diff options
Diffstat (limited to 'arch/s390')
73 files changed, 887 insertions, 1098 deletions
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 43c0aca..c802352 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -95,6 +95,34 @@ config S390 select HAVE_ARCH_TRACEHOOK select INIT_ALL_POSSIBLE select HAVE_PERF_EVENTS + select ARCH_INLINE_SPIN_TRYLOCK + select ARCH_INLINE_SPIN_TRYLOCK_BH + select ARCH_INLINE_SPIN_LOCK + select ARCH_INLINE_SPIN_LOCK_BH + select ARCH_INLINE_SPIN_LOCK_IRQ + select ARCH_INLINE_SPIN_LOCK_IRQSAVE + select ARCH_INLINE_SPIN_UNLOCK + select ARCH_INLINE_SPIN_UNLOCK_BH + select ARCH_INLINE_SPIN_UNLOCK_IRQ + select ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE + select ARCH_INLINE_READ_TRYLOCK + select ARCH_INLINE_READ_LOCK + select ARCH_INLINE_READ_LOCK_BH + select ARCH_INLINE_READ_LOCK_IRQ + select ARCH_INLINE_READ_LOCK_IRQSAVE + select ARCH_INLINE_READ_UNLOCK + select ARCH_INLINE_READ_UNLOCK_BH + select ARCH_INLINE_READ_UNLOCK_IRQ + select ARCH_INLINE_READ_UNLOCK_IRQRESTORE + select ARCH_INLINE_WRITE_TRYLOCK + select ARCH_INLINE_WRITE_LOCK + select ARCH_INLINE_WRITE_LOCK_BH + select ARCH_INLINE_WRITE_LOCK_IRQ + select ARCH_INLINE_WRITE_LOCK_IRQSAVE + select ARCH_INLINE_WRITE_UNLOCK + select ARCH_INLINE_WRITE_UNLOCK_BH + select ARCH_INLINE_WRITE_UNLOCK_IRQ + select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE config SCHED_OMIT_FRAME_POINTER bool @@ -192,23 +220,8 @@ config AUDIT_ARCH bool default y -config S390_SWITCH_AMODE - bool "Switch kernel/user addressing modes" - help - This option allows to switch the addressing modes of kernel and user - space. The kernel parameter switch_amode=on will enable this feature, - default is disabled. Enabling this (via kernel parameter) on machines - earlier than IBM System z9-109 EC/BC will reduce system performance. - - Note that this option will also be selected by selecting the execute - protection option below. Enabling the execute protection via the - noexec kernel parameter will also switch the addressing modes, - independent of the switch_amode kernel parameter. - - config S390_EXEC_PROTECT bool "Data execute protection" - select S390_SWITCH_AMODE help This option allows to enable a buffer overflow protection for user space programs and it also selects the addressing mode option above. diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c index b55fd7e..5c91995 100644 --- a/arch/s390/appldata/appldata_base.c +++ b/arch/s390/appldata/appldata_base.c @@ -61,12 +61,12 @@ static struct ctl_table appldata_table[] = { { .procname = "timer", .mode = S_IRUGO | S_IWUSR, - .proc_handler = &appldata_timer_handler, + .proc_handler = appldata_timer_handler, }, { .procname = "interval", .mode = S_IRUGO | S_IWUSR, - .proc_handler = &appldata_interval_handler, + .proc_handler = appldata_interval_handler, }, { }, }; @@ -551,7 +551,7 @@ static int appldata_thaw(struct device *dev) return appldata_restore(dev); } -static struct dev_pm_ops appldata_pm_ops = { +static const struct dev_pm_ops appldata_pm_ops = { .freeze = appldata_freeze, .thaw = appldata_thaw, .restore = appldata_restore, diff --git a/arch/s390/appldata/appldata_net_sum.c b/arch/s390/appldata/appldata_net_sum.c index fa741f8..4ce7fa9 100644 --- a/arch/s390/appldata/appldata_net_sum.c +++ b/arch/s390/appldata/appldata_net_sum.c @@ -83,8 +83,9 @@ static void appldata_get_net_sum_data(void *data) rx_dropped = 0; tx_dropped = 0; collisions = 0; - read_lock(&dev_base_lock); - for_each_netdev(&init_net, dev) { + + rcu_read_lock(); + for_each_netdev_rcu(&init_net, dev) { const struct net_device_stats *stats = dev_get_stats(dev); rx_packets += stats->rx_packets; @@ -98,7 +99,8 @@ static void appldata_get_net_sum_data(void *data) collisions += stats->collisions; i++; } - read_unlock(&dev_base_lock); + rcu_read_unlock(); + net_data->nr_interfaces = i; net_data->rx_packets = rx_packets; net_data->tx_packets = tx_packets; diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c index 6118890..6be4503 100644 --- a/arch/s390/crypto/aes_s390.c +++ b/arch/s390/crypto/aes_s390.c @@ -174,7 +174,7 @@ static int fallback_init_cip(struct crypto_tfm *tfm) if (IS_ERR(sctx->fallback.cip)) { pr_err("Allocating AES fallback algorithm %s failed\n", name); - return PTR_ERR(sctx->fallback.blk); + return PTR_ERR(sctx->fallback.cip); } return 0; diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c index b49c00c..a320990 100644 --- a/arch/s390/crypto/prng.c +++ b/arch/s390/crypto/prng.c @@ -6,7 +6,6 @@ #include <linux/fs.h> #include <linux/init.h> #include <linux/kernel.h> -#include <linux/smp_lock.h> #include <linux/miscdevice.h> #include <linux/module.h> #include <linux/moduleparam.h> @@ -49,7 +48,6 @@ static unsigned char parm_block[32] = { static int prng_open(struct inode *inode, struct file *file) { - cycle_kernel_lock(); return nonseekable_open(inode, file); } diff --git a/arch/s390/defconfig b/arch/s390/defconfig index ab44644..b416aa1 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -1,7 +1,7 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.31 -# Tue Sep 22 17:43:13 2009 +# Linux kernel version: 2.6.33-rc2 +# Mon Jan 4 09:03:07 2010 # CONFIG_SCHED_MC=y CONFIG_MMU=y @@ -51,6 +51,7 @@ CONFIG_AUDIT=y # CONFIG_TREE_RCU=y # CONFIG_TREE_PREEMPT_RCU is not set +# CONFIG_TINY_RCU is not set # CONFIG_RCU_TRACE is not set CONFIG_RCU_FANOUT=64 # CONFIG_RCU_FANOUT_EXACT is not set @@ -113,7 +114,6 @@ CONFIG_HAVE_PERF_EVENTS=y # CONFIG_PERF_EVENTS is not set # CONFIG_PERF_COUNTERS is not set CONFIG_VM_EVENT_COUNTERS=y -# CONFIG_STRIP_ASM_SYMS is not set # CONFIG_COMPAT_BRK is not set CONFIG_SLAB=y # CONFIG_SLUB is not set @@ -149,21 +149,78 @@ CONFIG_STOP_MACHINE=y CONFIG_BLOCK=y CONFIG_BLK_DEV_BSG=y # CONFIG_BLK_DEV_INTEGRITY is not set +# CONFIG_BLK_CGROUP is not set CONFIG_BLOCK_COMPAT=y # # IO Schedulers # CONFIG_IOSCHED_NOOP=y -CONFIG_IOSCHED_AS=y CONFIG_IOSCHED_DEADLINE=y CONFIG_IOSCHED_CFQ=y -# CONFIG_DEFAULT_AS is not set +# CONFIG_CFQ_GROUP_IOSCHED is not set CONFIG_DEFAULT_DEADLINE=y # CONFIG_DEFAULT_CFQ is not set # CONFIG_DEFAULT_NOOP is not set CONFIG_DEFAULT_IOSCHED="deadline" CONFIG_PREEMPT_NOTIFIERS=y +CONFIG_ARCH_INLINE_SPIN_TRYLOCK=y +CONFIG_ARCH_INLINE_SPIN_TRYLOCK_BH=y +CONFIG_ARCH_INLINE_SPIN_LOCK=y +CONFIG_ARCH_INLINE_SPIN_LOCK_BH=y +CONFIG_ARCH_INLINE_SPIN_LOCK_IRQ=y +CONFIG_ARCH_INLINE_SPIN_LOCK_IRQSAVE=y +CONFIG_ARCH_INLINE_SPIN_UNLOCK=y +CONFIG_ARCH_INLINE_SPIN_UNLOCK_BH=y +CONFIG_ARCH_INLINE_SPIN_UNLOCK_IRQ=y +CONFIG_ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE=y +CONFIG_ARCH_INLINE_READ_TRYLOCK=y +CONFIG_ARCH_INLINE_READ_LOCK=y +CONFIG_ARCH_INLINE_READ_LOCK_BH=y +CONFIG_ARCH_INLINE_READ_LOCK_IRQ=y +CONFIG_ARCH_INLINE_READ_LOCK_IRQSAVE=y +CONFIG_ARCH_INLINE_READ_UNLOCK=y +CONFIG_ARCH_INLINE_READ_UNLOCK_BH=y +CONFIG_ARCH_INLINE_READ_UNLOCK_IRQ=y +CONFIG_ARCH_INLINE_READ_UNLOCK_IRQRESTORE=y +CONFIG_ARCH_INLINE_WRITE_TRYLOCK=y +CONFIG_ARCH_INLINE_WRITE_LOCK=y +CONFIG_ARCH_INLINE_WRITE_LOCK_BH=y +CONFIG_ARCH_INLINE_WRITE_LOCK_IRQ=y +CONFIG_ARCH_INLINE_WRITE_LOCK_IRQSAVE=y +CONFIG_ARCH_INLINE_WRITE_UNLOCK=y +CONFIG_ARCH_INLINE_WRITE_UNLOCK_BH=y +CONFIG_ARCH_INLINE_WRITE_UNLOCK_IRQ=y +CONFIG_ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE=y +# CONFIG_INLINE_SPIN_TRYLOCK is not set +# CONFIG_INLINE_SPIN_TRYLOCK_BH is not set +# CONFIG_INLINE_SPIN_LOCK is not set +# CONFIG_INLINE_SPIN_LOCK_BH is not set +# CONFIG_INLINE_SPIN_LOCK_IRQ is not set +# CONFIG_INLINE_SPIN_LOCK_IRQSAVE is not set +# CONFIG_INLINE_SPIN_UNLOCK is not set +# CONFIG_INLINE_SPIN_UNLOCK_BH is not set +# CONFIG_INLINE_SPIN_UNLOCK_IRQ is not set +# CONFIG_INLINE_SPIN_UNLOCK_IRQRESTORE is not set +# CONFIG_INLINE_READ_TRYLOCK is not set +# CONFIG_INLINE_READ_LOCK is not set +# CONFIG_INLINE_READ_LOCK_BH is not set +# CONFIG_INLINE_READ_LOCK_IRQ is not set +# CONFIG_INLINE_READ_LOCK_IRQSAVE is not set +# CONFIG_INLINE_READ_UNLOCK is not set +# CONFIG_INLINE_READ_UNLOCK_BH is not set +# CONFIG_INLINE_READ_UNLOCK_IRQ is not set +# CONFIG_INLINE_READ_UNLOCK_IRQRESTORE is not set +# CONFIG_INLINE_WRITE_TRYLOCK is not set +# CONFIG_INLINE_WRITE_LOCK is not set +# CONFIG_INLINE_WRITE_LOCK_BH is not set +# CONFIG_INLINE_WRITE_LOCK_IRQ is not set +# CONFIG_INLINE_WRITE_LOCK_IRQSAVE is not set +# CONFIG_INLINE_WRITE_UNLOCK is not set +# CONFIG_INLINE_WRITE_UNLOCK_BH is not set +# CONFIG_INLINE_WRITE_UNLOCK_IRQ is not set +# CONFIG_INLINE_WRITE_UNLOCK_IRQRESTORE is not set +# CONFIG_MUTEX_SPIN_ON_OWNER is not set CONFIG_FREEZER=y # @@ -185,7 +242,6 @@ CONFIG_HOTPLUG_CPU=y CONFIG_COMPAT=y CONFIG_SYSVIPC_COMPAT=y CONFIG_AUDIT_ARCH=y -CONFIG_S390_SWITCH_AMODE=y CONFIG_S390_EXEC_PROTECT=y # @@ -228,14 +284,13 @@ CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTPLUG_SPARSE=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_PAGEFLAGS_EXTENDED=y -CONFIG_SPLIT_PTLOCK_CPUS=4 +CONFIG_SPLIT_PTLOCK_CPUS=999999 CONFIG_MIGRATION=y CONFIG_PHYS_ADDR_T_64BIT=y CONFIG_ZONE_DMA_FLAG=1 CONFIG_BOUNCE=y CONFIG_VIRT_TO_BUS=y -CONFIG_HAVE_MLOCK=y -CONFIG_HAVE_MLOCKED_PAGE_BIT=y +# CONFIG_KSM is not set CONFIG_DEFAULT_MMAP_MIN_ADDR=4096 # @@ -340,6 +395,7 @@ CONFIG_INET6_XFRM_MODE_TUNNEL=y CONFIG_INET6_XFRM_MODE_BEET=y # CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION is not set CONFIG_IPV6_SIT=y +# CONFIG_IPV6_SIT_6RD is not set CONFIG_IPV6_NDISC_NODETYPE=y # CONFIG_IPV6_TUNNEL is not set # CONFIG_IPV6_MULTIPLE_TABLES is not set @@ -505,6 +561,10 @@ CONFIG_BLK_DEV=y # CONFIG_BLK_DEV_COW_COMMON is not set CONFIG_BLK_DEV_LOOP=m # CONFIG_BLK_DEV_CRYPTOLOOP is not set + +# +# DRBD disabled because PROC_FS, INET or CONNECTOR not selected +# CONFIG_BLK_DEV_NBD=m # CONFIG_BLK_DEV_OSD is not set CONFIG_BLK_DEV_RAM=y @@ -711,7 +771,6 @@ CONFIG_S390_VMUR=m # CONFIG_PPS is not set # CONFIG_POWER_SUPPLY is not set # CONFIG_THERMAL is not set -# CONFIG_THERMAL_HWMON is not set # CONFIG_WATCHDOG is not set # CONFIG_REGULATOR is not set # CONFIG_MEMSTICK is not set @@ -865,6 +924,7 @@ CONFIG_ENABLE_WARN_DEPRECATED=y CONFIG_ENABLE_MUST_CHECK=y CONFIG_FRAME_WARN=2048 CONFIG_MAGIC_SYSRQ=y +# CONFIG_STRIP_ASM_SYMS is not set # CONFIG_UNUSED_SYMBOLS is not set CONFIG_DEBUG_FS=y # CONFIG_HEADERS_CHECK is not set @@ -932,7 +992,6 @@ CONFIG_BRANCH_PROFILE_NONE=y CONFIG_SAMPLES=y # CONFIG_SAMPLE_KOBJECT is not set # CONFIG_SAMPLE_KPROBES is not set -# CONFIG_KMEMCHECK is not set # # Security options @@ -940,7 +999,11 @@ CONFIG_SAMPLES=y # CONFIG_KEYS is not set # CONFIG_SECURITY is not set # CONFIG_SECURITYFS is not set -# CONFIG_SECURITY_FILE_CAPABILITIES is not set +# CONFIG_DEFAULT_SECURITY_SELINUX is not set +# CONFIG_DEFAULT_SECURITY_SMACK is not set +# CONFIG_DEFAULT_SECURITY_TOMOYO is not set +CONFIG_DEFAULT_SECURITY_DAC=y +CONFIG_DEFAULT_SECURITY="" CONFIG_CRYPTO=y # diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c index 704dd39..2b92d50 100644 --- a/arch/s390/hypfs/hypfs_diag.c +++ b/arch/s390/hypfs/hypfs_diag.c @@ -164,7 +164,7 @@ static inline void part_hdr__part_name(enum diag204_format type, void *hdr, LPAR_NAME_LEN); EBCASC(name, LPAR_NAME_LEN); name[LPAR_NAME_LEN] = 0; - strstrip(name); + strim(name); } struct cpu_info { @@ -438,7 +438,7 @@ static int diag204_probe(void) } if (diag204((unsigned long)SUBC_STIB6 | (unsigned long)INFO_EXT, pages, buf) >= 0) { - diag204_store_sc = SUBC_STIB7; + diag204_store_sc = SUBC_STIB6; diag204_info_type = INFO_EXT; goto out; } @@ -523,7 +523,7 @@ static int diag224_idx2name(int index, char *name) memcpy(name, diag224_cpu_names + ((index + 1) * CPU_NAME_LEN), CPU_NAME_LEN); name[CPU_NAME_LEN] = 0; - strstrip(name); + strim(name); return 0; } diff --git a/arch/s390/hypfs/hypfs_vm.c b/arch/s390/hypfs/hypfs_vm.c index d01fc8f7..f0b0d31 100644 --- a/arch/s390/hypfs/hypfs_vm.c +++ b/arch/s390/hypfs/hypfs_vm.c @@ -124,7 +124,7 @@ static int hpyfs_vm_create_guest(struct super_block *sb, /* guest dir */ memcpy(guest_name, data->guest_name, NAME_LEN); EBCASC(guest_name, NAME_LEN); - strstrip(guest_name); + strim(guest_name); guest_dir = hypfs_mkdir(sb, systems_dir, guest_name); if (IS_ERR(guest_dir)) return PTR_ERR(guest_dir); diff --git a/arch/s390/include/asm/asm-offsets.h b/arch/s390/include/asm/asm-offsets.h new file mode 100644 index 0000000..d370ee3 --- /dev/null +++ b/arch/s390/include/asm/asm-offsets.h @@ -0,0 +1 @@ +#include <generated/asm-offsets.h> diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h index ae7c8f9..2a113d6 100644 --- a/arch/s390/include/asm/atomic.h +++ b/arch/s390/include/asm/atomic.h @@ -21,7 +21,7 @@ #if __GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ > 2) #define __CS_LOOP(ptr, op_val, op_string) ({ \ - typeof(ptr->counter) old_val, new_val; \ + int old_val, new_val; \ asm volatile( \ " l %0,%2\n" \ "0: lr %1,%0\n" \ @@ -38,7 +38,7 @@ #else /* __GNUC__ */ #define __CS_LOOP(ptr, op_val, op_string) ({ \ - typeof(ptr->counter) old_val, new_val; \ + int old_val, new_val; \ asm volatile( \ " l %0,0(%3)\n" \ "0: lr %1,%0\n" \ @@ -143,7 +143,7 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u) #if __GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ > 2) #define __CSG_LOOP(ptr, op_val, op_string) ({ \ - typeof(ptr->counter) old_val, new_val; \ + long long old_val, new_val; \ asm volatile( \ " lg %0,%2\n" \ "0: lgr %1,%0\n" \ @@ -160,7 +160,7 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u) #else /* __GNUC__ */ #define __CSG_LOOP(ptr, op_val, op_string) ({ \ - typeof(ptr->counter) old_val, new_val; \ + long long old_val, new_val; \ asm volatile( \ " lg %0,0(%3)\n" \ "0: lgr %1,%0\n" \ diff --git a/arch/s390/include/asm/bug.h b/arch/s390/include/asm/bug.h index 7efd0ab..efb74fd 100644 --- a/arch/s390/include/asm/bug.h +++ b/arch/s390/include/asm/bug.h @@ -49,7 +49,7 @@ #define BUG() do { \ __EMIT_BUG(0); \ - for (;;); \ + unreachable(); \ } while (0) #define WARN_ON(x) ({ \ diff --git a/arch/s390/include/asm/cacheflush.h b/arch/s390/include/asm/cacheflush.h index 49d5af9..405cc97 100644 --- a/arch/s390/include/asm/cacheflush.h +++ b/arch/s390/include/asm/cacheflush.h @@ -10,6 +10,7 @@ #define flush_cache_dup_mm(mm) do { } while (0) #define flush_cache_range(vma, start, end) do { } while (0) #define flush_cache_page(vma, vmaddr, pfn) do { } while (0) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 #define flush_dcache_page(page) do { } while (0) #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) diff --git a/arch/s390/include/asm/ccwdev.h b/arch/s390/include/asm/ccwdev.h index 2a54195..f4bd346 100644 --- a/arch/s390/include/asm/ccwdev.h +++ b/arch/s390/include/asm/ccwdev.h @@ -142,6 +142,8 @@ struct ccw1; extern int ccw_device_set_options_mask(struct ccw_device *, unsigned long); extern int ccw_device_set_options(struct ccw_device *, unsigned long); extern void ccw_device_clear_options(struct ccw_device *, unsigned long); +int ccw_device_is_pathgroup(struct ccw_device *cdev); +int ccw_device_is_multipath(struct ccw_device *cdev); /* Allow for i/o completion notification after primary interrupt status. */ #define CCWDEV_EARLY_NOTIFICATION 0x0001 @@ -151,6 +153,8 @@ extern void ccw_device_clear_options(struct ccw_device *, unsigned long); #define CCWDEV_DO_PATHGROUP 0x0004 /* Allow forced onlining of boxed devices. */ #define CCWDEV_ALLOW_FORCE 0x0008 +/* Try to use