diff options
Diffstat (limited to 'arch/s390')
138 files changed, 4451 insertions, 1575 deletions
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index dcb667c4375..16c673096a2 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -82,12 +82,51 @@ config S390 select USE_GENERIC_SMP_HELPERS if SMP select HAVE_SYSCALL_WRAPPERS select HAVE_FUNCTION_TRACER + select HAVE_FUNCTION_TRACE_MCOUNT_TEST + select HAVE_FTRACE_MCOUNT_RECORD + select HAVE_SYSCALL_TRACEPOINTS + select HAVE_DYNAMIC_FTRACE + select HAVE_FUNCTION_GRAPH_TRACER + select HAVE_DEFAULT_NO_SPIN_MUTEXES select HAVE_OPROFILE select HAVE_KPROBES select HAVE_KRETPROBES select HAVE_KVM if 64BIT 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 + default y source "init/Kconfig" @@ -109,6 +148,9 @@ config 32BIT bool default y if !64BIT +config KTIME_SCALAR + def_bool 32BIT + config SMP bool "Symmetric multi-processing support" ---help--- @@ -342,6 +384,9 @@ config ARCH_ENABLE_MEMORY_HOTPLUG config ARCH_ENABLE_MEMORY_HOTREMOVE def_bool y +config ARCH_HIBERNATION_POSSIBLE + def_bool y if 64BIT + source "mm/Kconfig" comment "I/O subsystem configuration" @@ -463,13 +508,6 @@ config CMM_IUCV Select this option to enable the special message interface to the cooperative memory management. -config PAGE_STATES - bool "Unused page notification" - help - This enables the notification of unused pages to the - hypervisor. The ESSA instruction is used to do the states - changes between a page that has content and the unused state. - config APPLDATA_BASE bool "Linux - VM Monitor Stream, base infrastructure" depends on PROC_FS @@ -566,6 +604,30 @@ bool "s390 guest support for KVM (EXPERIMENTAL)" the KVM hypervisor. This will add detection for KVM as well as a virtio transport. If KVM is detected, the virtio console will be the default console. + +config SECCOMP + bool "Enable seccomp to safely compute untrusted bytecode" + depends on PROC_FS + default y + help + This kernel feature is useful for number crunching applications + that may need to compute untrusted bytecode during their + execution. By using pipes or other transports made available to + the process as file descriptors supporting the read/write + syscalls, it's possible to isolate those applications in + their own address space using seccomp. Once seccomp is + enabled via /proc/<pid>/seccomp, it cannot be disabled + and the task is only allowed to execute a few safe syscalls + defined by each seccomp mode. + + If unsure, say Y. + +endmenu + +menu "Power Management" + +source "kernel/power/Kconfig" + endmenu source "net/Kconfig" diff --git a/arch/s390/Kconfig.debug b/arch/s390/Kconfig.debug index 7e297a3cde3..2283933a9a9 100644 --- a/arch/s390/Kconfig.debug +++ b/arch/s390/Kconfig.debug @@ -6,13 +6,4 @@ config TRACE_IRQFLAGS_SUPPORT source "lib/Kconfig.debug" -config DEBUG_PAGEALLOC - bool "Debug page memory allocations" - depends on DEBUG_KERNEL - depends on ARCH_SUPPORTS_DEBUG_PAGEALLOC - help - Unmap pages from the kernel linear mapping after free_pages(). - This results in a slowdown, but helps to find certain types of - memory corruptions. - endmenu diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 578c61f15a4..fc8fb20e7fc 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -89,6 +89,7 @@ head-y := arch/s390/kernel/head.o arch/s390/kernel/init_task.o core-y += arch/s390/mm/ arch/s390/kernel/ arch/s390/crypto/ \ arch/s390/appldata/ arch/s390/hypfs/ arch/s390/kvm/ + libs-y += arch/s390/lib/ drivers-y += drivers/s390/ drivers-$(CONFIG_MATHEMU) += arch/s390/math-emu/ diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c index 27b70d8a359..495589950dc 100644 --- a/arch/s390/appldata/appldata_base.c +++ b/arch/s390/appldata/appldata_base.c @@ -5,7 +5,7 @@ * Exports appldata_register_ops() and appldata_unregister_ops() for the * data gathering modules. * - * Copyright IBM Corp. 2003, 2008 + * Copyright IBM Corp. 2003, 2009 * * Author: Gerald Schaefer <gerald.schaefer@de.ibm.com> */ @@ -26,6 +26,8 @@ #include <linux/notifier.h> #include <linux/cpu.h> #include <linux/workqueue.h> +#include <linux/suspend.h> +#include <linux/platform_device.h> #include <asm/appldata.h> #include <asm/timer.h> #include <asm/uaccess.h> @@ -41,14 +43,16 @@ #define TOD_MICRO 0x01000 /* nr. of TOD clock units for 1 microsecond */ + +static struct platform_device *appldata_pdev; + /* * /proc entries (sysctl) */ static const char appldata_proc_name[APPLDATA_PROC_NAME_LENGTH] = "appldata"; -static int appldata_timer_handler(ctl_table *ctl, int write, struct file *filp, +static int appldata_timer_handler(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos); static int appldata_interval_handler(ctl_table *ctl, int write, - struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos); @@ -57,12 +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, }, { }, }; @@ -86,6 +90,7 @@ static atomic_t appldata_expire_count = ATOMIC_INIT(0); static DEFINE_SPINLOCK(appldata_timer_lock); static int appldata_interval = APPLDATA_CPU_INTERVAL; static int appldata_timer_active; +static int appldata_timer_suspended = 0; /* * Work queue @@ -98,7 +103,7 @@ static DECLARE_WORK(appldata_work, appldata_work_fn); /* * Ops list */ -static DEFINE_SPINLOCK(appldata_ops_lock); +static DEFINE_MUTEX(appldata_ops_mutex); static LIST_HEAD(appldata_ops_list); @@ -129,14 +134,14 @@ static void appldata_work_fn(struct work_struct *work) i = 0; get_online_cpus(); - spin_lock(&appldata_ops_lock); + mutex_lock(&appldata_ops_mutex); list_for_each(lh, &appldata_ops_list) { ops = list_entry(lh, struct appldata_ops, list); if (ops->active == 1) { ops->callback(ops->data); } } - spin_unlock(&appldata_ops_lock); + mutex_unlock(&appldata_ops_mutex); put_online_cpus(); } @@ -176,7 +181,7 @@ static void __appldata_mod_vtimer_wrap(void *p) { struct vtimer_list *timer; u64 expires; } *args = p; - mod_virt_timer(args->timer, args->expires); + mod_virt_timer_periodic(args->timer, args->expires); } #define APPLDATA_ADD_TIMER 0 @@ -241,7 +246,7 @@ __appldata_vtimer_setup(int cmd) * Start/Stop timer, show status of timer (0 = not active, 1 = active) */ static int -appldata_timer_handler(ctl_table *ctl, int write, struct file *filp, +appldata_timer_handler(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int len; @@ -283,7 +288,7 @@ out: * current timer interval. */ static int -appldata_interval_handler(ctl_table *ctl, int write, struct file *filp, +appldata_interval_handler(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int len, interval; @@ -329,7 +334,7 @@ out: * monitoring (0 = not in process, 1 = in process) */ static int -appldata_generic_handler(ctl_table *ctl, int write, struct file *filp, +appldata_generic_handler(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct appldata_ops *ops = NULL, *tmp_ops; @@ -338,7 +343,7 @@ appldata_generic_handler(ctl_table *ctl, int write, struct file *filp, struct list_head *lh; found = 0; - spin_lock(&appldata_ops_lock); + mutex_lock(&appldata_ops_mutex); list_for_each(lh, &appldata_ops_list) { tmp_ops = list_entry(lh, struct appldata_ops, list); if (&tmp_ops->ctl_table[2] == ctl) { @@ -346,15 +351,15 @@ appldata_generic_handler(ctl_table *ctl, int write, struct file *filp, } } if (!found) { - spin_unlock(&appldata_ops_lock); + mutex_unlock(&appldata_ops_mutex); return -ENODEV; } ops = ctl->data; if (!try_module_get(ops->owner)) { // protect this function - spin_unlock(&appldata_ops_lock); + mutex_unlock(&appldata_ops_mutex); return -ENODEV; } - spin_unlock(&appldata_ops_lock); + mutex_unlock(&appldata_ops_mutex); if (!*lenp || *ppos) { *lenp = 0; @@ -378,11 +383,11 @@ appldata_generic_handler(ctl_table *ctl, int write, struct file *filp, return -EFAULT; } - spin_lock(&appldata_ops_lock); + mutex_lock(&appldata_ops_mutex); if ((buf[0] == '1') && (ops->active == 0)) { // protect work queue callback if (!try_module_get(ops->owner)) { - spin_unlock(&appldata_ops_lock); + mutex_unlock(&appldata_ops_mutex); module_put(ops->owner); return -ENODEV; } @@ -407,7 +412,7 @@ appldata_generic_handler(ctl_table *ctl, int write, struct file *filp, "failed with rc=%d\n", ops->name, rc); module_put(ops->owner); } - spin_unlock(&appldata_ops_lock); + mutex_unlock(&appldata_ops_mutex); out: *lenp = len; *ppos += len; @@ -433,9 +438,9 @@ int appldata_register_ops(struct appldata_ops *ops) if (!ops->ctl_table) return -ENOMEM; - spin_lock(&appldata_ops_lock); + mutex_lock(&appldata_ops_mutex); list_add(&ops->list, &appldata_ops_list); - spin_unlock(&appldata_ops_lock); + mutex_unlock(&appldata_ops_mutex); ops->ctl_table[0].procname = appldata_proc_name; ops->ctl_table[0].maxlen = 0; @@ -452,9 +457,9 @@ int appldata_register_ops(struct appldata_ops *ops) goto out; return 0; out: - spin_lock(&appldata_ops_lock); + mutex_lock(&appldata_ops_mutex); list_del(&ops->list); - spin_unlock(&appldata_ops_lock); + mutex_unlock(&appldata_ops_mutex); kfree(ops->ctl_table); return -ENOMEM; } @@ -466,15 +471,102 @@ out: */ void appldata_unregister_ops(struct appldata_ops *ops) { - spin_lock(&appldata_ops_lock); + mutex_lock(&appldata_ops_mutex); list_del(&ops->list); - spin_unlock(&appldata_ops_lock); + mutex_unlock(&appldata_ops_mutex); unregister_sysctl_table(ops->sysctl_header); kfree(ops->ctl_table); } /********************** module-ops management <END> **************************/ +/**************************** suspend / resume *******************************/ +static int appldata_freeze(struct device *dev) +{ + struct appldata_ops *ops; + int rc; + struct list_head *lh; + + get_online_cpus(); + spin_lock(&appldata_timer_lock); + if (appldata_timer_active) { + __appldata_vtimer_setup(APPLDATA_DEL_TIMER); + appldata_timer_suspended = 1; + } + spin_unlock(&appldata_timer_lock); + put_online_cpus(); + + mutex_lock(&appldata_ops_mutex); + list_for_each(lh, &appldata_ops_list) { + ops = list_entry(lh, struct appldata_ops, list); + if (ops->active == 1) { + rc = appldata_diag(ops->record_nr, APPLDATA_STOP_REC, + (unsigned long) ops->data, ops->size, + ops->mod_lvl); + if (rc != 0) + pr_err("Stopping the data collection for %s " + "failed with rc=%d\n", ops->name, rc); + } + } + mutex_unlock(&appldata_ops_mutex); + return 0; +} + +static int appldata_restore(struct device *dev) +{ + struct appldata_ops *ops; + int rc; + struct list_head *lh; + + get_online_cpus(); + spin_lock(&appldata_timer_lock); + if (appldata_timer_suspended) { + __appldata_vtimer_setup(APPLDATA_ADD_TIMER); + appldata_timer_suspended = 0; + } + spin_unlock(&appldata_timer_lock); + put_online_cpus(); + + mutex_lock(&appldata_ops_mutex); + list_for_each(lh, &appldata_ops_list) { + ops = list_entry(lh, struct appldata_ops, list); + if (ops->active == 1) { + ops->callback(ops->data); // init record + rc = appldata_diag(ops->record_nr, + APPLDATA_START_INTERVAL_REC, + (unsigned long) ops->data, ops->size, + ops->mod_lvl); + if (rc != 0) { + pr_err("Starting the data collection for %s " + "failed with rc=%d\n", ops->name, rc); + } + } + } + mutex_unlock(&appldata_ops_mutex); + return 0; +} + +static int appldata_thaw(struct device *dev) +{ + return appldata_restore(dev); +} + +static struct dev_pm_ops appldata_pm_ops = { + .freeze = appldata_freeze, + .thaw = appldata_thaw, + .restore = appldata_restore, +}; + +static struct platform_driver appldata_pdrv = { + .driver = { + .name = "appldata", + .owner = THIS_MODULE, + .pm = &appldata_pm_ops, + }, +}; +/************************* suspend / resume <END> ****************************/ + + /******************************* init / exit *********************************/ static void __cpuinit appldata_online_cpu(int cpu) @@ -531,11 +623,23 @@ static struct notifier_block __cpuinitdata appldata_nb = { */ static int __init appldata_init(void) { - int i; + int i, rc; + rc = platform_driver_register(&appldata_pdrv); + if (rc) + return rc; + + appldata_pdev = platform_device_register_simple("appldata", -1, NULL, + 0); + if (IS_ERR(appldata_pdev)) { + rc = PTR_ERR(appldata_pdev); + goto out_driver; + } appldata_wq = create_singlethread_workqueue("appldata"); - if (!appldata_wq) - return -ENOMEM; + if (!appldata_wq) { + rc = -ENOMEM; + goto out_device; + } get_online_cpus(); for_each_online_cpu(i) @@ -547,6 +651,12 @@ static int __init appldata_init(void) appldata_sysctl_header = register_sysctl_table(appldata_dir_table); return 0; + +out_device: + platform_device_unregister(appldata_pdev); +out_driver: + platform_driver_unregister(&appldata_pdrv); + return rc; } __initcall(appldata_init); diff --git a/arch/s390/appldata/appldata_mem.c b/arch/s390/appldata/appldata_mem.c index 3ed56b7d1b2..4188cbe63a5 100644 --- a/arch/s390/appldata/appldata_mem.c +++ b/arch/s390/appldata/appldata_mem.c @@ -78,7 +78,7 @@ static void appldata_get_mem_data(void *data) { /* * don't put large structures on the stack, we are - * serialized through the appldata_ops_lock and can use static + * serialized through the appldata_ops_mutex and can use static */ static struct sysinfo val; unsigned long ev[NR_VM_EVENT_ITEMS]; diff --git a/arch/s390/appldata/appldata_net_sum.c b/arch/s390/appldata/appldata_net_sum.c index fa741f84c5b..4ce7fa95880 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/boot/install.sh b/arch/s390/boot/install.sh index d4026f62cb0..aed3069699b 100644 --- a/arch/s390/boot/install.sh +++ b/arch/s390/boot/install.sh @@ -21,8 +21,8 @@ # User may have a custom install script -if [ -x ~/bin/${CROSS_COMPILE}installkernel ]; then exec ~/bin/${CROSS_COMPILE}installkernel "$@"; fi -if [ -x /sbin/${CROSS_COMPILE}installkernel ]; then exec /sbin/${CROSS_COMPILE}installkernel "$@"; fi +if [ -x ~/bin/${INSTALLKERNEL} ]; then exec ~/bin/${INSTALLKERNEL} "$@"; fi +if [ -x /sbin/${INSTALLKERNEL} ]; then exec /sbin/${INSTALLKERNEL} "$@"; fi # Default install - same as make zlilo diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c index 4aba83b3159..2bc479ab3a6 100644 --- a/arch/s390/crypto/des_s390.c +++ b/arch/s390/crypto/des_s390.c @@ -250,8 +250,9 @@ static int des3_128_setkey(struct crypto_tfm *tfm, const u8 *key, const u8 *temp_key = key; u32 *flags = &tfm->crt_flags; - if (!(memcmp(key, &key[DES_KEY_SIZE], DES_KEY_SIZE))) { - *flags |= CRYPTO_TFM_RES_BAD_KEY_SCHED; + if (!(memcmp(key, &key[DES_KEY_SIZE], DES_KEY_SIZE)) && + (*flags & CRYPTO_TFM_REQ_WEAK_KEY)) { + *flags |= CRYPTO_TFM_RES_WEAK_KEY; return -EINVAL; } for (i = 0; i < 2; i++, temp_key += DES_KEY_SIZE) { @@ -411,9 +412,9 @@ static int des3_192_setkey(struct crypto_tfm *tfm, const u8 *key, if (!(memcmp(key, &key[DES_KEY_SIZE], DES_KEY_SIZE) && memcmp(&key[DES_KEY_SIZE], &key[DES_KEY_SIZE * 2], - DES_KEY_SIZE))) { - - *flags |= CRYPTO_TFM_RES_BAD_KEY_SCHED; + DES_KEY_SIZE)) && + (*flags & CRYPTO_TFM_REQ_WEAK_KEY)) { + *flags |= CRYPTO_TFM_RES_WEAK_KEY; return -EINVAL; } for (i = 0; i < 3; i++, temp_key += DES_KEY_SIZE) { diff --git a/arch/s390/crypto/sha1_s390.c b/arch/s390/crypto/sha1_s390.c index e85ba348722..f6de7826c97 100644 --- a/arch/s390/crypto/sha1_s390.c +++ b/arch/s390/crypto/sha1_s390.c @@ -46,12 +46,38 @@ static int sha1_init(struct shash_desc *desc) return 0; } +static int sha1_export(struct shash_desc *desc, void *out) +{ + struct s390_sha_ctx *sctx = shash_desc_ctx(desc); + struct sha1_state *octx = out; + + octx->count = sctx->count; + memcpy(octx->state, sctx->state, sizeof(octx->state)); + memcpy(octx->buffer, sctx->buf, sizeof(octx->buffer)); + return 0; +} + +static int sha1_import(struct shash_desc *desc, const void *in) +{ + struct s390_sha_ctx *sctx = shash_desc_ctx(desc); + const struct sha1_state *ictx = in; + + sctx->count = ictx->count; + memcpy(sctx->state, ictx->state, sizeof(ictx->state)); + memcpy(sctx->buf, ictx->buffer, sizeof(ictx->buffer)); + sctx->func = KIMD_SHA_1; + return 0; +} + static struct shash_alg alg = { .digestsize = SHA1_DIGEST_SIZE, .init = sha1_init, .update = s390_sha_update, .final = s390_sha_final, + .export = sha1_export, + .import = sha1_import, .descsize = sizeof(struct s390_sha_ctx), + .statesize = sizeof(struct sha1_state), .base = { .cra_name = "sha1", .cra_driver_name= "sha1-s390", diff --git a/arch/s390/crypto/sha256_s390.c b/arch/s390/crypto/sha256_s390.c index f9fefc56963..61a7db37212 100644 --- a/arch/s390/crypto/sha256_s390.c +++ b/arch/s390/crypto/sha256_s390.c @@ -42,12 +42,38 @@ static int sha256_init(struct shash_desc *desc) return 0; } +static int sha256_export(struct shash_desc *desc, void *out) +{ + struct s390_sha_ctx *sctx = shash_desc_ctx(desc); + struct sha256_state *octx = out; + + octx->count = sctx->count; + memcpy(octx->state, sctx->state, sizeof(octx->state)); + memcpy(octx->buf, sctx->buf, sizeof(octx->buf)); + return 0; +} + +static int sha256_import(struct shash_desc *desc, const void *in) +{ + struct s390_sha_ctx *sctx = shash_desc_ctx(desc); + const struct sha256_state *ictx = in; + + sctx->count = ictx->count; + memcpy(sctx->state, ictx->state, sizeof(ictx->state)); + memcpy(sctx->buf, ictx->buf, sizeof(ictx->buf)); + sctx->func = KIMD_SHA_256; + return 0; +} + static struct shash_alg alg = { .digestsize = SHA256_DIGEST_SIZE, .init = sha256_init, .update = s390_sha_update, .final = s390_sha_final, + .export = sha256_export, + .import = sha256_import, .descsize = sizeof(struct s390_sha_ctx), + .statesize = sizeof(struct sha256_state), .base = { .cra_name = "sha256", .cra_driver_name= "sha256-s390", diff --git a/arch/s390/crypto/sha512_s390.c b/arch/s390/crypto/sha512_s390.c index 83192bfc804..4bf73d0dc52 100644 --- a/arch/s390/crypto/sha512_s390.c +++ b/arch/s390/crypto/sha512_s390.c @@ -13,7 +13,10 @@ * */ #include <crypto/internal/hash.h> +#include <crypto/sha.h> +#include <linux/errno.h> #include <linux/init.h> +#include <linux/kernel.h> #include <linux/module.h> #include "sha.h" @@ -37,12 +40,42 @@ static int sha512_init(struct shash_desc *desc) return 0; } +static int sha512_export(struct shash_desc *desc, void *out) +{ + struct s390_sha_ctx *sctx = shash_desc_ctx(desc); + struct sha512_state *octx = out; + + octx->count[0] = sctx->count; + octx->count[1] = 0; + memcpy(octx->state, sctx->state, sizeof(octx->state)); + memcpy(octx->buf, sctx->buf, sizeof(octx->buf)); + return 0; +} + +static int sha512_import(struct shash_desc *desc, const void *in) +{ + struct s390_sha_ctx *sctx = shash_desc_ctx(desc); + const struct sha512_state *ictx = in; + + if (unlikely(ictx->count[1])) + return -ERANGE; + sctx->count = ictx->count[0]; + + memcpy(sctx->state, ictx->state, sizeof(ictx->state)); + memcpy(sctx->buf, ictx->buf, sizeof(ictx->buf)); + sctx->func = KIMD_SHA_512; + return 0; +} + static struct shash_alg sha512_alg = { .digestsize = SHA512_DIGEST_SIZE, .init = sha512_init, .update = s390_sha_update, .final = s390_sha_final, + .export = sha512_export, + .import = sha512_import, .descsize = sizeof(struct s390_sha_ctx), + .statesize = sizeof(struct sha512_state), .base = { .cra_name = "sha512", .cra_driver_name= "sha512-s390", @@ -78,7 +111,10 @@ static struct shash_alg sha384_alg = { .init = sha384_init, .update = s390_sha_update, .final = s390_sha_final, + .export = sha512_export, + .import = sha512_import, .descsize = sizeof(struct s390_sha_ctx), + .statesize = sizeof(struct sha512_state), .base = { .cra_name = "sha384", .cra_driver_name= "sha384-s390", diff --git a/arch/s390/defconfig b/arch/s390/defconfig index 31e809c7779..ab4464486b7 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -1,7 +1,7 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.29-rc4 -# Wed Feb 11 10:07:16 2009 +# Linux kernel version: 2.6.31 +# Tue Sep 22 17:43:13 2009 # CONFIG_SCHED_MC=y CONFIG_MMU=y @@ -22,8 +22,11 @@ CONFIG_NO_DMA=y CONFIG_GENERIC_LOCKBREAK=y CONFIG_PGSTE=y CONFIG_VIRT_CPU_ACCOUNTING=y +CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC=y CONFIG_S390=y +CONFIG_SCHED_OMIT_FRAME_POINTER=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" +CONFIG_CONSTRUCTORS=y # # General setup @@ -37,6 +40,7 @@ CONFIG_SWAP=y CONFIG_SYSVIPC=y CONFIG_SYSVIPC_SYSCTL=y CONFIG_POSIX_MQUEUE=y +CONFIG_POSIX_MQUEUE_SYSCTL=y # CONFIG_BSD_PROCESS_ACCT is not set # CONFIG_TASKSTATS is not set CONFIG_AUDIT=y @@ -45,11 +49,12 @@ CONFIG_AUDIT=y # # RCU Subsystem # -CONFIG_CLASSIC_RCU=y -# CONFIG_TREE_RCU is not set -# CONFIG_PREEMPT_RCU is not set +CONFIG_TREE_RCU=y +# CONFIG_TREE_PREEMPT_RCU is not set +# CONFIG_RCU_TRACE is not set +CONFIG_RCU_FANOUT=64 +# CONFIG_RCU_FANOUT_EXACT is not set # CONFIG_TREE_RCU_TRACE is not set -# CONFIG_PREEMPT_RCU_TRACE is not set CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=17 @@ -77,8 +82,12 @@ CONFIG_IPC_NS=y # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y CONFIG_INITRAMFS_SOURCE="" +CONFIG_RD_GZIP=y +CONFIG_RD_BZIP2=y +CONFIG_RD_LZMA=y # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set CONFIG_SYSCTL=y +CONFIG_ANON_INODES=y # CONFIG_EMBEDDED is not set CONFIG_SYSCTL_SYSCALL=y CONFIG_KALLSYMS=y @@ -88,17 +97,24 @@ CONFIG_HOTPLUG=y CONFIG_PRINTK=y CONFIG_BUG=y CONFIG_ELF_CORE=y -# CONFIG_COMPAT_BRK is not set CONFIG_BASE_FULL=y CONFIG_FUTEX=y -CONFIG_ANON_INODES=y CONFIG_EPOLL=y CONFIG_SIGNALFD=y CONFIG_TIMERFD=y CONFIG_EVENTFD=y CONFIG_SHMEM=y CONFIG_AIO=y +CONFIG_HAVE_PERF_EVENTS=y + +# +# Kernel Performance Events And Counters +# +# 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 # CONFIG_SLOB is not set @@ -111,6 +127,13 @@ CONFIG_HAVE_KPROBES=y CONFIG_HAVE_KRETPROBES=y CONFIG_HAVE_ARCH_TRACEHOOK=y CONFIG_USE_GENERIC_SMP_HELPERS=y +CONFIG_HAVE_DEFAULT_NO_SPIN_MUTEXES=y + +# +# GCOV-based kernel profiling +# +# CONFIG_GCOV_KERNEL is not set +# CONFIG_SLOW_WORK is not set # CONFIG_HAVE_GENERIC_DMA_COHERENT is not set CONFIG_SLABINFO=y CONFIG_RT_MUTEXES=y @@ -124,7 +147,6 @@ CONFIG_MODVERSIONS=y CONFIG_INIT_ALL_POSSIBLE=y CONFIG_STOP_MACHINE=y CONFIG_BLOCK=y -# CONFIG_BLK_DEV_IO_TRACE is not set CONFIG_BLK_DEV_BSG=y # CONFIG_BLK_DEV_INTEGRITY is not set CONFIG_BLOCK_COMPAT=y @@ -142,7 +164,7 @@ CONFIG_DEFAULT_DEADLINE=y # CONFIG_DEFAULT_NOOP is not set CONFIG_DEFAULT_IOSCHED="deadline" CONFIG_PREEMPT_NOTIFIERS=y -# CONFIG_FREEZER is not set +CONFIG_FREEZER=y # # Base setup @@ -156,6 +178,7 @@ CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_GENERIC_CLOCKEVENTS_BUILD=y CONFIG_64BIT=y +# CONFIG_KTIME_SCALAR is not set CONFIG_SMP=y CONFIG_NR_CPUS=32 CONFIG_HOTPLUG_CPU=y @@ -191,6 +214,7 @@ CONFIG_ARCH_SPARSEMEM_DEFAULT=y CONFIG_ARCH_SELECT_MEMORY_MODEL=y CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y CONFIG_ARCH_ENABLE_MEMORY_HOTREMOVE=y +CONFIG_ARCH_HIBERNATION_POSSIBLE=y CONFIG_SELECT_MEMORY_MODEL=y # CONFIG_FLATMEM_MANUAL is not set # CONFIG_DISCONTIGMEM_MANUAL is not set @@ -210,12 +234,13 @@ CONFIG_PHYS_ADDR_T_64BIT=y CONFIG_ZONE_DMA_FLAG=1 CONFIG_BOUNCE=y CONFIG_VIRT_TO_BUS=y -CONFIG_UNEVICTABLE_LRU=y +CONFIG_HAVE_MLOCK=y +CONFIG_HAVE_MLOCKED_PAGE_BIT=y +CONFIG_DEFAULT_MMAP_MIN_ADDR=4096 # # I/O subsystem configuration # -CONFIG_MACHCHK_WARNING=y CONFIG_QDIO=y CONFIG_CHSC_SCH=m @@ -235,7 +260,6 @@ CONFIG_FORCE_MAX_ZONEORDER=9 CONFIG_PFAULT=y # CONFIG_SHARED_KERNEL is not set # CONFIG_CMM is not set -# CONFIG_PAGE_STATES is not set # CONFIG_APPLDATA_BASE is not set CONFIG_HZ_100=y # CONFIG_HZ_250 is not set @@ -247,12 +271,23 @@ CONFIG_S390_HYPFS_FS=y CONFIG_KEXEC=y # CONFIG_ZFCPDUMP is not set CONFIG_S390_GUEST=y +CONFIG_SECCOMP=y + +# +# Power Management +# +CONFIG_PM=y +# CONFIG_PM_DEBUG is not set +CONFIG_PM_SLEEP_SMP=y +CONFIG_PM_SLEEP=y +CONFIG_HIBERNATION=y +CONFIG_PM_STD_PARTITION="" +# CONFIG_PM_RUNTIME is not set CONFIG_NET=y # # Networking options # -CONFIG_COMPAT_NET_DEV_OPS=y CONFIG_PACKET=y # CONFIG_PACKET_MMAP is not set CONFIG_UNIX=y @@ -362,6 +397,7 @@ CONFIG_IP_SCTP=m # CONFIG_SCTP_HMAC_NONE is not set # CONFIG_SCTP_HMAC_SHA1 is not set CONFIG_SCTP_HMAC_MD5=y +# CONFIG_RDS is not set # CONFIG_TIPC is not set # CONFIG_ATM is not set # CONFIG_BRIDGE is not set @@ -374,6 +410,8 @@ CONFIG_SCTP_HMAC_MD5=y # CONFIG_LAPB is not set # CONFIG_ECONET is not set # CONFIG_WAN_ROUTER is not set +# CONFIG_PHONET is not set +# CONFIG_IEEE802154 is not set CONFIG_NET_SCHED=y # @@ -436,9 +474,9 @@ CONFIG_CAN_BCM=m # CAN Device Drivers # CONFIG_CAN_VCAN=m +# CONFIG_CAN_DEV is not set # CONFIG_CAN_DEBUG_DEVICES is not set # CONFIG_AF_RXRPC is not set -# CONFIG_PHONET is not set # CONFIG_WIMAX is not set # CONFIG_RFKILL is not set # CONFIG_NET_9P is not set @@ -453,6 +491,7 @@ CONFIG_CCW=y # Generic Driver Options # CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +# CONFIG_DEVTMPFS is not set CONFIG_STANDALONE=y CONFIG_PREVENT_FIRMWARE_BUILD=y CONFIG_FW_LOADER=y @@ -467,6 +506,7 @@ CONFIG_BLK_DEV=y CONFIG_BLK_DEV_LOOP=m # CONFIG_BLK_DEV_CRYPTOLOOP is not set CONFIG_BLK_DEV_NBD=m +# CONFIG_BLK_DEV_OSD is not set CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_COUNT=16 CONFIG_BLK_DEV_RAM_SIZE=4096 @@ -515,10 +555,6 @@ CONFIG_BLK_DEV_SR=y CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y # CONFIG_CHR_DEV_SCH is not set - -# -# Some SCSI devices (e.g. CD jukebox) support multiple LUNs -# CONFIG_SCSI_MULTI_LUN=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_LOGGING=y @@ -537,6 +573,7 @@ CONFIG_SCSI_FC_ATTRS=y CONFIG_SCSI_LOWLEVEL=y # CONFIG_ISCSI_TCP is not set # CONFIG_LIBFC is not set +# CONFIG_LIBFCOE is not set # CONFIG_SCSI_DEBUG is not set CONFIG_ZFCP=y CONFIG_SCSI_DH=m @@ -544,6 +581,10 @@ CONFIG_SCSI_DH_RDAC=m CONFIG_SCSI_DH_HP_SW=m CONFIG_SCSI_DH_EMC=m CONFIG_SCSI_DH_ALUA=m +CONFIG_SCSI_OSD_INITIATOR=m +CONFIG_SCSI_OSD_ULD=m +CONFIG_SCSI_OSD_DPRINT_SENSE=1 +# CONFIG_SCSI_OSD_DEBUG is not set CONFIG_MD=y CONFIG_BLK_DEV_MD=y CONFIG_MD_AUTODETECT=y @@ -559,8 +600,11 @@ CONFIG_BLK_DEV_DM=y CONFIG_DM_CRYPT=y CONFIG_DM_SNAPSHOT=y CONFIG_DM_MIRROR=y +# CONFIG_DM_LOG_USERSPACE is not set CONFIG_DM_ZERO=y CONFIG_DM_MULTIPATH=m +# CONFIG_DM_MULTIPATH_QL is not set +# CONFIG_DM_MULTIPATH_ST is not set # CONFIG_DM_DELAY is not set # CONFIG_DM_UEVENT is not set CONFIG_NETDEVICES=y @@ -642,6 +686,7 @@ CONFIG_SCLP_CONSOLE=y CONFIG_SCLP_VT220_TTY=y CONFIG_SCLP_VT220_CONSOLE=y CONFIG_SCLP_CPI=m +CONFIG_SCLP_ASYNC=m CONFIG_S390_TAPE=m # @@ -659,6 +704,11 @@ CONFIG_S390_TAPE_34XX=m # CONFIG_MONREADER is not set CONFIG_MONWRITER=m CONFIG_S390_VMUR=m + +# +# PPS support +# +# CONFIG_PPS is not set # CONFIG_POWER_SUPPLY is not set # CONFIG_THERMAL is not set # CONFIG_THERMAL_HWMON is not set @@ -667,6 +717,11 @@ CONFIG_S390_VMUR=m # CONFIG_MEMSTICK is not set # CONFIG_NEW_LEDS is not set CONFIG_ACCESSIBILITY=y +# CONFIG_AUXDISPLAY is not set + +# +# TI VLYNQ +# # CONFIG_STAGING is not set # @@ -676,6 +731,7 @@ CONFIG_EXT2_FS=y # CONFIG_EXT2_FS_XATTR is not set # CONFIG_EXT2_FS_XIP is not set CONFIG_EXT3_FS=y +# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set CONFIG_EXT3_FS_XATTR=y # CONFIG_EXT3_FS_POSIX_ACL is not set # CONFIG_EXT3_FS_SECURITY is not set @@ -686,11 +742,13 @@ CONFIG_FS_MBCACHE=y # CONFIG_REISERFS_FS is not set # CONFIG_JFS_FS is not set CONFIG_FS_POSIX_ACL=y -CONFIG_FILE_LOCKING=y # CONFIG_XFS_FS is not set # CONFIG_GFS2_FS is not set # CONFIG_OCFS2_FS is not set # CONFIG_BTRFS_FS is not set +# CONFIG_NILFS2_FS is not set +CONFIG_FILE_LOCKING=y +CONFIG_FSNOTIFY=y CONFIG_DNOTIFY=y CONFIG_INOTIFY=y CONFIG_INOTIFY_USER=y @@ -701,6 +759,11 @@ CONFIG_INOTIFY_USER=y CONFIG_GENERIC_ACL=y # +# Caches +# +# CONFIG_FSCACHE is not set + +# # CD-ROM/DVD Filesystems # # CONFIG_ISO9660_FS is not set @@ -744,6 +807,7 @@ CONFIG_MISC_FILESYSTEMS=y # CONFIG_ROMFS_FS is not set # CONFIG_SYSV_FS is not set # CONFIG_UFS_FS is not set +# CONFIG_EXOFS_FS is not set CONFIG_NETWORK_FILESYSTEMS=y CONFIG_NFS_FS=y CONFIG_NFS_V3=y @@ -758,7 +822,6 @@ CONFIG_LOCKD_V4=y CONFIG_EXPORTFS=y CONFIG_NFS_COMMON=y CONFIG_SUNRPC=y -# CONFIG_SUNRPC_REGISTER_V4 is not set # CONFIG_RPCSEC_GSS_KRB5 is not set # CONFIG_RPCSEC_GSS_SPKM3 is not set # CONFIG_SMB_FS is not set @@ -806,6 +869,7 @@ CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_FS=y # CONFIG_HEADERS_CHECK is not set CONFIG_DEBUG_KERNEL=y +# CONFIG_DETECT_HUNG_TASK is not set # CONFIG_SCHED_DEBUG is not set # CONFIG_SCHEDSTATS is not set # CONFIG_TIMER_STATS is not set @@ -830,34 +894,45 @@ CONFIG_DEBUG_MEMORY_INIT=y # CONFIG_DEBUG_LIST is not set # CONFIG_DEBUG_SG is not set # CONFIG_DEBUG_NOTIFIERS is not set -# CONFIG_FRAME_POINTER is not set +# CONFIG_DEBUG_CREDENTIALS is not set # CONFIG_RCU_TORTURE_TEST is not set # CONFIG_RCU_CPU_STALL_DETECTOR is not set # CONFIG_KPROBES_SANITY_TEST is not set # CONFIG_BACKTRACE_SELF_TEST is not set # CONFIG_DEBUG_BLOCK_EXT_DEVT is not set +CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y # CONFIG_LKDTM is not set # CONFIG_FAULT_INJECTION is not set # CONFIG_LATENCYTOP is not set CONFIG_SYSCTL_SYSCALL_CHECK=y +# CONFIG_DEBUG_PAGEALLOC is not set CONFIG_HAVE_FUNCTION_TRACER=y - -# -# Tracers -# +CONFIG_HAVE_FUNCTION_GRAPH_TRACER=y +CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST=y +CONFIG_HAVE_DYNAMIC_FTRACE=y +CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y +CONFIG_HAVE_SYSCALL_TRACEPOINTS=y +CONFIG_TRACING_SUPPORT=y +CONFIG_FTRACE=y # CONFIG_FUNCTION_TRACER is not set # CONFIG_IRQSOFF_TRACER is not set # CONFIG_PREEMPT_TRACER is not set # CONFIG_SCHED_TRACER is not set -# CONFIG_CONTEXT_SWITCH_TRACER is not set +# CONFIG_ENABLE_DEFAULT_TRACERS is not set +# CONFIG_FTRACE_SYSCALLS is not set # CONFIG_BOOT_TRACER is not set -# CONFIG_TRACE_BRANCH_PROFILING is not set +CONFIG_BRANCH_PROFILE_NONE=y +# CONFIG_PROFILE_ANNOTATED_BRANCHES is not set +# CONFIG_PROFILE_ALL_BRANCHES is not set # CONFIG_STACK_TRACER is not set -# CONFIG_DYNAMIC_PRINTK_DEBUG is not set +# CONFIG_KMEMTRACE is not set +# CONFIG_WORKQUEUE_TRACER is not set +# CONFIG_BLK_DEV_IO_TRACE is not set +# CONFIG_DYNAMIC_DEBUG is not set CONFIG_SAMPLES=y # CONFIG_SAMPLE_KOBJECT is not set # CONFIG_SAMPLE_KPROBES is not set -# CONFIG_DEBUG_PAGEALLOC is not set +# CONFIG_KMEMCHECK is not set # # Security options @@ -882,10 +957,12 @@ CONFIG_CRYPTO_HASH=m CONFIG_CRYPTO_HASH2=y CONFIG_CRYPTO_RNG=m CONFIG_CRYPTO_RNG2=y +CONFIG_CRYPTO_PCOMP=y CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_MANAGER2=y CONFIG_CRYPTO_GF128MUL=m # CONFIG_CRYPTO_NULL is not set +CONFIG_CRYPTO_WORKQUEUE=y # CONFIG_CRYPTO_CRYPTD is not set CONFIG_CRYPTO_AUTHENC=m # CONFIG_CRYPTO_TEST is not set @@ -913,11 +990,13 @@ CONFIG_CRYPTO_PCBC=m # CONFIG_CRYPTO_HMAC=m # CONFIG_CRYPTO_XCBC is not set +CONFIG_CRYPTO_VMAC=m # # Digest # CONFIG_CRYPTO_CRC32C=m +CONFIG_CRYPTO_GHASH=m # CONFIG_CRYPTO_MD4 is not set CONFIG_CRYPTO_MD5=m # CONFIG_CRYPTO_MICHAEL_MIC is not set @@ -954,6 +1033,7 @@ CONFIG_CRYPTO_SEED=m # Compression # # CONFIG_CRYPTO_DEFLATE is not set +CONFIG_CRYPTO_ZLIB=m CONFIG_CRYPTO_LZO=m # @@ -969,6 +1049,7 @@ CONFIG_CRYPTO_SHA512_S390=m # CONFIG_CRYPTO_DES_S390 is not set # CONFIG_CRYPTO_AES_S390 is not set CONFIG_S390_PRNG=m +# CONFIG_BINARY_PRINTF is not set # # Library routines @@ -982,9 +1063,14 @@ CONFIG_CRC_T10DIF=y CONFIG_CRC32=m CONFIG_CRC7=m CONFIG_LIBCRC32C=m +CONFIG_ZLIB_INFLATE=y +CONFIG_ZLIB_DEFLATE=m CONFIG_LZO_COMPRESS=m CONFIG_LZO_DECOMPRESS=m -CONFIG_PLIST=y +CONFIG_DECOMPRESS_GZIP=y +CONFIG_DECOMPRESS_BZIP2=y +CONFIG_DECOMPRESS_LZMA=y +CONFIG_NLATTR=y CONFIG_HAVE_KVM=y CONFIG_VIRTUALIZATION=y CONFIG_KVM=m diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c index 704dd396257..77df726180b 100644 --- a/arch/s390/hypfs/hypfs_diag.c +++ b/arch/s390/hypfs/hypfs_diag.c @@ -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; } diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index 5a805df216b..341aff2687a 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -41,7 +41,7 @@ struct hypfs_sb_info { static const struct file_operations hypfs_file_ops; static struct file_system_type hypfs_type; -static struct super_operations hypfs_s_ops; +static const struct super_operations hypfs_s_ops; /* start of list of all dentries, which have to be deleted on update */ static struct dentry *hypfs_last_dentry; @@ -355,11 +355,7 @@ static struct dentry *hypfs_create_file(struct super_block *sb, { struct dentry *dentry; struct inode *inode; - struct qstr qname; - qname.name = name; - qname.len = strlen(name); - qname.hash = full_name_hash(name, qname.len); mutex_lock(&parent->d_inode->i_mutex); dentry = lookup_one_len(name, parent, strlen(name)); if (IS_ERR(dentry)) { @@ -426,7 +422,7 @@ struct dentry *hypfs_create_u64(struct super_block *sb, struct dentry *dir, char tmp[TMP_SIZE]; struct dentry *dentry; - snprintf(tmp, TMP_SIZE, "%lld\n", (unsigned long long int)value); + snprintf(tmp, TMP_SIZE, "%llu\n", (unsigned long long int)value); buffer = kstrdup(tmp, GFP_KERNEL); if (!buffer) return ERR_PTR(-ENOMEM); @@ -476,7 +472,7 @@ static struct file_system_type hypfs_type = { .kill_sb = hypfs_kill_super }; -static struct super_operations hypfs_s_ops = { +static const struct super_operations hypfs_s_ops = { .statfs = simple_statfs, .drop_inode = hypfs_drop_inode, .show_options = hypfs_show_options, @@ -500,7 +496,7 @@ static int __init hypfs_init(void) } s390_kobj = kobject_create_and_add("s390", hypervisor_kobj); if (!s390_kobj) { - rc = -ENOMEM;; + rc = -ENOMEM; goto fail_sysfs; } rc = register_filesystem(&hypfs_type); diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h index de432f2de2d..ae7c8f9f94a 100644 --- a/arch/s390/include/asm/atomic.h +++ b/arch/s390/include/asm/atomic.h @@ -1,33 +1,23 @@ #ifndef __ARCH_S390_ATOMIC__ #define __ARCH_S390_ATOMIC__ -#include <linux/compiler.h> -#include <linux/types.h> - /* - * include/asm-s390/atomic.h + * Copyright 1999,2009 IBM Corp. + * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>, + * Denis Joseph Barrow, + * Arnd Bergmann <arndb@de.ibm.com>, * - * S390 version - * Copyright (C) 1999-2005 IBM Deutschland Entwicklung GmbH, IBM Corporation - * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), - * Denis Joseph Barrow, - * Arnd Bergmann (arndb@de.ibm.com) - * - * Derived from "include/asm-i386/bitops.h" - * Copyright (C) 1992, Linus Torvalds + * Atomic operations that C can't guarantee us. + * Useful for resource counting etc. + * s390 uses 'Compare And Swap' for atomicity in SMP enviroment. * */ -/* - * Atomic operations that C can't guarantee us. Useful for - * resource counting etc.. - * S390 uses 'Compare And Swap' for atomicity in SMP enviroment - */ +#include <linux/compiler.h> +#include <linux/types.h> #define ATOMIC_INIT(i) { (i) } -#ifdef __KERNEL__ - #if __GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ > 2) #define __CS_LOOP(ptr, op_val, op_string) ({ \ @@ -77,7 +67,7 @@ static inline void atomic_set(atomic_t *v, int i) barrier(); } -static __inline__ int atomic_add_return(int i, atomic_t * v) +static inline int atomic_add_return(int i, atomic_t *v) { return __CS_LOOP(v, i, "ar"); } @@ -87,7 +77,7 @@ static __inline__ int atomic_add_return(int i, atomic_t * v) #define atomic_inc_return(_v) atomic_add_return(1, _v) #define atomic_inc_and_test(_v) (atomic_add_return(1, _v) == 0) -static __inline__ int atomic_sub_return(int i, atomic_t * v) +static inline int atomic_sub_return(int i, atomic_t *v) { return __CS_LOOP(v, i, "sr"); } @@ -97,19 +87,19 @@ static __inline__ int atomic_sub_return(int i, atomic_t * v) #define atomic_dec_return(_v) atomic_sub_return(1, _v) #define atomic_dec_and_test(_v) (atomic_sub_return(1, _v) == 0) -static __inline__ void atomic_clear_mask(unsigned long mask, atomic_t * v) +static inline void atomic_clear_mask(unsigned long mask, atomic_t *v) { - __CS_LOOP(v, ~mask, "nr"); + __CS_LOOP(v, ~mask, "nr"); } -static __inline__ void atomic_set_mask(unsigned long mask, atomic_t * v) +static inline void atomic_set_mask(unsigned long mask, atomic_t *v) { - __CS_LOOP(v, mask, "or"); + __CS_LOOP(v, mask, "or"); } #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) -static __inline__ int atomic_cmpxchg(atomic_t *v, int old, int new) +static inline int atomic_cmpxchg(atomic_t *v, int old, int new) { #if __GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ > 2) asm volatile( @@ -127,7 +117,7 @@ static __inline__ int atomic_cmpxchg(atomic_t *v, int old, int new) return old; } -static __inline__ int atomic_add_unless(atomic_t *v, int a, int u) +static inline int atomic_add_unless(atomic_t *v, int a, int u) { int c, old; c = atomic_read(v); @@ -146,9 +136,10 @@ static __inline__ int atomic_add_unless(atomic_t *v, int a, int u) #undef __CS_LOOP -#ifdef __s390x__ #define ATOMIC64_INIT(i) { (i) } +#ifdef CONFIG_64BIT + #if __GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ > 2) #define __CSG_LOOP(ptr, op_val, op_string) ({ \ @@ -162,7 +153,7 @@ static __inline__ int atomic_add_unless(atomic_t *v, int a, int u) : "=&d" (old_val), "=&d" (new_val), \ "=Q" (((atomic_t *)(ptr))->counter) \ : "d" (op_val), "Q" (((atomic_t *)(ptr))->counter) \ - : "cc", "memory" ); \ + : "cc", "memory"); \ new_val; \ }) @@ -180,7 +171,7 @@ static __inline__ int atomic_add_unless(atomic_t *v, int a, int u) "=m" (((atomic_t *)(ptr))->counter) \ : "a" (ptr), "d" (op_val), \ "m" (((atomic_t *)(ptr))->counter) \ - : "cc", "memory" ); \ + : "cc", "memory"); \ new_val; \ }) @@ -198,39 +189,29 @@ static inline void atomic64_set(atomic64_t *v, long long i) barrier(); } -static __inline__ long long atomic64_add_return(long long i, atomic64_t * v) +static inline long long atomic64_add_return(long long i, atomic64_t *v) { return __CSG_LOOP(v, i, "agr"); } -#define atomic64_add(_i, _v) atomic64_add_return(_i, _v) -#define atomic64_add_negative(_i, _v) (atomic64_add_return(_i, _v) < 0) -#define atomic64_inc(_v) atomic64_add_return(1, _v) -#define atomic64_inc_return(_v) atomic64_add_return(1, _v) -#define atomic64_inc_and_test(_v) (atomic64_add_return(1, _v) == 0) -static __inline__ long long atomic64_sub_return(long long i, atomic64_t * v) +static inline long long atomic64_sub_return(long long i, atomic64_t *v) { return __CSG_LOOP(v, i, "sgr"); } -#define atomic64_sub(_i, _v) atomic64_sub_return(_i, _v) -#define atomic64_sub_and_test(_i, _v) (atomic64_sub_return(_i, _v) == 0) -#define atomic64_dec(_v) atomic64_sub_return(1, _v) -#define atomic64_dec_return(_v) atomic64_sub_return(1, _v) -#define atomic64_dec_and_test(_v) (atomic64_sub_return(1, _v) == 0) -static __inline__ void atomic64_clear_mask(unsigned long mask, atomic64_t * v) +static inline void atomic64_clear_mask(unsigned long mask, atomic64_t *v) { - __CSG_LOOP(v, ~mask, "ngr"); + __CSG_LOOP(v, ~mask, "ngr"); } -static __inline__ void atomic64_set_mask(unsigned long mask, atomic64_t * v) +static inline void atomic64_set_mask(unsigned long mask, atomic64_t *v) { - __CSG_LOOP(v, mask, "ogr"); + __CSG_LOOP(v, mask, "ogr"); } #define atomic64_xchg(v, new) (xchg(&((v)->counter), new)) -static __inline__ long long atomic64_cmpxchg(atomic64_t *v, +static inline long long atomic64_cmpxchg(atomic64_t *v, long long old, long long new) { #if __GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ > 2) @@ -249,8 +230,112 @@ static __inline__ long long atomic64_cmpxchg(atomic64_t *v, return old; } -static __inline__ int atomic64_add_unless(atomic64_t *v, - long long a, long long u) +#undef __CSG_LOOP + +#else /* CONFIG_64BIT */ + +typedef struct { + long long counter; +} atomic64_t; + +static inline long long atomic64_read(const atomic64_t *v) +{ + register_pair rp; + + asm volatile( + " lm %0,%N0,0(%1)" + : "=&d" (rp) + : "a" (&v->counter), "m" (v->counter) + ); + return rp.pair; +} + +static inline void atomic64_set(atomic64_t *v, long long i) +{ + register_pair rp = {.pair = i}; + + asm volatile( + " stm %1,%N1,0(%2)" + : "=m" (v->counter) + : "d" (rp), "a" (&v->counter) + ); +} + +static inline long long atomic64_xchg(atomic64_t *v, long long new) +{ + register_pair rp_new = {.pair = new}; + register_pair rp_old; + + asm volatile( + " lm %0,%N0,0(%2)\n" + "0: cds %0,%3,0(%2)\n" + " jl 0b\n" + : "=&d" (rp_old), "+m" (v->counter) + : "a" (&v->counter), "d" (rp_new) + : "cc"); + return rp_old.pair; +} + +static inline long long atomic64_cmpxchg(atomic64_t *v, + long long old, long long new) +{ + register_pair rp_old = {.pair = old}; + register_pair rp_new = {.pair = new}; + + asm volatile( + " cds %0,%3,0(%2)" + : "+&d" (rp_old), "+m" (v->counter) + : "a" (&v->counter), "d" (rp_new) + : "cc"); + return rp_old.pair; +} + + +static inline long long atomic64_add_return(long long i, atomic64_t *v) +{ + long long old, new; + + do { + old = atomic64_read(v); + new = old + i; + } while (atomic64_cmpxchg(v, old, new) != old); + return new; +} + +static inline long long atomic64_sub_return(long long i, atomic64_t *v) +{ + long long old, new; + + do { + old = atomic64_read(v); + new = old - i; + } while (atomic64_cmpxchg(v, old, new) != old); + return new; +} + +static inline void atomic64_set_mask(unsigned long long mask, atomic64_t *v) +{ + long long old, new; + + do { + old = atomic64_read(v); + new = old | mask; + } while (atomic64_cmpxchg(v, old, new) != old); +} + +static inline void atomic64_clear_mask(unsigned long long mask, atomic64_t *v) +{ + long long old, new; + + do { + old = atomic64_read(v); + new = old & mask; + } while (atomic64_cmpxchg(v, old, new) != old); +} + +#endif /* CONFIG_64BIT */ + +static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u) { long long c, old; c = atomic64_read(v); @@ -265,16 +350,23 @@ static __inline__ int atomic64_add_unless(atomic64_t *v, return c != u; } -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) - -#undef __CSG_LOOP -#endif +#define atomic64_add(_i, _v) atomic64_add_return(_i, _v) +#define atomic64_add_negative(_i, _v) (atomic64_add_return(_i, _v) < 0) +#define atomic64_inc(_v) atomic64_add_return(1, _v) +#define atomic64_inc_return(_v) atomic64_add_return(1, _v) +#define atomic64_inc_and_test(_v) (atomic64_add_return(1, _v) == 0) +#define atomic64_sub(_i, _v) atomic64_sub_return(_i, _v) +#define atomic64_sub_and_test(_i, _v) (atomic64_sub_return(_i, _v) == 0) +#define atomic64_dec(_v) atomic64_sub_return(1, _v) +#define atomic64_dec_return(_v) atomic64_sub_return(1, _v) +#define atomic64_dec_and_test(_v) (atomic64_sub_return(1, _v) == 0) +#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) #define smp_mb__before_atomic_dec() smp_mb() #define smp_mb__after_atomic_dec() smp_mb() #define smp_mb__before_atomic_inc() smp_mb() #define smp_mb__after_atomic_inc() smp_mb() -#include <asm-generic/atomic.h> -#endif /* __KERNEL__ */ +#include <asm-generic/atomic-long.h> + #endif /* __ARCH_S390_ATOMIC__ */ diff --git a/arch/s390/include/asm/bitsperlong.h b/arch/s390/include/asm/bitsperlong.h new file mode 100644 index 00000000000..6b235aea9c6 --- /dev/null +++ b/arch/s390/include/asm/bitsperlong.h @@ -0,0 +1,13 @@ +#ifndef __ASM_S390_BITSPERLONG_H +#define __ASM_S390_BITSPERLONG_H + +#ifndef __s390x__ +#define __BITS_PER_LONG 32 +#else +#define __BITS_PER_LONG 64 +#endif + +#include <asm-generic/bitsperlong.h> + +#endif /* __ASM_S390_BITSPERLONG_H */ + diff --git a/arch/s390/include/asm/bug.h b/arch/s390/include/asm/bug.h index 7efd0abe888..efb74fd5156 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 49d5af916d0..405cc97c624 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 ba007d8df94..2a541955117 100644 --- a/arch/s390/include/asm/ccwdev.h +++ b/arch/s390/include/asm/ccwdev.h @@ -1,11 +1,9 @@ /* - * include/asm-s390/ccwdev.h - * include/asm-s390x/ccwdev.h + * Copyright IBM Corp. 2002, 2009 * - * Copyright (C) 2002 IBM Deutschland Entwicklung GmbH, IBM Corporation - * Author(s): Arnd Bergmann <arndb@de.ibm.com> + * Author(s): Arnd Bergmann <arndb@de.ibm.com> * - * Interface for CCW device drivers + * Interface for CCW device drivers */ #ifndef _S390_CCWDEV_H_ #define _S390_CCWDEV_H_ @@ -104,6 +102,11 @@ struct ccw_device { * @set_offline: called when setting device offline * @notify: notify driver of device state changes * @shutdown: called at device shutdown + * @prepare: prepare for pm state transition + * @complete: undo work done in @prepare + * @freeze: callback for freezing during hibernation snapshotting + * @thaw: undo work done in @freeze + * @restore: callback for restoring after hibernation * @driver: embedded device driver structure * @name: device driver name */ @@ -116,6 +119,11 @@ struct ccw_driver { int (*set_offline) (struct ccw_device *); int (*notify) (struct ccw_device *, int); void (*shutdown) (struct ccw_device *); + int (*prepare) (struct ccw_device *); + void (*complete) (struct ccw_device *); + int (*freeze)(struct ccw_device *); + int (*thaw) (struct ccw_device *); + int (*restore)(struct ccw_device *); struct device_driver driver; char *name; }; @@ -184,6 +192,7 @@ extern void ccw_device_get_id(struct ccw_device *, struct ccw_dev_id *); #define to_ccwdrv(n) container_of(n, struct ccw_driver, driver) extern struct ccw_device *ccw_device_probe_console(void); +extern int ccw_device_force_console(void); // FIXME: these have to go extern int _ccw_device_get_subchannel_number(struct ccw_device *); diff --git a/arch/s390/include/asm/ccwgroup.h b/arch/s390/include/asm/ccwgroup.h index a27f68985a7..c79c1e787b8 100644 --- a/arch/s390/include/asm/ccwgroup.h +++ b/arch/s390/include/asm/ccwgroup.h @@ -38,6 +38,11 @@ struct ccwgroup_device { * @set_online: function called when device is set online * @set_offline: function called when device is set offline * @shutdown: function called when device is shut down + * @prepare: prepare for pm state transition + * @complete: undo work done in @prepare + * @freeze: callback for freezing during hibernation snapshotting + * @thaw: undo work done in @freeze + * @restore: callback for restoring after hibernation * @driver: embedded driver structure */ struct ccwgroup_driver { @@ -51,6 +56,11 @@ struct ccwgroup_driver { int (*set_online) (struct ccwgroup_device *); int (*set_offline) (struct ccwgroup_device *); void (*shutdown)(struct ccwgroup_device *); + int (*prepare) (struct ccwgroup_device *); + void (*complete) (struct ccwgroup_device *); + int (*freeze)(struct ccwgroup_device *); + int (*thaw) (struct ccwgroup_device *); + int (*restore)(struct ccwgroup_device *); struct device_driver driver; }; diff --git a/arch/s390/include/asm/checksum.h b/arch/s390/include/asm/checksum.h index d5a8e7c1477..6c00f6800a3 100644 --- a/arch/s390/include/asm/checksum.h +++ b/arch/s390/include/asm/checksum.h @@ -78,28 +78,11 @@ csum_partial_copy_nocheck (const void *src, void *dst, int len, __wsum sum) */ static inline __sum16 csum_fold(__wsum sum) { -#ifndef __s390x__ - register_pair rp; + u32 csum = (__force u32) sum; - asm volatile( - " slr %N1,%N1\n" /* %0 = H L */ - " lr %1,%0\n" /* %0 = H L, %1 = H L 0 0 */ - " srdl %1,16\n" /* %0 = H L, %1 = 0 H L 0 */ - " alr %1,%N1\n" /* %0 = H L, %1 = L H L 0 */ - " alr %0,%1\n" /* %0 = H+L+C L+H */ - " srl %0,16\n" /* %0 = H+L+C */ - : "+&d" (sum), "=d" (rp) : : "cc"); -#else /* __s390x__ */ - asm volatile( - " sr 3,3\n" /* %0 = H*65536 + L */ - " lr 2,%0\n" /* %0 = H L, 2/3 = H L / 0 0 */ - " srdl 2,16\n" /* %0 = H L, 2/3 = 0 H / L 0 */ - " alr 2,3\n" /* %0 = H L, 2/3 = L H / L 0 */ - " alr %0,2\n" /* %0 = H+L+C L+H */ - " srl %0,16\n" /* %0 = H+L+C */ - : "+&d" (sum) : : "cc", "2", "3"); -#endif /* __s390x__ */ - return (__force __sum16) ~sum; + csum += (csum >> 16) + (csum << 16); + csum >>= 16; + return (__force __sum16) ~csum; } /* diff --git a/arch/s390/include/asm/chsc.h b/arch/s390/include/asm/chsc.h index 807997f7414..4943654ed7f 100644 --- a/arch/s390/include/asm/chsc.h +++ b/arch/s390/include/asm/chsc.h @@ -125,4 +125,32 @@ struct chsc_cpd_info { #define CHSC_INFO_CPD _IOWR(CHSC_IOCTL_MAGIC, 0x87, struct chsc_cpd_info) #define CHSC_INFO_DCAL _IOWR(CHSC_IOCTL_MAGIC, 0x88, struct chsc_dcal) +#ifdef __KERNEL__ + +struct css_general_char { + u64 : 12; + u32 dynio : 1; /* bit 12 */ + u32 : 28; + u32 aif : 1; /* bit 41 */ + u32 : 3; + u32 mcss : 1; /* bit 45 */ + u32 fcs : 1; /* bit 46 */ + u32 : 1; + u32 ext_mb : 1; /* bit 48 */ + u32 : 7; + u32 aif_tdd : 1; /* bit 56 */ + u32 : 1; + u32 qebsm : 1; /* bit 58 */ + u32 : 8; + u32 aif_osa : 1; /* bit 67 */ + u32 : 14; + u32 cib : 1; /* bit 82 */ + u32 : 5; + u32 fcx : 1; /* bit 88 */ + u32 : 7; +}__attribute__((packed)); + +extern struct css_general_char css_general_characteristics; + +#endif /* __KERNEL__ */ #endif diff --git a/arch/s390/include/asm/cio.h b/arch/s390/include/asm/cio.h index 619bf94b11f..e85679af54d 100644 --- a/arch/s390/include/asm/cio.h +++ b/arch/s390/include/asm/cio.h @@ -15,228 +15,7 @@ #define LPM_ANYPATH 0xff #define __MAX_CSSID 0 -/** - * struct cmd_scsw - command-mode subchannel status word - * @key: subchannel key - * @sctl: suspend control - * @eswf: esw format - * @cc: deferred condition code - * @fmt: format - * @pfch: prefetch - * @isic: initial-status interruption control - * @alcc: address-limit checking control - * @ssi: suppress-suspended interruption - * @zcc: zero condition code - * @ectl: extended control - * @pno: path not operational - * @res: reserved - * @fctl: function control - * @actl: activity control - * @stctl: status control - * @cpa: channel program address - * @dstat: device status - * @cstat: subchannel status - * @count: residual count - */ -struct cmd_scsw { - __u32 key : 4; - __u32 sctl : 1; - __u32 eswf : 1; - __u32 cc : 2; - __u32 fmt : 1; - __u32 pfch : 1; - __u32 isic : 1; - __u32 alcc : 1; - __u32 ssi : 1; - __u32 zcc : 1; - __u32 ectl : 1; - __u32 pno : 1; - __u32 res : 1; - __u32 fctl : 3; - __u32 actl : 7; - __u32 stctl : 5; - __u32 cpa; - __u32 dstat : 8; - __u32 cstat : 8; - __u32 count : 16; -} __attribute__ ((packed)); - -/** - * struct tm_scsw - transport-mode subchannel status word - * @key: subchannel key - * @eswf: esw format - * @cc: deferred condition code - * @fmt: format - * @x: IRB-format control - * @q: interrogate-complete - * @ectl: extended control - * @pno: path not operational - * @fctl: function control - * @actl: activity control - * @stctl: status control - * @tcw: TCW address - * @dstat: device status - * @cstat: subchannel status - * @fcxs: FCX status - * @schxs: subchannel-extended status - */ -struct tm_scsw { - u32 key:4; - u32 :1; - u32 eswf:1; - u32 cc:2; - u32 fmt:3; - u32 x:1; - u32 q:1; - u32 :1; - u32 ectl:1; - u32 pno:1; - u32 :1; - u32 fctl:3; - u32 actl:7; - u32 stctl:5; - u32 tcw; - u32 dstat:8; - u32 cstat:8; - u32 fcxs:8; - u32 schxs:8; -} __attribute__ ((packed)); - -/** - * union scsw - subchannel status word - * @cmd: command-mode SCSW - * @tm: transport-mode SCSW - */ -union scsw { - struct cmd_scsw cmd; - struct tm_scsw tm; -} __attribute__ ((packed)); - -int scsw_is_tm(union scsw *scsw); -u32 scsw_key(union scsw *scsw); -u32 scsw_eswf(union scsw *scsw); -u32 scsw_cc(union scsw *scsw); -u32 scsw_ectl(union scsw *scsw); -u32 scsw_pno(union scsw *scsw); -u32 scsw_fctl(union scsw *scsw); -u32 scsw_actl(union scsw *scsw); -u32 scsw_stctl(union scsw *scsw); -u32 scsw_dstat(union scsw *scsw); -u32 scsw_cstat(union scsw *scsw); -int scsw_is_solicited(union scsw *scsw); -int scsw_is_valid_key(union scsw *scsw); -int scsw_is_valid_eswf(union scsw *scsw); -int scsw_is_valid_cc(union scsw *scsw); -int scsw_is_valid_ectl(union scsw *scsw); -int scsw_is_valid_pno(union scsw *scsw); -int scsw_is_valid_fctl(union scsw *scsw); -int scsw_is_valid_actl(union scsw *scsw); -int scsw_is_valid_stctl(union scsw *scsw); -int scsw_is_valid_dstat(union scsw *scsw); -int scsw_is_valid_cstat(union scsw *scsw); -int scsw_cmd_is_valid_key(union scsw *scsw); -int scsw_cmd_is_valid_sctl(union scsw *scsw); -int scsw_cmd_is_valid_eswf(union scsw *scsw); -int scsw_cmd_is_valid_cc(union scsw *scsw); -int scsw_cmd_is_valid_fmt(union scsw *scsw); -int scsw_cmd_is_valid_pfch(union scsw *scsw); -int scsw_cmd_is_valid_isic(union scsw *scsw); -int scsw_cmd_is_valid_alcc(union scsw *scsw); -int scsw_cmd_is_valid_ssi(union scsw *scsw); -int scsw_cmd_is_valid_zcc(union scsw *scsw); -int scsw_cmd_is_valid_ectl(union scsw *scsw); -int scsw_cmd_is_valid_pno(union scsw *scsw); -int scsw_cmd_is_valid_fctl(union scsw *scsw); -int scsw_cmd_is_valid_actl(union scsw *scsw); -int scsw_cmd_is_valid_stctl(union scsw *scsw); -int scsw_cmd_is_valid_dstat(union scsw *scsw); -int scsw_cmd_is_valid_cstat(union scsw *scsw); -int scsw_cmd_is_solicited(union scsw *scsw); -int scsw_tm_is_valid_key(union scsw *scsw); -int scsw_tm_is_valid_eswf(union scsw *scsw); -int scsw_tm_is_valid_cc(union scsw *scsw); -int scsw_tm_is_valid_fmt(union scsw *scsw); -int scsw_tm_is_valid_x(union scsw *scsw); -int scsw_tm_is_valid_q(union scsw *scsw); -int scsw_tm_is_valid_ectl(union scsw *scsw); -int scsw_tm_is_valid_pno(union scsw *scsw); -int scsw_tm_is_valid_fctl(union scsw *scsw); -int scsw_tm_is_valid_actl(union scsw *scsw); -int scsw_tm_is_valid_stctl(union scsw *scsw); -int scsw_tm_is_valid_dstat(union scsw *scsw); -int scsw_tm_is_valid_cstat(union scsw *scsw); -int scsw_tm_is_valid_fcxs(union scsw *scsw); -int scsw_tm_is_valid_schxs(union scsw *scsw); -int scsw_tm_is_solicited(union scsw *scsw); - -#define SCSW_FCTL_CLEAR_FUNC 0x1 -#define SCSW_FCTL_HALT_FUNC 0x2 -#define SCSW_FCTL_START_FUNC 0x4 - -#define SCSW_ACTL_SUSPENDED 0x1 -#define SCSW_ACTL_DEVACT 0x2 -#define SCSW_ACTL_SCHACT 0x4 -#define SCSW_ACTL_CLEAR_PEND 0x8 -#define SCSW_ACTL_HALT_PEND 0x10 -#define SCSW_ACTL_START_PEND 0x20 -#define SCSW_ACTL_RESUME_PEND 0x40 - -#define SCSW_STCTL_STATUS_PEND 0x1 -#define SCSW_STCTL_SEC_STATUS 0x2 -#define SCSW_STCTL_PRIM_STATUS 0x4 -#define SCSW_STCTL_INTER_STATUS 0x8 -#define SCSW_STCTL_ALERT_STATUS 0x10 - -#define DEV_STAT_ATTENTION 0x80 -#define DEV_STAT_STAT_MOD 0x40 -#define DEV_STAT_CU_END 0x20 -#define DEV_STAT_BUSY 0x10 -#define DEV_STAT_CHN_END 0x08 -#define DEV_STAT_DEV_END 0x04 -#define DEV_STAT_UNIT_CHECK 0x02 -#define DEV_STAT_UNIT_EXCEP 0x01 - -#define SCHN_STAT_PCI 0x80 -#define SCHN_STAT_INCORR_LEN 0x40 -#define SCHN_STAT_PROG_CHECK 0x20 -#define SCHN_STAT_PROT_CHECK 0x10 -#define SCHN_STAT_CHN_DATA_CHK 0x08 -#define SCHN_STAT_CHN_CTRL_CHK 0x04 -#define SCHN_STAT_INTF_CTRL_CHK 0x02 -#define SCHN_STAT_CHAIN_CHECK 0x01 - -/* - * architectured values for first sense byte - */ -#define SNS0_CMD_REJECT 0x80 -#define SNS_CMD_REJECT SNS0_CMD_REJEC -#define SNS0_INTERVENTION_REQ 0x40 -#define SNS0_BUS_OUT_CHECK 0x20 -#define SNS0_EQUIPMENT_CHECK 0x10 -#define SNS0_DATA_CHECK 0x08 -#define SNS0_OVERRUN 0x04 -#define SNS0_INCOMPL_DOMAIN 0x01 - -/* - * architectured values for second sense byte - */ -#define SNS1_PERM_ERR 0x80 -#define SNS1_INV_TRACK_FORMAT 0x40 -#define SNS1_EOC 0x20 -#define SNS1_MESSAGE_TO_OPER 0x10 -#define SNS1_NO_REC_FOUND 0x08 -#define SNS1_FILE_PROTECTED 0x04 -#define SNS1_WRITE_INHIBITED 0x02 -#define SNS1_INPRECISE_END 0x01 - -/* - * architectured values for third sense byte - */ -#define SNS2_REQ_INH_WRITE 0x80 -#define SNS2_CORRECTABLE 0x40 -#define SNS2_FIRST_LOG_ERR 0x20 -#define SNS2_ENV_DATA_PRESENT 0x10 -#define SNS2_INPRECISE_END 0x04 +#include <asm/scsw.h> /** * struct ccw1 - channel command word diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h index de065b32381..01a08020bc0 100644 --- a/arch/s390/include/asm/compat.h +++ b/arch/s390/include/asm/compat.h @@ -5,6 +5,7 @@ */ #include <linux/types.h> #include <linux/sched.h> +#include <linux/thread_info.h> #define PSW32_MASK_PER 0x40000000UL #define PSW32_MASK_DAT 0x04000000UL @@ -163,12 +164,28 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr) return (u32)(unsigned long)uptr; } +#ifdef CONFIG_COMPAT + +static inline int is_compat_task(void) +{ + return test_thread_flag(TIF_31BIT); +} + +#else + +static inline int is_compat_task(void) +{ + return 0; +} + +#endif + static inline void __user *compat_alloc_user_space(long len) { unsigned long stack; stack = KSTK_ESP(current); - if (test_thread_flag(TIF_31BIT)) + if (is_compat_task()) stack &= 0x7fffffffUL; return (void __user *) (stack - len); } diff --git a/arch/s390/include/asm/cpu.h b/arch/s390/include/asm/cpu.h index d60a2eefb17..471234b9057 100644 --- a/arch/s390/include/asm/cpu.h +++ b/arch/s390/include/asm/cpu.h @@ -1,32 +1,26 @@ /* - * include/asm-s390/cpu.h - * - * Copyright IBM Corp. 2007 - * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> + * Copyright IBM Corp. 2000,2009 + * Author(s): Hartmut Penner <hp@de.ibm.com>, + * Martin Schwidefsky <schwidefsky@de.ibm.com>, + * Christian Ehrhardt <ehrhardt@de.ibm.com>, */ -#ifndef _ASM_S390_CPU_H_ -#define _ASM_S390_CPU_H_ +#ifndef _ASM_S390_CPU_H +#define _ASM_S390_CPU_H -#include <linux/types.h> -#include <linux/percpu.h> -#include <linux/spinlock.h> - -struct s390_idle_data { - spinlock_t lock; - unsigned long long idle_count; - unsigned long long idle_enter; - unsigned long long idle_time; -}; +#define MAX_CPU_ADDRESS 255 -DECLARE_PER_CPU(struct s390_idle_data, s390_idle); +#ifndef __ASSEMBLY__ -void vtime_start_cpu(void); +#include <linux/types.h> -static inline void s390_idle_check(void) +struct cpuid { - if ((&__get_cpu_var(s390_idle))->idle_enter != 0ULL) - vtime_start_cpu(); -} + unsigned int version : 8; + unsigned int ident : 24; + unsigned int machine : 16; + unsigned int unused : 16; +} __packed; -#endif /* _ASM_S390_CPU_H_ */ +#endif /* __ASSEMBLY__ */ +#endif /* _ASM_S390_CPU_H */ diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h index 95b0f7db3c6..258ba88b7b5 100644 --- a/arch/s390/include/asm/cputime.h +++ b/arch/s390/include/asm/cputime.h @@ -9,6 +9,9 @@ #ifndef _S390_CPUTIME_H #define _S390_CPUTIME_H +#include <linux/types.h> +#include <linux/percpu.h> +#include <linux/spinlock.h> #include <asm/div64.h> /* We want to use full resolution of the CPU timer: 2**-12 micro-seconds. */ @@ -39,6 +42,7 @@ __div(unsigned long long n, unsigned int base) #endif /* __s390x__ */ #define cputime_zero (0ULL) +#define cputime_one_jiffy jiffies_to_cputime(1) #define cputime_max ((~0UL >> 1) - 1) #define cputime_add(__a, __b) ((__a) + (__b)) #define cputime_sub(__a, __b) ((__a) - (__b)) @@ -74,7 +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 @@ -156,7 +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 @@ -171,7 +175,35 @@ 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 { + unsigned int sequence; + 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); + +void vtime_start_cpu(void); +cputime64_t s390_get_idle_time(int cpu); + +#define arch_idle_time(cpu) s390_get_idle_time(cpu) + +static inline void s390_idle_check(void) +{ + if ((&__get_cpu_var(s390_idle))->idle_enter != 0ULL) + 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/debug.h b/arch/s390/include/asm/debug.h index 9450ce6e32d..18124b75a7a 100644 --- a/arch/s390/include/asm/debug.h +++ b/arch/s390/include/asm/debug.h @@ -167,6 +167,10 @@ debug_text_event(debug_info_t* id, int level, const char* txt) return debug_event_common(id,level,txt,strlen(txt)); } +/* + * IMPORTANT: Use "%s" in sprintf format strings with care! Only pointers are + * stored in the s390dbf. See Documentation/s390/s390dbf.txt for more details! + */ extern debug_entry_t * debug_sprintf_event(debug_info_t* id,int level,char *string,...) __attribute__ ((format(printf, 3, 4))); @@ -206,7 +210,10 @@ debug_text_exception(debug_info_t* id, int level, const char* txt) return debug_exception_common(id,level,txt,strlen(txt)); } - +/* + * IMPORTANT: Use "%s" in sprintf format strings with care! Only pointers are + * stored in the s390dbf. See Documentation/s390/s390dbf.txt for more details! + */ extern debug_entry_t * debug_sprintf_exception(debug_info_t* id,int level,char *string,...) __attribute__ ((format(printf, 3, 4))); @@ -248,14 +255,5 @@ int debug_unregister_view(debug_info_t* id, struct debug_view* view); #define PRINT_FATAL(x...) printk ( KERN_DEBUG PRINTK_HEADER x ) #endif /* DASD_DEBUG */ -#undef DEBUG_MALLOC -#ifdef DEBUG_MALLOC -void *b; -#define kmalloc(x...) (PRINT_INFO(" kmalloc %p\n",b=kmalloc(x)),b) -#define kfree(x) PRINT_INFO(" kfree %p\n",x);kfree(x) -#define get_zeroed_page(x...) (PRINT_INFO(" gfp %p\n",b=get_zeroed_page(x)),b) -#define __get_free_pages(x...) (PRINT_INFO(" gfps %p\n",b=__get_free_pages(x)),b) -#endif /* DEBUG_MALLOC */ - #endif /* __KERNEL__ */ #endif /* DEBUG_H */ diff --git a/arch/s390/include/asm/delay.h b/arch/s390/include/asm/delay.h index a356c958e26..8a096b83f51 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 74d0bbb7d95..e885442c1df 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. */ diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h index 5a5bc75e19d..96c14a9102b 100644 --- a/arch/s390/include/asm/ftrace.h +++ b/arch/s390/include/asm/ftrace.h @@ -2,7 +2,28 @@ #define _ASM_S390_FTRACE_H #ifndef __ASSEMBLY__ + extern void _mcount(void); +extern unsigned long ftrace_dyn_func; + +struct dyn_arch_ftrace { }; + +#define MCOUNT_ADDR ((long)_mcount) + +#ifdef CONFIG_64BIT +#define MCOUNT_OFFSET_RET 18 +#define MCOUNT_INSN_SIZE 24 +#define MCOUNT_OFFSET 14 +#else +#define MCOUNT_OFFSET_RET 26 +#define MCOUNT_INSN_SIZE 30 +#define MCOUNT_OFFSET 8 #endif +static inline unsigned long ftrace_call_adjust(unsigned long addr) +{ + return addr - MCOUNT_OFFSET; +} + +#endif /* __ASSEMBLY__ */ #endif /* _ASM_S390_FTRACE_H */ diff --git a/arch/s390/include/asm/hardirq.h b/arch/s390/include/asm/hardirq.h index 89ec7056da2..498bc389238 100644 --- a/arch/s390/include/asm/hardirq.h +++ b/arch/s390/include/asm/hardirq.h @@ -18,13 +18,6 @@ #include <linux/interrupt.h> #include <asm/lowcore.h> -/* irq_cpustat_t is unused currently, but could be converted - * into a percpu variable instead of storing softirq_pending - * on the lowcore */ -typedef struct { - unsigned int __softirq_pending; -} irq_cpustat_t; - #define local_softirq_pending() (S390_lowcore.softirq_pending) #define __ARCH_IRQ_STAT diff --git a/arch/s390/include/asm/ipl.h b/arch/s390/include/asm/ipl.h index 1171e6d144a..5e95d95450b 100644 --- a/arch/s390/include/asm/ipl.h +++ b/arch/s390/include/asm/ipl.h @@ -57,6 +57,8 @@ struct ipl_block_fcp { } __attribute__((packed)); #define DIAG308_VMPARM_SIZE 64 +#define DIAG308_SCPDATA_SIZE (PAGE_SIZE - (sizeof(struct ipl_list_hdr) + \ + offsetof(struct ipl_block_fcp, scp_data))) struct ipl_block_ccw { u8 load_parm[8]; @@ -91,7 +93,8 @@ extern void do_halt(void); extern void do_poff(void); extern void ipl_save_parameters(void); extern void ipl_update_parameters(void); -extern void get_ipl_vmparm(char *); +extern size_t append_ipl_vmparm(char *, size_t); +extern size_t append_ipl_scpdata(char *, size_t); enum { IPL_DEVNO_VALID = 1, diff --git a/arch/s390/include/asm/kmap_types.h b/arch/s390/include/asm/kmap_types.h index fd157464822..94ec3ee0798 100644 --- a/arch/s390/include/asm/kmap_types.h +++ b/arch/s390/include/asm/kmap_types.h @@ -2,22 +2,7 @@ #ifndef _ASM_KMAP_TYPES_H #define _ASM_KMAP_TYPES_H -enum km_type { - KM_BOUNCE_READ, - KM_SKB_SUNRPC_DATA, - KM_SKB_DATA_SOFTIRQ, - KM_USER0, - KM_USER1, - KM_BIO_SRC_IRQ, - KM_BIO_DST_IRQ, - KM_PTE0, - KM_PTE1, - KM_IRQ0, - KM_IRQ1, - KM_SOFTIRQ0, - KM_SOFTIRQ1, - KM_TYPE_NR -}; +#include <asm-generic/kmap_types.h> #endif #endif /* __KERNEL__ */ diff --git a/arch/s390/include/asm/kvm.h b/arch/s390/include/asm/kvm.h index 0b2f829f6d5..82b32a100c7 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 * @@ -15,14 +14,7 @@ */ #include <linux/types.h> -/* for KVM_GET_IRQCHIP and KVM_SET_IRQCHIP */ -struct kvm_pic_state { - /* no PIC for s390 */ -}; - -struct kvm_ioapic_state { - /* no IOAPIC for s390 */ -}; +#define __KVM_S390 /* for KVM_GET_REGS and KVM_SET_REGS */ struct kvm_regs { diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index c6e674f5fca..27605b62b98 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -1,7 +1,7 @@ /* * asm-s390/kvm_host.h - definition for kernel virtual machines on s390 * - * Copyright IBM Corp. 2008 + * Copyright IBM Corp. 2008,2009 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License (version 2 only) @@ -13,8 +13,11 @@ #ifndef ASM_KVM_HOST_H #define ASM_KVM_HOST_H +#include <linux/hrtimer.h> +#include <linux/interrupt.h> #include <linux/kvm_host.h> #include <asm/debug.h> +#include <asm/cpu.h> #define KVM_MAX_VCPUS 64 #define KVM_MEMORY_SLOTS 32 @@ -37,7 +40,11 @@ struct sca_block { struct sca_entry cpu[64]; } __attribute__((packed)); -#define KVM_PAGES_PER_HPAGE 256 +#define KVM_NR_PAGE_SIZES 2 +#define KVM_HPAGE_SHIFT(x) (PAGE_SHIFT + ((x) - 1) * 8) +#define KVM_HPAGE_SIZE(x) (1UL << KVM_HPAGE_SHIFT(x)) +#define KVM_HPAGE_MASK(x) (~(KVM_HPAGE_SIZE(x) - 1)) +#define KVM_PAGES_PER_HPAGE(x) (KVM_HPAGE_SIZE(x) / PAGE_SIZE) #define CPUSTAT_HOST 0x80000000 #define CPUSTAT_WAIT 0x10000000 @@ -96,7 +103,9 @@ struct kvm_s390_sie_block { __u8 reservedd0[48]; /* 0x00d0 */ __u64 gcr[16]; /* 0x0100 */ __u64 gbea; /* 0x0180 */ - __u8 reserved188[120]; /* 0x0188 */ + __u8 reserved188[24]; /* 0x0188 */ + __u32 fac; /* 0x01a0 */ + __u8 reserved1a4[92]; /* 0x01a4 */ } __attribute__((packed)); struct kvm_vcpu_stat { @@ -177,8 +186,9 @@ struct kvm_s390_interrupt_info { }; /* for local_interrupt.action_flags */ -#define ACTION_STORE_ON_STOP 1 -#define ACTION_STOP_ON_STOP 2 +#define ACTION_STORE_ON_STOP (1<<0) +#define ACTION_STOP_ON_STOP (1<<1) +#define ACTION_RELOADVCPU_ON_STOP (1<<2) struct kvm_s390_local_interrupt { spinlock_t lock; @@ -209,10 +219,11 @@ struct kvm_vcpu_arch { s390_fp_regs guest_fpregs; unsigned int guest_acrs[NUM_ACRS]; struct kvm_s390_local_interrupt local_int; - struct timer_list ckc_timer; + struct hrtimer ckc_timer; + struct tasklet_struct tasklet; union { - cpuid_t cpu_id; - u64 stidp_data; + struct cpuid cpu_id; + u64 stidp_data; }; }; @@ -221,8 +232,6 @@ struct kvm_vm_stat { }; struct kvm_arch{ - unsigned long guest_origin; - unsigned long guest_memsize; struct sca_block *sca; debug_info_t *dbf; struct kvm_s390_float_interrupt float_int; diff --git a/arch/s390/include/asm/kvm_para.h b/arch/s390/include/asm/kvm_para.h index 2c503796b61..6964db226f8 100644 --- a/arch/s390/include/asm/kvm_para.h +++ b/arch/s390/include/asm/kvm_para.h @@ -13,6 +13,8 @@ #ifndef __S390_KVM_PARA_H #define __S390_KVM_PARA_H +#ifdef __KERNEL__ + /* * Hypercalls for KVM on s390. The calling convention is similar to the * s390 ABI, so we use R2-R6 for parameters 1-5. In addition we use R1 @@ -147,4 +149,6 @@ static inline unsigned int kvm_arch_para_features(void) return 0; } +#endif + #endif /* __S390_KVM_PARA_H */ diff --git a/arch/s390/include/asm/kvm_virtio.h b/arch/s390/include/asm/kvm_virtio.h index 0503936f101..acdfdff2661 100644 --- a/arch/s390/include/asm/kvm_virtio.h +++ b/arch/s390/include/asm/kvm_virtio.h @@ -54,14 +54,4 @@ struct kvm_vqconfig { * This is pagesize for historical reasons. */ #define KVM_S390_VIRTIO_RING_ALIGN 4096 -#ifdef __KERNEL__ -/* early virtio console setup */ -#ifdef CONFIG_S390_GUEST -extern void s390_virtio_console_init(void); -#else -static inline void s390_virtio_console_init(void) -{ -} -#endif /* CONFIG_VIRTIO_CONSOLE */ -#endif /* __KERNEL__ */ #endif diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h index b349f1c7fdf..f2ef4b619ce 100644 --- a/arch/s390/include/asm/lowcore.h +++ b/arch/s390/include/asm/lowcore.h @@ -30,6 +30,7 @@ #define __LC_SUBCHANNEL_NR 0x00ba #define __LC_IO_INT_PARM 0x00bc #define __LC_IO_INT_WORD 0x00c0 +#define __LC_STFL_FAC_LIST 0x00c8 #define __LC_MCCK_CODE 0x00e8 #define __LC_DUMP_REIPL 0x0e00 @@ -66,6 +67,8 @@ #define __LC_USER_EXEC_ASCE 0x02ac #define __LC_CPUID 0x02b0 #define __LC_INT_CLOCK 0x02c8 +#define __LC_MACHINE_FLAGS 0x02d8 +#define __LC_FTRACE_FUNC 0x02dc #define __LC_IRB 0x0300 #define __LC_PFAULT_INTPARM 0x0080 #define __LC_CPU_TIMER_SAVE_AREA 0x00d8 @@ -83,6 +86,7 @@ #define __LC_PGM_OLD_PSW 0x0150 #define __LC_MCK_OLD_PSW 0x0160 #define __LC_IO_OLD_PSW 0x0170 +#define __LC_RESTART_PSW 0x01a0 #define __LC_EXT_NEW_PSW 0x01b0 #define __LC_SVC_NEW_PSW 0x01c0 #define __LC_PGM_NEW_PSW 0x01d0 @@ -110,6 +114,8 @@ #define __LC_CPUID 0x0320 #define __LC_INT_CLOCK 0x0340 #define __LC_VDSO_PER_CPU 0x0350 +#define __LC_MACHINE_FLAGS 0x0358 +#define __LC_FTRACE_FUNC 0x0360 #define __LC_IRB 0x0380 #define __LC_PASTE 0x03c0 #define __LC_PFAULT_INTPARM 0x11b8 @@ -127,9 +133,9 @@ #ifndef __ASSEMBLY__ -#include <asm/processor.h> +#include <asm/cpu.h> +#include <asm/ptrace.h> #include <linux/types.h> -#include <asm/sigp.h> void restart_int_handler(void); void ext_int_handler(void); @@ -184,6 +190,14 @@ union save_area { #define SAVE_AREA_BASE SAVE_AREA_BASE_S390X #endif +#ifndef __s390x__ +#define LC_ORDER 0 +#else +#define LC_ORDER 1 +#endif + +#define LC_PAGES (1UL << LC_ORDER) + struct _lowcore { #ifndef __s390x__ @@ -270,14 +284,16 @@ struct _lowcore __u32 user_exec_asce; /* 0x02ac */ /* SMP info area */ - cpuid_t cpu_id; /* 0x02b0 */ + struct cpuid cpu_id; /* 0x02b0 */ __u32 cpu_nr; /* 0x02b8 */ __u32 softirq_pending; /* 0x02bc */ __u32 percpu_offset; /* 0x02c0 */ __u32 ext_call_fast; /* 0x02c4 */ __u64 int_clock; /* 0x02c8 */ __u64 clock_comparator; /* 0x02d0 */ - __u8 pad_0x02d8[0x0300-0x02d8]; /* 0x02d8 */ + __u32 machine_flags; /* 0x02d8 */ + __u32 ftrace_func; /* 0x02dc */ + __u8 pad_0x02f0[0x0300-0x02f0]; /* 0x02f0 */ /* Interrupt response block */ __u8 irb[64]; /* 0x0300 */ @@ -373,7 +389,7 @@ struct _lowcore __u64 user_exec_asce; /* 0x0318 */ /* SMP info area */ - cpuid_t cpu_id; /* 0x0320 */ + struct cpuid cpu_id; /* 0x0320 */ __u32 cpu_nr; /* 0x0328 */ __u32 softirq_pending; /* 0x032c */ __u64 percpu_offset; /* 0x0330 */ @@ -381,7 +397,9 @@ struct _lowcore __u64 int_clock; /* 0x0340 */ __u64 clock_comparator; /* 0x0348 */ __u64 vdso_per_cpu_data; /* 0x0350 */ - __u8 pad_0x0358[0x0380-0x0358]; /* 0x0358 */ + __u64 machine_flags; /* 0x0358 */ + __u64 ftrace_func; /* 0x0360 */ + __u8 pad_0x0368[0x0380-0x0368]; /* 0x0368 */ /* Interrupt response block. */ __u8 irb[64]; /* 0x0380 */ diff --git a/arch/s390/include/asm/mman.h b/arch/s390/include/asm/mman.h index da01432e8f4..4e9c8ae0a63 100644 --- a/arch/s390/include/asm/mman.h +++ b/arch/s390/include/asm/mman.h @@ -11,17 +11,6 @@ #include <asm-generic/mman.h> -#define MAP_GROWSDOWN 0x0100 /* stack-like segment */ -#define MAP_DENYWRITE 0x0800 /* ETXTBSY */ -#define MAP_EXECUTABLE 0x1000 /* mark it as an executable */ -#define MAP_LOCKED 0x2000 /* pages are locked */ -#define MAP_NORESERVE 0x4000 /* don't check for reservations */ -#define MAP_POPULATE 0x8000 /* populate (prefault) pagetables */ -#define MAP_NONBLOCK 0x10000 /* do not block on IO */ - -#define MCL_CURRENT 1 /* lock all current mappings */ -#define MCL_FUTURE 2 /* lock all future mappings */ - #if defined(__KERNEL__) && !defined(__ASSEMBLY__) && defined(CONFIG_64BIT) int s390_mmap_check(unsigned long addr, unsigned long len); #define arch_mmap_check(addr,len,flags) s390_mmap_check(addr,len) diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h index 3b59216e628..03be99919d6 100644 --- a/arch/s390/include/asm/mmu.h +++ b/arch/s390/include/asm/mmu.h @@ -2,6 +2,7 @@ #define __MMU_H typedef struct { + spinlock_t list_lock; struct list_head crst_list; struct list_head pgtable_list; unsigned long asce_bits; diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index 32e8f6aa438..5e9daf5d7f2 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -125,8 +125,6 @@ page_get_storage_key(unsigned long addr) return skey; } -#ifdef CONFIG_PAGE_STATES - struct page; void arch_free_page(struct page *page, int order); void arch_alloc_page(struct page *page, int order); @@ -134,8 +132,6 @@ void arch_alloc_page(struct page *page, int order); #define HAVE_ARCH_FREE_PAGE #define HAVE_ARCH_ALLOC_PAGE -#endif - #endif /* !