Merge branch 'x86/urgent' into core/percpu
Conflicts:
arch/x86/kernel/acpi/boot.c
diff --git a/.mailmap b/.mailmap
index 4e83e7b..a62e6a8 100644
--- a/.mailmap
+++ b/.mailmap
@@ -92,6 +92,7 @@
Rui Saraiva <rmps@joel.ist.utl.pt>
Sachin P Sant <ssant@in.ibm.com>
Sam Ravnborg <sam@mars.ravnborg.org>
+Sascha Hauer <s.hauer@pengutronix.de>
S.Çağlar Onur <caglar@pardus.org.tr>
Simon Kelley <simon@thekelleys.org.uk>
Stéphane Witzmann <stephane.witzmann@ubpmes.univ-bpclermont.fr>
@@ -100,6 +101,7 @@
Thomas Graf <tgraf@suug.ch>
Tony Luck <tony.luck@intel.com>
Tsuneo Yoshioka <Tsuneo.Yoshioka@f-secure.com>
-Uwe Kleine-König <Uwe.Kleine-Koenig@digi.com>
Uwe Kleine-König <ukleinek@informatik.uni-freiburg.de>
+Uwe Kleine-König <ukl@pengutronix.de>
+Uwe Kleine-König <Uwe.Kleine-Koenig@digi.com>
Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
diff --git a/Documentation/cpu-freq/user-guide.txt b/Documentation/cpu-freq/user-guide.txt
index e3443dd..917918f 100644
--- a/Documentation/cpu-freq/user-guide.txt
+++ b/Documentation/cpu-freq/user-guide.txt
@@ -195,19 +195,3 @@
you can change the speed of the CPU,
but only within the limits of
scaling_min_freq and scaling_max_freq.
-
-
-3.2 Deprecated Interfaces
--------------------------
-
-Depending on your kernel configuration, you might find the following
-cpufreq-related files:
-/proc/cpufreq
-/proc/sys/cpu/*/speed
-/proc/sys/cpu/*/speed-min
-/proc/sys/cpu/*/speed-max
-
-These are files for deprecated interfaces to cpufreq, which offer far
-less functionality. Because of this, these interfaces aren't described
-here.
-
diff --git a/Documentation/cputopology.txt b/Documentation/cputopology.txt
index 45932ec..b41f3e5 100644
--- a/Documentation/cputopology.txt
+++ b/Documentation/cputopology.txt
@@ -18,11 +18,11 @@
these macros in include/asm-XXX/topology.h:
#define topology_physical_package_id(cpu)
#define topology_core_id(cpu)
-#define topology_thread_siblings(cpu)
-#define topology_core_siblings(cpu)
+#define topology_thread_cpumask(cpu)
+#define topology_core_cpumask(cpu)
The type of **_id is int.
-The type of siblings is cpumask_t.
+The type of siblings is (const) struct cpumask *.
To be consistent on all architectures, include/linux/topology.h
provides default definitions for any of the above macros that are
diff --git a/Documentation/filesystems/sysfs-pci.txt b/Documentation/filesystems/sysfs-pci.txt
index 68ef488..9f8740c 100644
--- a/Documentation/filesystems/sysfs-pci.txt
+++ b/Documentation/filesystems/sysfs-pci.txt
@@ -9,6 +9,7 @@
| |-- class
| |-- config
| |-- device
+ | |-- enable
| |-- irq
| |-- local_cpus
| |-- resource
@@ -32,6 +33,7 @@
class PCI class (ascii, ro)
config PCI config space (binary, rw)
device PCI device (ascii, ro)
+ enable Whether the device is enabled (ascii, rw)
irq IRQ number (ascii, ro)
local_cpus nearby CPU mask (cpumask, ro)
resource PCI resource host addresses (ascii, ro)
@@ -57,10 +59,19 @@
don't support mmapping of certain resources, so be sure to check the return
value from any attempted mmap.
+The 'enable' file provides a counter that indicates how many times the device
+has been enabled. If the 'enable' file currently returns '4', and a '1' is
+echoed into it, it will then return '5'. Echoing a '0' into it will decrease
+the count. Even when it returns to 0, though, some of the initialisation
+may not be reversed.
+
The 'rom' file is special in that it provides read-only access to the device's
ROM file, if available. It's disabled by default, however, so applications
should write the string "1" to the file to enable it before attempting a read
-call, and disable it following the access by writing "0" to the file.
+call, and disable it following the access by writing "0" to the file. Note
+that the device must be enabled for a rom read to return data succesfully.
+In the event a driver is not bound to the device, it can be enabled using the
+'enable' file, documented above.
Accessing legacy resources through sysfs
----------------------------------------
diff --git a/Documentation/filesystems/ubifs.txt b/Documentation/filesystems/ubifs.txt
index 84da2a4..12fedb7 100644
--- a/Documentation/filesystems/ubifs.txt
+++ b/Documentation/filesystems/ubifs.txt
@@ -79,13 +79,6 @@
(*) == default.
-norm_unmount (*) commit on unmount; the journal is committed
- when the file-system is unmounted so that the
- next mount does not have to replay the journal
- and it becomes very fast;
-fast_unmount do not commit on unmount; this option makes
- unmount faster, but the next mount slower
- because of the need to replay the journal.
bulk_read read more in one go to take advantage of flash
media that read faster sequentially
no_bulk_read (*) do not bulk-read
diff --git a/MAINTAINERS b/MAINTAINERS
index cf0ab3a..0ea3a6d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -911,7 +911,7 @@
BLACKFIN ARCHITECTURE
P: Bryan Wu
M: cooloney@kernel.org
-L: uclinux-dist-devel@blackfin.uclinux.org (subscribers-only)
+L: uclinux-dist-devel@blackfin.uclinux.org
W: http://blackfin.uclinux.org
S: Supported
@@ -1021,6 +1021,14 @@
W: http://bu3sch.de/btgpio.php
S: Maintained
+BTRFS FILE SYSTEM
+P: Chris Mason
+M: chris.mason@oracle.com
+L: linux-btrfs@vger.kernel.org
+W: http://btrfs.wiki.kernel.org/
+T: git kernel.org:/pub/scm/linux/kernel/git/mason/btrfs-unstable.git
+S: Maintained
+
BTTV VIDEO4LINUX DRIVER
P: Mauro Carvalho Chehab
M: mchehab@infradead.org
@@ -2212,7 +2220,7 @@
M: sean.hefty@intel.com
P: Hal Rosenstock
M: hal.rosenstock@gmail.com
-L: general@lists.openfabrics.org
+L: general@lists.openfabrics.org (moderated for non-subscribers)
W: http://www.openib.org/
T: git kernel.org:/pub/scm/linux/kernel/git/roland/infiniband.git
S: Supported
diff --git a/Makefile b/Makefile
index 7715b2c..681c1d2 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
VERSION = 2
PATCHLEVEL = 6
SUBLEVEL = 29
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc4
NAME = Erotic Pickled Herring
# *DOCUMENTATION*
diff --git a/arch/alpha/include/asm/bug.h b/arch/alpha/include/asm/bug.h
index 7b85b7c..1720c8a 100644
--- a/arch/alpha/include/asm/bug.h
+++ b/arch/alpha/include/asm/bug.h
@@ -8,12 +8,12 @@
/* ??? Would be nice to use .gprel32 here, but we can't be sure that the
function loaded the GP, so this could fail in modules. */
-#define BUG() { \
+#define BUG() do { \
__asm__ __volatile__( \
"call_pal %0 # bugchk\n\t" \
".long %1\n\t.8byte %2" \
: : "i"(PAL_bugchk), "i"(__LINE__), "i"(__FILE__)); \
- for ( ; ; ); }
+ for ( ; ; ); } while (0)
#define HAVE_ARCH_BUG
#endif
diff --git a/arch/alpha/kernel/irq.c b/arch/alpha/kernel/irq.c
index 703731a..7bc7489 100644
--- a/arch/alpha/kernel/irq.c
+++ b/arch/alpha/kernel/irq.c
@@ -55,7 +55,7 @@
cpu = (cpu < (NR_CPUS-1) ? cpu + 1 : 0);
last_cpu = cpu;
- irq_desc[irq].affinity = cpumask_of_cpu(cpu);
+ cpumask_copy(irq_desc[irq].affinity, cpumask_of(cpu));
irq_desc[irq].chip->set_affinity(irq, cpumask_of(cpu));
return 0;
}
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 77b0474..85040cf 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -650,6 +650,7 @@
no_fp: mov pc, lr
__und_usr_unknown:
+ enable_irq
mov r0, sp
adr lr, ret_from_exception
b do_undefinstr
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 06269ea..49a6ba9 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -136,7 +136,7 @@
ldmia sp!, {r0-r3, pc}
trace:
- ldr r1, [fp, #-4]
+ ldr r1, [fp, #-4] @ lr of instrumented routine
mov r0, lr
sub r0, r0, #MCOUNT_INSN_SIZE
mov lr, pc
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 7141cee..45eacb5 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -101,9 +101,14 @@
/* Handle bad interrupts */
static struct irq_desc bad_irq_desc = {
.handle_irq = handle_bad_irq,
- .lock = SPIN_LOCK_UNLOCKED
+ .lock = __SPIN_LOCK_UNLOCKED(bad_irq_desc.lock),
};
+#ifdef CONFIG_CPUMASK_OFFSTACK
+/* We are not allocating bad_irq_desc.affinity or .pending_mask */
+#error "ARM architecture does not support CONFIG_CPUMASK_OFFSTACK."
+#endif
+
/*
* do_IRQ handles all hardware IRQ's. Decoded IRQs should not
* come via this function. Instead, they should provide their
@@ -161,7 +166,7 @@
irq_desc[irq].status |= IRQ_NOREQUEST | IRQ_NOPROBE;
#ifdef CONFIG_SMP
- bad_irq_desc.affinity = CPU_MASK_ALL;
+ cpumask_setall(bad_irq_desc.affinity);
bad_irq_desc.cpu = smp_processor_id();
#endif
init_arch_irq();
@@ -191,15 +196,16 @@
struct irq_desc *desc = irq_desc + i;
if (desc->cpu == cpu) {
- unsigned int newcpu = any_online_cpu(desc->affinity);
-
- if (newcpu == NR_CPUS) {
+ unsigned int newcpu = cpumask_any_and(desc->affinity,
+ cpu_online_mask);
+ if (newcpu >= nr_cpu_ids) {
if (printk_ratelimit())
printk(KERN_INFO "IRQ%u no longer affine to CPU%u\n",
i, cpu);
- cpus_setall(desc->affinity);
- newcpu = any_online_cpu(desc->affinity);
+ cpumask_setall(desc->affinity);
+ newcpu = cpumask_any_and(desc->affinity,
+ cpu_online_mask);
}
route_irq(desc, i, newcpu);
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index 0021607..85598f7 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -65,6 +65,7 @@
#endif
. = ALIGN(4096);
__per_cpu_start = .;
+ *(.data.percpu.page_aligned)
*(.data.percpu)
*(.data.percpu.shared_aligned)
__per_cpu_end = .;
diff --git a/arch/arm/mach-msm/board-halibut.c b/arch/arm/mach-msm/board-halibut.c
index c2a96e3..e61967d 100644
--- a/arch/arm/mach-msm/board-halibut.c
+++ b/arch/arm/mach-msm/board-halibut.c
@@ -27,6 +27,7 @@
#include <asm/mach/map.h>
#include <asm/mach/flash.h>
+#include <mach/irqs.h>
#include <mach/board.h>
#include <mach/msm_iomap.h>
diff --git a/arch/arm/mach-omap1/devices.c b/arch/arm/mach-omap1/devices.c
index 77382d8..ba5d7c0 100644
--- a/arch/arm/mach-omap1/devices.c
+++ b/arch/arm/mach-omap1/devices.c
@@ -181,7 +181,7 @@
}
size = OMAP1_MMC_SIZE;
- omap_mmc_add(i, base, size, irq, mmc_data[i]);
+ omap_mmc_add("mmci-omap", i, base, size, irq, mmc_data[i]);
};
}
diff --git a/arch/arm/mach-omap1/mcbsp.c b/arch/arm/mach-omap1/mcbsp.c
index ca7a0cc..575ba31 100644
--- a/arch/arm/mach-omap1/mcbsp.c
+++ b/arch/arm/mach-omap1/mcbsp.c
@@ -28,81 +28,8 @@
#define DPS_RSTCT2_PER_EN (1 << 0)
#define DSP_RSTCT2_WD_PER_EN (1 << 1)
-struct mcbsp_internal_clk {
- struct clk clk;
- struct clk **childs;
- int n_childs;
-};
-
#if defined(CONFIG_ARCH_OMAP15XX) || defined(CONFIG_ARCH_OMAP16XX)
-static void omap_mcbsp_clk_init(struct mcbsp_internal_clk *mclk)
-{
- const char *clk_names[] = { "dsp_ck", "api_ck", "dspxor_ck" };
- int i;
-
- mclk->n_childs = ARRAY_SIZE(clk_names);
- mclk->childs = kzalloc(mclk->n_childs * sizeof(struct clk *),
- GFP_KERNEL);
-
- for (i = 0; i < mclk->n_childs; i++) {
- /* We fake a platform device to get correct device id */
- struct platform_device pdev;
-
- pdev.dev.bus = &platform_bus_type;
- pdev.id = mclk->clk.id;
- mclk->childs[i] = clk_get(&pdev.dev, clk_names[i]);
- if (IS_ERR(mclk->childs[i]))
- printk(KERN_ERR "Could not get clock %s (%d).\n",
- clk_names[i], mclk->clk.id);
- }
-}
-
-static int omap_mcbsp_clk_enable(struct clk *clk)
-{
- struct mcbsp_internal_clk *mclk = container_of(clk,
- struct mcbsp_internal_clk, clk);
- int i;
-
- for (i = 0; i < mclk->n_childs; i++)
- clk_enable(mclk->childs[i]);
- return 0;
-}
-
-static void omap_mcbsp_clk_disable(struct clk *clk)
-{
- struct mcbsp_internal_clk *mclk = container_of(clk,
- struct mcbsp_internal_clk, clk);
- int i;
-
- for (i = 0; i < mclk->n_childs; i++)
- clk_disable(mclk->childs[i]);
-}
-
-static struct mcbsp_internal_clk omap_mcbsp_clks[] = {
- {
- .clk = {
- .name = "mcbsp_clk",
- .id = 1,
- .enable = omap_mcbsp_clk_enable,
- .disable = omap_mcbsp_clk_disable,
- },
- },
- {
- .clk = {
- .name = "mcbsp_clk",
- .id = 3,
- .enable = omap_mcbsp_clk_enable,
- .disable = omap_mcbsp_clk_disable,
- },
- },
-};
-
-#define omap_mcbsp_clks_size ARRAY_SIZE(omap_mcbsp_clks)
-#else
-#define omap_mcbsp_clks_size 0
-static struct mcbsp_internal_clk __initdata *omap_mcbsp_clks;
-static inline void omap_mcbsp_clk_init(struct mcbsp_internal_clk *mclk)
-{ }
+const char *clk_names[] = { "dsp_ck", "api_ck", "dspxor_ck" };
#endif
static void omap1_mcbsp_request(unsigned int id)
@@ -167,8 +94,9 @@
.rx_irq = INT_McBSP1RX,
.tx_irq = INT_McBSP1TX,
.ops = &omap1_mcbsp_ops,
- .clk_name = "mcbsp_clk",
- },
+ .clk_names = clk_names,
+ .num_clks = 3,
+ },
{
.phys_base = OMAP1510_MCBSP2_BASE,
.dma_rx_sync = OMAP_DMA_MCBSP2_RX,
@@ -184,7 +112,8 @@
.rx_irq = INT_McBSP3RX,
.tx_irq = INT_McBSP3TX,
.ops = &omap1_mcbsp_ops,
- .clk_name = "mcbsp_clk",
+ .clk_names = clk_names,
+ .num_clks = 3,
},
};
#define OMAP15XX_MCBSP_PDATA_SZ ARRAY_SIZE(omap15xx_mcbsp_pdata)
@@ -202,7 +131,8 @@
.rx_irq = INT_McBSP1RX,
.tx_irq = INT_McBSP1TX,
.ops = &omap1_mcbsp_ops,
- .clk_name = "mcbsp_clk",
+ .clk_names = clk_names,
+ .num_clks = 3,
},
{
.phys_base = OMAP1610_MCBSP2_BASE,
@@ -219,7 +149,8 @@
.rx_irq = INT_McBSP3RX,
.tx_irq = INT_McBSP3TX,
.ops = &omap1_mcbsp_ops,
- .clk_name = "mcbsp_clk",
+ .clk_names = clk_names,
+ .num_clks = 3,
},
};
#define OMAP16XX_MCBSP_PDATA_SZ ARRAY_SIZE(omap16xx_mcbsp_pdata)
@@ -230,15 +161,6 @@
int __init omap1_mcbsp_init(void)
{
- int i;
-
- for (i = 0; i < omap_mcbsp_clks_size; i++) {
- if (cpu_is_omap15xx() || cpu_is_omap16xx()) {
- omap_mcbsp_clk_init(&omap_mcbsp_clks[i]);
- clk_register(&omap_mcbsp_clks[i].clk);
- }
- }
-
if (cpu_is_omap730())
omap_mcbsp_count = OMAP730_MCBSP_PDATA_SZ;
if (cpu_is_omap15xx())
diff --git a/arch/arm/mach-omap2/devices.c b/arch/arm/mach-omap2/devices.c
index 9d7216f..ce03fa7 100644
--- a/arch/arm/mach-omap2/devices.c
+++ b/arch/arm/mach-omap2/devices.c
@@ -421,6 +421,7 @@
int nr_controllers)
{
int i;
+ char *name;
for (i = 0; i < nr_controllers; i++) {
unsigned long base, size;
@@ -450,12 +451,14 @@
continue;
}
- if (cpu_is_omap2420())
+ if (cpu_is_omap2420()) {
size = OMAP2420_MMC_SIZE;
- else
+ name = "mmci-omap";
+ } else {
size = HSMMC_SIZE;
-
- omap_mmc_add(i, base, size, irq, mmc_data[i]);
+ name = "mmci-omap-hs";
+ }
+ omap_mmc_add(name, i, base, size, irq, mmc_data[i]);
};
}
diff --git a/arch/arm/mach-omap2/id.c b/arch/arm/mach-omap2/id.c
index b0f8e7d..b52a02f 100644
--- a/arch/arm/mach-omap2/id.c
+++ b/arch/arm/mach-omap2/id.c
@@ -172,9 +172,13 @@
omap_revision = OMAP3430_REV_ES3_0;
rev_name = "ES3.0";
break;
+ case 4:
+ omap_revision = OMAP3430_REV_ES3_1;
+ rev_name = "ES3.1";
+ break;
default:
/* Use the latest known revision as default */
- omap_revision = OMAP3430_REV_ES3_0;
+ omap_revision = OMAP3430_REV_ES3_1;
rev_name = "Unknown revision\n";
}
}
diff --git a/arch/arm/mach-omap2/irq.c b/arch/arm/mach-omap2/irq.c
index 636e282..9ba20d9 100644
--- a/arch/arm/mach-omap2/irq.c
+++ b/arch/arm/mach-omap2/irq.c
@@ -134,6 +134,7 @@
.ack = omap_mask_ack_irq,
.mask = omap_mask_irq,
.unmask = omap_unmask_irq,
+ .disable = omap_mask_irq,
};
static void __init omap_irq_bank_init_one(struct omap_irq_bank *bank)
diff --git a/arch/arm/mach-omap2/mcbsp.c b/arch/arm/mach-omap2/mcbsp.c
index e20023c..a9e631f 100644
--- a/arch/arm/mach-omap2/mcbsp.c
+++ b/arch/arm/mach-omap2/mcbsp.c
@@ -24,106 +24,7 @@
#include <mach/cpu.h>
#include <mach/mcbsp.h>
-struct mcbsp_internal_clk {
- struct clk clk;
- struct clk **childs;
- int n_childs;
-};
-
-#if defined(CONFIG_ARCH_OMAP24XX) || defined(CONFIG_ARCH_OMAP34XX)
-static void omap_mcbsp_clk_init(struct mcbsp_internal_clk *mclk)
-{
- const char *clk_names[] = { "mcbsp_ick", "mcbsp_fck" };
- int i;
-
- mclk->n_childs = ARRAY_SIZE(clk_names);
- mclk->childs = kzalloc(mclk->n_childs * sizeof(struct clk *),
- GFP_KERNEL);
-
- for (i = 0; i < mclk->n_childs; i++) {
- /* We fake a platform device to get correct device id */
- struct platform_device pdev;
-
- pdev.dev.bus = &platform_bus_type;
- pdev.id = mclk->clk.id;
- mclk->childs[i] = clk_get(&pdev.dev, clk_names[i]);
- if (IS_ERR(mclk->childs[i]))
- printk(KERN_ERR "Could not get clock %s (%d).\n",
- clk_names[i], mclk->clk.id);
- }
-}
-
-static int omap_mcbsp_clk_enable(struct clk *clk)
-{
- struct mcbsp_internal_clk *mclk = container_of(clk,
- struct mcbsp_internal_clk, clk);
- int i;
-
- for (i = 0; i < mclk->n_childs; i++)
- clk_enable(mclk->childs[i]);
- return 0;
-}
-
-static void omap_mcbsp_clk_disable(struct clk *clk)
-{
- struct mcbsp_internal_clk *mclk = container_of(clk,
- struct mcbsp_internal_clk, clk);
- int i;
-
- for (i = 0; i < mclk->n_childs; i++)
- clk_disable(mclk->childs[i]);
-}
-
-static struct mcbsp_internal_clk omap_mcbsp_clks[] = {
- {
- .clk = {
- .name = "mcbsp_clk",
- .id = 1,
- .enable = omap_mcbsp_clk_enable,
- .disable = omap_mcbsp_clk_disable,
- },
- },
- {
- .clk = {
- .name = "mcbsp_clk",
- .id = 2,
- .enable = omap_mcbsp_clk_enable,
- .disable = omap_mcbsp_clk_disable,
- },
- },
- {
- .clk = {
- .name = "mcbsp_clk",
- .id = 3,
- .enable = omap_mcbsp_clk_enable,
- .disable = omap_mcbsp_clk_disable,
- },
- },
- {
- .clk = {
- .name = "mcbsp_clk",
- .id = 4,
- .enable = omap_mcbsp_clk_enable,
- .disable = omap_mcbsp_clk_disable,
- },
- },
- {
- .clk = {
- .name = "mcbsp_clk",
- .id = 5,
- .enable = omap_mcbsp_clk_enable,
- .disable = omap_mcbsp_clk_disable,
- },
- },
-};
-
-#define omap_mcbsp_clks_size ARRAY_SIZE(omap_mcbsp_clks)
-#else
-#define omap_mcbsp_clks_size 0
-static struct mcbsp_internal_clk __initdata *omap_mcbsp_clks;
-static inline void omap_mcbsp_clk_init(struct clk *clk)
-{ }
-#endif
+const char *clk_names[] = { "mcbsp_ick", "mcbsp_fck" };
static void omap2_mcbsp2_mux_setup(void)
{
@@ -156,7 +57,8 @@
.rx_irq = INT_24XX_MCBSP1_IRQ_RX,
.tx_irq = INT_24XX_MCBSP1_IRQ_TX,
.ops = &omap2_mcbsp_ops,
- .clk_name = "mcbsp_clk",
+ .clk_names = clk_names,
+ .num_clks = 2,
},
{
.phys_base = OMAP24XX_MCBSP2_BASE,
@@ -165,7 +67,8 @@
.rx_irq = INT_24XX_MCBSP2_IRQ_RX,
.tx_irq = INT_24XX_MCBSP2_IRQ_TX,
.ops = &omap2_mcbsp_ops,
- .clk_name = "mcbsp_clk",
+ .clk_names = clk_names,
+ .num_clks = 2,
},
};
#define OMAP2420_MCBSP_PDATA_SZ ARRAY_SIZE(omap2420_mcbsp_pdata)
@@ -183,7 +86,8 @@
.rx_irq = INT_24XX_MCBSP1_IRQ_RX,
.tx_irq = INT_24XX_MCBSP1_IRQ_TX,
.ops = &omap2_mcbsp_ops,
- .clk_name = "mcbsp_clk",
+ .clk_names = clk_names,
+ .num_clks = 2,
},
{
.phys_base = OMAP24XX_MCBSP2_BASE,
@@ -192,7 +96,8 @@
.rx_irq = INT_24XX_MCBSP2_IRQ_RX,
.tx_irq = INT_24XX_MCBSP2_IRQ_TX,
.ops = &omap2_mcbsp_ops,
- .clk_name = "mcbsp_clk",
+ .clk_names = clk_names,
+ .num_clks = 2,
},
{
.phys_base = OMAP2430_MCBSP3_BASE,
@@ -201,7 +106,8 @@
.rx_irq = INT_24XX_MCBSP3_IRQ_RX,
.tx_irq = INT_24XX_MCBSP3_IRQ_TX,
.ops = &omap2_mcbsp_ops,
- .clk_name = "mcbsp_clk",
+ .clk_names = clk_names,
+ .num_clks = 2,
},
{
.phys_base = OMAP2430_MCBSP4_BASE,
@@ -210,7 +116,8 @@
.rx_irq = INT_24XX_MCBSP4_IRQ_RX,
.tx_irq = INT_24XX_MCBSP4_IRQ_TX,
.ops = &omap2_mcbsp_ops,
- .clk_name = "mcbsp_clk",
+ .clk_names = clk_names,
+ .num_clks = 2,
},
{
.phys_base = OMAP2430_MCBSP5_BASE,
@@ -219,7 +126,8 @@
.rx_irq = INT_24XX_MCBSP5_IRQ_RX,
.tx_irq = INT_24XX_MCBSP5_IRQ_TX,
.ops = &omap2_mcbsp_ops,
- .clk_name = "mcbsp_clk",
+ .clk_names = clk_names,
+ .num_clks = 2,
},
};
#define OMAP2430_MCBSP_PDATA_SZ ARRAY_SIZE(omap2430_mcbsp_pdata)
@@ -237,7 +145,8 @@
.rx_irq = INT_24XX_MCBSP1_IRQ_RX,
.tx_irq = INT_24XX_MCBSP1_IRQ_TX,
.ops = &omap2_mcbsp_ops,
- .clk_name = "mcbsp_clk",
+ .clk_names = clk_names,
+ .num_clks = 2,
},
{
.phys_base = OMAP34XX_MCBSP2_BASE,
@@ -246,7 +155,8 @@
.rx_irq = INT_24XX_MCBSP2_IRQ_RX,
.tx_irq = INT_24XX_MCBSP2_IRQ_TX,
.ops = &omap2_mcbsp_ops,
- .clk_name = "mcbsp_clk",
+ .clk_names = clk_names,
+ .num_clks = 2,
},
{
.phys_base = OMAP34XX_MCBSP3_BASE,
@@ -255,7 +165,8 @@
.rx_irq = INT_24XX_MCBSP3_IRQ_RX,
.tx_irq = INT_24XX_MCBSP3_IRQ_TX,
.ops = &omap2_mcbsp_ops,
- .clk_name = "mcbsp_clk",
+ .clk_names = clk_names,
+ .num_clks = 2,
},
{
.phys_base = OMAP34XX_MCBSP4_BASE,
@@ -264,7 +175,8 @@
.rx_irq = INT_24XX_MCBSP4_IRQ_RX,
.tx_irq = INT_24XX_MCBSP4_IRQ_TX,
.ops = &omap2_mcbsp_ops,
- .clk_name = "mcbsp_clk",
+ .clk_names = clk_names,
+ .num_clks = 2,
},
{
.phys_base = OMAP34XX_MCBSP5_BASE,
@@ -273,7 +185,8 @@
.rx_irq = INT_24XX_MCBSP5_IRQ_RX,
.tx_irq = INT_24XX_MCBSP5_IRQ_TX,
.ops = &omap2_mcbsp_ops,
- .clk_name = "mcbsp_clk",
+ .clk_names = clk_names,
+ .num_clks = 2,
},
};
#define OMAP34XX_MCBSP_PDATA_SZ ARRAY_SIZE(omap34xx_mcbsp_pdata)
@@ -284,14 +197,6 @@
static int __init omap2_mcbsp_init(void)
{
- int i;
-
- for (i = 0; i < omap_mcbsp_clks_size; i++) {
- /* Once we call clk_get inside init, we do not register it */
- omap_mcbsp_clk_init(&omap_mcbsp_clks[i]);
- clk_register(&omap_mcbsp_clks[i].clk);
- }
-
if (cpu_is_omap2420())
omap_mcbsp_count = OMAP2420_MCBSP_PDATA_SZ;
if (cpu_is_omap2430())
diff --git a/arch/arm/mach-omap2/sleep24xx.S b/arch/arm/mach-omap2/sleep24xx.S
index 43336b9..bf9e961 100644
--- a/arch/arm/mach-omap2/sleep24xx.S
+++ b/arch/arm/mach-omap2/sleep24xx.S
@@ -93,9 +93,8 @@
orr r4, r4, #0x40 @ enable self refresh on idle req
mov r5, #0x2000 @ set delay (DPLL relock + DLL relock)
str r4, [r2] @ make it so
- mov r2, #0
nop
- mcr p15, 0, r2, c7, c0, 4 @ wait for interrupt
+ mcr p15, 0, r3, c7, c0, 4 @ wait for interrupt
nop
loop:
subs r5, r5, #0x1 @ awake, wait just a bit
diff --git a/arch/arm/mach-omap2/timer-gp.c b/arch/arm/mach-omap2/timer-gp.c
index ae60363..9fc13a2 100644
--- a/arch/arm/mach-omap2/timer-gp.c
+++ b/arch/arm/mach-omap2/timer-gp.c
@@ -118,7 +118,8 @@
clockevent_gpt.max_delta_ns =
clockevent_delta2ns(0xffffffff, &clockevent_gpt);
clockevent_gpt.min_delta_ns =
- clockevent_delta2ns(1, &clockevent_gpt);
+ clockevent_delta2ns(3, &clockevent_gpt);
+ /* Timer internal resynch latency. */
clockevent_gpt.cpumask = cpumask_of(0);
clockevents_register_device(&clockevent_gpt);
diff --git a/arch/arm/mach-sa1100/generic.c b/arch/arm/mach-sa1100/generic.c
index c1fbd5b..23cfdd5 100644
--- a/arch/arm/mach-sa1100/generic.c
+++ b/arch/arm/mach-sa1100/generic.c
@@ -289,7 +289,7 @@
};
static struct platform_device sa11x0mtd_device = {
- .name = "flash",
+ .name = "sa1100-mtd",
.id = -1,
};
diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c
index 81d0b87..bc0099d 100644
--- a/arch/arm/mm/fault-armv.c
+++ b/arch/arm/mm/fault-armv.c
@@ -66,7 +66,10 @@
* fault (ie, is old), we can safely ignore any issues.
*/
if (ret && (pte_val(entry) & L_PTE_MT_MASK) != shared_pte_mask) {
- flush_cache_page(vma, address, pte_pfn(entry));
+ unsigned long pfn = pte_pfn(entry);
+ flush_cache_page(vma, address, pfn);
+ outer_flush_range((pfn << PAGE_SHIFT),
+ (pfn << PAGE_SHIFT) + PAGE_SIZE);
pte_val(entry) &= ~L_PTE_MT_MASK;
pte_val(entry) |= shared_pte_mask;
set_pte_at(vma->vm_mm, address, pte, entry);
diff --git a/arch/arm/oprofile/op_model_mpcore.c b/arch/arm/oprofile/op_model_mpcore.c
index 6d6bd58..853d42b 100644
--- a/arch/arm/oprofile/op_model_mpcore.c
+++ b/arch/arm/oprofile/op_model_mpcore.c
@@ -263,7 +263,7 @@
const struct cpumask *mask = cpumask_of(cpu);
spin_lock_irq(&desc->lock);
- desc->affinity = *mask;
+ cpumask_copy(desc->affinity, mask);
desc->chip->set_affinity(irq, mask);
spin_unlock_irq(&desc->lock);
}
diff --git a/arch/arm/plat-omap/devices.c b/arch/arm/plat-omap/devices.c
index ac15c23..208dbb1 100644
--- a/arch/arm/plat-omap/devices.c
+++ b/arch/arm/plat-omap/devices.c
@@ -200,14 +200,15 @@
/*
* Register MMC devices. Called from mach-omap1 and mach-omap2 device init.
*/
-int __init omap_mmc_add(int id, unsigned long base, unsigned long size,
- unsigned int irq, struct omap_mmc_platform_data *data)
+int __init omap_mmc_add(const char *name, int id, unsigned long base,
+ unsigned long size, unsigned int irq,
+ struct omap_mmc_platform_data *data)
{
struct platform_device *pdev;
struct resource res[OMAP_MMC_NR_RES];
int ret;
- pdev = platform_device_alloc("mmci-omap", id);
+ pdev = platform_device_alloc(name, id);
if (!pdev)
return -ENOMEM;
diff --git a/arch/arm/plat-omap/dma.c b/arch/arm/plat-omap/dma.c
index e77373c..47ec77a 100644
--- a/arch/arm/plat-omap/dma.c
+++ b/arch/arm/plat-omap/dma.c
@@ -709,6 +709,7 @@
chan->dev_name = dev_name;
chan->callback = callback;
chan->data = data;
+ chan->flags = 0;
#ifndef CONFIG_ARCH_OMAP1
if (cpu_class_is_omap2()) {
@@ -1888,11 +1889,11 @@
status = dma_read(CSR(ch));
}
+ dma_write(status, CSR(ch));
+
if (likely(dma_chan[ch].callback != NULL))
dma_chan[ch].callback(ch, status, dma_chan[ch].data);
- dma_write(status, CSR(ch));
-
return 0;
}
diff --git a/arch/arm/plat-omap/include/mach/cpu.h b/arch/arm/plat-omap/include/mach/cpu.h
index b2062f1..a8e1178 100644
--- a/arch/arm/plat-omap/include/mach/cpu.h
+++ b/arch/arm/plat-omap/include/mach/cpu.h
@@ -339,6 +339,7 @@
#define OMAP3430_REV_ES2_0 0x34301034
#define OMAP3430_REV_ES2_1 0x34302034
#define OMAP3430_REV_ES3_0 0x34303034
+#define OMAP3430_REV_ES3_1 0x34304034
/*
* omap_chip bits
diff --git a/arch/arm/plat-omap/include/mach/mcbsp.h b/arch/arm/plat-omap/include/mach/mcbsp.h
index eef873d..113c246 100644
--- a/arch/arm/plat-omap/include/mach/mcbsp.h
+++ b/arch/arm/plat-omap/include/mach/mcbsp.h
@@ -344,7 +344,8 @@
u8 dma_rx_sync, dma_tx_sync;
u16 rx_irq, tx_irq;
struct omap_mcbsp_ops *ops;
- char const *clk_name;
+ char const **clk_names;
+ int num_clks;
};
struct omap_mcbsp {
@@ -376,7 +377,8 @@
/* Protect the field .free, while checking if the mcbsp is in use */
spinlock_t lock;
struct omap_mcbsp_platform_data *pdata;
- struct clk *clk;
+ struct clk **clks;
+ int num_clks;
};
extern struct omap_mcbsp **mcbsp_ptr;
extern int omap_mcbsp_count;
diff --git a/arch/arm/plat-omap/include/mach/mmc.h b/arch/arm/plat-omap/include/mach/mmc.h
index 031250f..73a9e15 100644
--- a/arch/arm/plat-omap/include/mach/mmc.h
+++ b/arch/arm/plat-omap/include/mach/mmc.h
@@ -115,8 +115,9 @@
int nr_controllers);
void omap2_init_mmc(struct omap_mmc_platform_data **mmc_data,
int nr_controllers);
-int omap_mmc_add(int id, unsigned long base, unsigned long size,
- unsigned int irq, struct omap_mmc_platform_data *data);
+int omap_mmc_add(const char *name, int id, unsigned long base,
+ unsigned long size, unsigned int irq,
+ struct omap_mmc_platform_data *data);
#else
static inline void omap1_init_mmc(struct omap_mmc_platform_data **mmc_data,
int nr_controllers)
@@ -126,8 +127,9 @@
int nr_controllers)
{
}
-static inline int omap_mmc_add(int id, unsigned long base, unsigned long size,
- unsigned int irq, struct omap_mmc_platform_data *data)
+static inline int omap_mmc_add(const char *name, int id, unsigned long base,
+ unsigned long size, unsigned int irq,
+ struct omap_mmc_platform_data *data)
{
return 0;
}
diff --git a/arch/arm/plat-omap/mcbsp.c b/arch/arm/plat-omap/mcbsp.c
index f2401a8..e5842e3 100644
--- a/arch/arm/plat-omap/mcbsp.c
+++ b/arch/arm/plat-omap/mcbsp.c
@@ -214,6 +214,7 @@
int omap_mcbsp_request(unsigned int id)
{
struct omap_mcbsp *mcbsp;
+ int i;
int err;
if (!omap_mcbsp_check_valid_id(id)) {
@@ -225,7 +226,8 @@
if (mcbsp->pdata && mcbsp->pdata->ops && mcbsp->pdata->ops->request)
mcbsp->pdata->ops->request(id);
- clk_enable(mcbsp->clk);
+ for (i = 0; i < mcbsp->num_clks; i++)
+ clk_enable(mcbsp->clks[i]);
spin_lock(&mcbsp->lock);
if (!mcbsp->free) {
@@ -276,6 +278,7 @@
void omap_mcbsp_free(unsigned int id)
{
struct omap_mcbsp *mcbsp;
+ int i;
if (!omap_mcbsp_check_valid_id(id)) {
printk(KERN_ERR "%s: Invalid id (%d)\n", __func__, id + 1);
@@ -286,7 +289,8 @@
if (mcbsp->pdata && mcbsp->pdata->ops && mcbsp->pdata->ops->free)
mcbsp->pdata->ops->free(id);
- clk_disable(mcbsp->clk);
+ for (i = mcbsp->num_clks - 1; i >= 0; i--)
+ clk_disable(mcbsp->clks[i]);
spin_lock(&mcbsp->lock);
if (mcbsp->free) {
@@ -872,6 +876,7 @@
struct omap_mcbsp_platform_data *pdata = pdev->dev.platform_data;
struct omap_mcbsp *mcbsp;
int id = pdev->id - 1;
+ int i;
int ret = 0;
if (!pdata) {
@@ -916,14 +921,25 @@
mcbsp->dma_rx_sync = pdata->dma_rx_sync;
mcbsp->dma_tx_sync = pdata->dma_tx_sync;
- if (pdata->clk_name)
- mcbsp->clk = clk_get(&pdev->dev, pdata->clk_name);
- if (IS_ERR(mcbsp->clk)) {
- dev_err(&pdev->dev,
- "Invalid clock configuration for McBSP%d.\n",
- mcbsp->id);
- ret = PTR_ERR(mcbsp->clk);
- goto err_clk;
+ if (pdata->num_clks) {
+ mcbsp->num_clks = pdata->num_clks;
+ mcbsp->clks = kzalloc(mcbsp->num_clks * sizeof(struct clk *),
+ GFP_KERNEL);
+ if (!mcbsp->clks) {
+ ret = -ENOMEM;
+ goto exit;
+ }
+ for (i = 0; i < mcbsp->num_clks; i++) {
+ mcbsp->clks[i] = clk_get(&pdev->dev, pdata->clk_names[i]);
+ if (IS_ERR(mcbsp->clks[i])) {
+ dev_err(&pdev->dev,
+ "Invalid %s configuration for McBSP%d.\n",
+ pdata->clk_names[i], mcbsp->id);
+ ret = PTR_ERR(mcbsp->clks[i]);
+ goto err_clk;
+ }
+ }
+
}
mcbsp->pdata = pdata;
@@ -932,6 +948,9 @@
return 0;
err_clk:
+ while (i--)
+ clk_put(mcbsp->clks[i]);
+ kfree(mcbsp->clks);
iounmap(mcbsp->io_base);
err_ioremap:
mcbsp->free = 0;
@@ -942,6 +961,7 @@
static int __devexit omap_mcbsp_remove(struct platform_device *pdev)
{
struct omap_mcbsp *mcbsp = platform_get_drvdata(pdev);
+ int i;
platform_set_drvdata(pdev, NULL);
if (mcbsp) {
@@ -950,12 +970,18 @@
mcbsp->pdata->ops->free)
mcbsp->pdata->ops->free(mcbsp->id);
- clk_disable(mcbsp->clk);
- clk_put(mcbsp->clk);
+ for (i = mcbsp->num_clks - 1; i >= 0; i--) {
+ clk_disable(mcbsp->clks[i]);
+ clk_put(mcbsp->clks[i]);
+ }
iounmap(mcbsp->io_base);
- mcbsp->clk = NULL;
+ if (mcbsp->num_clks) {
+ kfree(mcbsp->clks);
+ mcbsp->clks = NULL;
+ mcbsp->num_clks = 0;
+ }
mcbsp->free = 0;
mcbsp->dev = NULL;
}
diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig
index a949c4f..8f1f97d 100644
--- a/arch/blackfin/Kconfig
+++ b/arch/blackfin/Kconfig
@@ -169,26 +169,51 @@
help
BF542 Processor Support.
+config BF542M
+ bool "BF542m"
+ help
+ BF542 Processor Support.
+
config BF544
bool "BF544"
help
BF544 Processor Support.
+config BF544M
+ bool "BF544m"
+ help
+ BF544 Processor Support.
+
config BF547
bool "BF547"
help
BF547 Processor Support.
+config BF547M
+ bool "BF547m"
+ help
+ BF547 Processor Support.
+
config BF548
bool "BF548"
help
BF548 Processor Support.
+config BF548M
+ bool "BF548m"
+ help
+ BF548 Processor Support.
+
config BF549
bool "BF549"
help
BF549 Processor Support.
+config BF549M
+ bool "BF549m"
+ help
+ BF549 Processor Support.
+
config BF561
bool "BF561"
help
@@ -224,39 +249,39 @@
config BF_REV_MIN
int
- default 0 if (BF51x || BF52x || BF54x)
+ default 0 if (BF51x || BF52x || (BF54x && !BF54xM))
default 2 if (BF537 || BF536 || BF534)
- default 3 if (BF561 ||BF533 || BF532 || BF531)
+ default 3 if (BF561 || BF533 || BF532 || BF531 || BF54xM)
default 4 if (BF538 || BF539)
config BF_REV_MAX
int
- default 2 if (BF51x || BF52x || BF54x)
- default 3 if (BF537 || BF536 || BF534)
+ default 2 if (BF51x || BF52x || (BF54x && !BF54xM))
+ default 3 if (BF537 || BF536 || BF534 || BF54xM)
default 5 if (BF561 || BF538 || BF539)
default 6 if (BF533 || BF532 || BF531)
choice
prompt "Silicon Rev"
- default BF_REV_0_1 if (BF51x || BF52x || BF54x)
+ default BF_REV_0_1 if (BF51x || BF52x || (BF54x && !BF54xM))
default BF_REV_0_2 if (BF534 || BF536 || BF537)
- default BF_REV_0_3 if (BF531 || BF532 || BF533 || BF561)
+ default BF_REV_0_3 if (BF531 || BF532 || BF533 || BF54xM || BF561)
config BF_REV_0_0
bool "0.0"
- depends on (BF51x || BF52x || BF54x)
+ depends on (BF51x || BF52x || (BF54x && !BF54xM))
config BF_REV_0_1
bool "0.1"
- depends on (BF52x || BF54x)
+ depends on (BF52x || (BF54x && !BF54xM))
config BF_REV_0_2
bool "0.2"
- depends on (BF52x || BF537 || BF536 || BF534 || BF54x)
+ depends on (BF52x || BF537 || BF536 || BF534 || (BF54x && !BF54xM))
config BF_REV_0_3
bool "0.3"
- depends on (BF561 || BF537 || BF536 || BF534 || BF533 || BF532 || BF531)
+ depends on (BF54xM || BF561 || BF537 || BF536 || BF534 || BF533 || BF532 || BF531)
config BF_REV_0_4
bool "0.4"
@@ -293,9 +318,14 @@
depends on (BF531 || BF532 || BF533 || BF534 || BF536 || BF537)
default y
+config BF54xM
+ bool
+ depends on (BF542M || BF544M || BF547M || BF548M || BF549M)
+ default y
+
config BF54x
bool
- depends on (BF542 || BF544 || BF547 || BF548 || BF549)
+ depends on (BF542 || BF544 || BF547 || BF548 || BF549 || BF54xM)
default y
config MEM_GENERIC_BOARD
diff --git a/arch/blackfin/Makefile b/arch/blackfin/Makefile
index e550c8d..d54c828 100644
--- a/arch/blackfin/Makefile
+++ b/arch/blackfin/Makefile
@@ -21,57 +21,67 @@
KBUILD_DEFCONFIG := BF537-STAMP_defconfig
# setup the machine name and the machine dependent settings
-machine-$(CONFIG_BF512) := bf518
-machine-$(CONFIG_BF514) := bf518
-machine-$(CONFIG_BF516) := bf518
-machine-$(CONFIG_BF518) := bf518
-machine-$(CONFIG_BF522) := bf527
-machine-$(CONFIG_BF523) := bf527
-machine-$(CONFIG_BF524) := bf527
-machine-$(CONFIG_BF525) := bf527
-machine-$(CONFIG_BF526) := bf527
-machine-$(CONFIG_BF527) := bf527
-machine-$(CONFIG_BF531) := bf533
-machine-$(CONFIG_BF532) := bf533
-machine-$(CONFIG_BF533) := bf533
-machine-$(CONFIG_BF534) := bf537
-machine-$(CONFIG_BF536) := bf537
-machine-$(CONFIG_BF537) := bf537
-machine-$(CONFIG_BF538) := bf538
-machine-$(CONFIG_BF539) := bf538
-machine-$(CONFIG_BF542) := bf548
-machine-$(CONFIG_BF544) := bf548
-machine-$(CONFIG_BF547) := bf548
-machine-$(CONFIG_BF548) := bf548
-machine-$(CONFIG_BF549) := bf548
-machine-$(CONFIG_BF561) := bf561
+machine-$(CONFIG_BF512) := bf518
+machine-$(CONFIG_BF514) := bf518
+machine-$(CONFIG_BF516) := bf518
+machine-$(CONFIG_BF518) := bf518
+machine-$(CONFIG_BF522) := bf527
+machine-$(CONFIG_BF523) := bf527
+machine-$(CONFIG_BF524) := bf527
+machine-$(CONFIG_BF525) := bf527
+machine-$(CONFIG_BF526) := bf527
+machine-$(CONFIG_BF527) := bf527
+machine-$(CONFIG_BF531) := bf533
+machine-$(CONFIG_BF532) := bf533
+machine-$(CONFIG_BF533) := bf533
+machine-$(CONFIG_BF534) := bf537
+machine-$(CONFIG_BF536) := bf537
+machine-$(CONFIG_BF537) := bf537
+machine-$(CONFIG_BF538) := bf538
+machine-$(CONFIG_BF539) := bf538
+machine-$(CONFIG_BF542) := bf548
+machine-$(CONFIG_BF542M) := bf548
+machine-$(CONFIG_BF544) := bf548
+machine-$(CONFIG_BF544M) := bf548
+machine-$(CONFIG_BF547) := bf548
+machine-$(CONFIG_BF547M) := bf548
+machine-$(CONFIG_BF548) := bf548
+machine-$(CONFIG_BF548M) := bf548
+machine-$(CONFIG_BF549) := bf548
+machine-$(CONFIG_BF549M) := bf548
+machine-$(CONFIG_BF561) := bf561
MACHINE := $(machine-y)
export MACHINE
-cpu-$(CONFIG_BF512) := bf512
-cpu-$(CONFIG_BF514) := bf514
-cpu-$(CONFIG_BF516) := bf516
-cpu-$(CONFIG_BF518) := bf518
-cpu-$(CONFIG_BF522) := bf522
-cpu-$(CONFIG_BF523) := bf523
-cpu-$(CONFIG_BF524) := bf524
-cpu-$(CONFIG_BF525) := bf525
-cpu-$(CONFIG_BF526) := bf526
-cpu-$(CONFIG_BF527) := bf527
-cpu-$(CONFIG_BF531) := bf531
-cpu-$(CONFIG_BF532) := bf532
-cpu-$(CONFIG_BF533) := bf533
-cpu-$(CONFIG_BF534) := bf534
-cpu-$(CONFIG_BF536) := bf536
-cpu-$(CONFIG_BF537) := bf537
-cpu-$(CONFIG_BF538) := bf538
-cpu-$(CONFIG_BF539) := bf539
-cpu-$(CONFIG_BF542) := bf542
-cpu-$(CONFIG_BF544) := bf544
-cpu-$(CONFIG_BF547) := bf547
-cpu-$(CONFIG_BF548) := bf548
-cpu-$(CONFIG_BF549) := bf549
-cpu-$(CONFIG_BF561) := bf561
+cpu-$(CONFIG_BF512) := bf512
+cpu-$(CONFIG_BF514) := bf514
+cpu-$(CONFIG_BF516) := bf516
+cpu-$(CONFIG_BF518) := bf518
+cpu-$(CONFIG_BF522) := bf522
+cpu-$(CONFIG_BF523) := bf523
+cpu-$(CONFIG_BF524) := bf524
+cpu-$(CONFIG_BF525) := bf525
+cpu-$(CONFIG_BF526) := bf526
+cpu-$(CONFIG_BF527) := bf527
+cpu-$(CONFIG_BF531) := bf531
+cpu-$(CONFIG_BF532) := bf532
+cpu-$(CONFIG_BF533) := bf533
+cpu-$(CONFIG_BF534) := bf534
+cpu-$(CONFIG_BF536) := bf536
+cpu-$(CONFIG_BF537) := bf537
+cpu-$(CONFIG_BF538) := bf538
+cpu-$(CONFIG_BF539) := bf539
+cpu-$(CONFIG_BF542) := bf542
+cpu-$(CONFIG_BF542M) := bf542m
+cpu-$(CONFIG_BF544) := bf544
+cpu-$(CONFIG_BF544M) := bf544m
+cpu-$(CONFIG_BF547) := bf547
+cpu-$(CONFIG_BF547M) := bf547m
+cpu-$(CONFIG_BF548) := bf548
+cpu-$(CONFIG_BF548M) := bf548m
+cpu-$(CONFIG_BF549) := bf549
+cpu-$(CONFIG_BF549M) := bf549m
+cpu-$(CONFIG_BF561) := bf561
rev-$(CONFIG_BF_REV_0_0) := 0.0
rev-$(CONFIG_BF_REV_0_1) := 0.1
diff --git a/arch/blackfin/configs/BF518F-EZBRD_defconfig b/arch/blackfin/configs/BF518F-EZBRD_defconfig
index defb978..4fdb9e0 100644
--- a/arch/blackfin/configs/BF518F-EZBRD_defconfig
+++ b/arch/blackfin/configs/BF518F-EZBRD_defconfig
@@ -1,6 +1,7 @@
#
# Automatically generated make config: don't edit
# Linux kernel version: 2.6.28-rc2
+# Fri Jan 9 17:58:41 2009
#
# CONFIG_MMU is not set
# CONFIG_FPU is not set
@@ -149,6 +150,7 @@
# CONFIG_BF_REV_ANY is not set
# CONFIG_BF_REV_NONE is not set
CONFIG_BF51x=y
+CONFIG_MEM_MT48LC32M8A2_75=y
CONFIG_BFIN518F_EZBRD=y
#
@@ -598,7 +600,10 @@
# CONFIG_MDIO_BITBANG is not set
CONFIG_NET_ETHERNET=y
CONFIG_MII=y
-# CONFIG_BFIN_MAC is not set
+CONFIG_BFIN_MAC=y
+CONFIG_BFIN_TX_DESC_NUM=10
+CONFIG_BFIN_RX_DESC_NUM=20
+# CONFIG_BFIN_MAC_RMII is not set
# CONFIG_SMC91X is not set
# CONFIG_SMSC911X is not set
# CONFIG_DM9000 is not set
@@ -679,7 +684,7 @@
CONFIG_HW_CONSOLE=y
# CONFIG_VT_HW_CONSOLE_BINDING is not set
# CONFIG_DEVKMEM is not set
-# CONFIG_BFIN_JTAG_COMM is not set
+CONFIG_BFIN_JTAG_COMM=m
# CONFIG_SERIAL_NONSTANDARD is not set
#
diff --git a/arch/blackfin/configs/BF526-EZBRD_defconfig b/arch/blackfin/configs/BF526-EZBRD_defconfig
index 992424f..8e2b855 100644
--- a/arch/blackfin/configs/BF526-EZBRD_defconfig
+++ b/arch/blackfin/configs/BF526-EZBRD_defconfig
@@ -723,7 +723,7 @@
CONFIG_HW_CONSOLE=y
# CONFIG_VT_HW_CONSOLE_BINDING is not set
# CONFIG_DEVKMEM is not set
-# CONFIG_BFIN_JTAG_COMM is not set
+CONFIG_BFIN_JTAG_COMM=m
# CONFIG_SERIAL_NONSTANDARD is not set
#
diff --git a/arch/blackfin/configs/BF527-EZKIT_defconfig b/arch/blackfin/configs/BF527-EZKIT_defconfig
index 21e3c1a..833128b 100644
--- a/arch/blackfin/configs/BF527-EZKIT_defconfig
+++ b/arch/blackfin/configs/BF527-EZKIT_defconfig
@@ -767,7 +767,7 @@
CONFIG_HW_CONSOLE=y
# CONFIG_VT_HW_CONSOLE_BINDING is not set
# CONFIG_DEVKMEM is not set
-# CONFIG_BFIN_JTAG_COMM is not set
+CONFIG_BFIN_JTAG_COMM=m
# CONFIG_SERIAL_NONSTANDARD is not set
#
diff --git a/arch/blackfin/configs/BF533-EZKIT_defconfig b/arch/blackfin/configs/BF533-EZKIT_defconfig
index 0bdf20a..334c94b 100644
--- a/arch/blackfin/configs/BF533-EZKIT_defconfig
+++ b/arch/blackfin/configs/BF533-EZKIT_defconfig
@@ -672,7 +672,7 @@
CONFIG_SIMPLE_GPIO=m
# CONFIG_VT is not set
# CONFIG_DEVKMEM is not set
-# CONFIG_BFIN_JTAG_COMM is not set
+CONFIG_BFIN_JTAG_COMM=m
# CONFIG_SERIAL_NONSTANDARD is not set
#
diff --git a/arch/blackfin/configs/BF533-STAMP_defconfig b/arch/blackfin/configs/BF533-STAMP_defconfig
index 2f747d6..9d73343 100644
--- a/arch/blackfin/configs/BF533-STAMP_defconfig
+++ b/arch/blackfin/configs/BF533-STAMP_defconfig
@@ -679,7 +679,7 @@
CONFIG_SIMPLE_GPIO=m
# CONFIG_VT is not set
# CONFIG_DEVKMEM is not set
-# CONFIG_BFIN_JTAG_COMM is not set
+CONFIG_BFIN_JTAG_COMM=m
# CONFIG_SERIAL_NONSTANDARD is not set
#
diff --git a/arch/blackfin/configs/BF537-STAMP_defconfig b/arch/blackfin/configs/BF537-STAMP_defconfig
index 8b0a812..4fb4108 100644
--- a/arch/blackfin/configs/BF537-STAMP_defconfig
+++ b/arch/blackfin/configs/BF537-STAMP_defconfig
@@ -722,7 +722,7 @@
CONFIG_SIMPLE_GPIO=m
# CONFIG_VT is not set
# CONFIG_DEVKMEM is not set
-# CONFIG_BFIN_JTAG_COMM is not set
+CONFIG_BFIN_JTAG_COMM=m
# CONFIG_SERIAL_NONSTANDARD is not set
#
diff --git a/arch/blackfin/configs/BF538-EZKIT_defconfig b/arch/blackfin/configs/BF538-EZKIT_defconfig
index a1f766b..cb32f56 100644
--- a/arch/blackfin/configs/BF538-EZKIT_defconfig
+++ b/arch/blackfin/configs/BF538-EZKIT_defconfig
@@ -726,7 +726,7 @@
CONFIG_SIMPLE_GPIO=m
# CONFIG_VT is not set
# CONFIG_DEVKMEM is not set
-# CONFIG_BFIN_JTAG_COMM is not set
+CONFIG_BFIN_JTAG_COMM=m
# CONFIG_SERIAL_NONSTANDARD is not set
#
diff --git a/arch/blackfin/configs/BF548-EZKIT_defconfig b/arch/blackfin/configs/BF548-EZKIT_defconfig
index cd2da6b..0f869761 100644
--- a/arch/blackfin/configs/BF548-EZKIT_defconfig
+++ b/arch/blackfin/configs/BF548-EZKIT_defconfig
@@ -856,7 +856,7 @@
CONFIG_HW_CONSOLE=y
# CONFIG_VT_HW_CONSOLE_BINDING is not set
# CONFIG_DEVKMEM is not set
-# CONFIG_BFIN_JTAG_COMM is not set
+CONFIG_BFIN_JTAG_COMM=m
# CONFIG_SERIAL_NONSTANDARD is not set
#
diff --git a/arch/blackfin/configs/BF561-EZKIT_defconfig b/arch/blackfin/configs/BF561-EZKIT_defconfig
index b398ca2..042c7ad 100644
--- a/arch/blackfin/configs/BF561-EZKIT_defconfig
+++ b/arch/blackfin/configs/BF561-EZKIT_defconfig
@@ -709,7 +709,7 @@
CONFIG_SIMPLE_GPIO=m
# CONFIG_VT is not set
# CONFIG_DEVKMEM is not set
-# CONFIG_BFIN_JTAG_COMM is not set
+CONFIG_BFIN_JTAG_COMM=m
# CONFIG_SERIAL_NONSTANDARD is not set
#
diff --git a/arch/blackfin/configs/CM-BF527_defconfig b/arch/blackfin/configs/CM-BF527_defconfig
index 9514694..865ed85 100644
--- a/arch/blackfin/configs/CM-BF527_defconfig
+++ b/arch/blackfin/configs/CM-BF527_defconfig
@@ -1,7 +1,6 @@
#
# Automatically generated make config: don't edit
-# Linux kernel version: 2.6.24.7
-# Fri Jul 18 18:00:41 2008
+# Linux kernel version: 2.6.28
#
# CONFIG_MMU is not set
# CONFIG_FPU is not set
@@ -9,7 +8,6 @@
# CONFIG_RWSEM_XCHGADD_ALGORITHM is not set
CONFIG_BLACKFIN=y
CONFIG_ZONE_DMA=y
-CONFIG_SEMAPHORE_SLEEPERS=y
CONFIG_GENERIC_FIND_NEXT_BIT=y
CONFIG_GENERIC_HWEIGHT=y
CONFIG_GENERIC_HARDIRQS=y
@@ -32,18 +30,16 @@
# CONFIG_POSIX_MQUEUE is not set
# CONFIG_BSD_PROCESS_ACCT is not set
# CONFIG_TASKSTATS is not set
-# CONFIG_USER_NS is not set
-# CONFIG_PID_NS is not set
# CONFIG_AUDIT is not set
CONFIG_IKCONFIG=y
CONFIG_IKCONFIG_PROC=y
CONFIG_LOG_BUF_SHIFT=14
# CONFIG_CGROUPS is not set
-CONFIG_FAIR_GROUP_SCHED=y
-CONFIG_FAIR_USER_SCHED=y
-# CONFIG_FAIR_CGROUP_SCHED is not set
-# CONFIG_SYSFS_DEPRECATED is not set
+# CONFIG_GROUP_SCHED is not set
+CONFIG_SYSFS_DEPRECATED=y
+CONFIG_SYSFS_DEPRECATED_V2=y
# CONFIG_RELAY is not set
+# CONFIG_NAMESPACES is not set
CONFIG_BLK_DEV_INITRD=y
CONFIG_INITRAMFS_SOURCE=""
# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
@@ -52,26 +48,35 @@
CONFIG_UID16=y
CONFIG_SYSCTL_SYSCALL=y
CONFIG_KALLSYMS=y
+# CONFIG_KALLSYMS_ALL is not set
# CONFIG_KALLSYMS_EXTRA_PASS is not set
CONFIG_HOTPLUG=y
CONFIG_PRINTK=y
CONFIG_BUG=y
# CONFIG_ELF_CORE is not set
+CONFIG_COMPAT_BRK=y
CONFIG_BASE_FULL=y
CONFIG_FUTEX=y
CONFIG_ANON_INODES=y
CONFIG_EPOLL=y
CONFIG_SIGNALFD=y
+CONFIG_TIMERFD=y
CONFIG_EVENTFD=y
+CONFIG_AIO=y
CONFIG_VM_EVENT_COUNTERS=y
CONFIG_SLAB=y
# CONFIG_SLUB is not set
# CONFIG_SLOB is not set
+# CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
+CONFIG_HAVE_OPROFILE=y
+# CONFIG_HAVE_GENERIC_DMA_COHERENT is not set
CONFIG_SLABINFO=y
CONFIG_RT_MUTEXES=y
CONFIG_TINY_SHMEM=y
CONFIG_BASE_SMALL=0
CONFIG_MODULES=y
+# CONFIG_MODULE_FORCE_LOAD is not set
CONFIG_MODULE_UNLOAD=y
# CONFIG_MODULE_FORCE_UNLOAD is not set
# CONFIG_MODVERSIONS is not set
@@ -82,6 +87,7 @@
# CONFIG_BLK_DEV_IO_TRACE is not set
# CONFIG_LSF is not set
# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_BLK_DEV_INTEGRITY is not set
#
# IO Schedulers
@@ -95,9 +101,11 @@
CONFIG_DEFAULT_CFQ=y
# CONFIG_DEFAULT_NOOP is not set
CONFIG_DEFAULT_IOSCHED="cfq"
+CONFIG_CLASSIC_RCU=y
# CONFIG_PREEMPT_NONE is not set
CONFIG_PREEMPT_VOLUNTARY=y
# CONFIG_PREEMPT is not set
+# CONFIG_FREEZER is not set
#
# Blackfin Processor Options
@@ -106,6 +114,10 @@
#
# Processor and Board Settings
#
+# CONFIG_BF512 is not set
+# CONFIG_BF514 is not set
+# CONFIG_BF516 is not set
+# CONFIG_BF518 is not set
# CONFIG_BF522 is not set
# CONFIG_BF523 is not set
# CONFIG_BF524 is not set
@@ -118,48 +130,32 @@
# CONFIG_BF534 is not set
# CONFIG_BF536 is not set
# CONFIG_BF537 is not set
+# CONFIG_BF538 is not set
+# CONFIG_BF539 is not set
# CONFIG_BF542 is not set
+# CONFIG_BF542M is not set
# CONFIG_BF544 is not set
+# CONFIG_BF544M is not set
# CONFIG_BF547 is not set
+# CONFIG_BF547M is not set
# CONFIG_BF548 is not set
+# CONFIG_BF548M is not set
# CONFIG_BF549 is not set
+# CONFIG_BF549M is not set
# CONFIG_BF561 is not set
+CONFIG_BF_REV_MIN=0
+CONFIG_BF_REV_MAX=2
# CONFIG_BF_REV_0_0 is not set
CONFIG_BF_REV_0_1=y
# CONFIG_BF_REV_0_2 is not set
# CONFIG_BF_REV_0_3 is not set
# CONFIG_BF_REV_0_4 is not set
# CONFIG_BF_REV_0_5 is not set
+# CONFIG_BF_REV_0_6 is not set
# CONFIG_BF_REV_ANY is not set
# CONFIG_BF_REV_NONE is not set
CONFIG_BF52x=y
CONFIG_MEM_MT48LC16M16A2TG_75=y
-# CONFIG_BFIN527_EZKIT is not set
-CONFIG_BFIN527_BLUETECHNIX_CM=y
-
-#
-# BF527 Specific Configuration
-#
-
-#
-# Alternative Multiplexing Scheme
-#
-# CONFIG_BF527_SPORT0_PORTF is not set
-CONFIG_BF527_SPORT0_PORTG=y
-CONFIG_BF527_SPORT0_TSCLK_PG10=y
-# CONFIG_BF527_SPORT0_TSCLK_PG14 is not set
-CONFIG_BF527_UART1_PORTF=y
-# CONFIG_BF527_UART1_PORTG is not set
-# CONFIG_BF527_NAND_D_PORTF is not set
-CONFIG_BF527_NAND_D_PORTH=y
-
-#
-# Interrupt Priority Assignment
-#
-
-#
-# Priority
-#
CONFIG_IRQ_PLL_WAKEUP=7
CONFIG_IRQ_DMA0_ERROR=7
CONFIG_IRQ_DMAR0_BLK=7
@@ -179,7 +175,6 @@
CONFIG_IRQ_SPORT1_RX=9
CONFIG_IRQ_SPORT1_TX=9
CONFIG_IRQ_TWI=10
-CONFIG_IRQ_SPI=10
CONFIG_IRQ_UART0_RX=10
CONFIG_IRQ_UART0_TX=10
CONFIG_IRQ_UART1_RX=10
@@ -205,6 +200,34 @@
CONFIG_IRQ_WATCH=13
CONFIG_IRQ_PORTF_INTA=13
CONFIG_IRQ_PORTF_INTB=13
+# CONFIG_BFIN527_EZKIT is not set
+CONFIG_BFIN527_BLUETECHNIX_CM=y
+# CONFIG_BFIN526_EZBRD is not set
+
+#
+# BF527 Specific Configuration
+#
+
+#
+# Alternative Multiplexing Scheme
+#
+# CONFIG_BF527_SPORT0_PORTF is not set
+CONFIG_BF527_SPORT0_PORTG=y
+CONFIG_BF527_SPORT0_TSCLK_PG10=y
+# CONFIG_BF527_SPORT0_TSCLK_PG14 is not set
+CONFIG_BF527_UART1_PORTF=y
+# CONFIG_BF527_UART1_PORTG is not set
+# CONFIG_BF527_NAND_D_PORTF is not set
+CONFIG_BF527_NAND_D_PORTH=y
+
+#
+# Interrupt Priority Assignment
+#
+
+#
+# Priority
+#
+CONFIG_IRQ_SPI=10
CONFIG_IRQ_SPI_ERROR=7
CONFIG_IRQ_NFC_ERROR=7
CONFIG_IRQ_HDMA_ERROR=7
@@ -226,7 +249,6 @@
#
CONFIG_CLKIN_HZ=25000000
# CONFIG_BFIN_KERNEL_CLOCK is not set
-CONFIG_MAX_MEM_SIZE=512
CONFIG_MAX_VCO_HZ=600000000
CONFIG_MIN_VCO_HZ=50000000
CONFIG_MAX_SCLK_HZ=133333333
@@ -240,10 +262,10 @@
# CONFIG_HZ_300 is not set
# CONFIG_HZ_1000 is not set
CONFIG_HZ=250
+# CONFIG_SCHED_HRTICK is not set
CONFIG_GENERIC_TIME=y
CONFIG_GENERIC_CLOCKEVENTS=y
# CONFIG_CYCLES_CLOCKSOURCE is not set
-# CONFIG_TICK_ONESHOT is not set
# CONFIG_NO_HZ is not set
# CONFIG_HIGH_RES_TIMERS is not set
CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
@@ -277,6 +299,12 @@
CONFIG_CACHELINE_ALIGNED_L1=y
# CONFIG_SYSCALL_TAB_L1 is not set
# CONFIG_CPLB_SWITCH_TAB_L1 is not set
+CONFIG_APP_STACK_L1=y
+
+#
+# Speed Optimizations
+#
+CONFIG_BFIN_INS_LOWOVERHEAD=y
CONFIG_RAMKERNEL=y
# CONFIG_ROMKERNEL is not set
CONFIG_SELECT_MEMORY_MODEL=y
@@ -285,10 +313,10 @@
# CONFIG_SPARSEMEM_MANUAL is not set
CONFIG_FLATMEM=y
CONFIG_FLAT_NODE_MEM_MAP=y
-# CONFIG_SPARSEMEM_STATIC is not set
-# CONFIG_SPARSEMEM_VMEMMAP_ENABLE is not set
+CONFIG_PAGEFLAGS_EXTENDED=y
CONFIG_SPLIT_PTLOCK_CPUS=4
# CONFIG_RESOURCES_64BIT is not set
+# CONFIG_PHYS_ADDR_T_64BIT is not set
CONFIG_ZONE_DMA_FLAG=1
CONFIG_VIRT_TO_BUS=y
CONFIG_BFIN_GPTIMERS=y
@@ -334,7 +362,6 @@
#
# Bus options (PCI, PCMCIA, EISA, MCA, ISA)
#
-# CONFIG_PCI is not set
# CONFIG_ARCH_SUPPORTS_MSI is not set
# CONFIG_PCCARD is not set
@@ -345,25 +372,20 @@
CONFIG_BINFMT_FLAT=y
CONFIG_BINFMT_ZFLAT=y
# CONFIG_BINFMT_SHARED_FLAT is not set
+# CONFIG_HAVE_AOUT is not set
# CONFIG_BINFMT_MISC is not set
#
# Power management options
#
# CONFIG_PM is not set
-CONFIG_SUSPEND_UP_POSSIBLE=y
-# CONFIG_PM_BFIN_SLEEP_DEEPER is not set
-# CONFIG_PM_BFIN_SLEEP is not set
+CONFIG_ARCH_SUSPEND_POSSIBLE=y
# CONFIG_PM_WAKEUP_BY_GPIO is not set
#
# CPU Frequency scaling
#
# CONFIG_CPU_FREQ is not set
-
-#
-# Networking
-#
CONFIG_NET=y
#
@@ -376,6 +398,7 @@
# CONFIG_XFRM_USER is not set
# CONFIG_XFRM_SUB_POLICY is not set
# CONFIG_XFRM_MIGRATE is not set
+# CONFIG_XFRM_STATISTICS is not set
# CONFIG_NET_KEY is not set
CONFIG_INET=y
# CONFIG_IP_MULTICAST is not set
@@ -405,8 +428,6 @@
CONFIG_DEFAULT_TCP_CONG="cubic"
# CONFIG_TCP_MD5SIG is not set
# CONFIG_IPV6 is not set
-# CONFIG_INET6_XFRM_TUNNEL is not set
-# CONFIG_INET6_TUNNEL is not set
# CONFIG_NETLABEL is not set
# CONFIG_NETWORK_SECMARK is not set
# CONFIG_NETFILTER is not set
@@ -415,6 +436,7 @@
# CONFIG_TIPC is not set
# CONFIG_ATM is not set
# CONFIG_BRIDGE is not set
+# CONFIG_NET_DSA is not set
# CONFIG_VLAN_8021Q is not set
# CONFIG_DECNET is not set
# CONFIG_LLC2 is not set
@@ -431,14 +453,14 @@
#
# CONFIG_NET_PKTGEN is not set
# CONFIG_HAMRADIO is not set
+# CONFIG_CAN is not set
# CONFIG_IRDA is not set
# CONFIG_BT is not set
# CONFIG_AF_RXRPC is not set
-
-#
-# Wireless
-#
+# CONFIG_PHONET is not set
+CONFIG_WIRELESS=y
# CONFIG_CFG80211 is not set
+CONFIG_WIRELESS_OLD_REGULATORY=y
# CONFIG_WIRELESS_EXT is not set
# CONFIG_MAC80211 is not set
# CONFIG_IEEE80211 is not set
@@ -456,6 +478,8 @@
CONFIG_STANDALONE=y
CONFIG_PREVENT_FIRMWARE_BUILD=y
# CONFIG_FW_LOADER is not set
+# CONFIG_DEBUG_DRIVER is not set
+# CONFIG_DEBUG_DEVRES is not set
# CONFIG_SYS_HYPERVISOR is not set
# CONFIG_CONNECTOR is not set
CONFIG_MTD=y
@@ -464,6 +488,7 @@
CONFIG_MTD_PARTITIONS=y
# CONFIG_MTD_REDBOOT_PARTS is not set
# CONFIG_MTD_CMDLINE_PARTS is not set
+# CONFIG_MTD_AR7_PARTS is not set
#
# User Modules And Translation Layers
@@ -507,6 +532,7 @@
#
CONFIG_MTD_COMPLEX_MAPPINGS=y
# CONFIG_MTD_PHYSMAP is not set
+# CONFIG_MTD_GPIO_ADDR is not set
# CONFIG_MTD_UCLINUX is not set
# CONFIG_MTD_PLATRAM is not set
@@ -542,10 +568,12 @@
CONFIG_BLK_DEV_RAM=y
CONFIG_BLK_DEV_RAM_COUNT=16
CONFIG_BLK_DEV_RAM_SIZE=4096
-CONFIG_BLK_DEV_RAM_BLOCKSIZE=1024
+# CONFIG_BLK_DEV_XIP is not set
# CONFIG_CDROM_PKTCDVD is not set
# CONFIG_ATA_OVER_ETH is not set
+# CONFIG_BLK_DEV_HD is not set
# CONFIG_MISC_DEVICES is not set
+CONFIG_HAVE_IDE=y
# CONFIG_IDE is not set
#
@@ -558,7 +586,6 @@
# CONFIG_ATA is not set
# CONFIG_MD is not set
CONFIG_NETDEVICES=y
-# CONFIG_NETDEVICES_MULTIQUEUE is not set
# CONFIG_DUMMY is not set
# CONFIG_BONDING is not set
# CONFIG_MACVLAN is not set
@@ -579,6 +606,7 @@
# CONFIG_SMSC_PHY is not set
# CONFIG_BROADCOM_PHY is not set
# CONFIG_ICPLUS_PHY is not set
+# CONFIG_REALTEK_PHY is not set
# CONFIG_FIXED_PHY is not set
# CONFIG_MDIO_BITBANG is not set
CONFIG_NET_ETHERNET=y
@@ -591,11 +619,14 @@
# CONFIG_SMC91X is not set
# CONFIG_SMSC911X is not set
# CONFIG_DM9000 is not set
+# CONFIG_ENC28J60 is not set
# CONFIG_IBM_NEW_EMAC_ZMII is not set
# CONFIG_IBM_NEW_EMAC_RGMII is not set
# CONFIG_IBM_NEW_EMAC_TAH is not set
# CONFIG_IBM_NEW_EMAC_EMAC4 is not set
-# CONFIG_B44 is not set
+# CONFIG_IBM_NEW_EMAC_NO_FLOW_CTRL is not set
+# CONFIG_IBM_NEW_EMAC_MAL_CLR_ICINTSTAT is not set
+# CONFIG_IBM_NEW_EMAC_MAL_COMMON_ERR is not set
# CONFIG_NETDEV_1000 is not set
# CONFIG_NETDEV_10000 is not set
@@ -604,6 +635,7 @@
#
# CONFIG_WLAN_PRE80211 is not set
# CONFIG_WLAN_80211 is not set
+# CONFIG_IWLWIFI_LEDS is not set
#
# USB Network Adapters
@@ -616,7 +648,6 @@
# CONFIG_WAN is not set
# CONFIG_PPP is not set
# CONFIG_SLIP is not set
-# CONFIG_SHAPER is not set
# CONFIG_NETCONSOLE is not set
# CONFIG_NETPOLL is not set
# CONFIG_NET_POLL_CONTROLLER is not set
@@ -642,14 +673,15 @@
# CONFIG_BF5xx_PPIFCD is not set
# CONFIG_BFIN_SIMPLE_TIMER is not set
# CONFIG_BF5xx_PPI is not set
-CONFIG_BFIN_OTP=y
-# CONFIG_BFIN_OTP_WRITE_ENABLE is not set
+# CONFIG_BF5xx_EPPI is not set
# CONFIG_BFIN_SPORT is not set
# CONFIG_BFIN_TIMER_LATENCY is not set
# CONFIG_TWI_LCD is not set
+CONFIG_BFIN_DMA_INTERFACE=m
CONFIG_SIMPLE_GPIO=m
# CONFIG_VT is not set
# CONFIG_DEVKMEM is not set
+# CONFIG_BFIN_JTAG_COMM is not set
# CONFIG_SERIAL_NONSTANDARD is not set
#
@@ -673,6 +705,8 @@
# CONFIG_SERIAL_BFIN_SPORT is not set
CONFIG_UNIX98_PTYS=y
# CONFIG_LEGACY_PTYS is not set
+CONFIG_BFIN_OTP=y
+# CONFIG_BFIN_OTP_WRITE_ENABLE is not set
#
# CAN, the car bus and industrial fieldbus
@@ -680,44 +714,49 @@
# CONFIG_CAN4LINUX is not set
# CONFIG_IPMI_HANDLER is not set
# CONFIG_HW_RANDOM is not set
-# CONFIG_GEN_RTC is not set
# CONFIG_R3964 is not set
# CONFIG_RAW_DRIVER is not set
# CONFIG_TCG_TPM is not set
CONFIG_I2C=y
CONFIG_I2C_BOARDINFO=y
CONFIG_I2C_CHARDEV=m
-
-#
-# I2C Algorithms
-#
-# CONFIG_I2C_ALGOBIT is not set
-# CONFIG_I2C_ALGOPCF is not set
-# CONFIG_I2C_ALGOPCA is not set
+CONFIG_I2C_HELPER_AUTO=y
#
# I2C Hardware Bus support
#
+
+#
+# I2C system bus drivers (mostly embedded / system-on-chip)
+#
CONFIG_I2C_BLACKFIN_TWI=m
CONFIG_I2C_BLACKFIN_TWI_CLK_KHZ=100
# CONFIG_I2C_GPIO is not set
# CONFIG_I2C_OCORES is not set
-# CONFIG_I2C_PARPORT_LIGHT is not set
# CONFIG_I2C_SIMTEC is not set
+
+#
+# External I2C/SMBus adapter drivers
+#
+# CONFIG_I2C_PARPORT_LIGHT is not set
# CONFIG_I2C_TAOS_EVM is not set
-# CONFIG_I2C_STUB is not set
# CONFIG_I2C_TINY_USB is not set
#
+# Other I2C/SMBus bus drivers
+#
+# CONFIG_I2C_PCA_PLATFORM is not set
+# CONFIG_I2C_STUB is not set
+
+#
# Miscellaneous I2C Chip support
#
-# CONFIG_SENSORS_DS1337 is not set
-# CONFIG_SENSORS_DS1374 is not set
# CONFIG_DS1682 is not set
+# CONFIG_AT24 is not set
# CONFIG_SENSORS_AD5252 is not set
-# CONFIG_EEPROM_LEGACY is not set
+# CONFIG_SENSORS_EEPROM is not set
# CONFIG_SENSORS_PCF8574 is not set
-# CONFIG_SENSORS_PCF8575 is not set
+# CONFIG_PCF8575 is not set
# CONFIG_SENSORS_PCA9539 is not set
# CONFIG_SENSORS_PCF8591 is not set
# CONFIG_SENSORS_MAX6875 is not set
@@ -726,37 +765,41 @@
# CONFIG_I2C_DEBUG_ALGO is not set
# CONFIG_I2C_DEBUG_BUS is not set
# CONFIG_I2C_DEBUG_CHIP is not set
-
-#
-# SPI support
-#
CONFIG_SPI=y
+# CONFIG_SPI_DEBUG is not set
CONFIG_SPI_MASTER=y
#
# SPI Master Controller Drivers
#
CONFIG_SPI_BFIN=y
+# CONFIG_SPI_BFIN_LOCK is not set
# CONFIG_SPI_BITBANG is not set
#
# SPI Protocol Masters
#
-# CONFIG_EEPROM_AT25 is not set
+# CONFIG_SPI_AT25 is not set
# CONFIG_SPI_SPIDEV is not set
# CONFIG_SPI_TLE62X0 is not set
+CONFIG_ARCH_WANT_OPTIONAL_GPIOLIB=y
+# CONFIG_GPIOLIB is not set
# CONFIG_W1 is not set
# CONFIG_POWER_SUPPLY is not set
CONFIG_HWMON=y
# CONFIG_HWMON_VID is not set
+# CONFIG_SENSORS_AD7414 is not set
# CONFIG_SENSORS_AD7418 is not set
+# CONFIG_SENSORS_ADCXX is not set
# CONFIG_SENSORS_ADM1021 is not set
# CONFIG_SENSORS_ADM1025 is not set
# CONFIG_SENSORS_ADM1026 is not set
# CONFIG_SENSORS_ADM1029 is not set
# CONFIG_SENSORS_ADM1031 is not set
# CONFIG_SENSORS_ADM9240 is not set
+# CONFIG_SENSORS_ADT7462 is not set
# CONFIG_SENSORS_ADT7470 is not set
+# CONFIG_SENSORS_ADT7473 is not set
# CONFIG_SENSORS_ATXP1 is not set
# CONFIG_SENSORS_DS1621 is not set
# CONFIG_SENSORS_F71805F is not set
@@ -777,6 +820,7 @@
# CONFIG_SENSORS_LM90 is not set
# CONFIG_SENSORS_LM92 is not set
# CONFIG_SENSORS_LM93 is not set
+# CONFIG_SENSORS_MAX1111 is not set
# CONFIG_SENSORS_MAX1619 is not set
# CONFIG_SENSORS_MAX6650 is not set
# CONFIG_SENSORS_PC87360 is not set
@@ -785,6 +829,7 @@
# CONFIG_SENSORS_SMSC47M1 is not set
# CONFIG_SENSORS_SMSC47M192 is not set
# CONFIG_SENSORS_SMSC47B397 is not set
+# CONFIG_SENSORS_ADS7828 is not set
# CONFIG_SENSORS_THMC50 is not set
# CONFIG_SENSORS_VT1211 is not set
# CONFIG_SENSORS_W83781D is not set
@@ -792,9 +837,12 @@
# CONFIG_SENSORS_W83792D is not set
# CONFIG_SENSORS_W83793 is not set
# CONFIG_SENSORS_W83L785TS is not set
+# CONFIG_SENSORS_W83L786NG is not set
# CONFIG_SENSORS_W83627HF is not set
# CONFIG_SENSORS_W83627EHF is not set
# CONFIG_HWMON_DEBUG_CHIP is not set
+# CONFIG_THERMAL is not set
+# CONFIG_THERMAL_HWMON is not set
CONFIG_WATCHDOG=y
# CONFIG_WATCHDOG_NOWAYOUT is not set
@@ -810,21 +858,31 @@
# CONFIG_USBPCWATCHDOG is not set
#
-# Sonics Silicon Backplane
-#
-CONFIG_SSB_POSSIBLE=y
-# CONFIG_SSB is not set
-
-#
# Multifunction device drivers
#
+# CONFIG_MFD_CORE is not set
# CONFIG_MFD_SM501 is not set
+# CONFIG_HTC_PASIC3 is not set
+# CONFIG_MFD_TMIO is not set
+# CONFIG_PMIC_DA903X is not set
+# CONFIG_MFD_WM8400 is not set
+# CONFIG_MFD_WM8350_I2C is not set
+# CONFIG_REGULATOR is not set
#
# Multimedia devices
#
+
+#
+# Multimedia core support
+#
# CONFIG_VIDEO_DEV is not set
# CONFIG_DVB_CORE is not set
+# CONFIG_VIDEO_MEDIA is not set
+
+#
+# Multimedia drivers
+#
# CONFIG_DAB is not set
#
@@ -839,10 +897,6 @@
# Display device support
#
# CONFIG_DISPLAY_SUPPORT is not set
-
-#
-# Sound
-#
# CONFIG_SOUND is not set
CONFIG_USB_SUPPORT=y
CONFIG_USB_ARCH_HAS_HCD=y
@@ -850,6 +904,7 @@
# CONFIG_USB_ARCH_HAS_EHCI is not set
CONFIG_USB=y
# CONFIG_USB_DEBUG is not set
+# CONFIG_USB_ANNOUNCE_NEW_DEVICES is not set
#
# Miscellaneous USB options
@@ -860,40 +915,48 @@
# CONFIG_USB_OTG is not set
# CONFIG_USB_OTG_WHITELIST is not set
CONFIG_USB_OTG_BLACKLIST_HUB=y
+CONFIG_USB_MON=y
+# CONFIG_USB_WUSB is not set
+# CONFIG_USB_WUSB_CBAF is not set
#
# USB Host Controller Drivers
#
+# CONFIG_USB_C67X00_HCD is not set
# CONFIG_USB_ISP116X_HCD is not set
-# CONFIG_USB_ISP1362_HCD is not set
# CONFIG_USB_ISP1760_HCD is not set
+# CONFIG_USB_ISP1362_HCD is not set
# CONFIG_USB_SL811_HCD is not set
# CONFIG_USB_R8A66597_HCD is not set
+# CONFIG_USB_HWA_HCD is not set
CONFIG_USB_MUSB_HDRC=y
CONFIG_USB_MUSB_SOC=y
#
-# Blackfin high speed USB support
+# Blackfin high speed USB Support
#
CONFIG_USB_MUSB_HOST=y
# CONFIG_USB_MUSB_PERIPHERAL is not set
# CONFIG_USB_MUSB_OTG is not set
CONFIG_USB_MUSB_HDRC_HCD=y
CONFIG_MUSB_PIO_ONLY=y
-CONFIG_USB_MUSB_LOGLEVEL=0
+CONFIG_MUSB_DMA_POLL=y
+# CONFIG_USB_MUSB_DEBUG is not set
#
# USB Device Class drivers
#
# CONFIG_USB_ACM is not set
# CONFIG_USB_PRINTER is not set
+# CONFIG_USB_WDM is not set
+# CONFIG_USB_TMC is not set
#
-# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support'
+# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may also be needed;
#
#
-# may also be needed; see USB_STORAGE Help for more information
+# see USB_STORAGE Help for more information
#
# CONFIG_USB_LIBUSUAL is not set
@@ -901,15 +964,10 @@
# USB Imaging devices
#
# CONFIG_USB_MDC800 is not set
-CONFIG_USB_MON=y
#
# USB port drivers
#
-
-#
-# USB Serial Converter support
-#
# CONFIG_USB_SERIAL is not set
#
@@ -918,7 +976,7 @@
# CONFIG_USB_EMI62 is not set
# CONFIG_USB_EMI26 is not set
# CONFIG_USB_ADUTUX is not set
-# CONFIG_USB_AUERSWALD is not set
+# CONFIG_USB_SEVSEG is not set
# CONFIG_USB_RIO500 is not set
# CONFIG_USB_LEGOTOWER is not set
# CONFIG_USB_LCD is not set
@@ -934,17 +992,13 @@
# CONFIG_USB_LD is not set
# CONFIG_USB_TRANCEVIBRATOR is not set
# CONFIG_USB_IOWARRIOR is not set
-
-#
-# USB DSL modem support
-#
-
-#
-# USB Gadget Support
-#
+# CONFIG_USB_ISIGHTFW is not set
+# CONFIG_USB_VST is not set
# CONFIG_USB_GADGET is not set
# CONFIG_MMC is not set
+# CONFIG_MEMSTICK is not set
# CONFIG_NEW_LEDS is not set
+# CONFIG_ACCESSIBILITY is not set
CONFIG_RTC_LIB=y
CONFIG_RTC_CLASS=y
CONFIG_RTC_HCTOSYS=y
@@ -973,51 +1027,59 @@
# CONFIG_RTC_DRV_PCF8563 is not set
# CONFIG_RTC_DRV_PCF8583 is not set
# CONFIG_RTC_DRV_M41T80 is not set
+# CONFIG_RTC_DRV_S35390A is not set
+# CONFIG_RTC_DRV_FM3130 is not set
+# CONFIG_RTC_DRV_RX8581 is not set
#
# SPI RTC drivers
#
-# CONFIG_RTC_DRV_RS5C348 is not set
+# CONFIG_RTC_DRV_M41T94 is not set
+# CONFIG_RTC_DRV_DS1305 is not set
+# CONFIG_RTC_DRV_DS1390 is not set
# CONFIG_RTC_DRV_MAX6902 is not set
+# CONFIG_RTC_DRV_R9701 is not set
+# CONFIG_RTC_DRV_RS5C348 is not set
+# CONFIG_RTC_DRV_DS3234 is not set
#
# Platform RTC drivers
#
+# CONFIG_RTC_DRV_DS1286 is not set
+# CONFIG_RTC_DRV_DS1511 is not set
# CONFIG_RTC_DRV_DS1553 is not set
-# CONFIG_RTC_DRV_STK17TA8 is not set
# CONFIG_RTC_DRV_DS1742 is not set
+# CONFIG_RTC_DRV_STK17TA8 is not set
# CONFIG_RTC_DRV_M48T86 is not set
+# CONFIG_RTC_DRV_M48T35 is not set
# CONFIG_RTC_DRV_M48T59 is not set
+# CONFIG_RTC_DRV_BQ4802 is not set
# CONFIG_RTC_DRV_V3020 is not set
#
# on-CPU RTC drivers
#
CONFIG_RTC_DRV_BFIN=y
-
-#
-# Userspace I/O
-#
+# CONFIG_DMADEVICES is not set
# CONFIG_UIO is not set
+# CONFIG_STAGING is not set
#
# File systems
#
# CONFIG_EXT2_FS is not set
# CONFIG_EXT3_FS is not set
-# CONFIG_EXT4DEV_FS is not set
+# CONFIG_EXT4_FS is not set
# CONFIG_REISERFS_FS is not set
# CONFIG_JFS_FS is not set
# CONFIG_FS_POSIX_ACL is not set
+CONFIG_FILE_LOCKING=y
# CONFIG_XFS_FS is not set
-# CONFIG_GFS2_FS is not set
# CONFIG_OCFS2_FS is not set
-# CONFIG_MINIX_FS is not set
-# CONFIG_ROMFS_FS is not set
+# CONFIG_DNOTIFY is not set
CONFIG_INOTIFY=y
CONFIG_INOTIFY_USER=y
# CONFIG_QUOTA is not set
-# CONFIG_DNOTIFY is not set
# CONFIG_AUTOFS_FS is not set
# CONFIG_AUTOFS4_FS is not set
# CONFIG_FUSE_FS is not set
@@ -1059,8 +1121,11 @@
# CONFIG_JFFS2_FS is not set
# CONFIG_CRAMFS is not set
# CONFIG_VXFS_FS is not set
+# CONFIG_MINIX_FS is not set
+# CONFIG_OMFS_FS is not set
# CONFIG_HPFS_FS is not set
# CONFIG_QNX4FS_FS is not set
+# CONFIG_ROMFS_FS is not set
# CONFIG_SYSV_FS is not set
# CONFIG_UFS_FS is not set
CONFIG_NETWORK_FILESYSTEMS=y
@@ -1068,13 +1133,12 @@
CONFIG_NFS_V3=y
# CONFIG_NFS_V3_ACL is not set
# CONFIG_NFS_V4 is not set
-# CONFIG_NFS_DIRECTIO is not set
# CONFIG_NFSD is not set
CONFIG_LOCKD=m
CONFIG_LOCKD_V4=y
CONFIG_NFS_COMMON=y
CONFIG_SUNRPC=m
-# CONFIG_SUNRPC_BIND34 is not set
+# CONFIG_SUNRPC_REGISTER_V4 is not set
# CONFIG_RPCSEC_GSS_KRB5 is not set
# CONFIG_RPCSEC_GSS_SPKM3 is not set
CONFIG_SMB_FS=m
@@ -1130,7 +1194,6 @@
# CONFIG_NLS_KOI8_U is not set
# CONFIG_NLS_UTF8 is not set
# CONFIG_DLM is not set
-# CONFIG_INSTRUMENTATION is not set
#
# Kernel hacking
@@ -1138,14 +1201,61 @@
# CONFIG_PRINTK_TIME is not set
CONFIG_ENABLE_WARN_DEPRECATED=y
CONFIG_ENABLE_MUST_CHECK=y
+CONFIG_FRAME_WARN=1024
# CONFIG_MAGIC_SYSRQ is not set
# CONFIG_UNUSED_SYMBOLS is not set
CONFIG_DEBUG_FS=y
# CONFIG_HEADERS_CHECK is not set
-# CONFIG_DEBUG_KERNEL is not set
+CONFIG_DEBUG_KERNEL=y
+# CONFIG_DEBUG_SHIRQ is not set
+CONFIG_DETECT_SOFTLOCKUP=y
+# CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set
+CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE=0
+# CONFIG_SCHED_DEBUG is not set
+# CONFIG_SCHEDSTATS is not set
+# CONFIG_TIMER_STATS is not set
+# CONFIG_DEBUG_OBJECTS is not set
+# CONFIG_DEBUG_SLAB is not set
+# CONFIG_DEBUG_RT_MUTEXES is not set
+# CONFIG_RT_MUTEX_TESTER is not set
+# CONFIG_DEBUG_SPINLOCK is not set
+# CONFIG_DEBUG_MUTEXES is not set
+# CONFIG_DEBUG_SPINLOCK_SLEEP is not set
+# CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set
+# CONFIG_DEBUG_KOBJECT is not set
# CONFIG_DEBUG_BUGVERBOSE is not set
+# CONFIG_DEBUG_INFO is not set
+# CONFIG_DEBUG_VM is not set
+# CONFIG_DEBUG_WRITECOUNT is not set
+# CONFIG_DEBUG_MEMORY_INIT is not set
+# CONFIG_DEBUG_LIST is not set
+# CONFIG_DEBUG_SG is not set
+# CONFIG_FRAME_POINTER is not set
+# CONFIG_BOOT_PRINTK_DELAY is not set
+# CONFIG_RCU_TORTURE_TEST is not set
+# CONFIG_RCU_CPU_STALL_DETECTOR is not set
+# CONFIG_BACKTRACE_SELF_TEST is not set
+# CONFIG_DEBUG_BLOCK_EXT_DEVT is not set
+# CONFIG_FAULT_INJECTION is not set
+# CONFIG_SYSCTL_SYSCALL_CHECK is not set
+
+#
+# Tracers
+#
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_DYNAMIC_PRINTK_DEBUG is not set
# CONFIG_SAMPLES is not set
+CONFIG_HAVE_ARCH_KGDB=y
+# CONFIG_KGDB is not set
+# CONFIG_DEBUG_STACKOVERFLOW is not set
+# CONFIG_DEBUG_STACK_USAGE is not set
+# CONFIG_KGDB_TESTCASE is not set
+CONFIG_DEBUG_VERBOSE=y
CONFIG_DEBUG_MMRS=y
+# CONFIG_DEBUG_HWERR is not set
+# CONFIG_DEBUG_DOUBLEFAULT is not set
CONFIG_DEBUG_HUNT_FOR_ZERO=y
CONFIG_DEBUG_BFIN_HWTRACE_ON=y
CONFIG_DEBUG_BFIN_HWTRACE_COMPRESSION_OFF=y
@@ -1154,7 +1264,7 @@
CONFIG_DEBUG_BFIN_HWTRACE_COMPRESSION=0
# CONFIG_DEBUG_BFIN_HWTRACE_EXPAND is not set
# CONFIG_DEBUG_BFIN_NO_KERN_HWTRACE is not set
-CONFIG_EARLY_PRINTK=y
+# CONFIG_EARLY_PRINTK is not set
# CONFIG_CPLB_INFO is not set
CONFIG_ACCESS_CHECK=y
@@ -1163,10 +1273,96 @@
#
# CONFIG_KEYS is not set
CONFIG_SECURITY=y
+# CONFIG_SECURITYFS is not set
# CONFIG_SECURITY_NETWORK is not set
-# CONFIG_SECURITY_CAPABILITIES is not set
+# CONFIG_SECURITY_FILE_CAPABILITIES is not set
# CONFIG_SECURITY_ROOTPLUG is not set
-# CONFIG_CRYPTO is not set
+CONFIG_SECURITY_DEFAULT_MMAP_MIN_ADDR=0
+CONFIG_CRYPTO=y
+
+#
+# Crypto core or helper
+#
+# CONFIG_CRYPTO_FIPS is not set
+# CONFIG_CRYPTO_MANAGER is not set
+# CONFIG_CRYPTO_MANAGER2 is not set
+# CONFIG_CRYPTO_GF128MUL is not set
+# CONFIG_CRYPTO_NULL is not set
+# CONFIG_CRYPTO_CRYPTD is not set
+# CONFIG_CRYPTO_AUTHENC is not set
+# CONFIG_CRYPTO_TEST is not set
+
+#
+# Authenticated Encryption with Associated Data
+#
+# CONFIG_CRYPTO_CCM is not set
+# CONFIG_CRYPTO_GCM is not set
+# CONFIG_CRYPTO_SEQIV is not set
+
+#
+# Block modes
+#
+# CONFIG_CRYPTO_CBC is not set
+# CONFIG_CRYPTO_CTR is not set
+# CONFIG_CRYPTO_CTS is not set
+# CONFIG_CRYPTO_ECB is not set
+# CONFIG_CRYPTO_LRW is not set
+# CONFIG_CRYPTO_PCBC is not set
+# CONFIG_CRYPTO_XTS is not set
+
+#
+# Hash modes
+#
+# CONFIG_CRYPTO_HMAC is not set
+# CONFIG_CRYPTO_XCBC is not set
+
+#
+# Digest
+#
+# CONFIG_CRYPTO_CRC32C is not set
+# CONFIG_CRYPTO_MD4 is not set
+# CONFIG_CRYPTO_MD5 is not set
+# CONFIG_CRYPTO_MICHAEL_MIC is not set
+# CONFIG_CRYPTO_RMD128 is not set
+# CONFIG_CRYPTO_RMD160 is not set
+# CONFIG_CRYPTO_RMD256 is not set
+# CONFIG_CRYPTO_RMD320 is not set
+# CONFIG_CRYPTO_SHA1 is not set
+# CONFIG_CRYPTO_SHA256 is not set
+# CONFIG_CRYPTO_SHA512 is not set
+# CONFIG_CRYPTO_TGR192 is not set
+# CONFIG_CRYPTO_WP512 is not set
+
+#
+# Ciphers
+#
+# CONFIG_CRYPTO_AES is not set
+# CONFIG_CRYPTO_ANUBIS is not set
+# CONFIG_CRYPTO_ARC4 is not set
+# CONFIG_CRYPTO_BLOWFISH is not set
+# CONFIG_CRYPTO_CAMELLIA is not set
+# CONFIG_CRYPTO_CAST5 is not set
+# CONFIG_CRYPTO_CAST6 is not set
+# CONFIG_CRYPTO_DES is not set
+# CONFIG_CRYPTO_FCRYPT is not set
+# CONFIG_CRYPTO_KHAZAD is not set
+# CONFIG_CRYPTO_SALSA20 is not set
+# CONFIG_CRYPTO_SEED is not set
+# CONFIG_CRYPTO_SERPENT is not set
+# CONFIG_CRYPTO_TEA is not set
+# CONFIG_CRYPTO_TWOFISH is not set
+
+#
+# Compression
+#
+# CONFIG_CRYPTO_DEFLATE is not set
+# CONFIG_CRYPTO_LZO is not set
+
+#
+# Random Number Generation
+#
+# CONFIG_CRYPTO_ANSI_CPRNG is not set
+CONFIG_CRYPTO_HW=y
#
# Library routines
@@ -1174,6 +1370,7 @@
CONFIG_BITREVERSE=y
CONFIG_CRC_CCITT=m
# CONFIG_CRC16 is not set
+# CONFIG_CRC_T10DIF is not set
# CONFIG_CRC_ITU_T is not set
CONFIG_CRC32=y
# CONFIG_CRC7 is not set
diff --git a/arch/blackfin/include/asm/checksum.h b/arch/blackfin/include/asm/checksum.h
index f67289a..793581f 100644
--- a/arch/blackfin/include/asm/checksum.h
+++ b/arch/blackfin/include/asm/checksum.h
@@ -63,23 +63,23 @@
csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
unsigned short proto, __wsum sum)
{
+ unsigned int carry;
- __asm__ ("%0 = %0 + %1;\n\t"
- "CC = AC0;\n\t"
- "if !CC jump 4;\n\t"
- "%0 = %0 + %4;\n\t"
- "%0 = %0 + %2;\n\t"
- "CC = AC0;\n\t"
- "if !CC jump 4;\n\t"
- "%0 = %0 + %4;\n\t"
- "%0 = %0 + %3;\n\t"
- "CC = AC0;\n\t"
- "if !CC jump 4;\n\t"
- "%0 = %0 + %4;\n\t"
- "NOP;\n\t"
- : "=d" (sum)
- : "d" (daddr), "d" (saddr), "d" ((ntohs(len)<<16)+proto*256), "d" (1), "0"(sum)
- : "CC");
+ __asm__ ("%0 = %0 + %2;\n\t"
+ "CC = AC0;\n\t"
+ "%1 = CC;\n\t"
+ "%0 = %0 + %1;\n\t"
+ "%0 = %0 + %3;\n\t"
+ "CC = AC0;\n\t"
+ "%1 = CC;\n\t"
+ "%0 = %0 + %1;\n\t"
+ "%0 = %0 + %4;\n\t"
+ "CC = AC0;\n\t"
+ "%1 = CC;\n\t"
+ "%0 = %0 + %1;\n\t"
+ : "=d" (sum), "=&d" (carry)
+ : "d" (daddr), "d" (saddr), "d" ((len + proto) << 8), "0"(sum)
+ : "CC");
return (sum);
}
diff --git a/arch/blackfin/include/asm/delay.h b/arch/blackfin/include/asm/delay.h
index 0889c3a..c31f91c 100644
--- a/arch/blackfin/include/asm/delay.h
+++ b/arch/blackfin/include/asm/delay.h
@@ -13,29 +13,7 @@
static inline void __delay(unsigned long loops)
{
- if (ANOMALY_05000312) {
- /* Interrupted loads to loop registers -> bad */
- unsigned long tmp;
- __asm__ __volatile__(
- "[--SP] = LC0;"
- "[--SP] = LT0;"
- "[--SP] = LB0;"
- "LSETUP (1f,1f) LC0 = %1;"
- "1: NOP;"
- /* We take advantage of the fact that LC0 is 0 at
- * the end of the loop. Otherwise we'd need some
- * NOPs after the CLI here.
- */
- "CLI %0;"
- "LB0 = [SP++];"
- "LT0 = [SP++];"
- "LC0 = [SP++];"
- "STI %0;"
- : "=d" (tmp)
- : "a" (loops)
- );
- } else
- __asm__ __volatile__ (
+__asm__ __volatile__ (
"LSETUP(1f, 1f) LC0 = %0;"
"1: NOP;"
:
@@ -47,16 +25,15 @@
#include <linux/param.h> /* needed for HZ */
/*
- * Use only for very small delays ( < 1 msec). Should probably use a
- * lookup table, really, as the multiplications take much too long with
- * short delays. This is a "reasonable" implementation, though (and the
- * first constant multiplications gets optimized away if the delay is
- * a constant)
+ * close approximation borrowed from m68knommu to avoid 64-bit math
*/
+
+#define HZSCALE (268435456 / (1000000/HZ))
+
static inline void udelay(unsigned long usecs)
{
extern unsigned long loops_per_jiffy;
- __delay(usecs * loops_per_jiffy / (1000000 / HZ));
+ __delay((((usecs * HZSCALE) >> 11) * (loops_per_jiffy >> 11)) >> 6);
}
#endif
diff --git a/arch/blackfin/include/asm/gpio.h b/arch/blackfin/include/asm/gpio.h
index 9477d82..d4a082ef 100644
--- a/arch/blackfin/include/asm/gpio.h
+++ b/arch/blackfin/include/asm/gpio.h
@@ -27,60 +27,6 @@
* 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
-/*
-* Number BF537/6/4 BF561 BF533/2/1
-* BF527/5/2
-*
-* GPIO_0 PF0 PF0 PF0
-* GPIO_1 PF1 PF1 PF1
-* GPIO_2 PF2 PF2 PF2
-* GPIO_3 PF3 PF3 PF3
-* GPIO_4 PF4 PF4 PF4
-* GPIO_5 PF5 PF5 PF5
-* GPIO_6 PF6 PF6 PF6
-* GPIO_7 PF7 PF7 PF7
-* GPIO_8 PF8 PF8 PF8
-* GPIO_9 PF9 PF9 PF9
-* GPIO_10 PF10 PF10 PF10
-* GPIO_11 PF11 PF11 PF11
-* GPIO_12 PF12 PF12 PF12
-* GPIO_13 PF13 PF13 PF13
-* GPIO_14 PF14 PF14 PF14
-* GPIO_15 PF15 PF15 PF15
-* GPIO_16 PG0 PF16
-* GPIO_17 PG1 PF17
-* GPIO_18 PG2 PF18
-* GPIO_19 PG3 PF19
-* GPIO_20 PG4 PF20
-* GPIO_21 PG5 PF21
-* GPIO_22 PG6 PF22
-* GPIO_23 PG7 PF23
-* GPIO_24 PG8 PF24
-* GPIO_25 PG9 PF25
-* GPIO_26 PG10 PF26
-* GPIO_27 PG11 PF27
-* GPIO_28 PG12 PF28
-* GPIO_29 PG13 PF29
-* GPIO_30 PG14 PF30
-* GPIO_31 PG15 PF31
-* GPIO_32 PH0 PF32
-* GPIO_33 PH1 PF33
-* GPIO_34 PH2 PF34
-* GPIO_35 PH3 PF35
-* GPIO_36 PH4 PF36
-* GPIO_37 PH5 PF37
-* GPIO_38 PH6 PF38
-* GPIO_39 PH7 PF39
-* GPIO_40 PH8 PF40
-* GPIO_41 PH9 PF41
-* GPIO_42 PH10 PF42
-* GPIO_43 PH11 PF43
-* GPIO_44 PH12 PF44
-* GPIO_45 PH13 PF45
-* GPIO_46 PH14 PF46
-* GPIO_47 PH15 PF47
-*/
-
#ifndef __ARCH_BLACKFIN_GPIO_H__
#define __ARCH_BLACKFIN_GPIO_H__
@@ -295,10 +241,6 @@
int bfin_gpio_get_value(unsigned gpio);
void bfin_gpio_set_value(unsigned gpio, int value);
-#ifndef BF548_FAMILY
-#define bfin_gpio_set_value(gpio, value) set_gpio_data(gpio, value)
-#endif
-
#ifdef CONFIG_GPIOLIB
#include <asm-generic/gpio.h> /* cansleep wrappers */
diff --git a/arch/blackfin/include/asm/kgdb.h b/arch/blackfin/include/asm/kgdb.h
index 26ebac6..c8b256d 100644
--- a/arch/blackfin/include/asm/kgdb.h
+++ b/arch/blackfin/include/asm/kgdb.h
@@ -1,32 +1,8 @@
-/*
- * File: include/asm-blackfin/kgdb.h
- * Based on:
- * Author: Sonic Zhang
+/* Blackfin KGDB header
*
- * Created:
- * Description:
+ * Copyright 2005-2009 Analog Devices Inc.
*
- * Rev: $Id: kgdb_bfin_linux-2.6.x.patch 4934 2007-02-13 09:32:11Z sonicz $
- *
- * Modified:
- * Copyright 2005-2006 Analog Devices Inc.
- *
- * Bugs: Enter bugs at http://blackfin.uclinux.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, see the file COPYING, or write
- * to the Free Software Foundation, Inc.,
- * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ * Licensed under the GPL-2 or later.
*/
#ifndef __ASM_BLACKFIN_KGDB_H__
@@ -37,17 +13,18 @@
/* gdb locks */
#define KGDB_MAX_NO_CPUS 8
-/************************************************************************/
-/* BUFMAX defines the maximum number of characters in inbound/outbound buffers*/
-/* at least NUMREGBYTES*2 are needed for register packets */
-/* Longer buffer is needed to list all threads */
+/*
+ * BUFMAX defines the maximum number of characters in inbound/outbound buffers.
+ * At least NUMREGBYTES*2 are needed for register packets.
+ * Longer buffer is needed to list all threads.
+ */
#define BUFMAX 2048
/*
- * Note that this register image is different from
- * the register image that Linux produces at interrupt time.
- *
- * Linux's register image is defined by struct pt_regs in ptrace.h.
+ * Note that this register image is different from
+ * the register image that Linux produces at interrupt time.
+ *
+ * Linux's register image is defined by struct pt_regs in ptrace.h.
*/
enum regnames {
/* Core Registers */
@@ -104,14 +81,14 @@
BFIN_RETX,
BFIN_RETN,
BFIN_RETE,
-
+
/* Pseudo Registers */
BFIN_PC,
BFIN_CC,
BFIN_EXTRA1, /* Address of .text section. */
BFIN_EXTRA2, /* Address of .data section. */
BFIN_EXTRA3, /* Address of .bss section. */
- BFIN_FDPIC_EXEC,
+ BFIN_FDPIC_EXEC,
BFIN_FDPIC_INTERP,
/* MMRs */
@@ -126,7 +103,7 @@
static inline void arch_kgdb_breakpoint(void)
{
- asm(" EXCPT 2;");
+ asm("EXCPT 2;");
}
#define BREAK_INSTR_SIZE 2
#define CACHE_FLUSH_IS_SAFE 1
diff --git a/arch/blackfin/include/asm/mem_init.h b/arch/blackfin/include/asm/mem_init.h
index 255a931..61f7487 100644
--- a/arch/blackfin/include/asm/mem_init.h
+++ b/arch/blackfin/include/asm/mem_init.h
@@ -115,7 +115,7 @@
#define mem_SDRRC (((CONFIG_SCLK_HZ / 1000) * SDRAM_Tref) / SDRAM_NRA) - (SDRAM_tRAS_num + SDRAM_tRP_num)
/* Enable SCLK Out */
-#define mem_SDGCTL (0x80000000 | SCTLE | SDRAM_CL | SDRAM_tRAS | SDRAM_tRP | SDRAM_tRCD | SDRAM_tWR | PSS)
+#define mem_SDGCTL (SCTLE | SDRAM_CL | SDRAM_tRAS | SDRAM_tRP | SDRAM_tRCD | SDRAM_tWR | PSS)
#else
#define mem_SDRRC CONFIG_MEM_SDRRC
#define mem_SDGCTL CONFIG_MEM_SDGCTL
diff --git a/arch/blackfin/include/asm/pda.h b/arch/blackfin/include/asm/pda.h
index bd8d4a7..a671427 100644
--- a/arch/blackfin/include/asm/pda.h
+++ b/arch/blackfin/include/asm/pda.h
@@ -59,6 +59,7 @@
unsigned long icplb_fault_addr;
unsigned long retx;
unsigned long seqstat;
+ unsigned int __nmi_count; /* number of times NMI asserted on this CPU */
};
extern struct blackfin_pda cpu_pda[];
diff --git a/arch/blackfin/include/asm/reboot.h b/arch/blackfin/include/asm/reboot.h
index 4856d62..ae1e363 100644
--- a/arch/blackfin/include/asm/reboot.h
+++ b/arch/blackfin/include/asm/reboot.h
@@ -15,6 +15,6 @@
extern void native_machine_power_off(void);
/* common reboot workarounds */
-extern void bfin_gpio_reset_spi0_ssel1(void);
+extern void bfin_reset_boot_spi_cs(unsigned short pin);
#endif
diff --git a/arch/blackfin/kernel/Makefile b/arch/blackfin/kernel/Makefile
index 38a2333..4a92a86 100644
--- a/arch/blackfin/kernel/Makefile
+++ b/arch/blackfin/kernel/Makefile
@@ -15,6 +15,8 @@
obj-y += time.o
endif
+CFLAGS_kgdb_test.o := -mlong-calls -O0
+
obj-$(CONFIG_IPIPE) += ipipe.o
obj-$(CONFIG_IPIPE_TRACE_MCOUNT) += mcount.o
obj-$(CONFIG_BFIN_GPTIMERS) += gptimers.o
diff --git a/arch/blackfin/kernel/bfin_dma_5xx.c b/arch/blackfin/kernel/bfin_dma_5xx.c
index 07e02c0..8531693 100644
--- a/arch/blackfin/kernel/bfin_dma_5xx.c
+++ b/arch/blackfin/kernel/bfin_dma_5xx.c
@@ -249,6 +249,13 @@
spin_lock_irqsave(&mdma_lock, flags);
+ /* Force a sync in case a previous config reset on this channel
+ * occurred. This is needed so subsequent writes to DMA registers
+ * are not spuriously lost/corrupted. Do it under irq lock and
+ * without the anomaly version (because we are atomic already).
+ */
+ __builtin_bfin_ssync();
+
if (bfin_read_MDMA_S0_CONFIG())
while (!(bfin_read_MDMA_D0_IRQ_STATUS() & DMA_DONE))
continue;
diff --git a/arch/blackfin/kernel/bfin_gpio.c b/arch/blackfin/kernel/bfin_gpio.c
index 4c14331..51dac55 100644
--- a/arch/blackfin/kernel/bfin_gpio.c
+++ b/arch/blackfin/kernel/bfin_gpio.c
@@ -27,59 +27,6 @@
* 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
-/*
-* Number BF537/6/4 BF561 BF533/2/1 BF549/8/4/2
-*
-* GPIO_0 PF0 PF0 PF0 PA0...PJ13
-* GPIO_1 PF1 PF1 PF1
-* GPIO_2 PF2 PF2 PF2
-* GPIO_3 PF3 PF3 PF3
-* GPIO_4 PF4 PF4 PF4
-* GPIO_5 PF5 PF5 PF5
-* GPIO_6 PF6 PF6 PF6
-* GPIO_7 PF7 PF7 PF7
-* GPIO_8 PF8 PF8 PF8
-* GPIO_9 PF9 PF9 PF9
-* GPIO_10 PF10 PF10 PF10
-* GPIO_11 PF11 PF11 PF11
-* GPIO_12 PF12 PF12 PF12
-* GPIO_13 PF13 PF13 PF13
-* GPIO_14 PF14 PF14 PF14
-* GPIO_15 PF15 PF15 PF15
-* GPIO_16 PG0 PF16
-* GPIO_17 PG1 PF17
-* GPIO_18 PG2 PF18
-* GPIO_19 PG3 PF19
-* GPIO_20 PG4 PF20
-* GPIO_21 PG5 PF21
-* GPIO_22 PG6 PF22
-* GPIO_23 PG7 PF23
-* GPIO_24 PG8 PF24
-* GPIO_25 PG9 PF25
-* GPIO_26 PG10 PF26
-* GPIO_27 PG11 PF27
-* GPIO_28 PG12 PF28
-* GPIO_29 PG13 PF29
-* GPIO_30 PG14 PF30
-* GPIO_31 PG15 PF31
-* GPIO_32 PH0 PF32
-* GPIO_33 PH1 PF33
-* GPIO_34 PH2 PF34
-* GPIO_35 PH3 PF35
-* GPIO_36 PH4 PF36
-* GPIO_37 PH5 PF37
-* GPIO_38 PH6 PF38
-* GPIO_39 PH7 PF39
-* GPIO_40 PH8 PF40
-* GPIO_41 PH9 PF41
-* GPIO_42 PH10 PF42
-* GPIO_43 PH11 PF43
-* GPIO_44 PH12 PF44
-* GPIO_45 PH13 PF45
-* GPIO_46 PH14 PF46
-* GPIO_47 PH15 PF47
-*/
-
#include <linux/delay.h>
#include <linux/module.h>
#include <linux/err.h>
@@ -119,51 +66,18 @@
#define AWA_DUMMY_READ(...) do { } while (0)
#endif
+static struct gpio_port_t * const gpio_array[] = {
#if defined(BF533_FAMILY) || defined(BF538_FAMILY)
-static struct gpio_port_t *gpio_bankb[] = {
(struct gpio_port_t *) FIO_FLAG_D,
-};
-#endif
-
-#if defined(BF527_FAMILY) || defined(BF537_FAMILY) || defined(BF518_FAMILY)
-static struct gpio_port_t *gpio_bankb[] = {
+#elif defined(BF527_FAMILY) || defined(BF537_FAMILY) || defined(BF518_FAMILY)
(struct gpio_port_t *) PORTFIO,
(struct gpio_port_t *) PORTGIO,
(struct gpio_port_t *) PORTHIO,
-};
-
-static unsigned short *port_fer[] = {
- (unsigned short *) PORTF_FER,
- (unsigned short *) PORTG_FER,
- (unsigned short *) PORTH_FER,
-};
-#endif
-
-#if defined(BF527_FAMILY) || defined(BF518_FAMILY)
-static unsigned short *port_mux[] = {
- (unsigned short *) PORTF_MUX,
- (unsigned short *) PORTG_MUX,
- (unsigned short *) PORTH_MUX,
-};
-
-static const
-u8 pmux_offset[][16] =
- {{ 0, 0, 0, 0, 0, 0, 0, 0, 2, 2, 4, 6, 8, 8, 10, 10 }, /* PORTF */
- { 0, 0, 0, 0, 0, 2, 2, 4, 4, 6, 8, 10, 10, 10, 12, 12 }, /* PORTG */
- { 0, 0, 0, 0, 0, 0, 0, 0, 2, 4, 4, 4, 4, 4, 4, 4 }, /* PORTH */
- };
-#endif
-
-#ifdef BF561_FAMILY
-static struct gpio_port_t *gpio_bankb[] = {
+#elif defined(BF561_FAMILY)
(struct gpio_port_t *) FIO0_FLAG_D,
(struct gpio_port_t *) FIO1_FLAG_D,
(struct gpio_port_t *) FIO2_FLAG_D,
-};
-#endif
-
-#ifdef BF548_FAMILY
-static struct gpio_port_t *gpio_array[] = {
+#elif defined(BF548_FAMILY)
(struct gpio_port_t *)PORTA_FER,
(struct gpio_port_t *)PORTB_FER,
(struct gpio_port_t *)PORTC_FER,
@@ -174,7 +88,39 @@
(struct gpio_port_t *)PORTH_FER,
(struct gpio_port_t *)PORTI_FER,
(struct gpio_port_t *)PORTJ_FER,
+#else
+# error no gpio arrays defined
+#endif
};
+
+#if defined(BF527_FAMILY) || defined(BF537_FAMILY) || defined(BF518_FAMILY)
+static unsigned short * const port_fer[] = {
+ (unsigned short *) PORTF_FER,
+ (unsigned short *) PORTG_FER,
+ (unsigned short *) PORTH_FER,
+};
+
+# if !defined(BF537_FAMILY)
+static unsigned short * const port_mux[] = {
+ (unsigned short *) PORTF_MUX,
+ (unsigned short *) PORTG_MUX,
+ (unsigned short *) PORTH_MUX,
+};
+
+static const
+u8 pmux_offset[][16] = {
+# if defined(BF527_FAMILY)
+ { 0, 0, 0, 0, 0, 0, 0, 0, 2, 2, 4, 6, 8, 8, 10, 10 }, /* PORTF */
+ { 0, 0, 0, 0, 0, 2, 2, 4, 4, 6, 8, 10, 10, 10, 12, 12 }, /* PORTG */
+ { 0, 0, 0, 0, 0, 0, 0, 0, 2, 4, 4, 4, 4, 4, 4, 4 }, /* PORTH */
+# elif defined(BF518_FAMILY)
+ { 0, 2, 2, 2, 2, 2, 2, 4, 6, 6, 6, 8, 8, 8, 8, 10 }, /* PORTF */
+ { 0, 0, 0, 2, 4, 6, 6, 6, 8, 10, 10, 12, 14, 14, 14, 14 }, /* PORTG */
+ { 0, 0, 0, 0, 2, 2, 4, 6, 10, 10, 10, 10, 10, 10, 10, 10 }, /* PORTH */
+# endif
+};
+# endif
+
#endif
static unsigned short reserved_gpio_map[GPIO_BANK_NUM];
@@ -188,35 +134,9 @@
} str_ident[MAX_RESOURCES];
#if defined(CONFIG_PM)
-#if defined(CONFIG_BF54x)
static struct gpio_port_s gpio_bank_saved[GPIO_BANK_NUM];
-#else
-static unsigned short wakeup_map[GPIO_BANK_NUM];
-static unsigned char wakeup_flags_map[MAX_BLACKFIN_GPIOS];
-static struct gpio_port_s gpio_bank_saved[GPIO_BANK_NUM];
-
-#ifdef BF533_FAMILY
-static unsigned int sic_iwr_irqs[] = {IRQ_PROG_INTB};
#endif
-#ifdef BF537_FAMILY
-static unsigned int sic_iwr_irqs[] = {IRQ_PROG_INTB, IRQ_PORTG_INTB, IRQ_MAC_TX};
-#endif
-
-#ifdef BF538_FAMILY
-static unsigned int sic_iwr_irqs[] = {IRQ_PORTF_INTB};
-#endif
-
-#if defined(BF527_FAMILY) || defined(BF518_FAMILY)
-static unsigned int sic_iwr_irqs[] = {IRQ_PORTF_INTB, IRQ_PORTG_INTB, IRQ_PORTH_INTB};
-#endif
-
-#ifdef BF561_FAMILY
-static unsigned int sic_iwr_irqs[] = {IRQ_PROG0_INTB, IRQ_PROG1_INTB, IRQ_PROG2_INTB};
-#endif
-#endif
-#endif /* CONFIG_PM */
-
inline int check_gpio(unsigned gpio)
{
#if defined(BF548_FAMILY)
@@ -330,9 +250,10 @@
{.res = P_SPI0_SSEL3, .offset = 0},
};
-static void portmux_setup(unsigned short per, unsigned short function)
+static void portmux_setup(unsigned short per)
{
u16 y, offset, muxreg;
+ u16 function = P_FUNCT2MUX(per);
for (y = 0; y < ARRAY_SIZE(port_mux_lut); y++) {
if (port_mux_lut[y].res == per) {
@@ -353,30 +274,33 @@
}
}
#elif defined(BF548_FAMILY)
-inline void portmux_setup(unsigned short portno, unsigned short function)
+inline void portmux_setup(unsigned short per)
{
u32 pmux;
+ u16 ident = P_IDENT(per);
+ u16 function = P_FUNCT2MUX(per);
- pmux = gpio_array[gpio_bank(portno)]->port_mux;
+ pmux = gpio_array[gpio_bank(ident)]->port_mux;
- pmux &= ~(0x3 << (2 * gpio_sub_n(portno)));
- pmux |= (function & 0x3) << (2 * gpio_sub_n(portno));
+ pmux &= ~(0x3 << (2 * gpio_sub_n(ident)));
+ pmux |= (function & 0x3) << (2 * gpio_sub_n(ident));
- gpio_array[gpio_bank(portno)]->port_mux = pmux;
+ gpio_array[gpio_bank(ident)]->port_mux = pmux;
}
-inline u16 get_portmux(unsigned short portno)
+inline u16 get_portmux(unsigned short per)
{
u32 pmux;
+ u16 ident = P_IDENT(per);
- pmux = gpio_array[gpio_bank(portno)]->port_mux;
+ pmux = gpio_array[gpio_bank(ident)]->port_mux;
- return (pmux >> (2 * gpio_sub_n(portno)) & 0x3);
+ return (pmux >> (2 * gpio_sub_n(ident)) & 0x3);
}
#elif defined(BF527_FAMILY) || defined(BF518_FAMILY)
-inline void portmux_setup(unsigned short portno, unsigned short function)
+inline void portmux_setup(unsigned short per)
{
- u16 pmux, ident = P_IDENT(portno);
+ u16 pmux, ident = P_IDENT(per), function = P_FUNCT2MUX(per);
u8 offset = pmux_offset[gpio_bank(ident)][gpio_sub_n(ident)];
pmux = *port_mux[gpio_bank(ident)];
@@ -424,90 +348,71 @@
unsigned long flags; \
local_irq_save_hw(flags); \
if (arg) \
- gpio_bankb[gpio_bank(gpio)]->name |= gpio_bit(gpio); \
+ gpio_array[gpio_bank(gpio)]->name |= gpio_bit(gpio); \
else \
- gpio_bankb[gpio_bank(gpio)]->name &= ~gpio_bit(gpio); \
+ gpio_array[gpio_bank(gpio)]->name &= ~gpio_bit(gpio); \
AWA_DUMMY_READ(name); \
local_irq_restore_hw(flags); \
} \
EXPORT_SYMBOL(set_gpio_ ## name);
-SET_GPIO(dir)
-SET_GPIO(inen)
-SET_GPIO(polar)
-SET_GPIO(edge)
-SET_GPIO(both)
+SET_GPIO(dir) /* set_gpio_dir() */
+SET_GPIO(inen) /* set_gpio_inen() */
+SET_GPIO(polar) /* set_gpio_polar() */
+SET_GPIO(edge) /* set_gpio_edge() */
+SET_GPIO(both) /* set_gpio_both() */
-#if ANOMALY_05000311 || ANOMALY_05000323
#define SET_GPIO_SC(name) \
void set_gpio_ ## name(unsigned gpio, unsigned short arg) \
{ \
unsigned long flags; \
- local_irq_save_hw(flags); \
+ if (ANOMALY_05000311 || ANOMALY_05000323) \
+ local_irq_save_hw(flags); \
if (arg) \
- gpio_bankb[gpio_bank(gpio)]->name ## _set = gpio_bit(gpio); \
+ gpio_array[gpio_bank(gpio)]->name ## _set = gpio_bit(gpio); \
else \
- gpio_bankb[gpio_bank(gpio)]->name ## _clear = gpio_bit(gpio); \
- AWA_DUMMY_READ(name); \
- local_irq_restore_hw(flags); \
+ gpio_array[gpio_bank(gpio)]->name ## _clear = gpio_bit(gpio); \
+ if (ANOMALY_05000311 || ANOMALY_05000323) { \
+ AWA_DUMMY_READ(name); \
+ local_irq_restore_hw(flags); \
+ } \
} \
EXPORT_SYMBOL(set_gpio_ ## name);
-#else
-#define SET_GPIO_SC(name) \
-void set_gpio_ ## name(unsigned gpio, unsigned short arg) \
-{ \
- if (arg) \
- gpio_bankb[gpio_bank(gpio)]->name ## _set = gpio_bit(gpio); \
- else \
- gpio_bankb[gpio_bank(gpio)]->name ## _clear = gpio_bit(gpio); \
-} \
-EXPORT_SYMBOL(set_gpio_ ## name);
-#endif
SET_GPIO_SC(maska)
SET_GPIO_SC(maskb)
SET_GPIO_SC(data)
-#if ANOMALY_05000311 || ANOMALY_05000323
void set_gpio_toggle(unsigned gpio)
{
unsigned long flags;
- local_irq_save_hw(flags);
- gpio_bankb[gpio_bank(gpio)]->toggle = gpio_bit(gpio);
- AWA_DUMMY_READ(toggle);
- local_irq_restore_hw(flags);
+ if (ANOMALY_05000311 || ANOMALY_05000323)
+ local_irq_save_hw(flags);
+ gpio_array[gpio_bank(gpio)]->toggle = gpio_bit(gpio);
+ if (ANOMALY_05000311 || ANOMALY_05000323) {
+ AWA_DUMMY_READ(toggle);
+ local_irq_restore_hw(flags);
+ }
}
-#else
-void set_gpio_toggle(unsigned gpio)
-{
- gpio_bankb[gpio_bank(gpio)]->toggle = gpio_bit(gpio);
-}
-#endif
EXPORT_SYMBOL(set_gpio_toggle);
/*Set current PORT date (16-bit word)*/
-#if ANOMALY_05000311 || ANOMALY_05000323
#define SET_GPIO_P(name) \
void set_gpiop_ ## name(unsigned gpio, unsigned short arg) \
{ \
unsigned long flags; \
- local_irq_save_hw(flags); \
- gpio_bankb[gpio_bank(gpio)]->name = arg; \
- AWA_DUMMY_READ(name); \
- local_irq_restore_hw(flags); \
+ if (ANOMALY_05000311 || ANOMALY_05000323) \
+ local_irq_save_hw(flags); \
+ gpio_array[gpio_bank(gpio)]->name = arg; \
+ if (ANOMALY_05000311 || ANOMALY_05000323) { \
+ AWA_DUMMY_READ(name); \
+ local_irq_restore_hw(flags); \
+ } \
} \
EXPORT_SYMBOL(set_gpiop_ ## name);
-#else
-#define SET_GPIO_P(name) \
-void set_gpiop_ ## name(unsigned gpio, unsigned short arg) \
-{ \
- gpio_bankb[gpio_bank(gpio)]->name = arg; \
-} \
-EXPORT_SYMBOL(set_gpiop_ ## name);
-#endif
SET_GPIO_P(data)
SET_GPIO_P(dir)
@@ -519,27 +424,21 @@
SET_GPIO_P(maskb)
/* Get a specific bit */
-#if ANOMALY_05000311 || ANOMALY_05000323
#define GET_GPIO(name) \
unsigned short get_gpio_ ## name(unsigned gpio) \
{ \
unsigned long flags; \
unsigned short ret; \
- local_irq_save_hw(flags); \
- ret = 0x01 & (gpio_bankb[gpio_bank(gpio)]->name >> gpio_sub_n(gpio)); \
- AWA_DUMMY_READ(name); \
- local_irq_restore_hw(flags); \
+ if (ANOMALY_05000311 || ANOMALY_05000323) \
+ local_irq_save_hw(flags); \
+ ret = 0x01 & (gpio_array[gpio_bank(gpio)]->name >> gpio_sub_n(gpio)); \
+ if (ANOMALY_05000311 || ANOMALY_05000323) { \
+ AWA_DUMMY_READ(name); \
+ local_irq_restore_hw(flags); \
+ } \
return ret; \
} \
EXPORT_SYMBOL(get_gpio_ ## name);
-#else
-#define GET_GPIO(name) \
-unsigned short get_gpio_ ## name(unsigned gpio) \
-{ \
- return (0x01 & (gpio_bankb[gpio_bank(gpio)]->name >> gpio_sub_n(gpio))); \
-} \
-EXPORT_SYMBOL(get_gpio_ ## name);
-#endif
GET_GPIO(data)
GET_GPIO(dir)
@@ -552,27 +451,21 @@
/*Get current PORT date (16-bit word)*/
-#if ANOMALY_05000311 || ANOMALY_05000323
#define GET_GPIO_P(name) \
unsigned short get_gpiop_ ## name(unsigned gpio) \
{ \
unsigned long flags; \
unsigned short ret; \
- local_irq_save_hw(flags); \
- ret = (gpio_bankb[gpio_bank(gpio)]->name); \
- AWA_DUMMY_READ(name); \
- local_irq_restore_hw(flags); \
+ if (ANOMALY_05000311 || ANOMALY_05000323) \
+ local_irq_save_hw(flags); \
+ ret = (gpio_array[gpio_bank(gpio)]->name); \
+ if (ANOMALY_05000311 || ANOMALY_05000323) { \
+ AWA_DUMMY_READ(name); \
+ local_irq_restore_hw(flags); \
+ } \
return ret; \
} \
EXPORT_SYMBOL(get_gpiop_ ## name);
-#else
-#define GET_GPIO_P(name) \
-unsigned short get_gpiop_ ## name(unsigned gpio) \
-{ \
- return (gpio_bankb[gpio_bank(gpio)]->name);\
-} \
-EXPORT_SYMBOL(get_gpiop_ ## name);
-#endif
GET_GPIO_P(data)
GET_GPIO_P(dir)
@@ -585,6 +478,26 @@
#ifdef CONFIG_PM
+
+static unsigned short wakeup_map[GPIO_BANK_NUM];
+static unsigned char wakeup_flags_map[MAX_BLACKFIN_GPIOS];
+
+static const unsigned int sic_iwr_irqs[] = {
+#if defined(BF533_FAMILY)
+ IRQ_PROG_INTB
+#elif defined(BF537_FAMILY)
+ IRQ_PROG_INTB, IRQ_PORTG_INTB, IRQ_MAC_TX
+#elif defined(BF538_FAMILY)
+ IRQ_PORTF_INTB
+#elif defined(BF527_FAMILY) || defined(BF518_FAMILY)
+ IRQ_PORTF_INTB, IRQ_PORTG_INTB, IRQ_PORTH_INTB
+#elif defined(BF561_FAMILY)
+ IRQ_PROG0_INTB, IRQ_PROG1_INTB, IRQ_PROG2_INTB
+#else
+# error no SIC_IWR defined
+#endif
+};
+
/***********************************************************
*
* FUNCTIONS: Blackfin PM Setup API
@@ -669,18 +582,18 @@
mask = wakeup_map[gpio_bank(i)];
bank = gpio_bank(i);
- gpio_bank_saved[bank].maskb = gpio_bankb[bank]->maskb;
- gpio_bankb[bank]->maskb = 0;
+ gpio_bank_saved[bank].maskb = gpio_array[bank]->maskb;
+ gpio_array[bank]->maskb = 0;
if (mask) {
#if defined(BF527_FAMILY) || defined(BF537_FAMILY) || defined(BF518_FAMILY)
gpio_bank_saved[bank].fer = *port_fer[bank];
#endif
- gpio_bank_saved[bank].inen = gpio_bankb[bank]->inen;
- gpio_bank_saved[bank].polar = gpio_bankb[bank]->polar;
- gpio_bank_saved[bank].dir = gpio_bankb[bank]->dir;
- gpio_bank_saved[bank].edge = gpio_bankb[bank]->edge;
- gpio_bank_saved[bank].both = gpio_bankb[bank]->both;
+ gpio_bank_saved[bank].inen = gpio_array[bank]->inen;
+ gpio_bank_saved[bank].polar = gpio_array[bank]->polar;
+ gpio_bank_saved[bank].dir = gpio_array[bank]->dir;
+ gpio_bank_saved[bank].edge = gpio_array[bank]->edge;
+ gpio_bank_saved[bank].both = gpio_array[bank]->both;
gpio_bank_saved[bank].reserved =
reserved_gpio_map[bank];
@@ -700,7 +613,7 @@
}
bfin_internal_set_wake(sic_iwr_irqs[bank], 1);
- gpio_bankb[bank]->maskb_set = wakeup_map[gpio_bank(i)];
+ gpio_array[bank]->maskb_set = wakeup_map[gpio_bank(i)];
}
}
@@ -721,18 +634,18 @@
#if defined(BF527_FAMILY) || defined(BF537_FAMILY) || defined(BF518_FAMILY)
*port_fer[bank] = gpio_bank_saved[bank].fer;
#endif
- gpio_bankb[bank]->inen = gpio_bank_saved[bank].inen;
- gpio_bankb[bank]->dir = gpio_bank_saved[bank].dir;
- gpio_bankb[bank]->polar = gpio_bank_saved[bank].polar;
- gpio_bankb[bank]->edge = gpio_bank_saved[bank].edge;
- gpio_bankb[bank]->both = gpio_bank_saved[bank].both;
+ gpio_array[bank]->inen = gpio_bank_saved[bank].inen;
+ gpio_array[bank]->dir = gpio_bank_saved[bank].dir;
+ gpio_array[bank]->polar = gpio_bank_saved[bank].polar;
+ gpio_array[bank]->edge = gpio_bank_saved[bank].edge;
+ gpio_array[bank]->both = gpio_bank_saved[bank].both;
reserved_gpio_map[bank] =
gpio_bank_saved[bank].reserved;
bfin_internal_set_wake(sic_iwr_irqs[bank], 0);
}
- gpio_bankb[bank]->maskb = gpio_bank_saved[bank].maskb;
+ gpio_array[bank]->maskb = gpio_bank_saved[bank].maskb;
}
AWA_DUMMY_READ(maskb);
}
@@ -745,21 +658,21 @@
bank = gpio_bank(i);
#if defined(BF527_FAMILY) || defined(BF537_FAMILY) || defined(BF518_FAMILY)
- gpio_bank_saved[bank].fer = *port_fer[bank];
+ gpio_bank_saved[bank].fer = *port_fer[bank];
#if defined(BF527_FAMILY) || defined(BF518_FAMILY)
- gpio_bank_saved[bank].mux = *port_mux[bank];
+ gpio_bank_saved[bank].mux = *port_mux[bank];
#else
- if (bank == 0)
- gpio_bank_saved[bank].mux = bfin_read_PORT_MUX();
+ if (bank == 0)
+ gpio_bank_saved[bank].mux = bfin_read_PORT_MUX();
#endif
#endif
- gpio_bank_saved[bank].data = gpio_bankb[bank]->data;
- gpio_bank_saved[bank].inen = gpio_bankb[bank]->inen;
- gpio_bank_saved[bank].polar = gpio_bankb[bank]->polar;
- gpio_bank_saved[bank].dir = gpio_bankb[bank]->dir;
- gpio_bank_saved[bank].edge = gpio_bankb[bank]->edge;
- gpio_bank_saved[bank].both = gpio_bankb[bank]->both;
- gpio_bank_saved[bank].maska = gpio_bankb[bank]->maska;
+ gpio_bank_saved[bank].data = gpio_array[bank]->data;
+ gpio_bank_saved[bank].inen = gpio_array[bank]->inen;
+ gpio_bank_saved[bank].polar = gpio_array[bank]->polar;
+ gpio_bank_saved[bank].dir = gpio_array[bank]->dir;
+ gpio_bank_saved[bank].edge = gpio_array[bank]->edge;
+ gpio_bank_saved[bank].both = gpio_array[bank]->both;
+ gpio_bank_saved[bank].maska = gpio_array[bank]->maska;
}
AWA_DUMMY_READ(maska);
@@ -770,27 +683,27 @@
int i, bank;
for (i = 0; i < MAX_BLACKFIN_GPIOS; i += GPIO_BANKSIZE) {
- bank = gpio_bank(i);
+ bank = gpio_bank(i);
#if defined(BF527_FAMILY) || defined(BF537_FAMILY) || defined(BF518_FAMILY)
#if defined(BF527_FAMILY) || defined(BF518_FAMILY)
- *port_mux[bank] = gpio_bank_saved[bank].mux;
+ *port_mux[bank] = gpio_bank_saved[bank].mux;
#else
- if (bank == 0)
- bfin_write_PORT_MUX(gpio_bank_saved[bank].mux);
+ if (bank == 0)
+ bfin_write_PORT_MUX(gpio_bank_saved[bank].mux);
#endif
- *port_fer[bank] = gpio_bank_saved[bank].fer;
+ *port_fer[bank] = gpio_bank_saved[bank].fer;
#endif
- gpio_bankb[bank]->inen = gpio_bank_saved[bank].inen;
- gpio_bankb[bank]->dir = gpio_bank_saved[bank].dir;
- gpio_bankb[bank]->polar = gpio_bank_saved[bank].polar;
- gpio_bankb[bank]->edge = gpio_bank_saved[bank].edge;
- gpio_bankb[bank]->both = gpio_bank_saved[bank].both;
+ gpio_array[bank]->inen = gpio_bank_saved[bank].inen;
+ gpio_array[bank]->dir = gpio_bank_saved[bank].dir;
+ gpio_array[bank]->polar = gpio_bank_saved[bank].polar;
+ gpio_array[bank]->edge = gpio_bank_saved[bank].edge;
+ gpio_array[bank]->both = gpio_bank_saved[bank].both;
- gpio_bankb[bank]->data_set = gpio_bank_saved[bank].data
- | gpio_bank_saved[bank].dir;
+ gpio_array[bank]->data_set = gpio_bank_saved[bank].data
+ | gpio_bank_saved[bank].dir;
- gpio_bankb[bank]->maska = gpio_bank_saved[bank].maska;
+ gpio_array[bank]->maska = gpio_bank_saved[bank].maska;
}
AWA_DUMMY_READ(maska);
}
@@ -817,12 +730,12 @@
for (i = 0; i < MAX_BLACKFIN_GPIOS; i += GPIO_BANKSIZE) {
bank = gpio_bank(i);
- gpio_bank_saved[bank].fer = gpio_array[bank]->port_fer;
- gpio_bank_saved[bank].mux = gpio_array[bank]->port_mux;
- gpio_bank_saved[bank].data = gpio_array[bank]->port_data;
- gpio_bank_saved[bank].data = gpio_array[bank]->port_data;
- gpio_bank_saved[bank].inen = gpio_array[bank]->port_inen;
- gpio_bank_saved[bank].dir = gpio_array[bank]->port_dir_set;
+ gpio_bank_saved[bank].fer = gpio_array[bank]->port_fer;
+ gpio_bank_saved[bank].mux = gpio_array[bank]->port_mux;
+ gpio_bank_saved[bank].data = gpio_array[bank]->data;
+ gpio_bank_saved[bank].data = gpio_array[bank]->data;
+ gpio_bank_saved[bank].inen = gpio_array[bank]->inen;
+ gpio_bank_saved[bank].dir = gpio_array[bank]->dir_set;
}
}
@@ -831,21 +744,21 @@
int i, bank;
for (i = 0; i < MAX_BLACKFIN_GPIOS; i += GPIO_BANKSIZE) {
- bank = gpio_bank(i);
+ bank = gpio_bank(i);
- gpio_array[bank]->port_mux = gpio_bank_saved[bank].mux;
- gpio_array[bank]->port_fer = gpio_bank_saved[bank].fer;
- gpio_array[bank]->port_inen = gpio_bank_saved[bank].inen;
- gpio_array[bank]->port_dir_set = gpio_bank_saved[bank].dir;
- gpio_array[bank]->port_set = gpio_bank_saved[bank].data
- | gpio_bank_saved[bank].dir;
+ gpio_array[bank]->port_mux = gpio_bank_saved[bank].mux;
+ gpio_array[bank]->port_fer = gpio_bank_saved[bank].fer;
+ gpio_array[bank]->inen = gpio_bank_saved[bank].inen;
+ gpio_array[bank]->dir_set = gpio_bank_saved[bank].dir;
+ gpio_array[bank]->data_set = gpio_bank_saved[bank].data
+ | gpio_bank_saved[bank].dir;
}
}
#endif
unsigned short get_gpio_dir(unsigned gpio)
{
- return (0x01 & (gpio_array[gpio_bank(gpio)]->port_dir_clear >> gpio_sub_n(gpio)));
+ return (0x01 & (gpio_array[gpio_bank(gpio)]->dir_clear >> gpio_sub_n(gpio)));
}
EXPORT_SYMBOL(get_gpio_dir);
@@ -905,9 +818,7 @@
*/
#ifdef BF548_FAMILY
- u16 funct = get_portmux(ident);
-
- if (!((per & P_MAYSHARE) && (funct == P_FUNCT2MUX(per)))) {
+ if (!((per & P_MAYSHARE) && get_portmux(per) == P_FUNCT2MUX(per))) {
#else
if (!(per & P_MAYSHARE)) {
#endif
@@ -931,11 +842,7 @@
anyway:
reserved_peri_map[gpio_bank(ident)] |= gpio_bit(ident);
-#ifdef BF548_FAMILY
- portmux_setup(ident, P_FUNCT2MUX(per));
-#else
- portmux_setup(per, P_FUNCT2MUX(per));
-#endif
+ portmux_setup(per);
port_setup(ident, PERIPHERAL_USAGE);
local_irq_restore_hw(flags);
@@ -977,9 +884,6 @@
if (!(per & P_DEFINED))
return;
- if (check_gpio(ident) < 0)
- return;
-
local_irq_save_hw(flags);
if (unlikely(!(reserved_peri_map[gpio_bank(ident)] & gpio_bit(ident)))) {
@@ -1056,9 +960,15 @@
local_irq_restore_hw(flags);
return -EBUSY;
}
- if (unlikely(reserved_gpio_irq_map[gpio_bank(gpio)] & gpio_bit(gpio)))
+ if (unlikely(reserved_gpio_irq_map[gpio_bank(gpio)] & gpio_bit(gpio))) {
printk(KERN_NOTICE "bfin-gpio: GPIO %d is already reserved as gpio-irq!"
" (Documentation/blackfin/bfin-gpio-notes.txt)\n", gpio);
+ }
+#ifndef BF548_FAMILY
+ else { /* Reset POLAR setting when acquiring a gpio for the first time */
+ set_gpio_polar(gpio, 0);
+ }
+#endif
reserved_gpio_map[gpio_bank(gpio)] |= gpio_bit(gpio);
set_label(gpio, label);
@@ -1078,6 +988,8 @@
if (check_gpio(gpio) < 0)
return;
+ might_sleep();
+
local_irq_save_hw(flags);
if (unlikely(!(reserved_gpio_map[gpio_bank(gpio)] & gpio_bit(gpio)))) {
@@ -1158,92 +1070,15 @@
local_irq_restore_hw(flags);
}
-
+static inline void __bfin_gpio_direction_input(unsigned gpio)
+{
#ifdef BF548_FAMILY
-int bfin_gpio_direction_input(unsigned gpio)
-{
- unsigned long flags;
-
- if (!(reserved_gpio_map[gpio_bank(gpio)] & gpio_bit(gpio))) {
- gpio_error(gpio);
- return -EINVAL;
- }
-
- local_irq_save_hw(flags);
- gpio_array[gpio_bank(gpio)]->port_dir_clear = gpio_bit(gpio);
- gpio_array[gpio_bank(gpio)]->port_inen |= gpio_bit(gpio);
- local_irq_restore_hw(flags);
-
- return 0;
-}
-EXPORT_SYMBOL(bfin_gpio_direction_input);
-
-int bfin_gpio_direction_output(unsigned gpio, int value)
-{
- unsigned long flags;
-
- if (!(reserved_gpio_map[gpio_bank(gpio)] & gpio_bit(gpio))) {
- gpio_error(gpio);
- return -EINVAL;
- }
-
- local_irq_save_hw(flags);
- gpio_array[gpio_bank(gpio)]->port_inen &= ~gpio_bit(gpio);
- gpio_set_value(gpio, value);
- gpio_array[gpio_bank(gpio)]->port_dir_set = gpio_bit(gpio);
- local_irq_restore_hw(flags);
-
- return 0;
-}
-EXPORT_SYMBOL(bfin_gpio_direction_output);
-
-void bfin_gpio_set_value(unsigned gpio, int arg)
-{
- if (arg)
- gpio_array[gpio_bank(gpio)]->port_set = gpio_bit(gpio);
- else
- gpio_array[gpio_bank(gpio)]->port_clear = gpio_bit(gpio);
-}
-EXPORT_SYMBOL(bfin_gpio_set_value);
-
-int bfin_gpio_get_value(unsigned gpio)
-{
- return (1 & (gpio_array[gpio_bank(gpio)]->port_data >> gpio_sub_n(gpio)));
-}
-EXPORT_SYMBOL(bfin_gpio_get_value);
-
-void bfin_gpio_irq_prepare(unsigned gpio)
-{
- unsigned long flags;
-
- port_setup(gpio, GPIO_USAGE);
-
- local_irq_save_hw(flags);
- gpio_array[gpio_bank(gpio)]->port_dir_clear = gpio_bit(gpio);
- gpio_array[gpio_bank(gpio)]->port_inen |= gpio_bit(gpio);
- local_irq_restore_hw(flags);
-}
-
+ gpio_array[gpio_bank(gpio)]->dir_clear = gpio_bit(gpio);
#else
-
-int bfin_gpio_get_value(unsigned gpio)
-{
- unsigned long flags;
- int ret;
-
- if (unlikely(get_gpio_edge(gpio))) {
- local_irq_save_hw(flags);
- set_gpio_edge(gpio, 0);
- ret = get_gpio_data(gpio);
- set_gpio_edge(gpio, 1);
- local_irq_restore_hw(flags);
-
- return ret;
- } else
- return get_gpio_data(gpio);
+ gpio_array[gpio_bank(gpio)]->dir &= ~gpio_bit(gpio);
+#endif
+ gpio_array[gpio_bank(gpio)]->inen |= gpio_bit(gpio);
}
-EXPORT_SYMBOL(bfin_gpio_get_value);
-
int bfin_gpio_direction_input(unsigned gpio)
{
@@ -1255,8 +1090,7 @@
}
local_irq_save_hw(flags);
- gpio_bankb[gpio_bank(gpio)]->dir &= ~gpio_bit(gpio);
- gpio_bankb[gpio_bank(gpio)]->inen |= gpio_bit(gpio);
+ __bfin_gpio_direction_input(gpio);
AWA_DUMMY_READ(inen);
local_irq_restore_hw(flags);
@@ -1264,6 +1098,30 @@
}
EXPORT_SYMBOL(bfin_gpio_direction_input);
+void bfin_gpio_irq_prepare(unsigned gpio)
+{
+#ifdef BF548_FAMILY
+ unsigned long flags;
+#endif
+
+ port_setup(gpio, GPIO_USAGE);
+
+#ifdef BF548_FAMILY
+ local_irq_save_hw(flags);
+ __bfin_gpio_direction_input(gpio);
+ local_irq_restore_hw(flags);
+#endif
+}
+
+void bfin_gpio_set_value(unsigned gpio, int arg)
+{
+ if (arg)
+ gpio_array[gpio_bank(gpio)]->data_set = gpio_bit(gpio);
+ else
+ gpio_array[gpio_bank(gpio)]->data_clear = gpio_bit(gpio);
+}
+EXPORT_SYMBOL(bfin_gpio_set_value);
+
int bfin_gpio_direction_output(unsigned gpio, int value)
{
unsigned long flags;
@@ -1274,14 +1132,15 @@
}
local_irq_save_hw(flags);
- gpio_bankb[gpio_bank(gpio)]->inen &= ~gpio_bit(gpio);
- if (value)
- gpio_bankb[gpio_bank(gpio)]->data_set = gpio_bit(gpio);
- else
- gpio_bankb[gpio_bank(gpio)]->data_clear = gpio_bit(gpio);
+ gpio_array[gpio_bank(gpio)]->inen &= ~gpio_bit(gpio);
+ gpio_set_value(gpio, value);
+#ifdef BF548_FAMILY
+ gpio_array[gpio_bank(gpio)]->dir_set = gpio_bit(gpio);
+#else
+ gpio_array[gpio_bank(gpio)]->dir |= gpio_bit(gpio);
+#endif
- gpio_bankb[gpio_bank(gpio)]->dir |= gpio_bit(gpio);
AWA_DUMMY_READ(dir);
local_irq_restore_hw(flags);
@@ -1289,6 +1148,27 @@
}
EXPORT_SYMBOL(bfin_gpio_direction_output);
+int bfin_gpio_get_value(unsigned gpio)
+{
+#ifdef BF548_FAMILY
+ return (1 & (gpio_array[gpio_bank(gpio)]->data >> gpio_sub_n(gpio)));
+#else
+ unsigned long flags;
+
+ if (unlikely(get_gpio_edge(gpio))) {
+ int ret;
+ local_irq_save_hw(flags);
+ set_gpio_edge(gpio, 0);
+ ret = get_gpio_data(gpio);
+ set_gpio_edge(gpio, 1);
+ local_irq_restore_hw(flags);
+ return ret;
+ } else
+ return get_gpio_data(gpio);
+#endif
+}
+EXPORT_SYMBOL(bfin_gpio_get_value);
+
/* If we are booting from SPI and our board lacks a strong enough pull up,
* the core can reset and execute the bootrom faster than the resistor can
* pull the signal logically high. To work around this (common) error in
@@ -1299,23 +1179,15 @@
* lives here as we need to force all the GPIO states w/out going through
* BUG() checks and such.