multipath mode. */ +#define CCWDEV_DO_MULTIPATH 0x0010 extern int ccw_device_start(struct ccw_device *, struct ccw1 *, unsigned long, __u8, unsigned long); diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h index 24b1244..258ba88 100644 --- a/arch/s390/include/asm/cputime.h +++ b/arch/s390/include/asm/cputime.h @@ -78,7 +78,7 @@ cputime64_to_jiffies64(cputime64_t cputime) static inline unsigned int cputime_to_msecs(const cputime_t cputime) { - return __div(cputime, 4096000); + return cputime_div(cputime, 4096000); } static inline cputime_t @@ -160,7 +160,7 @@ cputime_to_timeval(const cputime_t cputime, struct timeval *value) static inline clock_t cputime_to_clock_t(cputime_t cputime) { - return __div(cputime, 4096000000ULL / USER_HZ); + return cputime_div(cputime, 4096000000ULL / USER_HZ); } static inline cputime_t @@ -175,7 +175,7 @@ clock_t_to_cputime(unsigned long x) static inline clock_t cputime64_to_clock_t(cputime64_t cputime) { - return __div(cputime, 4096000000ULL / USER_HZ); + return cputime_div(cputime, 4096000000ULL / USER_HZ); } struct s390_idle_data { @@ -183,6 +183,7 @@ struct s390_idle_data { unsigned long long idle_count; unsigned long long idle_enter; unsigned long long idle_time; + int nohz_delay; }; DECLARE_PER_CPU(struct s390_idle_data, s390_idle); @@ -198,4 +199,11 @@ static inline void s390_idle_check(void) vtime_start_cpu(); } +static inline int s390_nohz_delay(int cpu) +{ + return per_cpu(s390_idle, cpu).nohz_delay != 0; +} + +#define arch_needs_cpu(cpu) s390_nohz_delay(cpu) + #endif /* _S390_CPUTIME_H */ diff --git a/arch/s390/include/asm/delay.h b/arch/s390/include/asm/delay.h index a356c95..8a096b8 100644 --- a/arch/s390/include/asm/delay.h +++ b/arch/s390/include/asm/delay.h @@ -14,10 +14,11 @@ #ifndef _S390_DELAY_H #define _S390_DELAY_H -extern void __udelay(unsigned long usecs); -extern void udelay_simple(unsigned long usecs); +extern void __udelay(unsigned long long usecs); +extern void udelay_simple(unsigned long long usecs); extern void __delay(unsigned long loops); -#define udelay(n) __udelay(n) +#define udelay(n) __udelay((unsigned long long) (n)) +#define mdelay(n) __udelay((unsigned long long) (n) * 1000) #endif /* defined(_S390_DELAY_H) */ diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h index 74d0bbb..354d426 100644 --- a/arch/s390/include/asm/elf.h +++ b/arch/s390/include/asm/elf.h @@ -92,6 +92,18 @@ /* Keep this the last entry. */ #define R_390_NUM 61 +/* Bits present in AT_HWCAP. */ +#define HWCAP_S390_ESAN3 1 +#define HWCAP_S390_ZARCH 2 +#define HWCAP_S390_STFLE 4 +#define HWCAP_S390_MSA 8 +#define HWCAP_S390_LDISP 16 +#define HWCAP_S390_EIMM 32 +#define HWCAP_S390_DFP 64 +#define HWCAP_S390_HPAGE 128 +#define HWCAP_S390_ETF3EH 256 +#define HWCAP_S390_HIGH_GPRS 512 + /* * These are used to set parameters in the core dumps. */ @@ -143,7 +155,6 @@ extern unsigned int vdso_enabled; } while (0) #define CORE_DUMP_USE_REGSET -#define USE_ELF_CORE_DUMP #define ELF_EXEC_PAGESIZE 4096 /* This is the location that an ET_DYN program is loaded if exec'ed. Typical diff --git a/arch/s390/include/asm/kvm.h b/arch/s390/include/asm/kvm.h index 3dfcaeb..82b32a1 100644 --- a/arch/s390/include/asm/kvm.h +++ b/arch/s390/include/asm/kvm.h @@ -1,6 +1,5 @@ #ifndef __LINUX_KVM_S390_H #define __LINUX_KVM_S390_H - /* * asm-s390/kvm.h - KVM s390 specific structures and definitions * @@ -15,6 +14,8 @@ */ #include <linux/types.h> +#define __KVM_S390 + /* for KVM_GET_REGS and KVM_SET_REGS */ struct kvm_regs { /* general purpose regs for s390 */ diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index fc7edd6..976e273 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -36,7 +36,7 @@ static inline int init_new_context(struct task_struct *tsk, mm->context.has_pgste = 1; mm->context.alloc_pgste = 1; } else { - mm->context.noexec = s390_noexec; + mm->context.noexec = (user_mode == SECONDARY_SPACE_MODE); mm->context.has_pgste = 0; mm->context.alloc_pgste = 0; } @@ -58,7 +58,7 @@ static inline void update_mm(struct mm_struct *mm, struct task_struct *tsk) pgd_t *pgd = mm->pgd; S390_lowcore.user_asce = mm->context.asce_bits | __pa(pgd); - if (switch_amode) { + if (user_mode != HOME_SPACE_MODE) { /* Load primary space page table origin. */ pgd = mm->context.noexec ? get_shadow_table(pgd) : pgd; S390_lowcore.user_exec_asce = mm->context.asce_bits | __pa(pgd); diff --git a/arch/s390/include/asm/param.h b/arch/s390/include/asm/param.h index 34aaa46..c616821 100644 --- a/arch/s390/include/asm/param.h +++ b/arch/s390/include/asm/param.h @@ -1,30 +1,6 @@ -/* - * include/asm-s390/param.h - * - * S390 version - * - * Derived from "include/asm-i386/param.h" - */ - #ifndef _ASMS390_PARAM_H #define _ASMS390_PARAM_H -#ifdef __KERNEL__ -# define HZ CONFIG_HZ /* Internal kernel timer frequency */ -# define USER_HZ 100 /* .. some user interfaces are in "ticks" */ -# define CLOCKS_PER_SEC (USER_HZ) /* like times() */ -#endif - -#ifndef HZ -#define HZ 100 -#endif - -#define EXEC_PAGESIZE 4096 - -#ifndef NOGROUP -#define NOGROUP (-1) -#endif - -#define MAXHOSTNAMELEN 64 /* max length of hostname */ +#include <asm-generic/param.h> -#endif +#endif /* _ASMS390_PARAM_H */ diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index ddad590..68940d0 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -143,7 +143,8 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) spin_lock_init(&mm->context.list_lock); INIT_LIST_HEAD(&mm->context.crst_list); INIT_LIST_HEAD(&mm->context.pgtable_list); - return (pgd_t *) crst_table_alloc(mm, s390_noexec); + return (pgd_t *) + crst_table_alloc(mm, user_mode == SECONDARY_SPACE_MODE); } #define pgd_free(mm, pgd) crst_table_free(mm, (unsigned long *) pgd) diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 60a7b1a..e2fa79c 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -169,12 +169,13 @@ extern unsigned long VMALLOC_START; * STL Segment-Table-Length: Segment-table length (STL+1*16 entries -> up to 2048) * * A 64 bit pagetable entry of S390 has following format: - * | PFRA |0IP0| OS | + * | PFRA |0IPC| OS | * 0000000000111111111122222222223333333333444444444455555555556666 * 0123456789012345678901234567890123456789012345678901234567890123 * * I Page-Invalid Bit: Page is not available for address-translation * P Page-Protection Bit: Store access not possible for page + * C Change-bit override: HW is not required to set change bit * * A 64 bit segmenttable entry of S390 has following format: * | P-table origin | TT @@ -218,6 +219,7 @@ extern unsigned long VMALLOC_START; */ /* Hardware bits in the page table entry */ +#define _PAGE_CO 0x100 /* HW Change-bit override */ #define _PAGE_RO 0x200 /* HW read-only bit */ #define _PAGE_INVALID 0x400 /* HW invalid bit */ diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h index 539263f..95dcf18 100644 --- a/arch/s390/include/asm/ptrace.h +++ b/arch/s390/include/asm/ptrace.h @@ -311,6 +311,10 @@ typedef struct __u32 orig_gpr2; } s390_compat_regs; +typedef struct +{ + __u32 gprs_high[NUM_GPRS]; +} s390_compat_regs_high; #ifdef __KERNEL__ diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index e37478e..52a779c 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -49,17 +49,12 @@ extern unsigned long memory_end; void detect_memory_layout(struct mem_chunk chunk[]); -#ifdef CONFIG_S390_SWITCH_AMODE -extern unsigned int switch_amode; -#else -#define switch_amode (0) -#endif - -#ifdef CONFIG_S390_EXEC_PROTECT -extern unsigned int s390_noexec; -#else -#define s390_noexec (0) -#endif +#define PRIMARY_SPACE_MODE 0 +#define ACCESS_REGISTER_MODE 1 +#define SECONDARY_SPACE_MODE 2 +#define HOME_SPACE_MODE 3 + +extern unsigned int user_mode; /* * Machine features detected in head.S diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h index a868b27..2ab1141 100644 --- a/arch/s390/include/asm/smp.h +++ b/arch/s390/include/asm/smp.h @@ -1,57 +1,22 @@ /* - * include/asm-s390/smp.h - * - * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation - * Author(s): Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com), - * Martin Schwidefsky (schwidefsky@de.ibm.com) - * Heiko Carstens (heiko.carstens@de.ibm.com) + * Copyright IBM Corp. 1999,2009 + * Author(s): Denis Joseph Barrow, + * Martin Schwidefsky <schwidefsky@de.ibm.com>, + * Heiko Carstens <heiko.carstens@de.ibm.com>, */ #ifndef __ASM_SMP_H #define __ASM_SMP_H -#include <linux/threads.h> -#include <linux/cpumask.h> -#include <linux/bitops.h> +#ifdef CONFIG_SMP -#if defined(__KERNEL__) && defined(CONFIG_SMP) && !defined(__ASSEMBLY__) - -#include <asm/lowcore.h> -#include <asm/sigp.h> -#include <asm/ptrace.h> #include <asm/system.h> - -/* - s390 specific smp.c headers - */ -typedef struct -{ - int intresting; - sigp_ccode ccode; - __u32 status; - __u16 cpu; -} sigp_info; +#include <asm/sigp.h> extern void machine_restart_smp(char *); extern void machine_halt_smp(void); extern void machine_power_off_smp(void); -#define NO_PROC_ID 0xFF /* No processor magic marker */ - -/* - * This magic constant controls our willingness to transfer - * a process across CPUs. Such a transfer incurs misses on the L1 - * cache, and on a P6 or P5 with multiple L2 caches L2 hits. My - * gut feeling is this will vary by board in value. For a board - * with separate L2 cache it probably depends also on the RSS, and - * for a board with shared L2 cache it ought to decay fast as other - * processes are run. - */ - -#define PROC_CHANGE_PENALTY 20 /* Schedule penalty */ - #define raw_smp_processor_id() (S390_lowcore.cpu_nr) -#define cpu_logical_map(cpu) (cpu) extern int __cpu_disable (void); extern void __cpu_die (unsigned int cpu); @@ -64,7 +29,9 @@ extern int smp_cpu_polarization[]; extern void arch_send_call_function_single_ipi(int cpu); extern void arch_send_call_function_ipi_mask(const struct cpumask *mask); -#endif +extern union save_area *zfcpdump_save_areas[NR_CPUS + 1]; + +#endif /* CONFIG_SMP */ #ifdef CONFIG_HOTPLUG_CPU extern int smp_rescan_cpus(void); @@ -72,5 +39,4 @@ extern int smp_rescan_cpus(void); static inline int smp_rescan_cpus(void) { return 0; } #endif -extern union save_area *zfcpdump_save_areas[NR_CPUS + 1]; -#endif +#endif /* __ASM_SMP_H */ diff --git a/arch/s390/include/asm/socket.h b/arch/s390/include/asm/socket.h index e42df89..fdff1e9 100644 --- a/arch/s390/include/asm/socket.h +++ b/arch/s390/include/asm/socket.h @@ -68,4 +68,6 @@ #define SO_PROTOCOL 38 #define SO_DOMAIN 39 +#define SO_RXQ_OVFL 40 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/s390/include/asm/sockios.h b/arch/s390/include/asm/sockios.h index f4fc16c..6f60eee 100644 --- a/arch/s390/include/asm/sockios.h +++ b/arch/s390/include/asm/sockios.h @@ -1,21 +1,6 @@ -/* - * include/asm-s390/sockios.h - * - * S390 version - * - * Derived from "include/asm-i386/sockios.h" - */ +#ifndef _ASM_S390_SOCKIOS_H +#define _ASM_S390_SOCKIOS_H -#ifndef __ARCH_S390_SOCKIOS__ -#define __ARCH_S390_SOCKIOS__ - -/* Socket-level I/O control calls. */ -#define FIOSETOWN 0x8901 -#define SIOCSPGRP 0x8902 -#define FIOGETOWN 0x8903 -#define SIOCGPGRP 0x8904 -#define SIOCATMARK 0x8905 -#define SIOCGSTAMP 0x8906 /* Get stamp (timeval) */ -#define SIOCGSTAMPNS 0x8907 /* Get stamp (timespec) */ +#include <asm-generic/sockios.h> #endif diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h index 41ce686..a587907 100644 --- a/arch/s390/include/asm/spinlock.h +++ b/arch/s390/include/asm/spinlock.h @@ -52,27 +52,27 @@ _raw_compare_and_swap(volatile unsigned int *lock, * (the type definitions are in asm/spinlock_types.h) */ -#define __raw_spin_is_locked(x) ((x)->owner_cpu != 0) -#define __raw_spin_unlock_wait(lock) \ - do { while (__raw_spin_is_locked(lock)) \ - _raw_spin_relax(lock); } while (0) +#define arch_spin_is_locked(x) ((x)->owner_cpu != 0) +#define arch_spin_unlock_wait(lock) \ + do { while (arch_spin_is_locked(lock)) \ + arch_spin_relax(lock); } while (0) -extern void _raw_spin_lock_wait(raw_spinlock_t *); -extern void _raw_spin_lock_wait_flags(raw_spinlock_t *, unsigned long flags); -extern int _raw_spin_trylock_retry(raw_spinlock_t *); -extern void _raw_spin_relax(raw_spinlock_t *lock); +extern void arch_spin_lock_wait(arch_spinlock_t *); +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 void __raw_spin_lock(raw_spinlock_t *lp) +static inline void arch_spin_lock(arch_spinlock_t *lp) { int old; old = _raw_compare_and_swap(&lp->owner_cpu, 0, ~smp_processor_id()); if (likely(old == 0)) return; - _raw_spin_lock_wait(lp); + arch_spin_lock_wait(lp); } -static inline void __raw_spin_lock_flags(raw_spinlock_t *lp, +static inline void arch_spin_lock_flags(arch_spinlock_t *lp, unsigned long flags) { int old; @@ -80,20 +80,20 @@ static inline void __raw_spin_lock_flags(raw_spinlock_t *lp, old = _raw_compare_and_swap(&lp->owner_cpu, 0, ~smp_processor_id()); if (likely(old == 0)) return; - _raw_spin_lock_wait_flags(lp, flags); + arch_spin_lock_wait_flags(lp, flags); } -static inline int __raw_spin_trylock(raw_spinlock_t *lp) +static inline int arch_spin_trylock(arch_spinlock_t *lp) { int old; old = _raw_compare_and_swap(&lp->owner_cpu, 0, ~smp_processor_id()); if (likely(old == 0)) return 1; - return _raw_spin_trylock_retry(lp); + return arch_spin_trylock_retry(lp); } -static inline void __raw_spin_unlock(raw_spinlock_t *lp) +static inline void arch_spin_unlock(arch_spinlock_t *lp) { _raw_compare_and_swap(&lp->owner_cpu, lp->owner_cpu, 0); } @@ -113,22 +113,22 @@ static inline void __raw_spin_unlock(raw_spinlock_t *lp) * read_can_lock - would read_trylock() succeed? * @lock: the rwlock in question. */ -#define __raw_read_can_lock(x) ((int)(x)->lock >= 0) +#define arch_read_can_lock(x) ((int)(x)->lock >= 0) /** * write_can_lock - would write_trylock() succeed? * @lock: the rwlock in question. */ -#define __raw_write_can_lock(x) ((x)->lock == 0) +#define arch_write_can_lock(x) ((x)->lock == 0) -extern void _raw_read_lock_wait(raw_rwlock_t *lp); -extern void _raw_read_lock_wait_flags(raw_rwlock_t *lp, unsigned long flags); -extern int _raw_read_trylock_retry(raw_rwlock_t *lp); -extern void _raw_write_lock_wait(raw_rwlock_t *lp); -extern void _raw_write_lock_wait_flags(raw_rwlock_t *lp, unsigned long flags); -extern int _raw_write_trylock_retry(raw_rwlock_t *lp); +extern void _raw_read_lock_wait(arch_rwlock_t *lp); +extern void _raw_read_lock_wait_flags(arch_rwlock_t *lp, unsigned long flags); +extern int _raw_read_trylock_retry(arch_rwlock_t *lp); +extern void _raw_write_lock_wait(arch_rwlock_t *lp); +extern void _raw_write_lock_wait_flags(arch_rwlock_t *lp, unsigned long flags); +extern int _raw_write_trylock_retry(arch_rwlock_t *lp); -static inline void __raw_read_lock(raw_rwlock_t *rw) +static inline void arch_read_lock(arch_rwlock_t *rw) { unsigned int old; old = rw->lock & 0x7fffffffU; @@ -136,7 +136,7 @@ static inline void __raw_read_lock(raw_rwlock_t *rw) _raw_read_lock_wait(rw); } -static inline void __raw_read_lock_flags(raw_rwlock_t *rw, unsigned long flags) +static inline void arch_read_lock_flags(arch_rwlock_t *rw, unsigned long flags) { unsigned int old; old = rw->lock & 0x7fffffffU; @@ -144,7 +144,7 @@ static inline void __raw_read_lock_flags(raw_rwlock_t *rw, unsigned long flags) _raw_read_lock_wait_flags(rw, flags); } -static inline void __raw_read_unlock(raw_rwlock_t *rw) +static inline void arch_read_unlock(arch_rwlock_t *rw) { unsigned int old, cmp; @@ -155,24 +155,24 @@ static inline void __raw_read_unlock(raw_rwlock_t *rw) } while (cmp != old); } -static inline void __raw_write_lock(raw_rwlock_t *rw) +static inline void arch_write_lock(arch_rwlock_t *rw) { if (unlikely(_raw_compare_and_swap(&rw->lock, 0, 0x80000000) != 0)) _raw_write_lock_wait(rw); } -static inline void __raw_write_lock_flags(raw_rwlock_t *rw, unsigned long flags) +static inline void arch_write_lock_flags(arch_rwlock_t *rw, unsigned long flags) { if (unlikely(_raw_compare_and_swap(&rw->lock, 0, 0x80000000) != 0)) _raw_write_lock_wait_flags(rw, flags); } -static inline void __raw_write_unlock(raw_rwlock_t *rw) +static inline void arch_write_unlock(arch_rwlock_t *rw) { _raw_compare_and_swap(&rw->lock, 0x80000000, 0); } -static inline int __raw_read_trylock(raw_rwlock_t *rw) +static inline int arch_read_trylock(arch_rwlock_t *rw) { unsigned int old; old = rw->lock & 0x7fffffffU; @@ -181,43 +181,14 @@ static inline int __raw_read_trylock(raw_rwlock_t *rw) return _raw_read_trylock_retry(rw); } -static inline int __raw_write_trylock(raw_rwlock_t *rw) +static inline int arch_write_trylock(arch_rwlock_t *rw) { if (likely(_raw_compare_and_swap(&rw->lock, 0, 0x80000000) == 0)) return 1; return _raw_write_trylock_retry(rw); } -#define _raw_read_relax(lock) cpu_relax() -#define _raw_write_relax(lock) cpu_relax() - -#define __always_inline__spin_lock -#define __always_inline__read_lock -#define __always_inline__write_lock -#define __always_inline__spin_lock_bh -#define __always_inline__read_lock_bh -#define __always_inline__write_lock_bh -#define __always_inline__spin_lock_irq -#define __always_inline__read_lock_irq -#define __always_inline__write_lock_irq -#define __always_inline__spin_lock_irqsave -#define __always_inline__read_lock_irqsave -#define __always_inline__write_lock_irqsave -#define __always_inline__spin_trylock -#define __always_inline__read_trylock -#define __always_inline__write_trylock -#define __always_inline__spin_trylock_bh -#define __always_inline__spin_unlock -#define __always_inline__read_unlock -#define __always_inline__write_unlock -#define __always_inline__spin_unlock_bh -#define __always_inline__read_unlock_bh -#define __always_inline__write_unlock_bh -#define __always_inline__spin_unlock_irq -#define __always_inline__read_unlock_irq -#define __always_inline__write_unlock_irq -#define __always_inline__spin_unlock_irqrestore -#define __always_inline__read_unlock_irqrestore -#define __always_inline__write_unlock_irqrestore +#define arch_read_relax(lock) cpu_relax() +#define arch_write_relax(lock) cpu_relax() #endif /* __ASM_SPINLOCK_H */ diff --git a/arch/s390/include/asm/spinlock_types.h b/arch/s390/include/asm/spinlock_types.h index 654abc4..9c76656 100644 --- a/arch/s390/include/asm/spinlock_types.h +++ b/arch/s390/include/asm/spinlock_types.h @@ -7,14 +7,14 @@ typedef struct { volatile unsigned int owner_cpu; -} __attribute__ ((aligned (4))) raw_spinlock_t; +} __attribute__ ((aligned (4))) arch_spinlock_t; -#define __RAW_SPIN_LOCK_UNLOCKED { 0 } +#define __ARCH_SPIN_LOCK_UNLOCKED { 0 } typedef struct { volatile unsigned int lock; -} raw_rwlock_t; +} arch_rwlock_t; -#define __RAW_RW_LOCK_UNLOCKED { 0 } +#define __ARCH_RW_LOCK_UNLOCKED { 0 } #endif diff --git a/arch/s390/include/asm/termbits.h b/arch/s390/include/asm/termbits.h index 58731853..71bf6ac 100644 --- a/arch/s390/include/asm/termbits.h +++ b/arch/s390/include/asm/termbits.h @@ -1,206 +1,6 @@ -/* - * include/asm-s390/termbits.h - * - * S390 version - * - * Derived from "include/asm-i386/termbits.h" - */ +#ifndef _ASM_S390_TERMBITS_H +#define _ASM_S390_TERMBITS_H -#ifndef __ARCH_S390_TERMBITS_H__ -#define __ARCH_S390_TERMBITS_H__ - -#include <linux/posix_types.h> - -typedef unsigned char cc_t; -typedef unsigned int speed_t; -typedef unsigned int tcflag_t; - -#define NCCS 19 -struct termios { - tcflag_t c_iflag; /* input mode flags */ - tcflag_t c_oflag; /* output mode flags */ - tcflag_t c_cflag; /* control mode flags */ - tcflag_t c_lflag; /* local mode flags */ - cc_t c_line; /* line discipline */ - cc_t c_cc[NCCS]; /* control characters */ -}; - -struct termios2 { - tcflag_t c_iflag; /* input mode flags */ - tcflag_t c_oflag; /* output mode flags */ - tcflag_t c_cflag; /* control mode flags */ - tcflag_t c_lflag; /* local mode flags */ - cc_t c_line; /* line discipline */ - cc_t c_cc[NCCS]; /* control characters */ - speed_t c_ispeed; /* input speed */ - speed_t c_ospeed; /* output speed */ -}; - -struct ktermios { - tcflag_t c_iflag; /* input mode flags */ - tcflag_t c_oflag; /* output mode flags */ - tcflag_t c_cflag; /* control mode flags */ - tcflag_t c_lflag; /* local mode flags */ - cc_t c_line; /* line discipline */ - cc_t c_cc[NCCS]; /* control characters */ - speed_t c_ispeed; /* input speed */ - speed_t c_ospeed; /* output speed */ -}; - -/* c_cc characters */ -#define VINTR 0 -#define VQUIT 1 -#define VERASE 2 -#define VKILL 3 -#define VEOF 4 -#define VTIME 5 -#define VMIN 6 -#define VSWTC 7 -#define VSTART 8 -#define VSTOP 9 -#define VSUSP 10 -#define VEOL 11 -#define VREPRINT 12 -#define VDISCARD 13 -#define VWERASE 14 -#define VLNEXT 15 -#define VEOL2 16 - -/* c_iflag bits */ -#define IGNBRK 0000001 -#define BRKINT 0000002 -#define IGNPAR 0000004 -#define PARMRK 0000010 -#define INPCK 0000020 -#define ISTRIP 0000040 -#define INLCR 0000100 -#define IGNCR 0000200 -#define ICRNL 0000400 -#define IUCLC 0001000 -#define IXON 0002000 -#define IXANY 0004000 -#define IXOFF 0010000 -#define IMAXBEL 0020000 -#define IUTF8 0040000 - -/* c_oflag bits */ -#define OPOST 0000001 -#define OLCUC 0000002 -#define ONLCR 0000004 -#define OCRNL 0000010 -#define ONOCR 0000020 -#define ONLRET 0000040 -#define OFILL 0000100 -#define OFDEL 0000200 -#define NLDLY 0000400 -#define NL0 0000000 -#define NL1 0000400 -#define CRDLY 0003000 -#define CR0 0000000 -#define CR1 0001000 -#define CR2 0002000 -#define CR3 0003000 -#define TABDLY 0014000 -#define TAB0 0000000 -#define TAB1 0004000 -#define TAB2 0010000 -#define TAB3 0014000 -#define XTABS 0014000 -#define BSDLY 0020000 -#define BS0 0000000 -#define BS1 0020000 -#define VTDLY 0040000 -#define VT0 0000000 -#define VT1 0040000 -#define FFDLY 0100000 -#define FF0 0000000 -#define FF1 0100000 - -/* c_cflag bit meaning */ -#define CBAUD 0010017 -#define B0 0000000 /* hang up */ -#define B50 0000001 -#define B75 0000002 -#define B110 0000003 -#define B134 0000004 -#define B150 0000005 -#define B200 0000006 -#define B300 0000007 -#define B600 0000010 -#define B1200 0000011 -#define B1800 0000012 -#define B2400 0000013 -#define B4800 0000014 -#define B9600 0000015 -#define B19200 0000016 -#define B38400 0000017 -#define EXTA B19200 -#define EXTB B38400 -#define CSIZE 0000060 -#define CS5 0000000 -#define CS6 0000020 -#define CS7 0000040 -#define CS8 0000060 -#define CSTOPB 0000100 -#define CREAD 0000200 -#define PARENB 0000400 -#define PARODD 0001000 -#define HUPCL 0002000 -#define CLOCAL 0004000 -#define CBAUDEX 0010000 -#define BOTHER 0010000 -#define B57600 0010001 -#define B115200 0010002 -#define B230400 0010003 -#define B460800 0010004 -#define B500000 0010005 -#define B576000 0010006 -#define B921600 0010007 -#define B1000000 0010010 -#define B1152000 0010011 -#define B1500000 0010012 -#define B2000000 0010013 -#define B2500000 0010014 -#define B3000000 0010015 -#define B3500000 0010016 -#define B4000000 0010017 -#define CIBAUD 002003600000 /* input baud rate */ -#define CMSPAR 010000000000 /* mark or space (stick) parity */ -#define CRTSCTS 020000000000 /* flow control */ - -#define IBSHIFT 16 /* Shift from CBAUD to CIBAUD */ - -/* c_lflag bits */ -#define ISIG 0000001 -#define ICANON 0000002 -#define XCASE 0000004 -#define ECHO 0000010 -#define ECHOE 0000020 -#define ECHOK 0000040 -#define ECHONL 0000100 -#define NOFLSH 0000200 -#define TOSTOP 0000400 -#define ECHOCTL 0001000 -#define ECHOPRT 0002000 -#define ECHOKE 0004000 -#define FLUSHO 0010000 -#define PENDIN 0040000 -#define IEXTEN 0100000 - -/* tcflow() and TCXONC use these */ -#define TCOOFF 0 -#define TCOON 1 -#define TCIOFF 2 -#define TCION 3 - -/* tcflush() and TCFLSH use these */ -#define TCIFLUSH 0 -#define TCOFLUSH 1 -#define TCIOFLUSH 2 - -/* tcsetattr uses these */ -#define TCSANOW 0 -#define TCSADRAIN 1 -#define TCSAFLUSH 2 +#include <asm-generic/termbits.h> #endif diff --git a/arch/s390/include/asm/todclk.h b/arch/s390/include/asm/todclk.h deleted file mode 100644 index c7f6205..0000000 --- a/arch/s390/include/asm/todclk.h +++ /dev/null @@ -1,23 +0,0 @@ -/* - * File...........: linux/include/asm/todclk.h - * Author(s)......: Holger Smolinski <Holger.Smolinski@de.ibm.com> - * Bugreports.to..: <Linux390@de.ibm.com> - * (C) IBM Corporation, IBM Deutschland Entwicklung GmbH, 1999,2000 - * - * History of changes (starts July 2000) - */ - -#ifndef __ASM_TODCLK_H -#define __ASM_TODCLK_H - -#ifdef __KERNEL__ - -#define TOD_uSEC (0x1000ULL) -#define TOD_mSEC (1000 * TOD_uSEC) -#define TOD_SEC (1000 * TOD_mSEC) -#define TOD_MIN (60 * TOD_SEC) -#define TOD_HOUR (60 * TOD_MIN) - -#endif - -#endif diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h index 8377e91..cbf0a87 100644 --- a/arch/s390/include/asm/uaccess.h +++ b/arch/s390/include/asm/uaccess.h @@ -93,6 +93,8 @@ extern struct uaccess_ops uaccess_mvcos; extern struct uaccess_ops uaccess_mvcos_switch; extern struct uaccess_ops uaccess_pt; +extern int __handle_fault(unsigned long, unsigned long, int); + static inline int __put_user_fn(size_t size, void __user *ptr, void *x) { size = uaccess.copy_to_user_small(size, ptr, x); diff --git a/arch/s390/include/asm/ucontext.h b/arch/s390/include/asm/ucontext.h index d69bec0..cfb874e 100644 --- a/arch/s390/include/asm/ucontext.h +++ b/arch/s390/include/asm/ucontext.h @@ -9,6 +9,21 @@ #ifndef _ASM_S390_UCONTEXT_H #define _ASM_S390_UCONTEXT_H +#define UC_EXTENDED 0x00000001 + +#ifndef __s390x__ + +struct ucontext_extended { + unsigned long uc_flags; + struct ucontext *uc_link; + stack_t uc_stack; + _sigregs uc_mcontext; + unsigned long uc_sigmask[2]; + unsigned long uc_gprs_high[16]; +}; + +#endif + struct ucontext { unsigned long uc_flags; struct ucontext *uc_link; diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h index cb5232d..192a720 100644 --- a/arch/s390/include/asm/unistd.h +++ b/arch/s390/include/asm/unistd.h @@ -269,7 +269,8 @@ #define __NR_pwritev 329 #define __NR_rt_tgsigqueueinfo 330 #define __NR_perf_event_open 331 -#define NR_syscalls 332 +#define __NR_recvmmsg 332 +#define NR_syscalls 333 /* * There are some system calls that are not present on 64 bit, some diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index c7be8e1..683f638 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -44,6 +44,7 @@ obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_FUNCTION_TRACER) += $(if $(CONFIG_64BIT),mcount64.o,mcount.o) obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o +obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o # Kexec part S390_KEXEC_OBJS := machine_kexec.o crash.o diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 0debcec..22c9e55 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -31,14 +31,8 @@ #include <linux/shm.h> #include <linux/slab.h> #include <linux/uio.h> -#include <linux/nfs_fs.h> #include <linux/quota.h> #include <linux/module.h> -#include <linux/sunrpc/svc.h> -#include <linux/nfsd/nfsd.h> -#include <linux/nfsd/cache.h> -#include <linux/nfsd/xdr.h> -#include <linux/nfsd/syscall.h> #include <linux/poll.h> #include <linux/personality.h> #include <linux/stat.h> @@ -527,59 +521,6 @@ asmlinkage long sys32_sendfile64(int out_fd, int in_fd, return ret; } -#ifdef CONFIG_SYSCTL_SYSCALL -struct __sysctl_args32 { - u32 name; - int nlen; - u32 oldval; - u32 oldlenp; - u32 newval; - u32 newlen; - u32 __unused[4]; -}; - -asmlinkage long sys32_sysctl(struct __sysctl_args32 __user *args) -{ - struct __sysctl_args32 tmp; - int error; - size_t oldlen; - size_t __user *oldlenp = NULL; - unsigned long addr = (((unsigned long)&args->__unused[0]) + 7) & ~7; - - if (copy_from_user(&tmp, args, sizeof(tmp))) - return -EFAULT; - - if (tmp.oldval && tmp.oldlenp) { - /* Duh, this is ugly and might not work if sysctl_args - is in read-only memory, but do_sysctl does indirectly - a lot of uaccess in both directions and we'd have to - basically copy the whole sysctl.c here, and - glibc's __sysctl uses rw memory for the structure - anyway. */ - if (get_user(oldlen, (u32 __user *)compat_ptr(tmp.oldlenp)) || - put_user(oldlen, (size_t __user *)addr)) - return -EFAULT; - oldlenp = (size_t __user *)addr; - } - - lock_kernel(); - error = do_sysctl(compat_ptr(tmp.name), tmp.nlen, compat_ptr(tmp.oldval), - oldlenp, compat_ptr(tmp.newval), tmp.newlen); - unlock_kernel(); - if (oldlenp) { - if (!error) { - if (get_user(oldlen, (size_t __user *)addr) || - put_user(oldlen, (u32 __user *)compat_ptr(tmp.oldlenp))) - error = -EFAULT; - } - if (copy_to_user(args->__unused, tmp.__unused, - sizeof(tmp.__unused))) - error = -EFAULT; - } - return error; -} -#endif - struct stat64_emu31 { unsigned long long st_dev; unsigned int __pad1; @@ -683,38 +624,6 @@ struct mmap_arg_struct_emu31 { u32 offset; }; -/* common code for old and new mmaps */ -static inline long do_mmap2( - unsigned long addr, unsigned long len, - unsigned long prot, unsigned long flags, - unsigned long fd, unsigned long pgoff) -{ - struct file * file = NULL; - unsigned long error = -EBADF; - - flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE); - if (!