__ASSEMBLY__ */ #define __PAGE_OFFSET 0x0UL @@ -150,7 +146,7 @@ void arch_alloc_page(struct page *page, int order); VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) #include <asm-generic/memory_model.h> -#include <asm-generic/page.h> +#include <asm-generic/getorder.h> #define __HAVE_ARCH_GATE_AREA 1 diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h index 408d60b4f75..f7ad8719d02 100644 --- a/arch/s390/include/asm/percpu.h +++ b/arch/s390/include/asm/percpu.h @@ -1,37 +1,21 @@ #ifndef __ARCH_S390_PERCPU__ #define __ARCH_S390_PERCPU__ -#include <linux/compiler.h> -#include <asm/lowcore.h> - /* * s390 uses its own implementation for per cpu data, the offset of * the cpu local data area is cached in the cpu's lowcore memory. - * For 64 bit module code s390 forces the use of a GOT slot for the - * address of the per cpu variable. This is needed because the module - * may be more than 4G above the per cpu area. */ -#if defined(__s390x__) && defined(MODULE) - -#define SHIFT_PERCPU_PTR(ptr,offset) (({ \ - extern int simple_identifier_##var(void); \ - unsigned long *__ptr; \ - asm ( "larl %0, %1@GOTENT" \ - : "=a" (__ptr) : "X" (ptr) ); \ - (typeof(ptr))((*__ptr) + (offset)); })) - -#else - -#define SHIFT_PERCPU_PTR(ptr, offset) (({ \ - extern int simple_identifier_##var(void); \ - unsigned long __ptr; \ - asm ( "" : "=a" (__ptr) : "0" (ptr) ); \ - (typeof(ptr)) (__ptr + (offset)); })) +#define __my_cpu_offset S390_lowcore.percpu_offset +/* + * For 64 bit module code, the module may be more than 4G above the + * per cpu area, use weak definitions to force the compiler to + * generate external references. + */ +#if defined(CONFIG_SMP) && defined(__s390x__) && defined(MODULE) +#define ARCH_NEEDS_WEAK_PER_CPU #endif -#define __my_cpu_offset S390_lowcore.percpu_offset - #include <asm-generic/percpu.h> #endif /* __ARCH_S390_PERCPU__ */ diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h new file mode 100644 index 00000000000..3840cbe7763 --- /dev/null +++ b/arch/s390/include/asm/perf_event.h @@ -0,0 +1,10 @@ +/* + * Performance event support - s390 specific definitions. + * + * Copyright 2009 Martin Schwidefsky, IBM Corporation. + */ + +static inline void set_perf_event_pending(void) {} +static inline void clear_perf_event_pending(void) {} + +#define PERF_EVENT_INDEX_OFFSET 0 diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index b2658b9220f..ddad5903341 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -140,6 +140,7 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) 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); diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 5caddd4f7be..60a7b1a1702 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -112,12 +112,15 @@ extern char empty_zero_page[PAGE_SIZE]; * effect, this also makes sure that 64 bit module code cannot be used * as system call address. */ + +extern unsigned long VMALLOC_START; + #ifndef __s390x__ -#define VMALLOC_START 0x78000000UL +#define VMALLOC_SIZE (96UL << 20) #define VMALLOC_END 0x7e000000UL #define VMEM_MAP_END 0x80000000UL #else /* __s390x__ */ -#define VMALLOC_START 0x3e000000000UL +#define VMALLOC_SIZE (1UL << 30) #define VMALLOC_END 0x3e040000000UL #define VMEM_MAP_END 0x40000000000UL #endif /* __s390x__ */ diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 61862b3ac79..b4271545831 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -14,7 +14,10 @@ #define __ASM_S390_PROCESSOR_H #include <linux/linkage.h> +#include <asm/cpu.h> +#include <asm/page.h> #include <asm/ptrace.h> +#include <asm/setup.h> #ifdef __KERNEL__ /* @@ -23,21 +26,7 @@ */ #define current_text_addr() ({ void *pc; asm("basr %0,0" : "=a" (pc)); pc; }) -/* - * CPU type and hardware bug flags. Kept separately for each CPU. - * Members of this structure are referenced in head.S, so think twice - * before touching them. [mj] - */ - -typedef struct -{ - unsigned int version : 8; - unsigned int ident : 24; - unsigned int machine : 16; - unsigned int unused : 16; -} __attribute__ ((packed)) cpuid_t; - -static inline void get_cpu_id(cpuid_t *ptr) +static inline void get_cpu_id(struct cpuid *ptr) { asm volatile("stidp 0(%1)" : "=m" (*ptr) : "a" (ptr)); } @@ -306,7 +295,7 @@ static inline void ATTRIB_NORET disabled_wait(unsigned long code) " oi 0x384(1),0x10\n"/* fake protection bit */ " lpswe 0(%1)" : "=m" (ctl_buf) - : "a" (&dw_psw), "a" (&ctl_buf), "m" (dw_psw) : "cc", "0"); + : "a" (&dw_psw), "a" (&ctl_buf), "m" (dw_psw) : "cc", "0", "1"); #endif /* __s390x__ */ while (1); } diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h index f1b051630c5..95dcf183a28 100644 --- a/arch/s390/include/asm/ptrace.h +++ b/arch/s390/include/asm/ptrace.h @@ -311,10 +311,12 @@ typedef struct __u32 orig_gpr2; } s390_compat_regs; +typedef struct +{ + __u32 gprs_high[NUM_GPRS]; +} s390_compat_regs_high; #ifdef __KERNEL__ -#include <asm/setup.h> -#include <asm/page.h> /* * The pt_regs struct defines the way the registers are stored on diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h index 402d6dcf0d2..79d849f014f 100644 --- a/arch/s390/include/asm/qdio.h +++ b/arch/s390/include/asm/qdio.h @@ -380,7 +380,7 @@ extern int qdio_establish(struct qdio_initialize *); extern int qdio_activate(struct ccw_device *); extern int do_QDIO(struct ccw_device *cdev, unsigned int callflags, - int q_nr, int bufnr, int count); + int q_nr, unsigned int bufnr, unsigned int count); extern int qdio_cleanup(struct ccw_device*, int); extern int qdio_shutdown(struct ccw_device*, int); extern int qdio_free(struct ccw_device *); diff --git a/arch/s390/include/asm/scatterlist.h b/arch/s390/include/asm/scatterlist.h index 29ec8e28c8d..35d786fe93a 100644 --- a/arch/s390/include/asm/scatterlist.h +++ b/arch/s390/include/asm/scatterlist.h @@ -1,19 +1 @@ -#ifndef _ASMS390_SCATTERLIST_H -#define _ASMS390_SCATTERLIST_H - -struct scatterlist { -#ifdef CONFIG_DEBUG_SG - unsigned long sg_magic; -#endif - unsigned long page_link; - unsigned int offset; - unsigned int length; -}; - -#ifdef __s390x__ -#define ISA_DMA_THRESHOLD (0xffffffffffffffffUL) -#else -#define ISA_DMA_THRESHOLD (0xffffffffUL) -#endif - -#endif /* _ASMS390X_SCATTERLIST_H */ +#include <asm-generic/scatterlist.h> diff --git a/arch/s390/include/asm/scsw.h b/arch/s390/include/asm/scsw.h new file mode 100644 index 00000000000..de389cb54d2 --- /dev/null +++ b/arch/s390/include/asm/scsw.h @@ -0,0 +1,956 @@ +/* + * Helper functions for scsw access. + * + * Copyright IBM Corp. 2008,2009 + * Author(s): Peter Oberparleiter <peter.oberparleiter@de.ibm.com> + */ + +#ifndef _ASM_S390_SCSW_H_ +#define _ASM_S390_SCSW_H_ + +#include <linux/types.h> +#include <asm/chsc.h> +#include <asm/cio.h> + +/** + * struct cmd_scsw - command-mode subchannel status word + * @key: subchannel key + * @sctl: suspend control + * @eswf: esw format + * @cc: deferred condition code + * @fmt: format + * @pfch: prefetch + * @isic: initial-status interruption control + * @alcc: address-limit checking control + * @ssi: suppress-suspended interruption + * @zcc: zero condition code + * @ectl: extended control + * @pno: path not operational + * @res: reserved + * @fctl: function control + * @actl: activity control + * @stctl: status control + * @cpa: channel program address + * @dstat: device status + * @cstat: subchannel status + * @count: residual count + */ +struct cmd_scsw { + __u32 key : 4; + __u32 sctl : 1; + __u32 eswf : 1; + __u32 cc : 2; + __u32 fmt : 1; + __u32 pfch : 1; + __u32 isic : 1; + __u32 alcc : 1; + __u32 ssi : 1; + __u32 zcc : 1; + __u32 ectl : 1; + __u32 pno : 1; + __u32 res : 1; + __u32 fctl : 3; + __u32 actl : 7; + __u32 stctl : 5; + __u32 cpa; + __u32 dstat : 8; + __u32 cstat : 8; + __u32 count : 16; +} __attribute__ ((packed)); + +/** + * struct tm_scsw - transport-mode subchannel status word + * @key: subchannel key + * @eswf: esw format + * @cc: deferred condition code + * @fmt: format + * @x: IRB-format control + * @q: interrogate-complete + * @ectl: extended control + * @pno: path not operational + * @fctl: function control + * @actl: activity control + * @stctl: status control + * @tcw: TCW address + * @dstat: device status + * @cstat: subchannel status + * @fcxs: FCX status + * @schxs: subchannel-extended status + */ +struct tm_scsw { + u32 key:4; + u32 :1; + u32 eswf:1; + u32 cc:2; + u32 fmt:3; + u32 x:1; + u32 q:1; + u32 :1; + u32 ectl:1; + u32 pno:1; + u32 :1; + u32 fctl:3; + u32 actl:7; + u32 stctl:5; + u32 tcw; + u32 dstat:8; + u32 cstat:8; + u32 fcxs:8; + u32 schxs:8; +} __attribute__ ((packed)); + +/** + * union scsw - subchannel status word + * @cmd: command-mode SCSW + * @tm: transport-mode SCSW + */ +union scsw { + struct cmd_scsw cmd; + struct tm_scsw tm; +} __attribute__ ((packed)); + +#define SCSW_FCTL_CLEAR_FUNC 0x1 +#define SCSW_FCTL_HALT_FUNC 0x2 +#define SCSW_FCTL_START_FUNC 0x4 + +#define SCSW_ACTL_SUSPENDED 0x1 +#define SCSW_ACTL_DEVACT 0x2 +#define SCSW_ACTL_SCHACT 0x4 +#define SCSW_ACTL_CLEAR_PEND 0x8 +#define SCSW_ACTL_HALT_PEND 0x10 +#define SCSW_ACTL_START_PEND 0x20 +#define SCSW_ACTL_RESUME_PEND 0x40 + +#define SCSW_STCTL_STATUS_PEND 0x1 +#define SCSW_STCTL_SEC_STATUS 0x2 +#define SCSW_STCTL_PRIM_STATUS 0x4 +#define SCSW_STCTL_INTER_STATUS 0x8 +#define SCSW_STCTL_ALERT_STATUS 0x10 + +#define DEV_STAT_ATTENTION 0x80 +#define DEV_STAT_STAT_MOD 0x40 +#define DEV_STAT_CU_END 0x20 +#define DEV_STAT_BUSY 0x10 +#define DEV_STAT_CHN_END 0x08 +#define DEV_STAT_DEV_END 0x04 +#define DEV_STAT_UNIT_CHECK 0x02 +#define DEV_STAT_UNIT_EXCEP 0x01 + +#define SCHN_STAT_PCI 0x80 +#define SCHN_STAT_INCORR_LEN 0x40 +#define SCHN_STAT_PROG_CHECK 0x20 +#define SCHN_STAT_PROT_CHECK 0x10 +#define SCHN_STAT_CHN_DATA_CHK 0x08 +#define SCHN_STAT_CHN_CTRL_CHK 0x04 +#define SCHN_STAT_INTF_CTRL_CHK 0x02 +#define SCHN_STAT_CHAIN_CHECK 0x01 + +/* + * architectured values for first sense byte + */ +#define SNS0_CMD_REJECT 0x80 +#define SNS_CMD_REJECT SNS0_CMD_REJEC +#define SNS0_INTERVENTION_REQ 0x40 +#define SNS0_BUS_OUT_CHECK 0x20 +#define SNS0_EQUIPMENT_CHECK 0x10 +#define SNS0_DATA_CHECK 0x08 +#define SNS0_OVERRUN 0x04 +#define SNS0_INCOMPL_DOMAIN 0x01 + +/* + * architectured values for second sense byte + */ +#define SNS1_PERM_ERR 0x80 +#define SNS1_INV_TRACK_FORMAT 0x40 +#define SNS1_EOC 0x20 +#define SNS1_MESSAGE_TO_OPER 0x10 +#define SNS1_NO_REC_FOUND 0x08 +#define SNS1_FILE_PROTECTED 0x04 +#define SNS1_WRITE_INHIBITED 0x02 +#define SNS1_INPRECISE_END 0x01 + +/* + * architectured values for third sense byte + */ +#define SNS2_REQ_INH_WRITE 0x80 +#define SNS2_CORRECTABLE 0x40 +#define SNS2_FIRST_LOG_ERR 0x20 +#define SNS2_ENV_DATA_PRESENT 0x10 +#define SNS2_INPRECISE_END 0x04 + +/** + * scsw_is_tm - check for transport mode scsw + * @scsw: pointer to scsw + * + * Return non-zero if the specified scsw is a transport mode scsw, zero + * otherwise. + */ +static inline int scsw_is_tm(union scsw *scsw) +{ + return css_general_characteristics.fcx && (scsw->tm.x == 1); +} + +/** + * scsw_key - return scsw key field + * @scsw: pointer to scsw + * + * Return the value of the key field of the specified scsw, regardless of + * whether it is a transport mode or command mode scsw. + */ +static inline u32 scsw_key(union scsw *scsw) +{ + if (scsw_is_tm(scsw)) + return scsw->tm.key; + else + return scsw->cmd.key; +} + +/** + * scsw_eswf - return scsw eswf field + * @scsw: pointer to scsw + * + * Return the value of the eswf field of the specified scsw, regardless of + * whether it is a transport mode or command mode scsw. + */ +static inline u32 scsw_eswf(union scsw *scsw) +{ + if (scsw_is_tm(scsw)) + return scsw->tm.eswf; + else + return scsw->cmd.eswf; +} + +/** + * scsw_cc - return scsw cc field + * @scsw: pointer to scsw + * + * Return the value of the cc field of the specified scsw, regardless of + * whether it is a transport mode or command mode scsw. + */ +static inline u32 scsw_cc(union scsw *scsw) +{ + if (scsw_is_tm(scsw)) + return scsw->tm.cc; + else + return scsw->cmd.cc; +} + +/** + * scsw_ectl - return scsw ectl field + * @scsw: pointer to scsw + * + * Return the value of the ectl field of the specified scsw, regardless of + * whether it is a transport mode or command mode scsw. + */ +static inline u32 scsw_ectl(union scsw *scsw) +{ + if (scsw_is_tm(scsw)) + return scsw->tm.ectl; + else + return scsw->cmd.ectl; +} + +/** + * scsw_pno - return scsw pno field + * @scsw: pointer to scsw + * + * Return the value of the pno field of the specified scsw, regardless of + * whether it is a transport mode or command mode scsw. + */ +static inline u32 scsw_pno(union scsw *scsw) +{ + if (scsw_is_tm(scsw)) + return scsw->tm.pno; + else + return scsw->cmd.pno; +} + +/** + * scsw_fctl - return scsw fctl field + * @scsw: pointer to scsw + * + * Return the value of the fctl field of the specified scsw, regardless of + * whether it is a transport mode or command mode scsw. + */ +static inline u32 scsw_fctl(union scsw *scsw) +{ + if (scsw_is_tm(scsw)) + return scsw->tm.fctl; + else + return scsw->cmd.fctl; +} + +/** + * scsw_actl - return scsw actl field + * @scsw: pointer to scsw + * + * Return the value of the actl field of the specified scsw, regardless of + * whether it is a transport mode or command mode scsw. + */ +static inline u32 scsw_actl(union scsw *scsw) +{ + if (scsw_is_tm(scsw)) + return scsw->tm.actl; + else + return scsw->cmd.actl; +} + +/** + * scsw_stctl - return scsw stctl field + * @scsw: pointer to scsw + * + * Return the value of the stctl field of the specified scsw, regardless of + * whether it is a transport mode or command mode scsw. + */ +static inline u32 scsw_stctl(union scsw *scsw) +{ + if (scsw_is_tm(scsw)) + return scsw->tm.stctl; + else + return scsw->cmd.stctl; +} + +/** + * scsw_dstat - return scsw dstat field + * @scsw: pointer to scsw + * + * Return the value of the dstat field of the specified scsw, regardless of + * whether it is a transport mode or command mode scsw. + */ +static inline u32 scsw_dstat(union scsw *scsw) +{ + if (scsw_is_tm(scsw)) + return scsw->tm.dstat; + else + return scsw->cmd.dstat; +} + +/** + * scsw_cstat - return scsw cstat field + * @scsw: pointer to scsw + * + * Return the value of the cstat field of the specified scsw, regardless of + * whether it is a transport mode or command mode scsw. + */ +static inline u32 scsw_cstat(union scsw *scsw) +{ + if (scsw_is_tm(scsw)) + return scsw->tm.cstat; + else + return scsw->cmd.cstat; +} + +/** + * scsw_cmd_is_valid_key - check key field validity + * @scsw: pointer to scsw + * + * Return non-zero if the key field of the specified command mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_cmd_is_valid_key(union scsw *scsw) +{ + return (scsw->cmd.fctl & SCSW_FCTL_START_FUNC); +} + +/** + * scsw_cmd_is_valid_sctl - check fctl field validity + * @scsw: pointer to scsw + * + * Return non-zero if the fctl field of the specified command mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_cmd_is_valid_sctl(union scsw *scsw) +{ + return (scsw->cmd.fctl & SCSW_FCTL_START_FUNC); +} + +/** + * scsw_cmd_is_valid_eswf - check eswf field validity + * @scsw: pointer to scsw + * + * Return non-zero if the eswf field of the specified command mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_cmd_is_valid_eswf(union scsw *scsw) +{ + return (scsw->cmd.stctl & SCSW_STCTL_STATUS_PEND); +} + +/** + * scsw_cmd_is_valid_cc - check cc field validity + * @scsw: pointer to scsw + * + * Return non-zero if the cc field of the specified command mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_cmd_is_valid_cc(union scsw *scsw) +{ + return (scsw->cmd.fctl & SCSW_FCTL_START_FUNC) && + (scsw->cmd.stctl & SCSW_STCTL_STATUS_PEND); +} + +/** + * scsw_cmd_is_valid_fmt - check fmt field validity + * @scsw: pointer to scsw + * + * Return non-zero if the fmt field of the specified command mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_cmd_is_valid_fmt(union scsw *scsw) +{ + return (scsw->cmd.fctl & SCSW_FCTL_START_FUNC); +} + +/** + * scsw_cmd_is_valid_pfch - check pfch field validity + * @scsw: pointer to scsw + * + * Return non-zero if the pfch field of the specified command mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_cmd_is_valid_pfch(union scsw *scsw) +{ + return (scsw->cmd.fctl & SCSW_FCTL_START_FUNC); +} + +/** + * scsw_cmd_is_valid_isic - check isic field validity + * @scsw: pointer to scsw + * + * Return non-zero if the isic field of the specified command mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_cmd_is_valid_isic(union scsw *scsw) +{ + return (scsw->cmd.fctl & SCSW_FCTL_START_FUNC); +} + +/** + * scsw_cmd_is_valid_alcc - check alcc field validity + * @scsw: pointer to scsw + * + * Return non-zero if the alcc field of the specified command mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_cmd_is_valid_alcc(union scsw *scsw) +{ + return (scsw->cmd.fctl & SCSW_FCTL_START_FUNC); +} + +/** + * scsw_cmd_is_valid_ssi - check ssi field validity + * @scsw: pointer to scsw + * + * Return non-zero if the ssi field of the specified command mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_cmd_is_valid_ssi(union scsw *scsw) +{ + return (scsw->cmd.fctl & SCSW_FCTL_START_FUNC); +} + +/** + * scsw_cmd_is_valid_zcc - check zcc field validity + * @scsw: pointer to scsw + * + * Return non-zero if the zcc field of the specified command mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_cmd_is_valid_zcc(union scsw *scsw) +{ + return (scsw->cmd.fctl & SCSW_FCTL_START_FUNC) && + (scsw->cmd.stctl & SCSW_STCTL_INTER_STATUS); +} + +/** + * scsw_cmd_is_valid_ectl - check ectl field validity + * @scsw: pointer to scsw + * + * Return non-zero if the ectl field of the specified command mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_cmd_is_valid_ectl(union scsw *scsw) +{ + return (scsw->cmd.stctl & SCSW_STCTL_STATUS_PEND) && + !(scsw->cmd.stctl & SCSW_STCTL_INTER_STATUS) && + (scsw->cmd.stctl & SCSW_STCTL_ALERT_STATUS); +} + +/** + * scsw_cmd_is_valid_pno - check pno field validity + * @scsw: pointer to scsw + * + * Return non-zero if the pno field of the specified command mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_cmd_is_valid_pno(union scsw *scsw) +{ + return (scsw->cmd.fctl != 0) && + (scsw->cmd.stctl & SCSW_STCTL_STATUS_PEND) && + (!(scsw->cmd.stctl & SCSW_STCTL_INTER_STATUS) || + ((scsw->cmd.stctl & SCSW_STCTL_INTER_STATUS) && + (scsw->cmd.actl & SCSW_ACTL_SUSPENDED))); +} + +/** + * scsw_cmd_is_valid_fctl - check fctl field validity + * @scsw: pointer to scsw + * + * Return non-zero if the fctl field of the specified command mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_cmd_is_valid_fctl(union scsw *scsw) +{ + /* Only valid if pmcw.dnv == 1*/ + return 1; +} + +/** + * scsw_cmd_is_valid_actl - check actl field validity + * @scsw: pointer to scsw + * + * Return non-zero if the actl field of the specified command mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_cmd_is_valid_actl(union scsw *scsw) +{ + /* Only valid if pmcw.dnv == 1*/ + return 1; +} + +/** + * scsw_cmd_is_valid_stctl - check stctl field validity + * @scsw: pointer to scsw + * + * Return non-zero if the stctl field of the specified command mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_cmd_is_valid_stctl(union scsw *scsw) +{ + /* Only valid if pmcw.dnv == 1*/ + return 1; +} + +/** + * scsw_cmd_is_valid_dstat - check dstat field validity + * @scsw: pointer to scsw + * + * Return non-zero if the dstat field of the specified command mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_cmd_is_valid_dstat(union scsw *scsw) +{ + return (scsw->cmd.stctl & SCSW_STCTL_STATUS_PEND) && + (scsw->cmd.cc != 3); +} + +/** + * scsw_cmd_is_valid_cstat - check cstat field validity + * @scsw: pointer to scsw + * + * Return non-zero if the cstat field of the specified command mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_cmd_is_valid_cstat(union scsw *scsw) +{ + return (scsw->cmd.stctl & SCSW_STCTL_STATUS_PEND) && + (scsw->cmd.cc != 3); +} + +/** + * scsw_tm_is_valid_key - check key field validity + * @scsw: pointer to scsw + * + * Return non-zero if the key field of the specified transport mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_tm_is_valid_key(union scsw *scsw) +{ + return (scsw->tm.fctl & SCSW_FCTL_START_FUNC); +} + +/** + * scsw_tm_is_valid_eswf - check eswf field validity + * @scsw: pointer to scsw + * + * Return non-zero if the eswf field of the specified transport mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_tm_is_valid_eswf(union scsw *scsw) +{ + return (scsw->tm.stctl & SCSW_STCTL_STATUS_PEND); +} + +/** + * scsw_tm_is_valid_cc - check cc field validity + * @scsw: pointer to scsw + * + * Return non-zero if the cc field of the specified transport mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_tm_is_valid_cc(union scsw *scsw) +{ + return (scsw->tm.fctl & SCSW_FCTL_START_FUNC) && + (scsw->tm.stctl & SCSW_STCTL_STATUS_PEND); +} + +/** + * scsw_tm_is_valid_fmt - check fmt field validity + * @scsw: pointer to scsw + * + * Return non-zero if the fmt field of the specified transport mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_tm_is_valid_fmt(union scsw *scsw) +{ + return 1; +} + +/** + * scsw_tm_is_valid_x - check x field validity + * @scsw: pointer to scsw + * + * Return non-zero if the x field of the specified transport mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_tm_is_valid_x(union scsw *scsw) +{ + return 1; +} + +/** + * scsw_tm_is_valid_q - check q field validity + * @scsw: pointer to scsw + * + * Return non-zero if the q field of the specified transport mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_tm_is_valid_q(union scsw *scsw) +{ + return 1; +} + +/** + * scsw_tm_is_valid_ectl - check ectl field validity + * @scsw: pointer to scsw + * + * Return non-zero if the ectl field of the specified transport mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_tm_is_valid_ectl(union scsw *scsw) +{ + return (scsw->tm.stctl & SCSW_STCTL_STATUS_PEND) && + !(scsw->tm.stctl & SCSW_STCTL_INTER_STATUS) && + (scsw->tm.stctl & SCSW_STCTL_ALERT_STATUS); +} + +/** + * scsw_tm_is_valid_pno - check pno field validity + * @scsw: pointer to scsw + * + * Return non-zero if the pno field of the specified transport mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_tm_is_valid_pno(union scsw *scsw) +{ + return (scsw->tm.fctl != 0) && + (scsw->tm.stctl & SCSW_STCTL_STATUS_PEND) && + (!(scsw->tm.stctl & SCSW_STCTL_INTER_STATUS) || + ((scsw->tm.stctl & SCSW_STCTL_INTER_STATUS) && + (scsw->tm.actl & SCSW_ACTL_SUSPENDED))); +} + +/** + * scsw_tm_is_valid_fctl - check fctl field validity + * @scsw: pointer to scsw + * + * Return non-zero if the fctl field of the specified transport mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_tm_is_valid_fctl(union scsw *scsw) +{ + /* Only valid if pmcw.dnv == 1*/ + return 1; +} + +/** + * scsw_tm_is_valid_actl - check actl field validity + * @scsw: pointer to scsw + * + * Return non-zero if the actl field of the specified transport mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_tm_is_valid_actl(union scsw *scsw) +{ + /* Only valid if pmcw.dnv == 1*/ + return 1; +} + +/** + * scsw_tm_is_valid_stctl - check stctl field validity + * @scsw: pointer to scsw + * + * Return non-zero if the stctl field of the specified transport mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_tm_is_valid_stctl(union scsw *scsw) +{ + /* Only valid if pmcw.dnv == 1*/ + return 1; +} + +/** + * scsw_tm_is_valid_dstat - check dstat field validity + * @scsw: pointer to scsw + * + * Return non-zero if the dstat field of the specified transport mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_tm_is_valid_dstat(union scsw *scsw) +{ + return (scsw->tm.stctl & SCSW_STCTL_STATUS_PEND) && + (scsw->tm.cc != 3); +} + +/** + * scsw_tm_is_valid_cstat - check cstat field validity + * @scsw: pointer to scsw + * + * Return non-zero if the cstat field of the specified transport mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_tm_is_valid_cstat(union scsw *scsw) +{ + return (scsw->tm.stctl & SCSW_STCTL_STATUS_PEND) && + (scsw->tm.cc != 3); +} + +/** + * scsw_tm_is_valid_fcxs - check fcxs field validity + * @scsw: pointer to scsw + * + * Return non-zero if the fcxs field of the specified transport mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_tm_is_valid_fcxs(union scsw *scsw) +{ + return 1; +} + +/** + * scsw_tm_is_valid_schxs - check schxs field validity + * @scsw: pointer to scsw + * + * Return non-zero if the schxs field of the specified transport mode scsw is + * valid, zero otherwise. + */ +static inline int scsw_tm_is_valid_schxs(union scsw *scsw) +{ + return (scsw->tm.cstat & (SCHN_STAT_PROG_CHECK | + SCHN_STAT_INTF_CTRL_CHK | + SCHN_STAT_PROT_CHECK | + SCHN_STAT_CHN_DATA_CHK)); +} + +/** + * scsw_is_valid_actl - check actl field validity + * @scsw: pointer to scsw + * + * Return non-zero if the actl field of the specified scsw is valid, + * regardless of whether it is a transport mode or command mode scsw. + * Return zero if the field does not contain a valid value. + */ +static inline int scsw_is_valid_actl(union scsw *scsw) +{ + if (scsw_is_tm(scsw)) + return scsw_tm_is_valid_actl(scsw); + else + return scsw_cmd_is_valid_actl(scsw); +} + +/** + * scsw_is_valid_cc - check cc field validity + * @scsw: pointer to scsw + * + * Return non-zero if the cc field of the specified scsw is valid, + * regardless of whether it is a transport mode or command mode scsw. + * Return zero if the field does not contain a valid value. + */ +static inline int scsw_is_valid_cc(union scsw *scsw) +{ + if (scsw_is_tm(scsw)) + return scsw_tm_is_valid_cc(scsw); + else + return scsw_cmd_is_valid_cc(scsw); +} + +/** + * scsw_is_valid_cstat - check cstat field validity + * @scsw: pointer to scsw + * + * Return non-zero if the cstat field of the specified scsw is valid, + * regardless of whether it is a transport mode or command mode scsw. + * Return zero if the field does not contain a valid value. + */ +static inline int scsw_is_valid_cstat(union scsw *scsw) +{ + if (scsw_is_tm(scsw)) + return scsw_tm_is_valid_cstat(scsw); + else + return scsw_cmd_is_valid_cstat(scsw); +} + +/** + * scsw_is_valid_dstat - check dstat field validity + * @scsw: pointer to scsw + * + * Return non-zero if the dstat field of the specified scsw is valid, + * regardless of whether it is a transport mode or command mode scsw. + * Return zero if the field does not contain a valid value. + */ +static inline int scsw_is_valid_dstat(union scsw *scsw) +{ + if (scsw_is_tm(scsw)) + return scsw_tm_is_valid_dstat(scsw); + else + return scsw_cmd_is_valid_dstat(scsw); +} + +/** + * scsw_is_valid_ectl - check ectl field validity + * @scsw: pointer to scsw + * + * Return non-zero if the ectl field of the specified scsw is valid, + * regardless of whether it is a transport mode or command mode scsw. + * Return zero if the field does not contain a valid value. + */ +static inline int scsw_is_valid_ectl(union scsw *scsw) +{ + if (scsw_is_tm(scsw)) + return scsw_tm_is_valid_ectl(scsw); + else + return scsw_cmd_is_valid_ectl(scsw); +} + +/** + * scsw_is_valid_eswf - check eswf field validity + * @scsw: pointer to scsw + * + * Return non-zero if the eswf field of the specified scsw is valid, + * regardless of whether it is a transport mode or command mode scsw. + * Return zero if the field does not contain a valid value. + */ +static inline int scsw_is_valid_eswf(union scsw *scsw) +{ + if (scsw_is_tm(scsw)) + return scsw_tm_is_valid_eswf(scsw); + else + return scsw_cmd_is_valid_eswf(scsw); +} + +/** + * scsw_is_valid_fctl - check fctl field validity + * @scsw: pointer to scsw + * + * Return non-zero if the fctl field of the specified scsw is valid, + * regardless of whether it is a transport mode or command mode scsw. + * Return zero if the field does not contain a valid value. + */ +static inline int scsw_is_valid_fctl(union scsw *scsw) +{ + if (scsw_is_tm(scsw)) + return scsw_tm_is_valid_fctl(scsw); + else + return scsw_cmd_is_valid_fctl(scsw); +} + +/** + * scsw_is_valid_key - check key field validity + * @scsw: pointer to scsw + * + * Return non-zero if the key field of the specified scsw is valid, + * regardless of whether it is a transport mode or command mode scsw. + * Return zero if the field does not contain a valid value. + */ +static inline int scsw_is_valid_key(union scsw *scsw) +{ + if (scsw_is_tm(scsw)) + return scsw_tm_is_valid_key(scsw); + else + return scsw_cmd_is_valid_key(scsw); +} + +/** + * scsw_is_valid_pno - check pno field validity + * @scsw: pointer to scsw + * + * Return non-zero if the pno field of the specified scsw is valid, + * regardless of whether it is a transport mode or command mode scsw. + * Return zero if the field does not contain a valid value. + */ +static inline int scsw_is_valid_pno(union scsw *scsw) +{ + if (scsw_is_tm(scsw)) + return scsw_tm_is_valid_pno(scsw); + else + return scsw_cmd_is_valid_pno(scsw); +} + +/** + * scsw_is_valid_stctl - check stctl field validity + * @scsw: pointer to scsw + * + * Return non-zero if the stctl field of the specified scsw is valid, + * regardless of whether it is a transport mode or command mode scsw. + * Return zero if the field does not contain a valid value. + */ +static inline int scsw_is_valid_stctl(union scsw *scsw) +{ + if (scsw_is_tm(scsw)) + return scsw_tm_is_valid_stctl(scsw); + else + return scsw_cmd_is_valid_stctl(scsw); +} + +/** + * scsw_cmd_is_solicited - check for solicited scsw + * @scsw: pointer to scsw + * + * Return non-zero if the command mode scsw indicates that the associated + * status condition is solicited, zero if it is unsolicited. + */ +static inline int scsw_cmd_is_solicited(union scsw *scsw) +{ + return (scsw->cmd.cc != 0) || (scsw->cmd.stctl != + (SCSW_STCTL_STATUS_PEND | SCSW_STCTL_ALERT_STATUS)); +} + +/** + * scsw_tm_is_solicited - check for solicited scsw + * @scsw: pointer to scsw + * + * Return non-zero if the transport mode scsw indicates that the associated + * status condition is solicited, zero if it is unsolicited. + */ +static inline int scsw_tm_is_solicited(union scsw *scsw) +{ + return (scsw->tm.cc != 0) || (scsw->tm.stctl != + (SCSW_STCTL_STATUS_PEND | SCSW_STCTL_ALERT_STATUS)); +} + +/** + * scsw_is_solicited - check for solicited scsw + * @scsw: pointer to scsw + * + * Return non-zero if the transport or command mode scsw indicates that the + * associated status condition is solicited, zero if it is unsolicited. + */ +static inline int scsw_is_solicited(union scsw *scsw) +{ + if (scsw_is_tm(scsw)) + return scsw_tm_is_solicited(scsw); + else + return scsw_cmd_is_solicited(scsw); +} + +#endif /* _ASM_S390_SCSW_H_ */ diff --git a/arch/s390/include/asm/seccomp.h b/arch/s390/include/asm/seccomp.h new file mode 100644 index 00000000000..781a9cf9b00 --- /dev/null +++ b/arch/s390/include/asm/seccomp.h @@ -0,0 +1,16 @@ +#ifndef _ASM_S390_SECCOMP_H +#define _ASM_S390_SECCOMP_H + +#include <linux/unistd.h> + +#define __NR_seccomp_read __NR_read +#define __NR_seccomp_write __NR_write +#define __NR_seccomp_exit __NR_exit +#define __NR_seccomp_sigreturn __NR_sigreturn + +#define __NR_seccomp_read_32 __NR_read +#define __NR_seccomp_write_32 __NR_write +#define __NR_seccomp_exit_32 __NR_exit +#define __NR_seccomp_sigreturn_32 __NR_sigreturn + +#endif /* _ASM_S390_SECCOMP_H */ diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index