diff options
author | Ingo Molnar <mingo@elte.hu> | 2008-12-08 15:07:49 +0100 |
---|---|---|
committer | Ingo Molnar <mingo@elte.hu> | 2008-12-08 15:07:49 +0100 |
commit | aa9c9b8c584a42a094202b7e0f63497e888f86a7 (patch) | |
tree | 3cb3b022054a7c1722657288518f495e0c4d9983 /kernel | |
parent | 87f7606591aea6a8a38ea4c8911b5eeeee2740b8 (diff) | |
parent | 218d11a8b071b23b76c484fd5f72a4fe3306801e (diff) |
Merge branch 'linus' into x86/quirks
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/Makefile | 4 | ||||
-rw-r--r-- | kernel/cgroup.c | 21 | ||||
-rw-r--r-- | kernel/cpu.c | 2 | ||||
-rw-r--r-- | kernel/cpuset.c | 33 | ||||
-rw-r--r-- | kernel/irq/internals.h | 2 | ||||
-rw-r--r-- | kernel/irq/manage.c | 68 | ||||
-rw-r--r-- | kernel/irq/migration.c | 11 | ||||
-rw-r--r-- | kernel/irq/proc.c | 2 | ||||
-rw-r--r-- | kernel/kallsyms.c | 17 | ||||
-rw-r--r-- | kernel/lockdep.c | 4 | ||||
-rw-r--r-- | kernel/panic.c | 1 | ||||
-rw-r--r-- | kernel/posix-cpu-timers.c | 9 | ||||
-rw-r--r-- | kernel/power/main.c | 2 | ||||
-rw-r--r-- | kernel/power/swap.c | 2 | ||||
-rw-r--r-- | kernel/profile.c | 6 | ||||
-rw-r--r-- | kernel/ptrace.c | 4 | ||||
-rw-r--r-- | kernel/relay.c | 9 | ||||
-rw-r--r-- | kernel/sched.c | 18 | ||||
-rw-r--r-- | kernel/sched_debug.c | 5 | ||||
-rw-r--r-- | kernel/sched_stats.h | 15 | ||||
-rw-r--r-- | kernel/softlockup.c | 2 | ||||
-rw-r--r-- | kernel/sys_ni.c | 2 | ||||
-rw-r--r-- | kernel/sysctl.c | 10 | ||||
-rw-r--r-- | kernel/time/timekeeping.c | 22 | ||||
-rw-r--r-- | kernel/trace/ftrace.c | 147 | ||||
-rw-r--r-- | kernel/trace/ring_buffer.c | 118 | ||||
-rw-r--r-- | kernel/trace/trace.c | 1 | ||||
-rw-r--r-- | kernel/trace/trace_mmiotrace.c | 16 | ||||
-rw-r--r-- | kernel/trace/trace_stack.c | 24 |
29 files changed, 397 insertions, 180 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index 9a3ec66a9d8..19fad003b19 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -11,8 +11,6 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o \ hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \ notifier.o ksysfs.o pm_qos_params.o sched_clock.o -CFLAGS_REMOVE_sched.o = -mno-spe - ifdef CONFIG_FUNCTION_TRACER # Do not trace debug files and internal ftrace files CFLAGS_REMOVE_lockdep.o = -pg @@ -21,7 +19,7 @@ CFLAGS_REMOVE_mutex-debug.o = -pg CFLAGS_REMOVE_rtmutex-debug.o = -pg CFLAGS_REMOVE_cgroup-debug.o = -pg CFLAGS_REMOVE_sched_clock.o = -pg -CFLAGS_REMOVE_sched.o = -mno-spe -pg +CFLAGS_REMOVE_sched.o = -pg endif obj-$(CONFIG_FREEZER) += freezer.o diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 358e77564e6..fe00b3b983a 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2039,10 +2039,13 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) struct cgroup *cgrp; struct cgroup_iter it; struct task_struct *tsk; + /* - * Validate dentry by checking the superblock operations + * Validate dentry by checking the superblock operations, + * and make sure it's a directory. */ - if (dentry->d_sb->s_op != &cgroup_ops) + if (dentry->d_sb->s_op != &cgroup_ops || + !S_ISDIR(dentry->d_inode->i_mode)) goto err; ret = 0; @@ -2472,10 +2475,7 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) mutex_unlock(&cgroup_mutex); return -EBUSY; } - - parent = cgrp->parent; - root = cgrp->root; - sb = root->sb; + mutex_unlock(&cgroup_mutex); /* * Call pre_destroy handlers of subsys. Notify subsystems @@ -2483,7 +2483,14 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) */ cgroup_call_pre_destroy(cgrp); - if (cgroup_has_css_refs(cgrp)) { + mutex_lock(&cgroup_mutex); + parent = cgrp->parent; + root = cgrp->root; + sb = root->sb; + + if (atomic_read(&cgrp->count) + || !list_empty(&cgrp->children) + || cgroup_has_css_refs(cgrp)) { mutex_unlock(&cgroup_mutex); return -EBUSY; } diff --git a/kernel/cpu.c b/kernel/cpu.c index 5a732c5ef08..8ea32e8d68b 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -462,7 +462,7 @@ out: * It must be called by the arch code on the new cpu, before the new cpu * enables interrupts and before the "boot" cpu returns from __cpu_up(). */ -void notify_cpu_starting(unsigned int cpu) +void __cpuinit notify_cpu_starting(unsigned int cpu) { unsigned long val = CPU_STARTING; diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 3e00526f52e..96c0ba13b8c 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -36,6 +36,7 @@ #include <linux/list.h> #include <linux/mempolicy.h> #include <linux/mm.h> +#include <linux/memory.h> #include <linux/module.h> #include <linux/mount.h> #include <linux/namei.h> @@ -584,10 +585,9 @@ static int generate_sched_domains(cpumask_t **domains, int i, j, k; /* indices for partition finding loops */ cpumask_t *doms; /* resulting partition; i.e. sched domains */ struct sched_domain_attr *dattr; /* attributes for custom domains */ - int ndoms; /* number of sched domains in result */ + int ndoms = 0; /* number of sched domains in result */ int nslot; /* next empty doms[] cpumask_t slot */ - ndoms = 0; doms = NULL; dattr = NULL; csa = NULL; @@ -674,10 +674,8 @@ restart: * Convert <csn, csa> to <ndoms, doms> and populate cpu masks. */ doms = kmalloc(ndoms * sizeof(cpumask_t), GFP_KERNEL); - if (!doms) { - ndoms = 0; + if (!doms) goto done; - } /* * The rest of the code, including the scheduler, can deal with @@ -732,6 +730,13 @@ restart: done: kfree(csa); + /* + * Fallback to the default domain if kmalloc() failed. + * See comments in partition_sched_domains(). + */ + if (doms == NULL) + ndoms = 1; + *domains = doms; *attributes = dattr; return ndoms; @@ -2011,12 +2016,23 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb, * Call this routine anytime after node_states[N_HIGH_MEMORY] changes. * See also the previous routine cpuset_track_online_cpus(). */ -void cpuset_track_online_nodes(void) +static int cpuset_track_online_nodes(struct notifier_block *self, + unsigned long action, void *arg) { cgroup_lock(); - top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY]; - scan_for_empty_cpusets(&top_cpuset); + switch (action) { + case MEM_ONLINE: + top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY]; + break; + case MEM_OFFLINE: + top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY]; + scan_for_empty_cpusets(&top_cpuset); + break; + default: + break; + } cgroup_unlock(); + return NOTIFY_OK; } #endif @@ -2032,6 +2048,7 @@ void __init cpuset_init_smp(void) top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY]; hotcpu_notifier(cpuset_track_online_cpus, 0); + hotplug_memory_notifier(cpuset_track_online_nodes, 10); } /** diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index c9767e64198..64c1c7253da 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -25,6 +25,8 @@ static inline void unregister_handler_proc(unsigned int irq, struct irqaction *action) { } #endif +extern int irq_select_affinity_usr(unsigned int irq); + /* * Debugging printout: */ diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index c498a1b8c62..801addda3c4 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -82,24 +82,27 @@ int irq_can_set_affinity(unsigned int irq) int irq_set_affinity(unsigned int irq, cpumask_t cpumask) { struct irq_desc *desc = irq_to_desc(irq); + unsigned long flags; if (!desc->chip->set_affinity) return -EINVAL; + spin_lock_irqsave(&desc->lock, flags); + #ifdef CONFIG_GENERIC_PENDING_IRQ if (desc->status & IRQ_MOVE_PCNTXT || desc->status & IRQ_DISABLED) { - unsigned long flags; - - spin_lock_irqsave(&desc->lock, flags); desc->affinity = cpumask; desc->chip->set_affinity(irq, cpumask); - spin_unlock_irqrestore(&desc->lock, flags); - } else - set_pending_irq(irq, cpumask); + } else { + desc->status |= IRQ_MOVE_PENDING; + desc->pending_mask = cpumask; + } #else desc->affinity = cpumask; desc->chip->set_affinity(irq, cpumask); #endif + desc->status |= IRQ_AFFINITY_SET; + spin_unlock_irqrestore(&desc->lock, flags); return 0; } @@ -107,24 +110,59 @@ int irq_set_affinity(unsigned int irq, cpumask_t cpumask) /* * Generic version of the affinity autoselector. */ -int irq_select_affinity(unsigned int irq) +int do_irq_select_affinity(unsigned int irq, struct irq_desc *desc) { cpumask_t mask; - struct irq_desc *desc; if (!irq_can_set_affinity(irq)) return 0; cpus_and(mask, cpu_online_map, irq_default_affinity); - desc = irq_to_desc(irq); + /* + * Preserve an userspace affinity setup, but make sure that + * one of the targets is online. + */ + if (desc->status & (IRQ_AFFINITY_SET | IRQ_NO_BALANCING)) { + if (cpus_intersects(desc->affinity, cpu_online_map)) + mask = desc->affinity; + else + desc->status &= ~IRQ_AFFINITY_SET; + } + desc->affinity = mask; desc->chip->set_affinity(irq, mask); return 0; } +#else +static inline int do_irq_select_affinity(unsigned int irq, struct irq_desc *d) +{ + return irq_select_affinity(irq); +} #endif +/* + * Called when affinity is set via /proc/irq + */ +int irq_select_affinity_usr(unsigned int irq) +{ + struct irq_desc *desc = irq_to_desc(irq); + unsigned long flags; + int ret; + + spin_lock_irqsave(&desc->lock, flags); + ret = do_irq_select_affinity(irq, desc); + spin_unlock_irqrestore(&desc->lock, flags); + + return ret; +} + +#else +static inline int do_irq_select_affinity(int irq, struct irq_desc *desc) +{ + return 0; +} #endif /** @@ -327,7 +365,7 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq, * IRQF_TRIGGER_* but the PIC does not support multiple * flow-types? */ - pr_warning("No set_type function for IRQ %d (%s)\n", irq, + pr_debug("No set_type function for IRQ %d (%s)\n", irq, chip ? (chip->name ? : "unknown") : "unknown"); return 0; } @@ -445,8 +483,12 @@ __setup_irq(unsigned int irq, struct irq_desc * desc, struct irqaction *new) /* Undo nested disables: */ desc->depth = 1; + /* Exclude IRQ from balancing if requested */ + if (new->flags & IRQF_NOBALANCING) + desc->status |= IRQ_NO_BALANCING; + /* Set default affinity mask once everything is setup */ - irq_select_affinity(irq); + do_irq_select_affinity(irq, desc); } else if ((new->flags & IRQF_TRIGGER_MASK) && (new->flags & IRQF_TRIGGER_MASK) @@ -459,10 +501,6 @@ __setup_irq(unsigned int irq, struct irq_desc * desc, struct irqaction *new) *p = new; - /* Exclude IRQ from balancing */ - if (new->flags & IRQF_NOBALANCING) - desc->status |= IRQ_NO_BALANCING; - /* Reset broken irq detection when installing new handler */ desc->irq_count = 0; desc->irqs_unhandled = 0; diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c index 90b920d3f52..9db681d9581 100644 --- a/kernel/irq/migration.c +++ b/kernel/irq/migration.c @@ -1,17 +1,6 @@ #include <linux/irq.h> -void set_pending_irq(unsigned int irq, cpumask_t mask) -{ - struct irq_desc *desc = irq_to_desc(irq); - unsigned long flags; - - spin_lock_irqsave(&desc->lock, flags); - desc->status |= IRQ_MOVE_PENDING; - desc->pending_mask = mask; - spin_unlock_irqrestore(&desc->lock, flags); -} - void move_masked_irq(int irq) { struct irq_desc *desc = irq_to_desc(irq); diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index 4d161c70ba5..d257e7d6a8a 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -62,7 +62,7 @@ static ssize_t irq_affinity_proc_write(struct file *file, if (!cpus_intersects(new_value, cpu_online_map)) /* Special case for empty set - allow the architecture code to set default SMP affinity. */ - return irq_select_affinity(irq) ? -EINVAL : count; + return irq_select_affinity_usr(irq) ? -EINVAL : count; irq_set_affinity(irq, new_value); diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 5072cf1685a..7b8b0f21a5b 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -304,17 +304,24 @@ int sprint_symbol(char *buffer, unsigned long address) char *modname; const char *name; unsigned long offset, size; - char namebuf[KSYM_NAME_LEN]; + int len; - name = kallsyms_lookup(address, &size, &offset, &modname, namebuf); + name = kallsyms_lookup(address, &size, &offset, &modname, buffer); if (!name) return sprintf(buffer, "0x%lx", address); + if (name != buffer) + strcpy(buffer, name); + len = strlen(buffer); + buffer += len; + if (modname) - return sprintf(buffer, "%s+%#lx/%#lx [%s]", name, offset, - size, modname); + len += sprintf(buffer, "+%#lx/%#lx [%s]", + offset, size, modname); else - return sprintf(buffer, "%s+%#lx/%#lx", name, offset, size); + len += sprintf(buffer, "+%#lx/%#lx", offset, size); + + return len; } /* Look up a kernel symbol and print it to the kernel messages. */ diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 06e157119d2..46a404173db 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -3276,10 +3276,10 @@ void __init lockdep_info(void) { printk("Lock dependency validator: Copyright (c) 2006 Red Hat, Inc., Ingo Molnar\n"); - printk("... MAX_LOCKDEP_SUBCLASSES: %lu\n", MAX_LOCKDEP_SUBCLASSES); + printk("... MAX_LOCKDEP_SUBCLASSES: %lu\n", MAX_LOCKDEP_SUBCLASSES); printk("... MAX_LOCK_DEPTH: %lu\n", MAX_LOCK_DEPTH); printk("... MAX_LOCKDEP_KEYS: %lu\n", MAX_LOCKDEP_KEYS); - printk("... CLASSHASH_SIZE: %lu\n", CLASSHASH_SIZE); + printk("... CLASSHASH_SIZE: %lu\n", CLASSHASH_SIZE); printk("... MAX_LOCKDEP_ENTRIES: %lu\n", MAX_LOCKDEP_ENTRIES); printk("... MAX_LOCKDEP_CHAINS: %lu\n", MAX_LOCKDEP_CHAINS); printk("... CHAINHASH_SIZE: %lu\n", CHAINHASH_SIZE); diff --git a/kernel/panic.c b/kernel/panic.c index 6513aac8e99..4d5088355bf 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -167,6 +167,7 @@ static const struct tnt tnts[] = { * 'M' - System experienced a machine check exception. * 'B' - System has hit bad_page. * 'U' - Userspace-defined naughtiness. + * 'D' - Kernel has oopsed before * 'A' - ACPI table overridden. * 'W' - Taint on warning. * 'C' - modules from drivers/staging are loaded. diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 153dcb2639c..4e5288a831d 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -311,7 +311,7 @@ static int cpu_clock_sample_group(const clockid_t which_clock, struct task_cputime cputime; thread_group_cputime(p, &cputime); - switch (which_clock) { + switch (CPUCLOCK_WHICH(which_clock)) { default: return -EINVAL; case CPUCLOCK_PROF: @@ -1308,9 +1308,10 @@ static inline int task_cputime_expired(const struct task_cputime *sample, */ static inline int fastpath_timer_check(struct task_struct *tsk) { - struct signal_struct *sig = tsk->signal; + struct signal_struct *sig; - if (unlikely(!sig)) + /* tsk == current, ensure it is safe to use ->signal/sighand */ + if (unlikely(tsk->exit_state)) return 0; if (!task_cputime_zero(&tsk->cputime_expires)) { @@ -1323,6 +1324,8 @@ static inline int fastpath_timer_check(struct task_struct *tsk) if (task_cputime_expired(&task_sample, &tsk->cputime_expires)) return 1; } + + sig = tsk->signal; if (!task_cputime_zero(&sig->cputime_expires)) { struct task_cputime group_sample; diff --git a/kernel/power/main.c b/kernel/power/main.c index 19122cf6d82..b8f7ce9473e 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -174,7 +174,7 @@ static void suspend_test_finish(const char *label) * has some performance issues. The stack dump of a WARN_ON * is more likely to get the right attention than a printk... */ - WARN_ON(msec > (TEST_SUSPEND_SECONDS * 1000)); + WARN(msec > (TEST_SUSPEND_SECONDS * 1000), "Component: %s\n", label); } #else diff --git a/kernel/power/swap.c b/kernel/power/swap.c index b7713b53d07..6da14358537 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -633,7 +633,7 @@ void swsusp_close(fmode_t mode) return; } - blkdev_put(resume_bdev, mode); /* move up */ + blkdev_put(resume_bdev, mode); } static int swsusp_header_init(void) diff --git a/kernel/profile.c b/kernel/profile.c index 9830a037d8d..dc41827fbfe 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -351,7 +351,7 @@ out: put_cpu(); } -static int __devinit profile_cpu_callback(struct notifier_block *info, +static int __cpuinit profile_cpu_callback(struct notifier_block *info, unsigned long action, void *__cpu) { int node, cpu = (unsigned long)__cpu; @@ -544,7 +544,7 @@ static const struct file_operations proc_profile_operations = { }; #ifdef CONFIG_SMP -static void __init profile_nop(void *unused) +static inline void profile_nop(void *unused) { } @@ -596,7 +596,7 @@ out_cleanup: #define create_hash_tables() ({ 0; }) #endif -int create_proc_profile(void) +int __ref create_proc_profile(void) /* false positive from hotcpu_notifier */ { struct proc_dir_entry *entry; diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 1e68e4c39e2..4c8bcd7dd8e 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -612,7 +612,7 @@ int generic_ptrace_pokedata(struct task_struct *tsk, long addr, long data) return (copied == sizeof(data)) ? 0 : -EIO; } -#if defined CONFIG_COMPAT && defined __ARCH_WANT_COMPAT_SYS_PTRACE +#if defined CONFIG_COMPAT #include <linux/compat.h> int compat_ptrace_request(struct task_struct *child, compat_long_t request, @@ -709,4 +709,4 @@ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid, unlock_kernel(); return ret; } -#endif /* CONFIG_COMPAT && __ARCH_WANT_COMPAT_SYS_PTRACE */ +#endif /* CONFIG_COMPAT */ diff --git a/kernel/relay.c b/kernel/relay.c index 8d13a7855c0..32b0befdcb6 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -400,7 +400,7 @@ void relay_reset(struct rchan *chan) } mutex_lock(&relay_channels_mutex); - for_each_online_cpu(i) + for_each_possible_cpu(i) if (chan->buf[i]) __relay_reset(chan->buf[i], 0); mutex_unlock(&relay_channels_mutex); @@ -611,10 +611,9 @@ struct rchan *relay_open(const char *base_filename, return chan; free_bufs: - for_each_online_cpu(i) { - if (!chan->buf[i]) - break; - relay_close_buf(chan->buf[i]); + for_each_possible_cpu(i) { + if (chan->buf[i]) + relay_close_buf(chan->buf[i]); } kref_put(&chan->kref, relay_destroy_channel); diff --git a/kernel/sched.c b/kernel/sched.c index c94baf2969e..b7480fb5c3d 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1453,9 +1453,10 @@ static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd); static unsigned long