Merge tag 'nmiforkvm' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into features
Pull kvm patches from Christian Borntraeger:
"s390,kvm: provide plumbing for machines checks when running guests"
This provides the basic plumbing for handling machine checks when
running guests
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index c6e5358..71f9305 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -253,8 +253,9 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
*/
off = offsetof(struct bpf_array, ptrs);
emit_a64_mov_i64(tmp, off, ctx);
- emit(A64_LDR64(tmp, r2, tmp), ctx);
- emit(A64_LDR64(prg, tmp, r3), ctx);
+ emit(A64_ADD(1, tmp, r2, tmp), ctx);
+ emit(A64_LSL(1, prg, r3, 3), ctx);
+ emit(A64_LDR64(prg, tmp, prg), ctx);
emit(A64_CBZ(1, prg, jmp_offset), ctx);
/* goto *(prog->bpf_func + prologue_size); */
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index e161faf..bb11f9f 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -64,6 +64,7 @@
config S390
def_bool y
+ select ARCH_BINFMT_ELF_STATE
select ARCH_HAS_DEVMEM_IS_ALLOWED
select ARCH_HAS_ELF_RANDOMIZE
select ARCH_HAS_GCOV_PROFILE_ALL
@@ -184,7 +185,7 @@
config PGTABLE_LEVELS
int
- default 4
+ default 5
source "init/Kconfig"
diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig
index a5039fa..2820722 100644
--- a/arch/s390/configs/default_defconfig
+++ b/arch/s390/configs/default_defconfig
@@ -30,6 +30,7 @@
CONFIG_SCHED_AUTOGROUP=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_EXPERT=y
+# CONFIG_SYSFS_SYSCALL is not set
CONFIG_BPF_SYSCALL=y
CONFIG_USERFAULTFD=y
# CONFIG_COMPAT_BRK is not set
@@ -44,7 +45,10 @@
CONFIG_MODULE_FORCE_UNLOAD=y
CONFIG_MODVERSIONS=y
CONFIG_MODULE_SRCVERSION_ALL=y
+CONFIG_BLK_DEV_INTEGRITY=y
CONFIG_BLK_DEV_THROTTLING=y
+CONFIG_BLK_WBT=y
+CONFIG_BLK_WBT_SQ=y
CONFIG_PARTITION_ADVANCED=y
CONFIG_IBM_PARTITION=y
CONFIG_BSD_DISKLABEL=y
@@ -90,6 +94,8 @@
CONFIG_UNIX_DIAG=m
CONFIG_XFRM_USER=m
CONFIG_NET_KEY=m
+CONFIG_SMC=m
+CONFIG_SMC_DIAG=m
CONFIG_INET=y
CONFIG_IP_MULTICAST=y
CONFIG_IP_ADVANCED_ROUTER=y
@@ -359,6 +365,7 @@
CONFIG_NET_ACT_SKBEDIT=m
CONFIG_NET_ACT_CSUM=m
CONFIG_DNS_RESOLVER=y
+CONFIG_NETLINK_DIAG=m
CONFIG_CGROUP_NET_PRIO=y
CONFIG_BPF_JIT=y
CONFIG_NET_PKTGEN=m
@@ -367,16 +374,19 @@
CONFIG_DMA_CMA=y
CONFIG_CMA_SIZE_MBYTES=0
CONFIG_CONNECTOR=y
+CONFIG_ZRAM=m
CONFIG_BLK_DEV_LOOP=m
CONFIG_BLK_DEV_CRYPTOLOOP=m
+CONFIG_BLK_DEV_DRBD=m
CONFIG_BLK_DEV_NBD=m
CONFIG_BLK_DEV_OSD=m
CONFIG_BLK_DEV_RAM=y
CONFIG_BLK_DEV_RAM_SIZE=32768
-CONFIG_CDROM_PKTCDVD=m
-CONFIG_ATA_OVER_ETH=m
+CONFIG_BLK_DEV_RAM_DAX=y
CONFIG_VIRTIO_BLK=y
+CONFIG_BLK_DEV_RBD=m
CONFIG_ENCLOSURE_SERVICES=m
+CONFIG_GENWQE=m
CONFIG_RAID_ATTRS=m
CONFIG_SCSI=y
CONFIG_BLK_DEV_SD=y
@@ -442,6 +452,8 @@
# CONFIG_NET_VENDOR_INTEL is not set
# CONFIG_NET_VENDOR_MARVELL is not set
CONFIG_MLX4_EN=m
+CONFIG_MLX5_CORE=m
+CONFIG_MLX5_CORE_EN=y
# CONFIG_NET_VENDOR_NATSEMI is not set
CONFIG_PPP=m
CONFIG_PPP_BSDCOMP=m
@@ -452,7 +464,6 @@
CONFIG_PPPOL2TP=m
CONFIG_PPP_ASYNC=m
CONFIG_PPP_SYNC_TTY=m
-# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
# CONFIG_INPUT_KEYBOARD is not set
# CONFIG_INPUT_MOUSE is not set
# CONFIG_SERIO is not set
@@ -471,6 +482,7 @@
CONFIG_INFINIBAND=m
CONFIG_INFINIBAND_USER_ACCESS=m
CONFIG_MLX4_INFINIBAND=m
+CONFIG_MLX5_INFINIBAND=m
CONFIG_VIRTIO_BALLOON=m
CONFIG_EXT4_FS=y
CONFIG_EXT4_FS_POSIX_ACL=y
@@ -487,12 +499,18 @@
CONFIG_XFS_RT=y
CONFIG_XFS_DEBUG=y
CONFIG_GFS2_FS=m
+CONFIG_GFS2_FS_LOCKING_DLM=y
CONFIG_OCFS2_FS=m
CONFIG_BTRFS_FS=y
CONFIG_BTRFS_FS_POSIX_ACL=y
+CONFIG_BTRFS_DEBUG=y
CONFIG_NILFS2_FS=m
+CONFIG_FS_DAX=y
+CONFIG_EXPORTFS_BLOCK_OPS=y
CONFIG_FANOTIFY=y
+CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y
CONFIG_QUOTA_NETLINK_INTERFACE=y
+CONFIG_QUOTA_DEBUG=y
CONFIG_QFMT_V1=m
CONFIG_QFMT_V2=m
CONFIG_AUTOFS4_FS=m
@@ -558,6 +576,7 @@
CONFIG_DEBUG_SECTION_MISMATCH=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_PAGEALLOC=y
+CONFIG_DEBUG_RODATA_TEST=y
CONFIG_DEBUG_OBJECTS=y
CONFIG_DEBUG_OBJECTS_SELFTEST=y
CONFIG_DEBUG_OBJECTS_FREE=y
@@ -580,7 +599,6 @@
CONFIG_WQ_WATCHDOG=y
CONFIG_PANIC_ON_OOPS=y
CONFIG_DEBUG_TIMEKEEPING=y
-CONFIG_TIMER_STATS=y
CONFIG_DEBUG_RT_MUTEXES=y
CONFIG_DEBUG_WW_MUTEX_SLOWPATH=y
CONFIG_PROVE_LOCKING=y
@@ -595,6 +613,7 @@
CONFIG_RCU_CPU_STALL_TIMEOUT=300
CONFIG_NOTIFIER_ERROR_INJECTION=m
CONFIG_PM_NOTIFIER_ERROR_INJECT=m
+CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m
CONFIG_FAULT_INJECTION=y
CONFIG_FAILSLAB=y
CONFIG_FAIL_PAGE_ALLOC=y
@@ -616,13 +635,12 @@
CONFIG_TRACE_ENUM_MAP_FILE=y
CONFIG_LKDTM=m
CONFIG_TEST_LIST_SORT=y
+CONFIG_TEST_SORT=y
CONFIG_KPROBES_SANITY_TEST=y
CONFIG_RBTREE_TEST=y
CONFIG_INTERVAL_TREE_TEST=m
CONFIG_PERCPU_TEST=m
CONFIG_ATOMIC64_SELFTEST=y
-CONFIG_TEST_STRING_HELPERS=y
-CONFIG_TEST_KSTRTOX=y
CONFIG_DMA_API_DEBUG=y
CONFIG_TEST_BPF=m
CONFIG_BUG_ON_DATA_CORRUPTION=y
@@ -630,6 +648,7 @@
CONFIG_ENCRYPTED_KEYS=m
CONFIG_SECURITY=y
CONFIG_SECURITY_NETWORK=y
+CONFIG_HARDENED_USERCOPY=y
CONFIG_SECURITY_SELINUX=y
CONFIG_SECURITY_SELINUX_BOOTPARAM=y
CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=0
@@ -640,7 +659,9 @@
CONFIG_CRYPTO_DH=m
CONFIG_CRYPTO_ECDH=m
CONFIG_CRYPTO_USER=m
+CONFIG_CRYPTO_PCRYPT=m
CONFIG_CRYPTO_CRYPTD=m
+CONFIG_CRYPTO_MCRYPTD=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CCM=m
CONFIG_CRYPTO_GCM=m
@@ -648,6 +669,7 @@
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_CMAC=m
CONFIG_CRYPTO_XCBC=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_CRC32=m
@@ -657,8 +679,10 @@
CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA512=m
+CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_ANUBIS=m
CONFIG_CRYPTO_BLOWFISH=m
CONFIG_CRYPTO_CAMELLIA=m
@@ -674,6 +698,7 @@
CONFIG_CRYPTO_842=m
CONFIG_CRYPTO_LZ4=m
CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ANSI_CPRNG=m
CONFIG_CRYPTO_USER_API_HASH=m
CONFIG_CRYPTO_USER_API_SKCIPHER=m
CONFIG_CRYPTO_USER_API_RNG=m
@@ -685,6 +710,7 @@
CONFIG_CRYPTO_SHA512_S390=m
CONFIG_CRYPTO_DES_S390=m
CONFIG_CRYPTO_AES_S390=m
+CONFIG_CRYPTO_PAES_S390=m
CONFIG_CRYPTO_GHASH_S390=m
CONFIG_CRYPTO_CRC32_S390=y
CONFIG_ASYMMETRIC_KEY_TYPE=y
@@ -692,6 +718,7 @@
CONFIG_X509_CERTIFICATE_PARSER=m
CONFIG_CRC7=m
CONFIG_CRC8=m
+CONFIG_RANDOM32_SELFTEST=y
CONFIG_CORDIC=m
CONFIG_CMM=m
CONFIG_APPLDATA_BASE=y
diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig
index 83970b5..3c6b781 100644
--- a/arch/s390/configs/gcov_defconfig
+++ b/arch/s390/configs/gcov_defconfig
@@ -31,6 +31,7 @@
CONFIG_SCHED_AUTOGROUP=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_EXPERT=y
+# CONFIG_SYSFS_SYSCALL is not set
CONFIG_BPF_SYSCALL=y
CONFIG_USERFAULTFD=y
# CONFIG_COMPAT_BRK is not set
@@ -46,7 +47,10 @@
CONFIG_MODULE_FORCE_UNLOAD=y
CONFIG_MODVERSIONS=y
CONFIG_MODULE_SRCVERSION_ALL=y
+CONFIG_BLK_DEV_INTEGRITY=y
CONFIG_BLK_DEV_THROTTLING=y
+CONFIG_BLK_WBT=y
+CONFIG_BLK_WBT_SQ=y
CONFIG_PARTITION_ADVANCED=y
CONFIG_IBM_PARTITION=y
CONFIG_BSD_DISKLABEL=y
@@ -88,6 +92,8 @@
CONFIG_UNIX_DIAG=m
CONFIG_XFRM_USER=m
CONFIG_NET_KEY=m
+CONFIG_SMC=m
+CONFIG_SMC_DIAG=m
CONFIG_INET=y
CONFIG_IP_MULTICAST=y
CONFIG_IP_ADVANCED_ROUTER=y
@@ -356,6 +362,7 @@
CONFIG_NET_ACT_SKBEDIT=m
CONFIG_NET_ACT_CSUM=m
CONFIG_DNS_RESOLVER=y
+CONFIG_NETLINK_DIAG=m
CONFIG_CGROUP_NET_PRIO=y
CONFIG_BPF_JIT=y
CONFIG_NET_PKTGEN=m
@@ -364,16 +371,18 @@
CONFIG_DMA_CMA=y
CONFIG_CMA_SIZE_MBYTES=0
CONFIG_CONNECTOR=y
+CONFIG_ZRAM=m
CONFIG_BLK_DEV_LOOP=m
CONFIG_BLK_DEV_CRYPTOLOOP=m
+CONFIG_BLK_DEV_DRBD=m
CONFIG_BLK_DEV_NBD=m
CONFIG_BLK_DEV_OSD=m
CONFIG_BLK_DEV_RAM=y
CONFIG_BLK_DEV_RAM_SIZE=32768
-CONFIG_CDROM_PKTCDVD=m
-CONFIG_ATA_OVER_ETH=m
+CONFIG_BLK_DEV_RAM_DAX=y
CONFIG_VIRTIO_BLK=y
CONFIG_ENCLOSURE_SERVICES=m
+CONFIG_GENWQE=m
CONFIG_RAID_ATTRS=m
CONFIG_SCSI=y
CONFIG_BLK_DEV_SD=y
@@ -439,6 +448,8 @@
# CONFIG_NET_VENDOR_INTEL is not set
# CONFIG_NET_VENDOR_MARVELL is not set
CONFIG_MLX4_EN=m
+CONFIG_MLX5_CORE=m
+CONFIG_MLX5_CORE_EN=y
# CONFIG_NET_VENDOR_NATSEMI is not set
CONFIG_PPP=m
CONFIG_PPP_BSDCOMP=m
@@ -449,7 +460,6 @@
CONFIG_PPPOL2TP=m
CONFIG_PPP_ASYNC=m
CONFIG_PPP_SYNC_TTY=m
-# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
# CONFIG_INPUT_KEYBOARD is not set
# CONFIG_INPUT_MOUSE is not set
# CONFIG_SERIO is not set
@@ -468,6 +478,7 @@
CONFIG_INFINIBAND=m
CONFIG_INFINIBAND_USER_ACCESS=m
CONFIG_MLX4_INFINIBAND=m
+CONFIG_MLX5_INFINIBAND=m
CONFIG_VIRTIO_BALLOON=m
CONFIG_EXT4_FS=y
CONFIG_EXT4_FS_POSIX_ACL=y
@@ -483,11 +494,15 @@
CONFIG_XFS_POSIX_ACL=y
CONFIG_XFS_RT=y
CONFIG_GFS2_FS=m
+CONFIG_GFS2_FS_LOCKING_DLM=y
CONFIG_OCFS2_FS=m
CONFIG_BTRFS_FS=y
CONFIG_BTRFS_FS_POSIX_ACL=y
CONFIG_NILFS2_FS=m
+CONFIG_FS_DAX=y
+CONFIG_EXPORTFS_BLOCK_OPS=y
CONFIG_FANOTIFY=y
+CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y
CONFIG_QUOTA_NETLINK_INTERFACE=y
CONFIG_QFMT_V1=m
CONFIG_QFMT_V2=m
@@ -553,7 +568,6 @@
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_MEMORY_INIT=y
CONFIG_PANIC_ON_OOPS=y
-CONFIG_TIMER_STATS=y
CONFIG_RCU_TORTURE_TEST=m
CONFIG_RCU_CPU_STALL_TIMEOUT=60
CONFIG_LATENCYTOP=y
@@ -576,6 +590,7 @@
CONFIG_ENCRYPTED_KEYS=m
CONFIG_SECURITY=y
CONFIG_SECURITY_NETWORK=y
+CONFIG_HARDENED_USERCOPY=y
CONFIG_SECURITY_SELINUX=y
CONFIG_SECURITY_SELINUX_BOOTPARAM=y
CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=0
@@ -599,6 +614,7 @@
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_CMAC=m
CONFIG_CRYPTO_XCBC=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_CRC32=m
@@ -611,6 +627,7 @@
CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_ANUBIS=m
CONFIG_CRYPTO_BLOWFISH=m
CONFIG_CRYPTO_CAMELLIA=m
@@ -626,16 +643,19 @@
CONFIG_CRYPTO_842=m
CONFIG_CRYPTO_LZ4=m
CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ANSI_CPRNG=m
CONFIG_CRYPTO_USER_API_HASH=m
CONFIG_CRYPTO_USER_API_SKCIPHER=m
CONFIG_CRYPTO_USER_API_RNG=m
CONFIG_CRYPTO_USER_API_AEAD=m
CONFIG_ZCRYPT=m
+CONFIG_PKEY=m
CONFIG_CRYPTO_SHA1_S390=m
CONFIG_CRYPTO_SHA256_S390=m
CONFIG_CRYPTO_SHA512_S390=m
CONFIG_CRYPTO_DES_S390=m
CONFIG_CRYPTO_AES_S390=m
+CONFIG_CRYPTO_PAES_S390=m
CONFIG_CRYPTO_GHASH_S390=m
CONFIG_CRYPTO_CRC32_S390=y
CONFIG_CRC7=m
diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig
index fbc6542..653d72b 100644
--- a/arch/s390/configs/performance_defconfig
+++ b/arch/s390/configs/performance_defconfig
@@ -31,6 +31,7 @@
CONFIG_SCHED_AUTOGROUP=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_EXPERT=y
+# CONFIG_SYSFS_SYSCALL is not set
CONFIG_BPF_SYSCALL=y
CONFIG_USERFAULTFD=y
# CONFIG_COMPAT_BRK is not set
@@ -44,7 +45,10 @@
CONFIG_MODULE_FORCE_UNLOAD=y
CONFIG_MODVERSIONS=y
CONFIG_MODULE_SRCVERSION_ALL=y
+CONFIG_BLK_DEV_INTEGRITY=y
CONFIG_BLK_DEV_THROTTLING=y
+CONFIG_BLK_WBT=y
+CONFIG_BLK_WBT_SQ=y
CONFIG_PARTITION_ADVANCED=y
CONFIG_IBM_PARTITION=y
CONFIG_BSD_DISKLABEL=y
@@ -86,6 +90,8 @@
CONFIG_UNIX_DIAG=m
CONFIG_XFRM_USER=m
CONFIG_NET_KEY=m
+CONFIG_SMC=m
+CONFIG_SMC_DIAG=m
CONFIG_INET=y
CONFIG_IP_MULTICAST=y
CONFIG_IP_ADVANCED_ROUTER=y
@@ -354,6 +360,7 @@
CONFIG_NET_ACT_SKBEDIT=m
CONFIG_NET_ACT_CSUM=m
CONFIG_DNS_RESOLVER=y
+CONFIG_NETLINK_DIAG=m
CONFIG_CGROUP_NET_PRIO=y
CONFIG_BPF_JIT=y
CONFIG_NET_PKTGEN=m
@@ -362,16 +369,18 @@
CONFIG_DMA_CMA=y
CONFIG_CMA_SIZE_MBYTES=0
CONFIG_CONNECTOR=y
+CONFIG_ZRAM=m
CONFIG_BLK_DEV_LOOP=m
CONFIG_BLK_DEV_CRYPTOLOOP=m
+CONFIG_BLK_DEV_DRBD=m
CONFIG_BLK_DEV_NBD=m
CONFIG_BLK_DEV_OSD=m
CONFIG_BLK_DEV_RAM=y
CONFIG_BLK_DEV_RAM_SIZE=32768
-CONFIG_CDROM_PKTCDVD=m
-CONFIG_ATA_OVER_ETH=m
+CONFIG_BLK_DEV_RAM_DAX=y
CONFIG_VIRTIO_BLK=y
CONFIG_ENCLOSURE_SERVICES=m
+CONFIG_GENWQE=m
CONFIG_RAID_ATTRS=m
CONFIG_SCSI=y
CONFIG_BLK_DEV_SD=y
@@ -437,6 +446,8 @@
# CONFIG_NET_VENDOR_INTEL is not set
# CONFIG_NET_VENDOR_MARVELL is not set
CONFIG_MLX4_EN=m
+CONFIG_MLX5_CORE=m
+CONFIG_MLX5_CORE_EN=y
# CONFIG_NET_VENDOR_NATSEMI is not set
CONFIG_PPP=m
CONFIG_PPP_BSDCOMP=m
@@ -447,7 +458,6 @@
CONFIG_PPPOL2TP=m
CONFIG_PPP_ASYNC=m
CONFIG_PPP_SYNC_TTY=m
-# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
# CONFIG_INPUT_KEYBOARD is not set
# CONFIG_INPUT_MOUSE is not set
# CONFIG_SERIO is not set
@@ -466,6 +476,7 @@
CONFIG_INFINIBAND=m
CONFIG_INFINIBAND_USER_ACCESS=m
CONFIG_MLX4_INFINIBAND=m
+CONFIG_MLX5_INFINIBAND=m
CONFIG_VIRTIO_BALLOON=m
CONFIG_EXT4_FS=y
CONFIG_EXT4_FS_POSIX_ACL=y
@@ -481,11 +492,15 @@
CONFIG_XFS_POSIX_ACL=y
CONFIG_XFS_RT=y
CONFIG_GFS2_FS=m
+CONFIG_GFS2_FS_LOCKING_DLM=y
CONFIG_OCFS2_FS=m
CONFIG_BTRFS_FS=y
CONFIG_BTRFS_FS_POSIX_ACL=y
CONFIG_NILFS2_FS=m
+CONFIG_FS_DAX=y
+CONFIG_EXPORTFS_BLOCK_OPS=y
CONFIG_FANOTIFY=y
+CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y
CONFIG_QUOTA_NETLINK_INTERFACE=y
CONFIG_QFMT_V1=m
CONFIG_QFMT_V2=m
@@ -551,7 +566,6 @@
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_MEMORY_INIT=y
CONFIG_PANIC_ON_OOPS=y
-CONFIG_TIMER_STATS=y
CONFIG_RCU_TORTURE_TEST=m
CONFIG_RCU_CPU_STALL_TIMEOUT=60
CONFIG_LATENCYTOP=y
@@ -574,6 +588,7 @@
CONFIG_ENCRYPTED_KEYS=m
CONFIG_SECURITY=y
CONFIG_SECURITY_NETWORK=y
+CONFIG_HARDENED_USERCOPY=y
CONFIG_SECURITY_SELINUX=y
CONFIG_SECURITY_SELINUX_BOOTPARAM=y
CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=0
@@ -597,6 +612,7 @@
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_CMAC=m
CONFIG_CRYPTO_XCBC=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_CRC32=m
@@ -609,6 +625,7 @@
CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_ANUBIS=m
CONFIG_CRYPTO_BLOWFISH=m
CONFIG_CRYPTO_CAMELLIA=m
@@ -624,6 +641,7 @@
CONFIG_CRYPTO_842=m
CONFIG_CRYPTO_LZ4=m
CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ANSI_CPRNG=m
CONFIG_CRYPTO_USER_API_HASH=m
CONFIG_CRYPTO_USER_API_SKCIPHER=m
CONFIG_CRYPTO_USER_API_RNG=m
@@ -635,6 +653,7 @@
CONFIG_CRYPTO_SHA512_S390=m
CONFIG_CRYPTO_DES_S390=m
CONFIG_CRYPTO_AES_S390=m
+CONFIG_CRYPTO_PAES_S390=m
CONFIG_CRYPTO_GHASH_S390=m
CONFIG_CRYPTO_CRC32_S390=y
CONFIG_CRC7=m
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index e23d97c1..afa46a7 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -12,8 +12,10 @@
CONFIG_NR_CPUS=2
# CONFIG_HOTPLUG_CPU is not set
CONFIG_HZ_100=y
+# CONFIG_ARCH_RANDOM is not set
# CONFIG_COMPACTION is not set
# CONFIG_MIGRATION is not set
+# CONFIG_BOUNCE is not set
# CONFIG_CHECK_STACK is not set
# CONFIG_CHSC_SCH is not set
# CONFIG_SCM_BUS is not set
@@ -36,11 +38,11 @@
CONFIG_SCSI_LOGGING=y
CONFIG_SCSI_FC_ATTRS=y
CONFIG_ZFCP=y
-# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
# CONFIG_INPUT_KEYBOARD is not set
# CONFIG_INPUT_MOUSE is not set
# CONFIG_SERIO is not set
# CONFIG_HVC_IUCV is not set
+# CONFIG_HW_RANDOM_S390 is not set
CONFIG_RAW_DRIVER=y
# CONFIG_SCLP_ASYNC is not set
# CONFIG_HMC_DRV is not set
@@ -54,9 +56,9 @@
# CONFIG_INOTIFY_USER is not set
CONFIG_CONFIGFS_FS=y
# CONFIG_MISC_FILESYSTEMS is not set
+# CONFIG_NETWORK_FILESYSTEMS is not set
CONFIG_PRINTK_TIME=y
CONFIG_DEBUG_INFO=y
-CONFIG_DEBUG_FS=y
CONFIG_DEBUG_KERNEL=y
CONFIG_PANIC_ON_OOPS=y
# CONFIG_SCHED_DEBUG is not set
diff --git a/arch/s390/crypto/Makefile b/arch/s390/crypto/Makefile
index 678d986..ad4bd77 100644
--- a/arch/s390/crypto/Makefile
+++ b/arch/s390/crypto/Makefile
@@ -6,7 +6,8 @@
obj-$(CONFIG_CRYPTO_SHA256_S390) += sha256_s390.o sha_common.o
obj-$(CONFIG_CRYPTO_SHA512_S390) += sha512_s390.o sha_common.o
obj-$(CONFIG_CRYPTO_DES_S390) += des_s390.o
-obj-$(CONFIG_CRYPTO_AES_S390) += aes_s390.o paes_s390.o
+obj-$(CONFIG_CRYPTO_AES_S390) += aes_s390.o
+obj-$(CONFIG_CRYPTO_PAES_S390) += paes_s390.o
obj-$(CONFIG_S390_PRNG) += prng.o
obj-$(CONFIG_CRYPTO_GHASH_S390) += ghash_s390.o
obj-$(CONFIG_CRYPTO_CRC32_S390) += crc32-vx_s390.o
diff --git a/arch/s390/crypto/arch_random.c b/arch/s390/crypto/arch_random.c
index 9317b3e..36aefc0 100644
--- a/arch/s390/crypto/arch_random.c
+++ b/arch/s390/crypto/arch_random.c
@@ -12,6 +12,7 @@
#include <linux/kernel.h>
#include <linux/atomic.h>
+#include <linux/random.h>
#include <linux/static_key.h>
#include <asm/cpacf.h>
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index 97189db..20244a3 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -28,6 +28,7 @@
CONFIG_USER_NS=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_EXPERT=y
+# CONFIG_SYSFS_SYSCALL is not set
CONFIG_BPF_SYSCALL=y
CONFIG_USERFAULTFD=y
# CONFIG_COMPAT_BRK is not set
@@ -108,7 +109,6 @@
CONFIG_SCSI_VIRTIO=y
CONFIG_MD=y
CONFIG_MD_LINEAR=m
-CONFIG_MD_RAID0=m
CONFIG_MD_MULTIPATH=m
CONFIG_BLK_DEV_DM=y
CONFIG_DM_CRYPT=m
@@ -131,6 +131,7 @@
CONFIG_VIRTIO_NET=y
# CONFIG_NET_VENDOR_ALACRITECH is not set
# CONFIG_NET_VENDOR_SOLARFLARE is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_INPUT is not set
# CONFIG_SERIO is not set
CONFIG_DEVKMEM=y
@@ -162,7 +163,6 @@
CONFIG_DEBUG_PAGEALLOC=y
CONFIG_DETECT_HUNG_TASK=y
CONFIG_PANIC_ON_OOPS=y
-CONFIG_TIMER_STATS=y
CONFIG_DEBUG_RT_MUTEXES=y
CONFIG_PROVE_LOCKING=y
CONFIG_LOCK_STAT=y
@@ -172,14 +172,12 @@
CONFIG_DEBUG_SG=y
CONFIG_DEBUG_NOTIFIERS=y
CONFIG_RCU_CPU_STALL_TIMEOUT=60
-CONFIG_RCU_TRACE=y
CONFIG_LATENCYTOP=y
CONFIG_SCHED_TRACER=y
CONFIG_FTRACE_SYSCALLS=y
CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y
CONFIG_STACK_TRACER=y
CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENTS=y
CONFIG_FUNCTION_PROFILER=y
CONFIG_TRACE_ENUM_MAP_FILE=y
CONFIG_KPROBES_SANITY_TEST=y
@@ -190,7 +188,6 @@
CONFIG_CRYPTO_GCM=m
CONFIG_CRYPTO_CBC=y
CONFIG_CRYPTO_CTS=m
-CONFIG_CRYPTO_ECB=m
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_XTS=m
@@ -230,6 +227,7 @@
CONFIG_CRYPTO_USER_API_RNG=m
CONFIG_ZCRYPT=m
CONFIG_PKEY=m
+CONFIG_CRYPTO_PAES_S390=m
CONFIG_CRYPTO_SHA1_S390=m
CONFIG_CRYPTO_SHA256_S390=m
CONFIG_CRYPTO_SHA512_S390=m
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild
index 45092b1..b3c8847 100644
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -1,10 +1,12 @@
generic-y += asm-offsets.h
generic-y += cacheflush.h
generic-y += clkdev.h
+generic-y += device.h
generic-y += dma-contiguous.h
generic-y += div64.h
generic-y += emergency-restart.h
generic-y += export.h
+generic-y += fb.h
generic-y += irq_regs.h
generic-y += irq_work.h
generic-y += kmap_types.h
diff --git a/arch/s390/include/asm/debug.h b/arch/s390/include/asm/debug.h
index 0206c80..df7b54e 100644
--- a/arch/s390/include/asm/debug.h
+++ b/arch/s390/include/asm/debug.h
@@ -10,6 +10,7 @@
#include <linux/spinlock.h>
#include <linux/kernel.h>
#include <linux/time.h>
+#include <linux/refcount.h>
#include <uapi/asm/debug.h>
#define DEBUG_MAX_LEVEL 6 /* debug levels range from 0 to 6 */
@@ -31,7 +32,7 @@ struct debug_view;
typedef struct debug_info {
struct debug_info* next;
struct debug_info* prev;
- atomic_t ref_count;
+ refcount_t ref_count;
spinlock_t lock;
int level;
int nr_areas;
diff --git a/arch/s390/include/asm/device.h b/arch/s390/include/asm/device.h
deleted file mode 100644
index 5203fc8..0000000
--- a/arch/s390/include/asm/device.h
+++ /dev/null
@@ -1,10 +0,0 @@
-/*
- * Arch specific extensions to struct device
- *
- * This file is released under the GPLv2
- */
-struct dev_archdata {
-};
-
-struct pdev_archdata {
-};
diff --git a/arch/s390/include/asm/dis.h b/arch/s390/include/asm/dis.h
index 60323c2..37f617d 100644
--- a/arch/s390/include/asm/dis.h
+++ b/arch/s390/include/asm/dis.h
@@ -40,6 +40,8 @@ static inline int insn_length(unsigned char code)
return ((((int) code + 64) >> 7) + 1) << 1;
}
+struct pt_regs;
+
void show_code(struct pt_regs *regs);
void print_fn_code(unsigned char *code, unsigned long len);
int insn_to_mnemonic(unsigned char *instruction, char *buf, unsigned int len);
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index e8f6230..ec024c0 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -117,6 +117,9 @@
#define ELF_DATA ELFDATA2MSB
#define ELF_ARCH EM_S390
+/* s390 specific phdr types */
+#define PT_S390_PGSTE 0x70000000
+
/*
* ELF register definitions..
*/
@@ -151,6 +154,35 @@ extern unsigned int vdso_enabled;
&& (x)->e_ident[EI_CLASS] == ELF_CLASS)
#define compat_start_thread start_thread31
+struct arch_elf_state {
+ int rc;
+};
+
+#define INIT_ARCH_ELF_STATE { .rc = 0 }
+
+#define arch_check_elf(ehdr, interp, interp_ehdr, state) (0)
+#ifdef CONFIG_PGSTE
+#define arch_elf_pt_proc(ehdr, phdr, elf, interp, state) \
+({ \
+ struct arch_elf_state *_state = state; \
+ if ((phdr)->p_type == PT_S390_PGSTE && \
+ !page_table_allocate_pgste && \
+ !test_thread_flag(TIF_PGSTE) && \
+ !current->mm->context.alloc_pgste) { \
+ set_thread_flag(TIF_PGSTE); \
+ set_pt_regs_flag(task_pt_regs(current), \
+ PIF_SYSCALL_RESTART); \
+ _state->rc = -EAGAIN; \
+ } \
+ _state->rc; \
+})
+#else
+#define arch_elf_pt_proc(ehdr, phdr, elf, interp, state) \
+({ \
+ (state)->rc; \
+})
+#endif
+
/* For SVR4/S390 the function pointer to be registered with `atexit` is
passed in R14. */
#define ELF_PLAT_INIT(_r, load_addr) \
diff --git a/arch/s390/include/asm/fb.h b/arch/s390/include/asm/fb.h
deleted file mode 100644
index c7df380..0000000
--- a/arch/s390/include/asm/fb.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef _ASM_FB_H_
-#define _ASM_FB_H_
-#include <linux/fb.h>
-
-#define fb_pgprotect(...) do {} while (0)
-
-static inline int fb_is_primary_device(struct fb_info *info)
-{
- return 0;
-}
-
-#endif /* _ASM_FB_H_ */
diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h
index 437e9af..904e4b3 100644
--- a/arch/s390/include/asm/io.h
+++ b/arch/s390/include/asm/io.h
@@ -25,8 +25,6 @@ void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr);
#define IO_SPACE_LIMIT 0
-#ifdef CONFIG_PCI
-
#define ioremap_nocache(addr, size) ioremap(addr, size)
#define ioremap_wc ioremap_nocache
#define ioremap_wt ioremap_nocache
@@ -49,6 +47,8 @@ static inline void ioport_unmap(void __iomem *p)
{
}
+#ifdef CONFIG_PCI
+
/*
* s390 needs a private implementation of pci_iomap since ioremap with its
* offset parameter isn't sufficient. That's because BAR spaces are not
diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h
index 1293c40..28792ef 100644
--- a/arch/s390/include/asm/kprobes.h
+++ b/arch/s390/include/asm/kprobes.h
@@ -27,12 +27,21 @@
* 2005-Dec Used as a template for s390 by Mike Grundy
* <grundym@us.ibm.com>
*/
+#include <linux/types.h>
#include <asm-generic/kprobes.h>
#define BREAKPOINT_INSTRUCTION 0x0002
+#define FIXUP_PSW_NORMAL 0x08
+#define FIXUP_BRANCH_NOT_TAKEN 0x04
+#define FIXUP_RETURN_REGISTER 0x02
+#define FIXUP_NOT_REQUIRED 0x01
+
+int probe_is_prohibited_opcode(u16 *insn);
+int probe_get_fixup_type(u16 *insn);
+int probe_is_insn_relative_long(u16 *insn);
+
#ifdef CONFIG_KPROBES
-#include <linux/types.h>
#include <linux/ptrace.h>
#include <linux/percpu.h>
#include <linux/sched/task_stack.h>
@@ -56,11 +65,6 @@ typedef u16 kprobe_opcode_t;
#define KPROBE_SWAP_INST 0x10
-#define FIXUP_PSW_NORMAL 0x08
-#define FIXUP_BRANCH_NOT_TAKEN 0x04
-#define FIXUP_RETURN_REGISTER 0x02
-#define FIXUP_NOT_REQUIRED 0x01
-
/* Architecture specific copy of original instruction */
struct arch_specific_insn {
/* copy of original instruction */
@@ -90,10 +94,6 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
int kprobe_exceptions_notify(struct notifier_block *self,
unsigned long val, void *data);
-int probe_is_prohibited_opcode(u16 *insn);
-int probe_get_fixup_type(u16 *insn);
-int probe_is_insn_relative_long(u16 *insn);
-
#define flush_insn_slot(p) do { } while (0)
#endif /* CONFIG_KPROBES */
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index 8712e11..4541ac4 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -25,7 +25,9 @@ static inline int init_new_context(struct task_struct *tsk,
mm->context.gmap_asce = 0;
mm->context.flush_mm = 0;
#ifdef CONFIG_PGSTE
- mm->context.alloc_pgste = page_table_allocate_pgste;
+ mm->context.alloc_pgste = page_table_allocate_pgste ||
+ test_thread_flag(TIF_PGSTE) ||
+ current->mm->context.alloc_pgste;
mm->context.has_pgste = 0;
mm->context.use_skey = 0;
mm->context.use_cmma = 0;
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index 69b8a41..624deaa 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -74,6 +74,7 @@ typedef struct { unsigned long pgste; } pgste_t;
typedef struct { unsigned long pte; } pte_t;
typedef struct { unsigned long pmd; } pmd_t;
typedef struct { unsigned long pud; } pud_t;
+typedef struct { unsigned long p4d; } p4d_t;
typedef struct { unsigned long pgd; } pgd_t;
typedef pte_t *pgtable_t;
@@ -82,12 +83,14 @@ typedef pte_t *pgtable_t;
#define pte_val(x) ((x).pte)
#define pmd_val(x) ((x).pmd)
#define pud_val(x) ((x).pud)
+#define p4d_val(x) ((x).p4d)
#define pgd_val(x) ((x).pgd)
#define __pgste(x) ((pgste_t) { (x) } )
#define __pte(x) ((pte_t) { (x) } )
#define __pmd(x) ((pmd_t) { (x) } )
#define __pud(x) ((pud_t) { (x) } )
+#define __p4d(x) ((p4d_t) { (x) } )
#define __pgd(x) ((pgd_t) { (x) } )
#define __pgprot(x) ((pgprot_t) { (x) } )
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 4e31866..f36b4b7 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -70,11 +70,10 @@ struct zpci_fmb {
} __packed __aligned(128);
enum zpci_state {
- ZPCI_FN_STATE_RESERVED,
- ZPCI_FN_STATE_STANDBY,
- ZPCI_FN_STATE_CONFIGURED,
- ZPCI_FN_STATE_ONLINE,
- NR_ZPCI_FN_STATES,
+ ZPCI_FN_STATE_STANDBY = 0,
+ ZPCI_FN_STATE_CONFIGURED = 1,
+ ZPCI_FN_STATE_RESERVED = 2,
+ ZPCI_FN_STATE_ONLINE = 3,
};
struct zpci_bar_struct {
@@ -109,7 +108,7 @@ struct zpci_dev {
u64 msi_addr; /* MSI address */
unsigned int max_msi; /* maximum number of MSI's */
struct airq_iv *aibv; /* adapter interrupt bit vector */
- unsigned int aisb; /* number of the summary bit */
+ unsigned long aisb; /* number of the summary bit */
/* DMA stuff */
unsigned long *dma_table;
@@ -159,11 +158,12 @@ extern const struct attribute_group *zpci_attr_groups[];
----------------------------------------------------------------------------- */
/* Base stuff */
int zpci_create_device(struct zpci_dev *);
+void zpci_remove_device(struct zpci_dev *zdev);
int zpci_enable_device(struct zpci_dev *);
int zpci_disable_device(struct zpci_dev *);
-void zpci_stop_device(struct zpci_dev *);
int zpci_register_ioat(struct zpci_dev *, u8, u64, u64, u64);
int zpci_unregister_ioat(struct zpci_dev *, u8);
+void zpci_remove_reserved_devices(void);
/* CLP */
int clp_scan_pci_devices(void);
@@ -172,6 +172,7 @@ int clp_rescan_pci_devices_simple(void);
int clp_add_pci_device(u32, u32, int);
int clp_enable_fh(struct zpci_dev *, u8);
int clp_disable_fh(struct zpci_dev *);
+int clp_get_state(u32 fid, enum zpci_state *state);
#ifdef CONFIG_PCI
/* Error handling and recovery */
diff --git a/arch/s390/include/asm/pci_insn.h b/arch/s390/include/asm/pci_insn.h
index 649eb62..34abcf2 100644
--- a/arch/s390/include/asm/pci_insn.h
+++ b/arch/s390/include/asm/pci_insn.h
@@ -76,7 +76,7 @@ struct zpci_fib {
u32 gd;
} __packed __aligned(8);
-int zpci_mod_fc(u64 req, struct zpci_fib *fib);
+u8 zpci_mod_fc(u64 req, struct zpci_fib *fib, u8 *status);
int zpci_refresh_trans(u64 fn, u64 addr, u64 range);
int zpci_load(u64 *data, u64 req, u64 offset);
int zpci_store(u64 data, u64 req, u64 offset);
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index 166f703..bb0ff1b 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -51,12 +51,24 @@ static inline unsigned long pgd_entry_type(struct mm_struct *mm)
return _SEGMENT_ENTRY_EMPTY;
if (mm->context.asce_limit <= (1UL << 42))
return _REGION3_ENTRY_EMPTY;
- return _REGION2_ENTRY_EMPTY;
+ if (mm->context.asce_limit <= (1UL << 53))
+ return _REGION2_ENTRY_EMPTY;
+ return _REGION1_ENTRY_EMPTY;
}
-int crst_table_upgrade(struct mm_struct *);
+int crst_table_upgrade(struct mm_struct *mm, unsigned long limit);
void crst_table_downgrade(struct mm_struct *);
+static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long address)
+{
+ unsigned long *table = crst_table_alloc(mm);
+
+ if (table)
+ crst_table_init(table, _REGION2_ENTRY_EMPTY);
+ return (p4d_t *) table;
+}
+#define p4d_free(mm, p4d) crst_table_free(mm, (unsigned long *) p4d)
+
static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
{
unsigned long *table = crst_table_alloc(mm);
@@ -86,9 +98,14 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
crst_table_free(mm, (unsigned long *) pmd);
}
-static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
+static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d)
{
- pgd_val(*pgd) = _REGION2_ENTRY | __pa(pud);
+ pgd_val(*pgd) = _REGION1_ENTRY | __pa(p4d);
+}
+
+static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud)
+{
+ p4d_val(*p4d) = _REGION2_ENTRY | __pa(pud);
}
static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index e6e3b88..57057fb 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -24,7 +24,6 @@
* the S390 page table tree.