*/
-void bfin_gpio_reset_spi0_ssel1(void)
+void bfin_reset_boot_spi_cs(unsigned short pin)
{
- u16 gpio = P_IDENT(P_SPI0_SSEL1);
-
+ unsigned short gpio = P_IDENT(pin);
port_setup(gpio, GPIO_USAGE);
- gpio_bankb[gpio_bank(gpio)]->data_set = gpio_bit(gpio);
+ gpio_array[gpio_bank(gpio)]->data_set = gpio_bit(gpio);
AWA_DUMMY_READ(data_set);
udelay(1);
}
-void bfin_gpio_irq_prepare(unsigned gpio)
-{
- port_setup(gpio, GPIO_USAGE);
-}
-
-#endif /*BF548_FAMILY */
-
#if defined(CONFIG_PROC_FS)
static int gpio_proc_read(char *buf, char **start, off_t offset,
int len, int *unused_i, void *unused_v)
@@ -1369,11 +1241,7 @@
void bfin_gpiolib_set_value(struct gpio_chip *chip, unsigned gpio, int value)
{
-#ifdef BF548_FAMILY
return bfin_gpio_set_value(gpio, value);
-#else
- return set_gpio_data(gpio, value);
-#endif
}
int bfin_gpiolib_gpio_request(struct gpio_chip *chip, unsigned gpio)
diff --git a/arch/blackfin/kernel/cplb-mpu/cplbinit.c b/arch/blackfin/kernel/cplb-mpu/cplbinit.c
index bdb9584..3e329a6 100644
--- a/arch/blackfin/kernel/cplb-mpu/cplbinit.c
+++ b/arch/blackfin/kernel/cplb-mpu/cplbinit.c
@@ -63,10 +63,8 @@
dcplb_tbl[cpu][i_d].addr = 0;
dcplb_tbl[cpu][i_d++].data = SDRAM_OOPS | PAGE_SIZE_1KB;
-#if 0
icplb_tbl[cpu][i_i].addr = 0;
- icplb_tbl[cpu][i_i++].data = i_cache | CPLB_USER_RD | PAGE_SIZE_4KB;
-#endif
+ icplb_tbl[cpu][i_i++].data = i_cache | CPLB_USER_RD | PAGE_SIZE_1KB;
/* Cover kernel memory with 4M pages. */
addr = 0;
diff --git a/arch/blackfin/kernel/cplb-nompu/cplbmgr.c b/arch/blackfin/kernel/cplb-nompu/cplbmgr.c
index 376249a..8cbb47c 100644
--- a/arch/blackfin/kernel/cplb-nompu/cplbmgr.c
+++ b/arch/blackfin/kernel/cplb-nompu/cplbmgr.c
@@ -163,12 +163,14 @@
nr_icplb_supv_miss[cpu]++;
base = 0;
- for (idx = 0; idx < icplb_nr_bounds; idx++) {
+ idx = 0;
+ do {
eaddr = icplb_bounds[idx].eaddr;
if (addr < eaddr)
break;
base = eaddr;
- }
+ } while (++idx < icplb_nr_bounds);
+
if (unlikely(idx == icplb_nr_bounds))
return CPLB_NO_ADDR_MATCH;
@@ -208,12 +210,14 @@
nr_dcplb_supv_miss[cpu]++;
base = 0;
- for (idx = 0; idx < dcplb_nr_bounds; idx++) {
+ idx = 0;
+ do {
eaddr = dcplb_bounds[idx].eaddr;
if (addr < eaddr)
break;
base = eaddr;
- }
+ } while (++idx < dcplb_nr_bounds);
+
if (unlikely(idx == dcplb_nr_bounds))
return CPLB_NO_ADDR_MATCH;
diff --git a/arch/blackfin/kernel/irqchip.c b/arch/blackfin/kernel/irqchip.c
index ab8209c..23e9aa0 100644
--- a/arch/blackfin/kernel/irqchip.c
+++ b/arch/blackfin/kernel/irqchip.c
@@ -35,6 +35,7 @@
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <asm/trace.h>
+#include <asm/pda.h>
static atomic_t irq_err_count;
static spinlock_t irq_controller_lock;
@@ -69,6 +70,11 @@
#endif
};
+#ifdef CONFIG_CPUMASK_OFFSTACK
+/* We are not allocating a variable-sized bad_irq_desc.affinity */
+#error "Blackfin architecture does not support CONFIG_CPUMASK_OFFSTACK."
+#endif
+
int show_interrupts(struct seq_file *p, void *v)
{
int i = *(loff_t *) v, j;
@@ -91,8 +97,13 @@
seq_putc(p, '\n');
skip:
spin_unlock_irqrestore(&irq_desc[i].lock, flags);
- } else if (i == NR_IRQS)
+ } else if (i == NR_IRQS) {
+ seq_printf(p, "NMI: ");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ", cpu_pda[j].__nmi_count);
+ seq_printf(p, " CORE Non Maskable Interrupt\n");
seq_printf(p, "Err: %10u\n", atomic_read(&irq_err_count));
+ }
return 0;
}
diff --git a/arch/blackfin/kernel/reboot.c b/arch/blackfin/kernel/reboot.c
index eeee8cb..53d08de 100644
--- a/arch/blackfin/kernel/reboot.c
+++ b/arch/blackfin/kernel/reboot.c
@@ -20,8 +20,8 @@
* reset while the Core B bit (on dual core parts) is cleared by
* the core reset.
*/
-__attribute__((l1_text))
-static void _bfin_reset(void)
+__attribute__ ((__l1_text__, __noreturn__))
+static void bfin_reset(void)
{
/* Wait for completion of "system" events such as cache line
* line fills so that we avoid infinite stalls later on as
@@ -30,7 +30,11 @@
*/
__builtin_bfin_ssync();
- while (1) {
+ /* The bootrom checks to see how it was reset and will
+ * automatically perform a software reset for us when
+ * it starts executing after the core reset.
+ */
+ if (ANOMALY_05000353 || ANOMALY_05000386) {
/* Initiate System software reset. */
bfin_write_SWRST(0x7);
@@ -50,6 +54,11 @@
/* Clear System software reset */
bfin_write_SWRST(0);
+ /* The BF526 ROM will crash during reset */
+#if defined(__ADSPBF522__) || defined(__ADSPBF524__) || defined(__ADSPBF526__)
+ bfin_read_SWRST();
+#endif
+
/* Wait for the SWRST write to complete. Cannot rely on SSYNC
* though as the System state is all reset now.
*/
@@ -60,22 +69,11 @@
: "a" (15 * 1)
: "LC1", "LB1", "LT1"
);
+ }
+ while (1)
/* Issue core reset */
asm("raise 1");
- }
-}
-
-static void bfin_reset(void)
-{
- if (ANOMALY_05000353 || ANOMALY_05000386)
- _bfin_reset();
- else
- /* the bootrom checks to see how it was reset and will
- * automatically perform a software reset for us when
- * it starts executing boot
- */
- asm("raise 1;");
}
__attribute__((weak))
diff --git a/arch/blackfin/kernel/setup.c b/arch/blackfin/kernel/setup.c
index b2a8113..e5c1162 100644
--- a/arch/blackfin/kernel/setup.c
+++ b/arch/blackfin/kernel/setup.c
@@ -60,7 +60,7 @@
#define BFIN_MEMMAP_MAX 128 /* number of entries in bfin_memmap */
#define BFIN_MEMMAP_RAM 1
#define BFIN_MEMMAP_RESERVED 2
-struct bfin_memmap {
+static struct bfin_memmap {
int nr_map;
struct bfin_memmap_entry {
unsigned long long addr; /* start of memory segment */
@@ -824,7 +824,15 @@
flash_probe();
#endif
+ printk(KERN_INFO "Boot Mode: %i\n", bfin_read_SYSCR() & 0xF);
+
+ /* Newer parts mirror SWRST bits in SYSCR */
+#if defined(CONFIG_BF53x) || defined(CONFIG_BF561) || \
+ defined(CONFIG_BF538) || defined(CONFIG_BF539)
_bfin_swrst = bfin_read_SWRST();
+#else
+ _bfin_swrst = bfin_read_SYSCR();
+#endif
#ifdef CONFIG_DEBUG_DOUBLEFAULT_PRINT
bfin_write_SWRST(_bfin_swrst & ~DOUBLE_FAULT);
@@ -853,7 +861,7 @@
else if (_bfin_swrst & RESET_SOFTWARE)
printk(KERN_NOTICE "Reset caused by Software reset\n");
- printk(KERN_INFO "Blackfin support (C) 2004-2008 Analog Devices, Inc.\n");
+ printk(KERN_INFO "Blackfin support (C) 2004-2009 Analog Devices, Inc.\n");
if (bfin_compiled_revid() == 0xffff)
printk(KERN_INFO "Compiled for ADSP-%s Rev any\n", CPU);
else if (bfin_compiled_revid() == -1)
diff --git a/arch/blackfin/kernel/traps.c b/arch/blackfin/kernel/traps.c
index 5b0667d..ffe7fb5 100644
--- a/arch/blackfin/kernel/traps.c
+++ b/arch/blackfin/kernel/traps.c
@@ -673,6 +673,14 @@
verbose_printk("RTI");
else if (opcode == 0x0012)
verbose_printk("RTX");
+ else if (opcode == 0x0013)
+ verbose_printk("RTN");
+ else if (opcode == 0x0014)
+ verbose_printk("RTE");
+ else if (opcode == 0x0025)
+ verbose_printk("EMUEXCPT");
+ else if (opcode == 0x0040 && opcode <= 0x0047)
+ verbose_printk("STI R%i", opcode & 7);
else if (opcode >= 0x0050 && opcode <= 0x0057)
verbose_printk("JUMP (P%i)", opcode & 7);
else if (opcode >= 0x0060 && opcode <= 0x0067)
@@ -681,6 +689,10 @@
verbose_printk("CALL (PC+P%i)", opcode & 7);
else if (opcode >= 0x0080 && opcode <= 0x0087)
verbose_printk("JUMP (PC+P%i)", opcode & 7);
+ else if (opcode >= 0x0090 && opcode <= 0x009F)
+ verbose_printk("RAISE 0x%x", opcode & 0xF);
+ else if (opcode >= 0x00A0 && opcode <= 0x00AF)
+ verbose_printk("EXCPT 0x%x", opcode & 0xF);
else if ((opcode >= 0x1000 && opcode <= 0x13FF) || (opcode >= 0x1800 && opcode <= 0x1BFF))
verbose_printk("IF !CC JUMP");
else if ((opcode >= 0x1400 && opcode <= 0x17ff) || (opcode >= 0x1c00 && opcode <= 0x1fff))
@@ -820,11 +832,8 @@
decode_address(buf, (unsigned int)stack);
printk(KERN_NOTICE " SP: [0x%p] %s\n", stack, buf);
- addr = (unsigned int *)((unsigned int)stack & ~0x3F);
-
/* First thing is to look for a frame pointer */
- for (addr = (unsigned int *)((unsigned int)stack & ~0xF), i = 0;
- addr < endstack; addr++, i++) {
+ for (addr = (unsigned int *)((unsigned int)stack & ~0xF); addr < endstack; addr++) {
if (*addr & 0x1)
continue;
ins_addr = (unsigned short *)*addr;
@@ -834,7 +843,8 @@
if (fp) {
/* Let's check to see if it is a frame pointer */
- while (fp >= (addr - 1) && fp < endstack && fp)
+ while (fp >= (addr - 1) && fp < endstack
+ && fp && ((unsigned int) fp & 0x3) == 0)
fp = (unsigned int *)*fp;
if (fp == 0 || fp == endstack) {
fp = addr - 1;
@@ -1052,8 +1062,9 @@
char buf [150];
struct irqaction *action;
unsigned int i;
- unsigned long flags;
+ unsigned long flags = 0;
unsigned int cpu = smp_processor_id();
+ unsigned char in_atomic = (bfin_read_IPEND() & 0x10) || in_atomic();
verbose_printk(KERN_NOTICE "\n" KERN_NOTICE "SEQUENCER STATUS:\t\t%s\n", print_tainted());
verbose_printk(KERN_NOTICE " SEQSTAT: %08lx IPEND: %04lx SYSCFG: %04lx\n",
@@ -1073,17 +1084,22 @@
}
verbose_printk(KERN_NOTICE " EXCAUSE : 0x%lx\n",
fp->seqstat & SEQSTAT_EXCAUSE);
- for (i = 6; i <= 15 ; i++) {
+ for (i = 2; i <= 15 ; i++) {
if (fp->ipend & (1 << i)) {
- decode_address(buf, bfin_read32(EVT0 + 4*i));
- verbose_printk(KERN_NOTICE " physical IVG%i asserted : %s\n", i, buf);
+ if (i != 4) {
+ decode_address(buf, bfin_read32(EVT0 + 4*i));
+ verbose_printk(KERN_NOTICE " physical IVG%i asserted : %s\n", i, buf);
+ } else
+ verbose_printk(KERN_NOTICE " interrupts disabled\n");
}
}
/* if no interrupts are going off, don't print this out */
if (fp->ipend & ~0x3F) {
for (i = 0; i < (NR_IRQS - 1); i++) {
- spin_lock_irqsave(&irq_desc[i].lock, flags);
+ if (!in_atomic)
+ spin_lock_irqsave(&irq_desc[i].lock, flags);
+
action = irq_desc[i].action;
if (!action)
goto unlock;
@@ -1096,7 +1112,8 @@
}
verbose_printk("\n");
unlock:
- spin_unlock_irqrestore(&irq_desc[i].lock, flags);
+ if (!in_atomic)
+ spin_unlock_irqrestore(&irq_desc[i].lock, flags);
}
}
diff --git a/arch/blackfin/mach-bf518/boards/ezbrd.c b/arch/blackfin/mach-bf518/boards/ezbrd.c
index 15f1351..0e17534 100644
--- a/arch/blackfin/mach-bf518/boards/ezbrd.c
+++ b/arch/blackfin/mach-bf518/boards/ezbrd.c
@@ -46,6 +46,7 @@
#include <asm/dpmc.h>
#include <asm/bfin_sdh.h>
#include <linux/spi/ad7877.h>
+#include <net/dsa.h>
/*
* Name the Board for the /proc/cpuinfo
@@ -104,8 +105,31 @@
#endif
#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)
+static struct platform_device bfin_mii_bus = {
+ .name = "bfin_mii_bus",
+};
+
static struct platform_device bfin_mac_device = {
.name = "bfin_mac",
+ .dev.platform_data = &bfin_mii_bus,
+};
+#endif
+
+#if defined(CONFIG_NET_DSA_KSZ8893M) || defined(CONFIG_NET_DSA_KSZ8893M_MODULE)
+static struct dsa_platform_data ksz8893m_switch_data = {
+ .mii_bus = &bfin_mii_bus.dev,
+ .netdev = &bfin_mac_device.dev,
+ .port_names[0] = NULL,
+ .port_names[1] = "eth%d",
+ .port_names[2] = "eth%d",
+ .port_names[3] = "cpu",
+};
+
+static struct platform_device ksz8893m_switch_device = {
+ .name = "dsa",
+ .id = 0,
+ .num_resources = 0,
+ .dev.platform_data = &ksz8893m_switch_data,
};
#endif
@@ -147,6 +171,15 @@
};
#endif
+#if defined(CONFIG_NET_DSA_KSZ8893M) \
+ || defined(CONFIG_NET_DSA_KSZ8893M_MODULE)
+/* SPI SWITCH CHIP */
+static struct bfin5xx_spi_chip spi_switch_info = {
+ .enable_dma = 0,
+ .bits_per_word = 8,
+};
+#endif
+
#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE)
static struct bfin5xx_spi_chip spi_mmc_chip_info = {
.enable_dma = 1,
@@ -226,6 +259,19 @@
},
#endif
+#if defined(CONFIG_NET_DSA_KSZ8893M) \
+ || defined(CONFIG_NET_DSA_KSZ8893M_MODULE)
+ {
+ .modalias = "ksz8893m",
+ .max_speed_hz = 5000000,
+ .bus_num = 0,
+ .chip_select = 1,
+ .platform_data = NULL,
+ .controller_data = &spi_switch_info,
+ .mode = SPI_MODE_3,
+ },
+#endif
+
#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE)
{
.modalias = "spi_mmc_dummy",
@@ -473,7 +519,6 @@
};
#endif
-#ifdef CONFIG_I2C_BOARDINFO
static struct i2c_board_info __initdata bfin_i2c_board_info[] = {
#if defined(CONFIG_TWI_LCD) || defined(CONFIG_TWI_LCD_MODULE)
{
@@ -487,7 +532,6 @@
},
#endif
};
-#endif
#if defined(CONFIG_SERIAL_BFIN_SPORT) || defined(CONFIG_SERIAL_BFIN_SPORT_MODULE)
static struct platform_device bfin_sport0_uart_device = {
@@ -584,9 +628,14 @@
#endif
#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)
+ &bfin_mii_bus,
&bfin_mac_device,
#endif
+#if defined(CONFIG_NET_DSA_KSZ8893M) || defined(CONFIG_NET_DSA_KSZ8893M_MODULE)
+ &ksz8893m_switch_device,
+#endif
+
#if defined(CONFIG_SPI_BFIN) || defined(CONFIG_SPI_BFIN_MODULE)
&bfin_spi0_device,
&bfin_spi1_device,
@@ -632,12 +681,8 @@
static int __init ezbrd_init(void)
{
printk(KERN_INFO "%s(): registering device resources\n", __func__);
-
-#ifdef CONFIG_I2C_BOARDINFO
i2c_register_board_info(0, bfin_i2c_board_info,
ARRAY_SIZE(bfin_i2c_board_info));
-#endif
-
platform_add_devices(stamp_devices, ARRAY_SIZE(stamp_devices));
spi_register_board_info(bfin_spi_board_info, ARRAY_SIZE(bfin_spi_board_info));
return 0;
@@ -649,7 +694,7 @@
{
/* workaround reboot hang when booting from SPI */
if ((bfin_read_SYSCR() & 0x7) == 0x3)
- bfin_gpio_reset_spi0_ssel1();
+ bfin_reset_boot_spi_cs(P_DEFAULT_BOOT_SPI_CS);
}
void bfin_get_ether_addr(char *addr)
diff --git a/arch/blackfin/mach-bf518/include/mach/portmux.h b/arch/blackfin/mach-bf518/include/mach/portmux.h
index ac16d54..f618b48 100644
--- a/arch/blackfin/mach-bf518/include/mach/portmux.h
+++ b/arch/blackfin/mach-bf518/include/mach/portmux.h
@@ -103,6 +103,8 @@
#define P_SPI1_SSEL4 (P_DEFINED | P_IDENT(GPIO_PF8) | P_FUNCT(2))
#define P_SPI1_SSEL5 (P_DEFINED | P_IDENT(GPIO_PG11) | P_FUNCT(2))
+#define P_DEFAULT_BOOT_SPI_CS P_SPI0_SSEL2
+
/* SPORT Port Mux */
#define P_SPORT0_DRPRI (P_DEFINED | P_IDENT(GPIO_PG3) | P_FUNCT(0))
#define P_SPORT0_RSCLK (P_DEFINED | P_IDENT(GPIO_PG4) | P_FUNCT(0))
diff --git a/arch/blackfin/mach-bf527/boards/cm_bf527.c b/arch/blackfin/mach-bf527/boards/cm_bf527.c
index a2c3578..856c097 100644
--- a/arch/blackfin/mach-bf527/boards/cm_bf527.c
+++ b/arch/blackfin/mach-bf527/boards/cm_bf527.c
@@ -403,8 +403,13 @@
#endif
#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)
+static struct platform_device bfin_mii_bus = {
+ .name = "bfin_mii_bus",
+};
+
static struct platform_device bfin_mac_device = {
.name = "bfin_mac",
+ .dev.platform_data = &bfin_mii_bus,
};
#endif
@@ -793,7 +798,6 @@
};
#endif
-#ifdef CONFIG_I2C_BOARDINFO
static struct i2c_board_info __initdata bfin_i2c_board_info[] = {
#if defined(CONFIG_TWI_LCD) || defined(CONFIG_TWI_LCD_MODULE)
{
@@ -809,7 +813,6 @@
},
#endif
};
-#endif
#if defined(CONFIG_SERIAL_BFIN_SPORT) || defined(CONFIG_SERIAL_BFIN_SPORT_MODULE)
static struct platform_device bfin_sport0_uart_device = {
@@ -920,6 +923,7 @@
#endif
#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)
+ &bfin_mii_bus,
&bfin_mac_device,
#endif
@@ -968,27 +972,23 @@
&bfin_gpios_device,
};
-static int __init stamp_init(void)
+static int __init cm_init(void)
{
printk(KERN_INFO "%s(): registering device resources\n", __func__);
-
-#ifdef CONFIG_I2C_BOARDINFO
i2c_register_board_info(0, bfin_i2c_board_info,
ARRAY_SIZE(bfin_i2c_board_info));
-#endif
-
platform_add_devices(stamp_devices, ARRAY_SIZE(stamp_devices));
spi_register_board_info(bfin_spi_board_info, ARRAY_SIZE(bfin_spi_board_info));
return 0;
}
-arch_initcall(stamp_init);
+arch_initcall(cm_init);
void native_machine_restart(char *cmd)
{
/* workaround reboot hang when booting from SPI */
if ((bfin_read_SYSCR() & 0x7) == 0x3)
- bfin_gpio_reset_spi0_ssel1();
+ bfin_reset_boot_spi_cs(P_DEFAULT_BOOT_SPI_CS);
}
void bfin_get_ether_addr(char *addr)
diff --git a/arch/blackfin/mach-bf527/boards/ezbrd.c b/arch/blackfin/mach-bf527/boards/ezbrd.c
index 0314bd3..83606fc 100644
--- a/arch/blackfin/mach-bf527/boards/ezbrd.c
+++ b/arch/blackfin/mach-bf527/boards/ezbrd.c
@@ -208,8 +208,13 @@
#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)
+static struct platform_device bfin_mii_bus = {
+ .name = "bfin_mii_bus",
+};
+
static struct platform_device bfin_mac_device = {
.name = "bfin_mac",
+ .dev.platform_data = &bfin_mii_bus,
};
#endif
@@ -590,7 +595,6 @@
};
#endif
-#ifdef CONFIG_I2C_BOARDINFO
static struct i2c_board_info __initdata bfin_i2c_board_info[] = {
#if defined(CONFIG_TWI_LCD) || defined(CONFIG_TWI_LCD_MODULE)
{
@@ -604,7 +608,6 @@
},
#endif
};
-#endif
#if defined(CONFIG_SERIAL_BFIN_SPORT) || defined(CONFIG_SERIAL_BFIN_SPORT_MODULE)
static struct platform_device bfin_sport0_uart_device = {
@@ -720,6 +723,7 @@
#endif
#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)
+ &bfin_mii_bus,
&bfin_mac_device,
#endif
@@ -764,27 +768,23 @@
&bfin_gpios_device,
};
-static int __init stamp_init(void)
+static int __init ezbrd_init(void)
{
printk(KERN_INFO "%s(): registering device resources\n", __func__);
-
-#ifdef CONFIG_I2C_BOARDINFO
i2c_register_board_info(0, bfin_i2c_board_info,
ARRAY_SIZE(bfin_i2c_board_info));
-#endif
-
platform_add_devices(stamp_devices, ARRAY_SIZE(stamp_devices));
spi_register_board_info(bfin_spi_board_info, ARRAY_SIZE(bfin_spi_board_info));
return 0;
}
-arch_initcall(stamp_init);
+arch_initcall(ezbrd_init);
void native_machine_restart(char *cmd)
{
/* workaround reboot hang when booting from SPI */
if ((bfin_read_SYSCR() & 0x7) == 0x3)
- bfin_gpio_reset_spi0_ssel1();
+ bfin_reset_boot_spi_cs(P_DEFAULT_BOOT_SPI_CS);
}
void bfin_get_ether_addr(char *addr)
diff --git a/arch/blackfin/mach-bf527/boards/ezkit.c b/arch/blackfin/mach-bf527/boards/ezkit.c
index 9454fb7..d086411 100644
--- a/arch/blackfin/mach-bf527/boards/ezkit.c
+++ b/arch/blackfin/mach-bf527/boards/ezkit.c
@@ -425,8 +425,13 @@
#endif
#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)
+static struct platform_device bfin_mii_bus = {
+ .name = "bfin_mii_bus",
+};
+
static struct platform_device bfin_mac_device = {
.name = "bfin_mac",
+ .dev.platform_data = &bfin_mii_bus,
};
#endif
@@ -830,7 +835,6 @@
};
#endif
-#ifdef CONFIG_I2C_BOARDINFO
static struct i2c_board_info __initdata bfin_i2c_board_info[] = {
#if defined(CONFIG_TWI_LCD) || defined(CONFIG_TWI_LCD_MODULE)
{
@@ -844,7 +848,6 @@
},
#endif
};
-#endif
#if defined(CONFIG_SERIAL_BFIN_SPORT) || defined(CONFIG_SERIAL_BFIN_SPORT_MODULE)
static struct platform_device bfin_sport0_uart_device = {
@@ -988,6 +991,7 @@
#endif
#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)
+ &bfin_mii_bus,
&bfin_mac_device,
#endif
@@ -1048,27 +1052,23 @@
&bfin_gpios_device,
};
-static int __init stamp_init(void)
+static int __init ezkit_init(void)
{
printk(KERN_INFO "%s(): registering device resources\n", __func__);
-
-#ifdef CONFIG_I2C_BOARDINFO
i2c_register_board_info(0, bfin_i2c_board_info,
ARRAY_SIZE(bfin_i2c_board_info));
-#endif
-
platform_add_devices(stamp_devices, ARRAY_SIZE(stamp_devices));
spi_register_board_info(bfin_spi_board_info, ARRAY_SIZE(bfin_spi_board_info));
return 0;
}
-arch_initcall(stamp_init);
+arch_initcall(ezkit_init);
void native_machine_restart(char *cmd)
{
/* workaround reboot hang when booting from SPI */
if ((bfin_read_SYSCR() & 0x7) == 0x3)
- bfin_gpio_reset_spi0_ssel1();
+ bfin_reset_boot_spi_cs(P_DEFAULT_BOOT_SPI_CS);
}
void bfin_get_ether_addr(char *addr)
diff --git a/arch/blackfin/mach-bf527/include/mach/portmux.h b/arch/blackfin/mach-bf527/include/mach/portmux.h
index 7f6da2c3..72b1652 100644
--- a/arch/blackfin/mach-bf527/include/mach/portmux.h
+++ b/arch/blackfin/mach-bf527/include/mach/portmux.h
@@ -73,6 +73,8 @@
#define P_HWAIT (P_DONTCARE)
+#define P_DEFAULT_BOOT_SPI_CS P_SPI0_SSEL1
+
#define P_SPI0_SS (P_DEFINED | P_IDENT(GPIO_PG1) | P_FUNCT(0))
#define P_SPI0_SSEL1 (P_DEFINED | P_IDENT(GPIO_PG1) | P_FUNCT(2))
#define P_SPI0_SCK (P_DEFINED | P_IDENT(GPIO_PG2) | P_FUNCT(2))
diff --git a/arch/blackfin/mach-bf533/boards/blackstamp.c b/arch/blackfin/mach-bf533/boards/blackstamp.c
index 6ee607c..015c18f 100644
--- a/arch/blackfin/mach-bf533/boards/blackstamp.c
+++ b/arch/blackfin/mach-bf533/boards/blackstamp.c
@@ -309,10 +309,8 @@
};
#endif
-#ifdef CONFIG_I2C_BOARDINFO
static struct i2c_board_info __initdata bfin_i2c_board_info[] = {
};
-#endif
static const unsigned int cclk_vlev_datasheet[] =
{
@@ -390,10 +388,8 @@
printk(KERN_INFO "%s(): registering device resources\n", __func__);
-#ifdef CONFIG_I2C_BOARDINFO
i2c_register_board_info(0, bfin_i2c_board_info,
ARRAY_SIZE(bfin_i2c_board_info));
-#endif
ret = platform_add_devices(stamp_devices, ARRAY_SIZE(stamp_devices));
if (ret < 0)
diff --git a/arch/blackfin/mach-bf533/boards/stamp.c b/arch/blackfin/mach-bf533/boards/stamp.c
index 07f9ad1..db96f33 100644
--- a/arch/blackfin/mach-bf533/boards/stamp.c
+++ b/arch/blackfin/mach-bf533/boards/stamp.c
@@ -441,7 +441,6 @@
};
#endif
-#ifdef CONFIG_I2C_BOARDINFO
static struct i2c_board_info __initdata bfin_i2c_board_info[] = {
#if defined(CONFIG_JOYSTICK_AD7142) || defined(CONFIG_JOYSTICK_AD7142_MODULE)
{
@@ -461,7 +460,6 @@
},
#endif
};
-#endif
static const unsigned int cclk_vlev_datasheet[] =
{
@@ -550,10 +548,8 @@
printk(KERN_INFO "%s(): registering device resources\n", __func__);
-#ifdef CONFIG_I2C_BOARDINFO
i2c_register_board_info(0, bfin_i2c_board_info,
ARRAY_SIZE(bfin_i2c_board_info));
-#endif
ret = platform_add_devices(stamp_devices, ARRAY_SIZE(stamp_devices));
if (ret < 0)
diff --git a/arch/blackfin/mach-bf533/include/mach/portmux.h b/arch/blackfin/mach-bf533/include/mach/portmux.h
index 685a265..2f59ce0 100644
--- a/arch/blackfin/mach-bf533/include/mach/portmux.h
+++ b/arch/blackfin/mach-bf533/include/mach/portmux.h
@@ -54,14 +54,11 @@
#define P_SPI0_SSEL2 (P_DEFINED | P_IDENT(GPIO_PF2))
#define P_SPI0_SSEL1 (P_DEFINED | P_IDENT(GPIO_PF1))
#define P_SPI0_SS (P_DEFINED | P_IDENT(GPIO_PF0))
+#define P_DEFAULT_BOOT_SPI_CS P_SPI0_SSEL2
#define P_TMR2 (P_DONTCARE)
#define P_TMR1 (P_DONTCARE)
#define P_TMR0 (P_DONTCARE)
#define P_TMRCLK (P_DEFINED | P_IDENT(GPIO_PF1))
-
-
-
-
#endif /* _MACH_PORTMUX_H_ */
diff --git a/arch/blackfin/mach-bf537/boards/cm_bf537.c b/arch/blackfin/mach-bf537/boards/cm_bf537.c
index 6ac8e4d..9cd8fb2 100644
--- a/arch/blackfin/mach-bf537/boards/cm_bf537.c
+++ b/arch/blackfin/mach-bf537/boards/cm_bf537.c
@@ -479,8 +479,13 @@
#endif
#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)
+static struct platform_device bfin_mii_bus = {
+ .name = "bfin_mii_bus",
+};
+
static struct platform_device bfin_mac_device = {
.name = "bfin_mac",
+ .dev.platform_data = &bfin_mii_bus,
};
#endif
@@ -591,6 +596,7 @@
#endif
#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)
+ &bfin_mii_bus,
&bfin_mac_device,
#endif
diff --git a/arch/blackfin/mach-bf537/boards/generic_board.c b/arch/blackfin/mach-bf537/boards/generic_board.c
index dd6e6bf..da710fd 100644
--- a/arch/blackfin/mach-bf537/boards/generic_board.c
+++ b/arch/blackfin/mach-bf537/boards/generic_board.c
@@ -262,8 +262,13 @@
#endif
#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)
+static struct platform_device bfin_mii_bus = {
+ .name = "bfin_mii_bus",
+};
+
static struct platform_device bfin_mac_device = {
.name = "bfin_mac",
+ .dev.platform_data = &bfin_mii_bus,
};
#endif
@@ -662,6 +667,7 @@
#endif
#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)
+ &bfin_mii_bus,
&bfin_mac_device,
#endif
@@ -708,7 +714,7 @@
#endif
};
-static int __init stamp_init(void)
+static int __init generic_init(void)
{
printk(KERN_INFO "%s(): registering device resources\n", __func__);
platform_add_devices(stamp_devices, ARRAY_SIZE(stamp_devices));
@@ -720,13 +726,13 @@
return 0;
}
-arch_initcall(stamp_init);
+arch_initcall(generic_init);
void native_machine_restart(char *cmd)
{
/* workaround reboot hang when booting from SPI */
if ((bfin_read_SYSCR() & 0x7) == 0x3)
- bfin_gpio_reset_spi0_ssel1();
+ bfin_reset_boot_spi_cs(P_DEFAULT_BOOT_SPI_CS);
}
#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)
diff --git a/arch/blackfin/mach-bf537/boards/minotaur.c b/arch/blackfin/mach-bf537/boards/minotaur.c
index bb79534..db7d3a3 100644
--- a/arch/blackfin/mach-bf537/boards/minotaur.c
+++ b/arch/blackfin/mach-bf537/boards/minotaur.c
@@ -61,8 +61,13 @@
#endif
#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)
+static struct platform_device bfin_mii_bus = {
+ .name = "bfin_mii_bus",
+};
+
static struct platform_device bfin_mac_device = {
.name = "bfin_mac",
+ .dev.platform_data = &bfin_mii_bus,
};
#endif
@@ -324,6 +329,7 @@
#endif
#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)
+ &bfin_mii_bus,
&bfin_mac_device,
#endif
@@ -377,5 +383,5 @@
{
/* workaround reboot hang when booting from SPI */
if ((bfin_read_SYSCR() & 0x7) == 0x3)
- bfin_gpio_reset_spi0_ssel1();
+ bfin_reset_boot_spi_cs(P_DEFAULT_BOOT_SPI_CS);
}
diff --git a/arch/blackfin/mach-bf537/boards/pnav10.c b/arch/blackfin/mach-bf537/boards/pnav10.c
index 89de94f..590eb3a 100644
--- a/arch/blackfin/mach-bf537/boards/pnav10.c
+++ b/arch/blackfin/mach-bf537/boards/pnav10.c
@@ -198,8 +198,13 @@
#endif
#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)
+static struct platform_device bfin_mii_bus = {
+ .name = "bfin_mii_bus",
+};
+
static struct platform_device bfin_mac_device = {
.name = "bfin_mac",
+ .dev.platform_data = &bfin_mii_bus,
};
#endif
@@ -529,6 +534,7 @@
#endif
#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)
+ &bfin_mii_bus,
&bfin_mac_device,
#endif
@@ -558,7 +564,7 @@
#endif
};
-static int __init stamp_init(void)
+static int __init pnav_init(void)
{
printk(KERN_INFO "%s(): registering device resources\n", __func__);
platform_add_devices(stamp_devices, ARRAY_SIZE(stamp_devices));
@@ -569,7 +575,7 @@
return 0;
}
-arch_initcall(stamp_init);
+arch_initcall(pnav_init);
void bfin_get_ether_addr(char *addr)
{
diff --git a/arch/blackfin/mach-bf537/boards/stamp.c b/arch/blackfin/mach-bf537/boards/stamp.c
index d812e25..cd04c5e 100644
--- a/arch/blackfin/mach-bf537/boards/stamp.c
+++ b/arch/blackfin/mach-bf537/boards/stamp.c
@@ -321,8 +321,13 @@
#endif
#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)
+static struct platform_device bfin_mii_bus = {
+ .name = "bfin_mii_bus",
+};
+
static struct platform_device bfin_mac_device = {
.name = "bfin_mac",
+ .dev.platform_data = &bfin_mii_bus,
};
#endif
@@ -1068,7 +1073,6 @@
};
#endif
-#ifdef CONFIG_I2C_BOARDINFO
static struct i2c_board_info __initdata bfin_i2c_board_info[] = {
#if defined(CONFIG_JOYSTICK_AD7142) || defined(CONFIG_JOYSTICK_AD7142_MODULE)
{
@@ -1102,7 +1106,6 @@
},
#endif
};
-#endif
#if defined(CONFIG_SERIAL_BFIN_SPORT) || defined(CONFIG_SERIAL_BFIN_SPORT_MODULE)
static struct platform_device bfin_sport0_uart_device = {
@@ -1217,6 +1220,7 @@
#endif
#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)
+ &bfin_mii_bus,
&bfin_mac_device,
#endif
@@ -1284,12 +1288,8 @@
static int __init stamp_init(void)
{
printk(KERN_INFO "%s(): registering device resources\n", __func__);
-
-#ifdef CONFIG_I2C_BOARDINFO
i2c_register_board_info(0, bfin_i2c_board_info,
ARRAY_SIZE(bfin_i2c_board_info));
-#endif
-
bfin_plat_nand_init();
platform_add_devices(stamp_devices, ARRAY_SIZE(stamp_devices));
spi_register_board_info(bfin_spi_board_info, ARRAY_SIZE(bfin_spi_board_info));
@@ -1307,7 +1307,7 @@
{
/* workaround reboot hang when booting from SPI */
if ((bfin_read_SYSCR() & 0x7) == 0x3)
- bfin_gpio_reset_spi0_ssel1();
+ bfin_reset_boot_spi_cs(P_DEFAULT_BOOT_SPI_CS);
}
/*
diff --git a/arch/blackfin/mach-bf537/boards/tcm_bf537.c b/arch/blackfin/mach-bf537/boards/tcm_bf537.c
index 2f4b066..3f4f203 100644
--- a/arch/blackfin/mach-bf537/boards/tcm_bf537.c
+++ b/arch/blackfin/mach-bf537/boards/tcm_bf537.c
@@ -481,8 +481,13 @@
#endif
#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)
+static struct platform_device bfin_mii_bus = {
+ .name = "bfin_mii_bus",
+};
+
static struct platform_device bfin_mac_device = {
.name = "bfin_mac",
+ .dev.platform_data = &bfin_mii_bus,
};
#endif
@@ -593,6 +598,7 @@
#endif
#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)
+ &bfin_mii_bus,
&bfin_mac_device,
#endif
@@ -615,7 +621,7 @@
&bfin_gpios_device,
};
-static int __init cm_bf537_init(void)
+static int __init tcm_bf537_init(void)
{
printk(KERN_INFO "%s(): registering device resources\n", __func__);
platform_add_devices(cm_bf537_devices, ARRAY_SIZE(cm_bf537_devices));
@@ -629,7 +635,7 @@
return 0;
}
-arch_initcall(cm_bf537_init);
+arch_initcall(tcm_bf537_init);
void bfin_get_ether_addr(char *addr)
{
diff --git a/arch/blackfin/mach-bf537/include/mach/portmux.h b/arch/blackfin/mach-bf537/include/mach/portmux.h
index 78fee6e..87285e7 100644
--- a/arch/blackfin/mach-bf537/include/mach/portmux.h
+++ b/arch/blackfin/mach-bf537/include/mach/portmux.h
@@ -31,6 +31,7 @@
#define P_PPI0_FS1 (P_DEFINED | P_IDENT(GPIO_PF9) | P_FUNCT(1))
#define P_TACLK0 (P_DEFINED | P_IDENT(GPIO_PF14) | P_FUNCT(1))
#define P_TMRCLK (P_DEFINED | P_IDENT(GPIO_PF15) | P_FUNCT(1))
+#define P_DEFAULT_BOOT_SPI_CS P_SPI0_SSEL1
#define P_PPI0_D0 (P_DEFINED | P_IDENT(GPIO_PG0) | P_FUNCT(0))
#define P_PPI0_D1 (P_DEFINED | P_IDENT(GPIO_PG1) | P_FUNCT(0))
diff --git a/arch/blackfin/mach-bf538/include/mach/portmux.h b/arch/blackfin/mach-bf538/include/mach/portmux.h
index 1e031b5..c8db264 100644
--- a/arch/blackfin/mach-bf538/include/mach/portmux.h
+++ b/arch/blackfin/mach-bf538/include/mach/portmux.h
@@ -102,5 +102,6 @@
#define P_SPI0_SSEL2 (P_DEFINED | P_IDENT(GPIO_PF2))
#define P_SPI0_SSEL1 (P_DEFINED | P_IDENT(GPIO_PF1))
#define P_SPI0_SS (P_DEFINED | P_IDENT(GPIO_PF0))
+#define P_DEFAULT_BOOT_SPI_CS P_SPI0_SSEL2
#endif /* _MACH_PORTMUX_H_ */
diff --git a/arch/blackfin/mach-bf548/boards/ezkit.c b/arch/blackfin/mach-bf548/boards/ezkit.c
index 309c160..096e661 100644
--- a/arch/blackfin/mach-bf548/boards/ezkit.c
+++ b/arch/blackfin/mach-bf548/boards/ezkit.c
@@ -781,7 +781,6 @@
#endif
#endif
-#ifdef CONFIG_I2C_BOARDINFO
static struct i2c_board_info __initdata bfin_i2c_board_info0[] = {
};
@@ -800,7 +799,6 @@
#endif
};
#endif
-#endif
#if defined(CONFIG_KEYBOARD_GPIO) || defined(CONFIG_KEYBOARD_GPIO_MODULE)
#include <linux/gpio_keys.h>
@@ -956,14 +954,12 @@
{
printk(KERN_INFO "%s(): registering device resources\n", __func__);
-#ifdef CONFIG_I2C_BOARDINFO
i2c_register_board_info(0, bfin_i2c_board_info0,
ARRAY_SIZE(bfin_i2c_board_info0));
#if !defined(CONFIG_BF542) /* The BF542 only has 1 TWI */
i2c_register_board_info(1, bfin_i2c_board_info1,
ARRAY_SIZE(bfin_i2c_board_info1));
#endif
-#endif
platform_add_devices(ezkit_devices, ARRAY_SIZE(ezkit_devices));
diff --git a/arch/blackfin/mach-bf548/include/mach/anomaly.h b/arch/blackfin/mach-bf548/include/mach/anomaly.h
index 3b54309..23d03c5 100644
--- a/arch/blackfin/mach-bf548/include/mach/anomaly.h
+++ b/arch/blackfin/mach-bf548/include/mach/anomaly.h
@@ -175,6 +175,7 @@
#define ANOMALY_05000311 (0)
#define ANOMALY_05000323 (0)
#define ANOMALY_05000363 (0)
+#define ANOMALY_05000380 (0)
#define ANOMALY_05000412 (0)
#define ANOMALY_05000432 (0)
#define ANOMALY_05000435 (0)
diff --git a/arch/blackfin/mach-bf548/include/mach/bf548.h b/arch/blackfin/mach-bf548/include/mach/bf548.h
index f0e5699..cd31f72 100644
--- a/arch/blackfin/mach-bf548/include/mach/bf548.h
+++ b/arch/blackfin/mach-bf548/include/mach/bf548.h
@@ -104,6 +104,18 @@
#define AMGCTLVAL (V_AMBEN | V_AMCKEN)
+#if defined(CONFIG_BF542M)
+# define CONFIG_BF542
+#elif defined(CONFIG_BF544M)
+# define CONFIG_BF544
+#elif defined(CONFIG_BF547M)
+# define CONFIG_BF547
+#elif defined(CONFIG_BF548M)
+# define CONFIG_BF548
+#elif defined(CONFIG_BF549M)
+# define CONFIG_BF549
+#endif
+
#if defined(CONFIG_BF542)
# define CPU "BF542"
# define CPUID 0x27de
diff --git a/arch/blackfin/mach-bf548/include/mach/gpio.h b/arch/blackfin/mach-bf548/include/mach/gpio.h
index bba82dc..3a20517 100644
--- a/arch/blackfin/mach-bf548/include/mach/gpio.h
+++ b/arch/blackfin/mach-bf548/include/mach/gpio.h
@@ -195,17 +195,17 @@
struct gpio_port_t {
unsigned short port_fer;
unsigned short dummy1;
- unsigned short port_data;
+ unsigned short data;
unsigned short dummy2;
- unsigned short port_set;
+ unsigned short data_set;
unsigned short dummy3;
- unsigned short port_clear;
+ unsigned short data_clear;
unsigned short dummy4;
- unsigned short port_dir_set;
+ unsigned short dir_set;
unsigned short dummy5;
- unsigned short port_dir_clear;
+ unsigned short dir_clear;
unsigned short dummy6;
- unsigned short port_inen;
+ unsigned short inen;
unsigned short dummy7;
unsigned int port_mux;
};
diff --git a/arch/blackfin/mach-bf548/include/mach/portmux.h b/arch/blackfin/mach-bf548/include/mach/portmux.h
index 8177a56..ffb1d0a 100644
--- a/arch/blackfin/mach-bf548/include/mach/portmux.h
+++ b/arch/blackfin/mach-bf548/include/mach/portmux.h
@@ -125,6 +125,7 @@
#define P_KEY_COL2 (P_DEFINED | P_IDENT(GPIO_PD14) | P_FUNCT(3))
#define P_KEY_COL3 (P_DEFINED | P_IDENT(GPIO_PD15) | P_FUNCT(3))
+#define P_DEFAULT_BOOT_SPI_CS P_SPI0_SSEL1
#define P_SPI0_SCK (P_DEFINED | P_IDENT(GPIO_PE0) | P_FUNCT(0))
#define P_SPI0_MISO (P_DEFINED | P_IDENT(GPIO_PE1) | P_FUNCT(0))
#define P_SPI0_MOSI (P_DEFINED | P_IDENT(GPIO_PE2) | P_FUNCT(0))
diff --git a/arch/blackfin/mach-bf561/include/mach/defBF561.h b/arch/blackfin/mach-bf561/include/mach/defBF561.h
index d7c5097..cf92229 100644
--- a/arch/blackfin/mach-bf561/include/mach/defBF561.h
+++ b/arch/blackfin/mach-bf561/include/mach/defBF561.h
@@ -1106,6 +1106,8 @@
#define DLEN_8 0x0 /* PPI Data Length mask for DLEN=8 */
#define DLEN(x) (((x-9) & 0x07) << 11) /* PPI Data Length (only works for x=10-->x=16) */
#define POL 0x0000C000 /* PPI Signal Polarities */
+#define POLC 0x4000 /* PPI Clock Polarity */
+#define POLS 0x8000 /* PPI Frame Sync Polarity */
/* PPI_STATUS Masks */
#define FLD 0x00000400 /* Field Indicator */
diff --git a/arch/blackfin/mach-bf561/include/mach/portmux.h b/arch/blackfin/mach-bf561/include/mach/portmux.h
index a6ee820..2e5ad63 100644
--- a/arch/blackfin/mach-bf561/include/mach/portmux.h
+++ b/arch/blackfin/mach-bf561/include/mach/portmux.h
@@ -85,5 +85,6 @@
#define P_SPI0_MOSI (P_DONTCARE)
#define P_SPI0_MISO (P_DONTCARE)
#define P_SPI0_SCK (P_DONTCARE)
+#define P_DEFAULT_BOOT_SPI_CS P_SPI0_SSEL2
#endif /* _MACH_PORTMUX_H_ */
diff --git a/arch/blackfin/mach-common/clocks-init.c b/arch/blackfin/mach-common/clocks-init.c
index 5d182ab..9dddb6f 100644
--- a/arch/blackfin/mach-common/clocks-init.c
+++ b/arch/blackfin/mach-common/clocks-init.c
@@ -14,6 +14,7 @@
#include <asm/clocks.h>
#include <asm/mem_init.h>
+#define SDGCTL_WIDTH (1 << 31) /* SDRAM external data path width */
#define PLL_CTL_VAL \
(((CONFIG_VCO_MULT & 63) << 9) | CLKIN_HALF | \
(PLL_BYPASS << 8) | (ANOMALY_05000265 ? 0x8000 : 0))
@@ -76,7 +77,7 @@
bfin_write_PLL_DIV(CONFIG_CCLK_ACT_DIV | CONFIG_SCLK_DIV);
#ifdef EBIU_SDGCTL
bfin_write_EBIU_SDRRC(mem_SDRRC);
- bfin_write_EBIU_SDGCTL(mem_SDGCTL);
+ bfin_write_EBIU_SDGCTL((bfin_read_EBIU_SDGCTL() & SDGCTL_WIDTH) | mem_SDGCTL);
#else
bfin_write_EBIU_RSTCTL(bfin_read_EBIU_RSTCTL() & ~(SRREQ));
do_sync();
diff --git a/arch/blackfin/mach-common/entry.S b/arch/blackfin/mach-common/entry.S
index fae7746..88de053 100644
--- a/arch/blackfin/mach-common/entry.S
+++ b/arch/blackfin/mach-common/entry.S
@@ -151,13 +151,6 @@
jump.s _bfin_return_from_exception;
ENDPROC(_ex_syscall)
-ENTRY(_ex_soft_bp)
- r7 = retx;
- r7 += -2;
- retx = r7;
- jump.s _ex_trap_c;
-ENDPROC(_ex_soft_bp)
-
ENTRY(_ex_single_step)
/* If we just returned from an interrupt, the single step event is
for the RTI instruction. */
@@ -1087,7 +1080,7 @@
* EXCPT instruction can provide 4 bits of EXCAUSE, allowing 16 to be user defined
*/
.long _ex_syscall /* 0x00 - User Defined - Linux Syscall */
- .long _ex_soft_bp /* 0x01 - User Defined - Software breakpoint */
+ .long _ex_trap_c /* 0x01 - User Defined - Software breakpoint */
#ifdef CONFIG_KGDB
.long _ex_trap_c /* 0x02 - User Defined - KGDB initial connection
and break signal trap */
diff --git a/arch/blackfin/mach-common/head.S b/arch/blackfin/mach-common/head.S
index e1e42c0..698d4c0 100644
--- a/arch/blackfin/mach-common/head.S
+++ b/arch/blackfin/mach-common/head.S
@@ -17,6 +17,19 @@
__INIT
+ENTRY(__init_clear_bss)
+ r2 = r2 - r1;
+ cc = r2 == 0;
+ if cc jump .L_bss_done;
+ r2 >>= 2;
+ p1 = r1;
+ p2 = r2;
+ lsetup (1f, 1f) lc0 = p2;
+1: [p1++] = r0;
+.L_bss_done:
+ rts;
+ENDPROC(__init_clear_bss)
+
#define INITIAL_STACK (L1_SCRATCH_START + L1_SCRATCH_LENGTH - 12)
ENTRY(__start)
@@ -144,6 +157,35 @@
call _init_early_exception_vectors;
#endif
+ r0 = 0 (x);
+ /* Zero out all of the fun bss regions */
+#if L1_DATA_A_LENGTH > 0
+ r1.l = __sbss_l1;
+ r1.h = __sbss_l1;
+ r2.l = __ebss_l1;
+ r2.h = __ebss_l1;
+ call __init_clear_bss
+#endif
+#if L1_DATA_B_LENGTH > 0
+ r1.l = __sbss_b_l1;
+ r1.h = __sbss_b_l1;
+ r2.l = __ebss_b_l1;
+ r2.h = __ebss_b_l1;
+ call __init_clear_bss
+#endif
+#if L2_LENGTH > 0
+ r1.l = __sbss_l2;
+ r1.h = __sbss_l2;
+ r2.l = __ebss_l2;
+ r2.h = __ebss_l2;
+ call __init_clear_bss
+#endif
+ r1.l = ___bss_start;
+ r1.h = ___bss_start;
+ r2.l = ___bss_stop;
+ r2.h = ___bss_stop;
+ call __init_clear_bss
+
/* Put The Code for PLL Programming and SDRAM Programming in L1 ISRAM */
call _bfin_relocate_l1_mem;
#ifdef CONFIG_BFIN_KERNEL_CLOCK
@@ -185,19 +227,6 @@
# define WDOG_CTL WDOGA_CTL
#endif
-ENTRY(__init_clear_bss)
- r2 = r2 - r1;
- cc = r2 == 0;
- if cc jump .L_bss_done;
- r2 >>= 2;
- p1 = r1;
- p2 = r2;
- lsetup (1f, 1f) lc0 = p2;
-1: [p1++] = r0;
-.L_bss_done:
- rts;
-ENDPROC(__init_clear_bss)
-
ENTRY(_real_start)
/* Enable nested interrupts */
[--sp] = reti;
@@ -209,35 +238,6 @@
w[p0] = r0;
ssync;
- r0 = 0 (x);
- /* Zero out all of the fun bss regions */
-#if L1_DATA_A_LENGTH > 0
- r1.l = __sbss_l1;
- r1.h = __sbss_l1;
- r2.l = __ebss_l1;
- r2.h = __ebss_l1;
- call __init_clear_bss
-#endif
-#if L1_DATA_B_LENGTH > 0
- r1.l = __sbss_b_l1;
- r1.h = __sbss_b_l1;
- r2.l = __ebss_b_l1;
- r2.h = __ebss_b_l1;
- call __init_clear_bss
-#endif
-#if L2_LENGTH > 0
- r1.l = __sbss_l2;
- r1.h = __sbss_l2;
- r2.l = __ebss_l2;
- r2.h = __ebss_l2;
- call __init_clear_bss
-#endif
- r1.l = ___bss_start;
- r1.h = ___bss_start;
- r2.l = ___bss_stop;
- r2.h = ___bss_stop;
- call __init_clear_bss
-
/* Pass the u-boot arguments to the global value command line */
R0 = R7;
call _cmdline_init;
diff --git a/arch/blackfin/mach-common/interrupt.S b/arch/blackfin/mach-common/interrupt.S
index 473df0f..43c4eb9 100644
--- a/arch/blackfin/mach-common/interrupt.S
+++ b/arch/blackfin/mach-common/interrupt.S
@@ -195,7 +195,7 @@
/* Interrupt routine for evt2 (NMI).
* We don't actually use this, so just return.
* For inner circle type details, please see:
- * http://docs.blackfin.uclinux.org/doku.php?id=linux:nmi
+ * http://docs.blackfin.uclinux.org/doku.php?id=linux-kernel:nmi
*/
ENTRY(_evt_nmi)
.weak _evt_nmi
diff --git a/arch/blackfin/mach-common/ints-priority.c b/arch/blackfin/mach-common/ints-priority.c
index 1bba603..2024945 100644
--- a/arch/blackfin/mach-common/ints-priority.c
+++ b/arch/blackfin/mach-common/ints-priority.c
@@ -1101,10 +1101,9 @@
IMASK_IVG14 | IMASK_IVG13 | IMASK_IVG12 | IMASK_IVG11 |
IMASK_IVG10 | IMASK_IVG9 | IMASK_IVG8 | IMASK_IVG7 | IMASK_IVGHW;
-#if defined(CONFIG_BF54x) || defined(CONFIG_BF52x) || defined(CONFIG_BF561) \
- || defined(BF538_FAMILY) || defined(CONFIG_BF51x)
+#ifdef SIC_IWR0
bfin_write_SIC_IWR0(IWR_DISABLE_ALL);
-#if defined(CONFIG_BF52x) || defined(CONFIG_BF51x)
+# ifdef SIC_IWR1
/* BF52x/BF51x system reset does not properly reset SIC_IWR1 which
* will screw up the bootrom as it relies on MDMA0/1 waking it
* up from IDLE instructions. See this report for more info:
@@ -1114,10 +1113,8 @@
bfin_write_SIC_IWR1(IWR_ENABLE(10) | IWR_ENABLE(11));
else
bfin_write_SIC_IWR1(IWR_DISABLE_ALL);
-#else
- bfin_write_SIC_IWR1(IWR_DISABLE_ALL);
-#endif
-# ifdef CONFIG_BF54x
+# endif
+# ifdef SIC_IWR2
bfin_write_SIC_IWR2(IWR_DISABLE_ALL);
# endif
#else
diff --git a/arch/blackfin/mach-common/pm.c b/arch/blackfin/mach-common/pm.c
index d3d70fd..f48a6ae 100644
--- a/arch/blackfin/mach-common/pm.c
+++ b/arch/blackfin/mach-common/pm.c
@@ -82,10 +82,9 @@
bfin_pm_standby_restore();
-#if defined(CONFIG_BF54x) || defined(CONFIG_BF52x) || defined(CONFIG_BF561) || \
- defined(CONFIG_BF538) || defined(CONFIG_BF539) || defined(CONFIG_BF51x)
+#ifdef SIC_IWR0
bfin_write_SIC_IWR0(IWR_DISABLE_ALL);
-#if defined(CONFIG_BF52x) || defined(CONFIG_BF51x)
+# ifdef SIC_IWR1
/* BF52x system reset does not properly reset SIC_IWR1 which
* will screw up the bootrom as it relies on MDMA0/1 waking it
* up from IDLE instructions. See this report for more info:
@@ -95,10 +94,8 @@
bfin_write_SIC_IWR1(IWR_ENABLE(10) | IWR_ENABLE(11));
else
bfin_write_SIC_IWR1(IWR_DISABLE_ALL);
-#else
- bfin_write_SIC_IWR1(IWR_DISABLE_ALL);
-#endif
-# ifdef CONFIG_BF54x
+# endif
+# ifdef SIC_IWR2
bfin_write_SIC_IWR2(IWR_DISABLE_ALL);
# endif
#else
diff --git a/arch/ia64/include/asm/percpu.h b/arch/ia64/include/asm/percpu.h
index 77f30b6..30cf465 100644
--- a/arch/ia64/include/asm/percpu.h
+++ b/arch/ia64/include/asm/percpu.h
@@ -27,12 +27,12 @@
#else /* ! SMP */
-#define PER_CPU_ATTRIBUTES __attribute__((__section__(".data.percpu")))
-
#define per_cpu_init() (__phys_per_cpu_start)
#endif /* SMP */
+#define PER_CPU_BASE_SECTION ".data.percpu"
+
/*
* Be extremely careful when taking the address of this variable! Due to virtual
* remapping, it is different from the canonical address returned by __get_cpu_var(var)!
diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h
index 32f3af1..3193f44 100644
--- a/arch/ia64/include/asm/topology.h
+++ b/arch/ia64/include/asm/topology.h
@@ -84,7 +84,7 @@
.child = NULL, \
.groups = NULL, \
.min_interval = 8, \
- .max_interval = 8*(min(num_online_cpus(), 32)), \
+ .max_interval = 8*(min(num_online_cpus(), 32U)), \
.busy_factor = 64, \
.imbalance_pct = 125, \
.cache_nice_tries = 2, \
diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c
index 5cfd3d9..006ad36 100644
--- a/arch/ia64/kernel/iosapic.c
+++ b/arch/ia64/kernel/iosapic.c
@@ -880,7 +880,7 @@
if (iosapic_intr_info[irq].count == 0) {
#ifdef CONFIG_SMP
/* Clear affinity */
- cpus_setall(idesc->affinity);
+ cpumask_setall(idesc->affinity);
#endif
/* Clear the interrupt information */
iosapic_intr_info[irq].dest = 0;
diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c
index a58f64c..226233a 100644
--- a/arch/ia64/kernel/irq.c
+++ b/arch/ia64/kernel/irq.c
@@ -103,7 +103,7 @@
void set_irq_affinity_info (unsigned int irq, int hwid, int redir)
{
if (irq < NR_IRQS) {
- cpumask_copy(&irq_desc[irq].affinity,
+ cpumask_copy(irq_desc[irq].affinity,
cpumask_of(cpu_logical_id(hwid)));
irq_redir[irq] = (char) (redir & 0xff);
}
@@ -148,7 +148,7 @@
if (desc->status == IRQ_PER_CPU)
continue;
- if (cpumask_any_and(&irq_desc[irq].affinity, cpu_online_mask)
+ if (cpumask_any_and(irq_desc[irq].affinity, cpu_online_mask)
>= nr_cpu_ids) {
/*
* Save it for phase 2 processing
diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c
index 28d3d48..927ad02 100644
--- a/arch/ia64/kernel/irq_ia64.c
+++ b/arch/ia64/kernel/irq_ia64.c
@@ -493,11 +493,13 @@
saved_tpr = ia64_getreg(_IA64_REG_CR_TPR);
ia64_srlz_d();
while (vector != IA64_SPURIOUS_INT_VECTOR) {
+ struct irq_desc *desc = irq_to_desc(vector);
+
if (unlikely(IS_LOCAL_TLB_FLUSH(vector))) {
smp_local_flush_tlb();
- kstat_this_cpu.irqs[vector]++;
+ kstat_incr_irqs_this_cpu(vector, desc);
} else if (unlikely(IS_RESCHEDULE(vector)))
- kstat_this_cpu.irqs[vector]++;
+ kstat_incr_irqs_this_cpu(vector, desc);
else {
int irq = local_vector_to_irq(vector);
@@ -551,11 +553,13 @@
* Perform normal interrupt style processing
*/
while (vector != IA64_SPURIOUS_INT_VECTOR) {
+ struct irq_desc *desc = irq_to_desc(vector);
+
if (unlikely(IS_LOCAL_TLB_FLUSH(vector))) {
smp_local_flush_tlb();
- kstat_this_cpu.irqs[vector]++;
+ kstat_incr_irqs_this_cpu(vector, desc);
} else if (unlikely(IS_RESCHEDULE(vector)))
- kstat_this_cpu.irqs[vector]++;
+ kstat_incr_irqs_this_cpu(vector, desc);
else {
struct pt_regs *old_regs = set_irq_regs(NULL);
int irq = local_vector_to_irq(vector);
diff --git a/arch/ia64/kernel/msi_ia64.c b/arch/ia64/kernel/msi_ia64.c
index 8903393..dcb6b7c 100644
--- a/arch/ia64/kernel/msi_ia64.c
+++ b/arch/ia64/kernel/msi_ia64.c
@@ -75,7 +75,7 @@
msg.data = data;
write_msi_msg(irq, &msg);
- irq_desc[irq].affinity = cpumask_of_cpu(cpu);
+ cpumask_copy(irq_desc[irq].affinity, cpumask_of(cpu));
}
#endif /* CONFIG_SMP */
@@ -187,7 +187,7 @@
msg.address_lo |= MSI_ADDR_DESTID_CPU(cpu_physical_id(cpu));
dmar_msi_write(irq, &msg);
- irq_desc[irq].affinity = *mask;
+ cpumask_copy(irq_desc[irq].affinity, mask);
}
#endif /* CONFIG_SMP */
diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S
index 10a7d47e..f45e4e5 100644
--- a/arch/ia64/kernel/vmlinux.lds.S
+++ b/arch/ia64/kernel/vmlinux.lds.S
@@ -219,6 +219,7 @@
.data.percpu PERCPU_ADDR : AT(__phys_per_cpu_start - LOAD_OFFSET)
{
__per_cpu_start = .;
+ *(.data.percpu.page_aligned)
*(.data.percpu)
*(.data.percpu.shared_aligned)
__per_cpu_end = .;
diff --git a/arch/ia64/sn/kernel/io_acpi_init.c b/arch/ia64/sn/kernel/io_acpi_init.c
index c5a2140..d0223ab 100644
--- a/arch/ia64/sn/kernel/io_acpi_init.c
+++ b/arch/ia64/sn/kernel/io_acpi_init.c
@@ -443,7 +443,7 @@
size = pci_resource_len(dev, PCI_ROM_RESOURCE);
addr = ioremap(pcidev_info->pdi_pio_mapped_addr[PCI_ROM_RESOURCE],
size);
- image_size = pci_get_rom_size(addr, size);
+ image_size = pci_get_rom_size(dev, addr, size);
dev->resource[PCI_ROM_RESOURCE].start = (unsigned long) addr;
dev->resource[PCI_ROM_RESOURCE].end =
(unsigned long) addr + image_size - 1;
diff --git a/arch/ia64/sn/kernel/io_init.c b/arch/ia64/sn/kernel/io_init.c
index 4e1801b..e2eb2da 100644
--- a/arch/ia64/sn/kernel/io_init.c
+++ b/arch/ia64/sn/kernel/io_init.c
@@ -269,7 +269,7 @@
rom = ioremap(pci_resource_start(dev, PCI_ROM_RESOURCE),
size + 1);
- image_size = pci_get_rom_size(rom, size + 1);
+ image_size = pci_get_rom_size(dev, rom, size + 1);
dev->resource[PCI_ROM_RESOURCE].end =
dev->resource[PCI_ROM_RESOURCE].start +
image_size - 1;
diff --git a/arch/ia64/sn/kernel/msi_sn.c b/arch/ia64/sn/kernel/msi_sn.c
index ca553b0..81e4289 100644
--- a/arch/ia64/sn/kernel/msi_sn.c
+++ b/arch/ia64/sn/kernel/msi_sn.c
@@ -205,7 +205,7 @@
msg.address_lo = (u32)(bus_addr & 0x00000000ffffffff);
write_msi_msg(irq, &msg);
- irq_desc[irq].affinity = *cpu_mask;
+ cpumask_copy(irq_desc[irq].affinity, cpu_mask);
}
#endif /* CONFIG_SMP */
diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h
index abc62aa..3214ade 100644
--- a/arch/mips/include/asm/irq.h
+++ b/arch/mips/include/asm/irq.h
@@ -66,7 +66,7 @@
*/
#define IRQ_AFFINITY_HOOK(irq) \
do { \
- if (!cpu_isset(smp_processor_id(), irq_desc[irq].affinity)) { \
+ if (!cpumask_test_cpu(smp_processor_id(), irq_desc[irq].affinity)) {\
smtc_forward_irq(irq); \
irq_exit(); \
return; \
diff --git a/arch/mips/kernel/irq-gic.c b/arch/mips/kernel/irq-gic.c
index 494a49a..87deb8f 100644
--- a/arch/mips/kernel/irq-gic.c
+++ b/arch/mips/kernel/irq-gic.c
@@ -187,7 +187,7 @@
set_bit(irq, pcpu_masks[first_cpu(tmp)].pcpu_mask);
}
- irq_desc[irq].affinity = *cpumask;
+ cpumask_copy(irq_desc[irq].affinity, cpumask);
spin_unlock_irqrestore(&gic_lock, flags);
}
diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c
index b6cca01..5f5af7d 100644
--- a/arch/mips/kernel/smtc.c
+++ b/arch/mips/kernel/smtc.c
@@ -686,7 +686,7 @@
* and efficiency, we just pick the easiest one to find.
*/
- target = first_cpu(irq_desc[irq].affinity);
+ target = cpumask_first(irq_desc[irq].affinity);
/*
* We depend on the platform code to have correctly processed
@@ -921,11 +921,13 @@
struct clock_event_device *cd;
void *arg_copy = pipi->arg;
int type_copy = pipi->type;
+ int irq = MIPS_CPU_IRQ_BASE + 1;
+
smtc_ipi_nq(&freeIPIq, pipi);
switch (type_copy) {
case SMTC_CLOCK_TICK:
irq_enter();
- kstat_this_cpu.irqs[MIPS_CPU_IRQ_BASE + 1]++;
+ kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
cd = &per_cpu(mips_clockevent_device, cpu);
cd->event_handler(cd);
irq_exit();
diff --git a/arch/mips/mti-malta/malta-smtc.c b/arch/mips/mti-malta/malta-smtc.c
index aabd727..5ba3188 100644
--- a/arch/mips/mti-malta/malta-smtc.c
+++ b/arch/mips/mti-malta/malta-smtc.c
@@ -116,7 +116,7 @@
void plat_set_irq_affinity(unsigned int irq, const struct cpumask *affinity)
{
- cpumask_t tmask = *affinity;
+ cpumask_t tmask;
int cpu = 0;
void smtc_set_irq_affinity(unsigned int irq, cpumask_t aff);
@@ -139,11 +139,12 @@
* be made to forward to an offline "CPU".
*/
+ cpumask_copy(&tmask, affinity);
for_each_cpu(cpu, affinity) {
if ((cpu_data[cpu].vpe_id != 0) || !cpu_online(cpu))
cpu_clear(cpu, tmask);
}
- irq_desc[irq].affinity = tmask;
+ cpumask_copy(irq_desc[irq].affinity, &tmask);
if (cpus_empty(tmask))
/*
diff --git a/arch/mips/sgi-ip22/ip22-int.c b/arch/mips/sgi-ip22/ip22-int.c
index f8b18af..0ecd5fe 100644
--- a/arch/mips/sgi-ip22/ip22-int.c
+++ b/arch/mips/sgi-ip22/ip22-int.c
@@ -155,7 +155,7 @@
int irq = SGI_BUSERR_IRQ;
irq_enter();
- kstat_this_cpu.irqs[irq]++;
+ kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
ip22_be_interrupt(irq);
irq_exit();
}
diff --git a/arch/mips/sgi-ip22/ip22-time.c b/arch/mips/sgi-ip22/ip22-time.c
index 3dcb27e..c8f7d23 100644
--- a/arch/mips/sgi-ip22/ip22-time.c
+++ b/arch/mips/sgi-ip22/ip22-time.c
@@ -122,7 +122,7 @@
char c;
irq_enter();
- kstat_this_cpu.irqs[irq]++;
+ kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
printk(KERN_ALERT "Oops, got 8254 interrupt.\n");
ArcRead(0, &c, 1, &cnt);
ArcEnterInteractiveMode();
diff --git a/arch/mips/sibyte/bcm1480/smp.c b/arch/mips/sibyte/bcm1480/smp.c
index dddfda8..3146916 100644
--- a/arch/mips/sibyte/bcm1480/smp.c
+++ b/arch/mips/sibyte/bcm1480/smp.c
@@ -178,9 +178,10 @@
void bcm1480_mailbox_interrupt(void)
{
int cpu = smp_processor_id();
+ int irq = K_BCM1480_INT_MBOX_0_0;
unsigned int action;
- kstat_this_cpu.irqs[K_BCM1480_INT_MBOX_0_0]++;
+ kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
/* Load the mailbox register to figure out what we're supposed to do */
action = (__raw_readq(mailbox_0_regs[cpu]) >> 48) & 0xffff;
diff --git a/arch/mips/sibyte/sb1250/smp.c b/arch/mips/sibyte/sb1250/smp.c
index 5950a288..cad1400 100644
--- a/arch/mips/sibyte/sb1250/smp.c
+++ b/arch/mips/sibyte/sb1250/smp.c
@@ -166,9 +166,10 @@
void sb1250_mailbox_interrupt(void)
{
int cpu = smp_processor_id();
+ int irq = K_INT_MBOX_0;
unsigned int action;
- kstat_this_cpu.irqs[K_INT_MBOX_0]++;
+ kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
/* Load the mailbox register to figure out what we're supposed to do */
action = (____raw_readq(mailbox_regs[cpu]) >> 48) & 0xffff;
diff --git a/arch/mn10300/kernel/mn10300-watchdog.c b/arch/mn10300/kernel/mn10300-watchdog.c
index 10811e9..2e370d8 100644
--- a/arch/mn10300/kernel/mn10300-watchdog.c
+++ b/arch/mn10300/kernel/mn10300-watchdog.c
@@ -130,6 +130,7 @@
* the stack NMI-atomically, it's safe to use smp_processor_id().
*/
int sum, cpu = smp_processor_id();
+ int irq = NMIIRQ;
u8 wdt, tmp;
wdt = WDCTR & ~WDCTR_WDCNE;
@@ -138,7 +139,7 @@
NMICR = NMICR_WDIF;
nmi_count(cpu)++;
- kstat_this_cpu.irqs[NMIIRQ]++;
+ kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
sum = irq_stat[cpu].__irq_count;
if (last_irq_sums[cpu] == sum) {
diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c
index ac2c822..4948280 100644
--- a/arch/parisc/kernel/irq.c
+++ b/arch/parisc/kernel/irq.c
@@ -120,7 +120,7 @@
if (CHECK_IRQ_PER_CPU(irq)) {
/* Bad linux design decision. The mask has already
* been set; we must reset it */
- irq_desc[irq].affinity = CPU_MASK_ALL;
+ cpumask_setall(irq_desc[irq].affinity);
return -EINVAL;
}
@@ -136,7 +136,7 @@
if (cpu_check_affinity(irq, dest))
return;
- irq_desc[irq].affinity = *dest;
+ cpumask_copy(irq_desc[irq].affinity, dest);
}
#endif
@@ -295,7 +295,7 @@
unsigned long txn_affinity_addr(unsigned int irq, int cpu)
{
#ifdef CONFIG_SMP
- irq_desc[irq].affinity = cpumask_of_cpu(cpu);
+ cpumask_copy(irq_desc[irq].affinity, cpumask_of(cpu));
#endif
return per_cpu(cpu_data, cpu).txn_addr;
@@ -352,7 +352,7 @@
irq = eirr_to_irq(eirr_val);
#ifdef CONFIG_SMP
- dest = irq_desc[irq].affinity;
+ cpumask_copy(&dest, irq_desc[irq].affinity);
if (CHECK_IRQ_PER_CPU(irq_desc[irq].status) &&
!cpu_isset(smp_processor_id(), dest)) {
int cpu = first_cpu(dest);
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 23b8b5e..ad1e5ac 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -231,7 +231,7 @@
if (irq_desc[irq].status & IRQ_PER_CPU)
continue;
- cpus_and(mask, irq_desc[irq].affinity, map);
+ cpumask_and(&mask, irq_desc[irq].affinity, &map);
if (any_online_cpu(mask) == NR_CPUS) {
printk("Breaking affinity for irq %i\n", irq);
mask = map;
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 161b9b9..295ccc5 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -184,6 +184,7 @@
. = ALIGN(PAGE_SIZE);
.data.percpu : AT(ADDR(.data.percpu) - LOAD_OFFSET) {
__per_cpu_start = .;
+ *(.data.percpu.page_aligned)
*(.data.percpu)
*(.data.percpu.shared_aligned)
__per_cpu_end = .;
diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c
index 84e058f..80b5134 100644
--- a/arch/powerpc/platforms/pseries/xics.c
+++ b/arch/powerpc/platforms/pseries/xics.c
@@ -153,9 +153,10 @@
{
int server;
/* For the moment only implement delivery to all cpus or one cpu */
- cpumask_t cpumask = irq_desc[virq].affinity;
+ cpumask_t cpumask;
cpumask_t tmp = CPU_MASK_NONE;
+ cpumask_copy(&cpumask, irq_desc[virq].affinity);
if (!distribute_irqs)
return default_server;
@@ -869,7 +870,7 @@
virq, cpu);
/* Reset affinity to all cpus */
- irq_desc[virq].affinity = CPU_MASK_ALL;
+ cpumask_setall(irq_desc[virq].affinity);
desc->chip->set_affinity(virq, cpu_all_mask);
unlock:
spin_unlock_irqrestore(&desc->lock, flags);
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index a35297d..532e205 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -566,9 +566,10 @@
#ifdef CONFIG_SMP
static int irq_choose_cpu(unsigned int virt_irq)
{
- cpumask_t mask = irq_desc[virt_irq].affinity;
+ cpumask_t mask;
int cpuid;
+ cpumask_copy(&mask, irq_desc[virt_irq].affinity);
if (cpus_equal(mask, CPU_MASK_ALL)) {
static int irq_rover;
static DEFINE_SPINLOCK(irq_rover_lock);
diff --git a/arch/sh/boards/board-ap325rxa.c b/arch/sh/boards/board-ap325rxa.c
index caf4c33..7c35787 100644
--- a/arch/sh/boards/board-ap325rxa.c
+++ b/arch/sh/boards/board-ap325rxa.c
@@ -22,6 +22,7 @@
#include <linux/gpio.h>
#include <linux/spi/spi.h>
#include <linux/spi/spi_gpio.h>
+#include <media/ov772x.h>
#include <media/soc_camera_platform.h>
#include <media/sh_mobile_ceu.h>
#include <video/sh_mobile_lcdc.h>
@@ -216,7 +217,14 @@
},
};
+static void camera_power(int val)
+{
+ gpio_set_value(GPIO_PTZ5, val); /* RST_CAM/RSTB */
+ mdelay(10);
+}
+
#ifdef CONFIG_I2C
+/* support for the old ncm03j camera */
static unsigned char camera_ncm03j_magic[] =
{
0x87, 0x00, 0x88, 0x08, 0x89, 0x01, 0x8A, 0xE8,
@@ -237,6 +245,23 @@
0x63, 0xD4, 0x64, 0xEA, 0xD6, 0x0F,
};
+static int camera_probe(void)
+{
+ struct i2c_adapter *a = i2c_get_adapter(0);
+ struct i2c_msg msg;
+ int ret;
+
+ camera_power(1);
+ msg.addr = 0x6e;
+ msg.buf = camera_ncm03j_magic;
+ msg.len = 2;
+ msg.flags = 0;
+ ret = i2c_transfer(a, &msg, 1);
+ camera_power(0);
+
+ return ret;
+}
+
static int camera_set_capture(struct soc_camera_platform_info *info,
int enable)
{
@@ -245,9 +270,11 @@
int ret = 0;
int i;
+ camera_power(0);
if (!enable)
return 0; /* no disable for now */
+ camera_power(1);
for (i = 0; i < ARRAY_SIZE(camera_ncm03j_magic); i += 2) {
u_int8_t buf[8];
@@ -286,8 +313,35 @@
.platform_data = &camera_info,
},
};
+
+static int __init camera_setup(void)
+{
+ if (camera_probe() > 0)
+ platform_device_register(&camera_device);
+
+ return 0;
+}
+late_initcall(camera_setup);
+
#endif /* CONFIG_I2C */
+static int ov7725_power(struct device *dev, int mode)
+{
+ camera_power(0);
+ if (mode)
+ camera_power(1);
+
+ return 0;
+}
+
+static struct ov772x_camera_info ov7725_info = {
+ .buswidth = SOCAM_DATAWIDTH_8,
+ .flags = OV772X_FLAG_VFLIP | OV772X_FLAG_HFLIP,
+ .link = {
+ .power = ov7725_power,
+ },
+};
+
static struct sh_mobile_ceu_info sh_mobile_ceu_info = {
.flags = SOCAM_PCLK_SAMPLE_RISING | SOCAM_HSYNC_ACTIVE_HIGH |
SOCAM_VSYNC_ACTIVE_HIGH | SOCAM_MASTER | SOCAM_DATAWIDTH_8,
@@ -338,9 +392,6 @@
&ap325rxa_nor_flash_device,
&lcdc_device,
&ceu_device,
-#ifdef CONFIG_I2C
- &camera_device,
-#endif
&nand_flash_device,
&sdcard_cn3_device,
};
@@ -349,6 +400,10 @@
{
I2C_BOARD_INFO("pcf8563", 0x51),
},
+ {
+ I2C_BOARD_INFO("ov772x", 0x21),
+ .platform_data = &ov7725_info,
+ },
};
static struct spi_board_info ap325rxa_spi_devices[] = {
@@ -426,7 +481,7 @@
gpio_request(GPIO_PTZ6, NULL);
gpio_direction_output(GPIO_PTZ6, 0); /* STBY_CAM */
gpio_request(GPIO_PTZ5, NULL);
- gpio_direction_output(GPIO_PTZ5, 1); /* RST_CAM */
+ gpio_direction_output(GPIO_PTZ5, 0); /* RST_CAM */
gpio_request(GPIO_PTZ4, NULL);
gpio_direction_output(GPIO_PTZ4, 0); /* SADDR */
diff --git a/arch/sh/configs/ap325rxa_defconfig b/arch/sh/configs/ap325rxa_defconfig
index 5c423fa..352f87d 100644
--- a/arch/sh/configs/ap325rxa_defconfig
+++ b/arch/sh/configs/ap325rxa_defconfig
@@ -1,7 +1,7 @@
#
# Automatically generated make config: don't edit
-# Linux kernel version: 2.6.28
-# Fri Jan 9 16:54:19 2009
+# Linux kernel version: 2.6.29-rc2
+# Tue Jan 27 11:45:08 2009
#
CONFIG_SUPERH=y
CONFIG_SUPERH32=y
@@ -45,12 +45,12 @@
# CONFIG_AUDIT is not set
# CONFIG_IKCONFIG is not set
CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_CGROUPS is not set
CONFIG_GROUP_SCHED=y
CONFIG_FAIR_GROUP_SCHED=y
# CONFIG_RT_GROUP_SCHED is not set
CONFIG_USER_SCHED=y
# CONFIG_CGROUP_SCHED is not set
+# CONFIG_CGROUPS is not set
CONFIG_SYSFS_DEPRECATED=y
CONFIG_SYSFS_DEPRECATED_V2=y
# CONFIG_RELAY is not set
@@ -378,6 +378,7 @@
# CONFIG_WIRELESS_EXT is not set
# CONFIG_LIB80211 is not set
# CONFIG_MAC80211 is not set
+# CONFIG_WIMAX is not set
# CONFIG_RFKILL is not set
# CONFIG_NET_9P is not set
@@ -400,6 +401,7 @@
# CONFIG_MTD_DEBUG is not set
CONFIG_MTD_CONCAT=y
CONFIG_MTD_PARTITIONS=y
+# CONFIG_MTD_TESTS is not set
# CONFIG_MTD_REDBOOT_PARTS is not set
CONFIG_MTD_CMDLINE_PARTS=y
# CONFIG_MTD_AR7_PARTS is not set
@@ -447,9 +449,7 @@
#
# CONFIG_MTD_COMPLEX_MAPPINGS is not set
CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_PHYSMAP_START=0xffffffff
-CONFIG_MTD_PHYSMAP_LEN=0
-CONFIG_MTD_PHYSMAP_BANKWIDTH=0
+# CONFIG_MTD_PHYSMAP_COMPAT is not set
# CONFIG_MTD_PLATRAM is not set
#
@@ -480,6 +480,12 @@
# CONFIG_MTD_ONENAND is not set
#
+# LPDDR flash memory drivers
+#
+# CONFIG_MTD_LPDDR is not set
+# CONFIG_MTD_QINFO_PROBE is not set
+
+#
# UBI - Unsorted block images
#
CONFIG_MTD_UBI=y
@@ -607,6 +613,10 @@
# CONFIG_WLAN_PRE80211 is not set
# CONFIG_WLAN_80211 is not set
# CONFIG_IWLWIFI_LEDS is not set
+
+#
+# Enable WiMAX (Networking options) to see the WiMAX drivers
+#
# CONFIG_WAN is not set
# CONFIG_PPP is not set
# CONFIG_SLIP is not set
@@ -790,6 +800,7 @@
# CONFIG_PMIC_DA903X is not set
# CONFIG_MFD_WM8400 is not set
# CONFIG_MFD_WM8350_I2C is not set
+# CONFIG_MFD_PCF50633 is not set
# CONFIG_REGULATOR is not set
#
@@ -837,7 +848,7 @@
# CONFIG_SOC_CAMERA_MT9V022 is not set
# CONFIG_SOC_CAMERA_TW9910 is not set
CONFIG_SOC_CAMERA_PLATFORM=y
-# CONFIG_SOC_CAMERA_OV772X is not set
+CONFIG_SOC_CAMERA_OV772X=y
CONFIG_VIDEO_SH_MOBILE_CEU=y
# CONFIG_RADIO_ADAPTERS is not set
# CONFIG_DAB is not set
@@ -1012,6 +1023,7 @@
CONFIG_FILE_LOCKING=y
# CONFIG_XFS_FS is not set
# CONFIG_OCFS2_FS is not set
+# CONFIG_BTRFS_FS is not set
CONFIG_DNOTIFY=y
CONFIG_INOTIFY=y
CONFIG_INOTIFY_USER=y
@@ -1060,6 +1072,7 @@
# CONFIG_JFFS2_FS is not set
# CONFIG_UBIFS_FS is not set
# CONFIG_CRAMFS is not set
+# CONFIG_SQUASHFS is not set
# CONFIG_VXFS_FS is not set
# CONFIG_MINIX_FS is not set
# CONFIG_OMFS_FS is not set
diff --git a/arch/sh/configs/migor_defconfig b/arch/sh/configs/migor_defconfig
index 7758263..6785767 100644
--- a/arch/sh/configs/migor_defconfig
+++ b/arch/sh/configs/migor_defconfig
@@ -1,7 +1,7 @@
#
# Automatically generated make config: don't edit
-# Linux kernel version: 2.6.28
-# Fri Jan 9 17:09:35 2009
+# Linux kernel version: 2.6.29-rc1
+# Thu Jan 22 09:16:16 2009
#
CONFIG_SUPERH=y
CONFIG_SUPERH32=y
@@ -45,8 +45,12 @@
CONFIG_IKCONFIG=y
CONFIG_IKCONFIG_PROC=y
CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_CGROUPS is not set
# CONFIG_GROUP_SCHED is not set
+
+#
+# Control Group support
+#
+# CONFIG_CGROUPS is not set
CONFIG_SYSFS_DEPRECATED=y
CONFIG_SYSFS_DEPRECATED_V2=y
# CONFIG_RELAY is not set
@@ -389,6 +393,7 @@
CONFIG_WIRELESS_EXT_SYSFS=y
# CONFIG_LIB80211 is not set
# CONFIG_MAC80211 is not set
+# CONFIG_WIMAX is not set
# CONFIG_RFKILL is not set
# CONFIG_NET_9P is not set
@@ -411,6 +416,7 @@
# CONFIG_MTD_DEBUG is not set
CONFIG_MTD_CONCAT=y
CONFIG_MTD_PARTITIONS=y
+# CONFIG_MTD_TESTS is not set
# CONFIG_MTD_REDBOOT_PARTS is not set
CONFIG_MTD_CMDLINE_PARTS=y
# CONFIG_MTD_AR7_PARTS is not set
@@ -458,9 +464,7 @@
#
# CONFIG_MTD_COMPLEX_MAPPINGS is not set
CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_PHYSMAP_START=0xffffffff
-CONFIG_MTD_PHYSMAP_LEN=0
-CONFIG_MTD_PHYSMAP_BANKWIDTH=0
+# CONFIG_MTD_PHYSMAP_COMPAT is not set
# CONFIG_MTD_PLATRAM is not set
#
@@ -488,6 +492,12 @@
# CONFIG_MTD_ONENAND is not set
#
+# LPDDR flash memory drivers
+#
+# CONFIG_MTD_LPDDR is not set
+# CONFIG_MTD_QINFO_PROBE is not set
+
+#
# UBI - Unsorted block images
#
# CONFIG_MTD_UBI is not set
@@ -587,6 +597,10 @@
# CONFIG_WLAN_PRE80211 is not set
# CONFIG_WLAN_80211 is not set
# CONFIG_IWLWIFI_LEDS is not set
+
+#
+# Enable WiMAX (Networking options) to see the WiMAX drivers
+#
# CONFIG_WAN is not set
# CONFIG_PPP is not set
# CONFIG_SLIP is not set
@@ -761,6 +775,7 @@
# CONFIG_PMIC_DA903X is not set
# CONFIG_MFD_WM8400 is not set
# CONFIG_MFD_WM8350_I2C is not set
+# CONFIG_MFD_PCF50633 is not set
# CONFIG_REGULATOR is not set
#
@@ -806,9 +821,9 @@
# CONFIG_SOC_CAMERA_MT9M111 is not set
# CONFIG_SOC_CAMERA_MT9T031 is not set
# CONFIG_SOC_CAMERA_MT9V022 is not set
-# CONFIG_SOC_CAMERA_TW9910 is not set
-CONFIG_SOC_CAMERA_PLATFORM=y
-# CONFIG_SOC_CAMERA_OV772X is not set
+CONFIG_SOC_CAMERA_TW9910=y
+# CONFIG_SOC_CAMERA_PLATFORM is not set
+CONFIG_SOC_CAMERA_OV772X=y
CONFIG_VIDEO_SH_MOBILE_CEU=y
# CONFIG_RADIO_ADAPTERS is not set
# CONFIG_DAB is not set
@@ -866,11 +881,13 @@
# CONFIG_USB_GADGET_PXA25X is not set
# CONFIG_USB_GADGET_PXA27X is not set
# CONFIG_USB_GADGET_S3C2410 is not set
+# CONFIG_USB_GADGET_IMX is not set
CONFIG_USB_GADGET_M66592=y
CONFIG_USB_M66592=y
CONFIG_SUPERH_BUILT_IN_M66592=y
# CONFIG_USB_GADGET_AMD5536UDC is not set
# CONFIG_USB_GADGET_FSL_QE is not set
+# CONFIG_USB_GADGET_CI13XXX is not set
# CONFIG_USB_GADGET_NET2280 is not set
# CONFIG_USB_GADGET_GOKU is not set
# CONFIG_USB_GADGET_DUMMY_HCD is not set
@@ -883,6 +900,11 @@
# CONFIG_USB_MIDI_GADGET is not set
# CONFIG_USB_G_PRINTER is not set
# CONFIG_USB_CDC_COMPOSITE is not set
+
+#
+# OTG and related infrastructure
+#
+# CONFIG_USB_GPIO_VBUS is not set
# CONFIG_MMC is not set
# CONFIG_MEMSTICK is not set
# CONFIG_NEW_LEDS is not set
@@ -961,6 +983,7 @@
CONFIG_FILE_LOCKING=y
# CONFIG_XFS_FS is not set
# CONFIG_OCFS2_FS is not set
+# CONFIG_BTRFS_FS is not set
# CONFIG_DNOTIFY is not set
# CONFIG_INOTIFY is not set
# CONFIG_QUOTA is not set
@@ -1004,6 +1027,7 @@
# CONFIG_EFS_FS is not set
# CONFIG_JFFS2_FS is not set
# CONFIG_CRAMFS is not set
+# CONFIG_SQUASHFS is not set
# CONFIG_VXFS_FS is not set
# CONFIG_MINIX_FS is not set
# CONFIG_OMFS_FS is not set
diff --git a/arch/sh/include/asm/mutex-llsc.h b/arch/sh/include/asm/mutex-llsc.h
index ee839ee..090358a 100644
--- a/arch/sh/include/asm/mutex-llsc.h
+++ b/arch/sh/include/asm/mutex-llsc.h
@@ -21,38 +21,36 @@
static inline void
__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *))
{
- int __ex_flag, __res;
+ int __done, __res;
__asm__ __volatile__ (
"movli.l @%2, %0 \n"
"add #-1, %0 \n"
"movco.l %0, @%2 \n"
"movt %1 \n"
- : "=&z" (__res), "=&r" (__ex_flag)
+ : "=&z" (__res), "=&r" (__done)
: "r" (&(count)->counter)
: "t");
- __res |= !__ex_flag;
- if (unlikely(__res != 0))
+ if (unlikely(!__done || __res != 0))
fail_fn(count);
}
static inline int
__mutex_fastpath_lock_retval(atomic_t *count, int (*fail_fn)(atomic_t *))
{
- int __ex_flag, __res;
+ int __done, __res;
__asm__ __volatile__ (
"movli.l @%2, %0 \n"
"add #-1, %0 \n"
"movco.l %0, @%2 \n"
"movt %1 \n"
- : "=&z" (__res), "=&r" (__ex_flag)
+ : "=&z" (__res), "=&r" (__done)
: "r" (&(count)->counter)
: "t");
- __res |= !__ex_flag;
- if (unlikely(__res != 0))
+ if (unlikely(!__done || __res != 0))
__res = fail_fn(count);
return __res;
@@ -61,19 +59,18 @@
static inline void
__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
{
- int __ex_flag, __res;
+ int __done, __res;
__asm__ __volatile__ (
"movli.l @%2, %0 \n\t"
"add #1, %0 \n\t"
"movco.l %0, @%2 \n\t"
"movt %1 \n\t"
- : "=&z" (__res), "=&r" (__ex_flag)
+ : "=&z" (__res), "=&r" (__done)
: "r" (&(count)->counter)
: "t");
- __res |= !__ex_flag;
- if (unlikely(__res <= 0))
+ if (unlikely(!__done || __res <= 0))
fail_fn(count);
}
diff --git a/arch/sh/include/asm/syscall_32.h b/arch/sh/include/asm/syscall_32.h
index 05a868a..5bc3468 100644
--- a/arch/sh/include/asm/syscall_32.h
+++ b/arch/sh/include/asm/syscall_32.h
@@ -21,23 +21,10 @@
*/
}
-static inline bool syscall_has_error(struct pt_regs *regs)
-{
- return (regs->sr & 0x1) ? true : false;
-}
-static inline void syscall_set_error(struct pt_regs *regs)
-{
- regs->sr |= 0x1;
-}
-static inline void syscall_clear_error(struct pt_regs *regs)
-{
- regs->sr &= ~0x1;
-}
-
static inline long syscall_get_error(struct task_struct *task,
struct pt_regs *regs)
{
- return syscall_has_error(regs) ? regs->regs[0] : 0;
+ return IS_ERR_VALUE(regs->regs[0]) ? regs->regs[0] : 0;
}
static inline long syscall_get_return_value(struct task_struct *task,
@@ -50,13 +37,10 @@
struct pt_regs *regs,
int error, long val)
{
- if (error) {
- syscall_set_error(regs);
+ if (error)
regs->regs[0] = -error;
- } else {
- syscall_clear_error(regs);
+ else
regs->regs[0] = val;
- }
}
static inline void syscall_get_arguments(struct task_struct *task,
diff --git a/arch/sh/include/asm/syscall_64.h b/arch/sh/include/asm/syscall_64.h
index e1143b9..c3561ca 100644
--- a/arch/sh/include/asm/syscall_64.h
+++ b/arch/sh/include/asm/syscall_64.h
@@ -21,23 +21,10 @@
*/
}
-static inline bool syscall_has_error(struct pt_regs *regs)
-{
- return (regs->sr & 0x1) ? true : false;
-}
-static inline void syscall_set_error(struct pt_regs *regs)
-{
- regs->sr |= 0x1;
-}
-static inline void syscall_clear_error(struct pt_regs *regs)
-{
- regs->sr &= ~0x1;
-}
-
static inline long syscall_get_error(struct task_struct *task,
struct pt_regs *regs)
{
- return syscall_has_error(regs) ? regs->regs[9] : 0;
+ return IS_ERR_VALUE(regs->regs[9]) ? regs->regs[9] : 0;
}
static inline long syscall_get_return_value(struct task_struct *task,
@@ -50,13 +37,10 @@
struct pt_regs *regs,
int error, long val)
{
- if (error) {
- syscall_set_error(regs);
+ if (error)
regs->regs[9] = -error;
- } else {
- syscall_clear_error(regs);
+ else
regs->regs[9] = val;
- }
}
static inline void syscall_get_arguments(struct task_struct *task,
diff --git a/arch/sh/kernel/cpu/sh4/fpu.c b/arch/sh/kernel/cpu/sh4/fpu.c
index 2780917..e3ea541 100644
--- a/arch/sh/kernel/cpu/sh4/fpu.c
+++ b/arch/sh/kernel/cpu/sh4/fpu.c
@@ -423,7 +423,7 @@
int m;
unsigned int hx;
- m = (finsn >> 9) & 0x7;
+ m = (finsn >> 8) & 0x7;
hx = tsk->thread.fpu.hard.fp_regs[m];
if ((tsk->thread.fpu.hard.fpscr & FPSCR_CAUSE_ERROR)
diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c
index 5342475..370d2cf 100644
--- a/arch/sh/kernel/setup.c
+++ b/arch/sh/kernel/setup.c
@@ -262,11 +262,11 @@
BOOTMEM_DEFAULT);
/*
- * reserve physical page 0 - it's a special BIOS page on many boxes,
- * enabling clean reboots, SMP operation, laptop functions.
+ * Reserve physical pages below CONFIG_ZERO_PAGE_OFFSET.
*/
- reserve_bootmem(__MEMORY_START, CONFIG_ZERO_PAGE_OFFSET,
- BOOTMEM_DEFAULT);
+ if (CONFIG_ZERO_PAGE_OFFSET != 0)
+ reserve_bootmem(__MEMORY_START, CONFIG_ZERO_PAGE_OFFSET,
+ BOOTMEM_DEFAULT);
sparse_memory_present_with_active_regions(0);
diff --git a/arch/sh/kernel/signal_32.c b/arch/sh/kernel/signal_32.c
index 77c21bd..17784e1 100644
--- a/arch/sh/kernel/signal_32.c
+++ b/arch/sh/kernel/signal_32.c
@@ -510,7 +510,6 @@
case -ERESTARTNOHAND:
no_system_call_restart:
regs->regs[0] = -EINTR;
- regs->sr |= 1;
break;
case -ERESTARTSYS:
@@ -589,8 +588,7 @@
signr = get_signal_to_deliver(&info, &ka, regs, NULL);
if (signr > 0) {
- if (regs->sr & 1)
- handle_syscall_restart(save_r0, regs, &ka.sa);
+ handle_syscall_restart(save_r0, regs, &ka.sa);
/* Whee! Actually deliver the signal. */
if (handle_signal(signr, &ka, &info, oldset,
diff --git a/arch/sh/kernel/signal_64.c b/arch/sh/kernel/signal_64.c
index b22fdfa..0663a0e 100644
--- a/arch/sh/kernel/signal_64.c
+++ b/arch/sh/kernel/signal_64.c
@@ -60,7 +60,6 @@
case -ERESTARTNOHAND:
no_system_call_restart:
regs->regs[REG_RET] = -EINTR;
- regs->sr |= 1;
break;
case -ERESTARTSYS:
@@ -109,8 +108,7 @@
signr = get_signal_to_deliver(&info, &ka, regs, 0);
if (signr > 0) {
- if (regs->sr & 1)
- handle_syscall_restart(regs, &ka.sa);
+ handle_syscall_restart(regs, &ka.sa);
/* Whee! Actually deliver the signal. */
if (handle_signal(signr, &info, &ka, oldset, regs) == 0) {
diff --git a/arch/sh/lib/checksum.S b/arch/sh/lib/checksum.S
index cbdd0d4..356c8ec9 100644
--- a/arch/sh/lib/checksum.S
+++ b/arch/sh/lib/checksum.S
@@ -36,8 +36,7 @@
*/
/*
- * unsigned int csum_partial(const unsigned char *buf, int len,
- * unsigned int sum);
+ * asmlinkage __wsum csum_partial(const void *buf, int len, __wsum sum);
*/
.text
@@ -49,11 +48,31 @@
* Fortunately, it is easy to convert 2-byte alignment to 4-byte
* alignment for the unrolled loop.
*/
- mov r5, r1
mov r4, r0
- tst #2, r0 ! Check alignment.
- bt 2f ! Jump if alignment is ok.
+ tst #3, r0 ! Check alignment.
+ bt/s 2f ! Jump if alignment is ok.
+ mov r4, r7 ! Keep a copy to check for alignment
!
+ tst #1, r0 ! Check alignment.
+ bt 21f ! Jump if alignment is boundary of 2bytes.
+
+ ! buf is odd
+ tst r5, r5
+ add #-1, r5
+ bt 9f
+ mov.b @r4+, r0
+ extu.b r0, r0
+ addc r0, r6 ! t=0 from previous tst
+ mov r6, r0
+ shll8 r6
+ shlr16 r0
+ shlr8 r0
+ or r0, r6
+ mov r4, r0
+ tst #2, r0
+ bt 2f
+21:
+ ! buf is 2 byte aligned (len could be 0)
add #-2, r5 ! Alignment uses up two bytes.
cmp/pz r5 !
bt/s 1f ! Jump if we had at least two bytes.
@@ -61,16 +80,17 @@
bra 6f
add #2, r5 ! r5 was < 2. Deal with it.
1:
- mov r5, r1 ! Save new len for later use.
mov.w @r4+, r0
extu.w r0, r0
addc r0, r6
bf 2f
add #1, r6
2:
+ ! buf is 4 byte aligned (len could be 0)
+ mov r5, r1
mov #-5, r0
- shld r0, r5
- tst r5, r5
+ shld r0, r1
+ tst r1, r1
bt/s 4f ! if it's =0, go to 4f
clrt
.align 2
@@ -92,30 +112,31 @@
addc r0, r6
addc r2, r6
movt r0
- dt r5
+ dt r1
bf/s 3b
cmp/eq #1, r0
- ! here, we know r5==0
- addc r5, r6 ! add carry to r6
+ ! here, we know r1==0
+ addc r1, r6 ! add carry to r6
4:
- mov r1, r0
+ mov r5, r0
and #0x1c, r0
tst r0, r0
- bt/s 6f
- mov r0, r5
- shlr2 r5
+ bt 6f
+ ! 4 bytes or more remaining
+ mov r0, r1
+ shlr2 r1
mov #0, r2
5:
addc r2, r6
mov.l @r4+, r2
movt r0
- dt r5
+ dt r1
bf/s 5b
cmp/eq #1, r0
addc r2, r6
- addc r5, r6 ! r5==0 here, so it means add carry-bit
+ addc r1, r6 ! r1==0 here, so it means add carry-bit
6:
- mov r1, r5
+ ! 3 bytes or less remaining
mov #3, r0
and r0, r5
tst r5, r5
@@ -139,8 +160,18 @@
8:
addc r0, r6
mov #0, r0
- addc r0, r6
+ addc r0, r6
9:
+ ! Check if the buffer was misaligned, if so realign sum
+ mov r7, r0
+ tst #1, r0
+ bt 10f
+ mov r6, r0
+ shll8 r6
+ shlr16 r0
+ shlr8 r0
+ or r0, r6
+10:
rts
mov r6, r0
diff --git a/arch/sparc/include/asm/cpudata_64.h b/arch/sparc/include/asm/cpudata_64.h
index 7da7c13..a11b89e 100644
--- a/arch/sparc/include/asm/cpudata_64.h
+++ b/arch/sparc/include/asm/cpudata_64.h
@@ -17,7 +17,7 @@
typedef struct {
/* Dcache line 1 */
unsigned int __softirq_pending; /* must be 1st, see rtrap.S */
- unsigned int __pad0;
+ unsigned int __nmi_count;
unsigned long clock_tick; /* %tick's per second */
unsigned long __pad;
unsigned int __pad1;
diff --git a/arch/sparc/include/asm/irq_64.h b/arch/sparc/include/asm/irq_64.h
index d47d4a1..1934f2c 100644
--- a/arch/sparc/include/asm/irq_64.h
+++ b/arch/sparc/include/asm/irq_64.h
@@ -66,9 +66,6 @@
extern void __init init_IRQ(void);
extern void fixup_irqs(void);
-extern int register_perfctr_intr(void (*handler)(struct pt_regs *));
-extern void release_perfctr_intr(void (*handler)(struct pt_regs *));
-
static inline void set_softint(unsigned long bits)
{
__asm__ __volatile__("wr %0, 0x0, %%set_softint"
@@ -98,5 +95,6 @@
extern void *hardirq_stack[NR_CPUS];
extern void *softirq_stack[NR_CPUS];
#define __ARCH_HAS_DO_SOFTIRQ
+#define ARCH_HAS_NMI_WATCHDOG
#endif
diff --git a/arch/sparc/include/asm/kdebug_64.h b/arch/sparc/include/asm/kdebug_64.h
index f905b77..feb3578 100644
--- a/arch/sparc/include/asm/kdebug_64.h
+++ b/arch/sparc/include/asm/kdebug_64.h
@@ -14,6 +14,8 @@
DIE_TRAP,
DIE_TRAP_TL1,
DIE_CALL,
+ DIE_NMI,
+ DIE_NMIWATCHDOG,
};
#endif
diff --git a/arch/sparc/include/asm/nmi.h b/arch/sparc/include/asm/nmi.h
new file mode 100644
index 0000000..fbd546d
--- /dev/null
+++ b/arch/sparc/include/asm/nmi.h
@@ -0,0 +1,10 @@
+#ifndef __NMI_H
+#define __NMI_H
+
+extern int __init nmi_init(void);
+extern void perfctr_irq(int irq, struct pt_regs *regs);
+extern void nmi_adjust_hz(unsigned int new_hz);
+
+extern int nmi_usable;
+
+#endif /* __NMI_H */
diff --git a/arch/sparc/include/asm/pcr.h b/arch/sparc/include/asm/pcr.h
new file mode 100644
index 0000000..a2f5c61
--- /dev/null
+++ b/arch/sparc/include/asm/pcr.h
@@ -0,0 +1,46 @@
+#ifndef __PCR_H
+#define __PCR_H
+
+struct pcr_ops {
+ u64 (*read)(void);
+ void (*write)(u64);
+};
+extern const struct pcr_ops *pcr_ops;
+
+extern void deferred_pcr_work_irq(int irq, struct pt_regs *regs);
+extern void schedule_deferred_pcr_work(void);
+
+#define PCR_PIC_PRIV 0x00000001 /* PIC access is privileged */
+#define PCR_STRACE 0x00000002 /* Trace supervisor events */
+#define PCR_UTRACE 0x00000004 /* Trace user events */
+#define PCR_N2_HTRACE 0x00000008 /* Trace hypervisor events */
+#define PCR_N2_TOE_OV0 0x00000010 /* Trap if PIC 0 overflows */
+#define PCR_N2_TOE_OV1 0x00000020 /* Trap if PIC 1 overflows */
+#define PCR_N2_MASK0 0x00003fc0
+#define PCR_N2_MASK0_SHIFT 6
+#define PCR_N2_SL0 0x0003c000
+#define PCR_N2_SL0_SHIFT 14
+#define PCR_N2_OV0 0x00040000
+#define PCR_N2_MASK1 0x07f80000
+#define PCR_N2_MASK1_SHIFT 19
+#define PCR_N2_SL1 0x78000000
+#define PCR_N2_SL1_SHIFT 27
+#define PCR_N2_OV1 0x80000000
+
+extern unsigned int picl_shift;
+
+/* In order to commonize as much of the implementation as
+ * possible, we use PICH as our counter. Mostly this is
+ * to accomodate Niagara-1 which can only count insn cycles
+ * in PICH.
+ */
+static inline u64 picl_value(unsigned int nmi_hz)
+{
+ u32 delta = local_cpu_data().clock_tick / (nmi_hz << picl_shift);
+
+ return ((u64)((0 - delta) & 0xffffffff)) << 32;
+}
+
+extern u64 pcr_enable;
+
+#endif /* __PCR_H */
diff --git a/arch/sparc/include/asm/pil.h b/arch/sparc/include/asm/pil.h
index d573820..32a7efe 100644
--- a/arch/sparc/include/asm/pil.h
+++ b/arch/sparc/include/asm/pil.h
@@ -23,6 +23,7 @@
#define PIL_SMP_CTX_NEW_VERSION 4
#define PIL_DEVICE_IRQ 5
#define PIL_SMP_CALL_FUNC_SNGL 6
+#define PIL_DEFERRED_PCR_WORK 7
#define PIL_NORMAL_MAX 14
#define PIL_NMI 15
diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile
index 53adcaa..54742e5 100644
--- a/arch/sparc/kernel/Makefile
+++ b/arch/sparc/kernel/Makefile
@@ -52,6 +52,8 @@
obj-$(CONFIG_SPARC64) += hvapi.o
obj-$(CONFIG_SPARC64) += sstate.o
obj-$(CONFIG_SPARC64) += mdesc.o
+obj-$(CONFIG_SPARC64) += pcr.o
+obj-$(CONFIG_SPARC64) += nmi.o
# sparc32 do not use GENERIC_HARDIRQS but uses the generic devres implementation
obj-$(CONFIG_SPARC32) += devres.o
diff --git a/arch/sparc/kernel/cpu.c b/arch/sparc/kernel/cpu.c
index 32d32b4..d85c3dc 100644
--- a/arch/sparc/kernel/cpu.c
+++ b/arch/sparc/kernel/cpu.c
@@ -26,6 +26,7 @@
struct cpu_info {
int psr_vers;
const char *name;
+ const char *pmu_name;
};
struct fpu_info {
@@ -45,6 +46,9 @@
#define CPU(ver, _name) \
{ .psr_vers = ver, .name = _name }
+#define CPU_PMU(ver, _name, _pmu_name) \
+{ .psr_vers = ver, .name = _name, .pmu_name = _pmu_name }
+
#define FPU(ver, _name) \
{ .fp_vers = ver, .name = _name }
@@ -183,10 +187,10 @@
},{
0x17,
.cpu_info = {
- CPU(0x10, "TI UltraSparc I (SpitFire)"),
- CPU(0x11, "TI UltraSparc II (BlackBird)"),
- CPU(0x12, "TI UltraSparc IIi (Sabre)"),
- CPU(0x13, "TI UltraSparc IIe (Hummingbird)"),
+ CPU_PMU(0x10, "TI UltraSparc I (SpitFire)", "ultra12"),
+ CPU_PMU(0x11, "TI UltraSparc II (BlackBird)", "ultra12"),
+ CPU_PMU(0x12, "TI UltraSparc IIi (Sabre)", "ultra12"),
+ CPU_PMU(0x13, "TI UltraSparc IIe (Hummingbird)", "ultra12"),
CPU(-1, NULL)
},
.fpu_info = {
@@ -199,7 +203,7 @@
},{
0x22,
.cpu_info = {
- CPU(0x10, "TI UltraSparc I (SpitFire)"),
+ CPU_PMU(0x10, "TI UltraSparc I (SpitFire)", "ultra12"),
CPU(-1, NULL)
},
.fpu_info = {
@@ -209,12 +213,12 @@
},{
0x3e,
.cpu_info = {
- CPU(0x14, "TI UltraSparc III (Cheetah)"),
- CPU(0x15, "TI UltraSparc III+ (Cheetah+)"),
- CPU(0x16, "TI UltraSparc IIIi (Jalapeno)"),
- CPU(0x18, "TI UltraSparc IV (Jaguar)"),
- CPU(0x19, "TI UltraSparc IV+ (Panther)"),
- CPU(0x22, "TI UltraSparc IIIi+ (Serrano)"),
+ CPU_PMU(0x14, "TI UltraSparc III (Cheetah)", "ultra3"),
+ CPU_PMU(0x15, "TI UltraSparc III+ (Cheetah+)", "ultra3+"),
+ CPU_PMU(0x16, "TI UltraSparc IIIi (Jalapeno)", "ultra3i"),
+ CPU_PMU(0x18, "TI UltraSparc IV (Jaguar)", "ultra3+"),
+ CPU_PMU(0x19, "TI UltraSparc IV+ (Panther)", "ultra4+"),
+ CPU_PMU(0x22, "TI UltraSparc IIIi+ (Serrano)", "ultra3i"),
CPU(-1, NULL)
},
.fpu_info = {
@@ -234,6 +238,7 @@
const char *sparc_cpu_type;
const char *sparc_fpu_type;
+const char *sparc_pmu_type;
unsigned int fsr_storage;
@@ -244,6 +249,7 @@
sparc_cpu_type = NULL;
sparc_fpu_type = NULL;
+ sparc_pmu_type = NULL;
manuf = NULL;
for (i = 0; i < ARRAY_SIZE(manufacturer_info); i++)
@@ -263,6 +269,7 @@
{
if (cpu->psr_vers == psr_vers) {
sparc_cpu_type = cpu->name;
+ sparc_pmu_type = cpu->pmu_name;
sparc_fpu_type = "No FPU";
break;
}
@@ -290,6 +297,8 @@
psr_impl, fpu_vers);
sparc_fpu_type = "Unknown FPU";
}
+ if (sparc_pmu_type == NULL)
+ sparc_pmu_type = "Unknown PMU";
}
#ifdef CONFIG_SPARC32
@@ -315,11 +324,13 @@
case SUN4V_CHIP_NIAGARA1:
sparc_cpu_type = "UltraSparc T1 (Niagara)";
sparc_fpu_type = "UltraSparc T1 integrated FPU";
+ sparc_pmu_type = "niagara";
break;
case SUN4V_CHIP_NIAGARA2:
sparc_cpu_type = "UltraSparc T2 (Niagara2)";
sparc_fpu_type = "UltraSparc T2 integrated FPU";
+ sparc_pmu_type = "niagara2";
break;
default:
diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
index cab8e028..3d2c6ba 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -196,6 +196,11 @@
seq_putc(p, '\n');
skip:
spin_unlock_irqrestore(&irq_desc[i].lock, flags);
+ } else if (i == NR_IRQS) {
+ seq_printf(p, "NMI: ");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ", cpu_data(j).__nmi_count);
+ seq_printf(p, " Non-maskable interrupts\n");
}
return 0;
}
@@ -247,9 +252,10 @@
#ifdef CONFIG_SMP
static int irq_choose_cpu(unsigned int virt_irq)
{
- cpumask_t mask = irq_desc[virt_irq].affinity;
+ cpumask_t mask;
int cpuid;
+ cpumask_copy(&mask, irq_desc[virt_irq].affinity);
if (cpus_equal(mask, CPU_MASK_ALL)) {
static int irq_rover;
static DEFINE_SPINLOCK(irq_rover_lock);
@@ -778,69 +784,6 @@
local_irq_restore(flags);
}
-static void unhandled_perf_irq(struct pt_regs *regs)
-{
- unsigned long pcr, pic;
-
- read_pcr(pcr);
- read_pic(pic);
-
- write_pcr(0);
-
- printk(KERN_EMERG "CPU %d: Got unexpected perf counter IRQ.\n",
- smp_processor_id());
- printk(KERN_EMERG "CPU %d: PCR[%016lx] PIC[%016lx]\n",
- smp_processor_id(), pcr, pic);
-}
-
-/* Almost a direct copy of the powerpc PMC code. */
-static DEFINE_SPINLOCK(perf_irq_lock);
-static void *perf_irq_owner_caller; /* mostly for debugging */
-static void (*perf_irq)(struct pt_regs *regs) = unhandled_perf_irq;
-
-/* Invoked from level 15 PIL handler in trap table. */
-void perfctr_irq(int irq, struct pt_regs *regs)
-{
- clear_softint(1 << irq);
- perf_irq(regs);
-}
-
-int register_perfctr_intr(void (*handler)(struct pt_regs *))
-{
- int ret;
-
- if (!handler)
- return -EINVAL;
-
- spin_lock(&perf_irq_lock);
- if (perf_irq != unhandled_perf_irq) {
- printk(KERN_WARNING "register_perfctr_intr: "
- "perf IRQ busy (reserved by caller %p)\n",
- perf_irq_owner_caller);
- ret = -EBUSY;
- goto out;
- }
-
- perf_irq_owner_caller = __builtin_return_address(0);
- perf_irq = handler;
-
- ret = 0;
-out:
- spin_unlock(&perf_irq_lock);
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(register_perfctr_intr);
-
-void release_perfctr_intr(void (*handler)(struct pt_regs *))
-{
- spin_lock(&perf_irq_lock);
- perf_irq_owner_caller = NULL;
- perf_irq = unhandled_perf_irq;
- spin_unlock(&perf_irq_lock);
-}
-EXPORT_SYMBOL_GPL(release_perfctr_intr);
-
#ifdef CONFIG_HOTPLUG_CPU
void fixup_irqs(void)
{
@@ -854,7 +797,7 @@
!(irq_desc[irq].status & IRQ_PER_CPU)) {
if (irq_desc[irq].chip->set_affinity)
irq_desc[irq].chip->set_affinity(irq,
- &irq_desc[irq].affinity);
+ irq_desc[irq].affinity);
}
spin_unlock_irqrestore(&irq_desc[irq].lock, flags);
}
diff --git a/arch/sparc/kernel/kernel.h b/arch/sparc/kernel/kernel.h
index 81a972e..15d8a3f 100644
--- a/arch/sparc/kernel/kernel.h
+++ b/arch/sparc/kernel/kernel.h
@@ -5,6 +5,7 @@
/* cpu.c */
extern const char *sparc_cpu_type;
+extern const char *sparc_pmu_type;
extern const char *sparc_fpu_type;
extern unsigned int fsr_storage;
diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c
new file mode 100644
index 0000000..09f088e
--- /dev/null
+++ b/arch/sparc/kernel/nmi.c
@@ -0,0 +1,224 @@
+/* Pseudo NMI support on sparc64 systems.
+ *
+ * Copyright (C) 2009 David S. Miller <davem@davemloft.net>
+ *
+ * The NMI watchdog support and infrastructure is based almost
+ * entirely upon the x86 NMI support code.
+ */
+#include <linux/kernel.h>
+#include <linux/param.h>
+#include <linux/init.h>
+#include <linux/percpu.h>
+#include <linux/nmi.h>
+#include <linux/module.h>
+#include <linux/kprobes.h>
+#include <linux/kernel_stat.h>
+#include <linux/slab.h>
+#include <linux/kdebug.h>
+#include <linux/delay.h>
+#include <linux/smp.h>
+
+#include <asm/ptrace.h>
+#include <asm/local.h>
+#include <asm/pcr.h>
+
+/* We don't have a real NMI on sparc64, but we can fake one
+ * up using profiling counter overflow interrupts and interrupt
+ * levels.
+ *
+ * The profile overflow interrupts at level 15, so we use
+ * level 14 as our IRQ off level.
+ */
+
+static int nmi_watchdog_active;
+static int panic_on_timeout;
+
+int nmi_usable;
+EXPORT_SYMBOL_GPL(nmi_usable);
+
+static unsigned int nmi_hz = HZ;
+
+static DEFINE_PER_CPU(unsigned int, last_irq_sum);
+static DEFINE_PER_CPU(local_t, alert_counter);
+static DEFINE_PER_CPU(int, nmi_touch);
+
+void touch_nmi_watchdog(void)
+{
+ if (nmi_watchdog_active) {
+ int cpu;
+
+ for_each_present_cpu(cpu) {
+ if (per_cpu(nmi_touch, cpu) != 1)
+ per_cpu(nmi_touch, cpu) = 1;
+ }
+ }
+
+ touch_softlockup_watchdog();
+}
+EXPORT_SYMBOL(touch_nmi_watchdog);
+
+static void die_nmi(const char *str, struct pt_regs *regs, int do_panic)
+{
+ if (notify_die(DIE_NMIWATCHDOG, str, regs, 0,
+ pt_regs_trap_type(regs), SIGINT) == NOTIFY_STOP)
+ return;
+
+ console_verbose();
+ bust_spinlocks(1);
+
+ printk(KERN_EMERG "%s", str);
+ printk(" on CPU%d, ip %08lx, registers:\n",
+ smp_processor_id(), regs->tpc);
+ show_regs(regs);
+
+ bust_spinlocks(0);
+
+ if (do_panic || panic_on_oops)
+ panic("Non maskable interrupt");
+
+ local_irq_enable();
+ do_exit(SIGBUS);
+}
+
+notrace __kprobes void perfctr_irq(int irq, struct pt_regs *regs)
+{
+ unsigned int sum, touched = 0;
+ int cpu = smp_processor_id();
+
+ clear_softint(1 << irq);
+ pcr_ops->write(PCR_PIC_PRIV);
+
+ local_cpu_data().__nmi_count++;
+
+ if (notify_die(DIE_NMI, "nmi", regs, 0,
+ pt_regs_trap_type(regs), SIGINT) == NOTIFY_STOP)
+ touched = 1;
+
+ sum = kstat_irqs_cpu(0, cpu);
+ if (__get_cpu_var(nmi_touch)) {
+ __get_cpu_var(nmi_touch) = 0;
+ touched = 1;
+ }
+ if (!touched && __get_cpu_var(last_irq_sum) == sum) {
+ local_inc(&__get_cpu_var(alert_counter));
+ if (local_read(&__get_cpu_var(alert_counter)) == 5 * nmi_hz)
+ die_nmi("BUG: NMI Watchdog detected LOCKUP",
+ regs, panic_on_timeout);
+ } else {
+ __get_cpu_var(last_irq_sum) = sum;
+ local_set(&__get_cpu_var(alert_counter), 0);
+ }
+ if (nmi_usable) {
+ write_pic(picl_value(nmi_hz));
+ pcr_ops->write(pcr_enable);
+ }
+}
+
+static inline unsigned int get_nmi_count(int cpu)
+{
+ return cpu_data(cpu).__nmi_count;
+}
+
+static int endflag __initdata;
+
+static __init void nmi_cpu_busy(void *data)
+{
+ local_irq_enable_in_hardirq();
+ while (endflag == 0)
+ mb();
+}
+
+static void report_broken_nmi(int cpu, int *prev_nmi_count)
+{
+ printk(KERN_CONT "\n");
+
+ printk(KERN_WARNING
+ "WARNING: CPU#%d: NMI appears to be stuck (%d->%d)!\n",
+ cpu, prev_nmi_count[cpu], get_nmi_count(cpu));
+
+ printk(KERN_WARNING
+ "Please report this to bugzilla.kernel.org,\n");
+ printk(KERN_WARNING
+ "and attach the output of the 'dmesg' command.\n");
+
+ nmi_usable = 0;
+}
+
+static void stop_watchdog(void *unused)
+{
+ pcr_ops->write(PCR_PIC_PRIV);
+}
+
+static int __init check_nmi_watchdog(void)
+{
+ unsigned int *prev_nmi_count;
+ int cpu, err;
+
+ prev_nmi_count = kmalloc(nr_cpu_ids * sizeof(unsigned int), GFP_KERNEL);
+ if (!prev_nmi_count) {
+ err = -ENOMEM;
+ goto error;
+ }
+
+ printk(KERN_INFO "Testing NMI watchdog ... ");
+
+ smp_call_function(nmi_cpu_busy, (void *)&endflag, 0);
+
+ for_each_possible_cpu(cpu)
+ prev_nmi_count[cpu] = get_nmi_count(cpu);
+ local_irq_enable();
+ mdelay((20 * 1000) / nmi_hz); /* wait 20 ticks */
+
+ for_each_online_cpu(cpu) {
+ if (get_nmi_count(cpu) - prev_nmi_count[cpu] <= 5)
+ report_broken_nmi(cpu, prev_nmi_count);
+ }
+ endflag = 1;
+ if (!nmi_usable) {
+ kfree(prev_nmi_count);
+ err = -ENODEV;
+ goto error;
+ }
+ printk("OK.\n");
+
+ nmi_hz = 1;
+
+ kfree(prev_nmi_count);
+ return 0;
+error:
+ on_each_cpu(stop_watchdog, NULL, 1);
+ return err;
+}
+
+static void start_watchdog(void *unused)
+{
+ pcr_ops->write(PCR_PIC_PRIV);
+ write_pic(picl_value(nmi_hz));
+
+ pcr_ops->write(pcr_enable);
+}
+
+void nmi_adjust_hz(unsigned int new_hz)
+{
+ nmi_hz = new_hz;
+ on_each_cpu(start_watchdog, NULL, 1);
+}
+EXPORT_SYMBOL_GPL(nmi_adjust_hz);
+
+int __init nmi_init(void)
+{
+ nmi_usable = 1;
+
+ on_each_cpu(start_watchdog, NULL, 1);
+
+ return check_nmi_watchdog();
+}
+
+static int __init setup_nmi_watchdog(char *str)
+{
+ if (!strncmp(str, "panic", 5))
+ panic_on_timeout = 1;
+
+ return 0;
+}
+__setup("nmi_watchdog=", setup_nmi_watchdog);
diff --git a/arch/sparc/kernel/pcr.c b/arch/sparc/kernel/pcr.c
new file mode 100644
index 0000000..92e0dda
--- /dev/null
+++ b/arch/sparc/kernel/pcr.c
@@ -0,0 +1,153 @@
+/* pcr.c: Generic sparc64 performance counter infrastructure.
+ *
+ * Copyright (C) 2009 David S. Miller (davem@davemloft.net)
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/irq.h>
+
+#include <asm/pil.h>
+#include <asm/pcr.h>
+#include <asm/nmi.h>
+
+/* This code is shared between various users of the performance
+ * counters. Users will be oprofile, pseudo-NMI watchdog, and the
+ * perf_counter support layer.
+ */
+
+#define PCR_SUN4U_ENABLE (PCR_PIC_PRIV | PCR_STRACE | PCR_UTRACE)
+#define PCR_N2_ENABLE (PCR_PIC_PRIV | PCR_STRACE | PCR_UTRACE | \
+ PCR_N2_TOE_OV1 | \
+ (2 << PCR_N2_SL1_SHIFT) | \
+ (0xff << PCR_N2_MASK1_SHIFT))
+
+u64 pcr_enable;
+unsigned int picl_shift;
+
+/* Performance counter interrupts run unmasked at PIL level 15.
+ * Therefore we can't do things like wakeups and other work
+ * that expects IRQ disabling to be adhered to in locking etc.
+ *
+ * Therefore in such situations we defer the work by signalling
+ * a lower level cpu IRQ.
+ */
+void deferred_pcr_work_irq(int irq, struct pt_regs *regs)
+{
+ clear_softint(1 << PIL_DEFERRED_PCR_WORK);
+}
+
+void schedule_deferred_pcr_work(void)
+{
+ set_softint(1 << PIL_DEFERRED_PCR_WORK);
+}
+
+const struct pcr_ops *pcr_ops;
+EXPORT_SYMBOL_GPL(pcr_ops);
+
+static u64 direct_pcr_read(void)
+{
+ u64 val;
+
+ read_pcr(val);
+ return val;
+}
+
+static void direct_pcr_write(u64 val)
+{
+ write_pcr(val);
+}
+
+static const struct pcr_ops direct_pcr_ops = {
+ .read = direct_pcr_read,
+ .write = direct_pcr_write,
+};
+
+static void n2_pcr_write(u64 val)
+{
+ unsigned long ret;
+
+ ret = sun4v_niagara2_setperf(HV_N2_PERF_SPARC_CTL, val);
+ if (val != HV_EOK)
+ write_pcr(val);
+}
+
+static const struct pcr_ops n2_pcr_ops = {
+ .read = direct_pcr_read,
+ .write = n2_pcr_write,
+};
+
+static unsigned long perf_hsvc_group;
+static unsigned long perf_hsvc_major;
+static unsigned long perf_hsvc_minor;
+
+static int __init register_perf_hsvc(void)
+{
+ if (tlb_type == hypervisor) {
+ switch (sun4v_chip_type) {
+ case SUN4V_CHIP_NIAGARA1:
+ perf_hsvc_group = HV_GRP_NIAG_PERF;
+ break;
+
+ case SUN4V_CHIP_NIAGARA2:
+ perf_hsvc_group = HV_GRP_N2_CPU;
+ break;
+
+ default:
+ return -ENODEV;
+ }
+
+
+ perf_hsvc_major = 1;
+ perf_hsvc_minor = 0;
+ if (sun4v_hvapi_register(perf_hsvc_group,
+ perf_hsvc_major,
+ &perf_hsvc_minor)) {
+ printk("perfmon: Could not register hvapi.\n");
+ return -ENODEV;
+ }
+ }
+ return 0;
+}
+
+static void __init unregister_perf_hsvc(void)
+{
+ if (tlb_type != hypervisor)
+ return;
+ sun4v_hvapi_unregister(perf_hsvc_group);
+}
+
+int __init pcr_arch_init(void)
+{
+ int err = register_perf_hsvc();
+
+ if (err)
+ return err;
+
+ switch (tlb_type) {
+ case hypervisor:
+ pcr_ops = &n2_pcr_ops;
+ pcr_enable = PCR_N2_ENABLE;
+ picl_shift = 2;
+ break;
+
+ case cheetah:
+ case cheetah_plus:
+ case spitfire:
+ pcr_ops = &direct_pcr_ops;
+ pcr_enable = PCR_SUN4U_ENABLE;
+ break;
+
+ default:
+ err = -ENODEV;
+ goto out_unregister;
+ }
+
+ return nmi_init();
+
+out_unregister:
+ unregister_perf_hsvc();
+ return err;
+}
+
+arch_initcall(pcr_arch_init);
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index cc8b560..a73954b 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -29,6 +29,7 @@
#include <linux/cpu.h>
#include <linux/elfcore.h>
#include <linux/sysrq.h>
+#include <linux/nmi.h>
#include <asm/uaccess.h>
#include <asm/system.h>
@@ -52,8 +53,10 @@
static void sparc64_yield(int cpu)
{
- if (tlb_type != hypervisor)
+ if (tlb_type != hypervisor) {
+ touch_nmi_watchdog();
return;
+ }
clear_thread_flag(TIF_POLLING_NRFLAG);
smp_mb__after_clear_bit();
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index 49d061f..f2bcfd2 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -354,6 +354,7 @@
seq_printf(m,
"cpu\t\t: %s\n"
"fpu\t\t: %s\n"
+ "pmu\t\t: %s\n"
"prom\t\t: %s\n"
"type\t\t: %s\n"
"ncpus probed\t: %d\n"
@@ -366,6 +367,7 @@
,
sparc_cpu_type,
sparc_fpu_type,
+ sparc_pmu_type,
prom_version,
((tlb_type == hypervisor) ?
"sun4v" :
diff --git a/arch/sparc/kernel/time_64.c b/arch/sparc/kernel/time_64.c
index 2db3c22..db310aa 100644
--- a/arch/sparc/kernel/time_64.c
+++ b/arch/sparc/kernel/time_64.c
@@ -729,7 +729,7 @@
irq_enter();
- kstat_this_cpu.irqs[0]++;
+ kstat_incr_irqs_this_cpu(0, irq_to_desc(0));
if (unlikely(!evt->event_handler)) {
printk(KERN_WARNING
diff --git a/arch/sparc/kernel/ttable.S b/arch/sparc/kernel/ttable.S
index ea92550..d9bdfb9 100644
--- a/arch/sparc/kernel/ttable.S
+++ b/arch/sparc/kernel/ttable.S
@@ -63,7 +63,8 @@
#else
tl0_irq6: BTRAP(0x46)
#endif
-tl0_irq7: BTRAP(0x47) BTRAP(0x48) BTRAP(0x49)
+tl0_irq7: TRAP_IRQ(deferred_pcr_work_irq, 7)
+tl0_irq8: BTRAP(0x48) BTRAP(0x49)
tl0_irq10: BTRAP(0x4a) BTRAP(0x4b) BTRAP(0x4c) BTRAP(0x4d)
tl0_irq14: TRAP_IRQ(timer_interrupt, 14)
tl0_irq15: TRAP_NMI_IRQ(perfctr_irq, 15)
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index a9e474b..4ab8993 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -19,6 +19,7 @@
#include <linux/interrupt.h>
#include <linux/kprobes.h>
#include <linux/kdebug.h>
+#include <linux/percpu.h>
#include <asm/page.h>
#include <asm/pgtable.h>
@@ -224,6 +225,30 @@
unhandled_fault (address, current, regs);
}
+static void noinline bogus_32bit_fault_tpc(struct pt_regs *regs)
+{
+ static int times;
+
+ if (times++ < 10)
+ printk(KERN_ERR "FAULT[%s:%d]: 32-bit process reports "
+ "64-bit TPC [%lx]\n",
+ current->comm, current->pid,
+ regs->tpc);
+ show_regs(regs);
+}
+
+static void noinline bogus_32bit_fault_address(struct pt_regs *regs,
+ unsigned long addr)
+{
+ static int times;
+
+ if (times++ < 10)
+ printk(KERN_ERR "FAULT[%s:%d]: 32-bit process "
+ "reports 64-bit fault address [%lx]\n",
+ current->comm, current->pid, addr);
+ show_regs(regs);
+}
+
asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
{
struct mm_struct *mm = current->mm;
@@ -244,6 +269,19 @@
(fault_code & FAULT_CODE_DTLB))
BUG();
+ if (test_thread_flag(TIF_32BIT)) {
+ if (!(regs->tstate & TSTATE_PRIV)) {
+ if (unlikely((regs->tpc >> 32) != 0)) {
+ bogus_32bit_fault_tpc(regs);
+ goto intr_or_no_mm;
+ }
+ }
+ if (unlikely((address >> 32) != 0)) {
+ bogus_32bit_fault_address(regs, address);
+ goto intr_or_no_mm;
+ }
+ }
+
if (regs->tstate & TSTATE_PRIV) {
unsigned long tpc = regs->tpc;
@@ -264,12 +302,6 @@
if (in_atomic() || !mm)
goto intr_or_no_mm;
- if (test_thread_flag(TIF_32BIT)) {
- if (!(regs->tstate & TSTATE_PRIV))
- regs->tpc &= 0xffffffff;
- address &= 0xffffffff;
- }
-
if (!down_read_trylock(&mm->mmap_sem)) {
if ((regs->tstate & TSTATE_PRIV) &&
!search_exception_tables(regs->tpc)) {
diff --git a/arch/sparc/oprofile/init.c b/arch/sparc/oprofile/init.c
index d6e170c..d172f86 100644
--- a/arch/sparc/oprofile/init.c
+++ b/arch/sparc/oprofile/init.c
@@ -13,217 +13,57 @@
#include <linux/init.h>
#ifdef CONFIG_SPARC64
-#include <asm/hypervisor.h>
-#include <asm/spitfire.h>
-#include <asm/cpudata.h>
-#include <asm/irq.h>
+#include <linux/notifier.h>
+#include <linux/rcupdate.h>
+#include <linux/kdebug.h>
+#include <asm/nmi.h>
-static int nmi_enabled;
-
-struct pcr_ops {
- u64 (*read)(void);
- void (*write)(u64);
-};
-static const struct pcr_ops *pcr_ops;
-
-static u64 direct_pcr_read(void)
+static int profile_timer_exceptions_notify(struct notifier_block *self,
+ unsigned long val, void *data)
{
- u64 val;
+ struct die_args *args = (struct die_args *)data;
+ int ret = NOTIFY_DONE;
- read_pcr(val);
- return val;
+ switch (val) {
+ case DIE_NMI:
+ oprofile_add_sample(args->regs, 0);
+ ret = NOTIFY_STOP;
+ break;
+ default:
+ break;
+ }
+ return ret;
}
-static void direct_pcr_write(u64 val)
-{
- write_pcr(val);
-}
-
-static const struct pcr_ops direct_pcr_ops = {
- .read = direct_pcr_read,
- .write = direct_pcr_write,
+static struct notifier_block profile_timer_exceptions_nb = {
+ .notifier_call = profile_timer_exceptions_notify,
};
-static void n2_pcr_write(u64 val)
+static int timer_start(void)
{
- unsigned long ret;
-
- ret = sun4v_niagara2_setperf(HV_N2_PERF_SPARC_CTL, val);
- if (val != HV_EOK)
- write_pcr(val);
-}
-
-static const struct pcr_ops n2_pcr_ops = {
- .read = direct_pcr_read,
- .write = n2_pcr_write,
-};
-
-/* In order to commonize as much of the implementation as
- * possible, we use PICH as our counter. Mostly this is
- * to accomodate Niagara-1 which can only count insn cycles
- * in PICH.
- */
-static u64 picl_value(void)
-{
- u32 delta = local_cpu_data().clock_tick / HZ;
-
- return ((u64)((0 - delta) & 0xffffffff)) << 32;
-}
-
-#define PCR_PIC_PRIV 0x00000001 /* PIC access is privileged */
-#define PCR_STRACE 0x00000002 /* Trace supervisor events */
-#define PCR_UTRACE 0x00000004 /* Trace user events */
-#define PCR_N2_HTRACE 0x00000008 /* Trace hypervisor events */
-#define PCR_N2_TOE_OV0 0x00000010 /* Trap if PIC 0 overflows */
-#define PCR_N2_TOE_OV1 0x00000020 /* Trap if PIC 1 overflows */
-#define PCR_N2_MASK0 0x00003fc0
-#define PCR_N2_MASK0_SHIFT 6
-#define PCR_N2_SL0 0x0003c000
-#define PCR_N2_SL0_SHIFT 14
-#define PCR_N2_OV0 0x00040000
-#define PCR_N2_MASK1 0x07f80000
-#define PCR_N2_MASK1_SHIFT 19
-#define PCR_N2_SL1 0x78000000
-#define PCR_N2_SL1_SHIFT 27
-#define PCR_N2_OV1 0x80000000
-
-#define PCR_SUN4U_ENABLE (PCR_PIC_PRIV | PCR_STRACE | PCR_UTRACE)
-#define PCR_N2_ENABLE (PCR_PIC_PRIV | PCR_STRACE | PCR_UTRACE | \
- PCR_N2_TOE_OV1 | \
- (2 << PCR_N2_SL1_SHIFT) | \
- (0xff << PCR_N2_MASK1_SHIFT))
-
-static u64 pcr_enable = PCR_SUN4U_ENABLE;
-
-static void nmi_handler(struct pt_regs *regs)
-{
- pcr_ops->write(PCR_PIC_PRIV);
-
- if (nmi_enabled) {
- oprofile_add_sample(regs, 0);
-
- write_pic(picl_value());
- pcr_ops->write(pcr_enable);
- }
-}
-
-/* We count "clock cycle" events in the lower 32-bit PIC.
- * Then configure it such that it overflows every HZ, and thus
- * generates a level 15 interrupt at that frequency.
- */
-static void cpu_nmi_start(void *_unused)
-{
- pcr_ops->write(PCR_PIC_PRIV);
- write_pic(picl_value());
-
- pcr_ops->write(pcr_enable);
-}
-
-static void cpu_nmi_stop(void *_unused)
-{
- pcr_ops->write(PCR_PIC_PRIV);
-}
-
-static int nmi_start(void)
-{
- int err = register_perfctr_intr(nmi_handler);
-
- if (!err) {
- nmi_enabled = 1;
- wmb();
- err = on_each_cpu(cpu_nmi_start, NULL, 1);
- if (err) {
- nmi_enabled = 0;
- wmb();
- on_each_cpu(cpu_nmi_stop, NULL, 1);
- release_perfctr_intr(nmi_handler);
- }
- }
-
- return err;
-}
-
-static void nmi_stop(void)
-{
- nmi_enabled = 0;
- wmb();
-
- on_each_cpu(cpu_nmi_stop, NULL, 1);
- release_perfctr_intr(nmi_handler);
- synchronize_sched();
-}
-
-static unsigned long perf_hsvc_group;
-static unsigned long perf_hsvc_major;
-static unsigned long perf_hsvc_minor;
-
-static int __init register_perf_hsvc(void)
-{
- if (tlb_type == hypervisor) {
- switch (sun4v_chip_type) {
- case SUN4V_CHIP_NIAGARA1:
- perf_hsvc_group = HV_GRP_NIAG_PERF;
- break;
-
- case SUN4V_CHIP_NIAGARA2:
- perf_hsvc_group = HV_GRP_N2_CPU;
- break;
-
- default:
- return -ENODEV;
- }
-
-
- perf_hsvc_major = 1;
- perf_hsvc_minor = 0;
- if (sun4v_hvapi_register(perf_hsvc_group,
- perf_hsvc_major,
- &perf_hsvc_minor)) {
- printk("perfmon: Could not register N2 hvapi.\n");
- return -ENODEV;
- }
- }
+ if (register_die_notifier(&profile_timer_exceptions_nb))
+ return 1;
+ nmi_adjust_hz(HZ);
return 0;
}
-static void unregister_perf_hsvc(void)
+
+static void timer_stop(void)
{
- if (tlb_type != hypervisor)
- return;
- sun4v_hvapi_unregister(perf_hsvc_group);
+ nmi_adjust_hz(1);
+ unregister_die_notifier(&profile_timer_exceptions_nb);
+ synchronize_sched(); /* Allow already-started NMIs to complete. */
}
-static int oprofile_nmi_init(struct oprofile_operations *ops)
+static int op_nmi_timer_init(struct oprofile_operations *ops)
{
- int err = register_perf_hsvc();
-
- if (err)
- return err;
-
- switch (tlb_type) {
- case hypervisor:
- pcr_ops = &n2_pcr_ops;
- pcr_enable = PCR_N2_ENABLE;
- break;
-
- case cheetah:
- case cheetah_plus:
- pcr_ops = &direct_pcr_ops;
- break;
-
- default:
+ if (!nmi_usable)
return -ENODEV;
- }
- ops->create_files = NULL;
- ops->setup = NULL;
- ops->shutdown = NULL;
- ops->start = nmi_start;
- ops->stop = nmi_stop;
+ ops->start = timer_start;
+ ops->stop = timer_stop;
ops->cpu_type = "timer";
-
- printk(KERN_INFO "oprofile: Using perfctr based NMI timer interrupt.\n");
-
+ printk(KERN_INFO "oprofile: Using perfctr NMI timer interrupt.\n");
return 0;
}
#endif
@@ -233,7 +73,7 @@
int ret = -ENODEV;
#ifdef CONFIG_SPARC64
- ret = oprofile_nmi_init(ops);
+ ret = op_nmi_timer_init(ops);
if (!ret)
return ret;
#endif
@@ -241,10 +81,6 @@
return ret;
}
-
void oprofile_arch_exit(void)
{
-#ifdef CONFIG_SPARC64
- unregister_perf_hsvc();
-#endif
}
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 9c39095..5c8e353 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -133,7 +133,7 @@
def_bool y
config HAVE_SETUP_PER_CPU_AREA
- def_bool X86_64_SMP || (X86_SMP && !X86_VOYAGER)
+ def_bool y
config HAVE_CPUMASK_OF_CPU_MAP
def_bool X86_64_SMP
@@ -391,6 +391,13 @@
as R-8610-(G).
If you don't have one of these chips, you should say N here.
+config X86_UV
+ bool "SGI Ultraviolet"
+ depends on X86_64
+ help
+ This option is needed in order to support SGI Ultraviolet systems.
+ If you don't have one of these, you should say N here.
+
config SCHED_OMIT_FRAME_POINTER
def_bool y
prompt "Single-depth WCHAN output"
@@ -1340,13 +1347,17 @@
If unsure, say Y. Only embedded should say N here.
+config CC_STACKPROTECTOR_ALL
+ bool
+
config CC_STACKPROTECTOR
bool "Enable -fstack-protector buffer overflow detection (EXPERIMENTAL)"
- depends on X86_64 && EXPERIMENTAL && BROKEN
+ depends on X86_64
+ select CC_STACKPROTECTOR_ALL
help
- This option turns on the -fstack-protector GCC feature. This
- feature puts, at the beginning of critical functions, a canary
- value on the stack just before the return address, and validates
+ This option turns on the -fstack-protector GCC feature. This
+ feature puts, at the beginning of functions, a canary value on
+ the stack just before the return address, and validates
the value just before actually returning. Stack based buffer
overflows (that need to overwrite this return address) now also
overwrite the canary, which gets detected and the attack is then
@@ -1354,15 +1365,8 @@
This feature requires gcc version 4.2 or above, or a distribution
gcc with the feature backported. Older versions are automatically
- detected and for those versions, this configuration option is ignored.
-
-config CC_STACKPROTECTOR_ALL
- bool "Use stack-protector for all functions"
- depends on CC_STACKPROTECTOR
- help
- Normally, GCC only inserts the canary value protection for
- functions that use large-ish on-stack buffers. By enabling
- this option, GCC will be asked to do this for ALL functions.
+ detected and for those versions, this configuration option is
+ ignored. (and a warning is printed during bootup)
source kernel/Kconfig.hz
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index c98d52e8..085fef4 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -294,25 +294,23 @@
# Define implied options from the CPU selection here
config X86_L1_CACHE_BYTES
int
- default "128" if GENERIC_CPU || MPSC
- default "64" if MK8 || MCORE2
- depends on X86_64
+ default "128" if MPSC
+ default "64" if GENERIC_CPU || MK8 || MCORE2 || X86_32
config X86_INTERNODE_CACHE_BYTES
int
default "4096" if X86_VSMP
default X86_L1_CACHE_BYTES if !X86_VSMP
- depends on X86_64
config X86_CMPXCHG
def_bool X86_64 || (X86_32 && !M386)
config X86_L1_CACHE_SHIFT
int
- default "7" if MPENTIUM4 || X86_GENERIC || GENERIC_CPU || MPSC
+ default "7" if MPENTIUM4 || MPSC
default "4" if X86_ELAN || M486 || M386 || MGEODEGX1
default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX
- default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MVIAC7
+ default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MVIAC7 || X86_GENERIC || GENERIC_CPU
config X86_XADD
def_bool y
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 10d6cc3..28f1114 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -117,6 +117,7 @@
config DEBUG_RODATA_TEST
bool "Testcase for the DEBUG_RODATA feature"
depends on DEBUG_RODATA
+ default y
help
This option enables a testcase for the DEBUG_RODATA
feature as well as for the change_page_attr() infrastructure.
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index d1a47ad..cacee98 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -73,7 +73,7 @@
stackp := $(CONFIG_SHELL) $(srctree)/scripts/gcc-x86_64-has-stack-protector.sh
stackp-$(CONFIG_CC_STACKPROTECTOR) := $(shell $(stackp) \
- "$(CC)" -fstack-protector )
+ "$(CC)" "-fstack-protector -DGCC_HAS_SP" )
stackp-$(CONFIG_CC_STACKPROTECTOR_ALL) += $(shell $(stackp) \
"$(CC)" -fstack-protector-all )
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index 9dabd00..dd77ac0 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -46,78 +46,83 @@
int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
{
- int err;
+ int err = 0;
if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t)))
return -EFAULT;
- /* If you change siginfo_t structure, please make sure that
- this code is fixed accordingly.
- It should never copy any pad contained in the structure
- to avoid security leaks, but must copy the generic
- 3 ints plus the relevant union member. */
- err = __put_user(from->si_signo, &to->si_signo);
- err |= __put_user(from->si_errno, &to->si_errno);
- err |= __put_user((short)from->si_code, &to->si_code);
+ put_user_try {
+ /* If you change siginfo_t structure, please make sure that
+ this code is fixed accordingly.
