summaryrefslogtreecommitdiff
path: root/arch/s390
diff options
context:
space:
mode:
Diffstat (limited to 'arch/s390')
-rw-r--r--arch/s390/Kconfig8
-rw-r--r--arch/s390/configs/default_defconfig39
-rw-r--r--arch/s390/configs/gcov_defconfig28
-rw-r--r--arch/s390/configs/performance_defconfig27
-rw-r--r--arch/s390/configs/zfcpdump_defconfig6
-rw-r--r--arch/s390/crypto/Makefile3
-rw-r--r--arch/s390/crypto/arch_random.c1
-rw-r--r--arch/s390/defconfig8
-rw-r--r--arch/s390/include/asm/Kbuild2
-rw-r--r--arch/s390/include/asm/compat.h1
-rw-r--r--arch/s390/include/asm/ctl_reg.h4
-rw-r--r--arch/s390/include/asm/debug.h3
-rw-r--r--arch/s390/include/asm/device.h10
-rw-r--r--arch/s390/include/asm/diag.h26
-rw-r--r--arch/s390/include/asm/dis.h2
-rw-r--r--arch/s390/include/asm/dma-mapping.h2
-rw-r--r--arch/s390/include/asm/eadm.h6
-rw-r--r--arch/s390/include/asm/elf.h47
-rw-r--r--arch/s390/include/asm/fb.h12
-rw-r--r--arch/s390/include/asm/hugetlb.h5
-rw-r--r--arch/s390/include/asm/io.h4
-rw-r--r--arch/s390/include/asm/kexec.h18
-rw-r--r--arch/s390/include/asm/kprobes.h20
-rw-r--r--arch/s390/include/asm/kvm_host.h51
-rw-r--r--arch/s390/include/asm/mmu_context.h4
-rw-r--r--arch/s390/include/asm/nmi.h13
-rw-r--r--arch/s390/include/asm/page.h3
-rw-r--r--arch/s390/include/asm/pci.h15
-rw-r--r--arch/s390/include/asm/pci_insn.h2
-rw-r--r--arch/s390/include/asm/pgalloc.h25
-rw-r--r--arch/s390/include/asm/pgtable.h105
-rw-r--r--arch/s390/include/asm/processor.h11
-rw-r--r--arch/s390/include/asm/ptrace.h54
-rw-r--r--arch/s390/include/asm/sigp.h2
-rw-r--r--arch/s390/include/asm/syscall.h6
-rw-r--r--arch/s390/include/asm/sysinfo.h6
-rw-r--r--arch/s390/include/asm/thread_info.h1
-rw-r--r--arch/s390/include/asm/tlb.h15
-rw-r--r--arch/s390/include/asm/uaccess.h17
-rw-r--r--arch/s390/include/uapi/asm/kvm.h12
-rw-r--r--arch/s390/include/uapi/asm/socket.h4
-rw-r--r--arch/s390/kernel/asm-offsets.c3
-rw-r--r--arch/s390/kernel/debug.c8
-rw-r--r--arch/s390/kernel/diag.c29
-rw-r--r--arch/s390/kernel/dumpstack.c33
-rw-r--r--arch/s390/kernel/entry.S70
-rw-r--r--arch/s390/kernel/ftrace.c4
-rw-r--r--arch/s390/kernel/ipl.c7
-rw-r--r--arch/s390/kernel/jump_label.c2
-rw-r--r--arch/s390/kernel/kprobes.c4
-rw-r--r--arch/s390/kernel/machine_kexec.c1
-rw-r--r--arch/s390/kernel/nmi.c84
-rw-r--r--arch/s390/kernel/perf_cpum_sf.c10
-rw-r--r--arch/s390/kernel/perf_event.c3
-rw-r--r--arch/s390/kernel/process.c25
-rw-r--r--arch/s390/kernel/ptrace.c15
-rw-r--r--arch/s390/kernel/setup.c6
-rw-r--r--arch/s390/kernel/smp.c3
-rw-r--r--arch/s390/kernel/sysinfo.c2
-rw-r--r--arch/s390/kernel/time.c6
-rw-r--r--arch/s390/kernel/traps.c1
-rw-r--r--arch/s390/kernel/uprobes.c12
-rw-r--r--arch/s390/kernel/vdso.c91
-rw-r--r--arch/s390/kernel/vmlinux.lds.S8
-rw-r--r--arch/s390/kernel/vtime.c14
-rw-r--r--arch/s390/kvm/gaccess.c80
-rw-r--r--arch/s390/kvm/gaccess.h4
-rw-r--r--arch/s390/kvm/guestdbg.c6
-rw-r--r--arch/s390/kvm/interrupt.c95
-rw-r--r--arch/s390/kvm/kvm-s390.c376
-rw-r--r--arch/s390/kvm/kvm-s390.h2
-rw-r--r--arch/s390/kvm/priv.c111
-rw-r--r--arch/s390/kvm/vsie.c25
-rw-r--r--arch/s390/lib/probes.c1
-rw-r--r--arch/s390/lib/uaccess.c4
-rw-r--r--arch/s390/mm/dump_pagetables.c23
-rw-r--r--arch/s390/mm/fault.c2
-rw-r--r--arch/s390/mm/gmap.c11
-rw-r--r--arch/s390/mm/gup.c33
-rw-r--r--arch/s390/mm/hugetlbpage.c33
-rw-r--r--arch/s390/mm/init.c38
-rw-r--r--arch/s390/mm/mmap.c8
-rw-r--r--arch/s390/mm/pageattr.c30
-rw-r--r--arch/s390/mm/pgalloc.c57
-rw-r--r--arch/s390/mm/pgtable.c6
-rw-r--r--arch/s390/mm/vmem.c44
-rw-r--r--arch/s390/net/bpf_jit_comp.c3
-rw-r--r--arch/s390/pci/pci.c173
-rw-r--r--arch/s390/pci/pci_clp.c77
-rw-r--r--arch/s390/pci/pci_dma.c22
-rw-r--r--arch/s390/pci/pci_event.c14
-rw-r--r--arch/s390/pci/pci_insn.c10
-rw-r--r--arch/s390/tools/gen_facilities.c2
93 files changed, 1745 insertions, 614 deletions
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index e161fafb495b..7eeb75d758c1 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -64,10 +64,11 @@ config ARCH_SUPPORTS_UPROBES
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
- select ARCH_HAS_GIGANTIC_PAGE
+ select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
select ARCH_HAS_KCOV
select ARCH_HAS_SET_MEMORY
select ARCH_HAS_SG_CHAIN
@@ -184,7 +185,7 @@ config SCHED_OMIT_FRAME_POINTER
config PGTABLE_LEVELS
int
- default 4
+ default 5
source "init/Kconfig"
@@ -363,9 +364,6 @@ config COMPAT
config SYSVIPC_COMPAT
def_bool y if COMPAT && SYSVIPC
-config KEYS_COMPAT
- def_bool y if COMPAT && KEYS
-
config SMP
def_bool y
prompt "Symmetric multi-processing support"
diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig
index a5039fa89314..282072206df7 100644
--- a/arch/s390/configs/default_defconfig
+++ b/arch/s390/configs/default_defconfig
@@ -30,6 +30,7 @@ CONFIG_USER_NS=y
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_UNLOAD=y
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=y
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_SIMP=m
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_DEVTMPFS=y
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_NLMON=m
# 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_PPTP=m
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_DIAG288_WATCHDOG=m
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_POSIX_ACL=y
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_HEADERS_CHECK=y
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_DETECT_HUNG_TASK=y
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_TORTURE_TEST=m
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_HIST_TRIGGERS=y
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_S390_PTDUMP=y
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_RSA=m
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_CHACHA20POLY1305=m
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_RMD160=m
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_TWOFISH=m
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_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_ASYMMETRIC_KEY_TYPE=y
@@ -692,6 +718,7 @@ CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m
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 83970b5afb2b..3c6b78189fbc 100644
--- a/arch/s390/configs/gcov_defconfig
+++ b/arch/s390/configs/gcov_defconfig
@@ -31,6 +31,7 @@ CONFIG_USER_NS=y
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_UNLOAD=y
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=y
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_SIMP=m
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_DEVTMPFS=y
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_NLMON=m
# 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_PPTP=m
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_DIAG288_WATCHDOG=m
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_QUOTA=y
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_UNUSED_SYMBOLS=y
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_BIG_KEYS=y
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_CHACHA20POLY1305=m
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_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
@@ -626,16 +643,19 @@ CONFIG_CRYPTO_TWOFISH=m
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 fbc6542aaf59..653d72bcc007 100644
--- a/arch/s390/configs/performance_defconfig
+++ b/arch/s390/configs/performance_defconfig
@@ -31,6 +31,7 @@ CONFIG_USER_NS=y
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_UNLOAD=y
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=y
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_SIMP=m
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_DEVTMPFS=y
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_NLMON=m
# 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_PPTP=m
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_DIAG288_WATCHDOG=m
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_QUOTA=y
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_UNUSED_SYMBOLS=y
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_BIG_KEYS=y
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_CHACHA20POLY1305=m
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_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
@@ -624,6 +641,7 @@ CONFIG_CRYPTO_TWOFISH=m
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_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/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index e23d97c13735..afa46a7406ea 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -12,8 +12,10 @@ CONFIG_TUNE_ZEC12=y
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_CONSTANTS=y
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_RAW_DRIVER=y
# 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 678d9863e3f0..ad4bd777768d 100644
--- a/arch/s390/crypto/Makefile
+++ b/arch/s390/crypto/Makefile
@@ -6,7 +6,8 @@ obj-$(CONFIG_CRYPTO_SHA1_S390) += sha1_s390.o sha_common.o
obj-$(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 9317b3e645e2..36aefc07d10c 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 97189dbaf34b..20244a38c886 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -28,6 +28,7 @@ CONFIG_NAMESPACES=y
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_ZFCP=y
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_TUN=m
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_MAGIC_SYSRQ=y
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_LIST=y
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_CCM=m
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_SKCIPHER=m
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 45092b12f54f..b3c88479feba 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/compat.h b/arch/s390/include/asm/compat.h
index 0ddd37e6c29d..b9300f8aee10 100644
--- a/arch/s390/include/asm/compat.h
+++ b/arch/s390/include/asm/compat.h
@@ -178,7 +178,6 @@ struct compat_statfs64 {
u32 f_spare[4];
};
-#define COMPAT_RLIM_OLD_INFINITY 0x7fffffff
#define COMPAT_RLIM_INFINITY 0xffffffff
typedef u32 compat_old_sigset_t; /* at least 32 bits */
diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h
index d0441ad2a990..e508dff92535 100644
--- a/arch/s390/include/asm/ctl_reg.h
+++ b/arch/s390/include/asm/ctl_reg.h
@@ -59,7 +59,9 @@ union ctlreg0 {
unsigned long lap : 1; /* Low-address-protection control */
unsigned long : 4;
unsigned long edat : 1; /* Enhanced-DAT-enablement control */
- unsigned long : 4;
+ unsigned long : 2;
+ unsigned long iep : 1; /* Instruction-Execution-Protection */
+ unsigned long : 1;
unsigned long afp : 1; /* AFP-register control */
unsigned long vx : 1; /* Vector enablement control */
unsigned long : 7;
diff --git a/arch/s390/include/asm/debug.h b/arch/s390/include/asm/debug.h
index 0206c8052328..df7b54ea956d 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 5203fc87f080..000000000000
--- 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/diag.h b/arch/s390/include/asm/diag.h
index 8acf482162ed..88162bb5c190 100644
--- a/arch/s390/include/asm/diag.h
+++ b/arch/s390/include/asm/diag.h
@@ -8,6 +8,7 @@
#ifndef _ASM_S390_DIAG_H
#define _ASM_S390_DIAG_H
+#include <linux/if_ether.h>
#include <linux/percpu.h>
enum diag_stat_enum {
@@ -24,6 +25,7 @@ enum diag_stat_enum {
DIAG_STAT_X224,
DIAG_STAT_X250,
DIAG_STAT_X258,
+ DIAG_STAT_X26C,
DIAG_STAT_X288,
DIAG_STAT_X2C4,
DIAG_STAT_X2FC,
@@ -225,6 +227,30 @@ struct diag204_x_phys_block {
struct diag204_x_phys_cpu cpus[];
