = (start_offset + src_offset) &
- ((unsigned long)PAGE_CACHE_SIZE - 1);
+ (PAGE_CACHE_SIZE - 1);
dst_i = (start_offset + dst_offset) >> PAGE_CACHE_SHIFT;
src_i = (start_offset + src_offset) >> PAGE_CACHE_SHIFT;
@@ -5075,9 +5177,9 @@
src_i = (start_offset + src_end) >> PAGE_CACHE_SHIFT;
dst_off_in_page = (start_offset + dst_end) &
- ((unsigned long)PAGE_CACHE_SIZE - 1);
+ (PAGE_CACHE_SIZE - 1);
src_off_in_page = (start_offset + src_end) &
- ((unsigned long)PAGE_CACHE_SIZE - 1);
+ (PAGE_CACHE_SIZE - 1);
cur = min_t(unsigned long, len, src_off_in_page + 1);
cur = min(cur, dst_off_in_page + 1);
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 3b8c4e2..6dbc645 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -29,6 +29,7 @@
*/
#define EXTENT_BIO_COMPRESSED 1
#define EXTENT_BIO_TREE_LOG 2
+#define EXTENT_BIO_PARENT_LOCKED 4
#define EXTENT_BIO_FLAG_SHIFT 16
/* these are bit numbers for test/set bit */
@@ -44,14 +45,11 @@
#define EXTENT_BUFFER_DUMMY 9
/* these are flags for extent_clear_unlock_delalloc */
-#define EXTENT_CLEAR_UNLOCK_PAGE 0x1
-#define EXTENT_CLEAR_UNLOCK 0x2
-#define EXTENT_CLEAR_DELALLOC 0x4
-#define EXTENT_CLEAR_DIRTY 0x8
-#define EXTENT_SET_WRITEBACK 0x10
-#define EXTENT_END_WRITEBACK 0x20
-#define EXTENT_SET_PRIVATE2 0x40
-#define EXTENT_CLEAR_ACCOUNTING 0x80
+#define PAGE_UNLOCK (1 << 0)
+#define PAGE_CLEAR_DIRTY (1 << 1)
+#define PAGE_SET_WRITEBACK (1 << 2)
+#define PAGE_END_WRITEBACK (1 << 3)
+#define PAGE_SET_PRIVATE2 (1 << 4)
/*
* page->private values. Every page that is controlled by the extent
@@ -62,6 +60,7 @@
struct extent_state;
struct btrfs_root;
+struct btrfs_io_bio;
typedef int (extent_submit_bio_hook_t)(struct inode *inode, int rw,
struct bio *bio, int mirror_num,
@@ -77,8 +76,9 @@
size_t size, struct bio *bio,
unsigned long bio_flags);
int (*readpage_io_failed_hook)(struct page *page, int failed_mirror);
- int (*readpage_end_io_hook)(struct page *page, u64 start, u64 end,
- struct extent_state *state, int mirror);
+ int (*readpage_end_io_hook)(struct btrfs_io_bio *io_bio, u64 phy_offset,
+ struct page *page, u64 start, u64 end,
+ int mirror);
int (*writepage_end_io_hook)(struct page *page, u64 start, u64 end,
struct extent_state *state, int uptodate);
void (*set_bit_hook)(struct inode *inode, struct extent_state *state,
@@ -200,6 +200,8 @@
int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end);
int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
get_extent_t *get_extent, int mirror_num);
+int extent_read_full_page_nolock(struct extent_io_tree *tree, struct page *page,
+ get_extent_t *get_extent, int mirror_num);
int __init extent_io_init(void);
void extent_io_exit(void);
@@ -261,11 +263,6 @@
get_extent_t get_extent);
int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len, get_extent_t *get_extent);
-int set_state_private(struct extent_io_tree *tree, u64 start, u64 private);
-void extent_cache_csums_dio(struct extent_io_tree *tree, u64 start, u32 csums[],
- int count);
-void extent_cache_csums(struct extent_io_tree *tree, struct bio *bio,
- int bvec_index, u32 csums[], int count);
int get_state_private(struct extent_io_tree *tree, u64 start, u64 *private);
void set_page_extent_mapped(struct page *page);
@@ -330,10 +327,10 @@
unsigned long *map_len);
int extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end);
int extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end);
-int extent_clear_unlock_delalloc(struct inode *inode,
- struct extent_io_tree *tree,
- u64 start, u64 end, struct page *locked_page,
- unsigned long op);
+int extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
+ struct page *locked_page,
+ unsigned long bits_to_clear,
+ unsigned long page_ops);
struct bio *
btrfs_bio_alloc(struct block_device *bdev, u64 first_sector, int nr_vecs,
gfp_t gfp_flags);
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index a7bfc95..4f53159 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -23,6 +23,7 @@
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
+#include "volumes.h"
#include "print-tree.h"
#define __MAX_CSUM_ITEMS(r, size) ((unsigned long)(((BTRFS_LEAF_DATA_SIZE(r) - \
@@ -152,28 +153,54 @@
return ret;
}
+static void btrfs_io_bio_endio_readpage(struct btrfs_io_bio *bio, int err)
+{
+ kfree(bio->csum_allocated);
+}
+
static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
struct inode *inode, struct bio *bio,
u64 logical_offset, u32 *dst, int dio)
{
- u32 sum[16];
- int len;
struct bio_vec *bvec = bio->bi_io_vec;
- int bio_index = 0;
+ struct btrfs_io_bio *btrfs_bio = btrfs_io_bio(bio);
+ struct btrfs_csum_item *item = NULL;
+ struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
+ struct btrfs_path *path;
+ u8 *csum;
u64 offset = 0;
u64 item_start_offset = 0;
u64 item_last_offset = 0;
u64 disk_bytenr;
u32 diff;
- u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy);
+ int nblocks;
+ int bio_index = 0;
int count;
- struct btrfs_path *path;
- struct btrfs_csum_item *item = NULL;
- struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
+ u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy);
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
+
+ nblocks = bio->bi_size >> inode->i_sb->s_blocksize_bits;
+ if (!dst) {
+ if (nblocks * csum_size > BTRFS_BIO_INLINE_CSUM_SIZE) {
+ btrfs_bio->csum_allocated = kmalloc(nblocks * csum_size,
+ GFP_NOFS);
+ if (!btrfs_bio->csum_allocated) {
+ btrfs_free_path(path);
+ return -ENOMEM;
+ }
+ btrfs_bio->csum = btrfs_bio->csum_allocated;
+ btrfs_bio->end_io = btrfs_io_bio_endio_readpage;
+ } else {
+ btrfs_bio->csum = btrfs_bio->csum_inline;
+ }
+ csum = btrfs_bio->csum;
+ } else {
+ csum = (u8 *)dst;
+ }
+
if (bio->bi_size > PAGE_CACHE_SIZE * 8)
path->reada = 2;
@@ -194,11 +221,10 @@
if (dio)
offset = logical_offset;
while (bio_index < bio->bi_vcnt) {
- len = min_t(int, ARRAY_SIZE(sum), bio->bi_vcnt - bio_index);
if (!dio)
offset = page_offset(bvec->bv_page) + bvec->bv_offset;
- count = btrfs_find_ordered_sum(inode, offset, disk_bytenr, sum,
- len);
+ count = btrfs_find_ordered_sum(inode, offset, disk_bytenr,
+ (u32 *)csum, nblocks);
if (count)
goto found;
@@ -213,7 +239,7 @@
path, disk_bytenr, 0);
if (IS_ERR(item)) {
count = 1;
- sum[0] = 0;
+ memset(csum, 0, csum_size);
if (BTRFS_I(inode)->root->root_key.objectid ==
BTRFS_DATA_RELOC_TREE_OBJECTID) {
set_extent_bits(io_tree, offset,
@@ -222,9 +248,7 @@
} else {
printk(KERN_INFO "btrfs no csum found "
"for inode %llu start %llu\n",
- (unsigned long long)
- btrfs_ino(inode),
- (unsigned long long)offset);
+ btrfs_ino(inode), offset);
}
item = NULL;
btrfs_release_path(path);
@@ -249,23 +273,14 @@
diff = disk_bytenr - item_start_offset;
diff = diff / root->sectorsize;
diff = diff * csum_size;
- count = min_t(int, len, (item_last_offset - disk_bytenr) >>
- inode->i_sb->s_blocksize_bits);
- read_extent_buffer(path->nodes[0], sum,
+ count = min_t(int, nblocks, (item_last_offset - disk_bytenr) >>
+ inode->i_sb->s_blocksize_bits);
+ read_extent_buffer(path->nodes[0], csum,
((unsigned long)item) + diff,
csum_size * count);
found:
- if (dst) {
- memcpy(dst, sum, count * csum_size);
- dst += count;
- } else {
- if (dio)
- extent_cache_csums_dio(io_tree, offset, sum,
- count);
- else
- extent_cache_csums(io_tree, bio, bio_index, sum,
- count);
- }
+ csum += count * csum_size;
+ nblocks -= count;
while (count--) {
disk_bytenr += bvec->bv_len;
offset += bvec->bv_len;
@@ -284,9 +299,19 @@
}
int btrfs_lookup_bio_sums_dio(struct btrfs_root *root, struct inode *inode,
- struct bio *bio, u64 offset)
+ struct btrfs_dio_private *dip, struct bio *bio,
+ u64 offset)
{
- return __btrfs_lookup_bio_sums(root, inode, bio, offset, NULL, 1);
+ int len = (bio->bi_sector << 9) - dip->disk_bytenr;
+ u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy);
+ int ret;
+
+ len >>= inode->i_sb->s_blocksize_bits;
+ len *= csum_size;
+
+ ret = __btrfs_lookup_bio_sums(root, inode, bio, offset,
+ (u32 *)(dip->csum + len), 1);
+ return ret;
}
int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 4d2eb64..bc5072b 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1334,7 +1334,6 @@
static noinline int check_can_nocow(struct inode *inode, loff_t pos,
size_t *write_bytes)
{
- struct btrfs_trans_handle *trans;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_ordered_extent *ordered;
u64 lockstart, lockend;
@@ -1356,16 +1355,8 @@
btrfs_put_ordered_extent(ordered);
}
- trans = btrfs_join_transaction(root);
- if (IS_ERR(trans)) {
- unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend);
- return PTR_ERR(trans);
- }
-
num_bytes = lockend - lockstart + 1;
- ret = can_nocow_extent(trans, inode, lockstart, &num_bytes, NULL, NULL,
- NULL);
- btrfs_end_transaction(trans, root);
+ ret = can_nocow_extent(inode, lockstart, &num_bytes, NULL, NULL, NULL);
if (ret <= 0) {
ret = 0;
} else {
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index b21a3cd..3f0ddfc 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -221,12 +221,10 @@
struct btrfs_path *path,
struct inode *inode)
{
- loff_t oldsize;
int ret = 0;
- oldsize = i_size_read(inode);
btrfs_i_size_write(inode, 0);
- truncate_pagecache(inode, oldsize, 0);
+ truncate_pagecache(inode, 0);
/*
* We don't need an orphan item because truncating the free space cache
@@ -308,7 +306,7 @@
static void io_ctl_map_page(struct io_ctl *io_ctl, int clear)
{
- BUG_ON(io_ctl->index >= io_ctl->num_pages);
+ ASSERT(io_ctl->index < io_ctl->num_pages);
io_ctl->page = io_ctl->pages[io_ctl->index++];
io_ctl->cur = kmap(io_ctl->page);
io_ctl->orig = io_ctl->cur;
@@ -673,8 +671,7 @@
btrfs_err(root->fs_info,
"free space inode generation (%llu) "
"did not match free space cache generation (%llu)",
- (unsigned long long)BTRFS_I(inode)->generation,
- (unsigned long long)generation);
+ BTRFS_I(inode)->generation, generation);
return 0;
}
@@ -729,7 +726,7 @@
goto free_cache;
}
} else {
- BUG_ON(!num_bitmaps);
+ ASSERT(num_bitmaps);
num_bitmaps--;
e->bitmap = kzalloc(PAGE_CACHE_SIZE, GFP_NOFS);
if (!e->bitmap) {
@@ -1029,7 +1026,7 @@
leaf = path->nodes[0];
if (ret > 0) {
struct btrfs_key found_key;
- BUG_ON(!path->slots[0]);
+ ASSERT(path->slots[0]);
path->slots[0]--;
btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
if (found_key.objectid != BTRFS_FREE_SPACE_OBJECTID ||
@@ -1117,7 +1114,7 @@
static inline unsigned long offset_to_bit(u64 bitmap_start, u32 unit,
u64 offset)
{
- BUG_ON(offset < bitmap_start);
+ ASSERT(offset >= bitmap_start);
offset -= bitmap_start;
return (unsigned long)(div_u64(offset, unit));
}
@@ -1272,7 +1269,7 @@
if (n) {
entry = rb_entry(n, struct btrfs_free_space,
offset_index);
- BUG_ON(entry->offset > offset);
+ ASSERT(entry->offset <= offset);
} else {
if (fuzzy)
return entry;
@@ -1336,7 +1333,7 @@
{
int ret = 0;
- BUG_ON(!info->bitmap && !info->bytes);
+ ASSERT(info->bytes || info->bitmap);
ret = tree_insert_offset(&ctl->free_space_offset, info->offset,
&info->offset_index, (info->bitmap != NULL));
if (ret)
@@ -1359,7 +1356,7 @@
max_bitmaps = max(max_bitmaps, 1);
- BUG_ON(ctl->total_bitmaps > max_bitmaps);
+ ASSERT(ctl->total_bitmaps <= max_bitmaps);
/*
* The goal is to keep the total amount of memory used per 1gb of space
@@ -1403,7 +1400,7 @@
start = offset_to_bit(info->offset, ctl->unit, offset);
count = bytes_to_bits(bytes, ctl->unit);
- BUG_ON(start + count > BITS_PER_BITMAP);
+ ASSERT(start + count <= BITS_PER_BITMAP);
bitmap_clear(info->bitmap, start, count);
@@ -1426,7 +1423,7 @@
start = offset_to_bit(info->offset, ctl->unit, offset);
count = bytes_to_bits(bytes, ctl->unit);
- BUG_ON(start + count > BITS_PER_BITMAP);
+ ASSERT(start + count <= BITS_PER_BITMAP);
bitmap_set(info->bitmap, start, count);
@@ -1742,7 +1739,7 @@
bitmap_info = tree_search_offset(ctl, offset_to_bitmap(ctl, offset),
1, 0);
if (!bitmap_info) {
- BUG_ON(added);
+ ASSERT(added == 0);
goto new_bitmap;
}
@@ -1882,7 +1879,7 @@
if (ret) {
printk(KERN_CRIT "btrfs: unable to add free space :%d\n", ret);
- BUG_ON(ret == -EEXIST);
+ ASSERT(ret != -EEXIST);
}
return ret;
@@ -1991,8 +1988,7 @@
if (info->bytes >= bytes && !block_group->ro)
count++;
printk(KERN_CRIT "entry offset %llu, bytes %llu, bitmap %s\n",
- (unsigned long long)info->offset,
- (unsigned long long)info->bytes,
+ info->offset, info->bytes,
(info->bitmap) ? "yes" : "no");
}
printk(KERN_INFO "block group has cluster?: %s\n",
@@ -2371,7 +2367,7 @@
rb_erase(&entry->offset_index, &ctl->free_space_offset);
ret = tree_insert_offset(&cluster->root, entry->offset,
&entry->offset_index, 1);
- BUG_ON(ret); /* -EEXIST; Logic error */
+ ASSERT(!ret); /* -EEXIST; Logic error */
trace_btrfs_setup_cluster(block_group, cluster,
total_found * ctl->unit, 1);
@@ -2464,7 +2460,7 @@
ret = tree_insert_offset(&cluster->root, entry->offset,
&entry->offset_index, 0);
total_size += entry->bytes;
- BUG_ON(ret); /* -EEXIST; Logic error */
+ ASSERT(!ret); /* -EEXIST; Logic error */
} while (node && entry != last);
cluster->max_size = max_extent;
@@ -2525,8 +2521,7 @@
* returns zero and sets up cluster if things worked out, otherwise
* it returns -enospc
*/
-int btrfs_find_space_cluster(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
+int btrfs_find_space_cluster(struct btrfs_root *root,
struct btrfs_block_group_cache *block_group,
struct btrfs_free_cluster *cluster,
u64 offset, u64 bytes, u64 empty_size)
@@ -2856,7 +2851,7 @@
ret = search_bitmap(ctl, entry, &offset, &count);
/* Logic error; Should be empty if it can't find anything */
- BUG_ON(ret);
+ ASSERT(!ret);
ino = offset;
bitmap_clear_bits(ctl, entry, offset, 1);
@@ -2973,33 +2968,68 @@
}
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
-static struct btrfs_block_group_cache *init_test_block_group(void)
+/*
+ * Use this if you need to make a bitmap or extent entry specifically, it
+ * doesn't do any of the merging that add_free_space does, this acts a lot like
+ * how the free space cache loading stuff works, so you can get really weird
+ * configurations.
+ */
+int test_add_free_space_entry(struct btrfs_block_group_cache *cache,
+ u64 offset, u64 bytes, bool bitmap)
{
- struct btrfs_block_group_cache *cache;
+ struct btrfs_free_space_ctl *ctl = cache->free_space_ctl;
+ struct btrfs_free_space *info = NULL, *bitmap_info;
+ void *map = NULL;
+ u64 bytes_added;
+ int ret;
- cache = kzalloc(sizeof(*cache), GFP_NOFS);
- if (!cache)
- return NULL;
- cache->free_space_ctl = kzalloc(sizeof(*cache->free_space_ctl),
- GFP_NOFS);
- if (!cache->free_space_ctl) {
- kfree(cache);
- return NULL;
+again:
+ if (!info) {
+ info = kmem_cache_zalloc(btrfs_free_space_cachep, GFP_NOFS);
+ if (!info)
+ return -ENOMEM;
}
- cache->key.objectid = 0;
- cache->key.offset = 1024 * 1024 * 1024;
- cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
- cache->sectorsize = 4096;
+ if (!bitmap) {
+ spin_lock(&ctl->tree_lock);
+ info->offset = offset;
+ info->bytes = bytes;
+ ret = link_free_space(ctl, info);
+ spin_unlock(&ctl->tree_lock);
+ if (ret)
+ kmem_cache_free(btrfs_free_space_cachep, info);
+ return ret;
+ }
- spin_lock_init(&cache->lock);
- INIT_LIST_HEAD(&cache->list);
- INIT_LIST_HEAD(&cache->cluster_list);
- INIT_LIST_HEAD(&cache->new_bg_list);
+ if (!map) {
+ map = kzalloc(PAGE_CACHE_SIZE, GFP_NOFS);
+ if (!map) {
+ kmem_cache_free(btrfs_free_space_cachep, info);
+ return -ENOMEM;
+ }
+ }
- btrfs_init_free_space_ctl(cache);
+ spin_lock(&ctl->tree_lock);
+ bitmap_info = tree_search_offset(ctl, offset_to_bitmap(ctl, offset),
+ 1, 0);
+ if (!bitmap_info) {
+ info->bitmap = map;
+ map = NULL;
+ add_new_bitmap(ctl, info, offset);
+ bitmap_info = info;
+ }
- return cache;
+ bytes_added = add_bytes_to_bitmap(ctl, bitmap_info, offset, bytes);
+ bytes -= bytes_added;
+ offset += bytes_added;
+ spin_unlock(&ctl->tree_lock);
+
+ if (bytes)
+ goto again;
+
+ if (map)
+ kfree(map);
+ return 0;
}
/*
@@ -3007,8 +3037,8 @@
* just used to check the absence of space, so if there is free space in the
* range at all we will return 1.
*/
-static int check_exists(struct btrfs_block_group_cache *cache, u64 offset,
- u64 bytes)
+int test_check_exists(struct btrfs_block_group_cache *cache,
+ u64 offset, u64 bytes)
{
struct btrfs_free_space_ctl *ctl = cache->free_space_ctl;
struct btrfs_free_space *info;
@@ -3085,411 +3115,4 @@
spin_unlock(&ctl->tree_lock);
return ret;
}
-
-/*
- * Use this if you need to make a bitmap or extent entry specifically, it
- * doesn't do any of the merging that add_free_space does, this acts a lot like
- * how the free space cache loading stuff works, so you can get really weird
- * configurations.
- */
-static int add_free_space_entry(struct btrfs_block_group_cache *cache,
- u64 offset, u64 bytes, bool bitmap)
-{
- struct btrfs_free_space_ctl *ctl = cache->free_space_ctl;
- struct btrfs_free_space *info = NULL, *bitmap_info;
- void *map = NULL;
- u64 bytes_added;
- int ret;
-
-again:
- if (!info) {
- info = kmem_cache_zalloc(btrfs_free_space_cachep, GFP_NOFS);
- if (!info)
- return -ENOMEM;
- }
-
- if (!bitmap) {
- spin_lock(&ctl->tree_lock);
- info->offset = offset;
- info->bytes = bytes;
- ret = link_free_space(ctl, info);
- spin_unlock(&ctl->tree_lock);
- if (ret)
- kmem_cache_free(btrfs_free_space_cachep, info);
- return ret;
- }
-
- if (!map) {
- map = kzalloc(PAGE_CACHE_SIZE, GFP_NOFS);
- if (!map) {
- kmem_cache_free(btrfs_free_space_cachep, info);
- return -ENOMEM;
- }
- }
-
- spin_lock(&ctl->tree_lock);
- bitmap_info = tree_search_offset(ctl, offset_to_bitmap(ctl, offset),
- 1, 0);
- if (!bitmap_info) {
- info->bitmap = map;
- map = NULL;
- add_new_bitmap(ctl, info, offset);
- bitmap_info = info;
- }
-
- bytes_added = add_bytes_to_bitmap(ctl, bitmap_info, offset, bytes);
- bytes -= bytes_added;
- offset += bytes_added;
- spin_unlock(&ctl->tree_lock);
-
- if (bytes)
- goto again;
-
- if (map)
- kfree(map);
- return 0;
-}
-
-#define test_msg(fmt, ...) printk(KERN_INFO "btrfs: selftest: " fmt, ##__VA_ARGS__)
-
-/*
- * This test just does basic sanity checking, making sure we can add an exten
- * entry and remove space from either end and the middle, and make sure we can
- * remove space that covers adjacent extent entries.
- */
-static int test_extents(struct btrfs_block_group_cache *cache)
-{
- int ret = 0;
-
- test_msg("Running extent only tests\n");
-
- /* First just make sure we can remove an entire entry */
- ret = btrfs_add_free_space(cache, 0, 4 * 1024 * 1024);
- if (ret) {
- test_msg("Error adding initial extents %d\n", ret);
- return ret;
- }
-
- ret = btrfs_remove_free_space(cache, 0, 4 * 1024 * 1024);
- if (ret) {
- test_msg("Error removing extent %d\n", ret);
- return ret;
- }
-
- if (check_exists(cache, 0, 4 * 1024 * 1024)) {
- test_msg("Full remove left some lingering space\n");
- return -1;
- }
-
- /* Ok edge and middle cases now */
- ret = btrfs_add_free_space(cache, 0, 4 * 1024 * 1024);
- if (ret) {
- test_msg("Error adding half extent %d\n", ret);
- return ret;
- }
-
- ret = btrfs_remove_free_space(cache, 3 * 1024 * 1024, 1 * 1024 * 1024);
- if (ret) {
- test_msg("Error removing tail end %d\n", ret);
- return ret;
- }
-
- ret = btrfs_remove_free_space(cache, 0, 1 * 1024 * 1024);
- if (ret) {
- test_msg("Error removing front end %d\n", ret);
- return ret;
- }
-
- ret = btrfs_remove_free_space(cache, 2 * 1024 * 1024, 4096);
- if (ret) {
- test_msg("Error removing middle piece %d\n", ret);
- return ret;
- }
-
- if (check_exists(cache, 0, 1 * 1024 * 1024)) {
- test_msg("Still have space at the front\n");
- return -1;
- }
-
- if (check_exists(cache, 2 * 1024 * 1024, 4096)) {
- test_msg("Still have space in the middle\n");
- return -1;
- }
-
- if (check_exists(cache, 3 * 1024 * 1024, 1 * 1024 * 1024)) {
- test_msg("Still have space at the end\n");
- return -1;
- }
-
- /* Cleanup */
- __btrfs_remove_free_space_cache(cache->free_space_ctl);
-
- return 0;
-}
-
-static int test_bitmaps(struct btrfs_block_group_cache *cache)
-{
- u64 next_bitmap_offset;
- int ret;
-
- test_msg("Running bitmap only tests\n");
-
- ret = add_free_space_entry(cache, 0, 4 * 1024 * 1024, 1);
- if (ret) {
- test_msg("Couldn't create a bitmap entry %d\n", ret);
- return ret;
- }
-
- ret = btrfs_remove_free_space(cache, 0, 4 * 1024 * 1024);
- if (ret) {
- test_msg("Error removing bitmap full range %d\n", ret);
- return ret;
- }
-
- if (check_exists(cache, 0, 4 * 1024 * 1024)) {
- test_msg("Left some space in bitmap\n");
- return -1;
- }
-
- ret = add_free_space_entry(cache, 0, 4 * 1024 * 1024, 1);
- if (ret) {
- test_msg("Couldn't add to our bitmap entry %d\n", ret);
- return ret;
- }
-
- ret = btrfs_remove_free_space(cache, 1 * 1024 * 1024, 2 * 1024 * 1024);
- if (ret) {
- test_msg("Couldn't remove middle chunk %d\n", ret);
- return ret;
- }
-
- /*
- * The first bitmap we have starts at offset 0 so the next one is just
- * at the end of the first bitmap.
- */
- next_bitmap_offset = (u64)(BITS_PER_BITMAP * 4096);
-
- /* Test a bit straddling two bitmaps */
- ret = add_free_space_entry(cache, next_bitmap_offset -
- (2 * 1024 * 1024), 4 * 1024 * 1024, 1);
- if (ret) {
- test_msg("Couldn't add space that straddles two bitmaps %d\n",
- ret);
- return ret;
- }
-
- ret = btrfs_remove_free_space(cache, next_bitmap_offset -
- (1 * 1024 * 1024), 2 * 1024 * 1024);
- if (ret) {
- test_msg("Couldn't remove overlapping space %d\n", ret);
- return ret;
- }
-
- if (check_exists(cache, next_bitmap_offset - (1 * 1024 * 1024),
- 2 * 1024 * 1024)) {
- test_msg("Left some space when removing overlapping\n");
- return -1;
- }
-
- __btrfs_remove_free_space_cache(cache->free_space_ctl);
-
- return 0;
-}
-
-/* This is the high grade jackassery */
-static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache)
-{
- u64 bitmap_offset = (u64)(BITS_PER_BITMAP * 4096);
- int ret;
-
- test_msg("Running bitmap and extent tests\n");
-
- /*
- * First let's do something simple, an extent at the same offset as the
- * bitmap, but the free space completely in the extent and then
- * completely in the bitmap.
- */
- ret = add_free_space_entry(cache, 4 * 1024 * 1024, 1 * 1024 * 1024, 1);
- if (ret) {
- test_msg("Couldn't create bitmap entry %d\n", ret);
- return ret;
- }
-
- ret = add_free_space_entry(cache, 0, 1 * 1024 * 1024, 0);
- if (ret) {
- test_msg("Couldn't add extent entry %d\n", ret);
- return ret;
- }
-
- ret = btrfs_remove_free_space(cache, 0, 1 * 1024 * 1024);
- if (ret) {
- test_msg("Couldn't remove extent entry %d\n", ret);
- return ret;
- }
-
- if (check_exists(cache, 0, 1 * 1024 * 1024)) {
- test_msg("Left remnants after our remove\n");
- return -1;
- }
-
- /* Now to add back the extent entry and remove from the bitmap */
- ret = add_free_space_entry(cache, 0, 1 * 1024 * 1024, 0);
- if (ret) {
- test_msg("Couldn't re-add extent entry %d\n", ret);
- return ret;
- }
-
- ret = btrfs_remove_free_space(cache, 4 * 1024 * 1024, 1 * 1024 * 1024);
- if (ret) {
- test_msg("Couldn't remove from bitmap %d\n", ret);
- return ret;
- }
-
- if (check_exists(cache, 4 * 1024 * 1024, 1 * 1024 * 1024)) {
- test_msg("Left remnants in the bitmap\n");
- return -1;
- }
-
- /*
- * Ok so a little more evil, extent entry and bitmap at the same offset,
- * removing an overlapping chunk.
- */
- ret = add_free_space_entry(cache, 1 * 1024 * 1024, 4 * 1024 * 1024, 1);
- if (ret) {
- test_msg("Couldn't add to a bitmap %d\n", ret);
- return ret;
- }
-
- ret = btrfs_remove_free_space(cache, 512 * 1024, 3 * 1024 * 1024);
- if (ret) {
- test_msg("Couldn't remove overlapping space %d\n", ret);
- return ret;
- }
-
- if (check_exists(cache, 512 * 1024, 3 * 1024 * 1024)) {
- test_msg("Left over peices after removing overlapping\n");
- return -1;
- }
-
- __btrfs_remove_free_space_cache(cache->free_space_ctl);
-
- /* Now with the extent entry offset into the bitmap */
- ret = add_free_space_entry(cache, 4 * 1024 * 1024, 4 * 1024 * 1024, 1);
- if (ret) {
- test_msg("Couldn't add space to the bitmap %d\n", ret);
- return ret;
- }
-
- ret = add_free_space_entry(cache, 2 * 1024 * 1024, 2 * 1024 * 1024, 0);
- if (ret) {
- test_msg("Couldn't add extent to the cache %d\n", ret);
- return ret;
- }
-
- ret = btrfs_remove_free_space(cache, 3 * 1024 * 1024, 4 * 1024 * 1024);
- if (ret) {
- test_msg("Problem removing overlapping space %d\n", ret);
- return ret;
- }
-
- if (check_exists(cache, 3 * 1024 * 1024, 4 * 1024 * 1024)) {
- test_msg("Left something behind when removing space");
- return -1;
- }
-
- /*
- * This has blown up in the past, the extent entry starts before the
- * bitmap entry, but we're trying to remove an offset that falls
- * completely within the bitmap range and is in both the extent entry
- * and the bitmap entry, looks like this
- *
- * [ extent ]
- * [ bitmap ]
- * [ del ]
- */
- __btrfs_remove_free_space_cache(cache->free_space_ctl);
- ret = add_free_space_entry(cache, bitmap_offset + 4 * 1024 * 1024,
- 4 * 1024 * 1024, 1);
- if (ret) {
- test_msg("Couldn't add bitmap %d\n", ret);
- return ret;
- }
-
- ret = add_free_space_entry(cache, bitmap_offset - 1 * 1024 * 1024,
- 5 * 1024 * 1024, 0);
- if (ret) {
- test_msg("Couldn't add extent entry %d\n", ret);
- return ret;
- }
-
- ret = btrfs_remove_free_space(cache, bitmap_offset + 1 * 1024 * 1024,
- 5 * 1024 * 1024);
- if (ret) {
- test_msg("Failed to free our space %d\n", ret);
- return ret;
- }
-
- if (check_exists(cache, bitmap_offset + 1 * 1024 * 1024,
- 5 * 1024 * 1024)) {
- test_msg("Left stuff over\n");
- return -1;
- }
-
- __btrfs_remove_free_space_cache(cache->free_space_ctl);
-
- /*
- * This blew up before, we have part of the free space in a bitmap and
- * then the entirety of the rest of the space in an extent. This used
- * to return -EAGAIN back from btrfs_remove_extent, make sure this
- * doesn't happen.
- */
- ret = add_free_space_entry(cache, 1 * 1024 * 1024, 2 * 1024 * 1024, 1);
- if (ret) {
- test_msg("Couldn't add bitmap entry %d\n", ret);
- return ret;
- }
-
- ret = add_free_space_entry(cache, 3 * 1024 * 1024, 1 * 1024 * 1024, 0);
- if (ret) {
- test_msg("Couldn't add extent entry %d\n", ret);
- return ret;
- }
-
- ret = btrfs_remove_free_space(cache, 1 * 1024 * 1024, 3 * 1024 * 1024);
- if (ret) {
- test_msg("Error removing bitmap and extent overlapping %d\n", ret);
- return ret;
- }
-
- __btrfs_remove_free_space_cache(cache->free_space_ctl);
- return 0;
-}
-
-void btrfs_test_free_space_cache(void)
-{
- struct btrfs_block_group_cache *cache;
-
- test_msg("Running btrfs free space cache tests\n");
-
- cache = init_test_block_group();
- if (!cache) {
- test_msg("Couldn't run the tests\n");
- return;
- }
-
- if (test_extents(cache))
- goto out;
- if (test_bitmaps(cache))
- goto out;
- if (test_bitmaps_and_extents(cache))
- goto out;
-out:
- __btrfs_remove_free_space_cache(cache->free_space_ctl);
- kfree(cache->free_space_ctl);
- kfree(cache);
- test_msg("Free space cache tests finished\n");
-}
-#undef test_msg
-#else /* !CONFIG_BTRFS_FS_RUN_SANITY_TESTS */
-void btrfs_test_free_space_cache(void) {}
-#endif /* !CONFIG_BTRFS_FS_RUN_SANITY_TESTS */
+#endif /* CONFIG_BTRFS_FS_RUN_SANITY_TESTS */
diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h
index 894116b7..c749041 100644
--- a/fs/btrfs/free-space-cache.h
+++ b/fs/btrfs/free-space-cache.h
@@ -98,8 +98,7 @@
u64 btrfs_find_ino_for_alloc(struct btrfs_root *fs_root);
void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group,
u64 bytes);
-int btrfs_find_space_cluster(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
+int btrfs_find_space_cluster(struct btrfs_root *root,
struct btrfs_block_group_cache *block_group,
struct btrfs_free_cluster *cluster,
u64 offset, u64 bytes, u64 empty_size);
@@ -113,6 +112,12 @@
int btrfs_trim_block_group(struct btrfs_block_group_cache *block_group,
u64 *trimmed, u64 start, u64 end, u64 minlen);
-void btrfs_test_free_space_cache(void);
+/* Support functions for runnint our sanity tests */
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+int test_add_free_space_entry(struct btrfs_block_group_cache *cache,
+ u64 offset, u64 bytes, bool bitmap);
+int test_check_exists(struct btrfs_block_group_cache *cache,
+ u64 offset, u64 bytes);
+#endif
#endif
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 7bdc83d..f338c56 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -230,12 +230,13 @@
* does the checks required to make sure the data is small enough
* to fit as an inline extent.
*/
-static noinline int cow_file_range_inline(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
- struct inode *inode, u64 start, u64 end,
- size_t compressed_size, int compress_type,
- struct page **compressed_pages)
+static noinline int cow_file_range_inline(struct btrfs_root *root,
+ struct inode *inode, u64 start,
+ u64 end, size_t compressed_size,
+ int compress_type,
+ struct page **compressed_pages)
{
+ struct btrfs_trans_handle *trans;
u64 isize = i_size_read(inode);
u64 actual_end = min(end + 1, isize);
u64 inline_len = actual_end - start;
@@ -256,9 +257,16 @@
return 1;
}
+ trans = btrfs_join_transaction(root);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
+ trans->block_rsv = &root->fs_info->delalloc_block_rsv;
+
ret = btrfs_drop_extents(trans, root, inode, start, aligned_end, 1);
- if (ret)
- return ret;
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ goto out;
+ }
if (isize > actual_end)
inline_len = min_t(u64, isize, actual_end);
@@ -267,15 +275,18 @@
compress_type, compressed_pages);
if (ret && ret != -ENOSPC) {
btrfs_abort_transaction(trans, root, ret);
- return ret;
+ goto out;
} else if (ret == -ENOSPC) {
- return 1;
+ ret = 1;
+ goto out;
}
set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(inode)->runtime_flags);
btrfs_delalloc_release_metadata(inode, end + 1 - start);
btrfs_drop_extent_cache(inode, start, aligned_end - 1, 0);
- return 0;
+out:
+ btrfs_end_transaction(trans, root);
+ return ret;
}
struct async_extent {
@@ -343,7 +354,6 @@
int *num_added)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
- struct btrfs_trans_handle *trans;
u64 num_bytes;
u64 blocksize = root->sectorsize;
u64 actual_end;
@@ -461,45 +471,36 @@
}
cont:
if (start == 0) {
- trans = btrfs_join_transaction(root);
- if (IS_ERR(trans)) {
- ret = PTR_ERR(trans);
- trans = NULL;
- goto cleanup_and_out;
- }
- trans->block_rsv = &root->fs_info->delalloc_block_rsv;
-
/* lets try to make an inline extent */
if (ret || total_in < (actual_end - start)) {
/* we didn't compress the entire range, try
* to make an uncompressed inline extent.
*/
- ret = cow_file_range_inline(trans, root, inode,
- start, end, 0, 0, NULL);
+ ret = cow_file_range_inline(root, inode, start, end,
+ 0, 0, NULL);
} else {
/* try making a compressed inline extent */
- ret = cow_file_range_inline(trans, root, inode,
- start, end,
+ ret = cow_file_range_inline(root, inode, start, end,
total_compressed,
compress_type, pages);
}
if (ret <= 0) {
+ unsigned long clear_flags = EXTENT_DELALLOC |
+ EXTENT_DEFRAG;
+ clear_flags |= (ret < 0) ? EXTENT_DO_ACCOUNTING : 0;
+
/*
* inline extent creation worked or returned error,
* we don't need to create any more async work items.
* Unlock and free up our temp pages.
*/
- extent_clear_unlock_delalloc(inode,
- &BTRFS_I(inode)->io_tree,
- start, end, NULL,
- EXTENT_CLEAR_UNLOCK_PAGE | EXTENT_CLEAR_DIRTY |
- EXTENT_CLEAR_DELALLOC |
- EXTENT_SET_WRITEBACK | EXTENT_END_WRITEBACK);
-
- btrfs_end_transaction(trans, root);
+ extent_clear_unlock_delalloc(inode, start, end, NULL,
+ clear_flags, PAGE_UNLOCK |
+ PAGE_CLEAR_DIRTY |
+ PAGE_SET_WRITEBACK |
+ PAGE_END_WRITEBACK);
goto free_pages_out;
}
- btrfs_end_transaction(trans, root);
}
if (will_compress) {
@@ -590,20 +591,6 @@
kfree(pages);
goto out;
-
-cleanup_and_out:
- extent_clear_unlock_delalloc(inode, &BTRFS_I(inode)->io_tree,
- start, end, NULL,
- EXTENT_CLEAR_UNLOCK_PAGE |
- EXTENT_CLEAR_DIRTY |
- EXTENT_CLEAR_DELALLOC |
- EXTENT_SET_WRITEBACK |
- EXTENT_END_WRITEBACK);
- if (!trans || IS_ERR(trans))
- btrfs_error(root->fs_info, ret, "Failed to join transaction");
- else
- btrfs_abort_transaction(trans, root, ret);
- goto free_pages_out;
}
/*
@@ -617,7 +604,6 @@
{
struct async_extent *async_extent;
u64 alloc_hint = 0;
- struct btrfs_trans_handle *trans;
struct btrfs_key ins;
struct extent_map *em;
struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -678,20 +664,10 @@
lock_extent(io_tree, async_extent->start,
async_extent->start + async_extent->ram_size - 1);
- trans = btrfs_join_transaction(root);
- if (IS_ERR(trans)) {
- ret = PTR_ERR(trans);
- } else {
- trans->block_rsv = &root->fs_info->delalloc_block_rsv;
- ret = btrfs_reserve_extent(trans, root,
+ ret = btrfs_reserve_extent(root,
async_extent->compressed_size,
async_extent->compressed_size,
0, alloc_hint, &ins, 1);
- if (ret && ret != -ENOSPC)
- btrfs_abort_transaction(trans, root, ret);
- btrfs_end_transaction(trans, root);
- }
-
if (ret) {
int i;
@@ -770,16 +746,12 @@
/*
* clear dirty, set writeback and unlock the pages.
*/
- extent_clear_unlock_delalloc(inode,
- &BTRFS_I(inode)->io_tree,
- async_extent->start,
+ extent_clear_unlock_delalloc(inode, async_extent->start,
async_extent->start +
async_extent->ram_size - 1,
- NULL, EXTENT_CLEAR_UNLOCK_PAGE |
- EXTENT_CLEAR_UNLOCK |
- EXTENT_CLEAR_DELALLOC |
- EXTENT_CLEAR_DIRTY | EXTENT_SET_WRITEBACK);
-
+ NULL, EXTENT_LOCKED | EXTENT_DELALLOC,
+ PAGE_UNLOCK | PAGE_CLEAR_DIRTY |
+ PAGE_SET_WRITEBACK);
ret = btrfs_submit_compressed_write(inode,
async_extent->start,
async_extent->ram_size,
@@ -798,16 +770,13 @@
out_free_reserve:
btrfs_free_reserved_extent(root, ins.objectid, ins.offset);
out_free:
- extent_clear_unlock_delalloc(inode, &BTRFS_I(inode)->io_tree,
- async_extent->start,
+ extent_clear_unlock_delalloc(inode, async_extent->start,
async_extent->start +
async_extent->ram_size - 1,
- NULL, EXTENT_CLEAR_UNLOCK_PAGE |
- EXTENT_CLEAR_UNLOCK |
- EXTENT_CLEAR_DELALLOC |
- EXTENT_CLEAR_DIRTY |
- EXTENT_SET_WRITEBACK |
- EXTENT_END_WRITEBACK);
+ NULL, EXTENT_LOCKED | EXTENT_DELALLOC |
+ EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING,
+ PAGE_UNLOCK | PAGE_CLEAR_DIRTY |
+ PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK);
kfree(async_extent);
goto again;
}
@@ -857,14 +826,13 @@
* required to start IO on it. It may be clean and already done with
* IO when we return.
*/
-static noinline int __cow_file_range(struct btrfs_trans_handle *trans,
- struct inode *inode,
- struct btrfs_root *root,
- struct page *locked_page,
- u64 start, u64 end, int *page_started,
- unsigned long *nr_written,
- int unlock)
+static noinline int cow_file_range(struct inode *inode,
+ struct page *locked_page,
+ u64 start, u64 end, int *page_started,
+ unsigned long *nr_written,
+ int unlock)
{
+ struct btrfs_root *root = BTRFS_I(inode)->root;
u64 alloc_hint = 0;
u64 num_bytes;
unsigned long ram_size;
@@ -885,29 +853,24 @@
/* if this is a small write inside eof, kick off defrag */
if (num_bytes < 64 * 1024 &&
(start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size))
- btrfs_add_inode_defrag(trans, inode);
+ btrfs_add_inode_defrag(NULL, inode);
if (start == 0) {
/* lets try to make an inline extent */
- ret = cow_file_range_inline(trans, root, inode,
- start, end, 0, 0, NULL);
+ ret = cow_file_range_inline(root, inode, start, end, 0, 0,
+ NULL);
if (ret == 0) {
- extent_clear_unlock_delalloc(inode,
- &BTRFS_I(inode)->io_tree,
- start, end, NULL,
- EXTENT_CLEAR_UNLOCK_PAGE |
- EXTENT_CLEAR_UNLOCK |
- EXTENT_CLEAR_DELALLOC |
- EXTENT_CLEAR_DIRTY |
- EXTENT_SET_WRITEBACK |
- EXTENT_END_WRITEBACK);
+ extent_clear_unlock_delalloc(inode, start, end, NULL,
+ EXTENT_LOCKED | EXTENT_DELALLOC |
+ EXTENT_DEFRAG, PAGE_UNLOCK |
+ PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK |
+ PAGE_END_WRITEBACK);
*nr_written = *nr_written +
(end - start + PAGE_CACHE_SIZE) / PAGE_CACHE_SIZE;
*page_started = 1;
goto out;
} else if (ret < 0) {
- btrfs_abort_transaction(trans, root, ret);
goto out_unlock;
}
}
@@ -922,13 +885,11 @@
unsigned long op;
cur_alloc_size = disk_num_bytes;
- ret = btrfs_reserve_extent(trans, root, cur_alloc_size,
+ ret = btrfs_reserve_extent(root, cur_alloc_size,
root->sectorsize, 0, alloc_hint,
&ins, 1);
- if (ret < 0) {
- btrfs_abort_transaction(trans, root, ret);
+ if (ret < 0)
goto out_unlock;
- }
em = alloc_extent_map();
if (!em) {
@@ -974,10 +935,8 @@
BTRFS_DATA_RELOC_TREE_OBJECTID) {
ret = btrfs_reloc_clone_csums(inode, start,
cur_alloc_size);
- if (ret) {
- btrfs_abort_transaction(trans, root, ret);
+ if (ret)
goto out_reserve;
- }
}
if (disk_num_bytes < cur_alloc_size)
@@ -990,13 +949,13 @@
* Do set the Private2 bit so we know this page was properly
* setup for writepage
*/
- op = unlock ? EXTENT_CLEAR_UNLOCK_PAGE : 0;
- op |= EXTENT_CLEAR_UNLOCK | EXTENT_CLEAR_DELALLOC |
- EXTENT_SET_PRIVATE2;
+ op = unlock ? PAGE_UNLOCK : 0;
+ op |= PAGE_SET_PRIVATE2;
- extent_clear_unlock_delalloc(inode, &BTRFS_I(inode)->io_tree,
- start, start + ram_size - 1,
- locked_page, op);
+ extent_clear_unlock_delalloc(inode, start,
+ start + ram_size - 1, locked_page,
+ EXTENT_LOCKED | EXTENT_DELALLOC,
+ op);
disk_num_bytes -= cur_alloc_size;
num_bytes -= cur_alloc_size;
alloc_hint = ins.objectid + ins.offset;
@@ -1008,52 +967,14 @@
out_reserve:
btrfs_free_reserved_extent(root, ins.objectid, ins.offset);
out_unlock:
- extent_clear_unlock_delalloc(inode,
- &BTRFS_I(inode)->io_tree,
- start, end, locked_page,
- EXTENT_CLEAR_UNLOCK_PAGE |
- EXTENT_CLEAR_UNLOCK |
- EXTENT_CLEAR_DELALLOC |
- EXTENT_CLEAR_DIRTY |
- EXTENT_SET_WRITEBACK |
- EXTENT_END_WRITEBACK);
-
+ extent_clear_unlock_delalloc(inode, start, end, locked_page,
+ EXTENT_LOCKED | EXTENT_DO_ACCOUNTING |
+ EXTENT_DELALLOC | EXTENT_DEFRAG,
+ PAGE_UNLOCK | PAGE_CLEAR_DIRTY |
+ PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK);
goto out;
}
-static noinline int cow_file_range(struct inode *inode,
- struct page *locked_page,
- u64 start, u64 end, int *page_started,
- unsigned long *nr_written,
- int unlock)
-{
- struct btrfs_trans_handle *trans;
- struct btrfs_root *root = BTRFS_I(inode)->root;
- int ret;
-
- trans = btrfs_join_transaction(root);
- if (IS_ERR(trans)) {
- extent_clear_unlock_delalloc(inode,
- &BTRFS_I(inode)->io_tree,
- start, end, locked_page,
- EXTENT_CLEAR_UNLOCK_PAGE |
- EXTENT_CLEAR_UNLOCK |
- EXTENT_CLEAR_DELALLOC |
- EXTENT_CLEAR_DIRTY |
- EXTENT_SET_WRITEBACK |
- EXTENT_END_WRITEBACK);
- return PTR_ERR(trans);
- }
- trans->block_rsv = &root->fs_info->delalloc_block_rsv;
-
- ret = __cow_file_range(trans, inode, root, locked_page, start, end,
- page_started, nr_written, unlock);
-
- btrfs_end_transaction(trans, root);
-
- return ret;
-}
-
/*
* work queue call back to started compression on a file and pages
*/
@@ -1221,15 +1142,13 @@
path = btrfs_alloc_path();
if (!path) {
- extent_clear_unlock_delalloc(inode,
- &BTRFS_I(inode)->io_tree,
- start, end, locked_page,
- EXTENT_CLEAR_UNLOCK_PAGE |
- EXTENT_CLEAR_UNLOCK |
- EXTENT_CLEAR_DELALLOC |
- EXTENT_CLEAR_DIRTY |
- EXTENT_SET_WRITEBACK |
- EXTENT_END_WRITEBACK);
+ extent_clear_unlock_delalloc(inode, start, end, locked_page,
+ EXTENT_LOCKED | EXTENT_DELALLOC |
+ EXTENT_DO_ACCOUNTING |
+ EXTENT_DEFRAG, PAGE_UNLOCK |
+ PAGE_CLEAR_DIRTY |
+ PAGE_SET_WRITEBACK |
+ PAGE_END_WRITEBACK);
return -ENOMEM;
}
@@ -1241,15 +1160,13 @@
trans = btrfs_join_transaction(root);
if (IS_ERR(trans)) {
- extent_clear_unlock_delalloc(inode,
- &BTRFS_I(inode)->io_tree,
- start, end, locked_page,
- EXTENT_CLEAR_UNLOCK_PAGE |
- EXTENT_CLEAR_UNLOCK |
- EXTENT_CLEAR_DELALLOC |
- EXTENT_CLEAR_DIRTY |
- EXTENT_SET_WRITEBACK |
- EXTENT_END_WRITEBACK);
+ extent_clear_unlock_delalloc(inode, start, end, locked_page,
+ EXTENT_LOCKED | EXTENT_DELALLOC |
+ EXTENT_DO_ACCOUNTING |
+ EXTENT_DEFRAG, PAGE_UNLOCK |
+ PAGE_CLEAR_DIRTY |
+ PAGE_SET_WRITEBACK |
+ PAGE_END_WRITEBACK);
btrfs_free_path(path);
return PTR_ERR(trans);
}
@@ -1369,9 +1286,9 @@
btrfs_release_path(path);
if (cow_start != (u64)-1) {
- ret = __cow_file_range(trans, inode, root, locked_page,
- cow_start, found_key.offset - 1,
- page_started, nr_written, 1);
+ ret = cow_file_range(inode, locked_page,
+ cow_start, found_key.offset - 1,
+ page_started, nr_written, 1);
if (ret) {
btrfs_abort_transaction(trans, root, ret);
goto error;
@@ -1428,11 +1345,11 @@
}
}
- extent_clear_unlock_delalloc(inode, &BTRFS_I(inode)->io_tree,
- cur_offset, cur_offset + num_bytes - 1,
- locked_page, EXTENT_CLEAR_UNLOCK_PAGE |
- EXTENT_CLEAR_UNLOCK | EXTENT_CLEAR_DELALLOC |
- EXTENT_SET_PRIVATE2);
+ extent_clear_unlock_delalloc(inode, cur_offset,
+ cur_offset + num_bytes - 1,
+ locked_page, EXTENT_LOCKED |
+ EXTENT_DELALLOC, PAGE_UNLOCK |
+ PAGE_SET_PRIVATE2);
cur_offset = extent_end;
if (cur_offset > end)
break;
@@ -1445,9 +1362,8 @@
}
if (cow_start != (u64)-1) {
- ret = __cow_file_range(trans, inode, root, locked_page,
- cow_start, end,
- page_started, nr_written, 1);
+ ret = cow_file_range(inode, locked_page, cow_start, end,
+ page_started, nr_written, 1);
if (ret) {
btrfs_abort_transaction(trans, root, ret);
goto error;
@@ -1460,16 +1376,13 @@
ret = err;
if (ret && cur_offset < end)
- extent_clear_unlock_delalloc(inode,
- &BTRFS_I(inode)->io_tree,
- cur_offset, end, locked_page,
- EXTENT_CLEAR_UNLOCK_PAGE |
- EXTENT_CLEAR_UNLOCK |
- EXTENT_CLEAR_DELALLOC |
- EXTENT_CLEAR_DIRTY |
- EXTENT_SET_WRITEBACK |
- EXTENT_END_WRITEBACK);
-
+ extent_clear_unlock_delalloc(inode, cur_offset, end,
+ locked_page, EXTENT_LOCKED |
+ EXTENT_DELALLOC | EXTENT_DEFRAG |
+ EXTENT_DO_ACCOUNTING, PAGE_UNLOCK |
+ PAGE_CLEAR_DIRTY |
+ PAGE_SET_WRITEBACK |
+ PAGE_END_WRITEBACK);
btrfs_free_path(path);
return ret;
}
@@ -2132,6 +2045,7 @@
WARN_ON(1);
return ret;
}
+ ret = 0;
while (1) {
cond_resched();
@@ -2181,8 +2095,6 @@
old->len || extent_offset + num_bytes <=
old->extent_offset + old->offset)
continue;
-
- ret = 0;
break;
}
@@ -2238,16 +2150,18 @@
static int relink_is_mergable(struct extent_buffer *leaf,
struct btrfs_file_extent_item *fi,
- u64 disk_bytenr)
+ struct new_sa_defrag_extent *new)
{
- if (btrfs_file_extent_disk_bytenr(leaf, fi) != disk_bytenr)
+ if (btrfs_file_extent_disk_bytenr(leaf, fi) != new->bytenr)
return 0;
if (btrfs_file_extent_type(leaf, fi) != BTRFS_FILE_EXTENT_REG)
return 0;
- if (btrfs_file_extent_compression(leaf, fi) ||
- btrfs_file_extent_encryption(leaf, fi) ||
+ if (btrfs_file_extent_compression(leaf, fi) != new->compress_type)
+ return 0;
+
+ if (btrfs_file_extent_encryption(leaf, fi) ||
btrfs_file_extent_other_encoding(leaf, fi))
return 0;
@@ -2391,8 +2305,8 @@
struct btrfs_file_extent_item);
extent_len = btrfs_file_extent_num_bytes(leaf, fi);
- if (relink_is_mergable(leaf, fi, new->bytenr) &&
- extent_len + found_key.offset == start) {
+ if (extent_len + found_key.offset == start &&
+ relink_is_mergable(leaf, fi, new)) {
btrfs_set_file_extent_num_bytes(leaf, fi,
extent_len + len);
btrfs_mark_buffer_dirty(leaf);
@@ -2648,8 +2562,10 @@
struct extent_state *cached_state = NULL;
struct new_sa_defrag_extent *new = NULL;
int compress_type = 0;
- int ret;
+ int ret = 0;
+ u64 logical_len = ordered_extent->len;
bool nolock;
+ bool truncated = false;
nolock = btrfs_is_free_space_inode(inode);
@@ -2658,6 +2574,14 @@
goto out;
}
+ if (test_bit(BTRFS_ORDERED_TRUNCATED, &ordered_extent->flags)) {
+ truncated = true;
+ logical_len = ordered_extent->truncated_len;
+ /* Truncated the entire extent, don't bother adding */
+ if (!logical_len)
+ goto out;
+ }
+
if (test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags)) {
BUG_ON(!list_empty(&ordered_extent->list)); /* Logic error */
btrfs_ordered_update_i_size(inode, 0, ordered_extent);
@@ -2713,15 +2637,14 @@
ret = btrfs_mark_extent_written(trans, inode,
ordered_extent->file_offset,
ordered_extent->file_offset +
- ordered_extent->len);
+ logical_len);
} else {
BUG_ON(root == root->fs_info->tree_root);
ret = insert_reserved_file_extent(trans, inode,
ordered_extent->file_offset,
ordered_extent->start,
ordered_extent->disk_len,
- ordered_extent->len,
- ordered_extent->len,
+ logical_len, logical_len,
compress_type, 0, 0,
BTRFS_FILE_EXTENT_REG);
}
@@ -2753,17 +2676,27 @@
if (trans)
btrfs_end_transaction(trans, root);
- if (ret) {
- clear_extent_uptodate(io_tree, ordered_extent->file_offset,
- ordered_extent->file_offset +
- ordered_extent->len - 1, NULL, GFP_NOFS);
+ if (ret || truncated) {
+ u64 start, end;
+
+ if (truncated)
+ start = ordered_extent->file_offset + logical_len;
+ else
+ start = ordered_extent->file_offset;
+ end = ordered_extent->file_offset + ordered_extent->len - 1;
+ clear_extent_uptodate(io_tree, start, end, NULL, GFP_NOFS);
+
+ /* Drop the cache for the part of the extent we didn't write. */
+ btrfs_drop_extent_cache(inode, start, end, 0);
/*
* If the ordered extent had an IOERR or something else went
* wrong we need to return the space for this ordered extent
- * back to the allocator.
+ * back to the allocator. We only free the extent in the
+ * truncated case if we didn't write out the extent at all.
*/
- if (!test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags) &&
+ if ((ret || !logical_len) &&
+ !test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags) &&
!test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags))
btrfs_free_reserved_extent(root, ordered_extent->start,
ordered_extent->disk_len);
@@ -2827,16 +2760,16 @@
* if there's a match, we allow the bio to finish. If not, the code in
* extent_io.c will try to find good copies for us.
*/
-static int btrfs_readpage_end_io_hook(struct page *page, u64 start, u64 end,
- struct extent_state *state, int mirror)
+static int btrfs_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
+ u64 phy_offset, struct page *page,
+ u64 start, u64 end, int mirror)
{
size_t offset = start - page_offset(page);
struct inode *inode = page->mapping->host;
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
char *kaddr;
- u64 private = ~(u32)0;
- int ret;
struct btrfs_root *root = BTRFS_I(inode)->root;
+ u32 csum_expected;
u32 csum = ~(u32)0;
static DEFINE_RATELIMIT_STATE(_rs, DEFAULT_RATELIMIT_INTERVAL,
DEFAULT_RATELIMIT_BURST);
@@ -2856,19 +2789,13 @@
return 0;
}
- if (state && state->start == start) {
- private = state->private;
- ret = 0;
- } else {
- ret = get_state_private(io_tree, start, &private);
- }
- kaddr = kmap_atomic(page);
- if (ret)
- goto zeroit;
+ phy_offset >>= inode->i_sb->s_blocksize_bits;
+ csum_expected = *(((u32 *)io_bio->csum) + phy_offset);
+ kaddr = kmap_atomic(page);
csum = btrfs_csum_data(kaddr + offset, csum, end - start + 1);
btrfs_csum_final(csum, (char *)&csum);
- if (csum != private)
+ if (csum != csum_expected)
goto zeroit;
kunmap_atomic(kaddr);
@@ -2877,14 +2804,12 @@
zeroit:
if (__ratelimit(&_rs))
- btrfs_info(root->fs_info, "csum failed ino %llu off %llu csum %u private %llu",
- (unsigned long long)btrfs_ino(page->mapping->host),
- (unsigned long long)start, csum,
- (unsigned long long)private);
+ btrfs_info(root->fs_info, "csum failed ino %llu off %llu csum %u expected csum %u",
+ btrfs_ino(page->mapping->host), start, csum, csum_expected);
memset(kaddr + offset, 1, end - start + 1);
flush_dcache_page(page);
kunmap_atomic(kaddr);
- if (private == 0)
+ if (csum_expected == 0)
return 0;
return -EIO;
}
@@ -2971,8 +2896,10 @@
btrfs_root_refs(&root->root_item) > 0) {
ret = btrfs_del_orphan_item(trans, root->fs_info->tree_root,
root->root_key.objectid);
- BUG_ON(ret);
- root->orphan_item_inserted = 0;
+ if (ret)
+ btrfs_abort_transaction(trans, root, ret);
+ else
+ root->orphan_item_inserted = 0;
}
if (block_rsv) {
@@ -3041,11 +2968,18 @@
/* insert an orphan item to track this unlinked/truncated file */
if (insert >= 1) {
ret = btrfs_insert_orphan_item(trans, root, btrfs_ino(inode));
- if (ret && ret != -EEXIST) {
- clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
- &BTRFS_I(inode)->runtime_flags);
- btrfs_abort_transaction(trans, root, ret);
- return ret;
+ if (ret) {
+ if (reserve) {
+ clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED,
+ &BTRFS_I(inode)->runtime_flags);
+ btrfs_orphan_release_metadata(inode);
+ }
+ if (ret != -EEXIST) {
+ clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
+ &BTRFS_I(inode)->runtime_flags);
+ btrfs_abort_transaction(trans, root, ret);
+ return ret;
+ }
}
ret = 0;
}
@@ -3084,17 +3018,15 @@
release_rsv = 1;
spin_unlock(&root->orphan_lock);
- if (trans && delete_item) {
+ if (trans && delete_item)
ret = btrfs_del_orphan_item(trans, root, btrfs_ino(inode));
- BUG_ON(ret); /* -ENOMEM or corruption (JDM: Recheck) */
- }
if (release_rsv) {
btrfs_orphan_release_metadata(inode);
atomic_dec(&root->orphan_inodes);
}
- return 0;
+ return ret;
}
/*
@@ -3224,8 +3156,9 @@
found_key.objectid);
ret = btrfs_del_orphan_item(trans, root,
found_key.objectid);
- BUG_ON(ret); /* -ENOMEM or corruption (JDM: Recheck) */
btrfs_end_transaction(trans, root);
+ if (ret)
+ goto out;
continue;
}
@@ -3657,8 +3590,7 @@
if (ret) {
btrfs_info(root->fs_info,
"failed to delete reference to %.*s, inode %llu parent %llu",
- name_len, name,
- (unsigned long long)ino, (unsigned long long)dir_ino);
+ name_len, name, ino, dir_ino);
btrfs_abort_transaction(trans, root, ret);
goto err;
}
@@ -3929,6 +3861,7 @@
u64 extent_num_bytes = 0;
u64 extent_offset = 0;
u64 item_end = 0;
+ u64 last_size = (u64)-1;
u32 found_type = (u8)-1;
int found_extent;
int del_item;
@@ -4026,6 +3959,11 @@
if (found_type != BTRFS_EXTENT_DATA_KEY)
goto delete;
+ if (del_item)
+ last_size = found_key.offset;
+ else
+ last_size = new_size;
+
if (extent_type != BTRFS_FILE_EXTENT_INLINE) {
u64 num_dec;
extent_start = btrfs_file_extent_disk_bytenr(leaf, fi);
@@ -4137,6 +4075,8 @@
btrfs_abort_transaction(trans, root, ret);
}
error:
+ if (last_size != (u64)-1)
+ btrfs_ordered_update_i_size(inode, last_size, NULL);
btrfs_free_path(path);
return err;
}
@@ -4409,7 +4349,7 @@
inode->i_ctime = inode->i_mtime = current_fs_time(inode->i_sb);
if (newsize > oldsize) {
- truncate_pagecache(inode, oldsize, newsize);
+ truncate_pagecache(inode, newsize);
ret = btrfs_cont_expand(inode, oldsize, newsize);
if (ret)
return ret;
@@ -4465,8 +4405,26 @@
btrfs_inode_resume_unlocked_dio(inode);
ret = btrfs_truncate(inode);
- if (ret && inode->i_nlink)
- btrfs_orphan_del(NULL, inode);
+ if (ret && inode->i_nlink) {
+ int err;
+
+ /*
+ * failed to truncate, disk_i_size is only adjusted down
+ * as we remove extents, so it should represent the true
+ * size of the inode, so reset the in memory size and
+ * delete our orphan entry.
+ */
+ trans = btrfs_join_transaction(root);
+ if (IS_ERR(trans)) {
+ btrfs_orphan_del(NULL, inode);
+ return ret;
+ }
+ i_size_write(inode, BTRFS_I(inode)->disk_i_size);
+ err = btrfs_orphan_del(trans, inode);
+ if (err)
+ btrfs_abort_transaction(trans, root, err);
+ btrfs_end_transaction(trans, root);
+ }
}
return ret;
@@ -4601,10 +4559,15 @@
btrfs_free_block_rsv(root, rsv);
+ /*
+ * Errors here aren't a big deal, it just means we leave orphan items
+ * in the tree. They will be cleaned up on the next mount.
+ */
if (ret == 0) {
trans->block_rsv = root->orphan_block_rsv;
- ret = btrfs_orphan_del(trans, inode);
- BUG_ON(ret);
+ btrfs_orphan_del(trans, inode);
+ } else {
+ btrfs_orphan_del(NULL, inode);
}
trans->block_rsv = &root->fs_info->trans_block_rsv;
@@ -6161,10 +6124,7 @@
btrfs_release_path(path);
if (em->start > start || extent_map_end(em) <= start) {
btrfs_err(root->fs_info, "bad extent! em: [%llu %llu] passed [%llu %llu]",
- (unsigned long long)em->start,
- (unsigned long long)em->len,
- (unsigned long long)start,
- (unsigned long long)len);
+ em->start, em->len, start, len);
err = -EIO;
goto out;
}
@@ -6362,39 +6322,32 @@
u64 start, u64 len)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
- struct btrfs_trans_handle *trans;
struct extent_map *em;
struct btrfs_key ins;
u64 alloc_hint;
int ret;
- trans = btrfs_join_transaction(root);
- if (IS_ERR(trans))
- return ERR_CAST(trans);
-
- trans->block_rsv = &root->fs_info->delalloc_block_rsv;
-
alloc_hint = get_extent_allocation_hint(inode, start, len);
- ret = btrfs_reserve_extent(trans, root, len, root->sectorsize, 0,
+ ret = btrfs_reserve_extent(root, len, root->sectorsize, 0,
alloc_hint, &ins, 1);
- if (ret) {
- em = ERR_PTR(ret);
- goto out;
- }
+ if (ret)
+ return ERR_PTR(ret);
em = create_pinned_em(inode, start, ins.offset, start, ins.objectid,
ins.offset, ins.offset, ins.offset, 0);
- if (IS_ERR(em))
- goto out;
+ if (IS_ERR(em)) {
+ btrfs_free_reserved_extent(root, ins.objectid, ins.offset);
+ return em;
+ }
ret = btrfs_add_ordered_extent_dio(inode, start, ins.objectid,
ins.offset, ins.offset, 0);
if (ret) {
btrfs_free_reserved_extent(root, ins.objectid, ins.offset);
- em = ERR_PTR(ret);
+ free_extent_map(em);
+ return ERR_PTR(ret);
}
-out:
- btrfs_end_transaction(trans, root);
+
return em;
}
@@ -6402,11 +6355,11 @@
* returns 1 when the nocow is safe, < 1 on error, 0 if the
* block must be cow'd
*/
-noinline int can_nocow_extent(struct btrfs_trans_handle *trans,
- struct inode *inode, u64 offset, u64 *len,
+noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
u64 *orig_start, u64 *orig_block_len,
u64 *ram_bytes)
{
+ struct btrfs_trans_handle *trans;
struct btrfs_path *path;
int ret;
struct extent_buffer *leaf;
@@ -6424,7 +6377,7 @@
if (!path)
return -ENOMEM;
- ret = btrfs_lookup_file_extent(trans, root, path, btrfs_ino(inode),
+ ret = btrfs_lookup_file_extent(NULL, root, path, btrfs_ino(inode),
offset, 0);
if (ret < 0)
goto out;
@@ -6489,9 +6442,19 @@
* look for other files referencing this extent, if we
* find any we must cow
*/
- if (btrfs_cross_ref_exist(trans, root, btrfs_ino(inode),
- key.offset - backref_offset, disk_bytenr))
+ trans = btrfs_join_transaction(root);
+ if (IS_ERR(trans)) {
+ ret = 0;
goto out;
+ }
+
+ ret = btrfs_cross_ref_exist(trans, root, btrfs_ino(inode),
+ key.offset - backref_offset, disk_bytenr);
+ btrfs_end_transaction(trans, root);
+ if (ret) {
+ ret = 0;
+ goto out;
+ }
/*
* adjust disk_bytenr and num_bytes to cover just the bytes
@@ -6633,7 +6596,6 @@
u64 start = iblock << inode->i_blkbits;
u64 lockstart, lockend;
u64 len = bh_result->b_size;
- struct btrfs_trans_handle *trans;
int unlock_bits = EXTENT_LOCKED;
int ret = 0;
@@ -6715,16 +6677,7 @@
len = min(len, em->len - (start - em->start));
block_start = em->block_start + (start - em->start);
- /*
- * we're not going to log anything, but we do need
- * to make sure the current transaction stays open
- * while we look for nocow cross refs
- */
- trans = btrfs_join_transaction(root);
- if (IS_ERR(trans))
- goto must_cow;
-
- if (can_nocow_extent(trans, inode, start, &len, &orig_start,
+ if (can_nocow_extent(inode, start, &len, &orig_start,
&orig_block_len, &ram_bytes) == 1) {
if (type == BTRFS_ORDERED_PREALLOC) {
free_extent_map(em);
@@ -6733,24 +6686,20 @@
block_start, len,
orig_block_len,
ram_bytes, type);
- if (IS_ERR(em)) {
- btrfs_end_transaction(trans, root);
+ if (IS_ERR(em))
goto unlock_err;
- }
}
ret = btrfs_add_ordered_extent_dio(inode, start,
block_start, len, len, type);
- btrfs_end_transaction(trans, root);
if (ret) {
free_extent_map(em);
goto unlock_err;
}
goto unlock;
}
- btrfs_end_transaction(trans, root);
}
-must_cow:
+
/*
* this will cow the extent, reset the len in case we changed
* it above
@@ -6813,26 +6762,6 @@
return ret;
}
-struct btrfs_dio_private {
- struct inode *inode;
- u64 logical_offset;
- u64 disk_bytenr;
- u64 bytes;
- void *private;
-
- /* number of bios pending for this dio */
- atomic_t pending_bios;
-
- /* IO errors */
- int errors;
-
- /* orig_bio is our btrfs_io_bio */
- struct bio *orig_bio;
-
- /* dio_bio came from fs/direct-io.c */
- struct bio *dio_bio;
-};
-
static void btrfs_endio_direct_read(struct bio *bio, int err)
{
struct btrfs_dio_private *dip = bio->bi_private;
@@ -6841,6 +6770,8 @@
struct inode *inode = dip->inode;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct bio *dio_bio;
+ u32 *csums = (u32 *)dip->csum;
+ int index = 0;
u64 start;
start = dip->logical_offset;
@@ -6849,12 +6780,8 @@
struct page *page = bvec->bv_page;
char *kaddr;
u32 csum = ~(u32)0;
- u64 private = ~(u32)0;
unsigned long flags;
- if (get_state_private(&BTRFS_I(inode)->io_tree,
- start, &private))
- goto failed;
local_irq_save(flags);
kaddr = kmap_atomic(page);
csum = btrfs_csum_data(kaddr + bvec->bv_offset,
@@ -6864,18 +6791,17 @@
local_irq_restore(flags);
flush_dcache_page(bvec->bv_page);
- if (csum != private) {
-failed:
- btrfs_err(root->fs_info, "csum failed ino %llu off %llu csum %u private %u",
- (unsigned long long)btrfs_ino(inode),
- (unsigned long long)start,
- csum, (unsigned)private);
+ if (csum != csums[index]) {
+ btrfs_err(root->fs_info, "csum failed ino %llu off %llu csum %u expected csum %u",
+ btrfs_ino(inode), start, csum,
+ csums[index]);
err = -EIO;
}
}
start += bvec->bv_len;
bvec++;
+ index++;
} while (bvec <= bvec_end);
unlock_extent(&BTRFS_I(inode)->io_tree, dip->logical_offset,
@@ -6956,7 +6882,7 @@
if (err) {
printk(KERN_ERR "btrfs direct IO failed ino %llu rw %lu "
"sector %#Lx len %u err no %d\n",
- (unsigned long long)btrfs_ino(dip->inode), bio->bi_rw,
+ btrfs_ino(dip->inode), bio->bi_rw,
(unsigned long long)bio->bi_sector, bio->bi_size, err);
dip->errors = 1;
@@ -6992,6 +6918,7 @@
int rw, u64 file_offset, int skip_sum,
int async_submit)
{
+ struct btrfs_dio_private *dip = bio->bi_private;
int write = rw & REQ_WRITE;
struct btrfs_root *root = BTRFS_I(inode)->root;
int ret;
@@ -7026,7 +6953,8 @@
if (ret)
goto err;
} else if (!skip_sum) {
- ret = btrfs_lookup_bio_sums_dio(root, inode, bio, file_offset);
+ ret = btrfs_lookup_bio_sums_dio(root, inode, dip, bio,
+ file_offset);
if (ret)
goto err;
}
@@ -7061,6 +6989,7 @@
bio_put(orig_bio);
return -EIO;
}
+
if (map_length >= orig_bio->bi_size) {
bio = orig_bio;
goto submit;
@@ -7156,19 +7085,28 @@
struct btrfs_dio_private *dip;
struct bio *io_bio;
int skip_sum;
+ int sum_len;
int write = rw & REQ_WRITE;
int ret = 0;
+ u16 csum_size;
skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
io_bio = btrfs_bio_clone(dio_bio, GFP_NOFS);
-
if (!io_bio) {
ret = -ENOMEM;
goto free_ordered;
}
- dip = kmalloc(sizeof(*dip), GFP_NOFS);
+ if (!skip_sum && !write) {
+ csum_size = btrfs_super_csum_size(root->fs_info->super_copy);
+ sum_len = dio_bio->bi_size >> inode->i_sb->s_blocksize_bits;
+ sum_len *= csum_size;
+ } else {
+ sum_len = 0;
+ }
+
+ dip = kmalloc(sizeof(*dip) + sum_len, GFP_NOFS);
if (!dip) {
ret = -ENOMEM;
goto free_io_bio;
@@ -7443,10 +7381,23 @@
* whoever cleared the private bit is responsible
* for the finish_ordered_io
*/
- if (TestClearPagePrivate2(page) &&
- btrfs_dec_test_ordered_pending(inode, &ordered, page_start,
- PAGE_CACHE_SIZE, 1)) {
- btrfs_finish_ordered_io(ordered);
+ if (TestClearPagePrivate2(page)) {
+ struct btrfs_ordered_inode_tree *tree;
+ u64 new_len;
+
+ tree = &BTRFS_I(inode)->ordered_tree;
+
+ spin_lock_irq(&tree->lock);
+ set_bit(BTRFS_ORDERED_TRUNCATED, &ordered->flags);
+ new_len = page_start - ordered->file_offset;
+ if (new_len < ordered->truncated_len)
+ ordered->truncated_len = new_len;
+ spin_unlock_irq(&tree->lock);
+
+ if (btrfs_dec_test_ordered_pending(inode, &ordered,
+ page_start,
+ PAGE_CACHE_SIZE, 1))
+ btrfs_finish_ordered_io(ordered);
}
btrfs_put_ordered_extent(ordered);
cached_state = NULL;
@@ -7612,7 +7563,6 @@
u64 min_size = btrfs_calc_trunc_metadata_size(root, 1);
btrfs_wait_ordered_range(inode, inode->i_size & (~mask), (u64)-1);
- btrfs_ordered_update_i_size(inode, inode->i_size, NULL);
/*
* Yes ladies and gentelment, this is indeed ugly. The fact is we have
@@ -7876,7 +7826,7 @@
if (test_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
&BTRFS_I(inode)->runtime_flags)) {
btrfs_info(root->fs_info, "inode %llu still on the orphan list",
- (unsigned long long)btrfs_ino(inode));
+ btrfs_ino(inode));
atomic_dec(&root->orphan_inodes);
}
@@ -7886,8 +7836,7 @@
break;
else {
btrfs_err(root->fs_info, "found ordered extent %llu %llu on inode cleanup",
- (unsigned long long)ordered->file_offset,
- (unsigned long long)ordered->len);
+ ordered->file_offset, ordered->len);
btrfs_remove_ordered_extent(inode, ordered);
btrfs_put_ordered_extent(ordered);
btrfs_put_ordered_extent(ordered);
@@ -8161,10 +8110,8 @@
new_dentry->d_name.name,
new_dentry->d_name.len);
}
- if (!ret && new_inode->i_nlink == 0) {
+ if (!ret && new_inode->i_nlink == 0)
ret = btrfs_orphan_add(trans, new_dentry->d_inode);
- BUG_ON(ret);
- }
if (ret) {
btrfs_abort_transaction(trans, root, ret);
goto out_fail;
@@ -8525,8 +8472,8 @@
cur_bytes = min(num_bytes, 256ULL * 1024 * 1024);
cur_bytes = max(cur_bytes, min_size);
- ret = btrfs_reserve_extent(trans, root, cur_bytes,
- min_size, 0, *alloc_hint, &ins, 1);
+ ret = btrfs_reserve_extent(root, cur_bytes, min_size, 0,
+ *alloc_hint, &ins, 1);
if (ret) {
if (own_trans)
btrfs_end_transaction(trans, root);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 238a055..1a5b946 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -43,6 +43,7 @@
#include <linux/blkdev.h>
#include <linux/uuid.h>
#include <linux/btrfs.h>
+#include <linux/uaccess.h>
#include "compat.h"
#include "ctree.h"
#include "disk-io.h"
@@ -57,6 +58,9 @@
#include "send.h"
#include "dev-replace.h"
+static int btrfs_clone(struct inode *src, struct inode *inode,
+ u64 off, u64 olen, u64 olen_aligned, u64 destoff);
+
/* Mask out flags that are inappropriate for the given type of inode. */
static inline __u32 btrfs_mask_flags(umode_t mode, __u32 flags)
{
@@ -363,6 +367,13 @@
return 0;
}
+int btrfs_is_empty_uuid(u8 *uuid)
+{
+ static char empty_uuid[BTRFS_UUID_SIZE] = {0};
+
+ return !memcmp(uuid, empty_uuid, BTRFS_UUID_SIZE);
+}
+
static noinline int create_subvol(struct inode *dir,
struct dentry *dentry,
char *name, int namelen,
@@ -396,7 +407,7 @@
* of create_snapshot().
*/
ret = btrfs_subvolume_reserve_metadata(root, &block_rsv,
- 7, &qgroup_reserved);
+ 8, &qgroup_reserved, false);
if (ret)
return ret;
@@ -425,26 +436,25 @@
btrfs_set_header_backref_rev(leaf, BTRFS_MIXED_BACKREF_REV);
btrfs_set_header_owner(leaf, objectid);
- write_extent_buffer(leaf, root->fs_info->fsid,
- (unsigned long)btrfs_header_fsid(leaf),
+ write_extent_buffer(leaf, root->fs_info->fsid, btrfs_header_fsid(leaf),
BTRFS_FSID_SIZE);
write_extent_buffer(leaf, root->fs_info->chunk_tree_uuid,
- (unsigned long)btrfs_header_chunk_tree_uuid(leaf),
+ btrfs_header_chunk_tree_uuid(leaf),
BTRFS_UUID_SIZE);
btrfs_mark_buffer_dirty(leaf);
memset(&root_item, 0, sizeof(root_item));
inode_item = &root_item.inode;
- inode_item->generation = cpu_to_le64(1);
- inode_item->size = cpu_to_le64(3);
- inode_item->nlink = cpu_to_le32(1);
- inode_item->nbytes = cpu_to_le64(root->leafsize);
- inode_item->mode = cpu_to_le32(S_IFDIR | 0755);
+ btrfs_set_stack_inode_generation(inode_item, 1);
+ btrfs_set_stack_inode_size(inode_item, 3);
+ btrfs_set_stack_inode_nlink(inode_item, 1);
+ btrfs_set_stack_inode_nbytes(inode_item, root->leafsize);
+ btrfs_set_stack_inode_mode(inode_item, S_IFDIR | 0755);
- root_item.flags = 0;
- root_item.byte_limit = 0;
- inode_item->flags = cpu_to_le64(BTRFS_INODE_ROOT_ITEM_INIT);
+ btrfs_set_root_flags(&root_item, 0);
+ btrfs_set_root_limit(&root_item, 0);
+ btrfs_set_stack_inode_flags(inode_item, BTRFS_INODE_ROOT_ITEM_INIT);
btrfs_set_root_bytenr(&root_item, leaf->start);
btrfs_set_root_generation(&root_item, trans->transid);
@@ -457,8 +467,8 @@
btrfs_root_generation(&root_item));
uuid_le_gen(&new_uuid);
memcpy(root_item.uuid, new_uuid.b, BTRFS_UUID_SIZE);
- root_item.otime.sec = cpu_to_le64(cur_time.tv_sec);
- root_item.otime.nsec = cpu_to_le32(cur_time.tv_nsec);
+ btrfs_set_stack_timespec_sec(&root_item.otime, cur_time.tv_sec);
+ btrfs_set_stack_timespec_nsec(&root_item.otime, cur_time.tv_nsec);
root_item.ctime = root_item.otime;
btrfs_set_root_ctransid(&root_item, trans->transid);
btrfs_set_root_otransid(&root_item, trans->transid);
@@ -518,9 +528,14 @@
ret = btrfs_add_root_ref(trans, root->fs_info->tree_root,
objectid, root->root_key.objectid,
btrfs_ino(dir), index, name, namelen);
-
BUG_ON(ret);
+ ret = btrfs_uuid_tree_add(trans, root->fs_info->uuid_root,
+ root_item.uuid, BTRFS_UUID_KEY_SUBVOL,
+ objectid);
+ if (ret)
+ btrfs_abort_transaction(trans, root, ret);
+
fail:
trans->block_rsv = NULL;
trans->bytes_reserved = 0;
@@ -573,10 +588,12 @@
* 1 - root item
* 2 - root ref/backref
* 1 - root of snapshot
+ * 1 - UUID item
*/
ret = btrfs_subvolume_reserve_metadata(BTRFS_I(dir)->root,
- &pending_snapshot->block_rsv, 7,
- &pending_snapshot->qgroup_reserved);
+ &pending_snapshot->block_rsv, 8,
+ &pending_snapshot->qgroup_reserved,
+ false);
if (ret)
goto out;
@@ -1267,9 +1284,6 @@
cluster = max_cluster;
}
- if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)
- BTRFS_I(inode)->force_compress = compress_type;
-
if (i + cluster > ra_index) {
ra_index = max(i, ra_index);
btrfs_force_ra(inode->i_mapping, ra, file, ra_index,
@@ -1278,6 +1292,8 @@
}
mutex_lock(&inode->i_mutex);
+ if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)
+ BTRFS_I(inode)->force_compress = compress_type;
ret = cluster_pages_for_defrag(inode, pages, i, cluster);
if (ret < 0) {
mutex_unlock(&inode->i_mutex);
@@ -1334,10 +1350,6 @@
atomic_read(&root->fs_info->async_delalloc_pages) == 0));
}
atomic_dec(&root->fs_info->async_submit_draining);
-
- mutex_lock(&inode->i_mutex);
- BTRFS_I(inode)->force_compress = BTRFS_COMPRESS_NONE;
- mutex_unlock(&inode->i_mutex);
}
if (range->compress_type == BTRFS_COMPRESS_LZO) {
@@ -1347,6 +1359,11 @@
ret = defrag_count;
out_ra:
+ if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS) {
+ mutex_lock(&inode->i_mutex);
+ BTRFS_I(inode)->force_compress = BTRFS_COMPRESS_NONE;
+ mutex_unlock(&inode->i_mutex);
+ }
if (!file)
kfree(ra);
kfree(pages);
@@ -1377,9 +1394,8 @@
if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
1)) {
- pr_info("btrfs: dev add/delete/balance/replace/resize operation in progress\n");
mnt_drop_write_file(file);
- return -EINVAL;
+ return BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
}
mutex_lock(&root->fs_info->volume_mutex);
@@ -1403,14 +1419,13 @@
ret = -EINVAL;
goto out_free;
}
- printk(KERN_INFO "btrfs: resizing devid %llu\n",
- (unsigned long long)devid);
+ printk(KERN_INFO "btrfs: resizing devid %llu\n", devid);
}
device = btrfs_find_device(root->fs_info, devid, NULL, NULL);
if (!device) {
printk(KERN_INFO "btrfs: resizer unable to find device %llu\n",
- (unsigned long long)devid);
+ devid);
ret = -ENODEV;
goto out_free;
}
@@ -1418,7 +1433,7 @@
if (!device->writeable) {
printk(KERN_INFO "btrfs: resizer unable to apply on "
"readonly device %llu\n",
- (unsigned long long)devid);
+ devid);
ret = -EPERM;
goto out_free;
}
@@ -1470,8 +1485,7 @@
new_size *= root->sectorsize;
printk_in_rcu(KERN_INFO "btrfs: new size for %s is %llu\n",
- rcu_str_deref(device->name),
- (unsigned long long)new_size);
+ rcu_str_deref(device->name), new_size);
if (new_size > old_size) {
trans = btrfs_start_transaction(root, 0);
@@ -1721,13 +1735,28 @@
static noinline int may_destroy_subvol(struct btrfs_root *root)
{
struct btrfs_path *path;
+ struct btrfs_dir_item *di;
struct btrfs_key key;
+ u64 dir_id;
int ret;
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
+ /* Make sure this root isn't set as the default subvol */
+ dir_id = btrfs_super_root_dir(root->fs_info->super_copy);
+ di = btrfs_lookup_dir_item(NULL, root->fs_info->tree_root, path,
+ dir_id, "default", 7, 0);
+ if (di && !IS_ERR(di)) {
+ btrfs_dir_item_key_to_cpu(path->nodes[0], di, &key);
+ if (key.objectid == root->root_key.objectid) {
+ ret = -ENOTEMPTY;
+ goto out;
+ }
+ btrfs_release_path(path);
+ }
+
key.objectid = root->root_key.objectid;
key.type = BTRFS_ROOT_REF_KEY;
key.offset = (u64)-1;
@@ -1993,25 +2022,29 @@
ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
if (ret < 0)
goto out;
+ else if (ret > 0) {
+ ret = btrfs_previous_item(root, path, dirid,
+ BTRFS_INODE_REF_KEY);
+ if (ret < 0)
+ goto out;
+ else if (ret > 0) {
+ ret = -ENOENT;
+ goto out;
+ }
+ }
l = path->nodes[0];
slot = path->slots[0];
- if (ret > 0 && slot > 0)
- slot--;
btrfs_item_key_to_cpu(l, &key, slot);
- if (ret > 0 && (key.objectid != dirid ||
- key.type != BTRFS_INODE_REF_KEY)) {
- ret = -ENOENT;
- goto out;
- }
-
iref = btrfs_item_ptr(l, slot, struct btrfs_inode_ref);
len = btrfs_inode_ref_name_len(l, iref);
ptr -= len + 1;
total_len += len + 1;
- if (ptr < name)
+ if (ptr < name) {
+ ret = -ENAMETOOLONG;
goto out;
+ }
*(ptr + len) = '/';
read_extent_buffer(l, ptr,(unsigned long)(iref + 1), len);
@@ -2024,8 +2057,6 @@
key.offset = (u64)-1;
dirid = key.objectid;
}
- if (ptr < name)
- goto out;
memmove(name, ptr, total_len);
name[total_len]='\0';
ret = 0;
@@ -2174,7 +2205,7 @@
* ref/backref.
*/
err = btrfs_subvolume_reserve_metadata(root, &block_rsv,
- 5, &qgroup_reserved);
+ 5, &qgroup_reserved, true);
if (err)
goto out_up_write;
@@ -2213,6 +2244,27 @@
goto out_end_trans;
}
}
+
+ ret = btrfs_uuid_tree_rem(trans, root->fs_info->uuid_root,
+ dest->root_item.uuid, BTRFS_UUID_KEY_SUBVOL,
+ dest->root_key.objectid);
+ if (ret && ret != -ENOENT) {
+ btrfs_abort_transaction(trans, root, ret);
+ err = ret;
+ goto out_end_trans;
+ }
+ if (!btrfs_is_empty_uuid(dest->root_item.received_uuid)) {
+ ret = btrfs_uuid_tree_rem(trans, root->fs_info->uuid_root,
+ dest->root_item.received_uuid,
+ BTRFS_UUID_KEY_RECEIVED_SUBVOL,
+ dest->root_key.objectid);
+ if (ret && ret != -ENOENT) {
+ btrfs_abort_transaction(trans, root, ret);
+ err = ret;
+ goto out_end_trans;
+ }
+ }
+
out_end_trans:
trans->block_rsv = NULL;
trans->bytes_reserved = 0;
@@ -2326,8 +2378,7 @@
if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
1)) {
- pr_info("btrfs: dev add/delete/balance/replace/resize operation in progress\n");
- return -EINVAL;
+ return BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
}
mutex_lock(&root->fs_info->volume_mutex);
@@ -2400,10 +2451,10 @@
if (!fi_args)
return -ENOMEM;
+ mutex_lock(&fs_devices->device_list_mutex);
fi_args->num_devices = fs_devices->num_devices;
memcpy(&fi_args->fsid, root->fs_info->fsid, sizeof(fi_args->fsid));
- mutex_lock(&fs_devices->device_list_mutex);
list_for_each_entry_safe(device, next, &fs_devices->devices, dev_list) {
if (device->devid > fi_args->max_id)
fi_args->max_id = device->devid;
@@ -2424,7 +2475,6 @@
struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices;
int ret = 0;
char *s_uuid = NULL;
- char empty_uuid[BTRFS_UUID_SIZE] = {0};
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -2433,7 +2483,7 @@
if (IS_ERR(di_args))
return PTR_ERR(di_args);
- if (memcmp(empty_uuid, di_args->uuid, BTRFS_UUID_SIZE) != 0)
+ if (!btrfs_is_empty_uuid(di_args->uuid))
s_uuid = di_args->uuid;
mutex_lock(&fs_devices->device_list_mutex);
@@ -2469,150 +2519,336 @@
return ret;
}
-static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
- u64 off, u64 olen, u64 destoff)
+static struct page *extent_same_get_page(struct inode *inode, u64 off)
{
- struct inode *inode = file_inode(file);
- struct btrfs_root *root = BTRFS_I(inode)->root;
- struct fd src_file;
- struct inode *src;
- struct btrfs_trans_handle *trans;
- struct btrfs_path *path;
- struct extent_buffer *leaf;
- char *buf;
- struct btrfs_key key;
- u32 nritems;
- int slot;
- int ret;
- u64 len = olen;
- u64 bs = root->fs_info->sb->s_blocksize;
- int same_inode = 0;
+ struct page *page;
+ pgoff_t index;
+ struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
- /*
- * TODO:
- * - split compressed inline extents. annoying: we need to
- * decompress into destination's address_space (the file offset
- * may change, so source mapping won't do), then recompress (or
- * otherwise reinsert) a subrange.
- * - allow ranges within the same file to be cloned (provided
- * they don't overlap)?
- */
+ index = off >> PAGE_CACHE_SHIFT;
- /* the destination must be opened for writing */
- if (!(file->f_mode & FMODE_WRITE) || (file->f_flags & O_APPEND))
+ page = grab_cache_page(inode->i_mapping, index);
+ if (!page)
+ return NULL;
+
+ if (!PageUptodate(page)) {
+ if (extent_read_full_page_nolock(tree, page, btrfs_get_extent,
+ 0))
+ return NULL;
+ lock_page(page);
+ if (!PageUptodate(page)) {
+ unlock_page(page);
+ page_cache_release(page);
+ return NULL;
+ }
+ }
+ unlock_page(page);
+
+ return page;
+}
+
+static inline void lock_extent_range(struct inode *inode, u64 off, u64 len)
+{
+ /* do any pending delalloc/csum calc on src, one way or
+ another, and lock file content */
+ while (1) {
+ struct btrfs_ordered_extent *ordered;
+ lock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1);
+ ordered = btrfs_lookup_first_ordered_extent(inode,
+ off + len - 1);
+ if (!ordered &&
+ !test_range_bit(&BTRFS_I(inode)->io_tree, off,
+ off + len - 1, EXTENT_DELALLOC, 0, NULL))
+ break;
+ unlock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1);
+ if (ordered)
+ btrfs_put_ordered_extent(ordered);
+ btrfs_wait_ordered_range(inode, off, len);
+ }
+}
+
+static void btrfs_double_unlock(struct inode *inode1, u64 loff1,
+ struct inode *inode2, u64 loff2, u64 len)
+{
+ unlock_extent(&BTRFS_I(inode1)->io_tree, loff1, loff1 + len - 1);
+ unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1);
+
+ mutex_unlock(&inode1->i_mutex);
+ mutex_unlock(&inode2->i_mutex);
+}
+
+static void btrfs_double_lock(struct inode *inode1, u64 loff1,
+ struct inode *inode2, u64 loff2, u64 len)
+{
+ if (inode1 < inode2) {
+ swap(inode1, inode2);
+ swap(loff1, loff2);
+ }
+
+ mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT);
+ lock_extent_range(inode1, loff1, len);
+ if (inode1 != inode2) {
+ mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD);
+ lock_extent_range(inode2, loff2, len);
+ }
+}
+
+static int btrfs_cmp_data(struct inode *src, u64 loff, struct inode *dst,
+ u64 dst_loff, u64 len)
+{
+ int ret = 0;
+ struct page *src_page, *dst_page;
+ unsigned int cmp_len = PAGE_CACHE_SIZE;
+ void *addr, *dst_addr;
+
+ while (len) {
+ if (len < PAGE_CACHE_SIZE)
+ cmp_len = len;
+
+ src_page = extent_same_get_page(src, loff);
+ if (!src_page)
+ return -EINVAL;
+ dst_page = extent_same_get_page(dst, dst_loff);
+ if (!dst_page) {
+ page_cache_release(src_page);
+ return -EINVAL;
+ }
+ addr = kmap_atomic(src_page);
+ dst_addr = kmap_atomic(dst_page);
+
+ flush_dcache_page(src_page);
+ flush_dcache_page(dst_page);
+
+ if (memcmp(addr, dst_addr, cmp_len))
+ ret = BTRFS_SAME_DATA_DIFFERS;
+
+ kunmap_atomic(addr);
+ kunmap_atomic(dst_addr);
+ page_cache_release(src_page);
+ page_cache_release(dst_page);
+
+ if (ret)
+ break;
+
+ loff += cmp_len;
+ dst_loff += cmp_len;
+ len -= cmp_len;
+ }
+
+ return ret;
+}
+
+static int extent_same_check_offsets(struct inode *inode, u64 off, u64 len)
+{
+ u64 bs = BTRFS_I(inode)->root->fs_info->sb->s_blocksize;
+
+ if (off + len > inode->i_size || off + len < off)
+ return -EINVAL;
+ /* Check that we are block aligned - btrfs_clone() requires this */
+ if (!IS_ALIGNED(off, bs) || !IS_ALIGNED(off + len, bs))
return -EINVAL;
- if (btrfs_root_readonly(root))
- return -EROFS;
+ return 0;
+}
+
+static int btrfs_extent_same(struct inode *src, u64 loff, u64 len,
+ struct inode *dst, u64 dst_loff)
+{
+ int ret;
+
+ /*
+ * btrfs_clone() can't handle extents in the same file
+ * yet. Once that works, we can drop this check and replace it
+ * with a check for the same inode, but overlapping extents.
+ */
+ if (src == dst)
+ return -EINVAL;
+
+ btrfs_double_lock(src, loff, dst, dst_loff, len);
+
+ ret = extent_same_check_offsets(src, loff, len);
+ if (ret)
+ goto out_unlock;
+
+ ret = extent_same_check_offsets(dst, dst_loff, len);
+ if (ret)
+ goto out_unlock;
+
+ /* don't make the dst file partly checksummed */
+ if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) !=
+ (BTRFS_I(dst)->flags & BTRFS_INODE_NODATASUM)) {
+ ret = -EINVAL;
+ goto out_unlock;
+ }
+
+ ret = btrfs_cmp_data(src, loff, dst, dst_loff, len);
+ if (ret == 0)
+ ret = btrfs_clone(src, dst, loff, len, len, dst_loff);
+
+out_unlock:
+ btrfs_double_unlock(src, loff, dst, dst_loff, len);
+
+ return ret;
+}
+
+#define BTRFS_MAX_DEDUPE_LEN (16 * 1024 * 1024)
+
+static long btrfs_ioctl_file_extent_same(struct file *file,
+ void __user *argp)
+{
+ struct btrfs_ioctl_same_args *args = argp;
+ struct btrfs_ioctl_same_args same;
+ struct btrfs_ioctl_same_extent_info info;
+ struct inode *src = file->f_dentry->d_inode;
+ struct file *dst_file = NULL;
+ struct inode *dst;
+ u64 off;
+ u64 len;
+ int i;
+ int ret;
+ u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize;
+ bool is_admin = capable(CAP_SYS_ADMIN);
+
+ if (!(file->f_mode & FMODE_READ))
+ return -EINVAL;
ret = mnt_want_write_file(file);
if (ret)
return ret;
- src_file = fdget(srcfd);
- if (!src_file.file) {
- ret = -EBADF;
- goto out_drop_write;
+ if (copy_from_user(&same,
+ (struct btrfs_ioctl_same_args __user *)argp,
+ sizeof(same))) {
+ ret = -EFAULT;
+ goto out;
}
- ret = -EXDEV;
- if (src_file.file->f_path.mnt != file->f_path.mnt)
- goto out_fput;
+ off = same.logical_offset;
+ len = same.length;
- src = file_inode(src_file.file);
+ /*
+ * Limit the total length we will dedupe for each operation.
+ * This is intended to bound the total time spent in this
+ * ioctl to something sane.
+ */
+ if (len > BTRFS_MAX_DEDUPE_LEN)
+ len = BTRFS_MAX_DEDUPE_LEN;
- ret = -EINVAL;
- if (src == inode)
- same_inode = 1;
-
- /* the src must be open for reading */
- if (!(src_file.file->f_mode & FMODE_READ))
- goto out_fput;
-
- /* don't make the dst file partly checksummed */
- if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) !=
- (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM))
- goto out_fput;
+ if (WARN_ON_ONCE(bs < PAGE_CACHE_SIZE)) {
+ /*
+ * Btrfs does not support blocksize < page_size. As a
+ * result, btrfs_cmp_data() won't correctly handle
+ * this situation without an update.
+ */
+ ret = -EINVAL;
+ goto out;
+ }
ret = -EISDIR;
- if (S_ISDIR(src->i_mode) || S_ISDIR(inode->i_mode))
- goto out_fput;
+ if (S_ISDIR(src->i_mode))
+ goto out;
- ret = -EXDEV;
- if (src->i_sb != inode->i_sb)
- goto out_fput;
+ ret = -EACCES;
+ if (!S_ISREG(src->i_mode))
+ goto out;
+
+ ret = 0;
+ for (i = 0; i < same.dest_count; i++) {
+ if (copy_from_user(&info, &args->info[i], sizeof(info))) {
+ ret = -EFAULT;
+ goto out;
+ }
+
+ info.bytes_deduped = 0;
+
+ dst_file = fget(info.fd);
+ if (!dst_file) {
+ info.status = -EBADF;
+ goto next;
+ }
+
+ if (!(is_admin || (dst_file->f_mode & FMODE_WRITE))) {
+ info.status = -EINVAL;
+ goto next;
+ }
+
+ info.status = -EXDEV;
+ if (file->f_path.mnt != dst_file->f_path.mnt)
+ goto next;
+
+ dst = dst_file->f_dentry->d_inode;
+ if (src->i_sb != dst->i_sb)
+ goto next;
+
+ if (S_ISDIR(dst->i_mode)) {
+ info.status = -EISDIR;
+ goto next;
+ }
+
+ if (!S_ISREG(dst->i_mode)) {
+ info.status = -EACCES;
+ goto next;
+ }
+
+ info.status = btrfs_extent_same(src, off, len, dst,
+ info.logical_offset);
+ if (info.status == 0)
+ info.bytes_deduped += len;
+
+next:
+ if (dst_file)
+ fput(dst_file);
+
+ if (__put_user_unaligned(info.status, &args->info[i].status) ||
+ __put_user_unaligned(info.bytes_deduped,
+ &args->info[i].bytes_deduped)) {
+ ret = -EFAULT;
+ goto out;
+ }
+ }
+
+out:
+ mnt_drop_write_file(file);
+ return ret;
+}
+
+/**
+ * btrfs_clone() - clone a range from inode file to another
+ *
+ * @src: Inode to clone from
+ * @inode: Inode to clone to
+ * @off: Offset within source to start clone from
+ * @olen: Original length, passed by user, of range to clone
+ * @olen_aligned: Block-aligned value of olen, extent_same uses
+ * identical values here
+ * @destoff: Offset within @inode to start clone
+ */
+static int btrfs_clone(struct inode *src, struct inode *inode,
+ u64 off, u64 olen, u64 olen_aligned, u64 destoff)
+{
+ struct btrfs_root *root = BTRFS_I(inode)->root;
+ struct btrfs_path *path = NULL;
+ struct extent_buffer *leaf;
+ struct btrfs_trans_handle *trans;
+ char *buf = NULL;
+ struct btrfs_key key;
+ u32 nritems;
+ int slot;
+ int ret;
+ u64 len = olen_aligned;
ret = -ENOMEM;
buf = vmalloc(btrfs_level_size(root, 0));
if (!buf)
- goto out_fput;
+ return ret;
path = btrfs_alloc_path();
if (!path) {
vfree(buf);
- goto out_fput;
+ return ret;
}
+
path->reada = 2;
-
- if (!same_inode) {
- if (inode < src) {
- mutex_lock_nested(&inode->i_mutex, I_MUTEX_PARENT);
- mutex_lock_nested(&src->i_mutex, I_MUTEX_CHILD);
- } else {
- mutex_lock_nested(&src->i_mutex, I_MUTEX_PARENT);
- mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD);
- }
- } else {
- mutex_lock(&src->i_mutex);
- }
-
- /* determine range to clone */
- ret = -EINVAL;
- if (off + len > src->i_size || off + len < off)
- goto out_unlock;
- if (len == 0)
- olen = len = src->i_size - off;
- /* if we extend to eof, continue to block boundary */
- if (off + len == src->i_size)
- len = ALIGN(src->i_size, bs) - off;
-
- /* verify the end result is block aligned */
- if (!IS_ALIGNED(off, bs) || !IS_ALIGNED(off + len, bs) ||
- !IS_ALIGNED(destoff, bs))
- goto out_unlock;
-
- /* verify if ranges are overlapped within the same file */
- if (same_inode) {
- if (destoff + len > off && destoff < off + len)
- goto out_unlock;
- }
-
- if (destoff > inode->i_size) {
- ret = btrfs_cont_expand(inode, inode->i_size, destoff);
- if (ret)
- goto out_unlock;
- }
-
- /* truncate page cache pages from target inode range */
- truncate_inode_pages_range(&inode->i_data, destoff,
- PAGE_CACHE_ALIGN(destoff + len) - 1);
-
- /* do any pending delalloc/csum calc on src, one way or
- another, and lock file content */
- while (1) {
- struct btrfs_ordered_extent *ordered;
- lock_extent(&BTRFS_I(src)->io_tree, off, off + len - 1);
- ordered = btrfs_lookup_first_ordered_extent(src, off + len - 1);
- if (!ordered &&
- !test_range_bit(&BTRFS_I(src)->io_tree, off, off + len - 1,
- EXTENT_DELALLOC, 0, NULL))
- break;
- unlock_extent(&BTRFS_I(src)->io_tree, off, off + len - 1);
- if (ordered)
- btrfs_put_ordered_extent(ordered);
- btrfs_wait_ordered_range(src, off, len);
- }
-
/* clone data */
key.objectid = btrfs_ino(src);
key.type = BTRFS_EXTENT_DATA_KEY;
@@ -2858,15 +3094,132 @@
key.offset++;
}
ret = 0;
+
out:
btrfs_release_path(path);
+ btrfs_free_path(path);
+ vfree(buf);
+ return ret;
+}
+
+static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
+ u64 off, u64 olen, u64 destoff)
+{
+ struct inode *inode = fdentry(file)->d_inode;
+ struct btrfs_root *root = BTRFS_I(inode)->root;
+ struct fd src_file;
+ struct inode *src;
+ int ret;
+ u64 len = olen;
+ u64 bs = root->fs_info->sb->s_blocksize;
+ int same_inode = 0;
+
+ /*
+ * TODO:
+ * - split compressed inline extents. annoying: we need to
+ * decompress into destination's address_space (the file offset
+ * may change, so source mapping won't do), then recompress (or
+ * otherwise reinsert) a subrange.
+ * - allow ranges within the same file to be cloned (provided
+ * they don't overlap)?
+ */
+
+ /* the destination must be opened for writing */
+ if (!(file->f_mode & FMODE_WRITE) || (file->f_flags & O_APPEND))
+ return -EINVAL;
+
+ if (btrfs_root_readonly(root))
+ return -EROFS;
+
+ ret = mnt_want_write_file(file);
+ if (ret)
+ return ret;
+
+ src_file = fdget(srcfd);
+ if (!src_file.file) {
+ ret = -EBADF;
+ goto out_drop_write;
+ }
+
+ ret = -EXDEV;
+ if (src_file.file->f_path.mnt != file->f_path.mnt)
+ goto out_fput;
+
+ src = file_inode(src_file.file);
+
+ ret = -EINVAL;
+ if (src == inode)
+ same_inode = 1;
+
+ /* the src must be open for reading */
+ if (!(src_file.file->f_mode & FMODE_READ))
+ goto out_fput;
+
+ /* don't make the dst file partly checksummed */
+ if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) !=
+ (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM))
+ goto out_fput;
+
+ ret = -EISDIR;
+ if (S_ISDIR(src->i_mode) || S_ISDIR(inode->i_mode))
+ goto out_fput;
+
+ ret = -EXDEV;
+ if (src->i_sb != inode->i_sb)
+ goto out_fput;
+
+ if (!same_inode) {
+ if (inode < src) {
+ mutex_lock_nested(&inode->i_mutex, I_MUTEX_PARENT);
+ mutex_lock_nested(&src->i_mutex, I_MUTEX_CHILD);
+ } else {
+ mutex_lock_nested(&src->i_mutex, I_MUTEX_PARENT);
+ mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD);
+ }
+ } else {
+ mutex_lock(&src->i_mutex);
+ }
+
+ /* determine range to clone */
+ ret = -EINVAL;
+ if (off + len > src->i_size || off + len < off)
+ goto out_unlock;
+ if (len == 0)
+ olen = len = src->i_size - off;
+ /* if we extend to eof, continue to block boundary */
+ if (off + len == src->i_size)
+ len = ALIGN(src->i_size, bs) - off;
+
+ /* verify the end result is block aligned */
+ if (!IS_ALIGNED(off, bs) || !IS_ALIGNED(off + len, bs) ||
+ !IS_ALIGNED(destoff, bs))
+ goto out_unlock;
+
+ /* verify if ranges are overlapped within the same file */
+ if (same_inode) {
+ if (destoff + len > off && destoff < off + len)
+ goto out_unlock;
+ }
+
+ if (destoff > inode->i_size) {
+ ret = btrfs_cont_expand(inode, inode->i_size, destoff);
+ if (ret)
+ goto out_unlock;
+ }
+
+ /* truncate page cache pages from target inode range */
+ truncate_inode_pages_range(&inode->i_data, destoff,
+ PAGE_CACHE_ALIGN(destoff + len) - 1);
+
+ lock_extent_range(src, off, len);
+
+ ret = btrfs_clone(src, inode, off, olen, len, destoff);
+
unlock_extent(&BTRFS_I(src)->io_tree, off, off + len - 1);
out_unlock:
mutex_unlock(&src->i_mutex);
if (!same_inode)
mutex_unlock(&inode->i_mutex);
- vfree(buf);
- btrfs_free_path(path);
out_fput:
fdput(src_file);
out_drop_write:
@@ -3312,11 +3665,13 @@
switch (p->cmd) {
case BTRFS_IOCTL_DEV_REPLACE_CMD_START:
+ if (root->fs_info->sb->s_flags & MS_RDONLY)
+ return -EROFS;
+
if (atomic_xchg(
&root->fs_info->mutually_exclusive_operation_running,
1)) {
- pr_info("btrfs: dev add/delete/balance/replace/resize operation in progress\n");
- ret = -EINPROGRESS;
+ ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
} else {
ret = btrfs_dev_replace_start(root, p);
atomic_set(
@@ -3560,8 +3915,7 @@
} else {
/* this is (1) */
mutex_unlock(&fs_info->balance_mutex);
- pr_info("btrfs: dev add/delete/balance/replace/resize operation in progress\n");
- ret = -EINVAL;
+ ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
goto out;
}
@@ -3967,6 +4321,7 @@
struct btrfs_trans_handle *trans;
struct timespec ct = CURRENT_TIME;
int ret = 0;
+ int received_uuid_changed;
ret = mnt_want_write_file(file);
if (ret < 0)
@@ -3996,7 +4351,11 @@
goto out;
}
- trans = btrfs_start_transaction(root, 1);
+ /*
+ * 1 - root item
+ * 2 - uuid items (received uuid + subvol uuid)
+ */
+ trans = btrfs_start_transaction(root, 3);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
trans = NULL;
@@ -4007,24 +4366,42 @@
sa->rtime.sec = ct.tv_sec;
sa->rtime.nsec = ct.tv_nsec;
+ received_uuid_changed = memcmp(root_item->received_uuid, sa->uuid,
+ BTRFS_UUID_SIZE);
+ if (received_uuid_changed &&
+ !btrfs_is_empty_uuid(root_item->received_uuid))
+ btrfs_uuid_tree_rem(trans, root->fs_info->uuid_root,
+ root_item->received_uuid,
+ BTRFS_UUID_KEY_RECEIVED_SUBVOL,
+ root->root_key.objectid);
memcpy(root_item->received_uuid, sa->uuid, BTRFS_UUID_SIZE);
btrfs_set_root_stransid(root_item, sa->stransid);
btrfs_set_root_rtransid(root_item, sa->rtransid);
- root_item->stime.sec = cpu_to_le64(sa->stime.sec);
- root_item->stime.nsec = cpu_to_le32(sa->stime.nsec);
- root_item->rtime.sec = cpu_to_le64(sa->rtime.sec);
- root_item->rtime.nsec = cpu_to_le32(sa->rtime.nsec);
+ btrfs_set_stack_timespec_sec(&root_item->stime, sa->stime.sec);
+ btrfs_set_stack_timespec_nsec(&root_item->stime, sa->stime.nsec);
+ btrfs_set_stack_timespec_sec(&root_item->rtime, sa->rtime.sec);
+ btrfs_set_stack_timespec_nsec(&root_item->rtime, sa->rtime.nsec);
ret = btrfs_update_root(trans, root->fs_info->tree_root,
&root->root_key, &root->root_item);
if (ret < 0) {
btrfs_end_transaction(trans, root);
- trans = NULL;
goto out;
- } else {
- ret = btrfs_commit_transaction(trans, root);
- if (ret < 0)
+ }
+ if (received_uuid_changed && !btrfs_is_empty_uuid(sa->uuid)) {
+ ret = btrfs_uuid_tree_add(trans, root->fs_info->uuid_root,
+ sa->uuid,
+ BTRFS_UUID_KEY_RECEIVED_SUBVOL,
+ root->root_key.objectid);
+ if (ret < 0 && ret != -EEXIST) {
+ btrfs_abort_transaction(trans, root, ret);
goto out;
+ }
+ }
+ ret = btrfs_commit_transaction(trans, root);
+ if (ret < 0) {
+ btrfs_abort_transaction(trans, root, ret);
+ goto out;
}
ret = copy_to_user(arg, sa, sizeof(*sa));
@@ -4041,18 +4418,22 @@
static int btrfs_ioctl_get_fslabel(struct file *file, void __user *arg)
{
struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
- const char *label = root->fs_info->super_copy->label;
- size_t len = strnlen(label, BTRFS_LABEL_SIZE);
+ size_t len;
int ret;
+ char label[BTRFS_LABEL_SIZE];
+
+ spin_lock(&root->fs_info->super_lock);
+ memcpy(label, root->fs_info->super_copy->label, BTRFS_LABEL_SIZE);
+ spin_unlock(&root->fs_info->super_lock);
+
+ len = strnlen(label, BTRFS_LABEL_SIZE);
if (len == BTRFS_LABEL_SIZE) {
pr_warn("btrfs: label is too long, return the first %zu bytes\n",
--len);
}
- mutex_lock(&root->fs_info->volume_mutex);
ret = copy_to_user(arg, label, len);
- mutex_unlock(&root->fs_info->volume_mutex);
return ret ? -EFAULT : 0;
}
@@ -4081,18 +4462,18 @@
if (ret)
return ret;
- mutex_lock(&root->fs_info->volume_mutex);
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
goto out_unlock;
}
+ spin_lock(&root->fs_info->super_lock);
strcpy(super_block->label, label);
+ spin_unlock(&root->fs_info->super_lock);
ret = btrfs_end_transaction(trans, root);
out_unlock:
- mutex_unlock(&root->fs_info->volume_mutex);
mnt_drop_write_file(file);
return ret;
}
@@ -4207,6 +4588,8 @@
return btrfs_ioctl_get_fslabel(file, argp);
case BTRFS_IOC_SET_FSLABEL:
return btrfs_ioctl_set_fslabel(file, argp);
+ case BTRFS_IOC_FILE_EXTENT_SAME:
+ return btrfs_ioctl_file_extent_same(file, argp);
}
return -ENOTTY;
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index f93151a..b6a6f07 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -207,8 +207,10 @@
}
/* we're making it bigger, give up */
- if (tot_in > 8192 && tot_in < tot_out)
+ if (tot_in > 8192 && tot_in < tot_out) {
+ ret = -1;
goto out;
+ }
/* we're all done */
if (tot_in >= len)
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 8136982..966b413 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -67,7 +67,7 @@
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
btrfs_panic(fs_info, errno, "Inconsistency in ordered tree at offset "
- "%llu\n", (unsigned long long)offset);
+ "%llu\n", offset);
}
/*
@@ -205,6 +205,7 @@
entry->bytes_left = len;
entry->inode = igrab(inode);
entry->compress_type = compress_type;
+ entry->truncated_len = (u64)-1;
if (type != BTRFS_ORDERED_IO_DONE && type != BTRFS_ORDERED_COMPLETE)
set_bit(type, &entry->flags);
@@ -336,14 +337,12 @@
*file_offset = dec_end;
if (dec_start > dec_end) {
printk(KERN_CRIT "bad ordering dec_start %llu end %llu\n",
- (unsigned long long)dec_start,
- (unsigned long long)dec_end);
+ dec_start, dec_end);
}
to_dec = dec_end - dec_start;
if (to_dec > entry->bytes_left) {
printk(KERN_CRIT "bad ordered accounting left %llu size %llu\n",
- (unsigned long long)entry->bytes_left,
- (unsigned long long)to_dec);
+ entry->bytes_left, to_dec);
}
entry->bytes_left -= to_dec;
if (!uptodate)
@@ -403,8 +402,7 @@
if (io_size > entry->bytes_left) {
printk(KERN_CRIT "bad ordered accounting left %llu size %llu\n",
- (unsigned long long)entry->bytes_left,
- (unsigned long long)io_size);
+ entry->bytes_left, io_size);
}
entry->bytes_left -= io_size;
if (!uptodate)
@@ -671,7 +669,7 @@
INIT_LIST_HEAD(&splice);
INIT_LIST_HEAD(&works);
- mutex_lock(&root->fs_info->ordered_operations_mutex);
+ mutex_lock(&root->fs_info->ordered_extent_flush_mutex);
spin_lock(&root->fs_info->ordered_root_lock);
list_splice_init(&cur_trans->ordered_operations, &splice);
while (!list_empty(&splice)) {
@@ -718,7 +716,7 @@
list_del_init(&work->list);
btrfs_wait_and_free_delalloc_work(work);
}
- mutex_unlock(&root->fs_info->ordered_operations_mutex);
+ mutex_unlock(&root->fs_info->ordered_extent_flush_mutex);
return ret;
}
@@ -923,12 +921,16 @@
struct btrfs_ordered_extent *test;
int ret = 1;
- if (ordered)
- offset = entry_end(ordered);
- else
- offset = ALIGN(offset, BTRFS_I(inode)->root->sectorsize);
-
spin_lock_irq(&tree->lock);
+ if (ordered) {
+ offset = entry_end(ordered);
+ if (test_bit(BTRFS_ORDERED_TRUNCATED, &ordered->flags))
+ offset = min(offset,
+ ordered->file_offset +
+ ordered->truncated_len);
+ } else {
+ offset = ALIGN(offset, BTRFS_I(inode)->root->sectorsize);
+ }
disk_i_size = BTRFS_I(inode)->disk_i_size;
/* truncate file */
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 68844d5..d9a5aa0 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -69,6 +69,7 @@
* the isize. */
#define BTRFS_ORDERED_LOGGED_CSUM 8 /* We've logged the csums on this ordered
ordered extent */
+#define BTRFS_ORDERED_TRUNCATED 9 /* Set when we have to truncate an extent */
struct btrfs_ordered_extent {
/* logical offset in the file */
@@ -96,6 +97,12 @@
*/
u64 outstanding_isize;
+ /*
+ * If we get truncated we need to adjust the file extent we enter for
+ * this ordered extent so that we do not expose stale data.
+ */
+ u64 truncated_len;
+
/* flags (described above) */
unsigned long flags;
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index dc0024f..0088bed 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -26,14 +26,12 @@
int i;
printk(KERN_INFO "\t\tchunk length %llu owner %llu type %llu "
"num_stripes %d\n",
- (unsigned long long)btrfs_chunk_length(eb, chunk),
- (unsigned long long)btrfs_chunk_owner(eb, chunk),
- (unsigned long long)btrfs_chunk_type(eb, chunk),
- num_stripes);
+ btrfs_chunk_length(eb, chunk), btrfs_chunk_owner(eb, chunk),
+ btrfs_chunk_type(eb, chunk), num_stripes);
for (i = 0 ; i < num_stripes ; i++) {
printk(KERN_INFO "\t\t\tstripe %d devid %llu offset %llu\n", i,
- (unsigned long long)btrfs_stripe_devid_nr(eb, chunk, i),
- (unsigned long long)btrfs_stripe_offset_nr(eb, chunk, i));
+ btrfs_stripe_devid_nr(eb, chunk, i),
+ btrfs_stripe_offset_nr(eb, chunk, i));
}
}
static void print_dev_item(struct extent_buffer *eb,
@@ -41,18 +39,18 @@
{
printk(KERN_INFO "\t\tdev item devid %llu "
"total_bytes %llu bytes used %llu\n",
- (unsigned long long)btrfs_device_id(eb, dev_item),
- (unsigned long long)btrfs_device_total_bytes(eb, dev_item),
- (unsigned long long)btrfs_device_bytes_used(eb, dev_item));
+ btrfs_device_id(eb, dev_item),
+ btrfs_device_total_bytes(eb, dev_item),
+ btrfs_device_bytes_used(eb, dev_item));
}
static void print_extent_data_ref(struct extent_buffer *eb,
struct btrfs_extent_data_ref *ref)
{
printk(KERN_INFO "\t\textent data backref root %llu "
"objectid %llu offset %llu count %u\n",
- (unsigned long long)btrfs_extent_data_ref_root(eb, ref),
- (unsigned long long)btrfs_extent_data_ref_objectid(eb, ref),
- (unsigned long long)btrfs_extent_data_ref_offset(eb, ref),
+ btrfs_extent_data_ref_root(eb, ref),
+ btrfs_extent_data_ref_objectid(eb, ref),
+ btrfs_extent_data_ref_offset(eb, ref),
btrfs_extent_data_ref_count(eb, ref));
}
@@ -87,19 +85,17 @@
flags = btrfs_extent_flags(eb, ei);
printk(KERN_INFO "\t\textent refs %llu gen %llu flags %llu\n",
- (unsigned long long)btrfs_extent_refs(eb, ei),
- (unsigned long long)btrfs_extent_generation(eb, ei),
- (unsigned long long)flags);
+ btrfs_extent_refs(eb, ei), btrfs_extent_generation(eb, ei),
+ flags);
if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
struct btrfs_tree_block_info *info;
info = (struct btrfs_tree_block_info *)(ei + 1);
btrfs_tree_block_key(eb, info, &key);
- printk(KERN_INFO "\t\ttree block key (%llu %x %llu) "
+ printk(KERN_INFO "\t\ttree block key (%llu %u %llu) "
"level %d\n",
- (unsigned long long)btrfs_disk_key_objectid(&key),
- key.type,
- (unsigned long long)btrfs_disk_key_offset(&key),
+ btrfs_disk_key_objectid(&key), key.type,
+ btrfs_disk_key_offset(&key),
btrfs_tree_block_level(eb, info));
iref = (struct btrfs_extent_inline_ref *)(info + 1);
} else {
@@ -115,11 +111,11 @@
switch (type) {
case BTRFS_TREE_BLOCK_REF_KEY:
printk(KERN_INFO "\t\ttree block backref "
- "root %llu\n", (unsigned long long)offset);
+ "root %llu\n", offset);
break;
case BTRFS_SHARED_BLOCK_REF_KEY:
printk(KERN_INFO "\t\tshared block backref "
- "parent %llu\n", (unsigned long long)offset);
+ "parent %llu\n", offset);
break;
case BTRFS_EXTENT_DATA_REF_KEY:
dref = (struct btrfs_extent_data_ref *)(&iref->offset);
@@ -129,8 +125,7 @@
sref = (struct btrfs_shared_data_ref *)(iref + 1);
printk(KERN_INFO "\t\tshared data backref "
"parent %llu count %u\n",
- (unsigned long long)offset,
- btrfs_shared_data_ref_count(eb, sref));
+ offset, btrfs_shared_data_ref_count(eb, sref));
break;
default:
BUG();
@@ -148,13 +143,32 @@
ref0 = btrfs_item_ptr(eb, slot, struct btrfs_extent_ref_v0);
printk("\t\textent back ref root %llu gen %llu "
"owner %llu num_refs %lu\n",
- (unsigned long long)btrfs_ref_root_v0(eb, ref0),
- (unsigned long long)btrfs_ref_generation_v0(eb, ref0),
- (unsigned long long)btrfs_ref_objectid_v0(eb, ref0),
+ btrfs_ref_root_v0(eb, ref0),
+ btrfs_ref_generation_v0(eb, ref0),
+ btrfs_ref_objectid_v0(eb, ref0),
(unsigned long)btrfs_ref_count_v0(eb, ref0));
}
#endif
+static void print_uuid_item(struct extent_buffer *l, unsigned long offset,
+ u32 item_size)
+{
+ if (!IS_ALIGNED(item_size, sizeof(u64))) {
+ pr_warn("btrfs: uuid item with illegal size %lu!\n",
+ (unsigned long)item_size);
+ return;
+ }
+ while (item_size) {
+ __le64 subvol_id;
+
+ read_extent_buffer(l, &subvol_id, offset, sizeof(subvol_id));
+ printk(KERN_INFO "\t\tsubvol_id %llu\n",
+ (unsigned long long)le64_to_cpu(subvol_id));
+ item_size -= sizeof(u64);
+ offset += sizeof(u64);
+ }
+}
+
void btrfs_print_leaf(struct btrfs_root *root, struct extent_buffer *l)
{
int i;
@@ -177,39 +191,34 @@
nr = btrfs_header_nritems(l);
btrfs_info(root->fs_info, "leaf %llu total ptrs %d free space %d",
- (unsigned long long)btrfs_header_bytenr(l), nr,
- btrfs_leaf_free_space(root, l));
+ btrfs_header_bytenr(l), nr, btrfs_leaf_free_space(root, l));
for (i = 0 ; i < nr ; i++) {
item = btrfs_item_nr(l, i);
btrfs_item_key_to_cpu(l, &key, i);
type = btrfs_key_type(&key);
- printk(KERN_INFO "\titem %d key (%llu %x %llu) itemoff %d "
+ printk(KERN_INFO "\titem %d key (%llu %u %llu) itemoff %d "
"itemsize %d\n",
- i,
- (unsigned long long)key.objectid, type,
- (unsigned long long)key.offset,
+ i, key.objectid, type, key.offset,
btrfs_item_offset(l, item), btrfs_item_size(l, item));
switch (type) {
case BTRFS_INODE_ITEM_KEY:
ii = btrfs_item_ptr(l, i, struct btrfs_inode_item);
printk(KERN_INFO "\t\tinode generation %llu size %llu "
"mode %o\n",
- (unsigned long long)
btrfs_inode_generation(l, ii),
- (unsigned long long)btrfs_inode_size(l, ii),
+ btrfs_inode_size(l, ii),
btrfs_inode_mode(l, ii));
break;
case BTRFS_DIR_ITEM_KEY:
di = btrfs_item_ptr(l, i, struct btrfs_dir_item);
btrfs_dir_item_key_to_cpu(l, di, &found_key);
printk(KERN_INFO "\t\tdir oid %llu type %u\n",
- (unsigned long long)found_key.objectid,
+ found_key.objectid,
btrfs_dir_type(l, di));
break;
case BTRFS_ROOT_ITEM_KEY:
ri = btrfs_item_ptr(l, i, struct btrfs_root_item);
printk(KERN_INFO "\t\troot data bytenr %llu refs %u\n",
- (unsigned long long)
btrfs_disk_root_bytenr(l, ri),
btrfs_disk_root_refs(l, ri));
break;
@@ -245,17 +254,12 @@
}
printk(KERN_INFO "\t\textent data disk bytenr %llu "
"nr %llu\n",
- (unsigned long long)
btrfs_file_extent_disk_bytenr(l, fi),
- (unsigned long long)
btrfs_file_extent_disk_num_bytes(l, fi));
printk(KERN_INFO "\t\textent data offset %llu "
"nr %llu ram %llu\n",
- (unsigned long long)
btrfs_file_extent_offset(l, fi),
- (unsigned long long)
btrfs_file_extent_num_bytes(l, fi),
- (unsigned long long)
btrfs_file_extent_ram_bytes(l, fi));
break;
case BTRFS_EXTENT_REF_V0_KEY:
@@ -269,7 +273,6 @@
bi = btrfs_item_ptr(l, i,
struct btrfs_block_group_item);
printk(KERN_INFO "\t\tblock group used %llu\n",
- (unsigned long long)
btrfs_disk_block_group_used(l, bi));
break;
case BTRFS_CHUNK_ITEM_KEY:
@@ -286,13 +289,9 @@
printk(KERN_INFO "\t\tdev extent chunk_tree %llu\n"
"\t\tchunk objectid %llu chunk offset %llu "
"length %llu\n",
- (unsigned long long)
btrfs_dev_extent_chunk_tree(l, dev_extent),
- (unsigned long long)
btrfs_dev_extent_chunk_objectid(l, dev_extent),
- (unsigned long long)
btrfs_dev_extent_chunk_offset(l, dev_extent),
- (unsigned long long)
btrfs_dev_extent_length(l, dev_extent));
break;
case BTRFS_DEV_STATS_KEY:
@@ -301,6 +300,11 @@
case BTRFS_DEV_REPLACE_KEY:
printk(KERN_INFO "\t\tdev replace\n");
break;
+ case BTRFS_UUID_KEY_SUBVOL:
+ case BTRFS_UUID_KEY_RECEIVED_SUBVOL:
+ print_uuid_item(l, btrfs_item_ptr_offset(l, i),
+ btrfs_item_size_nr(l, i));
+ break;
};
}
}
@@ -320,16 +324,13 @@
return;
}
btrfs_info(root->fs_info, "node %llu level %d total ptrs %d free spc %u",
- (unsigned long long)btrfs_header_bytenr(c),
- level, nr, (u32)BTRFS_NODEPTRS_PER_BLOCK(root) - nr);
+ btrfs_header_bytenr(c), level, nr,
+ (u32)BTRFS_NODEPTRS_PER_BLOCK(root) - nr);
for (i = 0; i < nr; i++) {
btrfs_node_key_to_cpu(c, &key, i);
printk(KERN_INFO "\tkey %d (%llu %u %llu) block %llu\n",
- i,
- (unsigned long long)key.objectid,
- key.type,
- (unsigned long long)key.offset,
- (unsigned long long)btrfs_node_blockptr(c, i));
+ i, key.objectid, key.type, key.offset,
+ btrfs_node_blockptr(c, i));
}
for (i = 0; i < nr; i++) {
struct extent_buffer *next = read_tree_block(root,
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 1280eff..4e6ef49 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -157,18 +157,11 @@
return qgroup;
}
-/* must be called with qgroup_lock held */
-static int del_qgroup_rb(struct btrfs_fs_info *fs_info, u64 qgroupid)
+static void __del_qgroup_rb(struct btrfs_qgroup *qgroup)
{
- struct btrfs_qgroup *qgroup = find_qgroup_rb(fs_info, qgroupid);
struct btrfs_qgroup_list *list;
- if (!qgroup)
- return -ENOENT;
-
- rb_erase(&qgroup->node, &fs_info->qgroup_tree);
list_del(&qgroup->dirty);
-
while (!list_empty(&qgroup->groups)) {
list = list_first_entry(&qgroup->groups,
struct btrfs_qgroup_list, next_group);
@@ -185,7 +178,18 @@
kfree(list);
}
kfree(qgroup);
+}
+/* must be called with qgroup_lock held */
+static int del_qgroup_rb(struct btrfs_fs_info *fs_info, u64 qgroupid)
+{
+ struct btrfs_qgroup *qgroup = find_qgroup_rb(fs_info, qgroupid);
+
+ if (!qgroup)
+ return -ENOENT;
+
+ rb_erase(&qgroup->node, &fs_info->qgroup_tree);
+ __del_qgroup_rb(qgroup);
return 0;
}
@@ -394,8 +398,7 @@
if (ret == -ENOENT) {
printk(KERN_WARNING
"btrfs: orphan qgroup relation 0x%llx->0x%llx\n",
- (unsigned long long)found_key.objectid,
- (unsigned long long)found_key.offset);
+ found_key.objectid, found_key.offset);
ret = 0; /* ignore the error */
}
if (ret)
@@ -428,39 +431,28 @@
}
/*
- * This is only called from close_ctree() or open_ctree(), both in single-
- * treaded paths. Clean up the in-memory structures. No locking needed.
+ * This is called from close_ctree() or open_ctree() or btrfs_quota_disable(),
+ * first two are in single-threaded paths.And for the third one, we have set
+ * quota_root to be null with qgroup_lock held before, so it is safe to clean
+ * up the in-memory structures without qgroup_lock held.
*/
void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info)
{
struct rb_node *n;
struct btrfs_qgroup *qgroup;
- struct btrfs_qgroup_list *list;
while ((n = rb_first(&fs_info->qgroup_tree))) {
qgroup = rb_entry(n, struct btrfs_qgroup, node);
rb_erase(n, &fs_info->qgroup_tree);
-
- while (!list_empty(&qgroup->groups)) {
- list = list_first_entry(&qgroup->groups,
- struct btrfs_qgroup_list,
- next_group);
- list_del(&list->next_group);
- list_del(&list->next_member);
- kfree(list);
- }
-
- while (!list_empty(&qgroup->members)) {
- list = list_first_entry(&qgroup->members,
- struct btrfs_qgroup_list,
- next_member);
- list_del(&list->next_group);
- list_del(&list->next_member);
- kfree(list);
- }
- kfree(qgroup);
+ __del_qgroup_rb(qgroup);
}
+ /*
+ * we call btrfs_free_qgroup_config() when umounting
+ * filesystem and disabling quota, so we set qgroup_ulit
+ * to be null here to avoid double free.
+ */
ulist_free(fs_info->qgroup_ulist);
+ fs_info->qgroup_ulist = NULL;
}
static int add_qgroup_relation_item(struct btrfs_trans_handle *trans,
@@ -946,13 +938,9 @@
fs_info->pending_quota_state = 0;
quota_root = fs_info->quota_root;
fs_info->quota_root = NULL;
- btrfs_free_qgroup_config(fs_info);
spin_unlock(&fs_info->qgroup_lock);
- if (!quota_root) {
- ret = -EINVAL;
- goto out;
- }
+ btrfs_free_qgroup_config(fs_info);
ret = btrfs_clean_quota_tree(trans, quota_root);
if (ret)
@@ -1174,7 +1162,7 @@
if (ret) {
fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
printk(KERN_INFO "unable to update quota limit for %llu\n",
- (unsigned long long)qgroupid);
+ qgroupid);
}
spin_lock(&fs_info->qgroup_lock);
@@ -1884,10 +1872,9 @@
path, 1, 0);
pr_debug("current progress key (%llu %u %llu), search_slot ret %d\n",
- (unsigned long long)fs_info->qgroup_rescan_progress.objectid,
+ fs_info->qgroup_rescan_progress.objectid,
fs_info->qgroup_rescan_progress.type,
- (unsigned long long)fs_info->qgroup_rescan_progress.offset,
- ret);
+ fs_info->qgroup_rescan_progress.offset, ret);
if (ret) {
/*
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 0525e13..d0ecfbd 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -1540,8 +1540,10 @@
int ret;
ret = alloc_rbio_parity_pages(rbio);
- if (ret)
+ if (ret) {
+ __free_raid_bio(rbio);
return ret;
+ }
ret = lock_stripe_add(rbio);
if (ret == 0)
@@ -1687,11 +1689,8 @@
struct blk_plug_cb *cb;
rbio = alloc_rbio(root, bbio, raid_map, stripe_len);
- if (IS_ERR(rbio)) {
- kfree(raid_map);
- kfree(bbio);
+ if (IS_ERR(rbio))
return PTR_ERR(rbio);
- }
bio_list_add(&rbio->bio_list, bio);
rbio->bio_list_bytes = bio->bi_size;
@@ -2041,9 +2040,8 @@
int ret;
rbio = alloc_rbio(root, bbio, raid_map, stripe_len);
- if (IS_ERR(rbio)) {
+ if (IS_ERR(rbio))
return PTR_ERR(rbio);
- }
rbio->read_rebuild = 1;
bio_list_add(&rbio->bio_list, bio);
@@ -2052,6 +2050,8 @@
rbio->faila = find_logical_bio_stripe(rbio, bio);
if (rbio->faila == -1) {
BUG();
+ kfree(raid_map);
+ kfree(bbio);
kfree(rbio);
return -EIO;
}
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 1209649..aacc212 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -335,7 +335,7 @@
if (bnode->root)
fs_info = bnode->root->fs_info;
btrfs_panic(fs_info, errno, "Inconsistency in backref cache "
- "found at offset %llu\n", (unsigned long long)bytenr);
+ "found at offset %llu\n", bytenr);
}
/*
@@ -641,6 +641,11 @@
WARN_ON(item_size < sizeof(*ei) + sizeof(*bi));
return 1;
}
+ if (key.type == BTRFS_METADATA_ITEM_KEY &&
+ item_size <= sizeof(*ei)) {
+ WARN_ON(item_size < sizeof(*ei));
+ return 1;
+ }
if (key.type == BTRFS_EXTENT_ITEM_KEY) {
bi = (struct btrfs_tree_block_info *)(ei + 1);
@@ -691,6 +696,7 @@
int cowonly;
int ret;
int err = 0;
+ bool need_check = true;
path1 = btrfs_alloc_path();
path2 = btrfs_alloc_path();
@@ -914,6 +920,7 @@
cur->bytenr);
lower = cur;
+ need_check = true;
for (; level < BTRFS_MAX_LEVEL; level++) {
if (!path2->nodes[level]) {
BUG_ON(btrfs_root_bytenr(&root->root_item) !=
@@ -957,14 +964,12 @@
/*
* add the block to pending list if we
- * need check its backrefs. only block
- * at 'cur->level + 1' is added to the
- * tail of pending list. this guarantees
- * we check backrefs from lower level
- * blocks to upper level blocks.
+ * need check its backrefs, we only do this once
+ * while walking up a tree as we will catch
+ * anything else later on.
*/
- if (!upper->checked &&
- level == cur->level + 1) {
+ if (!upper->checked && need_check) {
+ need_check = false;
list_add_tail(&edge->list[UPPER],
&list);
} else
@@ -2314,8 +2319,13 @@
BUG_ON(root->reloc_root != reloc_root);
ret = merge_reloc_root(rc, root);
- if (ret)
+ if (ret) {
+ __update_reloc_root(reloc_root, 1);
+ free_extent_buffer(reloc_root->node);
+ free_extent_buffer(reloc_root->commit_root);
+ kfree(reloc_root);
goto out;
+ }
} else {
list_del_init(&reloc_root->root_list);
}
@@ -2344,9 +2354,6 @@
if (IS_ERR(root))
continue;
- if (btrfs_root_refs(&root->root_item) == 0)
- continue;
-
trans = btrfs_join_transaction(root);
BUG_ON(IS_ERR(trans));
@@ -3628,7 +3635,7 @@
unsigned long ptr;
unsigned long end;
u32 blocksize = btrfs_level_size(rc->extent_root, 0);
- int ret;
+ int ret = 0;
int err = 0;
eb = path->nodes[0];
@@ -3655,6 +3662,10 @@
} else {
BUG();
}
+ if (ret) {
+ err = ret;
+ goto out;
+ }
ptr += btrfs_extent_inline_ref_size(key.type);
}
WARN_ON(ptr > end);
@@ -3700,6 +3711,7 @@
}
path->slots[0]++;
}
+out:
btrfs_release_path(path);
if (err)
free_block_list(blocks);
@@ -4219,8 +4231,7 @@
}
printk(KERN_INFO "btrfs: relocating block group %llu flags %llu\n",
- (unsigned long long)rc->block_group->key.objectid,
- (unsigned long long)rc->block_group->flags);
+ rc->block_group->key.objectid, rc->block_group->flags);
ret = btrfs_start_all_delalloc_inodes(fs_info, 0);
if (ret < 0) {
@@ -4242,7 +4253,7 @@
break;
printk(KERN_INFO "btrfs: found %llu extents\n",
- (unsigned long long)rc->extents_found);
+ rc->extents_found);
if (rc->stage == MOVE_DATA_EXTENTS && rc->found_file_extent) {
btrfs_wait_ordered_range(rc->data_inode, 0, (u64)-1);
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index ffb1036..0b1f4ef 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -29,8 +29,8 @@
* generation numbers as then we know the root was once mounted with an older
* kernel that was not aware of the root item structure change.
*/
-void btrfs_read_root_item(struct extent_buffer *eb, int slot,
- struct btrfs_root_item *item)
+static void btrfs_read_root_item(struct extent_buffer *eb, int slot,
+ struct btrfs_root_item *item)
{
uuid_le uuid;
int len;
@@ -155,8 +155,7 @@
if (ret != 0) {
btrfs_print_leaf(root, path->nodes[0]);
printk(KERN_CRIT "unable to update root key %llu %u %llu\n",
- (unsigned long long)key->objectid, key->type,
- (unsigned long long)key->offset);
+ key->objectid, key->type, key->offset);
BUG_ON(1);
}
@@ -490,13 +489,13 @@
*/
void btrfs_check_and_init_root_item(struct btrfs_root_item *root_item)
{
- u64 inode_flags = le64_to_cpu(root_item->inode.flags);
+ u64 inode_flags = btrfs_stack_inode_flags(&root_item->inode);
if (!(inode_flags & BTRFS_INODE_ROOT_ITEM_INIT)) {
inode_flags |= BTRFS_INODE_ROOT_ITEM_INIT;
- root_item->inode.flags = cpu_to_le64(inode_flags);
- root_item->flags = 0;
- root_item->byte_limit = 0;
+ btrfs_set_stack_inode_flags(&root_item->inode, inode_flags);
+ btrfs_set_root_flags(root_item, 0);
+ btrfs_set_root_limit(root_item, 0);
}
}
@@ -507,8 +506,8 @@
struct timespec ct = CURRENT_TIME;
spin_lock(&root->root_item_lock);
- item->ctransid = cpu_to_le64(trans->transid);
- item->ctime.sec = cpu_to_le64(ct.tv_sec);
- item->ctime.nsec = cpu_to_le32(ct.tv_nsec);
+ btrfs_set_root_ctransid(item, trans->transid);
+ btrfs_set_stack_timespec_sec(&item->ctime, ct.tv_sec);
+ btrfs_set_stack_timespec_nsec(&item->ctime, ct.tv_nsec);
spin_unlock(&root->root_item_lock);
}
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 64a157b..0afcd45 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -754,8 +754,7 @@
num_uncorrectable_read_errors);
printk_ratelimited_in_rcu(KERN_ERR
"btrfs: unable to fixup (nodatasum) error at logical %llu on dev %s\n",
- (unsigned long long)fixup->logical,
- rcu_str_deref(fixup->dev->name));
+ fixup->logical, rcu_str_deref(fixup->dev->name));
}
btrfs_free_path(path);
@@ -1154,8 +1153,7 @@
spin_unlock(&sctx->stat_lock);
printk_ratelimited_in_rcu(KERN_ERR
"btrfs: fixed up error at logical %llu on dev %s\n",
- (unsigned long long)logical,
- rcu_str_deref(dev->name));
+ logical, rcu_str_deref(dev->name));
}
} else {
did_not_correct_error:
@@ -1164,8 +1162,7 @@
spin_unlock(&sctx->stat_lock);
printk_ratelimited_in_rcu(KERN_ERR
"btrfs: unable to fixup (regular) error at logical %llu on dev %s\n",
- (unsigned long long)logical,
- rcu_str_deref(dev->name));
+ logical, rcu_str_deref(dev->name));
}
out:
@@ -1345,12 +1342,12 @@
mapped_buffer = kmap_atomic(sblock->pagev[0]->page);
h = (struct btrfs_header *)mapped_buffer;
- if (sblock->pagev[0]->logical != le64_to_cpu(h->bytenr) ||
+ if (sblock->pagev[0]->logical != btrfs_stack_header_bytenr(h) ||
memcmp(h->fsid, fs_info->fsid, BTRFS_UUID_SIZE) ||
memcmp(h->chunk_tree_uuid, fs_info->chunk_tree_uuid,
BTRFS_UUID_SIZE)) {
sblock->header_error = 1;
- } else if (generation != le64_to_cpu(h->generation)) {
+ } else if (generation != btrfs_stack_header_generation(h)) {
sblock->header_error = 1;
sblock->generation_error = 1;
}
@@ -1720,10 +1717,10 @@
* b) the page is already kmapped
*/
- if (sblock->pagev[0]->logical != le64_to_cpu(h->bytenr))
+ if (sblock->pagev[0]->logical != btrfs_stack_header_bytenr(h))
++fail;
- if (sblock->pagev[0]->generation != le64_to_cpu(h->generation))
+ if (sblock->pagev[0]->generation != btrfs_stack_header_generation(h))
++fail;
if (memcmp(h->fsid, fs_info->fsid, BTRFS_UUID_SIZE))
@@ -1786,10 +1783,10 @@
s = (struct btrfs_super_block *)mapped_buffer;
memcpy(on_disk_csum, s->csum, sctx->csum_size);
- if (sblock->pagev[0]->logical != le64_to_cpu(s->bytenr))
+ if (sblock->pagev[0]->logical != btrfs_super_bytenr(s))
++fail_cor;
- if (sblock->pagev[0]->generation != le64_to_cpu(s->generation))
+ if (sblock->pagev[0]->generation != btrfs_super_generation(s))
++fail_gen;
if (memcmp(s->fsid, fs_info->fsid, BTRFS_UUID_SIZE))
@@ -2455,8 +2452,7 @@
printk(KERN_ERR
"btrfs scrub: tree block %llu spanning "
"stripes, ignored. logical=%llu\n",
- (unsigned long long)key.objectid,
- (unsigned long long)logical);
+ key.objectid, logical);
goto next;
}
@@ -2863,9 +2859,8 @@
if (fs_info->chunk_root->sectorsize != PAGE_SIZE) {
/* not supported for data w/o checksums */
printk(KERN_ERR
- "btrfs_scrub: size assumption sectorsize != PAGE_SIZE (%d != %lld) fails\n",
- fs_info->chunk_root->sectorsize,
- (unsigned long long)PAGE_SIZE);
+ "btrfs_scrub: size assumption sectorsize != PAGE_SIZE (%d != %lu) fails\n",
+ fs_info->chunk_root->sectorsize, PAGE_SIZE);
return -EINVAL;
}
@@ -3175,11 +3170,9 @@
copy_nocow_pages_for_inode,
nocow_ctx);
if (ret != 0 && ret != -ENOENT) {
- pr_warn("iterate_inodes_from_logical() failed: log %llu, phys %llu, len %llu, mir %llu, ret %d\n",
- (unsigned long long)logical,
- (unsigned long long)physical_for_dev_replace,
- (unsigned long long)len,
- (unsigned long long)mirror_num, ret);
+ pr_warn("iterate_inodes_from_logical() failed: log %llu, phys %llu, len %llu, mir %u, ret %d\n",
+ logical, physical_for_dev_replace, len, mirror_num,
+ ret);
not_written = 1;
goto out;
}
@@ -3224,11 +3217,6 @@
return PTR_ERR(local_root);
}
- if (btrfs_root_refs(&local_root->root_item) == 0) {
- srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
- return -ENOENT;
- }
-
key.type = BTRFS_INODE_ITEM_KEY;
key.objectid = inum;
key.offset = 0;
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 2e14fd8..e46e0ed 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -26,6 +26,7 @@
#include <linux/radix-tree.h>
#include <linux/crc32c.h>
#include <linux/vmalloc.h>
+#include <linux/string.h>
#include "send.h"
#include "backref.h"
@@ -54,8 +55,8 @@
char *buf;
int buf_len;
- int reversed:1;
- int virtual_mem:1;
+ unsigned int reversed:1;
+ unsigned int virtual_mem:1;
char inline_buf[];
};
char pad[PAGE_SIZE];
@@ -1668,6 +1669,7 @@
u64 *who_ino, u64 *who_gen)
{
int ret = 0;
+ u64 gen;
u64 other_inode = 0;
u8 other_type = 0;
@@ -1678,6 +1680,24 @@
if (ret <= 0)
goto out;
+ /*
+ * If we have a parent root we need to verify that the parent dir was
+ * not delted and then re-created, if it was then we have no overwrite
+ * and we can just unlink this entry.
+ */
+ if (sctx->parent_root) {
+ ret = get_inode_info(sctx->parent_root, dir, NULL, &gen, NULL,
+ NULL, NULL, NULL);
+ if (ret < 0 && ret != -ENOENT)
+ goto out;
+ if (ret) {
+ ret = 0;
+ goto out;
+ }
+ if (gen != dir_gen)
+ goto out;
+ }
+
ret = lookup_dir_item_inode(sctx->parent_root, dir, name, name_len,
&other_inode, &other_type);
if (ret < 0 && ret != -ENOENT)
@@ -2519,7 +2539,8 @@
di = btrfs_item_ptr(eb, slot, struct btrfs_dir_item);
btrfs_dir_item_key_to_cpu(eb, di, &di_key);
- if (di_key.objectid < sctx->send_progress) {
+ if (di_key.type != BTRFS_ROOT_ITEM_KEY &&
+ di_key.objectid < sctx->send_progress) {
ret = 1;
goto out;
}
@@ -2581,7 +2602,6 @@
u64 dir_gen, struct fs_path *path)
{
struct recorded_ref *ref;
- char *tmp;
ref = kmalloc(sizeof(*ref), GFP_NOFS);
if (!ref)
@@ -2591,25 +2611,35 @@
ref->dir_gen = dir_gen;
ref->full_path = path;
- tmp = strrchr(ref->full_path->start, '/');
- if (!tmp) {
- ref->name_len = ref->full_path->end - ref->full_path->start;
- ref->name = ref->full_path->start;
+ ref->name = (char *)kbasename(ref->full_path->start);
+ ref->name_len = ref->full_path->end - ref->name;
+ ref->dir_path = ref->full_path->start;
+ if (ref->name == ref->full_path->start)
ref->dir_path_len = 0;
- ref->dir_path = ref->full_path->start;
- } else {
- tmp++;
- ref->name_len = ref->full_path->end - tmp;
- ref->name = tmp;
- ref->dir_path = ref->full_path->start;
+ else
ref->dir_path_len = ref->full_path->end -
ref->full_path->start - 1 - ref->name_len;
- }
list_add_tail(&ref->list, head);
return 0;
}
+static int dup_ref(struct recorded_ref *ref, struct list_head *list)
+{
+ struct recorded_ref *new;
+
+ new = kmalloc(sizeof(*ref), GFP_NOFS);
+ if (!new)
+ return -ENOMEM;
+
+ new->dir = ref->dir;
+ new->dir_gen = ref->dir_gen;
+ new->full_path = NULL;
+ INIT_LIST_HEAD(&new->list);
+ list_add_tail(&new->list, list);
+ return 0;
+}
+
static void __free_recorded_refs(struct list_head *head)
{
struct recorded_ref *cur;
@@ -2724,9 +2754,7 @@
int ret = 0;
struct recorded_ref *cur;
struct recorded_ref *cur2;
- struct ulist *check_dirs = NULL;
- struct ulist_iterator uit;
- struct ulist_node *un;
+ struct list_head check_dirs;
struct fs_path *valid_path = NULL;
u64 ow_inode = 0;
u64 ow_gen;
@@ -2740,6 +2768,7 @@
* which is always '..'
*/
BUG_ON(sctx->cur_ino <= BTRFS_FIRST_FREE_OBJECTID);
+ INIT_LIST_HEAD(&check_dirs);
valid_path = fs_path_alloc();
if (!valid_path) {
@@ -2747,12 +2776,6 @@
goto out;
}
- check_dirs = ulist_alloc(GFP_NOFS);
- if (!check_dirs) {
- ret = -ENOMEM;
- goto out;
- }
-
/*
* First, check if the first ref of the current inode was overwritten
* before. If yes, we know that the current inode was already orphanized
@@ -2889,8 +2912,7 @@
goto out;
}
}
- ret = ulist_add(check_dirs, cur->dir, cur->dir_gen,
- GFP_NOFS);
+ ret = dup_ref(cur, &check_dirs);
if (ret < 0)
goto out;
}
@@ -2918,8 +2940,7 @@
}
list_for_each_entry(cur, &sctx->deleted_refs, list) {
- ret = ulist_add(check_dirs, cur->dir, cur->dir_gen,
- GFP_NOFS);
+ ret = dup_ref(cur, &check_dirs);
if (ret < 0)
goto out;
}
@@ -2930,8 +2951,7 @@
*/
cur = list_entry(sctx->deleted_refs.next, struct recorded_ref,
list);
- ret = ulist_add(check_dirs, cur->dir, cur->dir_gen,
- GFP_NOFS);
+ ret = dup_ref(cur, &check_dirs);
if (ret < 0)
goto out;
} else if (!S_ISDIR(sctx->cur_inode_mode)) {
@@ -2951,12 +2971,10 @@
if (ret < 0)
goto out;
}
- ret = ulist_add(check_dirs, cur->dir, cur->dir_gen,
- GFP_NOFS);
+ ret = dup_ref(cur, &check_dirs);
if (ret < 0)
goto out;
}
-
/*
* If the inode is still orphan, unlink the orphan. This may
* happen when a previous inode did overwrite the first ref
@@ -2978,33 +2996,32 @@
* deletion and if it's finally possible to perform the rmdir now.
* We also update the inode stats of the parent dirs here.
*/
- ULIST_ITER_INIT(&uit);
- while ((un = ulist_next(check_dirs, &uit))) {
+ list_for_each_entry(cur, &check_dirs, list) {
/*
* In case we had refs into dirs that were not processed yet,
* we don't need to do the utime and rmdir logic for these dirs.
* The dir will be processed later.
*/
- if (un->val > sctx->cur_ino)
+ if (cur->dir > sctx->cur_ino)
continue;
- ret = get_cur_inode_state(sctx, un->val, un->aux);
+ ret = get_cur_inode_state(sctx, cur->dir, cur->dir_gen);
if (ret < 0)
goto out;
if (ret == inode_state_did_create ||
ret == inode_state_no_change) {
/* TODO delayed utimes */
- ret = send_utimes(sctx, un->val, un->aux);
+ ret = send_utimes(sctx, cur->dir, cur->dir_gen);
if (ret < 0)
goto out;
} else if (ret == inode_state_did_delete) {
- ret = can_rmdir(sctx, un->val, sctx->cur_ino);
+ ret = can_rmdir(sctx, cur->dir, sctx->cur_ino);
if (ret < 0)
goto out;
if (ret) {
- ret = get_cur_path(sctx, un->val, un->aux,
- valid_path);
+ ret = get_cur_path(sctx, cur->dir,
+ cur->dir_gen, valid_path);
if (ret < 0)
goto out;
ret = send_rmdir(sctx, valid_path);
@@ -3017,8 +3034,8 @@
ret = 0;
out:
+ __free_recorded_refs(&check_dirs);
free_recorded_refs(sctx);
- ulist_free(check_dirs);
fs_path_free(valid_path);
return ret;
}
@@ -3119,6 +3136,8 @@
struct find_ref_ctx {
u64 dir;
+ u64 dir_gen;
+ struct btrfs_root *root;
struct fs_path *name;
int found_idx;
};
@@ -3128,9 +3147,21 @@
void *ctx_)
{
struct find_ref_ctx *ctx = ctx_;
+ u64 dir_gen;
+ int ret;
if (dir == ctx->dir && fs_path_len(name) == fs_path_len(ctx->name) &&
strncmp(name->start, ctx->name->start, fs_path_len(name)) == 0) {
+ /*
+ * To avoid doing extra lookups we'll only do this if everything
+ * else matches.