+ It should never copy any pad contained in the structure
+ to avoid security leaks, but must copy the generic
+ 3 ints plus the relevant union member. */
+ put_user_ex(from->si_signo, &to->si_signo);
+ put_user_ex(from->si_errno, &to->si_errno);
+ put_user_ex((short)from->si_code, &to->si_code);
- if (from->si_code < 0) {
- err |= __put_user(from->si_pid, &to->si_pid);
- err |= __put_user(from->si_uid, &to->si_uid);
- err |= __put_user(ptr_to_compat(from->si_ptr), &to->si_ptr);
- } else {
- /*
- * First 32bits of unions are always present:
- * si_pid === si_band === si_tid === si_addr(LS half)
- */
- err |= __put_user(from->_sifields._pad[0],
- &to->_sifields._pad[0]);
- switch (from->si_code >> 16) {
- case __SI_FAULT >> 16:
- break;
- case __SI_CHLD >> 16:
- err |= __put_user(from->si_utime, &to->si_utime);
- err |= __put_user(from->si_stime, &to->si_stime);
- err |= __put_user(from->si_status, &to->si_status);
- /* FALL THROUGH */
- default:
- case __SI_KILL >> 16:
- err |= __put_user(from->si_uid, &to->si_uid);
- break;
- case __SI_POLL >> 16:
- err |= __put_user(from->si_fd, &to->si_fd);
- break;
- case __SI_TIMER >> 16:
- err |= __put_user(from->si_overrun, &to->si_overrun);
- err |= __put_user(ptr_to_compat(from->si_ptr),
- &to->si_ptr);
- break;
- /* This is not generated by the kernel as of now. */
- case __SI_RT >> 16:
- case __SI_MESGQ >> 16:
- err |= __put_user(from->si_uid, &to->si_uid);
- err |= __put_user(from->si_int, &to->si_int);
- break;
+ if (from->si_code < 0) {
+ put_user_ex(from->si_pid, &to->si_pid);
+ put_user_ex(from->si_uid, &to->si_uid);
+ put_user_ex(ptr_to_compat(from->si_ptr), &to->si_ptr);
+ } else {
+ /*
+ * First 32bits of unions are always present:
+ * si_pid === si_band === si_tid === si_addr(LS half)
+ */
+ put_user_ex(from->_sifields._pad[0],
+ &to->_sifields._pad[0]);
+ switch (from->si_code >> 16) {
+ case __SI_FAULT >> 16:
+ break;
+ case __SI_CHLD >> 16:
+ put_user_ex(from->si_utime, &to->si_utime);
+ put_user_ex(from->si_stime, &to->si_stime);
+ put_user_ex(from->si_status, &to->si_status);
+ /* FALL THROUGH */
+ default:
+ case __SI_KILL >> 16:
+ put_user_ex(from->si_uid, &to->si_uid);
+ break;
+ case __SI_POLL >> 16:
+ put_user_ex(from->si_fd, &to->si_fd);
+ break;
+ case __SI_TIMER >> 16:
+ put_user_ex(from->si_overrun, &to->si_overrun);
+ put_user_ex(ptr_to_compat(from->si_ptr),
+ &to->si_ptr);
+ break;
+ /* This is not generated by the kernel as of now. */
+ case __SI_RT >> 16:
+ case __SI_MESGQ >> 16:
+ put_user_ex(from->si_uid, &to->si_uid);
+ put_user_ex(from->si_int, &to->si_int);
+ break;
+ }
}
- }
+ } put_user_catch(err);
+
return err;
}
int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
{
- int err;
+ int err = 0;
u32 ptr32;
if (!access_ok(VERIFY_READ, from, sizeof(compat_siginfo_t)))
return -EFAULT;
- err = __get_user(to->si_signo, &from->si_signo);
- err |= __get_user(to->si_errno, &from->si_errno);
- err |= __get_user(to->si_code, &from->si_code);
+ get_user_try {
+ get_user_ex(to->si_signo, &from->si_signo);
+ get_user_ex(to->si_errno, &from->si_errno);
+ get_user_ex(to->si_code, &from->si_code);
- err |= __get_user(to->si_pid, &from->si_pid);
- err |= __get_user(to->si_uid, &from->si_uid);
- err |= __get_user(ptr32, &from->si_ptr);
- to->si_ptr = compat_ptr(ptr32);
+ get_user_ex(to->si_pid, &from->si_pid);
+ get_user_ex(to->si_uid, &from->si_uid);
+ get_user_ex(ptr32, &from->si_ptr);
+ to->si_ptr = compat_ptr(ptr32);
+ } get_user_catch(err);
return err;
}
@@ -142,17 +147,23 @@
struct pt_regs *regs)
{
stack_t uss, uoss;
- int ret;
+ int ret, err = 0;
mm_segment_t seg;
if (uss_ptr) {
u32 ptr;
memset(&uss, 0, sizeof(stack_t));
- if (!access_ok(VERIFY_READ, uss_ptr, sizeof(stack_ia32_t)) ||
- __get_user(ptr, &uss_ptr->ss_sp) ||
- __get_user(uss.ss_flags, &uss_ptr->ss_flags) ||
- __get_user(uss.ss_size, &uss_ptr->ss_size))
+ if (!access_ok(VERIFY_READ, uss_ptr, sizeof(stack_ia32_t)))
+ return -EFAULT;
+
+ get_user_try {
+ get_user_ex(ptr, &uss_ptr->ss_sp);
+ get_user_ex(uss.ss_flags, &uss_ptr->ss_flags);
+ get_user_ex(uss.ss_size, &uss_ptr->ss_size);
+ } get_user_catch(err);
+
+ if (err)
return -EFAULT;
uss.ss_sp = compat_ptr(ptr);
}
@@ -161,10 +172,16 @@
ret = do_sigaltstack(uss_ptr ? &uss : NULL, &uoss, regs->sp);
set_fs(seg);
if (ret >= 0 && uoss_ptr) {
- if (!access_ok(VERIFY_WRITE, uoss_ptr, sizeof(stack_ia32_t)) ||
- __put_user(ptr_to_compat(uoss.ss_sp), &uoss_ptr->ss_sp) ||
- __put_user(uoss.ss_flags, &uoss_ptr->ss_flags) ||
- __put_user(uoss.ss_size, &uoss_ptr->ss_size))
+ if (!access_ok(VERIFY_WRITE, uoss_ptr, sizeof(stack_ia32_t)))
+ return -EFAULT;
+
+ put_user_try {
+ put_user_ex(ptr_to_compat(uoss.ss_sp), &uoss_ptr->ss_sp);
+ put_user_ex(uoss.ss_flags, &uoss_ptr->ss_flags);
+ put_user_ex(uoss.ss_size, &uoss_ptr->ss_size);
+ } put_user_catch(err);
+
+ if (err)
ret = -EFAULT;
}
return ret;
@@ -174,18 +191,18 @@
* Do a signal return; undo the signal stack.
*/
#define COPY(x) { \
- err |= __get_user(regs->x, &sc->x); \
+ get_user_ex(regs->x, &sc->x); \
}
#define COPY_SEG_CPL3(seg) { \
unsigned short tmp; \
- err |= __get_user(tmp, &sc->seg); \
+ get_user_ex(tmp, &sc->seg); \
regs->seg = tmp | 3; \
}
#define RELOAD_SEG(seg) { \
unsigned int cur, pre; \
- err |= __get_user(pre, &sc->seg); \
+ get_user_ex(pre, &sc->seg); \
savesegment(seg, cur); \
pre |= 3; \
if (pre != cur) \
@@ -209,39 +226,42 @@
sc, sc->err, sc->ip, sc->cs, sc->flags);
#endif
- /*
- * Reload fs and gs if they have changed in the signal
- * handler. This does not handle long fs/gs base changes in
- * the handler, but does not clobber them at least in the
- * normal case.
- */
- err |= __get_user(gs, &sc->gs);
- gs |= 3;
- savesegment(gs, oldgs);
- if (gs != oldgs)
- load_gs_index(gs);
+ get_user_try {
+ /*
+ * Reload fs and gs if they have changed in the signal
+ * handler. This does not handle long fs/gs base changes in
+ * the handler, but does not clobber them at least in the
+ * normal case.
+ */
+ get_user_ex(gs, &sc->gs);
+ gs |= 3;
+ savesegment(gs, oldgs);
+ if (gs != oldgs)
+ load_gs_index(gs);
- RELOAD_SEG(fs);
- RELOAD_SEG(ds);
- RELOAD_SEG(es);
+ RELOAD_SEG(fs);
+ RELOAD_SEG(ds);
+ RELOAD_SEG(es);
- COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx);
- COPY(dx); COPY(cx); COPY(ip);
- /* Don't touch extended registers */
+ COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx);
+ COPY(dx); COPY(cx); COPY(ip);
+ /* Don't touch extended registers */
- COPY_SEG_CPL3(cs);
- COPY_SEG_CPL3(ss);
+ COPY_SEG_CPL3(cs);
+ COPY_SEG_CPL3(ss);
- err |= __get_user(tmpflags, &sc->flags);
- regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
- /* disable syscall checks */
- regs->orig_ax = -1;
+ get_user_ex(tmpflags, &sc->flags);
+ regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
+ /* disable syscall checks */
+ regs->orig_ax = -1;
- err |= __get_user(tmp, &sc->fpstate);
- buf = compat_ptr(tmp);
- err |= restore_i387_xstate_ia32(buf);
+ get_user_ex(tmp, &sc->fpstate);
+ buf = compat_ptr(tmp);
+ err |= restore_i387_xstate_ia32(buf);
- err |= __get_user(*pax, &sc->ax);
+ get_user_ex(*pax, &sc->ax);
+ } get_user_catch(err);
+
return err;
}
@@ -319,36 +339,38 @@
{
int tmp, err = 0;
- savesegment(gs, tmp);
- err |= __put_user(tmp, (unsigned int __user *)&sc->gs);
- savesegment(fs, tmp);
- err |= __put_user(tmp, (unsigned int __user *)&sc->fs);
- savesegment(ds, tmp);
- err |= __put_user(tmp, (unsigned int __user *)&sc->ds);
- savesegment(es, tmp);
- err |= __put_user(tmp, (unsigned int __user *)&sc->es);
+ put_user_try {
+ savesegment(gs, tmp);
+ put_user_ex(tmp, (unsigned int __user *)&sc->gs);
+ savesegment(fs, tmp);
+ put_user_ex(tmp, (unsigned int __user *)&sc->fs);
+ savesegment(ds, tmp);
+ put_user_ex(tmp, (unsigned int __user *)&sc->ds);
+ savesegment(es, tmp);
+ put_user_ex(tmp, (unsigned int __user *)&sc->es);
- err |= __put_user(regs->di, &sc->di);
- err |= __put_user(regs->si, &sc->si);
- err |= __put_user(regs->bp, &sc->bp);
- err |= __put_user(regs->sp, &sc->sp);
- err |= __put_user(regs->bx, &sc->bx);
- err |= __put_user(regs->dx, &sc->dx);
- err |= __put_user(regs->cx, &sc->cx);
- err |= __put_user(regs->ax, &sc->ax);
- err |= __put_user(current->thread.trap_no, &sc->trapno);
- err |= __put_user(current->thread.error_code, &sc->err);
- err |= __put_user(regs->ip, &sc->ip);
- err |= __put_user(regs->cs, (unsigned int __user *)&sc->cs);
- err |= __put_user(regs->flags, &sc->flags);
- err |= __put_user(regs->sp, &sc->sp_at_signal);
- err |= __put_user(regs->ss, (unsigned int __user *)&sc->ss);
+ put_user_ex(regs->di, &sc->di);
+ put_user_ex(regs->si, &sc->si);
+ put_user_ex(regs->bp, &sc->bp);
+ put_user_ex(regs->sp, &sc->sp);
+ put_user_ex(regs->bx, &sc->bx);
+ put_user_ex(regs->dx, &sc->dx);
+ put_user_ex(regs->cx, &sc->cx);
+ put_user_ex(regs->ax, &sc->ax);
+ put_user_ex(current->thread.trap_no, &sc->trapno);
+ put_user_ex(current->thread.error_code, &sc->err);
+ put_user_ex(regs->ip, &sc->ip);
+ put_user_ex(regs->cs, (unsigned int __user *)&sc->cs);
+ put_user_ex(regs->flags, &sc->flags);
+ put_user_ex(regs->sp, &sc->sp_at_signal);
+ put_user_ex(regs->ss, (unsigned int __user *)&sc->ss);
- err |= __put_user(ptr_to_compat(fpstate), &sc->fpstate);
+ put_user_ex(ptr_to_compat(fpstate), &sc->fpstate);
- /* non-iBCS2 extensions.. */
- err |= __put_user(mask, &sc->oldmask);
- err |= __put_user(current->thread.cr2, &sc->cr2);
+ /* non-iBCS2 extensions.. */
+ put_user_ex(mask, &sc->oldmask);
+ put_user_ex(current->thread.cr2, &sc->cr2);
+ } put_user_catch(err);
return err;
}
@@ -437,13 +459,17 @@
else
restorer = &frame->retcode;
}
- err |= __put_user(ptr_to_compat(restorer), &frame->pretcode);
- /*
- * These are actually not used anymore, but left because some
- * gdb versions depend on them as a marker.
- */
- err |= __put_user(*((u64 *)&code), (u64 *)frame->retcode);
+ put_user_try {
+ put_user_ex(ptr_to_compat(restorer), &frame->pretcode);
+
+ /*
+ * These are actually not used anymore, but left because some
+ * gdb versions depend on them as a marker.
+ */
+ put_user_ex(*((u64 *)&code), (u64 *)frame->retcode);
+ } put_user_catch(err);
+
if (err)
return -EFAULT;
@@ -496,41 +522,40 @@
if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
return -EFAULT;
- err |= __put_user(sig, &frame->sig);
- err |= __put_user(ptr_to_compat(&frame->info), &frame->pinfo);
- err |= __put_user(ptr_to_compat(&frame->uc), &frame->puc);
- err |= copy_siginfo_to_user32(&frame->info, info);
- if (err)
- return -EFAULT;
+ put_user_try {
+ put_user_ex(sig, &frame->sig);
+ put_user_ex(ptr_to_compat(&frame->info), &frame->pinfo);
+ put_user_ex(ptr_to_compat(&frame->uc), &frame->puc);
+ err |= copy_siginfo_to_user32(&frame->info, info);
- /* Create the ucontext. */
- if (cpu_has_xsave)
- err |= __put_user(UC_FP_XSTATE, &frame->uc.uc_flags);
- else
- err |= __put_user(0, &frame->uc.uc_flags);
- err |= __put_user(0, &frame->uc.uc_link);
- err |= __put_user(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
- err |= __put_user(sas_ss_flags(regs->sp),
- &frame->uc.uc_stack.ss_flags);
- err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
- err |= ia32_setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
- regs, set->sig[0]);
- err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
- if (err)
- return -EFAULT;
+ /* Create the ucontext. */
+ if (cpu_has_xsave)
+ put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
+ else
+ put_user_ex(0, &frame->uc.uc_flags);
+ put_user_ex(0, &frame->uc.uc_link);
+ put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
+ put_user_ex(sas_ss_flags(regs->sp),
+ &frame->uc.uc_stack.ss_flags);
+ put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
+ err |= ia32_setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
+ regs, set->sig[0]);
+ err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
- if (ka->sa.sa_flags & SA_RESTORER)
- restorer = ka->sa.sa_restorer;
- else
- restorer = VDSO32_SYMBOL(current->mm->context.vdso,
- rt_sigreturn);
- err |= __put_user(ptr_to_compat(restorer), &frame->pretcode);
+ if (ka->sa.sa_flags & SA_RESTORER)
+ restorer = ka->sa.sa_restorer;
+ else
+ restorer = VDSO32_SYMBOL(current->mm->context.vdso,
+ rt_sigreturn);
+ put_user_ex(ptr_to_compat(restorer), &frame->pretcode);
- /*
- * Not actually used anymore, but left because some gdb
- * versions need it.
- */
- err |= __put_user(*((u64 *)&code), (u64 *)frame->retcode);
+ /*
+ * Not actually used anymore, but left because some gdb
+ * versions need it.
+ */
+ put_user_ex(*((u64 *)&code), (u64 *)frame->retcode);
+ } put_user_catch(err);
+
if (err)
return -EFAULT;
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 256b00b..097a6b6 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -112,8 +112,8 @@
CFI_DEF_CFA rsp,0
CFI_REGISTER rsp,rbp
SWAPGS_UNSAFE_STACK
- movq %gs:pda_kernelstack, %rsp
- addq $(PDA_STACKOFFSET),%rsp
+ movq PER_CPU_VAR(kernel_stack), %rsp
+ addq $(KERNEL_STACK_OFFSET),%rsp
/*
* No need to follow this irqs on/off section: the syscall
* disabled irqs, here we enable it straight after entry:
@@ -273,13 +273,13 @@
ENTRY(ia32_cstar_target)
CFI_STARTPROC32 simple
CFI_SIGNAL_FRAME
- CFI_DEF_CFA rsp,PDA_STACKOFFSET
+ CFI_DEF_CFA rsp,KERNEL_STACK_OFFSET
CFI_REGISTER rip,rcx
/*CFI_REGISTER rflags,r11*/
SWAPGS_UNSAFE_STACK
movl %esp,%r8d
CFI_REGISTER rsp,r8
- movq %gs:pda_kernelstack,%rsp
+ movq PER_CPU_VAR(kernel_stack),%rsp
/*
* No need to follow this irqs on/off section: the syscall
* disabled irqs and here we enable it straight after entry:
@@ -418,9 +418,9 @@
orl $TS_COMPAT,TI_status(%r10)
testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%r10)
jnz ia32_tracesys
-ia32_do_syscall:
cmpl $(IA32_NR_syscalls-1),%eax
- ja int_ret_from_sys_call /* ia32_tracesys has set RAX(%rsp) */
+ ja ia32_badsys
+ia32_do_call:
IA32_ARG_FIXUP
call *ia32_sys_call_table(,%rax,8) # xxx: rip relative
ia32_sysret:
@@ -435,7 +435,9 @@
call syscall_trace_enter
LOAD_ARGS32 ARGOFFSET /* reload args from stack in case ptrace changed it */
RESTORE_REST
- jmp ia32_do_syscall
+ cmpl $(IA32_NR_syscalls-1),%eax
+ ja int_ret_from_sys_call /* ia32_tracesys has set RAX(%rsp) */
+ jmp ia32_do_call
END(ia32_syscall)
ia32_badsys:
diff --git a/arch/x86/include/asm/apicnum.h b/arch/x86/include/asm/apicnum.h
new file mode 100644
index 0000000..82f613c
--- /dev/null
+++ b/arch/x86/include/asm/apicnum.h
@@ -0,0 +1,12 @@
+#ifndef _ASM_X86_APICNUM_H
+#define _ASM_X86_APICNUM_H
+
+/* define MAX_IO_APICS */
+#ifdef CONFIG_X86_32
+# define MAX_IO_APICS 64
+#else
+# define MAX_IO_APICS 128
+# define MAX_LOCAL_APIC 32768
+#endif
+
+#endif /* _ASM_X86_APICNUM_H */
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index bae482d..f03b23e 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -7,6 +7,20 @@
#include <linux/nodemask.h>
#include <linux/percpu.h>
+#ifdef CONFIG_SMP
+
+extern void prefill_possible_map(void);
+
+#else /* CONFIG_SMP */
+
+static inline void prefill_possible_map(void) {}
+
+#define cpu_physical_id(cpu) boot_cpu_physical_apicid
+#define safe_smp_processor_id() 0
+#define stack_smp_processor_id() 0
+
+#endif /* CONFIG_SMP */
+
struct x86_cpu {
struct cpu cpu;
};
@@ -17,4 +31,11 @@
#endif
DECLARE_PER_CPU(int, cpu_state);
+
+#ifdef CONFIG_X86_HAS_BOOT_CPU_ID
+extern unsigned char boot_cpu_id;
+#else
+#define boot_cpu_id 0
+#endif
+
#endif /* _ASM_X86_CPU_H */
diff --git a/arch/x86/include/asm/cpumask.h b/arch/x86/include/asm/cpumask.h
new file mode 100644
index 0000000..a7f3c75
--- /dev/null
+++ b/arch/x86/include/asm/cpumask.h
@@ -0,0 +1,32 @@
+#ifndef _ASM_X86_CPUMASK_H
+#define _ASM_X86_CPUMASK_H
+#ifndef __ASSEMBLY__
+#include <linux/cpumask.h>
+
+#ifdef CONFIG_X86_64
+
+extern cpumask_var_t cpu_callin_mask;
+extern cpumask_var_t cpu_callout_mask;
+extern cpumask_var_t cpu_initialized_mask;
+extern cpumask_var_t cpu_sibling_setup_mask;
+
+extern void setup_cpu_local_masks(void);
+
+#else /* CONFIG_X86_32 */
+
+extern cpumask_t cpu_callin_map;
+extern cpumask_t cpu_callout_map;
+extern cpumask_t cpu_initialized;
+extern cpumask_t cpu_sibling_setup_map;
+
+#define cpu_callin_mask ((struct cpumask *)&cpu_callin_map)
+#define cpu_callout_mask ((struct cpumask *)&cpu_callout_map)
+#define cpu_initialized_mask ((struct cpumask *)&cpu_initialized)
+#define cpu_sibling_setup_mask ((struct cpumask *)&cpu_sibling_setup_map)
+
+static inline void setup_cpu_local_masks(void) { }
+
+#endif /* CONFIG_X86_32 */
+
+#endif /* __ASSEMBLY__ */
+#endif /* _ASM_X86_CPUMASK_H */
diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h
index 0930b4f..c68c361 100644
--- a/arch/x86/include/asm/current.h
+++ b/arch/x86/include/asm/current.h
@@ -1,39 +1,21 @@
#ifndef _ASM_X86_CURRENT_H
#define _ASM_X86_CURRENT_H
-#ifdef CONFIG_X86_32
#include <linux/compiler.h>
#include <asm/percpu.h>
+#ifndef __ASSEMBLY__
struct task_struct;
DECLARE_PER_CPU(struct task_struct *, current_task);
-static __always_inline struct task_struct *get_current(void)
-{
- return x86_read_percpu(current_task);
-}
-
-#else /* X86_32 */
-
-#ifndef __ASSEMBLY__
-#include <asm/pda.h>
-
-struct task_struct;
static __always_inline struct task_struct *get_current(void)
{
- return read_pda(pcurrent);
+ return percpu_read(current_task);
}
-#else /* __ASSEMBLY__ */
-
-#include <asm/asm-offsets.h>
-#define GET_CURRENT(reg) movq %gs:(pda_pcurrent),reg
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* X86_32 */
-
#define current get_current()
+#endif /* __ASSEMBLY__ */
+
#endif /* _ASM_X86_CURRENT_H */
diff --git a/arch/x86/include/asm/genapic_32.h b/arch/x86/include/asm/genapic_32.h
index 2c05b73..4334502 100644
--- a/arch/x86/include/asm/genapic_32.h
+++ b/arch/x86/include/asm/genapic_32.h
@@ -138,11 +138,4 @@
extern struct genapic *genapic;
extern void es7000_update_genapic_to_cluster(void);
-enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC};
-#define get_uv_system_type() UV_NONE
-#define is_uv_system() 0
-#define uv_wakeup_secondary(a, b) 1
-#define uv_system_init() do {} while (0)
-
-
#endif /* _ASM_X86_GENAPIC_32_H */
diff --git a/arch/x86/include/asm/genapic_64.h b/arch/x86/include/asm/genapic_64.h
index adf32fb..7bb092c 100644
--- a/arch/x86/include/asm/genapic_64.h
+++ b/arch/x86/include/asm/genapic_64.h
@@ -51,15 +51,9 @@
extern int acpi_madt_oem_check(char *, char *);
extern void apic_send_IPI_self(int vector);
-enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC};
-extern enum uv_system_type get_uv_system_type(void);
-extern int is_uv_system(void);
extern struct genapic apic_x2apic_uv_x;
DECLARE_PER_CPU(int, x2apic_extra_bits);
-extern void uv_cpu_init(void);
-extern void uv_system_init(void);
-extern int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip);
extern void setup_apic_routing(void);
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 000787d..176f058 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -1,11 +1,52 @@
-#ifdef CONFIG_X86_32
-# include "hardirq_32.h"
-#else
-# include "hardirq_64.h"
+#ifndef _ASM_X86_HARDIRQ_H
+#define _ASM_X86_HARDIRQ_H
+
+#include <linux/threads.h>
+#include <linux/irq.h>
+
+typedef struct {
+ unsigned int __softirq_pending;
+ unsigned int __nmi_count; /* arch dependent */
+ unsigned int irq0_irqs;
+#ifdef CONFIG_X86_LOCAL_APIC
+ unsigned int apic_timer_irqs; /* arch dependent */
+ unsigned int irq_spurious_count;
#endif
+#ifdef CONFIG_SMP
+ unsigned int irq_resched_count;
+ unsigned int irq_call_count;
+ unsigned int irq_tlb_count;
+#endif
+#ifdef CONFIG_X86_MCE
+ unsigned int irq_thermal_count;
+# ifdef CONFIG_X86_64
+ unsigned int irq_threshold_count;
+# endif
+#endif
+} ____cacheline_aligned irq_cpustat_t;
+
+DECLARE_PER_CPU(irq_cpustat_t, irq_stat);
+
+/* We can have at most NR_VECTORS irqs routed to a cpu at a time */
+#define MAX_HARDIRQS_PER_CPU NR_VECTORS
+
+#define __ARCH_IRQ_STAT
+
+#define inc_irq_stat(member) percpu_add(irq_stat.member, 1)
+
+#define local_softirq_pending() percpu_read(irq_stat.__softirq_pending)
+
+#define __ARCH_SET_SOFTIRQ_PENDING
+
+#define set_softirq_pending(x) percpu_write(irq_stat.__softirq_pending, (x))
+#define or_softirq_pending(x) percpu_or(irq_stat.__softirq_pending, (x))
+
+extern void ack_bad_irq(unsigned int irq);
extern u64 arch_irq_stat_cpu(unsigned int cpu);
#define arch_irq_stat_cpu arch_irq_stat_cpu
extern u64 arch_irq_stat(void);
#define arch_irq_stat arch_irq_stat
+
+#endif /* _ASM_X86_HARDIRQ_H */
diff --git a/arch/x86/include/asm/hardirq_32.h b/arch/x86/include/asm/hardirq_32.h
deleted file mode 100644
index cf7954d..0000000
--- a/arch/x86/include/asm/hardirq_32.h
+++ /dev/null
@@ -1,30 +0,0 @@
-#ifndef _ASM_X86_HARDIRQ_32_H
-#define _ASM_X86_HARDIRQ_32_H
-
-#include <linux/threads.h>
-#include <linux/irq.h>
-
-typedef struct {
- unsigned int __softirq_pending;
- unsigned long idle_timestamp;
- unsigned int __nmi_count; /* arch dependent */
- unsigned int apic_timer_irqs; /* arch dependent */
- unsigned int irq0_irqs;
- unsigned int irq_resched_count;
- unsigned int irq_call_count;
- unsigned int irq_tlb_count;
- unsigned int irq_thermal_count;
- unsigned int irq_spurious_count;
-} ____cacheline_aligned irq_cpustat_t;
-
-DECLARE_PER_CPU(irq_cpustat_t, irq_stat);
-
-#define __ARCH_IRQ_STAT
-#define __IRQ_STAT(cpu, member) (per_cpu(irq_stat, cpu).member)
-
-#define inc_irq_stat(member) (__get_cpu_var(irq_stat).member++)
-
-void ack_bad_irq(unsigned int irq);
-#include <linux/irq_cpustat.h>
-
-#endif /* _ASM_X86_HARDIRQ_32_H */
diff --git a/arch/x86/include/asm/hardirq_64.h b/arch/x86/include/asm/hardirq_64.h
deleted file mode 100644
index b5a6b5d..0000000
--- a/arch/x86/include/asm/hardirq_64.h
+++ /dev/null
@@ -1,25 +0,0 @@
-#ifndef _ASM_X86_HARDIRQ_64_H
-#define _ASM_X86_HARDIRQ_64_H
-
-#include <linux/threads.h>
-#include <linux/irq.h>
-#include <asm/pda.h>
-#include <asm/apic.h>
-
-/* We can have at most NR_VECTORS irqs routed to a cpu at a time */
-#define MAX_HARDIRQS_PER_CPU NR_VECTORS
-
-#define __ARCH_IRQ_STAT 1
-
-#define inc_irq_stat(member) add_pda(member, 1)
-
-#define local_softirq_pending() read_pda(__softirq_pending)
-
-#define __ARCH_SET_SOFTIRQ_PENDING 1
-
-#define set_softirq_pending(x) write_pda(__softirq_pending, (x))
-#define or_softirq_pending(x) or_pda(__softirq_pending, (x))
-
-extern void ack_bad_irq(unsigned int irq);
-
-#endif /* _ASM_X86_HARDIRQ_64_H */
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 7a1f44a..08ec793 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -114,38 +114,16 @@
extern int nr_ioapics;
extern int nr_ioapic_registers[MAX_IO_APICS];
-/*
- * MP-BIOS irq configuration table structures:
- */
-
#define MP_MAX_IOAPIC_PIN 127
-struct mp_config_ioapic {
- unsigned long mp_apicaddr;
- unsigned int mp_apicid;
- unsigned char mp_type;
- unsigned char mp_apicver;
- unsigned char mp_flags;
-};
-
-struct mp_config_intsrc {
- unsigned int mp_dstapic;
- unsigned char mp_type;
- unsigned char mp_irqtype;
- unsigned short mp_irqflag;
- unsigned char mp_srcbus;
- unsigned char mp_srcbusirq;
- unsigned char mp_dstirq;
-};
-
/* I/O APIC entries */
-extern struct mp_config_ioapic mp_ioapics[MAX_IO_APICS];
+extern struct mpc_ioapic mp_ioapics[MAX_IO_APICS];
/* # of MP IRQ source entries */
extern int mp_irq_entries;
/* MP IRQ source entries */
-extern struct mp_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
+extern struct mpc_intsrc mp_irqs[MAX_IRQ_SOURCES];
/* non-0 if default (table-less) MP configuration */
extern int mpc_default_type;
diff --git a/arch/x86/include/asm/irq_regs.h b/arch/x86/include/asm/irq_regs.h
index 89c898a..7784322 100644
--- a/arch/x86/include/asm/irq_regs.h
+++ b/arch/x86/include/asm/irq_regs.h
@@ -1,5 +1,31 @@
-#ifdef CONFIG_X86_32
-# include "irq_regs_32.h"
-#else
-# include "irq_regs_64.h"
-#endif
+/*
+ * Per-cpu current frame pointer - the location of the last exception frame on
+ * the stack, stored in the per-cpu area.
+ *
+ * Jeremy Fitzhardinge <jeremy@goop.org>
+ */
+#ifndef _ASM_X86_IRQ_REGS_H
+#define _ASM_X86_IRQ_REGS_H
+
+#include <asm/percpu.h>
+
+#define ARCH_HAS_OWN_IRQ_REGS
+
+DECLARE_PER_CPU(struct pt_regs *, irq_regs);
+
+static inline struct pt_regs *get_irq_regs(void)
+{
+ return percpu_read(irq_regs);
+}
+
+static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs)
+{
+ struct pt_regs *old_regs;
+
+ old_regs = get_irq_regs();
+ percpu_write(irq_regs, new_regs);
+
+ return old_regs;
+}
+
+#endif /* _ASM_X86_IRQ_REGS_32_H */
diff --git a/arch/x86/include/asm/irq_regs_32.h b/arch/x86/include/asm/irq_regs_32.h
deleted file mode 100644
index 86afd74..0000000
--- a/arch/x86/include/asm/irq_regs_32.h
+++ /dev/null
@@ -1,31 +0,0 @@
-/*
- * Per-cpu current frame pointer - the location of the last exception frame on
- * the stack, stored in the per-cpu area.
- *
- * Jeremy Fitzhardinge <jeremy@goop.org>
- */
-#ifndef _ASM_X86_IRQ_REGS_32_H
-#define _ASM_X86_IRQ_REGS_32_H
-
-#include <asm/percpu.h>
-
-#define ARCH_HAS_OWN_IRQ_REGS
-
-DECLARE_PER_CPU(struct pt_regs *, irq_regs);
-
-static inline struct pt_regs *get_irq_regs(void)
-{
- return x86_read_percpu(irq_regs);
-}
-
-static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs)
-{
- struct pt_regs *old_regs;
-
- old_regs = get_irq_regs();
- x86_write_percpu(irq_regs, new_regs);
-
- return old_regs;
-}
-
-#endif /* _ASM_X86_IRQ_REGS_32_H */
diff --git a/arch/x86/include/asm/irq_regs_64.h b/arch/x86/include/asm/irq_regs_64.h
deleted file mode 100644
index 3dd9c0b..0000000
--- a/arch/x86/include/asm/irq_regs_64.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/irq_regs.h>
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index f7ff650..9a83a10 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -49,31 +49,33 @@
* some of the following vectors are 'rare', they are merged
* into a single vector (CALL_FUNCTION_VECTOR) to save vector space.
* TLB, reschedule and local APIC vectors are performance-critical.
- *
- * Vectors 0xf0-0xfa are free (reserved for future Linux use).
*/
#ifdef CONFIG_X86_32
# define SPURIOUS_APIC_VECTOR 0xff
# define ERROR_APIC_VECTOR 0xfe
-# define INVALIDATE_TLB_VECTOR 0xfd
-# define RESCHEDULE_VECTOR 0xfc
-# define CALL_FUNCTION_VECTOR 0xfb
-# define CALL_FUNCTION_SINGLE_VECTOR 0xfa
-# define THERMAL_APIC_VECTOR 0xf0
+# define RESCHEDULE_VECTOR 0xfd
+# define CALL_FUNCTION_VECTOR 0xfc
+# define CALL_FUNCTION_SINGLE_VECTOR 0xfb
+# define THERMAL_APIC_VECTOR 0xfa
+/* 0xf8 - 0xf9 : free */
+# define INVALIDATE_TLB_VECTOR_END 0xf7
+# define INVALIDATE_TLB_VECTOR_START 0xf0 /* f0-f7 used for TLB flush */
+
+# define NUM_INVALIDATE_TLB_VECTORS 8
#else
-#define SPURIOUS_APIC_VECTOR 0xff
-#define ERROR_APIC_VECTOR 0xfe
-#define RESCHEDULE_VECTOR 0xfd
-#define CALL_FUNCTION_VECTOR 0xfc
-#define CALL_FUNCTION_SINGLE_VECTOR 0xfb
-#define THERMAL_APIC_VECTOR 0xfa
-#define THRESHOLD_APIC_VECTOR 0xf9
-#define UV_BAU_MESSAGE 0xf8
-#define INVALIDATE_TLB_VECTOR_END 0xf7
-#define INVALIDATE_TLB_VECTOR_START 0xf0 /* f0-f7 used for TLB flush */
+# define SPURIOUS_APIC_VECTOR 0xff
+# define ERROR_APIC_VECTOR 0xfe
+# define RESCHEDULE_VECTOR 0xfd
+# define CALL_FUNCTION_VECTOR 0xfc
+# define CALL_FUNCTION_SINGLE_VECTOR 0xfb
+# define THERMAL_APIC_VECTOR 0xfa
+# define THRESHOLD_APIC_VECTOR 0xf9
+# define UV_BAU_MESSAGE 0xf8
+# define INVALIDATE_TLB_VECTOR_END 0xf7
+# define INVALIDATE_TLB_VECTOR_START 0xf0 /* f0-f7 used for TLB flush */
#define NUM_INVALIDATE_TLB_VECTORS 8
@@ -105,6 +107,8 @@
#if defined(CONFIG_X86_IO_APIC) && !defined(CONFIG_X86_VOYAGER)
+#include <asm/apicnum.h> /* need MAX_IO_APICS */
+
#ifndef CONFIG_SPARSE_IRQ
# if NR_CPUS < MAX_IO_APICS
# define NR_IRQS (NR_VECTORS + (32 * NR_CPUS))
@@ -112,11 +116,12 @@
# define NR_IRQS (NR_VECTORS + (32 * MAX_IO_APICS))
# endif
#else
-# if (8 * NR_CPUS) > (32 * MAX_IO_APICS)
-# define NR_IRQS (NR_VECTORS + (8 * NR_CPUS))
-# else
-# define NR_IRQS (NR_VECTORS + (32 * MAX_IO_APICS))
-# endif
+
+# define NR_IRQS \
+ ((8 * NR_CPUS) > (32 * MAX_IO_APICS) ? \
+ (NR_VECTORS + (8 * NR_CPUS)) : \
+ (NR_VECTORS + (32 * MAX_IO_APICS))) \
+
#endif
#elif defined(CONFIG_X86_VOYAGER)
diff --git a/arch/x86/include/asm/mach-default/entry_arch.h b/arch/x86/include/asm/mach-default/entry_arch.h
index 6b1add8..6fa399a 100644
--- a/arch/x86/include/asm/mach-default/entry_arch.h
+++ b/arch/x86/include/asm/mach-default/entry_arch.h
@@ -11,10 +11,26 @@
*/
#ifdef CONFIG_X86_SMP
BUILD_INTERRUPT(reschedule_interrupt,RESCHEDULE_VECTOR)
-BUILD_INTERRUPT(invalidate_interrupt,INVALIDATE_TLB_VECTOR)
BUILD_INTERRUPT(call_function_interrupt,CALL_FUNCTION_VECTOR)
BUILD_INTERRUPT(call_function_single_interrupt,CALL_FUNCTION_SINGLE_VECTOR)
BUILD_INTERRUPT(irq_move_cleanup_interrupt,IRQ_MOVE_CLEANUP_VECTOR)
+
+BUILD_INTERRUPT3(invalidate_interrupt0,INVALIDATE_TLB_VECTOR_START+0,
+ smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt1,INVALIDATE_TLB_VECTOR_START+1,
+ smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt2,INVALIDATE_TLB_VECTOR_START+2,
+ smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt3,INVALIDATE_TLB_VECTOR_START+3,
+ smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt4,INVALIDATE_TLB_VECTOR_START+4,
+ smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt5,INVALIDATE_TLB_VECTOR_START+5,
+ smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt6,INVALIDATE_TLB_VECTOR_START+6,
+ smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt7,INVALIDATE_TLB_VECTOR_START+7,
+ smp_invalidate_interrupt)
#endif
/*
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 8aeeb3f..52948df 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -21,11 +21,54 @@
int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
void destroy_context(struct mm_struct *mm);
-#ifdef CONFIG_X86_32
-# include "mmu_context_32.h"
-#else
-# include "mmu_context_64.h"
+
+static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
+{
+#ifdef CONFIG_SMP
+ if (percpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
+ percpu_write(cpu_tlbstate.state, TLBSTATE_LAZY);
#endif
+}
+
+static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
+ struct task_struct *tsk)
+{
+ unsigned cpu = smp_processor_id();
+
+ if (likely(prev != next)) {
+ /* stop flush ipis for the previous mm */
+ cpu_clear(cpu, prev->cpu_vm_mask);
+#ifdef CONFIG_SMP
+ percpu_write(cpu_tlbstate.state, TLBSTATE_OK);
+ percpu_write(cpu_tlbstate.active_mm, next);
+#endif
+ cpu_set(cpu, next->cpu_vm_mask);
+
+ /* Re-load page tables */
+ load_cr3(next->pgd);
+
+ /*
+ * load the LDT, if the LDT is different:
+ */
+ if (unlikely(prev->context.ldt != next->context.ldt))
+ load_LDT_nolock(&next->context);
+ }
+#ifdef CONFIG_SMP
+ else {
+ percpu_write(cpu_tlbstate.state, TLBSTATE_OK);
+ BUG_ON(percpu_read(cpu_tlbstate.active_mm) != next);
+
+ if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) {
+ /* We were in lazy tlb mode and leave_mm disabled
+ * tlb flush IPI delivery. We must reload CR3
+ * to make sure to use no freed page tables.
+ */
+ load_cr3(next->pgd);
+ load_LDT_nolock(&next->context);
+ }
+ }
+#endif
+}
#define activate_mm(prev, next) \
do { \
@@ -33,5 +76,17 @@
switch_mm((prev), (next), NULL); \
} while (0);
+#ifdef CONFIG_X86_32
+#define deactivate_mm(tsk, mm) \
+do { \
+ loadsegment(gs, 0); \
+} while (0)
+#else
+#define deactivate_mm(tsk, mm) \
+do { \
+ load_gs_index(0); \
+ loadsegment(fs, 0); \
+} while (0)
+#endif
#endif /* _ASM_X86_MMU_CONTEXT_H */
diff --git a/arch/x86/include/asm/mmu_context_32.h b/arch/x86/include/asm/mmu_context_32.h
deleted file mode 100644
index 7e98ce1..0000000
--- a/arch/x86/include/asm/mmu_context_32.h
+++ /dev/null
@@ -1,55 +0,0 @@
-#ifndef _ASM_X86_MMU_CONTEXT_32_H
-#define _ASM_X86_MMU_CONTEXT_32_H
-
-static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
-{
-#ifdef CONFIG_SMP
- if (x86_read_percpu(cpu_tlbstate.state) == TLBSTATE_OK)
- x86_write_percpu(cpu_tlbstate.state, TLBSTATE_LAZY);
-#endif
-}
-
-static inline void switch_mm(struct mm_struct *prev,
- struct mm_struct *next,
- struct task_struct *tsk)
-{
- int cpu = smp_processor_id();
-
- if (likely(prev != next)) {
- /* stop flush ipis for the previous mm */
- cpu_clear(cpu, prev->cpu_vm_mask);
-#ifdef CONFIG_SMP
- x86_write_percpu(cpu_tlbstate.state, TLBSTATE_OK);
- x86_write_percpu(cpu_tlbstate.active_mm, next);
-#endif
- cpu_set(cpu, next->cpu_vm_mask);
-
- /* Re-load page tables */
- load_cr3(next->pgd);
-
- /*
- * load the LDT, if the LDT is different:
- */
- if (unlikely(prev->context.ldt != next->context.ldt))
- load_LDT_nolock(&next->context);
- }
-#ifdef CONFIG_SMP
- else {
- x86_write_percpu(cpu_tlbstate.state, TLBSTATE_OK);
- BUG_ON(x86_read_percpu(cpu_tlbstate.active_mm) != next);
-
- if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) {
- /* We were in lazy tlb mode and leave_mm disabled
- * tlb flush IPI delivery. We must reload %cr3.
- */
- load_cr3(next->pgd);
- load_LDT_nolock(&next->context);
- }
- }
-#endif
-}
-
-#define deactivate_mm(tsk, mm) \
- asm("movl %0,%%gs": :"r" (0));
-
-#endif /* _ASM_X86_MMU_CONTEXT_32_H */
diff --git a/arch/x86/include/asm/mmu_context_64.h b/arch/x86/include/asm/mmu_context_64.h
deleted file mode 100644
index 677d36e..0000000
--- a/arch/x86/include/asm/mmu_context_64.h
+++ /dev/null
@@ -1,54 +0,0 @@
-#ifndef _ASM_X86_MMU_CONTEXT_64_H
-#define _ASM_X86_MMU_CONTEXT_64_H
-
-#include <asm/pda.h>
-
-static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
-{
-#ifdef CONFIG_SMP
- if (read_pda(mmu_state) == TLBSTATE_OK)
- write_pda(mmu_state, TLBSTATE_LAZY);
-#endif
-}
-
-static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
- struct task_struct *tsk)
-{
- unsigned cpu = smp_processor_id();
- if (likely(prev != next)) {
- /* stop flush ipis for the previous mm */
- cpu_clear(cpu, prev->cpu_vm_mask);
-#ifdef CONFIG_SMP
- write_pda(mmu_state, TLBSTATE_OK);
- write_pda(active_mm, next);
-#endif
- cpu_set(cpu, next->cpu_vm_mask);
- load_cr3(next->pgd);
-
- if (unlikely(next->context.ldt != prev->context.ldt))
- load_LDT_nolock(&next->context);
- }
-#ifdef CONFIG_SMP
- else {
- write_pda(mmu_state, TLBSTATE_OK);
- if (read_pda(active_mm) != next)
- BUG();
- if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) {
- /* We were in lazy tlb mode and leave_mm disabled
- * tlb flush IPI delivery. We must reload CR3
- * to make sure to use no freed page tables.
- */
- load_cr3(next->pgd);
- load_LDT_nolock(&next->context);
- }
- }
-#endif
-}
-
-#define deactivate_mm(tsk, mm) \
-do { \
- load_gs_index(0); \
- asm volatile("movl %0,%%fs"::"r"(0)); \
-} while (0)
-
-#endif /* _ASM_X86_MMU_CONTEXT_64_H */
diff --git a/arch/x86/include/asm/mpspec_def.h b/arch/x86/include/asm/mpspec_def.h
index 59568bc..4a7f96d 100644
--- a/arch/x86/include/asm/mpspec_def.h
+++ b/arch/x86/include/asm/mpspec_def.h
@@ -24,17 +24,18 @@
# endif
#endif
-struct intel_mp_floating {
- char mpf_signature[4]; /* "_MP_" */
- unsigned int mpf_physptr; /* Configuration table address */
- unsigned char mpf_length; /* Our length (paragraphs) */
- unsigned char mpf_specification;/* Specification version */
- unsigned char mpf_checksum; /* Checksum (makes sum 0) */
- unsigned char mpf_feature1; /* Standard or configuration ? */
- unsigned char mpf_feature2; /* Bit7 set for IMCR|PIC */
- unsigned char mpf_feature3; /* Unused (0) */
- unsigned char mpf_feature4; /* Unused (0) */
- unsigned char mpf_feature5; /* Unused (0) */
+/* Intel MP Floating Pointer Structure */
+struct mpf_intel {
+ char signature[4]; /* "_MP_" */
+ unsigned int physptr; /* Configuration table address */
+ unsigned char length; /* Our length (paragraphs) */
+ unsigned char specification; /* Specification version */
+ unsigned char checksum; /* Checksum (makes sum 0) */
+ unsigned char feature1; /* Standard or configuration ? */
+ unsigned char feature2; /* Bit7 set for IMCR|PIC */
+ unsigned char feature3; /* Unused (0) */
+ unsigned char feature4; /* Unused (0) */
+ unsigned char feature5; /* Unused (0) */
};
#define MPC_SIGNATURE "PCMP"
diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h
index e9873a2..6b98108 100644
--- a/arch/x86/include/asm/page.h
+++ b/arch/x86/include/asm/page.h
@@ -147,7 +147,7 @@
return pte.pte;
}
-static inline pteval_t native_pte_flags(pte_t pte)
+static inline pteval_t pte_flags(pte_t pte)
{
return native_pte_val(pte) & PTE_FLAGS_MASK;
}
@@ -173,7 +173,6 @@
#endif
#define pte_val(x) native_pte_val(x)
-#define pte_flags(x) native_pte_flags(x)
#define __pte(x) native_make_pte(x)
#endif /* CONFIG_PARAVIRT */
diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
index 5ebca29..e27fdbe 100644
--- a/arch/x86/include/asm/page_64.h
+++ b/arch/x86/include/asm/page_64.h
@@ -13,8 +13,8 @@
#define DEBUG_STACK_ORDER (EXCEPTION_STACK_ORDER + 1)
#define DEBUG_STKSZ (PAGE_SIZE << DEBUG_STACK_ORDER)
-#define IRQSTACK_ORDER 2
-#define IRQSTACKSIZE (PAGE_SIZE << IRQSTACK_ORDER)
+#define IRQ_STACK_ORDER 2
+#define IRQ_STACK_SIZE (PAGE_SIZE << IRQ_STACK_ORDER)
#define STACKFAULT_STACK 1
#define DOUBLEFAULT_STACK 2
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index ba3e2ff..ff69173 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -12,21 +12,38 @@
#define CLBR_EAX (1 << 0)
#define CLBR_ECX (1 << 1)
#define CLBR_EDX (1 << 2)
+#define CLBR_EDI (1 << 3)
-#ifdef CONFIG_X86_64
-#define CLBR_RSI (1 << 3)
-#define CLBR_RDI (1 << 4)
+#ifdef CONFIG_X86_32
+/* CLBR_ANY should match all regs platform has. For i386, that's just it */
+#define CLBR_ANY ((1 << 4) - 1)
+
+#define CLBR_ARG_REGS (CLBR_EAX | CLBR_EDX | CLBR_ECX)
+#define CLBR_RET_REG (CLBR_EAX | CLBR_EDX)
+#define CLBR_SCRATCH (0)
+#else
+#define CLBR_RAX CLBR_EAX
+#define CLBR_RCX CLBR_ECX
+#define CLBR_RDX CLBR_EDX
+#define CLBR_RDI CLBR_EDI
+#define CLBR_RSI (1 << 4)
#define CLBR_R8 (1 << 5)
#define CLBR_R9 (1 << 6)
#define CLBR_R10 (1 << 7)
#define CLBR_R11 (1 << 8)
+
#define CLBR_ANY ((1 << 9) - 1)
+
+#define CLBR_ARG_REGS (CLBR_RDI | CLBR_RSI | CLBR_RDX | \
+ CLBR_RCX | CLBR_R8 | CLBR_R9)
+#define CLBR_RET_REG (CLBR_RAX)
+#define CLBR_SCRATCH (CLBR_R10 | CLBR_R11)
+
#include <asm/desc_defs.h>
-#else
-/* CLBR_ANY should match all regs platform has. For i386, that's just it */
-#define CLBR_ANY ((1 << 3) - 1)
#endif /* X86_64 */
+#define CLBR_CALLEE_SAVE ((CLBR_ARG_REGS | CLBR_SCRATCH) & ~CLBR_RET_REG)
+
#ifndef __ASSEMBLY__
#include <linux/types.h>
#include <linux/cpumask.h>
@@ -40,6 +57,14 @@
struct mm_struct;
struct desc_struct;
+/*
+ * Wrapper type for pointers to code which uses the non-standard
+ * calling convention. See PV_CALL_SAVE_REGS_THUNK below.
+ */
+struct paravirt_callee_save {
+ void *func;
+};
+
/* general info */
struct pv_info {
unsigned int kernel_rpl;
@@ -189,11 +214,15 @@
* expected to use X86_EFLAGS_IF; all other bits
* returned from save_fl are undefined, and may be ignored by
* restore_fl.
+ *
+ * NOTE: These functions callers expect the callee to preserve
+ * more registers than the standard C calling convention.
*/
- unsigned long (*save_fl)(void);
- void (*restore_fl)(unsigned long);
- void (*irq_disable)(void);
- void (*irq_enable)(void);
+ struct paravirt_callee_save save_fl;
+ struct paravirt_callee_save restore_fl;
+ struct paravirt_callee_save irq_disable;
+ struct paravirt_callee_save irq_enable;
+
void (*safe_halt)(void);
void (*halt)(void);
@@ -244,7 +273,8 @@
void (*flush_tlb_user)(void);
void (*flush_tlb_kernel)(void);
void (*flush_tlb_single)(unsigned long addr);
- void (*flush_tlb_others)(const cpumask_t *cpus, struct mm_struct *mm,
+ void (*flush_tlb_others)(const struct cpumask *cpus,
+ struct mm_struct *mm,
unsigned long va);
/* Hooks for allocating and freeing a pagetable top-level */
@@ -278,12 +308,11 @@
void (*ptep_modify_prot_commit)(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte);
- pteval_t (*pte_val)(pte_t);
- pteval_t (*pte_flags)(pte_t);
- pte_t (*make_pte)(pteval_t pte);
+ struct paravirt_callee_save pte_val;
+ struct paravirt_callee_save make_pte;
- pgdval_t (*pgd_val)(pgd_t);
- pgd_t (*make_pgd)(pgdval_t pgd);
+ struct paravirt_callee_save pgd_val;
+ struct paravirt_callee_save make_pgd;
#if PAGETABLE_LEVELS >= 3
#ifdef CONFIG_X86_PAE
@@ -298,12 +327,12 @@
void (*set_pud)(pud_t *pudp, pud_t pudval);
- pmdval_t (*pmd_val)(pmd_t);
- pmd_t (*make_pmd)(pmdval_t pmd);
+ struct paravirt_callee_save pmd_val;
+ struct paravirt_callee_save make_pmd;
#if PAGETABLE_LEVELS == 4
- pudval_t (*pud_val)(pud_t);
- pud_t (*make_pud)(pudval_t pud);
+ struct paravirt_callee_save pud_val;
+ struct paravirt_callee_save make_pud;
void (*set_pgd)(pgd_t *pudp, pgd_t pgdval);
#endif /* PAGETABLE_LEVELS == 4 */
@@ -388,6 +417,8 @@
asm("start_" #ops "_" #name ": " code "; end_" #ops "_" #name ":")
unsigned paravirt_patch_nop(void);
+unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len);
+unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len);
unsigned paravirt_patch_ignore(unsigned len);
unsigned paravirt_patch_call(void *insnbuf,
const void *target, u16 tgt_clobbers,
@@ -479,25 +510,45 @@
* makes sure the incoming and outgoing types are always correct.
*/
#ifdef CONFIG_X86_32
-#define PVOP_VCALL_ARGS unsigned long __eax, __edx, __ecx
+#define PVOP_VCALL_ARGS \
+ unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx
#define PVOP_CALL_ARGS PVOP_VCALL_ARGS
+
+#define PVOP_CALL_ARG1(x) "a" ((unsigned long)(x))
+#define PVOP_CALL_ARG2(x) "d" ((unsigned long)(x))
+#define PVOP_CALL_ARG3(x) "c" ((unsigned long)(x))
+
#define PVOP_VCALL_CLOBBERS "=a" (__eax), "=d" (__edx), \
"=c" (__ecx)
#define PVOP_CALL_CLOBBERS PVOP_VCALL_CLOBBERS
+
+#define PVOP_VCALLEE_CLOBBERS "=a" (__eax), "=d" (__edx)
+#define PVOP_CALLEE_CLOBBERS PVOP_VCALLEE_CLOBBERS
+
#define EXTRA_CLOBBERS
#define VEXTRA_CLOBBERS
-#else
-#define PVOP_VCALL_ARGS unsigned long __edi, __esi, __edx, __ecx
+#else /* CONFIG_X86_64 */
+#define PVOP_VCALL_ARGS \
+ unsigned long __edi = __edi, __esi = __esi, \
+ __edx = __edx, __ecx = __ecx
#define PVOP_CALL_ARGS PVOP_VCALL_ARGS, __eax
+
+#define PVOP_CALL_ARG1(x) "D" ((unsigned long)(x))
+#define PVOP_CALL_ARG2(x) "S" ((unsigned long)(x))
+#define PVOP_CALL_ARG3(x) "d" ((unsigned long)(x))
+#define PVOP_CALL_ARG4(x) "c" ((unsigned long)(x))
+
#define PVOP_VCALL_CLOBBERS "=D" (__edi), \
"=S" (__esi), "=d" (__edx), \
"=c" (__ecx)
-
#define PVOP_CALL_CLOBBERS PVOP_VCALL_CLOBBERS, "=a" (__eax)
+#define PVOP_VCALLEE_CLOBBERS "=a" (__eax)
+#define PVOP_CALLEE_CLOBBERS PVOP_VCALLEE_CLOBBERS
+
#define EXTRA_CLOBBERS , "r8", "r9", "r10", "r11"
#define VEXTRA_CLOBBERS , "rax", "r8", "r9", "r10", "r11"
-#endif
+#endif /* CONFIG_X86_32 */
#ifdef CONFIG_PARAVIRT_DEBUG
#define PVOP_TEST_NULL(op) BUG_ON(op == NULL)
@@ -505,10 +556,11 @@
#define PVOP_TEST_NULL(op) ((void)op)
#endif
-#define __PVOP_CALL(rettype, op, pre, post, ...) \
+#define ____PVOP_CALL(rettype, op, clbr, call_clbr, extra_clbr, \
+ pre, post, ...) \
({ \
rettype __ret; \
- PVOP_CALL_ARGS; \
+ PVOP_CALL_ARGS; \
PVOP_TEST_NULL(op); \
/* This is 32-bit specific, but is okay in 64-bit */ \
/* since this condition will never hold */ \
@@ -516,70 +568,113 @@
asm volatile(pre \
paravirt_alt(PARAVIRT_CALL) \
post \
- : PVOP_CALL_CLOBBERS \
+ : call_clbr \
: paravirt_type(op), \
- paravirt_clobber(CLBR_ANY), \
+ paravirt_clobber(clbr), \
##__VA_ARGS__ \
- : "memory", "cc" EXTRA_CLOBBERS); \
+ : "memory", "cc" extra_clbr); \
__ret = (rettype)((((u64)__edx) << 32) | __eax); \
} else { \
asm volatile(pre \
paravirt_alt(PARAVIRT_CALL) \
post \
- : PVOP_CALL_CLOBBERS \
+ : call_clbr \
: paravirt_type(op), \
- paravirt_clobber(CLBR_ANY), \
+ paravirt_clobber(clbr), \
##__VA_ARGS__ \
- : "memory", "cc" EXTRA_CLOBBERS); \
+ : "memory", "cc" extra_clbr); \
__ret = (rettype)__eax; \
} \
__ret; \
})
-#define __PVOP_VCALL(op, pre, post, ...) \
+
+#define __PVOP_CALL(rettype, op, pre, post, ...) \
+ ____PVOP_CALL(rettype, op, CLBR_ANY, PVOP_CALL_CLOBBERS, \
+ EXTRA_CLOBBERS, pre, post, ##__VA_ARGS__)
+
+#define __PVOP_CALLEESAVE(rettype, op, pre, post, ...) \
+ ____PVOP_CALL(rettype, op.func, CLBR_RET_REG, \
+ PVOP_CALLEE_CLOBBERS, , \
+ pre, post, ##__VA_ARGS__)
+
+
+#define ____PVOP_VCALL(op, clbr, call_clbr, extra_clbr, pre, post, ...) \
({ \
PVOP_VCALL_ARGS; \
PVOP_TEST_NULL(op); \
asm volatile(pre \
paravirt_alt(PARAVIRT_CALL) \
post \
- : PVOP_VCALL_CLOBBERS \
+ : call_clbr \
: paravirt_type(op), \
- paravirt_clobber(CLBR_ANY), \
+ paravirt_clobber(clbr), \
##__VA_ARGS__ \
- : "memory", "cc" VEXTRA_CLOBBERS); \
+ : "memory", "cc" extra_clbr); \
})
+#define __PVOP_VCALL(op, pre, post, ...) \
+ ____PVOP_VCALL(op, CLBR_ANY, PVOP_VCALL_CLOBBERS, \
+ VEXTRA_CLOBBERS, \
+ pre, post, ##__VA_ARGS__)
+
+#define __PVOP_VCALLEESAVE(rettype, op, pre, post, ...) \
+ ____PVOP_CALL(rettype, op.func, CLBR_RET_REG, \
+ PVOP_VCALLEE_CLOBBERS, , \
+ pre, post, ##__VA_ARGS__)
+
+
+
#define PVOP_CALL0(rettype, op) \
__PVOP_CALL(rettype, op, "", "")
#define PVOP_VCALL0(op) \
__PVOP_VCALL(op, "", "")
+#define PVOP_CALLEE0(rettype, op) \
+ __PVOP_CALLEESAVE(rettype, op, "", "")
+#define PVOP_VCALLEE0(op) \
+ __PVOP_VCALLEESAVE(op, "", "")
+
+
#define PVOP_CALL1(rettype, op, arg1) \
- __PVOP_CALL(rettype, op, "", "", "0" ((unsigned long)(arg1)))
+ __PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1))
#define PVOP_VCALL1(op, arg1) \
- __PVOP_VCALL(op, "", "", "0" ((unsigned long)(arg1)))
+ __PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1))
+
+#define PVOP_CALLEE1(rettype, op, arg1) \
+ __PVOP_CALLEESAVE(rettype, op, "", "", PVOP_CALL_ARG1(arg1))
+#define PVOP_VCALLEE1(op, arg1) \
+ __PVOP_VCALLEESAVE(op, "", "", PVOP_CALL_ARG1(arg1))
+
#define PVOP_CALL2(rettype, op, arg1, arg2) \
- __PVOP_CALL(rettype, op, "", "", "0" ((unsigned long)(arg1)), \
- "1" ((unsigned long)(arg2)))
+ __PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1), \
+ PVOP_CALL_ARG2(arg2))
#define PVOP_VCALL2(op, arg1, arg2) \
- __PVOP_VCALL(op, "", "", "0" ((unsigned long)(arg1)), \
- "1" ((unsigned long)(arg2)))
+ __PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1), \
+ PVOP_CALL_ARG2(arg2))
+
+#define PVOP_CALLEE2(rettype, op, arg1, arg2) \
+ __PVOP_CALLEESAVE(rettype, op, "", "", PVOP_CALL_ARG1(arg1), \
+ PVOP_CALL_ARG2(arg2))
+#define PVOP_VCALLEE2(op, arg1, arg2) \
+ __PVOP_VCALLEESAVE(op, "", "", PVOP_CALL_ARG1(arg1), \
+ PVOP_CALL_ARG2(arg2))
+
#define PVOP_CALL3(rettype, op, arg1, arg2, arg3) \
- __PVOP_CALL(rettype, op, "", "", "0" ((unsigned long)(arg1)), \
- "1"((unsigned long)(arg2)), "2"((unsigned long)(arg3)))
+ __PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1), \
+ PVOP_CALL_ARG2(arg2), PVOP_CALL_ARG3(arg3))
#define PVOP_VCALL3(op, arg1, arg2, arg3) \
- __PVOP_VCALL(op, "", "", "0" ((unsigned long)(arg1)), \
- "1"((unsigned long)(arg2)), "2"((unsigned long)(arg3)))
+ __PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1), \
+ PVOP_CALL_ARG2(arg2), PVOP_CALL_ARG3(arg3))
/* This is the only difference in x86_64. We can make it much simpler */
#ifdef CONFIG_X86_32
#define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4) \
__PVOP_CALL(rettype, op, \
"push %[_arg4];", "lea 4(%%esp),%%esp;", \
- "0" ((u32)(arg1)), "1" ((u32)(arg2)), \
- "2" ((u32)(arg3)), [_arg4] "mr" ((u32)(arg4)))
+ PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \
+ PVOP_CALL_ARG3(arg3), [_arg4] "mr" ((u32)(arg4)))
#define PVOP_VCALL4(op, arg1, arg2, arg3, arg4) \
__PVOP_VCALL(op, \
"push %[_arg4];", "lea 4(%%esp),%%esp;", \
@@ -587,13 +682,13 @@
"2" ((u32)(arg3)), [_arg4] "mr" ((u32)(arg4)))
#else
#define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4) \
- __PVOP_CALL(rettype, op, "", "", "0" ((unsigned long)(arg1)), \
- "1"((unsigned long)(arg2)), "2"((unsigned long)(arg3)), \
- "3"((unsigned long)(arg4)))
+ __PVOP_CALL(rettype, op, "", "", \
+ PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \
+ PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4))
#define PVOP_VCALL4(op, arg1, arg2, arg3, arg4) \
- __PVOP_VCALL(op, "", "", "0" ((unsigned long)(arg1)), \
- "1"((unsigned long)(arg2)), "2"((unsigned long)(arg3)), \
- "3"((unsigned long)(arg4)))
+ __PVOP_VCALL(op, "", "", \
+ PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \
+ PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4))
#endif
static inline int paravirt_enabled(void)
@@ -984,10 +1079,11 @@
PVOP_VCALL1(pv_mmu_ops.flush_tlb_single, addr);
}
-static inline void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
+static inline void flush_tlb_others(const struct cpumask *cpumask,
+ struct mm_struct *mm,
unsigned long va)
{
- PVOP_VCALL3(pv_mmu_ops.flush_tlb_others, &cpumask, mm, va);
+ PVOP_VCALL3(pv_mmu_ops.flush_tlb_others, cpumask, mm, va);
}
static inline int paravirt_pgd_alloc(struct mm_struct *mm)
@@ -1059,13 +1155,13 @@
pteval_t ret;
if (sizeof(pteval_t) > sizeof(long))
- ret = PVOP_CALL2(pteval_t,
- pv_mmu_ops.make_pte,
- val, (u64)val >> 32);
+ ret = PVOP_CALLEE2(pteval_t,
+ pv_mmu_ops.make_pte,
+ val, (u64)val >> 32);
else
- ret = PVOP_CALL1(pteval_t,
- pv_mmu_ops.make_pte,
- val);
+ ret = PVOP_CALLEE1(pteval_t,
+ pv_mmu_ops.make_pte,
+ val);
return (pte_t) { .pte = ret };
}
@@ -1075,42 +1171,25 @@
pteval_t ret;
if (sizeof(pteval_t) > sizeof(long))
- ret = PVOP_CALL2(pteval_t, pv_mmu_ops.pte_val,
- pte.pte, (u64)pte.pte >> 32);
+ ret = PVOP_CALLEE2(pteval_t, pv_mmu_ops.pte_val,
+ pte.pte, (u64)pte.pte >> 32);
else
- ret = PVOP_CALL1(pteval_t, pv_mmu_ops.pte_val,
- pte.pte);
+ ret = PVOP_CALLEE1(pteval_t, pv_mmu_ops.pte_val,
+ pte.pte);
return ret;
}
-static inline pteval_t pte_flags(pte_t pte)
-{
- pteval_t ret;
-
- if (sizeof(pteval_t) > sizeof(long))
- ret = PVOP_CALL2(pteval_t, pv_mmu_ops.pte_flags,
- pte.pte, (u64)pte.pte >> 32);
- else
- ret = PVOP_CALL1(pteval_t, pv_mmu_ops.pte_flags,
- pte.pte);
-
-#ifdef CONFIG_PARAVIRT_DEBUG
- BUG_ON(ret & PTE_PFN_MASK);
-#endif
- return ret;
-}
-
static inline pgd_t __pgd(pgdval_t val)
{
pgdval_t ret;
if (sizeof(pgdval_t) > sizeof(long))
- ret = PVOP_CALL2(pgdval_t, pv_mmu_ops.make_pgd,
- val, (u64)val >> 32);
+ ret = PVOP_CALLEE2(pgdval_t, pv_mmu_ops.make_pgd,
+ val, (u64)val >> 32);
else
- ret = PVOP_CALL1(pgdval_t, pv_mmu_ops.make_pgd,
- val);
+ ret = PVOP_CALLEE1(pgdval_t, pv_mmu_ops.make_pgd,
+ val);
return (pgd_t) { ret };
}
@@ -1120,11 +1199,11 @@
pgdval_t ret;
if (sizeof(pgdval_t) > sizeof(long))
- ret = PVOP_CALL2(pgdval_t, pv_mmu_ops.pgd_val,
- pgd.pgd, (u64)pgd.pgd >> 32);
+ ret = PVOP_CALLEE2(pgdval_t, pv_mmu_ops.pgd_val,
+ pgd.pgd, (u64)pgd.pgd >> 32);
else
- ret = PVOP_CALL1(pgdval_t, pv_mmu_ops.pgd_val,
- pgd.pgd);
+ ret = PVOP_CALLEE1(pgdval_t, pv_mmu_ops.pgd_val,
+ pgd.pgd);
return ret;
}
@@ -1188,11 +1267,11 @@
pmdval_t ret;
if (sizeof(pmdval_t) > sizeof(long))
- ret = PVOP_CALL2(pmdval_t, pv_mmu_ops.make_pmd,
- val, (u64)val >> 32);
+ ret = PVOP_CALLEE2(pmdval_t, pv_mmu_ops.make_pmd,
+ val, (u64)val >> 32);
else
- ret = PVOP_CALL1(pmdval_t, pv_mmu_ops.make_pmd,
- val);
+ ret = PVOP_CALLEE1(pmdval_t, pv_mmu_ops.make_pmd,
+ val);
return (pmd_t) { ret };
}
@@ -1202,11 +1281,11 @@
pmdval_t ret;
if (sizeof(pmdval_t) > sizeof(long))
- ret = PVOP_CALL2(pmdval_t, pv_mmu_ops.pmd_val,
- pmd.pmd, (u64)pmd.pmd >> 32);
+ ret = PVOP_CALLEE2(pmdval_t, pv_mmu_ops.pmd_val,
+ pmd.pmd, (u64)pmd.pmd >> 32);
else
- ret = PVOP_CALL1(pmdval_t, pv_mmu_ops.pmd_val,
- pmd.pmd);
+ ret = PVOP_CALLEE1(pmdval_t, pv_mmu_ops.pmd_val,
+ pmd.pmd);
return ret;
}
@@ -1228,11 +1307,11 @@
pudval_t ret;
if (sizeof(pudval_t) > sizeof(long))
- ret = PVOP_CALL2(pudval_t, pv_mmu_ops.make_pud,
- val, (u64)val >> 32);
+ ret = PVOP_CALLEE2(pudval_t, pv_mmu_ops.make_pud,
+ val, (u64)val >> 32);
else
- ret = PVOP_CALL1(pudval_t, pv_mmu_ops.make_pud,
- val);
+ ret = PVOP_CALLEE1(pudval_t, pv_mmu_ops.make_pud,
+ val);
return (pud_t) { ret };
}
@@ -1242,11 +1321,11 @@
pudval_t ret;
if (sizeof(pudval_t) > sizeof(long))
- ret = PVOP_CALL2(pudval_t, pv_mmu_ops.pud_val,
- pud.pud, (u64)pud.pud >> 32);
+ ret = PVOP_CALLEE2(pudval_t, pv_mmu_ops.pud_val,
+ pud.pud, (u64)pud.pud >> 32);
else
- ret = PVOP_CALL1(pudval_t, pv_mmu_ops.pud_val,
- pud.pud);
+ ret = PVOP_CALLEE1(pudval_t, pv_mmu_ops.pud_val,
+ pud.pud);
return ret;
}
@@ -1387,9 +1466,10 @@
}
void _paravirt_nop(void);
-#define paravirt_nop ((void *)_paravirt_nop)
+u32 _paravirt_ident_32(u32);
+u64 _paravirt_ident_64(u64);
-void paravirt_use_bytelocks(void);
+#define paravirt_nop ((void *)_paravirt_nop)
#ifdef CONFIG_SMP
@@ -1438,12 +1518,37 @@
__parainstructions_end[];
#ifdef CONFIG_X86_32
-#define PV_SAVE_REGS "pushl %%ecx; pushl %%edx;"
-#define PV_RESTORE_REGS "popl %%edx; popl %%ecx"
+#define PV_SAVE_REGS "pushl %ecx; pushl %edx;"
+#define PV_RESTORE_REGS "popl %edx; popl %ecx;"
+
+/* save and restore all caller-save registers, except return value */
+#define PV_SAVE_ALL_CALLER_REGS "pushl %ecx;"
+#define PV_RESTORE_ALL_CALLER_REGS "popl %ecx;"
+
#define PV_FLAGS_ARG "0"
#define PV_EXTRA_CLOBBERS
#define PV_VEXTRA_CLOBBERS
#else
+/* save and restore all caller-save registers, except return value */
+#define PV_SAVE_ALL_CALLER_REGS \
+ "push %rcx;" \
+ "push %rdx;" \
+ "push %rsi;" \
+ "push %rdi;" \
+ "push %r8;" \
+ "push %r9;" \
+ "push %r10;" \
+ "push %r11;"
+#define PV_RESTORE_ALL_CALLER_REGS \
+ "pop %r11;" \
+ "pop %r10;" \
+ "pop %r9;" \
+ "pop %r8;" \
+ "pop %rdi;" \
+ "pop %rsi;" \
+ "pop %rdx;" \
+ "pop %rcx;"
+
/* We save some registers, but all of them, that's too much. We clobber all
* caller saved registers but the argument parameter */
#define PV_SAVE_REGS "pushq %%rdi;"
@@ -1453,52 +1558,76 @@
#define PV_FLAGS_ARG "D"
#endif
+/*
+ * Generate a thunk around a function which saves all caller-save
+ * registers except for the return value. This allows C functions to
+ * be called from assembler code where fewer than normal registers are
+ * available. It may also help code generation around calls from C
+ * code if the common case doesn't use many registers.
+ *
+ * When a callee is wrapped in a thunk, the caller can assume that all
+ * arg regs and all scratch registers are preserved across the
+ * call. The return value in rax/eax will not be saved, even for void
+ * functions.
+ */
+#define PV_CALLEE_SAVE_REGS_THUNK(func) \
+ extern typeof(func) __raw_callee_save_##func; \
+ static void *__##func##__ __used = func; \
+ \
+ asm(".pushsection .text;" \
+ "__raw_callee_save_" #func ": " \
+ PV_SAVE_ALL_CALLER_REGS \
+ "call " #func ";" \
+ PV_RESTORE_ALL_CALLER_REGS \
+ "ret;" \
+ ".popsection")
+
+/* Get a reference to a callee-save function */
+#define PV_CALLEE_SAVE(func) \
+ ((struct paravirt_callee_save) { __raw_callee_save_##func })
+
+/* Promise that "func" already uses the right calling convention */
+#define __PV_IS_CALLEE_SAVE(func) \
+ ((struct paravirt_callee_save) { func })
+
static inline unsigned long __raw_local_save_flags(void)
{
unsigned long f;
- asm volatile(paravirt_alt(PV_SAVE_REGS
- PARAVIRT_CALL
- PV_RESTORE_REGS)
+ asm volatile(paravirt_alt(PARAVIRT_CALL)
: "=a"(f)
: paravirt_type(pv_irq_ops.save_fl),
paravirt_clobber(CLBR_EAX)
- : "memory", "cc" PV_VEXTRA_CLOBBERS);
+ : "memory", "cc");
return f;
}
static inline void raw_local_irq_restore(unsigned long f)
{
- asm volatile(paravirt_alt(PV_SAVE_REGS
- PARAVIRT_CALL
- PV_RESTORE_REGS)
+ asm volatile(paravirt_alt(PARAVIRT_CALL)
: "=a"(f)
: PV_FLAGS_ARG(f),
paravirt_type(pv_irq_ops.restore_fl),
paravirt_clobber(CLBR_EAX)
- : "memory", "cc" PV_EXTRA_CLOBBERS);
+ : "memory", "cc");
}
static inline void raw_local_irq_disable(void)
{
- asm volatile(paravirt_alt(PV_SAVE_REGS
- PARAVIRT_CALL
- PV_RESTORE_REGS)
+ asm volatile(paravirt_alt(PARAVIRT_CALL)
:
: paravirt_type(pv_irq_ops.irq_disable),
paravirt_clobber(CLBR_EAX)
- : "memory", "eax", "cc" PV_EXTRA_CLOBBERS);
+ : "memory", "eax", "cc");
}
static inline void raw_local_irq_enable(void)
{
- asm volatile(paravirt_alt(PV_SAVE_REGS
- PARAVIRT_CALL
- PV_RESTORE_REGS)
+ asm volatile(paravirt_alt(PARAVIRT_CALL)
:
: paravirt_type(pv_irq_ops.irq_enable),
paravirt_clobber(CLBR_EAX)
- : "memory", "eax", "cc" PV_EXTRA_CLOBBERS);
+ : "memory", "eax", "cc");
}
static inline unsigned long __raw_local_irq_save(void)
@@ -1541,33 +1670,49 @@
.popsection
+#define COND_PUSH(set, mask, reg) \
+ .if ((~(set)) & mask); push %reg; .endif
+#define COND_POP(set, mask, reg) \
+ .if ((~(set)) & mask); pop %reg; .endif
+
#ifdef CONFIG_X86_64
-#define PV_SAVE_REGS \
- push %rax; \
- push %rcx; \
- push %rdx; \
- push %rsi; \
- push %rdi; \
- push %r8; \
- push %r9; \
- push %r10; \
- push %r11
-#define PV_RESTORE_REGS \
- pop %r11; \
- pop %r10; \
- pop %r9; \
- pop %r8; \
- pop %rdi; \
- pop %rsi; \
- pop %rdx; \
- pop %rcx; \
- pop %rax
+
+#define PV_SAVE_REGS(set) \
+ COND_PUSH(set, CLBR_RAX, rax); \
+ COND_PUSH(set, CLBR_RCX, rcx); \
+ COND_PUSH(set, CLBR_RDX, rdx); \
+ COND_PUSH(set, CLBR_RSI, rsi); \
+ COND_PUSH(set, CLBR_RDI, rdi); \
+ COND_PUSH(set, CLBR_R8, r8); \
+ COND_PUSH(set, CLBR_R9, r9); \
+ COND_PUSH(set, CLBR_R10, r10); \
+ COND_PUSH(set, CLBR_R11, r11)
+#define PV_RESTORE_REGS(set) \
+ COND_POP(set, CLBR_R11, r11); \
+ COND_POP(set, CLBR_R10, r10); \
+ COND_POP(set, CLBR_R9, r9); \
+ COND_POP(set, CLBR_R8, r8); \
+ COND_POP(set, CLBR_RDI, rdi); \
+ COND_POP(set, CLBR_RSI, rsi); \
+ COND_POP(set, CLBR_RDX, rdx); \
+ COND_POP(set, CLBR_RCX, rcx); \
+ COND_POP(set, CLBR_RAX, rax)
+
#define PARA_PATCH(struct, off) ((PARAVIRT_PATCH_##struct + (off)) / 8)
#define PARA_SITE(ptype, clobbers, ops) _PVSITE(ptype, clobbers, ops, .quad, 8)
#define PARA_INDIRECT(addr) *addr(%rip)
#else
-#define PV_SAVE_REGS pushl %eax; pushl %edi; pushl %ecx; pushl %edx
-#define PV_RESTORE_REGS popl %edx; popl %ecx; popl %edi; popl %eax
+#define PV_SAVE_REGS(set) \
+ COND_PUSH(set, CLBR_EAX, eax); \
+ COND_PUSH(set, CLBR_EDI, edi); \
+ COND_PUSH(set, CLBR_ECX, ecx); \
+ COND_PUSH(set, CLBR_EDX, edx)
+#define PV_RESTORE_REGS(set) \
+ COND_POP(set, CLBR_EDX, edx); \
+ COND_POP(set, CLBR_ECX, ecx); \
+ COND_POP(set, CLBR_EDI, edi); \
+ COND_POP(set, CLBR_EAX, eax)
+
#define PARA_PATCH(struct, off) ((PARAVIRT_PATCH_##struct + (off)) / 4)
#define PARA_SITE(ptype, clobbers, ops) _PVSITE(ptype, clobbers, ops, .long, 4)
#define PARA_INDIRECT(addr) *%cs:addr
@@ -1579,15 +1724,15 @@
#define DISABLE_INTERRUPTS(clobbers) \
PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_disable), clobbers, \
- PV_SAVE_REGS; \
+ PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \
call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_disable); \
- PV_RESTORE_REGS;) \
+ PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
#define ENABLE_INTERRUPTS(clobbers) \
PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_enable), clobbers, \
- PV_SAVE_REGS; \
+ PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \
call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_enable); \
- PV_RESTORE_REGS;)
+ PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
#define USERGS_SYSRET32 \
PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret32), \
@@ -1617,11 +1762,15 @@
PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE, \
swapgs)
+/*
+ * Note: swapgs is very special, and in practise is either going to be
+ * implemented with a single "swapgs" instruction or something very
+ * special. Either way, we don't need to save any registers for
+ * it.
+ */
#define SWAPGS \
PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE, \
- PV_SAVE_REGS; \
- call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs); \
- PV_RESTORE_REGS \
+ call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs) \
)
#define GET_CR2_INTO_RCX \
diff --git a/arch/x86/include/asm/pda.h b/arch/x86/include/asm/pda.h
deleted file mode 100644
index 2fbfff8..0000000
--- a/arch/x86/include/asm/pda.h
+++ /dev/null
@@ -1,137 +0,0 @@
-#ifndef _ASM_X86_PDA_H
-#define _ASM_X86_PDA_H
-
-#ifndef __ASSEMBLY__
-#include <linux/stddef.h>
-#include <linux/types.h>
-#include <linux/cache.h>
-#include <asm/page.h>
-
-/* Per processor datastructure. %gs points to it while the kernel runs */
-struct x8664_pda {
- struct task_struct *pcurrent; /* 0 Current process */
- unsigned long data_offset; /* 8 Per cpu data offset from linker
- address */
- unsigned long kernelstack; /* 16 top of kernel stack for current */
- unsigned long oldrsp; /* 24 user rsp for system call */
- int irqcount; /* 32 Irq nesting counter. Starts -1 */
- unsigned int cpunumber; /* 36 Logical CPU number */
-#ifdef CONFIG_CC_STACKPROTECTOR
- unsigned long stack_canary; /* 40 stack canary value */
- /* gcc-ABI: this canary MUST be at
- offset 40!!! */
-#endif
- char *irqstackptr;
- short nodenumber; /* number of current node (32k max) */
- short in_bootmem; /* pda lives in bootmem */
- unsigned int __softirq_pending;
- unsigned int __nmi_count; /* number of NMI on this CPUs */
- short mmu_state;
- short isidle;
- struct mm_struct *active_mm;
- unsigned apic_timer_irqs;
- unsigned irq0_irqs;
- unsigned irq_resched_count;
- unsigned irq_call_count;
- unsigned irq_tlb_count;
- unsigned irq_thermal_count;
- unsigned irq_threshold_count;
- unsigned irq_spurious_count;
-} ____cacheline_aligned_in_smp;
-
-extern struct x8664_pda **_cpu_pda;
-extern void pda_init(int);
-
-#define cpu_pda(i) (_cpu_pda[i])
-
-/*
- * There is no fast way to get the base address of the PDA, all the accesses
- * have to mention %fs/%gs. So it needs to be done this Torvaldian way.
- */
-extern void __bad_pda_field(void) __attribute__((noreturn));
-
-/*
- * proxy_pda doesn't actually exist, but tell gcc it is accessed for
- * all PDA accesses so it gets read/write dependencies right.
- */
-extern struct x8664_pda _proxy_pda;
-
-#define pda_offset(field) offsetof(struct x8664_pda, field)
-
-#define pda_to_op(op, field, val) \
-do { \
- typedef typeof(_proxy_pda.field) T__; \
- if (0) { T__ tmp__; tmp__ = (val); } /* type checking */ \
- switch (sizeof(_proxy_pda.field)) { \
- case 2: \
- asm(op "w %1,%%gs:%c2" : \
- "+m" (_proxy_pda.field) : \
- "ri" ((T__)val), \
- "i"(pda_offset(field))); \
- break; \
- case 4: \
- asm(op "l %1,%%gs:%c2" : \
- "+m" (_proxy_pda.field) : \
- "ri" ((T__)val), \
- "i" (pda_offset(field))); \
- break; \
- case 8: \
- asm(op "q %1,%%gs:%c2": \
- "+m" (_proxy_pda.field) : \
- "ri" ((T__)val), \
- "i"(pda_offset(field))); \
- break; \
- default: \
- __bad_pda_field(); \
- } \
-} while (0)
-
-#define pda_from_op(op, field) \
-({ \
- typeof(_proxy_pda.field) ret__; \
- switch (sizeof(_proxy_pda.field)) { \
- case 2: \
- asm(op "w %%gs:%c1,%0" : \
- "=r" (ret__) : \
- "i" (pda_offset(field)), \
- "m" (_proxy_pda.field)); \
- break; \
- case 4: \
- asm(op "l %%gs:%c1,%0": \
- "=r" (ret__): \
- "i" (pda_offset(field)), \
- "m" (_proxy_pda.field)); \
- break; \
- case 8: \
- asm(op "q %%gs:%c1,%0": \
- "=r" (ret__) : \
- "i" (pda_offset(field)), \
- "m" (_proxy_pda.field)); \
- break; \
- default: \
- __bad_pda_field(); \
- } \
- ret__; \
-})
-
-#define read_pda(field) pda_from_op("mov", field)
-#define write_pda(field, val) pda_to_op("mov", field, val)
-#define add_pda(field, val) pda_to_op("add", field, val)
-#define sub_pda(field, val) pda_to_op("sub", field, val)
-#define or_pda(field, val) pda_to_op("or", field, val)
-
-/* This is not atomic against other CPUs -- CPU preemption needs to be off */
-#define test_and_clear_bit_pda(bit, field) \
-({ \
- int old__; \
- asm volatile("btr %2,%%gs:%c3\n\tsbbl %0,%0" \
- : "=r" (old__), "+m" (_proxy_pda.field) \
- : "dIr" (bit), "i" (pda_offset(field)) : "memory");\
- old__; \
-})
-
-#endif
-
-#define PDA_STACKOFFSET (5*8)
-
-#endif /* _ASM_X86_PDA_H */
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index ece7205..aee103b 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -2,53 +2,12 @@
#define _ASM_X86_PERCPU_H
#ifdef CONFIG_X86_64
-#include <linux/compiler.h>
-
-/* Same as asm-generic/percpu.h, except that we store the per cpu offset
- in the PDA. Longer term the PDA and every per cpu variable
- should be just put into a single section and referenced directly
- from %gs */
-
-#ifdef CONFIG_SMP
-#include <asm/pda.h>
-
-#define __per_cpu_offset(cpu) (cpu_pda(cpu)->data_offset)
-#define __my_cpu_offset read_pda(data_offset)
-
-#define per_cpu_offset(x) (__per_cpu_offset(x))
-
+#define __percpu_seg gs
+#define __percpu_mov_op movq
+#else
+#define __percpu_seg fs
+#define __percpu_mov_op movl
#endif
-#include <asm-generic/percpu.h>
-
-DECLARE_PER_CPU(struct x8664_pda, pda);
-
-/*
- * These are supposed to be implemented as a single instruction which
- * operates on the per-cpu data base segment. x86-64 doesn't have
- * that yet, so this is a fairly inefficient workaround for the
- * meantime. The single instruction is atomic with respect to
- * preemption and interrupts, so we need to explicitly disable
- * interrupts here to achieve the same effect. However, because it
- * can be used from within interrupt-disable/enable, we can't actually
- * disable interrupts; disabling preemption is enough.
- */
-#define x86_read_percpu(var) \
- ({ \
- typeof(per_cpu_var(var)) __tmp; \
- preempt_disable(); \
- __tmp = __get_cpu_var(var); \
- preempt_enable(); \
- __tmp; \
- })
-
-#define x86_write_percpu(var, val) \
- do { \
- preempt_disable(); \
- __get_cpu_var(var) = (val); \
- preempt_enable(); \
- } while(0)
-
-#else /* CONFIG_X86_64 */
#ifdef __ASSEMBLY__
@@ -65,47 +24,48 @@
* PER_CPU(cpu_gdt_descr, %ebx)
*/
#ifdef CONFIG_SMP
-#define PER_CPU(var, reg) \
- movl %fs:per_cpu__##this_cpu_off, reg; \
+#define PER_CPU(var, reg) \
+ __percpu_mov_op %__percpu_seg:per_cpu__this_cpu_off, reg; \
lea per_cpu__##var(reg), reg
-#define PER_CPU_VAR(var) %fs:per_cpu__##var
+#define PER_CPU_VAR(var) %__percpu_seg:per_cpu__##var
#else /* ! SMP */
-#define PER_CPU(var, reg) \
- movl $per_cpu__##var, reg
+#define PER_CPU(var, reg) \
+ __percpu_mov_op $per_cpu__##var, reg
#define PER_CPU_VAR(var) per_cpu__##var
#endif /* SMP */
+#ifdef CONFIG_X86_64_SMP
+#define INIT_PER_CPU_VAR(var) init_per_cpu__##var
+#else
+#define INIT_PER_CPU_VAR(var) per_cpu__##var
+#endif
+
#else /* ...!ASSEMBLY */
-/*
- * PER_CPU finds an address of a per-cpu variable.
- *
- * Args:
- * var - variable name
- * cpu - 32bit register containing the current CPU number
- *
- * The resulting address is stored in the "cpu" argument.
- *
- * Example:
- * PER_CPU(cpu_gdt_descr, %ebx)
- */
+#include <linux/stringify.h>
+
#ifdef CONFIG_SMP
+#define __percpu_arg(x) "%%"__stringify(__percpu_seg)":%P" #x
+#define __my_cpu_offset percpu_read(this_cpu_off)
+#else
+#define __percpu_arg(x) "%" #x
+#endif
-#define __my_cpu_offset x86_read_percpu(this_cpu_off)
+/*
+ * Initialized pointers to per-cpu variables needed for the boot
+ * processor need to use these macros to get the proper address
+ * offset from __per_cpu_load on SMP.
+ *
+ * There also must be an entry in vmlinux_64.lds.S
+ */
+#define DECLARE_INIT_PER_CPU(var) \
+ extern typeof(per_cpu_var(var)) init_per_cpu_var(var)
-/* fs segment starts at (positive) offset == __per_cpu_offset[cpu] */
-#define __percpu_seg "%%fs:"
-
-#else /* !SMP */
-
-#define __percpu_seg ""
-
-#endif /* SMP */
-
-#include <asm-generic/percpu.h>
-
-/* We can use this directly for local CPU (faster). */
-DECLARE_PER_CPU(unsigned long, this_cpu_off);
+#ifdef CONFIG_X86_64_SMP
+#define init_per_cpu_var(var) init_per_cpu__##var
+#else
+#define init_per_cpu_var(var) per_cpu_var(var)
+#endif
/* For arch-specific code, we can use direct single-insn ops (they
* don't give an lvalue though). */
@@ -120,20 +80,25 @@
} \
switch (sizeof(var)) { \
case 1: \
- asm(op "b %1,"__percpu_seg"%0" \
+ asm(op "b %1,"__percpu_arg(0) \
: "+m" (var) \
: "ri" ((T__)val)); \
break; \
case 2: \
- asm(op "w %1,"__percpu_seg"%0" \
+ asm(op "w %1,"__percpu_arg(0) \
: "+m" (var) \
: "ri" ((T__)val)); \
break; \
case 4: \
- asm(op "l %1,"__percpu_seg"%0" \
+ asm(op "l %1,"__percpu_arg(0) \
: "+m" (var) \
: "ri" ((T__)val)); \
break; \
+ case 8: \
+ asm(op "q %1,"__percpu_arg(0) \
+ : "+m" (var) \
+ : "re" ((T__)val)); \
+ break; \
default: __bad_percpu_size(); \
} \
} while (0)
@@ -143,17 +108,22 @@
typeof(var) ret__; \
switch (sizeof(var)) { \
case 1: \
- asm(op "b "__percpu_seg"%1,%0" \
+ asm(op "b "__percpu_arg(1)",%0" \
: "=r" (ret__) \
: "m" (var)); \
break; \
case 2: \
- asm(op "w "__percpu_seg"%1,%0" \
+ asm(op "w "__percpu_arg(1)",%0" \
: "=r" (ret__) \
: "m" (var)); \
break; \
case 4: \
- asm(op "l "__percpu_seg"%1,%0" \
+ asm(op "l "__percpu_arg(1)",%0" \
+ : "=r" (ret__) \
+ : "m" (var)); \
+ break; \
+ case 8: \
+ asm(op "q "__percpu_arg(1)",%0" \
: "=r" (ret__) \
: "m" (var)); \
break; \
@@ -162,13 +132,30 @@
ret__; \
})
-#define x86_read_percpu(var) percpu_from_op("mov", per_cpu__##var)
-#define x86_write_percpu(var, val) percpu_to_op("mov", per_cpu__##var, val)
-#define x86_add_percpu(var, val) percpu_to_op("add", per_cpu__##var, val)
-#define x86_sub_percpu(var, val) percpu_to_op("sub", per_cpu__##var, val)
-#define x86_or_percpu(var, val) percpu_to_op("or", per_cpu__##var, val)
+#define percpu_read(var) percpu_from_op("mov", per_cpu__##var)
+#define percpu_write(var, val) percpu_to_op("mov", per_cpu__##var, val)
+#define percpu_add(var, val) percpu_to_op("add", per_cpu__##var, val)
+#define percpu_sub(var, val) percpu_to_op("sub", per_cpu__##var, val)
+#define percpu_and(var, val) percpu_to_op("and", per_cpu__##var, val)
+#define percpu_or(var, val) percpu_to_op("or", per_cpu__##var, val)
+#define percpu_xor(var, val) percpu_to_op("xor", per_cpu__##var, val)
+
+/* This is not atomic against other CPUs -- CPU preemption needs to be off */
+#define x86_test_and_clear_bit_percpu(bit, var) \
+({ \
+ int old__; \
+ asm volatile("btr %2,"__percpu_arg(1)"\n\tsbbl %0,%0" \
+ : "=r" (old__), "+m" (per_cpu__##var) \
+ : "dIr" (bit)); \
+ old__; \
+})
+
+#include <asm-generic/percpu.h>
+
+/* We can use this directly for local CPU (faster). */
+DECLARE_PER_CPU(unsigned long, this_cpu_off);
+
#endif /* !__ASSEMBLY__ */
-#endif /* !CONFIG_X86_64 */
#ifdef CONFIG_SMP
@@ -195,9 +182,9 @@
#define early_per_cpu_ptr(_name) (_name##_early_ptr)
#define early_per_cpu_map(_name, _idx) (_name##_early_map[_idx])
#define early_per_cpu(_name, _cpu) \
- (early_per_cpu_ptr(_name) ? \
- early_per_cpu_ptr(_name)[_cpu] : \
- per_cpu(_name, _cpu))
+ *(early_per_cpu_ptr(_name) ? \
+ &early_per_cpu_ptr(_name)[_cpu] : \
+ &per_cpu(_name, _cpu))
#else /* !CONFIG_SMP */
#define DEFINE_EARLY_PER_CPU(_type, _name, _initvalue) \
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 4f5af84..6f7c102 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -240,64 +240,78 @@
(_PAGE_PSE | _PAGE_PRESENT);
}
+static inline pte_t pte_set_flags(pte_t pte, pteval_t set)
+{
+ pteval_t v = native_pte_val(pte);
+
+ return native_make_pte(v | set);
+}
+
+static inline pte_t pte_clear_flags(pte_t pte, pteval_t clear)
+{
+ pteval_t v = native_pte_val(pte);
+
+ return native_make_pte(v & ~clear);
+}
+
static inline pte_t pte_mkclean(pte_t pte)
{
- return __pte(pte_val(pte) & ~_PAGE_DIRTY);
+ return pte_clear_flags(pte, _PAGE_DIRTY);
}
static inline pte_t pte_mkold(pte_t pte)
{
- return __pte(pte_val(pte) & ~_PAGE_ACCESSED);
+ return pte_clear_flags(pte, _PAGE_ACCESSED);
}
static inline pte_t pte_wrprotect(pte_t pte)
{
- return __pte(pte_val(pte) & ~_PAGE_RW);
+ return pte_clear_flags(pte, _PAGE_RW);
}
static inline pte_t pte_mkexec(pte_t pte)
{
- return __pte(pte_val(pte) & ~_PAGE_NX);
+ return pte_clear_flags(pte, _PAGE_NX);
}
static inline pte_t pte_mkdirty(pte_t pte)
{
- return __pte(pte_val(pte) | _PAGE_DIRTY);
+ return pte_set_flags(pte, _PAGE_DIRTY);
}
static inline pte_t pte_mkyoung(pte_t pte)
{
- return __pte(pte_val(pte) | _PAGE_ACCESSED);
+ return pte_set_flags(pte, _PAGE_ACCESSED);
}
static inline pte_t pte_mkwrite(pte_t pte)
{
- return __pte(pte_val(pte) | _PAGE_RW);
+ return pte_set_flags(pte, _PAGE_RW);
}
static inline pte_t pte_mkhuge(pte_t pte)
{
- return __pte(pte_val(pte) | _PAGE_PSE);
+ return pte_set_flags(pte, _PAGE_PSE);
}
static inline pte_t pte_clrhuge(pte_t pte)
{
- return __pte(pte_val(pte) & ~_PAGE_PSE);
+ return pte_clear_flags(pte, _PAGE_PSE);
}
static inline pte_t pte_mkglobal(pte_t pte)
{
- return __pte(pte_val(pte) | _PAGE_GLOBAL);
+ return pte_set_flags(pte, _PAGE_GLOBAL);
}
static inline pte_t pte_clrglobal(pte_t pte)
{
- return __pte(pte_val(pte) & ~_PAGE_GLOBAL);
+ return pte_clear_flags(pte, _PAGE_GLOBAL);
}
static inline pte_t pte_mkspecial(pte_t pte)
{
- return __pte(pte_val(pte) | _PAGE_SPECIAL);
+ return pte_set_flags(pte, _PAGE_SPECIAL);
}
extern pteval_t __supported_pte_mask;
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index ba09289..1df9637 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -11,7 +11,6 @@
#include <asm/processor.h>
#include <linux/bitops.h>
#include <linux/threads.h>
-#include <asm/pda.h>
extern pud_t level3_kernel_pgt[512];
extern pud_t level3_ident_pgt[512];
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 3bfd523..9763eb7 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -378,6 +378,24 @@
#ifdef CONFIG_X86_64
DECLARE_PER_CPU(struct orig_ist, orig_ist);
+
+union irq_stack_union {
+ char irq_stack[IRQ_STACK_SIZE];
+ /*
+ * GCC hardcodes the stack canary as %gs:40. Since the
+ * irq_stack is the object at %gs:0, we reserve the bottom
+ * 48 bytes of the irq stack for the canary.
+ */
+ struct {
+ char gs_base[40];
+ unsigned long stack_canary;
+ };
+};
+
+DECLARE_PER_CPU(union irq_stack_union, irq_stack_union);
+DECLARE_INIT_PER_CPU(irq_stack_union);
+
+DECLARE_PER_CPU(char *, irq_stack_ptr);
#endif
extern void print_cpu_info(struct cpuinfo_x86 *);
@@ -752,9 +770,9 @@
extern struct desc_ptr early_gdt_descr;
extern void cpu_set_gdt(int);
-extern void switch_to_new_gdt(void);
+extern void switch_to_new_gdt(int);
+extern void load_percpu_segment(int);
extern void cpu_init(void);
-extern void init_gdt(int cpu);
static inline unsigned long get_debugctlmsr(void)
{
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index ebe858c..5369497 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -100,7 +100,6 @@
extern unsigned long init_pg_tables_end;
#else
-void __init x86_64_init_pda(void);
void __init x86_64_start_kernel(char *real_mode);
void __init x86_64_start_reservations(char *real_mode_data);
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 19953df..45ef8a1b 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -15,34 +15,8 @@
# include <asm/io_apic.h>
# endif
#endif
-#include <asm/pda.h>
#include <asm/thread_info.h>
-
-#ifdef CONFIG_X86_64
-
-extern cpumask_var_t cpu_callin_mask;
-extern cpumask_var_t cpu_callout_mask;
-extern cpumask_var_t cpu_initialized_mask;
-extern cpumask_var_t cpu_sibling_setup_mask;
-
-#else /* CONFIG_X86_32 */
-
-extern cpumask_t cpu_callin_map;
-extern cpumask_t cpu_callout_map;
-extern cpumask_t cpu_initialized;
-extern cpumask_t cpu_sibling_setup_map;
-
-#define cpu_callin_mask ((struct cpumask *)&cpu_callin_map)
-#define cpu_callout_mask ((struct cpumask *)&cpu_callout_map)
-#define cpu_initialized_mask ((struct cpumask *)&cpu_initialized)
-#define cpu_sibling_setup_mask ((struct cpumask *)&cpu_sibling_setup_map)
-
-#endif /* CONFIG_X86_32 */
-
-extern void (*mtrr_hook)(void);
-extern void zap_low_mappings(void);
-
-extern int __cpuinit get_local_pda(int cpu);
+#include <asm/cpumask.h>
extern int smp_num_siblings;
extern unsigned int num_processors;
@@ -50,9 +24,7 @@
DECLARE_PER_CPU(cpumask_t, cpu_sibling_map);
DECLARE_PER_CPU(cpumask_t, cpu_core_map);
DECLARE_PER_CPU(u16, cpu_llc_id);
-#ifdef CONFIG_X86_32
DECLARE_PER_CPU(int, cpu_number);
-#endif
static inline struct cpumask *cpu_sibling_mask(int cpu)
{
@@ -167,8 +139,6 @@
void native_send_call_func_ipi(const struct cpumask *mask);
void native_send_call_func_single_ipi(int cpu);
-extern void prefill_possible_map(void);
-
void smp_store_cpu_info(int id);
#define cpu_physical_id(cpu) per_cpu(x86_cpu_to_apicid, cpu)
@@ -177,10 +147,6 @@
{
return cpumask_weight(cpu_callout_mask);
}
-#else
-static inline void prefill_possible_map(void)
-{
-}
#endif /* CONFIG_SMP */
extern unsigned disabled_cpus __cpuinitdata;
@@ -191,11 +157,11 @@
* from the initial startup. We map APIC_BASE very early in page_setup(),
* so this is correct in the x86 case.
*/
-#define raw_smp_processor_id() (x86_read_percpu(cpu_number))
+#define raw_smp_processor_id() (percpu_read(cpu_number))
extern int safe_smp_processor_id(void);
#elif defined(CONFIG_X86_64_SMP)
-#define raw_smp_processor_id() read_pda(cpunumber)
+#define raw_smp_processor_id() (percpu_read(cpu_number))
#define stack_smp_processor_id() \
({ \
@@ -205,10 +171,6 @@
})
#define safe_smp_processor_id() smp_processor_id()
-#else /* !CONFIG_X86_32_SMP && !CONFIG_X86_64_SMP */
-#define cpu_physical_id(cpu) boot_cpu_physical_apicid
-#define safe_smp_processor_id() 0
-#define stack_smp_processor_id() 0
#endif
#ifdef CONFIG_X86_LOCAL_APIC
@@ -251,11 +213,5 @@
#endif /* CONFIG_X86_LOCAL_APIC */
-#ifdef CONFIG_X86_HAS_BOOT_CPU_ID
-extern unsigned char boot_cpu_id;
-#else
-#define boot_cpu_id 0
-#endif
-
#endif /* __ASSEMBLY__ */
#endif /* _ASM_X86_SMP_H */
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index d17c919..2bd6b11 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -172,70 +172,8 @@
return (((tmp >> TICKET_SHIFT) - tmp) & ((1 << TICKET_SHIFT) - 1)) > 1;
}
-#ifdef CONFIG_PARAVIRT
-/*
- * Define virtualization-friendly old-style lock byte lock, for use in
- * pv_lock_ops if desired.
- *
- * This differs from the pre-2.6.24 spinlock by always using xchgb
- * rather than decb to take the lock; this allows it to use a
- * zero-initialized lock structure. It also maintains a 1-byte
- * contention counter, so that we can implement
- * __byte_spin_is_contended.
- */
-struct __byte_spinlock {
- s8 lock;
- s8 spinners;
-};
+#ifndef CONFIG_PARAVIRT
-static inline int __byte_spin_is_locked(raw_spinlock_t *lock)
-{
- struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
- return bl->lock != 0;
-}
-
-static inline int __byte_spin_is_contended(raw_spinlock_t *lock)
-{
- struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
- return bl->spinners != 0;
-}
-
-static inline void __byte_spin_lock(raw_spinlock_t *lock)
-{
- struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
- s8 val = 1;
-
- asm("1: xchgb %1, %0\n"
- " test %1,%1\n"
- " jz 3f\n"
- " " LOCK_PREFIX "incb %2\n"
- "2: rep;nop\n"
- " cmpb $1, %0\n"
- " je 2b\n"
- " " LOCK_PREFIX "decb %2\n"
- " jmp 1b\n"
- "3:"
- : "+m" (bl->lock), "+q" (val), "+m" (bl->spinners): : "memory");
-}
-
-static inline int __byte_spin_trylock(raw_spinlock_t *lock)
-{
- struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
- u8 old = 1;
-
- asm("xchgb %1,%0"
- : "+m" (bl->lock), "+q" (old) : : "memory");
-
- return old == 0;
-}
-
-static inline void __byte_spin_unlock(raw_spinlock_t *lock)
-{
- struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
- smp_wmb();
- bl->lock = 0;
-}
-#else /* !CONFIG_PARAVIRT */
static inline int __raw_spin_is_locked(raw_spinlock_t *lock)
{
return __ticket_spin_is_locked(lock);
@@ -267,7 +205,7 @@
__raw_spin_lock(lock);
}
-#endif /* CONFIG_PARAVIRT */
+#endif
static inline void __raw_spin_unlock_wait(raw_spinlock_t *lock)
{
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
new file mode 100644
index 0000000..36a700a
--- /dev/null
+++ b/arch/x86/include/asm/stackprotector.h
@@ -0,0 +1,38 @@
+#ifndef _ASM_STACKPROTECTOR_H
+#define _ASM_STACKPROTECTOR_H 1
+
+#include <asm/tsc.h>
+#include <asm/processor.h>
+
+/*
+ * Initialize the stackprotector canary value.
+ *
+ * NOTE: this must only be called from functions that never return,
+ * and it must always be inlined.
+ */
+static __always_inline void boot_init_stack_canary(void)
+{
+ u64 canary;
+ u64 tsc;
+
+ /*
+ * Build time only check to make sure the stack_canary is at
+ * offset 40 in the pda; this is a gcc ABI requirement
+ */
+ BUILD_BUG_ON(offsetof(union irq_stack_union, stack_canary) != 40);
+
+ /*
+ * We both use the random pool and the current TSC as a source
+ * of randomness. The TSC only matters for very early init,
+ * there it already has some randomness on most systems. Later
+ * on during the bootup the random pool has true entropy too.
+ */
+ get_random_bytes(&canary, sizeof(canary));
+ tsc = __native_read_tsc();
+ canary += tsc + (tsc << 32UL);
+
+ current->stack_canary = canary;
+ percpu_write(irq_stack_union.stack_canary, canary);
+}
+
+#endif
diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h
index 8e626ea..2fcc70b 100644
--- a/arch/x86/include/asm/system.h
+++ b/arch/x86/include/asm/system.h
@@ -86,27 +86,44 @@
, "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \
"r12", "r13", "r14", "r15"
+#ifdef CONFIG_CC_STACKPROTECTOR
+#define __switch_canary \
+ "movq %P[task_canary](%%rsi),%%r8\n\t" \
+ "movq %%r8,"__percpu_arg([gs_canary])"\n\t"
+#define __switch_canary_oparam \
+ , [gs_canary] "=m" (per_cpu_var(irq_stack_union.stack_canary))
+#define __switch_canary_iparam \
+ , [task_canary] "i" (offsetof(struct task_struct, stack_canary))
+#else /* CC_STACKPROTECTOR */
+#define __switch_canary
+#define __switch_canary_oparam
+#define __switch_canary_iparam
+#endif /* CC_STACKPROTECTOR */
+
/* Save restore flags to clear handle leaking NT */
#define switch_to(prev, next, last) \
- asm volatile(SAVE_CONTEXT \
+ asm volatile(SAVE_CONTEXT \
"movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */ \
"movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */ \
"call __switch_to\n\t" \
".globl thread_return\n" \
"thread_return:\n\t" \
- "movq %%gs:%P[pda_pcurrent],%%rsi\n\t" \
+ "movq "__percpu_arg([current_task])",%%rsi\n\t" \
+ __switch_canary \
"movq %P[thread_info](%%rsi),%%r8\n\t" \
LOCK_PREFIX "btr %[tif_fork],%P[ti_flags](%%r8)\n\t" \
"movq %%rax,%%rdi\n\t" \
"jc ret_from_fork\n\t" \
RESTORE_CONTEXT \
: "=a" (last) \
+ __switch_canary_oparam \
: [next] "S" (next), [prev] "D" (prev), \
[threadrsp] "i" (offsetof(struct task_struct, thread.sp)), \
[ti_flags] "i" (offsetof(struct thread_info, flags)), \
[tif_fork] "i" (TIF_FORK), \
[thread_info] "i" (offsetof(struct task_struct, stack)), \
- [pda_pcurrent] "i" (offsetof(struct x8664_pda, pcurrent)) \
+ [current_task] "m" (per_cpu_var(current_task)) \
+ __switch_canary_iparam \
: "memory", "cc" __EXTRA_CLOBBER)
#endif
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 9878964..df9d5f7 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -40,6 +40,7 @@
*/
__u8 supervisor_stack[0];
#endif
+ int uaccess_err;
};
#define INIT_THREAD_INFO(tsk) \
@@ -194,25 +195,21 @@
#else /* X86_32 */
-#include <asm/pda.h>
+#include <asm/percpu.h>
+#define KERNEL_STACK_OFFSET (5*8)
/*
* macros/functions for gaining access to the thread information structure
* preempt_count needs to be 1 initially, until the scheduler is functional.
*/
#ifndef __ASSEMBLY__
+DECLARE_PER_CPU(unsigned long, kernel_stack);
+
static inline struct thread_info *current_thread_info(void)
{
struct thread_info *ti;
- ti = (void *)(read_pda(kernelstack) + PDA_STACKOFFSET - THREAD_SIZE);
- return ti;
-}
-
-/* do not use in interrupt context */
-static inline struct thread_info *stack_thread_info(void)
-{
- struct thread_info *ti;
- asm("andq %%rsp,%0; " : "=r" (ti) : "0" (~(THREAD_SIZE - 1)));
+ ti = (void *)(percpu_read(kernel_stack) +
+ KERNEL_STACK_OFFSET - THREAD_SIZE);
return ti;
}
@@ -220,8 +217,8 @@
/* how to get the thread information struct from ASM */
#define GET_THREAD_INFO(reg) \
- movq %gs:pda_kernelstack,reg ; \
- subq $(THREAD_SIZE-PDA_STACKOFFSET),reg
+ movq PER_CPU_VAR(kernel_stack),reg ; \
+ subq $(THREAD_SIZE-KERNEL_STACK_OFFSET),reg
#endif
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 0e7bbb5..d3539f9 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -113,7 +113,7 @@
__flush_tlb();
}
-static inline void native_flush_tlb_others(const cpumask_t *cpumask,
+static inline void native_flush_tlb_others(const struct cpumask *cpumask,
struct mm_struct *mm,
unsigned long va)
{
@@ -142,31 +142,28 @@
flush_tlb_mm(vma->vm_mm);
}
-void native_flush_tlb_others(const cpumask_t *cpumask, struct mm_struct *mm,
- unsigned long va);
+void native_flush_tlb_others(const struct cpumask *cpumask,
+ struct mm_struct *mm, unsigned long va);
#define TLBSTATE_OK 1
#define TLBSTATE_LAZY 2
-#ifdef CONFIG_X86_32
struct tlb_state {
struct mm_struct *active_mm;
int state;
- char __cacheline_padding[L1_CACHE_BYTES-8];
};
DECLARE_PER_CPU(struct tlb_state, cpu_tlbstate);
-void reset_lazy_tlbstate(void);
-#else
static inline void reset_lazy_tlbstate(void)
{
+ percpu_write(cpu_tlbstate.state, 0);
+ percpu_write(cpu_tlbstate.active_mm, &init_mm);
}
-#endif
#endif /* SMP */
#ifndef CONFIG_PARAVIRT
-#define flush_tlb_others(mask, mm, va) native_flush_tlb_others(&mask, mm, va)
+#define flush_tlb_others(mask, mm, va) native_flush_tlb_others(mask, mm, va)
#endif
static inline void flush_tlb_kernel_range(unsigned long start,
@@ -175,4 +172,6 @@
flush_tlb_all();
}
+extern void zap_low_mappings(void);
+
#endif /* _ASM_X86_TLBFLUSH_H */
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 4e2f2e0..77cfb2c 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -74,6 +74,8 @@
return &node_to_cpumask_map[node];
}
+static inline void setup_node_to_cpumask_map(void) { }
+
#else /* CONFIG_X86_64 */
/* Mappings between node number and cpus on that node. */
@@ -83,7 +85,8 @@
DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map);
/* Returns the number of the current Node. */
-#define numa_node_id() read_pda(nodenumber)
+DECLARE_PER_CPU(int, node_number);
+#define numa_node_id() percpu_read(node_number)
#ifdef CONFIG_DEBUG_PER_CPU_MAPS
extern int cpu_to_node(int cpu);
@@ -102,10 +105,7 @@
/* Same function but used if called before per_cpu areas are setup */
static inline int early_cpu_to_node(int cpu)
{
- if (early_per_cpu_ptr(x86_cpu_to_node_map))
- return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
-
- return per_cpu(x86_cpu_to_node_map, cpu);
+ return early_per_cpu(x86_cpu_to_node_map, cpu);
}
/* Returns a pointer to the cpumask of CPUs on Node 'node'. */
@@ -122,6 +122,8 @@
#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */
+extern void setup_node_to_cpumask_map(void);
+
/*
* Replace default node_to_cpumask_ptr with optimized version
* Deprecated: use "const struct cpumask *mask = cpumask_of_node(node)"
@@ -192,9 +194,20 @@
#else /* !CONFIG_NUMA */
-#define numa_node_id() 0
-#define cpu_to_node(cpu) 0
-#define early_cpu_to_node(cpu) 0
+static inline int numa_node_id(void)
+{
+ return 0;
+}
+
+static inline int cpu_to_node(int cpu)
+{
+ return 0;
+}
+
+static inline int early_cpu_to_node(int cpu)
+{
+ return 0;
+}
static inline const cpumask_t *cpumask_of_node(int node)
{
@@ -209,6 +222,8 @@
return first_cpu(cpu_online_map);
}
+static inline void setup_node_to_cpumask_map(void) { }
+
/*
* Replace default node_to_cpumask_ptr with optimized version
* Deprecated: use "const struct cpumask *mask = cpumask_of_node(node)"
diff --git a/arch/x86/include/asm/trampoline.h b/arch/x86/include/asm/trampoline.h
index 780ba0a..90f06c2 100644
--- a/arch/x86/include/asm/trampoline.h
+++ b/arch/x86/include/asm/trampoline.h
@@ -13,6 +13,7 @@
extern unsigned long init_rsp;
extern unsigned long initial_code;
+extern unsigned long initial_gs;
#define TRAMPOLINE_SIZE roundup(trampoline_end - trampoline_data, PAGE_SIZE)
#define TRAMPOLINE_BASE 0x6000
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 4340055..b685ece 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -121,7 +121,7 @@
#define __get_user_x(size, ret, x, ptr) \
asm volatile("call __get_user_" #size \
- : "=a" (ret),"=d" (x) \
+ : "=a" (ret), "=d" (x) \
: "0" (ptr)) \
/* Careful: we have to cast the result to the type of the pointer
@@ -181,12 +181,12 @@
#define __put_user_x(size, x, ptr, __ret_pu) \
asm volatile("call __put_user_" #size : "=a" (__ret_pu) \
- :"0" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx")
+ : "0" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx")
#ifdef CONFIG_X86_32
-#define __put_user_u64(x, addr, err) \
+#define __put_user_asm_u64(x, addr, err, errret) \
asm volatile("1: movl %%eax,0(%2)\n" \
"2: movl %%edx,4(%2)\n" \
"3:\n" \
@@ -197,14 +197,24 @@
_ASM_EXTABLE(1b, 4b) \
_ASM_EXTABLE(2b, 4b) \
: "=r" (err) \
- : "A" (x), "r" (addr), "i" (-EFAULT), "0" (err))
+ : "A" (x), "r" (addr), "i" (errret), "0" (err))
+
+#define __put_user_asm_ex_u64(x, addr) \
+ asm volatile("1: movl %%eax,0(%1)\n" \
+ "2: movl %%edx,4(%1)\n" \
+ "3:\n" \
+ _ASM_EXTABLE(1b, 2b - 1b) \
+ _ASM_EXTABLE(2b, 3b - 2b) \
+ : : "A" (x), "r" (addr))
#define __put_user_x8(x, ptr, __ret_pu) \
asm volatile("call __put_user_8" : "=a" (__ret_pu) \
: "A" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx")
#else
-#define __put_user_u64(x, ptr, retval) \
- __put_user_asm(x, ptr, retval, "q", "", "Zr", -EFAULT)
+#define __put_user_asm_u64(x, ptr, retval, errret) \
+ __put_user_asm(x, ptr, retval, "q", "", "Zr", errret)
+#define __put_user_asm_ex_u64(x, addr) \
+ __put_user_asm_ex(x, addr, "q", "", "Zr")
#define __put_user_x8(x, ptr, __ret_pu) __put_user_x(8, x, ptr, __ret_pu)
#endif
@@ -276,10 +286,32 @@
__put_user_asm(x, ptr, retval, "w", "w", "ir", errret); \
break; \
case 4: \
- __put_user_asm(x, ptr, retval, "l", "k", "ir", errret);\
+ __put_user_asm(x, ptr, retval, "l", "k", "ir", errret); \
break; \
case 8: \
- __put_user_u64((__typeof__(*ptr))(x), ptr, retval); \
+ __put_user_asm_u64((__typeof__(*ptr))(x), ptr, retval, \
+ errret); \
+ break; \
+ default: \
+ __put_user_bad(); \
+ } \
+} while (0)
+
+#define __put_user_size_ex(x, ptr, size) \
+do { \
+ __chk_user_ptr(ptr); \
+ switch (size) { \
+ case 1: \
+ __put_user_asm_ex(x, ptr, "b", "b", "iq"); \
+ break; \
+ case 2: \
+ __put_user_asm_ex(x, ptr, "w", "w", "ir"); \
+ break; \
+ case 4: \
+ __put_user_asm_ex(x, ptr, "l", "k", "ir"); \
+ break; \
+ case 8: \
+ __put_user_asm_ex_u64((__typeof__(*ptr))(x), ptr); \
break; \
default: \
__put_user_bad(); \
@@ -311,9 +343,12 @@
#ifdef CONFIG_X86_32
#define __get_user_asm_u64(x, ptr, retval, errret) (x) = __get_user_bad()
+#define __get_user_asm_ex_u64(x, ptr) (x) = __get_user_bad()
#else
#define __get_user_asm_u64(x, ptr, retval, errret) \
__get_user_asm(x, ptr, retval, "q", "", "=r", errret)
+#define __get_user_asm_ex_u64(x, ptr) \
+ __get_user_asm_ex(x, ptr, "q", "", "=r")
#endif
#define __get_user_size(x, ptr, size, retval, errret) \
@@ -350,6 +385,33 @@
: "=r" (err), ltype(x) \
: "m" (__m(addr)), "i" (errret), "0" (err))
+#define __get_user_size_ex(x, ptr, size) \
+do { \
+ __chk_user_ptr(ptr); \
+ switch (size) { \
+ case 1: \
+ __get_user_asm_ex(x, ptr, "b", "b", "=q"); \
+ break; \
+ case 2: \
+ __get_user_asm_ex(x, ptr, "w", "w", "=r"); \
+ break; \
+ case 4: \
+ __get_user_asm_ex(x, ptr, "l", "k", "=r"); \
+ break; \
+ case 8: \
+ __get_user_asm_ex_u64(x, ptr); \
+ break; \
+ default: \
+ (x) = __get_user_bad(); \
+ } \
+} while (0)
+
+#define __get_user_asm_ex(x, addr, itype, rtype, ltype) \
+ asm volatile("1: mov"itype" %1,%"rtype"0\n" \
+ "2:\n" \
+ _ASM_EXTABLE(1b, 2b - 1b) \
+ : ltype(x) : "m" (__m(addr)))
+
#define __put_user_nocheck(x, ptr, size) \
({ \
int __pu_err; \
@@ -385,6 +447,26 @@
_ASM_EXTABLE(1b, 3b) \
: "=r"(err) \
: ltype(x), "m" (__m(addr)), "i" (errret), "0" (err))
+
+#define __put_user_asm_ex(x, addr, itype, rtype, ltype) \
+ asm volatile("1: mov"itype" %"rtype"0,%1\n" \
+ "2:\n" \
+ _ASM_EXTABLE(1b, 2b - 1b) \
+ : : ltype(x), "m" (__m(addr)))
+
+/*
+ * uaccess_try and catch
+ */
+#define uaccess_try do { \
+ int prev_err = current_thread_info()->uaccess_err; \
+ current_thread_info()->uaccess_err = 0; \
+ barrier();
+
+#define uaccess_catch(err) \
+ (err) |= current_thread_info()->uaccess_err; \
+ current_thread_info()->uaccess_err = prev_err; \
+} while (0)
+
/**
* __get_user: - Get a simple variable from user space, with less checking.
* @x: Variable to store result.
@@ -408,6 +490,7 @@
#define __get_user(x, ptr) \
__get_user_nocheck((x), (ptr), sizeof(*(ptr)))
+
/**
* __put_user: - Write a simple value into user space, with less checking.
* @x: Value to copy to user space.
@@ -435,6 +518,45 @@
#define __put_user_unaligned __put_user
/*
+ * {get|put}_user_try and catch
+ *
+ * get_user_try {
+ * get_user_ex(...);
+ * } get_user_catch(err)
+ */
+#define get_user_try uaccess_try
+#define get_user_catch(err) uaccess_catch(err)
+
+#define get_user_ex(x, ptr) do { \
+ unsigned long __gue_val; \
+ __get_user_size_ex((__gue_val), (ptr), (sizeof(*(ptr)))); \
+ (x) = (__force __typeof__(*(ptr)))__gue_val; \
+} while (0)
+
+#ifdef CONFIG_X86_WP_WORKS_OK
+
+#define put_user_try uaccess_try
+#define put_user_catch(err) uaccess_catch(err)
+
+#define put_user_ex(x, ptr) \
+ __put_user_size_ex((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
+
+#else /* !CONFIG_X86_WP_WORKS_OK */
+
+#define put_user_try do { \
+ int __uaccess_err = 0;
+
+#define put_user_catch(err) \
+ (err) |= __uaccess_err; \
+} while (0)
+
+#define put_user_ex(x, ptr) do { \
+ __uaccess_err |= __put_user(x, ptr); \
+} while (0)
+
+#endif /* CONFIG_X86_WP_WORKS_OK */
+
+/*
* movsl can be slow when source and dest are not both 8-byte aligned
*/
#ifdef CONFIG_X86_INTEL_USERCOPY
diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h
new file mode 100644
index 0000000..8ac1d7e
--- /dev/null
+++ b/arch/x86/include/asm/uv/uv.h
@@ -0,0 +1,33 @@
+#ifndef _ASM_X86_UV_UV_H
+#define _ASM_X86_UV_UV_H
+
+enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC};
+
+#ifdef CONFIG_X86_UV
+
+extern enum uv_system_type get_uv_system_type(void);
+extern int is_uv_system(void);
+extern void uv_cpu_init(void);
+extern void uv_system_init(void);
+extern int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip);
+extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
+ struct mm_struct *mm,
+ unsigned long va,
+ unsigned int cpu);
+
+#else /* X86_UV */
+
+static inline enum uv_system_type get_uv_system_type(void) { return UV_NONE; }
+static inline int is_uv_system(void) { return 0; }
+static inline void uv_cpu_init(void) { }
+static inline void uv_system_init(void) { }
+static inline int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip)
+{ return 1; }
+static inline const struct cpumask *
+uv_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm,
+ unsigned long va, unsigned int cpu)
+{ return cpumask; }
+
+#endif /* X86_UV */
+
+#endif /* _ASM_X86_UV_UV_H */
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 50423c7..9b0e61b 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -325,7 +325,6 @@
#define cpubit_isset(cpu, bau_local_cpumask) \
test_bit((cpu), (bau_local_cpumask).bits)
-extern int uv_flush_tlb_others(cpumask_t *, struct mm_struct *, unsigned long);
extern void uv_bau_message_intr1(void);
extern void uv_bau_timeout_intr1(void);
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index d364df0..37fa30b 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -23,11 +23,12 @@
CFLAGS_vsyscall_64.o := $(PROFILING) -g0 $(nostackp)
CFLAGS_hpet.o := $(nostackp)
CFLAGS_tsc.o := $(nostackp)
+CFLAGS_paravirt.o := $(nostackp)
obj-y := process_$(BITS).o signal.o entry_$(BITS).o
obj-y += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
obj-y += time_$(BITS).o ioport.o ldt.o dumpstack.o
-obj-y += setup.o i8259.o irqinit_$(BITS).o setup_percpu.o
+obj-y += setup.o i8259.o irqinit_$(BITS).o
obj-$(CONFIG_X86_VISWS) += visws_quirks.o
obj-$(CONFIG_X86_32) += probe_roms_32.o
obj-$(CONFIG_X86_32) += sys_i386_32.o i386_ksyms_32.o
@@ -57,9 +58,9 @@
apm-y := apm_32.o
obj-$(CONFIG_APM) += apm.o
obj-$(CONFIG_X86_SMP) += smp.o
-obj-$(CONFIG_X86_SMP) += smpboot.o tsc_sync.o ipi.o tlb_$(BITS).o
-obj-$(CONFIG_X86_32_SMP) += smpcommon.o
-obj-$(CONFIG_X86_64_SMP) += tsc_sync.o smpcommon.o
+obj-$(CONFIG_X86_SMP) += smpboot.o tsc_sync.o ipi.o
+obj-$(CONFIG_SMP) += setup_percpu.o
+obj-$(CONFIG_X86_64_SMP) += tsc_sync.o
obj-$(CONFIG_X86_TRAMPOLINE) += trampoline_$(BITS).o
obj-$(CONFIG_X86_MPPARSE) += mpparse.o
obj-$(CONFIG_X86_LOCAL_APIC) += apic.o nmi.o
@@ -114,10 +115,11 @@
###
# 64 bit specific files
ifeq ($(CONFIG_X86_64),y)
- obj-y += genapic_64.o genapic_flat_64.o genx2apic_uv_x.o tlb_uv.o
- obj-y += bios_uv.o uv_irq.o uv_sysfs.o
+ obj-y += genapic_64.o genapic_flat_64.o
obj-y += genx2apic_cluster.o
obj-y += genx2apic_phys.o
+ obj-$(CONFIG_X86_UV) += genx2apic_uv_x.o tlb_uv.o
+ obj-$(CONFIG_X86_UV) += bios_uv.o uv_irq.o uv_sysfs.o
obj-$(CONFIG_X86_PM_TIMER) += pmtimer_64.o
obj-$(CONFIG_AUDIT) += audit_64.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 7678f10..c193ec3 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -912,8 +912,8 @@
DECLARE_BITMAP(used, 256);
bitmap_zero(used, 256);
for (i = 0; i < nr_ioapics; i++) {
- struct mp_config_ioapic *ia = &mp_ioapics[i];
- __set_bit(ia->mp_apicid, used);
+ struct mpc_ioapic *ia = &mp_ioapics[i];
+ __set_bit(ia->apicid, used);
}
if (!test_bit(id, used))
return id;
@@ -945,29 +945,29 @@
idx = nr_ioapics;
- mp_ioapics[idx].mp_type = MP_IOAPIC;
- mp_ioapics[idx].mp_flags = MPC_APIC_USABLE;
- mp_ioapics[idx].mp_apicaddr = address;
+ mp_ioapics[idx].type = MP_IOAPIC;
+ mp_ioapics[idx].flags = MPC_APIC_USABLE;
+ mp_ioapics[idx].apicaddr = address;
set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address);
- mp_ioapics[idx].mp_apicid = uniq_ioapic_id(id);
+ mp_ioapics[idx].apicid = uniq_ioapic_id(id);
#ifdef CONFIG_X86_32
- mp_ioapics[idx].mp_apicver = io_apic_get_version(idx);
+ mp_ioapics[idx].apicver = io_apic_get_version(idx);
#else
- mp_ioapics[idx].mp_apicver = 0;
+ mp_ioapics[idx].apicver = 0;
#endif
/*
* Build basic GSI lookup table to facilitate gsi->io_apic lookups
* and to prevent reprogramming of IOAPIC pins (PCI GSIs).
*/
- mp_ioapic_routing[idx].apic_id = mp_ioapics[idx].mp_apicid;
+ mp_ioapic_routing[idx].apic_id = mp_ioapics[idx].apicid;
mp_ioapic_routing[idx].gsi_base = gsi_base;
mp_ioapic_routing[idx].gsi_end = gsi_base +
io_apic_get_redir_entries(idx);
- printk(KERN_INFO "IOAPIC[%d]: apic_id %d, version %d, address 0x%lx, "
- "GSI %d-%d\n", idx, mp_ioapics[idx].mp_apicid,
- mp_ioapics[idx].mp_apicver, mp_ioapics[idx].mp_apicaddr,
+ printk(KERN_INFO "IOAPIC[%d]: apic_id %d, version %d, address 0x%x, "
+ "GSI %d-%d\n", idx, mp_ioapics[idx].apicid,
+ mp_ioapics[idx].apicver, mp_ioapics[idx].apicaddr,
mp_ioapic_routing[idx].gsi_base, mp_ioapic_routing[idx].gsi_end);
nr_ioapics++;
@@ -996,19 +996,19 @@
return max_gsi + 1;
}
-static void assign_to_mp_irq(struct mp_config_intsrc *m,
- struct mp_config_intsrc *mp_irq)
+static void assign_to_mp_irq(struct mpc_intsrc *m,
+ struct mpc_intsrc *mp_irq)
{
- memcpy(mp_irq, m, sizeof(struct mp_config_intsrc));
+ memcpy(mp_irq, m, sizeof(struct mpc_intsrc));
}
-static int mp_irq_cmp(struct mp_config_intsrc *mp_irq,
- struct mp_config_intsrc *m)
+static int mp_irq_cmp(struct mpc_intsrc *mp_irq,
+ struct mpc_intsrc *m)
{
- return memcmp(mp_irq, m, sizeof(struct mp_config_intsrc));
+ return memcmp(mp_irq, m, sizeof(struct mpc_intsrc));
}
-static void save_mp_irq(struct mp_config_intsrc *m)
+static void save_mp_irq(struct mpc_intsrc *m)
{
int i;
@@ -1026,7 +1026,7 @@
{
int ioapic;
int pin;
- struct mp_config_intsrc mp_irq;
+ struct mpc_intsrc mp_irq;
/*
* Convert 'gsi' to 'ioapic.pin'.
@@ -1044,13 +1044,13 @@
if ((bus_irq == 0) && (trigger == 3))
trigger = 1;
- mp_irq.mp_type = MP_INTSRC;
- mp_irq.mp_irqtype = mp_INT;
- mp_irq.mp_irqflag = (trigger << 2) | polarity;
- mp_irq.mp_srcbus = MP_ISA_BUS;
- mp_irq.mp_srcbusirq = bus_irq; /* IRQ */
- mp_irq.mp_dstapic = mp_ioapics[ioapic].mp_apicid; /* APIC ID */
- mp_irq.mp_dstirq = pin; /* INTIN# */
+ mp_irq.type = MP_INTSRC;
+ mp_irq.irqtype = mp_INT;
+ mp_irq.irqflag = (trigger << 2) | polarity;
+ mp_irq.srcbus = MP_ISA_BUS;
+ mp_irq.srcbusirq = bus_irq; /* IRQ */
+ mp_irq.dstapic = mp_ioapics[ioapic].apicid; /* APIC ID */
+ mp_irq.dstirq = pin; /* INTIN# */
save_mp_irq(&mp_irq);
}
@@ -1060,7 +1060,7 @@
int i;
int ioapic;
unsigned int dstapic;
- struct mp_config_intsrc mp_irq;
+ struct mpc_intsrc mp_irq;
#if defined (CONFIG_MCA) || defined (CONFIG_EISA)
/*
@@ -1085,7 +1085,7 @@
ioapic = mp_find_ioapic(0);
if (ioapic < 0)
return;
- dstapic = mp_ioapics[ioapic].mp_apicid;
+ dstapic = mp_ioapics[ioapic].apicid;
/*
* Use the default configuration for the IRQs 0-15. Unless
@@ -1095,16 +1095,14 @@
int idx;
for (idx = 0; idx < mp_irq_entries; idx++) {
- struct mp_config_intsrc *irq = mp_irqs + idx;
+ struct mpc_intsrc *irq = mp_irqs + idx;
/* Do we already have a mapping for this ISA IRQ? */
- if (irq->mp_srcbus == MP_ISA_BUS
- && irq->mp_srcbusirq == i)
+ if (irq->srcbus == MP_ISA_BUS && irq->srcbusirq == i)
break;
/* Do we already have a mapping for this IOAPIC pin */
- if (irq->mp_dstapic == dstapic &&
- irq->mp_dstirq == i)
+ if (irq->dstapic == dstapic && irq->dstirq == i)
break;
}
@@ -1113,13 +1111,13 @@
continue; /* IRQ already used */
}
- mp_irq.mp_type = MP_INTSRC;
- mp_irq.mp_irqflag = 0; /* Conforming */
- mp_irq.mp_srcbus = MP_ISA_BUS;
- mp_irq.mp_dstapic = dstapic;
- mp_irq.mp_irqtype = mp_INT;
- mp_irq.mp_srcbusirq = i; /* Identity mapped */
- mp_irq.mp_dstirq = i;
+ mp_irq.type = MP_INTSRC;
+ mp_irq.irqflag = 0; /* Conforming */
+ mp_irq.srcbus = MP_ISA_BUS;
+ mp_irq.dstapic = dstapic;
+ mp_irq.irqtype = mp_INT;
+ mp_irq.srcbusirq = i; /* Identity mapped */
+ mp_irq.dstirq = i;
save_mp_irq(&mp_irq);
}
@@ -1230,22 +1228,22 @@
u32 gsi, int triggering, int polarity)
{
#ifdef CONFIG_X86_MPPARSE
- struct mp_config_intsrc mp_irq;
+ struct mpc_intsrc mp_irq;
int ioapic;
if (!acpi_ioapic)
return 0;
/* print the entry should happen on mptable identically */
- mp_irq.mp_type = MP_INTSRC;
- mp_irq.mp_irqtype = mp_INT;
- mp_irq.mp_irqflag = (triggering == ACPI_EDGE_SENSITIVE ? 4 : 0x0c) |
+ mp_irq.type = MP_INTSRC;
+ mp_irq.irqtype = mp_INT;
+ mp_irq.irqflag = (triggering == ACPI_EDGE_SENSITIVE ? 4 : 0x0c) |
(polarity == ACPI_ACTIVE_HIGH ? 1 : 3);
- mp_irq.mp_srcbus = number;
- mp_irq.mp_srcbusirq = (((devfn >> 3) & 0x1f) << 2) | ((pin - 1) & 3);
+ mp_irq.srcbus = number;
+ mp_irq.srcbusirq = (((devfn >> 3) & 0x1f) << 2) | ((pin - 1) & 3);
ioapic = mp_find_ioapic(gsi);
- mp_irq.mp_dstapic = mp_ioapic_routing[ioapic].apic_id;
- mp_irq.mp_dstirq = gsi - mp_ioapic_routing[ioapic].gsi_base;
+ mp_irq.dstapic = mp_ioapic_routing[ioapic].apic_id;
+ mp_irq.dstirq = gsi - mp_ioapic_routing[ioapic].gsi_base;
save_mp_irq(&mp_irq);
#endif
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 707c1f6..7c243a2 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -101,6 +101,7 @@
stack_start.sp = temp_stack + sizeof(temp_stack);
early_gdt_descr.address =
(unsigned long)get_cpu_gdt_table(smp_processor_id());
+ initial_gs = per_cpu_offset(smp_processor_id());
#endif
initial_code = (unsigned long)wakeup_long64;
saved_magic = 0x123456789abcdef0;
@@ -156,11 +157,11 @@
#ifdef CONFIG_HIBERNATION
if (strncmp(str, "s4_nohwsig", 10) == 0)
acpi_no_s4_hw_signature();
+ if (strncmp(str, "s4_nonvs", 8) == 0)
+ acpi_s4_no_nvs();
#endif
if (strncmp(str, "old_ordering", 12) == 0)
acpi_old_suspend_ordering();
- if (strncmp(str, "s4_nonvs", 8) == 0)
- acpi_s4_no_nvs();
str = strchr(str, ',');
if (str != NULL)
str += strspn(str, ", \t");
diff --git a/arch/x86/kernel/apic.c b/arch/x86/kernel/apic.c
index 115449f..383d827 100644
--- a/arch/x86/kernel/apic.c
+++ b/arch/x86/kernel/apic.c
@@ -60,6 +60,24 @@
# error SPURIOUS_APIC_VECTOR definition error
#endif
+unsigned int num_processors;
+unsigned disabled_cpus __cpuinitdata;
+/* Processor that is doing the boot up */
+unsigned int boot_cpu_physical_apicid = -1U;
+EXPORT_SYMBOL(boot_cpu_physical_apicid);
+unsigned int max_physical_apicid;
+
+/* Bitmask of physically existing CPUs */
+physid_mask_t phys_cpu_present_map;
+
+/*
+ * Map cpu index to physical APIC ID
+ */
+DEFINE_EARLY_PER_CPU(u16, x86_cpu_to_apicid, BAD_APICID);
+DEFINE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid, BAD_APICID);
+EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid);
+EXPORT_EARLY_PER_CPU_SYMBOL(x86_bios_cpu_apicid);
+
#ifdef CONFIG_X86_32
/*
* Knob to control our willingness to enable the local APIC.
@@ -1130,6 +1148,13 @@
unsigned int value;
int i, j;
+ if (disable_apic) {
+#ifdef CONFIG_X86_IO_APIC
+ disable_ioapic_setup();
+#endif
+ return;
+ }
+
#ifdef CONFIG_X86_32
/* Pound the ESR really hard over the head with a big hammer - mbligh */
if (lapic_is_integrated() && esr_disable) {
@@ -1570,11 +1595,11 @@
int __init APIC_init_uniprocessor(void)
{
-#ifdef CONFIG_X86_64
if (disable_apic) {
pr_info("Apic disabled\n");
return -1;
}
+#ifdef CONFIG_X86_64
if (!cpu_has_apic) {
disable_apic = 1;
pr_info("Apic disabled by BIOS\n");
@@ -1877,17 +1902,8 @@
#endif
#if defined(CONFIG_X86_SMP) || defined(CONFIG_X86_64)
- /* are we being called early in kernel startup? */
- if (early_per_cpu_ptr(x86_cpu_to_apicid)) {
- u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid);
- u16 *bios_cpu_apicid = early_per_cpu_ptr(x86_bios_cpu_apicid);
-
- cpu_to_apicid[cpu] = apicid;
- bios_cpu_apicid[cpu] = apicid;
- } else {
- per_cpu(x86_cpu_to_apicid, cpu) = apicid;
- per_cpu(x86_bios_cpu_apicid, cpu) = apicid;
- }
+ early_per_cpu(x86_cpu_to_apicid, cpu) = apicid;
+ early_per_cpu(x86_bios_cpu_apicid, cpu) = apicid;
#endif
set_cpu_possible(cpu, true);
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 1d41d3f..8793ab3 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -11,7 +11,6 @@
#include <linux/hardirq.h>
#include <linux/suspend.h>
#include <linux/kbuild.h>
-#include <asm/pda.h>
#include <asm/processor.h>
#include <asm/segment.h>
#include <asm/thread_info.h>
@@ -48,16 +47,6 @@
#endif
BLANK();
#undef ENTRY
-#define ENTRY(entry) DEFINE(pda_ ## entry, offsetof(struct x8664_pda, entry))
- ENTRY(kernelstack);
- ENTRY(oldrsp);
- ENTRY(pcurrent);
- ENTRY(irqcount);
- ENTRY(cpunumber);
- ENTRY(irqstackptr);
- ENTRY(data_offset);
- BLANK();
-#undef ENTRY
#ifdef CONFIG_PARAVIRT
BLANK();
OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 83492b1..41b0de6 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -21,14 +21,16 @@
#include <asm/asm.h>
#include <asm/numa.h>
#include <asm/smp.h>
+#include <asm/cpu.h>
+#include <asm/cpumask.h>
#ifdef CONFIG_X86_LOCAL_APIC
#include <asm/mpspec.h>
#include <asm/apic.h>
#include <mach_apic.h>
#include <asm/genapic.h>
+#include <asm/uv/uv.h>
#endif
-#include <asm/pda.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
#include <asm/desc.h>
@@ -50,6 +52,15 @@
/* representing cpus for which sibling maps can be computed */
cpumask_var_t cpu_sibling_setup_mask;
+/* correctly size the local cpu masks */
+void __init setup_cpu_local_masks(void)
+{
+ alloc_bootmem_cpumask_var(&cpu_initialized_mask);
+ alloc_bootmem_cpumask_var(&cpu_callin_mask);
+ alloc_bootmem_cpumask_var(&cpu_callout_mask);
+ alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask);
+}
+
#else /* CONFIG_X86_32 */
cpumask_t cpu_callin_map;
@@ -62,23 +73,23 @@
static struct cpu_dev *this_cpu __cpuinitdata;
+DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
#ifdef CONFIG_X86_64
-/* We need valid kernel segments for data and code in long mode too
- * IRET will check the segment types kkeil 2000/10/28
- * Also sysret mandates a special GDT layout
- */
-/* The TLS descriptors are currently at a different place compared to i386.
- Hopefully nobody expects them at a fixed place (Wine?) */
-DEFINE_PER_CPU(struct gdt_page, gdt_page) = { .gdt = {
+ /*
+ * We need valid kernel segments for data and code in long mode too
+ * IRET will check the segment types kkeil 2000/10/28
+ * Also sysret mandates a special GDT layout
+ *
+ * The TLS descriptors are currently at a different place compared to i386.
+ * Hopefully nobody expects them at a fixed place (Wine?)
+ */
[GDT_ENTRY_KERNEL32_CS] = { { { 0x0000ffff, 0x00cf9b00 } } },
[GDT_ENTRY_KERNEL_CS] = { { { 0x0000ffff, 0x00af9b00 } } },
[GDT_ENTRY_KERNEL_DS] = { { { 0x0000ffff, 0x00cf9300 } } },
[GDT_ENTRY_DEFAULT_USER32_CS] = { { { 0x0000ffff, 0x00cffb00 } } },
[GDT_ENTRY_DEFAULT_USER_DS] = { { { 0x0000ffff, 0x00cff300 } } },
[GDT_ENTRY_DEFAULT_USER_CS] = { { { 0x0000ffff, 0x00affb00 } } },
-} };
#else
-DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
[GDT_ENTRY_KERNEL_CS] = { { { 0x0000ffff, 0x00cf9a00 } } },
[GDT_ENTRY_KERNEL_DS] = { { { 0x0000ffff, 0x00cf9200 } } },
[GDT_ENTRY_DEFAULT_USER_CS] = { { { 0x0000ffff, 0x00cffa00 } } },
@@ -110,9 +121,9 @@
[GDT_ENTRY_APMBIOS_BASE+2] = { { { 0x0000ffff, 0x00409200 } } },
[GDT_ENTRY_ESPFIX_SS] = { { { 0x00000000, 0x00c09200 } } },
- [GDT_ENTRY_PERCPU] = { { { 0x00000000, 0x00000000 } } },
-} };
+ [GDT_ENTRY_PERCPU] = { { { 0x0000ffff, 0x00cf9200 } } },
#endif
+} };
EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
#ifdef CONFIG_X86_32
@@ -242,18 +253,28 @@
__u32 cleared_cpu_caps[NCAPINTS] __cpuinitdata;
+void load_percpu_segment(int cpu)
+{
+#ifdef CONFIG_X86_32
+ loadsegment(fs, __KERNEL_PERCPU);
+#else
+ loadsegment(gs, 0);
+ wrmsrl(MSR_GS_BASE, (unsigned long)per_cpu(irq_stack_union.gs_base, cpu));
+#endif
+}
+
/* Current gdt points %fs at the "master" per-cpu area: after this,
* it's on the real one. */
-void switch_to_new_gdt(void)
+void switch_to_new_gdt(int cpu)
{
struct desc_ptr gdt_descr;
- gdt_descr.address = (long)get_cpu_gdt_table(smp_processor_id());
+ gdt_descr.address = (long)get_cpu_gdt_table(cpu);
gdt_descr.size = GDT_SIZE - 1;
load_gdt(&gdt_descr);
-#ifdef CONFIG_X86_32
- asm("mov %0, %%fs" : : "r" (__KERNEL_PERCPU) : "memory");
-#endif
+ /* Reload the per-cpu base */
+
+ load_percpu_segment(cpu);
}
static struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {};
@@ -877,54 +898,22 @@
__setup("clearcpuid=", setup_disablecpuid);
#ifdef CONFIG_X86_64
-struct x8664_pda **_cpu_pda __read_mostly;
-EXPORT_SYMBOL(_cpu_pda);
-
struct desc_ptr idt_descr = { 256 * 16 - 1, (unsigned long) idt_table };
-static char boot_cpu_stack[IRQSTACKSIZE] __page_aligned_bss;
+DEFINE_PER_CPU_FIRST(union irq_stack_union,
+ irq_stack_union) __aligned(PAGE_SIZE);
+DEFINE_PER_CPU(char *, irq_stack_ptr) =
+ init_per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE - 64;
-void __cpuinit pda_init(int cpu)
-{
- struct x8664_pda *pda = cpu_pda(cpu);
+DEFINE_PER_CPU(unsigned long, kernel_stack) =
+ (unsigned long)&init_thread_union - KERNEL_STACK_OFFSET + THREAD_SIZE;
+EXPORT_PER_CPU_SYMBOL(kernel_stack);
- /* Setup up data that may be needed in __get_free_pages early */
- loadsegment(fs, 0);
- loadsegment(gs, 0);
- /* Memory clobbers used to order PDA accessed */
- mb();
- wrmsrl(MSR_GS_BASE, pda);
- mb();
+DEFINE_PER_CPU(unsigned int, irq_count) = -1;
- pda->cpunumber = cpu;
- pda->irqcount = -1;
- pda->kernelstack = (unsigned long)stack_thread_info() -
- PDA_STACKOFFSET + THREAD_SIZE;
- pda->active_mm = &init_mm;
- pda->mmu_state = 0;
-
- if (cpu == 0) {
- /* others are initialized in smpboot.c */
- pda->pcurrent = &init_task;
- pda->irqstackptr = boot_cpu_stack;
- pda->irqstackptr += IRQSTACKSIZE - 64;
- } else {
- if (!pda->irqstackptr) {
- pda->irqstackptr = (char *)
- __get_free_pages(GFP_ATOMIC, IRQSTACK_ORDER);
- if (!pda->irqstackptr)
- panic("cannot allocate irqstack for cpu %d",
- cpu);
- pda->irqstackptr += IRQSTACKSIZE - 64;
- }
-
- if (pda->nodenumber == 0 && cpu_to_node(cpu) != NUMA_NO_NODE)
- pda->nodenumber = cpu_to_node(cpu);
- }
-}
-
-static char boot_exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ +
- DEBUG_STKSZ] __page_aligned_bss;
+static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
+ [(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ])
+ __aligned(PAGE_SIZE);
extern asmlinkage void ignore_sysret(void);
@@ -982,15 +971,14 @@
struct tss_struct *t = &per_cpu(init_tss, cpu);
struct orig_ist *orig_ist = &per_cpu(orig_ist, cpu);
unsigned long v;
- char *estacks = NULL;
struct task_struct *me;
int i;
- /* CPU 0 is initialised in head64.c */
- if (cpu != 0)
- pda_init(cpu);
- else
- estacks = boot_exception_stacks;
+#ifdef CONFIG_NUMA
+ if (cpu != 0 && percpu_read(node_number) == 0 &&
+ cpu_to_node(cpu) != NUMA_NO_NODE)
+ percpu_write(node_number, cpu_to_node(cpu));
+#endif
me = current;
@@ -1006,7 +994,9 @@
* and set up the GDT descriptor:
*/
- switch_to_new_gdt();
+ switch_to_new_gdt(cpu);
+ loadsegment(fs, 0);
+
load_idt((const struct desc_ptr *)&idt_descr);
memset(me->thread.tls_array, 0, GDT_ENTRY_TLS_ENTRIES * 8);
@@ -1024,18 +1014,13 @@
* set up and load the per-CPU TSS
*/
if (!orig_ist->ist[0]) {
- static const unsigned int order[N_EXCEPTION_STACKS] = {
- [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STACK_ORDER,
- [DEBUG_STACK - 1] = DEBUG_STACK_ORDER
+ static const unsigned int sizes[N_EXCEPTION_STACKS] = {
+ [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ,
+ [DEBUG_STACK - 1] = DEBUG_STKSZ
};
+ char *estacks = per_cpu(exception_stacks, cpu);
for (v = 0; v < N_EXCEPTION_STACKS; v++) {
- if (cpu) {
- estacks = (char *)__get_free_pages(GFP_ATOMIC, order[v]);
- if (!estacks)
- panic("Cannot allocate exception "
- "stack %ld %d\n", v, cpu);
- }
- estacks += PAGE_SIZE << order[v];
+ estacks += sizes[v];
orig_ist->ist[v] = t->x86_tss.ist[v] =
(unsigned long)estacks;
}
@@ -1114,7 +1099,7 @@
clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
load_idt(&idt_descr);
- switch_to_new_gdt();
+ switch_to_new_gdt(cpu);
/*
* Set up and load the per-CPU TSS and LDT
diff --git a/arch/x86/kernel/cpu/cpufreq/Kconfig b/arch/x86/kernel/cpu/cpufreq/Kconfig
index efae3b2..65792c2 100644
--- a/arch/x86/kernel/cpu/cpufreq/Kconfig
+++ b/arch/x86/kernel/cpu/cpufreq/Kconfig
@@ -245,17 +245,6 @@
comment "shared options"
-config X86_ACPI_CPUFREQ_PROC_INTF
- bool "/proc/acpi/processor/../performance interface (deprecated)"
- depends on PROC_FS
- depends on X86_ACPI_CPUFREQ || X86_POWERNOW_K7_ACPI || X86_POWERNOW_K8_ACPI
- help
- This enables the deprecated /proc/acpi/processor/../performance
- interface. While it is helpful for debugging, the generic,
- cross-architecture cpufreq interfaces should be used.