e8bd6ac22c9..e37478e8728 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -8,12 +8,13 @@ #ifndef _ASM_S390_SETUP_H #define _ASM_S390_SETUP_H -#define COMMAND_LINE_SIZE 1024 +#define COMMAND_LINE_SIZE 4096 #define ARCH_COMMAND_LINE_SIZE 896 #ifdef __KERNEL__ +#include <asm/lowcore.h> #include <asm/types.h> #define PARMAREA 0x10400 @@ -63,7 +64,6 @@ extern unsigned int s390_noexec; /* * Machine features detected in head.S */ -extern unsigned long machine_flags; #define MACHINE_FLAG_VM (1UL << 0) #define MACHINE_FLAG_IEEE (1UL << 1) @@ -77,28 +77,28 @@ extern unsigned long machine_flags; #define MACHINE_FLAG_HPAGE (1UL << 10) #define MACHINE_FLAG_PFMF (1UL << 11) -#define MACHINE_IS_VM (machine_flags & MACHINE_FLAG_VM) -#define MACHINE_IS_KVM (machine_flags & MACHINE_FLAG_KVM) -#define MACHINE_HAS_DIAG9C (machine_flags & MACHINE_FLAG_DIAG9C) +#define MACHINE_IS_VM (S390_lowcore.machine_flags & MACHINE_FLAG_VM) +#define MACHINE_IS_KVM (S390_lowcore.machine_flags & MACHINE_FLAG_KVM) +#define MACHINE_HAS_DIAG9C (S390_lowcore.machine_flags & MACHINE_FLAG_DIAG9C) #ifndef __s390x__ -#define MACHINE_HAS_IEEE (machine_flags & MACHINE_FLAG_IEEE) -#define MACHINE_HAS_CSP (machine_flags & MACHINE_FLAG_CSP) +#define MACHINE_HAS_IEEE (S390_lowcore.machine_flags & MACHINE_FLAG_IEEE) +#define MACHINE_HAS_CSP (S390_lowcore.machine_flags & MACHINE_FLAG_CSP) #define MACHINE_HAS_IDTE (0) #define MACHINE_HAS_DIAG44 (1) -#define MACHINE_HAS_MVPG (machine_flags & MACHINE_FLAG_MVPG) +#define MACHINE_HAS_MVPG (S390_lowcore.machine_flags & MACHINE_FLAG_MVPG) #define MACHINE_HAS_MVCOS (0) #define MACHINE_HAS_HPAGE (0) #define MACHINE_HAS_PFMF (0) #else /* __s390x__ */ #define MACHINE_HAS_IEEE (1) #define MACHINE_HAS_CSP (1) -#define MACHINE_HAS_IDTE (machine_flags & MACHINE_FLAG_IDTE) -#define MACHINE_HAS_DIAG44 (machine_flags & MACHINE_FLAG_DIAG44) +#define MACHINE_HAS_IDTE (S390_lowcore.machine_flags & MACHINE_FLAG_IDTE) +#define MACHINE_HAS_DIAG44 (S390_lowcore.machine_flags & MACHINE_FLAG_DIAG44) #define MACHINE_HAS_MVPG (1) -#define MACHINE_HAS_MVCOS (machine_flags & MACHINE_FLAG_MVCOS) -#define MACHINE_HAS_HPAGE (machine_flags & MACHINE_FLAG_HPAGE) -#define MACHINE_HAS_PFMF (machine_flags & MACHINE_FLAG_PFMF) +#define MACHINE_HAS_MVCOS (S390_lowcore.machine_flags & MACHINE_FLAG_MVCOS) +#define MACHINE_HAS_HPAGE (S390_lowcore.machine_flags & MACHINE_FLAG_HPAGE) +#define MACHINE_HAS_PFMF (S390_lowcore.machine_flags & MACHINE_FLAG_PFMF) #endif /* __s390x__ */ #define ZFCPDUMP_HSA_SIZE (32UL<<20) diff --git a/arch/s390/include/asm/signal.h b/arch/s390/include/asm/signal.h index f6cfddb278c..cdf5cb2fe03 100644 --- a/arch/s390/include/asm/signal.h +++ b/arch/s390/include/asm/signal.h @@ -115,7 +115,7 @@ typedef unsigned long sigset_t; #define MINSIGSTKSZ 2048 #define SIGSTKSZ 8192 -#include <asm-generic/signal.h> +#include <asm-generic/signal-defs.h> #ifdef __KERNEL__ struct old_sigaction { diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h index 2009158a450..a868b272c25 100644 --- a/arch/s390/include/asm/smp.h +++ b/arch/s390/include/asm/smp.h @@ -51,32 +51,7 @@ extern void machine_power_off_smp(void); #define PROC_CHANGE_PENALTY 20 /* Schedule penalty */ #define raw_smp_processor_id() (S390_lowcore.cpu_nr) - -/* - * returns 1 if cpu is in stopped/check stopped state or not operational - * returns 0 otherwise - */ -static inline int -smp_cpu_not_running(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) - return 1; - break; - case sigp_not_operational: - return 1; - default: - break; - } - return 0; -} - -#define cpu_logical_map(cpu) (cpu) +#define cpu_logical_map(cpu) (cpu) extern int __cpu_disable (void); extern void __cpu_die (unsigned int cpu); @@ -87,19 +62,8 @@ extern struct mutex smp_cpu_state_mutex; extern int smp_cpu_polarization[]; extern void arch_send_call_function_single_ipi(int cpu); -extern void arch_send_call_function_ipi(cpumask_t mask); - -#endif - -#ifndef CONFIG_SMP -static inline void smp_send_stop(void) -{ - /* Disable all interrupts/machine checks */ - __load_psw_mask(psw_kernel_bits & ~PSW_MASK_MCHECK); -} +extern void arch_send_call_function_ipi_mask(const struct cpumask *mask); -#define hard_smp_processor_id() 0 -#define smp_cpu_not_running(cpu) 1 #endif #ifdef CONFIG_HOTPLUG_CPU diff --git a/arch/s390/include/asm/socket.h b/arch/s390/include/asm/socket.h index 02330c50241..fdff1e995c7 100644 --- a/arch/s390/include/asm/socket.h +++ b/arch/s390/include/asm/socket.h @@ -65,4 +65,9 @@ #define SO_TIMESTAMPING 37 #define SCM_TIMESTAMPING SO_TIMESTAMPING +#define SO_PROTOCOL 38 +#define SO_DOMAIN 39 + +#define SO_RXQ_OVFL 40 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h index df84ae96915..c9af0d19c7a 100644 --- a/arch/s390/include/asm/spinlock.h +++ b/arch/s390/include/asm/spinlock.h @@ -122,8 +122,10 @@ static inline void __raw_spin_unlock(raw_spinlock_t *lp) #define __raw_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); static inline void __raw_read_lock(raw_rwlock_t *rw) @@ -134,6 +136,14 @@ 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) +{ + unsigned int old; + old = rw->lock & 0x7fffffffU; + if (_raw_compare_and_swap(&rw->lock, old, old + 1) != old) + _raw_read_lock_wait_flags(rw, flags); +} + static inline void __raw_read_unlock(raw_rwlock_t *rw) { unsigned int old, cmp; @@ -151,6 +161,12 @@ static inline void __raw_write_lock(raw_rwlock_t *rw) _raw_write_lock_wait(rw); } +static inline void __raw_write_lock_flags(raw_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) { _raw_compare_and_swap(&rw->lock, 0x80000000, 0); diff --git a/arch/s390/include/asm/suspend.h b/arch/s390/include/asm/suspend.h index 1f34580e67a..dc75c616eaf 100644 --- a/arch/s390/include/asm/suspend.h +++ b/arch/s390/include/asm/suspend.h @@ -1,5 +1,10 @@ #ifndef __ASM_S390_SUSPEND_H #define __ASM_S390_SUSPEND_H +static inline int arch_prepare_suspend(void) +{ + return 0; +} + #endif diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h index 2429b87eb28..e0a73d3eb83 100644 --- a/arch/s390/include/asm/syscall.h +++ b/arch/s390/include/asm/syscall.h @@ -12,6 +12,7 @@ #ifndef _ASM_SYSCALL_H #define _ASM_SYSCALL_H 1 +#include <linux/sched.h> #include <asm/ptrace.h> static inline long syscall_get_nr(struct task_struct *task, diff --git a/arch/s390/include/asm/system.h b/arch/s390/include/asm/system.h index 3a8b26eb1f2..379661d2f81 100644 --- a/arch/s390/include/asm/system.h +++ b/arch/s390/include/asm/system.h @@ -1,11 +1,7 @@ /* - * include/asm-s390/system.h + * Copyright IBM Corp. 1999, 2009 * - * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation - * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), - * - * Derived from "include/asm-i386/system.h" + * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> */ #ifndef __ASM_SYSTEM_H @@ -113,11 +109,7 @@ extern void pfault_fini(void); #define pfault_fini() do { } while (0) #endif /* CONFIG_PFAULT */ -#ifdef CONFIG_PAGE_STATES extern void cmma_init(void); -#else -static inline void cmma_init(void) { } -#endif #define finish_arch_switch(prev) do { \ set_fs(current->thread.mm_segment); \ @@ -469,6 +461,20 @@ extern psw_t sysc_restore_trace_psw; extern psw_t io_restore_trace_psw; #endif +static inline int tprot(unsigned long addr) +{ + int rc = -EFAULT; + + asm volatile( + " tprot 0(%1),0\n" + "0: ipm %0\n" + " srl %0,28\n" + "1:\n" + EX_TABLE(0b,1b) + : "+d" (rc) : "a" (addr) : "cc"); + return rc; +} + #endif /* __KERNEL__ */ #endif diff --git a/arch/s390/include/asm/termios.h b/arch/s390/include/asm/termios.h index 67f66278f53..bc3a35cefc9 100644 --- a/arch/s390/include/asm/termios.h +++ b/arch/s390/include/asm/termios.h @@ -60,7 +60,7 @@ struct termio { #define user_termios_to_kernel_termios(k, u) copy_from_user(k, u, sizeof(struct termios2)) #define kernel_termios_to_user_termios(u, k) copy_to_user(u, k, sizeof(struct termios2)) -#include <asm-generic/termios.h> +#include <asm-generic/termios-base.h> #endif /* __KERNEL__ */ diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h index c544aa52453..07eb61b2fb3 100644 --- a/arch/s390/include/asm/thread_info.h +++ b/arch/s390/include/asm/thread_info.h @@ -31,8 +31,9 @@ #define ASYNC_SIZE (PAGE_SIZE << ASYNC_ORDER) #ifndef __ASSEMBLY__ -#include <asm/processor.h> #include <asm/lowcore.h> +#include <asm/page.h> +#include <asm/processor.h> /* * low level task data that entry.S needs immediate access to @@ -60,7 +61,7 @@ struct thread_info { .exec_domain = &default_exec_domain, \ .flags = 0, \ .cpu = 0, \ - .preempt_count = 1, \ + .preempt_count = INIT_PREEMPT_COUNT, \ .restart_block = { \ .fn = do_no_restart_syscall, \ }, \ @@ -82,14 +83,16 @@ static inline struct thread_info *current_thread_info(void) /* * thread information flags bit numbers */ -#define TIF_SYSCALL_TRACE 0 /* syscall trace active */ #define TIF_NOTIFY_RESUME 1 /* callback before returning to user */ #define TIF_SIGPENDING 2 /* signal pending */ #define TIF_NEED_RESCHED 3 /* rescheduling necessary */ #define TIF_RESTART_SVC 4 /* restart svc with new svc number */ -#define TIF_SYSCALL_AUDIT 5 /* syscall auditing active */ #define TIF_SINGLE_STEP 6 /* deliver sigtrap on return to user */ #define TIF_MCCK_PENDING 7 /* machine check handling is pending */ +#define TIF_SYSCALL_TRACE 8 /* syscall trace active */ +#define TIF_SYSCALL_AUDIT 9 /* syscall auditing active */ +#define TIF_SECCOMP 10 /* secure computing */ +#define TIF_SYSCALL_TRACEPOINT 11 /* syscall tracepoint instrumentation */ #define TIF_USEDFPU 16 /* FPU was used by this task this quantum (SMP) */ #define TIF_POLLING_NRFLAG 17 /* true if poll_idle() is polling TIF_NEED_RESCHED */ @@ -98,15 +101,17 @@ static inline struct thread_info *current_thread_info(void) #define TIF_RESTORE_SIGMASK 20 /* restore signal mask in do_signal() */ #define TIF_FREEZE 21 /* thread is freezing for suspend */ -#define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE) #define _TIF_NOTIFY_RESUME (1<<TIF_NOTIFY_RESUME) #define _TIF_RESTORE_SIGMASK (1<<TIF_RESTORE_SIGMASK) #define _TIF_SIGPENDING (1<<TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1<<TIF_NEED_RESCHED) #define _TIF_RESTART_SVC (1<<TIF_RESTART_SVC) -#define _TIF_SYSCALL_AUDIT (1<<TIF_SYSCALL_AUDIT) #define _TIF_SINGLE_STEP (1<<TIF_SINGLE_STEP) #define _TIF_MCCK_PENDING (1<<TIF_MCCK_PENDING) +#define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE) +#define _TIF_SYSCALL_AUDIT (1<<TIF_SYSCALL_AUDIT) +#define _TIF_SECCOMP (1<<TIF_SECCOMP) +#define _TIF_SYSCALL_TRACEPOINT (1<<TIF_SYSCALL_TRACEPOINT) #define _TIF_USEDFPU (1<<TIF_USEDFPU) #define _TIF_POLLING_NRFLAG (1<<TIF_POLLING_NRFLAG) #define _TIF_31BIT (1<<TIF_31BIT) diff --git a/arch/s390/include/asm/timer.h b/arch/s390/include/asm/timer.h index e4bcab739c1..814243cafdf 100644 --- a/arch/s390/include/asm/timer.h +++ b/arch/s390/include/asm/timer.h @@ -41,6 +41,7 @@ extern void init_virt_timer(struct vtimer_list *timer); extern void add_virt_timer(void *new); extern void add_virt_timer_periodic(void *new); extern int mod_virt_timer(struct vtimer_list *timer, __u64 expires); +extern int mod_virt_timer_periodic(struct vtimer_list *timer, __u64 expires); extern int del_virt_timer(struct vtimer_list *timer); extern void init_cpu_vtimer(void); diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h index d744c3d62de..68d9fea34b4 100644 --- a/arch/s390/include/asm/timex.h +++ b/arch/s390/include/asm/timex.h @@ -11,6 +11,9 @@ #ifndef _ASM_S390_TIMEX_H #define _ASM_S390_TIMEX_H +/* The value of the TOD clock for 1.1.1970. */ +#define TOD_UNIX_EPOCH 0x7d91048bca000000ULL + /* Inline functions for clock register access. */ static inline int set_clock(__u64 time) { @@ -85,4 +88,28 @@ int get_sync_clock(unsigned long long *clock); void init_cpu_timer(void); unsigned long long monotonic_clock(void); +void tod_to_timeval(__u64, struct timespec *); + +static inline +void stck_to_timespec(unsigned long long stck, struct timespec *ts) +{ + tod_to_timeval(stck - TOD_UNIX_EPOCH, ts); +} + +extern u64 sched_clock_base_cc; + +/** + * get_clock_monotonic - returns current time in clock rate units + * + * The caller must ensure that preemption is disabled. + * The clock and sched_clock_base get changed via stop_machine. + * Therefore preemption must be disabled when calling this + * function, otherwise the returned value is not guaranteed to + * be monotonic. + */ +static inline unsigned long long get_clock_monotonic(void) +{ + return get_clock_xt() - sched_clock_base_cc; +} + #endif diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index 3d8a96d39d9..81150b05368 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -96,7 +96,8 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) * pte_free_tlb frees a pte table and clears the CRSTE for the * page table from the tlb. */ -static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte) +static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, + unsigned long address) { if (!tlb->fullmm) { tlb->array[tlb->nr_ptes++] = pte; @@ -113,7 +114,8 @@ static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte) * as the pgd. pmd_free_tlb checks the asce_limit against 2GB * to avoid the double free of the pmd in this case. */ -static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) +static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, + unsigned long address) { #ifdef __s390x__ if (tlb->mm->context.asce_limit <= (1UL << 31)) @@ -134,7 +136,8 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) * as the pgd. pud_free_tlb checks the asce_limit against 4TB * to avoid the double free of the pud in this case. */ -static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud) +static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, + unsigned long address) { #ifdef __s390x__ if (tlb->mm->context.asce_limit <= (1UL << 42)) diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h index 5e0ad618dc4..6e7211abd95 100644 --- a/arch/s390/include/asm/topology.h +++ b/arch/s390/include/asm/topology.h @@ -9,7 +9,6 @@ const struct cpumask *cpu_coregroup_mask(unsigned int cpu); extern cpumask_t cpu_core_map[NR_CPUS]; -#define topology_core_siblings(cpu) (cpu_core_map[cpu]) #define topology_core_cpumask(cpu) (&cpu_core_map[cpu]) int topology_set_cpu_management(int fc); diff --git a/arch/s390/include/asm/types.h b/arch/s390/include/asm/types.h index 3dc3fc22881..04d6b95a89c 100644 --- a/arch/s390/include/asm/types.h +++ b/arch/s390/include/asm/types.h @@ -28,12 +28,6 @@ typedef __signed__ long saddr_t; */ #ifdef __KERNEL__ -#ifndef __s390x__ -#define BITS_PER_LONG 32 -#else -#define BITS_PER_LONG 64 -#endif - #ifndef __ASSEMBLY__ typedef u64 dma64_addr_t; diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h index 0235970278f..8377e91533d 100644 --- a/arch/s390/include/asm/uaccess.h +++ b/arch/s390/include/asm/uaccess.h @@ -131,7 +131,7 @@ static inline int __get_user_fn(size_t size, const void __user *ptr, void *x) #define put_user(x, ptr) \ ({ \ - might_sleep(); \ + might_fault(); \ __put_user(x, ptr); \ }) @@ -180,7 +180,7 @@ extern int __put_user_bad(void) __attribute__((noreturn)); #define get_user(x, ptr) \ ({ \ - might_sleep(); \ + might_fault(); \ __get_user(x, ptr); \ }) @@ -231,7 +231,7 @@ __copy_to_user(void __user *to, const void *from, unsigned long n) static inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n) { - might_sleep(); + might_fault(); if (access_ok(VERIFY_WRITE, to, n)) n = __copy_to_user(to, from, n); return n; @@ -282,7 +282,7 @@ __copy_from_user(void *to, const void __user *from, unsigned long n) static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { - might_sleep(); + might_fault(); if (access_ok(VERIFY_READ, from, n)) n = __copy_from_user(to, from, n); else @@ -299,7 +299,7 @@ __copy_in_user(void __user *to, const void __user *from, unsigned long n) static inline unsigned long __must_check copy_in_user(void __user *to, const void __user *from, unsigned long n) { - might_sleep(); + might_fault(); if (__access_ok(from,n) && __access_ok(to,n)) n = __copy_in_user(to, from, n); return n; @@ -312,7 +312,7 @@ static inline long __must_check strncpy_from_user(char *dst, const char __user *src, long count) { long res = -EFAULT; - might_sleep(); + might_fault(); if (access_ok(VERIFY_READ, src, 1)) res = uaccess.strncpy_from_user(count, src, dst); return res; @@ -321,7 +321,7 @@ strncpy_from_user(char *dst, const char __user *src, long count) static inline unsigned long strnlen_user(const char __user * src, unsigned long n) { - might_sleep(); + might_fault(); return uaccess.strnlen_user(n, src); } @@ -354,7 +354,7 @@ __clear_user(void __user *to, unsigned long n) static inline unsigned long __must_check clear_user(void __user *to, unsigned long n) { - might_sleep(); + might_fault(); if (access_ok(VERIFY_WRITE, to, n)) n = uaccess.clear_user(n, to); return n; diff --git a/arch/s390/include/asm/ucontext.h b/arch/s390/include/asm/ucontext.h index d69bec0b03f..cfb874e66c9 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 c8ad350d144..cb5232df151 100644 --- a/arch/s390/include/asm/unistd.h +++ b/arch/s390/include/asm/unistd.h @@ -265,7 +265,11 @@ #define __NR_pipe2 325 #define __NR_dup3 326 #define __NR_epoll_create1 327 -#define NR_syscalls 328 +#define __NR_preadv 328 +#define __NR_pwritev 329 +#define __NR_rt_tgsigqueueinfo 330 +#define __NR_perf_event_open 331 +#define NR_syscalls 332 /* * 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 228e3105ded..c7be8e10b87 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -3,8 +3,9 @@ # ifdef CONFIG_FUNCTION_TRACER -# Do not trace early boot code +# Don't trace early setup code and tracing code CFLAGS_REMOVE_early.o = -pg +CFLAGS_REMOVE_ftrace.o = -pg endif # @@ -22,7 +23,7 @@ CFLAGS_sysinfo.o += -Iinclude/math-emu -Iarch/s390/math-emu -w obj-y := bitmap.o traps.o time.o process.o base.o early.o setup.o \ processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o \ s390_ext.o debug.o irq.o ipl.o dis.o diag.o mem_detect.o \ - vdso.o vtime.o sysinfo.o nmi.o + vdso.o vtime.o sysinfo.o nmi.o sclp.o obj-y += $(if $(CONFIG_64BIT),entry64.o,entry.o) obj-y += $(if $(CONFIG_64BIT),reipl64.o,reipl.o) @@ -31,7 +32,7 @@ extra-y += head.o init_task.o vmlinux.lds obj-$(CONFIG_MODULES) += s390_ksyms.o module.o obj-$(CONFIG_SMP) += smp.o topology.o - +obj-$(CONFIG_HIBERNATION) += suspend.o swsusp_asm64.o obj-$(CONFIG_AUDIT) += audit.o compat-obj-$(CONFIG_AUDIT) += compat_audit.o obj-$(CONFIG_COMPAT) += compat_linux.o compat_signal.o \ @@ -40,7 +41,9 @@ obj-$(CONFIG_COMPAT) += compat_linux.o compat_signal.o \ obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-$(CONFIG_KPROBES) += kprobes.o -obj-$(CONFIG_FUNCTION_TRACER) += mcount.o +obj-$(CONFIG_FUNCTION_TRACER) += $(if $(CONFIG_64BIT),mcount64.o,mcount.o) +obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o +obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o # Kexec part S390_KEXEC_OBJS := machine_kexec.o crash.o diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 67a60016bab..63e46433e81 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -7,6 +7,7 @@ #include <linux/sched.h> #include <linux/kbuild.h> #include <asm/vdso.h> +#include <asm/sigp.h> int main(void) { @@ -27,6 +28,8 @@ int main(void) DEFINE(__TI_flags, offsetof(struct thread_info, flags)); DEFINE(__TI_cpu, offsetof(struct thread_info, cpu)); DEFINE(__TI_precount, offsetof(struct thread_info, preempt_count)); + DEFINE(__TI_user_timer, offsetof(struct thread_info, user_timer)); + DEFINE(__TI_system_timer, offsetof(struct thread_info, system_timer)); BLANK(); DEFINE(__PT_ARGS, offsetof(struct pt_regs, args)); DEFINE(__PT_PSW, offsetof(struct pt_regs, psw)); @@ -57,6 +60,10 @@ int main(void) DEFINE(CLOCK_REALTIME, CLOCK_REALTIME); DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC); DEFINE(CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC); - + /* constants for SIGP */ + DEFINE(__SIGP_STOP, sigp_stop); + DEFINE(__SIGP_RESTART, sigp_restart); + DEFINE(__SIGP_SENSE, sigp_sense); + DEFINE(__SIGP_INITIAL_CPU_RESET, sigp_initial_cpu_reset); return 0; } diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 6cc87d8c868..fda1a8123f9 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -24,7 +24,6 @@ #include <linux/signal.h> #include <linux/resource.h> #include <linux/times.h> -#include <linux/utsname.h> #include <linux/smp.h> #include <linux/smp_lock.h> #include <linux/sem.h> @@ -443,69 +442,28 @@ sys32_rt_sigqueueinfo(int pid, int sig, compat_siginfo_t __user *uinfo) * sys32_execve() executes a new program after the asm stub has set * things up for us. This should basically do what I want it to. */ -asmlinkage long sys32_execve(void) +asmlinkage long sys32_execve(char __user *name, compat_uptr_t __user *argv, + compat_uptr_t __user *envp) { struct pt_regs *regs = task_pt_regs(current); char *filename; - unsigned long result; - int rc; - - filename = getname(compat_ptr(regs->orig_gpr2)); - if (IS_ERR(filename)) { - result = PTR_ERR(filename); - goto out; - } - rc = compat_do_execve(filename, compat_ptr(regs->gprs[3]), - compat_ptr(regs->gprs[4]), regs); - if (rc) { - result = rc; - goto out_putname; - } - task_lock(current); - current->ptrace &= ~PT_DTRACE; - task_unlock(current); + long rc; + + filename = getname(name); + rc = PTR_ERR(filename); + if (IS_ERR(filename)) + return rc; + rc = compat_do_execve(filename, argv, envp, regs); + if (rc) + goto out; current->thread.fp_regs.fpc=0; asm volatile("sfpc %0,0" : : "d" (0)); - result = regs->gprs[2]; -out_putname: - putname(filename); + rc = regs->gprs[2]; out: - return result; -} - - -#ifdef CONFIG_MODULES - -asmlinkage long -sys32_init_module(void __user *umod, unsigned long len, - const char __user *uargs) -{ - return sys_init_module(umod, len, uargs); -} - -asmlinkage long -sys32_delete_module(const char __user *name_user, unsigned int flags) -{ - return sys_delete_module(name_user, flags); + putname(filename); + return rc; } -#else /* CONFIG_MODULES */ - -asmlinkage long -sys32_init_module(void __user *umod, unsigned long len, - const char __user *uargs) -{ - return -ENOSYS; -} - -asmlinkage long -sys32_delete_module(const char __user *name_user, unsigned int flags) -{ - return -ENOSYS; -} - -#endif /* CONFIG_MODULES */ - asmlinkage long sys32_pread64(unsigned int fd, char __user *ubuf, size_t count, u32 poshi, u32 poslo) { @@ -569,59 +527,6 @@ 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; @@ -702,20 +607,12 @@ asmlinkage long sys32_fstatat64(unsigned int dfd, char __user *filename, struct stat64_emu31 __user* statbuf, int flag) { struct kstat stat; - int error = -EINVAL; - - if ((flag & ~AT_SYMLINK_NOFOLLOW) != 0) - goto out; - - if (flag & AT_SYMLINK_NOFOLLOW) - error = vfs_lstat_fd(dfd, filename, &stat); - else - error = vfs_stat_fd(dfd, filename, &stat); + int error; - if (!error) - error = cp_stat64(statbuf, &stat); -out: - return error; + error = vfs_fstatat(dfd, filename, &stat, flag); + if (error) + return error; + return cp_stat64(statbuf, &stat); } /* @@ -812,23 +709,6 @@ asmlinkage long sys32_write(unsigned int fd, char __user * buf, size_t count) return sys_write(fd, buf, count); } -asmlinkage long sys32_clone(void) -{ - struct pt_regs *regs = task_pt_regs(current); - unsigned long clone_flags; - unsigned long newsp; - int __user *parent_tidptr, *child_tidptr; - - clone_flags = regs->gprs[3] & 0xffffffffUL; - newsp = regs->orig_gpr2 & 0x7fffffffUL; - parent_tidptr = compat_ptr(regs->gprs[4]); - child_tidptr = compat_ptr(regs->gprs[5]); - if (!newsp) - newsp = regs->gprs[15]; - return do_fork(clone_flags, newsp, regs, 0, - parent_tidptr, child_tidptr); -} - /* * 31 bit emulation wrapper functions for sys_fadvise64/fadvise64_64. * These need to rewrite the advise values for POSIX_FADV_{DONTNEED,NOREUSE} diff --git a/arch/s390/kernel/compat_linux.h b/arch/s390/kernel/compat_linux.h index 836a2884290..45e9092b3aa 100644 --- a/arch/s390/kernel/compat_linux.h +++ b/arch/s390/kernel/compat_linux.h @@ -162,7 +162,6 @@ 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; @@ -198,7 +197,8 @@ long sys32_rt_sigprocmask(int how, compat_sigset_t __user *set, compat_sigset_t __user *oset, size_t sigsetsize); long sys32_rt_sigpending(compat_sigset_t __user *set, size_t sigsetsize); long sys32_rt_sigqueueinfo(int pid, int sig, compat_siginfo_t __user *uinfo); -long sys32_execve(void); +long sys32_execve(char __user *name, compat_uptr_t __user *argv, + compat_uptr_t __user *envp); long sys32_init_module(void __user *umod, unsigned long len, const char __user *uargs); long sys32_delete_module(const char __user *name_user, unsigned int flags); @@ -211,7 +211,6 @@ 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); @@ -222,7 +221,6 @@ unsigned long old32_mmap(struct mmap_arg_struct_emu31 __user *arg); long sys32_mmap2(struct mmap_arg_struct_emu31 __user *arg); long sys32_read(unsigned int fd, char __user * buf, size_t count); long sys32_write(unsigned int fd, char __user * buf, size_t count); -long sys32_clone(void); long sys32_fadvise64(int fd, loff_t offset, size_t len, int advise); long sys32_fadvise64_64(struct fadvise64_64_args __user *args); long sys32_sigaction(int sig, const struct old_sigaction32 __user *act, diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c index b537cb0e9b5..eee999853a7 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 87cf5a79a35..30de2d0e52b 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 @@ -568,18 +568,18 @@ compat_sys_sigprocmask_wrapper: llgtr %r4,%r4 # compat_old_sigset_t * jg compat_sys_sigprocmask # branch to system call - .globl sys32_init_module_wrapper -sys32_init_module_wrapper: + .globl sys_init_module_wrapper +sys_init_module_wrapper: llgtr %r2,%r2 # void * llgfr %r3,%r3 # unsigned long llgtr %r4,%r4 # char * - jg sys32_init_module # branch to system call + jg sys_init_module # branch to system call - .globl sys32_delete_module_wrapper -sys32_delete_module_wrapper: + .globl sys_delete_module_wrapper +sys_delete_module_wrapper: llgtr %r2,%r2 # const char * llgfr %r3,%r3 # unsigned int - jg sys32_delete_module # branch to system call + jg sys_delete_module # branch to system call .globl sys32_quotactl_wrapper sys32_quotactl_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: @@ -1805,3 +1803,53 @@ compat_sys_keyctl_wrapper: llgfr %r5,%r5 # u32 llgfr %r6,%r6 # u32 jg compat_sys_keyctl # branch to system call + + .globl compat_sys_preadv_wrapper +compat_sys_preadv_wrapper: + llgfr %r2,%r2 # unsigned long + llgtr %r3,%r3 # compat_iovec * + llgfr %r4,%r4 # unsigned long + llgfr %r5,%r5 # u32 + llgfr %r6,%r6 # u32 + jg compat_sys_preadv # branch to system call + + .globl compat_sys_pwritev_wrapper +compat_sys_pwritev_wrapper: + llgfr %r2,%r2 # unsigned long + llgtr %r3,%r3 # compat_iovec * + llgfr %r4,%r4 # unsigned long + llgfr %r5,%r5 # u32 + llgfr %r6,%r6 # u32 + jg compat_sys_pwritev # branch to system call + + .globl compat_sys_rt_tgsigqueueinfo_wrapper +compat_sys_rt_tgsigqueueinfo_wrapper: + lgfr %r2,%r2 # compat_pid_t + lgfr %r3,%r3 # compat_pid_t + lgfr %r4,%r4 # int + llgtr %r5,%r5 # struct compat_siginfo * + jg compat_sys_rt_tgsigqueueinfo_wrapper # branch to system call + + .globl sys_perf_event_open_wrapper +sys_perf_event_open_wrapper: + llgtr %r2,%r2 # const struct perf_event_attr * + lgfr %r3,%r3 # pid_t + lgfr %r4,%r4 # int + lgfr %r5,%r5 # int + llgfr %r6,%r6 # unsigned long + jg sys_perf_event_open # branch to system call + + .globl sys_clone_wrapper +sys_clone_wrapper: + llgfr %r2,%r2 # unsigned long + llgfr %r3,%r3 # unsigned long + llgtr %r4,%r4 # int * + llgtr %r5,%r5 # int * + jg sys_clone # branch to system call + + .globl sys32_execve_wrapper +sys32_execve_wrapper: + llgtr %r2,%r2 # char * + llgtr %r3,%r3 # compat_uptr_t * + llgtr %r4,%r4 # compat_uptr_t * + jg sys32_execve # branch to system call diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index be8bceaf37d..071c81f179e 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -63,8 +63,6 @@ typedef struct } debug_sprintf_entry_t; -extern void tod_to_timeval(uint64_t todval, struct timespec *xtime); - /* internal function prototyes */ static int debug_init(void); @@ -883,11 +881,11 @@ static int debug_active=1; * if debug_active is already off */ static int -s390dbf_procactive(ctl_table *table, int write, struct file *filp, +s390dbf_procactive(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { if (!write || debug_stoppable || !debug_active) - return proc_dointvec(table, write, filp, buffer, lenp, ppos); + return proc_dointvec(table, write, buffer, lenp, ppos); else return 0; } @@ -895,35 +893,30 @@ s390dbf_procactive(ctl_table *table, int write, struct file *filp, 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; @@ -1450,17 +1443,13 @@ debug_dflt_header_fn(debug_info_t * id, struct debug_view *view, int area, debug_entry_t * entry, char *out_buf) { struct timespec time_spec; - unsigned long long time; char *except_str; unsigned long caller; int rc = 0; unsigned int level; level = entry->id.fields.level; - time = entry->id.stck; - /* adjust todclock to 1970 */ - time -= 0x8126d60e46000000LL - (0x3c26700LL * 1000000 * 4096); - tod_to_timeval(time, &time_spec); + stck_to_timespec(entry->id.stck, &time_spec); if (entry->id.fields.exception) except_str = "*"; diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c index d2f270c995d..db943a7ec51 100644 --- a/arch/s390/kernel/dis.c +++ b/arch/s390/kernel/dis.c @@ -15,7 +15,6 @@ #include <linux/timer.h> #include <linux/mm.h> #include <linux/smp.h> -#include <linux/smp_lock.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/delay.h> diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 4d221c81c84..e49e9e0c69f 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -1,20 +1,25 @@ /* * arch/s390/kernel/early.c * - * Copyright IBM Corp. 2007 + * Copyright IBM Corp. 2007, 2009 * Author(s): Hongjie Yang <hongjie@us.ibm.com>, * Heiko Carstens <heiko.carstens@de.ibm.com> */ +#define KMSG_COMPONENT "setup" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include <linux/compiler.h> #include <linux/init.h> #include <linux/errno.h> #include <linux/string.h> #include <linux/ctype.h> +#include <linux/ftrace.h> #include <linux/lockdep.h> #include <linux/module.h> #include <linux/pfn.h> #include <linux/uaccess.h> +#include <linux/kernel.h> #include <asm/ebcdic.h> #include <asm/ipl.h> #include <asm/lowcore.h> @@ -36,6 +41,22 @@ char kernel_nss_name[NSS_NAME_SIZE + 1]; static void __init setup_boot_command_line(void); +/* + * Get the TOD clock running. + */ +static void __init reset_tod_clock(void) +{ + u64 time; + + if (store_clock(&time) == 0) + return; + /* TOD clock not running. Set the clock to Unix Epoch. */ + if (set_clock(TOD_UNIX_EPOCH) != 0 || store_clock(&time) != 0) + disabled_wait(0); + + sched_clock_base_cc = TOD_UNIX_EPOCH; + S390_lowcore.last_update_clock = sched_clock_base_cc; +} #ifdef CONFIG_SHARED_KERNEL int __init savesys_ipl_nss(char *cmd, const int cmdlen); @@ -63,6 +84,8 @@ asm( " br 14\n" " .size savesys_ipl_nss, .-savesys_ipl_nss\n"); +static __initdata char upper_command_line[COMMAND_LINE_SIZE]; + static noinline __init void create_kernel_nss(void) { unsigned int i, stext_pfn, eshared_pfn, end_pfn, min_size; @@ -72,7 +95,6 @@ static noinline __init void create_kernel_nss(void) int response; size_t len; char *savesys_ptr; - char upper_command_line[COMMAND_LINE_SIZE]; char defsys_cmd[DEFSYS_CMD_SIZE]; char savesys_cmd[SAVESYS_CMD_SIZE]; @@ -123,6 +145,8 @@ static noinline __init void create_kernel_nss(void) __cpcmd(defsys_cmd, NULL, 0, &response); if (response != 0) { + pr_err("Defining the Linux kernel NSS failed with rc=%d\n", + response); kernel_nss_name[0] = '\0'; return; } @@ -135,12 +159,23 @@ static noinline __init void create_kernel_nss(void) * max SAVESYS_CMD_SIZE * On error: response contains the numeric portion of cp error message. * for SAVESYS it will be >= 263 + * for missing privilege class, it will be 1 */ - if (response > SAVESYS_CMD_SIZE) { + if (response > SAVESYS_CMD_SIZE || response == 1) { + pr_err("Saving the Linux kernel NSS failed with rc=%d\n", + response); kernel_nss_name[0] = '\0'; 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(); @@ -187,9 +222,9 @@ static noinline __init void detect_machine_type(void) /* Running under KVM? If not we assume z/VM */ if (!memcmp(vmms.vm[0].cpi, "\xd2\xe5\xd4", 3)) - machine_flags |= MACHINE_FLAG_KVM; + S390_lowcore.machine_flags |= MACHINE_FLAG_KVM; else - machine_flags |= MACHINE_FLAG_VM; + S390_lowcore.machine_flags |= MACHINE_FLAG_VM; } static __init void early_pgm_check_handler(void) @@ -224,7 +259,7 @@ static noinline __init void setup_hpage(void) facilities = stfl(); if (!(facilities & (1UL << 23)) || !