(flags & MAP_ANONYMOUS)) { - file = fget(fd); - if (!file) - goto out; - } - - down_write(¤t->mm->mmap_sem); - error = do_mmap_pgoff(file, addr, len, prot, flags, pgoff); - if (!IS_ERR((void *) error) && error + len >= 0x80000000ULL) { - /* Result is out of bounds. */ - do_munmap(current->mm, addr, len); - error = -ENOMEM; - } - up_write(¤t->mm->mmap_sem); - - if (file) - fput(file); -out: - return error; -} - - asmlinkage unsigned long old32_mmap(struct mmap_arg_struct_emu31 __user *arg) { @@ -728,7 +637,8 @@ old32_mmap(struct mmap_arg_struct_emu31 __user *arg) if (a.offset & ~PAGE_MASK) goto out; - error = do_mmap2(a.addr, a.len, a.prot, a.flags, a.fd, a.offset >> PAGE_SHIFT); + error = sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, + a.offset >> PAGE_SHIFT); out: return error; } @@ -741,7 +651,7 @@ sys32_mmap2(struct mmap_arg_struct_emu31 __user *arg) if (copy_from_user(&a, arg, sizeof(a))) goto out; - error = do_mmap2(a.addr, a.len, a.prot, a.flags, a.fd, a.offset); + error = sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset); out: return error; } diff --git a/arch/s390/kernel/compat_linux.h b/arch/s390/kernel/compat_linux.h index c07f9ca..cb97afc 100644 --- a/arch/s390/kernel/compat_linux.h +++ b/arch/s390/kernel/compat_linux.h @@ -4,10 +4,6 @@ #include <linux/compat.h> #include <linux/socket.h> #include <linux/syscalls.h> -#include <linux/nfs_fs.h> -#include <linux/sunrpc/svc.h> -#include <linux/nfsd/nfsd.h> -#include <linux/nfsd/export.h> /* Macro that masks the high order bit of an 32 bit pointer and converts it*/ /* to a 64 bit pointer */ @@ -162,7 +158,6 @@ struct ucontext32 { compat_sigset_t uc_sigmask; /* mask last for extensibility */ }; -struct __sysctl_args32; struct stat64_emu31; struct mmap_arg_struct_emu31; struct fadvise64_64_args; @@ -212,7 +207,6 @@ long sys32_sendfile(int out_fd, int in_fd, compat_off_t __user *offset, size_t count); long sys32_sendfile64(int out_fd, int in_fd, compat_loff_t __user *offset, s32 count); -long sys32_sysctl(struct __sysctl_args32 __user *args); long sys32_stat64(char __user * filename, struct stat64_emu31 __user * statbuf); long sys32_lstat64(char __user * filename, struct stat64_emu31 __user * statbuf); diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c index b537cb0..eee9998 100644 --- a/arch/s390/kernel/compat_signal.c +++ b/arch/s390/kernel/compat_signal.c @@ -39,6 +39,7 @@ typedef struct struct sigcontext32 sc; _sigregs32 sregs; int signo; + __u32 gprs_high[NUM_GPRS]; __u8 retcode[S390_SYSCALL_SIZE]; } sigframe32; @@ -48,6 +49,7 @@ typedef struct __u8 retcode[S390_SYSCALL_SIZE]; compat_siginfo_t info; struct ucontext32 uc; + __u32 gprs_high[NUM_GPRS]; } rt_sigframe32; int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from) @@ -344,6 +346,30 @@ static int restore_sigregs32(struct pt_regs *regs,_sigregs32 __user *sregs) return 0; } +static int save_sigregs_gprs_high(struct pt_regs *regs, __u32 __user *uregs) +{ + __u32 gprs_high[NUM_GPRS]; + int i; + + for (i = 0; i < NUM_GPRS; i++) + gprs_high[i] = regs->gprs[i] >> 32; + + return __copy_to_user(uregs, &gprs_high, sizeof(gprs_high)); +} + +static int restore_sigregs_gprs_high(struct pt_regs *regs, __u32 __user *uregs) +{ + __u32 gprs_high[NUM_GPRS]; + int err, i; + + err = __copy_from_user(&gprs_high, uregs, sizeof(gprs_high)); + if (err) + return err; + for (i = 0; i < NUM_GPRS; i++) + *(__u32 *)®s->gprs[i] = gprs_high[i]; + return 0; +} + asmlinkage long sys32_sigreturn(void) { struct pt_regs *regs = task_pt_regs(current); @@ -363,6 +389,8 @@ asmlinkage long sys32_sigreturn(void) if (restore_sigregs32(regs, &frame->sregs)) goto badframe; + if (restore_sigregs_gprs_high(regs, frame->gprs_high)) + goto badframe; return regs->gprs[2]; @@ -394,6 +422,8 @@ asmlinkage long sys32_rt_sigreturn(void) if (restore_sigregs32(regs, &frame->uc.uc_mcontext)) goto badframe; + if (restore_sigregs_gprs_high(regs, frame->gprs_high)) + goto badframe; err = __get_user(ss_sp, &frame->uc.uc_stack.ss_sp); st.ss_sp = compat_ptr(ss_sp); @@ -474,6 +504,8 @@ static int setup_frame32(int sig, struct k_sigaction *ka, if (save_sigregs32(regs, &frame->sregs)) goto give_sigsegv; + if (save_sigregs_gprs_high(regs, frame->gprs_high)) + goto give_sigsegv; if (__put_user((unsigned long) &frame->sregs, &frame->sc.sregs)) goto give_sigsegv; @@ -529,13 +561,14 @@ static int setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info, goto give_sigsegv; /* Create the ucontext. */ - err |= __put_user(0, &frame->uc.uc_flags); + err |= __put_user(UC_EXTENDED, &frame->uc.uc_flags); err |= __put_user(0, &frame->uc.uc_link); err |= __put_user(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); err |= __put_user(sas_ss_flags(regs->gprs[15]), &frame->uc.uc_stack.ss_flags); err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size); err |= save_sigregs32(regs, &frame->uc.uc_mcontext); + err |= save_sigregs_gprs_high(regs, frame->gprs_high); err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); if (err) goto give_sigsegv; diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S index 682fb69..faeaccc 100644 --- a/arch/s390/kernel/compat_wrapper.S +++ b/arch/s390/kernel/compat_wrapper.S @@ -409,7 +409,7 @@ sys32_munmap_wrapper: .globl sys32_truncate_wrapper sys32_truncate_wrapper: llgtr %r2,%r2 # const char * - llgfr %r3,%r3 # unsigned long + lgfr %r3,%r3 # long jg sys_truncate # branch to system call .globl sys32_ftruncate_wrapper @@ -689,8 +689,6 @@ sys32_fdatasync_wrapper: llgfr %r2,%r2 # unsigned int jg sys_fdatasync # branch to system call -#sys32_sysctl_wrapper # tbd - .globl sys32_mlock_wrapper sys32_mlock_wrapper: llgfr %r2,%r2 # unsigned long @@ -1087,8 +1085,8 @@ sys32_stime_wrapper: .globl sys32_sysctl_wrapper sys32_sysctl_wrapper: - llgtr %r2,%r2 # struct __sysctl_args32 * - jg sys32_sysctl + llgtr %r2,%r2 # struct compat_sysctl_args * + jg compat_sys_sysctl .globl sys32_fstat64_wrapper sys32_fstat64_wrapper: @@ -1855,3 +1853,12 @@ sys32_execve_wrapper: llgtr %r3,%r3 # compat_uptr_t * llgtr %r4,%r4 # compat_uptr_t * jg sys32_execve # branch to system call + + .globl compat_sys_recvmmsg_wrapper +compat_sys_recvmmsg_wrapper: + lgfr %r2,%r2 # int + llgtr %r3,%r3 # struct compat_mmsghdr * + llgfr %r4,%r4 # unsigned int + llgfr %r5,%r5 # unsigned int + llgtr %r6,%r6 # struct compat_timespec * + jg compat_sys_recvmmsg diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index 20f282c..0168472 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -18,6 +18,7 @@ #include <linux/errno.h> #include <linux/slab.h> #include <linux/ctype.h> +#include <linux/string.h> #include <linux/sysctl.h> #include <asm/uaccess.h> #include <linux/module.h> @@ -893,35 +894,30 @@ s390dbf_procactive(ctl_table *table, int write, static struct ctl_table s390dbf_table[] = { { - .ctl_name = CTL_S390DBF_STOPPABLE, .procname = "debug_stoppable", .data = &debug_stoppable, .maxlen = sizeof(int), .mode = S_IRUGO | S_IWUSR, - .proc_handler = &proc_dointvec, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_S390DBF_ACTIVE, .procname = "debug_active", .data = &debug_active, .maxlen = sizeof(int), .mode = S_IRUGO | S_IWUSR, - .proc_handler = &s390dbf_procactive, - .strategy = &sysctl_intvec, + .proc_handler = s390dbf_procactive, }, - { .ctl_name = 0 } + { } }; static struct ctl_table s390dbf_dir_table[] = { { - .ctl_name = CTL_S390DBF, .procname = "s390dbf", .maxlen = 0, .mode = S_IRUGO | S_IXUGO, .child = s390dbf_table, }, - { .ctl_name = 0 } + { } }; static struct ctl_table_header *s390dbf_sysctl_header; @@ -1183,7 +1179,7 @@ debug_get_uint(char *buf) { int rc; - for(; isspace(*buf); buf++); + buf = skip_spaces(buf); rc = simple_strtoul(buf, &buf, 10); if(*buf){ rc = -EINVAL; diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index bf8b4ae..e49e9e0 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -55,6 +55,7 @@ static void __init reset_tod_clock(void) disabled_wait(0); sched_clock_base_cc = TOD_UNIX_EPOCH; + S390_lowcore.last_update_clock = sched_clock_base_cc; } #ifdef CONFIG_SHARED_KERNEL @@ -167,6 +168,14 @@ static noinline __init void create_kernel_nss(void) return; } + /* re-initialize cputime accounting. */ + sched_clock_base_cc = get_clock(); + S390_lowcore.last_update_clock = sched_clock_base_cc; + S390_lowcore.last_update_timer = 0x7fffffffffffffffULL; + S390_lowcore.user_timer = 0; + S390_lowcore.system_timer = 0; + asm volatile("SPT 0(%0)" : : "a" (&S390_lowcore.last_update_timer)); + /* re-setup boot command line with new ipl vm parms */ ipl_update_parameters(); setup_boot_command_line(); diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index f43d2ee..48215d1 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -565,10 +565,10 @@ pgm_svcper: lh %r7,0x8a # get svc number from lowcore l %r9,__LC_THREAD_INFO # load pointer to thread_info struct TRACE_IRQS_OFF - l %r1,__TI_task(%r9) - mvc __THREAD_per+__PER_atmid(2,%r1),__LC_PER_ATMID - mvc __THREAD_per+__PER_address(4,%r1),__LC_PER_ADDRESS - mvc __THREAD_per+__PER_access_id(1,%r1),__LC_PER_ACCESS_ID + l %r8,__TI_task(%r9) + mvc __THREAD_per+__PER_atmid(2,%r8),__LC_PER_ATMID + mvc __THREAD_per+__PER_address(4,%r8),__LC_PER_ADDRESS + mvc __THREAD_per+__PER_access_id(1,%r8),__LC_PER_ACCESS_ID oi __TI_flags+3(%r9),_TIF_SINGLE_STEP # set TIF_SINGLE_STEP TRACE_IRQS_ON stosm __SF_EMPTY(%r15),0x03 # reenable interrupts diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S index a6f7b20..9aff1d4 100644 --- a/arch/s390/kernel/entry64.S +++ b/arch/s390/kernel/entry64.S @@ -543,10 +543,10 @@ pgm_svcper: mvc __LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER llgh %r7,__LC_SVC_INT_CODE # get svc number from lowcore lg %r9,__LC_THREAD_INFO # load pointer to thread_info struct - lg %r1,__TI_task(%r9) - mvc __THREAD_per+__PER_atmid(2,%r1),__LC_PER_ATMID - mvc __THREAD_per+__PER_address(8,%r1),__LC_PER_ADDRESS - mvc __THREAD_per+__PER_access_id(1,%r1),__LC_PER_ACCESS_ID + lg %r8,__TI_task(%r9) + mvc __THREAD_per+__PER_atmid(2,%r8),__LC_PER_ATMID + mvc __THREAD_per+__PER_address(8,%r8),__LC_PER_ADDRESS + mvc __THREAD_per+__PER_access_id(1,%r8),__LC_PER_ACCESS_ID oi __TI_flags+7(%r9),_TIF_SINGLE_STEP # set TIF_SINGLE_STEP TRACE_IRQS_ON stosm __SF_EMPTY(%r15),0x03 # reenable interrupts diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 57bdcb1..5a82bc6 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -185,9 +185,6 @@ unsigned long prepare_ftrace_return(unsigned long ip, unsigned long parent) { struct ftrace_graph_ent trace; - /* Nmi's are currently unsupported. */ - if (unlikely(in_nmi())) - goto out; if (unlikely(atomic_read(¤t->tracing_graph_pause))) goto out; if (ftrace_push_return_trace(parent, ip, &trace.depth, 0) == -EBUSY) @@ -206,73 +203,10 @@ out: #ifdef CONFIG_FTRACE_SYSCALLS -extern unsigned long __start_syscalls_metadata[]; -extern unsigned long __stop_syscalls_metadata[]; extern unsigned int sys_call_table[]; -static struct syscall_metadata **syscalls_metadata; - -struct syscall_metadata *syscall_nr_to_meta(int nr) -{ - if (!syscalls_metadata || nr >= NR_syscalls || nr < 0) - return NULL; - - return syscalls_metadata[nr]; -} - -int syscall_name_to_nr(char *name) -{ - int i; - - if (!syscalls_metadata) - return -1; - for (i = 0; i < NR_syscalls; i++) - if (syscalls_metadata[i]) - if (!strcmp(syscalls_metadata[i]->name, name)) - return i; - return -1; -} - -void set_syscall_enter_id(int num, int id) -{ - syscalls_metadata[num]->enter_id = id; -} - -void set_syscall_exit_id(int num, int id) +unsigned long __init arch_syscall_addr(int nr) { - syscalls_metadata[num]->exit_id = id; -} - -static struct syscall_metadata *find_syscall_meta(unsigned long syscall) -{ - struct syscall_metadata *start; - struct syscall_metadata *stop; - char str[KSYM_SYMBOL_LEN]; - - start = (struct syscall_metadata *)__start_syscalls_metadata; - stop = (struct syscall_metadata *)__stop_syscalls_metadata; - kallsyms_lookup(syscall, NULL, NULL, NULL, str); - - for ( ; start < stop; start++) { - if (start->name && !strcmp(start->name + 3, str + 3)) - return start; - } - return NULL; -} - -static int __init arch_init_ftrace_syscalls(void) -{ - struct syscall_metadata *meta; - int i; - syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) * NR_syscalls, - GFP_KERNEL); - if (!syscalls_metadata) - return -ENOMEM; - for (i = 0; i < NR_syscalls; i++) { - meta = find_syscall_meta((unsigned long)sys_call_table[i]); - syscalls_metadata[i] = meta; - } - return 0; + return (unsigned long)sys_call_table[nr]; } -arch_initcall(arch_init_ftrace_syscalls); #endif diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S index 6a25080..d984a2a 100644 --- a/arch/s390/kernel/head64.S +++ b/arch/s390/kernel/head64.S @@ -83,6 +83,8 @@ startup_continue: slr %r0,%r0 # set cpuid to zero sigp %r1,%r0,0x12 # switch to esame mode sam64 # switch to 64 bit mode + llgfr %r13,%r13 # clear high-order half of base reg + lmh %r0,%r15,.Lzero64-.LPG1(%r13) # clear high-order half lctlg %c0,%c15,.Lctl-.LPG1(%r13) # load control registers lg %r12,.Lparmaddr-.LPG1(%r13) # pointer to parameter area # move IPL device to lowcore @@ -127,6 +129,7 @@ startup_continue: .L4malign:.quad 0xffffffffffc00000 .Lscan2g:.quad 0x80000000 + 0x20000 - 8 # 2GB + 128K - 8 .Lnop: .long 0x07000700 +.Lzero64:.fill 16,4,0x0 #ifdef CONFIG_ZFCPDUMP .Lcurrent_cpu: .long 0x0 diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index ee57a42..4d73296 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -221,7 +221,7 @@ static ssize_t sys_##_prefix##_##_name##_store(struct kobject *kobj, \ const char *buf, size_t len) \ { \ strncpy(_value, buf, sizeof(_value) - 1); \ - strstrip(_value); \ + strim(_value); \ return len; \ } \ static struct kobj_attribute sys_##_prefix##_##_name##_attr = \ @@ -472,7 +472,7 @@ static ssize_t ipl_ccw_loadparm_show(struct kobject *kobj, return sprintf(page, "#unknown#\n"); memcpy(loadparm, &sclp_ipl_info.loadparm, LOADPARM_LEN); EBCASC(loadparm, LOADPARM_LEN); - strstrip(loadparm); + strim(loadparm); return sprintf(page, "%s\n", loadparm); } @@ -776,7 +776,7 @@ static void reipl_get_ascii_loadparm(char *loadparm, memcpy(loadparm, ibp->ipl_info.ccw.load_parm, LOADPARM_LEN); EBCASC(loadparm, LOADPARM_LEN); loadparm[LOADPARM_LEN] = 0; - strstrip(loadparm); + strim(loadparm); } static ssize_t reipl_generic_loadparm_show(struct ipl_parameter_block *ipb, @@ -1595,10 +1595,9 @@ static void stop_run(struct shutdown_trigger *trigger) { if (strcmp(trigger->name, ON_PANIC_STR) == 0) disabled_wait((unsigned long) __builtin_return_address(0)); - else { - signal_processor(smp_processor_id(), sigp_stop); - for (;;); - } + while (signal_processor(smp_processor_id(), sigp_stop) == sigp_busy) + cpu_relax(); + for (;;); } static struct shutdown_action stop_action = {SHUTDOWN_ACTION_STOP_STR, diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index ab2e3ed..639380a 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -55,6 +55,8 @@ void *module_alloc(unsigned long size) /* Free memory returned from module_alloc */ void module_free(struct module *mod, void *module_region) { + vfree(mod->arch.syminfo); + mod->arch.syminfo = NULL; vfree(module_region); } @@ -402,6 +404,7 @@ int module_finalize(const Elf_Ehdr *hdr, struct module *me) { vfree(me->arch.syminfo); + me->arch.syminfo = NULL; return module_bug_finalize(hdr, sechdrs, me); } diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c index 802c8ab..0729f36 100644 --- a/arch/s390/kernel/processor.c +++ b/arch/s390/kernel/processor.c @@ -31,9 +31,9 @@ void __cpuinit print_cpu_info(void) static int show_cpuinfo(struct seq_file *m, void *v) { - static const char *hwcap_str[9] = { + static const char *hwcap_str[10] = { "esan3", "zarch", "stfle", "msa", "ldisp", "eimm", "dfp", - "edat", "etf3eh" + "edat", "etf3eh", "highgprs" }; struct _lowcore *lc; unsigned long n = (unsigned long) v - 1; @@ -48,7 +48,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) num_online_cpus(), loops_per_jiffy/(500000/HZ), (loops_per_jiffy/(5000/HZ))%100); seq_puts(m, "features\t: "); - for (i = 0; i < 9; i++) + for (i = 0; i < 10; i++) if (hwcap_str[i] && (elf_hwcap & (1UL << i))) seq_printf(m, "%s ", hwcap_str[i]); seq_puts(m, "\n"); diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index a873867..13815d3 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -57,6 +57,7 @@ enum s390_regset { REGSET_GENERAL, REGSET_FP, + REGSET_GENERAL_EXTENDED, }; static void @@ -879,6 +880,67 @@ static int s390_compat_regs_set(struct task_struct *target, return rc; } +static int s390_compat_regs_high_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + compat_ulong_t *gprs_high; + + gprs_high = (compat_ulong_t *) + &task_pt_regs(target)->gprs[pos / sizeof(compat_ulong_t)]; + if (kbuf) { + compat_ulong_t *k = kbuf; + while (count > 0) { + *k++ = *gprs_high; + gprs_high += 2; + count -= sizeof(*k); + } + } else { + compat_ulong_t __user *u = ubuf; + while (count > 0) { + if (__put_user(*gprs_high, u++)) + return -EFAULT; + gprs_high += 2; + count -= sizeof(*u); + } + } + return 0; +} + +static int s390_compat_regs_high_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + compat_ulong_t *gprs_high; + int rc = 0; + + gprs_high = (compat_ulong_t *) + &task_pt_regs(target)->gprs[pos / sizeof(compat_ulong_t)]; + if (kbuf) { + const compat_ulong_t *k = kbuf; + while (count > 0) { + *gprs_high = *k++; + *gprs_high += 2; + count -= sizeof(*k); + } + } else { + const compat_ulong_t __user *u = ubuf; + while (count > 0 && !rc) { + unsigned long word; + rc = __get_user(word, u++); + if (rc) + break; + *gprs_high = word; + *gprs_high += 2; + count -= sizeof(*u); + } + } + + return rc; +} + static const struct user_regset s390_compat_regsets[] = { [REGSET_GENERAL] = { .core_note_type = NT_PRSTATUS, @@ -896,6 +958,14 @@ static const struct user_regset s390_compat_regsets[] = { .get = s390_fpregs_get, .set = s390_fpregs_set, }, + [REGSET_GENERAL_EXTENDED] = { + .core_note_type = NT_S390_HIGH_GPRS, + .n = sizeof(s390_compat_regs_high) / sizeof(compat_long_t), + .size = sizeof(compat_long_t), + .align = sizeof(compat_long_t), + .get = s390_compat_regs_high_get, + .set = s390_compat_regs_high_set, + }, }; static const struct user_regset_view user_s390_compat_view = { diff --git a/arch/s390/kernel/s390_ext.c b/arch/s390/kernel/s390_ext.c index 0de305b..59618bc 100644 --- a/arch/s390/kernel/s390_ext.c +++ b/arch/s390/kernel/s390_ext.c @@ -126,6 +126,8 @@ void __irq_entry do_extint(struct pt_regs *regs, unsigned short code) /* Serve timer interrupts first. */ clock_comparator_work(); kstat_cpu(smp_processor_id()).irqs[EXTERNAL_INTERRUPT]++; + if (code != 0x1004) + __get_cpu_var(s390_idle).nohz_delay = 1; index = ext_hash(code); for (p = ext_int_hash[index]; p; p = p->next) { if (likely(p->code == code)) diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 9ed13a1..0663287 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -305,9 +305,8 @@ static int __init early_parse_mem(char *p) } early_param("mem", early_parse_mem); -#ifdef CONFIG_S390_SWITCH_AMODE -unsigned int switch_amode = 0; -EXPORT_SYMBOL_GPL(switch_amode); +unsigned int user_mode = HOME_SPACE_MODE; +EXPORT_SYMBOL_GPL(user_mode); static int set_amode_and_uaccess(unsigned long user_amode, unsigned long user32_amode) @@ -340,23 +339,29 @@ static int set_amode_and_uaccess(unsigned long user_amode, */ static int __init early_parse_switch_amode(char *p) { - switch_amode = 1; + if (user_mode != SECONDARY_SPACE_MODE) + user_mode = PRIMARY_SPACE_MODE; return 0; } early_param("switch_amode", early_parse_switch_amode); -#else /* CONFIG_S390_SWITCH_AMODE */ -static inline int set_amode_and_uaccess(unsigned long user_amode, - unsigned long user32_amode) +static int __init early_parse_user_mode(char *p) { + if (p && strcmp(p, "primary") == 0) + user_mode = PRIMARY_SPACE_MODE; +#ifdef CONFIG_S390_EXEC_PROTECT + else if (p && strcmp(p, "secondary") == 0) + user_mode = SECONDARY_SPACE_MODE; +#endif + else if (!p || strcmp(p, "home") == 0) + user_mode = HOME_SPACE_MODE; + else + return 1; return 0; } -#endif /* CONFIG_S390_SWITCH_AMODE */ +early_param("user_mode", early_parse_user_mode); #ifdef CONFIG_S390_EXEC_PROTECT -unsigned int s390_noexec = 0; -EXPORT_SYMBOL_GPL(s390_noexec); - /* * Enable execute protection? */ @@ -364,8 +369,7 @@ static int __init early_parse_noexec(char *p) { if (!strncmp(p, "off", 3)) return 0; - switch_amode = 1; - s390_noexec = 1; + user_mode = SECONDARY_SPACE_MODE; return 0; } early_param("noexec", early_parse_noexec); @@ -373,7 +377,7 @@ early_param("noexec", early_parse_noexec); static void setup_addressing_mode(void) { - if (s390_noexec) { + if (user_mode == SECONDARY_SPACE_MODE) { if (set_amode_and_uaccess(PSW_ASC_SECONDARY, PSW32_ASC_SECONDARY)) pr_info("Execute protection active, " @@ -381,7 +385,7 @@ static void setup_addressing_mode(void) else pr_info("Execute protection active, " "mvcos not available\n"); - } else if (switch_amode) { + } else if (user_mode == PRIMARY_SPACE_MODE) { if (set_amode_and_uaccess(PSW_ASC_PRIMARY, PSW32_ASC_PRIMARY)) pr_info("Address spaces switched, " "mvcos available\n"); @@ -411,7 +415,7 @@ setup_lowcore(void) lc->restart_psw.mask = PSW_BASE_BITS | PSW_DEFAULT_KEY; lc->restart_psw.addr = PSW_ADDR_AMODE | (unsigned long) restart_int_handler; - if (switch_amode) + if (user_mode != HOME_SPACE_MODE) lc->restart_psw.mask |= PSW_ASC_HOME; lc->external_new_psw.mask = psw_kernel_bits; lc->external_new_psw.addr = @@ -729,7 +733,7 @@ static void __init setup_hwcaps(void) if ((facility_list & (1UL << (31 - 22))) && (facility_list & (1UL << (31 - 30)))) - elf_hwcap |= 1UL << 8; + elf_hwcap |= HWCAP_S390_ETF3EH; /* * Check for additional facilities with store-facility-list-extended. @@ -748,11 +752,20 @@ static void __init setup_hwcaps(void) __stfle(&facility_list_extended, 1) > 0) { if ((facility_list_extended & (1ULL << (63 - 42))) && (facility_list_extended & (1ULL << (63 - 44)))) - elf_hwcap |= 1UL << 6; + elf_hwcap |= HWCAP_S390_DFP; } + /* + * Huge page support HWCAP_S390_HPAGE is bit 7. + */ if (MACHINE_HAS_HPAGE) - elf_hwcap |= 1UL << 7; + elf_hwcap |= HWCAP_S390_HPAGE; + + /* + * 64-bit register support for 31-bit processes + * HWCAP_S390_HIGH_GPRS is bit 9. + */ + elf_hwcap |= HWCAP_S390_HIGH_GPRS; switch (S390_lowcore.cpu_id.machine) { case 0x9672: diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index c932caa..93e5203 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -76,7 +76,6 @@ static int cpu_stopped(int cpu) __u32 status; switch (signal_processor_ps(&status, 0, cpu, sigp_sense)) { - case sigp_order_code_accepted: case sigp_status_stored: /* Check for stopped and check stop state */ if (status & 0x50) @@ -638,6 +637,8 @@ void __cpu_die(unsigned int cpu) /* Wait until target cpu is down */ while (!cpu_stopped(cpu)) cpu_relax(); + while (signal_processor_p(0, cpu, sigp_set_prefix) == sigp_busy) + udelay(10); smp_free_lowcore(cpu); pr_info("Processor %d stopped\n", cpu); } @@ -645,8 +646,8 @@ void __cpu_die(unsigned int cpu) void cpu_die(void) { idle_task_exit(); - signal_processor(smp_processor_id(), sigp_stop); - BUG(); + while (signal_processor(smp_processor_id(), sigp_stop) == sigp_busy) + cpu_relax(); for (;;); } diff --git a/arch/s390/kernel/swsusp_asm64.S b/arch/s390/kernel/swsusp_asm64.S index fe927d0..0c26cc1 100644 --- a/arch/s390/kernel/swsusp_asm64.S +++ b/arch/s390/kernel/swsusp_asm64.S @@ -43,7 +43,7 @@ swsusp_arch_suspend: lghi %r1,0x1000 /* Save CPU address */ - stap __LC_CPU_ADDRESS(%r1) + stap __LC_CPU_ADDRESS(%r0) /* Store registers */ mvc 0x318(4,%r1),__SF_EMPTY(%r15) /* move prefix to lowcore */ @@ -69,8 +69,21 @@ swsusp_arch_suspend: stmg %r0,%r15,0x280(%r1) /* store general registers */ stpt 0x328(%r1) /* store timer */ + stck __SF_EMPTY(%r15) /* store clock */ stckc 0x330(%r1) /* store clock comparator */ + /* Update cputime accounting before going to sleep */ + lg %r0,__LC_LAST_UPDATE_TIMER + slg %r0,0x328(%r1) + alg %r0,__LC_SYSTEM_TIMER + stg %r0,__LC_SYSTEM_TIMER + mvc __LC_LAST_UPDATE_TIMER(8),0x328(%r1) + lg %r0,__LC_LAST_UPDATE_CLOCK + slg %r0,__SF_EMPTY(%r15) + alg %r0,__LC_STEAL_TIMER + stg %r0,__LC_STEAL_TIMER + mvc __LC_LAST_UPDATE_CLOCK(8),__SF_EMPTY(%r15) + /* Activate DAT */ stosm __SF_EMPTY(%r15),0x04 @@ -159,8 +172,7 @@ pgm_check_entry: larl %r1,.Lresume_cpu /* Resume CPU address: r2 */ stap 0(%r1) llgh %r2,0(%r1) - lghi %r3,0x1000 - llgh %r1,__LC_CPU_ADDRESS(%r3) /* Suspend CPU address: r1 */ + llgh %r1,__LC_CPU_ADDRESS(%r0) /* Suspend CPU address: r1 */ cgr %r1,%r2 je restore_registers /* r1 = r2 -> nothing to do */ larl %r4,.Lrestart_suspend_psw /* Set new restart PSW */ @@ -187,6 +199,7 @@ pgm_check_entry: brc 2,4b /* busy, try again */ 5: sigp %r9,%r2,__SIGP_STOP /* stop resume (current) CPU */ + brc 2,5b /* busy, try again */ 6: j 6b restart_suspend: @@ -194,14 +207,18 @@ restart_suspend: llgh %r2,0(%r1) 7: sigp %r9,%r2,__SIGP_SENSE /* Wait for resume CPU */ + brc 8,7b /* accepted, status 0, still running */ brc 2,7b /* busy, try again */ tmll %r9,0x40 /* Test if resume CPU is stopped */ jz 7b restore_registers: /* Restore registers */ - lghi %r13,0x1000 /* %r1 = pointer to save arae */ + lghi %r13,0x1000 /* %r1 = pointer to save area */ + /* Ignore time spent in suspended state. */ + llgf %r1,0x318(%r13) + stck __LC_LAST_UPDATE_CLOCK(%r1) spt 0x328(%r13) /* reprogram timer */ //sckc 0x330(%r13) /* set clock comparator */ @@ -229,9 +246,6 @@ restore_registers: /* Load old stack */ lg %r15,0x2f8(%r13) - /* Pointer to save area */ - lghi %r13,0x1000 - /* Restore prefix register */ spx 0x318(%r13) diff --git a/arch/s390/kernel/sys_s390.c b/arch/s390/kernel/sys_s390.c index e9d94f6..86a74c9 100644 --- a/arch/s390/kernel/sys_s390.c +++ b/arch/s390/kernel/sys_s390.c @@ -32,32 +32,6 @@ #include <asm/uaccess.h> #include "entry.h" -/* common code for old and new mmaps */ -static inline long do_mmap2( - unsigned long addr, unsigned long len, - unsigned long prot, unsigned long flags, - unsigned long fd, unsigned long pgoff) -{ - long error = -EBADF; - struct file * file = NULL; - - flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE); - if (!(flags & MAP_ANONYMOUS)) { - file = fget(fd); - if (!file) - goto out; - } - - down_write(¤t->mm->mmap_sem); - error = do_mmap_pgoff(file, addr, len, prot, flags, pgoff); - up_write(¤t->mm->mmap_sem); - - if (file) - fput(file); -out: - return error; -} - /* * Perform the select(nd, in, out, ex, tv) and mmap() system * calls. Linux for S/390 isn't able to handle more than 5 @@ -81,7 +55,7 @@ SYSCALL_DEFINE1(mmap2, struct mmap_arg_struct __user *, arg) if (copy_from_user(&a, arg, sizeof(a))) goto out; - error = do_mmap2(a.addr, a.len, a.prot, a.flags, a.fd, a.offset); + error = sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset); out: return error; } @@ -98,7 +72,7 @@ SYSCALL_DEFINE1(s390_old_mmap, struct mmap_arg_struct __user *, arg) if (a.offset & ~PAGE_MASK) goto out; - error = do_mmap2(a.addr, a.len, a.prot, a.flags, a.fd, a.offset >> PAGE_SHIFT); + error = sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset >> PAGE_SHIFT); out: return error; } diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S index 30eca07..4f292c9 100644 --- a/arch/s390/kernel/syscalls.S +++ b/arch/s390/kernel/syscalls.S @@ -340,3 +340,4 @@ SYSCALL(sys_preadv,sys_preadv,compat_sys_preadv_wrapper) SYSCALL(sys_pwritev,sys_pwritev,compat_sys_pwritev_wrapper) SYSCALL(sys_rt_tgsigqueueinfo,sys_rt_tgsigqueueinfo,compat_sys_rt_tgsigqueueinfo_wrapper) /* 330 */ SYSCALL(sys_perf_event_open,sys_perf_event_open,sys_perf_event_open_wrapper) +SYSCALL(sys_recvmmsg,sys_recvmmsg,compat_sys_recvmmsg_wrapper) diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index 34162a0..65065ac 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -214,7 +214,8 @@ struct clocksource * __init clocksource_default_clock(void) return &clocksource_tod; } -void update_vsyscall(struct timespec *wall_time, struct clocksource *clock) +void update_vsyscall(struct timespec *wall_time, struct clocksource *clock, + u32 mult) { if (clock != &clocksource_tod) return; @@ -334,7 +335,7 @@ int get_sync_clock(unsigned long long *clock) sw0 = atomic_read(sw_ptr); *clock = get_clock(); sw1 = atomic_read(sw_ptr); - put_cpu_var(clock_sync_sync); + put_cpu_var(clock_sync_word); if (sw0 == sw1 && (sw0 & 0x80000000U)) /* Success: time is in sync. */ return 0; @@ -384,7 +385,7 @@ static inline int check_sync_clock(void) sw_ptr = &get_cpu_var(clock_sync_word); rc = (atomic_read(sw_ptr) & 0x80000000U) != 0; - put_cpu_var(clock_sync_sync); + put_cpu_var(clock_sync_word); return rc; } diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c index c2e42cc..6e7ad63 100644 --- a/arch/s390/kernel/traps.c +++ b/arch/s390/kernel/traps.c @@ -18,7 +18,7 @@ #include <linux/kernel.h> #include <linux/string.h> #include <linux/errno.h> -#include <linux/ptrace.h> +#include <linux/tracehook.h> #include <linux/timer.h> #include <linux/mm.h> #include <linux/smp.h> @@ -382,7 +382,7 @@ void __kprobes do_single_step(struct pt_regs *regs) SIGTRAP) == NOTIFY_STOP){ return; } - if ((current->ptrace & PT_PTRACED) != 0) + if (tracehook_consider_fatal_signal(current, SIGTRAP)) force_sig(SIGTRAP, current); } @@ -483,7 +483,7 @@ static void illegal_op(struct pt_regs * regs, long interruption_code) if (get_user(*((__u16 *) opcode), (__u16 __user *) location)) return; if (*((__u16 *) opcode) == S390_BREAKPOINT_U16) { - if (current->ptrace & PT_PTRACED) + if (tracehook_consider_fatal_signal(current, SIGTRAP)) force_sig(SIGTRAP, current); else signal = SIGILL; diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c index 45a3e9a..5f99e66 100644 --- a/arch/s390/kernel/vdso.c +++ b/arch/s390/kernel/vdso.c @@ -86,7 +86,8 @@ static void vdso_init_data(struct vdso_data *vd) unsigned int facility_list; facility_list = stfl(); - vd->ectg_available = switch_amode && (facility_list & 1); + vd->ectg_available = + user_mode != HOME_SPACE_MODE && (facility_list & 1); } #ifdef CONFIG_64BIT @@ -114,7 +115,7 @@ int vdso_alloc_per_cpu(int cpu, struct _lowcore *lowcore) lowcore->vdso_per_cpu_data = __LC_PASTE; - if (!switch_amode || !vdso_enabled) + if (user_mode == HOME_SPACE_MODE || !vdso_enabled) return 0; segment_table = __get_free_pages(GFP_KERNEL, SEGMENT_ORDER); @@ -160,7 +161,7 @@ void vdso_free_per_cpu(int cpu, struct _lowcore *lowcore) unsigned long segment_table, page_table, page_frame; u32 *psal, *aste; - if (!switch_amode || !vdso_enabled) + if (user_mode == HOME_SPACE_MODE || !vdso_enabled) return; psal = (u32 *)(addr_t) lowcore->paste[4]; @@ -184,7 +185,7 @@ static void __vdso_init_cr5(void *dummy) static void vdso_init_cr5(void) { - if (switch_amode && vdso_enabled) + if (user_mode != HOME_SPACE_MODE && vdso_enabled) on_each_cpu(__vdso_init_cr5, NULL, 1); } #endif /* CONFIG_64BIT */ @@ -247,6 +248,13 @@ 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 @@ -267,14 +275,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) VM_ALWAYSDUMP, vdso_pagelist); if (rc) - goto out_up; - - /* Put vDSO base into mm struct */ - current->mm->context.vdso_base = vdso_base; - - up_write(&mm->mmap_sem); - return 0; - + current->mm->context.vdso_base = 0; out_up: up_write(&mm->mmap_sem); return rc; diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index bc15ef9..a68ac10 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -51,6 +51,7 @@ SECTIONS . = ALIGN(PAGE_SIZE); _eshared = .; /* End of shareable data */ + _sdata = .; /* Start of data section */ EXCEPTION_TABLE(16) :data diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index c41bb0d..b59a812 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -167,6 +167,8 @@ void vtime_stop_cpu(void) /* Wait for external, I/O or machine check interrupt. */ psw.mask = psw_kernel_bits | PSW_MASK_WAIT | PSW_MASK_IO | PSW_MASK_EXT; + idle->nohz_delay = 0; + /* Check if the CPU timer needs to be reprogrammed. */ if (vq->do_spt) { __u64 vmax = VTIMER_MAX_SLICE; diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig index bf164fc..6ee55ae 100644 --- a/arch/s390/kvm/Kconfig +++ b/arch/s390/kvm/Kconfig @@ -20,7 +20,6 @@ config KVM depends on HAVE_KVM && EXPERIMENTAL select PREEMPT_NOTIFIERS select ANON_INODES - select S390_SWITCH_AMODE ---help--- Support hosting paravirtualized guest machines using the SIE virtualization capability on the mainframe. This should work diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 07ced89..f8bcaef 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -74,9 +74,10 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { static unsigned long long *facilities; /* Section: not file related */ -void kvm_arch_hardware_enable(void *garbage) +int kvm_arch_hardware_enable(void *garbage) { /* every s390 is virtualization enabled ;-) */ + return 0; } void kvm_arch_hardware_disable(void *garbage) @@ -116,10 +117,16 @@ long kvm_arch_dev_ioctl(struct file *filp, int kvm_dev_ioctl_check_extension(long ext) { + int r; + switch (ext) { + case KVM_CAP_S390_PSW: + r = 1; + break; default: - return 0; + r = 0; } + return r; } /* Section: vm related */ @@ -150,7 +157,7 @@ long kvm_arch_vm_ioctl(struct file *filp, break; } default: - r = -EINVAL; + r = -ENOTTY; } return r; @@ -419,8 +426,10 @@ static int kvm_arch_vcpu_ioctl_set_initial_psw(struct kvm_vcpu *vcpu, psw_t psw) vcpu_load(vcpu); if (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_RUNNING) rc = -EBUSY; - else - vcpu->arch.sie_block->gpsw = psw; + else { + vcpu->run->psw_mask = psw.mask; + vcpu->run->psw_addr = psw.addr; + } vcpu_put(vcpu); return rc; } @@ -508,9 +517,6 @@ rerun_vcpu: switch (kvm_run->exit_reason) { case KVM_EXIT_S390_SIEIC: - vcpu->arch.sie_block->gpsw.mask = kvm_run->s390_sieic.mask; - vcpu->arch.sie_block->gpsw.addr = kvm_run->s390_sieic.addr; - break; case KVM_EXIT_UNKNOWN: case KVM_EXIT_INTR: case KVM_EXIT_S390_RESET: @@ -519,6 +525,9 @@ rerun_vcpu: BUG(); } + vcpu->arch.sie_block->gpsw.mask = kvm_run->psw_mask; + vcpu->arch.sie_block->gpsw.addr = kvm_run->psw_addr; + might_fault(); do { @@ -538,8 +547,6 @@ rerun_vcpu: /* intercept cannot be handled in-kernel, prepare kvm-run */ kvm_run->exit_reason = KVM_EXIT_S390_SIEIC; kvm_run->s390_sieic.icptcode = vcpu->arch.sie_block->icptcode; - kvm_run->s390_sieic.mask = vcpu->arch.sie_block->gpsw.mask; - kvm_run->s390_sieic.addr = vcpu->arch.sie_block->gpsw.addr; kvm_run->s390_sieic.ipa = vcpu->arch.sie_block->ipa; kvm_run->s390_sieic.ipb = vcpu->arch.sie_block->ipb; rc = 0; @@ -551,6 +558,9 @@ rerun_vcpu: rc = 0; } + kvm_run->psw_mask = vcpu->arch.sie_block->gpsw.mask; + kvm_run->psw_addr = vcpu->arch.sie_block->gpsw.addr; + if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &sigsaved, NULL); diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index ec5eee7..06cce82 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -58,7 +58,7 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code); int kvm_s390_inject_sigp_stop(struct kvm_vcpu *vcpu, int action); -static inline int kvm_s390_vcpu_get_memsize(struct kvm_vcpu *vcpu) +static inline long kvm_s390_vcpu_get_memsize(struct kvm_vcpu *vcpu) { return vcpu->arch.sie_block->gmslm - vcpu->arch.sie_block->gmsor diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c index 40c8c67..15ee111 100644 --- a/arch/s390/kvm/sigp.c +++ b/arch/s390/kvm/sigp.c @@ -188,9 +188,9 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address, /* make sure that the new value is valid memory */ address = address & 0x7fffe000u; - if ((copy_from_guest(vcpu, &tmp, - (u64) (address + vcpu->arch.sie_block->gmsor) , 1)) || - (copy_from_guest(vcpu, &tmp, (u64) (address + + if ((copy_from_user(&tmp, (void __user *) + (address + vcpu->arch.sie_block->gmsor) , 1)) || + (copy_from_user(&tmp, (void __user *)(address + vcpu->arch.sie_block->gmsor + PAGE_SIZE), 1))) { *reg |= SIGP_STAT_INVALID_PARAMETER; return 1; /* invalid parameter */ diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c index 97c1eca8..752b362 100644 --- a/arch/s390/lib/delay.c +++ b/arch/s390/lib/delay.c @@ -25,13 +25,13 @@ void __delay(unsigned long loops) asm volatile("0: brct %0,0b" : : "d" ((loops/2) + 1)); } -static void __udelay_disabled(unsigned long usecs) +static void __udelay_disabled(unsigned long long usecs) { unsigned long mask, cr0, cr0_saved; u64 clock_saved; clock_saved = local_tick_disable(); - set_clock_comparator(get_clock() + ((u64) usecs << 12)); + set_clock_comparator(get_clock() + (usecs << 12)); __ctl_store(cr0_saved, 0, 0); cr0 = (cr0_saved & 0xffff00e0) | 0x00000800; __ctl_load(cr0 , 0, 0); @@ -46,20 +46,25 @@ static void __udelay_disabled(unsigned long usecs) set_clock_comparator(S390_lowcore.clock_comparator); } -static void __udelay_enabled(unsigned long usecs) +static void __udelay_enabled(unsigned long long usecs) { unsigned long mask; - u64 end, time; + u64 clock_saved; + u64 end; mask = psw_kernel_bits | PSW_MASK_WAIT | PSW_MASK_EXT | PSW_MASK_IO; - end = get_clock() + ((u64) usecs << 12); + end = get_clock() + (usecs << 12); do { - time = end < S390_lowcore.clock_comparator ? - end : S390_lowcore.clock_comparator; - set_clock_comparator(time); + clock_saved = 0; + if (end < S390_lowcore.clock_comparator) { + clock_saved = local_tick_disable(); + set_clock_comparator(end); + } trace_hardirqs_on(); __load_psw_mask(mask); local_irq_disable(); + if (clock_saved) + local_tick_enable(clock_saved); } while (get_clock() < end); set_clock_comparator(S390_lowcore.clock_comparator); } @@ -67,7 +72,7 @@ static void __udelay_enabled(unsigned long usecs) /* * Waits for 'usecs' microseconds using the TOD clock comparator. */ -void __udelay(unsigned long usecs) +void __udelay(unsigned long long usecs) { unsigned long flags; @@ -101,11 +106,11 @@ EXPORT_SYMBOL(__udelay); * Simple udelay variant. To be used on startup and reboot * when the interrupt handler isn't working. */ -void udelay_simple(unsigned long usecs) +void udelay_simple(unsigned long long usecs) { u64 end; - end = get_clock() + ((u64) usecs << 12); + end = get_clock() + (usecs << 12); while (get_clock() < end) cpu_relax(); } diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c index f7e0d30..10754a3 100644 --- a/arch/s390/lib/spinlock.c +++ b/arch/s390/lib/spinlock.c @@ -39,7 +39,7 @@ static inline void _raw_yield_cpu(int cpu) _raw_yield(); } -void _raw_spin_lock_wait(raw_spinlock_t *lp) +void arch_spin_lock_wait(arch_spinlock_t *lp) { int count = spin_retry; unsigned int cpu = ~smp_processor_id(); @@ -51,15 +51,15 @@ void _raw_spin_lock_wait(raw_spinlock_t *lp) _raw_yield_cpu(~owner); count = spin_retry; } - if (__raw_spin_is_locked(lp)) + if (arch_spin_is_locked(lp)) continue; if (_raw_compare_and_swap(&lp->owner_cpu, 0, cpu) == 0) return; } } -EXPORT_SYMBOL(_raw_spin_lock_wait); +EXPORT_SYMBOL(arch_spin_lock_wait); -void _raw_spin_lock_wait_flags(raw_spinlock_t *lp, unsigned long flags) +void arch_spin_lock_wait_flags(arch_spinlock_t *lp, unsigned long flags) { int count = spin_retry; unsigned int cpu = ~smp_processor_id(); @@ -72,7 +72,7 @@ void _raw_spin_lock_wait_flags(raw_spinlock_t *lp, unsigned long flags) _raw_yield_cpu(~owner); count = spin_retry; } - if (__raw_spin_is_locked(lp)) + if (arch_spin_is_locked(lp)) continue; local_irq_disable(); if (_raw_compare_and_swap(&lp->owner_cpu, 0, cpu) == 0) @@ -80,32 +80,32 @@ void _raw_spin_lock_wait_flags(raw_spinlock_t *lp, unsigned long flags) local_irq_restore(flags); } } -EXPORT_SYMBOL(_raw_spin_lock_wait_flags); +EXPORT_SYMBOL(arch_spin_lock_wait_flags); -int _raw_spin_trylock_retry(raw_spinlock_t *lp) +int arch_spin_trylock_retry(arch_spinlock_t *lp) { unsigned int cpu = ~smp_processor_id(); int count; for (count = spin_retry; count > 0; count--) { - if (__raw_spin_is_locked(lp)) + if (arch_spin_is_locked(lp)) continue; if (_raw_compare_and_swap(&lp->owner_cpu, 0, cpu) == 0) return 1; } return 0; } -EXPORT_SYMBOL(_raw_spin_trylock_retry); +EXPORT_SYMBOL(arch_spin_trylock_retry); -void _raw_spin_relax(raw_spinlock_t *lock) +void arch_spin_relax(arch_spinlock_t *lock) { unsigned int cpu = lock->owner_cpu; if (cpu != 0) _raw_yield_cpu(~cpu); } -EXPORT_SYMBOL(_raw_spin_relax); +EXPORT_SYMBOL(arch_spin_relax); -void _raw_read_lock_wait(raw_rwlock_t *rw) +void _raw_read_lock_wait(arch_rwlock_t *rw) { unsigned int old; int count = spin_retry; @@ -115,7 +115,7 @@ void _raw_read_lock_wait(raw_rwlock_t *rw) _raw_yield(); count = spin_retry; } - if (!__raw_read_can_lock(rw)) + if (!arch_read_can_lock(rw)) continue; old = rw->lock & 0x7fffffffU; if (_raw_compare_and_swap(&rw->lock, old, old + 1) == old) @@ -124,7 +124,7 @@ void _raw_read_lock_wait(raw_rwlock_t *rw) } EXPORT_SYMBOL(_raw_read_lock_wait); -void _raw_read_lock_wait_flags(raw_rwlock_t *rw, unsigned long flags) +void _raw_read_lock_wait_flags(arch_rwlock_t *rw, unsigned long flags) { unsigned int old; int count = spin_retry; @@ -135,7 +135,7 @@ void _raw_read_lock_wait_flags(raw_rwlock_t *rw, unsigned long flags) _raw_yield(); count = spin_retry; } - if (!__raw_read_can_lock(rw)) + if (!arch_read_can_lock(rw)) continue; old = rw->lock & 0x7fffffffU; local_irq_disable(); @@ -145,13 +145,13 @@ void _raw_read_lock_wait_flags(raw_rwlock_t *rw, unsigned long flags) } EXPORT_SYMBOL(_raw_read_lock_wait_flags); -int _raw_read_trylock_retry(raw_rwlock_t *rw) +int _raw_read_trylock_retry(arch_rwlock_t *rw) { unsigned int old; int count = spin_retry; while (count-- > 0) { - if (!__raw_read_can_lock(rw)) + if (!arch_read_can_lock(rw)) continue; old = rw->lock & 0x7fffffffU; if (_raw_compare_and_swap(&rw->lock, old, old + 1) == old) @@ -161,7 +161,7 @@ int _raw_read_trylock_retry(raw_rwlock_t *rw) } EXPORT_SYMBOL(_raw_read_trylock_retry); -void _raw_write_lock_wait(raw_rwlock_t *rw) +void _raw_write_lock_wait(arch_rwlock_t *rw) { int count = spin_retry; @@ -170,7 +170,7 @@ void _raw_write_lock_wait(raw_rwlock_t *rw) _raw_yield(); count = spin_retry; } - if (!__raw_write_can_lock(rw)) + if (!arch_write_can_lock(rw)) continue; if (_raw_compare_and_swap(&rw->lock, 0, 0x80000000) == 0) return; @@ -178,7 +178,7 @@ void _raw_write_lock_wait(raw_rwlock_t *rw) } EXPORT_SYMBOL(_raw_write_lock_wait); -void _raw_write_lock_wait_flags(raw_rwlock_t *rw, unsigned long flags) +void _raw_write_lock_wait_flags(arch_rwlock_t *rw, unsigned long flags) { int count = spin_retry; @@ -188,7 +188,7 @@ void _raw_write_lock_wait_flags(raw_rwlock_t *rw, unsigned long flags) _raw_yield(); count = spin_retry; } - if (!__raw_write_can_lock(rw)) + if (!arch_write_can_lock(rw)) continue; local_irq_disable(); if (_raw_compare_and_swap(&rw->lock, 0, 0x80000000) == 0) @@ -197,12 +197,12 @@ void _raw_write_lock_wait_flags(raw_rwlock_t *rw, unsigned long flags) } EXPORT_SYMBOL(_raw_write_lock_wait_flags); -int _raw_write_trylock_retry(raw_rwlock_t *rw) +int _raw_write_trylock_retry(arch_rwlock_t *rw) { int count = spin_retry; while (count-- > 0) { - if (!__raw_write_can_lock(rw)) + if (!arch_write_can_lock(rw)) continue; if (_raw_compare_and_swap(&rw->lock, 0, 0x80000000) == 0) return 1; diff --git a/arch/s390/lib/uaccess_mvcos.c b/arch/s390/lib/uaccess_mvcos.c index 3f15aaf..60455f1 100644 --- a/arch/s390/lib/uaccess_mvcos.c +++ b/arch/s390/lib/uaccess_mvcos.c @@ -36,7 +36,7 @@ static size_t copy_from_user_mvcos(size_t size, const void __user *ptr, void *x) tmp1 = -4096UL; asm volatile( "0: .insn ss,0xc80000000000,0(%0,%2),0(%1),0\n" - " jz 7f\n" + "9: jz 7f\n" "1:"ALR" %0,%3\n" " "SLR" %1,%3\n" " "SLR" %2,%3\n" @@ -47,7 +47,7 @@ static size_t copy_from_user_mvcos(size_t size, const void __user *ptr, void *x) " "CLR" %0,%4\n" /* copy crosses next page boundary? */ " jnh 4f\n" "3: .insn ss,0xc80000000000,0(%4,%2),0(%1),0\n" - " "SLR" %0,%4\n" + "10:"SLR" %0,%4\n" " "ALR" %2,%4\n" "4:"LHI" %4,-1\n" " "ALR" %4,%0\n" /* copy remaining size, subtract 1 */ @@ -61,7 +61,7 @@ static size_t copy_from_user_mvcos(size_t size, const void __user *ptr, void *x) " j 8f\n" "7:"SLR" %0,%0\n" "8: \n" - EX_TABLE(0b,2b) EX_TABLE(3b,4b) + EX_TABLE(0b,2b) EX_TABLE(3b,4b) EX_TABLE(9b,2b) EX_TABLE(10b,4b) : "+a" (size), "+a" (ptr), "+a" (x), "+a" (tmp1), "=a" (tmp2) : "d" (reg0) : "cc", "memory"); return size; @@ -82,7 +82,7 @@ static size_t copy_to_user_mvcos(size_t size, void __user *ptr, const void *x) tmp1 = -4096UL; asm volatile( "0: .insn ss,0xc80000000000,0(%0,%1),0(%2),0\n" - " jz 4f\n" + "6: jz 4f\n" "1:"ALR" %0,%3\n" " "SLR" %1,%3\n" " "SLR" %2,%3\n" @@ -93,11 +93,11 @@ static size_t copy_to_user_mvcos(size_t size, void __user *ptr, const void *x) " "CLR" %0,%4\n" /* copy crosses next page boundary? */ " jnh 5f\n" "3: .insn ss,0xc80000000000,0(%4,%1),0(%2),0\n" - " "SLR" %0,%4\n" + "7:"SLR" %0,%4\n" " j 5f\n" "4:"SLR" %0,%0\n" "5: \n" - EX_TABLE(0b,2b) EX_TABLE(3b,5b) + EX_TABLE(0b,2b) EX_TABLE(3b,5b) EX_TABLE(6b,2b) EX_TABLE(7b,5b) : "+a" (size), "+a" (ptr), "+a" (x), "+a" (tmp1), "=a" (tmp2) : "d" (reg0) : "cc", "memory"); return size; @@ -162,7 +162,6 @@ static size_t clear_user_mvcos(size_t size, void __user *to) return size; } -#ifdef CONFIG_S390_SWITCH_AMODE static size_t strnlen_user_mvcos(size_t count, const char __user *src) { char buf[256]; @@ -200,7 +199,6 @@ static size_t strncpy_from_user_mvcos(size_t count, const char __user *src, } while ((len_str == len) && (done < count)); return done; } -#endif /* CONFIG_S390_SWITCH_AMODE */ struct uaccess_ops uaccess_mvcos = { .copy_from_user = copy_from_user_mvcos_check, @@ -215,7 +213,6 @@ struct uaccess_ops uaccess_mvcos = { .futex_atomic_cmpxchg = futex_atomic_cmpxchg_std, }; -#ifdef CONFIG_S390_SWITCH_AMODE struct uaccess_ops uaccess_mvcos_switch = { .copy_from_user = copy_from_user_mvcos, .copy_from_user_small = copy_from_user_mvcos, @@ -228,4 +225,3 @@ struct uaccess_ops uaccess_mvcos_switch = { .futex_atomic_op = futex_atomic_op_pt, .futex_atomic_cmpxchg = futex_atomic_cmpxchg_pt, }; -#endif diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c index cb5d59e..404f2de 100644 --- a/arch/s390/lib/uaccess_pt.c +++ b/arch/s390/lib/uaccess_pt.c @@ -23,86 +23,21 @@ static inline pte_t *follow_table(struct mm_struct *mm, unsigned long addr) pgd = pgd_offset(mm, addr); if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) - return NULL; + return (pte_t *) 0x3a; pud = pud_offset(pgd, addr); if (pud_none(*pud) || unlikely(pud_bad(*pud))) - return NULL; + return (pte_t *) 0x3b; pmd = pmd_offset(pud, addr); if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) - return NULL; + return (pte_t *) 0x10; return pte_offset_map(pmd, addr); } -static int __handle_fault(struct mm_struct *mm, unsigned long address, - int write_access) -{ - struct vm_area_struct *vma; - int ret = -EFAULT; - int fault; - - if (in_atomic()) - return ret; - down_read(&mm->mmap_sem); - vma = find_vma(mm, address); - if (unlikely(!vma)) - goto out; - if (unlikely(vma->vm_start > address)) { - if (!(vma->vm_flags & VM_GROWSDOWN)) - goto out; - if (expand_stack(vma, address)) - goto out; - } - - if (!write_access) { - /* page not present, check vm flags */ - if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))) - goto out; - } else { - if (!