+ */
+ ret = get_inode_info(ctx->root, dir, NULL, &dir_gen, NULL,
+ NULL, NULL, NULL);
+ if (ret)
+ return ret;
+ if (dir_gen != ctx->dir_gen)
+ return 0;
ctx->found_idx = num;
return 1;
}
@@ -3140,14 +3171,16 @@
static int find_iref(struct btrfs_root *root,
struct btrfs_path *path,
struct btrfs_key *key,
- u64 dir, struct fs_path *name)
+ u64 dir, u64 dir_gen, struct fs_path *name)
{
int ret;
struct find_ref_ctx ctx;
ctx.dir = dir;
ctx.name = name;
+ ctx.dir_gen = dir_gen;
ctx.found_idx = -1;
+ ctx.root = root;
ret = iterate_inode_ref(root, path, key, 0, __find_iref, &ctx);
if (ret < 0)
@@ -3163,11 +3196,17 @@
struct fs_path *name,
void *ctx)
{
+ u64 dir_gen;
int ret;
struct send_ctx *sctx = ctx;
+ ret = get_inode_info(sctx->send_root, dir, NULL, &dir_gen, NULL,
+ NULL, NULL, NULL);
+ if (ret)
+ return ret;
+
ret = find_iref(sctx->parent_root, sctx->right_path,
- sctx->cmp_key, dir, name);
+ sctx->cmp_key, dir, dir_gen, name);
if (ret == -ENOENT)
ret = __record_new_ref(num, dir, index, name, sctx);
else if (ret > 0)
@@ -3180,11 +3219,17 @@
struct fs_path *name,
void *ctx)
{
+ u64 dir_gen;
int ret;
struct send_ctx *sctx = ctx;
+ ret = get_inode_info(sctx->parent_root, dir, NULL, &dir_gen, NULL,
+ NULL, NULL, NULL);
+ if (ret)
+ return ret;
+
ret = find_iref(sctx->send_root, sctx->left_path, sctx->cmp_key,
- dir, name);
+ dir, dir_gen, name);
if (ret == -ENOENT)
ret = __record_deleted_ref(num, dir, index, name, sctx);
else if (ret > 0)
@@ -3869,7 +3914,8 @@
btrfs_item_key_to_cpu(eb, &found_key, slot);
if (found_key.objectid != key.objectid ||
found_key.type != key.type) {
- ret = 0;
+ /* If we're a hole then just pretend nothing changed */
+ ret = (left_disknr) ? 0 : 1;
goto out;
}
@@ -3895,7 +3941,8 @@
* This may only happen on the first iteration.
*/
if (found_key.offset + right_len <= ekey->offset) {
- ret = 0;
+ /* If we're a hole just pretend nothing changed */
+ ret = (left_disknr) ? 0 : 1;
goto out;
}
@@ -3960,8 +4007,8 @@
struct btrfs_path *path,
struct btrfs_key *key)
{
- int ret = 0;
struct clone_root *found_clone = NULL;
+ int ret = 0;
if (S_ISLNK(sctx->cur_inode_mode))
return 0;
@@ -3974,6 +4021,32 @@
ret = 0;
goto out;
}
+ } else {
+ struct btrfs_file_extent_item *ei;
+ u8 type;
+
+ ei = btrfs_item_ptr(path->nodes[0], path->slots[0],
+ struct btrfs_file_extent_item);
+ type = btrfs_file_extent_type(path->nodes[0], ei);
+ if (type == BTRFS_FILE_EXTENT_PREALLOC ||
+ type == BTRFS_FILE_EXTENT_REG) {
+ /*
+ * The send spec does not have a prealloc command yet,
+ * so just leave a hole for prealloc'ed extents until
+ * we have enough commands queued up to justify rev'ing
+ * the send spec.
+ */
+ if (type == BTRFS_FILE_EXTENT_PREALLOC) {
+ ret = 0;
+ goto out;
+ }
+
+ /* Have a hole, just skip it. */
+ if (btrfs_file_extent_disk_bytenr(path->nodes[0], ei) == 0) {
+ ret = 0;
+ goto out;
+ }
+ }
}
ret = find_extent_clone(sctx, path, key->objectid, key->offset,
@@ -4361,6 +4434,64 @@
return ret;
}
+static int dir_changed(struct send_ctx *sctx, u64 dir)
+{
+ u64 orig_gen, new_gen;
+ int ret;
+
+ ret = get_inode_info(sctx->send_root, dir, NULL, &new_gen, NULL, NULL,
+ NULL, NULL);
+ if (ret)
+ return ret;
+
+ ret = get_inode_info(sctx->parent_root, dir, NULL, &orig_gen, NULL,
+ NULL, NULL, NULL);
+ if (ret)
+ return ret;
+
+ return (orig_gen != new_gen) ? 1 : 0;
+}
+
+static int compare_refs(struct send_ctx *sctx, struct btrfs_path *path,
+ struct btrfs_key *key)
+{
+ struct btrfs_inode_extref *extref;
+ struct extent_buffer *leaf;
+ u64 dirid = 0, last_dirid = 0;
+ unsigned long ptr;
+ u32 item_size;
+ u32 cur_offset = 0;
+ int ref_name_len;
+ int ret = 0;
+
+ /* Easy case, just check this one dirid */
+ if (key->type == BTRFS_INODE_REF_KEY) {
+ dirid = key->offset;
+
+ ret = dir_changed(sctx, dirid);
+ goto out;
+ }
+
+ leaf = path->nodes[0];
+ item_size = btrfs_item_size_nr(leaf, path->slots[0]);
+ ptr = btrfs_item_ptr_offset(leaf, path->slots[0]);
+ while (cur_offset < item_size) {
+ extref = (struct btrfs_inode_extref *)(ptr +
+ cur_offset);
+ dirid = btrfs_inode_extref_parent(leaf, extref);
+ ref_name_len = btrfs_inode_extref_name_len(leaf, extref);
+ cur_offset += ref_name_len + sizeof(*extref);
+ if (dirid == last_dirid)
+ continue;
+ ret = dir_changed(sctx, dirid);
+ if (ret)
+ break;
+ last_dirid = dirid;
+ }
+out:
+ return ret;
+}
+
/*
* Updates compare related fields in sctx and simply forwards to the actual
* changed_xxx functions.
@@ -4376,6 +4507,19 @@
int ret = 0;
struct send_ctx *sctx = ctx;
+ if (result == BTRFS_COMPARE_TREE_SAME) {
+ if (key->type != BTRFS_INODE_REF_KEY &&
+ key->type != BTRFS_INODE_EXTREF_KEY)
+ return 0;
+ ret = compare_refs(sctx, left_path, key);
+ if (!ret)
+ return 0;
+ if (ret < 0)
+ return ret;
+ result = BTRFS_COMPARE_TREE_CHANGED;
+ ret = 0;
+ }
+
sctx->left_path = left_path;
sctx->right_path = right_path;
sctx->cmp_key = key;
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 8eb6191..3aab10c 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -56,6 +56,8 @@
#include "rcu-string.h"
#include "dev-replace.h"
#include "free-space-cache.h"
+#include "backref.h"
+#include "tests/btrfs-tests.h"
#define CREATE_TRACE_POINTS
#include <trace/events/btrfs.h>
@@ -320,14 +322,15 @@
Opt_enospc_debug, Opt_subvolrootid, Opt_defrag, Opt_inode_cache,
Opt_no_space_cache, Opt_recovery, Opt_skip_balance,
Opt_check_integrity, Opt_check_integrity_including_extent_data,
- Opt_check_integrity_print_mask, Opt_fatal_errors,
+ Opt_check_integrity_print_mask, Opt_fatal_errors, Opt_rescan_uuid_tree,
+ Opt_commit_interval,
Opt_err,
};
static match_table_t tokens = {
{Opt_degraded, "degraded"},
{Opt_subvol, "subvol=%s"},
- {Opt_subvolid, "subvolid=%d"},
+ {Opt_subvolid, "subvolid=%s"},
{Opt_device, "device=%s"},
{Opt_nodatasum, "nodatasum"},
{Opt_nodatacow, "nodatacow"},
@@ -360,7 +363,9 @@
{Opt_check_integrity, "check_int"},
{Opt_check_integrity_including_extent_data, "check_int_data"},
{Opt_check_integrity_print_mask, "check_int_print_mask=%d"},
+ {Opt_rescan_uuid_tree, "rescan_uuid_tree"},
{Opt_fatal_errors, "fatal_errors=%s"},
+ {Opt_commit_interval, "commit=%d"},
{Opt_err, NULL},
};
@@ -496,10 +501,15 @@
btrfs_set_opt(info->mount_opt, NOBARRIER);
break;
case Opt_thread_pool:
- intarg = 0;
- match_int(&args[0], &intarg);
- if (intarg)
+ ret = match_int(&args[0], &intarg);
+ if (ret) {
+ goto out;
+ } else if (intarg > 0) {
info->thread_pool_size = intarg;
+ } else {
+ ret = -EINVAL;
+ goto out;
+ }
break;
case Opt_max_inline:
num = match_strdup(&args[0]);
@@ -513,7 +523,10 @@
root->sectorsize);
}
printk(KERN_INFO "btrfs: max_inline at %llu\n",
- (unsigned long long)info->max_inline);
+ info->max_inline);
+ } else {
+ ret = -ENOMEM;
+ goto out;
}
break;
case Opt_alloc_start:
@@ -525,7 +538,10 @@
kfree(num);
printk(KERN_INFO
"btrfs: allocations start at %llu\n",
- (unsigned long long)info->alloc_start);
+ info->alloc_start);
+ } else {
+ ret = -ENOMEM;
+ goto out;
}
break;
case Opt_noacl:
@@ -540,12 +556,16 @@
btrfs_set_opt(info->mount_opt, FLUSHONCOMMIT);
break;
case Opt_ratio:
- intarg = 0;
- match_int(&args[0], &intarg);
- if (intarg) {
+ ret = match_int(&args[0], &intarg);
+ if (ret) {
+ goto out;
+ } else if (intarg >= 0) {
info->metadata_ratio = intarg;
printk(KERN_INFO "btrfs: metadata ratio %d\n",
info->metadata_ratio);
+ } else {
+ ret = -EINVAL;
+ goto out;
}
break;
case Opt_discard:
@@ -554,6 +574,9 @@
case Opt_space_cache:
btrfs_set_opt(info->mount_opt, SPACE_CACHE);
break;
+ case Opt_rescan_uuid_tree:
+ btrfs_set_opt(info->mount_opt, RESCAN_UUID_TREE);
+ break;
case Opt_no_space_cache:
printk(KERN_INFO "btrfs: disabling disk space caching\n");
btrfs_clear_opt(info->mount_opt, SPACE_CACHE);
@@ -596,13 +619,17 @@
btrfs_set_opt(info->mount_opt, CHECK_INTEGRITY);
break;
case Opt_check_integrity_print_mask:
- intarg = 0;
- match_int(&args[0], &intarg);
- if (intarg) {
+ ret = match_int(&args[0], &intarg);
+ if (ret) {
+ goto out;
+ } else if (intarg >= 0) {
info->check_integrity_print_mask = intarg;
printk(KERN_INFO "btrfs:"
" check_integrity_print_mask 0x%x\n",
info->check_integrity_print_mask);
+ } else {
+ ret = -EINVAL;
+ goto out;
}
break;
#else
@@ -626,6 +653,29 @@
goto out;
}
break;
+ case Opt_commit_interval:
+ intarg = 0;
+ ret = match_int(&args[0], &intarg);
+ if (ret < 0) {
+ printk(KERN_ERR
+ "btrfs: invalid commit interval\n");
+ ret = -EINVAL;
+ goto out;
+ }
+ if (intarg > 0) {
+ if (intarg > 300) {
+ printk(KERN_WARNING
+ "btrfs: excessive commit interval %d\n",
+ intarg);
+ }
+ info->commit_interval = intarg;
+ } else {
+ printk(KERN_INFO
+ "btrfs: using default commit interval %ds\n",
+ BTRFS_DEFAULT_COMMIT_INTERVAL);
+ info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL;
+ }
+ break;
case Opt_err:
printk(KERN_INFO "btrfs: unrecognized mount option "
"'%s'\n", p);
@@ -654,8 +704,8 @@
{
substring_t args[MAX_OPT_ARGS];
char *device_name, *opts, *orig, *p;
+ char *num = NULL;
int error = 0;
- int intarg;
if (!options)
return 0;
@@ -679,17 +729,23 @@
case Opt_subvol:
kfree(*subvol_name);
*subvol_name = match_strdup(&args[0]);
+ if (!*subvol_name) {
+ error = -ENOMEM;
+ goto out;
+ }
break;
case Opt_subvolid:
- intarg = 0;
- error = match_int(&args[0], &intarg);
- if (!error) {
+ num = match_strdup(&args[0]);
+ if (num) {
+ *subvol_objectid = memparse(num, NULL);
+ kfree(num);
/* we want the original fs_tree */
- if (!intarg)
+ if (!*subvol_objectid)
*subvol_objectid =
BTRFS_FS_TREE_OBJECTID;
- else
- *subvol_objectid = intarg;
+ } else {
+ error = -EINVAL;
+ goto out;
}
break;
case Opt_subvolrootid:
@@ -892,11 +948,9 @@
if (btrfs_test_opt(root, NOBARRIER))
seq_puts(seq, ",nobarrier");
if (info->max_inline != 8192 * 1024)
- seq_printf(seq, ",max_inline=%llu",
- (unsigned long long)info->max_inline);
+ seq_printf(seq, ",max_inline=%llu", info->max_inline);
if (info->alloc_start != 0)
- seq_printf(seq, ",alloc_start=%llu",
- (unsigned long long)info->alloc_start);
+ seq_printf(seq, ",alloc_start=%llu", info->alloc_start);
if (info->thread_pool_size != min_t(unsigned long,
num_online_cpus() + 2, 8))
seq_printf(seq, ",thread_pool=%d", info->thread_pool_size);
@@ -928,6 +982,8 @@
seq_puts(seq, ",space_cache");
else
seq_puts(seq, ",nospace_cache");
+ if (btrfs_test_opt(root, RESCAN_UUID_TREE))
+ seq_puts(seq, ",rescan_uuid_tree");
if (btrfs_test_opt(root, CLEAR_CACHE))
seq_puts(seq, ",clear_cache");
if (btrfs_test_opt(root, USER_SUBVOL_RM_ALLOWED))
@@ -940,8 +996,24 @@
seq_puts(seq, ",inode_cache");
if (btrfs_test_opt(root, SKIP_BALANCE))
seq_puts(seq, ",skip_balance");
+ if (btrfs_test_opt(root, RECOVERY))
+ seq_puts(seq, ",recovery");
+#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
+ if (btrfs_test_opt(root, CHECK_INTEGRITY_INCLUDING_EXTENT_DATA))
+ seq_puts(seq, ",check_int_data");
+ else if (btrfs_test_opt(root, CHECK_INTEGRITY))
+ seq_puts(seq, ",check_int");
+ if (info->check_integrity_print_mask)
+ seq_printf(seq, ",check_int_print_mask=%d",
+ info->check_integrity_print_mask);
+#endif
+ if (info->metadata_ratio)
+ seq_printf(seq, ",metadata_ratio=%d",
+ info->metadata_ratio);
if (btrfs_test_opt(root, PANIC_ON_FATAL_ERROR))
seq_puts(seq, ",fatal_errors=panic");
+ if (info->commit_interval != BTRFS_DEFAULT_COMMIT_INTERVAL)
+ seq_printf(seq, ",commit=%d", info->commit_interval);
return 0;
}
@@ -1696,6 +1768,11 @@
"\n");
}
+static int btrfs_run_sanity_tests(void)
+{
+ return btrfs_test_free_space_cache();
+}
+
static int __init init_btrfs_fs(void)
{
int err;
@@ -1734,23 +1811,32 @@
if (err)
goto free_auto_defrag;
+ err = btrfs_prelim_ref_init();
+ if (err)
+ goto free_prelim_ref;
+
err = btrfs_interface_init();
if (err)
goto free_delayed_ref;
+ btrfs_init_lockdep();
+
+ btrfs_print_info();
+
+ err = btrfs_run_sanity_tests();
+ if (err)
+ goto unregister_ioctl;
+
err = register_filesystem(&btrfs_fs_type);
if (err)
goto unregister_ioctl;
- btrfs_init_lockdep();
-
- btrfs_print_info();
- btrfs_test_free_space_cache();
-
return 0;
unregister_ioctl:
btrfs_interface_exit();
+free_prelim_ref:
+ btrfs_prelim_ref_exit();
free_delayed_ref:
btrfs_delayed_ref_exit();
free_auto_defrag:
@@ -1777,6 +1863,7 @@
btrfs_delayed_ref_exit();
btrfs_auto_defrag_exit();
btrfs_delayed_inode_exit();
+ btrfs_prelim_ref_exit();
ordered_data_exit();
extent_map_exit();
extent_io_exit();
diff --git a/fs/btrfs/tests/btrfs-tests.h b/fs/btrfs/tests/btrfs-tests.h
new file mode 100644
index 0000000..5808776
--- /dev/null
+++ b/fs/btrfs/tests/btrfs-tests.h
@@ -0,0 +1,34 @@
+/*
+ * Copyright (C) 2013 Fusion IO. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ */
+
+#ifndef __BTRFS_TESTS
+#define __BTRFS_TESTS
+
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+
+#define test_msg(fmt, ...) pr_info("btrfs: selftest: " fmt, ##__VA_ARGS__)
+
+int btrfs_test_free_space_cache(void);
+#else
+static inline int btrfs_test_free_space_cache(void)
+{
+ return 0;
+}
+#endif
+
+#endif
diff --git a/fs/btrfs/tests/free-space-tests.c b/fs/btrfs/tests/free-space-tests.c
new file mode 100644
index 0000000..6fc8201
--- /dev/null
+++ b/fs/btrfs/tests/free-space-tests.c
@@ -0,0 +1,395 @@
+/*
+ * Copyright (C) 2013 Fusion IO. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ */
+
+#include <linux/slab.h>
+#include "btrfs-tests.h"
+#include "../ctree.h"
+#include "../free-space-cache.h"
+
+#define BITS_PER_BITMAP (PAGE_CACHE_SIZE * 8)
+static struct btrfs_block_group_cache *init_test_block_group(void)
+{
+ struct btrfs_block_group_cache *cache;
+
+ cache = kzalloc(sizeof(*cache), GFP_NOFS);
+ if (!cache)
+ return NULL;
+ cache->free_space_ctl = kzalloc(sizeof(*cache->free_space_ctl),
+ GFP_NOFS);
+ if (!cache->free_space_ctl) {
+ kfree(cache);
+ return NULL;
+ }
+
+ cache->key.objectid = 0;
+ cache->key.offset = 1024 * 1024 * 1024;
+ cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
+ cache->sectorsize = 4096;
+
+ spin_lock_init(&cache->lock);
+ INIT_LIST_HEAD(&cache->list);
+ INIT_LIST_HEAD(&cache->cluster_list);
+ INIT_LIST_HEAD(&cache->new_bg_list);
+
+ btrfs_init_free_space_ctl(cache);
+
+ return cache;
+}
+
+/*
+ * This test just does basic sanity checking, making sure we can add an exten
+ * entry and remove space from either end and the middle, and make sure we can
+ * remove space that covers adjacent extent entries.
+ */
+static int test_extents(struct btrfs_block_group_cache *cache)
+{
+ int ret = 0;
+
+ test_msg("Running extent only tests\n");
+
+ /* First just make sure we can remove an entire entry */
+ ret = btrfs_add_free_space(cache, 0, 4 * 1024 * 1024);
+ if (ret) {
+ test_msg("Error adding initial extents %d\n", ret);
+ return ret;
+ }
+
+ ret = btrfs_remove_free_space(cache, 0, 4 * 1024 * 1024);
+ if (ret) {
+ test_msg("Error removing extent %d\n", ret);
+ return ret;
+ }
+
+ if (test_check_exists(cache, 0, 4 * 1024 * 1024)) {
+ test_msg("Full remove left some lingering space\n");
+ return -1;
+ }
+
+ /* Ok edge and middle cases now */
+ ret = btrfs_add_free_space(cache, 0, 4 * 1024 * 1024);
+ if (ret) {
+ test_msg("Error adding half extent %d\n", ret);
+ return ret;
+ }
+
+ ret = btrfs_remove_free_space(cache, 3 * 1024 * 1024, 1 * 1024 * 1024);
+ if (ret) {
+ test_msg("Error removing tail end %d\n", ret);
+ return ret;
+ }
+
+ ret = btrfs_remove_free_space(cache, 0, 1 * 1024 * 1024);
+ if (ret) {
+ test_msg("Error removing front end %d\n", ret);
+ return ret;
+ }
+
+ ret = btrfs_remove_free_space(cache, 2 * 1024 * 1024, 4096);
+ if (ret) {
+ test_msg("Error removing middle peice %d\n", ret);
+ return ret;
+ }
+
+ if (test_check_exists(cache, 0, 1 * 1024 * 1024)) {
+ test_msg("Still have space at the front\n");
+ return -1;
+ }
+
+ if (test_check_exists(cache, 2 * 1024 * 1024, 4096)) {
+ test_msg("Still have space in the middle\n");
+ return -1;
+ }
+
+ if (test_check_exists(cache, 3 * 1024 * 1024, 1 * 1024 * 1024)) {
+ test_msg("Still have space at the end\n");
+ return -1;
+ }
+
+ /* Cleanup */
+ __btrfs_remove_free_space_cache(cache->free_space_ctl);
+
+ return 0;
+}
+
+static int test_bitmaps(struct btrfs_block_group_cache *cache)
+{
+ u64 next_bitmap_offset;
+ int ret;
+
+ test_msg("Running bitmap only tests\n");
+
+ ret = test_add_free_space_entry(cache, 0, 4 * 1024 * 1024, 1);
+ if (ret) {
+ test_msg("Couldn't create a bitmap entry %d\n", ret);
+ return ret;
+ }
+
+ ret = btrfs_remove_free_space(cache, 0, 4 * 1024 * 1024);
+ if (ret) {
+ test_msg("Error removing bitmap full range %d\n", ret);
+ return ret;
+ }
+
+ if (test_check_exists(cache, 0, 4 * 1024 * 1024)) {
+ test_msg("Left some space in bitmap\n");
+ return -1;
+ }
+
+ ret = test_add_free_space_entry(cache, 0, 4 * 1024 * 1024, 1);
+ if (ret) {
+ test_msg("Couldn't add to our bitmap entry %d\n", ret);
+ return ret;
+ }
+
+ ret = btrfs_remove_free_space(cache, 1 * 1024 * 1024, 2 * 1024 * 1024);
+ if (ret) {
+ test_msg("Couldn't remove middle chunk %d\n", ret);
+ return ret;
+ }
+
+ /*
+ * The first bitmap we have starts at offset 0 so the next one is just
+ * at the end of the first bitmap.
+ */
+ next_bitmap_offset = (u64)(BITS_PER_BITMAP * 4096);
+
+ /* Test a bit straddling two bitmaps */
+ ret = test_add_free_space_entry(cache, next_bitmap_offset -
+ (2 * 1024 * 1024), 4 * 1024 * 1024, 1);
+ if (ret) {
+ test_msg("Couldn't add space that straddles two bitmaps %d\n",
+ ret);
+ return ret;
+ }
+
+ ret = btrfs_remove_free_space(cache, next_bitmap_offset -
+ (1 * 1024 * 1024), 2 * 1024 * 1024);
+ if (ret) {
+ test_msg("Couldn't remove overlapping space %d\n", ret);
+ return ret;
+ }
+
+ if (test_check_exists(cache, next_bitmap_offset - (1 * 1024 * 1024),
+ 2 * 1024 * 1024)) {
+ test_msg("Left some space when removing overlapping\n");
+ return -1;
+ }
+
+ __btrfs_remove_free_space_cache(cache->free_space_ctl);
+
+ return 0;
+}
+
+/* This is the high grade jackassery */
+static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache)
+{
+ u64 bitmap_offset = (u64)(BITS_PER_BITMAP * 4096);
+ int ret;
+
+ test_msg("Running bitmap and extent tests\n");
+
+ /*
+ * First let's do something simple, an extent at the same offset as the
+ * bitmap, but the free space completely in the extent and then
+ * completely in the bitmap.
+ */
+ ret = test_add_free_space_entry(cache, 4 * 1024 * 1024, 1 * 1024 * 1024, 1);
+ if (ret) {
+ test_msg("Couldn't create bitmap entry %d\n", ret);
+ return ret;
+ }
+
+ ret = test_add_free_space_entry(cache, 0, 1 * 1024 * 1024, 0);
+ if (ret) {
+ test_msg("Couldn't add extent entry %d\n", ret);
+ return ret;
+ }
+
+ ret = btrfs_remove_free_space(cache, 0, 1 * 1024 * 1024);
+ if (ret) {
+ test_msg("Couldn't remove extent entry %d\n", ret);
+ return ret;
+ }
+
+ if (test_check_exists(cache, 0, 1 * 1024 * 1024)) {
+ test_msg("Left remnants after our remove\n");
+ return -1;
+ }
+
+ /* Now to add back the extent entry and remove from the bitmap */
+ ret = test_add_free_space_entry(cache, 0, 1 * 1024 * 1024, 0);
+ if (ret) {
+ test_msg("Couldn't re-add extent entry %d\n", ret);
+ return ret;
+ }
+
+ ret = btrfs_remove_free_space(cache, 4 * 1024 * 1024, 1 * 1024 * 1024);
+ if (ret) {
+ test_msg("Couldn't remove from bitmap %d\n", ret);
+ return ret;
+ }
+
+ if (test_check_exists(cache, 4 * 1024 * 1024, 1 * 1024 * 1024)) {
+ test_msg("Left remnants in the bitmap\n");
+ return -1;
+ }
+
+ /*
+ * Ok so a little more evil, extent entry and bitmap at the same offset,
+ * removing an overlapping chunk.
+ */
+ ret = test_add_free_space_entry(cache, 1 * 1024 * 1024, 4 * 1024 * 1024, 1);
+ if (ret) {
+ test_msg("Couldn't add to a bitmap %d\n", ret);
+ return ret;
+ }
+
+ ret = btrfs_remove_free_space(cache, 512 * 1024, 3 * 1024 * 1024);
+ if (ret) {
+ test_msg("Couldn't remove overlapping space %d\n", ret);
+ return ret;
+ }
+
+ if (test_check_exists(cache, 512 * 1024, 3 * 1024 * 1024)) {
+ test_msg("Left over peices after removing overlapping\n");
+ return -1;
+ }
+
+ __btrfs_remove_free_space_cache(cache->free_space_ctl);
+
+ /* Now with the extent entry offset into the bitmap */
+ ret = test_add_free_space_entry(cache, 4 * 1024 * 1024, 4 * 1024 * 1024, 1);
+ if (ret) {
+ test_msg("Couldn't add space to the bitmap %d\n", ret);
+ return ret;
+ }
+
+ ret = test_add_free_space_entry(cache, 2 * 1024 * 1024, 2 * 1024 * 1024, 0);
+ if (ret) {
+ test_msg("Couldn't add extent to the cache %d\n", ret);
+ return ret;
+ }
+
+ ret = btrfs_remove_free_space(cache, 3 * 1024 * 1024, 4 * 1024 * 1024);
+ if (ret) {
+ test_msg("Problem removing overlapping space %d\n", ret);
+ return ret;
+ }
+
+ if (test_check_exists(cache, 3 * 1024 * 1024, 4 * 1024 * 1024)) {
+ test_msg("Left something behind when removing space");
+ return -1;
+ }
+
+ /*
+ * This has blown up in the past, the extent entry starts before the
+ * bitmap entry, but we're trying to remove an offset that falls
+ * completely within the bitmap range and is in both the extent entry
+ * and the bitmap entry, looks like this
+ *
+ * [ extent ]
+ * [ bitmap ]
+ * [ del ]
+ */
+ __btrfs_remove_free_space_cache(cache->free_space_ctl);
+ ret = test_add_free_space_entry(cache, bitmap_offset + 4 * 1024 * 1024,
+ 4 * 1024 * 1024, 1);
+ if (ret) {
+ test_msg("Couldn't add bitmap %d\n", ret);
+ return ret;
+ }
+
+ ret = test_add_free_space_entry(cache, bitmap_offset - 1 * 1024 * 1024,
+ 5 * 1024 * 1024, 0);
+ if (ret) {
+ test_msg("Couldn't add extent entry %d\n", ret);
+ return ret;
+ }
+
+ ret = btrfs_remove_free_space(cache, bitmap_offset + 1 * 1024 * 1024,
+ 5 * 1024 * 1024);
+ if (ret) {
+ test_msg("Failed to free our space %d\n", ret);
+ return ret;
+ }
+
+ if (test_check_exists(cache, bitmap_offset + 1 * 1024 * 1024,
+ 5 * 1024 * 1024)) {
+ test_msg("Left stuff over\n");
+ return -1;
+ }
+
+ __btrfs_remove_free_space_cache(cache->free_space_ctl);
+
+ /*
+ * This blew up before, we have part of the free space in a bitmap and
+ * then the entirety of the rest of the space in an extent. This used
+ * to return -EAGAIN back from btrfs_remove_extent, make sure this
+ * doesn't happen.
+ */
+ ret = test_add_free_space_entry(cache, 1 * 1024 * 1024, 2 * 1024 * 1024, 1);
+ if (ret) {
+ test_msg("Couldn't add bitmap entry %d\n", ret);
+ return ret;
+ }
+
+ ret = test_add_free_space_entry(cache, 3 * 1024 * 1024, 1 * 1024 * 1024, 0);
+ if (ret) {
+ test_msg("Couldn't add extent entry %d\n", ret);
+ return ret;
+ }
+
+ ret = btrfs_remove_free_space(cache, 1 * 1024 * 1024, 3 * 1024 * 1024);
+ if (ret) {
+ test_msg("Error removing bitmap and extent overlapping %d\n", ret);
+ return ret;
+ }
+
+ __btrfs_remove_free_space_cache(cache->free_space_ctl);
+ return 0;
+}
+
+int btrfs_test_free_space_cache(void)
+{
+ struct btrfs_block_group_cache *cache;
+ int ret;
+
+ test_msg("Running btrfs free space cache tests\n");
+
+ cache = init_test_block_group();
+ if (!cache) {
+ test_msg("Couldn't run the tests\n");
+ return 0;
+ }
+
+ ret = test_extents(cache);
+ if (ret)
+ goto out;
+ ret = test_bitmaps(cache);
+ if (ret)
+ goto out;
+ ret = test_bitmaps_and_extents(cache);
+ if (ret)
+ goto out;
+out:
+ __btrfs_remove_free_space_cache(cache->free_space_ctl);
+ kfree(cache->free_space_ctl);
+ kfree(cache);
+ test_msg("Free space cache tests finished\n");
+ return ret;
+}
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index af1931a..cac4a3f 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -837,7 +837,7 @@
* them in one of two extent_io trees. This is used to make sure all of
* those extents are on disk for transaction or log commit
*/
-int btrfs_write_and_wait_marked_extents(struct btrfs_root *root,
+static int btrfs_write_and_wait_marked_extents(struct btrfs_root *root,
struct extent_io_tree *dirty_pages, int mark)
{
int ret;
@@ -1225,8 +1225,8 @@
btrfs_set_root_stransid(new_root_item, 0);
btrfs_set_root_rtransid(new_root_item, 0);
}
- new_root_item->otime.sec = cpu_to_le64(cur_time.tv_sec);
- new_root_item->otime.nsec = cpu_to_le32(cur_time.tv_nsec);
+ btrfs_set_stack_timespec_sec(&new_root_item->otime, cur_time.tv_sec);
+ btrfs_set_stack_timespec_nsec(&new_root_item->otime, cur_time.tv_nsec);
btrfs_set_root_otransid(new_root_item, trans->transid);
old = btrfs_lock_root_node(root);
@@ -1311,8 +1311,26 @@
dentry->d_name.len * 2);
parent_inode->i_mtime = parent_inode->i_ctime = CURRENT_TIME;
ret = btrfs_update_inode_fallback(trans, parent_root, parent_inode);
- if (ret)
+ if (ret) {
btrfs_abort_transaction(trans, root, ret);
+ goto fail;
+ }
+ ret = btrfs_uuid_tree_add(trans, fs_info->uuid_root, new_uuid.b,
+ BTRFS_UUID_KEY_SUBVOL, objectid);
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ goto fail;
+ }
+ if (!btrfs_is_empty_uuid(new_root_item->received_uuid)) {
+ ret = btrfs_uuid_tree_add(trans, fs_info->uuid_root,
+ new_root_item->received_uuid,
+ BTRFS_UUID_KEY_RECEIVED_SUBVOL,
+ objectid);
+ if (ret && ret != -EEXIST) {
+ btrfs_abort_transaction(trans, root, ret);
+ goto fail;
+ }
+ }
fail:
pending->error = ret;
dir_item_existed:
@@ -1362,6 +1380,8 @@
super->root_level = root_item->level;
if (btrfs_test_opt(root, SPACE_CACHE))
super->cache_generation = root_item->generation;
+ if (root->fs_info->update_uuid_tree_gen)
+ super->uuid_tree_generation = root_item->generation;
}
int btrfs_transaction_in_commit(struct btrfs_fs_info *info)
@@ -1928,8 +1948,7 @@
list_del_init(&root->root_list);
spin_unlock(&fs_info->trans_lock);
- pr_debug("btrfs: cleaner removing %llu\n",
- (unsigned long long)root->objectid);
+ pr_debug("btrfs: cleaner removing %llu\n", root->objectid);
btrfs_kill_all_delayed_nodes(root);
@@ -1942,6 +1961,5 @@
* If we encounter a transaction abort during snapshot cleaning, we
* don't want to crash here
*/
- BUG_ON(ret < 0 && ret != -EAGAIN && ret != -EROFS);
- return 1;
+ return (ret < 0) ? 0 : 1;
}
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index defbc42..5c2af84 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -160,8 +160,6 @@
void btrfs_throttle(struct btrfs_root *root);
int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
-int btrfs_write_and_wait_marked_extents(struct btrfs_root *root,
- struct extent_io_tree *dirty_pages, int mark);
int btrfs_write_marked_extents(struct btrfs_root *root,
struct extent_io_tree *dirty_pages, int mark);
int btrfs_wait_marked_extents(struct btrfs_root *root,
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index ff60d89..0d9613c 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -747,7 +747,8 @@
ret = btrfs_unlink_inode(trans, root, dir, inode, name, name_len);
if (ret)
goto out;
- btrfs_run_delayed_items(trans, root);
+ else
+ ret = btrfs_run_delayed_items(trans, root);
out:
kfree(name);
iput(inode);
@@ -923,7 +924,9 @@
kfree(victim_name);
if (ret)
return ret;
- btrfs_run_delayed_items(trans, root);
+ ret = btrfs_run_delayed_items(trans, root);
+ if (ret)
+ return ret;
*search_done = 1;
goto again;
}
@@ -990,7 +993,9 @@
inode,
victim_name,
victim_name_len);
- btrfs_run_delayed_items(trans, root);
+ if (!ret)
+ ret = btrfs_run_delayed_items(
+ trans, root);
}
iput(victim_parent);
kfree(victim_name);
@@ -1536,8 +1541,10 @@
name_len = btrfs_dir_name_len(eb, di);
name = kmalloc(name_len, GFP_NOFS);
- if (!name)
- return -ENOMEM;
+ if (!name) {
+ ret = -ENOMEM;
+ goto out;
+ }
log_type = btrfs_dir_type(eb, di);
read_extent_buffer(eb, name, (unsigned long)(di + 1),
@@ -1810,7 +1817,7 @@
ret = btrfs_unlink_inode(trans, root, dir, inode,
name, name_len);
if (!ret)
- btrfs_run_delayed_items(trans, root);
+ ret = btrfs_run_delayed_items(trans, root);
kfree(name);
iput(inode);
if (ret)
diff --git a/fs/btrfs/uuid-tree.c b/fs/btrfs/uuid-tree.c
new file mode 100644
index 0000000..dd0dea3
--- /dev/null
+++ b/fs/btrfs/uuid-tree.c
@@ -0,0 +1,358 @@
+/*
+ * Copyright (C) STRATO AG 2013. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ */
+#include <linux/uuid.h>
+#include <asm/unaligned.h>
+#include "ctree.h"
+#include "transaction.h"
+#include "disk-io.h"
+#include "print-tree.h"
+
+
+static void btrfs_uuid_to_key(u8 *uuid, u8 type, struct btrfs_key *key)
+{
+ key->type = type;
+ key->objectid = get_unaligned_le64(uuid);
+ key->offset = get_unaligned_le64(uuid + sizeof(u64));
+}
+
+/* return -ENOENT for !found, < 0 for errors, or 0 if an item was found */
+static int btrfs_uuid_tree_lookup(struct btrfs_root *uuid_root, u8 *uuid,
+ u8 type, u64 subid)
+{
+ int ret;
+ struct btrfs_path *path = NULL;
+ struct extent_buffer *eb;
+ int slot;
+ u32 item_size;
+ unsigned long offset;
+ struct btrfs_key key;
+
+ if (WARN_ON_ONCE(!uuid_root)) {
+ ret = -ENOENT;
+ goto out;
+ }
+
+ path = btrfs_alloc_path();
+ if (!path) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ btrfs_uuid_to_key(uuid, type, &key);
+ ret = btrfs_search_slot(NULL, uuid_root, &key, path, 0, 0);
+ if (ret < 0) {
+ goto out;
+ } else if (ret > 0) {
+ ret = -ENOENT;
+ goto out;
+ }
+
+ eb = path->nodes[0];
+ slot = path->slots[0];
+ item_size = btrfs_item_size_nr(eb, slot);
+ offset = btrfs_item_ptr_offset(eb, slot);
+ ret = -ENOENT;
+
+ if (!IS_ALIGNED(item_size, sizeof(u64))) {
+ pr_warn("btrfs: uuid item with illegal size %lu!\n",
+ (unsigned long)item_size);
+ goto out;
+ }
+ while (item_size) {
+ __le64 data;
+
+ read_extent_buffer(eb, &data, offset, sizeof(data));
+ if (le64_to_cpu(data) == subid) {
+ ret = 0;
+ break;
+ }
+ offset += sizeof(data);
+ item_size -= sizeof(data);
+ }
+
+out:
+ btrfs_free_path(path);
+ return ret;
+}
+
+int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans,
+ struct btrfs_root *uuid_root, u8 *uuid, u8 type,
+ u64 subid_cpu)
+{
+ int ret;
+ struct btrfs_path *path = NULL;
+ struct btrfs_key key;
+ struct extent_buffer *eb;
+ int slot;
+ unsigned long offset;
+ __le64 subid_le;
+
+ ret = btrfs_uuid_tree_lookup(uuid_root, uuid, type, subid_cpu);
+ if (ret != -ENOENT)
+ return ret;
+
+ if (WARN_ON_ONCE(!uuid_root)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ btrfs_uuid_to_key(uuid, type, &key);
+
+ path = btrfs_alloc_path();
+ if (!path) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ ret = btrfs_insert_empty_item(trans, uuid_root, path, &key,
+ sizeof(subid_le));
+ if (ret >= 0) {
+ /* Add an item for the type for the first time */
+ eb = path->nodes[0];
+ slot = path->slots[0];
+ offset = btrfs_item_ptr_offset(eb, slot);
+ } else if (ret == -EEXIST) {
+ /*
+ * An item with that type already exists.
+ * Extend the item and store the new subid at the end.
+ */
+ btrfs_extend_item(uuid_root, path, sizeof(subid_le));
+ eb = path->nodes[0];
+ slot = path->slots[0];
+ offset = btrfs_item_ptr_offset(eb, slot);
+ offset += btrfs_item_size_nr(eb, slot) - sizeof(subid_le);
+ } else if (ret < 0) {
+ pr_warn("btrfs: insert uuid item failed %d (0x%016llx, 0x%016llx) type %u!\n",
+ ret, (unsigned long long)key.objectid,
+ (unsigned long long)key.offset, type);
+ goto out;
+ }
+
+ ret = 0;
+ subid_le = cpu_to_le64(subid_cpu);
+ write_extent_buffer(eb, &subid_le, offset, sizeof(subid_le));
+ btrfs_mark_buffer_dirty(eb);
+
+out:
+ btrfs_free_path(path);
+ return ret;
+}
+
+int btrfs_uuid_tree_rem(struct btrfs_trans_handle *trans,
+ struct btrfs_root *uuid_root, u8 *uuid, u8 type,
+ u64 subid)
+{
+ int ret;
+ struct btrfs_path *path = NULL;
+ struct btrfs_key key;
+ struct extent_buffer *eb;
+ int slot;
+ unsigned long offset;
+ u32 item_size;
+ unsigned long move_dst;
+ unsigned long move_src;
+ unsigned long move_len;
+
+ if (WARN_ON_ONCE(!uuid_root)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ btrfs_uuid_to_key(uuid, type, &key);
+
+ path = btrfs_alloc_path();
+ if (!path) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ ret = btrfs_search_slot(trans, uuid_root, &key, path, -1, 1);
+ if (ret < 0) {
+ pr_warn("btrfs: error %d while searching for uuid item!\n",
+ ret);
+ goto out;
+ }
+ if (ret > 0) {
+ ret = -ENOENT;
+ goto out;
+ }
+
+ eb = path->nodes[0];
+ slot = path->slots[0];
+ offset = btrfs_item_ptr_offset(eb, slot);
+ item_size = btrfs_item_size_nr(eb, slot);
+ if (!IS_ALIGNED(item_size, sizeof(u64))) {
+ pr_warn("btrfs: uuid item with illegal size %lu!\n",
+ (unsigned long)item_size);
+ ret = -ENOENT;
+ goto out;
+ }
+ while (item_size) {
+ __le64 read_subid;
+
+ read_extent_buffer(eb, &read_subid, offset, sizeof(read_subid));
+ if (le64_to_cpu(read_subid) == subid)
+ break;
+ offset += sizeof(read_subid);
+ item_size -= sizeof(read_subid);
+ }
+
+ if (!item_size) {
+ ret = -ENOENT;
+ goto out;
+ }
+
+ item_size = btrfs_item_size_nr(eb, slot);
+ if (item_size == sizeof(subid)) {
+ ret = btrfs_del_item(trans, uuid_root, path);
+ goto out;
+ }
+
+ move_dst = offset;
+ move_src = offset + sizeof(subid);
+ move_len = item_size - (move_src - btrfs_item_ptr_offset(eb, slot));
+ memmove_extent_buffer(eb, move_dst, move_src, move_len);
+ btrfs_truncate_item(uuid_root, path, item_size - sizeof(subid), 1);
+
+out:
+ btrfs_free_path(path);
+ return ret;
+}
+
+static int btrfs_uuid_iter_rem(struct btrfs_root *uuid_root, u8 *uuid, u8 type,
+ u64 subid)
+{
+ struct btrfs_trans_handle *trans;
+ int ret;
+
+ /* 1 - for the uuid item */
+ trans = btrfs_start_transaction(uuid_root, 1);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ goto out;
+ }
+
+ ret = btrfs_uuid_tree_rem(trans, uuid_root, uuid, type, subid);
+ btrfs_end_transaction(trans, uuid_root);
+
+out:
+ return ret;
+}
+
+int btrfs_uuid_tree_iterate(struct btrfs_fs_info *fs_info,
+ int (*check_func)(struct btrfs_fs_info *, u8 *, u8,
+ u64))
+{
+ struct btrfs_root *root = fs_info->uuid_root;
+ struct btrfs_key key;
+ struct btrfs_key max_key;
+ struct btrfs_path *path;
+ int ret = 0;
+ struct extent_buffer *leaf;
+ int slot;
+ u32 item_size;
+ unsigned long offset;
+
+ path = btrfs_alloc_path();
+ if (!path) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ key.objectid = 0;
+ key.type = 0;
+ key.offset = 0;
+ max_key.objectid = (u64)-1;
+ max_key.type = (u8)-1;
+ max_key.offset = (u64)-1;
+
+again_search_slot:
+ path->keep_locks = 1;
+ ret = btrfs_search_forward(root, &key, &max_key, path, 0);
+ if (ret) {
+ if (ret > 0)
+ ret = 0;
+ goto out;
+ }
+
+ while (1) {
+ cond_resched();
+ leaf = path->nodes[0];
+ slot = path->slots[0];
+ btrfs_item_key_to_cpu(leaf, &key, slot);
+
+ if (key.type != BTRFS_UUID_KEY_SUBVOL &&
+ key.type != BTRFS_UUID_KEY_RECEIVED_SUBVOL)
+ goto skip;
+
+ offset = btrfs_item_ptr_offset(leaf, slot);
+ item_size = btrfs_item_size_nr(leaf, slot);
+ if (!IS_ALIGNED(item_size, sizeof(u64))) {
+ pr_warn("btrfs: uuid item with illegal size %lu!\n",
+ (unsigned long)item_size);
+ goto skip;
+ }
+ while (item_size) {
+ u8 uuid[BTRFS_UUID_SIZE];
+ __le64 subid_le;
+ u64 subid_cpu;
+
+ put_unaligned_le64(key.objectid, uuid);
+ put_unaligned_le64(key.offset, uuid + sizeof(u64));
+ read_extent_buffer(leaf, &subid_le, offset,
+ sizeof(subid_le));
+ subid_cpu = le64_to_cpu(subid_le);
+ ret = check_func(fs_info, uuid, key.type, subid_cpu);
+ if (ret < 0)
+ goto out;
+ if (ret > 0) {
+ btrfs_release_path(path);
+ ret = btrfs_uuid_iter_rem(root, uuid, key.type,
+ subid_cpu);
+ if (ret == 0) {
+ /*
+ * this might look inefficient, but the
+ * justification is that it is an
+ * exception that check_func returns 1,
+ * and that in the regular case only one
+ * entry per UUID exists.
+ */
+ goto again_search_slot;
+ }
+ if (ret < 0 && ret != -ENOENT)
+ goto out;
+ }
+ item_size -= sizeof(subid_le);
+ offset += sizeof(subid_le);
+ }
+
+skip:
+ ret = btrfs_next_item(root, path);
+ if (ret == 0)
+ continue;
+ else if (ret > 0)
+ ret = 0;
+ break;
+ }
+
+out:
+ btrfs_free_path(path);
+ if (ret)
+ pr_warn("btrfs: btrfs_uuid_tree_iterate failed %d\n", ret);
+ return 0;
+}
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 67a0853..0052ca8 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -26,6 +26,7 @@
#include <linux/ratelimit.h>
#include <linux/kthread.h>
#include <linux/raid/pq.h>
+#include <linux/semaphore.h>
#include <asm/div64.h>
#include "compat.h"
#include "ctree.h"
@@ -62,6 +63,48 @@
mutex_unlock(&root->fs_info->chunk_mutex);
}
+static struct btrfs_fs_devices *__alloc_fs_devices(void)
+{
+ struct btrfs_fs_devices *fs_devs;
+
+ fs_devs = kzalloc(sizeof(*fs_devs), GFP_NOFS);
+ if (!fs_devs)
+ return ERR_PTR(-ENOMEM);
+
+ mutex_init(&fs_devs->device_list_mutex);
+
+ INIT_LIST_HEAD(&fs_devs->devices);
+ INIT_LIST_HEAD(&fs_devs->alloc_list);
+ INIT_LIST_HEAD(&fs_devs->list);
+
+ return fs_devs;
+}
+
+/**
+ * alloc_fs_devices - allocate struct btrfs_fs_devices
+ * @fsid: a pointer to UUID for this FS. If NULL a new UUID is
+ * generated.
+ *
+ * Return: a pointer to a new &struct btrfs_fs_devices on success;
+ * ERR_PTR() on error. Returned struct is not linked onto any lists and
+ * can be destroyed with kfree() right away.
+ */
+static struct btrfs_fs_devices *alloc_fs_devices(const u8 *fsid)
+{
+ struct btrfs_fs_devices *fs_devs;
+
+ fs_devs = __alloc_fs_devices();
+ if (IS_ERR(fs_devs))
+ return fs_devs;
+
+ if (fsid)
+ memcpy(fs_devs->fsid, fsid, BTRFS_FSID_SIZE);
+ else
+ generate_random_uuid(fs_devs->fsid);
+
+ return fs_devs;
+}
+
static void free_fs_devices(struct btrfs_fs_devices *fs_devices)
{
struct btrfs_device *device;
@@ -101,6 +144,27 @@
}
}
+static struct btrfs_device *__alloc_device(void)
+{
+ struct btrfs_device *dev;
+
+ dev = kzalloc(sizeof(*dev), GFP_NOFS);
+ if (!dev)
+ return ERR_PTR(-ENOMEM);
+
+ INIT_LIST_HEAD(&dev->dev_list);
+ INIT_LIST_HEAD(&dev->dev_alloc_list);
+
+ spin_lock_init(&dev->io_lock);
+
+ spin_lock_init(&dev->reada_lock);
+ atomic_set(&dev->reada_in_flight, 0);
+ INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_WAIT);
+ INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_WAIT);
+
+ return dev;
+}
+
static noinline struct btrfs_device *__find_device(struct list_head *head,
u64 devid, u8 *uuid)
{
@@ -395,16 +459,14 @@
fs_devices = find_fsid(disk_super->fsid);
if (!fs_devices) {
- fs_devices = kzalloc(sizeof(*fs_devices), GFP_NOFS);
- if (!fs_devices)
- return -ENOMEM;
- INIT_LIST_HEAD(&fs_devices->devices);
- INIT_LIST_HEAD(&fs_devices->alloc_list);
+ fs_devices = alloc_fs_devices(disk_super->fsid);
+ if (IS_ERR(fs_devices))
+ return PTR_ERR(fs_devices);
+
list_add(&fs_devices->list, &fs_uuids);
- memcpy(fs_devices->fsid, disk_super->fsid, BTRFS_FSID_SIZE);
fs_devices->latest_devid = devid;
fs_devices->latest_trans = found_transid;
- mutex_init(&fs_devices->device_list_mutex);
+
device = NULL;
} else {
device = __find_device(&fs_devices->devices, devid,
@@ -414,17 +476,12 @@
if (fs_devices->opened)
return -EBUSY;
- device = kzalloc(sizeof(*device), GFP_NOFS);
- if (!device) {
+ device = btrfs_alloc_device(NULL, &devid,
+ disk_super->dev_item.uuid);
+ if (IS_ERR(device)) {
/* we can safely leave the fs_devices entry around */
- return -ENOMEM;
+ return PTR_ERR(device);
}
- device->devid = devid;
- device->dev_stats_valid = 0;
- device->work.func = pending_bios_fn;
- memcpy(device->uuid, disk_super->dev_item.uuid,
- BTRFS_UUID_SIZE);
- spin_lock_init(&device->io_lock);
name = rcu_string_strdup(path, GFP_NOFS);
if (!name) {
@@ -432,22 +489,13 @@
return -ENOMEM;
}
rcu_assign_pointer(device->name, name);
- INIT_LIST_HEAD(&device->dev_alloc_list);
-
- /* init readahead state */
- spin_lock_init(&device->reada_lock);
- device->reada_curr_zone = NULL;
- atomic_set(&device->reada_in_flight, 0);
- device->reada_next = 0;
- INIT_RADIX_TREE(&device->reada_zones, GFP_NOFS & ~__GFP_WAIT);
- INIT_RADIX_TREE(&device->reada_extents, GFP_NOFS & ~__GFP_WAIT);
mutex_lock(&fs_devices->device_list_mutex);
list_add_rcu(&device->dev_list, &fs_devices->devices);
+ fs_devices->num_devices++;
mutex_unlock(&fs_devices->device_list_mutex);
device->fs_devices = fs_devices;
- fs_devices->num_devices++;
} else if (!device->name || strcmp(device->name->str, path)) {
name = rcu_string_strdup(path, GFP_NOFS);
if (!name)
@@ -474,25 +522,21 @@
struct btrfs_device *device;
struct btrfs_device *orig_dev;
- fs_devices = kzalloc(sizeof(*fs_devices), GFP_NOFS);
- if (!fs_devices)
- return ERR_PTR(-ENOMEM);
+ fs_devices = alloc_fs_devices(orig->fsid);
+ if (IS_ERR(fs_devices))
+ return fs_devices;
- INIT_LIST_HEAD(&fs_devices->devices);
- INIT_LIST_HEAD(&fs_devices->alloc_list);
- INIT_LIST_HEAD(&fs_devices->list);
- mutex_init(&fs_devices->device_list_mutex);
fs_devices->latest_devid = orig->latest_devid;
fs_devices->latest_trans = orig->latest_trans;
fs_devices->total_devices = orig->total_devices;
- memcpy(fs_devices->fsid, orig->fsid, sizeof(fs_devices->fsid));
/* We have held the volume lock, it is safe to get the devices. */
list_for_each_entry(orig_dev, &orig->devices, dev_list) {
struct rcu_string *name;
- device = kzalloc(sizeof(*device), GFP_NOFS);
- if (!device)
+ device = btrfs_alloc_device(NULL, &orig_dev->devid,
+ orig_dev->uuid);
+ if (IS_ERR(device))
goto error;
/*
@@ -506,13 +550,6 @@
}
rcu_assign_pointer(device->name, name);
- device->devid = orig_dev->devid;
- device->work.func = pending_bios_fn;
- memcpy(device->uuid, orig_dev->uuid, sizeof(device->uuid));
- spin_lock_init(&device->io_lock);
- INIT_LIST_HEAD(&device->dev_list);
- INIT_LIST_HEAD(&device->dev_alloc_list);
-
list_add(&device->dev_list, &fs_devices->devices);
device->fs_devices = fs_devices;
fs_devices->num_devices++;
@@ -636,23 +673,22 @@
if (device->can_discard)
fs_devices->num_can_discard--;
+ if (device->missing)
+ fs_devices->missing_devices--;
- new_device = kmalloc(sizeof(*new_device), GFP_NOFS);
- BUG_ON(!new_device); /* -ENOMEM */
- memcpy(new_device, device, sizeof(*new_device));
+ new_device = btrfs_alloc_device(NULL, &device->devid,
+ device->uuid);
+ BUG_ON(IS_ERR(new_device)); /* -ENOMEM */
/* Safe because we are under uuid_mutex */
if (device->name) {
name = rcu_string_strdup(device->name->str, GFP_NOFS);
- BUG_ON(device->name && !name); /* -ENOMEM */
+ BUG_ON(!name); /* -ENOMEM */
rcu_assign_pointer(new_device->name, name);
}
- new_device->bdev = NULL;
- new_device->writeable = 0;
- new_device->in_fs_metadata = 0;
- new_device->can_discard = 0;
- spin_lock_init(&new_device->io_lock);
+
list_replace_rcu(&device->dev_list, &new_device->dev_list);
+ new_device->fs_devices = device->fs_devices;
call_rcu(&device->rcu, free_device);
}
@@ -865,7 +901,7 @@
disk_super = p + (bytenr & ~PAGE_CACHE_MASK);
if (btrfs_super_bytenr(disk_super) != bytenr ||
- disk_super->magic != cpu_to_le64(BTRFS_MAGIC))
+ btrfs_super_magic(disk_super) != BTRFS_MAGIC)
goto error_unmap;
devid = btrfs_stack_device_id(&disk_super->dev_item);
@@ -880,8 +916,7 @@
printk(KERN_INFO "device fsid %pU ", disk_super->fsid);
}
- printk(KERN_CONT "devid %llu transid %llu %s\n",
- (unsigned long long)devid, (unsigned long long)transid, path);
+ printk(KERN_CONT "devid %llu transid %llu %s\n", devid, transid, path);
ret = device_list_add(path, disk_super, devid, fs_devices_ret);
if (!ret && fs_devices_ret)
@@ -1278,8 +1313,7 @@
btrfs_set_dev_extent_chunk_offset(leaf, extent, chunk_offset);
write_extent_buffer(leaf, root->fs_info->chunk_tree_uuid,
- (unsigned long)btrfs_dev_extent_chunk_tree_uuid(extent),
- BTRFS_UUID_SIZE);
+ btrfs_dev_extent_chunk_tree_uuid(extent), BTRFS_UUID_SIZE);
btrfs_set_dev_extent_length(leaf, extent, num_bytes);
btrfs_mark_buffer_dirty(leaf);
@@ -1307,15 +1341,14 @@
return ret;
}
-static noinline int find_next_devid(struct btrfs_root *root, u64 *objectid)
+static noinline int find_next_devid(struct btrfs_fs_info *fs_info,
+ u64 *devid_ret)
{
int ret;
struct btrfs_key key;
struct btrfs_key found_key;
struct btrfs_path *path;
- root = root->fs_info->chunk_root;
-
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
@@ -1324,20 +1357,21 @@
key.type = BTRFS_DEV_ITEM_KEY;
key.offset = (u64)-1;
- ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+ ret = btrfs_search_slot(NULL, fs_info->chunk_root, &key, path, 0, 0);
if (ret < 0)
goto error;
BUG_ON(ret == 0); /* Corruption */
- ret = btrfs_previous_item(root, path, BTRFS_DEV_ITEMS_OBJECTID,
+ ret = btrfs_previous_item(fs_info->chunk_root, path,
+ BTRFS_DEV_ITEMS_OBJECTID,
BTRFS_DEV_ITEM_KEY);
if (ret) {
- *objectid = 1;
+ *devid_ret = 1;
} else {
btrfs_item_key_to_cpu(path->nodes[0], &found_key,
path->slots[0]);
- *objectid = found_key.offset + 1;
+ *devid_ret = found_key.offset + 1;
}
ret = 0;
error:
@@ -1391,9 +1425,9 @@
btrfs_set_device_bandwidth(leaf, dev_item, 0);
btrfs_set_device_start_offset(leaf, dev_item, 0);
- ptr = (unsigned long)btrfs_device_uuid(dev_item);
+ ptr = btrfs_device_uuid(dev_item);
write_extent_buffer(leaf, device->uuid, ptr, BTRFS_UUID_SIZE);
- ptr = (unsigned long)btrfs_device_fsid(dev_item);
+ ptr = btrfs_device_fsid(dev_item);
write_extent_buffer(leaf, root->fs_info->fsid, ptr, BTRFS_UUID_SIZE);
btrfs_mark_buffer_dirty(leaf);
@@ -1562,7 +1596,9 @@
clear_super = true;
}
+ mutex_unlock(&uuid_mutex);
ret = btrfs_shrink_device(device, 0);
+ mutex_lock(&uuid_mutex);
if (ret)
goto error_undo;
@@ -1586,7 +1622,11 @@
/*
* the device list mutex makes sure that we don't change
* the device list while someone else is writing out all
- * the device supers.
+ * the device supers. Whoever is writing all supers, should
+ * lock the device list mutex before getting the number of
+ * devices in the super block (super_copy). Conversely,
+ * whoever updates the number of devices in the super block
+ * (super_copy) should hold the device list mutex.
*/
cur_devices = device->fs_devices;
@@ -1610,10 +1650,10 @@
device->fs_devices->open_devices--;
call_rcu(&device->rcu, free_device);
- mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
num_devices = btrfs_super_num_devices(root->fs_info->super_copy) - 1;
btrfs_set_super_num_devices(root->fs_info->super_copy, num_devices);
+ mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
if (cur_devices->open_devices == 0) {
struct btrfs_fs_devices *fs_devices;
@@ -1793,9 +1833,9 @@
if (!fs_devices->seeding)
return -EINVAL;
- seed_devices = kzalloc(sizeof(*fs_devices), GFP_NOFS);
- if (!seed_devices)
- return -ENOMEM;
+ seed_devices = __alloc_fs_devices();
+ if (IS_ERR(seed_devices))
+ return PTR_ERR(seed_devices);
old_devices = clone_fs_devices(fs_devices);
if (IS_ERR(old_devices)) {
@@ -1814,7 +1854,6 @@
mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
list_splice_init_rcu(&fs_devices->devices, &seed_devices->devices,
synchronize_rcu);
- mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
list_splice_init(&fs_devices->alloc_list, &seed_devices->alloc_list);
list_for_each_entry(device, &seed_devices->devices, dev_list) {
@@ -1830,6 +1869,8 @@
generate_random_uuid(fs_devices->fsid);
memcpy(root->fs_info->fsid, fs_devices->fsid, BTRFS_FSID_SIZE);
memcpy(disk_super->fsid, fs_devices->fsid, BTRFS_FSID_SIZE);
+ mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
+
super_flags = btrfs_super_flags(disk_super) &
~BTRFS_SUPER_FLAG_SEEDING;
btrfs_set_super_flags(disk_super, super_flags);
@@ -1889,11 +1930,9 @@
dev_item = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_dev_item);
devid = btrfs_device_id(leaf, dev_item);
- read_extent_buffer(leaf, dev_uuid,
- (unsigned long)btrfs_device_uuid(dev_item),
+ read_extent_buffer(leaf, dev_uuid, btrfs_device_uuid(dev_item),
BTRFS_UUID_SIZE);
- read_extent_buffer(leaf, fs_uuid,
- (unsigned long)btrfs_device_fsid(dev_item),
+ read_extent_buffer(leaf, fs_uuid, btrfs_device_fsid(dev_item),
BTRFS_UUID_SIZE);
device = btrfs_find_device(root->fs_info, devid, dev_uuid,
fs_uuid);
@@ -1956,10 +1995,10 @@
}
mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
- device = kzalloc(sizeof(*device), GFP_NOFS);
- if (!device) {
+ device = btrfs_alloc_device(root->fs_info, NULL, NULL);
+ if (IS_ERR(device)) {
/* we can safely leave the fs_devices entry around */
- ret = -ENOMEM;
+ ret = PTR_ERR(device);
goto error;
}
@@ -1971,13 +2010,6 @@
}
rcu_assign_pointer(device->name, name);
- ret = find_next_devid(root, &device->devid);
- if (ret) {
- rcu_string_free(device->name);
- kfree(device);
- goto error;
- }
-
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
rcu_string_free(device->name);
@@ -1992,9 +2024,6 @@
if (blk_queue_discard(q))
device->can_discard = 1;
device->writeable = 1;
- device->work.func = pending_bios_fn;
- generate_random_uuid(device->uuid);
- spin_lock_init(&device->io_lock);
device->generation = trans->transid;
device->io_width = root->sectorsize;
device->io_align = root->sectorsize;
@@ -2121,6 +2150,7 @@
struct btrfs_fs_info *fs_info = root->fs_info;
struct list_head *devices;
struct rcu_string *name;
+ u64 devid = BTRFS_DEV_REPLACE_DEVID;
int ret = 0;
*device_out = NULL;
@@ -2142,9 +2172,9 @@
}
}
- device = kzalloc(sizeof(*device), GFP_NOFS);
- if (!device) {
- ret = -ENOMEM;
+ device = btrfs_alloc_device(NULL, &devid, NULL);
+ if (IS_ERR(device)) {
+ ret = PTR_ERR(device);
goto error;
}
@@ -2161,10 +2191,6 @@
device->can_discard = 1;
mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
device->writeable = 1;
- device->work.func = pending_bios_fn;
- generate_random_uuid(device->uuid);
- device->devid = BTRFS_DEV_REPLACE_DEVID;
- spin_lock_init(&device->io_lock);
device->generation = 0;
device->io_width = root->sectorsize;
device->io_align = root->sectorsize;
@@ -2971,10 +2997,6 @@
if (found_key.objectid != key.objectid)
break;
- /* chunk zero is special */
- if (found_key.offset == 0)
- break;
-
chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk);
if (!counting) {
@@ -3010,6 +3032,8 @@
spin_unlock(&fs_info->balance_lock);
}
loop:
+ if (found_key.offset == 0)
+ break;
key.offset = found_key.offset - 1;
}
@@ -3074,9 +3098,6 @@
atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
}
-void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock,
- struct btrfs_ioctl_balance_args *bargs);
-
/*
* Should be called with both balance and volume mutexes held
*/
@@ -3139,7 +3160,7 @@
(bctl->data.target & ~allowed))) {
printk(KERN_ERR "btrfs: unable to start balance with target "
"data profile %llu\n",
- (unsigned long long)bctl->data.target);
+ bctl->data.target);
ret = -EINVAL;
goto out;
}
@@ -3148,7 +3169,7 @@
(bctl->meta.target & ~allowed))) {
printk(KERN_ERR "btrfs: unable to start balance with target "
"metadata profile %llu\n",
- (unsigned long long)bctl->meta.target);
+ bctl->meta.target);
ret = -EINVAL;
goto out;
}
@@ -3157,7 +3178,7 @@
(bctl->sys.target & ~allowed))) {
printk(KERN_ERR "btrfs: unable to start balance with target "
"system profile %llu\n",
- (unsigned long long)bctl->sys.target);
+ bctl->sys.target);
ret = -EINVAL;
goto out;
}
@@ -3430,6 +3451,264 @@
return 0;
}
+static int btrfs_uuid_scan_kthread(void *data)
+{
+ struct btrfs_fs_info *fs_info = data;
+ struct btrfs_root *root = fs_info->tree_root;
+ struct btrfs_key key;
+ struct btrfs_key max_key;
+ struct btrfs_path *path = NULL;
+ int ret = 0;
+ struct extent_buffer *eb;
+ int slot;
+ struct btrfs_root_item root_item;
+ u32 item_size;
+ struct btrfs_trans_handle *trans = NULL;
+
+ path = btrfs_alloc_path();
+ if (!path) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ key.objectid = 0;
+ key.type = BTRFS_ROOT_ITEM_KEY;
+ key.offset = 0;
+
+ max_key.objectid = (u64)-1;
+ max_key.type = BTRFS_ROOT_ITEM_KEY;
+ max_key.offset = (u64)-1;
+
+ path->keep_locks = 1;
+
+ while (1) {
+ ret = btrfs_search_forward(root, &key, &max_key, path, 0);
+ if (ret) {
+ if (ret > 0)
+ ret = 0;
+ break;
+ }
+
+ if (key.type != BTRFS_ROOT_ITEM_KEY ||
+ (key.objectid < BTRFS_FIRST_FREE_OBJECTID &&
+ key.objectid != BTRFS_FS_TREE_OBJECTID) ||
+ key.objectid > BTRFS_LAST_FREE_OBJECTID)
+ goto skip;
+
+ eb = path->nodes[0];
+ slot = path->slots[0];
+ item_size = btrfs_item_size_nr(eb, slot);
+ if (item_size < sizeof(root_item))
+ goto skip;
+
+ read_extent_buffer(eb, &root_item,
+ btrfs_item_ptr_offset(eb, slot),
+ (int)sizeof(root_item));
+ if (btrfs_root_refs(&root_item) == 0)
+ goto skip;
+
+ if (!btrfs_is_empty_uuid(root_item.uuid) ||
+ !btrfs_is_empty_uuid(root_item.received_uuid)) {
+ if (trans)
+ goto update_tree;
+
+ btrfs_release_path(path);
+ /*
+ * 1 - subvol uuid item
+ * 1 - received_subvol uuid item
+ */
+ trans = btrfs_start_transaction(fs_info->uuid_root, 2);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ break;
+ }
+ continue;
+ } else {
+ goto skip;
+ }
+update_tree:
+ if (!btrfs_is_empty_uuid(root_item.uuid)) {
+ ret = btrfs_uuid_tree_add(trans, fs_info->uuid_root,
+ root_item.uuid,
+ BTRFS_UUID_KEY_SUBVOL,
+ key.objectid);
+ if (ret < 0) {
+ pr_warn("btrfs: uuid_tree_add failed %d\n",
+ ret);
+ break;
+ }
+ }
+
+ if (!btrfs_is_empty_uuid(root_item.received_uuid)) {
+ ret = btrfs_uuid_tree_add(trans, fs_info->uuid_root,
+ root_item.received_uuid,
+ BTRFS_UUID_KEY_RECEIVED_SUBVOL,
+ key.objectid);
+ if (ret < 0) {
+ pr_warn("btrfs: uuid_tree_add failed %d\n",
+ ret);
+ break;
+ }
+ }
+
+skip:
+ if (trans) {
+ ret = btrfs_end_transaction(trans, fs_info->uuid_root);
+ trans = NULL;
+ if (ret)
+ break;
+ }
+
+ btrfs_release_path(path);
+ if (key.offset < (u64)-1) {
+ key.offset++;
+ } else if (key.type < BTRFS_ROOT_ITEM_KEY) {
+ key.offset = 0;
+ key.type = BTRFS_ROOT_ITEM_KEY;
+ } else if (key.objectid < (u64)-1) {
+ key.offset = 0;
+ key.type = BTRFS_ROOT_ITEM_KEY;
+ key.objectid++;
+ } else {
+ break;
+ }
+ cond_resched();
+ }
+
+out:
+ btrfs_free_path(path);
+ if (trans && !IS_ERR(trans))
+ btrfs_end_transaction(trans, fs_info->uuid_root);
+ if (ret)
+ pr_warn("btrfs: btrfs_uuid_scan_kthread failed %d\n", ret);
+ else
+ fs_info->update_uuid_tree_gen = 1;
+ up(&fs_info->uuid_tree_rescan_sem);
+ return 0;
+}
+
+/*
+ * Callback for btrfs_uuid_tree_iterate().
+ * returns:
+ * 0 check succeeded, the entry is not outdated.
+ * < 0 if an error occured.
+ * > 0 if the check failed, which means the caller shall remove the entry.
+ */
+static int btrfs_check_uuid_tree_entry(struct btrfs_fs_info *fs_info,
+ u8 *uuid, u8 type, u64 subid)
+{
+ struct btrfs_key key;
+ int ret = 0;
+ struct btrfs_root *subvol_root;
+
+ if (type != BTRFS_UUID_KEY_SUBVOL &&
+ type != BTRFS_UUID_KEY_RECEIVED_SUBVOL)
+ goto out;
+
+ key.objectid = subid;
+ key.type = BTRFS_ROOT_ITEM_KEY;
+ key.offset = (u64)-1;
+ subvol_root = btrfs_read_fs_root_no_name(fs_info, &key);
+ if (IS_ERR(subvol_root)) {
+ ret = PTR_ERR(subvol_root);
+ if (ret == -ENOENT)
+ ret = 1;
+ goto out;
+ }
+
+ switch (type) {
+ case BTRFS_UUID_KEY_SUBVOL:
+ if (memcmp(uuid, subvol_root->root_item.uuid, BTRFS_UUID_SIZE))
+ ret = 1;
+ break;
+ case BTRFS_UUID_KEY_RECEIVED_SUBVOL:
+ if (memcmp(uuid, subvol_root->root_item.received_uuid,
+ BTRFS_UUID_SIZE))
+ ret = 1;
+ break;
+ }
+
+out:
+ return ret;
+}
+
+static int btrfs_uuid_rescan_kthread(void *data)
+{
+ struct btrfs_fs_info *fs_info = (struct btrfs_fs_info *)data;
+ int ret;
+
+ /*
+ * 1st step is to iterate through the existing UUID tree and
+ * to delete all entries that contain outdated data.
+ * 2nd step is to add all missing entries to the UUID tree.
+ */
+ ret = btrfs_uuid_tree_iterate(fs_info, btrfs_check_uuid_tree_entry);
+ if (ret < 0) {
+ pr_warn("btrfs: iterating uuid_tree failed %d\n", ret);
+ up(&fs_info->uuid_tree_rescan_sem);
+ return ret;
+ }
+ return btrfs_uuid_scan_kthread(data);
+}
+
+int btrfs_create_uuid_tree(struct btrfs_fs_info *fs_info)
+{
+ struct btrfs_trans_handle *trans;
+ struct btrfs_root *tree_root = fs_info->tree_root;
+ struct btrfs_root *uuid_root;
+ struct task_struct *task;
+ int ret;
+
+ /*
+ * 1 - root node
+ * 1 - root item
+ */
+ trans = btrfs_start_transaction(tree_root, 2);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
+
+ uuid_root = btrfs_create_tree(trans, fs_info,
+ BTRFS_UUID_TREE_OBJECTID);
+ if (IS_ERR(uuid_root)) {
+ btrfs_abort_transaction(trans, tree_root,
+ PTR_ERR(uuid_root));
+ return PTR_ERR(uuid_root);
+ }
+
+ fs_info->uuid_root = uuid_root;
+
+ ret = btrfs_commit_transaction(trans, tree_root);
+ if (ret)
+ return ret;
+
+ down(&fs_info->uuid_tree_rescan_sem);
+ task = kthread_run(btrfs_uuid_scan_kthread, fs_info, "btrfs-uuid");
+ if (IS_ERR(task)) {
+ /* fs_info->update_uuid_tree_gen remains 0 in all error case */
+ pr_warn("btrfs: failed to start uuid_scan task\n");
+ up(&fs_info->uuid_tree_rescan_sem);
+ return PTR_ERR(task);
+ }
+
+ return 0;
+}
+
+int btrfs_check_uuid_tree(struct btrfs_fs_info *fs_info)
+{
+ struct task_struct *task;
+
+ down(&fs_info->uuid_tree_rescan_sem);
+ task = kthread_run(btrfs_uuid_rescan_kthread, fs_info, "btrfs-uuid");
+ if (IS_ERR(task)) {
+ /* fs_info->update_uuid_tree_gen remains 0 in all error case */
+ pr_warn("btrfs: failed to start uuid_rescan task\n");
+ up(&fs_info->uuid_tree_rescan_sem);
+ return PTR_ERR(task);
+ }
+
+ return 0;
+}
+
/*
* shrinking a device means finding all of the device extents past
* the new size, and then following the back refs to the chunks.
@@ -4194,13 +4473,13 @@
* and exit, so return 1 so the callers don't try to use other copies.
*/
if (!em) {
- btrfs_emerg(fs_info, "No mapping for %Lu-%Lu\n", logical,
+ btrfs_crit(fs_info, "No mapping for %Lu-%Lu\n", logical,
logical+len);
return 1;
}
if (em->start > logical || em->start + em->len < logical) {
- btrfs_emerg(fs_info, "Invalid mapping for %Lu-%Lu, got "
+ btrfs_crit(fs_info, "Invalid mapping for %Lu-%Lu, got "
"%Lu-%Lu\n", logical, logical+len, em->start,
em->start + em->len);
return 1;
@@ -4375,8 +4654,7 @@
if (!em) {
btrfs_crit(fs_info, "unable to find logical %llu len %llu",
- (unsigned long long)logical,
- (unsigned long long)*length);
+ logical, *length);
return -EINVAL;
}
@@ -4671,6 +4949,7 @@
}
bbio = kzalloc(btrfs_bio_size(num_alloc_stripes), GFP_NOFS);
if (!bbio) {
+ kfree(raid_map);
ret = -ENOMEM;
goto out;
}
@@ -5246,9 +5525,7 @@
if (map_length < length) {
btrfs_crit(root->fs_info, "mapping failed logical %llu bio len %llu len %llu",
- (unsigned long long)logical,
- (unsigned long long)length,
- (unsigned long long)map_length);
+ logical, length, map_length);
BUG();
}
@@ -5314,23 +5591,72 @@
struct btrfs_device *device;
struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices;
- device = kzalloc(sizeof(*device), GFP_NOFS);
- if (!device)
+ device = btrfs_alloc_device(NULL, &devid, dev_uuid);
+ if (IS_ERR(device))
return NULL;
- list_add(&device->dev_list,
- &fs_devices->devices);
- device->devid = devid;
- device->work.func = pending_bios_fn;
+
+ list_add(&device->dev_list, &fs_devices->devices);
device->fs_devices = fs_devices;
- device->missing = 1;
fs_devices->num_devices++;
+
+ device->missing = 1;
fs_devices->missing_devices++;
- spin_lock_init(&device->io_lock);
- INIT_LIST_HEAD(&device->dev_alloc_list);
- memcpy(device->uuid, dev_uuid, BTRFS_UUID_SIZE);
+
return device;
}
+/**
+ * btrfs_alloc_device - allocate struct btrfs_device
+ * @fs_info: used only for generating a new devid, can be NULL if
+ * devid is provided (i.e. @devid != NULL).
+ * @devid: a pointer to devid for this device. If NULL a new devid
+ * is generated.
+ * @uuid: a pointer to UUID for this device. If NULL a new UUID
+ * is generated.
+ *
+ * Return: a pointer to a new &struct btrfs_device on success; ERR_PTR()
+ * on error. Returned struct is not linked onto any lists and can be
+ * destroyed with kfree() right away.
+ */
+struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
+ const u64 *devid,
+ const u8 *uuid)
+{
+ struct btrfs_device *dev;
+ u64 tmp;
+
+ if (!devid && !fs_info) {
+ WARN_ON(1);
+ return ERR_PTR(-EINVAL);
+ }
+
+ dev = __alloc_device();
+ if (IS_ERR(dev))
+ return dev;
+
+ if (devid)
+ tmp = *devid;
+ else {
+ int ret;
+
+ ret = find_next_devid(fs_info, &tmp);
+ if (ret) {
+ kfree(dev);
+ return ERR_PTR(ret);
+ }
+ }
+ dev->devid = tmp;
+
+ if (uuid)
+ memcpy(dev->uuid, uuid, BTRFS_UUID_SIZE);
+ else
+ generate_random_uuid(dev->uuid);
+
+ dev->work.func = pending_bios_fn;
+
+ return dev;
+}
+
static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
struct extent_buffer *leaf,
struct btrfs_chunk *chunk)
@@ -5437,7 +5763,7 @@
WARN_ON(device->devid == BTRFS_DEV_REPLACE_DEVID);
device->is_tgtdev_for_dev_replace = 0;
- ptr = (unsigned long)btrfs_device_uuid(dev_item);
+ ptr = btrfs_device_uuid(dev_item);
read_extent_buffer(leaf, device->uuid, ptr, BTRFS_UUID_SIZE);
}
@@ -5500,11 +5826,9 @@
u8 dev_uuid[BTRFS_UUID_SIZE];
devid = btrfs_device_id(leaf, dev_item);
- read_extent_buffer(leaf, dev_uuid,
- (unsigned long)btrfs_device_uuid(dev_item),
+ read_extent_buffer(leaf, dev_uuid, btrfs_device_uuid(dev_item),
BTRFS_UUID_SIZE);
- read_extent_buffer(leaf, fs_uuid,
- (unsigned long)btrfs_device_fsid(dev_item),
+ read_extent_buffer(leaf, fs_uuid, btrfs_device_fsid(dev_item),
BTRFS_UUID_SIZE);
if (memcmp(fs_uuid, root->fs_info->fsid, BTRFS_UUID_SIZE)) {
@@ -5519,8 +5843,7 @@
return -EIO;
if (!device) {
- btrfs_warn(root->fs_info, "devid %llu missing",
- (unsigned long long)devid);
+ btrfs_warn(root->fs_info, "devid %llu missing", devid);
device = add_missing_dev(root, devid, dev_uuid);
if (!device)
return -ENOMEM;
@@ -5644,14 +5967,15 @@
mutex_lock(&uuid_mutex);
lock_chunks(root);
- /* first we search for all of the device items, and then we
- * read in all of the chunk items. This way we can create chunk
- * mappings that reference all of the devices that are afound
+ /*
+ * Read all device items, and then all the chunk items. All
+ * device items are found before any chunk item (their object id
+ * is smaller than the lowest possible object id for a chunk
+ * item - BTRFS_FIRST_CHUNK_TREE_OBJECTID).
*/
key.objectid = BTRFS_DEV_ITEMS_OBJECTID;
key.offset = 0;
key.type = 0;
-again:
ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
if (ret < 0)
goto error;
@@ -5667,17 +5991,13 @@
break;
}
btrfs_item_key_to_cpu(leaf, &found_key, slot);
- if (key.objectid == BTRFS_DEV_ITEMS_OBJECTID) {
- if (found_key.objectid != BTRFS_DEV_ITEMS_OBJECTID)
- break;
- if (found_key.type == BTRFS_DEV_ITEM_KEY) {
- struct btrfs_dev_item *dev_item;
- dev_item = btrfs_item_ptr(leaf, slot,
+ if (found_key.type == BTRFS_DEV_ITEM_KEY) {
+ struct btrfs_dev_item *dev_item;
+ dev_item = btrfs_item_ptr(leaf, slot,
struct btrfs_dev_item);
- ret = read_one_dev(root, leaf, dev_item);
- if (ret)
- goto error;
- }
+ ret = read_one_dev(root, leaf, dev_item);
+ if (ret)
+ goto error;
} else if (found_key.type == BTRFS_CHUNK_ITEM_KEY) {
struct btrfs_chunk *chunk;
chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk);
@@ -5687,11 +6007,6 @@
}
path->slots[0]++;
}
- if (key.objectid == BTRFS_DEV_ITEMS_OBJECTID) {
- key.objectid = 0;
- btrfs_release_path(path);
- goto again;
- }
ret = 0;
error:
unlock_chunks(root);
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 8670558..b72f540 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -152,6 +152,8 @@
int rotating;
};
+#define BTRFS_BIO_INLINE_CSUM_SIZE 64
+
/*
* we need the mirror number and stripe index to be passed around
* the call chain while we are processing end_io (especially errors).
@@ -161,9 +163,14 @@
* we allocate are actually btrfs_io_bios. We'll cram as much of
* struct btrfs_bio as we can into this over time.
*/
+typedef void (btrfs_io_bio_end_io_t) (struct btrfs_io_bio *bio, int err);
struct btrfs_io_bio {
unsigned long mirror_num;
unsigned long stripe_index;
+ u8 *csum;
+ u8 csum_inline[BTRFS_BIO_INLINE_CSUM_SIZE];
+ u8 *csum_allocated;
+ btrfs_io_bio_end_io_t *end_io;
struct bio bio;
};
@@ -298,6 +305,9 @@
int btrfs_find_device_missing_or_by_path(struct btrfs_root *root,
char *device_path,
struct btrfs_device **device);
+struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
+ const u64 *devid,
+ const u8 *uuid);
int btrfs_rm_device(struct btrfs_root *root, char *device_path);
void btrfs_cleanup_fs_uuids(void);
int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len);
@@ -315,6 +325,8 @@
int btrfs_recover_balance(struct btrfs_fs_info *fs_info);
int btrfs_pause_balance(struct btrfs_fs_info *fs_info);
int btrfs_cancel_balance(struct btrfs_fs_info *fs_info);
+int btrfs_create_uuid_tree(struct btrfs_fs_info *fs_info);
+int btrfs_check_uuid_tree(struct btrfs_fs_info *fs_info);
int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset);
int find_free_dev_extent(struct btrfs_trans_handle *trans,
struct btrfs_device *device, u64 num_bytes,
diff --git a/fs/cifs/Makefile b/fs/cifs/Makefile
index aa0d68b..1964d21 100644
--- a/fs/cifs/Makefile
+++ b/fs/cifs/Makefile
@@ -6,7 +6,7 @@
cifs-y := cifsfs.o cifssmb.o cifs_debug.o connect.o dir.o file.o inode.o \
link.o misc.o netmisc.o smbencrypt.o transport.o asn1.o \
cifs_unicode.o nterr.o xattr.o cifsencrypt.o \
- readdir.o ioctl.o sess.o export.o smb1ops.o
+ readdir.o ioctl.o sess.o export.o smb1ops.o winucase.o
cifs-$(CONFIG_CIFS_ACL) += cifsacl.o
diff --git a/fs/cifs/cifs_unicode.h b/fs/cifs/cifs_unicode.h
index fe8d627..d8eac3b 100644
--- a/fs/cifs/cifs_unicode.h
+++ b/fs/cifs/cifs_unicode.h
@@ -91,6 +91,8 @@
#endif /* CONFIG_CIFS_SMB2 */
#endif
+wchar_t cifs_toupper(wchar_t in);
+
/*
* UniStrcat: Concatenate the second string to the first
*
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 85ea98d..a16b4e5 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -255,6 +255,7 @@
cifs_inode->server_eof = 0;
cifs_inode->uniqueid = 0;
cifs_inode->createtime = 0;
+ cifs_inode->epoch = 0;
#ifdef CONFIG_CIFS_SMB2
get_random_bytes(cifs_inode->lease_key, SMB2_LEASE_KEY_SIZE);
#endif
@@ -357,6 +358,18 @@
seq_printf(s, "loose");
}
+static void
+cifs_show_nls(struct seq_file *s, struct nls_table *cur)
+{
+ struct nls_table *def;
+
+ /* Display iocharset= option if it's not default charset */
+ def = load_nls_default();
+ if (def != cur)
+ seq_printf(s, ",iocharset=%s", cur->charset);
+ unload_nls(def);
+}
+
/*
* cifs_show_options() is for displaying mount options in /proc/mounts.
* Not all settable options are displayed but most of the important
@@ -418,6 +431,9 @@
seq_printf(s, ",file_mode=0%ho,dir_mode=0%ho",
cifs_sb->mnt_file_mode,
cifs_sb->mnt_dir_mode);
+
+ cifs_show_nls(s, cifs_sb->local_nls);
+
if (tcon->seal)
seq_printf(s, ",seal");
if (tcon->nocase)
@@ -718,7 +734,7 @@
written = generic_file_aio_write(iocb, iov, nr_segs, pos);
- if (CIFS_I(inode)->clientCanCacheAll)
+ if (CIFS_CACHE_WRITE(CIFS_I(inode)))
return written;
rc = filemap_fdatawrite(inode->i_mapping);
@@ -743,7 +759,7 @@
* We need to be sure that all dirty pages are written and the
* server has the newest file length.
*/
- if (!CIFS_I(inode)->clientCanCacheRead && inode->i_mapping &&
+ if (!CIFS_CACHE_READ(CIFS_I(inode)) && inode->i_mapping &&
inode->i_mapping->nrpages != 0) {
rc = filemap_fdatawait(inode->i_mapping);
if (rc) {
@@ -767,8 +783,10 @@
static int cifs_setlease(struct file *file, long arg, struct file_lock **lease)
{
- /* note that this is called by vfs setlease with i_lock held
- to protect *lease from going away */
+ /*
+ * Note that this is called by vfs setlease with i_lock held to
+ * protect *lease from going away.
+ */
struct inode *inode = file_inode(file);
struct cifsFileInfo *cfile = file->private_data;
@@ -776,20 +794,19 @@
return -EINVAL;
/* check if file is oplocked */
- if (((arg == F_RDLCK) &&
- (CIFS_I(inode)->clientCanCacheRead)) ||
- ((arg == F_WRLCK) &&
- (CIFS_I(inode)->clientCanCacheAll)))
+ if (((arg == F_RDLCK) && CIFS_CACHE_READ(CIFS_I(inode))) ||
+ ((arg == F_WRLCK) && CIFS_CACHE_WRITE(CIFS_I(inode))))
return generic_setlease(file, arg, lease);
else if (tlink_tcon(cfile->tlink)->local_lease &&
- !CIFS_I(inode)->clientCanCacheRead)
- /* If the server claims to support oplock on this
- file, then we still need to check oplock even
- if the local_lease mount option is set, but there
- are servers which do not support oplock for which
- this mount option may be useful if the user
- knows that the file won't be changed on the server
- by anyone else */
+ !CIFS_CACHE_READ(CIFS_I(inode)))
+ /*
+ * If the server claims to support oplock on this file, then we
+ * still need to check oplock even if the local_lease mount
+ * option is set, but there are servers which do not support
+ * oplock for which this mount option may be useful if the user
+ * knows that the file won't be changed on the server by anyone
+ * else.
+ */
return generic_setlease(file, arg, lease);
else
return -EAGAIN;
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 52ca861..cfa14c8 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -28,6 +28,7 @@
#include "cifsacl.h"
#include <crypto/internal/hash.h>
#include <linux/scatterlist.h>
+#include <uapi/linux/cifs/cifs_mount.h>
#ifdef CONFIG_CIFS_SMB2
#include "smb2pdu.h"
#endif
@@ -41,12 +42,7 @@
#define MAX_SES_INFO 2
#define MAX_TCON_INFO 4
-#define MAX_TREE_SIZE (2 + MAX_SERVER_SIZE + 1 + MAX_SHARE_SIZE + 1)
-#define MAX_SERVER_SIZE 15
-#define MAX_SHARE_SIZE 80
-#define CIFS_MAX_DOMAINNAME_LEN 256 /* max domain name length */
-#define MAX_USERNAME_SIZE 256 /* reasonable maximum for current servers */
-#define MAX_PASSWORD_SIZE 512 /* max for windows seems to be 256 wide chars */
+#define MAX_TREE_SIZE (2 + CIFS_NI_MAXHOST + 1 + CIFS_MAX_SHARE_LEN + 1)
#define CIFS_MIN_RCV_POOL 4
@@ -135,6 +131,7 @@
/* per smb session structure/fields */
struct ntlmssp_auth {
+ bool sesskey_per_smbsess; /* whether session key is per smb session */
__u32 client_flags; /* sent by client in type 1 ntlmsssp exchange */
__u32 server_flags; /* sent by server in type 2 ntlmssp exchange */
unsigned char ciphertext[CIFS_CPHTXT_SIZE]; /* sent to server */
@@ -308,6 +305,9 @@
int (*create_hardlink)(const unsigned int, struct cifs_tcon *,
const char *, const char *,
struct cifs_sb_info *);
+ /* query symlink target */
+ int (*query_symlink)(const unsigned int, struct cifs_tcon *,
+ const char *, char **, struct cifs_sb_info *);
/* open a file for non-posix mounts */
int (*open)(const unsigned int, struct cifs_open_parms *,
__u32 *, FILE_ALL_INFO *);
@@ -361,18 +361,24 @@
/* push brlocks from the cache to the server */
int (*push_mand_locks)(struct cifsFileInfo *);
/* get lease key of the inode */
- void (*get_lease_key)(struct inode *, struct cifs_fid *fid);
+ void (*get_lease_key)(struct inode *, struct cifs_fid *);
/* set lease key of the inode */
- void (*set_lease_key)(struct inode *, struct cifs_fid *fid);
+ void (*set_lease_key)(struct inode *, struct cifs_fid *);
/* generate new lease key */
- void (*new_lease_key)(struct cifs_fid *fid);
- /* The next two functions will need to be changed to per smb session */
- void (*generate_signingkey)(struct TCP_Server_Info *server);
- int (*calc_signature)(struct smb_rqst *rqst,
- struct TCP_Server_Info *server);
- int (*query_mf_symlink)(const unsigned char *path, char *pbuf,
- unsigned int *pbytes_read, struct cifs_sb_info *cifs_sb,
- unsigned int xid);
+ void (*new_lease_key)(struct cifs_fid *);
+ int (*generate_signingkey)(struct cifs_ses *);
+ int (*calc_signature)(struct smb_rqst *, struct TCP_Server_Info *);
+ int (*query_mf_symlink)(const unsigned char *, char *, unsigned int *,
+ struct cifs_sb_info *, unsigned int);
+ /* if we can do cache read operations */
+ bool (*is_read_op)(__u32);
+ /* set oplock level for the inode */
+ void (*set_oplock_level)(struct cifsInodeInfo *, __u32, unsigned int,
+ bool *);
+ /* create lease context buffer for CREATE request */
+ char * (*create_lease_buf)(u8 *, u8);
+ /* parse lease context buffer and return oplock/epoch info */
+ __u8 (*parse_lease_buf)(void *, unsigned int *);
};
struct smb_version_values {
@@ -390,9 +396,9 @@
unsigned int cap_unix;
unsigned int cap_nt_find;
unsigned int cap_large_files;
- unsigned int oplock_read;
__u16 signing_enabled;
__u16 signing_required;
+ size_t create_lease_size;
};
#define HEADER_SIZE(server) (server->vals->header_size)
@@ -548,7 +554,6 @@
int timeAdj; /* Adjust for difference in server time zone in sec */
__u64 CurrentMid; /* multiplex id - rotating counter */
char cryptkey[CIFS_CRYPTO_KEY_SIZE]; /* used by ntlm, ntlmv2 etc */
- char smb3signingkey[SMB3_SIGN_KEY_SIZE]; /* for signing smb3 packets */
/* 16th byte of RFC1001 workstation name is always null */
char workstation_RFC1001_name[RFC1001_NAME_LEN_WITH_NULL];
__u32 sequence_number; /* for signing, protected by srv_mutex */
@@ -731,6 +736,7 @@
bool need_reconnect:1; /* connection reset, uid now invalid */
#ifdef CONFIG_CIFS_SMB2
__u16 session_flags;
+ char smb3signingkey[SMB3_SIGN_KEY_SIZE]; /* for signing smb3 packets */
#endif /* CONFIG_CIFS_SMB2 */
};
@@ -935,6 +941,8 @@
__u8 lease_key[SMB2_LEASE_KEY_SIZE]; /* lease key for smb2 */
#endif
struct cifs_pending_open *pending_open;
+ unsigned int epoch;
+ bool purge_cache;
};
struct cifs_fid_locks {
@@ -1032,6 +1040,17 @@
struct cifsFileInfo *cifsFileInfo_get(struct cifsFileInfo *cifs_file);
void cifsFileInfo_put(struct cifsFileInfo *cifs_file);
+#define CIFS_CACHE_READ_FLG 1
+#define CIFS_CACHE_HANDLE_FLG 2
+#define CIFS_CACHE_RH_FLG (CIFS_CACHE_READ_FLG | CIFS_CACHE_HANDLE_FLG)
+#define CIFS_CACHE_WRITE_FLG 4
+#define CIFS_CACHE_RW_FLG (CIFS_CACHE_READ_FLG | CIFS_CACHE_WRITE_FLG)
+#define CIFS_CACHE_RHW_FLG (CIFS_CACHE_RW_FLG | CIFS_CACHE_HANDLE_FLG)
+
+#define CIFS_CACHE_READ(cinode) (cinode->oplock & CIFS_CACHE_READ_FLG)
+#define CIFS_CACHE_HANDLE(cinode) (cinode->oplock & CIFS_CACHE_HANDLE_FLG)
+#define CIFS_CACHE_WRITE(cinode) (cinode->oplock & CIFS_CACHE_WRITE_FLG)
+
/*
* One of these for each file inode
*/
@@ -1043,8 +1062,8 @@
/* BB add in lists for dirty pages i.e. write caching info for oplock */
struct list_head openFileList;
__u32 cifsAttrs; /* e.g. DOS archive bit, sparse, compressed, system */
- bool clientCanCacheRead; /* read oplock */
- bool clientCanCacheAll; /* read and writebehind oplock */
+ unsigned int oplock; /* oplock/lease level we have */
+ unsigned int epoch; /* used to track lease state changes */
bool delete_pending; /* DELETE_ON_CLOSE is set */
bool invalid_mapping; /* pagecache is invalid */
unsigned long time; /* jiffies of last update of inode */
@@ -1502,7 +1521,7 @@
extern struct smb_version_operations smb1_operations;
extern struct smb_version_values smb1_values;
#define SMB20_VERSION_STRING "2.0"
-/*extern struct smb_version_operations smb20_operations; */ /* not needed yet */
+extern struct smb_version_operations smb20_operations;
extern struct smb_version_values smb20_values;
#define SMB21_VERSION_STRING "2.1"
extern struct smb_version_operations smb21_operations;
diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h
index 11ca24a..948676d 100644
--- a/fs/cifs/cifspdu.h
+++ b/fs/cifs/cifspdu.h
@@ -1495,11 +1495,12 @@
__u32 ReparseTag;
__u16 ReparseDataLength;
__u16 Reserved;
- __u16 AltNameOffset;
- __u16 AltNameLen;
- __u16 TargetNameOffset;
- __u16 TargetNameLen;
- char LinkNamesBuf[1];
+ __u16 SubstituteNameOffset;
+ __u16 SubstituteNameLength;
+ __u16 PrintNameOffset;
+ __u16 PrintNameLength;
+ __u32 Flags;
+ char PathBuffer[0];
} __attribute__((packed));
struct cifs_quota_data {
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index b29a012..b5ec2a2 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -357,13 +357,9 @@
struct cifs_tcon *tcon,
const unsigned char *searchName, char **syminfo,
const struct nls_table *nls_codepage);
-#ifdef CONFIG_CIFS_SYMLINK_EXPERIMENTAL
-extern int CIFSSMBQueryReparseLinkInfo(const unsigned int xid,
- struct cifs_tcon *tcon,
- const unsigned char *searchName,
- char *symlinkinfo, const int buflen, __u16 fid,
- const struct nls_table *nls_codepage);
-#endif /* temporarily unused until cifs_symlink fixed */
+extern int CIFSSMBQuerySymLink(const unsigned int xid, struct cifs_tcon *tcon,
+ __u16 fid, char **symlinkinfo,
+ const struct nls_table *nls_codepage);
extern int CIFSSMBOpen(const unsigned int xid, struct cifs_tcon *tcon,
const char *fileName, const int disposition,
const int access_flags, const int omode,
@@ -435,7 +431,7 @@
extern int setup_ntlmv2_rsp(struct cifs_ses *, const struct nls_table *);
extern void cifs_crypto_shash_release(struct TCP_Server_Info *);
extern int calc_seckey(struct cifs_ses *);
-extern void generate_smb3signingkey(struct TCP_Server_Info *);
+extern int generate_smb3signingkey(struct cifs_ses *);
#ifdef CONFIG_CIFS_WEAK_PW_HASH
extern int calc_lanman_hash(const char *password, const char *cryptkey,
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index a89c4cb..a3d74fe 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -3067,7 +3067,6 @@
return rc;
}
-#ifdef CONFIG_CIFS_SYMLINK_EXPERIMENTAL
/*
* Recent Windows versions now create symlinks more frequently
* and they use the "reparse point" mechanism below. We can of course
@@ -3079,18 +3078,22 @@
* it is not compiled in by default until callers fixed up and more tested.
*/
int
-CIFSSMBQueryReparseLinkInfo(const unsigned int xid, struct cifs_tcon *tcon,
- const unsigned char *searchName,
- char *symlinkinfo, const int buflen, __u16 fid,
- const struct nls_table *nls_codepage)
+CIFSSMBQuerySymLink(const unsigned int xid, struct cifs_tcon *tcon,
+ __u16 fid, char **symlinkinfo,
+ const struct nls_table *nls_codepage)
{
int rc = 0;
int bytes_returned;
struct smb_com_transaction_ioctl_req *pSMB;
struct smb_com_transaction_ioctl_rsp *pSMBr;
+ bool is_unicode;
+ unsigned int sub_len;
+ char *sub_start;
+ struct reparse_data *reparse_buf;
+ __u32 data_offset, data_count;
+ char *end_of_smb;
- cifs_dbg(FYI, "In Windows reparse style QueryLink for path %s\n",
- searchName);
+ cifs_dbg(FYI, "In Windows reparse style QueryLink for fid %u\n", fid);
rc = smb_init(SMB_COM_NT_TRANSACT, 23, tcon, (void **) &pSMB,
(void **) &pSMBr);
if (rc)
@@ -3119,66 +3122,55 @@
(struct smb_hdr *) pSMBr, &bytes_returned, 0);
if (rc) {
cifs_dbg(FYI, "Send error in QueryReparseLinkInfo = %d\n", rc);
- } else { /* decode response */
- __u32 data_offset = le32_to_cpu(pSMBr->DataOffset);
- __u32 data_count = le32_to_cpu(pSMBr->DataCount);
- if (get_bcc(&pSMBr->hdr) < 2 || data_offset > 512) {
- /* BB also check enough total bytes returned */
- rc = -EIO; /* bad smb */
- goto qreparse_out;
- }
- if (data_count && (data_count < 2048)) {
- char *end_of_smb = 2 /* sizeof byte count */ +
- get_bcc(&pSMBr->hdr) + (char *)&pSMBr->ByteCount;
-
- struct reparse_data *reparse_buf =
- (struct reparse_data *)
- ((char *)&pSMBr->hdr.Protocol
- + data_offset);
- if ((char *)reparse_buf >= end_of_smb) {
- rc = -EIO;
- goto qreparse_out;
- }
- if ((reparse_buf->LinkNamesBuf +
- reparse_buf->TargetNameOffset +
- reparse_buf->TargetNameLen) > end_of_smb) {
- cifs_dbg(FYI, "reparse buf beyond SMB\n");
- rc = -EIO;
- goto qreparse_out;
- }
-
- if (pSMBr->hdr.Flags2 & SMBFLG2_UNICODE) {
- cifs_from_ucs2(symlinkinfo, (__le16 *)
- (reparse_buf->LinkNamesBuf +
- reparse_buf->TargetNameOffset),
- buflen,
- reparse_buf->TargetNameLen,
- nls_codepage, 0);
- } else { /* ASCII names */
- strncpy(symlinkinfo,
- reparse_buf->LinkNamesBuf +
- reparse_buf->TargetNameOffset,
- min_t(const int, buflen,
- reparse_buf->TargetNameLen));
- }
- } else {
- rc = -EIO;
- cifs_dbg(FYI, "Invalid return data count on get reparse info ioctl\n");
- }
- symlinkinfo[buflen] = 0; /* just in case so the caller
- does not go off the end of the buffer */
- cifs_dbg(FYI, "readlink result - %s\n", symlinkinfo);
+ goto qreparse_out;
}
+ data_offset = le32_to_cpu(pSMBr->DataOffset);
+ data_count = le32_to_cpu(pSMBr->DataCount);
+ if (get_bcc(&pSMBr->hdr) < 2 || data_offset > 512) {
+ /* BB also check enough total bytes returned */
+ rc = -EIO; /* bad smb */
+ goto qreparse_out;
+ }
+ if (!data_count || (data_count > 2048)) {
+ rc = -EIO;
+ cifs_dbg(FYI, "Invalid return data count on get reparse info ioctl\n");
+ goto qreparse_out;
+ }
+ end_of_smb = 2 + get_bcc(&pSMBr->hdr) + (char *)&pSMBr->ByteCount;
+ reparse_buf = (struct reparse_data *)
+ ((char *)&pSMBr->hdr.Protocol + data_offset);
+ if ((char *)reparse_buf >= end_of_smb) {
+ rc = -EIO;
+ goto qreparse_out;
+ }
+ if ((reparse_buf->PathBuffer + reparse_buf->PrintNameOffset +
+ reparse_buf->PrintNameLength) > end_of_smb) {
+ cifs_dbg(FYI, "reparse buf beyond SMB\n");
+ rc = -EIO;
+ goto qreparse_out;
+ }
+ sub_start = reparse_buf->SubstituteNameOffset + reparse_buf->PathBuffer;
+ sub_len = reparse_buf->SubstituteNameLength;
+ if (pSMBr->hdr.Flags2 & SMBFLG2_UNICODE)
+ is_unicode = true;
+ else
+ is_unicode = false;
+
+ /* BB FIXME investigate remapping reserved chars here */
+ *symlinkinfo = cifs_strndup_from_utf16(sub_start, sub_len, is_unicode,
+ nls_codepage);
+ if (!*symlinkinfo)
+ rc = -ENOMEM;
qreparse_out:
cifs_buf_release(pSMB);
- /* Note: On -EAGAIN error only caller can retry on handle based calls
- since file handle passed in no longer valid */
-
+ /*
+ * Note: On -EAGAIN error only caller can retry on handle based calls
+ * since file handle passed in no longer valid.
+ */
return rc;
}
-#endif /* CIFS_SYMLINK_EXPERIMENTAL */ /* BB temporarily unused */
#ifdef CONFIG_CIFS_POSIX
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index d67c550..a279ffc 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -379,6 +379,7 @@
try_to_freeze();
/* we should try only the port we connected to before */
+ mutex_lock(&server->srv_mutex);
rc = generic_ip_connect(server);
if (rc) {
cifs_dbg(FYI, "reconnect error %d\n", rc);
@@ -390,6 +391,7 @@
server->tcpStatus = CifsNeedNegotiate;
spin_unlock(&GlobalMid_Lock);
}
+ mutex_unlock(&server->srv_mutex);
} while (server->tcpStatus == CifsNeedReconnect);
return rc;
@@ -1114,7 +1116,7 @@
break;
#ifdef CONFIG_CIFS_SMB2
case Smb_20:
- vol->ops = &smb21_operations; /* currently identical with 2.1 */
+ vol->ops = &smb20_operations;
vol->vals = &smb20_values;
break;
case Smb_21:
@@ -1575,8 +1577,8 @@
if (string == NULL)
goto out_nomem;
- if (strnlen(string, MAX_USERNAME_SIZE) >
- MAX_USERNAME_SIZE) {
+ if (strnlen(string, CIFS_MAX_USERNAME_LEN) >
+ CIFS_MAX_USERNAME_LEN) {
printk(KERN_WARNING "CIFS: username too long\n");
goto cifs_parse_mount_err;
}
@@ -2221,13 +2223,13 @@
/* anything else takes username/password */
if (strncmp(ses->user_name,
vol->username ? vol->username : "",
- MAX_USERNAME_SIZE))
+ CIFS_MAX_USERNAME_LEN))
return 0;
if (strlen(vol->username) != 0 &&
ses->password != NULL &&
strncmp(ses->password,
vol->password ? vol->password : "",
- MAX_PASSWORD_SIZE))
+ CIFS_MAX_PASSWORD_LEN))
return 0;
}
return 1;
@@ -2352,7 +2354,7 @@
}
len = delim - payload;
- if (len > MAX_USERNAME_SIZE || len <= 0) {
+ if (len > CIFS_MAX_USERNAME_LEN || len <= 0) {
cifs_dbg(FYI, "Bad value from username search (len=%zd)\n",
len);
rc = -EINVAL;
@@ -2369,7 +2371,7 @@
cifs_dbg(FYI, "%s: username=%s\n", __func__, vol->username);
len = key->datalen - (len + 1);
- if (len > MAX_PASSWORD_SIZE || len <= 0) {
+ if (len > CIFS_MAX_PASSWORD_LEN || len <= 0) {
cifs_dbg(FYI, "Bad len for password search (len=%zd)\n", len);
rc = -EINVAL;
kfree(vol->username);
@@ -3826,33 +3828,8 @@
if (server->ops->sess_setup)
rc = server->ops->sess_setup(xid, ses, nls_info);
- if (rc) {
+ if (rc)
cifs_dbg(VFS, "Send error in SessSetup = %d\n", rc);
- } else {
- mutex_lock(&server->srv_mutex);
- if (!server->session_estab) {
- server->session_key.response = ses->auth_key.response;
- server->session_key.len = ses->auth_key.len;
- server->sequence_number = 0x2;
- server->session_estab = true;
- ses->auth_key.response = NULL;
- if (server->ops->generate_signingkey)
- server->ops->generate_signingkey(server);
- }
- mutex_unlock(&server->srv_mutex);
-
- cifs_dbg(FYI, "CIFS Session Established successfully\n");
- spin_lock(&GlobalMid_Lock);
- ses->status = CifsGood;
- ses->need_reconnect = false;
- spin_unlock(&GlobalMid_Lock);
- }
-
- kfree(ses->auth_key.response);
- ses->auth_key.response = NULL;
- ses->auth_key.len = 0;
- kfree(ses->ntlmssp);
- ses->ntlmssp = NULL;
return rc;
}
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index d62ce0d..d3e2eaa 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -32,6 +32,7 @@
#include "cifsproto.h"
#include "cifs_debug.h"
#include "cifs_fs_sb.h"
+#include "cifs_unicode.h"
static void
renew_parental_timestamps(struct dentry *direntry)
@@ -834,12 +835,17 @@
{
struct nls_table *codepage = CIFS_SB(dentry->d_sb)->local_nls;
unsigned long hash;
- int i;
+ wchar_t c;
+ int i, charlen;
hash = init_name_hash();
- for (i = 0; i < q->len; i++)
- hash = partial_name_hash(nls_tolower(codepage, q->name[i]),
- hash);
+ for (i = 0; i < q->len; i += charlen) {
+ charlen = codepage->char2uni(&q->name[i], q->len - i, &c);
+ /* error out if we can't convert the character */
+ if (unlikely(charlen < 0))
+ return charlen;
+ hash = partial_name_hash(cifs_toupper(c), hash);
+ }
q->hash = end_name_hash(hash);
return 0;
@@ -849,11 +855,47 @@
unsigned int len, const char *str, const struct qstr *name)
{
struct nls_table *codepage = CIFS_SB(parent->d_sb)->local_nls;
+ wchar_t c1, c2;
+ int i, l1, l2;
- if ((name->len == len) &&
- (nls_strnicmp(codepage, name->name, str, len) == 0))
- return 0;
- return 1;
+ /*
+ * We make the assumption here that uppercase characters in the local
+ * codepage are always the same length as their lowercase counterparts.
+ *
+ * If that's ever not the case, then this will fail to match it.
+ */
+ if (name->len != len)
+ return 1;
+
+ for (i = 0; i < len; i += l1) {
+ /* Convert characters in both strings to UTF-16. */
+ l1 = codepage->char2uni(&str[i], len - i, &c1);
+ l2 = codepage->char2uni(&name->name[i], name->len - i, &c2);
+
+ /*
+ * If we can't convert either character, just declare it to
+ * be 1 byte long and compare the original byte.
+ */
+ if (unlikely(l1 < 0 && l2 < 0)) {
+ if (str[i] != name->name[i])
+ return 1;
+ l1 = 1;
+ continue;
+ }
+
+ /*
+ * Here, we again ass|u|me that upper/lowercase versions of
+ * a character are the same length in the local NLS.
+ */
+ if (l1 != l2)
+ return 1;
+
+ /* Now compare uppercase versions of these characters */
+ if (cifs_toupper(c1) != cifs_toupper(c2))
+ return 1;
+ }
+
+ return 0;
}
const struct dentry_operations cifs_ci_dentry_ops = {
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 9d0dd95..d044b35 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -313,8 +313,7 @@
* If the server returned a read oplock and we have mandatory brlocks,
* set oplock level to None.
*/
- if (oplock == server->vals->oplock_read &&
- cifs_has_mand_locks(cinode)) {
+ if (server->ops->is_read_op(oplock) && cifs_has_mand_locks(cinode)) {
cifs_dbg(FYI, "Reset oplock val from read to None due to mand locks\n");
oplock = 0;
}
@@ -324,6 +323,7 @@
oplock = fid->pending_open->oplock;
list_del(&fid->pending_open->olist);
+ fid->purge_cache = false;
server->ops->set_fid(cfile, fid, oplock);
list_add(&cfile->tlist, &tcon->openFileList);
@@ -334,6 +334,9 @@
list_add_tail(&cfile->flist, &cinode->openFileList);
spin_unlock(&cifs_file_list_lock);
+ if (fid->purge_cache)
+ cifs_invalidate_mapping(inode);
+
file->private_data = cfile;
return cfile;
}
@@ -1524,12 +1527,12 @@
* read won't conflict with non-overlapted locks due to
* pagereading.
*/
- if (!CIFS_I(inode)->clientCanCacheAll &&
- CIFS_I(inode)->clientCanCacheRead) {
+ if (!CIFS_CACHE_WRITE(CIFS_I(inode)) &&
+ CIFS_CACHE_READ(CIFS_I(inode))) {
cifs_invalidate_mapping(inode);
cifs_dbg(FYI, "Set no oplock for inode=%p due to mand locks\n",
inode);
- CIFS_I(inode)->clientCanCacheRead = false;
+ CIFS_I(inode)->oplock = 0;
}
rc = server->ops->mand_lock(xid, cfile, flock->fl_start, length,
@@ -2213,7 +2216,7 @@
cifs_dbg(FYI, "Sync file - name: %s datasync: 0x%x\n",
file->f_path.dentry->d_name.name, datasync);
- if (!CIFS_I(inode)->clientCanCacheRead) {
+ if (!CIFS_CACHE_READ(CIFS_I(inode))) {
rc = cifs_invalidate_mapping(inode);
if (rc) {
cifs_dbg(FYI, "rc: %d during invalidate phase\n", rc);
@@ -2577,7 +2580,7 @@
struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
ssize_t written;
- if (cinode->clientCanCacheAll) {
+ if (CIFS_CACHE_WRITE(cinode)) {
if (cap_unix(tcon->ses) &&
(CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability))
&& ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0))
@@ -2591,7 +2594,7 @@
* these pages but not on the region from pos to ppos+len-1.
*/
written = cifs_user_writev(iocb, iov, nr_segs, pos);
- if (written > 0 && cinode->clientCanCacheRead) {
+ if (written > 0 && CIFS_CACHE_READ(cinode)) {
/*
* Windows 7 server can delay breaking level2 oplock if a write
* request comes - break it on the client to prevent reading
@@ -2600,7 +2603,7 @@
cifs_invalidate_mapping(inode);
cifs_dbg(FYI, "Set no oplock for inode=%p after a write operation\n",
inode);
- cinode->clientCanCacheRead = false;
+ cinode->oplock = 0;
}
return written;
}
@@ -2957,7 +2960,7 @@
* on pages affected by this read but not on the region from pos to
* pos+len-1.
*/
- if (!cinode->clientCanCacheRead)
+ if (!CIFS_CACHE_READ(cinode))
return cifs_user_readv(iocb, iov, nr_segs, pos);
if (cap_unix(tcon->ses) &&
@@ -3093,7 +3096,7 @@
xid = get_xid();
- if (!CIFS_I(inode)->clientCanCacheRead) {
+ if (!CIFS_CACHE_READ(CIFS_I(inode))) {
rc = cifs_invalidate_mapping(inode);
if (rc)
return rc;
@@ -3526,7 +3529,7 @@
* is, when the page lies beyond the EOF, or straddles the EOF
* and the write will cover all of the existing data.
*/
- if (CIFS_I(mapping->host)->clientCanCacheRead) {
+ if (CIFS_CACHE_READ(CIFS_I(mapping->host))) {
i_size = i_size_read(mapping->host);
if (page_start >= i_size ||
(offset == 0 && (pos + len) >= i_size)) {
@@ -3609,20 +3612,20 @@
struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
int rc = 0;
- if (!cinode->clientCanCacheAll && cinode->clientCanCacheRead &&
+ if (!CIFS_CACHE_WRITE(cinode) && CIFS_CACHE_READ(cinode) &&
cifs_has_mand_locks(cinode)) {
cifs_dbg(FYI, "Reset oplock to None for inode=%p due to mand locks\n",
inode);
- cinode->clientCanCacheRead = false;
+ cinode->oplock = 0;
}
if (inode && S_ISREG(inode->i_mode)) {
- if (cinode->clientCanCacheRead)
+ if (CIFS_CACHE_READ(cinode))
break_lease(inode, O_RDONLY);
else
break_lease(inode, O_WRONLY);
rc = filemap_fdatawrite(inode->i_mapping);
- if (cinode->clientCanCacheRead == 0) {
+ if (!CIFS_CACHE_READ(cinode)) {
rc = filemap_fdatawait(inode->i_mapping);
mapping_set_error(inode->i_mapping, rc);
cifs_invalidate_mapping(inode);
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 449b6cf..f9ff9c1 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -101,7 +101,7 @@
}
/* don't bother with revalidation if we have an oplock */
- if (cifs_i->clientCanCacheRead) {
+ if (CIFS_CACHE_READ(cifs_i)) {
cifs_dbg(FYI, "%s: inode %llu is oplocked\n",
__func__, cifs_i->uniqueid);
return;
@@ -549,6 +549,10 @@
* when Unix extensions are disabled - fake it.
*/
fattr->cf_nlink = 2;
+ } else if (fattr->cf_cifsattrs & ATTR_REPARSE) {
+ fattr->cf_mode = S_IFLNK;
+ fattr->cf_dtype = DT_LNK;
+ fattr->cf_nlink = le32_to_cpu(info->NumberOfLinks);
} else {
fattr->cf_mode = S_IFREG | cifs_sb->mnt_file_mode;
fattr->cf_dtype = DT_REG;
@@ -646,7 +650,7 @@
cifs_dbg(FYI, "Getting info on %s\n", full_path);
if ((data == NULL) && (*inode != NULL)) {
- if (CIFS_I(*inode)->clientCanCacheRead) {
+ if (CIFS_CACHE_READ(CIFS_I(*inode))) {
cifs_dbg(FYI, "No need to revalidate cached inode sizes\n");
goto cgii_exit;
}
@@ -1657,7 +1661,7 @@
struct cifsInodeInfo *cifs_i = CIFS_I(inode);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
- if (cifs_i->clientCanCacheRead)
+ if (CIFS_CACHE_READ(cifs_i))
return false;
if (!lookupCacheEnabled)
@@ -1800,7 +1804,7 @@
* We need to be sure that all dirty pages are written and the server
* has actual ctime, mtime and file length.
*/
- if (!CIFS_I(inode)->clientCanCacheRead && inode->i_mapping &&
+ if (!CIFS_CACHE_READ(CIFS_I(inode)) && inode->i_mapping &&
inode->i_mapping->nrpages != 0) {
rc = filemap_fdatawait(inode->i_mapping);
if (rc) {
@@ -1852,14 +1856,11 @@
static void cifs_setsize(struct inode *inode, loff_t offset)
{
- loff_t oldsize;
-
spin_lock(&inode->i_lock);
- oldsize = inode->i_size;
i_size_write(inode, offset);
spin_unlock(&inode->i_lock);
- truncate_pagecache(inode, oldsize, offset);
+ truncate_pagecache(inode, offset);
}
static int
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index 562044f..7e36ceb 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -509,6 +509,7 @@
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct tcon_link *tlink = NULL;
struct cifs_tcon *tcon;
+ struct TCP_Server_Info *server;
xid = get_xid();
@@ -519,25 +520,7 @@
goto out;
}
tcon = tlink_tcon(tlink);
-
- /*
- * For now, we just handle symlinks with unix extensions enabled.
- * Eventually we should handle NTFS reparse points, and MacOS
- * symlink support. For instance...
- *
- * rc = CIFSSMBQueryReparseLinkInfo(...)
- *
- * For now, just return -EACCES when the server doesn't support posix
- * extensions. Note that we still allow querying symlinks when posix
- * extensions are manually disabled. We could disable these as well
- * but there doesn't seem to be any harm in allowing the client to
- * read them.
- */
- if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) &&
- !cap_unix(tcon->ses)) {
- rc = -EACCES;
- goto out;
- }
+ server = tcon->ses->server;
full_path = build_path_from_dentry(direntry);
if (!full_path)
@@ -559,6 +542,9 @@
if ((rc != 0) && cap_unix(tcon->ses))
rc = CIFSSMBUnixQuerySymLink(xid, tcon, full_path, &target_path,
cifs_sb->local_nls);
+ else if (rc != 0 && server->ops->query_symlink)
+ rc = server->ops->query_symlink(xid, tcon, full_path,
+ &target_path, cifs_sb);
kfree(full_path);
out:
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index f7d4b22..138a011 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -105,6 +105,7 @@
}
kfree(buf_to_free->user_name);
kfree(buf_to_free->domainName);
+ kfree(buf_to_free->auth_key.response);
kfree(buf_to_free);
}
@@ -545,19 +546,15 @@
oplock &= 0xF;
if (oplock == OPLOCK_EXCLUSIVE) {
- cinode->clientCanCacheAll = true;
- cinode->clientCanCacheRead = true;
+ cinode->oplock = CIFS_CACHE_WRITE_FLG | CIFS_CACHE_READ_FLG;
cifs_dbg(FYI, "Exclusive Oplock granted on inode %p\n",
&cinode->vfs_inode);
} else if (oplock == OPLOCK_READ) {
- cinode->clientCanCacheAll = false;
- cinode->clientCanCacheRead = true;
+ cinode->oplock = CIFS_CACHE_READ_FLG;
cifs_dbg(FYI, "Level II Oplock granted on inode %p\n",
&cinode->vfs_inode);
- } else {
- cinode->clientCanCacheAll = false;
- cinode->clientCanCacheRead = false;
- }
+ } else
+ cinode->oplock = 0;
}
bool
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 69d2c82..42ef03b 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -172,6 +172,9 @@
if (cifs_dfs_is_possible(cifs_sb) &&
(fattr->cf_cifsattrs & ATTR_REPARSE))
fattr->cf_flags |= CIFS_FATTR_NEED_REVAL;
+ } else if (fattr->cf_cifsattrs & ATTR_REPARSE) {
+ fattr->cf_mode = S_IFLNK;
+ fattr->cf_dtype = DT_LNK;
} else {
fattr->cf_mode = S_IFREG | cifs_sb->mnt_file_mode;
fattr->cf_dtype = DT_REG;
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 08dd37b..5f99b7f 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -226,7 +226,7 @@
*(bcc_ptr+1) = 0;
} else {
bytes_ret = cifs_strtoUTF16((__le16 *) bcc_ptr, ses->user_name,
- MAX_USERNAME_SIZE, nls_cp);
+ CIFS_MAX_USERNAME_LEN, nls_cp);
}
bcc_ptr += 2 * bytes_ret;
bcc_ptr += 2; /* account for null termination */
@@ -246,8 +246,8 @@
/* BB what about null user mounts - check that we do this BB */
/* copy user */
if (ses->user_name != NULL) {
- strncpy(bcc_ptr, ses->user_name, MAX_USERNAME_SIZE);
- bcc_ptr += strnlen(ses->user_name, MAX_USERNAME_SIZE);
+ strncpy(bcc_ptr, ses->user_name, CIFS_MAX_USERNAME_LEN);
+ bcc_ptr += strnlen(ses->user_name, CIFS_MAX_USERNAME_LEN);
}
/* else null user mount */
*bcc_ptr = 0;
@@ -428,7 +428,8 @@
NTLMSSP_NEGOTIATE_NTLM | NTLMSSP_NEGOTIATE_EXTENDED_SEC;
if (ses->server->sign) {
flags |= NTLMSSP_NEGOTIATE_SIGN;
- if (!ses->server->session_estab)
+ if (!ses->server->session_estab ||
+ ses->ntlmssp->sesskey_per_smbsess)
flags |= NTLMSSP_NEGOTIATE_KEY_XCH;
}
@@ -466,7 +467,8 @@
NTLMSSP_NEGOTIATE_NTLM | NTLMSSP_NEGOTIATE_EXTENDED_SEC;
if (ses->server->sign) {
flags |= NTLMSSP_NEGOTIATE_SIGN;
- if (!ses->server->session_estab)
+ if (!ses->server->session_estab ||
+ ses->ntlmssp->sesskey_per_smbsess)
flags |= NTLMSSP_NEGOTIATE_KEY_XCH;
}
@@ -501,7 +503,7 @@
} else {
int len;
len = cifs_strtoUTF16((__le16 *)tmp, ses->domainName,
- MAX_USERNAME_SIZE, nls_cp);
+ CIFS_MAX_USERNAME_LEN, nls_cp);
len *= 2; /* unicode is 2 bytes each */
sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - pbuffer);
sec_blob->DomainName.Length = cpu_to_le16(len);
@@ -517,7 +519,7 @@
} else {
int len;
len = cifs_strtoUTF16((__le16 *)tmp, ses->user_name,
- MAX_USERNAME_SIZE, nls_cp);
+ CIFS_MAX_USERNAME_LEN, nls_cp);
len *= 2; /* unicode is 2 bytes each */
sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - pbuffer);
sec_blob->UserName.Length = cpu_to_le16(len);
@@ -629,7 +631,8 @@
type = select_sectype(ses->server, ses->sectype);
cifs_dbg(FYI, "sess setup type %d\n", type);
if (type == Unspecified) {
- cifs_dbg(VFS, "Unable to select appropriate authentication method!");
+ cifs_dbg(VFS,
+ "Unable to select appropriate authentication method!");
return -EINVAL;
}
@@ -640,6 +643,8 @@
ses->ntlmssp = kmalloc(sizeof(struct ntlmssp_auth), GFP_KERNEL);
if (!ses->ntlmssp)
return -ENOMEM;
+ ses->ntlmssp->sesskey_per_smbsess = false;
+
}
ssetup_ntlmssp_authenticate:
@@ -815,8 +820,9 @@
ses->auth_key.response = kmemdup(msg->data, msg->sesskey_len,
GFP_KERNEL);
if (!ses->auth_key.response) {
- cifs_dbg(VFS, "Kerberos can't allocate (%u bytes) memory",
- msg->sesskey_len);
+ cifs_dbg(VFS,
+ "Kerberos can't allocate (%u bytes) memory",
+ msg->sesskey_len);
rc = -ENOMEM;
goto ssetup_exit;
}
@@ -1005,5 +1011,37 @@
if ((phase == NtLmChallenge) && (rc == 0))
goto ssetup_ntlmssp_authenticate;
+ if (!rc) {
+ mutex_lock(&ses->server->srv_mutex);
+ if (!ses->server->session_estab) {
+ if (ses->server->sign) {
+ ses->server->session_key.response =
+ kmemdup(ses->auth_key.response,
+ ses->auth_key.len, GFP_KERNEL);
+ if (!ses->server->session_key.response) {
+ rc = -ENOMEM;
+ mutex_unlock(&ses->server->srv_mutex);
+ goto keycp_exit;
+ }
+ ses->server->session_key.len =
+ ses->auth_key.len;
+ }
+ ses->server->sequence_number = 0x2;
+ ses->server->session_estab = true;
+ }
+ mutex_unlock(&ses->server->srv_mutex);
+
+ cifs_dbg(FYI, "CIFS session established successfully\n");
+ spin_lock(&GlobalMid_Lock);
+ ses->status = CifsGood;
+ ses->need_reconnect = false;
+ spin_unlock(&GlobalMid_Lock);
+ }
+
+keycp_exit:
+ kfree(ses->auth_key.response);
+ ses->auth_key.response = NULL;
+ kfree(ses->ntlmssp);
+
return rc;
}
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index 6094397..8233b17 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -700,7 +700,7 @@
struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode);
cfile->fid.netfid = fid->netfid;
cifs_set_oplock_level(cinode, oplock);
- cinode->can_cache_brlcks = cinode->clientCanCacheAll;
+ cinode->can_cache_brlcks = CIFS_CACHE_WRITE(cinode);
}
static void
@@ -837,7 +837,7 @@
{
return CIFSSMBLock(0, tcon, fid->netfid, current->tgid, 0, 0, 0, 0,
LOCKING_ANDX_OPLOCK_RELEASE, false,
- cinode->clientCanCacheRead ? 1 : 0);
+ CIFS_CACHE_READ(cinode) ? 1 : 0);
}
static int
@@ -881,6 +881,43 @@
(__u8)type, wait, 0);
}
+static int
+cifs_query_symlink(const unsigned int xid, struct cifs_tcon *tcon,
+ const char *full_path, char **target_path,
+ struct cifs_sb_info *cifs_sb)
+{
+ int rc;
+ int oplock = 0;
+ __u16 netfid;
+
+ cifs_dbg(FYI, "%s: path: %s\n", __func__, full_path);
+
+ rc = CIFSSMBOpen(xid, tcon, full_path, FILE_OPEN,
+ FILE_READ_ATTRIBUTES, OPEN_REPARSE_POINT, &netfid,
+ &oplock, NULL, cifs_sb->local_nls,
+ cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+ if (rc)
+ return rc;
+
+ rc = CIFSSMBQuerySymLink(xid, tcon, netfid, target_path,
+ cifs_sb->local_nls);
+ if (rc) {
+ CIFSSMBClose(xid, tcon, netfid);
+ return rc;
+ }
+
+ convert_delimiter(*target_path, '/');
+ CIFSSMBClose(xid, tcon, netfid);
+ cifs_dbg(FYI, "%s: target path: %s\n", __func__, *target_path);
+ return rc;
+}
+
+static bool
+cifs_is_read_op(__u32 oplock)
+{
+ return oplock == OPLOCK_READ;
+}
+
struct smb_version_operations smb1_operations = {
.send_cancel = send_nt_cancel,
.compare_fids = cifs_compare_fids,
@@ -927,6 +964,7 @@
.rename_pending_delete = cifs_rename_pending_delete,
.rename = CIFSSMBRename,
.create_hardlink = CIFSCreateHardLink,
+ .query_symlink = cifs_query_symlink,
.open = cifs_open_file,
.set_fid = cifs_set_fid,
.close = cifs_close_file,
@@ -945,6 +983,7 @@
.mand_unlock_range = cifs_unlock_range,
.push_mand_locks = cifs_push_mandatory_locks,
.query_mf_symlink = open_query_close_cifs_symlink,
+ .is_read_op = cifs_is_read_op,
};
struct smb_version_values smb1_values = {
@@ -960,7 +999,6 @@
.cap_unix = CAP_UNIX,
.cap_nt_find = CAP_NT_SMBS | CAP_NT_FIND,
.cap_large_files = CAP_LARGE_FILES,
- .oplock_read = OPLOCK_READ,
.signing_enabled = SECMODE_SIGN_ENABLED,
.signing_required = SECMODE_SIGN_REQUIRED,
};
diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c
index 04a81a4..3f17b45 100644
--- a/fs/cifs/smb2file.c
+++ b/fs/cifs/smb2file.c
@@ -34,29 +34,6 @@
#include "fscache.h"
#include "smb2proto.h"
-void
-smb2_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock)
-{
- oplock &= 0xFF;
- if (oplock == SMB2_OPLOCK_LEVEL_NOCHANGE)
- return;
- if (oplock == SMB2_OPLOCK_LEVEL_EXCLUSIVE ||
- oplock == SMB2_OPLOCK_LEVEL_BATCH) {
- cinode->clientCanCacheAll = true;
- cinode->clientCanCacheRead = true;
- cifs_dbg(FYI, "Exclusive Oplock granted on inode %p\n",
- &cinode->vfs_inode);
- } else if (oplock == SMB2_OPLOCK_LEVEL_II) {
- cinode->clientCanCacheAll = false;
- cinode->clientCanCacheRead = true;
- cifs_dbg(FYI, "Level II Oplock granted on inode %p\n",
- &cinode->vfs_inode);
- } else {
- cinode->clientCanCacheAll = false;
- cinode->clientCanCacheRead = false;
- }
-}
-
int
smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms,
__u32 *oplock, FILE_ALL_INFO *buf)
@@ -86,7 +63,7 @@
if (oparms->tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_LEASING)
memcpy(smb2_oplock + 1, fid->lease_key, SMB2_LEASE_KEY_SIZE);
- rc = SMB2_open(xid, oparms, smb2_path, smb2_oplock, smb2_data);
+ rc = SMB2_open(xid, oparms, smb2_path, smb2_oplock, smb2_data, NULL);
if (rc)
goto out;
diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c
index c6ec163..78ff88c 100644
--- a/fs/cifs/smb2inode.c
+++ b/fs/cifs/smb2inode.c
@@ -60,7 +60,7 @@
oparms.fid = &fid;
oparms.reconnect = false;
- rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL);
+ rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL);
if (rc) {
kfree(utf16_path);
return rc;
@@ -136,7 +136,8 @@
return -ENOMEM;
rc = smb2_open_op_close(xid, tcon, cifs_sb, full_path,
- FILE_READ_ATTRIBUTES, FILE_OPEN, 0, smb2_data,
+ FILE_READ_ATTRIBUTES, FILE_OPEN,
+ OPEN_REPARSE_POINT, smb2_data,
SMB2_OP_QUERY_INFO);
if (rc)
goto out;
@@ -191,8 +192,8 @@
struct cifs_sb_info *cifs_sb)
{
return smb2_open_op_close(xid, tcon, cifs_sb, name, DELETE, FILE_OPEN,
- CREATE_DELETE_ON_CLOSE, NULL,
- SMB2_OP_DELETE);
+ CREATE_DELETE_ON_CLOSE | OPEN_REPARSE_POINT,
+ NULL, SMB2_OP_DELETE);
}
static int
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index b0c4334..fb39662 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -171,6 +171,10 @@
if (4 + len != clc_len) {
cifs_dbg(FYI, "Calculated size %u length %u mismatch mid %llu\n",
clc_len, 4 + len, mid);
+ /* create failed on symlink */
+ if (command == SMB2_CREATE_HE &&
+ hdr->Status == STATUS_STOPPED_ON_SYMLINK)
+ return 0;
/* Windows 7 server returns 24 bytes more */
if (clc_len + 20 == len && command == SMB2_OPLOCK_BREAK_HE)
return 0;
@@ -376,23 +380,15 @@
__le32
smb2_get_lease_state(struct cifsInodeInfo *cinode)
{
- if (cinode->clientCanCacheAll)
- return SMB2_LEASE_WRITE_CACHING | SMB2_LEASE_READ_CACHING;
- else if (cinode->clientCanCacheRead)
- return SMB2_LEASE_READ_CACHING;
- return 0;
-}
+ __le32 lease = 0;
-__u8 smb2_map_lease_to_oplock(__le32 lease_state)
-{
- if (lease_state & SMB2_LEASE_WRITE_CACHING) {
- if (lease_state & SMB2_LEASE_HANDLE_CACHING)
- return SMB2_OPLOCK_LEVEL_BATCH;
- else
- return SMB2_OPLOCK_LEVEL_EXCLUSIVE;
- } else if (lease_state & SMB2_LEASE_READ_CACHING)
- return SMB2_OPLOCK_LEVEL_II;
- return 0;
+ if (CIFS_CACHE_WRITE(cinode))
+ lease |= SMB2_LEASE_WRITE_CACHING;
+ if (CIFS_CACHE_HANDLE(cinode))
+ lease |= SMB2_LEASE_HANDLE_CACHING;
+ if (CIFS_CACHE_READ(cinode))
+ lease |= SMB2_LEASE_READ_CACHING;
+ return lease;
}
struct smb2_lease_break_work {
@@ -417,19 +413,77 @@
}
static bool
-smb2_is_valid_lease_break(char *buffer, struct TCP_Server_Info *server)
+smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp,
+ struct smb2_lease_break_work *lw)
+{
+ bool found;
+ __u8 lease_state;
+ struct list_head *tmp;
+ struct cifsFileInfo *cfile;
+ struct TCP_Server_Info *server = tcon->ses->server;
+ struct cifs_pending_open *open;
+ struct cifsInodeInfo *cinode;
+ int ack_req = le32_to_cpu(rsp->Flags &
+ SMB2_NOTIFY_BREAK_LEASE_FLAG_ACK_REQUIRED);
+
+ lease_state = le32_to_cpu(rsp->NewLeaseState);
+
+ list_for_each(tmp, &tcon->openFileList) {
+ cfile = list_entry(tmp, struct cifsFileInfo, tlist);
+ cinode = CIFS_I(cfile->dentry->d_inode);
+
+ if (memcmp(cinode->lease_key, rsp->LeaseKey,
+ SMB2_LEASE_KEY_SIZE))
+ continue;
+
+ cifs_dbg(FYI, "found in the open list\n");
+ cifs_dbg(FYI, "lease key match, lease break 0x%d\n",
+ le32_to_cpu(rsp->NewLeaseState));
+
+ server->ops->set_oplock_level(cinode, lease_state, 0, NULL);
+
+ if (ack_req)
+ cfile->oplock_break_cancelled = false;
+ else
+ cfile->oplock_break_cancelled = true;
+
+ queue_work(cifsiod_wq, &cfile->oplock_break);
+ kfree(lw);
+ return true;
+ }
+
+ found = false;
+ list_for_each_entry(open, &tcon->pending_opens, olist) {
+ if (memcmp(open->lease_key, rsp->LeaseKey,
+ SMB2_LEASE_KEY_SIZE))
+ continue;
+
+ if (!found && ack_req) {
+ found = true;
+ memcpy(lw->lease_key, open->lease_key,
+ SMB2_LEASE_KEY_SIZE);
+ lw->tlink = cifs_get_tlink(open->tlink);
+ queue_work(cifsiod_wq, &lw->lease_break);
+ }
+
+ cifs_dbg(FYI, "found in the pending open list\n");
+ cifs_dbg(FYI, "lease key match, lease break 0x%d\n",
+ le32_to_cpu(rsp->NewLeaseState));
+
+ open->oplock = lease_state;
+ }
+ return found;
+}
+
+static bool
+smb2_is_valid_lease_break(char *buffer)
{
struct smb2_lease_break *rsp = (struct smb2_lease_break *)buffer;
struct list_head *tmp, *tmp1, *tmp2;
+ struct TCP_Server_Info *server;
struct cifs_ses *ses;
struct cifs_tcon *tcon;
- struct cifsInodeInfo *cinode;
- struct cifsFileInfo *cfile;
- struct cifs_pending_open *open;
struct smb2_lease_break_work *lw;
- bool found;
- int ack_req = le32_to_cpu(rsp->Flags &
- SMB2_NOTIFY_BREAK_LEASE_FLAG_ACK_REQUIRED);
lw = kmalloc(sizeof(struct smb2_lease_break_work), GFP_KERNEL);
if (!lw)
@@ -442,71 +496,26 @@
/* look up tcon based on tid & uid */
spin_lock(&cifs_tcp_ses_lock);
- list_for_each(tmp, &server->smb_ses_list) {
- ses = list_entry(tmp, struct cifs_ses, smb_ses_list);
+ list_for_each(tmp, &cifs_tcp_ses_list) {
+ server = list_entry(tmp, struct TCP_Server_Info, tcp_ses_list);
- spin_lock(&cifs_file_list_lock);
- list_for_each(tmp1, &ses->tcon_list) {
- tcon = list_entry(tmp1, struct cifs_tcon, tcon_list);
+ list_for_each(tmp1, &server->smb_ses_list) {
+ ses = list_entry(tmp1, struct cifs_ses, smb_ses_list);
- cifs_stats_inc(&tcon->stats.cifs_stats.num_oplock_brks);
- list_for_each(tmp2, &tcon->openFileList) {
- cfile = list_entry(tmp2, struct cifsFileInfo,
- tlist);
- cinode = CIFS_I(cfile->dentry->d_inode);
-
- if (memcmp(cinode->lease_key, rsp->LeaseKey,
- SMB2_LEASE_KEY_SIZE))
- continue;
-
- cifs_dbg(FYI, "found in the open list\n");
- cifs_dbg(FYI, "lease key match, lease break 0x%d\n",
- le32_to_cpu(rsp->NewLeaseState));
-
- smb2_set_oplock_level(cinode,
- smb2_map_lease_to_oplock(rsp->NewLeaseState));
-
- if (ack_req)
- cfile->oplock_break_cancelled = false;
- else
- cfile->oplock_break_cancelled = true;
-
- queue_work(cifsiod_wq, &cfile->oplock_break);
-
- spin_unlock(&cifs_file_list_lock);
- spin_unlock(&cifs_tcp_ses_lock);
- return true;
- }
-
- found = false;
- list_for_each_entry(open, &tcon->pending_opens, olist) {
- if (memcmp(open->lease_key, rsp->LeaseKey,
- SMB2_LEASE_KEY_SIZE))
- continue;
-
- if (!found && ack_req) {
- found = true;
- memcpy(lw->lease_key, open->lease_key,
- SMB2_LEASE_KEY_SIZE);
- lw->tlink = cifs_get_tlink(open->tlink);
- queue_work(cifsiod_wq,
- &lw->lease_break);
+ spin_lock(&cifs_file_list_lock);
+ list_for_each(tmp2, &ses->tcon_list) {
+ tcon = list_entry(tmp2, struct cifs_tcon,
+ tcon_list);
+ cifs_stats_inc(
+ &tcon->stats.cifs_stats.num_oplock_brks);
+ if (smb2_tcon_has_lease(tcon, rsp, lw)) {
+ spin_unlock(&cifs_file_list_lock);
+ spin_unlock(&cifs_tcp_ses_lock);
+ return true;
}
-
- cifs_dbg(FYI, "found in the pending open list\n");
- cifs_dbg(FYI, "lease key match, lease break 0x%d\n",
- le32_to_cpu(rsp->NewLeaseState));
-
- open->oplock =
- smb2_map_lease_to_oplock(rsp->NewLeaseState);
}
- if (found) {
- spin_unlock(&cifs_file_list_lock);
- spin_unlock(&cifs_tcp_ses_lock);
- return true;
- }
+ spin_unlock(&cifs_file_list_lock);
}
- spin_unlock(&cifs_file_list_lock);
}
spin_unlock(&cifs_tcp_ses_lock);
kfree(lw);
@@ -532,7 +541,7 @@
if (rsp->StructureSize !=
smb2_rsp_struct_sizes[SMB2_OPLOCK_BREAK_HE]) {
if (le16_to_cpu(rsp->StructureSize) == 44)
- return smb2_is_valid_lease_break(buffer, server);
+ return smb2_is_valid_lease_break(buffer);
else
return false;
}
@@ -560,14 +569,15 @@
cifs_dbg(FYI, "file id match, oplock break\n");
cinode = CIFS_I(cfile->dentry->d_inode);
- if (!cinode->clientCanCacheAll &&
+ if (!CIFS_CACHE_WRITE(cinode) &&
rsp->OplockLevel == SMB2_OPLOCK_LEVEL_NONE)
cfile->oplock_break_cancelled = true;
else
cfile->oplock_break_cancelled = false;
- smb2_set_oplock_level(cinode,
- rsp->OplockLevel ? SMB2_OPLOCK_LEVEL_II : 0);
+ server->ops->set_oplock_level(cinode,
+ rsp->OplockLevel ? SMB2_OPLOCK_LEVEL_II : 0,
+ 0, NULL);
queue_work(cifsiod_wq, &cfile->oplock_break);
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index f259e6c..861b332 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -24,6 +24,7 @@
#include "smb2proto.h"
#include "cifsproto.h"
#include "cifs_debug.h"
+#include "cifs_unicode.h"
#include "smb2status.h"
#include "smb2glob.h"
@@ -229,7 +230,7 @@
oparms.fid = &fid;
oparms.reconnect = false;
- rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL);
+ rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL);
if (rc) {
kfree(utf16_path);
return rc;
@@ -376,10 +377,13 @@
smb2_set_fid(struct cifsFileInfo *cfile, struct cifs_fid *fid, __u32 oplock)
{
struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode);
+ struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server;
+
cfile->fid.persistent_fid = fid->persistent_fid;
cfile->fid.volatile_fid = fid->volatile_fid;
- smb2_set_oplock_level(cinode, oplock);
- cinode->can_cache_brlcks = cinode->clientCanCacheAll;
+ server->ops->set_oplock_level(cinode, oplock, fid->epoch,
+ &fid->purge_cache);
+ cinode->can_cache_brlcks = CIFS_CACHE_WRITE(cinode);
}
static void
@@ -463,7 +467,7 @@
oparms.fid = fid;
oparms.reconnect = false;
- rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL);
+ rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL);
kfree(utf16_path);
if (rc) {
cifs_dbg(VFS, "open dir failed\n");
@@ -530,7 +534,7 @@
return SMB2_oplock_break(0, tcon, fid->persistent_fid,
fid->volatile_fid,
- cinode->clientCanCacheRead ? 1 : 0);
+ CIFS_CACHE_READ(cinode) ? 1 : 0);
}
static int
@@ -550,7 +554,7 @@
oparms.fid = &fid;
oparms.reconnect = false;
- rc = SMB2_open(xid, &oparms, &srch_path, &oplock, NULL);
+ rc = SMB2_open(xid, &oparms, &srch_path, &oplock, NULL, NULL);
if (rc)
return rc;
buf->f_type = SMB2_MAGIC_NUMBER;
@@ -596,6 +600,315 @@
get_random_bytes(fid->lease_key, SMB2_LEASE_KEY_SIZE);
}
+static int
+smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon,
+ const char *full_path, char **target_path,
+ struct cifs_sb_info *cifs_sb)
+{
+ int rc;
+ __le16 *utf16_path;
+ __u8 oplock = SMB2_OPLOCK_LEVEL_NONE;
+ struct cifs_open_parms oparms;
+ struct cifs_fid fid;
+ struct smb2_err_rsp *err_buf = NULL;
+ struct smb2_symlink_err_rsp *symlink;
+ unsigned int sub_len, sub_offset;
+
+ cifs_dbg(FYI, "%s: path: %s\n", __func__, full_path);
+
+ utf16_path = cifs_convert_path_to_utf16(full_path, cifs_sb);
+ if (!utf16_path)
+ return -ENOMEM;
+
+ oparms.tcon = tcon;
+ oparms.desired_access = FILE_READ_ATTRIBUTES;
+ oparms.disposition = FILE_OPEN;
+ oparms.create_options = 0;
+ oparms.fid = &fid;
+ oparms.reconnect = false;
+
+ rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, &err_buf);
+
+ if (!rc || !err_buf) {
+ kfree(utf16_path);
+ return -ENOENT;
+ }
+ /* open must fail on symlink - reset rc */
+ rc = 0;
+ symlink = (struct smb2_symlink_err_rsp *)err_buf->ErrorData;
+ sub_len = le16_to_cpu(symlink->SubstituteNameLength);
+ sub_offset = le16_to_cpu(symlink->SubstituteNameOffset);
+ *target_path = cifs_strndup_from_utf16(
+ (char *)symlink->PathBuffer + sub_offset,
+ sub_len, true, cifs_sb->local_nls);
+ if (!(*target_path)) {
+ kfree(utf16_path);
+ return -ENOMEM;
+ }
+ convert_delimiter(*target_path, '/');
+ cifs_dbg(FYI, "%s: target path: %s\n", __func__, *target_path);
+ kfree(utf16_path);
+ return rc;
+}
+
+static void
+smb2_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock,
+ unsigned int epoch, bool *purge_cache)
+{
+ oplock &= 0xFF;
+ if (oplock == SMB2_OPLOCK_LEVEL_NOCHANGE)
+ return;
+ if (oplock == SMB2_OPLOCK_LEVEL_BATCH) {
+ cinode->oplock = CIFS_CACHE_RHW_FLG;
+ cifs_dbg(FYI, "Batch Oplock granted on inode %p\n",
+ &cinode->vfs_inode);
+ } else if (oplock == SMB2_OPLOCK_LEVEL_EXCLUSIVE) {
+ cinode->oplock = CIFS_CACHE_RW_FLG;
+ cifs_dbg(FYI, "Exclusive Oplock granted on inode %p\n",
+ &cinode->vfs_inode);
+ } else if (oplock == SMB2_OPLOCK_LEVEL_II) {
+ cinode->oplock = CIFS_CACHE_READ_FLG;
+ cifs_dbg(FYI, "Level II Oplock granted on inode %p\n",
+ &cinode->vfs_inode);
+ } else
+ cinode->oplock = 0;
+}
+
+static void
+smb21_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock,
+ unsigned int epoch, bool *purge_cache)
+{
+ char message[5] = {0};
+
+ oplock &= 0xFF;
+ if (oplock == SMB2_OPLOCK_LEVEL_NOCHANGE)
+ return;
+
+ cinode->oplock = 0;
+ if (oplock & SMB2_LEASE_READ_CACHING_HE) {
+ cinode->oplock |= CIFS_CACHE_READ_FLG;
+ strcat(message, "R");
+ }
+ if (oplock & SMB2_LEASE_HANDLE_CACHING_HE) {
+ cinode->oplock |= CIFS_CACHE_HANDLE_FLG;
+ strcat(message, "H");
+ }
+ if (oplock & SMB2_LEASE_WRITE_CACHING_HE) {
+ cinode->oplock |= CIFS_CACHE_WRITE_FLG;
+ strcat(message, "W");
+ }
+ if (!cinode->oplock)
+ strcat(message, "None");
+ cifs_dbg(FYI, "%s Lease granted on inode %p\n", message,
+ &cinode->vfs_inode);
+}
+
+static void
+smb3_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock,
+ unsigned int epoch, bool *purge_cache)
+{
+ unsigned int old_oplock = cinode->oplock;
+
+ smb21_set_oplock_level(cinode, oplock, epoch, purge_cache);
+
+ if (purge_cache) {
+ *purge_cache = false;
+ if (old_oplock == CIFS_CACHE_READ_FLG) {
+ if (cinode->oplock == CIFS_CACHE_READ_FLG &&
+ (epoch - cinode->epoch > 0))
+ *purge_cache = true;
+ else if (cinode->oplock == CIFS_CACHE_RH_FLG &&
+ (epoch - cinode->epoch > 1))
+ *purge_cache = true;
+ else if (cinode->oplock == CIFS_CACHE_RHW_FLG &&
+ (epoch - cinode->epoch > 1))
+ *purge_cache = true;
+ else if (cinode->oplock == 0 &&
+ (epoch - cinode->epoch > 0))
+ *purge_cache = true;
+ } else if (old_oplock == CIFS_CACHE_RH_FLG) {
+ if (cinode->oplock == CIFS_CACHE_RH_FLG &&
+ (epoch - cinode->epoch > 0))
+ *purge_cache = true;
+ else if (cinode->oplock == CIFS_CACHE_RHW_FLG &&
+ (epoch - cinode->epoch > 1))
+ *purge_cache = true;
+ }
+ cinode->epoch = epoch;
+ }
+}
+
+static bool
+smb2_is_read_op(__u32 oplock)
+{
+ return oplock == SMB2_OPLOCK_LEVEL_II;
+}
+
+static bool
+smb21_is_read_op(__u32 oplock)
+{
+ return (oplock & SMB2_LEASE_READ_CACHING_HE) &&
+ !(oplock & SMB2_LEASE_WRITE_CACHING_HE);
+}
+
+static __le32
+map_oplock_to_lease(u8 oplock)
+{
+ if (oplock == SMB2_OPLOCK_LEVEL_EXCLUSIVE)
+ return SMB2_LEASE_WRITE_CACHING | SMB2_LEASE_READ_CACHING;
+ else if (oplock == SMB2_OPLOCK_LEVEL_II)
+ return SMB2_LEASE_READ_CACHING;
+ else if (oplock == SMB2_OPLOCK_LEVEL_BATCH)
+ return SMB2_LEASE_HANDLE_CACHING | SMB2_LEASE_READ_CACHING |
+ SMB2_LEASE_WRITE_CACHING;
+ return 0;
+}
+
+static char *
+smb2_create_lease_buf(u8 *lease_key, u8 oplock)
+{
+ struct create_lease *buf;
+
+ buf = kzalloc(sizeof(struct create_lease), GFP_KERNEL);
+ if (!buf)
+ return NULL;
+
+ buf->lcontext.LeaseKeyLow = cpu_to_le64(*((u64 *)lease_key));
+ buf->lcontext.LeaseKeyHigh = cpu_to_le64(*((u64 *)(lease_key + 8)));
+ buf->lcontext.LeaseState = map_oplock_to_lease(oplock);
+
+ buf->ccontext.DataOffset = cpu_to_le16(offsetof
+ (struct create_lease, lcontext));
+ buf->ccontext.DataLength = cpu_to_le32(sizeof(struct lease_context));
+ buf->ccontext.NameOffset = cpu_to_le16(offsetof
+ (struct create_lease, Name));
+ buf->ccontext.NameLength = cpu_to_le16(4);
+ buf->Name[0] = 'R';
+ buf->Name[1] = 'q';
+ buf->Name[2] = 'L';
+ buf->Name[3] = 's';
+ return (char *)buf;
+}
+
+static char *
+smb3_create_lease_buf(u8 *lease_key, u8 oplock)
+{
+ struct create_lease_v2 *buf;
+
+ buf = kzalloc(sizeof(struct create_lease_v2), GFP_KERNEL);
+ if (!buf)
+ return NULL;
+
+ buf->lcontext.LeaseKeyLow = cpu_to_le64(*((u64 *)lease_key));
+ buf->lcontext.LeaseKeyHigh = cpu_to_le64(*((u64 *)(lease_key + 8)));
+ buf->lcontext.LeaseState = map_oplock_to_lease(oplock);
+
+ buf->ccontext.DataOffset = cpu_to_le16(offsetof
+ (struct create_lease_v2, lcontext));
+ buf->ccontext.DataLength = cpu_to_le32(sizeof(struct lease_context_v2));
+ buf->ccontext.NameOffset = cpu_to_le16(offsetof
+ (struct create_lease_v2, Name));
+ buf->ccontext.NameLength = cpu_to_le16(4);
+ buf->Name[0] = 'R';
+ buf->Name[1] = 'q';
+ buf->Name[2] = 'L';
+ buf->Name[3] = 's';
+ return (char *)buf;
+}
+
+static __u8
+smb2_parse_lease_buf(void *buf, unsigned int *epoch)
+{
+ struct create_lease *lc = (struct create_lease *)buf;
+
+ *epoch = 0; /* not used */
+ if (lc->lcontext.LeaseFlags & SMB2_LEASE_FLAG_BREAK_IN_PROGRESS)
+ return SMB2_OPLOCK_LEVEL_NOCHANGE;
+ return le32_to_cpu(lc->lcontext.LeaseState);
+}
+
+static __u8
+smb3_parse_lease_buf(void *buf, unsigned int *epoch)
+{
+ struct create_lease_v2 *lc = (struct create_lease_v2 *)buf;
+
+ *epoch = le16_to_cpu(lc->lcontext.Epoch);
+ if (lc->lcontext.LeaseFlags & SMB2_LEASE_FLAG_BREAK_IN_PROGRESS)
+ return SMB2_OPLOCK_LEVEL_NOCHANGE;
+ return le32_to_cpu(lc->lcontext.LeaseState);
+}
+
+struct smb_version_operations smb20_operations = {
+ .compare_fids = smb2_compare_fids,
+ .setup_request = smb2_setup_request,
+ .setup_async_request = smb2_setup_async_request,
+ .check_receive = smb2_check_receive,
+ .add_credits = smb2_add_credits,
+ .set_credits = smb2_set_credits,
+ .get_credits_field = smb2_get_credits_field,
+ .get_credits = smb2_get_credits,
+ .get_next_mid = smb2_get_next_mid,
+ .read_data_offset = smb2_read_data_offset,
+ .read_data_length = smb2_read_data_length,
+ .map_error = map_smb2_to_linux_error,
+ .find_mid = smb2_find_mid,
+ .check_message = smb2_check_message,
+ .dump_detail = smb2_dump_detail,
+ .clear_stats = smb2_clear_stats,
+ .print_stats = smb2_print_stats,
+ .is_oplock_break = smb2_is_valid_oplock_break,
+ .need_neg = smb2_need_neg,
+ .negotiate = smb2_negotiate,
+ .negotiate_wsize = smb2_negotiate_wsize,
+ .negotiate_rsize = smb2_negotiate_rsize,
+ .sess_setup = SMB2_sess_setup,
+ .logoff = SMB2_logoff,
+ .tree_connect = SMB2_tcon,
+ .tree_disconnect = SMB2_tdis,
+ .is_path_accessible = smb2_is_path_accessible,
+ .can_echo = smb2_can_echo,
+ .echo = SMB2_echo,
+ .query_path_info = smb2_query_path_info,
+ .get_srv_inum = smb2_get_srv_inum,
+ .query_file_info = smb2_query_file_info,
+ .set_path_size = smb2_set_path_size,
+ .set_file_size = smb2_set_file_size,
+ .set_file_info = smb2_set_file_info,
+ .mkdir = smb2_mkdir,
+ .mkdir_setinfo = smb2_mkdir_setinfo,
+ .rmdir = smb2_rmdir,
+ .unlink = smb2_unlink,
+ .rename = smb2_rename_path,
+ .create_hardlink = smb2_create_hardlink,
+ .query_symlink = smb2_query_symlink,
+ .open = smb2_open_file,
+ .set_fid = smb2_set_fid,
+ .close = smb2_close_file,
+ .flush = smb2_flush_file,
+ .async_readv = smb2_async_readv,
+ .async_writev = smb2_async_writev,
+ .sync_read = smb2_sync_read,
+ .sync_write = smb2_sync_write,
+ .query_dir_first = smb2_query_dir_first,
+ .query_dir_next = smb2_query_dir_next,
+ .close_dir = smb2_close_dir,
+ .calc_smb_size = smb2_calc_size,
+ .is_status_pending = smb2_is_status_pending,
+ .oplock_response = smb2_oplock_response,
+ .queryfs = smb2_queryfs,
+ .mand_lock = smb2_mand_lock,
+ .mand_unlock_range = smb2_unlock_range,
+ .push_mand_locks = smb2_push_mandatory_locks,
+ .get_lease_key = smb2_get_lease_key,
+ .set_lease_key = smb2_set_lease_key,
+ .new_lease_key = smb2_new_lease_key,
+ .calc_signature = smb2_calc_signature,
+ .is_read_op = smb2_is_read_op,
+ .set_oplock_level = smb2_set_oplock_level,
+ .create_lease_buf = smb2_create_lease_buf,
+ .parse_lease_buf = smb2_parse_lease_buf,
+};
+
struct smb_version_operations smb21_operations = {
.compare_fids = smb2_compare_fids,
.setup_request = smb2_setup_request,
@@ -638,6 +951,7 @@
.unlink = smb2_unlink,
.rename = smb2_rename_path,
.create_hardlink = smb2_create_hardlink,
+ .query_symlink = smb2_query_symlink,
.open = smb2_open_file,
.set_fid = smb2_set_fid,
.close = smb2_close_file,
@@ -660,9 +974,12 @@
.set_lease_key = smb2_set_lease_key,
.new_lease_key = smb2_new_lease_key,
.calc_signature = smb2_calc_signature,
+ .is_read_op = smb21_is_read_op,
+ .set_oplock_level = smb21_set_oplock_level,
+ .create_lease_buf = smb2_create_lease_buf,
+ .parse_lease_buf = smb2_parse_lease_buf,
};
-
struct smb_version_operations smb30_operations = {
.compare_fids = smb2_compare_fids,
.setup_request = smb2_setup_request,
@@ -706,6 +1023,7 @@
.unlink = smb2_unlink,
.rename = smb2_rename_path,
.create_hardlink = smb2_create_hardlink,
+ .query_symlink = smb2_query_symlink,
.open = smb2_open_file,
.set_fid = smb2_set_fid,
.close = smb2_close_file,
@@ -729,6 +1047,10 @@
.new_lease_key = smb2_new_lease_key,
.generate_signingkey = generate_smb3signingkey,
.calc_signature = smb3_calc_signature,
+ .is_read_op = smb21_is_read_op,
+ .set_oplock_level = smb3_set_oplock_level,
+ .create_lease_buf = smb3_create_lease_buf,
+ .parse_lease_buf = smb3_parse_lease_buf,
};
struct smb_version_values smb20_values = {
@@ -746,9 +1068,9 @@
.cap_unix = 0,
.cap_nt_find = SMB2_NT_FIND,
.cap_large_files = SMB2_LARGE_FILES,
- .oplock_read = SMB2_OPLOCK_LEVEL_II,
.signing_enabled = SMB2_NEGOTIATE_SIGNING_ENABLED | SMB2_NEGOTIATE_SIGNING_REQUIRED,
.signing_required = SMB2_NEGOTIATE_SIGNING_REQUIRED,
+ .create_lease_size = sizeof(struct create_lease),
};
struct smb_version_values smb21_values = {
@@ -766,9 +1088,9 @@
.cap_unix = 0,
.cap_nt_find = SMB2_NT_FIND,
.cap_large_files = SMB2_LARGE_FILES,
- .oplock_read = SMB2_OPLOCK_LEVEL_II,
.signing_enabled = SMB2_NEGOTIATE_SIGNING_ENABLED | SMB2_NEGOTIATE_SIGNING_REQUIRED,
.signing_required = SMB2_NEGOTIATE_SIGNING_REQUIRED,
+ .create_lease_size = sizeof(struct create_lease),
};
struct smb_version_values smb30_values = {
@@ -786,9 +1108,9 @@
.cap_unix = 0,
.cap_nt_find = SMB2_NT_FIND,
.cap_large_files = SMB2_LARGE_FILES,
- .oplock_read = SMB2_OPLOCK_LEVEL_II,
.signing_enabled = SMB2_NEGOTIATE_SIGNING_ENABLED | SMB2_NEGOTIATE_SIGNING_REQUIRED,
.signing_required = SMB2_NEGOTIATE_SIGNING_REQUIRED,
+ .create_lease_size = sizeof(struct create_lease_v2),
};
struct smb_version_values smb302_values = {
@@ -806,7 +1128,7 @@
.cap_unix = 0,
.cap_nt_find = SMB2_NT_FIND,
.cap_large_files = SMB2_LARGE_FILES,
- .oplock_read = SMB2_OPLOCK_LEVEL_II,
.signing_enabled = SMB2_NEGOTIATE_SIGNING_ENABLED | SMB2_NEGOTIATE_SIGNING_REQUIRED,
.signing_required = SMB2_NEGOTIATE_SIGNING_REQUIRED,
+ .create_lease_size = sizeof(struct create_lease_v2),
};
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index abc9c28..eba0efd 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -478,12 +478,20 @@
}
/*
+ * If we are here due to reconnect, free per-smb session key
+ * in case signing was required.