(facilities & (1UL << 29))) return; - machine_flags |= MACHINE_FLAG_HPAGE; + S390_lowcore.machine_flags |= MACHINE_FLAG_HPAGE; __ctl_set_bit(0, 23); #endif } @@ -242,7 +277,7 @@ static __init void detect_mvpg(void) EX_TABLE(0b,1b) : "=d" (rc) : "0" (-EOPNOTSUPP), "a" (0) : "memory", "cc", "0"); if (!rc) - machine_flags |= MACHINE_FLAG_MVPG; + S390_lowcore.machine_flags |= MACHINE_FLAG_MVPG; #endif } @@ -258,7 +293,7 @@ static __init void detect_ieee(void) EX_TABLE(0b,1b) : "=d" (rc), "=d" (tmp): "0" (-EOPNOTSUPP) : "cc"); if (!rc) - machine_flags |= MACHINE_FLAG_IEEE; + S390_lowcore.machine_flags |= MACHINE_FLAG_IEEE; #endif } @@ -277,7 +312,7 @@ static __init void detect_csp(void) EX_TABLE(0b,1b) : "=d" (rc) : "0" (-EOPNOTSUPP) : "cc", "0", "1", "2"); if (!rc) - machine_flags |= MACHINE_FLAG_CSP; + S390_lowcore.machine_flags |= MACHINE_FLAG_CSP; #endif } @@ -294,7 +329,7 @@ static __init void detect_diag9c(void) EX_TABLE(0b,1b) : "=d" (rc) : "0" (-EOPNOTSUPP), "d" (cpu_address) : "cc"); if (!rc) - machine_flags |= MACHINE_FLAG_DIAG9C; + S390_lowcore.machine_flags |= MACHINE_FLAG_DIAG9C; } static __init void detect_diag44(void) @@ -309,7 +344,7 @@ static __init void detect_diag44(void) EX_TABLE(0b,1b) : "=d" (rc) : "0" (-EOPNOTSUPP) : "cc"); if (!rc) - machine_flags |= MACHINE_FLAG_DIAG44; + S390_lowcore.machine_flags |= MACHINE_FLAG_DIAG44; #endif } @@ -320,11 +355,11 @@ static __init void detect_machine_facilities(void) facilities = stfl(); if (facilities & (1 << 28)) - machine_flags |= MACHINE_FLAG_IDTE; + S390_lowcore.machine_flags |= MACHINE_FLAG_IDTE; if (facilities & (1 << 23)) - machine_flags |= MACHINE_FLAG_PFMF; + S390_lowcore.machine_flags |= MACHINE_FLAG_PFMF; if (facilities & (1 << 4)) - machine_flags |= MACHINE_FLAG_MVCOS; + S390_lowcore.machine_flags |= MACHINE_FLAG_MVCOS; #endif } @@ -346,21 +381,35 @@ static __init void rescue_initrd(void) } /* Set up boot command line */ -static void __init setup_boot_command_line(void) +static void __init append_to_cmdline(size_t (*ipl_data)(char *, size_t)) { - char *parm = NULL; + char *parm, *delim; + size_t rc, len; + + len = strlen(boot_command_line); + + delim = boot_command_line + len; /* '\0' character position */ + parm = boot_command_line + len + 1; /* append right after '\0' */ + + rc = ipl_data(parm, COMMAND_LINE_SIZE - len - 1); + if (rc) { + if (*parm == '=') + memmove(boot_command_line, parm + 1, rc); + else + *delim = ' '; /* replace '\0' with space */ + } +} +static void __init setup_boot_command_line(void) +{ /* copy arch command line */ strlcpy(boot_command_line, COMMAND_LINE, ARCH_COMMAND_LINE_SIZE); /* append IPL PARM data to the boot command line */ - if (MACHINE_IS_VM) { - parm = boot_command_line + strlen(boot_command_line); - *parm++ = ' '; - get_ipl_vmparm(parm); - if (parm[0] == '=') - memmove(boot_command_line, parm + 1, strlen(parm)); - } + if (MACHINE_IS_VM) + append_to_cmdline(append_ipl_vmparm); + + append_to_cmdline(append_ipl_scpdata); } @@ -370,6 +419,7 @@ static void __init setup_boot_command_line(void) */ void __init startup_init(void) { + reset_tod_clock(); ipl_save_parameters(); rescue_initrd(); clear_bss_section(); @@ -391,5 +441,8 @@ void __init startup_init(void) setup_hpage(); sclp_facilities_detect(); detect_memory_layout(memory_chunk); +#ifdef CONFIG_DYNAMIC_FTRACE + S390_lowcore.ftrace_func = (unsigned long)ftrace_caller; +#endif lockdep_on(); } diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 1268aa2991b..48215d15762 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -53,6 +53,8 @@ _TIF_WORK_SVC = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ _TIF_MCCK_PENDING | _TIF_RESTART_SVC | _TIF_SINGLE_STEP ) _TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ _TIF_MCCK_PENDING) +_TIF_SYSCALL = (_TIF_SYSCALL_TRACE>>8 | _TIF_SYSCALL_AUDIT>>8 | \ + _TIF_SECCOMP>>8 | _TIF_SYSCALL_TRACEPOINT>>8) STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER STACK_SIZE = 1 << STACK_SHIFT @@ -265,7 +267,7 @@ sysc_do_restart: sth %r7,SP_SVCNR(%r15) sll %r7,2 # svc number *4 l %r8,BASED(.Lsysc_table) - tm __TI_flags+3(%r9),(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT) + tm __TI_flags+2(%r9),_TIF_SYSCALL l %r8,0(%r7,%r8) # get system call addr. bnz BASED(sysc_tracesys) basr %r14,%r8 # call sys_xxxx @@ -276,7 +278,8 @@ sysc_return: bnz BASED(sysc_work) # there is work to do (signals etc.) sysc_restore: #ifdef CONFIG_TRACE_IRQFLAGS - la %r1,BASED(sysc_restore_trace_psw) + la %r1,BASED(sysc_restore_trace_psw_addr) + l %r1,0(%r1) lpsw 0(%r1) sysc_restore_trace: TRACE_IRQS_CHECK @@ -287,10 +290,15 @@ sysc_leave: sysc_done: #ifdef CONFIG_TRACE_IRQFLAGS +sysc_restore_trace_psw_addr: + .long sysc_restore_trace_psw + + .section .data,"aw",@progbits .align 8 .globl sysc_restore_trace_psw sysc_restore_trace_psw: .long 0, sysc_restore_trace + 0x80000000 + .previous #endif # @@ -405,7 +413,7 @@ sysc_tracego: basr %r14,%r8 # call sys_xxx st %r2,SP_R2(%r15) # store return value sysc_tracenogo: - tm __TI_flags+3(%r9),(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT) + tm __TI_flags+2(%r9),_TIF_SYSCALL bz BASED(sysc_return) l %r1,BASED(.Ltrace_exit) la %r2,SP_PTREGS(%r15) # load pt_regs @@ -557,10 +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 @@ -604,7 +612,8 @@ io_return: bnz BASED(io_work) # there is work to do (signals etc.) io_restore: #ifdef CONFIG_TRACE_IRQFLAGS - la %r1,BASED(io_restore_trace_psw) + la %r1,BASED(io_restore_trace_psw_addr) + l %r1,0(%r1) lpsw 0(%r1) io_restore_trace: TRACE_IRQS_CHECK @@ -615,10 +624,15 @@ io_leave: io_done: #ifdef CONFIG_TRACE_IRQFLAGS +io_restore_trace_psw_addr: + .long io_restore_trace_psw + + .section .data,"aw",@progbits .align 8 .globl io_restore_trace_psw io_restore_trace_psw: .long 0, io_restore_trace + 0x80000000 + .previous #endif # @@ -837,16 +851,29 @@ mcck_return: __CPUINIT .globl restart_int_handler restart_int_handler: + basr %r1,0 +restart_base: + spt restart_vtime-restart_base(%r1) + stck __LC_LAST_UPDATE_CLOCK + mvc __LC_LAST_UPDATE_TIMER(8),restart_vtime-restart_base(%r1) + mvc __LC_EXIT_TIMER(8),restart_vtime-restart_base(%r1) l %r15,__LC_SAVE_AREA+60 # load ksp lctl %c0,%c15,__LC_CREGS_SAVE_AREA # get new ctl regs lam %a0,%a15,__LC_AREGS_SAVE_AREA lm %r6,%r15,__SF_GPRS(%r15) # load registers from clone + l %r1,__LC_THREAD_INFO + mvc __LC_USER_TIMER(8),__TI_user_timer(%r1) + mvc __LC_SYSTEM_TIMER(8),__TI_system_timer(%r1) + xc __LC_STEAL_TIMER(8),__LC_STEAL_TIMER stosm __SF_EMPTY(%r15),0x04 # now we can turn dat on basr %r14,0 l %r14,restart_addr-.(%r14) br %r14 # branch to start_secondary restart_addr: .long start_secondary + .align 8 +restart_vtime: + .long 0x7fffffff,0xffffffff .previous #else /* @@ -1094,6 +1121,7 @@ cleanup_io_leave_insn: .section .rodata, "a" #define SYSCALL(esa,esame,emu) .long esa + .globl sys_call_table sys_call_table: #include "syscalls.S" #undef SYSCALL diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index 950c59c6688..e1e5e767ab5 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -42,10 +42,12 @@ long sys_s390_fadvise64_64(struct fadvise64_64_args __user *args); long sys_s390_fallocate(int fd, int mode, loff_t offset, u32 len_high, u32 len_low); long sys_fork(void); -long sys_clone(void); +long sys_clone(unsigned long newsp, unsigned long clone_flags, + int __user *parent_tidptr, int __user *child_tidptr); long sys_vfork(void); void execve_tail(void); -long sys_execve(void); +long sys_execve(char __user *name, char __user * __user *argv, + char __user * __user *envp); long sys_sigsuspend(int history0, int history1, old_sigset_t mask); long sys_sigaction(int sig, const struct old_sigaction __user *act, struct old_sigaction __user *oact); diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S index c6fbde13971..9aff1d449b6 100644 --- a/arch/s390/kernel/entry64.S +++ b/arch/s390/kernel/entry64.S @@ -56,6 +56,8 @@ _TIF_WORK_SVC = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ _TIF_MCCK_PENDING | _TIF_RESTART_SVC | _TIF_SINGLE_STEP ) _TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ _TIF_MCCK_PENDING) +_TIF_SYSCALL = (_TIF_SYSCALL_TRACE>>8 | _TIF_SYSCALL_AUDIT>>8 | \ + _TIF_SECCOMP>>8 | _TIF_SYSCALL_TRACEPOINT>>8) #define BASED(name) name-system_call(%r13) @@ -260,7 +262,7 @@ sysc_do_restart: larl %r10,sys_call_table_emu # use 31 bit emulation system calls sysc_noemu: #endif - tm __TI_flags+7(%r9),(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT) + tm __TI_flags+6(%r9),_TIF_SYSCALL lgf %r8,0(%r7,%r10) # load address of system call routine jnz sysc_tracesys basr %r14,%r8 # call sys_xxxx @@ -282,10 +284,12 @@ sysc_leave: sysc_done: #ifdef CONFIG_TRACE_IRQFLAGS + .section .data,"aw",@progbits .align 8 .globl sysc_restore_trace_psw sysc_restore_trace_psw: .quad 0, sysc_restore_trace + .previous #endif # @@ -391,7 +395,7 @@ sysc_tracego: basr %r14,%r8 # call sys_xxx stg %r2,SP_R2(%r15) # store return value sysc_tracenogo: - tm __TI_flags+7(%r9),(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT) + tm __TI_flags+6(%r9),_TIF_SYSCALL jz sysc_return la %r2,SP_PTREGS(%r15) # load pt_regs larl %r14,sysc_return # return point is sysc_return @@ -539,10 +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 @@ -593,10 +597,12 @@ io_leave: io_done: #ifdef CONFIG_TRACE_IRQFLAGS + .section .data,"aw",@progbits .align 8 .globl io_restore_trace_psw io_restore_trace_psw: .quad 0, io_restore_trace + .previous #endif # @@ -831,14 +837,27 @@ mcck_return: __CPUINIT .globl restart_int_handler restart_int_handler: + basr %r1,0 +restart_base: + spt restart_vtime-restart_base(%r1) + stck __LC_LAST_UPDATE_CLOCK + mvc __LC_LAST_UPDATE_TIMER(8),restart_vtime-restart_base(%r1) + mvc __LC_EXIT_TIMER(8),restart_vtime-restart_base(%r1) lg %r15,__LC_SAVE_AREA+120 # load ksp lghi %r10,__LC_CREGS_SAVE_AREA lctlg %c0,%c15,0(%r10) # get new ctl regs lghi %r10,__LC_AREGS_SAVE_AREA lam %a0,%a15,0(%r10) lmg %r6,%r15,__SF_GPRS(%r15) # load registers from clone + lg %r1,__LC_THREAD_INFO + mvc __LC_USER_TIMER(8),__TI_user_timer(%r1) + mvc __LC_SYSTEM_TIMER(8),__TI_system_timer(%r1) + xc __LC_STEAL_TIMER(8),__LC_STEAL_TIMER stosm __SF_EMPTY(%r15),0x04 # now we can turn dat on jg start_secondary + .align 8 +restart_vtime: + .long 0x7fffffff,0xffffffff .previous #else /* @@ -1045,6 +1064,7 @@ cleanup_io_leave_insn: .section .rodata, "a" #define SYSCALL(esa,esame,emu) .long esame + .globl sys_call_table sys_call_table: #include "syscalls.S" #undef SYSCALL diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c new file mode 100644 index 00000000000..5a82bc68193 --- /dev/null +++ b/arch/s390/kernel/ftrace.c @@ -0,0 +1,212 @@ +/* + * Dynamic function tracer architecture backend. + * + * Copyright IBM Corp. 2009 + * + * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>, + * + */ + +#include <linux/hardirq.h> +#include <linux/uaccess.h> +#include <linux/ftrace.h> +#include <linux/kernel.h> +#include <linux/types.h> +#include <trace/syscall.h> +#include <asm/lowcore.h> + +#ifdef CONFIG_DYNAMIC_FTRACE + +void ftrace_disable_code(void); +void ftrace_disable_return(void); +void ftrace_call_code(void); +void ftrace_nop_code(void); + +#define FTRACE_INSN_SIZE 4 + +#ifdef CONFIG_64BIT + +asm( + " .align 4\n" + "ftrace_disable_code:\n" + " j 0f\n" + " .word 0x0024\n" + " lg %r1,"__stringify(__LC_FTRACE_FUNC)"\n" + " basr %r14,%r1\n" + "ftrace_disable_return:\n" + " lg %r14,8(15)\n" + " lgr %r0,%r0\n" + "0:\n"); + +asm( + " .align 4\n" + "ftrace_nop_code:\n" + " j .+"__stringify(MCOUNT_INSN_SIZE)"\n"); + +asm( + " .align 4\n" + "ftrace_call_code:\n" + " stg %r14,8(%r15)\n"); + +#else /* CONFIG_64BIT */ + +asm( + " .align 4\n" + "ftrace_disable_code:\n" + " j 0f\n" + " l %r1,"__stringify(__LC_FTRACE_FUNC)"\n" + " basr %r14,%r1\n" + "ftrace_disable_return:\n" + " l %r14,4(%r15)\n" + " j 0f\n" + " bcr 0,%r7\n" + " bcr 0,%r7\n" + " bcr 0,%r7\n" + " bcr 0,%r7\n" + " bcr 0,%r7\n" + " bcr 0,%r7\n" + "0:\n"); + +asm( + " .align 4\n" + "ftrace_nop_code:\n" + " j .+"__stringify(MCOUNT_INSN_SIZE)"\n"); + +asm( + " .align 4\n" + "ftrace_call_code:\n" + " st %r14,4(%r15)\n"); + +#endif /* CONFIG_64BIT */ + +static int ftrace_modify_code(unsigned long ip, + void *old_code, int old_size, + void *new_code, int new_size) +{ + unsigned char replaced[MCOUNT_INSN_SIZE]; + + /* + * Note: Due to modules code can disappear and change. + * We need to protect against faulting as well as code + * changing. We do this by using the probe_kernel_* + * functions. + * This however is just a simple sanity check. + */ + if (probe_kernel_read(replaced, (void *)ip, old_size)) + return -EFAULT; + if (memcmp(replaced, old_code, old_size) != 0) + return -EINVAL; + if (probe_kernel_write((void *)ip, new_code, new_size)) + return -EPERM; + return 0; +} + +static int ftrace_make_initial_nop(struct module *mod, struct dyn_ftrace *rec, + unsigned long addr) +{ + return ftrace_modify_code(rec->ip, + ftrace_call_code, FTRACE_INSN_SIZE, + ftrace_disable_code, MCOUNT_INSN_SIZE); +} + +int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, + unsigned long addr) +{ + if (addr == MCOUNT_ADDR) + return ftrace_make_initial_nop(mod, rec, addr); + return ftrace_modify_code(rec->ip, + ftrace_call_code, FTRACE_INSN_SIZE, + ftrace_nop_code, FTRACE_INSN_SIZE); +} + +int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ + return ftrace_modify_code(rec->ip, + ftrace_nop_code, FTRACE_INSN_SIZE, + ftrace_call_code, FTRACE_INSN_SIZE); +} + +int ftrace_update_ftrace_func(ftrace_func_t func) +{ + ftrace_dyn_func = (unsigned long)func; + return 0; +} + +int __init ftrace_dyn_arch_init(void *data) +{ + *(unsigned long *)data = 0; + return 0; +} + +#endif /* CONFIG_DYNAMIC_FTRACE */ + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +#ifdef CONFIG_DYNAMIC_FTRACE +/* + * Patch the kernel code at ftrace_graph_caller location: + * The instruction there is branch relative on condition. The condition mask + * is either all ones (always branch aka disable ftrace_graph_caller) or all + * zeroes (nop aka enable ftrace_graph_caller). + * Instruction format for brc is a7m4xxxx where m is the condition mask. + */ +int ftrace_enable_ftrace_graph_caller(void) +{ + unsigned short opcode = 0xa704; + + return probe_kernel_write(ftrace_graph_caller, &opcode, sizeof(opcode)); +} + +int ftrace_disable_ftrace_graph_caller(void) +{ + unsigned short opcode = 0xa7f4; + + return probe_kernel_write(ftrace_graph_caller, &opcode, sizeof(opcode)); +} + +static inline unsigned long ftrace_mcount_call_adjust(unsigned long addr) +{ + return addr - (ftrace_disable_return - ftrace_disable_code); +} + +#else /* CONFIG_DYNAMIC_FTRACE */ + +static inline unsigned long ftrace_mcount_call_adjust(unsigned long addr) +{ + return addr - MCOUNT_OFFSET_RET; +} + +#endif /* CONFIG_DYNAMIC_FTRACE */ + +/* + * Hook the return address and push it in the stack of return addresses + * in current thread info. + */ +unsigned long prepare_ftrace_return(unsigned long ip, unsigned long parent) +{ + struct ftrace_graph_ent trace; + + if (unlikely(atomic_read(¤t->tracing_graph_pause))) + goto out; + if (ftrace_push_return_trace(parent, ip, &trace.depth, 0) == -EBUSY) + goto out; + trace.func = ftrace_mcount_call_adjust(ip) & PSW_ADDR_INSN; + /* Only trace if the calling function expects to. */ + if (!ftrace_graph_entry(&trace)) { + current->curr_ret_stack--; + goto out; + } + parent = (unsigned long)return_to_handler; +out: + return parent; +} +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + +#ifdef CONFIG_FTRACE_SYSCALLS + +extern unsigned int sys_call_table[]; + +unsigned long __init arch_syscall_addr(int nr) +{ + return (unsigned long)sys_call_table[nr]; +} +#endif diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S index 1046c2c9f8d..c52b4f7742f 100644 --- a/arch/s390/kernel/head.S +++ b/arch/s390/kernel/head.S @@ -1,7 +1,5 @@ /* - * arch/s390/kernel/head.S - * - * Copyright (C) IBM Corp. 1999,2006 + * Copyright IBM Corp. 1999,2009 * * Author(s): Hartmut Penner <hp@de.ibm.com> * Martin Schwidefsky <schwidefsky@de.ibm.com> @@ -23,11 +21,13 @@ * */ +#include <linux/init.h> #include <asm/setup.h> #include <asm/lowcore.h> #include <asm/asm-offsets.h> #include <asm/thread_info.h> #include <asm/page.h> +#include <asm/cpu.h> #ifdef CONFIG_64BIT #define ARCH_OFFSET 4 @@ -35,7 +35,7 @@ #define ARCH_OFFSET 0 #endif -.section ".text.head","ax" +__HEAD #ifndef CONFIG_IPL .org 0 .long 0x00080000,0x80000000+startup # Just a restart PSW @@ -63,7 +63,7 @@ .org 0x100 # # subroutine for loading from tape -# Paramters: +# Parameters: # R1 = device number # R2 = load address .Lloader: @@ -471,34 +471,74 @@ startup:basr %r13,0 # get base .LPG0: xc 0x200(256),0x200 # partially clear lowcore xc 0x300(256),0x300 - + l %r1,5f-.LPG0(%r13) + stck 0(%r1) + spt 6f-.LPG0(%r13) + mvc __LC_LAST_UPDATE_CLOCK(8),0(%r1) + mvc __LC_LAST_UPDATE_TIMER(8),6f-.LPG0(%r13) + mvc __LC_EXIT_TIMER(8),5f-.LPG0(%r13) #ifndef CONFIG_MARCH_G5 - # check processor version against MARCH_{G5,Z900,Z990,Z9_109,Z10} - stidp __LC_CPUID # store cpuid - lhi %r0,(3f-2f) / 2 - la %r1,2f-.LPG0(%r13) -0: clc __LC_CPUID+4(2),0(%r1) - jne 3f - lpsw 1f-.LPG0(13) # machine type not good enough, crash + # check capabilities against MARCH_{G5,Z900,Z990,Z9_109,Z10} + xc __LC_STFL_FAC_LIST(8),__LC_STFL_FAC_LIST + stfl __LC_STFL_FAC_LIST # store facility list + tm __LC_STFL_FAC_LIST,0x01 # stfle available ? + jz 0f + la %r0,0 + .insn s,0xb2b00000,__LC_STFL_FAC_LIST # store facility list extended +0: l %r0,__LC_STFL_FAC_LIST + n %r0,2f+8-.LPG0(%r13) + cl %r0,2f+8-.LPG0(%r13) + jne 1f + l %r0,__LC_STFL_FAC_LIST+4 + n %r0,2f+12-.LPG0(%r13) + cl %r0,2f+12-.LPG0(%r13) + je 3f +1: l %r15,.Lstack-.LPG0(%r13) + ahi %r15,1<<(PAGE_SHIFT+THREAD_ORDER) # init_task_union+THREAD_SIZE + ahi %r15,-96 + la %r2,.Lals_string-.LPG0(%r13) + l %r3,.Lsclp_print-.LPG0(%r13) + basr %r14,%r3 + lpsw 2f-.LPG0(%r13) # machine type not good enough, crash +.Lals_string: + .asciz "The Linux kernel requires more recent processor hardware" +.Lsclp_print: + .long _sclp_print_early +.Lstack: + .long init_thread_union .align 16 -1: .long 0x000a0000,0x00000000 -2: +2: .long 0x000a0000,0x8badcccc +#if defined(CONFIG_64BIT) #if defined(CONFIG_MARCH_Z10) - .short 0x9672, 0x2064, 0x2066, 0x2084, 0x2086, 0x2094, 0x2096 + .long 0xc100efe3, 0xf0680000 #elif defined(CONFIG_MARCH_Z9_109) - .short 0x9672, 0x2064, 0x2066, 0x2084, 0x2086 + .long 0xc100efc3, 0x00000000 #elif defined(CONFIG_MARCH_Z990) - .short 0x9672, 0x2064, 0x2066 + .long 0xc0002000, 0x00000000 #elif defined(CONFIG_MARCH_Z900) - .short 0x9672 + .long 0xc0000000, 0x00000000 +#endif +#else +#if defined(CONFIG_MARCH_Z10) + .long 0x8100c880, 0x00000000 +#elif defined(CONFIG_MARCH_Z9_109) + .long 0x8100c880, 0x00000000 +#elif defined(CONFIG_MARCH_Z990) + .long 0x80002000, 0x00000000 +#elif defined(CONFIG_MARCH_Z900) + .long 0x80000000, 0x00000000 #endif -3: la %r1,2(%r1) - brct %r0,0b +#endif +3: #endif - l %r13,0f-.LPG0(%r13) + l %r13,4f-.LPG0(%r13) b 0(%r13) -0: .long startup_continue + .align 4 +4: .long startup_continue +5: .long sched_clock_base_cc + .align 8 +6: .long 0x7fffffff,0xffffffff # # params at 10400 (setup.h) diff --git a/arch/s390/kernel/head31.S b/arch/s390/kernel/head31.S index 2ced846065b..602b508cd4c 100644 --- a/arch/s390/kernel/head31.S +++ b/arch/s390/kernel/head31.S @@ -24,6 +24,7 @@ startup_continue: # Setup stack # l %r15,.Linittu-.LPG1(%r13) + st %r15,__LC_THREAD_INFO # cache thread info in lowcore mvc __LC_CURRENT(4),__TI_task(%r15) ahi %r15,1<<(PAGE_SHIFT+THREAD_ORDER) # init_task_union+THREAD_SIZE st %r15,__LC_KERNEL_STACK # set end of kernel stack diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S index 65667b2e65c..6a250808092 100644 --- a/arch/s390/kernel/head64.S +++ b/arch/s390/kernel/head64.S @@ -62,9 +62,9 @@ startup_continue: clr %r11,%r12 je 5f # no more space in prefix array 4: - ahi %r8,1 # next cpu (r8 += 1) - cl %r8,.Llast_cpu-.LPG1(%r13) # is last possible cpu ? - jl 1b # jump if not last cpu + ahi %r8,1 # next cpu (r8 += 1) + chi %r8,MAX_CPU_ADDRESS # is last possible cpu ? + jle 1b # jump if not last cpu 5: lhi %r1,2 # mode 2 = esame (dump) j 6f @@ -92,6 +92,7 @@ startup_continue: # Setup stack # larl %r15,init_thread_union + stg %r15,__LC_THREAD_INFO # cache thread info in lowcore lg %r14,__TI_task(%r15) # cache current in lowcore stg %r14,__LC_CURRENT aghi %r15,1<<(PAGE_SHIFT+THREAD_ORDER) # init_task_union + THREAD_SIZE @@ -129,8 +130,6 @@ startup_continue: #ifdef CONFIG_ZFCPDUMP .Lcurrent_cpu: .long 0x0 -.Llast_cpu: - .long 0x0000ffff .Lpref_arr_ptr: .long zfcpdump_prefix_array #endif /* CONFIG_ZFCPDUMP */ diff --git a/arch/s390/kernel/init_task.c b/arch/s390/kernel/init_task.c index 7db95c0b869..4d1c9fb0b54 100644 --- a/arch/s390/kernel/init_task.c +++ b/arch/s390/kernel/init_task.c @@ -18,10 +18,6 @@ static struct signal_struct init_signals = INIT_SIGNALS(init_signals); static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); -struct mm_struct init_mm = INIT_MM(init_mm); - -EXPORT_SYMBOL(init_mm); - /* * Initial thread structure. * @@ -29,9 +25,8 @@ EXPORT_SYMBOL(init_mm); * way process stacks are handled. This is done by having a special * "init_task" linker map entry.. */ -union thread_union init_thread_union - __attribute__((__section__(".data.init_task"))) = - { INIT_THREAD_INFO(init_task) }; +union thread_union init_thread_union __init_task_data = + { INIT_THREAD_INFO(init_task) }; /* * Initial task structure. diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 6f3711a0eaa..4890ac6d7fa 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -23,6 +23,7 @@ #include <asm/ebcdic.h> #include <asm/reset.h> #include <asm/sclp.h> +#include <asm/sigp.h> #include <asm/checksum.h> #define IPL_PARM_BLOCK_VERSION 0 @@ -69,6 +70,7 @@ struct shutdown_action { char *name; void (*fn) (struct shutdown_trigger *trigger); int (*init) (void); + int init_rc; }; static char *ipl_type_str(enum ipl_type type) @@ -270,17 +272,18 @@ static ssize_t ipl_type_show(struct kobject *kobj, struct kobj_attribute *attr, static struct kobj_attribute sys_ipl_type_attr = __ATTR_RO(ipl_type); /* VM IPL PARM routines */ -static void reipl_get_ascii_vmparm(char *dest, +size_t reipl_get_ascii_vmparm(char *dest, size_t size, const struct ipl_parameter_block *ipb) { int i; - int len = 0; + size_t len; char has_lowercase = 0; + len = 0; if ((ipb->ipl_info.ccw.vm_flags & DIAG308_VM_FLAGS_VP_VALID) && (ipb->ipl_info.ccw.vm_parm_len > 0)) { - len = ipb->ipl_info.ccw.vm_parm_len; + len = min_t(size_t, size - 1, ipb->ipl_info.ccw.vm_parm_len); memcpy(dest, ipb->ipl_info.ccw.vm_parm, len); /* If at least one character is lowercase, we assume mixed * case; otherwise we convert everything to lowercase. @@ -297,14 +300,20 @@ static void reipl_get_ascii_vmparm(char *dest, EBCASC(dest, len); } dest[len] = 0; + + return len; } -void get_ipl_vmparm(char *dest) +size_t append_ipl_vmparm(char *dest, size_t size) { + size_t rc; + + rc = 0; if (diag308_set_works && (ipl_block.hdr.pbt == DIAG308_IPL_TYPE_CCW)) - reipl_get_ascii_vmparm(dest, &ipl_block); + rc = reipl_get_ascii_vmparm(dest, size, &ipl_block); else dest[0] = 0; + return rc; } static ssize_t ipl_vm_parm_show(struct kobject *kobj, @@ -312,10 +321,65 @@ static ssize_t ipl_vm_parm_show(struct kobject *kobj, { char parm[DIAG308_VMPARM_SIZE + 1] = {}; - get_ipl_vmparm(parm); + append_ipl_vmparm(parm, sizeof(parm)); return sprintf(page, "%s\n", parm); } +static size_t scpdata_length(const char* buf, size_t count) +{ + while (count) { + if (buf[count - 1] != '\0' && buf[count - 1] != ' ') + break; + count--; + } + return count; +} + +size_t reipl_append_ascii_scpdata(char *dest, size_t size, + const struct ipl_parameter_block *ipb) +{ + size_t count; + size_t i; + int has_lowercase; + + count = min(size - 1, scpdata_length(ipb->ipl_info.fcp.scp_data, + ipb->ipl_info.fcp.scp_data_len)); + if (!count) + goto out; + + has_lowercase = 0; + for (i = 0; i < count; i++) { + if (!isascii(ipb->ipl_info.fcp.scp_data[i])) { + count = 0; + goto out; + } + if (!has_lowercase && islower(ipb->ipl_info.fcp.scp_data[i])) + has_lowercase = 1; + } + + if (has_lowercase) + memcpy(dest, ipb->ipl_info.fcp.scp_data, count); + else + for (i = 0; i < count; i++) + dest[i] = tolower(ipb->ipl_info.fcp.scp_data[i]); +out: + dest[count] = '\0'; + return count; +} + +size_t append_ipl_scpdata(char *dest, size_t len) +{ + size_t rc; + + rc = 0; + if (ipl_block.hdr.pbt == DIAG308_IPL_TYPE_FCP) + rc = reipl_append_ascii_scpdata(dest, len, &ipl_block); + else + dest[0] = 0; + return rc; +} + + static struct kobj_attribute sys_ipl_vm_parm_attr = __ATTR(parm, S_IRUGO, ipl_vm_parm_show, NULL); @@ -551,7 +615,7 @@ static ssize_t reipl_generic_vmparm_show(struct ipl_parameter_block *ipb, { char vmparm[DIAG308_VMPARM_SIZE + 1] = {}; - reipl_get_ascii_vmparm(vmparm, ipb); + reipl_get_ascii_vmparm(vmparm, sizeof(vmparm), ipb); return sprintf(page, "%s\n", vmparm); } @@ -624,6 +688,59 @@ static struct kobj_attribute sys_reipl_ccw_vmparm_attr = /* FCP reipl device attributes */ +static ssize_t reipl_fcp_scpdata_read(struct kobject *kobj, + struct bin_attribute *attr, + char *buf, loff_t off, size_t count) +{ + size_t size = reipl_block_fcp->ipl_info.fcp.scp_data_len; + void *scp_data = reipl_block_fcp->ipl_info.fcp.scp_data; + + return memory_read_from_buffer(buf, count, &off, scp_data, size); +} + +static ssize_t reipl_fcp_scpdata_write(struct kobject *kobj, + struct bin_attribute *attr, + char *buf, loff_t off, size_t count) +{ + size_t padding; + size_t scpdata_len; + + if (off < 0) + return -EINVAL; + + if (off >= DIAG308_SCPDATA_SIZE) + return -ENOSPC; + + if (count > DIAG308_SCPDATA_SIZE - off) + count = DIAG308_SCPDATA_SIZE - off; + + memcpy(reipl_block_fcp->ipl_info.fcp.scp_data, buf + off, count); + scpdata_len = off + count; + + if (scpdata_len % 8) { + padding = 8 - (scpdata_len % 8); + memset(reipl_block_fcp->ipl_info.fcp.scp_data + scpdata_len, + 0, padding); + scpdata_len += padding; + } + + reipl_block_fcp->ipl_info.fcp.scp_data_len = scpdata_len; + reipl_block_fcp->hdr.len = IPL_PARM_BLK_FCP_LEN + scpdata_len; + reipl_block_fcp->hdr.blk0_len = IPL_PARM_BLK0_FCP_LEN + scpdata_len; + + return count; +} + +static struct bin_attribute sys_reipl_fcp_scp_data_attr = { + .attr = { + .name = "scp_data", + .mode = S_IRUGO | S_IWUSR, + }, + .size = PAGE_SIZE, + .read = reipl_fcp_scpdata_read, + .write = reipl_fcp_scpdata_write, +}; + DEFINE_IPL_ATTR_RW(reipl_fcp, wwpn, "0x%016llx\n", "%016llx\n", reipl_block_fcp->ipl_info.fcp.wwpn); DEFINE_IPL_ATTR_RW(reipl_fcp, lun, "0x%016llx\n", "%016llx\n", @@ -645,7 +762,6 @@ static struct attribute *reipl_fcp_attrs[] = { }; static struct attribute_group reipl_fcp_attr_group = { - .name = IPL_FCP_STR, .attrs = reipl_fcp_attrs, }; @@ -893,6 +1009,7 @@ static struct kobj_attribute reipl_type_attr = __ATTR(reipl_type, 0644, reipl_type_show, reipl_type_store); static struct kset *reipl_kset; +static struct kset *reipl_fcp_kset; static void get_ipl_string(char *dst, struct ipl_parameter_block *ipb, const enum ipl_method m) @@ -904,7 +1021,7 @@ static void get_ipl_string(char *dst, struct ipl_parameter_block *ipb, reipl_get_ascii_loadparm(loadparm, ipb); reipl_get_ascii_nss_name(nss_name, ipb); - reipl_get_ascii_vmparm(vmparm, ipb); + reipl_get_ascii_vmparm(vmparm, sizeof(vmparm), ipb); switch (m) { case REIPL_METHOD_CCW_VM: @@ -1074,23 +1191,44 @@ static int __init reipl_fcp_init(void) int rc; if (!diag308_set_works) { - if (ipl_info.type == IPL_TYPE_FCP) + if (ipl_info.type == IPL_TYPE_FCP) { make_attrs_ro(reipl_fcp_attrs); - else + sys_reipl_fcp_scp_data_attr.attr.mode = S_IRUGO; + } else return 0; } reipl_block_fcp = (void *) get_zeroed_page(GFP_KERNEL); if (!reipl_block_fcp) return -ENOMEM; - rc = sysfs_create_group(&reipl_kset->kobj, &reipl_fcp_attr_group); + + /* sysfs: create fcp kset for mixing attr group and bin attrs */ + reipl_fcp_kset = kset_create_and_add(IPL_FCP_STR, NULL, + &reipl_kset->kobj); + if (!reipl_kset) { + free_page((unsigned long) reipl_block_fcp); + return -ENOMEM; + } + + rc = sysfs_create_group(&reipl_fcp_kset->kobj, &reipl_fcp_attr_group); if (rc) { - free_page((unsigned long)reipl_block_fcp); + kset_unregister(reipl_fcp_kset); + free_page((unsigned long) reipl_block_fcp); return rc; } - if (ipl_info.type == IPL_TYPE_FCP) { + + rc = sysfs_create_bin_file(&reipl_fcp_kset->kobj, + &sys_reipl_fcp_scp_data_attr); + if (rc) { + sysfs_remove_group(&reipl_fcp_kset->kobj, &reipl_fcp_attr_group); + kset_unregister(reipl_fcp_kset); + free_page((unsigned long) reipl_block_fcp); + return rc; + } + + if (ipl_info.type == IPL_TYPE_FCP) memcpy(reipl_block_fcp, IPL_PARMBLOCK_START, PAGE_SIZE); - } else { + else { reipl_block_fcp->hdr.len = IPL_PARM_BLK_FCP_LEN; reipl_block_fcp->hdr.version = IPL_PARM_BLOCK_VERSION; reipl_block_fcp->hdr.blk0_len = IPL_PARM_BLK0_FCP_LEN; @@ -1457,10 +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, @@ -1485,11 +1622,13 @@ static int set_trigger(const char *buf, struct shutdown_trigger *trigger, int i; for (i = 0; i < SHUTDOWN_ACTIONS_COUNT; i++) { - if (!shutdown_actions_list[i]) - continue; if (sysfs_streq(buf, shutdown_actions_list[i]->name)) { - trigger->action = shutdown_actions_list[i]; - return len; + if (shutdown_actions_list[i]->init_rc) { + return shutdown_actions_list[i]->init_rc; + } else { + trigger->action = shutdown_actions_list[i]; + return len; + } } } return -EINVAL; @@ -1639,8 +1778,8 @@ static void __init shutdown_actions_init(void) for (i = 0; i < SHUTDOWN_ACTIONS_COUNT; i++) { if (!shutdown_actions_list[i]->init) continue; - if (shutdown_actions_list[i]->init()) - shutdown_actions_list[i] = NULL; + shutdown_actions_list[i]->init_rc = + shutdown_actions_list[i]->init(); } } diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index a01cf0284db..86783efa24e 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -25,9 +25,9 @@ #include <linux/preempt.h> #include <linux/stop_machine.h> #include <linux/kdebug.h> +#include <linux/uaccess.h> #include <asm/cacheflush.h> #include <asm/sections.h> -#include <asm/uaccess.h> #include <linux/module.h> DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; @@ -154,66 +154,35 @@ void __kprobes get_instruction_type(struct arch_specific_insn *ainsn) static int __kprobes swap_instruction(void *aref) { + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + unsigned long status = kcb->kprobe_status; struct ins_replace_args *args = aref; - u32 *addr; - u32 instr; - int err = -EFAULT; + int rc; - /* - * Text segment is read-only, hence we use stura to bypass dynamic - * address translation to exchange the instruction. Since stura - * always operates on four bytes, but we only want to exchange two - * bytes do some calculations to get things right. In addition we - * shall not cross any page boundaries (vmalloc area!) when writing - * the new instruction. - */ - addr = (u32 *)((unsigned long)args->ptr & -4UL); - if ((unsigned long)args->ptr & 2) - instr = ((*addr) & 0xffff0000) | args->new; - else - instr = ((*addr) & 0x0000ffff) | args->new << 16; - - asm volatile( - " lra %1,0(%1)\n" - "0: stura %2,%1\n" - "1: la %0,0\n" - "2:\n" - EX_TABLE(0b,2b) - : "+d" (err) - : "a" (addr), "d" (instr) - : "memory", "cc"); - - return err; + kcb->kprobe_status = KPROBE_SWAP_INST; + rc = probe_kernel_write(args->ptr, &args->new, sizeof(args->new)); + kcb->kprobe_status = status; + return rc; } void __kprobes arch_arm_kprobe(struct kprobe *p) { - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - unsigned long status = kcb->kprobe_status; struct ins_replace_args args; args.ptr = p->addr; args.old = p->opcode; args.new = BREAKPOINT_INSTRUCTION; - - kcb->kprobe_status = KPROBE_SWAP_INST; stop_machine(swap_instruction, &args, NULL); - kcb->kprobe_status = status; } void __kprobes arch_disarm_kprobe(struct kprobe *p) { - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - unsigned long status = kcb->kprobe_status; struct ins_replace_args args; args.ptr = p->addr; args.old = BREAKPOINT_INSTRUCTION; args.new = p->opcode; - - kcb->kprobe_status = KPROBE_SWAP_INST; stop_machine(swap_instruction, &args, NULL); - kcb->kprobe_status = status; } void __kprobes arch_remove_kprobe(struct kprobe *p) diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S index 80641224a09..dfe015d7398 100644 --- a/arch/s390/kernel/mcount.S +++ b/arch/s390/kernel/mcount.S @@ -1,5 +1,5 @@ /* - * Copyright IBM Corp. 2008 + * Copyright IBM Corp. 2008,2009 * * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>, * @@ -7,52 +7,83 @@ #include <asm/asm-offsets.h> -#ifndef CONFIG_64BIT -.globl _mcount + .globl ftrace_stub +ftrace_stub: + br %r14 + + .globl _mcount _mcount: - stm %r0,%r5,8(%r15) +#ifdef CONFIG_DYNAMIC_FTRACE + br %r14 + + .data + .globl ftrace_dyn_func +ftrace_dyn_func: + .long ftrace_stub + .previous + + .globl ftrace_caller +ftrace_caller: +#endif + stm %r2,%r5,16(%r15) + bras %r1,2f +#ifdef CONFIG_DYNAMIC_FTRACE +0: .long ftrace_dyn_func +#else +0: .long ftrace_trace_function +#endif +1: .long function_trace_stop +2: l %r2,1b-0b(%r1) + icm %r2,0xf,0(%r2) + jnz 3f st %r14,56(%r15) - lr %r1,%r15 + lr %r0,%r15 ahi %r15,-96 l %r3,100(%r15) la %r2,0(%r14) - st %r1,__SF_BACKCHAIN(%r15) + st %r0,__SF_BACKCHAIN(%r15) la %r3,0(%r3) - bras %r14,0f - .long ftrace_trace_function -0: l %r14,0(%r14) + l %r14,0b-0b(%r1) l %r14,0(%r14) basr %r14,%r14 +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +#ifdef CONFIG_DYNAMIC_FTRACE + .globl ftrace_graph_caller +ftrace_graph_caller: + # This unconditional branch gets runtime patched. Change only if + # you know what you are doing. See ftrace_enable_graph_caller(). + j 1f +#endif + bras %r1,0f + .long prepare_ftrace_return +0: l %r2,152(%r15) + l %r4,0(%r1) + l %r3,100(%r15) + basr %r14,%r4 + st %r2,100(%r15) +1: +#endif ahi %r15,96 - lm %r0,%r5,8(%r15) l %r14,56(%r15) +3: lm %r2,%r5,16(%r15) br %r14 -.globl ftrace_stub -ftrace_stub: - br %r14 - -#else /* CONFIG_64BIT */ - -.globl _mcount -_mcount: - stmg %r0,%r5,16(%r15) - stg %r14,112(%r15) - lgr %r1,%r15 - aghi %r15,-160 - stg %r1,__SF_BACKCHAIN(%r15) - lgr %r2,%r14 - lg %r3,168(%r15) - larl %r14,ftrace_trace_function - lg %r14,0(%r14) - basr %r14,%r14 - aghi %r15,160 - lmg %r0,%r5,16(%r15) - lg %r14,112(%r15) - br %r14 +#ifdef CONFIG_FUNCTION_GRAPH_TRACER -.globl ftrace_stub -ftrace_stub: + .globl return_to_handler +return_to_handler: + stm %r2,%r5,16(%r15) + st %r14,56(%r15) + lr %r0,%r15 + ahi %r15,-96 + st %r0,__SF_BACKCHAIN(%r15) + bras %r1,0f + .long ftrace_return_to_handler +0: l %r2,0b-0b(%r1) + basr %r14,%r2 + lr %r14,%r2 + ahi %r15,96 + lm %r2,%r5,16(%r15) br %r14 -#endif /* CONFIG_64BIT */ +#endif diff --git a/arch/s390/kernel/mcount64.S b/arch/s390/kernel/mcount64.S new file mode 100644 index 00000000000..c37211c6092 --- /dev/null +++ b/arch/s390/kernel/mcount64.S @@ -0,0 +1,78 @@ +/* + * Copyright IBM Corp. 2008,2009 + * + * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>, + * + */ + +#include <asm/asm-offsets.h> + + .globl ftrace_stub +ftrace_stub: + br %r14 + + .globl _mcount +_mcount: +#ifdef CONFIG_DYNAMIC_FTRACE + br %r14 + + .data + .globl ftrace_dyn_func +ftrace_dyn_func: + .quad ftrace_stub + .previous + + .globl ftrace_caller +ftrace_caller: +#endif + larl %r1,function_trace_stop + icm %r1,0xf,0(%r1) + bnzr %r14 + stmg %r2,%r5,32(%r15) + stg %r14,112(%r15) + lgr %r1,%r15 + aghi %r15,-160 + stg %r1,__SF_BACKCHAIN(%r15) + lgr %r2,%r14 + lg %r3,168(%r15) +#ifdef CONFIG_DYNAMIC_FTRACE + larl %r14,ftrace_dyn_func +#else + larl %r14,ftrace_trace_function +#endif + lg %r14,0(%r14) + basr %r14,%r14 +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +#ifdef CONFIG_DYNAMIC_FTRACE + .globl ftrace_graph_caller +ftrace_graph_caller: + # This unconditional branch gets runtime patched. Change only if + # you know