(vma->vm_flags & VM_WRITE)) - goto out; - } - -survive: - fault = handle_mm_fault(mm, vma, address, write_access ? FAULT_FLAG_WRITE : 0); - if (unlikely(fault & VM_FAULT_ERROR)) { - if (fault & VM_FAULT_OOM) - goto out_of_memory; - else if (fault & VM_FAULT_SIGBUS) - goto out_sigbus; - BUG(); - } - if (fault & VM_FAULT_MAJOR) - current->maj_flt++; - else - current->min_flt++; - ret = 0; -out: - up_read(&mm->mmap_sem); - return ret; - -out_of_memory: - up_read(&mm->mmap_sem); - if (is_global_init(current)) { - yield(); - down_read(&mm->mmap_sem); - goto survive; - } - printk("VM: killing process %s\n", current->comm); - return ret; - -out_sigbus: - up_read(&mm->mmap_sem); - current->thread.prot_addr = address; - current->thread.trap_no = 0x11; - force_sig(SIGBUS, current); - return ret; -} - -static size_t __user_copy_pt(unsigned long uaddr, void *kptr, - size_t n, int write_user) +static __always_inline size_t __user_copy_pt(unsigned long uaddr, void *kptr, + size_t n, int write_user) { struct mm_struct *mm = current->mm; unsigned long offset, pfn, done, size; @@ -114,12 +49,17 @@ retry: spin_lock(&mm->page_table_lock); do { pte = follow_table(mm, uaddr); - if (!pte || !pte_present(*pte) || - (write_user && !pte_write(*pte))) + if ((unsigned long) pte < 0x1000) goto fault; + if (!pte_present(*pte)) { + pte = (pte_t *) 0x11; + goto fault; + } else if (write_user && !pte_write(*pte)) { + pte = (pte_t *) 0x04; + goto fault; + } pfn = pte_pfn(*pte); - offset = uaddr & (PAGE_SIZE - 1); size = min(n - done, PAGE_SIZE - offset); if (write_user) { @@ -137,7 +77,7 @@ retry: return n - done; fault: spin_unlock(&mm->page_table_lock); - if (__handle_fault(mm, uaddr, write_user)) + if (__handle_fault(uaddr, (unsigned long) pte, write_user)) return n - done; goto retry; } @@ -146,30 +86,31 @@ fault: * Do DAT for user address by page table walk, return kernel address. * This function needs to be called with current->mm->page_table_lock held. */ -static unsigned long __dat_user_addr(unsigned long uaddr) +static __always_inline unsigned long __dat_user_addr(unsigned long uaddr) { struct mm_struct *mm = current->mm; - unsigned long pfn, ret; + unsigned long pfn; pte_t *pte; int rc; - ret = 0; retry: pte = follow_table(mm, uaddr); - if (!pte || !pte_present(*pte)) + if ((unsigned long) pte < 0x1000) goto fault; + if (!pte_present(*pte)) { + pte = (pte_t *) 0x11; + goto fault; + } pfn = pte_pfn(*pte); - ret = (pfn << PAGE_SHIFT) + (uaddr & (PAGE_SIZE - 1)); -out: - return ret; + return (pfn << PAGE_SHIFT) + (uaddr & (PAGE_SIZE - 1)); fault: spin_unlock(&mm->page_table_lock); - rc = __handle_fault(mm, uaddr, 0); + rc = __handle_fault(uaddr, (unsigned long) pte, 0); spin_lock(&mm->page_table_lock); - if (rc) - goto out; - goto retry; + if (!rc) + goto retry; + return 0; } size_t copy_from_user_pt(size_t n, const void __user *from, void *to) @@ -234,8 +175,12 @@ retry: spin_lock(&mm->page_table_lock); do { pte = follow_table(mm, uaddr); - if (!pte || !pte_present(*pte)) + if ((unsigned long) pte < 0x1000) + goto fault; + if (!pte_present(*pte)) { + pte = (pte_t *) 0x11; goto fault; + } pfn = pte_pfn(*pte); offset = uaddr & (PAGE_SIZE-1); @@ -249,9 +194,8 @@ retry: return done + 1; fault: spin_unlock(&mm->page_table_lock); - if (__handle_fault(mm, uaddr, 0)) { + if (__handle_fault(uaddr, (unsigned long) pte, 0)) return 0; - } goto retry; } @@ -284,7 +228,7 @@ static size_t copy_in_user_pt(size_t n, void __user *to, { struct mm_struct *mm = current->mm; unsigned long offset_from, offset_to, offset_max, pfn_from, pfn_to, - uaddr, done, size; + uaddr, done, size, error_code; unsigned long uaddr_from = (unsigned long) from; unsigned long uaddr_to = (unsigned long) to; pte_t *pte_from, *pte_to; @@ -298,17 +242,28 @@ static size_t copy_in_user_pt(size_t n, void __user *to, retry: spin_lock(&mm->page_table_lock); do { + write_user = 0; + uaddr = uaddr_from; pte_from = follow_table(mm, uaddr_from); - if (!pte_from || !pte_present(*pte_from)) { - uaddr = uaddr_from; - write_user = 0; + error_code = (unsigned long) pte_from; + if (error_code < 0x1000) + goto fault; + if (!pte_present(*pte_from)) { + error_code = 0x11; goto fault; } + write_user = 1; + uaddr = uaddr_to; pte_to = follow_table(mm, uaddr_to); - if (!pte_to || !pte_present(*pte_to) || !pte_write(*pte_to)) { - uaddr = uaddr_to; - write_user = 1; + error_code = (unsigned long) pte_to; + if (error_code < 0x1000) + goto fault; + if (!pte_present(*pte_to)) { + error_code = 0x11; + goto fault; + } else if (!pte_write(*pte_to)) { + error_code = 0x04; goto fault; } @@ -329,7 +284,7 @@ retry: return n - done; fault: spin_unlock(&mm->page_table_lock); - if (__handle_fault(mm, uaddr, write_user)) + if (__handle_fault(uaddr, error_code, write_user)) return n - done; goto retry; } diff --git a/arch/s390/lib/uaccess_std.c b/arch/s390/lib/uaccess_std.c index d2ffbad..07deaee 100644 --- a/arch/s390/lib/uaccess_std.c +++ b/arch/s390/lib/uaccess_std.c @@ -36,12 +36,12 @@ size_t copy_from_user_std(size_t size, const void __user *ptr, void *x) tmp1 = -256UL; asm volatile( "0: mvcp 0(%0,%2),0(%1),%3\n" - " jz 8f\n" + "10:jz 8f\n" "1:"ALR" %0,%3\n" " la %1,256(%1)\n" " la %2,256(%2)\n" "2: mvcp 0(%0,%2),0(%1),%3\n" - " jnz 1b\n" + "11:jnz 1b\n" " j 8f\n" "3: la %4,255(%1)\n" /* %4 = ptr + 255 */ " "LHI" %3,-4096\n" @@ -50,7 +50,7 @@ size_t copy_from_user_std(size_t size, const void __user *ptr, void *x) " "CLR" %0,%4\n" /* copy crosses next page boundary? */ " jnh 5f\n" "4: mvcp 0(%4,%2),0(%1),%3\n" - " "SLR" %0,%4\n" + "12:"SLR" %0,%4\n" " "ALR" %2,%4\n" "5:"LHI" %4,-1\n" " "ALR" %4,%0\n" /* copy remaining size, subtract 1 */ @@ -65,6 +65,7 @@ size_t copy_from_user_std(size_t size, const void __user *ptr, void *x) "8:"SLR" %0,%0\n" "9: \n" EX_TABLE(0b,3b) EX_TABLE(2b,3b) EX_TABLE(4b,5b) + EX_TABLE(10b,3b) EX_TABLE(11b,3b) EX_TABLE(12b,5b) : "+a" (size), "+a" (ptr), "+a" (x), "+a" (tmp1), "=a" (tmp2) : : "cc", "memory"); return size; @@ -85,12 +86,12 @@ size_t copy_to_user_std(size_t size, void __user *ptr, const void *x) tmp1 = -256UL; asm volatile( "0: mvcs 0(%0,%1),0(%2),%3\n" - " jz 5f\n" + "7: jz 5f\n" "1:"ALR" %0,%3\n" " la %1,256(%1)\n" " la %2,256(%2)\n" "2: mvcs 0(%0,%1),0(%2),%3\n" - " jnz 1b\n" + "8: jnz 1b\n" " j 5f\n" "3: la %4,255(%1)\n" /* %4 = ptr + 255 */ " "LHI" %3,-4096\n" @@ -99,11 +100,12 @@ size_t copy_to_user_std(size_t size, void __user *ptr, const void *x) " "CLR" %0,%4\n" /* copy crosses next page boundary? */ " jnh 6f\n" "4: mvcs 0(%4,%1),0(%2),%3\n" - " "SLR" %0,%4\n" + "9:"SLR" %0,%4\n" " j 6f\n" "5:"SLR" %0,%0\n" "6: \n" EX_TABLE(0b,3b) EX_TABLE(2b,3b) EX_TABLE(4b,6b) + EX_TABLE(7b,3b) EX_TABLE(8b,3b) EX_TABLE(9b,6b) : "+a" (size), "+a" (ptr), "+a" (x), "+a" (tmp1), "=a" (tmp2) : : "cc", "memory"); return size; diff --git a/arch/s390/math-emu/math.c b/arch/s390/math-emu/math.c index 3ee78cc..cd4e9c1 100644 --- a/arch/s390/math-emu/math.c +++ b/arch/s390/math-emu/math.c @@ -2088,7 +2088,7 @@ int math_emu_ldr(__u8 *opcode) { __u16 opc = *((__u16 *) opcode); if ((opc & 0x90) == 0) { /* test if rx in {0,2,4,6} */ - /* we got an exception therfore ry can't be in {0,2,4,6} */ + /* we got an exception therefore ry can't be in {0,2,4,6} */ asm volatile( /* load rx from fp_regs.fprs[ry] */ " bras 1,0f\n" " ld 0,0(%1)\n" @@ -2118,7 +2118,7 @@ int math_emu_ler(__u8 *opcode) { __u16 opc = *((__u16 *) opcode); if ((opc & 0x90) == 0) { /* test if rx in {0,2,4,6} */ - /* we got an exception therfore ry can't be in {0,2,4,6} */ + /* we got an exception therefore ry can't be in {0,2,4,6} */ asm volatile( /* load rx from fp_regs.fprs[ry] */ " bras 1,0f\n" " le 0,0(%1)\n" diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c index b201135..76a3637 100644 --- a/arch/s390/mm/cmm.c +++ b/arch/s390/mm/cmm.c @@ -18,6 +18,7 @@ #include <linux/swap.h> #include <linux/kthread.h> #include <linux/oom.h> +#include <linux/suspend.h> #include <asm/pgalloc.h> #include <asm/uaccess.h> @@ -44,6 +45,7 @@ static volatile long cmm_pages_target; static volatile long cmm_timed_pages_target; static long cmm_timeout_pages; static long cmm_timeout_seconds; +static int cmm_suspended; static struct cmm_page_array *cmm_page_list; static struct cmm_page_array *cmm_timed_page_list; @@ -147,9 +149,9 @@ cmm_thread(void *dummy) while (1) { rc = wait_event_interruptible(cmm_thread_wait, - (cmm_pages != cmm_pages_target || - cmm_timed_pages != cmm_timed_pages_target || - kthread_should_stop())); + (!cmm_suspended && (cmm_pages != cmm_pages_target || + cmm_timed_pages != cmm_timed_pages_target)) || + kthread_should_stop()); if (kthread_should_stop() || rc == -ERESTARTSYS) { cmm_pages_target = cmm_pages; cmm_timed_pages_target = cmm_timed_pages; @@ -343,30 +345,29 @@ static struct ctl_table cmm_table[] = { { .procname = "cmm_pages", .mode = 0644, - .proc_handler = &cmm_pages_handler, + .proc_handler = cmm_pages_handler, }, { .procname = "cmm_timed_pages", .mode = 0644, - .proc_handler = &cmm_pages_handler, + .proc_handler = cmm_pages_handler, }, { .procname = "cmm_timeout", .mode = 0644, - .proc_handler = &cmm_timeout_handler, + .proc_handler = cmm_timeout_handler, }, - { .ctl_name = 0 } + { } }; static struct ctl_table cmm_dir_table[] = { { - .ctl_name = CTL_VM, .procname = "vm", .maxlen = 0, .mode = 0555, .child = cmm_table, }, - { .ctl_name = 0 } + { } }; #endif @@ -411,6 +412,38 @@ cmm_smsg_target(char *from, char *msg) static struct ctl_table_header *cmm_sysctl_header; +static int cmm_suspend(void) +{ + cmm_suspended = 1; + cmm_free_pages(cmm_pages, &cmm_pages, &cmm_page_list); + cmm_free_pages(cmm_timed_pages, &cmm_timed_pages, &cmm_timed_page_list); + return 0; +} + +static int cmm_resume(void) +{ + cmm_suspended = 0; + cmm_kick_thread(); + return 0; +} + +static int cmm_power_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + switch (event) { + case PM_POST_HIBERNATION: + return cmm_resume(); + case PM_HIBERNATION_PREPARE: + return cmm_suspend(); + default: + return NOTIFY_DONE; + } +} + +static struct notifier_block cmm_power_notifier = { + .notifier_call = cmm_power_event, +}; + static int cmm_init (void) { @@ -419,7 +452,7 @@ cmm_init (void) #ifdef CONFIG_CMM_PROC cmm_sysctl_header = register_sysctl_table(cmm_dir_table); if (!cmm_sysctl_header) - goto out; + goto out_sysctl; #endif #ifdef CONFIG_CMM_IUCV rc = smsg_register_callback(SMSG_PREFIX, cmm_smsg_target); @@ -429,17 +462,21 @@ cmm_init (void) rc = register_oom_notifier(&cmm_oom_nb); if (rc < 0) goto out_oom_notify; + rc = register_pm_notifier(&cmm_power_notifier); + if (rc) + goto out_pm; init_waitqueue_head(&cmm_thread_wait); init_timer(&cmm_timer); cmm_thread_ptr = kthread_run(cmm_thread, NULL, "cmmthread"); rc = IS_ERR(cmm_thread_ptr) ? PTR_ERR(cmm_thread_ptr) : 0; - if (!rc) - goto out; - /* - * kthread_create failed. undo all the stuff from above again. - */ - unregister_oom_notifier(&cmm_oom_nb); + if (rc) + goto out_kthread; + return 0; +out_kthread: + unregister_pm_notifier(&cmm_power_notifier); +out_pm: + unregister_oom_notifier(&cmm_oom_nb); out_oom_notify: #ifdef CONFIG_CMM_IUCV smsg_unregister_callback(SMSG_PREFIX, cmm_smsg_target); @@ -447,8 +484,8 @@ out_smsg: #endif #ifdef CONFIG_CMM_PROC unregister_sysctl_table(cmm_sysctl_header); +out_sysctl: #endif -out: return rc; } @@ -456,6 +493,7 @@ static void cmm_exit(void) { kthread_stop(cmm_thread_ptr); + unregister_pm_notifier(&cmm_power_notifier); unregister_oom_notifier(&cmm_oom_nb); cmm_free_pages(cmm_pages, &cmm_pages, &cmm_page_list); cmm_free_pages(cmm_timed_pages, &cmm_timed_pages, &cmm_timed_page_list); diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 6d50746..fc102e7 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -34,16 +34,15 @@ #include <asm/pgtable.h> #include <asm/s390_ext.h> #include <asm/mmu_context.h> +#include <asm/compat.h> #include "../kernel/entry.h" #ifndef CONFIG_64BIT #define __FAIL_ADDR_MASK 0x7ffff000 -#define __FIXUP_MASK 0x7fffffff #define __SUBCODE_MASK 0x0200 #define __PF_RES_FIELD 0ULL #else /* CONFIG_64BIT */ #define __FAIL_ADDR_MASK -4096L -#define __FIXUP_MASK ~0L #define __SUBCODE_MASK 0x0600 #define __PF_RES_FIELD 0x8000000000000000ULL #endif /* CONFIG_64BIT */ @@ -52,11 +51,15 @@ extern int sysctl_userprocess_debug; #endif -#ifdef CONFIG_KPROBES -static inline int notify_page_fault(struct pt_regs *regs, long err) +#define VM_FAULT_BADCONTEXT 0x010000 +#define VM_FAULT_BADMAP 0x020000 +#define VM_FAULT_BADACCESS 0x040000 + +static inline int notify_page_fault(struct pt_regs *regs) { int ret = 0; +#ifdef CONFIG_KPROBES /* kprobe_running() needs smp_processor_id() */ if (!user_mode(regs)) { preempt_disable(); @@ -64,15 +67,9 @@ static inline int notify_page_fault(struct pt_regs *regs, long err) ret = 1; preempt_enable(); } - +#endif return ret; } -#else -static inline int notify_page_fault(struct pt_regs *regs, long err) -{ - return 0; -} -#endif /* @@ -100,57 +97,50 @@ void bust_spinlocks(int yes) /* * Returns the address space associated with the fault. - * Returns 0 for kernel space, 1 for user space and - * 2 for code execution in user space with noexec=on. + * Returns 0 for kernel space and 1 for user space. */ -static inline int check_space(struct task_struct *tsk) +static inline int user_space_fault(unsigned long trans_exc_code) { /* - * The lowest two bits of S390_lowcore.trans_exc_code - * indicate which paging table was used. + * The lowest two bits of the translation exception + * identification indicate which paging table was used. */ - int desc = S390_lowcore.trans_exc_code & 3; - - if (desc == 3) /* Home Segment Table Descriptor */ - return switch_amode == 0; - if (desc == 2) /* Secondary Segment Table Descriptor */ - return tsk->thread.mm_segment.ar4; -#ifdef CONFIG_S390_SWITCH_AMODE - if (unlikely(desc == 1)) { /* STD determined via access register */ - /* %a0 always indicates primary space. */ - if (S390_lowcore.exc_access_id != 0) { - save_access_regs(tsk->thread.acrs); - /* - * An alet of 0 indicates primary space. - * An alet of 1 indicates secondary space. - * Any other alet values generate an - * alen-translation exception. - */ - if (tsk->thread.acrs[S390_lowcore.exc_access_id]) - return tsk->thread.mm_segment.ar4; - } - } -#endif - /* Primary Segment Table Descriptor */ - return switch_amode << s390_noexec; + trans_exc_code &= 3; + if (trans_exc_code == 2) + /* Access via secondary space, set_fs setting decides */ + return current->thread.mm_segment.ar4; + if (user_mode == HOME_SPACE_MODE) + /* User space if the access has been done via home space. */ + return trans_exc_code == 3; + /* + * If the user space is not the home space the kernel runs in home + * space. Access via secondary space has already been covered, + * access via primary space or access register is from user space + * and access via home space is from the kernel. + */ + return trans_exc_code != 3; } /* * Send SIGSEGV to task. This is an external routine * to keep the stack usage of do_page_fault small. */ -static void do_sigsegv(struct pt_regs *regs, unsigned long error_code, - int si_code, unsigned long address) +static noinline void do_sigsegv(struct pt_regs *regs, long int_code, + int si_code, unsigned long trans_exc_code) { struct siginfo si; + unsigned long address; + address = trans_exc_code & __FAIL_ADDR_MASK; + current->thread.prot_addr = address; + current->thread.trap_no = int_code; #if defined(CONFIG_SYSCTL) || defined(CONFIG_PROCESS_DEBUG) #if defined(CONFIG_SYSCTL) if (sysctl_userprocess_debug) #endif { printk("User process fault: interruption code 0x%lX\n", - error_code); + int_code); printk("failing address: %lX\n", address); show_regs(regs); } @@ -161,13 +151,14 @@ static void do_sigsegv(struct pt_regs *regs, unsigned long