} __packed;
+enum diag26c_sc {
+ DIAG26C_MAC_SERVICES = 0x00000030
+};
+
+enum diag26c_version {
+ DIAG26C_VERSION2 = 0x00000002 /* z/VM 5.4.0 */
+};
+
+#define DIAG26C_GET_MAC 0x0000
+struct diag26c_mac_req {
+ u32 resp_buf_len;
+ u32 resp_version;
+ u16 op_code;
+ u16 devno;
+ u8 res[4];
+};
+
+struct diag26c_mac_resp {
+ u32 version;
+ u8 mac[ETH_ALEN];
+ u8 res[2];
+} __aligned(8);
+
int diag204(unsigned long subcode, unsigned long size, void *addr);
int diag224(void *ptr);
+int diag26c(void *req, void *resp, enum diag26c_sc subcode);
#endif /* _ASM_S390_DIAG_H */
diff --git a/arch/s390/include/asm/dis.h b/arch/s390/include/asm/dis.h
index 60323c21938b..37f617dfbede 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/dma-mapping.h b/arch/s390/include/asm/dma-mapping.h
index 3108b8dbe266..512ad0eaa11a 100644
--- a/arch/s390/include/asm/dma-mapping.h
+++ b/arch/s390/include/asm/dma-mapping.h
@@ -8,8 +8,6 @@
#include <linux/dma-debug.h>
#include <linux/io.h>
-#define DMA_ERROR_CODE (~(dma_addr_t) 0x0)
-
extern const struct dma_map_ops s390_pci_dma_ops;
static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
diff --git a/arch/s390/include/asm/eadm.h b/arch/s390/include/asm/eadm.h
index 67026300c88e..144809a3f4f6 100644
--- a/arch/s390/include/asm/eadm.h
+++ b/arch/s390/include/asm/eadm.h
@@ -3,6 +3,7 @@
#include <linux/types.h>
#include <linux/device.h>
+#include <linux/blkdev.h>
struct arqb {
u64 data;
@@ -105,13 +106,14 @@ struct scm_driver {
int (*probe) (struct scm_device *scmdev);
int (*remove) (struct scm_device *scmdev);
void (*notify) (struct scm_device *scmdev, enum scm_event event);
- void (*handler) (struct scm_device *scmdev, void *data, int error);
+ void (*handler) (struct scm_device *scmdev, void *data,
+ blk_status_t error);
};
int scm_driver_register(struct scm_driver *scmdrv);
void scm_driver_unregister(struct scm_driver *scmdrv);
int eadm_start_aob(struct aob *aob);
-void scm_irq_handler(struct aob *aob, int error);
+void scm_irq_handler(struct aob *aob, blk_status_t error);
#endif /* _ASM_S390_EADM_H */
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index e8f623041769..c92ed0170be2 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) \
@@ -161,14 +193,13 @@ extern unsigned int vdso_enabled;
#define CORE_DUMP_USE_REGSET
#define ELF_EXEC_PAGESIZE 4096
-/* This is the location that an ET_DYN program is loaded if exec'ed. Typical
- use of this is to invoke "./ld.so someprog" to test out a new version of
- the loader. We need to make sure that it is out of the way of the program
- that it will "exec", and that there is sufficient room for the brk. 64-bit
- tasks are aligned to 4GB. */
-#define ELF_ET_DYN_BASE (is_compat_task() ? \
- (STACK_TOP / 3 * 2) : \
- (STACK_TOP / 3 * 2) & ~((1UL << 32) - 1))
+/*
+ * This is the base location for PIE (ET_DYN with INTERP) loads. On
+ * 64-bit, this is raised to 4GB to leave the entire 32-bit address
+ * space open for things that want to use the area for 32-bit pointers.
+ */
+#define ELF_ET_DYN_BASE (is_compat_task() ? 0x000400000UL : \
+ 0x100000000UL)
/* This yields a mask that user programs can use to figure out what
instruction set this CPU supports. */
diff --git a/arch/s390/include/asm/fb.h b/arch/s390/include/asm/fb.h
deleted file mode 100644
index c7df38030992..000000000000
--- 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/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index cd546a245c68..d95869ce3ca2 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -39,7 +39,7 @@ static inline int prepare_hugepage_range(struct file *file,
#define arch_clear_hugepage_flags(page) do { } while (0)
static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep)
+ pte_t *ptep, unsigned long sz)
{
if ((pte_val(*ptep) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3)
pte_val(*ptep) = _REGION3_ENTRY_EMPTY;
@@ -112,4 +112,7 @@ static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot)
return pte_modify(pte, newprot);
}
+#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
+static inline bool gigantic_page_supported(void) { return true; }
+#endif
#endif /* _ASM_S390_HUGETLB_H */
diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h
index 437e9af96688..904e4b3af95d 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/kexec.h b/arch/s390/include/asm/kexec.h
index 2f924bc30e35..dccf24ee26d3 100644
--- a/arch/s390/include/asm/kexec.h
+++ b/arch/s390/include/asm/kexec.h
@@ -41,24 +41,6 @@
/* The native architecture */
#define KEXEC_ARCH KEXEC_ARCH_S390
-/*
- * Size for s390x ELF notes per CPU
- *
- * Seven notes plus zero note at the end: prstatus, fpregset, timer,
- * tod_cmp, tod_reg, control regs, and prefix
- */
-#define KEXEC_NOTE_BYTES \
- (ALIGN(sizeof(struct elf_note), 4) * 8 + \
- ALIGN(sizeof("CORE"), 4) * 7 + \
- ALIGN(sizeof(struct elf_prstatus), 4) + \
- ALIGN(sizeof(elf_fpregset_t), 4) + \
- ALIGN(sizeof(u64), 4) + \
- ALIGN(sizeof(u64), 4) + \
- ALIGN(sizeof(u32), 4) + \
- ALIGN(sizeof(u64) * 16, 4) + \
- ALIGN(sizeof(u32), 4) \
- )
-
/* Provide a dummy definition to avoid build failures. */
static inline void crash_setup_regs(struct pt_regs *newregs,
struct pt_regs *oldregs) { }
diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h
index 1293c4066cfc..28792ef82c83 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/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 426614a882a9..a409d5991934 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -42,9 +42,11 @@
#define KVM_HALT_POLL_NS_DEFAULT 80000
/* s390-specific vcpu->requests bit members */
-#define KVM_REQ_ENABLE_IBS 8
-#define KVM_REQ_DISABLE_IBS 9
-#define KVM_REQ_ICPT_OPEREXC 10
+#define KVM_REQ_ENABLE_IBS KVM_ARCH_REQ(0)
+#define KVM_REQ_DISABLE_IBS KVM_ARCH_REQ(1)
+#define KVM_REQ_ICPT_OPEREXC KVM_ARCH_REQ(2)
+#define KVM_REQ_START_MIGRATION KVM_ARCH_REQ(3)
+#define KVM_REQ_STOP_MIGRATION KVM_ARCH_REQ(4)
#define SIGP_CTRL_C 0x80
#define SIGP_CTRL_SCN_MASK 0x3f
@@ -56,7 +58,7 @@ union bsca_sigp_ctrl {
__u8 r : 1;
__u8 scn : 6;
};
-} __packed;
+};
union esca_sigp_ctrl {
__u16 value;
@@ -65,14 +67,14 @@ union esca_sigp_ctrl {
__u8 reserved: 7;
__u8 scn;
};
-} __packed;
+};
struct esca_entry {
union esca_sigp_ctrl sigp_ctrl;
__u16 reserved1[3];
__u64 sda;
__u64 reserved2[6];
-} __packed;
+};
struct bsca_entry {
__u8 reserved0;
@@ -80,7 +82,7 @@ struct bsca_entry {
__u16 reserved[3];
__u64 sda;
__u64 reserved2[2];
-} __attribute__((packed));
+};
union ipte_control {
unsigned long val;
@@ -97,7 +99,7 @@ struct bsca_block {
__u64 mcn;
__u64 reserved2;
struct bsca_entry cpu[KVM_S390_BSCA_CPU_SLOTS];
-} __attribute__((packed));
+};
struct esca_block {
union ipte_control ipte_control;
@@ -105,7 +107,21 @@ struct esca_block {
__u64 mcn[4];
__u64 reserved2[20];
struct esca_entry cpu[KVM_S390_ESCA_CPU_SLOTS];
-} __packed;
+};
+
+/*
+ * This struct is used to store some machine check info from lowcore
+ * for machine checks that happen while the guest is running.
+ * This info in host's lowcore might be overwritten by a second machine
+ * check from host when host is in the machine check's high-level handling.
+ * The size is 24 bytes.
+ */
+struct mcck_volatile_info {
+ __u64 mcic;
+ __u64 failing_storage_address;
+ __u32 ext_damage_code;
+ __u32 reserved;
+};
#define CPUSTAT_STOPPED 0x80000000
#define CPUSTAT_WAIT 0x10000000
@@ -260,14 +276,15 @@ struct kvm_s390_sie_block {
struct kvm_s390_itdb {
__u8 data[256];
-} __packed;
+};
struct sie_page {
struct kvm_s390_sie_block sie_block;
- __u8 reserved200[1024]; /* 0x0200 */
+ struct mcck_volatile_info mcck_info; /* 0x0200 */
+ __u8 reserved218[1000]; /* 0x0218 */
struct kvm_s390_itdb itdb; /* 0x0600 */
__u8 reserved700[2304]; /* 0x0700 */
-} __packed;
+};
struct kvm_vcpu_stat {
u64 exit_userspace;
@@ -541,7 +558,6 @@ struct kvm_s390_float_interrupt {
struct mutex ais_lock;
u8 simm;
u8 nimm;
- int ais_enabled;
};
struct kvm_hw_wp_info_arch {
@@ -681,7 +697,7 @@ struct sie_page2 {
__u64 fac_list[S390_ARCH_FAC_LIST_SIZE_U64]; /* 0x0000 */
struct kvm_s390_crypto_cb crycb; /* 0x0800 */
u8 reserved900[0x1000 - 0x900]; /* 0x0900 */
-} __packed;
+};
struct kvm_s390_vsie {
struct mutex mutex;
@@ -691,6 +707,12 @@ struct kvm_s390_vsie {
struct page *pages[KVM_MAX_VCPUS];
};
+struct kvm_s390_migration_state {
+ unsigned long bitmap_size; /* in bits (number of guest pages) */
+ atomic64_t dirty_pages; /* number of dirty pages */
+ unsigned long *pgste_bitmap;
+};
+
struct kvm_arch{
void *sca;
int use_esca;
@@ -718,6 +740,7 @@ struct kvm_arch{
struct kvm_s390_crypto crypto;
struct kvm_s390_vsie vsie;
u64 epoch;
+ struct kvm_s390_migration_state *migration_state;
/* subset of available cpu features enabled by user space */
DECLARE_BITMAP(cpu_feat, KVM_S390_VM_CPU_FEAT_NR_BITS);
};
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index 8712e11bead4..4541ac44b35f 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/nmi.h b/arch/s390/include/asm/nmi.h
index e3e8895f5d3e..9d91cf3e427f 100644
--- a/arch/s390/include/asm/nmi.h
+++ b/arch/s390/include/asm/nmi.h
@@ -14,11 +14,24 @@
#include <linux/const.h>
#include <linux/types.h>
+#define MCIC_SUBCLASS_MASK (1ULL<<63 | 1ULL<<62 | 1ULL<<61 | \
+ 1ULL<<59 | 1ULL<<58 | 1ULL<<56 | \
+ 1ULL<<55 | 1ULL<<54 | 1ULL<<53 | \
+ 1ULL<<52 | 1ULL<<47 | 1ULL<<46 | \
+ 1ULL<<45 | 1ULL<<44)
#define MCCK_CODE_SYSTEM_DAMAGE _BITUL(63)
+#define MCCK_CODE_EXT_DAMAGE _BITUL(63 - 5)
+#define MCCK_CODE_CP _BITUL(63 - 9)
#define MCCK_CODE_CPU_TIMER_VALID _BITUL(63 - 46)
#define MCCK_CODE_PSW_MWP_VALID _BITUL(63 - 20)
#define MCCK_CODE_PSW_IA_VALID _BITUL(63 - 23)
+#define MCCK_CR14_CR_PENDING_SUB_MASK (1 << 28)
+#define MCCK_CR14_RECOVERY_SUB_MASK (1 << 27)
+#define MCCK_CR14_DEGRAD_SUB_MASK (1 << 26)
+#define MCCK_CR14_EXT_DAMAGE_SUB_MASK (1 << 25)
+#define MCCK_CR14_WARN_SUB_MASK (1 << 24)
+
#ifndef __ASSEMBLY__
union mci {
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index 69b8a41fca84..624deaa44230 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 4e3186649578..f36b4b726057 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 649eb62c52b3..34abcf275799 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 166f703dad7c..bb0ff1bb0c4a 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) = _REGION1_ENTRY | __pa(p4d);
+}
+
+static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud)
{
- pgd_val(*pgd) = _REGION2_ENTRY | __pa(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 e6e3b887bee3..57057fb1cc07 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 60d395fdc864..c25d57e0aad3 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -20,6 +20,7 @@
#define CIF_FPU 4 /* restore FPU registers */
#define CIF_IGNORE_IRQ 5 /* ignore interrupt (for udelay) */
#define CIF_ENABLED_WAIT 6 /* in enabled wait state */
+#define CIF_MCCK_GUEST 7 /* machine check happening in guest */
#define _CIF_MCCK_PENDING _BITUL(CIF_MCCK_PENDING)
#define _CIF_ASCE_PRIMARY _BITUL(CIF_ASCE_PRIMARY)
@@ -28,6 +29,7 @@
#define _CIF_FPU _BITUL(CIF_FPU)
#define _CIF_IGNORE_IRQ _BITUL(CIF_IGNORE_IRQ)
#define _CIF_ENABLED_WAIT _BITUL(CIF_ENABLED_WAIT)
+#define _CIF_MCCK_GUEST _BITUL(CIF_MCCK_GUEST)
#ifndef __ASSEMBLY__
@@ -92,11 +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))
@@ -221,11 +223,6 @@ extern void release_thread(struct task_struct *);
/* Free guarded storage control block for current */
void exit_thread_gs(void);
-/*
- * Return saved PC of a blocked thread.
