diff options
| author | Ingo Molnar <mingo@kernel.org> | 2013-10-04 09:59:13 +0200 |
|---|---|---|
| committer | Ingo Molnar <mingo@kernel.org> | 2013-10-04 09:59:13 +0200 |
| commit | fafd883f671dfc1c2f62009179920f27abc784a1 (patch) | |
| tree | 0eccb0baf343cad79a54e352598921db9ca17620 /arch/s390 | |
| parent | 92519bbc8af612975410def52bd462ca9af85cdb (diff) | |
| parent | d8b11a0cbd1c66ce283eb9dabe0498dfa6483f32 (diff) | |
Merge branch 'perf/urgent' into perf/core
Pick up the latest fixes before applying new patches.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'arch/s390')
44 files changed, 751 insertions, 407 deletions
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 8b7892bf6d8b..7143793859fa 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -62,6 +62,7 @@ config S390 def_bool y select ARCH_DISCARD_MEMBLOCK select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE + select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_INLINE_READ_LOCK select ARCH_INLINE_READ_LOCK_BH @@ -91,8 +92,8 @@ config S390 select ARCH_INLINE_WRITE_UNLOCK_BH select ARCH_INLINE_WRITE_UNLOCK_IRQ select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE - select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS select ARCH_SAVE_PAGE_KEYS if HIBERNATION + select ARCH_USE_CMPXCHG_LOCKREF select ARCH_WANT_IPC_PARSE_VERSION select BUILDTIME_EXTABLE_SORT select CLONE_BACKWARDS2 @@ -102,7 +103,6 @@ config S390 select GENERIC_TIME_VSYSCALL_OLD select HAVE_ALIGNED_STRUCT_PAGE if SLUB select HAVE_ARCH_JUMP_LABEL if !MARCH_G5 - select HAVE_ARCH_MUTEX_CPU_RELAX select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE if 64BIT @@ -116,7 +116,6 @@ config S390 select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_TRACE_MCOUNT_TEST - select HAVE_GENERIC_HARDIRQS select HAVE_KERNEL_BZIP2 select HAVE_KERNEL_GZIP select HAVE_KERNEL_LZ4 @@ -135,15 +134,15 @@ config S390 select HAVE_SYSCALL_TRACEPOINTS select HAVE_UID16 if 32BIT select HAVE_VIRT_CPU_ACCOUNTING - select VIRT_TO_BUS select INIT_ALL_POSSIBLE select KTIME_SCALAR if 32BIT select MODULES_USE_ELF_RELA - select OLD_SIGSUSPEND3 select OLD_SIGACTION + select OLD_SIGSUSPEND3 select SYSCTL_EXCEPTION_TRACE select USE_GENERIC_SMP_HELPERS if SMP select VIRT_CPU_ACCOUNTING + select VIRT_TO_BUS config SCHED_OMIT_FRAME_POINTER def_bool y @@ -431,7 +430,6 @@ menuconfig PCI bool "PCI support" default n depends on 64BIT - select ARCH_SUPPORTS_MSI select PCI_MSI help Enable PCI support. @@ -527,6 +525,7 @@ config CRASH_DUMP bool "kernel crash dumps" depends on 64BIT && SMP select KEXEC + select ZFCPDUMP help Generate crash dump after being started by kexec. Crash dump kernels are loaded in the main kernel with kexec-tools @@ -537,7 +536,7 @@ config CRASH_DUMP config ZFCPDUMP def_bool n prompt "zfcpdump support" - select SMP + depends on SMP help Select this option if you want to build an zfcpdump enabled kernel. Refer to <file:Documentation/s390/zfcpdump.txt> for more details on this. diff --git a/arch/s390/defconfig b/arch/s390/defconfig index b74400e3e035..d204c65bf722 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -1,14 +1,13 @@ -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_FHANDLE=y +CONFIG_AUDIT=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y CONFIG_TASKSTATS=y CONFIG_TASK_DELAY_ACCT=y CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y -CONFIG_AUDIT=y -CONFIG_NO_HZ=y -CONFIG_HIGH_RES_TIMERS=y CONFIG_RCU_FAST_NO_HZ=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y @@ -27,6 +26,7 @@ CONFIG_RD_BZIP2=y CONFIG_RD_LZMA=y CONFIG_RD_XZ=y CONFIG_RD_LZO=y +CONFIG_RD_LZ4=y CONFIG_EXPERT=y # CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y @@ -38,11 +38,13 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODVERSIONS=y CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y +# CONFIG_EFI_PARTITION is not set CONFIG_DEFAULT_DEADLINE=y CONFIG_HZ_100=y CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y +CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_CRASH_DUMP=y CONFIG_BINFMT_MISC=m CONFIG_HIBERNATION=y @@ -92,40 +94,49 @@ CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_LOGGING=y CONFIG_SCSI_SCAN_ASYNC=y CONFIG_ZFCP=y +CONFIG_SCSI_VIRTIO=y CONFIG_NETDEVICES=y CONFIG_BONDING=m CONFIG_DUMMY=m CONFIG_EQUALIZER=m CONFIG_TUN=m CONFIG_VIRTIO_NET=y +# CONFIG_INPUT is not set +# CONFIG_SERIO is not set CONFIG_RAW_DRIVER=m CONFIG_VIRTIO_BALLOON=y -CONFIG_EXT2_FS=y -CONFIG_EXT3_FS=y -# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y +CONFIG_XFS_FS=y +CONFIG_XFS_QUOTA=y +CONFIG_XFS_POSIX_ACL=y +CONFIG_XFS_RT=y +CONFIG_BTRFS_FS=y +CONFIG_BTRFS_FS_POSIX_ACL=y +CONFIG_FANOTIFY=y +CONFIG_FUSE_FS=y CONFIG_PROC_KCORE=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y +CONFIG_HUGETLBFS=y # CONFIG_NETWORK_FILESYSTEMS is not set +CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_PAGEALLOC=y CONFIG_TIMER_STATS=y CONFIG_PROVE_LOCKING=y -CONFIG_PROVE_RCU=y CONFIG_LOCK_STAT=y CONFIG_DEBUG_LOCKDEP=y CONFIG_DEBUG_LIST=y CONFIG_DEBUG_NOTIFIERS=y +CONFIG_PROVE_RCU=y +CONFIG_RCU_CPU_STALL_TIMEOUT=60 CONFIG_RCU_TRACE=y -CONFIG_KPROBES_SANITY_TEST=y -CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y CONFIG_LATENCYTOP=y -CONFIG_DEBUG_PAGEALLOC=y CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_KPROBES_SANITY_TEST=y # CONFIG_STRICT_DEVMEM is not set -CONFIG_CRYPTO_NULL=m CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_AUTHENC=m CONFIG_CRYPTO_TEST=m @@ -137,8 +148,10 @@ CONFIG_CRYPTO_ECB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m +CONFIG_CRYPTO_CMAC=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m +CONFIG_CRYPTO_CRC32=m CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD128=m @@ -165,6 +178,8 @@ CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_DEFLATE=m CONFIG_CRYPTO_ZLIB=m CONFIG_CRYPTO_LZO=m +CONFIG_CRYPTO_LZ4=m +CONFIG_CRYPTO_LZ4HC=m CONFIG_ZCRYPT=m CONFIG_CRYPTO_SHA1_S390=m CONFIG_CRYPTO_SHA256_S390=m diff --git a/arch/s390/hypfs/hypfs.h b/arch/s390/hypfs/hypfs.h index f41e0ef7fdf9..79f2ac55253f 100644 --- a/arch/s390/hypfs/hypfs.h +++ b/arch/s390/hypfs/hypfs.h @@ -18,26 +18,23 @@ #define UPDATE_FILE_MODE 0220 #define DIR_MODE 0550 -extern struct dentry *hypfs_mkdir(struct super_block *sb, struct dentry *parent, - const char *name); +extern struct dentry *hypfs_mkdir(struct dentry *parent, const char *name); -extern struct dentry *hypfs_create_u64(struct super_block *sb, - struct dentry *dir, const char *name, +extern struct dentry *hypfs_create_u64(struct dentry *dir, const char *name, __u64 value); -extern struct dentry *hypfs_create_str(struct super_block *sb, - struct dentry *dir, const char *name, +extern struct dentry *hypfs_create_str(struct dentry *dir, const char *name, char *string); /* LPAR Hypervisor */ extern int hypfs_diag_init(void); extern void hypfs_diag_exit(void); -extern int hypfs_diag_create_files(struct super_block *sb, struct dentry *root); +extern int hypfs_diag_create_files(struct dentry *root); /* VM Hypervisor */ extern int hypfs_vm_init(void); extern void hypfs_vm_exit(void); -extern int hypfs_vm_create_files(struct super_block *sb, struct dentry *root); +extern int hypfs_vm_create_files(struct dentry *root); /* debugfs interface */ struct hypfs_dbfs_file; diff --git a/arch/s390/hypfs/hypfs_dbfs.c b/arch/s390/hypfs/hypfs_dbfs.c index bb5dd496614f..17ab8b7b53cc 100644 --- a/arch/s390/hypfs/hypfs_dbfs.c +++ b/arch/s390/hypfs/hypfs_dbfs.c @@ -105,7 +105,7 @@ void hypfs_dbfs_remove_file(struct hypfs_dbfs_file *df) int hypfs_dbfs_init(void) { dbfs_dir = debugfs_create_dir("s390_hypfs", NULL); - return PTR_RET(dbfs_dir); + return PTR_ERR_OR_ZERO(dbfs_dir); } void hypfs_dbfs_exit(void) diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c index 138893e5f736..5eeffeefae06 100644 --- a/arch/s390/hypfs/hypfs_diag.c +++ b/arch/s390/hypfs/hypfs_diag.c @@ -623,8 +623,7 @@ void hypfs_diag_exit(void) * ******************************************* */ -static int hypfs_create_cpu_files(struct super_block *sb, - struct dentry *cpus_dir, void *cpu_info) +static int hypfs_create_cpu_files(struct dentry *cpus_dir, void *cpu_info) { struct dentry *cpu_dir; char buffer[TMP_SIZE]; @@ -632,30 +631,29 @@ static int hypfs_create_cpu_files(struct super_block *sb, snprintf(buffer, TMP_SIZE, "%d", cpu_info__cpu_addr(diag204_info_type, cpu_info)); - cpu_dir = hypfs_mkdir(sb, cpus_dir, buffer); - rc = hypfs_create_u64(sb, cpu_dir, "mgmtime", + cpu_dir = hypfs_mkdir(cpus_dir, buffer); + rc = hypfs_create_u64(cpu_dir, "mgmtime", cpu_info__acc_time(diag204_info_type, cpu_info) - cpu_info__lp_time(diag204_info_type, cpu_info)); if (IS_ERR(rc)) return PTR_ERR(rc); - rc = hypfs_create_u64(sb, cpu_dir, "cputime", + rc = hypfs_create_u64(cpu_dir, "cputime", cpu_info__lp_time(diag204_info_type, cpu_info)); if (IS_ERR(rc)) return PTR_ERR(rc); if (diag204_info_type == INFO_EXT) { - rc = hypfs_create_u64(sb, cpu_dir, "onlinetime", + rc = hypfs_create_u64(cpu_dir, "onlinetime", cpu_info__online_time(diag204_info_type, cpu_info)); if (IS_ERR(rc)) return PTR_ERR(rc); } diag224_idx2name(cpu_info__ctidx(diag204_info_type, cpu_info), buffer); - rc = hypfs_create_str(sb, cpu_dir, "type", buffer); + rc = hypfs_create_str(cpu_dir, "type", buffer); return PTR_RET(rc); } -static void *hypfs_create_lpar_files(struct super_block *sb, - struct dentry *systems_dir, void *part_hdr) +static void *hypfs_create_lpar_files(struct dentry *systems_dir, void *part_hdr) { struct dentry *cpus_dir; struct dentry *lpar_dir; @@ -665,16 +663,16 @@ static void *hypfs_create_lpar_files(struct super_block *sb, part_hdr__part_name(diag204_info_type, part_hdr, lpar_name); lpar_name[LPAR_NAME_LEN] = 0; - lpar_dir = hypfs_mkdir(sb, systems_dir, lpar_name); + lpar_dir = hypfs_mkdir(systems_dir, lpar_name); if (IS_ERR(lpar_dir)) return lpar_dir; - cpus_dir = hypfs_mkdir(sb, lpar_dir, "cpus"); + cpus_dir = hypfs_mkdir(lpar_dir, "cpus"); if (IS_ERR(cpus_dir)) return cpus_dir; cpu_info = part_hdr + part_hdr__size(diag204_info_type); for (i = 0; i < part_hdr__rcpus(diag204_info_type, part_hdr); i++) { int rc; - rc = hypfs_create_cpu_files(sb, cpus_dir, cpu_info); + rc = hypfs_create_cpu_files(cpus_dir, cpu_info); if (rc) return ERR_PTR(rc); cpu_info += cpu_info__size(diag204_info_type); @@ -682,8 +680,7 @@ static void *hypfs_create_lpar_files(struct super_block *sb, return cpu_info; } -static int hypfs_create_phys_cpu_files(struct super_block *sb, - struct dentry *cpus_dir, void *cpu_info) +static int hypfs_create_phys_cpu_files(struct dentry *cpus_dir, void *cpu_info) { struct dentry *cpu_dir; char buffer[TMP_SIZE]; @@ -691,32 +688,31 @@ static int hypfs_create_phys_cpu_files(struct super_block *sb, snprintf(buffer, TMP_SIZE, "%i", phys_cpu__cpu_addr(diag204_info_type, cpu_info)); - cpu_dir = hypfs_mkdir(sb, cpus_dir, buffer); + cpu_dir = hypfs_mkdir(cpus_dir, buffer); if (IS_ERR(cpu_dir)) return PTR_ERR(cpu_dir); - rc = hypfs_create_u64(sb, cpu_dir, "mgmtime", + rc = hypfs_create_u64(cpu_dir, "mgmtime", phys_cpu__mgm_time(diag204_info_type, cpu_info)); if (IS_ERR(rc)) return PTR_ERR(rc); diag224_idx2name(phys_cpu__ctidx(diag204_info_type, cpu_info), buffer); - rc = hypfs_create_str(sb, cpu_dir, "type", buffer); + rc = hypfs_create_str(cpu_dir, "type", buffer); return PTR_RET(rc); } -static void *hypfs_create_phys_files(struct super_block *sb, - struct dentry *parent_dir, void *phys_hdr) +static void *hypfs_create_phys_files(struct dentry *parent_dir, void *phys_hdr) { int i; void *cpu_info; struct dentry *cpus_dir; - cpus_dir = hypfs_mkdir(sb, parent_dir, "cpus"); + cpus_dir = hypfs_mkdir(parent_dir, "cpus"); if (IS_ERR(cpus_dir)) return cpus_dir; cpu_info = phys_hdr + phys_hdr__size(diag204_info_type); for (i = 0; i < phys_hdr__cpus(diag204_info_type, phys_hdr); i++) { int rc; - rc = hypfs_create_phys_cpu_files(sb, cpus_dir, cpu_info); + rc = hypfs_create_phys_cpu_files(cpus_dir, cpu_info); if (rc) return ERR_PTR(rc); cpu_info += phys_cpu__size(diag204_info_type); @@ -724,7 +720,7 @@ static void *hypfs_create_phys_files(struct super_block *sb, return cpu_info; } -int hypfs_diag_create_files(struct super_block *sb, struct dentry *root) +int hypfs_diag_create_files(struct dentry *root) { struct dentry *systems_dir, *hyp_dir; void *time_hdr, *part_hdr; @@ -735,7 +731,7 @@ int hypfs_diag_create_files(struct super_block *sb, struct dentry *root) if (IS_ERR(buffer)) return PTR_ERR(buffer); - systems_dir = hypfs_mkdir(sb, root, "systems"); + systems_dir = hypfs_mkdir(root, "systems"); if (IS_ERR(systems_dir)) { rc = PTR_ERR(systems_dir); goto err_out; @@ -743,25 +739,25 @@ int hypfs_diag_create_files(struct super_block *sb, struct dentry *root) time_hdr = (struct x_info_blk_hdr *)buffer; part_hdr = time_hdr + info_blk_hdr__size(diag204_info_type); for (i = 0; i < info_blk_hdr__npar(diag204_info_type, time_hdr); i++) { - part_hdr = hypfs_create_lpar_files(sb, systems_dir, part_hdr); + part_hdr = hypfs_create_lpar_files(systems_dir, part_hdr); if (IS_ERR(part_hdr)) { rc = PTR_ERR(part_hdr); goto err_out; } } if (info_blk_hdr__flags(diag204_info_type, time_hdr) & LPAR_PHYS_FLG) { - ptr = hypfs_create_phys_files(sb, root, part_hdr); + ptr = hypfs_create_phys_files(root, part_hdr); if (IS_ERR(ptr)) { rc = PTR_ERR(ptr); goto err_out; } } - hyp_dir = hypfs_mkdir(sb, root, "hyp"); + hyp_dir = hypfs_mkdir(root, "hyp"); if (IS_ERR(hyp_dir)) { rc = PTR_ERR(hyp_dir); goto err_out; } - ptr = hypfs_create_str(sb, hyp_dir, "type", "LPAR Hypervisor"); + ptr = hypfs_create_str(hyp_dir, "type", "LPAR Hypervisor"); if (IS_ERR(ptr)) { rc = PTR_ERR(ptr); goto err_out; diff --git a/arch/s390/hypfs/hypfs_vm.c b/arch/s390/hypfs/hypfs_vm.c index f364dcf77e8e..24908ce149f1 100644 --- a/arch/s390/hypfs/hypfs_vm.c +++ b/arch/s390/hypfs/hypfs_vm.c @@ -107,16 +107,15 @@ static void diag2fc_free(const void *data) vfree(data); } -#define ATTRIBUTE(sb, dir, name, member) \ +#define ATTRIBUTE(dir, name, member) \ do { \ void *rc; \ - rc = hypfs_create_u64(sb, dir, name, member); \ + rc = hypfs_create_u64(dir, name, member); \ if (IS_ERR(rc)) \ return PTR_ERR(rc); \ } while(0) -static int hpyfs_vm_create_guest(struct super_block *sb, - struct dentry *systems_dir, +static int hpyfs_vm_create_guest(struct dentry *systems_dir, struct diag2fc_data *data) { char guest_name[NAME_LEN + 1] = {}; @@ -130,46 +129,46 @@ static int hpyfs_vm_create_guest(struct super_block *sb, memcpy(guest_name, data->guest_name, NAME_LEN); EBCASC(guest_name, NAME_LEN); strim(guest_name); - guest_dir = hypfs_mkdir(sb, systems_dir, guest_name); + guest_dir = hypfs_mkdir(systems_dir, guest_name); if (IS_ERR(guest_dir)) return PTR_ERR(guest_dir); - ATTRIBUTE(sb, guest_dir, "onlinetime_us", data->el_time); + ATTRIBUTE(guest_dir, "onlinetime_us", data->el_time); /* logical cpu information */ - cpus_dir = hypfs_mkdir(sb, guest_dir, "cpus"); + cpus_dir = hypfs_mkdir(guest_dir, "cpus"); if (IS_ERR(cpus_dir)) return PTR_ERR(cpus_dir); - ATTRIBUTE(sb, cpus_dir, "cputime_us", data->used_cpu); - ATTRIBUTE(sb, cpus_dir, "capped", capped_value); - ATTRIBUTE(sb, cpus_dir, "dedicated", dedicated_flag); - ATTRIBUTE(sb, cpus_dir, "count", data->vcpus); - ATTRIBUTE(sb, cpus_dir, "weight_min", data->cpu_min); - ATTRIBUTE(sb, cpus_dir, "weight_max", data->cpu_max); - ATTRIBUTE(sb, cpus_dir, "weight_cur", data->cpu_shares); + ATTRIBUTE(cpus_dir, "cputime_us", data->used_cpu); + ATTRIBUTE(cpus_dir, "capped", capped_value); + ATTRIBUTE(cpus_dir, "dedicated", dedicated_flag); + ATTRIBUTE(cpus_dir, "count", data->vcpus); + ATTRIBUTE(cpus_dir, "weight_min", data->cpu_min); + ATTRIBUTE(cpus_dir, "weight_max", data->cpu_max); + ATTRIBUTE(cpus_dir, "weight_cur", data->cpu_shares); /* memory information */ - mem_dir = hypfs_mkdir(sb, guest_dir, "mem"); + mem_dir = hypfs_mkdir(guest_dir, "mem"); if (IS_ERR(mem_dir)) return PTR_ERR(mem_dir); - ATTRIBUTE(sb, mem_dir, "min_KiB", data->mem_min_kb); - ATTRIBUTE(sb, mem_dir, "max_KiB", data->mem_max_kb); - ATTRIBUTE(sb, mem_dir, "used_KiB", data->mem_used_kb); - ATTRIBUTE(sb, mem_dir, "share_KiB", data->mem_share_kb); + ATTRIBUTE(mem_dir, "min_KiB", data->mem_min_kb); + ATTRIBUTE(mem_dir, "max_KiB", data->mem_max_kb); + ATTRIBUTE(mem_dir, "used_KiB", data->mem_used_kb); + ATTRIBUTE(mem_dir, "share_KiB", data->mem_share_kb); /* samples */ - samples_dir = hypfs_mkdir(sb, guest_dir, "samples"); + samples_dir = hypfs_mkdir(guest_dir, "samples"); if (IS_ERR(samples_dir)) return PTR_ERR(samples_dir); - ATTRIBUTE(sb, samples_dir, "cpu_using", data->cpu_use_samp); - ATTRIBUTE(sb, samples_dir, "cpu_delay", data->cpu_delay_samp); - ATTRIBUTE(sb, samples_dir, "mem_delay", data->page_wait_samp); - ATTRIBUTE(sb, samples_dir, "idle", data->idle_samp); - ATTRIBUTE(sb, samples_dir, "other", data->other_samp); - ATTRIBUTE(sb, samples_dir, "total", data->total_samp); + ATTRIBUTE(samples_dir, "cpu_using", data->cpu_use_samp); + ATTRIBUTE(samples_dir, "cpu_delay", data->cpu_delay_samp); + ATTRIBUTE(samples_dir, "mem_delay", data->page_wait_samp); + ATTRIBUTE(samples_dir, "idle", data->idle_samp); + ATTRIBUTE(samples_dir, "other", data->other_samp); + ATTRIBUTE(samples_dir, "total", data->total_samp); return 0; } -int hypfs_vm_create_files(struct super_block *sb, struct dentry *root) +int hypfs_vm_create_files(struct dentry *root) { struct dentry *dir, *file; struct diag2fc_data *data; @@ -181,38 +180,38 @@ int hypfs_vm_create_files(struct super_block *sb, struct dentry *root) return PTR_ERR(data); /* Hpervisor Info */ - dir = hypfs_mkdir(sb, root, "hyp"); + dir = hypfs_mkdir(root, "hyp"); if (IS_ERR(dir)) { rc = PTR_ERR(dir); goto failed; } - file = hypfs_create_str(sb, dir, "type", "z/VM Hypervisor"); + file = hypfs_create_str(dir, "type", "z/VM Hypervisor"); if (IS_ERR(file)) { rc = PTR_ERR(file); goto failed; } /* physical cpus */ - dir = hypfs_mkdir(sb, root, "cpus"); + dir = hypfs_mkdir(root, "cpus"); if (IS_ERR(dir)) { rc = PTR_ERR(dir); goto failed; } - file = hypfs_create_u64(sb, dir, "count", data->lcpus); + file = hypfs_create_u64(dir, "count", data->lcpus); if (IS_ERR(file)) { rc = PTR_ERR(file); goto failed; } /* guests */ - dir = hypfs_mkdir(sb, root, "systems"); + dir = hypfs_mkdir(root, "systems"); if (IS_ERR(dir)) { rc = PTR_ERR(dir); goto failed; } for (i = 0; i < count; i++) { - rc = hpyfs_vm_create_guest(sb, dir, &(data[i])); + rc = hpyfs_vm_create_guest(dir, &(data[i])); if (rc) goto failed; } diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index 7a539f4f5e30..ddfe09b45134 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -28,8 +28,7 @@ #define HYPFS_MAGIC 0x687970 /* ASCII 'hyp' */ #define TMP_SIZE 64 /* size of temporary buffers */ -static struct dentry *hypfs_create_update_file(struct super_block *sb, - struct dentry *dir); +static struct dentry *hypfs_create_update_file(struct dentry *dir); struct hypfs_sb_info { kuid_t uid; /* uid used for files and dirs */ @@ -193,9 +192,9 @@ static ssize_t hypfs_aio_write(struct kiocb *iocb, const struct iovec *iov, } hypfs_delete_tree(sb->s_root); if (MACHINE_IS_VM) - rc = hypfs_vm_create_files(sb, sb->s_root); + rc = hypfs_vm_create_files(sb->s_root); else - rc = hypfs_diag_create_files(sb, sb->s_root); + rc = hypfs_diag_create_files(sb->s_root); if (rc) { pr_err("Updating the hypfs tree failed\n"); hypfs_delete_tree(sb->s_root); @@ -302,12 +301,12 @@ static int hypfs_fill_super(struct super_block *sb, void *data, int silent) if (!root_dentry) return -ENOMEM; if (MACHINE_IS_VM) - rc = hypfs_vm_create_files(sb, root_dentry); + rc = hypfs_vm_create_files(root_dentry); else - rc = hypfs_diag_create_files(sb, root_dentry); + rc = hypfs_diag_create_files(root_dentry); if (rc) return rc; - sbi->update_file = hypfs_create_update_file(sb, root_dentry); + sbi->update_file = hypfs_create_update_file(root_dentry); if (IS_ERR(sbi->update_file)) return