+ */
+ kfree(ses->auth_key.response);
+ ses->auth_key.response = NULL;
+
+ /*
* If memory allocation is successful, caller of this function
* frees it.
*/
ses->ntlmssp = kmalloc(sizeof(struct ntlmssp_auth), GFP_KERNEL);
if (!ses->ntlmssp)
return -ENOMEM;
+ ses->ntlmssp->sesskey_per_smbsess = true;
/* FIXME: allow for other auth types besides NTLMSSP (e.g. krb5) */
ses->sectype = RawNTLMSSP;
@@ -628,6 +636,40 @@
/* if ntlmssp, and negotiate succeeded, proceed to authenticate phase */
if ((phase == NtLmChallenge) && (rc == 0))
goto ssetup_ntlmssp_authenticate;
+
+ if (!rc) {
+ mutex_lock(&server->srv_mutex);
+ if (server->sign && server->ops->generate_signingkey) {
+ rc = server->ops->generate_signingkey(ses);
+ kfree(ses->auth_key.response);
+ ses->auth_key.response = NULL;
+ if (rc) {
+ cifs_dbg(FYI,
+ "SMB3 session key generation failed\n");
+ mutex_unlock(&server->srv_mutex);
+ goto keygen_exit;
+ }
+ }
+ if (!server->session_estab) {
+ server->sequence_number = 0x2;
+ server->session_estab = true;
+ }
+ mutex_unlock(&server->srv_mutex);
+
+ cifs_dbg(FYI, "SMB2/3 session established successfully\n");
+ spin_lock(&GlobalMid_Lock);
+ ses->status = CifsGood;
+ ses->need_reconnect = false;
+ spin_unlock(&GlobalMid_Lock);
+ }
+
+keygen_exit:
+ if (!server->sign) {
+ kfree(ses->auth_key.response);
+ ses->auth_key.response = NULL;
+ }
+ kfree(ses->ntlmssp);
+
return rc;
}
@@ -813,39 +855,6 @@
return rc;
}
-static struct create_lease *
-create_lease_buf(u8 *lease_key, u8 oplock)
-{
- struct create_lease *buf;
-
- buf = kzalloc(sizeof(struct create_lease), GFP_KERNEL);
- if (!buf)
- return NULL;
-
- buf->lcontext.LeaseKeyLow = cpu_to_le64(*((u64 *)lease_key));
- buf->lcontext.LeaseKeyHigh = cpu_to_le64(*((u64 *)(lease_key + 8)));
- if (oplock == SMB2_OPLOCK_LEVEL_EXCLUSIVE)
- buf->lcontext.LeaseState = SMB2_LEASE_WRITE_CACHING |
- SMB2_LEASE_READ_CACHING;
- else if (oplock == SMB2_OPLOCK_LEVEL_II)
- buf->lcontext.LeaseState = SMB2_LEASE_READ_CACHING;
- else if (oplock == SMB2_OPLOCK_LEVEL_BATCH)
- buf->lcontext.LeaseState = SMB2_LEASE_HANDLE_CACHING |
- SMB2_LEASE_READ_CACHING |
- SMB2_LEASE_WRITE_CACHING;
-
- buf->ccontext.DataOffset = cpu_to_le16(offsetof
- (struct create_lease, lcontext));
- buf->ccontext.DataLength = cpu_to_le32(sizeof(struct lease_context));
- buf->ccontext.NameOffset = cpu_to_le16(offsetof
- (struct create_lease, Name));
- buf->ccontext.NameLength = cpu_to_le16(4);
- buf->Name[0] = 'R';
- buf->Name[1] = 'q';
- buf->Name[2] = 'L';
- buf->Name[3] = 's';
- return buf;
-}
static struct create_durable *
create_durable_buf(void)
@@ -894,55 +903,49 @@
}
static __u8
-parse_lease_state(struct smb2_create_rsp *rsp)
+parse_lease_state(struct TCP_Server_Info *server, struct smb2_create_rsp *rsp,
+ unsigned int *epoch)
{
char *data_offset;
- struct create_lease *lc;
- bool found = false;
+ struct create_context *cc;
unsigned int next = 0;
char *name;
data_offset = (char *)rsp + 4 + le32_to_cpu(rsp->CreateContextsOffset);
- lc = (struct create_lease *)data_offset;
+ cc = (struct create_context *)data_offset;
do {
- lc = (struct create_lease *)((char *)lc + next);
- name = le16_to_cpu(lc->ccontext.NameOffset) + (char *)lc;
- if (le16_to_cpu(lc->ccontext.NameLength) != 4 ||
+ cc = (struct create_context *)((char *)cc + next);
+ name = le16_to_cpu(cc->NameOffset) + (char *)cc;
+ if (le16_to_cpu(cc->NameLength) != 4 ||
strncmp(name, "RqLs", 4)) {
- next = le32_to_cpu(lc->ccontext.Next);
+ next = le32_to_cpu(cc->Next);
continue;
}
- if (lc->lcontext.LeaseFlags & SMB2_LEASE_FLAG_BREAK_IN_PROGRESS)
- return SMB2_OPLOCK_LEVEL_NOCHANGE;
- found = true;
- break;
+ return server->ops->parse_lease_buf(cc, epoch);
} while (next != 0);
- if (!found)
- return 0;
-
- return smb2_map_lease_to_oplock(lc->lcontext.LeaseState);
+ return 0;
}
static int
-add_lease_context(struct kvec *iov, unsigned int *num_iovec, __u8 *oplock)
+add_lease_context(struct TCP_Server_Info *server, struct kvec *iov,
+ unsigned int *num_iovec, __u8 *oplock)
{
struct smb2_create_req *req = iov[0].iov_base;
unsigned int num = *num_iovec;
- iov[num].iov_base = create_lease_buf(oplock+1, *oplock);
+ iov[num].iov_base = server->ops->create_lease_buf(oplock+1, *oplock);
if (iov[num].iov_base == NULL)
return -ENOMEM;
- iov[num].iov_len = sizeof(struct create_lease);
+ iov[num].iov_len = server->vals->create_lease_size;
req->RequestedOplockLevel = SMB2_OPLOCK_LEVEL_LEASE;
if (!req->CreateContextsOffset)
req->CreateContextsOffset = cpu_to_le32(
sizeof(struct smb2_create_req) - 4 +
iov[num - 1].iov_len);
- req->CreateContextsLength = cpu_to_le32(
- le32_to_cpu(req->CreateContextsLength) +
- sizeof(struct create_lease));
- inc_rfc1001_len(&req->hdr, sizeof(struct create_lease));
+ le32_add_cpu(&req->CreateContextsLength,
+ server->vals->create_lease_size);
+ inc_rfc1001_len(&req->hdr, server->vals->create_lease_size);
*num_iovec = num + 1;
return 0;
}
@@ -967,9 +970,7 @@
req->CreateContextsOffset =
cpu_to_le32(sizeof(struct smb2_create_req) - 4 +
iov[1].iov_len);
- req->CreateContextsLength =
- cpu_to_le32(le32_to_cpu(req->CreateContextsLength) +
- sizeof(struct create_durable));
+ le32_add_cpu(&req->CreateContextsLength, sizeof(struct create_durable));
inc_rfc1001_len(&req->hdr, sizeof(struct create_durable));
*num_iovec = num + 1;
return 0;
@@ -977,7 +978,8 @@
int
SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
- __u8 *oplock, struct smb2_file_all_info *buf)
+ __u8 *oplock, struct smb2_file_all_info *buf,
+ struct smb2_err_rsp **err_buf)
{
struct smb2_create_req *req;
struct smb2_create_rsp *rsp;
@@ -1048,11 +1050,11 @@
if (!server->oplocks)
*oplock = SMB2_OPLOCK_LEVEL_NONE;
- if (!(tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_LEASING) ||
+ if (!(server->capabilities & SMB2_GLOBAL_CAP_LEASING) ||
*oplock == SMB2_OPLOCK_LEVEL_NONE)
req->RequestedOplockLevel = *oplock;
else {
- rc = add_lease_context(iov, &num_iovecs, oplock);
+ rc = add_lease_context(server, iov, &num_iovecs, oplock);
if (rc) {
cifs_small_buf_release(req);
kfree(copy_path);
@@ -1062,11 +1064,11 @@
if (*oplock == SMB2_OPLOCK_LEVEL_BATCH) {
/* need to set Next field of lease context if we request it */
- if (tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_LEASING) {
+ if (server->capabilities & SMB2_GLOBAL_CAP_LEASING) {
struct create_context *ccontext =
(struct create_context *)iov[num_iovecs-1].iov_base;
ccontext->Next =
- cpu_to_le32(sizeof(struct create_lease));
+ cpu_to_le32(server->vals->create_lease_size);
}
rc = add_durable_context(iov, &num_iovecs, oparms);
if (rc) {
@@ -1082,6 +1084,9 @@
if (rc != 0) {
cifs_stats_fail_inc(tcon, SMB2_CREATE_HE);
+ if (err_buf)
+ *err_buf = kmemdup(rsp, get_rfc1002_length(rsp) + 4,
+ GFP_KERNEL);
goto creat_exit;
}
@@ -1098,7 +1103,7 @@
}
if (rsp->OplockLevel == SMB2_OPLOCK_LEVEL_LEASE)
- *oplock = parse_lease_state(rsp);
+ *oplock = parse_lease_state(server, rsp, &oparms->fid->epoch);
else
*oplock = rsp->OplockLevel;
creat_exit:
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index 36b0d37..b83d011 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -150,6 +150,20 @@
__u8 ErrorData[1]; /* variable length */
} __packed;
+struct smb2_symlink_err_rsp {
+ __le32 SymLinkLength;
+ __le32 SymLinkErrorTag;
+ __le32 ReparseTag;
+ __le16 ReparseDataLength;
+ __le16 UnparsedPathLength;
+ __le16 SubstituteNameOffset;
+ __le16 SubstituteNameLength;
+ __le16 PrintNameOffset;
+ __le16 PrintNameLength;
+ __le32 Flags;
+ __u8 PathBuffer[0];
+} __packed;
+
#define SMB2_CLIENT_GUID_SIZE 16
extern __u8 cifs_client_guid[SMB2_CLIENT_GUID_SIZE];
@@ -462,6 +476,10 @@
__u8 Buffer[0];
} __packed;
+#define SMB2_LEASE_READ_CACHING_HE 0x01
+#define SMB2_LEASE_HANDLE_CACHING_HE 0x02
+#define SMB2_LEASE_WRITE_CACHING_HE 0x04
+
#define SMB2_LEASE_NONE __constant_cpu_to_le32(0x00)
#define SMB2_LEASE_READ_CACHING __constant_cpu_to_le32(0x01)
#define SMB2_LEASE_HANDLE_CACHING __constant_cpu_to_le32(0x02)
@@ -479,12 +497,31 @@
__le64 LeaseDuration;
} __packed;
+struct lease_context_v2 {
+ __le64 LeaseKeyLow;
+ __le64 LeaseKeyHigh;
+ __le32 LeaseState;
+ __le32 LeaseFlags;
+ __le64 LeaseDuration;
+ __le64 ParentLeaseKeyLow;
+ __le64 ParentLeaseKeyHigh;
+ __le16 Epoch;
+ __le16 Reserved;
+} __packed;
+
struct create_lease {
struct create_context ccontext;
__u8 Name[8];
struct lease_context lcontext;
} __packed;
+struct create_lease_v2 {
+ struct create_context ccontext;
+ __u8 Name[8];
+ struct lease_context_v2 lcontext;
+ __u8 Pad[4];
+} __packed;
+
struct create_durable {
struct create_context ccontext;
__u8 Name[8];
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index 1a5ecbe..e3fb480 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -53,7 +53,6 @@
struct TCP_Server_Info *server);
extern void smb2_echo_request(struct work_struct *work);
extern __le32 smb2_get_lease_state(struct cifsInodeInfo *cinode);
-extern __u8 smb2_map_lease_to_oplock(__le32 lease_state);
extern bool smb2_is_valid_oplock_break(char *buffer,
struct TCP_Server_Info *srv);
@@ -87,7 +86,6 @@
extern int smb2_open_file(const unsigned int xid,
struct cifs_open_parms *oparms,
__u32 *oplock, FILE_ALL_INFO *buf);
-extern void smb2_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock);
extern int smb2_unlock_range(struct cifsFileInfo *cfile,
struct file_lock *flock, const unsigned int xid);
extern int smb2_push_mandatory_locks(struct cifsFileInfo *cfile);
@@ -106,7 +104,8 @@
extern int SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon);
extern int SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms,
__le16 *path, __u8 *oplock,
- struct smb2_file_all_info *buf);
+ struct smb2_file_all_info *buf,
+ struct smb2_err_rsp **err_buf);
extern int SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon,
u64 persistent_fid, u64 volatile_fid, u32 opcode,
bool is_fsctl, char *in_data, u32 indatalen,
diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c
index 4f2300d..340abca 100644
--- a/fs/cifs/smb2transport.c
+++ b/fs/cifs/smb2transport.c
@@ -114,6 +114,23 @@
return 0;
}
+static struct cifs_ses *
+smb2_find_smb_ses(struct smb2_hdr *smb2hdr, struct TCP_Server_Info *server)
+{
+ struct cifs_ses *ses;
+
+ spin_lock(&cifs_tcp_ses_lock);
+ list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
+ if (ses->Suid != smb2hdr->SessionId)
+ continue;
+ spin_unlock(&cifs_tcp_ses_lock);
+ return ses;
+ }
+ spin_unlock(&cifs_tcp_ses_lock);
+
+ return NULL;
+}
+
int
smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
@@ -124,6 +141,13 @@
struct kvec *iov = rqst->rq_iov;
int n_vec = rqst->rq_nvec;
struct smb2_hdr *smb2_pdu = (struct smb2_hdr *)iov[0].iov_base;
+ struct cifs_ses *ses;
+
+ ses = smb2_find_smb_ses(smb2_pdu, server);
+ if (!ses) {
+ cifs_dbg(VFS, "%s: Could not find session\n", __func__);
+ return 0;
+ }
memset(smb2_signature, 0x0, SMB2_HMACSHA256_SIZE);
memset(smb2_pdu->Signature, 0x0, SMB2_SIGNATURE_SIZE);
@@ -135,7 +159,7 @@
}
rc = crypto_shash_setkey(server->secmech.hmacsha256,
- server->session_key.response, SMB2_NTLMV2_SESSKEY_SIZE);
+ ses->auth_key.response, SMB2_NTLMV2_SESSKEY_SIZE);
if (rc) {
cifs_dbg(VFS, "%s: Could not update with response\n", __func__);
return rc;
@@ -198,8 +222,8 @@
return rc;
}
-void
-generate_smb3signingkey(struct TCP_Server_Info *server)
+int
+generate_smb3signingkey(struct cifs_ses *ses)
{
unsigned char zero = 0x0;
__u8 i[4] = {0, 0, 0, 1};
@@ -209,90 +233,99 @@
unsigned char *hashptr = prfhash;
memset(prfhash, 0x0, SMB2_HMACSHA256_SIZE);
- memset(server->smb3signingkey, 0x0, SMB3_SIGNKEY_SIZE);
+ memset(ses->smb3signingkey, 0x0, SMB3_SIGNKEY_SIZE);
- rc = smb3_crypto_shash_allocate(server);
+ rc = smb3_crypto_shash_allocate(ses->server);
if (rc) {
cifs_dbg(VFS, "%s: crypto alloc failed\n", __func__);
goto smb3signkey_ret;
}
- rc = crypto_shash_setkey(server->secmech.hmacsha256,
- server->session_key.response, SMB2_NTLMV2_SESSKEY_SIZE);
+ rc = crypto_shash_setkey(ses->server->secmech.hmacsha256,
+ ses->auth_key.response, SMB2_NTLMV2_SESSKEY_SIZE);
if (rc) {
cifs_dbg(VFS, "%s: Could not set with session key\n", __func__);
goto smb3signkey_ret;
}
- rc = crypto_shash_init(&server->secmech.sdeschmacsha256->shash);
+ rc = crypto_shash_init(&ses->server->secmech.sdeschmacsha256->shash);
if (rc) {
cifs_dbg(VFS, "%s: Could not init sign hmac\n", __func__);
goto smb3signkey_ret;
}
- rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash,
+ rc = crypto_shash_update(&ses->server->secmech.sdeschmacsha256->shash,
i, 4);
if (rc) {
cifs_dbg(VFS, "%s: Could not update with n\n", __func__);
goto smb3signkey_ret;
}
- rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash,
+ rc = crypto_shash_update(&ses->server->secmech.sdeschmacsha256->shash,
"SMB2AESCMAC", 12);
if (rc) {
cifs_dbg(VFS, "%s: Could not update with label\n", __func__);
goto smb3signkey_ret;
}
- rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash,
+ rc = crypto_shash_update(&ses->server->secmech.sdeschmacsha256->shash,
&zero, 1);
if (rc) {
cifs_dbg(VFS, "%s: Could not update with zero\n", __func__);
goto smb3signkey_ret;
}
- rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash,
+ rc = crypto_shash_update(&ses->server->secmech.sdeschmacsha256->shash,
"SmbSign", 8);
if (rc) {
cifs_dbg(VFS, "%s: Could not update with context\n", __func__);
goto smb3signkey_ret;
}
- rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash,
+ rc = crypto_shash_update(&ses->server->secmech.sdeschmacsha256->shash,
L, 4);
if (rc) {
cifs_dbg(VFS, "%s: Could not update with L\n", __func__);
goto smb3signkey_ret;
}
- rc = crypto_shash_final(&server->secmech.sdeschmacsha256->shash,
+ rc = crypto_shash_final(&ses->server->secmech.sdeschmacsha256->shash,
hashptr);
if (rc) {
cifs_dbg(VFS, "%s: Could not generate sha256 hash\n", __func__);
goto smb3signkey_ret;
}
- memcpy(server->smb3signingkey, hashptr, SMB3_SIGNKEY_SIZE);
+ memcpy(ses->smb3signingkey, hashptr, SMB3_SIGNKEY_SIZE);
smb3signkey_ret:
- return;
+ return rc;
}
int
smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
{
- int i, rc;
+ int i;
+ int rc = 0;
unsigned char smb3_signature[SMB2_CMACAES_SIZE];
unsigned char *sigptr = smb3_signature;
struct kvec *iov = rqst->rq_iov;
int n_vec = rqst->rq_nvec;
struct smb2_hdr *smb2_pdu = (struct smb2_hdr *)iov[0].iov_base;
+ struct cifs_ses *ses;
+
+ ses = smb2_find_smb_ses(smb2_pdu, server);
+ if (!ses) {
+ cifs_dbg(VFS, "%s: Could not find session\n", __func__);
+ return 0;
+ }
memset(smb3_signature, 0x0, SMB2_CMACAES_SIZE);
memset(smb2_pdu->Signature, 0x0, SMB2_SIGNATURE_SIZE);
rc = crypto_shash_setkey(server->secmech.cmacaes,
- server->smb3signingkey, SMB2_CMACAES_SIZE);
+ ses->smb3signingkey, SMB2_CMACAES_SIZE);
+
if (rc) {
cifs_dbg(VFS, "%s: Could not set key for cmac aes\n", __func__);
return rc;
@@ -389,6 +422,7 @@
struct smb2_hdr *smb2_pdu = (struct smb2_hdr *)rqst->rq_iov[0].iov_base;
if ((smb2_pdu->Command == SMB2_NEGOTIATE) ||
+ (smb2_pdu->Command == SMB2_SESSION_SETUP) ||
(smb2_pdu->Command == SMB2_OPLOCK_BREAK) ||
(!server->session_estab))
return 0;
diff --git a/fs/cifs/winucase.c b/fs/cifs/winucase.c
new file mode 100644
index 0000000..1506d4f
--- /dev/null
+++ b/fs/cifs/winucase.c
@@ -0,0 +1,663 @@
+/*
+ * fs/cifs/winucase.c
+ *
+ * Copyright (c) Jeffrey Layton <jlayton@redhat.com>, 2013
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
+ * the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ *
+ * The const tables in this file were converted from the following info
+ * provided by Microsoft:
+ *
+ * 3.1.5.3 Mapping UTF-16 Strings to Upper Case:
+ *
+ * http://msdn.microsoft.com/en-us/library/hh877830.aspx
+ * http://www.microsoft.com/en-us/download/details.aspx?displaylang=en&id=10921
+ *
+ * In particular, the table in "Windows 8 Upper Case Mapping Table.txt" was
+ * post-processed using the winucase_convert.pl script.
+ */
+
+#include <linux/nls.h>
+
+wchar_t cifs_toupper(wchar_t in); /* quiet sparse */
+
+static const wchar_t t2_00[256] = {
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047,
+ 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f,
+ 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057,
+ 0x0058, 0x0059, 0x005a, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x00c0, 0x00c1, 0x00c2, 0x00c3, 0x00c4, 0x00c5, 0x00c6, 0x00c7,
+ 0x00c8, 0x00c9, 0x00ca, 0x00cb, 0x00cc, 0x00cd, 0x00ce, 0x00cf,
+ 0x00d0, 0x00d1, 0x00d2, 0x00d3, 0x00d4, 0x00d5, 0x00d6, 0x0000,
+ 0x00d8, 0x00d9, 0x00da, 0x00db, 0x00dc, 0x00dd, 0x00de, 0x0178,
+};
+
+static const wchar_t t2_01[256] = {
+ 0x0000, 0x0100, 0x0000, 0x0102, 0x0000, 0x0104, 0x0000, 0x0106,
+ 0x0000, 0x0108, 0x0000, 0x010a, 0x0000, 0x010c, 0x0000, 0x010e,
+ 0x0000, 0x0110, 0x0000, 0x0112, 0x0000, 0x0114, 0x0000, 0x0116,
+ 0x0000, 0x0118, 0x0000, 0x011a, 0x0000, 0x011c, 0x0000, 0x011e,
+ 0x0000, 0x0120, 0x0000, 0x0122, 0x0000, 0x0124, 0x0000, 0x0126,
+ 0x0000, 0x0128, 0x0000, 0x012a, 0x0000, 0x012c, 0x0000, 0x012e,
+ 0x0000, 0x0000, 0x0000, 0x0132, 0x0000, 0x0134, 0x0000, 0x0136,
+ 0x0000, 0x0000, 0x0139, 0x0000, 0x013b, 0x0000, 0x013d, 0x0000,
+ 0x013f, 0x0000, 0x0141, 0x0000, 0x0143, 0x0000, 0x0145, 0x0000,
+ 0x0147, 0x0000, 0x0000, 0x014a, 0x0000, 0x014c, 0x0000, 0x014e,
+ 0x0000, 0x0150, 0x0000, 0x0152, 0x0000, 0x0154, 0x0000, 0x0156,
+ 0x0000, 0x0158, 0x0000, 0x015a, 0x0000, 0x015c, 0x0000, 0x015e,
+ 0x0000, 0x0160, 0x0000, 0x0162, 0x0000, 0x0164, 0x0000, 0x0166,
+ 0x0000, 0x0168, 0x0000, 0x016a, 0x0000, 0x016c, 0x0000, 0x016e,
+ 0x0000, 0x0170, 0x0000, 0x0172, 0x0000, 0x0174, 0x0000, 0x0176,
+ 0x0000, 0x0000, 0x0179, 0x0000, 0x017b, 0x0000, 0x017d, 0x0000,
+ 0x0243, 0x0000, 0x0000, 0x0182, 0x0000, 0x0184, 0x0000, 0x0000,
+ 0x0187, 0x0000, 0x0000, 0x0000, 0x018b, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0191, 0x0000, 0x0000, 0x01f6, 0x0000, 0x0000,
+ 0x0000, 0x0198, 0x023d, 0x0000, 0x0000, 0x0000, 0x0220, 0x0000,
+ 0x0000, 0x01a0, 0x0000, 0x01a2, 0x0000, 0x01a4, 0x0000, 0x0000,
+ 0x01a7, 0x0000, 0x0000, 0x0000, 0x0000, 0x01ac, 0x0000, 0x0000,
+ 0x01af, 0x0000, 0x0000, 0x0000, 0x01b3, 0x0000, 0x01b5, 0x0000,
+ 0x0000, 0x01b8, 0x0000, 0x0000, 0x0000, 0x01bc, 0x0000, 0x01f7,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x01c4, 0x0000,
+ 0x0000, 0x01c7, 0x0000, 0x0000, 0x01ca, 0x0000, 0x01cd, 0x0000,
+ 0x01cf, 0x0000, 0x01d1, 0x0000, 0x01d3, 0x0000, 0x01d5, 0x0000,
+ 0x01d7, 0x0000, 0x01d9, 0x0000, 0x01db, 0x018e, 0x0000, 0x01de,
+ 0x0000, 0x01e0, 0x0000, 0x01e2, 0x0000, 0x01e4, 0x0000, 0x01e6,
+ 0x0000, 0x01e8, 0x0000, 0x01ea, 0x0000, 0x01ec, 0x0000, 0x01ee,
+ 0x0000, 0x0000, 0x0000, 0x01f1, 0x0000, 0x01f4, 0x0000, 0x0000,
+ 0x0000, 0x01f8, 0x0000, 0x01fa, 0x0000, 0x01fc, 0x0000, 0x01fe,
+};
+
+static const wchar_t t2_02[256] = {
+ 0x0000, 0x0200, 0x0000, 0x0202, 0x0000, 0x0204, 0x0000, 0x0206,
+ 0x0000, 0x0208, 0x0000, 0x020a, 0x0000, 0x020c, 0x0000, 0x020e,
+ 0x0000, 0x0210, 0x0000, 0x0212, 0x0000, 0x0214, 0x0000, 0x0216,
+ 0x0000, 0x0218, 0x0000, 0x021a, 0x0000, 0x021c, 0x0000, 0x021e,
+ 0x0000, 0x0000, 0x0000, 0x0222, 0x0000, 0x0224, 0x0000, 0x0226,
+ 0x0000, 0x0228, 0x0000, 0x022a, 0x0000, 0x022c, 0x0000, 0x022e,
+ 0x0000, 0x0230, 0x0000, 0x0232, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x023b, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0241, 0x0000, 0x0000, 0x0000, 0x0000, 0x0246,
+ 0x0000, 0x0248, 0x0000, 0x024a, 0x0000, 0x024c, 0x0000, 0x024e,
+ 0x2c6f, 0x2c6d, 0x0000, 0x0181, 0x0186, 0x0000, 0x0189, 0x018a,
+ 0x0000, 0x018f, 0x0000, 0x0190, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0193, 0x0000, 0x0000, 0x0194, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0197, 0x0196, 0x0000, 0x2c62, 0x0000, 0x0000, 0x0000, 0x019c,
+ 0x0000, 0x2c6e, 0x019d, 0x0000, 0x0000, 0x019f, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x2c64, 0x0000, 0x0000,
+ 0x01a6, 0x0000, 0x0000, 0x01a9, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x01ae, 0x0244, 0x01b1, 0x01b2, 0x0245, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x01b7, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+};
+
+static const wchar_t t2_03[256] = {
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0370, 0x0000, 0x0372, 0x0000, 0x0000, 0x0000, 0x0376,
+ 0x0000, 0x0000, 0x0000, 0x03fd, 0x03fe, 0x03ff, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0386, 0x0388, 0x0389, 0x038a,
+ 0x0000, 0x0391, 0x0392, 0x0393, 0x0394, 0x0395, 0x0396, 0x0397,
+ 0x0398, 0x0399, 0x039a, 0x039b, 0x039c, 0x039d, 0x039e, 0x039f,
+ 0x03a0, 0x03a1, 0x0000, 0x03a3, 0x03a4, 0x03a5, 0x03a6, 0x03a7,
+ 0x03a8, 0x03a9, 0x03aa, 0x03ab, 0x038c, 0x038e, 0x038f, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x03cf,
+ 0x0000, 0x03d8, 0x0000, 0x03da, 0x0000, 0x03dc, 0x0000, 0x03de,
+ 0x0000, 0x03e0, 0x0000, 0x03e2, 0x0000, 0x03e4, 0x0000, 0x03e6,
+ 0x0000, 0x03e8, 0x0000, 0x03ea, 0x0000, 0x03ec, 0x0000, 0x03ee,
+ 0x0000, 0x0000, 0x03f9, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x03f7, 0x0000, 0x0000, 0x03fa, 0x0000, 0x0000, 0x0000, 0x0000,
+};
+
+static const wchar_t t2_04[256] = {
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0410, 0x0411, 0x0412, 0x0413, 0x0414, 0x0415, 0x0416, 0x0417,
+ 0x0418, 0x0419, 0x041a, 0x041b, 0x041c, 0x041d, 0x041e, 0x041f,
+ 0x0420, 0x0421, 0x0422, 0x0423, 0x0424, 0x0425, 0x0426, 0x0427,
+ 0x0428, 0x0429, 0x042a, 0x042b, 0x042c, 0x042d, 0x042e, 0x042f,
+ 0x0400, 0x0401, 0x0402, 0x0403, 0x0404, 0x0405, 0x0406, 0x0407,
+ 0x0408, 0x0409, 0x040a, 0x040b, 0x040c, 0x040d, 0x040e, 0x040f,
+ 0x0000, 0x0460, 0x0000, 0x0462, 0x0000, 0x0464, 0x0000, 0x0466,
+ 0x0000, 0x0468, 0x0000, 0x046a, 0x0000, 0x046c, 0x0000, 0x046e,
+ 0x0000, 0x0470, 0x0000, 0x0472, 0x0000, 0x0474, 0x0000, 0x0476,
+ 0x0000, 0x0478, 0x0000, 0x047a, 0x0000, 0x047c, 0x0000, 0x047e,
+ 0x0000, 0x0480, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x048a, 0x0000, 0x048c, 0x0000, 0x048e,
+ 0x0000, 0x0490, 0x0000, 0x0492, 0x0000, 0x0494, 0x0000, 0x0496,
+ 0x0000, 0x0498, 0x0000, 0x049a, 0x0000, 0x049c, 0x0000, 0x049e,
+ 0x0000, 0x04a0, 0x0000, 0x04a2, 0x0000, 0x04a4, 0x0000, 0x04a6,
+ 0x0000, 0x04a8, 0x0000, 0x04aa, 0x0000, 0x04ac, 0x0000, 0x04ae,
+ 0x0000, 0x04b0, 0x0000, 0x04b2, 0x0000, 0x04b4, 0x0000, 0x04b6,
+ 0x0000, 0x04b8, 0x0000, 0x04ba, 0x0000, 0x04bc, 0x0000, 0x04be,
+ 0x0000, 0x0000, 0x04c1, 0x0000, 0x04c3, 0x0000, 0x04c5, 0x0000,
+ 0x04c7, 0x0000, 0x04c9, 0x0000, 0x04cb, 0x0000, 0x04cd, 0x04c0,
+ 0x0000, 0x04d0, 0x0000, 0x04d2, 0x0000, 0x04d4, 0x0000, 0x04d6,
+ 0x0000, 0x04d8, 0x0000, 0x04da, 0x0000, 0x04dc, 0x0000, 0x04de,
+ 0x0000, 0x04e0, 0x0000, 0x04e2, 0x0000, 0x04e4, 0x0000, 0x04e6,
+ 0x0000, 0x04e8, 0x0000, 0x04ea, 0x0000, 0x04ec, 0x0000, 0x04ee,
+ 0x0000, 0x04f0, 0x0000, 0x04f2, 0x0000, 0x04f4, 0x0000, 0x04f6,
+ 0x0000, 0x04f8, 0x0000, 0x04fa, 0x0000, 0x04fc, 0x0000, 0x04fe,
+};
+
+static const wchar_t t2_05[256] = {
+ 0x0000, 0x0500, 0x0000, 0x0502, 0x0000, 0x0504, 0x0000, 0x0506,
+ 0x0000, 0x0508, 0x0000, 0x050a, 0x0000, 0x050c, 0x0000, 0x050e,
+ 0x0000, 0x0510, 0x0000, 0x0512, 0x0000, 0x0514, 0x0000, 0x0516,
+ 0x0000, 0x0518, 0x0000, 0x051a, 0x0000, 0x051c, 0x0000, 0x051e,
+ 0x0000, 0x0520, 0x0000, 0x0522, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0531, 0x0532, 0x0533, 0x0534, 0x0535, 0x0536, 0x0537,
+ 0x0538, 0x0539, 0x053a, 0x053b, 0x053c, 0x053d, 0x053e, 0x053f,
+ 0x0540, 0x0541, 0x0542, 0x0543, 0x0544, 0x0545, 0x0546, 0x0547,
+ 0x0548, 0x0549, 0x054a, 0x054b, 0x054c, 0x054d, 0x054e, 0x054f,
+ 0x0550, 0x0551, 0x0552, 0x0553, 0x0554, 0x0555, 0x0556, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+};
+
+static const wchar_t t2_1d[256] = {
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0xa77d, 0x0000, 0x0000, 0x0000, 0x2c63, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+};
+
+static const wchar_t t2_1e[256] = {
+ 0x0000, 0x1e00, 0x0000, 0x1e02, 0x0000, 0x1e04, 0x0000, 0x1e06,
+ 0x0000, 0x1e08, 0x0000, 0x1e0a, 0x0000, 0x1e0c, 0x0000, 0x1e0e,
+ 0x0000, 0x1e10, 0x0000, 0x1e12, 0x0000, 0x1e14, 0x0000, 0x1e16,
+ 0x0000, 0x1e18, 0x0000, 0x1e1a, 0x0000, 0x1e1c, 0x0000, 0x1e1e,
+ 0x0000, 0x1e20, 0x0000, 0x1e22, 0x0000, 0x1e24, 0x0000, 0x1e26,
+ 0x0000, 0x1e28, 0x0000, 0x1e2a, 0x0000, 0x1e2c, 0x0000, 0x1e2e,
+ 0x0000, 0x1e30, 0x0000, 0x1e32, 0x0000, 0x1e34, 0x0000, 0x1e36,
+ 0x0000, 0x1e38, 0x0000, 0x1e3a, 0x0000, 0x1e3c, 0x0000, 0x1e3e,
+ 0x0000, 0x1e40, 0x0000, 0x1e42, 0x0000, 0x1e44, 0x0000, 0x1e46,
+ 0x0000, 0x1e48, 0x0000, 0x1e4a, 0x0000, 0x1e4c, 0x0000, 0x1e4e,
+ 0x0000, 0x1e50, 0x0000, 0x1e52, 0x0000, 0x1e54, 0x0000, 0x1e56,
+ 0x0000, 0x1e58, 0x0000, 0x1e5a, 0x0000, 0x1e5c, 0x0000, 0x1e5e,
+ 0x0000, 0x1e60, 0x0000, 0x1e62, 0x0000, 0x1e64, 0x0000, 0x1e66,
+ 0x0000, 0x1e68, 0x0000, 0x1e6a, 0x0000, 0x1e6c, 0x0000, 0x1e6e,
+ 0x0000, 0x1e70, 0x0000, 0x1e72, 0x0000, 0x1e74, 0x0000, 0x1e76,
+ 0x0000, 0x1e78, 0x0000, 0x1e7a, 0x0000, 0x1e7c, 0x0000, 0x1e7e,
+ 0x0000, 0x1e80, 0x0000, 0x1e82, 0x0000, 0x1e84, 0x0000, 0x1e86,
+ 0x0000, 0x1e88, 0x0000, 0x1e8a, 0x0000, 0x1e8c, 0x0000, 0x1e8e,
+ 0x0000, 0x1e90, 0x0000, 0x1e92, 0x0000, 0x1e94, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x1ea0, 0x0000, 0x1ea2, 0x0000, 0x1ea4, 0x0000, 0x1ea6,
+ 0x0000, 0x1ea8, 0x0000, 0x1eaa, 0x0000, 0x1eac, 0x0000, 0x1eae,
+ 0x0000, 0x1eb0, 0x0000, 0x1eb2, 0x0000, 0x1eb4, 0x0000, 0x1eb6,
+ 0x0000, 0x1eb8, 0x0000, 0x1eba, 0x0000, 0x1ebc, 0x0000, 0x1ebe,
+ 0x0000, 0x1ec0, 0x0000, 0x1ec2, 0x0000, 0x1ec4, 0x0000, 0x1ec6,
+ 0x0000, 0x1ec8, 0x0000, 0x1eca, 0x0000, 0x1ecc, 0x0000, 0x1ece,
+ 0x0000, 0x1ed0, 0x0000, 0x1ed2, 0x0000, 0x1ed4, 0x0000, 0x1ed6,
+ 0x0000, 0x1ed8, 0x0000, 0x1eda, 0x0000, 0x1edc, 0x0000, 0x1ede,
+ 0x0000, 0x1ee0, 0x0000, 0x1ee2, 0x0000, 0x1ee4, 0x0000, 0x1ee6,
+ 0x0000, 0x1ee8, 0x0000, 0x1eea, 0x0000, 0x1eec, 0x0000, 0x1eee,
+ 0x0000, 0x1ef0, 0x0000, 0x1ef2, 0x0000, 0x1ef4, 0x0000, 0x1ef6,
+ 0x0000, 0x1ef8, 0x0000, 0x1efa, 0x0000, 0x1efc, 0x0000, 0x1efe,
+};
+
+static const wchar_t t2_1f[256] = {
+ 0x1f08, 0x1f09, 0x1f0a, 0x1f0b, 0x1f0c, 0x1f0d, 0x1f0e, 0x1f0f,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x1f18, 0x1f19, 0x1f1a, 0x1f1b, 0x1f1c, 0x1f1d, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x1f28, 0x1f29, 0x1f2a, 0x1f2b, 0x1f2c, 0x1f2d, 0x1f2e, 0x1f2f,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x1f38, 0x1f39, 0x1f3a, 0x1f3b, 0x1f3c, 0x1f3d, 0x1f3e, 0x1f3f,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x1f48, 0x1f49, 0x1f4a, 0x1f4b, 0x1f4c, 0x1f4d, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x1f59, 0x0000, 0x1f5b, 0x0000, 0x1f5d, 0x0000, 0x1f5f,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x1f68, 0x1f69, 0x1f6a, 0x1f6b, 0x1f6c, 0x1f6d, 0x1f6e, 0x1f6f,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x1fba, 0x1fbb, 0x1fc8, 0x1fc9, 0x1fca, 0x1fcb, 0x1fda, 0x1fdb,
+ 0x1ff8, 0x1ff9, 0x1fea, 0x1feb, 0x1ffa, 0x1ffb, 0x0000, 0x0000,
+ 0x1f88, 0x1f89, 0x1f8a, 0x1f8b, 0x1f8c, 0x1f8d, 0x1f8e, 0x1f8f,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x1f98, 0x1f99, 0x1f9a, 0x1f9b, 0x1f9c, 0x1f9d, 0x1f9e, 0x1f9f,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x1fa8, 0x1fa9, 0x1faa, 0x1fab, 0x1fac, 0x1fad, 0x1fae, 0x1faf,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x1fb8, 0x1fb9, 0x0000, 0x1fbc, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x1fcc, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x1fd8, 0x1fd9, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x1fe8, 0x1fe9, 0x0000, 0x0000, 0x0000, 0x1fec, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x1ffc, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+};
+
+static const wchar_t t2_21[256] = {
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x2132, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x2160, 0x2161, 0x2162, 0x2163, 0x2164, 0x2165, 0x2166, 0x2167,
+ 0x2168, 0x2169, 0x216a, 0x216b, 0x216c, 0x216d, 0x216e, 0x216f,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x2183, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+};
+
+static const wchar_t t2_24[256] = {
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x24b6, 0x24b7, 0x24b8, 0x24b9, 0x24ba, 0x24bb, 0x24bc, 0x24bd,
+ 0x24be, 0x24bf, 0x24c0, 0x24c1, 0x24c2, 0x24c3, 0x24c4, 0x24c5,
+ 0x24c6, 0x24c7, 0x24c8, 0x24c9, 0x24ca, 0x24cb, 0x24cc, 0x24cd,
+ 0x24ce, 0x24cf, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+};
+
+static const wchar_t t2_2c[256] = {
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x2c00, 0x2c01, 0x2c02, 0x2c03, 0x2c04, 0x2c05, 0x2c06, 0x2c07,
+ 0x2c08, 0x2c09, 0x2c0a, 0x2c0b, 0x2c0c, 0x2c0d, 0x2c0e, 0x2c0f,
+ 0x2c10, 0x2c11, 0x2c12, 0x2c13, 0x2c14, 0x2c15, 0x2c16, 0x2c17,
+ 0x2c18, 0x2c19, 0x2c1a, 0x2c1b, 0x2c1c, 0x2c1d, 0x2c1e, 0x2c1f,
+ 0x2c20, 0x2c21, 0x2c22, 0x2c23, 0x2c24, 0x2c25, 0x2c26, 0x2c27,
+ 0x2c28, 0x2c29, 0x2c2a, 0x2c2b, 0x2c2c, 0x2c2d, 0x2c2e, 0x0000,
+ 0x0000, 0x2c60, 0x0000, 0x0000, 0x0000, 0x023a, 0x023e, 0x0000,
+ 0x2c67, 0x0000, 0x2c69, 0x0000, 0x2c6b, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x2c72, 0x0000, 0x0000, 0x2c75, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x2c80, 0x0000, 0x2c82, 0x0000, 0x2c84, 0x0000, 0x2c86,
+ 0x0000, 0x2c88, 0x0000, 0x2c8a, 0x0000, 0x2c8c, 0x0000, 0x2c8e,
+ 0x0000, 0x2c90, 0x0000, 0x2c92, 0x0000, 0x2c94, 0x0000, 0x2c96,
+ 0x0000, 0x2c98, 0x0000, 0x2c9a, 0x0000, 0x2c9c, 0x0000, 0x2c9e,
+ 0x0000, 0x2ca0, 0x0000, 0x2ca2, 0x0000, 0x2ca4, 0x0000, 0x2ca6,
+ 0x0000, 0x2ca8, 0x0000, 0x2caa, 0x0000, 0x2cac, 0x0000, 0x2cae,
+ 0x0000, 0x2cb0, 0x0000, 0x2cb2, 0x0000, 0x2cb4, 0x0000, 0x2cb6,
+ 0x0000, 0x2cb8, 0x0000, 0x2cba, 0x0000, 0x2cbc, 0x0000, 0x2cbe,
+ 0x0000, 0x2cc0, 0x0000, 0x2cc2, 0x0000, 0x2cc4, 0x0000, 0x2cc6,
+ 0x0000, 0x2cc8, 0x0000, 0x2cca, 0x0000, 0x2ccc, 0x0000, 0x2cce,
+ 0x0000, 0x2cd0, 0x0000, 0x2cd2, 0x0000, 0x2cd4, 0x0000, 0x2cd6,
+ 0x0000, 0x2cd8, 0x0000, 0x2cda, 0x0000, 0x2cdc, 0x0000, 0x2cde,
+ 0x0000, 0x2ce0, 0x0000, 0x2ce2, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+};
+
+static const wchar_t t2_2d[256] = {
+ 0x10a0, 0x10a1, 0x10a2, 0x10a3, 0x10a4, 0x10a5, 0x10a6, 0x10a7,
+ 0x10a8, 0x10a9, 0x10aa, 0x10ab, 0x10ac, 0x10ad, 0x10ae, 0x10af,
+ 0x10b0, 0x10b1, 0x10b2, 0x10b3, 0x10b4, 0x10b5, 0x10b6, 0x10b7,
+ 0x10b8, 0x10b9, 0x10ba, 0x10bb, 0x10bc, 0x10bd, 0x10be, 0x10bf,
+ 0x10c0, 0x10c1, 0x10c2, 0x10c3, 0x10c4, 0x10c5, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+};
+
+static const wchar_t t2_a6[256] = {
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0xa640, 0x0000, 0xa642, 0x0000, 0xa644, 0x0000, 0xa646,
+ 0x0000, 0xa648, 0x0000, 0xa64a, 0x0000, 0xa64c, 0x0000, 0xa64e,
+ 0x0000, 0xa650, 0x0000, 0xa652, 0x0000, 0xa654, 0x0000, 0xa656,
+ 0x0000, 0xa658, 0x0000, 0xa65a, 0x0000, 0xa65c, 0x0000, 0xa65e,
+ 0x0000, 0x0000, 0x0000, 0xa662, 0x0000, 0xa664, 0x0000, 0xa666,
+ 0x0000, 0xa668, 0x0000, 0xa66a, 0x0000, 0xa66c, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0xa680, 0x0000, 0xa682, 0x0000, 0xa684, 0x0000, 0xa686,
+ 0x0000, 0xa688, 0x0000, 0xa68a, 0x0000, 0xa68c, 0x0000, 0xa68e,
+ 0x0000, 0xa690, 0x0000, 0xa692, 0x0000, 0xa694, 0x0000, 0xa696,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+};
+
+static const wchar_t t2_a7[256] = {
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0xa722, 0x0000, 0xa724, 0x0000, 0xa726,
+ 0x0000, 0xa728, 0x0000, 0xa72a, 0x0000, 0xa72c, 0x0000, 0xa72e,
+ 0x0000, 0x0000, 0x0000, 0xa732, 0x0000, 0xa734, 0x0000, 0xa736,
+ 0x0000, 0xa738, 0x0000, 0xa73a, 0x0000, 0xa73c, 0x0000, 0xa73e,
+ 0x0000, 0xa740, 0x0000, 0xa742, 0x0000, 0xa744, 0x0000, 0xa746,
+ 0x0000, 0xa748, 0x0000, 0xa74a, 0x0000, 0xa74c, 0x0000, 0xa74e,
+ 0x0000, 0xa750, 0x0000, 0xa752, 0x0000, 0xa754, 0x0000, 0xa756,
+ 0x0000, 0xa758, 0x0000, 0xa75a, 0x0000, 0xa75c, 0x0000, 0xa75e,
+ 0x0000, 0xa760, 0x0000, 0xa762, 0x0000, 0xa764, 0x0000, 0xa766,
+ 0x0000, 0xa768, 0x0000, 0xa76a, 0x0000, 0xa76c, 0x0000, 0xa76e,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0xa779, 0x0000, 0xa77b, 0x0000, 0x0000, 0xa77e,
+ 0x0000, 0xa780, 0x0000, 0xa782, 0x0000, 0xa784, 0x0000, 0xa786,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0xa78b, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+};
+
+static const wchar_t t2_ff[256] = {
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0xff21, 0xff22, 0xff23, 0xff24, 0xff25, 0xff26, 0xff27,
+ 0xff28, 0xff29, 0xff2a, 0xff2b, 0xff2c, 0xff2d, 0xff2e, 0xff2f,
+ 0xff30, 0xff31, 0xff32, 0xff33, 0xff34, 0xff35, 0xff36, 0xff37,
+ 0xff38, 0xff39, 0xff3a, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+};
+
+static const wchar_t *const toplevel[256] = {
+ t2_00, t2_01, t2_02, t2_03, t2_04, t2_05, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, t2_1d, t2_1e, t2_1f,
+ NULL, t2_21, NULL, NULL, t2_24, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, t2_2c, t2_2d, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, t2_a6, t2_a7,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, t2_ff,
+};
+
+/**
+ * cifs_toupper - convert a wchar_t from lower to uppercase
+ * @in: character to convert from lower to uppercase
+ *
+ * This function consults the static tables above to convert a wchar_t from
+ * lower to uppercase. In the event that there is no mapping, the original
+ * "in" character is returned.
+ */
+wchar_t
+cifs_toupper(wchar_t in)
+{
+ unsigned char idx;
+ const wchar_t *tbl;
+ wchar_t out;
+
+ /* grab upper byte */
+ idx = (in & 0xff00) >> 8;
+
+ /* find pointer to 2nd layer table */
+ tbl = toplevel[idx];
+ if (!tbl)
+ return in;
+
+ /* grab lower byte */
+ idx = in & 0xff;
+
+ /* look up character in table */
+ out = tbl[idx];
+ if (out)
+ return out;
+
+ return in;
+}
diff --git a/fs/coredump.c b/fs/coredump.c
index 72f816d..9bdeca1 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -190,6 +190,11 @@
err = cn_printf(cn, "%d",
task_tgid_vnr(current));
break;
+ /* global pid */
+ case 'P':
+ err = cn_printf(cn, "%d",
+ task_tgid_nr(current));
+ break;
/* uid */
case 'u':
err = cn_printf(cn, "%d", cred->uid);
diff --git a/fs/dcache.c b/fs/dcache.c
index 4d9df3c..1bd4614 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -37,6 +37,7 @@
#include <linux/rculist_bl.h>
#include <linux/prefetch.h>
#include <linux/ratelimit.h>
+#include <linux/list_lru.h>
#include "internal.h"
#include "mount.h"
@@ -48,7 +49,7 @@
* - the dcache hash table
* s_anon bl list spinlock protects:
* - the s_anon list (see __d_drop)
- * dcache_lru_lock protects:
+ * dentry->d_sb->s_dentry_lru_lock protects:
* - the dcache lru lists and counters
* d_lock protects:
* - d_flags
@@ -63,7 +64,7 @@
* Ordering:
* dentry->d_inode->i_lock
* dentry->d_lock
- * dcache_lru_lock
+ * dentry->d_sb->s_dentry_lru_lock
* dcache_hash_bucket lock
* s_anon lock
*
@@ -81,7 +82,6 @@
int sysctl_vfs_cache_pressure __read_mostly = 100;
EXPORT_SYMBOL_GPL(sysctl_vfs_cache_pressure);
-static __cacheline_aligned_in_smp DEFINE_SPINLOCK(dcache_lru_lock);
__cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock);
EXPORT_SYMBOL(rename_lock);
@@ -90,8 +90,8 @@
/**
* read_seqbegin_or_lock - begin a sequence number check or locking block
- * lock: sequence lock
- * seq : sequence number to be checked
+ * @lock: sequence lock
+ * @seq : sequence number to be checked
*
* First try it once optimistically without taking the lock. If that fails,
* take the lock. The sequence number is also used as a marker for deciding
@@ -103,7 +103,7 @@
if (!(*seq & 1)) /* Even */
*seq = read_seqbegin(lock);
else /* Odd */
- write_seqlock(lock);
+ read_seqlock_excl(lock);
}
static inline int need_seqretry(seqlock_t *lock, int seq)
@@ -114,7 +114,7 @@
static inline void done_seqretry(seqlock_t *lock, int seq)
{
if (seq & 1)
- write_sequnlock(lock);
+ read_sequnlock_excl(lock);
}
/*
@@ -146,23 +146,47 @@
.age_limit = 45,
};
-static DEFINE_PER_CPU(unsigned int, nr_dentry);
+static DEFINE_PER_CPU(long, nr_dentry);
+static DEFINE_PER_CPU(long, nr_dentry_unused);
#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
-static int get_nr_dentry(void)
+
+/*
+ * Here we resort to our own counters instead of using generic per-cpu counters
+ * for consistency with what the vfs inode code does. We are expected to harvest
+ * better code and performance by having our own specialized counters.
+ *
+ * Please note that the loop is done over all possible CPUs, not over all online
+ * CPUs. The reason for this is that we don't want to play games with CPUs going
+ * on and off. If one of them goes off, we will just keep their counters.
+ *
+ * glommer: See cffbc8a for details, and if you ever intend to change this,
+ * please update all vfs counters to match.
+ */
+static long get_nr_dentry(void)
{
int i;
- int sum = 0;
+ long sum = 0;
for_each_possible_cpu(i)
sum += per_cpu(nr_dentry, i);
return sum < 0 ? 0 : sum;
}
+static long get_nr_dentry_unused(void)
+{
+ int i;
+ long sum = 0;
+ for_each_possible_cpu(i)
+ sum += per_cpu(nr_dentry_unused, i);
+ return sum < 0 ? 0 : sum;
+}
+
int proc_nr_dentry(ctl_table *table, int write, void __user *buffer,
size_t *lenp, loff_t *ppos)
{
dentry_stat.nr_dentry = get_nr_dentry();
- return proc_dointvec(table, write, buffer, lenp, ppos);
+ dentry_stat.nr_unused = get_nr_dentry_unused();
+ return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
}
#endif
@@ -333,52 +357,35 @@
}
/*
- * dentry_lru_(add|del|prune|move_tail) must be called with d_lock held.
+ * dentry_lru_(add|del)_list) must be called with d_lock held.
*/
static void dentry_lru_add(struct dentry *dentry)
{
if (unlikely(!(dentry->d_flags & DCACHE_LRU_LIST))) {
- spin_lock(&dcache_lru_lock);
+ if (list_lru_add(&dentry->d_sb->s_dentry_lru, &dentry->d_lru))
+ this_cpu_inc(nr_dentry_unused);
dentry->d_flags |= DCACHE_LRU_LIST;
- list_add(&dentry->d_lru, &dentry->d_sb->s_dentry_lru);
- dentry->d_sb->s_nr_dentry_unused++;
- dentry_stat.nr_unused++;
- spin_unlock(&dcache_lru_lock);
}
}
-static void __dentry_lru_del(struct dentry *dentry)
-{
- list_del_init(&dentry->d_lru);
- dentry->d_flags &= ~(DCACHE_SHRINK_LIST | DCACHE_LRU_LIST);
- dentry->d_sb->s_nr_dentry_unused--;
- dentry_stat.nr_unused--;
-}
-
/*
* Remove a dentry with references from the LRU.
+ *
+ * If we are on the shrink list, then we can get to try_prune_one_dentry() and
+ * lose our last reference through the parent walk. In this case, we need to
+ * remove ourselves from the shrink list, not the LRU.
*/
static void dentry_lru_del(struct dentry *dentry)
{
- if (!list_empty(&dentry->d_lru)) {
- spin_lock(&dcache_lru_lock);
- __dentry_lru_del(dentry);
- spin_unlock(&dcache_lru_lock);
+ if (dentry->d_flags & DCACHE_SHRINK_LIST) {
+ list_del_init(&dentry->d_lru);
+ dentry->d_flags &= ~DCACHE_SHRINK_LIST;
+ return;
}
-}
-static void dentry_lru_move_list(struct dentry *dentry, struct list_head *list)
-{
- spin_lock(&dcache_lru_lock);
- if (list_empty(&dentry->d_lru)) {
- dentry->d_flags |= DCACHE_LRU_LIST;
- list_add_tail(&dentry->d_lru, list);
- dentry->d_sb->s_nr_dentry_unused++;
- dentry_stat.nr_unused++;
- } else {
- list_move_tail(&dentry->d_lru, list);
- }
- spin_unlock(&dcache_lru_lock);
+ if (list_lru_del(&dentry->d_sb->s_dentry_lru, &dentry->d_lru))
+ this_cpu_dec(nr_dentry_unused);
+ dentry->d_flags &= ~DCACHE_LRU_LIST;
}
/**
@@ -474,7 +481,8 @@
* If ref is non-zero, then decrement the refcount too.
* Returns dentry requiring refcount drop, or NULL if we're done.
*/
-static inline struct dentry *dentry_kill(struct dentry *dentry)
+static inline struct dentry *
+dentry_kill(struct dentry *dentry, int unlock_on_failure)
__releases(dentry->d_lock)
{
struct inode *inode;
@@ -483,8 +491,10 @@
inode = dentry->d_inode;
if (inode && !spin_trylock(&inode->i_lock)) {
relock:
- spin_unlock(&dentry->d_lock);
- cpu_relax();
+ if (unlock_on_failure) {
+ spin_unlock(&dentry->d_lock);
+ cpu_relax();
+ }
return dentry; /* try again with same dentry */
}
if (IS_ROOT(dentry))
@@ -567,7 +577,7 @@
return;
kill_it:
- dentry = dentry_kill(dentry);
+ dentry = dentry_kill(dentry, 1);
if (dentry)
goto repeat;
}
@@ -787,12 +797,12 @@
*
* This may fail if locks cannot be acquired no problem, just try again.
*/
-static void try_prune_one_dentry(struct dentry *dentry)
+static struct dentry * try_prune_one_dentry(struct dentry *dentry)
__releases(dentry->d_lock)
{
struct dentry *parent;
- parent = dentry_kill(dentry);
+ parent = dentry_kill(dentry, 0);
/*
* If dentry_kill returns NULL, we have nothing more to do.
* if it returns the same dentry, trylocks failed. In either
@@ -804,17 +814,18 @@
* fragmentation.
*/
if (!parent)
- return;
+ return NULL;
if (parent == dentry)
- return;
+ return dentry;
/* Prune ancestors. */
dentry = parent;
while (dentry) {
if (lockref_put_or_lock(&dentry->d_lockref))
- return;
- dentry = dentry_kill(dentry);
+ return NULL;
+ dentry = dentry_kill(dentry, 1);
}
+ return NULL;
}
static void shrink_dentry_list(struct list_head *list)
@@ -833,76 +844,143 @@
}
/*
+ * The dispose list is isolated and dentries are not accounted
+ * to the LRU here, so we can simply remove it from the list
+ * here regardless of whether it is referenced or not.
+ */
+ list_del_init(&dentry->d_lru);
+ dentry->d_flags &= ~DCACHE_SHRINK_LIST;
+
+ /*
* We found an inuse dentry which was not removed from
- * the LRU because of laziness during lookup. Do not free
- * it - just keep it off the LRU list.
+ * the LRU because of laziness during lookup. Do not free it.
*/
if (dentry->d_lockref.count) {
- dentry_lru_del(dentry);
spin_unlock(&dentry->d_lock);
continue;
}
-
rcu_read_unlock();
- try_prune_one_dentry(dentry);
+ dentry = try_prune_one_dentry(dentry);
rcu_read_lock();
+ if (dentry) {
+ dentry->d_flags |= DCACHE_SHRINK_LIST;
+ list_add(&dentry->d_lru, list);
+ spin_unlock(&dentry->d_lock);
+ }
}
rcu_read_unlock();
}
+static enum lru_status
+dentry_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
+{
+ struct list_head *freeable = arg;
+ struct dentry *dentry = container_of(item, struct dentry, d_lru);
+
+
+ /*
+ * we are inverting the lru lock/dentry->d_lock here,
+ * so use a trylock. If we fail to get the lock, just skip
+ * it
+ */
+ if (!spin_trylock(&dentry->d_lock))
+ return LRU_SKIP;
+
+ /*
+ * Referenced dentries are still in use. If they have active
+ * counts, just remove them from the LRU. Otherwise give them
+ * another pass through the LRU.
+ */
+ if (dentry->d_lockref.count) {
+ list_del_init(&dentry->d_lru);
+ spin_unlock(&dentry->d_lock);
+ return LRU_REMOVED;
+ }
+
+ if (dentry->d_flags & DCACHE_REFERENCED) {
+ dentry->d_flags &= ~DCACHE_REFERENCED;
+ spin_unlock(&dentry->d_lock);
+
+ /*
+ * The list move itself will be made by the common LRU code. At
+ * this point, we've dropped the dentry->d_lock but keep the
+ * lru lock. This is safe to do, since every list movement is
+ * protected by the lru lock even if both locks are held.
+ *
+ * This is guaranteed by the fact that all LRU management
+ * functions are intermediated by the LRU API calls like
+ * list_lru_add and list_lru_del. List movement in this file
+ * only ever occur through this functions or through callbacks
+ * like this one, that are called from the LRU API.
+ *
+ * The only exceptions to this are functions like
+ * shrink_dentry_list, and code that first checks for the
+ * DCACHE_SHRINK_LIST flag. Those are guaranteed to be
+ * operating only with stack provided lists after they are
+ * properly isolated from the main list. It is thus, always a
+ * local access.
+ */
+ return LRU_ROTATE;
+ }
+
+ dentry->d_flags |= DCACHE_SHRINK_LIST;
+ list_move_tail(&dentry->d_lru, freeable);
+ this_cpu_dec(nr_dentry_unused);
+ spin_unlock(&dentry->d_lock);
+
+ return LRU_REMOVED;
+}
+
/**
* prune_dcache_sb - shrink the dcache
* @sb: superblock
- * @count: number of entries to try to free
+ * @nr_to_scan : number of entries to try to free
+ * @nid: which node to scan for freeable entities
*
- * Attempt to shrink the superblock dcache LRU by @count entries. This is
+ * Attempt to shrink the superblock dcache LRU by @nr_to_scan entries. This is
* done when we need more memory an called from the superblock shrinker
* function.
*
* This function may fail to free any resources if all the dentries are in
* use.
*/
-void prune_dcache_sb(struct super_block *sb, int count)
+long prune_dcache_sb(struct super_block *sb, unsigned long nr_to_scan,
+ int nid)
{
- struct dentry *dentry;
- LIST_HEAD(referenced);
- LIST_HEAD(tmp);
+ LIST_HEAD(dispose);
+ long freed;
-relock:
- spin_lock(&dcache_lru_lock);
- while (!list_empty(&sb->s_dentry_lru)) {
- dentry = list_entry(sb->s_dentry_lru.prev,
- struct dentry, d_lru);
- BUG_ON(dentry->d_sb != sb);
-
- if (!spin_trylock(&dentry->d_lock)) {
- spin_unlock(&dcache_lru_lock);
- cpu_relax();
- goto relock;
- }
-
- if (dentry->d_flags & DCACHE_REFERENCED) {
- dentry->d_flags &= ~DCACHE_REFERENCED;
- list_move(&dentry->d_lru, &referenced);
- spin_unlock(&dentry->d_lock);
- } else {
- list_move_tail(&dentry->d_lru, &tmp);
- dentry->d_flags |= DCACHE_SHRINK_LIST;
- spin_unlock(&dentry->d_lock);
- if (!--count)
- break;
- }
- cond_resched_lock(&dcache_lru_lock);
- }
- if (!list_empty(&referenced))
- list_splice(&referenced, &sb->s_dentry_lru);
- spin_unlock(&dcache_lru_lock);
-
- shrink_dentry_list(&tmp);
+ freed = list_lru_walk_node(&sb->s_dentry_lru, nid, dentry_lru_isolate,
+ &dispose, &nr_to_scan);
+ shrink_dentry_list(&dispose);
+ return freed;
}
+static enum lru_status dentry_lru_isolate_shrink(struct list_head *item,
+ spinlock_t *lru_lock, void *arg)
+{
+ struct list_head *freeable = arg;
+ struct dentry *dentry = container_of(item, struct dentry, d_lru);
+
+ /*
+ * we are inverting the lru lock/dentry->d_lock here,
+ * so use a trylock. If we fail to get the lock, just skip
+ * it
+ */
+ if (!spin_trylock(&dentry->d_lock))
+ return LRU_SKIP;
+
+ dentry->d_flags |= DCACHE_SHRINK_LIST;
+ list_move_tail(&dentry->d_lru, freeable);
+ this_cpu_dec(nr_dentry_unused);
+ spin_unlock(&dentry->d_lock);
+
+ return LRU_REMOVED;
+}
+
+
/**
* shrink_dcache_sb - shrink dcache for a superblock
* @sb: superblock
@@ -912,16 +990,17 @@
*/
void shrink_dcache_sb(struct super_block *sb)
{
- LIST_HEAD(tmp);
+ long freed;
- spin_lock(&dcache_lru_lock);
- while (!list_empty(&sb->s_dentry_lru)) {
- list_splice_init(&sb->s_dentry_lru, &tmp);
- spin_unlock(&dcache_lru_lock);
- shrink_dentry_list(&tmp);
- spin_lock(&dcache_lru_lock);
- }
- spin_unlock(&dcache_lru_lock);
+ do {
+ LIST_HEAD(dispose);
+
+ freed = list_lru_walk(&sb->s_dentry_lru,
+ dentry_lru_isolate_shrink, &dispose, UINT_MAX);
+
+ this_cpu_sub(nr_dentry_unused, freed);
+ shrink_dentry_list(&dispose);
+ } while (freed > 0);
}
EXPORT_SYMBOL(shrink_dcache_sb);
@@ -1283,7 +1362,8 @@
if (dentry->d_lockref.count) {
dentry_lru_del(dentry);
} else if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) {
- dentry_lru_move_list(dentry, &data->dispose);
+ dentry_lru_del(dentry);
+ list_add_tail(&dentry->d_lru, &data->dispose);
dentry->d_flags |= DCACHE_SHRINK_LIST;
data->found++;
ret = D_WALK_NORETRY;
@@ -2673,9 +2753,9 @@
/**
* prepend_name - prepend a pathname in front of current buffer pointer
- * buffer: buffer pointer
- * buflen: allocated length of the buffer
- * name: name string and length qstr structure
+ * @buffer: buffer pointer
+ * @buflen: allocated length of the buffer
+ * @name: name string and length qstr structure
*
* With RCU path tracing, it may race with d_move(). Use ACCESS_ONCE() to
* make sure that either the old or the new name pointer and length are
@@ -2713,14 +2793,15 @@
* @buffer: pointer to the end of the buffer
* @buflen: pointer to buffer length
*
- * The function tries to write out the pathname without taking any lock other
- * than the RCU read lock to make sure that dentries won't go away. It only
- * checks the sequence number of the global rename_lock as any change in the
- * dentry's d_seq will be preceded by changes in the rename_lock sequence
- * number. If the sequence number had been change, it will restart the whole
- * pathname back-tracing sequence again. It performs a total of 3 trials of
- * lockless back-tracing sequences before falling back to take the
- * rename_lock.
+ * The function will first try to write out the pathname without taking any
+ * lock other than the RCU read lock to make sure that dentries won't go away.
+ * It only checks the sequence number of the global rename_lock as any change
+ * in the dentry's d_seq will be preceded by changes in the rename_lock
+ * sequence number. If the sequence number had been changed, it will restart
+ * the whole pathname back-tracing sequence again by taking the rename_lock.
+ * In this case, there is no need to take the RCU read lock as the recursive
+ * parent pointer references will keep the dentry chain alive as long as no
+ * rename operation is performed.
*/
static int prepend_path(const struct path *path,
const struct path *root,
@@ -2868,6 +2949,16 @@
return prepend(buffer, buflen, "(unreachable)", 13);
}
+static void get_fs_root_rcu(struct fs_struct *fs, struct path *root)
+{
+ unsigned seq;
+
+ do {
+ seq = read_seqcount_begin(&fs->seq);
+ *root = fs->root;
+ } while (read_seqcount_retry(&fs->seq, seq));
+}
+
/**
* d_path - return the path of a dentry
* @path: path to report
@@ -2900,13 +2991,15 @@
if (path->dentry->d_op && path->dentry->d_op->d_dname)
return path->dentry->d_op->d_dname(path->dentry, buf, buflen);
- get_fs_root(current->fs, &root);
+ rcu_read_lock();
+ get_fs_root_rcu(current->fs, &root);
br_read_lock(&vfsmount_lock);
error = path_with_deleted(path, &root, &res, &buflen);
br_read_unlock(&vfsmount_lock);
+ rcu_read_unlock();
+
if (error < 0)
res = ERR_PTR(error);
- path_put(&root);
return res;
}
EXPORT_SYMBOL(d_path);
@@ -3014,6 +3107,18 @@
return ERR_PTR(-ENAMETOOLONG);
}
+static void get_fs_root_and_pwd_rcu(struct fs_struct *fs, struct path *root,
+ struct path *pwd)
+{
+ unsigned seq;
+
+ do {
+ seq = read_seqcount_begin(&fs->seq);
+ *root = fs->root;
+ *pwd = fs->pwd;
+ } while (read_seqcount_retry(&fs->seq, seq));
+}
+
/*
* NOTE! The user-level library version returns a
* character pointer. The kernel system call just
@@ -3036,23 +3141,25 @@
{
int error;
struct path pwd, root;
- char *page = (char *) __get_free_page(GFP_USER);
+ char *page = __getname();
if (!page)
return -ENOMEM;
- get_fs_root_and_pwd(current->fs, &root, &pwd);
+ rcu_read_lock();
+ get_fs_root_and_pwd_rcu(current->fs, &root, &pwd);
error = -ENOENT;
br_read_lock(&vfsmount_lock);
if (!d_unlinked(pwd.dentry)) {
unsigned long len;
- char *cwd = page + PAGE_SIZE;
- int buflen = PAGE_SIZE;
+ char *cwd = page + PATH_MAX;
+ int buflen = PATH_MAX;
prepend(&cwd, &buflen, "\0", 1);
error = prepend_path(&pwd, &root, &cwd, &buflen);
br_read_unlock(&vfsmount_lock);
+ rcu_read_unlock();
if (error < 0)
goto out;
@@ -3065,7 +3172,7 @@
}
error = -ERANGE;
- len = PAGE_SIZE + page - cwd;
+ len = PATH_MAX + page - cwd;
if (len <= size) {
error = len;
if (copy_to_user(buf, cwd, len))
@@ -3073,12 +3180,11 @@
}
} else {
br_read_unlock(&vfsmount_lock);
+ rcu_read_unlock();
}
out:
- path_put(&pwd);
- path_put(&root);
- free_page((unsigned long) page);
+ __putname(page);
return error;
}
diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index c00e055..9fd702f 100644
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -44,6 +44,7 @@
.gfp_mask = GFP_KERNEL,
};
+ nodes_setall(shrink.nodes_to_scan);
do {
nr_objects = shrink_slab(&shrink, 1000, 1000);
} while (nr_objects > 10);
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index d107576..c88e355 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -609,39 +609,35 @@
char *full_alg_name;
int rc = -EINVAL;
- if (!crypt_stat->cipher) {
- ecryptfs_printk(KERN_ERR, "No cipher specified\n");
- goto out;
- }
ecryptfs_printk(KERN_DEBUG,
"Initializing cipher [%s]; strlen = [%d]; "
"key_size_bits = [%zd]\n",
crypt_stat->cipher, (int)strlen(crypt_stat->cipher),
crypt_stat->key_size << 3);
+ mutex_lock(&crypt_stat->cs_tfm_mutex);
if (crypt_stat->tfm) {
rc = 0;
- goto out;
+ goto out_unlock;
}
- mutex_lock(&crypt_stat->cs_tfm_mutex);
rc = ecryptfs_crypto_api_algify_cipher_name(&full_alg_name,
crypt_stat->cipher, "cbc");
if (rc)
goto out_unlock;
crypt_stat->tfm = crypto_alloc_ablkcipher(full_alg_name, 0, 0);
- kfree(full_alg_name);
if (IS_ERR(crypt_stat->tfm)) {
rc = PTR_ERR(crypt_stat->tfm);
crypt_stat->tfm = NULL;
ecryptfs_printk(KERN_ERR, "cryptfs: init_crypt_ctx(): "
"Error initializing cipher [%s]\n",
- crypt_stat->cipher);
- goto out_unlock;
+ full_alg_name);
+ goto out_free;
}
crypto_ablkcipher_set_flags(crypt_stat->tfm, CRYPTO_TFM_REQ_WEAK_KEY);
rc = 0;
+out_free:
+ kfree(full_alg_name);
out_unlock:
mutex_unlock(&crypt_stat->cs_tfm_mutex);
-out:
return rc;
}
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 293f867..473e09d 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -740,6 +740,7 @@
epi = rb_entry(rbp, struct epitem, rbn);
ep_unregister_pollwait(ep, epi);
+ cond_resched();
}
/*
@@ -754,6 +755,7 @@
while ((rbp = rb_first(&ep->rbr)) != NULL) {
epi = rb_entry(rbp, struct epitem, rbn);
ep_remove(ep, epi);
+ cond_resched();
}
mutex_unlock(&ep->mtx);
diff --git a/fs/exec.c b/fs/exec.c
index fd774c7..8875dd1 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -74,6 +74,8 @@
void __register_binfmt(struct linux_binfmt * fmt, int insert)
{
BUG_ON(!fmt);
+ if (WARN_ON(!fmt->load_binary))
+ return;
write_lock(&binfmt_lock);
insert ? list_add(&fmt->lh, &formats) :
list_add_tail(&fmt->lh, &formats);
@@ -266,7 +268,7 @@
BUILD_BUG_ON(VM_STACK_FLAGS & VM_STACK_INCOMPLETE_SETUP);
vma->vm_end = STACK_TOP_MAX;
vma->vm_start = vma->vm_end - PAGE_SIZE;
- vma->vm_flags = VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP;
+ vma->vm_flags = VM_SOFTDIRTY | VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP;
vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
INIT_LIST_HEAD(&vma->anon_vma_chain);
@@ -1365,18 +1367,18 @@
}
EXPORT_SYMBOL(remove_arg_zero);
+#define printable(c) (((c)=='\t') || ((c)=='\n') || (0x20<=(c) && (c)<=0x7e))
/*
* cycle the list of binary formats handler, until one recognizes the image
*/
int search_binary_handler(struct linux_binprm *bprm)
{
- unsigned int depth = bprm->recursion_depth;
- int try,retval;
+ bool need_retry = IS_ENABLED(CONFIG_MODULES);
struct linux_binfmt *fmt;
- pid_t old_pid, old_vpid;
+ int retval;
/* This allows 4 levels of binfmt rewrites before failing hard. */
- if (depth > 5)
+ if (bprm->recursion_depth > 5)
return -ELOOP;
retval = security_bprm_check(bprm);
@@ -1387,71 +1389,67 @@
if (retval)
return retval;
+ retval = -ENOENT;
+ retry:
+ read_lock(&binfmt_lock);
+ list_for_each_entry(fmt, &formats, lh) {
+ if (!try_module_get(fmt->module))
+ continue;
+ read_unlock(&binfmt_lock);
+ bprm->recursion_depth++;
+ retval = fmt->load_binary(bprm);
+ bprm->recursion_depth--;
+ if (retval >= 0 || retval != -ENOEXEC ||
+ bprm->mm == NULL || bprm->file == NULL) {
+ put_binfmt(fmt);
+ return retval;
+ }
+ read_lock(&binfmt_lock);
+ put_binfmt(fmt);
+ }
+ read_unlock(&binfmt_lock);
+
+ if (need_retry && retval == -ENOEXEC) {
+ if (printable(bprm->buf[0]) && printable(bprm->buf[1]) &&
+ printable(bprm->buf[2]) && printable(bprm->buf[3]))
+ return retval;
+ if (request_module("binfmt-%04x", *(ushort *)(bprm->buf + 2)) < 0)
+ return retval;
+ need_retry = false;
+ goto retry;
+ }
+
+ return retval;
+}
+EXPORT_SYMBOL(search_binary_handler);
+
+static int exec_binprm(struct linux_binprm *bprm)
+{
+ pid_t old_pid, old_vpid;
+ int ret;
+
/* Need to fetch pid before load_binary changes it */
old_pid = current->pid;
rcu_read_lock();
old_vpid = task_pid_nr_ns(current, task_active_pid_ns(current->parent));
rcu_read_unlock();
- retval = -ENOENT;
- for (try=0; try<2; try++) {
- read_lock(&binfmt_lock);
- list_for_each_entry(fmt, &formats, lh) {
- int (*fn)(struct linux_binprm *) = fmt->load_binary;
- if (!fn)
- continue;
- if (!try_module_get(fmt->module))
- continue;
- read_unlock(&binfmt_lock);
- bprm->recursion_depth = depth + 1;
- retval = fn(bprm);
- bprm->recursion_depth = depth;
- if (retval >= 0) {
- if (depth == 0) {
- trace_sched_process_exec(current, old_pid, bprm);
- ptrace_event(PTRACE_EVENT_EXEC, old_vpid);
- }
- put_binfmt(fmt);
- allow_write_access(bprm->file);
- if (bprm->file)
- fput(bprm->file);
- bprm->file = NULL;
- current->did_exec = 1;
- proc_exec_connector(current);
- return retval;
- }
- read_lock(&binfmt_lock);
- put_binfmt(fmt);
- if (retval != -ENOEXEC || bprm->mm == NULL)
- break;
- if (!bprm->file) {
- read_unlock(&binfmt_lock);
- return retval;
- }
- }
- read_unlock(&binfmt_lock);
-#ifdef CONFIG_MODULES
- if (retval != -ENOEXEC || bprm->mm == NULL) {
- break;
- } else {
-#define printable(c) (((c)=='\t') || ((c)=='\n') || (0x20<=(c) && (c)<=0x7e))
- if (printable(bprm->buf[0]) &&
- printable(bprm->buf[1]) &&
- printable(bprm->buf[2]) &&
- printable(bprm->buf[3]))
- break; /* -ENOEXEC */
- if (try)
- break; /* -ENOEXEC */
- request_module("binfmt-%04x", *(unsigned short *)(&bprm->buf[2]));
- }
-#else
- break;
-#endif
- }
- return retval;
-}
+ ret = search_binary_handler(bprm);
+ if (ret >= 0) {
+ trace_sched_process_exec(current, old_pid, bprm);
+ ptrace_event(PTRACE_EVENT_EXEC, old_vpid);
+ current->did_exec = 1;
+ proc_exec_connector(current);
-EXPORT_SYMBOL(search_binary_handler);
+ if (bprm->file) {
+ allow_write_access(bprm->file);
+ fput(bprm->file);
+ bprm->file = NULL; /* to catch use-after-free */
+ }
+ }
+
+ return ret;
+}
/*
* sys_execve() executes a new program.
@@ -1541,7 +1539,7 @@
if (retval < 0)
goto out;
- retval = search_binary_handler(bprm);
+ retval = exec_binprm(bprm);
if (retval < 0)
goto out;
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index 2ec8eb1..a52a5d2 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -861,7 +861,7 @@
static void _write_failed(struct inode *inode, loff_t to)
{
if (to > inode->i_size)
- truncate_pagecache(inode, to, inode->i_size);
+ truncate_pagecache(inode, inode->i_size);
}
int exofs_write_begin(struct file *file, struct address_space *mapping,
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 0a87bb1..c260de6 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -58,7 +58,7 @@
struct inode *inode = mapping->host;
if (to > inode->i_size) {
- truncate_pagecache(inode, to, inode->i_size);
+ truncate_pagecache(inode, inode->i_size);
ext2_truncate_blocks(inode, inode->i_size);
}
}
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 2d1bdbe..3981ff7 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -931,13 +931,15 @@
struct ext4_inode_info *ei;
struct list_head *cur, *tmp;
LIST_HEAD(skipped);
- int ret, nr_shrunk = 0;
+ int nr_shrunk = 0;
int retried = 0, skip_precached = 1, nr_skipped = 0;
spin_lock(&sbi->s_es_lru_lock);
retry:
list_for_each_safe(cur, tmp, &sbi->s_es_lru) {
+ int shrunk;
+
/*
* If we have already reclaimed all extents from extent
* status tree, just stop the loop immediately.
@@ -964,13 +966,13 @@
continue;
write_lock(&ei->i_es_lock);
- ret = __es_try_to_reclaim_extents(ei, nr_to_scan);
+ shrunk = __es_try_to_reclaim_extents(ei, nr_to_scan);
if (ei->i_es_lru_nr == 0)
list_del_init(&ei->i_es_lru);
write_unlock(&ei->i_es_lock);
- nr_shrunk += ret;
- nr_to_scan -= ret;
+ nr_shrunk += shrunk;
+ nr_to_scan -= shrunk;
if (nr_to_scan == 0)
break;
}
@@ -1007,7 +1009,20 @@
return nr_shrunk;
}
-static int ext4_es_shrink(struct shrinker *shrink, struct shrink_control *sc)
+static unsigned long ext4_es_count(struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ unsigned long nr;
+ struct ext4_sb_info *sbi;
+
+ sbi = container_of(shrink, struct ext4_sb_info, s_es_shrinker);
+ nr = percpu_counter_read_positive(&sbi->s_extent_cache_cnt);
+ trace_ext4_es_shrink_enter(sbi->s_sb, sc->nr_to_scan, nr);
+ return nr;
+}
+
+static unsigned long ext4_es_scan(struct shrinker *shrink,
+ struct shrink_control *sc)
{
struct ext4_sb_info *sbi = container_of(shrink,
struct ext4_sb_info, s_es_shrinker);
@@ -1022,9 +1037,8 @@
nr_shrunk = __ext4_es_shrink(sbi, nr_to_scan, NULL);
- ret = percpu_counter_read_positive(&sbi->s_extent_cache_cnt);
trace_ext4_es_shrink_exit(sbi->s_sb, nr_shrunk, ret);
- return ret;
+ return nr_shrunk;
}
void ext4_es_register_shrinker(struct ext4_sb_info *sbi)
@@ -1032,7 +1046,8 @@
INIT_LIST_HEAD(&sbi->s_es_lru);
spin_lock_init(&sbi->s_es_lru_lock);
sbi->s_es_last_sorted = 0;
- sbi->s_es_shrinker.shrink = ext4_es_shrink;
+ sbi->s_es_shrinker.scan_objects = ext4_es_scan;
+ sbi->s_es_shrinker.count_objects = ext4_es_count;
sbi->s_es_shrinker.seeks = DEFAULT_SEEKS;
register_shrinker(&sbi->s_es_shrinker);
}
@@ -1076,7 +1091,7 @@
struct ext4_es_tree *tree = &ei->i_es_tree;
struct rb_node *node;
struct extent_status *es;
- int nr_shrunk = 0;
+ unsigned long nr_shrunk = 0;
static DEFINE_RATELIMIT_STATE(_rs, DEFAULT_RATELIMIT_INTERVAL,
DEFAULT_RATELIMIT_BURST);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index c79fd7d..0d424d7 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4587,7 +4587,6 @@
if (attr->ia_valid & ATTR_SIZE && attr->ia_size != inode->i_size) {
handle_t *handle;
- loff_t oldsize = inode->i_size;
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
@@ -4650,7 +4649,7 @@
* Truncate pagecache after we've waited for commit
* in data=journal mode to make pages freeable.
*/
- truncate_pagecache(inode, oldsize, inode->i_size);
+ truncate_pagecache(inode, inode->i_size);
}
/*
* We want to call ext4_truncate() even if attr->ia_size ==
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 11b51bb..0062da2 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -147,7 +147,7 @@
struct inode *inode = mapping->host;
if (to > inode->i_size) {
- truncate_pagecache(inode, to, inode->i_size);
+ truncate_pagecache(inode, inode->i_size);
fat_truncate_blocks(inode, inode->i_size);
}
}
diff --git a/fs/file_table.c b/fs/file_table.c
index 322cd37..abdd15a 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -311,8 +311,7 @@
return;
/*
* After this task has run exit_task_work(),
- * task_work_add() will fail. free_ipc_ns()->
- * shm_destroy() can do this. Fall through to delayed
+ * task_work_add() will fail. Fall through to delayed
* fput to avoid leaking *file.
*/
}
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 68851ff..30f6f27 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -723,7 +723,7 @@
return wrote;
}
-long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages,
+static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages,
enum wb_reason reason)
{
struct wb_writeback_work work = {
@@ -1049,10 +1049,8 @@
{
struct backing_dev_info *bdi;
- if (!nr_pages) {
- nr_pages = global_page_state(NR_FILE_DIRTY) +
- global_page_state(NR_UNSTABLE_NFS);
- }
+ if (!nr_pages)
+ nr_pages = get_nr_dirty_pages();
rcu_read_lock();
list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) {
@@ -1173,6 +1171,8 @@
bool wakeup_bdi = false;
bdi = inode_to_bdi(inode);
+ spin_unlock(&inode->i_lock);
+ spin_lock(&bdi->wb.list_lock);
if (bdi_cap_writeback_dirty(bdi)) {
WARN(!test_bit(BDI_registered, &bdi->state),
"bdi-%s not registered\n", bdi->name);
@@ -1187,8 +1187,6 @@
wakeup_bdi = true;
}
- spin_unlock(&inode->i_lock);
- spin_lock(&bdi->wb.list_lock);
inode->dirtied_when = jiffies;
list_move(&inode->i_wb_list, &bdi->wb.b_dirty);
spin_unlock(&bdi->wb.list_lock);
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
index 8702b73..73899c1 100644
--- a/fs/fscache/page.c
+++ b/fs/fscache/page.c
@@ -913,7 +913,7 @@
(1 << FSCACHE_OP_WAITING) |
(1 << FSCACHE_OP_UNUSE_COOKIE);
- ret = radix_tree_preload(gfp & ~__GFP_HIGHMEM);
+ ret = radix_tree_maybe_preload(gfp & ~__GFP_HIGHMEM);
if (ret < 0)
goto nomem_free;
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 3ac9108..62b43b5 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1678,7 +1678,7 @@
* FUSE_NOWRITE, otherwise fuse_launder_page() would deadlock.
*/
if (S_ISREG(inode->i_mode) && oldsize != outarg.attr.size) {
- truncate_pagecache(inode, oldsize, outarg.attr.size);
+ truncate_pagecache(inode, outarg.attr.size);
invalidate_inode_pages2(inode->i_mapping);
}
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index e0fe703..a8ce6da 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -218,7 +218,7 @@
bool inval = false;
if (oldsize != attr->size) {
- truncate_pagecache(inode, oldsize, attr->size);
+ truncate_pagecache(inode, attr->size);
inval = true;
} else if (fc->auto_inval_data) {
struct timespec new_mtime = {
@@ -930,7 +930,7 @@
fc->bdi.name = "fuse";
fc->bdi.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
/* fuse does it's own writeback accounting */
- fc->bdi.capabilities = BDI_CAP_NO_ACCT_WB;
+ fc->bdi.capabilities = BDI_CAP_NO_ACCT_WB | BDI_CAP_STRICTLIMIT;
err = bdi_init(&fc->bdi);
if (err)
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 5e2f56f..62a65fc 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -1016,7 +1016,7 @@
chunk = oldsize - newsize;
if (chunk > max_chunk)
chunk = max_chunk;
- truncate_pagecache(inode, oldsize, oldsize - chunk);
+ truncate_pagecache(inode, oldsize - chunk);
oldsize -= chunk;
gfs2_trans_end(sdp);
error = gfs2_trans_begin(sdp, RES_DINODE, GFS2_JTRUNC_REVOKES);
@@ -1067,7 +1067,7 @@
if (journaled)
error = gfs2_journaled_truncate(inode, oldsize, newsize);
else
- truncate_pagecache(inode, oldsize, newsize);
+ truncate_pagecache(inode, newsize);
if (error) {
brelse(dibh);
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 722329c..c2f41b4 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1427,21 +1427,22 @@
* gfs2_dispose_glock_lru() above.
*/
-static void gfs2_scan_glock_lru(int nr)
+static long gfs2_scan_glock_lru(int nr)
{
struct gfs2_glock *gl;
LIST_HEAD(skipped);
LIST_HEAD(dispose);
+ long freed = 0;
spin_lock(&lru_lock);
- while(nr && !list_empty(&lru_list)) {
+ while ((nr-- >= 0) && !list_empty(&lru_list)) {
gl = list_entry(lru_list.next, struct gfs2_glock, gl_lru);
/* Test for being demotable */
if (!test_and_set_bit(GLF_LOCK, &gl->gl_flags)) {
list_move(&gl->gl_lru, &dispose);
atomic_dec(&lru_count);
- nr--;
+ freed++;
continue;
}
@@ -1451,23 +1452,28 @@
if (!list_empty(&dispose))
gfs2_dispose_glock_lru(&dispose);
spin_unlock(&lru_lock);
+
+ return freed;
}
-static int gfs2_shrink_glock_memory(struct shrinker *shrink,
- struct shrink_control *sc)
+static unsigned long gfs2_glock_shrink_scan(struct shrinker *shrink,
+ struct shrink_control *sc)
{
- if (sc->nr_to_scan) {
- if (!(sc->gfp_mask & __GFP_FS))
- return -1;
- gfs2_scan_glock_lru(sc->nr_to_scan);
- }
+ if (!(sc->gfp_mask & __GFP_FS))
+ return SHRINK_STOP;
+ return gfs2_scan_glock_lru(sc->nr_to_scan);
+}
- return (atomic_read(&lru_count) / 100) * sysctl_vfs_cache_pressure;
+static unsigned long gfs2_glock_shrink_count(struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ return vfs_pressure_ratio(atomic_read(&lru_count));
}
static struct shrinker glock_shrinker = {
- .shrink = gfs2_shrink_glock_memory,
.seeks = DEFAULT_SEEKS,
+ .count_objects = gfs2_glock_shrink_count,
+ .scan_objects = gfs2_glock_shrink_scan,
};
/**
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index 7b0f504..351586e 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -32,7 +32,8 @@
struct workqueue_struct *gfs2_control_wq;
static struct shrinker qd_shrinker = {
- .shrink = gfs2_shrink_qd_memory,
+ .count_objects = gfs2_qd_shrink_count,
+ .scan_objects = gfs2_qd_shrink_scan,
.seeks = DEFAULT_SEEKS,
};
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 3768c2f..db44135 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -75,17 +75,16 @@
static atomic_t qd_lru_count = ATOMIC_INIT(0);
static DEFINE_SPINLOCK(qd_lru_lock);
-int gfs2_shrink_qd_memory(struct shrinker *shrink, struct shrink_control *sc)
+unsigned long gfs2_qd_shrink_scan(struct shrinker *shrink,
+ struct shrink_control *sc)
{
struct gfs2_quota_data *qd;
struct gfs2_sbd *sdp;
int nr_to_scan = sc->nr_to_scan;
-
- if (nr_to_scan == 0)
- goto out;
+ long freed = 0;
if (!(sc->gfp_mask & __GFP_FS))
- return -1;
+ return SHRINK_STOP;
spin_lock(&qd_lru_lock);
while (nr_to_scan && !list_empty(&qd_lru_list)) {
@@ -110,11 +109,16 @@
kmem_cache_free(gfs2_quotad_cachep, qd);
spin_lock(&qd_lru_lock);
nr_to_scan--;
+ freed++;
}
spin_unlock(&qd_lru_lock);
+ return freed;
+}
-out:
- return (atomic_read(&qd_lru_count) * sysctl_vfs_cache_pressure) / 100;
+unsigned long gfs2_qd_shrink_count(struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ return vfs_pressure_ratio(atomic_read(&qd_lru_count));
}
static u64 qd2index(struct gfs2_quota_data *qd)
diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h
index 4f5e6e4..0f64d9d 100644
--- a/fs/gfs2/quota.h
+++ b/fs/gfs2/quota.h
@@ -53,8 +53,10 @@
return ret;
}
-extern int gfs2_shrink_qd_memory(struct shrinker *shrink,
- struct shrink_control *sc);
+extern unsigned long gfs2_qd_shrink_count(struct shrinker *shrink,
+ struct shrink_control *sc);
+extern unsigned long gfs2_qd_shrink_scan(struct shrinker *shrink,
+ struct shrink_control *sc);
extern const struct quotactl_ops gfs2_quotactl_ops;
#endif /* __QUOTA_DOT_H__ */
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index f9299d8..380ab31 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -41,7 +41,7 @@
struct inode *inode = mapping->host;
if (to > inode->i_size) {
- truncate_pagecache(inode, to, inode->i_size);
+ truncate_pagecache(inode, inode->i_size);
hfs_file_truncate(inode);
}
}
diff --git a/fs/hfsplus/Kconfig b/fs/hfsplus/Kconfig
index a633718..24bc20f 100644
--- a/fs/hfsplus/Kconfig
+++ b/fs/hfsplus/Kconfig
@@ -11,3 +11,21 @@
MacOS 8. It includes all Mac specific filesystem data such as
data forks and creator codes, but it also has several UNIX
style features such as file ownership and permissions.
+
+config HFSPLUS_FS_POSIX_ACL
+ bool "HFS+ POSIX Access Control Lists"
+ depends on HFSPLUS_FS
+ select FS_POSIX_ACL
+ help
+ POSIX Access Control Lists (ACLs) support permissions for users and
+ groups beyond the owner/group/world scheme.
+
+ To learn more about Access Control Lists, visit the POSIX ACLs for
+ Linux website <http://acl.bestbits.at/>.
+
+ It needs to understand that POSIX ACLs are treated only under
+ Linux. POSIX ACLs doesn't mean something under Mac OS X.
+ Mac OS X beginning with version 10.4 ("Tiger") support NFSv4 ACLs,
+ which are part of the NFSv4 standard.
+
+ If you don't know what Access Control Lists are, say N
diff --git a/fs/hfsplus/Makefile b/fs/hfsplus/Makefile
index 09d278b..683fca2 100644
--- a/fs/hfsplus/Makefile
+++ b/fs/hfsplus/Makefile
@@ -7,3 +7,5 @@
hfsplus-objs := super.o options.o inode.o ioctl.o extents.o catalog.o dir.o btree.o \
bnode.o brec.o bfind.o tables.o unicode.o wrapper.o bitmap.o part_tbl.o \
attributes.o xattr.o xattr_user.o xattr_security.o xattr_trusted.o
+
+hfsplus-$(CONFIG_HFSPLUS_FS_POSIX_ACL) += posix_acl.o
diff --git a/fs/hfsplus/acl.h b/fs/hfsplus/acl.h
new file mode 100644
index 0000000..07c0d49
--- /dev/null
+++ b/fs/hfsplus/acl.h
@@ -0,0 +1,30 @@
+/*
+ * linux/fs/hfsplus/acl.h
+ *
+ * Vyacheslav Dubeyko <slava@dubeyko.com>
+ *
+ * Handler for Posix Access Control Lists (ACLs) support.
+ */
+
+#include <linux/posix_acl_xattr.h>
+
+#ifdef CONFIG_HFSPLUS_FS_POSIX_ACL
+
+/* posix_acl.c */
+struct posix_acl *hfsplus_get_posix_acl(struct inode *inode, int type);
+extern int hfsplus_posix_acl_chmod(struct inode *);
+extern int hfsplus_init_posix_acl(struct inode *, struct inode *);
+
+#else /* CONFIG_HFSPLUS_FS_POSIX_ACL */
+#define hfsplus_get_posix_acl NULL
+
+static inline int hfsplus_posix_acl_chmod(struct inode *inode)
+{
+ return 0;
+}
+
+static inline int hfsplus_init_posix_acl(struct inode *inode, struct inode *dir)
+{
+ return 0;
+}
+#endif /* CONFIG_HFSPLUS_FS_POSIX_ACL */
diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
index d8ce4bd..4a4fea0 100644
--- a/fs/hfsplus/dir.c
+++ b/fs/hfsplus/dir.c
@@ -16,6 +16,7 @@
#include "hfsplus_fs.h"
#include "hfsplus_raw.h"
#include "xattr.h"
+#include "acl.h"
static inline void hfsplus_instantiate(struct dentry *dentry,
struct inode *inode, u32 cnid)
@@ -529,6 +530,9 @@
.getxattr = generic_getxattr,
.listxattr = hfsplus_listxattr,
.removexattr = hfsplus_removexattr,
+#ifdef CONFIG_HFSPLUS_FS_POSIX_ACL
+ .get_acl = hfsplus_get_posix_acl,
+#endif
};
const struct file_operations hfsplus_dir_operations = {
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index ede7931..2b9cd016 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -30,6 +30,7 @@
#define DBG_EXTENT 0x00000020
#define DBG_BITMAP 0x00000040
#define DBG_ATTR_MOD 0x00000080
+#define DBG_ACL_MOD 0x00000100
#if 0
#define DBG_MASK (DBG_EXTENT|DBG_INODE|DBG_BNODE_MOD)
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index f833d35..37213d0 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -19,6 +19,7 @@
#include "hfsplus_fs.h"
#include "hfsplus_raw.h"
#include "xattr.h"
+#include "acl.h"
static int hfsplus_readpage(struct file *file, struct page *page)
{
@@ -35,7 +36,7 @@
struct inode *inode = mapping->host;
if (to > inode->i_size) {
- truncate_pagecache(inode, to, inode->i_size);
+ truncate_pagecache(inode, inode->i_size);
hfsplus_file_truncate(inode);
}
}
@@ -316,6 +317,13 @@
setattr_copy(inode, attr);
mark_inode_dirty(inode);
+
+ if (attr->ia_valid & ATTR_MODE) {
+ error = hfsplus_posix_acl_chmod(inode);
+ if (unlikely(error))
+ return error;
+ }
+
return 0;
}
@@ -383,6 +391,9 @@
.getxattr = generic_getxattr,
.listxattr = hfsplus_listxattr,
.removexattr = hfsplus_removexattr,
+#ifdef CONFIG_HFSPLUS_FS_POSIX_ACL
+ .get_acl = hfsplus_get_posix_acl,
+#endif
};
static const struct file_operations hfsplus_file_operations = {
diff --git a/fs/hfsplus/posix_acl.c b/fs/hfsplus/posix_acl.c
new file mode 100644
index 0000000..b609cc1
--- /dev/null
+++ b/fs/hfsplus/posix_acl.c
@@ -0,0 +1,274 @@
+/*
+ * linux/fs/hfsplus/posix_acl.c
+ *
+ * Vyacheslav Dubeyko <slava@dubeyko.com>
+ *
+ * Handler for Posix Access Control Lists (ACLs) support.
+ */
+
+#include "hfsplus_fs.h"
+#include "xattr.h"
+#include "acl.h"
+
+struct posix_acl *hfsplus_get_posix_acl(struct inode *inode, int type)
+{
+ struct posix_acl *acl;
+ char *xattr_name;
+ char *value = NULL;
+ ssize_t size;
+
+ acl = get_cached_acl(inode, type);
+ if (acl != ACL_NOT_CACHED)
+ return acl;
+
+ switch (type) {
+ case ACL_TYPE_ACCESS:
+ xattr_name = POSIX_ACL_XATTR_ACCESS;
+ break;
+ case ACL_TYPE_DEFAULT:
+ xattr_name = POSIX_ACL_XATTR_DEFAULT;
+ break;
+ default:
+ return ERR_PTR(-EINVAL);
+ }
+
+ size = __hfsplus_getxattr(inode, xattr_name, NULL, 0);
+
+ if (size > 0) {
+ value = (char *)hfsplus_alloc_attr_entry();
+ if (unlikely(!value))
+ return ERR_PTR(-ENOMEM);
+ size = __hfsplus_getxattr(inode, xattr_name, value, size);
+ }
+
+ if (size > 0)
+ acl = posix_acl_from_xattr(&init_user_ns, value, size);
+ else if (size == -ENODATA)
+ acl = NULL;
+ else
+ acl = ERR_PTR(size);
+
+ hfsplus_destroy_attr_entry((hfsplus_attr_entry *)value);
+
+ if (!IS_ERR(acl))
+ set_cached_acl(inode, type, acl);
+
+ return acl;
+}
+
+static int hfsplus_set_posix_acl(struct inode *inode,
+ int type,
+ struct posix_acl *acl)
+{
+ int err;
+ char *xattr_name;
+ size_t size = 0;
+ char *value = NULL;
+
+ if (S_ISLNK(inode->i_mode))
+ return -EOPNOTSUPP;
+
+ switch (type) {
+ case ACL_TYPE_ACCESS:
+ xattr_name = POSIX_ACL_XATTR_ACCESS;
+ if (acl) {
+ err = posix_acl_equiv_mode(acl, &inode->i_mode);
+ if (err < 0)
+ return err;
+ }
+ err = 0;
+ break;
+
+ case ACL_TYPE_DEFAULT:
+ xattr_name = POSIX_ACL_XATTR_DEFAULT;
+ if (!S_ISDIR(inode->i_mode))
+ return acl ? -EACCES : 0;
+ break;
+
+ default:
+ return -EINVAL;
+ }
+
+ if (acl) {
+ size = posix_acl_xattr_size(acl->a_count);
+ if (unlikely(size > HFSPLUS_MAX_INLINE_DATA_SIZE))
+ return -ENOMEM;
+ value = (char *)hfsplus_alloc_attr_entry();
+ if (unlikely(!value))
+ return -ENOMEM;
+ err = posix_acl_to_xattr(&init_user_ns, acl, value, size);
+ if (unlikely(err < 0))
+ goto end_set_acl;
+ }
+
+ err = __hfsplus_setxattr(inode, xattr_name, value, size, 0);
+
+end_set_acl:
+ hfsplus_destroy_attr_entry((hfsplus_attr_entry *)value);
+
+ if (!err)
+ set_cached_acl(inode, type, acl);
+
+ return err;
+}
+
+int hfsplus_init_posix_acl(struct inode *inode, struct inode *dir)
+{
+ int err = 0;
+ struct posix_acl *acl = NULL;
+
+ hfs_dbg(ACL_MOD,
+ "[%s]: ino %lu, dir->ino %lu\n",
+ __func__, inode->i_ino, dir->i_ino);
+
+ if (S_ISLNK(inode->i_mode))
+ return 0;
+
+ acl = hfsplus_get_posix_acl(dir, ACL_TYPE_DEFAULT);
+ if (IS_ERR(acl))
+ return PTR_ERR(acl);
+
+ if (acl) {
+ if (S_ISDIR(inode->i_mode)) {
+ err = hfsplus_set_posix_acl(inode,
+ ACL_TYPE_DEFAULT,
+ acl);
+ if (unlikely(err))
+ goto init_acl_cleanup;
+ }
+
+ err = posix_acl_create(&acl, GFP_NOFS, &inode->i_mode);
+ if (unlikely(err < 0))
+ return err;
+
+ if (err > 0)
+ err = hfsplus_set_posix_acl(inode,
+ ACL_TYPE_ACCESS,
+ acl);
+ } else
+ inode->i_mode &= ~current_umask();
+
+init_acl_cleanup:
+ posix_acl_release(acl);
+ return err;
+}
+
+int hfsplus_posix_acl_chmod(struct inode *inode)
+{
+ int err;
+ struct posix_acl *acl;
+
+ hfs_dbg(ACL_MOD, "[%s]: ino %lu\n", __func__, inode->i_ino);
+
+ if (S_ISLNK(inode->i_mode))
+ return -EOPNOTSUPP;
+
+ acl = hfsplus_get_posix_acl(inode, ACL_TYPE_ACCESS);
+ if (IS_ERR(acl) || !acl)
+ return PTR_ERR(acl);
+
+ err = posix_acl_chmod(&acl, GFP_KERNEL, inode->i_mode);
+ if (unlikely(err))
+ return err;
+
+ err = hfsplus_set_posix_acl(inode, ACL_TYPE_ACCESS, acl);
+ posix_acl_release(acl);
+ return err;
+}
+
+static int hfsplus_xattr_get_posix_acl(struct dentry *dentry,
+ const char *name,
+ void *buffer,
+ size_t size,
+ int type)
+{
+ int err = 0;
+ struct posix_acl *acl;
+
+ hfs_dbg(ACL_MOD,
+ "[%s]: ino %lu, buffer %p, size %zu, type %#x\n",
+ __func__, dentry->d_inode->i_ino, buffer, size, type);
+
+ if (strcmp(name, "") != 0)
+ return -EINVAL;
+
+ acl = hfsplus_get_posix_acl(dentry->d_inode, type);
+ if (IS_ERR(acl))
+ return PTR_ERR(acl);
+ if (acl == NULL)
+ return -ENODATA;
+
+ err = posix_acl_to_xattr(&init_user_ns, acl, buffer, size);
+ posix_acl_release(acl);
+
+ return err;
+}
+
+static int hfsplus_xattr_set_posix_acl(struct dentry *dentry,
+ const char *name,
+ const void *value,
+ size_t size,
+ int flags,
+ int type)
+{
+ int err = 0;
+ struct inode *inode = dentry->d_inode;
+ struct posix_acl *acl = NULL;
+
+ hfs_dbg(ACL_MOD,
+ "[%s]: ino %lu, value %p, size %zu, flags %#x, type %#x\n",
+ __func__, inode->i_ino, value, size, flags, type);
+
+ if (strcmp(name, "") != 0)
+ return -EINVAL;
+
+ if (!inode_owner_or_capable(inode))
+ return -EPERM;
+
+ if (value) {
+ acl = posix_acl_from_xattr(&init_user_ns, value, size);
+ if (IS_ERR(acl))
+ return PTR_ERR(acl);
+ else if (acl) {
+ err = posix_acl_valid(acl);
+ if (err)
+ goto end_xattr_set_acl;
+ }
+ }
+
+ err = hfsplus_set_posix_acl(inode, type, acl);
+
+end_xattr_set_acl:
+ posix_acl_release(acl);
+ return err;
+}
+
+static size_t hfsplus_xattr_list_posix_acl(struct dentry *dentry,
+ char *list,
+ size_t list_size,
+ const char *name,
+ size_t name_len,
+ int type)
+{
+ /*
+ * This method is not used.
+ * It is used hfsplus_listxattr() instead of generic_listxattr().
+ */
+ return -EOPNOTSUPP;
+}
+
+const struct xattr_handler hfsplus_xattr_acl_access_handler = {
+ .prefix = POSIX_ACL_XATTR_ACCESS,
+ .flags = ACL_TYPE_ACCESS,
+ .list = hfsplus_xattr_list_posix_acl,
+ .get = hfsplus_xattr_get_posix_acl,
+ .set = hfsplus_xattr_set_posix_acl,
+};
+
+const struct xattr_handler hfsplus_xattr_acl_default_handler = {
+ .prefix = POSIX_ACL_XATTR_DEFAULT,
+ .flags = ACL_TYPE_DEFAULT,
+ .list = hfsplus_xattr_list_posix_acl,
+ .get = hfsplus_xattr_get_posix_acl,
+ .set = hfsplus_xattr_set_posix_acl,
+};
diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c
index f6634615..bd8471f 100644
--- a/fs/hfsplus/xattr.c
+++ b/fs/hfsplus/xattr.c
@@ -8,11 +8,16 @@
#include "hfsplus_fs.h"
#include "xattr.h"
+#include "acl.h"
const struct xattr_handler *hfsplus_xattr_handlers[] = {
&hfsplus_xattr_osx_handler,
&hfsplus_xattr_user_handler,
&hfsplus_xattr_trusted_handler,
+#ifdef CONFIG_HFSPLUS_FS_POSIX_ACL
+ &hfsplus_xattr_acl_access_handler,
+ &hfsplus_xattr_acl_default_handler,
+#endif
&hfsplus_xattr_security_handler,
NULL
};
@@ -46,11 +51,58 @@
return true;
}
+static int can_set_system_xattr(struct inode *inode, const char *name,
+ const void *value, size_t size)
+{
+#ifdef CONFIG_HFSPLUS_FS_POSIX_ACL
+ struct posix_acl *acl;
+ int err;
+
+ if (!inode_owner_or_capable(inode))
+ return -EPERM;
+
+ /*
+ * POSIX_ACL_XATTR_ACCESS is tied to i_mode
+ */
+ if (strcmp(name, POSIX_ACL_XATTR_ACCESS) == 0) {
+ acl = posix_acl_from_xattr(&init_user_ns, value, size);
+ if (IS_ERR(acl))
+ return PTR_ERR(acl);
+ if (acl) {
+ err = posix_acl_equiv_mode(acl, &inode->i_mode);
+ posix_acl_release(acl);
+ if (err < 0)
+ return err;
+ mark_inode_dirty(inode);
+ }
+ /*
+ * We're changing the ACL. Get rid of the cached one
+ */
+ forget_cached_acl(inode, ACL_TYPE_ACCESS);
+
+ return 0;
+ } else if (strcmp(name, POSIX_ACL_XATTR_DEFAULT) == 0) {
+ acl = posix_acl_from_xattr(&init_user_ns, value, size);
+ if (IS_ERR(acl))
+ return PTR_ERR(acl);
+ posix_acl_release(acl);
+
+ /*
+ * We're changing the default ACL. Get rid of the cached one
+ */
+ forget_cached_acl(inode, ACL_TYPE_DEFAULT);
+
+ return 0;
+ }
+#endif /* CONFIG_HFSPLUS_FS_POSIX_ACL */
+ return -EOPNOTSUPP;
+}
+
static int can_set_xattr(struct inode *inode, const char *name,
const void *value, size_t value_len)
{
if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
- return -EOPNOTSUPP; /* TODO: implement ACL support */
+ return can_set_system_xattr(inode, name, value, value_len);
if (!strncmp(name, XATTR_MAC_OSX_PREFIX, XATTR_MAC_OSX_PREFIX_LEN)) {
/*
@@ -253,11 +305,10 @@
return len;
}
-static ssize_t hfsplus_getxattr_finder_info(struct dentry *dentry,
+static ssize_t hfsplus_getxattr_finder_info(struct inode *inode,
void *value, size_t size)
{
ssize_t res = 0;
- struct inode *inode = dentry->d_inode;
struct hfs_find_data fd;
u16 entry_type;
u16 folder_rec_len = sizeof(struct DInfo) + sizeof(struct DXInfo);
@@ -304,10 +355,9 @@
return res;
}
-ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name,
+ssize_t __hfsplus_getxattr(struct inode *inode, const char *name,
void *value, size_t size)
{
- struct inode *inode = dentry->d_inode;
struct hfs_find_data fd;
hfsplus_attr_entry *entry;
__be32 xattr_record_type;
@@ -333,7 +383,7 @@
}
if (!strcmp_xattr_finder_info(name))
- return hfsplus_getxattr_finder_info(dentry, value, size);
+ return hfsplus_getxattr_finder_info(inode, value, size);
if (!HFSPLUS_SB(inode->i_sb)->attr_tree)
return -EOPNOTSUPP;
diff --git a/fs/hfsplus/xattr.h b/fs/hfsplus/xattr.h
index 847b695..841b569 100644
--- a/fs/hfsplus/xattr.h
+++ b/fs/hfsplus/xattr.h
@@ -14,8 +14,8 @@
extern const struct xattr_handler hfsplus_xattr_osx_handler;
extern const struct xattr_handler hfsplus_xattr_user_handler;
extern const struct xattr_handler hfsplus_xattr_trusted_handler;
-/*extern const struct xattr_handler hfsplus_xattr_acl_access_handler;*/
-/*extern const struct xattr_handler hfsplus_xattr_acl_default_handler;*/
+extern const struct xattr_handler hfsplus_xattr_acl_access_handler;
+extern const struct xattr_handler hfsplus_xattr_acl_default_handler;
extern const struct xattr_handler hfsplus_xattr_security_handler;
extern const struct xattr_handler *hfsplus_xattr_handlers[];
@@ -29,9 +29,17 @@
return __hfsplus_setxattr(dentry->d_inode, name, value, size, flags);
}
-ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name,
+ssize_t __hfsplus_getxattr(struct inode *inode, const char *name,
void *value, size_t size);
+static inline ssize_t hfsplus_getxattr(struct dentry *dentry,
+ const char *name,
+ void *value,
+ size_t size)
+{
+ return __hfsplus_getxattr(dentry->d_inode, name, value, size);
+}
+
ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size);
int hfsplus_removexattr(struct dentry *dentry, const char *name);
@@ -39,22 +47,7 @@
int hfsplus_init_security(struct inode *inode, struct inode *dir,
const struct qstr *qstr);
-static inline int hfsplus_init_acl(struct inode *inode, struct inode *dir)
-{
- /*TODO: implement*/
- return 0;
-}
-
-static inline int hfsplus_init_inode_security(struct inode *inode,
- struct inode *dir,
- const struct qstr *qstr)
-{
- int err;
-
- err = hfsplus_init_acl(inode, dir);
- if (!err)
- err = hfsplus_init_security(inode, dir, qstr);
- return err;
-}
+int hfsplus_init_inode_security(struct inode *inode, struct inode *dir,
+ const struct qstr *qstr);
#endif
diff --git a/fs/hfsplus/xattr_security.c b/fs/hfsplus/xattr_security.c
index 83b842f..0072276 100644
--- a/fs/hfsplus/xattr_security.c
+++ b/fs/hfsplus/xattr_security.c
@@ -9,6 +9,7 @@
#include <linux/security.h>
#include "hfsplus_fs.h"
#include "xattr.h"
+#include "acl.h"
static int hfsplus_security_getxattr(struct dentry *dentry, const char *name,
void *buffer, size_t size, int type)
@@ -96,6 +97,18 @@
&hfsplus_initxattrs, NULL);
}
+int hfsplus_init_inode_security(struct inode *inode,
+ struct inode *dir,
+ const struct qstr *qstr)
+{
+ int err;
+
+ err = hfsplus_init_posix_acl(inode, dir);
+ if (!err)
+ err = hfsplus_init_security(inode, dir, qstr);
+ return err;
+}
+
const struct xattr_handler hfsplus_xattr_security_handler = {
.prefix = XATTR_SECURITY_PREFIX,
.list = hfsplus_security_listxattr,
diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c
index 4e9dabc..67c1a61 100644
--- a/fs/hpfs/file.c
+++ b/fs/hpfs/file.c
@@ -138,7 +138,7 @@
hpfs_lock(inode->i_sb);
if (to > inode->i_size) {
- truncate_pagecache(inode, to, inode->i_size);
+ truncate_pagecache(inode, inode->i_size);
hpfs_truncate(inode);
}
diff --git a/fs/inode.c b/fs/inode.c
index 93a0625..b33ba8e 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -17,6 +17,7 @@
#include <linux/prefetch.h>
#include <linux/buffer_head.h> /* for inode_has_buffers */
#include <linux/ratelimit.h>
+#include <linux/list_lru.h>
#include "internal.h"
/*
@@ -24,7 +25,7 @@
*
* inode->i_lock protects:
* inode->i_state, inode->i_hash, __iget()
- * inode->i_sb->s_inode_lru_lock protects:
+ * Inode LRU list locks protect:
* inode->i_sb->s_inode_lru, inode->i_lru
* inode_sb_list_lock protects:
* sb->s_inodes, inode->i_sb_list
@@ -37,7 +38,7 @@
*
* inode_sb_list_lock
* inode->i_lock
- * inode->i_sb->s_inode_lru_lock
+ * Inode LRU list locks
*
* bdi->wb.list_lock
* inode->i_lock
@@ -70,33 +71,33 @@
*/
struct inodes_stat_t inodes_stat;
-static DEFINE_PER_CPU(unsigned int, nr_inodes);
-static DEFINE_PER_CPU(unsigned int, nr_unused);
+static DEFINE_PER_CPU(unsigned long, nr_inodes);
+static DEFINE_PER_CPU(unsigned long, nr_unused);
static struct kmem_cache *inode_cachep __read_mostly;
-static int get_nr_inodes(void)
+static long get_nr_inodes(void)
{
int i;
- int sum = 0;
+ long sum = 0;
for_each_possible_cpu(i)
sum += per_cpu(nr_inodes, i);
return sum < 0 ? 0 : sum;
}
-static inline int get_nr_inodes_unused(void)
+static inline long get_nr_inodes_unused(void)
{
int i;
- int sum = 0;
+ long sum = 0;
for_each_possible_cpu(i)
sum += per_cpu(nr_unused, i);
return sum < 0 ? 0 : sum;
}
-int get_nr_dirty_inodes(void)
+long get_nr_dirty_inodes(void)
{
/* not actually dirty inodes, but a wild approximation */
- int nr_dirty = get_nr_inodes() - get_nr_inodes_unused();
+ long nr_dirty = get_nr_inodes() - get_nr_inodes_unused();
return nr_dirty > 0 ? nr_dirty : 0;
}
@@ -109,7 +110,7 @@
{
inodes_stat.nr_inodes = get_nr_inodes();
inodes_stat.nr_unused = get_nr_inodes_unused();
- return proc_dointvec(table, write, buffer, lenp, ppos);
+ return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
}
#endif
@@ -401,13 +402,8 @@
static void inode_lru_list_add(struct inode *inode)
{
- spin_lock(&inode->i_sb->s_inode_lru_lock);
- if (list_empty(&inode->i_lru)) {
- list_add(&inode->i_lru, &inode->i_sb->s_inode_lru);
- inode->i_sb->s_nr_inodes_unused++;
+ if (list_lru_add(&inode->i_sb->s_inode_lru, &inode->i_lru))
this_cpu_inc(nr_unused);
- }
- spin_unlock(&inode->i_sb->s_inode_lru_lock);
}
/*
@@ -425,13 +421,9 @@
static void inode_lru_list_del(struct inode *inode)
{
- spin_lock(&inode->i_sb->s_inode_lru_lock);
- if (!list_empty(&inode->i_lru)) {
- list_del_init(&inode->i_lru);
- inode->i_sb->s_nr_inodes_unused--;
+
+ if (list_lru_del(&inode->i_sb->s_inode_lru, &inode->i_lru))
this_cpu_dec(nr_unused);
- }
- spin_unlock(&inode->i_sb->s_inode_lru_lock);
}
/**
@@ -675,24 +667,8 @@
return busy;
}
-static int can_unuse(struct inode *inode)
-{
- if (inode->i_state & ~I_REFERENCED)
- return 0;
- if (inode_has_buffers(inode))
- return 0;
- if (atomic_read(&inode->i_count))
- return 0;
- if (inode->i_data.nrpages)
- return 0;
- return 1;
-}
-
/*
- * Walk the superblock inode LRU for freeable inodes and attempt to free them.
- * This is called from the superblock shrinker function with a number of inodes
- * to trim from the LRU. Inodes to be freed are moved to a temporary list and
- * then are freed outside inode_lock by dispose_list().
+ * Isolate the inode from the LRU in preparation for freeing it.
*
* Any inodes which are pinned purely because of attached pagecache have their
* pagecache removed. If the inode has metadata buffers attached to
@@ -706,89 +682,82 @@
* LRU does not have strict ordering. Hence we don't want to reclaim inodes
* with this flag set because they are the inodes that are out of order.
*/
-void prune_icache_sb(struct super_block *sb, int nr_to_scan)
+static enum lru_status
+inode_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
+{
+ struct list_head *freeable = arg;
+ struct inode *inode = container_of(item, struct inode, i_lru);
+
+ /*
+ * we are inverting the lru lock/inode->i_lock here, so use a trylock.
+ * If we fail to get the lock, just skip it.
+ */
+ if (!spin_trylock(&inode->i_lock))
+ return LRU_SKIP;
+
+ /*
+ * Referenced or dirty inodes are still in use. Give them another pass
+ * through the LRU as we canot reclaim them now.
+ */
+ if (atomic_read(&inode->i_count) ||
+ (inode->i_state & ~I_REFERENCED)) {
+ list_del_init(&inode->i_lru);
+ spin_unlock(&inode->i_lock);
+ this_cpu_dec(nr_unused);
+ return LRU_REMOVED;
+ }
+
+ /* recently referenced inodes get one more pass */
+ if (inode->i_state & I_REFERENCED) {
+ inode->i_state &= ~I_REFERENCED;
+ spin_unlock(&inode->i_lock);
+ return LRU_ROTATE;
+ }
+
+ if (inode_has_buffers(inode) || inode->i_data.nrpages) {
+ __iget(inode);
+ spin_unlock(&inode->i_lock);
+ spin_unlock(lru_lock);
+ if (remove_inode_buffers(inode)) {
+ unsigned long reap;
+ reap = invalidate_mapping_pages(&inode->i_data, 0, -1);
+ if (current_is_kswapd())
+ __count_vm_events(KSWAPD_INODESTEAL, reap);
+ else
+ __count_vm_events(PGINODESTEAL, reap);
+ if (current->reclaim_state)
+ current->reclaim_state->reclaimed_slab += reap;
+ }
+ iput(inode);
+ spin_lock(lru_lock);
+ return LRU_RETRY;
+ }
+
+ WARN_ON(inode->i_state & I_NEW);
+ inode->i_state |= I_FREEING;
+ list_move(&inode->i_lru, freeable);
+ spin_unlock(&inode->i_lock);
+
+ this_cpu_dec(nr_unused);
+ return LRU_REMOVED;
+}
+
+/*
+ * Walk the superblock inode LRU for freeable inodes and attempt to free them.
+ * This is called from the superblock shrinker function with a number of inodes
+ * to trim from the LRU. Inodes to be freed are moved to a temporary list and
+ * then are freed outside inode_lock by dispose_list().
+ */
+long prune_icache_sb(struct super_block *sb, unsigned long nr_to_scan,
+ int nid)
{
LIST_HEAD(freeable);
- int nr_scanned;
- unsigned long reap = 0;
+ long freed;
- spin_lock(&sb->s_inode_lru_lock);
- for (nr_scanned = nr_to_scan; nr_scanned >= 0; nr_scanned--) {
- struct inode *inode;
-
- if (list_empty(&sb->s_inode_lru))
- break;
-
- inode = list_entry(sb->s_inode_lru.prev, struct inode, i_lru);
-
- /*
- * we are inverting the sb->s_inode_lru_lock/inode->i_lock here,
- * so use a trylock. If we fail to get the lock, just move the
- * inode to the back of the list so we don't spin on it.
- */
- if (!spin_trylock(&inode->i_lock)) {
- list_move(&inode->i_lru, &sb->s_inode_lru);
- continue;
- }
-
- /*
- * Referenced or dirty inodes are still in use. Give them
- * another pass through the LRU as we canot reclaim them now.
- */
- if (atomic_read(&inode->i_count) ||
- (inode->i_state & ~I_REFERENCED)) {
- list_del_init(&inode->i_lru);
- spin_unlock(&inode->i_lock);
- sb->s_nr_inodes_unused--;
- this_cpu_dec(nr_unused);
- continue;
- }
-
- /* recently referenced inodes get one more pass */
- if (inode->i_state & I_REFERENCED) {
- inode->i_state &= ~I_REFERENCED;
- list_move(&inode->i_lru, &sb->s_inode_lru);
- spin_unlock(&inode->i_lock);
- continue;
- }
- if (inode_has_buffers(inode) || inode->i_data.nrpages) {
- __iget(inode);
- spin_unlock(&inode->i_lock);
- spin_unlock(&sb->s_inode_lru_lock);
- if (remove_inode_buffers(inode))
- reap += invalidate_mapping_pages(&inode->i_data,
- 0, -1);
- iput(inode);
- spin_lock(&sb->s_inode_lru_lock);
-
- if (inode != list_entry(sb->s_inode_lru.next,
- struct inode, i_lru))
- continue; /* wrong inode or list_empty */
- /* avoid lock inversions with trylock */
- if (!spin_trylock(&inode->i_lock))
- continue;
- if (!can_unuse(inode)) {
- spin_unlock(&inode->i_lock);
- continue;
- }
- }
- WARN_ON(inode->i_state & I_NEW);
- inode->i_state |= I_FREEING;
- spin_unlock(&inode->i_lock);
-
- list_move(&inode->i_lru, &freeable);
- sb->s_nr_inodes_unused--;
- this_cpu_dec(nr_unused);
- }
- if (current_is_kswapd())
- __count_vm_events(KSWAPD_INODESTEAL, reap);
- else
- __count_vm_events(PGINODESTEAL, reap);
- spin_unlock(&sb->s_inode_lru_lock);
- if (current->reclaim_state)
- current->reclaim_state->reclaimed_slab += reap;
-
+ freed = list_lru_walk_node(&sb->s_inode_lru, nid, inode_lru_isolate,
+ &freeable, &nr_to_scan);
dispose_list(&freeable);
+ return freed;
}
static void __wait_on_freeing_inode(struct inode *inode);
diff --git a/fs/internal.h b/fs/internal.h
index 2be46ea..513e0d8 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -114,6 +114,8 @@
* inode.c
*/
extern spinlock_t inode_sb_list_lock;
+extern long prune_icache_sb(struct super_block *sb, unsigned long nr_to_scan,
+ int nid);
extern void inode_add_lru(struct inode *inode);
/*
@@ -121,7 +123,7 @@
*/
extern void inode_wb_list_del(struct inode *inode);
-extern int get_nr_dirty_inodes(void);
+extern long get_nr_dirty_inodes(void);
extern void evict_inodes(struct super_block *);
extern int invalidate_inodes(struct super_block *, bool);
@@ -130,6 +132,8 @@
*/
extern struct dentry *__d_alloc(struct super_block *, const struct qstr *);
extern int d_set_mounted(struct dentry *dentry);
+extern long prune_dcache_sb(struct super_block *sb, unsigned long nr_to_scan,
+ int nid);
/*
* read_write.c
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index 730f24e..f4aab71 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -306,7 +306,7 @@
struct inode *inode = mapping->host;
if (to > inode->i_size) {
- truncate_pagecache(inode, to, inode->i_size);
+ truncate_pagecache(inode, inode->i_size);
jfs_truncate(inode);
}
}
diff --git a/fs/mbcache.c b/fs/mbcache.c
index 8c32ef3..e519e45 100644
--- a/fs/mbcache.c
+++ b/fs/mbcache.c
@@ -86,18 +86,6 @@
static LIST_HEAD(mb_cache_lru_list);
static DEFINE_SPINLOCK(mb_cache_spinlock);
-/*
- * What the mbcache registers as to get shrunk dynamically.
- */
-
-static int mb_cache_shrink_fn(struct shrinker *shrink,
- struct shrink_control *sc);
-
-static struct shrinker mb_cache_shrinker = {
- .shrink = mb_cache_shrink_fn,
- .seeks = DEFAULT_SEEKS,
-};
-
static inline int
__mb_cache_entry_is_hashed(struct mb_cache_entry *ce)
{
@@ -151,7 +139,7 @@
/*
- * mb_cache_shrink_fn() memory pressure callback
+ * mb_cache_shrink_scan() memory pressure callback
*
* This function is called by the kernel memory management when memory
* gets low.
@@ -159,17 +147,16 @@
* @shrink: (ignored)
* @sc: shrink_control passed from reclaim
*
- * Returns the number of objects which are present in the cache.
+ * Returns the number of objects freed.
*/
-static int
-mb_cache_shrink_fn(struct shrinker *shrink, struct shrink_control *sc)
+static unsigned long
+mb_cache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
{
LIST_HEAD(free_list);
- struct mb_cache *cache;
struct mb_cache_entry *entry, *tmp;
- int count = 0;
int nr_to_scan = sc->nr_to_scan;
gfp_t gfp_mask = sc->gfp_mask;
+ unsigned long freed = 0;
mb_debug("trying to free %d entries", nr_to_scan);
spin_lock(&mb_cache_spinlock);
@@ -179,19 +166,37 @@
struct mb_cache_entry, e_lru_list);
list_move_tail(&ce->e_lru_list, &free_list);
__mb_cache_entry_unhash(ce);
+ freed++;
}
+ spin_unlock(&mb_cache_spinlock);
+ list_for_each_entry_safe(entry, tmp, &free_list, e_lru_list) {
+ __mb_cache_entry_forget(entry, gfp_mask);
+ }
+ return freed;
+}
+
+static unsigned long
+mb_cache_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
+{
+ struct mb_cache *cache;
+ unsigned long count = 0;
+
+ spin_lock(&mb_cache_spinlock);
list_for_each_entry(cache, &mb_cache_list, c_cache_list) {
mb_debug("cache %s (%d)", cache->c_name,
atomic_read(&cache->c_entry_count));
count += atomic_read(&cache->c_entry_count);
}
spin_unlock(&mb_cache_spinlock);
- list_for_each_entry_safe(entry, tmp, &free_list, e_lru_list) {
- __mb_cache_entry_forget(entry, gfp_mask);
- }
- return (count / 100) * sysctl_vfs_cache_pressure;
+
+ return vfs_pressure_ratio(count);
}
+static struct shrinker mb_cache_shrinker = {
+ .count_objects = mb_cache_shrink_count,
+ .scan_objects = mb_cache_shrink_scan,
+ .seeks = DEFAULT_SEEKS,
+};
/*
* mb_cache_create() create a new cache
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index df12249..0332109 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -400,7 +400,7 @@
struct inode *inode = mapping->host;
if (to > inode->i_size) {
- truncate_pagecache(inode, to, inode->i_size);
+ truncate_pagecache(inode, inode->i_size);
minix_truncate(inode);
}
}
diff --git a/fs/namei.c b/fs/namei.c
index 409a441..0dc4cbf 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -660,29 +660,6 @@
}
}
-static __always_inline int __vfs_follow_link(struct nameidata *nd, const char *link)
-{
- int ret;
-
- if (IS_ERR(link))
- goto fail;
-
- if (*link == '/') {
- set_root(nd);
- path_put(&nd->path);
- nd->path = nd->root;
- path_get(&nd->root);
- nd->flags |= LOOKUP_JUMPED;
- }
- nd->inode = nd->path.dentry->d_inode;
-
- ret = link_path_walk(link, nd);
- return ret;
-fail:
- path_put(&nd->path);
- return PTR_ERR(link);
-}
-
static void path_put_conditional(struct path *path, struct nameidata *nd)
{
dput(path->dentry);
@@ -874,7 +851,20 @@
error = 0;
s = nd_get_link(nd);
if (s) {
- error = __vfs_follow_link(nd, s);
+ if (unlikely(IS_ERR(s))) {
+ path_put(&nd->path);
+ put_link(nd, link, *p);
+ return PTR_ERR(s);
+ }
+ if (*s == '/') {
+ set_root(nd);
+ path_put(&nd->path);
+ nd->path = nd->root;
+ path_get(&nd->root);
+ nd->flags |= LOOKUP_JUMPED;
+ }
+ nd->inode = nd->path.dentry->d_inode;
+ error = link_path_walk(s, nd);
if (unlikely(error))
put_link(nd, link, *p);
}
@@ -2271,12 +2261,15 @@
dentry = d_alloc(dir, &nd->last);
if (!dentry) {
error = -ENOMEM;
+ mutex_unlock(&dir->d_inode->i_mutex);
goto out;
}
dentry = lookup_real(dir->d_inode, dentry, nd->flags);
error = PTR_ERR(dentry);
- if (IS_ERR(dentry))
+ if (IS_ERR(dentry)) {
+ mutex_unlock(&dir->d_inode->i_mutex);
goto out;
+ }
}
mutex_unlock(&dir->d_inode->i_mutex);
@@ -4236,11 +4229,6 @@
return res;
}
-int vfs_follow_link(struct nameidata *nd, const char *link)
-{
- return __vfs_follow_link(nd, link);
-}
-
/* get the link contents into pagecache */
static char *page_getlink(struct dentry * dentry, struct page **ppage)
{
@@ -4352,7 +4340,6 @@
EXPORT_SYMBOL(inode_permission);
EXPORT_SYMBOL(unlock_rename);
EXPORT_SYMBOL(vfs_create);
-EXPORT_SYMBOL(vfs_follow_link);
EXPORT_SYMBOL(vfs_link);
EXPORT_SYMBOL(vfs_mkdir);
EXPORT_SYMBOL(vfs_mknod);
diff --git a/fs/namespace.c b/fs/namespace.c
index 25845d1..da5c494 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -17,7 +17,7 @@
#include <linux/security.h>
#include <linux/idr.h>
#include <linux/acct.h> /* acct_auto_close_mnt */
-#include <linux/ramfs.h> /* init_rootfs */
+#include <linux/init.h> /* init_rootfs */
#include <linux/fs_struct.h> /* get_fs_root et.al. */
#include <linux/fsnotify.h> /* fsnotify_vfsmount_delete */
#include <linux/uaccess.h>
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index e79bc6c..de434f3 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -2006,17 +2006,18 @@
}
}
-int nfs_access_cache_shrinker(struct shrinker *shrink,
- struct shrink_control *sc)
+unsigned long
+nfs_access_cache_scan(struct shrinker *shrink, struct shrink_control *sc)
{
LIST_HEAD(head);
struct nfs_inode *nfsi, *next;
struct nfs_access_entry *cache;
int nr_to_scan = sc->nr_to_scan;
gfp_t gfp_mask = sc->gfp_mask;
+ long freed = 0;
if ((gfp_mask & GFP_KERNEL) != GFP_KERNEL)
- return (nr_to_scan == 0) ? 0 : -1;
+ return SHRINK_STOP;
spin_lock(&nfs_access_lru_lock);
list_for_each_entry_safe(nfsi, next, &nfs_access_lru_list, access_cache_inode_lru) {
@@ -2032,6 +2033,7 @@
struct nfs_access_entry, lru);
list_move(&cache->lru, &head);
rb_erase(&cache->rb_node, &nfsi->access_cache);
+ freed++;
if (!list_empty(&nfsi->access_cache_entry_lru))
list_move_tail(&nfsi->access_cache_inode_lru,
&nfs_access_lru_list);
@@ -2046,7 +2048,13 @@
}
spin_unlock(&nfs_access_lru_lock);
nfs_access_free_list(&head);
- return (atomic_long_read(&nfs_access_nr_entries) / 100) * sysctl_vfs_cache_pressure;
+ return freed;
+}
+
+unsigned long
+nfs_access_cache_count(struct shrinker *shrink, struct shrink_control *sc)
+{
+ return vfs_pressure_ratio(atomic_long_read(&nfs_access_nr_entries));
}
static void __nfs_access_zap_cache(struct nfs_inode *nfsi, struct list_head *head)
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 0bd7a55..91ff089 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -130,7 +130,6 @@
return -EINVAL;
#else
- VM_BUG_ON(iocb->ki_left != PAGE_SIZE);
VM_BUG_ON(iocb->ki_nbytes != PAGE_SIZE);
if (rw == READ || rw == KERNEL_READ)
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 87e7976..eda8879 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -541,7 +541,6 @@
*/
static int nfs_vmtruncate(struct inode * inode, loff_t offset)
{
- loff_t oldsize;
int err;
err = inode_newsize_ok(inode, offset);
@@ -549,11 +548,10 @@
goto out;
spin_lock(&inode->i_lock);
- oldsize = inode->i_size;
i_size_write(inode, offset);
spin_unlock(&inode->i_lock);
- truncate_pagecache(inode, oldsize, offset);
+ truncate_pagecache(inode, offset);
out:
return err;
}
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index d388302c..38da8c2 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -273,8 +273,10 @@
const char *ip_addr);
/* dir.c */
-extern int nfs_access_cache_shrinker(struct shrinker *shrink,
- struct shrink_control *sc);
+extern unsigned long nfs_access_cache_count(struct shrinker *shrink,
+ struct shrink_control *sc);
+extern unsigned long nfs_access_cache_scan(struct shrinker *shrink,
+ struct shrink_control *sc);
struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int);
int nfs_create(struct inode *, struct dentry *, umode_t, bool);
int nfs_mkdir(struct inode *, struct dentry *, umode_t);
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index f520a11..28842ab 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -279,15 +279,15 @@
if (test_bit(sp4_mode, &clp->cl_sp4_flags)) {
spin_lock(&clp->cl_lock);
if (clp->cl_machine_cred != NULL)
- newcred = get_rpccred(clp->cl_machine_cred);
+ /* don't call get_rpccred on the machine cred -
+ * a reference will be held for life of clp */
+ newcred = clp->cl_machine_cred;
spin_unlock(&clp->cl_lock);
- if (msg->rpc_cred)
- put_rpccred(msg->rpc_cred);
msg->rpc_cred = newcred;
flavor = clp->cl_rpcclient->cl_auth->au_flavor;
- WARN_ON(flavor != RPC_AUTH_GSS_KRB5I &&
- flavor != RPC_AUTH_GSS_KRB5P);
+ WARN_ON_ONCE(flavor != RPC_AUTH_GSS_KRB5I &&
+ flavor != RPC_AUTH_GSS_KRB5P);
*clntp = clp->cl_rpcclient;
return true;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 39b6cf2..989bb9d 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -6001,10 +6001,12 @@
.rpc_resp = &res,
};
struct rpc_clnt *clnt = NFS_SERVER(dir)->client;
+ struct rpc_cred *cred = NULL;
if (use_integrity) {
clnt = NFS_SERVER(dir)->nfs_client->cl_rpcclient;
- msg.rpc_cred = nfs4_get_clid_cred(NFS_SERVER(dir)->nfs_client);
+ cred = nfs4_get_clid_cred(NFS_SERVER(dir)->nfs_client);
+ msg.rpc_cred = cred;
}
dprintk("NFS call secinfo %s\n", name->name);
@@ -6016,8 +6018,8 @@
&res.seq_res, 0);
dprintk("NFS reply secinfo: %d\n", status);
- if (msg.rpc_cred)
- put_rpccred(msg.rpc_cred);
+ if (cred)
+ put_rpccred(cred);
return status;
}
@@ -6151,11 +6153,13 @@
},
.allow.u.words = {
[0] = 1 << (OP_CLOSE) |
- 1 << (OP_LOCKU),
+ 1 << (OP_LOCKU) |
+ 1 << (OP_COMMIT),
[1] = 1 << (OP_SECINFO - 32) |
1 << (OP_SECINFO_NO_NAME - 32) |
1 << (OP_TEST_STATEID - 32) |
- 1 << (OP_FREE_STATEID - 32)
+ 1 << (OP_FREE_STATEID - 32) |
+ 1 << (OP_WRITE - 32)
}
};
@@ -7496,11 +7500,13 @@
.rpc_resp = &res,
};
struct rpc_clnt *clnt = server->client;
+ struct rpc_cred *cred = NULL;
int status;
if (use_integrity) {
clnt = server->nfs_client->cl_rpcclient;
- msg.rpc_cred = nfs4_get_clid_cred(server->nfs_client);
+ cred = nfs4_get_clid_cred(server->nfs_client);
+ msg.rpc_cred = cred;
}
dprintk("--> %s\n", __func__);
@@ -7508,8 +7514,8 @@
&res.seq_res, 0);
dprintk("<-- %s status=%d\n", __func__, status);
- if (msg.rpc_cred)
- put_rpccred(msg.rpc_cred);
+ if (cred)
+ put_rpccred(cred);
return status;
}
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index fbdad9e..79210d2 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -414,7 +414,7 @@
#define decode_test_stateid_maxsz (op_decode_hdr_maxsz + 2 + 1)
#define encode_free_stateid_maxsz (op_encode_hdr_maxsz + 1 + \
XDR_QUADLEN(NFS4_STATEID_SIZE))
-#define decode_free_stateid_maxsz (op_decode_hdr_maxsz + 1)
+#define decode_free_stateid_maxsz (op_decode_hdr_maxsz)
#else /* CONFIG_NFS_V4_1 */
#define encode_sequence_maxsz 0
#define decode_sequence_maxsz 0
@@ -5966,21 +5966,8 @@
static int decode_free_stateid(struct xdr_stream *xdr,
struct nfs41_free_stateid_res *res)
{
- __be32 *p;
- int status;
-
- status = decode_op_hdr(xdr, OP_FREE_STATEID);
- if (status)
- return status;
-
- p = xdr_inline_decode(xdr, 4);
- if (unlikely(!p))
- goto out_overflow;
- res->status = be32_to_cpup(p++);
+ res->status = decode_op_hdr(xdr, OP_FREE_STATEID);
return res->status;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
#endif /* CONFIG_NFS_V4_1 */
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 5793f24..a03b9c6 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -360,7 +360,8 @@
#endif
static struct shrinker acl_shrinker = {
- .shrink = nfs_access_cache_shrinker,
+ .count_objects = nfs_access_cache_count,
+ .scan_objects = nfs_access_cache_scan,
.seeks = DEFAULT_SEEKS,
};
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index e76244e..9186c7c 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -59,11 +59,14 @@
static int nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *vec);
static void cache_cleaner_func(struct work_struct *unused);
-static int nfsd_reply_cache_shrink(struct shrinker *shrink,
- struct shrink_control *sc);
+static unsigned long nfsd_reply_cache_count(struct shrinker *shrink,
+ struct shrink_control *sc);
+static unsigned long nfsd_reply_cache_scan(struct shrinker *shrink,
+ struct shrink_control *sc);
static struct shrinker nfsd_reply_cache_shrinker = {
- .shrink = nfsd_reply_cache_shrink,
+ .scan_objects = nfsd_reply_cache_scan,
+ .count_objects = nfsd_reply_cache_count,
.seeks = 1,
};
@@ -232,16 +235,18 @@
* Walk the LRU list and prune off entries that are older than RC_EXPIRE.
* Also prune the oldest ones when the total exceeds the max number of entries.