- */
-extern unsigned long thread_saved_pc(struct task_struct *t);
-
unsigned long get_wchan(struct task_struct *p);
#define task_pt_regs(tsk) ((struct pt_regs *) \
(task_stack_page(tsk) + THREAD_SIZE) - 1)
diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h
index 99bc456cc26a..853b01245c20 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 72df5f2de6b0..020a8814d511 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/syscall.h b/arch/s390/include/asm/syscall.h
index 6ba0bf928909..6bc941be6921 100644
--- a/arch/s390/include/asm/syscall.h
+++ b/arch/s390/include/asm/syscall.h
@@ -64,6 +64,12 @@ static inline void syscall_get_arguments(struct task_struct *task,
{
unsigned long mask = -1UL;
+ /*
+ * No arguments for this syscall, there's nothing to do.
+ */
+ if (!n)
+ return;
+
BUG_ON(i + n > 6);
#ifdef CONFIG_COMPAT
if (test_tsk_thread_flag(task, TIF_31BIT))
diff --git a/arch/s390/include/asm/sysinfo.h b/arch/s390/include/asm/sysinfo.h
index 73bff45ced55..2b498e58b914 100644
--- a/arch/s390/include/asm/sysinfo.h
+++ b/arch/s390/include/asm/sysinfo.h
@@ -109,7 +109,7 @@ struct sysinfo_2_2_2 {
unsigned short cpus_shared;
char reserved_4[3];
unsigned char vsne;
- uuid_be uuid;
+ uuid_t uuid;
char reserved_5[160];
char ext_name[256];
};
@@ -134,7 +134,7 @@ struct sysinfo_3_2_2 {
char reserved_1[3];
unsigned char evmne;
unsigned int reserved_2;
- uuid_be uuid;
+ uuid_t uuid;
} vm[8];
char reserved_3[1504];
char ext_names[8][256];
@@ -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 0b3ee083a665..1aecf432c48d 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 853b2a3d8dee..7317b3108a88 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/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index fad9df965ec2..304cfe44df50 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -273,23 +273,6 @@ static inline unsigned long strnlen_user(const char __user *src, unsigned long n
return __strnlen_user(src, n);
}
-/**
- * strlen_user: - Get the size of a string in user space.
- * @str: The string to measure.
- *
- * Context: User context only. This function may sleep if pagefaults are
- * enabled.
- *
- * Get the size of a NUL-terminated string in user space.
- *
- * Returns the size of the string INCLUDING the terminating NUL.
- * On exception, returns 0.
- *
- * If there is a limit on the length of a valid string, you may wish to
- * consider using strnlen_user() instead.
- */
-#define strlen_user(str) strnlen_user(str, ~0UL)
-
/*
* Zero Userspace
*/
diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h
index 3dd2a1d308dd..69d09c39bbcd 100644
--- a/arch/s390/include/uapi/asm/kvm.h
+++ b/arch/s390/include/uapi/asm/kvm.h
@@ -28,6 +28,7 @@
#define KVM_DEV_FLIC_CLEAR_IO_IRQ 8
#define KVM_DEV_FLIC_AISM 9
#define KVM_DEV_FLIC_AIRQ_INJECT 10
+#define KVM_DEV_FLIC_AISM_ALL 11
/*
* We can have up to 4*64k pending subchannels + 8 adapter interrupts,
* as well as up to ASYNC_PF_PER_VCPU*KVM_MAX_VCPUS pfault done interrupts.
@@ -53,6 +54,11 @@ struct kvm_s390_ais_req {
__u16 mode;
};
+struct kvm_s390_ais_all {
+ __u8 simm;
+ __u8 nimm;
+};
+
#define KVM_S390_IO_ADAPTER_MASK 1
#define KVM_S390_IO_ADAPTER_MAP 2
#define KVM_S390_IO_ADAPTER_UNMAP 3
@@ -70,6 +76,7 @@ struct kvm_s390_io_adapter_req {
#define KVM_S390_VM_TOD 1
#define KVM_S390_VM_CRYPTO 2
#define KVM_S390_VM_CPU_MODEL 3
+#define KVM_S390_VM_MIGRATION 4
/* kvm attributes for mem_ctrl */
#define KVM_S390_VM_MEM_ENABLE_CMMA 0
@@ -151,6 +158,11 @@ struct kvm_s390_vm_cpu_subfunc {
#define KVM_S390_VM_CRYPTO_DISABLE_AES_KW 2
#define KVM_S390_VM_CRYPTO_DISABLE_DEA_KW 3
+/* kvm attributes for migration mode */
+#define KVM_S390_VM_MIGRATION_STOP 0
+#define KVM_S390_VM_MIGRATION_START 1
+#define KVM_S390_VM_MIGRATION_STATUS 2
+
/* for KVM_GET_REGS and KVM_SET_REGS */
struct kvm_regs {
/* general purpose regs for s390 */
diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h
index e8e5ecf673fd..52a63f4175cb 100644
--- a/arch/s390/include/uapi/asm/socket.h
+++ b/arch/s390/include/uapi/asm/socket.h
@@ -104,4 +104,8 @@
#define SO_COOKIE 57
+#define SCM_TIMESTAMPING_PKTINFO 58
+
+#define SO_PEERGROUPS 59
+
#endif /* _ASM_SOCKET_H */
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index 6bb29633e1f1..b65c414b6c0e 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -58,6 +58,9 @@ int main(void)
OFFSET(__SF_BACKCHAIN, stack_frame, back_chain);
OFFSET(__SF_GPRS, stack_frame, gprs);
OFFSET(__SF_EMPTY, stack_frame, empty1);
+ OFFSET(__SF_SIE_CONTROL, stack_frame, empty1[0]);
+ OFFSET(__SF_SIE_SAVEAREA, stack_frame, empty1[1]);
+ OFFSET(__SF_SIE_REASON, stack_frame, empty1[2]);
BLANK();
/* timeval/timezone offsets for use by vdso */
OFFSET(__VDSO_UPD_COUNT, vdso_data, tb_update_count);
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index 530226b6cb19..86b3e74f569e 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/diag.c b/arch/s390/kernel/diag.c
index ac6abcd3fe6a..349914571772 100644
--- a/arch/s390/kernel/diag.c
+++ b/arch/s390/kernel/diag.c
@@ -38,6 +38,7 @@ static const struct diag_desc diag_map[NR_DIAG_STAT] = {
[DIAG_STAT_X224] = { .code = 0x224, .name = "EBCDIC-Name Table" },
[DIAG_STAT_X250] = { .code = 0x250, .name = "Block I/O" },
[DIAG_STAT_X258] = { .code = 0x258, .name = "Page-Reference Services" },
+ [DIAG_STAT_X26C] = { .code = 0x26c, .name = "Certain System Information" },
[DIAG_STAT_X288] = { .code = 0x288, .name = "Time Bomb" },
[DIAG_STAT_X2C4] = { .code = 0x2c4, .name = "FTP Services" },
[DIAG_STAT_X2FC] = { .code = 0x2fc, .name = "Guest Performance Data" },
@@ -236,3 +237,31 @@ int diag224(void *ptr)
return rc;
}
EXPORT_SYMBOL(diag224);
+
+/*
+ * Diagnose 26C: Access Certain System Information
+ */
+static inline int __diag26c(void *req, void *resp, enum diag26c_sc subcode)
+{
+ register unsigned long _req asm("2") = (addr_t) req;
+ register unsigned long _resp asm("3") = (addr_t) resp;
+ register unsigned long _subcode asm("4") = subcode;
+ register unsigned long _rc asm("5") = -EOPNOTSUPP;
+
+ asm volatile(
+ " sam31\n"
+ " diag %[rx],%[ry],0x26c\n"
+ "0: sam64\n"
+ EX_TABLE(0b,0b)
+ : "+d" (_rc)
+ : [rx] "d" (_req), "d" (_resp), [ry] "d" (_subcode)
+ : "cc", "memory");
+ return _rc;
+}
+
+int diag26c(void *req, void *resp, enum diag26c_sc subcode)
+{
+ diag_stat_inc(DIAG_STAT_X26C);
+ return __diag26c(req, resp, subcode);
+}
+EXPORT_SYMBOL(diag26c);
diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c
index 829e1c53005c..dab78babfab6 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 a5f5d3bb3dbc..21900e1cee9c 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -52,7 +52,7 @@ _TIF_TRACE = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \
_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)
@@ -225,18 +225,24 @@ ENTRY(sie64a)
jnz .Lsie_skip
TSTMSK __LC_CPU_FLAGS,_CIF_FPU
jo .Lsie_skip # exit if fp/vx regs changed
+.Lsie_entry:
sie 0(%r14)
.Lsie_skip:
ni __SIE_PROG0C+3(%r14),0xfe # no longer in SIE
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
@@ -249,7 +255,9 @@ sie_exit:
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)
@@ -312,6 +320,7 @@ ENTRY(system_call)
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)
@@ -326,6 +335,8 @@ ENTRY(system_call)
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
@@ -339,6 +350,8 @@ ENTRY(system_call)
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
@@ -440,6 +453,15 @@ ENTRY(system_call)
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
#
@@ -623,6 +645,7 @@ ENTRY(io_int_handler)
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)
@@ -872,9 +895,7 @@ ENTRY(save_fpu_regs)
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.
@@ -1102,7 +1123,13 @@ cleanup_critical:
.quad .Lsie_done
.Lcleanup_sie:
- lg %r9,__SF_EMPTY(%r15) # get control block pointer
+ cghi %r11,__LC_SAVE_AREA_ASYNC #Is this in normal interrupt?