-
- If in doubt, say N.
-
config X86_SPEEDSTEP_LIB
tristate
default (X86_SPEEDSTEP_ICH || X86_SPEEDSTEP_SMI || X86_P4_CLOCKMOD)
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index da299eb..7293508 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -147,7 +147,16 @@
union _cpuid4_leaf_ecx ecx;
unsigned long size;
unsigned long can_disable;
- cpumask_t shared_cpu_map; /* future?: only cpus/node is needed */
+ DECLARE_BITMAP(shared_cpu_map, NR_CPUS);
+};
+
+/* subset of above _cpuid4_info w/o shared_cpu_map */
+struct _cpuid4_info_regs {
+ union _cpuid4_leaf_eax eax;
+ union _cpuid4_leaf_ebx ebx;
+ union _cpuid4_leaf_ecx ecx;
+ unsigned long size;
+ unsigned long can_disable;
};
#ifdef CONFIG_PCI
@@ -278,7 +287,7 @@
}
static void __cpuinit
-amd_check_l3_disable(int index, struct _cpuid4_info *this_leaf)
+amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf)
{
if (index < 3)
return;
@@ -286,7 +295,8 @@
}
static int
-__cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf)
+__cpuinit cpuid4_cache_lookup_regs(int index,
+ struct _cpuid4_info_regs *this_leaf)
{
union _cpuid4_leaf_eax eax;
union _cpuid4_leaf_ebx ebx;
@@ -314,6 +324,15 @@
return 0;
}
+static int
+__cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf)
+{
+ struct _cpuid4_info_regs *leaf_regs =
+ (struct _cpuid4_info_regs *)this_leaf;
+
+ return cpuid4_cache_lookup_regs(index, leaf_regs);
+}
+
static int __cpuinit find_num_cache_leaves(void)
{
unsigned int eax, ebx, ecx, edx;
@@ -353,11 +372,10 @@
* parameters cpuid leaf to find the cache details
*/
for (i = 0; i < num_cache_leaves; i++) {
- struct _cpuid4_info this_leaf;
-
+ struct _cpuid4_info_regs this_leaf;
int retval;
- retval = cpuid4_cache_lookup(i, &this_leaf);
+ retval = cpuid4_cache_lookup_regs(i, &this_leaf);
if (retval >= 0) {
switch(this_leaf.eax.split.level) {
case 1:
@@ -506,17 +524,20 @@
num_threads_sharing = 1 + this_leaf->eax.split.num_threads_sharing;
if (num_threads_sharing == 1)
- cpu_set(cpu, this_leaf->shared_cpu_map);
+ cpumask_set_cpu(cpu, to_cpumask(this_leaf->shared_cpu_map));
else {
index_msb = get_count_order(num_threads_sharing);
for_each_online_cpu(i) {
if (cpu_data(i).apicid >> index_msb ==
c->apicid >> index_msb) {
- cpu_set(i, this_leaf->shared_cpu_map);
+ cpumask_set_cpu(i,
+ to_cpumask(this_leaf->shared_cpu_map));
if (i != cpu && per_cpu(cpuid4_info, i)) {
- sibling_leaf = CPUID4_INFO_IDX(i, index);
- cpu_set(cpu, sibling_leaf->shared_cpu_map);
+ sibling_leaf =
+ CPUID4_INFO_IDX(i, index);
+ cpumask_set_cpu(cpu, to_cpumask(
+ sibling_leaf->shared_cpu_map));
}
}
}
@@ -528,9 +549,10 @@
int sibling;
this_leaf = CPUID4_INFO_IDX(cpu, index);
- for_each_cpu_mask_nr(sibling, this_leaf->shared_cpu_map) {
+ for_each_cpu(sibling, to_cpumask(this_leaf->shared_cpu_map)) {
sibling_leaf = CPUID4_INFO_IDX(sibling, index);
- cpu_clear(cpu, sibling_leaf->shared_cpu_map);
+ cpumask_clear_cpu(cpu,
+ to_cpumask(sibling_leaf->shared_cpu_map));
}
}
#else
@@ -635,8 +657,9 @@
int n = 0;
if (len > 1) {
- cpumask_t *mask = &this_leaf->shared_cpu_map;
+ const struct cpumask *mask;
+ mask = to_cpumask(this_leaf->shared_cpu_map);
n = type?
cpulist_scnprintf(buf, len-2, mask) :
cpumask_scnprintf(buf, len-2, mask);
@@ -699,7 +722,8 @@
static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf)
{
- int node = cpu_to_node(first_cpu(this_leaf->shared_cpu_map));
+ const struct cpumask *mask = to_cpumask(this_leaf->shared_cpu_map);
+ int node = cpu_to_node(cpumask_first(mask));
struct pci_dev *dev = NULL;
ssize_t ret = 0;
int i;
@@ -733,7 +757,8 @@
store_cache_disable(struct _cpuid4_info *this_leaf, const char *buf,
size_t count)
{
- int node = cpu_to_node(first_cpu(this_leaf->shared_cpu_map));
+ const struct cpumask *mask = to_cpumask(this_leaf->shared_cpu_map);
+ int node = cpu_to_node(cpumask_first(mask));
struct pci_dev *dev = NULL;
unsigned int ret, index, val;
@@ -878,7 +903,7 @@
return -ENOMEM;
}
-static cpumask_t cache_dev_map = CPU_MASK_NONE;
+static DECLARE_BITMAP(cache_dev_map, NR_CPUS);
/* Add/Remove cache interface for CPU device */
static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
@@ -918,7 +943,7 @@
}
kobject_uevent(&(this_object->kobj), KOBJ_ADD);
}
- cpu_set(cpu, cache_dev_map);
+ cpumask_set_cpu(cpu, to_cpumask(cache_dev_map));
kobject_uevent(per_cpu(cache_kobject, cpu), KOBJ_ADD);
return 0;
@@ -931,9 +956,9 @@
if (per_cpu(cpuid4_info, cpu) == NULL)
return;
- if (!cpu_isset(cpu, cache_dev_map))
+ if (!cpumask_test_cpu(cpu, to_cpumask(cache_dev_map)))
return;
- cpu_clear(cpu, cache_dev_map);
+ cpumask_clear_cpu(cpu, to_cpumask(cache_dev_map));
for (i = 0; i < num_cache_leaves; i++)
kobject_put(&(INDEX_KOBJECT_PTR(cpu,i)->kobj));
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
index 8ae8c4f..4772e91 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
@@ -67,7 +67,7 @@
struct threshold_bank {
struct kobject *kobj;
struct threshold_block *blocks;
- cpumask_t cpus;
+ cpumask_var_t cpus;
};
static DEFINE_PER_CPU(struct threshold_bank *, threshold_banks[NR_BANKS]);
@@ -481,7 +481,7 @@
#ifdef CONFIG_SMP
if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) { /* symlink */
- i = first_cpu(per_cpu(cpu_core_map, cpu));
+ i = cpumask_first(&per_cpu(cpu_core_map, cpu));
/* first core not up yet */
if (cpu_data(i).cpu_core_id)
@@ -501,7 +501,7 @@
if (err)
goto out;
- b->cpus = per_cpu(cpu_core_map, cpu);
+ cpumask_copy(b->cpus, &per_cpu(cpu_core_map, cpu));
per_cpu(threshold_banks, cpu)[bank] = b;
goto out;
}
@@ -512,15 +512,20 @@
err = -ENOMEM;
goto out;
}
+ if (!alloc_cpumask_var(&b->cpus, GFP_KERNEL)) {
+ kfree(b);
+ err = -ENOMEM;
+ goto out;
+ }
b->kobj = kobject_create_and_add(name, &per_cpu(device_mce, cpu).kobj);
if (!b->kobj)
goto out_free;
#ifndef CONFIG_SMP
- b->cpus = CPU_MASK_ALL;
+ cpumask_setall(b->cpus);
#else
- b->cpus = per_cpu(cpu_core_map, cpu);
+ cpumask_copy(b->cpus, &per_cpu(cpu_core_map, cpu));
#endif
per_cpu(threshold_banks, cpu)[bank] = b;
@@ -529,7 +534,7 @@
if (err)
goto out_free;
- for_each_cpu_mask_nr(i, b->cpus) {
+ for_each_cpu(i, b->cpus) {
if (i == cpu)
continue;
@@ -545,6 +550,7 @@
out_free:
per_cpu(threshold_banks, cpu)[bank] = NULL;
+ free_cpumask_var(b->cpus);
kfree(b);
out:
return err;
@@ -619,7 +625,7 @@
#endif
/* remove all sibling symlinks before unregistering */
- for_each_cpu_mask_nr(i, b->cpus) {
+ for_each_cpu(i, b->cpus) {
if (i == cpu)
continue;
@@ -632,6 +638,7 @@
free_out:
kobject_del(b->kobj);
kobject_put(b->kobj);
+ free_cpumask_var(b->cpus);
kfree(b);
per_cpu(threshold_banks, cpu)[bank] = NULL;
}
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
index 4b48f25..5e8c79e 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
@@ -7,6 +7,7 @@
#include <linux/interrupt.h>
#include <linux/percpu.h>
#include <asm/processor.h>
+#include <asm/apic.h>
#include <asm/msr.h>
#include <asm/mce.h>
#include <asm/hw_irq.h>
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index c689d19..11b93ca 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -24,7 +24,7 @@
#include <asm/apic.h>
#include <asm/hpet.h>
#include <linux/kdebug.h>
-#include <asm/smp.h>
+#include <asm/cpu.h>
#include <asm/reboot.h>
#include <asm/virtext.h>
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index c302d07..d35db59 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -106,7 +106,8 @@
const struct stacktrace_ops *ops, void *data)
{
const unsigned cpu = get_cpu();
- unsigned long *irqstack_end = (unsigned long *)cpu_pda(cpu)->irqstackptr;
+ unsigned long *irq_stack_end =
+ (unsigned long *)per_cpu(irq_stack_ptr, cpu);
unsigned used = 0;
struct thread_info *tinfo;
int graph = 0;
@@ -160,23 +161,23 @@
stack = (unsigned long *) estack_end[-2];
continue;
}
- if (irqstack_end) {
- unsigned long *irqstack;
- irqstack = irqstack_end -
- (IRQSTACKSIZE - 64) / sizeof(*irqstack);
+ if (irq_stack_end) {
+ unsigned long *irq_stack;
+ irq_stack = irq_stack_end -
+ (IRQ_STACK_SIZE - 64) / sizeof(*irq_stack);
- if (stack >= irqstack && stack < irqstack_end) {
+ if (stack >= irq_stack && stack < irq_stack_end) {
if (ops->stack(data, "IRQ") < 0)
break;
bp = print_context_stack(tinfo, stack, bp,
- ops, data, irqstack_end, &graph);
+ ops, data, irq_stack_end, &graph);
/*
* We link to the next stack (which would be
* the process stack normally) the last
* pointer (index -1 to end) in the IRQ stack:
*/
- stack = (unsigned long *) (irqstack_end[-1]);
- irqstack_end = NULL;
+ stack = (unsigned long *) (irq_stack_end[-1]);
+ irq_stack_end = NULL;
ops->stack(data, "EOI");
continue;
}
@@ -199,10 +200,10 @@
unsigned long *stack;
int i;
const int cpu = smp_processor_id();
- unsigned long *irqstack_end =
- (unsigned long *) (cpu_pda(cpu)->irqstackptr);
- unsigned long *irqstack =
- (unsigned long *) (cpu_pda(cpu)->irqstackptr - IRQSTACKSIZE);
+ unsigned long *irq_stack_end =
+ (unsigned long *)(per_cpu(irq_stack_ptr, cpu));
+ unsigned long *irq_stack =
+ (unsigned long *)(per_cpu(irq_stack_ptr, cpu) - IRQ_STACK_SIZE);
/*
* debugging aid: "show_stack(NULL, NULL);" prints the
@@ -218,9 +219,9 @@
stack = sp;
for (i = 0; i < kstack_depth_to_print; i++) {
- if (stack >= irqstack && stack <= irqstack_end) {
- if (stack == irqstack_end) {
- stack = (unsigned long *) (irqstack_end[-1]);
+ if (stack >= irq_stack && stack <= irq_stack_end) {
+ if (stack == irq_stack_end) {
+ stack = (unsigned long *) (irq_stack_end[-1]);
printk(" <EOI> ");
}
} else {
@@ -241,7 +242,7 @@
int i;
unsigned long sp;
const int cpu = smp_processor_id();
- struct task_struct *cur = cpu_pda(cpu)->pcurrent;
+ struct task_struct *cur = current;
sp = regs->sp;
printk("CPU %d ", cpu);
diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c
index 1119d24..b205272 100644
--- a/arch/x86/kernel/efi.c
+++ b/arch/x86/kernel/efi.c
@@ -366,10 +366,12 @@
SMBIOS_TABLE_GUID)) {
efi.smbios = config_tables[i].table;
printk(" SMBIOS=0x%lx ", config_tables[i].table);
+#ifdef CONFIG_X86_UV
} else if (!efi_guidcmp(config_tables[i].guid,
UV_SYSTEM_TABLE_GUID)) {
efi.uv_systab = config_tables[i].table;
printk(" UVsystab=0x%lx ", config_tables[i].table);
+#endif
} else if (!efi_guidcmp(config_tables[i].guid,
HCDP_TABLE_GUID)) {
efi.hcdp = config_tables[i].table;
diff --git a/arch/x86/kernel/efi_64.c b/arch/x86/kernel/efi_64.c
index 652c528..a4ee291 100644
--- a/arch/x86/kernel/efi_64.c
+++ b/arch/x86/kernel/efi_64.c
@@ -36,6 +36,7 @@
#include <asm/proto.h>
#include <asm/efi.h>
#include <asm/cacheflush.h>
+#include <asm/fixmap.h>
static pgd_t save_pgd __initdata;
static unsigned long efi_flags __initdata;
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 4646902..a0b91aa 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -672,7 +672,7 @@
ENDPROC(common_interrupt)
CFI_ENDPROC
-#define BUILD_INTERRUPT(name, nr) \
+#define BUILD_INTERRUPT3(name, nr, fn) \
ENTRY(name) \
RING0_INT_FRAME; \
pushl $~(nr); \
@@ -680,11 +680,13 @@
SAVE_ALL; \
TRACE_IRQS_OFF \
movl %esp,%eax; \
- call smp_##name; \
+ call fn; \
jmp ret_from_intr; \
CFI_ENDPROC; \
ENDPROC(name)
+#define BUILD_INTERRUPT(name, nr) BUILD_INTERRUPT3(name, nr, smp_##name)
+
/* The include is where all of the SMP etc. interrupts come from */
#include "entry_arch.h"
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index a134621..586bed6 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -52,6 +52,7 @@
#include <asm/irqflags.h>
#include <asm/paravirt.h>
#include <asm/ftrace.h>
+#include <asm/percpu.h>
/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
#include <linux/elf-em.h>
@@ -209,7 +210,7 @@
/* %rsp:at FRAMEEND */
.macro FIXUP_TOP_OF_STACK tmp offset=0
- movq %gs:pda_oldrsp,\tmp
+ movq PER_CPU_VAR(old_rsp),\tmp
movq \tmp,RSP+\offset(%rsp)
movq $__USER_DS,SS+\offset(%rsp)
movq $__USER_CS,CS+\offset(%rsp)
@@ -220,7 +221,7 @@
.macro RESTORE_TOP_OF_STACK tmp offset=0
movq RSP+\offset(%rsp),\tmp
- movq \tmp,%gs:pda_oldrsp
+ movq \tmp,PER_CPU_VAR(old_rsp)
movq EFLAGS+\offset(%rsp),\tmp
movq \tmp,R11+\offset(%rsp)
.endm
@@ -336,15 +337,15 @@
je 1f
SWAPGS
/*
- * irqcount is used to check if a CPU is already on an interrupt stack
+ * irq_count is used to check if a CPU is already on an interrupt stack
* or not. While this is essentially redundant with preempt_count it is
* a little cheaper to use a separate counter in the PDA (short of
* moving irq_enter into assembly, which would be too much work)
*/
-1: incl %gs:pda_irqcount
+1: incl PER_CPU_VAR(irq_count)
jne 2f
popq_cfi %rax /* move return address... */
- mov %gs:pda_irqstackptr,%rsp
+ mov PER_CPU_VAR(irq_stack_ptr),%rsp
EMPTY_FRAME 0
pushq_cfi %rbp /* backlink for unwinder */
pushq_cfi %rax /* ... to the new stack */
@@ -468,7 +469,7 @@
ENTRY(system_call)
CFI_STARTPROC simple
CFI_SIGNAL_FRAME
- CFI_DEF_CFA rsp,PDA_STACKOFFSET
+ CFI_DEF_CFA rsp,KERNEL_STACK_OFFSET
CFI_REGISTER rip,rcx
/*CFI_REGISTER rflags,r11*/
SWAPGS_UNSAFE_STACK
@@ -479,8 +480,8 @@
*/
ENTRY(system_call_after_swapgs)
- movq %rsp,%gs:pda_oldrsp
- movq %gs:pda_kernelstack,%rsp
+ movq %rsp,PER_CPU_VAR(old_rsp)
+ movq PER_CPU_VAR(kernel_stack),%rsp
/*
* No need to follow this irqs off/on section - it's straight
* and short:
@@ -523,7 +524,7 @@
CFI_REGISTER rip,rcx
RESTORE_ARGS 0,-ARG_SKIP,1
/*CFI_REGISTER rflags,r11*/
- movq %gs:pda_oldrsp, %rsp
+ movq PER_CPU_VAR(old_rsp), %rsp
USERGS_SYSRET64
CFI_RESTORE_STATE
@@ -833,11 +834,11 @@
XCPT_FRAME
addq $-0x80,(%rsp) /* Adjust vector to [-256,-1] range */
interrupt do_IRQ
- /* 0(%rsp): oldrsp-ARGOFFSET */
+ /* 0(%rsp): old_rsp-ARGOFFSET */
ret_from_intr:
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
- decl %gs:pda_irqcount
+ decl PER_CPU_VAR(irq_count)
leaveq
CFI_DEF_CFA_REGISTER rsp
CFI_ADJUST_CFA_OFFSET -8
@@ -982,8 +983,10 @@
irq_move_cleanup_interrupt smp_irq_move_cleanup_interrupt
#endif
+#ifdef CONFIG_X86_UV
apicinterrupt UV_BAU_MESSAGE \
uv_bau_message_intr1 uv_bau_message_interrupt
+#endif
apicinterrupt LOCAL_TIMER_VECTOR \
apic_timer_interrupt smp_apic_timer_interrupt
@@ -1073,10 +1076,10 @@
TRACE_IRQS_OFF
movq %rsp,%rdi /* pt_regs pointer */
xorl %esi,%esi /* no error code */
- movq %gs:pda_data_offset, %rbp
- subq $EXCEPTION_STKSZ, per_cpu__init_tss + TSS_ist + (\ist - 1) * 8(%rbp)
+ PER_CPU(init_tss, %rbp)
+ subq $EXCEPTION_STKSZ, TSS_ist + (\ist - 1) * 8(%rbp)
call \do_sym
- addq $EXCEPTION_STKSZ, per_cpu__init_tss + TSS_ist + (\ist - 1) * 8(%rbp)
+ addq $EXCEPTION_STKSZ, TSS_ist + (\ist - 1) * 8(%rbp)
jmp paranoid_exit /* %ebx: no swapgs flag */
CFI_ENDPROC
END(\sym)
@@ -1138,7 +1141,7 @@
CFI_STARTPROC
pushf
CFI_ADJUST_CFA_OFFSET 8
- DISABLE_INTERRUPTS(CLBR_ANY | ~(CLBR_RDI))
+ DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI)
SWAPGS
gs_change:
movl %edi,%gs
@@ -1260,14 +1263,14 @@
CFI_REL_OFFSET rbp,0
mov %rsp,%rbp
CFI_DEF_CFA_REGISTER rbp
- incl %gs:pda_irqcount
- cmove %gs:pda_irqstackptr,%rsp
+ incl PER_CPU_VAR(irq_count)
+ cmove PER_CPU_VAR(irq_stack_ptr),%rsp
push %rbp # backlink for old unwinder
call __do_softirq
leaveq
CFI_DEF_CFA_REGISTER rsp
CFI_ADJUST_CFA_OFFSET -8
- decl %gs:pda_irqcount
+ decl PER_CPU_VAR(irq_count)
ret
CFI_ENDPROC
END(call_softirq)
@@ -1297,15 +1300,15 @@
movq %rdi, %rsp # we don't return, adjust the stack frame
CFI_ENDPROC
DEFAULT_FRAME
-11: incl %gs:pda_irqcount
+11: incl PER_CPU_VAR(irq_count)
movq %rsp,%rbp
CFI_DEF_CFA_REGISTER rbp
- cmovzq %gs:pda_irqstackptr,%rsp
+ cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp
pushq %rbp # backlink for old unwinder
call xen_evtchn_do_upcall
popq %rsp
CFI_DEF_CFA_REGISTER rsp
- decl %gs:pda_irqcount
+ decl PER_CPU_VAR(irq_count)
jmp error_exit
CFI_ENDPROC
END(do_hypervisor_callback)
diff --git a/arch/x86/kernel/genapic_64.c b/arch/x86/kernel/genapic_64.c
index 2bced78..e656c27 100644
--- a/arch/x86/kernel/genapic_64.c
+++ b/arch/x86/kernel/genapic_64.c
@@ -32,7 +32,9 @@
struct genapic __read_mostly *genapic = &apic_flat;
static struct genapic *apic_probe[] __initdata = {
+#ifdef CONFIG_X86_UV
&apic_x2apic_uv_x,
+#endif
&apic_x2apic_phys,
&apic_x2apic_cluster,
&apic_physflat,
diff --git a/arch/x86/kernel/genx2apic_uv_x.c b/arch/x86/kernel/genx2apic_uv_x.c
index b193e08..bfe3624 100644
--- a/arch/x86/kernel/genx2apic_uv_x.c
+++ b/arch/x86/kernel/genx2apic_uv_x.c
@@ -25,6 +25,7 @@
#include <asm/ipi.h>
#include <asm/genapic.h>
#include <asm/pgtable.h>
+#include <asm/uv/uv.h>
#include <asm/uv/uv_mmrs.h>
#include <asm/uv/uv_hub.h>
#include <asm/uv/bios.h>
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index b9a4d8c..f5b2722 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -26,27 +26,6 @@
#include <asm/bios_ebda.h>
#include <asm/trampoline.h>
-/* boot cpu pda */
-static struct x8664_pda _boot_cpu_pda;
-
-#ifdef CONFIG_SMP
-/*
- * We install an empty cpu_pda pointer table to indicate to early users
- * (numa_set_node) that the cpu_pda pointer table for cpus other than
- * the boot cpu is not yet setup.
- */
-static struct x8664_pda *__cpu_pda[NR_CPUS] __initdata;
-#else
-static struct x8664_pda *__cpu_pda[NR_CPUS] __read_mostly;
-#endif
-
-void __init x86_64_init_pda(void)
-{
- _cpu_pda = __cpu_pda;
- cpu_pda(0) = &_boot_cpu_pda;
- pda_init(0);
-}
-
static void __init zap_identity_mappings(void)
{
pgd_t *pgd = pgd_offset_k(0UL);
@@ -112,8 +91,6 @@
if (console_loglevel == 10)
early_printk("Kernel alive\n");
- x86_64_init_pda();
-
x86_64_start_reservations(real_mode_data);
}
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index e835b4e..24c0e5c 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -429,12 +429,14 @@
ljmp $(__KERNEL_CS),$1f
1: movl $(__KERNEL_DS),%eax # reload all the segment registers
movl %eax,%ss # after changing gdt.
- movl %eax,%fs # gets reset once there's real percpu
movl $(__USER_DS),%eax # DS/ES contains default USER segment
movl %eax,%ds
movl %eax,%es
+ movl $(__KERNEL_PERCPU), %eax
+ movl %eax,%fs # set this cpu's percpu
+
xorl %eax,%eax # Clear GS and LDT
movl %eax,%gs
lldt %ax
@@ -446,8 +448,6 @@
movb $1, ready
cmpb $0,%cl # the first CPU calls start_kernel
je 1f
- movl $(__KERNEL_PERCPU), %eax
- movl %eax,%fs # set this cpu's percpu
movl (stack_start), %esp
1:
#endif /* CONFIG_SMP */
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 0e275d4..2e648e3 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -19,6 +19,7 @@
#include <asm/msr.h>
#include <asm/cache.h>
#include <asm/processor-flags.h>
+#include <asm/percpu.h>
#ifdef CONFIG_PARAVIRT
#include <asm/asm-offsets.h>
@@ -226,12 +227,15 @@
movl %eax,%fs
movl %eax,%gs
- /*
- * Setup up a dummy PDA. this is just for some early bootup code
- * that does in_interrupt()
- */
+ /* Set up %gs.
+ *
+ * The base of %gs always points to the bottom of the irqstack
+ * union. If the stack protector canary is enabled, it is
+ * located at %gs:40. Note that, on SMP, the boot cpu uses
+ * init data section till per cpu areas are set up.
+ */
movl $MSR_GS_BASE,%ecx
- movq $empty_zero_page,%rax
+ movq initial_gs(%rip),%rax
movq %rax,%rdx
shrq $32,%rdx
wrmsr
@@ -257,6 +261,8 @@
.align 8
ENTRY(initial_code)
.quad x86_64_start_kernel
+ ENTRY(initial_gs)
+ .quad INIT_PER_CPU_VAR(irq_stack_union)
__FINITDATA
ENTRY(stack_start)
@@ -401,7 +407,8 @@
.globl early_gdt_descr
early_gdt_descr:
.word GDT_ENTRIES*8-1
- .quad per_cpu__gdt_page
+early_gdt_descr_base:
+ .quad INIT_PER_CPU_VAR(gdt_page)
ENTRY(phys_base)
/* This must match the first entry in level2_kernel_pgt */
diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index bc7ac4d..0480d06 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -46,6 +46,7 @@
#include <asm/idle.h>
#include <asm/io.h>
#include <asm/smp.h>
+#include <asm/cpu.h>
#include <asm/desc.h>
#include <asm/proto.h>
#include <asm/acpi.h>
@@ -82,11 +83,11 @@
int nr_ioapic_registers[MAX_IO_APICS];
/* I/O APIC entries */
-struct mp_config_ioapic mp_ioapics[MAX_IO_APICS];
+struct mpc_ioapic mp_ioapics[MAX_IO_APICS];
int nr_ioapics;
/* MP IRQ source entries */
-struct mp_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
+struct mpc_intsrc mp_irqs[MAX_IRQ_SOURCES];
/* # of MP IRQ source entries */
int mp_irq_entries;
@@ -356,7 +357,7 @@
if (!cfg->move_in_progress) {
/* it means that domain is not changed */
- if (!cpumask_intersects(&desc->affinity, mask))
+ if (!cpumask_intersects(desc->affinity, mask))
cfg->move_desc_pending = 1;
}
}
@@ -386,7 +387,7 @@
static __attribute_const__ struct io_apic __iomem *io_apic_base(int idx)
{
return (void __iomem *) __fix_to_virt(FIX_IO_APIC_BASE_0 + idx)
- + (mp_ioapics[idx].mp_apicaddr & ~PAGE_MASK);
+ + (mp_ioapics[idx].apicaddr & ~PAGE_MASK);
}
static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
@@ -579,9 +580,9 @@
if (assign_irq_vector(irq, cfg, mask))
return BAD_APICID;
- cpumask_and(&desc->affinity, cfg->domain, mask);
+ cpumask_and(desc->affinity, cfg->domain, mask);
set_extra_move_desc(desc, mask);
- return cpu_mask_to_apicid_and(&desc->affinity, cpu_online_mask);
+ return cpu_mask_to_apicid_and(desc->affinity, cpu_online_mask);
}
static void
@@ -944,10 +945,10 @@
int i;
for (i = 0; i < mp_irq_entries; i++)
- if (mp_irqs[i].mp_irqtype == type &&
- (mp_irqs[i].mp_dstapic == mp_ioapics[apic].mp_apicid ||
- mp_irqs[i].mp_dstapic == MP_APIC_ALL) &&
- mp_irqs[i].mp_dstirq == pin)
+ if (mp_irqs[i].irqtype == type &&
+ (mp_irqs[i].dstapic == mp_ioapics[apic].apicid ||
+ mp_irqs[i].dstapic == MP_APIC_ALL) &&
+ mp_irqs[i].dstirq == pin)
return i;
return -1;
@@ -961,13 +962,13 @@
int i;
for (i = 0; i < mp_irq_entries; i++) {
- int lbus = mp_irqs[i].mp_srcbus;
+ int lbus = mp_irqs[i].srcbus;
if (test_bit(lbus, mp_bus_not_pci) &&
- (mp_irqs[i].mp_irqtype == type) &&
- (mp_irqs[i].mp_srcbusirq == irq))
+ (mp_irqs[i].irqtype == type) &&
+ (mp_irqs[i].srcbusirq == irq))
- return mp_irqs[i].mp_dstirq;
+ return mp_irqs[i].dstirq;
}
return -1;
}
@@ -977,17 +978,17 @@
int i;
for (i = 0; i < mp_irq_entries; i++) {
- int lbus = mp_irqs[i].mp_srcbus;
+ int lbus = mp_irqs[i].srcbus;
if (test_bit(lbus, mp_bus_not_pci) &&
- (mp_irqs[i].mp_irqtype == type) &&
- (mp_irqs[i].mp_srcbusirq == irq))
+ (mp_irqs[i].irqtype == type) &&
+ (mp_irqs[i].srcbusirq == irq))
break;
}
if (i < mp_irq_entries) {
int apic;
for(apic = 0; apic < nr_ioapics; apic++) {
- if (mp_ioapics[apic].mp_apicid == mp_irqs[i].mp_dstapic)
+ if (mp_ioapics[apic].apicid == mp_irqs[i].dstapic)
return apic;
}
}
@@ -1012,23 +1013,23 @@
return -1;
}
for (i = 0; i < mp_irq_entries; i++) {
- int lbus = mp_irqs[i].mp_srcbus;
+ int lbus = mp_irqs[i].srcbus;
for (apic = 0; apic < nr_ioapics; apic++)
- if (mp_ioapics[apic].mp_apicid == mp_irqs[i].mp_dstapic ||
- mp_irqs[i].mp_dstapic == MP_APIC_ALL)
+ if (mp_ioapics[apic].apicid == mp_irqs[i].dstapic ||
+ mp_irqs[i].dstapic == MP_APIC_ALL)
break;
if (!test_bit(lbus, mp_bus_not_pci) &&
- !mp_irqs[i].mp_irqtype &&
+ !mp_irqs[i].irqtype &&
(bus == lbus) &&
- (slot == ((mp_irqs[i].mp_srcbusirq >> 2) & 0x1f))) {
- int irq = pin_2_irq(i,apic,mp_irqs[i].mp_dstirq);
+ (slot == ((mp_irqs[i].srcbusirq >> 2) & 0x1f))) {
+ int irq = pin_2_irq(i, apic, mp_irqs[i].dstirq);
if (!(apic || IO_APIC_IRQ(irq)))
continue;
- if (pin == (mp_irqs[i].mp_srcbusirq & 3))
+ if (pin == (mp_irqs[i].srcbusirq & 3))
return irq;
/*
* Use the first all-but-pin matching entry as a
@@ -1071,7 +1072,7 @@
* EISA conforming in the MP table, that means its trigger type must
* be read in from the ELCR */
-#define default_EISA_trigger(idx) (EISA_ELCR(mp_irqs[idx].mp_srcbusirq))
+#define default_EISA_trigger(idx) (EISA_ELCR(mp_irqs[idx].srcbusirq))
#define default_EISA_polarity(idx) default_ISA_polarity(idx)
/* PCI interrupts are always polarity one level triggered,
@@ -1088,13 +1089,13 @@
static int MPBIOS_polarity(int idx)
{
- int bus = mp_irqs[idx].mp_srcbus;
+ int bus = mp_irqs[idx].srcbus;
int polarity;
/*
* Determine IRQ line polarity (high active or low active):
*/
- switch (mp_irqs[idx].mp_irqflag & 3)
+ switch (mp_irqs[idx].irqflag & 3)
{
case 0: /* conforms, ie. bus-type dependent polarity */
if (test_bit(bus, mp_bus_not_pci))
@@ -1130,13 +1131,13 @@
static int MPBIOS_trigger(int idx)
{
- int bus = mp_irqs[idx].mp_srcbus;
+ int bus = mp_irqs[idx].srcbus;
int trigger;
/*
* Determine IRQ trigger mode (edge or level sensitive):
*/
- switch ((mp_irqs[idx].mp_irqflag>>2) & 3)
+ switch ((mp_irqs[idx].irqflag>>2) & 3)
{
case 0: /* conforms, ie. bus-type dependent */
if (test_bit(bus, mp_bus_not_pci))
@@ -1214,16 +1215,16 @@
static int pin_2_irq(int idx, int apic, int pin)
{
int irq, i;
- int bus = mp_irqs[idx].mp_srcbus;
+ int bus = mp_irqs[idx].srcbus;
/*
* Debugging check, we are in big trouble if this message pops up!
*/
- if (mp_irqs[idx].mp_dstirq != pin)
+ if (mp_irqs[idx].dstirq != pin)
printk(KERN_ERR "broken BIOS or MPTABLE parser, ayiee!!\n");
if (test_bit(bus, mp_bus_not_pci)) {
- irq = mp_irqs[idx].mp_srcbusirq;
+ irq = mp_irqs[idx].srcbusirq;
} else {
/*
* PCI IRQs are mapped in order
@@ -1566,14 +1567,14 @@
apic_printk(APIC_VERBOSE,KERN_DEBUG
"IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> "
"IRQ %d Mode:%i Active:%i)\n",
- apic, mp_ioapics[apic].mp_apicid, pin, cfg->vector,
+ apic, mp_ioapics[apic].apicid, pin, cfg->vector,
irq, trigger, polarity);
- if (setup_ioapic_entry(mp_ioapics[apic].mp_apicid, irq, &entry,
+ if (setup_ioapic_entry(mp_ioapics[apic].apicid, irq, &entry,
dest, trigger, polarity, cfg->vector)) {
printk("Failed to setup ioapic entry for ioapic %d, pin %d\n",
- mp_ioapics[apic].mp_apicid, pin);
+ mp_ioapics[apic].apicid, pin);
__clear_irq_vector(irq, cfg);
return;
}
@@ -1604,12 +1605,10 @@
notcon = 1;
apic_printk(APIC_VERBOSE,
KERN_DEBUG " %d-%d",
- mp_ioapics[apic].mp_apicid,
- pin);
+ mp_ioapics[apic].apicid, pin);
} else
apic_printk(APIC_VERBOSE, " %d-%d",
- mp_ioapics[apic].mp_apicid,
- pin);
+ mp_ioapics[apic].apicid, pin);
continue;
}
if (notcon) {
@@ -1699,7 +1698,7 @@
printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
for (i = 0; i < nr_ioapics; i++)
printk(KERN_DEBUG "number of IO-APIC #%d registers: %d.\n",
- mp_ioapics[i].mp_apicid, nr_ioapic_registers[i]);
+ mp_ioapics[i].apicid, nr_ioapic_registers[i]);
/*
* We are a bit conservative about what we expect. We have to
@@ -1719,7 +1718,7 @@
spin_unlock_irqrestore(&ioapic_lock, flags);
printk("\n");
- printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].mp_apicid);
+ printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].apicid);
printk(KERN_DEBUG ".... register #00: %08X\n", reg_00.raw);
printk(KERN_DEBUG "....... : physical APIC id: %02X\n", reg_00.bits.ID);
printk(KERN_DEBUG "....... : Delivery Type: %X\n", reg_00.bits.delivery_type);
@@ -2121,14 +2120,14 @@
reg_00.raw = io_apic_read(apic, 0);
spin_unlock_irqrestore(&ioapic_lock, flags);
- old_id = mp_ioapics[apic].mp_apicid;
+ old_id = mp_ioapics[apic].apicid;
- if (mp_ioapics[apic].mp_apicid >= get_physical_broadcast()) {
+ if (mp_ioapics[apic].apicid >= get_physical_broadcast()) {
printk(KERN_ERR "BIOS bug, IO-APIC#%d ID is %d in the MPC table!...\n",
- apic, mp_ioapics[apic].mp_apicid);
+ apic, mp_ioapics[apic].apicid);
printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n",
reg_00.bits.ID);
- mp_ioapics[apic].mp_apicid = reg_00.bits.ID;
+ mp_ioapics[apic].apicid = reg_00.bits.ID;
}
/*
@@ -2137,9 +2136,9 @@
* 'stuck on smp_invalidate_needed IPI wait' messages.
*/
if (check_apicid_used(phys_id_present_map,
- mp_ioapics[apic].mp_apicid)) {
+ mp_ioapics[apic].apicid)) {
printk(KERN_ERR "BIOS bug, IO-APIC#%d ID %d is already used!...\n",
- apic, mp_ioapics[apic].mp_apicid);
+ apic, mp_ioapics[apic].apicid);
for (i = 0; i < get_physical_broadcast(); i++)
if (!physid_isset(i, phys_id_present_map))
break;
@@ -2148,13 +2147,13 @@
printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n",
i);
physid_set(i, phys_id_present_map);
- mp_ioapics[apic].mp_apicid = i;
+ mp_ioapics[apic].apicid = i;
} else {
physid_mask_t tmp;
- tmp = apicid_to_cpu_present(mp_ioapics[apic].mp_apicid);
+ tmp = apicid_to_cpu_present(mp_ioapics[apic].apicid);
apic_printk(APIC_VERBOSE, "Setting %d in the "
"phys_id_present_map\n",
- mp_ioapics[apic].mp_apicid);
+ mp_ioapics[apic].apicid);
physids_or(phys_id_present_map, phys_id_present_map, tmp);
}
@@ -2163,11 +2162,11 @@
* We need to adjust the IRQ routing table
* if the ID changed.
*/
- if (old_id != mp_ioapics[apic].mp_apicid)
+ if (old_id != mp_ioapics[apic].apicid)
for (i = 0; i < mp_irq_entries; i++)
- if (mp_irqs[i].mp_dstapic == old_id)
- mp_irqs[i].mp_dstapic
- = mp_ioapics[apic].mp_apicid;
+ if (mp_irqs[i].dstapic == old_id)
+ mp_irqs[i].dstapic
+ = mp_ioapics[apic].apicid;
/*
* Read the right value from the MPC table and
@@ -2175,9 +2174,9 @@
*/
apic_printk(APIC_VERBOSE, KERN_INFO
"...changing IO-APIC physical APIC ID to %d ...",
- mp_ioapics[apic].mp_apicid);
+ mp_ioapics[apic].apicid);
- reg_00.bits.ID = mp_ioapics[apic].mp_apicid;
+ reg_00.bits.ID = mp_ioapics[apic].apicid;
spin_lock_irqsave(&ioapic_lock, flags);
io_apic_write(apic, 0, reg_00.raw);
spin_unlock_irqrestore(&ioapic_lock, flags);
@@ -2188,7 +2187,7 @@
spin_lock_irqsave(&ioapic_lock, flags);
reg_00.raw = io_apic_read(apic, 0);
spin_unlock_irqrestore(&ioapic_lock, flags);
- if (reg_00.bits.ID != mp_ioapics[apic].mp_apicid)
+ if (reg_00.bits.ID != mp_ioapics[apic].apicid)
printk("could not set ID!\n");
else
apic_printk(APIC_VERBOSE, " ok.\n");
@@ -2383,7 +2382,7 @@
if (cfg->move_in_progress)
send_cleanup_vector(cfg);
- cpumask_copy(&desc->affinity, mask);
+ cpumask_copy(desc->affinity, mask);
}
static int migrate_irq_remapped_level_desc(struct irq_desc *desc)
@@ -2405,11 +2404,11 @@
}
/* everthing is clear. we have right of way */
- migrate_ioapic_irq_desc(desc, &desc->pending_mask);
+ migrate_ioapic_irq_desc(desc, desc->pending_mask);
ret = 0;
desc->status &= ~IRQ_MOVE_PENDING;
- cpumask_clear(&desc->pending_mask);
+ cpumask_clear(desc->pending_mask);
unmask:
unmask_IO_APIC_irq_desc(desc);
@@ -2434,7 +2433,7 @@
continue;
}
- desc->chip->set_affinity(irq, &desc->pending_mask);
+ desc->chip->set_affinity(irq, desc->pending_mask);
spin_unlock_irqrestore(&desc->lock, flags);
}
}
@@ -2448,7 +2447,7 @@
{
if (desc->status & IRQ_LEVEL) {
desc->status |= IRQ_MOVE_PENDING;
- cpumask_copy(&desc->pending_mask, mask);
+ cpumask_copy(desc->pending_mask, mask);
migrate_irq_remapped_level_desc(desc);
return;
}
@@ -2516,7 +2515,7 @@
/* domain has not changed, but affinity did */
me = smp_processor_id();
- if (cpu_isset(me, desc->affinity)) {
+ if (cpumask_test_cpu(me, desc->affinity)) {
*descp = desc = move_irq_desc(desc, me);
/* get the new one */
cfg = desc->chip_data;
@@ -3118,8 +3117,8 @@
spin_lock_irqsave(&ioapic_lock, flags);
reg_00.raw = io_apic_read(dev->id, 0);
- if (reg_00.bits.ID != mp_ioapics[dev->id].mp_apicid) {
- reg_00.bits.ID = mp_ioapics[dev->id].mp_apicid;
+ if (reg_00.bits.ID != mp_ioapics[dev->id].apicid) {
+ reg_00.bits.ID = mp_ioapics[dev->id].apicid;
io_apic_write(dev->id, 0, reg_00.raw);
}
spin_unlock_irqrestore(&ioapic_lock, flags);
@@ -3184,7 +3183,7 @@
irq = 0;
spin_lock_irqsave(&vector_lock, flags);
- for (new = irq_want; new < NR_IRQS; new++) {
+ for (new = irq_want; new < nr_irqs; new++) {
if (platform_legacy_irq(new))
continue;
@@ -3259,6 +3258,9 @@
int err;
unsigned dest;
+ if (disable_apic)
+ return -ENXIO;
+
cfg = irq_cfg(irq);
err = assign_irq_vector(irq, cfg, TARGET_CPUS);
if (err)
@@ -3464,40 +3466,6 @@
return 0;
}
-int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc)
-{
- unsigned int irq;
- int ret;
- unsigned int irq_want;
-
- irq_want = nr_irqs_gsi;
- irq = create_irq_nr(irq_want);
- if (irq == 0)
- return -1;
-
-#ifdef CONFIG_INTR_REMAP
- if (!intr_remapping_enabled)
- goto no_ir;
-
- ret = msi_alloc_irte(dev, irq, 1);
- if (ret < 0)
- goto error;
-no_ir:
-#endif
- ret = setup_msi_irq(dev, msidesc, irq);
- if (ret < 0) {
- destroy_irq(irq);
- return ret;
- }
- return 0;
-
-#ifdef CONFIG_INTR_REMAP
-error:
- destroy_irq(irq);
- return ret;
-#endif
-}
-
int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
{
unsigned int irq;
@@ -3727,6 +3695,9 @@
struct irq_cfg *cfg;
int err;
+ if (disable_apic)
+ return -ENXIO;
+
cfg = irq_cfg(irq);
err = assign_irq_vector(irq, cfg, TARGET_CPUS);
if (!err) {
@@ -3761,7 +3732,7 @@
}
#endif /* CONFIG_HT_IRQ */
-#ifdef CONFIG_X86_64
+#ifdef CONFIG_X86_UV
/*
* Re-target the irq to the specified CPU and enable the specified MMR located
* on the specified blade to allow the sending of MSIs to the specified CPU.
@@ -3861,6 +3832,22 @@
printk(KERN_DEBUG "nr_irqs_gsi: %d\n", nr_irqs_gsi);
}
+#ifdef CONFIG_SPARSE_IRQ
+int __init arch_probe_nr_irqs(void)
+{
+ int nr;
+
+ nr = ((8 * nr_cpu_ids) > (32 * nr_ioapics) ?
+ (NR_VECTORS + (8 * nr_cpu_ids)) :
+ (NR_VECTORS + (32 * nr_ioapics)));
+
+ if (nr < nr_irqs && nr > nr_irqs_gsi)
+ nr_irqs = nr;
+
+ return 0;
+}
+#endif
+
/* --------------------------------------------------------------------------
ACPI-based IOAPIC Configuration
-------------------------------------------------------------------------- */
@@ -3995,8 +3982,8 @@
return -1;
for (i = 0; i < mp_irq_entries; i++)
- if (mp_irqs[i].mp_irqtype == mp_INT &&
- mp_irqs[i].mp_srcbusirq == bus_irq)
+ if (mp_irqs[i].irqtype == mp_INT &&
+ mp_irqs[i].srcbusirq == bus_irq)
break;
if (i >= mp_irq_entries)
return -1;
@@ -4050,7 +4037,7 @@
*/
if (desc->status &
(IRQ_NO_BALANCING | IRQ_AFFINITY_SET))
- mask = &desc->affinity;
+ mask = desc->affinity;
else
mask = TARGET_CPUS;
@@ -4111,7 +4098,7 @@
ioapic_res = ioapic_setup_resources();
for (i = 0; i < nr_ioapics; i++) {
if (smp_found_config) {
- ioapic_phys = mp_ioapics[i].mp_apicaddr;
+ ioapic_phys = mp_ioapics[i].apicaddr;
#ifdef CONFIG_X86_32
if (!ioapic_phys) {
printk(KERN_ERR
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 3973e2d..8b30d0c 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -36,11 +36,7 @@
#endif
}
-#ifdef CONFIG_X86_32
-# define irq_stats(x) (&per_cpu(irq_stat, x))
-#else
-# define irq_stats(x) cpu_pda(x)
-#endif
+#define irq_stats(x) (&per_cpu(irq_stat, x))
/*
* /proc/interrupts printing:
*/
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 74b9ff7..e0f29be 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -248,7 +248,7 @@
if (irq == 2)
continue;
- affinity = &desc->affinity;
+ affinity = desc->affinity;
if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
printk("Breaking affinity for irq %i\n", irq);
affinity = cpu_all_mask;
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 63c88e6..018963a 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -18,6 +18,13 @@
#include <linux/smp.h>
#include <asm/io_apic.h>
#include <asm/idle.h>
+#include <asm/apic.h>
+
+DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
+EXPORT_PER_CPU_SYMBOL(irq_stat);
+
+DEFINE_PER_CPU(struct pt_regs *, irq_regs);
+EXPORT_PER_CPU_SYMBOL(irq_regs);
/*
* Probabilistic stack overflow check:
@@ -100,7 +107,7 @@
/* interrupt's are disabled at this point */
spin_lock(&desc->lock);
- affinity = &desc->affinity;
+ affinity = desc->affinity;
if (!irq_has_action(irq) ||
cpumask_equal(affinity, cpu_online_mask)) {
spin_unlock(&desc->lock);
diff --git a/arch/x86/kernel/irqinit_32.c b/arch/x86/kernel/irqinit_32.c
index 10a09c2..22608eb 100644
--- a/arch/x86/kernel/irqinit_32.c
+++ b/arch/x86/kernel/irqinit_32.c
@@ -140,8 +140,15 @@
*/
alloc_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
- /* IPI for invalidation */
- alloc_intr_gate(INVALIDATE_TLB_VECTOR, invalidate_interrupt);
+ /* IPIs for invalidation */
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+0, invalidate_interrupt0);
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+1, invalidate_interrupt1);
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+2, invalidate_interrupt2);
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+3, invalidate_interrupt3);
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+4, invalidate_interrupt4);
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+5, invalidate_interrupt5);
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+6, invalidate_interrupt6);
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+7, invalidate_interrupt7);
/* IPI for generic function call */
alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c
index b7f4c92..5e9f4fc 100644
--- a/arch/x86/kernel/microcode_intel.c
+++ b/arch/x86/kernel/microcode_intel.c
@@ -87,9 +87,9 @@
#include <linux/cpu.h>
#include <linux/firmware.h>
#include <linux/platform_device.h>
+#include <linux/uaccess.h>
#include <asm/msr.h>
-#include <asm/uaccess.h>
#include <asm/processor.h>
#include <asm/microcode.h>
@@ -196,7 +196,7 @@
return (!sigmatch(sig, csig->sig, pf, csig->pf)) ? 0 : 1;
}
-static inline int
+static inline int
update_match_revision(struct microcode_header_intel *mc_header, int rev)
{
return (mc_header->rev <= rev) ? 0 : 1;
@@ -442,8 +442,8 @@
return ret;
}
- ret = generic_load_microcode(cpu, (void*)firmware->data, firmware->size,
- &get_ucode_fw);
+ ret = generic_load_microcode(cpu, (void *)firmware->data,
+ firmware->size, &get_ucode_fw);
release_firmware(firmware);
@@ -460,7 +460,7 @@
/* We should bind the task to the CPU */
BUG_ON(cpu != raw_smp_processor_id());
- return generic_load_microcode(cpu, (void*)buf, size, &get_ucode_user);
+ return generic_load_microcode(cpu, (void *)buf, size, &get_ucode_user);
}
static void microcode_fini_cpu(int cpu)
diff --git a/arch/x86/kernel/module_32.c b/arch/x86/kernel/module_32.c
index 3db0a544..0edd819 100644
--- a/arch/x86/kernel/module_32.c
+++ b/arch/x86/kernel/module_32.c
@@ -42,7 +42,7 @@
{
vfree(module_region);
/* FIXME: If module_region == mod->init_region, trim exception
- table entries. */
+ table entries. */
}
/* We don't need anything special. */
@@ -113,13 +113,13 @@
*para = NULL;
char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
- for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
+ for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
if (!strcmp(".text", secstrings + s->sh_name))
text = s;
if (!strcmp(".altinstructions", secstrings + s->sh_name))
alt = s;
if (!strcmp(".smp_locks", secstrings + s->sh_name))
- locks= s;
+ locks = s;
if (!strcmp(".parainstructions", secstrings + s->sh_name))
para = s;
}
diff --git a/arch/x86/kernel/module_64.c b/arch/x86/kernel/module_64.c
index 6ba8783..c23880b 100644
--- a/arch/x86/kernel/module_64.c
+++ b/arch/x86/kernel/module_64.c
@@ -30,14 +30,14 @@
#include <asm/page.h>
#include <asm/pgtable.h>
-#define DEBUGP(fmt...)
+#define DEBUGP(fmt...)
#ifndef CONFIG_UML
void module_free(struct module *mod, void *module_region)
{
vfree(module_region);
/* FIXME: If module_region == mod->init_region, trim exception
- table entries. */
+ table entries. */
}
void *module_alloc(unsigned long size)
@@ -77,7 +77,7 @@
Elf64_Rela *rel = (void *)sechdrs[relsec].sh_addr;
Elf64_Sym *sym;
void *loc;
- u64 val;
+ u64 val;
DEBUGP("Applying relocate section %u to %u\n", relsec,
sechdrs[relsec].sh_info);
@@ -91,11 +91,11 @@
sym = (Elf64_Sym *)sechdrs[symindex].sh_addr
+ ELF64_R_SYM(rel[i].r_info);
- DEBUGP("type %d st_value %Lx r_addend %Lx loc %Lx\n",
- (int)ELF64_R_TYPE(rel[i].r_info),
- sym->st_value, rel[i].r_addend, (u64)loc);
+ DEBUGP("type %d st_value %Lx r_addend %Lx loc %Lx\n",
+ (int)ELF64_R_TYPE(rel[i].r_info),
+ sym->st_value, rel[i].r_addend, (u64)loc);
- val = sym->st_value + rel[i].r_addend;
+ val = sym->st_value + rel[i].r_addend;
switch (ELF64_R_TYPE(rel[i].r_info)) {
case R_X86_64_NONE:
@@ -113,16 +113,16 @@
if ((s64)val != *(s32 *)loc)
goto overflow;
break;
- case R_X86_64_PC32:
+ case R_X86_64_PC32:
val -= (u64)loc;
*(u32 *)loc = val;
#if 0
if ((s64)val != *(s32 *)loc)
- goto overflow;
+ goto overflow;
#endif
break;
default:
- printk(KERN_ERR "module %s: Unknown rela relocation: %Lu\n",
+ printk(KERN_ERR "module %s: Unknown rela relocation: %llu\n",
me->name, ELF64_R_TYPE(rel[i].r_info));
return -ENOEXEC;
}
@@ -130,7 +130,7 @@
return 0;
overflow:
- printk(KERN_ERR "overflow in relocation type %d val %Lx\n",
+ printk(KERN_ERR "overflow in relocation type %d val %Lx\n",
(int)ELF64_R_TYPE(rel[i].r_info), val);
printk(KERN_ERR "`%s' likely not compiled with -mcmodel=kernel\n",
me->name);
@@ -143,13 +143,13 @@
unsigned int relsec,
struct module *me)
{
- printk("non add relocation not supported\n");
+ printk(KERN_ERR "non add relocation not supported\n");
return -ENOSYS;
-}
+}
int module_finalize(const Elf_Ehdr *hdr,
- const Elf_Shdr *sechdrs,
- struct module *me)
+ const Elf_Shdr *sechdrs,
+ struct module *me)
{
const Elf_Shdr *s, *text = NULL, *alt = NULL, *locks = NULL,
*para = NULL;
@@ -161,7 +161,7 @@
if (!strcmp(".altinstructions", secstrings + s->sh_name))
alt = s;
if (!strcmp(".smp_locks", secstrings + s->sh_name))
- locks= s;
+ locks = s;
if (!strcmp(".parainstructions", secstrings + s->sh_name))
para = s;
}
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index a649a4c..fa6bb26 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -144,11 +144,11 @@
if (bad_ioapic(m->apicaddr))
return;
- mp_ioapics[nr_ioapics].mp_apicaddr = m->apicaddr;
- mp_ioapics[nr_ioapics].mp_apicid = m->apicid;
- mp_ioapics[nr_ioapics].mp_type = m->type;
- mp_ioapics[nr_ioapics].mp_apicver = m->apicver;
- mp_ioapics[nr_ioapics].mp_flags = m->flags;
+ mp_ioapics[nr_ioapics].apicaddr = m->apicaddr;
+ mp_ioapics[nr_ioapics].apicid = m->apicid;
+ mp_ioapics[nr_ioapics].type = m->type;
+ mp_ioapics[nr_ioapics].apicver = m->apicver;
+ mp_ioapics[nr_ioapics].flags = m->flags;
nr_ioapics++;
}
@@ -160,55 +160,55 @@
m->srcbusirq, m->dstapic, m->dstirq);
}
-static void __init print_mp_irq_info(struct mp_config_intsrc *mp_irq)
+static void __init print_mp_irq_info(struct mpc_intsrc *mp_irq)
{
apic_printk(APIC_VERBOSE, "Int: type %d, pol %d, trig %d, bus %02x,"
" IRQ %02x, APIC ID %x, APIC INT %02x\n",
- mp_irq->mp_irqtype, mp_irq->mp_irqflag & 3,
- (mp_irq->mp_irqflag >> 2) & 3, mp_irq->mp_srcbus,
- mp_irq->mp_srcbusirq, mp_irq->mp_dstapic, mp_irq->mp_dstirq);
+ mp_irq->irqtype, mp_irq->irqflag & 3,
+ (mp_irq->irqflag >> 2) & 3, mp_irq->srcbus,
+ mp_irq->srcbusirq, mp_irq->dstapic, mp_irq->dstirq);
}
static void __init assign_to_mp_irq(struct mpc_intsrc *m,
- struct mp_config_intsrc *mp_irq)
+ struct mpc_intsrc *mp_irq)
{
- mp_irq->mp_dstapic = m->dstapic;
- mp_irq->mp_type = m->type;
- mp_irq->mp_irqtype = m->irqtype;
- mp_irq->mp_irqflag = m->irqflag;
- mp_irq->mp_srcbus = m->srcbus;
- mp_irq->mp_srcbusirq = m->srcbusirq;
- mp_irq->mp_dstirq = m->dstirq;
+ mp_irq->dstapic = m->dstapic;
+ mp_irq->type = m->type;
+ mp_irq->irqtype = m->irqtype;
+ mp_irq->irqflag = m->irqflag;
+ mp_irq->srcbus = m->srcbus;
+ mp_irq->srcbusirq = m->srcbusirq;
+ mp_irq->dstirq = m->dstirq;
}
-static void __init assign_to_mpc_intsrc(struct mp_config_intsrc *mp_irq,
+static void __init assign_to_mpc_intsrc(struct mpc_intsrc *mp_irq,
struct mpc_intsrc *m)
{
- m->dstapic = mp_irq->mp_dstapic;
- m->type = mp_irq->mp_type;
- m->irqtype = mp_irq->mp_irqtype;
- m->irqflag = mp_irq->mp_irqflag;
- m->srcbus = mp_irq->mp_srcbus;
- m->srcbusirq = mp_irq->mp_srcbusirq;
- m->dstirq = mp_irq->mp_dstirq;
+ m->dstapic = mp_irq->dstapic;
+ m->type = mp_irq->type;
+ m->irqtype = mp_irq->irqtype;
+ m->irqflag = mp_irq->irqflag;
+ m->srcbus = mp_irq->srcbus;
+ m->srcbusirq = mp_irq->srcbusirq;
+ m->dstirq = mp_irq->dstirq;
}
-static int __init mp_irq_mpc_intsrc_cmp(struct mp_config_intsrc *mp_irq,
+static int __init mp_irq_mpc_intsrc_cmp(struct mpc_intsrc *mp_irq,
struct mpc_intsrc *m)
{
- if (mp_irq->mp_dstapic != m->dstapic)
+ if (mp_irq->dstapic != m->dstapic)
return 1;
- if (mp_irq->mp_type != m->type)
+ if (mp_irq->type != m->type)
return 2;
- if (mp_irq->mp_irqtype != m->irqtype)
+ if (mp_irq->irqtype != m->irqtype)
return 3;
- if (mp_irq->mp_irqflag != m->irqflag)
+ if (mp_irq->irqflag != m->irqflag)
return 4;
- if (mp_irq->mp_srcbus != m->srcbus)
+ if (mp_irq->srcbus != m->srcbus)
return 5;
- if (mp_irq->mp_srcbusirq != m->srcbusirq)
+ if (mp_irq->srcbusirq != m->srcbusirq)
return 6;
- if (mp_irq->mp_dstirq != m->dstirq)
+ if (mp_irq->dstirq != m->dstirq)
return 7;
return 0;
@@ -417,7 +417,7 @@
intsrc.type = MP_INTSRC;
intsrc.irqflag = 0; /* conforming */
intsrc.srcbus = 0;
- intsrc.dstapic = mp_ioapics[0].mp_apicid;
+ intsrc.dstapic = mp_ioapics[0].apicid;
intsrc.irqtype = mp_INT;
@@ -570,14 +570,14 @@
}
}
-static struct intel_mp_floating *mpf_found;
+static struct mpf_intel *mpf_found;
/*
* Scan the memory blocks for an SMP configuration block.
*/
static void __init __get_smp_config(unsigned int early)
{
- struct intel_mp_floating *mpf = mpf_found;
+ struct mpf_intel *mpf = mpf_found;
if (!mpf)
return;
@@ -598,9 +598,9 @@
}
printk(KERN_INFO "Intel MultiProcessor Specification v1.%d\n",
- mpf->mpf_specification);
+ mpf->specification);
#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32)
- if (mpf->mpf_feature2 & (1 << 7)) {
+ if (mpf->feature2 & (1 << 7)) {
printk(KERN_INFO " IMCR and PIC compatibility mode.\n");
pic_mode = 1;
} else {
@@ -611,7 +611,7 @@
/*
* Now see if we need to read further.
*/
- if (mpf->mpf_feature1 != 0) {
+ if (mpf->feature1 != 0) {
if (early) {
/*
* local APIC has default address
@@ -621,16 +621,16 @@
}
printk(KERN_INFO "Default MP configuration #%d\n",
- mpf->mpf_feature1);
- construct_default_ISA_mptable(mpf->mpf_feature1);
+ mpf->feature1);
+ construct_default_ISA_mptable(mpf->feature1);
- } else if (mpf->mpf_physptr) {
+ } else if (mpf->physptr) {
/*
* Read the physical hardware table. Anything here will
* override the defaults.
*/
- if (!smp_read_mpc(phys_to_virt(mpf->mpf_physptr), early)) {
+ if (!smp_read_mpc(phys_to_virt(mpf->physptr), early)) {
#ifdef CONFIG_X86_LOCAL_APIC
smp_found_config = 0;
#endif
@@ -688,19 +688,19 @@
unsigned reserve)
{
unsigned int *bp = phys_to_virt(base);
- struct intel_mp_floating *mpf;
+ struct mpf_intel *mpf;
apic_printk(APIC_VERBOSE, "Scan SMP from %p for %ld bytes.\n",
bp, length);
BUILD_BUG_ON(sizeof(*mpf) != 16);
while (length > 0) {
- mpf = (struct intel_mp_floating *)bp;
+ mpf = (struct mpf_intel *)bp;
if ((*bp == SMP_MAGIC_IDENT) &&
- (mpf->mpf_length == 1) &&
+ (mpf->length == 1) &&
!mpf_checksum((unsigned char *)bp, 16) &&
- ((mpf->mpf_specification == 1)
- || (mpf->mpf_specification == 4))) {
+ ((mpf->specification == 1)
+ || (mpf->specification == 4))) {
#ifdef CONFIG_X86_LOCAL_APIC
smp_found_config = 1;
#endif
@@ -713,7 +713,7 @@
return 1;
reserve_bootmem_generic(virt_to_phys(mpf), PAGE_SIZE,
BOOTMEM_DEFAULT);
- if (mpf->mpf_physptr) {
+ if (mpf->physptr) {
unsigned long size = PAGE_SIZE;
#ifdef CONFIG_X86_32
/*
@@ -722,14 +722,14 @@
* the bottom is mapped now.
* PC-9800's MPC table places on the very last
* of physical memory; so that simply reserving
- * PAGE_SIZE from mpg->mpf_physptr yields BUG()
+ * PAGE_SIZE from mpf->physptr yields BUG()
* in reserve_bootmem.
*/
unsigned long end = max_low_pfn * PAGE_SIZE;
- if (mpf->mpf_physptr + size > end)
- size = end - mpf->mpf_physptr;
+ if (mpf->physptr + size > end)
+ size = end - mpf->physptr;
#endif
- reserve_bootmem_generic(mpf->mpf_physptr, size,
+ reserve_bootmem_generic(mpf->physptr, size,
BOOTMEM_DEFAULT);
}
@@ -809,15 +809,15 @@
/* not legacy */
for (i = 0; i < mp_irq_entries; i++) {
- if (mp_irqs[i].mp_irqtype != mp_INT)
+ if (mp_irqs[i].irqtype != mp_INT)
continue;
- if (mp_irqs[i].mp_irqflag != 0x0f)
+ if (mp_irqs[i].irqflag != 0x0f)
continue;
- if (mp_irqs[i].mp_srcbus != m->srcbus)
+ if (mp_irqs[i].srcbus != m->srcbus)
continue;
- if (mp_irqs[i].mp_srcbusirq != m->srcbusirq)
+ if (mp_irqs[i].srcbusirq != m->srcbusirq)
continue;
if (irq_used[i]) {
/* already claimed */
@@ -922,10 +922,10 @@
if (irq_used[i])
continue;
- if (mp_irqs[i].mp_irqtype != mp_INT)
+ if (mp_irqs[i].irqtype != mp_INT)
continue;
- if (mp_irqs[i].mp_irqflag != 0x0f)
+ if (mp_irqs[i].irqflag != 0x0f)
continue;
if (nr_m_spare > 0) {
@@ -1001,7 +1001,7 @@
{
char str[16];
char oem[10];
- struct intel_mp_floating *mpf;
+ struct mpf_intel *mpf;
struct mpc_table *mpc, *mpc_new;
if (!enable_update_mptable)
@@ -1014,19 +1014,19 @@
/*
* Now see if we need to go further.
*/
- if (mpf->mpf_feature1 != 0)
+ if (mpf->feature1 != 0)
return 0;
- if (!mpf->mpf_physptr)
+ if (!mpf->physptr)
return 0;
- mpc = phys_to_virt(mpf->mpf_physptr);
+ mpc = phys_to_virt(mpf->physptr);
if (!smp_check_mpc(mpc, oem, str))
return 0;
printk(KERN_INFO "mpf: %lx\n", virt_to_phys(mpf));
- printk(KERN_INFO "mpf_physptr: %x\n", mpf->mpf_physptr);
+ printk(KERN_INFO "physptr: %x\n", mpf->physptr);
if (mpc_new_phys && mpc->length > mpc_new_length) {
mpc_new_phys = 0;
@@ -1047,23 +1047,23 @@
}
printk(KERN_INFO "use in-positon replacing\n");
} else {
- mpf->mpf_physptr = mpc_new_phys;
+ mpf->physptr = mpc_new_phys;
mpc_new = phys_to_virt(mpc_new_phys);
memcpy(mpc_new, mpc, mpc->length);
mpc = mpc_new;
/* check if we can modify that */
- if (mpc_new_phys - mpf->mpf_physptr) {
- struct intel_mp_floating *mpf_new;
+ if (mpc_new_phys - mpf->physptr) {
+ struct mpf_intel *mpf_new;
/* steal 16 bytes from [0, 1k) */
printk(KERN_INFO "mpf new: %x\n", 0x400 - 16);
mpf_new = phys_to_virt(0x400 - 16);
memcpy(mpf_new, mpf, 16);
mpf = mpf_new;
- mpf->mpf_physptr = mpc_new_phys;
+ mpf->physptr = mpc_new_phys;
}
- mpf->mpf_checksum = 0;
- mpf->mpf_checksum -= mpf_checksum((unsigned char *)mpf, 16);
- printk(KERN_INFO "mpf_physptr new: %x\n", mpf->mpf_physptr);
+ mpf->checksum = 0;
+ mpf->checksum -= mpf_checksum((unsigned char *)mpf, 16);
+ printk(KERN_INFO "physptr new: %x\n", mpf->physptr);
}
/*
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index 7262666..3cf3413 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -35,10 +35,10 @@
#include <linux/device.h>
#include <linux/cpu.h>
#include <linux/notifier.h>
+#include <linux/uaccess.h>
#include <asm/processor.h>
#include <asm/msr.h>
-#include <asm/uaccess.h>
#include <asm/system.h>
static struct class *msr_class;
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 7228979..23b6d9e 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -61,11 +61,7 @@
static inline unsigned int get_nmi_count(int cpu)
{
-#ifdef CONFIG_X86_64
- return cpu_pda(cpu)->__nmi_count;
-#else
- return nmi_count(cpu);
-#endif
+ return per_cpu(irq_stat, cpu).__nmi_count;
}
static inline int mce_in_progress(void)
@@ -82,12 +78,8 @@
*/
static inline unsigned int get_timer_irqs(int cpu)
{
-#ifdef CONFIG_X86_64
- return read_pda(apic_timer_irqs) + read_pda(irq0_irqs);
-#else
return per_cpu(irq_stat, cpu).apic_timer_irqs +
per_cpu(irq_stat, cpu).irq0_irqs;
-#endif
}
#ifdef CONFIG_SMP
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index 95777b0..3a7c5a4 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -26,13 +26,3 @@
};
EXPORT_SYMBOL(pv_lock_ops);
-void __init paravirt_use_bytelocks(void)
-{
-#ifdef CONFIG_SMP
- pv_lock_ops.spin_is_locked = __byte_spin_is_locked;
- pv_lock_ops.spin_is_contended = __byte_spin_is_contended;
- pv_lock_ops.spin_lock = __byte_spin_lock;
- pv_lock_ops.spin_trylock = __byte_spin_trylock;
- pv_lock_ops.spin_unlock = __byte_spin_unlock;
-#endif
-}
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index e4c8fb6..cea11c8 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -44,6 +44,17 @@
{
}
+/* identity function, which can be inlined */
+u32 _paravirt_ident_32(u32 x)
+{
+ return x;
+}
+
+u64 _paravirt_ident_64(u64 x)
+{
+ return x;
+}
+
static void __init default_banner(void)
{
printk(KERN_INFO "Booting paravirtualized kernel on %s\n",
@@ -138,9 +149,16 @@
if (opfunc == NULL)
/* If there's no function, patch it with a ud2a (BUG) */
ret = paravirt_patch_insns(insnbuf, len, ud2a, ud2a+sizeof(ud2a));
- else if (opfunc == paravirt_nop)
+ else if (opfunc == _paravirt_nop)
/* If the operation is a nop, then nop the callsite */
ret = paravirt_patch_nop();
+
+ /* identity functions just return their single argument */
+ else if (opfunc == _paravirt_ident_32)
+ ret = paravirt_patch_ident_32(insnbuf, len);
+ else if (opfunc == _paravirt_ident_64)
+ ret = paravirt_patch_ident_64(insnbuf, len);
+
else if (type == PARAVIRT_PATCH(pv_cpu_ops.iret) ||
type == PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit) ||
type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret32) ||
@@ -292,10 +310,10 @@
struct pv_irq_ops pv_irq_ops = {
.init_IRQ = native_init_IRQ,
- .save_fl = native_save_fl,
- .restore_fl = native_restore_fl,
- .irq_disable = native_irq_disable,
- .irq_enable = native_irq_enable,
+ .save_fl = __PV_IS_CALLEE_SAVE(native_save_fl),
+ .restore_fl = __PV_IS_CALLEE_SAVE(native_restore_fl),
+ .irq_disable = __PV_IS_CALLEE_SAVE(native_irq_disable),
+ .irq_enable = __PV_IS_CALLEE_SAVE(native_irq_enable),
.safe_halt = native_safe_halt,
.halt = native_halt,
#ifdef CONFIG_X86_64
@@ -373,6 +391,14 @@
#endif
};
+#if defined(CONFIG_X86_32) && !defined(CONFIG_X86_PAE)
+/* 32-bit pagetable entries */
+#define PTE_IDENT __PV_IS_CALLEE_SAVE(_paravirt_ident_32)
+#else
+/* 64-bit pagetable entries */
+#define PTE_IDENT __PV_IS_CALLEE_SAVE(_paravirt_ident_64)
+#endif
+
struct pv_mmu_ops pv_mmu_ops = {
#ifndef CONFIG_X86_64
.pagetable_setup_start = native_pagetable_setup_start,
@@ -424,22 +450,23 @@
.pmd_clear = native_pmd_clear,
#endif
.set_pud = native_set_pud,
- .pmd_val = native_pmd_val,
- .make_pmd = native_make_pmd,
+
+ .pmd_val = PTE_IDENT,
+ .make_pmd = PTE_IDENT,
#if PAGETABLE_LEVELS == 4
- .pud_val = native_pud_val,
- .make_pud = native_make_pud,
+ .pud_val = PTE_IDENT,
+ .make_pud = PTE_IDENT,
+
.set_pgd = native_set_pgd,
#endif
#endif /* PAGETABLE_LEVELS >= 3 */
- .pte_val = native_pte_val,
- .pte_flags = native_pte_flags,
- .pgd_val = native_pgd_val,
+ .pte_val = PTE_IDENT,
+ .pgd_val = PTE_IDENT,
- .make_pte = native_make_pte,
- .make_pgd = native_make_pgd,
+ .make_pte = PTE_IDENT,
+ .make_pgd = PTE_IDENT,
.dup_mmap = paravirt_nop,
.exit_mmap = paravirt_nop,
diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c
index 9fe644f..d9f32e6 100644
--- a/arch/x86/kernel/paravirt_patch_32.c
+++ b/arch/x86/kernel/paravirt_patch_32.c
@@ -12,6 +12,18 @@
DEF_NATIVE(pv_cpu_ops, clts, "clts");
DEF_NATIVE(pv_cpu_ops, read_tsc, "rdtsc");
+unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
+{
+ /* arg in %eax, return in %eax */
+ return 0;
+}
+
+unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len)
+{
+ /* arg in %edx:%eax, return in %edx:%eax */
+ return 0;
+}
+
unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
unsigned long addr, unsigned len)
{
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index 061d01d..3f08f34 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -19,6 +19,21 @@
DEF_NATIVE(pv_cpu_ops, usergs_sysret32, "swapgs; sysretl");
DEF_NATIVE(pv_cpu_ops, swapgs, "swapgs");
+DEF_NATIVE(, mov32, "mov %edi, %eax");
+DEF_NATIVE(, mov64, "mov %rdi, %rax");
+
+unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
+{
+ return paravirt_patch_insns(insnbuf, len,
+ start__mov32, end__mov32);
+}
+
+unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len)
+{
+ return paravirt_patch_insns(insnbuf, len,
+ start__mov64, end__mov64);
+}
+
unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
unsigned long addr, unsigned len)
{
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index a546f55..1a1ae8e 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -66,9 +66,6 @@
DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
EXPORT_PER_CPU_SYMBOL(current_task);
-DEFINE_PER_CPU(int, cpu_number);
-EXPORT_PER_CPU_SYMBOL(cpu_number);
-
/*
* Return saved PC of a blocked thread.
*/
@@ -111,7 +108,6 @@
play_dead();
local_irq_disable();
- __get_cpu_var(irq_stat).idle_timestamp = jiffies;
/* Don't trace irqs off for idle */
stop_critical_timings();
pm_idle();
@@ -591,7 +587,7 @@
if (prev->gs | next->gs)
loadsegment(gs, next->gs);
- x86_write_percpu(current_task, next_p);
+ percpu_write(current_task, next_p);
return prev_p;
}
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 85b4cb5..8eb169e 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -16,6 +16,7 @@
#include <stdarg.h>
+#include <linux/stackprotector.h>
#include <linux/cpu.h>
#include <linux/errno.h>
#include <linux/sched.h>
@@ -47,7 +48,6 @@
#include <asm/processor.h>
#include <asm/i387.h>
#include <asm/mmu_context.h>
-#include <asm/pda.h>
#include <asm/prctl.h>
#include <asm/desc.h>
#include <asm/proto.h>
@@ -58,6 +58,12 @@
asmlinkage extern void ret_from_fork(void);
+DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
+EXPORT_PER_CPU_SYMBOL(current_task);
+
+DEFINE_PER_CPU(unsigned long, old_rsp);
+static DEFINE_PER_CPU(unsigned char, is_idle);
+
unsigned long kernel_thread_flags = CLONE_VM | CLONE_UNTRACED;
static ATOMIC_NOTIFIER_HEAD(idle_notifier);
@@ -76,13 +82,13 @@
void enter_idle(void)
{
- write_pda(isidle, 1);
+ percpu_write(is_idle, 1);
atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL);
}
static void __exit_idle(void)
{
- if (test_and_clear_bit_pda(0, isidle) == 0)
+ if (x86_test_and_clear_bit_percpu(0, is_idle) == 0)
return;
atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL);
}
@@ -112,6 +118,17 @@
void cpu_idle(void)
{
current_thread_info()->status |= TS_POLLING;
+
+ /*
+ * If we're the non-boot CPU, nothing set the PDA stack
+ * canary up for us - and if we are the boot CPU we have
+ * a 0 stack canary. This is a good place for updating
+ * it, as we wont ever return from this function (so the
+ * invalid canaries already on the stack wont ever
+ * trigger):
+ */
+ boot_init_stack_canary();
+
/* endless idle loop with no priority at all */
while (1) {
tick_nohz_stop_sched_tick(1);
@@ -397,7 +414,7 @@
load_gs_index(0);
regs->ip = new_ip;
regs->sp = new_sp;
- write_pda(oldrsp, new_sp);
+ percpu_write(old_rsp, new_sp);
regs->cs = __USER_CS;
regs->ss = __USER_DS;
regs->flags = 0x200;
@@ -618,21 +635,13 @@
/*
* Switch the PDA and FPU contexts.
*/
- prev->usersp = read_pda(oldrsp);
- write_pda(oldrsp, next->usersp);
- write_pda(pcurrent, next_p);
+ prev->usersp = percpu_read(old_rsp);
+ percpu_write(old_rsp, next->usersp);
+ percpu_write(current_task, next_p);
- write_pda(kernelstack,
+ percpu_write(kernel_stack,
(unsigned long)task_stack_page(next_p) +
- THREAD_SIZE - PDA_STACKOFFSET);
-#ifdef CONFIG_CC_STACKPROTECTOR
- write_pda(stack_canary, next_p->stack_canary);
- /*
- * Build time only check to make sure the stack_canary is at
- * offset 40 in the pda; this is a gcc ABI requirement
- */
- BUILD_BUG_ON(offsetof(struct x8664_pda, stack_canary) != 40);
-#endif
+ THREAD_SIZE - KERNEL_STACK_OFFSET);
/*
* Now maybe reload the debug registers and handle I/O bitmaps
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 2b46eb4..f8536fe 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -14,6 +14,7 @@
#include <asm/reboot.h>
#include <asm/pci_x86.h>
#include <asm/virtext.h>
+#include <asm/cpu.h>
#ifdef CONFIG_X86_32
# include <linux/dmi.h>
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index c461f6d..d5d6693b 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -89,7 +89,7 @@
#include <asm/system.h>
#include <asm/vsyscall.h>
-#include <asm/smp.h>
+#include <asm/cpu.h>
#include <asm/desc.h>
#include <asm/dma.h>
#include <asm/iommu.h>
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 0116107..ef91747 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -13,145 +13,46 @@
#include <asm/mpspec.h>
#include <asm/apicdef.h>
#include <asm/highmem.h>
+#include <asm/proto.h>
+#include <asm/cpumask.h>
+#include <asm/cpu.h>
-#ifdef CONFIG_X86_LOCAL_APIC
-unsigned int num_processors;
-unsigned disabled_cpus __cpuinitdata;
-/* Processor that is doing the boot up */
-unsigned int boot_cpu_physical_apicid = -1U;
-EXPORT_SYMBOL(boot_cpu_physical_apicid);
-unsigned int max_physical_apicid;
-
-/* Bitmask of physically existing CPUs */
-physid_mask_t phys_cpu_present_map;
-#endif
-
-/* map cpu index to physical APIC ID */
-DEFINE_EARLY_PER_CPU(u16, x86_cpu_to_apicid, BAD_APICID);
-DEFINE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid, BAD_APICID);
-EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid);
-EXPORT_EARLY_PER_CPU_SYMBOL(x86_bios_cpu_apicid);
-
-#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
-#define X86_64_NUMA 1
-
-/* map cpu index to node index */
-DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE);
-EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map);
-
-/* which logical CPUs are on which nodes */
-cpumask_t *node_to_cpumask_map;
-EXPORT_SYMBOL(node_to_cpumask_map);
-
-/* setup node_to_cpumask_map */
-static void __init setup_node_to_cpumask_map(void);
-
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+# define DBG(x...) printk(KERN_DEBUG x)
#else
-static inline void setup_node_to_cpumask_map(void) { }
+# define DBG(x...)
#endif
-#if defined(CONFIG_HAVE_SETUP_PER_CPU_AREA) && defined(CONFIG_X86_SMP)
-/*
- * Copy data used in early init routines from the initial arrays to the
- * per cpu data areas. These arrays then become expendable and the
- * *_early_ptr's are zeroed indicating that the static arrays are gone.
- */
-static void __init setup_per_cpu_maps(void)
-{
- int cpu;
-
- for_each_possible_cpu(cpu) {
- per_cpu(x86_cpu_to_apicid, cpu) =
- early_per_cpu_map(x86_cpu_to_apicid, cpu);
- per_cpu(x86_bios_cpu_apicid, cpu) =
- early_per_cpu_map(x86_bios_cpu_apicid, cpu);
-#ifdef X86_64_NUMA
- per_cpu(x86_cpu_to_node_map, cpu) =
- early_per_cpu_map(x86_cpu_to_node_map, cpu);
-#endif
- }
-
- /* indicate the early static arrays will soon be gone */
- early_per_cpu_ptr(x86_cpu_to_apicid) = NULL;
- early_per_cpu_ptr(x86_bios_cpu_apicid) = NULL;
-#ifdef X86_64_NUMA
- early_per_cpu_ptr(x86_cpu_to_node_map) = NULL;
-#endif
-}
-
-#ifdef CONFIG_X86_32
-/*
- * Great future not-so-futuristic plan: make i386 and x86_64 do it
- * the same way
- */
-unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
-EXPORT_SYMBOL(__per_cpu_offset);
-static inline void setup_cpu_pda_map(void) { }
-
-#elif !defined(CONFIG_SMP)
-static inline void setup_cpu_pda_map(void) { }
-
-#else /* CONFIG_SMP && CONFIG_X86_64 */
-
-/*
- * Allocate cpu_pda pointer table and array via alloc_bootmem.
- */
-static void __init setup_cpu_pda_map(void)
-{
- char *pda;
- struct x8664_pda **new_cpu_pda;
- unsigned long size;
- int cpu;
-
- size = roundup(sizeof(struct x8664_pda), cache_line_size());
-
- /* allocate cpu_pda array and pointer table */
- {
- unsigned long tsize = nr_cpu_ids * sizeof(void *);
- unsigned long asize = size * (nr_cpu_ids - 1);
-
- tsize = roundup(tsize, cache_line_size());
- new_cpu_pda = alloc_bootmem(tsize + asize);
- pda = (char *)new_cpu_pda + tsize;
- }
-
- /* initialize pointer table to static pda's */
- for_each_possible_cpu(cpu) {
- if (cpu == 0) {
- /* leave boot cpu pda in place */
- new_cpu_pda[0] = cpu_pda(0);
- continue;
- }
- new_cpu_pda[cpu] = (struct x8664_pda *)pda;
- new_cpu_pda[cpu]->in_bootmem = 1;
- pda += size;
- }
-
- /* point to new pointer table */
- _cpu_pda = new_cpu_pda;
-}
-
-#endif /* CONFIG_SMP && CONFIG_X86_64 */
+DEFINE_PER_CPU(int, cpu_number);
+EXPORT_PER_CPU_SYMBOL(cpu_number);
#ifdef CONFIG_X86_64
+#define BOOT_PERCPU_OFFSET ((unsigned long)__per_cpu_load)
+#else
+#define BOOT_PERCPU_OFFSET 0
+#endif
-/* correctly size the local cpu masks */
-static void __init setup_cpu_local_masks(void)
+DEFINE_PER_CPU(unsigned long, this_cpu_off) = BOOT_PERCPU_OFFSET;
+EXPORT_PER_CPU_SYMBOL(this_cpu_off);
+
+unsigned long __per_cpu_offset[NR_CPUS] __read_mostly = {
+ [0 ... NR_CPUS-1] = BOOT_PERCPU_OFFSET,
+};
+EXPORT_SYMBOL(__per_cpu_offset);
+
+static inline void setup_percpu_segment(int cpu)
{
- alloc_bootmem_cpumask_var(&cpu_initialized_mask);
- alloc_bootmem_cpumask_var(&cpu_callin_mask);
- alloc_bootmem_cpumask_var(&cpu_callout_mask);
- alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask);
+#ifdef CONFIG_X86_32
+ struct desc_struct gdt;
+
+ pack_descriptor(&gdt, per_cpu_offset(cpu), 0xFFFFF,
+ 0x2 | DESCTYPE_S, 0x8);
+ gdt.s = 1;
+ write_gdt_entry(get_cpu_gdt_table(cpu),
+ GDT_ENTRY_PERCPU, &gdt, DESCTYPE_S);
+#endif
}
-#else /* CONFIG_X86_32 */
-
-static inline void setup_cpu_local_masks(void)
-{
-}
-
-#endif /* CONFIG_X86_32 */
-
/*
* Great future plan:
* Declare PDA itself and support (irqstack,tss,pgd) as per cpu data.
@@ -159,18 +60,12 @@
*/
void __init setup_per_cpu_areas(void)
{
- ssize_t size, old_size;
+ ssize_t size;
char *ptr;
int cpu;
- unsigned long align = 1;
-
- /* Setup cpu_pda map */
- setup_cpu_pda_map();
/* Copy section for each CPU (we discard the original) */
- old_size = PERCPU_ENOUGH_ROOM;
- align = max_t(unsigned long, PAGE_SIZE, align);
- size = roundup(old_size, align);
+ size = roundup(PERCPU_ENOUGH_ROOM, PAGE_SIZE);
pr_info("NR_CPUS:%d nr_cpumask_bits:%d nr_cpu_ids:%d nr_node_ids:%d\n",
NR_CPUS, nr_cpumask_bits, nr_cpu_ids, nr_node_ids);
@@ -179,30 +74,67 @@
for_each_possible_cpu(cpu) {
#ifndef CONFIG_NEED_MULTIPLE_NODES
- ptr = __alloc_bootmem(size, align,
- __pa(MAX_DMA_ADDRESS));
+ ptr = alloc_bootmem_pages(size);
#else
int node = early_cpu_to_node(cpu);
if (!node_online(node) || !NODE_DATA(node)) {
- ptr = __alloc_bootmem(size, align,
- __pa(MAX_DMA_ADDRESS));
+ ptr = alloc_bootmem_pages(size);
pr_info("cpu %d has no node %d or node-local memory\n",
cpu, node);
pr_debug("per cpu data for cpu%d at %016lx\n",
cpu, __pa(ptr));
} else {
- ptr = __alloc_bootmem_node(NODE_DATA(node), size, align,
- __pa(MAX_DMA_ADDRESS));
+ ptr = alloc_bootmem_pages_node(NODE_DATA(node), size);
pr_debug("per cpu data for cpu%d on node%d at %016lx\n",
cpu, node, __pa(ptr));
}
#endif
+
+ memcpy(ptr, __per_cpu_load, __per_cpu_end - __per_cpu_start);
per_cpu_offset(cpu) = ptr - __per_cpu_start;
- memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
+ per_cpu(this_cpu_off, cpu) = per_cpu_offset(cpu);
+ per_cpu(cpu_number, cpu) = cpu;
+ setup_percpu_segment(cpu);
+ /*
+ * Copy data used in early init routines from the
+ * initial arrays to the per cpu data areas. These
+ * arrays then become expendable and the *_early_ptr's
+ * are zeroed indicating that the static arrays are
+ * gone.
+ */
+#ifdef CONFIG_X86_LOCAL_APIC
+ per_cpu(x86_cpu_to_apicid, cpu) =
+ early_per_cpu_map(x86_cpu_to_apicid, cpu);
+ per_cpu(x86_bios_cpu_apicid, cpu) =
+ early_per_cpu_map(x86_bios_cpu_apicid, cpu);
+#endif
+#ifdef CONFIG_X86_64
+ per_cpu(irq_stack_ptr, cpu) =
+ per_cpu(irq_stack_union.irq_stack, cpu) +
+ IRQ_STACK_SIZE - 64;
+#ifdef CONFIG_NUMA
+ per_cpu(x86_cpu_to_node_map, cpu) =
+ early_per_cpu_map(x86_cpu_to_node_map, cpu);
+#endif
+#endif
+ /*
+ * Up to this point, the boot CPU has been using .data.init
+ * area. Reload any changed state for the boot CPU.
+ */
+ if (cpu == boot_cpu_id)
+ switch_to_new_gdt(cpu);
+
+ DBG("PERCPU: cpu %4d %p\n", cpu, ptr);
}
- /* Setup percpu data maps */
- setup_per_cpu_maps();
+ /* indicate the early static arrays will soon be gone */
+#ifdef CONFIG_X86_LOCAL_APIC
+ early_per_cpu_ptr(x86_cpu_to_apicid) = NULL;
+ early_per_cpu_ptr(x86_bios_cpu_apicid) = NULL;
+#endif
+#if defined(CONFIG_X86_64) && defined(CONFIG_NUMA)
+ early_per_cpu_ptr(x86_cpu_to_node_map) = NULL;
+#endif
/* Setup node to cpumask map */
setup_node_to_cpumask_map();
@@ -210,199 +142,3 @@
/* Setup cpu initialized, callin, callout masks */
setup_cpu_local_masks();
}
-
-#endif
-
-#ifdef X86_64_NUMA
-
-/*
- * Allocate node_to_cpumask_map based on number of available nodes
- * Requires node_possible_map to be valid.
- *
- * Note: node_to_cpumask() is not valid until after this is done.
- */
-static void __init setup_node_to_cpumask_map(void)
-{
- unsigned int node, num = 0;
- cpumask_t *map;
-
- /* setup nr_node_ids if not done yet */
- if (nr_node_ids == MAX_NUMNODES) {
- for_each_node_mask(node, node_possible_map)
- num = node;
- nr_node_ids = num + 1;
- }
-
- /* allocate the map */
- map = alloc_bootmem_low(nr_node_ids * sizeof(cpumask_t));
-
- pr_debug("Node to cpumask map at %p for %d nodes\n",
- map, nr_node_ids);
-
- /* node_to_cpumask() will now work */
- node_to_cpumask_map = map;
-}
-
-void __cpuinit numa_set_node(int cpu, int node)
-{
- int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map);
-
- if (cpu_pda(cpu) && node != NUMA_NO_NODE)
- cpu_pda(cpu)->nodenumber = node;
-
- if (cpu_to_node_map)
- cpu_to_node_map[cpu] = node;
-
- else if (per_cpu_offset(cpu))
- per_cpu(x86_cpu_to_node_map, cpu) = node;
-
- else
- pr_debug("Setting node for non-present cpu %d\n", cpu);
-}
-
-void __cpuinit numa_clear_node(int cpu)
-{
- numa_set_node(cpu, NUMA_NO_NODE);
-}
-
-#ifndef CONFIG_DEBUG_PER_CPU_MAPS
-
-void __cpuinit numa_add_cpu(int cpu)
-{
- cpu_set(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
-}
-
-void __cpuinit numa_remove_cpu(int cpu)
-{
- cpu_clear(cpu, node_to_cpumask_map[cpu_to_node(cpu)]);
-}
-
-#else /* CONFIG_DEBUG_PER_CPU_MAPS */
-
-/*
- * --------- debug versions of the numa functions ---------
- */
-static void __cpuinit numa_set_cpumask(int cpu, int enable)
-{
- int node = cpu_to_node(cpu);
- cpumask_t *mask;
- char buf[64];
-
- if (node_to_cpumask_map == NULL) {
- printk(KERN_ERR "node_to_cpumask_map NULL\n");
- dump_stack();
- return;
- }
-
- mask = &node_to_cpumask_map[node];
- if (enable)
- cpu_set(cpu, *mask);
- else
- cpu_clear(cpu, *mask);
-
- cpulist_scnprintf(buf, sizeof(buf), mask);
- printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n",
- enable ? "numa_add_cpu" : "numa_remove_cpu", cpu, node, buf);
-}
-
-void __cpuinit numa_add_cpu(int cpu)
-{
- numa_set_cpumask(cpu, 1);
-}
-
-void __cpuinit numa_remove_cpu(int cpu)
-{
- numa_set_cpumask(cpu, 0);
-}
-
-int cpu_to_node(int cpu)
-{
- if (early_per_cpu_ptr(x86_cpu_to_node_map)) {
- printk(KERN_WARNING
- "cpu_to_node(%d): usage too early!\n", cpu);
- dump_stack();
- return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
- }
- return per_cpu(x86_cpu_to_node_map, cpu);
-}
-EXPORT_SYMBOL(cpu_to_node);
-
-/*
- * Same function as cpu_to_node() but used if called before the
- * per_cpu areas are setup.
- */
-int early_cpu_to_node(int cpu)
-{
- if (early_per_cpu_ptr(x86_cpu_to_node_map))
- return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
-
- if (!per_cpu_offset(cpu)) {
- printk(KERN_WARNING
- "early_cpu_to_node(%d): no per_cpu area!\n", cpu);
- dump_stack();
- return NUMA_NO_NODE;
- }
- return per_cpu(x86_cpu_to_node_map, cpu);
-}
-
-
-/* empty cpumask */
-static const cpumask_t cpu_mask_none;
-
-/*
- * Returns a pointer to the bitmask of CPUs on Node 'node'.
- */
-const cpumask_t *cpumask_of_node(int node)
-{
- if (node_to_cpumask_map == NULL) {
- printk(KERN_WARNING
- "cpumask_of_node(%d): no node_to_cpumask_map!\n",
- node);
- dump_stack();
- return (const cpumask_t *)&cpu_online_map;
- }
- if (node >= nr_node_ids) {
- printk(KERN_WARNING
- "cpumask_of_node(%d): node > nr_node_ids(%d)\n",
- node, nr_node_ids);
- dump_stack();
- return &cpu_mask_none;
- }
- return &node_to_cpumask_map[node];
-}
-EXPORT_SYMBOL(cpumask_of_node);
-
-/*
- * Returns a bitmask of CPUs on Node 'node'.
- *
- * Side note: this function creates the returned cpumask on the stack
- * so with a high NR_CPUS count, excessive stack space is used. The
- * node_to_cpumask_ptr function should be used whenever possible.
- */
-cpumask_t node_to_cpumask(int node)
-{
- if (node_to_cpumask_map == NULL) {
- printk(KERN_WARNING
- "node_to_cpumask(%d): no node_to_cpumask_map!\n", node);
- dump_stack();
- return cpu_online_map;
- }
- if (node >= nr_node_ids) {
- printk(KERN_WARNING
- "node_to_cpumask(%d): node > nr_node_ids(%d)\n",
- node, nr_node_ids);
- dump_stack();
- return cpu_mask_none;
- }
- return node_to_cpumask_map[node];
-}
-EXPORT_SYMBOL(node_to_cpumask);
-
-/*
- * --------- end of debug versions of the numa functions ---------
- */
-
-#endif /* CONFIG_DEBUG_PER_CPU_MAPS */
-
-#endif /* X86_64_NUMA */
-
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index df0587f..7fc78b0 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -51,24 +51,24 @@
#endif
#define COPY(x) { \
- err |= __get_user(regs->x, &sc->x); \
+ get_user_ex(regs->x, &sc->x); \
}
#define COPY_SEG(seg) { \
unsigned short tmp; \
- err |= __get_user(tmp, &sc->seg); \
+ get_user_ex(tmp, &sc->seg); \
regs->seg = tmp; \
}
#define COPY_SEG_CPL3(seg) { \
unsigned short tmp; \
- err |= __get_user(tmp, &sc->seg); \
+ get_user_ex(tmp, &sc->seg); \
regs->seg = tmp | 3; \
}
#define GET_SEG(seg) { \
unsigned short tmp; \
- err |= __get_user(tmp, &sc->seg); \
+ get_user_ex(tmp, &sc->seg); \
loadsegment(seg, tmp); \
}
@@ -83,45 +83,49 @@
/* Always make any pending restarted system calls return -EINTR */
current_thread_info()->restart_block.fn = do_no_restart_syscall;
+ get_user_try {
+
#ifdef CONFIG_X86_32
- GET_SEG(gs);
- COPY_SEG(fs);
- COPY_SEG(es);
- COPY_SEG(ds);
+ GET_SEG(gs);
+ COPY_SEG(fs);
+ COPY_SEG(es);
+ COPY_SEG(ds);
#endif /* CONFIG_X86_32 */
- COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx);
- COPY(dx); COPY(cx); COPY(ip);
+ COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx);
+ COPY(dx); COPY(cx); COPY(ip);
#ifdef CONFIG_X86_64
- COPY(r8);
- COPY(r9);
- COPY(r10);
- COPY(r11);
- COPY(r12);
- COPY(r13);
- COPY(r14);
- COPY(r15);
+ COPY(r8);
+ COPY(r9);
+ COPY(r10);
+ COPY(r11);
+ COPY(r12);
+ COPY(r13);
+ COPY(r14);
+ COPY(r15);
#endif /* CONFIG_X86_64 */
#ifdef CONFIG_X86_32
- COPY_SEG_CPL3(cs);
- COPY_SEG_CPL3(ss);
+ COPY_SEG_CPL3(cs);
+ COPY_SEG_CPL3(ss);
#else /* !CONFIG_X86_32 */
- /* Kernel saves and restores only the CS segment register on signals,
- * which is the bare minimum needed to allow mixed 32/64-bit code.
- * App's signal handler can save/restore other segments if needed. */
- COPY_SEG_CPL3(cs);
+ /* Kernel saves and restores only the CS segment register on signals,
+ * which is the bare minimum needed to allow mixed 32/64-bit code.
+ * App's signal handler can save/restore other segments if needed. */
+ COPY_SEG_CPL3(cs);
#endif /* CONFIG_X86_32 */
- err |= __get_user(tmpflags, &sc->flags);
- regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
- regs->orig_ax = -1; /* disable syscall checks */
+ get_user_ex(tmpflags, &sc->flags);
+ regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
+ regs->orig_ax = -1; /* disable syscall checks */
- err |= __get_user(buf, &sc->fpstate);
- err |= restore_i387_xstate(buf);
+ get_user_ex(buf, &sc->fpstate);
+ err |= restore_i387_xstate(buf);
- err |= __get_user(*pax, &sc->ax);
+ get_user_ex(*pax, &sc->ax);
+ } get_user_catch(err);
+
return err;
}
@@ -131,57 +135,60 @@
{
int err = 0;
-#ifdef CONFIG_X86_32
- {
- unsigned int tmp;
+ put_user_try {
- savesegment(gs, tmp);
- err |= __put_user(tmp, (unsigned int __user *)&sc->gs);
- }
- err |= __put_user(regs->fs, (unsigned int __user *)&sc->fs);
- err |= __put_user(regs->es, (unsigned int __user *)&sc->es);
- err |= __put_user(regs->ds, (unsigned int __user *)&sc->ds);
+#ifdef CONFIG_X86_32
+ {
+ unsigned int tmp;
+
+ savesegment(gs, tmp);
+ put_user_ex(tmp, (unsigned int __user *)&sc->gs);
+ }
+ put_user_ex(regs->fs, (unsigned int __user *)&sc->fs);
+ put_user_ex(regs->es, (unsigned int __user *)&sc->es);
+ put_user_ex(regs->ds, (unsigned int __user *)&sc->ds);
#endif /* CONFIG_X86_32 */
- err |= __put_user(regs->di, &sc->di);
- err |= __put_user(regs->si, &sc->si);
- err |= __put_user(regs->bp, &sc->bp);
- err |= __put_user(regs->sp, &sc->sp);
- err |= __put_user(regs->bx, &sc->bx);
- err |= __put_user(regs->dx, &sc->dx);
- err |= __put_user(regs->cx, &sc->cx);
- err |= __put_user(regs->ax, &sc->ax);
+ put_user_ex(regs->di, &sc->di);
+ put_user_ex(regs->si, &sc->si);
+ put_user_ex(regs->bp, &sc->bp);
+ put_user_ex(regs->sp, &sc->sp);
+ put_user_ex(regs->bx, &sc->bx);
+ put_user_ex(regs->dx, &sc->dx);
+ put_user_ex(regs->cx, &sc->cx);
+ put_user_ex(regs->ax, &sc->ax);
#ifdef CONFIG_X86_64
- err |= __put_user(regs->r8, &sc->r8);
- err |= __put_user(regs->r9, &sc->r9);
- err |= __put_user(regs->r10, &sc->r10);
- err |= __put_user(regs->r11, &sc->r11);
- err |= __put_user(regs->r12, &sc->r12);
- err |= __put_user(regs->r13, &sc->r13);
- err |= __put_user(regs->r14, &sc->r14);
- err |= __put_user(regs->r15, &sc->r15);
+ put_user_ex(regs->r8, &sc->r8);
+ put_user_ex(regs->r9, &sc->r9);
+ put_user_ex(regs->r10, &sc->r10);
+ put_user_ex(regs->r11, &sc->r11);
+ put_user_ex(regs->r12, &sc->r12);
+ put_user_ex(regs->r13, &sc->r13);
+ put_user_ex(regs->r14, &sc->r14);
+ put_user_ex(regs->r15, &sc->r15);
#endif /* CONFIG_X86_64 */
- err |= __put_user(current->thread.trap_no, &sc->trapno);
- err |= __put_user(current->thread.error_code, &sc->err);
- err |= __put_user(regs->ip, &sc->ip);
+ put_user_ex(current->thread.trap_no, &sc->trapno);
+ put_user_ex(current->thread.error_code, &sc->err);
+ put_user_ex(regs->ip, &sc->ip);
#ifdef CONFIG_X86_32
- err |= __put_user(regs->cs, (unsigned int __user *)&sc->cs);
- err |= __put_user(regs->flags, &sc->flags);
- err |= __put_user(regs->sp, &sc->sp_at_signal);
- err |= __put_user(regs->ss, (unsigned int __user *)&sc->ss);
+ put_user_ex(regs->cs, (unsigned int __user *)&sc->cs);
+ put_user_ex(regs->flags, &sc->flags);
+ put_user_ex(regs->sp, &sc->sp_at_signal);
+ put_user_ex(regs->ss, (unsigned int __user *)&sc->ss);
#else /* !CONFIG_X86_32 */
- err |= __put_user(regs->flags, &sc->flags);
- err |= __put_user(regs->cs, &sc->cs);
- err |= __put_user(0, &sc->gs);
- err |= __put_user(0, &sc->fs);
+ put_user_ex(regs->flags, &sc->flags);
+ put_user_ex(regs->cs, &sc->cs);
+ put_user_ex(0, &sc->gs);
+ put_user_ex(0, &sc->fs);
#endif /* CONFIG_X86_32 */
- err |= __put_user(fpstate, &sc->fpstate);
+ put_user_ex(fpstate, &sc->fpstate);
- /* non-iBCS2 extensions.. */
- err |= __put_user(mask, &sc->oldmask);
- err |= __put_user(current->thread.cr2, &sc->cr2);
+ /* non-iBCS2 extensions.. */
+ put_user_ex(mask, &sc->oldmask);
+ put_user_ex(current->thread.cr2, &sc->cr2);
+ } put_user_catch(err);
return err;
}
@@ -336,43 +343,41 @@
if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
return -EFAULT;
- err |= __put_user(sig, &frame->sig);
- err |= __put_user(&frame->info, &frame->pinfo);
- err |= __put_user(&frame->uc, &frame->puc);
- err |= copy_siginfo_to_user(&frame->info, info);
- if (err)
- return -EFAULT;
+ put_user_try {
+ put_user_ex(sig, &frame->sig);
+ put_user_ex(&frame->info, &frame->pinfo);
+ put_user_ex(&frame->uc, &frame->puc);
+ err |= copy_siginfo_to_user(&frame->info, info);
- /* Create the ucontext. */
- if (cpu_has_xsave)
- err |= __put_user(UC_FP_XSTATE, &frame->uc.uc_flags);
- else
- err |= __put_user(0, &frame->uc.uc_flags);
- err |= __put_user(0, &frame->uc.uc_link);
- err |= __put_user(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
- err |= __put_user(sas_ss_flags(regs->sp),
- &frame->uc.uc_stack.ss_flags);
- err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
- err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
- regs, set->sig[0]);
- err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
- if (err)
- return -EFAULT;
+ /* Create the ucontext. */
+ if (cpu_has_xsave)
+ put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
+ else
+ put_user_ex(0, &frame->uc.uc_flags);
+ put_user_ex(0, &frame->uc.uc_link);
+ put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
+ put_user_ex(sas_ss_flags(regs->sp),
+ &frame->uc.uc_stack.ss_flags);
+ put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
+ err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
+ regs, set->sig[0]);
+ err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
- /* Set up to return from userspace. */
- restorer = VDSO32_SYMBOL(current->mm->context.vdso, rt_sigreturn);
- if (ka->sa.sa_flags & SA_RESTORER)
- restorer = ka->sa.sa_restorer;
- err |= __put_user(restorer, &frame->pretcode);
+ /* Set up to return from userspace. */
+ restorer = VDSO32_SYMBOL(current->mm->context.vdso, rt_sigreturn);
+ if (ka->sa.sa_flags & SA_RESTORER)
+ restorer = ka->sa.sa_restorer;
+ put_user_ex(restorer, &frame->pretcode);
- /*
- * This is movl $__NR_rt_sigreturn, %ax ; int $0x80
- *
- * WE DO NOT USE IT ANY MORE! It's only left here for historical
- * reasons and because gdb uses it as a signature to notice
- * signal handler stack frames.
- */
- err |= __put_user(*((u64 *)&rt_retcode), (u64 *)frame->retcode);
+ /*
+ * This is movl $__NR_rt_sigreturn, %ax ; int $0x80
+ *
+ * WE DO NOT USE IT ANY MORE! It's only left here for historical
+ * reasons and because gdb uses it as a signature to notice
+ * signal handler stack frames.
+ */
+ put_user_ex(*((u64 *)&rt_retcode), (u64 *)frame->retcode);
+ } put_user_catch(err);
if (err)
return -EFAULT;
@@ -436,28 +441,30 @@
return -EFAULT;
}
- /* Create the ucontext. */
- if (cpu_has_xsave)
- err |= __put_user(UC_FP_XSTATE, &frame->uc.uc_flags);
- else
- err |= __put_user(0, &frame->uc.uc_flags);
- err |= __put_user(0, &frame->uc.uc_link);
- err |= __put_user(me->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
- err |= __put_user(sas_ss_flags(regs->sp),
- &frame->uc.uc_stack.ss_flags);
- err |= __put_user(me->sas_ss_size, &frame->uc.uc_stack.ss_size);
- err |= setup_sigcontext(&frame->uc.uc_mcontext, fp, regs, set->sig[0]);
- err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+ put_user_try {
+ /* Create the ucontext. */
+ if (cpu_has_xsave)
+ put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
+ else
+ put_user_ex(0, &frame->uc.uc_flags);
+ put_user_ex(0, &frame->uc.uc_link);
+ put_user_ex(me->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
+ put_user_ex(sas_ss_flags(regs->sp),
+ &frame->uc.uc_stack.ss_flags);
+ put_user_ex(me->sas_ss_size, &frame->uc.uc_stack.ss_size);
+ err |= setup_sigcontext(&frame->uc.uc_mcontext, fp, regs, set->sig[0]);
+ err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
- /* Set up to return from userspace. If provided, use a stub
- already in userspace. */
- /* x86-64 should always use SA_RESTORER. */
- if (ka->sa.sa_flags & SA_RESTORER) {
- err |= __put_user(ka->sa.sa_restorer, &frame->pretcode);
- } else {
- /* could use a vstub here */
- return -EFAULT;
- }
+ /* Set up to return from userspace. If provided, use a stub
+ already in userspace. */
+ /* x86-64 should always use SA_RESTORER. */
+ if (ka->sa.sa_flags & SA_RESTORER) {
+ put_user_ex(ka->sa.sa_restorer, &frame->pretcode);
+ } else {
+ /* could use a vstub here */
+ err |= -EFAULT;
+ }
+ } put_user_catch(err);
if (err)
return -EFAULT;
@@ -509,31 +516,41 @@
struct old_sigaction __user *oact)
{
struct k_sigaction new_ka, old_ka;
- int ret;
+ int ret = 0;
if (act) {
old_sigset_t mask;
- if (!access_ok(VERIFY_READ, act, sizeof(*act)) ||
- __get_user(new_ka.sa.sa_handler, &act->sa_handler) ||
- __get_user(new_ka.sa.sa_restorer, &act->sa_restorer))
+ if (!access_ok(VERIFY_READ, act, sizeof(*act)))
return -EFAULT;
- __get_user(new_ka.sa.sa_flags, &act->sa_flags);
- __get_user(mask, &act->sa_mask);
+ get_user_try {
+ get_user_ex(new_ka.sa.sa_handler, &act->sa_handler);
+ get_user_ex(new_ka.sa.sa_flags, &act->sa_flags);
+ get_user_ex(mask, &act->sa_mask);
+ get_user_ex(new_ka.sa.sa_restorer, &act->sa_restorer);
+ } get_user_catch(ret);
+
+ if (ret)
+ return -EFAULT;
siginitset(&new_ka.sa.sa_mask, mask);
}
ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL);
if (!ret && oact) {
- if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) ||
- __put_user(old_ka.sa.sa_handler, &oact->sa_handler) ||
- __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer))
+ if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)))
return -EFAULT;
- __put_user(old_ka.sa.sa_flags, &oact->sa_flags);
- __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask);
+ put_user_try {
+ put_user_ex(old_ka.sa.sa_handler, &oact->sa_handler);
+ put_user_ex(old_ka.sa.sa_flags, &oact->sa_flags);
+ put_user_ex(old_ka.sa.sa_mask.sig[0], &oact->sa_mask);
+ put_user_ex(old_ka.sa.sa_restorer, &oact->sa_restorer);
+ } put_user_catch(ret);
+
+ if (ret)
+ return -EFAULT;
}
return ret;
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index bb1a3b1..612d3c74 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -53,7 +53,6 @@
#include <asm/nmi.h>
#include <asm/irq.h>
#include <asm/idle.h>
-#include <asm/smp.h>
#include <asm/trampoline.h>
#include <asm/cpu.h>
#include <asm/numa.h>
@@ -63,6 +62,7 @@
#include <asm/vmi.h>
#include <asm/genapic.h>
#include <asm/setup.h>
+#include <asm/uv/uv.h>
#include <linux/mc146818rtc.h>
#include <mach_apic.h>
@@ -745,52 +745,6 @@
complete(&c_idle->done);
}
-#ifdef CONFIG_X86_64
-
-/* __ref because it's safe to call free_bootmem when after_bootmem == 0. */
-static void __ref free_bootmem_pda(struct x8664_pda *oldpda)
-{
- if (!after_bootmem)
- free_bootmem((unsigned long)oldpda, sizeof(*oldpda));
-}
-
-/*
- * Allocate node local memory for the AP pda.
- *
- * Must be called after the _cpu_pda pointer table is initialized.
- */
-int __cpuinit get_local_pda(int cpu)
-{
- struct x8664_pda *oldpda, *newpda;
- unsigned long size = sizeof(struct x8664_pda);
- int node = cpu_to_node(cpu);
-
- if (cpu_pda(cpu) && !cpu_pda(cpu)->in_bootmem)
- return 0;
-
- oldpda = cpu_pda(cpu);
- newpda = kmalloc_node(size, GFP_ATOMIC, node);
- if (!newpda) {
- printk(KERN_ERR "Could not allocate node local PDA "
- "for CPU %d on node %d\n", cpu, node);
-
- if (oldpda)
- return 0; /* have a usable pda */
- else
- return -1;
- }
-
- if (oldpda) {
- memcpy(newpda, oldpda, size);
- free_bootmem_pda(oldpda);
- }
-
- newpda->in_bootmem = 0;
- cpu_pda(cpu) = newpda;
- return 0;
-}
-#endif /* CONFIG_X86_64 */
-
static int __cpuinit do_boot_cpu(int apicid, int cpu)
/*
* NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad
@@ -808,16 +762,6 @@
};
INIT_WORK(&c_idle.work, do_fork_idle);
-#ifdef CONFIG_X86_64
- /* Allocate node local memory for AP pdas */
- if (cpu > 0) {
- boot_error = get_local_pda(cpu);
- if (boot_error)
- goto restore_state;
- /* if can't get pda memory, can't start cpu */
- }
-#endif
-
alternatives_smp_switch(1);
c_idle.idle = get_idle_for_cpu(cpu);
@@ -847,14 +791,16 @@
set_idle_for_cpu(cpu, c_idle.idle);
do_rest:
-#ifdef CONFIG_X86_32
per_cpu(current_task, cpu) = c_idle.idle;
- init_gdt(cpu);
+#ifdef CONFIG_X86_32
/* Stack for startup_32 can be just as for start_secondary onwards */
irq_ctx_init(cpu);
#else
- cpu_pda(cpu)->pcurrent = c_idle.idle;
clear_tsk_thread_flag(c_idle.idle, TIF_FORK);
+ initial_gs = per_cpu_offset(cpu);
+ per_cpu(kernel_stack, cpu) =
+ (unsigned long)task_stack_page(c_idle.idle) -
+ KERNEL_STACK_OFFSET + THREAD_SIZE;
#endif
early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
initial_code = (unsigned long)start_secondary;
@@ -931,9 +877,7 @@
inquire_remote_apic(apicid);
}
}
-#ifdef CONFIG_X86_64
-restore_state:
-#endif
+
if (boot_error) {
/* Try to put things back the way they were before ... */
numa_remove_cpu(cpu); /* was set by numa_add_cpu */
@@ -1125,6 +1069,7 @@
printk(KERN_ERR "... forcing use of dummy APIC emulation."
"(tell your hw vendor)\n");
smpboot_clear_io_apic();
+ disable_ioapic_setup();
return -1;
}
@@ -1240,10 +1185,7 @@
void __init native_smp_prepare_boot_cpu(void)
{
int me = smp_processor_id();
-#ifdef CONFIG_X86_32
- init_gdt(me);
-#endif
- switch_to_new_gdt();
+ switch_to_new_gdt(me);
/* already set me in cpu_online_mask in boot_cpu_init() */
cpumask_set_cpu(me, cpu_callout_mask);
per_cpu(cpu_state, me) = CPU_ONLINE;
diff --git a/arch/x86/kernel/smpcommon.c b/arch/x86/kernel/smpcommon.c
deleted file mode 100644
index 397e309..0000000
--- a/arch/x86/kernel/smpcommon.c
+++ /dev/null
@@ -1,30 +0,0 @@
-/*
- * SMP stuff which is common to all sub-architectures.
- */
-#include <linux/module.h>
-#include <asm/smp.h>
-
-#ifdef CONFIG_X86_32
-DEFINE_PER_CPU(unsigned long, this_cpu_off);
-EXPORT_PER_CPU_SYMBOL(this_cpu_off);
-
-/*
- * Initialize the CPU's GDT. This is either the boot CPU doing itself
- * (still using the master per-cpu area), or a CPU doing it for a
- * secondary which will soon come up.
- */
-__cpuinit void init_gdt(int cpu)
-{
- struct desc_struct gdt;
-
- pack_descriptor(&gdt, __per_cpu_offset[cpu], 0xFFFFF,
- 0x2 | DESCTYPE_S, 0x8);
- gdt.s = 1;
-
- write_gdt_entry(get_cpu_gdt_table(cpu),
- GDT_ENTRY_PERCPU, &gdt, DESCTYPE_S);
-
- per_cpu(this_cpu_off, cpu) = __per_cpu_offset[cpu];
- per_cpu(cpu_number, cpu) = cpu;
-}
-#endif
diff --git a/arch/x86/kernel/tlb_32.c b/arch/x86/kernel/tlb_32.c
deleted file mode 100644
index ce50546..0000000
--- a/arch/x86/kernel/tlb_32.c
+++ /dev/null
@@ -1,256 +0,0 @@
-#include <linux/spinlock.h>
-#include <linux/cpu.h>
-#include <linux/interrupt.h>
-
-#include <asm/tlbflush.h>
-
-DEFINE_PER_CPU(struct tlb_state, cpu_tlbstate)
- ____cacheline_aligned = { &init_mm, 0, };
-
-/* must come after the send_IPI functions above for inlining */
-#include <mach_ipi.h>
-
-/*
- * Smarter SMP flushing macros.
- * c/o Linus Torvalds.
- *
- * These mean you can really definitely utterly forget about
- * writing to user space from interrupts. (Its not allowed anyway).
- *
- * Optimizations Manfred Spraul <manfred@colorfullife.com>
- */
-
-static cpumask_t flush_cpumask;
-static struct mm_struct *flush_mm;
-static unsigned long flush_va;
-static DEFINE_SPINLOCK(tlbstate_lock);
-
-/*
- * We cannot call mmdrop() because we are in interrupt context,
- * instead update mm->cpu_vm_mask.
- *
- * We need to reload %cr3 since the page tables may be going
- * away from under us..
- */
-void leave_mm(int cpu)
-{
- BUG_ON(x86_read_percpu(cpu_tlbstate.state) == TLBSTATE_OK);
- cpu_clear(cpu, x86_read_percpu(cpu_tlbstate.active_mm)->cpu_vm_mask);
- load_cr3(swapper_pg_dir);
-}
-EXPORT_SYMBOL_GPL(leave_mm);
-
-/*
- *
- * The flush IPI assumes that a thread switch happens in this order:
- * [cpu0: the cpu that switches]
- * 1) switch_mm() either 1a) or 1b)
- * 1a) thread switch to a different mm
- * 1a1) cpu_clear(cpu, old_mm->cpu_vm_mask);
- * Stop ipi delivery for the old mm. This is not synchronized with
- * the other cpus, but smp_invalidate_interrupt ignore flush ipis
- * for the wrong mm, and in the worst case we perform a superfluous
- * tlb flush.
- * 1a2) set cpu_tlbstate to TLBSTATE_OK
- * Now the smp_invalidate_interrupt won't call leave_mm if cpu0
- * was in lazy tlb mode.
- * 1a3) update cpu_tlbstate[].active_mm
- * Now cpu0 accepts tlb flushes for the new mm.
- * 1a4) cpu_set(cpu, new_mm->cpu_vm_mask);
- * Now the other cpus will send tlb flush ipis.
- * 1a4) change cr3.
- * 1b) thread switch without mm change
- * cpu_tlbstate[].active_mm is correct, cpu0 already handles
- * flush ipis.
- * 1b1) set cpu_tlbstate to TLBSTATE_OK
- * 1b2) test_and_set the cpu bit in cpu_vm_mask.
- * Atomically set the bit [other cpus will start sending flush ipis],
- * and test the bit.
- * 1b3) if the bit was 0: leave_mm was called, flush the tlb.
- * 2) switch %%esp, ie current
- *
- * The interrupt must handle 2 special cases:
- * - cr3 is changed before %%esp, ie. it cannot use current->{active_,}mm.
- * - the cpu performs speculative tlb reads, i.e. even if the cpu only
- * runs in kernel space, the cpu could load tlb entries for user space
- * pages.
- *
- * The good news is that cpu_tlbstate is local to each cpu, no
- * write/read ordering problems.
- */
-
-/*
- * TLB flush IPI:
- *
- * 1) Flush the tlb entries if the cpu uses the mm that's being flushed.
- * 2) Leave the mm if we are in the lazy tlb mode.
- */
-
-void smp_invalidate_interrupt(struct pt_regs *regs)
-{
- unsigned long cpu;
-
- cpu = get_cpu();
-
- if (!cpu_isset(cpu, flush_cpumask))
- goto out;
- /*
- * This was a BUG() but until someone can quote me the
- * line from the intel manual that guarantees an IPI to
- * multiple CPUs is retried _only_ on the erroring CPUs
- * its staying as a return
- *
- * BUG();
- */
-
- if (flush_mm == x86_read_percpu(cpu_tlbstate.active_mm)) {
- if (x86_read_percpu(cpu_tlbstate.state) == TLBSTATE_OK) {
- if (flush_va == TLB_FLUSH_ALL)
- local_flush_tlb();
- else
- __flush_tlb_one(flush_va);
- } else
- leave_mm(cpu);
- }
- ack_APIC_irq();
- smp_mb__before_clear_bit();
- cpu_clear(cpu, flush_cpumask);
- smp_mb__after_clear_bit();
-out:
- put_cpu_no_resched();
- inc_irq_stat(irq_tlb_count);
-}
-
-void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm,
- unsigned long va)
-{
- cpumask_t cpumask = *cpumaskp;
-
- /*
- * A couple of (to be removed) sanity checks:
- *
- * - current CPU must not be in mask
- * - mask must exist :)
- */
- BUG_ON(cpus_empty(cpumask));
- BUG_ON(cpu_isset(smp_processor_id(), cpumask));
- BUG_ON(!mm);
-
-#ifdef CONFIG_HOTPLUG_CPU
- /* If a CPU which we ran on has gone down, OK. */
- cpus_and(cpumask, cpumask, cpu_online_map);
- if (unlikely(cpus_empty(cpumask)))
- return;
-#endif
-
- /*
- * i'm not happy about this global shared spinlock in the
- * MM hot path, but we'll see how contended it is.
- * AK: x86-64 has a faster method that could be ported.
- */
- spin_lock(&tlbstate_lock);
-
- flush_mm = mm;
- flush_va = va;
- cpus_or(flush_cpumask, cpumask, flush_cpumask);
-
- /*
- * Make the above memory operations globally visible before
- * sending the IPI.
- */
- smp_mb();
- /*
- * We have to send the IPI only to
- * CPUs affected.
- */
- send_IPI_mask(&cpumask, INVALIDATE_TLB_VECTOR);
-
- while (!cpus_empty(flush_cpumask))
- /* nothing. lockup detection does not belong here */
- cpu_relax();
-
- flush_mm = NULL;
- flush_va = 0;
- spin_unlock(&tlbstate_lock);
-}
-
-void flush_tlb_current_task(void)
-{
- struct mm_struct *mm = current->mm;
- cpumask_t cpu_mask;
-
- preempt_disable();
- cpu_mask = mm->cpu_vm_mask;
- cpu_clear(smp_processor_id(), cpu_mask);
-
- local_flush_tlb();
- if (!cpus_empty(cpu_mask))
- flush_tlb_others(cpu_mask, mm, TLB_FLUSH_ALL);
- preempt_enable();
-}
-
-void flush_tlb_mm(struct mm_struct *mm)
-{
- cpumask_t cpu_mask;
-
- preempt_disable();
- cpu_mask = mm->cpu_vm_mask;
- cpu_clear(smp_processor_id(), cpu_mask);
-
- if (current->active_mm == mm) {
- if (current->mm)
- local_flush_tlb();
- else
- leave_mm(smp_processor_id());
- }
- if (!cpus_empty(cpu_mask))
- flush_tlb_others(cpu_mask, mm, TLB_FLUSH_ALL);
-
- preempt_enable();
-}
-
-void flush_tlb_page(struct vm_area_struct *vma, unsigned long va)
-{
- struct mm_struct *mm = vma->vm_mm;
- cpumask_t cpu_mask;
-
- preempt_disable();
- cpu_mask = mm->cpu_vm_mask;
- cpu_clear(smp_processor_id(), cpu_mask);
-
- if (current->active_mm == mm) {
- if (current->mm)
- __flush_tlb_one(va);
- else
- leave_mm(smp_processor_id());
- }
-
- if (!cpus_empty(cpu_mask))
- flush_tlb_others(cpu_mask, mm, va);
-
- preempt_enable();
-}
-EXPORT_SYMBOL(flush_tlb_page);
-
-static void do_flush_tlb_all(void *info)
-{
- unsigned long cpu = smp_processor_id();
-
- __flush_tlb_all();
- if (x86_read_percpu(cpu_tlbstate.state) == TLBSTATE_LAZY)
- leave_mm(cpu);
-}
-
-void flush_tlb_all(void)
-{
- on_each_cpu(do_flush_tlb_all, NULL, 1);
-}
-
-void reset_lazy_tlbstate(void)
-{
- int cpu = raw_smp_processor_id();
-
- per_cpu(cpu_tlbstate, cpu).state = 0;
- per_cpu(cpu_tlbstate, cpu).active_mm = &init_mm;
-}
-
diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
index 6812b82..f4b2f27 100644
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -11,6 +11,7 @@
#include <linux/kernel.h>
#include <asm/mmu_context.h>
+#include <asm/uv/uv.h>
#include <asm/uv/uv_mmrs.h>
#include <asm/uv/uv_hub.h>
#include <asm/uv/uv_bau.h>
@@ -210,14 +211,15 @@
*
* Send a broadcast and wait for a broadcast message to complete.
*
- * The cpumaskp mask contains the cpus the broadcast was sent to.
+ * The flush_mask contains the cpus the broadcast was sent to.
*
- * Returns 1 if all remote flushing was done. The mask is zeroed.
- * Returns 0 if some remote flushing remains to be done. The mask is left
- * unchanged.
+ * Returns NULL if all remote flushing was done. The mask is zeroed.
+ * Returns @flush_mask if some remote flushing remains to be done. The
+ * mask will have some bits still set.
*/
-int uv_flush_send_and_wait(int cpu, int this_blade, struct bau_desc *bau_desc,
- cpumask_t *cpumaskp)
+const struct cpumask *uv_flush_send_and_wait(int cpu, int this_blade,
+ struct bau_desc *bau_desc,
+ struct cpumask *flush_mask)
{
int completion_status = 0;
int right_shift;
@@ -257,66 +259,76 @@
* the cpu's, all of which are still in the mask.
*/
__get_cpu_var(ptcstats).ptc_i++;
- return 0;
+ return flush_mask;
}
/*
* Success, so clear the remote cpu's from the mask so we don't
* use the IPI method of shootdown on them.
*/
- for_each_cpu_mask(bit, *cpumaskp) {
+ for_each_cpu(bit, flush_mask) {
blade = uv_cpu_to_blade_id(bit);
if (blade == this_blade)
continue;
- cpu_clear(bit, *cpumaskp);
+ cpumask_clear_cpu(bit, flush_mask);
}
- if (!cpus_empty(*cpumaskp))
- return 0;
- return 1;
+ if (!cpumask_empty(flush_mask))
+ return flush_mask;
+ return NULL;
}
/**
* uv_flush_tlb_others - globally purge translation cache of a virtual
* address or all TLB's
- * @cpumaskp: mask of all cpu's in which the address is to be removed
+ * @cpumask: mask of all cpu's in which the address is to be removed
* @mm: mm_struct containing virtual address range
* @va: virtual address to be removed (or TLB_FLUSH_ALL for all TLB's on cpu)
+ * @cpu: the current cpu
*
* This is the entry point for initiating any UV global TLB shootdown.
*
* Purges the translation caches of all specified processors of the given
* virtual address, or purges all TLB's on specified processors.
*
- * The caller has derived the cpumaskp from the mm_struct and has subtracted
- * the local cpu from the mask. This function is called only if there
- * are bits set in the mask. (e.g. flush_tlb_page())
+ * The caller has derived the cpumask from the mm_struct. This function
+ * is called only if there are bits set in the mask. (e.g. flush_tlb_page())
*
- * The cpumaskp is converted into a nodemask of the nodes containing
+ * The cpumask is converted into a nodemask of the nodes containing
* the cpus.
*
- * Returns 1 if all remote flushing was done.
- * Returns 0 if some remote flushing remains to be done.
+ * Note that this function should be called with preemption disabled.
+ *
+ * Returns NULL if all remote flushing was done.
+ * Returns pointer to cpumask if some remote flushing remains to be
+ * done. The returned pointer is valid till preemption is re-enabled.
*/
-int uv_flush_tlb_others(cpumask_t *cpumaskp, struct mm_struct *mm,
- unsigned long va)
+const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
+ struct mm_struct *mm,
+ unsigned long va, unsigned int cpu)
{
+ static DEFINE_PER_CPU(cpumask_t, flush_tlb_mask);
+ struct cpumask *flush_mask = &__get_cpu_var(flush_tlb_mask);
int i;
int bit;
int blade;
- int cpu;
+ int uv_cpu;
int this_blade;
int locals = 0;
struct bau_desc *bau_desc;
- cpu = uv_blade_processor_id();
+ WARN_ON(!in_atomic());
+
+ cpumask_andnot(flush_mask, cpumask, cpumask_of(cpu));
+
+ uv_cpu = uv_blade_processor_id();
this_blade = uv_numa_blade_id();
bau_desc = __get_cpu_var(bau_control).descriptor_base;
- bau_desc += UV_ITEMS_PER_DESCRIPTOR * cpu;
+ bau_desc += UV_ITEMS_PER_DESCRIPTOR * uv_cpu;
bau_nodes_clear(&bau_desc->distribution, UV_DISTRIBUTION_SIZE);
i = 0;
- for_each_cpu_mask(bit, *cpumaskp) {
+ for_each_cpu(bit, flush_mask) {
blade = uv_cpu_to_blade_id(bit);
BUG_ON(blade > (UV_DISTRIBUTION_SIZE - 1));
if (blade == this_blade) {
@@ -331,17 +343,17 @@
* no off_node flushing; return status for local node
*/
if (locals)
- return 0;
+ return flush_mask;
else
- return 1;
+ return NULL;
}
__get_cpu_var(ptcstats).requestor++;
__get_cpu_var(ptcstats).ntargeted += i;
bau_desc->payload.address = va;
- bau_desc->payload.sending_cpu = smp_processor_id();
+ bau_desc->payload.sending_cpu = cpu;
- return uv_flush_send_and_wait(cpu, this_blade, bau_desc, cpumaskp);
+ return uv_flush_send_and_wait(uv_cpu, this_blade, bau_desc, flush_mask);
}
/*
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 7932338..3b7b2e1 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -59,7 +59,6 @@
#ifdef CONFIG_X86_64
#include <asm/pgalloc.h>
#include <asm/proto.h>
-#include <asm/pda.h>
#else
#include <asm/processor-flags.h>
#include <asm/arch_hooks.h>
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index bef58b4..f052c84 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -680,10 +680,11 @@
para_fill(pv_mmu_ops.write_cr2, SetCR2);
para_fill(pv_mmu_ops.write_cr3, SetCR3);
para_fill(pv_cpu_ops.write_cr4, SetCR4);
- para_fill(pv_irq_ops.save_fl, GetInterruptMask);
- para_fill(pv_irq_ops.restore_fl, SetInterruptMask);
- para_fill(pv_irq_ops.irq_disable, DisableInterrupts);
- para_fill(pv_irq_ops.irq_enable, EnableInterrupts);
+
+ para_fill(pv_irq_ops.save_fl.func, GetInterruptMask);
+ para_fill(pv_irq_ops.restore_fl.func, SetInterruptMask);
+ para_fill(pv_irq_ops.irq_disable.func, DisableInterrupts);
+ para_fill(pv_irq_ops.irq_enable.func, EnableInterrupts);
para_fill(pv_cpu_ops.wbinvd, WBINVD);
para_fill(pv_cpu_ops.read_tsc, RDTSC);
diff --git a/arch/x86/kernel/vmlinux_32.lds.S b/arch/x86/kernel/vmlinux_32.lds.S
index 82c6755..3eba7f7 100644
--- a/arch/x86/kernel/vmlinux_32.lds.S
+++ b/arch/x86/kernel/vmlinux_32.lds.S
@@ -178,14 +178,7 @@
__initramfs_end = .;
}
#endif
- . = ALIGN(PAGE_SIZE);
- .data.percpu : AT(ADDR(.data.percpu) - LOAD_OFFSET) {
- __per_cpu_start = .;
- *(.data.percpu.page_aligned)
- *(.data.percpu)
- *(.data.percpu.shared_aligned)
- __per_cpu_end = .;
- }
+ PERCPU(PAGE_SIZE)
. = ALIGN(PAGE_SIZE);
/* freed after init ends here */
diff --git a/arch/x86/kernel/vmlinux_64.lds.S b/arch/x86/kernel/vmlinux_64.lds.S
index 1a614c0..087a7f2 100644
--- a/arch/x86/kernel/vmlinux_64.lds.S
+++ b/arch/x86/kernel/vmlinux_64.lds.S
@@ -5,6 +5,7 @@
#define LOAD_OFFSET __START_KERNEL_map
#include <asm-generic/vmlinux.lds.h>
+#include <asm/asm-offsets.h>
#include <asm/page.h>
#undef i386 /* in case the preprocessor is a 32bit one */
@@ -13,12 +14,15 @@
OUTPUT_ARCH(i386:x86-64)
ENTRY(phys_startup_64)
jiffies_64 = jiffies;
-_proxy_pda = 1;
PHDRS {
text PT_LOAD FLAGS(5); /* R_E */
data PT_LOAD FLAGS(7); /* RWE */
user PT_LOAD FLAGS(7); /* RWE */
data.init PT_LOAD FLAGS(7); /* RWE */
+#ifdef CONFIG_SMP
+ percpu PT_LOAD FLAGS(7); /* RWE */
+#endif
+ data.init2 PT_LOAD FLAGS(7); /* RWE */
note PT_NOTE FLAGS(0); /* ___ */
}
SECTIONS
@@ -208,14 +212,28 @@
__initramfs_end = .;
#endif
+#ifdef CONFIG_SMP
+ /*
+ * percpu offsets are zero-based on SMP. PERCPU_VADDR() changes the
+ * output PHDR, so the next output section - __data_nosave - should
+ * start another section data.init2. Also, pda should be at the head of
+ * percpu area. Preallocate it and define the percpu offset symbol
+ * so that it can be accessed as a percpu variable.
+ */
+ . = ALIGN(PAGE_SIZE);
+ PERCPU_VADDR(0, :percpu)
+#else
PERCPU(PAGE_SIZE)
+#endif
. = ALIGN(PAGE_SIZE);
__init_end = .;
. = ALIGN(PAGE_SIZE);
__nosave_begin = .;
- .data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) { *(.data.nosave) }
+ .data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
+ *(.data.nosave)
+ } :data.init2 /* use another section data.init2, see PERCPU_VADDR() above */
. = ALIGN(PAGE_SIZE);
__nosave_end = .;
@@ -239,8 +257,21 @@
DWARF_DEBUG
}
+ /*
+ * Per-cpu symbols which need to be offset from __per_cpu_load
+ * for the boot processor.
+ */
+#define INIT_PER_CPU(x) init_per_cpu__##x = per_cpu__##x + __per_cpu_load
+INIT_PER_CPU(gdt_page);
+INIT_PER_CPU(irq_stack_union);
+
/*
* Build-time check on the image size:
*/
ASSERT((_end - _text <= KERNEL_IMAGE_SIZE),
"kernel image bigger than KERNEL_IMAGE_SIZE")
+
+#ifdef CONFIG_SMP
+ASSERT((per_cpu__irq_stack_union == 0),
+ "irq_stack_union is not at start of per-cpu area");
+#endif
diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c
index a688f3b..c609205 100644
--- a/arch/x86/kernel/vsmp_64.c
+++ b/arch/x86/kernel/vsmp_64.c
@@ -37,6 +37,7 @@
flags &= ~X86_EFLAGS_IF;
return flags;
}
+PV_CALLEE_SAVE_REGS_THUNK(vsmp_save_fl);
static void vsmp_restore_fl(unsigned long flags)
{
@@ -46,6 +47,7 @@
flags |= X86_EFLAGS_AC;
native_restore_fl(flags);
}
+PV_CALLEE_SAVE_REGS_THUNK(vsmp_restore_fl);
static void vsmp_irq_disable(void)
{
@@ -53,6 +55,7 @@
native_restore_fl((flags & ~X86_EFLAGS_IF) | X86_EFLAGS_AC);
}
+PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_disable);
static void vsmp_irq_enable(void)
{
@@ -60,6 +63,7 @@
native_restore_fl((flags | X86_EFLAGS_IF) & (~X86_EFLAGS_AC));
}
+PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_enable);
static unsigned __init_or_module vsmp_patch(u8 type, u16 clobbers, void *ibuf,
unsigned long addr, unsigned len)
@@ -90,10 +94,10 @@
cap, ctl);
if (cap & ctl & (1 << 4)) {
/* Setup irq ops and turn on vSMP IRQ fastpath handling */
- pv_irq_ops.irq_disable = vsmp_irq_disable;
- pv_irq_ops.irq_enable = vsmp_irq_enable;
- pv_irq_ops.save_fl = vsmp_save_fl;
- pv_irq_ops.restore_fl = vsmp_restore_fl;
+ pv_irq_ops.irq_disable = PV_CALLEE_SAVE(vsmp_irq_disable);
+ pv_irq_ops.irq_enable = PV_CALLEE_SAVE(vsmp_irq_enable);
+ pv_irq_ops.save_fl = PV_CALLEE_SAVE(vsmp_save_fl);
+ pv_irq_ops.restore_fl = PV_CALLEE_SAVE(vsmp_restore_fl);
pv_init_ops.patch = vsmp_patch;
ctl &= ~(1 << 4);
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
index 695e426..3909e3b 100644
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -58,5 +58,3 @@
EXPORT_SYMBOL(empty_zero_page);
EXPORT_SYMBOL(init_level4_pgt);
EXPORT_SYMBOL(load_gs_index);
-
-EXPORT_SYMBOL(_proxy_pda);
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 92f1c6f..19e33b6 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -173,24 +173,29 @@
{
return lguest_data.irq_enabled;
}
+PV_CALLEE_SAVE_REGS_THUNK(save_fl);
/* restore_flags() just sets the flags back to the value given. */
static void restore_fl(unsigned long flags)
{
lguest_data.irq_enabled = flags;
}
+PV_CALLEE_SAVE_REGS_THUNK(restore_fl);
/* Interrupts go off... */
static void irq_disable(void)
{
lguest_data.irq_enabled = 0;
}
+PV_CALLEE_SAVE_REGS_THUNK(irq_disable);
/* Interrupts go on... */
static void irq_enable(void)
{
lguest_data.irq_enabled = X86_EFLAGS_IF;
}
+PV_CALLEE_SAVE_REGS_THUNK(irq_enable);
+
/*:*/
/*M:003 Note that we don't check for outstanding interrupts when we re-enable
* them (or when we unmask an interrupt). This seems to work for the moment,
@@ -984,10 +989,10 @@
/* interrupt-related operations */
pv_irq_ops.init_IRQ = lguest_init_IRQ;
- pv_irq_ops.save_fl = save_fl;
- pv_irq_ops.restore_fl = restore_fl;
- pv_irq_ops.irq_disable = irq_disable;
- pv_irq_ops.irq_enable = irq_enable;
+ pv_irq_ops.save_fl = PV_CALLEE_SAVE(save_fl);
+ pv_irq_ops.restore_fl = PV_CALLEE_SAVE(restore_fl);
+ pv_irq_ops.irq_disable = PV_CALLEE_SAVE(irq_disable);
+ pv_irq_ops.irq_enable = PV_CALLEE_SAVE(irq_enable);
pv_irq_ops.safe_halt = lguest_safe_halt;
/* init-time operations */
diff --git a/arch/x86/mach-voyager/setup.c b/arch/x86/mach-voyager/setup.c
index d914a79..66b7eb5 100644
--- a/arch/x86/mach-voyager/setup.c
+++ b/arch/x86/mach-voyager/setup.c
@@ -9,6 +9,7 @@
#include <asm/e820.h>
#include <asm/io.h>
#include <asm/setup.h>
+#include <asm/cpu.h>
void __init pre_intr_init_hook(void)
{
diff --git a/arch/x86/mach-voyager/voyager_smp.c b/arch/x86/mach-voyager/voyager_smp.c
index 7ffcdee..6f5a38c 100644
--- a/arch/x86/mach-voyager/voyager_smp.c
+++ b/arch/x86/mach-voyager/voyager_smp.c
@@ -400,7 +400,7 @@
VOYAGER_SUS_IN_CONTROL_PORT);
current_thread_info()->cpu = boot_cpu_id;
- x86_write_percpu(cpu_number, boot_cpu_id);
+ percpu_write(cpu_number, boot_cpu_id);
}
/*
@@ -528,7 +528,6 @@
/* init_tasks (in sched.c) is indexed logically */
stack_start.sp = (void *)idle->thread.sp;
- init_gdt(cpu);
per_cpu(current_task, cpu) = idle;
early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
irq_ctx_init(cpu);
@@ -1745,14 +1744,13 @@
static void __cpuinit voyager_smp_prepare_boot_cpu(void)
{
- init_gdt(smp_processor_id());
- switch_to_new_gdt();
+ int cpu = smp_processor_id();
+ switch_to_new_gdt(cpu);
cpu_online_map = cpumask_of_cpu(smp_processor_id());
cpu_callout_map = cpumask_of_cpu(smp_processor_id());
cpu_callin_map = CPU_MASK_NONE;
cpu_present_map = cpumask_of_cpu(smp_processor_id());
-
}
static int __cpuinit voyager_cpu_up(unsigned int cpu)
@@ -1779,7 +1777,6 @@
void __init smp_setup_processor_id(void)
{
current_thread_info()->cpu = hard_smp_processor_id();
- x86_write_percpu(cpu_number, hard_smp_processor_id());
}
static void voyager_send_call_func(const struct cpumask *callmask)
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index d8cc96a2..9f051572 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -1,6 +1,8 @@
obj-y := init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
pat.o pgtable.o gup.o
+obj-$(CONFIG_X86_SMP) += tlb.o
+
obj-$(CONFIG_X86_32) += pgtable_32.o iomap_32.o
obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 7e8db53..61b41ca 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -23,6 +23,12 @@
fixup = search_exception_tables(regs->ip);
if (fixup) {
+ /* If fixup is less than 16, it means uaccess error */
+ if (fixup->fixup < 16) {
+ current_thread_info()->uaccess_err = -EFAULT;
+ regs->ip += fixup->fixup;
+ return 1;
+ }
regs->ip = fixup->fixup;
return 1;
}
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 90dfae5..8c3f311 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -26,6 +26,7 @@
#include <linux/kprobes.h>
#include <linux/uaccess.h>
#include <linux/kdebug.h>
+#include <linux/magic.h>
#include <asm/system.h>
#include <asm/desc.h>
@@ -91,8 +92,8 @@
*
* Opcode checker based on code by Richard Brunner
*/
-static int is_prefetch(struct pt_regs *regs, unsigned long addr,
- unsigned long error_code)
+static int is_prefetch(struct pt_regs *regs, unsigned long error_code,
+ unsigned long addr)
{
unsigned char *instr;
int scan_more = 1;
@@ -409,15 +410,15 @@
}
#ifdef CONFIG_X86_64
-static noinline void pgtable_bad(unsigned long address, struct pt_regs *regs,
- unsigned long error_code)
+static noinline void pgtable_bad(struct pt_regs *regs,
+ unsigned long error_code, unsigned long address)
{
unsigned long flags = oops_begin();
int sig = SIGKILL;
- struct task_struct *tsk;
+ struct task_struct *tsk = current;
printk(KERN_ALERT "%s: Corrupted page table at address %lx\n",
- current->comm, address);
+ tsk->comm, address);
dump_pagetable(address);
tsk = current;
tsk->thread.cr2 = address;
@@ -429,6 +430,196 @@
}
#endif
+static noinline void no_context(struct pt_regs *regs,
+ unsigned long error_code, unsigned long address)
+{
+ struct task_struct *tsk = current;
+ unsigned long *stackend;
+
+#ifdef CONFIG_X86_64
+ unsigned long flags;
+ int sig;
+#endif
+
+ /* Are we prepared to handle this kernel fault? */
+ if (fixup_exception(regs))
+ return;
+
+ /*
+ * X86_32
+ * Valid to do another page fault here, because if this fault
+ * had been triggered by is_prefetch fixup_exception would have
+ * handled it.
+ *
+ * X86_64
+ * Hall of shame of CPU/BIOS bugs.
+ */
+ if (is_prefetch(regs, error_code, address))
+ return;
+
+ if (is_errata93(regs, address))
+ return;
+
+ /*
+ * Oops. The kernel tried to access some bad page. We'll have to
+ * terminate things with extreme prejudice.
+ */
+#ifdef CONFIG_X86_32
+ bust_spinlocks(1);
+#else
+ flags = oops_begin();
+#endif
+
+ show_fault_oops(regs, error_code, address);
+
+ stackend = end_of_stack(tsk);
+ if (*stackend != STACK_END_MAGIC)
+ printk(KERN_ALERT "Thread overran stack, or stack corrupted\n");
+
+ tsk->thread.cr2 = address;
+ tsk->thread.trap_no = 14;
+ tsk->thread.error_code = error_code;
+
+#ifdef CONFIG_X86_32
+ die("Oops", regs, error_code);
+ bust_spinlocks(0);
+ do_exit(SIGKILL);
+#else
+ sig = SIGKILL;
+ if (__die("Oops", regs, error_code))
+ sig = 0;
+ /* Executive summary in case the body of the oops scrolled away */
+ printk(KERN_EMERG "CR2: %016lx\n", address);
+ oops_end(flags, regs, sig);
+#endif
+}
+
+static void __bad_area_nosemaphore(struct pt_regs *regs,
+ unsigned long error_code, unsigned long address,
+ int si_code)
+{
+ struct task_struct *tsk = current;
+
+ /* User mode accesses just cause a SIGSEGV */
+ if (error_code & PF_USER) {
+ /*
+ * It's possible to have interrupts off here.
+ */
+ local_irq_enable();
+
+ /*
+ * Valid to do another page fault here because this one came
+ * from user space.
+ */
+ if (is_prefetch(regs, error_code, address))
+ return;
+
+ if (is_errata100(regs, address))
+ return;
+
+ if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) &&
+ printk_ratelimit()) {
+ printk(
+ "%s%s[%d]: segfault at %lx ip %p sp %p error %lx",
+ task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
+ tsk->comm, task_pid_nr(tsk), address,
+ (void *) regs->ip, (void *) regs->sp, error_code);
+ print_vma_addr(" in ", regs->ip);
+ printk("\n");
+ }
+
+ tsk->thread.cr2 = address;
+ /* Kernel addresses are always protection faults */
+ tsk->thread.error_code = error_code | (address >= TASK_SIZE);
+ tsk->thread.trap_no = 14;
+ force_sig_info_fault(SIGSEGV, si_code, address, tsk);
+ return;
+ }
+
+ if (is_f00f_bug(regs, address))
+ return;
+
+ no_context(regs, error_code, address);
+}
+
+static noinline void bad_area_nosemaphore(struct pt_regs *regs,
+ unsigned long error_code, unsigned long address)
+{
+ __bad_area_nosemaphore(regs, error_code, address, SEGV_MAPERR);
+}
+
+static void __bad_area(struct pt_regs *regs,
+ unsigned long error_code, unsigned long address,
+ int si_code)
+{
+ struct mm_struct *mm = current->mm;
+
+ /*
+ * Something tried to access memory that isn't in our memory map..
+ * Fix it, but check if it's kernel or user first..