*/
-static void
+static long
prune_cache_entries(void)
{
struct svc_cacherep *rp, *tmp;
+ long freed = 0;
list_for_each_entry_safe(rp, tmp, &lru_head, c_lru) {
if (!nfsd_cache_entry_expired(rp) &&
num_drc_entries <= max_drc_entries)
break;
nfsd_reply_cache_free_locked(rp);
+ freed++;
}
/*
@@ -254,6 +259,7 @@
cancel_delayed_work(&cache_cleaner);
else
mod_delayed_work(system_wq, &cache_cleaner, RC_EXPIRE);
+ return freed;
}
static void
@@ -264,20 +270,28 @@
spin_unlock(&cache_lock);
}
-static int
-nfsd_reply_cache_shrink(struct shrinker *shrink, struct shrink_control *sc)
+static unsigned long
+nfsd_reply_cache_count(struct shrinker *shrink, struct shrink_control *sc)
{
- unsigned int num;
+ unsigned long num;
spin_lock(&cache_lock);
- if (sc->nr_to_scan)
- prune_cache_entries();
num = num_drc_entries;
spin_unlock(&cache_lock);
return num;
}
+static unsigned long
+nfsd_reply_cache_scan(struct shrinker *shrink, struct shrink_control *sc)
+{
+ unsigned long freed;
+
+ spin_lock(&cache_lock);
+ freed = prune_cache_entries();
+ spin_unlock(&cache_lock);
+ return freed;
+}
/*
* Walk an xdr_buf and get a CRC for at most the first RC_CSUMLEN bytes
*/
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index b1a5277..7e350c5 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -254,7 +254,7 @@
struct inode *inode = mapping->host;
if (to > inode->i_size) {
- truncate_pagecache(inode, to, inode->i_size);
+ truncate_pagecache(inode, inode->i_size);
nilfs_truncate(inode);
}
}
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index c5670b8..ea4ba9d 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -1768,7 +1768,7 @@
struct inode *inode = mapping->host;
if (to > inode->i_size) {
- truncate_pagecache(inode, to, inode->i_size);
+ truncate_pagecache(inode, inode->i_size);
ntfs_truncate_vfs(inode);
}
}
diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
index 8a40457..b4f788e 100644
--- a/fs/ocfs2/acl.c
+++ b/fs/ocfs2/acl.c
@@ -51,10 +51,6 @@
return ERR_PTR(-EINVAL);
count = size / sizeof(struct posix_acl_entry);
- if (count < 0)
- return ERR_PTR(-EINVAL);
- if (count == 0)
- return NULL;
acl = posix_acl_alloc(count, GFP_NOFS);
if (!acl)
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 94417a8..f37d3c0 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -2044,7 +2044,7 @@
out_write_size:
pos += copied;
- if (pos > inode->i_size) {
+ if (pos > i_size_read(inode)) {
i_size_write(inode, pos);
mark_inode_dirty(inode);
}
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 5c1c864..363f0dc 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -628,11 +628,9 @@
struct o2nm_node *node,
int idx)
{
- struct list_head *iter;
struct o2hb_callback_func *f;
- list_for_each(iter, &hbcall->list) {
- f = list_entry(iter, struct o2hb_callback_func, hc_item);
+ list_for_each_entry(f, &hbcall->list, hc_item) {
mlog(ML_HEARTBEAT, "calling funcs %p\n", f);
(f->hc_func)(node, idx, f->hc_data);
}
@@ -641,16 +639,9 @@
/* Will run the list in order until we process the passed event */
static void o2hb_run_event_list(struct o2hb_node_event *queued_event)
{
- int empty;
struct o2hb_callback *hbcall;
struct o2hb_node_event *event;
- spin_lock(&o2hb_live_lock);
- empty = list_empty(&queued_event->hn_item);
- spin_unlock(&o2hb_live_lock);
- if (empty)
- return;
-
/* Holding callback sem assures we don't alter the callback
* lists when doing this, and serializes ourselves with other
* processes wanting callbacks. */
@@ -709,6 +700,7 @@
struct o2hb_node_event event =
{ .hn_item = LIST_HEAD_INIT(event.hn_item), };
struct o2nm_node *node;
+ int queued = 0;
node = o2nm_get_node_by_num(slot->ds_node_num);
if (!node)
@@ -726,11 +718,13 @@
o2hb_queue_node_event(&event, O2HB_NODE_DOWN_CB, node,
slot->ds_node_num);
+ queued = 1;
}
}
spin_unlock(&o2hb_live_lock);
- o2hb_run_event_list(&event);
+ if (queued)
+ o2hb_run_event_list(&event);
o2nm_node_put(node);
}
@@ -790,6 +784,7 @@
unsigned int dead_ms = o2hb_dead_threshold * O2HB_REGION_TIMEOUT_MS;
unsigned int slot_dead_ms;
int tmp;
+ int queued = 0;
memcpy(hb_block, slot->ds_raw_block, reg->hr_block_bytes);
@@ -883,6 +878,7 @@
slot->ds_node_num);
changed = 1;
+ queued = 1;
}
list_add_tail(&slot->ds_live_item,
@@ -934,6 +930,7 @@
node, slot->ds_node_num);
changed = 1;
+ queued = 1;
}
/* We don't clear this because the node is still
@@ -949,7 +946,8 @@
out:
spin_unlock(&o2hb_live_lock);
- o2hb_run_event_list(&event);
+ if (queued)
+ o2hb_run_event_list(&event);
if (node)
o2nm_node_put(node);
@@ -2516,8 +2514,7 @@
int o2hb_register_callback(const char *region_uuid,
struct o2hb_callback_func *hc)
{
- struct o2hb_callback_func *tmp;
- struct list_head *iter;
+ struct o2hb_callback_func *f;
struct o2hb_callback *hbcall;
int ret;
@@ -2540,10 +2537,9 @@
down_write(&o2hb_callback_sem);
- list_for_each(iter, &hbcall->list) {
- tmp = list_entry(iter, struct o2hb_callback_func, hc_item);
- if (hc->hc_priority < tmp->hc_priority) {
- list_add_tail(&hc->hc_item, iter);
+ list_for_each_entry(f, &hbcall->list, hc_item) {
+ if (hc->hc_priority < f->hc_priority) {
+ list_add_tail(&hc->hc_item, &f->hc_item);
break;
}
}
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index d644dc6..2cd2406 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -543,8 +543,9 @@
}
if (was_valid && !valid) {
- printk(KERN_NOTICE "o2net: No longer connected to "
- SC_NODEF_FMT "\n", SC_NODEF_ARGS(old_sc));
+ if (old_sc)
+ printk(KERN_NOTICE "o2net: No longer connected to "
+ SC_NODEF_FMT "\n", SC_NODEF_ARGS(old_sc));
o2net_complete_nodes_nsw(nn);
}
@@ -765,32 +766,32 @@
o2net_handler_tree_lookup(u32 msg_type, u32 key, struct rb_node ***ret_p,
struct rb_node **ret_parent)
{
- struct rb_node **p = &o2net_handler_tree.rb_node;
- struct rb_node *parent = NULL;
+ struct rb_node **p = &o2net_handler_tree.rb_node;
+ struct rb_node *parent = NULL;
struct o2net_msg_handler *nmh, *ret = NULL;
int cmp;
- while (*p) {
- parent = *p;
- nmh = rb_entry(parent, struct o2net_msg_handler, nh_node);
+ while (*p) {
+ parent = *p;
+ nmh = rb_entry(parent, struct o2net_msg_handler, nh_node);
cmp = o2net_handler_cmp(nmh, msg_type, key);
- if (cmp < 0)
- p = &(*p)->rb_left;
- else if (cmp > 0)
- p = &(*p)->rb_right;
- else {
+ if (cmp < 0)
+ p = &(*p)->rb_left;
+ else if (cmp > 0)
+ p = &(*p)->rb_right;
+ else {
ret = nmh;
- break;
+ break;
}
- }
+ }
- if (ret_p != NULL)
- *ret_p = p;
- if (ret_parent != NULL)
- *ret_parent = parent;
+ if (ret_p != NULL)
+ *ret_p = p;
+ if (ret_parent != NULL)
+ *ret_parent = parent;
- return ret;
+ return ret;
}
static void o2net_handler_kref_release(struct kref *kref)
@@ -1695,13 +1696,12 @@
ret = 0;
out:
- if (ret) {
+ if (ret && sc) {
printk(KERN_NOTICE "o2net: Connect attempt to " SC_NODEF_FMT
" failed with errno %d\n", SC_NODEF_ARGS(sc), ret);
/* 0 err so that another will be queued and attempted
* from set_nn_state */
- if (sc)
- o2net_ensure_shutdown(nn, sc, 0);
+ o2net_ensure_shutdown(nn, sc, 0);
}
if (sc)
sc_put(sc);
@@ -1873,12 +1873,16 @@
if (o2nm_this_node() >= node->nd_num) {
local_node = o2nm_get_node_by_num(o2nm_this_node());
- printk(KERN_NOTICE "o2net: Unexpected connect attempt seen "
- "at node '%s' (%u, %pI4:%d) from node '%s' (%u, "
- "%pI4:%d)\n", local_node->nd_name, local_node->nd_num,
- &(local_node->nd_ipv4_address),
- ntohs(local_node->nd_ipv4_port), node->nd_name,
- node->nd_num, &sin.sin_addr.s_addr, ntohs(sin.sin_port));
+ if (local_node)
+ printk(KERN_NOTICE "o2net: Unexpected connect attempt "
+ "seen at node '%s' (%u, %pI4:%d) from "
+ "node '%s' (%u, %pI4:%d)\n",
+ local_node->nd_name, local_node->nd_num,
+ &(local_node->nd_ipv4_address),
+ ntohs(local_node->nd_ipv4_port),
+ node->nd_name,
+ node->nd_num, &sin.sin_addr.s_addr,
+ ntohs(sin.sin_port));
ret = -EINVAL;
goto out;
}
diff --git a/fs/ocfs2/dlm/dlmast.c b/fs/ocfs2/dlm/dlmast.c
index fbec0be..b46278f 100644
--- a/fs/ocfs2/dlm/dlmast.c
+++ b/fs/ocfs2/dlm/dlmast.c
@@ -292,7 +292,7 @@
struct dlm_lock *lock = NULL;
struct dlm_proxy_ast *past = (struct dlm_proxy_ast *) msg->buf;
char *name;
- struct list_head *iter, *head=NULL;
+ struct list_head *head = NULL;
__be64 cookie;
u32 flags;
u8 node;
@@ -373,8 +373,7 @@
/* try convert queue for both ast/bast */
head = &res->converting;
lock = NULL;
- list_for_each(iter, head) {
- lock = list_entry (iter, struct dlm_lock, list);
+ list_for_each_entry(lock, head, list) {
if (lock->ml.cookie == cookie)
goto do_ast;
}
@@ -385,8 +384,7 @@
else
head = &res->granted;
- list_for_each(iter, head) {
- lock = list_entry (iter, struct dlm_lock, list);
+ list_for_each_entry(lock, head, list) {
if (lock->ml.cookie == cookie)
goto do_ast;
}
diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index de854cc..e051776 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -1079,11 +1079,9 @@
static inline int dlm_lock_on_list(struct list_head *head,
struct dlm_lock *lock)
{
- struct list_head *iter;
struct dlm_lock *tmplock;
- list_for_each(iter, head) {
- tmplock = list_entry(iter, struct dlm_lock, list);
+ list_for_each_entry(tmplock, head, list) {
if (tmplock == lock)
return 1;
}
diff --git a/fs/ocfs2/dlm/dlmconvert.c b/fs/ocfs2/dlm/dlmconvert.c
index 29a886d..e36d63f 100644
--- a/fs/ocfs2/dlm/dlmconvert.c
+++ b/fs/ocfs2/dlm/dlmconvert.c
@@ -123,7 +123,6 @@
int *kick_thread)
{
enum dlm_status status = DLM_NORMAL;
- struct list_head *iter;
struct dlm_lock *tmplock=NULL;
assert_spin_locked(&res->spinlock);
@@ -185,16 +184,14 @@
/* upconvert from here on */
status = DLM_NORMAL;
- list_for_each(iter, &res->granted) {
- tmplock = list_entry(iter, struct dlm_lock, list);
+ list_for_each_entry(tmplock, &res->granted, list) {
if (tmplock == lock)
continue;
if (!dlm_lock_compatible(tmplock->ml.type, type))
goto switch_queues;
}
- list_for_each(iter, &res->converting) {
- tmplock = list_entry(iter, struct dlm_lock, list);
+ list_for_each_entry(tmplock, &res->converting, list) {
if (!dlm_lock_compatible(tmplock->ml.type, type))
goto switch_queues;
/* existing conversion requests take precedence */
@@ -424,8 +421,8 @@
struct dlm_ctxt *dlm = data;
struct dlm_convert_lock *cnv = (struct dlm_convert_lock *)msg->buf;
struct dlm_lock_resource *res = NULL;
- struct list_head *iter;
struct dlm_lock *lock = NULL;
+ struct dlm_lock *tmp_lock;
struct dlm_lockstatus *lksb;
enum dlm_status status = DLM_NORMAL;
u32 flags;
@@ -471,14 +468,13 @@
dlm_error(status);
goto leave;
}
- list_for_each(iter, &res->granted) {
- lock = list_entry(iter, struct dlm_lock, list);
- if (lock->ml.cookie == cnv->cookie &&
- lock->ml.node == cnv->node_idx) {
+ list_for_each_entry(tmp_lock, &res->granted, list) {
+ if (tmp_lock->ml.cookie == cnv->cookie &&
+ tmp_lock->ml.node == cnv->node_idx) {
+ lock = tmp_lock;
dlm_lock_get(lock);
break;
}
- lock = NULL;
}
spin_unlock(&res->spinlock);
if (!lock) {
diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index 0e28e24..e33cd7a 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -96,7 +96,6 @@
void __dlm_print_one_lock_resource(struct dlm_lock_resource *res)
{
- struct list_head *iter2;
struct dlm_lock *lock;
char buf[DLM_LOCKID_NAME_MAX];
@@ -118,18 +117,15 @@
res->inflight_locks, atomic_read(&res->asts_reserved));
dlm_print_lockres_refmap(res);
printk(" granted queue:\n");
- list_for_each(iter2, &res->granted) {
- lock = list_entry(iter2, struct dlm_lock, list);
+ list_for_each_entry(lock, &res->granted, list) {
__dlm_print_lock(lock);
}
printk(" converting queue:\n");
- list_for_each(iter2, &res->converting) {
- lock = list_entry(iter2, struct dlm_lock, list);
+ list_for_each_entry(lock, &res->converting, list) {
__dlm_print_lock(lock);
}
printk(" blocked queue:\n");
- list_for_each(iter2, &res->blocked) {
- lock = list_entry(iter2, struct dlm_lock, list);
+ list_for_each_entry(lock, &res->blocked, list) {
__dlm_print_lock(lock);
}
}
@@ -446,7 +442,6 @@
{
struct dlm_master_list_entry *mle;
struct hlist_head *bucket;
- struct hlist_node *list;
int i, out = 0;
unsigned long total = 0, longest = 0, bucket_count = 0;
@@ -456,9 +451,7 @@
spin_lock(&dlm->master_lock);
for (i = 0; i < DLM_HASH_BUCKETS; i++) {
bucket = dlm_master_hash(dlm, i);
- hlist_for_each(list, bucket) {
- mle = hlist_entry(list, struct dlm_master_list_entry,
- master_hash_node);
+ hlist_for_each_entry(mle, bucket, master_hash_node) {
++total;
++bucket_count;
if (len - out < 200)
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index dbb17c0..8b3382a 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -193,7 +193,7 @@
unsigned int hash)
{
struct hlist_head *bucket;
- struct hlist_node *list;
+ struct dlm_lock_resource *res;
mlog(0, "%.*s\n", len, name);
@@ -201,9 +201,7 @@
bucket = dlm_lockres_hash(dlm, hash);
- hlist_for_each(list, bucket) {
- struct dlm_lock_resource *res = hlist_entry(list,
- struct dlm_lock_resource, hash_node);
+ hlist_for_each_entry(res, bucket, hash_node) {
if (res->lockname.name[0] != name[0])
continue;
if (unlikely(res->lockname.len != len))
@@ -262,22 +260,19 @@
static struct dlm_ctxt * __dlm_lookup_domain_full(const char *domain, int len)
{
- struct dlm_ctxt *tmp = NULL;
- struct list_head *iter;
+ struct dlm_ctxt *tmp;
assert_spin_locked(&dlm_domain_lock);
/* tmp->name here is always NULL terminated,
* but domain may not be! */
- list_for_each(iter, &dlm_domains) {
- tmp = list_entry (iter, struct dlm_ctxt, list);
+ list_for_each_entry(tmp, &dlm_domains, list) {
if (strlen(tmp->name) == len &&
memcmp(tmp->name, domain, len)==0)
- break;
- tmp = NULL;
+ return tmp;
}
- return tmp;
+ return NULL;
}
/* For null terminated domain strings ONLY */
@@ -366,25 +361,22 @@
* you shouldn't trust your pointer. */
struct dlm_ctxt *dlm_grab(struct dlm_ctxt *dlm)
{
- struct list_head *iter;
- struct dlm_ctxt *target = NULL;
+ struct dlm_ctxt *target;
+ struct dlm_ctxt *ret = NULL;
spin_lock(&dlm_domain_lock);
- list_for_each(iter, &dlm_domains) {
- target = list_entry (iter, struct dlm_ctxt, list);
-
+ list_for_each_entry(target, &dlm_domains, list) {
if (target == dlm) {
__dlm_get(target);
+ ret = target;
break;
}
-
- target = NULL;
}
spin_unlock(&dlm_domain_lock);
- return target;
+ return ret;
}
int dlm_domain_fully_joined(struct dlm_ctxt *dlm)
@@ -2296,13 +2288,10 @@
void dlm_fire_domain_eviction_callbacks(struct dlm_ctxt *dlm,
int node_num)
{
- struct list_head *iter;
struct dlm_eviction_cb *cb;
down_read(&dlm_callback_sem);
- list_for_each(iter, &dlm->dlm_eviction_callbacks) {
- cb = list_entry(iter, struct dlm_eviction_cb, ec_item);
-
+ list_for_each_entry(cb, &dlm->dlm_eviction_callbacks, ec_item) {
cb->ec_func(node_num, cb->ec_data);
}
up_read(&dlm_callback_sem);
diff --git a/fs/ocfs2/dlm/dlmlock.c b/fs/ocfs2/dlm/dlmlock.c
index 47e67c2..5d32f75 100644
--- a/fs/ocfs2/dlm/dlmlock.c
+++ b/fs/ocfs2/dlm/dlmlock.c
@@ -91,19 +91,14 @@
static int dlm_can_grant_new_lock(struct dlm_lock_resource *res,
struct dlm_lock *lock)
{
- struct list_head *iter;
struct dlm_lock *tmplock;
- list_for_each(iter, &res->granted) {
- tmplock = list_entry(iter, struct dlm_lock, list);
-
+ list_for_each_entry(tmplock, &res->granted, list) {
if (!dlm_lock_compatible(tmplock->ml.type, lock->ml.type))
return 0;
}
- list_for_each(iter, &res->converting) {
- tmplock = list_entry(iter, struct dlm_lock, list);
-
+ list_for_each_entry(tmplock, &res->converting, list) {
if (!dlm_lock_compatible(tmplock->ml.type, lock->ml.type))
return 0;
if (!dlm_lock_compatible(tmplock->ml.convert_type,
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 33ecbe0..cf0f103 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -342,16 +342,13 @@
{
struct dlm_master_list_entry *tmpmle;
struct hlist_head *bucket;
- struct hlist_node *list;
unsigned int hash;
assert_spin_locked(&dlm->master_lock);
hash = dlm_lockid_hash(name, namelen);
bucket = dlm_master_hash(dlm, hash);
- hlist_for_each(list, bucket) {
- tmpmle = hlist_entry(list, struct dlm_master_list_entry,
- master_hash_node);
+ hlist_for_each_entry(tmpmle, bucket, master_hash_node) {
if (!dlm_mle_equal(dlm, tmpmle, name, namelen))
continue;
dlm_get_mle(tmpmle);
@@ -3183,7 +3180,7 @@
struct dlm_master_list_entry *mle;
struct dlm_lock_resource *res;
struct hlist_head *bucket;
- struct hlist_node *list;
+ struct hlist_node *tmp;
unsigned int i;
mlog(0, "dlm=%s, dead node=%u\n", dlm->name, dead_node);
@@ -3194,10 +3191,7 @@
spin_lock(&dlm->master_lock);
for (i = 0; i < DLM_HASH_BUCKETS; i++) {
bucket = dlm_master_hash(dlm, i);
- hlist_for_each(list, bucket) {
- mle = hlist_entry(list, struct dlm_master_list_entry,
- master_hash_node);
-
+ hlist_for_each_entry_safe(mle, tmp, bucket, master_hash_node) {
BUG_ON(mle->type != DLM_MLE_BLOCK &&
mle->type != DLM_MLE_MASTER &&
mle->type != DLM_MLE_MIGRATION);
@@ -3378,7 +3372,7 @@
int i;
struct hlist_head *bucket;
struct dlm_master_list_entry *mle;
- struct hlist_node *tmp, *list;
+ struct hlist_node *tmp;
/*
* We notified all other nodes that we are exiting the domain and
@@ -3394,9 +3388,7 @@
for (i = 0; i < DLM_HASH_BUCKETS; i++) {
bucket = dlm_master_hash(dlm, i);
- hlist_for_each_safe(list, tmp, bucket) {
- mle = hlist_entry(list, struct dlm_master_list_entry,
- master_hash_node);
+ hlist_for_each_entry_safe(mle, tmp, bucket, master_hash_node) {
if (mle->type != DLM_MLE_BLOCK) {
mlog(ML_ERROR, "bad mle: %p\n", mle);
dlm_print_one_mle(mle);
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 773bd32..0b5adca 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -787,6 +787,7 @@
{
struct dlm_lock_request lr;
int ret;
+ int status;
mlog(0, "\n");
@@ -800,13 +801,15 @@
// send message
ret = o2net_send_message(DLM_LOCK_REQUEST_MSG, dlm->key,
- &lr, sizeof(lr), request_from, NULL);
+ &lr, sizeof(lr), request_from, &status);
/* negative status is handled by caller */
if (ret < 0)
mlog(ML_ERROR, "%s: Error %d send LOCK_REQUEST to node %u "
"to recover dead node %u\n", dlm->name, ret,
request_from, dead_node);
+ else
+ ret = status;
// return from here, then
// sleep until all received or error
return ret;
@@ -2328,6 +2331,14 @@
} else if (res->owner == dlm->node_num) {
dlm_free_dead_locks(dlm, res, dead_node);
__dlm_lockres_calc_usage(dlm, res);
+ } else if (res->owner == DLM_LOCK_RES_OWNER_UNKNOWN) {
+ if (test_bit(dead_node, res->refmap)) {
+ mlog(0, "%s:%.*s: dead node %u had a ref, but had "
+ "no locks and had not purged before dying\n",
+ dlm->name, res->lockname.len,
+ res->lockname.name, dead_node);
+ dlm_lockres_clear_refmap_bit(dlm, res, dead_node);
+ }
}
spin_unlock(&res->spinlock);
}
diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c
index e73c833..9db869d 100644
--- a/fs/ocfs2/dlm/dlmthread.c
+++ b/fs/ocfs2/dlm/dlmthread.c
@@ -286,8 +286,6 @@
struct dlm_lock_resource *res)
{
struct dlm_lock *lock, *target;
- struct list_head *iter;
- struct list_head *head;
int can_grant = 1;
/*
@@ -314,9 +312,7 @@
dlm->name, res->lockname.len, res->lockname.name);
BUG();
}
- head = &res->granted;
- list_for_each(iter, head) {
- lock = list_entry(iter, struct dlm_lock, list);
+ list_for_each_entry(lock, &res->granted, list) {
if (lock==target)
continue;
if (!dlm_lock_compatible(lock->ml.type,
@@ -333,9 +329,8 @@
target->ml.convert_type;
}
}
- head = &res->converting;
- list_for_each(iter, head) {
- lock = list_entry(iter, struct dlm_lock, list);
+
+ list_for_each_entry(lock, &res->converting, list) {
if (lock==target)
continue;
if (!dlm_lock_compatible(lock->ml.type,
@@ -384,9 +379,7 @@
goto leave;
target = list_entry(res->blocked.next, struct dlm_lock, list);
- head = &res->granted;
- list_for_each(iter, head) {
- lock = list_entry(iter, struct dlm_lock, list);
+ list_for_each_entry(lock, &res->granted, list) {
if (lock==target)
continue;
if (!dlm_lock_compatible(lock->ml.type, target->ml.type)) {
@@ -400,9 +393,7 @@
}
}
- head = &res->converting;
- list_for_each(iter, head) {
- lock = list_entry(iter, struct dlm_lock, list);
+ list_for_each_entry(lock, &res->converting, list) {
if (lock==target)
continue;
if (!dlm_lock_compatible(lock->ml.type, target->ml.type)) {
diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c
index 850aa7e..5698b52 100644
--- a/fs/ocfs2/dlm/dlmunlock.c
+++ b/fs/ocfs2/dlm/dlmunlock.c
@@ -388,7 +388,6 @@
struct dlm_ctxt *dlm = data;
struct dlm_unlock_lock *unlock = (struct dlm_unlock_lock *)msg->buf;
struct dlm_lock_resource *res = NULL;
- struct list_head *iter;
struct dlm_lock *lock = NULL;
enum dlm_status status = DLM_NORMAL;
int found = 0, i;
@@ -458,8 +457,7 @@
}
for (i=0; i<3; i++) {
- list_for_each(iter, queue) {
- lock = list_entry(iter, struct dlm_lock, list);
+ list_for_each_entry(lock, queue, list) {
if (lock->ml.cookie == unlock->cookie &&
lock->ml.node == unlock->node_idx) {
dlm_lock_get(lock);
diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
index 12bafb7..efa2b3d 100644
--- a/fs/ocfs2/dlmfs/dlmfs.c
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -401,11 +401,8 @@
{
struct inode *inode = new_inode(sb);
umode_t mode = S_IFDIR | 0755;
- struct dlmfs_inode_private *ip;
if (inode) {
- ip = DLMFS_I(inode);
-
inode->i_ino = get_next_ino();
inode_init_owner(inode, NULL, mode);
inode->i_mapping->backing_dev_info = &dlmfs_backing_dev_info;
diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c
index 2487116..767370b 100644
--- a/fs/ocfs2/extent_map.c
+++ b/fs/ocfs2/extent_map.c
@@ -781,7 +781,6 @@
cpos = map_start >> osb->s_clustersize_bits;
mapping_end = ocfs2_clusters_for_bytes(inode->i_sb,
map_start + map_len);
- mapping_end -= cpos;
is_last = 0;
while (cpos < mapping_end && !is_last) {
u32 fe_flags;
@@ -852,20 +851,20 @@
down_read(&OCFS2_I(inode)->ip_alloc_sem);
- if (*offset >= inode->i_size) {
+ if (*offset >= i_size_read(inode)) {
ret = -ENXIO;
goto out_unlock;
}
if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
if (whence == SEEK_HOLE)
- *offset = inode->i_size;
+ *offset = i_size_read(inode);
goto out_unlock;
}
clen = 0;
cpos = *offset >> cs_bits;
- cend = ocfs2_clusters_for_bytes(inode->i_sb, inode->i_size);
+ cend = ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode));
while (cpos < cend && !is_last) {
ret = ocfs2_get_clusters_nocache(inode, di_bh, cpos, &hole_size,
@@ -904,8 +903,8 @@
extlen = clen;
extlen <<= cs_bits;
- if ((extoff + extlen) > inode->i_size)
- extlen = inode->i_size - extoff;
+ if ((extoff + extlen) > i_size_read(inode))
+ extlen = i_size_read(inode) - extoff;
extoff += extlen;
if (extoff > *offset)
*offset = extoff;
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 3261d71..d71903c 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -671,11 +671,7 @@
} else {
BUG_ON(why != RESTART_TRANS);
- /* TODO: This can be more intelligent. */
- credits = ocfs2_calc_extend_credits(osb->sb,
- &fe->id2.i_list,
- clusters_to_add);
- status = ocfs2_extend_trans(handle, credits);
+ status = ocfs2_allocate_extend_trans(handle, 1);
if (status < 0) {
/* handle still has to be committed at
* this point. */
@@ -1800,6 +1796,7 @@
ocfs2_truncate_cluster_pages(inode, byte_start, byte_len);
out:
+ ocfs2_free_path(path);
ocfs2_schedule_truncate_log_flush(osb, 1);
ocfs2_run_deallocs(osb, &dealloc);
@@ -2245,7 +2242,7 @@
file->f_path.dentry->d_name.name,
(unsigned int)nr_segs);
- if (iocb->ki_left == 0)
+ if (iocb->ki_nbytes == 0)
return 0;
appending = file->f_flags & O_APPEND ? 1 : 0;
@@ -2296,7 +2293,7 @@
can_do_direct = direct_io;
ret = ocfs2_prepare_inode_for_write(file, ppos,
- iocb->ki_left, appending,
+ iocb->ki_nbytes, appending,
&can_do_direct, &has_refcount);
if (ret < 0) {
mlog_errno(ret);
@@ -2304,7 +2301,7 @@
}
if (direct_io && !is_sync_kiocb(iocb))
- unaligned_dio = ocfs2_is_io_unaligned(inode, iocb->ki_left,
+ unaligned_dio = ocfs2_is_io_unaligned(inode, iocb->ki_nbytes,
*ppos);
/*
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index 0c60ef2..fa32ce9 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -303,7 +303,7 @@
if (o2info_from_user(oij, req))
goto bail;
- oij.ij_journal_size = osb->journal->j_inode->i_size;
+ oij.ij_journal_size = i_size_read(osb->journal->j_inode);
o2info_set_request_filled(&oij.ij_req);
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 242170d..44fc3e5 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -455,6 +455,41 @@
return status;
}
+/*
+ * If we have fewer than thresh credits, extend by OCFS2_MAX_TRANS_DATA.
+ * If that fails, restart the transaction & regain write access for the
+ * buffer head which is used for metadata modifications.
+ * Taken from Ext4: extend_or_restart_transaction()
+ */
+int ocfs2_allocate_extend_trans(handle_t *handle, int thresh)
+{
+ int status, old_nblks;
+
+ BUG_ON(!handle);
+
+ old_nblks = handle->h_buffer_credits;
+ trace_ocfs2_allocate_extend_trans(old_nblks, thresh);
+
+ if (old_nblks < thresh)
+ return 0;
+
+ status = jbd2_journal_extend(handle, OCFS2_MAX_TRANS_DATA);
+ if (status < 0) {
+ mlog_errno(status);
+ goto bail;
+ }
+
+ if (status > 0) {
+ status = jbd2_journal_restart(handle, OCFS2_MAX_TRANS_DATA);
+ if (status < 0)
+ mlog_errno(status);
+ }
+
+bail:
+ return status;
+}
+
+
struct ocfs2_triggers {
struct jbd2_buffer_trigger_type ot_triggers;
int ot_offset;
@@ -801,14 +836,14 @@
inode_lock = 1;
di = (struct ocfs2_dinode *)bh->b_data;
- if (inode->i_size < OCFS2_MIN_JOURNAL_SIZE) {
+ if (i_size_read(inode) < OCFS2_MIN_JOURNAL_SIZE) {
mlog(ML_ERROR, "Journal file size (%lld) is too small!\n",
- inode->i_size);
+ i_size_read(inode));
status = -EINVAL;
goto done;
}
- trace_ocfs2_journal_init(inode->i_size,
+ trace_ocfs2_journal_init(i_size_read(inode),
(unsigned long long)inode->i_blocks,
OCFS2_I(inode)->ip_clusters);
@@ -1096,7 +1131,7 @@
memset(bhs, 0, sizeof(struct buffer_head *) * CONCURRENT_JOURNAL_FILL);
- num_blocks = ocfs2_blocks_for_bytes(inode->i_sb, inode->i_size);
+ num_blocks = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode));
v_blkno = 0;
while (v_blkno < num_blocks) {
status = ocfs2_extent_map_get_blocks(inode, v_blkno,
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index 0a99273..0b479ba 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -258,6 +258,17 @@
int ocfs2_commit_trans(struct ocfs2_super *osb,
handle_t *handle);
int ocfs2_extend_trans(handle_t *handle, int nblocks);
+int ocfs2_allocate_extend_trans(handle_t *handle,
+ int thresh);
+
+/*
+ * Define an arbitrary limit for the amount of data we will anticipate
+ * writing to any given transaction. For unbounded transactions such as
+ * fallocate(2) we can write more than this, but we always
+ * start off at the maximum transaction size and grow the transaction
+ * optimistically as we go.
+ */
+#define OCFS2_MAX_TRANS_DATA 64U
/*
* Create access is for when we get a newly created buffer and we're
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index aebeacd..cd5496b 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -1082,7 +1082,7 @@
}
retry_enospc:
- (*ac)->ac_bits_wanted = osb->local_alloc_default_bits;
+ (*ac)->ac_bits_wanted = osb->local_alloc_bits;
status = ocfs2_reserve_cluster_bitmap_bits(osb, *ac);
if (status == -ENOSPC) {
if (ocfs2_recalc_la_window(osb, OCFS2_LA_EVENT_ENOSPC) ==
@@ -1154,7 +1154,7 @@
OCFS2_LA_DISABLED)
goto bail;
- ac->ac_bits_wanted = osb->local_alloc_default_bits;
+ ac->ac_bits_wanted = osb->local_alloc_bits;
status = ocfs2_claim_clusters(handle, ac,
osb->local_alloc_bits,
&cluster_off,
diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index 452068b..3d3f3c8 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -152,6 +152,7 @@
}
out:
+ ocfs2_free_path(path);
return ret;
}
@@ -845,7 +846,7 @@
struct ocfs2_move_extents *range = context->range;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
- if ((inode->i_size == 0) || (range->me_len == 0))
+ if ((i_size_read(inode) == 0) || (range->me_len == 0))
return 0;
if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h
index 3b481f4..1b60c62 100644
--- a/fs/ocfs2/ocfs2_trace.h
+++ b/fs/ocfs2/ocfs2_trace.h
@@ -2579,6 +2579,8 @@
DEFINE_OCFS2_INT_EVENT(ocfs2_extend_trans_restart);
+DEFINE_OCFS2_INT_INT_EVENT(ocfs2_allocate_extend_trans);
+
DEFINE_OCFS2_ULL_ULL_UINT_UINT_EVENT(ocfs2_journal_access);
DEFINE_OCFS2_ULL_EVENT(ocfs2_journal_dirty);
diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index 332a281..aaa5061 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -234,7 +234,7 @@
len = sb->s_blocksize - OCFS2_QBLK_RESERVED_SPACE - offset;
}
- if (gqinode->i_size < off + len) {
+ if (i_size_read(gqinode) < off + len) {
loff_t rounded_end =
ocfs2_align_bytes_to_blocks(sb, off + len);
@@ -778,8 +778,8 @@
*/
WARN_ON(journal_current_handle());
status = ocfs2_extend_no_holes(gqinode, NULL,
- gqinode->i_size + (need_alloc << sb->s_blocksize_bits),
- gqinode->i_size);
+ i_size_read(gqinode) + (need_alloc << sb->s_blocksize_bits),
+ i_size_read(gqinode));
if (status < 0)
goto out_dq;
}
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index 27fe7ee..2e4344b 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -982,14 +982,14 @@
/* We are protected by dqio_sem so no locking needed */
status = ocfs2_extend_no_holes(lqinode, NULL,
- lqinode->i_size + 2 * sb->s_blocksize,
- lqinode->i_size);
+ i_size_read(lqinode) + 2 * sb->s_blocksize,
+ i_size_read(lqinode));
if (status < 0) {
mlog_errno(status);
goto out;
}
status = ocfs2_simple_size_update(lqinode, oinfo->dqi_lqi_bh,
- lqinode->i_size + 2 * sb->s_blocksize);
+ i_size_read(lqinode) + 2 * sb->s_blocksize);
if (status < 0) {
mlog_errno(status);
goto out;
@@ -1125,14 +1125,14 @@
/* We are protected by dqio_sem so no locking needed */
status = ocfs2_extend_no_holes(lqinode, NULL,
- lqinode->i_size + sb->s_blocksize,
- lqinode->i_size);
+ i_size_read(lqinode) + sb->s_blocksize,
+ i_size_read(lqinode));
if (status < 0) {
mlog_errno(status);
goto out;
}
status = ocfs2_simple_size_update(lqinode, oinfo->dqi_lqi_bh,
- lqinode->i_size + sb->s_blocksize);
+ i_size_read(lqinode) + sb->s_blocksize);
if (status < 0) {
mlog_errno(status);
goto out;
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index a70d604..bf4dfc1 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -3854,7 +3854,10 @@
while (cpos < clusters) {
ret = ocfs2_get_clusters(inode, cpos, &p_cluster,
&num_clusters, &ext_flags);
-
+ if (ret) {
+ mlog_errno(ret);
+ goto unlock;
+ }
if (p_cluster && !(ext_flags & OCFS2_EXT_REFCOUNTED)) {
ret = ocfs2_add_refcount_flag(inode, &di_et,
&ref_tree->rf_ci,
@@ -4025,7 +4028,10 @@
while (cpos < clusters) {
ret = ocfs2_get_clusters(s_inode, cpos, &p_cluster,
&num_clusters, &ext_flags);
-
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
if (p_cluster) {
ret = ocfs2_add_refcounted_extent(t_inode, &et,
ref_ci, ref_root_bh,
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index 317ef0a..6ce0686 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -3505,7 +3505,7 @@
int ret, credits, ref_meta = 0, ref_credits = 0;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
struct inode *tl_inode = osb->osb_tl_inode;
- struct ocfs2_xattr_set_ctxt ctxt = { NULL, NULL, };
+ struct ocfs2_xattr_set_ctxt ctxt = { NULL, NULL, NULL, };
struct ocfs2_refcount_tree *ref_tree = NULL;
struct ocfs2_xattr_info xi = {
@@ -3609,13 +3609,14 @@
if (IS_ERR(ctxt.handle)) {
ret = PTR_ERR(ctxt.handle);
mlog_errno(ret);
- goto cleanup;
+ goto out_free_ac;
}
ret = __ocfs2_xattr_set_handle(inode, di, &xi, &xis, &xbs, &ctxt);
ocfs2_commit_trans(osb, ctxt.handle);
+out_free_ac:
if (ctxt.data_ac)
ocfs2_free_alloc_context(ctxt.data_ac);
if (ctxt.meta_ac)
@@ -5881,6 +5882,10 @@
while (cpos < clusters) {
ret = ocfs2_xattr_get_clusters(inode, cpos, &p_cluster,
&num_clusters, el, &ext_flags);
+ if (ret) {
+ mlog_errno(ret);
+ break;
+ }
cpos += num_clusters;
if ((ext_flags & OCFS2_EXT_REFCOUNTED))
@@ -6797,7 +6802,7 @@
if (ret) {
if (*meta_ac) {
ocfs2_free_alloc_context(*meta_ac);
- meta_ac = NULL;
+ *meta_ac = NULL;
}
}
diff --git a/fs/omfs/file.c b/fs/omfs/file.c
index e0d9b3e..54d57d6 100644
--- a/fs/omfs/file.c
+++ b/fs/omfs/file.c
@@ -311,7 +311,7 @@
struct inode *inode = mapping->host;
if (to > inode->i_size) {
- truncate_pagecache(inode, to, inode->i_size);
+ truncate_pagecache(inode, inode->i_size);
omfs_truncate(inode);
}
}
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 0ff80f9..985ea88 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -286,7 +286,7 @@
int rv = generic_permission(inode, mask);
if (rv == 0)
return 0;
- if (task_pid(current) == proc_pid(inode))
+ if (task_tgid(current) == proc_pid(inode))
rv = 0;
return rv;
}
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 5aa847a..59d85d6 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -132,13 +132,7 @@
K(i.freeswap),
K(global_page_state(NR_FILE_DIRTY)),
K(global_page_state(NR_WRITEBACK)),
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- K(global_page_state(NR_ANON_PAGES)
- + global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) *
- HPAGE_PMD_NR),
-#else
K(global_page_state(NR_ANON_PAGES)),
-#endif
K(global_page_state(NR_FILE_MAPPED)),
K(global_page_state(NR_SHMEM)),
K(global_page_state(NR_SLAB_RECLAIMABLE) +
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 107d026..7366e9d 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -740,6 +740,9 @@
ptent = pte_file_clear_soft_dirty(ptent);
}
+ if (vma->vm_flags & VM_SOFTDIRTY)
+ vma->vm_flags &= ~VM_SOFTDIRTY;
+
set_pte_at(vma->vm_mm, addr, pte, ptent);
#endif
}
@@ -949,13 +952,15 @@
if (is_migration_entry(entry))
page = migration_entry_to_page(entry);
} else {
- *pme = make_pme(PM_NOT_PRESENT(pm->v2));
+ if (vma->vm_flags & VM_SOFTDIRTY)
+ flags2 |= __PM_SOFT_DIRTY;
+ *pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, flags2));
return;
}
if (page && !PageAnon(page))
flags |= PM_FILE;
- if (pte_soft_dirty(pte))
+ if ((vma->vm_flags & VM_SOFTDIRTY) || pte_soft_dirty(pte))
flags2 |= __PM_SOFT_DIRTY;
*pme = make_pme(PM_PFRAME(frame) | PM_STATUS2(pm->v2, flags2) | flags);
@@ -974,7 +979,7 @@
*pme = make_pme(PM_PFRAME(pmd_pfn(pmd) + offset)
| PM_STATUS2(pm->v2, pmd_flags2) | PM_PRESENT);
else
- *pme = make_pme(PM_NOT_PRESENT(pm->v2));
+ *pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, pmd_flags2));
}
#else
static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
@@ -997,7 +1002,11 @@
if (vma && pmd_trans_huge_lock(pmd, vma) == 1) {
int pmd_flags2;
- pmd_flags2 = (pmd_soft_dirty(*pmd) ? __PM_SOFT_DIRTY : 0);
+ if ((vma->vm_flags & VM_SOFTDIRTY) || pmd_soft_dirty(*pmd))
+ pmd_flags2 = __PM_SOFT_DIRTY;
+ else
+ pmd_flags2 = 0;
+
for (; addr != end; addr += PAGE_SIZE) {
unsigned long offset;
@@ -1015,12 +1024,17 @@
if (pmd_trans_unstable(pmd))
return 0;
for (; addr != end; addr += PAGE_SIZE) {
+ int flags2;
/* check to see if we've left 'vma' behind
* and need a new, higher one */
if (vma && (addr >= vma->vm_end)) {
vma = find_vma(walk->mm, addr);
- pme = make_pme(PM_NOT_PRESENT(pm->v2));
+ if (vma && (vma->vm_flags & VM_SOFTDIRTY))
+ flags2 = __PM_SOFT_DIRTY;
+ else
+ flags2 = 0;
+ pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, flags2));
}
/* check that 'vma' actually covers this address,
@@ -1044,13 +1058,15 @@
#ifdef CONFIG_HUGETLB_PAGE
static void huge_pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
- pte_t pte, int offset)
+ pte_t pte, int offset, int flags2)
{
if (pte_present(pte))
- *pme = make_pme(PM_PFRAME(pte_pfn(pte) + offset)
- | PM_STATUS2(pm->v2, 0) | PM_PRESENT);
+ *pme = make_pme(PM_PFRAME(pte_pfn(pte) + offset) |
+ PM_STATUS2(pm->v2, flags2) |
+ PM_PRESENT);
else
- *pme = make_pme(PM_NOT_PRESENT(pm->v2));
+ *pme = make_pme(PM_NOT_PRESENT(pm->v2) |
+ PM_STATUS2(pm->v2, flags2));
}
/* This function walks within one hugetlb entry in the single call */
@@ -1059,12 +1075,22 @@
struct mm_walk *walk)
{
struct pagemapread *pm = walk->private;
+ struct vm_area_struct *vma;
int err = 0;
+ int flags2;
pagemap_entry_t pme;
+ vma = find_vma(walk->mm, addr);
+ WARN_ON_ONCE(!vma);
+
+ if (vma && (vma->vm_flags & VM_SOFTDIRTY))
+ flags2 = __PM_SOFT_DIRTY;
+ else
+ flags2 = 0;
+
for (; addr != end; addr += PAGE_SIZE) {
int offset = (addr & ~hmask) >> PAGE_SHIFT;
- huge_pte_to_pagemap_entry(&pme, pm, *pte, offset);
+ huge_pte_to_pagemap_entry(&pme, pm, *pte, offset, flags2);
err = add_to_pagemap(addr, &pme, pm);
if (err)
return err;
@@ -1376,8 +1402,10 @@
walk.mm = mm;
pol = get_vma_policy(task, vma, vma->vm_start);
- mpol_to_str(buffer, sizeof(buffer), pol);
+ n = mpol_to_str(buffer, sizeof(buffer), pol);
mpol_cond_put(pol);
+ if (n < 0)
+ return n;
seq_printf(m, "%08lx %s", vma->vm_start, buffer);
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index a1a16eb..9100d69 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -21,6 +21,7 @@
#include <linux/crash_dump.h>
#include <linux/list.h>
#include <linux/vmalloc.h>
+#include <linux/pagemap.h>
#include <asm/uaccess.h>
#include <asm/io.h>
#include "internal.h"
@@ -123,11 +124,65 @@
return read;
}
+/*
+ * Architectures may override this function to allocate ELF header in 2nd kernel
+ */
+int __weak elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size)
+{
+ return 0;
+}
+
+/*
+ * Architectures may override this function to free header
+ */
+void __weak elfcorehdr_free(unsigned long long addr)
+{}
+
+/*
+ * Architectures may override this function to read from ELF header
+ */
+ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos)
+{
+ return read_from_oldmem(buf, count, ppos, 0);
+}
+
+/*
+ * Architectures may override this function to read from notes sections
+ */
+ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos)
+{
+ return read_from_oldmem(buf, count, ppos, 0);
+}
+
+/*
+ * Architectures may override this function to map oldmem
+ */
+int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma,
+ unsigned long from, unsigned long pfn,
+ unsigned long size, pgprot_t prot)
+{
+ return remap_pfn_range(vma, from, pfn, size, prot);
+}
+
+/*
+ * Copy to either kernel or user space
+ */
+static int copy_to(void *target, void *src, size_t size, int userbuf)
+{
+ if (userbuf) {
+ if (copy_to_user((char __user *) target, src, size))
+ return -EFAULT;
+ } else {
+ memcpy(target, src, size);
+ }
+ return 0;
+}
+
/* Read from the ELF header and then the crash dump. On error, negative value is
* returned otherwise number of bytes read are returned.
*/
-static ssize_t read_vmcore(struct file *file, char __user *buffer,
- size_t buflen, loff_t *fpos)
+static ssize_t __read_vmcore(char *buffer, size_t buflen, loff_t *fpos,
+ int userbuf)
{
ssize_t acc = 0, tmp;
size_t tsz;
@@ -144,7 +199,7 @@
/* Read ELF core header */
if (*fpos < elfcorebuf_sz) {
tsz = min(elfcorebuf_sz - (size_t)*fpos, buflen);
- if (copy_to_user(buffer, elfcorebuf + *fpos, tsz))
+ if (copy_to(buffer, elfcorebuf + *fpos, tsz, userbuf))
return -EFAULT;
buflen -= tsz;
*fpos += tsz;
@@ -162,7 +217,7 @@
tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)*fpos, buflen);
kaddr = elfnotes_buf + *fpos - elfcorebuf_sz;
- if (copy_to_user(buffer, kaddr, tsz))
+ if (copy_to(buffer, kaddr, tsz, userbuf))
return -EFAULT;
buflen -= tsz;
*fpos += tsz;
@@ -178,7 +233,7 @@
if (*fpos < m->offset + m->size) {
tsz = min_t(size_t, m->offset + m->size - *fpos, buflen);
start = m->paddr + *fpos - m->offset;
- tmp = read_from_oldmem(buffer, tsz, &start, 1);
+ tmp = read_from_oldmem(buffer, tsz, &start, userbuf);
if (tmp < 0)
return tmp;
buflen -= tsz;
@@ -195,6 +250,55 @@
return acc;
}
+static ssize_t read_vmcore(struct file *file, char __user *buffer,
+ size_t buflen, loff_t *fpos)
+{
+ return __read_vmcore((__force char *) buffer, buflen, fpos, 1);
+}
+
+/*
+ * The vmcore fault handler uses the page cache and fills data using the
+ * standard __vmcore_read() function.
+ *
+ * On s390 the fault handler is used for memory regions that can't be mapped
+ * directly with remap_pfn_range().
+ */
+static int mmap_vmcore_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+#ifdef CONFIG_S390
+ struct address_space *mapping = vma->vm_file->f_mapping;
+ pgoff_t index = vmf->pgoff;
+ struct page *page;
+ loff_t offset;
+ char *buf;
+ int rc;
+
+ page = find_or_create_page(mapping, index, GFP_KERNEL);
+ if (!page)
+ return VM_FAULT_OOM;
+ if (!PageUptodate(page)) {
+ offset = (loff_t) index << PAGE_CACHE_SHIFT;
+ buf = __va((page_to_pfn(page) << PAGE_SHIFT));
+ rc = __read_vmcore(buf, PAGE_SIZE, &offset, 0);
+ if (rc < 0) {
+ unlock_page(page);
+ page_cache_release(page);
+ return (rc == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS;
+ }
+ SetPageUptodate(page);
+ }
+ unlock_page(page);
+ vmf->page = page;
+ return 0;
+#else
+ return VM_FAULT_SIGBUS;
+#endif
+}
+
+static const struct vm_operations_struct vmcore_mmap_ops = {
+ .fault = mmap_vmcore_fault,
+};
+
/**
* alloc_elfnotes_buf - allocate buffer for ELF note segment in
* vmalloc memory
@@ -223,7 +327,7 @@
* regions in the 1st kernel pointed to by PT_LOAD entries) into
* virtually contiguous user-space in ELF layout.
*/
-#if defined(CONFIG_MMU) && !defined(CONFIG_S390)
+#ifdef CONFIG_MMU
static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
{
size_t size = vma->vm_end - vma->vm_start;
@@ -241,6 +345,7 @@
vma->vm_flags &= ~(VM_MAYWRITE | VM_MAYEXEC);
vma->vm_flags |= VM_MIXEDMAP;
+ vma->vm_ops = &vmcore_mmap_ops;
len = 0;
@@ -282,9 +387,9 @@
tsz = min_t(size_t, m->offset + m->size - start, size);
paddr = m->paddr + start - m->offset;
- if (remap_pfn_range(vma, vma->vm_start + len,
- paddr >> PAGE_SHIFT, tsz,
- vma->vm_page_prot))
+ if (remap_oldmem_pfn_range(vma, vma->vm_start + len,
+ paddr >> PAGE_SHIFT, tsz,
+ vma->vm_page_prot))
goto fail;
size -= tsz;
start += tsz;
@@ -357,7 +462,7 @@
notes_section = kmalloc(max_sz, GFP_KERNEL);
if (!notes_section)
return -ENOMEM;
- rc = read_from_oldmem(notes_section, max_sz, &offset, 0);
+ rc = elfcorehdr_read_notes(notes_section, max_sz, &offset);
if (rc < 0) {
kfree(notes_section);
return rc;
@@ -444,7 +549,8 @@
if (phdr_ptr->p_type != PT_NOTE)
continue;
offset = phdr_ptr->p_offset;
- rc = read_from_oldmem(notes_buf, phdr_ptr->p_memsz, &offset, 0);
+ rc = elfcorehdr_read_notes(notes_buf, phdr_ptr->p_memsz,
+ &offset);
if (rc < 0)
return rc;
notes_buf += phdr_ptr->p_memsz;
@@ -536,7 +642,7 @@
notes_section = kmalloc(max_sz, GFP_KERNEL);
if (!notes_section)
return -ENOMEM;
- rc = read_from_oldmem(notes_section, max_sz, &offset, 0);
+ rc = elfcorehdr_read_notes(notes_section, max_sz, &offset);
if (rc < 0) {
kfree(notes_section);
return rc;
@@ -623,7 +729,8 @@
if (phdr_ptr->p_type != PT_NOTE)
continue;
offset = phdr_ptr->p_offset;
- rc = read_from_oldmem(notes_buf, phdr_ptr->p_memsz, &offset, 0);
+ rc = elfcorehdr_read_notes(notes_buf, phdr_ptr->p_memsz,
+ &offset);
if (rc < 0)
return rc;
notes_buf += phdr_ptr->p_memsz;
@@ -810,7 +917,7 @@
addr = elfcorehdr_addr;
/* Read Elf header */
- rc = read_from_oldmem((char*)&ehdr, sizeof(Elf64_Ehdr), &addr, 0);
+ rc = elfcorehdr_read((char *)&ehdr, sizeof(Elf64_Ehdr), &addr);
if (rc < 0)
return rc;
@@ -837,7 +944,7 @@
if (!elfcorebuf)
return -ENOMEM;
addr = elfcorehdr_addr;
- rc = read_from_oldmem(elfcorebuf, elfcorebuf_sz_orig, &addr, 0);
+ rc = elfcorehdr_read(elfcorebuf, elfcorebuf_sz_orig, &addr);
if (rc < 0)
goto fail;
@@ -866,7 +973,7 @@
addr = elfcorehdr_addr;
/* Read Elf header */
- rc = read_from_oldmem((char*)&ehdr, sizeof(Elf32_Ehdr), &addr, 0);
+ rc = elfcorehdr_read((char *)&ehdr, sizeof(Elf32_Ehdr), &addr);
if (rc < 0)
return rc;
@@ -892,7 +999,7 @@
if (!elfcorebuf)
return -ENOMEM;
addr = elfcorehdr_addr;
- rc = read_from_oldmem(elfcorebuf, elfcorebuf_sz_orig, &addr, 0);
+ rc = elfcorehdr_read(elfcorebuf, elfcorebuf_sz_orig, &addr);
if (rc < 0)
goto fail;
@@ -919,7 +1026,7 @@
int rc=0;
addr = elfcorehdr_addr;
- rc = read_from_oldmem(e_ident, EI_NIDENT, &addr, 0);
+ rc = elfcorehdr_read(e_ident, EI_NIDENT, &addr);
if (rc < 0)
return rc;
if (memcmp(e_ident, ELFMAG, SELFMAG) != 0) {
@@ -952,7 +1059,14 @@
{
int rc = 0;
- /* If elfcorehdr= has been passed in cmdline, then capture the dump.*/
+ /* Allow architectures to allocate ELF header in 2nd kernel */
+ rc = elfcorehdr_alloc(&elfcorehdr_addr, &elfcorehdr_size);
+ if (rc)
+ return rc;
+ /*
+ * If elfcorehdr= has been passed in cmdline or created in 2nd kernel,
+ * then capture the dump.
+ */
if (!(is_vmcore_usable()))
return rc;
rc = parse_crash_elf_headers();
@@ -960,6 +1074,8 @@
pr_warn("Kdump: vmcore not initialized\n");
return rc;
}
+ elfcorehdr_free(elfcorehdr_addr);
+ elfcorehdr_addr = ELFCORE_ADDR_ERR;
proc_vmcore = proc_create("vmcore", S_IRUSR, NULL, &proc_vmcore_operations);
if (proc_vmcore)
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 9a702e19..831d49a 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -687,45 +687,37 @@
}
EXPORT_SYMBOL(dquot_quota_sync);
-/* Free unused dquots from cache */
-static void prune_dqcache(int count)
+static unsigned long
+dqcache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
{
struct list_head *head;
struct dquot *dquot;
+ unsigned long freed = 0;
head = free_dquots.prev;
- while (head != &free_dquots && count) {
+ while (head != &free_dquots && sc->nr_to_scan) {
dquot = list_entry(head, struct dquot, dq_free);
remove_dquot_hash(dquot);
remove_free_dquot(dquot);
remove_inuse(dquot);
do_destroy_dquot(dquot);
- count--;
+ sc->nr_to_scan--;
+ freed++;
head = free_dquots.prev;
}
+ return freed;
}
-/*
- * This is called from kswapd when we think we need some
- * more memory
- */
-static int shrink_dqcache_memory(struct shrinker *shrink,
- struct shrink_control *sc)
+static unsigned long
+dqcache_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
{
- int nr = sc->nr_to_scan;
-
- if (nr) {
- spin_lock(&dq_list_lock);
- prune_dqcache(nr);
- spin_unlock(&dq_list_lock);
- }
- return ((unsigned)
- percpu_counter_read_positive(&dqstats.counter[DQST_FREE_DQUOTS])
- /100) * sysctl_vfs_cache_pressure;
+ return vfs_pressure_ratio(
+ percpu_counter_read_positive(&dqstats.counter[DQST_FREE_DQUOTS]));
}
static struct shrinker dqcache_shrinker = {
- .shrink = shrink_dqcache_memory,
+ .count_objects = dqcache_shrink_count,
+ .scan_objects = dqcache_shrink_scan,
.seeks = DEFAULT_SEEKS,
};
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index c24f1e1..39d1465 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -244,12 +244,6 @@
return mount_nodev(fs_type, flags, data, ramfs_fill_super);
}
-static struct dentry *rootfs_mount(struct file_system_type *fs_type,
- int flags, const char *dev_name, void *data)
-{
- return mount_nodev(fs_type, flags|MS_NOUSER, data, ramfs_fill_super);
-}
-
static void ramfs_kill_sb(struct super_block *sb)
{
kfree(sb->s_fs_info);
@@ -262,29 +256,23 @@
.kill_sb = ramfs_kill_sb,
.fs_flags = FS_USERNS_MOUNT,
};
-static struct file_system_type rootfs_fs_type = {
- .name = "rootfs",
- .mount = rootfs_mount,
- .kill_sb = kill_litter_super,
-};
-static int __init init_ramfs_fs(void)
+int __init init_ramfs_fs(void)
{
- return register_filesystem(&ramfs_fs_type);
-}
-module_init(init_ramfs_fs)
-
-int __init init_rootfs(void)
-{
+ static unsigned long once;
int err;
+ if (test_and_set_bit(0, &once))
+ return 0;
+
err = bdi_init(&ramfs_backing_dev_info);
if (err)
return err;
- err = register_filesystem(&rootfs_fs_type);
+ err = register_filesystem(&ramfs_fs_type);
if (err)
bdi_destroy(&ramfs_backing_dev_info);
return err;
}
+module_init(init_ramfs_fs)
diff --git a/fs/read_write.c b/fs/read_write.c
index 122a384..e3cd280 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -367,7 +367,6 @@
init_sync_kiocb(&kiocb, filp);
kiocb.ki_pos = *ppos;
- kiocb.ki_left = len;
kiocb.ki_nbytes = len;
ret = filp->f_op->aio_read(&kiocb, &iov, 1, kiocb.ki_pos);
@@ -417,7 +416,6 @@
init_sync_kiocb(&kiocb, filp);
kiocb.ki_pos = *ppos;
- kiocb.ki_left = len;
kiocb.ki_nbytes = len;
ret = filp->f_op->aio_write(&kiocb, &iov, 1, kiocb.ki_pos);
@@ -599,7 +597,6 @@
init_sync_kiocb(&kiocb, filp);
kiocb.ki_pos = *ppos;
- kiocb.ki_left = len;
kiocb.ki_nbytes = len;
ret = fn(&kiocb, iov, nr_segs, kiocb.ki_pos);
diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c
index fb50652..41d108e 100644
--- a/fs/squashfs/block.c
+++ b/fs/squashfs/block.c
@@ -167,17 +167,14 @@
/*
* Block is uncompressed.
*/
- int i, in, pg_offset = 0;
-
- for (i = 0; i < b; i++) {
- wait_on_buffer(bh[i]);
- if (!buffer_uptodate(bh[i]))
- goto block_release;
- }
+ int in, pg_offset = 0;
for (bytes = length; k < b; k++) {
in = min(bytes, msblk->devblksize - offset);
bytes -= in;
+ wait_on_buffer(bh[k]);
+ if (!buffer_uptodate(bh[k]))
+ goto block_release;
while (in) {
if (pg_offset == PAGE_CACHE_SIZE) {
page++;
diff --git a/fs/squashfs/dir.c b/fs/squashfs/dir.c
index f7f527b..d8c2d74 100644
--- a/fs/squashfs/dir.c
+++ b/fs/squashfs/dir.c
@@ -54,6 +54,7 @@
{
struct squashfs_sb_info *msblk = sb->s_fs_info;
int err, i, index, length = 0;
+ unsigned int size;
struct squashfs_dir_index dir_index;
TRACE("Entered get_dir_index_using_offset, i_count %d, f_pos %lld\n",
@@ -81,8 +82,14 @@
*/
break;
+ size = le32_to_cpu(dir_index.size) + 1;
+
+ /* size should never be larger than SQUASHFS_NAME_LEN */
+ if (size > SQUASHFS_NAME_LEN)
+ break;
+
err = squashfs_read_metadata(sb, NULL, &index_start,
- &index_offset, le32_to_cpu(dir_index.size) + 1);
+ &index_offset, size);
if (err < 0)
break;
@@ -105,9 +112,8 @@
struct inode *inode = file_inode(file);
struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
u64 block = squashfs_i(inode)->start + msblk->directory_table;
- int offset = squashfs_i(inode)->offset, length, dir_count, size,
- type, err;
- unsigned int inode_number;
+ int offset = squashfs_i(inode)->offset, length, err;
+ unsigned int inode_number, dir_count, size, type;
struct squashfs_dir_header dirh;
struct squashfs_dir_entry *dire;
@@ -200,6 +206,9 @@
((short) le16_to_cpu(dire->inode_number));
type = le16_to_cpu(dire->type);
+ if (type > SQUASHFS_MAX_DIR_TYPE)
+ goto failed_read;
+
if (!dir_emit(ctx, dire->name, size,
inode_number,
squashfs_filetype_table[type]))
diff --git a/fs/squashfs/namei.c b/fs/squashfs/namei.c
index 7834a51..67cad77 100644
--- a/fs/squashfs/namei.c
+++ b/fs/squashfs/namei.c
@@ -79,7 +79,8 @@
int len)
{
struct squashfs_sb_info *msblk = sb->s_fs_info;
- int i, size, length = 0, err;
+ int i, length = 0, err;
+ unsigned int size;
struct squashfs_dir_index *index;
char *str;
@@ -103,6 +104,8 @@
size = le32_to_cpu(index->size) + 1;
+ if (size > SQUASHFS_NAME_LEN)
+ break;
err = squashfs_read_metadata(sb, index->name, &index_start,
&index_offset, size);
@@ -144,7 +147,8 @@
struct squashfs_dir_entry *dire;
u64 block = squashfs_i(dir)->start + msblk->directory_table;
int offset = squashfs_i(dir)->offset;
- int err, length, dir_count, size;
+ int err, length;
+ unsigned int dir_count, size;
TRACE("Entered squashfs_lookup [%llx:%x]\n", block, offset);
diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h
index 9e2349d..4b2beda 100644
--- a/fs/squashfs/squashfs_fs.h
+++ b/fs/squashfs/squashfs_fs.h
@@ -87,7 +87,7 @@
#define SQUASHFS_COMP_OPTS(flags) SQUASHFS_BIT(flags, \
SQUASHFS_COMP_OPT)
-/* Max number of types and file types */
+/* Inode types including extended types */
#define SQUASHFS_DIR_TYPE 1
#define SQUASHFS_REG_TYPE 2
#define SQUASHFS_SYMLINK_TYPE 3
@@ -103,6 +103,9 @@
#define SQUASHFS_LFIFO_TYPE 13
#define SQUASHFS_LSOCKET_TYPE 14
+/* Max type value stored in directory entry */
+#define SQUASHFS_MAX_DIR_TYPE 7
+
/* Xattr types */
#define SQUASHFS_XATTR_USER 0
#define SQUASHFS_XATTR_TRUSTED 1
diff --git a/fs/super.c b/fs/super.c
index f6961ea..3a96c97 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -53,11 +53,15 @@
* shrinker path and that leads to deadlock on the shrinker_rwsem. Hence we
* take a passive reference to the superblock to avoid this from occurring.
*/
-static int prune_super(struct shrinker *shrink, struct shrink_control *sc)
+static unsigned long super_cache_scan(struct shrinker *shrink,
+ struct shrink_control *sc)
{
struct super_block *sb;
- int fs_objects = 0;
- int total_objects;
+ long fs_objects = 0;
+ long total_objects;
+ long freed = 0;
+ long dentries;
+ long inodes;
sb = container_of(shrink, struct super_block, s_shrink);
@@ -65,46 +69,62 @@
* Deadlock avoidance. We may hold various FS locks, and we don't want
* to recurse into the FS that called us in clear_inode() and friends..
*/
- if (sc->nr_to_scan && !(sc->gfp_mask & __GFP_FS))
- return -1;
+ if (!(sc->gfp_mask & __GFP_FS))
+ return SHRINK_STOP;
if (!grab_super_passive(sb))
- return -1;
+ return SHRINK_STOP;
if (sb->s_op->nr_cached_objects)
- fs_objects = sb->s_op->nr_cached_objects(sb);
+ fs_objects = sb->s_op->nr_cached_objects(sb, sc->nid);
- total_objects = sb->s_nr_dentry_unused +
- sb->s_nr_inodes_unused + fs_objects + 1;
+ inodes = list_lru_count_node(&sb->s_inode_lru, sc->nid);
+ dentries = list_lru_count_node(&sb->s_dentry_lru, sc->nid);
+ total_objects = dentries + inodes + fs_objects + 1;
- if (sc->nr_to_scan) {
- int dentries;
- int inodes;
+ /* proportion the scan between the caches */
+ dentries = mult_frac(sc->nr_to_scan, dentries, total_objects);
+ inodes = mult_frac(sc->nr_to_scan, inodes, total_objects);
- /* proportion the scan between the caches */
- dentries = (sc->nr_to_scan * sb->s_nr_dentry_unused) /
- total_objects;
- inodes = (sc->nr_to_scan * sb->s_nr_inodes_unused) /
- total_objects;
- if (fs_objects)
- fs_objects = (sc->nr_to_scan * fs_objects) /
- total_objects;
- /*
- * prune the dcache first as the icache is pinned by it, then
- * prune the icache, followed by the filesystem specific caches
- */
- prune_dcache_sb(sb, dentries);
- prune_icache_sb(sb, inodes);
+ /*
+ * prune the dcache first as the icache is pinned by it, then
+ * prune the icache, followed by the filesystem specific caches
+ */
+ freed = prune_dcache_sb(sb, dentries, sc->nid);
+ freed += prune_icache_sb(sb, inodes, sc->nid);
- if (fs_objects && sb->s_op->free_cached_objects) {
- sb->s_op->free_cached_objects(sb, fs_objects);
- fs_objects = sb->s_op->nr_cached_objects(sb);
- }
- total_objects = sb->s_nr_dentry_unused +
- sb->s_nr_inodes_unused + fs_objects;
+ if (fs_objects) {
+ fs_objects = mult_frac(sc->nr_to_scan, fs_objects,
+ total_objects);
+ freed += sb->s_op->free_cached_objects(sb, fs_objects,
+ sc->nid);
}
- total_objects = (total_objects / 100) * sysctl_vfs_cache_pressure;
+ drop_super(sb);
+ return freed;
+}
+
+static unsigned long super_cache_count(struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ struct super_block *sb;
+ long total_objects = 0;
+
+ sb = container_of(shrink, struct super_block, s_shrink);
+
+ if (!grab_super_passive(sb))
+ return 0;
+
+ if (sb->s_op && sb->s_op->nr_cached_objects)
+ total_objects = sb->s_op->nr_cached_objects(sb,
+ sc->nid);
+
+ total_objects += list_lru_count_node(&sb->s_dentry_lru,
+ sc->nid);
+ total_objects += list_lru_count_node(&sb->s_inode_lru,
+ sc->nid);
+
+ total_objects = vfs_pressure_ratio(total_objects);
drop_super(sb);
return total_objects;
}
@@ -175,9 +195,12 @@
INIT_HLIST_NODE(&s->s_instances);
INIT_HLIST_BL_HEAD(&s->s_anon);
INIT_LIST_HEAD(&s->s_inodes);
- INIT_LIST_HEAD(&s->s_dentry_lru);
- INIT_LIST_HEAD(&s->s_inode_lru);
- spin_lock_init(&s->s_inode_lru_lock);
+
+ if (list_lru_init(&s->s_dentry_lru))
+ goto err_out;
+ if (list_lru_init(&s->s_inode_lru))
+ goto err_out_dentry_lru;
+
INIT_LIST_HEAD(&s->s_mounts);
init_rwsem(&s->s_umount);
lockdep_set_class(&s->s_umount, &type->s_umount_key);
@@ -210,11 +233,16 @@
s->cleancache_poolid = -1;
s->s_shrink.seeks = DEFAULT_SEEKS;
- s->s_shrink.shrink = prune_super;
+ s->s_shrink.scan_objects = super_cache_scan;
+ s->s_shrink.count_objects = super_cache_count;
s->s_shrink.batch = 1024;
+ s->s_shrink.flags = SHRINKER_NUMA_AWARE;
}
out:
return s;
+
+err_out_dentry_lru:
+ list_lru_destroy(&s->s_dentry_lru);
err_out:
security_sb_free(s);
#ifdef CONFIG_SMP
@@ -295,6 +323,9 @@
/* caches are now gone, we can safely kill the shrinker now */
unregister_shrinker(&s->s_shrink);
+ list_lru_destroy(&s->s_dentry_lru);
+ list_lru_destroy(&s->s_inode_lru);
+
put_filesystem(fs);
put_super(s);
} else {
diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c
index c1a591a..66bc316 100644
--- a/fs/sysv/itree.c
+++ b/fs/sysv/itree.c
@@ -469,7 +469,7 @@
struct inode *inode = mapping->host;
if (to > inode->i_size) {
- truncate_pagecache(inode, to, inode->i_size);
+ truncate_pagecache(inode, inode->i_size);
sysv_truncate(inode);
}
}
diff --git a/fs/ubifs/shrinker.c b/fs/ubifs/shrinker.c
index 9e1d056..f35135e 100644
--- a/fs/ubifs/shrinker.c
+++ b/fs/ubifs/shrinker.c
@@ -277,18 +277,25 @@
return 0;
}
-int ubifs_shrinker(struct shrinker *shrink, struct shrink_control *sc)
+unsigned long ubifs_shrink_count(struct shrinker *shrink,
+ struct shrink_control *sc)
{
- int nr = sc->nr_to_scan;
- int freed, contention = 0;
long clean_zn_cnt = atomic_long_read(&ubifs_clean_zn_cnt);
- if (nr == 0)
- /*
- * Due to the way UBIFS updates the clean znode counter it may
- * temporarily be negative.
- */
- return clean_zn_cnt >= 0 ? clean_zn_cnt : 1;
+ /*
+ * Due to the way UBIFS updates the clean znode counter it may
+ * temporarily be negative.
+ */
+ return clean_zn_cnt >= 0 ? clean_zn_cnt : 1;
+}
+
+unsigned long ubifs_shrink_scan(struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ unsigned long nr = sc->nr_to_scan;
+ int contention = 0;
+ unsigned long freed;
+ long clean_zn_cnt = atomic_long_read(&ubifs_clean_zn_cnt);
if (!clean_zn_cnt) {
/*
@@ -316,10 +323,10 @@
if (!freed && contention) {
dbg_tnc("freed nothing, but contention");
- return -1;
+ return SHRINK_STOP;
}
out:
- dbg_tnc("%d znodes were freed, requested %d", freed, nr);
+ dbg_tnc("%lu znodes were freed, requested %lu", freed, nr);
return freed;
}
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 879b997..3e4aa72 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -49,7 +49,8 @@
/* UBIFS TNC shrinker description */
static struct shrinker ubifs_shrinker_info = {
- .shrink = ubifs_shrinker,
+ .scan_objects = ubifs_shrink_scan,
+ .count_objects = ubifs_shrink_count,
.seeks = DEFAULT_SEEKS,
};
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index b2babce..e8c8cfe 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -1624,7 +1624,10 @@
int ubifs_tnc_end_commit(struct ubifs_info *c);
/* shrinker.c */
-int ubifs_shrinker(struct shrinker *shrink, struct shrink_control *sc);
+unsigned long ubifs_shrink_scan(struct shrinker *shrink,
+ struct shrink_control *sc);
+unsigned long ubifs_shrink_count(struct shrinker *shrink,
+ struct shrink_control *sc);
/* commit.c */
int ubifs_bg_thread(void *info);
diff --git a/fs/udf/file.c b/fs/udf/file.c
index 29569dd..c02a27a 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -141,7 +141,7 @@
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
int err, pos;
- size_t count = iocb->ki_left;
+ size_t count = iocb->ki_nbytes;
struct udf_inode_info *iinfo = UDF_I(inode);
down_write(&iinfo->i_data_sem);
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index b6d15d3..062b792 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -172,7 +172,7 @@
loff_t isize = inode->i_size;
if (to > isize) {
- truncate_pagecache(inode, to, isize);
+ truncate_pagecache(inode, isize);
if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) {
down_write(&iinfo->i_data_sem);
udf_clear_extent_cache(inode);
diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c
index ff24e44..c8ca960 100644
--- a/fs/ufs/inode.c
+++ b/fs/ufs/inode.c
@@ -531,7 +531,7 @@
struct inode *inode = mapping->host;
if (to > inode->i_size)
- truncate_pagecache(inode, to, inode->i_size);
+ truncate_pagecache(inode, inode->i_size);
}
static int ufs_write_begin(struct file *file, struct address_space *mapping,
diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c
index 4a7286c..a02cfb9 100644
--- a/fs/xfs/kmem.c
+++ b/fs/xfs/kmem.c
@@ -27,8 +27,6 @@
/*
* Greedy allocation. May fail and may return vmalloced memory.
- *
- * Must be freed using kmem_free_large.
*/
void *
kmem_zalloc_greedy(size_t *size, size_t minsize, size_t maxsize)
@@ -36,7 +34,7 @@
void *ptr;
size_t kmsize = maxsize;
- while (!(ptr = kmem_zalloc_large(kmsize))) {
+ while (!(ptr = vzalloc(kmsize))) {
if ((kmsize >>= 1) <= minsize)
kmsize = minsize;
}
@@ -75,6 +73,17 @@
return ptr;
}
+void *
+kmem_zalloc_large(size_t size, xfs_km_flags_t flags)
+{
+ void *ptr;
+
+ ptr = kmem_zalloc(size, flags | KM_MAYFAIL);
+ if (ptr)
+ return ptr;
+ return vzalloc(size);
+}
+
void
kmem_free(const void *ptr)
{
diff --git a/fs/xfs/kmem.h b/fs/xfs/kmem.h
index b2f2620..3a7371c 100644
--- a/fs/xfs/kmem.h
+++ b/fs/xfs/kmem.h
@@ -57,17 +57,10 @@
extern void *kmem_alloc(size_t, xfs_km_flags_t);
extern void *kmem_zalloc(size_t, xfs_km_flags_t);
+extern void *kmem_zalloc_large(size_t size, xfs_km_flags_t);
extern void *kmem_realloc(const void *, size_t, size_t, xfs_km_flags_t);
extern void kmem_free(const void *);
-static inline void *kmem_zalloc_large(size_t size)
-{
- return vzalloc(size);
-}
-static inline void kmem_free_large(void *ptr)
-{
- vfree(ptr);
-}
extern void *kmem_zalloc_greedy(size_t *, size_t, size_t);
diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c
index 6951896..0e2f37e 100644
--- a/fs/xfs/xfs_acl.c
+++ b/fs/xfs/xfs_acl.c
@@ -152,7 +152,7 @@
* go out to the disk.
*/
len = XFS_ACL_MAX_SIZE(ip->i_mount);
- xfs_acl = kzalloc(len, GFP_KERNEL);
+ xfs_acl = kmem_zalloc_large(len, KM_SLEEP);
if (!xfs_acl)
return ERR_PTR(-ENOMEM);
@@ -175,10 +175,10 @@
if (IS_ERR(acl))
goto out;
- out_update_cache:
+out_update_cache:
set_cached_acl(inode, type, acl);
- out:
- kfree(xfs_acl);
+out:
+ kmem_free(xfs_acl);
return acl;
}
@@ -209,7 +209,7 @@
struct xfs_acl *xfs_acl;
int len = XFS_ACL_MAX_SIZE(ip->i_mount);
- xfs_acl = kzalloc(len, GFP_KERNEL);
+ xfs_acl = kmem_zalloc_large(len, KM_SLEEP);
if (!xfs_acl)
return -ENOMEM;
@@ -222,7 +222,7 @@
error = -xfs_attr_set(ip, ea_name, (unsigned char *)xfs_acl,
len, ATTR_ROOT);
- kfree(xfs_acl);
+ kmem_free(xfs_acl);
} else {
/*
* A NULL ACL argument means we want to remove the ACL.
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 977da0e..e51e581 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1582,7 +1582,7 @@
unlock_page(page);
if (pos + len > i_size_read(inode))
- truncate_pagecache(inode, pos + len, i_size_read(inode));
+ truncate_pagecache(inode, i_size_read(inode));
page_cache_release(page);
page = NULL;
@@ -1618,7 +1618,7 @@
loff_t to = pos + len;
if (to > isize) {
- truncate_pagecache(inode, to, isize);
+ truncate_pagecache(inode, isize);
xfs_vm_kill_delalloc_range(inode, isize, to);
}
}
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index 92b8309..f47e65c 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -4450,7 +4450,7 @@
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_ifork *ifp;
- struct xfs_bmalloca bma = { 0 }; /* args for xfs_bmap_alloc */
+ struct xfs_bmalloca bma = { NULL }; /* args for xfs_bmap_alloc */
xfs_fileoff_t end; /* end of mapped file region */
int eof; /* after the end of extents */
int error; /* error return */
diff --git a/fs/xfs/xfs_bmap_btree.c b/fs/xfs/xfs_bmap_btree.c
index cf3bc76..bb8de8e 100644
--- a/fs/xfs/xfs_bmap_btree.c
+++ b/fs/xfs/xfs_bmap_btree.c
@@ -925,3 +925,47 @@
return blocklen / sizeof(xfs_bmdr_rec_t);
return blocklen / (sizeof(xfs_bmdr_key_t) + sizeof(xfs_bmdr_ptr_t));
}
+
+/*
+ * Change the owner of a btree format fork fo the inode passed in. Change it to
+ * the owner of that is passed in so that we can change owners before or after
+ * we switch forks between inodes. The operation that the caller is doing will
+ * determine whether is needs to change owner before or after the switch.
+ *
+ * For demand paged transactional modification, the fork switch should be done
+ * after reading in all the blocks, modifying them and pinning them in the
+ * transaction. For modification when the buffers are already pinned in memory,
+ * the fork switch can be done before changing the owner as we won't need to
+ * validate the owner until the btree buffers are unpinned and writes can occur
+ * again.
+ *
+ * For recovery based ownership change, there is no transactional context and
+ * so a buffer list must be supplied so that we can record the buffers that we
+ * modified for the caller to issue IO on.
+ */
+int
+xfs_bmbt_change_owner(
+ struct xfs_trans *tp,
+ struct xfs_inode *ip,
+ int whichfork,
+ xfs_ino_t new_owner,
+ struct list_head *buffer_list)
+{
+ struct xfs_btree_cur *cur;
+ int error;
+
+ ASSERT(tp || buffer_list);
+ ASSERT(!(tp && buffer_list));
+ if (whichfork == XFS_DATA_FORK)
+ ASSERT(ip->i_d.di_format == XFS_DINODE_FMT_BTREE);
+ else
+ ASSERT(ip->i_d.di_aformat == XFS_DINODE_FMT_BTREE);
+
+ cur = xfs_bmbt_init_cursor(ip->i_mount, tp, ip, whichfork);
+ if (!cur)
+ return ENOMEM;
+
+ error = xfs_btree_change_owner(cur, new_owner, buffer_list);
+ xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+ return error;
+}
diff --git a/fs/xfs/xfs_bmap_btree.h b/fs/xfs/xfs_bmap_btree.h
index 1b726d6..e367461 100644
--- a/fs/xfs/xfs_bmap_btree.h
+++ b/fs/xfs/xfs_bmap_btree.h
@@ -236,6 +236,10 @@
extern int xfs_bmdr_maxrecs(struct xfs_mount *, int blocklen, int leaf);
extern int xfs_bmbt_maxrecs(struct xfs_mount *, int blocklen, int leaf);
+extern int xfs_bmbt_change_owner(struct xfs_trans *tp, struct xfs_inode *ip,
+ int whichfork, xfs_ino_t new_owner,
+ struct list_head *buffer_list);
+
extern struct xfs_btree_cur *xfs_bmbt_init_cursor(struct xfs_mount *,
struct xfs_trans *, struct xfs_inode *, int);
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 541d59f..97f952c 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -612,13 +612,9 @@
if (bmv->bmv_count > ULONG_MAX / sizeof(struct getbmapx))
return XFS_ERROR(ENOMEM);
- out = kmem_zalloc(bmv->bmv_count * sizeof(struct getbmapx), KM_MAYFAIL);
- if (!out) {
- out = kmem_zalloc_large(bmv->bmv_count *
- sizeof(struct getbmapx));
- if (!out)
- return XFS_ERROR(ENOMEM);
- }
+ out = kmem_zalloc_large(bmv->bmv_count * sizeof(struct getbmapx), 0);
+ if (!out)
+ return XFS_ERROR(ENOMEM);
xfs_ilock(ip, XFS_IOLOCK_SHARED);
if (whichfork == XFS_DATA_FORK && !(iflags & BMV_IF_DELALLOC)) {
@@ -754,10 +750,7 @@
break;
}
- if (is_vmalloc_addr(out))
- kmem_free_large(out);
- else
- kmem_free(out);
+ kmem_free(out);
return error;
}
@@ -1789,14 +1782,6 @@
int taforkblks = 0;
__uint64_t tmp;
- /*
- * We have no way of updating owner information in the BMBT blocks for
- * each inode on CRC enabled filesystems, so to avoid corrupting the
- * this metadata we simply don't allow extent swaps to occur.
- */
- if (xfs_sb_version_hascrc(&mp->m_sb))
- return XFS_ERROR(EINVAL);
-
tempifp = kmem_alloc(sizeof(xfs_ifork_t), KM_MAYFAIL);
if (!tempifp) {
error = XFS_ERROR(ENOMEM);
@@ -1920,6 +1905,42 @@
goto out_trans_cancel;
}
+ xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+ xfs_trans_ijoin(tp, tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+
+ /*
+ * Before we've swapped the forks, lets set the owners of the forks
+ * appropriately. We have to do this as we are demand paging the btree
+ * buffers, and so the validation done on read will expect the owner
+ * field to be correctly set. Once we change the owners, we can swap the
+ * inode forks.
+ *
+ * Note the trickiness in setting the log flags - we set the owner log
+ * flag on the opposite inode (i.e. the inode we are setting the new
+ * owner to be) because once we swap the forks and log that, log
+ * recovery is going to see the fork as owned by the swapped inode,
+ * not the pre-swapped inodes.
+ */
+ src_log_flags = XFS_ILOG_CORE;
+ target_log_flags = XFS_ILOG_CORE;
+ if (ip->i_d.di_version == 3 &&
+ ip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
+ target_log_flags |= XFS_ILOG_DOWNER;
+ error = xfs_bmbt_change_owner(tp, ip, XFS_DATA_FORK,
+ tip->i_ino, NULL);
+ if (error)
+ goto out_trans_cancel;
+ }
+
+ if (tip->i_d.di_version == 3 &&
+ tip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
+ src_log_flags |= XFS_ILOG_DOWNER;
+ error = xfs_bmbt_change_owner(tp, tip, XFS_DATA_FORK,
+ ip->i_ino, NULL);
+ if (error)
+ goto out_trans_cancel;
+ }
+
/*
* Swap the data forks of the inodes
*/
@@ -1957,7 +1978,6 @@
tip->i_delayed_blks = ip->i_delayed_blks;
ip->i_delayed_blks = 0;
- src_log_flags = XFS_ILOG_CORE;
switch (ip->i_d.di_format) {
case XFS_DINODE_FMT_EXTENTS:
/* If the extents fit in the inode, fix the
@@ -1971,11 +1991,12 @@
src_log_flags |= XFS_ILOG_DEXT;
break;
case XFS_DINODE_FMT_BTREE:
+ ASSERT(ip->i_d.di_version < 3 ||
+ (src_log_flags & XFS_ILOG_DOWNER));
src_log_flags |= XFS_ILOG_DBROOT;
break;
}
- target_log_flags = XFS_ILOG_CORE;
switch (tip->i_d.di_format) {
case XFS_DINODE_FMT_EXTENTS:
/* If the extents fit in the inode, fix the
@@ -1990,13 +2011,11 @@
break;
case XFS_DINODE_FMT_BTREE:
target_log_flags |= XFS_ILOG_DBROOT;
+ ASSERT(tip->i_d.di_version < 3 ||
+ (target_log_flags & XFS_ILOG_DOWNER));
break;
}
-
- xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
- xfs_trans_ijoin(tp, tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
-
xfs_trans_log_inode(tp, ip, src_log_flags);
xfs_trans_log_inode(tp, tip, target_log_flags);
diff --git a/fs/xfs/xfs_btree.c b/fs/xfs/xfs_btree.c
index 7a2b4da..5690e102 100644
--- a/fs/xfs/xfs_btree.c
+++ b/fs/xfs/xfs_btree.c
@@ -855,6 +855,41 @@
return xfs_btree_readahead_sblock(cur, lr, block);
}
+STATIC xfs_daddr_t
+xfs_btree_ptr_to_daddr(
+ struct xfs_btree_cur *cur,
+ union xfs_btree_ptr *ptr)
+{
+ if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
+ ASSERT(ptr->l != cpu_to_be64(NULLDFSBNO));
+
+ return XFS_FSB_TO_DADDR(cur->bc_mp, be64_to_cpu(ptr->l));
+ } else {
+ ASSERT(cur->bc_private.a.agno != NULLAGNUMBER);
+ ASSERT(ptr->s != cpu_to_be32(NULLAGBLOCK));
+
+ return XFS_AGB_TO_DADDR(cur->bc_mp, cur->bc_private.a.agno,
+ be32_to_cpu(ptr->s));
+ }
+}
+
+/*
+ * Readahead @count btree blocks at the given @ptr location.
+ *
+ * We don't need to care about long or short form btrees here as we have a
+ * method of converting the ptr directly to a daddr available to us.
+ */
+STATIC void
+xfs_btree_readahead_ptr(
+ struct xfs_btree_cur *cur,
+ union xfs_btree_ptr *ptr,
+ xfs_extlen_t count)
+{
+ xfs_buf_readahead(cur->bc_mp->m_ddev_targp,
+ xfs_btree_ptr_to_daddr(cur, ptr),
+ cur->bc_mp->m_bsize * count, cur->bc_ops->buf_ops);
+}
+
/*
* Set the buffer for level "lev" in the cursor to bp, releasing
* any previous buffer.
@@ -1073,24 +1108,6 @@
}
}
-STATIC xfs_daddr_t
-xfs_btree_ptr_to_daddr(
- struct xfs_btree_cur *cur,
- union xfs_btree_ptr *ptr)
-{
- if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
- ASSERT(ptr->l != cpu_to_be64(NULLDFSBNO));
-
- return XFS_FSB_TO_DADDR(cur->bc_mp, be64_to_cpu(ptr->l));
- } else {
- ASSERT(cur->bc_private.a.agno != NULLAGNUMBER);
- ASSERT(ptr->s != cpu_to_be32(NULLAGBLOCK));
-
- return XFS_AGB_TO_DADDR(cur->bc_mp, cur->bc_private.a.agno,
- be32_to_cpu(ptr->s));
- }
-}
-
STATIC void
xfs_btree_set_refs(
struct xfs_btree_cur *cur,
@@ -3869,3 +3886,120 @@
*stat = 1;
return 0;
}
+
+/*
+ * Change the owner of a btree.
+ *
+ * The mechanism we use here is ordered buffer logging. Because we don't know
+ * how many buffers were are going to need to modify, we don't really want to
+ * have to make transaction reservations for the worst case of every buffer in a
+ * full size btree as that may be more space that we can fit in the log....
+ *
+ * We do the btree walk in the most optimal manner possible - we have sibling
+ * pointers so we can just walk all the blocks on each level from left to right
+ * in a single pass, and then move to the next level and do the same. We can
+ * also do readahead on the sibling pointers to get IO moving more quickly,
+ * though for slow disks this is unlikely to make much difference to performance
+ * as the amount of CPU work we have to do before moving to the next block is
+ * relatively small.
+ *
+ * For each btree block that we load, modify the owner appropriately, set the
+ * buffer as an ordered buffer and log it appropriately. We need to ensure that
+ * we mark the region we change dirty so that if the buffer is relogged in
+ * a subsequent transaction the changes we make here as an ordered buffer are
+ * correctly relogged in that transaction. If we are in recovery context, then
+ * just queue the modified buffer as delayed write buffer so the transaction
+ * recovery completion writes the changes to disk.
+ */
+static int
+xfs_btree_block_change_owner(
+ struct xfs_btree_cur *cur,
+ int level,
+ __uint64_t new_owner,
+ struct list_head *buffer_list)
+{
+ struct xfs_btree_block *block;
+ struct xfs_buf *bp;
+ union xfs_btree_ptr rptr;
+
+ /* do right sibling readahead */
+ xfs_btree_readahead(cur, level, XFS_BTCUR_RIGHTRA);
+
+ /* modify the owner */
+ block = xfs_btree_get_block(cur, level, &bp);
+ if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+ block->bb_u.l.bb_owner = cpu_to_be64(new_owner);
+ else
+ block->bb_u.s.bb_owner = cpu_to_be32(new_owner);
+
+ /*
+ * If the block is a root block hosted in an inode, we might not have a
+ * buffer pointer here and we shouldn't attempt to log the change as the
+ * information is already held in the inode and discarded when the root
+ * block is formatted into the on-disk inode fork. We still change it,
+ * though, so everything is consistent in memory.
+ */
+ if (bp) {
+ if (cur->bc_tp) {
+ xfs_trans_ordered_buf(cur->bc_tp, bp);
+ xfs_btree_log_block(cur, bp, XFS_BB_OWNER);
+ } else {
+ xfs_buf_delwri_queue(bp, buffer_list);
+ }
+ } else {
+ ASSERT(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE);
+ ASSERT(level == cur->bc_nlevels - 1);
+ }
+
+ /* now read rh sibling block for next iteration */
+ xfs_btree_get_sibling(cur, block, &rptr, XFS_BB_RIGHTSIB);
+ if (xfs_btree_ptr_is_null(cur, &rptr))
+ return ENOENT;
+
+ return xfs_btree_lookup_get_block(cur, level, &rptr, &block);
+}
+
+int
+xfs_btree_change_owner(
+ struct xfs_btree_cur *cur,
+ __uint64_t new_owner,
+ struct list_head *buffer_list)
+{
+ union xfs_btree_ptr lptr;
+ int level;
+ struct xfs_btree_block *block = NULL;
+ int error = 0;
+
+ cur->bc_ops->init_ptr_from_cur(cur, &lptr);
+
+ /* for each level */
+ for (level = cur->bc_nlevels - 1; level >= 0; level--) {
+ /* grab the left hand block */
+ error = xfs_btree_lookup_get_block(cur, level, &lptr, &block);
+ if (error)
+ return error;
+
+ /* readahead the left most block for the next level down */
+ if (level > 0) {
+ union xfs_btree_ptr *ptr;
+
+ ptr = xfs_btree_ptr_addr(cur, 1, block);
+ xfs_btree_readahead_ptr(cur, ptr, 1);
+
+ /* save for the next iteration of the loop */
+ lptr = *ptr;
+ }
+
+ /* for each buffer in the level */
+ do {
+ error = xfs_btree_block_change_owner(cur, level,
+ new_owner,
+ buffer_list);
+ } while (!error);
+
+ if (error != ENOENT)
+ return error;
+ }
+
+ return 0;
+}
diff --git a/fs/xfs/xfs_btree.h b/fs/xfs/xfs_btree.h
index c8473c7..06729b6 100644
--- a/fs/xfs/xfs_btree.h
+++ b/fs/xfs/xfs_btree.h
@@ -121,15 +121,18 @@
/*
* For logging record fields.
*/
-#define XFS_BB_MAGIC 0x01
-#define XFS_BB_LEVEL 0x02
-#define XFS_BB_NUMRECS 0x04
-#define XFS_BB_LEFTSIB 0x08
-#define XFS_BB_RIGHTSIB 0x10
-#define XFS_BB_BLKNO 0x20
+#define XFS_BB_MAGIC (1 << 0)
+#define XFS_BB_LEVEL (1 << 1)
+#define XFS_BB_NUMRECS (1 << 2)
+#define XFS_BB_LEFTSIB (1 << 3)
+#define XFS_BB_RIGHTSIB (1 << 4)
+#define XFS_BB_BLKNO (1 << 5)
+#define XFS_BB_LSN (1 << 6)
+#define XFS_BB_UUID (1 << 7)
+#define XFS_BB_OWNER (1 << 8)
#define XFS_BB_NUM_BITS 5
#define XFS_BB_ALL_BITS ((1 << XFS_BB_NUM_BITS) - 1)
-#define XFS_BB_NUM_BITS_CRC 8
+#define XFS_BB_NUM_BITS_CRC 9
#define XFS_BB_ALL_BITS_CRC ((1 << XFS_BB_NUM_BITS_CRC) - 1)
/*
@@ -442,6 +445,8 @@
int xfs_btree_insert(struct xfs_btree_cur *, int *);
int xfs_btree_delete(struct xfs_btree_cur *, int *);
int xfs_btree_get_rec(struct xfs_btree_cur *, union xfs_btree_rec **, int *);
+int xfs_btree_change_owner(struct xfs_btree_cur *cur, __uint64_t new_owner,
+ struct list_head *buffer_list);
/*
* btree block CRC helpers
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index c06823f..2634700 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -81,54 +81,6 @@
}
/*
- * xfs_buf_lru_add - add a buffer to the LRU.
- *
- * The LRU takes a new reference to the buffer so that it will only be freed
- * once the shrinker takes the buffer off the LRU.
- */
-STATIC void
-xfs_buf_lru_add(
- struct xfs_buf *bp)
-{
- struct xfs_buftarg *btp = bp->b_target;
-
- spin_lock(&btp->bt_lru_lock);
- if (list_empty(&bp->b_lru)) {
- atomic_inc(&bp->b_hold);
- list_add_tail(&bp->b_lru, &btp->bt_lru);
- btp->bt_lru_nr++;
- bp->b_lru_flags &= ~_XBF_LRU_DISPOSE;
- }
- spin_unlock(&btp->bt_lru_lock);
-}
-
-/*
- * xfs_buf_lru_del - remove a buffer from the LRU
- *
- * The unlocked check is safe here because it only occurs when there are not
- * b_lru_ref counts left on the inode under the pag->pag_buf_lock. it is there
- * to optimise the shrinker removing the buffer from the LRU and calling
- * xfs_buf_free(). i.e. it removes an unnecessary round trip on the
- * bt_lru_lock.
- */
-STATIC void
-xfs_buf_lru_del(
- struct xfs_buf *bp)
-{
- struct xfs_buftarg *btp = bp->b_target;
-
- if (list_empty(&bp->b_lru))
- return;
-
- spin_lock(&btp->bt_lru_lock);
- if (!list_empty(&bp->b_lru)) {
- list_del_init(&bp->b_lru);
- btp->bt_lru_nr--;
- }
- spin_unlock(&btp->bt_lru_lock);
-}
-
-/*
* When we mark a buffer stale, we remove the buffer from the LRU and clear the
* b_lru_ref count so that the buffer is freed immediately when the buffer
* reference count falls to zero. If the buffer is already on the LRU, we need
@@ -151,20 +103,14 @@
*/
bp->b_flags &= ~_XBF_DELWRI_Q;
- atomic_set(&(bp)->b_lru_ref, 0);
- if (!list_empty(&bp->b_lru)) {
- struct xfs_buftarg *btp = bp->b_target;
+ spin_lock(&bp->b_lock);
+ atomic_set(&bp->b_lru_ref, 0);
+ if (!(bp->b_state & XFS_BSTATE_DISPOSE) &&
+ (list_lru_del(&bp->b_target->bt_lru, &bp->b_lru)))
+ atomic_dec(&bp->b_hold);
- spin_lock(&btp->bt_lru_lock);
- if (!list_empty(&bp->b_lru) &&
- !(bp->b_lru_flags & _XBF_LRU_DISPOSE)) {
- list_del_init(&bp->b_lru);
- btp->bt_lru_nr--;
- atomic_dec(&bp->b_hold);
- }
- spin_unlock(&btp->bt_lru_lock);
- }
ASSERT(atomic_read(&bp->b_hold) >= 1);
+ spin_unlock(&bp->b_lock);
}
static int
@@ -228,6 +174,7 @@
INIT_LIST_HEAD(&bp->b_list);
RB_CLEAR_NODE(&bp->b_rbnode);
sema_init(&bp->b_sema, 0); /* held, no waiters */
+ spin_lock_init(&bp->b_lock);
XB_SET_OWNER(bp);
bp->b_target = target;
bp->b_flags = flags;
@@ -917,12 +864,33 @@
ASSERT(atomic_read(&bp->b_hold) > 0);
if (atomic_dec_and_lock(&bp->b_hold, &pag->pag_buf_lock)) {
- if (!(bp->b_flags & XBF_STALE) &&
- atomic_read(&bp->b_lru_ref)) {
- xfs_buf_lru_add(bp);
+ spin_lock(&bp->b_lock);
+ if (!(bp->b_flags & XBF_STALE) && atomic_read(&bp->b_lru_ref)) {
+ /*
+ * If the buffer is added to the LRU take a new
+ * reference to the buffer for the LRU and clear the
+ * (now stale) dispose list state flag
+ */
+ if (list_lru_add(&bp->b_target->bt_lru, &bp->b_lru)) {
+ bp->b_state &= ~XFS_BSTATE_DISPOSE;
+ atomic_inc(&bp->b_hold);
+ }
+ spin_unlock(&bp->b_lock);
spin_unlock(&pag->pag_buf_lock);
} else {
- xfs_buf_lru_del(bp);
+ /*
+ * most of the time buffers will already be removed from
+ * the LRU, so optimise that case by checking for the
+ * XFS_BSTATE_DISPOSE flag indicating the last list the
+ * buffer was on was the disposal list
+ */
+ if (!(bp->b_state & XFS_BSTATE_DISPOSE)) {
+ list_lru_del(&bp->b_target->bt_lru, &bp->b_lru);
+ } else {
+ ASSERT(list_empty(&bp->b_lru));
+ }
+ spin_unlock(&bp->b_lock);
+
ASSERT(!(bp->b_flags & _XBF_DELWRI_Q));
rb_erase(&bp->b_rbnode, &pag->pag_buf_tree);
spin_unlock(&pag->pag_buf_lock);
@@ -1502,83 +1470,121 @@
* returned. These buffers will have an elevated hold count, so wait on those
* while freeing all the buffers only held by the LRU.
*/
+static enum lru_status
+xfs_buftarg_wait_rele(
+ struct list_head *item,
+ spinlock_t *lru_lock,
+ void *arg)
+
+{
+ struct xfs_buf *bp = container_of(item, struct xfs_buf, b_lru);
+ struct list_head *dispose = arg;
+
+ if (atomic_read(&bp->b_hold) > 1) {
+ /* need to wait, so skip it this pass */
+ trace_xfs_buf_wait_buftarg(bp, _RET_IP_);
+ return LRU_SKIP;
+ }
+ if (!spin_trylock(&bp->b_lock))
+ return LRU_SKIP;
+
+ /*
+ * clear the LRU reference count so the buffer doesn't get
+ * ignored in xfs_buf_rele().
+ */
+ atomic_set(&bp->b_lru_ref, 0);
+ bp->b_state |= XFS_BSTATE_DISPOSE;
+ list_move(item, dispose);
+ spin_unlock(&bp->b_lock);
+ return LRU_REMOVED;
+}
+
void
xfs_wait_buftarg(
struct xfs_buftarg *btp)
{
- struct xfs_buf *bp;
+ LIST_HEAD(dispose);
+ int loop = 0;
-restart:
- spin_lock(&btp->bt_lru_lock);
- while (!list_empty(&btp->bt_lru)) {
- bp = list_first_entry(&btp->bt_lru, struct xfs_buf, b_lru);
- if (atomic_read(&bp->b_hold) > 1) {
- trace_xfs_buf_wait_buftarg(bp, _RET_IP_);
- list_move_tail(&bp->b_lru, &btp->bt_lru);
- spin_unlock(&btp->bt_lru_lock);
- delay(100);
- goto restart;
+ /* loop until there is nothing left on the lru list. */
+ while (list_lru_count(&btp->bt_lru)) {
+ list_lru_walk(&btp->bt_lru, xfs_buftarg_wait_rele,
+ &dispose, LONG_MAX);
+
+ while (!list_empty(&dispose)) {
+ struct xfs_buf *bp;
+ bp = list_first_entry(&dispose, struct xfs_buf, b_lru);
+ list_del_init(&bp->b_lru);
+ xfs_buf_rele(bp);
}
- /*
- * clear the LRU reference count so the buffer doesn't get
- * ignored in xfs_buf_rele().
- */
- atomic_set(&bp->b_lru_ref, 0);
- spin_unlock(&btp->bt_lru_lock);
- xfs_buf_rele(bp);
- spin_lock(&btp->bt_lru_lock);
+ if (loop++ != 0)
+ delay(100);
}
- spin_unlock(&btp->bt_lru_lock);
}
-int
-xfs_buftarg_shrink(
+static enum lru_status
+xfs_buftarg_isolate(
+ struct list_head *item,
+ spinlock_t *lru_lock,
+ void *arg)
+{
+ struct xfs_buf *bp = container_of(item, struct xfs_buf, b_lru);
+ struct list_head *dispose = arg;
+
+ /*
+ * we are inverting the lru lock/bp->b_lock here, so use a trylock.
+ * If we fail to get the lock, just skip it.
+ */
+ if (!spin_trylock(&bp->b_lock))
+ return LRU_SKIP;
+ /*
+ * Decrement the b_lru_ref count unless the value is already
+ * zero. If the value is already zero, we need to reclaim the
+ * buffer, otherwise it gets another trip through the LRU.
+ */
+ if (!atomic_add_unless(&bp->b_lru_ref, -1, 0)) {
+ spin_unlock(&bp->b_lock);
+ return LRU_ROTATE;
+ }
+
+ bp->b_state |= XFS_BSTATE_DISPOSE;
+ list_move(item, dispose);
+ spin_unlock(&bp->b_lock);
+ return LRU_REMOVED;
+}
+
+static unsigned long
+xfs_buftarg_shrink_scan(
struct shrinker *shrink,
struct shrink_control *sc)
{
struct xfs_buftarg *btp = container_of(shrink,
struct xfs_buftarg, bt_shrinker);
- struct xfs_buf *bp;
- int nr_to_scan = sc->nr_to_scan;
LIST_HEAD(dispose);
+ unsigned long freed;
+ unsigned long nr_to_scan = sc->nr_to_scan;
- if (!nr_to_scan)
- return btp->bt_lru_nr;
-
- spin_lock(&btp->bt_lru_lock);
- while (!list_empty(&btp->bt_lru)) {
- if (nr_to_scan-- <= 0)
- break;
-
- bp = list_first_entry(&btp->bt_lru, struct xfs_buf, b_lru);
-
- /*
- * Decrement the b_lru_ref count unless the value is already
- * zero. If the value is already zero, we need to reclaim the
- * buffer, otherwise it gets another trip through the LRU.
- */
- if (!atomic_add_unless(&bp->b_lru_ref, -1, 0)) {
- list_move_tail(&bp->b_lru, &btp->bt_lru);
- continue;
- }
-
- /*
- * remove the buffer from the LRU now to avoid needing another
- * lock round trip inside xfs_buf_rele().
- */
- list_move(&bp->b_lru, &dispose);
- btp->bt_lru_nr--;
- bp->b_lru_flags |= _XBF_LRU_DISPOSE;
- }
- spin_unlock(&btp->bt_lru_lock);
+ freed = list_lru_walk_node(&btp->bt_lru, sc->nid, xfs_buftarg_isolate,
+ &dispose, &nr_to_scan);
while (!list_empty(&dispose)) {
+ struct xfs_buf *bp;
bp = list_first_entry(&dispose, struct xfs_buf, b_lru);
list_del_init(&bp->b_lru);
xfs_buf_rele(bp);
}
- return btp->bt_lru_nr;
+ return freed;
+}
+
+static unsigned long
+xfs_buftarg_shrink_count(
+ struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ struct xfs_buftarg *btp = container_of(shrink,
+ struct xfs_buftarg, bt_shrinker);
+ return list_lru_count_node(&btp->bt_lru, sc->nid);
}
void
@@ -1587,6 +1593,7 @@
struct xfs_buftarg *btp)
{
unregister_shrinker(&btp->bt_shrinker);
+ list_lru_destroy(&btp->bt_lru);
if (mp->m_flags & XFS_MOUNT_BARRIER)
xfs_blkdev_issue_flush(btp);
@@ -1660,12 +1667,16 @@
if (!btp->bt_bdi)
goto error;
- INIT_LIST_HEAD(&btp->bt_lru);
- spin_lock_init(&btp->bt_lru_lock);
if (xfs_setsize_buftarg_early(btp, bdev))
goto error;
- btp->bt_shrinker.shrink = xfs_buftarg_shrink;
+
+ if (list_lru_init(&btp->bt_lru))
+ goto error;
+
+ btp->bt_shrinker.count_objects = xfs_buftarg_shrink_count;
+ btp->bt_shrinker.scan_objects = xfs_buftarg_shrink_scan;
btp->bt_shrinker.seeks = DEFAULT_SEEKS;
+ btp->bt_shrinker.flags = SHRINKER_NUMA_AWARE;
register_shrinker(&btp->bt_shrinker);
return btp;
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 433a12e..e656833 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -25,6 +25,7 @@
#include <linux/fs.h>
#include <linux/buffer_head.h>
#include <linux/uio.h>
+#include <linux/list_lru.h>
/*
* Base types
@@ -59,7 +60,6 @@
#define _XBF_KMEM (1 << 21)/* backed by heap memory */
#define _XBF_DELWRI_Q (1 << 22)/* buffer on a delwri queue */
#define _XBF_COMPOUND (1 << 23)/* compound buffer */
-#define _XBF_LRU_DISPOSE (1 << 24)/* buffer being discarded */
typedef unsigned int xfs_buf_flags_t;
@@ -78,8 +78,12 @@
{ _XBF_PAGES, "PAGES" }, \
{ _XBF_KMEM, "KMEM" }, \
{ _XBF_DELWRI_Q, "DELWRI_Q" }, \
- { _XBF_COMPOUND, "COMPOUND" }, \
- { _XBF_LRU_DISPOSE, "LRU_DISPOSE" }
+ { _XBF_COMPOUND, "COMPOUND" }
+
+/*
+ * Internal state flags.
+ */
+#define XFS_BSTATE_DISPOSE (1 << 0) /* buffer being discarded */
typedef struct xfs_buftarg {
dev_t bt_dev;
@@ -92,9 +96,7 @@
/* LRU control structures */
struct shrinker bt_shrinker;
- struct list_head bt_lru;
- spinlock_t bt_lru_lock;
- unsigned int bt_lru_nr;
+ struct list_lru bt_lru;
} xfs_buftarg_t;
struct xfs_buf;
@@ -137,7 +139,8 @@
* bt_lru_lock and not by b_sema
*/
struct list_head b_lru; /* lru list */
- xfs_buf_flags_t b_lru_flags; /* internal lru status flags */
+ spinlock_t b_lock; /* internal state lock */
+ unsigned int b_state; /* internal state flags */
wait_queue_head_t b_waiters; /* unpin waiters */
struct list_head b_list;
struct xfs_perag *b_pag; /* contains rbtree root */
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 3a944b1..88c5ea7 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -613,13 +613,27 @@
}
}
}
- if (clean || aborted) {
- if (atomic_dec_and_test(&bip->bli_refcount)) {
- ASSERT(!aborted || XFS_FORCED_SHUTDOWN(lip->li_mountp));
+
+ /*
+ * Clean buffers, by definition, cannot be in the AIL. However, aborted
+ * buffers may be dirty and hence in the AIL. Therefore if we are
+ * aborting a buffer and we've just taken the last refernce away, we
+ * have to check if it is in the AIL before freeing it. We need to free
+ * it in this case, because an aborted transaction has already shut the
+ * filesystem down and this is the last chance we will have to do so.
+ */
+ if (atomic_dec_and_test(&bip->bli_refcount)) {
+ if (clean)
+ xfs_buf_item_relse(bp);
+ else if (aborted) {
+ ASSERT(XFS_FORCED_SHUTDOWN(lip->li_mountp));
+ if (lip->li_flags & XFS_LI_IN_AIL) {
+ xfs_trans_ail_delete(lip->li_ailp, lip,
+ SHUTDOWN_LOG_IO_ERROR);
+ }
xfs_buf_item_relse(bp);
}
- } else
- atomic_dec(&bip->bli_refcount);
+ }
if (!(flags & XFS_BLI_HOLD))
xfs_buf_relse(bp);
diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c
index d4e59a4..069537c 100644
--- a/fs/xfs/xfs_da_btree.c
+++ b/fs/xfs/xfs_da_btree.c
@@ -635,6 +635,7 @@
xfs_trans_log_buf(tp, bp, 0, size - 1);
bp->b_ops = blk1->bp->b_ops;
+ xfs_trans_buf_copy_type(bp, blk1->bp);
blk1->bp = bp;
blk1->blkno = blkno;
diff --git a/fs/xfs/xfs_dir2_leaf.c b/fs/xfs/xfs_dir2_leaf.c
index 08984ee..1021c83 100644
--- a/fs/xfs/xfs_dir2_leaf.c
+++ b/fs/xfs/xfs_dir2_leaf.c
@@ -180,6 +180,11 @@
return true;
}
+/*
+ * We verify the magic numbers before decoding the leaf header so that on debug
+ * kernels we don't get assertion failures in xfs_dir3_leaf_hdr_from_disk() due
+ * to incorrect magic numbers.
+ */
static bool
xfs_dir3_leaf_verify(
struct xfs_buf *bp,
@@ -191,24 +196,25 @@
ASSERT(magic == XFS_DIR2_LEAF1_MAGIC || magic == XFS_DIR2_LEAFN_MAGIC);
- xfs_dir3_leaf_hdr_from_disk(&leafhdr, leaf);
if (xfs_sb_version_hascrc(&mp->m_sb)) {
struct xfs_dir3_leaf_hdr *leaf3 = bp->b_addr;
+ __uint16_t magic3;
- if ((magic == XFS_DIR2_LEAF1_MAGIC &&
- leafhdr.magic != XFS_DIR3_LEAF1_MAGIC) ||
- (magic == XFS_DIR2_LEAFN_MAGIC &&
- leafhdr.magic != XFS_DIR3_LEAFN_MAGIC))
+ magic3 = (magic == XFS_DIR2_LEAF1_MAGIC) ? XFS_DIR3_LEAF1_MAGIC
+ : XFS_DIR3_LEAFN_MAGIC;
+
+ if (leaf3->info.hdr.magic != cpu_to_be16(magic3))
return false;
-
if (!uuid_equal(&leaf3->info.uuid, &mp->m_sb.sb_uuid))
return false;
if (be64_to_cpu(leaf3->info.blkno) != bp->b_bn)
return false;
} else {
- if (leafhdr.magic != magic)
+ if (leaf->hdr.info.magic != cpu_to_be16(magic))
return false;
}
+
+ xfs_dir3_leaf_hdr_from_disk(&leafhdr, leaf);
return xfs_dir3_leaf_check_int(mp, &leafhdr, leaf);
}
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 251c666..71520e6 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -940,13 +940,8 @@
trace_xfs_dqput_free(dqp);
- mutex_lock(&qi->qi_lru_lock);
- if (list_empty(&dqp->q_lru)) {
- list_add_tail(&dqp->q_lru, &qi->qi_lru_list);
- qi->qi_lru_count++;
+ if (list_lru_add(&qi->qi_lru, &dqp->q_lru))
XFS_STATS_INC(xs_qm_dquot_unused);
- }
- mutex_unlock(&qi->qi_lru_lock);
/*
* If we just added a udquot to the freelist, then we want to release
diff --git a/fs/xfs/xfs_dquot_item.c b/fs/xfs/xfs_dquot_item.c
index 60c6e1f..e838d84 100644
--- a/fs/xfs/xfs_dquot_item.c
+++ b/fs/xfs/xfs_dquot_item.c
@@ -142,7 +142,8 @@
STATIC uint
xfs_qm_dquot_logitem_push(
struct xfs_log_item *lip,
- struct list_head *buffer_list)
+ struct list_head *buffer_list) __releases(&lip->li_ailp->xa_lock)
+ __acquires(&lip->li_ailp->xa_lock)
{
struct xfs_dquot *dqp = DQUOT_ITEM(lip)->qli_dquot;
struct xfs_buf *bp = NULL;
diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c
index 86f559f..e43708e 100644
--- a/fs/xfs/xfs_extent_busy.c
+++ b/fs/xfs/xfs_extent_busy.c
@@ -160,7 +160,8 @@
struct xfs_extent_busy *busyp,
xfs_agblock_t fbno,
xfs_extlen_t flen,
- bool userdata)
+ bool userdata) __releases(&pag->pagb_lock)
+ __acquires(&pag->pagb_lock)
{
xfs_agblock_t fend = fbno + flen;
xfs_agblock_t bbno = busyp->bno;
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 16219b9..193206b 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -48,7 +48,7 @@
/*
* Allocate and initialise an xfs_inode.
*/
-STATIC struct xfs_inode *
+struct xfs_inode *
xfs_inode_alloc(
struct xfs_mount *mp,
xfs_ino_t ino)
@@ -98,7 +98,7 @@
kmem_zone_free(xfs_inode_zone, ip);
}
-STATIC void
+void
xfs_inode_free(
struct xfs_inode *ip)
{
@@ -1167,7 +1167,7 @@
* them to be cleaned, which we hope will not be very long due to the
* background walker having already kicked the IO off on those dirty inodes.
*/
-void
+long
xfs_reclaim_inodes_nr(
struct xfs_mount *mp,
int nr_to_scan)
@@ -1176,7 +1176,7 @@
xfs_reclaim_work_queue(mp);
xfs_ail_push_all(mp->m_ail);
- xfs_reclaim_inodes_ag(mp, SYNC_TRYLOCK | SYNC_WAIT, &nr_to_scan);
+ return xfs_reclaim_inodes_ag(mp, SYNC_TRYLOCK | SYNC_WAIT, &nr_to_scan);
}
/*
diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h
index 8a89f7d..9ed68bb 100644
--- a/fs/xfs/xfs_icache.h
+++ b/fs/xfs/xfs_icache.h
@@ -42,11 +42,15 @@
int xfs_iget(struct xfs_mount *mp, struct xfs_trans *tp, xfs_ino_t ino,
uint flags, uint lock_flags, xfs_inode_t **ipp);
+/* recovery needs direct inode allocation capability */
+struct xfs_inode * xfs_inode_alloc(struct xfs_mount *mp, xfs_ino_t ino);
+void xfs_inode_free(struct xfs_inode *ip);
+
void xfs_reclaim_worker(struct work_struct *work);
int xfs_reclaim_inodes(struct xfs_mount *mp, int mode);
int xfs_reclaim_inodes_count(struct xfs_mount *mp);
-void xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan);
+long xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan);
void xfs_inode_set_reclaim_tag(struct xfs_inode *ip);
diff --git a/fs/xfs/xfs_inode_buf.c b/fs/xfs/xfs_inode_buf.c
index e011d59..63382d3 100644
--- a/fs/xfs/xfs_inode_buf.c
+++ b/fs/xfs/xfs_inode_buf.c
@@ -53,9 +53,8 @@
i * mp->m_sb.sb_inodesize);
if (!dip->di_next_unlinked) {
xfs_alert(mp,
- "Detected bogus zero next_unlinked field in incore inode buffer 0x%p.",
- bp);
- ASSERT(dip->di_next_unlinked);
+ "Detected bogus zero next_unlinked field in inode %d buffer 0x%llx.",
+ i, (long long)bp->b_bn);
}
}
}
@@ -106,11 +105,10 @@
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_HIGH,
mp, dip);
#ifdef DEBUG
- xfs_emerg(mp,
+ xfs_alert(mp,
"bad inode magic/vsn daddr %lld #%d (magic=%x)",
(unsigned long long)bp->b_bn, i,
be16_to_cpu(dip->di_magic));
- ASSERT(0);
#endif
}
}
@@ -196,7 +194,7 @@
return 0;
}
-STATIC void
+void
xfs_dinode_from_disk(
xfs_icdinode_t *to,
xfs_dinode_t *from)
diff --git a/fs/xfs/xfs_inode_buf.h b/fs/xfs/xfs_inode_buf.h
index 599e6c0..abba0ae 100644
--- a/fs/xfs/xfs_inode_buf.h
+++ b/fs/xfs/xfs_inode_buf.h
@@ -32,17 +32,17 @@
ushort im_boffset; /* inode offset in block in bytes */
};
-int xfs_imap_to_bp(struct xfs_mount *, struct xfs_trans *,
- struct xfs_imap *, struct xfs_dinode **,
- struct xfs_buf **, uint, uint);
-int xfs_iread(struct xfs_mount *, struct xfs_trans *,
- struct xfs_inode *, uint);
-void xfs_dinode_calc_crc(struct xfs_mount *, struct xfs_dinode *);
-void xfs_dinode_to_disk(struct xfs_dinode *,
- struct xfs_icdinode *);
+int xfs_imap_to_bp(struct xfs_mount *, struct xfs_trans *,
+ struct xfs_imap *, struct xfs_dinode **,
+ struct xfs_buf **, uint, uint);
+int xfs_iread(struct xfs_mount *, struct xfs_trans *,
+ struct xfs_inode *, uint);
+void xfs_dinode_calc_crc(struct xfs_mount *, struct xfs_dinode *);
+void xfs_dinode_to_disk(struct xfs_dinode *to, struct xfs_icdinode *from);
+void xfs_dinode_from_disk(struct xfs_icdinode *to, struct xfs_dinode *from);
#if defined(DEBUG)
-void xfs_inobp_check(struct xfs_mount *, struct xfs_buf *);
+void xfs_inobp_check(struct xfs_mount *, struct xfs_buf *);
#else
#define xfs_inobp_check(mp, bp)
#endif /* DEBUG */
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index bdebc21..668e8f4 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -71,7 +71,7 @@
int hsize;
xfs_handle_t handle;
struct inode *inode;
- struct fd f = {0};
+ struct fd f = {NULL};
struct path path;
int error;
struct xfs_inode *ip;
@@ -456,12 +456,9 @@
if (IS_ERR(dentry))
return PTR_ERR(dentry);
- kbuf = kmem_zalloc(al_hreq.buflen, KM_SLEEP | KM_MAYFAIL);
- if (!kbuf) {
- kbuf = kmem_zalloc_large(al_hreq.buflen);
- if (!kbuf)
- goto out_dput;
- }
+ kbuf = kmem_zalloc_large(al_hreq.buflen, KM_SLEEP);
+ if (!kbuf)
+ goto out_dput;
cursor = (attrlist_cursor_kern_t *)&al_hreq.pos;
error = -xfs_attr_list(XFS_I(dentry->d_inode), kbuf, al_hreq.buflen,
@@ -472,12 +469,9 @@
if (copy_to_user(al_hreq.buffer, kbuf, al_hreq.buflen))
error = -EFAULT;
- out_kfree:
- if (is_vmalloc_addr(kbuf))
- kmem_free_large(kbuf);
- else
- kmem_free(kbuf);
- out_dput:
+out_kfree:
+ kmem_free(kbuf);
+out_dput:
dput(dentry);
return error;
}
@@ -495,12 +489,9 @@
if (*len > XATTR_SIZE_MAX)
return EINVAL;
- kbuf = kmem_zalloc(*len, KM_SLEEP | KM_MAYFAIL);
- if (!kbuf) {
- kbuf = kmem_zalloc_large(*len);
- if (!kbuf)
- return ENOMEM;
- }
+ kbuf = kmem_zalloc_large(*len, KM_SLEEP);
+ if (!kbuf)
+ return ENOMEM;
error = xfs_attr_get(XFS_I(inode), name, kbuf, (int *)len, flags);
if (error)
@@ -509,11 +500,8 @@
if (copy_to_user(ubuf, kbuf, *len))
error = EFAULT;
- out_kfree:
- if (is_vmalloc_addr(kbuf))
- kmem_free_large(kbuf);
- else
- kmem_free(kbuf);
+out_kfree:
+ kmem_free(kbuf);
return error;
}
diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c
index d3ab953..f671f7e 100644
--- a/fs/xfs/xfs_ioctl32.c
+++ b/fs/xfs/xfs_ioctl32.c
@@ -371,12 +371,9 @@
return PTR_ERR(dentry);
error = -ENOMEM;
- kbuf = kmem_zalloc(al_hreq.buflen, KM_SLEEP | KM_MAYFAIL);
- if (!kbuf) {
- kbuf = kmem_zalloc_large(al_hreq.buflen);
- if (!kbuf)
- goto out_dput;
- }
+ kbuf = kmem_zalloc_large(al_hreq.buflen, KM_SLEEP);
+ if (!kbuf)
+ goto out_dput;
cursor = (attrlist_cursor_kern_t *)&al_hreq.pos;
error = -xfs_attr_list(XFS_I(dentry->d_inode), kbuf, al_hreq.buflen,
@@ -387,12 +384,9 @@
if (copy_to_user(compat_ptr(al_hreq.buffer), kbuf, al_hreq.buflen))
error = -EFAULT;
- out_kfree:
- if (is_vmalloc_addr(kbuf))
- kmem_free_large(kbuf);
- else
- kmem_free(kbuf);
- out_dput:
+out_kfree:
+ kmem_free(kbuf);
+out_dput:
dput(dentry);
return error;
}
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index b93e14b..084b3e1 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -495,7 +495,7 @@
/*
* Done, we're either out of filesystem or space to put the data.
*/
- kmem_free_large(irbuf);
+ kmem_free(irbuf);
*ubcountp = ubelem;
/*
* Found some inodes, return them now and return the error next time.
@@ -541,8 +541,9 @@
* at the expense of the error case.
*/
- ino = (xfs_ino_t)*lastinop;
- error = xfs_bulkstat_one(mp, ino, buffer, sizeof(xfs_bstat_t), 0, &res);
+ ino = *lastinop;
+ error = xfs_bulkstat_one(mp, ino, buffer, sizeof(xfs_bstat_t),
+ NULL, &res);
if (error) {
/*
* Special case way failed, do it the "long" way
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 5372d58..a2dea108 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -257,7 +257,8 @@
struct xlog *log,
struct xlog_grant_head *head,
struct xlog_ticket *tic,
- int need_bytes)
+ int need_bytes) __releases(&head->lock)
+ __acquires(&head->lock)
{
list_add_tail(&tic->t_queue, &head->waiters);
diff --git a/fs/xfs/xfs_log_format.h b/fs/xfs/xfs_log_format.h
index 31e3a06..ca7e28a8 100644
--- a/fs/xfs/xfs_log_format.h
+++ b/fs/xfs/xfs_log_format.h
@@ -474,6 +474,8 @@
#define XFS_ILOG_ADATA 0x040 /* log i_af.if_data */
#define XFS_ILOG_AEXT 0x080 /* log i_af.if_extents */
#define XFS_ILOG_ABROOT 0x100 /* log i_af.i_broot */
+#define XFS_ILOG_DOWNER 0x200 /* change the data fork owner on replay */
+#define XFS_ILOG_AOWNER 0x400 /* change the attr fork owner on replay */
/*
@@ -487,7 +489,8 @@
#define XFS_ILOG_NONCORE (XFS_ILOG_DDATA | XFS_ILOG_DEXT | \
XFS_ILOG_DBROOT | XFS_ILOG_DEV | \
XFS_ILOG_UUID | XFS_ILOG_ADATA | \
- XFS_ILOG_AEXT | XFS_ILOG_ABROOT)
+ XFS_ILOG_AEXT | XFS_ILOG_ABROOT | \
+ XFS_ILOG_DOWNER | XFS_ILOG_AOWNER)
#define XFS_ILOG_DFORK (XFS_ILOG_DDATA | XFS_ILOG_DEXT | \
XFS_ILOG_DBROOT)
@@ -499,7 +502,8 @@
XFS_ILOG_DEXT | XFS_ILOG_DBROOT | \
XFS_ILOG_DEV | XFS_ILOG_UUID | \
XFS_ILOG_ADATA | XFS_ILOG_AEXT | \
- XFS_ILOG_ABROOT | XFS_ILOG_TIMESTAMP)
+ XFS_ILOG_ABROOT | XFS_ILOG_TIMESTAMP | \
+ XFS_ILOG_DOWNER | XFS_ILOG_AOWNER)
static inline int xfs_ilog_fbroot(int w)
{
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 7c0c1fd..dabda95 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -2014,7 +2014,7 @@
case XFS_ATTR3_RMT_MAGIC:
return be64_to_cpu(((struct xfs_attr3_rmt_hdr *)blk)->rm_lsn);
case XFS_SB_MAGIC:
- return be64_to_cpu(((struct xfs_sb *)blk)->sb_lsn);
+ return be64_to_cpu(((struct xfs_dsb *)blk)->sb_lsn);
default:
break;
}
@@ -2629,6 +2629,82 @@
return error;
}
+/*
+ * Inode fork owner changes
+ *
+ * If we have been told that we have to reparent the inode fork, it's because an
+ * extent swap operation on a CRC enabled filesystem has been done and we are
+ * replaying it. We need to walk the BMBT of the appropriate fork and change the
+ * owners of it.
+ *
+ * The complexity here is that we don't have an inode context to work with, so
+ * after we've replayed the inode we need to instantiate one. This is where the
+ * fun begins.
+ *
+ * We are in the middle of log recovery, so we can't run transactions. That
+ * means we cannot use cache coherent inode instantiation via xfs_iget(), as
+ * that will result in the corresponding iput() running the inode through
+ * xfs_inactive(). If we've just replayed an inode core that changes the link
+ * count to zero (i.e. it's been unlinked), then xfs_inactive() will run
+ * transactions (bad!).
+ *
+ * So, to avoid this, we instantiate an inode directly from the inode core we've
+ * just recovered. We have the buffer still locked, and all we really need to
+ * instantiate is the inode core and the forks being modified. We can do this
+ * manually, then run the inode btree owner change, and then tear down the
+ * xfs_inode without having to run any transactions at all.
+ *
+ * Also, because we don't have a transaction context available here but need to
+ * gather all the buffers we modify for writeback so we pass the buffer_list
+ * instead for the operation to use.
+ */
+
+STATIC int
+xfs_recover_inode_owner_change(
+ struct xfs_mount *mp,
+ struct xfs_dinode *dip,
+ struct xfs_inode_log_format *in_f,
+ struct list_head *buffer_list)
+{
+ struct xfs_inode *ip;
+ int error;
+
+ ASSERT(in_f->ilf_fields & (XFS_ILOG_DOWNER|XFS_ILOG_AOWNER));
+
+ ip = xfs_inode_alloc(mp, in_f->ilf_ino);
+ if (!ip)
+ return ENOMEM;
+
+ /* instantiate the inode */
+ xfs_dinode_from_disk(&ip->i_d, dip);
+ ASSERT(ip->i_d.di_version >= 3);
+
+ error = xfs_iformat_fork(ip, dip);
+ if (error)
+ goto out_free_ip;
+
+
+ if (in_f->ilf_fields & XFS_ILOG_DOWNER) {
+ ASSERT(in_f->ilf_fields & XFS_ILOG_DBROOT);
+ error = xfs_bmbt_change_owner(NULL, ip, XFS_DATA_FORK,
+ ip->i_ino, buffer_list);
+ if (error)
+ goto out_free_ip;
+ }
+
+ if (in_f->ilf_fields & XFS_ILOG_AOWNER) {
+ ASSERT(in_f->ilf_fields & XFS_ILOG_ABROOT);
+ error = xfs_bmbt_change_owner(NULL, ip, XFS_ATTR_FORK,
+ ip->i_ino, buffer_list);
+ if (error)
+ goto out_free_ip;
+ }
+
+out_free_ip:
+ xfs_inode_free(ip);
+ return error;
+}
+
STATIC int
xlog_recover_inode_pass2(
struct xlog *log,
@@ -2681,8 +2757,7 @@
error = bp->b_error;
if (error) {
xfs_buf_ioerror_alert(bp, "xlog_recover_do..(read#2)");
- xfs_buf_relse(bp);
- goto error;
+ goto out_release;
}
ASSERT(in_f->ilf_fields & XFS_ILOG_CORE);
dip = (xfs_dinode_t *)xfs_buf_offset(bp, in_f->ilf_boffset);
@@ -2692,30 +2767,31 @@
* like an inode!
*/
if (unlikely(dip->di_magic != cpu_to_be16(XFS_DINODE_MAGIC))) {
- xfs_buf_relse(bp);
xfs_alert(mp,
"%s: Bad inode magic number, dip = 0x%p, dino bp = 0x%p, ino = %Ld",
__func__, dip, bp, in_f->ilf_ino);
XFS_ERROR_REPORT("xlog_recover_inode_pass2(1)",
XFS_ERRLEVEL_LOW, mp);
error = EFSCORRUPTED;
- goto error;
+ goto out_release;
}
dicp = item->ri_buf[1].i_addr;
if (unlikely(dicp->di_magic != XFS_DINODE_MAGIC)) {
- xfs_buf_relse(bp);
xfs_alert(mp,
"%s: Bad inode log record, rec ptr 0x%p, ino %Ld",
__func__, item, in_f->ilf_ino);
XFS_ERROR_REPORT("xlog_recover_inode_pass2(2)",
XFS_ERRLEVEL_LOW, mp);
error = EFSCORRUPTED;
- goto error;
+ goto out_release;
}
/*
* If the inode has an LSN in it, recover the inode only if it's less
- * than the lsn of the transaction we are replaying.
+ * than the lsn of the transaction we are replaying. Note: we still
+ * need to replay an owner change even though the inode is more recent
+ * than the transaction as there is no guarantee that all the btree
+ * blocks are more recent than this transaction, too.
*/
if (dip->di_version >= 3) {
xfs_lsn_t lsn = be64_to_cpu(dip->di_lsn);
@@ -2723,7 +2799,7 @@
if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) >= 0) {
trace_xfs_log_recover_inode_skip(log, in_f);
error = 0;
- goto out_release;
+ goto out_owner_change;
}
}
@@ -2745,10 +2821,9 @@
dicp->di_flushiter < (DI_MAX_FLUSH >> 1)) {
/* do nothing */
} else {
- xfs_buf_relse(bp);
trace_xfs_log_recover_inode_skip(log, in_f);
error = 0;
- goto error;
+ goto out_release;
}
}
@@ -2760,13 +2835,12 @@
(dicp->di_format != XFS_DINODE_FMT_BTREE)) {
XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(3)",
XFS_ERRLEVEL_LOW, mp, dicp);
- xfs_buf_relse(bp);
xfs_alert(mp,
"%s: Bad regular inode log record, rec ptr 0x%p, "
"ino ptr = 0x%p, ino bp = 0x%p, ino %Ld",
__func__, item, dip, bp, in_f->ilf_ino);
error = EFSCORRUPTED;
- goto error;
+ goto out_release;
}
} else if (unlikely(S_ISDIR(dicp->di_mode))) {
if ((dicp->di_format != XFS_DINODE_FMT_EXTENTS) &&
@@ -2774,19 +2848,17 @@
(dicp->di_format != XFS_DINODE_FMT_LOCAL)) {
XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(4)",
XFS_ERRLEVEL_LOW, mp, dicp);
- xfs_buf_relse(bp);
xfs_alert(mp,
"%s: Bad dir inode log record, rec ptr 0x%p, "
"ino ptr = 0x%p, ino bp = 0x%p, ino %Ld",
__func__, item, dip, bp, in_f->ilf_ino);
error = EFSCORRUPTED;
- goto error;
+ goto out_release;
}
}
if (unlikely(dicp->di_nextents + dicp->di_anextents > dicp->di_nblocks)){
XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(5)",
XFS_ERRLEVEL_LOW, mp, dicp);
- xfs_buf_relse(bp);
xfs_alert(mp,
"%s: Bad inode log record, rec ptr 0x%p, dino ptr 0x%p, "
"dino bp 0x%p, ino %Ld, total extents = %d, nblocks = %Ld",
@@ -2794,29 +2866,27 @@
dicp->di_nextents + dicp->di_anextents,
dicp->di_nblocks);
error = EFSCORRUPTED;
- goto error;
+ goto out_release;
}
if (unlikely(dicp->di_forkoff > mp->m_sb.sb_inodesize)) {
XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(6)",
XFS_ERRLEVEL_LOW, mp, dicp);
- xfs_buf_relse(bp);
xfs_alert(mp,
"%s: Bad inode log record, rec ptr 0x%p, dino ptr 0x%p, "
"dino bp 0x%p, ino %Ld, forkoff 0x%x", __func__,
item, dip, bp, in_f->ilf_ino, dicp->di_forkoff);
error = EFSCORRUPTED;
- goto error;
+ goto out_release;
}
isize = xfs_icdinode_size(dicp->di_version);
if (unlikely(item->ri_buf[1].i_len > isize)) {
XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(7)",
XFS_ERRLEVEL_LOW, mp, dicp);
- xfs_buf_relse(bp);
xfs_alert(mp,
"%s: Bad inode log record length %d, rec ptr 0x%p",
__func__, item->ri_buf[1].i_len, item);
error = EFSCORRUPTED;
- goto error;
+ goto out_release;
}
/* The core is in in-core format */
@@ -2842,7 +2912,7 @@
}
if (in_f->ilf_size == 2)
- goto write_inode_buffer;
+ goto out_owner_change;
len = item->ri_buf[2].i_len;
src = item->ri_buf[2].i_addr;
ASSERT(in_f->ilf_size <= 4);
@@ -2903,13 +2973,15 @@
default:
xfs_warn(log->l_mp, "%s: Invalid flag", __func__);
ASSERT(0);
- xfs_buf_relse(bp);
error = EIO;
- goto error;
+ goto out_release;
}
}
-write_inode_buffer:
+out_owner_change:
+ if (in_f->ilf_fields & (XFS_ILOG_DOWNER|XFS_ILOG_AOWNER))
+ error = xfs_recover_inode_owner_change(mp, dip, in_f,
+ buffer_list);
/* re-generate the checksum. */
xfs_dinode_calc_crc(log->l_mp, dip);
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 6218a0a..3e6c2e6 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -51,8 +51,9 @@
*/
STATIC int xfs_qm_init_quotainos(xfs_mount_t *);
STATIC int xfs_qm_init_quotainfo(xfs_mount_t *);
-STATIC int xfs_qm_shake(struct shrinker *, struct shrink_control *);
+
+STATIC void xfs_qm_dqfree_one(struct xfs_dquot *dqp);
/*
* We use the batch lookup interface to iterate over the dquots as it
* currently is the only interface into the radix tree code that allows
@@ -203,12 +204,9 @@
* We move dquots to the freelist as soon as their reference count
* hits zero, so it really should be on the freelist here.
*/
- mutex_lock(&qi->qi_lru_lock);
ASSERT(!list_empty(&dqp->q_lru));
- list_del_init(&dqp->q_lru);
- qi->qi_lru_count--;
+ list_lru_del(&qi->qi_lru, &dqp->q_lru);
XFS_STATS_DEC(xs_qm_dquot_unused);
- mutex_unlock(&qi->qi_lru_lock);
xfs_qm_dqdestroy(dqp);
@@ -680,6 +678,143 @@
return ndquots;
}
+struct xfs_qm_isolate {
+ struct list_head buffers;
+ struct list_head dispose;
+};
+
+static enum lru_status
+xfs_qm_dquot_isolate(
+ struct list_head *item,
+ spinlock_t *lru_lock,
+ void *arg)
+{
+ struct xfs_dquot *dqp = container_of(item,
+ struct xfs_dquot, q_lru);
+ struct xfs_qm_isolate *isol = arg;
+
+ if (!xfs_dqlock_nowait(dqp))
+ goto out_miss_busy;
+
+ /*
+ * This dquot has acquired a reference in the meantime remove it from
+ * the freelist and try again.
+ */
+ if (dqp->q_nrefs) {
+ xfs_dqunlock(dqp);
+ XFS_STATS_INC(xs_qm_dqwants);
+
+ trace_xfs_dqreclaim_want(dqp);
+ list_del_init(&dqp->q_lru);
+ XFS_STATS_DEC(xs_qm_dquot_unused);
+ return LRU_REMOVED;
+ }
+
+ /*
+ * If the dquot is dirty, flush it. If it's already being flushed, just
+ * skip it so there is time for the IO to complete before we try to
+ * reclaim it again on the next LRU pass.
+ */
+ if (!xfs_dqflock_nowait(dqp)) {
+ xfs_dqunlock(dqp);
+ goto out_miss_busy;
+ }
+
+ if (XFS_DQ_IS_DIRTY(dqp)) {
+ struct xfs_buf *bp = NULL;
+ int error;
+
+ trace_xfs_dqreclaim_dirty(dqp);
+
+ /* we have to drop the LRU lock to flush the dquot */
+ spin_unlock(lru_lock);
+
+ error = xfs_qm_dqflush(dqp, &bp);
+ if (error) {
+ xfs_warn(dqp->q_mount, "%s: dquot %p flush failed",
+ __func__, dqp);
+ goto out_unlock_dirty;
+ }
+
+ xfs_buf_delwri_queue(bp, &isol->buffers);
+ xfs_buf_relse(bp);
+ goto out_unlock_dirty;
+ }
+ xfs_dqfunlock(dqp);
+
+ /*
+ * Prevent lookups now that we are past the point of no return.
+ */
+ dqp->dq_flags |= XFS_DQ_FREEING;
+ xfs_dqunlock(dqp);
+
+ ASSERT(dqp->q_nrefs == 0);
+ list_move_tail(&dqp->q_lru, &isol->dispose);
+ XFS_STATS_DEC(xs_qm_dquot_unused);
+ trace_xfs_dqreclaim_done(dqp);
+ XFS_STATS_INC(xs_qm_dqreclaims);
+ return LRU_REMOVED;
+
+out_miss_busy:
+ trace_xfs_dqreclaim_busy(dqp);
+ XFS_STATS_INC(xs_qm_dqreclaim_misses);
+ return LRU_SKIP;
+
+out_unlock_dirty:
+ trace_xfs_dqreclaim_busy(dqp);
+ XFS_STATS_INC(xs_qm_dqreclaim_misses);
+ xfs_dqunlock(dqp);
+ spin_lock(lru_lock);
+ return LRU_RETRY;
+}
+
+static unsigned long
+xfs_qm_shrink_scan(
+ struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ struct xfs_quotainfo *qi = container_of(shrink,
+ struct xfs_quotainfo, qi_shrinker);
+ struct xfs_qm_isolate isol;
+ unsigned long freed;
+ int error;
+ unsigned long nr_to_scan = sc->nr_to_scan;
+
+ if ((sc->gfp_mask & (__GFP_FS|__GFP_WAIT)) != (__GFP_FS|__GFP_WAIT))
+ return 0;
+
+ INIT_LIST_HEAD(&isol.buffers);
+ INIT_LIST_HEAD(&isol.dispose);
+
+ freed = list_lru_walk_node(&qi->qi_lru, sc->nid, xfs_qm_dquot_isolate, &isol,
+ &nr_to_scan);
+
+ error = xfs_buf_delwri_submit(&isol.buffers);
+ if (error)
+ xfs_warn(NULL, "%s: dquot reclaim failed", __func__);
+
+ while (!list_empty(&isol.dispose)) {
+ struct xfs_dquot *dqp;
+
+ dqp = list_first_entry(&isol.dispose, struct xfs_dquot, q_lru);
+ list_del_init(&dqp->q_lru);
+ xfs_qm_dqfree_one(dqp);
+ }
+
+ return freed;
+}
+
+static unsigned long
+xfs_qm_shrink_count(
+ struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ struct xfs_quotainfo *qi = container_of(shrink,
+ struct xfs_quotainfo, qi_shrinker);
+
+ return list_lru_count_node(&qi->qi_lru, sc->nid);
+}
+
/*
* This initializes all the quota information that's kept in the
* mount structure
@@ -696,11 +831,18 @@
qinf = mp->m_quotainfo = kmem_zalloc(sizeof(xfs_quotainfo_t), KM_SLEEP);
+ if ((error = list_lru_init(&qinf->qi_lru))) {
+ kmem_free(qinf);
+ mp->m_quotainfo = NULL;
+ return error;
+ }
+
/*
* See if quotainodes are setup, and if not, allocate them,
* and change the superblock accordingly.
*/
if ((error = xfs_qm_init_quotainos(mp))) {
+ list_lru_destroy(&qinf->qi_lru);
kmem_free(qinf);
mp->m_quotainfo = NULL;
return error;
@@ -711,10 +853,6 @@
INIT_RADIX_TREE(&qinf->qi_pquota_tree, GFP_NOFS);
mutex_init(&qinf->qi_tree_lock);
- INIT_LIST_HEAD(&qinf->qi_lru_list);
- qinf->qi_lru_count = 0;
- mutex_init(&qinf->qi_lru_lock);
-
/* mutex used to serialize quotaoffs */
mutex_init(&qinf->qi_quotaofflock);
@@ -779,8 +917,10 @@
qinf->qi_rtbwarnlimit = XFS_QM_RTBWARNLIMIT;
}
- qinf->qi_shrinker.shrink = xfs_qm_shake;
+ qinf->qi_shrinker.count_objects = xfs_qm_shrink_count;
+ qinf->qi_shrinker.scan_objects = xfs_qm_shrink_scan;
qinf->qi_shrinker.seeks = DEFAULT_SEEKS;
+ qinf->qi_shrinker.flags = SHRINKER_NUMA_AWARE;
register_shrinker(&qinf->qi_shrinker);
return 0;
}
@@ -801,6 +941,7 @@
ASSERT(qi != NULL);
unregister_shrinker(&qi->qi_shrinker);
+ list_lru_destroy(&qi->qi_lru);
if (qi->qi_uquotaip) {
IRELE(qi->qi_uquotaip);
@@ -1599,132 +1740,6 @@
xfs_qm_dqdestroy(dqp);
}
-STATIC void
-xfs_qm_dqreclaim_one(
- struct xfs_dquot *dqp,
- struct list_head *buffer_list,
- struct list_head *dispose_list)
-{
- struct xfs_mount *mp = dqp->q_mount;
- struct xfs_quotainfo *qi = mp->m_quotainfo;
- int error;
-
- if (!xfs_dqlock_nowait(dqp))
- goto out_move_tail;
-
- /*
- * This dquot has acquired a reference in the meantime remove it from
- * the freelist and try again.
- */
- if (dqp->q_nrefs) {
- xfs_dqunlock(dqp);
-
- trace_xfs_dqreclaim_want(dqp);
- XFS_STATS_INC(xs_qm_dqwants);
-
- list_del_init(&dqp->q_lru);
- qi->qi_lru_count--;
- XFS_STATS_DEC(xs_qm_dquot_unused);
- return;
- }
-
- /*
- * Try to grab the flush lock. If this dquot is in the process of
- * getting flushed to disk, we don't want to reclaim it.
- */
- if (!xfs_dqflock_nowait(dqp))
- goto out_unlock_move_tail;
-
- if (XFS_DQ_IS_DIRTY(dqp)) {
- struct xfs_buf *bp = NULL;
-
- trace_xfs_dqreclaim_dirty(dqp);
-
- error = xfs_qm_dqflush(dqp, &bp);
- if (error) {
- xfs_warn(mp, "%s: dquot %p flush failed",
- __func__, dqp);
- goto out_unlock_move_tail;
- }
-
- xfs_buf_delwri_queue(bp, buffer_list);
- xfs_buf_relse(bp);
- /*
- * Give the dquot another try on the freelist, as the
- * flushing will take some time.
- */
- goto out_unlock_move_tail;
- }
- xfs_dqfunlock(dqp);
-
- /*
- * Prevent lookups now that we are past the point of no return.
- */
- dqp->dq_flags |= XFS_DQ_FREEING;
- xfs_dqunlock(dqp);
-
- ASSERT(dqp->q_nrefs == 0);
- list_move_tail(&dqp->q_lru, dispose_list);
- qi->qi_lru_count--;
- XFS_STATS_DEC(xs_qm_dquot_unused);
-
- trace_xfs_dqreclaim_done(dqp);
- XFS_STATS_INC(xs_qm_dqreclaims);
- return;
-
- /*
- * Move the dquot to the tail of the list so that we don't spin on it.
- */
-out_unlock_move_tail:
- xfs_dqunlock(dqp);
-out_move_tail:
- list_move_tail(&dqp->q_lru, &qi->qi_lru_list);
- trace_xfs_dqreclaim_busy(dqp);
- XFS_STATS_INC(xs_qm_dqreclaim_misses);
-}
-
-STATIC int
-xfs_qm_shake(
- struct shrinker *shrink,
- struct shrink_control *sc)
-{
- struct xfs_quotainfo *qi =
- container_of(shrink, struct xfs_quotainfo, qi_shrinker);
- int nr_to_scan = sc->nr_to_scan;
- LIST_HEAD (buffer_list);
- LIST_HEAD (dispose_list);
- struct xfs_dquot *dqp;
- int error;
-
- if ((sc->gfp_mask & (__GFP_FS|__GFP_WAIT)) != (__GFP_FS|__GFP_WAIT))
- return 0;
- if (!nr_to_scan)
- goto out;
-
- mutex_lock(&qi->qi_lru_lock);
- while (!list_empty(&qi->qi_lru_list)) {
- if (nr_to_scan-- <= 0)
- break;
- dqp = list_first_entry(&qi->qi_lru_list, struct xfs_dquot,
- q_lru);
- xfs_qm_dqreclaim_one(dqp, &buffer_list, &dispose_list);
- }
- mutex_unlock(&qi->qi_lru_lock);
-
- error = xfs_buf_delwri_submit(&buffer_list);
- if (error)
- xfs_warn(NULL, "%s: dquot reclaim failed", __func__);
-
- while (!list_empty(&dispose_list)) {
- dqp = list_first_entry(&dispose_list, struct xfs_dquot, q_lru);
- list_del_init(&dqp->q_lru);
- xfs_qm_dqfree_one(dqp);
- }
-
-out:
- return (qi->qi_lru_count / 100) * sysctl_vfs_cache_pressure;
-}
-
/*
* Start a transaction and write the incore superblock changes to
* disk. flags parameter indicates which fields have changed.
diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h
index 670cd44..2b602df 100644
--- a/fs/xfs/xfs_qm.h
+++ b/fs/xfs/xfs_qm.h
@@ -49,9 +49,7 @@
struct xfs_inode *qi_uquotaip; /* user quota inode */
struct xfs_inode *qi_gquotaip; /* group quota inode */
struct xfs_inode *qi_pquotaip; /* project quota inode */
- struct list_head qi_lru_list;
- struct mutex qi_lru_lock;
- int qi_lru_count;
+ struct list_lru qi_lru;
int qi_dquots;
time_t qi_btimelimit; /* limit for blks timer */
time_t qi_itimelimit; /* limit for inodes timer */
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 979a77d..15188cc 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1535,19 +1535,21 @@
return mount_bdev(fs_type, flags, dev_name, data, xfs_fs_fill_super);
}
-static int
+static long
xfs_fs_nr_cached_objects(
- struct super_block *sb)
+ struct super_block *sb,
+ int nid)
{
return xfs_reclaim_inodes_count(XFS_M(sb));
}
-static void
+static long
xfs_fs_free_cached_objects(
struct super_block *sb,
- int nr_to_scan)
+ long nr_to_scan,
+ int nid)
{
- xfs_reclaim_inodes_nr(XFS_M(sb), nr_to_scan);
+ return xfs_reclaim_inodes_nr(XFS_M(sb), nr_to_scan);
}
static const struct super_operations xfs_super_operations = {
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 2f2a7c0..f622a97 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -41,6 +41,7 @@
#include "xfs_trans_space.h"
#include "xfs_trace.h"
#include "xfs_symlink.h"
+#include "xfs_buf_item.h"
/* ----- Kernel only functions below ----- */
STATIC int
@@ -363,6 +364,7 @@
pathlen -= byte_cnt;
offset += byte_cnt;
+ xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SYMLINK_BUF);
xfs_trans_log_buf(tp, bp, 0, (buf + byte_cnt - 1) -
(char *)bp->b_addr);
}
diff --git a/include/linux/aio.h b/include/linux/aio.h
index 1bdf965..d9c92da 100644
--- a/include/linux/aio.h
+++ b/include/linux/aio.h
@@ -27,15 +27,13 @@
*/
#define KIOCB_CANCELLED ((void *) (~0ULL))
-typedef int (kiocb_cancel_fn)(struct kiocb *, struct io_event *);
+typedef int (kiocb_cancel_fn)(struct kiocb *);
struct kiocb {
- atomic_t ki_users;
-
struct file *ki_filp;
struct kioctx *ki_ctx; /* NULL for sync ops */
kiocb_cancel_fn *ki_cancel;
- void (*ki_dtor)(struct kiocb *);
+ void *private;
union {
void __user *user;
@@ -44,17 +42,7 @@
__u64 ki_user_data; /* user's data for completion */
loff_t ki_pos;
-
- void *private;
- /* State that we remember to be able to restart/retry */
- unsigned short ki_opcode;
- size_t ki_nbytes; /* copy of iocb->aio_nbytes */
- char __user *ki_buf; /* remaining iocb->aio_buf */
- size_t ki_left; /* remaining bytes */
- struct iovec ki_inline_vec; /* inline vector */
- struct iovec *ki_iovec;
- unsigned long ki_nr_segs;
- unsigned long ki_cur_seg;
+ size_t ki_nbytes; /* copy of iocb->aio_nbytes */
struct list_head ki_list; /* the aio core uses this
* for cancellation */
@@ -74,7 +62,6 @@
static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
{
*kiocb = (struct kiocb) {
- .ki_users = ATOMIC_INIT(1),
.ki_ctx = NULL,
.ki_filp = filp,
.ki_obj.tsk = current,
@@ -84,7 +71,6 @@
/* prototypes */
#ifdef CONFIG_AIO
extern ssize_t wait_on_sync_kiocb(struct kiocb *iocb);
-extern void aio_put_req(struct kiocb *iocb);
extern void aio_complete(struct kiocb *iocb, long res, long res2);
struct mm_struct;
extern void exit_aio(struct mm_struct *mm);
@@ -93,7 +79,6 @@
void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel);
#else
static inline ssize_t wait_on_sync_kiocb(struct kiocb *iocb) { return 0; }
-static inline void aio_put_req(struct kiocb *iocb) { }
static inline void aio_complete(struct kiocb *iocb, long res, long res2) { }
struct mm_struct;
static inline void exit_aio(struct mm_struct *mm) { }
diff --git a/include/linux/anon_inodes.h b/include/linux/anon_inodes.h
index 8013a45..cf573c2 100644
--- a/include/linux/anon_inodes.h
+++ b/include/linux/anon_inodes.h
@@ -13,6 +13,9 @@
struct file *anon_inode_getfile(const char *name,
const struct file_operations *fops,
void *priv, int flags);
+struct file *anon_inode_getfile_private(const char *name,
+ const struct file_operations *fops,
+ void *priv, int flags);
int anon_inode_getfd(const char *name, const struct file_operations *fops,
void *priv, int flags);
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index c388155..5f66d51 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -243,6 +243,8 @@
* BDI_CAP_EXEC_MAP: Can be mapped for execution
*
* BDI_CAP_SWAP_BACKED: Count shmem/tmpfs objects as swap-backed.
+ *
+ * BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold.
*/
#define BDI_CAP_NO_ACCT_DIRTY 0x00000001
#define BDI_CAP_NO_WRITEBACK 0x00000002
@@ -254,6 +256,7 @@
#define BDI_CAP_NO_ACCT_WB 0x00000080
#define BDI_CAP_SWAP_BACKED 0x00000100
#define BDI_CAP_STABLE_WRITES 0x00000200
+#define BDI_CAP_STRICTLIMIT 0x00000400
#define BDI_CAP_VMFLAGS \
(BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP)
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index 70cf138..e8112ae 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -31,7 +31,7 @@
#ifdef __alpha__
unsigned int taso:1;
#endif
- unsigned int recursion_depth;
+ unsigned int recursion_depth; /* only for search_binary_handler() */
struct file * file;
struct cred *cred; /* new credentials */
int unsafe; /* how unsafe this exec is (mask of LSM_UNSAFE_*) */
diff --git a/include/linux/cmdline-parser.h b/include/linux/cmdline-parser.h
new file mode 100644
index 0000000..98e892e
--- /dev/null
+++ b/include/linux/cmdline-parser.h
@@ -0,0 +1,43 @@
+/*
+ * Parsing command line, get the partitions information.