+ je 1f
+ slg %r9,BASED(.Lsie_crit_mcck_start)
+ clg %r9,BASED(.Lsie_crit_mcck_length)
+ jh 1f
+ oi __LC_CPU_FLAGS+7, _CIF_MCCK_GUEST
+1: lg %r9,__SF_EMPTY(%r15) # get control block pointer
ni __SIE_PROG0C+3(%r9),0xfe # no longer in SIE
lctlg %c1,%c1,__LC_USER_ASCE # load primary asce
larl %r9,sie_exit # skip forward to sie_exit
@@ -1174,15 +1201,23 @@ cleanup_critical:
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:
@@ -1190,15 +1225,20 @@ cleanup_critical:
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:
@@ -1274,6 +1314,10 @@ cleanup_critical:
.quad .Lsie_gmap
.Lsie_critical_length:
.quad .Lsie_done - .Lsie_gmap
+.Lsie_crit_mcck_start:
+ .quad .Lsie_entry
+.Lsie_crit_mcck_length:
+ .quad .Lsie_skip - .Lsie_entry
#endif
.section .rodata, "a"
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 27477f34cc0a..d03a6d12c4bd 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 e545ffe5155a..8e622bb52f7a 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/jump_label.c b/arch/s390/kernel/jump_label.c
index 6aa630a8d24f..262506cee4c3 100644
--- a/arch/s390/kernel/jump_label.c
+++ b/arch/s390/kernel/jump_label.c
@@ -93,7 +93,7 @@ void arch_jump_label_transform(struct jump_entry *entry,
args.entry = entry;
args.type = type;
- stop_machine(__sm_arch_jump_label_transform, &args, NULL);
+ stop_machine_cpuslocked(__sm_arch_jump_label_transform, &args, NULL);
}
void arch_jump_label_transform_static(struct jump_entry *entry,
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 3d6a99746454..6842e4501e2e 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -196,7 +196,7 @@ void arch_arm_kprobe(struct kprobe *p)
{
struct swap_insn_args args = {.p = p, .arm_kprobe = 1};
- stop_machine(swap_instruction, &args, NULL);
+ stop_machine_cpuslocked(swap_instruction, &args, NULL);
}
NOKPROBE_SYMBOL(arch_arm_kprobe);
@@ -204,7 +204,7 @@ void arch_disarm_kprobe(struct kprobe *p)
{
struct swap_insn_args args = {.p = p, .arm_kprobe = 0};
- stop_machine(swap_instruction, &args, NULL);
+ stop_machine_cpuslocked(swap_instruction, &args, NULL);
}
NOKPROBE_SYMBOL(arch_disarm_kprobe);
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index 49a6bd45957b..3d0b14afa232 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -246,6 +246,7 @@ void arch_crash_save_vmcoreinfo(void)
VMCOREINFO_SYMBOL(lowcore_ptr);
VMCOREINFO_SYMBOL(high_memory);
VMCOREINFO_LENGTH(lowcore_ptr, NR_CPUS);
+ mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note());
}
void machine_shutdown(void)
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index 985589523970..31d03a84126c 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -25,6 +25,8 @@
#include <asm/crw.h>
#include <asm/switch_to.h>
#include <asm/ctl_reg.h>
+#include <asm/asm-offsets.h>
+#include <linux/kvm_host.h>
struct mcck_struct {
unsigned int kill_task : 1;
@@ -274,12 +276,39 @@ static int notrace s390_validate_registers(union mci mci, int umode)
return kill_task;
}
+/*
+ * Backup the guest's machine check info to its description block
+ */
+static void notrace s390_backup_mcck_info(struct pt_regs *regs)
+{
+ struct mcck_volatile_info *mcck_backup;
+ struct sie_page *sie_page;
+
+ /* r14 contains the sie block, which was set in sie64a */
+ struct kvm_s390_sie_block *sie_block =
+ (struct kvm_s390_sie_block *) regs->gprs[14];
+
+ if (sie_block == NULL)
+ /* Something's seriously wrong, stop system. */
+ s390_handle_damage();
+
+ sie_page = container_of(sie_block, struct sie_page, sie_block);
+ mcck_backup = &sie_page->mcck_info;
+ mcck_backup->mcic = S390_lowcore.mcck_interruption_code &
+ ~(MCCK_CODE_CP | MCCK_CODE_EXT_DAMAGE);
+ mcck_backup->ext_damage_code = S390_lowcore.external_damage_code;
+ mcck_backup->failing_storage_address
+ = S390_lowcore.failing_storage_address;
+}
+
#define MAX_IPD_COUNT 29
#define MAX_IPD_TIME (5 * 60 * USEC_PER_SEC) /* 5 minutes */
#define ED_STP_ISLAND 6 /* External damage STP island check */
#define ED_STP_SYNC 7 /* External damage STP sync check */
+#define MCCK_CODE_NO_GUEST (MCCK_CODE_CP | MCCK_CODE_EXT_DAMAGE)
+
/*
* machine check handler.
*/
@@ -291,6 +320,7 @@ void notrace s390_do_machine_check(struct pt_regs *regs)
struct mcck_struct *mcck;
unsigned long long tmp;
union mci mci;
+ unsigned long mcck_dam_code;
nmi_enter();
inc_irq_stat(NMI_NMI);
@@ -301,7 +331,13 @@ void notrace s390_do_machine_check(struct pt_regs *regs)
/* System damage -> stopping machine */
s390_handle_damage();
}
- if (mci.pd) {
+
+ /*
+ * Reinject the instruction processing damages' machine checks
+ * including Delayed Access Exception into the guest
+ * instead of damaging the host if they happen in the guest.
+ */
+ if (mci.pd && !test_cpu_flag(CIF_MCCK_GUEST)) {
if (mci.b) {
/* Processing backup -> verify if we can survive this */
u64 z_mcic, o_mcic, t_mcic;
@@ -345,6 +381,14 @@ void notrace s390_do_machine_check(struct pt_regs *regs)
mcck->mcck_code = mci.val;
set_cpu_flag(CIF_MCCK_PENDING);
}
+
+ /*
+ * Backup the machine check's info if it happens when the guest
+ * is running.
+ */
+ if (test_cpu_flag(CIF_MCCK_GUEST))
+ s390_backup_mcck_info(regs);
+
if (mci.cd) {
/* Timing facility damage */
s390_handle_damage();
@@ -358,15 +402,22 @@ void notrace s390_do_machine_check(struct pt_regs *regs)
if (mcck->stp_queue)
set_cpu_flag(CIF_MCCK_PENDING);
}
- if (mci.se)
- /* Storage error uncorrected */
- s390_handle_damage();
- if (mci.ke)
- /* Storage key-error uncorrected */
- s390_handle_damage();
- if (mci.ds && mci.fa)
- /* Storage degradation */
- s390_handle_damage();
+
+ /*
+ * Reinject storage related machine checks into the guest if they
+ * happen when the guest is running.
+ */
+ if (!test_cpu_flag(CIF_MCCK_GUEST)) {
+ if (mci.se)
+ /* Storage error uncorrected */
+ s390_handle_damage();
+ if (mci.ke)
+ /* Storage key-error uncorrected */
+ s390_handle_damage();
+ if (mci.ds && mci.fa)
+ /* Storage degradation */
+ s390_handle_damage();
+ }
if (mci.cp) {
/* Channel report word pending */
mcck->channel_report = 1;
@@ -377,6 +428,19 @@ void notrace s390_do_machine_check(struct pt_regs *regs)
mcck->warning = 1;
set_cpu_flag(CIF_MCCK_PENDING);
}
+
+ /*
+ * If there are only Channel Report Pending and External Damage
+ * machine checks, they will not be reinjected into the guest
+ * because they refer to host conditions only.
+ */
+ mcck_dam_code = (mci.val & MCIC_SUBCLASS_MASK);
+ if (test_cpu_flag(CIF_MCCK_GUEST) &&
+ (mcck_dam_code & MCCK_CODE_NO_GUEST) != mcck_dam_code) {
+ /* Set exit reason code for host's later handling */
+ *((long *)(regs->gprs[15] + __SF_SIE_REASON)) = -EINTR;
+ }
+ clear_cpu_flag(CIF_MCCK_GUEST);
nmi_exit();
}
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index ca960d0370d5..0c82f7903fc7 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 *) &regs.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 955a7b6fa0a4..93a386f4a3b5 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/process.c b/arch/s390/kernel/process.c
index 999d7154bbdc..bb32b8618bf6 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -41,31 +41,6 @@
asmlinkage void ret_from_fork(void) asm ("ret_from_fork");
-/*
- * Return saved PC of a blocked thread. used in kernel/sched.
- * resume in entry.S does not create a new stack frame, it
- * just stores the registers %r6-%r15 to the frame given by
- * schedule. We want to return the address of the caller of
- * schedule, so we have to walk the backchain one time to
- * find the frame schedule() store its return address.
- */
-unsigned long thread_saved_pc(struct task_struct *tsk)
-{
- struct stack_frame *sf, *low, *high;
-
- if (!tsk || !task_stack_page(tsk))
- return 0;
- low = task_stack_page(tsk);
- high = (struct stack_frame *) task_pt_regs(tsk);
- sf = (struct stack_frame *) tsk->thread.ksp;
- if (sf <= low || sf > high)
- return 0;
- sf = (struct stack_frame *) sf->back_chain;
- if (sf <= low || sf > high)
- return 0;
- return sf->gprs[8];
-}
-
extern void kernel_thread_starter(void);
/*
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 488c5bb8dc77..252ed61a128b 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/setup.c b/arch/s390/kernel/setup.c
index 3ae756c0db3d..3d1d808ea8a9 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -496,11 +496,6 @@ static void __init setup_memory_end(void)
pr_notice("The maximum memory size is %luMB\n", memory_end >> 20);
}
-static void __init setup_vmcoreinfo(void)
-{
- mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note());
-}
-
#ifdef CONFIG_CRASH_DUMP
/*
@@ -939,7 +934,6 @@ void __init setup_arch(char **cmdline_p)
#endif
setup_resources();
- setup_vmcoreinfo();
setup_lowcore();
smp_fill_possible_mask();
cpu_detect_mhz_feature();
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 363000a77ffc..1020a11a24e5 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/sysinfo.c b/arch/s390/kernel/sysinfo.c
index eefcb54872a5..fb869b103825 100644
--- a/arch/s390/kernel/sysinfo.c
+++ b/arch/s390/kernel/sysinfo.c
@@ -242,7 +242,7 @@ static void print_ext_name(struct seq_file *m, int lvl,
static void print_uuid(struct seq_file *m, int i, struct sysinfo_3_2_2 *info)
{
- if (!memcmp(&info->vm[i].uuid, &NULL_UUID_BE, sizeof(uuid_be)))
+ if (uuid_is_null(&info->vm[i].uuid))
return;
seq_printf(m, "VM%02d UUID: %pUb\n", i, &info->vm[i].uuid);
}
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index c3a52f9a69a0..192efdfac918 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -636,10 +636,10 @@ static void stp_work_fn(struct work_struct *work)
goto out_unlock;
memset(&stp_sync, 0, sizeof(stp_sync));
- get_online_cpus();
+ cpus_read_lock();
atomic_set(&stp_sync.cpus, num_online_cpus() - 1);
- stop_machine(stp_sync_clock, &stp_sync, cpu_online_mask);
- put_online_cpus();
+ stop_machine_cpuslocked(stp_sync_clock, &stp_sync, cpu_online_mask);
+ cpus_read_unlock();
if (!check_sync_clock())
/*
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index f787b9d8f54c..442e5423ce3d 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 314e0ee3016a..d94baa8db507 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 10516ae3b55e..b89d19f6f2ab 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 72307f108c40..6e2c42bd1c3b 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -31,8 +31,14 @@ SECTIONS
{
. = 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 072d84ba42a3..dd7178fbb4f3 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 9da243d94cc3..653cae5e1ee1 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -89,7 +89,7 @@ struct region3_table_entry_fc1 {
unsigned long f : 1; /* Fetch-Protection Bit */
unsigned long fc : 1; /* Format-Control */
unsigned long p : 1; /* DAT-Protection Bit */
- unsigned long co : 1; /* Change-Recording Override */
+ unsigned long iep: 1; /* Instruction-Execution-Protection */
unsigned long : 2;
unsigned long i : 1; /* Region-Invalid Bit */
unsigned long cr : 1; /* Common-Region Bit */
@@ -131,7 +131,7 @@ struct segment_entry_fc1 {
unsigned long f : 1; /* Fetch-Protection Bit */
unsigned long fc : 1; /* Format-Control */
unsigned long p : 1; /* DAT-Protection Bit */
- unsigned long co : 1; /* Change-Recording Override */
+ unsigned long iep: 1; /* Instruction-Execution-Protection */
unsigned long : 2;
unsigned long i : 1; /* Segment-Invalid Bit */
unsigned long cs : 1; /* Common-Segment Bit */
@@ -168,7 +168,8 @@ union page_table_entry {
unsigned long z : 1; /* Zero Bit */
unsigned long i : 1; /* Page-Invalid Bit */
unsigned long p : 1; /* DAT-Protection Bit */
- unsigned long : 9;
+ unsigned long iep: 1; /* Instruction-Execution-Protection */
+ unsigned long : 8;
};
};
@@ -241,7 +242,7 @@ struct ale {
unsigned long asteo : 25; /* ASN-Second-Table-Entry Origin */
unsigned long : 6;
unsigned long astesn : 32; /* ASTE Sequence Number */
-} __packed;
+};
struct aste {
unsigned long i : 1; /* ASX-Invalid Bit */
@@ -257,7 +258,7 @@ struct aste {
unsigned long ald : 32;
unsigned long astesn : 32;
/* .. more fields there */
-} __packed;
+};
int ipte_lock_held(struct kvm_vcpu *vcpu)
{
@@ -485,6 +486,7 @@ enum prot_type {
PROT_TYPE_KEYC = 1,
PROT_TYPE_ALC = 2,
PROT_TYPE_DAT = 3,
+ PROT_TYPE_IEP = 4,
};
static int trans_exc(struct kvm_vcpu *vcpu, int code, unsigned long gva,
@@ -500,6 +502,9 @@ static int trans_exc(struct kvm_vcpu *vcpu, int code, unsigned long gva,
switch (code) {
case PGM_PROTECTION:
switch (prot) {
+ case PROT_TYPE_IEP:
+ tec->b61 = 1;
+ /* FALL THROUGH */
case PROT_TYPE_LA:
tec->b56 = 1;
break;
@@ -551,26 +556,26 @@ 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);
@@ -591,6 +596,7 @@ static int deref_table(struct kvm *kvm, unsigned long gpa, unsigned long *val)
* @gpa: points to where guest physical (absolute) address should be stored
* @asce: effective asce
* @mode: indicates the access mode to be used
+ * @prot: returns the type for protection exceptions
*
* Translate a guest virtual address into a guest absolute address by means
* of dynamic address translation as specified by the architecture.