+ */
+ up_read(&mm->mmap_sem);
+
+ __bad_area_nosemaphore(regs, error_code, address, si_code);
+}
+
+static noinline void bad_area(struct pt_regs *regs,
+ unsigned long error_code, unsigned long address)
+{
+ __bad_area(regs, error_code, address, SEGV_MAPERR);
+}
+
+static noinline void bad_area_access_error(struct pt_regs *regs,
+ unsigned long error_code, unsigned long address)
+{
+ __bad_area(regs, error_code, address, SEGV_ACCERR);
+}
+
+/* TODO: fixup for "mm-invoke-oom-killer-from-page-fault.patch" */
+static void out_of_memory(struct pt_regs *regs,
+ unsigned long error_code, unsigned long address)
+{
+ /*
+ * We ran out of memory, call the OOM killer, and return the userspace
+ * (which will retry the fault, or kill us if we got oom-killed).
+ */
+ up_read(¤t->mm->mmap_sem);
+ pagefault_out_of_memory();
+}
+
+static void do_sigbus(struct pt_regs *regs,
+ unsigned long error_code, unsigned long address)
+{
+ struct task_struct *tsk = current;
+ struct mm_struct *mm = tsk->mm;
+
+ up_read(&mm->mmap_sem);
+
+ /* Kernel mode? Handle exceptions or die */
+ if (!(error_code & PF_USER))
+ no_context(regs, error_code, address);
+#ifdef CONFIG_X86_32
+ /* User space => ok to do another page fault */
+ if (is_prefetch(regs, error_code, address))
+ return;
+#endif
+ tsk->thread.cr2 = address;
+ tsk->thread.error_code = error_code;
+ tsk->thread.trap_no = 14;
+ force_sig_info_fault(SIGBUS, BUS_ADRERR, address, tsk);
+}
+
+static noinline void mm_fault_error(struct pt_regs *regs,
+ unsigned long error_code, unsigned long address, unsigned int fault)
+{
+ if (fault & VM_FAULT_OOM)
+ out_of_memory(regs, error_code, address);
+ else if (fault & VM_FAULT_SIGBUS)
+ do_sigbus(regs, error_code, address);
+ else
+ BUG();
+}
+
static int spurious_fault_check(unsigned long error_code, pte_t *pte)
{
if ((error_code & PF_WRITE) && !pte_write(*pte))
@@ -448,8 +639,8 @@
* There are no security implications to leaving a stale TLB when
* increasing the permissions on a page.
*/
-static int spurious_fault(unsigned long address,
- unsigned long error_code)
+static noinline int spurious_fault(unsigned long error_code,
+ unsigned long address)
{
pgd_t *pgd;
pud_t *pud;
@@ -494,7 +685,7 @@
*
* This assumes no large pages in there.
*/
-static int vmalloc_fault(unsigned long address)
+static noinline int vmalloc_fault(unsigned long address)
{
#ifdef CONFIG_X86_32
unsigned long pgd_paddr;
@@ -573,6 +764,25 @@
int show_unhandled_signals = 1;
+static inline int access_error(unsigned long error_code, int write,
+ struct vm_area_struct *vma)
+{
+ if (write) {
+ /* write, present and write, not present */
+ if (unlikely(!(vma->vm_flags & VM_WRITE)))
+ return 1;
+ } else if (unlikely(error_code & PF_PROT)) {
+ /* read, present */
+ return 1;
+ } else {
+ /* read, not present */
+ if (unlikely(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))))
+ return 1;
+ }
+
+ return 0;
+}
+
/*
* This routine handles page faults. It determines the address,
* and the problem, and then passes it off to one of the appropriate
@@ -583,16 +793,12 @@
#endif
void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
{
+ unsigned long address;
struct task_struct *tsk;
struct mm_struct *mm;
struct vm_area_struct *vma;
- unsigned long address;
- int write, si_code;
+ int write;
int fault;
-#ifdef CONFIG_X86_64
- unsigned long flags;
- int sig;
-#endif
tsk = current;
mm = tsk->mm;
@@ -601,10 +807,6 @@
/* get the address */
address = read_cr2();
- si_code = SEGV_MAPERR;
-
- if (notify_page_fault(regs))
- return;
if (unlikely(kmmio_fault(regs, address)))
return;
@@ -631,17 +833,22 @@
return;
/* Can handle a stale RO->RW TLB */
- if (spurious_fault(address, error_code))
+ if (spurious_fault(error_code, address))
return;
+ /* kprobes don't want to hook the spurious faults. */
+ if (notify_page_fault(regs))
+ return;
/*
* Don't take the mm semaphore here. If we fixup a prefetch
* fault we could otherwise deadlock.
*/
- goto bad_area_nosemaphore;
+ bad_area_nosemaphore(regs, error_code, address);
+ return;
}
-
+ if (unlikely(notify_page_fault(regs)))
+ return;
/*
* It's safe to allow irq's after cr2 has been saved and the
* vmalloc fault has been handled.
@@ -657,15 +864,17 @@
#ifdef CONFIG_X86_64
if (unlikely(error_code & PF_RSVD))
- pgtable_bad(address, regs, error_code);
+ pgtable_bad(regs, error_code, address);
#endif
/*
* If we're in an interrupt, have no user context or are running in an
* atomic region then we must not take the fault.
*/
- if (unlikely(in_atomic() || !mm))
- goto bad_area_nosemaphore;
+ if (unlikely(in_atomic() || !mm)) {
+ bad_area_nosemaphore(regs, error_code, address);
+ return;
+ }
/*
* When running in the kernel we expect faults to occur only to
@@ -683,20 +892,26 @@
* source. If this is invalid we can skip the address space check,
* thus avoiding the deadlock.
*/
- if (!down_read_trylock(&mm->mmap_sem)) {
+ if (unlikely(!down_read_trylock(&mm->mmap_sem))) {
if ((error_code & PF_USER) == 0 &&
- !search_exception_tables(regs->ip))
- goto bad_area_nosemaphore;
+ !search_exception_tables(regs->ip)) {
+ bad_area_nosemaphore(regs, error_code, address);
+ return;
+ }
down_read(&mm->mmap_sem);
}
vma = find_vma(mm, address);
- if (!vma)
- goto bad_area;
- if (vma->vm_start <= address)
+ if (unlikely(!vma)) {
+ bad_area(regs, error_code, address);
+ return;
+ }
+ if (likely(vma->vm_start <= address))
goto good_area;
- if (!(vma->vm_flags & VM_GROWSDOWN))
- goto bad_area;
+ if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) {
+ bad_area(regs, error_code, address);
+ return;
+ }
if (error_code & PF_USER) {
/*
* Accessing the stack below %sp is always a bug.
@@ -704,31 +919,25 @@
* and pusha to work. ("enter $65535,$31" pushes
* 32 pointers and then decrements %sp by 65535.)
*/
- if (address + 65536 + 32 * sizeof(unsigned long) < regs->sp)
- goto bad_area;
+ if (unlikely(address + 65536 + 32 * sizeof(unsigned long) < regs->sp)) {
+ bad_area(regs, error_code, address);
+ return;
+ }
}
- if (expand_stack(vma, address))
- goto bad_area;
-/*
- * Ok, we have a good vm_area for this memory access, so
- * we can handle it..
- */
+ if (unlikely(expand_stack(vma, address))) {
+ bad_area(regs, error_code, address);
+ return;
+ }
+
+ /*
+ * Ok, we have a good vm_area for this memory access, so
+ * we can handle it..
+ */
good_area:
- si_code = SEGV_ACCERR;
- write = 0;
- switch (error_code & (PF_PROT|PF_WRITE)) {
- default: /* 3: write, present */
- /* fall through */
- case PF_WRITE: /* write, not present */
- if (!(vma->vm_flags & VM_WRITE))
- goto bad_area;
- write++;
- break;
- case PF_PROT: /* read, present */
- goto bad_area;
- case 0: /* read, not present */
- if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
- goto bad_area;
+ write = error_code & PF_WRITE;
+ if (unlikely(access_error(error_code, write, vma))) {
+ bad_area_access_error(regs, error_code, address);
+ return;
}
/*
@@ -738,11 +947,8 @@
*/
fault = handle_mm_fault(mm, vma, address, write);
if (unlikely(fault & VM_FAULT_ERROR)) {
- if (fault & VM_FAULT_OOM)
- goto out_of_memory;
- else if (fault & VM_FAULT_SIGBUS)
- goto do_sigbus;
- BUG();
+ mm_fault_error(regs, error_code, address, fault);
+ return;
}
if (fault & VM_FAULT_MAJOR)
tsk->maj_flt++;
@@ -760,128 +966,6 @@
}
#endif
up_read(&mm->mmap_sem);
- return;
-
-/*
- * Something tried to access memory that isn't in our memory map..
- * Fix it, but check if it's kernel or user first..
- */
-bad_area:
- up_read(&mm->mmap_sem);
-
-bad_area_nosemaphore:
- /* User mode accesses just cause a SIGSEGV */
- if (error_code & PF_USER) {
- /*
- * It's possible to have interrupts off here.
- */
- local_irq_enable();
-
- /*
- * Valid to do another page fault here because this one came
- * from user space.
- */
- if (is_prefetch(regs, address, error_code))
- return;
-
- if (is_errata100(regs, address))
- return;
-
- if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) &&
- printk_ratelimit()) {
- printk(
- "%s%s[%d]: segfault at %lx ip %p sp %p error %lx",
- task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
- tsk->comm, task_pid_nr(tsk), address,
- (void *) regs->ip, (void *) regs->sp, error_code);
- print_vma_addr(" in ", regs->ip);
- printk("\n");
- }
-
- tsk->thread.cr2 = address;
- /* Kernel addresses are always protection faults */
- tsk->thread.error_code = error_code | (address >= TASK_SIZE);
- tsk->thread.trap_no = 14;
- force_sig_info_fault(SIGSEGV, si_code, address, tsk);
- return;
- }
-
- if (is_f00f_bug(regs, address))
- return;
-
-no_context:
- /* Are we prepared to handle this kernel fault? */
- if (fixup_exception(regs))
- return;
-
- /*
- * X86_32
- * Valid to do another page fault here, because if this fault
- * had been triggered by is_prefetch fixup_exception would have
- * handled it.
- *
- * X86_64
- * Hall of shame of CPU/BIOS bugs.
- */
- if (is_prefetch(regs, address, error_code))
- return;
-
- if (is_errata93(regs, address))
- return;
-
-/*
- * Oops. The kernel tried to access some bad page. We'll have to
- * terminate things with extreme prejudice.
- */
-#ifdef CONFIG_X86_32
- bust_spinlocks(1);
-#else
- flags = oops_begin();
-#endif
-
- show_fault_oops(regs, error_code, address);
-
- tsk->thread.cr2 = address;
- tsk->thread.trap_no = 14;
- tsk->thread.error_code = error_code;
-
-#ifdef CONFIG_X86_32
- die("Oops", regs, error_code);
- bust_spinlocks(0);
- do_exit(SIGKILL);
-#else
- sig = SIGKILL;
- if (__die("Oops", regs, error_code))
- sig = 0;
- /* Executive summary in case the body of the oops scrolled away */
- printk(KERN_EMERG "CR2: %016lx\n", address);
- oops_end(flags, regs, sig);
-#endif
-
-out_of_memory:
- /*
- * We ran out of memory, call the OOM killer, and return the userspace
- * (which will retry the fault, or kill us if we got oom-killed).
- */
- up_read(&mm->mmap_sem);
- pagefault_out_of_memory();
- return;
-
-do_sigbus:
- up_read(&mm->mmap_sem);
-
- /* Kernel mode? Handle exceptions or die */
- if (!(error_code & PF_USER))
- goto no_context;
-#ifdef CONFIG_X86_32
- /* User space => ok to do another page fault */
- if (is_prefetch(regs, address, error_code))
- return;
-#endif
- tsk->thread.cr2 = address;
- tsk->thread.error_code = error_code;
- tsk->thread.trap_no = 14;
- force_sig_info_fault(SIGBUS, BUS_ADRERR, address, tsk);
}
DEFINE_SPINLOCK(pgd_lock);
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 2cef050..00263bf 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -49,7 +49,6 @@
#include <asm/paravirt.h>
#include <asm/setup.h>
#include <asm/cacheflush.h>
-#include <asm/smp.h>
unsigned int __VMALLOC_RESERVE = 128 << 20;
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 71a14f8..deb1c1a 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -20,6 +20,12 @@
#include <asm/acpi.h>
#include <asm/k8.h>
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+# define DBG(x...) printk(KERN_DEBUG x)
+#else
+# define DBG(x...)
+#endif
+
struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
EXPORT_SYMBOL(node_data);
@@ -33,6 +39,21 @@
static unsigned long __initdata nodemap_addr;
static unsigned long __initdata nodemap_size;
+DEFINE_PER_CPU(int, node_number) = 0;
+EXPORT_PER_CPU_SYMBOL(node_number);
+
+/*
+ * Map cpu index to node index
+ */
+DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE);
+EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map);
+
+/*
+ * Which logical CPUs are on which nodes
+ */
+cpumask_t *node_to_cpumask_map;
+EXPORT_SYMBOL(node_to_cpumask_map);
+
/*
* Given a shift value, try to populate memnodemap[]
* Returns :
@@ -640,3 +661,199 @@
#endif
+/*
+ * Allocate node_to_cpumask_map based on number of available nodes
+ * Requires node_possible_map to be valid.
+ *
+ * Note: node_to_cpumask() is not valid until after this is done.
+ * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.)
+ */
+void __init setup_node_to_cpumask_map(void)
+{
+ unsigned int node, num = 0;
+ cpumask_t *map;
+
+ /* setup nr_node_ids if not done yet */
+ if (nr_node_ids == MAX_NUMNODES) {
+ for_each_node_mask(node, node_possible_map)
+ num = node;
+ nr_node_ids = num + 1;
+ }
+
+ /* allocate the map */
+ map = alloc_bootmem_low(nr_node_ids * sizeof(cpumask_t));
+ DBG("node_to_cpumask_map at %p for %d nodes\n", map, nr_node_ids);
+
+ pr_debug("Node to cpumask map at %p for %d nodes\n",
+ map, nr_node_ids);
+
+ /* node_to_cpumask() will now work */
+ node_to_cpumask_map = map;
+}
+
+void __cpuinit numa_set_node(int cpu, int node)
+{
+ int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map);
+
+ /* early setting, no percpu area yet */
+ if (cpu_to_node_map) {
+ cpu_to_node_map[cpu] = node;
+ return;
+ }
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+ if (cpu >= nr_cpu_ids || !cpu_possible(cpu)) {
+ printk(KERN_ERR "numa_set_node: invalid cpu# (%d)\n", cpu);
+ dump_stack();
+ return;
+ }
+#endif
+ per_cpu(x86_cpu_to_node_map, cpu) = node;
+
+ if (node != NUMA_NO_NODE)
+ per_cpu(node_number, cpu) = node;
+}
+
+void __cpuinit numa_clear_node(int cpu)
+{
+ numa_set_node(cpu, NUMA_NO_NODE);
+}
+
+#ifndef CONFIG_DEBUG_PER_CPU_MAPS
+
+void __cpuinit numa_add_cpu(int cpu)
+{
+ cpu_set(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
+}
+
+void __cpuinit numa_remove_cpu(int cpu)
+{
+ cpu_clear(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
+}
+
+#else /* CONFIG_DEBUG_PER_CPU_MAPS */
+
+/*
+ * --------- debug versions of the numa functions ---------
+ */
+static void __cpuinit numa_set_cpumask(int cpu, int enable)
+{
+ int node = early_cpu_to_node(cpu);
+ cpumask_t *mask;
+ char buf[64];
+
+ if (node_to_cpumask_map == NULL) {
+ printk(KERN_ERR "node_to_cpumask_map NULL\n");
+ dump_stack();
+ return;
+ }
+
+ mask = &node_to_cpumask_map[node];
+ if (enable)
+ cpu_set(cpu, *mask);
+ else
+ cpu_clear(cpu, *mask);
+
+ cpulist_scnprintf(buf, sizeof(buf), mask);
+ printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n",
+ enable ? "numa_add_cpu" : "numa_remove_cpu", cpu, node, buf);
+}
+
+void __cpuinit numa_add_cpu(int cpu)
+{
+ numa_set_cpumask(cpu, 1);
+}
+
+void __cpuinit numa_remove_cpu(int cpu)
+{
+ numa_set_cpumask(cpu, 0);
+}
+
+int cpu_to_node(int cpu)
+{
+ if (early_per_cpu_ptr(x86_cpu_to_node_map)) {
+ printk(KERN_WARNING
+ "cpu_to_node(%d): usage too early!\n", cpu);
+ dump_stack();
+ return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
+ }
+ return per_cpu(x86_cpu_to_node_map, cpu);
+}
+EXPORT_SYMBOL(cpu_to_node);
+
+/*
+ * Same function as cpu_to_node() but used if called before the
+ * per_cpu areas are setup.
+ */
+int early_cpu_to_node(int cpu)
+{
+ if (early_per_cpu_ptr(x86_cpu_to_node_map))
+ return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
+
+ if (!cpu_possible(cpu)) {
+ printk(KERN_WARNING
+ "early_cpu_to_node(%d): no per_cpu area!\n", cpu);
+ dump_stack();
+ return NUMA_NO_NODE;
+ }
+ return per_cpu(x86_cpu_to_node_map, cpu);
+}
+
+
+/* empty cpumask */
+static const cpumask_t cpu_mask_none;
+
+/*
+ * Returns a pointer to the bitmask of CPUs on Node 'node'.
+ */
+const cpumask_t *cpumask_of_node(int node)
+{
+ if (node_to_cpumask_map == NULL) {
+ printk(KERN_WARNING
+ "cpumask_of_node(%d): no node_to_cpumask_map!\n",
+ node);
+ dump_stack();
+ return (const cpumask_t *)&cpu_online_map;
+ }
+ if (node >= nr_node_ids) {
+ printk(KERN_WARNING
+ "cpumask_of_node(%d): node > nr_node_ids(%d)\n",
+ node, nr_node_ids);
+ dump_stack();
+ return &cpu_mask_none;
+ }
+ return &node_to_cpumask_map[node];
+}
+EXPORT_SYMBOL(cpumask_of_node);
+
+/*
+ * Returns a bitmask of CPUs on Node 'node'.
+ *
+ * Side note: this function creates the returned cpumask on the stack
+ * so with a high NR_CPUS count, excessive stack space is used. The
+ * node_to_cpumask_ptr function should be used whenever possible.
+ */
+cpumask_t node_to_cpumask(int node)
+{
+ if (node_to_cpumask_map == NULL) {
+ printk(KERN_WARNING
+ "node_to_cpumask(%d): no node_to_cpumask_map!\n", node);
+ dump_stack();
+ return cpu_online_map;
+ }
+ if (node >= nr_node_ids) {
+ printk(KERN_WARNING
+ "node_to_cpumask(%d): node > nr_node_ids(%d)\n",
+ node, nr_node_ids);
+ dump_stack();
+ return cpu_mask_none;
+ }
+ return node_to_cpumask_map[node];
+}
+EXPORT_SYMBOL(node_to_cpumask);
+
+/*
+ * --------- end of debug versions of the numa functions ---------
+ */
+
+#endif /* CONFIG_DEBUG_PER_CPU_MAPS */
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index 09737c8..15df1bae 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -21,6 +21,7 @@
#include <asm/numa.h>
#include <asm/e820.h>
#include <asm/genapic.h>
+#include <asm/uv/uv.h>
int acpi_numa __initdata;
diff --git a/arch/x86/kernel/tlb_64.c b/arch/x86/mm/tlb.c
similarity index 67%
rename from arch/x86/kernel/tlb_64.c
rename to arch/x86/mm/tlb.c
index f8be6f1..72a6d4e 100644
--- a/arch/x86/kernel/tlb_64.c
+++ b/arch/x86/mm/tlb.c
@@ -1,22 +1,18 @@
#include <linux/init.h>
#include <linux/mm.h>
-#include <linux/delay.h>
#include <linux/spinlock.h>
#include <linux/smp.h>
-#include <linux/kernel_stat.h>
-#include <linux/mc146818rtc.h>
#include <linux/interrupt.h>
+#include <linux/module.h>
-#include <asm/mtrr.h>
-#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
-#include <asm/proto.h>
-#include <asm/apicdef.h>
-#include <asm/idle.h>
-#include <asm/uv/uv_hub.h>
-#include <asm/uv/uv_bau.h>
+#include <asm/apic.h>
+#include <asm/uv/uv.h>
+
+DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate)
+ = { &init_mm, 0, };
#include <mach_ipi.h>
/*
@@ -33,7 +29,7 @@
* To avoid global state use 8 different call vectors.
* Each CPU uses a specific vector to trigger flushes on other
* CPUs. Depending on the received vector the target CPUs look into
- * the right per cpu variable for the flush data.
+ * the right array slot for the flush data.
*
* With more than 8 CPUs they are hashed to the 8 available
* vectors. The limited global vector space forces us to this right now.
@@ -43,18 +39,18 @@
union smp_flush_state {
struct {
- cpumask_t flush_cpumask;
struct mm_struct *flush_mm;
unsigned long flush_va;
spinlock_t tlbstate_lock;
+ DECLARE_BITMAP(flush_cpumask, NR_CPUS);
};
- char pad[SMP_CACHE_BYTES];
-} ____cacheline_aligned;
+ char pad[CONFIG_X86_INTERNODE_CACHE_BYTES];
+} ____cacheline_internodealigned_in_smp;
/* State is put into the per CPU data section, but padded
to a full cache line because other CPUs can access it and we don't
want false sharing in the per cpu data segment. */
-static DEFINE_PER_CPU(union smp_flush_state, flush_state);
+static union smp_flush_state flush_state[NUM_INVALIDATE_TLB_VECTORS];
/*
* We cannot call mmdrop() because we are in interrupt context,
@@ -62,9 +58,9 @@
*/
void leave_mm(int cpu)
{
- if (read_pda(mmu_state) == TLBSTATE_OK)
+ if (percpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
BUG();
- cpu_clear(cpu, read_pda(active_mm)->cpu_vm_mask);
+ cpu_clear(cpu, percpu_read(cpu_tlbstate.active_mm)->cpu_vm_mask);
load_cr3(swapper_pg_dir);
}
EXPORT_SYMBOL_GPL(leave_mm);
@@ -117,10 +113,20 @@
* Interrupts are disabled.
*/
-asmlinkage void smp_invalidate_interrupt(struct pt_regs *regs)
+/*
+ * FIXME: use of asmlinkage is not consistent. On x86_64 it's noop
+ * but still used for documentation purpose but the usage is slightly
+ * inconsistent. On x86_32, asmlinkage is regparm(0) but interrupt
+ * entry calls in with the first parameter in %eax. Maybe define
+ * intrlinkage?
+ */
+#ifdef CONFIG_X86_64
+asmlinkage
+#endif
+void smp_invalidate_interrupt(struct pt_regs *regs)
{
- int cpu;
- int sender;
+ unsigned int cpu;
+ unsigned int sender;
union smp_flush_state *f;
cpu = smp_processor_id();
@@ -129,9 +135,9 @@
* Use that to determine where the sender put the data.
*/
sender = ~regs->orig_ax - INVALIDATE_TLB_VECTOR_START;
- f = &per_cpu(flush_state, sender);
+ f = &flush_state[sender];
- if (!cpu_isset(cpu, f->flush_cpumask))
+ if (!cpumask_test_cpu(cpu, to_cpumask(f->flush_cpumask)))
goto out;
/*
* This was a BUG() but until someone can quote me the
@@ -142,8 +148,8 @@
* BUG();
*/
- if (f->flush_mm == read_pda(active_mm)) {
- if (read_pda(mmu_state) == TLBSTATE_OK) {
+ if (f->flush_mm == percpu_read(cpu_tlbstate.active_mm)) {
+ if (percpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
if (f->flush_va == TLB_FLUSH_ALL)
local_flush_tlb();
else
@@ -153,23 +159,21 @@
}
out:
ack_APIC_irq();
- cpu_clear(cpu, f->flush_cpumask);
+ smp_mb__before_clear_bit();
+ cpumask_clear_cpu(cpu, to_cpumask(f->flush_cpumask));
+ smp_mb__after_clear_bit();
inc_irq_stat(irq_tlb_count);
}
-void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm,
- unsigned long va)
+static void flush_tlb_others_ipi(const struct cpumask *cpumask,
+ struct mm_struct *mm, unsigned long va)
{
- int sender;
+ unsigned int sender;
union smp_flush_state *f;
- cpumask_t cpumask = *cpumaskp;
-
- if (is_uv_system() && uv_flush_tlb_others(&cpumask, mm, va))
- return;
/* Caller has disabled preemption */
sender = smp_processor_id() % NUM_INVALIDATE_TLB_VECTORS;
- f = &per_cpu(flush_state, sender);
+ f = &flush_state[sender];
/*
* Could avoid this lock when
@@ -180,7 +184,8 @@
f->flush_mm = mm;
f->flush_va = va;
- cpus_or(f->flush_cpumask, cpumask, f->flush_cpumask);
+ cpumask_andnot(to_cpumask(f->flush_cpumask),
+ cpumask, cpumask_of(smp_processor_id()));
/*
* Make the above memory operations globally visible before
@@ -191,9 +196,10 @@
* We have to send the IPI only to
* CPUs affected.
*/
- send_IPI_mask(&cpumask, INVALIDATE_TLB_VECTOR_START + sender);
+ send_IPI_mask(to_cpumask(f->flush_cpumask),
+ INVALIDATE_TLB_VECTOR_START + sender);
- while (!cpus_empty(f->flush_cpumask))
+ while (!cpumask_empty(to_cpumask(f->flush_cpumask)))
cpu_relax();
f->flush_mm = NULL;
@@ -201,12 +207,28 @@
spin_unlock(&f->tlbstate_lock);
}
+void native_flush_tlb_others(const struct cpumask *cpumask,
+ struct mm_struct *mm, unsigned long va)
+{
+ if (is_uv_system()) {
+ unsigned int cpu;
+
+ cpu = get_cpu();
+ cpumask = uv_flush_tlb_others(cpumask, mm, va, cpu);
+ if (cpumask)
+ flush_tlb_others_ipi(cpumask, mm, va);
+ put_cpu();
+ return;
+ }
+ flush_tlb_others_ipi(cpumask, mm, va);
+}
+
static int __cpuinit init_smp_flush(void)
{
int i;
- for_each_possible_cpu(i)
- spin_lock_init(&per_cpu(flush_state, i).tlbstate_lock);
+ for (i = 0; i < ARRAY_SIZE(flush_state); i++)
+ spin_lock_init(&flush_state[i].tlbstate_lock);
return 0;
}
@@ -215,25 +237,18 @@
void flush_tlb_current_task(void)
{
struct mm_struct *mm = current->mm;
- cpumask_t cpu_mask;
preempt_disable();
- cpu_mask = mm->cpu_vm_mask;
- cpu_clear(smp_processor_id(), cpu_mask);
local_flush_tlb();
- if (!cpus_empty(cpu_mask))
- flush_tlb_others(cpu_mask, mm, TLB_FLUSH_ALL);
+ if (cpumask_any_but(&mm->cpu_vm_mask, smp_processor_id()) < nr_cpu_ids)
+ flush_tlb_others(&mm->cpu_vm_mask, mm, TLB_FLUSH_ALL);
preempt_enable();
}
void flush_tlb_mm(struct mm_struct *mm)
{
- cpumask_t cpu_mask;
-
preempt_disable();
- cpu_mask = mm->cpu_vm_mask;
- cpu_clear(smp_processor_id(), cpu_mask);
if (current->active_mm == mm) {
if (current->mm)
@@ -241,8 +256,8 @@
else
leave_mm(smp_processor_id());
}
- if (!cpus_empty(cpu_mask))
- flush_tlb_others(cpu_mask, mm, TLB_FLUSH_ALL);
+ if (cpumask_any_but(&mm->cpu_vm_mask, smp_processor_id()) < nr_cpu_ids)
+ flush_tlb_others(&mm->cpu_vm_mask, mm, TLB_FLUSH_ALL);
preempt_enable();
}
@@ -250,11 +265,8 @@
void flush_tlb_page(struct vm_area_struct *vma, unsigned long va)
{
struct mm_struct *mm = vma->vm_mm;
- cpumask_t cpu_mask;
preempt_disable();
- cpu_mask = mm->cpu_vm_mask;
- cpu_clear(smp_processor_id(), cpu_mask);
if (current->active_mm == mm) {
if (current->mm)
@@ -263,8 +275,8 @@
leave_mm(smp_processor_id());
}
- if (!cpus_empty(cpu_mask))
- flush_tlb_others(cpu_mask, mm, va);
+ if (cpumask_any_but(&mm->cpu_vm_mask, smp_processor_id()) < nr_cpu_ids)
+ flush_tlb_others(&mm->cpu_vm_mask, mm, va);
preempt_enable();
}
@@ -274,7 +286,7 @@
unsigned long cpu = smp_processor_id();
__flush_tlb_all();
- if (read_pda(mmu_state) == TLBSTATE_LAZY)
+ if (percpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY)
leave_mm(cpu);
}
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 6dcefba..3b767d0 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -6,7 +6,8 @@
endif
obj-y := enlighten.o setup.o multicalls.o mmu.o irq.o \
- time.o xen-asm_$(BITS).o grant-table.o suspend.o
+ time.o xen-asm.o xen-asm_$(BITS).o \
+ grant-table.o suspend.o
obj-$(CONFIG_SMP) += smp.o spinlock.o
obj-$(CONFIG_XEN_DEBUG_FS) += debugfs.o
\ No newline at end of file
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index bea2152..3723034 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -61,40 +61,13 @@
enum xen_domain_type xen_domain_type = XEN_NATIVE;
EXPORT_SYMBOL_GPL(xen_domain_type);
-/*
- * Identity map, in addition to plain kernel map. This needs to be
- * large enough to allocate page table pages to allocate the rest.
- * Each page can map 2MB.
- */
-static pte_t level1_ident_pgt[PTRS_PER_PTE * 4] __page_aligned_bss;
-
-#ifdef CONFIG_X86_64
-/* l3 pud for userspace vsyscall mapping */
-static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss;
-#endif /* CONFIG_X86_64 */
-
-/*
- * Note about cr3 (pagetable base) values:
- *
- * xen_cr3 contains the current logical cr3 value; it contains the
- * last set cr3. This may not be the current effective cr3, because
- * its update may be being lazily deferred. However, a vcpu looking
- * at its own cr3 can use this value knowing that it everything will
- * be self-consistent.
- *
- * xen_current_cr3 contains the actual vcpu cr3; it is set once the
- * hypercall to set the vcpu cr3 is complete (so it may be a little
- * out of date, but it will never be set early). If one vcpu is
- * looking at another vcpu's cr3 value, it should use this variable.
- */
-DEFINE_PER_CPU(unsigned long, xen_cr3); /* cr3 stored as physaddr */
-DEFINE_PER_CPU(unsigned long, xen_current_cr3); /* actual vcpu cr3 */
-
struct start_info *xen_start_info;
EXPORT_SYMBOL_GPL(xen_start_info);
struct shared_info xen_dummy_shared_info;
+void *xen_initial_gdt;
+
/*
* Point at some empty memory to start with. We map the real shared_info
* page as soon as fixmap is up and running.
@@ -114,14 +87,7 @@
*
* 0: not available, 1: available
*/
-static int have_vcpu_info_placement =
-#ifdef CONFIG_X86_32
- 1
-#else
- 0
-#endif
- ;
-
+static int have_vcpu_info_placement = 1;
static void xen_vcpu_setup(int cpu)
{
@@ -237,7 +203,7 @@
return HYPERVISOR_get_debugreg(reg);
}
-static void xen_leave_lazy(void)
+void xen_leave_lazy(void)
{
paravirt_leave_lazy(paravirt_get_lazy_mode());
xen_mc_flush();
@@ -598,83 +564,6 @@
#endif
-static void xen_flush_tlb(void)
-{
- struct mmuext_op *op;
- struct multicall_space mcs;
-
- preempt_disable();
-
- mcs = xen_mc_entry(sizeof(*op));
-
- op = mcs.args;
- op->cmd = MMUEXT_TLB_FLUSH_LOCAL;
- MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
-
- xen_mc_issue(PARAVIRT_LAZY_MMU);
-
- preempt_enable();
-}
-
-static void xen_flush_tlb_single(unsigned long addr)
-{
- struct mmuext_op *op;
- struct multicall_space mcs;
-
- preempt_disable();
-
- mcs = xen_mc_entry(sizeof(*op));
- op = mcs.args;
- op->cmd = MMUEXT_INVLPG_LOCAL;
- op->arg1.linear_addr = addr & PAGE_MASK;
- MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
-
- xen_mc_issue(PARAVIRT_LAZY_MMU);
-
- preempt_enable();
-}
-
-static void xen_flush_tlb_others(const cpumask_t *cpus, struct mm_struct *mm,
- unsigned long va)
-{
- struct {
- struct mmuext_op op;
- cpumask_t mask;
- } *args;
- cpumask_t cpumask = *cpus;
- struct multicall_space mcs;
-
- /*
- * A couple of (to be removed) sanity checks:
- *
- * - current CPU must not be in mask
- * - mask must exist :)
- */
- BUG_ON(cpus_empty(cpumask));
- BUG_ON(cpu_isset(smp_processor_id(), cpumask));
- BUG_ON(!mm);
-
- /* If a CPU which we ran on has gone down, OK. */
- cpus_and(cpumask, cpumask, cpu_online_map);
- if (cpus_empty(cpumask))
- return;
-
- mcs = xen_mc_entry(sizeof(*args));
- args = mcs.args;
- args->mask = cpumask;
- args->op.arg2.vcpumask = &args->mask;
-
- if (va == TLB_FLUSH_ALL) {
- args->op.cmd = MMUEXT_TLB_FLUSH_MULTI;
- } else {
- args->op.cmd = MMUEXT_INVLPG_MULTI;
- args->op.arg1.linear_addr = va;
- }
-
- MULTI_mmuext_op(mcs.mc, &args->op, 1, NULL, DOMID_SELF);
-
- xen_mc_issue(PARAVIRT_LAZY_MMU);
-}
static void xen_clts(void)
{
@@ -700,21 +589,6 @@
xen_mc_issue(PARAVIRT_LAZY_CPU);
}
-static void xen_write_cr2(unsigned long cr2)
-{
- x86_read_percpu(xen_vcpu)->arch.cr2 = cr2;
-}
-
-static unsigned long xen_read_cr2(void)
-{
- return x86_read_percpu(xen_vcpu)->arch.cr2;
-}
-
-static unsigned long xen_read_cr2_direct(void)
-{
- return x86_read_percpu(xen_vcpu_info.arch.cr2);
-}
-
static void xen_write_cr4(unsigned long cr4)
{
cr4 &= ~X86_CR4_PGE;
@@ -723,71 +597,6 @@
native_write_cr4(cr4);
}
-static unsigned long xen_read_cr3(void)
-{
- return x86_read_percpu(xen_cr3);
-}
-
-static void set_current_cr3(void *v)
-{
- x86_write_percpu(xen_current_cr3, (unsigned long)v);
-}
-
-static void __xen_write_cr3(bool kernel, unsigned long cr3)
-{
- struct mmuext_op *op;
- struct multicall_space mcs;
- unsigned long mfn;
-
- if (cr3)
- mfn = pfn_to_mfn(PFN_DOWN(cr3));
- else
- mfn = 0;
-
- WARN_ON(mfn == 0 && kernel);
-
- mcs = __xen_mc_entry(sizeof(*op));
-
- op = mcs.args;
- op->cmd = kernel ? MMUEXT_NEW_BASEPTR : MMUEXT_NEW_USER_BASEPTR;
- op->arg1.mfn = mfn;
-
- MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
-
- if (kernel) {
- x86_write_percpu(xen_cr3, cr3);
-
- /* Update xen_current_cr3 once the batch has actually
- been submitted. */
- xen_mc_callback(set_current_cr3, (void *)cr3);
- }
-}
-
-static void xen_write_cr3(unsigned long cr3)
-{
- BUG_ON(preemptible());
-
- xen_mc_batch(); /* disables interrupts */
-
- /* Update while interrupts are disabled, so its atomic with
- respect to ipis */
- x86_write_percpu(xen_cr3, cr3);
-
- __xen_write_cr3(true, cr3);
-
-#ifdef CONFIG_X86_64
- {
- pgd_t *user_pgd = xen_get_user_pgd(__va(cr3));
- if (user_pgd)
- __xen_write_cr3(false, __pa(user_pgd));
- else
- __xen_write_cr3(false, 0);
- }
-#endif
-
- xen_mc_issue(PARAVIRT_LAZY_CPU); /* interrupts restored */
-}
-
static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
{
int ret;
@@ -829,185 +638,6 @@
return ret;
}
-/* Early in boot, while setting up the initial pagetable, assume
- everything is pinned. */
-static __init void xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn)
-{
-#ifdef CONFIG_FLATMEM
- BUG_ON(mem_map); /* should only be used early */
-#endif
- make_lowmem_page_readonly(__va(PFN_PHYS(pfn)));
-}
-
-/* Early release_pte assumes that all pts are pinned, since there's
- only init_mm and anything attached to that is pinned. */
-static void xen_release_pte_init(unsigned long pfn)
-{
- make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
-}
-
-static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
-{
- struct mmuext_op op;
- op.cmd = cmd;
- op.arg1.mfn = pfn_to_mfn(pfn);
- if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF))
- BUG();
-}
-
-/* This needs to make sure the new pte page is pinned iff its being
- attached to a pinned pagetable. */
-static void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn, unsigned level)
-{
- struct page *page = pfn_to_page(pfn);
-
- if (PagePinned(virt_to_page(mm->pgd))) {
- SetPagePinned(page);
-
- vm_unmap_aliases();
- if (!PageHighMem(page)) {
- make_lowmem_page_readonly(__va(PFN_PHYS((unsigned long)pfn)));
- if (level == PT_PTE && USE_SPLIT_PTLOCKS)
- pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
- } else {
- /* make sure there are no stray mappings of
- this page */
- kmap_flush_unused();
- }
- }
-}
-
-static void xen_alloc_pte(struct mm_struct *mm, unsigned long pfn)
-{
- xen_alloc_ptpage(mm, pfn, PT_PTE);
-}
-
-static void xen_alloc_pmd(struct mm_struct *mm, unsigned long pfn)
-{
- xen_alloc_ptpage(mm, pfn, PT_PMD);
-}
-
-static int xen_pgd_alloc(struct mm_struct *mm)
-{
- pgd_t *pgd = mm->pgd;
- int ret = 0;
-
- BUG_ON(PagePinned(virt_to_page(pgd)));
-
-#ifdef CONFIG_X86_64
- {
- struct page *page = virt_to_page(pgd);
- pgd_t *user_pgd;
-
- BUG_ON(page->private != 0);
-
- ret = -ENOMEM;
-
- user_pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
- page->private = (unsigned long)user_pgd;
-
- if (user_pgd != NULL) {
- user_pgd[pgd_index(VSYSCALL_START)] =
- __pgd(__pa(level3_user_vsyscall) | _PAGE_TABLE);
- ret = 0;
- }
-
- BUG_ON(PagePinned(virt_to_page(xen_get_user_pgd(pgd))));
- }
-#endif
-
- return ret;
-}
-
-static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
-{
-#ifdef CONFIG_X86_64
- pgd_t *user_pgd = xen_get_user_pgd(pgd);
-
- if (user_pgd)
- free_page((unsigned long)user_pgd);
-#endif
-}
-
-/* This should never happen until we're OK to use struct page */
-static void xen_release_ptpage(unsigned long pfn, unsigned level)
-{
- struct page *page = pfn_to_page(pfn);
-
- if (PagePinned(page)) {
- if (!PageHighMem(page)) {
- if (level == PT_PTE && USE_SPLIT_PTLOCKS)
- pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
- make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
- }
- ClearPagePinned(page);
- }
-}
-
-static void xen_release_pte(unsigned long pfn)
-{
- xen_release_ptpage(pfn, PT_PTE);
-}
-
-static void xen_release_pmd(unsigned long pfn)
-{
- xen_release_ptpage(pfn, PT_PMD);
-}
-
-#if PAGETABLE_LEVELS == 4
-static void xen_alloc_pud(struct mm_struct *mm, unsigned long pfn)
-{
- xen_alloc_ptpage(mm, pfn, PT_PUD);
-}
-
-static void xen_release_pud(unsigned long pfn)
-{
- xen_release_ptpage(pfn, PT_PUD);
-}
-#endif
-
-#ifdef CONFIG_HIGHPTE
-static void *xen_kmap_atomic_pte(struct page *page, enum km_type type)
-{
- pgprot_t prot = PAGE_KERNEL;
-
- if (PagePinned(page))
- prot = PAGE_KERNEL_RO;
-
- if (0 && PageHighMem(page))
- printk("mapping highpte %lx type %d prot %s\n",
- page_to_pfn(page), type,
- (unsigned long)pgprot_val(prot) & _PAGE_RW ? "WRITE" : "READ");
-
- return kmap_atomic_prot(page, type, prot);
-}
-#endif
-
-#ifdef CONFIG_X86_32
-static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
-{
- /* If there's an existing pte, then don't allow _PAGE_RW to be set */
- if (pte_val_ma(*ptep) & _PAGE_PRESENT)
- pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) &
- pte_val_ma(pte));
-
- return pte;
-}
-
-/* Init-time set_pte while constructing initial pagetables, which
- doesn't allow RO pagetable pages to be remapped RW */
-static __init void xen_set_pte_init(pte_t *ptep, pte_t pte)
-{
- pte = mask_rw_pte(ptep, pte);
-
- xen_set_pte(ptep, pte);
-}
-#endif
-
-static __init void xen_pagetable_setup_start(pgd_t *base)
-{
-}
-
void xen_setup_shared_info(void)
{
if (!xen_feature(XENFEAT_auto_translated_physmap)) {
@@ -1028,37 +658,6 @@
xen_setup_mfn_list_list();
}
-static __init void xen_pagetable_setup_done(pgd_t *base)
-{
- xen_setup_shared_info();
-}
-
-static __init void xen_post_allocator_init(void)
-{
- pv_mmu_ops.set_pte = xen_set_pte;
- pv_mmu_ops.set_pmd = xen_set_pmd;
- pv_mmu_ops.set_pud = xen_set_pud;
-#if PAGETABLE_LEVELS == 4
- pv_mmu_ops.set_pgd = xen_set_pgd;
-#endif
-
- /* This will work as long as patching hasn't happened yet
- (which it hasn't) */
- pv_mmu_ops.alloc_pte = xen_alloc_pte;
- pv_mmu_ops.alloc_pmd = xen_alloc_pmd;
- pv_mmu_ops.release_pte = xen_release_pte;
- pv_mmu_ops.release_pmd = xen_release_pmd;
-#if PAGETABLE_LEVELS == 4
- pv_mmu_ops.alloc_pud = xen_alloc_pud;
- pv_mmu_ops.release_pud = xen_release_pud;
-#endif
-
-#ifdef CONFIG_X86_64
- SetPagePinned(virt_to_page(level3_user_vsyscall));
-#endif
- xen_mark_init_mm_pinned();
-}
-
/* This is called once we have the cpu_possible_map */
void xen_setup_vcpu_info_placement(void)
{
@@ -1072,10 +671,10 @@
if (have_vcpu_info_placement) {
printk(KERN_INFO "Xen: using vcpu_info placement\n");
- pv_irq_ops.save_fl = xen_save_fl_direct;
- pv_irq_ops.restore_fl = xen_restore_fl_direct;
- pv_irq_ops.irq_disable = xen_irq_disable_direct;
- pv_irq_ops.irq_enable = xen_irq_enable_direct;
+ pv_irq_ops.save_fl = __PV_IS_CALLEE_SAVE(xen_save_fl_direct);
+ pv_irq_ops.restore_fl = __PV_IS_CALLEE_SAVE(xen_restore_fl_direct);
+ pv_irq_ops.irq_disable = __PV_IS_CALLEE_SAVE(xen_irq_disable_direct);
+ pv_irq_ops.irq_enable = __PV_IS_CALLEE_SAVE(xen_irq_enable_direct);
pv_mmu_ops.read_cr2 = xen_read_cr2_direct;
}
}
@@ -1133,49 +732,6 @@
return ret;
}
-static void xen_set_fixmap(unsigned idx, unsigned long phys, pgprot_t prot)
-{
- pte_t pte;
-
- phys >>= PAGE_SHIFT;
-
- switch (idx) {
- case FIX_BTMAP_END ... FIX_BTMAP_BEGIN:
-#ifdef CONFIG_X86_F00F_BUG
- case FIX_F00F_IDT:
-#endif
-#ifdef CONFIG_X86_32
- case FIX_WP_TEST:
- case FIX_VDSO:
-# ifdef CONFIG_HIGHMEM
- case FIX_KMAP_BEGIN ... FIX_KMAP_END:
-# endif
-#else
- case VSYSCALL_LAST_PAGE ... VSYSCALL_FIRST_PAGE:
-#endif
-#ifdef CONFIG_X86_LOCAL_APIC
- case FIX_APIC_BASE: /* maps dummy local APIC */
-#endif
- pte = pfn_pte(phys, prot);
- break;
-
- default:
- pte = mfn_pte(phys, prot);
- break;
- }
-
- __native_set_fixmap(idx, pte);
-
-#ifdef CONFIG_X86_64
- /* Replicate changes to map the vsyscall page into the user
- pagetable vsyscall mapping. */
- if (idx >= VSYSCALL_LAST_PAGE && idx <= VSYSCALL_FIRST_PAGE) {
- unsigned long vaddr = __fix_to_virt(idx);
- set_pte_vaddr_pud(level3_user_vsyscall, vaddr, pte);
- }
-#endif
-}
-
static const struct pv_info xen_info __initdata = {
.paravirt_enabled = 1,
.shared_kernel_pmd = 0,
@@ -1271,87 +827,6 @@
#endif
};
-static const struct pv_mmu_ops xen_mmu_ops __initdata = {
- .pagetable_setup_start = xen_pagetable_setup_start,
- .pagetable_setup_done = xen_pagetable_setup_done,
-
- .read_cr2 = xen_read_cr2,
- .write_cr2 = xen_write_cr2,
-
- .read_cr3 = xen_read_cr3,
- .write_cr3 = xen_write_cr3,
-
- .flush_tlb_user = xen_flush_tlb,
- .flush_tlb_kernel = xen_flush_tlb,
- .flush_tlb_single = xen_flush_tlb_single,
- .flush_tlb_others = xen_flush_tlb_others,
-
- .pte_update = paravirt_nop,
- .pte_update_defer = paravirt_nop,
-
- .pgd_alloc = xen_pgd_alloc,
- .pgd_free = xen_pgd_free,
-
- .alloc_pte = xen_alloc_pte_init,
- .release_pte = xen_release_pte_init,
- .alloc_pmd = xen_alloc_pte_init,
- .alloc_pmd_clone = paravirt_nop,
- .release_pmd = xen_release_pte_init,
-
-#ifdef CONFIG_HIGHPTE
- .kmap_atomic_pte = xen_kmap_atomic_pte,
-#endif
-
-#ifdef CONFIG_X86_64
- .set_pte = xen_set_pte,
-#else
- .set_pte = xen_set_pte_init,
-#endif
- .set_pte_at = xen_set_pte_at,
- .set_pmd = xen_set_pmd_hyper,
-
- .ptep_modify_prot_start = __ptep_modify_prot_start,
- .ptep_modify_prot_commit = __ptep_modify_prot_commit,
-
- .pte_val = xen_pte_val,
- .pte_flags = native_pte_flags,
- .pgd_val = xen_pgd_val,
-
- .make_pte = xen_make_pte,
- .make_pgd = xen_make_pgd,
-
-#ifdef CONFIG_X86_PAE
- .set_pte_atomic = xen_set_pte_atomic,
- .set_pte_present = xen_set_pte_at,
- .pte_clear = xen_pte_clear,
- .pmd_clear = xen_pmd_clear,
-#endif /* CONFIG_X86_PAE */
- .set_pud = xen_set_pud_hyper,
-
- .make_pmd = xen_make_pmd,
- .pmd_val = xen_pmd_val,
-
-#if PAGETABLE_LEVELS == 4
- .pud_val = xen_pud_val,
- .make_pud = xen_make_pud,
- .set_pgd = xen_set_pgd_hyper,
-
- .alloc_pud = xen_alloc_pte_init,
- .release_pud = xen_release_pte_init,
-#endif /* PAGETABLE_LEVELS == 4 */
-
- .activate_mm = xen_activate_mm,
- .dup_mmap = xen_dup_mmap,
- .exit_mmap = xen_exit_mmap,
-
- .lazy_mode = {
- .enter = paravirt_enter_lazy_mmu,
- .leave = xen_leave_lazy,
- },
-
- .set_fixmap = xen_set_fixmap,
-};
-
static void xen_reboot(int reason)
{
struct sched_shutdown r = { .reason = reason };
@@ -1394,223 +869,6 @@
};
-static void __init xen_reserve_top(void)
-{
-#ifdef CONFIG_X86_32
- unsigned long top = HYPERVISOR_VIRT_START;
- struct xen_platform_parameters pp;
-
- if (HYPERVISOR_xen_version(XENVER_platform_parameters, &pp) == 0)
- top = pp.virt_start;
-
- reserve_top_address(-top);
-#endif /* CONFIG_X86_32 */
-}
-
-/*
- * Like __va(), but returns address in the kernel mapping (which is
- * all we have until the physical memory mapping has been set up.
- */
-static void *__ka(phys_addr_t paddr)
-{
-#ifdef CONFIG_X86_64
- return (void *)(paddr + __START_KERNEL_map);
-#else
- return __va(paddr);
-#endif
-}
-
-/* Convert a machine address to physical address */
-static unsigned long m2p(phys_addr_t maddr)
-{
- phys_addr_t paddr;
-
- maddr &= PTE_PFN_MASK;
- paddr = mfn_to_pfn(maddr >> PAGE_SHIFT) << PAGE_SHIFT;
-
- return paddr;
-}
-
-/* Convert a machine address to kernel virtual */
-static void *m2v(phys_addr_t maddr)
-{
- return __ka(m2p(maddr));
-}
-
-static void set_page_prot(void *addr, pgprot_t prot)
-{
- unsigned long pfn = __pa(addr) >> PAGE_SHIFT;
- pte_t pte = pfn_pte(pfn, prot);
-
- if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, 0))
- BUG();
-}
-
-static __init void xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
-{
- unsigned pmdidx, pteidx;
- unsigned ident_pte;
- unsigned long pfn;
-
- ident_pte = 0;
- pfn = 0;
- for (pmdidx = 0; pmdidx < PTRS_PER_PMD && pfn < max_pfn; pmdidx++) {
- pte_t *pte_page;
-
- /* Reuse or allocate a page of ptes */
- if (pmd_present(pmd[pmdidx]))
- pte_page = m2v(pmd[pmdidx].pmd);
- else {
- /* Check for free pte pages */
- if (ident_pte == ARRAY_SIZE(level1_ident_pgt))
- break;
-
- pte_page = &level1_ident_pgt[ident_pte];
- ident_pte += PTRS_PER_PTE;
-
- pmd[pmdidx] = __pmd(__pa(pte_page) | _PAGE_TABLE);
- }
-
- /* Install mappings */
- for (pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) {
- pte_t pte;
-
- if (pfn > max_pfn_mapped)
- max_pfn_mapped = pfn;
-
- if (!pte_none(pte_page[pteidx]))
- continue;
-
- pte = pfn_pte(pfn, PAGE_KERNEL_EXEC);
- pte_page[pteidx] = pte;
- }
- }
-
- for (pteidx = 0; pteidx < ident_pte; pteidx += PTRS_PER_PTE)
- set_page_prot(&level1_ident_pgt[pteidx], PAGE_KERNEL_RO);
-
- set_page_prot(pmd, PAGE_KERNEL_RO);
-}
-
-#ifdef CONFIG_X86_64
-static void convert_pfn_mfn(void *v)
-{
- pte_t *pte = v;
- int i;
-
- /* All levels are converted the same way, so just treat them
- as ptes. */
- for (i = 0; i < PTRS_PER_PTE; i++)
- pte[i] = xen_make_pte(pte[i].pte);
-}
-
-/*
- * Set up the inital kernel pagetable.
- *
- * We can construct this by grafting the Xen provided pagetable into
- * head_64.S's preconstructed pagetables. We copy the Xen L2's into
- * level2_ident_pgt, level2_kernel_pgt and level2_fixmap_pgt. This
- * means that only the kernel has a physical mapping to start with -
- * but that's enough to get __va working. We need to fill in the rest
- * of the physical mapping once some sort of allocator has been set
- * up.
- */
-static __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
- unsigned long max_pfn)
-{
- pud_t *l3;
- pmd_t *l2;
-
- /* Zap identity mapping */
- init_level4_pgt[0] = __pgd(0);
-
- /* Pre-constructed entries are in pfn, so convert to mfn */
- convert_pfn_mfn(init_level4_pgt);
- convert_pfn_mfn(level3_ident_pgt);
- convert_pfn_mfn(level3_kernel_pgt);
-
- l3 = m2v(pgd[pgd_index(__START_KERNEL_map)].pgd);
- l2 = m2v(l3[pud_index(__START_KERNEL_map)].pud);
-
- memcpy(level2_ident_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD);
- memcpy(level2_kernel_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD);
-
- l3 = m2v(pgd[pgd_index(__START_KERNEL_map + PMD_SIZE)].pgd);
- l2 = m2v(l3[pud_index(__START_KERNEL_map + PMD_SIZE)].pud);
- memcpy(level2_fixmap_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD);
-
- /* Set up identity map */
- xen_map_identity_early(level2_ident_pgt, max_pfn);
-
- /* Make pagetable pieces RO */
- set_page_prot(init_level4_pgt, PAGE_KERNEL_RO);
- set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO);
- set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO);
- set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO);
- set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
- set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO);
-
- /* Pin down new L4 */
- pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE,
- PFN_DOWN(__pa_symbol(init_level4_pgt)));
-
- /* Unpin Xen-provided one */
- pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
-
- /* Switch over */
- pgd = init_level4_pgt;
-
- /*
- * At this stage there can be no user pgd, and no page
- * structure to attach it to, so make sure we just set kernel
- * pgd.
- */
- xen_mc_batch();
- __xen_write_cr3(true, __pa(pgd));
- xen_mc_issue(PARAVIRT_LAZY_CPU);
-
- reserve_early(__pa(xen_start_info->pt_base),
- __pa(xen_start_info->pt_base +
- xen_start_info->nr_pt_frames * PAGE_SIZE),
- "XEN PAGETABLES");
-
- return pgd;
-}
-#else /* !CONFIG_X86_64 */
-static pmd_t level2_kernel_pgt[PTRS_PER_PMD] __page_aligned_bss;
-
-static __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
- unsigned long max_pfn)
-{
- pmd_t *kernel_pmd;
-
- init_pg_tables_start = __pa(pgd);
- init_pg_tables_end = __pa(pgd) + xen_start_info->nr_pt_frames*PAGE_SIZE;
- max_pfn_mapped = PFN_DOWN(init_pg_tables_end + 512*1024);
-
- kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd);
- memcpy(level2_kernel_pgt, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD);
-
- xen_map_identity_early(level2_kernel_pgt, max_pfn);
-
- memcpy(swapper_pg_dir, pgd, sizeof(pgd_t) * PTRS_PER_PGD);
- set_pgd(&swapper_pg_dir[KERNEL_PGD_BOUNDARY],
- __pgd(__pa(level2_kernel_pgt) | _PAGE_PRESENT));
-
- set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
- set_page_prot(swapper_pg_dir, PAGE_KERNEL_RO);
- set_page_prot(empty_zero_page, PAGE_KERNEL_RO);
-
- pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
-
- xen_write_cr3(__pa(swapper_pg_dir));
-
- pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(swapper_pg_dir)));
-
- return swapper_pg_dir;
-}
-#endif /* CONFIG_X86_64 */
-
/* First C function to be called on Xen boot */
asmlinkage void __init xen_start_kernel(void)
{
@@ -1650,10 +908,18 @@
machine_ops = xen_machine_ops;
#ifdef CONFIG_X86_64
- /* Disable until direct per-cpu data access. */
- have_vcpu_info_placement = 0;
- x86_64_init_pda();
+ /*
+ * Setup percpu state. We only need to do this for 64-bit
+ * because 32-bit already has %fs set properly.
+ */
+ load_percpu_segment(0);
#endif
+ /*
+ * The only reliable way to retain the initial address of the
+ * percpu gdt_page is to remember it here, so we can go and
+ * mark it RW later, when the initial percpu area is freed.
+ */
+ xen_initial_gdt = &per_cpu(gdt_page, 0);
xen_smp_init();
diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c
index bb04260..5a07090 100644
--- a/arch/x86/xen/irq.c
+++ b/arch/x86/xen/irq.c
@@ -39,7 +39,7 @@
struct vcpu_info *vcpu;
unsigned long flags;
- vcpu = x86_read_percpu(xen_vcpu);
+ vcpu = percpu_read(xen_vcpu);
/* flag has opposite sense of mask */
flags = !vcpu->evtchn_upcall_mask;
@@ -50,6 +50,7 @@
*/
return (-flags) & X86_EFLAGS_IF;
}
+PV_CALLEE_SAVE_REGS_THUNK(xen_save_fl);
static void xen_restore_fl(unsigned long flags)
{
@@ -62,7 +63,7 @@
make sure we're don't switch CPUs between getting the vcpu
pointer and updating the mask. */
preempt_disable();
- vcpu = x86_read_percpu(xen_vcpu);
+ vcpu = percpu_read(xen_vcpu);
vcpu->evtchn_upcall_mask = flags;
preempt_enable_no_resched();
@@ -76,6 +77,7 @@
xen_force_evtchn_callback();
}
}
+PV_CALLEE_SAVE_REGS_THUNK(xen_restore_fl);
static void xen_irq_disable(void)
{
@@ -83,9 +85,10 @@
make sure we're don't switch CPUs between getting the vcpu
pointer and updating the mask. */
preempt_disable();
- x86_read_percpu(xen_vcpu)->evtchn_upcall_mask = 1;
+ percpu_read(xen_vcpu)->evtchn_upcall_mask = 1;
preempt_enable_no_resched();
}
+PV_CALLEE_SAVE_REGS_THUNK(xen_irq_disable);
static void xen_irq_enable(void)
{
@@ -96,7 +99,7 @@
the caller is confused and is trying to re-enable interrupts
on an indeterminate processor. */
- vcpu = x86_read_percpu(xen_vcpu);
+ vcpu = percpu_read(xen_vcpu);
vcpu->evtchn_upcall_mask = 0;
/* Doesn't matter if we get preempted here, because any
@@ -106,6 +109,7 @@
if (unlikely(vcpu->evtchn_upcall_pending))
xen_force_evtchn_callback();
}
+PV_CALLEE_SAVE_REGS_THUNK(xen_irq_enable);
static void xen_safe_halt(void)
{
@@ -124,10 +128,12 @@
static const struct pv_irq_ops xen_irq_ops __initdata = {
.init_IRQ = __xen_init_IRQ,
- .save_fl = xen_save_fl,
- .restore_fl = xen_restore_fl,
- .irq_disable = xen_irq_disable,
- .irq_enable = xen_irq_enable,
+
+ .save_fl = PV_CALLEE_SAVE(xen_save_fl),
+ .restore_fl = PV_CALLEE_SAVE(xen_restore_fl),
+ .irq_disable = PV_CALLEE_SAVE(xen_irq_disable),
+ .irq_enable = PV_CALLEE_SAVE(xen_irq_enable),
+
.safe_halt = xen_safe_halt,
.halt = xen_halt,
#ifdef CONFIG_X86_64
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 503c240..d2e8ed1 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -47,6 +47,7 @@
#include <asm/tlbflush.h>
#include <asm/fixmap.h>
#include <asm/mmu_context.h>
+#include <asm/setup.h>
#include <asm/paravirt.h>
#include <asm/linkage.h>
@@ -55,6 +56,8 @@
#include <xen/page.h>
#include <xen/interface/xen.h>
+#include <xen/interface/version.h>
+#include <xen/hvc-console.h>
#include "multicalls.h"
#include "mmu.h"
@@ -114,6 +117,37 @@
#endif /* CONFIG_XEN_DEBUG_FS */
+
+/*
+ * Identity map, in addition to plain kernel map. This needs to be
+ * large enough to allocate page table pages to allocate the rest.
+ * Each page can map 2MB.
+ */
+static pte_t level1_ident_pgt[PTRS_PER_PTE * 4] __page_aligned_bss;
+
+#ifdef CONFIG_X86_64
+/* l3 pud for userspace vsyscall mapping */
+static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss;
+#endif /* CONFIG_X86_64 */
+
+/*
+ * Note about cr3 (pagetable base) values:
+ *
+ * xen_cr3 contains the current logical cr3 value; it contains the
+ * last set cr3. This may not be the current effective cr3, because
+ * its update may be being lazily deferred. However, a vcpu looking
+ * at its own cr3 can use this value knowing that it everything will
+ * be self-consistent.
+ *
+ * xen_current_cr3 contains the actual vcpu cr3; it is set once the
+ * hypercall to set the vcpu cr3 is complete (so it may be a little
+ * out of date, but it will never be set early). If one vcpu is
+ * looking at another vcpu's cr3 value, it should use this variable.
+ */
+DEFINE_PER_CPU(unsigned long, xen_cr3); /* cr3 stored as physaddr */
+DEFINE_PER_CPU(unsigned long, xen_current_cr3); /* actual vcpu cr3 */
+
+
/*
* Just beyond the highest usermode address. STACK_TOP_MAX has a
* redzone above it, so round it up to a PGD boundary.
@@ -458,28 +492,33 @@
{
return pte_mfn_to_pfn(pte.pte);
}
+PV_CALLEE_SAVE_REGS_THUNK(xen_pte_val);
pgdval_t xen_pgd_val(pgd_t pgd)
{
return pte_mfn_to_pfn(pgd.pgd);
}
+PV_CALLEE_SAVE_REGS_THUNK(xen_pgd_val);
pte_t xen_make_pte(pteval_t pte)
{
pte = pte_pfn_to_mfn(pte);
return native_make_pte(pte);
}
+PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte);
pgd_t xen_make_pgd(pgdval_t pgd)
{
pgd = pte_pfn_to_mfn(pgd);
return native_make_pgd(pgd);
}
+PV_CALLEE_SAVE_REGS_THUNK(xen_make_pgd);
pmdval_t xen_pmd_val(pmd_t pmd)
{
return pte_mfn_to_pfn(pmd.pmd);
}
+PV_CALLEE_SAVE_REGS_THUNK(xen_pmd_val);
void xen_set_pud_hyper(pud_t *ptr, pud_t val)
{
@@ -556,12 +595,14 @@
pmd = pte_pfn_to_mfn(pmd);
return native_make_pmd(pmd);
}
+PV_CALLEE_SAVE_REGS_THUNK(xen_make_pmd);
#if PAGETABLE_LEVELS == 4
pudval_t xen_pud_val(pud_t pud)
{
return pte_mfn_to_pfn(pud.pud);
}
+PV_CALLEE_SAVE_REGS_THUNK(xen_pud_val);
pud_t xen_make_pud(pudval_t pud)
{
@@ -569,6 +610,7 @@
return native_make_pud(pud);
}
+PV_CALLEE_SAVE_REGS_THUNK(xen_make_pud);
pgd_t *xen_get_user_pgd(pgd_t *pgd)
{
@@ -1063,18 +1105,14 @@
struct mm_struct *mm = info;
struct mm_struct *active_mm;
-#ifdef CONFIG_X86_64
- active_mm = read_pda(active_mm);
-#else
- active_mm = __get_cpu_var(cpu_tlbstate).active_mm;
-#endif
+ active_mm = percpu_read(cpu_tlbstate.active_mm);
if (active_mm == mm)
leave_mm(smp_processor_id());
/* If this cpu still has a stale cr3 reference, then make sure
it has been flushed. */
- if (x86_read_percpu(xen_current_cr3) == __pa(mm->pgd)) {
+ if (percpu_read(xen_current_cr3) == __pa(mm->pgd)) {
load_cr3(swapper_pg_dir);
arch_flush_lazy_cpu_mode();
}
@@ -1156,6 +1194,709 @@
spin_unlock(&mm->page_table_lock);
}
+static __init void xen_pagetable_setup_start(pgd_t *base)
+{
+}
+
+static __init void xen_pagetable_setup_done(pgd_t *base)
+{
+ xen_setup_shared_info();
+}
+
+static void xen_write_cr2(unsigned long cr2)
+{
+ percpu_read(xen_vcpu)->arch.cr2 = cr2;
+}
+
+static unsigned long xen_read_cr2(void)
+{
+ return percpu_read(xen_vcpu)->arch.cr2;
+}
+
+unsigned long xen_read_cr2_direct(void)
+{
+ return percpu_read(xen_vcpu_info.arch.cr2);
+}
+
+static void xen_flush_tlb(void)
+{
+ struct mmuext_op *op;
+ struct multicall_space mcs;
+
+ preempt_disable();
+
+ mcs = xen_mc_entry(sizeof(*op));
+
+ op = mcs.args;
+ op->cmd = MMUEXT_TLB_FLUSH_LOCAL;
+ MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+
+ xen_mc_issue(PARAVIRT_LAZY_MMU);
+
+ preempt_enable();
+}
+
+static void xen_flush_tlb_single(unsigned long addr)
+{
+ struct mmuext_op *op;
+ struct multicall_space mcs;
+
+ preempt_disable();
+
+ mcs = xen_mc_entry(sizeof(*op));
+ op = mcs.args;
+ op->cmd = MMUEXT_INVLPG_LOCAL;
+ op->arg1.linear_addr = addr & PAGE_MASK;
+ MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+
+ xen_mc_issue(PARAVIRT_LAZY_MMU);
+
+ preempt_enable();
+}
+
+static void xen_flush_tlb_others(const struct cpumask *cpus,
+ struct mm_struct *mm, unsigned long va)
+{
+ struct {
+ struct mmuext_op op;
+ DECLARE_BITMAP(mask, NR_CPUS);
+ } *args;
+ struct multicall_space mcs;
+
+ BUG_ON(cpumask_empty(cpus));
+ BUG_ON(!mm);
+
+ mcs = xen_mc_entry(sizeof(*args));
+ args = mcs.args;
+ args->op.arg2.vcpumask = to_cpumask(args->mask);
+
+ /* Remove us, and any offline CPUS. */
+ cpumask_and(to_cpumask(args->mask), cpus, cpu_online_mask);
+ cpumask_clear_cpu(smp_processor_id(), to_cpumask(args->mask));
+ if (unlikely(cpumask_empty(to_cpumask(args->mask))))
+ goto issue;
+
+ if (va == TLB_FLUSH_ALL) {
+ args->op.cmd = MMUEXT_TLB_FLUSH_MULTI;
+ } else {
+ args->op.cmd = MMUEXT_INVLPG_MULTI;
+ args->op.arg1.linear_addr = va;
+ }
+
+ MULTI_mmuext_op(mcs.mc, &args->op, 1, NULL, DOMID_SELF);
+
+issue:
+ xen_mc_issue(PARAVIRT_LAZY_MMU);
+}
+
+static unsigned long xen_read_cr3(void)
+{
+ return percpu_read(xen_cr3);
+}
+
+static void set_current_cr3(void *v)
+{
+ percpu_write(xen_current_cr3, (unsigned long)v);
+}
+
+static void __xen_write_cr3(bool kernel, unsigned long cr3)
+{
+ struct mmuext_op *op;
+ struct multicall_space mcs;
+ unsigned long mfn;
+
+ if (cr3)
+ mfn = pfn_to_mfn(PFN_DOWN(cr3));
+ else
+ mfn = 0;
+
+ WARN_ON(mfn == 0 && kernel);
+
+ mcs = __xen_mc_entry(sizeof(*op));
+
+ op = mcs.args;
+ op->cmd = kernel ? MMUEXT_NEW_BASEPTR : MMUEXT_NEW_USER_BASEPTR;
+ op->arg1.mfn = mfn;
+
+ MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+
+ if (kernel) {
+ percpu_write(xen_cr3, cr3);
+
+ /* Update xen_current_cr3 once the batch has actually
+ been submitted. */
+ xen_mc_callback(set_current_cr3, (void *)cr3);
+ }
+}
+
+static void xen_write_cr3(unsigned long cr3)
+{
+ BUG_ON(preemptible());
+
+ xen_mc_batch(); /* disables interrupts */
+
+ /* Update while interrupts are disabled, so its atomic with
+ respect to ipis */
+ percpu_write(xen_cr3, cr3);
+
+ __xen_write_cr3(true, cr3);
+
+#ifdef CONFIG_X86_64
+ {
+ pgd_t *user_pgd = xen_get_user_pgd(__va(cr3));
+ if (user_pgd)
+ __xen_write_cr3(false, __pa(user_pgd));
+ else
+ __xen_write_cr3(false, 0);
+ }
+#endif
+
+ xen_mc_issue(PARAVIRT_LAZY_CPU); /* interrupts restored */
+}
+
+static int xen_pgd_alloc(struct mm_struct *mm)
+{
+ pgd_t *pgd = mm->pgd;
+ int ret = 0;
+
+ BUG_ON(PagePinned(virt_to_page(pgd)));
+
+#ifdef CONFIG_X86_64
+ {
+ struct page *page = virt_to_page(pgd);
+ pgd_t *user_pgd;
+
+ BUG_ON(page->private != 0);
+
+ ret = -ENOMEM;
+
+ user_pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+ page->private = (unsigned long)user_pgd;
+
+ if (user_pgd != NULL) {
+ user_pgd[pgd_index(VSYSCALL_START)] =
+ __pgd(__pa(level3_user_vsyscall) | _PAGE_TABLE);
+ ret = 0;
+ }
+
+ BUG_ON(PagePinned(virt_to_page(xen_get_user_pgd(pgd))));
+ }
+#endif
+
+ return ret;
+}
+
+static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+#ifdef CONFIG_X86_64
+ pgd_t *user_pgd = xen_get_user_pgd(pgd);
+
+ if (user_pgd)
+ free_page((unsigned long)user_pgd);
+#endif
+}
+
+#ifdef CONFIG_HIGHPTE
+static void *xen_kmap_atomic_pte(struct page *page, enum km_type type)
+{
+ pgprot_t prot = PAGE_KERNEL;
+
+ if (PagePinned(page))
+ prot = PAGE_KERNEL_RO;
+
+ if (0 && PageHighMem(page))
+ printk("mapping highpte %lx type %d prot %s\n",
+ page_to_pfn(page), type,
+ (unsigned long)pgprot_val(prot) & _PAGE_RW ? "WRITE" : "READ");
+
+ return kmap_atomic_prot(page, type, prot);
+}
+#endif
+
+#ifdef CONFIG_X86_32
+static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
+{
+ /* If there's an existing pte, then don't allow _PAGE_RW to be set */
+ if (pte_val_ma(*ptep) & _PAGE_PRESENT)
+ pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) &
+ pte_val_ma(pte));
+
+ return pte;
+}
+
+/* Init-time set_pte while constructing initial pagetables, which
+ doesn't allow RO pagetable pages to be remapped RW */
+static __init void xen_set_pte_init(pte_t *ptep, pte_t pte)
+{
+ pte = mask_rw_pte(ptep, pte);
+
+ xen_set_pte(ptep, pte);
+}
+#endif
+
+/* Early in boot, while setting up the initial pagetable, assume
+ everything is pinned. */
+static __init void xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn)
+{
+#ifdef CONFIG_FLATMEM
+ BUG_ON(mem_map); /* should only be used early */
+#endif
+ make_lowmem_page_readonly(__va(PFN_PHYS(pfn)));
+}
+
+/* Early release_pte assumes that all pts are pinned, since there's
+ only init_mm and anything attached to that is pinned. */
+static void xen_release_pte_init(unsigned long pfn)
+{
+ make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
+}
+
+static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
+{
+ struct mmuext_op op;
+ op.cmd = cmd;
+ op.arg1.mfn = pfn_to_mfn(pfn);
+ if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF))
+ BUG();
+}
+
+/* This needs to make sure the new pte page is pinned iff its being
+ attached to a pinned pagetable. */
+static void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn, unsigned level)
+{
+ struct page *page = pfn_to_page(pfn);
+
+ if (PagePinned(virt_to_page(mm->pgd))) {
+ SetPagePinned(page);
+
+ vm_unmap_aliases();
+ if (!PageHighMem(page)) {
+ make_lowmem_page_readonly(__va(PFN_PHYS((unsigned long)pfn)));
+ if (level == PT_PTE && USE_SPLIT_PTLOCKS)
+ pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
+ } else {
+ /* make sure there are no stray mappings of
+ this page */
+ kmap_flush_unused();
+ }
+ }
+}
+
+static void xen_alloc_pte(struct mm_struct *mm, unsigned long pfn)
+{
+ xen_alloc_ptpage(mm, pfn, PT_PTE);
+}
+
+static void xen_alloc_pmd(struct mm_struct *mm, unsigned long pfn)
+{
+ xen_alloc_ptpage(mm, pfn, PT_PMD);
+}
+
+/* This should never happen until we're OK to use struct page */
+static void xen_release_ptpage(unsigned long pfn, unsigned level)
+{
+ struct page *page = pfn_to_page(pfn);
+
+ if (PagePinned(page)) {
+ if (!PageHighMem(page)) {
+ if (level == PT_PTE && USE_SPLIT_PTLOCKS)
+ pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
+ make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
+ }
+ ClearPagePinned(page);
+ }
+}
+
+static void xen_release_pte(unsigned long pfn)
+{
+ xen_release_ptpage(pfn, PT_PTE);
+}
+
+static void xen_release_pmd(unsigned long pfn)
+{
+ xen_release_ptpage(pfn, PT_PMD);
+}
+
+#if PAGETABLE_LEVELS == 4
+static void xen_alloc_pud(struct mm_struct *mm, unsigned long pfn)
+{
+ xen_alloc_ptpage(mm, pfn, PT_PUD);
+}
+
+static void xen_release_pud(unsigned long pfn)
+{
+ xen_release_ptpage(pfn, PT_PUD);
+}
+#endif
+
+void __init xen_reserve_top(void)
+{
+#ifdef CONFIG_X86_32
+ unsigned long top = HYPERVISOR_VIRT_START;
+ struct xen_platform_parameters pp;
+
+ if (HYPERVISOR_xen_version(XENVER_platform_parameters, &pp) == 0)
+ top = pp.virt_start;
+
+ reserve_top_address(-top);
+#endif /* CONFIG_X86_32 */
+}
+
+/*
+ * Like __va(), but returns address in the kernel mapping (which is
+ * all we have until the physical memory mapping has been set up.
+ */
+static void *__ka(phys_addr_t paddr)
+{
+#ifdef CONFIG_X86_64
+ return (void *)(paddr + __START_KERNEL_map);
+#else
+ return __va(paddr);
+#endif
+}
+
+/* Convert a machine address to physical address */
+static unsigned long m2p(phys_addr_t maddr)
+{
+ phys_addr_t paddr;
+
+ maddr &= PTE_PFN_MASK;
+ paddr = mfn_to_pfn(maddr >> PAGE_SHIFT) << PAGE_SHIFT;
+
+ return paddr;
+}
+
+/* Convert a machine address to kernel virtual */
+static void *m2v(phys_addr_t maddr)
+{
+ return __ka(m2p(maddr));
+}
+
+static void set_page_prot(void *addr, pgprot_t prot)
+{
+ unsigned long pfn = __pa(addr) >> PAGE_SHIFT;
+ pte_t pte = pfn_pte(pfn, prot);
+
+ if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, 0))
+ BUG();
+}
+
+static __init void xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
+{
+ unsigned pmdidx, pteidx;
+ unsigned ident_pte;
+ unsigned long pfn;
+
+ ident_pte = 0;
+ pfn = 0;
+ for (pmdidx = 0; pmdidx < PTRS_PER_PMD && pfn < max_pfn; pmdidx++) {
+ pte_t *pte_page;
+
+ /* Reuse or allocate a page of ptes */
+ if (pmd_present(pmd[pmdidx]))
+ pte_page = m2v(pmd[pmdidx].pmd);
+ else {
+ /* Check for free pte pages */
+ if (ident_pte == ARRAY_SIZE(level1_ident_pgt))
+ break;
+
+ pte_page = &level1_ident_pgt[ident_pte];
+ ident_pte += PTRS_PER_PTE;
+
+ pmd[pmdidx] = __pmd(__pa(pte_page) | _PAGE_TABLE);
+ }
+
+ /* Install mappings */
+ for (pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) {
+ pte_t pte;
+
+ if (pfn > max_pfn_mapped)
+ max_pfn_mapped = pfn;
+
+ if (!pte_none(pte_page[pteidx]))
+ continue;
+
+ pte = pfn_pte(pfn, PAGE_KERNEL_EXEC);
+ pte_page[pteidx] = pte;
+ }
+ }
+
+ for (pteidx = 0; pteidx < ident_pte; pteidx += PTRS_PER_PTE)
+ set_page_prot(&level1_ident_pgt[pteidx], PAGE_KERNEL_RO);
+
+ set_page_prot(pmd, PAGE_KERNEL_RO);
+}
+
+#ifdef CONFIG_X86_64
+static void convert_pfn_mfn(void *v)
+{
+ pte_t *pte = v;
+ int i;
+
+ /* All levels are converted the same way, so just treat them
+ as ptes. */
+ for (i = 0; i < PTRS_PER_PTE; i++)
+ pte[i] = xen_make_pte(pte[i].pte);
+}
+
+/*
+ * Set up the inital kernel pagetable.
+ *
+ * We can construct this by grafting the Xen provided pagetable into
+ * head_64.S's preconstructed pagetables. We copy the Xen L2's into
+ * level2_ident_pgt, level2_kernel_pgt and level2_fixmap_pgt. This
+ * means that only the kernel has a physical mapping to start with -
+ * but that's enough to get __va working. We need to fill in the rest
+ * of the physical mapping once some sort of allocator has been set
+ * up.
+ */
+__init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
+ unsigned long max_pfn)
+{
+ pud_t *l3;
+ pmd_t *l2;
+
+ /* Zap identity mapping */
+ init_level4_pgt[0] = __pgd(0);
+
+ /* Pre-constructed entries are in pfn, so convert to mfn */
+ convert_pfn_mfn(init_level4_pgt);
+ convert_pfn_mfn(level3_ident_pgt);
+ convert_pfn_mfn(level3_kernel_pgt);
+
+ l3 = m2v(pgd[pgd_index(__START_KERNEL_map)].pgd);
+ l2 = m2v(l3[pud_index(__START_KERNEL_map)].pud);
+
+ memcpy(level2_ident_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD);
+ memcpy(level2_kernel_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD);
+
+ l3 = m2v(pgd[pgd_index(__START_KERNEL_map + PMD_SIZE)].pgd);
+ l2 = m2v(l3[pud_index(__START_KERNEL_map + PMD_SIZE)].pud);
+ memcpy(level2_fixmap_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD);
+
+ /* Set up identity map */
+ xen_map_identity_early(level2_ident_pgt, max_pfn);
+
+ /* Make pagetable pieces RO */
+ set_page_prot(init_level4_pgt, PAGE_KERNEL_RO);
+ set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO);
+ set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO);
+ set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO);
+ set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
+ set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO);
+
+ /* Pin down new L4 */
+ pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE,
+ PFN_DOWN(__pa_symbol(init_level4_pgt)));
+
+ /* Unpin Xen-provided one */
+ pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
+
+ /* Switch over */
+ pgd = init_level4_pgt;
+
+ /*
+ * At this stage there can be no user pgd, and no page
+ * structure to attach it to, so make sure we just set kernel
+ * pgd.
+ */
+ xen_mc_batch();
+ __xen_write_cr3(true, __pa(pgd));
+ xen_mc_issue(PARAVIRT_LAZY_CPU);
+
+ reserve_early(__pa(xen_start_info->pt_base),
+ __pa(xen_start_info->pt_base +
+ xen_start_info->nr_pt_frames * PAGE_SIZE),
+ "XEN PAGETABLES");
+
+ return pgd;
+}
+#else /* !CONFIG_X86_64 */
+static pmd_t level2_kernel_pgt[PTRS_PER_PMD] __page_aligned_bss;
+
+__init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
+ unsigned long max_pfn)
+{
+ pmd_t *kernel_pmd;
+
+ init_pg_tables_start = __pa(pgd);
+ init_pg_tables_end = __pa(pgd) + xen_start_info->nr_pt_frames*PAGE_SIZE;
+ max_pfn_mapped = PFN_DOWN(init_pg_tables_end + 512*1024);
+
+ kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd);
+ memcpy(level2_kernel_pgt, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD);
+
+ xen_map_identity_early(level2_kernel_pgt, max_pfn);
+
+ memcpy(swapper_pg_dir, pgd, sizeof(pgd_t) * PTRS_PER_PGD);
+ set_pgd(&swapper_pg_dir[KERNEL_PGD_BOUNDARY],
+ __pgd(__pa(level2_kernel_pgt) | _PAGE_PRESENT));
+
+ set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
+ set_page_prot(swapper_pg_dir, PAGE_KERNEL_RO);
+ set_page_prot(empty_zero_page, PAGE_KERNEL_RO);
+
+ pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
+
+ xen_write_cr3(__pa(swapper_pg_dir));
+
+ pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(swapper_pg_dir)));
+
+ return swapper_pg_dir;
+}
+#endif /* CONFIG_X86_64 */
+
+static void xen_set_fixmap(unsigned idx, unsigned long phys, pgprot_t prot)
+{
+ pte_t pte;
+
+ phys >>= PAGE_SHIFT;
+
+ switch (idx) {
+ case FIX_BTMAP_END ... FIX_BTMAP_BEGIN:
+#ifdef CONFIG_X86_F00F_BUG
+ case FIX_F00F_IDT:
+#endif
+#ifdef CONFIG_X86_32
+ case FIX_WP_TEST:
+ case FIX_VDSO:
+# ifdef CONFIG_HIGHMEM
+ case FIX_KMAP_BEGIN ... FIX_KMAP_END:
+# endif
+#else
+ case VSYSCALL_LAST_PAGE ... VSYSCALL_FIRST_PAGE:
+#endif
+#ifdef CONFIG_X86_LOCAL_APIC
+ case FIX_APIC_BASE: /* maps dummy local APIC */
+#endif
+ pte = pfn_pte(phys, prot);
+ break;
+
+ default:
+ pte = mfn_pte(phys, prot);
+ break;
+ }
+
+ __native_set_fixmap(idx, pte);
+
+#ifdef CONFIG_X86_64
+ /* Replicate changes to map the vsyscall page into the user
+ pagetable vsyscall mapping. */
+ if (idx >= VSYSCALL_LAST_PAGE && idx <= VSYSCALL_FIRST_PAGE) {
+ unsigned long vaddr = __fix_to_virt(idx);
+ set_pte_vaddr_pud(level3_user_vsyscall, vaddr, pte);
+ }
+#endif
+}
+
+__init void xen_post_allocator_init(void)
+{
+ pv_mmu_ops.set_pte = xen_set_pte;
+ pv_mmu_ops.set_pmd = xen_set_pmd;
+ pv_mmu_ops.set_pud = xen_set_pud;
+#if PAGETABLE_LEVELS == 4
+ pv_mmu_ops.set_pgd = xen_set_pgd;
+#endif
+
+ /* This will work as long as patching hasn't happened yet
+ (which it hasn't) */
+ pv_mmu_ops.alloc_pte = xen_alloc_pte;
+ pv_mmu_ops.alloc_pmd = xen_alloc_pmd;
+ pv_mmu_ops.release_pte = xen_release_pte;
+ pv_mmu_ops.release_pmd = xen_release_pmd;
+#if PAGETABLE_LEVELS == 4
+ pv_mmu_ops.alloc_pud = xen_alloc_pud;
+ pv_mmu_ops.release_pud = xen_release_pud;
+#endif
+
+#ifdef CONFIG_X86_64
+ SetPagePinned(virt_to_page(level3_user_vsyscall));
+#endif
+ xen_mark_init_mm_pinned();
+}
+
+
+const struct pv_mmu_ops xen_mmu_ops __initdata = {
+ .pagetable_setup_start = xen_pagetable_setup_start,
+ .pagetable_setup_done = xen_pagetable_setup_done,
+
+ .read_cr2 = xen_read_cr2,
+ .write_cr2 = xen_write_cr2,
+
+ .read_cr3 = xen_read_cr3,
+ .write_cr3 = xen_write_cr3,
+
+ .flush_tlb_user = xen_flush_tlb,
+ .flush_tlb_kernel = xen_flush_tlb,
+ .flush_tlb_single = xen_flush_tlb_single,
+ .flush_tlb_others = xen_flush_tlb_others,
+
+ .pte_update = paravirt_nop,
+ .pte_update_defer = paravirt_nop,
+
+ .pgd_alloc = xen_pgd_alloc,
+ .pgd_free = xen_pgd_free,
+
+ .alloc_pte = xen_alloc_pte_init,
+ .release_pte = xen_release_pte_init,
+ .alloc_pmd = xen_alloc_pte_init,
+ .alloc_pmd_clone = paravirt_nop,
+ .release_pmd = xen_release_pte_init,
+
+#ifdef CONFIG_HIGHPTE
+ .kmap_atomic_pte = xen_kmap_atomic_pte,
+#endif
+
+#ifdef CONFIG_X86_64
+ .set_pte = xen_set_pte,
+#else
+ .set_pte = xen_set_pte_init,
+#endif
+ .set_pte_at = xen_set_pte_at,
+ .set_pmd = xen_set_pmd_hyper,
+
+ .ptep_modify_prot_start = __ptep_modify_prot_start,
+ .ptep_modify_prot_commit = __ptep_modify_prot_commit,
+
+ .pte_val = PV_CALLEE_SAVE(xen_pte_val),
+ .pgd_val = PV_CALLEE_SAVE(xen_pgd_val),
+
+ .make_pte = PV_CALLEE_SAVE(xen_make_pte),
+ .make_pgd = PV_CALLEE_SAVE(xen_make_pgd),
+
+#ifdef CONFIG_X86_PAE
+ .set_pte_atomic = xen_set_pte_atomic,
+ .set_pte_present = xen_set_pte_at,
+ .pte_clear = xen_pte_clear,
+ .pmd_clear = xen_pmd_clear,
+#endif /* CONFIG_X86_PAE */
+ .set_pud = xen_set_pud_hyper,
+
+ .make_pmd = PV_CALLEE_SAVE(xen_make_pmd),
+ .pmd_val = PV_CALLEE_SAVE(xen_pmd_val),
+
+#if PAGETABLE_LEVELS == 4
+ .pud_val = PV_CALLEE_SAVE(xen_pud_val),
+ .make_pud = PV_CALLEE_SAVE(xen_make_pud),
+ .set_pgd = xen_set_pgd_hyper,
+
+ .alloc_pud = xen_alloc_pte_init,
+ .release_pud = xen_release_pte_init,
+#endif /* PAGETABLE_LEVELS == 4 */
+
+ .activate_mm = xen_activate_mm,
+ .dup_mmap = xen_dup_mmap,
+ .exit_mmap = xen_exit_mmap,
+
+ .lazy_mode = {
+ .enter = paravirt_enter_lazy_mmu,
+ .leave = xen_leave_lazy,
+ },
+
+ .set_fixmap = xen_set_fixmap,
+};
+
+
#ifdef CONFIG_XEN_DEBUG_FS
static struct dentry *d_mmu_debug;
diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h
index 98d7165..24d1b44 100644
--- a/arch/x86/xen/mmu.h
+++ b/arch/x86/xen/mmu.h
@@ -54,4 +54,7 @@
void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte);
+unsigned long xen_read_cr2_direct(void);
+
+extern const struct pv_mmu_ops xen_mmu_ops;
#endif /* _XEN_MMU_H */
diff --git a/arch/x86/xen/multicalls.h b/arch/x86/xen/multicalls.h
index fa3e107..9e565da 100644
--- a/arch/x86/xen/multicalls.h
+++ b/arch/x86/xen/multicalls.h
@@ -41,7 +41,7 @@
xen_mc_flush();
/* restore flags saved in xen_mc_batch */
- local_irq_restore(x86_read_percpu(xen_mc_irq_flags));
+ local_irq_restore(percpu_read(xen_mc_irq_flags));
}
/* Set up a callback to be called when the current batch is flushed */
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index c44e206..035582a 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -50,11 +50,7 @@
*/
static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id)
{
-#ifdef CONFIG_X86_32
- __get_cpu_var(irq_stat).irq_resched_count++;
-#else
- add_pda(irq_resched_count, 1);
-#endif
+ inc_irq_stat(irq_resched_count);
return IRQ_HANDLED;
}
@@ -78,7 +74,7 @@
xen_setup_cpu_clockevents();
cpu_set(cpu, cpu_online_map);
- x86_write_percpu(cpu_state, CPU_ONLINE);
+ percpu_write(cpu_state, CPU_ONLINE);
wmb();
/* We can take interrupts now: we're officially "up". */
@@ -174,7 +170,7 @@
/* We've switched to the "real" per-cpu gdt, so make sure the
old memory can be recycled */
- make_lowmem_page_readwrite(&per_cpu_var(gdt_page));
+ make_lowmem_page_readwrite(xen_initial_gdt);
xen_setup_vcpu_info_placement();
}
@@ -239,6 +235,8 @@
ctxt->user_regs.ss = __KERNEL_DS;
#ifdef CONFIG_X86_32
ctxt->user_regs.fs = __KERNEL_PERCPU;
+#else
+ ctxt->gs_base_kernel = per_cpu_offset(cpu);
#endif
ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle;
ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */
@@ -283,23 +281,14 @@
struct task_struct *idle = idle_task(cpu);
int rc;
-#ifdef CONFIG_X86_64
- /* Allocate node local memory for AP pdas */
- WARN_ON(cpu == 0);
- if (cpu > 0) {
- rc = get_local_pda(cpu);
- if (rc)
- return rc;
- }
-#endif
-
-#ifdef CONFIG_X86_32
- init_gdt(cpu);
per_cpu(current_task, cpu) = idle;
+#ifdef CONFIG_X86_32
irq_ctx_init(cpu);
#else
- cpu_pda(cpu)->pcurrent = idle;
clear_tsk_thread_flag(idle, TIF_FORK);
+ per_cpu(kernel_stack, cpu) =
+ (unsigned long)task_stack_page(idle) -
+ KERNEL_STACK_OFFSET + THREAD_SIZE;
#endif
xen_setup_timer(cpu);
xen_init_lock_cpu(cpu);
@@ -445,11 +434,7 @@
{
irq_enter();
generic_smp_call_function_interrupt();
-#ifdef CONFIG_X86_32
- __get_cpu_var(irq_stat).irq_call_count++;
-#else
- add_pda(irq_call_count, 1);
-#endif
+ inc_irq_stat(irq_call_count);
irq_exit();
return IRQ_HANDLED;
@@ -459,11 +444,7 @@
{
irq_enter();
generic_smp_call_function_single_interrupt();
-#ifdef CONFIG_X86_32
- __get_cpu_var(irq_stat).irq_call_count++;
-#else
- add_pda(irq_call_count, 1);
-#endif
+ inc_irq_stat(irq_call_count);
irq_exit();
return IRQ_HANDLED;
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index 212ffe0..95be7b4 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -6,6 +6,7 @@
#include <asm/xen/hypercall.h>
#include <asm/xen/page.h>
+#include <asm/fixmap.h>
#include "xen-ops.h"
#include "mmu.h"
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
new file mode 100644
index 0000000..79d7362
--- /dev/null
+++ b/arch/x86/xen/xen-asm.S
@@ -0,0 +1,142 @@
+/*
+ * Asm versions of Xen pv-ops, suitable for either direct use or
+ * inlining. The inline versions are the same as the direct-use
+ * versions, with the pre- and post-amble chopped off.
+ *
+ * This code is encoded for size rather than absolute efficiency, with
+ * a view to being able to inline as much as possible.
+ *
+ * We only bother with direct forms (ie, vcpu in percpu data) of the
+ * operations here; the indirect forms are better handled in C, since
+ * they're generally too large to inline anyway.
+ */
+
+#include <asm/asm-offsets.h>
+#include <asm/percpu.h>
+#include <asm/processor-flags.h>
+
+#include "xen-asm.h"
+
+/*
+ * Enable events. This clears the event mask and tests the pending
+ * event status with one and operation. If there are pending events,
+ * then enter the hypervisor to get them handled.
+ */
+ENTRY(xen_irq_enable_direct)
+ /* Unmask events */
+ movb $0, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
+
+ /*
+ * Preempt here doesn't matter because that will deal with any
+ * pending interrupts. The pending check may end up being run
+ * on the wrong CPU, but that doesn't hurt.
+ */
+
+ /* Test for pending */
+ testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending
+ jz 1f
+
+2: call check_events
+1:
+ENDPATCH(xen_irq_enable_direct)
+ ret
+ ENDPROC(xen_irq_enable_direct)
+ RELOC(xen_irq_enable_direct, 2b+1)
+
+
+/*
+ * Disabling events is simply a matter of making the event mask
+ * non-zero.
+ */
+ENTRY(xen_irq_disable_direct)
+ movb $1, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
+ENDPATCH(xen_irq_disable_direct)
+ ret
+ ENDPROC(xen_irq_disable_direct)
+ RELOC(xen_irq_disable_direct, 0)
+
+/*
+ * (xen_)save_fl is used to get the current interrupt enable status.
+ * Callers expect the status to be in X86_EFLAGS_IF, and other bits
+ * may be set in the return value. We take advantage of this by
+ * making sure that X86_EFLAGS_IF has the right value (and other bits
+ * in that byte are 0), but other bits in the return value are
+ * undefined. We need to toggle the state of the bit, because Xen and
+ * x86 use opposite senses (mask vs enable).
+ */
+ENTRY(xen_save_fl_direct)
+ testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
+ setz %ah
+ addb %ah, %ah
+ENDPATCH(xen_save_fl_direct)
+ ret
+ ENDPROC(xen_save_fl_direct)
+ RELOC(xen_save_fl_direct, 0)
+
+
+/*
+ * In principle the caller should be passing us a value return from
+ * xen_save_fl_direct, but for robustness sake we test only the
+ * X86_EFLAGS_IF flag rather than the whole byte. After setting the
+ * interrupt mask state, it checks for unmasked pending events and
+ * enters the hypervisor to get them delivered if so.
+ */
+ENTRY(xen_restore_fl_direct)
+#ifdef CONFIG_X86_64
+ testw $X86_EFLAGS_IF, %di
+#else
+ testb $X86_EFLAGS_IF>>8, %ah
+#endif
+ setz PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
+ /*
+ * Preempt here doesn't matter because that will deal with any
+ * pending interrupts. The pending check may end up being run
+ * on the wrong CPU, but that doesn't hurt.
+ */
+
+ /* check for unmasked and pending */
+ cmpw $0x0001, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending
+ jz 1f
+2: call check_events
+1:
+ENDPATCH(xen_restore_fl_direct)
+ ret
+ ENDPROC(xen_restore_fl_direct)
+ RELOC(xen_restore_fl_direct, 2b+1)
+
+
+/*
+ * Force an event check by making a hypercall, but preserve regs
+ * before making the call.
+ */
+check_events:
+#ifdef CONFIG_X86_32
+ push %eax
+ push %ecx
+ push %edx
+ call xen_force_evtchn_callback
+ pop %edx
+ pop %ecx
+ pop %eax
+#else
+ push %rax
+ push %rcx
+ push %rdx
+ push %rsi
+ push %rdi
+ push %r8
+ push %r9
+ push %r10
+ push %r11
+ call xen_force_evtchn_callback
+ pop %r11
+ pop %r10
+ pop %r9
+ pop %r8
+ pop %rdi
+ pop %rsi
+ pop %rdx
+ pop %rcx
+ pop %rax
+#endif
+ ret
diff --git a/arch/x86/xen/xen-asm.h b/arch/x86/xen/xen-asm.h
new file mode 100644
index 0000000..4652764
--- /dev/null
+++ b/arch/x86/xen/xen-asm.h
@@ -0,0 +1,12 @@
+#ifndef _XEN_XEN_ASM_H
+#define _XEN_XEN_ASM_H
+
+#include <linux/linkage.h>
+
+#define RELOC(x, v) .globl x##_reloc; x##_reloc=v
+#define ENDPATCH(x) .globl x##_end; x##_end=.
+
+/* Pseudo-flag used for virtual NMI, which we don't implement yet */
+#define XEN_EFLAGS_NMI 0x80000000
+
+#endif
diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S
index 42786f5..88e15de 100644
--- a/arch/x86/xen/xen-asm_32.S
+++ b/arch/x86/xen/xen-asm_32.S
@@ -1,298 +1,27 @@
/*
- Asm versions of Xen pv-ops, suitable for either direct use or inlining.
- The inline versions are the same as the direct-use versions, with the
- pre- and post-amble chopped off.
-
- This code is encoded for size rather than absolute efficiency,
- with a view to being able to inline as much as possible.
-
- We only bother with direct forms (ie, vcpu in pda) of the operations
- here; the indirect forms are better handled in C, since they're
- generally too large to inline anyway.
+ * Asm versions of Xen pv-ops, suitable for either direct use or
+ * inlining. The inline versions are the same as the direct-use
+ * versions, with the pre- and post-amble chopped off.
+ *
+ * This code is encoded for size rather than absolute efficiency, with
+ * a view to being able to inline as much as possible.
+ *
+ * We only bother with direct forms (ie, vcpu in pda) of the
+ * operations here; the indirect forms are better handled in C, since
+ * they're generally too large to inline anyway.
*/
-#include <linux/linkage.h>
-
-#include <asm/asm-offsets.h>
#include <asm/thread_info.h>
-#include <asm/percpu.h>
#include <asm/processor-flags.h>
#include <asm/segment.h>
#include <xen/interface/xen.h>
-#define RELOC(x, v) .globl x##_reloc; x##_reloc=v
-#define ENDPATCH(x) .globl x##_end; x##_end=.
-
-/* Pseudo-flag used for virtual NMI, which we don't implement yet */
-#define XEN_EFLAGS_NMI 0x80000000
+#include "xen-asm.h"
/*
- Enable events. This clears the event mask and tests the pending
- event status with one and operation. If there are pending
- events, then enter the hypervisor to get them handled.
- */
-ENTRY(xen_irq_enable_direct)
- /* Unmask events */
- movb $0, PER_CPU_VAR(xen_vcpu_info)+XEN_vcpu_info_mask
-
- /* Preempt here doesn't matter because that will deal with
- any pending interrupts. The pending check may end up being
- run on the wrong CPU, but that doesn't hurt. */
-
- /* Test for pending */
- testb $0xff, PER_CPU_VAR(xen_vcpu_info)+XEN_vcpu_info_pending
- jz 1f
-
-2: call check_events
-1:
-ENDPATCH(xen_irq_enable_direct)
- ret
- ENDPROC(xen_irq_enable_direct)
- RELOC(xen_irq_enable_direct, 2b+1)
-
-
-/*
- Disabling events is simply a matter of making the event mask
- non-zero.
- */
-ENTRY(xen_irq_disable_direct)
- movb $1, PER_CPU_VAR(xen_vcpu_info)+XEN_vcpu_info_mask
-ENDPATCH(xen_irq_disable_direct)
- ret
- ENDPROC(xen_irq_disable_direct)
- RELOC(xen_irq_disable_direct, 0)
-
-/*
- (xen_)save_fl is used to get the current interrupt enable status.
- Callers expect the status to be in X86_EFLAGS_IF, and other bits
- may be set in the return value. We take advantage of this by
- making sure that X86_EFLAGS_IF has the right value (and other bits
- in that byte are 0), but other bits in the return value are
- undefined. We need to toggle the state of the bit, because
- Xen and x86 use opposite senses (mask vs enable).
- */
-ENTRY(xen_save_fl_direct)
- testb $0xff, PER_CPU_VAR(xen_vcpu_info)+XEN_vcpu_info_mask
- setz %ah
- addb %ah,%ah
-ENDPATCH(xen_save_fl_direct)
- ret
- ENDPROC(xen_save_fl_direct)
- RELOC(xen_save_fl_direct, 0)
-
-
-/*
- In principle the caller should be passing us a value return
- from xen_save_fl_direct, but for robustness sake we test only
- the X86_EFLAGS_IF flag rather than the whole byte. After
- setting the interrupt mask state, it checks for unmasked
- pending events and enters the hypervisor to get them delivered
- if so.
- */
-ENTRY(xen_restore_fl_direct)
- testb $X86_EFLAGS_IF>>8, %ah
- setz PER_CPU_VAR(xen_vcpu_info)+XEN_vcpu_info_mask
- /* Preempt here doesn't matter because that will deal with
- any pending interrupts. The pending check may end up being
- run on the wrong CPU, but that doesn't hurt. */
-
- /* check for unmasked and pending */
- cmpw $0x0001, PER_CPU_VAR(xen_vcpu_info)+XEN_vcpu_info_pending
- jz 1f
-2: call check_events
-1:
-ENDPATCH(xen_restore_fl_direct)
- ret
- ENDPROC(xen_restore_fl_direct)
- RELOC(xen_restore_fl_direct, 2b+1)
-
-/*
- We can't use sysexit directly, because we're not running in ring0.
- But we can easily fake it up using iret. Assuming xen_sysexit
- is jumped to with a standard stack frame, we can just strip it
- back to a standard iret frame and use iret.
- */
-ENTRY(xen_sysexit)
- movl PT_EAX(%esp), %eax /* Shouldn't be necessary? */
- orl $X86_EFLAGS_IF, PT_EFLAGS(%esp)
- lea PT_EIP(%esp), %esp
-
- jmp xen_iret
-ENDPROC(xen_sysexit)
-
-/*
- This is run where a normal iret would be run, with the same stack setup:
- 8: eflags
- 4: cs
- esp-> 0: eip
-
- This attempts to make sure that any pending events are dealt
- with on return to usermode, but there is a small window in
- which an event can happen just before entering usermode. If
- the nested interrupt ends up setting one of the TIF_WORK_MASK
- pending work flags, they will not be tested again before
- returning to usermode. This means that a process can end up
- with pending work, which will be unprocessed until the process
- enters and leaves the kernel again, which could be an
- unbounded amount of time. This means that a pending signal or
- reschedule event could be indefinitely delayed.
-
- The fix is to notice a nested interrupt in the critical
- window, and if one occurs, then fold the nested interrupt into
- the current interrupt stack frame, and re-process it
- iteratively rather than recursively. This means that it will
- exit via the normal path, and all pending work will be dealt
- with appropriately.
-
- Because the nested interrupt handler needs to deal with the
- current stack state in whatever form its in, we keep things
- simple by only using a single register which is pushed/popped
- on the stack.
- */
-ENTRY(xen_iret)
- /* test eflags for special cases */
- testl $(X86_EFLAGS_VM | XEN_EFLAGS_NMI), 8(%esp)
- jnz hyper_iret
-
- push %eax
- ESP_OFFSET=4 # bytes pushed onto stack
-
- /* Store vcpu_info pointer for easy access. Do it this
- way to avoid having to reload %fs */
-#ifdef CONFIG_SMP
- GET_THREAD_INFO(%eax)
- movl TI_cpu(%eax),%eax
- movl __per_cpu_offset(,%eax,4),%eax
- mov per_cpu__xen_vcpu(%eax),%eax
-#else
- movl per_cpu__xen_vcpu, %eax
-#endif
-
- /* check IF state we're restoring */
- testb $X86_EFLAGS_IF>>8, 8+1+ESP_OFFSET(%esp)
-
- /* Maybe enable events. Once this happens we could get a
- recursive event, so the critical region starts immediately
- afterwards. However, if that happens we don't end up
- resuming the code, so we don't have to be worried about
- being preempted to another CPU. */
- setz XEN_vcpu_info_mask(%eax)
-xen_iret_start_crit:
-
- /* check for unmasked and pending */
- cmpw $0x0001, XEN_vcpu_info_pending(%eax)
-
- /* If there's something pending, mask events again so we
- can jump back into xen_hypervisor_callback */
- sete XEN_vcpu_info_mask(%eax)
-
- popl %eax
-
- /* From this point on the registers are restored and the stack
- updated, so we don't need to worry about it if we're preempted */
-iret_restore_end:
-
- /* Jump to hypervisor_callback after fixing up the stack.
- Events are masked, so jumping out of the critical
- region is OK. */
- je xen_hypervisor_callback
-
-1: iret
-xen_iret_end_crit:
-.section __ex_table,"a"
- .align 4
- .long 1b,iret_exc
-.previous
-
-hyper_iret:
- /* put this out of line since its very rarely used */
- jmp hypercall_page + __HYPERVISOR_iret * 32
-
- .globl xen_iret_start_crit, xen_iret_end_crit
-
-/*
- This is called by xen_hypervisor_callback in entry.S when it sees
- that the EIP at the time of interrupt was between xen_iret_start_crit
- and xen_iret_end_crit. We're passed the EIP in %eax so we can do
- a more refined determination of what to do.
-
- The stack format at this point is:
- ----------------
- ss : (ss/esp may be present if we came from usermode)
- esp :
- eflags } outer exception info
- cs }
- eip }
- ---------------- <- edi (copy dest)
- eax : outer eax if it hasn't been restored
- ----------------
- eflags } nested exception info
- cs } (no ss/esp because we're nested
- eip } from the same ring)
- orig_eax }<- esi (copy src)
- - - - - - - - -
- fs }
- es }
- ds } SAVE_ALL state
- eax }
- : :
- ebx }<- esp
- ----------------
-
- In order to deliver the nested exception properly, we need to shift
- everything from the return addr up to the error code so it
- sits just under the outer exception info. This means that when we
- handle the exception, we do it in the context of the outer exception
- rather than starting a new one.
-
- The only caveat is that if the outer eax hasn't been
- restored yet (ie, it's still on stack), we need to insert
- its value into the SAVE_ALL state before going on, since
- it's usermode state which we eventually need to restore.
- */
-ENTRY(xen_iret_crit_fixup)
- /*
- Paranoia: Make sure we're really coming from kernel space.
- One could imagine a case where userspace jumps into the
- critical range address, but just before the CPU delivers a GP,
- it decides to deliver an interrupt instead. Unlikely?
- Definitely. Easy to avoid? Yes. The Intel documents
- explicitly say that the reported EIP for a bad jump is the
- jump instruction itself, not the destination, but some virtual
- environments get this wrong.
- */
- movl PT_CS(%esp), %ecx
- andl $SEGMENT_RPL_MASK, %ecx
- cmpl $USER_RPL, %ecx
- je 2f
-
- lea PT_ORIG_EAX(%esp), %esi
- lea PT_EFLAGS(%esp), %edi
-
- /* If eip is before iret_restore_end then stack
- hasn't been restored yet. */
- cmp $iret_restore_end, %eax
- jae 1f
-
- movl 0+4(%edi),%eax /* copy EAX (just above top of frame) */
- movl %eax, PT_EAX(%esp)
-
- lea ESP_OFFSET(%edi),%edi /* move dest up over saved regs */
-
- /* set up the copy */
-1: std
- mov $PT_EIP / 4, %ecx /* saved regs up to orig_eax */
- rep movsl
- cld
-
- lea 4(%edi),%esp /* point esp to new frame */
-2: jmp xen_do_upcall
-
-
-/*
- Force an event check by making a hypercall,
- but preserve regs before making the call.
+ * Force an event check by making a hypercall, but preserve regs
+ * before making the call.
*/
check_events:
push %eax
@@ -303,3 +32,197 @@
pop %ecx
pop %eax
ret
+
+/*
+ * We can't use sysexit directly, because we're not running in ring0.
+ * But we can easily fake it up using iret. Assuming xen_sysexit is
+ * jumped to with a standard stack frame, we can just strip it back to
+ * a standard iret frame and use iret.
+ */
+ENTRY(xen_sysexit)
+ movl PT_EAX(%esp), %eax /* Shouldn't be necessary? */
+ orl $X86_EFLAGS_IF, PT_EFLAGS(%esp)
+ lea PT_EIP(%esp), %esp
+
+ jmp xen_iret
+ENDPROC(xen_sysexit)
+
+/*
+ * This is run where a normal iret would be run, with the same stack setup:
+ * 8: eflags
+ * 4: cs
+ * esp-> 0: eip
+ *
+ * This attempts to make sure that any pending events are dealt with
+ * on return to usermode, but there is a small window in which an
+ * event can happen just before entering usermode. If the nested
+ * interrupt ends up setting one of the TIF_WORK_MASK pending work
+ * flags, they will not be tested again before returning to
+ * usermode. This means that a process can end up with pending work,
+ * which will be unprocessed until the process enters and leaves the
+ * kernel again, which could be an unbounded amount of time. This
+ * means that a pending signal or reschedule event could be
+ * indefinitely delayed.
+ *
+ * The fix is to notice a nested interrupt in the critical window, and
+ * if one occurs, then fold the nested interrupt into the current
+ * interrupt stack frame, and re-process it iteratively rather than
+ * recursively. This means that it will exit via the normal path, and
+ * all pending work will be dealt with appropriately.
+ *
+ * Because the nested interrupt handler needs to deal with the current
+ * stack state in whatever form its in, we keep things simple by only
+ * using a single register which is pushed/popped on the stack.
+ */
+ENTRY(xen_iret)
+ /* test eflags for special cases */
+ testl $(X86_EFLAGS_VM | XEN_EFLAGS_NMI), 8(%esp)
+ jnz hyper_iret
+
+ push %eax
+ ESP_OFFSET=4 # bytes pushed onto stack
+
+ /*
+ * Store vcpu_info pointer for easy access. Do it this way to
+ * avoid having to reload %fs
+ */
+#ifdef CONFIG_SMP
+ GET_THREAD_INFO(%eax)
+ movl TI_cpu(%eax), %eax
+ movl __per_cpu_offset(,%eax,4), %eax
+ mov per_cpu__xen_vcpu(%eax), %eax
+#else
+ movl per_cpu__xen_vcpu, %eax
+#endif
+
+ /* check IF state we're restoring */
+ testb $X86_EFLAGS_IF>>8, 8+1+ESP_OFFSET(%esp)
+
+ /*
+ * Maybe enable events. Once this happens we could get a
+ * recursive event, so the critical region starts immediately
+ * afterwards. However, if that happens we don't end up
+ * resuming the code, so we don't have to be worried about
+ * being preempted to another CPU.
+ */
+ setz XEN_vcpu_info_mask(%eax)
+xen_iret_start_crit:
+
+ /* check for unmasked and pending */
+ cmpw $0x0001, XEN_vcpu_info_pending(%eax)
+
+ /*
+ * If there's something pending, mask events again so we can
+ * jump back into xen_hypervisor_callback
+ */
+ sete XEN_vcpu_info_mask(%eax)
+
+ popl %eax
+
+ /*
+ * From this point on the registers are restored and the stack
+ * updated, so we don't need to worry about it if we're
+ * preempted
+ */
+iret_restore_end:
+
+ /*
+ * Jump to hypervisor_callback after fixing up the stack.
+ * Events are masked, so jumping out of the critical region is
+ * OK.
+ */
+ je xen_hypervisor_callback
+
+1: iret
+xen_iret_end_crit:
+.section __ex_table, "a"
+ .align 4
+ .long 1b, iret_exc
+.previous
+
+hyper_iret:
+ /* put this out of line since its very rarely used */
+ jmp hypercall_page + __HYPERVISOR_iret * 32
+
+ .globl xen_iret_start_crit, xen_iret_end_crit
+
+/*
+ * This is called by xen_hypervisor_callback in entry.S when it sees
+ * that the EIP at the time of interrupt was between
+ * xen_iret_start_crit and xen_iret_end_crit. We're passed the EIP in
+ * %eax so we can do a more refined determination of what to do.
+ *
+ * The stack format at this point is:
+ * ----------------
+ * ss : (ss/esp may be present if we came from usermode)
+ * esp :
+ * eflags } outer exception info
+ * cs }
+ * eip }
+ * ---------------- <- edi (copy dest)
+ * eax : outer eax if it hasn't been restored
+ * ----------------
+ * eflags } nested exception info
+ * cs } (no ss/esp because we're nested
+ * eip } from the same ring)
+ * orig_eax }<- esi (copy src)
+ * - - - - - - - -
+ * fs }
+ * es }
+ * ds } SAVE_ALL state
+ * eax }
+ * : :
+ * ebx }<- esp
+ * ----------------
+ *
+ * In order to deliver the nested exception properly, we need to shift
+ * everything from the return addr up to the error code so it sits
+ * just under the outer exception info. This means that when we
+ * handle the exception, we do it in the context of the outer
+ * exception rather than starting a new one.
+ *
+ * The only caveat is that if the outer eax hasn't been restored yet
+ * (ie, it's still on stack), we need to insert its value into the
+ * SAVE_ALL state before going on, since it's usermode state which we
+ * eventually need to restore.
+ */
+ENTRY(xen_iret_crit_fixup)
+ /*
+ * Paranoia: Make sure we're really coming from kernel space.
+ * One could imagine a case where userspace jumps into the
+ * critical range address, but just before the CPU delivers a
+ * GP, it decides to deliver an interrupt instead. Unlikely?
+ * Definitely. Easy to avoid? Yes. The Intel documents
+ * explicitly say that the reported EIP for a bad jump is the
+ * jump instruction itself, not the destination, but some
+ * virtual environments get this wrong.
+ */
+ movl PT_CS(%esp), %ecx
+ andl $SEGMENT_RPL_MASK, %ecx
+ cmpl $USER_RPL, %ecx
+ je 2f
+
+ lea PT_ORIG_EAX(%esp), %esi
+ lea PT_EFLAGS(%esp), %edi
+
+ /*
+ * If eip is before iret_restore_end then stack
+ * hasn't been restored yet.
+ */
+ cmp $iret_restore_end, %eax
+ jae 1f
+
+ movl 0+4(%edi), %eax /* copy EAX (just above top of frame) */
+ movl %eax, PT_EAX(%esp)
+
+ lea ESP_OFFSET(%edi), %edi /* move dest up over saved regs */
+
+ /* set up the copy */
+1: std
+ mov $PT_EIP / 4, %ecx /* saved regs up to orig_eax */
+ rep movsl
+ cld
+
+ lea 4(%edi), %esp /* point esp to new frame */
+2: jmp xen_do_upcall
+
diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S
index 05794c5..02f496a 100644
--- a/arch/x86/xen/xen-asm_64.S
+++ b/arch/x86/xen/xen-asm_64.S
@@ -1,174 +1,45 @@
/*
- Asm versions of Xen pv-ops, suitable for either direct use or inlining.
- The inline versions are the same as the direct-use versions, with the
- pre- and post-amble chopped off.
-
- This code is encoded for size rather than absolute efficiency,
- with a view to being able to inline as much as possible.
-
- We only bother with direct forms (ie, vcpu in pda) of the operations
- here; the indirect forms are better handled in C, since they're
- generally too large to inline anyway.
+ * Asm versions of Xen pv-ops, suitable for either direct use or
+ * inlining. The inline versions are the same as the direct-use
+ * versions, with the pre- and post-amble chopped off.
+ *
+ * This code is encoded for size rather than absolute efficiency, with
+ * a view to being able to inline as much as possible.
+ *
+ * We only bother with direct forms (ie, vcpu in pda) of the
+ * operations here; the indirect forms are better handled in C, since
+ * they're generally too large to inline anyway.
*/
-#include <linux/linkage.h>
-
-#include <asm/asm-offsets.h>
-#include <asm/processor-flags.h>
#include <asm/errno.h>
+#include <asm/percpu.h>
+#include <asm/processor-flags.h>
#include <asm/segment.h>
#include <xen/interface/xen.h>
-#define RELOC(x, v) .globl x##_reloc; x##_reloc=v
-#define ENDPATCH(x) .globl x##_end; x##_end=.
-
-/* Pseudo-flag used for virtual NMI, which we don't implement yet */
-#define XEN_EFLAGS_NMI 0x80000000
-
-#if 1
-/*
- x86-64 does not yet support direct access to percpu variables
- via a segment override, so we just need to make sure this code
- never gets used
- */
-#define BUG ud2a
-#define PER_CPU_VAR(var, off) 0xdeadbeef
-#endif
-
-/*
- Enable events. This clears the event mask and tests the pending
- event status with one and operation. If there are pending
- events, then enter the hypervisor to get them handled.
- */
-ENTRY(xen_irq_enable_direct)
- BUG
-
- /* Unmask events */
- movb $0, PER_CPU_VAR(xen_vcpu_info, XEN_vcpu_info_mask)
-
- /* Preempt here doesn't matter because that will deal with
- any pending interrupts. The pending check may end up being
- run on the wrong CPU, but that doesn't hurt. */
-
- /* Test for pending */
- testb $0xff, PER_CPU_VAR(xen_vcpu_info, XEN_vcpu_info_pending)
- jz 1f
-
-2: call check_events
-1:
-ENDPATCH(xen_irq_enable_direct)
- ret
- ENDPROC(xen_irq_enable_direct)
- RELOC(xen_irq_enable_direct, 2b+1)
-
-/*
- Disabling events is simply a matter of making the event mask
- non-zero.
- */
-ENTRY(xen_irq_disable_direct)
- BUG
-
- movb $1, PER_CPU_VAR(xen_vcpu_info, XEN_vcpu_info_mask)
-ENDPATCH(xen_irq_disable_direct)
- ret
- ENDPROC(xen_irq_disable_direct)
- RELOC(xen_irq_disable_direct, 0)
-
-/*
- (xen_)save_fl is used to get the current interrupt enable status.
- Callers expect the status to be in X86_EFLAGS_IF, and other bits
- may be set in the return value. We take advantage of this by
- making sure that X86_EFLAGS_IF has the right value (and other bits
- in that byte are 0), but other bits in the return value are
- undefined. We need to toggle the state of the bit, because
- Xen and x86 use opposite senses (mask vs enable).
- */
-ENTRY(xen_save_fl_direct)
- BUG
-
- testb $0xff, PER_CPU_VAR(xen_vcpu_info, XEN_vcpu_info_mask)
- setz %ah
- addb %ah,%ah
-ENDPATCH(xen_save_fl_direct)
- ret
- ENDPROC(xen_save_fl_direct)
- RELOC(xen_save_fl_direct, 0)
-
-/*
- In principle the caller should be passing us a value return
- from xen_save_fl_direct, but for robustness sake we test only
- the X86_EFLAGS_IF flag rather than the whole byte. After
- setting the interrupt mask state, it checks for unmasked
- pending events and enters the hypervisor to get them delivered
- if so.
- */
-ENTRY(xen_restore_fl_direct)
- BUG
-
- testb $X86_EFLAGS_IF>>8, %ah
- setz PER_CPU_VAR(xen_vcpu_info, XEN_vcpu_info_mask)
- /* Preempt here doesn't matter because that will deal with
- any pending interrupts. The pending check may end up being
- run on the wrong CPU, but that doesn't hurt. */
-
- /* check for unmasked and pending */
- cmpw $0x0001, PER_CPU_VAR(xen_vcpu_info, XEN_vcpu_info_pending)
- jz 1f
-2: call check_events
-1:
-ENDPATCH(xen_restore_fl_direct)
- ret
- ENDPROC(xen_restore_fl_direct)
- RELOC(xen_restore_fl_direct, 2b+1)
-
-
-/*
- Force an event check by making a hypercall,
- but preserve regs before making the call.
- */
-check_events:
- push %rax
- push %rcx
- push %rdx
- push %rsi
- push %rdi
- push %r8
- push %r9
- push %r10
- push %r11
- call xen_force_evtchn_callback
- pop %r11
- pop %r10
- pop %r9
- pop %r8
- pop %rdi
- pop %rsi
- pop %rdx
- pop %rcx
- pop %rax
- ret
+#include "xen-asm.h"
ENTRY(xen_adjust_exception_frame)
- mov 8+0(%rsp),%rcx
- mov 8+8(%rsp),%r11
+ mov 8+0(%rsp), %rcx
+ mov 8+8(%rsp), %r11
ret $16
hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32
/*
- Xen64 iret frame:
-
- ss
- rsp
- rflags
- cs
- rip <-- standard iret frame
-
- flags
-
- rcx }
- r11 }<-- pushed by hypercall page
-rsp -> rax }
+ * Xen64 iret frame:
+ *
+ * ss
+ * rsp
+ * rflags
+ * cs
+ * rip <-- standard iret frame
+ *
+ * flags
+ *
+ * rcx }
+ * r11 }<-- pushed by hypercall page
+ * rsp->rax }
*/
ENTRY(xen_iret)
pushq $0
@@ -177,8 +48,8 @@
RELOC(xen_iret, 1b+1)
/*
- sysexit is not used for 64-bit processes, so it's
- only ever used to return to 32-bit compat userspace.
+ * sysexit is not used for 64-bit processes, so it's only ever used to
+ * return to 32-bit compat userspace.
*/
ENTRY(xen_sysexit)
pushq $__USER32_DS
@@ -193,13 +64,15 @@
RELOC(xen_sysexit, 1b+1)
ENTRY(xen_sysret64)
- /* We're already on the usermode stack at this point, but still
- with the kernel gs, so we can easily switch back */
- movq %rsp, %gs:pda_oldrsp
- movq %gs:pda_kernelstack,%rsp
+ /*
+ * We're already on the usermode stack at this point, but
+ * still with the kernel gs, so we can easily switch back
+ */
+ movq %rsp, PER_CPU_VAR(old_rsp)
+ movq PER_CPU_VAR(kernel_stack), %rsp
pushq $__USER_DS
- pushq %gs:pda_oldrsp
+ pushq PER_CPU_VAR(old_rsp)
pushq %r11
pushq $__USER_CS
pushq %rcx
@@ -210,13 +83,15 @@
RELOC(xen_sysret64, 1b+1)
ENTRY(xen_sysret32)
- /* We're already on the usermode stack at this point, but still
- with the kernel gs, so we can easily switch back */
- movq %rsp, %gs:pda_oldrsp
- movq %gs:pda_kernelstack, %rsp
+ /*
+ * We're already on the usermode stack at this point, but
+ * still with the kernel gs, so we can easily switch back
+ */
+ movq %rsp, PER_CPU_VAR(old_rsp)
+ movq PER_CPU_VAR(kernel_stack), %rsp
pushq $__USER32_DS
- pushq %gs:pda_oldrsp
+ pushq PER_CPU_VAR(old_rsp)
pushq %r11
pushq $__USER32_CS
pushq %rcx
@@ -227,28 +102,27 @@
RELOC(xen_sysret32, 1b+1)
/*
- Xen handles syscall callbacks much like ordinary exceptions,
- which means we have:
- - kernel gs
- - kernel rsp
- - an iret-like stack frame on the stack (including rcx and r11):
- ss
- rsp
- rflags
- cs
- rip
- r11
- rsp-> rcx
-
- In all the entrypoints, we undo all that to make it look
- like a CPU-generated syscall/sysenter and jump to the normal
- entrypoint.
+ * Xen handles syscall callbacks much like ordinary exceptions, which
+ * means we have:
+ * - kernel gs
+ * - kernel rsp
+ * - an iret-like stack frame on the stack (including rcx and r11):
+ * ss
+ * rsp
+ * rflags
+ * cs
+ * rip
+ * r11
+ * rsp->rcx
+ *
+ * In all the entrypoints, we undo all that to make it look like a
+ * CPU-generated syscall/sysenter and jump to the normal entrypoint.
*/
.macro undo_xen_syscall
- mov 0*8(%rsp),%rcx
- mov 1*8(%rsp),%r11
- mov 5*8(%rsp),%rsp
+ mov 0*8(%rsp), %rcx
+ mov 1*8(%rsp), %r11
+ mov 5*8(%rsp), %rsp
.endm
/* Normal 64-bit system call target */
@@ -275,7 +149,7 @@
ENTRY(xen_syscall32_target)
ENTRY(xen_sysenter_target)
- lea 16(%rsp), %rsp /* strip %rcx,%r11 */
+ lea 16(%rsp), %rsp /* strip %rcx, %r11 */
mov $-ENOSYS, %rax
pushq $VGCF_in_syscall
jmp hypercall_iret
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index c1f8faf..2f5ef26 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -10,9 +10,12 @@
extern const char xen_hypervisor_callback[];
extern const char xen_failsafe_callback[];
+extern void *xen_initial_gdt;
+
struct trap_info;
void xen_copy_trap_info(struct trap_info *traps);
+DECLARE_PER_CPU(struct vcpu_info, xen_vcpu_info);
DECLARE_PER_CPU(unsigned long, xen_cr3);
DECLARE_PER_CPU(unsigned long, xen_current_cr3);
@@ -22,6 +25,13 @@
void xen_setup_mfn_list_list(void);
void xen_setup_shared_info(void);
+void xen_setup_machphys_mapping(void);
+pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn);
+void xen_ident_map_ISA(void);
+void xen_reserve_top(void);
+
+void xen_leave_lazy(void);
+void xen_post_allocator_init(void);
char * __init xen_memory_setup(void);
void __init xen_arch_setup(void);
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index d7f9839..a7799a9 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -9,6 +9,7 @@
depends on PCI
depends on PM
select PNP
+ select CPU_IDLE
default y
---help---
Advanced Configuration and Power Interface (ACPI) support for
@@ -287,7 +288,7 @@
support physical cpu/memory hot-plug.
If one selects "m", this driver can be loaded with
- "modprobe acpi_container".
+ "modprobe container".
config ACPI_HOTPLUG_MEMORY
tristate "Memory Hotplug"
diff --git a/drivers/acpi/acpica/tbutils.c b/drivers/acpi/acpica/tbutils.c
index 9684cc8..22ce489 100644
--- a/drivers/acpi/acpica/tbutils.c
+++ b/drivers/acpi/acpica/tbutils.c
@@ -538,10 +538,9 @@
if (ACPI_FAILURE(status)) {
ACPI_WARNING((AE_INFO,
"Truncating %u table entries!",
- (unsigned)
- (acpi_gbl_root_table_list.size -
- acpi_gbl_root_table_list.
- count)));
+ (unsigned) (table_count -
+ (acpi_gbl_root_table_list.
+ count - 2))));
break;
}
}
diff --git a/drivers/acpi/acpica/uteval.c b/drivers/acpi/acpica/uteval.c
index da9450bc..9c9897d 100644
--- a/drivers/acpi/acpica/uteval.c
+++ b/drivers/acpi/acpica/uteval.c
@@ -116,9 +116,9 @@
return_ACPI_STATUS(AE_NO_MEMORY);
}
- /* Default return value is SUPPORTED */
+ /* Default return value is 0, NOT-SUPPORTED */
- return_desc->integer.value = ACPI_UINT32_MAX;
+ return_desc->integer.value = 0;
walk_state->return_desc = return_desc;
/* Compare input string to static table of supported interfaces */
@@ -127,10 +127,8 @@
if (!ACPI_STRCMP
(string_desc->string.pointer,
acpi_interfaces_supported[i])) {
-
- /* The interface is supported */
-
- return_ACPI_STATUS(AE_OK);
+ return_desc->integer.value = ACPI_UINT32_MAX;
+ goto done;
}
}
@@ -141,15 +139,14 @@
*/
status = acpi_os_validate_interface(string_desc->string.pointer);
if (ACPI_SUCCESS(status)) {
-
- /* The interface is supported */
-
- return_ACPI_STATUS(AE_OK);
+ return_desc->integer.value = ACPI_UINT32_MAX;
}
- /* The interface is not supported */
+done:
+ ACPI_DEBUG_PRINT_RAW((ACPI_DB_INFO, "ACPI: BIOS _OSI(%s) %ssupported\n",
+ string_desc->string.pointer,
+ return_desc->integer.value == 0 ? "not-" : ""));
- return_desc->integer.value = 0;
return_ACPI_STATUS(AE_OK);
}
diff --git a/drivers/acpi/container.c b/drivers/acpi/container.c
index 17020c1..fe0cdf8 100644
--- a/drivers/acpi/container.c
+++ b/drivers/acpi/container.c
@@ -163,7 +163,7 @@
case ACPI_NOTIFY_BUS_CHECK:
/* Fall through */
case ACPI_NOTIFY_DEVICE_CHECK:
- printk("Container driver received %s event\n",
+ printk(KERN_WARNING "Container driver received %s event\n",
(type == ACPI_NOTIFY_BUS_CHECK) ?
"ACPI_NOTIFY_BUS_CHECK" : "ACPI_NOTIFY_DEVICE_CHECK");
status = acpi_bus_get_device(handle, &device);
@@ -174,7 +174,8 @@
kobject_uevent(&device->dev.kobj,
KOBJ_ONLINE);
else
- printk("Failed to add container\n");
+ printk(KERN_WARNING
+ "Failed to add container\n");
}
} else {
if (ACPI_SUCCESS(status)) {
diff --git a/drivers/acpi/dock.c b/drivers/acpi/dock.c
index 5b30b8d..35094f2 100644
--- a/drivers/acpi/dock.c
+++ b/drivers/acpi/dock.c
@@ -855,10 +855,14 @@
static ssize_t show_docked(struct device *dev,
struct device_attribute *attr, char *buf)
{
+ struct acpi_device *tmp;
+
struct dock_station *dock_station = *((struct dock_station **)
dev->platform_data);
- return snprintf(buf, PAGE_SIZE, "%d\n", dock_present(dock_station));
+ if (ACPI_SUCCESS(acpi_bus_get_device(dock_station->handle, &tmp)))
+ return snprintf(buf, PAGE_SIZE, "1\n");
+ return snprintf(buf, PAGE_SIZE, "0\n");
}
static DEVICE_ATTR(docked, S_IRUGO, show_docked, NULL);
@@ -984,7 +988,7 @@
ret = device_create_file(&dock_device->dev, &dev_attr_docked);
if (ret) {
- printk("Error %d adding sysfs file\n", ret);
+ printk(KERN_ERR "Error %d adding sysfs file\n", ret);
platform_device_unregister(dock_device);
kfree(dock_station);
dock_station = NULL;
@@ -992,7 +996,7 @@
}
ret = device_create_file(&dock_device->dev, &dev_attr_undock);
if (ret) {
- printk("Error %d adding sysfs file\n", ret);
+ printk(KERN_ERR "Error %d adding sysfs file\n", ret);
device_remove_file(&dock_device->dev, &dev_attr_docked);
platform_device_unregister(dock_device);
kfree(dock_station);
@@ -1001,7 +1005,7 @@
}
ret = device_create_file(&dock_device->dev, &dev_attr_uid);
if (ret) {
- printk("Error %d adding sysfs file\n", ret);
+ printk(KERN_ERR "Error %d adding sysfs file\n", ret);
device_remove_file(&dock_device->dev, &dev_attr_docked);
device_remove_file(&dock_device->dev, &dev_attr_undock);
platform_device_unregister(dock_device);
@@ -1011,7 +1015,7 @@
}
ret = device_create_file(&dock_device->dev, &dev_attr_flags);
if (ret) {
- printk("Error %d adding sysfs file\n", ret);
+ printk(KERN_ERR "Error %d adding sysfs file\n", ret);
device_remove_file(&dock_device->dev, &dev_attr_docked);
device_remove_file(&dock_device->dev, &dev_attr_undock);
device_remove_file(&dock_device->dev, &dev_attr_uid);
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index a2b82c9..5c2f5d3 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -982,7 +982,7 @@
saved_ec = kmalloc(sizeof(struct acpi_ec), GFP_KERNEL);
if (!saved_ec)
return -ENOMEM;
- memcpy(&saved_ec, boot_ec, sizeof(saved_ec));
+ memcpy(saved_ec, boot_ec, sizeof(*saved_ec));
/* fall through */
}
/* This workaround is needed only on some broken machines,
diff --git a/drivers/acpi/glue.c b/drivers/acpi/glue.c
index adec3d1..5479b9f 100644
--- a/drivers/acpi/glue.c
+++ b/drivers/acpi/glue.c
@@ -255,12 +255,12 @@
}
type = acpi_get_bus_type(dev->bus);
if (!type) {
- DBG("No ACPI bus support for %s\n", dev->bus_id);
+ DBG("No ACPI bus support for %s\n", dev_name(dev));
ret = -EINVAL;
goto end;
}
if ((ret = type->find_device(dev, &handle)) != 0)
- DBG("Can't get handler for %s\n", dev->bus_id);
+ DBG("Can't get handler for %s\n", dev_name(dev));
end:
if (!ret)
acpi_bind_one(dev, handle);
@@ -271,10 +271,10 @@
acpi_get_name(dev->archdata.acpi_handle,
ACPI_FULL_PATHNAME, &buffer);
- DBG("Device %s -> %s\n", dev->bus_id, (char *)buffer.pointer);
+ DBG("Device %s -> %s\n", dev_name(dev), (char *)buffer.pointer);
kfree(buffer.pointer);
} else
- DBG("Device %s -> No ACPI support\n", dev->bus_id);
+ DBG("Device %s -> No ACPI support\n", dev_name(dev));
#endif
return ret;
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 6729a49..b3193ec 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -228,10 +228,10 @@
if (acpi_in_debugger) {
kdb_printf("%s", buffer);
} else {
- printk("%s", buffer);
+ printk(KERN_CONT "%s", buffer);
}
#else
- printk("%s", buffer);
+ printk(KERN_CONT "%s", buffer);
#endif
}
@@ -1317,6 +1317,54 @@
return AE_SUPPORT;
}
+#ifdef CONFIG_X86
+
+struct aml_port_desc {
+ uint start;
+ uint end;
+ char* name;
+ char warned;
+};
+
+static struct aml_port_desc aml_invalid_port_list[] = {
+ {0x20, 0x21, "PIC0", 0},
+ {0xA0, 0xA1, "PIC1", 0},
+ {0x4D0, 0x4D1, "ELCR", 0}
+};
+
+/*
+ * valid_aml_io_address()
+ *
+ * if valid, return true
+ * else invalid, warn once, return false
+ */
+static bool valid_aml_io_address(uint address, uint length)
+{
+ int i;
+ int entries = sizeof(aml_invalid_port_list) / sizeof(struct aml_port_desc);
+
+ for (i = 0; i < entries; ++i) {
+ if ((address >= aml_invalid_port_list[i].start &&
+ address <= aml_invalid_port_list[i].end) ||
+ (address + length >= aml_invalid_port_list[i].start &&
+ address + length <= aml_invalid_port_list[i].end))
+ {
+ if (!aml_invalid_port_list[i].warned)
+ {
+ printk(KERN_ERR "ACPI: Denied BIOS AML access"
+ " to invalid port 0x%x+0x%x (%s)\n",
+ address, length,
+ aml_invalid_port_list[i].name);
+ aml_invalid_port_list[i].warned = 1;
+ }
+ return false; /* invalid */
+ }
+ }
+ return true; /* valid */
+}
+#else
+static inline bool valid_aml_io_address(uint address, uint length) { return true; }
+#endif
/******************************************************************************
*
* FUNCTION: acpi_os_validate_address
@@ -1346,6 +1394,8 @@
switch (space_id) {
case ACPI_ADR_SPACE_SYSTEM_IO:
+ if (!valid_aml_io_address(address, length))
+ return AE_AML_ILLEGAL_ADDRESS;
case ACPI_ADR_SPACE_SYSTEM_MEMORY:
/* Only interference checks against SystemIO and SytemMemory
are needed */
diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c
index 1c6e73c..6c772ca 100644
--- a/drivers/acpi/pci_link.c
+++ b/drivers/acpi/pci_link.c
@@ -593,7 +593,7 @@
return -ENODEV;
} else {
acpi_irq_penalty[link->irq.active] += PIRQ_PENALTY_PCI_USING;
- printk(PREFIX "%s [%s] enabled at IRQ %d\n",
+ printk(KERN_WARNING PREFIX "%s [%s] enabled at IRQ %d\n",
acpi_device_name(link->device),
acpi_device_bid(link->device), link->irq.active);
}
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 66a9d81..7bc22a4 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -66,43 +66,17 @@
#define ACPI_PROCESSOR_FILE_POWER "power"
#define US_TO_PM_TIMER_TICKS(t) ((t * (PM_TIMER_FREQUENCY/1000)) / 1000)
#define PM_TIMER_TICK_NS (1000000000ULL/PM_TIMER_FREQUENCY)
-#ifndef CONFIG_CPU_IDLE
-#define C2_OVERHEAD 4 /* 1us (3.579 ticks per us) */
-#define C3_OVERHEAD 4 /* 1us (3.579 ticks per us) */
-static void (*pm_idle_save) (void) __read_mostly;
-#else
#define C2_OVERHEAD 1 /* 1us */
#define C3_OVERHEAD 1 /* 1us */
-#endif
#define PM_TIMER_TICKS_TO_US(p) (((p) * 1000)/(PM_TIMER_FREQUENCY/1000))
static unsigned int max_cstate __read_mostly = ACPI_PROCESSOR_MAX_POWER;
-#ifdef CONFIG_CPU_IDLE
module_param(max_cstate, uint, 0000);
-#else
-module_param(max_cstate, uint, 0644);
-#endif
static unsigned int nocst __read_mostly;
module_param(nocst, uint, 0000);
-#ifndef CONFIG_CPU_IDLE
-/*
- * bm_history -- bit-mask with a bit per jiffy of bus-master activity
- * 1000 HZ: 0xFFFFFFFF: 32 jiffies = 32ms
- * 800 HZ: 0xFFFFFFFF: 32 jiffies = 40ms
- * 100 HZ: 0x0000000F: 4 jiffies = 40ms
- * reduce history for more aggressive entry into C3
- */
-static unsigned int bm_history __read_mostly =
- (HZ >= 800 ? 0xFFFFFFFF : ((1U << (HZ / 25)) - 1));
-module_param(bm_history, uint, 0644);
-
-static int acpi_processor_set_power_policy(struct acpi_processor *pr);
-
-#else /* CONFIG_CPU_IDLE */
static unsigned int latency_factor __read_mostly = 2;
module_param(latency_factor, uint, 0644);
-#endif
/*
* IBM ThinkPad R40e crashes mysteriously when going into C2 or C3.
@@ -224,71 +198,6 @@
current_thread_info()->status |= TS_POLLING;
}
-#ifndef CONFIG_CPU_IDLE
-
-static void
-acpi_processor_power_activate(struct acpi_processor *pr,
- struct acpi_processor_cx *new)
-{
- struct acpi_processor_cx *old;
-
- if (!pr || !new)
- return;
-
- old = pr->power.state;
-
- if (old)
- old->promotion.count = 0;
- new->demotion.count = 0;
-
- /* Cleanup from old state. */
- if (old) {
- switch (old->type) {
- case ACPI_STATE_C3:
- /* Disable bus master reload */
- if (new->type != ACPI_STATE_C3 && pr->flags.bm_check)
- acpi_set_register(ACPI_BITREG_BUS_MASTER_RLD, 0);
- break;
- }
- }
-
- /* Prepare to use new state. */
- switch (new->type) {
- case ACPI_STATE_C3:
- /* Enable bus master reload */
- if (old->type != ACPI_STATE_C3 && pr->flags.bm_check)
- acpi_set_register(ACPI_BITREG_BUS_MASTER_RLD, 1);
- break;
- }
-
- pr->power.state = new;
-
- return;
-}
-
-static atomic_t c3_cpu_count;
-
-/* Common C-state entry for C2, C3, .. */
-static void acpi_cstate_enter(struct acpi_processor_cx *cstate)
-{
- /* Don't trace irqs off for idle */
- stop_critical_timings();
- if (cstate->entry_method == ACPI_CSTATE_FFH) {
- /* Call into architectural FFH based C-state */
- acpi_processor_ffh_cstate_enter(cstate);
- } else {
- int unused;
- /* IO port based C-state */
- inb(cstate->address);
- /* Dummy wait op - must do something useless after P_LVL2 read
- because chipsets cannot guarantee that STPCLK# signal
- gets asserted in time to freeze execution properly. */
- unused = inl(acpi_gbl_FADT.xpm_timer_block.address);
- }
- start_critical_timings();
-}
-#endif /* !CONFIG_CPU_IDLE */
-
#ifdef ARCH_APICTIMER_STOPS_ON_C3
/*
@@ -390,421 +299,6 @@
}
#endif
-#ifndef CONFIG_CPU_IDLE
-static void acpi_processor_idle(void)
-{
- struct acpi_processor *pr = NULL;
- struct acpi_processor_cx *cx = NULL;
- struct acpi_processor_cx *next_state = NULL;
- int sleep_ticks = 0;
- u32 t1, t2 = 0;
-
- /*
- * Interrupts must be disabled during bus mastering calculations and
- * for C2/C3 transitions.
- */
- local_irq_disable();
-
- pr = __get_cpu_var(processors);
- if (!pr) {
- local_irq_enable();
- return;
- }
-
- /*
- * Check whether we truly need to go idle, or should
- * reschedule:
- */
- if (unlikely(need_resched())) {
- local_irq_enable();
- return;
- }
-
- cx = pr->power.state;
- if (!cx || acpi_idle_suspend) {
- if (pm_idle_save) {
- pm_idle_save(); /* enables IRQs */
- } else {
- acpi_safe_halt();
- local_irq_enable();
- }
-
- return;
- }
-
- /*
- * Check BM Activity
- * -----------------
- * Check for bus mastering activity (if required), record, and check
- * for demotion.
- */
- if (pr->flags.bm_check) {
- u32 bm_status = 0;
- unsigned long diff = jiffies - pr->power.bm_check_timestamp;
-
- if (diff > 31)
- diff = 31;
-
- pr->power.bm_activity <<= diff;
-
- acpi_get_register(ACPI_BITREG_BUS_MASTER_STATUS, &bm_status);
- if (bm_status) {
- pr->power.bm_activity |= 0x1;
- acpi_set_register(ACPI_BITREG_BUS_MASTER_STATUS, 1);
- }
- /*
- * PIIX4 Erratum #18: Note that BM_STS doesn't always reflect
- * the true state of bus mastering activity; forcing us to
- * manually check the BMIDEA bit of each IDE channel.
- */
- else if (errata.piix4.bmisx) {
- if ((inb_p(errata.piix4.bmisx + 0x02) & 0x01)
- || (inb_p(errata.piix4.bmisx + 0x0A) & 0x01))
- pr->power.bm_activity |= 0x1;
- }
-
- pr->power.bm_check_timestamp = jiffies;
-
- /*
- * If bus mastering is or was active this jiffy, demote
- * to avoid a faulty transition. Note that the processor
- * won't enter a low-power state during this call (to this
- * function) but should upon the next.
- *
- * TBD: A better policy might be to fallback to the demotion
- * state (use it for this quantum only) istead of
- * demoting -- and rely on duration as our sole demotion
- * qualification. This may, however, introduce DMA
- * issues (e.g. floppy DMA transfer overrun/underrun).
- */
- if ((pr->power.bm_activity & 0x1) &&
- cx->demotion.threshold.bm) {
- local_irq_enable();
- next_state = cx->demotion.state;
- goto end;
- }
- }
-
-#ifdef CONFIG_HOTPLUG_CPU
- /*
- * Check for P_LVL2_UP flag before entering C2 and above on
- * an SMP system. We do it here instead of doing it at _CST/P_LVL
- * detection phase, to work cleanly with logical CPU hotplug.
- */
- if ((cx->type != ACPI_STATE_C1) && (num_online_cpus() > 1) &&
- !pr->flags.has_cst && !(acpi_gbl_FADT.flags & ACPI_FADT_C2_MP_SUPPORTED))
- cx = &pr->power.states[ACPI_STATE_C1];
-#endif
-
- /*
- * Sleep:
- * ------
- * Invoke the current Cx state to put the processor to sleep.
- */
- if (cx->type == ACPI_STATE_C2 || cx->type == ACPI_STATE_C3) {
- current_thread_info()->status &= ~TS_POLLING;
- /*
- * TS_POLLING-cleared state must be visible before we
- * test NEED_RESCHED:
- */
- smp_mb();
- if (need_resched()) {
- current_thread_info()->status |= TS_POLLING;
- local_irq_enable();
- return;
- }
- }
-
- switch (cx->type) {
-
- case ACPI_STATE_C1:
- /*
- * Invoke C1.
- * Use the appropriate idle routine, the one that would
- * be used without acpi C-states.
- */
- if (pm_idle_save) {
- pm_idle_save(); /* enables IRQs */
- } else {
- acpi_safe_halt();
- local_irq_enable();
- }
-
- /*
- * TBD: Can't get time duration while in C1, as resumes
- * go to an ISR rather than here. Need to instrument
- * base interrupt handler.
- *
- * Note: the TSC better not stop in C1, sched_clock() will
- * skew otherwise.
- */
- sleep_ticks = 0xFFFFFFFF;
-
- break;
-
- case ACPI_STATE_C2:
- /* Get start time (ticks) */
- t1 = inl(acpi_gbl_FADT.xpm_timer_block.address);
- /* Tell the scheduler that we are going deep-idle: */
- sched_clock_idle_sleep_event();
- /* Invoke C2 */
- acpi_state_timer_broadcast(pr, cx, 1);
- acpi_cstate_enter(cx);
- /* Get end time (ticks) */
- t2 = inl(acpi_gbl_FADT.xpm_timer_block.address);
-
-#if defined (CONFIG_GENERIC_TIME) && defined (CONFIG_X86)
- /* TSC halts in C2, so notify users */
- if (tsc_halts_in_c(ACPI_STATE_C2))
- mark_tsc_unstable("possible TSC halt in C2");
-#endif
- /* Compute time (ticks) that we were actually asleep */
- sleep_ticks = ticks_elapsed(t1, t2);
-
- /* Tell the scheduler how much we idled: */
- sched_clock_idle_wakeup_event(sleep_ticks*PM_TIMER_TICK_NS);
-
- /* Re-enable interrupts */
- local_irq_enable();
- /* Do not account our idle-switching overhead: */
- sleep_ticks -= cx->latency_ticks + C2_OVERHEAD;
-
- current_thread_info()->status |= TS_POLLING;
- acpi_state_timer_broadcast(pr, cx, 0);
- break;
-
- case ACPI_STATE_C3:
- acpi_unlazy_tlb(smp_processor_id());
- /*
- * Must be done before busmaster disable as we might
- * need to access HPET !
- */
- acpi_state_timer_broadcast(pr, cx, 1);
- /*
- * disable bus master
- * bm_check implies we need ARB_DIS
- * !bm_check implies we need cache flush
- * bm_control implies whether we can do ARB_DIS
- *
- * That leaves a case where bm_check is set and bm_control is
- * not set. In that case we cannot do much, we enter C3
- * without doing anything.