+ *
+ * Written by Cai Zhiyong <caizhiyong@huawei.com>
+ *
+ */
+#ifndef CMDLINEPARSEH
+#define CMDLINEPARSEH
+
+#include <linux/blkdev.h>
+
+/* partition flags */
+#define PF_RDONLY 0x01 /* Device is read only */
+#define PF_POWERUP_LOCK 0x02 /* Always locked after reset */
+
+struct cmdline_subpart {
+ char name[BDEVNAME_SIZE]; /* partition name, such as 'rootfs' */
+ sector_t from;
+ sector_t size;
+ int flags;
+ struct cmdline_subpart *next_subpart;
+};
+
+struct cmdline_parts {
+ char name[BDEVNAME_SIZE]; /* block device, such as 'mmcblk0' */
+ unsigned int nr_subparts;
+ struct cmdline_subpart *subpart;
+ struct cmdline_parts *next_parts;
+};
+
+void cmdline_parts_free(struct cmdline_parts **parts);
+
+int cmdline_parts_parse(struct cmdline_parts **parts, const char *cmdline);
+
+struct cmdline_parts *cmdline_parts_find(struct cmdline_parts *parts,
+ const char *bdev);
+
+void cmdline_parts_set(struct cmdline_parts *parts, sector_t disk_size,
+ int slot,
+ int (*add_part)(int, struct cmdline_subpart *, void *),
+ void *param);
+
+#endif /* CMDLINEPARSEH */
diff --git a/include/linux/compat.h b/include/linux/compat.h
index ec1aee4..345da00 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -43,6 +43,7 @@
#define COMPAT_SYSCALL_DEFINEx(x, name, ...) \
asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\
static inline long C_SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__));\
+ asmlinkage long compat_SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__));\
asmlinkage long compat_SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__))\
{ \
return C_SYSC##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__)); \
diff --git a/include/linux/cpu_rmap.h b/include/linux/cpu_rmap.h
index 1739510..bdd18ca 100644
--- a/include/linux/cpu_rmap.h
+++ b/include/linux/cpu_rmap.h
@@ -52,8 +52,6 @@
return rmap->obj[rmap->near[cpu].index];
}
-#ifdef CONFIG_GENERIC_HARDIRQS
-
/**
* alloc_irq_cpu_rmap - allocate CPU affinity reverse-map for IRQs
* @size: Number of objects to be mapped
@@ -68,5 +66,4 @@
extern int irq_cpu_rmap_add(struct cpu_rmap *rmap, int irq);
-#endif
#endif /* __LINUX_CPU_RMAP_H */
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index d568f39..fcabc42 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -85,7 +85,6 @@
struct list_head policy_list;
struct kobject kobj;
struct completion kobj_unregister;
- int transition_ongoing; /* Tracks transition status */
};
/* Only for ACPI */
diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h
index 37e4f8d..fe68a5a 100644
--- a/include/linux/crash_dump.h
+++ b/include/linux/crash_dump.h
@@ -12,6 +12,15 @@
extern unsigned long long elfcorehdr_addr;
extern unsigned long long elfcorehdr_size;
+extern int __weak elfcorehdr_alloc(unsigned long long *addr,
+ unsigned long long *size);
+extern void __weak elfcorehdr_free(unsigned long long addr);
+extern ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos);
+extern ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos);
+extern int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma,
+ unsigned long from, unsigned long pfn,
+ unsigned long size, pgprot_t prot);
+
extern ssize_t copy_oldmem_page(unsigned long, char *, size_t,
unsigned long, int);
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index feaa8d8..59066e0 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -55,11 +55,11 @@
#define hashlen_len(hashlen) ((u32)((hashlen) >> 32))
struct dentry_stat_t {
- int nr_dentry;
- int nr_unused;
- int age_limit; /* age in seconds */
- int want_pages; /* pages requested by system */
- int dummy[2];
+ long nr_dentry;
+ long nr_unused;
+ long age_limit; /* age in seconds */
+ long want_pages; /* pages requested by system */
+ long dummy[2];
};
extern struct dentry_stat_t dentry_stat;
@@ -395,4 +395,8 @@
extern int sysctl_vfs_cache_pressure;
+static inline unsigned long vfs_pressure_ratio(unsigned long val)
+{
+ return mult_frac(val, sysctl_vfs_cache_pressure, 100);
+}
#endif /* __LINUX_DCACHE_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 529d871..a4acd3c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -10,6 +10,7 @@
#include <linux/stat.h>
#include <linux/cache.h>
#include <linux/list.h>
+#include <linux/list_lru.h>
#include <linux/llist.h>
#include <linux/radix-tree.h>
#include <linux/rbtree.h>
@@ -1269,15 +1270,6 @@
struct list_head s_files;
#endif
struct list_head s_mounts; /* list of mounts; _not_ for fs use */
- /* s_dentry_lru, s_nr_dentry_unused protected by dcache.c lru locks */
- struct list_head s_dentry_lru; /* unused dentry lru */
- int s_nr_dentry_unused; /* # of dentry on lru */
-
- /* s_inode_lru_lock protects s_inode_lru and s_nr_inodes_unused */
- spinlock_t s_inode_lru_lock ____cacheline_aligned_in_smp;
- struct list_head s_inode_lru; /* unused inode lru */
- int s_nr_inodes_unused; /* # of inodes on lru */
-
struct block_device *s_bdev;
struct backing_dev_info *s_bdi;
struct mtd_info *s_mtd;
@@ -1331,11 +1323,14 @@
/* AIO completions deferred from interrupt context */
struct workqueue_struct *s_dio_done_wq;
-};
-/* superblock cache pruning functions */
-extern void prune_icache_sb(struct super_block *sb, int nr_to_scan);
-extern void prune_dcache_sb(struct super_block *sb, int nr_to_scan);
+ /*
+ * Keep the lru lists last in the structure so they always sit on their
+ * own individual cachelines.
+ */
+ struct list_lru s_dentry_lru ____cacheline_aligned_in_smp;
+ struct list_lru s_inode_lru ____cacheline_aligned_in_smp;
+};
extern struct timespec current_fs_time(struct super_block *sb);
@@ -1629,8 +1624,8 @@
ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
#endif
int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
- int (*nr_cached_objects)(struct super_block *);
- void (*free_cached_objects)(struct super_block *, int);
+ long (*nr_cached_objects)(struct super_block *, int);
+ long (*free_cached_objects)(struct super_block *, long, int);
};
/*
@@ -2494,7 +2489,6 @@
#define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m))
extern int vfs_readlink(struct dentry *, char __user *, int, const char *);
-extern int vfs_follow_link(struct nameidata *, const char *);
extern int page_readlink(struct dentry *, char __user *, int);
extern void *page_follow_link_light(struct dentry *, struct nameidata *);
extern void page_put_link(struct dentry *, struct nameidata *, void *);
diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h
index 2b93a9a..0efc3e6 100644
--- a/include/linux/fs_struct.h
+++ b/include/linux/fs_struct.h
@@ -39,17 +39,6 @@
spin_unlock(&fs->lock);
}
-static inline void get_fs_root_and_pwd(struct fs_struct *fs, struct path *root,
- struct path *pwd)
-{
- spin_lock(&fs->lock);
- *root = fs->root;
- path_get(root);
- *pwd = fs->pwd;
- path_get(pwd);
- spin_unlock(&fs->lock);
-}
-
extern bool current_chrooted(void);
#endif /* _LINUX_FS_STRUCT_H */
diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h
index 661d374..f8d41cb 100644
--- a/include/linux/genalloc.h
+++ b/include/linux/genalloc.h
@@ -66,8 +66,8 @@
struct list_head next_chunk; /* next chunk in pool */
atomic_t avail;
phys_addr_t phys_addr; /* physical starting address of memory chunk */
- unsigned long start_addr; /* starting address of memory chunk */
- unsigned long end_addr; /* ending address of memory chunk */
+ unsigned long start_addr; /* start address of memory chunk */
+ unsigned long end_addr; /* end address of memory chunk (inclusive) */
unsigned long bits[0]; /* bitmap for allocating memory chunk */
};
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index ccfe17c..1e04106 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -7,11 +7,7 @@
#include <linux/vtime.h>
-#if defined(CONFIG_SMP) || defined(CONFIG_GENERIC_HARDIRQS)
extern void synchronize_irq(unsigned int irq);
-#else
-# define synchronize_irq(irq) barrier()
-#endif
#if defined(CONFIG_TINY_RCU)
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index b60de92..3935428 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -96,9 +96,6 @@
pmd_t *dst_pmd, pmd_t *src_pmd,
struct vm_area_struct *vma,
unsigned long addr, unsigned long end);
-extern int handle_pte_fault(struct mm_struct *mm,
- struct vm_area_struct *vma, unsigned long address,
- pte_t *pte, pmd_t *pmd, unsigned int flags);
extern int split_huge_page_to_list(struct page *page, struct list_head *list);
static inline int split_huge_page(struct page *page)
{
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index c2b1801..0393270 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -66,6 +66,9 @@
vm_flags_t vm_flags);
void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed);
int dequeue_hwpoisoned_huge_page(struct page *page);
+bool isolate_huge_page(struct page *page, struct list_head *list);
+void putback_active_hugepage(struct page *page);
+bool is_hugepage_active(struct page *page);
void copy_huge_page(struct page *dst, struct page *src);
#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
@@ -134,6 +137,9 @@
return 0;
}
+#define isolate_huge_page(p, l) false
+#define putback_active_hugepage(p) do {} while (0)
+#define is_hugepage_active(x) false
static inline void copy_huge_page(struct page *dst, struct page *src)
{
}
@@ -261,6 +267,8 @@
};
struct page *alloc_huge_page_node(struct hstate *h, int nid);
+struct page *alloc_huge_page_noerr(struct vm_area_struct *vma,
+ unsigned long addr, int avoid_reserve);
/* arch callback */
int __init alloc_bootmem_huge_page(struct hstate *h);
@@ -371,9 +379,23 @@
return __basepage_index(page);
}
+extern void dissolve_free_huge_pages(unsigned long start_pfn,
+ unsigned long end_pfn);
+int pmd_huge_support(void);
+/*
+ * Currently hugepage migration is enabled only for pmd-based hugepage.
+ * This function will be updated when hugepage migration is more widely
+ * supported.
+ */
+static inline int hugepage_migration_support(struct hstate *h)
+{
+ return pmd_huge_support() && (huge_page_shift(h) == PMD_SHIFT);
+}
+
#else /* CONFIG_HUGETLB_PAGE */
struct hstate {};
#define alloc_huge_page_node(h, nid) NULL
+#define alloc_huge_page_noerr(v, a, r) NULL
#define alloc_bootmem_huge_page(h) NULL
#define hstate_file(f) NULL
#define hstate_sizelog(s) NULL
@@ -396,6 +418,9 @@
{
return page->index;
}
+#define dissolve_free_huge_pages(s, e) do {} while (0)
+#define pmd_huge_support() 0
+#define hugepage_migration_support(h) 0
#endif /* CONFIG_HUGETLB_PAGE */
#endif /* _LINUX_HUGETLB_H */
diff --git a/include/linux/init.h b/include/linux/init.h
index e73f2b7..f1c27a7 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -153,6 +153,7 @@
void setup_arch(char **);
void prepare_namespace(void);
void __init load_default_modules(void);
+int __init init_rootfs(void);
extern void (*late_time_init)(void);
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 5fa5afe..5e865b5 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -120,7 +120,6 @@
extern irqreturn_t no_action(int cpl, void *dev_id);
-#ifdef CONFIG_GENERIC_HARDIRQS
extern int __must_check
request_threaded_irq(unsigned int irq, irq_handler_t handler,
irq_handler_t thread_fn,
@@ -140,40 +139,6 @@
extern int __must_check
request_percpu_irq(unsigned int irq, irq_handler_t handler,
const char *devname, void __percpu *percpu_dev_id);
-#else
-
-extern int __must_check
-request_irq(unsigned int irq, irq_handler_t handler, unsigned long flags,
- const char *name, void *dev);
-
-/*
- * Special function to avoid ifdeffery in kernel/irq/devres.c which
- * gets magically built by GENERIC_HARDIRQS=n architectures (sparc,
- * m68k). I really love these $@%#!* obvious Makefile references:
- * ../../../kernel/irq/devres.o
- */
-static inline int __must_check
-request_threaded_irq(unsigned int irq, irq_handler_t handler,
- irq_handler_t thread_fn,
- unsigned long flags, const char *name, void *dev)
-{
- return request_irq(irq, handler, flags, name, dev);
-}
-
-static inline int __must_check
-request_any_context_irq(unsigned int irq, irq_handler_t handler,
- unsigned long flags, const char *name, void *dev_id)
-{
- return request_irq(irq, handler, flags, name, dev_id);
-}
-
-static inline int __must_check
-request_percpu_irq(unsigned int irq, irq_handler_t handler,
- const char *devname, void __percpu *percpu_dev_id)
-{
- return request_irq(irq, handler, 0, devname, percpu_dev_id);
-}
-#endif
extern void free_irq(unsigned int, void *);
extern void free_percpu_irq(unsigned int, void __percpu *);
@@ -221,7 +186,6 @@
extern void enable_percpu_irq(unsigned int irq, unsigned int type);
/* The following three functions are for the core kernel use only. */
-#ifdef CONFIG_GENERIC_HARDIRQS
extern void suspend_device_irqs(void);
extern void resume_device_irqs(void);
#ifdef CONFIG_PM_SLEEP
@@ -229,13 +193,8 @@
#else
static inline int check_wakeup_irqs(void) { return 0; }
#endif
-#else
-static inline void suspend_device_irqs(void) { };
-static inline void resume_device_irqs(void) { };
-static inline int check_wakeup_irqs(void) { return 0; }
-#endif
-#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS)
+#if defined(CONFIG_SMP)
extern cpumask_var_t irq_default_affinity;
@@ -287,9 +246,8 @@
{
return -EINVAL;
}
-#endif /* CONFIG_SMP && CONFIG_GENERIC_HARDIRQS */
+#endif /* CONFIG_SMP */
-#ifdef CONFIG_GENERIC_HARDIRQS
/*
* Special lockdep variants of irq disabling/enabling.
* These should be used for locking constructs that
@@ -354,33 +312,6 @@
return irq_set_irq_wake(irq, 0);
}
-#else /* !CONFIG_GENERIC_HARDIRQS */
-/*
- * NOTE: non-genirq architectures, if they want to support the lock
- * validator need to define the methods below in their asm/irq.h
- * files, under an #ifdef CONFIG_LOCKDEP section.
- */
-#ifndef CONFIG_LOCKDEP
-# define disable_irq_nosync_lockdep(irq) disable_irq_nosync(irq)
-# define disable_irq_nosync_lockdep_irqsave(irq, flags) \
- disable_irq_nosync(irq)
-# define disable_irq_lockdep(irq) disable_irq(irq)
-# define enable_irq_lockdep(irq) enable_irq(irq)
-# define enable_irq_lockdep_irqrestore(irq, flags) \
- enable_irq(irq)
-# endif
-
-static inline int enable_irq_wake(unsigned int irq)
-{
- return 0;
-}
-
-static inline int disable_irq_wake(unsigned int irq)
-{
- return 0;
-}
-#endif /* CONFIG_GENERIC_HARDIRQS */
-
#ifdef CONFIG_IRQ_FORCED_THREADING
extern bool force_irqthreads;
@@ -655,7 +586,7 @@
* if more than one irq occurred.
*/
-#if defined(CONFIG_GENERIC_HARDIRQS) && !defined(CONFIG_GENERIC_IRQ_PROBE)
+#if !defined(CONFIG_GENERIC_IRQ_PROBE)
static inline unsigned long probe_irq_on(void)
{
return 0;
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 3aeb730..7ea319e 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -58,10 +58,26 @@
#define IOMMU_CAP_CACHE_COHERENCY 0x1
#define IOMMU_CAP_INTR_REMAP 0x2 /* isolates device intrs */
+/*
+ * Following constraints are specifc to FSL_PAMUV1:
+ * -aperture must be power of 2, and naturally aligned
+ * -number of windows must be power of 2, and address space size
+ * of each window is determined by aperture size / # of windows
+ * -the actual size of the mapped region of a window must be power
+ * of 2 starting with 4KB and physical address must be naturally
+ * aligned.
+ * DOMAIN_ATTR_FSL_PAMUV1 corresponds to the above mentioned contraints.
+ * The caller can invoke iommu_domain_get_attr to check if the underlying
+ * iommu implementation supports these constraints.
+ */
+
enum iommu_attr {
DOMAIN_ATTR_GEOMETRY,
DOMAIN_ATTR_PAGING,
DOMAIN_ATTR_WINDOWS,
+ DOMAIN_ATTR_FSL_PAMU_STASH,
+ DOMAIN_ATTR_FSL_PAMU_ENABLE,
+ DOMAIN_ATTR_FSL_PAMUV1,
DOMAIN_ATTR_MAX,
};
diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index c4d870b..19c19a5 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -22,7 +22,7 @@
int in_use;
unsigned short seq;
unsigned short seq_max;
- struct rw_semaphore rw_mutex;
+ struct rw_semaphore rwsem;
struct idr ipcs_idr;
int next_id;
};
diff --git a/include/linux/irq.h b/include/linux/irq.h
index f04d3ba..56bb0dc 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -382,8 +382,6 @@
extern void irq_cpu_offline(void);
extern int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *cpumask);
-#ifdef CONFIG_GENERIC_HARDIRQS
-
#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_PENDING_IRQ)
void irq_move_irq(struct irq_data *data);
void irq_move_masked_irq(struct irq_data *data);
@@ -802,11 +800,4 @@
static inline void irq_gc_unlock(struct irq_chip_generic *gc) { }
#endif
-#else /* !CONFIG_GENERIC_HARDIRQS */
-
-extern struct msi_desc *irq_get_msi_desc(unsigned int irq);
-extern int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry);
-
-#endif /* CONFIG_GENERIC_HARDIRQS */
-
#endif /* _LINUX_IRQ_H */
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 623325e..56fb646 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -76,8 +76,6 @@
extern struct irq_desc irq_desc[NR_IRQS];
#endif
-#ifdef CONFIG_GENERIC_HARDIRQS
-
static inline struct irq_data *irq_desc_get_irq_data(struct irq_desc *desc)
{
return &desc->irq_data;
@@ -173,6 +171,5 @@
desc->preflow_handler = handler;
}
#endif
-#endif
#endif
diff --git a/include/linux/irqnr.h b/include/linux/irqnr.h
index 0a2dc46..fdd5cc1 100644
--- a/include/linux/irqnr.h
+++ b/include/linux/irqnr.h
@@ -4,23 +4,6 @@
#include <uapi/linux/irqnr.h>
-#ifndef CONFIG_GENERIC_HARDIRQS
-#include <asm/irq.h>
-
-/*
- * Wrappers for non-genirq architectures:
- */
-#define nr_irqs NR_IRQS
-#define irq_to_desc(irq) (&irq_desc[irq])
-
-# define for_each_irq_desc(irq, desc) \
- for (irq = 0; irq < nr_irqs; irq++)
-
-# define for_each_irq_desc_reverse(irq, desc) \
- for (irq = nr_irqs - 1; irq >= 0; irq--)
-
-#else /* CONFIG_GENERIC_HARDIRQS */
-
extern int nr_irqs;
extern struct irq_desc *irq_to_desc(unsigned int irq);
unsigned int irq_get_next_irq(unsigned int offset);
@@ -50,8 +33,6 @@
for (irq = irq_get_next_irq(0); irq < nr_irqs; \
irq = irq_get_next_irq(irq + 1))
-#endif /* CONFIG_GENERIC_HARDIRQS */
-
#define for_each_irq_nr(irq) \
for (irq = 0; irq < nr_irqs; irq++)
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index ed5f6ed..51c72be 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -36,9 +36,6 @@
};
struct kernel_stat {
-#ifndef CONFIG_GENERIC_HARDIRQS
- unsigned int irqs[NR_IRQS];
-#endif
unsigned long irqs_sum;
unsigned int softirqs[NR_SOFTIRQS];
};
@@ -54,22 +51,6 @@
extern unsigned long long nr_context_switches(void);
-#ifndef CONFIG_GENERIC_HARDIRQS
-
-struct irq_desc;
-
-static inline void kstat_incr_irqs_this_cpu(unsigned int irq,
- struct irq_desc *desc)
-{
- __this_cpu_inc(kstat.irqs[irq]);
- __this_cpu_inc(kstat.irqs_sum);
-}
-
-static inline unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
-{
- return kstat_cpu(cpu).irqs[irq];
-}
-#else
#include <linux/irq.h>
extern unsigned int kstat_irqs_cpu(unsigned int irq, int cpu);
@@ -79,8 +60,6 @@
__this_cpu_inc(kstat.irqs_sum); \
} while (0)
-#endif
-
static inline void kstat_incr_softirqs_this_cpu(unsigned int irq)
{
__this_cpu_inc(kstat.softirqs[irq]);
@@ -94,20 +73,7 @@
/*
* Number of interrupts per specific IRQ source, since bootup
*/
-#ifndef CONFIG_GENERIC_HARDIRQS
-static inline unsigned int kstat_irqs(unsigned int irq)
-{
- unsigned int sum = 0;
- int cpu;
-
- for_each_possible_cpu(cpu)
- sum += kstat_irqs_cpu(irq, cpu);
-
- return sum;
-}
-#else
extern unsigned int kstat_irqs(unsigned int irq);
-#endif
/*
* Number of interrupts per cpu, since bootup
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index ca1d27a..925eaf2 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -264,10 +264,36 @@
extern void arch_disarm_kprobe(struct kprobe *p);
extern int arch_init_kprobes(void);
extern void show_registers(struct pt_regs *regs);
-extern kprobe_opcode_t *get_insn_slot(void);
-extern void free_insn_slot(kprobe_opcode_t *slot, int dirty);
extern void kprobes_inc_nmissed_count(struct kprobe *p);
+struct kprobe_insn_cache {
+ struct mutex mutex;
+ void *(*alloc)(void); /* allocate insn page */
+ void (*free)(void *); /* free insn page */
+ struct list_head pages; /* list of kprobe_insn_page */
+ size_t insn_size; /* size of instruction slot */
+ int nr_garbage;
+};
+
+extern kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c);
+extern void __free_insn_slot(struct kprobe_insn_cache *c,
+ kprobe_opcode_t *slot, int dirty);
+
+#define DEFINE_INSN_CACHE_OPS(__name) \
+extern struct kprobe_insn_cache kprobe_##__name##_slots; \
+ \
+static inline kprobe_opcode_t *get_##__name##_slot(void) \
+{ \
+ return __get_insn_slot(&kprobe_##__name##_slots); \
+} \
+ \
+static inline void free_##__name##_slot(kprobe_opcode_t *slot, int dirty)\
+{ \
+ __free_insn_slot(&kprobe_##__name##_slots, slot, dirty); \
+} \
+
+DEFINE_INSN_CACHE_OPS(insn);
+
#ifdef CONFIG_OPTPROBES
/*
* Internal structure for direct jump optimized probe
@@ -287,13 +313,13 @@
extern void arch_unoptimize_kprobes(struct list_head *oplist,
struct list_head *done_list);
extern void arch_unoptimize_kprobe(struct optimized_kprobe *op);
-extern kprobe_opcode_t *get_optinsn_slot(void);
-extern void free_optinsn_slot(kprobe_opcode_t *slot, int dirty);
extern int arch_within_optimized_kprobe(struct optimized_kprobe *op,
unsigned long addr);
extern void opt_pre_handler(struct kprobe *p, struct pt_regs *regs);
+DEFINE_INSN_CACHE_OPS(optinsn);
+
#ifdef CONFIG_SYSCTL
extern int sysctl_kprobes_optimization;
extern int proc_kprobes_optimization_handler(struct ctl_table *table,
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
new file mode 100644
index 0000000..3ce5417
--- /dev/null
+++ b/include/linux/list_lru.h
@@ -0,0 +1,131 @@
+/*
+ * Copyright (c) 2013 Red Hat, Inc. and Parallels Inc. All rights reserved.
+ * Authors: David Chinner and Glauber Costa
+ *
+ * Generic LRU infrastructure
+ */
+#ifndef _LRU_LIST_H
+#define _LRU_LIST_H
+
+#include <linux/list.h>
+#include <linux/nodemask.h>
+
+/* list_lru_walk_cb has to always return one of those */
+enum lru_status {
+ LRU_REMOVED, /* item removed from list */
+ LRU_ROTATE, /* item referenced, give another pass */
+ LRU_SKIP, /* item cannot be locked, skip */
+ LRU_RETRY, /* item not freeable. May drop the lock
+ internally, but has to return locked. */
+};
+
+struct list_lru_node {
+ spinlock_t lock;
+ struct list_head list;
+ /* kept as signed so we can catch imbalance bugs */
+ long nr_items;
+} ____cacheline_aligned_in_smp;
+
+struct list_lru {
+ struct list_lru_node *node;
+ nodemask_t active_nodes;
+};
+
+void list_lru_destroy(struct list_lru *lru);
+int list_lru_init(struct list_lru *lru);
+
+/**
+ * list_lru_add: add an element to the lru list's tail
+ * @list_lru: the lru pointer
+ * @item: the item to be added.
+ *
+ * If the element is already part of a list, this function returns doing
+ * nothing. Therefore the caller does not need to keep state about whether or
+ * not the element already belongs in the list and is allowed to lazy update
+ * it. Note however that this is valid for *a* list, not *this* list. If
+ * the caller organize itself in a way that elements can be in more than
+ * one type of list, it is up to the caller to fully remove the item from
+ * the previous list (with list_lru_del() for instance) before moving it
+ * to @list_lru
+ *
+ * Return value: true if the list was updated, false otherwise
+ */
+bool list_lru_add(struct list_lru *lru, struct list_head *item);
+
+/**
+ * list_lru_del: delete an element to the lru list
+ * @list_lru: the lru pointer
+ * @item: the item to be deleted.
+ *
+ * This function works analogously as list_lru_add in terms of list
+ * manipulation. The comments about an element already pertaining to
+ * a list are also valid for list_lru_del.
+ *
+ * Return value: true if the list was updated, false otherwise
+ */
+bool list_lru_del(struct list_lru *lru, struct list_head *item);
+
+/**
+ * list_lru_count_node: return the number of objects currently held by @lru
+ * @lru: the lru pointer.
+ * @nid: the node id to count from.
+ *
+ * Always return a non-negative number, 0 for empty lists. There is no
+ * guarantee that the list is not updated while the count is being computed.
+ * Callers that want such a guarantee need to provide an outer lock.
+ */
+unsigned long list_lru_count_node(struct list_lru *lru, int nid);
+static inline unsigned long list_lru_count(struct list_lru *lru)
+{
+ long count = 0;
+ int nid;
+
+ for_each_node_mask(nid, lru->active_nodes)
+ count += list_lru_count_node(lru, nid);
+
+ return count;
+}
+
+typedef enum lru_status
+(*list_lru_walk_cb)(struct list_head *item, spinlock_t *lock, void *cb_arg);
+/**
+ * list_lru_walk_node: walk a list_lru, isolating and disposing freeable items.
+ * @lru: the lru pointer.
+ * @nid: the node id to scan from.
+ * @isolate: callback function that is resposible for deciding what to do with
+ * the item currently being scanned
+ * @cb_arg: opaque type that will be passed to @isolate
+ * @nr_to_walk: how many items to scan.
+ *
+ * This function will scan all elements in a particular list_lru, calling the
+ * @isolate callback for each of those items, along with the current list
+ * spinlock and a caller-provided opaque. The @isolate callback can choose to
+ * drop the lock internally, but *must* return with the lock held. The callback
+ * will return an enum lru_status telling the list_lru infrastructure what to
+ * do with the object being scanned.
+ *
+ * Please note that nr_to_walk does not mean how many objects will be freed,
+ * just how many objects will be scanned.
+ *
+ * Return value: the number of objects effectively removed from the LRU.
+ */
+unsigned long list_lru_walk_node(struct list_lru *lru, int nid,
+ list_lru_walk_cb isolate, void *cb_arg,
+ unsigned long *nr_to_walk);
+
+static inline unsigned long
+list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate,
+ void *cb_arg, unsigned long nr_to_walk)
+{
+ long isolated = 0;
+ int nid;
+
+ for_each_node_mask(nid, lru->active_nodes) {
+ isolated += list_lru_walk_node(lru, nid, isolate,
+ cb_arg, &nr_to_walk);
+ if (nr_to_walk <= 0)
+ break;
+ }
+ return isolated;
+}
+#endif /* _LRU_LIST_H */
diff --git a/include/linux/lz4.h b/include/linux/lz4.h
index d21c13f..4356686 100644
--- a/include/linux/lz4.h
+++ b/include/linux/lz4.h
@@ -67,8 +67,8 @@
* note : Destination buffer must be already allocated.
* slightly faster than lz4_decompress_unknownoutputsize()
*/
-int lz4_decompress(const char *src, size_t *src_len, char *dest,
- size_t actual_dest_len);
+int lz4_decompress(const unsigned char *src, size_t *src_len,
+ unsigned char *dest, size_t actual_dest_len);
/*
* lz4_decompress_unknownoutputsize()
@@ -82,6 +82,6 @@
* Error if return (< 0)
* note : Destination buffer must be already allocated.
*/
-int lz4_decompress_unknownoutputsize(const char *src, size_t src_len,
- char *dest, size_t *dest_len);
+int lz4_decompress_unknownoutputsize(const unsigned char *src, size_t src_len,
+ unsigned char *dest, size_t *dest_len);
#endif
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index f388203..31e95ac 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -60,6 +60,8 @@
void memblock_trim_memory(phys_addr_t align);
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn,
+ unsigned long *end_pfn);
void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn,
unsigned long *out_end_pfn, int *out_nid);
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 6c41609..60e9587 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -30,9 +30,21 @@
struct mm_struct;
struct kmem_cache;
-/* Stats that can be updated by kernel. */
-enum mem_cgroup_page_stat_item {
- MEMCG_NR_FILE_MAPPED, /* # of pages charged as file rss */
+/*
+ * The corresponding mem_cgroup_stat_names is defined in mm/memcontrol.c,
+ * These two lists should keep in accord with each other.
+ */
+enum mem_cgroup_stat_index {
+ /*
+ * For MEM_CONTAINER_TYPE_ALL, usage = pagecache + rss.
+ */
+ MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */
+ MEM_CGROUP_STAT_RSS, /* # of pages charged as anon rss */
+ MEM_CGROUP_STAT_RSS_HUGE, /* # of pages charged as anon huge */
+ MEM_CGROUP_STAT_FILE_MAPPED, /* # of pages charged as file rss */
+ MEM_CGROUP_STAT_WRITEBACK, /* # of pages under writeback */
+ MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */
+ MEM_CGROUP_STAT_NSTATS,
};
struct mem_cgroup_reclaim_cookie {
@@ -41,6 +53,23 @@
unsigned int generation;
};
+enum mem_cgroup_filter_t {
+ VISIT, /* visit current node */
+ SKIP, /* skip the current node and continue traversal */
+ SKIP_TREE, /* skip the whole subtree and continue traversal */
+};
+
+/*
+ * mem_cgroup_filter_t predicate might instruct mem_cgroup_iter_cond how to
+ * iterate through the hierarchy tree. Each tree element is checked by the
+ * predicate before it is returned by the iterator. If a filter returns
+ * SKIP or SKIP_TREE then the iterator code continues traversal (with the
+ * next node down the hierarchy or the next node that doesn't belong under the
+ * memcg's subtree).
+ */
+typedef enum mem_cgroup_filter_t
+(*mem_cgroup_iter_filter)(struct mem_cgroup *memcg, struct mem_cgroup *root);
+
#ifdef CONFIG_MEMCG
/*
* All "charge" functions with gfp_mask should use GFP_KERNEL or
@@ -108,9 +137,18 @@
extern void mem_cgroup_end_migration(struct mem_cgroup *memcg,
struct page *oldpage, struct page *newpage, bool migration_ok);
-struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *,
- struct mem_cgroup *,
- struct mem_cgroup_reclaim_cookie *);
+struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root,
+ struct mem_cgroup *prev,
+ struct mem_cgroup_reclaim_cookie *reclaim,
+ mem_cgroup_iter_filter cond);
+
+static inline struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
+ struct mem_cgroup *prev,
+ struct mem_cgroup_reclaim_cookie *reclaim)
+{
+ return mem_cgroup_iter_cond(root, prev, reclaim, NULL);
+}
+
void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *);
/*
@@ -125,6 +163,48 @@
extern void mem_cgroup_replace_page_cache(struct page *oldpage,
struct page *newpage);
+/**
+ * mem_cgroup_toggle_oom - toggle the memcg OOM killer for the current task
+ * @new: true to enable, false to disable
+ *
+ * Toggle whether a failed memcg charge should invoke the OOM killer
+ * or just return -ENOMEM. Returns the previous toggle state.
+ *
+ * NOTE: Any path that enables the OOM killer before charging must
+ * call mem_cgroup_oom_synchronize() afterward to finalize the
+ * OOM handling and clean up.
+ */
+static inline bool mem_cgroup_toggle_oom(bool new)
+{
+ bool old;
+
+ old = current->memcg_oom.may_oom;
+ current->memcg_oom.may_oom = new;
+
+ return old;
+}
+
+static inline void mem_cgroup_enable_oom(void)
+{
+ bool old = mem_cgroup_toggle_oom(true);
+
+ WARN_ON(old == true);
+}
+
+static inline void mem_cgroup_disable_oom(void)
+{
+ bool old = mem_cgroup_toggle_oom(false);
+
+ WARN_ON(old == false);
+}
+
+static inline bool task_in_memcg_oom(struct task_struct *p)
+{
+ return p->memcg_oom.in_memcg_oom;
+}
+
+bool mem_cgroup_oom_synchronize(void);
+
#ifdef CONFIG_MEMCG_SWAP
extern int do_swap_account;
#endif
@@ -165,24 +245,24 @@
}
void mem_cgroup_update_page_stat(struct page *page,
- enum mem_cgroup_page_stat_item idx,
+ enum mem_cgroup_stat_index idx,
int val);
static inline void mem_cgroup_inc_page_stat(struct page *page,
- enum mem_cgroup_page_stat_item idx)
+ enum mem_cgroup_stat_index idx)
{
mem_cgroup_update_page_stat(page, idx, 1);
}
static inline void mem_cgroup_dec_page_stat(struct page *page,
- enum mem_cgroup_page_stat_item idx)
+ enum mem_cgroup_stat_index idx)
{
mem_cgroup_update_page_stat(page, idx, -1);
}
-unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
- gfp_t gfp_mask,
- unsigned long *total_scanned);
+enum mem_cgroup_filter_t
+mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg,
+ struct mem_cgroup *root);
void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx);
static inline void mem_cgroup_count_vm_event(struct mm_struct *mm,
@@ -296,6 +376,15 @@
struct page *oldpage, struct page *newpage, bool migration_ok)
{
}
+static inline struct mem_cgroup *
+mem_cgroup_iter_cond(struct mem_cgroup *root,
+ struct mem_cgroup *prev,
+ struct mem_cgroup_reclaim_cookie *reclaim,
+ mem_cgroup_iter_filter cond)
+{
+ /* first call must return non-NULL, second return NULL */
+ return (struct mem_cgroup *)(unsigned long)!prev;
+}
static inline struct mem_cgroup *
mem_cgroup_iter(struct mem_cgroup *root,
@@ -348,22 +437,45 @@
{
}
+static inline bool mem_cgroup_toggle_oom(bool new)
+{
+ return false;
+}
+
+static inline void mem_cgroup_enable_oom(void)
+{
+}
+
+static inline void mem_cgroup_disable_oom(void)
+{
+}
+
+static inline bool task_in_memcg_oom(struct task_struct *p)
+{
+ return false;
+}
+
+static inline bool mem_cgroup_oom_synchronize(void)
+{
+ return false;
+}
+
static inline void mem_cgroup_inc_page_stat(struct page *page,
- enum mem_cgroup_page_stat_item idx)
+ enum mem_cgroup_stat_index idx)
{
}
static inline void mem_cgroup_dec_page_stat(struct page *page,
- enum mem_cgroup_page_stat_item idx)
+ enum mem_cgroup_stat_index idx)
{
}
static inline
-unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
- gfp_t gfp_mask,
- unsigned long *total_scanned)
+enum mem_cgroup_filter_t
+mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg,
+ struct mem_cgroup *root)
{
- return 0;
+ return VISIT;
}
static inline void mem_cgroup_split_huge_fixup(struct page *head)
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 0d7df39..da6716b 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -91,7 +91,6 @@
}
#define vma_policy(vma) ((vma)->vm_policy)
-#define vma_set_policy(vma, pol) ((vma)->vm_policy = (pol))
static inline void mpol_get(struct mempolicy *pol)
{
@@ -126,6 +125,7 @@
spinlock_t lock;
};
+int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst);
void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol);
int mpol_set_shared_policy(struct shared_policy *info,
struct vm_area_struct *vma,
@@ -173,7 +173,7 @@
/* Check if a vma is migratable */
static inline int vma_migratable(struct vm_area_struct *vma)
{
- if (vma->vm_flags & (VM_IO | VM_HUGETLB | VM_PFNMAP))
+ if (vma->vm_flags & (VM_IO | VM_PFNMAP))
return 0;
/*
* Migration allocates pages in the highest zone. If we cannot
@@ -240,7 +240,12 @@
}
#define vma_policy(vma) NULL
-#define vma_set_policy(vma, pol) do {} while(0)
+
+static inline int
+vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst)
+{
+ return 0;
+}
static inline void numa_policy_init(void)
{
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index a405d3dc..8d3c57f 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -41,8 +41,6 @@
struct page *, struct page *, enum migrate_mode);
extern int migrate_pages(struct list_head *l, new_page_t x,
unsigned long private, enum migrate_mode mode, int reason);
-extern int migrate_huge_page(struct page *, new_page_t x,
- unsigned long private, enum migrate_mode mode);
extern int fail_migrate_page(struct address_space *,
struct page *, struct page *);
@@ -55,6 +53,9 @@
extern void migrate_page_copy(struct page *newpage, struct page *page);
extern int migrate_huge_page_move_mapping(struct address_space *mapping,
struct page *newpage, struct page *page);
+extern int migrate_page_move_mapping(struct address_space *mapping,
+ struct page *newpage, struct page *page,
+ struct buffer_head *head, enum migrate_mode mode);
#else
static inline void putback_lru_pages(struct list_head *l) {}
@@ -62,9 +63,6 @@
static inline int migrate_pages(struct list_head *l, new_page_t x,
unsigned long private, enum migrate_mode mode, int reason)
{ return -ENOSYS; }
-static inline int migrate_huge_page(struct page *page, new_page_t x,
- unsigned long private, enum migrate_mode mode)
- { return -ENOSYS; }
static inline int migrate_prep(void) { return -ENOSYS; }
static inline int migrate_prep_local(void) { return -ENOSYS; }
diff --git a/include/linux/mm.h b/include/linux/mm.h
index d2d59b4..8b6e55e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -115,6 +115,12 @@
#define VM_ARCH_1 0x01000000 /* Architecture-specific flag */
#define VM_DONTDUMP 0x04000000 /* Do not include in the core dump */
+#ifdef CONFIG_MEM_SOFT_DIRTY
+# define VM_SOFTDIRTY 0x08000000 /* Not soft dirty clean area */
+#else
+# define VM_SOFTDIRTY 0
+#endif
+
#define VM_MIXEDMAP 0x10000000 /* Can contain "struct page" and pure PFN pages */
#define VM_HUGEPAGE 0x20000000 /* MADV_HUGEPAGE marked this vma */
#define VM_NOHUGEPAGE 0x40000000 /* MADV_NOHUGEPAGE marked this vma */
@@ -170,6 +176,7 @@
#define FAULT_FLAG_RETRY_NOWAIT 0x10 /* Don't drop mmap_sem and wait when retrying */
#define FAULT_FLAG_KILLABLE 0x20 /* The fault task is in SIGKILL killable region */
#define FAULT_FLAG_TRIED 0x40 /* second try */
+#define FAULT_FLAG_USER 0x80 /* The fault originated in userspace */
/*
* vm_fault is filled by the the pagefault handler and passed to the vma's
@@ -489,20 +496,6 @@
return (unsigned long)page[1].lru.prev;
}
-static inline int compound_trans_order(struct page *page)
-{
- int order;
- unsigned long flags;
-
- if (!PageHead(page))
- return 0;
-
- flags = compound_lock_irqsave(page);
- order = compound_order(page);
- compound_unlock_irqrestore(page, flags);
- return order;
-}
-
static inline void set_compound_order(struct page *page, unsigned long order)
{
page[1].lru.prev = (void *)order;
@@ -637,12 +630,12 @@
#endif
/*
- * The identification function is only used by the buddy allocator for
- * determining if two pages could be buddies. We are not really
- * identifying a zone since we could be using a the section number
- * id if we have not node id available in page flags.
- * We guarantee only that it will return the same value for two
- * combinable pages in a zone.
+ * The identification function is mainly used by the buddy allocator for
+ * determining if two pages could be buddies. We are not really identifying
+ * the zone since we could be using the section number id if we do not have
+ * node id available in page flags.
+ * We only guarantee that it will return the same value for two combinable
+ * pages in a zone.
*/
static inline int page_zone_id(struct page *page)
{
@@ -884,11 +877,12 @@
#define VM_FAULT_NOPAGE 0x0100 /* ->fault installed the pte, not return page */
#define VM_FAULT_LOCKED 0x0200 /* ->fault locked the returned page */
#define VM_FAULT_RETRY 0x0400 /* ->fault blocked, must retry */
+#define VM_FAULT_FALLBACK 0x0800 /* huge page fault failed, fall back to small */
#define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */
#define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | \
- VM_FAULT_HWPOISON_LARGE)
+ VM_FAULT_FALLBACK | VM_FAULT_HWPOISON_LARGE)
/* Encode hstate index for a hwpoisoned large page */
#define VM_FAULT_SET_HINDEX(x) ((x) << 12)
@@ -992,7 +986,7 @@
unmap_mapping_range(mapping, holebegin, holelen, 0);
}
-extern void truncate_pagecache(struct inode *inode, loff_t old, loff_t new);
+extern void truncate_pagecache(struct inode *inode, loff_t new);
extern void truncate_setsize(struct inode *inode, loff_t newsize);
void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end);
int truncate_inode_page(struct address_space *mapping, struct page *page);
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 1397ccf..cf55945 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -2,6 +2,7 @@
#define LINUX_MM_INLINE_H
#include <linux/huge_mm.h>
+#include <linux/swap.h>
/**
* page_is_file_cache - should the page be on a file LRU or anon LRU?
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index faf4b7c..d9851ee 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -322,6 +322,7 @@
atomic_long_t count[NR_MM_COUNTERS];
};
+struct kioctx_table;
struct mm_struct {
struct vm_area_struct * mmap; /* list of VMAs */
struct rb_root mm_rb;
@@ -383,8 +384,8 @@
struct core_state *core_state; /* coredumping support */
#ifdef CONFIG_AIO
- spinlock_t ioctx_lock;
- struct hlist_head ioctx_list;
+ spinlock_t ioctx_lock;
+ struct kioctx_table __rcu *ioctx_table;
#endif
#ifdef CONFIG_MM_OWNER
/*
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index af4a3b7..bd791e4 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -105,6 +105,7 @@
enum zone_stat_item {
/* First 128 byte cacheline (assuming 64 bit words) */
NR_FREE_PAGES,
+ NR_ALLOC_BATCH,
NR_LRU_BASE,
NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */
NR_ACTIVE_ANON, /* " " " " " */
@@ -352,7 +353,6 @@
* free areas of different sizes
*/
spinlock_t lock;
- int all_unreclaimable; /* All pages pinned */
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
/* Set to true when the PG_migrate_skip bits should be cleared */
bool compact_blockskip_flush;
diff --git a/include/linux/percpu_ida.h b/include/linux/percpu_ida.h
new file mode 100644
index 0000000..0b23edb
--- /dev/null
+++ b/include/linux/percpu_ida.h
@@ -0,0 +1,60 @@
+#ifndef __PERCPU_IDA_H__
+#define __PERCPU_IDA_H__
+
+#include <linux/types.h>
+#include <linux/bitops.h>
+#include <linux/init.h>
+#include <linux/spinlock_types.h>
+#include <linux/wait.h>
+#include <linux/cpumask.h>
+
+struct percpu_ida_cpu;
+
+struct percpu_ida {
+ /*
+ * number of tags available to be allocated, as passed to
+ * percpu_ida_init()
+ */
+ unsigned nr_tags;
+
+ struct percpu_ida_cpu __percpu *tag_cpu;
+
+ /*
+ * Bitmap of cpus that (may) have tags on their percpu freelists:
+ * steal_tags() uses this to decide when to steal tags, and which cpus
+ * to try stealing from.
+ *
+ * It's ok for a freelist to be empty when its bit is set - steal_tags()
+ * will just keep looking - but the bitmap _must_ be set whenever a
+ * percpu freelist does have tags.
+ */
+ cpumask_t cpus_have_tags;
+
+ struct {
+ spinlock_t lock;
+ /*
+ * When we go to steal tags from another cpu (see steal_tags()),
+ * we want to pick a cpu at random. Cycling through them every
+ * time we steal is a bit easier and more or less equivalent:
+ */
+ unsigned cpu_last_stolen;
+
+ /* For sleeping on allocation failure */
+ wait_queue_head_t wait;
+
+ /*
+ * Global freelist - it's a stack where nr_free points to the
+ * top
+ */
+ unsigned nr_free;
+ unsigned *freelist;
+ } ____cacheline_aligned_in_smp;
+};
+
+int percpu_ida_alloc(struct percpu_ida *pool, gfp_t gfp);
+void percpu_ida_free(struct percpu_ida *pool, unsigned tag);
+
+void percpu_ida_destroy(struct percpu_ida *pool);
+int percpu_ida_init(struct percpu_ida *pool, unsigned long nr_tags);
+
+#endif /* __PERCPU_IDA_H__ */
diff --git a/include/linux/platform_data/exynos_thermal.h b/include/linux/platform_data/exynos_thermal.h
deleted file mode 100644
index da7e627..0000000
--- a/include/linux/platform_data/exynos_thermal.h
+++ /dev/null
@@ -1,119 +0,0 @@
-/*
- * exynos_thermal.h - Samsung EXYNOS TMU (Thermal Management Unit)
- *
- * Copyright (C) 2011 Samsung Electronics
- * Donggeun Kim <dg77.kim@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- */
-
-#ifndef _LINUX_EXYNOS_THERMAL_H
-#define _LINUX_EXYNOS_THERMAL_H
-#include <linux/cpu_cooling.h>
-
-enum calibration_type {
- TYPE_ONE_POINT_TRIMMING,
- TYPE_TWO_POINT_TRIMMING,
- TYPE_NONE,
-};
-
-enum soc_type {
- SOC_ARCH_EXYNOS4210 = 1,
- SOC_ARCH_EXYNOS,
-};
-/**
- * struct freq_clip_table
- * @freq_clip_max: maximum frequency allowed for this cooling state.
- * @temp_level: Temperature level at which the temperature clipping will
- * happen.
- * @mask_val: cpumask of the allowed cpu's where the clipping will take place.
- *
- * This structure is required to be filled and passed to the
- * cpufreq_cooling_unregister function.
- */
-struct freq_clip_table {
- unsigned int freq_clip_max;
- unsigned int temp_level;
- const struct cpumask *mask_val;
-};
-
-/**
- * struct exynos_tmu_platform_data
- * @threshold: basic temperature for generating interrupt
- * 25 <= threshold <= 125 [unit: degree Celsius]
- * @threshold_falling: differntial value for setting threshold
- * of temperature falling interrupt.
- * @trigger_levels: array for each interrupt levels
- * [unit: degree Celsius]
- * 0: temperature for trigger_level0 interrupt
- * condition for trigger_level0 interrupt:
- * current temperature > threshold + trigger_levels[0]
- * 1: temperature for trigger_level1 interrupt
- * condition for trigger_level1 interrupt:
- * current temperature > threshold + trigger_levels[1]
- * 2: temperature for trigger_level2 interrupt
- * condition for trigger_level2 interrupt:
- * current temperature > threshold + trigger_levels[2]
- * 3: temperature for trigger_level3 interrupt
- * condition for trigger_level3 interrupt:
- * current temperature > threshold + trigger_levels[3]
- * @trigger_level0_en:
- * 1 = enable trigger_level0 interrupt,
- * 0 = disable trigger_level0 interrupt
- * @trigger_level1_en:
- * 1 = enable trigger_level1 interrupt,
- * 0 = disable trigger_level1 interrupt
- * @trigger_level2_en:
- * 1 = enable trigger_level2 interrupt,
- * 0 = disable trigger_level2 interrupt
- * @trigger_level3_en:
- * 1 = enable trigger_level3 interrupt,
- * 0 = disable trigger_level3 interrupt
- * @gain: gain of amplifier in the positive-TC generator block
- * 0 <= gain <= 15
- * @reference_voltage: reference voltage of amplifier
- * in the positive-TC generator block
- * 0 <= reference_voltage <= 31
- * @noise_cancel_mode: noise cancellation mode
- * 000, 100, 101, 110 and 111 can be different modes
- * @type: determines the type of SOC
- * @efuse_value: platform defined fuse value
- * @cal_type: calibration type for temperature
- * @freq_clip_table: Table representing frequency reduction percentage.
- * @freq_tab_count: Count of the above table as frequency reduction may
- * applicable to only some of the trigger levels.
- *
- * This structure is required for configuration of exynos_tmu driver.
- */
-struct exynos_tmu_platform_data {
- u8 threshold;
- u8 threshold_falling;
- u8 trigger_levels[4];
- bool trigger_level0_en;
- bool trigger_level1_en;
- bool trigger_level2_en;
- bool trigger_level3_en;
-
- u8 gain;
- u8 reference_voltage;
- u8 noise_cancel_mode;
- u32 efuse_value;
-
- enum calibration_type cal_type;
- enum soc_type type;
- struct freq_clip_table freq_tab[4];
- unsigned int freq_tab_count;
-};
-#endif /* _LINUX_EXYNOS_THERMAL_H */
diff --git a/include/linux/platform_data/leds-lp55xx.h b/include/linux/platform_data/leds-lp55xx.h
index 202e290..51a2ff5 100644
--- a/include/linux/platform_data/leds-lp55xx.h
+++ b/include/linux/platform_data/leds-lp55xx.h
@@ -36,6 +36,13 @@
u8 size_b;
};
+enum lp8501_pwr_sel {
+ LP8501_ALL_VDD, /* D1~9 are connected to VDD */
+ LP8501_6VDD_3VOUT, /* D1~6 with VDD, D7~9 with VOUT */
+ LP8501_3VDD_6VOUT, /* D1~6 with VOUT, D7~9 with VDD */
+ LP8501_ALL_VOUT, /* D1~9 are connected to VOUT */
+};
+
/*
* struct lp55xx_platform_data
* @led_config : Configurable led class device
@@ -67,6 +74,9 @@
/* Predefined pattern data */
struct lp55xx_predef_pattern *patterns;
unsigned int num_patterns;
+
+ /* LP8501 specific */
+ enum lp8501_pwr_sel pwr_sel;
};
#endif /* _LEDS_LP55XX_H */
diff --git a/include/linux/platform_data/leds-pca9633.h b/include/linux/platform_data/leds-pca963x.h
similarity index 66%
rename from include/linux/platform_data/leds-pca9633.h
rename to include/linux/platform_data/leds-pca963x.h
index c5bf29b..e731f00 100644
--- a/include/linux/platform_data/leds-pca9633.h
+++ b/include/linux/platform_data/leds-pca963x.h
@@ -1,7 +1,8 @@
/*
- * PCA9633 LED chip driver.
+ * PCA963X LED chip driver.
*
* Copyright 2012 bct electronic GmbH
+ * Copyright 2013 Qtechnology A/S
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
@@ -18,18 +19,24 @@
* 02110-1301 USA
*/
-#ifndef __LINUX_PCA9633_H
-#define __LINUX_PCA9633_H
+#ifndef __LINUX_PCA963X_H
+#define __LINUX_PCA963X_H
#include <linux/leds.h>
-enum pca9633_outdrv {
- PCA9633_OPEN_DRAIN,
- PCA9633_TOTEM_POLE, /* aka push-pull */
+enum pca963x_outdrv {
+ PCA963X_OPEN_DRAIN,
+ PCA963X_TOTEM_POLE, /* aka push-pull */
};
-struct pca9633_platform_data {
+enum pca963x_blink_type {
+ PCA963X_SW_BLINK,
+ PCA963X_HW_BLINK,
+};
+
+struct pca963x_platform_data {
struct led_platform_data leds;
- enum pca9633_outdrv outdrv;
+ enum pca963x_outdrv outdrv;
+ enum pca963x_blink_type blink_type;
};
-#endif /* __LINUX_PCA9633_H*/
+#endif /* __LINUX_PCA963X_H*/
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index ffc444c..4039407 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -231,6 +231,7 @@
unsigned long radix_tree_prev_hole(struct radix_tree_root *root,
unsigned long index, unsigned long max_scan);
int radix_tree_preload(gfp_t gfp_mask);
+int radix_tree_maybe_preload(gfp_t gfp_mask);
void radix_tree_init(void);
void *radix_tree_tag_set(struct radix_tree_root *root,
unsigned long index, unsigned int tag);
diff --git a/include/linux/ramfs.h b/include/linux/ramfs.h
index 69e37c2..753207c 100644
--- a/include/linux/ramfs.h
+++ b/include/linux/ramfs.h
@@ -25,7 +25,7 @@
extern const struct file_operations ramfs_file_operations;
extern const struct vm_operations_struct generic_file_vm_ops;
-extern int __init init_rootfs(void);
+extern int __init init_ramfs_fs(void);
int ramfs_fill_super(struct super_block *sb, void *data, int silent);
diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h
index 0022c1b..aa870a4 100644
--- a/include/linux/rbtree.h
+++ b/include/linux/rbtree.h
@@ -68,6 +68,10 @@
extern struct rb_node *rb_first(const struct rb_root *);
extern struct rb_node *rb_last(const struct rb_root *);
+/* Postorder iteration - always visit the parent after its children */
+extern struct rb_node *rb_first_postorder(const struct rb_root *);
+extern struct rb_node *rb_next_postorder(const struct rb_node *);
+
/* Fast replacement of a single node without remove/rebalance/add/rebalance */
extern void rb_replace_node(struct rb_node *victim, struct rb_node *new,
struct rb_root *root);
@@ -81,4 +85,22 @@
*rb_link = node;
}
+/**
+ * rbtree_postorder_for_each_entry_safe - iterate over rb_root in post order of
+ * given type safe against removal of rb_node entry
+ *
+ * @pos: the 'type *' to use as a loop cursor.
+ * @n: another 'type *' to use as temporary storage
+ * @root: 'rb_root *' of the rbtree.
+ * @field: the name of the rb_node field within 'type'.
+ */
+#define rbtree_postorder_for_each_entry_safe(pos, n, root, field) \
+ for (pos = rb_entry(rb_first_postorder(root), typeof(*pos), field),\
+ n = rb_entry(rb_next_postorder(&pos->field), \
+ typeof(*pos), field); \
+ &pos->field; \
+ pos = n, \
+ n = rb_entry(rb_next_postorder(&pos->field), \
+ typeof(*pos), field))
+
#endif /* _LINUX_RBTREE_H */
diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h
index 96a509b..201a697 100644
--- a/include/linux/res_counter.h
+++ b/include/linux/res_counter.h
@@ -54,7 +54,7 @@
struct res_counter *parent;
};
-#define RESOURCE_MAX (unsigned long long)LLONG_MAX
+#define RES_COUNTER_MAX ULLONG_MAX
/**
* Helpers to interact with userspace
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ce1e1c0..6682da3 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1393,6 +1393,13 @@
unsigned long memsw_nr_pages; /* uncharged mem+swap usage */
} memcg_batch;
unsigned int memcg_kmem_skip_account;
+ struct memcg_oom_info {
+ unsigned int may_oom:1;
+ unsigned int in_memcg_oom:1;
+ unsigned int oom_locked:1;
+ int wakeups;
+ struct mem_cgroup *wait_on_memcg;
+ } memcg_oom;
#endif
#ifdef CONFIG_UPROBES
struct uprobe_task *utask;
@@ -2169,15 +2176,15 @@
* all we care about is that we have a task with the appropriate
* pid, we don't actually care if we have the right task.
*/
-static inline int has_group_leader_pid(struct task_struct *p)
+static inline bool has_group_leader_pid(struct task_struct *p)
{
- return p->pid == p->tgid;
+ return task_pid(p) == p->signal->leader_pid;
}
static inline
-int same_thread_group(struct task_struct *p1, struct task_struct *p2)
+bool same_thread_group(struct task_struct *p1, struct task_struct *p2)
{
- return p1->tgid == p2->tgid;
+ return p1->signal == p2->signal;
}
static inline struct task_struct *next_thread(const struct task_struct *p)
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 1829905..21a2093 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -3,15 +3,21 @@
/*
* Reader/writer consistent mechanism without starving writers. This type of
* lock for data where the reader wants a consistent set of information
- * and is willing to retry if the information changes. Readers never
- * block but they may have to retry if a writer is in
- * progress. Writers do not wait for readers.
+ * and is willing to retry if the information changes. There are two types
+ * of readers:
+ * 1. Sequence readers which never block a writer but they may have to retry
+ * if a writer is in progress by detecting change in sequence number.
+ * Writers do not wait for a sequence reader.
+ * 2. Locking readers which will wait if a writer or another locking reader
+ * is in progress. A locking reader in progress will also block a writer
+ * from going forward. Unlike the regular rwlock, the read lock here is
+ * exclusive so that only one locking reader can get it.
*
- * This is not as cache friendly as brlock. Also, this will not work
+ * This is not as cache friendly as brlock. Also, this may not work well
* for data that contains pointers, because any writer could
* invalidate a pointer that a reader was following.
*
- * Expected reader usage:
+ * Expected non-blocking reader usage:
* do {
* seq = read_seqbegin(&foo);
* ...
@@ -268,4 +274,56 @@
spin_unlock_irqrestore(&sl->lock, flags);
}
+/*
+ * A locking reader exclusively locks out other writers and locking readers,
+ * but doesn't update the sequence number. Acts like a normal spin_lock/unlock.
+ * Don't need preempt_disable() because that is in the spin_lock already.
+ */
+static inline void read_seqlock_excl(seqlock_t *sl)
+{
+ spin_lock(&sl->lock);
+}
+
+static inline void read_sequnlock_excl(seqlock_t *sl)
+{
+ spin_unlock(&sl->lock);
+}
+
+static inline void read_seqlock_excl_bh(seqlock_t *sl)
+{
+ spin_lock_bh(&sl->lock);
+}
+
+static inline void read_sequnlock_excl_bh(seqlock_t *sl)
+{
+ spin_unlock_bh(&sl->lock);
+}
+
+static inline void read_seqlock_excl_irq(seqlock_t *sl)
+{
+ spin_lock_irq(&sl->lock);
+}
+
+static inline void read_sequnlock_excl_irq(seqlock_t *sl)
+{
+ spin_unlock_irq(&sl->lock);
+}
+
+static inline unsigned long __read_seqlock_excl_irqsave(seqlock_t *sl)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&sl->lock, flags);
+ return flags;
+}
+
+#define read_seqlock_excl_irqsave(lock, flags) \
+ do { flags = __read_seqlock_excl_irqsave(lock); } while (0)
+
+static inline void
+read_sequnlock_excl_irqrestore(seqlock_t *sl, unsigned long flags)
+{
+ spin_unlock_irqrestore(&sl->lock, flags);
+}
+
#endif /* __LINUX_SEQLOCK_H */
diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
index ac6b8ee..68c0970 100644
--- a/include/linux/shrinker.h
+++ b/include/linux/shrinker.h
@@ -4,39 +4,67 @@
/*
* This struct is used to pass information from page reclaim to the shrinkers.
* We consolidate the values for easier extention later.
+ *
+ * The 'gfpmask' refers to the allocation we are currently trying to
+ * fulfil.
*/
struct shrink_control {
gfp_t gfp_mask;
- /* How many slab objects shrinker() should scan and try to reclaim */
+ /*
+ * How many objects scan_objects should scan and try to reclaim.
+ * This is reset before every call, so it is safe for callees
+ * to modify.
+ */
unsigned long nr_to_scan;
+
+ /* shrink from these nodes */
+ nodemask_t nodes_to_scan;
+ /* current node being shrunk (for NUMA aware shrinkers) */
+ int nid;
};
+#define SHRINK_STOP (~0UL)
/*
* A callback you can register to apply pressure to ageable caches.
*
- * 'sc' is passed shrink_control which includes a count 'nr_to_scan'
- * and a 'gfpmask'. It should look through the least-recently-used
- * 'nr_to_scan' entries and attempt to free them up. It should return
- * the number of objects which remain in the cache. If it returns -1, it means
- * it cannot do any scanning at this time (eg. there is a risk of deadlock).
+ * @count_objects should return the number of freeable items in the cache. If
+ * there are no objects to free or the number of freeable items cannot be
+ * determined, it should return 0. No deadlock checks should be done during the
+ * count callback - the shrinker relies on aggregating scan counts that couldn't
+ * be executed due to potential deadlocks to be run at a later call when the
+ * deadlock condition is no longer pending.
*
- * The 'gfpmask' refers to the allocation we are currently trying to
- * fulfil.
+ * @scan_objects will only be called if @count_objects returned a non-zero
+ * value for the number of freeable objects. The callout should scan the cache
+ * and attempt to free items from the cache. It should then return the number
+ * of objects freed during the scan, or SHRINK_STOP if progress cannot be made
+ * due to potential deadlocks. If SHRINK_STOP is returned, then no further
+ * attempts to call the @scan_objects will be made from the current reclaim
+ * context.
*
- * Note that 'shrink' will be passed nr_to_scan == 0 when the VM is
- * querying the cache size, so a fastpath for that case is appropriate.
+ * @flags determine the shrinker abilities, like numa awareness
*/
struct shrinker {
- int (*shrink)(struct shrinker *, struct shrink_control *sc);
+ unsigned long (*count_objects)(struct shrinker *,
+ struct shrink_control *sc);
+ unsigned long (*scan_objects)(struct shrinker *,
+ struct shrink_control *sc);
+
int seeks; /* seeks to recreate an obj */
long batch; /* reclaim batch size, 0 = default */
+ unsigned long flags;
/* These are for internal use */
struct list_head list;
- atomic_long_t nr_in_batch; /* objs pending delete */
+ /* objs pending delete, per node */
+ atomic_long_t *nr_deferred;
};
#define DEFAULT_SEEKS 2 /* A good number if you don't know better. */
-extern void register_shrinker(struct shrinker *);
+
+/* Flags */
+#define SHRINKER_NUMA_AWARE (1 << 0)
+
+extern int register_shrinker(struct shrinker *);
extern void unregister_shrinker(struct shrinker *);
#endif
diff --git a/include/linux/smp.h b/include/linux/smp.h
index c181399..cfb7ca0 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -28,6 +28,27 @@
int smp_call_function_single(int cpuid, smp_call_func_t func, void *info,
int wait);
+/*
+ * Call a function on all processors
+ */
+int on_each_cpu(smp_call_func_t func, void *info, int wait);
+
+/*
+ * Call a function on processors specified by mask, which might include
+ * the local one.
+ */
+void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func,
+ void *info, bool wait);
+
+/*
+ * Call a function on each processor for which the supplied function
+ * cond_func returns a positive value. This may include the local
+ * processor.
+ */
+void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
+ smp_call_func_t func, void *info, bool wait,
+ gfp_t gfp_flags);
+
#ifdef CONFIG_SMP
#include <linux/preempt.h>
@@ -95,27 +116,6 @@
#endif
/*
- * Call a function on all processors
- */
-int on_each_cpu(smp_call_func_t func, void *info, int wait);
-
-/*
- * Call a function on processors specified by mask, which might include
- * the local one.
- */
-void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func,
- void *info, bool wait);
-
-/*
- * Call a function on each processor for which the supplied function
- * cond_func returns a positive value. This may include the local
- * processor.
- */
-void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
- smp_call_func_t func, void *info, bool wait,
- gfp_t gfp_flags);
-
-/*
* Mark the boot cpu "online" so that it can call console drivers in
* printk() and can access its per-cpu storage.
*/
@@ -139,43 +139,6 @@
}
#define smp_call_function(func, info, wait) \
(up_smp_call_function(func, info))
-#define on_each_cpu(func, info, wait) \
- ({ \
- unsigned long __flags; \
- local_irq_save(__flags); \
- func(info); \
- local_irq_restore(__flags); \
- 0; \
- })
-/*
- * Note we still need to test the mask even for UP
- * because we actually can get an empty mask from
- * code that on SMP might call us without the local
- * CPU in the mask.
- */
-#define on_each_cpu_mask(mask, func, info, wait) \
- do { \
- if (cpumask_test_cpu(0, (mask))) { \
- local_irq_disable(); \
- (func)(info); \
- local_irq_enable(); \
- } \
- } while (0)
-/*
- * Preemption is disabled here to make sure the cond_func is called under the
- * same condtions in UP and SMP.
- */
-#define on_each_cpu_cond(cond_func, func, info, wait, gfp_flags)\
- do { \
- void *__info = (info); \
- preempt_disable(); \
- if ((cond_func)(0, __info)) { \
- local_irq_disable(); \
- (func)(__info); \
- local_irq_enable(); \
- } \
- preempt_enable(); \
- } while (0)
static inline void smp_send_reschedule(int cpu) { }
#define smp_prepare_boot_cpu() do {} while (0)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index d95cde5..46ba0c6 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -182,6 +182,33 @@
#define SWAP_MAP_SHMEM 0xbf /* Owned by shmem/tmpfs, in first swap_map */
/*
+ * We use this to track usage of a cluster. A cluster is a block of swap disk
+ * space with SWAPFILE_CLUSTER pages long and naturally aligns in disk. All
+ * free clusters are organized into a list. We fetch an entry from the list to
+ * get a free cluster.
+ *
+ * The data field stores next cluster if the cluster is free or cluster usage
+ * counter otherwise. The flags field determines if a cluster is free. This is
+ * protected by swap_info_struct.lock.
+ */
+struct swap_cluster_info {
+ unsigned int data:24;
+ unsigned int flags:8;
+};
+#define CLUSTER_FLAG_FREE 1 /* This cluster is free */
+#define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */
+
+/*
+ * We assign a cluster to each CPU, so each CPU can allocate swap entry from
+ * its own cluster and swapout sequentially. The purpose is to optimize swapout
+ * throughput.
+ */
+struct percpu_cluster {
+ struct swap_cluster_info index; /* Current cluster index */
+ unsigned int next; /* Likely next allocation offset */
+};
+
+/*
* The in-memory structure used to track swap areas.
*/
struct swap_info_struct {
@@ -191,14 +218,16 @@
signed char next; /* next type on the swap list */
unsigned int max; /* extent of the swap_map */
unsigned char *swap_map; /* vmalloc'ed array of usage counts */
+ struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */
+ struct swap_cluster_info free_cluster_head; /* free cluster list head */
+ struct swap_cluster_info free_cluster_tail; /* free cluster list tail */
unsigned int lowest_bit; /* index of first free in swap_map */
unsigned int highest_bit; /* index of last free in swap_map */
unsigned int pages; /* total of usable pages of swap */
unsigned int inuse_pages; /* number of those currently in use */
unsigned int cluster_next; /* likely index for next allocation */
unsigned int cluster_nr; /* countdown to next cluster search */
- unsigned int lowest_alloc; /* while preparing discard cluster */
- unsigned int highest_alloc; /* while preparing discard cluster */
+ struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */
struct swap_extent *curr_swap_extent;
struct swap_extent first_swap_extent;
struct block_device *bdev; /* swap device or bdev of swap file */
@@ -212,14 +241,18 @@
* protect map scan related fields like
* swap_map, lowest_bit, highest_bit,
* inuse_pages, cluster_next,
- * cluster_nr, lowest_alloc and
- * highest_alloc. other fields are only
- * changed at swapon/swapoff, so are
- * protected by swap_lock. changing
- * flags need hold this lock and
- * swap_lock. If both locks need hold,
- * hold swap_lock first.
+ * cluster_nr, lowest_alloc,
+ * highest_alloc, free/discard cluster
+ * list. other fields are only changed
+ * at swapon/swapoff, so are protected
+ * by swap_lock. changing flags need
+ * hold this lock and swap_lock. If
+ * both locks need hold, hold swap_lock
+ * first.
*/
+ struct work_struct discard_work; /* discard worker */
+ struct swap_cluster_info discard_cluster_head; /* list head of discard clusters */
+ struct swap_cluster_info discard_cluster_tail; /* list tail of discard clusters */
};
struct swap_list_t {
@@ -247,7 +280,7 @@
extern void mark_page_accessed(struct page *);
extern void lru_add_drain(void);
extern void lru_add_drain_cpu(int cpu);
-extern int lru_add_drain_all(void);
+extern void lru_add_drain_all(void);
extern void rotate_reclaimable_page(struct page *page);
extern void deactivate_page(struct page *page);
extern void swap_setup(void);
@@ -414,6 +447,7 @@
#else /* CONFIG_SWAP */
+#define swap_address_space(entry) (NULL)
#define get_nr_swap_pages() 0L
#define total_swap_pages 0L
#define total_swapcache_pages() 0UL
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 84662ec..7fac04e 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -186,6 +186,7 @@
#define __SYSCALL_DEFINEx(x, name, ...) \
asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \
static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \
+ asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \
asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \
{ \
long ret = SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__)); \
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index a386a1c..b268d3c 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -207,6 +207,16 @@
* See Documentation/thermal/sysfs-api.txt for more information.
*/
int trip_mask;
+
+ /*
+ * This is an array of cooling state limits. Must have exactly
+ * 2 * thermal_zone.number_of_trip_points. It is an array consisting
+ * of tuples <lower-state upper-state> of state limits. Each trip
+ * will be associated with one state limit tuple when binding.
+ * A NULL pointer means <THERMAL_NO_LIMITS THERMAL_NO_LIMITS>
+ * on all trips.
+ */
+ unsigned long *binding_limits;
int (*match) (struct thermal_zone_device *tz,
struct thermal_cooling_device *cdev);
};
@@ -214,6 +224,14 @@
/* Structure to define Thermal Zone parameters */
struct thermal_zone_params {
char governor_name[THERMAL_NAME_LENGTH];
+
+ /*
+ * a boolean to indicate if the thermal to hwmon sysfs interface
+ * is required. when no_hwmon == false, a hwmon sysfs interface
+ * will be created. when no_hwmon == true, nothing will be done
+ */
+ bool no_hwmon;
+
int num_tbps; /* Number of tbp entries */
struct thermal_bind_params *tbp;
};
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index bd6cf61..1855f0a 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -70,6 +70,12 @@
THP_ZERO_PAGE_ALLOC,
THP_ZERO_PAGE_ALLOC_FAILED,
#endif
+#ifdef CONFIG_SMP
+ NR_TLB_REMOTE_FLUSH, /* cpu tried to flush others' tlbs */
+ NR_TLB_REMOTE_FLUSH_RECEIVED,/* cpu received ipi for flush */
+#endif
+ NR_TLB_LOCAL_FLUSH_ALL,
+ NR_TLB_LOCAL_FLUSH_ONE,
NR_VM_EVENT_ITEMS
};
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index c586679..e4b9480 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -143,7 +143,6 @@
}
extern unsigned long global_reclaimable_pages(void);
-extern unsigned long zone_reclaimable_pages(struct zone *zone);
#ifdef CONFIG_NUMA
/*
@@ -198,7 +197,7 @@
extern void dec_zone_state(struct zone *, enum zone_stat_item);
extern void __dec_zone_state(struct zone *, enum zone_stat_item);
-void refresh_cpu_vm_stats(int);
+void cpu_vm_stats_fold(int cpu);
void refresh_zone_stat_thresholds(void);
void drain_zonestat(struct zone *zone, struct per_cpu_pageset *);
@@ -255,6 +254,7 @@
static inline void refresh_cpu_vm_stats(int cpu) { }
static inline void refresh_zone_stat_thresholds(void) { }
+static inline void cpu_vm_stats_fold(int cpu) { }
static inline void drain_zonestat(struct zone *zone,
struct per_cpu_pageset *pset) { }
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 4e198ca..021b8a3 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -98,8 +98,6 @@
int try_to_writeback_inodes_sb_nr(struct super_block *, unsigned long nr,
enum wb_reason reason);
void sync_inodes_sb(struct super_block *);
-long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages,
- enum wb_reason reason);
void wakeup_flusher_threads(long nr_pages, enum wb_reason reason);
void inode_wait_for_writeback(struct inode *inode);
diff --git a/include/net/9p/client.h b/include/net/9p/client.h
index 4c7c01a..c38a005 100644
--- a/include/net/9p/client.h
+++ b/include/net/9p/client.h
@@ -26,6 +26,8 @@
#ifndef NET_9P_CLIENT_H
#define NET_9P_CLIENT_H
+#include <linux/utsname.h>
+
/* Number of requests per row */
#define P9_ROW_MAXTAG 255
@@ -134,6 +136,7 @@
* @tagpool - transaction id accounting for session
* @reqs - 2D array of requests
* @max_tag - current maximum tag id allocated
+ * @name - node name used as client id
*
* The client structure is used to keep track of various per-client
* state that has been instantiated.
@@ -164,6 +167,8 @@
struct p9_idpool *tagpool;
struct p9_req_t *reqs[P9_ROW_MAXTAG];
int max_tag;
+
+ char name[__NEW_UTS_LEN + 1];
};
/**
diff --git a/include/net/ndisc.h b/include/net/ndisc.h
index 3c4211f..ea0cc26 100644
--- a/include/net/ndisc.h
+++ b/include/net/ndisc.h
@@ -190,7 +190,9 @@
}
extern int ndisc_init(void);
+extern int ndisc_late_init(void);
+extern void ndisc_late_cleanup(void);
extern void ndisc_cleanup(void);
extern int ndisc_rcv(struct sk_buff *skb);
diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h
index d477bfb..66d42ed 100644
--- a/include/scsi/scsi.h
+++ b/include/scsi/scsi.h
@@ -144,6 +144,7 @@
#define ACCESS_CONTROL_IN 0x86
#define ACCESS_CONTROL_OUT 0x87
#define READ_16 0x88
+#define COMPARE_AND_WRITE 0x89
#define WRITE_16 0x8a
#define READ_ATTRIBUTE 0x8c
#define WRITE_ATTRIBUTE 0x8d
diff --git a/include/sound/rcar_snd.h b/include/sound/rcar_snd.h
index d35412a..fe66533 100644
--- a/include/sound/rcar_snd.h
+++ b/include/sound/rcar_snd.h
@@ -55,7 +55,7 @@
/*
* flags
*/
-#define RSND_SCU_USB_HPBIF (1 << 31) /* it needs RSND_SSI_DEPENDENT */
+#define RSND_SCU_USE_HPBIF (1 << 31) /* it needs RSND_SSI_DEPENDENT */
struct rsnd_scu_platform_info {
u32 flags;
diff --git a/include/target/iscsi/iscsi_transport.h b/include/target/iscsi/iscsi_transport.h
index e5d09d2..a12589c 100644
--- a/include/target/iscsi/iscsi_transport.h
+++ b/include/target/iscsi/iscsi_transport.h
@@ -6,13 +6,13 @@
#define ISCSIT_TRANSPORT_NAME 16
char name[ISCSIT_TRANSPORT_NAME];
int transport_type;
+ int priv_size;
struct module *owner;
struct list_head t_node;
int (*iscsit_setup_np)(struct iscsi_np *, struct __kernel_sockaddr_storage *);
int (*iscsit_accept_np)(struct iscsi_np *, struct iscsi_conn *);
void (*iscsit_free_np)(struct iscsi_np *);
void (*iscsit_free_conn)(struct iscsi_conn *);
- struct iscsi_cmd *(*iscsit_alloc_cmd)(struct iscsi_conn *, gfp_t);
int (*iscsit_get_login_rx)(struct iscsi_conn *, struct iscsi_login *);
int (*iscsit_put_login_tx)(struct iscsi_conn *, struct iscsi_login *, u32);
int (*iscsit_immediate_queue)(struct iscsi_conn *, struct iscsi_cmd *, int);
@@ -22,6 +22,11 @@
int (*iscsit_queue_status)(struct iscsi_conn *, struct iscsi_cmd *);
};
+static inline void *iscsit_priv_cmd(struct iscsi_cmd *cmd)
+{
+ return (void *)(cmd + 1);
+}
+
/*
* From iscsi_target_transport.c
*/
@@ -92,3 +97,4 @@
extern struct iscsi_cmd *iscsit_allocate_cmd(struct iscsi_conn *, gfp_t);
extern int iscsit_sequence_cmd(struct iscsi_conn *, struct iscsi_cmd *,
unsigned char *, __be32);
+extern void iscsit_release_cmd(struct iscsi_cmd *);
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index ffa2696..5ebe21c 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -39,7 +39,8 @@
};
struct sbc_ops {
- sense_reason_t (*execute_rw)(struct se_cmd *cmd);
+ sense_reason_t (*execute_rw)(struct se_cmd *cmd, struct scatterlist *,
+ u32, enum dma_data_direction);
sense_reason_t (*execute_sync_cache)(struct se_cmd *cmd);
sense_reason_t (*execute_write_same)(struct se_cmd *cmd);
sense_reason_t (*execute_write_same_unmap)(struct se_cmd *cmd);
@@ -73,6 +74,10 @@
/* core helpers also used by command snooping in pscsi */
void *transport_kmap_data_sg(struct se_cmd *);
void transport_kunmap_data_sg(struct se_cmd *);
+/* core helpers also used by xcopy during internal command setup */
+int target_alloc_sgl(struct scatterlist **, unsigned int *, u32, bool);
+sense_reason_t transport_generic_map_mem_to_cmd(struct se_cmd *,
+ struct scatterlist *, u32, struct scatterlist *, u32);
void array_free(void *array, int n);
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index e34fc90..5bdb8b7 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -5,11 +5,12 @@
#include <linux/configfs.h>
#include <linux/dma-mapping.h>
#include <linux/blkdev.h>
+#include <linux/percpu_ida.h>
#include <scsi/scsi_cmnd.h>
#include <net/sock.h>
#include <net/tcp.h>
-#define TARGET_CORE_MOD_VERSION "v4.1.0-rc2-ml"
+#define TARGET_CORE_MOD_VERSION "v4.1.0"
#define TARGET_CORE_VERSION TARGET_CORE_MOD_VERSION
/* Maximum Number of LUNs per Target Portal Group */
@@ -96,6 +97,10 @@
* block/blk-lib.c:blkdev_issue_discard()
*/
#define DA_EMULATE_TPWS 0
+/* Emulation for CompareAndWrite (AtomicTestandSet) by default */
+#define DA_EMULATE_CAW 1
+/* Emulation for 3rd Party Copy (ExtendedCopy) by default */
+#define DA_EMULATE_3PC 1
/* No Emulation for PSCSI by default */
#define DA_EMULATE_ALUA 0
/* Enforce SCSI Initiator Port TransportID with 'ISID' for PR */
@@ -158,6 +163,9 @@
SCF_ALUA_NON_OPTIMIZED = 0x00008000,
SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC = 0x00020000,
SCF_ACK_KREF = 0x00040000,
+ SCF_COMPARE_AND_WRITE = 0x00080000,
+ SCF_COMPARE_AND_WRITE_POST = 0x00100000,
+ SCF_CMD_XCOPY_PASSTHROUGH = 0x00200000,
};
/* struct se_dev_entry->lun_flags and struct se_lun->lun_access */
@@ -196,6 +204,7 @@
TCM_ADDRESS_OUT_OF_RANGE = R(0x11),
TCM_OUT_OF_RESOURCES = R(0x12),
TCM_PARAMETER_LIST_LENGTH_ERROR = R(0x13),
+ TCM_MISCOMPARE_VERIFY = R(0x14),
#undef R
};
@@ -415,6 +424,8 @@
enum dma_data_direction data_direction;
/* For SAM Task Attribute */
int sam_task_attr;
+ /* Used for se_sess->sess_tag_pool */
+ unsigned int map_tag;
/* Transport protocol dependent state, see transport_state_table */
enum transport_state_table t_state;
unsigned cmd_wait_set:1;
@@ -444,11 +455,14 @@
struct kref cmd_kref;
struct target_core_fabric_ops *se_tfo;
sense_reason_t (*execute_cmd)(struct se_cmd *);
- void (*transport_complete_callback)(struct se_cmd *);
+ sense_reason_t (*execute_rw)(struct se_cmd *, struct scatterlist *,
+ u32, enum dma_data_direction);
+ sense_reason_t (*transport_complete_callback)(struct se_cmd *);
unsigned char *t_task_cdb;
unsigned char __t_task_cdb[TCM_MAX_COMMAND_SIZE];
unsigned long long t_task_lba;
+ unsigned int t_task_nolb;
unsigned int transport_state;
#define CMD_T_ABORTED (1 << 0)
#define CMD_T_ACTIVE (1 << 1)
@@ -469,7 +483,9 @@
struct work_struct work;
struct scatterlist *t_data_sg;
+ struct scatterlist *t_data_sg_orig;
unsigned int t_data_nents;
+ unsigned int t_data_nents_orig;
void *t_data_vmap;
struct scatterlist *t_bidi_data_sg;
unsigned int t_bidi_data_nents;
@@ -536,6 +552,8 @@
struct list_head sess_wait_list;
spinlock_t sess_cmd_lock;
struct kref sess_kref;
+ void *sess_cmd_map;
+ struct percpu_ida sess_tag_pool;
};
struct se_device;
@@ -589,6 +607,8 @@
int emulate_tas;
int emulate_tpu;
int emulate_tpws;
+ int emulate_caw;
+ int emulate_3pc;
int enforce_pr_isids;
int is_nonrot;
int emulate_rest_reord;
@@ -656,6 +676,7 @@
spinlock_t se_port_lock;
spinlock_t se_tmr_lock;
spinlock_t qf_cmd_lock;
+ struct semaphore caw_sem;
/* Used for legacy SPC-2 reservationsa */
struct se_node_acl *dev_reserved_node_acl;
/* Used for ALUA Logical Unit Group membership */
@@ -669,6 +690,7 @@
struct list_head delayed_cmd_list;
struct list_head state_list;
struct list_head qf_cmd_list;
+ struct list_head g_dev_node;
/* Pointer to associated SE HBA */
struct se_hba *se_hba;
/* T10 Inquiry and VPD WWN Information */
diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h
index 7a16178..882b650e 100644
--- a/include/target/target_core_fabric.h
+++ b/include/target/target_core_fabric.h
@@ -84,6 +84,9 @@
};
struct se_session *transport_init_session(void);
+int transport_alloc_session_tags(struct se_session *, unsigned int,
+ unsigned int);
+struct se_session *transport_init_session_tags(unsigned int, unsigned int);
void __transport_register_session(struct se_portal_group *,
struct se_node_acl *, struct se_session *, void *);
void transport_register_session(struct se_portal_group *,
@@ -131,6 +134,7 @@
void core_tmr_release_req(struct se_tmr_req *);
int transport_generic_handle_tmr(struct se_cmd *);
void transport_generic_request_failure(struct se_cmd *, sense_reason_t);
+void __target_execute_cmd(struct se_cmd *);
int transport_lookup_tmr_lun(struct se_cmd *, u32);
struct se_node_acl *core_tpg_check_initiator_node_acl(struct se_portal_group *,
@@ -175,4 +179,30 @@
char *iscsi_parse_pr_out_transport_id(struct se_portal_group *, const char *,
u32 *, char **);
+/*
+ * The LIO target core uses DMA_TO_DEVICE to mean that data is going
+ * to the target (eg handling a WRITE) and DMA_FROM_DEVICE to mean
+ * that data is coming from the target (eg handling a READ). However,
+ * this is just the opposite of what we have to tell the DMA mapping
+ * layer -- eg when handling a READ, the HBA will have to DMA the data
+ * out of memory so it can send it to the initiator, which means we
+ * need to use DMA_TO_DEVICE when we map the data.
+ */
+static inline enum dma_data_direction
+target_reverse_dma_direction(struct se_cmd *se_cmd)
+{
+ if (se_cmd->se_cmd_flags & SCF_BIDI)
+ return DMA_BIDIRECTIONAL;
+
+ switch (se_cmd->data_direction) {
+ case DMA_TO_DEVICE:
+ return DMA_FROM_DEVICE;
+ case DMA_FROM_DEVICE:
+ return DMA_TO_DEVICE;
+ case DMA_NONE:
+ default:
+ return DMA_NONE;
+ }
+}
+
#endif /* TARGET_CORE_FABRICH */
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 2902657..45702c3 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -439,7 +439,7 @@
{ BTRFS_UPDATE_DELAYED_HEAD, "UPDATE_DELAYED_HEAD" })
-TRACE_EVENT(btrfs_delayed_tree_ref,
+DECLARE_EVENT_CLASS(btrfs_delayed_tree_ref,
TP_PROTO(struct btrfs_delayed_ref_node *ref,
struct btrfs_delayed_tree_ref *full_ref,
@@ -481,7 +481,25 @@
(unsigned long long)__entry->seq)
);
-TRACE_EVENT(btrfs_delayed_data_ref,
+DEFINE_EVENT(btrfs_delayed_tree_ref, add_delayed_tree_ref,
+
+ TP_PROTO(struct btrfs_delayed_ref_node *ref,
+ struct btrfs_delayed_tree_ref *full_ref,
+ int action),
+
+ TP_ARGS(ref, full_ref, action)
+);
+
+DEFINE_EVENT(btrfs_delayed_tree_ref, run_delayed_tree_ref,
+
+ TP_PROTO(struct btrfs_delayed_ref_node *ref,
+ struct btrfs_delayed_tree_ref *full_ref,
+ int action),
+
+ TP_ARGS(ref, full_ref, action)
+);
+
+DECLARE_EVENT_CLASS(btrfs_delayed_data_ref,
TP_PROTO(struct btrfs_delayed_ref_node *ref,
struct btrfs_delayed_data_ref *full_ref,
@@ -527,7 +545,25 @@
(unsigned long long)__entry->seq)
);
-TRACE_EVENT(btrfs_delayed_ref_head,
+DEFINE_EVENT(btrfs_delayed_data_ref, add_delayed_data_ref,
+
+ TP_PROTO(struct btrfs_delayed_ref_node *ref,
+ struct btrfs_delayed_data_ref *full_ref,
+ int action),
+
+ TP_ARGS(ref, full_ref, action)
+);
+
+DEFINE_EVENT(btrfs_delayed_data_ref, run_delayed_data_ref,
+
+ TP_PROTO(struct btrfs_delayed_ref_node *ref,
+ struct btrfs_delayed_data_ref *full_ref,
+ int action),
+
+ TP_ARGS(ref, full_ref, action)
+);
+
+DECLARE_EVENT_CLASS(btrfs_delayed_ref_head,
TP_PROTO(struct btrfs_delayed_ref_node *ref,
struct btrfs_delayed_ref_head *head_ref,
@@ -556,6 +592,24 @@
__entry->is_data)
);
+DEFINE_EVENT(btrfs_delayed_ref_head, add_delayed_ref_head,
+
+ TP_PROTO(struct btrfs_delayed_ref_node *ref,
+ struct btrfs_delayed_ref_head *head_ref,
+ int action),
+
+ TP_ARGS(ref, head_ref, action)
+);
+
+DEFINE_EVENT(btrfs_delayed_ref_head, run_delayed_ref_head,
+
+ TP_PROTO(struct btrfs_delayed_ref_node *ref,
+ struct btrfs_delayed_ref_head *head_ref,
+ int action),
+
+ TP_ARGS(ref, head_ref, action)
+);
+
#define show_chunk_type(type) \
__print_flags(type, "|", \
{ BTRFS_BLOCK_GROUP_DATA, "DATA" }, \
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index 6bc943e..d0c6134 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -268,11 +268,13 @@
TP_PROTO(struct page *page,
int alloc_order, int fallback_order,
- int alloc_migratetype, int fallback_migratetype),
+ int alloc_migratetype, int fallback_migratetype,
+ int change_ownership),
TP_ARGS(page,
alloc_order, fallback_order,
- alloc_migratetype, fallback_migratetype),
+ alloc_migratetype, fallback_migratetype,
+ change_ownership),
TP_STRUCT__entry(
__field( struct page *, page )
@@ -280,6 +282,7 @@
__field( int, fallback_order )
__field( int, alloc_migratetype )
__field( int, fallback_migratetype )
+ __field( int, change_ownership )
),
TP_fast_assign(
@@ -288,6 +291,7 @@
__entry->fallback_order = fallback_order;
__entry->alloc_migratetype = alloc_migratetype;
__entry->fallback_migratetype = fallback_migratetype;
+ __entry->change_ownership = change_ownership;
),
TP_printk("page=%p pfn=%lu alloc_order=%d fallback_order=%d pageblock_order=%d alloc_migratetype=%d fallback_migratetype=%d fragmenting=%d change_ownership=%d",
@@ -299,7 +303,7 @@
__entry->alloc_migratetype,
__entry->fallback_migratetype,
__entry->fallback_order < pageblock_order,
- __entry->alloc_migratetype == __entry->fallback_migratetype)
+ __entry->change_ownership)
);
#endif /* _TRACE_KMEM_H */
diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index 63cfccc..132a985 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -202,7 +202,7 @@
TP_fast_assign(
__entry->shr = shr;
- __entry->shrink = shr->shrink;
+ __entry->shrink = shr->scan_objects;
__entry->nr_objects_to_shrink = nr_objects_to_shrink;
__entry->gfp_flags = sc->gfp_mask;
__entry->pgs_scanned = pgs_scanned;
@@ -241,7 +241,7 @@
TP_fast_assign(
__entry->shr = shr;
- __entry->shrink = shr->shrink;
+ __entry->shrink = shr->scan_objects;
__entry->unused_scan = unused_scan_cnt;
__entry->new_scan = new_scan_cnt;
__entry->retval = shrinker_retval;
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index 05aed70..45e6189 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -305,6 +305,31 @@
#define BTRFS_DEFRAG_RANGE_COMPRESS 1
#define BTRFS_DEFRAG_RANGE_START_IO 2
+#define BTRFS_SAME_DATA_DIFFERS 1
+/* For extent-same ioctl */
+struct btrfs_ioctl_same_extent_info {
+ __s64 fd; /* in - destination file */
+ __u64 logical_offset; /* in - start of extent in destination */
+ __u64 bytes_deduped; /* out - total # of bytes we were able
+ * to dedupe from this file */
+ /* status of this dedupe operation:
+ * 0 if dedup succeeds
+ * < 0 for error
+ * == BTRFS_SAME_DATA_DIFFERS if data differs
+ */
+ __s32 status; /* out - see above description */
+ __u32 reserved;
+};
+
+struct btrfs_ioctl_same_args {
+ __u64 logical_offset; /* in - start of extent in source */
+ __u64 length; /* in - length of extent */
+ __u16 dest_count; /* in - total elements in info array */
+ __u16 reserved1;
+ __u32 reserved2;
+ struct btrfs_ioctl_same_extent_info info[0];
+};
+
struct btrfs_ioctl_space_info {
__u64 flags;
__u64 total_bytes;
@@ -524,7 +549,7 @@
struct btrfs_ioctl_search_args)
#define BTRFS_IOC_INO_LOOKUP _IOWR(BTRFS_IOCTL_MAGIC, 18, \
struct btrfs_ioctl_ino_lookup_args)
-#define BTRFS_IOC_DEFAULT_SUBVOL _IOW(BTRFS_IOCTL_MAGIC, 19, u64)
+#define BTRFS_IOC_DEFAULT_SUBVOL _IOW(BTRFS_IOCTL_MAGIC, 19, __u64)
#define BTRFS_IOC_SPACE_INFO _IOWR(BTRFS_IOCTL_MAGIC, 20, \
struct btrfs_ioctl_space_args)
#define BTRFS_IOC_START_SYNC _IOR(BTRFS_IOCTL_MAGIC, 24, __u64)
@@ -579,4 +604,7 @@
struct btrfs_ioctl_get_dev_stats)
#define BTRFS_IOC_DEV_REPLACE _IOWR(BTRFS_IOCTL_MAGIC, 53, \
struct btrfs_ioctl_dev_replace_args)
+#define BTRFS_IOC_FILE_EXTENT_SAME _IOWR(BTRFS_IOCTL_MAGIC, 54, \
+ struct btrfs_ioctl_same_args)
+
#endif /* _UAPI_LINUX_BTRFS_H */
diff --git a/include/uapi/linux/cifs/cifs_mount.h b/include/uapi/linux/cifs/cifs_mount.h
new file mode 100644
index 0000000..d7e4c6c
--- /dev/null
+++ b/include/uapi/linux/cifs/cifs_mount.h
@@ -0,0 +1,27 @@
+/*
+ * include/uapi/linux/cifs/cifs_mount.h
+ *
+ * Author(s): Scott Lovenberg (scott.lovenberg@gmail.com)
+ *
+ * This library is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published
+ * by the Free Software Foundation; either version 2.1 of the License, or
+ * (at your option) any later version.
+ *
+ * This library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
+ * the GNU Lesser General Public License for more details.
+ */
+#ifndef _CIFS_MOUNT_H
+#define _CIFS_MOUNT_H
+
+/* Max string lengths for cifs mounting options. */
+#define CIFS_MAX_DOMAINNAME_LEN 256 /* max fully qualified domain name */
+#define CIFS_MAX_USERNAME_LEN 256 /* reasonable max for current servers */
+#define CIFS_MAX_PASSWORD_LEN 512 /* Windows max seems to be 256 wide chars */
+#define CIFS_MAX_SHARE_LEN 256 /* reasonable max share name length */
+#define CIFS_NI_MAXHOST 1024 /* max host name length (256 * 4 bytes) */
+
+
+#endif /* _CIFS_MOUNT_H */
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index a4ed56c..6c28b61 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -49,9 +49,9 @@
};
struct inodes_stat_t {
- int nr_inodes;
- int nr_unused;
- int dummy[5]; /* padding for sysctl ABI compatibility */
+ long nr_inodes;
+ long nr_unused;
+ long dummy[5]; /* padding for sysctl ABI compatibility */
};
diff --git a/init/Kconfig b/init/Kconfig
index bfa9e13..18bd9e3 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1670,6 +1670,7 @@
menuconfig MODULES
bool "Enable loadable module support"
+ option modules
help
Kernel modules are small pieces of compiled code which can
be inserted in the running kernel, rather than being
diff --git a/init/do_mounts.c b/init/do_mounts.c
index 816014c..a51cddc 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -26,6 +26,8 @@
#include <linux/async.h>
#include <linux/fs_struct.h>
#include <linux/slab.h>
+#include <linux/ramfs.h>
+#include <linux/shmem_fs.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_fs_sb.h>
@@ -588,3 +590,46 @@
sys_mount(".", "/", NULL, MS_MOVE, NULL);
sys_chroot(".");
}
+
+static bool is_tmpfs;
+static struct dentry *rootfs_mount(struct file_system_type *fs_type,
+ int flags, const char *dev_name, void *data)
+{
+ static unsigned long once;
+ void *fill = ramfs_fill_super;
+
+ if (test_and_set_bit(0, &once))
+ return ERR_PTR(-ENODEV);
+
+ if (IS_ENABLED(CONFIG_TMPFS) && is_tmpfs)
+ fill = shmem_fill_super;
+
+ return mount_nodev(fs_type, flags, data, fill);
+}
+
+static struct file_system_type rootfs_fs_type = {
+ .name = "rootfs",
+ .mount = rootfs_mount,
+ .kill_sb = kill_litter_super,
+};
+
+int __init init_rootfs(void)
+{
+ int err = register_filesystem(&rootfs_fs_type);
+
+ if (err)
+ return err;
+
+ if (IS_ENABLED(CONFIG_TMPFS) && !saved_root_name[0] &&
+ (!root_fs_names || strstr(root_fs_names, "tmpfs"))) {
+ err = shmem_init();
+ is_tmpfs = true;
+ } else {
+ err = init_ramfs_fs();
+ }
+
+ if (err)
+ unregister_filesystem(&rootfs_fs_type);
+
+ return err;
+}
diff --git a/ipc/msg.c b/ipc/msg.c
index b65fdf1..b0d541d4 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -70,8 +70,6 @@
#define msg_ids(ns) ((ns)->ids[IPC_MSG_IDS])
-#define msg_unlock(msq) ipc_unlock(&(msq)->q_perm)
-
static void freeque(struct ipc_namespace *, struct kern_ipc_perm *);
static int newque(struct ipc_namespace *, struct ipc_params *);
#ifdef CONFIG_PROC_FS
@@ -172,7 +170,7 @@
* @ns: namespace
* @params: ptr to the structure that contains the key and msgflg
*
- * Called with msg_ids.rw_mutex held (writer)
+ * Called with msg_ids.rwsem held (writer)
*/
static int newque(struct ipc_namespace *ns, struct ipc_params *params)
{
@@ -259,8 +257,8 @@
* removes the message queue from message queue ID IDR, and cleans up all the
* messages associated with this queue.
*
- * msg_ids.rw_mutex (writer) and the spinlock for this message queue are held
- * before freeque() is called. msg_ids.rw_mutex remains locked on exit.
+ * msg_ids.rwsem (writer) and the spinlock for this message queue are held
+ * before freeque() is called. msg_ids.rwsem remains locked on exit.
*/
static void freeque(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
{
@@ -270,7 +268,8 @@
expunge_all(msq, -EIDRM);
ss_wakeup(&msq->q_senders, 1);
msg_rmid(ns, msq);
- msg_unlock(msq);
+ ipc_unlock_object(&msq->q_perm);
+ rcu_read_unlock();
list_for_each_entry_safe(msg, t, &msq->q_messages, m_list) {
atomic_dec(&ns->msg_hdrs);
@@ -282,7 +281,7 @@
}
/*
- * Called with msg_ids.rw_mutex and ipcp locked.
+ * Called with msg_ids.rwsem and ipcp locked.
*/
static inline int msg_security(struct kern_ipc_perm *ipcp, int msgflg)
{
@@ -386,9 +385,9 @@
}
/*
- * This function handles some msgctl commands which require the rw_mutex
+ * This function handles some msgctl commands which require the rwsem
* to be held in write mode.
- * NOTE: no locks must be held, the rw_mutex is taken inside this function.
+ * NOTE: no locks must be held, the rwsem is taken inside this function.
*/
static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd,
struct msqid_ds __user *buf, int version)
@@ -403,7 +402,7 @@
return -EFAULT;
}
- down_write(&msg_ids(ns).rw_mutex);
+ down_write(&msg_ids(ns).rwsem);
rcu_read_lock();
ipcp = ipcctl_pre_down_nolock(ns, &msg_ids(ns), msqid, cmd,
@@ -459,7 +458,7 @@
out_unlock1:
rcu_read_unlock();
out_up:
- up_write(&msg_ids(ns).rw_mutex);
+ up_write(&msg_ids(ns).rwsem);
return err;
}
@@ -494,7 +493,7 @@
msginfo.msgmnb = ns->msg_ctlmnb;
msginfo.msgssz = MSGSSZ;
msginfo.msgseg = MSGSEG;
- down_read(&msg_ids(ns).rw_mutex);
+ down_read(&msg_ids(ns).rwsem);
if (cmd == MSG_INFO) {
msginfo.msgpool = msg_ids(ns).in_use;
msginfo.msgmap = atomic_read(&ns->msg_hdrs);
@@ -505,7 +504,7 @@
msginfo.msgtql = MSGTQL;
}
max_id = ipc_get_maxid(&msg_ids(ns));
- up_read(&msg_ids(ns).rw_mutex);
+ up_read(&msg_ids(ns).rwsem);
if (copy_to_user(buf, &msginfo, sizeof(struct msginfo)))
return -EFAULT;
return (max_id < 0) ? 0 : max_id;
diff --git a/ipc/namespace.c b/ipc/namespace.c
index 4be6581..59451c1 100644
--- a/ipc/namespace.c
+++ b/ipc/namespace.c
@@ -81,7 +81,7 @@
int next_id;
int total, in_use;
- down_write(&ids->rw_mutex);
+ down_write(&ids->rwsem);
in_use = ids->in_use;
@@ -89,11 +89,12 @@
perm = idr_find(&ids->ipcs_idr, next_id);
if (perm == NULL)
continue;
- ipc_lock_by_ptr(perm);
+ rcu_read_lock();
+ ipc_lock_object(perm);
free(ns, perm);
total++;
}
- up_write(&ids->rw_mutex);
+ up_write(&ids->rwsem);
}
static void free_ipc_ns(struct ipc_namespace *ns)
diff --git a/ipc/sem.c b/ipc/sem.c
index 4108889..69b6a21 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -322,7 +322,7 @@
}
/*
- * sem_lock_(check_) routines are called in the paths where the rw_mutex
+ * sem_lock_(check_) routines are called in the paths where the rwsem
* is not held.
*
* The caller holds the RCU read lock.
@@ -426,7 +426,7 @@
* @ns: namespace
* @params: ptr to the structure that contains key, semflg and nsems
*
- * Called with sem_ids.rw_mutex held (as a writer)
+ * Called with sem_ids.rwsem held (as a writer)
*/
static int newary(struct ipc_namespace *ns, struct ipc_params *params)
@@ -492,7 +492,7 @@
/*
- * Called with sem_ids.rw_mutex and ipcp locked.
+ * Called with sem_ids.rwsem and ipcp locked.
*/
static inline int sem_security(struct kern_ipc_perm *ipcp, int semflg)
{
@@ -503,7 +503,7 @@
}
/*
- * Called with sem_ids.rw_mutex and ipcp locked.
+ * Called with sem_ids.rwsem and ipcp locked.
*/
static inline int sem_more_checks(struct kern_ipc_perm *ipcp,
struct ipc_params *params)
@@ -994,8 +994,8 @@
return semzcnt;
}
-/* Free a semaphore set. freeary() is called with sem_ids.rw_mutex locked
- * as a writer and the spinlock for this semaphore set hold. sem_ids.rw_mutex
+/* Free a semaphore set. freeary() is called with sem_ids.rwsem locked
+ * as a writer and the spinlock for this semaphore set hold. sem_ids.rwsem
* remains locked on exit.
*/
static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
@@ -1116,7 +1116,7 @@
seminfo.semmnu = SEMMNU;
seminfo.semmap = SEMMAP;
seminfo.semume = SEMUME;
- down_read(&sem_ids(ns).rw_mutex);
+ down_read(&sem_ids(ns).rwsem);
if (cmd == SEM_INFO) {
seminfo.semusz = sem_ids(ns).in_use;
seminfo.semaem = ns->used_sems;
@@ -1125,7 +1125,7 @@
seminfo.semaem = SEMAEM;
}
max_id = ipc_get_maxid(&sem_ids(ns));
- up_read(&sem_ids(ns).rw_mutex);
+ up_read(&sem_ids(ns).rwsem);
if (copy_to_user(p, &seminfo, sizeof(struct seminfo)))
return -EFAULT;
return (max_id < 0) ? 0: max_id;
@@ -1431,9 +1431,9 @@
}
/*
- * This function handles some semctl commands which require the rw_mutex
+ * This function handles some semctl commands which require the rwsem
* to be held in write mode.
- * NOTE: no locks must be held, the rw_mutex is taken inside this function.
+ * NOTE: no locks must be held, the rwsem is taken inside this function.
*/
static int semctl_down(struct ipc_namespace *ns, int semid,
int cmd, int version, void __user *p)
@@ -1448,7 +1448,7 @@
return -EFAULT;
}
- down_write(&sem_ids(ns).rw_mutex);
+ down_write(&sem_ids(ns).rwsem);
rcu_read_lock();
ipcp = ipcctl_pre_down_nolock(ns, &sem_ids(ns), semid, cmd,
@@ -1487,7 +1487,7 @@
out_unlock1:
rcu_read_unlock();
out_up:
- up_write(&sem_ids(ns).rw_mutex);
+ up_write(&sem_ids(ns).rwsem);
return err;
}
diff --git a/ipc/shm.c b/ipc/shm.c
index c6b4ad5..2821cdf 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -19,6 +19,9 @@
* namespaces support
* OpenVZ, SWsoft Inc.
* Pavel Emelianov <xemul@openvz.org>
+ *
+ * Better ipc lock (kern_ipc_perm.lock) handling
+ * Davidlohr Bueso <davidlohr.bueso@hp.com>, June 2013.
*/
#include <linux/slab.h>
@@ -80,8 +83,8 @@
}
/*
- * Called with shm_ids.rw_mutex (writer) and the shp structure locked.
- * Only shm_ids.rw_mutex remains locked on exit.
+ * Called with shm_ids.rwsem (writer) and the shp structure locked.
+ * Only shm_ids.rwsem remains locked on exit.
*/
static void do_shm_rmid(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
{
@@ -124,8 +127,28 @@
IPC_SHM_IDS, sysvipc_shm_proc_show);
}
+static inline struct shmid_kernel *shm_obtain_object(struct ipc_namespace *ns, int id)
+{
+ struct kern_ipc_perm *ipcp = ipc_obtain_object(&shm_ids(ns), id);
+
+ if (IS_ERR(ipcp))
+ return ERR_CAST(ipcp);
+
+ return container_of(ipcp, struct shmid_kernel, shm_perm);
+}
+
+static inline struct shmid_kernel *shm_obtain_object_check(struct ipc_namespace *ns, int id)
+{
+ struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&shm_ids(ns), id);
+
+ if (IS_ERR(ipcp))
+ return ERR_CAST(ipcp);
+
+ return container_of(ipcp, struct shmid_kernel, shm_perm);
+}
+
/*
- * shm_lock_(check_) routines are called in the paths where the rw_mutex
+ * shm_lock_(check_) routines are called in the paths where the rwsem
* is not necessarily held.
*/
static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id)
@@ -144,17 +167,6 @@
ipc_lock_object(&ipcp->shm_perm);
}
-static inline struct shmid_kernel *shm_lock_check(struct ipc_namespace *ns,
- int id)
-{
- struct kern_ipc_perm *ipcp = ipc_lock_check(&shm_ids(ns), id);
-
- if (IS_ERR(ipcp))
- return (struct shmid_kernel *)ipcp;
-
- return container_of(ipcp, struct shmid_kernel, shm_perm);
-}
-
static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s)
{
ipc_rmid(&shm_ids(ns), &s->shm_perm);
@@ -182,7 +194,7 @@
* @ns: namespace
* @shp: struct to free
*
- * It has to be called with shp and shm_ids.rw_mutex (writer) locked,
+ * It has to be called with shp and shm_ids.rwsem (writer) locked,
* but returns with shp unlocked and freed.
*/
static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
@@ -230,7 +242,7 @@
struct shmid_kernel *shp;
struct ipc_namespace *ns = sfd->ns;
- down_write(&shm_ids(ns).rw_mutex);
+ down_write(&shm_ids(ns).rwsem);
/* remove from the list of attaches of the shm segment */
shp = shm_lock(ns, sfd->id);
BUG_ON(IS_ERR(shp));
@@ -241,10 +253,10 @@
shm_destroy(ns, shp);
else
shm_unlock(shp);
- up_write(&shm_ids(ns).rw_mutex);
+ up_write(&shm_ids(ns).rwsem);
}
-/* Called with ns->shm_ids(ns).rw_mutex locked */
+/* Called with ns->shm_ids(ns).rwsem locked */
static int shm_try_destroy_current(int id, void *p, void *data)
{
struct ipc_namespace *ns = data;
@@ -275,7 +287,7 @@
return 0;
}
-/* Called with ns->shm_ids(ns).rw_mutex locked */
+/* Called with ns->shm_ids(ns).rwsem locked */
static int shm_try_destroy_orphaned(int id, void *p, void *data)
{
struct ipc_namespace *ns = data;
@@ -286,7 +298,7 @@
* We want to destroy segments without users and with already
* exit'ed originating process.
*
- * As shp->* are changed under rw_mutex, it's safe to skip shp locking.
+ * As shp->* are changed under rwsem, it's safe to skip shp locking.
*/
if (shp->shm_creator != NULL)
return 0;
@@ -300,10 +312,10 @@
void shm_destroy_orphaned(struct ipc_namespace *ns)
{
- down_write(&shm_ids(ns).rw_mutex);
+ down_write(&shm_ids(ns).rwsem);
if (shm_ids(ns).in_use)
idr_for_each(&shm_ids(ns).ipcs_idr, &shm_try_destroy_orphaned, ns);
- up_write(&shm_ids(ns).rw_mutex);
+ up_write(&shm_ids(ns).rwsem);
}
@@ -315,10 +327,10 @@
return;
/* Destroy all already created segments, but not mapped yet */
- down_write(&shm_ids(ns).rw_mutex);
+ down_write(&shm_ids(ns).rwsem);
if (shm_ids(ns).in_use)
idr_for_each(&shm_ids(ns).ipcs_idr, &shm_try_destroy_current, ns);
- up_write(&shm_ids(ns).rw_mutex);
+ up_write(&shm_ids(ns).rwsem);
}
static int shm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
@@ -452,7 +464,7 @@
* @ns: namespace
* @params: ptr to the structure that contains key, size and shmflg
*
- * Called with shm_ids.rw_mutex held as a writer.
+ * Called with shm_ids.rwsem held as a writer.
*/
static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
@@ -560,7 +572,7 @@
}
/*
- * Called with shm_ids.rw_mutex and ipcp locked.
+ * Called with shm_ids.rwsem and ipcp locked.
*/
static inline int shm_security(struct kern_ipc_perm *ipcp, int shmflg)
{
@@ -571,7 +583,7 @@
}
/*
- * Called with shm_ids.rw_mutex and ipcp locked.
+ * Called with shm_ids.rwsem and ipcp locked.
*/
static inline int shm_more_checks(struct kern_ipc_perm *ipcp,
struct ipc_params *params)
@@ -684,7 +696,7 @@
/*
* Calculate and add used RSS and swap pages of a shm.
- * Called with shm_ids.rw_mutex held as a reader
+ * Called with shm_ids.rwsem held as a reader
*/
static void shm_add_rss_swap(struct shmid_kernel *shp,
unsigned long *rss_add, unsigned long *swp_add)
@@ -711,7 +723,7 @@
}
/*
- * Called with shm_ids.rw_mutex held as a reader
+ * Called with shm_ids.rwsem held as a reader
*/
static void shm_get_stat(struct ipc_namespace *ns, unsigned long *rss,
unsigned long *swp)
@@ -740,9 +752,9 @@
}
/*
- * This function handles some shmctl commands which require the rw_mutex
+ * This function handles some shmctl commands which require the rwsem
* to be held in write mode.
- * NOTE: no locks must be held, the rw_mutex is taken inside this function.
+ * NOTE: no locks must be held, the rwsem is taken inside this function.
*/
static int shmctl_down(struct ipc_namespace *ns, int shmid, int cmd,
struct shmid_ds __user *buf, int version)
@@ -757,14 +769,13 @@
return -EFAULT;
}
- down_write(&shm_ids(ns).rw_mutex);
+ down_write(&shm_ids(ns).rwsem);
rcu_read_lock();
- ipcp = ipcctl_pre_down(ns, &shm_ids(ns), shmid, cmd,
- &shmid64.shm_perm, 0);
+ ipcp = ipcctl_pre_down_nolock(ns, &shm_ids(ns), shmid, cmd,
+ &shmid64.shm_perm, 0);
if (IS_ERR(ipcp)) {
err = PTR_ERR(ipcp);
- /* the ipc lock is not held upon failure */
goto out_unlock1;
}
@@ -772,14 +783,16 @@
err = security_shm_shmctl(shp, cmd);
if (err)
- goto out_unlock0;
+ goto out_unlock1;
switch (cmd) {
case IPC_RMID:
+ ipc_lock_object(&shp->shm_perm);
/* do_shm_rmid unlocks the ipc object and rcu */
do_shm_rmid(ns, ipcp);
goto out_up;
case IPC_SET:
+ ipc_lock_object(&shp->shm_perm);
err = ipc_update_perm(&shmid64.shm_perm, ipcp);
if (err)
goto out_unlock0;
@@ -787,6 +800,7 @@
break;
default:
err = -EINVAL;
+ goto out_unlock1;
}
out_unlock0:
@@ -794,32 +808,27 @@
out_unlock1:
rcu_read_unlock();
out_up:
- up_write(&shm_ids(ns).rw_mutex);
+ up_write(&shm_ids(ns).rwsem);
return err;
}
-SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
+static int shmctl_nolock(struct ipc_namespace *ns, int shmid,
+ int cmd, int version, void __user *buf)
{
+ int err;
struct shmid_kernel *shp;
- int err, version;
- struct ipc_namespace *ns;
- if (cmd < 0 || shmid < 0) {
- err = -EINVAL;
- goto out;
- }
-
- version = ipc_parse_version(&cmd);
- ns = current->nsproxy->ipc_ns;
-
- switch (cmd) { /* replace with proc interface ? */
- case IPC_INFO:
- {
- struct shminfo64 shminfo;
-
+ /* preliminary security checks for *_INFO */
+ if (cmd == IPC_INFO || cmd == SHM_INFO) {
err = security_shm_shmctl(NULL, cmd);
if (err)
return err;
+ }
+
+ switch (cmd) {
+ case IPC_INFO:
+ {
+ struct shminfo64 shminfo;
memset(&shminfo, 0, sizeof(shminfo));
shminfo.shmmni = shminfo.shmseg = ns->shm_ctlmni;
@@ -830,9 +839,9 @@
if(copy_shminfo_to_user (buf, &shminfo, version))
return -EFAULT;
- down_read(&shm_ids(ns).rw_mutex);
+ down_read(&shm_ids(ns).rwsem);
err = ipc_get_maxid(&shm_ids(ns));
- up_read(&shm_ids(ns).rw_mutex);
+ up_read(&shm_ids(ns).rwsem);
if(err<0)
err = 0;
@@ -842,19 +851,15 @@
{
struct shm_info shm_info;
- err = security_shm_shmctl(NULL, cmd);
- if (err)
- return err;
-
memset(&shm_info, 0, sizeof(shm_info));
- down_read(&shm_ids(ns).rw_mutex);
+ down_read(&shm_ids(ns).rwsem);
shm_info.used_ids = shm_ids(ns).in_use;
shm_get_stat (ns, &shm_info.shm_rss, &shm_info.shm_swp);
shm_info.shm_tot = ns->shm_tot;
shm_info.swap_attempts = 0;
shm_info.swap_successes = 0;
err = ipc_get_maxid(&shm_ids(ns));
- up_read(&shm_ids(ns).rw_mutex);
+ up_read(&shm_ids(ns).rwsem);
if (copy_to_user(buf, &shm_info, sizeof(shm_info))) {
err = -EFAULT;
goto out;
@@ -869,27 +874,31 @@
struct shmid64_ds tbuf;
int result;
+ rcu_read_lock();
if (cmd == SHM_STAT) {
- shp = shm_lock(ns, shmid);
+ shp = shm_obtain_object(ns, shmid);
if (IS_ERR(shp)) {
err = PTR_ERR(shp);
- goto out;
+ goto out_unlock;
}
result = shp->shm_perm.id;
} else {
- shp = shm_lock_check(ns, shmid);
+ shp = shm_obtain_object_check(ns, shmid);
if (IS_ERR(shp)) {
err = PTR_ERR(shp);
- goto out;
+ goto out_unlock;
}
result = 0;
}
+
err = -EACCES;
if (ipcperms(ns, &shp->shm_perm, S_IRUGO))
goto out_unlock;
+
err = security_shm_shmctl(shp, cmd);
if (err)
goto out_unlock;
+
memset(&tbuf, 0, sizeof(tbuf));
kernel_to_ipc64_perm(&shp->shm_perm, &tbuf.shm_perm);
tbuf.shm_segsz = shp->shm_segsz;
@@ -899,43 +908,76 @@
tbuf.shm_cpid = shp->shm_cprid;
tbuf.shm_lpid = shp->shm_lprid;
tbuf.shm_nattch = shp->shm_nattch;
- shm_unlock(shp);
- if(copy_shmid_to_user (buf, &tbuf, version))
+ rcu_read_unlock();
+
+ if (copy_shmid_to_user(buf, &tbuf, version))
err = -EFAULT;
else
err = result;
goto out;
}
+ default:
+ return -EINVAL;
+ }
+
+out_unlock:
+ rcu_read_unlock();
+out:
+ return err;
+}
+
+SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
+{
+ struct shmid_kernel *shp;
+ int err, version;
+ struct ipc_namespace *ns;
+
+ if (cmd < 0 || shmid < 0)
+ return -EINVAL;
+
+ version = ipc_parse_version(&cmd);
+ ns = current->nsproxy->ipc_ns;
+
+ switch (cmd) {
+ case IPC_INFO:
+ case SHM_INFO:
+ case SHM_STAT:
+ case IPC_STAT:
+ return shmctl_nolock(ns, shmid, cmd, version, buf);
+ case IPC_RMID:
+ case IPC_SET:
+ return shmctl_down(ns, shmid, cmd, buf, version);
case SHM_LOCK:
case SHM_UNLOCK:
{
struct file *shm_file;
- shp = shm_lock_check(ns, shmid);
+ rcu_read_lock();
+ shp = shm_obtain_object_check(ns, shmid);
if (IS_ERR(shp)) {
err = PTR_ERR(shp);
- goto out;
+ goto out_unlock1;
}
audit_ipc_obj(&(shp->shm_perm));
+ err = security_shm_shmctl(shp, cmd);
+ if (err)
+ goto out_unlock1;
+ ipc_lock_object(&shp->shm_perm);
if (!ns_capable(ns->user_ns, CAP_IPC_LOCK)) {
kuid_t euid = current_euid();
err = -EPERM;
if (!uid_eq(euid, shp->shm_perm.uid) &&
!uid_eq(euid, shp->shm_perm.cuid))
- goto out_unlock;
+ goto out_unlock0;
if (cmd == SHM_LOCK && !rlimit(RLIMIT_MEMLOCK))
- goto out_unlock;
+ goto out_unlock0;
}
- err = security_shm_shmctl(shp, cmd);
- if (err)
- goto out_unlock;
-
shm_file = shp->shm_file;
if (is_file_hugepages(shm_file))
- goto out_unlock;
+ goto out_unlock0;
if (cmd == SHM_LOCK) {
struct user_struct *user = current_user();
@@ -944,32 +986,31 @@
shp->shm_perm.mode |= SHM_LOCKED;
shp->mlock_user = user;
}
- goto out_unlock;
+ goto out_unlock0;
}
/* SHM_UNLOCK */
if (!(shp->shm_perm.mode & SHM_LOCKED))
- goto out_unlock;
+ goto out_unlock0;
shmem_lock(shm_file, 0, shp->mlock_user);
shp->shm_perm.mode &= ~SHM_LOCKED;
shp->mlock_user = NULL;
get_file(shm_file);
- shm_unlock(shp);
+ ipc_unlock_object(&shp->shm_perm);
+ rcu_read_unlock();
shmem_unlock_mapping(shm_file->f_mapping);
+
fput(shm_file);
- goto out;
- }
- case IPC_RMID:
- case IPC_SET:
- err = shmctl_down(ns, shmid, cmd, buf, version);
return err;
+ }
default:
return -EINVAL;
}
-out_unlock:
- shm_unlock(shp);
-out:
+out_unlock0:
+ ipc_unlock_object(&shp->shm_perm);
+out_unlock1:
+ rcu_read_unlock();
return err;
}
@@ -1037,10 +1078,11 @@
* additional creator id...
*/
ns = current->nsproxy->ipc_ns;
- shp = shm_lock_check(ns, shmid);
+ rcu_read_lock();
+ shp = shm_obtain_object_check(ns, shmid);
if (IS_ERR(shp)) {
err = PTR_ERR(shp);
- goto out;
+ goto out_unlock;
}
err = -EACCES;
@@ -1051,24 +1093,31 @@
if (err)
goto out_unlock;
+ ipc_lock_object(&shp->shm_perm);
path = shp->shm_file->f_path;
path_get(&path);
shp->shm_nattch++;
size = i_size_read(path.dentry->d_inode);
- shm_unlock(shp);
+ ipc_unlock_object(&shp->shm_perm);
+ rcu_read_unlock();
err = -ENOMEM;
sfd = kzalloc(sizeof(*sfd), GFP_KERNEL);
- if (!sfd)
- goto out_put_dentry;
+ if (!sfd) {
+ path_put(&path);
+ goto out_nattch;
+ }
file = alloc_file(&path, f_mode,
is_file_hugepages(shp->shm_file) ?
&shm_file_operations_huge :
&shm_file_operations);
err = PTR_ERR(file);
- if (IS_ERR(file))
- goto out_free;
+ if (IS_ERR(file)) {
+ kfree(sfd);
+ path_put(&path);
+ goto out_nattch;
+ }
file->private_data = sfd;
file->f_mapping = shp->shm_file->f_mapping;
@@ -1094,7 +1143,7 @@
addr > current->mm->start_stack - size - PAGE_SIZE * 5)
goto invalid;
}
-
+
addr = do_mmap_pgoff(file, addr, size, prot, flags, 0, &populate);
*raddr = addr;
err = 0;
@@ -1109,7 +1158,7 @@
fput(file);
out_nattch:
- down_write(&shm_ids(ns).rw_mutex);
+ down_write(&shm_ids(ns).rwsem);
shp = shm_lock(ns, shmid);
BUG_ON(IS_ERR(shp));
shp->shm_nattch--;
@@ -1117,20 +1166,13 @@
shm_destroy(ns, shp);
else
shm_unlock(shp);
- up_write(&shm_ids(ns).rw_mutex);
-
-out:
+ up_write(&shm_ids(ns).rwsem);
return err;
out_unlock:
- shm_unlock(shp);
- goto out;
-
-out_free:
- kfree(sfd);
-out_put_dentry:
- path_put(&path);
- goto out_nattch;
+ rcu_read_unlock();
+out:
+ return err;
}
SYSCALL_DEFINE3(shmat, int, shmid, char __user *, shmaddr, int, shmflg)
@@ -1235,8 +1277,7 @@
#else /* CONFIG_MMU */
/* under NOMMU conditions, the exact address to be destroyed must be
* given */
- retval = -EINVAL;
- if (vma->vm_start == addr && vma->vm_ops == &shm_vm_ops) {
+ if (vma && vma->vm_start == addr && vma->vm_ops == &shm_vm_ops) {
do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start);
retval = 0;
}
diff --git a/ipc/util.c b/ipc/util.c
index 4704223..e829da9 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -15,6 +15,14 @@
* Jun 2006 - namespaces ssupport
* OpenVZ, SWsoft Inc.
* Pavel Emelianov <xemul@openvz.org>
+ *
+ * General sysv ipc locking scheme:
+ * when doing ipc id lookups, take the ids->rwsem
+ * rcu_read_lock()
+ * obtain the ipc object (kern_ipc_perm)
+ * perform security, capabilities, auditing and permission checks, etc.
+ * acquire the ipc lock (kern_ipc_perm.lock) throught ipc_lock_object()
+ * perform data updates (ie: SET, RMID, LOCK/UNLOCK commands)
*/
#include <linux/mm.h>
@@ -119,7 +127,7 @@
void ipc_init_ids(struct ipc_ids *ids)
{
- init_rwsem(&ids->rw_mutex);
+ init_rwsem(&ids->rwsem);
ids->in_use = 0;
ids->seq = 0;
@@ -174,7 +182,7 @@
* @ids: Identifier set
* @key: The key to find
*
- * Requires ipc_ids.rw_mutex locked.
+ * Requires ipc_ids.rwsem locked.
* Returns the LOCKED pointer to the ipc structure if found or NULL
* if not.
* If key is found ipc points to the owning ipc structure
@@ -197,7 +205,8 @@
continue;
}
- ipc_lock_by_ptr(ipc);
+ rcu_read_lock();
+ ipc_lock_object(ipc);
return ipc;
}
@@ -208,7 +217,7 @@
* ipc_get_maxid - get the last assigned id
* @ids: IPC identifier set
*
- * Called with ipc_ids.rw_mutex held.
+ * Called with ipc_ids.rwsem held.
*/
int ipc_get_maxid(struct ipc_ids *ids)
@@ -246,7 +255,7 @@
* is returned. The 'new' entry is returned in a locked state on success.
* On failure the entry is not locked and a negative err-code is returned.
*
- * Called with writer ipc_ids.rw_mutex held.
+ * Called with writer ipc_ids.rwsem held.
*/
int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size)
{
@@ -312,9 +321,9 @@
{
int err;
- down_write(&ids->rw_mutex);
+ down_write(&ids->rwsem);
err = ops->getnew(ns, params);
- up_write(&ids->rw_mutex);
+ up_write(&ids->rwsem);
return err;
}
@@ -331,7 +340,7 @@
*
* On success, the IPC id is returned.
*
- * It is called with ipc_ids.rw_mutex and ipcp->lock held.
+ * It is called with ipc_ids.rwsem and ipcp->lock held.
*/
static int ipc_check_perms(struct ipc_namespace *ns,
struct kern_ipc_perm *ipcp,
@@ -376,7 +385,7 @@
* Take the lock as a writer since we are potentially going to add
* a new entry + read locks are not "upgradable"
*/
- down_write(&ids->rw_mutex);
+ down_write(&ids->rwsem);
ipcp = ipc_findkey(ids, params->key);
if (ipcp == NULL) {
/* key not used */
@@ -402,7 +411,7 @@
}
ipc_unlock(ipcp);
}
- up_write(&ids->rw_mutex);
+ up_write(&ids->rwsem);
return err;
}
@@ -413,7 +422,7 @@
* @ids: IPC identifier set
* @ipcp: ipc perm structure containing the identifier to remove
*
- * ipc_ids.rw_mutex (as a writer) and the spinlock for this ID are held
+ * ipc_ids.rwsem (as a writer) and the spinlock for this ID are held
* before this function is called, and remain locked on the exit.
*/
@@ -621,7 +630,7 @@
}
/**
- * ipc_lock - Lock an ipc structure without rw_mutex held
+ * ipc_lock - Lock an ipc structure without rwsem held
* @ids: IPC identifier set
* @id: ipc id to look for
*
@@ -677,22 +686,6 @@
return out;
}
-struct kern_ipc_perm *ipc_lock_check(struct ipc_ids *ids, int id)
-{
- struct kern_ipc_perm *out;
-
- out = ipc_lock(ids, id);
- if (IS_ERR(out))
- return out;
-
- if (ipc_checkid(out, id)) {
- ipc_unlock(out);
- return ERR_PTR(-EIDRM);
- }
-
- return out;
-}
-
/**
* ipcget - Common sys_*get() code
* @ns : namsepace
@@ -733,7 +726,7 @@
}
/**
- * ipcctl_pre_down - retrieve an ipc and check permissions for some IPC_XXX cmd
+ * ipcctl_pre_down_nolock - retrieve an ipc and check permissions for some IPC_XXX cmd
* @ns: the ipc namespace
* @ids: the table of ids where to look for the ipc
* @id: the id of the ipc to retrieve
@@ -746,29 +739,13 @@
* It must be called without any lock held and
* - retrieves the ipc with the given id in the given table.
* - performs some audit and permission check, depending on the given cmd
- * - returns the ipc with the ipc lock held in case of success
- * or an err-code without any lock held otherwise.
+ * - returns a pointer to the ipc object or otherwise, the corresponding error.
*
- * Call holding the both the rw_mutex and the rcu read lock.
+ * Call holding the both the rwsem and the rcu read lock.
*/
-struct kern_ipc_perm *ipcctl_pre_down(struct ipc_namespace *ns,
- struct ipc_ids *ids, int id, int cmd,
- struct ipc64_perm *perm, int extra_perm)
-{
- struct kern_ipc_perm *ipcp;
-
- ipcp = ipcctl_pre_down_nolock(ns, ids, id, cmd, perm, extra_perm);
- if (IS_ERR(ipcp))
- goto out;
-
- spin_lock(&ipcp->lock);
-out:
- return ipcp;
-}
-
struct kern_ipc_perm *ipcctl_pre_down_nolock(struct ipc_namespace *ns,
- struct ipc_ids *ids, int id, int cmd,
- struct ipc64_perm *perm, int extra_perm)
+ struct ipc_ids *ids, int id, int cmd,
+ struct ipc64_perm *perm, int extra_perm)
{
kuid_t euid;
int err = -EPERM;
@@ -846,7 +823,8 @@
ipc = idr_find(&ids->ipcs_idr, pos);
if (ipc != NULL) {
*new_pos = pos + 1;
- ipc_lock_by_ptr(ipc);
+ rcu_read_lock();
+ ipc_lock_object(ipc);
return ipc;
}
}
@@ -884,7 +862,7 @@
* Take the lock - this will be released by the corresponding
* call to stop().
*/
- down_read(&ids->rw_mutex);
+ down_read(&ids->rwsem);
/* pos < 0 is invalid */
if (*pos < 0)
@@ -911,7 +889,7 @@
ids = &iter->ns->ids[iface->ids];
/* Release the lock we took in start() */
- up_read(&ids->rw_mutex);
+ up_read(&ids->rwsem);
}
static int sysvipc_proc_show(struct seq_file *s, void *it)
diff --git a/ipc/util.h b/ipc/util.h
index b6a6a88..c5f3338b 100644
--- a/ipc/util.h
+++ b/ipc/util.h
@@ -94,10 +94,10 @@
#define ipcid_to_idx(id) ((id) % SEQ_MULTIPLIER)
#define ipcid_to_seqx(id) ((id) / SEQ_MULTIPLIER)
-/* must be called with ids->rw_mutex acquired for writing */
+/* must be called with ids->rwsem acquired for writing */
int ipc_addid(struct ipc_ids *, struct kern_ipc_perm *, int);
-/* must be called with ids->rw_mutex acquired for reading */
+/* must be called with ids->rwsem acquired for reading */
int ipc_get_maxid(struct ipc_ids *);
/* must be called with both locks acquired. */
@@ -131,9 +131,6 @@
struct kern_ipc_perm *ipcctl_pre_down_nolock(struct ipc_namespace *ns,
struct ipc_ids *ids, int id, int cmd,
struct ipc64_perm *perm, int extra_perm);
-struct kern_ipc_perm *ipcctl_pre_down(struct ipc_namespace *ns,
- struct ipc_ids *ids, int id, int cmd,
- struct ipc64_perm *perm, int extra_perm);
#ifndef CONFIG_ARCH_WANT_IPC_PARSE_VERSION
/* On IA-64, we always use the "64-bit version" of the IPC structures. */
@@ -174,19 +171,12 @@
assert_spin_locked(&perm->lock);
}
-static inline void ipc_lock_by_ptr(struct kern_ipc_perm *perm)
-{
- rcu_read_lock();
- ipc_lock_object(perm);
-}
-
static inline void ipc_unlock(struct kern_ipc_perm *perm)
{
ipc_unlock_object(perm);
rcu_read_unlock();
}
-struct kern_ipc_perm *ipc_lock_check(struct ipc_ids *ids, int id);
struct kern_ipc_perm *ipc_obtain_object_check(struct ipc_ids *ids, int id);
int ipcget(struct ipc_namespace *ns, struct ipc_ids *ids,
struct ipc_ops *ops, struct ipc_params *params);
diff --git a/kernel/Makefile b/kernel/Makefile
index 35ef118..1ce4755 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -26,6 +26,7 @@
obj-y += power/
obj-y += printk/
obj-y += cpu/
+obj-y += irq/
obj-$(CONFIG_CHECKPOINT_RESTORE) += kcmp.o
obj-$(CONFIG_FREEZER) += freezer.o
@@ -79,7 +80,6 @@
obj-$(CONFIG_KGDB) += debug/
obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o
obj-$(CONFIG_LOCKUP_DETECTOR) += watchdog.o
-obj-$(CONFIG_GENERIC_HARDIRQS) += irq/
obj-$(CONFIG_SECCOMP) += seccomp.o
obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
obj-$(CONFIG_TREE_RCU) += rcutree.o
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 2207efc..dd236b6 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5039,6 +5039,7 @@
mmap_event->event_id.header.size += sizeof(mmap_event->maj);
mmap_event->event_id.header.size += sizeof(mmap_event->min);
mmap_event->event_id.header.size += sizeof(mmap_event->ino);
+ mmap_event->event_id.header.size += sizeof(mmap_event->ino_generation);
}
perf_event_header__init_id(&mmap_event->event_id.header, &sample, event);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index f356974..ad8e1bd 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1682,12 +1682,10 @@
tmp = ri;
ri = ri->next;
kfree(tmp);
+ utask->depth--;
if (!chained)
break;
-
- utask->depth--;
-
BUG_ON(!ri);
}
diff --git a/kernel/extable.c b/kernel/extable.c
index 67460b9..832cb28 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -41,7 +41,7 @@
/* Sort the kernel's built-in exception table */
void __init sort_main_extable(void)
{
- if (main_extable_sort_needed) {
+ if (main_extable_sort_needed && __stop___ex_table > __start___ex_table) {
pr_notice("Sorting __ex_table...\n");
sort_extable(__start___ex_table, __stop___ex_table);
}
diff --git a/kernel/fork.c b/kernel/fork.c
index c9eaf201..086fe73 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -351,7 +351,6 @@
struct rb_node **rb_link, *rb_parent;
int retval;
unsigned long charge;
- struct mempolicy *pol;
uprobe_start_dup_mmap();
down_write(&oldmm->mmap_sem);
@@ -400,11 +399,9 @@
goto fail_nomem;
*tmp = *mpnt;
INIT_LIST_HEAD(&tmp->anon_vma_chain);
- pol = mpol_dup(vma_policy(mpnt));
- retval = PTR_ERR(pol);
- if (IS_ERR(pol))
+ retval = vma_dup_policy(mpnt, tmp);
+ if (retval)
goto fail_nomem_policy;
- vma_set_policy(tmp, pol);
tmp->vm_mm = mm;
if (anon_vma_fork(tmp, mpnt))
goto fail_nomem_anon_vma_fork;
@@ -472,7 +469,7 @@
uprobe_end_dup_mmap();
return retval;
fail_nomem_anon_vma_fork:
- mpol_put(pol);
+ mpol_put(vma_policy(tmp));
fail_nomem_policy:
kmem_cache_free(vm_area_cachep, tmp);
fail_nomem:
@@ -522,7 +519,7 @@
{
#ifdef CONFIG_AIO
spin_lock_init(&mm->ioctx_lock);
- INIT_HLIST_HEAD(&mm->ioctx_list);
+ mm->ioctx_table = NULL;
#endif
}
@@ -1173,13 +1170,16 @@
return ERR_PTR(-EINVAL);
/*
- * If the new process will be in a different pid namespace
- * don't allow the creation of threads.
+ * If the new process will be in a different pid or user namespace
+ * do not allow it to share a thread group or signal handlers or
+ * parent with the forking task.
*/
- if ((clone_flags & (CLONE_VM|CLONE_NEWPID)) &&
- (task_active_pid_ns(current) !=
- current->nsproxy->pid_ns_for_children))
- return ERR_PTR(-EINVAL);
+ if (clone_flags & (CLONE_SIGHAND | CLONE_PARENT)) {
+ if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) ||
+ (task_active_pid_ns(current) !=
+ current->nsproxy->pid_ns_for_children))
+ return ERR_PTR(-EINVAL);
+ }
retval = security_task_create(clone_flags);
if (retval)
@@ -1576,15 +1576,6 @@
long nr;
/*
- * Do some preliminary argument and permissions checking before we
- * actually start allocating stuff
- */
- if (clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) {
- if (clone_flags & (CLONE_THREAD|CLONE_PARENT))
- return -EINVAL;
- }
-
- /*
* Determine whether and which event to report to ptracer. When
* called from kernel_thread or CLONE_UNTRACED is explicitly
* requested, no event is reported; otherwise, report if the event
diff --git a/kernel/gcov/fs.c b/kernel/gcov/fs.c
index 9bd0934..7a7d2ee 100644
--- a/kernel/gcov/fs.c
+++ b/kernel/gcov/fs.c
@@ -74,7 +74,7 @@
{
unsigned long val;
- if (strict_strtoul(str, 0, &val)) {
+ if (kstrtoul(str, 0, &val)) {
pr_warning("invalid gcov_persist parameter '%s'\n", str);
return 0;
}
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index d1a758b..4a1fef0 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -1,15 +1,4 @@
-# Select this to activate the generic irq options below
-config HAVE_GENERIC_HARDIRQS
- bool
-
-if HAVE_GENERIC_HARDIRQS
menu "IRQ subsystem"
-#
-# Interrupt subsystem related configuration options
-#
-config GENERIC_HARDIRQS
- def_bool y
-
# Options selectable by the architecture code
# Make sparse irq Kconfig switch below available
@@ -84,4 +73,3 @@
If you don't know what to do here, say N.
endmenu
-endif
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 59f7b55..2a74f30 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1474,11 +1474,8 @@
if (first_colon && (!first_space || first_colon < first_space))
return parse_crashkernel_mem(ck_cmdline, system_ram,
crash_size, crash_base);
- else
- return parse_crashkernel_simple(ck_cmdline, crash_size,
- crash_base);
- return 0;
+ return parse_crashkernel_simple(ck_cmdline, crash_size, crash_base);
}
/*
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 6e33498..a0d367a 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -112,6 +112,7 @@
struct kprobe_insn_page {
struct list_head list;
kprobe_opcode_t *insns; /* Page of instruction slots */
+ struct kprobe_insn_cache *cache;
int nused;
int ngarbage;
char slot_used[];
@@ -121,12 +122,6 @@
(offsetof(struct kprobe_insn_page, slot_used) + \
(sizeof(char) * (slots)))
-struct kprobe_insn_cache {
- struct list_head pages; /* list of kprobe_insn_page */
- size_t insn_size; /* size of instruction slot */
- int nr_garbage;
-};
-
static int slots_per_page(struct kprobe_insn_cache *c)
{
return PAGE_SIZE/(c->insn_size * sizeof(kprobe_opcode_t));
@@ -138,8 +133,20 @@
SLOT_USED = 2,
};
-static DEFINE_MUTEX(kprobe_insn_mutex); /* Protects kprobe_insn_slots */
-static struct kprobe_insn_cache kprobe_insn_slots = {
+static void *alloc_insn_page(void)
+{
+ return module_alloc(PAGE_SIZE);
+}
+
+static void free_insn_page(void *page)
+{
+ module_free(NULL, page);
+}
+
+struct kprobe_insn_cache kprobe_insn_slots = {
+ .mutex = __MUTEX_INITIALIZER(kprobe_insn_slots.mutex),
+ .alloc = alloc_insn_page,
+ .free = free_insn_page,
.pages = LIST_HEAD_INIT(kprobe_insn_slots.pages),
.insn_size = MAX_INSN_SIZE,
.nr_garbage = 0,
@@ -150,10 +157,12 @@
* __get_insn_slot() - Find a slot on an executable page for an instruction.
* We allocate an executable page if there's no room on existing ones.
*/
-static kprobe_opcode_t __kprobes *__get_insn_slot(struct kprobe_insn_cache *c)
+kprobe_opcode_t __kprobes *__get_insn_slot(struct kprobe_insn_cache *c)
{
struct kprobe_insn_page *kip;
+ kprobe_opcode_t *slot = NULL;
+ mutex_lock(&c->mutex);
retry:
list_for_each_entry(kip, &c->pages, list) {
if (kip->nused < slots_per_page(c)) {
@@ -162,7 +171,8 @@
if (kip->slot_used[i] == SLOT_CLEAN) {
kip->slot_used[i] = SLOT_USED;
kip->nused++;
- return kip->insns + (i * c->insn_size);
+ slot = kip->insns + (i * c->insn_size);
+ goto out;
}
}
/* kip->nused is broken. Fix it. */
@@ -178,37 +188,29 @@
/* All out of space. Need to allocate a new page. */
kip = kmalloc(KPROBE_INSN_PAGE_SIZE(slots_per_page(c)), GFP_KERNEL);
if (!kip)
- return NULL;
+ goto out;
/*
* Use module_alloc so this page is within +/- 2GB of where the
* kernel image and loaded module images reside. This is required
* so x86_64 can correctly handle the %rip-relative fixups.
*/
- kip->insns = module_alloc(PAGE_SIZE);
+ kip->insns = c->alloc();
if (!kip->insns) {
kfree(kip);
- return NULL;
+ goto out;
}
INIT_LIST_HEAD(&kip->list);
memset(kip->slot_used, SLOT_CLEAN, slots_per_page(c));
kip->slot_used[0] = SLOT_USED;
kip->nused = 1;
kip->ngarbage = 0;
+ kip->cache = c;
list_add(&kip->list, &c->pages);
- return kip->insns;
-}
-
-
-kprobe_opcode_t __kprobes *get_insn_slot(void)
-{
- kprobe_opcode_t *ret = NULL;
-
- mutex_lock(&kprobe_insn_mutex);
- ret = __get_insn_slot(&kprobe_insn_slots);
- mutex_unlock(&kprobe_insn_mutex);
-
- return ret;
+ slot = kip->insns;
+out:
+ mutex_unlock(&c->mutex);
+ return slot;
}
/* Return 1 if all garbages are collected, otherwise 0. */
@@ -225,7 +227,7 @@
*/
if (!list_is_singular(&kip->list)) {
list_del(&kip->list);
- module_free(NULL, kip->insns);
+ kip->cache->free(kip->insns);
kfree(kip);
}
return 1;
@@ -255,11 +257,12 @@
return 0;
}
-static void __kprobes __free_insn_slot(struct kprobe_insn_cache *c,
- kprobe_opcode_t *slot, int dirty)
+void __kprobes __free_insn_slot(struct kprobe_insn_cache *c,
+ kprobe_opcode_t *slot, int dirty)
{
struct kprobe_insn_page *kip;
+ mutex_lock(&c->mutex);
list_for_each_entry(kip, &c->pages, list) {
long idx = ((long)slot - (long)kip->insns) /
(c->insn_size * sizeof(kprobe_opcode_t));
@@ -272,45 +275,25 @@
collect_garbage_slots(c);
} else
collect_one_slot(kip, idx);
- return;
+ goto out;
}
}
/* Could not free this slot. */
WARN_ON(1);
+out:
+ mutex_unlock(&c->mutex);
}
-void __kprobes free_insn_slot(kprobe_opcode_t * slot, int dirty)
-{
- mutex_lock(&kprobe_insn_mutex);
- __free_insn_slot(&kprobe_insn_slots, slot, dirty);
- mutex_unlock(&kprobe_insn_mutex);
-}
#ifdef CONFIG_OPTPROBES
/* For optimized_kprobe buffer */
-static DEFINE_MUTEX(kprobe_optinsn_mutex); /* Protects kprobe_optinsn_slots */
-static struct kprobe_insn_cache kprobe_optinsn_slots = {
+struct kprobe_insn_cache kprobe_optinsn_slots = {
+ .mutex = __MUTEX_INITIALIZER(kprobe_optinsn_slots.mutex),
+ .alloc = alloc_insn_page,
+ .free = free_insn_page,
.pages = LIST_HEAD_INIT(kprobe_optinsn_slots.pages),
/* .insn_size is initialized later */
.nr_garbage = 0,
};
-/* Get a slot for optimized_kprobe buffer */
-kprobe_opcode_t __kprobes *get_optinsn_slot(void)
-{
- kprobe_opcode_t *ret = NULL;
-
- mutex_lock(&kprobe_optinsn_mutex);
- ret = __get_insn_slot(&kprobe_optinsn_slots);
- mutex_unlock(&kprobe_optinsn_mutex);
-
- return ret;
-}
-
-void __kprobes free_optinsn_slot(kprobe_opcode_t * slot, int dirty)
-{
- mutex_lock(&kprobe_optinsn_mutex);
- __free_insn_slot(&kprobe_optinsn_slots, slot, dirty);
- mutex_unlock(&kprobe_optinsn_mutex);
-}
#endif
#endif
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index 6ada93c..9659d38 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -113,7 +113,7 @@
unsigned long cnt;
int ret;
- if (strict_strtoul(buf, 0, &cnt))
+ if (kstrtoul(buf, 0, &cnt))
return -EINVAL;
ret = crash_shrink_memory(cnt);
diff --git a/kernel/modsign_pubkey.c b/kernel/modsign_pubkey.c
index 2b6e699..7cbd450 100644
--- a/kernel/modsign_pubkey.c
+++ b/kernel/modsign_pubkey.c
@@ -18,14 +18,14 @@
struct key *modsign_keyring;
-extern __initdata const u8 modsign_certificate_list[];
-extern __initdata const u8 modsign_certificate_list_end[];
+extern __initconst const u8 modsign_certificate_list[];
+extern __initconst const u8 modsign_certificate_list_end[];
/*
* We need to make sure ccache doesn't cache the .o file as it doesn't notice
* if modsign.pub changes.
*/
-static __initdata const char annoy_ccache[] = __TIME__ "foo";
+static __initconst const char annoy_ccache[] = __TIME__ "foo";
/*
* Load the compiled-in keys
diff --git a/kernel/panic.c b/kernel/panic.c
index 8018646..b6c482c 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -123,10 +123,14 @@
*/
smp_send_stop();
- kmsg_dump(KMSG_DUMP_PANIC);
-
+ /*
+ * Run any panic handlers, including those that might need to
+ * add information to the kmsg dump output.
+ */
atomic_notifier_call_chain(&panic_notifier_list, 0, buf);
+ kmsg_dump(KMSG_DUMP_PANIC);
+
bust_spinlocks(0);
if (!panic_blink)
diff --git a/kernel/params.c b/kernel/params.c
index 501bde4..81c4e78 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -253,13 +253,13 @@
EXPORT_SYMBOL(param_ops_##name)
-STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", unsigned long, strict_strtoul);
-STANDARD_PARAM_DEF(short, short, "%hi", long, strict_strtol);
-STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", unsigned long, strict_strtoul);
-STANDARD_PARAM_DEF(int, int, "%i", long, strict_strtol);
-STANDARD_PARAM_DEF(uint, unsigned int, "%u", unsigned long, strict_strtoul);
-STANDARD_PARAM_DEF(long, long, "%li", long, strict_strtol);
-STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", unsigned long, strict_strtoul);
+STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", unsigned long, kstrtoul);
+STANDARD_PARAM_DEF(short, short, "%hi", long, kstrtoul);
+STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", unsigned long, kstrtoul);
+STANDARD_PARAM_DEF(int, int, "%i", long, kstrtoul);
+STANDARD_PARAM_DEF(uint, unsigned int, "%u", unsigned long, kstrtoul);
+STANDARD_PARAM_DEF(long, long, "%li", long, kstrtoul);
+STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", unsigned long, kstrtoul);
int param_set_charp(const char *val, const struct kernel_param *kp)
{
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 3085e62..c9c759d 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -644,22 +644,23 @@
if (error)
goto Exit;
- /* Allocate memory management structures */
- error = create_basic_memory_bitmaps();
- if (error)
- goto Exit;
-
printk(KERN_INFO "PM: Syncing filesystems ... ");
sys_sync();
printk("done.\n");
error = freeze_processes();
if (error)
- goto Free_bitmaps;
+ goto Exit;
+
+ lock_device_hotplug();
+ /* Allocate memory management structures */
+ error = create_basic_memory_bitmaps();
+ if (error)
+ goto Thaw;
error = hibernation_snapshot(hibernation_mode == HIBERNATION_PLATFORM);
if (error || freezer_test_done)
- goto Thaw;
+ goto Free_bitmaps;
if (in_suspend) {
unsigned int flags = 0;
@@ -682,14 +683,14 @@
pr_debug("PM: Image restored successfully.\n");
}
+ Free_bitmaps:
+ free_basic_memory_bitmaps();
Thaw:
+ unlock_device_hotplug();
thaw_processes();
/* Don't bother checking whether freezer_test_done is true */
freezer_test_done = false;
-
- Free_bitmaps:
- free_basic_memory_bitmaps();
Exit:
pm_notifier_call_chain(PM_POST_HIBERNATION);
pm_restore_console();
@@ -806,21 +807,20 @@
pm_prepare_console();
error = pm_notifier_call_chain(PM_RESTORE_PREPARE);
if (error)
- goto close_finish;
-
- error = create_basic_memory_bitmaps();
- if (error)
- goto close_finish;
+ goto Close_Finish;
pr_debug("PM: Preparing processes for restore.\n");
error = freeze_processes();
- if (error) {
- swsusp_close(FMODE_READ);
- goto Done;
- }
+ if (error)
+ goto Close_Finish;
pr_debug("PM: Loading hibernation image.\n");
+ lock_device_hotplug();
+ error = create_basic_memory_bitmaps();
+ if (error)
+ goto Thaw;
+
error = swsusp_read(&flags);
swsusp_close(FMODE_READ);
if (!error)
@@ -828,9 +828,10 @@
printk(KERN_ERR "PM: Failed to load hibernation image, recovering.\n");
swsusp_free();
- thaw_processes();
- Done:
free_basic_memory_bitmaps();
+ Thaw:
+ unlock_device_hotplug();
+ thaw_processes();
Finish:
pm_notifier_call_chain(PM_POST_RESTORE);
pm_restore_console();
@@ -840,7 +841,7 @@
mutex_unlock(&pm_mutex);
pr_debug("PM: Hibernation image not present or could not be loaded.\n");
return error;
-close_finish:
+ Close_Finish:
swsusp_close(FMODE_READ);
goto Finish;
}
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 349587b..358a146 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -352,7 +352,7 @@
struct mem_extent *ext, *cur, *aux;
zone_start = zone->zone_start_pfn;
- zone_end = zone->zone_start_pfn + zone->spanned_pages;
+ zone_end = zone_end_pfn(zone);
list_for_each_entry(ext, list, hook)
if (zone_start <= ext->end)
@@ -884,7 +884,7 @@
continue;
mark_free_pages(zone);
- max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
+ max_zone_pfn = zone_end_pfn(zone);
for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
if (saveable_highmem_page(zone, pfn))
n++;
@@ -948,7 +948,7 @@
continue;
mark_free_pages(zone);
- max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
+ max_zone_pfn = zone_end_pfn(zone);
for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
if (saveable_page(zone, pfn))
n++;
@@ -1041,7 +1041,7 @@
unsigned long max_zone_pfn;
mark_free_pages(zone);
- max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
+ max_zone_pfn = zone_end_pfn(zone);
for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
if (page_is_saveable(zone, pfn))
memory_bm_set_bit(orig_bm, pfn);
@@ -1093,7 +1093,7 @@
unsigned long pfn, max_zone_pfn;
for_each_populated_zone(zone) {
- max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
+ max_zone_pfn = zone_end_pfn(zone);
for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
if (pfn_valid(pfn)) {
struct page *page = pfn_to_page(pfn);
@@ -1755,7 +1755,7 @@
/* Clear page flags */
for_each_populated_zone(zone) {
- max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
+ max_zone_pfn = zone_end_pfn(zone);
for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
if (pfn_valid(pfn))
swsusp_unset_page_free(pfn_to_page(pfn));
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 4ed81e7..72e8f4f 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -60,11 +60,6 @@
error = -ENOSYS;
goto Unlock;
}
- if(create_basic_memory_bitmaps()) {
- atomic_inc(&snapshot_device_available);
- error = -ENOMEM;
- goto Unlock;
- }
nonseekable_open(inode, filp);
data = &snapshot_state;
filp->private_data = data;
@@ -90,10 +85,9 @@
if (error)
pm_notifier_call_chain(PM_POST_RESTORE);
}
- if (error) {
- free_basic_memory_bitmaps();
+ if (error)
atomic_inc(&snapshot_device_available);
- }
+
data->frozen = 0;
data->ready = 0;
data->platform_support = 0;
@@ -111,11 +105,11 @@
lock_system_sleep();
swsusp_free();
- free_basic_memory_bitmaps();
data = filp->private_data;
free_all_swap_pages(data->swap);
if (data->frozen) {
pm_restore_gfp_mask();
+ free_basic_memory_bitmaps();
thaw_processes();
}
pm_notifier_call_chain(data->mode == O_RDONLY ?
@@ -207,6 +201,7 @@
if (!mutex_trylock(&pm_mutex))
return -EBUSY;
+ lock_device_hotplug();
data = filp->private_data;
switch (cmd) {
@@ -220,14 +215,22 @@
printk("done.\n");
error = freeze_processes();
- if (!error)
+ if (error)
+ break;
+
+ error = create_basic_memory_bitmaps();
+ if (error)
+ thaw_processes();
+ else
data->frozen = 1;
+
break;
case SNAPSHOT_UNFREEZE:
if (!data->frozen || data->ready)
break;
pm_restore_gfp_mask();
+ free_basic_memory_bitmaps();
thaw_processes();
data->frozen = 0;
break;
@@ -371,6 +374,7 @@
}
+ unlock_device_hotplug();
mutex_unlock(&pm_mutex);
return error;
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index a146ee3..dd562e9 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -236,7 +236,7 @@
*/
int dumpable = 0;
/* Don't let security modules deny introspection */
- if (task == current)
+ if (same_thread_group(task, current))
return 0;
rcu_read_lock();
tcred = __task_cred(task);
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
index ff55247..4aa8a30 100644
--- a/kernel/res_counter.c
+++ b/kernel/res_counter.c
@@ -17,8 +17,8 @@
void res_counter_init(struct res_counter *counter, struct res_counter *parent)
{
spin_lock_init(&counter->lock);
- counter->limit = RESOURCE_MAX;
- counter->soft_limit = RESOURCE_MAX;
+ counter->limit = RES_COUNTER_MAX;
+ counter->soft_limit = RES_COUNTER_MAX;
counter->parent = parent;
}
@@ -178,23 +178,30 @@
#endif
int res_counter_memparse_write_strategy(const char *buf,
- unsigned long long *res)
+ unsigned long long *resp)
{
char *end;
+ unsigned long long res;
- /* return RESOURCE_MAX(unlimited) if "-1" is specified */
+ /* return RES_COUNTER_MAX(unlimited) if "-1" is specified */
if (*buf == '-') {
- *res = simple_strtoull(buf + 1, &end, 10);
- if (*res != 1 || *end != '\0')
+ res = simple_strtoull(buf + 1, &end, 10);
+ if (res != 1 || *end != '\0')
return -EINVAL;
- *res = RESOURCE_MAX;
+ *resp = RES_COUNTER_MAX;
return 0;
}
- *res = memparse(buf, &end);
+ res = memparse(buf, &end);
if (*end != '\0')
return -EINVAL;
- *res = PAGE_ALIGN(*res);
+ if (PAGE_ALIGN(res) >= res)
+ res = PAGE_ALIGN(res);
+ else
+ res = RES_COUNTER_MAX;
+
+ *resp = res;
+
return 0;
}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7f0a5e6..9b3fe1c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5151,7 +5151,7 @@
* First idle cpu or the first cpu(busiest) in this sched group
* is eligible for doing load balancing at this and above domains.