what you are doing. See ftrace_enable_graph_caller(). + j 0f +#endif + lg %r2,272(%r15) + lg %r3,168(%r15) + brasl %r14,prepare_ftrace_return + stg %r2,168(%r15) +0: +#endif + aghi %r15,160 + lmg %r2,%r5,32(%r15) + lg %r14,112(%r15) + br %r14 + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + + .globl return_to_handler +return_to_handler: + stmg %r2,%r5,32(%r15) + lgr %r1,%r15 + aghi %r15,-160 + stg %r1,__SF_BACKCHAIN(%r15) + brasl %r14,ftrace_return_to_handler + aghi %r15,160 + lgr %r14,%r2 + lmg %r2,%r5,32(%r15) + br %r14 + +#endif diff --git a/arch/s390/kernel/mem_detect.c b/arch/s390/kernel/mem_detect.c index 9872999c66d..559af0d0787 100644 --- a/arch/s390/kernel/mem_detect.c +++ b/arch/s390/kernel/mem_detect.c @@ -1,6 +1,7 @@ /* - * Copyright IBM Corp. 2008 - * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> + * Copyright IBM Corp. 2008, 2009 + * + * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> */ #include <linux/kernel.h> @@ -9,20 +10,6 @@ #include <asm/sclp.h> #include <asm/setup.h> -static inline int tprot(unsigned long addr) -{ - int rc = -EFAULT; - - asm volatile( - " tprot 0(%1),0\n" - "0: ipm %0\n" - " srl %0,28\n" - "1:\n" - EX_TABLE(0b,1b) - : "+d" (rc) : "a" (addr) : "cc"); - return rc; -} - #define ADDR2G (1ULL << 31) static void find_memory_chunks(struct mem_chunk chunk[]) diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index eed4a00cb67..639380a0c45 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -55,9 +55,9 @@ 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); - /* FIXME: If module_region == mod->init_region, trim exception - table entries. */ } static void @@ -404,6 +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/nmi.c b/arch/s390/kernel/nmi.c index 4bfdc421d7e..015e27da40e 100644 --- a/arch/s390/kernel/nmi.c +++ b/arch/s390/kernel/nmi.c @@ -10,12 +10,13 @@ #include <linux/init.h> #include <linux/errno.h> +#include <linux/hardirq.h> #include <linux/time.h> #include <linux/module.h> #include <asm/lowcore.h> #include <asm/smp.h> #include <asm/etr.h> -#include <asm/cpu.h> +#include <asm/cputime.h> #include <asm/nmi.h> #include <asm/crw.h> @@ -253,7 +254,7 @@ void notrace s390_do_machine_check(struct pt_regs *regs) struct mci *mci; int umode; - lockdep_off(); + nmi_enter(); s390_idle_check(); mci = (struct mci *) &S390_lowcore.mcck_interruption_code; @@ -363,7 +364,7 @@ void notrace s390_do_machine_check(struct pt_regs *regs) mcck->warning = 1; set_thread_flag(TIF_MCCK_PENDING); } - lockdep_on(); + nmi_exit(); } static int __init machine_check_init(void) diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index b48e961a38f..5417eb57271 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -27,11 +27,12 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/notifier.h> -#include <linux/utsname.h> #include <linux/tick.h> #include <linux/elfcore.h> #include <linux/kernel_stat.h> #include <linux/syscalls.h> +#include <linux/compat.h> +#include <asm/compat.h> #include <asm/uaccess.h> #include <asm/pgtable.h> #include <asm/system.h> @@ -160,7 +161,7 @@ void release_thread(struct task_struct *dead_task) { } -int copy_thread(int nr, unsigned long clone_flags, unsigned long new_stackp, +int copy_thread(unsigned long clone_flags, unsigned long new_stackp, unsigned long unused, struct task_struct *p, struct pt_regs *regs) { @@ -204,7 +205,7 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long new_stackp, save_fp_regs(&p->thread.fp_regs); /* Set a new TLS ? */ if (clone_flags & CLONE_SETTLS) { - if (test_thread_flag(TIF_31BIT)) { + if (is_compat_task()) { p->thread.acrs[0] = (unsigned int) regs->gprs[6]; } else { p->thread.acrs[0] = (unsigned int)(regs->gprs[6] >> 32); @@ -229,17 +230,11 @@ SYSCALL_DEFINE0(fork) return do_fork(SIGCHLD, regs->gprs[15], regs, 0, NULL, NULL); } -SYSCALL_DEFINE0(clone) +SYSCALL_DEFINE4(clone, unsigned long, newsp, unsigned long, clone_flags, + int __user *, parent_tidptr, int __user *, child_tidptr) { struct pt_regs *regs = task_pt_regs(current); - unsigned long clone_flags; - unsigned long newsp; - int __user *parent_tidptr, *child_tidptr; - clone_flags = regs->gprs[3]; - newsp = regs->orig_gpr2; - parent_tidptr = (int __user *) regs->gprs[4]; - child_tidptr = (int __user *) regs->gprs[5]; if (!newsp) newsp = regs->gprs[15]; return do_fork(clone_flags, newsp, regs, 0, @@ -265,9 +260,6 @@ SYSCALL_DEFINE0(vfork) asmlinkage void execve_tail(void) { - task_lock(current); - current->ptrace &= ~PT_DTRACE; - task_unlock(current); current->thread.fp_regs.fpc = 0; if (MACHINE_HAS_IEEE) asm volatile("sfpc %0,%0" : : "d" (0)); @@ -276,30 +268,25 @@ asmlinkage void execve_tail(void) /* * sys_execve() executes a new program. */ -SYSCALL_DEFINE0(execve) +SYSCALL_DEFINE3(execve, char __user *, name, char __user * __user *, argv, + char __user * __user *, envp) { struct pt_regs *regs = task_pt_regs(current); char *filename; - unsigned long result; - int rc; + long rc; - filename = getname((char __user *) regs->orig_gpr2); - if (IS_ERR(filename)) { - result = PTR_ERR(filename); + filename = getname(name); + rc = PTR_ERR(filename); + if (IS_ERR(filename)) + return rc; + rc = do_execve(filename, argv, envp, regs); + if (rc) goto out; - } - rc = do_execve(filename, (char __user * __user *) regs->gprs[3], - (char __user * __user *) regs->gprs[4], regs); - if (rc) { - result = rc; - goto out_putname; - } execve_tail(); - result = regs->gprs[2]; -out_putname: - putname(filename); + rc = regs->gprs[2]; out: - return result; + putname(filename); + return rc; } /* diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c index 802c8ab247f..0729f36c2fe 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 75c496f4f16..653c6a17874 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -26,7 +26,6 @@ #include <linux/sched.h> #include <linux/mm.h> #include <linux/smp.h> -#include <linux/smp_lock.h> #include <linux/errno.h> #include <linux/ptrace.h> #include <linux/user.h> @@ -36,7 +35,9 @@ #include <linux/elf.h> #include <linux/regset.h> #include <linux/tracehook.h> - +#include <linux/seccomp.h> +#include <trace/syscall.h> +#include <asm/compat.h> #include <asm/segment.h> #include <asm/page.h> #include <asm/pgtable.h> @@ -50,9 +51,13 @@ #include "compat_ptrace.h" #endif +#define CREATE_TRACE_POINTS +#include <trace/events/syscalls.h> + enum s390_regset { REGSET_GENERAL, REGSET_FP, + REGSET_GENERAL_EXTENDED, }; static void @@ -69,7 +74,7 @@ FixPerRegisters(struct task_struct *task) if (per_info->single_step) { per_info->control_regs.bits.starting_addr = 0; #ifdef CONFIG_COMPAT - if (test_thread_flag(TIF_31BIT)) + if (is_compat_task()) per_info->control_regs.bits.ending_addr = 0x7fffffffUL; else #endif @@ -335,24 +340,10 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) int copied, ret; switch (request) { - case PTRACE_PEEKTEXT: - case PTRACE_PEEKDATA: - /* Remove high order bit from address (only for 31 bit). */ - addr &= PSW_ADDR_INSN; - /* read word at location addr. */ - return generic_ptrace_peekdata(child, addr, data); - case PTRACE_PEEKUSR: /* read the word at location addr in the USER area. */ return peek_user(child, addr, data); - case PTRACE_POKETEXT: - case PTRACE_POKEDATA: - /* Remove high order bit from address (only for 31 bit). */ - addr &= PSW_ADDR_INSN; - /* write the word at location addr. */ - return generic_ptrace_pokedata(child, addr, data); - case PTRACE_POKEUSR: /* write the word at location addr in the USER area */ return poke_user(child, addr, data); @@ -382,8 +373,11 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) copied += sizeof(unsigned long); } return 0; + default: + /* Removing high order bit from addr (only for 31 bit). */ + addr &= PSW_ADDR_INSN; + return ptrace_request(child, request, addr, data); } - return ptrace_request(child, request, addr, data); } #ifdef CONFIG_COMPAT @@ -482,8 +476,7 @@ static int peek_user_compat(struct task_struct *child, { __u32 tmp; - if (!test_thread_flag(TIF_31BIT) || - (addr & 3) || addr > sizeof(struct user) - 3) + if (!is_compat_task() || (addr & 3) || addr > sizeof(struct user) - 3) return -EIO; tmp = __peek_user_compat(child, addr); @@ -584,8 +577,7 @@ static int __poke_user_compat(struct task_struct *child, static int poke_user_compat(struct task_struct *child, addr_t addr, addr_t data) { - if (!test_thread_flag(TIF_31BIT) || - (addr & 3) || addr > sizeof(struct user32) - 3) + if (!is_compat_task() || (addr & 3) || addr > sizeof(struct user32) - 3) return -EIO; return __poke_user_compat(child, addr, data); @@ -642,6 +634,9 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) { long ret; + /* Do the secure computing check first. */ + secure_computing(regs->gprs[2]); + /* * The sysc_tracesys code in entry.S stored the system * call number to gprs[2]. @@ -659,8 +654,11 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) ret = -1; } + if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) + trace_sys_enter(regs, regs->gprs[2]); + if (unlikely(current->audit_context)) - audit_syscall_entry(test_thread_flag(TIF_31BIT) ? + audit_syscall_entry(is_compat_task() ? AUDIT_ARCH_S390 : AUDIT_ARCH_S390X, regs->gprs[2], regs->orig_gpr2, regs->gprs[3], regs->gprs[4], @@ -674,6 +672,9 @@ asmlinkage void do_syscall_trace_exit(struct pt_regs *regs) audit_syscall_exit(AUDITSC_RESULT(regs->gprs[2]), regs->gprs[2]); + if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) + trace_sys_exit(regs, regs->gprs[2]); + if (test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall_exit(regs, 0); } @@ -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_PRXSTATUS, + .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 a0d2d55d7fb..59618bcd99b 100644 --- a/arch/s390/kernel/s390_ext.c +++ b/arch/s390/kernel/s390_ext.c @@ -10,10 +10,11 @@ #include <linux/module.h> #include <linux/kernel.h> #include <linux/slab.h> +#include <linux/ftrace.h> #include <linux/errno.h> #include <linux/kernel_stat.h> #include <linux/interrupt.h> -#include <asm/cpu.h> +#include <asm/cputime.h> #include <asm/lowcore.h> #include <asm/s390_ext.h> #include <asm/irq_regs.h> @@ -112,7 +113,7 @@ int unregister_early_external_interrupt(__u16 code, ext_int_handler_t handler, return 0; } -void do_extint(struct pt_regs *regs, unsigned short code) +void __irq_entry do_extint(struct pt_regs *regs, unsigned short code) { ext_int_info_t *p; int index; @@ -125,6 +126,8 @@ void 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/sclp.S b/arch/s390/kernel/sclp.S new file mode 100644 index 00000000000..e27ca63076d --- /dev/null +++ b/arch/s390/kernel/sclp.S @@ -0,0 +1,324 @@ +/* + * Mini SCLP driver. + * + * Copyright IBM Corp. 2004,2009 + * + * Author(s): Peter Oberparleiter <Peter.Oberparleiter@de.ibm.com>, + * Heiko Carstens <heiko.carstens@de.ibm.com>, + * + */ + +LC_EXT_NEW_PSW = 0x58 # addr of ext int handler +LC_EXT_INT_PARAM = 0x80 # addr of ext int parameter +LC_EXT_INT_CODE = 0x86 # addr of ext int code + +# +# Subroutine which waits synchronously until either an external interruption +# or a timeout occurs. +# +# Parameters: +# R2 = 0 for no timeout, non-zero for timeout in (approximated) seconds +# +# Returns: +# R2 = 0 on interrupt, 2 on timeout +# R3 = external interruption parameter if R2=0 +# + +_sclp_wait_int: + stm %r6,%r15,24(%r15) # save registers + basr %r13,0 # get base register +.LbaseS1: + ahi %r15,-96 # create stack frame + la %r8,LC_EXT_NEW_PSW # register int handler + mvc .LoldpswS1-.LbaseS1(8,%r13),0(%r8) + mvc 0(8,%r8),.LextpswS1-.LbaseS1(%r13) + lhi %r6,0x0200 # cr mask for ext int (cr0.54) + ltr %r2,%r2 + jz .LsetctS1 + ahi %r6,0x0800 # cr mask for clock int (cr0.52) + stck .LtimeS1-.LbaseS1(%r13) # initiate timeout + al %r2,.LtimeS1-.LbaseS1(%r13) + st %r2,.LtimeS1-.LbaseS1(%r13) + sckc .LtimeS1-.LbaseS1(%r13) + +.LsetctS1: + stctl %c0,%c0,.LctlS1-.LbaseS1(%r13) # enable required interrupts + l %r0,.LctlS1-.LbaseS1(%r13) + lhi %r1,~(0x200 | 0x800) # clear old values + nr %r1,%r0 + or %r1,%r6 # set new value + st %r1,.LctlS1-.LbaseS1(%r13) + lctl %c0,%c0,.LctlS1-.LbaseS1(%r13) + st %r0,.LctlS1-.LbaseS1(%r13) + lhi %r2,2 # return code for timeout +.LloopS1: + lpsw .LwaitpswS1-.LbaseS1(%r13) # wait until interrupt +.LwaitS1: + lh %r7,LC_EXT_INT_CODE + chi %r7,0x1004 # timeout? + je .LtimeoutS1 + chi %r7,0x2401 # service int? + jne .LloopS1 + sr %r2,%r2 + l %r3,LC_EXT_INT_PARAM +.LtimeoutS1: + lctl %c0,%c0,.LctlS1-.LbaseS1(%r13) # restore interrupt setting + # restore old handler + mvc 0(8,%r8),.LoldpswS1-.LbaseS1(%r13) + lm %r6,%r15,120(%r15) # restore registers + br %r14 # return to caller + + .align 8 +.LoldpswS1: + .long 0, 0 # old ext int PSW +.LextpswS1: + .long 0x00080000, 0x80000000+.LwaitS1 # PSW to handle ext int +.LwaitpswS1: + .long 0x010a0000, 0x00000000+.LloopS1 # PSW to wait for ext int +.LtimeS1: + .quad 0 # current time +.LctlS1: + .long 0 # CT0 contents + +# +# Subroutine to synchronously issue a service call. +# +# Parameters: +# R2 = command word +# R3 = sccb address +# +# Returns: +# R2 = 0 on success, 1 on failure +# R3 = sccb response code if R2 = 0 +# + +_sclp_servc: + stm %r6,%r15,24(%r15) # save registers + ahi %r15,-96 # create stack frame + lr %r6,%r2 # save command word + lr %r7,%r3 # save sccb address +.LretryS2: + lhi %r2,1 # error return code + .insn rre,0xb2200000,%r6,%r7 # servc + brc 1,.LendS2 # exit if not operational + brc 8,.LnotbusyS2 # go on if not busy + sr %r2,%r2 # wait until no longer busy + bras %r14,_sclp_wait_int + j .LretryS2 # retry +.LnotbusyS2: + sr %r2,%r2 # wait until result + bras %r14,_sclp_wait_int + sr %r2,%r2 + lh %r3,6(%r7) +.LendS2: + lm %r6,%r15,120(%r15) # restore registers + br %r14 + +# +# Subroutine to set up the SCLP interface. +# +# Parameters: +# R2 = 0 to activate, non-zero to deactivate +# +# Returns: +# R2 = 0 on success, non-zero on failure +# + +_sclp_setup: + stm %r6,%r15,24(%r15) # save registers + ahi %r15,-96 # create stack frame + basr %r13,0 # get base register +.LbaseS3: + l %r6,.LsccbS0-.LbaseS3(%r13) # prepare init mask sccb + mvc 0(.LinitendS3-.LinitsccbS3,%r6),.LinitsccbS3-.LbaseS3(%r13) + ltr %r2,%r2 # initialization? + jz .LdoinitS3 # go ahead + # clear masks + xc .LinitmaskS3-.LinitsccbS3(8,%r6),.LinitmaskS3-.LinitsccbS3(%r6) +.LdoinitS3: + l %r2,.LwritemaskS3-.LbaseS3(%r13)# get command word + lr %r3,%r6 # get sccb address + bras %r14,_sclp_servc # issue service call + ltr %r2,%r2 # servc successful? + jnz .LerrorS3 + chi %r3,0x20 # write mask successful? + jne .LerrorS3 + # check masks + la %r2,.LinitmaskS3-.LinitsccbS3(%r6) + l %r1,0(%r2) # receive mask ok? + n %r1,12(%r2) + cl %r1,0(%r2) + jne .LerrorS3 + l %r1,4(%r2) # send mask ok? + n %r1,8(%r2) + cl %r1,4(%r2) + sr %r2,%r2 + je .LendS3 +.LerrorS3: + lhi %r2,1 # error return code +.LendS3: + lm %r6,%r15,120(%r15) # restore registers + br %r14 +.LwritemaskS3: + .long 0x00780005 # SCLP command for write mask +.LinitsccbS3: + .word .LinitendS3-.LinitsccbS3 + .byte 0,0,0,0 + .word 0 + .word 0 + .word 4 +.LinitmaskS3: + .long 0x80000000 + .long 0x40000000 + .long 0 + .long 0 +.LinitendS3: + +# +# Subroutine which prints a given text to the SCLP console. +# +# Parameters: +# R2 = address of nil-terminated ASCII text +# +# Returns: +# R2 = 0 on success, 1 on failure +# + +_sclp_print: + stm %r6,%r15,24(%r15) # save registers + ahi %r15,-96 # create stack frame + basr %r13,0 # get base register +.LbaseS4: + l %r8,.LsccbS0-.LbaseS4(%r13) # prepare write data sccb + mvc 0(.LmtoS4-.LwritesccbS4,%r8),.LwritesccbS4-.LbaseS4(%r13) + la %r7,.LmtoS4-.LwritesccbS4(%r8) # current mto addr + sr %r0,%r0 + l %r10,.Lascebc-.LbaseS4(%r13) # address of translation table +.LinitmtoS4: + # initialize mto + mvc 0(.LmtoendS4-.LmtoS4,%r7),.LmtoS4-.LbaseS4(%r13) + lhi %r6,.LmtoendS4-.LmtoS4 # current mto length +.LloopS4: + ic %r0,0(%r2) # get character + ahi %r2,1 + ltr %r0,%r0 # end of string? + jz .LfinalizemtoS4 + chi %r0,0x15 # end of line (NL)? + jz .LfinalizemtoS4 + stc %r0,0(%r6,%r7) # copy to mto + la %r11,0(%r6,%r7) + tr 0(1,%r11),0(%r10) # translate to EBCDIC + ahi %r6,1 + j .LloopS4 +.LfinalizemtoS4: + sth %r6,0(%r7) # update mto length + lh %r9,.LmdbS4-.LwritesccbS4(%r8) # update mdb length + ar %r9,%r6 + sth %r9,.LmdbS4-.LwritesccbS4(%r8) + lh %r9,.LevbufS4-.LwritesccbS4(%r8)# update evbuf length + ar %r9,%r6 + sth %r9,.LevbufS4-.LwritesccbS4(%r8) + lh %r9,0(%r8) # update sccb length + ar %r9,%r6 + sth %r9,0(%r8) + ar %r7,%r6 # update current mto adress + ltr %r0,%r0 # more characters? + jnz .LinitmtoS4 + l %r2,.LwritedataS4-.LbaseS4(%r13)# write data + lr %r3,%r8 + bras %r14,_sclp_servc + ltr %r2,%r2 # servc successful? + jnz .LendS4 + chi %r3,0x20 # write data successful? + je .LendS4 + lhi %r2,1 # error return code +.LendS4: + lm %r6,%r15,120(%r15) # restore registers + br %r14 + +# +# Function which prints a given text to the SCLP console. +# +# Parameters: +# R2 = address of nil-terminated ASCII text +# +# Returns: +# R2 = 0 on success, 1 on failure +# + + .globl _sclp_print_early +_sclp_print_early: + stm %r6,%r15,24(%r15) # save registers + ahi %r15,-96 # create stack frame + lr %r10,%r2 # save string pointer + lhi %r2,0 + bras %r14,_sclp_setup # enable console + ltr %r2,%r2 + jnz .LendS5 + lr %r2,%r10 + bras %r14,_sclp_print # print string + ltr %r2,%r2 + jnz .LendS5 + lhi %r2,1 + bras %r14,_sclp_setup # disable console +.LendS5: + lm %r6,%r15,120(%r15) # restore registers + br %r14 + +.LwritedataS4: + .long 0x00760005 # SCLP command for write data +.LwritesccbS4: + # sccb + .word .LmtoS4-.LwritesccbS4 + .byte 0 + .byte 0,0,0 + .word 0 + + # evbuf +.LevbufS4: + .word .LmtoS4-.LevbufS4 + .byte 0x02 + .byte 0 + .word 0 + +.LmdbS4: + # mdb + .word .LmtoS4-.LmdbS4 + .word 1 + .long 0xd4c4c240 + .long 1 + + # go +.LgoS4: + .word .LmtoS4-.LgoS4 + .word 1 + .long 0 + .byte 0,0,0,0,0,0,0,0 + .byte 0,0,0 + .byte 0 + .byte 0,0,0,0,0,0,0 + .byte 0 + .word 0 + .byte 0,0,0,0,0,0,0,0,0,0 + .byte 0,0,0,0,0,0,0,0 + .byte 0,0,0,0,0,0,0,0 + +.LmtoS4: + .word .LmtoendS4-.LmtoS4 + .word 4 + .word 0x1000 + .byte 0 + .byte 0,0,0 +.LmtoendS4: + + # Global constants +.LsccbS0: + .long _sclp_work_area +.Lascebc: + .long _ascebc + +.section .data,"aw",@progbits + .balign 4096 +_sclp_work_area: + .fill 4096 +.previous diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 06201b93cbb..061479ff029 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -42,6 +42,7 @@ #include <linux/ctype.h> #include <linux/reboot.h> #include <linux/topology.h> +#include <linux/ftrace.h> #include <asm/ipl.h> #include <asm/uaccess.h> @@ -82,9 +83,6 @@ EXPORT_SYMBOL(console_devno); unsigned int console_irq = -1; EXPORT_SYMBOL(console_irq); -unsigned long machine_flags; -EXPORT_SYMBOL(machine_flags); - unsigned long elf_hwcap = 0; char elf_platform[ELF_PLATFORM_SIZE]; @@ -156,6 +154,16 @@ static int __init condev_setup(char *str) __setup("condev=", condev_setup); +static void __init set_preferred_console(void) +{ + if (MACHINE_IS_KVM) + add_preferred_console("hvc", 0, NULL); + else if (CONSOLE_IS_3215 || CONSOLE_IS_SCLP) + add_preferred_console("ttyS", 0, NULL); + else if (CONSOLE_IS_3270) + add_preferred_console("tty3270", 0, NULL); +} + static int __init conmode_setup(char *str) { #if defined(CONFIG_SCLP_CONSOLE) || defined(CONFIG_SCLP_VT220_CONSOLE) @@ -170,6 +178,7 @@ static int __init conmode_setup(char *str) if (strncmp(str, "3270", 5) == 0) SET_CONSOLE_3270; #endif + set_preferred_console(); return 1; } @@ -426,6 +435,7 @@ setup_lowcore(void) __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, 0) + PAGE_SIZE; lc->current_task = (unsigned long) init_thread_union.thread_info.task; lc->thread_info = (unsigned long) &init_thread_union; + lc->machine_flags = S390_lowcore.machine_flags; #ifndef CONFIG_64BIT if (MACHINE_HAS_IEEE) { lc->extended_save_area_addr = (__u32) @@ -436,6 +446,15 @@ setup_lowcore(void) #else lc->vdso_per_cpu_data = (unsigned long) &lc->paste[0]; #endif + lc->sync_enter_timer = S390_lowcore.sync_enter_timer; + lc->async_enter_timer = S390_lowcore.async_enter_timer; + lc->exit_timer = S390_lowcore.exit_timer; + lc->user_timer = S390_lowcore.user_timer; + lc->system_timer = S390_lowcore.system_timer; + lc->steal_timer = S390_lowcore.steal_timer; + lc->last_update_timer = S390_lowcore.last_update_timer; + lc->last_update_clock = S390_lowcore.last_update_clock; + lc->ftrace_func = S390_lowcore.ftrace_func; set_prefix((u32)(unsigned long) lc); lowcore_ptr[0] = lc; } @@ -710,7 +729,7 @@ 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. @@ -729,11 +748,20 @@ 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: @@ -772,9 +800,6 @@ static void __init setup_hwcaps(void) void __init setup_arch(char **cmdline_p) { - /* set up preferred console */ - add_preferred_console("ttyS", 0, NULL); - /* * print what head.S has found out about the machine */ @@ -794,11 +819,9 @@ setup_arch(char **cmdline_p) if (MACHINE_IS_VM) pr_info("Linux is running as a z/VM " "guest operating system in 64-bit mode\n"); - else if (MACHINE_IS_KVM) { + else if (MACHINE_IS_KVM) pr_info("Linux is running under KVM in 64-bit mode\n"); - add_preferred_console("hvc", 0, NULL); - s390_virtio_console_init(); - } else + else pr_info("Linux is running natively in 64-bit mode\n"); #endif /* CONFIG_64BIT */ @@ -843,6 +866,7 @@ setup_arch(char **cmdline_p) /* Setup default console */ conmode_default(); + set_preferred_console(); /* Setup zfcpdump support */ setup_zfcpdump(console_devno); diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c index 3cf74c3ccb6..6b4fef877f9 100644 --- a/arch/s390/kernel/signal.c +++ b/arch/s390/kernel/signal.c @@ -26,6 +26,7 @@ #include <linux/binfmts.h> #include <linux/tracehook.h> #include <linux/syscalls.h> +#include <linux/compat.h> #include <asm/ucontext.h> #include <asm/uaccess.h> #include <asm/lowcore.h> @@ -482,7 +483,7 @@ void do_signal(struct pt_regs *regs) /* Whee! Actually deliver the signal. */ int ret; #ifdef CONFIG_COMPAT - if (test_thread_flag(TIF_31BIT)) { + if (is_compat_task()) { ret = handle_signal32(signr, &ka, &info, oldset, regs); } else @@ -535,4 +536,6 @@ void do_notify_resume(struct pt_regs *regs) { clear_thread_flag(TIF_NOTIFY_RESUME); tracehook_notify_resume(regs); + if (current->replacement_session_keyring) + key_replace_session_keyring(); } diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 006ed5016eb..93e52039321 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -1,7 +1,7 @@ /* * arch/s390/kernel/smp.c * - * Copyright IBM Corp. 1999,2007 + * Copyright IBM Corp. 1999, 2009 * 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) @@ -47,8 +47,9 @@ #include <asm/timer.h> #include <asm/lowcore.h> #include <asm/sclp.h> -#include <asm/cpu.h> +#include <asm/cputime.h> #include <asm/vdso.h> +#include <asm/cpu.h> #include "entry.h" static struct task_struct *current_set[NR_CPUS]; @@ -70,6 +71,22 @@ static DEFINE_PER_CPU(struct cpu, cpu_devices); static void smp_ext_bitcall(int, ec_bit_sig); +static int cpu_stopped(int cpu) +{ + __u32 status; + + switch (signal_processor_ps(&status, 0, cpu, sigp_sense)) { + case sigp_status_stored: + /* Check for stopped and check stop state */ + if (status & 0x50) + return 1; + break; + default: + break; + } + return 0; +} + void smp_send_stop(void) { int cpu, rc; @@ -86,7 +103,7 @@ void smp_send_stop(void) rc = signal_processor(cpu, sigp_stop); } while (rc == sigp_busy); - while (!smp_cpu_not_running(cpu)) + while (!cpu_stopped(cpu)) cpu_relax(); } } @@ -129,11 +146,11 @@ static void smp_ext_bitcall(int cpu, ec_bit_sig sig) udelay(10); } -void arch_send_call_function_ipi(cpumask_t mask) +void arch_send_call_function_ipi_mask(const struct cpumask *mask) { int cpu; - for_each_cpu_mask(cpu, mask) + for_each_cpu(cpu, mask) smp_ext_bitcall(cpu, ec_call_function); } @@ -269,19 +286,6 @@ static inline void smp_get_save_area(unsigned int cpu, unsigned int phy_cpu) { } #endif /* CONFIG_ZFCPDUMP */ -static int cpu_stopped(int cpu) -{ - __u32 status; - - /* Check for stopped state */ - if (signal_processor_ps(&status, 0, cpu, sigp_sense) == - sigp_status_stored) { - if (status & 0x40) - return 1; - } - return 0; -} - static int cpu_known(int cpu_id) { int cpu; @@ -300,7 +304,7 @@ static int smp_rescan_cpus_sigp(cpumask_t avail) logical_cpu = cpumask_first(&avail); if (logical_cpu >= nr_cpu_ids) return 0; - for (cpu_id = 0; cpu_id <= 65535; cpu_id++) { + for (cpu_id = 0; cpu_id <= MAX_CPU_ADDRESS; cpu_id++) { if (cpu_known(cpu_id)) continue; __cpu_logical_map[logical_cpu] = cpu_id; @@ -379,7 +383,7 @@ static void __init smp_detect_cpus(void) /* Use sigp detection algorithm if sclp doesn't work. */ if (sclp_get_cpu_info(info)) { smp_use_sigp_detection = 1; - for (cpu = 0; cpu <= 65535; cpu++) { + for (cpu = 0; cpu <= MAX_CPU_ADDRESS; cpu++) { if (cpu == boot_cpu_addr) continue; __cpu_logical_map[CPU_INIT_NO] = cpu; @@ -470,10 +474,8 @@ static int __cpuinit smp_alloc_lowcore(int cpu) { unsigned long async_stack, panic_stack; struct _lowcore *lowcore; - int lc_order; - lc_order = sizeof(long) == 8 ? 1 : 0; - lowcore = (void *) __get_free_pages(GFP_KERNEL | GFP_DMA, lc_order); + lowcore = (void *) __get_free_pages(GFP_KERNEL | GFP_DMA, LC_ORDER); if (!lowcore) return -ENOMEM; async_stack = __get_free_pages(GFP_KERNEL, ASYNC_ORDER); @@ -504,16 +506,14 @@ static int __cpuinit smp_alloc_lowcore(int cpu) out: free_page(panic_stack); free_pages(async_stack, ASYNC_ORDER); - free_pages((unsigned long) lowcore, lc_order); + free_pages((unsigned long) lowcore, LC_ORDER); return -ENOMEM; } static void smp_free_lowcore(int cpu) { struct _lowcore *lowcore; - int lc_order; - lc_order = sizeof(long) == 8 ? 1 : 0; lowcore = lowcore_ptr[cpu]; #ifndef CONFIG_64BIT if (MACHINE_HAS_IEEE) @@ -523,7 +523,7 @@ static void smp_free_lowcore(int cpu) #endif free_page(lowcore->panic_stack - PAGE_SIZE); free_pages(lowcore->async_stack - ASYNC_SIZE, ASYNC_ORDER); - free_pages((unsigned long) lowcore, lc_order); + free_pages((unsigned long) lowcore, LC_ORDER); lowcore_ptr[cpu] = NULL; } @@ -571,6 +571,8 @@ int __cpuinit __cpu_up(unsigned int cpu) cpu_lowcore->current_task = (unsigned long) idle; cpu_lowcore->cpu_nr = cpu; cpu_lowcore->kernel_asce = S390_lowcore.kernel_asce; + cpu_lowcore->machine_flags = S390_lowcore.machine_flags; + cpu_lowcore->ftrace_func = S390_lowcore.ftrace_func; eieio(); while (signal_processor(cpu, sigp_restart) == sigp_busy) @@ -590,7 +592,8 @@ static int __init setup_possible_cpus(char *s) int pcpus, cpu; pcpus = simple_strtoul(s, NULL, 0); - for (cpu = 0; cpu < pcpus && cpu < nr_cpu_ids; cpu++) + init_cpu_possible(cpumask_of(0)); + for (cpu = 1; cpu < pcpus && cpu < nr_cpu_ids; cpu++) set_cpu_possible(cpu, true); return 0; } @@ -632,8 +635,10 @@ int __cpu_disable(void) void __cpu_die(unsigned int cpu) { /* Wait until target cpu is down */ - while (!smp_cpu_not_running(cpu)) + 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); } @@ -641,8 +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 (;;); } @@ -656,7 +661,6 @@ void __init smp_prepare_cpus(unsigned int max_cpus) unsigned long async_stack, panic_stack; struct _lowcore *lowcore; unsigned int cpu; - int lc_order; smp_detect_cpus(); @@ -666,8 +670,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus) print_cpu_info(); /* Reallocate current lowcore, but keep its contents. */ - lc_order = sizeof(long) == 8 ? 1 : 0; - lowcore = (void *) __get_free_pages(GFP_KERNEL | GFP_DMA, lc_order); + lowcore = (void *) __get_free_pages(GFP_KERNEL | GFP_DMA, LC_ORDER); panic_stack = __get_free_page(GFP_KERNEL); async_stack = __get_free_pages(GFP_KERNEL, ASYNC_ORDER); BUG_ON(!lowcore || !panic_stack || !async_stack); @@ -684,13 +687,14 @@ void __init smp_prepare_cpus(unsigned int max_cpus) #ifndef CONFIG_64BIT if (MACHINE_HAS_IEEE) lowcore->extended_save_area_addr = (u32) save_area; -#else - if (vdso_alloc_per_cpu(smp_processor_id(), lowcore)) - BUG(); #endif set_prefix((u32)(unsigned long) lowcore); local_mcck_enable(); local_irq_enable(); +#ifdef CONFIG_64BIT + if (vdso_alloc_per_cpu(smp_processor_id(), &S390_lowcore)) + BUG(); +#endif for_each_possible_cpu(cpu) if (cpu != smp_processor_id()) smp_create_idle(cpu); @@ -853,13 +857,20 @@ static ssize_t show_idle_count(struct sys_device *dev, { struct s390_idle_data *idle; unsigned long long idle_count; + unsigned int sequence; idle = &per_cpu(s390_idle, dev->id); - spin_lock(&idle->lock); +repeat: + sequence = idle->sequence; + smp_rmb(); + if (sequence & 1) + goto repeat; idle_count = idle->idle_count; if (idle->idle_enter) idle_count++; - spin_unlock(&idle->lock); + smp_rmb(); + if (idle->sequence != sequence) + goto repeat; return sprintf(buf, "%llu\n", idle_count); } static SYSDEV_ATTR(idle_count, 0444, show_idle_count, NULL); @@ -869,15 +880,22 @@ static ssize_t show_idle_time(struct sys_device *dev, { struct s390_idle_data *idle; unsigned long long now, idle_time, idle_enter; + unsigned int sequence; idle = &per_cpu(s390_idle, dev->id); - spin_lock(&idle->lock); now = get_clock(); +repeat: + sequence = idle->sequence; + smp_rmb(); + if (sequence & 1) + goto repeat; idle_time = idle->idle_time; idle_enter = idle->idle_enter; if (idle_enter != 0ULL && idle_enter < now) idle_time += now - idle_enter; - spin_unlock(&idle->lock); + smp_rmb(); + if (idle->sequence != sequence) + goto repeat; return sprintf(buf, "%llu\n", idle_time >> 12); } static SYSDEV_ATTR(idle_time_us, 0444, show_idle_time, NULL); @@ -905,11 +923,7 @@ static int __cpuinit smp_cpu_notify(struct notifier_block *self, case CPU_ONLINE: case CPU_ONLINE_FROZEN: idle = &per_cpu(s390_idle, cpu); - spin_lock_irq(&idle->lock); - idle->idle_enter = 0; - idle->idle_time = 0; - idle->idle_count = 0; - spin_unlock_irq(&idle->lock); + memset(idle, 0, sizeof(struct s390_idle_data)); if (sysfs_create_group(&s->kobj, &cpu_online_attr_group)) return NOTIFY_BAD; break; diff --git a/arch/s390/kernel/suspend.c b/arch/s390/kernel/suspend.c new file mode 100644 index 00000000000..cf9e5c6d552 --- /dev/null +++ b/arch/s390/kernel/suspend.c @@ -0,0 +1,63 @@ +/* + * Suspend support specific for s390. + * + * Copyright IBM Corp. 2009 + * + * Author(s): Hans-Joachim Picht <hans@linux.vnet.ibm.com> + */ + +#include <linux/pfn.h> +#include <asm/system.h> + +/* + * References to section boundaries + */ +extern const void __nosave_begin, __nosave_end; + +int pfn_is_nosave(unsigned long pfn) +{ + unsigned long nosave_begin_pfn = PFN_DOWN(__pa(&__nosave_begin)); + unsigned long nosave_end_pfn = PFN_DOWN(__pa(&__nosave_end)); + + /* Always save lowcore pages (LC protection might be enabled). */ + if (pfn <= LC_PAGES) + return 0; + if (pfn >= nosave_begin_pfn && pfn < nosave_end_pfn) + return 1; + /* Skip memory holes and read-only pages (NSS, DCSS, ...). */ + if (tprot(PFN_PHYS(pfn))) + return 1; + return 0; +} + +void save_processor_state(void) +{ + /* swsusp_arch_suspend() actually saves all cpu register contents. + * Machine checks must be disabled since swsusp_arch_suspend() stores + * register contents to their lowcore save areas. That's the same + * place where register contents on machine checks would be saved. + * To avoid register corruption disable machine checks. + * We must also disable machine checks in the new psw mask for + * program checks, since swsusp_arch_suspend() may generate program + * checks. Disabling machine checks for all other new psw masks is + * just paranoia. + */ + local_mcck_disable(); + /* Disable lowcore protection */ + __ctl_clear_bit(0,28); + S390_lowcore.external_new_psw.mask &= ~PSW_MASK_MCHECK; + S390_lowcore.svc_new_psw.mask &= ~PSW_MASK_MCHECK; + S390_lowcore.io_new_psw.mask &= ~PSW_MASK_MCHECK; + S390_lowcore.program_new_psw.mask &= ~PSW_MASK_MCHECK; +} + +void restore_processor_state(void) +{ + S390_lowcore.external_new_psw.mask |= PSW_MASK_MCHECK; + S390_lowcore.svc_new_psw.mask |= PSW_MASK_MCHECK; + S390_lowcore.io_new_psw.mask |= PSW_MASK_MCHECK; + S390_lowcore.program_new_psw.mask |= PSW_MASK_MCHECK; + /* Enable lowcore protection */ + __ctl_set_bit(0,28); + local_mcck_enable(); +} diff --git a/arch/s390/kernel/swsusp_asm64.S b/arch/s390/kernel/swsusp_asm64.S new file mode 100644 index 00000000000..0c26cc1898e --- /dev/null +++ b/arch/s390/kernel/swsusp_asm64.S @@ -0,0 +1,278 @@ +/* + * S390 64-bit swsusp implementation + * + * Copyright IBM Corp. 2009 + * + * Author(s): Hans-Joachim Picht <hans@linux.vnet.ibm.com> + * Michael Holzheu <holzheu@linux.vnet.ibm.com> + */ + +#include <asm/page.h> +#include <asm/ptrace.h> +#include <asm/thread_info.h> +#include <asm/asm-offsets.h> + +/* + * Save register context in absolute 0 lowcore and call swsusp_save() to + * create in-memory kernel image. The context is saved in the designated + * "store status" memory locations (see POP). + * We return from this function twice. The first time during the suspend to + * disk process. The second time via the swsusp_arch_resume() function + * (see below) in the resume process. + * This function runs with disabled interrupts. + */ + .section .text + .align 4 + .globl swsusp_arch_suspend +swsusp_arch_suspend: + stmg %r6,%r15,__SF_GPRS(%r15) + lgr %r1,%r15 + aghi %r15,-STACK_FRAME_OVERHEAD + stg %r1,__SF_BACKCHAIN(%r15) + + /* Deactivate DAT */ + stnsm __SF_EMPTY(%r15),0xfb + + /* Store prefix register on stack */ + stpx __SF_EMPTY(%r15) + + /* Save prefix register contents for lowcore */ + llgf %r4,__SF_EMPTY(%r15) + + /* Get pointer to save area */ + lghi %r1,0x1000 + + /* Save CPU address */ + stap __LC_CPU_ADDRESS(%r0) + + /* Store registers */ + mvc 0x318(4,%r1),__SF_EMPTY(%r15) /* move prefix to lowcore */ + stfpc 0x31c(%r1) /* store fpu control */ + std 0,0x200(%r1) /* store f0 */ + std 1,0x208(%r1) /* store f1 */ + std 2,0x210(%r1) /* store f2 */ + std 3,0x218(%r1) /* store f3 */ + std 4,0x220(%r1) /* store f4 */ + std 5,0x228(%r1) /* store f5 */ + std 6,0x230(%r1) /* store f6 */ + std 7,0x238(%r1) /* store f7 */ + std 8,0x240(%r1) /* store f8 */ + std 9,0x248(%r1) /* store f9 */ + std 10,0x250(%r1) /* store f10 */ + std 11,0x258(%r1) /* store f11 */ + std 12,0x260(%r1) /* store f12 */ + std 13,0x268(%r1) /* store f13 */ + std 14,0x270(%r1) /* store f14 */ + std 15,0x278(%r1) /* store f15 */ + stam %a0,%a15,0x340(%r1) /* store access registers */ + stctg %c0,%c15,0x380(%r1) /* store control registers */ + 