@@ -606,19 +612,21 @@ static int deref_table(struct kvm *kvm, unsigned long gpa, unsigned long *val)
*/
static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva,
unsigned long *gpa, const union asce asce,
- enum gacc_mode mode)
+ enum gacc_mode mode, enum prot_type *prot)
{
union vaddress vaddr = {.addr = gva};
union raddress raddr = {.addr = gva};
union page_table_entry pte;
int dat_protection = 0;
+ int iep_protection = 0;
union ctlreg0 ctlreg0;
unsigned long ptr;
- int edat1, edat2;
+ int edat1, edat2, iep;
ctlreg0.val = vcpu->arch.sie_block->gcr[0];
edat1 = ctlreg0.edat && test_kvm_facility(vcpu->kvm, 8);
edat2 = edat1 && test_kvm_facility(vcpu->kvm, 78);
+ iep = ctlreg0.iep && test_kvm_facility(vcpu->kvm, 130);
if (asce.r)
goto real_address;
ptr = asce.origin * 4096;
@@ -702,6 +710,7 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva,
return PGM_TRANSLATION_SPEC;
if (rtte.fc && edat2) {
dat_protection |= rtte.fc1.p;
+ iep_protection = rtte.fc1.iep;
raddr.rfaa = rtte.fc1.rfaa;
goto absolute_address;
}
@@ -729,6 +738,7 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva,
return PGM_TRANSLATION_SPEC;
if (ste.fc && edat1) {
dat_protection |= ste.fc1.p;
+ iep_protection = ste.fc1.iep;
raddr.sfaa = ste.fc1.sfaa;
goto absolute_address;
}
@@ -745,12 +755,19 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva,
if (pte.z)
return PGM_TRANSLATION_SPEC;
dat_protection |= pte.p;
+ iep_protection = pte.iep;
raddr.pfra = pte.pfra;
real_address:
raddr.addr = kvm_s390_real_to_abs(vcpu, raddr.addr);
absolute_address:
- if (mode == GACC_STORE && dat_protection)
+ if (mode == GACC_STORE && dat_protection) {
+ *prot = PROT_TYPE_DAT;
return PGM_PROTECTION;
+ }
+ if (mode == GACC_IFETCH && iep_protection && iep) {
+ *prot = PROT_TYPE_IEP;
+ return PGM_PROTECTION;
+ }
if (kvm_is_error_gpa(vcpu->kvm, raddr.addr))
return PGM_ADDRESSING;
*gpa = raddr.addr;
@@ -771,7 +788,7 @@ 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;
}
@@ -782,6 +799,7 @@ static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar,
{
psw_t *psw = &vcpu->arch.sie_block->gpsw;
int lap_enabled, rc = 0;
+ enum prot_type prot;
lap_enabled = low_address_protection_enabled(vcpu, asce);
while (nr_pages) {
@@ -790,8 +808,8 @@ 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) {
- rc = guest_translate(vcpu, ga, pages, asce, mode);
+ if (psw_bits(*psw).dat) {
+ rc = guest_translate(vcpu, ga, pages, asce, mode, &prot);
if (rc < 0)
return rc;
} else {
@@ -800,7 +818,7 @@ static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar,
rc = PGM_ADDRESSING;
}
if (rc)
- return trans_exc(vcpu, rc, ga, ar, mode, PROT_TYPE_DAT);
+ return trans_exc(vcpu, rc, ga, ar, mode, prot);
ga += PAGE_SIZE;
pages++;
nr_pages--;
@@ -831,7 +849,7 @@ 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);
@@ -886,6 +904,7 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
unsigned long *gpa, enum gacc_mode mode)
{
psw_t *psw = &vcpu->arch.sie_block->gpsw;
+ enum prot_type prot;
union asce asce;
int rc;
@@ -899,10 +918,10 @@ 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? */
- rc = guest_translate(vcpu, gva, gpa, asce, mode);
+ if (psw_bits(*psw).dat && !asce.r) { /* Use DAT? */
+ rc = guest_translate(vcpu, gva, gpa, asce, mode, &prot);
if (rc > 0)
- return trans_exc(vcpu, rc, gva, 0, mode, PROT_TYPE_DAT);
+ return trans_exc(vcpu, rc, gva, 0, mode, prot);
} else {
*gpa = kvm_s390_real_to_abs(vcpu, gva);
if (kvm_is_error_gpa(vcpu->kvm, *gpa))
@@ -977,11 +996,12 @@ static int kvm_s390_shadow_tables(struct gmap *sg, unsigned long saddr,
ptr = asce.origin * 4096;
if (asce.r) {
*fake = 1;
+ ptr = 0;
asce.dt = ASCE_TYPE_REGION1;
}
switch (asce.dt) {
case ASCE_TYPE_REGION1:
- if (vaddr.rfx01 > asce.tl && !asce.r)
+ if (vaddr.rfx01 > asce.tl && !*fake)
return PGM_REGION_FIRST_TRANS;
break;
case ASCE_TYPE_REGION2:
@@ -1009,8 +1029,7 @@ static int kvm_s390_shadow_tables(struct gmap *sg, unsigned long saddr,
union region1_table_entry rfte;
if (*fake) {
- /* offset in 16EB guest memory block */
- ptr = ptr + ((unsigned long) vaddr.rsx << 53UL);
+ ptr += (unsigned long) vaddr.rfx << 53;
rfte.val = ptr;
goto shadow_r2t;
}
@@ -1036,8 +1055,7 @@ shadow_r2t:
union region2_table_entry rste;
if (*fake) {
- /* offset in 8PB guest memory block */
- ptr = ptr + ((unsigned long) vaddr.rtx << 42UL);
+ ptr += (unsigned long) vaddr.rsx << 42;
rste.val = ptr;
goto shadow_r3t;
}
@@ -1064,8 +1082,7 @@ shadow_r3t:
union region3_table_entry rtte;
if (*fake) {
- /* offset in 4TB guest memory block */
- ptr = ptr + ((unsigned long) vaddr.sx << 31UL);
+ ptr += (unsigned long) vaddr.rtx << 31;
rtte.val = ptr;
goto shadow_sgt;
}
@@ -1101,8 +1118,7 @@ shadow_sgt:
union segment_table_entry ste;
if (*fake) {
- /* offset in 2G guest memory block */
- ptr = ptr + ((unsigned long) vaddr.sx << 20UL);
+ ptr += (unsigned long) vaddr.sx << 20;
ste.val = ptr;
goto shadow_pgt;
}
diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h
index 7ce47fd36f28..bec42b852246 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 23d9a4e12da1..c2e0ddc1356e 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/interrupt.c b/arch/s390/kvm/interrupt.c
index caf15c8a8948..a619ddae610d 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -251,8 +251,13 @@ static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu)
__clear_bit(IRQ_PEND_EXT_SERVICE, &active_mask);
if (psw_mchk_disabled(vcpu))
active_mask &= ~IRQ_PEND_MCHK_MASK;
+ /*
+ * Check both floating and local interrupt's cr14 because
+ * bit IRQ_PEND_MCHK_REP could be set in both cases.
+ */
if (!(vcpu->arch.sie_block->gcr[14] &
- vcpu->kvm->arch.float_int.mchk.cr14))
+ (vcpu->kvm->arch.float_int.mchk.cr14 |
+ vcpu->arch.local_int.irq.mchk.cr14)))
__clear_bit(IRQ_PEND_MCHK_REP, &active_mask);
/*
@@ -1876,6 +1881,28 @@ out:
return ret < 0 ? ret : n;
}
+static int flic_ais_mode_get_all(struct kvm *kvm, struct kvm_device_attr *attr)
+{
+ struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;
+ struct kvm_s390_ais_all ais;
+
+ if (attr->attr < sizeof(ais))
+ return -EINVAL;
+
+ if (!test_kvm_facility(kvm, 72))
+ return -ENOTSUPP;
+
+ mutex_lock(&fi->ais_lock);
+ ais.simm = fi->simm;
+ ais.nimm = fi->nimm;
+ mutex_unlock(&fi->ais_lock);
+
+ if (copy_to_user((void __user *)attr->addr, &ais, sizeof(ais)))
+ return -EFAULT;
+
+ return 0;
+}
+
static int flic_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
{
int r;
@@ -1885,6 +1912,9 @@ static int flic_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
r = get_all_floating_irqs(dev->kvm, (u8 __user *) attr->addr,
attr->attr);
break;
+ case KVM_DEV_FLIC_AISM_ALL:
+ r = flic_ais_mode_get_all(dev->kvm, attr);
+ break;
default:
r = -EINVAL;
}
@@ -2160,7 +2190,7 @@ static int modify_ais_mode(struct kvm *kvm, struct kvm_device_attr *attr)
struct kvm_s390_ais_req req;
int ret = 0;
- if (!fi->ais_enabled)
+ if (!test_kvm_facility(kvm, 72))
return -ENOTSUPP;
if (copy_from_user(&req, (void __user *)attr->addr, sizeof(req)))
@@ -2204,7 +2234,7 @@ static int kvm_s390_inject_airq(struct kvm *kvm,
};
int ret = 0;
- if (!fi->ais_enabled || !adapter->suppressible)
+ if (!test_kvm_facility(kvm, 72) || !adapter->suppressible)
return kvm_s390_inject_vm(kvm, &s390int);
mutex_lock(&fi->ais_lock);
@@ -2235,6 +2265,25 @@ static int flic_inject_airq(struct kvm *kvm, struct kvm_device_attr *attr)
return kvm_s390_inject_airq(kvm, adapter);
}
+static int flic_ais_mode_set_all(struct kvm *kvm, struct kvm_device_attr *attr)
+{
+ struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;
+ struct kvm_s390_ais_all ais;
+
+ if (!test_kvm_facility(kvm, 72))
+ return -ENOTSUPP;
+
+ if (copy_from_user(&ais, (void __user *)attr->addr, sizeof(ais)))
+ return -EFAULT;
+
+ mutex_lock(&fi->ais_lock);
+ fi->simm = ais.simm;
+ fi->nimm = ais.nimm;
+ mutex_unlock(&fi->ais_lock);
+
+ return 0;
+}
+
static int flic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
{
int r = 0;
@@ -2277,6 +2326,9 @@ static int flic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
case KVM_DEV_FLIC_AIRQ_INJECT:
r = flic_inject_airq(dev->kvm, attr);
break;
+ case KVM_DEV_FLIC_AISM_ALL:
+ r = flic_ais_mode_set_all(dev->kvm, attr);
+ break;
default:
r = -EINVAL;
}
@@ -2298,6 +2350,7 @@ static int flic_has_attr(struct kvm_device *dev,
case KVM_DEV_FLIC_CLEAR_IO_IRQ:
case KVM_DEV_FLIC_AISM:
case KVM_DEV_FLIC_AIRQ_INJECT:
+ case KVM_DEV_FLIC_AISM_ALL:
return 0;
}
return -ENXIO;
@@ -2415,6 +2468,42 @@ static int set_adapter_int(struct kvm_kernel_irq_routing_entry *e,
return ret;
}
+/*
+ * Inject the machine check to the guest.