PTR_ERR(sbi->update_file); hypfs_update_update(sb); @@ -334,8 +333,7 @@ static void hypfs_kill_super(struct super_block *sb) kill_litter_super(sb); } -static struct dentry *hypfs_create_file(struct super_block *sb, - struct dentry *parent, const char *name, +static struct dentry *hypfs_create_file(struct dentry *parent, const char *name, char *data, umode_t mode) { struct dentry *dentry; @@ -347,7 +345,7 @@ static struct dentry *hypfs_create_file(struct super_block *sb, dentry = ERR_PTR(-ENOMEM); goto fail; } - inode = hypfs_make_inode(sb, mode); + inode = hypfs_make_inode(parent->d_sb, mode); if (!inode) { dput(dentry); dentry = ERR_PTR(-ENOMEM); @@ -373,24 +371,22 @@ fail: return dentry; } -struct dentry *hypfs_mkdir(struct super_block *sb, struct dentry *parent, - const char *name) +struct dentry *hypfs_mkdir(struct dentry *parent, const char *name) { struct dentry *dentry; - dentry = hypfs_create_file(sb, parent, name, NULL, S_IFDIR | DIR_MODE); + dentry = hypfs_create_file(parent, name, NULL, S_IFDIR | DIR_MODE); if (IS_ERR(dentry)) return dentry; hypfs_add_dentry(dentry); return dentry; } -static struct dentry *hypfs_create_update_file(struct super_block *sb, - struct dentry *dir) +static struct dentry *hypfs_create_update_file(struct dentry *dir) { struct dentry *dentry; - dentry = hypfs_create_file(sb, dir, "update", NULL, + dentry = hypfs_create_file(dir, "update", NULL, S_IFREG | UPDATE_FILE_MODE); /* * We do not put the update file on the 'delete' list with @@ -400,7 +396,7 @@ static struct dentry *hypfs_create_update_file(struct super_block *sb, return dentry; } -struct dentry *hypfs_create_u64(struct super_block *sb, struct dentry *dir, +struct dentry *hypfs_create_u64(struct dentry *dir, const char *name, __u64 value) { char *buffer; @@ -412,7 +408,7 @@ struct dentry *hypfs_create_u64(struct super_block *sb, struct dentry *dir, if (!buffer) return ERR_PTR(-ENOMEM); dentry = - hypfs_create_file(sb, dir, name, buffer, S_IFREG | REG_FILE_MODE); + hypfs_create_file(dir, name, buffer, S_IFREG | REG_FILE_MODE); if (IS_ERR(dentry)) { kfree(buffer); return ERR_PTR(-ENOMEM); @@ -421,7 +417,7 @@ struct dentry *hypfs_create_u64(struct super_block *sb, struct dentry *dir, return dentry; } -struct dentry *hypfs_create_str(struct super_block *sb, struct dentry *dir, +struct dentry *hypfs_create_str(struct dentry *dir, const char *name, char *string) { char *buffer; @@ -432,7 +428,7 @@ struct dentry *hypfs_create_str(struct super_block *sb, struct dentry *dir, return ERR_PTR(-ENOMEM); sprintf(buffer, "%s\n", string); dentry = - hypfs_create_file(sb, dir, name, buffer, S_IFREG | REG_FILE_MODE); + hypfs_create_file(dir, name, buffer, S_IFREG | REG_FILE_MODE); if (IS_ERR(dentry)) { kfree(buffer); return ERR_PTR(-ENOMEM); diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h index 1eaa3625803c..5f8bcc5fe423 100644 --- a/arch/s390/include/asm/irq.h +++ b/arch/s390/include/asm/irq.h @@ -78,10 +78,14 @@ typedef void (*ext_int_handler_t)(struct ext_code, unsigned int, unsigned long); int register_external_interrupt(u16 code, ext_int_handler_t handler); int unregister_external_interrupt(u16 code, ext_int_handler_t handler); -void service_subclass_irq_register(void); -void service_subclass_irq_unregister(void); -void measurement_alert_subclass_register(void); -void measurement_alert_subclass_unregister(void); + +enum irq_subclass { + IRQ_SUBCLASS_MEASUREMENT_ALERT = 5, + IRQ_SUBCLASS_SERVICE_SIGNAL = 9, +}; + +void irq_subclass_register(enum irq_subclass subclass); +void irq_subclass_unregister(enum irq_subclass subclass); #define irq_canonicalize(irq) (irq) diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h index dcf6948a875c..4176dfe0fba1 100644 --- a/arch/s390/include/asm/kprobes.h +++ b/arch/s390/include/asm/kprobes.h @@ -31,6 +31,8 @@ #include <linux/ptrace.h> #include <linux/percpu.h> +#define __ARCH_WANT_KPROBES_INSN_SLOT + struct pt_regs; struct kprobe; @@ -57,7 +59,7 @@ typedef u16 kprobe_opcode_t; /* Architecture specific copy of original instruction */ struct arch_specific_insn { /* copy of original instruction */ - kprobe_opcode_t insn[MAX_INSN_SIZE]; + kprobe_opcode_t *insn; }; struct prev_kprobe { diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 3238d4004e84..e87ecaa2c569 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -274,6 +274,14 @@ struct kvm_arch{ int css_support; }; +#define KVM_HVA_ERR_BAD (-1UL) +#define KVM_HVA_ERR_RO_BAD (-2UL) + +static inline bool kvm_is_error_hva(unsigned long addr) +{ + return IS_ERR_VALUE(addr); +} + extern int sie64a(struct kvm_s390_sie_block *, u64 *); extern char sie_exit; #endif diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h index 6340178748bf..ff132ac64ddd 100644 --- a/arch/s390/include/asm/mmu.h +++ b/arch/s390/include/asm/mmu.h @@ -12,8 +12,6 @@ typedef struct { unsigned long asce_bits; unsigned long asce_limit; unsigned long vdso_base; - /* Cloned contexts will be created with extended page tables. */ - unsigned int alloc_pgste:1; /* The mmu context has extended page tables. */ unsigned int has_pgste:1; } mm_context_t; diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index 7b7fce4e8469..9f973d8de90e 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -21,24 +21,7 @@ static inline int init_new_context(struct task_struct *tsk, #ifdef CONFIG_64BIT mm->context.asce_bits |= _ASCE_TYPE_REGION3; #endif - if (current->mm && current->mm->context.alloc_pgste) { - /* - * alloc_pgste indicates, that any NEW context will be created - * with extended page tables. The old context is unchanged. The - * page table allocation and the page table operations will - * look at has_pgste to distinguish normal and extended page - * tables. The only way to create extended page tables is to - * set alloc_pgste and then create a new context (e.g. dup_mm). - * The page table allocation is called after init_new_context - * and if has_pgste is set, it will create extended page - * tables. - */ - mm->context.has_pgste = 1; - mm->context.alloc_pgste = 1; - } else { - mm->context.has_pgste = 0; - mm->context.alloc_pgste = 0; - } + mm->context.has_pgste = 0; mm->context.asce_limit = STACK_TOP_MAX; crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm)); return 0; diff --git a/arch/s390/include/asm/mutex.h b/arch/s390/include/asm/mutex.h index 688271f5f2e4..458c1f7fbc18 100644 --- a/arch/s390/include/asm/mutex.h +++ b/arch/s390/include/asm/mutex.h @@ -7,5 +7,3 @@ */ #include <asm-generic/mutex-dec.h> - -#define arch_mutex_cpu_relax() barrier() diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index c290f13d1c47..1cc185da9d38 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -22,10 +22,6 @@ void pci_iounmap(struct pci_dev *, void __iomem *); int pci_domain_nr(struct pci_bus *); int pci_proc_domain(struct pci_bus *); -/* MSI arch hooks */ -#define arch_setup_msi_irqs arch_setup_msi_irqs -#define arch_teardown_msi_irqs arch_teardown_msi_irqs - #define ZPCI_BUS_NR 0 /* default bus number */ #define ZPCI_DEVFN 0 /* default device number */ diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 9f215b40109e..9b60a36c348d 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1442,6 +1442,17 @@ static inline pmd_t pmd_mkwrite(pmd_t pmd) } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLB_PAGE */ +static inline void pmdp_flush_lazy(struct mm_struct *mm, + unsigned long address, pmd_t *pmdp) +{ + int active = (mm == current->active_mm) ? 1 : 0; + + if ((atomic_read(&mm->context.attach_count) & 0xffff) > active) + __pmd_idte(address, pmdp); + else + mm->context.flush_mm = 1; +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_PGTABLE_DEPOSIT diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index b0e6435b2f02..ca7821f07260 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -43,6 +43,7 @@ extern void execve_tail(void); #ifndef CONFIG_64BIT #define TASK_SIZE (1UL << 31) +#define TASK_MAX_SIZE (1UL << 31) #define TASK_UNMAPPED_BASE (1UL << 30) #else /* CONFIG_64BIT */ @@ -51,6 +52,7 @@ extern void execve_tail(void); #define TASK_UNMAPPED_BASE (test_thread_flag(TIF_31BIT) ? \ (1UL << 30) : (1UL << 41)) #define TASK_SIZE TASK_SIZE_OF(current) +#define TASK_MAX_SIZE (1UL << 53) #endif /* CONFIG_64BIT */ @@ -196,6 +198,8 @@ static inline void cpu_relax(void) barrier(); } +#define arch_mutex_cpu_relax() barrier() + static inline void psw_set_key(unsigned int key) { asm volatile("spka 0(%0)" : : "d" (key)); diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h index 06a136136047..7dc7f9c63b65 100644 --- a/arch/s390/include/asm/sclp.h +++ b/arch/s390/include/asm/sclp.h @@ -56,5 +56,6 @@ bool sclp_has_linemode(void); bool sclp_has_vt220(void); int sclp_pci_configure(u32 fid); int sclp_pci_deconfigure(u32 fid); +int memcpy_hsa(void *dest, unsigned long src, size_t count, int mode); #endif /* _ASM_S390_SCLP_H */ diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h index 701fe8c59e1f..83e5d216105e 100644 --- a/arch/s390/include/asm/spinlock.h +++ b/arch/s390/include/asm/spinlock.h @@ -44,6 +44,11 @@ extern void arch_spin_lock_wait_flags(arch_spinlock_t *, unsigned long flags); extern int arch_spin_trylock_retry(arch_spinlock_t *); extern void arch_spin_relax(arch_spinlock_t *lock); +static inline int arch_spin_value_unlocked(arch_spinlock_t lock) +{ + return lock.owner_cpu == 0; +} + static inline void arch_spin_lock(arch_spinlock_t *lp) { int old; diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 8b6e4f5288a2..1f1b8c70ab97 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -221,25 +221,26 @@ static int groups16_from_user(struct group_info *group_info, u16 __user *groupli asmlinkage long sys32_getgroups16(int gidsetsize, u16 __user *grouplist) { + const struct cred *cred = current_cred(); int i; if (gidsetsize < 0) return -EINVAL; - get_group_info(current->cred->group_info); - i = current->cred->group_info->ngroups; + get_group_info(cred->group_info); + i = cred->group_info->ngroups; if (gidsetsize) { if (i > gidsetsize) { i = -EINVAL; goto out; } - if (groups16_to_user(grouplist, current->cred->group_info)) { + if (groups16_to_user(grouplist, cred->group_info)) { i = -EFAULT; goto out; } } out: - put_group_info(current->cred->group_info); + put_group_info(cred->group_info); return i; } diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c index c439ac9ced09..1389b637dae5 100644 --- a/arch/s390/kernel/compat_signal.c +++ b/arch/s390/kernel/compat_signal.c @@ -332,9 +332,9 @@ static int setup_frame32(int sig, struct k_sigaction *ka, /* Set up to return from userspace. If provided, use a stub already in userspace. */ if (ka->sa.sa_flags & SA_RESTORER) { - regs->gprs[14] = (__u64) ka->sa.sa_restorer | PSW32_ADDR_AMODE; + regs->gprs[14] = (__u64 __force) ka->sa.sa_restorer | PSW32_ADDR_AMODE; } else { - regs->gprs[14] = (__u64) frame->retcode | PSW32_ADDR_AMODE; + regs->gprs[14] = (__u64 __force) frame->retcode | PSW32_ADDR_AMODE; if (__put_user(S390_SYSCALL_OPCODE | __NR_sigreturn, (u16 __force __user *)(frame->retcode))) goto give_sigsegv; @@ -400,9 +400,9 @@ static int setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info, /* Set up to return from userspace. If provided, use a stub already in userspace. */ if (ka->sa.sa_flags & SA_RESTORER) { - regs->gprs[14] = (__u64) ka->sa.sa_restorer | PSW32_ADDR_AMODE; + regs->gprs[14] = (__u64 __force) ka->sa.sa_restorer | PSW32_ADDR_AMODE; } else { - regs->gprs[14] = (__u64) frame->retcode | PSW32_ADDR_AMODE; + regs->gprs[14] = (__u64 __force) frame->retcode | PSW32_ADDR_AMODE; err |= __put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn, (u16 __force __user *)(frame->retcode)); } @@ -417,7 +417,7 @@ static int setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info, regs->psw.mask = PSW_MASK_BA | (psw_user_bits & PSW_MASK_ASC) | (regs->psw.mask & ~PSW_MASK_ASC); - regs->psw.addr = (__u64) ka->sa.sa_handler; + regs->psw.addr = (__u64 __force) ka->sa.sa_handler; regs->gprs[2] = map_signal(sig); regs->gprs[3] = (__force __u64) &frame->info; diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index d8f355657171..c84f33d51f7b 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -16,6 +16,7 @@ #include <asm/os_info.h> #include <asm/elf.h> #include <asm/ipl.h> +#include <asm/sclp.h> #define PTR_ADD(x, y) (((char *) (x)) + ((unsigned long) (y))) #define PTR_SUB(x, y) (((char *) (x)) - ((unsigned long) (y))) @@ -64,22 +65,46 @@ static ssize_t copy_page_real(void *buf, void *src, size_t csize) } /* - * Copy one page from "oldmem" + * Pointer to ELF header in new kernel + */ +static void *elfcorehdr_newmem; + +/* + * Copy one page from zfcpdump "oldmem" + * + * For pages below ZFCPDUMP_HSA_SIZE memory from the HSA is copied. Otherwise + * real memory copy is used. + */ +static ssize_t copy_oldmem_page_zfcpdump(char *buf, size_t csize, + unsigned long src, int userbuf) +{ + int rc; + + if (src < ZFCPDUMP_HSA_SIZE) { + rc = memcpy_hsa(buf, src, csize, userbuf); + } else { + if (userbuf) + rc = copy_to_user_real((void __force __user *) buf, + (void *) src, csize); + else + rc = memcpy_real(buf, (void *) src, csize); + } + return rc ? rc : csize; +} + +/* + * Copy one page from kdump "oldmem" * * For the kdump reserved memory this functions performs a swap operation: * - [OLDMEM_BASE - OLDMEM_BASE + OLDMEM_SIZE] is mapped to [0 - OLDMEM_SIZE]. * - [0 - OLDMEM_SIZE] is mapped to [OLDMEM_BASE - OLDMEM_BASE + OLDMEM_SIZE] */ -ssize_t copy_oldmem_page(unsigned long pfn, char *buf, - size_t csize, unsigned long offset, int userbuf) +static ssize_t copy_oldmem_page_kdump(char *buf, size_t csize, + unsigned long src, int userbuf) + { - unsigned long src; int rc; - if (!csize) - return 0; - - src = (pfn << PAGE_SHIFT) + offset; if (src < OLDMEM_SIZE) src += OLDMEM_BASE; else if (src > OLDMEM_BASE && @@ -90,7 +115,88 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, (void *) src, csize); else rc = copy_page_real(buf, (void *) src, csize); - return (rc == 0) ? csize : rc; + return (rc == 0) ? rc : csize; +} + +/* + * Copy one page from "oldmem" + */ +ssize_t copy_oldmem_page(unsigned long pfn, char *buf, size_t csize, + unsigned long offset, int userbuf) +{ + unsigned long src; + + if (!csize) + return 0; + src = (pfn << PAGE_SHIFT) + offset; + if (OLDMEM_BASE) + return copy_oldmem_page_kdump(buf, csize, src, userbuf); + else + return copy_oldmem_page_zfcpdump(buf, csize, src, userbuf); +} + +/* + * Remap "oldmem" for kdump + * + * For the kdump reserved memory this functions performs a swap operation: + * [0 - OLDMEM_SIZE] is mapped to [OLDMEM_BASE - OLDMEM_BASE + OLDMEM_SIZE] + */ +static int remap_oldmem_pfn_range_kdump(struct vm_area_struct *vma, + unsigned long from, unsigned long pfn, + unsigned long size, pgprot_t prot) +{ + unsigned long size_old; + int rc; + + if (pfn < OLDMEM_SIZE >> PAGE_SHIFT) { + size_old = min(size, OLDMEM_SIZE - (pfn << PAGE_SHIFT)); + rc = remap_pfn_range(vma, from, + pfn + (OLDMEM_BASE >> PAGE_SHIFT), + size_old, prot); + if (rc || size == size_old) + return rc; + size -= size_old; + from += size_old; + pfn += size_old >> PAGE_SHIFT; + } + return remap_pfn_range(vma, from, pfn, size, prot); +} + +/* + * Remap "oldmem" for zfcpdump + * + * We only map available memory above ZFCPDUMP_HSA_SIZE. Memory below + * ZFCPDUMP_HSA_SIZE is read on demand using the copy_oldmem_page() function. + */ +static int remap_oldmem_pfn_range_zfcpdump(struct vm_area_struct *vma, + unsigned long from, + unsigned long pfn, + unsigned long size, pgprot_t prot) +{ + unsigned long size_hsa; + + if (pfn < ZFCPDUMP_HSA_SIZE >> PAGE_SHIFT) { + size_hsa = min(size, ZFCPDUMP_HSA_SIZE - (pfn << PAGE_SHIFT)); + if (size == size_hsa) + return 0; + size -= size_hsa; + from += size_hsa; + pfn += size_hsa >> PAGE_SHIFT; + } + return remap_pfn_range(vma, from, pfn, size, prot); +} + +/* + * Remap "oldmem" for kdump or zfcpdump + */ +int remap_oldmem_pfn_range(struct vm_area_struct *vma, unsigned long from, + unsigned long pfn, unsigned long size, pgprot_t prot) +{ + if (OLDMEM_BASE) + return remap_oldmem_pfn_range_kdump(vma, from, pfn, size, prot); + else + return remap_oldmem_pfn_range_zfcpdump(vma, from, pfn, size, + prot); } /* @@ -101,11 +207,21 @@ int copy_from_oldmem(void *dest, void *src, size_t count) unsigned long copied = 0; int rc; - if ((unsigned long) src < OLDMEM_SIZE) { - copied = min(count, OLDMEM_SIZE - (unsigned long) src); - rc = memcpy_real(dest, src + OLDMEM_BASE, copied); - if (rc) - return rc; + if (OLDMEM_BASE) { + if ((unsigned long) src < OLDMEM_SIZE) { + copied = min(count, OLDMEM_SIZE - (unsigned long) src); + rc = memcpy_real(dest, src + OLDMEM_BASE, copied); + if (rc) + return rc; + } + } else { + if ((unsigned long) src < ZFCPDUMP_HSA_SIZE) { + copied = min(count, + ZFCPDUMP_HSA_SIZE - (unsigned long) src); + rc = memcpy_hsa(dest, (unsigned long) src, copied, 0); + if (rc) + return rc; + } } return memcpy_real(dest + copied, src + copied, count - copied); } @@ -368,14 +484,6 @@ static int get_mem_chunk_cnt(void) } /* - * Relocate pointer in order to allow vmcore code access the data - */ -static inline unsigned long relocate(unsigned long addr) -{ - return OLDMEM_BASE + addr; -} - -/* * Initialize ELF loads (new kernel) */ static int loads_init(Elf64_Phdr *phdr, u64 loads_offset) @@ -426,7 +534,7 @@ static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset) ptr = nt_vmcoreinfo(ptr); memset(phdr, 0, sizeof(*phdr)); phdr->p_type = PT_NOTE; - phdr->p_offset = relocate(notes_offset); + phdr->p_offset = notes_offset; phdr->p_filesz = (unsigned long) PTR_SUB(ptr, ptr_start); phdr->p_memsz = phdr->p_filesz; return ptr; @@ -435,7 +543,7 @@ static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset) /* * Create ELF core header (new kernel) */ -static void s390_elf_corehdr_create(char **elfcorebuf, size_t *elfcorebuf_sz) +int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size) { Elf64_Phdr *phdr_notes, *phdr_loads; int mem_chunk_cnt; @@ -443,6 +551,12 @@ static void s390_elf_corehdr_create(char **elfcorebuf, size_t *elfcorebuf_sz) u32 alloc_size; u64 hdr_off; + /* If we are not in kdump or zfcpdump mode return */ + if (!OLDMEM_BASE && ipl_info.type != IPL_TYPE_FCP_DUMP) + return 0; + /* If elfcorehdr= has been passed via cmdline, we use that one */ + if (elfcorehdr_addr != ELFCORE_ADDR_MAX) + return 0; mem_chunk_cnt = get_mem_chunk_cnt(); alloc_size = 0x1000 + get_cpu_cnt() * 0x300 + @@ -460,27 +574,52 @@ static void s390_elf_corehdr_create(char **elfcorebuf, size_t *elfcorebuf_sz) ptr = notes_init(phdr_notes, ptr, ((unsigned long) hdr) + hdr_off); /* Init loads */ hdr_off = PTR_DIFF(ptr, hdr); - loads_init(phdr_loads, ((unsigned long) hdr) + hdr_off); - *elfcorebuf_sz = hdr_off; - *elfcorebuf = (void *) relocate((unsigned long) hdr); - BUG_ON(*elfcorebuf_sz > alloc_size); + loads_init(phdr_loads, hdr_off); + *addr = (unsigned long long) hdr; + elfcorehdr_newmem = hdr; + *size = (unsigned long long) hdr_off; + BUG_ON(elfcorehdr_size > alloc_size); + return 0; } /* - * Create kdump ELF core header in new kernel, if it has not been passed via - * the "elfcorehdr" kernel parameter + * Free ELF core header (new kernel) */ -static int setup_kdump_elfcorehdr(void) +void elfcorehdr_free(unsigned long long addr) { - size_t elfcorebuf_sz; - char *elfcorebuf; + if (!elfcorehdr_newmem) + return; + kfree((void *)(unsigned long)addr); +} - if (!OLDMEM_BASE || is_kdump_kernel()) - return -EINVAL; - s390_elf_corehdr_create(&elfcorebuf, &elfcorebuf_sz); - elfcorehdr_addr = (unsigned long long) elfcorebuf; - elfcorehdr_size = elfcorebuf_sz; - return 0; +/* + * Read from ELF header + */ +ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos) +{ + void *src = (void *)(unsigned long)*ppos; + + src = elfcorehdr_newmem ? src : src - OLDMEM_BASE; + memcpy(buf, src, count); + *ppos += count; + return count; } -subsys_initcall(setup_kdump_elfcorehdr); +/* + * Read from ELF notes data + */ +ssize_t elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos) +{ + void *src = (void *)(unsigned long)*ppos; + int rc; + + if (elfcorehdr_newmem) { + memcpy(buf, src, count); + } else { + rc = copy_from_oldmem(buf, src, count); + if (rc) + return rc; + } + *ppos += count; + return count; +} diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c index 87acc38f73c6..99e7f6035895 100644 --- a/arch/s390/kernel/dumpstack.c +++ b/arch/s390/kernel/dumpstack.c @@ -40,14 +40,15 @@ __show_trace(unsigned long sp, unsigned long low, unsigned long high) { struct stack_frame *sf; struct pt_regs *regs; + unsigned long addr; while (1) { sp = sp & PSW_ADDR_INSN; if (sp < low || sp > high - sizeof(*sf)) return sp; sf = (struct stack_frame *) sp; - printk("([<%016lx>] ", sf->gprs[8] & PSW_ADDR_INSN); - print_symbol("%s)\n", sf->gprs[8] & PSW_ADDR_INSN); + addr = sf->gprs[8] & PSW_ADDR_INSN; + printk("([<%016lx>] %pSR)\n", addr, (void *)addr); /* Follow the backchain. */ while (1) { low = sp; @@ -57,16 +58,16 @@ __show_trace(unsigned long sp, unsigned long low, unsigned long high) if (sp <= low || sp > high - sizeof(*sf)) return sp; sf = (struct stack_frame *) sp; - printk(" [<%016lx>] ", sf->gprs[8] & PSW_ADDR_INSN); - print_symbol("%s\n", sf->gprs[8] & PSW_ADDR_INSN); + addr = sf->gprs[8] & PSW_ADDR_INSN; + printk(" [<%016lx>] %pSR\n", addr, (void *)addr); } /* Zero backchain detected, check for interrupt frame. */ sp = (unsigned long) (sf + 1); if (sp <= low || sp > high - sizeof(*regs)) return sp; regs = (struct pt_regs *) sp; - printk(" [<%016lx>] ", regs->psw.addr & PSW_ADDR_INSN); - print_symbol("%s\n", regs->psw.addr & PSW_ADDR_INSN); + addr = regs->psw.addr & PSW_ADDR_INSN; + printk(" [<%016lx>] %pSR\n", addr, (void *)addr); low = sp; sp = regs->gprs[15]; } @@ -128,8 +129,7 @@ static void show_last_breaking_event(struct pt_regs *regs) { #ifdef CONFIG_64BIT printk("Last Breaking-Event-Address:\n"); - printk(" [<%016lx>] ", regs->args[0] & PSW_ADDR_INSN); - print_symbol("%s\n", regs->args[0] & PSW_ADDR_INSN); + printk(" [<%016lx>] %pSR\n", regs->args[0], (void *)regs->args[0]); #endif } @@ -143,10 +143,10 @@ void show_registers(struct pt_regs *regs) char *mode; mode = user_mode(regs) ? "User" : "Krnl"; - printk("%s PSW : %p %p", + printk("%s PSW : %p %p (%pSR)\n", mode, (void *) regs->psw.mask, + (void *) regs->psw.addr, (void *) regs->psw.addr); - print_symbol(" (%s)\n", regs->psw.addr & PSW_ADDR_INSN); printk(" R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x " "P:%x AS:%x CC:%x PM:%x", mask_bits(regs, PSW_MASK_PER), mask_bits(regs, PSW_MASK_DAT), mask_bits(regs, PSW_MASK_IO), diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index 3ddbc26d246e..e9b04c33d383 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -53,27 +53,21 @@ void handle_signal32(unsigned long sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *oldset, struct pt_regs *regs); void do_notify_resume(struct pt_regs *regs); -struct ext_code; -void do_extint(struct pt_regs *regs); +void __init init_IRQ(void); +void do_IRQ(struct pt_regs *regs, int irq); void do_restart(void); void __init startup_init(void); void die(struct pt_regs *regs, const char *str); - +int setup_profiling_timer(unsigned int multiplier); void __init time_init(void); +int pfn_is_nosave(unsigned long); +void s390_early_resume(void); +unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip); struct s390_mmap_arg_struct; struct fadvise64_64_args; struct old_sigaction; -long sys_mmap2(struct s390_mmap_arg_struct __user *arg); -long sys_s390_ipc(uint call, int first, unsigned long second, - unsigned long third, void __user *ptr); -long sys_s390_personality(unsigned int personality); -long sys_s390_fadvise64(int fd, u32 offset_high, u32 offset_low, - size_t len, int advice); -long sys_s390_fadvise64_64(struct fadvise64_64_args __user *args); -long sys_s390_fallocate(int fd, int mode, loff_t offset, u32 len_high, - u32 len_low); long sys_sigreturn(void); long sys_rt_sigreturn(void); long sys32_sigreturn(void); diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index e3043aef87a9..1014ad5f7693 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -15,6 +15,7 @@ #include <linux/kprobes.h> #include <trace/syscall.h> #include <asm/asm-offsets.h> +#include "entry.h" #ifdef CONFIG_DYNAMIC_FTRACE @@ -177,7 +178,7 @@ int ftrace_enable_ftrace_graph_caller(void) offset = ((void *) prepare_ftrace_return - (void *) ftrace_graph_caller) / 2; - return probe_kernel_write(ftrace_graph_caller + 2, + return probe_kernel_write((void *) ftrace_graph_caller + 2, &offset, sizeof(offset)); } @@ -185,7 +186,7 @@ int ftrace_disable_ftrace_graph_caller(void) { static unsigned short offset = 0x0002; - return probe_kernel_write(ftrace_graph_caller + 2, + return probe_kernel_write((void *) ftrace_graph_caller + 2, &offset, sizeof(offset)); } diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index b34ba0ea96a9..8ac2097f13d4 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -196,21 +196,23 @@ asmlinkage void do_softirq(void) * ext_int_hash[index] is the list head for all external interrupts that hash * to this index. */ -static struct list_head ext_int_hash[256]; +static struct hlist_head ext_int_hash[32] ____cacheline_aligned; struct ext_int_info { ext_int_handler_t handler; - u16 code; - struct list_head entry; + struct hlist_node entry; struct rcu_head rcu; + u16 code; }; /* ext_int_hash_lock protects the handler lists for external interrupts */ -DEFINE_SPINLOCK(ext_int_hash_lock); +static DEFINE_SPINLOCK(ext_int_hash_lock); static inline int ext_hash(u16 code) { - return (code + (code >> 9)) & 0xff; + BUILD_BUG_ON(!is_power_of_2(ARRAY_SIZE(ext_int_hash))); + + return (code + (code >> 9)) & (ARRAY_SIZE(ext_int_hash) - 1); } int register_external_interrupt(u16 code, ext_int_handler_t handler) @@ -227,7 +229,7 @@ int register_external_interrupt(u16 code, ext_int_handler_t handler) index = ext_hash(code); spin_lock_irqsave(&ext_int_hash_lock, flags); - list_add_rcu(&p->entry, &ext_int_hash[index]); + hlist_add_head_rcu(&p->entry, &ext_int_hash[index]); spin_unlock_irqrestore(&ext_int_hash_lock, flags); return 0; } @@ -240,9 +242,9 @@ int unregister_external_interrupt(u16 code, ext_int_handler_t handler) int index = ext_hash(code); spin_lock_irqsave(&ext_int_hash_lock, flags); - list_for_each_entry_rcu(p, &ext_int_hash[index], entry) { + hlist_for_each_entry_rcu(p, &ext_int_hash[index], entry) { if (p->code == code && p->handler == handler) { - list_del_rcu(&p->entry); + hlist_del_rcu(&p->entry); kfree_rcu(p, rcu); } } @@ -264,12 +266,12 @@ static irqreturn_t do_ext_interrupt(int irq, void *dummy) index = ext_hash(ext_code.code); rcu_read_lock(); - list_for_each_entry_rcu(p, &ext_int_hash[index], entry) - if (likely(p->code == ext_code.code)) - p->handler(ext_code, regs->int_parm, - regs->int_parm_long); + hlist_for_each_entry_rcu(p, &ext_int_hash[index], entry) { + if (unlikely(p->code != ext_code.code)) + continue; + p->handler(ext_code, regs->int_parm, regs->int_parm_long); + } rcu_read_unlock(); - return IRQ_HANDLED; } @@ -283,55 +285,32 @@ void __init init_ext_interrupts(void) int idx; for (idx = 0; idx < ARRAY_SIZE(ext_int_hash); idx++) - INIT_LIST_HEAD(&ext_int_hash[idx]); + INIT_HLIST_HEAD(&ext_int_hash[idx]); irq_set_chip_and_handler(EXT_INTERRUPT, &dummy_irq_chip, handle_percpu_irq); setup_irq(EXT_INTERRUPT, &external_interrupt); } -static DEFINE_SPINLOCK(sc_irq_lock); -static int sc_irq_refcount; - -void service_subclass_irq_register(void) -{ - spin_lock(&sc_irq_lock); - if (!sc_irq_refcount) - ctl_set_bit(0, 9); - sc_irq_refcount++; - spin_unlock(&sc_irq_lock); -} -EXPORT_SYMBOL(service_subclass_irq_register); - -void service_subclass_irq_unregister(void) -{ - spin_lock(&sc_irq_lock); - sc_irq_refcount--; - if (!sc_irq_refcount) - ctl_clear_bit(0, 9); - spin_unlock(&sc_irq_lock); -} -EXPORT_SYMBOL(service_subclass_irq_unregister); - -static DEFINE_SPINLOCK(ma_subclass_lock); -static int ma_subclass_refcount; +static DEFINE_SPINLOCK(irq_subclass_lock); +static unsigned char irq_subclass_refcount[64]; -void measurement_alert_subclass_register(void) +void irq_subclass_register(enum irq_subclass subclass) { - spin_lock(&ma_subclass_lock); - if (!ma_subclass_refcount) - ctl_set_bit(0, 5); - ma_subclass_refcount++; - spin_unlock(&ma_subclass_lock); + spin_lock(&irq_subclass_lock); + if (!irq_subclass_refcount[subclass]) + ctl_set_bit(0, subclass); + irq_subclass_refcount[subclass]++; + spin_unlock(&irq_subclass_lock); } -EXPORT_SYMBOL(measurement_alert_subclass_register); +EXPORT_SYMBOL(irq_subclass_register); -void measurement_alert_subclass_unregister(void) +void irq_subclass_unregister(enum irq_subclass subclass) { - spin_lock(&ma_subclass_lock); - ma_subclass_refcount--; - if (!ma_subclass_refcount) - ctl_clear_bit(0, 5); - spin_unlock(&ma_subclass_lock); + spin_lock(&irq_subclass_lock); + irq_subclass_refcount[subclass]--; + if (!irq_subclass_refcount[subclass]) + ctl_clear_bit(0, subclass); + spin_unlock(&irq_subclass_lock); } -EXPORT_SYMBOL(measurement_alert_subclass_unregister); +EXPORT_SYMBOL(irq_subclass_unregister); diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index adbbe7f1cb0d..0ce9fb245034 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -37,6 +37,26 @@ DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); struct kretprobe_blackpoint kretprobe_blacklist[] = { }; +DEFINE_INSN_CACHE_OPS(dmainsn); + +static void *alloc_dmainsn_page(void) +{ + return (void *)__get_free_page(GFP_KERNEL | GFP_DMA); +} + +static void free_dmainsn_page(void *page) +{ + free_page((unsigned long)page); +} + +struct kprobe_insn_cache kprobe_dmainsn_slots = { + .mutex = __MUTEX_INITIALIZER(kprobe_dmainsn_slots.mutex), + .alloc = alloc_dmainsn_page, + .free = free_dmainsn_page, + .pages = LIST_HEAD_INIT(kprobe_dmainsn_slots.pages), + .insn_size = MAX_INSN_SIZE, +}; + static int __kprobes is_prohibited_opcode(kprobe_opcode_t *insn) { switch (insn[0] >> 8) { @@ -100,9 +120,8 @@ static int __kprobes get_fixup_type(kprobe_opcode_t *insn) fixup |= FIXUP_RETURN_REGISTER; break; case 0xc0: - if ((insn[0] & 0x0f) == 0x00 || /* larl */ - (insn[0] & 0x0f) == 0x05) /* brasl */ - fixup |= FIXUP_RETURN_REGISTER; + if ((insn[0] & 0x0f) == 0x05) /* brasl */ + fixup |= FIXUP_RETURN_REGISTER; break; case 0xeb: switch (insn[2] & 0xff) { @@ -134,18 +153,128 @@ static int __kprobes get_fixup_type(kprobe_opcode_t *insn) return fixup; } +static int __kprobes is_insn_relative_long(kprobe_opcode_t *insn) +{ + /* Check if we have a RIL-b or RIL-c format instruction which + * we need to modify in order to avoid instruction emulation. */ + switch (insn[0] >> 8) { + case 0xc0: + if ((insn[0] & 0x0f) == 0x00) /* larl */ + return true; + break; + case 0xc4: + switch (insn[0] & 0x0f) { + case 0x02: /* llhrl */ + case 0x04: /* lghrl */ + case 0x05: /* lhrl */ + case 0x06: /* llghrl */ + case 0x07: /* sthrl */ + case 0x08: /* lgrl */ + case 0x0b: /* stgrl */ + case 0x0c: /* lgfrl */ + case 0x0d: /* lrl */ + case 0x0e: /* llgfrl */ + case 0x0f: /* strl */ + return true; + } + break; + case 0xc6: + switch (insn[0] & 0x0f) { + case 0x00: /* exrl */ + case 0x02: /* pfdrl */ + case 0x04: /* cghrl */ + case 0x05: /* chrl */ + case 0x06: /* clghrl */ + case 0x07: /* clhrl */ + case 0x08: /* cgrl */ + case 0x0a: /* clgrl */ + case 0x0c: /* cgfrl */ + case 0x0d: /* crl */ + case 0x0e: /* clgfrl */ + case 0x0f: /* clrl */ + return true; + } + break; + } + return false; +} + +static void __kprobes copy_instruction(struct kprobe *p) +{ + s64 disp, new_disp; + u64 addr, new_addr; + + memcpy(p->ainsn.insn, p->addr, ((p->opcode >> 14) + 3) & -2); + if (!is_insn_relative_long(p->ainsn.insn)) + return; + /* + * For pc-relative instructions in RIL-b or RIL-c format patch the + * RI2 displacement field. We have already made sure that the insn + * slot for the patched instruction is within the same 2GB area + * as the original instruction (either kernel image or module area). + * Therefore the new displacement will always fit. + */ + disp = *(s32 *)&p->ainsn.insn[1]; + addr = (u64)(unsigned long)p->addr; + new_addr = (u64)(unsigned long)p->ainsn.insn; + new_disp = ((addr + (disp * 2)) - new_addr) / 2; + *(s32 *)&p->ainsn.insn[1] = new_disp; +} + +static inline int is_kernel_addr(void *addr) +{ + return addr < (void *)_end; +} + +static inline int is_module_addr(void *addr) +{ +#ifdef CONFIG_64BIT + BUILD_BUG_ON(MODULES_LEN > (1UL << 31)); + if (addr < (void *)MODULES_VADDR) + return 0; + if (addr > (void *)MODULES_END) + return 0; +#endif + return 1; +} + +static int __kprobes s390_get_insn_slot(struct kprobe *p) +{ + /* + * Get an insn slot that is within the same 2GB area like the original + * instruction. That way instructions with a 32bit signed displacement + * field can be patched and executed within the insn slot. + */ + p->ainsn.insn = NULL; + if (is_kernel_addr(p->addr)) + p->ainsn.insn = get_dmainsn_slot(); + if (is_module_addr(p->addr)) + p->ainsn.insn = get_insn_slot(); + return p->ainsn.insn ? 0 : -ENOMEM; +} + +static void __kprobes s390_free_insn_slot(struct kprobe *p) +{ + if (!p->ainsn.insn) + return; + if (is_kernel_addr(p->addr)) + free_dmainsn_slot(p->ainsn.insn, 0); + else + free_insn_slot(p->ainsn.insn, 0); + p->ainsn.insn = NULL; +} + int __kprobes arch_prepare_kprobe(struct kprobe *p) { if ((unsigned long) p->addr & 0x01) return -EINVAL; - /* Make sure the probe isn't going on a difficult instruction */ if (is_prohibited_opcode(p->addr)) return -EINVAL; - + if (s390_get_insn_slot(p)) + return -ENOMEM; p->opcode = *p->addr; - memcpy(p->ainsn.insn, p->addr, ((p->opcode >> 14) + 3) & -2); - + copy_instruction(p); return 0; } @@ -186,6 +315,7 @@ void __kprobes arch_disarm_kprobe(struct kprobe *p) void __kprobes arch_remove_kprobe(struct kprobe *p) { + s390_free_insn_slot(p); } static void __kprobes enable_singlestep(struct kprobe_ctlblk *kcb, diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index ac2178161ec3..719e27b2cf22 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -50,7 +50,7 @@ static void add_elf_notes(int cpu) /* * Initialize CPU ELF notes */ -void setup_regs(void) +static void setup_regs(void) { unsigned long sa = S390_lowcore.prefixreg_save_area + SAVE_AREA_BASE; int cpu, this_cpu; diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index fb99c2057b85..1105502bf6e9 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -274,7 +274,7 @@ static int reserve_pmc_hardware(void) int flags = PMC_INIT; on_each_cpu(setup_pmc_cpu, &flags, 1); - measurement_alert_subclass_register(); + irq_subclass_register(IRQ_SUBCLASS_MEASUREMENT_ALERT); return 0; } @@ -285,7 +285,7 @@ static void release_pmc_hardware(void) int flags = PMC_RELEASE; on_each_cpu(setup_pmc_cpu, &flags, 1); - measurement_alert_subclass_unregister(); + irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT); } /* Release the PMU if event is the last perf event */ diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c index 500aa1029bcb..2343c218b8f9 100644 --- a/arch/s390/kernel/perf_event.c +++ b/arch/s390/kernel/perf_event.c @@ -105,13 +105,10 @@ void perf_event_print_debug(void) cpu = smp_processor_id(); memset(&cf_info, 0, sizeof(cf_info)); - if (!qctri(&cf_info)) { + if (!qctri(&cf_info)) pr_info("CPU[%i] CPUM_CF: ver=%u.%u A=%04x E=%04x C=%04x\n", cpu, cf_info.cfvn, cf_info.csvn, cf_info.auth_ctl, cf_info.enable_ctl, cf_info.act_ctl); - print_hex_dump_bytes("CPUMF Query: ", DUMP_PREFIX_OFFSET, - &cf_info, sizeof(cf_info)); - } local_irq_restore(flags); } diff --git a/arch/s390/kernel/runtime_instr.c b/arch/s390/kernel/runtime_instr.c index 077a99389b07..e1c9d1c292fa 100644 --- a/arch/s390/kernel/runtime_instr.c +++ b/arch/s390/kernel/runtime_instr.c @@ -139,10 +139,10 @@ static int __init runtime_instr_init(void) if (!runtime_instr_avail()) return 0; - measurement_alert_subclass_register(); + irq_subclass_register(IRQ_SUBCLASS_MEASUREMENT_ALERT); rc = register_external_interrupt(0x1407, runtime_instr_int_handler); if (rc) - measurement_alert_subclass_unregister(); + irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT); else pr_info("Runtime instrumentation facility initialized\n"); return rc; diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index d386c4e9d2e5..1a4313a1b60f 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -362,7 +362,7 @@ void smp_yield_cpu(int cpu) * Send cpus emergency shutdown signal. This gives the cpus the * opportunity to complete outstanding interrupts. */ -void smp_emergency_stop(cpumask_t *cpumask) +static void smp_emergency_stop(cpumask_t *cpumask) { u64 end; int cpu; diff --git a/arch/s390/kernel/suspend.c b/arch/s390/kernel/suspend.c index 737bff38e3ee..a7a7537ce1e7 100644 --- a/arch/s390/kernel/suspend.c +++ b/arch/s390/kernel/suspend.c @@ -13,6 +13,7 @@ #include <asm/ipl.h> #include <asm/cio.h> #include <asm/pci.h> +#include "entry.h" /* * References to section boundaries diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index 3074475c8ae0..3a74d8af0d69 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -119,12 +119,21 @@ static int __diag_virtio_hypercall(struct kvm_vcpu *vcpu) * The layout is as follows: * - gpr 2 contains the subchannel id (passed as addr) * - gpr 3 contains the virtqueue index (passed as datamatch) + * - gpr 4 contains the index on the bus (optionally) */ - ret = kvm_io_bus_write(vcpu->kvm, KVM_VIRTIO_CCW_NOTIFY_BUS, - vcpu->run->s.regs.gprs[2], - 8, &vcpu->run->s.regs.gprs[3]); + ret = kvm_io_bus_write_cookie(vcpu->kvm, KVM_VIRTIO_CCW_NOTIFY_BUS, + vcpu->run->s.regs.gprs[2], + 8, &vcpu->run->s.regs.gprs[3], + vcpu->run->s.regs.gprs[4]); srcu_read_unlock(&vcpu->kvm->srcu, idx); - /* kvm_io_bus_write returns -EOPNOTSUPP if it found no match. */ + + /* + * Return cookie in gpr 2, but don't overwrite the register if the + * diagnose will be handled by userspace. + */ + if (ret != -EOPNOTSUPP) + vcpu->run->s.regs.gprs[2] = ret; + /* kvm_io_bus_write_cookie returns -EOPNOTSUPP if it found no match. */ return ret < 0 ? ret : 0; } diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h index 302e0e52b009..99d789e8a018 100644 --- a/arch/s390/kvm/gaccess.h +++ b/arch/s390/kvm/gaccess.h @@ -42,9 +42,11 @@ static inline void __user *__gptr_to_uptr(struct kvm_vcpu *vcpu, ({ \ __typeof__(gptr) __uptr = __gptr_to_uptr(vcpu, gptr, 1);\ int __mask = sizeof(__typeof__(*(gptr))) - 1; \ - int __ret = PTR_RET((void __force *)__uptr); \ + int __ret; \ \ - if (!__ret) { \ + if (IS_ERR((void __force *)__uptr)) { \ + __ret = PTR_ERR((void __force *)__uptr); \ + } else { \ BUG_ON((unsigned long)__uptr & __mask); \ __ret = get_user(x, __uptr); \ } \ @@ -55,9 +57,11 @@ static inline void __user *__gptr_to_uptr(struct kvm_vcpu *vcpu, ({ \ __typeof__(gptr) __uptr = __gptr_to_uptr(vcpu, gptr, 1);\ int __mask = sizeof(__typeof__(*(gptr))) - 1; \ - int __ret = PTR_RET((void __force *)__uptr); \ + int __ret; \ \ - if (!