*/
#ifndef __ASSEMBLY__
-#include <asm-generic/5level-fixup.h>
#include <linux/sched.h>
#include <linux/mm_types.h>
#include <linux/page-flags.h>
@@ -87,12 +86,15 @@ extern unsigned long zero_page_mask;
*/
#define PMD_SHIFT 20
#define PUD_SHIFT 31
-#define PGDIR_SHIFT 42
+#define P4D_SHIFT 42
+#define PGDIR_SHIFT 53
#define PMD_SIZE (1UL << PMD_SHIFT)
#define PMD_MASK (~(PMD_SIZE-1))
#define PUD_SIZE (1UL << PUD_SHIFT)
#define PUD_MASK (~(PUD_SIZE-1))
+#define P4D_SIZE (1UL << P4D_SHIFT)
+#define P4D_MASK (~(P4D_SIZE-1))
#define PGDIR_SIZE (1UL << PGDIR_SHIFT)
#define PGDIR_MASK (~(PGDIR_SIZE-1))
@@ -105,6 +107,7 @@ extern unsigned long zero_page_mask;
#define PTRS_PER_PTE 256
#define PTRS_PER_PMD 2048
#define PTRS_PER_PUD 2048
+#define PTRS_PER_P4D 2048
#define PTRS_PER_PGD 2048
#define FIRST_USER_ADDRESS 0UL
@@ -115,6 +118,8 @@ extern unsigned long zero_page_mask;
printk("%s:%d: bad pmd %p.\n", __FILE__, __LINE__, (void *) pmd_val(e))
#define pud_ERROR(e) \
printk("%s:%d: bad pud %p.\n", __FILE__, __LINE__, (void *) pud_val(e))
+#define p4d_ERROR(e) \
+ printk("%s:%d: bad p4d %p.\n", __FILE__, __LINE__, (void *) p4d_val(e))
#define pgd_ERROR(e) \
printk("%s:%d: bad pgd %p.\n", __FILE__, __LINE__, (void *) pgd_val(e))
@@ -296,8 +301,6 @@ static inline int is_module_addr(void *addr)
#define _REGION3_ENTRY_EMPTY (_REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_INVALID)
#define _REGION3_ENTRY_ORIGIN_LARGE ~0x7fffffffUL /* large page address */
-#define _REGION3_ENTRY_ORIGIN ~0x7ffUL/* region third table origin */
-
#define _REGION3_ENTRY_DIRTY 0x2000 /* SW region dirty bit */
#define _REGION3_ENTRY_YOUNG 0x1000 /* SW region young bit */
#define _REGION3_ENTRY_LARGE 0x0400 /* RTTE-format control, large page */
@@ -310,8 +313,8 @@ static inline int is_module_addr(void *addr)
#define _REGION3_ENTRY_SOFT_DIRTY 0x0000 /* SW region soft dirty bit */
#endif
-#define _REGION_ENTRY_BITS 0xfffffffffffff227UL
-#define _REGION_ENTRY_BITS_LARGE 0xffffffff8000fe27UL
+#define _REGION_ENTRY_BITS 0xfffffffffffff22fUL
+#define _REGION_ENTRY_BITS_LARGE 0xffffffff8000fe2fUL
/* Bits in the segment table entry */
#define _SEGMENT_ENTRY_BITS 0xfffffffffffffe33UL
@@ -560,18 +563,23 @@ static inline void crdte(unsigned long old, unsigned long new,
}
/*
- * pgd/pmd/pte query functions
+ * pgd/p4d/pud/pmd/pte query functions
*/
+static inline int pgd_folded(pgd_t pgd)
+{
+ return (pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R1;
+}
+
static inline int pgd_present(pgd_t pgd)
{
- if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R2)
+ if (pgd_folded(pgd))
return 1;
return (pgd_val(pgd) & _REGION_ENTRY_ORIGIN) != 0UL;
}
static inline int pgd_none(pgd_t pgd)
{
- if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R2)
+ if (pgd_folded(pgd))
return 0;
return (pgd_val(pgd) & _REGION_ENTRY_INVALID) != 0UL;
}
@@ -589,16 +597,48 @@ static inline int pgd_bad(pgd_t pgd)
return (pgd_val(pgd) & mask) != 0;
}
+static inline int p4d_folded(p4d_t p4d)
+{
+ return (p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R2;
+}
+
+static inline int p4d_present(p4d_t p4d)
+{
+ if (p4d_folded(p4d))
+ return 1;
+ return (p4d_val(p4d) & _REGION_ENTRY_ORIGIN) != 0UL;
+}
+
+static inline int p4d_none(p4d_t p4d)
+{
+ if (p4d_folded(p4d))
+ return 0;
+ return p4d_val(p4d) == _REGION2_ENTRY_EMPTY;
+}
+
+static inline unsigned long p4d_pfn(p4d_t p4d)
+{
+ unsigned long origin_mask;
+
+ origin_mask = _REGION_ENTRY_ORIGIN;
+ return (p4d_val(p4d) & origin_mask) >> PAGE_SHIFT;
+}
+
+static inline int pud_folded(pud_t pud)
+{
+ return (pud_val(pud) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R3;
+}
+
static inline int pud_present(pud_t pud)
{
- if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R3)
+ if (pud_folded(pud))
return 1;
return (pud_val(pud) & _REGION_ENTRY_ORIGIN) != 0UL;
}
static inline int pud_none(pud_t pud)
{
- if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R3)
+ if (pud_folded(pud))
return 0;
return pud_val(pud) == _REGION3_ENTRY_EMPTY;
}
@@ -614,7 +654,7 @@ static inline unsigned long pud_pfn(pud_t pud)
{
unsigned long origin_mask;
- origin_mask = _REGION3_ENTRY_ORIGIN;
+ origin_mask = _REGION_ENTRY_ORIGIN;
if (pud_large(pud))
origin_mask = _REGION3_ENTRY_ORIGIN_LARGE;
return (pud_val(pud) & origin_mask) >> PAGE_SHIFT;
@@ -641,6 +681,13 @@ static inline int pud_bad(pud_t pud)
return (pud_val(pud) & ~_REGION_ENTRY_BITS) != 0;
}
+static inline int p4d_bad(p4d_t p4d)
+{
+ if ((p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R2)
+ return pud_bad(__pud(p4d_val(p4d)));
+ return (p4d_val(p4d) & ~_REGION_ENTRY_BITS) != 0;
+}
+
static inline int pmd_present(pmd_t pmd)
{
return pmd_val(pmd) != _SEGMENT_ENTRY_EMPTY;
@@ -794,8 +841,14 @@ static inline int pte_unused(pte_t pte)
static inline void pgd_clear(pgd_t *pgd)
{
- if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2)
- pgd_val(*pgd) = _REGION2_ENTRY_EMPTY;
+ if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R1)
+ pgd_val(*pgd) = _REGION1_ENTRY_EMPTY;
+}
+
+static inline void p4d_clear(p4d_t *p4d)
+{
+ if ((p4d_val(*p4d) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2)
+ p4d_val(*p4d) = _REGION2_ENTRY_EMPTY;
}
static inline void pud_clear(pud_t *pud)
@@ -1089,6 +1142,7 @@ static inline pte_t mk_pte(struct page *page, pgprot_t pgprot)
}
#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD-1))
+#define p4d_index(address) (((address) >> P4D_SHIFT) & (PTRS_PER_P4D-1))
#define pud_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1))
#define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
#define pte_index(address) (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE-1))
@@ -1098,19 +1152,31 @@ static inline pte_t mk_pte(struct page *page, pgprot_t pgprot)
#define pmd_deref(pmd) (pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN)
#define pud_deref(pud) (pud_val(pud) & _REGION_ENTRY_ORIGIN)
+#define p4d_deref(pud) (p4d_val(pud) & _REGION_ENTRY_ORIGIN)
#define pgd_deref(pgd) (pgd_val(pgd) & _REGION_ENTRY_ORIGIN)
-static inline pud_t *pud_offset(pgd_t *pgd, unsigned long address)
+static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
{
- pud_t *pud = (pud_t *) pgd;
- if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2)
- pud = (pud_t *) pgd_deref(*pgd);
- return pud + pud_index(address);
+ p4d_t *p4d = (p4d_t *) pgd;
+
+ if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R1)
+ p4d = (p4d_t *) pgd_deref(*pgd);
+ return p4d + p4d_index(address);
+}
+
+static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
+{
+ pud_t *pud = (pud_t *) p4d;
+
+ if ((p4d_val(*p4d) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2)
+ pud = (pud_t *) p4d_deref(*p4d);
+ return pud + pud_index(address);
}
static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
{
pmd_t *pmd = (pmd_t *) pud;
+
if ((pud_val(*pud) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3)
pmd = (pmd_t *) pud_deref(*pud);
return pmd + pmd_index(address);
@@ -1122,6 +1188,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
#define pmd_page(pmd) pfn_to_page(pmd_pfn(pmd))
#define pud_page(pud) pfn_to_page(pud_pfn(pud))
+#define p4d_page(pud) pfn_to_page(p4d_pfn(p4d))
/* Find an entry in the lowest level page table.. */
#define pte_offset(pmd, addr) ((pte_t *) pmd_deref(*(pmd)) + pte_index(addr))
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 5b1b247..72c7b88 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -94,11 +94,11 @@ extern void execve_tail(void);
*/
#define TASK_SIZE_OF(tsk) (test_tsk_thread_flag(tsk, TIF_31BIT) ? \
- (1UL << 31) : (1UL << 53))
+ (1UL << 31) : -PAGE_SIZE)
#define TASK_UNMAPPED_BASE (test_thread_flag(TIF_31BIT) ? \
(1UL << 30) : (1UL << 41))
#define TASK_SIZE TASK_SIZE_OF(current)
-#define TASK_SIZE_MAX (1UL << 53)
+#define TASK_SIZE_MAX (-PAGE_SIZE)
#define STACK_TOP (test_thread_flag(TIF_31BIT) ? \
(1UL << 31) : (1UL << 42))
diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h
index 99bc456..853b012 100644
--- a/arch/s390/include/asm/ptrace.h
+++ b/arch/s390/include/asm/ptrace.h
@@ -11,9 +11,11 @@
#define PIF_SYSCALL 0 /* inside a system call */
#define PIF_PER_TRAP 1 /* deliver sigtrap on return to user */
+#define PIF_SYSCALL_RESTART 2 /* restart the current system call */
#define _PIF_SYSCALL _BITUL(PIF_SYSCALL)
#define _PIF_PER_TRAP _BITUL(PIF_PER_TRAP)
+#define _PIF_SYSCALL_RESTART _BITUL(PIF_SYSCALL_RESTART)
#ifndef __ASSEMBLY__
@@ -24,38 +26,38 @@
PSW_MASK_PSTATE | PSW_ASC_PRIMARY)
struct psw_bits {
- unsigned long : 1;
- unsigned long r : 1; /* PER-Mask */
- unsigned long : 3;
- unsigned long t : 1; /* DAT Mode */
- unsigned long i : 1; /* Input/Output Mask */
- unsigned long e : 1; /* External Mask */
- unsigned long key : 4; /* PSW Key */
- unsigned long : 1;
- unsigned long m : 1; /* Machine-Check Mask */
- unsigned long w : 1; /* Wait State */
- unsigned long p : 1; /* Problem State */
- unsigned long as : 2; /* Address Space Control */
- unsigned long cc : 2; /* Condition Code */
- unsigned long pm : 4; /* Program Mask */
- unsigned long ri : 1; /* Runtime Instrumentation */
- unsigned long : 6;
- unsigned long eaba : 2; /* Addressing Mode */
- unsigned long : 31;
- unsigned long ia : 64; /* Instruction Address */
+ unsigned long : 1;
+ unsigned long per : 1; /* PER-Mask */
+ unsigned long : 3;
+ unsigned long dat : 1; /* DAT Mode */
+ unsigned long io : 1; /* Input/Output Mask */
+ unsigned long ext : 1; /* External Mask */
+ unsigned long key : 4; /* PSW Key */
+ unsigned long : 1;
+ unsigned long mcheck : 1; /* Machine-Check Mask */
+ unsigned long wait : 1; /* Wait State */
+ unsigned long pstate : 1; /* Problem State */
+ unsigned long as : 2; /* Address Space Control */
+ unsigned long cc : 2; /* Condition Code */
+ unsigned long pm : 4; /* Program Mask */
+ unsigned long ri : 1; /* Runtime Instrumentation */
+ unsigned long : 6;
+ unsigned long eaba : 2; /* Addressing Mode */
+ unsigned long : 31;
+ unsigned long ia : 64; /* Instruction Address */
};
enum {
- PSW_AMODE_24BIT = 0,
- PSW_AMODE_31BIT = 1,
- PSW_AMODE_64BIT = 3
+ PSW_BITS_AMODE_24BIT = 0,
+ PSW_BITS_AMODE_31BIT = 1,
+ PSW_BITS_AMODE_64BIT = 3
};
enum {
- PSW_AS_PRIMARY = 0,
- PSW_AS_ACCREG = 1,
- PSW_AS_SECONDARY = 2,
- PSW_AS_HOME = 3
+ PSW_BITS_AS_PRIMARY = 0,
+ PSW_BITS_AS_ACCREG = 1,
+ PSW_BITS_AS_SECONDARY = 2,
+ PSW_BITS_AS_HOME = 3
};
#define psw_bits(__psw) (*({ \
diff --git a/arch/s390/include/asm/sigp.h b/arch/s390/include/asm/sigp.h
index 72df5f2..020a881 100644
--- a/arch/s390/include/asm/sigp.h
+++ b/arch/s390/include/asm/sigp.h
@@ -59,7 +59,7 @@ static inline int __pcpu_sigp(u16 addr, u8 order, unsigned long parm,
int cc;
cc = ____pcpu_sigp(addr, order, parm, &_status);
- if (status && cc == 1)
+ if (status && cc == SIGP_CC_STATUS_STORED)
*status = _status;
return cc;
}
diff --git a/arch/s390/include/asm/sysinfo.h b/arch/s390/include/asm/sysinfo.h
index 73bff45..e784bed 100644
--- a/arch/s390/include/asm/sysinfo.h
+++ b/arch/s390/include/asm/sysinfo.h
@@ -146,7 +146,7 @@ extern int topology_max_mnest;
* Returns the maximum nesting level supported by the cpu topology code.
* The current maximum level is 4 which is the drawer level.
*/
-static inline int topology_mnest_limit(void)
+static inline unsigned char topology_mnest_limit(void)
{
return min(topology_max_mnest, 4);
}
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index 0b3ee08..1aecf43 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -58,6 +58,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
#define TIF_UPROBE 3 /* breakpointed or single-stepping */
#define TIF_GUARDED_STORAGE 4 /* load guarded storage control block */
#define TIF_PATCH_PENDING 5 /* pending live patching update */
+#define TIF_PGSTE 6 /* New mm's will use 4K page tables */
#define TIF_31BIT 16 /* 32bit process */
#define TIF_MEMDIE 17 /* is terminating due to OOM killer */
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index 853b2a3..7317b31 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -137,6 +137,21 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
}
/*
+ * p4d_free_tlb frees a pud table and clears the CRSTE for the
+ * region second table entry from the tlb.
+ * If the mm uses a four level page table the single p4d is freed
+ * as the pgd. p4d_free_tlb checks the asce_limit against 8PB
+ * to avoid the double free of the p4d in this case.
+ */
+static inline void p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
+ unsigned long address)
+{
+ if (tlb->mm->context.asce_limit <= (1UL << 53))
+ return;
+ tlb_remove_table(tlb, p4d);
+}
+
+/*
* pud_free_tlb frees a pud table and clears the CRSTE for the
* region third table entry from the tlb.
* If the mm uses a three level page table the single pud is freed
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index 530226b..86b3e74 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -277,7 +277,7 @@ debug_info_alloc(const char *name, int pages_per_area, int nr_areas,
memset(rc->views, 0, DEBUG_MAX_VIEWS * sizeof(struct debug_view *));
memset(rc->debugfs_entries, 0 ,DEBUG_MAX_VIEWS *
sizeof(struct dentry*));
- atomic_set(&(rc->ref_count), 0);
+ refcount_set(&(rc->ref_count), 0);
return rc;
@@ -361,7 +361,7 @@ debug_info_create(const char *name, int pages_per_area, int nr_areas,
debug_area_last = rc;
rc->next = NULL;
- debug_info_get(rc);
+ refcount_set(&rc->ref_count, 1);
out:
return rc;
}
@@ -416,7 +416,7 @@ static void
debug_info_get(debug_info_t * db_info)
{
if (db_info)
- atomic_inc(&db_info->ref_count);
+ refcount_inc(&db_info->ref_count);
}
/*
@@ -431,7 +431,7 @@ debug_info_put(debug_info_t *db_info)
if (!db_info)
return;
- if (atomic_dec_and_test(&db_info->ref_count)) {
+ if (refcount_dec_and_test(&db_info->ref_count)) {
for (i = 0; i < DEBUG_MAX_VIEWS; i++) {
if (!db_info->views[i])
continue;
diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c
index 829e1c5..dab78ba 100644
--- a/arch/s390/kernel/dumpstack.c
+++ b/arch/s390/kernel/dumpstack.c
@@ -98,8 +98,10 @@ static int show_address(void *data, unsigned long address, int reliable)
return 0;
}
-static void show_trace(struct task_struct *task, unsigned long sp)
+void show_stack(struct task_struct *task, unsigned long *stack)
{
+ unsigned long sp = (unsigned long) stack;
+
if (!sp)
sp = task ? task->thread.ksp : current_stack_pointer();
printk("Call Trace:\n");
@@ -109,29 +111,6 @@ static void show_trace(struct task_struct *task, unsigned long sp)
debug_show_held_locks(task);
}
-void show_stack(struct task_struct *task, unsigned long *sp)
-{
- unsigned long *stack;
- int i;
-
- stack = sp;
- if (!stack) {
- if (!task)
- stack = (unsigned long *)current_stack_pointer();
- else
- stack = (unsigned long *)task->thread.ksp;
- }
- printk(KERN_DEFAULT "Stack:\n");
- for (i = 0; i < 20; i++) {
- if (((addr_t) stack & (THREAD_SIZE-1)) == 0)
- break;
- if (i % 4 == 0)
- printk(KERN_DEFAULT " ");
- pr_cont("%016lx%c", *stack++, i % 4 == 3 ? '\n' : ' ');
- }
- show_trace(task, (unsigned long)sp);
-}
-
static void show_last_breaking_event(struct pt_regs *regs)
{
printk("Last Breaking-Event-Address:\n");
@@ -149,8 +128,8 @@ void show_registers(struct pt_regs *regs)
pr_cont(" (%pSR)", (void *)regs->psw.addr);
pr_cont("\n");
printk(" R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x "
- "P:%x AS:%x CC:%x PM:%x", psw->r, psw->t, psw->i, psw->e,
- psw->key, psw->m, psw->w, psw->p, psw->as, psw->cc, psw->pm);
+ "P:%x AS:%x CC:%x PM:%x", psw->per, psw->dat, psw->io, psw->ext,
+ psw->key, psw->mcheck, psw->wait, psw->pstate, psw->as, psw->cc, psw->pm);
pr_cont(" RI:%x EA:%x\n", psw->ri, psw->eaba);
printk("%s GPRS: %016lx %016lx %016lx %016lx\n", mode,
regs->gprs[0], regs->gprs[1], regs->gprs[2], regs->gprs[3]);
@@ -169,7 +148,7 @@ void show_regs(struct pt_regs *regs)
show_registers(regs);
/* Show stack backtrace if pt_regs is from kernel mode */
if (!user_mode(regs))
- show_trace(NULL, regs->gprs[15]);
+ show_stack(NULL, (unsigned long *) regs->gprs[15]);
show_last_breaking_event(regs);
}
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 9b48196..21900e1 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -52,7 +52,7 @@
_TIF_SYSCALL_TRACEPOINT)
_CIF_WORK = (_CIF_MCCK_PENDING | _CIF_ASCE_PRIMARY | \
_CIF_ASCE_SECONDARY | _CIF_FPU)
-_PIF_WORK = (_PIF_PER_TRAP)
+_PIF_WORK = (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART)
#define BASED(name) name-cleanup_critical(%r13)
@@ -232,12 +232,17 @@
lctlg %c1,%c1,__LC_USER_ASCE # load primary asce
.Lsie_done:
# some program checks are suppressing. C code (e.g. do_protection_exception)
-# will rewind the PSW by the ILC, which is 4 bytes in case of SIE. Other
-# instructions between sie64a and .Lsie_done should not cause program
-# interrupts. So lets use a nop (47 00 00 00) as a landing pad.
+# will rewind the PSW by the ILC, which is often 4 bytes in case of SIE. There
+# are some corner cases (e.g. runtime instrumentation) where ILC is unpredictable.
+# Other instructions between sie64a and .Lsie_done should not cause program
+# interrupts. So lets use 3 nops as a landing pad for all possible rewinds.
# See also .Lcleanup_sie
-.Lrewind_pad:
- nop 0
+.Lrewind_pad6:
+ nopr 7
+.Lrewind_pad4:
+ nopr 7
+.Lrewind_pad2:
+ nopr 7
.globl sie_exit
sie_exit:
lg %r14,__SF_EMPTY+8(%r15) # load guest register save area
@@ -250,7 +255,9 @@
stg %r14,__SF_EMPTY+16(%r15) # set exit reason code
j sie_exit
- EX_TABLE(.Lrewind_pad,.Lsie_fault)
+ EX_TABLE(.Lrewind_pad6,.Lsie_fault)
+ EX_TABLE(.Lrewind_pad4,.Lsie_fault)
+ EX_TABLE(.Lrewind_pad2,.Lsie_fault)
EX_TABLE(sie_exit,.Lsie_fault)
EXPORT_SYMBOL(sie64a)
EXPORT_SYMBOL(sie_exit)
@@ -313,6 +320,7 @@
lg %r14,__LC_VDSO_PER_CPU
lmg %r0,%r10,__PT_R0(%r11)
mvc __LC_RETURN_PSW(16),__PT_PSW(%r11)
+.Lsysc_exit_timer:
stpt __LC_EXIT_TIMER
mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
lmg %r11,%r15,__PT_R11(%r11)
@@ -327,6 +335,8 @@
jo .Lsysc_mcck_pending
TSTMSK __TI_flags(%r12),_TIF_NEED_RESCHED
jo .Lsysc_reschedule
+ TSTMSK __PT_FLAGS(%r11),_PIF_SYSCALL_RESTART
+ jo .Lsysc_syscall_restart
#ifdef CONFIG_UPROBES
TSTMSK __TI_flags(%r12),_TIF_UPROBE
jo .Lsysc_uprobe_notify
@@ -340,6 +350,8 @@
jo .Lsysc_patch_pending # handle live patching just before
# signals and possible syscall restart
#endif
+ TSTMSK __PT_FLAGS(%r11),_PIF_SYSCALL_RESTART
+ jo .Lsysc_syscall_restart
TSTMSK __TI_flags(%r12),_TIF_SIGPENDING
jo .Lsysc_sigpending
TSTMSK __TI_flags(%r12),_TIF_NOTIFY_RESUME
@@ -441,6 +453,15 @@
jg do_per_trap
#
+# _PIF_SYSCALL_RESTART is set, repeat the current system call
+#
+.Lsysc_syscall_restart:
+ ni __PT_FLAGS+7(%r11),255-_PIF_SYSCALL_RESTART
+ lmg %r1,%r7,__PT_R1(%r11) # load svc arguments
+ lg %r2,__PT_ORIG_GPR2(%r11)
+ j .Lsysc_do_svc
+
+#
# call tracehook_report_syscall_entry/tracehook_report_syscall_exit before
# and after the system call
#
@@ -624,6 +645,7 @@
lg %r14,__LC_VDSO_PER_CPU
lmg %r0,%r10,__PT_R0(%r11)
mvc __LC_RETURN_PSW(16),__PT_PSW(%r11)
+.Lio_exit_timer:
stpt __LC_EXIT_TIMER
mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
lmg %r11,%r15,__PT_R11(%r11)
@@ -873,9 +895,7 @@
oi __LC_CPU_FLAGS+7,_CIF_FPU
br %r14
.Lsave_fpu_regs_end:
-#if IS_ENABLED(CONFIG_KVM)
EXPORT_SYMBOL(save_fpu_regs)
-#endif
/*
* Load floating-point controls and floating-point or vector registers.
@@ -1181,15 +1201,23 @@
br %r14
.Lcleanup_sysc_restore:
+ # check if stpt has been executed
clg %r9,BASED(.Lcleanup_sysc_restore_insn)
+ jh 0f
+ mvc __LC_EXIT_TIMER(8),__LC_ASYNC_ENTER_TIMER
+ cghi %r11,__LC_SAVE_AREA_ASYNC
je 0f
+ mvc __LC_EXIT_TIMER(8),__LC_MCCK_ENTER_TIMER
+0: clg %r9,BASED(.Lcleanup_sysc_restore_insn+8)
+ je 1f
lg %r9,24(%r11) # get saved pointer to pt_regs
mvc __LC_RETURN_PSW(16),__PT_PSW(%r9)
mvc 0(64,%r11),__PT_R8(%r9)
lmg %r0,%r7,__PT_R0(%r9)
-0: lmg %r8,%r9,__LC_RETURN_PSW
+1: lmg %r8,%r9,__LC_RETURN_PSW
br %r14
.Lcleanup_sysc_restore_insn:
+ .quad .Lsysc_exit_timer
.quad .Lsysc_done - 4
.Lcleanup_io_tif:
@@ -1197,15 +1225,20 @@
br %r14
.Lcleanup_io_restore:
+ # check if stpt has been executed
clg %r9,BASED(.Lcleanup_io_restore_insn)
- je 0f
+ jh 0f
+ mvc __LC_EXIT_TIMER(8),__LC_MCCK_ENTER_TIMER
+0: clg %r9,BASED(.Lcleanup_io_restore_insn+8)
+ je 1f
lg %r9,24(%r11) # get saved r11 pointer to pt_regs
mvc __LC_RETURN_PSW(16),__PT_PSW(%r9)
mvc 0(64,%r11),__PT_R8(%r9)
lmg %r0,%r7,__PT_R0(%r9)
-0: lmg %r8,%r9,__LC_RETURN_PSW
+1: lmg %r8,%r9,__LC_RETURN_PSW
br %r14
.Lcleanup_io_restore_insn:
+ .quad .Lio_exit_timer
.quad .Lio_done - 4
.Lcleanup_idle:
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 27477f3..d03a6d1 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -173,6 +173,8 @@ int __init ftrace_dyn_arch_init(void)
return 0;
}
+#ifdef CONFIG_MODULES
+
static int __init ftrace_plt_init(void)
{
unsigned int *ip;
@@ -191,6 +193,8 @@ static int __init ftrace_plt_init(void)
}
device_initcall(ftrace_plt_init);
+#endif /* CONFIG_MODULES */
+
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
/*
* Hook the return address and push it in the stack of return addresses
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index e545ffe..8e622bb5 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -564,8 +564,6 @@ static struct kset *ipl_kset;
static void __ipl_run(void *unused)
{
- if (MACHINE_IS_LPAR && ipl_info.type == IPL_TYPE_CCW)
- diag308(DIAG308_LOAD_NORMAL_DUMP, NULL);
diag308(DIAG308_LOAD_CLEAR, NULL);
if (MACHINE_IS_VM)
__cpcmd("IPL", NULL, 0, NULL);
@@ -1088,10 +1086,7 @@ static void __reipl_run(void *unused)
break;
case REIPL_METHOD_CCW_DIAG:
diag308(DIAG308_SET, reipl_block_ccw);
- if (MACHINE_IS_LPAR)
- diag308(DIAG308_LOAD_NORMAL_DUMP, NULL);
- else
- diag308(DIAG308_LOAD_CLEAR, NULL);
+ diag308(DIAG308_LOAD_CLEAR, NULL);
break;
case REIPL_METHOD_FCP_RW_DIAG:
diag308(DIAG308_SET, reipl_block_fcp);
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index ca960d0..0c82f79 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -995,11 +995,11 @@ static int perf_push_sample(struct perf_event *event, struct sf_raw_sample *sfr)
regs.int_parm = CPU_MF_INT_SF_PRA;
sde_regs = (struct perf_sf_sde_regs *) ®s.int_parm_long;
- psw_bits(regs.psw).ia = sfr->basic.ia;
- psw_bits(regs.psw).t = sfr->basic.T;
- psw_bits(regs.psw).w = sfr->basic.W;
- psw_bits(regs.psw).p = sfr->basic.P;
- psw_bits(regs.psw).as = sfr->basic.AS;
+ psw_bits(regs.psw).ia = sfr->basic.ia;
+ psw_bits(regs.psw).dat = sfr->basic.T;
+ psw_bits(regs.psw).wait = sfr->basic.W;
+ psw_bits(regs.psw).per = sfr->basic.P;
+ psw_bits(regs.psw).as = sfr->basic.AS;
/*
* Use the hardware provided configuration level to decide if the
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index 955a7b6..93a386f 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -245,6 +245,5 @@ ssize_t cpumf_events_sysfs_show(struct device *dev,
struct perf_pmu_events_attr *pmu_attr;
pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
- return sprintf(page, "event=0x%04llx,name=%s\n",
- pmu_attr->id, attr->attr.name);
+ return sprintf(page, "event=0x%04llx\n", pmu_attr->id);
}
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 488c5bb..252ed61 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -1160,6 +1160,8 @@ static int s390_gs_cb_get(struct task_struct *target,
return -ENODEV;
if (!data)
return -ENODATA;
+ if (target == current)
+ save_gs_cb(data);
return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
data, 0, sizeof(struct gs_cb));
}
@@ -1170,6 +1172,7 @@ static int s390_gs_cb_set(struct task_struct *target,
const void *kbuf, const void __user *ubuf)
{
struct gs_cb *data = target->thread.gs_cb;
+ int rc;
if (!MACHINE_HAS_GS)
return -ENODEV;
@@ -1177,10 +1180,18 @@ static int s390_gs_cb_set(struct task_struct *target,
data = kzalloc(sizeof(*data), GFP_KERNEL);
if (!data)
return -ENOMEM;
+ data->gsd = 25;
target->thread.gs_cb = data;
+ if (target == current)
+ __ctl_set_bit(2, 4);
+ } else if (target == current) {
+ save_gs_cb(data);
}
- return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- data, 0, sizeof(struct gs_cb));
+ rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ data, 0, sizeof(struct gs_cb));
+ if (target == current)
+ restore_gs_cb(data);
+ return rc;
}
static int s390_gs_bc_get(struct task_struct *target,
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 363000a..1020a11 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -26,6 +26,7 @@
#include <linux/err.h>
#include <linux/spinlock.h>
#include <linux/kernel_stat.h>
+#include <linux/kmemleak.h>
#include <linux/delay.h>
#include <linux/interrupt.h>
#include <linux/irqflags.h>
@@ -207,6 +208,8 @@ static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu)
kmem_cache_alloc(pcpu_mcesa_cache, GFP_KERNEL);
if (!mcesa_origin)
goto out;
+ /* The pointer is stored with mcesa_bits ORed in */
+ kmemleak_not_leak((void *) mcesa_origin);
mcesa_bits = MACHINE_HAS_GS ? 11 : 0;
}
} else {
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index f787b9d..442e542 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -21,6 +21,7 @@
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
+#include <linux/cpu.h>
#include <asm/fpu/api.h>
#include "entry.h"
diff --git a/arch/s390/kernel/uprobes.c b/arch/s390/kernel/uprobes.c
index 314e0ee..d94baa8 100644
--- a/arch/s390/kernel/uprobes.c
+++ b/arch/s390/kernel/uprobes.c
@@ -27,12 +27,12 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm,
int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
{
- if (psw_bits(regs->psw).eaba == PSW_AMODE_24BIT)
+ if (psw_bits(regs->psw).eaba == PSW_BITS_AMODE_24BIT)
return -EINVAL;
- if (!is_compat_task() && psw_bits(regs->psw).eaba == PSW_AMODE_31BIT)
+ if (!is_compat_task() && psw_bits(regs->psw).eaba == PSW_BITS_AMODE_31BIT)
return -EINVAL;
clear_pt_regs_flag(regs, PIF_PER_TRAP);
- auprobe->saved_per = psw_bits(regs->psw).r;
+ auprobe->saved_per = psw_bits(regs->psw).per;
auprobe->saved_int_code = regs->int_code;
regs->int_code = UPROBE_TRAP_NR;
regs->psw.addr = current->utask->xol_vaddr;
@@ -81,7 +81,7 @@ int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
clear_tsk_thread_flag(current, TIF_UPROBE_SINGLESTEP);
update_cr_regs(current);
- psw_bits(regs->psw).r = auprobe->saved_per;
+ psw_bits(regs->psw).per = auprobe->saved_per;
regs->int_code = auprobe->saved_int_code;
if (fixup & FIXUP_PSW_NORMAL)
@@ -372,8 +372,8 @@ static void handle_insn_ril(struct arch_uprobe *auprobe, struct pt_regs *regs)
bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
{
- if ((psw_bits(regs->psw).eaba == PSW_AMODE_24BIT) ||
- ((psw_bits(regs->psw).eaba == PSW_AMODE_31BIT) &&
+ if ((psw_bits(regs->psw).eaba == PSW_BITS_AMODE_24BIT) ||
+ ((psw_bits(regs->psw).eaba == PSW_BITS_AMODE_31BIT) &&
!is_compat_task())) {
regs->psw.addr = __rewind_psw(regs->psw, UPROBE_SWBP_INSN_SIZE);
do_report_trap(regs, SIGILL, ILL_ILLADR, NULL);
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index 10516ae..b89d19f6 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -50,6 +50,56 @@ static struct page **vdso64_pagelist;
*/
unsigned int __read_mostly vdso_enabled = 1;
+static int vdso_fault(const struct vm_special_mapping *sm,
+ struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+ struct page **vdso_pagelist;
+ unsigned long vdso_pages;
+
+ vdso_pagelist = vdso64_pagelist;
+ vdso_pages = vdso64_pages;
+#ifdef CONFIG_COMPAT
+ if (is_compat_task()) {
+ vdso_pagelist = vdso32_pagelist;
+ vdso_pages = vdso32_pages;
+ }
+#endif
+
+ if (vmf->pgoff >= vdso_pages)
+ return VM_FAULT_SIGBUS;
+
+ vmf->page = vdso_pagelist[vmf->pgoff];
+ get_page(vmf->page);
+ return 0;
+}
+
+static int vdso_mremap(const struct vm_special_mapping *sm,
+ struct vm_area_struct *vma)
+{
+ unsigned long vdso_pages;
+
+ vdso_pages = vdso64_pages;
+#ifdef CONFIG_COMPAT
+ if (is_compat_task())
+ vdso_pages = vdso32_pages;
+#endif
+
+ if ((vdso_pages << PAGE_SHIFT) != vma->vm_end - vma->vm_start)
+ return -EINVAL;
+
+ if (WARN_ON_ONCE(current->mm != vma->vm_mm))
+ return -EFAULT;
+
+ current->mm->context.vdso_base = vma->vm_start;
+ return 0;
+}
+
+static const struct vm_special_mapping vdso_mapping = {
+ .name = "[vdso]",
+ .fault = vdso_fault,
+ .mremap = vdso_mremap,
+};
+
static int __init vdso_setup(char *s)
{
unsigned long val;
@@ -181,7 +231,7 @@ static void vdso_init_cr5(void)
int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
{
struct mm_struct *mm = current->mm;
- struct page **vdso_pagelist;
+ struct vm_area_struct *vma;
unsigned long vdso_pages;
unsigned long vdso_base;
int rc;
@@ -194,13 +244,10 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
if (!uses_interp)
return 0;
- vdso_pagelist = vdso64_pagelist;
vdso_pages = vdso64_pages;
#ifdef CONFIG_COMPAT
- if (is_compat_task()) {
- vdso_pagelist = vdso32_pagelist;
+ if (is_compat_task())
vdso_pages = vdso32_pages;
- }
#endif
/*
* vDSO has a problem and was disabled, just don't "enable" it for
@@ -209,8 +256,6 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
if (vdso_pages == 0)
return 0;
- current->mm->context.vdso_base = 0;
-
/*
* pick a base address for the vDSO in process space. We try to put
* it at vdso_base which is the "natural" base for it, but we might
@@ -225,13 +270,6 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
}
/*
- * Put vDSO base into mm struct. We need to do this before calling
- * install_special_mapping or the perf counter mmap tracking code
- * will fail to recognise it as a vDSO (since arch_vma_name fails).