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 + + /* Set prefix page to zero */ + xc __SF_EMPTY(4,%r15),__SF_EMPTY(%r15) + spx __SF_EMPTY(%r15) + + lghi %r2,0 + lghi %r3,2*PAGE_SIZE + lghi %r5,2*PAGE_SIZE +1: mvcle %r2,%r4,0 + jo 1b + + /* Save image */ + brasl %r14,swsusp_save + + /* Restore prefix register and return */ + lghi %r1,0x1000 + spx 0x318(%r1) + lmg %r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15) + lghi %r2,0 + br %r14 + +/* + * Restore saved memory image to correct place and restore register context. + * Then we return to the function that called swsusp_arch_suspend(). + * swsusp_arch_resume() runs with disabled interrupts. + */ + .globl swsusp_arch_resume +swsusp_arch_resume: + stmg %r6,%r15,__SF_GPRS(%r15) + lgr %r1,%r15 + aghi %r15,-STACK_FRAME_OVERHEAD + stg %r1,__SF_BACKCHAIN(%r15) + + /* Make all free pages stable */ + lghi %r2,1 + brasl %r14,arch_set_page_states + + /* Deactivate DAT */ + stnsm __SF_EMPTY(%r15),0xfb + + /* Set prefix page to zero */ + xc __SF_EMPTY(4,%r15),__SF_EMPTY(%r15) + spx __SF_EMPTY(%r15) + + /* Restore saved image */ + larl %r1,restore_pblist + lg %r1,0(%r1) + ltgr %r1,%r1 + jz 2f +0: + lg %r2,8(%r1) + lg %r4,0(%r1) + lghi %r3,PAGE_SIZE + lghi %r5,PAGE_SIZE +1: + mvcle %r2,%r4,0 + jo 1b + lg %r1,16(%r1) + ltgr %r1,%r1 + jnz 0b +2: + ptlb /* flush tlb */ + + /* Reset System */ + larl %r1,restart_entry + larl %r2,.Lrestart_diag308_psw + og %r1,0(%r2) + stg %r1,0(%r0) + larl %r1,.Lnew_pgm_check_psw + epsw %r2,%r3 + stm %r2,%r3,0(%r1) + mvc __LC_PGM_NEW_PSW(16,%r0),0(%r1) + lghi %r0,0 + diag %r0,%r0,0x308 +restart_entry: + lhi %r1,1 + sigp %r1,%r0,0x12 + sam64 + larl %r1,.Lnew_pgm_check_psw + lpswe 0(%r1) +pgm_check_entry: + + /* Switch to original suspend CPU */ + larl %r1,.Lresume_cpu /* Resume CPU address: r2 */ + stap 0(%r1) + llgh %r2,0(%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 */ + mvc __LC_RESTART_PSW(16,%r0),0(%r4) +3: + sigp %r9,%r1,__SIGP_INITIAL_CPU_RESET + brc 8,4f /* accepted */ + brc 2,3b /* busy, try again */ + + /* Suspend CPU not available -> panic */ + larl %r15,init_thread_union + ahi %r15,1<<(PAGE_SHIFT+THREAD_ORDER) + larl %r2,.Lpanic_string + larl %r3,_sclp_print_early + lghi %r1,0 + sam31 + sigp %r1,%r0,0x12 + basr %r14,%r3 + larl %r3,.Ldisabled_wait_31 + lpsw 0(%r3) +4: + /* Switch to suspend CPU */ + sigp %r9,%r1,__SIGP_RESTART /* start suspend CPU */ + 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: + larl %r1,.Lresume_cpu + 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 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 */ + + lctlg %c0,%c15,0x380(%r13) /* load control registers */ + lam %a0,%a15,0x340(%r13) /* load access registers */ + + lfpc 0x31c(%r13) /* load fpu control */ + ld 0,0x200(%r13) /* load f0 */ + ld 1,0x208(%r13) /* load f1 */ + ld 2,0x210(%r13) /* load f2 */ + ld 3,0x218(%r13) /* load f3 */ + ld 4,0x220(%r13) /* load f4 */ + ld 5,0x228(%r13) /* load f5 */ + ld 6,0x230(%r13) /* load f6 */ + ld 7,0x238(%r13) /* load f7 */ + ld 8,0x240(%r13) /* load f8 */ + ld 9,0x248(%r13) /* load f9 */ + ld 10,0x250(%r13) /* load f10 */ + ld 11,0x258(%r13) /* load f11 */ + ld 12,0x260(%r13) /* load f12 */ + ld 13,0x268(%r13) /* load f13 */ + ld 14,0x270(%r13) /* load f14 */ + ld 15,0x278(%r13) /* load f15 */ + + /* Load old stack */ + lg %r15,0x2f8(%r13) + + /* Restore prefix register */ + spx 0x318(%r13) + + /* Activate DAT */ + stosm __SF_EMPTY(%r15),0x04 + + /* Make all free pages unstable */ + lghi %r2,0 + brasl %r14,arch_set_page_states + + /* Return 0 */ + lmg %r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15) + lghi %r2,0 + br %r14 + + .section .data.nosave,"aw",@progbits + .align 8 +.Ldisabled_wait_31: + .long 0x000a0000,0x00000000 +.Lpanic_string: + .asciz "Resume not possible because suspend CPU is no longer available" + .align 8 +.Lrestart_diag308_psw: + .long 0x00080000,0x80000000 +.Lrestart_suspend_psw: + .quad 0x0000000180000000,restart_suspend +.Lnew_pgm_check_psw: + .quad 0,pgm_check_entry +.Lresume_cpu: + .byte 0,0 diff --git a/arch/s390/kernel/sys_s390.c b/arch/s390/kernel/sys_s390.c index c7ae4b17e0e..e9d94f61d50 100644 --- a/arch/s390/kernel/sys_s390.c +++ b/arch/s390/kernel/sys_s390.c @@ -29,7 +29,6 @@ #include <linux/personality.h> #include <linux/unistd.h> #include <linux/ipc.h> -#include <linux/syscalls.h> #include <asm/uaccess.h> #include "entry.h" diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S index fe5b25a988a..30eca070d42 100644 --- a/arch/s390/kernel/syscalls.S +++ b/arch/s390/kernel/syscalls.S @@ -19,7 +19,7 @@ SYSCALL(sys_restart_syscall,sys_restart_syscall,sys_restart_syscall) SYSCALL(sys_creat,sys_creat,sys32_creat_wrapper) SYSCALL(sys_link,sys_link,sys32_link_wrapper) SYSCALL(sys_unlink,sys_unlink,sys32_unlink_wrapper) /* 10 */ -SYSCALL(sys_execve,sys_execve,sys32_execve) +SYSCALL(sys_execve,sys_execve,sys32_execve_wrapper) SYSCALL(sys_chdir,sys_chdir,sys32_chdir_wrapper) SYSCALL(sys_time,sys_ni_syscall,sys32_time_wrapper) /* old time syscall */ SYSCALL(sys_mknod,sys_mknod,sys32_mknod_wrapper) @@ -128,7 +128,7 @@ SYSCALL(sys_sysinfo,sys_sysinfo,compat_sys_sysinfo_wrapper) SYSCALL(sys_ipc,sys_ipc,sys32_ipc_wrapper) SYSCALL(sys_fsync,sys_fsync,sys32_fsync_wrapper) SYSCALL(sys_sigreturn,sys_sigreturn,sys32_sigreturn) -SYSCALL(sys_clone,sys_clone,sys32_clone) /* 120 */ +SYSCALL(sys_clone,sys_clone,sys_clone_wrapper) /* 120 */ SYSCALL(sys_setdomainname,sys_setdomainname,sys32_setdomainname_wrapper) SYSCALL(sys_newuname,sys_s390_newuname,sys32_newuname_wrapper) NI_SYSCALL /* modify_ldt for i386 */ @@ -136,8 +136,8 @@ SYSCALL(sys_adjtimex,sys_adjtimex,compat_sys_adjtimex_wrapper) SYSCALL(sys_mprotect,sys_mprotect,sys32_mprotect_wrapper) /* 125 */ SYSCALL(sys_sigprocmask,sys_sigprocmask,compat_sys_sigprocmask_wrapper) NI_SYSCALL /* old "create module" */ -SYSCALL(sys_init_module,sys_init_module,sys32_init_module_wrapper) -SYSCALL(sys_delete_module,sys_delete_module,sys32_delete_module_wrapper) +SYSCALL(sys_init_module,sys_init_module,sys_init_module_wrapper) +SYSCALL(sys_delete_module,sys_delete_module,sys_delete_module_wrapper) NI_SYSCALL /* 130: old get_kernel_syms */ SYSCALL(sys_quotactl,sys_quotactl,sys32_quotactl_wrapper) SYSCALL(sys_getpgid,sys_getpgid,sys32_getpgid_wrapper) @@ -336,3 +336,7 @@ SYSCALL(sys_inotify_init1,sys_inotify_init1,sys_inotify_init1_wrapper) SYSCALL(sys_pipe2,sys_pipe2,sys_pipe2_wrapper) /* 325 */ SYSCALL(sys_dup3,sys_dup3,sys_dup3_wrapper) SYSCALL(sys_epoll_create1,sys_epoll_create1,sys_epoll_create1_wrapper) +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) diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index f72d41068dc..68e1ecf5eba 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -36,7 +36,6 @@ #include <linux/notifier.h> #include <linux/clocksource.h> #include <linux/clockchips.h> -#include <linux/bootmem.h> #include <asm/uaccess.h> #include <asm/delay.h> #include <asm/s390_ext.h> @@ -52,9 +51,6 @@ #define USECS_PER_JIFFY ((unsigned long) 1000000/HZ) #define CLK_TICKS_PER_JIFFY ((unsigned long) USECS_PER_JIFFY << 12) -/* The value of the TOD clock for 1.1.1970. */ -#define TOD_UNIX_EPOCH 0x7d91048bca000000ULL - /* * Create a small time difference between the timer interrupts * on the different cpus to avoid lock contention. @@ -63,18 +59,17 @@ #define TICK_SIZE tick -static ext_int_info_t ext_int_info_cc; -static ext_int_info_t ext_int_etr_cc; -static u64 sched_clock_base_cc; +u64 sched_clock_base_cc = -1; /* Force to data section. */ +EXPORT_SYMBOL_GPL(sched_clock_base_cc); static DEFINE_PER_CPU(struct clock_event_device, comparators); /* * Scheduler clock - returns current time in nanosec units. */ -unsigned long long sched_clock(void) +unsigned long long notrace sched_clock(void) { - return ((get_clock_xt() - sched_clock_base_cc) * 125) >> 9; + return (get_clock_monotonic() * 125) >> 9; } /* @@ -96,12 +91,7 @@ void tod_to_timeval(__u64 todval, struct timespec *xtime) todval -= (sec * 1000000) << 12; xtime->tv_nsec = ((todval * 1000) >> 12); } - -#ifdef CONFIG_PROFILING -#define s390_do_profile() profile_tick(CPU_PROFILING) -#else -#define s390_do_profile() do { ; } while(0) -#endif /* CONFIG_PROFILING */ +EXPORT_SYMBOL(tod_to_timeval); void clock_comparator_work(void) { @@ -111,7 +101,6 @@ void clock_comparator_work(void) set_clock_comparator(S390_lowcore.clock_comparator); cd = &__get_cpu_var(comparators); cd->event_handler(cd); - s390_do_profile(); } /* @@ -195,25 +184,17 @@ static void timing_alert_interrupt(__u16 code) static void etr_reset(void); static void stp_reset(void); -/* - * Get the TOD clock running. - */ -static u64 __init reset_tod_clock(void) +void read_persistent_clock(struct timespec *ts) { - u64 time; - - etr_reset(); - stp_reset(); - if (store_clock(&time) == 0) - return time; - /* TOD clock not running. Set the clock to Unix Epoch. */ - if (set_clock(TOD_UNIX_EPOCH) != 0 || store_clock(&time) != 0) - panic("TOD clock not operational."); + tod_to_timeval(get_clock() - TOD_UNIX_EPOCH, ts); +} - return TOD_UNIX_EPOCH; +void read_boot_clock(struct timespec *ts) +{ + tod_to_timeval(sched_clock_base_cc - TOD_UNIX_EPOCH, ts); } -static cycle_t read_tod_clock(void) +static cycle_t read_tod_clock(struct clocksource *cs) { return get_clock(); } @@ -228,8 +209,13 @@ static struct clocksource clocksource_tod = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; +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; @@ -265,30 +251,24 @@ void update_vsyscall_tz(void) */ void __init time_init(void) { - sched_clock_base_cc = reset_tod_clock(); - - /* set xtime */ - tod_to_timeval(sched_clock_base_cc - TOD_UNIX_EPOCH, &xtime); - set_normalized_timespec(&wall_to_monotonic, - -xtime.tv_sec, -xtime.tv_nsec); + /* Reset time synchronization interfaces. */ + etr_reset(); + stp_reset(); /* request the clock comparator external interrupt */ - if (register_early_external_interrupt(0x1004, - clock_comparator_interrupt, - &ext_int_info_cc) != 0) + if (register_external_interrupt(0x1004, clock_comparator_interrupt)) panic("Couldn't request external interrupt 0x1004"); - if (clocksource_register(&clocksource_tod) != 0) - panic("Could not register TOD clock source"); - /* request the timing alert external interrupt */ - if (register_early_external_interrupt(0x1406, - timing_alert_interrupt, - &ext_int_etr_cc) != 0) + if (register_external_interrupt(0x1406, timing_alert_interrupt)) panic("Couldn't request external interrupt 0x1406"); + if (clocksource_register(&clocksource_tod) != 0) + panic("Could not register TOD clock source"); + /* Enable TOD clock interrupts on the boot cpu. */ init_cpu_timer(); + /* Enable cpu timer interrupts on the boot cpu. */ vtime_init(); } @@ -1423,6 +1403,7 @@ static void *stp_page; static void stp_work_fn(struct work_struct *work); static DEFINE_MUTEX(stp_work_mutex); static DECLARE_WORK(stp_work, stp_work_fn); +static struct timer_list stp_timer; static int __init early_parse_stp(char *p) { @@ -1441,23 +1422,29 @@ static void __init stp_reset(void) { int rc; - stp_page = alloc_bootmem_pages(PAGE_SIZE); + stp_page = (void *) get_zeroed_page(GFP_ATOMIC); rc = chsc_sstpc(stp_page, STP_OP_CTRL, 0x0000); if (rc == 0) set_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags); else if (stp_online) { pr_warning("The real or virtual hardware system does " "not provide an STP interface\n"); - free_bootmem((unsigned long) stp_page, PAGE_SIZE); + free_page((unsigned long) stp_page); stp_page = NULL; stp_online = 0; } } +static void stp_timeout(unsigned long dummy) +{ + queue_work(time_sync_wq, &stp_work); +} + static int __init stp_init(void) { if (!test_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags)) return 0; + setup_timer(&stp_timer, stp_timeout, 0UL); time_init_wq(); if (!stp_online) return 0; @@ -1565,6 +1552,7 @@ static void stp_work_fn(struct work_struct *work) if (!stp_online) { chsc_sstpc(stp_page, STP_OP_CTRL, 0x0000); + del_timer_sync(&stp_timer); goto out_unlock; } @@ -1586,6 +1574,13 @@ static void stp_work_fn(struct work_struct *work) stop_machine(stp_sync_clock, &stp_sync, &cpu_online_map); put_online_cpus(); + if (!check_sync_clock()) + /* + * There is a usable clock but the synchonization failed. + * Retry after a second. + */ + mod_timer(&stp_timer, jiffies + HZ); + out_unlock: mutex_unlock(&stp_work_mutex); } diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c index 89b2e7f1b7a..adfb32aa6d5 100644 --- a/arch/s390/kernel/vdso.c +++ b/arch/s390/kernel/vdso.c @@ -22,7 +22,7 @@ #include <linux/elf.h> #include <linux/security.h> #include <linux/bootmem.h> - +#include <linux/compat.h> #include <asm/pgtable.h> #include <asm/system.h> #include <asm/processor.h> @@ -53,8 +53,19 @@ unsigned int __read_mostly vdso_enabled = 1; static int __init vdso_setup(char *s) { - vdso_enabled = simple_strtoul(s, NULL, 0); - return 1; + unsigned long val; + int rc; + + rc = 0; + if (strncmp(s, "on", 3) == 0) + vdso_enabled = 1; + else if (strncmp(s, "off", 4) == 0) + vdso_enabled = 0; + else { + rc = strict_strtoul(s, 0, &val); + vdso_enabled = rc ? 0 : !!val; + } + return !rc; } __setup("vdso=", vdso_setup); @@ -64,7 +75,7 @@ __setup("vdso=", vdso_setup); static union { struct vdso_data data; u8 page[PAGE_SIZE]; -} vdso_data_store __attribute__((__section__(".data.page_aligned"))); +} vdso_data_store __page_aligned_data; struct vdso_data *vdso_data = &vdso_data_store.data; /* @@ -203,7 +214,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) vdso_pagelist = vdso64_pagelist; vdso_pages = vdso64_pages; #ifdef CONFIG_COMPAT - if (test_thread_flag(TIF_31BIT)) { + if (is_compat_task()) { vdso_pagelist = vdso32_pagelist; vdso_pages = vdso32_pages; } @@ -236,6 +247,13 @@ 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 @@ -256,14 +274,7 @@ 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/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile index ca78ad60ba2..d13e8755a8c 100644 --- a/arch/s390/kernel/vdso32/Makefile +++ b/arch/s390/kernel/vdso32/Makefile @@ -13,7 +13,7 @@ KBUILD_AFLAGS_31 += -m31 -s KBUILD_CFLAGS_31 := $(filter-out -m64,$(KBUILD_CFLAGS)) KBUILD_CFLAGS_31 += -m31 -fPIC -shared -fno-common -fno-builtin KBUILD_CFLAGS_31 += -nostdlib -Wl,-soname=linux-vdso32.so.1 \ - $(call ld-option, -Wl$(comma)--hash-style=sysv) + $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_31) $(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_31) diff --git a/arch/s390/kernel/vdso32/vdso32_wrapper.S b/arch/s390/kernel/vdso32/vdso32_wrapper.S index 61639a89e70..ae42f8ce350 100644 --- a/arch/s390/kernel/vdso32/vdso32_wrapper.S +++ b/arch/s390/kernel/vdso32/vdso32_wrapper.S @@ -1,7 +1,8 @@ #include <linux/init.h> +#include <linux/linkage.h> #include <asm/page.h> - .section ".data.page_aligned" + __PAGE_ALIGNED_DATA .globl vdso32_start, vdso32_end .balign PAGE_SIZE diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile index 6fc8e829258..449352dda9c 100644 --- a/arch/s390/kernel/vdso64/Makefile +++ b/arch/s390/kernel/vdso64/Makefile @@ -13,7 +13,7 @@ KBUILD_AFLAGS_64 += -m64 -s KBUILD_CFLAGS_64 := $(filter-out -m64,$(KBUILD_CFLAGS)) KBUILD_CFLAGS_64 += -m64 -fPIC -shared -fno-common -fno-builtin KBUILD_CFLAGS_64 += -nostdlib -Wl,-soname=linux-vdso64.so.1 \ - $(call ld-option, -Wl$(comma)--hash-style=sysv) + $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_64) $(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_64) diff --git a/arch/s390/kernel/vdso64/clock_gettime.S b/arch/s390/kernel/vdso64/clock_gettime.S index 79dbfee831e..49106c6e6f8 100644 --- a/arch/s390/kernel/vdso64/clock_gettime.S +++ b/arch/s390/kernel/vdso64/clock_gettime.S @@ -88,10 +88,17 @@ __kernel_clock_gettime: llilh %r4,0x0100 sar %a4,%r4 lghi %r4,0 + epsw %r5,0 sacf 512 /* Magic ectg instruction */ .insn ssf,0xc80100000000,__VDSO_ECTG_BASE(4),__VDSO_ECTG_USER(4),4 - sacf 0 - sar %a4,%r2 + tml %r5,0x4000 + jo 11f + tml %r5,0x8000 + jno 10f + sacf 256 + j 11f +10: sacf 0 +11: sar %a4,%r2 algr %r1,%r0 /* r1 = cputime as TOD value */ mghi %r1,1000 /* convert to nanoseconds */ srlg %r1,%r1,12 /* r1 = cputime in nanosec */ diff --git a/arch/s390/kernel/vdso64/vdso64_wrapper.S b/arch/s390/kernel/vdso64/vdso64_wrapper.S index d8e2ac14d56..c245842b516 100644 --- a/arch/s390/kernel/vdso64/vdso64_wrapper.S +++ b/arch/s390/kernel/vdso64/vdso64_wrapper.S @@ -1,7 +1,8 @@ #include <linux/init.h> +#include <linux/linkage.h> #include <asm/page.h> - .section ".data.page_aligned" + __PAGE_ALIGNED_DATA .globl vdso64_start, vdso64_end .balign PAGE_SIZE diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 7a2063eb88f..a68ac10213b 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -29,11 +29,12 @@ SECTIONS . = 0x00000000; .text : { _text = .; /* Text and read-only data */ - *(.text.head) - TEXT_TEXT + HEAD_TEXT + TEXT_TEXT SCHED_TEXT LOCK_TEXT KPROBES_TEXT + IRQENTRY_TEXT *(.fixup) *(.gnu.warning) } :text = 0x0700 @@ -50,56 +51,20 @@ SECTIONS . = ALIGN(PAGE_SIZE); _eshared = .; /* End of shareable data */ + _sdata = .; /* Start of data section */ - . = ALIGN(16); /* Exception table */ - __ex_table : { - __start___ex_table = .; - *(__ex_table) - __stop___ex_table = .; - } :data + EXCEPTION_TABLE(16) :data - .data : { /* Data */ - DATA_DATA - CONSTRUCTORS - } - - . = ALIGN(PAGE_SIZE); - .data_nosave : { - __nosave_begin = .; - *(.data.nosave) - } - . = ALIGN(PAGE_SIZE); - __nosave_end = .; - - . = ALIGN(PAGE_SIZE); - .data.page_aligned : { - *(.data.idt) - } + RW_DATA_SECTION(0x100, PAGE_SIZE, THREAD_SIZE) - . = ALIGN(0x100); - .data.cacheline_aligned : { - *(.data.cacheline_aligned) - } - - . = ALIGN(0x100); - .data.read_mostly : { - *(.data.read_mostly) - } _edata = .; /* End of data section */ - . = ALIGN(THREAD_SIZE); /* init_task */ - .data.init_task : { - *(.data.init_task) - } - /* will be freed after init */ . = ALIGN(PAGE_SIZE); /* Init code and data */ __init_begin = .; - .init.text : { - _sinittext = .; - INIT_TEXT - _einittext = .; - } + + INIT_TEXT_SECTION(PAGE_SIZE) + /* * .exit.text is discarded at runtime, not link time, * to deal with references from __bug_table @@ -110,59 +75,20 @@ SECTIONS /* early.c uses stsi, which requires page aligned data. */ . = ALIGN(PAGE_SIZE); - .init.data : { - INIT_DATA - } - . = ALIGN(0x100); - .init.setup : { - __setup_start = .; - *(.init.setup) - __setup_end = .; - } - .initcall.init : { - __initcall_start = .; - INITCALLS - __initcall_end = .; - } - - .con_initcall.init : { - __con_initcall_start = .; - *(.con_initcall.init) - __con_initcall_end = .; - } - SECURITY_INIT - -#ifdef CONFIG_BLK_DEV_INITRD - . = ALIGN(0x100); - .init.ramfs : { - __initramfs_start = .; - *(.init.ramfs) - . = ALIGN(2); - __initramfs_end = .; - } -#endif + INIT_DATA_SECTION(0x100) PERCPU(PAGE_SIZE) . = ALIGN(PAGE_SIZE); __init_end = .; /* freed after init ends here */ - /* BSS */ - .bss : { - __bss_start = .; - *(.bss) - . = ALIGN(2); - __bss_stop = .; - } + BSS_SECTION(0, 2, 0) _end = . ; - /* Sections to be discarded */ - /DISCARD/ : { - EXIT_DATA - *(.exitcall.exit) - } - /* Debugging sections. */ STABS_DEBUG DWARF_DEBUG + + /* Sections to be discarded */ + DISCARDS } diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index ecf0304e61c..b59a812a010 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -23,15 +23,11 @@ #include <asm/s390_ext.h> #include <asm/timer.h> #include <asm/irq_regs.h> -#include <asm/cpu.h> - -static ext_int_info_t ext_int_info_timer; +#include <asm/cputime.h> static DEFINE_PER_CPU(struct vtimer_queue, virt_cpu_timer); -DEFINE_PER_CPU(struct s390_idle_data, s390_idle) = { - .lock = __SPIN_LOCK_UNLOCKED(s390_idle.lock) -}; +DEFINE_PER_CPU(struct s390_idle_data, s390_idle); static inline __u64 get_vtimer(void) { @@ -134,6 +130,8 @@ void vtime_start_cpu(void) /* Account time spent with enabled wait psw loaded as idle time. */ idle_time = S390_lowcore.int_clock - idle->idle_enter; account_idle_time(idle_time); + S390_lowcore.steal_timer += + idle->idle_enter - S390_lowcore.last_update_clock; S390_lowcore.last_update_clock = S390_lowcore.int_clock; /* Account system time spent going idle. */ @@ -151,11 +149,13 @@ void vtime_start_cpu(void) vq->elapsed -= vq->idle - S390_lowcore.async_enter_timer; } - spin_lock(&idle->lock); + idle->sequence++; + smp_wmb(); idle->idle_time += idle_time; idle->idle_enter = 0ULL; idle->idle_count++; - spin_unlock(&idle->lock); + smp_wmb(); + idle->sequence++; } void vtime_stop_cpu(void) @@ -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; @@ -238,6 +240,30 @@ void vtime_stop_cpu(void) } } +cputime64_t s390_get_idle_time(int cpu) +{ + struct s390_idle_data *idle; + unsigned long long now, idle_time, idle_enter; + unsigned int sequence; + + idle = &per_cpu(s390_idle, cpu); + + now = get_clock(); +repeat: + sequence = idle->sequence; + smp_rmb(); + if (sequence & 1) + goto repeat; + idle_time = 0; + idle_enter = idle->idle_enter; + if (idle_enter != 0ULL && idle_enter < now) + idle_time = now - idle_enter; + smp_rmb(); + if (idle->sequence != sequence) + goto repeat; + return idle_time; +} + /* * Sorted add to a list. List is linear searched until first bigger * element is found. @@ -425,17 +451,7 @@ void add_virt_timer_periodic(void *new) } EXPORT_SYMBOL(add_virt_timer_periodic); -/* - * If we change a pending timer the function must be called on the CPU - * where the timer is running on, e.g. by smp_call_function_single() - * - * The original mod_timer adds the timer if it is not pending. For - * compatibility we do the same. The timer will be added on the current - * CPU as a oneshot timer. - * - * returns whether it has modified a pending timer (1) or not (0) - */ -int mod_virt_timer(struct vtimer_list *timer, __u64 expires) +int __mod_vtimer(struct vtimer_list *timer, __u64 expires, int periodic) { struct vtimer_queue *vq; unsigned long flags; @@ -444,39 +460,35 @@ int mod_virt_timer(struct vtimer_list *timer, __u64 expires) BUG_ON(!timer->function); BUG_ON(!expires || expires > VTIMER_MAX_SLICE); - /* - * This is a common optimization triggered by the - * networking code - if the timer is re-modified - * to be the same thing then just return: - */ if (timer->expires == expires && vtimer_pending(timer)) return 1; cpu = get_cpu(); vq = &per_cpu(virt_cpu_timer, cpu); - /* check if we run on the right CPU */ - BUG_ON(timer->cpu != cpu); - /* disable interrupts before test if timer is pending */ spin_lock_irqsave(&vq->lock, flags); /* if timer isn't pending add it on the current CPU */ if (!vtimer_pending(timer)) { spin_unlock_irqrestore(&vq->lock, flags); - /* we do not activate an interval timer with mod_virt_timer */ - timer->interval = 0; + + if (periodic) + timer->interval = expires; + else + timer->interval = 0; timer->expires = expires; timer->cpu = cpu; internal_add_vtimer(timer); return 0; } + /* check if we run on the right CPU */ + BUG_ON(timer->cpu != cpu); + list_del_init(&timer->entry); timer->expires = expires; - - /* also change the interval if we have an interval timer */ - if (timer->interval) + if (periodic) timer->interval = expires; /* the timer can't expire anymore so we can release the lock */ @@ -484,9 +496,32 @@ int mod_virt_timer(struct vtimer_list *timer, __u64 expires) internal_add_vtimer(timer); return 1; } + +/* + * If we change a pending timer the function must be called on the CPU + * where the timer is running on. + * + * returns whether it has modified a pending timer (1) or not (0) + */ +int mod_virt_timer(struct vtimer_list *timer, __u64 expires) +{ + return __mod_vtimer(timer, expires, 0); +} EXPORT_SYMBOL(mod_virt_timer); /* + * If we change a pending timer the function must be called on the CPU + * where the timer is running on. + * + * returns whether it has modified a pending timer (1) or not (0) + */ +int mod_virt_timer_periodic(struct vtimer_list *timer, __u64 expires) +{ + return __mod_vtimer(timer, expires, 1); +} +EXPORT_SYMBOL(mod_virt_timer_periodic); + +/* * delete a virtual timer * * returns whether the deleted timer was pending (1) or not (0) @@ -516,16 +551,8 @@ EXPORT_SYMBOL(del_virt_timer); */ void init_cpu_vtimer(void) { - struct thread_info *ti = current_thread_info(); struct vtimer_queue *vq; - S390_lowcore.user_timer = ti->user_timer; - S390_lowcore.system_timer = ti->system_timer; - - /* kick the virtual timer */ - asm volatile ("STCK %0" : "=m" (S390_lowcore.last_update_clock)); - asm volatile ("STPT %0" : "=m" (S390_lowcore.last_update_timer)); - /* initialize per cpu vtimer structure */ vq = &__get_cpu_var(virt_cpu_timer); INIT_LIST_HEAD(&vq->list); @@ -538,8 +565,7 @@ void init_cpu_vtimer(void) void __init vtime_init(void) { /* request the cpu timer external interrupt */ - if (register_early_external_interrupt(0x1005, do_cpu_timer_interrupt, - &ext_int_info_timer) != 0) + if (register_external_interrupt(0x1005, do_cpu_timer_interrupt)) panic("Couldn't request external interrupt 0x1005"); /* Enable cpu timer interrupts on the boot cpu. */ diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig index 3e260b7e37b..bf164fc2186 100644 --- a/arch/s390/kvm/Kconfig +++ b/arch/s390/kvm/Kconfig @@ -1,11 +1,7 @@ # # KVM configuration # -config HAVE_KVM - bool - -config HAVE_KVM_IRQCHIP - bool +source "virt/kvm/Kconfig" menuconfig VIRTUALIZATION bool "Virtualization" @@ -38,9 +34,6 @@ config KVM If unsure, say N. -config KVM_TRACE - bool - # OK, it's a little counter-intuitive to do this, but it puts it neatly under # the virtualization menu. source drivers/virtio/Kconfig diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h index ed60f3a74a8..03c716a0f01 100644 --- a/arch/s390/kvm/gaccess.h +++ b/arch/s390/kvm/gaccess.h @@ -1,7 +1,7 @@ /* * gaccess.h - access guest memory * - * Copyright IBM Corp. 2008 + * Copyright IBM Corp. 2008,2009 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License (version 2 only) @@ -16,13 +16,14 @@ #include <linux/compiler.h> #include <linux/kvm_host.h> #include <asm/uaccess.h> +#include "kvm-s390.h" static inline void __user *__guestaddr_to_user(struct kvm_vcpu *vcpu, unsigned long guestaddr) { unsigned long prefix = vcpu->arch.sie_block->prefix; - unsigned long origin = vcpu->kvm->arch.guest_origin; - unsigned long memsize = vcpu->kvm->arch.guest_memsize; + unsigned long origin = vcpu->arch.sie_block->gmsor; + unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu); if (guestaddr < 2 * PAGE_SIZE) guestaddr += prefix; @@ -158,8 +159,8 @@ static inline int copy_to_guest(struct kvm_vcpu *vcpu, unsigned long guestdest, const void *from, unsigned long n) { unsigned long prefix = vcpu->arch.sie_block->prefix; - unsigned long origin = vcpu->kvm->arch.guest_origin; - unsigned long memsize = vcpu->kvm->arch.guest_memsize; + unsigned long origin = vcpu->arch.sie_block->gmsor; + unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu); if ((guestdest < 2 * PAGE_SIZE) && (guestdest + n > 2 * PAGE_SIZE)) goto slowpath; @@ -209,8 +210,8 @@ static inline int copy_from_guest(struct kvm_vcpu *vcpu, void *to, unsigned long guestsrc, unsigned long n) { unsigned long prefix = vcpu->arch.sie_block->prefix; - unsigned long origin = vcpu->kvm->arch.guest_origin; - unsigned long memsize = vcpu->kvm->arch.guest_memsize; + unsigned long origin = vcpu->arch.sie_block->gmsor; + unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu); if ((guestsrc < 2 * PAGE_SIZE) && (guestsrc + n > 2 * PAGE_SIZE)) goto slowpath; @@ -244,8 +245,8 @@ static inline int copy_to_guest_absolute(struct kvm_vcpu *vcpu, unsigned long guestdest, const void *from, unsigned long n) { - unsigned long origin = vcpu->kvm->arch.guest_origin; - unsigned long memsize = vcpu->kvm->arch.guest_memsize; + unsigned long origin = vcpu->arch.sie_block->gmsor; + unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu); if (guestdest + n > memsize) return -EFAULT; @@ -262,8 +263,8 @@ static inline int copy_from_guest_absolute(struct kvm_vcpu *vcpu, void *to, unsigned long guestsrc, unsigned long n) { - unsigned long origin = vcpu->kvm->arch.guest_origin; - unsigned long memsize = vcpu->kvm->arch.guest_memsize; + unsigned long origin = vcpu->arch.sie_block->gmsor; + unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu); if (guestsrc + n > memsize) return -EFAULT; diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index 9d19803111b..ba9d8a7bc1a 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -1,7 +1,7 @@ /* * intercept.c - in-kernel handling for sie intercepts * - * Copyright IBM Corp. 2008 + * Copyright IBM Corp. 2008,2009 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License (version 2 only) @@ -128,7 +128,7 @@ static int handle_noop(struct kvm_vcpu *vcpu) static int handle_stop(struct kvm_vcpu *vcpu) { - int rc; + int rc = 0; vcpu->stat.exit_stop_request++; atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags); @@ -141,12 +141,18 @@ static int handle_stop(struct kvm_vcpu *vcpu) rc = -ENOTSUPP; } + if (vcpu->arch.local_int.action_bits & ACTION_RELOADVCPU_ON_STOP) { + vcpu->arch.local_int.action_bits &= ~ACTION_RELOADVCPU_ON_STOP; + rc = SIE_INTERCEPT_RERUNVCPU; + vcpu->run->exit_reason = KVM_EXIT_INTR; + } + if (vcpu->arch.local_int.action_bits & ACTION_STOP_ON_STOP) { vcpu->arch.local_int.action_bits &= ~ACTION_STOP_ON_STOP; VCPU_EVENT(vcpu, 3, "%s", "cpu stopped"); rc = -ENOTSUPP; - } else - rc = 0; + } + spin_unlock_bh(&vcpu->arch.local_int.lock); return rc; } @@ -154,17 +160,25 @@ static int handle_stop(struct kvm_vcpu *vcpu) static int handle_validity(struct kvm_vcpu *vcpu) { int viwhy = vcpu->arch.sie_block->ipb >> 16; + int rc; + vcpu->stat.exit_validity++; - if (viwhy == 0x37) { - fault_in_pages_writeable((char __user *) - vcpu->kvm->arch.guest_origin + - vcpu->arch.sie_block->prefix, - PAGE_SIZE); - return 0; - } - VCPU_EVENT(vcpu, 2, "unhandled validity intercept code %d", - viwhy); - return -ENOTSUPP; + if ((viwhy == 0x37) && (vcpu->arch.sie_block->prefix + <= kvm_s390_vcpu_get_memsize(vcpu) - 2*PAGE_SIZE)) { + rc = fault_in_pages_writeable((char __user *) + vcpu->arch.sie_block->gmsor + + vcpu->arch.sie_block->prefix, + 2*PAGE_SIZE); + if (rc) + /* user will receive sigsegv, exit to user */ + rc = -ENOTSUPP; + } else + rc = -ENOTSUPP; + + if (rc) + VCPU_EVENT(vcpu, 2, "unhandled validity intercept code %d", + viwhy); + return rc; } static int handle_instruction(struct kvm_vcpu *vcpu) diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 0189356fe20..43486c2408e 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -12,6 +12,8 @@ #include <asm/lowcore.h> #include <asm/uaccess.h> +#include <linux/hrtimer.h> +#include <linux/interrupt.h> #include <linux/kvm_host.h> #include <linux/signal.h> #include "kvm-s390.h" @@ -281,7 +283,7 @@ static int __try_deliver_ckc_interrupt(struct kvm_vcpu *vcpu) return 1; } -int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu) +static int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int; @@ -299,13 +301,13 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu) } if ((!rc) && atomic_read(&fi->active)) { - spin_lock_bh(&fi->lock); + spin_lock(&fi->lock); list_for_each_entry(inti, &fi->list, list) if (__interrupt_is_deliverable(vcpu, inti)) { rc = 1; break; } - spin_unlock_bh(&fi->lock); + spin_unlock(&fi->lock); } if ((!rc) && (vcpu->arch.sie_block->ckc < @@ -355,14 +357,12 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu) return 0; } - sltime = (vcpu->arch.sie_block->ckc - now) / (0xf4240000ul / HZ) + 1; + sltime = ((vcpu->arch.sie_block->ckc - now)*125)>>9; - vcpu->arch.ckc_timer.expires = jiffies + sltime; - - add_timer(&vcpu->arch.ckc_timer); - VCPU_EVENT(vcpu, 5, "enabled wait timer:%llx jiffies", sltime); + hrtimer_start(&vcpu->arch.ckc_timer, ktime_set (0, sltime) , HRTIMER_MODE_REL); + VCPU_EVENT(vcpu, 5, "enabled wait via clock comparator: %llx ns", sltime); no_timer: - spin_lock_bh(&vcpu->arch.local_int.float_int->lock); + spin_lock(&vcpu->arch.local_int.float_int->lock); spin_lock_bh(&vcpu->arch.local_int.lock); add_wait_queue(&vcpu->arch.local_int.wq, &wait); while (list_empty(&vcpu->arch.local_int.list) && @@ -371,33 +371,46 @@ no_timer: !signal_pending(current)) { set_current_state(TASK_INTERRUPTIBLE); spin_unlock_bh(&vcpu->arch.local_int.lock); - spin_unlock_bh(&vcpu->arch.local_int.float_int->lock); + spin_unlock(&vcpu->arch.local_int.float_int->lock); vcpu_put(vcpu); schedule(); vcpu_load(vcpu); - spin_lock_bh(&vcpu->arch.local_int.float_int->lock); + spin_lock(&vcpu->arch.local_int.float_int->lock); spin_lock_bh(&vcpu->arch.local_int.lock); } __unset_cpu_idle(vcpu); __set_current_state(TASK_RUNNING); - remove_wait_queue(&vcpu->wq, &wait); + remove_wait_queue(&vcpu->arch.local_int.wq, &wait); spin_unlock_bh(&vcpu->arch.local_int.lock); - spin_unlock_bh(&vcpu->arch.local_int.float_int->lock); - del_timer(&vcpu->arch.ckc_timer); + spin_unlock(&vcpu->arch.local_int.float_int->lock); + hrtimer_try_to_cancel(&vcpu->arch.ckc_timer); return 0; } -void kvm_s390_idle_wakeup(unsigned long data) +void kvm_s390_tasklet(unsigned long parm) { - struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data; + struct kvm_vcpu *vcpu = (struct kvm_vcpu *) parm; - spin_lock_bh(&vcpu->arch.local_int.lock); + spin_lock(&vcpu->arch.local_int.lock); vcpu->arch.local_int.timer_due = 1; if (waitqueue_active(&vcpu->arch.local_int.wq)) wake_up_interruptible(&vcpu->arch.local_int.wq); - spin_unlock_bh(&vcpu->arch.local_int.lock); + spin_unlock(&vcpu->arch.local_int.lock); } +/* + * low level hrtimer wake routine. Because this runs in hardirq context + * we schedule a tasklet to do the real work. + */ +enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer) +{ + struct kvm_vcpu *vcpu; + + vcpu = container_of(timer, struct kvm_vcpu, arch.ckc_timer); + tasklet_schedule(&vcpu->arch.tasklet); + + return HRTIMER_NORESTART; +} void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) { @@ -436,7 +449,7 @@ void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) if (atomic_read(&fi->active)) { do { deliver = 0; - spin_lock_bh(&fi->lock); + spin_lock(&fi->lock); list_for_each_entry_safe(inti, n, &fi->list, list) { if (__interrupt_is_deliverable(vcpu, inti)) { list_del(&inti->list); @@ -447,7 +460,7 @@ void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) } if (list_empty(&fi->list)) atomic_set(&fi->active, 0); - spin_unlock_bh(&fi->lock); + spin_unlock(&fi->lock); if (deliver) { __do_deliver_interrupt(vcpu, inti); kfree(inti); @@ -465,7 +478,7 @@ int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code) if (!inti) return -ENOMEM; - inti->type = KVM_S390_PROGRAM_INT;; + inti->type = KVM_S390_PROGRAM_INT; inti->pgm.code = code; VCPU_EVENT(vcpu, 3, "inject: program check %d (from kernel)", code); @@ -512,7 +525,7 @@ int kvm_s390_inject_vm(struct kvm *kvm, mutex_lock(&kvm->lock); fi = &kvm->arch.float_int; - spin_lock_bh(&fi->lock); + spin_lock(&fi->lock); list_add_tail(&inti->list, &fi->list); atomic_set(&fi->active, 1); sigcpu = find_first_bit(fi->idle_mask, KVM_MAX_VCPUS); @@ -529,7 +542,7 @@ int kvm_s390_inject_vm(struct kvm *kvm, if (waitqueue_active(&li->wq)) wake_up_interruptible(&li->wq); spin_unlock_bh(&li->lock); - spin_unlock_bh(&fi->lock); + spin_unlock(&fi->lock); mutex_unlock(&kvm->lock); return 0; } diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index f4d56e9939c..f8bcaefd7d3 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1,7 +1,7 @@ /* * s390host.c -- hosting zSeries kernel virtual machines * - * Copyright IBM Corp. 2008 + * Copyright IBM Corp. 2008,2009 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License (version 2 only) @@ -10,11 +10,13 @@ * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> * Heiko Carstens <heiko.carstens@de.ibm.com> + * Christian Ehrhardt <ehrhardt@de.ibm.com> */ #include <linux/compiler.h> #include <linux/err.h> #include <linux/fs.h> +#include <linux/hrtimer.h> #include <linux/init.h> #include <linux/kvm.h> #include <linux/kvm_host.h> @@ -24,6 +26,7 @@ #include <asm/lowcore.h> #include <asm/pgtable.h> #include <asm/nmi.h> +#include <asm/system.h> #include "kvm-s390.h" #include "gaccess.h" @@ -68,11 +71,13 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { NULL } }; +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) @@ -112,10 +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 */ @@ -146,7 +157,7 @@ long kvm_arch_vm_ioctl(struct file *filp, break; } default: - r = -EINVAL; + r = -ENOTTY; } return r; @@ -195,6 +206,10 @@ out_nokvm: void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { VCPU_EVENT(vcpu, 3, "%s", "free cpu"); + if (vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda == + (__u64) vcpu->arch.sie_block) + vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda = 0; + smp_mb(); free_page((unsigned long)(vcpu->arch.sie_block)); kvm_vcpu_uninit(vcpu); kfree(vcpu); @@ -203,13 +218,17 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) static void kvm_free_vcpus(struct kvm *kvm) { unsigned int i; + struct kvm_vcpu *vcpu; - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - if (kvm->vcpus[i]) { - kvm_arch_vcpu_destroy(kvm->vcpus[i]); - kvm->vcpus[i] = NULL; - } - } + kvm_for_each_vcpu(i, vcpu, kvm) + kvm_arch_vcpu_destroy(vcpu); + + mutex_lock(&kvm->lock); + for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) + kvm->vcpus[i] = NULL; + + atomic_set(&kvm->online_vcpus, 0); + mutex_unlock(&kvm->lock); } void kvm_arch_sync_events(struct kvm *kvm) @@ -271,20 +290,17 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu) vcpu->arch.sie_block->gbea = 1; } -/* The current code can have up to 256 pages for virtio */ -#define VIRTIODESCSPACE (256ul * 4096ul) - int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH); - vcpu->arch.sie_block->gmslm = vcpu->kvm->arch.guest_memsize + - vcpu->kvm->arch.guest_origin + - VIRTIODESCSPACE - 1ul; - vcpu->arch.sie_block->gmsor = vcpu->kvm->arch.guest_origin; + set_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests); vcpu->arch.sie_block->ecb = 2; vcpu->arch.sie_block->eca = 0xC1002001U; - setup_timer(&vcpu->arch.ckc_timer, kvm_s390_idle_wakeup, - (unsigned long) vcpu); + vcpu->arch.sie_block->fac = (int) (long) facilities; + hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS); + tasklet_init(&vcpu->arch.tasklet, kvm_s390_tasklet, + (unsigned long) vcpu); + vcpu->arch.ckc_timer.function = kvm_s390_idle_wakeup; get_cpu_id(&vcpu->arch.cpu_id); vcpu->arch.cpu_id.version = 0xff; return 0; @@ -307,19 +323,19 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, vcpu->arch.sie_block->icpua = id; BUG_ON(!kvm->arch.sca); - BUG_ON(kvm->arch.sca->cpu[id].sda); - kvm->arch.sca->cpu[id].sda = (__u64) vcpu->arch.sie_block; + if (!kvm->arch.sca->cpu[id].sda) + kvm->arch.sca->cpu[id].sda = (__u64) vcpu->arch.sie_block; vcpu->arch.sie_block->scaoh = (__u32)(((__u64)kvm->arch.sca) >> 32); vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca; spin_lock_init(&vcpu->arch.local_int.lock); INIT_LIST_HEAD(&vcpu->arch.local_int.list); vcpu->arch.local_int.float_int = &kvm->arch.float_int; - spin_lock_bh(&kvm->arch.float_int.lock); + spin_lock(&kvm->arch.float_int.lock); kvm->arch.float_int.local_int[id] = &vcpu->arch.local_int; init_waitqueue_head(&vcpu->arch.local_int.wq); vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags; - spin_unlock_bh(&kvm->arch.float_int.lock); + spin_unlock(&kvm->arch.float_int.lock); rc = kvm_vcpu_init(vcpu, kvm, id); if (rc) @@ -410,8 +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; } @@ -478,6 +496,18 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) vcpu_load(vcpu); +rerun_vcpu: + if (vcpu->requests) + if (test_and_clear_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests)) + kvm_s390_vcpu_set_mem(vcpu); + + /* verify, that memory has been registered */ + if (!vcpu->arch.sie_block->gmslm) { + vcpu_put(vcpu); + VCPU_EVENT(vcpu, 3, "%s", "no memory registered to run vcpu"); + return -EINVAL; + } + if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved); @@ -487,32 +517,36 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) 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: break; default: BUG(); } - might_sleep(); + vcpu->arch.sie_block->gpsw.mask = kvm_run->psw_mask; + vcpu->arch.sie_block->gpsw.addr = kvm_run->psw_addr; + + might_fault(); do { __vcpu_run(vcpu); rc = kvm_handle_sie_intercept(vcpu); } while (!signal_pending(current) && !rc); - if (signal_pending(current) && !rc) + if (rc == SIE_INTERCEPT_RERUNVCPU) + goto rerun_vcpu; + + if (signal_pending(current) && !rc) { + kvm_run->exit_reason = KVM_EXIT_INTR; rc = -EINTR; + } if (rc == -ENOTSUPP) { /* 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; @@ -524,6 +558,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) 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); @@ -657,6 +694,9 @@ int kvm_arch_set_memory_region(struct kvm *kvm, struct kvm_memory_slot old, int user_alloc) { + int i; + struct kvm_vcpu *vcpu; + /* A few sanity checks. We can have exactly one memory slot which has to start at guest virtual zero and which has to be located at a page boundary in userland and which has to end at a page boundary. @@ -676,13 +716,15 @@ int kvm_arch_set_memory_region(struct kvm *kvm, if (mem->memory_size & (PAGE_SIZE - 1)) return -EINVAL; - kvm->arch.guest_origin = mem->userspace_addr; - kvm->arch.guest_memsize = mem->memory_size; + if (!user_alloc) + return -EINVAL; - /* FIXME: we do want to interrupt running CPUs and update their memory - configuration now to avoid race conditions. But hey, changing the - memory layout while virtual CPUs are running is usually bad - programming practice. */ + /* request update of sie control block for all available vcpus */ + kvm_for_each_vcpu(i, vcpu, kvm) { + if (test_and_set_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests)) + continue; + kvm_s390_inject_sigp_stop(vcpu, ACTION_RELOADVCPU_ON_STOP); + } return 0; } @@ -698,11 +740,29 @@ gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn) static int __init kvm_s390_init(void) { - return kvm_init(NULL, sizeof(struct kvm_vcpu), THIS_MODULE); + int ret; + ret = kvm_init(NULL, sizeof(struct kvm_vcpu), THIS_MODULE); + if (ret) + return ret; + + /* + * guests can ask for up to 255+1 double words, we need a full page + * to hold the maximum amount of facilites. On the other hand, we + * only set facilities that are known to work in KVM. + */ + facilities = (unsigned long long *) get_zeroed_page(GFP_DMA); + if (!facilities) { + kvm_exit(); + return -ENOMEM; + } + stfle(facilities, 1); + facilities[0] &= 0xff00fff3f0700000ULL; + return 0; } static void __exit kvm_s390_exit(void) { + free_page((unsigned long) facilities); kvm_exit(); } diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 00bbe69b78d..06cce8285ba 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -1,7 +1,7 @@ /* * kvm_s390.h - definition for kvm on s390 * - * Copyright IBM Corp. 2008 + * Copyright IBM Corp. 2008,2009 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License (version 2 only) @@ -9,16 +9,23 @@ * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> + * Christian Ehrhardt <ehrhardt@de.ibm.com> */ #ifndef ARCH_S390_KVM_S390_H #define ARCH_S390_KVM_S390_H +#include <linux/hrtimer.h> #include <linux/kvm.h> #include <linux/kvm_host.h> +/* The current code can have up to 256 pages for virtio */ +#define VIRTIODESCSPACE (256ul * 4096ul) + typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu); +/* negativ values are error codes, positive values for internal conditions */ +#define SIE_INTERCEPT_RERUNVCPU (1<<0) int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu); #define VM_EVENT(d_kvm, d_loglevel, d_string, d_args...)\ @@ -41,13 +48,38 @@ static inline int __cpu_is_stopped(struct kvm_vcpu *vcpu) } int kvm_s390_handle_wait(struct kvm_vcpu *vcpu); -void kvm_s390_idle_wakeup(unsigned long data); +enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer); +void kvm_s390_tasklet(unsigned long parm); void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu); int kvm_s390_inject_vm(struct kvm *kvm, struct kvm_s390_interrupt *s390int); int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_interrupt *s390int); 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 long kvm_s390_vcpu_get_memsize(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.sie_block->gmslm + - vcpu->arch.sie_block->gmsor + - VIRTIODESCSPACE + 1ul; +} + +static inline void kvm_s390_vcpu_set_mem(struct kvm_vcpu *vcpu) +{ + struct kvm_memory_slot *mem; + + down_read(&vcpu->kvm->slots_lock); + mem = &vcpu->kvm->memslots[0]; + + vcpu->arch.sie_block->gmsor = mem->userspace_addr; + vcpu->arch.sie_block->gmslm = + mem->userspace_addr + + (mem->npages << PAGE_SHIFT) + + VIRTIODESCSPACE - 1ul; + + up_read(&vcpu->kvm->slots_lock); +} /* implemented in priv.c */ int kvm_s390_handle_b2(struct kvm_vcpu *vcpu); diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 4b88834b8dd..d426aac8095 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -158,7 +158,7 @@ static int handle_stfl(struct kvm_vcpu *vcpu) vcpu->stat.instruction_stfl++; /* only pass the facility bits, which we can handle */ - facility_list &= 0xfe00fff3; + facility_list &= 0xff00fff3; rc = copy_to_guest(vcpu, offsetof(struct _lowcore, stfl_fac_list), &facility_list, sizeof(facility_list)); @@ -204,11 +204,11 @@ static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem) int cpus = 0; int n; - spin_lock_bh(&fi->lock); + spin_lock(&fi->lock); for (n = 0; n < KVM_MAX_VCPUS; n++) if (fi->local_int[n]) cpus++; - spin_unlock_bh(&fi->lock); + spin_unlock(&fi->lock); /* deal with other level 3 hypervisors */ if (stsi(mem, 3, 2, 2) == -ENOSYS) diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c index f27dbedf086..15ee1111de5 100644 --- a/arch/s390/kvm/sigp.c +++ b/arch/s390/kvm/sigp.c @@ -1,7 +1,7 @@ /* * sigp.c - handlinge interprocessor communication * - * Copyright IBM Corp. 2008 + * Copyright IBM Corp. 2008,2009 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License (version 2 only) @@ -9,6 +9,7 @@ * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> + * Christian Ehrhardt <ehrhardt@de.ibm.com> */ #include <linux/kvm.h> @@ -52,7 +53,7 @@ static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr, if (cpu_addr >= KVM_MAX_VCPUS) return 3; /* not operational */ - spin_lock_bh(&fi->lock); + spin_lock(&fi->lock); if (fi->local_int[cpu_addr] == NULL) rc = 3; /* not operational */ else if (atomic_read(fi->local_int[cpu_addr]->cpuflags) @@ -64,7 +65,7 @@ static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr, *reg |= SIGP_STAT_STOPPED; rc = 1; /* status stored */ } - spin_unlock_bh(&fi->lock); + spin_unlock(&fi->lock); VCPU_EVENT(vcpu, 4, "sensed status of cpu %x rc %x", cpu_addr, rc); return rc; @@ -86,7 +87,7 @@ static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr) inti->type = KVM_S390_INT_EMERGENCY; - spin_lock_bh(&fi->lock); + spin_lock(&fi->lock); li = fi->local_int[cpu_addr]; if (li == NULL) { rc = 3; /* not operational */ @@ -102,51 +103,62 @@ static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr) spin_unlock_bh(&li->lock); rc = 0; /* order accepted */ unlock: - spin_unlock_bh(&fi->lock); + spin_unlock(&fi->lock); VCPU_EVENT(vcpu, 4, "sent sigp emerg to cpu %x", cpu_addr); return rc; } -static int __sigp_stop(struct kvm_vcpu *vcpu, u16 cpu_addr, int store) +static int __inject_sigp_stop(struct kvm_s390_local_interrupt *li, int action) { - struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; - struct kvm_s390_local_interrupt *li; struct kvm_s390_interrupt_info *inti; - int rc; - - if (cpu_addr >= KVM_MAX_VCPUS) - return 3; /* not operational */ inti = kzalloc(sizeof(*inti), GFP_KERNEL); if (!inti) return -ENOMEM; - inti->type = KVM_S390_SIGP_STOP; - spin_lock_bh(&fi->lock); - li = fi->local_int[cpu_addr]; - if (li == NULL) { - rc = 3; /* not operational */ - kfree(inti); - goto unlock; - } spin_lock_bh(&li->lock); list_add_tail(&inti->list, &li->list); atomic_set(&li->active, 1); atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags); - if (store) - li->action_bits |= ACTION_STORE_ON_STOP; - li->action_bits |= ACTION_STOP_ON_STOP; + li->action_bits |= action; if (waitqueue_active(&li->wq)) wake_up_interruptible(&li->wq); spin_unlock_bh(&li->lock); - rc = 0; /* order accepted */ + + return 0; /* order accepted */ +} + +static int __sigp_stop(struct kvm_vcpu *vcpu, u16 cpu_addr, int action) +{ + struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; + struct kvm_s390_local_interrupt *li; + int rc; + + if (cpu_addr >= KVM_MAX_VCPUS) + return 3; /* not operational */ + + spin_lock(&fi->lock); + li = fi->local_int[cpu_addr]; + if (li == NULL) { + rc = 3; /* not operational */ + goto unlock; + } + + rc = __inject_sigp_stop(li, action); + unlock: - spin_unlock_bh(&fi->lock); + spin_unlock(&fi->lock); VCPU_EVENT(vcpu, 4, "sent sigp stop to cpu %x", cpu_addr); return rc; } +int kvm_s390_inject_sigp_stop(struct kvm_vcpu *vcpu, int action) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + return __inject_sigp_stop(li, action); +} + static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter) { int rc; @@ -169,17 +181,17 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address, unsigned long *reg) { struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; - struct kvm_s390_local_interrupt *li; + struct kvm_s390_local_interrupt *li = NULL; struct kvm_s390_interrupt_info *inti; int rc; u8 tmp; /* make sure that the new value is valid memory */ address = address & 0x7fffe000u; - if ((copy_from_guest(vcpu, &tmp, - (u64) (address + vcpu->kvm->arch.guest_origin) , 1)) || - (copy_from_guest(vcpu, &tmp, (u64) (address + - vcpu->kvm->arch.guest_origin + PAGE_SIZE), 1))) { + 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 */ } @@ -188,10 +200,11 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address, if (!inti) return 2; /* busy */ - spin_lock_bh(&fi->lock); - li = fi->local_int[cpu_addr]; + spin_lock(&fi->lock); + if (cpu_addr < KVM_MAX_VCPUS) + li = fi->local_int[cpu_addr]; - if ((cpu_addr >= KVM_MAX_VCPUS) || (li == NULL)) { + if (li == NULL) { rc = 1; /* incorrect state */ *reg &= SIGP_STAT_INCORRECT_STATE; kfree(inti); @@ -220,7 +233,7 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address, out_li: spin_unlock_bh(&li->lock); out_fi: - spin_unlock_bh(&fi->lock); + spin_unlock(&fi->lock); return rc; } @@ -261,11 +274,11 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu) break; case SIGP_STOP: vcpu->stat.instruction_sigp_stop++; - rc = __sigp_stop(vcpu, cpu_addr, 0); + rc = __sigp_stop(vcpu, cpu_addr, ACTION_STOP_ON_STOP); break; case SIGP_STOP_STORE_STATUS: vcpu->stat.instruction_sigp_stop++; - rc = __sigp_stop(vcpu, cpu_addr, 1); + rc = __sigp_stop(vcpu, cpu_addr, ACTION_STORE_ON_STOP); break; case SIGP_SET_ARCH: vcpu->stat.instruction_sigp_arch++; diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile index ab6735df2d2..97975ec7a27 100644 --- a/arch/s390/lib/Makefile +++ b/arch/s390/lib/Makefile @@ -3,6 +3,6 @@ # lib-y += delay.o string.o uaccess_std.o uaccess_pt.o -obj-$(CONFIG_32BIT) += div64.o qrnnd.o +obj-$(CONFIG_32BIT) += div64.o qrnnd.o ucmpdi2.o lib-$(CONFIG_64BIT) += uaccess_mvcos.o lib-$(CONFIG_SMP) += spinlock.o diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c index 3f5f680726e..752b362bf65 100644 --- a/arch/s390/lib/delay.c +++ b/arch/s390/lib/delay.c @@ -25,39 +25,46 @@ 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); mask = psw_kernel_bits | PSW_MASK_WAIT | PSW_MASK_EXT; + lockdep_off(); trace_hardirqs_on(); __load_psw_mask(mask); local_irq_disable(); + lockdep_on(); __ctl_load(cr0_saved, 0, 0); local_tick_enable(clock_saved); 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); } @@ -65,7 +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; @@ -99,11 +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 e41f4008afc..f7e0d30250b 100644 --- a/arch/s390/lib/spinlock.c +++ b/arch/s390/lib/spinlock.c @@ -124,6 +124,27 @@ 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) +{ + unsigned int old; + int count = spin_retry; + + local_irq_restore(flags); + while (1) { + if (count-- <= 0) { + _raw_yield(); + count = spin_retry; + } + if (!__raw_read_can_lock(rw)) + continue; + old = rw->lock & 0x7fffffffU; + local_irq_disable(); + if (_raw_compare_and_swap(&rw->lock, old, old + 1) == old) + return; + } +} +EXPORT_SYMBOL(_raw_read_lock_wait_flags); + int _raw_read_trylock_retry(raw_rwlock_t *rw) { unsigned int old; @@ -157,6 +178,25 @@ 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) +{ + int count = spin_retry; + + local_irq_restore(flags); + while (1) { + if (count-- <= 0) { + _raw_yield(); + count = spin_retry; + } + if (!__raw_write_can_lock(rw)) + continue; + local_irq_disable(); + if (_raw_compare_and_swap(&rw->lock, 0, 0x80000000) == 0) + return; + } +} +EXPORT_SYMBOL(_raw_write_lock_wait_flags); + int _raw_write_trylock_retry(raw_rwlock_t *rw) { int count = spin_retry; diff --git a/arch/s390/lib/uaccess_mvcos.c b/arch/s390/lib/uaccess_mvcos.c index 3f15aaf5485..58da3f46121 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; diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c index b0b84c35b0a..cb5d59eab0e 100644 --- a/arch/s390/lib/uaccess_pt.c +++ b/arch/s390/lib/uaccess_pt.c @@ -66,7 +66,7 @@ static int __handle_fault(struct mm_struct *mm, unsigned long address, } survive: - fault = handle_mm_fault(mm, vma, address, write_access); + 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; diff --git a/arch/s390/lib/uaccess_std.c b/arch/s390/lib/uaccess_std.c index d2ffbadb51a..07deaeee14c 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/lib/ucmpdi2.c b/arch/s390/lib/ucmpdi2.c new file mode 100644 index 00000000000..3e05ff53258 --- /dev/null +++ b/arch/s390/lib/ucmpdi2.c @@ -0,0 +1,26 @@ +#include <linux/module.h> + +union ull_union { + unsigned long long ull; + struct { + unsigned int high; + unsigned int low; + } ui; +}; + +int __ucmpdi2(unsigned long long a, unsigned long long b) +{ + union ull_union au = {.ull = a}; + union ull_union bu = {.ull = b}; + + if (au.ui.high < bu.ui.high) + return 0; + else if (au.ui.high > bu.ui.high) + return 2; + if (au.ui.low < bu.ui.low) + return 0; + else if (au.ui.low > bu.ui.low) + return 2; + return 1; +} +EXPORT_SYMBOL(__ucmpdi2); diff --git a/arch/s390/mm/Makefile b/arch/s390/mm/Makefile index 2a745813454..eec05448441 100644 --- a/arch/s390/mm/Makefile +++ b/arch/s390/mm/Makefile @@ -2,7 +2,7 @@ # Makefile for the linux s390-specific parts of the memory manager. # -obj-y := init.o fault.o extmem.o mmap.o vmem.o pgtable.o +obj-y := init.o fault.o extmem.o mmap.o vmem.o pgtable.o maccess.o \ + page-states.o obj-$(CONFIG_CMM) += cmm.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o -obj-$(CONFIG_PAGE_STATES) += page-states.o diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c index 413c240cbca..ff58779bf7e 100644 --- a/arch/s390/mm/cmm.c +++ b/arch/s390/mm/cmm.c @@ -262,7 +262,7 @@ cmm_skip_blanks(char *cp, char **endp) static struct ctl_table cmm_table[]; static int -cmm_pages_handler(ctl_table *ctl, int write, struct file *filp, +cmm_pages_handler(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { char buf[16], *p; @@ -303,7 +303,7 @@ cmm_pages_handler(ctl_table *ctl, int write, struct file *filp, } static int -cmm_timeout_handler(ctl_table *ctl, int write, struct file *filp, +cmm_timeout_handler(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { char buf[64], *p; @@ -343,30 +343,29 @@ 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 diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 833e8366c35..6d507462967 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -10,6 +10,7 @@ * Copyright (C) 1995 Linus Torvalds */ +#include <linux/perf_event.h> #include <linux/signal.h> #include <linux/sched.h> #include <linux/kernel.h> @@ -19,9 +20,9 @@ #include <linux/ptrace.h> #include <linux/mman.h> #include <linux/mm.h> +#include <linux/compat.h> #include <linux/smp.h> #include <linux/kdebug.h> -#include <linux/smp_lock.h> #include <linux/init.h> #include <linux/console.h> #include <linux/module.h> @@ -239,7 +240,7 @@ static int signal_return(struct mm_struct *mm, struct pt_regs *regs, up_read(&mm->mmap_sem); clear_tsk_thread_flag(current, TIF_SINGLE_STEP); #ifdef CONFIG_COMPAT - compat = test_tsk_thread_flag(current, TIF_31BIT); + compat = is_compat_task(); if (compat && instruction == 0x0a77) sys32_sigreturn(); else if (compat && instruction == 0x0aad) @@ -305,7 +306,7 @@ do_exception(struct pt_regs *regs, unsigned long error_code, int write) * interrupts again and then search the VMAs */ local_irq_enable(); - + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address); down_read(&mm->mmap_sem); si_code = SEGV_MAPERR; @@ -351,7 +352,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(mm, vma, address, write); + 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); @@ -363,11 +364,15 @@ good_area: } BUG(); } - if (fault & VM_FAULT_MAJOR) + if (fault & VM_FAULT_MAJOR) { tsk->maj_flt++; - else + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0, + regs, address); + } else { tsk->min_flt++; - + 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 diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index c634dfbe92e..76564795222 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -105,7 +105,7 @@ void __init mem_init(void) datasize = (unsigned long) &_edata - (unsigned long) &_etext; initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin; printk("Memory: %luk/%luk available (%ldk kernel code, %ldk reserved, %ldk data, %ldk init)\n", - (unsigned long) nr_free_pages() << (PAGE_SHIFT-10), + nr_free_pages() << (PAGE_SHIFT-10), max_mapnr << (PAGE_SHIFT-10), codesize >> 10, reservedpages << (PAGE_SHIFT-10), diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c new file mode 100644 index 00000000000..81756271dc4 --- /dev/null +++ b/arch/s390/mm/maccess.c @@ -0,0 +1,61 @@ +/* + * Access kernel memory without faulting -- s390 specific implementation. + * + * Copyright IBM Corp. 2009 + * + * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>, + * + */ + +#include <linux/uaccess.h> +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/errno.h> +#include <asm/system.h> + +/* + * This function writes to kernel memory bypassing DAT and possible + * write protection. It copies one to four bytes from src to dst + * using the stura instruction. + * Returns the number of bytes copied or -EFAULT. + */ +static long probe_kernel_write_odd(void *dst, void *src, size_t size) +{ + unsigned long count, aligned; + int offset, mask; + int rc = -EFAULT; + + aligned = (unsigned long) dst & ~3UL; + offset = (unsigned long) dst & 3; + count = min_t(unsigned long, 4 - offset, size); + mask = (0xf << (4 - count)) & 0xf; + mask >>= offset; + asm volatile( + " bras 1,0f\n" + " icm 0,0,0(%3)\n" + "0: l 0,0(%1)\n" + " lra %1,0(%1)\n" + "1: ex %2,0(1)\n" + "2: stura 0,%1\n" + " la %0,0\n" + "3:\n" + EX_TABLE(0b,3b) EX_TABLE(1b,3b) EX_TABLE(2b,3b) + : "+d" (rc), "+a" (aligned) + : "a" (mask), "a" (src) : "cc", "memory", "0", "1"); + return rc ? rc : count; +} + +long probe_kernel_write(void *dst, void *src, size_t size) +{ + long copied = 0; + + while (size) { + copied = probe_kernel_write_odd(dst, src, size); + if (copied < 0) + break; + dst += copied; + src += copied; + size -= copied; + } + return copied < 0 ? -EFAULT : 0; +} diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index e008d236cc1..f4558ccf02b 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -28,6 +28,7 @@ #include <linux/mm.h> #include <linux/module.h> #include <asm/pgalloc.h> +#include <asm/compat.h> /* * Top of mmap area (just below the process stack). @@ -55,7 +56,7 @@ static inline int mmap_is_legacy(void) /* * Force standard allocation for 64 bit programs. */ - if (!test_thread_flag(TIF_31BIT)) + if (!is_compat_task()) return 1; #endif return sysctl_legacy_va_layout || @@ -91,7 +92,7 @@ EXPORT_SYMBOL_GPL(arch_pick_mmap_layout); int s390_mmap_check(unsigned long addr, unsigned long len) { - if (!test_thread_flag(TIF_31BIT) && + if (!is_compat_task() && len >= TASK_SIZE && TASK_SIZE < (1UL << 53)) return crst_table_upgrade(current->mm, 1UL << 53); return 0; @@ -108,8 +109,7 @@ s390_get_unmapped_area(struct file *filp, unsigned long addr, area = arch_get_unmapped_area(filp, addr, len, pgoff, flags); if (!(area & ~PAGE_MASK)) return area; - if (area == -ENOMEM && - !test_thread_flag(TIF_31BIT) && TASK_SIZE < (1UL << 53)) { + if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < (1UL << 53)) { /* Upgrade the page table to 4 levels and retry. */ rc = crst_table_upgrade(mm, 1UL << 53); if (rc) @@ -131,8 +131,7 @@ s390_get_unmapped_area_topdown(struct file *filp, const unsigned long addr, area = arch_get_unmapped_area_topdown(filp, addr, len, pgoff, flags); if (!(area & ~PAGE_MASK)) return area; - if (area == -ENOMEM && - !test_thread_flag(TIF_31BIT) && TASK_SIZE < (1UL << 53)) { + if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < (1UL << 53)) { /* Upgrade the page table to 4 levels and retry. */ rc = crst_table_upgrade(mm, 1UL << 53); if (rc) diff --git a/arch/s390/mm/page-states.c b/arch/s390/mm/page-states.c index fc0ad73ffd9..098923ae458 100644 --- a/arch/s390/mm/page-states.c +++ b/arch/s390/mm/page-states.c @@ -1,6 +1,4 @@ /* - * arch/s390/mm/page-states.c - * * Copyright IBM Corp. 2008 * * Guest page hinting for unused pages. @@ -17,11 +15,12 @@ #define ESSA_SET_STABLE 1 #define ESSA_SET_UNUSED 2 -static int cmma_flag; +static int cmma_flag = 1; static int __init cmma(char *str) { char *parm; + parm = strstrip(str); if (strcmp(parm, "yes") == 0 || strcmp(parm, "on") == 0) { cmma_flag = 1; @@ -32,7 +31,6 @@ static int __init cmma(char *str) return 1; return 0; } - __setup("cmma=", cmma); void __init cmma_init(void) @@ -52,28 +50,64 @@ void __init cmma_init(void) cmma_flag = 0; } -void arch_free_page(struct page *page, int order) +static inline void set_page_unstable(struct page *page, int order) { int i, rc; - if (!cmma_flag) - return; for (i = 0; i < (1 << order); i++) asm volatile(".insn rrf,0xb9ab0000,%0,%1,%2,0" : "=&d" (rc) - : "a" ((page_to_pfn(page) + i) << PAGE_SHIFT), + : "a" (page_to_phys(page + i)), "i" (ESSA_SET_UNUSED)); } -void arch_alloc_page(struct page *page, int order) +void arch_free_page(struct page *page, int order) { - int i, rc; - if (!cmma_flag) return; + set_page_unstable(page, order); +} + +static inline void set_page_stable(struct page *page, int order) +{ + int i, rc; + for (i = 0; i < (1 << order); i++) asm volatile(".insn rrf,0xb9ab0000,%0,%1,%2,0" : "=&d" (rc) - : "a" ((page_to_pfn(page) + i) << PAGE_SHIFT), + : "a" (page_to_phys(page + i)), "i" (ESSA_SET_STABLE)); } + +void arch_alloc_page(struct page *page, int order) +{ + if (!cmma_flag) + return; + set_page_stable(page, order); +} + +void arch_set_page_states(int make_stable) +{ + unsigned long flags, order, t; + struct list_head *l; + struct page *page; + struct zone *zone; + + if (!cmma_flag) + return; + if (make_stable) + drain_local_pages(NULL); + for_each_populated_zone(zone) { + spin_lock_irqsave(&zone->lock, flags); + for_each_migratetype_order(order, t) { + list_for_each(l, &zone->free_area[order].free_list[t]) { + page = list_entry(l, struct page, lru); + if (make_stable) + set_page_stable(page, order); + else + set_page_unstable(page, order); + } + } + spin_unlock_irqrestore(&zone->lock, flags); + } +} diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index be6c1cf4ad5..2757c5616a0 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -1,7 +1,5 @@ /* - * arch/s390/mm/pgtable.c - * - * Copyright IBM Corp. 2007 + * Copyright IBM Corp. 2007,2009 * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> */ @@ -53,6 +51,18 @@ void clear_table_pgstes(unsigned long *table) #endif +unsigned long VMALLOC_START = VMALLOC_END - VMALLOC_SIZE; +EXPORT_SYMBOL(VMALLOC_START); + +static int __init parse_vmalloc(char *arg) +{ + if (!arg) + return -EINVAL; + VMALLOC_START = (VMALLOC_END - memparse(arg, &arg)) & PAGE_MASK; + return 0; +} +early_param("vmalloc", parse_vmalloc); + unsigned long *crst_table_alloc(struct mm_struct *mm, int noexec) { struct page *page = alloc_pages(GFP_KERNEL, ALLOC_ORDER); @@ -68,9 +78,9 @@ unsigned long *crst_table_alloc(struct mm_struct *mm, int noexec) } page->index = page_to_phys(shadow); } - spin_lock(&mm->page_table_lock); + spin_lock(&mm->context.list_lock); list_add(&page->lru, &mm->context.crst_list); - spin_unlock(&mm->page_table_lock); + spin_unlock(&mm->context.list_lock); return (unsigned long *) page_to_phys(page); } @@ -79,9 +89,9 @@ void crst_table_free(struct mm_struct *mm, unsigned long *table) unsigned long *shadow = get_shadow_table(table); struct page *page = virt_to_page(table); - spin_lock(&mm->page_table_lock); + spin_lock(&mm->context.list_lock); list_del(&page->lru); - spin_unlock(&mm->page_table_lock); + spin_unlock(&mm->context.list_lock); if (shadow) free_pages((unsigned long) shadow, ALLOC_ORDER); free_pages((unsigned long) table, ALLOC_ORDER); @@ -172,7 +182,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm) unsigned long bits; bits = (mm->context.noexec || mm->context.has_pgste) ? 3UL : 1UL; - spin_lock(&mm->page_table_lock); + spin_lock(&mm->context.list_lock); page = NULL; if (!list_empty(&mm->context.pgtable_list)) { page = list_first_entry(&mm->context.pgtable_list, @@ -181,7 +191,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm) page = NULL; } if (!page) { - spin_unlock(&mm->page_table_lock); + spin_unlock(&mm->context.list_lock); page = alloc_page(GFP_KERNEL|__GFP_REPEAT); if (!page) return NULL; @@ -192,7 +202,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm) clear_table_pgstes(table); else clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE); - spin_lock(&mm->page_table_lock); + spin_lock(&mm->context.list_lock); list_add(&page->lru, &mm->context.pgtable_list); } table = (unsigned long *) page_to_phys(page); @@ -203,7 +213,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm) page->flags |= bits; if ((page->flags & FRAG_MASK) == ((1UL << TABLES_PER_PAGE) - 1)) list_move_tail(&page->lru, &mm->context.pgtable_list); - spin_unlock(&mm->page_table_lock); + spin_unlock(&mm->context.list_lock); return table; } @@ -215,7 +225,7 @@ void page_table_free(struct mm_struct *mm, unsigned long *table) bits = (mm->context.noexec || mm->context.has_pgste) ? 3UL : 1UL; bits <<= (__pa(table) & (PAGE_SIZE - 1)) / 256 / sizeof(unsigned long); page = pfn_to_page(__pa(table) >> PAGE_SHIFT); - spin_lock(&mm->page_table_lock); + spin_lock(&mm->context.list_lock); page->flags ^= bits; if (page->flags & FRAG_MASK) { /* Page now has some free pgtable fragments. */ @@ -224,7 +234,7 @@ void page_table_free(struct mm_struct *mm, unsigned long *table) } else /* All fragments of the 4K page have been freed. */ list_del(&page->lru); - spin_unlock(&mm->page_table_lock); + spin_unlock(&mm->context.list_lock); if (page) { pgtable_page_dtor(page); __free_page(page); @@ -235,7 +245,7 @@ void disable_noexec(struct mm_struct *mm, struct task_struct *tsk) { struct page *page; - spin_lock(&mm->page_table_lock); + spin_lock(&mm->context.list_lock); /* Free shadow region and segment tables. */ list_for_each_entry(page, &mm->context.crst_list, lru) if (page->index) { @@ -245,7 +255,7 @@ void disable_noexec(struct mm_struct *mm, struct task_struct *tsk) /* "Free" second halves of page tables. */ list_for_each_entry(page, &mm->context.pgtable_list, lru) page->flags &= ~SECOND_HALVES; - spin_unlock(&mm->page_table_lock); + spin_unlock(&mm->context.list_lock); mm->context.noexec = 0; update_mm(mm, tsk); } @@ -269,7 +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; } @@ -285,7 +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; @@ -303,3 +319,19 @@ int s390_enable_sie(void) return 0; } EXPORT_SYMBOL_GPL(s390_enable_sie); + +#if defined(CONFIG_DEBUG_PAGEALLOC) && defined(CONFIG_HIBERNATION) +bool kernel_page_present(struct page *page) +{ + unsigned long addr; + int cc; + + addr = page_to_phys(page); + asm volatile( + " lra %1,0(%1)\n" + " ipm %0\n" + " srl %0,28" + : "=d" (cc), "+a" (addr) : : "cc"); + return cc == 0; +} +#endif /* CONFIG_HIBERNATION && CONFIG_DEBUG_PAGEALLOC */ diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index e4868bfc672..5f91a38d759 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -331,6 +331,7 @@ void __init vmem_map_init(void) unsigned long start, end; int i; + spin_lock_init(&init_mm.context.list_lock); INIT_LIST_HEAD(&init_mm.context.crst_list); INIT_LIST_HEAD(&init_mm.context.pgtable_list); init_mm.context.noexec = 0; |