__ret) { \ + if (IS_ERR((void __force *)__uptr)) { \ + __ret = PTR_ERR((void __force *)__uptr); \ + } else { \ BUG_ON((unsigned long)__uptr & __mask); \ __ret = put_user(x, __uptr); \ } \ diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 34c1c9a90be2..776dafe918db 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -28,6 +28,7 @@ #include <asm/pgtable.h> #include <asm/nmi.h> #include <asm/switch_to.h> +#include <asm/facility.h> #include <asm/sclp.h> #include "kvm-s390.h" #include "gaccess.h" @@ -84,9 +85,15 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { NULL } }; -static unsigned long long *facilities; +unsigned long *vfacilities; static struct gmap_notifier gmap_notifier; +/* test availability of vfacility */ +static inline int test_vfacility(unsigned long nr) +{ + return __test_facility(nr, (void *) vfacilities); +} + /* Section: not file related */ int kvm_arch_hardware_enable(void *garbage) { @@ -387,7 +394,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) vcpu->arch.sie_block->ecb = 6; vcpu->arch.sie_block->ecb2 = 8; vcpu->arch.sie_block->eca = 0xC1002001U; - vcpu->arch.sie_block->fac = (int) (long) facilities; + vcpu->arch.sie_block->fac = (int) (long) vfacilities; hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS); tasklet_init(&vcpu->arch.tasklet, kvm_s390_tasklet, (unsigned long) vcpu); @@ -1063,6 +1070,10 @@ int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages) return 0; } +void kvm_arch_memslots_updated(struct kvm *kvm) +{ +} + /* Section: memory related */ int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, @@ -1129,20 +1140,20 @@ static int __init kvm_s390_init(void) * to hold the maximum amount of facilities. On the other hand, we * only set facilities that are known to work in KVM. */ - facilities = (unsigned long long *) get_zeroed_page(GFP_KERNEL|GFP_DMA); - if (!facilities) { + vfacilities = (unsigned long *) get_zeroed_page(GFP_KERNEL|GFP_DMA); + if (!vfacilities) { kvm_exit(); return -ENOMEM; } - memcpy(facilities, S390_lowcore.stfle_fac_list, 16); - facilities[0] &= 0xff82fff3f47c0000ULL; - facilities[1] &= 0x001c000000000000ULL; + memcpy(vfacilities, S390_lowcore.stfle_fac_list, 16); + vfacilities[0] &= 0xff82fff3f47c0000UL; + vfacilities[1] &= 0x001c000000000000UL; return 0; } static void __exit kvm_s390_exit(void) { - free_page((unsigned long) facilities); + free_page((unsigned long) vfacilities); kvm_exit(); } diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 028ca9fd2158..dc99f1ca4267 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -24,6 +24,9 @@ typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu); +/* declare vfacilities extern */ +extern unsigned long *vfacilities; + /* negativ values are error codes, positive values for internal conditions */ #define SIE_INTERCEPT_RERUNVCPU (1<<0) #define SIE_INTERCEPT_UCONTROL (1<<1) @@ -112,6 +115,13 @@ static inline u64 kvm_s390_get_base_disp_rs(struct kvm_vcpu *vcpu) return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2; } +/* Set the condition code in the guest program status word */ +static inline void kvm_s390_set_psw_cc(struct kvm_vcpu *vcpu, unsigned long cc) +{ + vcpu->arch.sie_block->gpsw.mask &= ~(3UL << 44); + vcpu->arch.sie_block->gpsw.mask |= cc << 44; +} + int kvm_s390_handle_wait(struct kvm_vcpu *vcpu); enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer); void kvm_s390_tasklet(unsigned long parm); diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 4cdc54e63ebc..59200ee275e5 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -164,8 +164,7 @@ static int handle_tpi(struct kvm_vcpu *vcpu) kfree(inti); no_interrupt: /* Set condition code and we're done. */ - vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44); - vcpu->arch.sie_block->gpsw.mask |= (cc & 3ul) << 44; + kvm_s390_set_psw_cc(vcpu, cc); return 0; } @@ -220,15 +219,13 @@ static int handle_io_inst(struct kvm_vcpu *vcpu) * Set condition code 3 to stop the guest from issueing channel * I/O instructions. */ - vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44); - vcpu->arch.sie_block->gpsw.mask |= (3 & 3ul) << 44; + kvm_s390_set_psw_cc(vcpu, 3); return 0; } } static int handle_stfl(struct kvm_vcpu *vcpu) { - unsigned int facility_list; int rc; vcpu->stat.instruction_stfl++; @@ -236,15 +233,13 @@ static int handle_stfl(struct kvm_vcpu *vcpu) if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - /* only pass the facility bits, which we can handle */ - facility_list = S390_lowcore.stfl_fac_list & 0xff82fff3; - rc = copy_to_guest(vcpu, offsetof(struct _lowcore, stfl_fac_list), - &facility_list, sizeof(facility_list)); + vfacilities, 4); if (rc) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - VCPU_EVENT(vcpu, 5, "store facility list value %x", facility_list); - trace_kvm_s390_handle_stfl(vcpu, facility_list); + VCPU_EVENT(vcpu, 5, "store facility list value %x", + *(unsigned int *) vfacilities); + trace_kvm_s390_handle_stfl(vcpu, *(unsigned int *) vfacilities); return 0; } @@ -387,7 +382,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); if (fc > 3) { - vcpu->arch.sie_block->gpsw.mask |= 3ul << 44; /* cc 3 */ + kvm_s390_set_psw_cc(vcpu, 3); return 0; } @@ -397,7 +392,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu) if (fc == 0) { vcpu->run->s.regs.gprs[0] = 3 << 28; - vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44); /* cc 0 */ + kvm_s390_set_psw_cc(vcpu, 0); return 0; } @@ -431,12 +426,11 @@ static int handle_stsi(struct kvm_vcpu *vcpu) } trace_kvm_s390_handle_stsi(vcpu, fc, sel1, sel2, operand2); free_page(mem); - vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44); + kvm_s390_set_psw_cc(vcpu, 0); vcpu->run->s.regs.gprs[0] = 0; return 0; out_no_data: - /* condition code 3 */ - vcpu->arch.sie_block->gpsw.mask |= 3ul << 44; + kvm_s390_set_psw_cc(vcpu, 3); out_exception: free_page(mem); return rc; @@ -494,12 +488,12 @@ static int handle_epsw(struct kvm_vcpu *vcpu) kvm_s390_get_regs_rre(vcpu, ®1, ®2); /* This basically extracts the mask half of the psw. */ - vcpu->run->s.regs.gprs[reg1] &= 0xffffffff00000000; + vcpu->run->s.regs.gprs[reg1] &= 0xffffffff00000000UL; vcpu->run->s.regs.gprs[reg1] |= vcpu->arch.sie_block->gpsw.mask >> 32; if (reg2) { - vcpu->run->s.regs.gprs[reg2] &= 0xffffffff00000000; + vcpu->run->s.regs.gprs[reg2] &= 0xffffffff00000000UL; vcpu->run->s.regs.gprs[reg2] |= - vcpu->arch.sie_block->gpsw.mask & 0x00000000ffffffff; + vcpu->arch.sie_block->gpsw.mask & 0x00000000ffffffffUL; } return 0; } diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index f00aefb66a4e..fc6679210d83 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -302,6 +302,8 @@ static inline int do_exception(struct pt_regs *regs, int access) address = trans_exc_code & __FAIL_ADDR_MASK; perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + if (user_mode(regs)) + flags |= FAULT_FLAG_USER; if (access == VM_WRITE || (trans_exc_code & store_indication) == 0x400) flags |= FAULT_FLAG_WRITE; down_read(&mm->mmap_sem); @@ -673,7 +675,7 @@ static int __init pfault_irq_init(void) rc = pfault_init() == 0 ? 0 : -EOPNOTSUPP; if (rc) goto out_pfault; - service_subclass_irq_register(); + irq_subclass_register(IRQ_SUBCLASS_SERVICE_SIGNAL); hotcpu_notifier(pfault_cpu_notify, 0); return 0; diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index 248445f92604..d261c62e40a6 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -223,6 +223,11 @@ int pud_huge(pud_t pud) return 0; } +int pmd_huge_support(void) +{ + return 1; +} + struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmdp, int write) { diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c index 921fa541dc04..d1e0e0c7a7e2 100644 --- a/arch/s390/mm/maccess.c +++ b/arch/s390/mm/maccess.c @@ -14,6 +14,7 @@ #include <linux/gfp.h> #include <linux/cpu.h> #include <asm/ctl_reg.h> +#include <asm/io.h> /* * This function writes to kernel memory bypassing DAT and possible diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 6d16132d0850..de8cbc30dcd1 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -245,7 +245,9 @@ EXPORT_SYMBOL_GPL(gmap_disable); * gmap_alloc_table is assumed to be called with mmap_sem held */ static int gmap_alloc_table(struct gmap *gmap, - unsigned long *table, unsigned long init) + unsigned long *table, unsigned long init) + __releases(&gmap->mm->page_table_lock) + __acquires(&gmap->mm->page_table_lock) { struct page *page; unsigned long *new; @@ -335,7 +337,7 @@ int gmap_map_segment(struct gmap *gmap, unsigned long from, if ((from | to | len) & (PMD_SIZE - 1)) return -EINVAL; - if (len == 0 || from + len > PGDIR_SIZE || + if (len == 0 || from + len > TASK_MAX_SIZE || from + len < from || to + len < to) return -EINVAL; @@ -732,6 +734,11 @@ void gmap_do_ipte_notify(struct mm_struct *mm, unsigned long addr, pte_t *pte) spin_unlock(&gmap_notifier_lock); } +static inline int page_table_with_pgste(struct page *page) +{ + return atomic_read(&page->_mapcount) == 0; +} + static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm, unsigned long vmaddr) { @@ -751,7 +758,7 @@ static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm, mp->vmaddr = vmaddr & PMD_MASK; INIT_LIST_HEAD(&mp->mapper); page->index = (unsigned long) mp; - atomic_set(&page->_mapcount, 3); + atomic_set(&page->_mapcount, 0); table = (unsigned long *) page_to_phys(page); clear_table(table, _PAGE_INVALID, PAGE_SIZE/2); clear_table(table + PTRS_PER_PTE, PGSTE_HR_BIT | PGSTE_HC_BIT, @@ -818,6 +825,11 @@ EXPORT_SYMBOL(set_guest_storage_key); #else /* CONFIG_PGSTE */ +static inline int page_table_with_pgste(struct page *page) +{ + return 0; +} + static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm, unsigned long vmaddr) { @@ -894,12 +906,12 @@ void page_table_free(struct mm_struct *mm, unsigned long *table) struct page *page; unsigned int bit, mask; - if (mm_has_pgste(mm)) { + page = pfn_to_page(__pa(table) >> PAGE_SHIFT); + if (page_table_with_pgste(page)) { gmap_disconnect_pgtable(mm, table); return page_table_free_pgste(table); } /* Free 1K/2K page table fragment of a 4K page */ - page = pfn_to_page(__pa(table) >> PAGE_SHIFT); bit = 1 << ((__pa(table) & ~PAGE_MASK)/(PTRS_PER_PTE*sizeof(pte_t))); spin_lock_bh(&mm->context.list_lock); if ((atomic_read(&page->_mapcount) & FRAG_MASK) != FRAG_MASK) @@ -937,14 +949,14 @@ void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table) unsigned int bit, mask; mm = tlb->mm; - if (mm_has_pgste(mm)) { + page = pfn_to_page(__pa(table) >> PAGE_SHIFT); + if (page_table_with_pgste(page)) { gmap_disconnect_pgtable(mm, table); table = (unsigned long *) (__pa(table) | FRAG_MASK); tlb_remove_table(tlb, table); return; } bit = 1 << ((__pa(table) & ~PAGE_MASK) / (PTRS_PER_PTE*sizeof(pte_t))); - page = pfn_to_page(__pa(table) >> PAGE_SHIFT); spin_lock_bh(&mm->context.list_lock); if ((atomic_read(&page->_mapcount) & FRAG_MASK) != FRAG_MASK) list_del(&page->lru); @@ -956,7 +968,7 @@ void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table) tlb_remove_table(tlb, table); } -void __tlb_remove_table(void *_table) +static void __tlb_remove_table(void *_table) { const unsigned long mask = (FRAG_MASK << 4) | FRAG_MASK; void *table = (void *)((unsigned long) _table & ~mask); @@ -1030,36 +1042,120 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table) } #ifdef CONFIG_TRANSPARENT_HUGEPAGE -void thp_split_vma(struct vm_area_struct *vma) +static inline void thp_split_vma(struct vm_area_struct *vma) { unsigned long addr; - struct page *page; - for (addr = vma->vm_start; addr < vma->vm_end; addr += PAGE_SIZE) { - page = follow_page(vma, addr, FOLL_SPLIT); - } + for (addr = vma->vm_start; addr < vma->vm_end; addr += PAGE_SIZE) + follow_page(vma, addr, FOLL_SPLIT); } -void thp_split_mm(struct mm_struct *mm) +static inline void thp_split_mm(struct mm_struct *mm) { - struct vm_area_struct *vma = mm->mmap; + struct vm_area_struct *vma; - while (vma != NULL) { + for (vma = mm->mmap; vma != NULL; vma = vma->vm_next) { thp_split_vma(vma); vma->vm_flags &= ~VM_HUGEPAGE; vma->vm_flags |= VM_NOHUGEPAGE; - vma = vma->vm_next; } + mm->def_flags |= VM_NOHUGEPAGE; +} +#else +static inline void thp_split_mm(struct mm_struct *mm) +{ } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +static unsigned long page_table_realloc_pmd(struct mmu_gather *tlb, + struct mm_struct *mm, pud_t *pud, + unsigned long addr, unsigned long end) +{ + unsigned long next, *table, *new; + struct page *page; + pmd_t *pmd; + + pmd = pmd_offset(pud, addr); + do { + next = pmd_addr_end(addr, end); +again: + if (pmd_none_or_clear_bad(pmd)) + continue; + table = (unsigned long *) pmd_deref(*pmd); + page = pfn_to_page(__pa(table) >> PAGE_SHIFT); + if (page_table_with_pgste(page)) + continue; + /* Allocate new page table with pgstes */ + new = page_table_alloc_pgste(mm, addr); + if (!new) { + mm->context.has_pgste = 0; + continue; + } + spin_lock(&mm->page_table_lock); + if (likely((unsigned long *) pmd_deref(*pmd) == table)) { + /* Nuke pmd entry pointing to the "short" page table */ + pmdp_flush_lazy(mm, addr, pmd); + pmd_clear(pmd); + /* Copy ptes from old table to new table */ + memcpy(new, table, PAGE_SIZE/2); + clear_table(table, _PAGE_INVALID, PAGE_SIZE/2); + /* Establish new table */ + pmd_populate(mm, pmd, (pte_t *) new); + /* Free old table with rcu, there might be a walker! */ + page_table_free_rcu(tlb, table); + new = NULL; + } + spin_unlock(&mm->page_table_lock); + if (new) { + page_table_free_pgste(new); + goto again; + } + } while (pmd++, addr = next, addr != end); + + return addr; +} + +static unsigned long page_table_realloc_pud(struct mmu_gather *tlb, + struct mm_struct *mm, pgd_t *pgd, + unsigned long addr, unsigned long end) +{ + unsigned long next; + pud_t *pud; + + pud = pud_offset(pgd, addr); + do { + next = pud_addr_end(addr, end); + if (pud_none_or_clear_bad(pud)) + continue; + next = page_table_realloc_pmd(tlb, mm, pud, addr, next); + } while (pud++, addr = next, addr != end); + + return addr; +} + +static void page_table_realloc(struct mmu_gather *tlb, struct mm_struct *mm, + unsigned long addr, unsigned long end) +{ + unsigned long next; + pgd_t *pgd; + + pgd = pgd_offset(mm, addr); + do { + next = pgd_addr_end(addr, end); + if (pgd_none_or_clear_bad(pgd)) + continue; + next = page_table_realloc_pud(tlb, mm, pgd, addr, next); + } while (pgd++, addr = next, addr != end); +} + /* * switch on pgstes for its userspace process (for kvm) */ int s390_enable_sie(void) { struct task_struct *tsk = current; - struct mm_struct *mm, *old_mm; + struct mm_struct *mm = tsk->mm; + struct mmu_gather tlb; /* Do we have switched amode? If no, we cannot do sie */ if (s390_user_mode == HOME_SPACE_MODE) @@ -1069,57 +1165,16 @@ int s390_enable_sie(void) if (mm_has_pgste(tsk->mm)) return 0; - /* lets check if we are allowed to replace the mm */ - task_lock(tsk); - if (!tsk->mm || atomic_read(&tsk->mm->mm_users) > 1 || -#ifdef CONFIG_AIO - !hlist_empty(&tsk->mm->ioctx_list) || -#endif - tsk->mm != tsk->active_mm) { - task_unlock(tsk); - return -EINVAL; - } - task_unlock(tsk); - - /* we copy the mm and let dup_mm create the page tables with_pgstes */ - tsk->mm->context.alloc_pgste = 1; - /* make sure that both mms have a correct rss state */ - sync_mm_rss(tsk->mm); - mm = dup_mm(tsk); - tsk->mm->context.alloc_pgste = 0; - if (!mm) - return -ENOMEM; - -#ifdef CONFIG_TRANSPARENT_HUGEPAGE + down_write(&mm->mmap_sem); /* split thp mappings and disable thp for future mappings */ thp_split_mm(mm); - mm->def_flags |= VM_NOHUGEPAGE; -#endif - - /* Now lets check again if something happened */ - task_lock(tsk); - if (!tsk->mm || atomic_read(&tsk->mm->mm_users) > 1 || -#ifdef CONFIG_AIO - !hlist_empty(&tsk->mm->ioctx_list) || -#endif - tsk->mm != tsk->active_mm) { - mmput(mm); - task_unlock(tsk); - return -EINVAL; - } - - /* ok, we are alone. No ptrace, no threads, etc. */ - old_mm = tsk->mm; - tsk->mm = tsk->active_mm = mm; - preempt_disable(); - update_mm(mm, tsk); - atomic_inc(&mm->context.attach_count); - atomic_dec(&old_mm->context.attach_count); - cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm)); - preempt_enable(); - task_unlock(tsk); - mmput(old_mm); - return 0; + /* Reallocate the page tables with pgstes */ + mm->context.has_pgste = 1; + tlb_gather_mmu(&tlb, mm, 0, TASK_SIZE); + page_table_realloc(&tlb, mm, 0, TASK_SIZE); + tlb_finish_mmu(&tlb, 0, TASK_SIZE); + up_write(&mm->mmap_sem); + return mm->context.has_pgste ? 0 : -ENOMEM; } EXPORT_SYMBOL_GPL(s390_enable_sie); diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index d5f10a43a58f..709239285869 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -805,7 +805,7 @@ static struct bpf_binary_header *bpf_alloc_binary(unsigned int bpfsize, return NULL; memset(header, 0, sz); header->pages = sz / PAGE_SIZE; - hole = sz - bpfsize + sizeof(*header); + hole = sz - (bpfsize + sizeof(*header)); /* Insert random number of illegal instructions before BPF code * and make sure the first instruction starts at an even address. */ diff --git a/arch/s390/oprofile/hwsampler.c b/arch/s390/oprofile/hwsampler.c index b5b2916895e0..231cecafc2f1 100644 --- a/arch/s390/oprofile/hwsampler.c +++ b/arch/s390/oprofile/hwsampler.c @@ -1001,7 +1001,7 @@ int hwsampler_deallocate(void) if (hws_state != HWS_STOPPED) goto deallocate_exit; - measurement_alert_subclass_unregister(); + irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT); deallocate_sdbt(); hws_state = HWS_DEALLOCATED; @@ -1115,7 +1115,7 @@ int hwsampler_shutdown(void) mutex_lock(&hws_sem); if (hws_state == HWS_STOPPED) { - measurement_alert_subclass_unregister(); + irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT); deallocate_sdbt(); } if (hws_wq) { @@ -1190,7 +1190,7 @@ start_all_exit: hws_oom = 1; hws_flush_all = 0; /* now let them in, 1407 CPUMF external interrupts */ - measurement_alert_subclass_register(); + irq_subclass_register(IRQ_SUBCLASS_MEASUREMENT_ALERT); return 0; } diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c index 930783d2c99b..04e1b6a85362 100644 --- a/arch/s390/oprofile/init.c +++ b/arch/s390/oprofile/init.c @@ -346,16 +346,15 @@ static const struct file_operations timer_enabled_fops = { }; -static int oprofile_create_hwsampling_files(struct super_block *sb, - struct dentry *root) +static int oprofile_create_hwsampling_files(struct dentry *root) { struct dentry *dir; - dir = oprofilefs_mkdir(sb, root, "timer"); + dir = oprofilefs_mkdir(root, "timer"); if (!dir) return -EINVAL; - oprofilefs_create_file(sb, dir, "enabled", &timer_enabled_fops); + oprofilefs_create_file(dir, "enabled", &timer_enabled_fops); if (!hwsampler_available) return 0; @@ -376,17 +375,17 @@ static int oprofile_create_hwsampling_files(struct super_block *sb, * and can only be set to 0. */ - dir = oprofilefs_mkdir(sb, root, "0"); + dir = oprofilefs_mkdir(root, "0"); if (!dir) return -EINVAL; - oprofilefs_create_file(sb, dir, "enabled", &hwsampler_fops); - oprofilefs_create_file(sb, dir, "event", &zero_fops); - oprofilefs_create_file(sb, dir, "count", &hw_interval_fops); - oprofilefs_create_file(sb, dir, "unit_mask", &zero_fops); - oprofilefs_create_file(sb, dir, "kernel", &kernel_fops); - oprofilefs_create_file(sb, dir, "user", &user_fops); - oprofilefs_create_ulong(sb, dir, "hw_sdbt_blocks", + oprofilefs_create_file(dir, "enabled", &hwsampler_fops); + oprofilefs_create_file(dir, "event", &zero_fops); + oprofilefs_create_file(dir, "count", &hw_interval_fops); + oprofilefs_create_file(dir, "unit_mask", &zero_fops); + oprofilefs_create_file(dir, "kernel", &kernel_fops); + oprofilefs_create_file(dir, "user", &user_fops); + oprofilefs_create_ulong(dir, "hw_sdbt_blocks", &oprofile_sdbt_blocks); } else { @@ -396,19 +395,19 @@ static int oprofile_create_hwsampling_files(struct super_block *sb, * space tools. The /dev/oprofile/hwsampling fs is * provided in that case. */ - dir = oprofilefs_mkdir(sb, root, "hwsampling"); + dir = oprofilefs_mkdir(root, "hwsampling"); if (!dir) return -EINVAL; - oprofilefs_create_file(sb, dir, "hwsampler", + oprofilefs_create_file(dir, "hwsampler", &hwsampler_fops); - oprofilefs_create_file(sb, dir, "hw_interval", + oprofilefs_create_file(dir, "hw_interval", &hw_interval_fops); - oprofilefs_create_ro_ulong(sb, dir, "hw_min_interval", + oprofilefs_create_ro_ulong(dir, "hw_min_interval", &oprofile_min_interval); - oprofilefs_create_ro_ulong(sb, dir, "hw_max_interval", + oprofilefs_create_ro_ulong(dir, "hw_max_interval", &oprofile_max_interval); - oprofilefs_create_ulong(sb, dir, "hw_sdbt_blocks", + oprofilefs_create_ulong(dir, "hw_sdbt_blocks", &oprofile_sdbt_blocks); } return 0; |