*/
- return balance_cpu != env->dst_cpu;
+ return balance_cpu == env->dst_cpu;
}
/*
diff --git a/kernel/signal.c b/kernel/signal.c
index 50e4107..ded28b9 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -3394,7 +3394,7 @@
new_ka.sa.sa_restorer = compat_ptr(restorer);
#endif
ret |= copy_from_user(&mask, &act->sa_mask, sizeof(mask));
- ret |= __get_user(new_ka.sa.sa_flags, &act->sa_flags);
+ ret |= get_user(new_ka.sa.sa_flags, &act->sa_flags);
if (ret)
return -EFAULT;
sigset_from_compat(&new_ka.sa.sa_mask, &mask);
@@ -3406,7 +3406,7 @@
ret = put_user(ptr_to_compat(old_ka.sa.sa_handler),
&oact->sa_handler);
ret |= copy_to_user(&oact->sa_mask, &mask, sizeof(mask));
- ret |= __put_user(old_ka.sa.sa_flags, &oact->sa_flags);
+ ret |= put_user(old_ka.sa.sa_flags, &oact->sa_flags);
#ifdef __ARCH_HAS_SA_RESTORER
ret |= put_user(ptr_to_compat(old_ka.sa.sa_restorer),
&oact->sa_restorer);
diff --git a/kernel/smp.c b/kernel/smp.c
index 449b707..0564571 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -48,10 +48,13 @@
cpu_to_node(cpu)))
return notifier_from_errno(-ENOMEM);
if (!zalloc_cpumask_var_node(&cfd->cpumask_ipi, GFP_KERNEL,
- cpu_to_node(cpu)))
+ cpu_to_node(cpu))) {
+ free_cpumask_var(cfd->cpumask);
return notifier_from_errno(-ENOMEM);
+ }
cfd->csd = alloc_percpu(struct call_single_data);
if (!cfd->csd) {
+ free_cpumask_var(cfd->cpumask_ipi);
free_cpumask_var(cfd->cpumask);
return notifier_from_errno(-ENOMEM);
}
@@ -572,8 +575,10 @@
*
* If @wait is true, then returns once @func has returned.
*
- * You must not call this function with disabled interrupts or
- * from a hardware interrupt handler or from a bottom half handler.
+ * You must not call this function with disabled interrupts or from a
+ * hardware interrupt handler or from a bottom half handler. The
+ * exception is that it may be used during early boot while
+ * early_boot_irqs_disabled is set.
*/
void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func,
void *info, bool wait)
@@ -582,9 +587,10 @@
smp_call_function_many(mask, func, info, wait);
if (cpumask_test_cpu(cpu, mask)) {
- local_irq_disable();
+ unsigned long flags;
+ local_irq_save(flags);
func(info);
- local_irq_enable();
+ local_irq_restore(flags);
}
put_cpu();
}
diff --git a/kernel/softirq.c b/kernel/softirq.c
index be3d351..53cc09c 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -876,7 +876,6 @@
return 0;
}
-#ifdef CONFIG_GENERIC_HARDIRQS
int __init __weak arch_probe_nr_irqs(void)
{
return NR_IRQS_LEGACY;
@@ -886,4 +885,3 @@
{
return 0;
}
-#endif
diff --git a/kernel/spinlock.c b/kernel/spinlock.c
index 5cdd806..4b082b5 100644
--- a/kernel/spinlock.c
+++ b/kernel/spinlock.c
@@ -34,6 +34,20 @@
#else
#define raw_read_can_lock(l) read_can_lock(l)
#define raw_write_can_lock(l) write_can_lock(l)
+
+/*
+ * Some architectures can relax in favour of the CPU owning the lock.
+ */
+#ifndef arch_read_relax
+# define arch_read_relax(l) cpu_relax()
+#endif
+#ifndef arch_write_relax
+# define arch_write_relax(l) cpu_relax()
+#endif
+#ifndef arch_spin_relax
+# define arch_spin_relax(l) cpu_relax()
+#endif
+
/*
* We build the __lock_function inlines here. They are too large for
* inlining all over the place, but here is only one user per function
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 07f6fc4..b2f06f3 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1225,7 +1225,7 @@
.data = &hugepages_treat_as_movable,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = hugetlb_treat_movable_handler,
+ .proc_handler = proc_dointvec,
},
{
.procname = "nr_overcommit_hugepages",
@@ -1471,14 +1471,14 @@
{
.procname = "inode-nr",
.data = &inodes_stat,
- .maxlen = 2*sizeof(int),
+ .maxlen = 2*sizeof(long),
.mode = 0444,
.proc_handler = proc_nr_inodes,
},
{
.procname = "inode-state",
.data = &inodes_stat,
- .maxlen = 7*sizeof(int),
+ .maxlen = 7*sizeof(long),
.mode = 0444,
.proc_handler = proc_nr_inodes,
},
@@ -1508,7 +1508,7 @@
{
.procname = "dentry-state",
.data = &dentry_stat,
- .maxlen = 6*sizeof(int),
+ .maxlen = 6*sizeof(long),
.mode = 0444,
.proc_handler = proc_nr_dentry,
},
diff --git a/kernel/task_work.c b/kernel/task_work.c
index 65bd3c9..8727032 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -4,6 +4,23 @@
static struct callback_head work_exited; /* all we need is ->next == NULL */
+/**
+ * task_work_add - ask the @task to execute @work->func()
+ * @task: the task which should run the callback
+ * @work: the callback to run
+ * @notify: send the notification if true
+ *
+ * Queue @work for task_work_run() below and notify the @task if @notify.
+ * Fails if the @task is exiting/exited and thus it can't process this @work.
+ * Otherwise @work->func() will be called when the @task returns from kernel
+ * mode or exits.
+ *
+ * This is like the signal handler which runs in kernel mode, but it doesn't
+ * try to wake up the @task.
+ *
+ * RETURNS:
+ * 0 if succeeds or -ESRCH.
+ */
int
task_work_add(struct task_struct *task, struct callback_head *work, bool notify)
{
@@ -21,11 +38,22 @@
return 0;
}
+/**
+ * task_work_cancel - cancel a pending work added by task_work_add()
+ * @task: the task which should execute the work
+ * @func: identifies the work to remove
+ *
+ * Find the last queued pending work with ->func == @func and remove
+ * it from queue.
+ *
+ * RETURNS:
+ * The found work or NULL if not found.
+ */
struct callback_head *
task_work_cancel(struct task_struct *task, task_work_func_t func)
{
struct callback_head **pprev = &task->task_works;
- struct callback_head *work = NULL;
+ struct callback_head *work;
unsigned long flags;
/*
* If cmpxchg() fails we continue without updating pprev.
@@ -35,7 +63,7 @@
*/
raw_spin_lock_irqsave(&task->pi_lock, flags);
while ((work = ACCESS_ONCE(*pprev))) {
- read_barrier_depends();
+ smp_read_barrier_depends();
if (work->func != func)
pprev = &work->next;
else if (cmpxchg(pprev, work, work->next) == work)
@@ -46,6 +74,14 @@
return work;
}
+/**
+ * task_work_run - execute the works added by task_work_add()
+ *
+ * Flush the pending works. Should be used by the core kernel code.
+ * Called before the task returns to the user-mode or stops, or when
+ * it exits. In the latter case task_work_add() can no longer add the
+ * new work after task_work_run() returns.
+ */
void task_work_run(void)
{
struct task_struct *task = current;
diff --git a/kernel/up.c b/kernel/up.c
index c54c75e..630d72b 100644
--- a/kernel/up.c
+++ b/kernel/up.c
@@ -10,12 +10,64 @@
int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
int wait)
{
+ unsigned long flags;
+
WARN_ON(cpu != 0);
- local_irq_disable();
- (func)(info);
- local_irq_enable();
+ local_irq_save(flags);
+ func(info);
+ local_irq_restore(flags);
return 0;
}
EXPORT_SYMBOL(smp_call_function_single);
+
+int on_each_cpu(smp_call_func_t func, void *info, int wait)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ func(info);
+ local_irq_restore(flags);
+ return 0;
+}
+EXPORT_SYMBOL(on_each_cpu);
+
+/*
+ * Note we still need to test the mask even for UP
+ * because we actually can get an empty mask from
+ * code that on SMP might call us without the local
+ * CPU in the mask.
+ */
+void on_each_cpu_mask(const struct cpumask *mask,
+ smp_call_func_t func, void *info, bool wait)
+{
+ unsigned long flags;
+
+ if (cpumask_test_cpu(0, mask)) {
+ local_irq_save(flags);
+ func(info);
+ local_irq_restore(flags);
+ }
+}
+EXPORT_SYMBOL(on_each_cpu_mask);
+
+/*
+ * Preemption is disabled here to make sure the cond_func is called under the
+ * same condtions in UP and SMP.
+ */
+void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
+ smp_call_func_t func, void *info, bool wait,
+ gfp_t gfp_flags)
+{
+ unsigned long flags;
+
+ preempt_disable();
+ if (cond_func(0, info)) {
+ local_irq_save(flags);
+ func(info);
+ local_irq_restore(flags);
+ }
+ preempt_enable();
+}
+EXPORT_SYMBOL(on_each_cpu_cond);
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 652bea9..06344d9 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -597,7 +597,7 @@
config DEBUG_SHIRQ
bool "Debug shared IRQ handlers"
- depends on DEBUG_KERNEL && GENERIC_HARDIRQS
+ depends on DEBUG_KERNEL
help
Enable this to generate a spurious interrupt as soon as a shared
interrupt handler is registered, and just before one is deregistered.
@@ -1461,7 +1461,7 @@
config RBTREE_TEST
tristate "Red-Black tree test"
- depends on m && DEBUG_KERNEL
+ depends on DEBUG_KERNEL
help
A benchmark measuring the performance of the rbtree library.
Also includes rbtree invariant checks.
diff --git a/lib/Makefile b/lib/Makefile
index f2cb308..f3bb2cb 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -13,7 +13,7 @@
sha1.o md5.o irq_regs.o reciprocal_div.o argv_split.o \
proportions.o flex_proportions.o prio_heap.o ratelimit.o show_mem.o \
is_single_threaded.o plist.o decompress.o kobject_uevent.o \
- earlycpio.o percpu-refcount.o
+ earlycpio.o percpu-refcount.o percpu_ida.o
obj-$(CONFIG_ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS) += usercopy.o
lib-$(CONFIG_MMU) += ioremap.o
@@ -25,7 +25,8 @@
obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \
bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \
gcd.o lcm.o list_sort.o uuid.o flex_array.o iovec.o clz_ctz.o \
- bsearch.o find_last_bit.o find_next_bit.o llist.o memweight.o kfifo.o
+ bsearch.o find_last_bit.o find_next_bit.o llist.o memweight.o kfifo.o \
+ percpu_ida.o
obj-y += string_helpers.o
obj-$(CONFIG_TEST_STRING_HELPERS) += test-string_helpers.o
obj-y += kstrtox.o
diff --git a/lib/cpu_rmap.c b/lib/cpu_rmap.c
index 5fbed5c..4f134d8 100644
--- a/lib/cpu_rmap.c
+++ b/lib/cpu_rmap.c
@@ -8,9 +8,7 @@
*/
#include <linux/cpu_rmap.h>
-#ifdef CONFIG_GENERIC_HARDIRQS
#include <linux/interrupt.h>
-#endif
#include <linux/export.h>
/*
@@ -213,8 +211,6 @@
}
EXPORT_SYMBOL(cpu_rmap_update);
-#ifdef CONFIG_GENERIC_HARDIRQS
-
/* Glue between IRQ affinity notifiers and CPU rmaps */
struct irq_glue {
@@ -309,5 +305,3 @@
return rc;
}
EXPORT_SYMBOL(irq_cpu_rmap_add);
-
-#endif /* CONFIG_GENERIC_HARDIRQS */
diff --git a/lib/crc-t10dif.c b/lib/crc-t10dif.c
index 43bc5b0..dfe6ec1 100644
--- a/lib/crc-t10dif.c
+++ b/lib/crc-t10dif.c
@@ -14,8 +14,10 @@
#include <linux/err.h>
#include <linux/init.h>
#include <crypto/hash.h>
+#include <linux/static_key.h>
static struct crypto_shash *crct10dif_tfm;
+static struct static_key crct10dif_fallback __read_mostly;
__u16 crc_t10dif(const unsigned char *buffer, size_t len)
{
@@ -25,6 +27,9 @@
} desc;
int err;
+ if (static_key_false(&crct10dif_fallback))
+ return crc_t10dif_generic(0, buffer, len);
+
desc.shash.tfm = crct10dif_tfm;
desc.shash.flags = 0;
*(__u16 *)desc.ctx = 0;
@@ -39,7 +44,11 @@
static int __init crc_t10dif_mod_init(void)
{
crct10dif_tfm = crypto_alloc_shash("crct10dif", 0, 0);
- return PTR_RET(crct10dif_tfm);
+ if (IS_ERR(crct10dif_tfm)) {
+ static_key_slow_inc(&crct10dif_fallback);
+ crct10dif_tfm = NULL;
+ }
+ return 0;
}
static void __exit crc_t10dif_mod_fini(void)
diff --git a/lib/crc32.c b/lib/crc32.c
index 072fbd8..410093d 100644
--- a/lib/crc32.c
+++ b/lib/crc32.c
@@ -131,11 +131,14 @@
#endif
/**
- * crc32_le() - Calculate bitwise little-endian Ethernet AUTODIN II CRC32
- * @crc: seed value for computation. ~0 for Ethernet, sometimes 0 for
- * other uses, or the previous crc32 value if computing incrementally.
- * @p: pointer to buffer over which CRC is run
+ * crc32_le_generic() - Calculate bitwise little-endian Ethernet AUTODIN II
+ * CRC32/CRC32C
+ * @crc: seed value for computation. ~0 for Ethernet, sometimes 0 for other
+ * uses, or the previous crc32/crc32c value if computing incrementally.
+ * @p: pointer to buffer over which CRC32/CRC32C is run
* @len: length of buffer @p
+ * @tab: little-endian Ethernet table
+ * @polynomial: CRC32/CRC32c LE polynomial
*/
static inline u32 __pure crc32_le_generic(u32 crc, unsigned char const *p,
size_t len, const u32 (*tab)[256],
@@ -201,11 +204,13 @@
EXPORT_SYMBOL(__crc32c_le);
/**
- * crc32_be() - Calculate bitwise big-endian Ethernet AUTODIN II CRC32
+ * crc32_be_generic() - Calculate bitwise big-endian Ethernet AUTODIN II CRC32
* @crc: seed value for computation. ~0 for Ethernet, sometimes 0 for
* other uses, or the previous crc32 value if computing incrementally.
- * @p: pointer to buffer over which CRC is run
+ * @p: pointer to buffer over which CRC32 is run
* @len: length of buffer @p
+ * @tab: big-endian Ethernet table
+ * @polynomial: CRC32 BE polynomial
*/
static inline u32 __pure crc32_be_generic(u32 crc, unsigned char const *p,
size_t len, const u32 (*tab)[256],
diff --git a/lib/decompress_inflate.c b/lib/decompress_inflate.c
index 19ff89e..d619b28 100644
--- a/lib/decompress_inflate.c
+++ b/lib/decompress_inflate.c
@@ -48,7 +48,7 @@
out_len = 0x8000; /* 32 K */
out_buf = malloc(out_len);
} else {
- out_len = 0x7fffffff; /* no limit */
+ out_len = ((size_t)~0) - (size_t)out_buf; /* no limit */
}
if (!out_buf) {
error("Out of memory while allocating output buffer");
diff --git a/lib/genalloc.c b/lib/genalloc.c
index b35cfa9..26cf20b 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -37,6 +37,11 @@
#include <linux/of_address.h>
#include <linux/of_device.h>
+static inline size_t chunk_size(const struct gen_pool_chunk *chunk)
+{
+ return chunk->end_addr - chunk->start_addr + 1;
+}
+
static int set_bits_ll(unsigned long *addr, unsigned long mask_to_set)
{
unsigned long val, nval;
@@ -182,13 +187,13 @@
int nbytes = sizeof(struct gen_pool_chunk) +
BITS_TO_LONGS(nbits) * sizeof(long);
- chunk = kmalloc_node(nbytes, GFP_KERNEL | __GFP_ZERO, nid);
+ chunk = kzalloc_node(nbytes, GFP_KERNEL, nid);
if (unlikely(chunk == NULL))
return -ENOMEM;
chunk->phys_addr = phys;
chunk->start_addr = virt;
- chunk->end_addr = virt + size;
+ chunk->end_addr = virt + size - 1;
atomic_set(&chunk->avail, size);
spin_lock(&pool->lock);
@@ -213,7 +218,7 @@
rcu_read_lock();
list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk) {
- if (addr >= chunk->start_addr && addr < chunk->end_addr) {
+ if (addr >= chunk->start_addr && addr <= chunk->end_addr) {
paddr = chunk->phys_addr + (addr - chunk->start_addr);
break;
}
@@ -242,7 +247,7 @@
chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk);
list_del(&chunk->next_chunk);
- end_bit = (chunk->end_addr - chunk->start_addr) >> order;
+ end_bit = chunk_size(chunk) >> order;
bit = find_next_bit(chunk->bits, end_bit, 0);
BUG_ON(bit < end_bit);
@@ -283,7 +288,7 @@
if (size > atomic_read(&chunk->avail))
continue;
- end_bit = (chunk->end_addr - chunk->start_addr) >> order;
+ end_bit = chunk_size(chunk) >> order;
retry:
start_bit = pool->algo(chunk->bits, end_bit, start_bit, nbits,
pool->data);
@@ -330,8 +335,8 @@
nbits = (size + (1UL << order) - 1) >> order;
rcu_read_lock();
list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk) {
- if (addr >= chunk->start_addr && addr < chunk->end_addr) {
- BUG_ON(addr + size > chunk->end_addr);
+ if (addr >= chunk->start_addr && addr <= chunk->end_addr) {
+ BUG_ON(addr + size - 1 > chunk->end_addr);
start_bit = (addr - chunk->start_addr) >> order;
remain = bitmap_clear_ll(chunk->bits, start_bit, nbits);
BUG_ON(remain);
@@ -400,7 +405,7 @@
rcu_read_lock();
list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk)
- size += chunk->end_addr - chunk->start_addr;
+ size += chunk_size(chunk);
rcu_read_unlock();
return size;
}
@@ -519,7 +524,6 @@
/**
* dev_get_gen_pool - Obtain the gen_pool (if any) for a device
* @dev: device to retrieve the gen_pool from
- * @name: Optional name for the gen_pool, usually NULL
*
* Returns the gen_pool for the device if one is present, or NULL.
*/
diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c
index 411be80..df6839e 100644
--- a/lib/lz4/lz4_decompress.c
+++ b/lib/lz4/lz4_decompress.c
@@ -283,8 +283,8 @@
return (int) (-(((char *) ip) - source));
}
-int lz4_decompress(const char *src, size_t *src_len, char *dest,
- size_t actual_dest_len)
+int lz4_decompress(const unsigned char *src, size_t *src_len,
+ unsigned char *dest, size_t actual_dest_len)
{
int ret = -1;
int input_len = 0;
@@ -302,8 +302,8 @@
EXPORT_SYMBOL(lz4_decompress);
#endif
-int lz4_decompress_unknownoutputsize(const char *src, size_t src_len,
- char *dest, size_t *dest_len)
+int lz4_decompress_unknownoutputsize(const unsigned char *src, size_t src_len,
+ unsigned char *dest, size_t *dest_len)
{
int ret = -1;
int out_len = 0;
diff --git a/lib/percpu_ida.c b/lib/percpu_ida.c
new file mode 100644
index 0000000..bab1ba2
--- /dev/null
+++ b/lib/percpu_ida.c
@@ -0,0 +1,335 @@
+/*
+ * Percpu IDA library
+ *
+ * Copyright (C) 2013 Datera, Inc. Kent Overstreet
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2, or (at
+ * your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+#include <linux/bug.h>
+#include <linux/err.h>
+#include <linux/export.h>
+#include <linux/hardirq.h>
+#include <linux/idr.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/percpu.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/spinlock.h>
+#include <linux/percpu_ida.h>
+
+/*
+ * Number of tags we move between the percpu freelist and the global freelist at
+ * a time
+ */
+#define IDA_PCPU_BATCH_MOVE 32U
+
+/* Max size of percpu freelist, */
+#define IDA_PCPU_SIZE ((IDA_PCPU_BATCH_MOVE * 3) / 2)
+
+struct percpu_ida_cpu {
+ /*
+ * Even though this is percpu, we need a lock for tag stealing by remote
+ * CPUs:
+ */
+ spinlock_t lock;
+
+ /* nr_free/freelist form a stack of free IDs */
+ unsigned nr_free;
+ unsigned freelist[];
+};
+
+static inline void move_tags(unsigned *dst, unsigned *dst_nr,
+ unsigned *src, unsigned *src_nr,
+ unsigned nr)
+{
+ *src_nr -= nr;
+ memcpy(dst + *dst_nr, src + *src_nr, sizeof(unsigned) * nr);
+ *dst_nr += nr;
+}
+
+/*
+ * Try to steal tags from a remote cpu's percpu freelist.
+ *
+ * We first check how many percpu freelists have tags - we don't steal tags
+ * unless enough percpu freelists have tags on them that it's possible more than
+ * half the total tags could be stuck on remote percpu freelists.
+ *
+ * Then we iterate through the cpus until we find some tags - we don't attempt
+ * to find the "best" cpu to steal from, to keep cacheline bouncing to a
+ * minimum.
+ */
+static inline void steal_tags(struct percpu_ida *pool,
+ struct percpu_ida_cpu *tags)
+{
+ unsigned cpus_have_tags, cpu = pool->cpu_last_stolen;
+ struct percpu_ida_cpu *remote;
+
+ for (cpus_have_tags = cpumask_weight(&pool->cpus_have_tags);
+ cpus_have_tags * IDA_PCPU_SIZE > pool->nr_tags / 2;
+ cpus_have_tags--) {
+ cpu = cpumask_next(cpu, &pool->cpus_have_tags);
+
+ if (cpu >= nr_cpu_ids) {
+ cpu = cpumask_first(&pool->cpus_have_tags);
+ if (cpu >= nr_cpu_ids)
+ BUG();
+ }
+
+ pool->cpu_last_stolen = cpu;
+ remote = per_cpu_ptr(pool->tag_cpu, cpu);
+
+ cpumask_clear_cpu(cpu, &pool->cpus_have_tags);
+
+ if (remote == tags)
+ continue;
+
+ spin_lock(&remote->lock);
+
+ if (remote->nr_free) {
+ memcpy(tags->freelist,
+ remote->freelist,
+ sizeof(unsigned) * remote->nr_free);
+
+ tags->nr_free = remote->nr_free;
+ remote->nr_free = 0;
+ }
+
+ spin_unlock(&remote->lock);
+
+ if (tags->nr_free)
+ break;
+ }
+}
+
+/*
+ * Pop up to IDA_PCPU_BATCH_MOVE IDs off the global freelist, and push them onto
+ * our percpu freelist:
+ */
+static inline void alloc_global_tags(struct percpu_ida *pool,
+ struct percpu_ida_cpu *tags)
+{
+ move_tags(tags->freelist, &tags->nr_free,
+ pool->freelist, &pool->nr_free,
+ min(pool->nr_free, IDA_PCPU_BATCH_MOVE));
+}
+
+static inline unsigned alloc_local_tag(struct percpu_ida *pool,
+ struct percpu_ida_cpu *tags)
+{
+ int tag = -ENOSPC;
+
+ spin_lock(&tags->lock);
+ if (tags->nr_free)
+ tag = tags->freelist[--tags->nr_free];
+ spin_unlock(&tags->lock);
+
+ return tag;
+}
+
+/**
+ * percpu_ida_alloc - allocate a tag
+ * @pool: pool to allocate from
+ * @gfp: gfp flags
+ *
+ * Returns a tag - an integer in the range [0..nr_tags) (passed to
+ * tag_pool_init()), or otherwise -ENOSPC on allocation failure.
+ *
+ * Safe to be called from interrupt context (assuming it isn't passed
+ * __GFP_WAIT, of course).
+ *
+ * @gfp indicates whether or not to wait until a free id is available (it's not
+ * used for internal memory allocations); thus if passed __GFP_WAIT we may sleep
+ * however long it takes until another thread frees an id (same semantics as a
+ * mempool).
+ *
+ * Will not fail if passed __GFP_WAIT.
+ */
+int percpu_ida_alloc(struct percpu_ida *pool, gfp_t gfp)
+{
+ DEFINE_WAIT(wait);
+ struct percpu_ida_cpu *tags;
+ unsigned long flags;
+ int tag;
+
+ local_irq_save(flags);
+ tags = this_cpu_ptr(pool->tag_cpu);
+
+ /* Fastpath */
+ tag = alloc_local_tag(pool, tags);
+ if (likely(tag >= 0)) {
+ local_irq_restore(flags);
+ return tag;
+ }
+
+ while (1) {
+ spin_lock(&pool->lock);
+
+ /*
+ * prepare_to_wait() must come before steal_tags(), in case
+ * percpu_ida_free() on another cpu flips a bit in
+ * cpus_have_tags
+ *
+ * global lock held and irqs disabled, don't need percpu lock
+ */
+ prepare_to_wait(&pool->wait, &wait, TASK_UNINTERRUPTIBLE);
+
+ if (!tags->nr_free)
+ alloc_global_tags(pool, tags);
+ if (!tags->nr_free)
+ steal_tags(pool, tags);
+
+ if (tags->nr_free) {
+ tag = tags->freelist[--tags->nr_free];
+ if (tags->nr_free)
+ cpumask_set_cpu(smp_processor_id(),
+ &pool->cpus_have_tags);
+ }
+
+ spin_unlock(&pool->lock);
+ local_irq_restore(flags);
+
+ if (tag >= 0 || !(gfp & __GFP_WAIT))
+ break;
+
+ schedule();
+
+ local_irq_save(flags);
+ tags = this_cpu_ptr(pool->tag_cpu);
+ }
+
+ finish_wait(&pool->wait, &wait);
+ return tag;
+}
+EXPORT_SYMBOL_GPL(percpu_ida_alloc);
+
+/**
+ * percpu_ida_free - free a tag
+ * @pool: pool @tag was allocated from
+ * @tag: a tag previously allocated with percpu_ida_alloc()
+ *
+ * Safe to be called from interrupt context.
+ */
+void percpu_ida_free(struct percpu_ida *pool, unsigned tag)
+{
+ struct percpu_ida_cpu *tags;
+ unsigned long flags;
+ unsigned nr_free;
+
+ BUG_ON(tag >= pool->nr_tags);
+
+ local_irq_save(flags);
+ tags = this_cpu_ptr(pool->tag_cpu);
+
+ spin_lock(&tags->lock);
+ tags->freelist[tags->nr_free++] = tag;
+
+ nr_free = tags->nr_free;
+ spin_unlock(&tags->lock);
+
+ if (nr_free == 1) {
+ cpumask_set_cpu(smp_processor_id(),
+ &pool->cpus_have_tags);
+ wake_up(&pool->wait);
+ }
+
+ if (nr_free == IDA_PCPU_SIZE) {
+ spin_lock(&pool->lock);
+
+ /*
+ * Global lock held and irqs disabled, don't need percpu
+ * lock
+ */
+ if (tags->nr_free == IDA_PCPU_SIZE) {
+ move_tags(pool->freelist, &pool->nr_free,
+ tags->freelist, &tags->nr_free,
+ IDA_PCPU_BATCH_MOVE);
+
+ wake_up(&pool->wait);
+ }
+ spin_unlock(&pool->lock);
+ }
+
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(percpu_ida_free);
+
+/**
+ * percpu_ida_destroy - release a tag pool's resources
+ * @pool: pool to free
+ *
+ * Frees the resources allocated by percpu_ida_init().
+ */
+void percpu_ida_destroy(struct percpu_ida *pool)
+{
+ free_percpu(pool->tag_cpu);
+ free_pages((unsigned long) pool->freelist,
+ get_order(pool->nr_tags * sizeof(unsigned)));
+}
+EXPORT_SYMBOL_GPL(percpu_ida_destroy);
+
+/**
+ * percpu_ida_init - initialize a percpu tag pool
+ * @pool: pool to initialize
+ * @nr_tags: number of tags that will be available for allocation
+ *
+ * Initializes @pool so that it can be used to allocate tags - integers in the
+ * range [0, nr_tags). Typically, they'll be used by driver code to refer to a
+ * preallocated array of tag structures.
+ *
+ * Allocation is percpu, but sharding is limited by nr_tags - for best
+ * performance, the workload should not span more cpus than nr_tags / 128.
+ */
+int percpu_ida_init(struct percpu_ida *pool, unsigned long nr_tags)
+{
+ unsigned i, cpu, order;
+
+ memset(pool, 0, sizeof(*pool));
+
+ init_waitqueue_head(&pool->wait);
+ spin_lock_init(&pool->lock);
+ pool->nr_tags = nr_tags;
+
+ /* Guard against overflow */
+ if (nr_tags > (unsigned) INT_MAX + 1) {
+ pr_err("percpu_ida_init(): nr_tags too large\n");
+ return -EINVAL;
+ }
+
+ order = get_order(nr_tags * sizeof(unsigned));
+ pool->freelist = (void *) __get_free_pages(GFP_KERNEL, order);
+ if (!pool->freelist)
+ return -ENOMEM;
+
+ for (i = 0; i < nr_tags; i++)
+ pool->freelist[i] = i;
+
+ pool->nr_free = nr_tags;
+
+ pool->tag_cpu = __alloc_percpu(sizeof(struct percpu_ida_cpu) +
+ IDA_PCPU_SIZE * sizeof(unsigned),
+ sizeof(unsigned));
+ if (!pool->tag_cpu)
+ goto err;
+
+ for_each_possible_cpu(cpu)
+ spin_lock_init(&per_cpu_ptr(pool->tag_cpu, cpu)->lock);
+
+ return 0;
+err:
+ percpu_ida_destroy(pool);
+ return -ENOMEM;
+}
+EXPORT_SYMBOL_GPL(percpu_ida_init);
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index e796429..7811ed3 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -32,6 +32,7 @@
#include <linux/string.h>
#include <linux/bitops.h>
#include <linux/rcupdate.h>
+#include <linux/hardirq.h> /* in_interrupt() */
#ifdef __KERNEL__
@@ -207,7 +208,12 @@
struct radix_tree_node *ret = NULL;
gfp_t gfp_mask = root_gfp_mask(root);
- if (!(gfp_mask & __GFP_WAIT)) {
+ /*
+ * Preload code isn't irq safe and it doesn't make sence to use
+ * preloading in the interrupt anyway as all the allocations have to
+ * be atomic. So just do normal allocation when in interrupt.
+ */
+ if (!(gfp_mask & __GFP_WAIT) && !in_interrupt()) {
struct radix_tree_preload *rtp;
/*
@@ -264,7 +270,7 @@
* To make use of this facility, the radix tree must be initialised without
* __GFP_WAIT being passed to INIT_RADIX_TREE().
*/
-int radix_tree_preload(gfp_t gfp_mask)
+static int __radix_tree_preload(gfp_t gfp_mask)
{
struct radix_tree_preload *rtp;
struct radix_tree_node *node;
@@ -288,9 +294,40 @@
out:
return ret;
}
+
+/*
+ * Load up this CPU's radix_tree_node buffer with sufficient objects to
+ * ensure that the addition of a single element in the tree cannot fail. On
+ * success, return zero, with preemption disabled. On error, return -ENOMEM
+ * with preemption not disabled.
+ *
+ * To make use of this facility, the radix tree must be initialised without
+ * __GFP_WAIT being passed to INIT_RADIX_TREE().
+ */
+int radix_tree_preload(gfp_t gfp_mask)
+{
+ /* Warn on non-sensical use... */
+ WARN_ON_ONCE(!(gfp_mask & __GFP_WAIT));
+ return __radix_tree_preload(gfp_mask);
+}
EXPORT_SYMBOL(radix_tree_preload);
/*
+ * The same as above function, except we don't guarantee preloading happens.
+ * We do it, if we decide it helps. On success, return zero with preemption
+ * disabled. On error, return -ENOMEM with preemption not disabled.
+ */
+int radix_tree_maybe_preload(gfp_t gfp_mask)
+{
+ if (gfp_mask & __GFP_WAIT)
+ return __radix_tree_preload(gfp_mask);
+ /* Preloading doesn't help anything with this gfp mask, skip it */
+ preempt_disable();
+ return 0;
+}
+EXPORT_SYMBOL(radix_tree_maybe_preload);
+
+/*
* Return the maximum key which can be store into a
* radix tree with height HEIGHT.
*/
diff --git a/lib/rbtree.c b/lib/rbtree.c
index c0e31fe..65f4eff 100644
--- a/lib/rbtree.c
+++ b/lib/rbtree.c
@@ -518,3 +518,43 @@
*new = *victim;
}
EXPORT_SYMBOL(rb_replace_node);
+
+static struct rb_node *rb_left_deepest_node(const struct rb_node *node)
+{
+ for (;;) {
+ if (node->rb_left)
+ node = node->rb_left;
+ else if (node->rb_right)
+ node = node->rb_right;
+ else
+ return (struct rb_node *)node;
+ }
+}
+
+struct rb_node *rb_next_postorder(const struct rb_node *node)
+{
+ const struct rb_node *parent;
+ if (!node)
+ return NULL;
+ parent = rb_parent(node);
+
+ /* If we're sitting on node, we've already seen our children */
+ if (parent && node == parent->rb_left && parent->rb_right) {
+ /* If we are the parent's left node, go to the parent's right
+ * node then all the way down to the left */
+ return rb_left_deepest_node(parent->rb_right);
+ } else
+ /* Otherwise we are the parent's right node, and the parent
+ * should be next */
+ return (struct rb_node *)parent;
+}
+EXPORT_SYMBOL(rb_next_postorder);
+
+struct rb_node *rb_first_postorder(const struct rb_root *root)
+{
+ if (!root->rb_node)
+ return NULL;
+
+ return rb_left_deepest_node(root->rb_node);
+}
+EXPORT_SYMBOL(rb_first_postorder);
diff --git a/lib/rbtree_test.c b/lib/rbtree_test.c
index 122f02f..31dd4cc 100644
--- a/lib/rbtree_test.c
+++ b/lib/rbtree_test.c
@@ -114,6 +114,16 @@
return count;
}
+static void check_postorder(int nr_nodes)
+{
+ struct rb_node *rb;
+ int count = 0;
+ for (rb = rb_first_postorder(&root); rb; rb = rb_next_postorder(rb))
+ count++;
+
+ WARN_ON_ONCE(count != nr_nodes);
+}
+
static void check(int nr_nodes)
{
struct rb_node *rb;
@@ -136,6 +146,8 @@
WARN_ON_ONCE(count != nr_nodes);
WARN_ON_ONCE(count < (1 << black_path_count(rb_last(&root))) - 1);
+
+ check_postorder(nr_nodes);
}
static void check_augmented(int nr_nodes)
diff --git a/mm/Kconfig b/mm/Kconfig
index 6cdd270..026771a 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -245,7 +245,7 @@
config MIGRATION
bool "Page migration"
def_bool y
- depends on NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA
+ depends on (NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA) && MMU
help
Allows the migration of the physical location of pages of processes
while the virtual addresses are not changed. This is useful in
@@ -480,7 +480,7 @@
config CMA
bool "Contiguous Memory Allocator"
- depends on HAVE_MEMBLOCK
+ depends on HAVE_MEMBLOCK && MMU
select MIGRATION
select MEMORY_ISOLATION
help
diff --git a/mm/Makefile b/mm/Makefile
index f008033..305d10a 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -17,7 +17,7 @@
util.o mmzone.o vmstat.o backing-dev.o \
mm_init.o mmu_context.o percpu.o slab_common.o \
compaction.o balloon_compaction.o \
- interval_tree.o $(mmu-y)
+ interval_tree.o list_lru.o $(mmu-y)
obj-y += init-mm.o
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 37d9edc..ce682f7 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -652,7 +652,7 @@
{
char kbuf[] = "0\n";
- if (*ppos) {
+ if (*ppos || *lenp < sizeof(kbuf)) {
*lenp = 0;
return 0;
}
diff --git a/mm/compaction.c b/mm/compaction.c
index 05ccb4c..c437893 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1131,6 +1131,9 @@
.sync = false,
};
+ if (!order)
+ return;
+
__compact_pgdat(pgdat, &cc);
}
diff --git a/mm/filemap.c b/mm/filemap.c
index 731a2c2..1e6aec4 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -467,32 +467,34 @@
error = mem_cgroup_cache_charge(page, current->mm,
gfp_mask & GFP_RECLAIM_MASK);
if (error)
- goto out;
+ return error;
- error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM);
- if (error == 0) {
- page_cache_get(page);
- page->mapping = mapping;
- page->index = offset;
-
- spin_lock_irq(&mapping->tree_lock);
- error = radix_tree_insert(&mapping->page_tree, offset, page);
- if (likely(!error)) {
- mapping->nrpages++;
- __inc_zone_page_state(page, NR_FILE_PAGES);
- spin_unlock_irq(&mapping->tree_lock);
- trace_mm_filemap_add_to_page_cache(page);
- } else {
- page->mapping = NULL;
- /* Leave page->index set: truncation relies upon it */
- spin_unlock_irq(&mapping->tree_lock);
- mem_cgroup_uncharge_cache_page(page);
- page_cache_release(page);
- }
- radix_tree_preload_end();
- } else
+ error = radix_tree_maybe_preload(gfp_mask & ~__GFP_HIGHMEM);
+ if (error) {
mem_cgroup_uncharge_cache_page(page);
-out:
+ return error;
+ }
+
+ page_cache_get(page);
+ page->mapping = mapping;
+ page->index = offset;
+
+ spin_lock_irq(&mapping->tree_lock);
+ error = radix_tree_insert(&mapping->page_tree, offset, page);
+ radix_tree_preload_end();
+ if (unlikely(error))
+ goto err_insert;
+ mapping->nrpages++;
+ __inc_zone_page_state(page, NR_FILE_PAGES);
+ spin_unlock_irq(&mapping->tree_lock);
+ trace_mm_filemap_add_to_page_cache(page);
+ return 0;
+err_insert:
+ page->mapping = NULL;
+ /* Leave page->index set: truncation relies upon it */
+ spin_unlock_irq(&mapping->tree_lock);
+ mem_cgroup_uncharge_cache_page(page);
+ page_cache_release(page);
return error;
}
EXPORT_SYMBOL(add_to_page_cache_locked);
@@ -1614,6 +1616,7 @@
struct inode *inode = mapping->host;
pgoff_t offset = vmf->pgoff;
struct page *page;
+ bool memcg_oom;
pgoff_t size;
int ret = 0;
@@ -1622,7 +1625,11 @@
return VM_FAULT_SIGBUS;
/*
- * Do we have something in the page cache already?
+ * Do we have something in the page cache already? Either
+ * way, try readahead, but disable the memcg OOM killer for it
+ * as readahead is optional and no errors are propagated up
+ * the fault stack. The OOM killer is enabled while trying to
+ * instantiate the faulting page individually below.
*/
page = find_get_page(mapping, offset);
if (likely(page) && !(vmf->flags & FAULT_FLAG_TRIED)) {
@@ -1630,10 +1637,14 @@
* We found the page, so try async readahead before
* waiting for the lock.
*/
+ memcg_oom = mem_cgroup_toggle_oom(false);
do_async_mmap_readahead(vma, ra, file, page, offset);
+ mem_cgroup_toggle_oom(memcg_oom);
} else if (!page) {
/* No page in the page cache at all */
+ memcg_oom = mem_cgroup_toggle_oom(false);
do_sync_mmap_readahead(vma, ra, file, offset);
+ mem_cgroup_toggle_oom(memcg_oom);
count_vm_event(PGMAJFAULT);
mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
ret = VM_FAULT_MAJOR;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index a92012a..7489884 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -211,24 +211,29 @@
BUG_ON(atomic_dec_and_test(&huge_zero_refcount));
}
-static int shrink_huge_zero_page(struct shrinker *shrink,
- struct shrink_control *sc)
+static unsigned long shrink_huge_zero_page_count(struct shrinker *shrink,
+ struct shrink_control *sc)
{
- if (!sc->nr_to_scan)
- /* we can free zero page only if last reference remains */
- return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0;
+ /* we can free zero page only if last reference remains */
+ return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0;
+}
+static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink,
+ struct shrink_control *sc)
+{
if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) {
struct page *zero_page = xchg(&huge_zero_page, NULL);
BUG_ON(zero_page == NULL);
__free_page(zero_page);
+ return HPAGE_PMD_NR;
}
return 0;
}
static struct shrinker huge_zero_page_shrinker = {
- .shrink = shrink_huge_zero_page,
+ .count_objects = shrink_huge_zero_page_count,
+ .scan_objects = shrink_huge_zero_page_scan,
.seeks = DEFAULT_SEEKS,
};
@@ -417,7 +422,7 @@
unsigned long msecs;
int err;
- err = strict_strtoul(buf, 10, &msecs);
+ err = kstrtoul(buf, 10, &msecs);
if (err || msecs > UINT_MAX)
return -EINVAL;
@@ -444,7 +449,7 @@
unsigned long msecs;
int err;
- err = strict_strtoul(buf, 10, &msecs);
+ err = kstrtoul(buf, 10, &msecs);
if (err || msecs > UINT_MAX)
return -EINVAL;
@@ -470,7 +475,7 @@
int err;
unsigned long pages;
- err = strict_strtoul(buf, 10, &pages);
+ err = kstrtoul(buf, 10, &pages);
if (err || !pages || pages > UINT_MAX)
return -EINVAL;
@@ -538,7 +543,7 @@
int err;
unsigned long max_ptes_none;
- err = strict_strtoul(buf, 10, &max_ptes_none);
+ err = kstrtoul(buf, 10, &max_ptes_none);
if (err || max_ptes_none > HPAGE_PMD_NR-1)
return -EINVAL;
@@ -690,11 +695,10 @@
return pmd;
}
-static inline pmd_t mk_huge_pmd(struct page *page, struct vm_area_struct *vma)
+static inline pmd_t mk_huge_pmd(struct page *page, pgprot_t prot)
{
pmd_t entry;
- entry = mk_pmd(page, vma->vm_page_prot);
- entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
+ entry = mk_pmd(page, prot);
entry = pmd_mkhuge(entry);
return entry;
}
@@ -727,7 +731,8 @@
pte_free(mm, pgtable);
} else {
pmd_t entry;
- entry = mk_huge_pmd(page, vma);
+ entry = mk_huge_pmd(page, vma->vm_page_prot);
+ entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
page_add_new_anon_rmap(page, vma, haddr);
pgtable_trans_huge_deposit(mm, pmd, pgtable);
set_pmd_at(mm, haddr, pmd, entry);
@@ -783,77 +788,57 @@
{
struct page *page;
unsigned long haddr = address & HPAGE_PMD_MASK;
- pte_t *pte;
- if (haddr >= vma->vm_start && haddr + HPAGE_PMD_SIZE <= vma->vm_end) {
- if (unlikely(anon_vma_prepare(vma)))
+ if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end)
+ return VM_FAULT_FALLBACK;
+ if (unlikely(anon_vma_prepare(vma)))
+ return VM_FAULT_OOM;
+ if (unlikely(khugepaged_enter(vma)))
+ return VM_FAULT_OOM;
+ if (!(flags & FAULT_FLAG_WRITE) &&
+ transparent_hugepage_use_zero_page()) {
+ pgtable_t pgtable;
+ struct page *zero_page;
+ bool set;
+ pgtable = pte_alloc_one(mm, haddr);
+ if (unlikely(!pgtable))
return VM_FAULT_OOM;
- if (unlikely(khugepaged_enter(vma)))
- return VM_FAULT_OOM;
- if (!(flags & FAULT_FLAG_WRITE) &&
- transparent_hugepage_use_zero_page()) {
- pgtable_t pgtable;
- struct page *zero_page;
- bool set;
- pgtable = pte_alloc_one(mm, haddr);
- if (unlikely(!pgtable))
- return VM_FAULT_OOM;
- zero_page = get_huge_zero_page();
- if (unlikely(!zero_page)) {
- pte_free(mm, pgtable);
- count_vm_event(THP_FAULT_FALLBACK);
- goto out;
- }
- spin_lock(&mm->page_table_lock);
- set = set_huge_zero_page(pgtable, mm, vma, haddr, pmd,
- zero_page);
- spin_unlock(&mm->page_table_lock);
- if (!set) {
- pte_free(mm, pgtable);
- put_huge_zero_page();
- }
- return 0;
- }
- page = alloc_hugepage_vma(transparent_hugepage_defrag(vma),
- vma, haddr, numa_node_id(), 0);
- if (unlikely(!page)) {
+ zero_page = get_huge_zero_page();
+ if (unlikely(!zero_page)) {
+ pte_free(mm, pgtable);
count_vm_event(THP_FAULT_FALLBACK);
- goto out;
+ return VM_FAULT_FALLBACK;
}
- count_vm_event(THP_FAULT_ALLOC);
- if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) {
- put_page(page);
- goto out;
+ spin_lock(&mm->page_table_lock);
+ set = set_huge_zero_page(pgtable, mm, vma, haddr, pmd,
+ zero_page);
+ spin_unlock(&mm->page_table_lock);
+ if (!set) {
+ pte_free(mm, pgtable);
+ put_huge_zero_page();
}
- if (unlikely(__do_huge_pmd_anonymous_page(mm, vma, haddr, pmd,
- page))) {
- mem_cgroup_uncharge_page(page);
- put_page(page);
- goto out;
- }
-
return 0;
}
-out:
- /*
- * Use __pte_alloc instead of pte_alloc_map, because we can't
- * run pte_offset_map on the pmd, if an huge pmd could
- * materialize from under us from a different thread.
- */
- if (unlikely(pmd_none(*pmd)) &&
- unlikely(__pte_alloc(mm, vma, pmd, address)))
- return VM_FAULT_OOM;
- /* if an huge pmd materialized from under us just retry later */
- if (unlikely(pmd_trans_huge(*pmd)))
- return 0;
- /*
- * A regular pmd is established and it can't morph into a huge pmd
- * from under us anymore at this point because we hold the mmap_sem
- * read mode and khugepaged takes it in write mode. So now it's
- * safe to run pte_offset_map().
- */
- pte = pte_offset_map(pmd, address);
- return handle_pte_fault(mm, vma, address, pte, pmd, flags);
+ page = alloc_hugepage_vma(transparent_hugepage_defrag(vma),
+ vma, haddr, numa_node_id(), 0);
+ if (unlikely(!page)) {
+ count_vm_event(THP_FAULT_FALLBACK);
+ return VM_FAULT_FALLBACK;
+ }
+ if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) {
+ put_page(page);
+ count_vm_event(THP_FAULT_FALLBACK);
+ return VM_FAULT_FALLBACK;
+ }
+ if (unlikely(__do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, page))) {
+ mem_cgroup_uncharge_page(page);
+ put_page(page);
+ count_vm_event(THP_FAULT_FALLBACK);
+ return VM_FAULT_FALLBACK;
+ }
+
+ count_vm_event(THP_FAULT_ALLOC);
+ return 0;
}
int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
@@ -1165,7 +1150,6 @@
new_page = NULL;
if (unlikely(!new_page)) {
- count_vm_event(THP_FAULT_FALLBACK);
if (is_huge_zero_pmd(orig_pmd)) {
ret = do_huge_pmd_wp_zero_page_fallback(mm, vma,
address, pmd, orig_pmd, haddr);
@@ -1176,9 +1160,9 @@
split_huge_page(page);
put_page(page);
}
+ count_vm_event(THP_FAULT_FALLBACK);
goto out;
}
- count_vm_event(THP_FAULT_ALLOC);
if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) {
put_page(new_page);
@@ -1186,10 +1170,13 @@
split_huge_page(page);
put_page(page);
}
+ count_vm_event(THP_FAULT_FALLBACK);
ret |= VM_FAULT_OOM;
goto out;
}
+ count_vm_event(THP_FAULT_ALLOC);
+
if (is_huge_zero_pmd(orig_pmd))
clear_huge_page(new_page, haddr, HPAGE_PMD_NR);
else
@@ -1210,7 +1197,8 @@
goto out_mn;
} else {
pmd_t entry;
- entry = mk_huge_pmd(new_page, vma);
+ entry = mk_huge_pmd(new_page, vma->vm_page_prot);
+ entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
pmdp_clear_flush(vma, haddr, pmd);
page_add_new_anon_rmap(new_page, vma, haddr);
set_pmd_at(mm, haddr, pmd, entry);
@@ -1661,7 +1649,6 @@
BUG_ON(atomic_read(&page->_count) <= 0);
__mod_zone_page_state(zone, NR_ANON_TRANSPARENT_HUGEPAGES, -1);
- __mod_zone_page_state(zone, NR_ANON_PAGES, HPAGE_PMD_NR);
ClearPageCompound(page);
compound_unlock(page);
@@ -2296,6 +2283,8 @@
goto out;
vma = find_vma(mm, address);
+ if (!vma)
+ goto out;
hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
hend = vma->vm_end & HPAGE_PMD_MASK;
if (address < hstart || address + HPAGE_PMD_SIZE > hend)
@@ -2357,7 +2346,8 @@
__SetPageUptodate(new_page);
pgtable = pmd_pgtable(_pmd);
- _pmd = mk_huge_pmd(new_page, vma);
+ _pmd = mk_huge_pmd(new_page, vma->vm_page_prot);
+ _pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma);
/*
* spin_lock() below is not the equivalent of smp_wmb(), so
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index b60f330..b49579c 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -21,6 +21,7 @@
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/swapops.h>
+#include <linux/page-isolation.h>
#include <asm/page.h>
#include <asm/pgtable.h>
@@ -33,7 +34,6 @@
#include "internal.h"
const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL;
-static gfp_t htlb_alloc_mask = GFP_HIGHUSER;
unsigned long hugepages_treat_as_movable;
int hugetlb_max_hstate __read_mostly;
@@ -48,7 +48,8 @@
static unsigned long __initdata default_hstate_size;
/*
- * Protects updates to hugepage_freelists, nr_huge_pages, and free_huge_pages
+ * Protects updates to hugepage_freelists, hugepage_activelist, nr_huge_pages,
+ * free_huge_pages, and surplus_huge_pages.
*/
DEFINE_SPINLOCK(hugetlb_lock);
@@ -135,9 +136,9 @@
* across the pages in a mapping.
*
* The region data structures are protected by a combination of the mmap_sem
- * and the hugetlb_instantion_mutex. To access or modify a region the caller
+ * and the hugetlb_instantiation_mutex. To access or modify a region the caller
* must either hold the mmap_sem for write, or the mmap_sem for read and
- * the hugetlb_instantiation mutex:
+ * the hugetlb_instantiation_mutex:
*
* down_write(&mm->mmap_sem);
* or
@@ -434,25 +435,6 @@
return (get_vma_private_data(vma) & flag) != 0;
}
-/* Decrement the reserved pages in the hugepage pool by one */
-static void decrement_hugepage_resv_vma(struct hstate *h,
- struct vm_area_struct *vma)
-{
- if (vma->vm_flags & VM_NORESERVE)
- return;
-
- if (vma->vm_flags & VM_MAYSHARE) {
- /* Shared mappings always use reserves */
- h->resv_huge_pages--;
- } else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
- /*
- * Only the process that called mmap() has reserves for
- * private mappings.
- */
- h->resv_huge_pages--;
- }
-}
-
/* Reset counters to 0 and clear all HPAGE_RESV_* flags */
void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
{
@@ -462,12 +444,35 @@
}
/* Returns true if the VMA has associated reserve pages */
-static int vma_has_reserves(struct vm_area_struct *vma)
+static int vma_has_reserves(struct vm_area_struct *vma, long chg)
{
+ if (vma->vm_flags & VM_NORESERVE) {
+ /*
+ * This address is already reserved by other process(chg == 0),
+ * so, we should decrement reserved count. Without decrementing,
+ * reserve count remains after releasing inode, because this
+ * allocated page will go into page cache and is regarded as
+ * coming from reserved pool in releasing step. Currently, we
+ * don't have any other solution to deal with this situation
+ * properly, so add work-around here.
+ */
+ if (vma->vm_flags & VM_MAYSHARE && chg == 0)
+ return 1;
+ else
+ return 0;
+ }
+
+ /* Shared mappings always use reserves */
if (vma->vm_flags & VM_MAYSHARE)
return 1;
+
+ /*
+ * Only the process that called mmap() has reserves for
+ * private mappings.
+ */
if (is_vma_resv_set(vma, HPAGE_RESV_OWNER))
return 1;
+
return 0;
}
@@ -517,9 +522,15 @@
{
struct page *page;
- if (list_empty(&h->hugepage_freelists[nid]))
+ list_for_each_entry(page, &h->hugepage_freelists[nid], lru)
+ if (!is_migrate_isolate_page(page))
+ break;
+ /*
+ * if 'non-isolated free hugepage' not found on the list,
+ * the allocation fails.
+ */
+ if (&h->hugepage_freelists[nid] == &page->lru)
return NULL;
- page = list_entry(h->hugepage_freelists[nid].next, struct page, lru);
list_move(&page->lru, &h->hugepage_activelist);
set_page_refcounted(page);
h->free_huge_pages--;
@@ -527,9 +538,19 @@
return page;
}
+/* Movability of hugepages depends on migration support. */
+static inline gfp_t htlb_alloc_mask(struct hstate *h)
+{
+ if (hugepages_treat_as_movable || hugepage_migration_support(h))
+ return GFP_HIGHUSER_MOVABLE;
+ else
+ return GFP_HIGHUSER;
+}
+
static struct page *dequeue_huge_page_vma(struct hstate *h,
struct vm_area_struct *vma,
- unsigned long address, int avoid_reserve)
+ unsigned long address, int avoid_reserve,
+ long chg)
{
struct page *page = NULL;
struct mempolicy *mpol;
@@ -539,16 +560,12 @@
struct zoneref *z;
unsigned int cpuset_mems_cookie;
-retry_cpuset:
- cpuset_mems_cookie = get_mems_allowed();
- zonelist = huge_zonelist(vma, address,
- htlb_alloc_mask, &mpol, &nodemask);
/*
* A child process with MAP_PRIVATE mappings created by their parent
* have no page reserves. This check ensures that reservations are
* not "stolen". The child may still get SIGKILLed
*/
- if (!vma_has_reserves(vma) &&
+ if (!vma_has_reserves(vma, chg) &&
h->free_huge_pages - h->resv_huge_pages == 0)
goto err;
@@ -556,13 +573,23 @@
if (avoid_reserve && h->free_huge_pages - h->resv_huge_pages == 0)
goto err;
+retry_cpuset:
+ cpuset_mems_cookie = get_mems_allowed();
+ zonelist = huge_zonelist(vma, address,
+ htlb_alloc_mask(h), &mpol, &nodemask);
+
for_each_zone_zonelist_nodemask(zone, z, zonelist,
MAX_NR_ZONES - 1, nodemask) {
- if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask)) {
+ if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask(h))) {
page = dequeue_huge_page_node(h, zone_to_nid(zone));
if (page) {
- if (!avoid_reserve)
- decrement_hugepage_resv_vma(h, vma);
+ if (avoid_reserve)
+ break;
+ if (!vma_has_reserves(vma, chg))
+ break;
+
+ SetPagePrivate(page);
+ h->resv_huge_pages--;
break;
}
}
@@ -574,7 +601,6 @@
return page;
err:
- mpol_cond_put(mpol);
return NULL;
}
@@ -620,15 +646,20 @@
int nid = page_to_nid(page);
struct hugepage_subpool *spool =
(struct hugepage_subpool *)page_private(page);
+ bool restore_reserve;
set_page_private(page, 0);
page->mapping = NULL;
BUG_ON(page_count(page));
BUG_ON(page_mapcount(page));
+ restore_reserve = PagePrivate(page);
spin_lock(&hugetlb_lock);
hugetlb_cgroup_uncharge_page(hstate_index(h),
pages_per_huge_page(h), page);
+ if (restore_reserve)
+ h->resv_huge_pages++;
+
if (h->surplus_huge_pages_node[nid] && huge_page_order(h) < MAX_ORDER) {
/* remove the page from active list */
list_del(&page->lru);
@@ -715,7 +746,7 @@
return NULL;
page = alloc_pages_exact_node(nid,
- htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|
+ htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE|
__GFP_REPEAT|__GFP_NOWARN,
huge_page_order(h));
if (page) {
@@ -772,33 +803,6 @@
return nid;
}
-static int alloc_fresh_huge_page(struct hstate *h, nodemask_t *nodes_allowed)
-{
- struct page *page;
- int start_nid;
- int next_nid;
- int ret = 0;
-
- start_nid = hstate_next_node_to_alloc(h, nodes_allowed);
- next_nid = start_nid;
-
- do {
- page = alloc_fresh_huge_page_node(h, next_nid);
- if (page) {
- ret = 1;
- break;
- }
- next_nid = hstate_next_node_to_alloc(h, nodes_allowed);
- } while (next_nid != start_nid);
-
- if (ret)
- count_vm_event(HTLB_BUDDY_PGALLOC);
- else
- count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);
-
- return ret;
-}
-
/*
* helper for free_pool_huge_page() - return the previously saved
* node ["this node"] from which to free a huge page. Advance the
@@ -817,6 +821,40 @@
return nid;
}
+#define for_each_node_mask_to_alloc(hs, nr_nodes, node, mask) \
+ for (nr_nodes = nodes_weight(*mask); \
+ nr_nodes > 0 && \
+ ((node = hstate_next_node_to_alloc(hs, mask)) || 1); \
+ nr_nodes--)
+
+#define for_each_node_mask_to_free(hs, nr_nodes, node, mask) \
+ for (nr_nodes = nodes_weight(*mask); \
+ nr_nodes > 0 && \
+ ((node = hstate_next_node_to_free(hs, mask)) || 1); \
+ nr_nodes--)
+
+static int alloc_fresh_huge_page(struct hstate *h, nodemask_t *nodes_allowed)
+{
+ struct page *page;
+ int nr_nodes, node;
+ int ret = 0;
+
+ for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) {
+ page = alloc_fresh_huge_page_node(h, node);
+ if (page) {
+ ret = 1;
+ break;
+ }
+ }
+
+ if (ret)
+ count_vm_event(HTLB_BUDDY_PGALLOC);
+ else
+ count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);
+
+ return ret;
+}
+
/*
* Free huge page from pool from next node to free.
* Attempt to keep persistent huge pages more or less
@@ -826,40 +864,73 @@
static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
bool acct_surplus)
{
- int start_nid;
- int next_nid;
+ int nr_nodes, node;
int ret = 0;
- start_nid = hstate_next_node_to_free(h, nodes_allowed);
- next_nid = start_nid;
-
- do {
+ for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) {
/*
* If we're returning unused surplus pages, only examine
* nodes with surplus pages.
*/
- if ((!acct_surplus || h->surplus_huge_pages_node[next_nid]) &&
- !list_empty(&h->hugepage_freelists[next_nid])) {
+ if ((!acct_surplus || h->surplus_huge_pages_node[node]) &&
+ !list_empty(&h->hugepage_freelists[node])) {
struct page *page =
- list_entry(h->hugepage_freelists[next_nid].next,
+ list_entry(h->hugepage_freelists[node].next,
struct page, lru);
list_del(&page->lru);
h->free_huge_pages--;
- h->free_huge_pages_node[next_nid]--;
+ h->free_huge_pages_node[node]--;
if (acct_surplus) {
h->surplus_huge_pages--;
- h->surplus_huge_pages_node[next_nid]--;
+ h->surplus_huge_pages_node[node]--;
}
update_and_free_page(h, page);
ret = 1;
break;
}
- next_nid = hstate_next_node_to_free(h, nodes_allowed);
- } while (next_nid != start_nid);
+ }
return ret;
}
+/*
+ * Dissolve a given free hugepage into free buddy pages. This function does
+ * nothing for in-use (including surplus) hugepages.
+ */
+static void dissolve_free_huge_page(struct page *page)
+{
+ spin_lock(&hugetlb_lock);
+ if (PageHuge(page) && !page_count(page)) {
+ struct hstate *h = page_hstate(page);
+ int nid = page_to_nid(page);
+ list_del(&page->lru);
+ h->free_huge_pages--;
+ h->free_huge_pages_node[nid]--;
+ update_and_free_page(h, page);
+ }
+ spin_unlock(&hugetlb_lock);
+}
+
+/*
+ * Dissolve free hugepages in a given pfn range. Used by memory hotplug to
+ * make specified memory blocks removable from the system.
+ * Note that start_pfn should aligned with (minimum) hugepage size.
+ */
+void dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn)
+{
+ unsigned int order = 8 * sizeof(void *);
+ unsigned long pfn;
+ struct hstate *h;
+
+ /* Set scan step to minimum hugepage size */
+ for_each_hstate(h)
+ if (order > huge_page_order(h))
+ order = huge_page_order(h);
+ VM_BUG_ON(!IS_ALIGNED(start_pfn, 1 << order));
+ for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << order)
+ dissolve_free_huge_page(pfn_to_page(pfn));
+}
+
static struct page *alloc_buddy_huge_page(struct hstate *h, int nid)
{
struct page *page;
@@ -902,12 +973,12 @@
spin_unlock(&hugetlb_lock);
if (nid == NUMA_NO_NODE)
- page = alloc_pages(htlb_alloc_mask|__GFP_COMP|
+ page = alloc_pages(htlb_alloc_mask(h)|__GFP_COMP|
__GFP_REPEAT|__GFP_NOWARN,
huge_page_order(h));
else
page = alloc_pages_exact_node(nid,
- htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|
+ htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE|
__GFP_REPEAT|__GFP_NOWARN, huge_page_order(h));
if (page && arch_prepare_hugepage(page)) {
@@ -944,10 +1015,11 @@
*/
struct page *alloc_huge_page_node(struct hstate *h, int nid)
{
- struct page *page;
+ struct page *page = NULL;
spin_lock(&hugetlb_lock);
- page = dequeue_huge_page_node(h, nid);
+ if (h->free_huge_pages - h->resv_huge_pages > 0)
+ page = dequeue_huge_page_node(h, nid);
spin_unlock(&hugetlb_lock);
if (!page)
@@ -1035,11 +1107,8 @@
spin_unlock(&hugetlb_lock);
/* Free unnecessary surplus pages to the buddy allocator */
- if (!list_empty(&surplus_list)) {
- list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
- put_page(page);
- }
- }
+ list_for_each_entry_safe(page, tmp, &surplus_list, lru)
+ put_page(page);
spin_lock(&hugetlb_lock);
return ret;
@@ -1106,9 +1175,9 @@
} else {
long err;
pgoff_t idx = vma_hugecache_offset(h, vma, addr);
- struct resv_map *reservations = vma_resv_map(vma);
+ struct resv_map *resv = vma_resv_map(vma);
- err = region_chg(&reservations->regions, idx, idx + 1);
+ err = region_chg(&resv->regions, idx, idx + 1);
if (err < 0)
return err;
return 0;
@@ -1126,10 +1195,10 @@
} else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
pgoff_t idx = vma_hugecache_offset(h, vma, addr);
- struct resv_map *reservations = vma_resv_map(vma);
+ struct resv_map *resv = vma_resv_map(vma);
/* Mark this page used in the map. */
- region_add(&reservations->regions, idx, idx + 1);
+ region_add(&resv->regions, idx, idx + 1);
}
}
@@ -1155,38 +1224,35 @@
chg = vma_needs_reservation(h, vma, addr);
if (chg < 0)
return ERR_PTR(-ENOMEM);
- if (chg)
- if (hugepage_subpool_get_pages(spool, chg))
+ if (chg || avoid_reserve)
+ if (hugepage_subpool_get_pages(spool, 1))
return ERR_PTR(-ENOSPC);
ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg);
if (ret) {
- hugepage_subpool_put_pages(spool, chg);
+ if (chg || avoid_reserve)
+ hugepage_subpool_put_pages(spool, 1);
return ERR_PTR(-ENOSPC);
}
spin_lock(&hugetlb_lock);
- page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve);
- if (page) {
- /* update page cgroup details */
- hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h),
- h_cg, page);
- spin_unlock(&hugetlb_lock);
- } else {
+ page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve, chg);
+ if (!page) {
spin_unlock(&hugetlb_lock);
page = alloc_buddy_huge_page(h, NUMA_NO_NODE);
if (!page) {
hugetlb_cgroup_uncharge_cgroup(idx,
pages_per_huge_page(h),
h_cg);
- hugepage_subpool_put_pages(spool, chg);
+ if (chg || avoid_reserve)
+ hugepage_subpool_put_pages(spool, 1);
return ERR_PTR(-ENOSPC);
}
spin_lock(&hugetlb_lock);
- hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h),
- h_cg, page);
list_move(&page->lru, &h->hugepage_activelist);
- spin_unlock(&hugetlb_lock);
+ /* Fall through */
}
+ hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, page);
+ spin_unlock(&hugetlb_lock);
set_page_private(page, (unsigned long)spool);
@@ -1194,17 +1260,29 @@
return page;
}
+/*
+ * alloc_huge_page()'s wrapper which simply returns the page if allocation
+ * succeeds, otherwise NULL. This function is called from new_vma_page(),
+ * where no ERR_VALUE is expected to be returned.
+ */
+struct page *alloc_huge_page_noerr(struct vm_area_struct *vma,
+ unsigned long addr, int avoid_reserve)
+{
+ struct page *page = alloc_huge_page(vma, addr, avoid_reserve);
+ if (IS_ERR(page))
+ page = NULL;
+ return page;
+}
+
int __weak alloc_bootmem_huge_page(struct hstate *h)
{
struct huge_bootmem_page *m;
- int nr_nodes = nodes_weight(node_states[N_MEMORY]);
+ int nr_nodes, node;
- while (nr_nodes) {
+ for_each_node_mask_to_alloc(h, nr_nodes, node, &node_states[N_MEMORY]) {
void *addr;
- addr = __alloc_bootmem_node_nopanic(
- NODE_DATA(hstate_next_node_to_alloc(h,
- &node_states[N_MEMORY])),
+ addr = __alloc_bootmem_node_nopanic(NODE_DATA(node),
huge_page_size(h), huge_page_size(h), 0);
if (addr) {
@@ -1216,7 +1294,6 @@
m = addr;
goto found;
}
- nr_nodes--;
}
return 0;
@@ -1355,48 +1432,28 @@
static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed,
int delta)
{
- int start_nid, next_nid;
- int ret = 0;
+ int nr_nodes, node;
VM_BUG_ON(delta != -1 && delta != 1);
- if (delta < 0)
- start_nid = hstate_next_node_to_alloc(h, nodes_allowed);
- else
- start_nid = hstate_next_node_to_free(h, nodes_allowed);
- next_nid = start_nid;
-
- do {
- int nid = next_nid;
- if (delta < 0) {
- /*
- * To shrink on this node, there must be a surplus page
- */
- if (!h->surplus_huge_pages_node[nid]) {
- next_nid = hstate_next_node_to_alloc(h,
- nodes_allowed);
- continue;
- }
+ if (delta < 0) {
+ for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) {
+ if (h->surplus_huge_pages_node[node])
+ goto found;
}
- if (delta > 0) {
- /*
- * Surplus cannot exceed the total number of pages
- */
- if (h->surplus_huge_pages_node[nid] >=
- h->nr_huge_pages_node[nid]) {
- next_nid = hstate_next_node_to_free(h,
- nodes_allowed);
- continue;
- }
+ } else {
+ for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) {
+ if (h->surplus_huge_pages_node[node] <
+ h->nr_huge_pages_node[node])
+ goto found;
}
+ }
+ return 0;
- h->surplus_huge_pages += delta;
- h->surplus_huge_pages_node[nid] += delta;
- ret = 1;
- break;
- } while (next_nid != start_nid);
-
- return ret;
+found:
+ h->surplus_huge_pages += delta;
+ h->surplus_huge_pages_node[node] += delta;
+ return 1;
}
#define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages)
@@ -1526,7 +1583,7 @@
struct hstate *h;
NODEMASK_ALLOC(nodemask_t, nodes_allowed, GFP_KERNEL | __GFP_NORETRY);
- err = strict_strtoul(buf, 10, &count);
+ err = kstrtoul(buf, 10, &count);
if (err)
goto out;
@@ -1617,7 +1674,7 @@
if (h->order >= MAX_ORDER)
return -EINVAL;
- err = strict_strtoul(buf, 10, &input);
+ err = kstrtoul(buf, 10, &input);
if (err)
return err;
@@ -2068,18 +2125,6 @@
}
#endif /* CONFIG_NUMA */
-int hugetlb_treat_movable_handler(struct ctl_table *table, int write,
- void __user *buffer,
- size_t *length, loff_t *ppos)
-{
- proc_dointvec(table, write, buffer, length, ppos);
- if (hugepages_treat_as_movable)
- htlb_alloc_mask = GFP_HIGHUSER_MOVABLE;
- else
- htlb_alloc_mask = GFP_HIGHUSER;
- return 0;
-}
-
int hugetlb_overcommit_handler(struct ctl_table *table, int write,
void __user *buffer,
size_t *length, loff_t *ppos)
@@ -2207,7 +2252,7 @@
static void hugetlb_vm_op_open(struct vm_area_struct *vma)
{
- struct resv_map *reservations = vma_resv_map(vma);
+ struct resv_map *resv = vma_resv_map(vma);
/*
* This new VMA should share its siblings reservation map if present.
@@ -2217,34 +2262,34 @@
* after this open call completes. It is therefore safe to take a
* new reference here without additional locking.
*/
- if (reservations)
- kref_get(&reservations->refs);
+ if (resv)
+ kref_get(&resv->refs);
}
static void resv_map_put(struct vm_area_struct *vma)
{
- struct resv_map *reservations = vma_resv_map(vma);
+ struct resv_map *resv = vma_resv_map(vma);
- if (!reservations)
+ if (!resv)
return;
- kref_put(&reservations->refs, resv_map_release);
+ kref_put(&resv->refs, resv_map_release);
}
static void hugetlb_vm_op_close(struct vm_area_struct *vma)
{
struct hstate *h = hstate_vma(vma);
- struct resv_map *reservations = vma_resv_map(vma);
+ struct resv_map *resv = vma_resv_map(vma);
struct hugepage_subpool *spool = subpool_vma(vma);
unsigned long reserve;
unsigned long start;
unsigned long end;
- if (reservations) {
+ if (resv) {
start = vma_hugecache_offset(h, vma, vma->vm_start);
end = vma_hugecache_offset(h, vma, vma->vm_end);
reserve = (end - start) -
- region_count(&reservations->regions, start, end);
+ region_count(&resv->regions, start, end);
resv_map_put(vma);
@@ -2557,7 +2602,6 @@
{
struct hstate *h = hstate_vma(vma);
struct page *old_page, *new_page;
- int avoidcopy;
int outside_reserve = 0;
unsigned long mmun_start; /* For mmu_notifiers */
unsigned long mmun_end; /* For mmu_notifiers */
@@ -2567,10 +2611,8 @@
retry_avoidcopy:
/* If no-one else is actually using this page, avoid the copy
* and just make the page writable */
- avoidcopy = (page_mapcount(old_page) == 1);
- if (avoidcopy) {
- if (PageAnon(old_page))
- page_move_anon_rmap(old_page, vma, address);
+ if (page_mapcount(old_page) == 1 && PageAnon(old_page)) {
+ page_move_anon_rmap(old_page, vma, address);
set_huge_ptep_writable(vma, address, ptep);
return 0;
}
@@ -2584,8 +2626,7 @@
* at the time of fork() could consume its reserves on COW instead
* of the full address range.
*/
- if (!(vma->vm_flags & VM_MAYSHARE) &&
- is_vma_resv_set(vma, HPAGE_RESV_OWNER) &&
+ if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) &&
old_page != pagecache_page)
outside_reserve = 1;
@@ -2657,6 +2698,8 @@
spin_lock(&mm->page_table_lock);
ptep = huge_pte_offset(mm, address & huge_page_mask(h));
if (likely(pte_same(huge_ptep_get(ptep), pte))) {
+ ClearPagePrivate(new_page);
+
/* Break COW */
huge_ptep_clear_flush(vma, address, ptep);
set_huge_pte_at(mm, address, ptep,
@@ -2668,10 +2711,11 @@
}
spin_unlock(&mm->page_table_lock);
mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
- /* Caller expects lock to be held */
- spin_lock(&mm->page_table_lock);
page_cache_release(new_page);
page_cache_release(old_page);
+
+ /* Caller expects lock to be held */
+ spin_lock(&mm->page_table_lock);
return 0;
}
@@ -2767,6 +2811,7 @@
goto retry;
goto out;
}
+ ClearPagePrivate(page);
spin_lock(&inode->i_lock);
inode->i_blocks += blocks_per_huge_page(h);
@@ -2813,8 +2858,10 @@
if (!huge_pte_none(huge_ptep_get(ptep)))
goto backout;
- if (anon_rmap)
+ if (anon_rmap) {
+ ClearPagePrivate(page);
hugepage_add_new_anon_rmap(page, vma, address);
+ }
else
page_dup_rmap(page);
new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE)
@@ -3431,3 +3478,45 @@
return ret;
}
#endif
+
+bool isolate_huge_page(struct page *page, struct list_head *list)
+{
+ VM_BUG_ON(!PageHead(page));
+ if (!get_page_unless_zero(page))
+ return false;
+ spin_lock(&hugetlb_lock);
+ list_move_tail(&page->lru, list);
+ spin_unlock(&hugetlb_lock);
+ return true;
+}
+
+void putback_active_hugepage(struct page *page)
+{
+ VM_BUG_ON(!PageHead(page));
+ spin_lock(&hugetlb_lock);
+ list_move_tail(&page->lru, &(page_hstate(page))->hugepage_activelist);
+ spin_unlock(&hugetlb_lock);
+ put_page(page);
+}
+
+bool is_hugepage_active(struct page *page)
+{
+ VM_BUG_ON(!PageHuge(page));
+ /*
+ * This function can be called for a tail page because the caller,
+ * scan_movable_pages, scans through a given pfn-range which typically
+ * covers one memory block. In systems using gigantic hugepage (1GB
+ * for x86_64,) a hugepage is larger than a memory block, and we don't
+ * support migrating such large hugepages for now, so return false
+ * when called for tail pages.
+ */
+ if (PageTail(page))
+ return false;
+ /*
+ * Refcount of a hwpoisoned hugepages is 1, but they are not active,
+ * so we should return false for them.
+ */
+ if (unlikely(PageHWPoison(page)))
+ return false;
+ return page_count(page) > 0;
+}
diff --git a/mm/hwpoison-inject.c b/mm/hwpoison-inject.c
index 3a61efc..afc2daa 100644
--- a/mm/hwpoison-inject.c
+++ b/mm/hwpoison-inject.c
@@ -88,12 +88,12 @@
* hardware status change, hence do not require hardware support.
* They are mainly for testing hwpoison in software level.
*/
- dentry = debugfs_create_file("corrupt-pfn", 0600, hwpoison_dir,
+ dentry = debugfs_create_file("corrupt-pfn", 0200, hwpoison_dir,
NULL, &hwpoison_fops);
if (!dentry)
goto fail;
- dentry = debugfs_create_file("unpoison-pfn", 0600, hwpoison_dir,
+ dentry = debugfs_create_file("unpoison-pfn", 0200, hwpoison_dir,
NULL, &unpoison_fops);
if (!dentry)
goto fail;
diff --git a/mm/internal.h b/mm/internal.h
index 4390ac6..684f7aa 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -85,6 +85,8 @@
*/
extern int isolate_lru_page(struct page *page);
extern void putback_lru_page(struct page *page);
+extern unsigned long zone_reclaimable_pages(struct zone *zone);
+extern bool zone_reclaimable(struct zone *zone);
/*
* in mm/rmap.c:
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index c8d7f31..e126b0e 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1639,7 +1639,7 @@
else if (strncmp(buf, "scan=", 5) == 0) {
unsigned long secs;
- ret = strict_strtoul(buf + 5, 0, &secs);
+ ret = kstrtoul(buf + 5, 0, &secs);
if (ret < 0)
goto out;
stop_scan_thread();
diff --git a/mm/ksm.c b/mm/ksm.c
index b6afe0c..0bea2b2 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -2194,7 +2194,7 @@
unsigned long msecs;
int err;
- err = strict_strtoul(buf, 10, &msecs);
+ err = kstrtoul(buf, 10, &msecs);
if (err || msecs > UINT_MAX)
return -EINVAL;
@@ -2217,7 +2217,7 @@
int err;
unsigned long nr_pages;
- err = strict_strtoul(buf, 10, &nr_pages);
+ err = kstrtoul(buf, 10, &nr_pages);
if (err || nr_pages > UINT_MAX)
return -EINVAL;
@@ -2239,7 +2239,7 @@
int err;
unsigned long flags;
- err = strict_strtoul(buf, 10, &flags);
+ err = kstrtoul(buf, 10, &flags);
if (err || flags > UINT_MAX)
return -EINVAL;
if (flags > KSM_RUN_UNMERGE)
diff --git a/mm/list_lru.c b/mm/list_lru.c
new file mode 100644
index 0000000..7246791
--- /dev/null
+++ b/mm/list_lru.c
@@ -0,0 +1,139 @@
+/*
+ * Copyright (c) 2013 Red Hat, Inc. and Parallels Inc. All rights reserved.
+ * Authors: David Chinner and Glauber Costa
+ *
+ * Generic LRU infrastructure
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/list_lru.h>
+#include <linux/slab.h>
+
+bool list_lru_add(struct list_lru *lru, struct list_head *item)
+{
+ int nid = page_to_nid(virt_to_page(item));
+ struct list_lru_node *nlru = &lru->node[nid];
+
+ spin_lock(&nlru->lock);
+ WARN_ON_ONCE(nlru->nr_items < 0);
+ if (list_empty(item)) {
+ list_add_tail(item, &nlru->list);
+ if (nlru->nr_items++ == 0)
+ node_set(nid, lru->active_nodes);
+ spin_unlock(&nlru->lock);
+ return true;
+ }
+ spin_unlock(&nlru->lock);
+ return false;
+}
+EXPORT_SYMBOL_GPL(list_lru_add);
+
+bool list_lru_del(struct list_lru *lru, struct list_head *item)
+{
+ int nid = page_to_nid(virt_to_page(item));
+ struct list_lru_node *nlru = &lru->node[nid];
+
+ spin_lock(&nlru->lock);
+ if (!list_empty(item)) {
+ list_del_init(item);
+ if (--nlru->nr_items == 0)
+ node_clear(nid, lru->active_nodes);
+ WARN_ON_ONCE(nlru->nr_items < 0);
+ spin_unlock(&nlru->lock);
+ return true;
+ }
+ spin_unlock(&nlru->lock);
+ return false;
+}
+EXPORT_SYMBOL_GPL(list_lru_del);
+
+unsigned long
+list_lru_count_node(struct list_lru *lru, int nid)
+{
+ unsigned long count = 0;
+ struct list_lru_node *nlru = &lru->node[nid];
+
+ spin_lock(&nlru->lock);
+ WARN_ON_ONCE(nlru->nr_items < 0);
+ count += nlru->nr_items;
+ spin_unlock(&nlru->lock);
+
+ return count;
+}
+EXPORT_SYMBOL_GPL(list_lru_count_node);
+
+unsigned long
+list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate,
+ void *cb_arg, unsigned long *nr_to_walk)
+{
+
+ struct list_lru_node *nlru = &lru->node[nid];
+ struct list_head *item, *n;
+ unsigned long isolated = 0;
+
+ spin_lock(&nlru->lock);
+restart:
+ list_for_each_safe(item, n, &nlru->list) {
+ enum lru_status ret;
+
+ /*
+ * decrement nr_to_walk first so that we don't livelock if we
+ * get stuck on large numbesr of LRU_RETRY items
+ */
+ if (--(*nr_to_walk) == 0)
+ break;
+
+ ret = isolate(item, &nlru->lock, cb_arg);
+ switch (ret) {
+ case LRU_REMOVED:
+ if (--nlru->nr_items == 0)
+ node_clear(nid, lru->active_nodes);
+ WARN_ON_ONCE(nlru->nr_items < 0);
+ isolated++;
+ break;
+ case LRU_ROTATE:
+ list_move_tail(item, &nlru->list);
+ break;
+ case LRU_SKIP:
+ break;
+ case LRU_RETRY:
+ /*
+ * The lru lock has been dropped, our list traversal is
+ * now invalid and so we have to restart from scratch.
+ */
+ goto restart;
+ default:
+ BUG();
+ }
+ }
+
+ spin_unlock(&nlru->lock);
+ return isolated;
+}
+EXPORT_SYMBOL_GPL(list_lru_walk_node);
+
+int list_lru_init(struct list_lru *lru)
+{
+ int i;
+ size_t size = sizeof(*lru->node) * nr_node_ids;
+
+ lru->node = kzalloc(size, GFP_KERNEL);
+ if (!lru->node)
+ return -ENOMEM;
+
+ nodes_clear(lru->active_nodes);
+ for (i = 0; i < nr_node_ids; i++) {
+ spin_lock_init(&lru->node[i].lock);
+ INIT_LIST_HEAD(&lru->node[i].list);
+ lru->node[i].nr_items = 0;
+ }
+ return 0;
+}
+EXPORT_SYMBOL_GPL(list_lru_init);
+
+void list_lru_destroy(struct list_lru *lru)
+{
+ kfree(lru->node);
+}
+EXPORT_SYMBOL_GPL(list_lru_destroy);
diff --git a/mm/madvise.c b/mm/madvise.c
index 7055883..6975bc8 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -42,11 +42,11 @@
* We can potentially split a vm area into separate
* areas, each area with its own behavior.
*/
-static long madvise_behavior(struct vm_area_struct * vma,
+static long madvise_behavior(struct vm_area_struct *vma,
struct vm_area_struct **prev,
unsigned long start, unsigned long end, int behavior)
{
- struct mm_struct * mm = vma->vm_mm;
+ struct mm_struct *mm = vma->vm_mm;
int error = 0;
pgoff_t pgoff;
unsigned long new_flags = vma->vm_flags;
@@ -215,8 +215,8 @@
/*
* Schedule all required I/O operations. Do not wait for completion.
*/
-static long madvise_willneed(struct vm_area_struct * vma,
- struct vm_area_struct ** prev,
+static long madvise_willneed(struct vm_area_struct *vma,
+ struct vm_area_struct **prev,
unsigned long start, unsigned long end)
{
struct file *file = vma->vm_file;
@@ -270,8 +270,8 @@
* An interface that causes the system to free clean pages and flush
* dirty pages is already available as msync(MS_INVALIDATE).
*/
-static long madvise_dontneed(struct vm_area_struct * vma,
- struct vm_area_struct ** prev,
+static long madvise_dontneed(struct vm_area_struct *vma,
+ struct vm_area_struct **prev,
unsigned long start, unsigned long end)
{
*prev = vma;
@@ -343,29 +343,34 @@
*/
static int madvise_hwpoison(int bhv, unsigned long start, unsigned long end)
{
- int ret = 0;
-
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
for (; start < end; start += PAGE_SIZE) {
struct page *p;
- int ret = get_user_pages_fast(start, 1, 0, &p);
+ int ret;
+
+ ret = get_user_pages_fast(start, 1, 0, &p);
if (ret != 1)
return ret;
+
+ if (PageHWPoison(p)) {
+ put_page(p);
+ continue;
+ }
if (bhv == MADV_SOFT_OFFLINE) {
- printk(KERN_INFO "Soft offlining page %lx at %lx\n",
+ pr_info("Soft offlining page %#lx at %#lx\n",
page_to_pfn(p), start);
ret = soft_offline_page(p, MF_COUNT_INCREASED);
if (ret)
- break;
+ return ret;
continue;
}
- printk(KERN_INFO "Injecting memory failure for page %lx at %lx\n",
+ pr_info("Injecting memory failure for page %#lx at %#lx\n",
page_to_pfn(p), start);
/* Ignore return value for now */
memory_failure(page_to_pfn(p), 0, MF_COUNT_INCREASED);
}
- return ret;
+ return 0;
}
#endif
@@ -459,7 +464,7 @@
SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
{
unsigned long end, tmp;
- struct vm_area_struct * vma, *prev;
+ struct vm_area_struct *vma, *prev;
int unmapped_error = 0;
int error = -EINVAL;
int write;
diff --git a/mm/memblock.c b/mm/memblock.c
index a847bfe6..0ac412a 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -914,6 +914,24 @@
return memblock_search(&memblock.memory, addr) != -1;
}
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+int __init_memblock memblock_search_pfn_nid(unsigned long pfn,
+ unsigned long *start_pfn, unsigned long *end_pfn)
+{
+ struct memblock_type *type = &memblock.memory;
+ int mid = memblock_search(type, (phys_addr_t)pfn << PAGE_SHIFT);
+
+ if (mid == -1)
+ return -1;
+
+ *start_pfn = type->regions[mid].base >> PAGE_SHIFT;
+ *end_pfn = (type->regions[mid].base + type->regions[mid].size)
+ >> PAGE_SHIFT;
+
+ return type->regions[mid].nid;
+}
+#endif
+
/**
* memblock_is_region_memory - check if a region is a subset of memory
* @base: base of region to check
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 3b83957..d5ff3ce 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -39,7 +39,6 @@
#include <linux/limits.h>
#include <linux/export.h>
#include <linux/mutex.h>
-#include <linux/rbtree.h>
#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/swapops.h>
@@ -85,26 +84,12 @@
#endif
-/*
- * Statistics for memory cgroup.
- */
-enum mem_cgroup_stat_index {
- /*
- * For MEM_CONTAINER_TYPE_ALL, usage = pagecache + rss.
- */
- MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */
- MEM_CGROUP_STAT_RSS, /* # of pages charged as anon rss */
- MEM_CGROUP_STAT_RSS_HUGE, /* # of pages charged as anon huge */
- MEM_CGROUP_STAT_FILE_MAPPED, /* # of pages charged as file rss */
- MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */
- MEM_CGROUP_STAT_NSTATS,
-};
-
static const char * const mem_cgroup_stat_names[] = {
"cache",
"rss",
"rss_huge",
"mapped_file",
+ "writeback",
"swap",
};
@@ -175,10 +160,6 @@
struct mem_cgroup_reclaim_iter reclaim_iter[DEF_PRIORITY + 1];
- struct rb_node tree_node; /* RB tree node */
- unsigned long long usage_in_excess;/* Set to the value by which */
- /* the soft limit is exceeded*/
- bool on_tree;
struct mem_cgroup *memcg; /* Back pointer, we cannot */
/* use container_of */
};
@@ -187,26 +168,6 @@
struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES];
};
-/*
- * Cgroups above their limits are maintained in a RB-Tree, independent of
- * their hierarchy representation
- */
-
-struct mem_cgroup_tree_per_zone {
- struct rb_root rb_root;
- spinlock_t lock;
-};
-
-struct mem_cgroup_tree_per_node {
- struct mem_cgroup_tree_per_zone rb_tree_per_zone[MAX_NR_ZONES];
-};
-
-struct mem_cgroup_tree {
- struct mem_cgroup_tree_per_node *rb_tree_per_node[MAX_NUMNODES];
-};
-
-static struct mem_cgroup_tree soft_limit_tree __read_mostly;
-
struct mem_cgroup_threshold {
struct eventfd_ctx *eventfd;
u64 threshold;
@@ -280,6 +241,7 @@
bool oom_lock;
atomic_t under_oom;
+ atomic_t oom_wakeups;
int swappiness;
/* OOM-Killer disable */
@@ -304,7 +266,7 @@
* Should we move charges of a task when a task is moved into this
* mem_cgroup ? And what type of charges should we move ?
*/
- unsigned long move_charge_at_immigrate;
+ unsigned long move_charge_at_immigrate;
/*
* set > 0 if pages under this cgroup are moving to other cgroup.
*/
@@ -341,6 +303,22 @@
atomic_t numainfo_events;
atomic_t numainfo_updating;
#endif
+ /*
+ * Protects soft_contributed transitions.
+ * See mem_cgroup_update_soft_limit
+ */
+ spinlock_t soft_lock;
+
+ /*
+ * If true then this group has increased parents' children_in_excess
+ * when it got over the soft limit.
+ * When a group falls bellow the soft limit, parents' children_in_excess
+ * is decreased and soft_contributed changed to false.
+ */
+ bool soft_contributed;
+
+ /* Number of children that are in soft limit excess */
+ atomic_t children_in_excess;
struct mem_cgroup_per_node *nodeinfo[0];
/* WARNING: nodeinfo must be the last member here */
@@ -444,7 +422,6 @@
* limit reclaim to prevent infinite loops, if they ever occur.
*/
#define MEM_CGROUP_MAX_RECLAIM_LOOPS 100
-#define MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS 2
enum charge_type {
MEM_CGROUP_CHARGE_TYPE_CACHE = 0,
@@ -671,164 +648,6 @@
return mem_cgroup_zoneinfo(memcg, nid, zid);
}
-static struct mem_cgroup_tree_per_zone *
-soft_limit_tree_node_zone(int nid, int zid)
-{
- return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid];
-}
-
-static struct mem_cgroup_tree_per_zone *
-soft_limit_tree_from_page(struct page *page)
-{
- int nid = page_to_nid(page);
- int zid = page_zonenum(page);
-
- return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid];
-}
-
-static void
-__mem_cgroup_insert_exceeded(struct mem_cgroup *memcg,
- struct mem_cgroup_per_zone *mz,
- struct mem_cgroup_tree_per_zone *mctz,
- unsigned long long new_usage_in_excess)
-{
- struct rb_node **p = &mctz->rb_root.rb_node;
- struct rb_node *parent = NULL;
- struct mem_cgroup_per_zone *mz_node;
-
- if (mz->on_tree)
- return;
-
- mz->usage_in_excess = new_usage_in_excess;
- if (!mz->usage_in_excess)
- return;
- while (*p) {
- parent = *p;
- mz_node = rb_entry(parent, struct mem_cgroup_per_zone,
- tree_node);
- if (mz->usage_in_excess < mz_node->usage_in_excess)
- p = &(*p)->rb_left;
- /*
- * We can't avoid mem cgroups that are over their soft
- * limit by the same amount
- */
- else if (mz->usage_in_excess >= mz_node->usage_in_excess)
- p = &(*p)->rb_right;
- }
- rb_link_node(&mz->tree_node, parent, p);
- rb_insert_color(&mz->tree_node, &mctz->rb_root);
- mz->on_tree = true;
-}
-
-static void
-__mem_cgroup_remove_exceeded(struct mem_cgroup *memcg,
- struct mem_cgroup_per_zone *mz,
- struct mem_cgroup_tree_per_zone *mctz)
-{
- if (!mz->on_tree)
- return;
- rb_erase(&mz->tree_node, &mctz->rb_root);
- mz->on_tree = false;
-}
-
-static void
-mem_cgroup_remove_exceeded(struct mem_cgroup *memcg,
- struct mem_cgroup_per_zone *mz,
- struct mem_cgroup_tree_per_zone *mctz)
-{
- spin_lock(&mctz->lock);
- __mem_cgroup_remove_exceeded(memcg, mz, mctz);
- spin_unlock(&mctz->lock);
-}
-
-
-static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
-{
- unsigned long long excess;
- struct mem_cgroup_per_zone *mz;
- struct mem_cgroup_tree_per_zone *mctz;
- int nid = page_to_nid(page);
- int zid = page_zonenum(page);
- mctz = soft_limit_tree_from_page(page);
-
- /*
- * Necessary to update all ancestors when hierarchy is used.
- * because their event counter is not touched.
- */
- for (; memcg; memcg = parent_mem_cgroup(memcg)) {
- mz = mem_cgroup_zoneinfo(memcg, nid, zid);
- excess = res_counter_soft_limit_excess(&memcg->res);
- /*
- * We have to update the tree if mz is on RB-tree or
- * mem is over its softlimit.
- */
- if (excess || mz->on_tree) {
- spin_lock(&mctz->lock);
- /* if on-tree, remove it */
- if (mz->on_tree)
- __mem_cgroup_remove_exceeded(memcg, mz, mctz);
- /*
- * Insert again. mz->usage_in_excess will be updated.
- * If excess is 0, no tree ops.
- */
- __mem_cgroup_insert_exceeded(memcg, mz, mctz, excess);
- spin_unlock(&mctz->lock);
- }
- }
-}
-
-static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg)
-{
- int node, zone;
- struct mem_cgroup_per_zone *mz;
- struct mem_cgroup_tree_per_zone *mctz;
-
- for_each_node(node) {
- for (zone = 0; zone < MAX_NR_ZONES; zone++) {
- mz = mem_cgroup_zoneinfo(memcg, node, zone);
- mctz = soft_limit_tree_node_zone(node, zone);
- mem_cgroup_remove_exceeded(memcg, mz, mctz);
- }
- }
-}
-
-static struct mem_cgroup_per_zone *
-__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
-{
- struct rb_node *rightmost = NULL;
- struct mem_cgroup_per_zone *mz;
-
-retry:
- mz = NULL;
- rightmost = rb_last(&mctz->rb_root);
- if (!rightmost)
- goto done; /* Nothing to reclaim from */
-
- mz = rb_entry(rightmost, struct mem_cgroup_per_zone, tree_node);
- /*
- * Remove the node now but someone else can add it back,
- * we will to add it back at the end of reclaim to its correct
- * position in the tree.
- */
- __mem_cgroup_remove_exceeded(mz->memcg, mz, mctz);
- if (!res_counter_soft_limit_excess(&mz->memcg->res) ||
- !css_tryget(&mz->memcg->css))
- goto retry;
-done:
- return mz;
-}
-
-static struct mem_cgroup_per_zone *
-mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
-{
- struct mem_cgroup_per_zone *mz;
-
- spin_lock(&mctz->lock);
- mz = __mem_cgroup_largest_soft_limit_node(mctz);
- spin_unlock(&mctz->lock);
- return mz;
-}
-
/*
* Implementation Note: reading percpu statistics for memcg.
*
@@ -1003,6 +822,48 @@
}
/*
+ * Called from rate-limited memcg_check_events when enough
+ * MEM_CGROUP_TARGET_SOFTLIMIT events are accumulated and it makes sure
+ * that all the parents up the hierarchy will be notified that this group
+ * is in excess or that it is not in excess anymore. mmecg->soft_contributed
+ * makes the transition a single action whenever the state flips from one to
+ * the other.
+ */
+static void mem_cgroup_update_soft_limit(struct mem_cgroup *memcg)
+{
+ unsigned long long excess = res_counter_soft_limit_excess(&memcg->res);
+ struct mem_cgroup *parent = memcg;
+ int delta = 0;
+
+ spin_lock(&memcg->soft_lock);
+ if (excess) {
+ if (!memcg->soft_contributed) {
+ delta = 1;
+ memcg->soft_contributed = true;
+ }
+ } else {
+ if (memcg->soft_contributed) {
+ delta = -1;
+ memcg->soft_contributed = false;
+ }
+ }
+
+ /*
+ * Necessary to update all ancestors when hierarchy is used
+ * because their event counter is not touched.
+ * We track children even outside the hierarchy for the root
+ * cgroup because tree walk starting at root should visit
+ * all cgroups and we want to prevent from pointless tree
+ * walk if no children is below the limit.
+ */
+ while (delta && (parent = parent_mem_cgroup(parent)))
+ atomic_add(delta, &parent->children_in_excess);
+ if (memcg != root_mem_cgroup && !root_mem_cgroup->use_hierarchy)
+ atomic_add(delta, &root_mem_cgroup->children_in_excess);
+ spin_unlock(&memcg->soft_lock);
+}
+
+/*
* Check events in order.
*
*/
@@ -1025,7 +886,7 @@
mem_cgroup_threshold(memcg);
if (unlikely(do_softlimit))
- mem_cgroup_update_tree(memcg, page);
+ mem_cgroup_update_soft_limit(memcg);
#if MAX_NUMNODES > 1
if (unlikely(do_numainfo))
atomic_inc(&memcg->numainfo_events);
@@ -1068,6 +929,15 @@
return memcg;
}
+static enum mem_cgroup_filter_t
+mem_cgroup_filter(struct mem_cgroup *memcg, struct mem_cgroup *root,
+ mem_cgroup_iter_filter cond)
+{
+ if (!cond)
+ return VISIT;
+ return cond(memcg, root);
+}
+
/*
* Returns a next (in a pre-order walk) alive memcg (with elevated css
* ref. count) or NULL if the whole root's subtree has been visited.
@@ -1075,7 +945,7 @@
* helper function to be used by mem_cgroup_iter
*/
static struct mem_cgroup *__mem_cgroup_iter_next(struct mem_cgroup *root,
- struct mem_cgroup *last_visited)
+ struct mem_cgroup *last_visited, mem_cgroup_iter_filter cond)
{
struct cgroup_subsys_state *prev_css, *next_css;
@@ -1093,11 +963,31 @@
if (next_css) {
struct mem_cgroup *mem = mem_cgroup_from_css(next_css);
- if (css_tryget(&mem->css))
- return mem;
- else {
+ switch (mem_cgroup_filter(mem, root, cond)) {
+ case SKIP:
prev_css = next_css;
goto skip_node;
+ case SKIP_TREE:
+ if (mem == root)
+ return NULL;
+ /*
+ * css_rightmost_descendant is not an optimal way to
+ * skip through a subtree (especially for imbalanced
+ * trees leaning to right) but that's what we have right
+ * now. More effective solution would be traversing
+ * right-up for first non-NULL without calling
+ * css_next_descendant_pre afterwards.
+ */
+ prev_css = css_rightmost_descendant(next_css);
+ goto skip_node;
+ case VISIT:
+ if (css_tryget(&mem->css))
+ return mem;
+ else {
+ prev_css = next_css;
+ goto skip_node;
+ }
+ break;
}
}
@@ -1161,6 +1051,7 @@
* @root: hierarchy root
* @prev: previously returned memcg, NULL on first invocation
* @reclaim: cookie for shared reclaim walks, NULL for full walks
+ * @cond: filter for visited nodes, NULL for no filter
*
* Returns references to children of the hierarchy below @root, or
* @root itself, or %NULL after a full round-trip.
@@ -1173,15 +1064,18 @@
* divide up the memcgs in the hierarchy among all concurrent
* reclaimers operating on the same zone and priority.
*/
-struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
+struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root,
struct mem_cgroup *prev,
- struct mem_cgroup_reclaim_cookie *reclaim)
+ struct mem_cgroup_reclaim_cookie *reclaim,
+ mem_cgroup_iter_filter cond)
{
struct mem_cgroup *memcg = NULL;
struct mem_cgroup *last_visited = NULL;
- if (mem_cgroup_disabled())
- return NULL;
+ if (mem_cgroup_disabled()) {
+ /* first call must return non-NULL, second return NULL */
+ return (struct mem_cgroup *)(unsigned long)!prev;
+ }
if (!root)
root = root_mem_cgroup;
@@ -1192,7 +1086,9 @@
if (!root->use_hierarchy && root != root_mem_cgroup) {
if (prev)
goto out_css_put;
- return root;
+ if (mem_cgroup_filter(root, root, cond) == VISIT)
+ return root;
+ return NULL;
}
rcu_read_lock();
@@ -1215,7 +1111,7 @@
last_visited = mem_cgroup_iter_load(iter, root, &seq);
}
- memcg = __mem_cgroup_iter_next(root, last_visited);
+ memcg = __mem_cgroup_iter_next(root, last_visited, cond);
if (reclaim) {
mem_cgroup_iter_update(iter, last_visited, memcg, seq);
@@ -1226,7 +1122,11 @@
reclaim->generation = iter->generation;
}
- if (prev && !memcg)
+ /*
+ * We have finished the whole tree walk or no group has been
+ * visited because filter told us to skip the root node.
+ */
+ if (!memcg && (prev || (cond && !last_visited)))
goto out_unlock;
}
out_unlock:
@@ -1867,6 +1767,7 @@
return total;
}
+#if MAX_NUMNODES > 1
/**
* test_mem_cgroup_node_reclaimable
* @memcg: the target memcg
@@ -1889,7 +1790,6 @@
return false;
}
-#if MAX_NUMNODES > 1
/*
* Always updating the nodemask is not very good - even if we have an empty
@@ -1957,115 +1857,64 @@
return node;
}
-/*
- * Check all nodes whether it contains reclaimable pages or not.
- * For quick scan, we make use of scan_nodes. This will allow us to skip
- * unused nodes. But scan_nodes is lazily updated and may not cotain
- * enough new information. We need to do double check.
- */
-static bool mem_cgroup_reclaimable(struct mem_cgroup *memcg, bool noswap)
-{
- int nid;
-
- /*
- * quick check...making use of scan_node.
- * We can skip unused nodes.
- */
- if (!nodes_empty(memcg->scan_nodes)) {
- for (nid = first_node(memcg->scan_nodes);
- nid < MAX_NUMNODES;
- nid = next_node(nid, memcg->scan_nodes)) {
-
- if (test_mem_cgroup_node_reclaimable(memcg, nid, noswap))
- return true;
- }
- }
- /*
- * Check rest of nodes.
- */
- for_each_node_state(nid, N_MEMORY) {
- if (node_isset(nid, memcg->scan_nodes))
- continue;
- if (test_mem_cgroup_node_reclaimable(memcg, nid, noswap))
- return true;
- }
- return false;
-}
-
#else
int mem_cgroup_select_victim_node(struct mem_cgroup *memcg)
{
return 0;
}
-static bool mem_cgroup_reclaimable(struct mem_cgroup *memcg, bool noswap)
-{
- return test_mem_cgroup_node_reclaimable(memcg, 0, noswap);
-}
#endif
-static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
- struct zone *zone,
- gfp_t gfp_mask,
- unsigned long *total_scanned)
+/*
+ * A group is eligible for the soft limit reclaim under the given root
+ * hierarchy if
+ * a) it is over its soft limit
+ * b) any parent up the hierarchy is over its soft limit
+ *
+ * If the given group doesn't have any children over the limit then it
+ * doesn't make any sense to iterate its subtree.
+ */
+enum mem_cgroup_filter_t
+mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg,
+ struct mem_cgroup *root)
{
- struct mem_cgroup *victim = NULL;
- int total = 0;
- int loop = 0;
- unsigned long excess;
- unsigned long nr_scanned;
- struct mem_cgroup_reclaim_cookie reclaim = {
- .zone = zone,
- .priority = 0,
- };
+ struct mem_cgroup *parent;
- excess = res_counter_soft_limit_excess(&root_memcg->res) >> PAGE_SHIFT;
+ if (!memcg)
+ memcg = root_mem_cgroup;
+ parent = memcg;
- while (1) {
- victim = mem_cgroup_iter(root_memcg, victim, &reclaim);
- if (!victim) {
- loop++;
- if (loop >= 2) {
- /*
- * If we have not been able to reclaim
- * anything, it might because there are
- * no reclaimable pages under this hierarchy
- */
- if (!total)
- break;
- /*
- * We want to do more targeted reclaim.
- * excess >> 2 is not to excessive so as to
- * reclaim too much, nor too less that we keep
- * coming back to reclaim from this cgroup
- */
- if (total >= (excess >> 2) ||
- (loop > MEM_CGROUP_MAX_RECLAIM_LOOPS))
- break;
- }
- continue;
- }
- if (!mem_cgroup_reclaimable(victim, false))
- continue;
- total += mem_cgroup_shrink_node_zone(victim, gfp_mask, false,
- zone, &nr_scanned);
- *total_scanned += nr_scanned;
- if (!res_counter_soft_limit_excess(&root_memcg->res))
+ if (res_counter_soft_limit_excess(&memcg->res))
+ return VISIT;
+
+ /*
+ * If any parent up to the root in the hierarchy is over its soft limit
+ * then we have to obey and reclaim from this group as well.
+ */
+ while ((parent = parent_mem_cgroup(parent))) {
+ if (res_counter_soft_limit_excess(&parent->res))
+ return VISIT;
+ if (parent == root)
break;
}
- mem_cgroup_iter_break(root_memcg, victim);
- return total;
+
+ if (!atomic_read(&memcg->children_in_excess))
+ return SKIP_TREE;
+ return SKIP;
}
+static DEFINE_SPINLOCK(memcg_oom_lock);
+
/*
* Check OOM-Killer is already running under our hierarchy.
* If someone is running, return false.
- * Has to be called with memcg_oom_lock
*/
-static bool mem_cgroup_oom_lock(struct mem_cgroup *memcg)
+static bool mem_cgroup_oom_trylock(struct mem_cgroup *memcg)
{
struct mem_cgroup *iter, *failed = NULL;
+ spin_lock(&memcg_oom_lock);
+
for_each_mem_cgroup_tree(iter, memcg) {
if (iter->oom_lock) {
/*
@@ -2079,33 +1928,33 @@
iter->oom_lock = true;
}
- if (!failed)
- return true;
-
- /*
- * OK, we failed to lock the whole subtree so we have to clean up
- * what we set up to the failing subtree
- */
- for_each_mem_cgroup_tree(iter, memcg) {
- if (iter == failed) {
- mem_cgroup_iter_break(memcg, iter);
- break;
+ if (failed) {
+ /*
+ * OK, we failed to lock the whole subtree so we have
+ * to clean up what we set up to the failing subtree
+ */
+ for_each_mem_cgroup_tree(iter, memcg) {
+ if (iter == failed) {
+ mem_cgroup_iter_break(memcg, iter);
+ break;
+ }
+ iter->oom_lock = false;
}
- iter->oom_lock = false;
}
- return false;
+
+ spin_unlock(&memcg_oom_lock);
+
+ return !failed;
}
-/*
- * Has to be called with memcg_oom_lock
- */
-static int mem_cgroup_oom_unlock(struct mem_cgroup *memcg)
+static void mem_cgroup_oom_unlock(struct mem_cgroup *memcg)
{
struct mem_cgroup *iter;
+ spin_lock(&memcg_oom_lock);
for_each_mem_cgroup_tree(iter, memcg)
iter->oom_lock = false;
- return 0;
+ spin_unlock(&memcg_oom_lock);
}
static void mem_cgroup_mark_under_oom(struct mem_cgroup *memcg)
@@ -2129,7 +1978,6 @@
atomic_add_unless(&iter->under_oom, -1, 0);
}
-static DEFINE_SPINLOCK(memcg_oom_lock);
static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq);
struct oom_wait_info {
@@ -2159,6 +2007,7 @@
static void memcg_wakeup_oom(struct mem_cgroup *memcg)
{
+ atomic_inc(&memcg->oom_wakeups);
/* for filtering, pass "memcg" as argument. */
__wake_up(&memcg_oom_waitq, TASK_NORMAL, 0, memcg);
}
@@ -2170,56 +2019,136 @@
}
/*
- * try to call OOM killer. returns false if we should exit memory-reclaim loop.
+ * try to call OOM killer
*/
-static bool mem_cgroup_handle_oom(struct mem_cgroup *memcg, gfp_t mask,
- int order)
+static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
+{
+ bool locked;
+ int wakeups;
+
+ if (!current->memcg_oom.may_oom)
+ return;
+
+ current->memcg_oom.in_memcg_oom = 1;
+
+ /*
+ * As with any blocking lock, a contender needs to start
+ * listening for wakeups before attempting the trylock,
+ * otherwise it can miss the wakeup from the unlock and sleep
+ * indefinitely. This is just open-coded because our locking
+ * is so particular to memcg hierarchies.
+ */
+ wakeups = atomic_read(&memcg->oom_wakeups);
+ mem_cgroup_mark_under_oom(memcg);
+
+ locked = mem_cgroup_oom_trylock(memcg);
+
+ if (locked)
+ mem_cgroup_oom_notify(memcg);
+
+ if (locked && !memcg->oom_kill_disable) {
+ mem_cgroup_unmark_under_oom(memcg);
+ mem_cgroup_out_of_memory(memcg, mask, order);
+ mem_cgroup_oom_unlock(memcg);
+ /*
+ * There is no guarantee that an OOM-lock contender
+ * sees the wakeups triggered by the OOM kill
+ * uncharges. Wake any sleepers explicitely.
+ */
+ memcg_oom_recover(memcg);
+ } else {
+ /*
+ * A system call can just return -ENOMEM, but if this
+ * is a page fault and somebody else is handling the
+ * OOM already, we need to sleep on the OOM waitqueue
+ * for this memcg until the situation is resolved.
+ * Which can take some time because it might be
+ * handled by a userspace task.
+ *
+ * However, this is the charge context, which means
+ * that we may sit on a large call stack and hold
+ * various filesystem locks, the mmap_sem etc. and we
+ * don't want the OOM handler to deadlock on them
+ * while we sit here and wait. Store the current OOM
+ * context in the task_struct, then return -ENOMEM.
+ * At the end of the page fault handler, with the
+ * stack unwound, pagefault_out_of_memory() will check
+ * back with us by calling
+ * mem_cgroup_oom_synchronize(), possibly putting the
+ * task to sleep.
+ */
+ current->memcg_oom.oom_locked = locked;
+ current->memcg_oom.wakeups = wakeups;
+ css_get(&memcg->css);
+ current->memcg_oom.wait_on_memcg = memcg;
+ }
+}
+
+/**
+ * mem_cgroup_oom_synchronize - complete memcg OOM handling
+ *
+ * This has to be called at the end of a page fault if the the memcg
+ * OOM handler was enabled and the fault is returning %VM_FAULT_OOM.
+ *
+ * Memcg supports userspace OOM handling, so failed allocations must
+ * sleep on a waitqueue until the userspace task resolves the
+ * situation. Sleeping directly in the charge context with all kinds
+ * of locks held is not a good idea, instead we remember an OOM state
+ * in the task and mem_cgroup_oom_synchronize() has to be called at
+ * the end of the page fault to put the task to sleep and clean up the
+ * OOM state.
+ *
+ * Returns %true if an ongoing memcg OOM situation was detected and
+ * finalized, %false otherwise.
+ */
+bool mem_cgroup_oom_synchronize(void)
{
struct oom_wait_info owait;
- bool locked, need_to_kill;
+ struct mem_cgroup *memcg;
+
+ /* OOM is global, do not handle */
+ if (!current->memcg_oom.in_memcg_oom)
+ return false;
+
+ /*
+ * We invoked the OOM killer but there is a chance that a kill
+ * did not free up any charges. Everybody else might already
+ * be sleeping, so restart the fault and keep the rampage
+ * going until some charges are released.
+ */
+ memcg = current->memcg_oom.wait_on_memcg;
+ if (!memcg)
+ goto out;
+
+ if (test_thread_flag(TIF_MEMDIE) || fatal_signal_pending(current))
+ goto out_memcg;
owait.memcg = memcg;
owait.wait.flags = 0;
owait.wait.func = memcg_oom_wake_function;
owait.wait.private = current;
INIT_LIST_HEAD(&owait.wait.task_list);
- need_to_kill = true;
- mem_cgroup_mark_under_oom(memcg);
- /* At first, try to OOM lock hierarchy under memcg.*/
- spin_lock(&memcg_oom_lock);
- locked = mem_cgroup_oom_lock(memcg);
- /*
- * Even if signal_pending(), we can't quit charge() loop without
- * accounting. So, UNINTERRUPTIBLE is appropriate. But SIGKILL
- * under OOM is always welcomed, use TASK_KILLABLE here.
- */
prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE);
- if (!locked || memcg->oom_kill_disable)
- need_to_kill = false;
- if (locked)
- mem_cgroup_oom_notify(memcg);
- spin_unlock(&memcg_oom_lock);
-
- if (need_to_kill) {
- finish_wait(&memcg_oom_waitq, &owait.wait);
- mem_cgroup_out_of_memory(memcg, mask, order);
- } else {
+ /* Only sleep if we didn't miss any wakeups since OOM */
+ if (atomic_read(&memcg->oom_wakeups) == current->memcg_oom.wakeups)
schedule();
- finish_wait(&memcg_oom_waitq, &owait.wait);
- }
- spin_lock(&memcg_oom_lock);
- if (locked)
- mem_cgroup_oom_unlock(memcg);
- memcg_wakeup_oom(memcg);
- spin_unlock(&memcg_oom_lock);
-
+ finish_wait(&memcg_oom_waitq, &owait.wait);
+out_memcg:
mem_cgroup_unmark_under_oom(memcg);
-
- if (test_thread_flag(TIF_MEMDIE) || fatal_signal_pending(current))
- return false;
- /* Give chance to dying process */
- schedule_timeout_uninterruptible(1);
+ if (current->memcg_oom.oom_locked) {
+ mem_cgroup_oom_unlock(memcg);
+ /*
+ * There is no guarantee that an OOM-lock contender
+ * sees the wakeups triggered by the OOM kill
+ * uncharges. Wake any sleepers explicitely.
+ */
+ memcg_oom_recover(memcg);
+ }
+ css_put(&memcg->css);
+ current->memcg_oom.wait_on_memcg = NULL;
+out:
+ current->memcg_oom.in_memcg_oom = 0;
return true;
}
@@ -2288,7 +2217,7 @@
}
void mem_cgroup_update_page_stat(struct page *page,
- enum mem_cgroup_page_stat_item idx, int val)
+ enum mem_cgroup_stat_index idx, int val)
{
struct mem_cgroup *memcg;
struct page_cgroup *pc = lookup_page_cgroup(page);
@@ -2297,18 +2226,11 @@
if (mem_cgroup_disabled())
return;
+ VM_BUG_ON(!rcu_read_lock_held());
memcg = pc->mem_cgroup;
if (unlikely(!memcg || !PageCgroupUsed(pc)))
return;
- switch (idx) {
- case MEMCG_NR_FILE_MAPPED:
- idx = MEM_CGROUP_STAT_FILE_MAPPED;
- break;
- default:
- BUG();
- }
-
this_cpu_add(memcg->stat->count[idx], val);
}
@@ -2450,7 +2372,7 @@
flush_work(&stock->work);
}
out:
- put_online_cpus();
+ put_online_cpus();
}
/*
@@ -2532,12 +2454,11 @@
CHARGE_RETRY, /* need to retry but retry is not bad */
CHARGE_NOMEM, /* we can't do more. return -ENOMEM */
CHARGE_WOULDBLOCK, /* GFP_WAIT wasn't set and no enough res. */
- CHARGE_OOM_DIE, /* the current is killed because of OOM */
};
static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
unsigned int nr_pages, unsigned int min_pages,
- bool oom_check)
+ bool invoke_oom)
{
unsigned long csize = nr_pages * PAGE_SIZE;
struct mem_cgroup *mem_over_limit;
@@ -2594,14 +2515,10 @@
if (mem_cgroup_wait_acct_move(mem_over_limit))
return CHARGE_RETRY;
- /* If we don't need to call oom-killer at el, return immediately */
- if (!oom_check)
- return CHARGE_NOMEM;
- /* check OOM */
- if (!mem_cgroup_handle_oom(mem_over_limit, gfp_mask, get_order(csize)))
- return CHARGE_OOM_DIE;
+ if (invoke_oom)
+ mem_cgroup_oom(mem_over_limit, gfp_mask, get_order(csize));
- return CHARGE_RETRY;
+ return CHARGE_NOMEM;
}
/*
@@ -2704,7 +2621,7 @@
}
do {
- bool oom_check;
+ bool invoke_oom = oom && !nr_oom_retries;
/* If killed, bypass charge */
if (fatal_signal_pending(current)) {
@@ -2712,14 +2629,8 @@
goto bypass;
}
- oom_check = false;
- if (oom && !nr_oom_retries) {
- oom_check = true;
- nr_oom_retries = MEM_CGROUP_RECLAIM_RETRIES;
- }
-
- ret = mem_cgroup_do_charge(memcg, gfp_mask, batch, nr_pages,
- oom_check);
+ ret = mem_cgroup_do_charge(memcg, gfp_mask, batch,
+ nr_pages, invoke_oom);
switch (ret) {
case CHARGE_OK:
break;
@@ -2732,16 +2643,12 @@
css_put(&memcg->css);
goto nomem;
case CHARGE_NOMEM: /* OOM routine works */
- if (!oom) {
+ if (!oom || invoke_oom) {
css_put(&memcg->css);
goto nomem;
}
- /* If oom, we never return -ENOMEM */
nr_oom_retries--;
break;
- case CHARGE_OOM_DIE: /* Killed by OOM Killer */
- css_put(&memcg->css);
- goto bypass;
}
} while (ret != CHARGE_OK);
@@ -2882,7 +2789,7 @@
* is accessed after testing USED bit. To make pc->mem_cgroup visible
* before USED bit, we need memory barrier here.
* See mem_cgroup_add_lru_list(), etc.
- */
+ */
smp_wmb();
SetPageCgroupUsed(pc);
@@ -2905,9 +2812,7 @@
unlock_page_cgroup(pc);
/*
- * "charge_statistics" updated event counter. Then, check it.
- * Insert ancestor (and ancestor's ancestors), to softlimit RB-tree.
- * if they exceeds softlimit.
+ * "charge_statistics" updated event counter.
*/
memcg_check_events(memcg, page);
}
@@ -3121,7 +3026,7 @@
ssize_t size = memcg_caches_array_size(num_groups);
size *= sizeof(void *);
- size += sizeof(struct memcg_cache_params);
+ size += offsetof(struct memcg_cache_params, memcg_caches);
s->memcg_params = kzalloc(size, GFP_KERNEL);
if (!s->memcg_params) {
@@ -3164,13 +3069,16 @@
int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s,
struct kmem_cache *root_cache)
{
- size_t size = sizeof(struct memcg_cache_params);
+ size_t size;
if (!memcg_kmem_enabled())
return 0;
- if (!memcg)
+ if (!memcg) {
+ size = offsetof(struct memcg_cache_params, memcg_caches);
size += memcg_limited_groups_array_size * sizeof(void *);
+ } else
+ size = sizeof(struct memcg_cache_params);
s->memcg_params = kzalloc(size, GFP_KERNEL);
if (!s->memcg_params)
@@ -3623,9 +3531,9 @@
* the page allocator. Therefore, the following sequence when backed by
* the SLUB allocator:
*
- * memcg_stop_kmem_account();
- * kmalloc(<large_number>)
- * memcg_resume_kmem_account();
+ * memcg_stop_kmem_account();
+ * kmalloc(<large_number>)
+ * memcg_resume_kmem_account();
*
* would effectively ignore the fact that we should skip accounting,
* since it will drive us directly to this function without passing
@@ -3747,6 +3655,20 @@
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+static inline
+void mem_cgroup_move_account_page_stat(struct mem_cgroup *from,
+ struct mem_cgroup *to,
+ unsigned int nr_pages,
+ enum mem_cgroup_stat_index idx)
+{
+ /* Update stat data for mem_cgroup */
+ preempt_disable();
+ WARN_ON_ONCE(from->stat->count[idx] < nr_pages);
+ __this_cpu_add(from->stat->count[idx], -nr_pages);
+ __this_cpu_add(to->stat->count[idx], nr_pages);
+ preempt_enable();
+}
+
/**
* mem_cgroup_move_account - move account of the page
* @page: the page
@@ -3792,13 +3714,14 @@
move_lock_mem_cgroup(from, &flags);
- if (!anon && page_mapped(page)) {
- /* Update mapped_file data for mem_cgroup */
- preempt_disable();
- __this_cpu_dec(from->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
- __this_cpu_inc(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
- preempt_enable();
- }
+ if (!anon && page_mapped(page))
+ mem_cgroup_move_account_page_stat(from, to, nr_pages,
+ MEM_CGROUP_STAT_FILE_MAPPED);
+
+ if (PageWriteback(page))
+ mem_cgroup_move_account_page_stat(from, to, nr_pages,
+ MEM_CGROUP_STAT_WRITEBACK);
+
mem_cgroup_charge_statistics(from, page, anon, -nr_pages);
/* caller should have done css_get */
@@ -4654,7 +4577,7 @@
MEM_CGROUP_RECLAIM_SHRINK);
curusage = res_counter_read_u64(&memcg->res, RES_USAGE);
/* Usage is reduced ? */
- if (curusage >= oldusage)
+ if (curusage >= oldusage)
retry_count--;
else
oldusage = curusage;
@@ -4675,7 +4598,7 @@
int enlarge = 0;
/* see mem_cgroup_resize_res_limit */
- retry_count = children * MEM_CGROUP_RECLAIM_RETRIES;
+ retry_count = children * MEM_CGROUP_RECLAIM_RETRIES;
oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
while (retry_count) {
if (signal_pending(current)) {
@@ -4724,98 +4647,6 @@
return ret;
}
-unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
- gfp_t gfp_mask,
- unsigned long *total_scanned)
-{
- unsigned long nr_reclaimed = 0;
- struct mem_cgroup_per_zone *mz, *next_mz = NULL;
- unsigned long reclaimed;
- int loop = 0;
- struct mem_cgroup_tree_per_zone *mctz;
- unsigned long long excess;
- unsigned long nr_scanned;
-
- if (order > 0)
- return 0;
-
- mctz = soft_limit_tree_node_zone(zone_to_nid(zone), zone_idx(zone));
- /*
- * This loop can run a while, specially if mem_cgroup's continuously
- * keep exceeding their soft limit and putting the system under
- * pressure
- */
- do {
- if (next_mz)
- mz = next_mz;
- else
- mz = mem_cgroup_largest_soft_limit_node(mctz);
- if (!mz)
- break;
-
- nr_scanned = 0;
- reclaimed = mem_cgroup_soft_reclaim(mz->memcg, zone,
- gfp_mask, &nr_scanned);
- nr_reclaimed += reclaimed;
- *total_scanned += nr_scanned;
- spin_lock(&mctz->lock);
-
- /*
- * If we failed to reclaim anything from this memory cgroup
- * it is time to move on to the next cgroup
- */
- next_mz = NULL;
- if (!reclaimed) {
- do {
- /*
- * Loop until we find yet another one.
- *
- * By the time we get the soft_limit lock
- * again, someone might have aded the
- * group back on the RB tree. Iterate to
- * make sure we get a different mem.
- * mem_cgroup_largest_soft_limit_node returns
- * NULL if no other cgroup is present on
- * the tree
- */
- next_mz =
- __mem_cgroup_largest_soft_limit_node(mctz);
- if (next_mz == mz)
- css_put(&next_mz->memcg->css);
- else /* next_mz == NULL or other memcg */
- break;
- } while (1);
- }
- __mem_cgroup_remove_exceeded(mz->memcg, mz, mctz);
- excess = res_counter_soft_limit_excess(&mz->memcg->res);
- /*
- * One school of thought says that we should not add
- * back the node to the tree if reclaim returns 0.
- * But our reclaim could return 0, simply because due
- * to priority we are exposing a smaller subset of
- * memory to reclaim from. Consider this as a longer
- * term TODO.
- */
- /* If excess == 0, no tree ops */
- __mem_cgroup_insert_exceeded(mz->memcg, mz, mctz, excess);
- spin_unlock(&mctz->lock);
- css_put(&mz->memcg->css);
- loop++;
- /*
- * Could not reclaim anything and there are no more
- * mem cgroups to try or we seem to be looping without
- * reclaiming anything.
- */
- if (!nr_reclaimed &&
- (next_mz == NULL ||
- loop > MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS))
- break;
- } while (!nr_reclaimed);
- if (next_mz)
- css_put(&next_mz->memcg->css);
- return nr_reclaimed;
-}
-
/**
* mem_cgroup_force_empty_list - clears LRU of a group
* @memcg: group to clear
@@ -4987,18 +4818,12 @@
unsigned int event)
{
struct mem_cgroup *memcg = mem_cgroup_from_css(css);
- int ret;
if (mem_cgroup_is_root(memcg))
return -EINVAL;
- css_get(&memcg->css);
- ret = mem_cgroup_force_empty(memcg);
- css_put(&memcg->css);
-
- return ret;
+ return mem_cgroup_force_empty(memcg);
}
-
static u64 mem_cgroup_hierarchy_read(struct cgroup_subsys_state *css,
struct cftype *cft)
{
@@ -5136,7 +4961,7 @@
*/
mutex_lock(&memcg_create_mutex);
mutex_lock(&set_limit_mutex);
- if (!memcg->kmem_account_flags && val != RESOURCE_MAX) {
+ if (!memcg->kmem_account_flags && val != RES_COUNTER_MAX) {
if (cgroup_task_count(css->cgroup) || memcg_has_children(memcg)) {
ret = -EBUSY;
goto out;
@@ -5146,7 +4971,7 @@
ret = memcg_update_cache_sizes(memcg);
if (ret) {
- res_counter_set_limit(&memcg->kmem, RESOURCE_MAX);
+ res_counter_set_limit(&memcg->kmem, RES_COUNTER_MAX);
goto out;
}
static_key_slow_inc(&memcg_kmem_enabled_key);
@@ -5588,7 +5413,13 @@
const struct mem_cgroup_threshold *_a = a;
const struct mem_cgroup_threshold *_b = b;
- return _a->threshold - _b->threshold;
+ if (_a->threshold > _b->threshold)
+ return 1;
+
+ if (_a->threshold < _b->threshold)
+ return -1;
+
+ return 0;
}
static int mem_cgroup_oom_notify_cb(struct mem_cgroup *memcg)
@@ -6080,8 +5911,6 @@
for (zone = 0; zone < MAX_NR_ZONES; zone++) {
mz = &pn->zoneinfo[zone];
lruvec_init(&mz->lruvec);
- mz->usage_in_excess = 0;
- mz->on_tree = false;
mz->memcg = memcg;
}
memcg->nodeinfo[node] = pn;
@@ -6137,7 +5966,6 @@
int node;
size_t size = memcg_size();
- mem_cgroup_remove_from_trees(memcg);
free_css_id(&mem_cgroup_subsys, &memcg->css);
for_each_node(node)
@@ -6174,29 +6002,6 @@
}
EXPORT_SYMBOL(parent_mem_cgroup);
-static void __init mem_cgroup_soft_limit_tree_init(void)
-{
- struct mem_cgroup_tree_per_node *rtpn;
- struct mem_cgroup_tree_per_zone *rtpz;
- int tmp, node, zone;
-
- for_each_node(node) {
- tmp = node;
- if (!node_state(node, N_NORMAL_MEMORY))
- tmp = -1;
- rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, tmp);
- BUG_ON(!rtpn);
-
- soft_limit_tree.rb_tree_per_node[node] = rtpn;
-
- for (zone = 0; zone < MAX_NR_ZONES; zone++) {
- rtpz = &rtpn->rb_tree_per_zone[zone];
- rtpz->rb_root = RB_ROOT;
- spin_lock_init(&rtpz->lock);
- }
- }
-}
-
static struct cgroup_subsys_state * __ref
mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
{
@@ -6226,6 +6031,7 @@
mutex_init(&memcg->thresholds_lock);
spin_lock_init(&memcg->move_lock);
vmpressure_init(&memcg->vmpressure);
+ spin_lock_init(&memcg->soft_lock);
return &memcg->css;
@@ -6303,6 +6109,13 @@
mem_cgroup_invalidate_reclaim_iterators(memcg);
mem_cgroup_reparent_charges(memcg);
+ if (memcg->soft_contributed) {
+ while ((memcg = parent_mem_cgroup(memcg)))
+ atomic_dec(&memcg->children_in_excess);
+
+ if (memcg != root_mem_cgroup && !root_mem_cgroup->use_hierarchy)
+ atomic_dec(&root_mem_cgroup->children_in_excess);
+ }
mem_cgroup_destroy_all_caches(memcg);
vmpressure_cleanup(&memcg->vmpressure);
}
@@ -6977,7 +6790,6 @@
{
hotcpu_notifier(memcg_cpu_hotplug_callback, 0);
enable_swap_cgroup();
- mem_cgroup_soft_limit_tree_init();
memcg_stock_init();
return 0;
}
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index d84c5e5..947ed54 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -206,7 +206,7 @@
#ifdef __ARCH_SI_TRAPNO
si.si_trapno = trapno;
#endif
- si.si_addr_lsb = compound_trans_order(compound_head(page)) + PAGE_SHIFT;
+ si.si_addr_lsb = compound_order(compound_head(page)) + PAGE_SHIFT;
if ((flags & MF_ACTION_REQUIRED) && t == current) {
si.si_code = BUS_MCEERR_AR;
@@ -248,10 +248,12 @@
*/
if (access) {
int nr;
+ int nid = page_to_nid(p);
do {
struct shrink_control shrink = {
.gfp_mask = GFP_KERNEL,
};
+ node_set(nid, shrink.nodes_to_scan);
nr = shrink_slab(&shrink, 1000, 1000);
if (page_count(p) == 1)
@@ -983,7 +985,7 @@
static void set_page_hwpoison_huge_page(struct page *hpage)
{
int i;
- int nr_pages = 1 << compound_trans_order(hpage);
+ int nr_pages = 1 << compound_order(hpage);
for (i = 0; i < nr_pages; i++)
SetPageHWPoison(hpage + i);
}
@@ -991,7 +993,7 @@
static void clear_page_hwpoison_huge_page(struct page *hpage)
{
int i;
- int nr_pages = 1 << compound_trans_order(hpage);
+ int nr_pages = 1 << compound_order(hpage);
for (i = 0; i < nr_pages; i++)
ClearPageHWPoison(hpage + i);
}
@@ -1204,6 +1206,9 @@
for (ps = error_states;; ps++)
if ((p->flags & ps->mask) == ps->res)
break;
+
+ page_flags |= (p->flags & (1UL << PG_dirty));
+
if (!ps->mask)
for (ps = error_states;; ps++)
if ((page_flags & ps->mask) == ps->res)
@@ -1339,7 +1344,17 @@
return 0;
}
- nr_pages = 1 << compound_trans_order(page);
+ /*
+ * unpoison_memory() can encounter thp only when the thp is being
+ * worked by memory_failure() and the page lock is not held yet.
+ * In such case, we yield to memory_failure() and make unpoison fail.
+ */
+ if (PageTransHuge(page)) {
+ pr_info("MCE: Memory failure is now running on %#lx\n", pfn);
+ return 0;
+ }
+
+ nr_pages = 1 << compound_order(page);
if (!get_page_unless_zero(page)) {
/*
@@ -1353,7 +1368,7 @@
return 0;
}
if (TestClearPageHWPoison(p))
- atomic_long_sub(nr_pages, &num_poisoned_pages);
+ atomic_long_dec(&num_poisoned_pages);
pr_info("MCE: Software-unpoisoned free page %#lx\n", pfn);
return 0;
}
@@ -1375,7 +1390,7 @@
unlock_page(page);
put_page(page);
- if (freeit)
+ if (freeit && !(pfn == my_zero_pfn(0) && page_count(p) == 1))
put_page(page);
return 0;
@@ -1416,7 +1431,8 @@
* was free. This flag should be kept set until the source page
* is freed and PG_hwpoison on it is set.
*/
- set_migratetype_isolate(p, true);
+ if (get_pageblock_migratetype(p) != MIGRATE_ISOLATE)
+ set_migratetype_isolate(p, true);
/*
* When the target page is a free hugepage, just remove it
* from free hugepage list.
@@ -1470,6 +1486,7 @@
int ret;
unsigned long pfn = page_to_pfn(page);
struct page *hpage = compound_head(page);
+ LIST_HEAD(pagelist);
/*
* This double-check of PageHWPoison is to avoid the race with
@@ -1485,86 +1502,29 @@
unlock_page(hpage);
/* Keep page count to indicate a given hugepage is isolated. */
- ret = migrate_huge_page(hpage, new_page, MPOL_MF_MOVE_ALL,
- MIGRATE_SYNC);
- put_page(hpage);
+ list_move(&hpage->lru, &pagelist);
+ ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL,
+ MIGRATE_SYNC, MR_MEMORY_FAILURE);
if (ret) {
pr_info("soft offline: %#lx: migration failed %d, type %lx\n",
pfn, ret, page->flags);
+ /*
+ * We know that soft_offline_huge_page() tries to migrate
+ * only one hugepage pointed to by hpage, so we need not
+ * run through the pagelist here.
+ */
+ putback_active_hugepage(hpage);
+ if (ret > 0)
+ ret = -EIO;
} else {
set_page_hwpoison_huge_page(hpage);
dequeue_hwpoisoned_huge_page(hpage);
- atomic_long_add(1 << compound_trans_order(hpage),
+ atomic_long_add(1 << compound_order(hpage),
&num_poisoned_pages);
}
return ret;
}
-static int __soft_offline_page(struct page *page, int flags);
-
-/**
- * soft_offline_page - Soft offline a page.
- * @page: page to offline
- * @flags: flags. Same as memory_failure().
- *
- * Returns 0 on success, otherwise negated errno.
- *
- * Soft offline a page, by migration or invalidation,
- * without killing anything. This is for the case when
- * a page is not corrupted yet (so it's still valid to access),
- * but has had a number of corrected errors and is better taken
- * out.
- *
- * The actual policy on when to do that is maintained by
- * user space.
- *
- * This should never impact any application or cause data loss,
- * however it might take some time.
- *
- * This is not a 100% solution for all memory, but tries to be
- * ``good enough'' for the majority of memory.
- */
-int soft_offline_page(struct page *page, int flags)
-{
- int ret;
- unsigned long pfn = page_to_pfn(page);
- struct page *hpage = compound_trans_head(page);
-
- if (PageHWPoison(page)) {
- pr_info("soft offline: %#lx page already poisoned\n", pfn);
- return -EBUSY;
- }
- if (!PageHuge(page) && PageTransHuge(hpage)) {
- if (PageAnon(hpage) && unlikely(split_huge_page(hpage))) {
- pr_info("soft offline: %#lx: failed to split THP\n",
- pfn);
- return -EBUSY;
- }
- }
-
- ret = get_any_page(page, pfn, flags);
- if (ret < 0)
- return ret;
- if (ret) { /* for in-use pages */
- if (PageHuge(page))
- ret = soft_offline_huge_page(page, flags);
- else
- ret = __soft_offline_page(page, flags);
- } else { /* for free pages */
- if (PageHuge(page)) {
- set_page_hwpoison_huge_page(hpage);
- dequeue_hwpoisoned_huge_page(hpage);
- atomic_long_add(1 << compound_trans_order(hpage),
- &num_poisoned_pages);
- } else {
- SetPageHWPoison(page);
- atomic_long_inc(&num_poisoned_pages);
- }
- }
- unset_migratetype_isolate(page, MIGRATE_MOVABLE);
- return ret;
-}
-
static int __soft_offline_page(struct page *page, int flags)
{
int ret;
@@ -1651,3 +1611,67 @@
}
return ret;
}
+
+/**
+ * soft_offline_page - Soft offline a page.
+ * @page: page to offline
+ * @flags: flags. Same as memory_failure().
+ *
+ * Returns 0 on success, otherwise negated errno.
+ *
+ * Soft offline a page, by migration or invalidation,
+ * without killing anything. This is for the case when
+ * a page is not corrupted yet (so it's still valid to access),
+ * but has had a number of corrected errors and is better taken
+ * out.
+ *
+ * The actual policy on when to do that is maintained by
+ * user space.
+ *
+ * This should never impact any application or cause data loss,
+ * however it might take some time.
+ *
+ * This is not a 100% solution for all memory, but tries to be
+ * ``good enough'' for the majority of memory.
+ */
+int soft_offline_page(struct page *page, int flags)
+{
+ int ret;
+ unsigned long pfn = page_to_pfn(page);
+ struct page *hpage = compound_trans_head(page);
+
+ if (PageHWPoison(page)) {
+ pr_info("soft offline: %#lx page already poisoned\n", pfn);
+ return -EBUSY;
+ }
+ if (!PageHuge(page) && PageTransHuge(hpage)) {
+ if (PageAnon(hpage) && unlikely(split_huge_page(hpage))) {
+ pr_info("soft offline: %#lx: failed to split THP\n",
+ pfn);
+ return -EBUSY;
+ }
+ }
+
+ ret = get_any_page(page, pfn, flags);
+ if (ret < 0)
+ goto unset;
+ if (ret) { /* for in-use pages */
+ if (PageHuge(page))
+ ret = soft_offline_huge_page(page, flags);
+ else
+ ret = __soft_offline_page(page, flags);
+ } else { /* for free pages */
+ if (PageHuge(page)) {
+ set_page_hwpoison_huge_page(hpage);
+ dequeue_hwpoisoned_huge_page(hpage);
+ atomic_long_add(1 << compound_order(hpage),
+ &num_poisoned_pages);
+ } else {
+ SetPageHWPoison(page);
+ atomic_long_inc(&num_poisoned_pages);
+ }
+ }
+unset:
+ unset_migratetype_isolate(page, MIGRATE_MOVABLE);
+ return ret;
+}
diff --git a/mm/memory.c b/mm/memory.c
index b3c6bf9..ca00039 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -373,30 +373,6 @@
#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
/*
- * If a p?d_bad entry is found while walking page tables, report
- * the error, before resetting entry to p?d_none. Usually (but
- * very seldom) called out from the p?d_none_or_clear_bad macros.
- */
-
-void pgd_clear_bad(pgd_t *pgd)
-{
- pgd_ERROR(*pgd);
- pgd_clear(pgd);
-}
-
-void pud_clear_bad(pud_t *pud)
-{
- pud_ERROR(*pud);
- pud_clear(pud);
-}
-
-void pmd_clear_bad(pmd_t *pmd)
-{
- pmd_ERROR(*pmd);
- pmd_clear(pmd);
-}
-
-/*
* Note: this doesn't free the actual pages themselves. That
* has been handled earlier when unmapping all the memory regions.
*/
@@ -1505,7 +1481,8 @@
if (pud_none(*pud))
goto no_page_table;
if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) {
- BUG_ON(flags & FOLL_GET);
+ if (flags & FOLL_GET)
+ goto out;
page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE);
goto out;
}
@@ -1516,8 +1493,20 @@
if (pmd_none(*pmd))
goto no_page_table;
if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) {
- BUG_ON(flags & FOLL_GET);
page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE);
+ if (flags & FOLL_GET) {
+ /*
+ * Refcount on tail pages are not well-defined and
+ * shouldn't be taken. The caller should handle a NULL
+ * return when trying to follow tail pages.
+ */
+ if (PageHead(page))
+ get_page(page);
+ else {
+ page = NULL;
+ goto out;
+ }
+ }
goto out;
}
if ((flags & FOLL_NUMA) && pmd_numa(*pmd))
@@ -3706,7 +3695,7 @@
* but allow concurrent faults), and pte mapped but not yet locked.
* We return with mmap_sem still held, but pte unmapped and unlocked.
*/
-int handle_pte_fault(struct mm_struct *mm,
+static int handle_pte_fault(struct mm_struct *mm,
struct vm_area_struct *vma, unsigned long address,
pte_t *pte, pmd_t *pmd, unsigned int flags)
{
@@ -3765,22 +3754,14 @@
/*
* By the time we get here, we already hold the mm semaphore
*/
-int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
- unsigned long address, unsigned int flags)
+static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long address, unsigned int flags)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
- __set_current_state(TASK_RUNNING);
-
- count_vm_event(PGFAULT);
- mem_cgroup_count_vm_event(mm, PGFAULT);
-
- /* do counter updates before entering really critical section. */
- check_sync_rss_stat(current);
-
if (unlikely(is_vm_hugetlb_page(vma)))
return hugetlb_fault(mm, vma, address, flags);
@@ -3793,9 +3774,12 @@
if (!pmd)
return VM_FAULT_OOM;
if (pmd_none(*pmd) && transparent_hugepage_enabled(vma)) {
+ int ret = VM_FAULT_FALLBACK;
if (!vma->vm_ops)
- return do_huge_pmd_anonymous_page(mm, vma, address,
- pmd, flags);
+ ret = do_huge_pmd_anonymous_page(mm, vma, address,
+ pmd, flags);
+ if (!(ret & VM_FAULT_FALLBACK))
+ return ret;
} else {
pmd_t orig_pmd = *pmd;
int ret;
@@ -3861,6 +3845,37 @@
return handle_pte_fault(mm, vma, address, pte, pmd, flags);
}
+int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long address, unsigned int flags)
+{
+ int ret;
+
+ __set_current_state(TASK_RUNNING);
+
+ count_vm_event(PGFAULT);
+ mem_cgroup_count_vm_event(mm, PGFAULT);
+
+ /* do counter updates before entering really critical section. */
+ check_sync_rss_stat(current);
+
+ /*
+ * Enable the memcg OOM handling for faults triggered in user
+ * space. Kernel faults are handled more gracefully.
+ */
+ if (flags & FAULT_FLAG_USER)
+ mem_cgroup_enable_oom();
+
+ ret = __handle_mm_fault(mm, vma, address, flags);
+
+ if (flags & FAULT_FLAG_USER)
+ mem_cgroup_disable_oom();
+
+ if (WARN_ON(task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM)))
+ mem_cgroup_oom_synchronize();
+
+ return ret;
+}
+
#ifndef __PAGETABLE_PUD_FOLDED
/*
* Allocate page upper directory.
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index ca1dd3a..ed85fe3 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -30,6 +30,7 @@
#include <linux/mm_inline.h>
#include <linux/firmware-map.h>
#include <linux/stop_machine.h>
+#include <linux/hugetlb.h>
#include <asm/tlbflush.h>
@@ -51,14 +52,10 @@
void lock_memory_hotplug(void)
{
mutex_lock(&mem_hotplug_mutex);
-
- /* for exclusive hibernation if CONFIG_HIBERNATION=y */
- lock_system_sleep();
}
void unlock_memory_hotplug(void)
{
- unlock_system_sleep();
mutex_unlock(&mem_hotplug_mutex);
}
@@ -194,7 +191,7 @@
zone = &pgdat->node_zones[0];
for (; zone < pgdat->node_zones + MAX_NR_ZONES - 1; zone++) {
- if (zone->wait_table) {
+ if (zone_is_initialized(zone)) {
nr_pages = zone->wait_table_hash_nr_entries
* sizeof(wait_queue_head_t);
nr_pages = PAGE_ALIGN(nr_pages) >> PAGE_SHIFT;
@@ -229,8 +226,8 @@
zone_span_writelock(zone);
- old_zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages;
- if (!zone->spanned_pages || start_pfn < zone->zone_start_pfn)
+ old_zone_end_pfn = zone_end_pfn(zone);
+ if (zone_is_empty(zone) || start_pfn < zone->zone_start_pfn)
zone->zone_start_pfn = start_pfn;
zone->spanned_pages = max(old_zone_end_pfn, end_pfn) -
@@ -305,7 +302,7 @@
goto out_fail;
/* use start_pfn for z1's start_pfn if z1 is empty */
- if (z1->spanned_pages)
+ if (!zone_is_empty(z1))
z1_start_pfn = z1->zone_start_pfn;
else
z1_start_pfn = start_pfn;
@@ -347,7 +344,7 @@
goto out_fail;
/* use end_pfn for z2's end_pfn if z2 is empty */
- if (z2->spanned_pages)
+ if (!zone_is_empty(z2))
z2_end_pfn = zone_end_pfn(z2);
else
z2_end_pfn = end_pfn;
@@ -514,8 +511,9 @@
static void shrink_zone_span(struct zone *zone, unsigned long start_pfn,
unsigned long end_pfn)
{
- unsigned long zone_start_pfn = zone->zone_start_pfn;
- unsigned long zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages;
+ unsigned long zone_start_pfn = zone->zone_start_pfn;
+ unsigned long z = zone_end_pfn(zone); /* zone_end_pfn namespace clash */
+ unsigned long zone_end_pfn = z;
unsigned long pfn;
struct mem_section *ms;
int nid = zone_to_nid(zone);
@@ -1069,6 +1067,23 @@
return ret;
}
+static int check_hotplug_memory_range(u64 start, u64 size)
+{
+ u64 start_pfn = start >> PAGE_SHIFT;
+ u64 nr_pages = size >> PAGE_SHIFT;
+
+ /* Memory range must be aligned with section */
+ if ((start_pfn & ~PAGE_SECTION_MASK) ||
+ (nr_pages % PAGES_PER_SECTION) || (!nr_pages)) {
+ pr_err("Section-unaligned hotplug range: start 0x%llx, size 0x%llx\n",
+ (unsigned long long)start,
+ (unsigned long long)size);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */
int __ref add_memory(int nid, u64 start, u64 size)
{
@@ -1078,6 +1093,10 @@
struct resource *res;
int ret;
+ ret = check_hotplug_memory_range(start, size);
+ if (ret)
+ return ret;
+
lock_memory_hotplug();
res = register_memory_resource(start, size);
@@ -1208,10 +1227,12 @@
}
/*
- * Scanning pfn is much easier than scanning lru list.
- * Scan pfn from start to end and Find LRU page.
+ * Scan pfn range [start,end) to find movable/migratable pages (LRU pages
+ * and hugepages). We scan pfn because it's much easier than scanning over
+ * linked list. This function returns the pfn of the first found movable
+ * page if it's found, otherwise 0.
*/
-static unsigned long scan_lru_pages(unsigned long start, unsigned long end)
+static unsigned long scan_movable_pages(unsigned long start, unsigned long end)
{
unsigned long pfn;
struct page *page;
@@ -1220,6 +1241,13 @@
page = pfn_to_page(pfn);
if (PageLRU(page))
return pfn;
+ if (PageHuge(page)) {
+ if (is_hugepage_active(page))
+ return pfn;
+ else
+ pfn = round_up(pfn + 1,
+ 1 << compound_order(page)) - 1;
+ }
}
}
return 0;
@@ -1240,6 +1268,19 @@
if (!pfn_valid(pfn))
continue;
page = pfn_to_page(pfn);
+
+ if (PageHuge(page)) {
+ struct page *head = compound_head(page);
+ pfn = page_to_pfn(head) + (1<<compound_order(head)) - 1;
+ if (compound_order(head) > PFN_SECTION_SHIFT) {
+ ret = -EBUSY;
+ break;
+ }
+ if (isolate_huge_page(page, &source))
+ move_pages -= 1 << compound_order(head);
+ continue;
+ }
+
if (!get_page_unless_zero(page))
continue;
/*
@@ -1272,7 +1313,7 @@
}
if (!list_empty(&source)) {
if (not_managed) {
- putback_lru_pages(&source);
+ putback_movable_pages(&source);
goto out;
}
@@ -1283,7 +1324,7 @@
ret = migrate_pages(&source, alloc_migrate_target, 0,
MIGRATE_SYNC, MR_MEMORY_HOTPLUG);
if (ret)
- putback_lru_pages(&source);
+ putback_movable_pages(&source);
}
out:
return ret;
@@ -1472,7 +1513,6 @@
struct zone *zone;
struct memory_notify arg;
- BUG_ON(start_pfn >= end_pfn);
/* at least, alignment against pageblock is necessary */
if (!IS_ALIGNED(start_pfn, pageblock_nr_pages))
return -EINVAL;
@@ -1527,8 +1567,8 @@
drain_all_pages();
}
- pfn = scan_lru_pages(start_pfn, end_pfn);
- if (pfn) { /* We have page on LRU */
+ pfn = scan_movable_pages(start_pfn, end_pfn);
+ if (pfn) { /* We have movable pages */
ret = do_migrate_range(pfn, end_pfn);
if (!ret) {
drain = 1;
@@ -1547,6 +1587,11 @@
yield();
/* drain pcp pages, this is synchronous. */
drain_all_pages();
+ /*
+ * dissolve free hugepages in the memory block before doing offlining
+ * actually in order to make hugetlbfs's object counting consistent.
+ */
+ dissolve_free_huge_pages(start_pfn, end_pfn);
/* check again */
offlined_pages = check_pages_isolated(start_pfn, end_pfn);
if (offlined_pages < 0) {
@@ -1674,9 +1719,8 @@
return ret;
}
-static int check_cpu_on_node(void *data)
+static int check_cpu_on_node(pg_data_t *pgdat)
{
- struct pglist_data *pgdat = data;
int cpu;
for_each_present_cpu(cpu) {
@@ -1691,10 +1735,9 @@
return 0;
}
-static void unmap_cpu_on_node(void *data)
+static void unmap_cpu_on_node(pg_data_t *pgdat)
{
#ifdef CONFIG_ACPI_NUMA
- struct pglist_data *pgdat = data;
int cpu;
for_each_possible_cpu(cpu)
@@ -1703,10 +1746,11 @@
#endif
}
-static int check_and_unmap_cpu_on_node(void *data)
+static int check_and_unmap_cpu_on_node(pg_data_t *pgdat)
{
- int ret = check_cpu_on_node(data);
+ int ret;
+ ret = check_cpu_on_node(pgdat);
if (ret)
return ret;
@@ -1715,11 +1759,18 @@
* the cpu_to_node() now.
*/
- unmap_cpu_on_node(data);
+ unmap_cpu_on_node(pgdat);
return 0;
}
-/* offline the node if all memory sections of this node are removed */
+/**
+ * try_offline_node
+ *
+ * Offline a node if all memory sections and cpus of the node are removed.
+ *
+ * NOTE: The caller must call lock_device_hotplug() to serialize hotplug
+ * and online/offline operations before this call.
+ */
void try_offline_node(int nid)
{
pg_data_t *pgdat = NODE_DATA(nid);
@@ -1745,7 +1796,7 @@
return;
}
- if (stop_machine(check_and_unmap_cpu_on_node, pgdat, NULL))
+ if (check_and_unmap_cpu_on_node(pgdat))
return;
/*
@@ -1782,10 +1833,19 @@
}
EXPORT_SYMBOL(try_offline_node);
+/**
+ * remove_memory
+ *
+ * NOTE: The caller must call lock_device_hotplug() to serialize hotplug
+ * and online/offline operations before this call, as required by
+ * try_offline_node().
+ */
void __ref remove_memory(int nid, u64 start, u64 size)
{
int ret;
+ BUG_ON(check_hotplug_memory_range(start, size));
+
lock_memory_hotplug();
/*
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 4baf12e..0472964 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -123,16 +123,19 @@
static struct mempolicy *get_task_policy(struct task_struct *p)
{
struct mempolicy *pol = p->mempolicy;
- int node;
if (!pol) {
- node = numa_node_id();
- if (node != NUMA_NO_NODE)
- pol = &preferred_node_policy[node];
+ int node = numa_node_id();
- /* preferred_node_policy is not initialised early in boot */
- if (!pol->mode)
- pol = NULL;
+ if (node != NUMA_NO_NODE) {
+ pol = &preferred_node_policy[node];
+ /*
+ * preferred_node_policy is not initialised early in
+ * boot
+ */
+ if (!pol->mode)
+ pol = NULL;
+ }
}
return pol;
@@ -473,8 +476,11 @@
static void migrate_page_add(struct page *page, struct list_head *pagelist,
unsigned long flags);
-/* Scan through pages checking if pages follow certain conditions. */
-static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
+/*
+ * Scan through pages checking if pages follow certain conditions,
+ * and move them to the pagelist if they do.