+ */
+void kvm_s390_reinject_machine_check(struct kvm_vcpu *vcpu,
+ struct mcck_volatile_info *mcck_info)
+{
+ struct kvm_s390_interrupt_info inti;
+ struct kvm_s390_irq irq;
+ struct kvm_s390_mchk_info *mchk;
+ union mci mci;
+ __u64 cr14 = 0; /* upper bits are not used */
+
+ mci.val = mcck_info->mcic;
+ if (mci.sr)
+ cr14 |= MCCK_CR14_RECOVERY_SUB_MASK;
+ if (mci.dg)
+ cr14 |= MCCK_CR14_DEGRAD_SUB_MASK;
+ if (mci.w)
+ cr14 |= MCCK_CR14_WARN_SUB_MASK;
+
+ mchk = mci.ck ? &inti.mchk : &irq.u.mchk;
+ mchk->cr14 = cr14;
+ mchk->mcic = mcck_info->mcic;
+ mchk->ext_damage_code = mcck_info->ext_damage_code;
+ mchk->failing_storage_address = mcck_info->failing_storage_address;
+ if (mci.ck) {
+ /* Inject the floating machine check */
+ inti.type = KVM_S390_MCHK;
+ WARN_ON_ONCE(__inject_vm(vcpu->kvm, &inti));
+ } else {
+ /* Inject the machine check to specified vcpu */
+ irq.type = KVM_S390_MCHK;
+ WARN_ON_ONCE(kvm_s390_inject_vcpu(vcpu, &irq));
+ }
+}
+
int kvm_set_routing_entry(struct kvm *kvm,
struct kvm_kernel_irq_routing_entry *e,
const struct kvm_irq_routing_entry *ue)
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 689ac48361c6..3f2884e99ed4 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -30,6 +30,7 @@
#include <linux/vmalloc.h>
#include <linux/bitmap.h>
#include <linux/sched/signal.h>
+#include <linux/string.h>
#include <asm/asm-offsets.h>
#include <asm/lowcore.h>
@@ -386,6 +387,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_S390_SKEYS:
case KVM_CAP_S390_IRQ_STATE:
case KVM_CAP_S390_USER_INSTR0:
+ case KVM_CAP_S390_CMMA_MIGRATION:
case KVM_CAP_S390_AIS:
r = 1;
break;
@@ -558,7 +560,6 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
} else {
set_kvm_facility(kvm->arch.model.fac_mask, 72);
set_kvm_facility(kvm->arch.model.fac_list, 72);
- kvm->arch.float_int.ais_enabled = 1;
r = 0;
}
mutex_unlock(&kvm->lock);
@@ -750,6 +751,129 @@ static int kvm_s390_vm_set_crypto(struct kvm *kvm, struct kvm_device_attr *attr)
return 0;
}
+static void kvm_s390_sync_request_broadcast(struct kvm *kvm, int req)
+{
+ int cx;
+ struct kvm_vcpu *vcpu;
+
+ kvm_for_each_vcpu(cx, vcpu, kvm)
+ kvm_s390_sync_request(req, vcpu);
+}
+
+/*
+ * Must be called with kvm->srcu held to avoid races on memslots, and with
+ * kvm->lock to avoid races with ourselves and kvm_s390_vm_stop_migration.
+ */
+static int kvm_s390_vm_start_migration(struct kvm *kvm)
+{
+ struct kvm_s390_migration_state *mgs;
+ struct kvm_memory_slot *ms;
+ /* should be the only one */
+ struct kvm_memslots *slots;
+ unsigned long ram_pages;
+ int slotnr;
+
+ /* migration mode already enabled */
+ if (kvm->arch.migration_state)
+ return 0;
+
+ slots = kvm_memslots(kvm);
+ if (!slots || !slots->used_slots)
+ return -EINVAL;
+
+ mgs = kzalloc(sizeof(*mgs), GFP_KERNEL);
+ if (!mgs)
+ return -ENOMEM;
+ kvm->arch.migration_state = mgs;
+
+ if (kvm->arch.use_cmma) {
+ /*
+ * Get the last slot. They should be sorted by base_gfn, so the
+ * last slot is also the one at the end of the address space.
+ * We have verified above that at least one slot is present.
+ */
+ ms = slots->memslots + slots->used_slots - 1;
+ /* round up so we only use full longs */
+ ram_pages = roundup(ms->base_gfn + ms->npages, BITS_PER_LONG);
+ /* allocate enough bytes to store all the bits */
+ mgs->pgste_bitmap = vmalloc(ram_pages / 8);
+ if (!mgs->pgste_bitmap) {
+ kfree(mgs);
+ kvm->arch.migration_state = NULL;
+ return -ENOMEM;
+ }
+
+ mgs->bitmap_size = ram_pages;
+ atomic64_set(&mgs->dirty_pages, ram_pages);
+ /* mark all the pages in active slots as dirty */
+ for (slotnr = 0; slotnr < slots->used_slots; slotnr++) {
+ ms = slots->memslots + slotnr;
+ bitmap_set(mgs->pgste_bitmap, ms->base_gfn, ms->npages);
+ }
+
+ kvm_s390_sync_request_broadcast(kvm, KVM_REQ_START_MIGRATION);
+ }
+ return 0;
+}
+
+/*
+ * Must be called with kvm->lock to avoid races with ourselves and
+ * kvm_s390_vm_start_migration.
+ */
+static int kvm_s390_vm_stop_migration(struct kvm *kvm)
+{
+ struct kvm_s390_migration_state *mgs;
+
+ /* migration mode already disabled */
+ if (!kvm->arch.migration_state)
+ return 0;
+ mgs = kvm->arch.migration_state;
+ kvm->arch.migration_state = NULL;
+
+ if (kvm->arch.use_cmma) {
+ kvm_s390_sync_request_broadcast(kvm, KVM_REQ_STOP_MIGRATION);
+ vfree(mgs->pgste_bitmap);
+ }
+ kfree(mgs);
+ return 0;
+}
+
+static int kvm_s390_vm_set_migration(struct kvm *kvm,
+ struct kvm_device_attr *attr)
+{
+ int idx, res = -ENXIO;
+
+ mutex_lock(&kvm->lock);
+ switch (attr->attr) {
+ case KVM_S390_VM_MIGRATION_START:
+ idx = srcu_read_lock(&kvm->srcu);
+ res = kvm_s390_vm_start_migration(kvm);
+ srcu_read_unlock(&kvm->srcu, idx);
+ break;
+ case KVM_S390_VM_MIGRATION_STOP:
+ res = kvm_s390_vm_stop_migration(kvm);
+ break;
+ default:
+ break;
+ }
+ mutex_unlock(&kvm->lock);
+
+ return res;
+}
+
+static int kvm_s390_vm_get_migration(struct kvm *kvm,
+ struct kvm_device_attr *attr)
+{
+ u64 mig = (kvm->arch.migration_state != NULL);
+
+ if (attr->attr != KVM_S390_VM_MIGRATION_STATUS)
+ return -ENXIO;
+
+ if (copy_to_user((void __user *)attr->addr, &mig, sizeof(mig)))
+ return -EFAULT;
+ return 0;
+}
+
static int kvm_s390_set_tod_high(struct kvm *kvm, struct kvm_device_attr *attr)
{
u8 gtod_high;
@@ -1090,6 +1214,9 @@ static int kvm_s390_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr)
case KVM_S390_VM_CRYPTO:
ret = kvm_s390_vm_set_crypto(kvm, attr);
break;
+ case KVM_S390_VM_MIGRATION:
+ ret = kvm_s390_vm_set_migration(kvm, attr);
+ break;
default:
ret = -ENXIO;
break;
@@ -1112,6 +1239,9 @@ static int kvm_s390_vm_get_attr(struct kvm *kvm, struct kvm_device_attr *attr)
case KVM_S390_VM_CPU_MODEL:
ret = kvm_s390_get_cpu_model(kvm, attr);
break;
+ case KVM_S390_VM_MIGRATION:
+ ret = kvm_s390_vm_get_migration(kvm, attr);
+ break;
default:
ret = -ENXIO;
break;
@@ -1179,6 +1309,9 @@ static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr)
break;
}
break;
+ case KVM_S390_VM_MIGRATION:
+ ret = 0;
+ break;
default:
ret = -ENXIO;
break;
@@ -1286,6 +1419,182 @@ out:
return r;
}
+/*
+ * Base address and length must be sent at the start of each block, therefore
+ * it's cheaper to send some clean data, as long as it's less than the size of
+ * two longs.
+ */
+#define KVM_S390_MAX_BIT_DISTANCE (2 * sizeof(void *))
+/* for consistency */
+#define KVM_S390_CMMA_SIZE_MAX ((u32)KVM_S390_SKEYS_MAX)
+
+/*
+ * This function searches for the next page with dirty CMMA attributes, and
+ * saves the attributes in the buffer up to either the end of the buffer or
+ * until a block of at least KVM_S390_MAX_BIT_DISTANCE clean bits is found;
+ * no trailing clean bytes are saved.
+ * In case no dirty bits were found, or if CMMA was not enabled or used, the
+ * output buffer will indicate 0 as length.
+ */
+static int kvm_s390_get_cmma_bits(struct kvm *kvm,
+ struct kvm_s390_cmma_log *args)
+{
+ struct kvm_s390_migration_state *s = kvm->arch.migration_state;
+ unsigned long bufsize, hva, pgstev, i, next, cur;
+ int srcu_idx, peek, r = 0, rr;
+ u8 *res;
+
+ cur = args->start_gfn;
+ i = next = pgstev = 0;
+
+ if (unlikely(!kvm->arch.use_cmma))
+ return -ENXIO;
+ /* Invalid/unsupported flags were specified */
+ if (args->flags & ~KVM_S390_CMMA_PEEK)
+ return -EINVAL;
+ /* Migration mode query, and we are not doing a migration */
+ peek = !!(args->flags & KVM_S390_CMMA_PEEK);
+ if (!peek && !s)
+ return -EINVAL;
+ /* CMMA is disabled or was not used, or the buffer has length zero */
+ bufsize = min(args->count, KVM_S390_CMMA_SIZE_MAX);
+ if (!bufsize || !kvm->mm->context.use_cmma) {
+ memset(args, 0, sizeof(*args));
+ return 0;
+ }
+
+ if (!peek) {
+ /* We are not peeking, and there are no dirty pages */
+ if (!atomic64_read(&s->dirty_pages)) {
+ memset(args, 0, sizeof(*args));
+ return 0;
+ }
+ cur = find_next_bit(s->pgste_bitmap, s->bitmap_size,
+ args->start_gfn);
+ if (cur >= s->bitmap_size) /* nothing found, loop back */
+ cur = find_next_bit(s->pgste_bitmap, s->bitmap_size, 0);
+ if (cur >= s->bitmap_size) { /* again! (very unlikely) */
+ memset(args, 0, sizeof(*args));
+ return 0;
+ }
+ next = find_next_bit(s->pgste_bitmap, s->bitmap_size, cur + 1);
+ }
+
+ res = vmalloc(bufsize);
+ if (!res)
+ return -ENOMEM;
+
+ args->start_gfn = cur;
+
+ down_read(&kvm->mm->mmap_sem);
+ srcu_idx = srcu_read_lock(&kvm->srcu);
+ while (i < bufsize) {
+ hva = gfn_to_hva(kvm, cur);
+ if (kvm_is_error_hva(hva)) {
+ r = -EFAULT;
+ break;
+ }
+ /* decrement only if we actually flipped the bit to 0 */
+ if (!peek && test_and_clear_bit(cur, s->pgste_bitmap))
+ atomic64_dec(&s->dirty_pages);
+ r = get_pgste(kvm->mm, hva, &pgstev);
+ if (r < 0)
+ pgstev = 0;
+ /* save the value */
+ res[i++] = (pgstev >> 24) & 0x3;
+ /*
+ * if the next bit is too far away, stop.