- */
- current->mm->context.vdso_base = vdso_base;
-
- /*
* our vma flags don't have VM_WRITE so by default, the process
* isn't allowed to write those pages.
* gdb can break that with ptrace interface, and thus trigger COW
@@ -241,24 +279,23 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
* It's fine to use that for setting breakpoints in the vDSO code
* pages though.
*/
- rc = install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT,
- VM_READ|VM_EXEC|
- VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
- vdso_pagelist);
- if (rc)
- current->mm->context.vdso_base = 0;
+ vma = _install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT,
+ VM_READ|VM_EXEC|
+ VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
+ &vdso_mapping);
+ if (IS_ERR(vma)) {
+ rc = PTR_ERR(vma);
+ goto out_up;
+ }
+
+ current->mm->context.vdso_base = vdso_base;
+ rc = 0;
+
out_up:
up_write(&mm->mmap_sem);
return rc;
}
-const char *arch_vma_name(struct vm_area_struct *vma)
-{
- if (vma->vm_mm && vma->vm_start == vma->vm_mm->context.vdso_base)
- return "[vdso]";
- return NULL;
-}
-
static int __init vdso_init(void)
{
int i;
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 72307f1..6e2c42b 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -31,8 +31,14 @@
{
. = 0x00000000;
.text : {
- _text = .; /* Text and read-only data */
+ /* Text and read-only data */
HEAD_TEXT
+ /*
+ * E.g. perf doesn't like symbols starting at address zero,
+ * therefore skip the initial PSW and channel program located
+ * at address zero and let _text start at 0x200.
+ */
+ _text = 0x200;
TEXT_TEXT
SCHED_TEXT
CPUIDLE_TEXT
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 072d84b..dd7178f 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -110,11 +110,10 @@ static inline u64 scale_vtime(u64 vtime)
return vtime;
}
-static void account_system_index_scaled(struct task_struct *p,
- u64 cputime, u64 scaled,
+static void account_system_index_scaled(struct task_struct *p, u64 cputime,
enum cpu_usage_stat index)
{
- p->stimescaled += cputime_to_nsecs(scaled);
+ p->stimescaled += cputime_to_nsecs(scale_vtime(cputime));
account_system_index_time(p, cputime_to_nsecs(cputime), index);
}
@@ -176,14 +175,11 @@ static int do_account_vtime(struct task_struct *tsk)
}
if (system)
- account_system_index_scaled(tsk, system, scale_vtime(system),
- CPUTIME_SYSTEM);
+ account_system_index_scaled(tsk, system, CPUTIME_SYSTEM);
if (hardirq)
- account_system_index_scaled(tsk, hardirq, scale_vtime(hardirq),
- CPUTIME_IRQ);
+ account_system_index_scaled(tsk, hardirq, CPUTIME_IRQ);
if (softirq)
- account_system_index_scaled(tsk, softirq, scale_vtime(softirq),
- CPUTIME_SOFTIRQ);
+ account_system_index_scaled(tsk, softirq, CPUTIME_SOFTIRQ);
steal = S390_lowcore.steal_timer;
if ((s64) steal > 0) {
diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index 9da243d..e0f7d5fc 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -551,26 +551,26 @@ static int get_vcpu_asce(struct kvm_vcpu *vcpu, union asce *asce,
int rc;
struct psw_bits psw = psw_bits(vcpu->arch.sie_block->gpsw);
- if (!psw.t) {
+ if (!psw.dat) {
asce->val = 0;
asce->r = 1;
return 0;
}
- if (mode == GACC_IFETCH)
- psw.as = psw.as == PSW_AS_HOME ? PSW_AS_HOME : PSW_AS_PRIMARY;
+ if ((mode == GACC_IFETCH) && (psw.as != PSW_BITS_AS_HOME))
+ psw.as = PSW_BITS_AS_PRIMARY;
switch (psw.as) {
- case PSW_AS_PRIMARY:
+ case PSW_BITS_AS_PRIMARY:
asce->val = vcpu->arch.sie_block->gcr[1];
return 0;
- case PSW_AS_SECONDARY:
+ case PSW_BITS_AS_SECONDARY:
asce->val = vcpu->arch.sie_block->gcr[7];
return 0;
- case PSW_AS_HOME:
+ case PSW_BITS_AS_HOME:
asce->val = vcpu->arch.sie_block->gcr[13];
return 0;
- case PSW_AS_ACCREG:
+ case PSW_BITS_AS_ACCREG:
rc = ar_translation(vcpu, asce, ar, mode);
if (rc > 0)
return trans_exc(vcpu, rc, ga, ar, mode, PROT_TYPE_ALC);
@@ -771,7 +771,7 @@ static int low_address_protection_enabled(struct kvm_vcpu *vcpu,
if (!ctlreg0.lap)
return 0;
- if (psw_bits(*psw).t && asce.p)
+ if (psw_bits(*psw).dat && asce.p)
return 0;
return 1;
}
@@ -790,7 +790,7 @@ static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar,
return trans_exc(vcpu, PGM_PROTECTION, ga, ar, mode,
PROT_TYPE_LA);
ga &= PAGE_MASK;
- if (psw_bits(*psw).t) {
+ if (psw_bits(*psw).dat) {
rc = guest_translate(vcpu, ga, pages, asce, mode);
if (rc < 0)
return rc;
@@ -831,7 +831,7 @@ int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, void *data,
pages = vmalloc(nr_pages * sizeof(unsigned long));
if (!pages)
return -ENOMEM;
- need_ipte_lock = psw_bits(*psw).t && !asce.r;
+ need_ipte_lock = psw_bits(*psw).dat && !asce.r;
if (need_ipte_lock)
ipte_lock(vcpu);
rc = guest_page_range(vcpu, ga, ar, pages, nr_pages, asce, mode);
@@ -899,7 +899,7 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
mode, PROT_TYPE_LA);
}
- if (psw_bits(*psw).t && !asce.r) { /* Use DAT? */
+ if (psw_bits(*psw).dat && !asce.r) { /* Use DAT? */
rc = guest_translate(vcpu, gva, gpa, asce, mode);
if (rc > 0)
return trans_exc(vcpu, rc, gva, 0, mode, PROT_TYPE_DAT);
diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h
index 7ce47fd..bec42b8 100644
--- a/arch/s390/kvm/gaccess.h
+++ b/arch/s390/kvm/gaccess.h
@@ -57,9 +57,9 @@ static inline unsigned long kvm_s390_logical_to_effective(struct kvm_vcpu *vcpu,
{
psw_t *psw = &vcpu->arch.sie_block->gpsw;
- if (psw_bits(*psw).eaba == PSW_AMODE_64BIT)
+ if (psw_bits(*psw).eaba == PSW_BITS_AMODE_64BIT)
return ga;
- if (psw_bits(*psw).eaba == PSW_AMODE_31BIT)
+ if (psw_bits(*psw).eaba == PSW_BITS_AMODE_31BIT)
return ga & ((1UL << 31) - 1);
return ga & ((1UL << 24) - 1);
}
diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c
index 23d9a4e..c2e0ddc 100644
--- a/arch/s390/kvm/guestdbg.c
+++ b/arch/s390/kvm/guestdbg.c
@@ -613,15 +613,15 @@ int kvm_s390_handle_per_event(struct kvm_vcpu *vcpu)
* instruction. Check primary and home space-switch-event
* controls. (theoretically home -> home produced no event)
*/
- if (((new_as == PSW_AS_HOME) ^ old_as_is_home(vcpu)) &&
- (pssec(vcpu) || hssec(vcpu)))
+ if (((new_as == PSW_BITS_AS_HOME) ^ old_as_is_home(vcpu)) &&
+ (pssec(vcpu) || hssec(vcpu)))
vcpu->arch.sie_block->iprcc = PGM_SPACE_SWITCH;
/*
* PT, PTI, PR, PC instruction operate on primary AS only. Check
* if the primary-space-switch-event control was or got set.
*/
- if (new_as == PSW_AS_PRIMARY && !old_as_is_home(vcpu) &&
+ if (new_as == PSW_BITS_AS_PRIMARY && !old_as_is_home(vcpu) &&
(pssec(vcpu) || old_ssec(vcpu)))
vcpu->arch.sie_block->iprcc = PGM_SPACE_SWITCH;
}
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index c03106c..e53292a 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -361,7 +361,7 @@ static int handle_sske(struct kvm_vcpu *vcpu)
}
}
if (m3 & SSKE_MB) {
- if (psw_bits(vcpu->arch.sie_block->gpsw).eaba == PSW_AMODE_64BIT)
+ if (psw_bits(vcpu->arch.sie_block->gpsw).eaba == PSW_BITS_AMODE_64BIT)
vcpu->run->s.regs.gprs[reg2] &= ~PAGE_MASK;
else
vcpu->run->s.regs.gprs[reg2] &= ~0xfffff000UL;
@@ -374,7 +374,7 @@ static int handle_sske(struct kvm_vcpu *vcpu)
static int handle_ipte_interlock(struct kvm_vcpu *vcpu)
{
vcpu->stat.instruction_ipte_interlock++;
- if (psw_bits(vcpu->arch.sie_block->gpsw).p)
+ if (psw_bits(vcpu->arch.sie_block->gpsw).pstate)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
wait_event(vcpu->kvm->arch.ipte_wq, !ipte_lock_held(vcpu));
kvm_s390_retry_instr(vcpu);
@@ -901,7 +901,7 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
/* only support 2G frame size if EDAT2 is available and we are
not in 24-bit addressing mode */
if (!test_kvm_facility(vcpu->kvm, 78) ||
- psw_bits(vcpu->arch.sie_block->gpsw).eaba == PSW_AMODE_24BIT)
+ psw_bits(vcpu->arch.sie_block->gpsw).eaba == PSW_BITS_AMODE_24BIT)
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
end = (start + (1UL << 31)) & ~((1UL << 31) - 1);
break;
@@ -938,7 +938,7 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
start += PAGE_SIZE;
}
if (vcpu->run->s.regs.gprs[reg1] & PFMF_FSC) {
- if (psw_bits(vcpu->arch.sie_block->gpsw).eaba == PSW_AMODE_64BIT) {
+ if (psw_bits(vcpu->arch.sie_block->gpsw).eaba == PSW_BITS_AMODE_64BIT) {
vcpu->run->s.regs.gprs[reg2] = end;
} else {
vcpu->run->s.regs.gprs[reg2] &= ~0xffffffffUL;
diff --git a/arch/s390/lib/probes.c b/arch/s390/lib/probes.c
index ae90e1a..1963ddb 100644
--- a/arch/s390/lib/probes.c
+++ b/arch/s390/lib/probes.c
@@ -4,6 +4,7 @@
* Copyright IBM Corp. 2014
*/
+#include <linux/errno.h>
#include <asm/kprobes.h>
#include <asm/dis.h>
diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c
index 1e5bb2b..b3bd3f2 100644
--- a/arch/s390/lib/uaccess.c
+++ b/arch/s390/lib/uaccess.c
@@ -337,8 +337,8 @@ long __strncpy_from_user(char *dst, const char __user *src, long size)
return 0;
done = 0;
do {
- offset = (size_t)src & ~PAGE_MASK;
- len = min(size - done, PAGE_SIZE - offset);
+ offset = (size_t)src & (L1_CACHE_BYTES - 1);
+ len = min(size - done, L1_CACHE_BYTES - offset);
if (copy_from_user(dst, src, len))
return -EFAULT;
len_str = strnlen(dst, len);
diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c
index 1b553d8..049c3c4 100644
--- a/arch/s390/mm/dump_pagetables.c
+++ b/arch/s390/mm/dump_pagetables.c
@@ -149,7 +149,7 @@ static void walk_pmd_level(struct seq_file *m, struct pg_state *st,
}
static void walk_pud_level(struct seq_file *m, struct pg_state *st,
- pgd_t *pgd, unsigned long addr)
+ p4d_t *p4d, unsigned long addr)
{
unsigned int prot;
pud_t *pud;
@@ -157,7 +157,7 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st,
for (i = 0; i < PTRS_PER_PUD && addr < max_addr; i++) {
st->current_address = addr;
- pud = pud_offset(pgd, addr);
+ pud = pud_offset(p4d, addr);
if (!pud_none(*pud))
if (pud_large(*pud)) {
prot = pud_val(*pud) &
@@ -172,6 +172,23 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st,
}
}
+static void walk_p4d_level(struct seq_file *m, struct pg_state *st,
+ pgd_t *pgd, unsigned long addr)
+{
+ p4d_t *p4d;
+ int i;
+
+ for (i = 0; i < PTRS_PER_P4D && addr < max_addr; i++) {
+ st->current_address = addr;
+ p4d = p4d_offset(pgd, addr);
+ if (!p4d_none(*p4d))
+ walk_pud_level(m, st, p4d, addr);
+ else
+ note_page(m, st, _PAGE_INVALID, 2);
+ addr += P4D_SIZE;
+ }
+}
+
static void walk_pgd_level(struct seq_file *m)
{
unsigned long addr = 0;
@@ -184,7 +201,7 @@ static void walk_pgd_level(struct seq_file *m)
st.current_address = addr;
pgd = pgd_offset_k(addr);
if (!pgd_none(*pgd))
- walk_pud_level(m, &st, pgd, addr);
+ walk_p4d_level(m, &st, pgd, addr);
else
note_page(m, &st, _PAGE_INVALID, 1);
addr += PGDIR_SIZE;
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 5845d30..14f2579 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -130,7 +130,7 @@ static int bad_address(void *p)
static void dump_pagetable(unsigned long asce, unsigned long address)
{
- unsigned long *table = __va(asce & PAGE_MASK);
+ unsigned long *table = __va(asce & _ASCE_ORIGIN);
pr_alert("AS:%016lx ", asce);
switch (asce & _ASCE_TYPE_MASK) {
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 7f6db1e..4fb3d3c 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -125,7 +125,7 @@ static void gmap_radix_tree_free(struct radix_tree_root *root)
struct radix_tree_iter iter;
unsigned long indices[16];
unsigned long index;
- void **slot;
+ void __rcu **slot;
int i, nr;
/* A radix tree is freed by deleting all of its entries */
@@ -150,7 +150,7 @@ static void gmap_rmap_radix_tree_free(struct radix_tree_root *root)
struct radix_tree_iter iter;
unsigned long indices[16];
unsigned long index;
- void **slot;
+ void __rcu **slot;
int i, nr;
/* A radix tree is freed by deleting all of its entries */
@@ -537,6 +537,7 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr)
unsigned long *table;
spinlock_t *ptl;
pgd_t *pgd;
+ p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
int rc;
@@ -573,7 +574,9 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr)
mm = gmap->mm;
pgd = pgd_offset(mm, vmaddr);
VM_BUG_ON(pgd_none(*pgd));
- pud = pud_offset(pgd, vmaddr);
+ p4d = p4d_offset(pgd, vmaddr);
+ VM_BUG_ON(p4d_none(*p4d));
+ pud = pud_offset(p4d, vmaddr);
VM_BUG_ON(pud_none(*pud));
/* large puds cannot yet be handled */
if (pud_large(*pud))
@@ -1008,7 +1011,7 @@ EXPORT_SYMBOL_GPL(gmap_read_table);
static inline void gmap_insert_rmap(struct gmap *sg, unsigned long vmaddr,
struct gmap_rmap *rmap)
{
- void **slot;
+ void __rcu **slot;
BUG_ON(!gmap_is_shadow(sg));
slot = radix_tree_lookup_slot(&sg->host_to_rmap, vmaddr >> PAGE_SHIFT);
diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c
index b7b779c..8ecc25e 100644
--- a/arch/s390/mm/gup.c
+++ b/arch/s390/mm/gup.c
@@ -166,15 +166,15 @@ static int gup_huge_pud(pud_t *pudp, pud_t pud, unsigned long addr,
return 1;
}
-static inline int gup_pud_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr,
+static inline int gup_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr,
unsigned long end, int write, struct page **pages, int *nr)
{
unsigned long next;
pud_t *pudp, pud;
- pudp = (pud_t *) pgdp;
- if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2)
- pudp = (pud_t *) pgd_deref(pgd);
+ pudp = (pud_t *) p4dp;
+ if ((p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2)
+ pudp = (pud_t *) p4d_deref(p4d);
pudp += pud_index(addr);
do {
pud = *pudp;
@@ -194,6 +194,29 @@ static inline int gup_pud_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr,
return 1;
}
+static inline int gup_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr,
+ unsigned long end, int write, struct page **pages, int *nr)
+{
+ unsigned long next;
+ p4d_t *p4dp, p4d;
+
+ p4dp = (p4d_t *) pgdp;
+ if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R1)
+ p4dp = (p4d_t *) pgd_deref(pgd);
+ p4dp += p4d_index(addr);
+ do {
+ p4d = *p4dp;
+ barrier();
+ next = p4d_addr_end(addr, end);
+ if (p4d_none(p4d))
+ return 0;
+ if (!gup_pud_range(p4dp, p4d, addr, next, write, pages, nr))
+ return 0;
+ } while (p4dp++, addr = next, addr != end);
+
+ return 1;
+}
+
/*
* Like get_user_pages_fast() except its IRQ-safe in that it won't fall
* back to the regular GUP.
@@ -228,7 +251,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
next = pgd_addr_end(addr, end);
if (pgd_none(pgd))
break;
- if (!gup_pud_range(pgdp, pgd, addr, next, write, pages, &nr))
+ if (!gup_p4d_range(pgdp, pgd, addr, next, write, pages, &nr))
break;
} while (pgdp++, addr = next, addr != end);
local_irq_restore(flags);
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index 9b4050c..d3a5e39 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -162,16 +162,20 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
unsigned long addr, unsigned long sz)
{
pgd_t *pgdp;
+ p4d_t *p4dp;
pud_t *pudp;
pmd_t *pmdp = NULL;
pgdp = pgd_offset(mm, addr);
- pudp = pud_alloc(mm, pgdp, addr);
- if (pudp) {
- if (sz == PUD_SIZE)
- return (pte_t *) pudp;
- else if (sz == PMD_SIZE)
- pmdp = pmd_alloc(mm, pudp, addr);
+ p4dp = p4d_alloc(mm, pgdp, addr);
+ if (p4dp) {
+ pudp = pud_alloc(mm, p4dp, addr);
+ if (pudp) {
+ if (sz == PUD_SIZE)
+ return (pte_t *) pudp;
+ else if (sz == PMD_SIZE)
+ pmdp = pmd_alloc(mm, pudp, addr);
+ }
}
return (pte_t *) pmdp;
}
@@ -179,16 +183,20 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
{
pgd_t *pgdp;
+ p4d_t *p4dp;
pud_t *pudp;
pmd_t *pmdp = NULL;
pgdp = pgd_offset(mm, addr);
if (pgd_present(*pgdp)) {
- pudp = pud_offset(pgdp, addr);
- if (pud_present(*pudp)) {
- if (pud_large(*pudp))
- return (pte_t *) pudp;
- pmdp = pmd_offset(pudp, addr);
+ p4dp = p4d_offset(pgdp, addr);
+ if (p4d_present(*p4dp)) {
+ pudp = pud_offset(p4dp, addr);
+ if (pud_present(*pudp)) {
+ if (pud_large(*pudp))
+ return (pte_t *) pudp;
+ pmdp = pmd_offset(pudp, addr);
+ }
}
}
return (pte_t *) pmdp;
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index ee6a1d3..3348e60 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -81,6 +81,7 @@ void __init paging_init(void)
{
unsigned long max_zone_pfns[MAX_NR_ZONES];
unsigned long pgd_type, asce_bits;
+ psw_t psw;
init_mm.pgd = swapper_pg_dir;
if (VMALLOC_END > (1UL << 42)) {
@@ -100,7 +101,10 @@ void __init paging_init(void)
__ctl_load(S390_lowcore.kernel_asce, 1, 1);
__ctl_load(S390_lowcore.kernel_asce, 7, 7);
__ctl_load(S390_lowcore.kernel_asce, 13, 13);
- __arch_local_irq_stosm(0x04);
+ psw.mask = __extract_psw();
+ psw_bits(psw).dat = 1;
+ psw_bits(psw).as = PSW_BITS_AS_HOME;
+ __load_psw_mask(psw.mask);
sparse_memory_present_with_active_regions(MAX_NUMNODES);
sparse_init();
diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c
index b017dae..8c5f284 100644
--- a/arch/s390/mm/mmap.c
+++ b/arch/s390/mm/mmap.c
@@ -120,7 +120,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
check_asce_limit:
if (addr + len > current->mm->context.asce_limit) {
- rc = crst_table_upgrade(mm);
+ rc = crst_table_upgrade(mm, addr + len);
if (rc)
return (unsigned long) rc;
}
@@ -184,7 +184,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
check_asce_limit:
if (addr + len > current->mm->context.asce_limit) {
- rc = crst_table_upgrade(mm);
+ rc = crst_table_upgrade(mm, addr + len);
if (rc)
return (unsigned long) rc;
}
diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c
index 49e721f..1804815 100644
--- a/arch/s390/mm/pageattr.c
+++ b/arch/s390/mm/pageattr.c
@@ -229,14 +229,14 @@ static void modify_pud_page(pud_t *pudp, unsigned long addr,
pgt_set((unsigned long *)pudp, pud_val(new), addr, CRDTE_DTT_REGION3);
}
-static int walk_pud_level(pgd_t *pgd, unsigned long addr, unsigned long end,
+static int walk_pud_level(p4d_t *p4d, unsigned long addr, unsigned long end,
unsigned long flags)
{
unsigned long next;
pud_t *pudp;
int rc = 0;
- pudp = pud_offset(pgd, addr);
+ pudp = pud_offset(p4d, addr);
do {
if (pud_none(*pudp))
return -EINVAL;
@@ -259,6 +259,26 @@ static int walk_pud_level(pgd_t *pgd, unsigned long addr, unsigned long end,
return rc;
}
+static int walk_p4d_level(pgd_t *pgd, unsigned long addr, unsigned long end,
+ unsigned long flags)
+{
+ unsigned long next;
+ p4d_t *p4dp;
+ int rc = 0;
+
+ p4dp = p4d_offset(pgd, addr);
+ do {
+ if (p4d_none(*p4dp))
+ return -EINVAL;
+ next = p4d_addr_end(addr, end);
+ rc = walk_pud_level(p4dp, addr, next, flags);
+ p4dp++;
+ addr = next;
+ cond_resched();
+ } while (addr < end && !rc);
+ return rc;
+}
+
static DEFINE_MUTEX(cpa_mutex);
static int change_page_attr(unsigned long addr, unsigned long end,
@@ -278,7 +298,7 @@ static int change_page_attr(unsigned long addr, unsigned long end,
if (pgd_none(*pgdp))
break;
next = pgd_addr_end(addr, end);
- rc = walk_pud_level(pgdp, addr, next, flags);
+ rc = walk_p4d_level(pgdp, addr, next, flags);
if (rc)
break;
cond_resched();
@@ -319,6 +339,7 @@ void __kernel_map_pages(struct page *page, int numpages, int enable)
unsigned long address;
int nr, i, j;
pgd_t *pgd;
+ p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
@@ -326,7 +347,8 @@ void __kernel_map_pages(struct page *page, int numpages, int enable)
for (i = 0; i < numpages;) {
address = page_to_phys(page + i);
pgd = pgd_offset_k(address);
- pud = pud_offset(pgd, address);
+ p4d = p4d_offset(pgd, address);
+ pud = pud_offset(p4d, address);
pmd = pmd_offset(pud, address);
pte = pte_offset_kernel(pmd, address);
nr = (unsigned long)pte >> ilog2(sizeof(long));
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index f502cbe..18918e3 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -76,29 +76,46 @@ static void __crst_table_upgrade(void *arg)
__tlb_flush_local();
}
-int crst_table_upgrade(struct mm_struct *mm)
+int crst_table_upgrade(struct mm_struct *mm, unsigned long end)
{
unsigned long *table, *pgd;
+ int rc, notify;
- /* upgrade should only happen from 3 to 4 levels */
- BUG_ON(mm->context.asce_limit != (1UL << 42));
-
- table = crst_table_alloc(mm);
- if (!table)
+ /* upgrade should only happen from 3 to 4, 3 to 5, or 4 to 5 levels */
+ BUG_ON(mm->context.asce_limit < (1UL << 42));
+ if (end >= TASK_SIZE_MAX)
return -ENOMEM;
-
- spin_lock_bh(&mm->page_table_lock);
- pgd = (unsigned long *) mm->pgd;
- crst_table_init(table, _REGION2_ENTRY_EMPTY);
- pgd_populate(mm, (pgd_t *) table, (pud_t *) pgd);
- mm->pgd = (pgd_t *) table;
- mm->context.asce_limit = 1UL << 53;
- mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
- _ASCE_USER_BITS | _ASCE_TYPE_REGION2;
- spin_unlock_bh(&mm->page_table_lock);
-
- on_each_cpu(__crst_table_upgrade, mm, 0);
- return 0;
+ rc = 0;
+ notify = 0;
+ while (mm->context.asce_limit < end) {
+ table = crst_table_alloc(mm);
+ if (!table) {
+ rc = -ENOMEM;
+ break;
+ }
+ spin_lock_bh(&mm->page_table_lock);
+ pgd = (unsigned long *) mm->pgd;
+ if (mm->context.asce_limit == (1UL << 42)) {
+ crst_table_init(table, _REGION2_ENTRY_EMPTY);
+ p4d_populate(mm, (p4d_t *) table, (pud_t *) pgd);
+ mm->pgd = (pgd_t *) table;
+ mm->context.asce_limit = 1UL << 53;
+ mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
+ _ASCE_USER_BITS | _ASCE_TYPE_REGION2;
+ } else {
+ crst_table_init(table, _REGION1_ENTRY_EMPTY);
+ pgd_populate(mm, (pgd_t *) table, (p4d_t *) pgd);
+ mm->pgd = (pgd_t *) table;
+ mm->context.asce_limit = -PAGE_SIZE;
+ mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
+ _ASCE_USER_BITS | _ASCE_TYPE_REGION1;
+ }
+ notify = 1;
+ spin_unlock_bh(&mm->page_table_lock);
+ }
+ if (notify)
+ on_each_cpu(__crst_table_upgrade, mm, 0);
+ return rc;
}
void crst_table_downgrade(struct mm_struct *mm)
@@ -274,7 +291,7 @@ static void __tlb_remove_table(void *_table)
struct page *page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
switch (mask) {
- case 0: /* pmd or pud */
+ case 0: /* pmd, pud, or p4d */
free_pages((unsigned long) table, 2);
break;
case 1: /* lower 2K of a 4K page table */
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 947b66a..d4d409b 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -610,6 +610,7 @@ bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long addr)
{
spinlock_t *ptl;
pgd_t *pgd;
+ p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
pgste_t pgste;
@@ -618,7 +619,10 @@ bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long addr)
bool dirty;
pgd = pgd_offset(mm, addr);
- pud = pud_alloc(mm, pgd, addr);
+ p4d = p4d_alloc(mm, pgd, addr);
+ if (!p4d)
+ return false;
+ pud = pud_alloc(mm, p4d, addr);
if (!pud)
return false;
pmd = pmd_alloc(mm, pud, addr);
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index c33c94b..d839896 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -38,6 +38,17 @@ static void __ref *vmem_alloc_pages(unsigned int order)
return (void *) memblock_alloc(size, size);
}
+static inline p4d_t *vmem_p4d_alloc(void)
+{
+ p4d_t *p4d = NULL;
+
+ p4d = vmem_alloc_pages(2);
+ if (!p4d)
+ return NULL;
+ clear_table((unsigned long *) p4d, _REGION2_ENTRY_EMPTY, PAGE_SIZE * 4);
+ return p4d;
+}
+
static inline pud_t *vmem_pud_alloc(void)
{
pud_t *pud = NULL;
@@ -85,6 +96,7 @@ static int vmem_add_mem(unsigned long start, unsigned long size)
unsigned long end = start + size;
unsigned long address = start;
pgd_t *pg_dir;
+ p4d_t *p4_dir;
pud_t *pu_dir;
pmd_t *pm_dir;
pte_t *pt_dir;
@@ -102,12 +114,19 @@ static int vmem_add_mem(unsigned long start, unsigned long size)
while (address < end) {
pg_dir = pgd_offset_k(address);
if (pgd_none(*pg_dir)) {
+ p4_dir = vmem_p4d_alloc();
+ if (!p4_dir)
+ goto out;
+ pgd_populate(&init_mm, pg_dir, p4_dir);
+ }
+ p4_dir = p4d_offset(pg_dir, address);
+ if (p4d_none(*p4_dir)) {
pu_dir = vmem_pud_alloc();
if (!pu_dir)
goto out;
- pgd_populate(&init_mm, pg_dir, pu_dir);
+ p4d_populate(&init_mm, p4_dir, pu_dir);
}
- pu_dir = pud_offset(pg_dir, address);
+ pu_dir = pud_offset(p4_dir, address);
if (MACHINE_HAS_EDAT2 && pud_none(*pu_dir) && address &&
!(address & ~PUD_MASK) && (address + PUD_SIZE <= end) &&
!debug_pagealloc_enabled()) {
@@ -161,6 +180,7 @@ static void vmem_remove_range(unsigned long start, unsigned long size)
unsigned long end = start + size;
unsigned long address = start;
pgd_t *pg_dir;
+ p4d_t *p4_dir;
pud_t *pu_dir;
pmd_t *pm_dir;
pte_t *pt_dir;
@@ -172,7 +192,12 @@ static void vmem_remove_range(unsigned long start, unsigned long size)
address += PGDIR_SIZE;
continue;
}
- pu_dir = pud_offset(pg_dir, address);
+ p4_dir = p4d_offset(pg_dir, address);
+ if (p4d_none(*p4_dir)) {
+ address += P4D_SIZE;
+ continue;
+ }
+ pu_dir = pud_offset(p4_dir, address);
if (pud_none(*pu_dir)) {
address += PUD_SIZE;
continue;
@@ -213,6 +238,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
unsigned long pgt_prot, sgt_prot;
unsigned long address = start;
pgd_t *pg_dir;
+ p4d_t *p4_dir;
pud_t *pu_dir;
pmd_t *pm_dir;
pte_t *pt_dir;
@@ -227,13 +253,21 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
for (address = start; address < end;) {
pg_dir = pgd_offset_k(address);
if (pgd_none(*pg_dir)) {
+ p4_dir = vmem_p4d_alloc();
+ if (!p4_dir)
+ goto out;
+ pgd_populate(&init_mm, pg_dir, p4_dir);
+ }
+
+ p4_dir = p4d_offset(pg_dir, address);
+ if (p4d_none(*p4_dir)) {
pu_dir = vmem_pud_alloc();
if (!pu_dir)
goto out;
- pgd_populate(&init_mm, pg_dir, pu_dir);
+ p4d_populate(&init_mm, p4_dir, pu_dir);
}
- pu_dir = pud_offset(pg_dir, address);
+ pu_dir = pud_offset(p4_dir, address);
if (pud_none(*pu_dir)) {
pm_dir = vmem_pmd_alloc();
if (!pm_dir)
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 8051df1..7b30af5 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -86,6 +86,25 @@ struct zpci_dev *get_zdev_by_fid(u32 fid)
return zdev;
}
+void zpci_remove_reserved_devices(void)
+{
+ struct zpci_dev *tmp, *zdev;
+ enum zpci_state state;
+ LIST_HEAD(remove);
+
+ spin_lock(&zpci_list_lock);
+ list_for_each_entry_safe(zdev, tmp, &zpci_list, entry) {
+ if (zdev->state == ZPCI_FN_STATE_STANDBY &&
+ !clp_get_state(zdev->fid, &state) &&
+ state == ZPCI_FN_STATE_RESERVED)
+ list_move_tail(&zdev->entry, &remove);
+ }
+ spin_unlock(&zpci_list_lock);
+
+ list_for_each_entry_safe(zdev, tmp, &remove, entry)
+ zpci_remove_device(zdev);
+}
+
static struct zpci_dev *get_zdev_by_bus(struct pci_bus *bus)
{
return (bus && bus->sysdata) ? (struct zpci_dev *) bus->sysdata : NULL;
@@ -108,6 +127,7 @@ static int zpci_set_airq(struct zpci_dev *zdev)
{
u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_REG_INT);
struct zpci_fib fib = {0};
+ u8 status;
fib.isc = PCI_ISC;
fib.sum = 1; /* enable summary notifications */
@@ -117,60 +137,58 @@ static int zpci_set_airq(struct zpci_dev *zdev)
fib.aisb = (unsigned long) zpci_aisb_iv->vector + (zdev->aisb/64)*8;
fib.aisbo = zdev->aisb & 63;
- return zpci_mod_fc(req, &fib);
+ return zpci_mod_fc(req, &fib, &status) ? -EIO : 0;
}
-struct mod_pci_args {
- u64 base;
- u64 limit;
- u64 iota;
- u64 fmb_addr;
-};
-
-static int mod_pci(struct zpci_dev *zdev, int fn, u8 dmaas, struct mod_pci_args *args)
+/* Modify PCI: Unregister adapter interruptions */
+static int zpci_clear_airq(struct zpci_dev *zdev)
{
- u64 req = ZPCI_CREATE_REQ(zdev->fh, dmaas, fn);
+ u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_DEREG_INT);
struct zpci_fib fib = {0};
+ u8 cc, status;
- fib.pba = args->base;
- fib.pal = args->limit;
- fib.iota = args->iota;
- fib.fmb_addr = args->fmb_addr;
+ cc = zpci_mod_fc(req, &fib, &status);
+ if (cc == 3 || (cc == 1 && status == 24))
+ /* Function already gone or IRQs already deregistered. */
+ cc = 0;
- return zpci_mod_fc(req, &fib);
+ return cc ? -EIO : 0;
}
/* Modify PCI: Register I/O address translation parameters */
int zpci_register_ioat(struct zpci_dev *zdev, u8 dmaas,
u64 base, u64 limit, u64 iota)
{
- struct mod_pci_args args = { base, limit, iota, 0 };
+ u64 req = ZPCI_CREATE_REQ(zdev->fh, dmaas, ZPCI_MOD_FC_REG_IOAT);
+ struct zpci_fib fib = {0};
+ u8 status;
WARN_ON_ONCE(iota & 0x3fff);
- args.iota |= ZPCI_IOTA_RTTO_FLAG;
- return mod_pci(zdev, ZPCI_MOD_FC_REG_IOAT, dmaas, &args);
+ fib.pba = base;
+ fib.pal = limit;
+ fib.iota = iota | ZPCI_IOTA_RTTO_FLAG;
+ return zpci_mod_fc(req, &fib, &status) ? -EIO : 0;
}
/* Modify PCI: Unregister I/O address translation parameters */
int zpci_unregister_ioat(struct zpci_dev *zdev, u8 dmaas)
{
- struct mod_pci_args args = { 0, 0, 0, 0 };
+ u64 req = ZPCI_CREATE_REQ(zdev->fh, dmaas, ZPCI_MOD_FC_DEREG_IOAT);
+ struct zpci_fib fib = {0};
+ u8 cc, status;
- return mod_pci(zdev, ZPCI_MOD_FC_DEREG_IOAT, dmaas, &args);
-}
-
-/* Modify PCI: Unregister adapter interruptions */
-static int zpci_clear_airq(struct zpci_dev *zdev)
-{
- struct mod_pci_args args = { 0, 0, 0, 0 };
-
- return mod_pci(zdev, ZPCI_MOD_FC_DEREG_INT, 0, &args);
+ cc = zpci_mod_fc(req, &fib, &status);
+ if (cc == 3) /* Function already gone. */
+ cc = 0;
+ return cc ? -EIO : 0;
}
/* Modify PCI: Set PCI function measurement parameters */
int zpci_fmb_enable_device(struct zpci_dev *zdev)
{
- struct mod_pci_args args = { 0, 0, 0, 0 };
+ u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_SET_MEASURE);
+ struct zpci_fib fib = {0};
+ u8 cc, status;
if (zdev->fmb || sizeof(*zdev->fmb) < zdev->fmb_length)
return -EINVAL;
@@ -185,25 +203,35 @@ int zpci_fmb_enable_device(struct zpci_dev *zdev)
atomic64_set(&zdev->mapped_pages, 0);
atomic64_set(&zdev->unmapped_pages, 0);
- args.fmb_addr = virt_to_phys(zdev->fmb);
- return mod_pci(zdev, ZPCI_MOD_FC_SET_MEASURE, 0, &args);
+ fib.fmb_addr = virt_to_phys(zdev->fmb);
+ cc = zpci_mod_fc(req, &fib, &status);
+ if (cc) {
+ kmem_cache_free(zdev_fmb_cache, zdev->fmb);
+ zdev->fmb = NULL;
+ }
+ return cc ? -EIO : 0;
}
/* Modify PCI: Disable PCI function measurement */
int zpci_fmb_disable_device(struct zpci_dev *zdev)
{
- struct mod_pci_args args = { 0, 0, 0, 0 };
- int rc;
+ u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_SET_MEASURE);
+ struct zpci_fib fib = {0};
+ u8 cc, status;
if (!zdev->fmb)
return -EINVAL;
/* Function measurement is disabled if fmb address is zero */
- rc = mod_pci(zdev, ZPCI_MOD_FC_SET_MEASURE, 0, &args);
+ cc = zpci_mod_fc(req, &fib, &status);
+ if (cc == 3) /* Function already gone. */
+ cc = 0;
- kmem_cache_free(zdev_fmb_cache, zdev->fmb);
- zdev->fmb = NULL;
- return rc;
+ if (!cc) {
+ kmem_cache_free(zdev_fmb_cache, zdev->fmb);
+ zdev->fmb = NULL;
+ }
+ return cc ? -EIO : 0;
}
static int zpci_cfg_load(struct zpci_dev *zdev, int offset, u32 *val, u8 len)
@@ -372,22 +400,21 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
struct msi_msg msg;
int rc, irq;
+ zdev->aisb = -1UL;
if (type == PCI_CAP_ID_MSI && nvec > 1)
return 1;
msi_vecs = min_t(unsigned int, nvec, zdev->max_msi);
/* Allocate adapter summary indicator bit */
- rc = -EIO;
aisb = airq_iv_alloc_bit(zpci_aisb_iv);
if (aisb == -1UL)
- goto out;
+ return -EIO;
zdev->aisb = aisb;
/* Create adapter interrupt vector */
- rc = -ENOMEM;
zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK);
if (!zdev->aibv)
- goto out_si;
+ return -ENOMEM;
/* Wire up shortcut pointer */
zpci_aibv[aisb] = zdev->aibv;
@@ -398,10 +425,10 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
rc = -EIO;
irq = irq_alloc_desc(0); /* Alloc irq on node 0 */
if (irq < 0)
- goto out_msi;
+ return -ENOMEM;
rc = irq_set_msi_desc(irq, msi);
if (rc)
- goto out_msi;
+ return rc;
irq_set_chip_and_handler(irq, &zpci_irq_chip,
handle_simple_irq);
msg.data = hwirq;
@@ -415,27 +442,9 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
/* Enable adapter interrupts */
rc = zpci_set_airq(zdev);
if (rc)
- goto out_msi;
+ return rc;
return (msi_vecs == nvec) ? 0 : msi_vecs;
-
-out_msi:
- for_each_pci_msi_entry(msi, pdev) {
- if (hwirq-- == 0)
- break;
- irq_set_msi_desc(msi->irq, NULL);
- irq_free_desc(msi->irq);
- msi->msg.address_lo = 0;
- msi->msg.address_hi = 0;
- msi->msg.data = 0;
- msi->irq = 0;
- }
- zpci_aibv[aisb] = NULL;
- airq_iv_release(zdev->aibv);
-out_si:
- airq_iv_free_bit(zpci_aisb_iv, aisb);
-out:
- return rc;
}
void arch_teardown_msi_irqs(struct pci_dev *pdev)
@@ -451,6 +460,8 @@ void arch_teardown_msi_irqs(struct pci_dev *pdev)
/* Release MSI interrupts */
for_each_pci_msi_entry(msi, pdev) {
+ if (!msi->irq)
+ continue;
if (msi->msi_attrib.is_msix)
__pci_msix_desc_mask_irq(msi, 1);
else
@@ -463,9 +474,15 @@ void arch_teardown_msi_irqs(struct pci_dev *pdev)
msi->irq = 0;
}
- zpci_aibv[zdev->aisb] = NULL;
- airq_iv_release(zdev->aibv);
- airq_iv_free_bit(zpci_aisb_iv, zdev->aisb);
+ if (zdev->aisb != -1UL) {
+ zpci_aibv[zdev->aisb] = NULL;
+ airq_iv_free_bit(zpci_aisb_iv, zdev->aisb);
+ zdev->aisb = -1UL;
+ }
+ if (zdev->aibv) {
+ airq_iv_release(zdev->aibv);
+ zdev->aibv = NULL;
+ }
}
static void zpci_map_resources(struct pci_dev *pdev)
@@ -719,6 +736,16 @@ static int zpci_alloc_domain(struct zpci_dev *zdev)
{
if (zpci_unique_uid) {
zdev->domain = (u16) zdev->uid;
+ if (zdev->domain >= ZPCI_NR_DEVICES)
+ return 0;
+
+ spin_lock(&zpci_domain_lock);
+ if (test_bit(zdev->domain, zpci_domain)) {
+ spin_unlock(&zpci_domain_lock);
+ return -EEXIST;
+ }
+ set_bit(zdev->domain, zpci_domain);
+ spin_unlock(&zpci_domain_lock);
return 0;
}
@@ -735,7 +762,7 @@ static int zpci_alloc_domain(struct zpci_dev *zdev)
static void zpci_free_domain(struct zpci_dev *zdev)
{
- if (zpci_unique_uid)
+ if (zdev->domain >= ZPCI_NR_DEVICES)
return;
spin_lock(&zpci_domain_lock);
@@ -755,6 +782,7 @@ void pcibios_remove_bus(struct pci_bus *bus)
list_del(&zdev->entry);
spin_unlock(&zpci_list_lock);
+ zpci_dbg(3, "rem fid:%x\n", zdev->fid);
kfree(zdev);
}
@@ -847,15 +875,14 @@ int zpci_create_device(struct zpci_dev *zdev)
return rc;
}
-void zpci_stop_device(struct zpci_dev *zdev)
+void zpci_remove_device(struct zpci_dev *zdev)
{
- zpci_dma_exit_device(zdev);
- /*
- * Note: SCLP disables fh via set-pci-fn so don't
- * do that here.