- */
- if (pr->flags.bm_check && pr->flags.bm_control) {
- if (atomic_inc_return(&c3_cpu_count) ==
- num_online_cpus()) {
- /*
- * All CPUs are trying to go to C3
- * Disable bus master arbitration
- */
- acpi_set_register(ACPI_BITREG_ARB_DISABLE, 1);
- }
- } else if (!pr->flags.bm_check) {
- /* SMP with no shared cache... Invalidate cache */
- ACPI_FLUSH_CPU_CACHE();
- }
-
- /* Get start time (ticks) */
- t1 = inl(acpi_gbl_FADT.xpm_timer_block.address);
- /* Invoke C3 */
- /* Tell the scheduler that we are going deep-idle: */
- sched_clock_idle_sleep_event();
- acpi_cstate_enter(cx);
- /* Get end time (ticks) */
- t2 = inl(acpi_gbl_FADT.xpm_timer_block.address);
- if (pr->flags.bm_check && pr->flags.bm_control) {
- /* Enable bus master arbitration */
- atomic_dec(&c3_cpu_count);
- acpi_set_register(ACPI_BITREG_ARB_DISABLE, 0);
- }
-
-#if defined (CONFIG_GENERIC_TIME) && defined (CONFIG_X86)
- /* TSC halts in C3, so notify users */
- if (tsc_halts_in_c(ACPI_STATE_C3))
- mark_tsc_unstable("TSC halts in C3");
-#endif
- /* Compute time (ticks) that we were actually asleep */
- sleep_ticks = ticks_elapsed(t1, t2);
- /* Tell the scheduler how much we idled: */
- sched_clock_idle_wakeup_event(sleep_ticks*PM_TIMER_TICK_NS);
-
- /* Re-enable interrupts */
- local_irq_enable();
- /* Do not account our idle-switching overhead: */
- sleep_ticks -= cx->latency_ticks + C3_OVERHEAD;
-
- current_thread_info()->status |= TS_POLLING;
- acpi_state_timer_broadcast(pr, cx, 0);
- break;
-
- default:
- local_irq_enable();
- return;
- }
- cx->usage++;
- if ((cx->type != ACPI_STATE_C1) && (sleep_ticks > 0))
- cx->time += sleep_ticks;
-
- next_state = pr->power.state;
-
-#ifdef CONFIG_HOTPLUG_CPU
- /* Don't do promotion/demotion */
- if ((cx->type == ACPI_STATE_C1) && (num_online_cpus() > 1) &&
- !pr->flags.has_cst && !(acpi_gbl_FADT.flags & ACPI_FADT_C2_MP_SUPPORTED)) {
- next_state = cx;
- goto end;
- }
-#endif
-
- /*
- * Promotion?
- * ----------
- * Track the number of longs (time asleep is greater than threshold)
- * and promote when the count threshold is reached. Note that bus
- * mastering activity may prevent promotions.
- * Do not promote above max_cstate.
- */
- if (cx->promotion.state &&
- ((cx->promotion.state - pr->power.states) <= max_cstate)) {
- if (sleep_ticks > cx->promotion.threshold.ticks &&
- cx->promotion.state->latency <=
- pm_qos_requirement(PM_QOS_CPU_DMA_LATENCY)) {
- cx->promotion.count++;
- cx->demotion.count = 0;
- if (cx->promotion.count >=
- cx->promotion.threshold.count) {
- if (pr->flags.bm_check) {
- if (!
- (pr->power.bm_activity & cx->
- promotion.threshold.bm)) {
- next_state =
- cx->promotion.state;
- goto end;
- }
- } else {
- next_state = cx->promotion.state;
- goto end;
- }
- }
- }
- }
-
- /*
- * Demotion?
- * ---------
- * Track the number of shorts (time asleep is less than time threshold)
- * and demote when the usage threshold is reached.
- */
- if (cx->demotion.state) {
- if (sleep_ticks < cx->demotion.threshold.ticks) {
- cx->demotion.count++;
- cx->promotion.count = 0;
- if (cx->demotion.count >= cx->demotion.threshold.count) {
- next_state = cx->demotion.state;
- goto end;
- }
- }
- }
-
- end:
- /*
- * Demote if current state exceeds max_cstate
- * or if the latency of the current state is unacceptable
- */
- if ((pr->power.state - pr->power.states) > max_cstate ||
- pr->power.state->latency >
- pm_qos_requirement(PM_QOS_CPU_DMA_LATENCY)) {
- if (cx->demotion.state)
- next_state = cx->demotion.state;
- }
-
- /*
- * New Cx State?
- * -------------
- * If we're going to start using a new Cx state we must clean up
- * from the previous and prepare to use the new.
- */
- if (next_state != pr->power.state)
- acpi_processor_power_activate(pr, next_state);
-}
-
-static int acpi_processor_set_power_policy(struct acpi_processor *pr)
-{
- unsigned int i;
- unsigned int state_is_set = 0;
- struct acpi_processor_cx *lower = NULL;
- struct acpi_processor_cx *higher = NULL;
- struct acpi_processor_cx *cx;
-
-
- if (!pr)
- return -EINVAL;
-
- /*
- * This function sets the default Cx state policy (OS idle handler).
- * Our scheme is to promote quickly to C2 but more conservatively
- * to C3. We're favoring C2 for its characteristics of low latency
- * (quick response), good power savings, and ability to allow bus
- * mastering activity. Note that the Cx state policy is completely
- * customizable and can be altered dynamically.
- */
-
- /* startup state */
- for (i = 1; i < ACPI_PROCESSOR_MAX_POWER; i++) {
- cx = &pr->power.states[i];
- if (!cx->valid)
- continue;
-
- if (!state_is_set)
- pr->power.state = cx;
- state_is_set++;
- break;
- }
-
- if (!state_is_set)
- return -ENODEV;
-
- /* demotion */
- for (i = 1; i < ACPI_PROCESSOR_MAX_POWER; i++) {
- cx = &pr->power.states[i];
- if (!cx->valid)
- continue;
-
- if (lower) {
- cx->demotion.state = lower;
- cx->demotion.threshold.ticks = cx->latency_ticks;
- cx->demotion.threshold.count = 1;
- if (cx->type == ACPI_STATE_C3)
- cx->demotion.threshold.bm = bm_history;
- }
-
- lower = cx;
- }
-
- /* promotion */
- for (i = (ACPI_PROCESSOR_MAX_POWER - 1); i > 0; i--) {
- cx = &pr->power.states[i];
- if (!cx->valid)
- continue;
-
- if (higher) {
- cx->promotion.state = higher;
- cx->promotion.threshold.ticks = cx->latency_ticks;
- if (cx->type >= ACPI_STATE_C2)
- cx->promotion.threshold.count = 4;
- else
- cx->promotion.threshold.count = 10;
- if (higher->type == ACPI_STATE_C3)
- cx->promotion.threshold.bm = bm_history;
- }
-
- higher = cx;
- }
-
- return 0;
-}
-#endif /* !CONFIG_CPU_IDLE */
-
static int acpi_processor_get_power_info_fadt(struct acpi_processor *pr)
{
@@ -1047,11 +541,7 @@
*/
cx->valid = 1;
-#ifndef CONFIG_CPU_IDLE
- cx->latency_ticks = US_TO_PM_TIMER_TICKS(cx->latency);
-#else
cx->latency_ticks = cx->latency;
-#endif
return;
}
@@ -1121,7 +611,6 @@
" for C3 to be enabled on SMP systems\n"));
return;
}
- acpi_set_register(ACPI_BITREG_BUS_MASTER_RLD, 0);
}
/*
@@ -1132,11 +621,16 @@
*/
cx->valid = 1;
-#ifndef CONFIG_CPU_IDLE
- cx->latency_ticks = US_TO_PM_TIMER_TICKS(cx->latency);
-#else
cx->latency_ticks = cx->latency;
-#endif
+ /*
+ * On older chipsets, BM_RLD needs to be set
+ * in order for Bus Master activity to wake the
+ * system from C3. Newer chipsets handle DMA
+ * during C3 automatically and BM_RLD is a NOP.
+ * In either case, the proper way to
+ * handle BM_RLD is to set it and leave it set.
+ */
+ acpi_set_register(ACPI_BITREG_BUS_MASTER_RLD, 1);
return;
}
@@ -1201,20 +695,6 @@
pr->power.count = acpi_processor_power_verify(pr);
-#ifndef CONFIG_CPU_IDLE
- /*
- * Set Default Policy
- * ------------------
- * Now that we know which states are supported, set the default
- * policy. Note that this policy can be changed dynamically
- * (e.g. encourage deeper sleeps to conserve battery life when
- * not on AC).
- */
- result = acpi_processor_set_power_policy(pr);
- if (result)
- return result;
-#endif
-
/*
* if one state of type C2 or C3 is available, mark this
* CPU as being "idle manageable"
@@ -1312,69 +792,6 @@
.release = single_release,
};
-#ifndef CONFIG_CPU_IDLE
-
-int acpi_processor_cst_has_changed(struct acpi_processor *pr)
-{
- int result = 0;
-
- if (boot_option_idle_override)
- return 0;
-
- if (!pr)
- return -EINVAL;
-
- if (nocst) {
- return -ENODEV;
- }
-
- if (!pr->flags.power_setup_done)
- return -ENODEV;
-
- /*
- * Fall back to the default idle loop, when pm_idle_save had
- * been initialized.
- */
- if (pm_idle_save) {
- pm_idle = pm_idle_save;
- /* Relies on interrupts forcing exit from idle. */
- synchronize_sched();
- }
-
- pr->flags.power = 0;
- result = acpi_processor_get_power_info(pr);
- if ((pr->flags.power == 1) && (pr->flags.power_setup_done))
- pm_idle = acpi_processor_idle;
-
- return result;
-}
-
-#ifdef CONFIG_SMP
-static void smp_callback(void *v)
-{
- /* we already woke the CPU up, nothing more to do */
-}
-
-/*
- * This function gets called when a part of the kernel has a new latency
- * requirement. This means we need to get all processors out of their C-state,
- * and then recalculate a new suitable C-state. Just do a cross-cpu IPI; that
- * wakes them all right up.
- */
-static int acpi_processor_latency_notify(struct notifier_block *b,
- unsigned long l, void *v)
-{
- smp_call_function(smp_callback, NULL, 1);
- return NOTIFY_OK;
-}
-
-static struct notifier_block acpi_processor_latency_notifier = {
- .notifier_call = acpi_processor_latency_notify,
-};
-
-#endif
-
-#else /* CONFIG_CPU_IDLE */
/**
* acpi_idle_bm_check - checks if bus master activity was detected
@@ -1383,7 +800,7 @@
{
u32 bm_status = 0;
- acpi_get_register(ACPI_BITREG_BUS_MASTER_STATUS, &bm_status);
+ acpi_get_register_unlocked(ACPI_BITREG_BUS_MASTER_STATUS, &bm_status);
if (bm_status)
acpi_set_register(ACPI_BITREG_BUS_MASTER_STATUS, 1);
/*
@@ -1400,25 +817,6 @@
}
/**
- * acpi_idle_update_bm_rld - updates the BM_RLD bit depending on target state
- * @pr: the processor
- * @target: the new target state
- */
-static inline void acpi_idle_update_bm_rld(struct acpi_processor *pr,
- struct acpi_processor_cx *target)
-{
- if (pr->flags.bm_rld_set && target->type != ACPI_STATE_C3) {
- acpi_set_register(ACPI_BITREG_BUS_MASTER_RLD, 0);
- pr->flags.bm_rld_set = 0;
- }
-
- if (!pr->flags.bm_rld_set && target->type == ACPI_STATE_C3) {
- acpi_set_register(ACPI_BITREG_BUS_MASTER_RLD, 1);
- pr->flags.bm_rld_set = 1;
- }
-}
-
-/**
* acpi_idle_do_entry - a helper function that does C2 and C3 type entry
* @cx: cstate data
*
@@ -1473,9 +871,6 @@
return 0;
}
- if (pr->flags.bm_check)
- acpi_idle_update_bm_rld(pr, cx);
-
t1 = inl(acpi_gbl_FADT.xpm_timer_block.address);
acpi_idle_do_entry(cx);
t2 = inl(acpi_gbl_FADT.xpm_timer_block.address);
@@ -1527,9 +922,6 @@
*/
acpi_state_timer_broadcast(pr, cx, 1);
- if (pr->flags.bm_check)
- acpi_idle_update_bm_rld(pr, cx);
-
if (cx->type == ACPI_STATE_C3)
ACPI_FLUSH_CPU_CACHE();
@@ -1621,8 +1013,6 @@
*/
acpi_state_timer_broadcast(pr, cx, 1);
- acpi_idle_update_bm_rld(pr, cx);
-
/*
* disable bus master
* bm_check implies we need ARB_DIS
@@ -1795,8 +1185,6 @@
return ret;
}
-#endif /* CONFIG_CPU_IDLE */
-
int __cpuinit acpi_processor_power_init(struct acpi_processor *pr,
struct acpi_device *device)
{
@@ -1825,10 +1213,6 @@
"ACPI: processor limited to max C-state %d\n",
max_cstate);
first_run++;
-#if !defined(CONFIG_CPU_IDLE) && defined(CONFIG_SMP)
- pm_qos_add_notifier(PM_QOS_CPU_DMA_LATENCY,
- &acpi_processor_latency_notifier);
-#endif
}
if (!pr)
@@ -1852,11 +1236,9 @@
* platforms that only support C1.
*/
if (pr->flags.power) {
-#ifdef CONFIG_CPU_IDLE
acpi_processor_setup_cpuidle(pr);
if (cpuidle_register_device(&pr->power.dev))
return -EIO;
-#endif
printk(KERN_INFO PREFIX "CPU%d (power states:", pr->id);
for (i = 1; i <= pr->power.count; i++)
@@ -1864,13 +1246,6 @@
printk(" C%d[C%d]", i,
pr->power.states[i].type);
printk(")\n");
-
-#ifndef CONFIG_CPU_IDLE
- if (pr->id == 0) {
- pm_idle_save = pm_idle;
- pm_idle = acpi_processor_idle;
- }
-#endif
}
/* 'power' [R] */
@@ -1889,34 +1264,12 @@
if (boot_option_idle_override)
return 0;
-#ifdef CONFIG_CPU_IDLE
cpuidle_unregister_device(&pr->power.dev);
-#endif
pr->flags.power_setup_done = 0;
if (acpi_device_dir(device))
remove_proc_entry(ACPI_PROCESSOR_FILE_POWER,
acpi_device_dir(device));
-#ifndef CONFIG_CPU_IDLE
-
- /* Unregister the idle handler when processor #0 is removed. */
- if (pr->id == 0) {
- if (pm_idle_save)
- pm_idle = pm_idle_save;
-
- /*
- * We are about to unload the current idle thread pm callback
- * (pm_idle), Wait for all processors to update cached/local
- * copies of pm_idle before proceeding.
- */
- cpu_idle_wait();
-#ifdef CONFIG_SMP
- pm_qos_remove_notifier(PM_QOS_CPU_DMA_LATENCY,
- &acpi_processor_latency_notifier);
-#endif
- }
-#endif
-
return 0;
}
diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c
index 846e227..9cc769b 100644
--- a/drivers/acpi/processor_perflib.c
+++ b/drivers/acpi/processor_perflib.c
@@ -31,14 +31,6 @@
#include <linux/init.h>
#include <linux/cpufreq.h>
-#ifdef CONFIG_X86_ACPI_CPUFREQ_PROC_INTF
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-#include <linux/mutex.h>
-
-#include <asm/uaccess.h>
-#endif
-
#ifdef CONFIG_X86
#include <asm/cpufeature.h>
#endif
@@ -434,96 +426,6 @@
EXPORT_SYMBOL(acpi_processor_notify_smm);
-#ifdef CONFIG_X86_ACPI_CPUFREQ_PROC_INTF
-/* /proc/acpi/processor/../performance interface (DEPRECATED) */
-
-static int acpi_processor_perf_open_fs(struct inode *inode, struct file *file);
-static struct file_operations acpi_processor_perf_fops = {
- .owner = THIS_MODULE,
- .open = acpi_processor_perf_open_fs,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
-static int acpi_processor_perf_seq_show(struct seq_file *seq, void *offset)
-{
- struct acpi_processor *pr = seq->private;
- int i;
-
-
- if (!pr)
- goto end;
-
- if (!pr->performance) {
- seq_puts(seq, "<not supported>\n");
- goto end;
- }
-
- seq_printf(seq, "state count: %d\n"
- "active state: P%d\n",
- pr->performance->state_count, pr->performance->state);
-
- seq_puts(seq, "states:\n");
- for (i = 0; i < pr->performance->state_count; i++)
- seq_printf(seq,
- " %cP%d: %d MHz, %d mW, %d uS\n",
- (i == pr->performance->state ? '*' : ' '), i,
- (u32) pr->performance->states[i].core_frequency,
- (u32) pr->performance->states[i].power,
- (u32) pr->performance->states[i].transition_latency);
-
- end:
- return 0;
-}
-
-static int acpi_processor_perf_open_fs(struct inode *inode, struct file *file)
-{
- return single_open(file, acpi_processor_perf_seq_show,
- PDE(inode)->data);
-}
-
-static void acpi_cpufreq_add_file(struct acpi_processor *pr)
-{
- struct acpi_device *device = NULL;
-
-
- if (acpi_bus_get_device(pr->handle, &device))
- return;
-
- /* add file 'performance' [R/W] */
- proc_create_data(ACPI_PROCESSOR_FILE_PERFORMANCE, S_IFREG | S_IRUGO,
- acpi_device_dir(device),
- &acpi_processor_perf_fops, acpi_driver_data(device));
- return;
-}
-
-static void acpi_cpufreq_remove_file(struct acpi_processor *pr)
-{
- struct acpi_device *device = NULL;
-
-
- if (acpi_bus_get_device(pr->handle, &device))
- return;
-
- /* remove file 'performance' */
- remove_proc_entry(ACPI_PROCESSOR_FILE_PERFORMANCE,
- acpi_device_dir(device));
-
- return;
-}
-
-#else
-static void acpi_cpufreq_add_file(struct acpi_processor *pr)
-{
- return;
-}
-static void acpi_cpufreq_remove_file(struct acpi_processor *pr)
-{
- return;
-}
-#endif /* CONFIG_X86_ACPI_CPUFREQ_PROC_INTF */
-
static int acpi_processor_get_psd(struct acpi_processor *pr)
{
int result = 0;
@@ -747,14 +649,12 @@
}
EXPORT_SYMBOL(acpi_processor_preregister_performance);
-
int
acpi_processor_register_performance(struct acpi_processor_performance
*performance, unsigned int cpu)
{
struct acpi_processor *pr;
-
if (!(acpi_processor_ppc_status & PPC_REGISTERED))
return -EINVAL;
@@ -781,8 +681,6 @@
return -EIO;
}
- acpi_cpufreq_add_file(pr);
-
mutex_unlock(&performance_mutex);
return 0;
}
@@ -795,7 +693,6 @@
{
struct acpi_processor *pr;
-
mutex_lock(&performance_mutex);
pr = per_cpu(processors, cpu);
@@ -808,8 +705,6 @@
kfree(pr->performance->states);
pr->performance = NULL;
- acpi_cpufreq_remove_file(pr);
-
mutex_unlock(&performance_mutex);
return;
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 7e3c609..5192666 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -90,31 +90,6 @@
old_suspend_ordering = true;
}
-/*
- * According to the ACPI specification the BIOS should make sure that ACPI is
- * enabled and SCI_EN bit is set on wake-up from S1 - S3 sleep states. Still,
- * some BIOSes don't do that and therefore we use acpi_enable() to enable ACPI
- * on such systems during resume. Unfortunately that doesn't help in
- * particularly pathological cases in which SCI_EN has to be set directly on
- * resume, although the specification states very clearly that this flag is
- * owned by the hardware. The set_sci_en_on_resume variable will be set in such
- * cases.
- */
-static bool set_sci_en_on_resume;
-/*
- * The ACPI specification wants us to save NVS memory regions during hibernation
- * and to restore them during the subsequent resume. However, it is not certain
- * if this mechanism is going to work on all machines, so we allow the user to
- * disable this mechanism using the 'acpi_sleep=s4_nonvs' kernel command line
- * option.
- */
-static bool s4_no_nvs;
-
-void __init acpi_s4_no_nvs(void)
-{
- s4_no_nvs = true;
-}
-
/**
* acpi_pm_disable_gpes - Disable the GPEs.
*/
@@ -193,6 +168,18 @@
#endif /* CONFIG_ACPI_SLEEP */
#ifdef CONFIG_SUSPEND
+/*
+ * According to the ACPI specification the BIOS should make sure that ACPI is
+ * enabled and SCI_EN bit is set on wake-up from S1 - S3 sleep states. Still,
+ * some BIOSes don't do that and therefore we use acpi_enable() to enable ACPI
+ * on such systems during resume. Unfortunately that doesn't help in
+ * particularly pathological cases in which SCI_EN has to be set directly on
+ * resume, although the specification states very clearly that this flag is
+ * owned by the hardware. The set_sci_en_on_resume variable will be set in such
+ * cases.
+ */
+static bool set_sci_en_on_resume;
+
extern void do_suspend_lowlevel(void);
static u32 acpi_suspend_states[] = {
@@ -396,6 +383,20 @@
#endif /* CONFIG_SUSPEND */
#ifdef CONFIG_HIBERNATION
+/*
+ * The ACPI specification wants us to save NVS memory regions during hibernation
+ * and to restore them during the subsequent resume. However, it is not certain
+ * if this mechanism is going to work on all machines, so we allow the user to
+ * disable this mechanism using the 'acpi_sleep=s4_nonvs' kernel command line
+ * option.
+ */
+static bool s4_no_nvs;
+
+void __init acpi_s4_no_nvs(void)
+{
+ s4_no_nvs = true;
+}
+
static unsigned long s4_hardware_signature;
static struct acpi_table_facs *facs;
static bool nosigcheck;
@@ -679,7 +680,7 @@
static void acpi_power_off(void)
{
/* acpi_sleep_prepare(ACPI_STATE_S5) should have already been called */
- printk("%s called\n", __func__);
+ printk(KERN_DEBUG "%s called\n", __func__);
local_irq_disable();
acpi_enable_wakeup_device(ACPI_STATE_S5);
acpi_enter_sleep_state(ACPI_STATE_S5);
diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c
index 775c97a..a885295 100644
--- a/drivers/acpi/tables.c
+++ b/drivers/acpi/tables.c
@@ -293,7 +293,12 @@
int __init acpi_table_init(void)
{
- acpi_initialize_tables(initial_tables, ACPI_MAX_TABLES, 0);
+ acpi_status status;
+
+ status = acpi_initialize_tables(initial_tables, ACPI_MAX_TABLES, 0);
+ if (ACPI_FAILURE(status))
+ return 1;
+
check_multiple_madt();
return 0;
}
diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c
index f261737..bb5ed05 100644
--- a/drivers/acpi/video.c
+++ b/drivers/acpi/video.c
@@ -1020,7 +1020,7 @@
}
seq_printf(seq, "levels: ");
- for (i = 0; i < dev->brightness->count; i++)
+ for (i = 2; i < dev->brightness->count; i++)
seq_printf(seq, " %d", dev->brightness->levels[i]);
seq_printf(seq, "\ncurrent: %d\n", dev->brightness->curr);
@@ -1059,7 +1059,7 @@
return -EFAULT;
/* validate through the list of available levels */
- for (i = 0; i < dev->brightness->count; i++)
+ for (i = 2; i < dev->brightness->count; i++)
if (level == dev->brightness->levels[i]) {
if (ACPI_SUCCESS
(acpi_video_device_lcd_set_level(dev, level)))
@@ -1260,7 +1260,7 @@
printk(KERN_WARNING PREFIX
"This indicates a BIOS bug. Please contact the manufacturer.\n");
}
- printk("%llx\n", options);
+ printk(KERN_WARNING "%llx\n", options);
seq_printf(seq, "can POST: <integrated video>");
if (options & 2)
seq_printf(seq, " <PCI video>");
@@ -1712,7 +1712,7 @@
max = max_below = 0;
min = min_above = 255;
/* Find closest level to level_current */
- for (i = 0; i < device->brightness->count; i++) {
+ for (i = 2; i < device->brightness->count; i++) {
l = device->brightness->levels[i];
if (abs(l - level_current) < abs(delta)) {
delta = l - level_current;
@@ -1722,7 +1722,7 @@
}
/* Ajust level_current to closest available level */
level_current += delta;
- for (i = 0; i < device->brightness->count; i++) {
+ for (i = 2; i < device->brightness->count; i++) {
l = device->brightness->levels[i];
if (l < min)
min = l;
@@ -2006,6 +2006,12 @@
device->pnp.bus_id[3] = '0' + instance;
instance ++;
}
+ /* a hack to fix the duplicate name "VGA" problem on Pa 3553 */
+ if (!strcmp(device->pnp.bus_id, "VGA")) {
+ if (instance)
+ device->pnp.bus_id[3] = '0' + instance;
+ instance++;
+ }
video->device = device;
strcpy(acpi_device_name(device), ACPI_VIDEO_BUS_NAME);
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 77bba4c..a603bbf 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -61,9 +61,14 @@
#define EM_MSG_LED_VALUE_ON 0x00010000
static int ahci_skip_host_reset;
+static int ahci_ignore_sss;
+
module_param_named(skip_host_reset, ahci_skip_host_reset, int, 0444);
MODULE_PARM_DESC(skip_host_reset, "skip global host reset (0=don't skip, 1=skip)");
+module_param_named(ignore_sss, ahci_ignore_sss, int, 0444);
+MODULE_PARM_DESC(ignore_sss, "Ignore staggered spinup flag (0=don't ignore, 1=ignore)");
+
static int ahci_enable_alpm(struct ata_port *ap,
enum link_pm policy);
static void ahci_disable_alpm(struct ata_port *ap);
@@ -2692,8 +2697,10 @@
host->iomap = pcim_iomap_table(pdev);
host->private_data = hpriv;
- if (!(hpriv->cap & HOST_CAP_SSS))
+ if (!(hpriv->cap & HOST_CAP_SSS) || ahci_ignore_sss)
host->flags |= ATA_HOST_PARALLEL_SCAN;
+ else
+ printk(KERN_INFO "ahci: SSS flag set, parallel bus scan disabled\n");
if (pi.flags & ATA_FLAG_EM)
ahci_reset_em(host);
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 88c2428..9fbf059 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -164,6 +164,11 @@
MODULE_VERSION(DRV_VERSION);
+static bool ata_sstatus_online(u32 sstatus)
+{
+ return (sstatus & 0xf) == 0x3;
+}
+
/**
* ata_link_next - link iteration helper
* @link: the previous link, NULL to start
@@ -1015,18 +1020,6 @@
return spd_str[spd - 1];
}
-void ata_dev_disable(struct ata_device *dev)
-{
- if (ata_dev_enabled(dev)) {
- if (ata_msg_drv(dev->link->ap))
- ata_dev_printk(dev, KERN_WARNING, "disabled\n");
- ata_acpi_on_disable(dev);
- ata_down_xfermask_limit(dev, ATA_DNXFER_FORCE_PIO0 |
- ATA_DNXFER_QUIET);
- dev->class++;
- }
-}
-
static int ata_dev_set_dipm(struct ata_device *dev, enum link_pm policy)
{
struct ata_link *link = dev->link;
@@ -2239,6 +2232,40 @@
return rc;
}
+static int ata_do_link_spd_horkage(struct ata_device *dev)
+{
+ struct ata_link *plink = ata_dev_phys_link(dev);
+ u32 target, target_limit;
+
+ if (!sata_scr_valid(plink))
+ return 0;
+
+ if (dev->horkage & ATA_HORKAGE_1_5_GBPS)
+ target = 1;
+ else
+ return 0;
+
+ target_limit = (1 << target) - 1;
+
+ /* if already on stricter limit, no need to push further */
+ if (plink->sata_spd_limit <= target_limit)
+ return 0;
+
+ plink->sata_spd_limit = target_limit;
+
+ /* Request another EH round by returning -EAGAIN if link is
+ * going faster than the target speed. Forward progress is
+ * guaranteed by setting sata_spd_limit to target_limit above.
+ */
+ if (plink->sata_spd > target) {
+ ata_dev_printk(dev, KERN_INFO,
+ "applying link speed limit horkage to %s\n",
+ sata_spd_string(target));
+ return -EAGAIN;
+ }
+ return 0;
+}
+
static inline u8 ata_dev_knobble(struct ata_device *dev)
{
struct ata_port *ap = dev->link->ap;
@@ -2329,6 +2356,10 @@
return 0;
}
+ rc = ata_do_link_spd_horkage(dev);
+ if (rc)
+ return rc;
+
/* let ACPI work its magic */
rc = ata_acpi_on_devcfg(dev);
if (rc)
@@ -2784,7 +2815,7 @@
/* This is the last chance, better to slow
* down than lose it.
*/
- sata_down_spd_limit(&ap->link);
+ sata_down_spd_limit(&ap->link, 0);
ata_down_xfermask_limit(dev, ATA_DNXFER_PIO);
}
}
@@ -2880,21 +2911,27 @@
/**
* sata_down_spd_limit - adjust SATA spd limit downward
* @link: Link to adjust SATA spd limit for
+ * @spd_limit: Additional limit
*
* Adjust SATA spd limit of @link downward. Note that this
* function only adjusts the limit. The change must be applied
* using sata_set_spd().
*
+ * If @spd_limit is non-zero, the speed is limited to equal to or
+ * lower than @spd_limit if such speed is supported. If
+ * @spd_limit is slower than any supported speed, only the lowest
+ * supported speed is allowed.
+ *
* LOCKING:
* Inherited from caller.
*
* RETURNS:
* 0 on success, negative errno on failure
*/
-int sata_down_spd_limit(struct ata_link *link)
+int sata_down_spd_limit(struct ata_link *link, u32 spd_limit)
{
u32 sstatus, spd, mask;
- int rc, highbit;
+ int rc, bit;
if (!sata_scr_valid(link))
return -EOPNOTSUPP;
@@ -2903,7 +2940,7 @@
* If not, use cached value in link->sata_spd.
*/
rc = sata_scr_read(link, SCR_STATUS, &sstatus);
- if (rc == 0)
+ if (rc == 0 && ata_sstatus_online(sstatus))
spd = (sstatus >> 4) & 0xf;
else
spd = link->sata_spd;
@@ -2913,8 +2950,8 @@
return -EINVAL;
/* unconditionally mask off the highest bit */
- highbit = fls(mask) - 1;
- mask &= ~(1 << highbit);
+ bit = fls(mask) - 1;
+ mask &= ~(1 << bit);
/* Mask off all speeds higher than or equal to the current
* one. Force 1.5Gbps if current SPD is not available.
@@ -2928,6 +2965,15 @@
if (!mask)
return -EINVAL;
+ if (spd_limit) {
+ if (mask & ((1 << spd_limit) - 1))
+ mask &= (1 << spd_limit) - 1;
+ else {
+ bit = ffs(mask) - 1;
+ mask = 1 << bit;
+ }
+ }
+
link->sata_spd_limit = mask;
ata_link_printk(link, KERN_WARNING, "limiting SATA link speed to %s\n",
@@ -4215,6 +4261,9 @@
/* Devices that do not need bridging limits applied */
{ "MTRON MSP-SATA*", NULL, ATA_HORKAGE_BRIDGE_OK, },
+ /* Devices which aren't very happy with higher link speeds */
+ { "WD My Book", NULL, ATA_HORKAGE_1_5_GBPS, },
+
/* End Marker */
{ }
};
@@ -4709,8 +4758,7 @@
/**
* ata_qc_new - Request an available ATA command, for queueing
- * @ap: Port associated with device @dev
- * @dev: Device from whom we request an available command structure
+ * @ap: target port
*
* LOCKING:
* None.
@@ -5175,7 +5223,7 @@
u32 sstatus;
if (sata_scr_read(link, SCR_STATUS, &sstatus) == 0 &&
- (sstatus & 0xf) == 0x3)
+ ata_sstatus_online(sstatus))
return true;
return false;
}
@@ -5199,7 +5247,7 @@
u32 sstatus;
if (sata_scr_read(link, SCR_STATUS, &sstatus) == 0 &&
- (sstatus & 0xf) != 0x3)
+ !ata_sstatus_online(sstatus))
return true;
return false;
}
@@ -5412,8 +5460,8 @@
dev->horkage = 0;
spin_unlock_irqrestore(ap->lock, flags);
- memset((void *)dev + ATA_DEVICE_CLEAR_OFFSET, 0,
- sizeof(*dev) - ATA_DEVICE_CLEAR_OFFSET);
+ memset((void *)dev + ATA_DEVICE_CLEAR_BEGIN, 0,
+ ATA_DEVICE_CLEAR_END - ATA_DEVICE_CLEAR_BEGIN);
dev->pio_mask = UINT_MAX;
dev->mwdma_mask = UINT_MAX;
dev->udma_mask = UINT_MAX;
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 8147a83..ce2ef04 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -82,6 +82,10 @@
ATA_EH_FASTDRAIN_INTERVAL = 3000,
ATA_EH_UA_TRIES = 5,
+
+ /* probe speed down parameters, see ata_eh_schedule_probe() */
+ ATA_EH_PROBE_TRIAL_INTERVAL = 60000, /* 1 min */
+ ATA_EH_PROBE_TRIALS = 2,
};
/* The following table determines how we sequence resets. Each entry
@@ -1176,6 +1180,32 @@
}
/**
+ * ata_dev_disable - disable ATA device
+ * @dev: ATA device to disable
+ *
+ * Disable @dev.
+ *
+ * Locking:
+ * EH context.
+ */
+void ata_dev_disable(struct ata_device *dev)
+{
+ if (!ata_dev_enabled(dev))
+ return;
+
+ if (ata_msg_drv(dev->link->ap))
+ ata_dev_printk(dev, KERN_WARNING, "disabled\n");
+ ata_acpi_on_disable(dev);
+ ata_down_xfermask_limit(dev, ATA_DNXFER_FORCE_PIO0 | ATA_DNXFER_QUIET);
+ dev->class++;
+
+ /* From now till the next successful probe, ering is used to
+ * track probe failures. Clear accumulated device error info.
+ */
+ ata_ering_clear(&dev->ering);
+}
+
+/**
* ata_eh_detach_dev - detach ATA device
* @dev: ATA device to detach
*
@@ -1849,7 +1879,7 @@
/* speed down? */
if (verdict & ATA_EH_SPDN_SPEED_DOWN) {
/* speed down SATA link speed if possible */
- if (sata_down_spd_limit(link) == 0) {
+ if (sata_down_spd_limit(link, 0) == 0) {
action |= ATA_EH_RESET;
goto done;
}
@@ -2601,11 +2631,11 @@
}
if (try == max_tries - 1) {
- sata_down_spd_limit(link);
+ sata_down_spd_limit(link, 0);
if (slave)
- sata_down_spd_limit(slave);
+ sata_down_spd_limit(slave, 0);
} else if (rc == -EPIPE)
- sata_down_spd_limit(failed_link);
+ sata_down_spd_limit(failed_link, 0);
if (hardreset)
reset = hardreset;
@@ -2744,6 +2774,8 @@
readid_flags, dev->id);
switch (rc) {
case 0:
+ /* clear error info accumulated during probe */
+ ata_ering_clear(&dev->ering);
new_mask |= 1 << dev->devno;
break;
case -ENOENT:
@@ -2947,9 +2979,24 @@
return 1;
}
+static int ata_count_probe_trials_cb(struct ata_ering_entry *ent, void *void_arg)
+{
+ u64 interval = msecs_to_jiffies(ATA_EH_PROBE_TRIAL_INTERVAL);
+ u64 now = get_jiffies_64();
+ int *trials = void_arg;
+
+ if (ent->timestamp < now - min(now, interval))
+ return -1;
+
+ (*trials)++;
+ return 0;
+}
+
static int ata_eh_schedule_probe(struct ata_device *dev)
{
struct ata_eh_context *ehc = &dev->link->eh_context;
+ struct ata_link *link = ata_dev_phys_link(dev);
+ int trials = 0;
if (!(ehc->i.probe_mask & (1 << dev->devno)) ||
(ehc->did_probe_mask & (1 << dev->devno)))
@@ -2962,6 +3009,25 @@
ehc->saved_xfer_mode[dev->devno] = 0;
ehc->saved_ncq_enabled &= ~(1 << dev->devno);
+ /* Record and count probe trials on the ering. The specific
+ * error mask used is irrelevant. Because a successful device
+ * detection clears the ering, this count accumulates only if
+ * there are consecutive failed probes.
+ *
+ * If the count is equal to or higher than ATA_EH_PROBE_TRIALS
+ * in the last ATA_EH_PROBE_TRIAL_INTERVAL, link speed is
+ * forced to 1.5Gbps.
+ *
+ * This is to work around cases where failed link speed
+ * negotiation results in device misdetection leading to
+ * infinite DEVXCHG or PHRDY CHG events.
+ */
+ ata_ering_record(&dev->ering, 0, AC_ERR_OTHER);
+ ata_ering_map(&dev->ering, ata_count_probe_trials_cb, &trials);
+
+ if (trials > ATA_EH_PROBE_TRIALS)
+ sata_down_spd_limit(link, 1);
+
return 1;
}
@@ -2969,7 +3035,11 @@
{
struct ata_eh_context *ehc = &dev->link->eh_context;
- ehc->tries[dev->devno]--;
+ /* -EAGAIN from EH routine indicates retry without prejudice.
+ * The requester is responsible for ensuring forward progress.
+ */
+ if (err != -EAGAIN)
+ ehc->tries[dev->devno]--;
switch (err) {
case -ENODEV:
@@ -2979,12 +3049,13 @@
/* give it just one more chance */
ehc->tries[dev->devno] = min(ehc->tries[dev->devno], 1);
case -EIO:
- if (ehc->tries[dev->devno] == 1 && dev->pio_mode > XFER_PIO_0) {
+ if (ehc->tries[dev->devno] == 1) {
/* This is the last chance, better to slow
* down than lose it.
*/
- sata_down_spd_limit(ata_dev_phys_link(dev));
- ata_down_xfermask_limit(dev, ATA_DNXFER_PIO);
+ sata_down_spd_limit(ata_dev_phys_link(dev), 0);
+ if (dev->pio_mode > XFER_PIO_0)
+ ata_down_xfermask_limit(dev, ATA_DNXFER_PIO);
}
}
diff --git a/drivers/ata/libata-pmp.c b/drivers/ata/libata-pmp.c
index 98ca07a..619f2c3 100644
--- a/drivers/ata/libata-pmp.c
+++ b/drivers/ata/libata-pmp.c
@@ -729,7 +729,7 @@
if (tries) {
/* consecutive revalidation failures? speed down */
if (reval_failed)
- sata_down_spd_limit(link);
+ sata_down_spd_limit(link, 0);
else
reval_failed = 1;
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 3c4c5ae..b9747fa 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -415,6 +415,7 @@
/**
* ata_get_identity - Handler for HDIO_GET_IDENTITY ioctl
+ * @ap: target port
* @sdev: SCSI device to get identify data for
* @arg: User buffer area for identify data
*
diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h
index fe2839e..cea8014 100644
--- a/drivers/ata/libata.h
+++ b/drivers/ata/libata.h
@@ -79,7 +79,6 @@
u64 block, u32 n_block, unsigned int tf_flags,
unsigned int tag);
extern u64 ata_tf_read_block(struct ata_taskfile *tf, struct ata_device *dev);
-extern void ata_dev_disable(struct ata_device *dev);
extern void ata_pio_queue_task(struct ata_port *ap, void *data,
unsigned long delay);
extern void ata_port_flush_task(struct ata_port *ap);
@@ -100,7 +99,7 @@
extern int ata_dev_revalidate(struct ata_device *dev, unsigned int new_class,
unsigned int readid_flags);
extern int ata_dev_configure(struct ata_device *dev);
-extern int sata_down_spd_limit(struct ata_link *link);
+extern int sata_down_spd_limit(struct ata_link *link, u32 spd_limit);
extern int ata_down_xfermask_limit(struct ata_device *dev, unsigned int sel);
extern void ata_sg_clean(struct ata_queued_cmd *qc);
extern void ata_qc_free(struct ata_queued_cmd *qc);
@@ -160,6 +159,7 @@
extern void ata_port_wait_eh(struct ata_port *ap);
extern void ata_eh_fastdrain_timerfn(unsigned long arg);
extern void ata_qc_schedule_eh(struct ata_queued_cmd *qc);
+extern void ata_dev_disable(struct ata_device *dev);
extern void ata_eh_detach_dev(struct ata_device *dev);
extern void ata_eh_about_to_do(struct ata_link *link, struct ata_device *dev,
unsigned int action);
diff --git a/drivers/ata/pata_qdi.c b/drivers/ata/pata_qdi.c
index 3080f37..f1b26f7 100644
--- a/drivers/ata/pata_qdi.c
+++ b/drivers/ata/pata_qdi.c
@@ -12,7 +12,7 @@
*
* Probe code based on drivers/ide/legacy/qd65xx.c
* Rewritten from the work of Colten Edwards <pje120@cs.usask.ca> by
- * Samuel Thibault <samuel.thibault@fnac.net>
+ * Samuel Thibault <samuel.thibault@ens-lyon.org>
*/
#include <linux/kernel.h>
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index f2d8a020..4ae1a41 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -663,8 +663,8 @@
{ PCI_VDEVICE(MARVELL, 0x5081), chip_508x },
/* RocketRAID 1720/174x have different identifiers */
{ PCI_VDEVICE(TTI, 0x1720), chip_6042 },
- { PCI_VDEVICE(TTI, 0x1740), chip_508x },
- { PCI_VDEVICE(TTI, 0x1742), chip_508x },
+ { PCI_VDEVICE(TTI, 0x1740), chip_6042 },
+ { PCI_VDEVICE(TTI, 0x1742), chip_6042 },
{ PCI_VDEVICE(MARVELL, 0x6040), chip_604x },
{ PCI_VDEVICE(MARVELL, 0x6041), chip_604x },
diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c
index c49ad0e..444af04 100644
--- a/drivers/ata/sata_nv.c
+++ b/drivers/ata/sata_nv.c
@@ -436,11 +436,16 @@
.hardreset = nv_noclassify_hardreset,
};
-/* CK804 finally gets hardreset right */
+/* For initial probing after boot and hot plugging, hardreset mostly
+ * works fine on CK804 but curiously, reprobing on the initial port by
+ * rescanning or rmmod/insmod fails to acquire the initial D2H Reg FIS
+ * in somewhat undeterministic way. Use noclassify hardreset.
+ */
static struct ata_port_operations nv_ck804_ops = {
.inherits = &nv_common_ops,
.freeze = nv_ck804_freeze,
.thaw = nv_ck804_thaw,
+ .hardreset = nv_noclassify_hardreset,
.host_stop = nv_ck804_host_stop,
};
diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c
index 9f02959..d009160 100644
--- a/drivers/ata/sata_sil.c
+++ b/drivers/ata/sata_sil.c
@@ -324,7 +324,7 @@
prd->addr = cpu_to_le32(addr);
prd->flags_len = cpu_to_le32(sg_len);
- VPRINTK("PRD[%u] = (0x%X, 0x%X)\n", pi, addr, sg_len);
+ VPRINTK("PRD[%u] = (0x%X, 0x%X)\n", si, addr, sg_len);
last_prd = prd;
prd++;
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 719ee5c..5b257a5 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -107,7 +107,7 @@
/*
* Print cpu online, possible, present, and system maps
*/
-static ssize_t print_cpus_map(char *buf, cpumask_t *map)
+static ssize_t print_cpus_map(char *buf, const struct cpumask *map)
{
int n = cpulist_scnprintf(buf, PAGE_SIZE-2, map);
diff --git a/drivers/base/topology.c b/drivers/base/topology.c
index a778fb5..bf6b132 100644
--- a/drivers/base/topology.c
+++ b/drivers/base/topology.c
@@ -31,7 +31,10 @@
#include <linux/hardirq.h>
#include <linux/topology.h>
-#define define_one_ro(_name) \
+#define define_one_ro_named(_name, _func) \
+static SYSDEV_ATTR(_name, 0444, _func, NULL)
+
+#define define_one_ro(_name) \
static SYSDEV_ATTR(_name, 0444, show_##_name, NULL)
#define define_id_show_func(name) \
@@ -42,8 +45,8 @@
return sprintf(buf, "%d\n", topology_##name(cpu)); \
}
-#if defined(topology_thread_siblings) || defined(topology_core_siblings)
-static ssize_t show_cpumap(int type, cpumask_t *mask, char *buf)
+#if defined(topology_thread_cpumask) || defined(topology_core_cpumask)
+static ssize_t show_cpumap(int type, const struct cpumask *mask, char *buf)
{
ptrdiff_t len = PTR_ALIGN(buf + PAGE_SIZE - 1, PAGE_SIZE) - buf;
int n = 0;
@@ -65,7 +68,7 @@
struct sysdev_attribute *attr, char *buf) \
{ \
unsigned int cpu = dev->id; \
- return show_cpumap(0, &(topology_##name(cpu)), buf); \
+ return show_cpumap(0, topology_##name(cpu), buf); \
}
#define define_siblings_show_list(name) \
@@ -74,7 +77,7 @@
char *buf) \
{ \
unsigned int cpu = dev->id; \
- return show_cpumap(1, &(topology_##name(cpu)), buf); \
+ return show_cpumap(1, topology_##name(cpu), buf); \
}
#else
@@ -82,9 +85,7 @@
static ssize_t show_##name(struct sys_device *dev, \
struct sysdev_attribute *attr, char *buf) \
{ \
- unsigned int cpu = dev->id; \
- cpumask_t mask = topology_##name(cpu); \
- return show_cpumap(0, &mask, buf); \
+ return show_cpumap(0, topology_##name(dev->id), buf); \
}
#define define_siblings_show_list(name) \
@@ -92,9 +93,7 @@
struct sysdev_attribute *attr, \
char *buf) \
{ \
- unsigned int cpu = dev->id; \
- cpumask_t mask = topology_##name(cpu); \
- return show_cpumap(1, &mask, buf); \
+ return show_cpumap(1, topology_##name(dev->id), buf); \
}
#endif
@@ -107,13 +106,13 @@
define_id_show_func(core_id);
define_one_ro(core_id);
-define_siblings_show_func(thread_siblings);
-define_one_ro(thread_siblings);
-define_one_ro(thread_siblings_list);
+define_siblings_show_func(thread_cpumask);
+define_one_ro_named(thread_siblings, show_thread_cpumask);
+define_one_ro_named(thread_siblings_list, show_thread_cpumask_list);
-define_siblings_show_func(core_siblings);
-define_one_ro(core_siblings);
-define_one_ro(core_siblings_list);
+define_siblings_show_func(core_cpumask);
+define_one_ro_named(core_siblings, show_core_cpumask);
+define_one_ro_named(core_siblings_list, show_core_cpumask_list);
static struct attribute *default_attrs[] = {
&attr_physical_package_id.attr,
diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig
index f5be808..735bbe2 100644
--- a/drivers/char/Kconfig
+++ b/drivers/char/Kconfig
@@ -761,7 +761,7 @@
config NVRAM
tristate "/dev/nvram support"
- depends on ATARI || X86 || ARM || GENERIC_NVRAM
+ depends on ATARI || X86 || (ARM && RTC_DRV_CMOS) || GENERIC_NVRAM
---help---
If you say Y here and create a character special file /dev/nvram
with major number 10 and minor number 144 using mknod ("man mknod"),
diff --git a/drivers/char/sx.c b/drivers/char/sx.c
index b60be7b..f146e90 100644
--- a/drivers/char/sx.c
+++ b/drivers/char/sx.c
@@ -1713,8 +1713,8 @@
for (i = 0; i < SX_NBOARDS; i++)
sx_dprintk(SX_DEBUG_FIRMWARE, "<%x> ", boards[i].flags);
sx_dprintk(SX_DEBUG_FIRMWARE, "\n");
- unlock_kernel();
- return -EIO;
+ rc = -EIO;
+ goto out;
}
switch (cmd) {
@@ -1747,7 +1747,8 @@
break;
case SXIO_DO_RAMTEST:
if (sx_initialized) /* Already initialized: better not ramtest the board. */
- return -EPERM;
+ rc = -EPERM;
+ break;
if (IS_SX_BOARD(board)) {
rc = do_memtest(board, 0, 0x7000);
if (!rc)
@@ -1844,6 +1845,7 @@
rc = -ENOTTY;
break;
}
+out:
unlock_kernel();
func_exit();
return rc;
diff --git a/drivers/dca/dca-core.c b/drivers/dca/dca-core.c
index 5543384..33bd753 100644
--- a/drivers/dca/dca-core.c
+++ b/drivers/dca/dca-core.c
@@ -28,7 +28,7 @@
#include <linux/device.h>
#include <linux/dca.h>
-#define DCA_VERSION "1.4"
+#define DCA_VERSION "1.8"
MODULE_VERSION(DCA_VERSION);
MODULE_LICENSE("GPL");
@@ -60,16 +60,17 @@
{
struct dca_provider *dca;
int err, slot = -ENODEV;
+ unsigned long flags;
if (!dev)
return -EFAULT;
- spin_lock(&dca_lock);
+ spin_lock_irqsave(&dca_lock, flags);
/* check if the requester has not been added already */
dca = dca_find_provider_by_dev(dev);
if (dca) {
- spin_unlock(&dca_lock);
+ spin_unlock_irqrestore(&dca_lock, flags);
return -EEXIST;
}
@@ -78,19 +79,21 @@
if (slot >= 0)
break;
}
- if (slot < 0) {
- spin_unlock(&dca_lock);
+
+ spin_unlock_irqrestore(&dca_lock, flags);
+
+ if (slot < 0)
return slot;
- }
err = dca_sysfs_add_req(dca, dev, slot);
if (err) {
- dca->ops->remove_requester(dca, dev);
- spin_unlock(&dca_lock);
+ spin_lock_irqsave(&dca_lock, flags);
+ if (dca == dca_find_provider_by_dev(dev))
+ dca->ops->remove_requester(dca, dev);
+ spin_unlock_irqrestore(&dca_lock, flags);
return err;
}
- spin_unlock(&dca_lock);
return 0;
}
EXPORT_SYMBOL_GPL(dca_add_requester);
@@ -103,25 +106,25 @@
{
struct dca_provider *dca;
int slot;
+ unsigned long flags;
if (!dev)
return -EFAULT;
- spin_lock(&dca_lock);
+ spin_lock_irqsave(&dca_lock, flags);
dca = dca_find_provider_by_dev(dev);
if (!dca) {
- spin_unlock(&dca_lock);
+ spin_unlock_irqrestore(&dca_lock, flags);
return -ENODEV;
}
slot = dca->ops->remove_requester(dca, dev);
- if (slot < 0) {
- spin_unlock(&dca_lock);
+ spin_unlock_irqrestore(&dca_lock, flags);
+
+ if (slot < 0)
return slot;
- }
dca_sysfs_remove_req(dca, slot);
- spin_unlock(&dca_lock);
return 0;
}
EXPORT_SYMBOL_GPL(dca_remove_requester);
@@ -135,17 +138,18 @@
{
struct dca_provider *dca;
u8 tag;
+ unsigned long flags;
- spin_lock(&dca_lock);
+ spin_lock_irqsave(&dca_lock, flags);
dca = dca_find_provider_by_dev(dev);
if (!dca) {
- spin_unlock(&dca_lock);
+ spin_unlock_irqrestore(&dca_lock, flags);
return -ENODEV;
}
tag = dca->ops->get_tag(dca, dev, cpu);
- spin_unlock(&dca_lock);
+ spin_unlock_irqrestore(&dca_lock, flags);
return tag;
}
@@ -217,11 +221,16 @@
int register_dca_provider(struct dca_provider *dca, struct device *dev)
{
int err;
+ unsigned long flags;
err = dca_sysfs_add_provider(dca, dev);
if (err)
return err;
+
+ spin_lock_irqsave(&dca_lock, flags);
list_add(&dca->node, &dca_providers);
+ spin_unlock_irqrestore(&dca_lock, flags);
+
blocking_notifier_call_chain(&dca_provider_chain,
DCA_PROVIDER_ADD, NULL);
return 0;
@@ -234,9 +243,15 @@
*/
void unregister_dca_provider(struct dca_provider *dca)
{
+ unsigned long flags;
+
blocking_notifier_call_chain(&dca_provider_chain,
DCA_PROVIDER_REMOVE, NULL);
+
+ spin_lock_irqsave(&dca_lock, flags);
list_del(&dca->node);
+ spin_unlock_irqrestore(&dca_lock, flags);
+
dca_sysfs_remove_provider(dca);
}
EXPORT_SYMBOL_GPL(unregister_dca_provider);
diff --git a/drivers/firewire/fw-card.c b/drivers/firewire/fw-card.c
index 7be2cf3..a5dd7a6 100644
--- a/drivers/firewire/fw-card.c
+++ b/drivers/firewire/fw-card.c
@@ -412,6 +412,7 @@
{
u32 *config_rom;
size_t length;
+ int err;
card->max_receive = max_receive;
card->link_speed = link_speed;
@@ -422,7 +423,13 @@
list_add_tail(&card->link, &card_list);
mutex_unlock(&card_mutex);
- return card->driver->enable(card, config_rom, length);
+ err = card->driver->enable(card, config_rom, length);
+ if (err < 0) {
+ mutex_lock(&card_mutex);
+ list_del(&card->link);
+ mutex_unlock(&card_mutex);
+ }
+ return err;
}
EXPORT_SYMBOL(fw_card_add);
diff --git a/drivers/firmware/dcdbas.c b/drivers/firmware/dcdbas.c
index 777fba4..3009e01 100644
--- a/drivers/firmware/dcdbas.c
+++ b/drivers/firmware/dcdbas.c
@@ -244,7 +244,7 @@
*/
int dcdbas_smi_request(struct smi_cmd *smi_cmd)
{
- cpumask_t old_mask;
+ cpumask_var_t old_mask;
int ret = 0;
if (smi_cmd->magic != SMI_CMD_MAGIC) {
@@ -254,8 +254,11 @@
}
/* SMI requires CPU 0 */
- old_mask = current->cpus_allowed;
- set_cpus_allowed_ptr(current, &cpumask_of_cpu(0));
+ if (!alloc_cpumask_var(&old_mask, GFP_KERNEL))
+ return -ENOMEM;
+
+ cpumask_copy(old_mask, ¤t->cpus_allowed);
+ set_cpus_allowed_ptr(current, cpumask_of(0));
if (smp_processor_id() != 0) {
dev_dbg(&dcdbas_pdev->dev, "%s: failed to get CPU 0\n",
__func__);
@@ -275,7 +278,8 @@
);
out:
- set_cpus_allowed_ptr(current, &old_mask);
+ set_cpus_allowed_ptr(current, old_mask);
+ free_cpumask_var(old_mask);
return ret;
}
diff --git a/drivers/hwmon/hp_accel.c b/drivers/hwmon/hp_accel.c
index 0370524..abf4dfc 100644
--- a/drivers/hwmon/hp_accel.c
+++ b/drivers/hwmon/hp_accel.c
@@ -153,7 +153,10 @@
static struct axis_conversion lis3lv02d_axis_x_inverted = {-1, 2, 3};
static struct axis_conversion lis3lv02d_axis_z_inverted = {1, 2, -3};
static struct axis_conversion lis3lv02d_axis_xy_rotated_left = {-2, 1, 3};
+static struct axis_conversion lis3lv02d_axis_xy_rotated_left_usd = {-2, 1, -3};
static struct axis_conversion lis3lv02d_axis_xy_swap_inverted = {-2, -1, 3};
+static struct axis_conversion lis3lv02d_axis_xy_rotated_right = {2, -1, 3};
+static struct axis_conversion lis3lv02d_axis_xy_swap_yz_inverted = {2, -1, -3};
#define AXIS_DMI_MATCH(_ident, _name, _axis) { \
.ident = _ident, \
@@ -172,10 +175,12 @@
AXIS_DMI_MATCH("NC2510", "HP Compaq 2510", y_inverted),
AXIS_DMI_MATCH("NC8510", "HP Compaq 8510", xy_swap_inverted),
AXIS_DMI_MATCH("HP2133", "HP 2133", xy_rotated_left),
+ AXIS_DMI_MATCH("NC653x", "HP Compaq 653", xy_rotated_left_usd),
+ AXIS_DMI_MATCH("NC673x", "HP Compaq 673", xy_rotated_left_usd),
+ AXIS_DMI_MATCH("NC651xx", "HP Compaq 651", xy_rotated_right),
+ AXIS_DMI_MATCH("NC671xx", "HP Compaq 671", xy_swap_yz_inverted),
{ NULL, }
/* Laptop models without axis info (yet):
- * "NC651xx" "HP Compaq 651"
- * "NC671xx" "HP Compaq 671"
* "NC6910" "HP Compaq 6910"
* HP Compaq 8710x Notebook PC / Mobile Workstation
* "NC2400" "HP Compaq nc2400"
diff --git a/drivers/ide/qd65xx.c b/drivers/ide/qd65xx.c
index 5b2e3af4..08c4fa3 100644
--- a/drivers/ide/qd65xx.c
+++ b/drivers/ide/qd65xx.c
@@ -16,7 +16,7 @@
/*
* Rewritten from the work of Colten Edwards <pje120@cs.usask.ca> by
- * Samuel Thibault <samuel.thibault@fnac.net>
+ * Samuel Thibault <samuel.thibault@ens-lyon.org>
*/
#include <linux/module.h>
diff --git a/drivers/ide/qd65xx.h b/drivers/ide/qd65xx.h
index 6636f96..d7e67a1 100644
--- a/drivers/ide/qd65xx.h
+++ b/drivers/ide/qd65xx.h
@@ -4,7 +4,7 @@
/*
* Authors: Petr Soucek <petr@ryston.cz>
- * Samuel Thibault <samuel.thibault@fnac.net>
+ * Samuel Thibault <samuel.thibault@ens-lyon.org>
*/
/* truncates a in [b,c] */
diff --git a/drivers/ieee1394/dv1394.c b/drivers/ieee1394/dv1394.c
index a329e6b..3838bc4 100644
--- a/drivers/ieee1394/dv1394.c
+++ b/drivers/ieee1394/dv1394.c
@@ -1823,6 +1823,10 @@
#endif
+ printk(KERN_INFO "%s: NOTE, the dv1394 interface is unsupported "
+ "and will not be available in the new firewire driver stack. "
+ "Try libraw1394 based programs instead.\n", current->comm);
+
return 0;
}
@@ -2567,10 +2571,6 @@
{
int ret;
- printk(KERN_WARNING
- "NOTE: The dv1394 driver is unsupported and may be removed in a "
- "future Linux release. Use raw1394 instead.\n");
-
cdev_init(&dv1394_cdev, &dv1394_fops);
dv1394_cdev.owner = THIS_MODULE;
ret = cdev_add(&dv1394_cdev, IEEE1394_DV1394_DEV, 16);
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 1e3aea9..09658b2 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -25,13 +25,13 @@
{
dev_info_t *hash;
linear_conf_t *conf = mddev_to_conf(mddev);
+ sector_t idx = sector >> conf->sector_shift;
/*
* sector_div(a,b) returns the remainer and sets a to a/b
*/
- sector >>= conf->sector_shift;
- (void)sector_div(sector, conf->spacing);
- hash = conf->hash_table[sector];
+ (void)sector_div(idx, conf->spacing);
+ hash = conf->hash_table[idx];
while (sector >= hash->num_sectors + hash->start_sector)
hash++;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 41e2509..4495104 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1481,6 +1481,11 @@
if (find_rdev_nr(mddev, rdev->desc_nr))
return -EBUSY;
}
+ if (mddev->max_disks && rdev->desc_nr >= mddev->max_disks) {
+ printk(KERN_WARNING "md: %s: array is limited to %d devices\n",
+ mdname(mddev), mddev->max_disks);
+ return -EBUSY;
+ }
bdevname(rdev->bdev,b);
while ( (s=strchr(b, '/')) != NULL)
*s = '!';
@@ -2441,6 +2446,15 @@
i = 0;
rdev_for_each(rdev, tmp, mddev) {
+ if (rdev->desc_nr >= mddev->max_disks ||
+ i > mddev->max_disks) {
+ printk(KERN_WARNING
+ "md: %s: %s: only %d devices permitted\n",
+ mdname(mddev), bdevname(rdev->bdev, b),
+ mddev->max_disks);
+ kick_rdev_from_array(rdev);
+ continue;
+ }
if (rdev != freshest)
if (super_types[mddev->major_version].
validate_super(mddev, rdev)) {
@@ -4614,13 +4628,6 @@
* noticed in interrupt contexts ...
*/
- if (rdev->desc_nr == mddev->max_disks) {
- printk(KERN_WARNING "%s: can not hot-add to full array!\n",
- mdname(mddev));
- err = -EBUSY;
- goto abort_unbind_export;
- }
-
rdev->raid_disk = -1;
md_update_sb(mddev, 1);
@@ -4634,9 +4641,6 @@
md_new_event(mddev);
return 0;
-abort_unbind_export:
- unbind_rdev_from_array(rdev);
-
abort_export:
export_rdev(rdev);
return err;
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 7b4f5f7..01e3cff 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1640,7 +1640,8 @@
}
bio = r1_bio->bios[r1_bio->read_disk];
- if ((disk=read_balance(conf, r1_bio)) == -1) {
+ if ((disk=read_balance(conf, r1_bio)) == -1 ||
+ disk == r1_bio->read_disk) {
printk(KERN_ALERT "raid1: %s: unrecoverable I/O"
" read error for block %llu\n",
bdevname(bio->bi_bdev,b),
diff --git a/drivers/mfd/pcf50633-core.c b/drivers/mfd/pcf50633-core.c
index 24508e2..ea9488e 100644
--- a/drivers/mfd/pcf50633-core.c
+++ b/drivers/mfd/pcf50633-core.c
@@ -626,7 +626,6 @@
}
if (client->irq) {
- set_irq_handler(client->irq, handle_level_irq);
ret = request_irq(client->irq, pcf50633_irq,
IRQF_TRIGGER_LOW, "pcf50633", pcf);
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index 5607319..1c48408 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -162,7 +162,7 @@
config SGI_XP
tristate "Support communication between SGI SSIs"
depends on NET
- depends on (IA64_GENERIC || IA64_SGI_SN2 || IA64_SGI_UV || X86_64) && SMP
+ depends on (IA64_GENERIC || IA64_SGI_SN2 || IA64_SGI_UV || X86_UV) && SMP
select IA64_UNCACHED_ALLOCATOR if IA64_GENERIC || IA64_SGI_SN2
select GENERIC_ALLOCATOR if IA64_GENERIC || IA64_SGI_SN2
select SGI_GRU if (IA64_GENERIC || IA64_SGI_UV || X86_64) && SMP
@@ -189,7 +189,7 @@
config SGI_GRU
tristate "SGI GRU driver"
- depends on (X86_64 || IA64_SGI_UV || IA64_GENERIC) && SMP
+ depends on (X86_UV || IA64_SGI_UV || IA64_GENERIC) && SMP
default n
select MMU_NOTIFIER
---help---
@@ -217,6 +217,7 @@
depends on EXPERIMENTAL
depends on BACKLIGHT_CLASS_DEVICE
depends on RFKILL
+ depends on POWER_SUPPLY
default n
---help---
This driver adds support for rfkill and backlight control to Dell
diff --git a/drivers/misc/atmel-ssc.c b/drivers/misc/atmel-ssc.c
index bf5e4d0..558bf3f 100644
--- a/drivers/misc/atmel-ssc.c
+++ b/drivers/misc/atmel-ssc.c
@@ -35,7 +35,7 @@
if (!ssc_valid) {
spin_unlock(&user_lock);
- dev_dbg(&ssc->pdev->dev, "could not find requested device\n");
+ pr_err("ssc: ssc%d platform device is missing\n", ssc_num);
return ERR_PTR(-ENODEV);
}
diff --git a/drivers/misc/hpilo.c b/drivers/misc/hpilo.c
index 10c421b..f26667a 100644
--- a/drivers/misc/hpilo.c
+++ b/drivers/misc/hpilo.c
@@ -207,7 +207,7 @@
&device_ccb->recv_ctrl);
/* give iLO some time to process stop request */
- for (retries = 1000; retries > 0; retries--) {
+ for (retries = MAX_WAIT; retries > 0; retries--) {
doorbell_set(driver_ccb);
udelay(1);
if (!(ioread32(&device_ccb->send_ctrl) & (1 << CTRL_BITPOS_A))
@@ -309,7 +309,7 @@
doorbell_clr(driver_ccb);
/* make sure iLO is really handling requests */
- for (i = 1000; i > 0; i--) {
+ for (i = MAX_WAIT; i > 0; i--) {
if (ilo_pkt_dequeue(hw, driver_ccb, SENDQ, &pkt_id, NULL, NULL))
break;
udelay(1);
@@ -326,7 +326,7 @@
return 0;
free:
- pci_free_consistent(pdev, data->dma_size, data->dma_va, data->dma_pa);
+ ilo_ccb_close(pdev, data);
out:
return error;
}
diff --git a/drivers/misc/hpilo.h b/drivers/misc/hpilo.h
index a281207..b64a20e 100644
--- a/drivers/misc/hpilo.h
+++ b/drivers/misc/hpilo.h
@@ -19,6 +19,8 @@
#define MAX_ILO_DEV 1
/* max number of files */
#define MAX_OPEN (MAX_CCB * MAX_ILO_DEV)
+/* spin counter for open/close delay */
+#define MAX_WAIT 10000
/*
* Per device, used to track global memory allocations.
diff --git a/drivers/misc/sgi-gru/gru.h b/drivers/misc/sgi-gru/gru.h
index f93f03a..1b5f579 100644
--- a/drivers/misc/sgi-gru/gru.h
+++ b/drivers/misc/sgi-gru/gru.h
@@ -19,6 +19,8 @@
#ifndef __GRU_H__
#define __GRU_H__
+#include <asm/uv/uv.h>
+
/*
* GRU architectural definitions
*/
diff --git a/drivers/misc/sgi-xp/xp.h b/drivers/misc/sgi-xp/xp.h
index 7b4cbd5..069ad3a 100644
--- a/drivers/misc/sgi-xp/xp.h
+++ b/drivers/misc/sgi-xp/xp.h
@@ -15,6 +15,8 @@
#include <linux/mutex.h>
+#include <asm/uv/uv.h>
+
#ifdef CONFIG_IA64
#include <asm/system.h>
#include <asm/sn/arch.h> /* defines is_shub1() and is_shub2() */
diff --git a/drivers/misc/sgi-xp/xpc.h b/drivers/misc/sgi-xp/xpc.h
index a5bd658..275b788 100644
--- a/drivers/misc/sgi-xp/xpc.h
+++ b/drivers/misc/sgi-xp/xpc.h
@@ -3,7 +3,7 @@
* License. See the file "COPYING" in the main directory of this archive
* for more details.
*
- * Copyright (c) 2004-2008 Silicon Graphics, Inc. All Rights Reserved.
+ * Copyright (c) 2004-2009 Silicon Graphics, Inc. All Rights Reserved.
*/
/*
@@ -514,7 +514,8 @@
/* partition's notify mq */
struct xpc_send_msg_slot_uv *send_msg_slots;
- struct xpc_notify_mq_msg_uv *recv_msg_slots;
+ void *recv_msg_slots; /* each slot will hold a xpc_notify_mq_msg_uv */
+ /* structure plus the user's payload */
struct xpc_fifo_head_uv msg_slot_free_list;
struct xpc_fifo_head_uv recv_msg_list; /* deliverable payloads */
diff --git a/drivers/misc/sgi-xp/xpc_main.c b/drivers/misc/sgi-xp/xpc_main.c
index 89218f7..6576170 100644
--- a/drivers/misc/sgi-xp/xpc_main.c
+++ b/drivers/misc/sgi-xp/xpc_main.c
@@ -318,7 +318,7 @@
/* this thread was marked active by xpc_hb_init() */
- set_cpus_allowed_ptr(current, &cpumask_of_cpu(XPC_HB_CHECK_CPU));
+ set_cpus_allowed_ptr(current, cpumask_of(XPC_HB_CHECK_CPU));
/* set our heartbeating to other partitions into motion */
xpc_hb_check_timeout = jiffies + (xpc_hb_check_interval * HZ);
diff --git a/drivers/misc/sgi-xp/xpc_uv.c b/drivers/misc/sgi-xp/xpc_uv.c
index f17f7d4..29c0502 100644
--- a/drivers/misc/sgi-xp/xpc_uv.c
+++ b/drivers/misc/sgi-xp/xpc_uv.c
@@ -3,7 +3,7 @@
* License. See the file "COPYING" in the main directory of this archive
* for more details.
*
- * Copyright (c) 2008 Silicon Graphics, Inc. All Rights Reserved.
+ * Copyright (c) 2008-2009 Silicon Graphics, Inc. All Rights Reserved.
*/
/*
@@ -1010,8 +1010,8 @@
continue;
for (entry = 0; entry < nentries; entry++) {
- msg_slot = ch_uv->recv_msg_slots + entry *
- ch->entry_size;
+ msg_slot = ch_uv->recv_msg_slots +
+ entry * ch->entry_size;
msg_slot->hdr.msg_slot_number = entry;
}
@@ -1308,9 +1308,8 @@
/* we're dealing with a normal message sent via the notify_mq */
ch_uv = &ch->sn.uv;
- msg_slot = (struct xpc_notify_mq_msg_uv *)((u64)ch_uv->recv_msg_slots +
- (msg->hdr.msg_slot_number % ch->remote_nentries) *
- ch->entry_size);
+ msg_slot = ch_uv->recv_msg_slots +
+ (msg->hdr.msg_slot_number % ch->remote_nentries) * ch->entry_size;
BUG_ON(msg->hdr.msg_slot_number != msg_slot->hdr.msg_slot_number);
BUG_ON(msg_slot->hdr.size != 0);
diff --git a/drivers/misc/sgi-xp/xpnet.c b/drivers/misc/sgi-xp/xpnet.c
index 7957f52..6faefcf 100644
--- a/drivers/misc/sgi-xp/xpnet.c
+++ b/drivers/misc/sgi-xp/xpnet.c
@@ -3,7 +3,7 @@
* License. See the file "COPYING" in the main directory of this archive
* for more details.
*
- * Copyright (C) 1999-2008 Silicon Graphics, Inc. All rights reserved.
+ * Copyright (C) 1999-2009 Silicon Graphics, Inc. All rights reserved.
*/
/*
@@ -551,6 +551,7 @@
netif_carrier_off(xpnet_device);
+ xpnet_device->netdev_ops = &xpnet_netdev_ops;
xpnet_device->mtu = XPNET_DEF_MTU;
/*
diff --git a/drivers/mtd/maps/sa1100-flash.c b/drivers/mtd/maps/sa1100-flash.c
index 7df6bbf..6f6a0f6 100644
--- a/drivers/mtd/maps/sa1100-flash.c
+++ b/drivers/mtd/maps/sa1100-flash.c
@@ -453,7 +453,7 @@
.resume = sa1100_mtd_resume,
.shutdown = sa1100_mtd_shutdown,
.driver = {
- .name = "flash",
+ .name = "sa1100-mtd",
.owner = THIS_MODULE,
},
};
@@ -474,4 +474,4 @@
MODULE_AUTHOR("Nicolas Pitre");
MODULE_DESCRIPTION("SA1100 CFI map driver");
MODULE_LICENSE("GPL");
-MODULE_ALIAS("platform:flash");
+MODULE_ALIAS("platform:sa1100-mtd");
diff --git a/drivers/net/arm/etherh.c b/drivers/net/arm/etherh.c
index d15d8b7..54b52e5 100644
--- a/drivers/net/arm/etherh.c
+++ b/drivers/net/arm/etherh.c
@@ -646,7 +646,7 @@
.ndo_get_stats = ei_get_stats,
.ndo_set_multicast_list = ei_set_multicast_list,
.ndo_validate_addr = eth_validate_addr,
- .ndo_set_mac_address = eth_set_mac_addr,
+ .ndo_set_mac_address = eth_mac_addr,
.ndo_change_mtu = eth_change_mtu,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = ei_poll,
diff --git a/drivers/net/cassini.c b/drivers/net/cassini.c
index 840b3d1..bbbc3bb 100644
--- a/drivers/net/cassini.c
+++ b/drivers/net/cassini.c
@@ -806,7 +806,7 @@
cas_phy_write(cp, MII_BMCR, BMCR_RESET);
udelay(100);
- while (limit--) {
+ while (--limit) {
val = cas_phy_read(cp, MII_BMCR);
if ((val & BMCR_RESET) == 0)
break;
@@ -979,7 +979,7 @@
writel(val, cp->regs + REG_PCS_MII_CTRL);
limit = STOP_TRIES;
- while (limit-- > 0) {
+ while (--limit > 0) {
udelay(10);
if ((readl(cp->regs + REG_PCS_MII_CTRL) &
PCS_MII_RESET) == 0)
diff --git a/drivers/net/cxgb3/sge.c b/drivers/net/cxgb3/sge.c
index 379a132..d31791f 100644
--- a/drivers/net/cxgb3/sge.c
+++ b/drivers/net/cxgb3/sge.c
@@ -2276,8 +2276,7 @@
} else if ((len = ntohl(r->len_cq)) != 0) {
struct sge_fl *fl;
- if (eth)
- lro = qs->lro_enabled && is_eth_tcp(rss_hi);
+ lro &= eth && is_eth_tcp(rss_hi);
fl = (len & F_RSPD_FLQ) ? &qs->fl[1] : &qs->fl[0];
if (fl->use_pages) {
diff --git a/drivers/net/e1000/e1000_main.c b/drivers/net/e1000/e1000_main.c
index c986978..6bd63cc 100644
--- a/drivers/net/e1000/e1000_main.c
+++ b/drivers/net/e1000/e1000_main.c
@@ -940,7 +940,7 @@
err = pci_enable_device(pdev);
} else {
bars = pci_select_bars(pdev, IORESOURCE_MEM);
- err = pci_enable_device(pdev);
+ err = pci_enable_device_mem(pdev);
}
if (err)
return err;
diff --git a/drivers/net/gianfar.c b/drivers/net/gianfar.c
index 3f7eab4..acae2d8 100644
--- a/drivers/net/gianfar.c
+++ b/drivers/net/gianfar.c
@@ -351,6 +351,9 @@
/* Reset MAC layer */
gfar_write(&priv->regs->maccfg1, MACCFG1_SOFT_RESET);
+ /* We need to delay at least 3 TX clocks */
+ udelay(2);
+
tempval = (MACCFG1_TX_FLOW | MACCFG1_RX_FLOW);
gfar_write(&priv->regs->maccfg1, tempval);
diff --git a/drivers/net/gianfar.h b/drivers/net/gianfar.h
index b1a8334..eaa8689 100644
--- a/drivers/net/gianfar.h
+++ b/drivers/net/gianfar.h
@@ -312,7 +312,7 @@
#define ATTRELI_EI(x) (x)
#define BD_LFLAG(flags) ((flags) << 16)
-#define BD_LENGTH_MASK 0x00ff
+#define BD_LENGTH_MASK 0x0000ffff
/* TxBD status field bits */
#define TXBD_READY 0x8000
diff --git a/drivers/net/ibm_newemac/phy.c b/drivers/net/ibm_newemac/phy.c
index c40cd8d..ac9d964 100644
--- a/drivers/net/ibm_newemac/phy.c
+++ b/drivers/net/ibm_newemac/phy.c
@@ -60,7 +60,7 @@
udelay(300);
- while (limit--) {
+ while (--limit) {
val = phy_read(phy, MII_BMCR);
if (val >= 0 && (val & BMCR_RESET) == 0)
break;
@@ -84,7 +84,7 @@
udelay(300);
- while (limit--) {
+ while (--limit) {
val = gpcs_phy_read(phy, MII_BMCR);
if (val >= 0 && (val & BMCR_RESET) == 0)
break;
diff --git a/drivers/net/pcmcia/pcnet_cs.c b/drivers/net/pcmcia/pcnet_cs.c
index c38ed77..a699940 100644
--- a/drivers/net/pcmcia/pcnet_cs.c
+++ b/drivers/net/pcmcia/pcnet_cs.c
@@ -586,7 +586,7 @@
}
if ((link->conf.ConfigBase == 0x03c0)
- && (link->manf_id == 0x149) && (link->card_id = 0xc1ab)) {
+ && (link->manf_id == 0x149) && (link->card_id == 0xc1ab)) {
printk(KERN_INFO "pcnet_cs: this is an AX88190 card!\n");
printk(KERN_INFO "pcnet_cs: use axnet_cs instead.\n");
goto failed;
diff --git a/drivers/net/qlge/qlge.h b/drivers/net/qlge/qlge.h
index c1dadad..e6fdce9 100644
--- a/drivers/net/qlge/qlge.h
+++ b/drivers/net/qlge/qlge.h
@@ -787,12 +787,12 @@
struct flash_params {
u8 dev_id_str[4];
- u16 size;
- u16 csum;
- u16 ver;
- u16 sub_dev_id;
+ __le16 size;
+ __le16 csum;
+ __le16 ver;
+ __le16 sub_dev_id;
u8 mac_addr[6];
- u16 res;
+ __le16 res;
};
diff --git a/drivers/net/qlge/qlge_main.c b/drivers/net/qlge/qlge_main.c
index 45421c8..3d1d7b6 100644
--- a/drivers/net/qlge/qlge_main.c
+++ b/drivers/net/qlge/qlge_main.c
@@ -641,7 +641,7 @@
}
-static int ql_read_flash_word(struct ql_adapter *qdev, int offset, u32 *data)
+static int ql_read_flash_word(struct ql_adapter *qdev, int offset, __le32 *data)
{
int status = 0;
/* wait for reg to come ready */
@@ -656,8 +656,11 @@
FLASH_ADDR, FLASH_ADDR_RDY, FLASH_ADDR_ERR);
if (status)
goto exit;
- /* get the data */
- *data = ql_read32(qdev, FLASH_DATA);
+ /* This data is stored on flash as an array of
+ * __le32. Since ql_read32() returns cpu endian
+ * we need to swap it back.
+ */
+ *data = cpu_to_le32(ql_read32(qdev, FLASH_DATA));
exit:
return status;
}
@@ -666,13 +669,20 @@
{
int i;
int status;
- u32 *p = (u32 *)&qdev->flash;
+ __le32 *p = (__le32 *)&qdev->flash;
+ u32 offset = 0;
+
+ /* Second function's parameters follow the first
+ * function's.
+ */
+ if (qdev->func)
+ offset = sizeof(qdev->flash) / sizeof(u32);
if (ql_sem_spinlock(qdev, SEM_FLASH_MASK))
return -ETIMEDOUT;
for (i = 0; i < sizeof(qdev->flash) / sizeof(u32); i++, p++) {
- status = ql_read_flash_word(qdev, i, p);
+ status = ql_read_flash_word(qdev, i+offset, p);
if (status) {
QPRINTK(qdev, IFUP, ERR, "Error reading flash.\n");
goto exit;
@@ -3826,7 +3836,7 @@
{
struct net_device *ndev = pci_get_drvdata(pdev);
struct ql_adapter *qdev = netdev_priv(ndev);
- int err;
+ int err, i;
netif_device_detach(ndev);
@@ -3836,6 +3846,9 @@
return err;
}
+ for (i = qdev->rss_ring_first_cq_id; i < qdev->rx_ring_count; i++)
+ netif_napi_del(&qdev->rx_ring[i].napi);
+
err = pci_save_state(pdev);
if (err)
return err;
diff --git a/drivers/net/sfc/efx.c b/drivers/net/sfc/efx.c
index ab0e09b..847e9bb 100644
--- a/drivers/net/sfc/efx.c
+++ b/drivers/net/sfc/efx.c
@@ -854,20 +854,27 @@
* interrupts across them. */
static int efx_wanted_rx_queues(void)
{
- cpumask_t core_mask;
+ cpumask_var_t core_mask;
int count;
int cpu;
- cpus_clear(core_mask);
+ if (!alloc_cpumask_var(&core_mask, GFP_KERNEL)) {
+ printk(KERN_WARNING
+ "efx.c: allocation failure, irq balancing hobbled\n");
+ return 1;
+ }
+
+ cpumask_clear(core_mask);
count = 0;
for_each_online_cpu(cpu) {
- if (!cpu_isset(cpu, core_mask)) {
+ if (!cpumask_test_cpu(cpu, core_mask)) {
++count;
- cpus_or(core_mask, core_mask,
- topology_core_siblings(cpu));
+ cpumask_or(core_mask, core_mask,
+ topology_core_cpumask(cpu));
}
}
+ free_cpumask_var(core_mask);
return count;
}
diff --git a/drivers/net/smc911x.c b/drivers/net/smc911x.c
index bf3aa2a..223cde0 100644
--- a/drivers/net/smc911x.c
+++ b/drivers/net/smc911x.c
@@ -220,9 +220,9 @@
/* make sure EEPROM has finished loading before setting GPIO_CFG */
timeout=1000;
- while ( timeout-- && (SMC_GET_E2P_CMD(lp) & E2P_CMD_EPC_BUSY_)) {
+ while (--timeout && (SMC_GET_E2P_CMD(lp) & E2P_CMD_EPC_BUSY_))
udelay(10);
- }
+
if (timeout == 0){
PRINTK("%s: smc911x_reset timeout waiting for EEPROM busy\n", dev->name);
return;
diff --git a/drivers/net/smsc9420.c b/drivers/net/smsc9420.c
index d801900..a1e4b38 100644
--- a/drivers/net/smsc9420.c
+++ b/drivers/net/smsc9420.c
@@ -498,7 +498,7 @@
static void smsc9420_stop_tx(struct smsc9420_pdata *pd)
{
u32 dmac_control, mac_cr, dma_intr_ena;
- int timeOut = 1000;
+ int timeout = 1000;
/* disable TX DMAC */
dmac_control = smsc9420_reg_read(pd, DMAC_CONTROL);
@@ -506,13 +506,13 @@
smsc9420_reg_write(pd, DMAC_CONTROL, dmac_control);
/* Wait max 10ms for transmit process to stop */
- while (timeOut--) {
+ while (--timeout) {
if (smsc9420_reg_read(pd, DMAC_STATUS) & DMAC_STS_TS_)
break;
udelay(10);
}
- if (!timeOut)
+ if (!timeout)
smsc_warn(IFDOWN, "TX DMAC failed to stop");
/* ACK Tx DMAC stop bit */
@@ -596,7 +596,7 @@
static void smsc9420_stop_rx(struct smsc9420_pdata *pd)
{
- int timeOut = 1000;
+ int timeout = 1000;
u32 mac_cr, dmac_control, dma_intr_ena;
/* mask RX DMAC interrupts */
@@ -617,13 +617,13 @@
smsc9420_pci_flush_write(pd);
/* wait up to 10ms for receive to stop */
- while (timeOut--) {
+ while (--timeout) {
if (smsc9420_reg_read(pd, DMAC_STATUS) & DMAC_STS_RS_)
break;
udelay(10);
}
- if (!timeOut)
+ if (!timeout)
smsc_warn(IFDOWN, "RX DMAC did not stop! timeout.");
/* ACK the Rx DMAC stop bit */
diff --git a/drivers/net/sungem.c b/drivers/net/sungem.c
index 86c765d..b17efa9 100644
--- a/drivers/net/sungem.c
+++ b/drivers/net/sungem.c
@@ -148,7 +148,7 @@
cmd |= (MIF_FRAME_TAMSB);
writel(cmd, gp->regs + MIF_FRAME);
- while (limit--) {
+ while (--limit) {
cmd = readl(gp->regs + MIF_FRAME);
if (cmd & MIF_FRAME_TALSB)
break;
diff --git a/drivers/net/sungem_phy.c b/drivers/net/sungem_phy.c
index 61843fd..78f8cee 100644
--- a/drivers/net/sungem_phy.c
+++ b/drivers/net/sungem_phy.c
@@ -79,7 +79,7 @@
udelay(100);
- while (limit--) {
+ while (--limit) {
val = __phy_read(phy, phy_id, MII_BMCR);
if ((val & BMCR_RESET) == 0)
break;
diff --git a/drivers/net/sunqe.c b/drivers/net/sunqe.c
index 6e8f377..fe0c3f2 100644
--- a/drivers/net/sunqe.c
+++ b/drivers/net/sunqe.c
@@ -227,7 +227,7 @@
if (!(sbus_readb(mregs + MREGS_PHYCONFIG) & MREGS_PHYCONFIG_LTESTDIS)) {
int tries = 50;
- while (tries--) {
+ while (--tries) {
u8 tmp;
mdelay(5);
diff --git a/drivers/net/tsi108_eth.c b/drivers/net/tsi108_eth.c
index 75461db..a9fd2b2 100644
--- a/drivers/net/tsi108_eth.c
+++ b/drivers/net/tsi108_eth.c
@@ -1237,7 +1237,7 @@
spin_lock_irqsave(&phy_lock, flags);
tsi108_write_mii(data, MII_BMCR, BMCR_RESET);
- while (i--){
+ while (--i) {
if(!(tsi108_read_mii(data, MII_BMCR) & BMCR_RESET))
break;
udelay(10);
diff --git a/drivers/net/tulip/de2104x.c b/drivers/net/tulip/de2104x.c
index d5d53b6..0bf2114 100644
--- a/drivers/net/tulip/de2104x.c
+++ b/drivers/net/tulip/de2104x.c
@@ -392,7 +392,7 @@
unsigned drop = 0;
int rc;
- while (rx_work--) {
+ while (--rx_work) {
u32 status, len;
dma_addr_t mapping;
struct sk_buff *skb, *copy_skb;
diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index 0d0fa91..fe98aca 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -455,6 +455,7 @@
{icon321_port_device(0x0af0, 0xd033)}, /* Icon-322 */
{USB_DEVICE(0x0af0, 0x7301)}, /* GE40x */
{USB_DEVICE(0x0af0, 0x7361)}, /* GE40x */
+ {USB_DEVICE(0x0af0, 0x7381)}, /* GE40x */
{USB_DEVICE(0x0af0, 0x7401)}, /* GI 0401 */
{USB_DEVICE(0x0af0, 0x7501)}, /* GTM 382 */
{USB_DEVICE(0x0af0, 0x7601)}, /* GE40x */
@@ -462,7 +463,8 @@
{USB_DEVICE(0x0af0, 0x7801)},
{USB_DEVICE(0x0af0, 0x7901)},
{USB_DEVICE(0x0af0, 0x7361)},
- {icon321_port_device(0x0af0, 0xd051)},
+ {USB_DEVICE(0x0af0, 0xd057)},
+ {USB_DEVICE(0x0af0, 0xd055)},
{}
};
MODULE_DEVICE_TABLE(usb, hso_ids);
diff --git a/drivers/net/wireless/iwlwifi/iwl-agn.c b/drivers/net/wireless/iwlwifi/iwl-agn.c
index b35c881..c01ea48d 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn.c
+++ b/drivers/net/wireless/iwlwifi/iwl-agn.c
@@ -4042,6 +4042,7 @@
priv->is_open = 1;
}
+ pci_save_state(pdev);
pci_set_power_state(pdev, PCI_D3hot);
return 0;
@@ -4052,6 +4053,7 @@
struct iwl_priv *priv = pci_get_drvdata(pdev);
pci_set_power_state(pdev, PCI_D0);
+ pci_restore_state(pdev);
if (priv->is_open)
iwl_mac_start(priv->hw);
diff --git a/drivers/net/wireless/iwlwifi/iwl-sta.c b/drivers/net/wireless/iwlwifi/iwl-sta.c
index 412f66b..70a8b21 100644
--- a/drivers/net/wireless/iwlwifi/iwl-sta.c
+++ b/drivers/net/wireless/iwlwifi/iwl-sta.c
@@ -480,6 +480,9 @@
priv->num_stations = 0;
memset(priv->stations, 0, sizeof(priv->stations));
+ /* clean ucode key table bit map */
+ priv->ucode_key_table = 0;
+
spin_unlock_irqrestore(&priv->sta_lock, flags);
}
EXPORT_SYMBOL(iwl_clear_stations_table);
diff --git a/drivers/net/wireless/iwlwifi/iwl3945-base.c b/drivers/net/wireless/iwlwifi/iwl3945-base.c
index 95d0198..5b44d32 100644
--- a/drivers/net/wireless/iwlwifi/iwl3945-base.c
+++ b/drivers/net/wireless/iwlwifi/iwl3945-base.c
@@ -8143,6 +8143,7 @@
priv->is_open = 1;
}
+ pci_save_state(pdev);
pci_set_power_state(pdev, PCI_D3hot);
return 0;
@@ -8153,6 +8154,7 @@
struct iwl3945_priv *priv = pci_get_drvdata(pdev);
pci_set_power_state(pdev, PCI_D0);
+ pci_restore_state(pdev);
if (priv->is_open)
iwl3945_mac_start(priv->hw);
diff --git a/drivers/oprofile/buffer_sync.c b/drivers/oprofile/buffer_sync.c
index 9da5a4b..c3ea5fa 100644
--- a/drivers/oprofile/buffer_sync.c
+++ b/drivers/oprofile/buffer_sync.c
@@ -38,7 +38,7 @@
static LIST_HEAD(dying_tasks);
static LIST_HEAD(dead_tasks);
-static cpumask_t marked_cpus = CPU_MASK_NONE;
+static cpumask_var_t marked_cpus;
static DEFINE_SPINLOCK(task_mortuary);
static void process_task_mortuary(void);
@@ -456,10 +456,10 @@
{
int i;
- cpu_set(cpu, marked_cpus);
+ cpumask_set_cpu(cpu, marked_cpus);
for_each_online_cpu(i) {
- if (!cpu_isset(i, marked_cpus))
+ if (!cpumask_test_cpu(i, marked_cpus))
return;
}
@@ -468,7 +468,7 @@
*/
process_task_mortuary();
- cpus_clear(marked_cpus);
+ cpumask_clear(marked_cpus);
}
@@ -565,6 +565,20 @@
mutex_unlock(&buffer_mutex);
}
+int __init buffer_sync_init(void)
+{
+ if (!alloc_cpumask_var(&marked_cpus, GFP_KERNEL))
+ return -ENOMEM;
+
+ cpumask_clear(marked_cpus);
+ return 0;
+}
+
+void __exit buffer_sync_cleanup(void)
+{
+ free_cpumask_var(marked_cpus);
+}
+
/* The function can be used to add a buffer worth of data directly to
* the kernel buffer. The buffer is assumed to be a circular buffer.
* Take the entries from index start and end at index end, wrapping
diff --git a/drivers/oprofile/buffer_sync.h b/drivers/oprofile/buffer_sync.h
index 3110732..0ebf5db 100644
--- a/drivers/oprofile/buffer_sync.h
+++ b/drivers/oprofile/buffer_sync.h
@@ -19,4 +19,8 @@
/* sync the given CPU's buffer */
void sync_buffer(int cpu);
+/* initialize/destroy the buffer system. */
+int buffer_sync_init(void);
+void buffer_sync_cleanup(void);
+
#endif /* OPROFILE_BUFFER_SYNC_H */
diff --git a/drivers/oprofile/oprof.c b/drivers/oprofile/oprof.c
index 3cffce9..ced39f6 100644
--- a/drivers/oprofile/oprof.c
+++ b/drivers/oprofile/oprof.c
@@ -183,6 +183,10 @@
{
int err;
+ err = buffer_sync_init();
+ if (err)
+ return err;
+
err = oprofile_arch_init(&oprofile_ops);
if (err < 0 || timer) {
@@ -191,8 +195,10 @@
}
err = oprofilefs_register();
- if (err)
+ if (err) {
oprofile_arch_exit();
+ buffer_sync_cleanup();
+ }
return err;
}
@@ -202,6 +208,7 @@
{
oprofilefs_unregister();
oprofile_arch_exit();
+ buffer_sync_cleanup();
}
diff --git a/drivers/pci/intr_remapping.c b/drivers/pci/intr_remapping.c
index f78371b..5a57753 100644
--- a/drivers/pci/intr_remapping.c
+++ b/drivers/pci/intr_remapping.c
@@ -6,6 +6,7 @@
#include <linux/irq.h>
#include <asm/io_apic.h>
#include <asm/smp.h>
+#include <asm/cpu.h>
#include <linux/intel-iommu.h>
#include "intr_remapping.h"
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index ab1d615..93eac14 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -355,6 +355,8 @@
int i = 0;
if (drv && drv->suspend) {
+ pci_power_t prev = pci_dev->current_state;
+
pci_dev->state_saved = false;
i = drv->suspend(pci_dev, state);
@@ -365,12 +367,16 @@
if (pci_dev->state_saved)
goto Fixup;
- if (WARN_ON_ONCE(pci_dev->current_state != PCI_D0))
+ if (pci_dev->current_state != PCI_D0
+ && pci_dev->current_state != PCI_UNKNOWN) {
+ WARN_ONCE(pci_dev->current_state != prev,
+ "PCI PM: Device state not saved by %pF\n",
+ drv->suspend);
goto Fixup;
+ }
}
pci_save_state(pci_dev);
- pci_dev->state_saved = true;
/*
* This is for compatibility with existing code with legacy PM support.
*/
@@ -424,35 +430,20 @@
pci_fixup_device(pci_fixup_resume_early, pci_dev);
}
-static int pci_pm_default_resume(struct pci_dev *pci_dev)
+static void pci_pm_default_resume(struct pci_dev *pci_dev)
{
pci_fixup_device(pci_fixup_resume, pci_dev);
if (!pci_is_bridge(pci_dev))
pci_enable_wake(pci_dev, PCI_D0, false);
-
- return pci_pm_reenable_device(pci_dev);
-}
-
-static void pci_pm_default_suspend_generic(struct pci_dev *pci_dev)
-{
- /* If device is enabled at this point, disable it */
- pci_disable_enabled_device(pci_dev);
- /*
- * Save state with interrupts enabled, because in principle the bus the
- * device is on may be put into a low power state after this code runs.
- */
- pci_save_state(pci_dev);
}
static void pci_pm_default_suspend(struct pci_dev *pci_dev)
{
- pci_pm_default_suspend_generic(pci_dev);
-
+ /* Disable non-bridge devices without PM support */
if (!pci_is_bridge(pci_dev))
- pci_prepare_to_sleep(pci_dev);
-
- pci_fixup_device(pci_fixup_suspend, pci_dev);
+ pci_disable_enabled_device(pci_dev);
+ pci_save_state(pci_dev);
}
static bool pci_has_legacy_pm_support(struct pci_dev *pci_dev)
@@ -497,21 +488,49 @@
static int pci_pm_suspend(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
- struct device_driver *drv = dev->driver;
- int error = 0;
+ struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
if (pci_has_legacy_pm_support(pci_dev))
return pci_legacy_suspend(dev, PMSG_SUSPEND);
- if (drv && drv->pm && drv->pm->suspend) {
- error = drv->pm->suspend(dev);
- suspend_report_result(drv->pm->suspend, error);
+ if (!pm) {
+ pci_pm_default_suspend(pci_dev);
+ goto Fixup;
}
- if (!error)
- pci_pm_default_suspend(pci_dev);
+ pci_dev->state_saved = false;
- return error;
+ if (pm->suspend) {
+ pci_power_t prev = pci_dev->current_state;
+ int error;
+
+ error = pm->suspend(dev);
+ suspend_report_result(pm->suspend, error);
+ if (error)
+ return error;
+
+ if (pci_dev->state_saved)
+ goto Fixup;
+
+ if (pci_dev->current_state != PCI_D0
+ && pci_dev->current_state != PCI_UNKNOWN) {
+ WARN_ONCE(pci_dev->current_state != prev,
+ "PCI PM: State of device not saved by %pF\n",
+ pm->suspend);
+ goto Fixup;
+ }
+ }
+
+ if (!pci_dev->state_saved) {
+ pci_save_state(pci_dev);
+ if (!pci_is_bridge(pci_dev))
+ pci_prepare_to_sleep(pci_dev);
+ }
+
+ Fixup:
+ pci_fixup_device(pci_fixup_suspend, pci_dev);
+
+ return 0;
}
static int pci_pm_suspend_noirq(struct device *dev)
@@ -554,7 +573,7 @@
static int pci_pm_resume(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
- struct device_driver *drv = dev->driver;
+ struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
int error = 0;
/*
@@ -567,12 +586,16 @@
if (pci_has_legacy_pm_support(pci_dev))
return pci_legacy_resume(dev);
- error = pci_pm_default_resume(pci_dev);
+ pci_pm_default_resume(pci_dev);
- if (!error && drv && drv->pm && drv->pm->resume)
- error = drv->pm->resume(dev);
+ if (pm) {
+ if (pm->resume)
+ error = pm->resume(dev);
+ } else {
+ pci_pm_reenable_device(pci_dev);
+ }
- return error;
+ return 0;
}
#else /* !CONFIG_SUSPEND */
@@ -589,21 +612,31 @@
static int pci_pm_freeze(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
- struct device_driver *drv = dev->driver;
- int error = 0;
+ struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
if (pci_has_legacy_pm_support(pci_dev))
return pci_legacy_suspend(dev, PMSG_FREEZE);
- if (drv && drv->pm && drv->pm->freeze) {
- error = drv->pm->freeze(dev);
- suspend_report_result(drv->pm->freeze, error);
+ if (!pm) {
+ pci_pm_default_suspend(pci_dev);
+ return 0;
}
- if (!error)
- pci_pm_default_suspend_generic(pci_dev);
+ pci_dev->state_saved = false;
- return error;
+ if (pm->freeze) {
+ int error;
+
+ error = pm->freeze(dev);
+ suspend_report_result(pm->freeze, error);
+ if (error)
+ return error;
+ }
+
+ if (!pci_dev->state_saved)
+ pci_save_state(pci_dev);
+
+ return 0;
}
static int pci_pm_freeze_noirq(struct device *dev)
@@ -646,16 +679,18 @@
static int pci_pm_thaw(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
- struct device_driver *drv = dev->driver;
+ struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
int error = 0;
if (pci_has_legacy_pm_support(pci_dev))
return pci_legacy_resume(dev);
- pci_pm_reenable_device(pci_dev);
-
- if (drv && drv->pm && drv->pm->thaw)
- error = drv->pm->thaw(dev);
+ if (pm) {
+ if (pm->thaw)
+ error = pm->thaw(dev);
+ } else {
+ pci_pm_reenable_device(pci_dev);
+ }
return error;
}
@@ -663,22 +698,29 @@
static int pci_pm_poweroff(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
- struct device_driver *drv = dev->driver;
+ struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
int error = 0;
if (pci_has_legacy_pm_support(pci_dev))
return pci_legacy_suspend(dev, PMSG_HIBERNATE);
- if (!drv || !drv->pm)
- return 0;
-
- if (drv->pm->poweroff) {
- error = drv->pm->poweroff(dev);
- suspend_report_result(drv->pm->poweroff, error);
+ if (!pm) {
+ pci_pm_default_suspend(pci_dev);
+ goto Fixup;
}
- if (!error)
- pci_pm_default_suspend(pci_dev);
+ pci_dev->state_saved = false;
+
+ if (pm->poweroff) {
+ error = pm->poweroff(dev);
+ suspend_report_result(pm->poweroff, error);
+ }
+
+ if (!pci_dev->state_saved && !pci_is_bridge(pci_dev))
+ pci_prepare_to_sleep(pci_dev);
+
+ Fixup:
+ pci_fixup_device(pci_fixup_suspend, pci_dev);
return error;
}
@@ -719,7 +761,7 @@
static int pci_pm_restore(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
- struct device_driver *drv = dev->driver;
+ struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
int error = 0;
/*
@@ -732,10 +774,14 @@
if (pci_has_legacy_pm_support(pci_dev))
return pci_legacy_resume(dev);
- error = pci_pm_default_resume(pci_dev);
+ pci_pm_default_resume(pci_dev);
- if (!error && drv && drv->pm && drv->pm->restore)
- error = drv->pm->restore(dev);
+ if (pm) {
+ if (pm->restore)
+ error = pm->restore(dev);
+ } else {
+ pci_pm_reenable_device(pci_dev);
+ }
return error;
}
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index db7ec14..dfc4e0d 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -768,8 +768,8 @@
return -EINVAL;
rom = pci_map_rom(pdev, &size); /* size starts out as PCI window size */
- if (!rom)
- return 0;
+ if (!rom || !size)
+ return -EIO;
if (off >= size)
count = 0;
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 4880755..e3efe6b 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1418,10 +1418,10 @@
break;
}
- dev->current_state = PCI_D0;
+ pci_update_current_state(dev, PCI_D0);
Restore:
- return pci_restore_state(dev);
+ return dev->state_saved ? pci_restore_state(dev) : 0;
}
/**
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index 586b6f7..b0367f1 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -718,9 +718,9 @@
/*
* All PCIe functions are in one slot, remove one function will remove
- * the the whole slot, so just wait
+ * the whole slot, so just wait until we are the last function left.
*/
- if (!list_empty(&parent->subordinate->devices))
+ if (!list_is_last(&pdev->bus_list, &parent->subordinate->devices))
goto out;
/* All functions are removed, so just disable ASPM for the link */
diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c
index 99a914a..f9b874e 100644
--- a/drivers/pci/pcie/portdrv_pci.c
+++ b/drivers/pci/pcie/portdrv_pci.c
@@ -55,25 +55,13 @@
}
-static int pcie_portdrv_suspend_late(struct pci_dev *dev, pm_message_t state)
-{
- return pci_save_state(dev);
-}
-
-static int pcie_portdrv_resume_early(struct pci_dev *dev)
-{
- return pci_restore_state(dev);
-}
-
static int pcie_portdrv_resume(struct pci_dev *dev)
{
- pcie_portdrv_restore_config(dev);
+ pci_set_master(dev);
return pcie_port_device_resume(dev);
}
#else
#define pcie_portdrv_suspend NULL
-#define pcie_portdrv_suspend_late NULL
-#define pcie_portdrv_resume_early NULL
#define pcie_portdrv_resume NULL
#endif
@@ -292,8 +280,6 @@
.remove = pcie_portdrv_remove,
.suspend = pcie_portdrv_suspend,
- .suspend_late = pcie_portdrv_suspend_late,
- .resume_early = pcie_portdrv_resume_early,
.resume = pcie_portdrv_resume,
.err_handler = &pcie_portdrv_err_handler,
diff --git a/drivers/pci/rom.c b/drivers/pci/rom.c
index 132a781..29cbe47 100644
--- a/drivers/pci/rom.c
+++ b/drivers/pci/rom.c
@@ -63,7 +63,7 @@
* The PCI window size could be much larger than the
* actual image size.
*/
-size_t pci_get_rom_size(void __iomem *rom, size_t size)
+size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size)
{
void __iomem *image;
int last_image;
@@ -72,8 +72,10 @@
do {
void __iomem *pds;
/* Standard PCI ROMs start out with these bytes 55 AA */
- if (readb(image) != 0x55)
+ if (readb(image) != 0x55) {
+ dev_err(&pdev->dev, "Invalid ROM contents\n");
break;
+ }
if (readb(image + 1) != 0xAA)
break;
/* get the PCI data structure and check its signature */
@@ -159,7 +161,7 @@
* size is much larger than the actual size of the ROM.
* True size is important if the ROM is going to be copied.
*/
- *size = pci_get_rom_size(rom, *size);
+ *size = pci_get_rom_size(pdev, rom, *size);
return rom;
}
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index 1a266d4..9436311 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -42,6 +42,7 @@
depends on LEDS_CLASS
depends on NEW_LEDS
depends on BACKLIGHT_CLASS_DEVICE
+ depends on INPUT
---help---
This is the new Linux driver for Asus laptops. It may also support some
MEDION, JVC or VICTOR laptops. It makes all the extra buttons generate
diff --git a/drivers/platform/x86/asus-laptop.c b/drivers/platform/x86/asus-laptop.c
index 8fb8b35..56af6cf 100644
--- a/drivers/platform/x86/asus-laptop.c
+++ b/drivers/platform/x86/asus-laptop.c
@@ -46,6 +46,7 @@
#include <acpi/acpi_drivers.h>
#include <acpi/acpi_bus.h>
#include <asm/uaccess.h>
+#include <linux/input.h>
#define ASUS_LAPTOP_VERSION "0.42"
@@ -181,6 +182,8 @@
u8 light_level; //light sensor level
u8 light_switch; //light sensor switch value
u16 event_count[128]; //count for each event TODO make this better
+ struct input_dev *inputdev;
+ u16 *keycode_map;
};
/*
@@ -250,6 +253,37 @@
ASUS_LED(pled, "phone");
ASUS_LED(gled, "gaming");
+struct key_entry {
+ char type;
+ u8 code;
+ u16 keycode;
+};
+
+enum { KE_KEY, KE_END };
+
+static struct key_entry asus_keymap[] = {
+ {KE_KEY, 0x30, KEY_VOLUMEUP},
+ {KE_KEY, 0x31, KEY_VOLUMEDOWN},
+ {KE_KEY, 0x32, KEY_MUTE},
+ {KE_KEY, 0x33, KEY_SWITCHVIDEOMODE},
+ {KE_KEY, 0x34, KEY_SWITCHVIDEOMODE},
+ {KE_KEY, 0x40, KEY_PREVIOUSSONG},
+ {KE_KEY, 0x41, KEY_NEXTSONG},
+ {KE_KEY, 0x43, KEY_STOP},
+ {KE_KEY, 0x45, KEY_PLAYPAUSE},
+ {KE_KEY, 0x50, KEY_EMAIL},
+ {KE_KEY, 0x51, KEY_WWW},
+ {KE_KEY, 0x5C, BTN_EXTRA}, /* Performance */
+ {KE_KEY, 0x5D, KEY_WLAN},
+ {KE_KEY, 0x61, KEY_SWITCHVIDEOMODE},
+ {KE_KEY, 0x6B, BTN_TOUCH}, /* Lock Mouse */
+ {KE_KEY, 0x82, KEY_CAMERA},
+ {KE_KEY, 0x8A, KEY_TV},
+ {KE_KEY, 0x95, KEY_MEDIA},
+ {KE_KEY, 0x99, KEY_PHONE},
+ {KE_END, 0},
+};
+
/*
* This function evaluates an ACPI method, given an int as parameter, the
* method is searched within the scope of the handle, can be NULL. The output
@@ -720,8 +754,68 @@
return store_status(buf, count, NULL, GPS_ON);
}
+/*
+ * Hotkey functions
+ */
+static struct key_entry *asus_get_entry_by_scancode(int code)
+{
+ struct key_entry *key;
+
+ for (key = asus_keymap; key->type != KE_END; key++)
+ if (code == key->code)
+ return key;
+
+ return NULL;
+}
+
+static struct key_entry *asus_get_entry_by_keycode(int code)
+{
+ struct key_entry *key;
+
+ for (key = asus_keymap; key->type != KE_END; key++)
+ if (code == key->keycode && key->type == KE_KEY)
+ return key;
+
+ return NULL;
+}
+
+static int asus_getkeycode(struct input_dev *dev, int scancode, int *keycode)
+{
+ struct key_entry *key = asus_get_entry_by_scancode(scancode);
+
+ if (key && key->type == KE_KEY) {
+ *keycode = key->keycode;
+ return 0;
+ }
+
+ return -EINVAL;
+}
+
+static int asus_setkeycode(struct input_dev *dev, int scancode, int keycode)
+{
+ struct key_entry *key;
+ int old_keycode;
+
+ if (keycode < 0 || keycode > KEY_MAX)
+ return -EINVAL;
+
+ key = asus_get_entry_by_scancode(scancode);
+ if (key && key->type == KE_KEY) {
+ old_keycode = key->keycode;
+ key->keycode = keycode;
+ set_bit(keycode, dev->keybit);
+ if (!asus_get_entry_by_keycode(old_keycode))
+ clear_bit(old_keycode, dev->keybit);
+ return 0;
+ }
+
+ return -EINVAL;
+}
+
static void asus_hotk_notify(acpi_handle handle, u32 event, void *data)
{
+ static struct key_entry *key;
+
/* TODO Find a better way to handle events count. */
if (!hotk)
return;
@@ -738,10 +832,24 @@
lcd_blank(FB_BLANK_POWERDOWN);
}
- acpi_bus_generate_proc_event(hotk->device, event,
- hotk->event_count[event % 128]++);
+ acpi_bus_generate_netlink_event(hotk->device->pnp.device_class,
+ dev_name(&hotk->device->dev), event,
+ hotk->event_count[event % 128]++);
- return;
+ if (hotk->inputdev) {
+ key = asus_get_entry_by_scancode(event);
+ if (!key)
+ return ;
+
+ switch (key->type) {
+ case KE_KEY:
+ input_report_key(hotk->inputdev, key->keycode, 1);
+ input_sync(hotk->inputdev);
+ input_report_key(hotk->inputdev, key->keycode, 0);
+ input_sync(hotk->inputdev);
+ break;
+ }
+ }
}
#define ASUS_CREATE_DEVICE_ATTR(_name) \
@@ -959,6 +1067,38 @@
return AE_OK;
}
+static int asus_input_init(void)
+{
+ const struct key_entry *key;
+ int result;
+
+ hotk->inputdev = input_allocate_device();
+ if (!hotk->inputdev) {
+ printk(ASUS_INFO "Unable to allocate input device\n");
+ return 0;
+ }
+ hotk->inputdev->name = "Asus Laptop extra buttons";
+ hotk->inputdev->phys = ASUS_HOTK_FILE "/input0";
+ hotk->inputdev->id.bustype = BUS_HOST;
+ hotk->inputdev->getkeycode = asus_getkeycode;
+ hotk->inputdev->setkeycode = asus_setkeycode;
+
+ for (key = asus_keymap; key->type != KE_END; key++) {
+ switch (key->type) {
+ case KE_KEY:
+ set_bit(EV_KEY, hotk->inputdev->evbit);
+ set_bit(key->keycode, hotk->inputdev->keybit);
+ break;
+ }
+ }
+ result = input_register_device(hotk->inputdev);
+ if (result) {
+ printk(ASUS_INFO "Unable to register input device\n");
+ input_free_device(hotk->inputdev);
+ }
+ return result;
+}
+
static int asus_hotk_check(void)
{
int result = 0;
@@ -1044,7 +1184,7 @@
/* GPS is on by default */
write_status(NULL, 1, GPS_ON);
- end:
+end:
if (result) {
kfree(hotk->name);
kfree(hotk);
@@ -1091,10 +1231,17 @@
ASUS_LED_UNREGISTER(gled);
}
+static void asus_input_exit(void)
+{
+ if (hotk->inputdev)
+ input_unregister_device(hotk->inputdev);
+}
+
static void __exit asus_laptop_exit(void)
{
asus_backlight_exit();
asus_led_exit();
+ asus_input_exit();
acpi_bus_unregister_driver(&asus_hotk_driver);
sysfs_remove_group(&asuspf_device->dev.kobj, &asuspf_attribute_group);
@@ -1216,6 +1363,10 @@
printk(ASUS_INFO "Brightness ignored, must be controlled by "
"ACPI video driver\n");
+ result = asus_input_init();
+ if (result)
+ goto fail_input;
+
result = asus_led_init(dev);
if (result)
goto fail_led;
@@ -1242,22 +1393,25 @@
return 0;
- fail_sysfs:
+fail_sysfs:
platform_device_del(asuspf_device);
- fail_platform_device2:
+fail_platform_device2:
platform_device_put(asuspf_device);
- fail_platform_device1:
+fail_platform_device1:
platform_driver_unregister(&asuspf_driver);
- fail_platform_driver:
+fail_platform_driver:
asus_led_exit();
- fail_led:
+fail_led:
+ asus_input_exit();
+
+fail_input:
asus_backlight_exit();
- fail_backlight:
+fail_backlight:
return result;
}
diff --git a/drivers/platform/x86/asus_acpi.c b/drivers/platform/x86/asus_acpi.c
index 1e74988..d63f26e 100644
--- a/drivers/platform/x86/asus_acpi.c
+++ b/drivers/platform/x86/asus_acpi.c
@@ -143,6 +143,7 @@
S1300N, S5200N*/
A4S, /* Z81sp */
F3Sa, /* (Centrino) */
+ R1F,
END_MODEL
} model; /* Models currently supported */
u16 event_count[128]; /* Count for each event TODO make this better */
@@ -420,7 +421,18 @@
.display_get = "\\ADVG",
.display_set = "SDSP",
},
-
+ {
+ .name = "R1F",
+ .mt_bt_switch = "BLED",
+ .mt_mled = "MLED",
+ .mt_wled = "WLED",
+ .mt_lcd_switch = "\\Q10",
+ .lcd_status = "\\GP06",
+ .brightness_set = "SPLV",
+ .brightness_get = "GPLV",
+ .display_set = "SDSP",
+ .display_get = "\\INFB"
+ }
};
/* procdir we use */
@@ -1165,6 +1177,8 @@
return W3V;
else if (strncmp(model, "W5A", 3) == 0)
return W5A;
+ else if (strncmp(model, "R1F", 3) == 0)
+ return R1F;
else if (strncmp(model, "A4S", 3) == 0)
return A4S;
else if (strncmp(model, "F3Sa", 4) == 0)
diff --git a/drivers/platform/x86/eeepc-laptop.c b/drivers/platform/x86/eeepc-laptop.c
index 9d93cb9..786ed86 100644
--- a/drivers/platform/x86/eeepc-laptop.c
+++ b/drivers/platform/x86/eeepc-laptop.c
@@ -30,6 +30,7 @@
#include <linux/uaccess.h>
#include <linux/input.h>
#include <linux/rfkill.h>
+#include <linux/pci.h>
#define EEEPC_LAPTOP_VERSION "0.1"
@@ -161,6 +162,10 @@
{KE_KEY, 0x13, KEY_MUTE },
{KE_KEY, 0x14, KEY_VOLUMEDOWN },
{KE_KEY, 0x15, KEY_VOLUMEUP },
+ {KE_KEY, 0x1a, KEY_COFFEE },
+ {KE_KEY, 0x1b, KEY_ZOOM },
+ {KE_KEY, 0x1c, KEY_PROG2 },
+ {KE_KEY, 0x1d, KEY_PROG3 },
{KE_KEY, 0x30, KEY_SWITCHVIDEOMODE },
{KE_KEY, 0x31, KEY_SWITCHVIDEOMODE },
{KE_KEY, 0x32, KEY_SWITCHVIDEOMODE },
@@ -510,7 +515,43 @@
static void notify_brn(void)
{
struct backlight_device *bd = eeepc_backlight_device;
- bd->props.brightness = read_brightness(bd);
+ if (bd)
+ bd->props.brightness = read_brightness(bd);
+}
+
+static void eeepc_rfkill_notify(acpi_handle handle, u32 event, void *data)
+{
+ struct pci_dev *dev;
+ struct pci_bus *bus = pci_find_bus(0, 1);
+
+ if (event != ACPI_NOTIFY_BUS_CHECK)
+ return;
+
+ if (!bus) {
+ printk(EEEPC_WARNING "Unable to find PCI bus 1?\n");
+ return;
+ }
+
+ if (get_acpi(CM_ASL_WLAN) == 1) {
+ dev = pci_get_slot(bus, 0);
+ if (dev) {
+ /* Device already present */
+ pci_dev_put(dev);
+ return;
+ }
+ dev = pci_scan_single_device(bus, 0);
+ if (dev) {
+ pci_bus_assign_resources(bus);
+ if (pci_bus_add_device(dev))
+ printk(EEEPC_ERR "Unable to hotplug wifi\n");
+ }
+ } else {
+ dev = pci_get_slot(bus, 0);
+ if (dev) {
+ pci_remove_bus_device(dev);
+ pci_dev_put(dev);
+ }
+ }
}
static void eeepc_hotk_notify(acpi_handle handle, u32 event, void *data)
@@ -520,8 +561,9 @@
return;
if (event >= NOTIFY_BRN_MIN && event <= NOTIFY_BRN_MAX)
notify_brn();
- acpi_bus_generate_proc_event(ehotk->device, event,
- ehotk->event_count[event % 128]++);
+ acpi_bus_generate_netlink_event(ehotk->device->pnp.device_class,
+ dev_name(&ehotk->device->dev), event,
+ ehotk->event_count[event % 128]++);
if (ehotk->inputdev) {
key = eepc_get_entry_by_scancode(event);
if (key) {
@@ -539,6 +581,45 @@
}
}
+static int eeepc_register_rfkill_notifier(char *node)
+{
+ acpi_status status = AE_OK;
+ acpi_handle handle;
+
+ status = acpi_get_handle(NULL, node, &handle);
+
+ if (ACPI_SUCCESS(status)) {
+ status = acpi_install_notify_handler(handle,
+ ACPI_SYSTEM_NOTIFY,
+ eeepc_rfkill_notify,
+ NULL);
+ if (ACPI_FAILURE(status))
+ printk(EEEPC_WARNING
+ "Failed to register notify on %s\n", node);
+ } else
+ return -ENODEV;
+
+ return 0;
+}
+
+static void eeepc_unregister_rfkill_notifier(char *node)
+{
+ acpi_status status = AE_OK;
+ acpi_handle handle;
+
+ status = acpi_get_handle(NULL, node, &handle);
+
+ if (ACPI_SUCCESS(status)) {
+ status = acpi_remove_notify_handler(handle,
+ ACPI_SYSTEM_NOTIFY,
+ eeepc_rfkill_notify);
+ if (ACPI_FAILURE(status))
+ printk(EEEPC_ERR
+ "Error removing rfkill notify handler %s\n",
+ node);
+ }
+}
+
static int eeepc_hotk_add(struct acpi_device *device)
{
acpi_status status = AE_OK;
@@ -558,7 +639,7 @@
ehotk->device = device;
result = eeepc_hotk_check();
if (result)
- goto end;
+ goto ehotk_fail;
status = acpi_install_notify_handler(ehotk->handle, ACPI_SYSTEM_NOTIFY,
eeepc_hotk_notify, ehotk);
if (ACPI_FAILURE(status))
@@ -569,18 +650,25 @@
RFKILL_TYPE_WLAN);
if (!ehotk->eeepc_wlan_rfkill)
- goto end;
+ goto wlan_fail;
ehotk->eeepc_wlan_rfkill->name = "eeepc-wlan";
ehotk->eeepc_wlan_rfkill->toggle_radio = eeepc_wlan_rfkill_set;
ehotk->eeepc_wlan_rfkill->get_state = eeepc_wlan_rfkill_state;
- if (get_acpi(CM_ASL_WLAN) == 1)
+ if (get_acpi(CM_ASL_WLAN) == 1) {
ehotk->eeepc_wlan_rfkill->state =
RFKILL_STATE_UNBLOCKED;
- else
+ rfkill_set_default(RFKILL_TYPE_WLAN,
+ RFKILL_STATE_UNBLOCKED);
+ } else {
ehotk->eeepc_wlan_rfkill->state =
RFKILL_STATE_SOFT_BLOCKED;
- rfkill_register(ehotk->eeepc_wlan_rfkill);
+ rfkill_set_default(RFKILL_TYPE_WLAN,
+ RFKILL_STATE_SOFT_BLOCKED);
+ }
+ result = rfkill_register(ehotk->eeepc_wlan_rfkill);
+ if (result)
+ goto wlan_fail;
}
if (get_acpi(CM_ASL_BLUETOOTH) != -1) {
@@ -588,27 +676,47 @@
rfkill_allocate(&device->dev, RFKILL_TYPE_BLUETOOTH);
if (!ehotk->eeepc_bluetooth_rfkill)
- goto end;
+ goto bluetooth_fail;
ehotk->eeepc_bluetooth_rfkill->name = "eeepc-bluetooth";
ehotk->eeepc_bluetooth_rfkill->toggle_radio =
eeepc_bluetooth_rfkill_set;
ehotk->eeepc_bluetooth_rfkill->get_state =
eeepc_bluetooth_rfkill_state;
- if (get_acpi(CM_ASL_BLUETOOTH) == 1)
+ if (get_acpi(CM_ASL_BLUETOOTH) == 1) {
ehotk->eeepc_bluetooth_rfkill->state =
RFKILL_STATE_UNBLOCKED;
- else
+ rfkill_set_default(RFKILL_TYPE_BLUETOOTH,
+ RFKILL_STATE_UNBLOCKED);
+ } else {
ehotk->eeepc_bluetooth_rfkill->state =
RFKILL_STATE_SOFT_BLOCKED;
- rfkill_register(ehotk->eeepc_bluetooth_rfkill);
+ rfkill_set_default(RFKILL_TYPE_BLUETOOTH,
+ RFKILL_STATE_SOFT_BLOCKED);
+ }
+
+ result = rfkill_register(ehotk->eeepc_bluetooth_rfkill);
+ if (result)
+ goto bluetooth_fail;
}
- end:
- if (result) {
- kfree(ehotk);
- ehotk = NULL;
- }
+ eeepc_register_rfkill_notifier("\\_SB.PCI0.P0P6");
+ eeepc_register_rfkill_notifier("\\_SB.PCI0.P0P7");
+
+ return 0;
+
+ bluetooth_fail:
+ if (ehotk->eeepc_bluetooth_rfkill)
+ rfkill_free(ehotk->eeepc_bluetooth_rfkill);
+ rfkill_unregister(ehotk->eeepc_wlan_rfkill);
+ ehotk->eeepc_wlan_rfkill = NULL;
+ wlan_fail:
+ if (ehotk->eeepc_wlan_rfkill)
+ rfkill_free(ehotk->eeepc_wlan_rfkill);
+ ehotk_fail:
+ kfree(ehotk);
+ ehotk = NULL;
+
return result;
}
@@ -622,6 +730,10 @@
eeepc_hotk_notify);
if (ACPI_FAILURE(status))
printk(EEEPC_ERR "Error removing notify handler\n");
+
+ eeepc_unregister_rfkill_notifier("\\_SB.PCI0.P0P6");
+ eeepc_unregister_rfkill_notifier("\\_SB.PCI0.P0P7");
+
kfree(ehotk);
return 0;
}
@@ -737,13 +849,21 @@
{
if (eeepc_backlight_device)
backlight_device_unregister(eeepc_backlight_device);
- if (ehotk->inputdev)
- input_unregister_device(ehotk->inputdev);
+ eeepc_backlight_device = NULL;
+}
+
+static void eeepc_rfkill_exit(void)
+{
if (ehotk->eeepc_wlan_rfkill)
rfkill_unregister(ehotk->eeepc_wlan_rfkill);
if (ehotk->eeepc_bluetooth_rfkill)
rfkill_unregister(ehotk->eeepc_bluetooth_rfkill);
- eeepc_backlight_device = NULL;
+}
+
+static void eeepc_input_exit(void)
+{
+ if (ehotk->inputdev)
+ input_unregister_device(ehotk->inputdev);
}
static void eeepc_hwmon_exit(void)
@@ -762,6 +882,8 @@
static void __exit eeepc_laptop_exit(void)
{
eeepc_backlight_exit();
+ eeepc_rfkill_exit();
+ eeepc_input_exit();
eeepc_hwmon_exit();
acpi_bus_unregister_driver(&eeepc_hotk_driver);
sysfs_remove_group(&platform_device->dev.kobj,
@@ -865,6 +987,8 @@
fail_hwmon:
eeepc_backlight_exit();
fail_backlight:
+ eeepc_input_exit();
+ eeepc_rfkill_exit();
return result;
}
diff --git a/drivers/platform/x86/hp-wmi.c b/drivers/platform/x86/hp-wmi.c
index de91dda..f41135f 100644
--- a/drivers/platform/x86/hp-wmi.c
+++ b/drivers/platform/x86/hp-wmi.c
@@ -463,9 +463,11 @@
return 0;
register_wwan_err:
- rfkill_unregister(bluetooth_rfkill);
+ if (bluetooth_rfkill)
+ rfkill_unregister(bluetooth_rfkill);
register_bluetooth_error:
- rfkill_unregister(wifi_rfkill);
+ if (wifi_rfkill)
+ rfkill_unregister(wifi_rfkill);
add_sysfs_error:
cleanup_sysfs(device);
return err;
diff --git a/drivers/platform/x86/panasonic-laptop.c b/drivers/platform/x86/panasonic-laptop.c
index f30db36..c47a44d 100644
--- a/drivers/platform/x86/panasonic-laptop.c
+++ b/drivers/platform/x86/panasonic-laptop.c
@@ -507,7 +507,7 @@
hkey_num = result & 0xf;
- if (hkey_num < 0 || hkey_num > ARRAY_SIZE(pcc->keymap)) {
+ if (hkey_num < 0 || hkey_num >= ARRAY_SIZE(pcc->keymap)) {
ACPI_DEBUG_PRINT((ACPI_DB_ERROR,
"hotkey number out of range: %d\n",
hkey_num));
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index cced4d1..81450fb 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -241,6 +241,12 @@
If you say Y here you will get support for the
watchdog timer in the ST M41T60 and M41T80 RTC chips series.
+config RTC_DRV_DM355EVM
+ tristate "TI DaVinci DM355 EVM RTC"
+ depends on MFD_DM355EVM_MSP
+ help
+ Supports the RTC firmware in the MSP430 on the DM355 EVM.
+
config RTC_DRV_TWL92330
boolean "TI TWL92330/Menelaus"
depends on MENELAUS
diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile
index 6e28021..0e697aa 100644
--- a/drivers/rtc/Makefile
+++ b/drivers/rtc/Makefile
@@ -23,6 +23,7 @@
obj-$(CONFIG_RTC_DRV_AU1XXX) += rtc-au1xxx.o
obj-$(CONFIG_RTC_DRV_BFIN) += rtc-bfin.o
obj-$(CONFIG_RTC_DRV_CMOS) += rtc-cmos.o
+obj-$(CONFIG_RTC_DRV_DM355EVM) += rtc-dm355evm.o
obj-$(CONFIG_RTC_DRV_DS1216) += rtc-ds1216.o
obj-$(CONFIG_RTC_DRV_DS1286) += rtc-ds1286.o
obj-$(CONFIG_RTC_DRV_DS1302) += rtc-ds1302.o
diff --git a/drivers/rtc/rtc-dm355evm.c b/drivers/rtc/rtc-dm355evm.c
new file mode 100644
index 0000000..58d4e18
--- /dev/null
+++ b/drivers/rtc/rtc-dm355evm.c
@@ -0,0 +1,175 @@
+/*
+ * rtc-dm355evm.c - access battery-backed counter in MSP430 firmware
+ *
+ * Copyright (c) 2008 by David Brownell
+ *
+ * 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.
+ */
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/rtc.h>
+#include <linux/platform_device.h>
+
+#include <linux/i2c/dm355evm_msp.h>
+
+
+/*
+ * The MSP430 firmware on the DM355 EVM uses a watch crystal to feed
+ * a 1 Hz counter. When a backup battery is supplied, that makes a
+ * reasonable RTC for applications where alarms and non-NTP drift
+ * compensation aren't important.
+ *
+ * The only real glitch is the inability to read or write all four
+ * counter bytes atomically: the count may increment in the middle
+ * of an operation, causing trouble when the LSB rolls over.
+ *
+ * This driver was tested with firmware revision A4.
+ */
+union evm_time {
+ u8 bytes[4];
+ u32 value;
+};
+
+static int dm355evm_rtc_read_time(struct device *dev, struct rtc_time *tm)
+{
+ union evm_time time;
+ int status;
+ int tries = 0;
+
+ do {
+ /*
+ * Read LSB(0) to MSB(3) bytes. Defend against the counter
+ * rolling over by re-reading until the value is stable,
+ * and assuming the four reads take at most a few seconds.
+ */
+ status = dm355evm_msp_read(DM355EVM_MSP_RTC_0);
+ if (status < 0)
+ return status;
+ if (tries && time.bytes[0] == status)
+ break;
+ time.bytes[0] = status;
+
+ status = dm355evm_msp_read(DM355EVM_MSP_RTC_1);
+ if (status < 0)
+ return status;
+ if (tries && time.bytes[1] == status)
+ break;
+ time.bytes[1] = status;
+
+ status = dm355evm_msp_read(DM355EVM_MSP_RTC_2);
+ if (status < 0)
+ return status;
+ if (tries && time.bytes[2] == status)
+ break;
+ time.bytes[2] = status;
+
+ status = dm355evm_msp_read(DM355EVM_MSP_RTC_3);
+ if (status < 0)
+ return status;
+ if (tries && time.bytes[3] == status)
+ break;
+ time.bytes[3] = status;
+
+ } while (++tries < 5);
+
+ dev_dbg(dev, "read timestamp %08x\n", time.value);
+
+ rtc_time_to_tm(le32_to_cpu(time.value), tm);
+ return 0;
+}
+
+static int dm355evm_rtc_set_time(struct device *dev, struct rtc_time *tm)
+{
+ union evm_time time;
+ unsigned long value;
+ int status;
+
+ rtc_tm_to_time(tm, &value);
+ time.value = cpu_to_le32(value);
+
+ dev_dbg(dev, "write timestamp %08x\n", time.value);
+
+ /*
+ * REVISIT handle non-atomic writes ... maybe just retry until
+ * byte[1] sticks (no rollover)?
+ */
+ status = dm355evm_msp_write(time.bytes[0], DM355EVM_MSP_RTC_0);
+ if (status < 0)
+ return status;
+
+ status = dm355evm_msp_write(time.bytes[1], DM355EVM_MSP_RTC_1);
+ if (status < 0)
+ return status;
+
+ status = dm355evm_msp_write(time.bytes[2], DM355EVM_MSP_RTC_2);
+ if (status < 0)
+ return status;
+
+ status = dm355evm_msp_write(time.bytes[3], DM355EVM_MSP_RTC_3);
+ if (status < 0)
+ return status;
+
+ return 0;
+}
+
+static struct rtc_class_ops dm355evm_rtc_ops = {
+ .read_time = dm355evm_rtc_read_time,
+ .set_time = dm355evm_rtc_set_time,
+};
+
+/*----------------------------------------------------------------------*/
+
+static int __devinit dm355evm_rtc_probe(struct platform_device *pdev)
+{
+ struct rtc_device *rtc;
+
+ rtc = rtc_device_register(pdev->name,
+ &pdev->dev, &dm355evm_rtc_ops, THIS_MODULE);
+ if (IS_ERR(rtc)) {
+ dev_err(&pdev->dev, "can't register RTC device, err %ld\n",
+ PTR_ERR(rtc));
+ return PTR_ERR(rtc);
+ }
+ platform_set_drvdata(pdev, rtc);
+
+ return 0;
+}
+
+static int __devexit dm355evm_rtc_remove(struct platform_device *pdev)
+{
+ struct rtc_device *rtc = platform_get_drvdata(pdev);
+
+ rtc_device_unregister(rtc);
+ platform_set_drvdata(pdev, NULL);
+ return 0;
+}
+
+/*
+ * I2C is used to talk to the MSP430, but this platform device is
+ * exposed by an MFD driver that manages I2C communications.
+ */
+static struct platform_driver rtc_dm355evm_driver = {
+ .probe = dm355evm_rtc_probe,
+ .remove = __devexit_p(dm355evm_rtc_remove),
+ .driver = {
+ .owner = THIS_MODULE,
+ .name = "rtc-dm355evm",
+ },
+};
+
+static int __init dm355evm_rtc_init(void)
+{
+ return platform_driver_register(&rtc_dm355evm_driver);
+}
+module_init(dm355evm_rtc_init);
+
+static void __exit dm355evm_rtc_exit(void)
+{
+ platform_driver_unregister(&rtc_dm355evm_driver);
+}
+module_exit(dm355evm_rtc_exit);
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/rtc/rtc-ds1390.c b/drivers/rtc/rtc-ds1390.c
index e54b5c6..e01b955 100644
--- a/drivers/rtc/rtc-ds1390.c
+++ b/drivers/rtc/rtc-ds1390.c
@@ -122,7 +122,6 @@
static int __devinit ds1390_probe(struct spi_device *spi)
{
- struct rtc_device *rtc;
unsigned char tmp;
struct ds1390 *chip;
int res;
diff --git a/drivers/video/aty/aty128fb.c b/drivers/video/aty/aty128fb.c
index db16112..e6e299f 100644
--- a/drivers/video/aty/aty128fb.c
+++ b/drivers/video/aty/aty128fb.c
@@ -1475,7 +1475,7 @@
aty128_set_pll(&par->pll, par);
aty128_set_fifo(&par->fifo_reg, par);
- config = aty_ld_le32(CONFIG_CNTL) & ~3;
+ config = aty_ld_le32(CNFG_CNTL) & ~3;
#if defined(__BIG_ENDIAN)
if (par->crtc.bpp == 32)
@@ -1484,7 +1484,7 @@
config |= 1; /* make aperture do 16 bit swapping */
#endif
- aty_st_le32(CONFIG_CNTL, config);
+ aty_st_le32(CNFG_CNTL, config);
aty_st_8(CRTC_EXT_CNTL + 1, 0); /* turn the video back on */
info->fix.line_length = (par->crtc.vxres * par->crtc.bpp) >> 3;
@@ -1875,7 +1875,7 @@
u32 dac;
/* Get the chip revision */
- chip_rev = (aty_ld_le32(CONFIG_CNTL) >> 16) & 0x1F;
+ chip_rev = (aty_ld_le32(CNFG_CNTL) >> 16) & 0x1F;
strcpy(video_card, "Rage128 XX ");
video_card[8] = ent->device >> 8;
@@ -2057,7 +2057,7 @@
/* Grab memory size from the card */
// How does this relate to the resource length from the PCI hardware?
- par->vram_size = aty_ld_le32(CONFIG_MEMSIZE) & 0x03FFFFFF;
+ par->vram_size = aty_ld_le32(CNFG_MEMSIZE) & 0x03FFFFFF;
/* Virtualize the framebuffer */
info->screen_base = ioremap(fb_addr, par->vram_size);
@@ -2374,6 +2374,8 @@
/* Set the chip into the appropriate suspend mode (we use D2,
* D3 would require a complete re-initialisation of the chip,
* including PCI config registers, clocks, AGP configuration, ...)
+ *
+ * For resume, the core will have already brought us back to D0
*/
if (suspend) {
/* Make sure CRTC2 is reset. Remove that the day we decide to
@@ -2391,17 +2393,9 @@
aty_st_le32(BUS_CNTL1, 0x00000010);
aty_st_le32(MEM_POWER_MISC, 0x0c830000);
mdelay(100);
- pci_read_config_word(pdev, par->pm_reg+PCI_PM_CTRL, &pwr_command);
+
/* Switch PCI power management to D2 */
- pci_write_config_word(pdev, par->pm_reg+PCI_PM_CTRL,
- (pwr_command & ~PCI_PM_CTRL_STATE_MASK) | 2);
- pci_read_config_word(pdev, par->pm_reg+PCI_PM_CTRL, &pwr_command);
- } else {
- /* Switch back PCI power management to D0 */
- mdelay(100);
- pci_write_config_word(pdev, par->pm_reg+PCI_PM_CTRL, 0);
- pci_read_config_word(pdev, par->pm_reg+PCI_PM_CTRL, &pwr_command);
- mdelay(100);
+ pci_set_power_state(pdev, PCI_D2);
}
}
@@ -2410,6 +2404,12 @@
struct fb_info *info = pci_get_drvdata(pdev);
struct aty128fb_par *par = info->par;
+ /* Because we may change PCI D state ourselves, we need to
+ * first save the config space content so the core can
+ * restore it properly on resume.
+ */
+ pci_save_state(pdev);
+
/* We don't do anything but D2, for now we return 0, but
* we may want to change that. How do we know if the BIOS
* can properly take care of D3 ? Also, with swsusp, we
@@ -2476,6 +2476,11 @@
if (pdev->dev.power.power_state.event == PM_EVENT_ON)
return 0;
+ /* PCI state will have been restored by the core, so
+ * we should be in D0 now with our config space fully
+ * restored
+ */
+
/* Wakeup chip */
aty128_set_suspend(par, 0);
par->asleep = 0;
diff --git a/drivers/video/aty/atyfb_base.c b/drivers/video/aty/atyfb_base.c
index cc6b470..1207c20 100644
--- a/drivers/video/aty/atyfb_base.c
+++ b/drivers/video/aty/atyfb_base.c
@@ -135,7 +135,7 @@
#if defined(CONFIG_PM) || defined(CONFIG_PMAC_BACKLIGHT) || \
defined (CONFIG_FB_ATY_GENERIC_LCD) || defined(CONFIG_FB_ATY_BACKLIGHT)
static const u32 lt_lcd_regs[] = {
- CONFIG_PANEL_LG,
+ CNFG_PANEL_LG,
LCD_GEN_CNTL_LG,
DSTN_CONTROL_LG,
HFB_PITCH_ADDR_LG,
@@ -446,7 +446,7 @@
par->pll_limits.ecp_max = aty_chips[i].ecp_max;
par->features = aty_chips[i].features;
- chip_id = aty_ld_le32(CONFIG_CHIP_ID, par);
+ chip_id = aty_ld_le32(CNFG_CHIP_ID, par);
type = chip_id & CFG_CHIP_TYPE;
rev = (chip_id & CFG_CHIP_REV) >> 24;
@@ -629,7 +629,7 @@
crtc->lcd_index = aty_ld_le32(LCD_INDEX, par);
aty_st_le32(LCD_INDEX, crtc->lcd_index, par);
}
- crtc->lcd_config_panel = aty_ld_lcd(CONFIG_PANEL, par);
+ crtc->lcd_config_panel = aty_ld_lcd(CNFG_PANEL, par);
crtc->lcd_gen_cntl = aty_ld_lcd(LCD_GEN_CNTL, par);
@@ -676,7 +676,7 @@
aty_st_le32(CRTC_GEN_CNTL, crtc->gen_cntl & ~(CRTC_EXT_DISP_EN | CRTC_EN), par);
/* update non-shadow registers first */
- aty_st_lcd(CONFIG_PANEL, crtc->lcd_config_panel, par);
+ aty_st_lcd(CNFG_PANEL, crtc->lcd_config_panel, par);
aty_st_lcd(LCD_GEN_CNTL, crtc->lcd_gen_cntl &
~(CRTC_RW_SELECT | SHADOW_EN | SHADOW_RW_EN), par);
@@ -858,7 +858,7 @@
if (!M64_HAS(MOBIL_BUS))
crtc->lcd_index |= CRTC2_DISPLAY_DIS;
- crtc->lcd_config_panel = aty_ld_lcd(CONFIG_PANEL, par) | 0x4000;
+ crtc->lcd_config_panel = aty_ld_lcd(CNFG_PANEL, par) | 0x4000;
crtc->lcd_gen_cntl = aty_ld_lcd(LCD_GEN_CNTL, par) & ~CRTC_RW_SELECT;
crtc->lcd_gen_cntl &=
@@ -1978,7 +1978,7 @@
return timeout ? 0 : -EIO;
}
-#endif
+#endif /* CONFIG_PPC_PMAC */
static int atyfb_pci_suspend(struct pci_dev *pdev, pm_message_t state)
{
@@ -2002,9 +2002,15 @@
par->asleep = 1;
par->lock_blank = 1;
+ /* Because we may change PCI D state ourselves, we need to
+ * first save the config space content so the core can
+ * restore it properly on resume.
+ */
+ pci_save_state(pdev);
+
#ifdef CONFIG_PPC_PMAC
/* Set chip to "suspend" mode */
- if (aty_power_mgmt(1, par)) {
+ if (machine_is(powermac) && aty_power_mgmt(1, par)) {
par->asleep = 0;
par->lock_blank = 0;
atyfb_blank(FB_BLANK_UNBLANK, info);
@@ -2047,11 +2053,15 @@
acquire_console_sem();
+ /* PCI state will have been restored by the core, so
+ * we should be in D0 now with our config space fully
+ * restored
+ */
+
#ifdef CONFIG_PPC_PMAC
- if (pdev->dev.power.power_state.event == 2)
+ if (machine_is(powermac) &&
+ pdev->dev.power.power_state.event == PM_EVENT_SUSPEND)
aty_power_mgmt(0, par);
-#else
- pci_set_power_state(pdev, PCI_D0);
#endif
aty_resume_chip(info);
@@ -2254,7 +2264,7 @@
if (!M64_HAS(INTEGRATED)) {
u32 stat0;
u8 dac_type, dac_subtype, clk_type;
- stat0 = aty_ld_le32(CONFIG_STAT0, par);
+ stat0 = aty_ld_le32(CNFG_STAT0, par);
par->bus_type = (stat0 >> 0) & 0x07;
par->ram_type = (stat0 >> 3) & 0x07;
ramname = aty_gx_ram[par->ram_type];
@@ -2324,7 +2334,7 @@
par->dac_ops = &aty_dac_ct;
par->pll_ops = &aty_pll_ct;
par->bus_type = PCI;
- par->ram_type = (aty_ld_le32(CONFIG_STAT0, par) & 0x07);
+ par->ram_type = (aty_ld_le32(CNFG_STAT0, par) & 0x07);
ramname = aty_ct_ram[par->ram_type];
/* for many chips, the mclk is 67 MHz for SDRAM, 63 MHz otherwise */
if (par->pll_limits.mclk == 67 && par->ram_type < SDRAM)
@@ -2433,7 +2443,7 @@
}
if (M64_HAS(MAGIC_VRAM_SIZE)) {
- if (aty_ld_le32(CONFIG_STAT1, par) & 0x40000000)
+ if (aty_ld_le32(CNFG_STAT1, par) & 0x40000000)
info->fix.smem_len += 0x400000;
}
@@ -2946,7 +2956,7 @@
* Fix PROMs idea of MEM_CNTL settings...