+ */
+static int queue_pages_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, unsigned long end,
const nodemask_t *nodes, unsigned long flags,
void *private)
@@ -512,7 +518,31 @@
return addr != end;
}
-static inline int check_pmd_range(struct vm_area_struct *vma, pud_t *pud,
+static void queue_pages_hugetlb_pmd_range(struct vm_area_struct *vma,
+ pmd_t *pmd, const nodemask_t *nodes, unsigned long flags,
+ void *private)
+{
+#ifdef CONFIG_HUGETLB_PAGE
+ int nid;
+ struct page *page;
+
+ spin_lock(&vma->vm_mm->page_table_lock);
+ page = pte_page(huge_ptep_get((pte_t *)pmd));
+ nid = page_to_nid(page);
+ if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT))
+ goto unlock;
+ /* With MPOL_MF_MOVE, we migrate only unshared hugepage. */
+ if (flags & (MPOL_MF_MOVE_ALL) ||
+ (flags & MPOL_MF_MOVE && page_mapcount(page) == 1))
+ isolate_huge_page(page, private);
+unlock:
+ spin_unlock(&vma->vm_mm->page_table_lock);
+#else
+ BUG();
+#endif
+}
+
+static inline int queue_pages_pmd_range(struct vm_area_struct *vma, pud_t *pud,
unsigned long addr, unsigned long end,
const nodemask_t *nodes, unsigned long flags,
void *private)
@@ -523,17 +553,24 @@
pmd = pmd_offset(pud, addr);
do {
next = pmd_addr_end(addr, end);
+ if (!pmd_present(*pmd))
+ continue;
+ if (pmd_huge(*pmd) && is_vm_hugetlb_page(vma)) {
+ queue_pages_hugetlb_pmd_range(vma, pmd, nodes,
+ flags, private);
+ continue;
+ }
split_huge_page_pmd(vma, addr, pmd);
if (pmd_none_or_trans_huge_or_clear_bad(pmd))
continue;
- if (check_pte_range(vma, pmd, addr, next, nodes,
+ if (queue_pages_pte_range(vma, pmd, addr, next, nodes,
flags, private))
return -EIO;
} while (pmd++, addr = next, addr != end);
return 0;
}
-static inline int check_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
+static inline int queue_pages_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
unsigned long addr, unsigned long end,
const nodemask_t *nodes, unsigned long flags,
void *private)
@@ -544,16 +581,18 @@
pud = pud_offset(pgd, addr);
do {
next = pud_addr_end(addr, end);
+ if (pud_huge(*pud) && is_vm_hugetlb_page(vma))
+ continue;
if (pud_none_or_clear_bad(pud))
continue;
- if (check_pmd_range(vma, pud, addr, next, nodes,
+ if (queue_pages_pmd_range(vma, pud, addr, next, nodes,
flags, private))
return -EIO;
} while (pud++, addr = next, addr != end);
return 0;
}
-static inline int check_pgd_range(struct vm_area_struct *vma,
+static inline int queue_pages_pgd_range(struct vm_area_struct *vma,
unsigned long addr, unsigned long end,
const nodemask_t *nodes, unsigned long flags,
void *private)
@@ -566,7 +605,7 @@
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
- if (check_pud_range(vma, pgd, addr, next, nodes,
+ if (queue_pages_pud_range(vma, pgd, addr, next, nodes,
flags, private))
return -EIO;
} while (pgd++, addr = next, addr != end);
@@ -604,12 +643,14 @@
#endif /* CONFIG_ARCH_USES_NUMA_PROT_NONE */
/*
- * Check if all pages in a range are on a set of nodes.
- * If pagelist != NULL then isolate pages from the LRU and
- * put them on the pagelist.
+ * Walk through page tables and collect pages to be migrated.
+ *
+ * If pages found in a given range are on a set of nodes (determined by
+ * @nodes and @flags,) it's isolated and queued to the pagelist which is
+ * passed via @private.)
*/
static struct vm_area_struct *
-check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
+queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
const nodemask_t *nodes, unsigned long flags, void *private)
{
int err;
@@ -635,9 +676,6 @@
return ERR_PTR(-EFAULT);
}
- if (is_vm_hugetlb_page(vma))
- goto next;
-
if (flags & MPOL_MF_LAZY) {
change_prot_numa(vma, start, endvma);
goto next;
@@ -647,7 +685,7 @@
((flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) &&
vma_migratable(vma))) {
- err = check_pgd_range(vma, start, endvma, nodes,
+ err = queue_pages_pgd_range(vma, start, endvma, nodes,
flags, private);
if (err) {
first = ERR_PTR(err);
@@ -990,7 +1028,11 @@
static struct page *new_node_page(struct page *page, unsigned long node, int **x)
{
- return alloc_pages_exact_node(node, GFP_HIGHUSER_MOVABLE, 0);
+ if (PageHuge(page))
+ return alloc_huge_page_node(page_hstate(compound_head(page)),
+ node);
+ else
+ return alloc_pages_exact_node(node, GFP_HIGHUSER_MOVABLE, 0);
}
/*
@@ -1013,14 +1055,14 @@
* space range and MPOL_MF_DISCONTIG_OK, this call can not fail.
*/
VM_BUG_ON(!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)));
- check_range(mm, mm->mmap->vm_start, mm->task_size, &nmask,
+ queue_pages_range(mm, mm->mmap->vm_start, mm->task_size, &nmask,
flags | MPOL_MF_DISCONTIG_OK, &pagelist);
if (!list_empty(&pagelist)) {
err = migrate_pages(&pagelist, new_node_page, dest,
MIGRATE_SYNC, MR_SYSCALL);
if (err)
- putback_lru_pages(&pagelist);
+ putback_movable_pages(&pagelist);
}
return err;
@@ -1154,10 +1196,14 @@
break;
vma = vma->vm_next;
}
-
/*
- * if !vma, alloc_page_vma() will use task or system default policy
+ * queue_pages_range() confirms that @page belongs to some vma,
+ * so vma shouldn't be NULL.
*/
+ BUG_ON(!vma);
+
+ if (PageHuge(page))
+ return alloc_huge_page_noerr(vma, address, 1);
return alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
}
#else
@@ -1249,7 +1295,7 @@
if (err)
goto mpol_out;
- vma = check_range(mm, start, end, nmask,
+ vma = queue_pages_range(mm, start, end, nmask,
flags | MPOL_MF_INVERT, &pagelist);
err = PTR_ERR(vma); /* maybe ... */
@@ -1265,7 +1311,7 @@
(unsigned long)vma,
MIGRATE_SYNC, MR_MEMPOLICY_MBIND);
if (nr_failed)
- putback_lru_pages(&pagelist);
+ putback_movable_pages(&pagelist);
}
if (nr_failed && (flags & MPOL_MF_STRICT))
@@ -2065,6 +2111,16 @@
}
EXPORT_SYMBOL(alloc_pages_current);
+int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst)
+{
+ struct mempolicy *pol = mpol_dup(vma_policy(src));
+
+ if (IS_ERR(pol))
+ return PTR_ERR(pol);
+ dst->vm_policy = pol;
+ return 0;
+}
+
/*
* If mpol_dup() sees current->cpuset == cpuset_being_rebound, then it
* rebinds the mempolicy its copying by calling mpol_rebind_policy()
diff --git a/mm/mempool.c b/mm/mempool.c
index 5499047..659aa42 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -73,7 +73,7 @@
gfp_t gfp_mask, int node_id)
{
mempool_t *pool;
- pool = kmalloc_node(sizeof(*pool), gfp_mask | __GFP_ZERO, node_id);
+ pool = kzalloc_node(sizeof(*pool), gfp_mask, node_id);
if (!pool)
return NULL;
pool->elements = kmalloc_node(min_nr * sizeof(void *),
diff --git a/mm/migrate.c b/mm/migrate.c
index 6f0c244..9c8d5f5 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -100,6 +100,10 @@
struct page *page2;
list_for_each_entry_safe(page, page2, l, lru) {
+ if (unlikely(PageHuge(page))) {
+ putback_active_hugepage(page);
+ continue;
+ }
list_del(&page->lru);
dec_zone_page_state(page, NR_ISOLATED_ANON +
page_is_file_cache(page));
@@ -307,7 +311,7 @@
* 2 for pages with a mapping
* 3 for pages with a mapping and PagePrivate/PagePrivate2 set.
*/
-static int migrate_page_move_mapping(struct address_space *mapping,
+int migrate_page_move_mapping(struct address_space *mapping,
struct page *newpage, struct page *page,
struct buffer_head *head, enum migrate_mode mode)
{
@@ -945,6 +949,16 @@
struct page *new_hpage = get_new_page(hpage, private, &result);
struct anon_vma *anon_vma = NULL;
+ /*
+ * Movability of hugepages depends on architectures and hugepage size.
+ * This check is necessary because some callers of hugepage migration
+ * like soft offline and memory hotremove don't walk through page
+ * tables or check whether the hugepage is pmd-based or not before
+ * kicking migration.
+ */
+ if (!hugepage_migration_support(page_hstate(hpage)))
+ return -ENOSYS;
+
if (!new_hpage)
return -ENOMEM;
@@ -975,6 +989,8 @@
unlock_page(hpage);
out:
+ if (rc != -EAGAIN)
+ putback_active_hugepage(hpage);
put_page(new_hpage);
if (result) {
if (rc)
@@ -1025,7 +1041,11 @@
list_for_each_entry_safe(page, page2, from, lru) {
cond_resched();
- rc = unmap_and_move(get_new_page, private,
+ if (PageHuge(page))
+ rc = unmap_and_move_huge_page(get_new_page,
+ private, page, pass > 2, mode);
+ else
+ rc = unmap_and_move(get_new_page, private,
page, pass > 2, mode);
switch(rc) {
@@ -1058,32 +1078,6 @@
return rc;
}
-int migrate_huge_page(struct page *hpage, new_page_t get_new_page,
- unsigned long private, enum migrate_mode mode)
-{
- int pass, rc;
-
- for (pass = 0; pass < 10; pass++) {
- rc = unmap_and_move_huge_page(get_new_page, private,
- hpage, pass > 2, mode);
- switch (rc) {
- case -ENOMEM:
- goto out;
- case -EAGAIN:
- /* try again */
- cond_resched();
- break;
- case MIGRATEPAGE_SUCCESS:
- goto out;
- default:
- rc = -EIO;
- goto out;
- }
- }
-out:
- return rc;
-}
-
#ifdef CONFIG_NUMA
/*
* Move a list of individual pages
@@ -1108,7 +1102,11 @@
*result = &pm->status;
- return alloc_pages_exact_node(pm->node,
+ if (PageHuge(p))
+ return alloc_huge_page_node(page_hstate(compound_head(p)),
+ pm->node);
+ else
+ return alloc_pages_exact_node(pm->node,
GFP_HIGHUSER_MOVABLE | GFP_THISNODE, 0);
}
@@ -1168,6 +1166,11 @@
!migrate_all)
goto put_and_set;
+ if (PageHuge(page)) {
+ isolate_huge_page(page, &pagelist);
+ goto put_and_set;
+ }
+
err = isolate_lru_page(page);
if (!err) {
list_add_tail(&page->lru, &pagelist);
@@ -1190,7 +1193,7 @@
err = migrate_pages(&pagelist, new_page_node,
(unsigned long)pm, MIGRATE_SYNC, MR_SYSCALL);
if (err)
- putback_lru_pages(&pagelist);
+ putback_movable_pages(&pagelist);
}
up_read(&mm->mmap_sem);
@@ -1468,7 +1471,7 @@
if (!populated_zone(zone))
continue;
- if (zone->all_unreclaimable)
+ if (!zone_reclaimable(zone))
continue;
/* Avoid waking kswapd by allocating pages_to_migrate pages. */
diff --git a/mm/mlock.c b/mm/mlock.c
index 79b7cf7..d638026 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -11,6 +11,7 @@
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/pagemap.h>
+#include <linux/pagevec.h>
#include <linux/mempolicy.h>
#include <linux/syscalls.h>
#include <linux/sched.h>
@@ -18,6 +19,8 @@
#include <linux/rmap.h>
#include <linux/mmzone.h>
#include <linux/hugetlb.h>
+#include <linux/memcontrol.h>
+#include <linux/mm_inline.h>
#include "internal.h"
@@ -87,6 +90,47 @@
}
}
+/*
+ * Finish munlock after successful page isolation
+ *
+ * Page must be locked. This is a wrapper for try_to_munlock()
+ * and putback_lru_page() with munlock accounting.
+ */
+static void __munlock_isolated_page(struct page *page)
+{
+ int ret = SWAP_AGAIN;
+
+ /*
+ * Optimization: if the page was mapped just once, that's our mapping
+ * and we don't need to check all the other vmas.
+ */
+ if (page_mapcount(page) > 1)
+ ret = try_to_munlock(page);
+
+ /* Did try_to_unlock() succeed or punt? */
+ if (ret != SWAP_MLOCK)
+ count_vm_event(UNEVICTABLE_PGMUNLOCKED);
+
+ putback_lru_page(page);
+}
+
+/*
+ * Accounting for page isolation fail during munlock
+ *
+ * Performs accounting when page isolation fails in munlock. There is nothing
+ * else to do because it means some other task has already removed the page
+ * from the LRU. putback_lru_page() will take care of removing the page from
+ * the unevictable list, if necessary. vmscan [page_referenced()] will move
+ * the page back to the unevictable list if some other vma has it mlocked.
+ */
+static void __munlock_isolation_failed(struct page *page)
+{
+ if (PageUnevictable(page))
+ count_vm_event(UNEVICTABLE_PGSTRANDED);
+ else
+ count_vm_event(UNEVICTABLE_PGMUNLOCKED);
+}
+
/**
* munlock_vma_page - munlock a vma page
* @page - page to be unlocked
@@ -112,37 +156,10 @@
unsigned int nr_pages = hpage_nr_pages(page);
mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
page_mask = nr_pages - 1;
- if (!isolate_lru_page(page)) {
- int ret = SWAP_AGAIN;
-
- /*
- * Optimization: if the page was mapped just once,
- * that's our mapping and we don't need to check all the
- * other vmas.
- */
- if (page_mapcount(page) > 1)
- ret = try_to_munlock(page);
- /*
- * did try_to_unlock() succeed or punt?
- */
- if (ret != SWAP_MLOCK)
- count_vm_event(UNEVICTABLE_PGMUNLOCKED);
-
- putback_lru_page(page);
- } else {
- /*
- * Some other task has removed the page from the LRU.
- * putback_lru_page() will take care of removing the
- * page from the unevictable list, if necessary.
- * vmscan [page_referenced()] will move the page back
- * to the unevictable list if some other vma has it
- * mlocked.
- */
- if (PageUnevictable(page))
- count_vm_event(UNEVICTABLE_PGSTRANDED);
- else
- count_vm_event(UNEVICTABLE_PGMUNLOCKED);
- }
+ if (!isolate_lru_page(page))
+ __munlock_isolated_page(page);
+ else
+ __munlock_isolation_failed(page);
}
return page_mask;
@@ -210,6 +227,191 @@
}
/*
+ * Prepare page for fast batched LRU putback via putback_lru_evictable_pagevec()
+ *
+ * The fast path is available only for evictable pages with single mapping.
+ * Then we can bypass the per-cpu pvec and get better performance.
+ * when mapcount > 1 we need try_to_munlock() which can fail.
+ * when !page_evictable(), we need the full redo logic of putback_lru_page to
+ * avoid leaving evictable page in unevictable list.
+ *
+ * In case of success, @page is added to @pvec and @pgrescued is incremented
+ * in case that the page was previously unevictable. @page is also unlocked.
+ */
+static bool __putback_lru_fast_prepare(struct page *page, struct pagevec *pvec,
+ int *pgrescued)
+{
+ VM_BUG_ON(PageLRU(page));
+ VM_BUG_ON(!PageLocked(page));
+
+ if (page_mapcount(page) <= 1 && page_evictable(page)) {
+ pagevec_add(pvec, page);
+ if (TestClearPageUnevictable(page))
+ (*pgrescued)++;
+ unlock_page(page);
+ return true;
+ }
+
+ return false;
+}
+
+/*
+ * Putback multiple evictable pages to the LRU
+ *
+ * Batched putback of evictable pages that bypasses the per-cpu pvec. Some of
+ * the pages might have meanwhile become unevictable but that is OK.
+ */
+static void __putback_lru_fast(struct pagevec *pvec, int pgrescued)
+{
+ count_vm_events(UNEVICTABLE_PGMUNLOCKED, pagevec_count(pvec));
+ /*
+ *__pagevec_lru_add() calls release_pages() so we don't call
+ * put_page() explicitly
+ */
+ __pagevec_lru_add(pvec);
+ count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued);
+}
+
+/*
+ * Munlock a batch of pages from the same zone
+ *
+ * The work is split to two main phases. First phase clears the Mlocked flag
+ * and attempts to isolate the pages, all under a single zone lru lock.
+ * The second phase finishes the munlock only for pages where isolation
+ * succeeded.
+ *
+ * Note that the pagevec may be modified during the process.
+ */
+static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
+{
+ int i;
+ int nr = pagevec_count(pvec);
+ int delta_munlocked = -nr;
+ struct pagevec pvec_putback;
+ int pgrescued = 0;
+
+ /* Phase 1: page isolation */
+ spin_lock_irq(&zone->lru_lock);
+ for (i = 0; i < nr; i++) {
+ struct page *page = pvec->pages[i];
+
+ if (TestClearPageMlocked(page)) {
+ struct lruvec *lruvec;
+ int lru;
+
+ if (PageLRU(page)) {
+ lruvec = mem_cgroup_page_lruvec(page, zone);
+ lru = page_lru(page);
+ /*
+ * We already have pin from follow_page_mask()
+ * so we can spare the get_page() here.
+ */
+ ClearPageLRU(page);
+ del_page_from_lru_list(page, lruvec, lru);
+ } else {
+ __munlock_isolation_failed(page);
+ goto skip_munlock;
+ }
+
+ } else {
+skip_munlock:
+ /*
+ * We won't be munlocking this page in the next phase
+ * but we still need to release the follow_page_mask()
+ * pin.
+ */
+ pvec->pages[i] = NULL;
+ put_page(page);
+ delta_munlocked++;
+ }
+ }
+ __mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
+ spin_unlock_irq(&zone->lru_lock);
+
+ /* Phase 2: page munlock */
+ pagevec_init(&pvec_putback, 0);
+ for (i = 0; i < nr; i++) {
+ struct page *page = pvec->pages[i];
+
+ if (page) {
+ lock_page(page);
+ if (!__putback_lru_fast_prepare(page, &pvec_putback,
+ &pgrescued)) {
+ /*
+ * Slow path. We don't want to lose the last
+ * pin before unlock_page()
+ */
+ get_page(page); /* for putback_lru_page() */
+ __munlock_isolated_page(page);
+ unlock_page(page);
+ put_page(page); /* from follow_page_mask() */
+ }
+ }
+ }
+
+ /*
+ * Phase 3: page putback for pages that qualified for the fast path
+ * This will also call put_page() to return pin from follow_page_mask()
+ */
+ if (pagevec_count(&pvec_putback))
+ __putback_lru_fast(&pvec_putback, pgrescued);
+}
+
+/*
+ * Fill up pagevec for __munlock_pagevec using pte walk
+ *
+ * The function expects that the struct page corresponding to @start address is
+ * a non-TPH page already pinned and in the @pvec, and that it belongs to @zone.
+ *
+ * The rest of @pvec is filled by subsequent pages within the same pmd and same
+ * zone, as long as the pte's are present and vm_normal_page() succeeds. These
+ * pages also get pinned.
+ *
+ * Returns the address of the next page that should be scanned. This equals
+ * @start + PAGE_SIZE when no page could be added by the pte walk.
+ */
+static unsigned long __munlock_pagevec_fill(struct pagevec *pvec,
+ struct vm_area_struct *vma, int zoneid, unsigned long start,
+ unsigned long end)
+{
+ pte_t *pte;
+ spinlock_t *ptl;
+
+ /*
+ * Initialize pte walk starting at the already pinned page where we
+ * are sure that there is a pte.
+ */
+ pte = get_locked_pte(vma->vm_mm, start, &ptl);
+ end = min(end, pmd_addr_end(start, end));
+
+ /* The page next to the pinned page is the first we will try to get */
+ start += PAGE_SIZE;
+ while (start < end) {
+ struct page *page = NULL;
+ pte++;
+ if (pte_present(*pte))
+ page = vm_normal_page(vma, start, *pte);
+ /*
+ * Break if page could not be obtained or the page's node+zone does not
+ * match
+ */
+ if (!page || page_zone_id(page) != zoneid)
+ break;
+
+ get_page(page);
+ /*
+ * Increase the address that will be returned *before* the
+ * eventual break due to pvec becoming full by adding the page
+ */
+ start += PAGE_SIZE;
+ if (pagevec_add(pvec, page) == 0)
+ break;
+ }
+ pte_unmap_unlock(pte, ptl);
+ return start;
+}
+
+/*
* munlock_vma_pages_range() - munlock all pages in the vma range.'
* @vma - vma containing range to be munlock()ed.
* @start - start address in @vma of the range
@@ -233,9 +435,13 @@
vma->vm_flags &= ~VM_LOCKED;
while (start < end) {
- struct page *page;
+ struct page *page = NULL;
unsigned int page_mask, page_increm;
+ struct pagevec pvec;
+ struct zone *zone;
+ int zoneid;
+ pagevec_init(&pvec, 0);
/*
* Although FOLL_DUMP is intended for get_dump_page(),
* it just so happens that its special treatment of the
@@ -244,21 +450,45 @@
* has sneaked into the range, we won't oops here: great).
*/
page = follow_page_mask(vma, start, FOLL_GET | FOLL_DUMP,
- &page_mask);
+ &page_mask);
+
if (page && !IS_ERR(page)) {
- lock_page(page);
- lru_add_drain();
- /*
- * Any THP page found by follow_page_mask() may have
- * gotten split before reaching munlock_vma_page(),
- * so we need to recompute the page_mask here.
- */
- page_mask = munlock_vma_page(page);
- unlock_page(page);
- put_page(page);
+ if (PageTransHuge(page)) {
+ lock_page(page);
+ /*
+ * Any THP page found by follow_page_mask() may
+ * have gotten split before reaching
+ * munlock_vma_page(), so we need to recompute
+ * the page_mask here.
+ */
+ page_mask = munlock_vma_page(page);
+ unlock_page(page);
+ put_page(page); /* follow_page_mask() */
+ } else {
+ /*
+ * Non-huge pages are handled in batches via
+ * pagevec. The pin from follow_page_mask()
+ * prevents them from collapsing by THP.
+ */
+ pagevec_add(&pvec, page);
+ zone = page_zone(page);
+ zoneid = page_zone_id(page);
+
+ /*
+ * Try to fill the rest of pagevec using fast
+ * pte walk. This will also update start to
+ * the next page to process. Then munlock the
+ * pagevec.
+ */
+ start = __munlock_pagevec_fill(&pvec, vma,
+ zoneid, start, end);
+ __munlock_pagevec(&pvec, zone);
+ goto next;
+ }
}
page_increm = 1 + (~(start >> PAGE_SHIFT) & page_mask);
start += page_increm * PAGE_SIZE;
+next:
cond_resched();
}
}
diff --git a/mm/mmap.c b/mm/mmap.c
index f9c97d1..9d54851 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1202,7 +1202,6 @@
unsigned long *populate)
{
struct mm_struct * mm = current->mm;
- struct inode *inode;
vm_flags_t vm_flags;
*populate = 0;
@@ -1265,9 +1264,9 @@
return -EAGAIN;
}
- inode = file ? file_inode(file) : NULL;
-
if (file) {
+ struct inode *inode = file_inode(file);
+
switch (flags & MAP_TYPE) {
case MAP_SHARED:
if ((prot&PROT_WRITE) && !(file->f_mode&FMODE_WRITE))
@@ -1302,6 +1301,8 @@
if (!file->f_op || !file->f_op->mmap)
return -ENODEV;
+ if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP))
+ return -EINVAL;
break;
default:
@@ -1310,6 +1311,8 @@
} else {
switch (flags & MAP_TYPE) {
case MAP_SHARED:
+ if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP))
+ return -EINVAL;
/*
* Ignore pgoff.
*/
@@ -1476,11 +1479,9 @@
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma, *prev;
- int correct_wcount = 0;
int error;
struct rb_node **rb_link, *rb_parent;
unsigned long charged = 0;
- struct inode *inode = file ? file_inode(file) : NULL;
/* Check against address space limit. */
if (!may_expand_vm(mm, len >> PAGE_SHIFT)) {
@@ -1544,16 +1545,11 @@
vma->vm_pgoff = pgoff;
INIT_LIST_HEAD(&vma->anon_vma_chain);
- error = -EINVAL; /* when rejecting VM_GROWSDOWN|VM_GROWSUP */
-
if (file) {
- if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP))
- goto free_vma;
if (vm_flags & VM_DENYWRITE) {
error = deny_write_access(file);
if (error)
goto free_vma;
- correct_wcount = 1;
}
vma->vm_file = get_file(file);
error = file->f_op->mmap(file, vma);
@@ -1570,11 +1566,8 @@
WARN_ON_ONCE(addr != vma->vm_start);
addr = vma->vm_start;
- pgoff = vma->vm_pgoff;
vm_flags = vma->vm_flags;
} else if (vm_flags & VM_SHARED) {
- if (unlikely(vm_flags & (VM_GROWSDOWN|VM_GROWSUP)))
- goto free_vma;
error = shmem_zero_setup(vma);
if (error)
goto free_vma;
@@ -1596,11 +1589,10 @@
}
vma_link(mm, vma, prev, rb_link, rb_parent);
- file = vma->vm_file;
-
/* Once vma denies write, undo our temporary denial count */
- if (correct_wcount)
- atomic_inc(&inode->i_writecount);
+ if (vm_flags & VM_DENYWRITE)
+ allow_write_access(file);
+ file = vma->vm_file;
out:
perf_event_mmap(vma);
@@ -1616,11 +1608,20 @@
if (file)
uprobe_mmap(vma);
+ /*
+ * New (or expanded) vma always get soft dirty status.
+ * Otherwise user-space soft-dirty page tracker won't
+ * be able to distinguish situation when vma area unmapped,
+ * then new mapped in-place (which must be aimed as
+ * a completely new data area).
+ */
+ vma->vm_flags |= VM_SOFTDIRTY;
+
return addr;
unmap_and_free_vma:
- if (correct_wcount)
- atomic_inc(&inode->i_writecount);
+ if (vm_flags & VM_DENYWRITE)
+ allow_write_access(file);
vma->vm_file = NULL;
fput(file);
@@ -2380,7 +2381,6 @@
static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
unsigned long addr, int new_below)
{
- struct mempolicy *pol;
struct vm_area_struct *new;
int err = -ENOMEM;
@@ -2404,12 +2404,9 @@
new->vm_pgoff += ((addr - vma->vm_start) >> PAGE_SHIFT);
}
- pol = mpol_dup(vma_policy(vma));
- if (IS_ERR(pol)) {
- err = PTR_ERR(pol);
+ err = vma_dup_policy(vma, new);
+ if (err)
goto out_free_vma;
- }
- vma_set_policy(new, pol);
if (anon_vma_clone(new, vma))
goto out_free_mpol;
@@ -2437,7 +2434,7 @@
fput(new->vm_file);
unlink_anon_vmas(new);
out_free_mpol:
- mpol_put(pol);
+ mpol_put(vma_policy(new));
out_free_vma:
kmem_cache_free(vm_area_cachep, new);
out_err:
@@ -2663,6 +2660,7 @@
mm->total_vm += len >> PAGE_SHIFT;
if (flags & VM_LOCKED)
mm->locked_vm += (len >> PAGE_SHIFT);
+ vma->vm_flags |= VM_SOFTDIRTY;
return addr;
}
@@ -2780,7 +2778,6 @@
struct mm_struct *mm = vma->vm_mm;
struct vm_area_struct *new_vma, *prev;
struct rb_node **rb_link, *rb_parent;
- struct mempolicy *pol;
bool faulted_in_anon_vma = true;
/*
@@ -2825,10 +2822,8 @@
new_vma->vm_start = addr;
new_vma->vm_end = addr + len;
new_vma->vm_pgoff = pgoff;
- pol = mpol_dup(vma_policy(vma));
- if (IS_ERR(pol))
+ if (vma_dup_policy(vma, new_vma))
goto out_free_vma;
- vma_set_policy(new_vma, pol);
INIT_LIST_HEAD(&new_vma->anon_vma_chain);
if (anon_vma_clone(new_vma, vma))
goto out_free_mempol;
@@ -2843,7 +2838,7 @@
return new_vma;
out_free_mempol:
- mpol_put(pol);
+ mpol_put(vma_policy(new_vma));
out_free_vma:
kmem_cache_free(vm_area_cachep, new_vma);
return NULL;
@@ -2930,7 +2925,7 @@
vma->vm_start = addr;
vma->vm_end = addr + len;
- vma->vm_flags = vm_flags | mm->def_flags | VM_DONTEXPAND;
+ vma->vm_flags = vm_flags | mm->def_flags | VM_DONTEXPAND | VM_SOFTDIRTY;
vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
vma->vm_ops = &special_mapping_vmops;
diff --git a/mm/mremap.c b/mm/mremap.c
index 0843feb..91b13d6 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -25,6 +25,7 @@
#include <asm/uaccess.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
+#include <asm/pgalloc.h>
#include "internal.h"
@@ -62,8 +63,10 @@
return NULL;
pmd = pmd_alloc(mm, pud, addr);
- if (!pmd)
+ if (!pmd) {
+ pud_free(mm, pud);
return NULL;
+ }
VM_BUG_ON(pmd_trans_huge(*pmd));
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 98e75f2..314e9d2 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -678,9 +678,12 @@
*/
void pagefault_out_of_memory(void)
{
- struct zonelist *zonelist = node_zonelist(first_online_node,
- GFP_KERNEL);
+ struct zonelist *zonelist;
+ if (mem_cgroup_oom_synchronize())
+ return;
+
+ zonelist = node_zonelist(first_online_node, GFP_KERNEL);
if (try_set_zonelist_oom(zonelist, GFP_KERNEL)) {
out_of_memory(NULL, 0, 0, NULL, false);
clear_zonelist_oom(zonelist, GFP_KERNEL);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 3f0c895..f5236f8 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -36,8 +36,11 @@
#include <linux/pagevec.h>
#include <linux/timer.h>
#include <linux/sched/rt.h>
+#include <linux/mm_inline.h>
#include <trace/events/writeback.h>
+#include "internal.h"
+
/*
* Sleep at most 200ms at a time in balance_dirty_pages().
*/
@@ -241,9 +244,6 @@
if (!vm_highmem_is_dirtyable)
x -= highmem_dirtyable_memory(x);
- /* Subtract min_free_kbytes */
- x -= min_t(unsigned long, x, min_free_kbytes >> (PAGE_SHIFT - 10));
-
return x + 1; /* Ensure that we never return 0 */
}
@@ -585,6 +585,37 @@
}
/*
+ * setpoint - dirty 3
+ * f(dirty) := 1.0 + (----------------)
+ * limit - setpoint
+ *
+ * it's a 3rd order polynomial that subjects to
+ *
+ * (1) f(freerun) = 2.0 => rampup dirty_ratelimit reasonably fast
+ * (2) f(setpoint) = 1.0 => the balance point
+ * (3) f(limit) = 0 => the hard limit
+ * (4) df/dx <= 0 => negative feedback control
+ * (5) the closer to setpoint, the smaller |df/dx| (and the reverse)
+ * => fast response on large errors; small oscillation near setpoint
+ */
+static inline long long pos_ratio_polynom(unsigned long setpoint,
+ unsigned long dirty,
+ unsigned long limit)
+{
+ long long pos_ratio;
+ long x;
+
+ x = div_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT,
+ limit - setpoint + 1);
+ pos_ratio = x;
+ pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT;
+ pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT;
+ pos_ratio += 1 << RATELIMIT_CALC_SHIFT;
+
+ return clamp(pos_ratio, 0LL, 2LL << RATELIMIT_CALC_SHIFT);
+}
+
+/*
* Dirty position control.
*
* (o) global/bdi setpoints
@@ -682,26 +713,80 @@
/*
* global setpoint
*
- * setpoint - dirty 3
- * f(dirty) := 1.0 + (----------------)
- * limit - setpoint
- *
- * it's a 3rd order polynomial that subjects to
- *
- * (1) f(freerun) = 2.0 => rampup dirty_ratelimit reasonably fast
- * (2) f(setpoint) = 1.0 => the balance point
- * (3) f(limit) = 0 => the hard limit
- * (4) df/dx <= 0 => negative feedback control
- * (5) the closer to setpoint, the smaller |df/dx| (and the reverse)
- * => fast response on large errors; small oscillation near setpoint
+ * See comment for pos_ratio_polynom().
*/
setpoint = (freerun + limit) / 2;
- x = div_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT,
- limit - setpoint + 1);
- pos_ratio = x;
- pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT;
- pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT;
- pos_ratio += 1 << RATELIMIT_CALC_SHIFT;
+ pos_ratio = pos_ratio_polynom(setpoint, dirty, limit);
+
+ /*
+ * The strictlimit feature is a tool preventing mistrusted filesystems
+ * from growing a large number of dirty pages before throttling. For
+ * such filesystems balance_dirty_pages always checks bdi counters
+ * against bdi limits. Even if global "nr_dirty" is under "freerun".
+ * This is especially important for fuse which sets bdi->max_ratio to
+ * 1% by default. Without strictlimit feature, fuse writeback may
+ * consume arbitrary amount of RAM because it is accounted in
+ * NR_WRITEBACK_TEMP which is not involved in calculating "nr_dirty".
+ *
+ * Here, in bdi_position_ratio(), we calculate pos_ratio based on
+ * two values: bdi_dirty and bdi_thresh. Let's consider an example:
+ * total amount of RAM is 16GB, bdi->max_ratio is equal to 1%, global
+ * limits are set by default to 10% and 20% (background and throttle).
+ * Then bdi_thresh is 1% of 20% of 16GB. This amounts to ~8K pages.
+ * bdi_dirty_limit(bdi, bg_thresh) is about ~4K pages. bdi_setpoint is
+ * about ~6K pages (as the average of background and throttle bdi
+ * limits). The 3rd order polynomial will provide positive feedback if
+ * bdi_dirty is under bdi_setpoint and vice versa.
+ *
+ * Note, that we cannot use global counters in these calculations
+ * because we want to throttle process writing to a strictlimit BDI
+ * much earlier than global "freerun" is reached (~23MB vs. ~2.3GB
+ * in the example above).
+ */
+ if (unlikely(bdi->capabilities & BDI_CAP_STRICTLIMIT)) {
+ long long bdi_pos_ratio;
+ unsigned long bdi_bg_thresh;
+
+ if (bdi_dirty < 8)
+ return min_t(long long, pos_ratio * 2,
+ 2 << RATELIMIT_CALC_SHIFT);
+
+ if (bdi_dirty >= bdi_thresh)
+ return 0;
+
+ bdi_bg_thresh = div_u64((u64)bdi_thresh * bg_thresh, thresh);
+ bdi_setpoint = dirty_freerun_ceiling(bdi_thresh,
+ bdi_bg_thresh);
+
+ if (bdi_setpoint == 0 || bdi_setpoint == bdi_thresh)
+ return 0;
+
+ bdi_pos_ratio = pos_ratio_polynom(bdi_setpoint, bdi_dirty,
+ bdi_thresh);
+
+ /*
+ * Typically, for strictlimit case, bdi_setpoint << setpoint
+ * and pos_ratio >> bdi_pos_ratio. In the other words global
+ * state ("dirty") is not limiting factor and we have to
+ * make decision based on bdi counters. But there is an
+ * important case when global pos_ratio should get precedence:
+ * global limits are exceeded (e.g. due to activities on other
+ * BDIs) while given strictlimit BDI is below limit.
+ *
+ * "pos_ratio * bdi_pos_ratio" would work for the case above,
+ * but it would look too non-natural for the case of all
+ * activity in the system coming from a single strictlimit BDI
+ * with bdi->max_ratio == 100%.
+ *
+ * Note that min() below somewhat changes the dynamics of the
+ * control system. Normally, pos_ratio value can be well over 3
+ * (when globally we are at freerun and bdi is well below bdi
+ * setpoint). Now the maximum pos_ratio in the same situation
+ * is 2. We might want to tweak this if we observe the control
+ * system is too slow to adapt.
+ */
+ return min(pos_ratio, bdi_pos_ratio);
+ }
/*
* We have computed basic pos_ratio above based on global situation. If
@@ -994,6 +1079,27 @@
* keep that period small to reduce time lags).
*/
step = 0;
+
+ /*
+ * For strictlimit case, calculations above were based on bdi counters
+ * and limits (starting from pos_ratio = bdi_position_ratio() and up to
+ * balanced_dirty_ratelimit = task_ratelimit * write_bw / dirty_rate).
+ * Hence, to calculate "step" properly, we have to use bdi_dirty as
+ * "dirty" and bdi_setpoint as "setpoint".
+ *
+ * We rampup dirty_ratelimit forcibly if bdi_dirty is low because
+ * it's possible that bdi_thresh is close to zero due to inactivity
+ * of backing device (see the implementation of bdi_dirty_limit()).
+ */
+ if (unlikely(bdi->capabilities & BDI_CAP_STRICTLIMIT)) {
+ dirty = bdi_dirty;
+ if (bdi_dirty < 8)
+ setpoint = bdi_dirty + 1;
+ else
+ setpoint = (bdi_thresh +
+ bdi_dirty_limit(bdi, bg_thresh)) / 2;
+ }
+
if (dirty < setpoint) {
x = min(bdi->balanced_dirty_ratelimit,
min(balanced_dirty_ratelimit, task_ratelimit));
@@ -1198,6 +1304,56 @@
return pages >= DIRTY_POLL_THRESH ? 1 + t / 2 : t;
}
+static inline void bdi_dirty_limits(struct backing_dev_info *bdi,
+ unsigned long dirty_thresh,
+ unsigned long background_thresh,
+ unsigned long *bdi_dirty,
+ unsigned long *bdi_thresh,
+ unsigned long *bdi_bg_thresh)
+{
+ unsigned long bdi_reclaimable;
+
+ /*
+ * bdi_thresh is not treated as some limiting factor as
+ * dirty_thresh, due to reasons
+ * - in JBOD setup, bdi_thresh can fluctuate a lot
+ * - in a system with HDD and USB key, the USB key may somehow
+ * go into state (bdi_dirty >> bdi_thresh) either because
+ * bdi_dirty starts high, or because bdi_thresh drops low.
+ * In this case we don't want to hard throttle the USB key
+ * dirtiers for 100 seconds until bdi_dirty drops under
+ * bdi_thresh. Instead the auxiliary bdi control line in
+ * bdi_position_ratio() will let the dirtier task progress
+ * at some rate <= (write_bw / 2) for bringing down bdi_dirty.
+ */
+ *bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh);
+
+ if (bdi_bg_thresh)
+ *bdi_bg_thresh = div_u64((u64)*bdi_thresh *
+ background_thresh,
+ dirty_thresh);
+
+ /*
+ * In order to avoid the stacked BDI deadlock we need
+ * to ensure we accurately count the 'dirty' pages when
+ * the threshold is low.
+ *
+ * Otherwise it would be possible to get thresh+n pages
+ * reported dirty, even though there are thresh-m pages
+ * actually dirty; with m+n sitting in the percpu
+ * deltas.
+ */
+ if (*bdi_thresh < 2 * bdi_stat_error(bdi)) {
+ bdi_reclaimable = bdi_stat_sum(bdi, BDI_RECLAIMABLE);
+ *bdi_dirty = bdi_reclaimable +
+ bdi_stat_sum(bdi, BDI_WRITEBACK);
+ } else {
+ bdi_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE);
+ *bdi_dirty = bdi_reclaimable +
+ bdi_stat(bdi, BDI_WRITEBACK);
+ }
+}
+
/*
* balance_dirty_pages() must be called by processes which are generating dirty
* data. It looks at the number of dirty pages in the machine and will force
@@ -1209,13 +1365,9 @@
unsigned long pages_dirtied)
{
unsigned long nr_reclaimable; /* = file_dirty + unstable_nfs */
- unsigned long bdi_reclaimable;
unsigned long nr_dirty; /* = file_dirty + writeback + unstable_nfs */
- unsigned long bdi_dirty;
- unsigned long freerun;
unsigned long background_thresh;
unsigned long dirty_thresh;
- unsigned long bdi_thresh;
long period;
long pause;
long max_pause;
@@ -1226,10 +1378,16 @@
unsigned long dirty_ratelimit;
unsigned long pos_ratio;
struct backing_dev_info *bdi = mapping->backing_dev_info;
+ bool strictlimit = bdi->capabilities & BDI_CAP_STRICTLIMIT;
unsigned long start_time = jiffies;
for (;;) {
unsigned long now = jiffies;
+ unsigned long uninitialized_var(bdi_thresh);
+ unsigned long thresh;
+ unsigned long uninitialized_var(bdi_dirty);
+ unsigned long dirty;
+ unsigned long bg_thresh;
/*
* Unstable writes are a feature of certain networked
@@ -1243,61 +1401,44 @@
global_dirty_limits(&background_thresh, &dirty_thresh);
+ if (unlikely(strictlimit)) {
+ bdi_dirty_limits(bdi, dirty_thresh, background_thresh,
+ &bdi_dirty, &bdi_thresh, &bg_thresh);
+
+ dirty = bdi_dirty;
+ thresh = bdi_thresh;
+ } else {
+ dirty = nr_dirty;
+ thresh = dirty_thresh;
+ bg_thresh = background_thresh;
+ }
+
/*
* Throttle it only when the background writeback cannot
* catch-up. This avoids (excessively) small writeouts
- * when the bdi limits are ramping up.
+ * when the bdi limits are ramping up in case of !strictlimit.
+ *
+ * In strictlimit case make decision based on the bdi counters
+ * and limits. Small writeouts when the bdi limits are ramping
+ * up are the price we consciously pay for strictlimit-ing.
*/
- freerun = dirty_freerun_ceiling(dirty_thresh,
- background_thresh);
- if (nr_dirty <= freerun) {
+ if (dirty <= dirty_freerun_ceiling(thresh, bg_thresh)) {
current->dirty_paused_when = now;
current->nr_dirtied = 0;
current->nr_dirtied_pause =
- dirty_poll_interval(nr_dirty, dirty_thresh);
+ dirty_poll_interval(dirty, thresh);
break;
}
if (unlikely(!writeback_in_progress(bdi)))
bdi_start_background_writeback(bdi);
- /*
- * bdi_thresh is not treated as some limiting factor as
- * dirty_thresh, due to reasons
- * - in JBOD setup, bdi_thresh can fluctuate a lot
- * - in a system with HDD and USB key, the USB key may somehow
- * go into state (bdi_dirty >> bdi_thresh) either because
- * bdi_dirty starts high, or because bdi_thresh drops low.
- * In this case we don't want to hard throttle the USB key
- * dirtiers for 100 seconds until bdi_dirty drops under
- * bdi_thresh. Instead the auxiliary bdi control line in
- * bdi_position_ratio() will let the dirtier task progress
- * at some rate <= (write_bw / 2) for bringing down bdi_dirty.
- */
- bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh);
-
- /*
- * In order to avoid the stacked BDI deadlock we need
- * to ensure we accurately count the 'dirty' pages when
- * the threshold is low.
- *
- * Otherwise it would be possible to get thresh+n pages
- * reported dirty, even though there are thresh-m pages
- * actually dirty; with m+n sitting in the percpu
- * deltas.
- */
- if (bdi_thresh < 2 * bdi_stat_error(bdi)) {
- bdi_reclaimable = bdi_stat_sum(bdi, BDI_RECLAIMABLE);
- bdi_dirty = bdi_reclaimable +
- bdi_stat_sum(bdi, BDI_WRITEBACK);
- } else {
- bdi_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE);
- bdi_dirty = bdi_reclaimable +
- bdi_stat(bdi, BDI_WRITEBACK);
- }
+ if (!strictlimit)
+ bdi_dirty_limits(bdi, dirty_thresh, background_thresh,
+ &bdi_dirty, &bdi_thresh, NULL);
dirty_exceeded = (bdi_dirty > bdi_thresh) &&
- (nr_dirty > dirty_thresh);
+ ((nr_dirty > dirty_thresh) || strictlimit);
if (dirty_exceeded && !bdi->dirty_exceeded)
bdi->dirty_exceeded = 1;
@@ -2002,11 +2143,17 @@
/*
* Helper function for set_page_writeback family.
+ *
+ * The caller must hold mem_cgroup_begin/end_update_page_stat() lock
+ * while calling this function.
+ * See test_set_page_writeback for example.
+ *
* NOTE: Unlike account_page_dirtied this does not rely on being atomic
* wrt interrupts.
*/
void account_page_writeback(struct page *page)
{
+ mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_WRITEBACK);
inc_zone_page_state(page, NR_WRITEBACK);
}
EXPORT_SYMBOL(account_page_writeback);
@@ -2223,7 +2370,10 @@
{
struct address_space *mapping = page_mapping(page);
int ret;
+ bool locked;
+ unsigned long memcg_flags;
+ mem_cgroup_begin_update_page_stat(page, &locked, &memcg_flags);
if (mapping) {
struct backing_dev_info *bdi = mapping->backing_dev_info;
unsigned long flags;
@@ -2244,9 +2394,11 @@
ret = TestClearPageWriteback(page);
}
if (ret) {
+ mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_WRITEBACK);
dec_zone_page_state(page, NR_WRITEBACK);
inc_zone_page_state(page, NR_WRITTEN);
}
+ mem_cgroup_end_update_page_stat(page, &locked, &memcg_flags);
return ret;
}
@@ -2254,7 +2406,10 @@
{
struct address_space *mapping = page_mapping(page);
int ret;
+ bool locked;
+ unsigned long memcg_flags;
+ mem_cgroup_begin_update_page_stat(page, &locked, &memcg_flags);
if (mapping) {
struct backing_dev_info *bdi = mapping->backing_dev_info;
unsigned long flags;
@@ -2281,6 +2436,7 @@
}
if (!ret)
account_page_writeback(page);
+ mem_cgroup_end_update_page_stat(page, &locked, &memcg_flags);
return ret;
}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c2b59db..0ee638f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -56,6 +56,7 @@
#include <linux/ftrace_event.h>
#include <linux/memcontrol.h>
#include <linux/prefetch.h>
+#include <linux/mm_inline.h>
#include <linux/migrate.h>
#include <linux/page-debug-flags.h>
#include <linux/hugetlb.h>
@@ -488,8 +489,10 @@
* (c) a page and its buddy have the same order &&
* (d) a page and its buddy are in the same zone.
*
- * For recording whether a page is in the buddy system, we set ->_mapcount -2.
- * Setting, clearing, and testing _mapcount -2 is serialized by zone->lock.
+ * For recording whether a page is in the buddy system, we set ->_mapcount
+ * PAGE_BUDDY_MAPCOUNT_VALUE.
+ * Setting, clearing, and testing _mapcount PAGE_BUDDY_MAPCOUNT_VALUE is
+ * serialized by zone->lock.
*
* For recording page's order, we use page_private(page).
*/
@@ -527,8 +530,9 @@
* as necessary, plus some accounting needed to play nicely with other
* parts of the VM system.
* At each level, we keep a list of pages, which are heads of continuous
- * free pages of length of (1 << order) and marked with _mapcount -2. Page's
- * order is recorded in page_private(page) field.
+ * free pages of length of (1 << order) and marked with _mapcount
+ * PAGE_BUDDY_MAPCOUNT_VALUE. Page's order is recorded in page_private(page)
+ * field.
* So when we are allocating or freeing one, we can derive the state of the
* other. That is, if we allocate a small block, and both were
* free, the remainder of the region must be split into blocks.
@@ -647,7 +651,6 @@
int to_free = count;
spin_lock(&zone->lock);
- zone->all_unreclaimable = 0;
zone->pages_scanned = 0;
while (to_free) {
@@ -696,7 +699,6 @@
int migratetype)
{
spin_lock(&zone->lock);
- zone->all_unreclaimable = 0;
zone->pages_scanned = 0;
__free_one_page(page, zone, order, migratetype);
@@ -721,7 +723,8 @@
return false;
if (!PageHighMem(page)) {
- debug_check_no_locks_freed(page_address(page),PAGE_SIZE<<order);
+ debug_check_no_locks_freed(page_address(page),
+ PAGE_SIZE << order);
debug_check_no_obj_freed(page_address(page),
PAGE_SIZE << order);
}
@@ -750,19 +753,19 @@
void __init __free_pages_bootmem(struct page *page, unsigned int order)
{
unsigned int nr_pages = 1 << order;
+ struct page *p = page;
unsigned int loop;
- prefetchw(page);
- for (loop = 0; loop < nr_pages; loop++) {
- struct page *p = &page[loop];
-
- if (loop + 1 < nr_pages)
- prefetchw(p + 1);
+ prefetchw(p);
+ for (loop = 0; loop < (nr_pages - 1); loop++, p++) {
+ prefetchw(p + 1);
__ClearPageReserved(p);
set_page_count(p, 0);
}
+ __ClearPageReserved(p);
+ set_page_count(p, 0);
- page_zone(page)->managed_pages += 1 << order;
+ page_zone(page)->managed_pages += nr_pages;
set_page_refcounted(page);
__free_pages(page, order);
}
@@ -885,7 +888,7 @@
int migratetype)
{
unsigned int current_order;
- struct free_area * area;
+ struct free_area *area;
struct page *page;
/* Find a page of the appropriate size in the preferred list */
@@ -1007,14 +1010,60 @@
}
}
+/*
+ * If breaking a large block of pages, move all free pages to the preferred
+ * allocation list. If falling back for a reclaimable kernel allocation, be
+ * more aggressive about taking ownership of free pages.
+ *
+ * On the other hand, never change migration type of MIGRATE_CMA pageblocks
+ * nor move CMA pages to different free lists. We don't want unmovable pages
+ * to be allocated from MIGRATE_CMA areas.
+ *
+ * Returns the new migratetype of the pageblock (or the same old migratetype
+ * if it was unchanged).
+ */
+static int try_to_steal_freepages(struct zone *zone, struct page *page,
+ int start_type, int fallback_type)
+{
+ int current_order = page_order(page);
+
+ if (is_migrate_cma(fallback_type))
+ return fallback_type;
+
+ /* Take ownership for orders >= pageblock_order */
+ if (current_order >= pageblock_order) {
+ change_pageblock_range(page, current_order, start_type);
+ return start_type;
+ }
+
+ if (current_order >= pageblock_order / 2 ||
+ start_type == MIGRATE_RECLAIMABLE ||
+ page_group_by_mobility_disabled) {
+ int pages;
+
+ pages = move_freepages_block(zone, page, start_type);
+
+ /* Claim the whole block if over half of it is free */
+ if (pages >= (1 << (pageblock_order-1)) ||
+ page_group_by_mobility_disabled) {
+
+ set_pageblock_migratetype(page, start_type);
+ return start_type;
+ }
+
+ }
+
+ return fallback_type;
+}
+
/* Remove an element from the buddy allocator from the fallback list */
static inline struct page *
__rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
{
- struct free_area * area;
+ struct free_area *area;
int current_order;
struct page *page;
- int migratetype, i;
+ int migratetype, new_type, i;
/* Find the largest possible block of pages in the other list */
for (current_order = MAX_ORDER-1; current_order >= order;
@@ -1034,51 +1083,29 @@
struct page, lru);
area->nr_free--;
- /*
- * If breaking a large block of pages, move all free
- * pages to the preferred allocation list. If falling
- * back for a reclaimable kernel allocation, be more
- * aggressive about taking ownership of free pages
- *
- * On the other hand, never change migration
- * type of MIGRATE_CMA pageblocks nor move CMA
- * pages on different free lists. We don't
- * want unmovable pages to be allocated from
- * MIGRATE_CMA areas.
- */
- if (!is_migrate_cma(migratetype) &&
- (current_order >= pageblock_order / 2 ||
- start_migratetype == MIGRATE_RECLAIMABLE ||
- page_group_by_mobility_disabled)) {
- int pages;
- pages = move_freepages_block(zone, page,
- start_migratetype);
-
- /* Claim the whole block if over half of it is free */
- if (pages >= (1 << (pageblock_order-1)) ||
- page_group_by_mobility_disabled)
- set_pageblock_migratetype(page,
- start_migratetype);
-
- migratetype = start_migratetype;
- }
+ new_type = try_to_steal_freepages(zone, page,
+ start_migratetype,
+ migratetype);
/* Remove the page from the freelists */
list_del(&page->lru);
rmv_page_order(page);
- /* Take ownership for orders >= pageblock_order */
- if (current_order >= pageblock_order &&
- !is_migrate_cma(migratetype))
- change_pageblock_range(page, current_order,
- start_migratetype);
-
+ /*
+ * Borrow the excess buddy pages as well, irrespective
+ * of whether we stole freepages, or took ownership of
+ * the pageblock or not.
+ *
+ * Exception: When borrowing from MIGRATE_CMA, release
+ * the excess buddy pages to CMA itself.
+ */
expand(zone, page, order, current_order, area,
is_migrate_cma(migratetype)
? migratetype : start_migratetype);
- trace_mm_page_alloc_extfrag(page, order, current_order,
- start_migratetype, migratetype);
+ trace_mm_page_alloc_extfrag(page, order,
+ current_order, start_migratetype, migratetype,
+ new_type == start_migratetype);
return page;
}
@@ -1281,7 +1308,7 @@
int order, t;
struct list_head *curr;
- if (!zone->spanned_pages)
+ if (zone_is_empty(zone))
return;
spin_lock_irqsave(&zone->lock, flags);
@@ -1526,6 +1553,7 @@
get_pageblock_migratetype(page));
}
+ __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
__count_zone_vm_events(PGALLOC, zone, 1 << order);
zone_statistics(preferred_zone, zone, gfp_flags);
local_irq_restore(flags);
@@ -1792,6 +1820,11 @@
bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
}
+static bool zone_local(struct zone *local_zone, struct zone *zone)
+{
+ return node_distance(local_zone->node, zone->node) == LOCAL_DISTANCE;
+}
+
static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
{
return node_isset(local_zone->node, zone->zone_pgdat->reclaim_nodes);
@@ -1829,6 +1862,11 @@
{
}
+static bool zone_local(struct zone *local_zone, struct zone *zone)
+{
+ return true;
+}
+
static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
{
return true;
@@ -1860,16 +1898,41 @@
zonelist_scan:
/*
* Scan zonelist, looking for a zone with enough free.
- * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
+ * See also __cpuset_node_allowed_softwall() comment in kernel/cpuset.c.
*/
for_each_zone_zonelist_nodemask(zone, z, zonelist,
high_zoneidx, nodemask) {
+ unsigned long mark;
+
if (IS_ENABLED(CONFIG_NUMA) && zlc_active &&
!zlc_zone_worth_trying(zonelist, z, allowednodes))
continue;
if ((alloc_flags & ALLOC_CPUSET) &&
!cpuset_zone_allowed_softwall(zone, gfp_mask))
continue;
+ BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK);
+ if (unlikely(alloc_flags & ALLOC_NO_WATERMARKS))
+ goto try_this_zone;
+ /*
+ * Distribute pages in proportion to the individual
+ * zone size to ensure fair page aging. The zone a
+ * page was allocated in should have no effect on the
+ * time the page has in memory before being reclaimed.
+ *
+ * When zone_reclaim_mode is enabled, try to stay in
+ * local zones in the fastpath. If that fails, the
+ * slowpath is entered, which will do another pass
+ * starting with the local zones, but ultimately fall
+ * back to remote zones that do not partake in the
+ * fairness round-robin cycle of this zonelist.
+ */
+ if (alloc_flags & ALLOC_WMARK_LOW) {
+ if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0)
+ continue;
+ if (zone_reclaim_mode &&
+ !zone_local(preferred_zone, zone))
+ continue;
+ }
/*
* When allocating a page cache page for writing, we
* want to get it from a zone that is within its dirty
@@ -1900,16 +1963,11 @@
(gfp_mask & __GFP_WRITE) && !zone_dirty_ok(zone))
goto this_zone_full;
- BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK);
- if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {
- unsigned long mark;
+ mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
+ if (!zone_watermark_ok(zone, order, mark,
+ classzone_idx, alloc_flags)) {
int ret;
- mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
- if (zone_watermark_ok(zone, order, mark,
- classzone_idx, alloc_flags))
- goto try_this_zone;
-
if (IS_ENABLED(CONFIG_NUMA) &&
!did_zlc_setup && nr_online_nodes > 1) {
/*
@@ -2321,16 +2379,30 @@
return page;
}
-static inline
-void wake_all_kswapd(unsigned int order, struct zonelist *zonelist,
- enum zone_type high_zoneidx,
- enum zone_type classzone_idx)
+static void prepare_slowpath(gfp_t gfp_mask, unsigned int order,
+ struct zonelist *zonelist,
+ enum zone_type high_zoneidx,
+ struct zone *preferred_zone)
{
struct zoneref *z;
struct zone *zone;
- for_each_zone_zonelist(zone, z, zonelist, high_zoneidx)
- wakeup_kswapd(zone, order, classzone_idx);
+ for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
+ if (!(gfp_mask & __GFP_NO_KSWAPD))
+ wakeup_kswapd(zone, order, zone_idx(preferred_zone));
+ /*
+ * Only reset the batches of zones that were actually
+ * considered in the fast path, we don't want to
+ * thrash fairness information for zones that are not
+ * actually part of this zonelist's round-robin cycle.
+ */
+ if (zone_reclaim_mode && !zone_local(preferred_zone, zone))
+ continue;
+ mod_zone_page_state(zone, NR_ALLOC_BATCH,
+ high_wmark_pages(zone) -
+ low_wmark_pages(zone) -
+ zone_page_state(zone, NR_ALLOC_BATCH));
+ }
}
static inline int
@@ -2426,9 +2498,8 @@
goto nopage;
restart:
- if (!(gfp_mask & __GFP_NO_KSWAPD))
- wake_all_kswapd(order, zonelist, high_zoneidx,
- zone_idx(preferred_zone));
+ prepare_slowpath(gfp_mask, order, zonelist,
+ high_zoneidx, preferred_zone);
/*
* OK, we're below the kswapd watermark and have kicked background
@@ -3095,7 +3166,7 @@
K(zone_page_state(zone, NR_FREE_CMA_PAGES)),
K(zone_page_state(zone, NR_WRITEBACK_TEMP)),
zone->pages_scanned,
- (zone->all_unreclaimable ? "yes" : "no")
+ (!zone_reclaimable(zone) ? "yes" : "no")
);
printk("lowmem_reserve[]:");
for (i = 0; i < MAX_NR_ZONES; i++)
@@ -3104,7 +3175,7 @@
}
for_each_populated_zone(zone) {
- unsigned long nr[MAX_ORDER], flags, order, total = 0;
+ unsigned long nr[MAX_ORDER], flags, order, total = 0;
unsigned char types[MAX_ORDER];
if (skip_free_areas_node(filter, zone_to_nid(zone)))
@@ -3416,11 +3487,11 @@
static int default_zonelist_order(void)
{
int nid, zone_type;
- unsigned long low_kmem_size,total_size;
+ unsigned long low_kmem_size, total_size;
struct zone *z;
int average_size;
/*
- * ZONE_DMA and ZONE_DMA32 can be very small area in the system.
+ * ZONE_DMA and ZONE_DMA32 can be very small area in the system.
* If they are really small and used heavily, the system can fall
* into OOM very easily.
* This function detect ZONE_DMA/DMA32 size and configures zone order.
@@ -3452,9 +3523,9 @@
return ZONELIST_ORDER_NODE;
/*
* look into each node's config.
- * If there is a node whose DMA/DMA32 memory is very big area on
- * local memory, NODE_ORDER may be suitable.
- */
+ * If there is a node whose DMA/DMA32 memory is very big area on
+ * local memory, NODE_ORDER may be suitable.
+ */
average_size = total_size /
(nodes_weight(node_states[N_MEMORY]) + 1);
for_each_online_node(nid) {
@@ -4180,7 +4251,7 @@
if (!zone->wait_table)
return -ENOMEM;
- for(i = 0; i < zone->wait_table_hash_nr_entries; ++i)
+ for (i = 0; i < zone->wait_table_hash_nr_entries; ++i)
init_waitqueue_head(zone->wait_table + i);
return 0;
@@ -4237,7 +4308,7 @@
int __meminit __early_pfn_to_nid(unsigned long pfn)
{
unsigned long start_pfn, end_pfn;
- int i, nid;
+ int nid;
/*
* NOTE: The following SMP-unsafe globals are only used early in boot
* when the kernel is running single-threaded.
@@ -4248,15 +4319,14 @@
if (last_start_pfn <= pfn && pfn < last_end_pfn)
return last_nid;
- for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid)
- if (start_pfn <= pfn && pfn < end_pfn) {
- last_start_pfn = start_pfn;
- last_end_pfn = end_pfn;
- last_nid = nid;
- return nid;
- }
- /* This is a memory hole */
- return -1;
+ nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn);
+ if (nid != -1) {
+ last_start_pfn = start_pfn;
+ last_end_pfn = end_pfn;
+ last_nid = nid;
+ }
+
+ return nid;
}
#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */
@@ -4586,7 +4656,7 @@
#ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
/* Initialise the number of pages represented by NR_PAGEBLOCK_BITS */
-void __init set_pageblock_order(void)
+void __paginginit set_pageblock_order(void)
{
unsigned int order;
@@ -4614,7 +4684,7 @@
* include/linux/pageblock-flags.h for the values of pageblock_order based on
* the kernel config
*/
-void __init set_pageblock_order(void)
+void __paginginit set_pageblock_order(void)
{
}
@@ -4728,8 +4798,11 @@
spin_lock_init(&zone->lru_lock);
zone_seqlock_init(zone);
zone->zone_pgdat = pgdat;
-
zone_pcp_init(zone);
+
+ /* For bootup, initialized properly in watermark setup */
+ mod_zone_page_state(zone, NR_ALLOC_BATCH, zone->managed_pages);
+
lruvec_init(&zone->lruvec);
if (!size)
continue;
@@ -4930,7 +5003,7 @@
if (pages)
node_set_state(nid, N_MEMORY);
}
- return totalpages;
+ return totalpages;
}
/*
@@ -5047,7 +5120,7 @@
/*
* Some kernelcore has been met, update counts and
* break if the kernelcore for this node has been
- * satisified
+ * satisfied
*/
required_kernelcore -= min(required_kernelcore,
size_pages);
@@ -5061,7 +5134,7 @@
* If there is still required_kernelcore, we do another pass with one
* less node in the count. This will push zone_movable_pfn[nid] further
* along on the nodes that still have memory until kernelcore is
- * satisified
+ * satisfied
*/
usable_nodes--;
if (usable_nodes && required_kernelcore > usable_nodes)
@@ -5286,8 +5359,10 @@
* 3) .rodata.* may be embedded into .text or .data sections.
*/
#define adj_init_size(start, end, size, pos, adj) \
- if (start <= pos && pos < end && size > adj) \
- size -= adj;
+ do { \
+ if (start <= pos && pos < end && size > adj) \
+ size -= adj; \
+ } while (0)
adj_init_size(__init_begin, __init_end, init_data_size,
_sinittext, init_code_size);
@@ -5361,7 +5436,7 @@
* This is only okay since the processor is dead and cannot
* race with what we are doing.
*/
- refresh_cpu_vm_stats(cpu);
+ cpu_vm_stats_fold(cpu);
}
return NOTIFY_OK;
}
@@ -5498,6 +5573,11 @@
zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + (tmp >> 2);
zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1);
+ __mod_zone_page_state(zone, NR_ALLOC_BATCH,
+ high_wmark_pages(zone) -
+ low_wmark_pages(zone) -
+ zone_page_state(zone, NR_ALLOC_BATCH));
+
setup_zone_migrate_reserve(zone);
spin_unlock_irqrestore(&zone->lock, flags);
}
@@ -5570,7 +5650,7 @@
* we want it large (64MB max). But it is not linear, because network
* bandwidth does not increase linearly with machine size. We use
*
- * min_free_kbytes = 4 * sqrt(lowmem_kbytes), for better accuracy:
+ * min_free_kbytes = 4 * sqrt(lowmem_kbytes), for better accuracy:
* min_free_kbytes = sqrt(lowmem_kbytes * 16)
*
* which yields
@@ -5614,11 +5694,11 @@
module_init(init_per_zone_wmark_min)
/*
- * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so
+ * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so
* that we can call two helper functions whenever min_free_kbytes
* changes.
*/
-int min_free_kbytes_sysctl_handler(ctl_table *table, int write,
+int min_free_kbytes_sysctl_handler(ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
{
proc_dointvec(table, write, buffer, length, ppos);
@@ -5682,8 +5762,8 @@
/*
* percpu_pagelist_fraction - changes the pcp->high for each zone on each
- * cpu. It is the fraction of total pages in each zone that a hot per cpu pagelist
- * can have before it gets flushed back to buddy allocator.
+ * cpu. It is the fraction of total pages in each zone that a hot per cpu
+ * pagelist can have before it gets flushed back to buddy allocator.
*/
int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
@@ -5745,9 +5825,10 @@
if (!numentries) {
/* round applicable memory size up to nearest megabyte */
numentries = nr_kernel_pages;
- numentries += (1UL << (20 - PAGE_SHIFT)) - 1;
- numentries >>= 20 - PAGE_SHIFT;
- numentries <<= 20 - PAGE_SHIFT;
+
+ /* It isn't necessary when PAGE_SIZE >= 1MB */
+ if (PAGE_SHIFT < 20)
+ numentries = round_up(numentries, (1<<20)/PAGE_SIZE);
/* limit to 1 bucket per 2^scale bytes of low memory */
if (scale > PAGE_SHIFT)
@@ -5900,7 +5981,7 @@
* This function checks whether pageblock includes unmovable pages or not.
* If @count is not zero, it is okay to include less @count unmovable pages
*
- * PageLRU check wihtout isolation or lru_lock could race so that
+ * PageLRU check without isolation or lru_lock could race so that
* MIGRATE_MOVABLE block might include unmovable pages. It means you can't
* expect this function should be exact.
*/
@@ -5928,6 +6009,17 @@
continue;
page = pfn_to_page(check);
+
+ /*
+ * Hugepages are not in LRU lists, but they're movable.
+ * We need not scan over tail pages bacause we don't
+ * handle each tail page individually in migration.
+ */
+ if (PageHuge(page)) {
+ iter = round_up(iter + 1, 1<<compound_order(page)) - 1;
+ continue;
+ }
+
/*
* We can't use page_count without pin a page
* because another CPU can free compound page.
diff --git a/mm/page_io.c b/mm/page_io.c
index ba05b64..8c79a47 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -266,7 +266,6 @@
init_sync_kiocb(&kiocb, swap_file);
kiocb.ki_pos = page_file_offset(page);
- kiocb.ki_left = PAGE_SIZE;
kiocb.ki_nbytes = PAGE_SIZE;
set_page_writeback(page);
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 0cee10f..d1473b2 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -6,6 +6,7 @@
#include <linux/page-isolation.h>
#include <linux/pageblock-flags.h>
#include <linux/memory.h>
+#include <linux/hugetlb.h>
#include "internal.h"
int set_migratetype_isolate(struct page *page, bool skip_hwpoisoned_pages)
@@ -252,6 +253,19 @@
{
gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE;
+ /*
+ * TODO: allocate a destination hugepage from a nearest neighbor node,
+ * accordance with memory policy of the user process if possible. For
+ * now as a simple work-around, we use the next node for destination.
+ */
+ if (PageHuge(page)) {
+ nodemask_t src = nodemask_of_node(page_to_nid(page));
+ nodemask_t dst;
+ nodes_complement(dst, src);
+ return alloc_huge_page_node(page_hstate(compound_head(page)),
+ next_node(page_to_nid(page), dst));
+ }
+
if (PageHighMem(page))
gfp_mask |= __GFP_HIGHMEM;
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index e1a6e4f..3929a40 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -10,6 +10,30 @@
#include <asm/tlb.h>
#include <asm-generic/pgtable.h>
+/*
+ * If a p?d_bad entry is found while walking page tables, report
+ * the error, before resetting entry to p?d_none. Usually (but
+ * very seldom) called out from the p?d_none_or_clear_bad macros.
+ */
+
+void pgd_clear_bad(pgd_t *pgd)
+{
+ pgd_ERROR(*pgd);
+ pgd_clear(pgd);
+}
+
+void pud_clear_bad(pud_t *pud)
+{
+ pud_ERROR(*pud);
+ pud_clear(pud);
+}
+
+void pmd_clear_bad(pmd_t *pmd)
+{
+ pmd_ERROR(*pmd);
+ pmd_clear(pmd);
+}
+
#ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
/*
* Only sets the access flags (dirty, accessed), as well as write
diff --git a/mm/readahead.c b/mm/readahead.c
index 829a77c..e4ed041 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -371,10 +371,10 @@
size = count_history_pages(mapping, ra, offset, max);
/*
- * no history pages:
+ * not enough history pages:
* it could be a random read
*/
- if (!size)
+ if (size <= req_size)
return 0;
/*
@@ -385,8 +385,8 @@
size *= 2;
ra->start = offset;
- ra->size = get_init_ra_size(size + req_size, max);
- ra->async_size = ra->size;
+ ra->size = min(size + req_size, max);
+ ra->async_size = 1;
return 1;
}
diff --git a/mm/rmap.c b/mm/rmap.c
index 07748e6..fd3ee7a 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1052,11 +1052,11 @@
{
int first = atomic_inc_and_test(&page->_mapcount);
if (first) {
- if (!PageTransHuge(page))
- __inc_zone_page_state(page, NR_ANON_PAGES);
- else
+ if (PageTransHuge(page))
__inc_zone_page_state(page,
NR_ANON_TRANSPARENT_HUGEPAGES);
+ __mod_zone_page_state(page_zone(page), NR_ANON_PAGES,
+ hpage_nr_pages(page));
}
if (unlikely(PageKsm(page)))
return;
@@ -1085,10 +1085,10 @@
VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end);
SetPageSwapBacked(page);
atomic_set(&page->_mapcount, 0); /* increment count (starts at -1) */
- if (!PageTransHuge(page))
- __inc_zone_page_state(page, NR_ANON_PAGES);
- else
+ if (PageTransHuge(page))
__inc_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES);
+ __mod_zone_page_state(page_zone(page), NR_ANON_PAGES,
+ hpage_nr_pages(page));
__page_set_anon_rmap(page, vma, address, 1);
if (!mlocked_vma_newpage(vma, page)) {
SetPageActive(page);
@@ -1111,7 +1111,7 @@
mem_cgroup_begin_update_page_stat(page, &locked, &flags);
if (atomic_inc_and_test(&page->_mapcount)) {
__inc_zone_page_state(page, NR_FILE_MAPPED);
- mem_cgroup_inc_page_stat(page, MEMCG_NR_FILE_MAPPED);
+ mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED);
}
mem_cgroup_end_update_page_stat(page, &locked, &flags);
}
@@ -1148,14 +1148,14 @@
goto out;
if (anon) {
mem_cgroup_uncharge_page(page);
- if (!PageTransHuge(page))
- __dec_zone_page_state(page, NR_ANON_PAGES);
- else
+ if (PageTransHuge(page))
__dec_zone_page_state(page,
NR_ANON_TRANSPARENT_HUGEPAGES);
+ __mod_zone_page_state(page_zone(page), NR_ANON_PAGES,
+ -hpage_nr_pages(page));
} else {
__dec_zone_page_state(page, NR_FILE_MAPPED);
- mem_cgroup_dec_page_stat(page, MEMCG_NR_FILE_MAPPED);
+ mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED);
mem_cgroup_end_update_page_stat(page, &locked, &flags);
}
if (unlikely(PageMlocked(page)))
diff --git a/mm/shmem.c b/mm/shmem.c
index 5261498..8297623 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1205,7 +1205,7 @@
gfp & GFP_RECLAIM_MASK);
if (error)
goto decused;
- error = radix_tree_preload(gfp & GFP_RECLAIM_MASK);
+ error = radix_tree_maybe_preload(gfp & GFP_RECLAIM_MASK);
if (!error) {
error = shmem_add_to_page_cache(page, mapping, index,
gfp, NULL);
@@ -2819,6 +2819,10 @@
{
int error;
+ /* If rootfs called this, don't re-init */
+ if (shmem_inode_cachep)
+ return 0;
+
error = bdi_init(&shmem_backing_dev_info);
if (error)
goto out4;
diff --git a/mm/slub.c b/mm/slub.c
index e3ba1f2..51df827 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -4420,7 +4420,7 @@
unsigned long order;
int err;
- err = strict_strtoul(buf, 10, &order);
+ err = kstrtoul(buf, 10, &order);
if (err)
return err;
@@ -4448,7 +4448,7 @@
unsigned long min;
int err;
- err = strict_strtoul(buf, 10, &min);
+ err = kstrtoul(buf, 10, &min);
if (err)
return err;
@@ -4468,7 +4468,7 @@
unsigned long objects;
int err;
- err = strict_strtoul(buf, 10, &objects);
+ err = kstrtoul(buf, 10, &objects);
if (err)
return err;
if (objects && !kmem_cache_has_cpu_partial(s))
@@ -4784,7 +4784,7 @@
unsigned long ratio;
int err;
- err = strict_strtoul(buf, 10, &ratio);
+ err = kstrtoul(buf, 10, &ratio);
if (err)
return err;
diff --git a/mm/sparse.c b/mm/sparse.c
index 308d5033..4ac1d7e 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -339,13 +339,14 @@
}
#endif /* CONFIG_MEMORY_HOTREMOVE */
-static void __init sparse_early_usemaps_alloc_node(unsigned long**usemap_map,
+static void __init sparse_early_usemaps_alloc_node(void *data,
unsigned long pnum_begin,
unsigned long pnum_end,
unsigned long usemap_count, int nodeid)
{
void *usemap;
unsigned long pnum;
+ unsigned long **usemap_map = (unsigned long **)data;
int size = usemap_size();
usemap = sparse_early_usemaps_alloc_pgdat_section(NODE_DATA(nodeid),
@@ -430,11 +431,12 @@
#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
-static void __init sparse_early_mem_maps_alloc_node(struct page **map_map,
+static void __init sparse_early_mem_maps_alloc_node(void *data,
unsigned long pnum_begin,
unsigned long pnum_end,
unsigned long map_count, int nodeid)
{
+ struct page **map_map = (struct page **)data;
sparse_mem_maps_populate_node(map_map, pnum_begin, pnum_end,
map_count, nodeid);
}
@@ -460,88 +462,18 @@
{
}
-/*
- * Allocate the accumulated non-linear sections, allocate a mem_map
- * for each and record the physical to section mapping.
+/**
+ * alloc_usemap_and_memmap - memory alloction for pageblock flags and vmemmap
+ * @map: usemap_map for pageblock flags or mmap_map for vmemmap
*/
-void __init sparse_init(void)
+static void __init alloc_usemap_and_memmap(void (*alloc_func)
+ (void *, unsigned long, unsigned long,
+ unsigned long, int), void *data)
{
unsigned long pnum;
- struct page *map;
- unsigned long *usemap;
- unsigned long **usemap_map;
- int size;
+ unsigned long map_count;
int nodeid_begin = 0;
unsigned long pnum_begin = 0;
- unsigned long usemap_count;
-#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
- unsigned long map_count;
- int size2;
- struct page **map_map;
-#endif
-
- /* see include/linux/mmzone.h 'struct mem_section' definition */
- BUILD_BUG_ON(!is_power_of_2(sizeof(struct mem_section)));
-
- /* Setup pageblock_order for HUGETLB_PAGE_SIZE_VARIABLE */
- set_pageblock_order();
-
- /*
- * map is using big page (aka 2M in x86 64 bit)
- * usemap is less one page (aka 24 bytes)
- * so alloc 2M (with 2M align) and 24 bytes in turn will
- * make next 2M slip to one more 2M later.
- * then in big system, the memory will have a lot of holes...
- * here try to allocate 2M pages continuously.
- *
- * powerpc need to call sparse_init_one_section right after each
- * sparse_early_mem_map_alloc, so allocate usemap_map at first.
- */
- size = sizeof(unsigned long *) * NR_MEM_SECTIONS;
- usemap_map = alloc_bootmem(size);
- if (!usemap_map)
- panic("can not allocate usemap_map\n");
-
- for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
- struct mem_section *ms;
-
- if (!present_section_nr(pnum))
- continue;
- ms = __nr_to_section(pnum);
- nodeid_begin = sparse_early_nid(ms);
- pnum_begin = pnum;
- break;
- }
- usemap_count = 1;
- for (pnum = pnum_begin + 1; pnum < NR_MEM_SECTIONS; pnum++) {
- struct mem_section *ms;
- int nodeid;
-
- if (!present_section_nr(pnum))
- continue;
- ms = __nr_to_section(pnum);
- nodeid = sparse_early_nid(ms);
- if (nodeid == nodeid_begin) {
- usemap_count++;
- continue;
- }
- /* ok, we need to take cake of from pnum_begin to pnum - 1*/
- sparse_early_usemaps_alloc_node(usemap_map, pnum_begin, pnum,
- usemap_count, nodeid_begin);
- /* new start, update count etc*/
- nodeid_begin = nodeid;
- pnum_begin = pnum;
- usemap_count = 1;
- }
- /* ok, last chunk */
- sparse_early_usemaps_alloc_node(usemap_map, pnum_begin, NR_MEM_SECTIONS,
- usemap_count, nodeid_begin);
-
-#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
- size2 = sizeof(struct page *) * NR_MEM_SECTIONS;
- map_map = alloc_bootmem(size2);
- if (!map_map)
- panic("can not allocate map_map\n");
for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
struct mem_section *ms;
@@ -567,16 +499,65 @@
continue;
}
/* ok, we need to take cake of from pnum_begin to pnum - 1*/
- sparse_early_mem_maps_alloc_node(map_map, pnum_begin, pnum,
- map_count, nodeid_begin);
+ alloc_func(data, pnum_begin, pnum,
+ map_count, nodeid_begin);
/* new start, update count etc*/
nodeid_begin = nodeid;
pnum_begin = pnum;
map_count = 1;
}
/* ok, last chunk */
- sparse_early_mem_maps_alloc_node(map_map, pnum_begin, NR_MEM_SECTIONS,
- map_count, nodeid_begin);
+ alloc_func(data, pnum_begin, NR_MEM_SECTIONS,
+ map_count, nodeid_begin);
+}
+
+/*
+ * Allocate the accumulated non-linear sections, allocate a mem_map
+ * for each and record the physical to section mapping.
+ */
+void __init sparse_init(void)
+{
+ unsigned long pnum;
+ struct page *map;
+ unsigned long *usemap;
+ unsigned long **usemap_map;
+ int size;
+#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
+ int size2;
+ struct page **map_map;
+#endif
+
+ /* see include/linux/mmzone.h 'struct mem_section' definition */
+ BUILD_BUG_ON(!is_power_of_2(sizeof(struct mem_section)));
+
+ /* Setup pageblock_order for HUGETLB_PAGE_SIZE_VARIABLE */
+ set_pageblock_order();
+
+ /*
+ * map is using big page (aka 2M in x86 64 bit)
+ * usemap is less one page (aka 24 bytes)
+ * so alloc 2M (with 2M align) and 24 bytes in turn will
+ * make next 2M slip to one more 2M later.
+ * then in big system, the memory will have a lot of holes...
+ * here try to allocate 2M pages continuously.
+ *
+ * powerpc need to call sparse_init_one_section right after each
+ * sparse_early_mem_map_alloc, so allocate usemap_map at first.
+ */
+ size = sizeof(unsigned long *) * NR_MEM_SECTIONS;
+ usemap_map = alloc_bootmem(size);
+ if (!usemap_map)
+ panic("can not allocate usemap_map\n");
+ alloc_usemap_and_memmap(sparse_early_usemaps_alloc_node,
+ (void *)usemap_map);
+
+#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
+ size2 = sizeof(struct page *) * NR_MEM_SECTIONS;
+ map_map = alloc_bootmem(size2);
+ if (!map_map)
+ panic("can not allocate map_map\n");
+ alloc_usemap_and_memmap(sparse_early_mem_maps_alloc_node,
+ (void *)map_map);
#endif
for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
diff --git a/mm/swap.c b/mm/swap.c
index 62b78a6..759c3ca 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -31,6 +31,7 @@
#include <linux/memcontrol.h>
#include <linux/gfp.h>
#include <linux/uio.h>
+#include <linux/hugetlb.h>
#include "internal.h"
@@ -81,6 +82,19 @@
static void put_compound_page(struct page *page)
{
+ /*
+ * hugetlbfs pages cannot be split from under us. If this is a
+ * hugetlbfs page, check refcount on head page and release the page if
+ * the refcount becomes zero.
+ */
+ if (PageHuge(page)) {
+ page = compound_head(page);
+ if (put_page_testzero(page))
+ __put_compound_page(page);
+
+ return;
+ }
+
if (unlikely(PageTail(page))) {
/* __split_huge_page_refcount can run under us */
struct page *page_head = compound_trans_head(page);
@@ -184,38 +198,51 @@
* proper PT lock that already serializes against
* split_huge_page().
*/
- unsigned long flags;
bool got = false;
- struct page *page_head = compound_trans_head(page);
+ struct page *page_head;
- if (likely(page != page_head && get_page_unless_zero(page_head))) {
+ /*
+ * If this is a hugetlbfs page it cannot be split under us. Simply
+ * increment refcount for the head page.
+ */
+ if (PageHuge(page)) {
+ page_head = compound_head(page);
+ atomic_inc(&page_head->_count);
+ got = true;
+ } else {
+ unsigned long flags;
- /* Ref to put_compound_page() comment. */
- if (PageSlab(page_head)) {
+ page_head = compound_trans_head(page);
+ if (likely(page != page_head &&
+ get_page_unless_zero(page_head))) {
+
+ /* Ref to put_compound_page() comment. */
+ if (PageSlab(page_head)) {
+ if (likely(PageTail(page))) {
+ __get_page_tail_foll(page, false);
+ return true;
+ } else {
+ put_page(page_head);
+ return false;
+ }
+ }
+
+ /*
+ * page_head wasn't a dangling pointer but it
+ * may not be a head page anymore by the time
+ * we obtain the lock. That is ok as long as it
+ * can't be freed from under us.
+ */
+ flags = compound_lock_irqsave(page_head);
+ /* here __split_huge_page_refcount won't run anymore */
if (likely(PageTail(page))) {
__get_page_tail_foll(page, false);
- return true;
- } else {
- put_page(page_head);
- return false;
+ got = true;
}
+ compound_unlock_irqrestore(page_head, flags);
+ if (unlikely(!got))
+ put_page(page_head);
}
-
- /*
- * page_head wasn't a dangling pointer but it
- * may not be a head page anymore by the time
- * we obtain the lock. That is ok as long as it
- * can't be freed from under us.
- */
- flags = compound_lock_irqsave(page_head);
- /* here __split_huge_page_refcount won't run anymore */
- if (likely(PageTail(page))) {
- __get_page_tail_foll(page, false);
- got = true;
- }
- compound_unlock_irqrestore(page_head, flags);
- if (unlikely(!got))
- put_page(page_head);
}
return got;
}
@@ -405,6 +432,11 @@
pagevec_lru_move_fn(pvec, __activate_page, NULL);
}
+static bool need_activate_page_drain(int cpu)
+{
+ return pagevec_count(&per_cpu(activate_page_pvecs, cpu)) != 0;
+}
+
void activate_page(struct page *page)
{
if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
@@ -422,6 +454,11 @@
{
}
+static bool need_activate_page_drain(int cpu)
+{
+ return false;
+}
+
void activate_page(struct page *page)
{
struct zone *zone = page_zone(page);
@@ -674,12 +711,36 @@
lru_add_drain();
}
-/*
- * Returns 0 for success
- */
-int lru_add_drain_all(void)
+static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work);
+
+void lru_add_drain_all(void)
{
- return schedule_on_each_cpu(lru_add_drain_per_cpu);
+ static DEFINE_MUTEX(lock);
+ static struct cpumask has_work;
+ int cpu;
+
+ mutex_lock(&lock);
+ get_online_cpus();
+ cpumask_clear(&has_work);
+
+ for_each_online_cpu(cpu) {
+ struct work_struct *work = &per_cpu(lru_add_drain_work, cpu);
+
+ if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) ||
+ pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) ||
+ pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) ||
+ need_activate_page_drain(cpu)) {
+ INIT_WORK(work, lru_add_drain_per_cpu);
+ schedule_work_on(cpu, work);
+ cpumask_set_cpu(cpu, &has_work);
+ }
+ }
+
+ for_each_cpu(cpu, &has_work)
+ flush_work(&per_cpu(lru_add_drain_work, cpu));
+
+ put_online_cpus();
+ mutex_unlock(&lock);
}
/*
diff --git a/mm/swap_state.c b/mm/swap_state.c
index f24ab0d..e6f15f8 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -122,7 +122,7 @@
{
int error;
- error = radix_tree_preload(gfp_mask);
+ error = radix_tree_maybe_preload(gfp_mask);
if (!error) {
error = __add_to_swap_cache(page, entry);
radix_tree_preload_end();
@@ -328,7 +328,7 @@
/*
* call radix_tree_preload() while we can wait.
*/
- err = radix_tree_preload(gfp_mask & GFP_KERNEL);
+ err = radix_tree_maybe_preload(gfp_mask & GFP_KERNEL);
if (err)
break;
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 6cf2e60..3963fc2 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -175,15 +175,297 @@
}
}
-static int wait_for_discard(void *word)
-{
- schedule();
- return 0;
-}
-
#define SWAPFILE_CLUSTER 256
#define LATENCY_LIMIT 256
+static inline void cluster_set_flag(struct swap_cluster_info *info,
+ unsigned int flag)
+{
+ info->flags = flag;
+}
+
+static inline unsigned int cluster_count(struct swap_cluster_info *info)
+{
+ return info->data;
+}
+
+static inline void cluster_set_count(struct swap_cluster_info *info,
+ unsigned int c)
+{
+ info->data = c;
+}
+
+static inline void cluster_set_count_flag(struct swap_cluster_info *info,
+ unsigned int c, unsigned int f)
+{
+ info->flags = f;
+ info->data = c;
+}
+
+static inline unsigned int cluster_next(struct swap_cluster_info *info)
+{
+ return info->data;
+}
+
+static inline void cluster_set_next(struct swap_cluster_info *info,
+ unsigned int n)
+{
+ info->data = n;
+}
+
+static inline void cluster_set_next_flag(struct swap_cluster_info *info,
+ unsigned int n, unsigned int f)
+{
+ info->flags = f;
+ info->data = n;
+}
+
+static inline bool cluster_is_free(struct swap_cluster_info *info)
+{
+ return info->flags & CLUSTER_FLAG_FREE;
+}
+
+static inline bool cluster_is_null(struct swap_cluster_info *info)
+{
+ return info->flags & CLUSTER_FLAG_NEXT_NULL;
+}
+
+static inline void cluster_set_null(struct swap_cluster_info *info)
+{
+ info->flags = CLUSTER_FLAG_NEXT_NULL;
+ info->data = 0;
+}
+
+/* Add a cluster to discard list and schedule it to do discard */
+static void swap_cluster_schedule_discard(struct swap_info_struct *si,
+ unsigned int idx)
+{
+ /*
+ * If scan_swap_map() can't find a free cluster, it will check
+ * si->swap_map directly. To make sure the discarding cluster isn't
+ * taken by scan_swap_map(), mark the swap entries bad (occupied). It
+ * will be cleared after discard
+ */
+ memset(si->swap_map + idx * SWAPFILE_CLUSTER,
+ SWAP_MAP_BAD, SWAPFILE_CLUSTER);
+
+ if (cluster_is_null(&si->discard_cluster_head)) {
+ cluster_set_next_flag(&si->discard_cluster_head,
+ idx, 0);
+ cluster_set_next_flag(&si->discard_cluster_tail,
+ idx, 0);
+ } else {
+ unsigned int tail = cluster_next(&si->discard_cluster_tail);
+ cluster_set_next(&si->cluster_info[tail], idx);
+ cluster_set_next_flag(&si->discard_cluster_tail,
+ idx, 0);
+ }
+
+ schedule_work(&si->discard_work);
+}
+
+/*
+ * Doing discard actually. After a cluster discard is finished, the cluster
+ * will be added to free cluster list. caller should hold si->lock.
+*/
+static void swap_do_scheduled_discard(struct swap_info_struct *si)
+{
+ struct swap_cluster_info *info;
+ unsigned int idx;
+
+ info = si->cluster_info;
+
+ while (!cluster_is_null(&si->discard_cluster_head)) {
+ idx = cluster_next(&si->discard_cluster_head);
+
+ cluster_set_next_flag(&si->discard_cluster_head,
+ cluster_next(&info[idx]), 0);
+ if (cluster_next(&si->discard_cluster_tail) == idx) {
+ cluster_set_null(&si->discard_cluster_head);
+ cluster_set_null(&si->discard_cluster_tail);
+ }
+ spin_unlock(&si->lock);
+
+ discard_swap_cluster(si, idx * SWAPFILE_CLUSTER,
+ SWAPFILE_CLUSTER);
+
+ spin_lock(&si->lock);
+ cluster_set_flag(&info[idx], CLUSTER_FLAG_FREE);
+ if (cluster_is_null(&si->free_cluster_head)) {
+ cluster_set_next_flag(&si->free_cluster_head,
+ idx, 0);
+ cluster_set_next_flag(&si->free_cluster_tail,
+ idx, 0);
+ } else {
+ unsigned int tail;
+
+ tail = cluster_next(&si->free_cluster_tail);
+ cluster_set_next(&info[tail], idx);
+ cluster_set_next_flag(&si->free_cluster_tail,
+ idx, 0);
+ }
+ memset(si->swap_map + idx * SWAPFILE_CLUSTER,
+ 0, SWAPFILE_CLUSTER);
+ }
+}
+
+static void swap_discard_work(struct work_struct *work)
+{
+ struct swap_info_struct *si;
+
+ si = container_of(work, struct swap_info_struct, discard_work);
+
+ spin_lock(&si->lock);
+ swap_do_scheduled_discard(si);
+ spin_unlock(&si->lock);
+}
+
+/*
+ * The cluster corresponding to page_nr will be used. The cluster will be
+ * removed from free cluster list and its usage counter will be increased.
+ */
+static void inc_cluster_info_page(struct swap_info_struct *p,
+ struct swap_cluster_info *cluster_info, unsigned long page_nr)
+{
+ unsigned long idx = page_nr / SWAPFILE_CLUSTER;
+
+ if (!cluster_info)
+ return;
+ if (cluster_is_free(&cluster_info[idx])) {
+ VM_BUG_ON(cluster_next(&p->free_cluster_head) != idx);
+ cluster_set_next_flag(&p->free_cluster_head,
+ cluster_next(&cluster_info[idx]), 0);
+ if (cluster_next(&p->free_cluster_tail) == idx) {
+ cluster_set_null(&p->free_cluster_tail);
+ cluster_set_null(&p->free_cluster_head);
+ }
+ cluster_set_count_flag(&cluster_info[idx], 0, 0);
+ }
+
+ VM_BUG_ON(cluster_count(&cluster_info[idx]) >= SWAPFILE_CLUSTER);
+ cluster_set_count(&cluster_info[idx],
+ cluster_count(&cluster_info[idx]) + 1);
+}
+
+/*
+ * The cluster corresponding to page_nr decreases one usage. If the usage
+ * counter becomes 0, which means no page in the cluster is in using, we can
+ * optionally discard the cluster and add it to free cluster list.
+ */
+static void dec_cluster_info_page(struct swap_info_struct *p,
+ struct swap_cluster_info *cluster_info, unsigned long page_nr)
+{
+ unsigned long idx = page_nr / SWAPFILE_CLUSTER;
+
+ if (!cluster_info)
+ return;
+
+ VM_BUG_ON(cluster_count(&cluster_info[idx]) == 0);
+ cluster_set_count(&cluster_info[idx],
+ cluster_count(&cluster_info[idx]) - 1);
+
+ if (cluster_count(&cluster_info[idx]) == 0) {
+ /*
+ * If the swap is discardable, prepare discard the cluster
+ * instead of free it immediately. The cluster will be freed
+ * after discard.
+ */
+ if ((p->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) ==
+ (SWP_WRITEOK | SWP_PAGE_DISCARD)) {
+ swap_cluster_schedule_discard(p, idx);
+ return;
+ }
+
+ cluster_set_flag(&cluster_info[idx], CLUSTER_FLAG_FREE);
+ if (cluster_is_null(&p->free_cluster_head)) {
+ cluster_set_next_flag(&p->free_cluster_head, idx, 0);
+ cluster_set_next_flag(&p->free_cluster_tail, idx, 0);
+ } else {
+ unsigned int tail = cluster_next(&p->free_cluster_tail);
+ cluster_set_next(&cluster_info[tail], idx);
+ cluster_set_next_flag(&p->free_cluster_tail, idx, 0);
+ }
+ }
+}
+
+/*
+ * It's possible scan_swap_map() uses a free cluster in the middle of free
+ * cluster list. Avoiding such abuse to avoid list corruption.
+ */
+static bool
+scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si,
+ unsigned long offset)
+{
+ struct percpu_cluster *percpu_cluster;
+ bool conflict;
+
+ offset /= SWAPFILE_CLUSTER;
+ conflict = !cluster_is_null(&si->free_cluster_head) &&
+ offset != cluster_next(&si->free_cluster_head) &&
+ cluster_is_free(&si->cluster_info[offset]);
+
+ if (!conflict)
+ return false;
+
+ percpu_cluster = this_cpu_ptr(si->percpu_cluster);
+ cluster_set_null(&percpu_cluster->index);
+ return true;
+}
+
+/*
+ * Try to get a swap entry from current cpu's swap entry pool (a cluster). This
+ * might involve allocating a new cluster for current CPU too.
+ */
+static void scan_swap_map_try_ssd_cluster(struct swap_info_struct *si,
+ unsigned long *offset, unsigned long *scan_base)
+{
+ struct percpu_cluster *cluster;
+ bool found_free;
+ unsigned long tmp;
+
+new_cluster:
+ cluster = this_cpu_ptr(si->percpu_cluster);
+ if (cluster_is_null(&cluster->index)) {
+ if (!cluster_is_null(&si->free_cluster_head)) {
+ cluster->index = si->free_cluster_head;
+ cluster->next = cluster_next(&cluster->index) *
+ SWAPFILE_CLUSTER;
+ } else if (!cluster_is_null(&si->discard_cluster_head)) {
+ /*
+ * we don't have free cluster but have some clusters in
+ * discarding, do discard now and reclaim them
+ */
+ swap_do_scheduled_discard(si);
+ *scan_base = *offset = si->cluster_next;
+ goto new_cluster;
+ } else
+ return;
+ }
+
+ found_free = false;
+
+ /*
+ * Other CPUs can use our cluster if they can't find a free cluster,
+ * check if there is still free entry in the cluster
+ */
+ tmp = cluster->next;
+ while (tmp < si->max && tmp < (cluster_next(&cluster->index) + 1) *
+ SWAPFILE_CLUSTER) {
+ if (!si->swap_map[tmp]) {
+ found_free = true;
+ break;
+ }
+ tmp++;
+ }
+ if (!found_free) {
+ cluster_set_null(&cluster->index);
+ goto new_cluster;
+ }
+ cluster->next = tmp + 1;
+ *offset = tmp;
+ *scan_base = tmp;
+}
+
static unsigned long scan_swap_map(struct swap_info_struct *si,
unsigned char usage)
{
@@ -191,7 +473,6 @@
unsigned long scan_base;
unsigned long last_in_cluster = 0;
int latency_ration = LATENCY_LIMIT;
- int found_free_cluster = 0;
/*
* We try to cluster swap pages by allocating them sequentially
@@ -207,24 +488,18 @@
si->flags += SWP_SCANNING;
scan_base = offset = si->cluster_next;
+ /* SSD algorithm */
+ if (si->cluster_info) {
+ scan_swap_map_try_ssd_cluster(si, &offset, &scan_base);
+ goto checks;
+ }
+
if (unlikely(!si->cluster_nr--)) {
if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) {
si->cluster_nr = SWAPFILE_CLUSTER - 1;
goto checks;
}
- if (si->flags & SWP_PAGE_DISCARD) {
- /*
- * Start range check on racing allocations, in case
- * they overlap the cluster we eventually decide on
- * (we scan without swap_lock to allow preemption).
- * It's hardly conceivable that cluster_nr could be
- * wrapped during our scan, but don't depend on it.
- */
- if (si->lowest_alloc)
- goto checks;
- si->lowest_alloc = si->max;
- si->highest_alloc = 0;
- }
+
spin_unlock(&si->lock);
/*
@@ -248,7 +523,6 @@
offset -= SWAPFILE_CLUSTER - 1;
si->cluster_next = offset;
si->cluster_nr = SWAPFILE_CLUSTER - 1;
- found_free_cluster = 1;
goto checks;
}
if (unlikely(--latency_ration < 0)) {
@@ -269,7 +543,6 @@
offset -= SWAPFILE_CLUSTER - 1;
si->cluster_next = offset;
si->cluster_nr = SWAPFILE_CLUSTER - 1;
- found_free_cluster = 1;
goto checks;
}
if (unlikely(--latency_ration < 0)) {
@@ -281,10 +554,13 @@
offset = scan_base;
spin_lock(&si->lock);
si->cluster_nr = SWAPFILE_CLUSTER - 1;
- si->lowest_alloc = 0;
}
checks:
+ if (si->cluster_info) {
+ while (scan_swap_map_ssd_cluster_conflict(si, offset))
+ scan_swap_map_try_ssd_cluster(si, &offset, &scan_base);
+ }
if (!(si->flags & SWP_WRITEOK))
goto no_page;
if (!si->highest_bit)
@@ -317,62 +593,10 @@
si->highest_bit = 0;
}
si->swap_map[offset] = usage;
+ inc_cluster_info_page(si, si->cluster_info, offset);
si->cluster_next = offset + 1;
si->flags -= SWP_SCANNING;
- if (si->lowest_alloc) {
- /*
- * Only set when SWP_PAGE_DISCARD, and there's a scan
- * for a free cluster in progress or just completed.
- */
- if (found_free_cluster) {
- /*
- * To optimize wear-levelling, discard the
- * old data of the cluster, taking care not to
- * discard any of its pages that have already
- * been allocated by racing tasks (offset has
- * already stepped over any at the beginning).
- */
- if (offset < si->highest_alloc &&
- si->lowest_alloc <= last_in_cluster)
- last_in_cluster = si->lowest_alloc - 1;
- si->flags |= SWP_DISCARDING;
- spin_unlock(&si->lock);
-
- if (offset < last_in_cluster)
- discard_swap_cluster(si, offset,
- last_in_cluster - offset + 1);
-
- spin_lock(&si->lock);
- si->lowest_alloc = 0;
- si->flags &= ~SWP_DISCARDING;
-
- smp_mb(); /* wake_up_bit advises this */
- wake_up_bit(&si->flags, ilog2(SWP_DISCARDING));
-
- } else if (si->flags & SWP_DISCARDING) {
- /*
- * Delay using pages allocated by racing tasks
- * until the whole discard has been issued. We
- * could defer that delay until swap_writepage,
- * but it's easier to keep this self-contained.
- */
- spin_unlock(&si->lock);
- wait_on_bit(&si->flags, ilog2(SWP_DISCARDING),
- wait_for_discard, TASK_UNINTERRUPTIBLE);
- spin_lock(&si->lock);
- } else {
- /*
- * Note pages allocated by racing tasks while
- * scan for a free cluster is in progress, so
- * that its final discard can exclude them.
- */
- if (offset < si->lowest_alloc)
- si->lowest_alloc = offset;
- if (offset > si->highest_alloc)
- si->highest_alloc = offset;
- }
- }
return offset;
scan:
@@ -527,16 +751,16 @@
return p;
bad_free:
- printk(KERN_ERR "swap_free: %s%08lx\n", Unused_offset, entry.val);
+ pr_err("swap_free: %s%08lx\n", Unused_offset, entry.val);
goto out;
bad_offset:
- printk(KERN_ERR "swap_free: %s%08lx\n", Bad_offset, entry.val);
+ pr_err("swap_free: %s%08lx\n", Bad_offset, entry.val);
goto out;
bad_device:
- printk(KERN_ERR "swap_free: %s%08lx\n", Unused_file, entry.val);
+ pr_err("swap_free: %s%08lx\n", Unused_file, entry.val);
goto out;
bad_nofile:
- printk(KERN_ERR "swap_free: %s%08lx\n", Bad_file, entry.val);
+ pr_err("swap_free: %s%08lx\n", Bad_file, entry.val);
out:
return NULL;
}
@@ -600,6 +824,7 @@
/* free if no reference */
if (!usage) {
+ dec_cluster_info_page(p, p->cluster_info, offset);
if (offset < p->lowest_bit)
p->lowest_bit = offset;
if (offset > p->highest_bit)
@@ -1107,7 +1332,7 @@
else
continue;
}
- count = si->swap_map[i];
+ count = ACCESS_ONCE(si->swap_map[i]);
if (count && swap_count(count) != SWAP_MAP_BAD)
break;
}
@@ -1127,7 +1352,11 @@
{
struct swap_info_struct *si = swap_info[type];
struct mm_struct *start_mm;
- unsigned char *swap_map;
+ volatile unsigned char *swap_map; /* swap_map is accessed without
+ * locking. Mark it as volatile
+ * to prevent compiler doing
+ * something odd.
+ */
unsigned char swcount;
struct page *page;
swp_entry_t entry;
@@ -1178,7 +1407,15 @@
* reused since sys_swapoff() already disabled
* allocation from here, or alloc_page() failed.
*/
- if (!*swap_map)
+ swcount = *swap_map;
+ /*
+ * We don't hold lock here, so the swap entry could be
+ * SWAP_MAP_BAD (when the cluster is discarding).
+ * Instead of fail out, We can just skip the swap
+ * entry because swapoff will wait for discarding
+ * finish anyway.
+ */
+ if (!swcount || swcount == SWAP_MAP_BAD)
continue;
retval = -ENOMEM;
break;
@@ -1524,7 +1761,8 @@
}
static void _enable_swap_info(struct swap_info_struct *p, int prio,
- unsigned char *swap_map)
+ unsigned char *swap_map,
+ struct swap_cluster_info *cluster_info)
{
int i, prev;
@@ -1533,6 +1771,7 @@
else
p->prio = --least_priority;
p->swap_map = swap_map;
+ p->cluster_info = cluster_info;
p->flags |= SWP_WRITEOK;
atomic_long_add(p->pages, &nr_swap_pages);
total_swap_pages += p->pages;
@@ -1553,12 +1792,13 @@
static void enable_swap_info(struct swap_info_struct *p, int prio,
unsigned char *swap_map,
+ struct swap_cluster_info *cluster_info,
unsigned long *frontswap_map)
{
frontswap_init(p->type, frontswap_map);
spin_lock(&swap_lock);
spin_lock(&p->lock);
- _enable_swap_info(p, prio, swap_map);
+ _enable_swap_info(p, prio, swap_map, cluster_info);
spin_unlock(&p->lock);
spin_unlock(&swap_lock);
}
@@ -1567,7 +1807,7 @@
{
spin_lock(&swap_lock);
spin_lock(&p->lock);
- _enable_swap_info(p, p->prio, p->swap_map);
+ _enable_swap_info(p, p->prio, p->swap_map, p->cluster_info);
spin_unlock(&p->lock);
spin_unlock(&swap_lock);
}
@@ -1576,6 +1816,7 @@
{
struct swap_info_struct *p = NULL;
unsigned char *swap_map;
+ struct swap_cluster_info *cluster_info;
unsigned long *frontswap_map;
struct file *swap_file, *victim;
struct address_space *mapping;
@@ -1651,6 +1892,8 @@
goto out_dput;
}
+ flush_work(&p->discard_work);
+
destroy_swap_extents(p);
if (p->flags & SWP_CONTINUED)
free_swap_count_continuations(p);
@@ -1675,6 +1918,8 @@
p->max = 0;
swap_map = p->swap_map;
p->swap_map = NULL;
+ cluster_info = p->cluster_info;
+ p->cluster_info = NULL;
p->flags = 0;
frontswap_map = frontswap_map_get(p);
frontswap_map_set(p, NULL);
@@ -1682,7 +1927,10 @@
spin_unlock(&swap_lock);
frontswap_invalidate_area(type);
mutex_unlock(&swapon_mutex);
+ free_percpu(p->percpu_cluster);
+ p->percpu_cluster = NULL;
vfree(swap_map);
+ vfree(cluster_info);
vfree(frontswap_map);
/* Destroy swap account informatin */
swap_cgroup_swapoff(type);
@@ -1926,9 +2174,10 @@
int i;
unsigned long maxpages;
unsigned long swapfilepages;
+ unsigned long last_page;
if (memcmp("SWAPSPACE2", swap_header->magic.magic, 10)) {
- printk(KERN_ERR "Unable to find swap-space signature\n");
+ pr_err("Unable to find swap-space signature\n");
return 0;
}
@@ -1942,9 +2191,8 @@
}
/* Check the swap header's sub-version */
if (swap_header->info.version != 1) {
- printk(KERN_WARNING
- "Unable to handle swap header version %d\n",
- swap_header->info.version);
+ pr_warn("Unable to handle swap header version %d\n",
+ swap_header->info.version);
return 0;
}
@@ -1968,8 +2216,14 @@
*/
maxpages = swp_offset(pte_to_swp_entry(
swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1;
- if (maxpages > swap_header->info.last_page) {
- maxpages = swap_header->info.last_page + 1;
+ last_page = swap_header->info.last_page;
+ if (last_page > maxpages) {
+ pr_warn("Truncating oversized swap area, only using %luk out of %luk\n",
+ maxpages << (PAGE_SHIFT - 10),
+ last_page << (PAGE_SHIFT - 10));
+ }
+ if (maxpages > last_page) {
+ maxpages = last_page + 1;
/* p->max is an unsigned int: don't overflow it */
if ((unsigned int)maxpages == 0)
maxpages = UINT_MAX;
@@ -1980,8 +2234,7 @@
return 0;
swapfilepages = i_size_read(inode) >> PAGE_SHIFT;
if (swapfilepages && maxpages > swapfilepages) {
- printk(KERN_WARNING
- "Swap area shorter than signature indicates\n");
+ pr_warn("Swap area shorter than signature indicates\n");
return 0;
}
if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode))
@@ -1995,15 +2248,23 @@
static int setup_swap_map_and_extents(struct swap_info_struct *p,
union swap_header *swap_header,
unsigned char *swap_map,
+ struct swap_cluster_info *cluster_info,
unsigned long maxpages,
sector_t *span)
{
int i;
unsigned int nr_good_pages;
int nr_extents;
+ unsigned long nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER);
+ unsigned long idx = p->cluster_next / SWAPFILE_CLUSTER;
nr_good_pages = maxpages - 1; /* omit header page */
+ cluster_set_null(&p->free_cluster_head);
+ cluster_set_null(&p->free_cluster_tail);
+ cluster_set_null(&p->discard_cluster_head);
+ cluster_set_null(&p->discard_cluster_tail);
+
for (i = 0; i < swap_header->info.nr_badpages; i++) {
unsigned int page_nr = swap_header->info.badpages[i];
if (page_nr == 0 || page_nr > swap_header->info.last_page)
@@ -2011,11 +2272,25 @@
if (page_nr < maxpages) {
swap_map[page_nr] = SWAP_MAP_BAD;
nr_good_pages--;
+ /*
+ * Haven't marked the cluster free yet, no list
+ * operation involved
+ */
+ inc_cluster_info_page(p, cluster_info, page_nr);
}
}
+ /* Haven't marked the cluster free yet, no list operation involved */
+ for (i = maxpages; i < round_up(maxpages, SWAPFILE_CLUSTER); i++)
+ inc_cluster_info_page(p, cluster_info, i);
+
if (nr_good_pages) {
swap_map[0] = SWAP_MAP_BAD;
+ /*
+ * Not mark the cluster free yet, no list
+ * operation involved
+ */
+ inc_cluster_info_page(p, cluster_info, 0);
p->max = maxpages;
p->pages = nr_good_pages;
nr_extents = setup_swap_extents(p, span);
@@ -2024,10 +2299,34 @@
nr_good_pages = p->pages;
}
if (!nr_good_pages) {
- printk(KERN_WARNING "Empty swap-file\n");
+ pr_warn("Empty swap-file\n");
return -EINVAL;
}
+ if (!cluster_info)
+ return nr_extents;
+
+ for (i = 0; i < nr_clusters; i++) {
+ if (!cluster_count(&cluster_info[idx])) {
+ cluster_set_flag(&cluster_info[idx], CLUSTER_FLAG_FREE);
+ if (cluster_is_null(&p->free_cluster_head)) {
+ cluster_set_next_flag(&p->free_cluster_head,
+ idx, 0);
+ cluster_set_next_flag(&p->free_cluster_tail,
+ idx, 0);
+ } else {
+ unsigned int tail;
+
+ tail = cluster_next(&p->free_cluster_tail);
+ cluster_set_next(&cluster_info[tail], idx);
+ cluster_set_next_flag(&p->free_cluster_tail,
+ idx, 0);
+ }
+ }
+ idx++;
+ if (idx == nr_clusters)
+ idx = 0;
+ }
return nr_extents;
}
@@ -2059,6 +2358,7 @@
sector_t span;
unsigned long maxpages;
unsigned char *swap_map = NULL;
+ struct swap_cluster_info *cluster_info = NULL;
unsigned long *frontswap_map = NULL;
struct page *page = NULL;
struct inode *inode = NULL;
@@ -2073,6 +2373,8 @@
if (IS_ERR(p))
return PTR_ERR(p);
+ INIT_WORK(&p->discard_work, swap_discard_work);
+
name = getname(specialfile);
if (IS_ERR(name)) {
error = PTR_ERR(name);
@@ -2132,13 +2434,38 @@
error = -ENOMEM;
goto bad_swap;
}
+ if (p->bdev && blk_queue_nonrot(bdev_get_queue(p->bdev))) {
+ p->flags |= SWP_SOLIDSTATE;
+ /*
+ * select a random position to start with to help wear leveling
+ * SSD
+ */
+ p->cluster_next = 1 + (prandom_u32() % p->highest_bit);
+
+ cluster_info = vzalloc(DIV_ROUND_UP(maxpages,
+ SWAPFILE_CLUSTER) * sizeof(*cluster_info));
+ if (!cluster_info) {
+ error = -ENOMEM;
+ goto bad_swap;
+ }
+ p->percpu_cluster = alloc_percpu(struct percpu_cluster);
+ if (!p->percpu_cluster) {
+ error = -ENOMEM;
+ goto bad_swap;
+ }
+ for_each_possible_cpu(i) {
+ struct percpu_cluster *cluster;
+ cluster = per_cpu_ptr(p->percpu_cluster, i);
+ cluster_set_null(&cluster->index);
+ }
+ }
error = swap_cgroup_swapon(p->type, maxpages);
if (error)
goto bad_swap;
nr_extents = setup_swap_map_and_extents(p, swap_header, swap_map,
- maxpages, &span);
+ cluster_info, maxpages, &span);
if (unlikely(nr_extents < 0)) {
error = nr_extents;
goto bad_swap;
@@ -2147,41 +2474,33 @@
if (frontswap_enabled)
frontswap_map = vzalloc(BITS_TO_LONGS(maxpages) * sizeof(long));
- if (p->bdev) {
- if (blk_queue_nonrot(bdev_get_queue(p->bdev))) {
- p->flags |= SWP_SOLIDSTATE;
- p->cluster_next = 1 + (prandom_u32() % p->highest_bit);
- }
+ if (p->bdev &&(swap_flags & SWAP_FLAG_DISCARD) && swap_discardable(p)) {
+ /*
+ * When discard is enabled for swap with no particular
+ * policy flagged, we set all swap discard flags here in
+ * order to sustain backward compatibility with older
+ * swapon(8) releases.
+ */
+ p->flags |= (SWP_DISCARDABLE | SWP_AREA_DISCARD |
+ SWP_PAGE_DISCARD);
- if ((swap_flags & SWAP_FLAG_DISCARD) && swap_discardable(p)) {
- /*
- * When discard is enabled for swap with no particular
- * policy flagged, we set all swap discard flags here in
- * order to sustain backward compatibility with older
- * swapon(8) releases.
- */
- p->flags |= (SWP_DISCARDABLE | SWP_AREA_DISCARD |
- SWP_PAGE_DISCARD);
+ /*
+ * By flagging sys_swapon, a sysadmin can tell us to
+ * either do single-time area discards only, or to just
+ * perform discards for released swap page-clusters.
+ * Now it's time to adjust the p->flags accordingly.
+ */
+ if (swap_flags & SWAP_FLAG_DISCARD_ONCE)
+ p->flags &= ~SWP_PAGE_DISCARD;
+ else if (swap_flags & SWAP_FLAG_DISCARD_PAGES)
+ p->flags &= ~SWP_AREA_DISCARD;
- /*
- * By flagging sys_swapon, a sysadmin can tell us to
- * either do single-time area discards only, or to just
- * perform discards for released swap page-clusters.
- * Now it's time to adjust the p->flags accordingly.
- */
- if (swap_flags & SWAP_FLAG_DISCARD_ONCE)
- p->flags &= ~SWP_PAGE_DISCARD;
- else if (swap_flags & SWAP_FLAG_DISCARD_PAGES)
- p->flags &= ~SWP_AREA_DISCARD;
-
- /* issue a swapon-time discard if it's still required */
- if (p->flags & SWP_AREA_DISCARD) {
- int err = discard_swap(p);
- if (unlikely(err))
- printk(KERN_ERR
- "swapon: discard_swap(%p): %d\n",
- p, err);
- }
+ /* issue a swapon-time discard if it's still required */
+ if (p->flags & SWP_AREA_DISCARD) {
+ int err = discard_swap(p);
+ if (unlikely(err))
+ pr_err("swapon: discard_swap(%p): %d\n",
+ p, err);
}
}
@@ -2190,9 +2509,9 @@
if (swap_flags & SWAP_FLAG_PREFER)
prio =
(swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT;
- enable_swap_info(p, prio, swap_map, frontswap_map);
+ enable_swap_info(p, prio, swap_map, cluster_info, frontswap_map);
- printk(KERN_INFO "Adding %uk swap on %s. "
+ pr_info("Adding %uk swap on %s. "
"Priority:%d extents:%d across:%lluk %s%s%s%s%s\n",
p->pages<<(PAGE_SHIFT-10), name->name, p->prio,
nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10),
@@ -2211,6 +2530,8 @@
error = 0;
goto out;
bad_swap:
+ free_percpu(p->percpu_cluster);
+ p->percpu_cluster = NULL;
if (inode && S_ISBLK(inode->i_mode) && p->bdev) {
set_blocksize(p->bdev, p->old_block_size);
blkdev_put(p->bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
@@ -2222,6 +2543,7 @@
p->flags = 0;
spin_unlock(&swap_lock);
vfree(swap_map);
+ vfree(cluster_info);
if (swap_file) {
if (inode && S_ISREG(inode->i_mode)) {
mutex_unlock(&inode->i_mutex);
@@ -2291,6 +2613,16 @@
goto unlock_out;
count = p->swap_map[offset];
+
+ /*
+ * swapin_readahead() doesn't check if a swap entry is valid, so the
+ * swap entry could be SWAP_MAP_BAD. Check here with lock held.
+ */
+ if (unlikely(swap_count(count) == SWAP_MAP_BAD)) {
+ err = -ENOENT;
+ goto unlock_out;
+ }
+
has_cache = count & SWAP_HAS_CACHE;
count &= ~SWAP_HAS_CACHE;
err = 0;
@@ -2326,7 +2658,7 @@
return err;
bad_file:
- printk(KERN_ERR "swap_dup: %s%08lx\n", Bad_file, entry.val);
+ pr_err("swap_dup: %s%08lx\n", Bad_file, entry.val);
goto out;
}
diff --git a/mm/truncate.c b/mm/truncate.c
index e2e8a8a..353b683 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -567,7 +567,6 @@
/**
* truncate_pagecache - unmap and remove pagecache that has been truncated
* @inode: inode
- * @oldsize: old file size
* @newsize: new file size
*
* inode's new i_size must already be written before truncate_pagecache
@@ -580,7 +579,7 @@
* situations such as writepage being called for a page that has already
* had its underlying blocks deallocated.
*/
-void truncate_pagecache(struct inode *inode, loff_t oldsize, loff_t newsize)
+void truncate_pagecache(struct inode *inode, loff_t newsize)
{
struct address_space *mapping = inode->i_mapping;
loff_t holebegin = round_up(newsize, PAGE_SIZE);
@@ -614,12 +613,8 @@
*/
void truncate_setsize(struct inode *inode, loff_t newsize)
{
- loff_t oldsize;
-
- oldsize = inode->i_size;
i_size_write(inode, newsize);
-
- truncate_pagecache(inode, oldsize, newsize);
+ truncate_pagecache(inode, newsize);
}
EXPORT_SYMBOL(truncate_setsize);
diff --git a/mm/util.c b/mm/util.c
index 7441c41..eaf63fc2 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -388,15 +388,12 @@
struct address_space *mapping = page->mapping;
VM_BUG_ON(PageSlab(page));
-#ifdef CONFIG_SWAP
if (unlikely(PageSwapCache(page))) {
swp_entry_t entry;
entry.val = page_private(page);
mapping = swap_address_space(entry);
- } else
-#endif
- if ((unsigned long)mapping & PAGE_MAPPING_ANON)
+ } else if ((unsigned long)mapping & PAGE_MAPPING_ANON)
mapping = NULL;
return mapping;
}
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 13a5495..1074543 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -752,7 +752,6 @@
struct vmap_block {
spinlock_t lock;
struct vmap_area *va;
- struct vmap_block_queue *vbq;
unsigned long free, dirty;
DECLARE_BITMAP(dirty_map, VMAP_BBMAP_BITS);
struct list_head free_list;
@@ -830,7 +829,6 @@
radix_tree_preload_end();
vbq = &get_cpu_var(vmap_block_queue);
- vb->vbq = vbq;
spin_lock(&vbq->lock);
list_add_rcu(&vb->free_list, &vbq->free);
spin_unlock(&vbq->lock);
@@ -1018,15 +1016,16 @@
rcu_read_lock();
list_for_each_entry_rcu(vb, &vbq->free, free_list) {
- int i;
+ int i, j;
spin_lock(&vb->lock);
i = find_first_bit(vb->dirty_map, VMAP_BBMAP_BITS);
- while (i < VMAP_BBMAP_BITS) {
+ if (i < VMAP_BBMAP_BITS) {
unsigned long s, e;
- int j;
- j = find_next_zero_bit(vb->dirty_map,
- VMAP_BBMAP_BITS, i);
+
+ j = find_last_bit(vb->dirty_map,
+ VMAP_BBMAP_BITS);
+ j = j + 1; /* need exclusive index */
s = vb->va->va_start + (i << PAGE_SHIFT);
e = vb->va->va_start + (j << PAGE_SHIFT);
@@ -1036,10 +1035,6 @@
start = s;
if (e > end)
end = e;
-
- i = j;
- i = find_next_bit(vb->dirty_map,
- VMAP_BBMAP_BITS, i);
}
spin_unlock(&vb->lock);
}
@@ -1263,7 +1258,7 @@
int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page ***pages)
{
unsigned long addr = (unsigned long)area->addr;
- unsigned long end = addr + area->size - PAGE_SIZE;
+ unsigned long end = addr + get_vm_area_size(area);
int err;
err = vmap_page_range(addr, end, prot, *pages);
@@ -1558,7 +1553,7 @@
unsigned int nr_pages, array_size, i;
gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO;
- nr_pages = (area->size - PAGE_SIZE) >> PAGE_SHIFT;
+ nr_pages = get_vm_area_size(area) >> PAGE_SHIFT;
array_size = (nr_pages * sizeof(struct page *));
area->nr_pages = nr_pages;
@@ -1990,7 +1985,7 @@
vm = va->vm;
vaddr = (char *) vm->addr;
- if (addr >= vaddr + vm->size - PAGE_SIZE)
+ if (addr >= vaddr + get_vm_area_size(vm))
continue;
while (addr < vaddr) {
if (count == 0)
@@ -2000,7 +1995,7 @@
addr++;
count--;
}
- n = vaddr + vm->size - PAGE_SIZE - addr;
+ n = vaddr + get_vm_area_size(vm) - addr;
if (n > count)
n = count;
if (!(vm->flags & VM_IOREMAP))
@@ -2072,7 +2067,7 @@
vm = va->vm;
vaddr = (char *) vm->addr;
- if (addr >= vaddr + vm->size - PAGE_SIZE)
+ if (addr >= vaddr + get_vm_area_size(vm))
continue;
while (addr < vaddr) {
if (count == 0)
@@ -2081,7 +2076,7 @@
addr++;
count--;
}
- n = vaddr + vm->size - PAGE_SIZE - addr;
+ n = vaddr + get_vm_area_size(vm) - addr;
if (n > count)
n = count;
if (!(vm->flags & VM_IOREMAP)) {
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 2cff0d4..8ed1b77 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -139,13 +139,44 @@
{
return !sc->target_mem_cgroup;
}
+
+static bool mem_cgroup_should_soft_reclaim(struct scan_control *sc)
+{
+ struct mem_cgroup *root = sc->target_mem_cgroup;
+ return !mem_cgroup_disabled() &&
+ mem_cgroup_soft_reclaim_eligible(root, root) != SKIP_TREE;
+}
#else
static bool global_reclaim(struct scan_control *sc)
{
return true;
}
+
+static bool mem_cgroup_should_soft_reclaim(struct scan_control *sc)
+{
+ return false;
+}
#endif
+unsigned long zone_reclaimable_pages(struct zone *zone)
+{
+ int nr;
+
+ nr = zone_page_state(zone, NR_ACTIVE_FILE) +
+ zone_page_state(zone, NR_INACTIVE_FILE);
+
+ if (get_nr_swap_pages() > 0)
+ nr += zone_page_state(zone, NR_ACTIVE_ANON) +
+ zone_page_state(zone, NR_INACTIVE_ANON);
+
+ return nr;
+}
+
+bool zone_reclaimable(struct zone *zone)
+{
+ return zone->pages_scanned < zone_reclaimable_pages(zone) * 6;
+}
+
static unsigned long get_lru_size(struct lruvec *lruvec, enum lru_list lru)
{
if (!mem_cgroup_disabled())
@@ -155,14 +186,31 @@
}
/*
- * Add a shrinker callback to be called from the vm
+ * Add a shrinker callback to be called from the vm.
*/
-void register_shrinker(struct shrinker *shrinker)
+int register_shrinker(struct shrinker *shrinker)
{
- atomic_long_set(&shrinker->nr_in_batch, 0);
+ size_t size = sizeof(*shrinker->nr_deferred);
+
+ /*
+ * If we only have one possible node in the system anyway, save
+ * ourselves the trouble and disable NUMA aware behavior. This way we
+ * will save memory and some small loop time later.
+ */
+ if (nr_node_ids == 1)
+ shrinker->flags &= ~SHRINKER_NUMA_AWARE;
+
+ if (shrinker->flags & SHRINKER_NUMA_AWARE)
+ size *= nr_node_ids;
+
+ shrinker->nr_deferred = kzalloc(size, GFP_KERNEL);
+ if (!shrinker->nr_deferred)
+ return -ENOMEM;
+
down_write(&shrinker_rwsem);
list_add_tail(&shrinker->list, &shrinker_list);
up_write(&shrinker_rwsem);
+ return 0;
}
EXPORT_SYMBOL(register_shrinker);
@@ -177,15 +225,102 @@
}
EXPORT_SYMBOL(unregister_shrinker);
-static inline int do_shrinker_shrink(struct shrinker *shrinker,
- struct shrink_control *sc,
- unsigned long nr_to_scan)
+#define SHRINK_BATCH 128
+
+static unsigned long
+shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker,
+ unsigned long nr_pages_scanned, unsigned long lru_pages)
{
- sc->nr_to_scan = nr_to_scan;
- return (*shrinker->shrink)(shrinker, sc);
+ unsigned long freed = 0;
+ unsigned long long delta;
+ long total_scan;
+ long max_pass;
+ long nr;
+ long new_nr;
+ int nid = shrinkctl->nid;
+ long batch_size = shrinker->batch ? shrinker->batch
+ : SHRINK_BATCH;
+
+ max_pass = shrinker->count_objects(shrinker, shrinkctl);
+ if (max_pass == 0)
+ return 0;
+
+ /*
+ * copy the current shrinker scan count into a local variable
+ * and zero it so that other concurrent shrinker invocations
+ * don't also do this scanning work.
+ */
+ nr = atomic_long_xchg(&shrinker->nr_deferred[nid], 0);
+
+ total_scan = nr;
+ delta = (4 * nr_pages_scanned) / shrinker->seeks;
+ delta *= max_pass;
+ do_div(delta, lru_pages + 1);
+ total_scan += delta;
+ if (total_scan < 0) {
+ printk(KERN_ERR
+ "shrink_slab: %pF negative objects to delete nr=%ld\n",
+ shrinker->scan_objects, total_scan);
+ total_scan = max_pass;
+ }
+
+ /*
+ * We need to avoid excessive windup on filesystem shrinkers
+ * due to large numbers of GFP_NOFS allocations causing the
+ * shrinkers to return -1 all the time. This results in a large
+ * nr being built up so when a shrink that can do some work
+ * comes along it empties the entire cache due to nr >>>
+ * max_pass. This is bad for sustaining a working set in
+ * memory.
+ *
+ * Hence only allow the shrinker to scan the entire cache when
+ * a large delta change is calculated directly.
+ */
+ if (delta < max_pass / 4)
+ total_scan = min(total_scan, max_pass / 2);
+
+ /*
+ * Avoid risking looping forever due to too large nr value:
+ * never try to free more than twice the estimate number of
+ * freeable entries.
+ */
+ if (total_scan > max_pass * 2)
+ total_scan = max_pass * 2;
+
+ trace_mm_shrink_slab_start(shrinker, shrinkctl, nr,
+ nr_pages_scanned, lru_pages,
+ max_pass, delta, total_scan);
+
+ while (total_scan >= batch_size) {
+ unsigned long ret;
+
+ shrinkctl->nr_to_scan = batch_size;
+ ret = shrinker->scan_objects(shrinker, shrinkctl);
+ if (ret == SHRINK_STOP)
+ break;
+ freed += ret;
+
+ count_vm_events(SLABS_SCANNED, batch_size);
+ total_scan -= batch_size;
+
+ cond_resched();
+ }
+
+ /*
+ * move the unused scan count back into the shrinker in a
+ * manner that handles concurrent updates. If we exhausted the
+ * scan, there is no need to do an update.
+ */
+ if (total_scan > 0)
+ new_nr = atomic_long_add_return(total_scan,
+ &shrinker->nr_deferred[nid]);
+ else
+ new_nr = atomic_long_read(&shrinker->nr_deferred[nid]);
+
+ trace_mm_shrink_slab_end(shrinker, freed, nr, new_nr);
+ return freed;
}
-#define SHRINK_BATCH 128
/*
* Call the shrink functions to age shrinkable caches
*
@@ -205,115 +340,45 @@
*
* Returns the number of slab objects which we shrunk.
*/
-unsigned long shrink_slab(struct shrink_control *shrink,
+unsigned long shrink_slab(struct shrink_control *shrinkctl,
unsigned long nr_pages_scanned,
unsigned long lru_pages)
{
struct shrinker *shrinker;
- unsigned long ret = 0;
+ unsigned long freed = 0;
if (nr_pages_scanned == 0)
nr_pages_scanned = SWAP_CLUSTER_MAX;
if (!down_read_trylock(&shrinker_rwsem)) {
- /* Assume we'll be able to shrink next time */
- ret = 1;
+ /*
+ * If we would return 0, our callers would understand that we
+ * have nothing else to shrink and give up trying. By returning
+ * 1 we keep it going and assume we'll be able to shrink next
+ * time.
+ */
+ freed = 1;
goto out;
}
list_for_each_entry(shrinker, &shrinker_list, list) {
- unsigned long long delta;
- long total_scan;
- long max_pass;
- int shrink_ret = 0;
- long nr;
- long new_nr;
- long batch_size = shrinker->batch ? shrinker->batch
- : SHRINK_BATCH;
+ for_each_node_mask(shrinkctl->nid, shrinkctl->nodes_to_scan) {
+ if (!node_online(shrinkctl->nid))
+ continue;
- max_pass = do_shrinker_shrink(shrinker, shrink, 0);
- if (max_pass <= 0)
- continue;
-
- /*
- * copy the current shrinker scan count into a local variable
- * and zero it so that other concurrent shrinker invocations
- * don't also do this scanning work.
- */
- nr = atomic_long_xchg(&shrinker->nr_in_batch, 0);
-
- total_scan = nr;
- delta = (4 * nr_pages_scanned) / shrinker->seeks;
- delta *= max_pass;
- do_div(delta, lru_pages + 1);
- total_scan += delta;
- if (total_scan < 0) {
- printk(KERN_ERR "shrink_slab: %pF negative objects to "
- "delete nr=%ld\n",
- shrinker->shrink, total_scan);
- total_scan = max_pass;
- }
-
- /*
- * We need to avoid excessive windup on filesystem shrinkers
- * due to large numbers of GFP_NOFS allocations causing the
- * shrinkers to return -1 all the time. This results in a large
- * nr being built up so when a shrink that can do some work
- * comes along it empties the entire cache due to nr >>>
- * max_pass. This is bad for sustaining a working set in
- * memory.
- *
- * Hence only allow the shrinker to scan the entire cache when
- * a large delta change is calculated directly.
- */
- if (delta < max_pass / 4)
- total_scan = min(total_scan, max_pass / 2);
-
- /*
- * Avoid risking looping forever due to too large nr value:
- * never try to free more than twice the estimate number of
- * freeable entries.
- */
- if (total_scan > max_pass * 2)
- total_scan = max_pass * 2;
-
- trace_mm_shrink_slab_start(shrinker, shrink, nr,
- nr_pages_scanned, lru_pages,
- max_pass, delta, total_scan);
-
- while (total_scan >= batch_size) {
- int nr_before;
-
- nr_before = do_shrinker_shrink(shrinker, shrink, 0);
- shrink_ret = do_shrinker_shrink(shrinker, shrink,
- batch_size);
- if (shrink_ret == -1)
+ if (!(shrinker->flags & SHRINKER_NUMA_AWARE) &&
+ (shrinkctl->nid != 0))
break;
- if (shrink_ret < nr_before)
- ret += nr_before - shrink_ret;
- count_vm_events(SLABS_SCANNED, batch_size);
- total_scan -= batch_size;
- cond_resched();
+ freed += shrink_slab_node(shrinkctl, shrinker,
+ nr_pages_scanned, lru_pages);
+
}
-
- /*
- * move the unused scan count back into the shrinker in a
- * manner that handles concurrent updates. If we exhausted the
- * scan, there is no need to do an update.
- */
- if (total_scan > 0)
- new_nr = atomic_long_add_return(total_scan,
- &shrinker->nr_in_batch);
- else
- new_nr = atomic_long_read(&shrinker->nr_in_batch);
-
- trace_mm_shrink_slab_end(shrinker, shrink_ret, nr, new_nr);
}
up_read(&shrinker_rwsem);
out:
cond_resched();
- return ret;
+ return freed;
}
static inline int is_page_cache_freeable(struct page *page)
@@ -545,7 +610,7 @@
*/
void putback_lru_page(struct page *page)
{
- int lru;
+ bool is_unevictable;
int was_unevictable = PageUnevictable(page);
VM_BUG_ON(PageLRU(page));
@@ -560,14 +625,14 @@
* unevictable page on [in]active list.
* We know how to handle that.
*/
- lru = page_lru_base_type(page);
+ is_unevictable = false;
lru_cache_add(page);
} else {
/*
* Put unevictable pages directly on zone's unevictable
* list.
*/
- lru = LRU_UNEVICTABLE;
+ is_unevictable = true;
add_page_to_unevictable_list(page);
/*
* When racing with an mlock or AS_UNEVICTABLE clearing
@@ -587,7 +652,7 @@
* page is on unevictable list, it never be freed. To avoid that,
* check after we added it to the list, again.
*/
- if (lru == LRU_UNEVICTABLE && page_evictable(page)) {
+ if (is_unevictable && page_evictable(page)) {
if (!isolate_lru_page(page)) {
put_page(page);
goto redo;
@@ -598,9 +663,9 @@
*/
}
- if (was_unevictable && lru != LRU_UNEVICTABLE)
+ if (was_unevictable && !is_unevictable)
count_vm_event(UNEVICTABLE_PGRESCUED);
- else if (!was_unevictable && lru == LRU_UNEVICTABLE)
+ else if (!was_unevictable && is_unevictable)
count_vm_event(UNEVICTABLE_PGCULLED);
put_page(page); /* drop ref from isolate */
@@ -1789,7 +1854,7 @@
* latencies, so it's better to scan a minimum amount there as
* well.
*/
- if (current_is_kswapd() && zone->all_unreclaimable)
+ if (current_is_kswapd() && !zone_reclaimable(zone))
force_scan = true;
if (!global_reclaim(sc))
force_scan = true;
@@ -2111,9 +2176,11 @@
}
}
-static void shrink_zone(struct zone *zone, struct scan_control *sc)
+static int
+__shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim)
{
unsigned long nr_reclaimed, nr_scanned;
+ int groups_scanned = 0;
do {
struct mem_cgroup *root = sc->target_mem_cgroup;
@@ -2121,15 +2188,17 @@
.zone = zone,
.priority = sc->priority,
};
- struct mem_cgroup *memcg;
+ struct mem_cgroup *memcg = NULL;
+ mem_cgroup_iter_filter filter = (soft_reclaim) ?
+ mem_cgroup_soft_reclaim_eligible : NULL;
nr_reclaimed = sc->nr_reclaimed;
nr_scanned = sc->nr_scanned;
- memcg = mem_cgroup_iter(root, NULL, &reclaim);
- do {
+ while ((memcg = mem_cgroup_iter_cond(root, memcg, &reclaim, filter))) {
struct lruvec *lruvec;
+ groups_scanned++;
lruvec = mem_cgroup_zone_lruvec(zone, memcg);
shrink_lruvec(lruvec, sc);
@@ -2149,8 +2218,7 @@
mem_cgroup_iter_break(root, memcg);
break;
}
- memcg = mem_cgroup_iter(root, memcg, &reclaim);
- } while (memcg);
+ }
vmpressure(sc->gfp_mask, sc->target_mem_cgroup,
sc->nr_scanned - nr_scanned,
@@ -2158,6 +2226,37 @@
} while (should_continue_reclaim(zone, sc->nr_reclaimed - nr_reclaimed,
sc->nr_scanned - nr_scanned, sc));
+
+ return groups_scanned;
+}
+
+
+static void shrink_zone(struct zone *zone, struct scan_control *sc)
+{
+ bool do_soft_reclaim = mem_cgroup_should_soft_reclaim(sc);
+ unsigned long nr_scanned = sc->nr_scanned;
+ int scanned_groups;
+
+ scanned_groups = __shrink_zone(zone, sc, do_soft_reclaim);
+ /*
+ * memcg iterator might race with other reclaimer or start from
+ * a incomplete tree walk so the tree walk in __shrink_zone
+ * might have missed groups that are above the soft limit. Try
+ * another loop to catch up with others. Do it just once to
+ * prevent from reclaim latencies when other reclaimers always
+ * preempt this one.
+ */
+ if (do_soft_reclaim && !scanned_groups)
+ __shrink_zone(zone, sc, do_soft_reclaim);
+
+ /*
+ * No group is over the soft limit or those that are do not have
+ * pages in the zone we are reclaiming so we have to reclaim everybody
+ */
+ if (do_soft_reclaim && (sc->nr_scanned == nr_scanned)) {
+ __shrink_zone(zone, sc, false);
+ return;
+ }
}
/* Returns true if compaction should go ahead for a high-order request */
@@ -2221,8 +2320,6 @@
{
struct zoneref *z;
struct zone *zone;
- unsigned long nr_soft_reclaimed;
- unsigned long nr_soft_scanned;
bool aborted_reclaim = false;
/*
@@ -2244,8 +2341,8 @@
if (global_reclaim(sc)) {
if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
continue;
- if (zone->all_unreclaimable &&
- sc->priority != DEF_PRIORITY)
+ if (sc->priority != DEF_PRIORITY &&
+ !zone_reclaimable(zone))
continue; /* Let kswapd poll it */
if (IS_ENABLED(CONFIG_COMPACTION)) {
/*
@@ -2262,18 +2359,6 @@
continue;
}
}
- /*
- * This steals pages from memory cgroups over softlimit
- * and returns the number of reclaimed pages and
- * scanned pages. This works for global memory pressure
- * and balancing, not for a memcg's limit.
- */
- nr_soft_scanned = 0;
- nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
- sc->order, sc->gfp_mask,
- &nr_soft_scanned);
- sc->nr_reclaimed += nr_soft_reclaimed;
- sc->nr_scanned += nr_soft_scanned;
/* need some check for avoid more shrink_zone() */
}
@@ -2283,11 +2368,6 @@
return aborted_reclaim;
}
-static bool zone_reclaimable(struct zone *zone)
-{
- return zone->pages_scanned < zone_reclaimable_pages(zone) * 6;
-}
-
/* All zones in zonelist are unreclaimable? */
static bool all_unreclaimable(struct zonelist *zonelist,
struct scan_control *sc)
@@ -2301,7 +2381,7 @@
continue;
if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
continue;
- if (!zone->all_unreclaimable)
+ if (zone_reclaimable(zone))
return false;
}
@@ -2354,12 +2434,16 @@
*/
if (global_reclaim(sc)) {
unsigned long lru_pages = 0;
+
+ nodes_clear(shrink->nodes_to_scan);
for_each_zone_zonelist(zone, z, zonelist,
gfp_zone(sc->gfp_mask)) {
if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
continue;
lru_pages += zone_reclaimable_pages(zone);
+ node_set(zone_to_nid(zone),
+ shrink->nodes_to_scan);
}
shrink_slab(shrink, sc->nr_scanned, lru_pages);
@@ -2712,7 +2796,7 @@
* DEF_PRIORITY. Effectively, it considers them balanced so
* they must be considered balanced here as well!
*/
- if (zone->all_unreclaimable) {
+ if (!zone_reclaimable(zone)) {
balanced_pages += zone->managed_pages;
continue;
}
@@ -2773,7 +2857,6 @@
unsigned long lru_pages,
unsigned long *nr_attempted)
{
- unsigned long nr_slab;
int testorder = sc->order;
unsigned long balance_gap;
struct reclaim_state *reclaim_state = current->reclaim_state;
@@ -2816,17 +2899,16 @@
return true;
shrink_zone(zone, sc);
+ nodes_clear(shrink.nodes_to_scan);
+ node_set(zone_to_nid(zone), shrink.nodes_to_scan);
reclaim_state->reclaimed_slab = 0;
- nr_slab = shrink_slab(&shrink, sc->nr_scanned, lru_pages);
+ shrink_slab(&shrink, sc->nr_scanned, lru_pages);
sc->nr_reclaimed += reclaim_state->reclaimed_slab;
/* Account for the number of pages attempted to reclaim */
*nr_attempted += sc->nr_to_reclaim;
- if (nr_slab == 0 && !zone_reclaimable(zone))
- zone->all_unreclaimable = 1;
-
zone_clear_flag(zone, ZONE_WRITEBACK);
/*
@@ -2835,7 +2917,7 @@
* BDIs but as pressure is relieved, speculatively avoid congestion
* waits.
*/
- if (!zone->all_unreclaimable &&
+ if (zone_reclaimable(zone) &&
zone_balanced(zone, testorder, 0, classzone_idx)) {
zone_clear_flag(zone, ZONE_CONGESTED);
zone_clear_flag(zone, ZONE_TAIL_LRU_DIRTY);
@@ -2870,8 +2952,6 @@
{
int i;
int end_zone = 0; /* Inclusive. 0 = ZONE_DMA */
- unsigned long nr_soft_reclaimed;
- unsigned long nr_soft_scanned;
struct scan_control sc = {
.gfp_mask = GFP_KERNEL,
.priority = DEF_PRIORITY,
@@ -2901,8 +2981,8 @@
if (!populated_zone(zone))
continue;
- if (zone->all_unreclaimable &&
- sc.priority != DEF_PRIORITY)
+ if (sc.priority != DEF_PRIORITY &&
+ !zone_reclaimable(zone))
continue;
/*
@@ -2980,21 +3060,12 @@
if (!populated_zone(zone))
continue;
- if (zone->all_unreclaimable &&
- sc.priority != DEF_PRIORITY)
+ if (sc.priority != DEF_PRIORITY &&
+ !zone_reclaimable(zone))
continue;
sc.nr_scanned = 0;
- nr_soft_scanned = 0;
- /*
- * Call soft limit reclaim before calling shrink_zone.
- */
- nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
- order, sc.gfp_mask,
- &nr_soft_scanned);
- sc.nr_reclaimed += nr_soft_reclaimed;
-
/*
* There should be no need to raise the scanning
* priority if enough pages are already being scanned
@@ -3237,7 +3308,7 @@
}
if (!waitqueue_active(&pgdat->kswapd_wait))
return;
- if (zone_watermark_ok_safe(zone, order, low_wmark_pages(zone), 0, 0))
+ if (zone_balanced(zone, order, 0, 0))
return;
trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, zone_idx(zone), order);
@@ -3265,20 +3336,6 @@
return nr;
}
-unsigned long zone_reclaimable_pages(struct zone *zone)
-{
- int nr;
-
- nr = zone_page_state(zone, NR_ACTIVE_FILE) +
- zone_page_state(zone, NR_INACTIVE_FILE);
-
- if (get_nr_swap_pages() > 0)
- nr += zone_page_state(zone, NR_ACTIVE_ANON) +
- zone_page_state(zone, NR_INACTIVE_ANON);
-
- return nr;
-}
-
#ifdef CONFIG_HIBERNATION
/*
* Try to free `nr_to_reclaim' of memory, system-wide, and return the number of
@@ -3524,10 +3581,9 @@
* number of slab pages and shake the slab until it is reduced
* by the same nr_pages that we used for reclaiming unmapped
* pages.
- *
- * Note that shrink_slab will free memory on all zones and may
- * take a long time.
*/
+ nodes_clear(shrink.nodes_to_scan);
+ node_set(zone_to_nid(zone), shrink.nodes_to_scan);
for (;;) {
unsigned long lru_pages = zone_reclaimable_pages(zone);
@@ -3576,7 +3632,7 @@
zone_page_state(zone, NR_SLAB_RECLAIMABLE) <= zone->min_slab_pages)
return ZONE_RECLAIM_FULL;
- if (zone->all_unreclaimable)
+ if (!zone_reclaimable(zone))
return ZONE_RECLAIM_FULL;
/*
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 20c2ef4..9bb3145 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -19,6 +19,9 @@
#include <linux/math64.h>
#include <linux/writeback.h>
#include <linux/compaction.h>
+#include <linux/mm_inline.h>
+
+#include "internal.h"
#ifdef CONFIG_VM_EVENT_COUNTERS
DEFINE_PER_CPU(struct vm_event_state, vm_event_states) = {{0}};
@@ -414,12 +417,17 @@
EXPORT_SYMBOL(dec_zone_page_state);
#endif
+static inline void fold_diff(int *diff)
+{
+ int i;
+
+ for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
+ if (diff[i])
+ atomic_long_add(diff[i], &vm_stat[i]);
+}
+
/*
- * Update the zone counters for one cpu.
- *
- * The cpu specified must be either the current cpu or a processor that
- * is not online. If it is the current cpu then the execution thread must
- * be pinned to the current cpu.
+ * Update the zone counters for the current cpu.
*
* Note that refresh_cpu_vm_stats strives to only access
* node local memory. The per cpu pagesets on remote zones are placed
@@ -432,7 +440,67 @@
* with the global counters. These could cause remote node cache line
* bouncing and will have to be only done when necessary.
*/
-void refresh_cpu_vm_stats(int cpu)
+static void refresh_cpu_vm_stats(void)
+{
+ struct zone *zone;
+ int i;
+ int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
+
+ for_each_populated_zone(zone) {
+ struct per_cpu_pageset __percpu *p = zone->pageset;
+
+ for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) {
+ int v;
+
+ v = this_cpu_xchg(p->vm_stat_diff[i], 0);
+ if (v) {
+
+ atomic_long_add(v, &zone->vm_stat[i]);
+ global_diff[i] += v;
+#ifdef CONFIG_NUMA
+ /* 3 seconds idle till flush */
+ __this_cpu_write(p->expire, 3);
+#endif
+ }
+ }
+ cond_resched();
+#ifdef CONFIG_NUMA
+ /*
+ * Deal with draining the remote pageset of this
+ * processor
+ *
+ * Check if there are pages remaining in this pageset
+ * if not then there is nothing to expire.
+ */
+ if (!__this_cpu_read(p->expire) ||
+ !__this_cpu_read(p->pcp.count))
+ continue;
+
+ /*
+ * We never drain zones local to this processor.
+ */
+ if (zone_to_nid(zone) == numa_node_id()) {
+ __this_cpu_write(p->expire, 0);
+ continue;
+ }
+
+
+ if (__this_cpu_dec_return(p->expire))
+ continue;
+
+ if (__this_cpu_read(p->pcp.count))
+ drain_zone_pages(zone, __this_cpu_ptr(&p->pcp));
+#endif
+ }
+ fold_diff(global_diff);
+}
+
+/*
+ * Fold the data for an offline cpu into the global array.
+ * There cannot be any access by the offline cpu and therefore
+ * synchronization is simplified.
+ */
+void cpu_vm_stats_fold(int cpu)
{
struct zone *zone;
int i;
@@ -445,52 +513,16 @@
for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
if (p->vm_stat_diff[i]) {
- unsigned long flags;
int v;
- local_irq_save(flags);
v = p->vm_stat_diff[i];
p->vm_stat_diff[i] = 0;
- local_irq_restore(flags);
atomic_long_add(v, &zone->vm_stat[i]);
global_diff[i] += v;
-#ifdef CONFIG_NUMA
- /* 3 seconds idle till flush */
- p->expire = 3;
-#endif
}
- cond_resched();
-#ifdef CONFIG_NUMA
- /*
- * Deal with draining the remote pageset of this
- * processor
- *
- * Check if there are pages remaining in this pageset
- * if not then there is nothing to expire.
- */
- if (!p->expire || !p->pcp.count)
- continue;
-
- /*
- * We never drain zones local to this processor.
- */
- if (zone_to_nid(zone) == numa_node_id()) {
- p->expire = 0;
- continue;
- }
-
- p->expire--;
- if (p->expire)
- continue;
-
- if (p->pcp.count)
- drain_zone_pages(zone, &p->pcp);
-#endif
}
- for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
- if (global_diff[i])
- atomic_long_add(global_diff[i], &vm_stat[i]);
+ fold_diff(global_diff);
}
/*
@@ -703,6 +735,7 @@
const char * const vmstat_text[] = {
/* Zoned VM counters */
"nr_free_pages",
+ "nr_alloc_batch",
"nr_inactive_anon",
"nr_active_anon",
"nr_inactive_file",
@@ -817,6 +850,12 @@
"thp_zero_page_alloc",
"thp_zero_page_alloc_failed",
#endif
+#ifdef CONFIG_SMP
+ "nr_tlb_remote_flush",
+ "nr_tlb_remote_flush_received",
+#endif
+ "nr_tlb_local_flush_all",
+ "nr_tlb_local_flush_one",
#endif /* CONFIG_VM_EVENTS_COUNTERS */
};
@@ -1052,7 +1091,7 @@
"\n all_unreclaimable: %u"
"\n start_pfn: %lu"
"\n inactive_ratio: %u",
- zone->all_unreclaimable,
+ !zone_reclaimable(zone),
zone->zone_start_pfn,
zone->inactive_ratio);
seq_putc(m, '\n');
@@ -1177,7 +1216,7 @@
static void vmstat_update(struct work_struct *w)
{
- refresh_cpu_vm_stats(smp_processor_id());
+ refresh_cpu_vm_stats();
schedule_delayed_work(&__get_cpu_var(vmstat_work),
round_jiffies_relative(sysctl_stat_interval));
}
diff --git a/mm/zbud.c b/mm/zbud.c
index ad1e781..9451361 100644
--- a/mm/zbud.c
+++ b/mm/zbud.c
@@ -16,7 +16,7 @@
*
* zbud works by storing compressed pages, or "zpages", together in pairs in a
* single memory page called a "zbud page". The first buddy is "left
- * justifed" at the beginning of the zbud page, and the last buddy is "right
+ * justified" at the beginning of the zbud page, and the last buddy is "right
* justified" at the end of the zbud page. The benefit is that if either
* buddy is freed, the freed buddy space, coalesced with whatever slack space
* that existed between the buddies, results in the largest possible free region
@@ -243,7 +243,7 @@
* gfp should not set __GFP_HIGHMEM as highmem pages cannot be used
* as zbud pool pages.
*
- * Return: 0 if success and handle is set, otherwise -EINVAL is the size or
+ * Return: 0 if success and handle is set, otherwise -EINVAL if the size or
* gfp arguments are invalid or -ENOMEM if the pool was unable to allocate
* a new page.
*/
diff --git a/mm/zswap.c b/mm/zswap.c
index deda2b6..841e35f 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -409,7 +409,7 @@
struct page **retpage)
{
struct page *found_page, *new_page = NULL;
- struct address_space *swapper_space = &swapper_spaces[swp_type(entry)];
+ struct address_space *swapper_space = swap_address_space(entry);
int err;
*retpage = NULL;
@@ -790,26 +790,14 @@
static void zswap_frontswap_invalidate_area(unsigned type)
{
struct zswap_tree *tree = zswap_trees[type];
- struct rb_node *node;
- struct zswap_entry *entry;
+ struct zswap_entry *entry, *n;
if (!tree)
return;
/* walk the tree and free everything */
spin_lock(&tree->lock);
- /*
- * TODO: Even though this code should not be executed because
- * the try_to_unuse() in swapoff should have emptied the tree,
- * it is very wasteful to rebalance the tree after every
- * removal when we are freeing the whole tree.
- *
- * If post-order traversal code is ever added to the rbtree
- * implementation, it should be used here.