- */
+ if (!zdev->bus)
+ return;
+
+ pci_stop_root_bus(zdev->bus);
+ pci_remove_root_bus(zdev->bus);
}
-EXPORT_SYMBOL_GPL(zpci_stop_device);
int zpci_report_error(struct pci_dev *pdev,
struct zpci_report_error_header *report)
diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c
index 1c3332a..bd534b4 100644
--- a/arch/s390/pci/pci_clp.c
+++ b/arch/s390/pci/pci_clp.c
@@ -193,12 +193,12 @@ static int clp_query_pci_fn(struct zpci_dev *zdev, u32 fh)
int clp_add_pci_device(u32 fid, u32 fh, int configured)
{
struct zpci_dev *zdev;
- int rc;
+ int rc = -ENOMEM;
zpci_dbg(3, "add fid:%x, fh:%x, c:%d\n", fid, fh, configured);
zdev = kzalloc(sizeof(*zdev), GFP_KERNEL);
if (!zdev)
- return -ENOMEM;
+ goto error;
zdev->fh = fh;
zdev->fid = fid;
@@ -219,6 +219,7 @@ int clp_add_pci_device(u32 fid, u32 fh, int configured)
return 0;
error:
+ zpci_dbg(0, "add fid:%x, rc:%d\n", fid, rc);
kfree(zdev);
return rc;
}
@@ -295,8 +296,8 @@ int clp_disable_fh(struct zpci_dev *zdev)
return rc;
}
-static int clp_list_pci(struct clp_req_rsp_list_pci *rrb,
- void (*cb)(struct clp_fh_list_entry *entry))
+static int clp_list_pci(struct clp_req_rsp_list_pci *rrb, void *data,
+ void (*cb)(struct clp_fh_list_entry *, void *))
{
u64 resume_token = 0;
int entries, i, rc;
@@ -327,21 +328,13 @@ static int clp_list_pci(struct clp_req_rsp_list_pci *rrb,
resume_token = rrb->response.resume_token;
for (i = 0; i < entries; i++)
- cb(&rrb->response.fh_list[i]);
+ cb(&rrb->response.fh_list[i], data);
} while (resume_token);
out:
return rc;
}
-static void __clp_add(struct clp_fh_list_entry *entry)
-{
- if (!entry->vendor_id)
- return;
-
- clp_add_pci_device(entry->fid, entry->fh, entry->config_state);
-}
-
-static void __clp_rescan(struct clp_fh_list_entry *entry)
+static void __clp_add(struct clp_fh_list_entry *entry, void *data)
{
struct zpci_dev *zdev;
@@ -349,22 +342,11 @@ static void __clp_rescan(struct clp_fh_list_entry *entry)
return;
zdev = get_zdev_by_fid(entry->fid);
- if (!zdev) {
+ if (!zdev)
clp_add_pci_device(entry->fid, entry->fh, entry->config_state);
- return;
- }
-
- if (!entry->config_state) {
- /*
- * The handle is already disabled, that means no iota/irq freeing via
- * the firmware interfaces anymore. Need to free resources manually
- * (DMA memory, debug, sysfs)...
- */
- zpci_stop_device(zdev);
- }
}
-static void __clp_update(struct clp_fh_list_entry *entry)
+static void __clp_update(struct clp_fh_list_entry *entry, void *data)
{
struct zpci_dev *zdev;
@@ -387,7 +369,7 @@ int clp_scan_pci_devices(void)
if (!rrb)
return -ENOMEM;
- rc = clp_list_pci(rrb, __clp_add);
+ rc = clp_list_pci(rrb, NULL, __clp_add);
clp_free_block(rrb);
return rc;
@@ -398,11 +380,13 @@ int clp_rescan_pci_devices(void)
struct clp_req_rsp_list_pci *rrb;
int rc;
+ zpci_remove_reserved_devices();
+
rrb = clp_alloc_block(GFP_KERNEL);
if (!rrb)
return -ENOMEM;
- rc = clp_list_pci(rrb, __clp_rescan);
+ rc = clp_list_pci(rrb, NULL, __clp_add);
clp_free_block(rrb);
return rc;
@@ -417,7 +401,40 @@ int clp_rescan_pci_devices_simple(void)
if (!rrb)
return -ENOMEM;
- rc = clp_list_pci(rrb, __clp_update);
+ rc = clp_list_pci(rrb, NULL, __clp_update);
+
+ clp_free_block(rrb);
+ return rc;
+}
+
+struct clp_state_data {
+ u32 fid;
+ enum zpci_state state;
+};
+
+static void __clp_get_state(struct clp_fh_list_entry *entry, void *data)
+{
+ struct clp_state_data *sd = data;
+
+ if (entry->fid != sd->fid)
+ return;
+
+ sd->state = entry->config_state;
+}
+
+int clp_get_state(u32 fid, enum zpci_state *state)
+{
+ struct clp_req_rsp_list_pci *rrb;
+ struct clp_state_data sd = {fid, ZPCI_FN_STATE_RESERVED};
+ int rc;
+
+ rrb = clp_alloc_block(GFP_KERNEL);
+ if (!rrb)
+ return -ENOMEM;
+
+ rc = clp_list_pci(rrb, &sd, __clp_get_state);
+ if (!rc)
+ *state = sd.state;
clp_free_block(rrb);
return rc;
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 9081a57..8eb1cc3 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -601,7 +601,9 @@ void zpci_dma_exit_device(struct zpci_dev *zdev)
*/
WARN_ON(zdev->s390_domain);
- zpci_unregister_ioat(zdev, 0);
+ if (zpci_unregister_ioat(zdev, 0))
+ return;
+
dma_cleanup_tables(zdev->dma_table);
zdev->dma_table = NULL;
vfree(zdev->iommu_bitmap);
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index c2b27ad..0bbc04a 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -74,6 +74,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
{
struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid);
struct pci_dev *pdev = NULL;
+ enum zpci_state state;
int ret;
if (zdev)
@@ -108,6 +109,8 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
clp_add_pci_device(ccdf->fid, ccdf->fh, 0);
break;
case 0x0303: /* Deconfiguration requested */
+ if (!zdev)
+ break;
if (pdev)
pci_stop_and_remove_bus_device_locked(pdev);
@@ -121,7 +124,9 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
zdev->state = ZPCI_FN_STATE_STANDBY;
break;
- case 0x0304: /* Configured -> Standby */
+ case 0x0304: /* Configured -> Standby|Reserved */
+ if (!zdev)
+ break;
if (pdev) {
/* Give the driver a hint that the function is
* already unusable. */
@@ -132,6 +137,10 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
zdev->fh = ccdf->fh;
zpci_disable_device(zdev);
zdev->state = ZPCI_FN_STATE_STANDBY;
+ if (!clp_get_state(ccdf->fid, &state) &&
+ state == ZPCI_FN_STATE_RESERVED) {
+ zpci_remove_device(zdev);
+ }
break;
case 0x0306: /* 0x308 or 0x302 for multiple devices */
clp_rescan_pci_devices();
@@ -139,8 +148,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
case 0x0308: /* Standby -> Reserved */
if (!zdev)
break;
- pci_stop_root_bus(zdev->bus);
- pci_remove_root_bus(zdev->bus);
+ zpci_remove_device(zdev);
break;
default:
break;
diff --git a/arch/s390/pci/pci_insn.c b/arch/s390/pci/pci_insn.c
index fa8d7d4..ea34086 100644
--- a/arch/s390/pci/pci_insn.c
+++ b/arch/s390/pci/pci_insn.c
@@ -40,20 +40,20 @@ static inline u8 __mpcifc(u64 req, struct zpci_fib *fib, u8 *status)
return cc;
}
-int zpci_mod_fc(u64 req, struct zpci_fib *fib)
+u8 zpci_mod_fc(u64 req, struct zpci_fib *fib, u8 *status)
{
- u8 cc, status;
+ u8 cc;
do {
- cc = __mpcifc(req, fib, &status);
+ cc = __mpcifc(req, fib, status);
if (cc == 2)
msleep(ZPCI_INSN_BUSY_DELAY);
} while (cc == 2);
if (cc)
- zpci_err_insn(cc, status, req, 0);
+ zpci_err_insn(cc, *status, req, 0);
- return (cc) ? -EIO : 0;
+ return cc;
}
/* Refresh PCI Translations */
diff --git a/arch/s390/tools/gen_facilities.c b/arch/s390/tools/gen_facilities.c
index be63fbd..025ea20 100644
--- a/arch/s390/tools/gen_facilities.c
+++ b/arch/s390/tools/gen_facilities.c
@@ -34,8 +34,6 @@ static struct facility_def facility_defs[] = {
18, /* long displacement facility */
#endif
#ifdef CONFIG_HAVE_MARCH_Z9_109_FEATURES
- 7, /* stfle */
- 17, /* message security assist */
21, /* extended-immediate facility */
25, /* store clock fast */
#endif
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index fb1e60f..9c7951b 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -89,6 +89,20 @@
requires to have at least one CEX card in coprocessor mode
available at runtime.
+config CRYPTO_PAES_S390
+ tristate "PAES cipher algorithms"
+ depends on S390
+ depends on ZCRYPT
+ depends on PKEY
+ select CRYPTO_ALGAPI
+ select CRYPTO_BLKCIPHER
+ help
+ This is the s390 hardware accelerated implementation of the
+ AES cipher algorithms for use with protected key.
+
+ Select this option if you want to use the paes cipher
+ for example to use protected key encrypted devices.
+
config CRYPTO_SHA1_S390
tristate "SHA1 digest algorithm"
depends on S390
@@ -137,7 +151,6 @@
depends on S390
select CRYPTO_ALGAPI
select CRYPTO_BLKCIPHER
- select PKEY
help
This is the s390 hardware accelerated implementation of the
AES cipher algorithms (FIPS-197).
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 82dab16..3aea556 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -782,24 +782,26 @@ static void debug_dump_dramcfg_low(struct amd64_pvt *pvt, u32 dclr, int chan)
static void debug_display_dimm_sizes_df(struct amd64_pvt *pvt, u8 ctrl)
{
- u32 *dcsb = ctrl ? pvt->csels[1].csbases : pvt->csels[0].csbases;
- int dimm, size0, size1;
+ int dimm, size0, size1, cs0, cs1;
edac_printk(KERN_DEBUG, EDAC_MC, "UMC%d chip selects:\n", ctrl);
for (dimm = 0; dimm < 4; dimm++) {
size0 = 0;
+ cs0 = dimm * 2;
- if (dcsb[dimm*2] & DCSB_CS_ENABLE)
- size0 = pvt->ops->dbam_to_cs(pvt, ctrl, 0, dimm);
+ if (csrow_enabled(cs0, ctrl, pvt))
+ size0 = pvt->ops->dbam_to_cs(pvt, ctrl, 0, cs0);
size1 = 0;
- if (dcsb[dimm*2 + 1] & DCSB_CS_ENABLE)
- size1 = pvt->ops->dbam_to_cs(pvt, ctrl, 0, dimm);
+ cs1 = dimm * 2 + 1;
+
+ if (csrow_enabled(cs1, ctrl, pvt))
+ size1 = pvt->ops->dbam_to_cs(pvt, ctrl, 0, cs1);
amd64_info(EDAC_MC ": %d: %5dMB %d: %5dMB\n",
- dimm * 2, size0,
- dimm * 2 + 1, size1);
+ cs0, size0,
+ cs1, size1);
}
}
@@ -2756,26 +2758,22 @@ static void read_mc_regs(struct amd64_pvt *pvt)
* encompasses
*
*/
-static u32 get_csrow_nr_pages(struct amd64_pvt *pvt, u8 dct, int csrow_nr)
+static u32 get_csrow_nr_pages(struct amd64_pvt *pvt, u8 dct, int csrow_nr_orig)
{
- u32 cs_mode, nr_pages;
u32 dbam = dct ? pvt->dbam1 : pvt->dbam0;
+ int csrow_nr = csrow_nr_orig;
+ u32 cs_mode, nr_pages;
+ if (!pvt->umc)
+ csrow_nr >>= 1;
- /*
- * The math on this doesn't look right on the surface because x/2*4 can
- * be simplified to x*2 but this expression makes use of the fact that
- * it is integral math where 1/2=0. This intermediate value becomes the
- * number of bits to shift the DBAM register to extract the proper CSROW
- * field.
- */
- cs_mode = DBAM_DIMM(csrow_nr / 2, dbam);
+ cs_mode = DBAM_DIMM(csrow_nr, dbam);
- nr_pages = pvt->ops->dbam_to_cs(pvt, dct, cs_mode, (csrow_nr / 2))
- << (20 - PAGE_SHIFT);
+ nr_pages = pvt->ops->dbam_to_cs(pvt, dct, cs_mode, csrow_nr);
+ nr_pages <<= 20 - PAGE_SHIFT;
edac_dbg(0, "csrow: %d, channel: %d, DBAM idx: %d\n",
- csrow_nr, dct, cs_mode);
+ csrow_nr_orig, dct, cs_mode);
edac_dbg(0, "nr_pages/channel: %u\n", nr_pages);
return nr_pages;
diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c
index ed3137c..ab3a951a 100644
--- a/drivers/firmware/efi/efi-pstore.c
+++ b/drivers/firmware/efi/efi-pstore.c
@@ -155,19 +155,14 @@ static int efi_pstore_scan_sysfs_exit(struct efivar_entry *pos,
* efi_pstore_sysfs_entry_iter
*
* @record: pstore record to pass to callback
- * @pos: entry to begin iterating from
*
* You MUST call efivar_enter_iter_begin() before this function, and
* efivar_entry_iter_end() afterwards.
*
- * It is possible to begin iteration from an arbitrary entry within
- * the list by passing @pos. @pos is updated on return to point to
- * the next entry of the last one passed to efi_pstore_read_func().
- * To begin iterating from the beginning of the list @pos must be %NULL.
*/
-static int efi_pstore_sysfs_entry_iter(struct pstore_record *record,
- struct efivar_entry **pos)
+static int efi_pstore_sysfs_entry_iter(struct pstore_record *record)
{
+ struct efivar_entry **pos = (struct efivar_entry **)&record->psi->data;
struct efivar_entry *entry, *n;
struct list_head *head = &efivar_sysfs_list;
int size = 0;
@@ -218,7 +213,6 @@ static int efi_pstore_sysfs_entry_iter(struct pstore_record *record,
*/
static ssize_t efi_pstore_read(struct pstore_record *record)
{
- struct efivar_entry *entry = (struct efivar_entry *)record->psi->data;
ssize_t size;
record->buf = kzalloc(EFIVARS_DATA_SIZE_MAX, GFP_KERNEL);
@@ -229,7 +223,7 @@ static ssize_t efi_pstore_read(struct pstore_record *record)
size = -EINTR;
goto out;
}
- size = efi_pstore_sysfs_entry_iter(record, &entry);
+ size = efi_pstore_sysfs_entry_iter(record);
efivar_entry_iter_end();
out:
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 19581d7..d034d8c 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -849,6 +849,9 @@ static uint64_t _mv88e6xxx_get_ethtool_stat(struct mv88e6xxx_chip *chip,
mv88e6xxx_g1_stats_read(chip, reg, &low);
if (s->sizeof_stat == 8)
mv88e6xxx_g1_stats_read(chip, reg + 1, &high);
+ break;
+ default:
+ return UINT64_MAX;
}
value = (((u64)high) << 16) | low;
return value;
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
index 4ee15ff..faeb493 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
@@ -200,29 +200,18 @@ static int hw_atl_a0_hw_rss_set(struct aq_hw_s *self,
static int hw_atl_a0_hw_offload_set(struct aq_hw_s *self,
struct aq_nic_cfg_s *aq_nic_cfg)
{
- int err = 0;
-
/* TX checksums offloads*/
tpo_ipv4header_crc_offload_en_set(self, 1);
tpo_tcp_udp_crc_offload_en_set(self, 1);
- if (err < 0)
- goto err_exit;
/* RX checksums offloads*/
rpo_ipv4header_crc_offload_en_set(self, 1);
rpo_tcp_udp_crc_offload_en_set(self, 1);
- if (err < 0)
- goto err_exit;
/* LSO offloads*/
tdm_large_send_offload_en_set(self, 0xFFFFFFFFU);
- if (err < 0)
- goto err_exit;
- err = aq_hw_err_from_flags(self);
-
-err_exit:
- return err;
+ return aq_hw_err_from_flags(self);
}
static int hw_atl_a0_hw_init_tx_path(struct aq_hw_s *self)
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 4215070..1bceb73 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -200,25 +200,18 @@ static int hw_atl_b0_hw_rss_set(struct aq_hw_s *self,
static int hw_atl_b0_hw_offload_set(struct aq_hw_s *self,
struct aq_nic_cfg_s *aq_nic_cfg)
{
- int err = 0;
unsigned int i;
/* TX checksums offloads*/
tpo_ipv4header_crc_offload_en_set(self, 1);
tpo_tcp_udp_crc_offload_en_set(self, 1);
- if (err < 0)
- goto err_exit;
/* RX checksums offloads*/
rpo_ipv4header_crc_offload_en_set(self, 1);
rpo_tcp_udp_crc_offload_en_set(self, 1);
- if (err < 0)
- goto err_exit;
/* LSO offloads*/
tdm_large_send_offload_en_set(self, 0xFFFFFFFFU);
- if (err < 0)
- goto err_exit;
/* LRO offloads */
{
@@ -245,10 +238,7 @@ static int hw_atl_b0_hw_offload_set(struct aq_hw_s *self,
rpo_lro_en_set(self, aq_nic_cfg->is_lro ? 0xFFFFFFFFU : 0U);
}
- err = aq_hw_err_from_flags(self);
-
-err_exit:
- return err;
+ return aq_hw_err_from_flags(self);
}
static int hw_atl_b0_hw_init_tx_path(struct aq_hw_s *self)
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 7032054..83aab1e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -2862,12 +2862,10 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
int port = 0;
if (msi_x) {
- int nreq = dev->caps.num_ports * num_online_cpus() + 1;
-
- nreq = min_t(int, dev->caps.num_eqs - dev->caps.reserved_eqs,
- nreq);
- if (nreq > MAX_MSIX)
- nreq = MAX_MSIX;
+ int nreq = min3(dev->caps.num_ports *
+ (int)num_online_cpus() + 1,
+ dev->caps.num_eqs - dev->caps.reserved_eqs,
+ MAX_MSIX);
entries = kcalloc(nreq, sizeof *entries, GFP_KERNEL);
if (!entries)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 0099a3e..2fd044b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -1003,7 +1003,7 @@ int mlx5e_create_direct_tirs(struct mlx5e_priv *priv);
void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv);
void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt);
-int mlx5e_create_ttc_table(struct mlx5e_priv *priv, u32 underlay_qpn);
+int mlx5e_create_ttc_table(struct mlx5e_priv *priv);
void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv);
int mlx5e_create_tis(struct mlx5_core_dev *mdev, int tc,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index ce7b09d..8209aff 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -794,7 +794,6 @@ static void get_supported(u32 eth_proto_cap,
ptys2ethtool_supported_port(link_ksettings, eth_proto_cap);
ptys2ethtool_supported_link(supported, eth_proto_cap);
ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Pause);
- ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Asym_Pause);
}
static void get_advertising(u32 eth_proto_cap, u8 tx_pause,
@@ -804,7 +803,7 @@ static void get_advertising(u32 eth_proto_cap, u8 tx_pause,
unsigned long *advertising = link_ksettings->link_modes.advertising;
ptys2ethtool_adver_link(advertising, eth_proto_cap);
- if (tx_pause)
+ if (rx_pause)
ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, Pause);
if (tx_pause ^ rx_pause)
ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, Asym_Pause);
@@ -849,6 +848,8 @@ static int mlx5e_get_link_ksettings(struct net_device *netdev,
struct mlx5e_priv *priv = netdev_priv(netdev);
struct mlx5_core_dev *mdev = priv->mdev;
u32 out[MLX5_ST_SZ_DW(ptys_reg)] = {0};
+ u32 rx_pause = 0;
+ u32 tx_pause = 0;
u32 eth_proto_cap;
u32 eth_proto_admin;
u32 eth_proto_lp;
@@ -871,11 +872,13 @@ static int mlx5e_get_link_ksettings(struct net_device *netdev,
an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin);
an_status = MLX5_GET(ptys_reg, out, an_status);
+ mlx5_query_port_pause(mdev, &rx_pause, &tx_pause);
+
ethtool_link_ksettings_zero_link_mode(link_ksettings, supported);
ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising);
get_supported(eth_proto_cap, link_ksettings);
- get_advertising(eth_proto_admin, 0, 0, link_ksettings);
+ get_advertising(eth_proto_admin, tx_pause, rx_pause, link_ksettings);
get_speed_duplex(netdev, eth_proto_oper, link_ksettings);
eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index 576d678..53ed583 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -800,7 +800,7 @@ void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv)
mlx5e_destroy_flow_table(&ttc->ft);
}
-int mlx5e_create_ttc_table(struct mlx5e_priv *priv, u32 underlay_qpn)
+int mlx5e_create_ttc_table(struct mlx5e_priv *priv)
{
struct mlx5e_ttc_table *ttc = &priv->fs.ttc;
struct mlx5_flow_table_attr ft_attr = {};
@@ -810,7 +810,6 @@ int mlx5e_create_ttc_table(struct mlx5e_priv *priv, u32 underlay_qpn)
ft_attr.max_fte = MLX5E_TTC_TABLE_SIZE;
ft_attr.level = MLX5E_TTC_FT_LEVEL;
ft_attr.prio = MLX5E_NIC_PRIO;
- ft_attr.underlay_qpn = underlay_qpn;
ft->t = mlx5_create_flow_table(priv->fs.ns, &ft_attr);
if (IS_ERR(ft->t)) {
@@ -1147,7 +1146,7 @@ int mlx5e_create_flow_steering(struct mlx5e_priv *priv)
priv->netdev->hw_features &= ~NETIF_F_NTUPLE;
}
- err = mlx5e_create_ttc_table(priv, 0);
+ err = mlx5e_create_ttc_table(priv);
if (err) {
netdev_err(priv->netdev, "Failed to create ttc table, err=%d\n",
err);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index a61b71b..41cd22a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2976,7 +2976,7 @@ static int mlx5e_setup_tc(struct net_device *netdev, u8 tc)
new_channels.params = priv->channels.params;
new_channels.params.num_tc = tc ? tc : 1;
- if (test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+ if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
priv->channels.params = new_channels.params;
goto out;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index 19e3d2f..fcec7be 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -40,28 +40,25 @@
#include "eswitch.h"
int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev,
- struct mlx5_flow_table *ft)
+ struct mlx5_flow_table *ft, u32 underlay_qpn)
{
u32 in[MLX5_ST_SZ_DW(set_flow_table_root_in)] = {0};
u32 out[MLX5_ST_SZ_DW(set_flow_table_root_out)] = {0};
if ((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_IB) &&
- ft->underlay_qpn == 0)
+ underlay_qpn == 0)
return 0;
MLX5_SET(set_flow_table_root_in, in, opcode,
MLX5_CMD_OP_SET_FLOW_TABLE_ROOT);
MLX5_SET(set_flow_table_root_in, in, table_type, ft->type);
MLX5_SET(set_flow_table_root_in, in, table_id, ft->id);
+ MLX5_SET(set_flow_table_root_in, in, underlay_qpn, underlay_qpn);
if (ft->vport) {
MLX5_SET(set_flow_table_root_in, in, vport_number, ft->vport);
MLX5_SET(set_flow_table_root_in, in, other_vport, 1);
}
- if ((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_IB) &&
- ft->underlay_qpn != 0)
- MLX5_SET(set_flow_table_root_in, in, underlay_qpn, ft->underlay_qpn);
-
return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h
index 8fad806..0f98a7c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h
@@ -71,7 +71,8 @@ int mlx5_cmd_delete_fte(struct mlx5_core_dev *dev,
unsigned int index);
int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev,
- struct mlx5_flow_table *ft);
+ struct mlx5_flow_table *ft,
+ u32 underlay_qpn);
int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u16 *id);
int mlx5_cmd_fc_free(struct mlx5_core_dev *dev, u16 id);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index b8a1765..0e487e8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -650,7 +650,7 @@ static int update_root_ft_create(struct mlx5_flow_table *ft, struct fs_prio
if (ft->level >= min_level)
return 0;
- err = mlx5_cmd_update_root_ft(root->dev, ft);
+ err = mlx5_cmd_update_root_ft(root->dev, ft, root->underlay_qpn);
if (err)
mlx5_core_warn(root->dev, "Update root flow table of id=%u failed\n",
ft->id);
@@ -818,8 +818,6 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa
goto unlock_root;
}
- ft->underlay_qpn = ft_attr->underlay_qpn;
-
tree_init_node(&ft->node, 1, del_flow_table);
log_table_sz = ft->max_fte ? ilog2(ft->max_fte) : 0;
next_ft = find_next_chained_ft(fs_prio);
@@ -1489,7 +1487,8 @@ static int update_root_ft_destroy(struct mlx5_flow_table *ft)
new_root_ft = find_next_ft(ft);
if (new_root_ft) {
- int err = mlx5_cmd_update_root_ft(root->dev, new_root_ft);
+ int err = mlx5_cmd_update_root_ft(root->dev, new_root_ft,
+ root->underlay_qpn);
if (err) {
mlx5_core_warn(root->dev, "Update root flow table of id=%u failed\n",
@@ -2062,3 +2061,21 @@ int mlx5_init_fs(struct mlx5_core_dev *dev)
mlx5_cleanup_fs(dev);
return err;
}
+
+int mlx5_fs_add_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn)
+{
+ struct mlx5_flow_root_namespace *root = dev->priv.steering->root_ns;
+
+ root->underlay_qpn = underlay_qpn;
+ return 0;
+}
+EXPORT_SYMBOL(mlx5_fs_add_rx_underlay_qpn);
+
+int mlx5_fs_remove_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn)
+{
+ struct mlx5_flow_root_namespace *root = dev->priv.steering->root_ns;
+
+ root->underlay_qpn = 0;
+ return 0;
+}
+EXPORT_SYMBOL(mlx5_fs_remove_rx_underlay_qpn);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index 81eafc7..990acee 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -118,7 +118,6 @@ struct mlx5_flow_table {
/* FWD rules that point on this flow table */
struct list_head fwd_rules;
u32 flags;
- u32 underlay_qpn;
};
struct mlx5_fc_cache {
@@ -195,6 +194,7 @@ struct mlx5_flow_root_namespace {
struct mlx5_flow_table *root_ft;
/* Should be held when chaining flow tables */
struct mutex chain_lock;
+ u32 underlay_qpn;
};
int mlx5_init_fc_stats(struct mlx5_core_dev *dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib.c
index 019c230..cc18587 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib.c
@@ -66,6 +66,10 @@ static void mlx5i_init(struct mlx5_core_dev *mdev,
mlx5e_build_nic_params(mdev, &priv->channels.params, profile->max_nch(mdev));
+ /* Override RQ params as IPoIB supports only LINKED LIST RQ for now */
+ mlx5e_set_rq_type_params(mdev, &priv->channels.params, MLX5_WQ_TYPE_LINKED_LIST);
+ priv->channels.params.lro_en = false;
+
mutex_init(&priv->state_lock);
netdev->hw_features |= NETIF_F_SG;
@@ -156,6 +160,8 @@ static int mlx5i_create_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core
static void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp)
{
+ mlx5_fs_remove_rx_underlay_qpn(mdev, qp->qpn);
+
mlx5_core_destroy_qp(mdev, qp);
}
@@ -170,6 +176,8 @@ static int mlx5i_init_tx(struct mlx5e_priv *priv)
return err;
}
+ mlx5_fs_add_rx_underlay_qpn(priv->mdev, ipriv->qp.qpn);
+
err = mlx5e_create_tis(priv->mdev, 0 /* tc */, ipriv->qp.qpn, &priv->tisn[0]);
if (err) {
mlx5_core_warn(priv->mdev, "create tis failed, %d\n", err);
@@ -189,7 +197,6 @@ static void mlx5i_cleanup_tx(struct mlx5e_priv *priv)
static int mlx5i_create_flow_steering(struct mlx5e_priv *priv)
{
- struct mlx5i_priv *ipriv = priv->ppriv;
int err;
priv->fs.ns = mlx5_get_flow_namespace(priv->mdev,
@@ -205,7 +212,7 @@ static int mlx5i_create_flow_steering(struct mlx5e_priv *priv)
priv->netdev->hw_features &= ~NETIF_F_NTUPLE;
}
- err = mlx5e_create_ttc_table(priv, ipriv->qp.qpn);
+ err = mlx5e_create_ttc_table(priv);
if (err) {
netdev_err(priv->netdev, "Failed to create ttc table, err=%d\n",
err);
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ctx.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ctx.c
index b8d5270..e306765 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ctx.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ctx.c
@@ -247,7 +247,7 @@ nx_fw_cmd_set_mtu(struct netxen_adapter *adapter, int mtu)
cmd.req.arg3 = 0;
if (recv_ctx->state == NX_HOST_CTX_STATE_ACTIVE)
- netxen_issue_cmd(adapter, &cmd);
+ rcode = netxen_issue_cmd(adapter, &cmd);
if (rcode != NX_RCODE_SUCCESS)
return -EIO;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
index 67200c5..0a8fde6 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
@@ -983,7 +983,7 @@ void qed_set_rfs_mode_disable(struct qed_hwfn *p_hwfn,
memset(&camline, 0, sizeof(union gft_cam_line_union));
qed_wr(p_hwfn, p_ptt, PRS_REG_GFT_CAM + CAM_LINE_SIZE * pf_id,
camline.cam_line_mapped.camline);
- memset(&ramline, 0, sizeof(union gft_cam_line_union));
+ memset(&ramline, 0, sizeof(ramline));
for (i = 0; i < RAM_LINE_SIZE / REG_SIZE; i++) {
u32 hw_addr = PRS_REG_GFT_PROFILE_MASK_RAM;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index 49bad00..7245b10 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -37,8 +37,8 @@
#define _QLCNIC_LINUX_MAJOR 5
#define _QLCNIC_LINUX_MINOR 3
-#define _QLCNIC_LINUX_SUBVERSION 65
-#define QLCNIC_LINUX_VERSIONID "5.3.65"
+#define _QLCNIC_LINUX_SUBVERSION 66
+#define QLCNIC_LINUX_VERSIONID "5.3.66"
#define QLCNIC_DRV_IDC_VER 0x01
#define QLCNIC_DRIVER_VERSION ((_QLCNIC_LINUX_MAJOR << 16) |\
(_QLCNIC_LINUX_MINOR << 8) | (_QLCNIC_LINUX_SUBVERSION))
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index 718bf58..4fb6879 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -3168,6 +3168,40 @@ int qlcnic_83xx_flash_read32(struct qlcnic_adapter *adapter, u32 flash_addr,
return 0;
}
+void qlcnic_83xx_get_port_type(struct qlcnic_adapter *adapter)
+{
+ struct qlcnic_hardware_context *ahw = adapter->ahw;
+ struct qlcnic_cmd_args cmd;
+ u32 config;
+ int err;
+
+ err = qlcnic_alloc_mbx_args(&cmd, adapter, QLCNIC_CMD_GET_LINK_STATUS);
+ if (err)
+ return;
+
+ err = qlcnic_issue_cmd(adapter, &cmd);
+ if (err) {
+ dev_info(&adapter->pdev->dev,
+ "Get Link Status Command failed: 0x%x\n", err);
+ goto out;
+ } else {
+ config = cmd.rsp.arg[3];
+
+ switch (QLC_83XX_SFP_MODULE_TYPE(config)) {
+ case QLC_83XX_MODULE_FIBRE_1000BASE_SX:
+ case QLC_83XX_MODULE_FIBRE_1000BASE_LX:
+ case QLC_83XX_MODULE_FIBRE_1000BASE_CX:
+ case QLC_83XX_MODULE_TP_1000BASE_T:
+ ahw->port_type = QLCNIC_GBE;
+ break;
+ default:
+ ahw->port_type = QLCNIC_XGBE;
+ }
+ }
+out:
+ qlcnic_free_mbx_args(&cmd);
+}
+
int qlcnic_83xx_test_link(struct qlcnic_adapter *adapter)
{
u8 pci_func;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h
index 3dfe8e2..b75a812 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h
@@ -637,6 +637,7 @@ void qlcnic_83xx_get_pauseparam(struct qlcnic_adapter *,
int qlcnic_83xx_set_pauseparam(struct qlcnic_adapter *,
struct ethtool_pauseparam *);
int qlcnic_83xx_test_link(struct qlcnic_adapter *);
+void qlcnic_83xx_get_port_type(struct qlcnic_adapter *adapter);
int qlcnic_83xx_reg_test(struct qlcnic_adapter *);
int qlcnic_83xx_get_regs_len(struct qlcnic_adapter *);
int qlcnic_83xx_get_registers(struct qlcnic_adapter *, u32 *);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
index 9a869c1..7f7deea 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
@@ -486,6 +486,9 @@ static int qlcnic_set_link_ksettings(struct net_device *dev,
u32 ret = 0;
struct qlcnic_adapter *adapter = netdev_priv(dev);
+ if (qlcnic_83xx_check(adapter))
+ qlcnic_83xx_get_port_type(adapter);
+
if (adapter->ahw->port_type != QLCNIC_GBE)
return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index 513e6c7..24ca7df 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -296,8 +296,9 @@ qcaspi_receive(struct qcaspi *qca)
/* Allocate rx SKB if we don't have one available. */
if (!qca->rx_skb) {
- qca->rx_skb = netdev_alloc_skb(net_dev,
- net_dev->mtu + VLAN_ETH_HLEN);
+ qca->rx_skb = netdev_alloc_skb_ip_align(net_dev,
+ net_dev->mtu +
+ VLAN_ETH_HLEN);
if (!qca->rx_skb) {
netdev_dbg(net_dev, "out of RX resources\n");
qca->stats.out_of_mem++;
@@ -377,7 +378,7 @@ qcaspi_receive(struct qcaspi *qca)
qca->rx_skb, qca->rx_skb->dev);
qca->rx_skb->ip_summed = CHECKSUM_UNNECESSARY;
netif_rx_ni(qca->rx_skb);
- qca->rx_skb = netdev_alloc_skb(net_dev,
+ qca->rx_skb = netdev_alloc_skb_ip_align(net_dev,
net_dev->mtu + VLAN_ETH_HLEN);
if (!qca->rx_skb) {
netdev_dbg(net_dev, "out of RX resources\n");
@@ -759,7 +760,8 @@ qcaspi_netdev_init(struct net_device *dev)
if (!qca->rx_buffer)
return -ENOBUFS;
- qca->rx_skb = netdev_alloc_skb(dev, qca->net_dev->mtu + VLAN_ETH_HLEN);
+ qca->rx_skb = netdev_alloc_skb_ip_align(dev, qca->net_dev->mtu +
+ VLAN_ETH_HLEN);
if (!qca->rx_skb) {
kfree(qca->rx_buffer);
netdev_info(qca->net_dev, "Failed to allocate RX sk_buff.\n");
diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h
index 7b916aa..4d7fb8a 100644
--- a/drivers/net/ethernet/sfc/nic.h
+++ b/drivers/net/ethernet/sfc/nic.h
@@ -18,8 +18,12 @@
#include "mcdi.h"
enum {
- EFX_REV_SIENA_A0 = 0,
- EFX_REV_HUNT_A0 = 1,
+ /* Revisions 0-2 were Falcon A0, A1 and B0 respectively.
+ * They are not supported by this driver but these revision numbers
+ * form part of the ethtool API for register dumping.