*/
mem = aty_ld_le32(MEM_CNTL, par);
- chip_id = aty_ld_le32(CONFIG_CHIP_ID, par);
+ chip_id = aty_ld_le32(CNFG_CHIP_ID, par);
if (((chip_id & CFG_CHIP_TYPE) == VT_CHIP_ID) && !((chip_id >> 24) & 1)) {
switch (mem & 0x0f) {
case 3:
@@ -2964,7 +2974,7 @@
default:
break;
}
- if ((aty_ld_le32(CONFIG_STAT0, par) & 7) >= SDRAM)
+ if ((aty_ld_le32(CNFG_STAT0, par) & 7) >= SDRAM)
mem &= ~(0x00700000);
}
mem &= ~(0xcf80e000); /* Turn off all undocumented bits. */
@@ -3572,7 +3582,7 @@
}
/* Fake pci_id for correct_chipset() */
- switch (aty_ld_le32(CONFIG_CHIP_ID, par) & CFG_CHIP_TYPE) {
+ switch (aty_ld_le32(CNFG_CHIP_ID, par) & CFG_CHIP_TYPE) {
case 0x00d7:
par->pci_id = PCI_CHIP_MACH64GX;
break;
diff --git a/drivers/video/aty/radeon_base.c b/drivers/video/aty/radeon_base.c
index d0f1a7f..16bb7e3 100644
--- a/drivers/video/aty/radeon_base.c
+++ b/drivers/video/aty/radeon_base.c
@@ -1936,8 +1936,8 @@
OUTREG(CRTC_GEN_CNTL, save_crtc_gen_cntl | CRTC_DISP_REQ_EN_B);
mdelay(100);
- aper_base = INREG(CONFIG_APER_0_BASE);
- aper_size = INREG(CONFIG_APER_SIZE);
+ aper_base = INREG(CNFG_APER_0_BASE);
+ aper_size = INREG(CNFG_APER_SIZE);
#ifdef SET_MC_FB_FROM_APERTURE
/* Set framebuffer to be at the same address as set in PCI BAR */
@@ -2024,11 +2024,11 @@
~CRTC_H_CUTOFF_ACTIVE_EN);
}
} else {
- tmp = INREG(CONFIG_MEMSIZE);
+ tmp = INREG(CNFG_MEMSIZE);
}
/* mem size is bits [28:0], mask off the rest */
- rinfo->video_ram = tmp & CONFIG_MEMSIZE_MASK;
+ rinfo->video_ram = tmp & CNFG_MEMSIZE_MASK;
/*
* Hack to get around some busted production M6's
@@ -2228,7 +2228,7 @@
*/
rinfo->errata = 0;
if (rinfo->family == CHIP_FAMILY_R300 &&
- (INREG(CONFIG_CNTL) & CFG_ATI_REV_ID_MASK)
+ (INREG(CNFG_CNTL) & CFG_ATI_REV_ID_MASK)
== CFG_ATI_REV_A11)
rinfo->errata |= CHIP_ERRATA_R300_CG;
diff --git a/drivers/video/aty/radeon_pm.c b/drivers/video/aty/radeon_pm.c
index 675abda..ca5f0dc 100644
--- a/drivers/video/aty/radeon_pm.c
+++ b/drivers/video/aty/radeon_pm.c
@@ -333,7 +333,7 @@
if (!rinfo->has_CRTC2) {
tmp = INPLL(pllSCLK_CNTL);
- if ((INREG(CONFIG_CNTL) & CFG_ATI_REV_ID_MASK) > CFG_ATI_REV_A13)
+ if ((INREG(CNFG_CNTL) & CFG_ATI_REV_ID_MASK) > CFG_ATI_REV_A13)
tmp &= ~(SCLK_CNTL__FORCE_CP | SCLK_CNTL__FORCE_RB);
tmp &= ~(SCLK_CNTL__FORCE_HDP | SCLK_CNTL__FORCE_DISP1 |
SCLK_CNTL__FORCE_TOP | SCLK_CNTL__FORCE_SE |
@@ -468,9 +468,9 @@
/*RAGE_6::A11 A12 A12N1 A13, RV250::A11 A12, R300*/
if ((rinfo->family == CHIP_FAMILY_RV250 &&
- ((INREG(CONFIG_CNTL) & CFG_ATI_REV_ID_MASK) < CFG_ATI_REV_A13)) ||
+ ((INREG(CNFG_CNTL) & CFG_ATI_REV_ID_MASK) < CFG_ATI_REV_A13)) ||
((rinfo->family == CHIP_FAMILY_RV100) &&
- ((INREG(CONFIG_CNTL) & CFG_ATI_REV_ID_MASK) <= CFG_ATI_REV_A13))) {
+ ((INREG(CNFG_CNTL) & CFG_ATI_REV_ID_MASK) <= CFG_ATI_REV_A13))) {
tmp |= SCLK_CNTL__FORCE_CP;
tmp |= SCLK_CNTL__FORCE_VIP;
}
@@ -486,7 +486,7 @@
/* RV200::A11 A12 RV250::A11 A12 */
if (((rinfo->family == CHIP_FAMILY_RV200) ||
(rinfo->family == CHIP_FAMILY_RV250)) &&
- ((INREG(CONFIG_CNTL) & CFG_ATI_REV_ID_MASK) < CFG_ATI_REV_A13))
+ ((INREG(CNFG_CNTL) & CFG_ATI_REV_ID_MASK) < CFG_ATI_REV_A13))
tmp |= SCLK_MORE_CNTL__FORCEON;
OUTPLL(pllSCLK_MORE_CNTL, tmp);
@@ -497,7 +497,7 @@
/* RV200::A11 A12, RV250::A11 A12 */
if (((rinfo->family == CHIP_FAMILY_RV200) ||
(rinfo->family == CHIP_FAMILY_RV250)) &&
- ((INREG(CONFIG_CNTL) & CFG_ATI_REV_ID_MASK) < CFG_ATI_REV_A13)) {
+ ((INREG(CNFG_CNTL) & CFG_ATI_REV_ID_MASK) < CFG_ATI_REV_A13)) {
tmp = INPLL(pllPLL_PWRMGT_CNTL);
tmp |= PLL_PWRMGT_CNTL__TCL_BYPASS_DISABLE;
OUTPLL(pllPLL_PWRMGT_CNTL, tmp);
@@ -702,7 +702,7 @@
OUTREG(DISPLAY_BASE_ADDR, rinfo->save_regs[31]);
OUTREG(MC_AGP_LOCATION, rinfo->save_regs[32]);
OUTREG(CRTC2_DISPLAY_BASE_ADDR, rinfo->save_regs[33]);
- OUTREG(CONFIG_MEMSIZE, rinfo->video_ram);
+ OUTREG(CNFG_MEMSIZE, rinfo->video_ram);
OUTREG(DISP_MISC_CNTL, rinfo->save_regs[9]);
OUTREG(DISP_PWR_MAN, rinfo->save_regs[10]);
@@ -1723,7 +1723,7 @@
OUTREG(CRTC2_DISPLAY_BASE_ADDR, rinfo->save_regs[33]);
OUTREG(MC_FB_LOCATION, rinfo->save_regs[30]);
OUTREG(OV0_BASE_ADDR, rinfo->save_regs[80]);
- OUTREG(CONFIG_MEMSIZE, rinfo->video_ram);
+ OUTREG(CNFG_MEMSIZE, rinfo->video_ram);
OUTREG(BUS_CNTL, rinfo->save_regs[36]);
OUTREG(BUS_CNTL1, rinfo->save_regs[14]);
OUTREG(MPP_TB_CONFIG, rinfo->save_regs[37]);
@@ -1961,7 +1961,7 @@
OUTMC(rinfo, ixMC_CHP_IO_CNTL_B1, rinfo->save_regs[68] /*0x141555ff*/);
OUTMC(rinfo, ixMC_IMP_CNTL_0, rinfo->save_regs[71] /*0x00009249*/);
OUTREG(MC_IND_INDEX, 0);
- OUTREG(CONFIG_MEMSIZE, rinfo->video_ram);
+ OUTREG(CNFG_MEMSIZE, rinfo->video_ram);
mdelay(20);
}
@@ -2361,7 +2361,7 @@
OUTMC(rinfo, ixMC_IMP_CNTL_0, 0x00009249);
OUTREG(MC_IND_INDEX, 0);
- OUTREG(CONFIG_MEMSIZE, rinfo->video_ram);
+ OUTREG(CNFG_MEMSIZE, rinfo->video_ram);
radeon_pm_full_reset_sdram(rinfo);
@@ -2509,9 +2509,7 @@
static void radeon_set_suspend(struct radeonfb_info *rinfo, int suspend)
{
- u16 pwr_cmd;
u32 tmp;
- int i;
if (!rinfo->pm_reg)
return;
@@ -2557,32 +2555,14 @@
}
}
- for (i = 0; i < 64; ++i)
- pci_read_config_dword(rinfo->pdev, i * 4,
- &rinfo->cfg_save[i]);
-
/* Switch PCI power management to D2. */
pci_disable_device(rinfo->pdev);
- for (;;) {
- pci_read_config_word(
- rinfo->pdev, rinfo->pm_reg+PCI_PM_CTRL,
- &pwr_cmd);
- if (pwr_cmd & 2)
- break;
- pci_write_config_word(
- rinfo->pdev, rinfo->pm_reg+PCI_PM_CTRL,
- (pwr_cmd & ~PCI_PM_CTRL_STATE_MASK) | 2);
- mdelay(500);
- }
+ pci_save_state(rinfo->pdev);
+ pci_set_power_state(rinfo->pdev, PCI_D2);
} else {
printk(KERN_DEBUG "radeonfb (%s): switching to D0 state...\n",
pci_name(rinfo->pdev));
- /* Switch back PCI powermanagment to D0 */
- mdelay(200);
- pci_write_config_word(rinfo->pdev, rinfo->pm_reg+PCI_PM_CTRL, 0);
- mdelay(500);
-
if (rinfo->family <= CHIP_FAMILY_RV250) {
/* Reset the SDRAM controller */
radeon_pm_full_reset_sdram(rinfo);
@@ -2598,37 +2578,10 @@
}
}
-static int radeon_restore_pci_cfg(struct radeonfb_info *rinfo)
-{
- int i;
- static u32 radeon_cfg_after_resume[64];
-
- for (i = 0; i < 64; ++i)
- pci_read_config_dword(rinfo->pdev, i * 4,
- &radeon_cfg_after_resume[i]);
-
- if (radeon_cfg_after_resume[PCI_BASE_ADDRESS_0/4]
- == rinfo->cfg_save[PCI_BASE_ADDRESS_0/4])
- return 0; /* assume everything is ok */
-
- for (i = PCI_BASE_ADDRESS_0/4; i < 64; ++i) {
- if (radeon_cfg_after_resume[i] != rinfo->cfg_save[i])
- pci_write_config_dword(rinfo->pdev, i * 4,
- rinfo->cfg_save[i]);
- }
- pci_write_config_word(rinfo->pdev, PCI_CACHE_LINE_SIZE,
- rinfo->cfg_save[PCI_CACHE_LINE_SIZE/4]);
- pci_write_config_word(rinfo->pdev, PCI_COMMAND,
- rinfo->cfg_save[PCI_COMMAND/4]);
- return 1;
-}
-
-
int radeonfb_pci_suspend(struct pci_dev *pdev, pm_message_t mesg)
{
struct fb_info *info = pci_get_drvdata(pdev);
struct radeonfb_info *rinfo = info->par;
- int i;
if (mesg.event == pdev->dev.power.power_state.event)
return 0;
@@ -2674,6 +2627,11 @@
pmac_suspend_agp_for_card(pdev);
#endif /* CONFIG_PPC_PMAC */
+ /* It's unclear whether or when the generic code will do that, so let's
+ * do it ourselves. We save state before we do any power management
+ */
+ pci_save_state(pdev);
+
/* If we support wakeup from poweroff, we save all regs we can including cfg
* space
*/
@@ -2698,9 +2656,6 @@
mdelay(20);
OUTREG(LVDS_GEN_CNTL, INREG(LVDS_GEN_CNTL) & ~(LVDS_DIGON));
}
- // FIXME: Use PCI layer
- for (i = 0; i < 64; ++i)
- pci_read_config_dword(pdev, i * 4, &rinfo->cfg_save[i]);
pci_disable_device(pdev);
}
/* If we support D2, we go to it (should be fixed later with a flag forcing
@@ -2717,6 +2672,13 @@
return 0;
}
+static int radeon_check_power_loss(struct radeonfb_info *rinfo)
+{
+ return rinfo->save_regs[4] != INPLL(CLK_PIN_CNTL) ||
+ rinfo->save_regs[2] != INPLL(MCLK_CNTL) ||
+ rinfo->save_regs[3] != INPLL(SCLK_CNTL);
+}
+
int radeonfb_pci_resume(struct pci_dev *pdev)
{
struct fb_info *info = pci_get_drvdata(pdev);
@@ -2735,20 +2697,13 @@
printk(KERN_DEBUG "radeonfb (%s): resuming from state: %d...\n",
pci_name(pdev), pdev->dev.power.power_state.event);
-
- if (pci_enable_device(pdev)) {
- rc = -ENODEV;
- printk(KERN_ERR "radeonfb (%s): can't enable PCI device !\n",
- pci_name(pdev));
- goto bail;
- }
- pci_set_master(pdev);
-
+ /* PCI state will have been restored by the core, so
+ * we should be in D0 now with our config space fully
+ * restored
+ */
if (pdev->dev.power.power_state.event == PM_EVENT_SUSPEND) {
- /* Wakeup chip. Check from config space if we were powered off
- * (todo: additionally, check CLK_PIN_CNTL too)
- */
- if ((rinfo->pm_mode & radeon_pm_off) && radeon_restore_pci_cfg(rinfo)) {
+ /* Wakeup chip */
+ if ((rinfo->pm_mode & radeon_pm_off) && radeon_check_power_loss(rinfo)) {
if (rinfo->reinit_func != NULL)
rinfo->reinit_func(rinfo);
else {
diff --git a/drivers/video/aty/radeonfb.h b/drivers/video/aty/radeonfb.h
index 3ea1b00..7351e66 100644
--- a/drivers/video/aty/radeonfb.h
+++ b/drivers/video/aty/radeonfb.h
@@ -361,8 +361,6 @@
#ifdef CONFIG_FB_RADEON_I2C
struct radeon_i2c_chan i2c[4];
#endif
-
- u32 cfg_save[64];
};
diff --git a/drivers/video/backlight/Makefile b/drivers/video/backlight/Makefile
index 363b3cb..63d7594 100644
--- a/drivers/video/backlight/Makefile
+++ b/drivers/video/backlight/Makefile
@@ -18,7 +18,7 @@
obj-$(CONFIG_BACKLIGHT_PROGEAR) += progear_bl.o
obj-$(CONFIG_BACKLIGHT_CARILLO_RANCH) += cr_bllcd.o
obj-$(CONFIG_BACKLIGHT_PWM) += pwm_bl.o
-obj-$(CONFIG_BACKLIGHT_DA903X) += da903x.o
+obj-$(CONFIG_BACKLIGHT_DA903X) += da903x_bl.o
obj-$(CONFIG_BACKLIGHT_MBP_NVIDIA) += mbp_nvidia_bl.o
obj-$(CONFIG_BACKLIGHT_TOSA) += tosa_bl.o
obj-$(CONFIG_BACKLIGHT_SAHARA) += kb3886_bl.o
diff --git a/drivers/video/backlight/da903x.c b/drivers/video/backlight/da903x_bl.c
similarity index 100%
rename from drivers/video/backlight/da903x.c
rename to drivers/video/backlight/da903x_bl.c
diff --git a/drivers/video/fbcmap.c b/drivers/video/fbcmap.c
index 91b78e6..f53b9f1 100644
--- a/drivers/video/fbcmap.c
+++ b/drivers/video/fbcmap.c
@@ -250,10 +250,6 @@
int rc, size = cmap->len * sizeof(u16);
struct fb_cmap umap;
- if (cmap->start < 0 || (!info->fbops->fb_setcolreg &&
- !info->fbops->fb_setcmap))
- return -EINVAL;
-
memset(&umap, 0, sizeof(struct fb_cmap));
rc = fb_alloc_cmap(&umap, cmap->len, cmap->transp != NULL);
if (rc)
@@ -262,11 +258,23 @@
copy_from_user(umap.green, cmap->green, size) ||
copy_from_user(umap.blue, cmap->blue, size) ||
(cmap->transp && copy_from_user(umap.transp, cmap->transp, size))) {
- fb_dealloc_cmap(&umap);
- return -EFAULT;
+ rc = -EFAULT;
+ goto out;
}
umap.start = cmap->start;
+ if (!lock_fb_info(info)) {
+ rc = -ENODEV;
+ goto out;
+ }
+ if (cmap->start < 0 || (!info->fbops->fb_setcolreg &&
+ !info->fbops->fb_setcmap)) {
+ rc = -EINVAL;
+ goto out1;
+ }
rc = fb_set_cmap(&umap, info);
+out1:
+ unlock_fb_info(info);
+out:
fb_dealloc_cmap(&umap);
return rc;
}
diff --git a/drivers/video/fbmem.c b/drivers/video/fbmem.c
index 756efeb..cfd9dce 100644
--- a/drivers/video/fbmem.c
+++ b/drivers/video/fbmem.c
@@ -1013,132 +1013,139 @@
struct fb_var_screeninfo var;
struct fb_fix_screeninfo fix;
struct fb_con2fbmap con2fb;
+ struct fb_cmap cmap_from;
struct fb_cmap_user cmap;
struct fb_event event;
void __user *argp = (void __user *)arg;
long ret = 0;
- fb = info->fbops;
- if (!fb)
- return -ENODEV;
-
switch (cmd) {
case FBIOGET_VSCREENINFO:
- ret = copy_to_user(argp, &info->var,
- sizeof(var)) ? -EFAULT : 0;
+ if (!lock_fb_info(info))
+ return -ENODEV;
+ var = info->var;
+ unlock_fb_info(info);
+
+ ret = copy_to_user(argp, &var, sizeof(var)) ? -EFAULT : 0;
break;
case FBIOPUT_VSCREENINFO:
- if (copy_from_user(&var, argp, sizeof(var))) {
- ret = -EFAULT;
- break;
- }
+ if (copy_from_user(&var, argp, sizeof(var)))
+ return -EFAULT;
+ if (!lock_fb_info(info))
+ return -ENODEV;
acquire_console_sem();
info->flags |= FBINFO_MISC_USEREVENT;
ret = fb_set_var(info, &var);
info->flags &= ~FBINFO_MISC_USEREVENT;
release_console_sem();
- if (ret == 0 && copy_to_user(argp, &var, sizeof(var)))
+ unlock_fb_info(info);
+ if (!ret && copy_to_user(argp, &var, sizeof(var)))
ret = -EFAULT;
break;
case FBIOGET_FSCREENINFO:
- ret = copy_to_user(argp, &info->fix,
- sizeof(fix)) ? -EFAULT : 0;
+ if (!lock_fb_info(info))
+ return -ENODEV;
+ fix = info->fix;
+ unlock_fb_info(info);
+
+ ret = copy_to_user(argp, &fix, sizeof(fix)) ? -EFAULT : 0;
break;
case FBIOPUTCMAP:
if (copy_from_user(&cmap, argp, sizeof(cmap)))
- ret = -EFAULT;
- else
- ret = fb_set_user_cmap(&cmap, info);
+ return -EFAULT;
+ ret = fb_set_user_cmap(&cmap, info);
break;
case FBIOGETCMAP:
if (copy_from_user(&cmap, argp, sizeof(cmap)))
- ret = -EFAULT;
- else
- ret = fb_cmap_to_user(&info->cmap, &cmap);
+ return -EFAULT;
+ if (!lock_fb_info(info))
+ return -ENODEV;
+ cmap_from = info->cmap;
+ unlock_fb_info(info);
+ ret = fb_cmap_to_user(&cmap_from, &cmap);
break;
case FBIOPAN_DISPLAY:
- if (copy_from_user(&var, argp, sizeof(var))) {
- ret = -EFAULT;
- break;
- }
+ if (copy_from_user(&var, argp, sizeof(var)))
+ return -EFAULT;
+ if (!lock_fb_info(info))
+ return -ENODEV;
acquire_console_sem();
ret = fb_pan_display(info, &var);
release_console_sem();
+ unlock_fb_info(info);
if (ret == 0 && copy_to_user(argp, &var, sizeof(var)))
- ret = -EFAULT;
+ return -EFAULT;
break;
case FBIO_CURSOR:
ret = -EINVAL;
break;
case FBIOGET_CON2FBMAP:
if (copy_from_user(&con2fb, argp, sizeof(con2fb)))
- ret = -EFAULT;
- else if (con2fb.console < 1 || con2fb.console > MAX_NR_CONSOLES)
- ret = -EINVAL;
- else {
- con2fb.framebuffer = -1;
- event.info = info;
- event.data = &con2fb;
- fb_notifier_call_chain(FB_EVENT_GET_CONSOLE_MAP,
- &event);
- ret = copy_to_user(argp, &con2fb,
- sizeof(con2fb)) ? -EFAULT : 0;
- }
+ return -EFAULT;
+ if (con2fb.console < 1 || con2fb.console > MAX_NR_CONSOLES)
+ return -EINVAL;
+ con2fb.framebuffer = -1;
+ event.data = &con2fb;
+
+ if (!lock_fb_info(info))
+ return -ENODEV;
+ event.info = info;
+ fb_notifier_call_chain(FB_EVENT_GET_CONSOLE_MAP, &event);
+ unlock_fb_info(info);
+
+ ret = copy_to_user(argp, &con2fb, sizeof(con2fb)) ? -EFAULT : 0;
break;
case FBIOPUT_CON2FBMAP:
- if (copy_from_user(&con2fb, argp, sizeof(con2fb))) {
- ret = -EFAULT;
- break;
- }
- if (con2fb.console < 1 || con2fb.console > MAX_NR_CONSOLES) {
- ret = -EINVAL;
- break;
- }
- if (con2fb.framebuffer < 0 || con2fb.framebuffer >= FB_MAX) {
- ret = -EINVAL;
- break;
- }
+ if (copy_from_user(&con2fb, argp, sizeof(con2fb)))
+ return -EFAULT;
+ if (con2fb.console < 1 || con2fb.console > MAX_NR_CONSOLES)
+ return -EINVAL;
+ if (con2fb.framebuffer < 0 || con2fb.framebuffer >= FB_MAX)
+ return -EINVAL;
if (!registered_fb[con2fb.framebuffer])
request_module("fb%d", con2fb.framebuffer);
if (!registered_fb[con2fb.framebuffer]) {
ret = -EINVAL;
break;
}
- event.info = info;
event.data = &con2fb;
+ if (!lock_fb_info(info))
+ return -ENODEV;
+ event.info = info;
ret = fb_notifier_call_chain(FB_EVENT_SET_CONSOLE_MAP,
&event);
+ unlock_fb_info(info);
break;
case FBIOBLANK:
+ if (!lock_fb_info(info))
+ return -ENODEV;
acquire_console_sem();
info->flags |= FBINFO_MISC_USEREVENT;
ret = fb_blank(info, arg);
info->flags &= ~FBINFO_MISC_USEREVENT;
release_console_sem();
- break;;
+ unlock_fb_info(info);
+ break;
default:
- if (fb->fb_ioctl == NULL)
- ret = -ENOTTY;
- else
+ if (!lock_fb_info(info))
+ return -ENODEV;
+ fb = info->fbops;
+ if (fb->fb_ioctl)
ret = fb->fb_ioctl(info, cmd, arg);
+ else
+ ret = -ENOTTY;
+ unlock_fb_info(info);
}
return ret;
}
static long fb_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
-__acquires(&info->lock)
-__releases(&info->lock)
{
struct inode *inode = file->f_path.dentry->d_inode;
int fbidx = iminor(inode);
- struct fb_info *info;
- long ret;
+ struct fb_info *info = registered_fb[fbidx];
- info = registered_fb[fbidx];
- mutex_lock(&info->lock);
- ret = do_fb_ioctl(info, cmd, arg);
- mutex_unlock(&info->lock);
- return ret;
+ return do_fb_ioctl(info, cmd, arg);
}
#ifdef CONFIG_COMPAT
@@ -1257,8 +1264,6 @@
static long fb_compat_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
-__acquires(&info->lock)
-__releases(&info->lock)
{
struct inode *inode = file->f_path.dentry->d_inode;
int fbidx = iminor(inode);
@@ -1266,7 +1271,6 @@
struct fb_ops *fb = info->fbops;
long ret = -ENOIOCTLCMD;
- mutex_lock(&info->lock);
switch(cmd) {
case FBIOGET_VSCREENINFO:
case FBIOPUT_VSCREENINFO:
@@ -1292,7 +1296,6 @@
ret = fb->fb_compat_ioctl(info, cmd, arg);
break;
}
- mutex_unlock(&info->lock);
return ret;
}
#endif
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index eb0dfde..3141e14 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -26,6 +26,7 @@
#include <linux/irq.h>
#include <linux/module.h>
#include <linux/string.h>
+#include <linux/bootmem.h>
#include <asm/ptrace.h>
#include <asm/irq.h>
@@ -75,7 +76,14 @@
static int evtchn_to_irq[NR_EVENT_CHANNELS] = {
[0 ... NR_EVENT_CHANNELS-1] = -1
};
-static unsigned long cpu_evtchn_mask[NR_CPUS][NR_EVENT_CHANNELS/BITS_PER_LONG];
+struct cpu_evtchn_s {
+ unsigned long bits[NR_EVENT_CHANNELS/BITS_PER_LONG];
+};
+static struct cpu_evtchn_s *cpu_evtchn_mask_p;
+static inline unsigned long *cpu_evtchn_mask(int cpu)
+{
+ return cpu_evtchn_mask_p[cpu].bits;
+}
static u8 cpu_evtchn[NR_EVENT_CHANNELS];
/* Reference counts for bindings to IRQs. */
@@ -115,7 +123,7 @@
unsigned int idx)
{
return (sh->evtchn_pending[idx] &
- cpu_evtchn_mask[cpu][idx] &
+ cpu_evtchn_mask(cpu)[idx] &
~sh->evtchn_mask[idx]);
}
@@ -125,11 +133,11 @@
BUG_ON(irq == -1);
#ifdef CONFIG_SMP
- irq_to_desc(irq)->affinity = cpumask_of_cpu(cpu);
+ cpumask_copy(irq_to_desc(irq)->affinity, cpumask_of(cpu));
#endif
- __clear_bit(chn, cpu_evtchn_mask[cpu_evtchn[chn]]);
- __set_bit(chn, cpu_evtchn_mask[cpu]);
+ __clear_bit(chn, cpu_evtchn_mask(cpu_evtchn[chn]));
+ __set_bit(chn, cpu_evtchn_mask(cpu));
cpu_evtchn[chn] = cpu;
}
@@ -142,12 +150,12 @@
/* By default all event channels notify CPU#0. */
for_each_irq_desc(i, desc) {
- desc->affinity = cpumask_of_cpu(0);
+ cpumask_copy(desc->affinity, cpumask_of(0));
}
#endif
memset(cpu_evtchn, 0, sizeof(cpu_evtchn));
- memset(cpu_evtchn_mask[0], ~0, sizeof(cpu_evtchn_mask[0]));
+ memset(cpu_evtchn_mask(0), ~0, sizeof(cpu_evtchn_mask(0)));
}
static inline unsigned int cpu_from_evtchn(unsigned int evtchn)
@@ -822,6 +830,10 @@
void __init xen_init_IRQ(void)
{
int i;
+ size_t size = nr_cpu_ids * sizeof(struct cpu_evtchn_s);
+
+ cpu_evtchn_mask_p = alloc_bootmem(size);
+ BUG_ON(cpu_evtchn_mask_p == NULL);
init_evtchn_cpu_bindings();
diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c
index 9b91617..e7e83b6 100644
--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -100,7 +100,7 @@
/* XXX use normal device tree? */
xenbus_suspend();
- err = stop_machine(xen_suspend, &cancelled, &cpumask_of_cpu(0));
+ err = stop_machine(xen_suspend, &cancelled, cpumask_of(0));
if (err) {
printk(KERN_ERR "failed to start xen_suspend: %d\n", err);
goto out;
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index e3ff2b9..33b7235 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1208,9 +1208,11 @@
* check for an ELF header. If we find one, dump the first page to
* aid in determining what was mapped here.
*/
- if (FILTER(ELF_HEADERS) && vma->vm_file != NULL && vma->vm_pgoff == 0) {
+ if (FILTER(ELF_HEADERS) &&
+ vma->vm_pgoff == 0 && (vma->vm_flags & VM_READ)) {
u32 __user *header = (u32 __user *) vma->vm_start;
u32 word;
+ mm_segment_t fs = get_fs();
/*
* Doing it this way gets the constant folded by GCC.
*/
@@ -1223,7 +1225,15 @@
magic.elfmag[EI_MAG1] = ELFMAG1;
magic.elfmag[EI_MAG2] = ELFMAG2;
magic.elfmag[EI_MAG3] = ELFMAG3;
- if (get_user(word, header) == 0 && word == magic.cmp)
+ /*
+ * Switch to the user "segment" for get_user(),
+ * then put back what elf_core_dump() had in place.
+ */
+ set_fs(USER_DS);
+ if (unlikely(get_user(word, header)))
+ word = 0;
+ set_fs(fs);
+ if (word == magic.cmp)
return PAGE_SIZE;
}
diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig
index f8fcf99..7bb3c02 100644
--- a/fs/btrfs/Kconfig
+++ b/fs/btrfs/Kconfig
@@ -16,3 +16,16 @@
module will be called btrfs.
If unsure, say N.
+
+config BTRFS_FS_POSIX_ACL
+ bool "Btrfs POSIX Access Control Lists"
+ depends on BTRFS_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/>.
+
+ If you don't know what Access Control Lists are, say N
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 8e2fec0..c84ca1f 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -16,11 +16,11 @@
* Boston, MA 021110-1307, USA.
*/
-#include <linux/version.h>
#include <linux/kthread.h>
#include <linux/list.h>
#include <linux/spinlock.h>
-# include <linux/freezer.h>
+#include <linux/freezer.h>
+#include <linux/ftrace.h>
#include "async-thread.h"
#define WORK_QUEUED_BIT 0
@@ -143,6 +143,7 @@
struct btrfs_work *work;
do {
spin_lock_irq(&worker->lock);
+again_locked:
while (!list_empty(&worker->pending)) {
cur = worker->pending.next;
work = list_entry(cur, struct btrfs_work, list);
@@ -165,14 +166,50 @@
check_idle_worker(worker);
}
- worker->working = 0;
if (freezing(current)) {
+ worker->working = 0;
+ spin_unlock_irq(&worker->lock);
refrigerator();
} else {
- set_current_state(TASK_INTERRUPTIBLE);
spin_unlock_irq(&worker->lock);
- if (!kthread_should_stop())
+ if (!kthread_should_stop()) {
+ cpu_relax();
+ /*
+ * we've dropped the lock, did someone else
+ * jump_in?
+ */
+ smp_mb();
+ if (!list_empty(&worker->pending))
+ continue;
+
+ /*
+ * this short schedule allows more work to
+ * come in without the queue functions
+ * needing to go through wake_up_process()
+ *
+ * worker->working is still 1, so nobody
+ * is going to try and wake us up
+ */
+ schedule_timeout(1);
+ smp_mb();
+ if (!list_empty(&worker->pending))
+ continue;
+
+ /* still no more work?, sleep for real */
+ spin_lock_irq(&worker->lock);
+ set_current_state(TASK_INTERRUPTIBLE);
+ if (!list_empty(&worker->pending))
+ goto again_locked;
+
+ /*
+ * this makes sure we get a wakeup when someone
+ * adds something new to the queue
+ */
+ worker->working = 0;
+ spin_unlock_irq(&worker->lock);
+
schedule();
+ }
__set_current_state(TASK_RUNNING);
}
} while (!kthread_should_stop());
@@ -350,13 +387,14 @@
{
struct btrfs_worker_thread *worker = work->worker;
unsigned long flags;
+ int wake = 0;
if (test_and_set_bit(WORK_QUEUED_BIT, &work->flags))
goto out;
spin_lock_irqsave(&worker->lock, flags);
- atomic_inc(&worker->num_pending);
list_add_tail(&work->list, &worker->pending);
+ atomic_inc(&worker->num_pending);
/* by definition we're busy, take ourselves off the idle
* list
@@ -368,10 +406,16 @@
&worker->workers->worker_list);
spin_unlock_irqrestore(&worker->workers->lock, flags);
}
+ if (!worker->working) {
+ wake = 1;
+ worker->working = 1;
+ }
spin_unlock_irqrestore(&worker->lock, flags);
-
+ if (wake)
+ wake_up_process(worker->task);
out:
+
return 0;
}
@@ -398,9 +442,10 @@
}
spin_lock_irqsave(&worker->lock, flags);
+
+ list_add_tail(&work->list, &worker->pending);
atomic_inc(&worker->num_pending);
check_busy_worker(worker);
- list_add_tail(&work->list, &worker->pending);
/*
* avoid calling into wake_up_process if this thread has already
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index ee848d8..ab07627 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -32,7 +32,6 @@
#include <linux/swap.h>
#include <linux/writeback.h>
#include <linux/bit_spinlock.h>
-#include <linux/version.h>
#include <linux/pagevec.h>
#include "compat.h"
#include "ctree.h"
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 9e46c07..551177c 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -54,6 +54,31 @@
return path;
}
+/*
+ * set all locked nodes in the path to blocking locks. This should
+ * be done before scheduling
+ */
+noinline void btrfs_set_path_blocking(struct btrfs_path *p)
+{
+ int i;
+ for (i = 0; i < BTRFS_MAX_LEVEL; i++) {
+ if (p->nodes[i] && p->locks[i])
+ btrfs_set_lock_blocking(p->nodes[i]);
+ }
+}
+
+/*
+ * reset all the locked nodes in the patch to spinning locks.
+ */
+noinline void btrfs_clear_path_blocking(struct btrfs_path *p)
+{
+ int i;
+ for (i = 0; i < BTRFS_MAX_LEVEL; i++) {
+ if (p->nodes[i] && p->locks[i])
+ btrfs_clear_lock_blocking(p->nodes[i]);
+ }
+}
+
/* this also releases the path */
void btrfs_free_path(struct btrfs_path *p)
{
@@ -272,6 +297,8 @@
if (IS_ERR(cow))
return PTR_ERR(cow);
+ /* cow is set to blocking by btrfs_init_new_buffer */
+
copy_extent_buffer(cow, buf, 0, 0, cow->len);
btrfs_set_header_bytenr(cow, cow->start);
btrfs_set_header_generation(cow, trans->transid);
@@ -388,17 +415,20 @@
WARN_ON(1);
}
- spin_lock(&root->fs_info->hash_lock);
if (btrfs_header_generation(buf) == trans->transid &&
btrfs_header_owner(buf) == root->root_key.objectid &&
!btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN)) {
*cow_ret = buf;
- spin_unlock(&root->fs_info->hash_lock);
WARN_ON(prealloc_dest);
return 0;
}
- spin_unlock(&root->fs_info->hash_lock);
+
search_start = buf->start & ~((u64)(1024 * 1024 * 1024) - 1);
+
+ if (parent)
+ btrfs_set_lock_blocking(parent);
+ btrfs_set_lock_blocking(buf);
+
ret = __btrfs_cow_block(trans, root, buf, parent,
parent_slot, cow_ret, search_start, 0,
prealloc_dest);
@@ -504,6 +534,8 @@
if (parent_nritems == 1)
return 0;
+ btrfs_set_lock_blocking(parent);
+
for (i = start_slot; i < end_slot; i++) {
int close = 1;
@@ -564,6 +596,7 @@
search_start = last_block;
btrfs_tree_lock(cur);
+ btrfs_set_lock_blocking(cur);
err = __btrfs_cow_block(trans, root, cur, parent, i,
&cur, search_start,
min(16 * blocksize,
@@ -862,6 +895,7 @@
return 0;
mid = path->nodes[level];
+
WARN_ON(!path->locks[level]);
WARN_ON(btrfs_header_generation(mid) != trans->transid);
@@ -884,6 +918,7 @@
/* promote the child to a root */
child = read_node_slot(root, mid, 0);
btrfs_tree_lock(child);
+ btrfs_set_lock_blocking(child);
BUG_ON(!child);
ret = btrfs_cow_block(trans, root, child, mid, 0, &child, 0);
BUG_ON(ret);
@@ -900,6 +935,7 @@
add_root_to_dirty_list(root);
btrfs_tree_unlock(child);
+
path->locks[level] = 0;
path->nodes[level] = NULL;
clean_tree_block(trans, root, mid);
@@ -924,6 +960,7 @@
left = read_node_slot(root, parent, pslot - 1);
if (left) {
btrfs_tree_lock(left);
+ btrfs_set_lock_blocking(left);
wret = btrfs_cow_block(trans, root, left,
parent, pslot - 1, &left, 0);
if (wret) {
@@ -934,6 +971,7 @@
right = read_node_slot(root, parent, pslot + 1);
if (right) {
btrfs_tree_lock(right);
+ btrfs_set_lock_blocking(right);
wret = btrfs_cow_block(trans, root, right,
parent, pslot + 1, &right, 0);
if (wret) {
@@ -1109,6 +1147,8 @@
u32 left_nr;
btrfs_tree_lock(left);
+ btrfs_set_lock_blocking(left);
+
left_nr = btrfs_header_nritems(left);
if (left_nr >= BTRFS_NODEPTRS_PER_BLOCK(root) - 1) {
wret = 1;
@@ -1155,7 +1195,10 @@
*/
if (right) {
u32 right_nr;
+
btrfs_tree_lock(right);
+ btrfs_set_lock_blocking(right);
+
right_nr = btrfs_header_nritems(right);
if (right_nr >= BTRFS_NODEPTRS_PER_BLOCK(root) - 1) {
wret = 1;
@@ -1210,8 +1253,7 @@
struct btrfs_disk_key disk_key;
u32 nritems;
u64 search;
- u64 lowest_read;
- u64 highest_read;
+ u64 target;
u64 nread = 0;
int direction = path->reada;
struct extent_buffer *eb;
@@ -1235,8 +1277,7 @@
return;
}
- highest_read = search;
- lowest_read = search;
+ target = search;
nritems = btrfs_header_nritems(node);
nr = slot;
@@ -1256,28 +1297,81 @@
break;
}
search = btrfs_node_blockptr(node, nr);
- if ((search >= lowest_read && search <= highest_read) ||
- (search < lowest_read && lowest_read - search <= 16384) ||
- (search > highest_read && search - highest_read <= 16384)) {
+ if ((search <= target && target - search <= 65536) ||
+ (search > target && search - target <= 65536)) {
readahead_tree_block(root, search, blocksize,
btrfs_node_ptr_generation(node, nr));
nread += blocksize;
}
nscan++;
- if (path->reada < 2 && (nread > (64 * 1024) || nscan > 32))
+ if ((nread > 65536 || nscan > 32))
break;
-
- if (nread > (256 * 1024) || nscan > 128)
- break;
-
- if (search < lowest_read)
- lowest_read = search;
- if (search > highest_read)
- highest_read = search;
}
}
/*
+ * returns -EAGAIN if it had to drop the path, or zero if everything was in
+ * cache
+ */
+static noinline int reada_for_balance(struct btrfs_root *root,
+ struct btrfs_path *path, int level)
+{
+ int slot;
+ int nritems;
+ struct extent_buffer *parent;
+ struct extent_buffer *eb;
+ u64 gen;
+ u64 block1 = 0;
+ u64 block2 = 0;
+ int ret = 0;
+ int blocksize;
+
+ parent = path->nodes[level - 1];
+ if (!parent)
+ return 0;
+
+ nritems = btrfs_header_nritems(parent);
+ slot = path->slots[level];
+ blocksize = btrfs_level_size(root, level);
+
+ if (slot > 0) {
+ block1 = btrfs_node_blockptr(parent, slot - 1);
+ gen = btrfs_node_ptr_generation(parent, slot - 1);
+ eb = btrfs_find_tree_block(root, block1, blocksize);
+ if (eb && btrfs_buffer_uptodate(eb, gen))
+ block1 = 0;
+ free_extent_buffer(eb);
+ }
+ if (slot < nritems) {
+ block2 = btrfs_node_blockptr(parent, slot + 1);
+ gen = btrfs_node_ptr_generation(parent, slot + 1);
+ eb = btrfs_find_tree_block(root, block2, blocksize);
+ if (eb && btrfs_buffer_uptodate(eb, gen))
+ block2 = 0;
+ free_extent_buffer(eb);
+ }
+ if (block1 || block2) {
+ ret = -EAGAIN;
+ btrfs_release_path(root, path);
+ if (block1)
+ readahead_tree_block(root, block1, blocksize, 0);
+ if (block2)
+ readahead_tree_block(root, block2, blocksize, 0);
+
+ if (block1) {
+ eb = read_tree_block(root, block1, blocksize, 0);
+ free_extent_buffer(eb);
+ }
+ if (block1) {
+ eb = read_tree_block(root, block2, blocksize, 0);
+ free_extent_buffer(eb);
+ }
+ }
+ return ret;
+}
+
+
+/*
* when we walk down the tree, it is usually safe to unlock the higher layers
* in the tree. The exceptions are when our path goes through slot 0, because
* operations on the tree might require changing key pointers higher up in the
@@ -1328,6 +1422,32 @@
}
/*
+ * This releases any locks held in the path starting at level and
+ * going all the way up to the root.
+ *
+ * btrfs_search_slot will keep the lock held on higher nodes in a few
+ * corner cases, such as COW of the block at slot zero in the node. This
+ * ignores those rules, and it should only be called when there are no
+ * more updates to be done higher up in the tree.
+ */
+noinline void btrfs_unlock_up_safe(struct btrfs_path *path, int level)
+{
+ int i;
+
+ if (path->keep_locks || path->lowest_level)
+ return;
+
+ for (i = level; i < BTRFS_MAX_LEVEL; i++) {
+ if (!path->nodes[i])
+ continue;
+ if (!path->locks[i])
+ continue;
+ btrfs_tree_unlock(path->nodes[i]);
+ path->locks[i] = 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
* level of the path (level 0)
@@ -1387,31 +1507,30 @@
int wret;
/* is a cow on this block not required */
- spin_lock(&root->fs_info->hash_lock);
if (btrfs_header_generation(b) == trans->transid &&
btrfs_header_owner(b) == root->root_key.objectid &&
!btrfs_header_flag(b, BTRFS_HEADER_FLAG_WRITTEN)) {
- spin_unlock(&root->fs_info->hash_lock);
goto cow_done;
}
- spin_unlock(&root->fs_info->hash_lock);
/* ok, we have to cow, is our old prealloc the right
* size?
*/
if (prealloc_block.objectid &&
prealloc_block.offset != b->len) {
+ btrfs_release_path(root, p);
btrfs_free_reserved_extent(root,
prealloc_block.objectid,
prealloc_block.offset);
prealloc_block.objectid = 0;
+ goto again;
}
/*
* for higher level blocks, try not to allocate blocks
* with the block and the parent locks held.
*/
- if (level > 1 && !prealloc_block.objectid &&
+ if (level > 0 && !prealloc_block.objectid &&
btrfs_path_lock_waiting(p, level)) {
u32 size = b->len;
u64 hint = b->start;
@@ -1425,6 +1544,8 @@
goto again;
}
+ btrfs_set_path_blocking(p);
+
wret = btrfs_cow_block(trans, root, b,
p->nodes[level + 1],
p->slots[level + 1],
@@ -1446,6 +1567,22 @@
if (!p->skip_locking)
p->locks[level] = 1;
+ btrfs_clear_path_blocking(p);
+
+ /*
+ * we have a lock on b and as long as we aren't changing
+ * the tree, there is no way to for the items in b to change.
+ * It is safe to drop the lock on our parent before we
+ * go through the expensive btree search on b.
+ *
+ * If cow is true, then we might be changing slot zero,
+ * which may require changing the parent. So, we can't
+ * drop the lock until after we know which slot we're
+ * operating on.
+ */
+ if (!cow)
+ btrfs_unlock_up_safe(p, level + 1);
+
ret = check_block(root, p, level);
if (ret) {
ret = -1;
@@ -1453,6 +1590,7 @@
}
ret = bin_search(b, key, level, &slot);
+
if (level != 0) {
if (ret && slot > 0)
slot -= 1;
@@ -1460,7 +1598,16 @@
if ((p->search_for_split || ins_len > 0) &&
btrfs_header_nritems(b) >=
BTRFS_NODEPTRS_PER_BLOCK(root) - 3) {
- int sret = split_node(trans, root, p, level);
+ int sret;
+
+ sret = reada_for_balance(root, p, level);
+ if (sret)
+ goto again;
+
+ btrfs_set_path_blocking(p);
+ sret = split_node(trans, root, p, level);
+ btrfs_clear_path_blocking(p);
+
BUG_ON(sret > 0);
if (sret) {
ret = sret;
@@ -1468,9 +1615,19 @@
}
b = p->nodes[level];
slot = p->slots[level];
- } else if (ins_len < 0) {
- int sret = balance_level(trans, root, p,
- level);
+ } else if (ins_len < 0 &&
+ btrfs_header_nritems(b) <
+ BTRFS_NODEPTRS_PER_BLOCK(root) / 4) {
+ int sret;
+
+ sret = reada_for_balance(root, p, level);
+ if (sret)
+ goto again;
+
+ btrfs_set_path_blocking(p);
+ sret = balance_level(trans, root, p, level);
+ btrfs_clear_path_blocking(p);
+
if (sret) {
ret = sret;
goto done;
@@ -1504,7 +1661,7 @@
* of the btree by dropping locks before
* we read.
*/
- if (level > 1) {
+ if (level > 0) {
btrfs_release_path(NULL, p);
if (tmp)
free_extent_buffer(tmp);
@@ -1519,6 +1676,7 @@
free_extent_buffer(tmp);
goto again;
} else {
+ btrfs_set_path_blocking(p);
if (tmp)
free_extent_buffer(tmp);
if (should_reada)
@@ -1528,14 +1686,29 @@
b = read_node_slot(root, b, slot);
}
}
- if (!p->skip_locking)
- btrfs_tree_lock(b);
+ if (!p->skip_locking) {
+ int lret;
+
+ btrfs_clear_path_blocking(p);
+ lret = btrfs_try_spin_lock(b);
+
+ if (!lret) {
+ btrfs_set_path_blocking(p);
+ btrfs_tree_lock(b);
+ btrfs_clear_path_blocking(p);
+ }
+ }
} else {
p->slots[level] = slot;
if (ins_len > 0 &&
btrfs_leaf_free_space(root, b) < ins_len) {
- int sret = split_leaf(trans, root, key,
+ int sret;
+
+ btrfs_set_path_blocking(p);
+ sret = split_leaf(trans, root, key,
p, ins_len, ret == 0);
+ btrfs_clear_path_blocking(p);
+
BUG_ON(sret > 0);
if (sret) {
ret = sret;
@@ -1549,12 +1722,16 @@
}
ret = 1;
done:
+ /*
+ * we don't really know what they plan on doing with the path
+ * from here on, so for now just mark it as blocking
+ */
+ btrfs_set_path_blocking(p);
if (prealloc_block.objectid) {
btrfs_free_reserved_extent(root,
prealloc_block.objectid,
prealloc_block.offset);
}
-
return ret;
}
@@ -1578,6 +1755,8 @@
ret = btrfs_cow_block(trans, root, eb, NULL, 0, &eb, 0);
BUG_ON(ret);
+ btrfs_set_lock_blocking(eb);
+
parent = eb;
while (1) {
level = btrfs_header_level(parent);
@@ -1602,6 +1781,7 @@
eb = read_tree_block(root, bytenr, blocksize,
generation);
btrfs_tree_lock(eb);
+ btrfs_set_lock_blocking(eb);
}
/*
@@ -1626,6 +1806,7 @@
eb = read_tree_block(root, bytenr, blocksize,
generation);
btrfs_tree_lock(eb);
+ btrfs_set_lock_blocking(eb);
}
ret = btrfs_cow_block(trans, root, eb, parent, slot,
@@ -2172,6 +2353,8 @@
right = read_node_slot(root, upper, slot + 1);
btrfs_tree_lock(right);
+ btrfs_set_lock_blocking(right);
+
free_space = btrfs_leaf_free_space(root, right);
if (free_space < data_size)
goto out_unlock;
@@ -2367,6 +2550,8 @@
left = read_node_slot(root, path->nodes[1], slot - 1);
btrfs_tree_lock(left);
+ btrfs_set_lock_blocking(left);
+
free_space = btrfs_leaf_free_space(root, left);
if (free_space < data_size) {
ret = 1;
@@ -2825,6 +3010,12 @@
path->keep_locks = 0;
BUG_ON(ret);
+ /*
+ * make sure any changes to the path from split_leaf leave it
+ * in a blocking state
+ */
+ btrfs_set_path_blocking(path);
+
leaf = path->nodes[0];
BUG_ON(btrfs_leaf_free_space(root, leaf) < sizeof(struct btrfs_item));
@@ -3354,6 +3545,7 @@
BUG();
}
out:
+ btrfs_unlock_up_safe(path, 1);
return ret;
}
@@ -3441,15 +3633,22 @@
{
int ret;
u64 root_gen = btrfs_header_generation(path->nodes[1]);
+ u64 parent_start = path->nodes[1]->start;
+ u64 parent_owner = btrfs_header_owner(path->nodes[1]);
ret = del_ptr(trans, root, path, 1, path->slots[1]);
if (ret)
return ret;
+ /*
+ * btrfs_free_extent is expensive, we want to make sure we
+ * aren't holding any locks when we call it
+ */
+ btrfs_unlock_up_safe(path, 0);
+
ret = btrfs_free_extent(trans, root, bytenr,
btrfs_level_size(root, 0),
- path->nodes[1]->start,
- btrfs_header_owner(path->nodes[1]),
+ parent_start, parent_owner,
root_gen, 0, 1);
return ret;
}
@@ -3721,12 +3920,14 @@
*/
if (slot >= nritems) {
path->slots[level] = slot;
+ btrfs_set_path_blocking(path);
sret = btrfs_find_next_key(root, path, min_key, level,
cache_only, min_trans);
if (sret == 0) {
btrfs_release_path(root, path);
goto again;
} else {
+ btrfs_clear_path_blocking(path);
goto out;
}
}
@@ -3738,16 +3939,20 @@
unlock_up(path, level, 1);
goto out;
}
+ btrfs_set_path_blocking(path);
cur = read_node_slot(root, cur, slot);
btrfs_tree_lock(cur);
+
path->locks[level - 1] = 1;
path->nodes[level - 1] = cur;
unlock_up(path, level, 1);
+ btrfs_clear_path_blocking(path);
}
out:
if (ret == 0)
memcpy(min_key, &found_key, sizeof(found_key));
+ btrfs_set_path_blocking(path);
return ret;
}
@@ -3843,6 +4048,7 @@
if (ret < 0)
return ret;
+ btrfs_set_path_blocking(path);
nritems = btrfs_header_nritems(path->nodes[0]);
/*
* by releasing the path above we dropped all our locks. A balance
@@ -3873,6 +4079,7 @@
free_extent_buffer(next);
}
+ /* the path was set to blocking above */
if (level == 1 && (path->locks[1] || path->skip_locking) &&
path->reada)
reada_for_search(root, path, level, slot, 0);
@@ -3881,6 +4088,7 @@
if (!path->skip_locking) {
WARN_ON(!btrfs_tree_locked(c));
btrfs_tree_lock(next);
+ btrfs_set_lock_blocking(next);
}
break;
}
@@ -3897,12 +4105,15 @@
path->locks[level] = 1;
if (!level)
break;
+
+ btrfs_set_path_blocking(path);
if (level == 1 && path->locks[1] && path->reada)
reada_for_search(root, path, level, slot, 0);
next = read_node_slot(root, next, 0);
if (!path->skip_locking) {
WARN_ON(!btrfs_tree_locked(path->nodes[level]));
btrfs_tree_lock(next);
+ btrfs_set_lock_blocking(next);
}
}
done:
@@ -3927,6 +4138,7 @@
while (1) {
if (path->slots[0] == 0) {
+ btrfs_set_path_blocking(path);
ret = btrfs_prev_leaf(root, path);
if (ret != 0)
return ret;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index eee060f..531db11 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -454,17 +454,11 @@
__le32 nsec;
} __attribute__ ((__packed__));
-typedef enum {
+enum btrfs_compression_type {
BTRFS_COMPRESS_NONE = 0,
BTRFS_COMPRESS_ZLIB = 1,
BTRFS_COMPRESS_LAST = 2,
-} btrfs_compression_type;
-
-/* we don't understand any encryption methods right now */
-typedef enum {
- BTRFS_ENCRYPTION_NONE = 0,
- BTRFS_ENCRYPTION_LAST = 1,
-} btrfs_encryption_type;
+};
struct btrfs_inode_item {
/* nfs style generation number */
@@ -701,9 +695,7 @@
struct btrfs_transaction *running_transaction;
wait_queue_head_t transaction_throttle;
wait_queue_head_t transaction_wait;
-
wait_queue_head_t async_submit_wait;
- wait_queue_head_t tree_log_wait;
struct btrfs_super_block super_copy;
struct btrfs_super_block super_for_commit;
@@ -711,7 +703,6 @@
struct super_block *sb;
struct inode *btree_inode;
struct backing_dev_info bdi;
- spinlock_t hash_lock;
struct mutex trans_mutex;
struct mutex tree_log_mutex;
struct mutex transaction_kthread_mutex;
@@ -730,10 +721,6 @@
atomic_t async_submit_draining;
atomic_t nr_async_bios;
atomic_t async_delalloc_pages;
- atomic_t tree_log_writers;
- atomic_t tree_log_commit;
- unsigned long tree_log_batch;
- u64 tree_log_transid;
/*
* this is used by the balancing code to wait for all the pending
@@ -833,7 +820,14 @@
struct kobject root_kobj;
struct completion kobj_unregister;
struct mutex objectid_mutex;
+
struct mutex log_mutex;
+ wait_queue_head_t log_writer_wait;
+ wait_queue_head_t log_commit_wait[2];
+ atomic_t log_writers;
+ atomic_t log_commit[2];
+ unsigned long log_transid;
+ unsigned long log_batch;
u64 objectid;
u64 last_trans;
@@ -1841,6 +1835,10 @@
struct btrfs_path *btrfs_alloc_path(void);
void btrfs_free_path(struct btrfs_path *p);
void btrfs_init_path(struct btrfs_path *p);
+void btrfs_set_path_blocking(struct btrfs_path *p);
+void btrfs_clear_path_blocking(struct btrfs_path *p);
+void btrfs_unlock_up_safe(struct btrfs_path *p, int level);
+
int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
struct btrfs_path *path, int slot, int nr);
int btrfs_del_leaf(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 81a3138..5aebddd 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -16,7 +16,6 @@
* Boston, MA 021110-1307, USA.
*/
-#include <linux/version.h>
#include <linux/fs.h>
#include <linux/blkdev.h>
#include <linux/scatterlist.h>
@@ -800,7 +799,7 @@
ret = btree_read_extent_buffer_pages(root, buf, 0, parent_transid);
if (ret == 0)
- buf->flags |= EXTENT_UPTODATE;
+ set_bit(EXTENT_BUFFER_UPTODATE, &buf->bflags);
else
WARN_ON(1);
return buf;
@@ -814,6 +813,10 @@
if (btrfs_header_generation(buf) ==
root->fs_info->running_transaction->transid) {
WARN_ON(!btrfs_tree_locked(buf));
+
+ /* ugh, clear_extent_buffer_dirty can be expensive */
+ btrfs_set_lock_blocking(buf);
+
clear_extent_buffer_dirty(&BTRFS_I(btree_inode)->io_tree,
buf);
}
@@ -850,6 +853,14 @@
spin_lock_init(&root->list_lock);
mutex_init(&root->objectid_mutex);
mutex_init(&root->log_mutex);
+ init_waitqueue_head(&root->log_writer_wait);
+ init_waitqueue_head(&root->log_commit_wait[0]);
+ init_waitqueue_head(&root->log_commit_wait[1]);
+ atomic_set(&root->log_commit[0], 0);
+ atomic_set(&root->log_commit[1], 0);
+ atomic_set(&root->log_writers, 0);
+ root->log_batch = 0;
+ root->log_transid = 0;
extent_io_tree_init(&root->dirty_log_pages,
fs_info->btree_inode->i_mapping, GFP_NOFS);
@@ -934,15 +945,16 @@
return 0;
}
-int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info)
+static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
+ struct btrfs_fs_info *fs_info)
{
struct btrfs_root *root;
struct btrfs_root *tree_root = fs_info->tree_root;
+ struct extent_buffer *leaf;
root = kzalloc(sizeof(*root), GFP_NOFS);
if (!root)
- return -ENOMEM;
+ return ERR_PTR(-ENOMEM);
__setup_root(tree_root->nodesize, tree_root->leafsize,
tree_root->sectorsize, tree_root->stripesize,
@@ -951,12 +963,23 @@
root->root_key.objectid = BTRFS_TREE_LOG_OBJECTID;
root->root_key.type = BTRFS_ROOT_ITEM_KEY;
root->root_key.offset = BTRFS_TREE_LOG_OBJECTID;
+ /*
+ * log trees do not get reference counted because they go away
+ * before a real commit is actually done. They do store pointers
+ * to file data extents, and those reference counts still get
+ * updated (along with back refs to the log tree).
+ */
root->ref_cows = 0;
- root->node = btrfs_alloc_free_block(trans, root, root->leafsize,
- 0, BTRFS_TREE_LOG_OBJECTID,
- trans->transid, 0, 0, 0);
+ leaf = btrfs_alloc_free_block(trans, root, root->leafsize,
+ 0, BTRFS_TREE_LOG_OBJECTID,
+ trans->transid, 0, 0, 0);
+ if (IS_ERR(leaf)) {
+ kfree(root);
+ return ERR_CAST(leaf);
+ }
+ root->node = leaf;
btrfs_set_header_nritems(root->node, 0);
btrfs_set_header_level(root->node, 0);
btrfs_set_header_bytenr(root->node, root->node->start);
@@ -968,7 +991,48 @@
BTRFS_FSID_SIZE);
btrfs_mark_buffer_dirty(root->node);
btrfs_tree_unlock(root->node);
- fs_info->log_root_tree = root;
+ return root;
+}
+
+int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans,
+ struct btrfs_fs_info *fs_info)
+{
+ struct btrfs_root *log_root;
+
+ log_root = alloc_log_tree(trans, fs_info);
+ if (IS_ERR(log_root))
+ return PTR_ERR(log_root);
+ WARN_ON(fs_info->log_root_tree);
+ fs_info->log_root_tree = log_root;
+ return 0;
+}
+
+int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root)
+{
+ struct btrfs_root *log_root;
+ struct btrfs_inode_item *inode_item;
+
+ log_root = alloc_log_tree(trans, root->fs_info);
+ if (IS_ERR(log_root))
+ return PTR_ERR(log_root);
+
+ log_root->last_trans = trans->transid;
+ 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_root_bytenr(&log_root->root_item, log_root->node->start);
+ btrfs_set_root_generation(&log_root->root_item, trans->transid);
+
+ WARN_ON(root->log_root);
+ root->log_root = log_root;
+ root->log_transid = 0;
return 0;
}
@@ -1136,7 +1200,6 @@
{
struct btrfs_fs_info *info = (struct btrfs_fs_info *)congested_data;
int ret = 0;
- struct list_head *cur;
struct btrfs_device *device;
struct backing_dev_info *bdi;
#if 0
@@ -1144,8 +1207,7 @@
btrfs_congested_async(info, 0))
return 1;
#endif
- list_for_each(cur, &info->fs_devices->devices) {
- device = list_entry(cur, struct btrfs_device, dev_list);
+ list_for_each_entry(device, &info->fs_devices->devices, dev_list) {
if (!device->bdev)
continue;
bdi = blk_get_backing_dev_info(device->bdev);
@@ -1163,13 +1225,11 @@
*/
static void __unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
{
- struct list_head *cur;
struct btrfs_device *device;
struct btrfs_fs_info *info;
info = (struct btrfs_fs_info *)bdi->unplug_io_data;
- list_for_each(cur, &info->fs_devices->devices) {
- device = list_entry(cur, struct btrfs_device, dev_list);
+ list_for_each_entry(device, &info->fs_devices->devices, dev_list) {
if (!device->bdev)
continue;
@@ -1447,7 +1507,6 @@
INIT_LIST_HEAD(&fs_info->dead_roots);
INIT_LIST_HEAD(&fs_info->hashers);
INIT_LIST_HEAD(&fs_info->delalloc_inodes);
- spin_lock_init(&fs_info->hash_lock);
spin_lock_init(&fs_info->delalloc_lock);
spin_lock_init(&fs_info->new_trans_lock);
spin_lock_init(&fs_info->ref_cache_lock);
@@ -1535,10 +1594,6 @@
init_waitqueue_head(&fs_info->transaction_throttle);
init_waitqueue_head(&fs_info->transaction_wait);
init_waitqueue_head(&fs_info->async_submit_wait);
- init_waitqueue_head(&fs_info->tree_log_wait);
- atomic_set(&fs_info->tree_log_commit, 0);
- atomic_set(&fs_info->tree_log_writers, 0);
- fs_info->tree_log_transid = 0;
__setup_root(4096, 4096, 4096, 4096, tree_root,
fs_info, BTRFS_ROOT_TREE_OBJECTID);
@@ -1627,6 +1682,8 @@
* low idle thresh
*/
fs_info->endio_workers.idle_thresh = 4;
+ fs_info->endio_meta_workers.idle_thresh = 4;
+
fs_info->endio_write_workers.idle_thresh = 64;
fs_info->endio_meta_write_workers.idle_thresh = 64;
@@ -1740,13 +1797,13 @@
fs_info->system_alloc_profile = fs_info->metadata_alloc_profile;
fs_info->cleaner_kthread = kthread_run(cleaner_kthread, tree_root,
"btrfs-cleaner");
- if (!fs_info->cleaner_kthread)
+ if (IS_ERR(fs_info->cleaner_kthread))
goto fail_csum_root;
fs_info->transaction_kthread = kthread_run(transaction_kthread,
tree_root,
"btrfs-transaction");
- if (!fs_info->transaction_kthread)
+ if (IS_ERR(fs_info->transaction_kthread))
goto fail_cleaner;
if (btrfs_super_log_root(disk_super) != 0) {
@@ -1828,13 +1885,14 @@
fail_iput:
invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
iput(fs_info->btree_inode);
-fail:
+
btrfs_close_devices(fs_info->fs_devices);
btrfs_mapping_tree_free(&fs_info->mapping_tree);
+ bdi_destroy(&fs_info->bdi);
+fail:
kfree(extent_root);
kfree(tree_root);
- bdi_destroy(&fs_info->bdi);
kfree(fs_info);
kfree(chunk_root);
kfree(dev_root);
@@ -1995,7 +2053,6 @@
int write_all_supers(struct btrfs_root *root, int max_mirrors)
{
- struct list_head *cur;
struct list_head *head = &root->fs_info->fs_devices->devices;
struct btrfs_device *dev;
struct btrfs_super_block *sb;
@@ -2011,8 +2068,7 @@
sb = &root->fs_info->super_for_commit;
dev_item = &sb->dev_item;
- list_for_each(cur, head) {
- dev = list_entry(cur, struct btrfs_device, dev_list);
+ list_for_each_entry(dev, head, dev_list) {
if (!dev->bdev) {
total_errors++;
continue;
@@ -2045,8 +2101,7 @@
}
total_errors = 0;
- list_for_each(cur, head) {
- dev = list_entry(cur, struct btrfs_device, dev_list);
+ list_for_each_entry(dev, head, dev_list) {
if (!dev->bdev)
continue;
if (!dev->in_fs_metadata || !dev->writeable)
@@ -2260,6 +2315,8 @@
u64 transid = btrfs_header_generation(buf);
struct inode *btree_inode = root->fs_info->btree_inode;
+ btrfs_set_lock_blocking(buf);
+
WARN_ON(!btrfs_tree_locked(buf));
if (transid != root->fs_info->generation) {
printk(KERN_CRIT "btrfs transid mismatch buffer %llu, "
@@ -2302,14 +2359,13 @@
int ret;
ret = btree_read_extent_buffer_pages(root, buf, 0, parent_transid);
if (ret == 0)
- buf->flags |= EXTENT_UPTODATE;
+ set_bit(EXTENT_BUFFER_UPTODATE, &buf->bflags);
return ret;
}
int btree_lock_page_hook(struct page *page)
{
struct inode *inode = page->mapping->host;
- struct btrfs_root *root = BTRFS_I(inode)->root;
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
struct extent_buffer *eb;
unsigned long len;
@@ -2324,9 +2380,7 @@
goto out;
btrfs_tree_lock(eb);
- spin_lock(&root->fs_info->hash_lock);
btrfs_set_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN);
- spin_unlock(&root->fs_info->hash_lock);
btrfs_tree_unlock(eb);
free_extent_buffer(eb);
out:
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index c0ff404..494a56e 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -98,5 +98,7 @@
struct btrfs_fs_info *fs_info);
int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info);
+int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root);
int btree_lock_page_hook(struct page *page);
#endif
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 293da65..7527523 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -19,7 +19,7 @@
#include <linux/pagemap.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
-#include <linux/version.h>
+#include <linux/sort.h>
#include "compat.h"
#include "hash.h"
#include "crc32c.h"
@@ -30,7 +30,6 @@
#include "volumes.h"
#include "locking.h"
#include "ref-cache.h"
-#include "compat.h"
#define PENDING_EXTENT_INSERT 0
#define PENDING_EXTENT_DELETE 1
@@ -326,10 +325,8 @@
u64 flags)
{
struct list_head *head = &info->space_info;
- struct list_head *cur;
struct btrfs_space_info *found;
- list_for_each(cur, head) {
- found = list_entry(cur, struct btrfs_space_info, list);
+ list_for_each_entry(found, head, list) {
if (found->flags == flags)
return found;
}
@@ -1525,15 +1522,55 @@
return ret;
}
-int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
- struct extent_buffer *orig_buf, struct extent_buffer *buf,
- u32 *nr_extents)
+/* when a block goes through cow, we update the reference counts of
+ * everything that block points to. The internal pointers of the block
+ * can be in just about any order, and it is likely to have clusters of
+ * things that are close together and clusters of things that are not.
+ *
+ * To help reduce the seeks that come with updating all of these reference
+ * counts, sort them by byte number before actual updates are done.
+ *
+ * struct refsort is used to match byte number to slot in the btree block.
+ * we sort based on the byte number and then use the slot to actually
+ * find the item.
+ *
+ * struct refsort is smaller than strcut btrfs_item and smaller than
+ * struct btrfs_key_ptr. Since we're currently limited to the page size
+ * for a btree block, there's no way for a kmalloc of refsorts for a
+ * single node to be bigger than a page.
+ */
+struct refsort {
+ u64 bytenr;
+ u32 slot;
+};
+
+/*
+ * for passing into sort()
+ */
+static int refsort_cmp(const void *a_void, const void *b_void)
+{
+ const struct refsort *a = a_void;
+ const struct refsort *b = b_void;
+
+ if (a->bytenr < b->bytenr)
+ return -1;
+ if (a->bytenr > b->bytenr)
+ return 1;
+ return 0;
+}
+
+
+noinline int btrfs_inc_ref(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct extent_buffer *orig_buf,
+ struct extent_buffer *buf, u32 *nr_extents)
{
u64 bytenr;
u64 ref_root;
u64 orig_root;
u64 ref_generation;
u64 orig_generation;
+ struct refsort *sorted;
u32 nritems;
u32 nr_file_extents = 0;
struct btrfs_key key;
@@ -1542,6 +1579,8 @@
int level;
int ret = 0;
int faili = 0;
+ int refi = 0;
+ int slot;
int (*process_func)(struct btrfs_trans_handle *, struct btrfs_root *,
u64, u64, u64, u64, u64, u64, u64, u64);
@@ -1553,6 +1592,9 @@
nritems = btrfs_header_nritems(buf);
level = btrfs_header_level(buf);
+ sorted = kmalloc(sizeof(struct refsort) * nritems, GFP_NOFS);
+ BUG_ON(!sorted);
+
if (root->ref_cows) {
process_func = __btrfs_inc_extent_ref;
} else {
@@ -1565,6 +1607,11 @@
process_func = __btrfs_update_extent_ref;
}
+ /*
+ * we make two passes through the items. In the first pass we
+ * only record the byte number and slot. Then we sort based on
+ * byte number and do the actual work based on the sorted results
+ */
for (i = 0; i < nritems; i++) {
cond_resched();
if (level == 0) {
@@ -1581,6 +1628,32 @@
continue;
nr_file_extents++;
+ sorted[refi].bytenr = bytenr;
+ sorted[refi].slot = i;
+ refi++;
+ } else {
+ bytenr = btrfs_node_blockptr(buf, i);
+ sorted[refi].bytenr = bytenr;
+ sorted[refi].slot = i;
+ refi++;
+ }
+ }
+ /*
+ * if refi == 0, we didn't actually put anything into the sorted
+ * array and we're done
+ */
+ if (refi == 0)
+ goto out;
+
+ sort(sorted, refi, sizeof(struct refsort), refsort_cmp, NULL);
+
+ for (i = 0; i < refi; i++) {
+ cond_resched();
+ slot = sorted[i].slot;
+ bytenr = sorted[i].bytenr;
+
+ if (level == 0) {
+ btrfs_item_key_to_cpu(buf, &key, slot);
ret = process_func(trans, root, bytenr,
orig_buf->start, buf->start,
@@ -1589,25 +1662,25 @@
key.objectid);
if (ret) {
- faili = i;
+ faili = slot;
WARN_ON(1);
goto fail;
}
} else {
- bytenr = btrfs_node_blockptr(buf, i);
ret = process_func(trans, root, bytenr,
orig_buf->start, buf->start,
orig_root, ref_root,
orig_generation, ref_generation,
level - 1);
if (ret) {
- faili = i;
+ faili = slot;
WARN_ON(1);
goto fail;
}
}
}
out:
+ kfree(sorted);
if (nr_extents) {
if (level == 0)
*nr_extents = nr_file_extents;
@@ -1616,6 +1689,7 @@
}
return 0;
fail:
+ kfree(sorted);
WARN_ON(1);
return ret;
}
@@ -2159,7 +2233,8 @@
ret = find_first_extent_bit(&info->extent_ins, search, &start,
&end, EXTENT_WRITEBACK);
if (ret) {
- if (skipped && all && !num_inserts) {
+ if (skipped && all && !num_inserts &&
+ list_empty(&update_list)) {
skipped = 0;
search = 0;
continue;
@@ -2547,6 +2622,7 @@
if (ret) {
if (all && skipped && !nr) {
search = 0;
+ skipped = 0;
continue;
}
mutex_unlock(&info->extent_ins_mutex);
@@ -2700,13 +2776,9 @@
/* if metadata always pin */
if (owner_objectid < BTRFS_FIRST_FREE_OBJECTID) {
if (root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID) {
- struct btrfs_block_group_cache *cache;
-
- /* btrfs_free_reserved_extent */
- cache = btrfs_lookup_block_group(root->fs_info, bytenr);
- BUG_ON(!cache);
- btrfs_add_free_space(cache, bytenr, num_bytes);
- put_block_group(cache);
+ mutex_lock(&root->fs_info->pinned_mutex);
+ btrfs_update_pinned_extents(root, bytenr, num_bytes, 1);
+ mutex_unlock(&root->fs_info->pinned_mutex);
update_reserved_extents(root, bytenr, num_bytes, 0);
return 0;
}
@@ -3014,7 +3086,6 @@
static void dump_space_info(struct btrfs_space_info *info, u64 bytes)
{
struct btrfs_block_group_cache *cache;
- struct list_head *l;
printk(KERN_INFO "space_info has %llu free, is %sfull\n",
(unsigned long long)(info->total_bytes - info->bytes_used -
@@ -3022,8 +3093,7 @@
(info->full) ? "" : "not ");
down_read(&info->groups_sem);
- list_for_each(l, &info->block_groups) {
- cache = list_entry(l, struct btrfs_block_group_cache, list);
+ list_for_each_entry(cache, &info->block_groups, list) {
spin_lock(&cache->lock);
printk(KERN_INFO "block group %llu has %llu bytes, %llu used "
"%llu pinned %llu reserved\n",
@@ -3342,7 +3412,10 @@
btrfs_set_header_generation(buf, trans->transid);
btrfs_tree_lock(buf);
clean_tree_block(trans, root, buf);
+
+ btrfs_set_lock_blocking(buf);
btrfs_set_buffer_uptodate(buf);
+
if (root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID) {
set_extent_dirty(&root->dirty_log_pages, buf->start,
buf->start + buf->len - 1, GFP_NOFS);
@@ -3351,6 +3424,7 @@
buf->start + buf->len - 1, GFP_NOFS);
}
trans->blocks_used++;
+ /* this returns a buffer locked for blocking */
return buf;
}
@@ -3388,36 +3462,73 @@
{
u64 leaf_owner;
u64 leaf_generation;
+ struct refsort *sorted;
struct btrfs_key key;
struct btrfs_file_extent_item *fi;
int i;
int nritems;
int ret;
+ int refi = 0;
+ int slot;
BUG_ON(!btrfs_is_leaf(leaf));
nritems = btrfs_header_nritems(leaf);
leaf_owner = btrfs_header_owner(leaf);
leaf_generation = btrfs_header_generation(leaf);
+ sorted = kmalloc(sizeof(*sorted) * nritems, GFP_NOFS);
+ /* we do this loop twice. The first time we build a list
+ * of the extents we have a reference on, then we sort the list
+ * by bytenr. The second time around we actually do the
+ * extent freeing.
+ */
for (i = 0; i < nritems; i++) {
u64 disk_bytenr;
cond_resched();
btrfs_item_key_to_cpu(leaf, &key, i);
+
+ /* only extents have references, skip everything else */
if (btrfs_key_type(&key) != BTRFS_EXTENT_DATA_KEY)
continue;
+
fi = btrfs_item_ptr(leaf, i, struct btrfs_file_extent_item);
+
+ /* inline extents live in the btree, they don't have refs */
if (btrfs_file_extent_type(leaf, fi) ==
BTRFS_FILE_EXTENT_INLINE)
continue;
- /*
- * FIXME make sure to insert a trans record that
- * repeats the snapshot del on crash
- */
+
disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, fi);
+
+ /* holes don't have refs */
if (disk_bytenr == 0)
continue;
+ sorted[refi].bytenr = disk_bytenr;
+ sorted[refi].slot = i;
+ refi++;
+ }
+
+ if (refi == 0)
+ goto out;
+
+ sort(sorted, refi, sizeof(struct refsort), refsort_cmp, NULL);
+
+ for (i = 0; i < refi; i++) {
+ u64 disk_bytenr;
+
+ disk_bytenr = sorted[i].bytenr;
+ slot = sorted[i].slot;
+
+ cond_resched();
+
+ btrfs_item_key_to_cpu(leaf, &key, slot);
+ if (btrfs_key_type(&key) != BTRFS_EXTENT_DATA_KEY)
+ continue;
+
+ fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
+
ret = __btrfs_free_extent(trans, root, disk_bytenr,
btrfs_file_extent_disk_num_bytes(leaf, fi),
leaf->start, leaf_owner, leaf_generation,
@@ -3428,6 +3539,8 @@
wake_up(&root->fs_info->transaction_throttle);
cond_resched();
}
+out:
+ kfree(sorted);
return 0;
}
@@ -3437,9 +3550,25 @@
{
int i;
int ret;
- struct btrfs_extent_info *info = ref->extents;
+ struct btrfs_extent_info *info;
+ struct refsort *sorted;
+ if (ref->nritems == 0)
+ return 0;
+
+ sorted = kmalloc(sizeof(*sorted) * ref->nritems, GFP_NOFS);
for (i = 0; i < ref->nritems; i++) {
+ sorted[i].bytenr = ref->extents[i].bytenr;
+ sorted[i].slot = i;
+ }
+ sort(sorted, ref->nritems, sizeof(struct refsort), refsort_cmp, NULL);
+
+ /*
+ * the items in the ref were sorted when the ref was inserted
+ * into the ref cache, so this is already in order
+ */
+ for (i = 0; i < ref->nritems; i++) {
+ info = ref->extents + sorted[i].slot;
ret = __btrfs_free_extent(trans, root, info->bytenr,
info->num_bytes, ref->bytenr,
ref->owner, ref->generation,
@@ -3453,6 +3582,7 @@
info++;
}
+ kfree(sorted);
return 0;
}
@@ -3497,6 +3627,152 @@
}
/*
+ * this is used while deleting old snapshots, and it drops the refs
+ * on a whole subtree starting from a level 1 node.
+ *
+ * The idea is to sort all the leaf pointers, and then drop the
+ * ref on all the leaves in order. Most of the time the leaves
+ * will have ref cache entries, so no leaf IOs will be required to
+ * find the extents they have references on.
+ *
+ * For each leaf, any references it has are also dropped in order
+ *
+ * This ends up dropping the references in something close to optimal
+ * order for reading and modifying the extent allocation tree.
+ */
+static noinline int drop_level_one_refs(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct btrfs_path *path)
+{
+ u64 bytenr;
+ u64 root_owner;
+ u64 root_gen;
+ struct extent_buffer *eb = path->nodes[1];
+ struct extent_buffer *leaf;
+ struct btrfs_leaf_ref *ref;
+ struct refsort *sorted = NULL;
+ int nritems = btrfs_header_nritems(eb);
+ int ret;
+ int i;
+ int refi = 0;
+ int slot = path->slots[1];
+ u32 blocksize = btrfs_level_size(root, 0);
+ u32 refs;
+
+ if (nritems == 0)
+ goto out;
+
+ root_owner = btrfs_header_owner(eb);
+ root_gen = btrfs_header_generation(eb);
+ sorted = kmalloc(sizeof(*sorted) * nritems, GFP_NOFS);
+
+ /*
+ * step one, sort all the leaf pointers so we don't scribble
+ * randomly into the extent allocation tree
+ */
+ for (i = slot; i < nritems; i++) {
+ sorted[refi].bytenr = btrfs_node_blockptr(eb, i);
+ sorted[refi].slot = i;
+ refi++;
+ }
+
+ /*
+ * nritems won't be zero, but if we're picking up drop_snapshot
+ * after a crash, slot might be > 0, so double check things
+ * just in case.
+ */
+ if (refi == 0)
+ goto out;
+
+ sort(sorted, refi, sizeof(struct refsort), refsort_cmp, NULL);
+
+ /*
+ * the first loop frees everything the leaves point to
+ */
+ for (i = 0; i < refi; i++) {
+ u64 ptr_gen;
+
+ bytenr = sorted[i].bytenr;
+
+ /*
+ * check the reference count on this leaf. If it is > 1
+ * we just decrement it below and don't update any
+ * of the refs the leaf points to.
+ */
+ ret = drop_snap_lookup_refcount(root, bytenr, blocksize, &refs);
+ BUG_ON(ret);
+ if (refs != 1)
+ continue;
+
+ ptr_gen = btrfs_node_ptr_generation(eb, sorted[i].slot);
+
+ /*
+ * the leaf only had one reference, which means the
+ * only thing pointing to this leaf is the snapshot
+ * we're deleting. It isn't possible for the reference
+ * count to increase again later
+ *
+ * The reference cache is checked for the leaf,
+ * and if found we'll be able to drop any refs held by
+ * the leaf without needing to read it in.
+ */
+ ref = btrfs_lookup_leaf_ref(root, bytenr);
+ if (ref && ref->generation != ptr_gen) {
+ btrfs_free_leaf_ref(root, ref);
+ ref = NULL;
+ }
+ if (ref) {
+ ret = cache_drop_leaf_ref(trans, root, ref);
+ BUG_ON(ret);
+ btrfs_remove_leaf_ref(root, ref);
+ btrfs_free_leaf_ref(root, ref);
+ } else {
+ /*
+ * the leaf wasn't in the reference cache, so
+ * we have to read it.
+ */
+ leaf = read_tree_block(root, bytenr, blocksize,
+ ptr_gen);
+ ret = btrfs_drop_leaf_ref(trans, root, leaf);
+ BUG_ON(ret);
+ free_extent_buffer(leaf);
+ }
+ atomic_inc(&root->fs_info->throttle_gen);
+ wake_up(&root->fs_info->transaction_throttle);
+ cond_resched();
+ }
+
+ /*
+ * run through the loop again to free the refs on the leaves.
+ * This is faster than doing it in the loop above because
+ * the leaves are likely to be clustered together. We end up
+ * working in nice chunks on the extent allocation tree.
+ */
+ for (i = 0; i < refi; i++) {
+ bytenr = sorted[i].bytenr;
+ ret = __btrfs_free_extent(trans, root, bytenr,
+ blocksize, eb->start,
+ root_owner, root_gen, 0, 1);
+ BUG_ON(ret);
+
+ atomic_inc(&root->fs_info->throttle_gen);
+ wake_up(&root->fs_info->transaction_throttle);
+ cond_resched();
+ }
+out:
+ kfree(sorted);
+
+ /*
+ * update the path to show we've processed the entire level 1
+ * node. This will get saved into the root's drop_snapshot_progress
+ * field so these drops are not repeated again if this transaction
+ * commits.
+ */
+ path->slots[1] = nritems;
+ return 0;
+}
+
+/*
* helper function for drop_snapshot, this walks down the tree dropping ref
* counts as it goes.
*/
@@ -3511,7 +3787,6 @@
struct extent_buffer *next;
struct extent_buffer *cur;
struct extent_buffer *parent;
- struct btrfs_leaf_ref *ref;
u32 blocksize;
int ret;
u32 refs;
@@ -3538,17 +3813,46 @@
if (path->slots[*level] >=
btrfs_header_nritems(cur))
break;
+
+ /* the new code goes down to level 1 and does all the
+ * leaves pointed to that node in bulk. So, this check
+ * for level 0 will always be false.
+ *
+ * But, the disk format allows the drop_snapshot_progress
+ * field in the root to leave things in a state where
+ * a leaf will need cleaning up here. If someone crashes
+ * with the old code and then boots with the new code,
+ * we might find a leaf here.
+ */
if (*level == 0) {
ret = btrfs_drop_leaf_ref(trans, root, cur);
BUG_ON(ret);
break;
}
+
+ /*
+ * once we get to level one, process the whole node
+ * at once, including everything below it.
+ */
+ if (*level == 1) {
+ ret = drop_level_one_refs(trans, root, path);
+ BUG_ON(ret);
+ break;
+ }
+
bytenr = btrfs_node_blockptr(cur, path->slots[*level]);
ptr_gen = btrfs_node_ptr_generation(cur, path->slots[*level]);
blocksize = btrfs_level_size(root, *level - 1);
ret = drop_snap_lookup_refcount(root, bytenr, blocksize, &refs);
BUG_ON(ret);
+
+ /*
+ * if there is more than one reference, we don't need
+ * to read that node to drop any references it has. We
+ * just drop the ref we hold on that node and move on to the
+ * next slot in this level.
+ */
if (refs != 1) {
parent = path->nodes[*level];
root_owner = btrfs_header_owner(parent);
@@ -3567,46 +3871,12 @@
continue;
}
- /*
- * at this point, we have a single ref, and since the
- * only place referencing this extent is a dead root
- * the reference count should never go higher.
- * So, we don't need to check it again
- */
- if (*level == 1) {
- ref = btrfs_lookup_leaf_ref(root, bytenr);
- if (ref && ref->generation != ptr_gen) {
- btrfs_free_leaf_ref(root, ref);
- ref = NULL;
- }
- if (ref) {
- ret = cache_drop_leaf_ref(trans, root, ref);
- BUG_ON(ret);
- btrfs_remove_leaf_ref(root, ref);
- btrfs_free_leaf_ref(root, ref);
- *level = 0;
- break;
- }
- }
- next = btrfs_find_tree_block(root, bytenr, blocksize);
- if (!next || !btrfs_buffer_uptodate(next, ptr_gen)) {
- free_extent_buffer(next);
- next = read_tree_block(root, bytenr, blocksize,
- ptr_gen);
- cond_resched();
-#if 0
- /*
- * this is a debugging check and can go away
- * the ref should never go all the way down to 1
- * at this point
- */
- ret = lookup_extent_ref(NULL, root, bytenr, blocksize,
- &refs);
- BUG_ON(ret);
- WARN_ON(refs != 1);
-#endif
- }
+ /*
+ * we need to keep freeing things in the next level down.
+ * read the block and loop around to process it
+ */
+ next = read_tree_block(root, bytenr, blocksize, ptr_gen);
WARN_ON(*level <= 0);
if (path->nodes[*level-1])
free_extent_buffer(path->nodes[*level-1]);
@@ -3631,11 +3901,16 @@
root_owner = btrfs_header_owner(parent);
root_gen = btrfs_header_generation(parent);
+ /*
+ * cleanup and free the reference on the last node
+ * we processed
+ */
ret = __btrfs_free_extent(trans, root, bytenr, blocksize,
parent->start, root_owner, root_gen,
*level, 1);
free_extent_buffer(path->nodes[*level]);
path->nodes[*level] = NULL;
+
*level += 1;
BUG_ON(ret);
@@ -3687,6 +3962,7 @@
next = read_tree_block(root, bytenr, blocksize, ptr_gen);
btrfs_tree_lock(next);
+ btrfs_set_lock_blocking(next);
ret = btrfs_lookup_extent_ref(trans, root, bytenr, blocksize,
&refs);
@@ -3754,6 +4030,13 @@
if (slot < btrfs_header_nritems(path->nodes[i]) - 1) {
struct extent_buffer *node;
struct btrfs_disk_key disk_key;
+
+ /*
+ * there is more work to do in this level.
+ * Update the drop_progress marker to reflect
+ * the work we've done so far, and then bump
+ * the slot number
+ */
node = path->nodes[i];
path->slots[i]++;
*level = i;
@@ -3765,6 +4048,11 @@
return 0;
} else {
struct extent_buffer *parent;
+
+ /*
+ * this whole node is done, free our reference
+ * on it and go up one level
+ */
if (path->nodes[*level] == root->node)
parent = path->nodes[*level];
else
@@ -4444,7 +4732,7 @@
u64 lock_end = 0;
u64 num_bytes;
u64 ext_offset;
- u64 first_pos;
+ u64 search_end = (u64)-1;
u32 nritems;
int nr_scaned = 0;
int extent_locked = 0;
@@ -4452,7 +4740,6 @@
int ret;
memcpy(&key, leaf_key, sizeof(key));
- first_pos = INT_LIMIT(loff_t) - extent_key->offset;
if (ref_path->owner_objectid != BTRFS_MULTIPLE_OBJECTIDS) {
if (key.objectid < ref_path->owner_objectid ||
(key.objectid == ref_path->owner_objectid &&
@@ -4501,7 +4788,7 @@
if ((key.objectid > ref_path->owner_objectid) ||
(key.objectid == ref_path->owner_objectid &&
key.type > BTRFS_EXTENT_DATA_KEY) ||
- (key.offset >= first_pos + extent_key->offset))
+ key.offset >= search_end)
break;
}
@@ -4534,8 +4821,10 @@
num_bytes = btrfs_file_extent_num_bytes(leaf, fi);
ext_offset = btrfs_file_extent_offset(leaf, fi);
- if (first_pos > key.offset - ext_offset)
- first_pos = key.offset - ext_offset;
+ if (search_end == (u64)-1) {
+ search_end = key.offset - ext_offset +
+ btrfs_file_extent_ram_bytes(leaf, fi);
+ }
if (!extent_locked) {
lock_start = key.offset;
@@ -4724,7 +5013,7 @@
}
skip:
if (ref_path->owner_objectid != BTRFS_MULTIPLE_OBJECTIDS &&
- key.offset >= first_pos + extent_key->offset)
+ key.offset >= search_end)
break;
cond_resched();
@@ -4778,6 +5067,7 @@
ref->bytenr = buf->start;
ref->owner = btrfs_header_owner(buf);
ref->generation = btrfs_header_generation(buf);
+
ret = btrfs_add_leaf_ref(root, ref, 0);
WARN_ON(ret);
btrfs_free_leaf_ref(root, ref);
@@ -5957,9 +6247,11 @@
path = btrfs_alloc_path();
BUG_ON(!path);
- btrfs_remove_free_space_cache(block_group);
+ spin_lock(&root->fs_info->block_group_cache_lock);
rb_erase(&block_group->cache_node,
&root->fs_info->block_group_cache_tree);
+ spin_unlock(&root->fs_info->block_group_cache_lock);
+ btrfs_remove_free_space_cache(block_group);
down_write(&block_group->space_info->groups_sem);
list_del(&block_group->list);
up_write(&block_group->space_info->groups_sem);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index e086d40..37d43b5 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -9,7 +9,6 @@
#include <linux/spinlock.h>
#include <linux/blkdev.h>
#include <linux/swap.h>
-#include <linux/version.h>
#include <linux/writeback.h>
#include <linux/pagevec.h>
#include "extent_io.h"
@@ -31,7 +30,7 @@
static LIST_HEAD(states);
#define LEAK_DEBUG 0
-#ifdef LEAK_DEBUG
+#if LEAK_DEBUG
static DEFINE_SPINLOCK(leak_lock);
#endif
@@ -120,7 +119,7 @@
static struct extent_state *alloc_extent_state(gfp_t mask)
{
struct extent_state *state;
-#ifdef LEAK_DEBUG
+#if LEAK_DEBUG
unsigned long flags;
#endif
@@ -130,7 +129,7 @@
state->state = 0;
state->private = 0;
state->tree = NULL;
-#ifdef LEAK_DEBUG
+#if LEAK_DEBUG
spin_lock_irqsave(&leak_lock, flags);
list_add(&state->leak_list, &states);
spin_unlock_irqrestore(&leak_lock, flags);
@@ -145,11 +144,11 @@
if (!state)
return;
if (atomic_dec_and_test(&state->refs)) {
-#ifdef LEAK_DEBUG
+#if LEAK_DEBUG
unsigned long flags;
#endif
WARN_ON(state->tree);
-#ifdef LEAK_DEBUG
+#if LEAK_DEBUG
spin_lock_irqsave(&leak_lock, flags);
list_del(&state->leak_list);
spin_unlock_irqrestore(&leak_lock, flags);
@@ -2378,11 +2377,6 @@
int scanned = 0;
int range_whole = 0;
- if (wbc->nonblocking && bdi_write_congested(bdi)) {
- wbc->encountered_congestion = 1;
- return 0;
- }
-
pagevec_init(&pvec, 0);
if (wbc->range_cyclic) {
index = mapping->writeback_index; /* Start from prev offset */
@@ -2855,6 +2849,98 @@
return sector;
}
+int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ __u64 start, __u64 len, get_extent_t *get_extent)
+{
+ int ret;
+ u64 off = start;
+ u64 max = start + len;
+ u32 flags = 0;
+ u64 disko = 0;
+ struct extent_map *em = NULL;
+ int end = 0;
+ u64 em_start = 0, em_len = 0;
+ unsigned long emflags;
+ ret = 0;
+
+ if (len == 0)
+ return -EINVAL;
+
+ lock_extent(&BTRFS_I(inode)->io_tree, start, start + len,
+ GFP_NOFS);
+ em = get_extent(inode, NULL, 0, off, max - off, 0);
+ if (!em)
+ goto out;
+ if (IS_ERR(em)) {
+ ret = PTR_ERR(em);
+ goto out;
+ }
+ while (!end) {
+ off = em->start + em->len;
+ if (off >= max)
+ end = 1;
+
+ em_start = em->start;
+ em_len = em->len;
+
+ disko = 0;
+ flags = 0;
+
+ switch (em->block_start) {
+ case EXTENT_MAP_LAST_BYTE:
+ end = 1;
+ flags |= FIEMAP_EXTENT_LAST;
+ break;
+ case EXTENT_MAP_HOLE:
+ flags |= FIEMAP_EXTENT_UNWRITTEN;
+ break;
+ case EXTENT_MAP_INLINE:
+ flags |= (FIEMAP_EXTENT_DATA_INLINE |
+ FIEMAP_EXTENT_NOT_ALIGNED);
+ break;
+ case EXTENT_MAP_DELALLOC:
+ flags |= (FIEMAP_EXTENT_DELALLOC |
+ FIEMAP_EXTENT_UNKNOWN);
+ break;
+ default:
+ disko = em->block_start;
+ break;
+ }
+ if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags))
+ flags |= FIEMAP_EXTENT_ENCODED;
+
+ emflags = em->flags;
+ free_extent_map(em);
+ em = NULL;
+
+ if (!end) {
+ em = get_extent(inode, NULL, 0, off, max - off, 0);
+ if (!em)
+ goto out;
+ if (IS_ERR(em)) {
+ ret = PTR_ERR(em);
+ goto out;
+ }
+ emflags = em->flags;
+ }
+ if (test_bit(EXTENT_FLAG_VACANCY, &emflags)) {
+ flags |= FIEMAP_EXTENT_LAST;
+ end = 1;
+ }
+
+ ret = fiemap_fill_next_extent(fieinfo, em_start, disko,
+ em_len, flags);
+ if (ret)
+ goto out_free;
+ }
+out_free:
+ free_extent_map(em);
+out:
+ unlock_extent(&BTRFS_I(inode)->io_tree, start, start + len,
+ GFP_NOFS);
+ return ret;
+}
+
static inline struct page *extent_buffer_page(struct extent_buffer *eb,
unsigned long i)
{
@@ -2892,15 +2978,17 @@
gfp_t mask)
{
struct extent_buffer *eb = NULL;
-#ifdef LEAK_DEBUG
+#if LEAK_DEBUG
unsigned long flags;
#endif
eb = kmem_cache_zalloc(extent_buffer_cache, mask);
eb->start = start;
eb->len = len;
- mutex_init(&eb->mutex);
-#ifdef LEAK_DEBUG
+ spin_lock_init(&eb->lock);
+ init_waitqueue_head(&eb->lock_wq);
+
+#if LEAK_DEBUG
spin_lock_irqsave(&leak_lock, flags);
list_add(&eb->leak_list, &buffers);
spin_unlock_irqrestore(&leak_lock, flags);
@@ -2912,7 +3000,7 @@
static void __free_extent_buffer(struct extent_buffer *eb)
{
-#ifdef LEAK_DEBUG
+#if LEAK_DEBUG
unsigned long flags;
spin_lock_irqsave(&leak_lock, flags);
list_del(&eb->leak_list);
@@ -2980,8 +3068,7 @@
unlock_page(p);
}
if (uptodate)
- eb->flags |= EXTENT_UPTODATE;
- eb->flags |= EXTENT_BUFFER_FILLED;
+ set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
spin_lock(&tree->buffer_lock);
exists = buffer_tree_insert(tree, start, &eb->rb_node);
@@ -3135,7 +3222,7 @@
unsigned long num_pages;
num_pages = num_extent_pages(eb->start, eb->len);
- eb->flags &= ~EXTENT_UPTODATE;
+ clear_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
clear_extent_uptodate(tree, eb->start, eb->start + eb->len - 1,
GFP_NOFS);
@@ -3206,7 +3293,7 @@
struct page *page;
int pg_uptodate = 1;
- if (eb->flags & EXTENT_UPTODATE)
+ if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))
return 1;
ret = test_range_bit(tree, eb->start, eb->start + eb->len - 1,
@@ -3242,7 +3329,7 @@
struct bio *bio = NULL;
unsigned long bio_flags = 0;
- if (eb->flags & EXTENT_UPTODATE)
+ if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))
return 0;
if (test_range_bit(tree, eb->start, eb->start + eb->len - 1,
@@ -3273,7 +3360,7 @@
}
if (all_uptodate) {
if (start_i == 0)
- eb->flags |= EXTENT_UPTODATE;
+ set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
goto unlock_exit;
}
@@ -3309,7 +3396,7 @@
}
if (!ret)
- eb->flags |= EXTENT_UPTODATE;
+ set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
return ret;
unlock_exit:
@@ -3406,7 +3493,6 @@
unmap_extent_buffer(eb, eb->map_token, km);
eb->map_token = NULL;
save = 1;
- WARN_ON(!mutex_is_locked(&eb->mutex));
}
err = map_private_extent_buffer(eb, start, min_len, token, map,
map_start, map_len, km);
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index c5b483a..1f9df88 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -22,6 +22,10 @@
/* flags for bio submission */
#define EXTENT_BIO_COMPRESSED 1
+/* these are bit numbers for test/set bit */
+#define EXTENT_BUFFER_UPTODATE 0
+#define EXTENT_BUFFER_BLOCKING 1
+
/*
* page->private values. Every page that is controlled by the extent
* map has page->private set to one.
@@ -95,11 +99,19 @@
unsigned long map_start;
unsigned long map_len;
struct page *first_page;
+ unsigned long bflags;
atomic_t refs;
- int flags;
struct list_head leak_list;
struct rb_node rb_node;
- struct mutex mutex;
+
+ /* the spinlock is used to protect most operations */
+ spinlock_t lock;
+
+ /*
+ * when we keep the lock held while blocking, waiters go onto
+ * the wq
+ */
+ wait_queue_head_t lock_wq;
};
struct extent_map_tree;
@@ -193,6 +205,8 @@
unsigned from, unsigned to);
sector_t extent_bmap(struct address_space *mapping, sector_t iblock,
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_range_dirty(struct extent_io_tree *tree, u64 start, u64 end);
int set_state_private(struct extent_io_tree *tree, u64 start, u64 private);
int get_state_private(struct extent_io_tree *tree, u64 start, u64 *private);
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 4a83e33..50da69d 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -3,7 +3,6 @@
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/spinlock.h>
-#include <linux/version.h>
#include <linux/hardirq.h>
#include "extent_map.h"
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 9026833..3e8023e 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -29,7 +29,6 @@
#include <linux/writeback.h>
#include <linux/statfs.h>
#include <linux/compat.h>
-#include <linux/version.h>
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
@@ -1215,10 +1214,10 @@
}
mutex_unlock(&root->fs_info->trans_mutex);
- root->fs_info->tree_log_batch++;
+ root->log_batch++;
filemap_fdatawrite(inode->i_mapping);
btrfs_wait_ordered_range(inode, 0, (u64)-1);
- root->fs_info->tree_log_batch++;
+ root->log_batch++;
/*
* ok we haven't committed the transaction yet, lets do a commit
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 8adfe05..8f07062 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -34,7 +34,6 @@
#include <linux/statfs.h>
#include <linux/compat.h>
#include <linux/bit_spinlock.h>
-#include <linux/version.h>
#include <linux/xattr.h>
#include <linux/posix_acl.h>
#include <linux/falloc.h>
@@ -51,6 +50,7 @@
#include "tree-log.h"
#include "ref-cache.h"
#include "compression.h"
+#include "locking.h"
struct btrfs_iget_args {
u64 ino;
@@ -91,6 +91,16 @@
u64 start, u64 end, int *page_started,
unsigned long *nr_written, int unlock);
+static int btrfs_init_inode_security(struct inode *inode, struct inode *dir)
+{
+ int err;
+
+ err = btrfs_init_acl(inode, dir);
+ if (!err)
+ err = btrfs_xattr_security_init(inode, dir);
+ return err;
+}
+
/*
* a very lame attempt at stopping writes when the FS is 85% full. There
* are countless ways this is incorrect, but it is better than nothing.
@@ -350,6 +360,19 @@
nr_pages = (end >> PAGE_CACHE_SHIFT) - (start >> PAGE_CACHE_SHIFT) + 1;
nr_pages = min(nr_pages, (128 * 1024UL) / PAGE_CACHE_SIZE);
+ /*
+ * we don't want to send crud past the end of i_size through
+ * compression, that's just a waste of CPU time. So, if the
+ * end of the file is before the start of our current
+ * requested range of bytes, we bail out to the uncompressed
+ * cleanup code that can deal with all of this.
+ *
+ * It isn't really the fastest way to fix things, but this is a
+ * very uncommon corner.
+ */
+ if (actual_end <= start)
+ goto cleanup_and_bail_uncompressed;
+
total_compressed = actual_end - start;
/* we want to make sure that amount of ram required to uncompress
@@ -494,6 +517,7 @@
goto again;
}
} else {
+cleanup_and_bail_uncompressed:
/*
* No compression, but we still need to write the pages in
* the file we've been given so far. redirty the locked
@@ -1324,12 +1348,11 @@
struct inode *inode, u64 file_offset,
struct list_head *list)
{
- struct list_head *cur;
struct btrfs_ordered_sum *sum;
btrfs_set_trans_block_group(trans, inode);
- list_for_each(cur, list) {
- sum = list_entry(cur, struct btrfs_ordered_sum, list);
+
+ list_for_each_entry(sum, list, list) {
btrfs_csum_file_blocks(trans,
BTRFS_I(inode)->root->fs_info->csum_root, sum);
}
@@ -2013,6 +2036,7 @@
BTRFS_I(inode)->flags = btrfs_inode_flags(leaf, inode_item);
alloc_group_block = btrfs_inode_block_group(leaf, inode_item);
+
BTRFS_I(inode)->block_group = btrfs_find_block_group(root, 0,
alloc_group_block, 0);
btrfs_free_path(path);
@@ -2039,6 +2063,7 @@
inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
break;
default:
+ inode->i_op = &btrfs_special_inode_operations;
init_special_inode(inode, inode->i_mode, rdev);
break;
}
@@ -2108,6 +2133,7 @@
goto failed;
}
+ btrfs_unlock_up_safe(path, 1);
leaf = path->nodes[0];
inode_item = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_inode_item);
@@ -2429,6 +2455,8 @@
ref->generation = leaf_gen;
ref->nritems = 0;
+ btrfs_sort_leaf_ref(ref);
+
ret = btrfs_add_leaf_ref(root, ref, 0);
WARN_ON(ret);
btrfs_free_leaf_ref(root, ref);
@@ -2476,7 +2504,7 @@
struct btrfs_path *path;
struct btrfs_key key;
struct btrfs_key found_key;
- u32 found_type;
+ u32 found_type = (u8)-1;
struct extent_buffer *leaf;
struct btrfs_file_extent_item *fi;
u64 extent_start = 0;
@@ -2663,6 +2691,8 @@
if (pending_del_nr)
goto del_pending;
btrfs_release_path(root, path);
+ if (found_type == BTRFS_INODE_ITEM_KEY)
+ break;
goto search_again;
}
@@ -2679,6 +2709,8 @@
BUG_ON(ret);
pending_del_nr = 0;
btrfs_release_path(root, path);
+ if (found_type == BTRFS_INODE_ITEM_KEY)
+ break;
goto search_again;
}
}
@@ -3265,7 +3297,7 @@
/* Reached end of directory/root. Bump pos past the last item. */
if (key_type == BTRFS_DIR_INDEX_KEY)
- filp->f_pos = INT_LIMIT(typeof(filp->f_pos));
+ filp->f_pos = INT_LIMIT(off_t);
else
filp->f_pos++;
nopos:
@@ -3458,7 +3490,14 @@
root->highest_inode = objectid;
inode->i_uid = current_fsuid();
- inode->i_gid = current_fsgid();
+
+ if (dir && (dir->i_mode & S_ISGID)) {
+ inode->i_gid = dir->i_gid;
+ if (S_ISDIR(mode))
+ mode |= S_ISGID;
+ } else
+ inode->i_gid = current_fsgid();
+
inode->i_mode = mode;
inode->i_ino = objectid;
inode_set_bytes(inode, 0);
@@ -3586,7 +3625,7 @@
if (IS_ERR(inode))
goto out_unlock;
- err = btrfs_init_acl(inode, dir);
+ err = btrfs_init_inode_security(inode, dir);
if (err) {
drop_inode = 1;
goto out_unlock;
@@ -3649,7 +3688,7 @@
if (IS_ERR(inode))
goto out_unlock;
- err = btrfs_init_acl(inode, dir);
+ err = btrfs_init_inode_security(inode, dir);
if (err) {
drop_inode = 1;
goto out_unlock;
@@ -3772,7 +3811,7 @@
drop_on_err = 1;
- err = btrfs_init_acl(inode, dir);
+ err = btrfs_init_inode_security(inode, dir);
if (err)
goto out_fail;
@@ -4158,9 +4197,10 @@
return -EINVAL;
}
-static sector_t btrfs_bmap(struct address_space *mapping, sector_t iblock)
+static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ __u64 start, __u64 len)
{
- return extent_bmap(mapping, iblock, btrfs_get_extent);
+ return extent_fiemap(inode, fieinfo, start, len, btrfs_get_extent);
}
int btrfs_readpage(struct file *file, struct page *page)
@@ -4733,7 +4773,7 @@
if (IS_ERR(inode))
goto out_unlock;
- err = btrfs_init_acl(inode, dir);
+ err = btrfs_init_inode_security(inode, dir);
if (err) {
drop_inode = 1;
goto out_unlock;
@@ -4987,13 +5027,24 @@
.clear_bit_hook = btrfs_clear_bit_hook,
};
+/*
+ * btrfs doesn't support the bmap operation because swapfiles
+ * use bmap to make a mapping of extents in the file. They assume
+ * these extents won't change over the life of the file and they
+ * use the bmap result to do IO directly to the drive.
+ *
+ * the btrfs bmap call would return logical addresses that aren't
+ * suitable for IO and they also will change frequently as COW
+ * operations happen. So, swapfile + btrfs == corruption.
+ *
+ * For now we're avoiding this by dropping bmap.
+ */
static struct address_space_operations btrfs_aops = {
.readpage = btrfs_readpage,
.writepage = btrfs_writepage,
.writepages = btrfs_writepages,
.readpages = btrfs_readpages,
.sync_page = block_sync_page,
- .bmap = btrfs_bmap,
.direct_IO = btrfs_direct_IO,
.invalidatepage = btrfs_invalidatepage,
.releasepage = btrfs_releasepage,
@@ -5017,6 +5068,7 @@
.removexattr = btrfs_removexattr,
.permission = btrfs_permission,
.fallocate = btrfs_fallocate,
+ .fiemap = btrfs_fiemap,
};
static struct inode_operations btrfs_special_inode_operations = {
.getattr = btrfs_getattr,
@@ -5032,4 +5084,8 @@
.follow_link = page_follow_link_light,
.put_link = page_put_link,
.permission = btrfs_permission,
+ .setxattr = btrfs_setxattr,
+ .getxattr = btrfs_getxattr,
+ .listxattr = btrfs_listxattr,
+ .removexattr = btrfs_removexattr,
};
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index c2aa33e..988fdc8 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -38,7 +38,6 @@
#include <linux/compat.h>
#include <linux/bit_spinlock.h>
#include <linux/security.h>
-#include <linux/version.h>
#include <linux/xattr.h>
#include <linux/vmalloc.h>
#include "compat.h"
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index 39bae77..68fd9cc 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -26,45 +26,215 @@
#include "locking.h"
/*
- * locks the per buffer mutex in an extent buffer. This uses adaptive locks
- * and the spin is not tuned very extensively. The spinning does make a big
- * difference in almost every workload, but spinning for the right amount of
- * time needs some help.
- *
- * In general, we want to spin as long as the lock holder is doing btree
- * searches, and we should give up if they are in more expensive code.
+ * btrfs_header_level() isn't free, so don't call it when lockdep isn't
+ * on
*/
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+static inline void spin_nested(struct extent_buffer *eb)
+{
+ spin_lock_nested(&eb->lock, BTRFS_MAX_LEVEL - btrfs_header_level(eb));
+}
+#else
+static inline void spin_nested(struct extent_buffer *eb)
+{
+ spin_lock(&eb->lock);
+}
+#endif
-int btrfs_tree_lock(struct extent_buffer *eb)
+/*
+ * Setting a lock to blocking will drop the spinlock and set the
+ * flag that forces other procs who want the lock to wait. After
+ * this you can safely schedule with the lock held.
+ */
+void btrfs_set_lock_blocking(struct extent_buffer *eb)
+{
+ if (!test_bit(EXTENT_BUFFER_BLOCKING, &eb->bflags)) {
+ set_bit(EXTENT_BUFFER_BLOCKING, &eb->bflags);
+ spin_unlock(&eb->lock);
+ }
+ /* exit with the spin lock released and the bit set */
+}
+
+/*
+ * clearing the blocking flag will take the spinlock again.
+ * After this you can't safely schedule
+ */
+void btrfs_clear_lock_blocking(struct extent_buffer *eb)
+{
+ if (test_bit(EXTENT_BUFFER_BLOCKING, &eb->bflags)) {
+ spin_nested(eb);
+ clear_bit(EXTENT_BUFFER_BLOCKING, &eb->bflags);
+ smp_mb__after_clear_bit();
+ }
+ /* exit with the spin lock held */
+}
+
+/*
+ * unfortunately, many of the places that currently set a lock to blocking
+ * don't end up blocking for every long, and often they don't block
+ * at all. For a dbench 50 run, if we don't spin one the blocking bit
+ * at all, the context switch rate can jump up to 400,000/sec or more.
+ *
+ * So, we're still stuck with this crummy spin on the blocking bit,
+ * at least until the most common causes of the short blocks
+ * can be dealt with.
+ */
+static int btrfs_spin_on_block(struct extent_buffer *eb)
{
int i;
-
- if (mutex_trylock(&eb->mutex))
- return 0;
for (i = 0; i < 512; i++) {
cpu_relax();
- if (mutex_trylock(&eb->mutex))
- return 0;
+ if (!test_bit(EXTENT_BUFFER_BLOCKING, &eb->bflags))
+ return 1;
+ if (need_resched())
+ break;
}
- cpu_relax();
- mutex_lock_nested(&eb->mutex, BTRFS_MAX_LEVEL - btrfs_header_level(eb));
return 0;
}
+/*
+ * This is somewhat different from trylock. It will take the
+ * spinlock but if it finds the lock is set to blocking, it will
+ * return without the lock held.
+ *
+ * returns 1 if it was able to take the lock and zero otherwise
+ *
+ * After this call, scheduling is not safe without first calling
+ * btrfs_set_lock_blocking()
+ */
+int btrfs_try_spin_lock(struct extent_buffer *eb)
+{
+ int i;
+
+ spin_nested(eb);
+ if (!test_bit(EXTENT_BUFFER_BLOCKING, &eb->bflags))
+ return 1;
+ spin_unlock(&eb->lock);
+
+ /* spin for a bit on the BLOCKING flag */
+ for (i = 0; i < 2; i++) {
+ if (!btrfs_spin_on_block(eb))
+ break;
+
+ spin_nested(eb);
+ if (!test_bit(EXTENT_BUFFER_BLOCKING, &eb->bflags))
+ return 1;
+ spin_unlock(&eb->lock);
+ }
+ return 0;
+}
+
+/*
+ * the autoremove wake function will return 0 if it tried to wake up
+ * a process that was already awake, which means that process won't
+ * count as an exclusive wakeup. The waitq code will continue waking
+ * procs until it finds one that was actually sleeping.
+ *
+ * For btrfs, this isn't quite what we want. We want a single proc
+ * to be notified that the lock is ready for taking. If that proc
+ * already happen to be awake, great, it will loop around and try for
+ * the lock.
+ *
+ * So, btrfs_wake_function always returns 1, even when the proc that we
+ * tried to wake up was already awake.
+ */
+static int btrfs_wake_function(wait_queue_t *wait, unsigned mode,
+ int sync, void *key)
+{
+ autoremove_wake_function(wait, mode, sync, key);
+ return 1;
+}
+
+/*
+ * returns with the extent buffer spinlocked.
+ *
+ * This will spin and/or wait as required to take the lock, and then
+ * return with the spinlock held.
+ *
+ * After this call, scheduling is not safe without first calling
+ * btrfs_set_lock_blocking()
+ */
+int btrfs_tree_lock(struct extent_buffer *eb)
+{
+ DEFINE_WAIT(wait);
+ wait.func = btrfs_wake_function;
+
+ while(1) {
+ spin_nested(eb);
+
+ /* nobody is blocking, exit with the spinlock held */
+ if (!test_bit(EXTENT_BUFFER_BLOCKING, &eb->bflags))
+ return 0;
+
+ /*
+ * we have the spinlock, but the real owner is blocking.
+ * wait for them
+ */
+ spin_unlock(&eb->lock);
+
+ /*
+ * spin for a bit, and if the blocking flag goes away,
+ * loop around
+ */
+ if (btrfs_spin_on_block(eb))
+ continue;
+
+ prepare_to_wait_exclusive(&eb->lock_wq, &wait,
+ TASK_UNINTERRUPTIBLE);
+
+ if (test_bit(EXTENT_BUFFER_BLOCKING, &eb->bflags))
+ schedule();
+
+ finish_wait(&eb->lock_wq, &wait);
+ }
+ return 0;
+}
+
+/*
+ * Very quick trylock, this does not spin or schedule. It returns
+ * 1 with the spinlock held if it was able to take the lock, or it
+ * returns zero if it was unable to take the lock.
+ *
+ * After this call, scheduling is not safe without first calling
+ * btrfs_set_lock_blocking()
+ */
int btrfs_try_tree_lock(struct extent_buffer *eb)
{
- return mutex_trylock(&eb->mutex);
+ if (spin_trylock(&eb->lock)) {
+ if (test_bit(EXTENT_BUFFER_BLOCKING, &eb->bflags)) {
+ /*
+ * we've got the spinlock, but the real owner is
+ * blocking. Drop the spinlock and return failure
+ */
+ spin_unlock(&eb->lock);
+ return 0;
+ }
+ return 1;
+ }
+ /* someone else has the spinlock giveup */
+ return 0;
}
int btrfs_tree_unlock(struct extent_buffer *eb)
{
- mutex_unlock(&eb->mutex);
+ /*
+ * if we were a blocking owner, we don't have the spinlock held
+ * just clear the bit and look for waiters
+ */
+ if (test_and_clear_bit(EXTENT_BUFFER_BLOCKING, &eb->bflags))
+ smp_mb__after_clear_bit();
+ else
+ spin_unlock(&eb->lock);
+
+ if (waitqueue_active(&eb->lock_wq))
+ wake_up(&eb->lock_wq);
return 0;
}
int btrfs_tree_locked(struct extent_buffer *eb)
{
- return mutex_is_locked(&eb->mutex);
+ return test_bit(EXTENT_BUFFER_BLOCKING, &eb->bflags) ||
+ spin_is_locked(&eb->lock);
}
/*
@@ -75,12 +245,14 @@
{
int i;
struct extent_buffer *eb;
+
for (i = level; i <= level + 1 && i < BTRFS_MAX_LEVEL; i++) {
eb = path->nodes[i];
if (!eb)
break;
smp_mb();
- if (!list_empty(&eb->mutex.wait_list))
+ if (spin_is_contended(&eb->lock) ||
+ waitqueue_active(&eb->lock_wq))
return 1;
}
return 0;
diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h
index bc1faef..d92e707 100644
--- a/fs/btrfs/locking.h
+++ b/fs/btrfs/locking.h
@@ -22,6 +22,12 @@
int btrfs_tree_lock(struct extent_buffer *eb);
int btrfs_tree_unlock(struct extent_buffer *eb);
int btrfs_tree_locked(struct extent_buffer *eb);
+
int btrfs_try_tree_lock(struct extent_buffer *eb);
+int btrfs_try_spin_lock(struct extent_buffer *eb);
+
int btrfs_path_lock_waiting(struct btrfs_path *path, int level);
+
+void btrfs_set_lock_blocking(struct extent_buffer *eb);
+void btrfs_clear_lock_blocking(struct extent_buffer *eb);
#endif
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index a209401..77c2411 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -613,7 +613,6 @@
struct btrfs_sector_sum *sector_sums;
struct btrfs_ordered_extent *ordered;
struct btrfs_ordered_inode_tree *tree = &BTRFS_I(inode)->ordered_tree;
- struct list_head *cur;
unsigned long num_sectors;
unsigned long i;
u32 sectorsize = BTRFS_I(inode)->root->sectorsize;
@@ -624,8 +623,7 @@
return 1;
mutex_lock(&tree->mutex);
- list_for_each_prev(cur, &ordered->list) {
- ordered_sum = list_entry(cur, struct btrfs_ordered_sum, list);
+ list_for_each_entry_reverse(ordered_sum, &ordered->list, list) {
if (disk_bytenr >= ordered_sum->bytenr) {
num_sectors = ordered_sum->len / sectorsize;
sector_sums = ordered_sum->sums;
diff --git a/fs/btrfs/ref-cache.c b/fs/btrfs/ref-cache.c
index 6f0acc4..d0cc62b 100644
--- a/fs/btrfs/ref-cache.c
+++ b/fs/btrfs/ref-cache.c
@@ -17,6 +17,7 @@
*/
#include <linux/sched.h>
+#include <linux/sort.h>
#include "ctree.h"
#include "ref-cache.h"
#include "transaction.h"
diff --git a/fs/btrfs/ref-cache.h b/fs/btrfs/ref-cache.h
index 16f3183..bc283ad 100644
--- a/fs/btrfs/ref-cache.h
+++ b/fs/btrfs/ref-cache.h
@@ -73,5 +73,4 @@
int btrfs_remove_leaf_refs(struct btrfs_root *root, u64 max_root_gen,
int shared);
int btrfs_remove_leaf_ref(struct btrfs_root *root, struct btrfs_leaf_ref *ref);
-
#endif
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index db9fb3b..f3fd7e2 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -37,7 +37,6 @@
#include <linux/ctype.h>
#include <linux/namei.h>
#include <linux/miscdevice.h>
-#include <linux/version.h>
#include <linux/magic.h>
#include "compat.h"
#include "ctree.h"
@@ -583,17 +582,18 @@
struct btrfs_ioctl_vol_args *vol;
struct btrfs_fs_devices *fs_devices;
int ret = -ENOTTY;
- int len;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
vol = kmalloc(sizeof(*vol), GFP_KERNEL);
+ if (!vol)
+ return -ENOMEM;
+
if (copy_from_user(vol, (void __user *)arg, sizeof(*vol))) {
ret = -EFAULT;
goto out;
}
- len = strnlen(vol->name, BTRFS_PATH_NAME_MAX);
switch (cmd) {
case BTRFS_IOC_SCAN_DEV:
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 8a08f94..919172de 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -852,11 +852,9 @@
{
struct btrfs_pending_snapshot *pending;
struct list_head *head = &trans->transaction->pending_snapshots;
- struct list_head *cur;
int ret;
- list_for_each(cur, head) {
- pending = list_entry(cur, struct btrfs_pending_snapshot, list);
+ list_for_each_entry(pending, head, list) {
ret = create_pending_snapshot(trans, fs_info, pending);
BUG_ON(ret);
}
diff --git a/fs/btrfs/tree-defrag.c b/fs/btrfs/tree-defrag.c
index 3e8358c..98d25fa 100644
--- a/fs/btrfs/tree-defrag.c
+++ b/fs/btrfs/tree-defrag.c
@@ -74,6 +74,7 @@
u32 nritems;
root_node = btrfs_lock_root_node(root);
+ btrfs_set_lock_blocking(root_node);
nritems = btrfs_header_nritems(root_node);
root->defrag_max.objectid = 0;
/* from above we know this is not a leaf */
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index d81cda2..2079429 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -78,104 +78,6 @@
*/
/*
- * btrfs_add_log_tree adds a new per-subvolume log tree into the
- * tree of log tree roots. This must be called with a tree log transaction
- * running (see start_log_trans).
- */
-static int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
- struct btrfs_root *root)
-{
- struct btrfs_key key;
- struct btrfs_root_item root_item;
- struct btrfs_inode_item *inode_item;
- struct extent_buffer *leaf;
- struct btrfs_root *new_root = root;
- int ret;
- u64 objectid = root->root_key.objectid;
-
- leaf = btrfs_alloc_free_block(trans, root, root->leafsize, 0,
- BTRFS_TREE_LOG_OBJECTID,
- trans->transid, 0, 0, 0);
- if (IS_ERR(leaf)) {
- ret = PTR_ERR(leaf);
- return ret;
- }
-
- btrfs_set_header_nritems(leaf, 0);
- btrfs_set_header_level(leaf, 0);
- btrfs_set_header_bytenr(leaf, leaf->start);
- btrfs_set_header_generation(leaf, trans->transid);
- btrfs_set_header_owner(leaf, BTRFS_TREE_LOG_OBJECTID);
-
- write_extent_buffer(leaf, root->fs_info->fsid,
- (unsigned long)btrfs_header_fsid(leaf),
- BTRFS_FSID_SIZE);
- btrfs_mark_buffer_dirty(leaf);
-
- inode_item = &root_item.inode;
- memset(inode_item, 0, sizeof(*inode_item));
- 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_root_bytenr(&root_item, leaf->start);
- btrfs_set_root_generation(&root_item, trans->transid);
- btrfs_set_root_level(&root_item, 0);
- btrfs_set_root_refs(&root_item, 0);
- btrfs_set_root_used(&root_item, 0);
-
- memset(&root_item.drop_progress, 0, sizeof(root_item.drop_progress));
- root_item.drop_level = 0;
-
- btrfs_tree_unlock(leaf);
- free_extent_buffer(leaf);
- leaf = NULL;
-
- btrfs_set_root_dirid(&root_item, 0);
-
- key.objectid = BTRFS_TREE_LOG_OBJECTID;
- key.offset = objectid;
- btrfs_set_key_type(&key, BTRFS_ROOT_ITEM_KEY);
- ret = btrfs_insert_root(trans, root->fs_info->log_root_tree, &key,
- &root_item);
- if (ret)
- goto fail;
-
- new_root = btrfs_read_fs_root_no_radix(root->fs_info->log_root_tree,
- &key);
- BUG_ON(!new_root);
-
- WARN_ON(root->log_root);
- root->log_root = new_root;
-
- /*
- * log trees do not get reference counted because they go away
- * before a real commit is actually done. They do store pointers
- * to file data extents, and those reference counts still get
- * updated (along with back refs to the log tree).
- */
- new_root->ref_cows = 0;
- new_root->last_trans = trans->transid;
-
- /*
- * we need to make sure the root block for this new tree
- * is marked as dirty in the dirty_log_pages tree. This
- * is how it gets flushed down to disk at tree log commit time.
- *
- * the tree logging mutex keeps others from coming in and changing
- * the new_root->node, so we can safely access it here
- */
- set_extent_dirty(&new_root->dirty_log_pages, new_root->node->start,
- new_root->node->start + new_root->node->len - 1,
- GFP_NOFS);
-
-fail:
- return ret;
-}
-
-/*
* start a sub transaction and setup the log tree
* this increments the log tree writer count to make the people
* syncing the tree wait for us to finish
@@ -184,6 +86,14 @@
struct btrfs_root *root)
{
int ret;
+
+ mutex_lock(&root->log_mutex);
+ if (root->log_root) {
+ root->log_batch++;
+ atomic_inc(&root->log_writers);
+ mutex_unlock(&root->log_mutex);
+ return 0;
+ }
mutex_lock(&root->fs_info->tree_log_mutex);
if (!root->fs_info->log_root_tree) {
ret = btrfs_init_log_root_tree(trans, root->fs_info);
@@ -193,9 +103,10 @@
ret = btrfs_add_log_tree(trans, root);
BUG_ON(ret);
}
- atomic_inc(&root->fs_info->tree_log_writers);
- root->fs_info->tree_log_batch++;
mutex_unlock(&root->fs_info->tree_log_mutex);
+ root->log_batch++;
+ atomic_inc(&root->log_writers);
+ mutex_unlock(&root->log_mutex);
return 0;
}
@@ -212,13 +123,12 @@
if (!root->log_root)
return -ENOENT;
- mutex_lock(&root->fs_info->tree_log_mutex);
+ mutex_lock(&root->log_mutex);
if (root->log_root) {
ret = 0;
- atomic_inc(&root->fs_info->tree_log_writers);
- root->fs_info->tree_log_batch++;
+ atomic_inc(&root->log_writers);
}
- mutex_unlock(&root->fs_info->tree_log_mutex);
+ mutex_unlock(&root->log_mutex);
return ret;
}
@@ -228,10 +138,11 @@
*/
static int end_log_trans(struct btrfs_root *root)
{
- atomic_dec(&root->fs_info->tree_log_writers);
- smp_mb();
- if (waitqueue_active(&root->fs_info->tree_log_wait))
- wake_up(&root->fs_info->tree_log_wait);
+ if (atomic_dec_and_test(&root->log_writers)) {
+ smp_mb();
+ if (waitqueue_active(&root->log_writer_wait))
+ wake_up(&root->log_writer_wait);
+ }
return 0;
}
@@ -1704,6 +1615,7 @@
btrfs_tree_lock(next);
clean_tree_block(trans, root, next);
+ btrfs_set_lock_blocking(next);
btrfs_wait_tree_block_writeback(next);
btrfs_tree_unlock(next);
@@ -1750,6 +1662,7 @@
next = path->nodes[*level];
btrfs_tree_lock(next);
clean_tree_block(trans, root, next);
+ btrfs_set_lock_blocking(next);
btrfs_wait_tree_block_writeback(next);
btrfs_tree_unlock(next);
@@ -1807,6 +1720,7 @@
btrfs_tree_lock(next);
clean_tree_block(trans, root, next);
+ btrfs_set_lock_blocking(next);
btrfs_wait_tree_block_writeback(next);
btrfs_tree_unlock(next);
@@ -1879,6 +1793,7 @@
btrfs_tree_lock(next);
clean_tree_block(trans, log, next);
+ btrfs_set_lock_blocking(next);
btrfs_wait_tree_block_writeback(next);
btrfs_tree_unlock(next);
@@ -1902,26 +1817,65 @@
}
}
btrfs_free_path(path);
- if (wc->free)
- free_extent_buffer(log->node);
return ret;
}
-static int wait_log_commit(struct btrfs_root *log)
+/*
+ * helper function to update the item for a given subvolumes log root
+ * in the tree of log roots
+ */
+static int update_log_root(struct btrfs_trans_handle *trans,
+ struct btrfs_root *log)
+{
+ int ret;
+
+ if (log->log_transid == 1) {
+ /* insert root item on the first sync */
+ ret = btrfs_insert_root(trans, log->fs_info->log_root_tree,
+ &log->root_key, &log->root_item);
+ } else {
+ ret = btrfs_update_root(trans, log->fs_info->log_root_tree,
+ &log->root_key, &log->root_item);
+ }
+ return ret;
+}
+
+static int wait_log_commit(struct btrfs_root *root, unsigned long transid)
{
DEFINE_WAIT(wait);
- u64 transid = log->fs_info->tree_log_transid;
+ int index = transid % 2;
+ /*
+ * we only allow two pending log transactions at a time,
+ * so we know that if ours is more than 2 older than the
+ * current transaction, we're done
+ */
do {
- prepare_to_wait(&log->fs_info->tree_log_wait, &wait,
- TASK_UNINTERRUPTIBLE);
- mutex_unlock(&log->fs_info->tree_log_mutex);
- if (atomic_read(&log->fs_info->tree_log_commit))
+ prepare_to_wait(&root->log_commit_wait[index],
+ &wait, TASK_UNINTERRUPTIBLE);
+ mutex_unlock(&root->log_mutex);
+ if (root->log_transid < transid + 2 &&
+ atomic_read(&root->log_commit[index]))
schedule();
- finish_wait(&log->fs_info->tree_log_wait, &wait);
- mutex_lock(&log->fs_info->tree_log_mutex);
- } while (transid == log->fs_info->tree_log_transid &&
- atomic_read(&log->fs_info->tree_log_commit));
+ finish_wait(&root->log_commit_wait[index], &wait);
+ mutex_lock(&root->log_mutex);
+ } while (root->log_transid < transid + 2 &&
+ atomic_read(&root->log_commit[index]));
+ return 0;
+}
+
+static int wait_for_writer(struct btrfs_root *root)
+{
+ DEFINE_WAIT(wait);
+ while (atomic_read(&root->log_writers)) {
+ prepare_to_wait(&root->log_writer_wait,
+ &wait, TASK_UNINTERRUPTIBLE);
+ mutex_unlock(&root->log_mutex);
+ if (atomic_read(&root->log_writers))
+ schedule();
+ mutex_lock(&root->log_mutex);
+ finish_wait(&root->log_writer_wait, &wait);
+ }
return 0;
}
@@ -1933,57 +1887,114 @@
int btrfs_sync_log(struct btrfs_trans_handle *trans,
struct btrfs_root *root)
{
+ int index1;
+ int index2;
int ret;
- unsigned long batch;
struct btrfs_root *log = root->log_root;
+ struct btrfs_root *log_root_tree = root->fs_info->log_root_tree;
- mutex_lock(&log->fs_info->tree_log_mutex);
- if (atomic_read(&log->fs_info->tree_log_commit)) {
- wait_log_commit(log);
- goto out;
+ mutex_lock(&root->log_mutex);
+ index1 = root->log_transid % 2;
+ if (atomic_read(&root->log_commit[index1])) {
+ wait_log_commit(root, root->log_transid);
+ mutex_unlock(&root->log_mutex);
+ return 0;
}
- atomic_set(&log->fs_info->tree_log_commit, 1);
+ atomic_set(&root->log_commit[index1], 1);
+
+ /* wait for previous tree log sync to complete */
+ if (atomic_read(&root->log_commit[(index1 + 1) % 2]))
+ wait_log_commit(root, root->log_transid - 1);
while (1) {
- batch = log->fs_info->tree_log_batch;
- mutex_unlock(&log->fs_info->tree_log_mutex);
+ unsigned long batch = root->log_batch;
+ mutex_unlock(&root->log_mutex);
schedule_timeout_uninterruptible(1);
- mutex_lock(&log->fs_info->tree_log_mutex);
-
- while (atomic_read(&log->fs_info->tree_log_writers)) {
- DEFINE_WAIT(wait);
- prepare_to_wait(&log->fs_info->tree_log_wait, &wait,
- TASK_UNINTERRUPTIBLE);
- mutex_unlock(&log->fs_info->tree_log_mutex);
- if (atomic_read(&log->fs_info->tree_log_writers))
- schedule();
- mutex_lock(&log->fs_info->tree_log_mutex);
- finish_wait(&log->fs_info->tree_log_wait, &wait);
- }
- if (batch == log->fs_info->tree_log_batch)
+ mutex_lock(&root->log_mutex);
+ wait_for_writer(root);
+ if (batch == root->log_batch)
break;
}
ret = btrfs_write_and_wait_marked_extents(log, &log->dirty_log_pages);
BUG_ON(ret);
- ret = btrfs_write_and_wait_marked_extents(root->fs_info->log_root_tree,
- &root->fs_info->log_root_tree->dirty_log_pages);
+
+ btrfs_set_root_bytenr(&log->root_item, log->node->start);
+ btrfs_set_root_generation(&log->root_item, trans->transid);
+ btrfs_set_root_level(&log->root_item, btrfs_header_level(log->node));
+
+ root->log_batch = 0;
+ root->log_transid++;
+ log->log_transid = root->log_transid;
+ smp_mb();
+ /*
+ * log tree has been flushed to disk, new modifications of
+ * the log will be written to new positions. so it's safe to
+ * allow log writers to go in.
+ */
+ mutex_unlock(&root->log_mutex);
+
+ mutex_lock(&log_root_tree->log_mutex);
+ log_root_tree->log_batch++;
+ atomic_inc(&log_root_tree->log_writers);
+ mutex_unlock(&log_root_tree->log_mutex);
+
+ ret = update_log_root(trans, log);
+ BUG_ON(ret);
+
+ mutex_lock(&log_root_tree->log_mutex);
+ if (atomic_dec_and_test(&log_root_tree->log_writers)) {
+ smp_mb();
+ if (waitqueue_active(&log_root_tree->log_writer_wait))
+ wake_up(&log_root_tree->log_writer_wait);
+ }
+
+ index2 = log_root_tree->log_transid % 2;
+ if (atomic_read(&log_root_tree->log_commit[index2])) {
+ wait_log_commit(log_root_tree, log_root_tree->log_transid);
+ mutex_unlock(&log_root_tree->log_mutex);
+ goto out;
+ }
+ atomic_set(&log_root_tree->log_commit[index2], 1);
+
+ if (atomic_read(&log_root_tree->log_commit[(index2 + 1) % 2]))
+ wait_log_commit(log_root_tree, log_root_tree->log_transid - 1);
+
+ wait_for_writer(log_root_tree);
+
+ ret = btrfs_write_and_wait_marked_extents(log_root_tree,
+ &log_root_tree->dirty_log_pages);
BUG_ON(ret);
btrfs_set_super_log_root(&root->fs_info->super_for_commit,
- log->fs_info->log_root_tree->node->start);
+ log_root_tree->node->start);
btrfs_set_super_log_root_level(&root->fs_info->super_for_commit,
- btrfs_header_level(log->fs_info->log_root_tree->node));
+ btrfs_header_level(log_root_tree->node));
- write_ctree_super(trans, log->fs_info->tree_root, 2);
- log->fs_info->tree_log_transid++;
- log->fs_info->tree_log_batch = 0;
- atomic_set(&log->fs_info->tree_log_commit, 0);
+ log_root_tree->log_batch = 0;
+ log_root_tree->log_transid++;
smp_mb();
- if (waitqueue_active(&log->fs_info->tree_log_wait))
- wake_up(&log->fs_info->tree_log_wait);
+
+ mutex_unlock(&log_root_tree->log_mutex);
+
+ /*
+ * nobody else is going to jump in and write the the ctree
+ * super here because the log_commit atomic below is protecting
+ * us. We must be called with a transaction handle pinning
+ * the running transaction open, so a full commit can't hop
+ * in and cause problems either.
+ */
+ write_ctree_super(trans, root->fs_info->tree_root, 2);
+
+ atomic_set(&log_root_tree->log_commit[index2], 0);
+ smp_mb();
+ if (waitqueue_active(&log_root_tree->log_commit_wait[index2]))
+ wake_up(&log_root_tree->log_commit_wait[index2]);
out:
- mutex_unlock(&log->fs_info->tree_log_mutex);
+ atomic_set(&root->log_commit[index1], 0);
+ smp_mb();
+ if (waitqueue_active(&root->log_commit_wait[index1]))
+ wake_up(&root->log_commit_wait[index1]);
return 0;
}
@@ -2019,38 +2030,18 @@
start, end, GFP_NOFS);
}
- log = root->log_root;
- ret = btrfs_del_root(trans, root->fs_info->log_root_tree,
- &log->root_key);
- BUG_ON(ret);
+ if (log->log_transid > 0) {
+ ret = btrfs_del_root(trans, root->fs_info->log_root_tree,
+ &log->root_key);
+ BUG_ON(ret);
+ }
root->log_root = NULL;
- kfree(root->log_root);
+ free_extent_buffer(log->node);
+ kfree(log);
return 0;
}
/*
- * helper function to update the item for a given subvolumes log root
- * in the tree of log roots
- */
-static int update_log_root(struct btrfs_trans_handle *trans,
- struct btrfs_root *log)
-{
- u64 bytenr = btrfs_root_bytenr(&log->root_item);
- int ret;
-
- if (log->node->start == bytenr)
- return 0;
-
- btrfs_set_root_bytenr(&log->root_item, log->node->start);
- btrfs_set_root_generation(&log->root_item, trans->transid);
- btrfs_set_root_level(&log->root_item, btrfs_header_level(log->node));
- ret = btrfs_update_root(trans, log->fs_info->log_root_tree,
- &log->root_key, &log->root_item);
- BUG_ON(ret);
- return ret;
-}
-
-/*
* If both a file and directory are logged, and unlinks or renames are
* mixed in, we have a few interesting corners:
*
@@ -2711,11 +2702,6 @@
btrfs_free_path(path);
btrfs_free_path(dst_path);
-
- mutex_lock(&root->fs_info->tree_log_mutex);
- ret = update_log_root(trans, log);
- BUG_ON(ret);
- mutex_unlock(&root->fs_info->tree_log_mutex);
out:
return 0;
}
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 3451e1c..bcd14eb 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -20,7 +20,6 @@
#include <linux/buffer_head.h>
#include <linux/blkdev.h>
#include <linux/random.h>
-#include <linux/version.h>
#include <asm/div64.h>
#include "compat.h"
#include "ctree.h"
@@ -104,10 +103,8 @@
u64 devid, u8 *uuid)
{
struct btrfs_device *dev;
- struct list_head *cur;
- list_for_each(cur, head) {
- dev = list_entry(cur, struct btrfs_device, dev_list);
+ list_for_each_entry(dev, head, dev_list) {
if (dev->devid == devid &&
(!uuid || !memcmp(dev->uuid, uuid, BTRFS_UUID_SIZE))) {
return dev;
@@ -118,11 +115,9 @@
static noinline struct btrfs_fs_devices *find_fsid(u8 *fsid)
{
- struct list_head *cur;
struct btrfs_fs_devices *fs_devices;
- list_for_each(cur, &fs_uuids) {
- fs_devices = list_entry(cur, struct btrfs_fs_devices, list);
+ list_for_each_entry(fs_devices, &fs_uuids, list) {
if (memcmp(fsid, fs_devices->fsid, BTRFS_FSID_SIZE) == 0)
return fs_devices;
}
@@ -159,6 +154,7 @@
loop:
spin_lock(&device->io_lock);
+loop_lock:
/* take all the bios off the list at once and process them
* later on (without the lock held). But, remember the
* tail and other pointers so the bios can be properly reinserted
@@ -208,7 +204,7 @@
* is now congested. Back off and let other work structs
* run instead
*/
- if (pending && bdi_write_congested(bdi) &&
+ if (pending && bdi_write_congested(bdi) && num_run > 16 &&
fs_info->fs_devices->open_devices > 1) {
struct bio *old_head;
@@ -220,7 +216,8 @@
tail->bi_next = old_head;
else
device->pending_bio_tail = tail;
- device->running_pending = 0;
+
+ device->running_pending = 1;
spin_unlock(&device->io_lock);
btrfs_requeue_work(&device->work);
@@ -229,6 +226,11 @@
}
if (again)
goto loop;
+
+ spin_lock(&device->io_lock);
+ if (device->pending_bios)
+ goto loop_lock;
+ spin_unlock(&device->io_lock);
done:
return 0;
}
@@ -345,14 +347,11 @@
int btrfs_close_extra_devices(struct btrfs_fs_devices *fs_devices)
{
- struct list_head *tmp;
- struct list_head *cur;
- struct btrfs_device *device;
+ struct btrfs_device *device, *next;
mutex_lock(&uuid_mutex);
again:
- list_for_each_safe(cur, tmp, &fs_devices->devices) {
- device = list_entry(cur, struct btrfs_device, dev_list);
+ list_for_each_entry_safe(device, next, &fs_devices->devices, dev_list) {
if (device->in_fs_metadata)
continue;
@@ -383,14 +382,12 @@
static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
{
- struct list_head *cur;
struct btrfs_device *device;
if (--fs_devices->opened > 0)
return 0;
- list_for_each(cur, &fs_devices->devices) {
- device = list_entry(cur, struct btrfs_device, dev_list);
+ list_for_each_entry(device, &fs_devices->devices, dev_list) {
if (device->bdev) {
close_bdev_exclusive(device->bdev, device->mode);
fs_devices->open_devices--;
@@ -439,7 +436,6 @@
{
struct block_device *bdev;
struct list_head *head = &fs_devices->devices;
- struct list_head *cur;
struct btrfs_device *device;
struct block_device *latest_bdev = NULL;
struct buffer_head *bh;
@@ -450,8 +446,7 @@
int seeding = 1;
int ret = 0;
- list_for_each(cur, head) {
- device = list_entry(cur, struct btrfs_device, dev_list);
+ list_for_each_entry(device, head, dev_list) {
if (device->bdev)
continue;
if (!device->name)
@@ -578,7 +573,7 @@
*(unsigned long long *)disk_super->fsid,
*(unsigned long long *)(disk_super->fsid + 8));
}
- printk(KERN_INFO "devid %llu transid %llu %s\n",
+ printk(KERN_CONT "devid %llu transid %llu %s\n",
(unsigned long long)devid, (unsigned long long)transid, path);
ret = device_list_add(path, disk_super, devid, fs_devices_ret);
@@ -1017,14 +1012,12 @@
}
if (strcmp(device_path, "missing") == 0) {
- struct list_head *cur;
struct list_head *devices;
struct btrfs_device *tmp;
device = NULL;
devices = &root->fs_info->fs_devices->devices;
- list_for_each(cur, devices) {
- tmp = list_entry(cur, struct btrfs_device, dev_list);
+ list_for_each_entry(tmp, devices, dev_list) {
if (tmp->in_fs_metadata && !tmp->bdev) {
device = tmp;
break;
@@ -1280,7 +1273,6 @@
struct btrfs_trans_handle *trans;
struct btrfs_device *device;
struct block_device *bdev;
- struct list_head *cur;
struct list_head *devices;
struct super_block *sb = root->fs_info->sb;
u64 total_bytes;
@@ -1304,8 +1296,7 @@
mutex_lock(&root->fs_info->volume_mutex);
devices = &root->fs_info->fs_devices->devices;
- list_for_each(cur, devices) {
- device = list_entry(cur, struct btrfs_device, dev_list);
+ list_for_each_entry(device, devices, dev_list) {
if (device->bdev == bdev) {
ret = -EEXIST;
goto error;
@@ -1704,7 +1695,6 @@
int btrfs_balance(struct btrfs_root *dev_root)
{
int ret;
- struct list_head *cur;
struct list_head *devices = &dev_root->fs_info->fs_devices->devices;
struct btrfs_device *device;
u64 old_size;
@@ -1723,8 +1713,7 @@
dev_root = dev_root->fs_info->dev_root;
/* step one make some room on all the devices */
- list_for_each(cur, devices) {
- device = list_entry(cur, struct btrfs_device, dev_list);
+ list_for_each_entry(device, devices, dev_list) {
old_size = device->total_bytes;
size_to_free = div_factor(old_size, 1);
size_to_free = min(size_to_free, (u64)1 * 1024 * 1024);
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index 7f332e2..a9d3bf4 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -21,6 +21,7 @@
#include <linux/slab.h>
#include <linux/rwsem.h>
#include <linux/xattr.h>
+#include <linux/security.h>
#include "ctree.h"
#include "btrfs_inode.h"
#include "transaction.h"
@@ -45,9 +46,12 @@
/* lookup the xattr by name */
di = btrfs_lookup_xattr(NULL, root, path, inode->i_ino, name,
strlen(name), 0);
- if (!di || IS_ERR(di)) {
+ if (!di) {
ret = -ENODATA;
goto out;
+ } else if (IS_ERR(di)) {
+ ret = PTR_ERR(di);
+ goto out;
}
leaf = path->nodes[0];
@@ -62,6 +66,14 @@
ret = -ERANGE;
goto out;
}
+
+ /*
+ * The way things are packed into the leaf is like this
+ * |struct btrfs_dir_item|name|data|
+ * where name is the xattr name, so security.foo, and data is the
+ * content of the xattr. data_ptr points to the location in memory
+ * where the data starts in the in memory leaf
+ */
data_ptr = (unsigned long)((char *)(di + 1) +
btrfs_dir_name_len(leaf, di));
read_extent_buffer(leaf, buffer, data_ptr,
@@ -86,7 +98,7 @@
if (!path)
return -ENOMEM;
- trans = btrfs_start_transaction(root, 1);
+ trans = btrfs_join_transaction(root, 1);
btrfs_set_trans_block_group(trans, inode);
/* first lets see if we already have this xattr */
@@ -176,7 +188,6 @@
ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
if (ret < 0)
goto err;
- ret = 0;
advance = 0;
while (1) {
leaf = path->nodes[0];
@@ -320,3 +331,34 @@
return -EOPNOTSUPP;
return __btrfs_setxattr(dentry->d_inode, name, NULL, 0, XATTR_REPLACE);
}
+
+int btrfs_xattr_security_init(struct inode *inode, struct inode *dir)
+{
+ int err;
+ size_t len;
+ void *value;
+ char *suffix;
+ char *name;
+
+ err = security_inode_init_security(inode, dir, &suffix, &value, &len);
+ if (err) {
+ if (err == -EOPNOTSUPP)
+ return 0;
+ return err;
+ }
+
+ name = kmalloc(XATTR_SECURITY_PREFIX_LEN + strlen(suffix) + 1,
+ GFP_NOFS);
+ if (!name) {
+ err = -ENOMEM;
+ } else {
+ strcpy(name, XATTR_SECURITY_PREFIX);
+ strcpy(name + XATTR_SECURITY_PREFIX_LEN, suffix);
+ err = __btrfs_setxattr(inode, name, value, len, 0);
+ kfree(name);
+ }
+
+ kfree(suffix);
+ kfree(value);
+ return err;
+}
diff --git a/fs/btrfs/xattr.h b/fs/btrfs/xattr.h
index 5b1d08f..c71e9c3 100644
--- a/fs/btrfs/xattr.h
+++ b/fs/btrfs/xattr.h
@@ -36,4 +36,6 @@
const void *value, size_t size, int flags);
extern int btrfs_removexattr(struct dentry *dentry, const char *name);
+extern int btrfs_xattr_security_init(struct inode *inode, struct inode *dir);
+
#endif /* __XATTR__ */
diff --git a/fs/buffer.c b/fs/buffer.c
index b58208f..665d446 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2688,7 +2688,7 @@
struct buffer_head *bh;
BUG_ON(fsdata != NULL && page_has_buffers(page));
- if (unlikely(copied < len) && !page_has_buffers(page))
+ if (unlikely(copied < len) && head)
attach_nobh_buffers(page, head);
if (page_has_buffers(page))
return generic_write_end(file, mapping, pos, len,
diff --git a/fs/compat.c b/fs/compat.c
index 65a070e..d0145ca 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -1407,7 +1407,7 @@
bprm->cred = prepare_exec_creds();
if (!bprm->cred)
goto out_unlock;
- check_unsafe_exec(bprm);
+ check_unsafe_exec(bprm, current->files);
file = open_exec(filename);
retval = PTR_ERR(file);
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index c8f8d59..9c6d815 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -785,7 +785,7 @@
if (copy_in_user(&sgio->status, &sgio32->status,
(4 * sizeof(unsigned char)) +
- (2 * sizeof(unsigned (short))) +
+ (2 * sizeof(unsigned short)) +
(3 * sizeof(int))))
return -EFAULT;
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index c01e043..f6caeb1 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -1716,7 +1716,7 @@
{
int rc = 0;
- (*copied_name) = kmalloc((name_size + 2), GFP_KERNEL);
+ (*copied_name) = kmalloc((name_size + 1), GFP_KERNEL);
if (!(*copied_name)) {
rc = -ENOMEM;
goto out;
@@ -1726,7 +1726,7 @@
* in printing out the
* string in debug
* messages */
- (*copied_name_size) = (name_size + 1);
+ (*copied_name_size) = name_size;
out:
return rc;
}
diff --git a/fs/exec.c b/fs/exec.c
index 0dd60a0..929b580 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1049,16 +1049,32 @@
* - the caller must hold current->cred_exec_mutex to protect against
* PTRACE_ATTACH
*/
-void check_unsafe_exec(struct linux_binprm *bprm)
+void check_unsafe_exec(struct linux_binprm *bprm, struct files_struct *files)
{
- struct task_struct *p = current;
+ struct task_struct *p = current, *t;
+ unsigned long flags;
+ unsigned n_fs, n_files, n_sighand;
bprm->unsafe = tracehook_unsafe_exec(p);
- if (atomic_read(&p->fs->count) > 1 ||
- atomic_read(&p->files->count) > 1 ||
- atomic_read(&p->sighand->count) > 1)
+ n_fs = 1;
+ n_files = 1;
+ n_sighand = 1;
+ lock_task_sighand(p, &flags);
+ for (t = next_thread(p); t != p; t = next_thread(t)) {
+ if (t->fs == p->fs)
+ n_fs++;
+ if (t->files == files)
+ n_files++;
+ n_sighand++;
+ }
+
+ if (atomic_read(&p->fs->count) > n_fs ||
+ atomic_read(&p->files->count) > n_files ||
+ atomic_read(&p->sighand->count) > n_sighand)
bprm->unsafe |= LSM_UNSAFE_SHARE;
+
+ unlock_task_sighand(p, &flags);
}
/*
@@ -1273,7 +1289,7 @@
bprm->cred = prepare_exec_creds();
if (!bprm->cred)
goto out_unlock;
- check_unsafe_exec(bprm);
+ check_unsafe_exec(bprm, displaced);
file = open_exec(filename);
retval = PTR_ERR(file);
diff --git a/fs/internal.h b/fs/internal.h
index 53af885..0d8ac49 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -43,7 +43,7 @@
/*
* exec.c
*/
-extern void check_unsafe_exec(struct linux_binprm *);
+extern void check_unsafe_exec(struct linux_binprm *, struct files_struct *);
/*
* namespace.c
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index d861096c..60fe74035 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -5390,6 +5390,9 @@
goto out;
}
+ vfs_dq_free_space_nodirty(inode,
+ ocfs2_clusters_to_bytes(inode->i_sb, len));
+
ret = ocfs2_remove_extent(inode, et, cpos, len, handle, meta_ac,
dealloc);
if (ret) {
diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c
index b1cc7c3..e9d7c20 100644
--- a/fs/ocfs2/dcache.c
+++ b/fs/ocfs2/dcache.c
@@ -38,6 +38,7 @@
#include "dlmglue.h"
#include "file.h"
#include "inode.h"
+#include "super.h"
static int ocfs2_dentry_revalidate(struct dentry *dentry,
@@ -294,6 +295,34 @@
return ret;
}
+static DEFINE_SPINLOCK(dentry_list_lock);
+
+/* We limit the number of dentry locks to drop in one go. We have
+ * this limit so that we don't starve other users of ocfs2_wq. */
+#define DL_INODE_DROP_COUNT 64
+
+/* Drop inode references from dentry locks */
+void ocfs2_drop_dl_inodes(struct work_struct *work)
+{
+ struct ocfs2_super *osb = container_of(work, struct ocfs2_super,
+ dentry_lock_work);
+ struct ocfs2_dentry_lock *dl;
+ int drop_count = DL_INODE_DROP_COUNT;
+
+ spin_lock(&dentry_list_lock);
+ while (osb->dentry_lock_list && drop_count--) {
+ dl = osb->dentry_lock_list;
+ osb->dentry_lock_list = dl->dl_next;
+ spin_unlock(&dentry_list_lock);
+ iput(dl->dl_inode);
+ kfree(dl);
+ spin_lock(&dentry_list_lock);
+ }
+ if (osb->dentry_lock_list)
+ queue_work(ocfs2_wq, &osb->dentry_lock_work);
+ spin_unlock(&dentry_list_lock);
+}
+
/*
* ocfs2_dentry_iput() and friends.
*
@@ -318,16 +347,23 @@
static void ocfs2_drop_dentry_lock(struct ocfs2_super *osb,
struct ocfs2_dentry_lock *dl)
{
- iput(dl->dl_inode);
ocfs2_simple_drop_lockres(osb, &dl->dl_lockres);
ocfs2_lock_res_free(&dl->dl_lockres);
- kfree(dl);
+
+ /* We leave dropping of inode reference to ocfs2_wq as that can
+ * possibly lead to inode deletion which gets tricky */
+ spin_lock(&dentry_list_lock);
+ if (!osb->dentry_lock_list)
+ queue_work(ocfs2_wq, &osb->dentry_lock_work);
+ dl->dl_next = osb->dentry_lock_list;
+ osb->dentry_lock_list = dl;
+ spin_unlock(&dentry_list_lock);
}
void ocfs2_dentry_lock_put(struct ocfs2_super *osb,
struct ocfs2_dentry_lock *dl)
{
- int unlock = 0;
+ int unlock;
BUG_ON(dl->dl_count == 0);
diff --git a/fs/ocfs2/dcache.h b/fs/ocfs2/dcache.h
index c091c34..d06e16c 100644
--- a/fs/ocfs2/dcache.h
+++ b/fs/ocfs2/dcache.h
@@ -29,8 +29,13 @@
extern struct dentry_operations ocfs2_dentry_ops;
struct ocfs2_dentry_lock {
+ /* Use count of dentry lock */
unsigned int dl_count;
- u64 dl_parent_blkno;
+ union {
+ /* Linked list of dentry locks to release */
+ struct ocfs2_dentry_lock *dl_next;
+ u64 dl_parent_blkno;
+ };
/*
* The ocfs2_dentry_lock keeps an inode reference until
@@ -47,6 +52,8 @@
void ocfs2_dentry_lock_put(struct ocfs2_super *osb,
struct ocfs2_dentry_lock *dl);
+void ocfs2_drop_dl_inodes(struct work_struct *work);
+
struct dentry *ocfs2_find_local_alias(struct inode *inode, u64 parent_blkno,
int skip_unhashed);
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index b0c4cad..206a237 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -2860,6 +2860,10 @@
case OCFS2_UNLOCK_CANCEL_CONVERT:
mlog(0, "Cancel convert success for %s\n", lockres->l_name);
lockres->l_action = OCFS2_AST_INVALID;
+ /* Downconvert thread may have requeued this lock, we
+ * need to wake it. */
+ if (lockres->l_flags & OCFS2_LOCK_BLOCKED)
+ ocfs2_wake_downconvert_thread(ocfs2_get_lockres_osb(lockres));
break;
case OCFS2_UNLOCK_DROP_LOCK:
lockres->l_level = DLM_LOCK_IV;
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index ad5c24a..0773841 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -210,6 +210,7 @@
struct ocfs2_slot_info;
struct ocfs2_recovery_map;
struct ocfs2_quota_recovery;
+struct ocfs2_dentry_lock;
struct ocfs2_super
{
struct task_struct *commit_task;
@@ -325,6 +326,11 @@
struct list_head blocked_lock_list;
unsigned long blocked_lock_count;
+ /* List of dentry locks to release. Anyone can add locks to
+ * the list, ocfs2_wq processes the list */
+ struct ocfs2_dentry_lock *dentry_lock_list;
+ struct work_struct dentry_lock_work;
+
wait_queue_head_t osb_mount_event;
/* Truncate log info */
diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index f4efa89..1ed0f7c 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -754,7 +754,9 @@
if (dquot->dq_flags & mask)
sync = 1;
spin_unlock(&dq_data_lock);
- if (!sync) {
+ /* This is a slight hack but we can't afford getting global quota
+ * lock if we already have a transaction started. */
+ if (!sync || journal_current_handle()) {
status = ocfs2_write_dquot(dquot);
goto out;
}
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 43ed113..b1cb38f 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1887,6 +1887,9 @@
INIT_WORK(&journal->j_recovery_work, ocfs2_complete_recovery);
journal->j_state = OCFS2_JOURNAL_FREE;
+ INIT_WORK(&osb->dentry_lock_work, ocfs2_drop_dl_inodes);
+ osb->dentry_lock_list = NULL;
+
/* get some pseudo constants for clustersize bits */
osb->s_clustersize_bits =
le32_to_cpu(di->id2.i_super.s_clustersize_bits);
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index e1d638a..915039f 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -4729,13 +4729,6 @@
vb.vb_xv = (struct ocfs2_xattr_value_root *)
(vb.vb_bh->b_data + offset % blocksize);
- ret = ocfs2_xattr_bucket_journal_access(ctxt->handle, bucket,
- OCFS2_JOURNAL_ACCESS_WRITE);
- if (ret) {
- mlog_errno(ret);
- goto out;
- }
-
/*
* From here on out we have to dirty the bucket. The generic
* value calls only modify one of the bucket's bhs, but we need
@@ -4748,12 +4741,18 @@
ret = ocfs2_xattr_value_truncate(inode, &vb, len, ctxt);
if (ret) {
mlog_errno(ret);
- goto out_dirty;
+ goto out;
+ }
+
+ ret = ocfs2_xattr_bucket_journal_access(ctxt->handle, bucket,
+ OCFS2_JOURNAL_ACCESS_WRITE);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
}
xe->xe_value_size = cpu_to_le64(len);
-out_dirty:
ocfs2_xattr_bucket_journal_dirty(ctxt->handle, bucket);
out:
diff --git a/fs/seq_file.c b/fs/seq_file.c
index b569ff1..5267098 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -54,6 +54,64 @@
}
EXPORT_SYMBOL(seq_open);
+static int traverse(struct seq_file *m, loff_t offset)
+{
+ loff_t pos = 0, index;
+ int error = 0;
+ void *p;
+
+ m->version = 0;
+ index = 0;
+ m->count = m->from = 0;
+ if (!offset) {
+ m->index = index;
+ return 0;
+ }
+ if (!m->buf) {
+ m->buf = kmalloc(m->size = PAGE_SIZE, GFP_KERNEL);
+ if (!m->buf)
+ return -ENOMEM;
+ }
+ p = m->op->start(m, &index);
+ while (p) {
+ error = PTR_ERR(p);
+ if (IS_ERR(p))
+ break;
+ error = m->op->show(m, p);
+ if (error < 0)
+ break;
+ if (unlikely(error)) {
+ error = 0;
+ m->count = 0;
+ }
+ if (m->count == m->size)
+ goto Eoverflow;
+ if (pos + m->count > offset) {
+ m->from = offset - pos;
+ m->count -= m->from;
+ m->index = index;
+ break;
+ }
+ pos += m->count;
+ m->count = 0;
+ if (pos == offset) {
+ index++;
+ m->index = index;
+ break;
+ }
+ p = m->op->next(m, p, &index);
+ }
+ m->op->stop(m, p);
+ m->index = index;
+ return error;
+
+Eoverflow:
+ m->op->stop(m, p);
+ kfree(m->buf);
+ m->buf = kmalloc(m->size <<= 1, GFP_KERNEL);
+ return !m->buf ? -ENOMEM : -EAGAIN;
+}
+
/**
* seq_read - ->read() method for sequential files.