error_code, force_sig_info(SIGSEGV, &si, current); } -static void do_no_context(struct pt_regs *regs, unsigned long error_code, - unsigned long address) +static noinline void do_no_context(struct pt_regs *regs, long int_code, + unsigned long trans_exc_code) { const struct exception_table_entry *fixup; + unsigned long address; /* Are we prepared to handle this kernel fault? */ - fixup = search_exception_tables(regs->psw.addr & __FIXUP_MASK); + fixup = search_exception_tables(regs->psw.addr & PSW_ADDR_INSN); if (fixup) { regs->psw.addr = fixup->fixup | PSW_ADDR_AMODE; return; @@ -177,129 +168,149 @@ static void do_no_context(struct pt_regs *regs, unsigned long error_code, * Oops. The kernel tried to access some bad page. We'll have to * terminate things with extreme prejudice. */ - if (check_space(current) == 0) + address = trans_exc_code & __FAIL_ADDR_MASK; + if (!user_space_fault(trans_exc_code)) printk(KERN_ALERT "Unable to handle kernel pointer dereference" " at virtual kernel address %p\n", (void *)address); else printk(KERN_ALERT "Unable to handle kernel paging request" " at virtual user address %p\n", (void *)address); - die("Oops", regs, error_code); + die("Oops", regs, int_code); do_exit(SIGKILL); } -static void do_low_address(struct pt_regs *regs, unsigned long error_code) +static noinline void do_low_address(struct pt_regs *regs, long int_code, + unsigned long trans_exc_code) { /* Low-address protection hit in kernel mode means NULL pointer write access in kernel mode. */ if (regs->psw.mask & PSW_MASK_PSTATE) { /* Low-address protection hit in user mode 'cannot happen'. */ - die ("Low-address protection", regs, error_code); + die ("Low-address protection", regs, int_code); do_exit(SIGKILL); } - do_no_context(regs, error_code, 0); + do_no_context(regs, int_code, trans_exc_code); } -static void do_sigbus(struct pt_regs *regs, unsigned long error_code, - unsigned long address) +static noinline void do_sigbus(struct pt_regs *regs, long int_code, + unsigned long trans_exc_code) { struct task_struct *tsk = current; - struct mm_struct *mm = tsk->mm; - up_read(&mm->mmap_sem); /* * Send a sigbus, regardless of whether we were in kernel * or user mode. */ - tsk->thread.prot_addr = address; - tsk->thread.trap_no = error_code; + tsk->thread.prot_addr = trans_exc_code & __FAIL_ADDR_MASK; + tsk->thread.trap_no = int_code; force_sig(SIGBUS, tsk); - - /* Kernel mode? Handle exceptions or die */ - if (!(regs->psw.mask & PSW_MASK_PSTATE)) - do_no_context(regs, error_code, address); } #ifdef CONFIG_S390_EXEC_PROTECT -static int signal_return(struct mm_struct *mm, struct pt_regs *regs, - unsigned long address, unsigned long error_code) +static noinline int signal_return(struct pt_regs *regs, long int_code, + unsigned long trans_exc_code) { u16 instruction; int rc; -#ifdef CONFIG_COMPAT - int compat; -#endif - pagefault_disable(); rc = __get_user(instruction, (u16 __user *) regs->psw.addr); - pagefault_enable(); - if (rc) - return -EFAULT; - up_read(&mm->mmap_sem); - clear_tsk_thread_flag(current, TIF_SINGLE_STEP); -#ifdef CONFIG_COMPAT - compat = is_compat_task(); - if (compat && instruction == 0x0a77) - sys32_sigreturn(); - else if (compat && instruction == 0x0aad) - sys32_rt_sigreturn(); - else -#endif - if (instruction == 0x0a77) - sys_sigreturn(); - else if (instruction == 0x0aad) - sys_rt_sigreturn(); - else { - current->thread.prot_addr = address; - current->thread.trap_no = error_code; - do_sigsegv(regs, error_code, SEGV_MAPERR, address); - } + if (!rc && instruction == 0x0a77) { + clear_tsk_thread_flag(current, TIF_SINGLE_STEP); + if (is_compat_task()) + sys32_sigreturn(); + else + sys_sigreturn(); + } else if (!rc && instruction == 0x0aad) { + clear_tsk_thread_flag(current, TIF_SINGLE_STEP); + if (is_compat_task()) + sys32_rt_sigreturn(); + else + sys_rt_sigreturn(); + } else + do_sigsegv(regs, int_code, SEGV_MAPERR, trans_exc_code); return 0; } #endif /* CONFIG_S390_EXEC_PROTECT */ +static noinline void do_fault_error(struct pt_regs *regs, long int_code, + unsigned long trans_exc_code, int fault) +{ + int si_code; + + switch (fault) { + case VM_FAULT_BADACCESS: +#ifdef CONFIG_S390_EXEC_PROTECT + if ((regs->psw.mask & PSW_MASK_ASC) == PSW_ASC_SECONDARY && + (trans_exc_code & 3) == 0) { + signal_return(regs, int_code, trans_exc_code); + break; + } +#endif /* CONFIG_S390_EXEC_PROTECT */ + case VM_FAULT_BADMAP: + /* Bad memory access. Check if it is kernel or user space. */ + if (regs->psw.mask & PSW_MASK_PSTATE) { + /* User mode accesses just cause a SIGSEGV */ + si_code = (fault == VM_FAULT_BADMAP) ? + SEGV_MAPERR : SEGV_ACCERR; + do_sigsegv(regs, int_code, si_code, trans_exc_code); + return; + } + case VM_FAULT_BADCONTEXT: + do_no_context(regs, int_code, trans_exc_code); + break; + default: /* fault & VM_FAULT_ERROR */ + if (fault & VM_FAULT_OOM) + pagefault_out_of_memory(); + else if (fault & VM_FAULT_SIGBUS) { + do_sigbus(regs, int_code, trans_exc_code); + /* Kernel mode? Handle exceptions or die */ + if (!(regs->psw.mask & PSW_MASK_PSTATE)) + do_no_context(regs, int_code, trans_exc_code); + } else + BUG(); + break; + } +} + /* * This routine handles page faults. It determines the address, * and the problem, and then passes it off to one of the appropriate * routines. * - * error_code: + * interruption code (int_code): * 04 Protection -> Write-Protection (suprression) * 10 Segment translation -> Not present (nullification) * 11 Page translation -> Not present (nullification) * 3b Region third trans. -> Not present (nullification) */ -static inline void -do_exception(struct pt_regs *regs, unsigned long error_code, int write) +static inline int do_exception(struct pt_regs *regs, int access, + unsigned long trans_exc_code) { struct task_struct *tsk; struct mm_struct *mm; struct vm_area_struct *vma; unsigned long address; - int space; - int si_code; int fault; - if (notify_page_fault(regs, error_code)) - return; + if (notify_page_fault(regs)) + return 0; tsk = current; mm = tsk->mm; - /* get the failing address and the affected space */ - address = S390_lowcore.trans_exc_code & __FAIL_ADDR_MASK; - space = check_space(tsk); - /* * Verify that the fault happened in user space, that * we are not in an interrupt and that there is a * user context. */ - if (unlikely(space == 0 || in_atomic() || !mm)) - goto no_context; + fault = VM_FAULT_BADCONTEXT; + if (unlikely(!user_space_fault(trans_exc_code) || in_atomic() || !mm)) + goto out; + address = trans_exc_code & __FAIL_ADDR_MASK; /* * When we get here, the fault happened in the current * task's user address space, so we can switch on the @@ -309,42 +320,26 @@ do_exception(struct pt_regs *regs, unsigned long error_code, int write) perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address); down_read(&mm->mmap_sem); - si_code = SEGV_MAPERR; + fault = VM_FAULT_BADMAP; vma = find_vma(mm, address); if (!vma) - goto bad_area; - -#ifdef CONFIG_S390_EXEC_PROTECT - if (unlikely((space == 2) && !(vma->vm_flags & VM_EXEC))) - if (!signal_return(mm, regs, address, error_code)) - /* - * signal_return() has done an up_read(&mm->mmap_sem) - * if it returns 0. - */ - return; -#endif + goto out_up; - if (vma->vm_start <= address) - goto good_area; - if (!(vma->vm_flags & VM_GROWSDOWN)) - goto bad_area; - if (expand_stack(vma, address)) - goto bad_area; -/* - * Ok, we have a good vm_area for this memory access, so - * we can handle it.. - */ -good_area: - si_code = SEGV_ACCERR; - if (!write) { - /* page not present, check vm flags */ - if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))) - goto bad_area; - } else { - if (!(vma->vm_flags & VM_WRITE)) - goto bad_area; + if (unlikely(vma->vm_start > address)) { + if (!(vma->vm_flags & VM_GROWSDOWN)) + goto out_up; + if (expand_stack(vma, address)) + goto out_up; } + /* + * Ok, we have a good vm_area for this memory access, so + * we can handle it.. + */ + fault = VM_FAULT_BADACCESS; + if (unlikely(!(vma->vm_flags & access))) + goto out_up; + if (is_vm_hugetlb_page(vma)) address &= HPAGE_MASK; /* @@ -352,18 +347,11 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0); - if (unlikely(fault & VM_FAULT_ERROR)) { - if (fault & VM_FAULT_OOM) { - up_read(&mm->mmap_sem); - pagefault_out_of_memory(); - return; - } else if (fault & VM_FAULT_SIGBUS) { - do_sigbus(regs, error_code, address); - return; - } - BUG(); - } + fault = handle_mm_fault(mm, vma, address, + (access == VM_WRITE) ? FAULT_FLAG_WRITE : 0); + if (unlikely(fault & VM_FAULT_ERROR)) + goto out_up; + if (fault & VM_FAULT_MAJOR) { tsk->maj_flt++; perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0, @@ -373,74 +361,69 @@ good_area: perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0, regs, address); } - up_read(&mm->mmap_sem); /* * The instruction that caused the program check will * be repeated. Don't signal single step via SIGTRAP. */ clear_tsk_thread_flag(tsk, TIF_SINGLE_STEP); - return; - -/* - * Something tried to access memory that isn't in our memory map.. - * Fix it, but check if it's kernel or user first.. - */ -bad_area: + fault = 0; +out_up: up_read(&mm->mmap_sem); - - /* User mode accesses just cause a SIGSEGV */ - if (regs->psw.mask & PSW_MASK_PSTATE) { - tsk->thread.prot_addr = address; - tsk->thread.trap_no = error_code; - do_sigsegv(regs, error_code, si_code, address); - return; - } - -no_context: - do_no_context(regs, error_code, address); +out: + return fault; } -void __kprobes do_protection_exception(struct pt_regs *regs, - long error_code) +void __kprobes do_protection_exception(struct pt_regs *regs, long int_code) { + unsigned long trans_exc_code = S390_lowcore.trans_exc_code; + int fault; + /* Protection exception is supressing, decrement psw address. */ - regs->psw.addr -= (error_code >> 16); + regs->psw.addr -= (int_code >> 16); /* * Check for low-address protection. This needs to be treated * as a special case because the translation exception code * field is not guaranteed to contain valid data in this case. */ - if (unlikely(!(S390_lowcore.trans_exc_code & 4))) { - do_low_address(regs, error_code); + if (unlikely(!(trans_exc_code & 4))) { + do_low_address(regs, int_code, trans_exc_code); return; } - do_exception(regs, 4, 1); + fault = do_exception(regs, VM_WRITE, trans_exc_code); + if (unlikely(fault)) + do_fault_error(regs, 4, trans_exc_code, fault); } -void __kprobes do_dat_exception(struct pt_regs *regs, long error_code) +void __kprobes do_dat_exception(struct pt_regs *regs, long int_code) { - do_exception(regs, error_code & 0xff, 0); + unsigned long trans_exc_code = S390_lowcore.trans_exc_code; + int access, fault; + + access = VM_READ | VM_EXEC | VM_WRITE; +#ifdef CONFIG_S390_EXEC_PROTECT + if ((regs->psw.mask & PSW_MASK_ASC) == PSW_ASC_SECONDARY && + (trans_exc_code & 3) == 0) + access = VM_EXEC; +#endif + fault = do_exception(regs, access, trans_exc_code); + if (unlikely(fault)) + do_fault_error(regs, int_code & 255, trans_exc_code, fault); } #ifdef CONFIG_64BIT -void __kprobes do_asce_exception(struct pt_regs *regs, unsigned long error_code) +void __kprobes do_asce_exception(struct pt_regs *regs, long int_code) { - struct mm_struct *mm; + unsigned long trans_exc_code = S390_lowcore.trans_exc_code; + struct mm_struct *mm = current->mm; struct vm_area_struct *vma; - unsigned long address; - int space; - - mm = current->mm; - address = S390_lowcore.trans_exc_code & __FAIL_ADDR_MASK; - space = check_space(current); - if (unlikely(space == 0 || in_atomic() || !mm)) + if (unlikely(!user_space_fault(trans_exc_code) || in_atomic() || !mm)) goto no_context; local_irq_enable(); down_read(&mm->mmap_sem); - vma = find_vma(mm, address); + vma = find_vma(mm, trans_exc_code & __FAIL_ADDR_MASK); up_read(&mm->mmap_sem); if (vma) { @@ -450,17 +433,38 @@ void __kprobes do_asce_exception(struct pt_regs *regs, unsigned long error_code) /* User mode accesses just cause a SIGSEGV */ if (regs->psw.mask & PSW_MASK_PSTATE) { - current->thread.prot_addr = address; - current->thread.trap_no = error_code; - do_sigsegv(regs, error_code, SEGV_MAPERR, address); + do_sigsegv(regs, int_code, SEGV_MAPERR, trans_exc_code); return; } no_context: - do_no_context(regs, error_code, address); + do_no_context(regs, int_code, trans_exc_code); } #endif +int __handle_fault(unsigned long uaddr, unsigned long int_code, int write_user) +{ + struct pt_regs regs; + int access, fault; + + regs.psw.mask = psw_kernel_bits; + if (!irqs_disabled()) + regs.psw.mask |= PSW_MASK_IO | PSW_MASK_EXT; + regs.psw.addr = (unsigned long) __builtin_return_address(0); + regs.psw.addr |= PSW_ADDR_AMODE; + uaddr &= PAGE_MASK; + access = write_user ? VM_WRITE : VM_READ; + fault = do_exception(®s, access, uaddr | 2); + if (unlikely(fault)) { + if (fault & VM_FAULT_OOM) { + pagefault_out_of_memory(); + fault = 0; + } else if (fault & VM_FAULT_SIGBUS) + do_sigbus(®s, int_code, uaddr); + } + return fault ? -EFAULT : 0; +} + #ifdef CONFIG_PFAULT /* * 'pfault' pseudo page faults routines. @@ -522,7 +526,7 @@ void pfault_fini(void) : : "a" (&refbk), "m" (refbk) : "cc"); } -static void pfault_interrupt(__u16 error_code) +static void pfault_interrupt(__u16 int_code) { struct task_struct *tsk; __u16 subcode; diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index c60bfb3..ad621e0 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -269,7 +269,7 @@ int s390_enable_sie(void) struct mm_struct *mm, *old_mm; /* Do we have switched amode? If no, we cannot do sie */ - if (!switch_amode) + if (user_mode == HOME_SPACE_MODE) return -EINVAL; /* Do we have pgstes? if yes, we are done */ @@ -279,7 +279,10 @@ int s390_enable_sie(void) /* lets check if we are allowed to replace the mm */ task_lock(tsk); if (!tsk->mm || atomic_read(&tsk->mm->mm_users) > 1 || - tsk->mm != tsk->active_mm || !hlist_empty(&tsk->mm->ioctx_list)) { +#ifdef CONFIG_AIO + !hlist_empty(&tsk->mm->ioctx_list) || +#endif + tsk->mm != tsk->active_mm) { task_unlock(tsk); return -EINVAL; } @@ -295,7 +298,10 @@ int s390_enable_sie(void) /* Now lets check again if something happened */ task_lock(tsk); if (!tsk->mm || atomic_read(&tsk->mm->mm_users) > 1 || - tsk->mm != tsk->active_mm || !hlist_empty(&tsk->mm->ioctx_list)) { +#ifdef CONFIG_AIO + !hlist_empty(&tsk->mm->ioctx_list) || +#endif + tsk->mm != tsk->active_mm) { mmput(mm); task_unlock(tsk); return -EINVAL; diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 5f91a38..300ab01 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -70,8 +70,12 @@ static pte_t __ref *vmem_pte_alloc(void) pte = alloc_bootmem(PTRS_PER_PTE * sizeof(pte_t)); if (!pte) return NULL; - clear_table((unsigned long *) pte, _PAGE_TYPE_EMPTY, - PTRS_PER_PTE * sizeof(pte_t)); + if (MACHINE_HAS_HPAGE) + clear_table((unsigned long *) pte, _PAGE_TYPE_EMPTY | _PAGE_CO, + PTRS_PER_PTE * sizeof(pte_t)); + else + clear_table((unsigned long *) pte, _PAGE_TYPE_EMPTY, + PTRS_PER_PTE * sizeof(pte_t)); return pte; } @@ -112,7 +116,8 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro) if (MACHINE_HAS_HPAGE && !(address & ~HPAGE_MASK) && (address + HPAGE_SIZE <= start + size) && (address >= HPAGE_SIZE)) { - pte_val(pte) |= _SEGMENT_ENTRY_LARGE; + pte_val(pte) |= _SEGMENT_ENTRY_LARGE | + _SEGMENT_ENTRY_CO; pmd_val(*pm_dir) = pte_val(pte); address += HPAGE_SIZE - PAGE_SIZE; continue; |