+ */
+ EFX_REV_SIENA_A0 = 3,
+ EFX_REV_HUNT_A0 = 4,
};
static inline int efx_nic_rev(struct efx_nic *efx)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index cd8c601..a74c481 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3725,7 +3725,7 @@ static void sysfs_display_ring(void *head, int size, int extend_desc,
ep++;
} else {
seq_printf(seq, "%d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n",
- i, (unsigned int)virt_to_phys(ep),
+ i, (unsigned int)virt_to_phys(p),
le32_to_cpu(p->des0), le32_to_cpu(p->des1),
le32_to_cpu(p->des2), le32_to_cpu(p->des3));
p++;
diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c
index 5a90fed..5b56c24 100644
--- a/drivers/net/ethernet/sun/ldmvsw.c
+++ b/drivers/net/ethernet/sun/ldmvsw.c
@@ -411,13 +411,14 @@ static int vsw_port_remove(struct vio_dev *vdev)
if (port) {
del_timer_sync(&port->vio.timer);
+ del_timer_sync(&port->clean_timer);
napi_disable(&port->napi);
+ unregister_netdev(port->dev);
list_del_rcu(&port->list);
synchronize_rcu();
- del_timer_sync(&port->clean_timer);
spin_lock_irqsave(&port->vp->lock, flags);
sunvnet_port_rm_txq_common(port);
spin_unlock_irqrestore(&port->vp->lock, flags);
@@ -427,7 +428,6 @@ static int vsw_port_remove(struct vio_dev *vdev)
dev_set_drvdata(&vdev->dev, NULL);
- unregister_netdev(port->dev);
free_netdev(port->dev);
}
diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c
index 729a7da..e6222e5 100644
--- a/drivers/net/ethernet/ti/netcp_core.c
+++ b/drivers/net/ethernet/ti/netcp_core.c
@@ -1353,9 +1353,10 @@ int netcp_txpipe_open(struct netcp_tx_pipe *tx_pipe)
tx_pipe->dma_channel = knav_dma_open_channel(dev,
tx_pipe->dma_chan_name, &config);
- if (IS_ERR_OR_NULL(tx_pipe->dma_channel)) {
+ if (IS_ERR(tx_pipe->dma_channel)) {
dev_err(dev, "failed opening tx chan(%s)\n",
tx_pipe->dma_chan_name);
+ ret = PTR_ERR(tx_pipe->dma_channel);
goto err;
}
@@ -1673,9 +1674,10 @@ static int netcp_setup_navigator_resources(struct net_device *ndev)
netcp->rx_channel = knav_dma_open_channel(netcp->netcp_device->device,
netcp->dma_chan_name, &config);
- if (IS_ERR_OR_NULL(netcp->rx_channel)) {
+ if (IS_ERR(netcp->rx_channel)) {
dev_err(netcp->ndev_dev, "failed opening rx chan(%s\n",
netcp->dma_chan_name);
+ ret = PTR_ERR(netcp->rx_channel);
goto fail;
}
diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c
index 897176f..dd92950 100644
--- a/drivers/net/ethernet/ti/netcp_ethss.c
+++ b/drivers/net/ethernet/ti/netcp_ethss.c
@@ -2651,7 +2651,6 @@ static int gbe_hwtstamp_set(struct gbe_intf *gbe_intf, struct ifreq *ifr)
case HWTSTAMP_FILTER_NONE:
cpts_rx_enable(cpts, 0);
break;
- case HWTSTAMP_FILTER_ALL:
case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
diff --git a/drivers/net/irda/irda-usb.c b/drivers/net/irda/irda-usb.c
index 8716b8c..6f3c805 100644
--- a/drivers/net/irda/irda-usb.c
+++ b/drivers/net/irda/irda-usb.c
@@ -1077,7 +1077,7 @@ static int stir421x_patch_device(struct irda_usb_cb *self)
* are "42101001.sb" or "42101002.sb"
*/
sprintf(stir421x_fw_name, "4210%4X.sb",
- self->usbdev->descriptor.bcdDevice);
+ le16_to_cpu(self->usbdev->descriptor.bcdDevice));
ret = request_firmware(&fw, stir421x_fw_name, &self->usbdev->dev);
if (ret < 0)
return ret;
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index b34eaaa..346ad2f 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -789,10 +789,12 @@ static int macvlan_change_mtu(struct net_device *dev, int new_mtu)
*/
static struct lock_class_key macvlan_netdev_addr_lock_key;
-#define ALWAYS_ON_FEATURES \
- (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE | NETIF_F_LLTX | \
+#define ALWAYS_ON_OFFLOADS \
+ (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE | \
NETIF_F_GSO_ROBUST)
+#define ALWAYS_ON_FEATURES (ALWAYS_ON_OFFLOADS | NETIF_F_LLTX)
+
#define MACVLAN_FEATURES \
(NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \
NETIF_F_GSO | NETIF_F_TSO | NETIF_F_UFO | NETIF_F_LRO | \
@@ -827,6 +829,7 @@ static int macvlan_init(struct net_device *dev)
dev->features |= ALWAYS_ON_FEATURES;
dev->hw_features |= NETIF_F_LRO;
dev->vlan_features = lowerdev->vlan_features & MACVLAN_FEATURES;
+ dev->vlan_features |= ALWAYS_ON_OFFLOADS;
dev->gso_max_size = lowerdev->gso_max_size;
dev->gso_max_segs = lowerdev->gso_max_segs;
dev->hard_header_len = lowerdev->hard_header_len;
diff --git a/drivers/net/phy/mdio-mux.c b/drivers/net/phy/mdio-mux.c
index 963838d..599ce24 100644
--- a/drivers/net/phy/mdio-mux.c
+++ b/drivers/net/phy/mdio-mux.c
@@ -122,10 +122,9 @@ int mdio_mux_init(struct device *dev,
pb = devm_kzalloc(dev, sizeof(*pb), GFP_KERNEL);
if (pb == NULL) {
ret_val = -ENOMEM;
- goto err_parent_bus;
+ goto err_pb_kz;
}
-
pb->switch_data = data;
pb->switch_fn = switch_fn;
pb->current_child = -1;
@@ -154,6 +153,7 @@ int mdio_mux_init(struct device *dev,
cb->mii_bus = mdiobus_alloc();
if (!cb->mii_bus) {
ret_val = -ENOMEM;
+ devm_kfree(dev, cb);
of_node_put(child_bus_node);
break;
}
@@ -170,7 +170,6 @@ int mdio_mux_init(struct device *dev,
mdiobus_free(cb->mii_bus);
devm_kfree(dev, cb);
} else {
- of_node_get(child_bus_node);
cb->next = pb->children;
pb->children = cb;
}
@@ -181,9 +180,11 @@ int mdio_mux_init(struct device *dev,
return 0;
}
+ devm_kfree(dev, pb);
+err_pb_kz:
/* balance the reference of_mdio_find_bus() took */
- put_device(&pb->mii_bus->dev);
-
+ if (!mux_bus)
+ put_device(&parent_bus->dev);
err_parent_bus:
of_node_put(parent_bus_node);
return ret_val;
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index a898e5c..8e73f5f 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -364,9 +364,6 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner)
mutex_init(&bus->mdio_lock);
- if (bus->reset)
- bus->reset(bus);
-
/* de-assert bus level PHY GPIO resets */
if (bus->num_reset_gpios > 0) {
bus->reset_gpiod = devm_kcalloc(&bus->dev,
@@ -396,6 +393,9 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner)
}
}
+ if (bus->reset)
+ bus->reset(bus);
+
for (i = 0; i < PHY_MAX_ADDR; i++) {
if ((bus->phy_mask & (1 << i)) == 0) {
struct phy_device *phydev;
diff --git a/drivers/net/usb/ch9200.c b/drivers/net/usb/ch9200.c
index c4f1c36..9df3c1f 100644
--- a/drivers/net/usb/ch9200.c
+++ b/drivers/net/usb/ch9200.c
@@ -310,8 +310,8 @@ static int get_mac_address(struct usbnet *dev, unsigned char *data)
int rd_mac_len = 0;
netdev_dbg(dev->net, "get_mac_address:\n\tusbnet VID:%0x PID:%0x\n",
- dev->udev->descriptor.idVendor,
- dev->udev->descriptor.idProduct);
+ le16_to_cpu(dev->udev->descriptor.idVendor),
+ le16_to_cpu(dev->udev->descriptor.idProduct));
memset(mac_addr, 0, sizeof(mac_addr));
rd_mac_len = control_read(dev, REQUEST_READ, 0,
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 25bc764..d1c7029 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -2962,6 +2962,11 @@ vmxnet3_force_close(struct vmxnet3_adapter *adapter)
/* we need to enable NAPI, otherwise dev_close will deadlock */
for (i = 0; i < adapter->num_rx_queues; i++)
napi_enable(&adapter->rx_queue[i].napi);
+ /*
+ * Need to clear the quiesce bit to ensure that vmxnet3_close
+ * can quiesce the device properly
+ */
+ clear_bit(VMXNET3_STATE_BIT_QUIESCED, &adapter->state);
dev_close(adapter->netdev);
}
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index ceda586..db88249 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -989,6 +989,7 @@ static u32 vrf_fib_table(const struct net_device *dev)
static int vrf_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
+ kfree_skb(skb);
return 0;
}
@@ -998,7 +999,7 @@ static struct sk_buff *vrf_rcv_nfhook(u8 pf, unsigned int hook,
{
struct net *net = dev_net(dev);
- if (NF_HOOK(pf, hook, net, NULL, skb, dev, NULL, vrf_rcv_finish) < 0)
+ if (nf_hook(pf, hook, net, NULL, skb, dev, NULL, vrf_rcv_finish) != 1)
skb = NULL; /* kfree_skb(skb) handled by nf code */
return skb;
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 6ffc482..7b61adb 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -1934,8 +1934,7 @@ static int talk_to_netback(struct xenbus_device *dev,
xennet_disconnect_backend(info);
xennet_destroy_queues(info);
out:
- unregister_netdev(info->netdev);
- xennet_free_netdev(info->netdev);
+ device_unregister(&dev->dev);
return err;
}
diff --git a/drivers/s390/block/Kconfig b/drivers/s390/block/Kconfig
index 0acb8c2..31f014b 100644
--- a/drivers/s390/block/Kconfig
+++ b/drivers/s390/block/Kconfig
@@ -82,10 +82,3 @@
To compile this driver as a module, choose M here: the
module will be called scm_block.
-
-config SCM_BLOCK_CLUSTER_WRITE
- def_bool y
- prompt "SCM force cluster writes"
- depends on SCM_BLOCK
- help
- Force writes to Storage Class Memory (SCM) to be in done in clusters.
diff --git a/drivers/s390/block/Makefile b/drivers/s390/block/Makefile
index c2f4e67..b64e2b3 100644
--- a/drivers/s390/block/Makefile
+++ b/drivers/s390/block/Makefile
@@ -19,7 +19,4 @@
obj-$(CONFIG_DCSSBLK) += dcssblk.o
scm_block-objs := scm_drv.o scm_blk.o
-ifdef CONFIG_SCM_BLOCK_CLUSTER_WRITE
-scm_block-objs += scm_blk_cluster.o
-endif
obj-$(CONFIG_SCM_BLOCK) += scm_block.o
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index 6fb3fd5..c72ac57 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -1965,8 +1965,12 @@ static int __dasd_device_is_unusable(struct dasd_device *device,
{
int mask = ~(DASD_STOPPED_DC_WAIT | DASD_UNRESUMED_PM);
- if (test_bit(DASD_FLAG_OFFLINE, &device->flags)) {
- /* dasd is being set offline. */
+ if (test_bit(DASD_FLAG_OFFLINE, &device->flags) &&
+ !test_bit(DASD_FLAG_SAFE_OFFLINE_RUNNING, &device->flags)) {
+ /*
+ * dasd is being set offline
+ * but it is no safe offline where we have to allow I/O
+ */
return 1;
}
if (device->stopped) {
@@ -3562,57 +3566,69 @@ int dasd_generic_set_offline(struct ccw_device *cdev)
else
pr_warn("%s: The DASD cannot be set offline while it is in use\n",
dev_name(&cdev->dev));
- clear_bit(DASD_FLAG_OFFLINE, &device->flags);
- goto out_busy;
+ rc = -EBUSY;
+ goto out_err;
}
}
- if (test_bit(DASD_FLAG_SAFE_OFFLINE_RUNNING, &device->flags)) {
- /*
- * safe offline already running
- * could only be called by normal offline so safe_offline flag
- * needs to be removed to run normal offline and kill all I/O
- */
- if (test_and_set_bit(DASD_FLAG_OFFLINE, &device->flags))
- /* Already doing normal offline processing */
- goto out_busy;
- else
- clear_bit(DASD_FLAG_SAFE_OFFLINE, &device->flags);
- } else {
- if (test_bit(DASD_FLAG_OFFLINE, &device->flags))
- /* Already doing offline processing */
- goto out_busy;
+ /*
+ * Test if the offline processing is already running and exit if so.
+ * If a safe offline is being processed this could only be a normal
+ * offline that should be able to overtake the safe offline and
+ * cancel any I/O we do not want to wait for any longer
+ */
+ if (test_bit(DASD_FLAG_OFFLINE, &device->flags)) {
+ if (test_bit(DASD_FLAG_SAFE_OFFLINE_RUNNING, &device->flags)) {
+ clear_bit(DASD_FLAG_SAFE_OFFLINE_RUNNING,
+ &device->flags);
+ } else {
+ rc = -EBUSY;
+ goto out_err;
+ }
}
-
set_bit(DASD_FLAG_OFFLINE, &device->flags);
- spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags);
/*
- * if safe_offline called set safe_offline_running flag and
+ * if safe_offline is called set safe_offline_running flag and
* clear safe_offline so that a call to normal offline
* can overrun safe_offline processing
*/
if (test_and_clear_bit(DASD_FLAG_SAFE_OFFLINE, &device->flags) &&
!test_and_set_bit(DASD_FLAG_SAFE_OFFLINE_RUNNING, &device->flags)) {
+ /* need to unlock here to wait for outstanding I/O */
+ spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags);
/*
* If we want to set the device safe offline all IO operations
* should be finished before continuing the offline process
* so sync bdev first and then wait for our queues to become
* empty
*/
- /* sync blockdev and partitions */
if (device->block) {
rc = fsync_bdev(device->block->bdev);
if (rc != 0)
goto interrupted;
}
- /* schedule device tasklet and wait for completion */
dasd_schedule_device_bh(device);
rc = wait_event_interruptible(shutdown_waitq,
_wait_for_empty_queues(device));
if (rc != 0)
goto interrupted;
+
+ /*
+ * check if a normal offline process overtook the offline
+ * processing in this case simply do nothing beside returning
+ * that we got interrupted
+ * otherwise mark safe offline as not running any longer and
+ * continue with normal offline
+ */
+ spin_lock_irqsave(get_ccwdev_lock(cdev), flags);
+ if (!test_bit(DASD_FLAG_SAFE_OFFLINE_RUNNING, &device->flags)) {
+ rc = -ERESTARTSYS;
+ goto out_err;
+ }
+ clear_bit(DASD_FLAG_SAFE_OFFLINE_RUNNING, &device->flags);
}
+ spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags);
dasd_set_target_state(device, DASD_STATE_NEW);
/* dasd_delete_device destroys the device reference. */
@@ -3624,22 +3640,18 @@ int dasd_generic_set_offline(struct ccw_device *cdev)
*/
if (block)
dasd_free_block(block);
+
return 0;
interrupted:
/* interrupted by signal */
- clear_bit(DASD_FLAG_SAFE_OFFLINE, &device->flags);
+ spin_lock_irqsave(get_ccwdev_lock(cdev), flags);
clear_bit(DASD_FLAG_SAFE_OFFLINE_RUNNING, &device->flags);
clear_bit(DASD_FLAG_OFFLINE, &device->flags);
- dasd_put_device(device);
-
- return rc;
-
-out_busy:
+out_err:
dasd_put_device(device);
spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags);
-
- return -EBUSY;
+ return rc;
}
EXPORT_SYMBOL_GPL(dasd_generic_set_offline);
diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c
index 1164b51..7c73512 100644
--- a/drivers/s390/block/dasd_devmap.c
+++ b/drivers/s390/block/dasd_devmap.c
@@ -315,45 +315,58 @@ static int __init dasd_parse_range(const char *range)
char *features_str = NULL;
char *from_str = NULL;
char *to_str = NULL;
- size_t len = strlen(range) + 1;
- char tmp[len];
+ int rc = 0;
+ char *tmp;
- strlcpy(tmp, range, len);
+ tmp = kstrdup(range, GFP_KERNEL);
+ if (!tmp)
+ return -ENOMEM;
- if (dasd_evaluate_range_param(tmp, &from_str, &to_str, &features_str))
- goto out_err;
+ if (dasd_evaluate_range_param(tmp, &from_str, &to_str, &features_str)) {
+ rc = -EINVAL;
+ goto out;
+ }
- if (dasd_busid(from_str, &from_id0, &from_id1, &from))
- goto out_err;
+ if (dasd_busid(from_str, &from_id0, &from_id1, &from)) {
+ rc = -EINVAL;
+ goto out;
+ }
to = from;
to_id0 = from_id0;
to_id1 = from_id1;
if (to_str) {
- if (dasd_busid(to_str, &to_id0, &to_id1, &to))
- goto out_err;
+ if (dasd_busid(to_str, &to_id0, &to_id1, &to)) {
+ rc = -EINVAL;
+ goto out;
+ }
if (from_id0 != to_id0 || from_id1 != to_id1 || from > to) {
pr_err("%s is not a valid device range\n", range);
- goto out_err;
+ rc = -EINVAL;
+ goto out;
}
}
features = dasd_feature_list(features_str);
- if (features < 0)
- goto out_err;
+ if (features < 0) {
+ rc = -EINVAL;
+ goto out;
+ }
/* each device in dasd= parameter should be set initially online */
features |= DASD_FEATURE_INITIAL_ONLINE;
while (from <= to) {
sprintf(bus_id, "%01x.%01x.%04x", from_id0, from_id1, from++);
devmap = dasd_add_busid(bus_id, features);
- if (IS_ERR(devmap))
- return PTR_ERR(devmap);
+ if (IS_ERR(devmap)) {
+ rc = PTR_ERR(devmap);
+ goto out;
+ }
}
- return 0;
+out:
+ kfree(tmp);
-out_err:
- return -EINVAL;
+ return rc;
}
/*
@@ -735,13 +748,22 @@ static ssize_t
dasd_ro_show(struct device *dev, struct device_attribute *attr, char *buf)
{
struct dasd_devmap *devmap;
- int ro_flag;
+ struct dasd_device *device;
+ int ro_flag = 0;
devmap = dasd_find_busid(dev_name(dev));
- if (!IS_ERR(devmap))
- ro_flag = (devmap->features & DASD_FEATURE_READONLY) != 0;
- else
- ro_flag = (DASD_FEATURE_DEFAULT & DASD_FEATURE_READONLY) != 0;
+ if (IS_ERR(devmap))
+ goto out;
+
+ ro_flag = !!(devmap->features & DASD_FEATURE_READONLY);
+
+ spin_lock(&dasd_devmap_lock);
+ device = devmap->device;
+ if (device)
+ ro_flag |= test_bit(DASD_FLAG_DEVICE_RO, &device->flags);
+ spin_unlock(&dasd_devmap_lock);
+
+out:
return snprintf(buf, PAGE_SIZE, ro_flag ? "1\n" : "0\n");
}
@@ -764,7 +786,7 @@ dasd_ro_store(struct device *dev, struct device_attribute *attr,
device = dasd_device_from_cdev(cdev);
if (IS_ERR(device))
- return PTR_ERR(device);
+ return count;
spin_lock_irqsave(get_ccwdev_lock(cdev), flags);
val = val || test_bit(DASD_FLAG_DEVICE_RO, &device->flags);
@@ -928,11 +950,14 @@ dasd_safe_offline_store(struct device *dev, struct device_attribute *attr,
{
struct ccw_device *cdev = to_ccwdev(dev);
struct dasd_device *device;
+ unsigned long flags;
int rc;
- device = dasd_device_from_cdev(cdev);
+ spin_lock_irqsave(get_ccwdev_lock(cdev), flags);
+ device = dasd_device_from_cdev_locked(cdev);
if (IS_ERR(device)) {
rc = PTR_ERR(device);
+ spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags);
goto out;
}
@@ -940,12 +965,14 @@ dasd_safe_offline_store(struct device *dev, struct device_attribute *attr,
test_bit(DASD_FLAG_SAFE_OFFLINE_RUNNING, &device->flags)) {
/* Already doing offline processing */
dasd_put_device(device);
+ spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags);
rc = -EBUSY;
goto out;
}
set_bit(DASD_FLAG_SAFE_OFFLINE, &device->flags);
dasd_put_device(device);
+ spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags);
rc = ccw_device_set_offline(cdev);
diff --git a/drivers/s390/block/scm_blk.c b/drivers/s390/block/scm_blk.c
index 152de68..725f912 100644
--- a/drivers/s390/block/scm_blk.c
+++ b/drivers/s390/block/scm_blk.c
@@ -13,6 +13,7 @@
#include <linux/mempool.h>
#include <linux/module.h>
#include <linux/blkdev.h>
+#include <linux/blk-mq.h>
#include <linux/genhd.h>
#include <linux/slab.h>
#include <linux/list.h>
@@ -42,7 +43,6 @@ static void __scm_free_rq(struct scm_request *scmrq)
struct aob_rq_header *aobrq = to_aobrq(scmrq);
free_page((unsigned long) scmrq->aob);
- __scm_free_rq_cluster(scmrq);
kfree(scmrq->request);
kfree(aobrq);
}
@@ -82,9 +82,6 @@ static int __scm_alloc_rq(void)
if (!scmrq->request)
goto free;
- if (__scm_alloc_rq_cluster(scmrq))
- goto free;
-
INIT_LIST_HEAD(&scmrq->list);
spin_lock_irq(&list_lock);
list_add(&scmrq->list, &inactive_requests);
@@ -114,13 +111,13 @@ static struct scm_request *scm_request_fetch(void)
{
struct scm_request *scmrq = NULL;
- spin_lock(&list_lock);
+ spin_lock_irq(&list_lock);
if (list_empty(&inactive_requests))
goto out;
scmrq = list_first_entry(&inactive_requests, struct scm_request, list);
list_del(&scmrq->list);
out:
- spin_unlock(&list_lock);
+ spin_unlock_irq(&list_lock);
return scmrq;
}
@@ -234,130 +231,123 @@ static inline void scm_request_init(struct scm_blk_dev *bdev,
scmrq->error = 0;
/* We don't use all msbs - place aidaws at the end of the aob page. */
scmrq->next_aidaw = (void *) &aob->msb[nr_requests_per_io];
- scm_request_cluster_init(scmrq);
}
-static void scm_ensure_queue_restart(struct scm_blk_dev *bdev)
+static void scm_request_requeue(struct scm_request *scmrq)
{
- if (atomic_read(&bdev->queued_reqs)) {
- /* Queue restart is triggered by the next interrupt. */
- return;
+ struct scm_blk_dev *bdev = scmrq->bdev;
+ int i;
+
+ for (i = 0; i < nr_requests_per_io && scmrq->request[i]; i++)
+ blk_mq_requeue_request(scmrq->request[i], false);
+
+ atomic_dec(&bdev->queued_reqs);
+ scm_request_done(scmrq);
+ blk_mq_kick_requeue_list(bdev->rq);
+}
+
+static void scm_request_finish(struct scm_request *scmrq)
+{
+ struct scm_blk_dev *bdev = scmrq->bdev;
+ int i;
+
+ for (i = 0; i < nr_requests_per_io && scmrq->request[i]; i++) {
+ if (scmrq->error)
+ blk_mq_end_request(scmrq->request[i], scmrq->error);
+ else
+ blk_mq_complete_request(scmrq->request[i]);
}
- blk_delay_queue(bdev->rq, SCM_QUEUE_DELAY);
-}
-
-void scm_request_requeue(struct scm_request *scmrq)
-{
- struct scm_blk_dev *bdev = scmrq->bdev;
- int i;
-
- scm_release_cluster(scmrq);
- for (i = 0; i < nr_requests_per_io && scmrq->request[i]; i++)
- blk_requeue_request(bdev->rq, scmrq->request[i]);
-
- atomic_dec(&bdev->queued_reqs);
- scm_request_done(scmrq);
- scm_ensure_queue_restart(bdev);
-}
-
-void scm_request_finish(struct scm_request *scmrq)
-{
- struct scm_blk_dev *bdev = scmrq->bdev;
- int i;
-
- scm_release_cluster(scmrq);
- for (i = 0; i < nr_requests_per_io && scmrq->request[i]; i++)
- blk_end_request_all(scmrq->request[i], scmrq->error);
atomic_dec(&bdev->queued_reqs);
scm_request_done(scmrq);
}
-static int scm_request_start(struct scm_request *scmrq)
+static void scm_request_start(struct scm_request *scmrq)
{
struct scm_blk_dev *bdev = scmrq->bdev;
- int ret;
atomic_inc(&bdev->queued_reqs);
- if (!scmrq->aob->request.msb_count) {
- scm_request_requeue(scmrq);
- return -EINVAL;
- }
-
- ret = eadm_start_aob(scmrq->aob);
- if (ret) {
+ if (eadm_start_aob(scmrq->aob)) {
SCM_LOG(5, "no subchannel");
scm_request_requeue(scmrq);
}
- return ret;
}
-static void scm_blk_request(struct request_queue *rq)
+struct scm_queue {
+ struct scm_request *scmrq;
+ spinlock_t lock;
+};
+
+static int scm_blk_request(struct blk_mq_hw_ctx *hctx,
+ const struct blk_mq_queue_data *qd)
{
- struct scm_device *scmdev = rq->queuedata;
+ struct scm_device *scmdev = hctx->queue->queuedata;
struct scm_blk_dev *bdev = dev_get_drvdata(&scmdev->dev);
- struct scm_request *scmrq = NULL;
- struct request *req;
+ struct scm_queue *sq = hctx->driver_data;
+ struct request *req = qd->rq;
+ struct scm_request *scmrq;
- while ((req = blk_peek_request(rq))) {
- if (!scm_permit_request(bdev, req))
- goto out;
-
- if (!scmrq) {
- scmrq = scm_request_fetch();
- if (!scmrq) {
- SCM_LOG(5, "no request");
- goto out;
- }
- scm_request_init(bdev, scmrq);
- }
- scm_request_set(scmrq, req);
-
- if (!scm_reserve_cluster(scmrq)) {
- SCM_LOG(5, "cluster busy");
- scm_request_set(scmrq, NULL);
- if (scmrq->aob->request.msb_count)
- goto out;
-
- scm_request_done(scmrq);
- return;
- }
-
- if (scm_need_cluster_request(scmrq)) {
- if (scmrq->aob->request.msb_count) {
- /* Start cluster requests separately. */
- scm_request_set(scmrq, NULL);
- if (scm_request_start(scmrq))
- return;
- } else {
- atomic_inc(&bdev->queued_reqs);
- blk_start_request(req);
- scm_initiate_cluster_request(scmrq);
- }
- scmrq = NULL;
- continue;
- }
-
- if (scm_request_prepare(scmrq)) {
- SCM_LOG(5, "aidaw alloc failed");
- scm_request_set(scmrq, NULL);
- goto out;
- }
- blk_start_request(req);
-
- if (scmrq->aob->request.msb_count < nr_requests_per_io)
- continue;
-
- if (scm_request_start(scmrq))
- return;
-
- scmrq = NULL;
+ spin_lock(&sq->lock);
+ if (!scm_permit_request(bdev, req)) {
+ spin_unlock(&sq->lock);
+ return BLK_MQ_RQ_QUEUE_BUSY;
}
-out:
- if (scmrq)
+
+ scmrq = sq->scmrq;
+ if (!scmrq) {
+ scmrq = scm_request_fetch();
+ if (!scmrq) {
+ SCM_LOG(5, "no request");
+ spin_unlock(&sq->lock);
+ return BLK_MQ_RQ_QUEUE_BUSY;
+ }
+ scm_request_init(bdev, scmrq);
+ sq->scmrq = scmrq;
+ }
+ scm_request_set(scmrq, req);
+
+ if (scm_request_prepare(scmrq)) {
+ SCM_LOG(5, "aidaw alloc failed");
+ scm_request_set(scmrq, NULL);
+
+ if (scmrq->aob->request.msb_count)
+ scm_request_start(scmrq);
+
+ sq->scmrq = NULL;
+ spin_unlock(&sq->lock);
+ return BLK_MQ_RQ_QUEUE_BUSY;
+ }
+ blk_mq_start_request(req);
+
+ if (qd->last || scmrq->aob->request.msb_count == nr_requests_per_io) {
scm_request_start(scmrq);
- else
- scm_ensure_queue_restart(bdev);
+ sq->scmrq = NULL;
+ }
+ spin_unlock(&sq->lock);
+ return BLK_MQ_RQ_QUEUE_OK;
+}
+
+static int scm_blk_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
+ unsigned int idx)
+{
+ struct scm_queue *qd = kzalloc(sizeof(*qd), GFP_KERNEL);
+
+ if (!qd)
+ return -ENOMEM;
+
+ spin_lock_init(&qd->lock);
+ hctx->driver_data = qd;
+
+ return 0;
+}
+
+static void scm_blk_exit_hctx(struct blk_mq_hw_ctx *hctx, unsigned int idx)
+{
+ struct scm_queue *qd = hctx->driver_data;
+
+ WARN_ON(qd->scmrq);
+ kfree(hctx->driver_data);
+ hctx->driver_data = NULL;
}
static void __scmrq_log_error(struct scm_request *scmrq)
@@ -377,21 +367,6 @@ static void __scmrq_log_error(struct scm_request *scmrq)
scmrq->error);
}
-void scm_blk_irq(struct scm_device *scmdev, void *data, int error)
-{
- struct scm_request *scmrq = data;
- struct scm_blk_dev *bdev = scmrq->bdev;
-
- scmrq->error = error;
- if (error)
- __scmrq_log_error(scmrq);
-
- spin_lock(&bdev->lock);
- list_add_tail(&scmrq->list, &bdev->finished_requests);
- spin_unlock(&bdev->lock);
- tasklet_hi_schedule(&bdev->tasklet);
-}
-
static void scm_blk_handle_error(struct scm_request *scmrq)
{
struct scm_blk_dev *bdev = scmrq->bdev;
@@ -419,54 +394,46 @@ static void scm_blk_handle_error(struct scm_request *scmrq)
return;
requeue:
- spin_lock_irqsave(&bdev->rq_lock, flags);
scm_request_requeue(scmrq);
- spin_unlock_irqrestore(&bdev->rq_lock, flags);
}
-static void scm_blk_tasklet(struct scm_blk_dev *bdev)
+void scm_blk_irq(struct scm_device *scmdev, void *data, int error)
{
- struct scm_request *scmrq;
- unsigned long flags;
+ struct scm_request *scmrq = data;
- spin_lock_irqsave(&bdev->lock, flags);
- while (!list_empty(&bdev->finished_requests)) {
- scmrq = list_first_entry(&bdev->finished_requests,
- struct scm_request, list);
- list_del(&scmrq->list);
- spin_unlock_irqrestore(&bdev->lock, flags);
-
- if (scmrq->error && scmrq->retries-- > 0) {
+ scmrq->error = error;
+ if (error) {
+ __scmrq_log_error(scmrq);
+ if (scmrq->retries-- > 0) {
scm_blk_handle_error(scmrq);
-
- /* Request restarted or requeued, handle next. */
- spin_lock_irqsave(&bdev->lock, flags);
- continue;
+ return;
}
-
- if (scm_test_cluster_request(scmrq)) {
- scm_cluster_request_irq(scmrq);
- spin_lock_irqsave(&bdev->lock, flags);
- continue;
- }
-
- scm_request_finish(scmrq);
- spin_lock_irqsave(&bdev->lock, flags);
}
- spin_unlock_irqrestore(&bdev->lock, flags);
- /* Look out for more requests. */
- blk_run_queue(bdev->rq);
+
+ scm_request_finish(scmrq);
+}
+
+static void scm_blk_request_done(struct request *req)
+{
+ blk_mq_end_request(req, 0);
}
static const struct block_device_operations scm_blk_devops = {
.owner = THIS_MODULE,
};
+static const struct blk_mq_ops scm_mq_ops = {
+ .queue_rq = scm_blk_request,
+ .complete = scm_blk_request_done,
+ .init_hctx = scm_blk_init_hctx,
+ .exit_hctx = scm_blk_exit_hctx,
+};
+
int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev)
{
- struct request_queue *rq;
- int len, ret = -ENOMEM;
unsigned int devindex, nr_max_blk;
+ struct request_queue *rq;
+ int len, ret;
devindex = atomic_inc_return(&nr_devices) - 1;
/* scma..scmz + scmaa..scmzz */
@@ -477,18 +444,23 @@ int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev)
bdev->scmdev = scmdev;
bdev->state = SCM_OPER;
- spin_lock_init(&bdev->rq_lock);
spin_lock_init(&bdev->lock);
- INIT_LIST_HEAD(&bdev->finished_requests);
atomic_set(&bdev->queued_reqs, 0);
- tasklet_init(&bdev->tasklet,
- (void (*)(unsigned long)) scm_blk_tasklet,
- (unsigned long) bdev);
- rq = blk_init_queue(scm_blk_request, &bdev->rq_lock);
- if (!rq)
+ bdev->tag_set.ops = &scm_mq_ops;
+ bdev->tag_set.nr_hw_queues = nr_requests;
+ bdev->tag_set.queue_depth = nr_requests_per_io * nr_requests;
+ bdev->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
+
+ ret = blk_mq_alloc_tag_set(&bdev->tag_set);
+ if (ret)
goto out;
+ rq = blk_mq_init_queue(&bdev->tag_set);
+ if (IS_ERR(rq)) {
+ ret = PTR_ERR(rq);
+ goto out_tag;
+ }
bdev->rq = rq;
nr_max_blk = min(scmdev->nr_max_block,
(unsigned int) (PAGE_SIZE / sizeof(struct aidaw)));
@@ -498,12 +470,12 @@ int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev)
blk_queue_max_segments(rq, nr_max_blk);
queue_flag_set_unlocked(QUEUE_FLAG_NONROT, rq);
queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, rq);
- scm_blk_dev_cluster_setup(bdev);
bdev->gendisk = alloc_disk(SCM_NR_PARTS);
- if (!bdev->gendisk)
+ if (!bdev->gendisk) {
+ ret = -ENOMEM;
goto out_queue;
-
+ }
rq->queuedata = scmdev;
bdev->gendisk->private_data = scmdev;
bdev->gendisk->fops = &scm_blk_devops;
@@ -528,6 +500,8 @@ int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev)
out_queue:
blk_cleanup_queue(rq);
+out_tag:
+ blk_mq_free_tag_set(&bdev->tag_set);
out:
atomic_dec(&nr_devices);
return ret;
@@ -535,9 +509,9 @@ int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev)
void scm_blk_dev_cleanup(struct scm_blk_dev *bdev)
{
- tasklet_kill(&bdev->tasklet);
del_gendisk(bdev->gendisk);
blk_cleanup_queue(bdev->gendisk->queue);
+ blk_mq_free_tag_set(&bdev->tag_set);
put_disk(bdev->gendisk);
}
@@ -558,7 +532,7 @@ static bool __init scm_blk_params_valid(void)
if (!nr_requests_per_io || nr_requests_per_io > 64)
return false;
- return scm_cluster_size_valid();
+ return true;
}
static int __init scm_blk_init(void)
diff --git a/drivers/s390/block/scm_blk.h b/drivers/s390/block/scm_blk.h
index 09218cd..242d17a 100644
--- a/drivers/s390/block/scm_blk.h
+++ b/drivers/s390/block/scm_blk.h
@@ -4,6 +4,7 @@
#include <linux/interrupt.h>
#include <linux/spinlock.h>
#include <linux/blkdev.h>
+#include <linux/blk-mq.h>
#include <linux/genhd.h>
#include <linux/list.h>
@@ -14,18 +15,14 @@
#define SCM_QUEUE_DELAY 5
struct scm_blk_dev {
- struct tasklet_struct tasklet;
struct request_queue *rq;
struct gendisk *gendisk;
+ struct blk_mq_tag_set tag_set;
struct scm_device *scmdev;
- spinlock_t rq_lock; /* guard the request queue */
- spinlock_t lock; /* guard the rest of the blockdev */
+ spinlock_t lock;
atomic_t queued_reqs;
enum {SCM_OPER, SCM_WR_PROHIBIT} state;
struct list_head finished_requests;
-#ifdef CONFIG_SCM_BLOCK_CLUSTER_WRITE
- struct list_head cluster_list;
-#endif
};
struct scm_request {
@@ -36,13 +33,6 @@ struct scm_request {
struct list_head list;
u8 retries;
int error;
-#ifdef CONFIG_SCM_BLOCK_CLUSTER_WRITE
- struct {
- enum {CLUSTER_NONE, CLUSTER_READ, CLUSTER_WRITE} state;
- struct list_head list;
- void **buf;
- } cluster;
-#endif
};
#define to_aobrq(rq) container_of((void *) rq, struct aob_rq_header, data)
@@ -52,55 +42,11 @@ void scm_blk_dev_cleanup(struct scm_blk_dev *);
void scm_blk_set_available(struct scm_blk_dev *);
void scm_blk_irq(struct scm_device *, void *, int);
-void scm_request_finish(struct scm_request *);
-void scm_request_requeue(struct scm_request *);
-
struct aidaw *scm_aidaw_fetch(struct scm_request *scmrq, unsigned int bytes);
int scm_drv_init(void);
void scm_drv_cleanup(void);
-#ifdef CONFIG_SCM_BLOCK_CLUSTER_WRITE
-void __scm_free_rq_cluster(struct scm_request *);
-int __scm_alloc_rq_cluster(struct scm_request *);
-void scm_request_cluster_init(struct scm_request *);
-bool scm_reserve_cluster(struct scm_request *);
-void scm_release_cluster(struct scm_request *);
-void scm_blk_dev_cluster_setup(struct scm_blk_dev *);
-bool scm_need_cluster_request(struct scm_request *);
-void scm_initiate_cluster_request(struct scm_request *);
-void scm_cluster_request_irq(struct scm_request *);
-bool scm_test_cluster_request(struct scm_request *);
-bool scm_cluster_size_valid(void);
-#else /* CONFIG_SCM_BLOCK_CLUSTER_WRITE */
-static inline void __scm_free_rq_cluster(struct scm_request *scmrq) {}
-static inline int __scm_alloc_rq_cluster(struct scm_request *scmrq)
-{
- return 0;
-}
-static inline void scm_request_cluster_init(struct scm_request *scmrq) {}
-static inline bool scm_reserve_cluster(struct scm_request *scmrq)
-{
- return true;
-}
-static inline void scm_release_cluster(struct scm_request *scmrq) {}
-static inline void scm_blk_dev_cluster_setup(struct scm_blk_dev *bdev) {}
-static inline bool scm_need_cluster_request(struct scm_request *scmrq)
-{
- return false;
-}
-static inline void scm_initiate_cluster_request(struct scm_request *scmrq) {}
-static inline void scm_cluster_request_irq(struct scm_request *scmrq) {}
-static inline bool scm_test_cluster_request(struct scm_request *scmrq)
-{
- return false;
-}
-static inline bool scm_cluster_size_valid(void)
-{
- return true;
-}
-#endif /* CONFIG_SCM_BLOCK_CLUSTER_WRITE */
-
extern debug_info_t *scm_debug;
#define SCM_LOG(imp, txt) do { \
diff --git a/drivers/s390/block/scm_blk_cluster.c b/drivers/s390/block/scm_blk_cluster.c
deleted file mode 100644
index 7497ddde..0000000
--- a/drivers/s390/block/scm_blk_cluster.c
+++ /dev/null
@@ -1,255 +0,0 @@
-/*
- * Block driver for s390 storage class memory.