+ * if we reached the previous "next", find the next one
+ */
+ if (!peek) {
+ if (next > cur + KVM_S390_MAX_BIT_DISTANCE)
+ break;
+ if (cur == next)
+ next = find_next_bit(s->pgste_bitmap,
+ s->bitmap_size, cur + 1);
+ /* reached the end of the bitmap or of the buffer, stop */
+ if ((next >= s->bitmap_size) ||
+ (next >= args->start_gfn + bufsize))
+ break;
+ }
+ cur++;
+ }
+ srcu_read_unlock(&kvm->srcu, srcu_idx);
+ up_read(&kvm->mm->mmap_sem);
+ args->count = i;
+ args->remaining = s ? atomic64_read(&s->dirty_pages) : 0;
+
+ rr = copy_to_user((void __user *)args->values, res, args->count);
+ if (rr)
+ r = -EFAULT;
+
+ vfree(res);
+ return r;
+}
+
+/*
+ * This function sets the CMMA attributes for the given pages. If the input
+ * buffer has zero length, no action is taken, otherwise the attributes are
+ * set and the mm->context.use_cmma flag is set.
+ */
+static int kvm_s390_set_cmma_bits(struct kvm *kvm,
+ const struct kvm_s390_cmma_log *args)
+{
+ unsigned long hva, mask, pgstev, i;
+ uint8_t *bits;
+ int srcu_idx, r = 0;
+
+ mask = args->mask;
+
+ if (!kvm->arch.use_cmma)
+ return -ENXIO;
+ /* invalid/unsupported flags */
+ if (args->flags != 0)
+ return -EINVAL;
+ /* Enforce sane limit on memory allocation */
+ if (args->count > KVM_S390_CMMA_SIZE_MAX)
+ return -EINVAL;
+ /* Nothing to do */
+ if (args->count == 0)
+ return 0;
+
+ bits = vmalloc(sizeof(*bits) * args->count);
+ if (!bits)
+ return -ENOMEM;
+
+ r = copy_from_user(bits, (void __user *)args->values, args->count);
+ if (r) {
+ r = -EFAULT;
+ goto out;
+ }
+
+ down_read(&kvm->mm->mmap_sem);
+ srcu_idx = srcu_read_lock(&kvm->srcu);
+ for (i = 0; i < args->count; i++) {
+ hva = gfn_to_hva(kvm, args->start_gfn + i);
+ if (kvm_is_error_hva(hva)) {
+ r = -EFAULT;
+ break;
+ }
+
+ pgstev = bits[i];
+ pgstev = pgstev << 24;
+ mask &= _PGSTE_GPS_USAGE_MASK;
+ set_pgste_bits(kvm->mm, hva, mask, pgstev);
+ }
+ srcu_read_unlock(&kvm->srcu, srcu_idx);
+ up_read(&kvm->mm->mmap_sem);
+
+ if (!kvm->mm->context.use_cmma) {
+ down_write(&kvm->mm->mmap_sem);
+ kvm->mm->context.use_cmma = 1;
+ up_write(&kvm->mm->mmap_sem);
+ }
+out:
+ vfree(bits);
+ return r;
+}
+
long kvm_arch_vm_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
@@ -1364,6 +1673,29 @@ long kvm_arch_vm_ioctl(struct file *filp,
r = kvm_s390_set_skeys(kvm, &args);
break;
}
+ case KVM_S390_GET_CMMA_BITS: {
+ struct kvm_s390_cmma_log args;
+
+ r = -EFAULT;
+ if (copy_from_user(&args, argp, sizeof(args)))
+ break;
+ r = kvm_s390_get_cmma_bits(kvm, &args);
+ if (!r) {
+ r = copy_to_user(argp, &args, sizeof(args));
+ if (r)
+ r = -EFAULT;
+ }
+ break;
+ }
+ case KVM_S390_SET_CMMA_BITS: {
+ struct kvm_s390_cmma_log args;
+
+ r = -EFAULT;
+ if (copy_from_user(&args, argp, sizeof(args)))
+ break;
+ r = kvm_s390_set_cmma_bits(kvm, &args);
+ break;
+ }
default:
r = -ENOTTY;
}
@@ -1533,7 +1865,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
mutex_init(&kvm->arch.float_int.ais_lock);
kvm->arch.float_int.simm = 0;
kvm->arch.float_int.nimm = 0;
- kvm->arch.float_int.ais_enabled = 0;
spin_lock_init(&kvm->arch.float_int.lock);
for (i = 0; i < FIRQ_LIST_COUNT; i++)
INIT_LIST_HEAD(&kvm->arch.float_int.lists[i]);
@@ -1633,6 +1964,10 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
kvm_s390_destroy_adapters(kvm);
kvm_s390_clear_float_irqs(kvm);
kvm_s390_vsie_destroy(kvm);
+ if (kvm->arch.migration_state) {
+ vfree(kvm->arch.migration_state->pgste_bitmap);
+ kfree(kvm->arch.migration_state);
+ }
KVM_EVENT(3, "vm 0x%pK destroyed", kvm);
}
@@ -1977,7 +2312,6 @@ int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu)
if (!vcpu->arch.sie_block->cbrlo)
return -ENOMEM;
- vcpu->arch.sie_block->ecb2 |= ECB2_CMMA;
vcpu->arch.sie_block->ecb2 &= ~ECB2_PFMFI;
return 0;
}
@@ -2069,6 +2403,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
if (!vcpu)
goto out;
+ BUILD_BUG_ON(sizeof(struct sie_page) != 4096);
sie_page = (struct sie_page *) get_zeroed_page(GFP_KERNEL);
if (!sie_page)
goto out_free_cpu;
@@ -2440,7 +2775,7 @@ static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu)
{
retry:
kvm_s390_vcpu_request_handled(vcpu);
- if (!vcpu->requests)
+ if (!kvm_request_pending(vcpu))
return 0;
/*
* We use MMU_RELOAD just to re-arm the ipte notifier for the
@@ -2489,6 +2824,27 @@ retry:
goto retry;
}
+ if (kvm_check_request(KVM_REQ_START_MIGRATION, vcpu)) {
+ /*
+ * Disable CMMA virtualization; we will emulate the ESSA
+ * instruction manually, in order to provide additional
+ * functionalities needed for live migration.
+ */
+ vcpu->arch.sie_block->ecb2 &= ~ECB2_CMMA;
+ goto retry;
+ }
+
+ if (kvm_check_request(KVM_REQ_STOP_MIGRATION, vcpu)) {
+ /*
+ * Re-enable CMMA virtualization if CMMA is available and
+ * was used.
+ */
+ if ((vcpu->kvm->arch.use_cmma) &&
+ (vcpu->kvm->mm->context.use_cmma))
+ vcpu->arch.sie_block->ecb2 |= ECB2_CMMA;
+ goto retry;
+ }
+
/* nothing to do, just clear the request */
kvm_clear_request(KVM_REQ_UNHALT, vcpu);
@@ -2683,6 +3039,9 @@ static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu)
static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
{
+ struct mcck_volatile_info *mcck_info;
+ struct sie_page *sie_page;
+
VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
vcpu->arch.sie_block->icptcode);
trace_kvm_s390_sie_exit(vcpu, vcpu->arch.sie_block->icptcode);
@@ -2693,6 +3052,15 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
vcpu->run->s.regs.gprs[14] = vcpu->arch.sie_block->gg14;
vcpu->run->s.regs.gprs[15] = vcpu->arch.sie_block->gg15;
+ if (exit_reason == -EINTR) {
+ VCPU_EVENT(vcpu, 3, "%s", "machine check");
+ sie_page = container_of(vcpu->arch.sie_block,
+ struct sie_page, sie_block);
+ mcck_info = &sie_page->mcck_info;
+ kvm_s390_reinject_machine_check(vcpu, mcck_info);
+ return 0;
+ }
+
if (vcpu->arch.sie_block->icptcode > 0) {
int rc = kvm_handle_sie_intercept(vcpu);
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 55f5c8457d6d..6fedc8bc7a37 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -397,4 +397,6 @@ static inline int kvm_s390_use_sca_entries(void)
*/
return sclp.has_sigpif;
}
+void kvm_s390_reinject_machine_check(struct kvm_vcpu *vcpu,
+ struct mcck_volatile_info *mcck_info);
#endif
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index c03106c428cf..8a1dac793d6b 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -24,6 +24,7 @@
#include <asm/ebcdic.h>
#include <asm/sysinfo.h>
#include <asm/pgtable.h>
+#include <asm/page-states.h>
#include <asm/pgalloc.h>
#include <asm/gmap.h>
#include <asm/io.h>
@@ -361,7 +362,7 @@ 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 +375,7 @@ 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 +902,7 @@ 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 +939,7 @@ 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;
@@ -949,13 +950,72 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
return 0;
}
+static inline int do_essa(struct kvm_vcpu *vcpu, const int orc)
+{
+ struct kvm_s390_migration_state *ms = vcpu->kvm->arch.migration_state;
+ int r1, r2, nappended, entries;
+ unsigned long gfn, hva, res, pgstev, ptev;
+ unsigned long *cbrlo;
+
+ /*
+ * We don't need to set SD.FPF.SK to 1 here, because if we have a
+ * machine check here we either handle it or crash
+ */
+
+ kvm_s390_get_regs_rre(vcpu, &r1, &r2);
+ gfn = vcpu->run->s.regs.gprs[r2] >> PAGE_SHIFT;
+ hva = gfn_to_hva(vcpu->kvm, gfn);
+ entries = (vcpu->arch.sie_block->cbrlo & ~PAGE_MASK) >> 3;
+
+ if (kvm_is_error_hva(hva))
+ return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+
+ nappended = pgste_perform_essa(vcpu->kvm->mm, hva, orc, &ptev, &pgstev);
+ if (nappended < 0) {
+ res = orc ? 0x10 : 0;
+ vcpu->run->s.regs.gprs[r1] = res; /* Exception Indication */
+ return 0;
+ }
+ res = (pgstev & _PGSTE_GPS_USAGE_MASK) >> 22;
+ /*
+ * Set the block-content state part of the result. 0 means resident, so
+ * nothing to do if the page is valid. 2 is for preserved pages
+ * (non-present and non-zero), and 3 for zero pages (non-present and
+ * zero).
+ */
+ if (ptev & _PAGE_INVALID) {
+ res |= 2;
+ if (pgstev & _PGSTE_GPS_ZERO)
+ res |= 1;
+ }
+ vcpu->run->s.regs.gprs[r1] = res;
+ /*
+ * It is possible that all the normal 511 slots were full, in which case
+ * we will now write in the 512th slot, which is reserved for host use.
+ * In both cases we let the normal essa handling code process all the
+ * slots, including the reserved one, if needed.