* @file: the file to read from
@@ -186,63 +244,6 @@
}
EXPORT_SYMBOL(seq_read);
-static int traverse(struct seq_file *m, loff_t offset)
-{
- loff_t pos = 0, index;
- int error = 0;
- void *p;
-
- m->version = 0;
- index = 0;
- m->count = m->from = 0;
- if (!offset) {
- m->index = index;
- return 0;
- }
- if (!m->buf) {
- m->buf = kmalloc(m->size = PAGE_SIZE, GFP_KERNEL);
- if (!m->buf)
- return -ENOMEM;
- }
- p = m->op->start(m, &index);
- while (p) {
- error = PTR_ERR(p);
- if (IS_ERR(p))
- break;
- error = m->op->show(m, p);
- if (error < 0)
- break;
- if (unlikely(error)) {
- error = 0;
- m->count = 0;
- }
- if (m->count == m->size)
- goto Eoverflow;
- if (pos + m->count > offset) {
- m->from = offset - pos;
- m->count -= m->from;
- m->index = index;
- break;
- }
- pos += m->count;
- m->count = 0;
- if (pos == offset) {
- index++;
- m->index = index;
- break;
- }
- p = m->op->next(m, p, &index);
- }
- m->op->stop(m, p);
- return error;
-
-Eoverflow:
- m->op->stop(m, p);
- kfree(m->buf);
- m->buf = kmalloc(m->size <<= 1, GFP_KERNEL);
- return !m->buf ? -ENOMEM : -EAGAIN;
-}
-
/**
* seq_lseek - ->llseek() method for sequential files.
* @file: the file in question
diff --git a/fs/super.c b/fs/super.c
index 645e540..61dce00 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -301,7 +301,7 @@
/*
* wait for asynchronous fs operations to finish before going further
*/
- async_synchronize_full_special(&sb->s_async_list);
+ async_synchronize_full_domain(&sb->s_async_list);
/* bad name - it should be evict_inodes() */
invalidate_inodes(sb);
@@ -470,7 +470,7 @@
sb->s_count++;
spin_unlock(&sb_lock);
down_read(&sb->s_umount);
- async_synchronize_full_special(&sb->s_async_list);
+ async_synchronize_full_domain(&sb->s_async_list);
if (sb->s_root && (wait || sb->s_dirt))
sb->s_op->sync_fs(sb, wait);
up_read(&sb->s_umount);
diff --git a/fs/ubifs/budget.c b/fs/ubifs/budget.c
index 175f9c5..f393620 100644
--- a/fs/ubifs/budget.c
+++ b/fs/ubifs/budget.c
@@ -689,7 +689,7 @@
}
/**
- * ubifs_get_free_space - return amount of free space.
+ * ubifs_get_free_space_nolock - return amount of free space.
* @c: UBIFS file-system description object
*
* This function calculates amount of free space to report to user-space.
@@ -704,16 +704,14 @@
* traditional file-systems, because they have way less overhead than UBIFS.
* So, to keep users happy, UBIFS tries to take the overhead into account.
*/
-long long ubifs_get_free_space(struct ubifs_info *c)
+long long ubifs_get_free_space_nolock(struct ubifs_info *c)
{
- int min_idx_lebs, rsvd_idx_lebs, lebs;
+ int rsvd_idx_lebs, lebs;
long long available, outstanding, free;
- spin_lock(&c->space_lock);
- min_idx_lebs = c->min_idx_lebs;
- ubifs_assert(min_idx_lebs == ubifs_calc_min_idx_lebs(c));
+ ubifs_assert(c->min_idx_lebs == ubifs_calc_min_idx_lebs(c));
outstanding = c->budg_data_growth + c->budg_dd_growth;
- available = ubifs_calc_available(c, min_idx_lebs);
+ available = ubifs_calc_available(c, c->min_idx_lebs);
/*
* When reporting free space to user-space, UBIFS guarantees that it is
@@ -726,15 +724,14 @@
* Note, the calculations below are similar to what we have in
* 'do_budget_space()', so refer there for comments.
*/
- if (min_idx_lebs > c->lst.idx_lebs)
- rsvd_idx_lebs = min_idx_lebs - c->lst.idx_lebs;
+ if (c->min_idx_lebs > c->lst.idx_lebs)
+ rsvd_idx_lebs = c->min_idx_lebs - c->lst.idx_lebs;
else
rsvd_idx_lebs = 0;
lebs = c->lst.empty_lebs + c->freeable_cnt + c->idx_gc_cnt -
c->lst.taken_empty_lebs;
lebs -= rsvd_idx_lebs;
available += lebs * (c->dark_wm - c->leb_overhead);
- spin_unlock(&c->space_lock);
if (available > outstanding)
free = ubifs_reported_space(c, available - outstanding);
@@ -742,3 +739,21 @@
free = 0;
return free;
}
+
+/**
+ * ubifs_get_free_space - return amount of free space.
+ * @c: UBIFS file-system description object
+ *
+ * This function calculates and retuns amount of free space to report to
+ * user-space.
+ */
+long long ubifs_get_free_space(struct ubifs_info *c)
+{
+ long long free;
+
+ spin_lock(&c->space_lock);
+ free = ubifs_get_free_space_nolock(c);
+ spin_unlock(&c->space_lock);
+
+ return free;
+}
diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c
index 792c5a1..e975bd8 100644
--- a/fs/ubifs/debug.c
+++ b/fs/ubifs/debug.c
@@ -620,9 +620,11 @@
c->dark_wm, c->dead_wm, c->max_idx_node_sz);
printk(KERN_DEBUG "\tgc_lnum %d, ihead_lnum %d\n",
c->gc_lnum, c->ihead_lnum);
- for (i = 0; i < c->jhead_cnt; i++)
- printk(KERN_DEBUG "\tjhead %d\t LEB %d\n",
- c->jheads[i].wbuf.jhead, c->jheads[i].wbuf.lnum);
+ /* If we are in R/O mode, journal heads do not exist */
+ if (c->jheads)
+ for (i = 0; i < c->jhead_cnt; i++)
+ printk(KERN_DEBUG "\tjhead %d\t LEB %d\n",
+ c->jheads[i].wbuf.jhead, c->jheads[i].wbuf.lnum);
for (rb = rb_first(&c->buds); rb; rb = rb_next(rb)) {
bud = rb_entry(rb, struct ubifs_bud, rb);
printk(KERN_DEBUG "\tbud LEB %d\n", bud->lnum);
@@ -637,10 +639,7 @@
/* Print budgeting predictions */
available = ubifs_calc_available(c, c->min_idx_lebs);
outstanding = c->budg_data_growth + c->budg_dd_growth;
- if (available > outstanding)
- free = ubifs_reported_space(c, available - outstanding);
- else
- free = 0;
+ free = ubifs_get_free_space_nolock(c);
printk(KERN_DEBUG "Budgeting predictions:\n");
printk(KERN_DEBUG "\tavailable: %lld, outstanding %lld, free %lld\n",
available, outstanding, free);
@@ -861,6 +860,65 @@
}
/**
+ * dbg_save_space_info - save information about flash space.
+ * @c: UBIFS file-system description object
+ *
+ * This function saves information about UBIFS free space, dirty space, etc, in
+ * order to check it later.
+ */
+void dbg_save_space_info(struct ubifs_info *c)
+{
+ struct ubifs_debug_info *d = c->dbg;
+
+ ubifs_get_lp_stats(c, &d->saved_lst);
+
+ spin_lock(&c->space_lock);
+ d->saved_free = ubifs_get_free_space_nolock(c);
+ spin_unlock(&c->space_lock);
+}
+
+/**
+ * dbg_check_space_info - check flash space information.
+ * @c: UBIFS file-system description object
+ *
+ * This function compares current flash space information with the information
+ * which was saved when the 'dbg_save_space_info()' function was called.
+ * Returns zero if the information has not changed, and %-EINVAL it it has
+ * changed.
+ */
+int dbg_check_space_info(struct ubifs_info *c)
+{
+ struct ubifs_debug_info *d = c->dbg;
+ struct ubifs_lp_stats lst;
+ long long avail, free;
+
+ spin_lock(&c->space_lock);
+ avail = ubifs_calc_available(c, c->min_idx_lebs);
+ spin_unlock(&c->space_lock);
+ free = ubifs_get_free_space(c);
+
+ if (free != d->saved_free) {
+ ubifs_err("free space changed from %lld to %lld",
+ d->saved_free, free);
+ goto out;
+ }
+
+ return 0;
+
+out:
+ ubifs_msg("saved lprops statistics dump");
+ dbg_dump_lstats(&d->saved_lst);
+ ubifs_get_lp_stats(c, &lst);
+ ubifs_msg("current lprops statistics dump");
+ dbg_dump_lstats(&d->saved_lst);
+ spin_lock(&c->space_lock);
+ dbg_dump_budg(c);
+ spin_unlock(&c->space_lock);
+ dump_stack();
+ return -EINVAL;
+}
+
+/**
* dbg_check_synced_i_size - check synchronized inode size.
* @inode: inode to check
*
@@ -1349,7 +1407,7 @@
* @c: UBIFS file-system description object
* @leaf_cb: called for each leaf node
* @znode_cb: called for each indexing node
- * @priv: private date which is passed to callbacks
+ * @priv: private data which is passed to callbacks
*
* This function walks the UBIFS index and calls the @leaf_cb for each leaf
* node and @znode_cb for each indexing node. Returns zero in case of success
@@ -2409,7 +2467,7 @@
* Root directory for UBIFS stuff in debugfs. Contains sub-directories which
* contain the stuff specific to particular file-system mounts.
*/
-static struct dentry *debugfs_rootdir;
+static struct dentry *dfs_rootdir;
/**
* dbg_debugfs_init - initialize debugfs file-system.
@@ -2421,9 +2479,9 @@
*/
int dbg_debugfs_init(void)
{
- debugfs_rootdir = debugfs_create_dir("ubifs", NULL);
- if (IS_ERR(debugfs_rootdir)) {
- int err = PTR_ERR(debugfs_rootdir);
+ dfs_rootdir = debugfs_create_dir("ubifs", NULL);
+ if (IS_ERR(dfs_rootdir)) {
+ int err = PTR_ERR(dfs_rootdir);
ubifs_err("cannot create \"ubifs\" debugfs directory, "
"error %d\n", err);
return err;
@@ -2437,7 +2495,7 @@
*/
void dbg_debugfs_exit(void)
{
- debugfs_remove(debugfs_rootdir);
+ debugfs_remove(dfs_rootdir);
}
static int open_debugfs_file(struct inode *inode, struct file *file)
@@ -2452,13 +2510,13 @@
struct ubifs_info *c = file->private_data;
struct ubifs_debug_info *d = c->dbg;
- if (file->f_path.dentry == d->dump_lprops)
+ if (file->f_path.dentry == d->dfs_dump_lprops)
dbg_dump_lprops(c);
- else if (file->f_path.dentry == d->dump_budg) {
+ else if (file->f_path.dentry == d->dfs_dump_budg) {
spin_lock(&c->space_lock);
dbg_dump_budg(c);
spin_unlock(&c->space_lock);
- } else if (file->f_path.dentry == d->dump_tnc) {
+ } else if (file->f_path.dentry == d->dfs_dump_tnc) {
mutex_lock(&c->tnc_mutex);
dbg_dump_tnc(c);
mutex_unlock(&c->tnc_mutex);
@@ -2469,7 +2527,7 @@
return count;
}
-static const struct file_operations debugfs_fops = {
+static const struct file_operations dfs_fops = {
.open = open_debugfs_file,
.write = write_debugfs_file,
.owner = THIS_MODULE,
@@ -2494,36 +2552,32 @@
struct dentry *dent;
struct ubifs_debug_info *d = c->dbg;
- sprintf(d->debugfs_dir_name, "ubi%d_%d", c->vi.ubi_num, c->vi.vol_id);
- d->debugfs_dir = debugfs_create_dir(d->debugfs_dir_name,
- debugfs_rootdir);
- if (IS_ERR(d->debugfs_dir)) {
- err = PTR_ERR(d->debugfs_dir);
+ sprintf(d->dfs_dir_name, "ubi%d_%d", c->vi.ubi_num, c->vi.vol_id);
+ d->dfs_dir = debugfs_create_dir(d->dfs_dir_name, dfs_rootdir);
+ if (IS_ERR(d->dfs_dir)) {
+ err = PTR_ERR(d->dfs_dir);
ubifs_err("cannot create \"%s\" debugfs directory, error %d\n",
- d->debugfs_dir_name, err);
+ d->dfs_dir_name, err);
goto out;
}
fname = "dump_lprops";
- dent = debugfs_create_file(fname, S_IWUGO, d->debugfs_dir, c,
- &debugfs_fops);
+ dent = debugfs_create_file(fname, S_IWUGO, d->dfs_dir, c, &dfs_fops);
if (IS_ERR(dent))
goto out_remove;
- d->dump_lprops = dent;
+ d->dfs_dump_lprops = dent;
fname = "dump_budg";
- dent = debugfs_create_file(fname, S_IWUGO, d->debugfs_dir, c,
- &debugfs_fops);
+ dent = debugfs_create_file(fname, S_IWUGO, d->dfs_dir, c, &dfs_fops);
if (IS_ERR(dent))
goto out_remove;
- d->dump_budg = dent;
+ d->dfs_dump_budg = dent;
fname = "dump_tnc";
- dent = debugfs_create_file(fname, S_IWUGO, d->debugfs_dir, c,
- &debugfs_fops);
+ dent = debugfs_create_file(fname, S_IWUGO, d->dfs_dir, c, &dfs_fops);
if (IS_ERR(dent))
goto out_remove;
- d->dump_tnc = dent;
+ d->dfs_dump_tnc = dent;
return 0;
@@ -2531,7 +2585,7 @@
err = PTR_ERR(dent);
ubifs_err("cannot create \"%s\" debugfs directory, error %d\n",
fname, err);
- debugfs_remove_recursive(d->debugfs_dir);
+ debugfs_remove_recursive(d->dfs_dir);
out:
return err;
}
@@ -2542,7 +2596,7 @@
*/
void dbg_debugfs_exit_fs(struct ubifs_info *c)
{
- debugfs_remove_recursive(c->dbg->debugfs_dir);
+ debugfs_remove_recursive(c->dbg->dfs_dir);
}
#endif /* CONFIG_UBIFS_FS_DEBUG */
diff --git a/fs/ubifs/debug.h b/fs/ubifs/debug.h
index 9820d69..c1cd73b 100644
--- a/fs/ubifs/debug.h
+++ b/fs/ubifs/debug.h
@@ -41,15 +41,17 @@
* @chk_lpt_wastage: used by LPT tree size checker
* @chk_lpt_lebs: used by LPT tree size checker
* @new_nhead_offs: used by LPT tree size checker
- * @new_ihead_lnum: used by debugging to check ihead_lnum
- * @new_ihead_offs: used by debugging to check ihead_offs
+ * @new_ihead_lnum: used by debugging to check @c->ihead_lnum
+ * @new_ihead_offs: used by debugging to check @c->ihead_offs
*
- * debugfs_dir_name: name of debugfs directory containing this file-system's
- * files
- * debugfs_dir: direntry object of the file-system debugfs directory
- * dump_lprops: "dump lprops" debugfs knob
- * dump_budg: "dump budgeting information" debugfs knob
- * dump_tnc: "dump TNC" debugfs knob
+ * @saved_lst: saved lprops statistics (used by 'dbg_save_space_info()')
+ * @saved_free: saved free space (used by 'dbg_save_space_info()')
+ *
+ * dfs_dir_name: name of debugfs directory containing this file-system's files
+ * dfs_dir: direntry object of the file-system debugfs directory
+ * dfs_dump_lprops: "dump lprops" debugfs knob
+ * dfs_dump_budg: "dump budgeting information" debugfs knob
+ * dfs_dump_tnc: "dump TNC" debugfs knob
*/
struct ubifs_debug_info {
void *buf;
@@ -69,11 +71,14 @@
int new_ihead_lnum;
int new_ihead_offs;
- char debugfs_dir_name[100];
- struct dentry *debugfs_dir;
- struct dentry *dump_lprops;
- struct dentry *dump_budg;
- struct dentry *dump_tnc;
+ struct ubifs_lp_stats saved_lst;
+ long long saved_free;
+
+ char dfs_dir_name[100];
+ struct dentry *dfs_dir;
+ struct dentry *dfs_dump_lprops;
+ struct dentry *dfs_dump_budg;
+ struct dentry *dfs_dump_tnc;
};
#define ubifs_assert(expr) do { \
@@ -297,7 +302,8 @@
dbg_znode_callback znode_cb, void *priv);
/* Checking functions */
-
+void dbg_save_space_info(struct ubifs_info *c);
+int dbg_check_space_info(struct ubifs_info *c);
int dbg_check_lprops(struct ubifs_info *c);
int dbg_old_index_check_init(struct ubifs_info *c, struct ubifs_zbranch *zroot);
int dbg_check_old_index(struct ubifs_info *c, struct ubifs_zbranch *zroot);
@@ -439,6 +445,8 @@
#define dbg_walk_index(c, leaf_cb, znode_cb, priv) 0
#define dbg_old_index_check_init(c, zroot) 0
+#define dbg_save_space_info(c) ({})
+#define dbg_check_space_info(c) 0
#define dbg_check_old_index(c, zroot) 0
#define dbg_check_cats(c) 0
#define dbg_check_ltab(c) 0
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index f448ab1..f55d523 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -482,30 +482,29 @@
}
/**
- * lock_2_inodes - lock two UBIFS inodes.
+ * lock_2_inodes - a wrapper for locking two UBIFS inodes.
* @inode1: first inode
* @inode2: second inode
+ *
+ * We do not implement any tricks to guarantee strict lock ordering, because
+ * VFS has already done it for us on the @i_mutex. So this is just a simple
+ * wrapper function.
*/
static void lock_2_inodes(struct inode *inode1, struct inode *inode2)
{
- if (inode1->i_ino < inode2->i_ino) {
- mutex_lock_nested(&ubifs_inode(inode1)->ui_mutex, WB_MUTEX_2);
- mutex_lock_nested(&ubifs_inode(inode2)->ui_mutex, WB_MUTEX_3);
- } else {
- mutex_lock_nested(&ubifs_inode(inode2)->ui_mutex, WB_MUTEX_2);
- mutex_lock_nested(&ubifs_inode(inode1)->ui_mutex, WB_MUTEX_3);
- }
+ mutex_lock_nested(&ubifs_inode(inode1)->ui_mutex, WB_MUTEX_1);
+ mutex_lock_nested(&ubifs_inode(inode2)->ui_mutex, WB_MUTEX_2);
}
/**
- * unlock_2_inodes - unlock two UBIFS inodes inodes.
+ * unlock_2_inodes - a wrapper for unlocking two UBIFS inodes.
* @inode1: first inode
* @inode2: second inode
*/
static void unlock_2_inodes(struct inode *inode1, struct inode *inode2)
{
- mutex_unlock(&ubifs_inode(inode1)->ui_mutex);
mutex_unlock(&ubifs_inode(inode2)->ui_mutex);
+ mutex_unlock(&ubifs_inode(inode1)->ui_mutex);
}
static int ubifs_link(struct dentry *old_dentry, struct inode *dir,
@@ -527,6 +526,8 @@
dbg_gen("dent '%.*s' to ino %lu (nlink %d) in dir ino %lu",
dentry->d_name.len, dentry->d_name.name, inode->i_ino,
inode->i_nlink, dir->i_ino);
+ ubifs_assert(mutex_is_locked(&dir->i_mutex));
+ ubifs_assert(mutex_is_locked(&inode->i_mutex));
err = dbg_check_synced_i_size(inode);
if (err)
return err;
@@ -580,6 +581,8 @@
dbg_gen("dent '%.*s' from ino %lu (nlink %d) in dir ino %lu",
dentry->d_name.len, dentry->d_name.name, inode->i_ino,
inode->i_nlink, dir->i_ino);
+ ubifs_assert(mutex_is_locked(&dir->i_mutex));
+ ubifs_assert(mutex_is_locked(&inode->i_mutex));
err = dbg_check_synced_i_size(inode);
if (err)
return err;
@@ -667,7 +670,8 @@
dbg_gen("directory '%.*s', ino %lu in dir ino %lu", dentry->d_name.len,
dentry->d_name.name, inode->i_ino, dir->i_ino);
-
+ ubifs_assert(mutex_is_locked(&dir->i_mutex));
+ ubifs_assert(mutex_is_locked(&inode->i_mutex));
err = check_dir_empty(c, dentry->d_inode);
if (err)
return err;
@@ -922,59 +926,30 @@
}
/**
- * lock_3_inodes - lock three UBIFS inodes for rename.
+ * lock_3_inodes - a wrapper for locking three UBIFS inodes.
* @inode1: first inode
* @inode2: second inode
* @inode3: third inode
*
- * For 'ubifs_rename()', @inode1 may be the same as @inode2 whereas @inode3 may
- * be null.
+ * This function is used for 'ubifs_rename()' and @inode1 may be the same as
+ * @inode2 whereas @inode3 may be %NULL.
+ *
+ * We do not implement any tricks to guarantee strict lock ordering, because
+ * VFS has already done it for us on the @i_mutex. So this is just a simple
+ * wrapper function.
*/
static void lock_3_inodes(struct inode *inode1, struct inode *inode2,
struct inode *inode3)
{
- struct inode *i1, *i2, *i3;
-
- if (!inode3) {
- if (inode1 != inode2) {
- lock_2_inodes(inode1, inode2);
- return;
- }
- mutex_lock_nested(&ubifs_inode(inode1)->ui_mutex, WB_MUTEX_1);
- return;
- }
-
- if (inode1 == inode2) {
- lock_2_inodes(inode1, inode3);
- return;
- }
-
- /* 3 different inodes */
- if (inode1 < inode2) {
- i3 = inode2;
- if (inode1 < inode3) {
- i1 = inode1;
- i2 = inode3;
- } else {
- i1 = inode3;
- i2 = inode1;
- }
- } else {
- i3 = inode1;
- if (inode2 < inode3) {
- i1 = inode2;
- i2 = inode3;
- } else {
- i1 = inode3;
- i2 = inode2;
- }
- }
- mutex_lock_nested(&ubifs_inode(i1)->ui_mutex, WB_MUTEX_1);
- lock_2_inodes(i2, i3);
+ mutex_lock_nested(&ubifs_inode(inode1)->ui_mutex, WB_MUTEX_1);
+ if (inode2 != inode1)
+ mutex_lock_nested(&ubifs_inode(inode2)->ui_mutex, WB_MUTEX_2);
+ if (inode3)
+ mutex_lock_nested(&ubifs_inode(inode3)->ui_mutex, WB_MUTEX_3);
}
/**
- * unlock_3_inodes - unlock three UBIFS inodes for rename.
+ * unlock_3_inodes - a wrapper for unlocking three UBIFS inodes for rename.
* @inode1: first inode
* @inode2: second inode
* @inode3: third inode
@@ -982,11 +957,11 @@
static void unlock_3_inodes(struct inode *inode1, struct inode *inode2,
struct inode *inode3)
{
- mutex_unlock(&ubifs_inode(inode1)->ui_mutex);
- if (inode1 != inode2)
- mutex_unlock(&ubifs_inode(inode2)->ui_mutex);
if (inode3)
mutex_unlock(&ubifs_inode(inode3)->ui_mutex);
+ if (inode1 != inode2)
+ mutex_unlock(&ubifs_inode(inode2)->ui_mutex);
+ mutex_unlock(&ubifs_inode(inode1)->ui_mutex);
}
static int ubifs_rename(struct inode *old_dir, struct dentry *old_dentry,
@@ -1020,6 +995,11 @@
"dir ino %lu", old_dentry->d_name.len, old_dentry->d_name.name,
old_inode->i_ino, old_dir->i_ino, new_dentry->d_name.len,
new_dentry->d_name.name, new_dir->i_ino);
+ ubifs_assert(mutex_is_locked(&old_dir->i_mutex));
+ ubifs_assert(mutex_is_locked(&new_dir->i_mutex));
+ if (unlink)
+ ubifs_assert(mutex_is_locked(&new_inode->i_mutex));
+
if (unlink && is_dir) {
err = check_dir_empty(c, new_inode);
@@ -1199,7 +1179,7 @@
return 0;
}
-struct inode_operations ubifs_dir_inode_operations = {
+const struct inode_operations ubifs_dir_inode_operations = {
.lookup = ubifs_lookup,
.create = ubifs_create,
.link = ubifs_link,
@@ -1219,7 +1199,7 @@
#endif
};
-struct file_operations ubifs_dir_operations = {
+const struct file_operations ubifs_dir_operations = {
.llseek = ubifs_dir_llseek,
.release = ubifs_dir_release,
.read = generic_read_dir,
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index bf373745..93b6de5 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -432,7 +432,6 @@
int uninitialized_var(err), appending = !!(pos + len > inode->i_size);
struct page *page;
-
ubifs_assert(ubifs_inode(inode)->ui_size == inode->i_size);
if (unlikely(c->ro_media))
@@ -1541,7 +1540,7 @@
return 0;
}
-struct address_space_operations ubifs_file_address_operations = {
+const struct address_space_operations ubifs_file_address_operations = {
.readpage = ubifs_readpage,
.writepage = ubifs_writepage,
.write_begin = ubifs_write_begin,
@@ -1551,7 +1550,7 @@
.releasepage = ubifs_releasepage,
};
-struct inode_operations ubifs_file_inode_operations = {
+const struct inode_operations ubifs_file_inode_operations = {
.setattr = ubifs_setattr,
.getattr = ubifs_getattr,
#ifdef CONFIG_UBIFS_FS_XATTR
@@ -1562,14 +1561,14 @@
#endif
};
-struct inode_operations ubifs_symlink_inode_operations = {
+const struct inode_operations ubifs_symlink_inode_operations = {
.readlink = generic_readlink,
.follow_link = ubifs_follow_link,
.setattr = ubifs_setattr,
.getattr = ubifs_getattr,
};
-struct file_operations ubifs_file_operations = {
+const struct file_operations ubifs_file_operations = {
.llseek = generic_file_llseek,
.read = do_sync_read,
.write = do_sync_write,
diff --git a/fs/ubifs/gc.c b/fs/ubifs/gc.c
index 9832f9a..a711d33 100644
--- a/fs/ubifs/gc.c
+++ b/fs/ubifs/gc.c
@@ -31,6 +31,26 @@
* to be reused. Garbage collection will cause the number of dirty index nodes
* to grow, however sufficient space is reserved for the index to ensure the
* commit will never run out of space.
+ *
+ * Notes about dead watermark. At current UBIFS implementation we assume that
+ * LEBs which have less than @c->dead_wm bytes of free + dirty space are full
+ * and not worth garbage-collecting. The dead watermark is one min. I/O unit
+ * size, or min. UBIFS node size, depending on what is greater. Indeed, UBIFS
+ * Garbage Collector has to synchronize the GC head's write buffer before
+ * returning, so this is about wasting one min. I/O unit. However, UBIFS GC can
+ * actually reclaim even very small pieces of dirty space by garbage collecting
+ * enough dirty LEBs, but we do not bother doing this at this implementation.
+ *
+ * Notes about dark watermark. The results of GC work depends on how big are
+ * the UBIFS nodes GC deals with. Large nodes make GC waste more space. Indeed,
+ * if GC move data from LEB A to LEB B and nodes in LEB A are large, GC would
+ * have to waste large pieces of free space at the end of LEB B, because nodes
+ * from LEB A would not fit. And the worst situation is when all nodes are of
+ * maximum size. So dark watermark is the amount of free + dirty space in LEB
+ * which are guaranteed to be reclaimable. If LEB has less space, the GC migh
+ * be unable to reclaim it. So, LEBs with free + dirty greater than dark
+ * watermark are "good" LEBs from GC's point of few. The other LEBs are not so
+ * good, and GC takes extra care when moving them.
*/
#include <linux/pagemap.h>
@@ -381,7 +401,7 @@
/*
* Don't release the LEB until after the next commit, because
- * it may contain date which is needed for recovery. So
+ * it may contain data which is needed for recovery. So
* although we freed this LEB, it will become usable only after
* the commit.
*/
@@ -810,8 +830,9 @@
* ubifs_destroy_idx_gc - destroy idx_gc list.
* @c: UBIFS file-system description object
*
- * This function destroys the idx_gc list. It is called when unmounting or
- * remounting read-only so locks are not needed.
+ * This function destroys the @c->idx_gc list. It is called when unmounting
+ * so locks are not needed. Returns zero in case of success and a negative
+ * error code in case of failure.
*/
void ubifs_destroy_idx_gc(struct ubifs_info *c)
{
@@ -824,7 +845,6 @@
list_del(&idx_gc->list);
kfree(idx_gc);
}
-
}
/**
diff --git a/fs/ubifs/io.c b/fs/ubifs/io.c
index 0168271..e8e632a 100644
--- a/fs/ubifs/io.c
+++ b/fs/ubifs/io.c
@@ -29,7 +29,7 @@
* would have been wasted for padding to the nearest minimal I/O unit boundary.
* Instead, data first goes to the write-buffer and is flushed when the
* buffer is full or when it is not used for some time (by timer). This is
- * similarto the mechanism is used by JFFS2.
+ * similar to the mechanism is used by JFFS2.
*
* Write-buffers are defined by 'struct ubifs_wbuf' objects and protected by
* mutexes defined inside these objects. Since sometimes upper-level code
@@ -75,7 +75,7 @@
* @lnum: logical eraseblock number
* @offs: offset within the logical eraseblock
* @quiet: print no messages
- * @chk_crc: indicates whether to always check the CRC
+ * @must_chk_crc: indicates whether to always check the CRC
*
* This function checks node magic number and CRC checksum. This function also
* validates node length to prevent UBIFS from becoming crazy when an attacker
@@ -83,11 +83,17 @@
* node length in the common header could cause UBIFS to read memory outside of
* allocated buffer when checking the CRC checksum.
*
- * This function returns zero in case of success %-EUCLEAN in case of bad CRC
- * or magic.
+ * This function may skip data nodes CRC checking if @c->no_chk_data_crc is
+ * true, which is controlled by corresponding UBIFS mount option. However, if
+ * @must_chk_crc is true, then @c->no_chk_data_crc is ignored and CRC is
+ * checked. Similarly, if @c->always_chk_crc is true, @c->no_chk_data_crc is
+ * ignored and CRC is checked.
+ *
+ * This function returns zero in case of success and %-EUCLEAN in case of bad
+ * CRC or magic.
*/
int ubifs_check_node(const struct ubifs_info *c, const void *buf, int lnum,
- int offs, int quiet, int chk_crc)
+ int offs, int quiet, int must_chk_crc)
{
int err = -EINVAL, type, node_len;
uint32_t crc, node_crc, magic;
@@ -123,9 +129,9 @@
node_len > c->ranges[type].max_len)
goto out_len;
- if (!chk_crc && type == UBIFS_DATA_NODE && !c->always_chk_crc)
- if (c->no_chk_data_crc)
- return 0;
+ if (!must_chk_crc && type == UBIFS_DATA_NODE && !c->always_chk_crc &&
+ c->no_chk_data_crc)
+ return 0;
crc = crc32(UBIFS_CRC32_INIT, buf + 8, node_len - 8);
node_crc = le32_to_cpu(ch->crc);
diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c
index 9b7c54e..a11ca09 100644
--- a/fs/ubifs/journal.c
+++ b/fs/ubifs/journal.c
@@ -208,7 +208,7 @@
offs = 0;
out:
- err = ubifs_wbuf_seek_nolock(wbuf, lnum, offs, UBI_SHORTTERM);
+ err = ubifs_wbuf_seek_nolock(wbuf, lnum, offs, wbuf->dtype);
if (err)
goto out_unlock;
diff --git a/fs/ubifs/lprops.c b/fs/ubifs/lprops.c
index dfd2bce..4cdd284 100644
--- a/fs/ubifs/lprops.c
+++ b/fs/ubifs/lprops.c
@@ -635,10 +635,10 @@
* @c: UBIFS file-system description object
* @st: return statistics
*/
-void ubifs_get_lp_stats(struct ubifs_info *c, struct ubifs_lp_stats *st)
+void ubifs_get_lp_stats(struct ubifs_info *c, struct ubifs_lp_stats *lst)
{
spin_lock(&c->space_lock);
- memcpy(st, &c->lst, sizeof(struct ubifs_lp_stats));
+ memcpy(lst, &c->lst, sizeof(struct ubifs_lp_stats));
spin_unlock(&c->space_lock);
}
@@ -678,6 +678,9 @@
out:
ubifs_release_lprops(c);
+ if (err)
+ ubifs_err("cannot change properties of LEB %d, error %d",
+ lnum, err);
return err;
}
@@ -714,6 +717,9 @@
out:
ubifs_release_lprops(c);
+ if (err)
+ ubifs_err("cannot update properties of LEB %d, error %d",
+ lnum, err);
return err;
}
@@ -737,6 +743,8 @@
lpp = ubifs_lpt_lookup(c, lnum);
if (IS_ERR(lpp)) {
err = PTR_ERR(lpp);
+ ubifs_err("cannot read properties of LEB %d, error %d",
+ lnum, err);
goto out;
}
diff --git a/fs/ubifs/lpt_commit.c b/fs/ubifs/lpt_commit.c
index 96ca957..3216a1f 100644
--- a/fs/ubifs/lpt_commit.c
+++ b/fs/ubifs/lpt_commit.c
@@ -556,23 +556,23 @@
}
/**
- * next_pnode - find next pnode.
+ * next_pnode_to_dirty - find next pnode to dirty.
* @c: UBIFS file-system description object
* @pnode: pnode
*
- * This function returns the next pnode or %NULL if there are no more pnodes.
+ * This function returns the next pnode to dirty or %NULL if there are no more
+ * pnodes. Note that pnodes that have never been written (lnum == 0) are
+ * skipped.
*/
-static struct ubifs_pnode *next_pnode(struct ubifs_info *c,
- struct ubifs_pnode *pnode)
+static struct ubifs_pnode *next_pnode_to_dirty(struct ubifs_info *c,
+ struct ubifs_pnode *pnode)
{
struct ubifs_nnode *nnode;
int iip;
/* Try to go right */
nnode = pnode->parent;
- iip = pnode->iip + 1;
- if (iip < UBIFS_LPT_FANOUT) {
- /* We assume here that LEB zero is never an LPT LEB */
+ for (iip = pnode->iip + 1; iip < UBIFS_LPT_FANOUT; iip++) {
if (nnode->nbranch[iip].lnum)
return ubifs_get_pnode(c, nnode, iip);
}
@@ -583,8 +583,11 @@
nnode = nnode->parent;
if (!nnode)
return NULL;
- /* We assume here that LEB zero is never an LPT LEB */
- } while (iip >= UBIFS_LPT_FANOUT || !nnode->nbranch[iip].lnum);
+ for (; iip < UBIFS_LPT_FANOUT; iip++) {
+ if (nnode->nbranch[iip].lnum)
+ break;
+ }
+ } while (iip >= UBIFS_LPT_FANOUT);
/* Go right */
nnode = ubifs_get_nnode(c, nnode, iip);
@@ -593,12 +596,29 @@
/* Go down to level 1 */
while (nnode->level > 1) {
- nnode = ubifs_get_nnode(c, nnode, 0);
+ for (iip = 0; iip < UBIFS_LPT_FANOUT; iip++) {
+ if (nnode->nbranch[iip].lnum)
+ break;
+ }
+ if (iip >= UBIFS_LPT_FANOUT) {
+ /*
+ * Should not happen, but we need to keep going
+ * if it does.
+ */
+ iip = 0;
+ }
+ nnode = ubifs_get_nnode(c, nnode, iip);
if (IS_ERR(nnode))
return (void *)nnode;
}
- return ubifs_get_pnode(c, nnode, 0);
+ for (iip = 0; iip < UBIFS_LPT_FANOUT; iip++)
+ if (nnode->nbranch[iip].lnum)
+ break;
+ if (iip >= UBIFS_LPT_FANOUT)
+ /* Should not happen, but we need to keep going if it does */
+ iip = 0;
+ return ubifs_get_pnode(c, nnode, iip);
}
/**
@@ -688,7 +708,7 @@
pnode = pnode_lookup(c, 0);
while (pnode) {
do_make_pnode_dirty(c, pnode);
- pnode = next_pnode(c, pnode);
+ pnode = next_pnode_to_dirty(c, pnode);
if (IS_ERR(pnode))
return PTR_ERR(pnode);
}
diff --git a/fs/ubifs/master.c b/fs/ubifs/master.c
index 71d5493..a88f338 100644
--- a/fs/ubifs/master.c
+++ b/fs/ubifs/master.c
@@ -354,7 +354,7 @@
int err, lnum, offs, len;
if (c->ro_media)
- return -EINVAL;
+ return -EROFS;
lnum = UBIFS_MST_LNUM;
offs = c->mst_offs + c->mst_node_alsz;
diff --git a/fs/ubifs/orphan.c b/fs/ubifs/orphan.c
index 9e6f403..152a7b3 100644
--- a/fs/ubifs/orphan.c
+++ b/fs/ubifs/orphan.c
@@ -46,7 +46,7 @@
* Orphans are accumulated in a rb-tree. When an inode's link count drops to
* zero, the inode number is added to the rb-tree. It is removed from the tree
* when the inode is deleted. Any new orphans that are in the orphan tree when
- * the commit is run, are written to the orphan area in 1 or more orph nodes.
+ * the commit is run, are written to the orphan area in 1 or more orphan nodes.
* If the orphan area is full, it is consolidated to make space. There is
* always enough space because validation prevents the user from creating more
* than the maximum number of orphans allowed.
@@ -231,7 +231,7 @@
}
/**
- * do_write_orph_node - write a node
+ * do_write_orph_node - write a node to the orphan head.
* @c: UBIFS file-system description object
* @len: length of node
* @atomic: write atomically
@@ -264,11 +264,11 @@
}
/**
- * write_orph_node - write an orph node
+ * write_orph_node - write an orphan node.
* @c: UBIFS file-system description object
* @atomic: write atomically
*
- * This function builds an orph node from the cnext list and writes it to the
+ * This function builds an orphan node from the cnext list and writes it to the
* orphan head. On success, %0 is returned, otherwise a negative error code
* is returned.
*/
@@ -326,11 +326,11 @@
}
/**
- * write_orph_nodes - write orph nodes until there are no more to commit
+ * write_orph_nodes - write orphan nodes until there are no more to commit.
* @c: UBIFS file-system description object
* @atomic: write atomically
*
- * This function writes orph nodes for all the orphans to commit. On success,
+ * This function writes orphan nodes for all the orphans to commit. On success,
* %0 is returned, otherwise a negative error code is returned.
*/
static int write_orph_nodes(struct ubifs_info *c, int atomic)
@@ -478,14 +478,14 @@
}
/**
- * clear_orphans - erase all LEBs used for orphans.
+ * ubifs_clear_orphans - erase all LEBs used for orphans.
* @c: UBIFS file-system description object
*
* If recovery is not required, then the orphans from the previous session
* are not needed. This function locates the LEBs used to record
* orphans, and un-maps them.
*/
-static int clear_orphans(struct ubifs_info *c)
+int ubifs_clear_orphans(struct ubifs_info *c)
{
int lnum, err;
@@ -547,9 +547,9 @@
* do_kill_orphans - remove orphan inodes from the index.
* @c: UBIFS file-system description object
* @sleb: scanned LEB
- * @last_cmt_no: cmt_no of last orph node read is passed and returned here
+ * @last_cmt_no: cmt_no of last orphan node read is passed and returned here
* @outofdate: whether the LEB is out of date is returned here
- * @last_flagged: whether the end orph node is encountered
+ * @last_flagged: whether the end orphan node is encountered
*
* This function is a helper to the 'kill_orphans()' function. It goes through
* every orphan node in a LEB and for every inode number recorded, removes
@@ -580,8 +580,8 @@
/*
* The commit number on the master node may be less, because
* of a failed commit. If there are several failed commits in a
- * row, the commit number written on orph nodes will continue to
- * increase (because the commit number is adjusted here) even
+ * row, the commit number written on orphan nodes will continue
+ * to increase (because the commit number is adjusted here) even
* though the commit number on the master node stays the same
* because the master node has not been re-written.
*/
@@ -589,9 +589,9 @@
c->cmt_no = cmt_no;
if (cmt_no < *last_cmt_no && *last_flagged) {
/*
- * The last orph node had a higher commit number and was
- * flagged as the last written for that commit number.
- * That makes this orph node, out of date.
+ * The last orphan node had a higher commit number and
+ * was flagged as the last written for that commit
+ * number. That makes this orphan node, out of date.
*/
if (!first) {
ubifs_err("out of order commit number %llu in "
@@ -658,10 +658,10 @@
/*
* Orph nodes always start at c->orph_first and are written to each
* successive LEB in turn. Generally unused LEBs will have been unmapped
- * but may contain out of date orph nodes if the unmap didn't go
- * through. In addition, the last orph node written for each commit is
+ * but may contain out of date orphan nodes if the unmap didn't go
+ * through. In addition, the last orphan node written for each commit is
* marked (top bit of orph->cmt_no is set to 1). It is possible that
- * there are orph nodes from the next commit (i.e. the commit did not
+ * there are orphan nodes from the next commit (i.e. the commit did not
* complete successfully). In that case, no orphans will have been lost
* due to the way that orphans are written, and any orphans added will
* be valid orphans anyway and so can be deleted.
@@ -718,7 +718,7 @@
if (unclean)
err = kill_orphans(c);
else if (!read_only)
- err = clear_orphans(c);
+ err = ubifs_clear_orphans(c);
return err;
}
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 89556ee..1182b66 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -397,6 +397,7 @@
buf->f_namelen = UBIFS_MAX_NLEN;
buf->f_fsid.val[0] = le32_to_cpu(uuid[0]) ^ le32_to_cpu(uuid[2]);
buf->f_fsid.val[1] = le32_to_cpu(uuid[1]) ^ le32_to_cpu(uuid[3]);
+ ubifs_assert(buf->f_bfree <= c->block_cnt);
return 0;
}
@@ -432,33 +433,24 @@
int i, err;
struct ubifs_info *c = sb->s_fs_info;
struct writeback_control wbc = {
- .sync_mode = wait ? WB_SYNC_ALL : WB_SYNC_NONE,
+ .sync_mode = WB_SYNC_ALL,
.range_start = 0,
.range_end = LLONG_MAX,
.nr_to_write = LONG_MAX,
};
/*
- * Note by akpm about WB_SYNC_NONE used above: zero @wait is just an
- * advisory thing to help the file system shove lots of data into the
- * queues. If some gets missed then it'll be picked up on the second
+ * Zero @wait is just an advisory thing to help the file system shove
+ * lots of data into the queues, and there will be the second
* '->sync_fs()' call, with non-zero @wait.
*/
+ if (!wait)
+ return 0;
if (sb->s_flags & MS_RDONLY)
return 0;
/*
- * Synchronize write buffers, because 'ubifs_run_commit()' does not
- * do this if it waits for an already running commit.
- */
- for (i = 0; i < c->jhead_cnt; i++) {
- err = ubifs_wbuf_sync(&c->jheads[i].wbuf);
- if (err)
- return err;
- }
-
- /*
* VFS calls '->sync_fs()' before synchronizing all dirty inodes and
* pages, so synchronize them first, then commit the journal. Strictly
* speaking, it is not necessary to commit the journal here,
@@ -469,6 +461,16 @@
*/
generic_sync_sb_inodes(sb, &wbc);
+ /*
+ * Synchronize write buffers, because 'ubifs_run_commit()' does not
+ * do this if it waits for an already running commit.
+ */
+ for (i = 0; i < c->jhead_cnt; i++) {
+ err = ubifs_wbuf_sync(&c->jheads[i].wbuf);
+ if (err)
+ return err;
+ }
+
err = ubifs_run_commit(c);
if (err)
return err;
@@ -572,15 +574,8 @@
c->ranges[UBIFS_IDX_NODE].max_len = INT_MAX;
/*
- * Initialize dead and dark LEB space watermarks.
- *
- * Dead space is the space which cannot be used. Its watermark is
- * equivalent to min. I/O unit or minimum node size if it is greater
- * then min. I/O unit.
- *
- * Dark space is the space which might be used, or might not, depending
- * on which node should be written to the LEB. Its watermark is
- * equivalent to maximum UBIFS node size.
+ * Initialize dead and dark LEB space watermarks. See gc.c for comments
+ * about these values.
*/
c->dead_wm = ALIGN(MIN_WRITE_SZ, c->min_io_size);
c->dark_wm = ALIGN(UBIFS_MAX_NODE_SZ, c->min_io_size);
@@ -741,12 +736,12 @@
* take_gc_lnum - reserve GC LEB.
* @c: UBIFS file-system description object
*
- * This function ensures that the LEB reserved for garbage collection is
- * unmapped and is marked as "taken" in lprops. We also have to set free space
- * to LEB size and dirty space to zero, because lprops may contain out-of-date
- * information if the file-system was un-mounted before it has been committed.
- * This function returns zero in case of success and a negative error code in
- * case of failure.
+ * This function ensures that the LEB reserved for garbage collection is marked
+ * as "taken" in lprops. We also have to set free space to LEB size and dirty
+ * space to zero, because lprops may contain out-of-date information if the
+ * file-system was un-mounted before it has been committed. This function
+ * returns zero in case of success and a negative error code in case of
+ * failure.
*/
static int take_gc_lnum(struct ubifs_info *c)
{
@@ -757,10 +752,6 @@
return -EINVAL;
}
- err = ubifs_leb_unmap(c, c->gc_lnum);
- if (err)
- return err;
-
/* And we have to tell lprops that this LEB is taken */
err = ubifs_change_one_lp(c, c->gc_lnum, c->leb_size, 0,
LPROPS_TAKEN, 0, 0);
@@ -966,13 +957,16 @@
token = match_token(p, tokens, args);
switch (token) {
+ /*
+ * %Opt_fast_unmount and %Opt_norm_unmount options are ignored.
+ * We accepte them in order to be backware-compatible. But this
+ * should be removed at some point.
+ */
case Opt_fast_unmount:
c->mount_opts.unmount_mode = 2;
- c->fast_unmount = 1;
break;
case Opt_norm_unmount:
c->mount_opts.unmount_mode = 1;
- c->fast_unmount = 0;
break;
case Opt_bulk_read:
c->mount_opts.bulk_read = 2;
@@ -1094,12 +1088,7 @@
ubifs_err("insufficient free space to mount in read/write mode");
dbg_dump_budg(c);
dbg_dump_lprops(c);
- /*
- * We return %-EINVAL instead of %-ENOSPC because it seems to
- * be the closest error code mentioned in the mount function
- * documentation.
- */
- return -EINVAL;
+ return -ENOSPC;
}
return 0;
}
@@ -1286,10 +1275,19 @@
if (err)
goto out_orphans;
err = ubifs_rcvry_gc_commit(c);
- } else
+ } else {
err = take_gc_lnum(c);
- if (err)
- goto out_orphans;
+ if (err)
+ goto out_orphans;
+
+ /*
+ * GC LEB may contain garbage if there was an unclean
+ * reboot, and it should be un-mapped.
+ */
+ err = ubifs_leb_unmap(c, c->gc_lnum);
+ if (err)
+ return err;
+ }
err = dbg_check_lprops(c);
if (err)
@@ -1298,6 +1296,16 @@
err = ubifs_recover_size(c);
if (err)
goto out_orphans;
+ } else {
+ /*
+ * Even if we mount read-only, we have to set space in GC LEB
+ * to proper value because this affects UBIFS free space
+ * reporting. We do not want to have a situation when
+ * re-mounting from R/O to R/W changes amount of free space.
+ */
+ err = take_gc_lnum(c);
+ if (err)
+ goto out_orphans;
}
spin_lock(&ubifs_infos_lock);
@@ -1310,14 +1318,17 @@
else {
c->need_recovery = 0;
ubifs_msg("recovery completed");
+ /* GC LEB has to be empty and taken at this point */
+ ubifs_assert(c->lst.taken_empty_lebs == 1);
}
- }
+ } else
+ ubifs_assert(c->lst.taken_empty_lebs == 1);
- err = dbg_debugfs_init_fs(c);
+ err = dbg_check_filesystem(c);
if (err)
goto out_infos;
- err = dbg_check_filesystem(c);
+ err = dbg_debugfs_init_fs(c);
if (err)
goto out_infos;
@@ -1351,7 +1362,6 @@
c->uuid[4], c->uuid[5], c->uuid[6], c->uuid[7],
c->uuid[8], c->uuid[9], c->uuid[10], c->uuid[11],
c->uuid[12], c->uuid[13], c->uuid[14], c->uuid[15]);
- dbg_msg("fast unmount: %d", c->fast_unmount);
dbg_msg("big_lpt %d", c->big_lpt);
dbg_msg("log LEBs: %d (%d - %d)",
c->log_lebs, UBIFS_LOG_LNUM, c->log_last);
@@ -1475,10 +1485,8 @@
{
int err, lnum;
- if (c->ro_media)
- return -EINVAL;
-
mutex_lock(&c->umount_mutex);
+ dbg_save_space_info(c);
c->remounting_rw = 1;
c->always_chk_crc = 1;
@@ -1514,6 +1522,12 @@
err = ubifs_recover_inl_heads(c, c->sbuf);
if (err)
goto out;
+ } else {
+ /* A readonly mount is not allowed to have orphans */
+ ubifs_assert(c->tot_orphans == 0);
+ err = ubifs_clear_orphans(c);
+ if (err)
+ goto out;
}
if (!(c->mst_node->flags & cpu_to_le32(UBIFS_MST_DIRTY))) {
@@ -1569,7 +1583,7 @@
if (c->need_recovery)
err = ubifs_rcvry_gc_commit(c);
else
- err = take_gc_lnum(c);
+ err = ubifs_leb_unmap(c, c->gc_lnum);
if (err)
goto out;
@@ -1582,8 +1596,9 @@
c->vfs_sb->s_flags &= ~MS_RDONLY;
c->remounting_rw = 0;
c->always_chk_crc = 0;
+ err = dbg_check_space_info(c);
mutex_unlock(&c->umount_mutex);
- return 0;
+ return err;
out:
vfree(c->orph_buf);
@@ -1603,43 +1618,18 @@
}
/**
- * commit_on_unmount - commit the journal when un-mounting.
- * @c: UBIFS file-system description object
- *
- * This function is called during un-mounting and re-mounting, and it commits
- * the journal unless the "fast unmount" mode is enabled.
- */
-static void commit_on_unmount(struct ubifs_info *c)
-{
- struct super_block *sb = c->vfs_sb;
- long long bud_bytes;
-
- /*
- * This function is called before the background thread is stopped, so
- * we may race with ongoing commit, which means we have to take
- * @c->bud_lock to access @c->bud_bytes.
- */
- spin_lock(&c->buds_lock);
- bud_bytes = c->bud_bytes;
- spin_unlock(&c->buds_lock);
-
- if (!c->fast_unmount && !(sb->s_flags & MS_RDONLY) && bud_bytes)
- ubifs_run_commit(c);
-}
-
-/**
* ubifs_remount_ro - re-mount in read-only mode.
* @c: UBIFS file-system description object
*
- * We rely on VFS to have stopped writing. Possibly the background thread could
- * be running a commit, however kthread_stop will wait in that case.
+ * We assume VFS has stopped writing. Possibly the background thread could be
+ * running a commit, however kthread_stop will wait in that case.
*/
static void ubifs_remount_ro(struct ubifs_info *c)
{
int i, err;
ubifs_assert(!c->need_recovery);
- commit_on_unmount(c);
+ ubifs_assert(!(c->vfs_sb->s_flags & MS_RDONLY));
mutex_lock(&c->umount_mutex);
if (c->bgt) {
@@ -1647,27 +1637,29 @@
c->bgt = NULL;
}
+ dbg_save_space_info(c);
+
for (i = 0; i < c->jhead_cnt; i++) {
ubifs_wbuf_sync(&c->jheads[i].wbuf);
del_timer_sync(&c->jheads[i].wbuf.timer);
}
- if (!c->ro_media) {
- c->mst_node->flags &= ~cpu_to_le32(UBIFS_MST_DIRTY);
- c->mst_node->flags |= cpu_to_le32(UBIFS_MST_NO_ORPHS);
- c->mst_node->gc_lnum = cpu_to_le32(c->gc_lnum);
- err = ubifs_write_master(c);
- if (err)
- ubifs_ro_mode(c, err);
- }
+ c->mst_node->flags &= ~cpu_to_le32(UBIFS_MST_DIRTY);
+ c->mst_node->flags |= cpu_to_le32(UBIFS_MST_NO_ORPHS);
+ c->mst_node->gc_lnum = cpu_to_le32(c->gc_lnum);
+ err = ubifs_write_master(c);
+ if (err)
+ ubifs_ro_mode(c, err);
- ubifs_destroy_idx_gc(c);
free_wbufs(c);
vfree(c->orph_buf);
c->orph_buf = NULL;
vfree(c->ileb_buf);
c->ileb_buf = NULL;
ubifs_lpt_free(c, 1);
+ err = dbg_check_space_info(c);
+ if (err)
+ ubifs_ro_mode(c, err);
mutex_unlock(&c->umount_mutex);
}
@@ -1760,11 +1752,20 @@
}
if ((sb->s_flags & MS_RDONLY) && !(*flags & MS_RDONLY)) {
+ if (c->ro_media) {
+ ubifs_msg("cannot re-mount due to prior errors");
+ return -EROFS;
+ }
err = ubifs_remount_rw(c);
if (err)
return err;
- } else if (!(sb->s_flags & MS_RDONLY) && (*flags & MS_RDONLY))
+ } else if (!(sb->s_flags & MS_RDONLY) && (*flags & MS_RDONLY)) {
+ if (c->ro_media) {
+ ubifs_msg("cannot re-mount due to prior errors");
+ return -EROFS;
+ }
ubifs_remount_ro(c);
+ }
if (c->bulk_read == 1)
bu_init(c);
@@ -1774,10 +1775,11 @@
c->bu.buf = NULL;
}
+ ubifs_assert(c->lst.taken_empty_lebs == 1);
return 0;
}
-struct super_operations ubifs_super_operations = {
+const struct super_operations ubifs_super_operations = {
.alloc_inode = ubifs_alloc_inode,
.destroy_inode = ubifs_destroy_inode,
.put_super = ubifs_put_super,
@@ -2044,15 +2046,6 @@
static void ubifs_kill_sb(struct super_block *sb)
{
- struct ubifs_info *c = sb->s_fs_info;
-
- /*
- * We do 'commit_on_unmount()' here instead of 'ubifs_put_super()'
- * in order to be outside BKL.
- */
- if (sb->s_root)
- commit_on_unmount(c);
- /* The un-mount routine is actually done in put_super() */
generic_shutdown_super(sb);
}
diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c
index f7e36f5..fa28a84 100644
--- a/fs/ubifs/tnc.c
+++ b/fs/ubifs/tnc.c
@@ -443,6 +443,11 @@
* This function performs that same function as ubifs_read_node except that
* it does not require that there is actually a node present and instead
* the return code indicates if a node was read.
+ *
+ * Note, this function does not check CRC of data nodes if @c->no_chk_data_crc
+ * is true (it is controlled by corresponding mount option). However, if
+ * @c->always_chk_crc is true, @c->no_chk_data_crc is ignored and CRC is always
+ * checked.
*/
static int try_read_node(const struct ubifs_info *c, void *buf, int type,
int len, int lnum, int offs)
@@ -470,9 +475,8 @@
if (node_len != len)
return 0;
- if (type == UBIFS_DATA_NODE && !c->always_chk_crc)
- if (c->no_chk_data_crc)
- return 0;
+ if (type == UBIFS_DATA_NODE && !c->always_chk_crc && c->no_chk_data_crc)
+ return 1;
crc = crc32(UBIFS_CRC32_INIT, buf + 8, node_len - 8);
node_crc = le32_to_cpu(ch->crc);
@@ -1506,7 +1510,7 @@
*
* Note, if the bulk-read buffer length (@bu->buf_len) is known, this function
* makes sure bulk-read nodes fit the buffer. Otherwise, this function prepares
- * maxumum possible amount of nodes for bulk-read.
+ * maximum possible amount of nodes for bulk-read.
*/
int ubifs_tnc_get_bu_keys(struct ubifs_info *c, struct bu_info *bu)
{
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index fc2a4cc..039a68b 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -426,9 +426,9 @@
* LEB properties flags.
*
* LPROPS_UNCAT: not categorized
- * LPROPS_DIRTY: dirty > 0, not index
+ * LPROPS_DIRTY: dirty > free, dirty >= @c->dead_wm, not index
* LPROPS_DIRTY_IDX: dirty + free > @c->min_idx_node_sze and index
- * LPROPS_FREE: free > 0, not empty, not index
+ * LPROPS_FREE: free > 0, dirty < @c->dead_wm, not empty, not index
* LPROPS_HEAP_CNT: number of heaps used for storing categorized LEBs
* LPROPS_EMPTY: LEB is empty, not taken
* LPROPS_FREEABLE: free + dirty == leb_size, not index, not taken
@@ -961,7 +961,6 @@
* @cs_lock: commit state lock
* @cmt_wq: wait queue to sleep on if the log is full and a commit is running
*
- * @fast_unmount: do not run journal commit before un-mounting
* @big_lpt: flag that LPT is too big to write whole during commit
* @no_chk_data_crc: do not check CRCs when reading data nodes (except during
* recovery)
@@ -1202,7 +1201,6 @@
spinlock_t cs_lock;
wait_queue_head_t cmt_wq;
- unsigned int fast_unmount:1;
unsigned int big_lpt:1;
unsigned int no_chk_data_crc:1;
unsigned int bulk_read:1;
@@ -1405,13 +1403,13 @@
extern spinlock_t ubifs_infos_lock;
extern atomic_long_t ubifs_clean_zn_cnt;
extern struct kmem_cache *ubifs_inode_slab;
-extern struct super_operations ubifs_super_operations;
-extern struct address_space_operations ubifs_file_address_operations;
-extern struct file_operations ubifs_file_operations;
-extern struct inode_operations ubifs_file_inode_operations;
-extern struct file_operations ubifs_dir_operations;
-extern struct inode_operations ubifs_dir_inode_operations;
-extern struct inode_operations ubifs_symlink_inode_operations;
+extern const struct super_operations ubifs_super_operations;
+extern const struct address_space_operations ubifs_file_address_operations;
+extern const struct file_operations ubifs_file_operations;
+extern const struct inode_operations ubifs_file_inode_operations;
+extern const struct file_operations ubifs_dir_operations;
+extern const struct inode_operations ubifs_dir_inode_operations;
+extern const struct inode_operations ubifs_symlink_inode_operations;
extern struct backing_dev_info ubifs_backing_dev_info;
extern struct ubifs_compressor *ubifs_compressors[UBIFS_COMPR_TYPES_CNT];
@@ -1428,7 +1426,7 @@
int ubifs_write_node(struct ubifs_info *c, void *node, int len, int lnum,
int offs, int dtype);
int ubifs_check_node(const struct ubifs_info *c, const void *buf, int lnum,
- int offs, int quiet, int chk_crc);
+ int offs, int quiet, int must_chk_crc);
void ubifs_prepare_node(struct ubifs_info *c, void *buf, int len, int pad);
void ubifs_prep_grp_node(struct ubifs_info *c, void *node, int len, int last);
int ubifs_io_init(struct ubifs_info *c);
@@ -1495,6 +1493,7 @@
void ubifs_cancel_ino_op(struct ubifs_info *c, struct inode *inode,
struct ubifs_budget_req *req);
long long ubifs_get_free_space(struct ubifs_info *c);
+long long ubifs_get_free_space_nolock(struct ubifs_info *c);
int ubifs_calc_min_idx_lebs(struct ubifs_info *c);
void ubifs_convert_page_budget(struct ubifs_info *c);
long long ubifs_reported_space(const struct ubifs_info *c, long long free);
@@ -1603,6 +1602,7 @@
int ubifs_orphan_start_commit(struct ubifs_info *c);
int ubifs_orphan_end_commit(struct ubifs_info *c);
int ubifs_mount_orphans(struct ubifs_info *c, int unclean, int read_only);
+int ubifs_clear_orphans(struct ubifs_info *c);
/* lpt.c */
int ubifs_calc_lpt_geom(struct ubifs_info *c);
@@ -1646,7 +1646,7 @@
const struct ubifs_lprops *lp,
int free, int dirty, int flags,
int idx_gc_cnt);
-void ubifs_get_lp_stats(struct ubifs_info *c, struct ubifs_lp_stats *stats);
+void ubifs_get_lp_stats(struct ubifs_info *c, struct ubifs_lp_stats *lst);
void ubifs_add_to_cat(struct ubifs_info *c, struct ubifs_lprops *lprops,
int cat);
void ubifs_replace_cat(struct ubifs_info *c, struct ubifs_lprops *old_lprops,
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index 2ed0353..a608e72 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -371,7 +371,11 @@
/* flush inodes and push all remaining buffers out to disk */
xfs_quiesce_fs(mp);
- ASSERT_ALWAYS(atomic_read(&mp->m_active_trans) == 0);
+ /*
+ * Just warn here till VFS can correctly support
+ * read-only remount without racing.
+ */
+ WARN_ON(atomic_read(&mp->m_active_trans) != 0);
/* Push the superblock and write an unmount record */
error = xfs_log_sbcount(mp, 1);
diff --git a/fs/xfs/xfs_dfrag.c b/fs/xfs/xfs_dfrag.c
index b4c1ee7..f8278cf 100644
--- a/fs/xfs/xfs_dfrag.c
+++ b/fs/xfs/xfs_dfrag.c
@@ -55,17 +55,11 @@
struct file *file, *target_file;
int error = 0;
- sxp = kmem_alloc(sizeof(xfs_swapext_t), KM_MAYFAIL);
- if (!sxp) {
- error = XFS_ERROR(ENOMEM);
- goto out;
- }
-
/* Pull information for the target fd */
file = fget((int)sxp->sx_fdtarget);
if (!file) {
error = XFS_ERROR(EINVAL);
- goto out_free_sxp;
+ goto out;
}
if (!(file->f_mode & FMODE_WRITE) || (file->f_flags & O_APPEND)) {
@@ -109,8 +103,6 @@
fput(target_file);
out_put_file:
fput(file);
- out_free_sxp:
- kmem_free(sxp);
out:
return error;
}
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 35cca98..b1047de 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -70,16 +70,21 @@
xfs_buf_t *
xlog_get_bp(
xlog_t *log,
- int num_bblks)
+ int nbblks)
{
- ASSERT(num_bblks > 0);
+ if (nbblks <= 0 || nbblks > log->l_logBBsize) {
+ xlog_warn("XFS: Invalid block length (0x%x) given for buffer", nbblks);
+ XFS_ERROR_REPORT("xlog_get_bp(1)",
+ XFS_ERRLEVEL_HIGH, log->l_mp);
+ return NULL;
+ }
if (log->l_sectbb_log) {
- if (num_bblks > 1)
- num_bblks += XLOG_SECTOR_ROUNDUP_BBCOUNT(log, 1);
- num_bblks = XLOG_SECTOR_ROUNDUP_BBCOUNT(log, num_bblks);
+ if (nbblks > 1)
+ nbblks += XLOG_SECTOR_ROUNDUP_BBCOUNT(log, 1);
+ nbblks = XLOG_SECTOR_ROUNDUP_BBCOUNT(log, nbblks);
}
- return xfs_buf_get_noaddr(BBTOB(num_bblks), log->l_mp->m_logdev_targp);
+ return xfs_buf_get_noaddr(BBTOB(nbblks), log->l_mp->m_logdev_targp);
}
void
@@ -102,6 +107,13 @@
{
int error;
+ if (nbblks <= 0 || nbblks > log->l_logBBsize) {
+ xlog_warn("XFS: Invalid block length (0x%x) given for buffer", nbblks);
+ XFS_ERROR_REPORT("xlog_bread(1)",
+ XFS_ERRLEVEL_HIGH, log->l_mp);
+ return EFSCORRUPTED;
+ }
+
if (log->l_sectbb_log) {
blk_no = XLOG_SECTOR_ROUNDDOWN_BLKNO(log, blk_no);
nbblks = XLOG_SECTOR_ROUNDUP_BBCOUNT(log, nbblks);
@@ -139,6 +151,13 @@
{
int error;
+ if (nbblks <= 0 || nbblks > log->l_logBBsize) {
+ xlog_warn("XFS: Invalid block length (0x%x) given for buffer", nbblks);
+ XFS_ERROR_REPORT("xlog_bwrite(1)",
+ XFS_ERRLEVEL_HIGH, log->l_mp);
+ return EFSCORRUPTED;
+ }
+
if (log->l_sectbb_log) {
blk_no = XLOG_SECTOR_ROUNDDOWN_BLKNO(log, blk_no);
nbblks = XLOG_SECTOR_ROUNDUP_BBCOUNT(log, nbblks);
diff --git a/include/acpi/pdc_intel.h b/include/acpi/pdc_intel.h
index e72bfdd..552637b 100644
--- a/include/acpi/pdc_intel.h
+++ b/include/acpi/pdc_intel.h
@@ -14,6 +14,7 @@
#define ACPI_PDC_SMP_T_SWCOORD (0x0080)
#define ACPI_PDC_C_C1_FFH (0x0100)
#define ACPI_PDC_C_C2C3_FFH (0x0200)
+#define ACPI_PDC_SMP_P_HWCOORD (0x0800)
#define ACPI_PDC_EST_CAPABILITY_SMP (ACPI_PDC_SMP_C1PT | \
ACPI_PDC_C_C1_HALT | \
@@ -22,6 +23,7 @@
#define ACPI_PDC_EST_CAPABILITY_SWSMP (ACPI_PDC_SMP_C1PT | \
ACPI_PDC_C_C1_HALT | \
ACPI_PDC_SMP_P_SWCOORD | \
+ ACPI_PDC_SMP_P_HWCOORD | \
ACPI_PDC_P_FFH)
#define ACPI_PDC_C_CAPABILITY_SMP (ACPI_PDC_SMP_C2C3 | \
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index b0e63c6..00f45ff 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -80,4 +80,56 @@
#define DECLARE_PER_CPU(type, name) extern PER_CPU_ATTRIBUTES \
__typeof__(type) per_cpu_var(name)
+/*
+ * Optional methods for optimized non-lvalue per-cpu variable access.
+ *
+ * @var can be a percpu variable or a field of it and its size should
+ * equal char, int or long. percpu_read() evaluates to a lvalue and
+ * all others to void.
+ *
+ * These operations are guaranteed to be atomic w.r.t. preemption.
+ * The generic versions use plain get/put_cpu_var(). Archs are
+ * encouraged to implement single-instruction alternatives which don't
+ * require preemption protection.
+ */
+#ifndef percpu_read
+# define percpu_read(var) \
+ ({ \
+ typeof(per_cpu_var(var)) __tmp_var__; \
+ __tmp_var__ = get_cpu_var(var); \
+ put_cpu_var(var); \
+ __tmp_var__; \
+ })
+#endif
+
+#define __percpu_generic_to_op(var, val, op) \
+do { \
+ get_cpu_var(var) op val; \
+ put_cpu_var(var); \
+} while (0)
+
+#ifndef percpu_write
+# define percpu_write(var, val) __percpu_generic_to_op(var, (val), =)
+#endif
+
+#ifndef percpu_add
+# define percpu_add(var, val) __percpu_generic_to_op(var, (val), +=)
+#endif
+
+#ifndef percpu_sub
+# define percpu_sub(var, val) __percpu_generic_to_op(var, (val), -=)
+#endif
+
+#ifndef percpu_and
+# define percpu_and(var, val) __percpu_generic_to_op(var, (val), &=)
+#endif
+
+#ifndef percpu_or
+# define percpu_or(var, val) __percpu_generic_to_op(var, (val), |=)
+#endif
+
+#ifndef percpu_xor
+# define percpu_xor(var, val) __percpu_generic_to_op(var, (val), ^=)
+#endif
+
#endif /* _ASM_GENERIC_PERCPU_H_ */
diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index 79a7ff9..4ce48e8 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -9,7 +9,7 @@
extern char __init_begin[], __init_end[];
extern char _sinittext[], _einittext[];
extern char _end[];
-extern char __per_cpu_start[], __per_cpu_end[];
+extern char __per_cpu_load[], __per_cpu_start[], __per_cpu_end[];
extern char __kprobes_text_start[], __kprobes_text_end[];
extern char __initdata_begin[], __initdata_end[];
extern char __start_rodata[], __end_rodata[];
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index c61fab1..5406e70 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -430,12 +430,59 @@
*(.initcall7.init) \
*(.initcall7s.init)
-#define PERCPU(align) \
- . = ALIGN(align); \
- VMLINUX_SYMBOL(__per_cpu_start) = .; \
- .data.percpu : AT(ADDR(.data.percpu) - LOAD_OFFSET) { \
+/**
+ * PERCPU_VADDR - define output section for percpu area
+ * @vaddr: explicit base address (optional)
+ * @phdr: destination PHDR (optional)
+ *
+ * Macro which expands to output section for percpu area. If @vaddr
+ * is not blank, it specifies explicit base address and all percpu
+ * symbols will be offset from the given address. If blank, @vaddr
+ * always equals @laddr + LOAD_OFFSET.
+ *
+ * @phdr defines the output PHDR to use if not blank. Be warned that
+ * output PHDR is sticky. If @phdr is specified, the next output
+ * section in the linker script will go there too. @phdr should have
+ * a leading colon.
+ *
+ * Note that this macros defines __per_cpu_load as an absolute symbol.
+ * If there is no need to put the percpu section at a predetermined
+ * address, use PERCPU().
+ */
+#define PERCPU_VADDR(vaddr, phdr) \
+ VMLINUX_SYMBOL(__per_cpu_load) = .; \
+ .data.percpu vaddr : AT(VMLINUX_SYMBOL(__per_cpu_load) \
+ - LOAD_OFFSET) { \
+ VMLINUX_SYMBOL(__per_cpu_start) = .; \
+ *(.data.percpu.first) \
*(.data.percpu.page_aligned) \
*(.data.percpu) \
*(.data.percpu.shared_aligned) \
- } \
- VMLINUX_SYMBOL(__per_cpu_end) = .;
+ VMLINUX_SYMBOL(__per_cpu_end) = .; \
+ } phdr \
+ . = VMLINUX_SYMBOL(__per_cpu_load) + SIZEOF(.data.percpu);
+
+/**
+ * PERCPU - define output section for percpu area, simple version
+ * @align: required alignment
+ *
+ * Align to @align and outputs output section for percpu area. This
+ * macro doesn't maniuplate @vaddr or @phdr and __per_cpu_load and
+ * __per_cpu_start will be identical.
+ *
+ * This macro is equivalent to ALIGN(align); PERCPU_VADDR( , ) except
+ * that __per_cpu_load is defined as a relative symbol against
+ * .data.percpu which is required for relocatable x86_32
+ * configuration.
+ */
+#define PERCPU(align) \
+ . = ALIGN(align); \
+ .data.percpu : AT(ADDR(.data.percpu) - LOAD_OFFSET) { \
+ VMLINUX_SYMBOL(__per_cpu_load) = .; \
+ VMLINUX_SYMBOL(__per_cpu_start) = .; \
+ *(.data.percpu.first) \
+ *(.data.percpu.page_aligned) \
+ *(.data.percpu) \
+ *(.data.percpu.shared_aligned) \
+ VMLINUX_SYMBOL(__per_cpu_end) = .; \
+ }
diff --git a/include/linux/Kbuild b/include/linux/Kbuild
index 2124c06..b97cdc5 100644
--- a/include/linux/Kbuild
+++ b/include/linux/Kbuild
@@ -90,7 +90,6 @@
header-y += if_slip.h
header-y += if_strip.h
header-y += if_tun.h
-header-y += if_tunnel.h
header-y += in_route.h
header-y += ioctl.h
header-y += ip6_tunnel.h
@@ -236,6 +235,7 @@
unifdef-y += if_pppol2tp.h
unifdef-y += if_pppox.h
unifdef-y += if_tr.h
+unifdef-y += if_tunnel.h
unifdef-y += if_vlan.h
unifdef-y += igmp.h
unifdef-y += inet_diag.h
diff --git a/include/linux/async.h b/include/linux/async.h
index c4ecacd..68a9530 100644
--- a/include/linux/async.h
+++ b/include/linux/async.h
@@ -17,9 +17,11 @@
typedef void (async_func_ptr) (void *data, async_cookie_t cookie);
extern async_cookie_t async_schedule(async_func_ptr *ptr, void *data);
-extern async_cookie_t async_schedule_special(async_func_ptr *ptr, void *data, struct list_head *list);
+extern async_cookie_t async_schedule_domain(async_func_ptr *ptr, void *data,
+ struct list_head *list);
extern void async_synchronize_full(void);
-extern void async_synchronize_full_special(struct list_head *list);
+extern void async_synchronize_full_domain(struct list_head *list);
extern void async_synchronize_cookie(async_cookie_t cookie);
-extern void async_synchronize_cookie_special(async_cookie_t cookie, struct list_head *list);
+extern void async_synchronize_cookie_domain(async_cookie_t cookie,
+ struct list_head *list);
diff --git a/include/linux/ata.h b/include/linux/ata.h
index a53318b..08a86d5 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -731,12 +731,17 @@
static inline int ata_id_is_cfa(const u16 *id)
{
- if (id[ATA_ID_CONFIG] == 0x848A) /* Standard CF */
+ if (id[ATA_ID_CONFIG] == 0x848A) /* Traditional CF */
return 1;
- /* Could be CF hiding as standard ATA */
- if (ata_id_major_version(id) >= 3 &&
- id[ATA_ID_COMMAND_SET_1] != 0xFFFF &&
- (id[ATA_ID_COMMAND_SET_1] & (1 << 2)))
+ /*
+ * CF specs don't require specific value in the word 0 anymore and yet
+ * they forbid to report the ATA version in the word 80 and require the
+ * CFA feature set support to be indicated in the word 83 in this case.
+ * Unfortunately, some cards only follow either of this requirements,
+ * and while those that don't indicate CFA feature support need some
+ * sort of quirk list, it seems impractical for the ones that do...
+ */
+ if ((id[ATA_ID_COMMAND_SET_2] & 0xC004) == 0x4004)
return 1;
return 0;
}
diff --git a/include/linux/fb.h b/include/linux/fb.h
index 818fe21..31527e1 100644
--- a/include/linux/fb.h
+++ b/include/linux/fb.h
@@ -960,6 +960,21 @@
extern int num_registered_fb;
extern struct class *fb_class;
+static inline int lock_fb_info(struct fb_info *info)
+{
+ mutex_lock(&info->lock);
+ if (!info->fbops) {
+ mutex_unlock(&info->lock);
+ return 0;
+ }
+ return 1;
+}
+
+static inline void unlock_fb_info(struct fb_info *info)
+{
+ mutex_unlock(&info->lock);
+}
+
static inline void __fb_pad_aligned_buffer(u8 *dst, u32 d_pitch,
u8 *src, u32 s_pitch, u32 height)
{
diff --git a/include/linux/if_tunnel.h b/include/linux/if_tunnel.h
index aeab2cb..82c43624 100644
--- a/include/linux/if_tunnel.h
+++ b/include/linux/if_tunnel.h
@@ -2,7 +2,10 @@
#define _IF_TUNNEL_H_
#include <linux/types.h>
+
+#ifdef __KERNEL__
#include <linux/ip.h>
+#endif
#define SIOCGETTUNNEL (SIOCDEVPRIVATE + 0)
#define SIOCADDTUNNEL (SIOCDEVPRIVATE + 1)
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 9127f6b..472f117 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -467,6 +467,7 @@
struct irq_desc;
extern int early_irq_init(void);
+extern int arch_probe_nr_irqs(void);
extern int arch_early_irq_init(void);
extern int arch_init_chip_data(struct irq_desc *desc, int cpu);
diff --git a/include/linux/irq.h b/include/linux/irq.h
index f899b50..27a6753 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -182,11 +182,11 @@
unsigned int irqs_unhandled;
spinlock_t lock;
#ifdef CONFIG_SMP
- cpumask_t affinity;
+ cpumask_var_t affinity;
unsigned int cpu;
-#endif
#ifdef CONFIG_GENERIC_PENDING_IRQ
- cpumask_t pending_mask;
+ cpumask_var_t pending_mask;
+#endif
#endif
#ifdef CONFIG_PROC_FS
struct proc_dir_entry *dir;
@@ -422,4 +422,84 @@
#endif /* !CONFIG_S390 */
+#ifdef CONFIG_SMP
+/**
+ * init_alloc_desc_masks - allocate cpumasks for irq_desc
+ * @desc: pointer to irq_desc struct
+ * @cpu: cpu which will be handling the cpumasks
+ * @boot: true if need bootmem
+ *
+ * Allocates affinity and pending_mask cpumask if required.
+ * Returns true if successful (or not required).
+ * Side effect: affinity has all bits set, pending_mask has all bits clear.
+ */
+static inline bool init_alloc_desc_masks(struct irq_desc *desc, int cpu,
+ bool boot)
+{
+ int node;
+
+ if (boot) {
+ alloc_bootmem_cpumask_var(&desc->affinity);
+ cpumask_setall(desc->affinity);
+
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+ alloc_bootmem_cpumask_var(&desc->pending_mask);
+ cpumask_clear(desc->pending_mask);
+#endif
+ return true;
+ }
+
+ node = cpu_to_node(cpu);
+
+ if (!alloc_cpumask_var_node(&desc->affinity, GFP_ATOMIC, node))
+ return false;
+ cpumask_setall(desc->affinity);
+
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+ if (!alloc_cpumask_var_node(&desc->pending_mask, GFP_ATOMIC, node)) {
+ free_cpumask_var(desc->affinity);
+ return false;
+ }
+ cpumask_clear(desc->pending_mask);
+#endif
+ return true;
+}
+
+/**
+ * init_copy_desc_masks - copy cpumasks for irq_desc
+ * @old_desc: pointer to old irq_desc struct
+ * @new_desc: pointer to new irq_desc struct
+ *
+ * Insures affinity and pending_masks are copied to new irq_desc.
+ * If !CONFIG_CPUMASKS_OFFSTACK the cpumasks are embedded in the
+ * irq_desc struct so the copy is redundant.
+ */
+
+static inline void init_copy_desc_masks(struct irq_desc *old_desc,
+ struct irq_desc *new_desc)
+{
+#ifdef CONFIG_CPUMASKS_OFFSTACK
+ cpumask_copy(new_desc->affinity, old_desc->affinity);
+
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+ cpumask_copy(new_desc->pending_mask, old_desc->pending_mask);
+#endif
+#endif
+}
+
+#else /* !CONFIG_SMP */
+
+static inline bool init_alloc_desc_masks(struct irq_desc *desc, int cpu,
+ bool boot)
+{
+ return true;
+}
+
+static inline void init_copy_desc_masks(struct irq_desc *old_desc,
+ struct irq_desc *new_desc)
+{
+}
+
+#endif /* CONFIG_SMP */
+
#endif /* _LINUX_IRQ_H */
diff --git a/include/linux/irqnr.h b/include/linux/irqnr.h
index 86af92e..887477b 100644
--- a/include/linux/irqnr.h
+++ b/include/linux/irqnr.h
@@ -20,6 +20,7 @@
# define for_each_irq_desc_reverse(irq, desc) \
for (irq = nr_irqs - 1; irq >= 0; irq--)
+
#else /* CONFIG_GENERIC_HARDIRQS */
extern int nr_irqs;
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 343df9e..7fa3718 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -480,7 +480,8 @@
/*
* swap - swap value of @a and @b
*/
-#define swap(a, b) ({ typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; })
+#define swap(a, b) \
+ do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
/**
* container_of - cast a member of a structure out to the containing structure
diff --git a/include/linux/libata.h b/include/linux/libata.h
index bca3ba2..5d87bc0 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -380,6 +380,7 @@
ATA_HORKAGE_ATAPI_MOD16_DMA = (1 << 11), /* use ATAPI DMA for commands
not multiple of 16 bytes */
ATA_HORKAGE_FIRMWARE_WARN = (1 << 12), /* firwmare update warning */
+ ATA_HORKAGE_1_5_GBPS = (1 << 13), /* force 1.5 Gbps */
/* DMA mask for user DMA control: User visible values; DO NOT
renumber */
@@ -580,7 +581,7 @@
acpi_handle acpi_handle;
union acpi_object *gtf_cache;
#endif
- /* n_sector is used as CLEAR_OFFSET, read comment above CLEAR_OFFSET */
+ /* n_sector is CLEAR_BEGIN, read comment above CLEAR_BEGIN */
u64 n_sectors; /* size of device, if ATA */
unsigned int class; /* ATA_DEV_xxx */
unsigned long unpark_deadline;
@@ -605,20 +606,22 @@
u16 heads; /* Number of heads */
u16 sectors; /* Number of sectors per track */
- /* error history */
- int spdn_cnt;
- struct ata_ering ering;
-
union {
u16 id[ATA_ID_WORDS]; /* IDENTIFY xxx DEVICE data */
u32 gscr[SATA_PMP_GSCR_DWORDS]; /* PMP GSCR block */
};
+
+ /* error history */
+ int spdn_cnt;
+ /* ering is CLEAR_END, read comment above CLEAR_END */
+ struct ata_ering ering;
};
-/* Offset into struct ata_device. Fields above it are maintained
- * acress device init. Fields below are zeroed.
+/* Fields between ATA_DEVICE_CLEAR_BEGIN and ATA_DEVICE_CLEAR_END are
+ * cleared to zero on ata_dev_init().
*/
-#define ATA_DEVICE_CLEAR_OFFSET offsetof(struct ata_device, n_sectors)
+#define ATA_DEVICE_CLEAR_BEGIN offsetof(struct ata_device, n_sectors)
+#define ATA_DEVICE_CLEAR_END offsetof(struct ata_device, ering)
struct ata_eh_info {
struct ata_device *dev; /* offending device */
diff --git a/include/linux/magic.h b/include/linux/magic.h
index 0b4df7e..5b4e28b 100644
--- a/include/linux/magic.h
+++ b/include/linux/magic.h
@@ -49,4 +49,5 @@
#define FUTEXFS_SUPER_MAGIC 0xBAD1DEA
#define INOTIFYFS_SUPER_MAGIC 0x2BAD1DEA
+#define STACK_END_MAGIC 0x57AC6E9D
#endif /* __LINUX_MAGIC_H__ */
diff --git a/include/linux/module.h b/include/linux/module.h
index f3b8329..145a755 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -407,7 +407,6 @@
static inline void __module_get(struct module *module)
{
if (module) {
- BUG_ON(module_refcount(module) == 0);
local_inc(__module_ref_addr(module, get_cpu()));
put_cpu();
}
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 48890cf..7bd624b 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -684,7 +684,7 @@
void pci_disable_rom(struct pci_dev *pdev);
void __iomem __must_check *pci_map_rom(struct pci_dev *pdev, size_t *size);
void pci_unmap_rom(struct pci_dev *pdev, void __iomem *rom);
-size_t pci_get_rom_size(void __iomem *rom, size_t size);
+size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size);
/* Power management related routines */
int pci_save_state(struct pci_dev *dev);
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 9f2a375..3577ffd 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -8,35 +8,46 @@
#include <asm/percpu.h>
+#ifndef PER_CPU_BASE_SECTION
#ifdef CONFIG_SMP
-#define DEFINE_PER_CPU(type, name) \
- __attribute__((__section__(".data.percpu"))) \
- PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
+#define PER_CPU_BASE_SECTION ".data.percpu"
+#else
+#define PER_CPU_BASE_SECTION ".data"
+#endif
+#endif
+
+#ifdef CONFIG_SMP
#ifdef MODULE
-#define SHARED_ALIGNED_SECTION ".data.percpu"
+#define PER_CPU_SHARED_ALIGNED_SECTION ""
#else
-#define SHARED_ALIGNED_SECTION ".data.percpu.shared_aligned"
+#define PER_CPU_SHARED_ALIGNED_SECTION ".shared_aligned"
#endif
+#define PER_CPU_FIRST_SECTION ".first"
+
+#else
+
+#define PER_CPU_SHARED_ALIGNED_SECTION ""
+#define PER_CPU_FIRST_SECTION ""
+
+#endif
+
+#define DEFINE_PER_CPU_SECTION(type, name, section) \
+ __attribute__((__section__(PER_CPU_BASE_SECTION section))) \
+ PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
+
+#define DEFINE_PER_CPU(type, name) \
+ DEFINE_PER_CPU_SECTION(type, name, "")
#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name) \
- __attribute__((__section__(SHARED_ALIGNED_SECTION))) \
- PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name \
+ DEFINE_PER_CPU_SECTION(type, name, PER_CPU_SHARED_ALIGNED_SECTION) \
____cacheline_aligned_in_smp
-#define DEFINE_PER_CPU_PAGE_ALIGNED(type, name) \
- __attribute__((__section__(".data.percpu.page_aligned"))) \
- PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
-#else
-#define DEFINE_PER_CPU(type, name) \
- PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
+#define DEFINE_PER_CPU_PAGE_ALIGNED(type, name) \
+ DEFINE_PER_CPU_SECTION(type, name, ".page_aligned")
-#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name) \
- DEFINE_PER_CPU(type, name)
-
-#define DEFINE_PER_CPU_PAGE_ALIGNED(type, name) \
- DEFINE_PER_CPU(type, name)
-#endif
+#define DEFINE_PER_CPU_FIRST(type, name) \
+ DEFINE_PER_CPU_SECTION(type, name, PER_CPU_FIRST_SECTION)
#define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var)
#define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5a7c763..28b3f50 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -443,6 +443,7 @@
* @utime: time spent in user mode, in &cputime_t units
* @stime: time spent in kernel mode, in &cputime_t units
* @sum_exec_runtime: total time spent on the CPU, in nanoseconds
+ * @lock: lock for fields in this struct
*
* This structure groups together three kinds of CPU time that are
* tracked for threads and thread groups. Most things considering
@@ -1160,10 +1161,9 @@
pid_t pid;
pid_t tgid;
-#ifdef CONFIG_CC_STACKPROTECTOR
/* Canary value for the -fstack-protector gcc feature */
unsigned long stack_canary;
-#endif
+
/*
* pointers to (original) parent process, youngest child, younger sibling,
* older sibling, respectively. (p->father can be replaced with
@@ -2069,6 +2069,19 @@
extern void thread_info_cache_init(void);
+#ifdef CONFIG_DEBUG_STACK_USAGE
+static inline unsigned long stack_not_used(struct task_struct *p)
+{
+ unsigned long *n = end_of_stack(p);
+
+ do { /* Skip over canary */
+ n++;
+ } while (!*n);
+
+ return (unsigned long)n - (unsigned long)end_of_stack(p);
+}
+#endif
+
/* set thread flags in other task's structures
* - see asm/thread_info.h for TIF_xxxx flags available
*/
diff --git a/include/linux/stackprotector.h b/include/linux/stackprotector.h
new file mode 100644
index 0000000..6f3e54c
--- /dev/null
+++ b/include/linux/stackprotector.h
@@ -0,0 +1,16 @@
+#ifndef _LINUX_STACKPROTECTOR_H
+#define _LINUX_STACKPROTECTOR_H 1
+
+#include <linux/compiler.h>
+#include <linux/sched.h>
+#include <linux/random.h>
+
+#ifdef CONFIG_CC_STACKPROTECTOR
+# include <asm/stackprotector.h>
+#else
+static inline void boot_init_stack_canary(void)
+{
+}
+#endif
+
+#endif
diff --git a/include/linux/topology.h b/include/linux/topology.h
index e632d29..a16b9e0 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -193,5 +193,11 @@
#ifndef topology_core_siblings
#define topology_core_siblings(cpu) cpumask_of_cpu(cpu)
#endif
+#ifndef topology_thread_cpumask
+#define topology_thread_cpumask(cpu) cpumask_of(cpu)
+#endif
+#ifndef topology_core_cpumask
+#define topology_core_cpumask(cpu) cpumask_of(cpu)
+#endif
#endif /* _LINUX_TOPOLOGY_H */
diff --git a/include/linux/wait.h b/include/linux/wait.h
index ef609f8..a210ede 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -132,6 +132,8 @@
list_del(&old->task_list);
}
+void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
+ int nr_exclusive, int sync, void *key);
void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
extern void __wake_up_locked(wait_queue_head_t *q, unsigned int mode);
extern void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr);
@@ -333,16 +335,19 @@
for (;;) { \
prepare_to_wait_exclusive(&wq, &__wait, \
TASK_INTERRUPTIBLE); \
- if (condition) \
+ if (condition) { \
+ finish_wait(&wq, &__wait); \
break; \
+ } \
if (!signal_pending(current)) { \
schedule(); \
continue; \
} \
ret = -ERESTARTSYS; \
+ abort_exclusive_wait(&wq, &__wait, \
+ TASK_INTERRUPTIBLE, NULL); \
break; \
} \
- finish_wait(&wq, &__wait); \
} while (0)
#define wait_event_interruptible_exclusive(wq, condition) \
@@ -431,6 +436,8 @@
void prepare_to_wait(wait_queue_head_t *q, wait_queue_t *wait, int state);
void prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state);
void finish_wait(wait_queue_head_t *q, wait_queue_t *wait);
+void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait,
+ unsigned int mode, void *key);
int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
diff --git a/include/video/aty128.h b/include/video/aty128.h
index 7079beb..51ac69f 100644
--- a/include/video/aty128.h
+++ b/include/video/aty128.h
@@ -21,9 +21,9 @@
#define I2C_CNTL_1 0x0094
#define PALETTE_INDEX 0x00b0
#define PALETTE_DATA 0x00b4
-#define CONFIG_CNTL 0x00e0
+#define CNFG_CNTL 0x00e0
#define GEN_RESET_CNTL 0x00f0
-#define CONFIG_MEMSIZE 0x00f8
+#define CNFG_MEMSIZE 0x00f8
#define MEM_CNTL 0x0140
#define MEM_POWER_MISC 0x015c
#define AGP_BASE 0x0170
diff --git a/include/video/mach64.h b/include/video/mach64.h
index a8332e5..89e91c0 100644
--- a/include/video/mach64.h
+++ b/include/video/mach64.h
@@ -103,7 +103,7 @@
#define CUR_HORZ_VERT_OFF 0x0070 /* Dword offset 0_1C */
#define CUR2_HORZ_VERT_OFF 0x0070 /* Dword offset 0_1C */
-#define CONFIG_PANEL_LG 0x0074 /* Dword offset 0_1D (LG) */
+#define CNFG_PANEL_LG 0x0074 /* Dword offset 0_1D (LG) */
/* General I/O Control */
#define GP_IO 0x0078 /* Dword offset 0_1E */
@@ -146,8 +146,8 @@
#define CLOCK_SEL_CNTL 0x0090 /* Dword offset 0_24 */
/* Configuration */
-#define CONFIG_STAT1 0x0094 /* Dword offset 0_25 */
-#define CONFIG_STAT2 0x0098 /* Dword offset 0_26 */
+#define CNFG_STAT1 0x0094 /* Dword offset 0_25 */
+#define CNFG_STAT2 0x0098 /* Dword offset 0_26 */
/* Bus Control */
#define BUS_CNTL 0x00A0 /* Dword offset 0_28 */
@@ -190,9 +190,9 @@
#define POWER_MANAGEMENT_LG 0x00D8 /* Dword offset 0_36 (LG) */
/* Configuration */
-#define CONFIG_CNTL 0x00DC /* Dword offset 0_37 (CT, ET, VT) */
-#define CONFIG_CHIP_ID 0x00E0 /* Dword offset 0_38 */
-#define CONFIG_STAT0 0x00E4 /* Dword offset 0_39 */
+#define CNFG_CNTL 0x00DC /* Dword offset 0_37 (CT, ET, VT) */
+#define CNFG_CHIP_ID 0x00E0 /* Dword offset 0_38 */
+#define CNFG_STAT0 0x00E4 /* Dword offset 0_39 */
/* Test and Debug */
#define CRC_SIG 0x00E8 /* Dword offset 0_3A */
@@ -851,17 +851,17 @@
#define PLL_YCLK_CNTL 0x29
#define PM_DYN_CLK_CNTL 0x2A
-/* CONFIG_CNTL register constants */
+/* CNFG_CNTL register constants */
#define APERTURE_4M_ENABLE 1
#define APERTURE_8M_ENABLE 2
#define VGA_APERTURE_ENABLE 4
-/* CONFIG_STAT0 register constants (GX, CX) */
+/* CNFG_STAT0 register constants (GX, CX) */
#define CFG_BUS_TYPE 0x00000007
#define CFG_MEM_TYPE 0x00000038
#define CFG_INIT_DAC_TYPE 0x00000e00
-/* CONFIG_STAT0 register constants (CT, ET, VT) */
+/* CNFG_STAT0 register constants (CT, ET, VT) */
#define CFG_MEM_TYPE_xT 0x00000007
#define ISA 0
@@ -942,7 +942,7 @@
#define PCI_ATI_VENDOR_ID 0x1002
-/* CONFIG_CHIP_ID register constants */
+/* CNFG_CHIP_ID register constants */
#define CFG_CHIP_TYPE 0x0000FFFF
#define CFG_CHIP_CLASS 0x00FF0000
#define CFG_CHIP_REV 0xFF000000
@@ -951,7 +951,7 @@
#define CFG_CHIP_MINOR 0xC0000000
-/* Chip IDs read from CONFIG_CHIP_ID */
+/* Chip IDs read from CNFG_CHIP_ID */
/* mach64GX family */
#define GX_CHIP_ID 0xD7 /* mach64GX (ATI888GX00) */
@@ -1254,7 +1254,7 @@
#define CRTC2_DISPLAY_DIS 0x00000400
/* LCD register indices */
-#define CONFIG_PANEL 0x00
+#define CNFG_PANEL 0x00
#define LCD_GEN_CNTL 0x01
#define DSTN_CONTROL 0x02
#define HFB_PITCH_ADDR 0x03
diff --git a/include/video/radeon.h b/include/video/radeon.h
index 1cd09cc..e072b16 100644
--- a/include/video/radeon.h
+++ b/include/video/radeon.h
@@ -11,13 +11,13 @@
#define HI_STAT 0x004C
#define BUS_CNTL1 0x0034
#define I2C_CNTL_1 0x0094
-#define CONFIG_CNTL 0x00E0
-#define CONFIG_MEMSIZE 0x00F8
-#define CONFIG_APER_0_BASE 0x0100
-#define CONFIG_APER_1_BASE 0x0104
-#define CONFIG_APER_SIZE 0x0108
-#define CONFIG_REG_1_BASE 0x010C
-#define CONFIG_REG_APER_SIZE 0x0110
+#define CNFG_CNTL 0x00E0
+#define CNFG_MEMSIZE 0x00F8
+#define CNFG_APER_0_BASE 0x0100
+#define CNFG_APER_1_BASE 0x0104
+#define CNFG_APER_SIZE 0x0108
+#define CNFG_REG_1_BASE 0x010C
+#define CNFG_REG_APER_SIZE 0x0110
#define PAD_AGPINPUT_DELAY 0x0164
#define PAD_CTLR_STRENGTH 0x0168
#define PAD_CTLR_UPDATE 0x016C
@@ -509,7 +509,7 @@
/* CLOCK_CNTL_INDEX bit constants */
#define PLL_WR_EN 0x00000080
-/* CONFIG_CNTL bit constants */
+/* CNFG_CNTL bit constants */
#define CFG_VGA_RAM_EN 0x00000100
#define CFG_ATI_REV_ID_MASK (0xf << 16)
#define CFG_ATI_REV_A11 (0 << 16)
@@ -980,7 +980,7 @@
/* masks */
-#define CONFIG_MEMSIZE_MASK 0x1f000000
+#define CNFG_MEMSIZE_MASK 0x1f000000
#define MEM_CFG_TYPE 0x40000000
#define DST_OFFSET_MASK 0x003fffff
#define DST_PITCH_MASK 0x3fc00000
diff --git a/init/main.c b/init/main.c
index 8442094..bfe4fb0 100644
--- a/init/main.c
+++ b/init/main.c
@@ -14,6 +14,7 @@
#include <linux/proc_fs.h>
#include <linux/kernel.h>
#include <linux/syscalls.h>
+#include <linux/stackprotector.h>
#include <linux/string.h>
#include <linux/ctype.h>
#include <linux/delay.h>
@@ -539,6 +540,12 @@
*/
lockdep_init();
debug_objects_early_init();
+
+ /*
+ * Set up the the initial canary ASAP:
+ */
+ boot_init_stack_canary();
+
cgroup_init_early();
local_irq_disable();
diff --git a/ipc/shm.c b/ipc/shm.c
index c0a021f..f8f69fa 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -565,11 +565,15 @@
struct hstate *h = hstate_file(shp->shm_file);
*rss += pages_per_huge_page(h) * mapping->nrpages;
} else {
+#ifdef CONFIG_SHMEM
struct shmem_inode_info *info = SHMEM_I(inode);
spin_lock(&info->lock);
*rss += inode->i_mapping->nrpages;
*swp += info->swapped;
spin_unlock(&info->lock);
+#else
+ *rss += inode->i_mapping->nrpages;
+#endif
}
total++;
diff --git a/kernel/async.c b/kernel/async.c
index 608b32b..f565891 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -54,6 +54,7 @@
#include <linux/sched.h>
#include <linux/init.h>
#include <linux/kthread.h>
+#include <linux/delay.h>
#include <asm/atomic.h>
static async_cookie_t next_cookie = 1;
@@ -132,21 +133,23 @@
entry = list_first_entry(&async_pending, struct async_entry, list);
/* 2) move it to the running queue */
- list_del(&entry->list);
- list_add_tail(&entry->list, &async_running);
+ list_move_tail(&entry->list, entry->running);
spin_unlock_irqrestore(&async_lock, flags);
/* 3) run it (and print duration)*/
if (initcall_debug && system_state == SYSTEM_BOOTING) {
- printk("calling %lli_%pF @ %i\n", entry->cookie, entry->func, task_pid_nr(current));
+ printk("calling %lli_%pF @ %i\n", (long long)entry->cookie,
+ entry->func, task_pid_nr(current));
calltime = ktime_get();
}
entry->func(entry->data, entry->cookie);
if (initcall_debug && system_state == SYSTEM_BOOTING) {
rettime = ktime_get();
delta = ktime_sub(rettime, calltime);
- printk("initcall %lli_%pF returned 0 after %lld usecs\n", entry->cookie,
- entry->func, ktime_to_ns(delta) >> 10);
+ printk("initcall %lli_%pF returned 0 after %lld usecs\n",
+ (long long)entry->cookie,
+ entry->func,
+ (long long)ktime_to_ns(delta) >> 10);
}
/* 4) remove it from the running queue */
@@ -205,18 +208,44 @@
return newcookie;
}
+/**
+ * async_schedule - schedule a function for asynchronous execution
+ * @ptr: function to execute asynchronously
+ * @data: data pointer to pass to the function
+ *
+ * Returns an async_cookie_t that may be used for checkpointing later.
+ * Note: This function may be called from atomic or non-atomic contexts.
+ */
async_cookie_t async_schedule(async_func_ptr *ptr, void *data)
{
- return __async_schedule(ptr, data, &async_pending);
+ return __async_schedule(ptr, data, &async_running);
}
EXPORT_SYMBOL_GPL(async_schedule);
-async_cookie_t async_schedule_special(async_func_ptr *ptr, void *data, struct list_head *running)
+/**
+ * async_schedule_domain - schedule a function for asynchronous execution within a certain domain
+ * @ptr: function to execute asynchronously
+ * @data: data pointer to pass to the function
+ * @running: running list for the domain
+ *
+ * Returns an async_cookie_t that may be used for checkpointing later.
+ * @running may be used in the async_synchronize_*_domain() functions
+ * to wait within a certain synchronization domain rather than globally.
+ * A synchronization domain is specified via the running queue @running to use.
+ * Note: This function may be called from atomic or non-atomic contexts.
+ */
+async_cookie_t async_schedule_domain(async_func_ptr *ptr, void *data,
+ struct list_head *running)
{
return __async_schedule(ptr, data, running);
}
-EXPORT_SYMBOL_GPL(async_schedule_special);
+EXPORT_SYMBOL_GPL(async_schedule_domain);
+/**
+ * async_synchronize_full - synchronize all asynchronous function calls
+ *
+ * This function waits until all asynchronous function calls have been done.
+ */
void async_synchronize_full(void)
{
do {
@@ -225,13 +254,30 @@
}
EXPORT_SYMBOL_GPL(async_synchronize_full);
-void async_synchronize_full_special(struct list_head *list)
+/**
+ * async_synchronize_full_domain - synchronize all asynchronous function within a certain domain
+ * @list: running list to synchronize on
+ *
+ * This function waits until all asynchronous function calls for the
+ * synchronization domain specified by the running list @list have been done.
+ */
+void async_synchronize_full_domain(struct list_head *list)
{
- async_synchronize_cookie_special(next_cookie, list);
+ async_synchronize_cookie_domain(next_cookie, list);
}
-EXPORT_SYMBOL_GPL(async_synchronize_full_special);
+EXPORT_SYMBOL_GPL(async_synchronize_full_domain);
-void async_synchronize_cookie_special(async_cookie_t cookie, struct list_head *running)
+/**
+ * async_synchronize_cookie_domain - synchronize asynchronous function calls within a certain domain with cookie checkpointing
+ * @cookie: async_cookie_t to use as checkpoint
+ * @running: running list to synchronize on
+ *
+ * This function waits until all asynchronous function calls for the
+ * synchronization domain specified by the running list @list submitted
+ * prior to @cookie have been done.
+ */
+void async_synchronize_cookie_domain(async_cookie_t cookie,
+ struct list_head *running)
{
ktime_t starttime, delta, endtime;
@@ -247,14 +293,22 @@
delta = ktime_sub(endtime, starttime);
printk("async_continuing @ %i after %lli usec\n",
- task_pid_nr(current), ktime_to_ns(delta) >> 10);
+ task_pid_nr(current),
+ (long long)ktime_to_ns(delta) >> 10);
}
}
-EXPORT_SYMBOL_GPL(async_synchronize_cookie_special);
+EXPORT_SYMBOL_GPL(async_synchronize_cookie_domain);
+/**
+ * async_synchronize_cookie - synchronize asynchronous function calls with cookie checkpointing
+ * @cookie: async_cookie_t to use as checkpoint
+ *
+ * This function waits until all asynchronous function calls prior to @cookie
+ * have been done.
+ */
void async_synchronize_cookie(async_cookie_t cookie)
{
- async_synchronize_cookie_special(cookie, &async_running);
+ async_synchronize_cookie_domain(cookie, &async_running);
}
EXPORT_SYMBOL_GPL(async_synchronize_cookie);
@@ -315,7 +369,11 @@
ec = atomic_read(&entry_count);
while (tc < ec && tc < MAX_THREADS) {
- kthread_run(async_thread, NULL, "async/%i", tc);
+ if (IS_ERR(kthread_run(async_thread, NULL, "async/%i",
+ tc))) {
+ msleep(100);
+ continue;
+ }
atomic_inc(&thread_count);
tc++;
}
@@ -330,7 +388,9 @@
static int __init async_init(void)
{
if (async_enabled)
- kthread_run(async_manager_thread, NULL, "async/mgr");
+ if (IS_ERR(kthread_run(async_manager_thread, NULL,
+ "async/mgr")))
+ async_enabled = 0;
return 0;
}
diff --git a/kernel/exit.c b/kernel/exit.c
index f80dec3..70612c1 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -977,12 +977,9 @@
{
static DEFINE_SPINLOCK(low_water_lock);
static int lowest_to_date = THREAD_SIZE;
- unsigned long *n = end_of_stack(current);
unsigned long free;
- while (*n == 0)
- n++;
- free = (unsigned long)n - (unsigned long)end_of_stack(current);
+ free = stack_not_used(current);
if (free >= lowest_to_date)
return;
diff --git a/kernel/fork.c b/kernel/fork.c
index 242a706..c078438 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -61,6 +61,7 @@
#include <linux/proc_fs.h>
#include <linux/blkdev.h>
#include <trace/sched.h>
+#include <linux/magic.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
@@ -212,6 +213,8 @@
{
struct task_struct *tsk;
struct thread_info *ti;
+ unsigned long *stackend;
+
int err;
prepare_to_copy(orig);
@@ -237,6 +240,8 @@
goto out;
setup_thread_stack(tsk, orig);
+ stackend = end_of_stack(tsk);
+ *stackend = STACK_END_MAGIC; /* for overflow detection */
#ifdef CONFIG_CC_STACKPROTECTOR
tsk->stack_canary = get_random_int();
@@ -1005,6 +1010,7 @@
* triggers too late. This doesn't hurt, the check is only there
* to stop root fork bombs.
*/
+ retval = -EAGAIN;
if (nr_threads >= max_threads)
goto bad_fork_cleanup_count;
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 7de11bd..122fef4 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -46,7 +46,10 @@
desc->irq_count = 0;
desc->irqs_unhandled = 0;
#ifdef CONFIG_SMP
- cpumask_setall(&desc->affinity);
+ cpumask_setall(desc->affinity);
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+ cpumask_clear(desc->pending_mask);
+#endif
#endif
spin_unlock_irqrestore(&desc->lock, flags);
}
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 3aba8d1..f51eaee 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -17,6 +17,7 @@
#include <linux/kernel_stat.h>
#include <linux/rculist.h>
#include <linux/hash.h>
+#include <linux/bootmem.h>
#include "internals.h"
@@ -69,6 +70,7 @@
EXPORT_SYMBOL_GPL(nr_irqs);
#ifdef CONFIG_SPARSE_IRQ
+
static struct irq_desc irq_desc_init = {
.irq = -1,
.status = IRQ_DISABLED,
@@ -76,9 +78,6 @@
.handle_irq = handle_bad_irq,
.depth = 1,
.lock = __SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
-#ifdef CONFIG_SMP
- .affinity = CPU_MASK_ALL
-#endif
};
void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr)
@@ -113,6 +112,10 @@
printk(KERN_ERR "can not alloc kstat_irqs\n");
BUG_ON(1);
}
+ if (!init_alloc_desc_masks(desc, cpu, false)) {
+ printk(KERN_ERR "can not alloc irq_desc cpumasks\n");
+ BUG_ON(1);
+ }
arch_init_chip_data(desc, cpu);
}
@@ -121,7 +124,7 @@
*/
DEFINE_SPINLOCK(sparse_irq_lock);
-struct irq_desc *irq_desc_ptrs[NR_IRQS] __read_mostly;
+struct irq_desc **irq_desc_ptrs __read_mostly;
static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_smp = {
[0 ... NR_IRQS_LEGACY-1] = {
@@ -131,14 +134,10 @@
.handle_irq = handle_bad_irq,
.depth = 1,
.lock = __SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
-#ifdef CONFIG_SMP
- .affinity = CPU_MASK_ALL
-#endif
}
};
-/* FIXME: use bootmem alloc ...*/
-static unsigned int kstat_irqs_legacy[NR_IRQS_LEGACY][NR_CPUS];
+static unsigned int *kstat_irqs_legacy;
int __init early_irq_init(void)
{
@@ -148,18 +147,30 @@
init_irq_default_affinity();
+ /* initialize nr_irqs based on nr_cpu_ids */
+ arch_probe_nr_irqs();
+ printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d\n", NR_IRQS, nr_irqs);
+
desc = irq_desc_legacy;
legacy_count = ARRAY_SIZE(irq_desc_legacy);
+ /* allocate irq_desc_ptrs array based on nr_irqs */
+ irq_desc_ptrs = alloc_bootmem(nr_irqs * sizeof(void *));
+
+ /* allocate based on nr_cpu_ids */
+ /* FIXME: invert kstat_irgs, and it'd be a per_cpu_alloc'd thing */
+ kstat_irqs_legacy = alloc_bootmem(NR_IRQS_LEGACY * nr_cpu_ids *
+ sizeof(int));
+
for (i = 0; i < legacy_count; i++) {
desc[i].irq = i;
- desc[i].kstat_irqs = kstat_irqs_legacy[i];
+ desc[i].kstat_irqs = kstat_irqs_legacy + i * nr_cpu_ids;
lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
-
+ init_alloc_desc_masks(&desc[i], 0, true);
irq_desc_ptrs[i] = desc + i;
}
- for (i = legacy_count; i < NR_IRQS; i++)
+ for (i = legacy_count; i < nr_irqs; i++)
irq_desc_ptrs[i] = NULL;
return arch_early_irq_init();
@@ -167,7 +178,10 @@
struct irq_desc *irq_to_desc(unsigned int irq)
{
- return (irq < NR_IRQS) ? irq_desc_ptrs[irq] : NULL;
+ if (irq_desc_ptrs && irq < nr_irqs)
+ return irq_desc_ptrs[irq];
+
+ return NULL;
}
struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
@@ -176,10 +190,9 @@
unsigned long flags;
int node;
- if (irq >= NR_IRQS) {
- printk(KERN_WARNING "irq >= NR_IRQS in irq_to_desc_alloc: %d %d\n",
- irq, NR_IRQS);
- WARN_ON(1);
+ if (irq >= nr_irqs) {
+ WARN(1, "irq (%d) >= nr_irqs (%d) in irq_to_desc_alloc\n",
+ irq, nr_irqs);
return NULL;
}
@@ -221,9 +234,6 @@
.handle_irq = handle_bad_irq,
.depth = 1,
.lock = __SPIN_LOCK_UNLOCKED(irq_desc->lock),
-#ifdef CONFIG_SMP
- .affinity = CPU_MASK_ALL
-#endif
}
};
@@ -235,12 +245,15 @@
init_irq_default_affinity();
+ printk(KERN_INFO "NR_IRQS:%d\n", NR_IRQS);
+
desc = irq_desc;
count = ARRAY_SIZE(irq_desc);
- for (i = 0; i < count; i++)
+ for (i = 0; i < count; i++) {
desc[i].irq = i;
-
+ init_alloc_desc_masks(&desc[i], 0, true);
+ }
return arch_early_irq_init();
}
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index e6d0a43..40416a8 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -16,7 +16,14 @@
extern struct lock_class_key irq_desc_lock_class;
extern void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr);
extern spinlock_t sparse_irq_lock;
+
+#ifdef CONFIG_SPARSE_IRQ
+/* irq_desc_ptrs allocated at boot time */
+extern struct irq_desc **irq_desc_ptrs;
+#else
+/* irq_desc_ptrs is a fixed size array */
extern struct irq_desc *irq_desc_ptrs[NR_IRQS];
+#endif
#ifdef CONFIG_PROC_FS
extern void register_irq_proc(unsigned int irq, struct irq_desc *desc);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 291f036..a3a5dc9 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -90,14 +90,14 @@
#ifdef CONFIG_GENERIC_PENDING_IRQ
if (desc->status & IRQ_MOVE_PCNTXT || desc->status & IRQ_DISABLED) {
- cpumask_copy(&desc->affinity, cpumask);
+ cpumask_copy(desc->affinity, cpumask);
desc->chip->set_affinity(irq, cpumask);
} else {
desc->status |= IRQ_MOVE_PENDING;
- cpumask_copy(&desc->pending_mask, cpumask);
+ cpumask_copy(desc->pending_mask, cpumask);
}
#else
- cpumask_copy(&desc->affinity, cpumask);
+ cpumask_copy(desc->affinity, cpumask);
desc->chip->set_affinity(irq, cpumask);
#endif
desc->status |= IRQ_AFFINITY_SET;
@@ -119,16 +119,16 @@
* one of the targets is online.
*/
if (desc->status & (IRQ_AFFINITY_SET | IRQ_NO_BALANCING)) {
- if (cpumask_any_and(&desc->affinity, cpu_online_mask)
+ if (cpumask_any_and(desc->affinity, cpu_online_mask)
< nr_cpu_ids)
goto set_affinity;
else
desc->status &= ~IRQ_AFFINITY_SET;
}
- cpumask_and(&desc->affinity, cpu_online_mask, irq_default_affinity);
+ cpumask_and(desc->affinity, cpu_online_mask, irq_default_affinity);
set_affinity:
- desc->chip->set_affinity(irq, &desc->affinity);
+ desc->chip->set_affinity(irq, desc->affinity);
return 0;
}
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index bd72329..e05ad9b 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -18,7 +18,7 @@
desc->status &= ~IRQ_MOVE_PENDING;
- if (unlikely(cpumask_empty(&desc->pending_mask)))
+ if (unlikely(cpumask_empty(desc->pending_mask)))
return;
if (!desc->chip->set_affinity)
@@ -38,13 +38,13 @@
* For correct operation this depends on the caller
* masking the irqs.
*/
- if (likely(cpumask_any_and(&desc->pending_mask, cpu_online_mask)
+ if (likely(cpumask_any_and(desc->pending_mask, cpu_online_mask)
< nr_cpu_ids)) {
- cpumask_and(&desc->affinity,
- &desc->pending_mask, cpu_online_mask);
- desc->chip->set_affinity(irq, &desc->affinity);
+ cpumask_and(desc->affinity,
+ desc->pending_mask, cpu_online_mask);
+ desc->chip->set_affinity(irq, desc->affinity);
}
- cpumask_clear(&desc->pending_mask);
+ cpumask_clear(desc->pending_mask);
}
void move_native_irq(int irq)
diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c
index acd8835..7f9b804 100644
--- a/kernel/irq/numa_migrate.c
+++ b/kernel/irq/numa_migrate.c
@@ -38,15 +38,22 @@
old_desc->kstat_irqs = NULL;
}
-static void init_copy_one_irq_desc(int irq, struct irq_desc *old_desc,
+static bool init_copy_one_irq_desc(int irq, struct irq_desc *old_desc,
struct irq_desc *desc, int cpu)
{
memcpy(desc, old_desc, sizeof(struct irq_desc));
+ if (!init_alloc_desc_masks(desc, cpu, false)) {
+ printk(KERN_ERR "irq %d: can not get new irq_desc cpumask "
+ "for migration.\n", irq);
+ return false;
+ }
spin_lock_init(&desc->lock);
desc->cpu = cpu;
lockdep_set_class(&desc->lock, &irq_desc_lock_class);
init_copy_kstat_irqs(old_desc, desc, cpu, nr_cpu_ids);
+ init_copy_desc_masks(old_desc, desc);
arch_init_copy_chip_data(old_desc, desc, cpu);
+ return true;
}
static void free_one_irq_desc(struct irq_desc *old_desc, struct irq_desc *desc)
@@ -76,12 +83,18 @@
node = cpu_to_node(cpu);
desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
if (!desc) {
- printk(KERN_ERR "irq %d: can not get new irq_desc for migration.\n", irq);
+ printk(KERN_ERR "irq %d: can not get new irq_desc "
+ "for migration.\n", irq);
/* still use old one */
desc = old_desc;
goto out_unlock;
}
- init_copy_one_irq_desc(irq, old_desc, desc, cpu);
+ if (!init_copy_one_irq_desc(irq, old_desc, desc, cpu)) {
+ /* still use old one */
+ kfree(desc);
+ desc = old_desc;
+ goto out_unlock;
+ }
irq_desc_ptrs[irq] = desc;
spin_unlock_irqrestore(&sparse_irq_lock, flags);
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index aae3f74..692363d 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -20,11 +20,11 @@
static int irq_affinity_proc_show(struct seq_file *m, void *v)
{
struct irq_desc *desc = irq_to_desc((long)m->private);
- const struct cpumask *mask = &desc->affinity;
+ const struct cpumask *mask = desc->affinity;
#ifdef CONFIG_GENERIC_PENDING_IRQ
if (desc->status & IRQ_MOVE_PENDING)
- mask = &desc->pending_mask;
+ mask = desc->pending_mask;
#endif
seq_cpumask(m, mask);
seq_putc(m, '\n');
diff --git a/kernel/panic.c b/kernel/panic.c
index 2a2ff36..33cab3d 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -74,6 +74,9 @@
vsnprintf(buf, sizeof(buf), fmt, args);
va_end(args);
printk(KERN_EMERG "Kernel panic - not syncing: %s\n",buf);
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+ dump_stack();
+#endif
bust_spinlocks(0);
/*
@@ -355,15 +358,22 @@
#endif
#ifdef CONFIG_CC_STACKPROTECTOR
+
+#ifndef GCC_HAS_SP
+#warning You have selected the CONFIG_CC_STACKPROTECTOR option, but the gcc used does not support this.
+#endif
+
/*
* Called when gcc's -fstack-protector feature is used, and
* gcc detects corruption of the on-stack canary value
*/
void __stack_chk_fail(void)
{
- panic("stack-protector: Kernel stack is corrupted");
+ panic("stack-protector: Kernel stack is corrupted in: %p\n",
+ __builtin_return_address(0));
}
EXPORT_SYMBOL(__stack_chk_fail);
+
#endif
core_param(panic, panic_timeout, int, 0644);
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 2399888..b4d2190 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -57,16 +57,6 @@
#ifdef CONFIG_PM_DEBUG
int pm_test_level = TEST_NONE;
-static int suspend_test(int level)
-{
- if (pm_test_level == level) {
- printk(KERN_INFO "suspend debug: Waiting for 5 seconds.\n");
- mdelay(5000);
- return 1;
- }
- return 0;
-}
-
static const char * const pm_tests[__TEST_AFTER_LAST] = {
[TEST_NONE] = "none",
[TEST_CORE] = "core",
@@ -125,14 +115,24 @@
}
power_attr(pm_test);
-#else /* !CONFIG_PM_DEBUG */
-static inline int suspend_test(int level) { return 0; }
-#endif /* !CONFIG_PM_DEBUG */
+#endif /* CONFIG_PM_DEBUG */
#endif /* CONFIG_PM_SLEEP */
#ifdef CONFIG_SUSPEND
+static int suspend_test(int level)
+{
+#ifdef CONFIG_PM_DEBUG
+ if (pm_test_level == level) {
+ printk(KERN_INFO "suspend debug: Waiting for 5 seconds.\n");
+ mdelay(5000);
+ return 1;
+ }
+#endif /* !CONFIG_PM_DEBUG */
+ return 0;
+}
+
#ifdef CONFIG_PM_TEST_SUSPEND
/*
diff --git a/kernel/sched.c b/kernel/sched.c
index 242d0d4..fc17fd9 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4697,8 +4697,8 @@
* started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
* zero in this (rare) case, and we handle it by continuing to scan the queue.
*/
-static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
- int nr_exclusive, int sync, void *key)
+void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
+ int nr_exclusive, int sync, void *key)
{
wait_queue_t *curr, *next;
@@ -5949,12 +5949,7 @@
printk(KERN_CONT " %016lx ", thread_saved_pc(p));
#endif
#ifdef CONFIG_DEBUG_STACK_USAGE
- {
- unsigned long *n = end_of_stack(p);
- while (!*n)
- n++;
- free = (unsigned long)n - (unsigned long)end_of_stack(p);
- }
+ free = stack_not_used(p);
#endif
printk(KERN_CONT "%5lu %5d %6d\n", free,
task_pid_nr(p), task_pid_nr(p->real_parent));
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index bac1061..da932f4 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -960,12 +960,13 @@
static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask);
-static inline int pick_optimal_cpu(int this_cpu, cpumask_t *mask)
+static inline int pick_optimal_cpu(int this_cpu,
+ const struct cpumask *mask)
{
int first;
/* "this_cpu" is cheaper to preempt than a remote processor */
- if ((this_cpu != -1) && cpu_isset(this_cpu, *mask))
+ if ((this_cpu != -1) && cpumask_test_cpu(this_cpu, mask))
return this_cpu;
first = cpumask_first(mask);
@@ -981,6 +982,7 @@
struct cpumask *lowest_mask = __get_cpu_var(local_cpu_mask);
int this_cpu = smp_processor_id();
int cpu = task_cpu(task);
+ cpumask_var_t domain_mask;
if (task->rt.nr_cpus_allowed == 1)
return -1; /* No other targets possible */
@@ -1013,19 +1015,25 @@
if (this_cpu == cpu)
this_cpu = -1; /* Skip this_cpu opt if the same */
- for_each_domain(cpu, sd) {
- if (sd->flags & SD_WAKE_AFFINE) {
- cpumask_t domain_mask;
- int best_cpu;
+ if (alloc_cpumask_var(&domain_mask, GFP_ATOMIC)) {
+ for_each_domain(cpu, sd) {
+ if (sd->flags & SD_WAKE_AFFINE) {
+ int best_cpu;
- cpumask_and(&domain_mask, sched_domain_span(sd),
- lowest_mask);
+ cpumask_and(domain_mask,
+ sched_domain_span(sd),
+ lowest_mask);
- best_cpu = pick_optimal_cpu(this_cpu,
- &domain_mask);
- if (best_cpu != -1)
- return best_cpu;
+ best_cpu = pick_optimal_cpu(this_cpu,
+ domain_mask);
+
+ if (best_cpu != -1) {
+ free_cpumask_var(domain_mask);
+ return best_cpu;
+ }
+ }
}
+ free_cpumask_var(domain_mask);
}
/*
diff --git a/kernel/softirq.c b/kernel/softirq.c
index bdbe9de..0365b48 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -795,6 +795,11 @@
return 0;
}
+int __init __weak arch_probe_nr_irqs(void)
+{
+ return 0;
+}
+
int __init __weak arch_early_irq_init(void)
{
return 0;
diff --git a/kernel/sys.c b/kernel/sys.c
index e7dc0e1..f145c41 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1525,22 +1525,14 @@
return -EINVAL;
if (copy_from_user(&new_rlim, rlim, sizeof(*rlim)))
return -EFAULT;
+ if (new_rlim.rlim_cur > new_rlim.rlim_max)
+ return -EINVAL;
old_rlim = current->signal->rlim + resource;
if ((new_rlim.rlim_max > old_rlim->rlim_max) &&
!capable(CAP_SYS_RESOURCE))
return -EPERM;
-
- if (resource == RLIMIT_NOFILE) {
- if (new_rlim.rlim_max == RLIM_INFINITY)
- new_rlim.rlim_max = sysctl_nr_open;
- if (new_rlim.rlim_cur == RLIM_INFINITY)
- new_rlim.rlim_cur = sysctl_nr_open;
- if (new_rlim.rlim_max > sysctl_nr_open)
- return -EPERM;
- }
-
- if (new_rlim.rlim_cur > new_rlim.rlim_max)
- return -EINVAL;
+ if (resource == RLIMIT_NOFILE && new_rlim.rlim_max > sysctl_nr_open)
+ return -EPERM;
retval = security_task_setrlimit(resource, &new_rlim);
if (retval)
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 7dcf6e9..9a236ff 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1737,9 +1737,12 @@
{
struct task_struct *p;
+ rcu_read_lock();
do_each_pid_task(pid, PIDTYPE_PID, p) {
clear_tsk_trace_trace(p);
} while_each_pid_task(pid, PIDTYPE_PID, p);
+ rcu_read_unlock();
+
put_pid(pid);
}
@@ -1747,9 +1750,11 @@
{
struct task_struct *p;
+ rcu_read_lock();
do_each_pid_task(pid, PIDTYPE_PID, p) {
set_tsk_trace_trace(p);
} while_each_pid_task(pid, PIDTYPE_PID, p);
+ rcu_read_unlock();
}
static void clear_ftrace_pid_task(struct pid **pid)
diff --git a/kernel/wait.c b/kernel/wait.c
index cd87131..42a2dbc 100644
--- a/kernel/wait.c
+++ b/kernel/wait.c
@@ -91,6 +91,15 @@
}
EXPORT_SYMBOL(prepare_to_wait_exclusive);
+/*
+ * finish_wait - clean up after waiting in a queue
+ * @q: waitqueue waited on
+ * @wait: wait descriptor
+ *
+ * Sets current thread back to running state and removes
+ * the wait descriptor from the given waitqueue if still
+ * queued.
+ */
void finish_wait(wait_queue_head_t *q, wait_queue_t *wait)
{
unsigned long flags;
@@ -117,6 +126,39 @@
}
EXPORT_SYMBOL(finish_wait);
+/*
+ * abort_exclusive_wait - abort exclusive waiting in a queue
+ * @q: waitqueue waited on
+ * @wait: wait descriptor
+ * @state: runstate of the waiter to be woken
+ * @key: key to identify a wait bit queue or %NULL
+ *
+ * Sets current thread back to running state and removes
+ * the wait descriptor from the given waitqueue if still
+ * queued.
+ *
+ * Wakes up the next waiter if the caller is concurrently
+ * woken up through the queue.
+ *
+ * This prevents waiter starvation where an exclusive waiter
+ * aborts and is woken up concurrently and noone wakes up
+ * the next waiter.
+ */
+void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait,
+ unsigned int mode, void *key)
+{
+ unsigned long flags;
+
+ __set_current_state(TASK_RUNNING);
+ spin_lock_irqsave(&q->lock, flags);
+ if (!list_empty(&wait->task_list))
+ list_del_init(&wait->task_list);
+ else if (waitqueue_active(q))
+ __wake_up_common(q, mode, 1, 0, key);
+ spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(abort_exclusive_wait);
+
int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key)
{
int ret = default_wake_function(wait, mode, sync, key);
@@ -177,17 +219,20 @@
__wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q,
int (*action)(void *), unsigned mode)
{
- int ret = 0;
-
do {
+ int ret;
+
prepare_to_wait_exclusive(wq, &q->wait, mode);
- if (test_bit(q->key.bit_nr, q->key.flags)) {
- if ((ret = (*action)(q->key.flags)))
- break;
- }
+ if (!test_bit(q->key.bit_nr, q->key.flags))
+ continue;
+ ret = action(q->key.flags);
+ if (!ret)
+ continue;
+ abort_exclusive_wait(wq, &q->wait, mode, &q->key);
+ return ret;
} while (test_and_set_bit(q->key.bit_nr, q->key.flags));
finish_wait(wq, &q->wait);
- return ret;
+ return 0;
}
EXPORT_SYMBOL(__wait_on_bit_lock);
diff --git a/mm/memory.c b/mm/memory.c
index 22bfa7a..baa999e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1999,7 +1999,7 @@
* Don't let another task, with possibly unlocked vma,
* keep the mlocked page.
*/
- if (vma->vm_flags & VM_LOCKED) {
+ if ((vma->vm_flags & VM_LOCKED) && old_page) {
lock_page(old_page); /* for LRU manipulation */
clear_page_mlock(old_page);
unlock_page(old_page);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index b493db7..dc32dae 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1051,13 +1051,22 @@
}
}
- if (wbc->sync_mode == WB_SYNC_NONE) {
- wbc->nr_to_write--;
- if (wbc->nr_to_write <= 0) {
- done = 1;
- break;
- }
+ if (nr_to_write > 0)
+ nr_to_write--;
+ else if (wbc->sync_mode == WB_SYNC_NONE) {
+ /*
+ * We stop writing back only if we are not
+ * doing integrity sync. In case of integrity
+ * sync we have to keep going because someone
+ * may be concurrently dirtying pages, and we
+ * might have synced a lot of newly appeared
+ * dirty pages, but have not synced all of the
+ * old dirty pages.
+ */
+ done = 1;
+ break;
}
+
if (wbc->nonblocking && bdi_write_congested(bdi)) {
wbc->encountered_congestion = 1;
done = 1;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 557fe16..dda42f0 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -663,14 +663,10 @@
th->urg_ptr = 0;
/* The urg_mode check is necessary during a below snd_una win probe */
- if (unlikely(tcp_urg_mode(tp))) {
- if (between(tp->snd_up, tcb->seq + 1, tcb->seq + 0xFFFF)) {
- th->urg_ptr = htons(tp->snd_up - tcb->seq);
- th->urg = 1;
- } else if (after(tcb->seq + 0xFFFF, tp->snd_nxt)) {
- th->urg_ptr = 0xFFFF;
- th->urg = 1;
- }
+ if (unlikely(tcp_urg_mode(tp) &&
+ between(tp->snd_up, tcb->seq + 1, tcb->seq + 0xFFFF))) {
+ th->urg_ptr = htons(tp->snd_up - tcb->seq);
+ th->urg = 1;
}
tcp_options_write((__be32 *)(th + 1), tp, &opts, &md5_hash_location);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index b7faffe..cc3a0a0 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1015,9 +1015,11 @@
if ((rc = sock_queue_rcv_skb(sk, skb)) < 0) {
/* Note that an ENOMEM error is charged twice */
- if (rc == -ENOMEM)
+ if (rc == -ENOMEM) {
UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS,
is_udplite);
+ atomic_inc(&sk->sk_drops);
+ }
goto drop;
}
@@ -1229,7 +1231,7 @@
int proto)
{
struct sock *sk;
- struct udphdr *uh = udp_hdr(skb);
+ struct udphdr *uh;
unsigned short ulen;
struct rtable *rt = (struct rtable*)skb->dst;
__be32 saddr = ip_hdr(skb)->saddr;
@@ -1242,6 +1244,7 @@
if (!pskb_may_pull(skb, sizeof(struct udphdr)))
goto drop; /* No space for header. */
+ uh = udp_hdr(skb);
ulen = ntohs(uh->len);
if (ulen > skb->len)
goto short_packet;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 4b15938..9fb49c3 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1105,6 +1105,18 @@
return err;
}
+static inline struct ipv6_opt_hdr *ip6_opt_dup(struct ipv6_opt_hdr *src,
+ gfp_t gfp)
+{
+ return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL;
+}
+
+static inline struct ipv6_rt_hdr *ip6_rthdr_dup(struct ipv6_rt_hdr *src,
+ gfp_t gfp)
+{
+ return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL;
+}
+
int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
int offset, int len, int odd, struct sk_buff *skb),
void *from, int length, int transhdrlen,
@@ -1130,17 +1142,37 @@
* setup for corking
*/
if (opt) {
- if (np->cork.opt == NULL) {
- np->cork.opt = kmalloc(opt->tot_len,
- sk->sk_allocation);
- if (unlikely(np->cork.opt == NULL))
- return -ENOBUFS;
- } else if (np->cork.opt->tot_len < opt->tot_len) {
- printk(KERN_DEBUG "ip6_append_data: invalid option length\n");
+ if (WARN_ON(np->cork.opt))
return -EINVAL;
- }
- memcpy(np->cork.opt, opt, opt->tot_len);
- inet->cork.flags |= IPCORK_OPT;
+
+ np->cork.opt = kmalloc(opt->tot_len, sk->sk_allocation);
+ if (unlikely(np->cork.opt == NULL))
+ return -ENOBUFS;
+
+ np->cork.opt->tot_len = opt->tot_len;
+ np->cork.opt->opt_flen = opt->opt_flen;
+ np->cork.opt->opt_nflen = opt->opt_nflen;
+
+ np->cork.opt->dst0opt = ip6_opt_dup(opt->dst0opt,
+ sk->sk_allocation);
+ if (opt->dst0opt && !np->cork.opt->dst0opt)
+ return -ENOBUFS;
+
+ np->cork.opt->dst1opt = ip6_opt_dup(opt->dst1opt,
+ sk->sk_allocation);
+ if (opt->dst1opt && !np->cork.opt->dst1opt)
+ return -ENOBUFS;
+
+ np->cork.opt->hopopt = ip6_opt_dup(opt->hopopt,
+ sk->sk_allocation);
+ if (opt->hopopt && !np->cork.opt->hopopt)
+ return -ENOBUFS;
+
+ np->cork.opt->srcrt = ip6_rthdr_dup(opt->srcrt,
+ sk->sk_allocation);
+ if (opt->srcrt && !np->cork.opt->srcrt)
+ return -ENOBUFS;
+
/* need source address above miyazawa*/
}
dst_hold(&rt->u.dst);
@@ -1167,8 +1199,7 @@
} else {
rt = (struct rt6_info *)inet->cork.dst;
fl = &inet->cork.fl;
- if (inet->cork.flags & IPCORK_OPT)
- opt = np->cork.opt;
+ opt = np->cork.opt;
transhdrlen = 0;
exthdrlen = 0;
mtu = inet->cork.fragsize;
@@ -1407,9 +1438,15 @@
static void ip6_cork_release(struct inet_sock *inet, struct ipv6_pinfo *np)
{
- inet->cork.flags &= ~IPCORK_OPT;
- kfree(np->cork.opt);
- np->cork.opt = NULL;
+ if (np->cork.opt) {
+ kfree(np->cork.opt->dst0opt);
+ kfree(np->cork.opt->dst1opt);
+ kfree(np->cork.opt->hopopt);
+ kfree(np->cork.opt->srcrt);
+ kfree(np->cork.opt);
+ np->cork.opt = NULL;
+ }
+
if (inet->cork.dst) {
dst_release(inet->cork.dst);
inet->cork.dst = NULL;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 9454d4a..1fc4a78 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -222,13 +222,13 @@
h.raw = po->pg_vec[pg_vec_pos] + (frame_offset * po->frame_size);
switch (po->tp_version) {
case TPACKET_V1:
- if (status != h.h1->tp_status ? TP_STATUS_USER :
- TP_STATUS_KERNEL)
+ if (status != (h.h1->tp_status ? TP_STATUS_USER :
+ TP_STATUS_KERNEL))
return NULL;
break;
case TPACKET_V2:
- if (status != h.h2->tp_status ? TP_STATUS_USER :
- TP_STATUS_KERNEL)
+ if (status != (h.h2->tp_status ? TP_STATUS_USER :
+ TP_STATUS_KERNEL))
return NULL;
break;
}
diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig
index dcef600..5592883 100644
--- a/net/sunrpc/Kconfig
+++ b/net/sunrpc/Kconfig
@@ -6,7 +6,7 @@
config SUNRPC_XPRT_RDMA
tristate
- depends on SUNRPC && INFINIBAND && EXPERIMENTAL
+ depends on SUNRPC && INFINIBAND && INFINIBAND_ADDR_TRANS && EXPERIMENTAL
default SUNRPC && INFINIBAND
help
This option allows the NFS client and server to support
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 8892161..7e62303 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -415,8 +415,9 @@
const char *secstrings
= (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
const char *secname;
+ int nobits = sechdrs[i].sh_type == SHT_NOBITS;
- if (sechdrs[i].sh_offset > info->size) {
+ if (!nobits && sechdrs[i].sh_offset > info->size) {
fatal("%s is truncated. sechdrs[i].sh_offset=%lu > "
"sizeof(*hrd)=%zu\n", filename,
(unsigned long)sechdrs[i].sh_offset,
@@ -425,6 +426,8 @@
}
secname = secstrings + sechdrs[i].sh_name;
if (strcmp(secname, ".modinfo") == 0) {
+ if (nobits)
+ fatal("%s has NOBITS .modinfo\n", filename);
info->modinfo = (void *)hdr + sechdrs[i].sh_offset;
info->modinfo_len = sechdrs[i].sh_size;
} else if (strcmp(secname, "__ksymtab") == 0)
diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c
index e178366..0a1798e 100644
--- a/sound/core/oss/pcm_oss.c
+++ b/sound/core/oss/pcm_oss.c
@@ -1767,7 +1767,7 @@
AFMT_S8 | AFMT_U16_LE |
AFMT_U16_BE |
AFMT_S32_LE | AFMT_S32_BE |
- AFMT_S24_LE | AFMT_S24_LE |
+ AFMT_S24_LE | AFMT_S24_BE |
AFMT_S24_PACKED;
params = kmalloc(sizeof(*params), GFP_KERNEL);
if (!params)
diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index b7bba7d..0b70813 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -487,7 +487,6 @@
{
struct hda_bus *bus;
int err;
- char qname[8];
static struct snd_device_ops dev_ops = {
.dev_register = snd_hda_bus_dev_register,
.dev_free = snd_hda_bus_dev_free,
@@ -517,10 +516,12 @@
mutex_init(&bus->cmd_mutex);
INIT_LIST_HEAD(&bus->codec_list);
- snprintf(qname, sizeof(qname), "hda%d", card->number);
- bus->workq = create_workqueue(qname);
+ snprintf(bus->workq_name, sizeof(bus->workq_name),
+ "hd-audio%d", card->number);
+ bus->workq = create_singlethread_workqueue(bus->workq_name);
if (!bus->workq) {
- snd_printk(KERN_ERR "cannot create workqueue %s\n", qname);
+ snd_printk(KERN_ERR "cannot create workqueue %s\n",
+ bus->workq_name);
kfree(bus);
return -ENOMEM;
}
diff --git a/sound/pci/hda/hda_codec.h b/sound/pci/hda/hda_codec.h
index 5810ef5..09a332a 100644
--- a/sound/pci/hda/hda_codec.h
+++ b/sound/pci/hda/hda_codec.h
@@ -614,6 +614,7 @@
/* unsolicited event queue */
struct hda_bus_unsolicited *unsol;
+ char workq_name[16];
struct workqueue_struct *workq; /* common workqueue for codecs */
/* assigned PCMs */
diff --git a/sound/pci/hda/hda_proc.c b/sound/pci/hda/hda_proc.c
index 7ca66d6..144b852 100644
--- a/sound/pci/hda/hda_proc.c
+++ b/sound/pci/hda/hda_proc.c
@@ -399,7 +399,8 @@
{
int c, curr = -1;
- if (conn_len > 1 && wid_type != AC_WID_AUD_MIX)
+ if (conn_len > 1 && wid_type != AC_WID_AUD_MIX &&
+ wid_type != AC_WID_VOL_KNB)
curr = snd_hda_codec_read(codec, nid, 0,
AC_VERB_GET_CONNECT_SEL, 0);
snd_iprintf(buffer, " Connection: %d\n", conn_len);
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 7884a4e..ae5c8a0 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -1037,6 +1037,7 @@
case 0x10ec0267:
case 0x10ec0268:
case 0x10ec0269:
+ case 0x10ec0272:
case 0x10ec0660:
case 0x10ec0662:
case 0x10ec0663:
@@ -1065,6 +1066,7 @@
case 0x10ec0882:
case 0x10ec0883:
case 0x10ec0885:
+ case 0x10ec0887:
case 0x10ec0889:
snd_hda_codec_write(codec, 0x20, 0,
AC_VERB_SET_COEF_INDEX, 7);
@@ -7012,6 +7014,7 @@
break;
case 0x106b1000: /* iMac 24 */
case 0x106b2800: /* AppleTV */
+ case 0x106b3e00: /* iMac 24 Aluminium */
board_config = ALC885_IMAC24;
break;
case 0x106b00a1: /* Macbook (might be wrong - PCI SSID?) */
@@ -8514,6 +8517,8 @@
SND_PCI_QUIRK(0x1558, 0, "Clevo laptop", ALC883_LAPTOP_EAPD),
SND_PCI_QUIRK(0x15d9, 0x8780, "Supermicro PDSBA", ALC883_3ST_6ch),
SND_PCI_QUIRK(0x161f, 0x2054, "Medion laptop", ALC883_MEDION),
+ SND_PCI_QUIRK(0x1734, 0x1107, "FSC AMILO Xi2550",
+ ALC883_FUJITSU_PI2515),
SND_PCI_QUIRK(0x1734, 0x1108, "Fujitsu AMILO Pi2515", ALC883_FUJITSU_PI2515),
SND_PCI_QUIRK(0x1734, 0x113d, "Fujitsu AMILO Xa3530",
ALC888_FUJITSU_XA3530),
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index b787b3c..38428e2 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -1804,6 +1804,8 @@
"HP dv4", STAC_HP_DV5),
SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x30fc,
"HP dv7", STAC_HP_M4),
+ SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x3600,
+ "HP dv5", STAC_HP_DV5),
SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x3603,
"HP dv5", STAC_HP_DV5),
SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x361a,
diff --git a/sound/pci/intel8x0.c b/sound/pci/intel8x0.c
index 19d3391..e900cdc 100644
--- a/sound/pci/intel8x0.c
+++ b/sound/pci/intel8x0.c
@@ -617,7 +617,7 @@
int time = 100;
if (chip->buggy_semaphore)
return 0; /* just ignore ... */
- while (time-- && (igetdword(chip, ICHREG(ALI_CAS)) & ALI_CAS_SEM_BUSY))
+ while (--time && (igetdword(chip, ICHREG(ALI_CAS)) & ALI_CAS_SEM_BUSY))
udelay(1);
if (! time && ! chip->in_ac97_init)
snd_printk(KERN_WARNING "ali_codec_semaphore timeout\n");
diff --git a/sound/soc/atmel/atmel_ssc_dai.c b/sound/soc/atmel/atmel_ssc_dai.c
index c5d6790..ff0054b 100644
--- a/sound/soc/atmel/atmel_ssc_dai.c
+++ b/sound/soc/atmel/atmel_ssc_dai.c
@@ -10,7 +10,7 @@
* Based on at91-ssc.c by
* Frank Mandarino <fmandarino@endrelia.com>
* Based on pxa2xx Platform drivers by
- * Liam Girdwood <liam.girdwood@wolfsonmicro.com>
+ * Liam Girdwood <lrg@slimlogic.co.uk>
*
* 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
diff --git a/sound/soc/atmel/atmel_ssc_dai.h b/sound/soc/atmel/atmel_ssc_dai.h
index a828746..391135f 100644
--- a/sound/soc/atmel/atmel_ssc_dai.h
+++ b/sound/soc/atmel/atmel_ssc_dai.h
@@ -10,7 +10,7 @@
* Based on at91-ssc.c by
* Frank Mandarino <fmandarino@endrelia.com>
* Based on pxa2xx Platform drivers by
- * Liam Girdwood <liam.girdwood@wolfsonmicro.com>
+ * Liam Girdwood <lrg@slimlogic.co.uk>
*
* 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
diff --git a/sound/soc/codecs/wm8350.c b/sound/soc/codecs/wm8350.c
index e3989d4..35d9975 100644
--- a/sound/soc/codecs/wm8350.c
+++ b/sound/soc/codecs/wm8350.c
@@ -3,7 +3,7 @@
*
* Copyright (C) 2007, 2008 Wolfson Microelectronics PLC.
*
- * Author: Liam Girdwood <lg@opensource.wolfsonmicro.com>
+ * Author: Liam Girdwood <lrg@slimlogic.co.uk>
*
* 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
diff --git a/sound/soc/codecs/wm8990.c b/sound/soc/codecs/wm8990.c
index 5b5afc1..1cbb7b9 100644
--- a/sound/soc/codecs/wm8990.c
+++ b/sound/soc/codecs/wm8990.c
@@ -2,8 +2,7 @@
* wm8990.c -- WM8990 ALSA Soc Audio driver
*
* Copyright 2008 Wolfson Microelectronics PLC.
- * Author: Liam Girdwood
- * lg@opensource.wolfsonmicro.com or linux@wolfsonmicro.com
+ * Author: Liam Girdwood <lrg@slimlogic.co.uk>
*
* 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
diff --git a/sound/soc/omap/omap-pcm.c b/sound/soc/omap/omap-pcm.c
index b0362df..dd3bb29 100644
--- a/sound/soc/omap/omap-pcm.c
+++ b/sound/soc/omap/omap-pcm.c
@@ -175,9 +175,10 @@
{
struct snd_pcm_runtime *runtime = substream->runtime;
struct omap_runtime_data *prtd = runtime->private_data;
+ unsigned long flags;
int ret = 0;
- spin_lock_irq(&prtd->lock);
+ spin_lock_irqsave(&prtd->lock, flags);
switch (cmd) {
case SNDRV_PCM_TRIGGER_START:
case SNDRV_PCM_TRIGGER_RESUME:
@@ -195,7 +196,7 @@
default:
ret = -EINVAL;
}
- spin_unlock_irq(&prtd->lock);
+ spin_unlock_irqrestore(&prtd->lock, flags);
return ret;
}
diff --git a/sound/usb/usbaudio.c b/sound/usb/usbaudio.c
index c709b95..2ab8312 100644
--- a/sound/usb/usbaudio.c
+++ b/sound/usb/usbaudio.c
@@ -2966,6 +2966,7 @@
return -EINVAL;
}
alts = &iface->altsetting[fp->altset_idx];
+ fp->maxpacksize = le16_to_cpu(get_endpoint(alts, 0)->wMaxPacketSize);
usb_set_interface(chip->dev, fp->iface, 0);
init_usb_pitch(chip->dev, fp->iface, alts, fp);
init_usb_sample_rate(chip->dev, fp->iface, alts, fp, fp->rate_max);