- *
- * Copyright IBM Corp. 2012
- * Author(s): Sebastian Ott <sebott@linux.vnet.ibm.com>
- */
-
-#include <linux/spinlock.h>
-#include <linux/module.h>
-#include <linux/blkdev.h>
-#include <linux/genhd.h>
-#include <linux/slab.h>
-#include <linux/list.h>
-#include <asm/eadm.h>
-#include "scm_blk.h"
-
-static unsigned int write_cluster_size = 64;
-module_param(write_cluster_size, uint, S_IRUGO);
-MODULE_PARM_DESC(write_cluster_size,
- "Number of pages used for contiguous writes.");
-
-#define CLUSTER_SIZE (write_cluster_size * PAGE_SIZE)
-
-void __scm_free_rq_cluster(struct scm_request *scmrq)
-{
- int i;
-
- if (!scmrq->cluster.buf)
- return;
-
- for (i = 0; i < 2 * write_cluster_size; i++)
- free_page((unsigned long) scmrq->cluster.buf[i]);
-
- kfree(scmrq->cluster.buf);
-}
-
-int __scm_alloc_rq_cluster(struct scm_request *scmrq)
-{
- int i;
-
- scmrq->cluster.buf = kzalloc(sizeof(void *) * 2 * write_cluster_size,
- GFP_KERNEL);
- if (!scmrq->cluster.buf)
- return -ENOMEM;
-
- for (i = 0; i < 2 * write_cluster_size; i++) {
- scmrq->cluster.buf[i] = (void *) get_zeroed_page(GFP_DMA);
- if (!scmrq->cluster.buf[i])
- return -ENOMEM;
- }
- INIT_LIST_HEAD(&scmrq->cluster.list);
- return 0;
-}
-
-void scm_request_cluster_init(struct scm_request *scmrq)
-{
- scmrq->cluster.state = CLUSTER_NONE;
-}
-
-static bool clusters_intersect(struct request *A, struct request *B)
-{
- unsigned long firstA, lastA, firstB, lastB;
-
- firstA = ((u64) blk_rq_pos(A) << 9) / CLUSTER_SIZE;
- lastA = (((u64) blk_rq_pos(A) << 9) +
- blk_rq_bytes(A) - 1) / CLUSTER_SIZE;
-
- firstB = ((u64) blk_rq_pos(B) << 9) / CLUSTER_SIZE;
- lastB = (((u64) blk_rq_pos(B) << 9) +
- blk_rq_bytes(B) - 1) / CLUSTER_SIZE;
-
- return (firstB <= lastA && firstA <= lastB);
-}
-
-bool scm_reserve_cluster(struct scm_request *scmrq)
-{
- struct request *req = scmrq->request[scmrq->aob->request.msb_count];
- struct scm_blk_dev *bdev = scmrq->bdev;
- struct scm_request *iter;
- int pos, add = 1;
-
- if (write_cluster_size == 0)
- return true;
-
- spin_lock(&bdev->lock);
- list_for_each_entry(iter, &bdev->cluster_list, cluster.list) {
- if (iter == scmrq) {
- /*
- * We don't have to use clusters_intersect here, since
- * cluster requests are always started separately.
- */
- add = 0;
- continue;
- }
- for (pos = 0; pos < iter->aob->request.msb_count; pos++) {
- if (clusters_intersect(req, iter->request[pos]) &&
- (rq_data_dir(req) == WRITE ||
- rq_data_dir(iter->request[pos]) == WRITE)) {
- spin_unlock(&bdev->lock);
- return false;
- }
- }
- }
- if (add)
- list_add(&scmrq->cluster.list, &bdev->cluster_list);
- spin_unlock(&bdev->lock);
-
- return true;
-}
-
-void scm_release_cluster(struct scm_request *scmrq)
-{
- struct scm_blk_dev *bdev = scmrq->bdev;
- unsigned long flags;
-
- if (write_cluster_size == 0)
- return;
-
- spin_lock_irqsave(&bdev->lock, flags);
- list_del(&scmrq->cluster.list);
- spin_unlock_irqrestore(&bdev->lock, flags);
-}
-
-void scm_blk_dev_cluster_setup(struct scm_blk_dev *bdev)
-{
- INIT_LIST_HEAD(&bdev->cluster_list);
- blk_queue_io_opt(bdev->rq, CLUSTER_SIZE);
-}
-
-static int scm_prepare_cluster_request(struct scm_request *scmrq)
-{
- struct scm_blk_dev *bdev = scmrq->bdev;
- struct scm_device *scmdev = bdev->gendisk->private_data;
- struct request *req = scmrq->request[0];
- struct msb *msb = &scmrq->aob->msb[0];
- struct req_iterator iter;
- struct aidaw *aidaw;
- struct bio_vec bv;
- int i = 0;
- u64 addr;
-
- switch (scmrq->cluster.state) {
- case CLUSTER_NONE:
- scmrq->cluster.state = CLUSTER_READ;
- /* fall through */
- case CLUSTER_READ:
- msb->bs = MSB_BS_4K;
- msb->oc = MSB_OC_READ;
- msb->flags = MSB_FLAG_IDA;
- msb->blk_count = write_cluster_size;
-
- addr = scmdev->address + ((u64) blk_rq_pos(req) << 9);
- msb->scm_addr = round_down(addr, CLUSTER_SIZE);
-
- if (msb->scm_addr !=
- round_down(addr + (u64) blk_rq_bytes(req) - 1,
- CLUSTER_SIZE))
- msb->blk_count = 2 * write_cluster_size;
-
- aidaw = scm_aidaw_fetch(scmrq, msb->blk_count * PAGE_SIZE);
- if (!aidaw)
- return -ENOMEM;
-
- scmrq->aob->request.msb_count = 1;
- msb->data_addr = (u64) aidaw;
- for (i = 0; i < msb->blk_count; i++) {
- aidaw->data_addr = (u64) scmrq->cluster.buf[i];
- aidaw++;
- }
-
- break;
- case CLUSTER_WRITE:
- aidaw = (void *) msb->data_addr;
- msb->oc = MSB_OC_WRITE;
-
- for (addr = msb->scm_addr;
- addr < scmdev->address + ((u64) blk_rq_pos(req) << 9);
- addr += PAGE_SIZE) {
- aidaw->data_addr = (u64) scmrq->cluster.buf[i];
- aidaw++;
- i++;
- }
- rq_for_each_segment(bv, req, iter) {
- aidaw->data_addr = (u64) page_address(bv.bv_page);
- aidaw++;
- i++;
- }
- for (; i < msb->blk_count; i++) {
- aidaw->data_addr = (u64) scmrq->cluster.buf[i];
- aidaw++;
- }
- break;
- }
- return 0;
-}
-
-bool scm_need_cluster_request(struct scm_request *scmrq)
-{
- int pos = scmrq->aob->request.msb_count;
-
- if (rq_data_dir(scmrq->request[pos]) == READ)
- return false;
-
- return blk_rq_bytes(scmrq->request[pos]) < CLUSTER_SIZE;
-}
-
-/* Called with queue lock held. */
-void scm_initiate_cluster_request(struct scm_request *scmrq)
-{
- if (scm_prepare_cluster_request(scmrq))
- goto requeue;
- if (eadm_start_aob(scmrq->aob))
- goto requeue;
- return;
-requeue:
- scm_request_requeue(scmrq);
-}
-
-bool scm_test_cluster_request(struct scm_request *scmrq)
-{
- return scmrq->cluster.state != CLUSTER_NONE;
-}
-
-void scm_cluster_request_irq(struct scm_request *scmrq)
-{
- struct scm_blk_dev *bdev = scmrq->bdev;
- unsigned long flags;
-
- switch (scmrq->cluster.state) {
- case CLUSTER_NONE:
- BUG();
- break;
- case CLUSTER_READ:
- if (scmrq->error) {
- scm_request_finish(scmrq);
- break;
- }
- scmrq->cluster.state = CLUSTER_WRITE;
- spin_lock_irqsave(&bdev->rq_lock, flags);
- scm_initiate_cluster_request(scmrq);
- spin_unlock_irqrestore(&bdev->rq_lock, flags);
- break;
- case CLUSTER_WRITE:
- scm_request_finish(scmrq);
- break;
- }
-}
-
-bool scm_cluster_size_valid(void)
-{
- if (write_cluster_size == 1 || write_cluster_size > 128)
- return false;
-
- return !(write_cluster_size & (write_cluster_size - 1));
-}
diff --git a/drivers/s390/cio/ccwgroup.c b/drivers/s390/cio/ccwgroup.c
index e443b0d..34b9ad6 100644
--- a/drivers/s390/cio/ccwgroup.c
+++ b/drivers/s390/cio/ccwgroup.c
@@ -35,7 +35,7 @@ static struct bus_type ccwgroup_bus_type;
static void __ccwgroup_remove_symlinks(struct ccwgroup_device *gdev)
{
int i;
- char str[8];
+ char str[16];
for (i = 0; i < gdev->count; i++) {
sprintf(str, "cdev%d", i);
@@ -238,7 +238,7 @@ static void ccwgroup_release(struct device *dev)
static int __ccwgroup_create_symlinks(struct ccwgroup_device *gdev)
{
- char str[8];
+ char str[16];
int i, rc;
for (i = 0; i < gdev->count; i++) {
diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c
index e2aa944..d3e504c 100644
--- a/drivers/s390/cio/css.c
+++ b/drivers/s390/cio/css.c
@@ -296,6 +296,51 @@ static const struct attribute_group *default_subch_attr_groups[] = {
NULL,
};
+static ssize_t chpids_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct subchannel *sch = to_subchannel(dev);
+ struct chsc_ssd_info *ssd = &sch->ssd_info;
+ ssize_t ret = 0;
+ int mask;
+ int chp;
+
+ for (chp = 0; chp < 8; chp++) {
+ mask = 0x80 >> chp;
+ if (ssd->path_mask & mask)
+ ret += sprintf(buf + ret, "%02x ", ssd->chpid[chp].id);
+ else
+ ret += sprintf(buf + ret, "00 ");
+ }
+ ret += sprintf(buf + ret, "\n");
+ return ret;
+}
+static DEVICE_ATTR(chpids, 0444, chpids_show, NULL);
+
+static ssize_t pimpampom_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct subchannel *sch = to_subchannel(dev);
+ struct pmcw *pmcw = &sch->schib.pmcw;
+
+ return sprintf(buf, "%02x %02x %02x\n",
+ pmcw->pim, pmcw->pam, pmcw->pom);
+}
+static DEVICE_ATTR(pimpampom, 0444, pimpampom_show, NULL);
+
+static struct attribute *io_subchannel_type_attrs[] = {
+ &dev_attr_chpids.attr,
+ &dev_attr_pimpampom.attr,
+ NULL,
+};
+ATTRIBUTE_GROUPS(io_subchannel_type);
+
+static const struct device_type io_subchannel_type = {
+ .groups = io_subchannel_type_groups,
+};
+
int css_register_subchannel(struct subchannel *sch)
{
int ret;
@@ -304,6 +349,10 @@ int css_register_subchannel(struct subchannel *sch)
sch->dev.parent = &channel_subsystems[0]->device;
sch->dev.bus = &css_bus_type;
sch->dev.groups = default_subch_attr_groups;
+
+ if (sch->st == SUBCHANNEL_TYPE_IO)
+ sch->dev.type = &io_subchannel_type;
+
/*
* We don't want to generate uevents for I/O subchannels that don't
* have a working ccw device behind them since they will be
diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c
index b8006ea..7be01a5 100644
--- a/drivers/s390/cio/device.c
+++ b/drivers/s390/cio/device.c
@@ -208,44 +208,6 @@ int __init io_subchannel_init(void)
/************************ device handling **************************/
-/*
- * A ccw_device has some interfaces in sysfs in addition to the
- * standard ones.
- * The following entries are designed to export the information which
- * resided in 2.4 in /proc/subchannels. Subchannel and device number
- * are obvious, so they don't have an entry :)
- * TODO: Split chpids and pimpampom up? Where is "in use" in the tree?
- */
-static ssize_t
-chpids_show (struct device * dev, struct device_attribute *attr, char * buf)
-{
- struct subchannel *sch = to_subchannel(dev);
- struct chsc_ssd_info *ssd = &sch->ssd_info;
- ssize_t ret = 0;
- int chp;
- int mask;
-
- for (chp = 0; chp < 8; chp++) {
- mask = 0x80 >> chp;
- if (ssd->path_mask & mask)
- ret += sprintf(buf + ret, "%02x ", ssd->chpid[chp].id);
- else
- ret += sprintf(buf + ret, "00 ");
- }
- ret += sprintf (buf+ret, "\n");
- return min((ssize_t)PAGE_SIZE, ret);
-}
-
-static ssize_t
-pimpampom_show (struct device * dev, struct device_attribute *attr, char * buf)
-{
- struct subchannel *sch = to_subchannel(dev);
- struct pmcw *pmcw = &sch->schib.pmcw;
-
- return sprintf (buf, "%02x %02x %02x\n",
- pmcw->pim, pmcw->pam, pmcw->pom);
-}
-
static ssize_t
devtype_show (struct device *dev, struct device_attribute *attr, char *buf)
{
@@ -636,8 +598,6 @@ static ssize_t vpm_show(struct device *dev, struct device_attribute *attr,
return sprintf(buf, "%02x\n", sch->vpm);
}
-static DEVICE_ATTR(chpids, 0444, chpids_show, NULL);
-static DEVICE_ATTR(pimpampom, 0444, pimpampom_show, NULL);
static DEVICE_ATTR(devtype, 0444, devtype_show, NULL);
static DEVICE_ATTR(cutype, 0444, cutype_show, NULL);
static DEVICE_ATTR(modalias, 0444, modalias_show, NULL);
@@ -647,8 +607,6 @@ static DEVICE_ATTR(logging, 0200, NULL, initiate_logging);
static DEVICE_ATTR(vpm, 0444, vpm_show, NULL);
static struct attribute *io_subchannel_attrs[] = {
- &dev_attr_chpids.attr,
- &dev_attr_pimpampom.attr,
&dev_attr_logging.attr,
&dev_attr_vpm.attr,
NULL,
diff --git a/drivers/s390/cio/qdio_debug.h b/drivers/s390/cio/qdio_debug.h
index f33ce85..1d595d1 100644
--- a/drivers/s390/cio/qdio_debug.h
+++ b/drivers/s390/cio/qdio_debug.h
@@ -11,7 +11,7 @@
#include "qdio.h"
/* that gives us 15 characters in the text event views */
-#define QDIO_DBF_LEN 16
+#define QDIO_DBF_LEN 32
extern debug_info_t *qdio_dbf_setup;
extern debug_info_t *qdio_dbf_error;
diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
index e90dd43..a25367e 100644
--- a/drivers/s390/cio/vfio_ccw_drv.c
+++ b/drivers/s390/cio/vfio_ccw_drv.c
@@ -90,54 +90,6 @@ static void vfio_ccw_sch_io_todo(struct work_struct *work)
}
/*
- * Sysfs interfaces
- */
-static ssize_t chpids_show(struct device *dev,
- struct device_attribute *attr,
- char *buf)
-{
- struct subchannel *sch = to_subchannel(dev);
- struct chsc_ssd_info *ssd = &sch->ssd_info;
- ssize_t ret = 0;
- int chp;
- int mask;
-
- for (chp = 0; chp < 8; chp++) {
- mask = 0x80 >> chp;
- if (ssd->path_mask & mask)
- ret += sprintf(buf + ret, "%02x ", ssd->chpid[chp].id);
- else
- ret += sprintf(buf + ret, "00 ");
- }
- ret += sprintf(buf+ret, "\n");
- return ret;
-}
-
-static ssize_t pimpampom_show(struct device *dev,
- struct device_attribute *attr,
- char *buf)
-{
- struct subchannel *sch = to_subchannel(dev);
- struct pmcw *pmcw = &sch->schib.pmcw;
-
- return sprintf(buf, "%02x %02x %02x\n",
- pmcw->pim, pmcw->pam, pmcw->pom);
-}
-
-static DEVICE_ATTR(chpids, 0444, chpids_show, NULL);
-static DEVICE_ATTR(pimpampom, 0444, pimpampom_show, NULL);
-
-static struct attribute *vfio_subchannel_attrs[] = {
- &dev_attr_chpids.attr,
- &dev_attr_pimpampom.attr,
- NULL,
-};
-
-static struct attribute_group vfio_subchannel_attr_group = {
- .attrs = vfio_subchannel_attrs,
-};
-
-/*
* Css driver callbacks
*/
static void vfio_ccw_sch_irq(struct subchannel *sch)
@@ -174,13 +126,9 @@ static int vfio_ccw_sch_probe(struct subchannel *sch)
if (ret)
goto out_free;
- ret = sysfs_create_group(&sch->dev.kobj, &vfio_subchannel_attr_group);
- if (ret)
- goto out_disable;
-
ret = vfio_ccw_mdev_reg(sch);
if (ret)
- goto out_rm_group;
+ goto out_disable;
INIT_WORK(&private->io_work, vfio_ccw_sch_io_todo);
atomic_set(&private->avail, 1);
@@ -188,8 +136,6 @@ static int vfio_ccw_sch_probe(struct subchannel *sch)
return 0;
-out_rm_group:
- sysfs_remove_group(&sch->dev.kobj, &vfio_subchannel_attr_group);
out_disable:
cio_disable_subchannel(sch);
out_free:
@@ -206,8 +152,6 @@ static int vfio_ccw_sch_remove(struct subchannel *sch)
vfio_ccw_mdev_unreg(sch);
- sysfs_remove_group(&sch->dev.kobj, &vfio_subchannel_attr_group);
-
dev_set_drvdata(&sch->dev, NULL);
kfree(private);
diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
index e72abbc..a66a317 100644
--- a/drivers/s390/cio/vfio_ccw_ops.c
+++ b/drivers/s390/cio/vfio_ccw_ops.c
@@ -70,14 +70,14 @@ static ssize_t name_show(struct kobject *kobj, struct device *dev, char *buf)
{
return sprintf(buf, "I/O subchannel (Non-QDIO)\n");
}
-MDEV_TYPE_ATTR_RO(name);
+static MDEV_TYPE_ATTR_RO(name);
static ssize_t device_api_show(struct kobject *kobj, struct device *dev,
char *buf)
{
return sprintf(buf, "%s\n", VFIO_DEVICE_API_CCW_STRING);
}
-MDEV_TYPE_ATTR_RO(device_api);
+static MDEV_TYPE_ATTR_RO(device_api);
static ssize_t available_instances_show(struct kobject *kobj,
struct device *dev, char *buf)
@@ -86,7 +86,7 @@ static ssize_t available_instances_show(struct kobject *kobj,
return sprintf(buf, "%d\n", atomic_read(&private->avail));
}
-MDEV_TYPE_ATTR_RO(available_instances);
+static MDEV_TYPE_ATTR_RO(available_instances);
static struct attribute *mdev_types_attrs[] = {
&mdev_type_attr_name.attr,
@@ -100,7 +100,7 @@ static struct attribute_group mdev_type_group = {
.attrs = mdev_types_attrs,
};
-struct attribute_group *mdev_type_groups[] = {
+static struct attribute_group *mdev_type_groups[] = {
&mdev_type_group,
NULL,
};
@@ -152,7 +152,7 @@ static int vfio_ccw_mdev_open(struct mdev_device *mdev)
&events, &private->nb);
}
-void vfio_ccw_mdev_release(struct mdev_device *mdev)
+static void vfio_ccw_mdev_release(struct mdev_device *mdev)
{
struct vfio_ccw_private *private =
dev_get_drvdata(mdev_parent_dev(mdev));
@@ -233,7 +233,7 @@ static int vfio_ccw_mdev_get_region_info(struct vfio_region_info *info,
}
}
-int vfio_ccw_mdev_get_irq_info(struct vfio_irq_info *info)
+static int vfio_ccw_mdev_get_irq_info(struct vfio_irq_info *info)
{
if (info->index != VFIO_CCW_IO_IRQ_INDEX)
return -EINVAL;
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 9be4596..6dee598 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -668,10 +668,28 @@ static int ap_device_probe(struct device *dev)
struct ap_driver *ap_drv = to_ap_drv(dev->driver);
int rc;
+ /* Add queue/card to list of active queues/cards */
+ spin_lock_bh(&ap_list_lock);
+ if (is_card_dev(dev))
+ list_add(&to_ap_card(dev)->list, &ap_card_list);
+ else
+ list_add(&to_ap_queue(dev)->list,
+ &to_ap_queue(dev)->card->queues);
+ spin_unlock_bh(&ap_list_lock);
+
ap_dev->drv = ap_drv;
rc = ap_drv->probe ? ap_drv->probe(ap_dev) : -ENODEV;
- if (rc)
+
+ if (rc) {
+ spin_lock_bh(&ap_list_lock);
+ if (is_card_dev(dev))
+ list_del_init(&to_ap_card(dev)->list);
+ else
+ list_del_init(&to_ap_queue(dev)->list);
+ spin_unlock_bh(&ap_list_lock);
ap_dev->drv = NULL;
+ }
+
return rc;
}
@@ -680,14 +698,17 @@ static int ap_device_remove(struct device *dev)
struct ap_device *ap_dev = to_ap_dev(dev);
struct ap_driver *ap_drv = ap_dev->drv;
+ if (ap_drv->remove)
+ ap_drv->remove(ap_dev);
+
+ /* Remove queue/card from list of active queues/cards */
spin_lock_bh(&ap_list_lock);
if (is_card_dev(dev))
list_del_init(&to_ap_card(dev)->list);
else
list_del_init(&to_ap_queue(dev)->list);
spin_unlock_bh(&ap_list_lock);
- if (ap_drv->remove)
- ap_drv->remove(ap_dev);
+
return 0;
}
@@ -745,7 +766,7 @@ static ssize_t ap_domain_store(struct bus_type *bus,
ap_domain_index = domain;
spin_unlock_bh(&ap_domain_lock);
- AP_DBF(DBF_DEBUG, "store new default domain=%d\n", domain);
+ AP_DBF(DBF_DEBUG, "stored new default domain=%d\n", domain);
return count;
}
@@ -931,6 +952,7 @@ static int ap_select_domain(void)
}
if (best_domain >= 0){
ap_domain_index = best_domain;
+ AP_DBF(DBF_DEBUG, "new ap_domain_index=%d\n", ap_domain_index);
spin_unlock_bh(&ap_domain_lock);
return 0;
}
@@ -967,7 +989,7 @@ static void ap_scan_bus(struct work_struct *unused)
ap_qid_t qid;
int depth = 0, type = 0;
unsigned int functions = 0;
- int rc, id, dom, borked, domains;
+ int rc, id, dom, borked, domains, defdomdevs = 0;
AP_DBF(DBF_DEBUG, "ap_scan_bus running\n");
@@ -1031,6 +1053,8 @@ static void ap_scan_bus(struct work_struct *unused)
put_device(dev);
if (!borked) {
domains++;
+ if (dom == ap_domain_index)
+ defdomdevs++;
continue;
}
}
@@ -1056,10 +1080,6 @@ static void ap_scan_bus(struct work_struct *unused)
}
/* get it and thus adjust reference counter */
get_device(&ac->ap_dev.device);
- /* Add card device to card list */
- spin_lock_bh(&ap_list_lock);
- list_add(&ac->list, &ap_card_list);
- spin_unlock_bh(&ap_list_lock);
}
/* now create the new queue device */
aq = ap_queue_create(qid, type);
@@ -1070,10 +1090,6 @@ static void ap_scan_bus(struct work_struct *unused)
aq->ap_dev.device.parent = &ac->ap_dev.device;
dev_set_name(&aq->ap_dev.device,
"%02x.%04x", id, dom);
- /* Add queue device to card queue list */
- spin_lock_bh(&ap_list_lock);
- list_add(&aq->list, &ac->queues);
- spin_unlock_bh(&ap_list_lock);
/* Start with a device reset */
spin_lock_bh(&aq->lock);
ap_wait(ap_sm_event(aq, AP_EVENT_POLL));
@@ -1081,13 +1097,12 @@ static void ap_scan_bus(struct work_struct *unused)
/* Register device */
rc = device_register(&aq->ap_dev.device);
if (rc) {
- spin_lock_bh(&ap_list_lock);
- list_del_init(&aq->list);
- spin_unlock_bh(&ap_list_lock);
put_device(&aq->ap_dev.device);
continue;
}
domains++;
+ if (dom == ap_domain_index)
+ defdomdevs++;
} /* end domain loop */
if (ac) {
/* remove card dev if there are no queue devices */
@@ -1096,6 +1111,11 @@ static void ap_scan_bus(struct work_struct *unused)
put_device(&ac->ap_dev.device);
}
} /* end device loop */
+
+ if (defdomdevs < 1)
+ AP_DBF(DBF_INFO, "no queue device with default domain %d available\n",
+ ap_domain_index);
+
out:
mod_timer(&ap_config_timer, jiffies + ap_config_time * HZ);
}
@@ -1164,14 +1184,14 @@ int __init ap_module_init(void)
ap_init_configuration();
if (ap_configuration)
- max_domain_id = ap_max_domain_id ? : (AP_DOMAINS - 1);
+ max_domain_id =
+ ap_max_domain_id ? ap_max_domain_id : AP_DOMAINS - 1;
else
max_domain_id = 15;
if (ap_domain_index < -1 || ap_domain_index > max_domain_id) {
pr_warn("%d is not a valid cryptographic domain\n",
ap_domain_index);
- rc = -EINVAL;
- goto out_free;
+ ap_domain_index = -1;
}
/* In resume callback we need to know if the user had set the domain.
* If so, we can not just reset it.
@@ -1244,7 +1264,6 @@ int __init ap_module_init(void)
unregister_reset_call(&ap_reset_call);
if (ap_using_interrupts())
unregister_adapter_interrupt(&ap_airq);
-out_free:
kfree(ap_configuration);
return rc;
}
diff --git a/drivers/s390/crypto/ap_card.c b/drivers/s390/crypto/ap_card.c
index cfa161c..836efac9 100644
--- a/drivers/s390/crypto/ap_card.c
+++ b/drivers/s390/crypto/ap_card.c
@@ -160,7 +160,14 @@ static struct device_type ap_card_type = {
static void ap_card_device_release(struct device *dev)
{
- kfree(to_ap_card(dev));
+ struct ap_card *ac = to_ap_card(dev);
+
+ if (!list_empty(&ac->list)) {
+ spin_lock_bh(&ap_list_lock);
+ list_del_init(&ac->list);
+ spin_unlock_bh(&ap_list_lock);
+ }
+ kfree(ac);
}
struct ap_card *ap_card_create(int id, int queue_depth, int device_type,
diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c
index 480c58a..0f1a5d0 100644
--- a/drivers/s390/crypto/ap_queue.c
+++ b/drivers/s390/crypto/ap_queue.c
@@ -584,7 +584,14 @@ static struct device_type ap_queue_type = {
static void ap_queue_device_release(struct device *dev)
{
- kfree(to_ap_queue(dev));
+ struct ap_queue *aq = to_ap_queue(dev);
+
+ if (!list_empty(&aq->list)) {
+ spin_lock_bh(&ap_list_lock);
+ list_del_init(&aq->list);
+ spin_unlock_bh(&ap_list_lock);
+ }
+ kfree(aq);
}
struct ap_queue *ap_queue_create(ap_qid_t qid, int device_type)
diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c
index ea86da8..f61fa47 100644
--- a/drivers/s390/crypto/pkey_api.c
+++ b/drivers/s390/crypto/pkey_api.c
@@ -178,9 +178,9 @@ static inline void prep_xcrb(struct ica_xcRB *pxcrb,
pxcrb->user_defined = (cardnr == 0xFFFF ? AUTOSELECT : cardnr);
pxcrb->request_control_blk_length =
preqcblk->cprb_len + preqcblk->req_parml;
- pxcrb->request_control_blk_addr = (void *) preqcblk;
+ pxcrb->request_control_blk_addr = (void __user *) preqcblk;
pxcrb->reply_control_blk_length = preqcblk->rpl_msgbl;
- pxcrb->reply_control_blk_addr = (void *) prepcblk;
+ pxcrb->reply_control_blk_addr = (void __user *) prepcblk;
}
/*
@@ -1194,7 +1194,7 @@ static struct miscdevice pkey_dev = {
/*
* Module init
*/
-int __init pkey_init(void)
+static int __init pkey_init(void)
{
cpacf_mask_t pckmo_functions;
diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c
index 93015f8..b1c27e2 100644
--- a/drivers/s390/crypto/zcrypt_api.c
+++ b/drivers/s390/crypto/zcrypt_api.c
@@ -821,8 +821,10 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd,
do {
rc = zcrypt_rsa_modexpo(&mex);
} while (rc == -EAGAIN);
- if (rc)
+ if (rc) {
+ ZCRYPT_DBF(DBF_DEBUG, "ioctl ICARSAMODEXPO rc=%d", rc);
return rc;
+ }
return put_user(mex.outputdatalength, &umex->outputdatalength);
}
case ICARSACRT: {
@@ -838,8 +840,10 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd,
do {
rc = zcrypt_rsa_crt(&crt);
} while (rc == -EAGAIN);
- if (rc)
+ if (rc) {
+ ZCRYPT_DBF(DBF_DEBUG, "ioctl ICARSACRT rc=%d", rc);
return rc;
+ }
return put_user(crt.outputdatalength, &ucrt->outputdatalength);
}
case ZSECSENDCPRB: {
@@ -855,6 +859,8 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd,
do {
rc = zcrypt_send_cprb(&xcRB);
} while (rc == -EAGAIN);
+ if (rc)
+ ZCRYPT_DBF(DBF_DEBUG, "ioctl ZSENDCPRB rc=%d", rc);
if (copy_to_user(uxcRB, &xcRB, sizeof(xcRB)))
return -EFAULT;
return rc;
@@ -872,6 +878,8 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd,
do {
rc = zcrypt_send_ep11_cprb(&xcrb);
} while (rc == -EAGAIN);
+ if (rc)
+ ZCRYPT_DBF(DBF_DEBUG, "ioctl ZSENDEP11CPRB rc=%d", rc);
if (copy_to_user(uxcrb, &xcrb, sizeof(xcrb)))
return -EFAULT;
return rc;
diff --git a/drivers/s390/crypto/zcrypt_cca_key.h b/drivers/s390/crypto/zcrypt_cca_key.h
index ca0cdbe..12cff62 100644
--- a/drivers/s390/crypto/zcrypt_cca_key.h
+++ b/drivers/s390/crypto/zcrypt_cca_key.h
@@ -48,26 +48,6 @@ struct cca_token_hdr {
#define CCA_TKN_HDR_ID_EXT 0x1E
-/**
- * mapping for the cca private ME section
- */
-struct cca_private_ext_ME_sec {
- unsigned char section_identifier;
- unsigned char version;
- unsigned short section_length;
- unsigned char private_key_hash[20];
- unsigned char reserved1[4];
- unsigned char key_format;
- unsigned char reserved2;
- unsigned char key_name_hash[20];
- unsigned char key_use_flags[4];
- unsigned char reserved3[6];
- unsigned char reserved4[24];
- unsigned char confounder[24];
- unsigned char exponent[128];
- unsigned char modulus[128];
-} __attribute__((packed));
-
#define CCA_PVT_USAGE_ALL 0x80
/**
@@ -124,77 +104,6 @@ struct cca_pvt_ext_CRT_sec {
#define CCA_PVT_EXT_CRT_SEC_FMT_CL 0x40
/**
- * Set up private key fields of a type6 MEX message.
- * Note that all numerics in the key token are big-endian,
- * while the entries in the key block header are little-endian.
- *
- * @mex: pointer to user input data
- * @p: pointer to memory area for the key
- *
- * Returns the size of the key area or -EFAULT
- */
-static inline int zcrypt_type6_mex_key_de(struct ica_rsa_modexpo *mex,
- void *p, int big_endian)
-{
- static struct cca_token_hdr static_pvt_me_hdr = {
- .token_identifier = 0x1E,
- .token_length = 0x0183,
- };
- static struct cca_private_ext_ME_sec static_pvt_me_sec = {
- .section_identifier = 0x02,
- .section_length = 0x016C,
- .key_use_flags = {0x80,0x00,0x00,0x00},
- };
- static struct cca_public_sec static_pub_me_sec = {
- .section_identifier = 0x04,
- .section_length = 0x000F,
- .exponent_len = 0x0003,
- };
- static char pk_exponent[3] = { 0x01, 0x00, 0x01 };
- struct {
- struct T6_keyBlock_hdr t6_hdr;
- struct cca_token_hdr pvtMeHdr;
- struct cca_private_ext_ME_sec pvtMeSec;
- struct cca_public_sec pubMeSec;
- char exponent[3];
- } __attribute__((packed)) *key = p;
- unsigned char *temp;
-
- memset(key, 0, sizeof(*key));
-
- if (big_endian) {
- key->t6_hdr.blen = cpu_to_be16(0x189);
- key->t6_hdr.ulen = cpu_to_be16(0x189 - 2);
- } else {
- key->t6_hdr.blen = cpu_to_le16(0x189);
- key->t6_hdr.ulen = cpu_to_le16(0x189 - 2);
- }
- key->pvtMeHdr = static_pvt_me_hdr;
- key->pvtMeSec = static_pvt_me_sec;
- key->pubMeSec = static_pub_me_sec;
- /*
- * In a private key, the modulus doesn't appear in the public
- * section. So, an arbitrary public exponent of 0x010001 will be
- * used.
- */
- memcpy(key->exponent, pk_exponent, 3);
-
- /* key parameter block */
- temp = key->pvtMeSec.exponent +
- sizeof(key->pvtMeSec.exponent) - mex->inputdatalength;
- if (copy_from_user(temp, mex->b_key, mex->inputdatalength))
- return -EFAULT;
-
- /* modulus */
- temp = key->pvtMeSec.modulus +
- sizeof(key->pvtMeSec.modulus) - mex->inputdatalength;
- if (copy_from_user(temp, mex->n_modulus, mex->inputdatalength))
- return -EFAULT;
- key->pubMeSec.modulus_bit_len = 8 * mex->inputdatalength;
- return sizeof(*key);
-}
-
-/**
* Set up private key fields of a type6 MEX message. The _pad variant
* strips leading zeroes from the b_key.