- */
- while ((node = rb_first(&tree->rbroot))) {
- entry = rb_entry(node, struct zswap_entry, rbnode);
- rb_erase(&entry->rbnode, &tree->rbroot);
+ rbtree_postorder_for_each_entry_safe(entry, n, &tree->rbroot, rbnode) {
zbud_free(tree->pool, entry->handle);
zswap_entry_cache_free(entry);
atomic_dec(&zswap_stored_pages);
diff --git a/net/9p/client.c b/net/9p/client.c
index ba93bda..ee8fd6b 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -987,6 +987,7 @@
{
int err;
struct p9_client *clnt;
+ char *client_id;
err = 0;
clnt = kmalloc(sizeof(struct p9_client), GFP_KERNEL);
@@ -995,6 +996,10 @@
clnt->trans_mod = NULL;
clnt->trans = NULL;
+
+ client_id = utsname()->nodename;
+ memcpy(clnt->name, client_id, strlen(client_id) + 1);
+
spin_lock_init(&clnt->lock);
INIT_LIST_HEAD(&clnt->fidlist);
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index e1c26b1..990afab 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -577,6 +577,10 @@
mutex_lock(&virtio_9p_lock);
list_add_tail(&chan->chan_list, &virtio_chan_list);
mutex_unlock(&virtio_9p_lock);
+
+ /* Let udev rules use the new mount_tag attribute. */
+ kobject_uevent(&(vdev->dev.kobj), KOBJ_CHANGE);
+
return 0;
out_free_tag:
@@ -654,6 +658,7 @@
list_del(&chan->chan_list);
mutex_unlock(&virtio_9p_lock);
sysfs_remove_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr);
+ kobject_uevent(&(vdev->dev.kobj), KOBJ_CHANGE);
kfree(chan->tag);
kfree(chan->vc_wq);
kfree(chan);
diff --git a/net/Kconfig b/net/Kconfig
index ee02136..b50dacc 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -228,7 +228,7 @@
config RFS_ACCEL
boolean
- depends on RPS && GENERIC_HARDIRQS
+ depends on RPS
select CPU_RMAP
default y
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 0ff42f0..1929af8 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -352,7 +352,7 @@
if (queue_index != new_index && sk &&
rcu_access_pointer(sk->sk_dst_cache))
- sk_tx_queue_set(sk, queue_index);
+ sk_tx_queue_set(sk, new_index);
queue_index = new_index;
}
diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
index 8a57d79..559d4ae 100644
--- a/net/ipv4/tcp_memcontrol.c
+++ b/net/ipv4/tcp_memcontrol.c
@@ -87,8 +87,8 @@
if (!cg_proto)
return -EINVAL;
- if (val > RESOURCE_MAX)
- val = RESOURCE_MAX;
+ if (val > RES_COUNTER_MAX)
+ val = RES_COUNTER_MAX;
tcp = tcp_from_cgproto(cg_proto);
@@ -101,9 +101,9 @@
tcp->tcp_prot_mem[i] = min_t(long, val >> PAGE_SHIFT,
net->ipv4.sysctl_tcp_mem[i]);
- if (val == RESOURCE_MAX)
+ if (val == RES_COUNTER_MAX)
clear_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags);
- else if (val != RESOURCE_MAX) {
+ else if (val != RES_COUNTER_MAX) {
/*
* The active bit needs to be written after the static_key
* update. This is what guarantees that the socket activation
@@ -187,7 +187,7 @@
switch (cft->private) {
case RES_LIMIT:
- val = tcp_read_stat(memcg, RES_LIMIT, RESOURCE_MAX);
+ val = tcp_read_stat(memcg, RES_LIMIT, RES_COUNTER_MAX);
break;
case RES_USAGE:
val = tcp_read_usage(memcg);
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 136fe55..7c96100 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -915,6 +915,9 @@
err = ip6_route_init();
if (err)
goto ip6_route_fail;
+ err = ndisc_late_init();
+ if (err)
+ goto ndisc_late_fail;
err = ip6_flowlabel_init();
if (err)
goto ip6_flowlabel_fail;
@@ -981,6 +984,8 @@
addrconf_fail:
ip6_flowlabel_cleanup();
ip6_flowlabel_fail:
+ ndisc_late_cleanup();
+ndisc_late_fail:
ip6_route_cleanup();
ip6_route_fail:
#ifdef CONFIG_PROC_FS
@@ -1043,6 +1048,7 @@
ipv6_exthdrs_exit();
addrconf_cleanup();
ip6_flowlabel_cleanup();
+ ndisc_late_cleanup();
ip6_route_cleanup();
#ifdef CONFIG_PROC_FS
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 07a7d65..8d67900 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -162,12 +162,6 @@
off += optlen;
len -= optlen;
}
- /* This case will not be caught by above check since its padding
- * length is smaller than 7:
- * 1 byte NH + 1 byte Length + 6 bytes Padding
- */
- if ((padlen == 6) && ((off - skb_network_header_len(skb)) == 8))
- goto bad;
if (len == 0)
return true;
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index a6c58ce..e275916 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -138,8 +138,8 @@
return false;
suppress_route:
- ip6_rt_put(rt);
- return true;
+ ip6_rt_put(rt);
+ return true;
}
static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags)
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 73db48e..5bec666 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -825,9 +825,9 @@
fn = fib6_add_1(root, &rt->rt6i_dst.addr, rt->rt6i_dst.plen,
offsetof(struct rt6_info, rt6i_dst), allow_create,
replace_required);
-
if (IS_ERR(fn)) {
err = PTR_ERR(fn);
+ fn = NULL;
goto out;
}
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 1217945..f8a55ff 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1727,24 +1727,28 @@
if (err)
goto out_unregister_pernet;
#endif
- err = register_netdevice_notifier(&ndisc_netdev_notifier);
- if (err)
- goto out_unregister_sysctl;
out:
return err;
-out_unregister_sysctl:
#ifdef CONFIG_SYSCTL
- neigh_sysctl_unregister(&nd_tbl.parms);
out_unregister_pernet:
-#endif
unregister_pernet_subsys(&ndisc_net_ops);
goto out;
+#endif
+}
+
+int __init ndisc_late_init(void)
+{
+ return register_netdevice_notifier(&ndisc_netdev_notifier);
+}
+
+void ndisc_late_cleanup(void)
+{
+ unregister_netdevice_notifier(&ndisc_netdev_notifier);
}
void ndisc_cleanup(void)
{
- unregister_netdevice_notifier(&ndisc_netdev_notifier);
#ifdef CONFIG_SYSCTL
neigh_sysctl_unregister(&nd_tbl.parms);
#endif
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index fb36f85..410db90 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -1178,6 +1178,7 @@
if (type > OVS_KEY_ATTR_MAX) {
OVS_NLERR("Unknown key attribute (type=%d, max=%d).\n",
type, OVS_KEY_ATTR_MAX);
+ return -EINVAL;
}
if (attrs & (1 << type)) {
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index c2178b1..863846c 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1495,7 +1495,7 @@
psched_ratecfg_precompute(&cl->ceil, &hopt->ceil);
cl->buffer = PSCHED_TICKS2NS(hopt->buffer);
- cl->cbuffer = PSCHED_TICKS2NS(hopt->buffer);
+ cl->cbuffer = PSCHED_TICKS2NS(hopt->cbuffer);
sch_tree_unlock(sch);
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index d5d5882..911b71b 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -806,6 +806,9 @@
goto skip_mkasconf;
}
+ if (laddr == NULL)
+ return -EINVAL;
+
/* We do not need RCU protection throughout this loop
* because this is done under a socket lock from the
* setsockopt call.
@@ -6176,7 +6179,7 @@
/* Is there any exceptional events? */
if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
mask |= POLLERR |
- sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0;
+ (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0);
if (sk->sk_shutdown & RCV_SHUTDOWN)
mask |= POLLRDHUP | POLLIN | POLLRDNORM;
if (sk->sk_shutdown == SHUTDOWN_MASK)
diff --git a/net/socket.c b/net/socket.c
index b2d7c62..ebed4b6 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -854,11 +854,6 @@
}
EXPORT_SYMBOL(kernel_recvmsg);
-static void sock_aio_dtor(struct kiocb *iocb)
-{
- kfree(iocb->private);
-}
-
static ssize_t sock_sendpage(struct file *file, struct page *page,
int offset, size_t size, loff_t *ppos, int more)
{
@@ -889,12 +884,8 @@
static struct sock_iocb *alloc_sock_iocb(struct kiocb *iocb,
struct sock_iocb *siocb)
{
- if (!is_sync_kiocb(iocb)) {
- siocb = kmalloc(sizeof(*siocb), GFP_KERNEL);
- if (!siocb)
- return NULL;
- iocb->ki_dtor = sock_aio_dtor;
- }
+ if (!is_sync_kiocb(iocb))
+ BUG();
siocb->kiocb = iocb;
iocb->private = siocb;
@@ -931,7 +922,7 @@
if (pos != 0)
return -ESPIPE;
- if (iocb->ki_left == 0) /* Match SYS5 behaviour */
+ if (iocb->ki_nbytes == 0) /* Match SYS5 behaviour */
return 0;
@@ -3072,12 +3063,12 @@
uifmap32 = &uifr32->ifr_ifru.ifru_map;
err = copy_from_user(&ifr, uifr32, sizeof(ifr.ifr_name));
- err |= __get_user(ifr.ifr_map.mem_start, &uifmap32->mem_start);
- err |= __get_user(ifr.ifr_map.mem_end, &uifmap32->mem_end);
- err |= __get_user(ifr.ifr_map.base_addr, &uifmap32->base_addr);
- err |= __get_user(ifr.ifr_map.irq, &uifmap32->irq);
- err |= __get_user(ifr.ifr_map.dma, &uifmap32->dma);
- err |= __get_user(ifr.ifr_map.port, &uifmap32->port);
+ err |= get_user(ifr.ifr_map.mem_start, &uifmap32->mem_start);
+ err |= get_user(ifr.ifr_map.mem_end, &uifmap32->mem_end);
+ err |= get_user(ifr.ifr_map.base_addr, &uifmap32->base_addr);
+ err |= get_user(ifr.ifr_map.irq, &uifmap32->irq);
+ err |= get_user(ifr.ifr_map.dma, &uifmap32->dma);
+ err |= get_user(ifr.ifr_map.port, &uifmap32->port);
if (err)
return -EFAULT;
@@ -3088,12 +3079,12 @@
if (cmd == SIOCGIFMAP && !err) {
err = copy_to_user(uifr32, &ifr, sizeof(ifr.ifr_name));
- err |= __put_user(ifr.ifr_map.mem_start, &uifmap32->mem_start);
- err |= __put_user(ifr.ifr_map.mem_end, &uifmap32->mem_end);
- err |= __put_user(ifr.ifr_map.base_addr, &uifmap32->base_addr);
- err |= __put_user(ifr.ifr_map.irq, &uifmap32->irq);
- err |= __put_user(ifr.ifr_map.dma, &uifmap32->dma);
- err |= __put_user(ifr.ifr_map.port, &uifmap32->port);
+ err |= put_user(ifr.ifr_map.mem_start, &uifmap32->mem_start);
+ err |= put_user(ifr.ifr_map.mem_end, &uifmap32->mem_end);
+ err |= put_user(ifr.ifr_map.base_addr, &uifmap32->base_addr);
+ err |= put_user(ifr.ifr_map.irq, &uifmap32->irq);
+ err |= put_user(ifr.ifr_map.dma, &uifmap32->dma);
+ err |= put_user(ifr.ifr_map.port, &uifmap32->port);
if (err)
err = -EFAULT;
}
@@ -3167,25 +3158,25 @@
struct in6_rtmsg32 __user *ur6 = argp;
ret = copy_from_user(&r6.rtmsg_dst, &(ur6->rtmsg_dst),
3 * sizeof(struct in6_addr));
- ret |= __get_user(r6.rtmsg_type, &(ur6->rtmsg_type));
- ret |= __get_user(r6.rtmsg_dst_len, &(ur6->rtmsg_dst_len));
- ret |= __get_user(r6.rtmsg_src_len, &(ur6->rtmsg_src_len));
- ret |= __get_user(r6.rtmsg_metric, &(ur6->rtmsg_metric));
- ret |= __get_user(r6.rtmsg_info, &(ur6->rtmsg_info));
- ret |= __get_user(r6.rtmsg_flags, &(ur6->rtmsg_flags));
- ret |= __get_user(r6.rtmsg_ifindex, &(ur6->rtmsg_ifindex));
+ ret |= get_user(r6.rtmsg_type, &(ur6->rtmsg_type));
+ ret |= get_user(r6.rtmsg_dst_len, &(ur6->rtmsg_dst_len));
+ ret |= get_user(r6.rtmsg_src_len, &(ur6->rtmsg_src_len));
+ ret |= get_user(r6.rtmsg_metric, &(ur6->rtmsg_metric));
+ ret |= get_user(r6.rtmsg_info, &(ur6->rtmsg_info));
+ ret |= get_user(r6.rtmsg_flags, &(ur6->rtmsg_flags));
+ ret |= get_user(r6.rtmsg_ifindex, &(ur6->rtmsg_ifindex));
r = (void *) &r6;
} else { /* ipv4 */
struct rtentry32 __user *ur4 = argp;
ret = copy_from_user(&r4.rt_dst, &(ur4->rt_dst),
3 * sizeof(struct sockaddr));
- ret |= __get_user(r4.rt_flags, &(ur4->rt_flags));
- ret |= __get_user(r4.rt_metric, &(ur4->rt_metric));
- ret |= __get_user(r4.rt_mtu, &(ur4->rt_mtu));
- ret |= __get_user(r4.rt_window, &(ur4->rt_window));
- ret |= __get_user(r4.rt_irtt, &(ur4->rt_irtt));
- ret |= __get_user(rtdev, &(ur4->rt_dev));
+ ret |= get_user(r4.rt_flags, &(ur4->rt_flags));
+ ret |= get_user(r4.rt_metric, &(ur4->rt_metric));
+ ret |= get_user(r4.rt_mtu, &(ur4->rt_mtu));
+ ret |= get_user(r4.rt_window, &(ur4->rt_window));
+ ret |= get_user(r4.rt_irtt, &(ur4->rt_irtt));
+ ret |= get_user(rtdev, &(ur4->rt_dev));
if (rtdev) {
ret |= copy_from_user(devname, compat_ptr(rtdev), 15);
r4.rt_dev = (char __user __force *)devname;
diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c
index 4151590..5285ead 100644
--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -434,12 +434,13 @@
/*
* Remove stale credentials. Avoid sleeping inside the loop.
*/
-static int
+static long
rpcauth_prune_expired(struct list_head *free, int nr_to_scan)
{
spinlock_t *cache_lock;
struct rpc_cred *cred, *next;
unsigned long expired = jiffies - RPC_AUTH_EXPIRY_MORATORIUM;
+ long freed = 0;
list_for_each_entry_safe(cred, next, &cred_unused, cr_lru) {
@@ -451,10 +452,11 @@
*/
if (time_in_range(cred->cr_expire, expired, jiffies) &&
test_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags) != 0)
- return 0;
+ break;
list_del_init(&cred->cr_lru);
number_cred_unused--;
+ freed++;
if (atomic_read(&cred->cr_count) != 0)
continue;
@@ -467,29 +469,39 @@
}
spin_unlock(cache_lock);
}
- return (number_cred_unused / 100) * sysctl_vfs_cache_pressure;
+ return freed;
}
/*
* Run memory cache shrinker.
*/
-static int
-rpcauth_cache_shrinker(struct shrinker *shrink, struct shrink_control *sc)
+static unsigned long
+rpcauth_cache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
+
{
LIST_HEAD(free);
- int res;
- int nr_to_scan = sc->nr_to_scan;
- gfp_t gfp_mask = sc->gfp_mask;
+ unsigned long freed;
- if ((gfp_mask & GFP_KERNEL) != GFP_KERNEL)
- return (nr_to_scan == 0) ? 0 : -1;
+ if ((sc->gfp_mask & GFP_KERNEL) != GFP_KERNEL)
+ return SHRINK_STOP;
+
+ /* nothing left, don't come back */
if (list_empty(&cred_unused))
- return 0;
+ return SHRINK_STOP;
+
spin_lock(&rpc_credcache_lock);
- res = rpcauth_prune_expired(&free, nr_to_scan);
+ freed = rpcauth_prune_expired(&free, sc->nr_to_scan);
spin_unlock(&rpc_credcache_lock);
rpcauth_destroy_credlist(&free);
- return res;
+
+ return freed;
+}
+
+static unsigned long
+rpcauth_cache_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
+
+{
+ return (number_cred_unused / 100) * sysctl_vfs_cache_pressure;
}
/*
@@ -805,7 +817,8 @@
}
static struct shrinker rpc_cred_shrinker = {
- .shrink = rpcauth_cache_shrinker,
+ .count_objects = rpcauth_cache_shrink_count,
+ .scan_objects = rpcauth_cache_shrink_scan,
.seeks = DEFAULT_SEEKS,
};
diff --git a/net/sunrpc/auth_generic.c b/net/sunrpc/auth_generic.c
index f6d84be..ed04869 100644
--- a/net/sunrpc/auth_generic.c
+++ b/net/sunrpc/auth_generic.c
@@ -239,7 +239,7 @@
if (test_and_clear_bit(RPC_CRED_KEY_EXPIRE_SOON,
&acred->ac_flags))
dprintk("RPC: UID %d Credential key reset\n",
- tcred->cr_uid);
+ from_kuid(&init_user_ns, tcred->cr_uid));
/* set up fasttrack for the normal case */
set_bit(RPC_CRED_NOTIFY_TIMEOUT, &acred->ac_flags);
}
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 30eb502..fcac5d1 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -75,7 +75,7 @@
* using integrity (two 4-byte integers): */
#define GSS_VERF_SLACK 100
-static DEFINE_HASHTABLE(gss_auth_hash_table, 16);
+static DEFINE_HASHTABLE(gss_auth_hash_table, 4);
static DEFINE_SPINLOCK(gss_auth_hash_lock);
struct gss_pipe {
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 2ee9eb7..47016c3 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -31,12 +31,16 @@
my $fix = 0;
my $root;
my %debug;
-my %ignore_type = ();
my %camelcase = ();
+my %use_type = ();
+my @use = ();
+my %ignore_type = ();
my @ignore = ();
my $help = 0;
my $configuration_file = ".checkpatch.conf";
my $max_line_length = 80;
+my $ignore_perl_version = 0;
+my $minimum_perl_version = 5.10.0;
sub help {
my ($exitcode) = @_;
@@ -54,6 +58,7 @@
--terse one line per report
-f, --file treat FILE as regular source file
--subjective, --strict enable more subjective tests
+ --types TYPE(,TYPE2...) show only these comma separated message types
--ignore TYPE(,TYPE2...) ignore various comma separated message types
--max-line-length=n set the maximum line length, if exceeded, warn
--show-types show the message "types" in the output
@@ -71,6 +76,8 @@
"<inputfile>.EXPERIMENTAL-checkpatch-fixes"
with potential errors corrected to the preferred
checkpatch style
+ --ignore-perl-version override checking of perl version. expect
+ runtime errors.
-h, --help, --version display this help and exit
When FILE is - read standard input.
@@ -116,6 +123,7 @@
'subjective!' => \$check,
'strict!' => \$check,
'ignore=s' => \@ignore,
+ 'types=s' => \@use,
'show-types!' => \$show_types,
'max-line-length=i' => \$max_line_length,
'root=s' => \$root,
@@ -123,6 +131,7 @@
'mailback!' => \$mailback,
'summary-file!' => \$summary_file,
'fix!' => \$fix,
+ 'ignore-perl-version!' => \$ignore_perl_version,
'debug=s' => \%debug,
'test-only=s' => \$tst_only,
'h|help' => \$help,
@@ -133,24 +142,50 @@
my $exit = 0;
+if ($^V && $^V lt $minimum_perl_version) {
+ printf "$P: requires at least perl version %vd\n", $minimum_perl_version;
+ if (!$ignore_perl_version) {
+ exit(1);
+ }
+}
+
if ($#ARGV < 0) {
print "$P: no input files\n";
exit(1);
}
-@ignore = split(/,/, join(',',@ignore));
-foreach my $word (@ignore) {
- $word =~ s/\s*\n?$//g;
- $word =~ s/^\s*//g;
- $word =~ s/\s+/ /g;
- $word =~ tr/[a-z]/[A-Z]/;
+sub hash_save_array_words {
+ my ($hashRef, $arrayRef) = @_;
- next if ($word =~ m/^\s*#/);
- next if ($word =~ m/^\s*$/);
+ my @array = split(/,/, join(',', @$arrayRef));
+ foreach my $word (@array) {
+ $word =~ s/\s*\n?$//g;
+ $word =~ s/^\s*//g;
+ $word =~ s/\s+/ /g;
+ $word =~ tr/[a-z]/[A-Z]/;
- $ignore_type{$word}++;
+ next if ($word =~ m/^\s*#/);
+ next if ($word =~ m/^\s*$/);
+
+ $hashRef->{$word}++;
+ }
}
+sub hash_show_words {
+ my ($hashRef, $prefix) = @_;
+
+ if ($quiet == 0 && keys %$hashRef) {
+ print "NOTE: $prefix message types:";
+ foreach my $word (sort keys %$hashRef) {
+ print " $word";
+ }
+ print "\n\n";
+ }
+}
+
+hash_save_array_words(\%ignore_type, \@ignore);
+hash_save_array_words(\%use_type, \@use);
+
my $dbg_values = 0;
my $dbg_possible = 0;
my $dbg_type = 0;
@@ -207,6 +242,8 @@
__rcu
}x;
+our $InitAttribute = qr{__(?:mem|cpu|dev|net_|)(?:initdata|initconst|init\b)};
+
# Notes to $Attribute:
# We need \b after 'init' otherwise 'initconst' will cause a false positive in a check
our $Attribute = qr{
@@ -227,7 +264,7 @@
__deprecated|
__read_mostly|
__kprobes|
- __(?:mem|cpu|dev|)(?:initdata|initconst|init\b)|
+ $InitAttribute|
____cacheline_aligned|
____cacheline_aligned_in_smp|
____cacheline_internodealigned_in_smp|
@@ -257,6 +294,7 @@
}x;
our $NonptrType;
+our $NonptrTypeWithAttr;
our $Type;
our $Declare;
@@ -319,6 +357,12 @@
qr{${Ident}_handler},
qr{${Ident}_handler_fn},
);
+our @typeListWithAttr = (
+ @typeList,
+ qr{struct\s+$InitAttribute\s+$Ident},
+ qr{union\s+$InitAttribute\s+$Ident},
+);
+
our @modifierList = (
qr{fastcall},
);
@@ -332,6 +376,7 @@
sub build_types {
my $mods = "(?x: \n" . join("|\n ", @modifierList) . "\n)";
my $all = "(?x: \n" . join("|\n ", @typeList) . "\n)";
+ my $allWithAttr = "(?x: \n" . join("|\n ", @typeListWithAttr) . "\n)";
$Modifier = qr{(?:$Attribute|$Sparse|$mods)};
$NonptrType = qr{
(?:$Modifier\s+|const\s+)*
@@ -342,6 +387,15 @@
)
(?:\s+$Modifier|\s+const)*
}x;
+ $NonptrTypeWithAttr = qr{
+ (?:$Modifier\s+|const\s+)*
+ (?:
+ (?:typeof|__typeof__)\s*\([^\)]*\)|
+ (?:$typeTypedefs\b)|
+ (?:${allWithAttr}\b)
+ )
+ (?:\s+$Modifier|\s+const)*
+ }x;
$Type = qr{
$NonptrType
(?:(?:\s|\*|\[\])+\s*const|(?:\s|\*|\[\])+|(?:\s*\[\s*\])+)?
@@ -1355,7 +1409,9 @@
my $prefix = '';
sub show_type {
- return !defined $ignore_type{$_[0]};
+ return defined $use_type{$_[0]} if (scalar keys %use_type > 0);
+
+ return !defined $ignore_type{$_[0]};
}
sub report {
@@ -1435,7 +1491,23 @@
sub trim {
my ($string) = @_;
- $string =~ s/(^\s+|\s+$)//g;
+ $string =~ s/^\s+|\s+$//g;
+
+ return $string;
+}
+
+sub ltrim {
+ my ($string) = @_;
+
+ $string =~ s/^\s+//;
+
+ return $string;
+}
+
+sub rtrim {
+ my ($string) = @_;
+
+ $string =~ s/\s+$//;
return $string;
}
@@ -1532,6 +1604,7 @@
my %suppress_export;
my $suppress_statement = 0;
+ my %signatures = ();
# Pre-scan the patch sanitizing the lines.
# Pre-scan the patch looking for any __setup documentation.
@@ -1624,6 +1697,8 @@
$linenr = 0;
foreach my $line (@lines) {
$linenr++;
+ my $sline = $line; #copy of $line
+ $sline =~ s/$;/ /g; #with comments as spaces
my $rawline = $rawlines[$linenr - 1];
@@ -1781,6 +1856,17 @@
"email address '$email' might be better as '$suggested_email$comment'\n" . $herecurr);
}
}
+
+# Check for duplicate signatures
+ my $sig_nospace = $line;
+ $sig_nospace =~ s/\s//g;
+ $sig_nospace = lc($sig_nospace);
+ if (defined $signatures{$sig_nospace}) {
+ WARN("BAD_SIGN_OFF",
+ "Duplicate signature\n" . $herecurr);
+ } else {
+ $signatures{$sig_nospace} = 1;
+ }
}
# Check for wrappage within a valid hunk of the file
@@ -1845,15 +1931,17 @@
#trailing whitespace
if ($line =~ /^\+.*\015/) {
my $herevet = "$here\n" . cat_vet($rawline) . "\n";
- ERROR("DOS_LINE_ENDINGS",
- "DOS line endings\n" . $herevet);
-
+ if (ERROR("DOS_LINE_ENDINGS",
+ "DOS line endings\n" . $herevet) &&
+ $fix) {
+ $fixed[$linenr - 1] =~ s/[\s\015]+$//;
+ }
} elsif ($rawline =~ /^\+.*\S\s+$/ || $rawline =~ /^\+\s+$/) {
my $herevet = "$here\n" . cat_vet($rawline) . "\n";
if (ERROR("TRAILING_WHITESPACE",
"trailing whitespace\n" . $herevet) &&
$fix) {
- $fixed[$linenr - 1] =~ s/^(\+.*?)\s+$/$1/;
+ $fixed[$linenr - 1] =~ s/\s+$//;
}
$rpt_cleaners = 1;
@@ -2060,6 +2148,7 @@
if ($realfile =~ m@^(drivers/net/|net/)@ &&
$prevrawline =~ /^\+[ \t]*\/\*/ && #starting /*
$prevrawline !~ /\*\/[ \t]*$/ && #no trailing */
+ $rawline =~ /^\+/ && #line is new
$rawline !~ /^\+[ \t]*\*/) { #no leading *
WARN("NETWORKING_BLOCK_COMMENT_STYLE",
"networking block comments start with * on subsequent lines\n" . $hereprev);
@@ -2126,7 +2215,7 @@
$realline_next);
#print "LINE<$line>\n";
if ($linenr >= $suppress_statement &&
- $realcnt && $line =~ /.\s*\S/) {
+ $realcnt && $sline =~ /.\s*\S/) {
($stat, $cond, $line_nr_next, $remain_next, $off_next) =
ctx_statement_block($linenr, $realcnt, 0);
$stat =~ s/\n./\n /g;
@@ -2486,16 +2575,22 @@
}
# check for global initialisers.
- if ($line =~ /^.$Type\s*$Ident\s*(?:\s+$Modifier)*\s*=\s*(0|NULL|false)\s*;/) {
- ERROR("GLOBAL_INITIALISERS",
- "do not initialise globals to 0 or NULL\n" .
- $herecurr);
+ if ($line =~ /^\+(\s*$Type\s*$Ident\s*(?:\s+$Modifier))*\s*=\s*(0|NULL|false)\s*;/) {
+ if (ERROR("GLOBAL_INITIALISERS",
+ "do not initialise globals to 0 or NULL\n" .
+ $herecurr) &&
+ $fix) {
+ $fixed[$linenr - 1] =~ s/($Type\s*$Ident\s*(?:\s+$Modifier))*\s*=\s*(0|NULL|false)\s*;/$1;/;
+ }
}
# check for static initialisers.
- if ($line =~ /\bstatic\s.*=\s*(0|NULL|false)\s*;/) {
- ERROR("INITIALISED_STATIC",
- "do not initialise statics to 0 or NULL\n" .
- $herecurr);
+ if ($line =~ /^\+.*\bstatic\s.*=\s*(0|NULL|false)\s*;/) {
+ if (ERROR("INITIALISED_STATIC",
+ "do not initialise statics to 0 or NULL\n" .
+ $herecurr) &&
+ $fix) {
+ $fixed[$linenr - 1] =~ s/(\bstatic\s.*?)\s*=\s*(0|NULL|false)\s*;/$1;/;
+ }
}
# check for static const char * arrays.
@@ -2638,8 +2733,12 @@
}
if ($line =~ /\bpr_warning\s*\(/) {
- WARN("PREFER_PR_LEVEL",
- "Prefer pr_warn(... to pr_warning(...\n" . $herecurr);
+ if (WARN("PREFER_PR_LEVEL",
+ "Prefer pr_warn(... to pr_warning(...\n" . $herecurr) &&
+ $fix) {
+ $fixed[$linenr - 1] =~
+ s/\bpr_warning\b/pr_warn/;
+ }
}
if ($line =~ /\bdev_printk\s*\(\s*KERN_([A-Z]+)/) {
@@ -2759,6 +2858,7 @@
$off = 0;
my $blank = copy_spacing($opline);
+ my $last_after = -1;
for (my $n = 0; $n < $#elements; $n += 2) {
@@ -2824,7 +2924,7 @@
$cc !~ /^\\/ && $cc !~ /^;/) {
if (ERROR("SPACING",
"space required after that '$op' $at\n" . $hereptr)) {
- $good = trim($fix_elements[$n]) . " " . trim($fix_elements[$n + 1]) . " ";
+ $good = $fix_elements[$n] . trim($fix_elements[$n + 1]) . " ";
$line_fixed = 1;
}
}
@@ -2839,11 +2939,11 @@
if ($ctx =~ /Wx.|.xW/) {
if (ERROR("SPACING",
"spaces prohibited around that '$op' $at\n" . $hereptr)) {
- $good = trim($fix_elements[$n]) . trim($fix_elements[$n + 1]);
- $line_fixed = 1;
+ $good = rtrim($fix_elements[$n]) . trim($fix_elements[$n + 1]);
if (defined $fix_elements[$n + 2]) {
$fix_elements[$n + 2] =~ s/^\s+//;
}
+ $line_fixed = 1;
}
}
@@ -2852,8 +2952,9 @@
if ($ctx !~ /.x[WEC]/ && $cc !~ /^}/) {
if (ERROR("SPACING",
"space required after that '$op' $at\n" . $hereptr)) {
- $good = trim($fix_elements[$n]) . trim($fix_elements[$n + 1]) . " ";
+ $good = $fix_elements[$n] . trim($fix_elements[$n + 1]) . " ";
$line_fixed = 1;
+ $last_after = $n;
}
}
@@ -2870,8 +2971,10 @@
if ($ctx !~ /[WEBC]x./ && $ca !~ /(?:\)|!|~|\*|-|\&|\||\+\+|\-\-|\{)$/) {
if (ERROR("SPACING",
"space required before that '$op' $at\n" . $hereptr)) {
- $good = trim($fix_elements[$n]) . " " . trim($fix_elements[$n + 1]);
- $line_fixed = 1;
+ if ($n != $last_after + 2) {
+ $good = $fix_elements[$n] . " " . ltrim($fix_elements[$n + 1]);
+ $line_fixed = 1;
+ }
}
}
if ($op eq '*' && $cc =~/\s*$Modifier\b/) {
@@ -2880,12 +2983,11 @@
} elsif ($ctx =~ /.xW/) {
if (ERROR("SPACING",
"space prohibited after that '$op' $at\n" . $hereptr)) {
- $fixed_line =~ s/\s+$//;
- $good = trim($fix_elements[$n]) . trim($fix_elements[$n + 1]);
- $line_fixed = 1;
+ $good = $fix_elements[$n] . rtrim($fix_elements[$n + 1]);
if (defined $fix_elements[$n + 2]) {
$fix_elements[$n + 2] =~ s/^\s+//;
}
+ $line_fixed = 1;
}
}
@@ -2894,8 +2996,7 @@
if ($ctx !~ /[WEOBC]x[^W]/ && $ctx !~ /[^W]x[WOBEC]/) {
if (ERROR("SPACING",
"space required one side of that '$op' $at\n" . $hereptr)) {
- $fixed_line =~ s/\s+$//;
- $good = trim($fix_elements[$n]) . trim($fix_elements[$n + 1]) . " ";
+ $good = $fix_elements[$n] . trim($fix_elements[$n + 1]) . " ";
$line_fixed = 1;
}
}
@@ -2903,20 +3004,18 @@
($ctx =~ /Wx./ && $cc =~ /^;/)) {
if (ERROR("SPACING",
"space prohibited before that '$op' $at\n" . $hereptr)) {
- $fixed_line =~ s/\s+$//;
- $good = trim($fix_elements[$n]) . trim($fix_elements[$n + 1]);
+ $good = rtrim($fix_elements[$n]) . trim($fix_elements[$n + 1]);
$line_fixed = 1;
}
}
if ($ctx =~ /ExW/) {
if (ERROR("SPACING",
"space prohibited after that '$op' $at\n" . $hereptr)) {
- $fixed_line =~ s/\s+$//;
- $good = trim($fix_elements[$n]) . trim($fix_elements[$n + 1]);
- $line_fixed = 1;
+ $good = $fix_elements[$n] . trim($fix_elements[$n + 1]);
if (defined $fix_elements[$n + 2]) {
$fix_elements[$n + 2] =~ s/^\s+//;
}
+ $line_fixed = 1;
}
}
@@ -2930,8 +3029,10 @@
if ($ctx =~ /Wx[^WCE]|[^WCE]xW/) {
if (ERROR("SPACING",
"need consistent spacing around '$op' $at\n" . $hereptr)) {
- $fixed_line =~ s/\s+$//;
- $good = trim($fix_elements[$n]) . " " . trim($fix_elements[$n + 1]) . " ";
+ $good = rtrim($fix_elements[$n]) . " " . trim($fix_elements[$n + 1]) . " ";
+ if (defined $fix_elements[$n + 2]) {
+ $fix_elements[$n + 2] =~ s/^\s+//;
+ }
$line_fixed = 1;
}
}
@@ -2942,7 +3043,7 @@
if ($ctx =~ /Wx./) {
if (ERROR("SPACING",
"space prohibited before that '$op' $at\n" . $hereptr)) {
- $good = trim($fix_elements[$n]) . trim($fix_elements[$n + 1]);
+ $good = rtrim($fix_elements[$n]) . trim($fix_elements[$n + 1]);
$line_fixed = 1;
}
}
@@ -2969,8 +3070,10 @@
if ($ok == 0) {
if (ERROR("SPACING",
"spaces required around that '$op' $at\n" . $hereptr)) {
- $good = trim($fix_elements[$n]) . " " . trim($fix_elements[$n + 1]) . " ";
- $good = $fix_elements[$n] . " " . trim($fix_elements[$n + 1]) . " ";
+ $good = rtrim($fix_elements[$n]) . " " . trim($fix_elements[$n + 1]) . " ";
+ if (defined $fix_elements[$n + 2]) {
+ $fix_elements[$n + 2] =~ s/^\s+//;
+ }
$line_fixed = 1;
}
}
@@ -3031,8 +3134,7 @@
if (ERROR("SPACING",
"space required before the open brace '{'\n" . $herecurr) &&
$fix) {
- $fixed[$linenr - 1] =~
- s/^(\+.*(?:do|\))){/$1 {/;
+ $fixed[$linenr - 1] =~ s/^(\+.*(?:do|\))){/$1 {/;
}
}
@@ -3047,8 +3149,12 @@
# closing brace should have a space following it when it has anything
# on the line
if ($line =~ /}(?!(?:,|;|\)))\S/) {
- ERROR("SPACING",
- "space required after that close brace '}'\n" . $herecurr);
+ if (ERROR("SPACING",
+ "space required after that close brace '}'\n" . $herecurr) &&
+ $fix) {
+ $fixed[$linenr - 1] =~
+ s/}((?!(?:,|;|\)))\S)/} $1/;
+ }
}
# check spacing on square brackets
@@ -3271,8 +3377,13 @@
#gcc binary extension
if ($var =~ /^$Binary$/) {
- WARN("GCC_BINARY_CONSTANT",
- "Avoid gcc v4.3+ binary constant extension: <$var>\n" . $herecurr);
+ if (WARN("GCC_BINARY_CONSTANT",
+ "Avoid gcc v4.3+ binary constant extension: <$var>\n" . $herecurr) &&
+ $fix) {
+ my $hexval = sprintf("0x%x", oct($var));
+ $fixed[$linenr - 1] =~
+ s/\b$var\b/$hexval/;
+ }
}
#CamelCase
@@ -3282,19 +3393,26 @@
$var !~ /^(?:Clear|Set|TestClear|TestSet|)Page[A-Z]/ &&
#Ignore SI style variants like nS, mV and dB (ie: max_uV, regulator_min_uA_show)
$var !~ /^(?:[a-z_]*?)_?[a-z][A-Z](?:_[a-z_]+)?$/) {
- seed_camelcase_includes() if ($check);
- if (!defined $camelcase{$var}) {
- $camelcase{$var} = 1;
- CHK("CAMELCASE",
- "Avoid CamelCase: <$var>\n" . $herecurr);
+ while ($var =~ m{($Ident)}g) {
+ my $word = $1;
+ next if ($word !~ /[A-Z][a-z]|[a-z][A-Z]/);
+ seed_camelcase_includes() if ($check);
+ if (!defined $camelcase{$word}) {
+ $camelcase{$word} = 1;
+ CHK("CAMELCASE",
+ "Avoid CamelCase: <$word>\n" . $herecurr);
+ }
}
}
}
#no spaces allowed after \ in define
- if ($line=~/\#\s*define.*\\\s$/) {
- WARN("WHITESPACE_AFTER_LINE_CONTINUATION",
- "Whitepspace after \\ makes next lines useless\n" . $herecurr);
+ if ($line =~ /\#\s*define.*\\\s+$/) {
+ if (WARN("WHITESPACE_AFTER_LINE_CONTINUATION",
+ "Whitespace after \\ makes next lines useless\n" . $herecurr) &&
+ $fix) {
+ $fixed[$linenr - 1] =~ s/\s+$//;
+ }
}
#warn if <asm/foo.h> is #included and <linux/foo.h> is available (uses RAW line)
@@ -3374,7 +3492,8 @@
$dstat !~ /^for\s*$Constant$/ && # for (...)
$dstat !~ /^for\s*$Constant\s+(?:$Ident|-?$Constant)$/ && # for (...) bar()
$dstat !~ /^do\s*{/ && # do {...
- $dstat !~ /^\({/) # ({...
+ $dstat !~ /^\({/ && # ({...
+ $ctx !~ /^.\s*#\s*define\s+TRACE_(?:SYSTEM|INCLUDE_FILE|INCLUDE_PATH)\b/)
{
$ctx =~ s/\n*$//;
my $herectx = $here . "\n";
@@ -3606,6 +3725,32 @@
}
}
+sub string_find_replace {
+ my ($string, $find, $replace) = @_;
+
+ $string =~ s/$find/$replace/g;
+
+ return $string;
+}
+
+# check for bad placement of section $InitAttribute (e.g.: __initdata)
+ if ($line =~ /(\b$InitAttribute\b)/) {
+ my $attr = $1;
+ if ($line =~ /^\+\s*static\s+(?:const\s+)?(?:$attr\s+)?($NonptrTypeWithAttr)\s+(?:$attr\s+)?($Ident(?:\[[^]]*\])?)\s*[=;]/) {
+ my $ptr = $1;
+ my $var = $2;
+ if ((($ptr =~ /\b(union|struct)\s+$attr\b/ &&
+ ERROR("MISPLACED_INIT",
+ "$attr should be placed after $var\n" . $herecurr)) ||
+ ($ptr !~ /\b(union|struct)\s+$attr\b/ &&
+ WARN("MISPLACED_INIT",
+ "$attr should be placed after $var\n" . $herecurr))) &&
+ $fix) {
+ $fixed[$linenr - 1] =~ s/(\bstatic\s+(?:const\s+)?)(?:$attr\s+)?($NonptrTypeWithAttr)\s+(?:$attr\s+)?($Ident(?:\[[^]]*\])?)\s*([=;])\s*/"$1" . trim(string_find_replace($2, "\\s*$attr\\s*", " ")) . " " . trim(string_find_replace($3, "\\s*$attr\\s*", "")) . " $attr" . ("$4" eq ";" ? ";" : " = ")/e;
+ }
+ }
+ }
+
# prefer usleep_range over udelay
if ($line =~ /\budelay\s*\(\s*(\d+)\s*\)/) {
# ignore udelay's < 10, however
@@ -3691,8 +3836,12 @@
# Check for __inline__ and __inline, prefer inline
if ($line =~ /\b(__inline__|__inline)\b/) {
- WARN("INLINE",
- "plain inline is preferred over $1\n" . $herecurr);
+ if (WARN("INLINE",
+ "plain inline is preferred over $1\n" . $herecurr) &&
+ $fix) {
+ $fixed[$linenr - 1] =~ s/\b(__inline__|__inline)\b/inline/;
+
+ }
}
# Check for __attribute__ packed, prefer __packed
@@ -3709,14 +3858,21 @@
# Check for __attribute__ format(printf, prefer __printf
if ($line =~ /\b__attribute__\s*\(\s*\(\s*format\s*\(\s*printf/) {
- WARN("PREFER_PRINTF",
- "__printf(string-index, first-to-check) is preferred over __attribute__((format(printf, string-index, first-to-check)))\n" . $herecurr);
+ if (WARN("PREFER_PRINTF",
+ "__printf(string-index, first-to-check) is preferred over __attribute__((format(printf, string-index, first-to-check)))\n" . $herecurr) &&
+ $fix) {
+ $fixed[$linenr - 1] =~ s/\b__attribute__\s*\(\s*\(\s*format\s*\(\s*printf\s*,\s*(.*)\)\s*\)\s*\)/"__printf(" . trim($1) . ")"/ex;
+
+ }
}
# Check for __attribute__ format(scanf, prefer __scanf
if ($line =~ /\b__attribute__\s*\(\s*\(\s*format\s*\(\s*scanf\b/) {
- WARN("PREFER_SCANF",
- "__scanf(string-index, first-to-check) is preferred over __attribute__((format(scanf, string-index, first-to-check)))\n" . $herecurr);
+ if (WARN("PREFER_SCANF",
+ "__scanf(string-index, first-to-check) is preferred over __attribute__((format(scanf, string-index, first-to-check)))\n" . $herecurr) &&
+ $fix) {
+ $fixed[$linenr - 1] =~ s/\b__attribute__\s*\(\s*\(\s*format\s*\(\s*scanf\s*,\s*(.*)\)\s*\)\s*\)/"__scanf(" . trim($1) . ")"/ex;
+ }
}
# check for sizeof(&)
@@ -3727,8 +3883,11 @@
# check for sizeof without parenthesis
if ($line =~ /\bsizeof\s+((?:\*\s*|)$Lval|$Type(?:\s+$Lval|))/) {
- WARN("SIZEOF_PARENTHESIS",
- "sizeof $1 should be sizeof($1)\n" . $herecurr);
+ if (WARN("SIZEOF_PARENTHESIS",
+ "sizeof $1 should be sizeof($1)\n" . $herecurr) &&
+ $fix) {
+ $fixed[$linenr - 1] =~ s/\bsizeof\s+((?:\*\s*|)$Lval|$Type(?:\s+$Lval|))/"sizeof(" . trim($1) . ")"/ex;
+ }
}
# check for line continuations in quoted strings with odd counts of "
@@ -3747,8 +3906,11 @@
if ($line =~ /\bseq_printf\s*\(/) {
my $fmt = get_quoted_string($line, $rawline);
if ($fmt !~ /[^\\]\%/) {
- WARN("PREFER_SEQ_PUTS",
- "Prefer seq_puts to seq_printf\n" . $herecurr);
+ if (WARN("PREFER_SEQ_PUTS",
+ "Prefer seq_puts to seq_printf\n" . $herecurr) &&
+ $fix) {
+ $fixed[$linenr - 1] =~ s/\bseq_printf\b/seq_puts/;
+ }
}
}
@@ -3810,6 +3972,16 @@
}
}
+# check for new externs in .h files.
+ if ($realfile =~ /\.h$/ &&
+ $line =~ /^\+\s*(extern\s+)$Type\s*$Ident\s*\(/s) {
+ if (WARN("AVOID_EXTERNS",
+ "extern prototypes should be avoided in .h files\n" . $herecurr) &&
+ $fix) {
+ $fixed[$linenr - 1] =~ s/(.*)\bextern\b\s*(.*)/$1$2/;
+ }
+ }
+
# check for new externs in .c files.
if ($realfile =~ /\.c$/ && defined $stat &&
$stat =~ /^.\s*(?:extern\s+)?$Type\s+($Ident)(\s*)\(/s)
@@ -3879,8 +4051,11 @@
# check for multiple semicolons
if ($line =~ /;\s*;\s*$/) {
- WARN("ONE_SEMICOLON",
- "Statements terminations use 1 semicolon\n" . $herecurr);
+ if (WARN("ONE_SEMICOLON",
+ "Statements terminations use 1 semicolon\n" . $herecurr) &&
+ $fix) {
+ $fixed[$linenr - 1] =~ s/(\s*;\s*){2,}$/;/g;
+ }
}
# check for switch/default statements without a break;
@@ -3898,9 +4073,12 @@
}
# check for gcc specific __FUNCTION__
- if ($line =~ /__FUNCTION__/) {
- WARN("USE_FUNC",
- "__func__ should be used instead of gcc specific __FUNCTION__\n" . $herecurr);
+ if ($line =~ /\b__FUNCTION__\b/) {
+ if (WARN("USE_FUNC",
+ "__func__ should be used instead of gcc specific __FUNCTION__\n" . $herecurr) &&
+ $fix) {
+ $fixed[$linenr - 1] =~ s/\b__FUNCTION__\b/__func__/g;
+ }
}
# check for use of yield()
@@ -4105,13 +4283,8 @@
}
}
- if ($quiet == 0 && keys %ignore_type) {
- print "NOTE: Ignored message types:";
- foreach my $ignore (sort keys %ignore_type) {
- print " $ignore";
- }
- print "\n\n";
- }
+ hash_show_words(\%use_type, "Used");
+ hash_show_words(\%ignore_type, "Ignored");
if ($clean == 0 && $fix && "@rawlines" ne "@fixed") {
my $newfile = $filename . ".EXPERIMENTAL-checkpatch-fixes";
diff --git a/scripts/config b/scripts/config
index 567120a..6804179 100755
--- a/scripts/config
+++ b/scripts/config
@@ -62,15 +62,52 @@
fi
}
+txt_append() {
+ local anchor="$1"
+ local insert="$2"
+ local infile="$3"
+ local tmpfile="$infile.swp"
+
+ # sed append cmd: 'a\' + newline + text + newline
+ cmd="$(printf "a\\%b$insert" "\n")"
+
+ sed -e "/$anchor/$cmd" "$infile" >"$tmpfile"
+ # replace original file with the edited one
+ mv "$tmpfile" "$infile"
+}
+
+txt_subst() {
+ local before="$1"
+ local after="$2"
+ local infile="$3"
+ local tmpfile="$infile.swp"
+
+ sed -e "s:$before:$after:" "$infile" >"$tmpfile"
+ # replace original file with the edited one
+ mv "$tmpfile" "$infile"
+}
+
+txt_delete() {
+ local text="$1"
+ local infile="$2"
+ local tmpfile="$infile.swp"
+
+ sed -e "/$text/d" "$infile" >"$tmpfile"
+ # replace original file with the edited one
+ mv "$tmpfile" "$infile"
+}
+
set_var() {
local name=$1 new=$2 before=$3
name_re="^($name=|# $name is not set)"
before_re="^($before=|# $before is not set)"
if test -n "$before" && grep -Eq "$before_re" "$FN"; then
- sed -ri "/$before_re/a $new" "$FN"
+ txt_append "^$before=" "$new" "$FN"
+ txt_append "^# $before is not set" "$new" "$FN"
elif grep -Eq "$name_re" "$FN"; then
- sed -ri "s:$name_re.*:$new:" "$FN"
+ txt_subst "^$name=.*" "$new" "$FN"
+ txt_subst "^# $name is not set" "$new" "$FN"
else
echo "$new" >>"$FN"
fi
@@ -79,7 +116,8 @@
undef_var() {
local name=$1
- sed -ri "/^($name=|# $name is not set)/d" "$FN"
+ txt_delete "^$name=" "$FN"
+ txt_delete "^# $name is not set" "$FN"
}
if [ "$1" = "--file" ]; then
diff --git a/scripts/diffconfig b/scripts/diffconfig
index b91f3e3..6d67283 100755
--- a/scripts/diffconfig
+++ b/scripts/diffconfig
@@ -10,7 +10,7 @@
import sys, os
def usage():
- print """Usage: diffconfig [-h] [-m] [<config1> <config2>]
+ print("""Usage: diffconfig [-h] [-m] [<config1> <config2>]
Diffconfig is a simple utility for comparing two .config files.
Using standard diff to compare .config files often includes extraneous and
@@ -33,7 +33,7 @@
EXT2_FS y -> n
LOG_BUF_SHIFT 14 -> 16
PRINTK_TIME n -> y
-"""
+""")
sys.exit(0)
# returns a dictionary of name/value pairs for config items in the file
@@ -54,23 +54,23 @@
if merge_style:
if new_value:
if new_value=="n":
- print "# CONFIG_%s is not set" % config
+ print("# CONFIG_%s is not set" % config)
else:
- print "CONFIG_%s=%s" % (config, new_value)
+ print("CONFIG_%s=%s" % (config, new_value))
else:
if op=="-":
- print "-%s %s" % (config, value)
+ print("-%s %s" % (config, value))
elif op=="+":
- print "+%s %s" % (config, new_value)
+ print("+%s %s" % (config, new_value))
else:
- print " %s %s -> %s" % (config, value, new_value)
+ print(" %s %s -> %s" % (config, value, new_value))
def main():
global merge_style
# parse command line args
if ("-h" in sys.argv or "--help" in sys.argv):
- usage()
+ usage()
merge_style = 0
if "-m" in sys.argv:
@@ -79,23 +79,27 @@
argc = len(sys.argv)
if not (argc==1 or argc == 3):
- print "Error: incorrect number of arguments or unrecognized option"
+ print("Error: incorrect number of arguments or unrecognized option")
usage()
if argc == 1:
# if no filenames given, assume .config and .config.old
build_dir=""
- if os.environ.has_key("KBUILD_OUTPUT"):
+ if "KBUILD_OUTPUT" in os.environ:
build_dir = os.environ["KBUILD_OUTPUT"]+"/"
-
configa_filename = build_dir + ".config.old"
configb_filename = build_dir + ".config"
else:
configa_filename = sys.argv[1]
configb_filename = sys.argv[2]
- a = readconfig(file(configa_filename))
- b = readconfig(file(configb_filename))
+ try:
+ a = readconfig(open(configa_filename))
+ b = readconfig(open(configb_filename))
+ except (IOError):
+ e = sys.exc_info()[1]
+ print("I/O error[%s]: %s\n" % (e.args[0],e.args[1]))
+ usage()
# print items in a but not b (accumulate, sort and print)
old = []
@@ -121,8 +125,7 @@
# now print items in b but not in a
# (items from b that were in a were removed above)
- new = b.keys()
- new.sort()
+ new = sorted(b.keys())
for config in new:
print_config("+", config, None, b[config])
diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index c55c227..87f7238 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -140,7 +140,9 @@
sym->flags |= def_flags;
break;
}
- conf_warning("symbol value '%s' invalid for %s", p, sym->name);
+ if (def != S_DEF_AUTO)
+ conf_warning("symbol value '%s' invalid for %s",
+ p, sym->name);
return 1;
case S_OTHER:
if (*p != '"') {
@@ -161,7 +163,8 @@
memmove(p2, p2 + 1, strlen(p2));
}
if (!p2) {
- conf_warning("invalid string found");
+ if (def != S_DEF_AUTO)
+ conf_warning("invalid string found");
return 1;
}
/* fall through */
@@ -172,7 +175,9 @@
sym->def[def].val = strdup(p);
sym->flags |= def_flags;
} else {
- conf_warning("symbol value '%s' invalid for %s", p, sym->name);
+ if (def != S_DEF_AUTO)
+ conf_warning("symbol value '%s' invalid for %s",
+ p, sym->name);
return 1;
}
break;
diff --git a/scripts/kconfig/mconf.c b/scripts/kconfig/mconf.c
index 6c9c45f..2c39631 100644
--- a/scripts/kconfig/mconf.c
+++ b/scripts/kconfig/mconf.c
@@ -401,8 +401,8 @@
struct subtitle_part stpart;
title = str_new();
- str_printf( &title, _("Enter %s (sub)string or regexp to search for "
- "(with or without \"%s\")"), CONFIG_, CONFIG_);
+ str_printf( &title, _("Enter (sub)string or regexp to search for "
+ "(with or without \"%s\")"), CONFIG_);
again:
dialog_clear();
diff --git a/scripts/kconfig/menu.c b/scripts/kconfig/menu.c
index 7e233a6..c1d5320 100644
--- a/scripts/kconfig/menu.c
+++ b/scripts/kconfig/menu.c
@@ -197,12 +197,15 @@
void menu_add_option(int token, char *arg)
{
- struct property *prop;
-
switch (token) {
case T_OPT_MODULES:
- prop = prop_alloc(P_DEFAULT, modules_sym);
- prop->expr = expr_alloc_symbol(current_entry->sym);
+ if (modules_sym)
+ zconf_error("symbol '%s' redefines option 'modules'"
+ " already defined by symbol '%s'",
+ current_entry->sym->name,
+ modules_sym->name
+ );
+ modules_sym = current_entry->sym;
break;
case T_OPT_DEFCONFIG_LIST:
if (!sym_defconfig_list)
diff --git a/scripts/kconfig/nconf.c b/scripts/kconfig/nconf.c
index 7975d8d..4fbecd2 100644
--- a/scripts/kconfig/nconf.c
+++ b/scripts/kconfig/nconf.c
@@ -695,8 +695,8 @@
int dres;
title = str_new();
- str_printf( &title, _("Enter %s (sub)string or regexp to search for "
- "(with or without \"%s\")"), CONFIG_, CONFIG_);
+ str_printf( &title, _("Enter (sub)string or regexp to search for "
+ "(with or without \"%s\")"), CONFIG_);
again:
dres = dialog_inputbox(main_window,
diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c
index d550300..c9a6775 100644
--- a/scripts/kconfig/symbol.c
+++ b/scripts/kconfig/symbol.c
@@ -136,7 +136,7 @@
return NULL;
}
-static long sym_get_range_val(struct symbol *sym, int base)
+static long long sym_get_range_val(struct symbol *sym, int base)
{
sym_calc_value(sym);
switch (sym->type) {
@@ -149,13 +149,14 @@
default:
break;
}
- return strtol(sym->curr.val, NULL, base);
+ return strtoll(sym->curr.val, NULL, base);
}
static void sym_validate_range(struct symbol *sym)
{
struct property *prop;
- long base, val, val2;
+ int base;
+ long long val, val2;
char str[64];
switch (sym->type) {
@@ -171,7 +172,7 @@
prop = sym_get_range_prop(sym);
if (!prop)
return;
- val = strtol(sym->curr.val, NULL, base);
+ val = strtoll(sym->curr.val, NULL, base);
val2 = sym_get_range_val(prop->expr->left.sym, base);
if (val >= val2) {
val2 = sym_get_range_val(prop->expr->right.sym, base);
@@ -179,9 +180,9 @@
return;
}
if (sym->type == S_INT)
- sprintf(str, "%ld", val2);
+ sprintf(str, "%lld", val2);
else
- sprintf(str, "0x%lx", val2);
+ sprintf(str, "0x%llx", val2);
sym->curr.val = strdup(str);
}
@@ -594,7 +595,7 @@
bool sym_string_within_range(struct symbol *sym, const char *str)
{
struct property *prop;
- long val;
+ long long val;
switch (sym->type) {
case S_STRING:
@@ -605,7 +606,7 @@
prop = sym_get_range_prop(sym);
if (!prop)
return true;
- val = strtol(str, NULL, 10);
+ val = strtoll(str, NULL, 10);
return val >= sym_get_range_val(prop->expr->left.sym, 10) &&
val <= sym_get_range_val(prop->expr->right.sym, 10);
case S_HEX:
@@ -614,7 +615,7 @@
prop = sym_get_range_prop(sym);
if (!prop)
return true;
- val = strtol(str, NULL, 16);
+ val = strtoll(str, NULL, 16);
return val >= sym_get_range_val(prop->expr->left.sym, 16) &&
val <= sym_get_range_val(prop->expr->right.sym, 16);
case S_BOOLEAN:
@@ -963,11 +964,11 @@
* - first, symbols that match exactly
* - then, alphabetical sort
*/
-static int sym_rel_comp( const void *sym1, const void *sym2 )
+static int sym_rel_comp(const void *sym1, const void *sym2)
{
- struct sym_match *s1 = *(struct sym_match **)sym1;
- struct sym_match *s2 = *(struct sym_match **)sym2;
- int l1, l2;
+ const struct sym_match *s1 = sym1;
+ const struct sym_match *s2 = sym2;
+ int exact1, exact2;
/* Exact match:
* - if matched length on symbol s1 is the length of that symbol,
@@ -978,11 +979,11 @@
* exactly; if this is the case, we can't decide which comes first,
* and we fallback to sorting alphabetically.
*/
- l1 = s1->eo - s1->so;
- l2 = s2->eo - s2->so;
- if (l1 == strlen(s1->sym->name) && l2 != strlen(s2->sym->name))
+ exact1 = (s1->eo - s1->so) == strlen(s1->sym->name);
+ exact2 = (s2->eo - s2->so) == strlen(s2->sym->name);
+ if (exact1 && !exact2)
return -1;
- if (l1 != strlen(s1->sym->name) && l2 == strlen(s2->sym->name))
+ if (!exact1 && exact2)
return 1;
/* As a fallback, sort symbols alphabetically */
@@ -992,7 +993,7 @@
struct symbol **sym_re_search(const char *pattern)
{
struct symbol *sym, **sym_arr = NULL;
- struct sym_match **sym_match_arr = NULL;
+ struct sym_match *sym_match_arr = NULL;
int i, cnt, size;
regex_t re;
regmatch_t match[1];
@@ -1005,47 +1006,38 @@
return NULL;
for_all_symbols(i, sym) {
- struct sym_match *tmp_sym_match;
if (sym->flags & SYMBOL_CONST || !sym->name)
continue;
if (regexec(&re, sym->name, 1, match, 0))
continue;
- if (cnt + 1 >= size) {
+ if (cnt >= size) {
void *tmp;
size += 16;
- tmp = realloc(sym_match_arr, size * sizeof(struct sym_match *));
- if (!tmp) {
+ tmp = realloc(sym_match_arr, size * sizeof(struct sym_match));
+ if (!tmp)
goto sym_re_search_free;
- }
sym_match_arr = tmp;
}
sym_calc_value(sym);
- tmp_sym_match = (struct sym_match*)malloc(sizeof(struct sym_match));
- if (!tmp_sym_match)
- goto sym_re_search_free;
- tmp_sym_match->sym = sym;
- /* As regexec return 0, we know we have a match, so
+ /* As regexec returned 0, we know we have a match, so
* we can use match[0].rm_[se]o without further checks
*/
- tmp_sym_match->so = match[0].rm_so;
- tmp_sym_match->eo = match[0].rm_eo;
- sym_match_arr[cnt++] = tmp_sym_match;
+ sym_match_arr[cnt].so = match[0].rm_so;
+ sym_match_arr[cnt].eo = match[0].rm_eo;
+ sym_match_arr[cnt++].sym = sym;
}
if (sym_match_arr) {
- qsort(sym_match_arr, cnt, sizeof(struct sym_match*), sym_rel_comp);
+ qsort(sym_match_arr, cnt, sizeof(struct sym_match), sym_rel_comp);
sym_arr = malloc((cnt+1) * sizeof(struct symbol));
if (!sym_arr)
goto sym_re_search_free;
for (i = 0; i < cnt; i++)
- sym_arr[i] = sym_match_arr[i]->sym;
+ sym_arr[i] = sym_match_arr[i].sym;
sym_arr[cnt] = NULL;
}
sym_re_search_free:
- if (sym_match_arr) {
- for (i = 0; i < cnt; i++)
- free(sym_match_arr[i]);
- free(sym_match_arr);
- }
+ /* sym_match_arr can be NULL if no match, but free(NULL) is OK */
+ free(sym_match_arr);
regfree(&re);
return sym_arr;
diff --git a/scripts/kconfig/zconf.tab.c_shipped b/scripts/kconfig/zconf.tab.c_shipped
index f636141..25ae16a 100644
--- a/scripts/kconfig/zconf.tab.c_shipped
+++ b/scripts/kconfig/zconf.tab.c_shipped
@@ -1,9 +1,8 @@
-/* A Bison parser, made by GNU Bison 2.4.3. */
+/* A Bison parser, made by GNU Bison 2.5. */
-/* Skeleton implementation for Bison's Yacc-like parsers in C
+/* Bison implementation for Yacc-like parsers in C
- Copyright (C) 1984, 1989, 1990, 2000, 2001, 2002, 2003, 2004, 2005, 2006,
- 2009, 2010 Free Software Foundation, Inc.
+ Copyright (C) 1984, 1989-1990, 2000-2011 Free Software Foundation, Inc.
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
@@ -45,7 +44,7 @@
#define YYBISON 1
/* Bison version. */
-#define YYBISON_VERSION "2.4.3"
+#define YYBISON_VERSION "2.5"
/* Skeleton name. */
#define YYSKELETON_NAME "yacc.c"
@@ -302,11 +301,11 @@
# define alloca _alloca
# else
# define YYSTACK_ALLOC alloca
-# if ! defined _ALLOCA_H && ! defined _STDLIB_H && (defined __STDC__ || defined __C99__FUNC__ \
+# if ! defined _ALLOCA_H && ! defined EXIT_SUCCESS && (defined __STDC__ || defined __C99__FUNC__ \
|| defined __cplusplus || defined _MSC_VER)
# include <stdlib.h> /* INFRINGES ON USER NAME SPACE */
-# ifndef _STDLIB_H
-# define _STDLIB_H 1
+# ifndef EXIT_SUCCESS
+# define EXIT_SUCCESS 0
# endif
# endif
# endif
@@ -329,24 +328,24 @@
# ifndef YYSTACK_ALLOC_MAXIMUM
# define YYSTACK_ALLOC_MAXIMUM YYSIZE_MAXIMUM
# endif
-# if (defined __cplusplus && ! defined _STDLIB_H \
+# if (defined __cplusplus && ! defined EXIT_SUCCESS \
&& ! ((defined YYMALLOC || defined malloc) \
&& (defined YYFREE || defined free)))
# include <stdlib.h> /* INFRINGES ON USER NAME SPACE */
-# ifndef _STDLIB_H
-# define _STDLIB_H 1
+# ifndef EXIT_SUCCESS
+# define EXIT_SUCCESS 0
# endif
# endif
# ifndef YYMALLOC
# define YYMALLOC malloc
-# if ! defined malloc && ! defined _STDLIB_H && (defined __STDC__ || defined __C99__FUNC__ \
+# if ! defined malloc && ! defined EXIT_SUCCESS && (defined __STDC__ || defined __C99__FUNC__ \
|| defined __cplusplus || defined _MSC_VER)
void *malloc (YYSIZE_T); /* INFRINGES ON USER NAME SPACE */
# endif
# endif
# ifndef YYFREE
# define YYFREE free
-# if ! defined free && ! defined _STDLIB_H && (defined __STDC__ || defined __C99__FUNC__ \
+# if ! defined free && ! defined EXIT_SUCCESS && (defined __STDC__ || defined __C99__FUNC__ \
|| defined __cplusplus || defined _MSC_VER)
void free (void *); /* INFRINGES ON USER NAME SPACE */
# endif
@@ -375,23 +374,7 @@
((N) * (sizeof (yytype_int16) + sizeof (YYSTYPE)) \
+ YYSTACK_GAP_MAXIMUM)
-/* Copy COUNT objects from FROM to TO. The source and destination do
- not overlap. */
-# ifndef YYCOPY
-# if defined __GNUC__ && 1 < __GNUC__
-# define YYCOPY(To, From, Count) \
- __builtin_memcpy (To, From, (Count) * sizeof (*(From)))
-# else
-# define YYCOPY(To, From, Count) \
- do \
- { \
- YYSIZE_T yyi; \
- for (yyi = 0; yyi < (Count); yyi++) \
- (To)[yyi] = (From)[yyi]; \
- } \
- while (YYID (0))
-# endif
-# endif
+# define YYCOPY_NEEDED 1
/* Relocate STACK from its old location to the new one. The
local variables YYSIZE and YYSTACKSIZE give the old and new number of
@@ -411,6 +394,26 @@
#endif
+#if defined YYCOPY_NEEDED && YYCOPY_NEEDED
+/* Copy COUNT objects from FROM to TO. The source and destination do
+ not overlap. */
+# ifndef YYCOPY
+# if defined __GNUC__ && 1 < __GNUC__
+# define YYCOPY(To, From, Count) \
+ __builtin_memcpy (To, From, (Count) * sizeof (*(From)))
+# else
+# define YYCOPY(To, From, Count) \
+ do \
+ { \
+ YYSIZE_T yyi; \
+ for (yyi = 0; yyi < (Count); yyi++) \
+ (To)[yyi] = (From)[yyi]; \
+ } \
+ while (YYID (0))
+# endif
+# endif
+#endif /* !YYCOPY_NEEDED */
+
/* YYFINAL -- State number of the termination state. */
#define YYFINAL 11
/* YYLAST -- Last index in YYTABLE. */
@@ -529,18 +532,18 @@
/* YYRLINE[YYN] -- source line where rule number YYN was defined. */
static const yytype_uint16 yyrline[] =
{
- 0, 104, 104, 104, 106, 106, 108, 110, 111, 112,
- 113, 114, 115, 119, 123, 123, 123, 123, 123, 123,
- 123, 123, 127, 128, 129, 130, 131, 132, 136, 137,
- 143, 151, 157, 165, 175, 177, 178, 179, 180, 181,
- 182, 185, 193, 199, 209, 215, 221, 224, 226, 237,
- 238, 243, 252, 257, 265, 268, 270, 271, 272, 273,
- 274, 277, 283, 294, 300, 310, 312, 317, 325, 333,
- 336, 338, 339, 340, 345, 352, 359, 364, 372, 375,
- 377, 378, 379, 382, 390, 397, 404, 410, 417, 419,
- 420, 421, 424, 432, 434, 435, 438, 445, 447, 452,
- 453, 456, 457, 458, 462, 463, 466, 467, 470, 471,
- 472, 473, 474, 475, 476, 479, 480, 483, 484
+ 0, 103, 103, 103, 105, 105, 107, 109, 110, 111,
+ 112, 113, 114, 118, 122, 122, 122, 122, 122, 122,
+ 122, 122, 126, 127, 128, 129, 130, 131, 135, 136,
+ 142, 150, 156, 164, 174, 176, 177, 178, 179, 180,
+ 181, 184, 192, 198, 208, 214, 220, 223, 225, 236,
+ 237, 242, 251, 256, 264, 267, 269, 270, 271, 272,
+ 273, 276, 282, 293, 299, 309, 311, 316, 324, 332,
+ 335, 337, 338, 339, 344, 351, 358, 363, 371, 374,
+ 376, 377, 378, 381, 389, 396, 403, 409, 416, 418,
+ 419, 420, 423, 431, 433, 434, 437, 444, 446, 451,
+ 452, 455, 456, 457, 461, 462, 465, 466, 469, 470,
+ 471, 472, 473, 474, 475, 478, 479, 482, 483
};
#endif
@@ -615,8 +618,8 @@
3, 3, 2, 3, 3, 1, 1, 0, 1
};
-/* YYDEFACT[STATE-NAME] -- Default rule to reduce with in state
- STATE-NUM when YYTABLE doesn't specify something else to do. Zero
+/* YYDEFACT[STATE-NAME] -- Default reduction number in state STATE-NUM.
+ Performed when YYTABLE doesn't specify something else to do. Zero
means the default is an error. */
static const yytype_uint8 yydefact[] =
{
@@ -691,8 +694,7 @@
/* YYTABLE[YYPACT[STATE-NUM]]. What to do in state STATE-NUM. If
positive, shift that token. If negative, reduce the rule which
- number is the opposite. If zero, do what YYDEFACT says.
- If YYTABLE_NINF, syntax error. */
+ number is the opposite. If YYTABLE_NINF, syntax error. */
#define YYTABLE_NINF -86
static const yytype_int16 yytable[] =
{
@@ -728,6 +730,12 @@
184
};
+#define yypact_value_is_default(yystate) \
+ ((yystate) == (-90))
+
+#define yytable_value_is_error(yytable_value) \
+ YYID (0)
+
static const yytype_int16 yycheck[] =
{
1, 67, 68, 10, 93, 94, 76, 3, 76, 14,
@@ -821,7 +829,6 @@
{ \
yychar = (Token); \
yylval = (Value); \
- yytoken = YYTRANSLATE (yychar); \
YYPOPSTACK (1); \
goto yybackup; \
} \
@@ -863,19 +870,10 @@
#endif
-/* YY_LOCATION_PRINT -- Print the location on the stream.
- This macro was not mandated originally: define only if we know
- we won't break user code: when these are the locations we know. */
+/* This macro is provided for backward compatibility. */
#ifndef YY_LOCATION_PRINT
-# if defined YYLTYPE_IS_TRIVIAL && YYLTYPE_IS_TRIVIAL
-# define YY_LOCATION_PRINT(File, Loc) \
- fprintf (File, "%d.%d-%d.%d", \
- (Loc).first_line, (Loc).first_column, \
- (Loc).last_line, (Loc).last_column)
-# else
-# define YY_LOCATION_PRINT(File, Loc) ((void) 0)
-# endif
+# define YY_LOCATION_PRINT(File, Loc) ((void) 0)
#endif
@@ -1067,7 +1065,6 @@
# define YYMAXDEPTH 10000
#endif
-
#if YYERROR_VERBOSE
@@ -1170,115 +1167,142 @@
}
# endif
-/* Copy into YYRESULT an error message about the unexpected token
- YYCHAR while in state YYSTATE. Return the number of bytes copied,
- including the terminating null byte. If YYRESULT is null, do not
- copy anything; just return the number of bytes that would be
- copied. As a special case, return 0 if an ordinary "syntax error"
- message will do. Return YYSIZE_MAXIMUM if overflow occurs during
- size calculation. */
-static YYSIZE_T
-yysyntax_error (char *yyresult, int yystate, int yychar)
+/* Copy into *YYMSG, which is of size *YYMSG_ALLOC, an error message
+ about the unexpected token YYTOKEN for the state stack whose top is
+ YYSSP.
+
+ Return 0 if *YYMSG was successfully written. Return 1 if *YYMSG is
+ not large enough to hold the message. In that case, also set
+ *YYMSG_ALLOC to the required number of bytes. Return 2 if the
+ required number of bytes is too large to store. */
+static int
+yysyntax_error (YYSIZE_T *yymsg_alloc, char **yymsg,
+ yytype_int16 *yyssp, int yytoken)
{
- int yyn = yypact[yystate];
+ YYSIZE_T yysize0 = yytnamerr (0, yytname[yytoken]);
+ YYSIZE_T yysize = yysize0;
+ YYSIZE_T yysize1;
+ enum { YYERROR_VERBOSE_ARGS_MAXIMUM = 5 };
+ /* Internationalized format string. */
+ const char *yyformat = 0;
+ /* Arguments of yyformat. */
+ char const *yyarg[YYERROR_VERBOSE_ARGS_MAXIMUM];
+ /* Number of reported tokens (one for the "unexpected", one per
+ "expected"). */
+ int yycount = 0;
- if (! (YYPACT_NINF < yyn && yyn <= YYLAST))
- return 0;
- else
+ /* There are many possibilities here to consider:
+ - Assume YYFAIL is not used. It's too flawed to consider. See
+ <http://lists.gnu.org/archive/html/bison-patches/2009-12/msg00024.html>
+ for details. YYERROR is fine as it does not invoke this
+ function.
+ - If this state is a consistent state with a default action, then
+ the only way this function was invoked is if the default action
+ is an error action. In that case, don't check for expected
+ tokens because there are none.
+ - The only way there can be no lookahead present (in yychar) is if
+ this state is a consistent state with a default action. Thus,
+ detecting the absence of a lookahead is sufficient to determine
+ that there is no unexpected or expected token to report. In that
+ case, just report a simple "syntax error".
+ - Don't assume there isn't a lookahead just because this state is a
+ consistent state with a default action. There might have been a
+ previous inconsistent state, consistent state with a non-default
+ action, or user semantic action that manipulated yychar.
+ - Of course, the expected token list depends on states to have
+ correct lookahead information, and it depends on the parser not
+ to perform extra reductions after fetching a lookahead from the
+ scanner and before detecting a syntax error. Thus, state merging
+ (from LALR or IELR) and default reductions corrupt the expected
+ token list. However, the list is correct for canonical LR with
+ one exception: it will still contain any token that will not be
+ accepted due to an error action in a later state.
+ */
+ if (yytoken != YYEMPTY)
{
- int yytype = YYTRANSLATE (yychar);
- YYSIZE_T yysize0 = yytnamerr (0, yytname[yytype]);
- YYSIZE_T yysize = yysize0;
- YYSIZE_T yysize1;
- int yysize_overflow = 0;
- enum { YYERROR_VERBOSE_ARGS_MAXIMUM = 5 };
- char const *yyarg[YYERROR_VERBOSE_ARGS_MAXIMUM];
- int yyx;
+ int yyn = yypact[*yyssp];
+ yyarg[yycount++] = yytname[yytoken];
+ if (!yypact_value_is_default (yyn))
+ {
+ /* Start YYX at -YYN if negative to avoid negative indexes in
+ YYCHECK. In other words, skip the first -YYN actions for
+ this state because they are default actions. */
+ int yyxbegin = yyn < 0 ? -yyn : 0;
+ /* Stay within bounds of both yycheck and yytname. */
+ int yychecklim = YYLAST - yyn + 1;
+ int yyxend = yychecklim < YYNTOKENS ? yychecklim : YYNTOKENS;
+ int yyx;
-# if 0
- /* This is so xgettext sees the translatable formats that are
- constructed on the fly. */
- YY_("syntax error, unexpected %s");
- YY_("syntax error, unexpected %s, expecting %s");
- YY_("syntax error, unexpected %s, expecting %s or %s");
- YY_("syntax error, unexpected %s, expecting %s or %s or %s");
- YY_("syntax error, unexpected %s, expecting %s or %s or %s or %s");
-# endif
- char *yyfmt;
- char const *yyf;
- static char const yyunexpected[] = "syntax error, unexpected %s";
- static char const yyexpecting[] = ", expecting %s";
- static char const yyor[] = " or %s";
- char yyformat[sizeof yyunexpected
- + sizeof yyexpecting - 1
- + ((YYERROR_VERBOSE_ARGS_MAXIMUM - 2)
- * (sizeof yyor - 1))];
- char const *yyprefix = yyexpecting;
-
- /* Start YYX at -YYN if negative to avoid negative indexes in
- YYCHECK. */
- int yyxbegin = yyn < 0 ? -yyn : 0;
-
- /* Stay within bounds of both yycheck and yytname. */
- int yychecklim = YYLAST - yyn + 1;
- int yyxend = yychecklim < YYNTOKENS ? yychecklim : YYNTOKENS;
- int yycount = 1;
-
- yyarg[0] = yytname[yytype];
- yyfmt = yystpcpy (yyformat, yyunexpected);
-
- for (yyx = yyxbegin; yyx < yyxend; ++yyx)
- if (yycheck[yyx + yyn] == yyx && yyx != YYTERROR)
- {
- if (yycount == YYERROR_VERBOSE_ARGS_MAXIMUM)
- {
- yycount = 1;
- yysize = yysize0;
- yyformat[sizeof yyunexpected - 1] = '\0';
- break;
- }
- yyarg[yycount++] = yytname[yyx];
- yysize1 = yysize + yytnamerr (0, yytname[yyx]);
- yysize_overflow |= (yysize1 < yysize);
- yysize = yysize1;
- yyfmt = yystpcpy (yyfmt, yyprefix);
- yyprefix = yyor;
- }
-
- yyf = YY_(yyformat);
- yysize1 = yysize + yystrlen (yyf);
- yysize_overflow |= (yysize1 < yysize);
- yysize = yysize1;
-
- if (yysize_overflow)
- return YYSIZE_MAXIMUM;
-
- if (yyresult)
- {
- /* Avoid sprintf, as that infringes on the user's name space.
- Don't have undefined behavior even if the translation
- produced a string with the wrong number of "%s"s. */
- char *yyp = yyresult;
- int yyi = 0;
- while ((*yyp = *yyf) != '\0')
- {
- if (*yyp == '%' && yyf[1] == 's' && yyi < yycount)
- {
- yyp += yytnamerr (yyp, yyarg[yyi++]);
- yyf += 2;
- }
- else
- {
- yyp++;
- yyf++;
- }
- }
- }
- return yysize;
+ for (yyx = yyxbegin; yyx < yyxend; ++yyx)
+ if (yycheck[yyx + yyn] == yyx && yyx != YYTERROR
+ && !yytable_value_is_error (yytable[yyx + yyn]))
+ {
+ if (yycount == YYERROR_VERBOSE_ARGS_MAXIMUM)
+ {
+ yycount = 1;
+ yysize = yysize0;
+ break;
+ }
+ yyarg[yycount++] = yytname[yyx];
+ yysize1 = yysize + yytnamerr (0, yytname[yyx]);
+ if (! (yysize <= yysize1
+ && yysize1 <= YYSTACK_ALLOC_MAXIMUM))
+ return 2;
+ yysize = yysize1;
+ }
+ }
}
+
+ switch (yycount)
+ {
+# define YYCASE_(N, S) \
+ case N: \
+ yyformat = S; \
+ break
+ YYCASE_(0, YY_("syntax error"));
+ YYCASE_(1, YY_("syntax error, unexpected %s"));
+ YYCASE_(2, YY_("syntax error, unexpected %s, expecting %s"));
+ YYCASE_(3, YY_("syntax error, unexpected %s, expecting %s or %s"));
+ YYCASE_(4, YY_("syntax error, unexpected %s, expecting %s or %s or %s"));
+ YYCASE_(5, YY_("syntax error, unexpected %s, expecting %s or %s or %s or %s"));
+# undef YYCASE_
+ }
+
+ yysize1 = yysize + yystrlen (yyformat);
+ if (! (yysize <= yysize1 && yysize1 <= YYSTACK_ALLOC_MAXIMUM))
+ return 2;
+ yysize = yysize1;
+
+ if (*yymsg_alloc < yysize)
+ {
+ *yymsg_alloc = 2 * yysize;
+ if (! (yysize <= *yymsg_alloc
+ && *yymsg_alloc <= YYSTACK_ALLOC_MAXIMUM))
+ *yymsg_alloc = YYSTACK_ALLOC_MAXIMUM;
+ return 1;
+ }
+
+ /* Avoid sprintf, as that infringes on the user's name space.
+ Don't have undefined behavior even if the translation
+ produced a string with the wrong number of "%s"s. */
+ {
+ char *yyp = *yymsg;
+ int yyi = 0;
+ while ((*yyp = *yyformat) != '\0')
+ if (*yyp == '%' && yyformat[1] == 's' && yyi < yycount)
+ {
+ yyp += yytnamerr (yyp, yyarg[yyi++]);
+ yyformat += 2;
+ }
+ else
+ {
+ yyp++;
+ yyformat++;
+ }
+ }
+ return 0;
}
#endif /* YYERROR_VERBOSE */
-
/*-----------------------------------------------.
| Release the memory associated to this symbol. |
@@ -1341,6 +1365,7 @@
}
}
+
/* Prevent warnings from -Wmissing-prototypes. */
#ifdef YYPARSE_PARAM
#if defined __STDC__ || defined __cplusplus
@@ -1367,10 +1392,9 @@
int yynerrs;
-
-/*-------------------------.
-| yyparse or yypush_parse. |
-`-------------------------*/
+/*----------.
+| yyparse. |
+`----------*/
#ifdef YYPARSE_PARAM
#if (defined __STDC__ || defined __C99__FUNC__ \
@@ -1394,8 +1418,6 @@
#endif
#endif
{
-
-
int yystate;
/* Number of tokens to shift before error messages enabled. */
int yyerrstatus;
@@ -1550,7 +1572,7 @@
/* First try to decide what to do without reference to lookahead token. */
yyn = yypact[yystate];
- if (yyn == YYPACT_NINF)
+ if (yypact_value_is_default (yyn))
goto yydefault;
/* Not known => get a lookahead token if don't already have one. */
@@ -1581,8 +1603,8 @@
yyn = yytable[yyn];
if (yyn <= 0)
{
- if (yyn == 0 || yyn == YYTABLE_NINF)
- goto yyerrlab;
+ if (yytable_value_is_error (yyn))
+ goto yyerrlab;
yyn = -yyn;
goto yyreduce;
}
@@ -1637,34 +1659,34 @@
{
case 10:
- { zconf_error("unexpected end statement"); ;}
+ { zconf_error("unexpected end statement"); }
break;
case 11:
- { zconf_error("unknown statement \"%s\"", (yyvsp[(2) - (4)].string)); ;}
+ { zconf_error("unknown statement \"%s\"", (yyvsp[(2) - (4)].string)); }
break;
case 12:
{
zconf_error("unexpected option \"%s\"", kconf_id_strings + (yyvsp[(2) - (4)].id)->name);
-;}
+}
break;
case 13:
- { zconf_error("invalid statement"); ;}
+ { zconf_error("invalid statement"); }
break;
case 28:
- { zconf_error("unknown option \"%s\"", (yyvsp[(1) - (3)].string)); ;}
+ { zconf_error("unknown option \"%s\"", (yyvsp[(1) - (3)].string)); }
break;
case 29:
- { zconf_error("invalid option"); ;}
+ { zconf_error("invalid option"); }
break;
case 30:
@@ -1674,7 +1696,7 @@
sym->flags |= SYMBOL_OPTIONAL;
menu_add_entry(sym);
printd(DEBUG_PARSE, "%s:%d:config %s\n", zconf_curname(), zconf_lineno(), (yyvsp[(2) - (3)].string));
-;}
+}
break;
case 31:
@@ -1682,7 +1704,7 @@
{
menu_end_entry();
printd(DEBUG_PARSE, "%s:%d:endconfig\n", zconf_curname(), zconf_lineno());
-;}
+}
break;
case 32:
@@ -1692,7 +1714,7 @@
sym->flags |= SYMBOL_OPTIONAL;
menu_add_entry(sym);
printd(DEBUG_PARSE, "%s:%d:menuconfig %s\n", zconf_curname(), zconf_lineno(), (yyvsp[(2) - (3)].string));
-;}
+}
break;
case 33:
@@ -1704,7 +1726,7 @@
zconfprint("warning: menuconfig statement without prompt");
menu_end_entry();
printd(DEBUG_PARSE, "%s:%d:endconfig\n", zconf_curname(), zconf_lineno());
-;}
+}
break;
case 41:
@@ -1714,7 +1736,7 @@
printd(DEBUG_PARSE, "%s:%d:type(%u)\n",
zconf_curname(), zconf_lineno(),
(yyvsp[(1) - (3)].id)->stype);
-;}
+}
break;
case 42:
@@ -1722,7 +1744,7 @@
{
menu_add_prompt(P_PROMPT, (yyvsp[(2) - (4)].string), (yyvsp[(3) - (4)].expr));
printd(DEBUG_PARSE, "%s:%d:prompt\n", zconf_curname(), zconf_lineno());
-;}
+}
break;
case 43:
@@ -1734,7 +1756,7 @@
printd(DEBUG_PARSE, "%s:%d:default(%u)\n",
zconf_curname(), zconf_lineno(),
(yyvsp[(1) - (4)].id)->stype);
-;}
+}
break;
case 44:
@@ -1742,7 +1764,7 @@
{
menu_add_symbol(P_SELECT, sym_lookup((yyvsp[(2) - (4)].string), 0), (yyvsp[(3) - (4)].expr));
printd(DEBUG_PARSE, "%s:%d:select\n", zconf_curname(), zconf_lineno());
-;}
+}
break;
case 45:
@@ -1750,7 +1772,7 @@
{
menu_add_expr(P_RANGE, expr_alloc_comp(E_RANGE,(yyvsp[(2) - (5)].symbol), (yyvsp[(3) - (5)].symbol)), (yyvsp[(4) - (5)].expr));
printd(DEBUG_PARSE, "%s:%d:range\n", zconf_curname(), zconf_lineno());
-;}
+}
break;
case 48:
@@ -1762,17 +1784,17 @@
else
zconfprint("warning: ignoring unknown option %s", (yyvsp[(2) - (3)].string));
free((yyvsp[(2) - (3)].string));
-;}
+}
break;
case 49:
- { (yyval.string) = NULL; ;}
+ { (yyval.string) = NULL; }
break;
case 50:
- { (yyval.string) = (yyvsp[(2) - (2)].string); ;}
+ { (yyval.string) = (yyvsp[(2) - (2)].string); }
break;
case 51:
@@ -1783,14 +1805,14 @@
menu_add_entry(sym);
menu_add_expr(P_CHOICE, NULL, NULL);
printd(DEBUG_PARSE, "%s:%d:choice\n", zconf_curname(), zconf_lineno());
-;}
+}
break;
case 52:
{
(yyval.menu) = menu_add_menu();
-;}
+}
break;
case 53:
@@ -1800,7 +1822,7 @@
menu_end_menu();
printd(DEBUG_PARSE, "%s:%d:endchoice\n", zconf_curname(), zconf_lineno());
}
-;}
+}
break;
case 61:
@@ -1808,7 +1830,7 @@
{
menu_add_prompt(P_PROMPT, (yyvsp[(2) - (4)].string), (yyvsp[(3) - (4)].expr));
printd(DEBUG_PARSE, "%s:%d:prompt\n", zconf_curname(), zconf_lineno());
-;}
+}
break;
case 62:
@@ -1821,7 +1843,7 @@
(yyvsp[(1) - (3)].id)->stype);
} else
YYERROR;
-;}
+}
break;
case 63:
@@ -1829,7 +1851,7 @@
{
current_entry->sym->flags |= SYMBOL_OPTIONAL;
printd(DEBUG_PARSE, "%s:%d:optional\n", zconf_curname(), zconf_lineno());
-;}
+}
break;
case 64:
@@ -1841,7 +1863,7 @@
zconf_curname(), zconf_lineno());
} else
YYERROR;
-;}
+}
break;
case 67:
@@ -1851,7 +1873,7 @@
menu_add_entry(NULL);
menu_add_dep((yyvsp[(2) - (3)].expr));
(yyval.menu) = menu_add_menu();
-;}
+}
break;
case 68:
@@ -1861,14 +1883,14 @@
menu_end_menu();
printd(DEBUG_PARSE, "%s:%d:endif\n", zconf_curname(), zconf_lineno());
}
-;}
+}
break;
case 74:
{
menu_add_prompt(P_MENU, (yyvsp[(2) - (3)].string), NULL);
-;}
+}
break;
case 75:
@@ -1877,14 +1899,14 @@
menu_add_entry(NULL);
menu_add_prompt(P_MENU, (yyvsp[(2) - (3)].string), NULL);
printd(DEBUG_PARSE, "%s:%d:menu\n", zconf_curname(), zconf_lineno());
-;}
+}
break;
case 76:
{
(yyval.menu) = menu_add_menu();
-;}
+}
break;
case 77:
@@ -1894,7 +1916,7 @@
menu_end_menu();
printd(DEBUG_PARSE, "%s:%d:endmenu\n", zconf_curname(), zconf_lineno());
}
-;}
+}
break;
case 83:
@@ -1902,7 +1924,7 @@
{
printd(DEBUG_PARSE, "%s:%d:source %s\n", zconf_curname(), zconf_lineno(), (yyvsp[(2) - (3)].string));
zconf_nextfile((yyvsp[(2) - (3)].string));
-;}
+}
break;
case 84:
@@ -1911,14 +1933,14 @@
menu_add_entry(NULL);
menu_add_prompt(P_COMMENT, (yyvsp[(2) - (3)].string), NULL);
printd(DEBUG_PARSE, "%s:%d:comment\n", zconf_curname(), zconf_lineno());
-;}
+}
break;
case 85:
{
menu_end_entry();
-;}
+}
break;
case 86:
@@ -1926,14 +1948,14 @@
{
printd(DEBUG_PARSE, "%s:%d:help\n", zconf_curname(), zconf_lineno());
zconf_starthelp();
-;}
+}
break;
case 87:
{
current_entry->help = (yyvsp[(2) - (2)].string);
-;}
+}
break;
case 92:
@@ -1941,102 +1963,113 @@
{
menu_add_dep((yyvsp[(3) - (4)].expr));
printd(DEBUG_PARSE, "%s:%d:depends on\n", zconf_curname(), zconf_lineno());
-;}
+}
break;
case 96:
{
menu_add_visibility((yyvsp[(2) - (2)].expr));
-;}
+}
break;
case 98:
{
menu_add_prompt(P_PROMPT, (yyvsp[(1) - (2)].string), (yyvsp[(2) - (2)].expr));
-;}
+}
break;
case 101:
- { (yyval.id) = (yyvsp[(1) - (2)].id); ;}
+ { (yyval.id) = (yyvsp[(1) - (2)].id); }
break;
case 102:
- { (yyval.id) = (yyvsp[(1) - (2)].id); ;}
+ { (yyval.id) = (yyvsp[(1) - (2)].id); }
break;
case 103:
- { (yyval.id) = (yyvsp[(1) - (2)].id); ;}
+ { (yyval.id) = (yyvsp[(1) - (2)].id); }
break;
case 106:
- { (yyval.expr) = NULL; ;}
+ { (yyval.expr) = NULL; }
break;
case 107:
- { (yyval.expr) = (yyvsp[(2) - (2)].expr); ;}
+ { (yyval.expr) = (yyvsp[(2) - (2)].expr); }
break;
case 108:
- { (yyval.expr) = expr_alloc_symbol((yyvsp[(1) - (1)].symbol)); ;}
+ { (yyval.expr) = expr_alloc_symbol((yyvsp[(1) - (1)].symbol)); }
break;
case 109:
- { (yyval.expr) = expr_alloc_comp(E_EQUAL, (yyvsp[(1) - (3)].symbol), (yyvsp[(3) - (3)].symbol)); ;}
+ { (yyval.expr) = expr_alloc_comp(E_EQUAL, (yyvsp[(1) - (3)].symbol), (yyvsp[(3) - (3)].symbol)); }
break;
case 110:
- { (yyval.expr) = expr_alloc_comp(E_UNEQUAL, (yyvsp[(1) - (3)].symbol), (yyvsp[(3) - (3)].symbol)); ;}
+ { (yyval.expr) = expr_alloc_comp(E_UNEQUAL, (yyvsp[(1) - (3)].symbol), (yyvsp[(3) - (3)].symbol)); }
break;
case 111:
- { (yyval.expr) = (yyvsp[(2) - (3)].expr); ;}
+ { (yyval.expr) = (yyvsp[(2) - (3)].expr); }
break;
case 112:
- { (yyval.expr) = expr_alloc_one(E_NOT, (yyvsp[(2) - (2)].expr)); ;}
+ { (yyval.expr) = expr_alloc_one(E_NOT, (yyvsp[(2) - (2)].expr)); }
break;
case 113:
- { (yyval.expr) = expr_alloc_two(E_OR, (yyvsp[(1) - (3)].expr), (yyvsp[(3) - (3)].expr)); ;}
+ { (yyval.expr) = expr_alloc_two(E_OR, (yyvsp[(1) - (3)].expr), (yyvsp[(3) - (3)].expr)); }
break;
case 114:
- { (yyval.expr) = expr_alloc_two(E_AND, (yyvsp[(1) - (3)].expr), (yyvsp[(3) - (3)].expr)); ;}
+ { (yyval.expr) = expr_alloc_two(E_AND, (yyvsp[(1) - (3)].expr), (yyvsp[(3) - (3)].expr)); }
break;
case 115:
- { (yyval.symbol) = sym_lookup((yyvsp[(1) - (1)].string), 0); free((yyvsp[(1) - (1)].string)); ;}
+ { (yyval.symbol) = sym_lookup((yyvsp[(1) - (1)].string), 0); free((yyvsp[(1) - (1)].string)); }
break;
case 116:
- { (yyval.symbol) = sym_lookup((yyvsp[(1) - (1)].string), SYMBOL_CONST); free((yyvsp[(1) - (1)].string)); ;}
+ { (yyval.symbol) = sym_lookup((yyvsp[(1) - (1)].string), SYMBOL_CONST); free((yyvsp[(1) - (1)].string)); }
break;
case 117:
- { (yyval.string) = NULL; ;}
+ { (yyval.string) = NULL; }
break;
default: break;
}
+ /* User semantic actions sometimes alter yychar, and that requires
+ that yytoken be updated with the new translation. We take the
+ approach of translating immediately before every use of yytoken.
+ One alternative is translating here after every semantic action,
+ but that translation would be missed if the semantic action invokes
+ YYABORT, YYACCEPT, or YYERROR immediately after altering yychar or
+ if it invokes YYBACKUP. In the case of YYABORT or YYACCEPT, an
+ incorrect destructor might then be invoked immediately. In the
+ case of YYERROR or YYBACKUP, subsequent parser actions might lead
+ to an incorrect destructor call or verbose syntax error message
+ before the lookahead is translated. */
YY_SYMBOL_PRINT ("-> $$ =", yyr1[yyn], &yyval, &yyloc);
YYPOPSTACK (yylen);
@@ -2064,6 +2097,10 @@
| yyerrlab -- here on detecting error |
`------------------------------------*/
yyerrlab:
+ /* Make sure we have latest lookahead translation. See comments at
+ user semantic actions for why this is necessary. */
+ yytoken = yychar == YYEMPTY ? YYEMPTY : YYTRANSLATE (yychar);
+
/* If not already recovering from an error, report this error. */
if (!yyerrstatus)
{
@@ -2071,37 +2108,36 @@
#if ! YYERROR_VERBOSE
yyerror (YY_("syntax error"));
#else
+# define YYSYNTAX_ERROR yysyntax_error (&yymsg_alloc, &yymsg, \
+ yyssp, yytoken)
{
- YYSIZE_T yysize = yysyntax_error (0, yystate, yychar);
- if (yymsg_alloc < yysize && yymsg_alloc < YYSTACK_ALLOC_MAXIMUM)
- {
- YYSIZE_T yyalloc = 2 * yysize;
- if (! (yysize <= yyalloc && yyalloc <= YYSTACK_ALLOC_MAXIMUM))
- yyalloc = YYSTACK_ALLOC_MAXIMUM;
- if (yymsg != yymsgbuf)
- YYSTACK_FREE (yymsg);
- yymsg = (char *) YYSTACK_ALLOC (yyalloc);
- if (yymsg)
- yymsg_alloc = yyalloc;
- else
- {
- yymsg = yymsgbuf;
- yymsg_alloc = sizeof yymsgbuf;
- }
- }
-
- if (0 < yysize && yysize <= yymsg_alloc)
- {
- (void) yysyntax_error (yymsg, yystate, yychar);
- yyerror (yymsg);
- }
- else
- {
- yyerror (YY_("syntax error"));
- if (yysize != 0)
- goto yyexhaustedlab;
- }
+ char const *yymsgp = YY_("syntax error");
+ int yysyntax_error_status;
+ yysyntax_error_status = YYSYNTAX_ERROR;
+ if (yysyntax_error_status == 0)
+ yymsgp = yymsg;
+ else if (yysyntax_error_status == 1)
+ {
+ if (yymsg != yymsgbuf)
+ YYSTACK_FREE (yymsg);
+ yymsg = (char *) YYSTACK_ALLOC (yymsg_alloc);
+ if (!yymsg)
+ {
+ yymsg = yymsgbuf;
+ yymsg_alloc = sizeof yymsgbuf;
+ yysyntax_error_status = 2;
+ }
+ else
+ {
+ yysyntax_error_status = YYSYNTAX_ERROR;
+ yymsgp = yymsg;
+ }
+ }
+ yyerror (yymsgp);
+ if (yysyntax_error_status == 2)
+ goto yyexhaustedlab;
}
+# undef YYSYNTAX_ERROR
#endif
}
@@ -2160,7 +2196,7 @@
for (;;)
{
yyn = yypact[yystate];
- if (yyn != YYPACT_NINF)
+ if (!yypact_value_is_default (yyn))
{
yyn += YYTERROR;
if (0 <= yyn && yyn <= YYLAST && yycheck[yyn] == YYTERROR)
@@ -2219,8 +2255,13 @@
yyreturn:
if (yychar != YYEMPTY)
- yydestruct ("Cleanup: discarding lookahead",
- yytoken, &yylval);
+ {
+ /* Make sure we have latest lookahead translation. See comments at
+ user semantic actions for why this is necessary. */
+ yytoken = YYTRANSLATE (yychar);
+ yydestruct ("Cleanup: discarding lookahead",
+ yytoken, &yylval);
+ }
/* Do not reclaim the symbols of the rule which action triggered
this YYABORT or YYACCEPT. */
YYPOPSTACK (yylen);
@@ -2256,9 +2297,6 @@
sym_init();
_menu_init();
- modules_sym = sym_lookup(NULL, 0);
- modules_sym->type = S_BOOLEAN;
- modules_sym->flags |= SYMBOL_AUTO;
rootmenu.prompt = menu_add_prompt(P_MENU, "Linux Kernel Configuration", NULL);
if (getenv("ZCONF_DEBUG"))
@@ -2266,12 +2304,8 @@
zconfparse();
if (zconfnerrs)
exit(1);
- if (!modules_sym->prop) {
- struct property *prop;
-
- prop = prop_alloc(P_DEFAULT, modules_sym);
- prop->expr = expr_alloc_symbol(sym_lookup("MODULES", 0));
- }
+ if (!modules_sym)
+ modules_sym = sym_find( "n" );
rootmenu.prompt->text = _(rootmenu.prompt->text);
rootmenu.prompt->text = sym_expand_string_value(rootmenu.prompt->text);
diff --git a/scripts/kconfig/zconf.y b/scripts/kconfig/zconf.y
index 864da07..0653886 100644
--- a/scripts/kconfig/zconf.y
+++ b/scripts/kconfig/zconf.y
@@ -493,9 +493,6 @@
sym_init();
_menu_init();
- modules_sym = sym_lookup(NULL, 0);
- modules_sym->type = S_BOOLEAN;
- modules_sym->flags |= SYMBOL_AUTO;
rootmenu.prompt = menu_add_prompt(P_MENU, "Linux Kernel Configuration", NULL);
if (getenv("ZCONF_DEBUG"))
@@ -503,12 +500,8 @@
zconfparse();
if (zconfnerrs)
exit(1);
- if (!modules_sym->prop) {
- struct property *prop;
-
- prop = prop_alloc(P_DEFAULT, modules_sym);
- prop->expr = expr_alloc_symbol(sym_lookup("MODULES", 0));
- }
+ if (!modules_sym)
+ modules_sym = sym_find( "n" );
rootmenu.prompt->text = _(rootmenu.prompt->text);
rootmenu.prompt->text = sym_expand_string_value(rootmenu.prompt->text);
diff --git a/scripts/package/buildtar b/scripts/package/buildtar
index cdd9bb9..aa22f94 100644
--- a/scripts/package/buildtar
+++ b/scripts/package/buildtar
@@ -87,6 +87,27 @@
[ -f "${objtree}/vmlinux.SYS" ] && cp -v -- "${objtree}/vmlinux.SYS" "${tmpdir}/boot/vmlinux-${KERNELRELEASE}.SYS"
[ -f "${objtree}/vmlinux.dsk" ] && cp -v -- "${objtree}/vmlinux.dsk" "${tmpdir}/boot/vmlinux-${KERNELRELEASE}.dsk"
;;
+ mips)
+ if [ -f "${objtree}/arch/mips/boot/compressed/vmlinux.bin" ]; then
+ cp -v -- "${objtree}/arch/mips/boot/compressed/vmlinux.bin" "${tmpdir}/boot/vmlinuz-${KERNELRELEASE}"
+ elif [ -f "${objtree}/arch/mips/boot/compressed/vmlinux.ecoff" ]; then
+ cp -v -- "${objtree}/arch/mips/boot/compressed/vmlinux.ecoff" "${tmpdir}/boot/vmlinuz-${KERNELRELEASE}"
+ elif [ -f "${objtree}/arch/mips/boot/compressed/vmlinux.srec" ]; then
+ cp -v -- "${objtree}/arch/mips/boot/compressed/vmlinux.srec" "${tmpdir}/boot/vmlinuz-${KERNELRELEASE}"
+ elif [ -f "${objtree}/vmlinux.32" ]; then
+ cp -v -- "${objtree}/vmlinux.32" "${tmpdir}/boot/vmlinux-${KERNELRELEASE}"
+ elif [ -f "${objtree}/vmlinux.64" ]; then
+ cp -v -- "${objtree}/vmlinux.64" "${tmpdir}/boot/vmlinux-${KERNELRELEASE}"
+ elif [ -f "${objtree}/arch/mips/boot/vmlinux.bin" ]; then
+ cp -v -- "${objtree}/arch/mips/boot/vmlinux.bin" "${tmpdir}/boot/vmlinux-${KERNELRELEASE}"
+ elif [ -f "${objtree}/arch/mips/boot/vmlinux.ecoff" ]; then
+ cp -v -- "${objtree}/arch/mips/boot/vmlinux.ecoff" "${tmpdir}/boot/vmlinux-${KERNELRELEASE}"
+ elif [ -f "${objtree}/arch/mips/boot/vmlinux.srec" ]; then
+ cp -v -- "${objtree}/arch/mips/boot/vmlinux.srec" "${tmpdir}/boot/vmlinux-${KERNELRELEASE}"
+ elif [ -f "${objtree}/vmlinux" ]; then
+ cp -v -- "${objtree}/vmlinux" "${tmpdir}/boot/vmlinux-${KERNELRELEASE}"
+ fi
+ ;;
*)
[ -f "${KBUILD_IMAGE}" ] && cp -v -- "${KBUILD_IMAGE}" "${tmpdir}/boot/vmlinux-kbuild-${KERNELRELEASE}"
echo "" >&2
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index e54ebd5..6e61a01 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -3428,6 +3428,7 @@
SND_PCI_QUIRK(0x1043, 0x81f2, "ASUS", 0), /* Athlon64 X2 + nvidia */
SND_PCI_QUIRK(0x1043, 0x81f6, "ASUS", 0), /* nvidia */
SND_PCI_QUIRK(0x1043, 0x822d, "ASUS", 0), /* Athlon64 X2 + nvidia MCP55 */
+ SND_PCI_QUIRK(0x1179, 0xfb44, "Toshiba Satellite C870", 0), /* AMD Hudson */
SND_PCI_QUIRK(0x1849, 0x0888, "ASRock", 0), /* Athlon64 X2 + nvidia */
SND_PCI_QUIRK(0xa0a0, 0x0575, "Aopen MZ915-M", 0), /* ICH6 */
{}
diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c
index cccaf9c..b524f89 100644
--- a/sound/pci/hda/patch_cirrus.c
+++ b/sound/pci/hda/patch_cirrus.c
@@ -169,7 +169,7 @@
snd_hda_gen_update_outputs(codec);
- if (spec->gpio_eapd_hp) {
+ if (spec->gpio_eapd_hp || spec->gpio_eapd_speaker) {
spec->gpio_data = spec->gen.hp_jack_present ?
spec->gpio_eapd_hp : spec->gpio_eapd_speaker;
snd_hda_codec_write(codec, 0x01, 0,
@@ -291,10 +291,11 @@
{
struct cs_spec *spec = codec->spec;
- /* init_verb sequence for C0/C1/C2 errata*/
- snd_hda_sequence_write(codec, cs_errata_init_verbs);
-
- snd_hda_sequence_write(codec, cs_coef_init_verbs);
+ if (spec->vendor_nid == CS420X_VENDOR_NID) {
+ /* init_verb sequence for C0/C1/C2 errata*/
+ snd_hda_sequence_write(codec, cs_errata_init_verbs);
+ snd_hda_sequence_write(codec, cs_coef_init_verbs);
+ }
snd_hda_gen_init(codec);
@@ -307,8 +308,10 @@
spec->gpio_data);
}
- init_input_coef(codec);
- init_digital_coef(codec);
+ if (spec->vendor_nid == CS420X_VENDOR_NID) {
+ init_input_coef(codec);
+ init_digital_coef(codec);
+ }
return 0;
}
@@ -552,6 +555,76 @@
}
/*
+ * CS4208 support:
+ * Its layout is no longer compatible with CS4206/CS4207, and the generic
+ * parser seems working fairly well, except for trivial fixups.
+ */
+enum {
+ CS4208_GPIO0,
+};
+
+static const struct hda_model_fixup cs4208_models[] = {
+ { .id = CS4208_GPIO0, .name = "gpio0" },
+ {}
+};
+
+static const struct snd_pci_quirk cs4208_fixup_tbl[] = {
+ /* codec SSID */
+ SND_PCI_QUIRK(0x106b, 0x7100, "MacBookPro 6,1", CS4208_GPIO0),
+ SND_PCI_QUIRK(0x106b, 0x7200, "MacBookPro 6,2", CS4208_GPIO0),
+ {} /* terminator */
+};
+
+static void cs4208_fixup_gpio0(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+ struct cs_spec *spec = codec->spec;
+ spec->gpio_eapd_hp = 0;
+ spec->gpio_eapd_speaker = 1;
+ spec->gpio_mask = spec->gpio_dir =
+ spec->gpio_eapd_hp | spec->gpio_eapd_speaker;
+ }
+}
+
+static const struct hda_fixup cs4208_fixups[] = {
+ [CS4208_GPIO0] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = cs4208_fixup_gpio0,
+ },
+};
+
+static int patch_cs4208(struct hda_codec *codec)
+{
+ struct cs_spec *spec;
+ int err;
+
+ spec = cs_alloc_spec(codec, 0); /* no specific w/a */
+ if (!spec)
+ return -ENOMEM;
+
+ spec->gen.automute_hook = cs_automute;
+
+ snd_hda_pick_fixup(codec, cs4208_models, cs4208_fixup_tbl,
+ cs4208_fixups);
+ snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PRE_PROBE);
+
+ err = cs_parse_auto_config(codec);
+ if (err < 0)
+ goto error;
+
+ codec->patch_ops = cs_patch_ops;
+
+ snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PROBE);
+
+ return 0;
+
+ error:
+ cs_free(codec);
+ return err;
+}
+
+/*
* Cirrus Logic CS4210
*
* 1 DAC => HP(sense) / Speakers,
@@ -991,6 +1064,7 @@
static const struct hda_codec_preset snd_hda_preset_cirrus[] = {
{ .id = 0x10134206, .name = "CS4206", .patch = patch_cs420x },
{ .id = 0x10134207, .name = "CS4207", .patch = patch_cs420x },
+ { .id = 0x10134208, .name = "CS4208", .patch = patch_cs4208 },
{ .id = 0x10134210, .name = "CS4210", .patch = patch_cs4210 },
{ .id = 0x10134213, .name = "CS4213", .patch = patch_cs4213 },
{} /* terminator */
@@ -998,6 +1072,7 @@
MODULE_ALIAS("snd-hda-codec-id:10134206");
MODULE_ALIAS("snd-hda-codec-id:10134207");
+MODULE_ALIAS("snd-hda-codec-id:10134208");
MODULE_ALIAS("snd-hda-codec-id:10134210");
MODULE_ALIAS("snd-hda-codec-id:10134213");
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 9a58893..3d8cd044 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -44,6 +44,8 @@
module_param(static_hdmi_pcm, bool, 0644);
MODULE_PARM_DESC(static_hdmi_pcm, "Don't restrict PCM parameters per ELD info");
+#define is_haswell(codec) ((codec)->vendor_id == 0x80862807)
+
struct hdmi_spec_per_cvt {
hda_nid_t cvt_nid;
int assigned;
@@ -894,6 +896,11 @@
if (!channels)
return;
+ if (is_haswell(codec))
+ snd_hda_codec_write(codec, pin_nid, 0,
+ AC_VERB_SET_AMP_GAIN_MUTE,
+ AMP_OUT_UNMUTE);
+
eld = &per_pin->sink_eld;
if (!eld->monitor_present)
return;
@@ -1033,10 +1040,10 @@
hdmi_non_intrinsic_event(codec, res);
}
-static void haswell_verify_pin_D0(struct hda_codec *codec,
+static void haswell_verify_D0(struct hda_codec *codec,
hda_nid_t cvt_nid, hda_nid_t nid)
{
- int pwr, lamp, ramp;
+ int pwr;
/* For Haswell, the converter 1/2 may keep in D3 state after bootup,
* thus pins could only choose converter 0 for use. Make sure the
@@ -1052,25 +1059,6 @@
pwr = (pwr & AC_PWRST_ACTUAL) >> AC_PWRST_ACTUAL_SHIFT;
snd_printd("Haswell HDMI audio: Power for pin 0x%x is now D%d\n", nid, pwr);
}
-
- lamp = snd_hda_codec_read(codec, nid, 0,
- AC_VERB_GET_AMP_GAIN_MUTE,
- AC_AMP_GET_LEFT | AC_AMP_GET_OUTPUT);
- ramp = snd_hda_codec_read(codec, nid, 0,
- AC_VERB_GET_AMP_GAIN_MUTE,
- AC_AMP_GET_RIGHT | AC_AMP_GET_OUTPUT);
- if (lamp != ramp) {
- snd_hda_codec_write(codec, nid, 0, AC_VERB_SET_AMP_GAIN_MUTE,
- AC_AMP_SET_RIGHT | AC_AMP_SET_OUTPUT | lamp);
-
- lamp = snd_hda_codec_read(codec, nid, 0,
- AC_VERB_GET_AMP_GAIN_MUTE,
- AC_AMP_GET_LEFT | AC_AMP_GET_OUTPUT);
- ramp = snd_hda_codec_read(codec, nid, 0,
- AC_VERB_GET_AMP_GAIN_MUTE,
- AC_AMP_GET_RIGHT | AC_AMP_GET_OUTPUT);
- snd_printd("Haswell HDMI audio: Mute after set on pin 0x%x: [0x%x 0x%x]\n", nid, lamp, ramp);
- }
}
/*
@@ -1087,8 +1075,8 @@
int pinctl;
int new_pinctl = 0;
- if (codec->vendor_id == 0x80862807)
- haswell_verify_pin_D0(codec, cvt_nid, pin_nid);
+ if (is_haswell(codec))
+ haswell_verify_D0(codec, cvt_nid, pin_nid);
if (snd_hda_query_pin_caps(codec, pin_nid) & AC_PINCAP_HBR) {
pinctl = snd_hda_codec_read(codec, pin_nid, 0,
@@ -1227,7 +1215,7 @@
mux_idx);
/* configure unused pins to choose other converters */
- if (codec->vendor_id == 0x80862807)
+ if (is_haswell(codec))
haswell_config_cvts(codec, pin_idx, mux_idx);
snd_hda_spdif_ctls_assign(codec, pin_idx, per_cvt->cvt_nid);
@@ -1358,14 +1346,10 @@
/* Haswell-specific workaround: re-setup when the transcoder is
* changed during the stream playback
*/
- if (codec->vendor_id == 0x80862807 &&
- eld->eld_valid && !old_eld_valid && per_pin->setup) {
- snd_hda_codec_write(codec, pin_nid, 0,
- AC_VERB_SET_AMP_GAIN_MUTE,
- AMP_OUT_UNMUTE);
+ if (is_haswell(codec) &&
+ eld->eld_valid && !old_eld_valid && per_pin->setup)
hdmi_setup_audio_infoframe(codec, per_pin,
per_pin->non_pcm);
- }
}
mutex_unlock(&pin_eld->lock);
@@ -1405,7 +1389,7 @@
if (get_defcfg_connect(config) == AC_JACK_PORT_NONE)
return 0;
- if (codec->vendor_id == 0x80862807)
+ if (is_haswell(codec))
intel_haswell_fixup_connect_list(codec, pin_nid);
pin_idx = spec->num_pins;
@@ -2014,7 +1998,7 @@
codec->spec = spec;
hdmi_array_init(spec, 4);
- if (codec->vendor_id == 0x80862807) {
+ if (is_haswell(codec)) {
intel_haswell_enable_all_pins(codec, true);
intel_haswell_fixup_enable_dp12(codec);
}
@@ -2025,7 +2009,7 @@
return -EINVAL;
}
codec->patch_ops = generic_hdmi_patch_ops;
- if (codec->vendor_id == 0x80862807) {
+ if (is_haswell(codec)) {
codec->patch_ops.set_power_state = haswell_set_power_state;
codec->dp_mst = true;
}
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 9e9378c..bc07d36 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -3443,6 +3443,56 @@
}
}
+/* mute tablet speaker pin (0x14) via dock plugging in addition */
+static void asus_tx300_automute(struct hda_codec *codec)
+{
+ struct alc_spec *spec = codec->spec;
+ snd_hda_gen_update_outputs(codec);
+ if (snd_hda_jack_detect(codec, 0x1b))
+ spec->gen.mute_bits |= (1ULL << 0x14);
+}
+
+static void alc282_fixup_asus_tx300(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ struct alc_spec *spec = codec->spec;
+ /* TX300 needs to set up GPIO2 for the speaker amp */
+ static const struct hda_verb gpio2_verbs[] = {
+ { 0x01, AC_VERB_SET_GPIO_MASK, 0x04 },
+ { 0x01, AC_VERB_SET_GPIO_DIRECTION, 0x04 },
+ { 0x01, AC_VERB_SET_GPIO_DATA, 0x04 },
+ {}
+ };
+ static const struct hda_pintbl dock_pins[] = {
+ { 0x1b, 0x21114000 }, /* dock speaker pin */
+ {}
+ };
+ struct snd_kcontrol *kctl;
+
+ switch (action) {
+ case HDA_FIXUP_ACT_PRE_PROBE:
+ snd_hda_add_verbs(codec, gpio2_verbs);
+ snd_hda_apply_pincfgs(codec, dock_pins);
+ spec->gen.auto_mute_via_amp = 1;
+ spec->gen.automute_hook = asus_tx300_automute;
+ snd_hda_jack_detect_enable_callback(codec, 0x1b,
+ HDA_GEN_HP_EVENT,
+ snd_hda_gen_hp_automute);
+ break;
+ case HDA_FIXUP_ACT_BUILD:
+ /* this is a bit tricky; give more sane names for the main
+ * (tablet) speaker and the dock speaker, respectively
+ */
+ kctl = snd_hda_find_mixer_ctl(codec, "Speaker Playback Switch");
+ if (kctl)
+ strcpy(kctl->id.name, "Dock Speaker Playback Switch");
+ kctl = snd_hda_find_mixer_ctl(codec, "Bass Speaker Playback Switch");
+ if (kctl)
+ strcpy(kctl->id.name, "Speaker Playback Switch");
+ break;
+ }
+}
+
enum {
ALC269_FIXUP_SONY_VAIO,
ALC275_FIXUP_SONY_VAIO_GPIO2,
@@ -3480,6 +3530,7 @@
ALC269_FIXUP_LIMIT_INT_MIC_BOOST,
ALC269VB_FIXUP_ORDISSIMO_EVE2,
ALC283_FIXUP_CHROME_BOOK,
+ ALC282_FIXUP_ASUS_TX300,
};
static const struct hda_fixup alc269_fixups[] = {
@@ -3735,6 +3786,10 @@
.type = HDA_FIXUP_FUNC,
.v.func = alc283_fixup_chromebook,
},
+ [ALC282_FIXUP_ASUS_TX300] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc282_fixup_asus_tx300,
+ },
};
static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -3784,6 +3839,7 @@
SND_PCI_QUIRK(0x103c, 0x1983, "HP Pavilion", ALC269_FIXUP_HP_MUTE_LED_MIC1),
SND_PCI_QUIRK(0x103c, 0x21ed, "HP Falco Chromebook", ALC283_FIXUP_CHROME_BOOK),
SND_PCI_QUIRK_VENDOR(0x103c, "HP", ALC269_FIXUP_HP_MUTE_LED),
+ SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
SND_PCI_QUIRK(0x1043, 0x115d, "Asus 1015E", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_DMIC),
diff --git a/sound/soc/atmel/atmel_ssc_dai.c b/sound/soc/atmel/atmel_ssc_dai.c
index 0ecf356..bb53dea 100644
--- a/sound/soc/atmel/atmel_ssc_dai.c
+++ b/sound/soc/atmel/atmel_ssc_dai.c
@@ -649,7 +649,7 @@
dma_params = ssc_p->dma_params[dir];
ssc_writel(ssc_p->ssc->regs, CR, dma_params->mask->ssc_enable);
- ssc_writel(ssc_p->ssc->regs, IER, dma_params->mask->ssc_error);
+ ssc_writel(ssc_p->ssc->regs, IDR, dma_params->mask->ssc_error);
pr_debug("%s enabled SSC_SR=0x%08x\n",
dir ? "receive" : "transmit",
diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index 15106c0..b33b45d 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -107,7 +107,7 @@
select SND_SOC_WM8782
select SND_SOC_WM8804 if SND_SOC_I2C_AND_SPI
select SND_SOC_WM8900 if I2C
- select SND_SOC_WM8903 if I2C && GENERIC_HARDIRQS
+ select SND_SOC_WM8903 if I2C
select SND_SOC_WM8904 if I2C
select SND_SOC_WM8940 if I2C
select SND_SOC_WM8955 if I2C
diff --git a/sound/soc/codecs/mc13783.c b/sound/soc/codecs/mc13783.c
index 4d3c8fd..ea141e1 100644
--- a/sound/soc/codecs/mc13783.c
+++ b/sound/soc/codecs/mc13783.c
@@ -125,6 +125,10 @@
ret = mc13xxx_reg_write(priv->mc13xxx, reg, value);
+ /* include errata fix for spi audio problems */
+ if (reg == MC13783_AUDIO_CODEC || reg == MC13783_AUDIO_DAC)
+ ret = mc13xxx_reg_write(priv->mc13xxx, reg, value);
+
mc13xxx_unlock(priv->mc13xxx);
return ret;
diff --git a/sound/soc/fsl/Kconfig b/sound/soc/fsl/Kconfig
index 704e246..b7ab71f 100644
--- a/sound/soc/fsl/Kconfig
+++ b/sound/soc/fsl/Kconfig
@@ -198,6 +198,7 @@
select SND_SOC_IMX_PCM_DMA
select SND_SOC_FSL_SPDIF
select SND_SOC_SPDIF
+ select REGMAP_MMIO
help
SoC Audio support for i.MX boards with S/PDIF
Say Y if you want to add support for SoC audio on an i.MX board with
diff --git a/sound/soc/fsl/imx-audmux.c b/sound/soc/fsl/imx-audmux.c
index ab17381..d3bf71a 100644
--- a/sound/soc/fsl/imx-audmux.c
+++ b/sound/soc/fsl/imx-audmux.c
@@ -335,7 +335,8 @@
if (audmux_type == IMX31_AUDMUX)
audmux_debugfs_init();
- imx_audmux_parse_dt_defaults(pdev, pdev->dev.of_node);
+ if (of_id)
+ imx_audmux_parse_dt_defaults(pdev, pdev->dev.of_node);
return 0;
}
diff --git a/sound/soc/kirkwood/kirkwood-i2s.c b/sound/soc/kirkwood/kirkwood-i2s.c
index 7fce340..0f3d73d 100644
--- a/sound/soc/kirkwood/kirkwood-i2s.c
+++ b/sound/soc/kirkwood/kirkwood-i2s.c
@@ -559,7 +559,8 @@
#ifdef CONFIG_OF
static struct of_device_id mvebu_audio_of_match[] = {
- { .compatible = "marvell,mvebu-audio" },
+ { .compatible = "marvell,kirkwood-audio" },
+ { .compatible = "marvell,dove-audio" },
{ }
};
MODULE_DEVICE_TABLE(of, mvebu_audio_of_match);
diff --git a/sound/soc/samsung/Kconfig b/sound/soc/samsung/Kconfig
index 9855dfc..2eea184 100644
--- a/sound/soc/samsung/Kconfig
+++ b/sound/soc/samsung/Kconfig
@@ -63,7 +63,7 @@
config SND_SOC_SAMSUNG_SMDK_WM8994
tristate "SoC I2S Audio support for WM8994 on SMDK"
depends on SND_SOC_SAMSUNG
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
select MFD_WM8994
select SND_SOC_WM8994
select SND_SAMSUNG_I2S
@@ -151,7 +151,7 @@
config SND_SOC_GONI_AQUILA_WM8994
tristate "SoC I2S Audio support for AQUILA/GONI - WM8994"
depends on SND_SOC_SAMSUNG && (MACH_GONI || MACH_AQUILA)
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
select SND_SAMSUNG_I2S
select MFD_WM8994
select SND_SOC_WM8994
@@ -177,7 +177,7 @@
config SND_SOC_SMDK_WM8994_PCM
tristate "SoC PCM Audio support for WM8994 on SMDK"
depends on SND_SOC_SAMSUNG
- depends on I2C=y && GENERIC_HARDIRQS
+ depends on I2C=y
select MFD_WM8994
select SND_SOC_WM8994
select SND_SAMSUNG_PCM
diff --git a/sound/soc/sh/rcar/scu.c b/sound/soc/sh/rcar/scu.c
index 184d9008..2df2e91 100644
--- a/sound/soc/sh/rcar/scu.c
+++ b/sound/soc/sh/rcar/scu.c
@@ -157,9 +157,9 @@
int ret;
/*
- * SCU will be used if it has RSND_SCU_USB_HPBIF flags
+ * SCU will be used if it has RSND_SCU_USE_HPBIF flags
*/
- if (!(flags & RSND_SCU_USB_HPBIF)) {
+ if (!(flags & RSND_SCU_USE_HPBIF)) {
/* it use PIO transter */
dev_dbg(dev, "%s%d is not used\n",
rsnd_mod_name(mod), rsnd_mod_id(mod));
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index c5dc1ad..3a0ff7f 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -394,6 +394,8 @@
LIB_OBJS += $(OUTPUT)tests/perf-time-to-tsc.o
endif
LIB_OBJS += $(OUTPUT)tests/code-reading.o
+LIB_OBJS += $(OUTPUT)tests/sample-parsing.o
+LIB_OBJS += $(OUTPUT)tests/parse-no-sample-id-all.o
BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
@@ -439,7 +441,6 @@
ifneq ($(OUTPUT),)
CFLAGS += -I$(OUTPUT)
endif
-LIB_OBJS += $(OUTPUT)tests/sample-parsing.o
ifdef NO_LIBELF
EXTLIBS := $(filter-out -lelf,$(EXTLIBS))
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index f988d38..5ebd0c3 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -277,6 +277,7 @@
.tool = {
.sample = process_sample_event,
.mmap = perf_event__process_mmap,
+ .mmap2 = perf_event__process_mmap2,
.comm = perf_event__process_comm,
.exit = perf_event__process_exit,
.fork = perf_event__process_fork,
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 9b336fd..423875c99 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -123,6 +123,19 @@
return err;
}
+static int perf_event__repipe_mmap2(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine)
+{
+ int err;
+
+ err = perf_event__process_mmap2(tool, event, sample, machine);
+ perf_event__repipe(tool, event, sample, machine);
+
+ return err;
+}
+
static int perf_event__repipe_fork(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
@@ -339,6 +352,7 @@
if (inject->build_ids || inject->sched_stat) {
inject->tool.mmap = perf_event__repipe_mmap;
+ inject->tool.mmap2 = perf_event__repipe_mmap2;
inject->tool.fork = perf_event__repipe_fork;
inject->tool.tracing_data = perf_event__repipe_tracing_data;
}
@@ -390,6 +404,7 @@
.tool = {
.sample = perf_event__repipe_sample,
.mmap = perf_event__repipe,
+ .mmap2 = perf_event__repipe,
.comm = perf_event__repipe,
.fork = perf_event__repipe,
.exit = perf_event__repipe,
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 47b3540..935d522 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1165,16 +1165,16 @@
struct perf_event_attr *attr = &pos->attr;
/* make sure these *are* set */
- attr->sample_type |= PERF_SAMPLE_TID;
- attr->sample_type |= PERF_SAMPLE_TIME;
- attr->sample_type |= PERF_SAMPLE_CPU;
- attr->sample_type |= PERF_SAMPLE_RAW;
+ perf_evsel__set_sample_bit(pos, TID);
+ perf_evsel__set_sample_bit(pos, TIME);
+ perf_evsel__set_sample_bit(pos, CPU);
+ perf_evsel__set_sample_bit(pos, RAW);
/* make sure these are *not*; want as small a sample as possible */
- attr->sample_type &= ~PERF_SAMPLE_PERIOD;
- attr->sample_type &= ~PERF_SAMPLE_IP;
- attr->sample_type &= ~PERF_SAMPLE_CALLCHAIN;
- attr->sample_type &= ~PERF_SAMPLE_ADDR;
- attr->sample_type &= ~PERF_SAMPLE_READ;
+ perf_evsel__reset_sample_bit(pos, PERIOD);
+ perf_evsel__reset_sample_bit(pos, IP);
+ perf_evsel__reset_sample_bit(pos, CALLCHAIN);
+ perf_evsel__reset_sample_bit(pos, ADDR);
+ perf_evsel__reset_sample_bit(pos, READ);
attr->mmap = 0;
attr->comm = 0;
attr->task = 0;
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 791b432..253133a 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -190,6 +190,7 @@
.tool = {
.sample = process_sample_event,
.mmap = perf_event__process_mmap,
+ .mmap2 = perf_event__process_mmap2,
.comm = perf_event__process_comm,
.lost = perf_event__process_lost,
.fork = perf_event__process_fork,
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 9725aa3..8e50d8d 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -744,6 +744,7 @@
.tool = {
.sample = process_sample_event,
.mmap = perf_event__process_mmap,
+ .mmap2 = perf_event__process_mmap2,
.comm = perf_event__process_comm,
.exit = perf_event__process_exit,
.fork = perf_event__process_fork,
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 93a34ce..7f31a3d 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -542,6 +542,7 @@
static struct perf_tool perf_script = {
.sample = process_sample_event,
.mmap = perf_event__process_mmap,
+ .mmap2 = perf_event__process_mmap2,
.comm = perf_event__process_comm,
.exit = perf_event__process_exit,
.fork = perf_event__process_fork,
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index b6f0725..f5aa637 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -100,7 +100,9 @@
P_MMAP_FLAG(SHARED);
P_MMAP_FLAG(PRIVATE);
+#ifdef MAP_32BIT
P_MMAP_FLAG(32BIT);
+#endif
P_MMAP_FLAG(ANONYMOUS);
P_MMAP_FLAG(DENYWRITE);
P_MMAP_FLAG(EXECUTABLE);
@@ -994,6 +996,9 @@
handler = evsel->handler.func;
handler(trace, evsel, &sample);
+
+ if (done)
+ goto out_unmap_evlist;
}
}
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 8bbeba3..1e67437 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -112,6 +112,10 @@
.func = test__keep_tracking,
},
{
+ .desc = "Test parsing with no sample_id_all bit set",
+ .func = test__parse_no_sample_id_all,
+ },
+ {
.func = NULL,
},
};
diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c
new file mode 100644
index 0000000..e117b6c
--- /dev/null
+++ b/tools/perf/tests/parse-no-sample-id-all.c
@@ -0,0 +1,108 @@
+#include <sys/types.h>
+#include <stddef.h>
+
+#include "tests.h"
+
+#include "event.h"
+#include "evlist.h"
+#include "header.h"
+#include "util.h"
+
+static int process_event(struct perf_evlist **pevlist, union perf_event *event)
+{
+ struct perf_sample sample;
+
+ if (event->header.type == PERF_RECORD_HEADER_ATTR) {
+ if (perf_event__process_attr(NULL, event, pevlist)) {
+ pr_debug("perf_event__process_attr failed\n");
+ return -1;
+ }
+ return 0;
+ }
+
+ if (event->header.type >= PERF_RECORD_USER_TYPE_START)
+ return -1;
+
+ if (!*pevlist)
+ return -1;
+
+ if (perf_evlist__parse_sample(*pevlist, event, &sample)) {
+ pr_debug("perf_evlist__parse_sample failed\n");
+ return -1;
+ }
+
+ return 0;
+}
+
+static int process_events(union perf_event **events, size_t count)
+{
+ struct perf_evlist *evlist = NULL;
+ int err = 0;
+ size_t i;
+
+ for (i = 0; i < count && !err; i++)
+ err = process_event(&evlist, events[i]);
+
+ if (evlist)
+ perf_evlist__delete(evlist);
+
+ return err;
+}
+
+struct test_attr_event {
+ struct attr_event attr;
+ u64 id;
+};
+
+/**
+ * test__parse_no_sample_id_all - test parsing with no sample_id_all bit set.
+ *
+ * This function tests parsing data produced on kernel's that do not support the
+ * sample_id_all bit. Without the sample_id_all bit, non-sample events (such as
+ * mmap events) do not have an id sample appended, and consequently logic
+ * designed to determine the id will not work. That case happens when there is
+ * more than one selected event, so this test processes three events: 2
+ * attributes representing the selected events and one mmap event.
+ *
+ * Return: %0 on success, %-1 if the test fails.
+ */
+int test__parse_no_sample_id_all(void)
+{
+ int err;
+
+ struct test_attr_event event1 = {
+ .attr = {
+ .header = {
+ .type = PERF_RECORD_HEADER_ATTR,
+ .size = sizeof(struct test_attr_event),
+ },
+ },
+ .id = 1,
+ };
+ struct test_attr_event event2 = {
+ .attr = {
+ .header = {
+ .type = PERF_RECORD_HEADER_ATTR,
+ .size = sizeof(struct test_attr_event),
+ },
+ },
+ .id = 2,
+ };
+ struct mmap_event event3 = {
+ .header = {
+ .type = PERF_RECORD_MMAP,
+ .size = sizeof(struct mmap_event),
+ },
+ };
+ union perf_event *events[] = {
+ (union perf_event *)&event1,
+ (union perf_event *)&event2,
+ (union perf_event *)&event3,
+ };
+
+ err = process_events(events, ARRAY_SIZE(events));
+ if (err)
+ return -1;
+
+ return 0;
+}
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 72d8881..b8a7056 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -50,7 +50,7 @@
struct perf_sample sample;
const char *cmd = "sleep";
const char *argv[] = { cmd, "1", NULL, };
- char *bname;
+ char *bname, *mmap_filename;
u64 prev_time = 0;
bool found_cmd_mmap = false,
found_libc_mmap = false,
@@ -212,6 +212,7 @@
if ((type == PERF_RECORD_COMM ||
type == PERF_RECORD_MMAP ||
+ type == PERF_RECORD_MMAP2 ||
type == PERF_RECORD_FORK ||
type == PERF_RECORD_EXIT) &&
(pid_t)event->comm.pid != evlist->workload.pid) {
@@ -220,7 +221,8 @@
}
if ((type == PERF_RECORD_COMM ||
- type == PERF_RECORD_MMAP) &&
+ type == PERF_RECORD_MMAP ||
+ type == PERF_RECORD_MMAP2) &&
event->comm.pid != event->comm.tid) {
pr_debug("%s with different pid/tid!\n", name);
++errs;
@@ -236,7 +238,12 @@
case PERF_RECORD_EXIT:
goto found_exit;
case PERF_RECORD_MMAP:
- bname = strrchr(event->mmap.filename, '/');
+ mmap_filename = event->mmap.filename;
+ goto check_bname;
+ case PERF_RECORD_MMAP2:
+ mmap_filename = event->mmap2.filename;
+ check_bname:
+ bname = strrchr(mmap_filename, '/');
if (bname != NULL) {
if (!found_cmd_mmap)
found_cmd_mmap = !strcmp(bname + 1, cmd);
@@ -245,7 +252,7 @@
if (!found_ld_mmap)
found_ld_mmap = !strncmp(bname + 1, "ld", 2);
} else if (!found_vdso_mmap)
- found_vdso_mmap = !strcmp(event->mmap.filename, "[vdso]");
+ found_vdso_mmap = !strcmp(mmap_filename, "[vdso]");
break;
case PERF_RECORD_SAMPLE:
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index c048b58..e0ac713 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -39,5 +39,6 @@
int test__code_reading(void);
int test__sample_parsing(void);
int test__keep_tracking(void);
+int test__parse_no_sample_id_all(void);
#endif /* TESTS_H */
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 5b4fb33..194e2f4 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -350,9 +350,9 @@
}
static int hist_entry__fprintf(struct hist_entry *he, size_t size,
- struct hists *hists, FILE *fp)
+ struct hists *hists,
+ char *bf, size_t bfsz, FILE *fp)
{
- char bf[512];
int ret;
struct perf_hpp hpp = {
.buf = bf,
@@ -360,8 +360,8 @@
};
bool color = !symbol_conf.field_sep;
- if (size == 0 || size > sizeof(bf))
- size = hpp.size = sizeof(bf);
+ if (size == 0 || size > bfsz)
+ size = hpp.size = bfsz;
ret = hist_entry__period_snprintf(&hpp, he, color);
hist_entry__sort_snprintf(he, bf + ret, size - ret, hists);
@@ -392,6 +392,8 @@
.ptr = hists_to_evsel(hists),
};
bool first = true;
+ size_t linesz;
+ char *line = NULL;
init_rem_hits();
@@ -479,6 +481,13 @@
goto out;
print_entries:
+ linesz = hists__sort_list_width(hists) + 3 + 1;
+ line = malloc(linesz);
+ if (line == NULL) {
+ ret = -1;
+ goto out;
+ }
+
for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
float percent = h->stat.period * 100.0 /
@@ -490,10 +499,10 @@
if (percent < min_pcnt)
continue;
- ret += hist_entry__fprintf(h, max_cols, hists, fp);
+ ret += hist_entry__fprintf(h, max_cols, hists, line, linesz, fp);
if (max_rows && ++nr_rows >= max_rows)
- goto out;
+ break;
if (h->ms.map == NULL && verbose > 1) {
__map_groups__fprintf_maps(&h->thread->mg,
@@ -501,6 +510,8 @@
fprintf(fp, "%.10s end\n", graph_dotted_line);
}
}
+
+ free(line);
out:
free(rem_sq_bracket);
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index fb58409..7ded71d 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -67,6 +67,7 @@
struct perf_tool build_id__mark_dso_hit_ops = {
.sample = build_id__mark_dso_hit,
.mmap = perf_event__process_mmap,
+ .mmap2 = perf_event__process_mmap2,
.fork = perf_event__process_fork,
.exit = perf_event__exit_del_thread,
.attr = perf_event__process_attr,
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 8d51f21..9b393e7 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -11,6 +11,7 @@
static const char *perf_event__names[] = {
[0] = "TOTAL",
[PERF_RECORD_MMAP] = "MMAP",
+ [PERF_RECORD_MMAP2] = "MMAP2",
[PERF_RECORD_LOST] = "LOST",
[PERF_RECORD_COMM] = "COMM",
[PERF_RECORD_EXIT] = "EXIT",
@@ -186,7 +187,7 @@
return -1;
}
- event->header.type = PERF_RECORD_MMAP;
+ event->header.type = PERF_RECORD_MMAP2;
/*
* Just like the kernel, see __perf_event_mmap in kernel/perf_event.c
*/
@@ -197,7 +198,9 @@
char prot[5];
char execname[PATH_MAX];
char anonstr[] = "//anon";
+ unsigned int ino;
size_t size;
+ ssize_t n;
if (fgets(bf, sizeof(bf), fp) == NULL)
break;
@@ -206,9 +209,16 @@
strcpy(execname, "");
/* 00400000-0040c000 r-xp 00000000 fd:01 41038 /bin/cat */
- sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %*x:%*x %*u %s\n",
- &event->mmap.start, &event->mmap.len, prot,
- &event->mmap.pgoff, execname);
+ n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %s\n",
+ &event->mmap2.start, &event->mmap2.len, prot,
+ &event->mmap2.pgoff, &event->mmap2.maj,
+ &event->mmap2.min,
+ &ino, execname);
+
+ event->mmap2.ino = (u64)ino;
+
+ if (n != 8)
+ continue;
if (prot[2] != 'x')
continue;
@@ -217,15 +227,15 @@
strcpy(execname, anonstr);
size = strlen(execname) + 1;
- memcpy(event->mmap.filename, execname, size);
+ memcpy(event->mmap2.filename, execname, size);
size = PERF_ALIGN(size, sizeof(u64));
- event->mmap.len -= event->mmap.start;
- event->mmap.header.size = (sizeof(event->mmap) -
- (sizeof(event->mmap.filename) - size));
- memset(event->mmap.filename + size, 0, machine->id_hdr_size);
- event->mmap.header.size += machine->id_hdr_size;
- event->mmap.pid = tgid;
- event->mmap.tid = pid;
+ event->mmap2.len -= event->mmap.start;
+ event->mmap2.header.size = (sizeof(event->mmap2) -
+ (sizeof(event->mmap2.filename) - size));
+ memset(event->mmap2.filename + size, 0, machine->id_hdr_size);
+ event->mmap2.header.size += machine->id_hdr_size;
+ event->mmap2.pid = tgid;
+ event->mmap2.tid = pid;
if (process(tool, event, &synth_sample, machine) != 0) {
rc = -1;
@@ -527,6 +537,17 @@
event->mmap.len, event->mmap.pgoff, event->mmap.filename);
}
+size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp)
+{
+ return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64
+ " %02x:%02x %"PRIu64" %"PRIu64"]: %s\n",
+ event->mmap2.pid, event->mmap2.tid, event->mmap2.start,
+ event->mmap2.len, event->mmap2.pgoff, event->mmap2.maj,
+ event->mmap2.min, event->mmap2.ino,
+ event->mmap2.ino_generation,
+ event->mmap2.filename);
+}
+
int perf_event__process_mmap(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
@@ -535,6 +556,14 @@
return machine__process_mmap_event(machine, event);
}
+int perf_event__process_mmap2(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_sample *sample __maybe_unused,
+ struct machine *machine)
+{
+ return machine__process_mmap2_event(machine, event);
+}
+
size_t perf_event__fprintf_task(union perf_event *event, FILE *fp)
{
return fprintf(fp, "(%d:%d):(%d:%d)\n",
@@ -574,6 +603,9 @@
case PERF_RECORD_MMAP:
ret += perf_event__fprintf_mmap(event, fp);
break;
+ case PERF_RECORD_MMAP2:
+ ret += perf_event__fprintf_mmap2(event, fp);
+ break;
default:
ret += fprintf(fp, "\n");
}
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 93130d8..c67ecc4 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -17,6 +17,19 @@
char filename[PATH_MAX];
};
+struct mmap2_event {
+ struct perf_event_header header;
+ u32 pid, tid;
+ u64 start;
+ u64 len;
+ u64 pgoff;
+ u32 maj;
+ u32 min;
+ u64 ino;
+ u64 ino_generation;
+ char filename[PATH_MAX];
+};
+
struct comm_event {
struct perf_event_header header;
u32 pid, tid;
@@ -159,6 +172,7 @@
union perf_event {
struct perf_event_header header;
struct mmap_event mmap;
+ struct mmap2_event mmap2;
struct comm_event comm;
struct fork_event fork;
struct lost_event lost;
@@ -208,6 +222,10 @@
union perf_event *event,
struct perf_sample *sample,
struct machine *machine);
+int perf_event__process_mmap2(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine);
int perf_event__process_fork(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
@@ -238,6 +256,7 @@
size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_task(union perf_event *event, FILE *fp);
size_t perf_event__fprintf(union perf_event *event, FILE *fp);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index b8727ae..f9f77be 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -64,6 +64,16 @@
evlist->is_pos = first->is_pos;
}
+static void perf_evlist__update_id_pos(struct perf_evlist *evlist)
+{
+ struct perf_evsel *evsel;
+
+ list_for_each_entry(evsel, &evlist->entries, node)
+ perf_evsel__calc_id_pos(evsel);
+
+ perf_evlist__set_id_pos(evlist);
+}
+
static void perf_evlist__purge(struct perf_evlist *evlist)
{
struct perf_evsel *pos, *n;
@@ -446,20 +456,25 @@
static struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
union perf_event *event)
{
+ struct perf_evsel *first = perf_evlist__first(evlist);
struct hlist_head *head;
struct perf_sample_id *sid;
int hash;
u64 id;
if (evlist->nr_entries == 1)
- return perf_evlist__first(evlist);
+ return first;
+
+ if (!first->attr.sample_id_all &&
+ event->header.type != PERF_RECORD_SAMPLE)
+ return first;
if (perf_evlist__event2id(evlist, event, &id))
return NULL;
/* Synthesized events have an id of zero */
if (!id)
- return perf_evlist__first(evlist);
+ return first;
hash = hash_64(id, PERF_EVLIST__HLIST_BITS);
head = &evlist->heads[hash];
@@ -915,6 +930,8 @@
struct perf_evsel *evsel;
int err;
+ perf_evlist__update_id_pos(evlist);
+
list_for_each_entry(evsel, &evlist->entries, node) {
err = perf_evsel__open(evsel, evlist->cpus, evlist->threads);
if (err < 0)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 3612183..0ce9feb 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -27,6 +27,7 @@
static struct {
bool sample_id_all;
bool exclude_guest;
+ bool mmap2;
} perf_missing_features;
#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
@@ -676,8 +677,9 @@
if (opts->sample_weight)
attr->sample_type |= PERF_SAMPLE_WEIGHT;
- attr->mmap = track;
- attr->comm = track;
+ attr->mmap = track;
+ attr->mmap2 = track && !perf_missing_features.mmap2;
+ attr->comm = track;
/*
* XXX see the function comment above
@@ -1016,6 +1018,8 @@
}
fallback_missing_features:
+ if (perf_missing_features.mmap2)
+ evsel->attr.mmap2 = 0;
if (perf_missing_features.exclude_guest)
evsel->attr.exclude_guest = evsel->attr.exclude_host = 0;
retry_sample_id:
@@ -1080,8 +1084,11 @@
if (err != -EINVAL || cpu > 0 || thread > 0)
goto out_close;
- if (!perf_missing_features.exclude_guest &&
- (evsel->attr.exclude_guest || evsel->attr.exclude_host)) {
+ if (!perf_missing_features.mmap2 && evsel->attr.mmap2) {
+ perf_missing_features.mmap2 = true;
+ goto fallback_missing_features;
+ } else if (!perf_missing_features.exclude_guest &&
+ (evsel->attr.exclude_guest || evsel->attr.exclude_host)) {
perf_missing_features.exclude_guest = true;
goto fallback_missing_features;
} else if (!perf_missing_features.sample_id_all) {
@@ -1925,6 +1932,7 @@
if_print(exclude_hv);
if_print(exclude_idle);
if_print(mmap);
+ if_print(mmap2);
if_print(comm);
if_print(freq);
if_print(inherit_stat);
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index a33197a..26441d0 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1351,6 +1351,9 @@
fprintf(fp, ", precise_ip = %d", evsel->attr.precise_ip);
+ fprintf(fp, ", attr_mmap2 = %d", evsel->attr.mmap2);
+ fprintf(fp, ", attr_mmap = %d", evsel->attr.mmap);
+ fprintf(fp, ", attr_mmap_data = %d", evsel->attr.mmap_data);
if (evsel->ids) {
fprintf(fp, ", id = {");
for (j = 0, id = evsel->id; j < evsel->ids; j++, id++) {
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 1dca61f..933d14f 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -997,6 +997,54 @@
return -1;
}
+int machine__process_mmap2_event(struct machine *machine,
+ union perf_event *event)
+{
+ u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+ struct thread *thread;
+ struct map *map;
+ enum map_type type;
+ int ret = 0;
+
+ if (dump_trace)
+ perf_event__fprintf_mmap2(event, stdout);
+
+ if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL ||
+ cpumode == PERF_RECORD_MISC_KERNEL) {
+ ret = machine__process_kernel_mmap_event(machine, event);
+ if (ret < 0)
+ goto out_problem;
+ return 0;
+ }
+
+ thread = machine__findnew_thread(machine, event->mmap2.pid,
+ event->mmap2.pid);
+ if (thread == NULL)
+ goto out_problem;
+
+ if (event->header.misc & PERF_RECORD_MISC_MMAP_DATA)
+ type = MAP__VARIABLE;
+ else
+ type = MAP__FUNCTION;
+
+ map = map__new(&machine->user_dsos, event->mmap2.start,
+ event->mmap2.len, event->mmap2.pgoff,
+ event->mmap2.pid, event->mmap2.maj,
+ event->mmap2.min, event->mmap2.ino,
+ event->mmap2.ino_generation,
+ event->mmap2.filename, type);
+
+ if (map == NULL)
+ goto out_problem;
+
+ thread__insert_map(thread, map);
+ return 0;
+
+out_problem:
+ dump_printf("problem processing PERF_RECORD_MMAP2, skipping event.\n");
+ return 0;
+}
+
int machine__process_mmap_event(struct machine *machine, union perf_event *event)
{
u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
@@ -1028,7 +1076,8 @@
map = map__new(&machine->user_dsos, event->mmap.start,
event->mmap.len, event->mmap.pgoff,
- event->mmap.pid, event->mmap.filename,
+ event->mmap.pid, 0, 0, 0, 0,
+ event->mmap.filename,
type);
if (map == NULL)
@@ -1101,6 +1150,8 @@
ret = machine__process_comm_event(machine, event); break;
case PERF_RECORD_MMAP:
ret = machine__process_mmap_event(machine, event); break;
+ case PERF_RECORD_MMAP2:
+ ret = machine__process_mmap2_event(machine, event); break;
case PERF_RECORD_FORK:
ret = machine__process_fork_event(machine, event); break;
case PERF_RECORD_EXIT:
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 0df925b..58a6be1 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -45,6 +45,7 @@
int machine__process_fork_event(struct machine *machine, union perf_event *event);
int machine__process_lost_event(struct machine *machine, union perf_event *event);
int machine__process_mmap_event(struct machine *machine, union perf_event *event);
+int machine__process_mmap2_event(struct machine *machine, union perf_event *event);
int machine__process_event(struct machine *machine, union perf_event *event);
typedef void (*machine__process_t)(struct machine *machine, void *data);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 9e8304c..4f6680d 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -48,7 +48,8 @@
}
struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
- u64 pgoff, u32 pid, char *filename,
+ u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino,
+ u64 ino_gen, char *filename,
enum map_type type)
{
struct map *map = malloc(sizeof(*map));
@@ -62,6 +63,11 @@
vdso = is_vdso_map(filename);
no_dso = is_no_dso_memory(filename);
+ map->maj = d_maj;
+ map->min = d_min;
+ map->ino = ino;
+ map->ino_generation = ino_gen;
+
if (anon) {
snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", pid);
filename = newfilename;
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 2cc93cb..4886ca2 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -36,6 +36,9 @@
bool erange_warned;
u32 priv;
u64 pgoff;
+ u32 maj, min; /* only valid for MMAP2 record */
+ u64 ino; /* only valid for MMAP2 record */
+ u64 ino_generation;/* only valid for MMAP2 record */
/* ip -> dso rip */
u64 (*map_ip)(struct map *, u64);
@@ -88,8 +91,9 @@
void map__init(struct map *map, enum map_type type,
u64 start, u64 end, u64 pgoff, struct dso *dso);
struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
- u64 pgoff, u32 pid, char *filename,
- enum map_type type);
+ u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino,
+ u64 ino_gen,
+ char *filename, enum map_type type);
struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
void map__delete(struct map *map);
struct map *map__clone(struct map *map);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 1fc0c62..51f5edf 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -351,6 +351,25 @@
}
}
+static void perf_event__mmap2_swap(union perf_event *event,
+ bool sample_id_all)
+{
+ event->mmap2.pid = bswap_32(event->mmap2.pid);
+ event->mmap2.tid = bswap_32(event->mmap2.tid);
+ event->mmap2.start = bswap_64(event->mmap2.start);
+ event->mmap2.len = bswap_64(event->mmap2.len);
+ event->mmap2.pgoff = bswap_64(event->mmap2.pgoff);
+ event->mmap2.maj = bswap_32(event->mmap2.maj);
+ event->mmap2.min = bswap_32(event->mmap2.min);
+ event->mmap2.ino = bswap_64(event->mmap2.ino);
+
+ if (sample_id_all) {
+ void *data = &event->mmap2.filename;
+
+ data += PERF_ALIGN(strlen(data) + 1, sizeof(u64));
+ swap_sample_id_all(event, data);
+ }
+}
static void perf_event__task_swap(union perf_event *event, bool sample_id_all)
{
event->fork.pid = bswap_32(event->fork.pid);
@@ -455,6 +474,7 @@
static perf_event__swap_op perf_event__swap_ops[] = {
[PERF_RECORD_MMAP] = perf_event__mmap_swap,
+ [PERF_RECORD_MMAP2] = perf_event__mmap2_swap,
[PERF_RECORD_COMM] = perf_event__comm_swap,
[PERF_RECORD_FORK] = perf_event__task_swap,
[PERF_RECORD_EXIT] = perf_event__task_swap,
@@ -504,6 +524,7 @@
u64 limit = os->next_flush;
u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL;
unsigned idx = 0, progress_next = os->nr_samples / 16;
+ bool show_progress = limit == ULLONG_MAX;
int ret;
if (!tool->ordered_samples || !limit)
@@ -526,7 +547,7 @@
os->last_flush = iter->timestamp;
list_del(&iter->list);
list_add(&iter->list, &os->sample_cache);
- if (++idx >= progress_next) {
+ if (show_progress && (++idx >= progress_next)) {
progress_next += os->nr_samples / 16;
ui_progress__update(idx, os->nr_samples,
"Processing time ordered events...");
@@ -850,7 +871,8 @@
(cpumode == PERF_RECORD_MISC_GUEST_USER))) {
u32 pid;
- if (event->header.type == PERF_RECORD_MMAP)
+ if (event->header.type == PERF_RECORD_MMAP
+ || event->header.type == PERF_RECORD_MMAP2)
pid = event->mmap.pid;
else
pid = sample->pid;
@@ -977,6 +999,8 @@
sample, evsel, machine);
case PERF_RECORD_MMAP:
return tool->mmap(tool, event, sample, machine);
+ case PERF_RECORD_MMAP2:
+ return tool->mmap2(tool, event, sample, machine);
case PERF_RECORD_COMM:
return tool->comm(tool, event, sample, machine);
case PERF_RECORD_FORK:
@@ -1619,52 +1643,26 @@
const struct perf_evsel_str_handler *assocs,
size_t nr_assocs)
{
- struct perf_evlist *evlist = session->evlist;
- struct event_format *format;
struct perf_evsel *evsel;
- char *tracepoint, *name;
size_t i;
int err;
for (i = 0; i < nr_assocs; i++) {
- err = -ENOMEM;
- tracepoint = strdup(assocs[i].name);
- if (tracepoint == NULL)
- goto out;
-
- err = -ENOENT;
- name = strchr(tracepoint, ':');
- if (name == NULL)
- goto out_free;
-
- *name++ = '\0';
- format = pevent_find_event_by_name(session->pevent,
- tracepoint, name);
- if (format == NULL) {
- /*
- * Adding a handler for an event not in the session,
- * just ignore it.
- */
- goto next;
- }
-
- evsel = perf_evlist__find_tracepoint_by_id(evlist, format->id);
+ /*
+ * Adding a handler for an event not in the session,
+ * just ignore it.
+ */
+ evsel = perf_evlist__find_tracepoint_by_name(session->evlist, assocs[i].name);
if (evsel == NULL)
- goto next;
+ continue;
err = -EEXIST;
if (evsel->handler.func != NULL)
- goto out_free;
+ goto out;
evsel->handler.func = assocs[i].handler;
-next:
- free(tracepoint);
}
err = 0;
out:
return err;
-
-out_free:
- free(tracepoint);
- goto out;
}
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 62b16b6..4385816 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -29,6 +29,7 @@
event_sample sample,
read;
event_op mmap,
+ mmap2,
comm,
fork,
exit,