+ */
+ if (nappended > 0) {
+ cbrlo = phys_to_virt(vcpu->arch.sie_block->cbrlo & PAGE_MASK);
+ cbrlo[entries] = gfn << PAGE_SHIFT;
+ }
+
+ if (orc) {
+ /* increment only if we are really flipping the bit to 1 */
+ if (!test_and_set_bit(gfn, ms->pgste_bitmap))
+ atomic64_inc(&ms->dirty_pages);
+ }
+
+ return nappended;
+}
+
static int handle_essa(struct kvm_vcpu *vcpu)
{
/* entries expected to be 1FF */
int entries = (vcpu->arch.sie_block->cbrlo & ~PAGE_MASK) >> 3;
unsigned long *cbrlo;
struct gmap *gmap;
- int i;
+ int i, orc;
VCPU_EVENT(vcpu, 4, "ESSA: release %d pages", entries);
gmap = vcpu->arch.gmap;
@@ -965,12 +1025,45 @@ static int handle_essa(struct kvm_vcpu *vcpu)
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
-
- if (((vcpu->arch.sie_block->ipb & 0xf0000000) >> 28) > 6)
+ /* Check for invalid operation request code */
+ orc = (vcpu->arch.sie_block->ipb & 0xf0000000) >> 28;
+ if (orc > ESSA_MAX)
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
- /* Retry the ESSA instruction */
- kvm_s390_retry_instr(vcpu);
+ if (likely(!vcpu->kvm->arch.migration_state)) {
+ /*
+ * CMMA is enabled in the KVM settings, but is disabled in
+ * the SIE block and in the mm_context, and we are not doing
+ * a migration. Enable CMMA in the mm_context.
+ * Since we need to take a write lock to write to the context
+ * to avoid races with storage keys handling, we check if the
+ * value really needs to be written to; if the value is
+ * already correct, we do nothing and avoid the lock.
+ */
+ if (vcpu->kvm->mm->context.use_cmma == 0) {
+ down_write(&vcpu->kvm->mm->mmap_sem);
+ vcpu->kvm->mm->context.use_cmma = 1;
+ up_write(&vcpu->kvm->mm->mmap_sem);
+ }
+ /*
+ * If we are here, we are supposed to have CMMA enabled in
+ * the SIE block. Enabling CMMA works on a per-CPU basis,
+ * while the context use_cmma flag is per process.
+ * It's possible that the context flag is enabled and the
+ * SIE flag is not, so we set the flag always; if it was
+ * already set, nothing changes, otherwise we enable it
+ * on this CPU too.
+ */
+ vcpu->arch.sie_block->ecb2 |= ECB2_CMMA;
+ /* Retry the ESSA instruction */
+ kvm_s390_retry_instr(vcpu);
+ } else {
+ /* Account for the possible extra cbrl entry */
+ i = do_essa(vcpu, orc);
+ if (i < 0)
+ return i;
+ entries += i;
+ }
vcpu->arch.sie_block->cbrlo &= PAGE_MASK; /* reset nceo */
cbrlo = phys_to_virt(vcpu->arch.sie_block->cbrlo);
down_read(&gmap->mm->mmap_sem);
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index 4719ecb9ab42..715c19c45d9a 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -26,16 +26,21 @@
struct vsie_page {
struct kvm_s390_sie_block scb_s; /* 0x0000 */
+ /*
+ * the backup info for machine check. ensure it's at
+ * the same offset as that in struct sie_page!
+ */
+ struct mcck_volatile_info mcck_info; /* 0x0200 */
/* the pinned originial scb */
- struct kvm_s390_sie_block *scb_o; /* 0x0200 */
+ struct kvm_s390_sie_block *scb_o; /* 0x0218 */
/* the shadow gmap in use by the vsie_page */
- struct gmap *gmap; /* 0x0208 */
+ struct gmap *gmap; /* 0x0220 */
/* address of the last reported fault to guest2 */
- unsigned long fault_addr; /* 0x0210 */
- __u8 reserved[0x0700 - 0x0218]; /* 0x0218 */
+ unsigned long fault_addr; /* 0x0228 */
+ __u8 reserved[0x0700 - 0x0230]; /* 0x0230 */
struct kvm_s390_crypto_cb crycb; /* 0x0700 */
__u8 fac[S390_ARCH_FAC_LIST_SIZE_BYTE]; /* 0x0800 */
-} __packed;
+};
/* trigger a validity icpt for the given scb */
static int set_validity_icpt(struct kvm_s390_sie_block *scb,
@@ -801,6 +806,8 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
{
struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
+ struct mcck_volatile_info *mcck_info;
+ struct sie_page *sie_page;
int rc;
handle_last_fault(vcpu, vsie_page);
@@ -822,6 +829,14 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
local_irq_enable();
vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+ if (rc == -EINTR) {
+ VCPU_EVENT(vcpu, 3, "%s", "machine check");
+ sie_page = container_of(scb_s, struct sie_page, sie_block);
+ mcck_info = &sie_page->mcck_info;
+ kvm_s390_reinject_machine_check(vcpu, mcck_info);
+ return 0;
+ }
+
if (rc > 0)
rc = 0; /* we could still have an icpt */
else if (rc == -EFAULT)
diff --git a/arch/s390/lib/probes.c b/arch/s390/lib/probes.c
index ae90e1ae3607..1963ddbf4ab3 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 1e5bb2b86c42..b3bd3f23b8e8 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 1b553d847140..049c3c455b32 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 5845d3028ffc..14f25798b001 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 7f6db1e6c048..4fb3d3cdb370 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 b7b779c40a5b..8ecc25e760fa 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 9b4050caa4e9..44a8e6f0391e 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -162,33 +162,42 @@ 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;
}
-pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_offset(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);
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 ee6a1d3d4983..8111694ce55a 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();
@@ -162,43 +166,17 @@ unsigned long memory_block_size_bytes(void)
}
#ifdef CONFIG_MEMORY_HOTPLUG
-int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
+int arch_add_memory(int nid, u64 start, u64 size, bool want_memblock)
{
- unsigned long zone_start_pfn, zone_end_pfn, nr_pages;
unsigned long start_pfn = PFN_DOWN(start);
unsigned long size_pages = PFN_DOWN(size);
- pg_data_t *pgdat = NODE_DATA(nid);
- struct zone *zone;
- int rc, i;
+ int rc;
rc = vmem_add_mapping(start, size);
if (rc)
return rc;
- for (i = 0; i < MAX_NR_ZONES; i++) {
- zone = pgdat->node_zones + i;
- if (zone_idx(zone) != ZONE_MOVABLE) {
- /* Add range within existing zone limits, if possible */
- zone_start_pfn = zone->zone_start_pfn;
- zone_end_pfn = zone->zone_start_pfn +
- zone->spanned_pages;
- } else {
- /* Add remaining range to ZONE_MOVABLE */
- zone_start_pfn = start_pfn;
- zone_end_pfn = start_pfn + size_pages;
- }
- if (start_pfn < zone_start_pfn || start_pfn >= zone_end_pfn)
- continue;
- nr_pages = (start_pfn + size_pages > zone_end_pfn) ?
- zone_end_pfn - start_pfn : size_pages;
- rc = __add_pages(nid, zone, start_pfn, nr_pages);
- if (rc)
- break;
- start_pfn += nr_pages;
- size_pages -= nr_pages;
- if (!size_pages)
- break;
- }
+ rc = __add_pages(nid, start_pfn, size_pages, want_memblock);
if (rc)
vmem_remove_mapping(start, size);
return rc;
diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c
index b017daed6887..2e10d2b8ad35 100644
--- a/arch/s390/mm/mmap.c
+++ b/arch/s390/mm/mmap.c
@@ -101,7 +101,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
addr = PAGE_ALIGN(addr);
vma = find_vma(mm, addr);
if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
- (!vma || addr + len <= vma->vm_start))
+ (!vma || addr + len <= vm_start_gap(vma)))
goto check_asce_limit;
}
@@ -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;
}
@@ -151,7 +151,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
addr = PAGE_ALIGN(addr);
vma = find_vma(mm, addr);
if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
- (!vma || addr + len <= vma->vm_start))
+ (!vma || addr + len <= vm_start_gap(vma)))
goto check_asce_limit;
}
@@ -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 49e721f3645e..180481589246 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 f502cbe657af..18918e394ce4 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 947b66a5cdba..d4d409ba206b 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 c33c94b4be60..d8398962a723 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/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 6e97a2e3fd8d..01c6fbc3e85b 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -991,7 +991,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
}
break;
}
- case BPF_JMP | BPF_CALL | BPF_X:
+ case BPF_JMP | BPF_TAIL_CALL:
/*
* Implicit input:
* B1: pointer to ctx
@@ -1329,6 +1329,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
bpf_jit_binary_lock_ro(header);
fp->bpf_func = (void *) jit.prg_buf;
fp->jited = 1;
+ fp->jited_len = jit.size;
free_addrs:
kfree(jit.addrs);
out:
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 8051df109db3..7b30af5da222 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 };
-
- 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 };
+ 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_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 @@ out:
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 1c3332ac1957..bd534b4d40e3 100644
--- a/arch/s390/pci/pci_clp.c
+++ b/arch/s390/pci/pci_clp.c
@@ -193,12 +193,12 @@ out:
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 9081a57fa340..0d300ee00f4e 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -14,6 +14,8 @@
#include <linux/pci.h>
#include <asm/pci_dma.h>
+#define S390_MAPPING_ERROR (~(dma_addr_t) 0x0)
+
static struct kmem_cache *dma_region_table_cache;
static struct kmem_cache *dma_page_table_cache;
static int s390_iommu_strict;
@@ -281,7 +283,7 @@ static dma_addr_t dma_alloc_address(struct device *dev, int size)
out_error:
spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, flags);
- return DMA_ERROR_CODE;
+ return S390_MAPPING_ERROR;
}
static void dma_free_address(struct device *dev, dma_addr_t dma_addr, int size)
@@ -329,7 +331,7 @@ static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page,
/* This rounds up number of pages based on size and offset */
nr_pages = iommu_num_pages(pa, size, PAGE_SIZE);
dma_addr = dma_alloc_address(dev, nr_pages);
- if (dma_addr == DMA_ERROR_CODE) {
+ if (dma_addr == S390_MAPPING_ERROR) {
ret = -ENOSPC;
goto out_err;
}
@@ -352,7 +354,7 @@ out_free:
out_err:
zpci_err("map error:\n");
zpci_err_dma(ret, pa);
- return DMA_ERROR_CODE;
+ return S390_MAPPING_ERROR;
}
static void s390_dma_unmap_pages(struct device *dev, dma_addr_t dma_addr,
@@ -429,7 +431,7 @@ static int __s390_dma_map_sg(struct device *dev, struct scatterlist *sg,
int ret;
dma_addr_base = dma_alloc_address(dev, nr_pages);
- if (dma_addr_base == DMA_ERROR_CODE)
+ if (dma_addr_base == S390_MAPPING_ERROR)
return -ENOMEM;
dma_addr = dma_addr_base;
@@ -476,7 +478,7 @@ static int s390_dma_map_sg(struct device *dev, struct scatterlist *sg,
for (i = 1; i < nr_elements; i++) {
s = sg_next(s);
- s->dma_address = DMA_ERROR_CODE;
+ s->dma_address = S390_MAPPING_ERROR;
s->dma_length = 0;
if (s->offset || (size & ~PAGE_MASK) ||
@@ -525,6 +527,11 @@ static void s390_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
s->dma_length = 0;
}
}
+
+static int s390_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+ return dma_addr == S390_MAPPING_ERROR;
+}
int zpci_dma_init_device(struct zpci_dev *zdev)
{
@@ -601,7 +608,9 @@ 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);
@@ -657,6 +666,7 @@ const struct dma_map_ops s390_pci_dma_ops = {
.unmap_sg = s390_dma_unmap_sg,
.map_page = s390_dma_map_pages,
.unmap_page = s390_dma_unmap_pages,
+ .mapping_error = s390_mapping_error,
/* if we support direct DMA this must be conditional */
.is_phys = 0,
/* dma_supported is unconditionally true without a callback */
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index c2b27ad8e94d..0bbc04af4418 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 fa8d7d4b9751..ea34086c8674 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 be63fbd699fd..025ea20fc4b4 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