* Note that all numerics in the key token are big-endian,
@@ -205,8 +114,7 @@ static inline int zcrypt_type6_mex_key_de(struct ica_rsa_modexpo *mex,
*
* Returns the size of the key area or -EFAULT
*/
-static inline int zcrypt_type6_mex_key_en(struct ica_rsa_modexpo *mex,
- void *p, int big_endian)
+static inline int zcrypt_type6_mex_key_en(struct ica_rsa_modexpo *mex, void *p)
{
static struct cca_token_hdr static_pub_hdr = {
.token_identifier = 0x1E,
@@ -251,13 +159,8 @@ static inline int zcrypt_type6_mex_key_en(struct ica_rsa_modexpo *mex,
2*mex->inputdatalength - i;
key->pubHdr.token_length =
key->pubSec.section_length + sizeof(key->pubHdr);
- if (big_endian) {
- key->t6_hdr.ulen = cpu_to_be16(key->pubHdr.token_length + 4);
- key->t6_hdr.blen = cpu_to_be16(key->pubHdr.token_length + 6);
- } else {
- key->t6_hdr.ulen = cpu_to_le16(key->pubHdr.token_length + 4);
- key->t6_hdr.blen = cpu_to_le16(key->pubHdr.token_length + 6);
- }
+ key->t6_hdr.ulen = key->pubHdr.token_length + 4;
+ key->t6_hdr.blen = key->pubHdr.token_length + 6;
return sizeof(*key) + 2*mex->inputdatalength - i;
}
@@ -271,8 +174,7 @@ static inline int zcrypt_type6_mex_key_en(struct ica_rsa_modexpo *mex,
*
* Returns the size of the key area or -EFAULT
*/
-static inline int zcrypt_type6_crt_key(struct ica_rsa_modexpo_crt *crt,
- void *p, int big_endian)
+static inline int zcrypt_type6_crt_key(struct ica_rsa_modexpo_crt *crt, void *p)
{
static struct cca_public_sec static_cca_pub_sec = {
.section_identifier = 4,
@@ -298,13 +200,8 @@ static inline int zcrypt_type6_crt_key(struct ica_rsa_modexpo_crt *crt,
size = sizeof(*key) + key_len + sizeof(*pub) + 3;
/* parameter block.key block */
- if (big_endian) {
- key->t6_hdr.blen = cpu_to_be16(size);
- key->t6_hdr.ulen = cpu_to_be16(size - 2);
- } else {
- key->t6_hdr.blen = cpu_to_le16(size);
- key->t6_hdr.ulen = cpu_to_le16(size - 2);
- }
+ key->t6_hdr.blen = size;
+ key->t6_hdr.ulen = size - 2;
/* key token header */
key->token.token_identifier = CCA_TKN_HDR_ID_EXT;
diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c
index e5563ff..4fddb43 100644
--- a/drivers/s390/crypto/zcrypt_msgtype6.c
+++ b/drivers/s390/crypto/zcrypt_msgtype6.c
@@ -291,7 +291,7 @@ static int ICAMEX_msg_to_type6MEX_msgX(struct zcrypt_queue *zq,
return -EFAULT;
/* Set up key which is located after the variable length text. */
- size = zcrypt_type6_mex_key_en(mex, msg->text+mex->inputdatalength, 1);
+ size = zcrypt_type6_mex_key_en(mex, msg->text+mex->inputdatalength);
if (size < 0)
return size;
size += sizeof(*msg) + mex->inputdatalength;
@@ -353,7 +353,7 @@ static int ICACRT_msg_to_type6CRT_msgX(struct zcrypt_queue *zq,
return -EFAULT;
/* Set up key which is located after the variable length text. */
- size = zcrypt_type6_crt_key(crt, msg->text + crt->inputdatalength, 1);
+ size = zcrypt_type6_crt_key(crt, msg->text + crt->inputdatalength);
if (size < 0)
return size;
size += sizeof(*msg) + crt->inputdatalength; /* total size of msg */
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index f6aa211..30bc610 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -701,6 +701,7 @@ enum qeth_discipline_id {
};
struct qeth_discipline {
+ const struct device_type *devtype;
void (*start_poll)(struct ccw_device *, int, unsigned long);
qdio_handler_t *input_handler;
qdio_handler_t *output_handler;
@@ -875,6 +876,9 @@ extern struct qeth_discipline qeth_l2_discipline;
extern struct qeth_discipline qeth_l3_discipline;
extern const struct attribute_group *qeth_generic_attr_groups[];
extern const struct attribute_group *qeth_osn_attr_groups[];
+extern const struct attribute_group qeth_device_attr_group;
+extern const struct attribute_group qeth_device_blkt_group;
+extern const struct device_type qeth_generic_devtype;
extern struct workqueue_struct *qeth_wq;
int qeth_card_hw_is_reachable(struct qeth_card *);
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 38114a8..fc6d85f 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -5530,10 +5530,12 @@ void qeth_core_free_discipline(struct qeth_card *card)
card->discipline = NULL;
}
-static const struct device_type qeth_generic_devtype = {
+const struct device_type qeth_generic_devtype = {
.name = "qeth_generic",
.groups = qeth_generic_attr_groups,
};
+EXPORT_SYMBOL_GPL(qeth_generic_devtype);
+
static const struct device_type qeth_osn_devtype = {
.name = "qeth_osn",
.groups = qeth_osn_attr_groups,
@@ -5659,23 +5661,22 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev)
goto err_card;
}
- if (card->info.type == QETH_CARD_TYPE_OSN)
- gdev->dev.type = &qeth_osn_devtype;
- else
- gdev->dev.type = &qeth_generic_devtype;
-
switch (card->info.type) {
case QETH_CARD_TYPE_OSN:
case QETH_CARD_TYPE_OSM:
rc = qeth_core_load_discipline(card, QETH_DISCIPLINE_LAYER2);
if (rc)
goto err_card;
+
+ gdev->dev.type = (card->info.type != QETH_CARD_TYPE_OSN)
+ ? card->discipline->devtype
+ : &qeth_osn_devtype;
rc = card->discipline->setup(card->gdev);
if (rc)
goto err_disc;
- case QETH_CARD_TYPE_OSD:
- case QETH_CARD_TYPE_OSX:
+ break;
default:
+ gdev->dev.type = &qeth_generic_devtype;
break;
}
@@ -5731,8 +5732,10 @@ static int qeth_core_set_online(struct ccwgroup_device *gdev)
if (rc)
goto err;
rc = card->discipline->setup(card->gdev);
- if (rc)
+ if (rc) {
+ qeth_core_free_discipline(card);
goto err;
+ }
}
rc = card->discipline->set_online(gdev);
err:
diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c
index 75b29fd2..db6a285 100644
--- a/drivers/s390/net/qeth_core_sys.c
+++ b/drivers/s390/net/qeth_core_sys.c
@@ -413,12 +413,16 @@ static ssize_t qeth_dev_layer2_store(struct device *dev,
if (card->options.layer2 == newdis)
goto out;
- else {
- card->info.mac_bits = 0;
- if (card->discipline) {
- card->discipline->remove(card->gdev);
- qeth_core_free_discipline(card);
- }
+ if (card->info.type == QETH_CARD_TYPE_OSM) {
+ /* fixed layer, can't switch */
+ rc = -EOPNOTSUPP;
+ goto out;
+ }
+
+ card->info.mac_bits = 0;
+ if (card->discipline) {
+ card->discipline->remove(card->gdev);
+ qeth_core_free_discipline(card);
}
rc = qeth_core_load_discipline(card, newdis);
@@ -426,6 +430,8 @@ static ssize_t qeth_dev_layer2_store(struct device *dev,
goto out;
rc = card->discipline->setup(card->gdev);
+ if (rc)
+ qeth_core_free_discipline(card);
out:
mutex_unlock(&card->discipline_mutex);
return rc ? rc : count;
@@ -703,10 +709,11 @@ static struct attribute *qeth_blkt_device_attrs[] = {
&dev_attr_inter_jumbo.attr,
NULL,
};
-static struct attribute_group qeth_device_blkt_group = {
+const struct attribute_group qeth_device_blkt_group = {
.name = "blkt",
.attrs = qeth_blkt_device_attrs,
};
+EXPORT_SYMBOL_GPL(qeth_device_blkt_group);
static struct attribute *qeth_device_attrs[] = {
&dev_attr_state.attr,
@@ -726,9 +733,10 @@ static struct attribute *qeth_device_attrs[] = {
&dev_attr_switch_attrs.attr,
NULL,
};
-static struct attribute_group qeth_device_attr_group = {
+const struct attribute_group qeth_device_attr_group = {
.attrs = qeth_device_attrs,
};
+EXPORT_SYMBOL_GPL(qeth_device_attr_group);
const struct attribute_group *qeth_generic_attr_groups[] = {
&qeth_device_attr_group,
diff --git a/drivers/s390/net/qeth_l2.h b/drivers/s390/net/qeth_l2.h
index 29d9fb3..0d59f9a 100644
--- a/drivers/s390/net/qeth_l2.h
+++ b/drivers/s390/net/qeth_l2.h
@@ -8,6 +8,8 @@
#include "qeth_core.h"
+extern const struct attribute_group *qeth_l2_attr_groups[];
+
int qeth_l2_create_device_attributes(struct device *);
void qeth_l2_remove_device_attributes(struct device *);
void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card);
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 1b07f38..bd2df62 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -880,11 +880,21 @@ static int qeth_l2_stop(struct net_device *dev)
return 0;
}
+static const struct device_type qeth_l2_devtype = {
+ .name = "qeth_layer2",
+ .groups = qeth_l2_attr_groups,
+};
+
static int qeth_l2_probe_device(struct ccwgroup_device *gdev)
{
struct qeth_card *card = dev_get_drvdata(&gdev->dev);
+ int rc;
- qeth_l2_create_device_attributes(&gdev->dev);
+ if (gdev->dev.type == &qeth_generic_devtype) {
+ rc = qeth_l2_create_device_attributes(&gdev->dev);
+ if (rc)
+ return rc;
+ }
INIT_LIST_HEAD(&card->vid_list);
hash_init(card->mac_htable);
card->options.layer2 = 1;
@@ -896,7 +906,8 @@ static void qeth_l2_remove_device(struct ccwgroup_device *cgdev)
{
struct qeth_card *card = dev_get_drvdata(&cgdev->dev);
- qeth_l2_remove_device_attributes(&cgdev->dev);
+ if (cgdev->dev.type == &qeth_generic_devtype)
+ qeth_l2_remove_device_attributes(&cgdev->dev);
qeth_set_allowed_threads(card, 0, 1);
wait_event(card->wait_q, qeth_threads_running(card, 0xffffffff) == 0);
@@ -954,7 +965,6 @@ static int qeth_l2_setup_netdev(struct qeth_card *card)
case QETH_CARD_TYPE_OSN:
card->dev = alloc_netdev(0, "osn%d", NET_NAME_UNKNOWN,
ether_setup);
- card->dev->flags |= IFF_NOARP;
break;
default:
card->dev = alloc_etherdev(0);
@@ -969,9 +979,12 @@ static int qeth_l2_setup_netdev(struct qeth_card *card)
card->dev->min_mtu = 64;
card->dev->max_mtu = ETH_MAX_MTU;
card->dev->netdev_ops = &qeth_l2_netdev_ops;
- card->dev->ethtool_ops =
- (card->info.type != QETH_CARD_TYPE_OSN) ?
- &qeth_l2_ethtool_ops : &qeth_l2_osn_ops;
+ if (card->info.type == QETH_CARD_TYPE_OSN) {
+ card->dev->ethtool_ops = &qeth_l2_osn_ops;
+ card->dev->flags |= IFF_NOARP;
+ } else {
+ card->dev->ethtool_ops = &qeth_l2_ethtool_ops;
+ }
card->dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
if (card->info.type == QETH_CARD_TYPE_OSD && !card->info.guestlan) {
card->dev->hw_features = NETIF_F_SG;
@@ -1269,6 +1282,7 @@ static int qeth_l2_control_event(struct qeth_card *card,
}
struct qeth_discipline qeth_l2_discipline = {
+ .devtype = &qeth_l2_devtype,
.start_poll = qeth_qdio_start_poll,
.input_handler = (qdio_handler_t *) qeth_qdio_input_handler,
.output_handler = (qdio_handler_t *) qeth_qdio_output_handler,
diff --git a/drivers/s390/net/qeth_l2_sys.c b/drivers/s390/net/qeth_l2_sys.c
index 6879723..9696baa 100644
--- a/drivers/s390/net/qeth_l2_sys.c
+++ b/drivers/s390/net/qeth_l2_sys.c
@@ -269,3 +269,11 @@ void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card)
} else
qeth_bridgeport_an_set(card, 0);
}
+
+const struct attribute_group *qeth_l2_attr_groups[] = {
+ &qeth_device_attr_group,
+ &qeth_device_blkt_group,
+ /* l2 specific, see l2_{create,remove}_device_attributes(): */
+ &qeth_l2_bridgeport_attr_group,
+ NULL,
+};
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 6e0354e..d8df1e6 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -3039,8 +3039,13 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
static int qeth_l3_probe_device(struct ccwgroup_device *gdev)
{
struct qeth_card *card = dev_get_drvdata(&gdev->dev);
+ int rc;
- qeth_l3_create_device_attributes(&gdev->dev);
+ rc = qeth_l3_create_device_attributes(&gdev->dev);
+ if (rc)
+ return rc;
+ hash_init(card->ip_htable);
+ hash_init(card->ip_mc_htable);
card->options.layer2 = 0;
card->info.hwtrap = 0;
return 0;
@@ -3306,6 +3311,7 @@ static int qeth_l3_control_event(struct qeth_card *card,
}
struct qeth_discipline qeth_l3_discipline = {
+ .devtype = &qeth_generic_devtype,
.start_poll = qeth_qdio_start_poll,
.input_handler = (qdio_handler_t *) qeth_qdio_input_handler,
.output_handler = (qdio_handler_t *) qeth_qdio_output_handler,
diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c
index 2a76ea7..b18fe20 100644
--- a/drivers/s390/virtio/virtio_ccw.c
+++ b/drivers/s390/virtio/virtio_ccw.c
@@ -87,7 +87,7 @@ struct vq_info_block {
} __packed;
struct virtio_feature_desc {
- __u32 features;
+ __le32 features;
__u8 index;
} __packed;
diff --git a/drivers/soc/ti/knav_dma.c b/drivers/soc/ti/knav_dma.c
index ecebe2e..026182d 100644
--- a/drivers/soc/ti/knav_dma.c
+++ b/drivers/soc/ti/knav_dma.c
@@ -413,7 +413,7 @@ static int of_channel_match_helper(struct device_node *np, const char *name,
* @name: slave channel name
* @config: dma configuration parameters
*
- * Returns pointer to appropriate DMA channel on success or NULL.
+ * Returns pointer to appropriate DMA channel on success or error.
*/
void *knav_dma_open_channel(struct device *dev, const char *name,
struct knav_dma_cfg *config)
diff --git a/drivers/tty/hvc/Kconfig b/drivers/tty/hvc/Kconfig
index 574da15..b8d5ea0 100644
--- a/drivers/tty/hvc/Kconfig
+++ b/drivers/tty/hvc/Kconfig
@@ -44,7 +44,7 @@
config HVC_IUCV
bool "z/VM IUCV Hypervisor console support (VM only)"
- depends on S390
+ depends on S390 && NET
select HVC_DRIVER
select IUCV
default y
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 15bac39..b98436f 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -1135,20 +1135,19 @@ cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr,
u32 acllen = 0;
int rc = 0;
struct tcon_link *tlink = cifs_sb_tlink(cifs_sb);
- struct cifs_tcon *tcon;
+ struct smb_version_operations *ops;
cifs_dbg(NOISY, "converting ACL to mode for %s\n", path);
if (IS_ERR(tlink))
return PTR_ERR(tlink);
- tcon = tlink_tcon(tlink);
- if (pfid && (tcon->ses->server->ops->get_acl_by_fid))
- pntsd = tcon->ses->server->ops->get_acl_by_fid(cifs_sb, pfid,
- &acllen);
- else if (tcon->ses->server->ops->get_acl)
- pntsd = tcon->ses->server->ops->get_acl(cifs_sb, inode, path,
- &acllen);
+ ops = tlink_tcon(tlink)->ses->server->ops;
+
+ if (pfid && (ops->get_acl_by_fid))
+ pntsd = ops->get_acl_by_fid(cifs_sb, pfid, &acllen);
+ else if (ops->get_acl)
+ pntsd = ops->get_acl(cifs_sb, inode, path, &acllen);
else {
cifs_put_tlink(tlink);
return -EOPNOTSUPP;
@@ -1181,23 +1180,23 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 nmode,
struct cifs_ntsd *pnntsd = NULL; /* modified acl to be sent to server */
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct tcon_link *tlink = cifs_sb_tlink(cifs_sb);
- struct cifs_tcon *tcon;
+ struct smb_version_operations *ops;
if (IS_ERR(tlink))
return PTR_ERR(tlink);
- tcon = tlink_tcon(tlink);
+
+ ops = tlink_tcon(tlink)->ses->server->ops;
cifs_dbg(NOISY, "set ACL from mode for %s\n", path);
/* Get the security descriptor */
- if (tcon->ses->server->ops->get_acl == NULL) {
+ if (ops->get_acl == NULL) {
cifs_put_tlink(tlink);
return -EOPNOTSUPP;
}
- pntsd = tcon->ses->server->ops->get_acl(cifs_sb, inode, path,
- &secdesclen);
+ pntsd = ops->get_acl(cifs_sb, inode, path, &secdesclen);
if (IS_ERR(pntsd)) {
rc = PTR_ERR(pntsd);
cifs_dbg(VFS, "%s: error %d getting sec desc\n", __func__, rc);
@@ -1224,13 +1223,12 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 nmode,
cifs_dbg(NOISY, "build_sec_desc rc: %d\n", rc);
- if (tcon->ses->server->ops->set_acl == NULL)
+ if (ops->set_acl == NULL)
rc = -EOPNOTSUPP;
if (!rc) {
/* Set the security descriptor */
- rc = tcon->ses->server->ops->set_acl(pnntsd, secdesclen, inode,
- path, aclflag);
+ rc = ops->set_acl(pnntsd, secdesclen, inode, path, aclflag);
cifs_dbg(NOISY, "set_cifs_acl rc: %d\n", rc);
}
cifs_put_tlink(tlink);
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 8be55be..bcc7d9a 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -418,7 +418,7 @@ struct smb_version_operations {
int (*validate_negotiate)(const unsigned int, struct cifs_tcon *);
ssize_t (*query_all_EAs)(const unsigned int, struct cifs_tcon *,
const unsigned char *, const unsigned char *, char *,
- size_t, const struct nls_table *, int);
+ size_t, struct cifs_sb_info *);
int (*set_EA)(const unsigned int, struct cifs_tcon *, const char *,
const char *, const void *, const __u16,
const struct nls_table *, int);
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index e49958c..6eb3147 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -480,8 +480,7 @@ extern int CIFSSMBCopy(unsigned int xid,
extern ssize_t CIFSSMBQAllEAs(const unsigned int xid, struct cifs_tcon *tcon,
const unsigned char *searchName,
const unsigned char *ea_name, char *EAData,
- size_t bufsize, const struct nls_table *nls_codepage,
- int remap_special_chars);
+ size_t bufsize, struct cifs_sb_info *cifs_sb);
extern int CIFSSMBSetEA(const unsigned int xid, struct cifs_tcon *tcon,
const char *fileName, const char *ea_name,
const void *ea_value, const __u16 ea_value_len,
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 4c01b3f..fbb0d4c 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -697,9 +697,7 @@ cifs_echo_callback(struct mid_q_entry *mid)
{
struct TCP_Server_Info *server = mid->callback_data;
- mutex_lock(&server->srv_mutex);
DeleteMidQEntry(mid);
- mutex_unlock(&server->srv_mutex);
add_credits(server, 1, CIFS_ECHO_OP);
}
@@ -1599,9 +1597,7 @@ cifs_readv_callback(struct mid_q_entry *mid)
}
queue_work(cifsiod_wq, &rdata->work);
- mutex_lock(&server->srv_mutex);
DeleteMidQEntry(mid);
- mutex_unlock(&server->srv_mutex);
add_credits(server, 1, 0);
}
@@ -2058,7 +2054,6 @@ cifs_writev_callback(struct mid_q_entry *mid)
{
struct cifs_writedata *wdata = mid->callback_data;
struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink);
- struct TCP_Server_Info *server = tcon->ses->server;
unsigned int written;
WRITE_RSP *smb = (WRITE_RSP *)mid->resp_buf;
@@ -2095,9 +2090,7 @@ cifs_writev_callback(struct mid_q_entry *mid)
}
queue_work(cifsiod_wq, &wdata->work);
- mutex_lock(&server->srv_mutex);
DeleteMidQEntry(mid);
- mutex_unlock(&server->srv_mutex);
add_credits(tcon->ses->server, 1, 0);
}
@@ -6076,11 +6069,13 @@ ssize_t
CIFSSMBQAllEAs(const unsigned int xid, struct cifs_tcon *tcon,
const unsigned char *searchName, const unsigned char *ea_name,
char *EAData, size_t buf_size,
- const struct nls_table *nls_codepage, int remap)
+ struct cifs_sb_info *cifs_sb)
{
/* BB assumes one setup word */
TRANSACTION2_QPI_REQ *pSMB = NULL;
TRANSACTION2_QPI_RSP *pSMBr = NULL;
+ int remap = cifs_remap(cifs_sb);
+ struct nls_table *nls_codepage = cifs_sb->local_nls;
int rc = 0;
int bytes_returned;
int list_len;
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 6ef78ad..0fd081b 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -582,7 +582,7 @@ cifs_relock_file(struct cifsFileInfo *cfile)
struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
int rc = 0;
- down_read(&cinode->lock_sem);
+ down_read_nested(&cinode->lock_sem, SINGLE_DEPTH_NESTING);
if (cinode->can_cache_brlcks) {
/* can cache locks - no need to relock */
up_read(&cinode->lock_sem);
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index c3b2fa0..4d1fcd7 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -563,8 +563,7 @@ static int cifs_sfu_mode(struct cifs_fattr *fattr, const unsigned char *path,
rc = tcon->ses->server->ops->query_all_EAs(xid, tcon, path,
"SETFILEBITS", ea_value, 4 /* size of buf */,
- cifs_sb->local_nls,
- cifs_remap(cifs_sb));
+ cifs_sb);
cifs_put_tlink(tlink);
if (rc < 0)
return (int)rc;
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 48ff770..e4afdaa 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -1240,15 +1240,19 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
goto tcon_exit;
}
- if (rsp->ShareType & SMB2_SHARE_TYPE_DISK)
+ switch (rsp->ShareType) {
+ case SMB2_SHARE_TYPE_DISK:
cifs_dbg(FYI, "connection to disk share\n");
- else if (rsp->ShareType & SMB2_SHARE_TYPE_PIPE) {
+ break;
+ case SMB2_SHARE_TYPE_PIPE:
tcon->ipc = true;
cifs_dbg(FYI, "connection to pipe share\n");
- } else if (rsp->ShareType & SMB2_SHARE_TYPE_PRINT) {
- tcon->print = true;
+ break;
+ case SMB2_SHARE_TYPE_PRINT:
+ tcon->ipc = true;
cifs_dbg(FYI, "connection to printer\n");
- } else {
+ break;
+ default:
cifs_dbg(VFS, "unknown share type %d\n", rsp->ShareType);
rc = -EOPNOTSUPP;
goto tcon_error_exit;
@@ -2173,9 +2177,7 @@ smb2_echo_callback(struct mid_q_entry *mid)
if (mid->mid_state == MID_RESPONSE_RECEIVED)
credits_received = le16_to_cpu(rsp->hdr.sync_hdr.CreditRequest);
- mutex_lock(&server->srv_mutex);
DeleteMidQEntry(mid);
- mutex_unlock(&server->srv_mutex);
add_credits(server, credits_received, CIFS_ECHO_OP);
}
@@ -2433,9 +2435,7 @@ smb2_readv_callback(struct mid_q_entry *mid)
cifs_stats_fail_inc(tcon, SMB2_READ_HE);
queue_work(cifsiod_wq, &rdata->work);
- mutex_lock(&server->srv_mutex);
DeleteMidQEntry(mid);
- mutex_unlock(&server->srv_mutex);
add_credits(server, credits_received, 0);
}
@@ -2594,7 +2594,6 @@ smb2_writev_callback(struct mid_q_entry *mid)
{
struct cifs_writedata *wdata = mid->callback_data;
struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink);
- struct TCP_Server_Info *server = tcon->ses->server;
unsigned int written;
struct smb2_write_rsp *rsp = (struct smb2_write_rsp *)mid->resp_buf;
unsigned int credits_received = 1;
@@ -2634,9 +2633,7 @@ smb2_writev_callback(struct mid_q_entry *mid)
cifs_stats_fail_inc(tcon, SMB2_WRITE_HE);
queue_work(cifsiod_wq, &wdata->work);
- mutex_lock(&server->srv_mutex);
DeleteMidQEntry(mid);
- mutex_unlock(&server->srv_mutex);
add_credits(tcon->ses->server, credits_received, 0);
}
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 4d64b5b..47a125e 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -94,7 +94,7 @@ DeleteMidQEntry(struct mid_q_entry *midEntry)
now = jiffies;
/* commands taking longer than one second are indications that
something is wrong, unless it is quite a slow link or server */
- if ((now - midEntry->when_alloc) > HZ) {
+ if (time_after(now, midEntry->when_alloc + HZ)) {
if ((cifsFYI & CIFS_TIMER) && (midEntry->command != command)) {
pr_debug(" CIFS slow rsp: cmd %d mid %llu",
midEntry->command, midEntry->mid);
@@ -613,9 +613,7 @@ cifs_sync_mid_result(struct mid_q_entry *mid, struct TCP_Server_Info *server)
}
spin_unlock(&GlobalMid_Lock);
- mutex_lock(&server->srv_mutex);
DeleteMidQEntry(mid);
- mutex_unlock(&server->srv_mutex);
return rc;
}
diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c
index 20af518..3cb5c9e 100644
--- a/fs/cifs/xattr.c
+++ b/fs/cifs/xattr.c
@@ -235,8 +235,7 @@ static int cifs_xattr_get(const struct xattr_handler *handler,
if (pTcon->ses->server->ops->query_all_EAs)
rc = pTcon->ses->server->ops->query_all_EAs(xid, pTcon,
- full_path, name, value, size,
- cifs_sb->local_nls, cifs_remap(cifs_sb));
+ full_path, name, value, size, cifs_sb);
break;
case XATTR_CIFS_ACL: {
@@ -336,8 +335,7 @@ ssize_t cifs_listxattr(struct dentry *direntry, char *data, size_t buf_size)
if (pTcon->ses->server->ops->query_all_EAs)
rc = pTcon->ses->server->ops->query_all_EAs(xid, pTcon,
- full_path, NULL, data, buf_size,
- cifs_sb->local_nls, cifs_remap(cifs_sb));
+ full_path, NULL, data, buf_size, cifs_sb);
list_ea_exit:
kfree(full_path);
free_xid(xid);
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 5efb4db..d5093b5 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -40,6 +40,9 @@ struct bpf_reg_state {
*/
s64 min_value;
u64 max_value;
+ u32 min_align;
+ u32 aux_off;
+ u32 aux_off_align;
};
enum bpf_stack_slot_type {
@@ -87,6 +90,7 @@ struct bpf_verifier_env {
struct bpf_prog *prog; /* eBPF program being verified */
struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */
int stack_size; /* number of states to be processed */
+ bool strict_alignment; /* perform strict pointer alignment checks */
struct bpf_verifier_state cur_state; /* current verifier state */
struct bpf_verifier_state_list **explored_states; /* search pruning optimization */
const struct bpf_ext_analyzer_ops *analyzer_ops; /* external analyzer ops */
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 1b166d2..b25e7ba 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -109,7 +109,6 @@ struct mlx5_flow_table_attr {
int max_fte;
u32 level;
u32 flags;
- u32 underlay_qpn;
};
struct mlx5_flow_table *
@@ -167,4 +166,7 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging);
void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter);
void mlx5_fc_query_cached(struct mlx5_fc *counter,
u64 *bytes, u64 *packets, u64 *lastuse);
+int mlx5_fs_add_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn);
+int mlx5_fs_remove_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn);
+
#endif
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 9c23bd2..3f39d27 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3296,11 +3296,15 @@ int dev_get_phys_port_id(struct net_device *dev,
int dev_get_phys_port_name(struct net_device *dev,
char *name, size_t len);
int dev_change_proto_down(struct net_device *dev, bool proto_down);
-int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
- int fd, u32 flags);
struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev);
struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
struct netdev_queue *txq, int *ret);
+
+typedef int (*xdp_op_t)(struct net_device *dev, struct netdev_xdp *xdp);
+int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
+ int fd, u32 flags);
+bool __dev_xdp_attached(struct net_device *dev, xdp_op_t xdp_op);
+
int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
bool is_skb_forwardable(const struct net_device *dev,
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 945a1f5..94dfa9d 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -132,6 +132,13 @@ enum bpf_attach_type {
*/
#define BPF_F_ALLOW_OVERRIDE (1U << 0)
+/* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the
+ * verifier will perform strict alignment checking as if the kernel
+ * has been built with CONFIG_EFFICIENT_UNALIGNED_ACCESS not set,
+ * and NET_IP_ALIGN defined to 2.
+ */
+#define BPF_F_STRICT_ALIGNMENT (1U << 0)
+
#define BPF_PSEUDO_MAP_FD 1
/* flags for BPF_MAP_UPDATE_ELEM command */
@@ -177,6 +184,7 @@ union bpf_attr {
__u32 log_size; /* size of user buffer */
__aligned_u64 log_buf; /* user supplied buffer */
__u32 kern_version; /* checked when prog_type=kprobe */
+ __u32 prog_flags;
};
struct { /* anonymous struct used by BPF_OBJ_* commands */
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 8e56ac7..15ac203 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -888,9 +888,18 @@ enum {
/* XDP section */
#define XDP_FLAGS_UPDATE_IF_NOEXIST (1U << 0)
-#define XDP_FLAGS_SKB_MODE (2U << 0)
+#define XDP_FLAGS_SKB_MODE (1U << 1)
+#define XDP_FLAGS_DRV_MODE (1U << 2)
#define XDP_FLAGS_MASK (XDP_FLAGS_UPDATE_IF_NOEXIST | \
- XDP_FLAGS_SKB_MODE)
+ XDP_FLAGS_SKB_MODE | \
+ XDP_FLAGS_DRV_MODE)
+
+/* These are stored into IFLA_XDP_ATTACHED on dump. */
+enum {
+ XDP_ATTACHED_NONE = 0,
+ XDP_ATTACHED_DRV,
+ XDP_ATTACHED_SKB,
+};
enum {
IFLA_XDP_UNSPEC,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index fd2411f..265a0d8 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -783,7 +783,7 @@ struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type)
EXPORT_SYMBOL_GPL(bpf_prog_get_type);
/* last field in 'union bpf_attr' used by this command */
-#define BPF_PROG_LOAD_LAST_FIELD kern_version
+#define BPF_PROG_LOAD_LAST_FIELD prog_flags
static int bpf_prog_load(union bpf_attr *attr)
{
@@ -796,6 +796,9 @@ static int bpf_prog_load(union bpf_attr *attr)
if (CHECK_ATTR(BPF_PROG_LOAD))
return -EINVAL;
+ if (attr->prog_flags & ~BPF_F_STRICT_ALIGNMENT)
+ return -EINVAL;
+
/* copy eBPF program license from user space */
if (strncpy_from_user(license, u64_to_user_ptr(attr->license),
sizeof(license) - 1) < 0)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c5b56c9..39f2dcb 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -241,6 +241,12 @@ static void print_verifier_state(struct bpf_verifier_state *state)
if (reg->max_value != BPF_REGISTER_MAX_RANGE)
verbose(",max_value=%llu",
(unsigned long long)reg->max_value);
+ if (reg->min_align)
+ verbose(",min_align=%u", reg->min_align);
+ if (reg->aux_off)
+ verbose(",aux_off=%u", reg->aux_off);
+ if (reg->aux_off_align)
+ verbose(",aux_off_align=%u", reg->aux_off_align);
}
for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
if (state->stack_slot_type[i] == STACK_SPILL)
@@ -466,6 +472,9 @@ static void init_reg_state(struct bpf_reg_state *regs)
regs[i].imm = 0;
regs[i].min_value = BPF_REGISTER_MIN_RANGE;
regs[i].max_value = BPF_REGISTER_MAX_RANGE;
+ regs[i].min_align = 0;
+ regs[i].aux_off = 0;
+ regs[i].aux_off_align = 0;
}
/* frame pointer */
@@ -492,6 +501,7 @@ static void reset_reg_range_values(struct bpf_reg_state *regs, u32 regno)
{
regs[regno].min_value = BPF_REGISTER_MIN_RANGE;
regs[regno].max_value = BPF_REGISTER_MAX_RANGE;
+ regs[regno].min_align = 0;
}
static void mark_reg_unknown_value_and_range(struct bpf_reg_state *regs,
@@ -779,17 +789,33 @@ static bool is_pointer_value(struct bpf_verifier_env *env, int regno)
}
static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg,
- int off, int size)
+ int off, int size, bool strict)
{
- if (reg->id && size != 1) {
- verbose("Unknown alignment. Only byte-sized access allowed in packet access.\n");
- return -EACCES;
+ int ip_align;
+ int reg_off;
+
+ /* Byte size accesses are always allowed. */
+ if (!strict || size == 1)
+ return 0;
+
+ reg_off = reg->off;
+ if (reg->id) {
+ if (reg->aux_off_align % size) {
+ verbose("Packet access is only %u byte aligned, %d byte access not allowed\n",
+ reg->aux_off_align, size);
+ return -EACCES;
+ }
+ reg_off += reg->aux_off;
}
- /* skb->data is NET_IP_ALIGN-ed */
- if ((NET_IP_ALIGN + reg->off + off) % size != 0) {
+ /* skb->data is NET_IP_ALIGN-ed, but for strict alignment checking
+ * we force this to 2 which is universally what architectures use
+ * when they don't set CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS.
+ */
+ ip_align = strict ? 2 : NET_IP_ALIGN;
+ if ((ip_align + reg_off + off) % size != 0) {
verbose("misaligned packet access off %d+%d+%d size %d\n",
- NET_IP_ALIGN, reg->off, off, size);
+ ip_align, reg_off, off, size);
return -EACCES;
}
@@ -797,9 +823,9 @@ static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg,
}
static int check_val_ptr_alignment(const struct bpf_reg_state *reg,
- int size)
+ int size, bool strict)
{
- if (size != 1) {
+ if (strict && size != 1) {
verbose("Unknown alignment. Only byte-sized access allowed in value access.\n");
return -EACCES;
}
@@ -807,16 +833,20 @@ static int check_val_ptr_alignment(const struct bpf_reg_state *reg,
return 0;
}
-static int check_ptr_alignment(const struct bpf_reg_state *reg,
+static int check_ptr_alignment(struct bpf_verifier_env *env,
+ const struct bpf_reg_state *reg,
int off, int size)
{
+ bool strict = env->strict_alignment;
+
+ if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
+ strict = true;
+
switch (reg->type) {
case PTR_TO_PACKET:
- return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ? 0 :
- check_pkt_ptr_alignment(reg, off, size);
+ return check_pkt_ptr_alignment(reg, off, size, strict);
case PTR_TO_MAP_VALUE_ADJ:
- return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ? 0 :
- check_val_ptr_alignment(reg, size);
+ return check_val_ptr_alignment(reg, size, strict);
default:
if (off % size != 0) {
verbose("misaligned access off %d size %d\n",
@@ -849,7 +879,7 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off,
if (size < 0)
return size;
- err = check_ptr_alignment(reg, off, size);
+ err = check_ptr_alignment(env, reg, off, size);
if (err)
return err;
@@ -883,6 +913,8 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off,
value_regno);
/* note that reg.[id|off|range] == 0 */
state->regs[value_regno].type = reg_type;
+ state->regs[value_regno].aux_off = 0;
+ state->regs[value_regno].aux_off_align = 0;
}
} else if (reg->type == FRAME_PTR || reg->type == PTR_TO_STACK) {
@@ -1455,6 +1487,8 @@ static int check_packet_ptr_add(struct bpf_verifier_env *env,
*/
dst_reg->off += imm;
} else {
+ bool had_id;
+
if (src_reg->type == PTR_TO_PACKET) {
/* R6=pkt(id=0,off=0,r=62) R7=imm22; r7 += r6 */
tmp_reg = *dst_reg; /* save r7 state */
@@ -1488,14 +1522,23 @@ static int check_packet_ptr_add(struct bpf_verifier_env *env,
src_reg->imm);
return -EACCES;
}
+
+ had_id = (dst_reg->id != 0);
+
/* dst_reg stays as pkt_ptr type and since some positive
* integer value was added to the pointer, increment its 'id'
*/
dst_reg->id = ++env->id_gen;
- /* something was added to pkt_ptr, set range and off to zero */
+ /* something was added to pkt_ptr, set range to zero */
+ dst_reg->aux_off += dst_reg->off;
dst_reg->off = 0;
dst_reg->range = 0;
+ if (had_id)
+ dst_reg->aux_off_align = min(dst_reg->aux_off_align,
+ src_reg->min_align);
+ else
+ dst_reg->aux_off_align = src_reg->min_align;
}
return 0;
}
@@ -1669,6 +1712,13 @@ static void check_reg_overflow(struct bpf_reg_state *reg)
reg->min_value = BPF_REGISTER_MIN_RANGE;
}
+static u32 calc_align(u32 imm)
+{
+ if (!imm)
+ return 1U << 31;
+ return imm - ((imm - 1) & imm);
+}
+
static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
struct bpf_insn *insn)
{
@@ -1676,8 +1726,10 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
s64 min_val = BPF_REGISTER_MIN_RANGE;
u64 max_val = BPF_REGISTER_MAX_RANGE;
u8 opcode = BPF_OP(insn->code);
+ u32 dst_align, src_align;
dst_reg = ®s[insn->dst_reg];
+ src_align = 0;
if (BPF_SRC(insn->code) == BPF_X) {
check_reg_overflow(®s[insn->src_reg]);
min_val = regs[insn->src_reg].min_value;
@@ -1693,12 +1745,18 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
regs[insn->src_reg].type != UNKNOWN_VALUE) {
min_val = BPF_REGISTER_MIN_RANGE;
max_val = BPF_REGISTER_MAX_RANGE;
+ src_align = 0;
+ } else {
+ src_align = regs[insn->src_reg].min_align;
}
} else if (insn->imm < BPF_REGISTER_MAX_RANGE &&
(s64)insn->imm > BPF_REGISTER_MIN_RANGE) {
min_val = max_val = insn->imm;
+ src_align = calc_align(insn->imm);
}
+ dst_align = dst_reg->min_align;
+
/* We don't know anything about what was done to this register, mark it
* as unknown.
*/
@@ -1723,18 +1781,21 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
dst_reg->min_value += min_val;
if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
dst_reg->max_value += max_val;
+ dst_reg->min_align = min(src_align, dst_align);
break;
case BPF_SUB:
if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
dst_reg->min_value -= min_val;
if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
dst_reg->max_value -= max_val;
+ dst_reg->min_align = min(src_align, dst_align);
break;
case BPF_MUL:
if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
dst_reg->min_value *= min_val;
if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
dst_reg->max_value *= max_val;
+ dst_reg->min_align = max(src_align, dst_align);
break;
case BPF_AND:
/* Disallow AND'ing of negative numbers, ain't nobody got time
@@ -1746,17 +1807,23 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
else
dst_reg->min_value = 0;
dst_reg->max_value = max_val;
+ dst_reg->min_align = max(src_align, dst_align);
break;
case BPF_LSH:
/* Gotta have special overflow logic here, if we're shifting
* more than MAX_RANGE then just assume we have an invalid
* range.
*/
- if (min_val > ilog2(BPF_REGISTER_MAX_RANGE))
+ if (min_val > ilog2(BPF_REGISTER_MAX_RANGE)) {
dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
- else if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
- dst_reg->min_value <<= min_val;
-
+ dst_reg->min_align = 1;
+ } else {
+ if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
+ dst_reg->min_value <<= min_val;
+ if (!dst_reg->min_align)
+ dst_reg->min_align = 1;
+ dst_reg->min_align <<= min_val;
+ }
if (max_val > ilog2(BPF_REGISTER_MAX_RANGE))
dst_reg->max_value = BPF_REGISTER_MAX_RANGE;
else if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
@@ -1766,11 +1833,19 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
/* RSH by a negative number is undefined, and the BPF_RSH is an
* unsigned shift, so make the appropriate casts.
*/
- if (min_val < 0 || dst_reg->min_value < 0)
+ if (min_val < 0 || dst_reg->min_value < 0) {
dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
- else
+ } else {
dst_reg->min_value =
(u64)(dst_reg->min_value) >> min_val;
+ }
+ if (min_val < 0) {
+ dst_reg->min_align = 1;
+ } else {
+ dst_reg->min_align >>= (u64) min_val;
+ if (!dst_reg->min_align)
+ dst_reg->min_align = 1;
+ }
if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
dst_reg->max_value >>= max_val;
break;
@@ -1872,6 +1947,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
regs[insn->dst_reg].imm = insn->imm;
regs[insn->dst_reg].max_value = insn->imm;
regs[insn->dst_reg].min_value = insn->imm;
+ regs[insn->dst_reg].min_align = calc_align(insn->imm);
}
} else if (opcode > BPF_END) {
@@ -2856,8 +2932,12 @@ static int do_check(struct bpf_verifier_env *env)
goto process_bpf_exit;
}
- if (log_level && do_print_state) {
- verbose("\nfrom %d to %d:", prev_insn_idx, insn_idx);
+ if (log_level > 1 || (log_level && do_print_state)) {
+ if (log_level > 1)
+ verbose("%d:", insn_idx);
+ else
+ verbose("\nfrom %d to %d:",
+ prev_insn_idx, insn_idx);
print_verifier_state(&env->cur_state);
do_print_state = false;
}
@@ -3494,6 +3574,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
} else {
log_level = 0;
}
+ if (attr->prog_flags & BPF_F_STRICT_ALIGNMENT)
+ env->strict_alignment = true;
+ else
+ env->strict_alignment = false;
ret = replace_map_fd_with_map_ptr(env);
if (ret < 0)
@@ -3599,6 +3683,7 @@ int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops,
mutex_lock(&bpf_verifier_lock);
log_level = 0;
+ env->strict_alignment = false;
env->explored_states = kcalloc(env->prog->len,
sizeof(struct bpf_verifier_state_list *),
diff --git a/net/core/dev.c b/net/core/dev.c
index 96cf83d..fca407b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6852,6 +6852,32 @@ int dev_change_proto_down(struct net_device *dev, bool proto_down)
}
EXPORT_SYMBOL(dev_change_proto_down);
+bool __dev_xdp_attached(struct net_device *dev, xdp_op_t xdp_op)
+{
+ struct netdev_xdp xdp;
+
+ memset(&xdp, 0, sizeof(xdp));
+ xdp.command = XDP_QUERY_PROG;
+
+ /* Query must always succeed. */
+ WARN_ON(xdp_op(dev, &xdp) < 0);
+ return xdp.prog_attached;
+}
+
+static int dev_xdp_install(struct net_device *dev, xdp_op_t xdp_op,
+ struct netlink_ext_ack *extack,
+ struct bpf_prog *prog)
+{
+ struct netdev_xdp xdp;
+
+ memset(&xdp, 0, sizeof(xdp));
+ xdp.command = XDP_SETUP_PROG;
+ xdp.extack = extack;
+ xdp.prog = prog;
+
+ return xdp_op(dev, &xdp);
+}
+
/**
* dev_change_xdp_fd - set or clear a bpf program for a device rx path
* @dev: device
@@ -6864,41 +6890,34 @@ EXPORT_SYMBOL(dev_change_proto_down);
int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
int fd, u32 flags)
{
- int (*xdp_op)(struct net_device *dev, struct netdev_xdp *xdp);
const struct net_device_ops *ops = dev->netdev_ops;
struct bpf_prog *prog = NULL;
- struct netdev_xdp xdp;
+ xdp_op_t xdp_op, xdp_chk;
int err;
ASSERT_RTNL();
- xdp_op = ops->ndo_xdp;
+ xdp_op = xdp_chk = ops->ndo_xdp;
+ if (!xdp_op && (flags & XDP_FLAGS_DRV_MODE))
+ return -EOPNOTSUPP;
if (!xdp_op || (flags & XDP_FLAGS_SKB_MODE))
xdp_op = generic_xdp_install;
+ if (xdp_op == xdp_chk)
+ xdp_chk = generic_xdp_install;
if (fd >= 0) {
- if (flags & XDP_FLAGS_UPDATE_IF_NOEXIST) {
- memset(&xdp, 0, sizeof(xdp));
- xdp.command = XDP_QUERY_PROG;
-
- err = xdp_op(dev, &xdp);
- if (err < 0)
- return err;
- if (xdp.prog_attached)
- return -EBUSY;
- }
+ if (xdp_chk && __dev_xdp_attached(dev, xdp_chk))
+ return -EEXIST;
+ if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) &&
+ __dev_xdp_attached(dev, xdp_op))
+ return -EBUSY;
prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_XDP);
if (IS_ERR(prog))
return PTR_ERR(prog);
}
- memset(&xdp, 0, sizeof(xdp));
- xdp.command = XDP_SETUP_PROG;
- xdp.extack = extack;
- xdp.prog = prog;
-
- err = xdp_op(dev, &xdp);
+ err = dev_xdp_install(dev, xdp_op, extack, prog);
if (err < 0 && prog)
bpf_prog_put(prog);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index bcb0f610..d7f82c3 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -899,8 +899,7 @@ static size_t rtnl_port_size(const struct net_device *dev,
static size_t rtnl_xdp_size(void)
{
size_t xdp_size = nla_total_size(0) + /* nest IFLA_XDP */
- nla_total_size(1) + /* XDP_ATTACHED */
- nla_total_size(4); /* XDP_FLAGS */
+ nla_total_size(1); /* XDP_ATTACHED */
return xdp_size;
}
@@ -1247,37 +1246,34 @@ static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev)
return 0;
}
+static u8 rtnl_xdp_attached_mode(struct net_device *dev)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+
+ ASSERT_RTNL();
+
+ if (rcu_access_pointer(dev->xdp_prog))
+ return XDP_ATTACHED_SKB;
+ if (ops->ndo_xdp && __dev_xdp_attached(dev, ops->ndo_xdp))
+ return XDP_ATTACHED_DRV;
+
+ return XDP_ATTACHED_NONE;
+}
+
static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev)
{
struct nlattr *xdp;
- u32 xdp_flags = 0;
- u8 val = 0;
int err;
xdp = nla_nest_start(skb, IFLA_XDP);
if (!xdp)
return -EMSGSIZE;
- if (rcu_access_pointer(dev->xdp_prog)) {
- xdp_flags = XDP_FLAGS_SKB_MODE;
- val = 1;
- } else if (dev->netdev_ops->ndo_xdp) {
- struct netdev_xdp xdp_op = {};
- xdp_op.command = XDP_QUERY_PROG;
- err = dev->netdev_ops->ndo_xdp(dev, &xdp_op);
- if (err)
- goto err_cancel;
- val = xdp_op.prog_attached;
- }
- err = nla_put_u8(skb, IFLA_XDP_ATTACHED, val);
+ err = nla_put_u8(skb, IFLA_XDP_ATTACHED,
+ rtnl_xdp_attached_mode(dev));
if (err)
goto err_cancel;
- if (xdp_flags) {
- err = nla_put_u32(skb, IFLA_XDP_FLAGS, xdp_flags);
- if (err)
- goto err_cancel;
- }
nla_nest_end(skb, xdp);
return 0;
@@ -2199,6 +2195,11 @@ static int do_setlink(const struct sk_buff *skb,
err = -EINVAL;
goto errout;
}
+ if ((xdp_flags & XDP_FLAGS_SKB_MODE) &&
+ (xdp_flags & XDP_FLAGS_DRV_MODE)) {
+ err = -EINVAL;
+ goto errout;
+ }
}
if (xdp[IFLA_XDP_FD]) {
diff --git a/net/core/sock.c b/net/core/sock.c
index 79c6aee..e43e71d 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1803,28 +1803,24 @@ EXPORT_SYMBOL(skb_set_owner_w);
* delay queue. We want to allow the owner socket to send more
* packets, as if they were already TX completed by a typical driver.
* But we also want to keep skb->sk set because some packet schedulers
- * rely on it (sch_fq for example). So we set skb->truesize to a small
- * amount (1) and decrease sk_wmem_alloc accordingly.
+ * rely on it (sch_fq for example).
*/
void skb_orphan_partial(struct sk_buff *skb)
{
- /* If this skb is a TCP pure ACK or already went here,
- * we have nothing to do. 2 is already a very small truesize.
- */
- if (skb->truesize <= 2)
+ if (skb_is_tcp_pure_ack(skb))
return;
- /* TCP stack sets skb->ooo_okay based on sk_wmem_alloc,
- * so we do not completely orphan skb, but transfert all
- * accounted bytes but one, to avoid unexpected reorders.
- */
if (skb->destructor == sock_wfree
#ifdef CONFIG_INET
|| skb->destructor == tcp_wfree
#endif
) {
- atomic_sub(skb->truesize - 1, &skb->sk->sk_wmem_alloc);
- skb->truesize = 1;
+ struct sock *sk = skb->sk;
+
+ if (atomic_inc_not_zero(&sk->sk_refcnt)) {
+ atomic_sub(skb->truesize, &sk->sk_wmem_alloc);
+ skb->destructor = sock_efree;
+ }
} else {
skb_orphan(skb);
}
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 840f14a..9926211 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -426,6 +426,9 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
newsk->sk_backlog_rcv = dccp_v4_do_rcv;
newnp->pktoptions = NULL;
newnp->opt = NULL;
+ newnp->ipv6_mc_list = NULL;
+ newnp->ipv6_ac_list = NULL;
+ newnp->ipv6_fl_list = NULL;
newnp->mcast_oif = inet6_iif(skb);
newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;
@@ -490,6 +493,9 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
/* Clone RX bits */
newnp->rxopt.all = np->rxopt.all;
+ newnp->ipv6_mc_list = NULL;
+ newnp->ipv6_ac_list = NULL;
+ newnp->ipv6_fl_list = NULL;
newnp->pktoptions = NULL;
newnp->opt = NULL;
newnp->mcast_oif = inet6_iif(skb);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 5a3ad09..06e2dbc 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1179,13 +1179,14 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb,
*/
if (pkt_len > mss) {
unsigned int new_len = (pkt_len / mss) * mss;
- if (!in_sack && new_len < pkt_len) {
+ if (!in_sack && new_len < pkt_len)
new_len += mss;
- if (new_len >= skb->len)
- return 0;
- }
pkt_len = new_len;
}
+
+ if (pkt_len >= skb->len && !in_sack)
+ return 0;
+
err = tcp_fragment(sk, skb, pkt_len, mss, GFP_ATOMIC);
if (err < 0)
return err;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 8d297a7..6a4fb1e 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1022,7 +1022,10 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
INIT_HLIST_NODE(&ifa->addr_lst);
ifa->scope = scope;
ifa->prefix_len = pfxlen;
- ifa->flags = flags | IFA_F_TENTATIVE;
+ ifa->flags = flags;
+ /* No need to add the TENTATIVE flag for addresses with NODAD */
+ if (!(flags & IFA_F_NODAD))
+ ifa->flags |= IFA_F_TENTATIVE;
ifa->valid_lft = valid_lft;
ifa->prefered_lft = prefered_lft;
ifa->cstamp = ifa->tstamp = jiffies;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 7a8237a..4f4310a 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1062,6 +1062,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
newtp->af_specific = &tcp_sock_ipv6_mapped_specific;
#endif
+ newnp->ipv6_mc_list = NULL;
newnp->ipv6_ac_list = NULL;
newnp->ipv6_fl_list = NULL;
newnp->pktoptions = NULL;
@@ -1131,6 +1132,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
First: no IPv4 options.
*/
newinet->inet_opt = NULL;
+ newnp->ipv6_mc_list = NULL;
newnp->ipv6_ac_list = NULL;
newnp->ipv6_fl_list = NULL;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index f400176..e3eeed1 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2658,13 +2658,6 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex);
}
- sockc.tsflags = po->sk.sk_tsflags;
- if (msg->msg_controllen) {
- err = sock_cmsg_send(&po->sk, msg, &sockc);
- if (unlikely(err))
- goto out;
- }
-
err = -ENXIO;
if (unlikely(dev == NULL))
goto out;
@@ -2672,6 +2665,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
if (unlikely(!(dev->flags & IFF_UP)))
goto out_put;
+ sockc.tsflags = po->sk.sk_tsflags;
+ if (msg->msg_controllen) {
+ err = sock_cmsg_send(&po->sk, msg, &sockc);
+ if (unlikely(err))
+ goto out_put;
+ }
+
if (po->sk.sk_socket->type == SOCK_RAW)
reserve = dev->hard_header_len;
size_max = po->tx_ring.frame_size
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index bbe57d5..e88342f 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1831,6 +1831,12 @@ static int tc_dump_tclass_root(struct Qdisc *root, struct sk_buff *skb,
if (!qdisc_dev(root))
return 0;
+ if (tcm->tcm_parent) {
+ q = qdisc_match_from_root(root, TC_H_MAJ(tcm->tcm_parent));
+ if (q && tc_dump_tclass_qdisc(q, skb, tcm, cb, t_p, s_t) < 0)
+ return -1;
+ return 0;
+ }
hash_for_each(qdisc_dev(root)->qdisc_hash, b, q, hash) {
if (tc_dump_tclass_qdisc(q, skb, tcm, cb, t_p, s_t) < 0)
return -1;
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 961ee59..142b70e 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -240,12 +240,10 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
struct sctp_bind_addr *bp;
struct ipv6_pinfo *np = inet6_sk(sk);
struct sctp_sockaddr_entry *laddr;
- union sctp_addr *baddr = NULL;
union sctp_addr *daddr = &t->ipaddr;
union sctp_addr dst_saddr;
struct in6_addr *final_p, final;
__u8 matchlen = 0;
- __u8 bmatchlen;
sctp_scope_t scope;
memset(fl6, 0, sizeof(struct flowi6));
@@ -312,23 +310,37 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
*/
rcu_read_lock();
list_for_each_entry_rcu(laddr, &bp->address_list, list) {
- if (!laddr->valid)
+ struct dst_entry *bdst;
+ __u8 bmatchlen;
+
+ if (!laddr->valid ||
+ laddr->state != SCTP_ADDR_SRC ||
+ laddr->a.sa.sa_family != AF_INET6 ||
+ scope > sctp_scope(&laddr->a))
continue;
- if ((laddr->state == SCTP_ADDR_SRC) &&
- (laddr->a.sa.sa_family == AF_INET6) &&
- (scope <= sctp_scope(&laddr->a))) {
- bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a);
- if (!baddr || (matchlen < bmatchlen)) {
- baddr = &laddr->a;
- matchlen = bmatchlen;
- }
- }
- }
- if (baddr) {
- fl6->saddr = baddr->v6.sin6_addr;
- fl6->fl6_sport = baddr->v6.sin6_port;
+
+ fl6->saddr = laddr->a.v6.sin6_addr;
+ fl6->fl6_sport = laddr->a.v6.sin6_port;
final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
- dst = ip6_dst_lookup_flow(sk, fl6, final_p);
+ bdst = ip6_dst_lookup_flow(sk, fl6, final_p);
+
+ if (!IS_ERR(bdst) &&
+ ipv6_chk_addr(dev_net(bdst->dev),
+ &laddr->a.v6.sin6_addr, bdst->dev, 1)) {
+ if (!IS_ERR_OR_NULL(dst))
+ dst_release(dst);
+ dst = bdst;
+ break;
+ }
+
+ bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a);
+ if (matchlen > bmatchlen)
+ continue;
+
+ if (!IS_ERR_OR_NULL(dst))
+ dst_release(dst);
+ dst = bdst;
+ matchlen = bmatchlen;
}
rcu_read_unlock();
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 0d4f2f4..1b92b72 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -362,25 +362,25 @@ static int tipc_sk_sock_err(struct socket *sock, long *timeout)
return 0;
}
-#define tipc_wait_for_cond(sock_, timeout_, condition_) \
-({ \
- int rc_ = 0; \
- int done_ = 0; \
- \
- while (!(condition_) && !done_) { \
- struct sock *sk_ = sock->sk; \
- DEFINE_WAIT_FUNC(wait_, woken_wake_function); \
- \
- rc_ = tipc_sk_sock_err(sock_, timeout_); \
- if (rc_) \
- break; \
- prepare_to_wait(sk_sleep(sk_), &wait_, \
- TASK_INTERRUPTIBLE); \
- done_ = sk_wait_event(sk_, timeout_, \
- (condition_), &wait_); \
- remove_wait_queue(sk_sleep(sk_), &wait_); \
- } \
- rc_; \
+#define tipc_wait_for_cond(sock_, timeo_, condition_) \
+({ \
+ struct sock *sk_; \
+ int rc_; \
+ \
+ while ((rc_ = !(condition_))) { \
+ DEFINE_WAIT_FUNC(wait_, woken_wake_function); \
+ sk_ = (sock_)->sk; \
+ rc_ = tipc_sk_sock_err((sock_), timeo_); \
+ if (rc_) \
+ break; \
+ prepare_to_wait(sk_sleep(sk_), &wait_, TASK_INTERRUPTIBLE); \
+ release_sock(sk_); \
+ *(timeo_) = wait_woken(&wait_, TASK_INTERRUPTIBLE, *(timeo_)); \
+ sched_annotate_sleep(); \
+ lock_sock(sk_); \
+ remove_wait_queue(sk_sleep(sk_), &wait_); \
+ } \
+ rc_; \
})
/**
diff --git a/samples/bpf/cookie_uid_helper_example.c b/samples/bpf/cookie_uid_helper_example.c
index b08ab4e..9d751e2 100644
--- a/samples/bpf/cookie_uid_helper_example.c
+++ b/samples/bpf/cookie_uid_helper_example.c
@@ -306,7 +306,9 @@ int main(int argc, char *argv[])
prog_attach_iptables(argv[2]);
if (cfg_test_traffic) {
if (signal(SIGINT, finish) == SIG_ERR)
- error(1, errno, "register handler failed");
+ error(1, errno, "register SIGINT handler failed");
+ if (signal(SIGTERM, finish) == SIG_ERR)
+ error(1, errno, "register SIGTERM handler failed");
while (!test_finish) {
print_table();
printf("\n");
diff --git a/samples/bpf/offwaketime_user.c b/samples/bpf/offwaketime_user.c
index 9cce2a6..512f87a 100644
--- a/samples/bpf/offwaketime_user.c
+++ b/samples/bpf/offwaketime_user.c
@@ -100,6 +100,7 @@ int main(int argc, char **argv)
setrlimit(RLIMIT_MEMLOCK, &r);
signal(SIGINT, int_exit);
+ signal(SIGTERM, int_exit);
if (load_kallsyms()) {
printf("failed to process /proc/kallsyms\n");
diff --git a/samples/bpf/sampleip_user.c b/samples/bpf/sampleip_user.c
index be59d7d..4ed690b 100644
--- a/samples/bpf/sampleip_user.c
+++ b/samples/bpf/sampleip_user.c
@@ -180,6 +180,7 @@ int main(int argc, char **argv)
return 1;
}
signal(SIGINT, int_exit);
+ signal(SIGTERM, int_exit);
/* do sampling */
printf("Sampling at %d Hertz for %d seconds. Ctrl-C also ends.\n",
diff --git a/samples/bpf/trace_event_user.c b/samples/bpf/trace_event_user.c
index 0c5561d..fa43364 100644
--- a/samples/bpf/trace_event_user.c
+++ b/samples/bpf/trace_event_user.c
@@ -192,6 +192,7 @@ int main(int argc, char **argv)
setrlimit(RLIMIT_MEMLOCK, &r);
signal(SIGINT, int_exit);
+ signal(SIGTERM, int_exit);
if (load_kallsyms()) {
printf("failed to process /proc/kallsyms\n");
diff --git a/samples/bpf/tracex2_user.c b/samples/bpf/tracex2_user.c
index 7fee0f1..7321a3f 100644
--- a/samples/bpf/tracex2_user.c
+++ b/samples/bpf/tracex2_user.c
@@ -127,6 +127,7 @@ int main(int ac, char **argv)
}
signal(SIGINT, int_exit);
+ signal(SIGTERM, int_exit);
/* start 'ping' in the background to have some kfree_skb events */
f = popen("ping -c5 localhost", "r");
diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c
index 378850c..2431c03 100644
--- a/samples/bpf/xdp1_user.c
+++ b/samples/bpf/xdp1_user.c
@@ -62,13 +62,14 @@ static void usage(const char *prog)
fprintf(stderr,
"usage: %s [OPTS] IFINDEX\n\n"
"OPTS:\n"
- " -S use skb-mode\n",
+ " -S use skb-mode\n"
+ " -N enforce native mode\n",
prog);
}
int main(int argc, char **argv)
{
- const char *optstr = "S";
+ const char *optstr = "SN";
char filename[256];
int opt;
@@ -77,6 +78,9 @@ int main(int argc, char **argv)
case 'S':
xdp_flags |= XDP_FLAGS_SKB_MODE;
break;
+ case 'N':
+ xdp_flags |= XDP_FLAGS_DRV_MODE;
+ break;
default:
usage(basename(argv[0]));
return 1;
@@ -102,6 +106,7 @@ int main(int argc, char **argv)
}
signal(SIGINT, int_exit);
+ signal(SIGTERM, int_exit);
if (set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) {
printf("link set xdp fd failed\n");
diff --git a/samples/bpf/xdp_tx_iptunnel_user.c b/samples/bpf/xdp_tx_iptunnel_user.c
index 92b8bde..715cd12 100644
--- a/samples/bpf/xdp_tx_iptunnel_user.c
+++ b/samples/bpf/xdp_tx_iptunnel_user.c
@@ -79,6 +79,8 @@ static void usage(const char *cmd)
printf(" -m <dest-MAC> Used in sending the IP Tunneled pkt\n");
printf(" -T <stop-after-X-seconds> Default: 0 (forever)\n");
printf(" -P <IP-Protocol> Default is TCP\n");
+ printf(" -S use skb-mode\n");
+ printf(" -N enforce native mode\n");
printf(" -h Display this help\n");
}
@@ -138,7 +140,7 @@ int main(int argc, char **argv)
{
unsigned char opt_flags[256] = {};
unsigned int kill_after_s = 0;
- const char *optstr = "i:a:p:s:d:m:T:P:Sh";
+ const char *optstr = "i:a:p:s:d:m:T:P:SNh";
int min_port = 0, max_port = 0;
struct iptnl_info tnl = {};
struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
@@ -206,6 +208,9 @@ int main(int argc, char **argv)
case 'S':
xdp_flags |= XDP_FLAGS_SKB_MODE;
break;
+ case 'N':
+ xdp_flags |= XDP_FLAGS_DRV_MODE;
+ break;
default:
usage(argv[0]);
return 1;
@@ -239,6 +244,7 @@ int main(int argc, char **argv)
}
signal(SIGINT, int_exit);
+ signal(SIGTERM, int_exit);
while (min_port <= max_port) {
vip.dport = htons(min_port++);
diff --git a/tools/build/feature/test-bpf.c b/tools/build/feature/test-bpf.c
index ebc6dce..7598361 100644
--- a/tools/build/feature/test-bpf.c
+++ b/tools/build/feature/test-bpf.c
@@ -29,6 +29,7 @@ int main(void)
attr.log_size = 0;
attr.log_level = 0;
attr.kern_version = 0;
+ attr.prog_flags = 0;
/*
* Test existence of __NR_bpf and BPF_PROG_LOAD.
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e553529..94dfa9d 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -132,6 +132,13 @@ enum bpf_attach_type {
*/
#define BPF_F_ALLOW_OVERRIDE (1U << 0)
+/* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the
+ * verifier will perform strict alignment checking as if the kernel
+ * has been built with CONFIG_EFFICIENT_UNALIGNED_ACCESS not set,
+ * and NET_IP_ALIGN defined to 2.
+ */
+#define BPF_F_STRICT_ALIGNMENT (1U << 0)
+
#define BPF_PSEUDO_MAP_FD 1
/* flags for BPF_MAP_UPDATE_ELEM command */
@@ -177,6 +184,7 @@ union bpf_attr {
__u32 log_size; /* size of user buffer */
__aligned_u64 log_buf; /* user supplied buffer */
__u32 kern_version; /* checked when prog_type=kprobe */
+ __u32 prog_flags;
};
struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -481,8 +489,7 @@ union bpf_attr {
* u32 bpf_get_socket_uid(skb)
* Get the owner uid of the socket stored inside sk_buff.
* @skb: pointer to skb
- * Return: uid of the socket owner on success or 0 if the socket pointer
- * inside sk_buff is NULL
+ * Return: uid of the socket owner on success or overflowuid if failed.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 4fe444b80..6e17898 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -117,6 +117,28 @@ int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
}
+int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns,
+ size_t insns_cnt, int strict_alignment,
+ const char *license, __u32 kern_version,
+ char *log_buf, size_t log_buf_sz)
+{
+ union bpf_attr attr;
+
+ bzero(&attr, sizeof(attr));
+ attr.prog_type = type;
+ attr.insn_cnt = (__u32)insns_cnt;
+ attr.insns = ptr_to_u64(insns);
+ attr.license = ptr_to_u64(license);
+ attr.log_buf = ptr_to_u64(log_buf);
+ attr.log_size = log_buf_sz;
+ attr.log_level = 2;
+ log_buf[0] = 0;
+ attr.kern_version = kern_version;
+ attr.prog_flags = strict_alignment ? BPF_F_STRICT_ALIGNMENT : 0;
+
+ return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
+}
+
int bpf_map_update_elem(int fd, const void *key, const void *value,
__u64 flags)
{
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index edb4dae..972bd83 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -35,6 +35,10 @@ int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
size_t insns_cnt, const char *license,
__u32 kern_version, char *log_buf,
size_t log_buf_sz);
+int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns,
+ size_t insns_cnt, int strict_alignment,
+ const char *license, __u32 kern_version,
+ char *log_buf, size_t log_buf_sz);
int bpf_map_update_elem(int fd, const void *key, const void *value,
__u64 flags);
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 91edd05..f389b02 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -11,7 +11,8 @@
CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include
LDLIBS += -lcap -lelf
-TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs
+TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
+ test_align
TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o
@@ -34,6 +35,7 @@
CLANG ?= clang
%.o: %.c
- $(CLANG) -I. -I../../../include/uapi -I../../../../samples/bpf/ \
+ $(CLANG) -I. -I./include/uapi -I../../../include/uapi \
+ -I../../../../samples/bpf/ \
-Wno-compare-distinct-pointer-types \
-O2 -target bpf -c $< -o $@
diff --git a/tools/testing/selftests/bpf/include/uapi/linux/types.h b/tools/testing/selftests/bpf/include/uapi/linux/types.h
new file mode 100644
index 0000000..fbd16a7
--- /dev/null
+++ b/tools/testing/selftests/bpf/include/uapi/linux/types.h
@@ -0,0 +1,6 @@
+#ifndef _UAPI_LINUX_TYPES_H
+#define _UAPI_LINUX_TYPES_H
+
+#include <asm-generic/int-ll64.h>
+
+#endif /* _UAPI_LINUX_TYPES_H */
diff --git a/tools/testing/selftests/bpf/test_align.c b/tools/testing/selftests/bpf/test_align.c
new file mode 100644
index 0000000..9644d4e
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_align.c
@@ -0,0 +1,453 @@
+#include <asm/types.h>
+#include <linux/types.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <errno.h>
+#include <string.h>
+#include <stddef.h>
+#include <stdbool.h>
+
+#include <linux/unistd.h>
+#include <linux/filter.h>
+#include <linux/bpf_perf_event.h>
+#include <linux/bpf.h>
+
+#include <bpf/bpf.h>
+
+#include "../../../include/linux/filter.h"
+
+#ifndef ARRAY_SIZE
+# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#endif
+
+#define MAX_INSNS 512
+#define MAX_MATCHES 16
+
+struct bpf_align_test {
+ const char *descr;
+ struct bpf_insn insns[MAX_INSNS];
+ enum {
+ UNDEF,
+ ACCEPT,
+ REJECT
+ } result;
+ enum bpf_prog_type prog_type;
+ const char *matches[MAX_MATCHES];
+};
+
+static struct bpf_align_test tests[] = {
+ {
+ .descr = "mov",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_3, 2),
+ BPF_MOV64_IMM(BPF_REG_3, 4),
+ BPF_MOV64_IMM(BPF_REG_3, 8),
+ BPF_MOV64_IMM(BPF_REG_3, 16),
+ BPF_MOV64_IMM(BPF_REG_3, 32),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .matches = {
+ "1: R1=ctx R3=imm2,min_value=2,max_value=2,min_align=2 R10=fp",
+ "2: R1=ctx R3=imm4,min_value=4,max_value=4,min_align=4 R10=fp",
+ "3: R1=ctx R3=imm8,min_value=8,max_value=8,min_align=8 R10=fp",
+ "4: R1=ctx R3=imm16,min_value=16,max_value=16,min_align=16 R10=fp",
+ "5: R1=ctx R3=imm32,min_value=32,max_value=32,min_align=32 R10=fp",
+ },
+ },
+ {
+ .descr = "shift",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_3, 1),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
+ BPF_ALU64_IMM(BPF_RSH, BPF_REG_3, 4),
+ BPF_MOV64_IMM(BPF_REG_4, 32),
+ BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
+ BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
+ BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
+ BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .matches = {
+ "1: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R10=fp",
+ "2: R1=ctx R3=imm2,min_value=2,max_value=2,min_align=2 R10=fp",
+ "3: R1=ctx R3=imm4,min_value=4,max_value=4,min_align=4 R10=fp",
+ "4: R1=ctx R3=imm8,min_value=8,max_value=8,min_align=8 R10=fp",
+ "5: R1=ctx R3=imm16,min_value=16,max_value=16,min_align=16 R10=fp",
+ "6: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R10=fp",
+ "7: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm32,min_value=32,max_value=32,min_align=32 R10=fp",
+ "8: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm16,min_value=16,max_value=16,min_align=16 R10=fp",
+ "9: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm8,min_value=8,max_value=8,min_align=8 R10=fp",
+ "10: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm4,min_value=4,max_value=4,min_align=4 R10=fp",
+ "11: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm2,min_value=2,max_value=2,min_align=2 R10=fp",
+ },
+ },
+ {
+ .descr = "addsub",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_3, 4),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 4),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 2),
+ BPF_MOV64_IMM(BPF_REG_4, 8),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 2),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .matches = {
+ "1: R1=ctx R3=imm4,min_value=4,max_value=4,min_align=4 R10=fp",
+ "2: R1=ctx R3=imm8,min_value=8,max_value=8,min_align=4 R10=fp",
+ "3: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R10=fp",
+ "4: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R4=imm8,min_value=8,max_value=8,min_align=8 R10=fp",
+ "5: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R4=imm12,min_value=12,max_value=12,min_align=4 R10=fp",
+ "6: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R4=imm14,min_value=14,max_value=14,min_align=2 R10=fp",
+ },
+ },
+ {
+ .descr = "mul",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_3, 7),
+ BPF_ALU64_IMM(BPF_MUL, BPF_REG_3, 1),
+ BPF_ALU64_IMM(BPF_MUL, BPF_REG_3, 2),
+ BPF_ALU64_IMM(BPF_MUL, BPF_REG_3, 4),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .matches = {
+ "1: R1=ctx R3=imm7,min_value=7,max_value=7,min_align=1 R10=fp",
+ "2: R1=ctx R3=imm7,min_value=7,max_value=7,min_align=1 R10=fp",
+ "3: R1=ctx R3=imm14,min_value=14,max_value=14,min_align=2 R10=fp",
+ "4: R1=ctx R3=imm56,min_value=56,max_value=56,min_align=4 R10=fp",
+ },
+ },
+
+#define PREP_PKT_POINTERS \
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, \
+ offsetof(struct __sk_buff, data)), \
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, \
+ offsetof(struct __sk_buff, data_end))
+
+#define LOAD_UNKNOWN(DST_REG) \
+ PREP_PKT_POINTERS, \
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), \
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), \
+ BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_0, 1), \
+ BPF_EXIT_INSN(), \
+ BPF_LDX_MEM(BPF_B, DST_REG, BPF_REG_2, 0)
+
+ {
+ .descr = "unknown shift",
+ .insns = {
+ LOAD_UNKNOWN(BPF_REG_3),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
+ LOAD_UNKNOWN(BPF_REG_4),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_4, 5),
+ BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
+ BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
+ BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
+ BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .matches = {
+ "7: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R10=fp",
+ "8: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv55,min_align=2 R10=fp",
+ "9: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv54,min_align=4 R10=fp",
+ "10: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv53,min_align=8 R10=fp",
+ "11: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv52,min_align=16 R10=fp",
+ "18: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv56 R10=fp",
+ "19: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv51,min_align=32 R10=fp",
+ "20: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv52,min_align=16 R10=fp",
+ "21: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv53,min_align=8 R10=fp",
+ "22: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv54,min_align=4 R10=fp",
+ "23: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv55,min_align=2 R10=fp",
+ },
+ },
+ {
+ .descr = "unknown mul",
+ .insns = {
+ LOAD_UNKNOWN(BPF_REG_3),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_3),
+ BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 1),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_3),
+ BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 2),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_3),
+ BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 4),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_3),
+ BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 8),
+ BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 2),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .matches = {
+ "7: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R10=fp",
+ "8: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp",
+ "9: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv55,min_align=1 R10=fp",
+ "10: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp",
+ "11: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv54,min_align=2 R10=fp",
+ "12: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp",
+ "13: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv53,min_align=4 R10=fp",
+ "14: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp",
+ "15: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv52,min_align=8 R10=fp",
+ "16: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv50,min_align=8 R10=fp"
+ },
+ },
+ {
+ .descr = "packet const offset",
+ .insns = {
+ PREP_PKT_POINTERS,
+ BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
+
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+
+ /* Skip over ethernet header. */
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
+ BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1),
+ BPF_EXIT_INSN(),
+
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_5, 0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_5, 1),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_5, 2),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_5, 3),
+ BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_5, 0),
+ BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_5, 2),
+ BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_5, 0),
+
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .matches = {
+ "4: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=0) R3=pkt_end R5=pkt(id=0,off=0,r=0) R10=fp",
+ "5: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=0) R3=pkt_end R5=pkt(id=0,off=14,r=0) R10=fp",
+ "6: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=0) R3=pkt_end R4=pkt(id=0,off=14,r=0) R5=pkt(id=0,off=14,r=0) R10=fp",
+ "10: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=18) R3=pkt_end R4=inv56 R5=pkt(id=0,off=14,r=18) R10=fp",
+ "14: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=18) R3=pkt_end R4=inv48 R5=pkt(id=0,off=14,r=18) R10=fp",
+ "15: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=18) R3=pkt_end R4=inv48 R5=pkt(id=0,off=14,r=18) R10=fp",
+ },
+ },
+ {
+ .descr = "packet variable offset",
+ .insns = {
+ LOAD_UNKNOWN(BPF_REG_6),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_6, 2),
+
+ /* First, add a constant to the R5 packet pointer,
+ * then a variable with a known alignment.
+ */
+ BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
+ BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1),
+ BPF_EXIT_INSN(),
+ BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_5, 0),
+
+ /* Now, test in the other direction. Adding first
+ * the variable offset to R5, then the constant.
+ */
+ BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
+ BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1),
+ BPF_EXIT_INSN(),
+ BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_5, 0),
+
+ /* Test multiple accumulations of unknown values
+ * into a packet pointer.
+ */
+ BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 4),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
+ BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1),
+ BPF_EXIT_INSN(),
+ BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_5, 0),
+
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .matches = {
+ /* Calculated offset in R6 has unknown value, but known
+ * alignment of 4.
+ */
+ "8: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R6=inv54,min_align=4 R10=fp",
+
+ /* Offset is added to packet pointer R5, resulting in known
+ * auxiliary alignment and offset.
+ */
+ "11: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R5=pkt(id=1,off=0,r=0),aux_off=14,aux_off_align=4 R6=inv54,min_align=4 R10=fp",
+
+ /* At the time the word size load is performed from R5,
+ * it's total offset is NET_IP_ALIGN + reg->off (0) +
+ * reg->aux_off (14) which is 16. Then the variable
+ * offset is considered using reg->aux_off_align which
+ * is 4 and meets the load's requirements.
+ */
+ "15: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=pkt(id=1,off=4,r=4),aux_off=14,aux_off_align=4 R5=pkt(id=1,off=0,r=4),aux_off=14,aux_off_align=4 R6=inv54,min_align=4 R10=fp",
+
+
+ /* Variable offset is added to R5 packet pointer,
+ * resulting in auxiliary alignment of 4.
+ */
+ "18: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off=14,aux_off_align=4 R5=pkt(id=2,off=0,r=0),aux_off_align=4 R6=inv54,min_align=4 R10=fp",
+
+ /* Constant offset is added to R5, resulting in
+ * reg->off of 14.
+ */
+ "19: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off=14,aux_off_align=4 R5=pkt(id=2,off=14,r=0),aux_off_align=4 R6=inv54,min_align=4 R10=fp",
+
+ /* At the time the word size load is performed from R5,
+ * it's total offset is NET_IP_ALIGN + reg->off (14) which
+ * is 16. Then the variable offset is considered using
+ * reg->aux_off_align which is 4 and meets the load's
+ * requirements.
+ */
+ "23: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=pkt(id=2,off=18,r=18),aux_off_align=4 R5=pkt(id=2,off=14,r=18),aux_off_align=4 R6=inv54,min_align=4 R10=fp",
+
+ /* Constant offset is added to R5 packet pointer,
+ * resulting in reg->off value of 14.
+ */
+ "26: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off_align=4 R5=pkt(id=0,off=14,r=8) R6=inv54,min_align=4 R10=fp",
+ /* Variable offset is added to R5, resulting in an
+ * auxiliary offset of 14, and an auxiliary alignment of 4.
+ */
+ "27: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off_align=4 R5=pkt(id=3,off=0,r=0),aux_off=14,aux_off_align=4 R6=inv54,min_align=4 R10=fp",
+ /* Constant is added to R5 again, setting reg->off to 4. */
+ "28: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off_align=4 R5=pkt(id=3,off=4,r=0),aux_off=14,aux_off_align=4 R6=inv54,min_align=4 R10=fp",
+ /* And once more we add a variable, which causes an accumulation
+ * of reg->off into reg->aux_off_align, with resulting value of
+ * 18. The auxiliary alignment stays at 4.
+ */
+ "29: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off_align=4 R5=pkt(id=4,off=0,r=0),aux_off=18,aux_off_align=4 R6=inv54,min_align=4 R10=fp",
+ /* At the time the word size load is performed from R5,
+ * it's total offset is NET_IP_ALIGN + reg->off (0) +
+ * reg->aux_off (18) which is 20. Then the variable offset
+ * is considered using reg->aux_off_align which is 4 and meets
+ * the load's requirements.
+ */
+ "33: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=pkt(id=4,off=4,r=4),aux_off=18,aux_off_align=4 R5=pkt(id=4,off=0,r=4),aux_off=18,aux_off_align=4 R6=inv54,min_align=4 R10=fp",
+ },
+ },
+};
+
+static int probe_filter_length(const struct bpf_insn *fp)
+{
+ int len;
+
+ for (len = MAX_INSNS - 1; len > 0; --len)
+ if (fp[len].code != 0 || fp[len].imm != 0)
+ break;
+ return len + 1;
+}
+
+static char bpf_vlog[32768];
+
+static int do_test_single(struct bpf_align_test *test)
+{
+ struct bpf_insn *prog = test->insns;
+ int prog_type = test->prog_type;
+ int prog_len, i;
+ int fd_prog;
+ int ret;
+
+ prog_len = probe_filter_length(prog);
+ fd_prog = bpf_verify_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER,
+ prog, prog_len, 1, "GPL", 0,
+ bpf_vlog, sizeof(bpf_vlog));
+ if (fd_prog < 0) {
+ printf("Failed to load program.\n");
+ printf("%s", bpf_vlog);
+ ret = 1;
+ } else {
+ ret = 0;
+ for (i = 0; i < MAX_MATCHES; i++) {
+ const char *t, *m = test->matches[i];
+
+ if (!m)
+ break;
+ t = strstr(bpf_vlog, m);
+ if (!t) {
+ printf("Failed to find match: %s\n", m);
+ ret = 1;
+ printf("%s", bpf_vlog);
+ break;
+ }
+ }
+ close(fd_prog);
+ }
+ return ret;
+}
+
+static int do_test(unsigned int from, unsigned int to)
+{
+ int all_pass = 0;
+ int all_fail = 0;
+ unsigned int i;
+
+ for (i = from; i < to; i++) {
+ struct bpf_align_test *test = &tests[i];
+ int fail;
+
+ printf("Test %3d: %s ... ",
+ i, test->descr);
+ fail = do_test_single(test);
+ if (fail) {
+ all_fail++;
+ printf("FAIL\n");
+ } else {
+ all_pass++;
+ printf("PASS\n");
+ }
+ }
+ printf("Results: %d pass %d fail\n",
+ all_pass, all_fail);
+ return 0;
+}
+
+int main(int argc, char **argv)
+{
+ unsigned int from = 0, to = ARRAY_SIZE(tests);
+
+ if (argc == 3) {
+ unsigned int l = atoi(argv[argc - 2]);
+ unsigned int u = atoi(argv[argc - 1]);
+
+ if (l < to && u < to) {
+ from = l;
+ to = u + 1;
+ }
+ } else if (argc == 2) {
+ unsigned int t = atoi(argv[argc - 1]);
+
+ if (t < to) {
+ from = t;
+ to = t + 1;
+ }
+ }
+ return do_test(from, to);
+}