cpu_avg_load_per_task(int cpu) { struct rq *rq = cpu_rq(cpu); + unsigned long nr_running = ACCESS_ONCE(rq->nr_running); - if (rq->nr_running) - rq->avg_load_per_task = rq->load.weight / rq->nr_running; + if (nr_running) + rq->avg_load_per_task = rq->load.weight / nr_running; else rq->avg_load_per_task = 0; @@ -7789,13 +7790,14 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur, * * The passed in 'doms_new' should be kmalloc'd. This routine takes * ownership of it and will kfree it when done with it. If the caller - * failed the kmalloc call, then it can pass in doms_new == NULL, - * and partition_sched_domains() will fallback to the single partition - * 'fallback_doms', it also forces the domains to be rebuilt. + * failed the kmalloc call, then it can pass in doms_new == NULL && + * ndoms_new == 1, and partition_sched_domains() will fallback to + * the single partition 'fallback_doms', it also forces the domains + * to be rebuilt. * - * If doms_new==NULL it will be replaced with cpu_online_map. - * ndoms_new==0 is a special case for destroying existing domains. - * It will not create the default domain. + * If doms_new == NULL it will be replaced with cpu_online_map. + * ndoms_new == 0 is a special case for destroying existing domains, + * and it will not create the default domain. * * Call with hotplug lock held */ diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index 48ecc51e770..26ed8e3d1c1 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -423,10 +423,11 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) #undef __P { + unsigned int this_cpu = raw_smp_processor_id(); u64 t0, t1; - t0 = sched_clock(); - t1 = sched_clock(); + t0 = cpu_clock(this_cpu); + t1 = cpu_clock(this_cpu); SEQ_printf(m, "%-35s:%21Ld\n", "clock-delta", (long long)(t1-t0)); } diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h index ee71bec1da6..7dbf72a2b02 100644 --- a/kernel/sched_stats.h +++ b/kernel/sched_stats.h @@ -298,9 +298,11 @@ static inline void account_group_user_time(struct task_struct *tsk, { struct signal_struct *sig; - sig = tsk->signal; - if (unlikely(!sig)) + /* tsk == current, ensure it is safe to use ->signal */ + if (unlikely(tsk->exit_state)) return; + + sig = tsk->signal; if (sig->cputime.totals) { struct task_cputime *times; @@ -325,9 +327,11 @@ static inline void account_group_system_time(struct task_struct *tsk, { struct signal_struct *sig; - sig = tsk->signal; - if (unlikely(!sig)) + /* tsk == current, ensure it is safe to use ->signal */ + if (unlikely(tsk->exit_state)) return; + + sig = tsk->signal; if (sig->cputime.totals) { struct task_cputime *times; @@ -353,8 +357,11 @@ static inline void account_group_exec_runtime(struct task_struct *tsk, struct signal_struct *sig; sig = tsk->signal; + /* see __exit_signal()->task_rq_unlock_wait() */ + barrier(); if (unlikely(!sig)) return; + if (sig->cputime.totals) { struct task_cputime *times; diff --git a/kernel/softlockup.c b/kernel/softlockup.c index 3953e4aed73..dc0b3be6b7d 100644 --- a/kernel/softlockup.c +++ b/kernel/softlockup.c @@ -188,7 +188,7 @@ static void check_hung_task(struct task_struct *t, unsigned long now) if ((long)(now - t->last_switch_timestamp) < sysctl_hung_task_timeout_secs) return; - if (sysctl_hung_task_warnings < 0) + if (!sysctl_hung_task_warnings) return; sysctl_hung_task_warnings--; diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index a77b27b11b0..e14a2328170 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -31,7 +31,7 @@ cond_syscall(sys_socketpair); cond_syscall(sys_bind); cond_syscall(sys_listen); cond_syscall(sys_accept); -cond_syscall(sys_paccept); +cond_syscall(sys_accept4); cond_syscall(sys_connect); cond_syscall(sys_getsockname); cond_syscall(sys_getpeername); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 9d048fa2d90..3d56fe7570d 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -176,6 +176,9 @@ extern struct ctl_table random_table[]; #ifdef CONFIG_INOTIFY_USER extern struct ctl_table inotify_table[]; #endif +#ifdef CONFIG_EPOLL +extern struct ctl_table epoll_table[]; +#endif #ifdef HAVE_ARCH_PICK_MMAP_LAYOUT int sysctl_legacy_va_layout; @@ -1325,6 +1328,13 @@ static struct ctl_table fs_table[] = { .child = inotify_table, }, #endif +#ifdef CONFIG_EPOLL + { + .procname = "epoll", + .mode = 0555, + .child = epoll_table, + }, +#endif #endif { .ctl_name = KERN_SETUID_DUMPABLE, diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index e7acfb482a6..fa05e88aa76 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -518,6 +518,28 @@ void update_wall_time(void) /* correct the clock when NTP error is too big */ clocksource_adjust(offset); + /* + * Since in the loop above, we accumulate any amount of time + * in xtime_nsec over a second into xtime.tv_sec, its possible for + * xtime_nsec to be fairly small after the loop. Further, if we're + * slightly speeding the clocksource up in clocksource_adjust(), + * its possible the required corrective factor to xtime_nsec could + * cause it to underflow. + * + * Now, we cannot simply roll the accumulated second back, since + * the NTP subsystem has been notified via second_overflow. So + * instead we push xtime_nsec forward by the amount we underflowed, + * and add that amount into the error. + * + * We'll correct this error next time through this function, when + * xtime_nsec is not as small. + */ + if (unlikely((s64)clock->xtime_nsec < 0)) { + s64 neg = -(s64)clock->xtime_nsec; + clock->xtime_nsec = 0; + clock->error += neg << (NTP_SCALE_SHIFT - clock->shift); + } + /* store full nanoseconds into xtime after rounding it up and * add the remainder to the error difference. */ diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 4a39d24568c..78db083390f 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -185,7 +185,6 @@ enum { }; static int ftrace_filtered; -static int tracing_on; static LIST_HEAD(ftrace_new_addrs); @@ -327,96 +326,89 @@ ftrace_record_ip(unsigned long ip) static int __ftrace_replace_code(struct dyn_ftrace *rec, - unsigned char *old, unsigned char *new, int enable) + unsigned char *nop, int enable) { unsigned long ip, fl; + unsigned char *call, *old, *new; ip = rec->ip; - if (ftrace_filtered && enable) { + /* + * If this record is not to be traced and + * it is not enabled then do nothing. + * + * If this record is not to be traced and + * it is enabled then disabled it. + * + */ + if (rec->flags & FTRACE_FL_NOTRACE) { + if (rec->flags & FTRACE_FL_ENABLED) + rec->flags &= ~FTRACE_FL_ENABLED; + else + return 0; + + } else if (ftrace_filtered && enable) { /* - * If filtering is on: - * - * If this record is set to be filtered and - * is enabled then do nothing. - * - * If this record is set to be filtered and - * it is not enabled, enable it. - * - * If this record is not set to be filtered - * and it is not enabled do nothing. - * - * If this record is set not to trace then - * do nothing. - * - * If this record is set not to trace and - * it is enabled then disable it. - * - * If this record is not set to be filtered and - * it is enabled, disable it. + * Filtering is on: */ - fl = rec->flags & (FTRACE_FL_FILTER | FTRACE_FL_NOTRACE | - FTRACE_FL_ENABLED); + fl = rec->flags & (FTRACE_FL_FILTER | FTRACE_FL_ENABLED); - if ((fl == (FTRACE_FL_FILTER | FTRACE_FL_ENABLED)) || - (fl == (FTRACE_FL_FILTER | FTRACE_FL_NOTRACE)) || - !fl || (fl == FTRACE_FL_NOTRACE)) + /* Record is filtered and enabled, do nothing */ + if (fl == (FTRACE_FL_FILTER | FTRACE_FL_ENABLED)) return 0; - /* - * If it is enabled disable it, - * otherwise enable it! - */ - if (fl & FTRACE_FL_ENABLED) { - /* swap new and old */ - new = old; - old = ftrace_call_replace(ip, FTRACE_ADDR); + /* Record is not filtered and is not enabled do nothing */ + if (!fl) + return 0; + + /* Record is not filtered but enabled, disable it */ + if (fl == FTRACE_FL_ENABLED) rec->flags &= ~FTRACE_FL_ENABLED; - } else { - new = ftrace_call_replace(ip, FTRACE_ADDR); + else + /* Otherwise record is filtered but not enabled, enable it */ rec->flags |= FTRACE_FL_ENABLED; - } } else { + /* Disable or not filtered */ if (enable) { - /* - * If this record is set not to trace and is - * not enabled, do nothing. - */ - fl = rec->flags & (FTRACE_FL_NOTRACE | FTRACE_FL_ENABLED); - if (fl == FTRACE_FL_NOTRACE) - return 0; - - new = ftrace_call_replace(ip, FTRACE_ADDR); - } else - old = ftrace_call_replace(ip, FTRACE_ADDR); - - if (enable) { + /* if record is enabled, do nothing */ if (rec->flags & FTRACE_FL_ENABLED) return 0; + rec->flags |= FTRACE_FL_ENABLED; + } else { + + /* if record is not enabled do nothing */ if (!(rec->flags & FTRACE_FL_ENABLED)) return 0; + rec->flags &= ~FTRACE_FL_ENABLED; } } + call = ftrace_call_replace(ip, FTRACE_ADDR); + + if (rec->flags & FTRACE_FL_ENABLED) { + old = nop; + new = call; + } else { + old = call; + new = nop; + } + return ftrace_modify_code(ip, old, new); } static void ftrace_replace_code(int enable) { int i, failed; - unsigned char *new = NULL, *old = NULL; + unsigned char *nop = NULL; struct dyn_ftrace *rec; struct ftrace_page *pg; - if (enable) - old = ftrace_nop_replace(); - else - new = ftrace_nop_replace(); + nop = ftrace_nop_replace(); for (pg = ftrace_pages_start; pg; pg = pg->next) { for (i = 0; i < pg->index; i++) { @@ -434,7 +426,7 @@ static void ftrace_replace_code(int enable) unfreeze_record(rec); } - failed = __ftrace_replace_code(rec, old, new, enable); + failed = __ftrace_replace_code(rec, nop, enable); if (failed && (rec->flags & FTRACE_FL_CONVERTED)) { rec->flags |= FTRACE_FL_FAILED; if ((system_state == SYSTEM_BOOTING) || @@ -506,13 +498,10 @@ static int __ftrace_modify_code(void *data) { int *command = data; - if (*command & FTRACE_ENABLE_CALLS) { + if (*command & FTRACE_ENABLE_CALLS) ftrace_replace_code(1); - tracing_on = 1; - } else if (*command & FTRACE_DISABLE_CALLS) { + else if (*command & FTRACE_DISABLE_CALLS) ftrace_replace_code(0); - tracing_on = 0; - } if (*command & FTRACE_UPDATE_TRACE_FUNC) ftrace_update_ftrace_func(ftrace_trace_function); @@ -538,8 +527,7 @@ static void ftrace_startup(void) mutex_lock(&ftrace_start_lock); ftrace_start++; - if (ftrace_start == 1) - command |= FTRACE_ENABLE_CALLS; + command |= FTRACE_ENABLE_CALLS; if (saved_ftrace_func != ftrace_trace_function) { saved_ftrace_func = ftrace_trace_function; @@ -677,7 +665,7 @@ static int __init ftrace_dyn_table_alloc(unsigned long num_to_init) cnt = num_to_init / ENTRIES_PER_PAGE; pr_info("ftrace: allocating %ld entries in %d pages\n", - num_to_init, cnt); + num_to_init, cnt + 1); for (i = 0; i < cnt; i++) { pg->next = (void *)get_zeroed_page(GFP_KERNEL); @@ -738,6 +726,9 @@ t_next(struct seq_file *m, void *v, loff_t *pos) ((iter->flags & FTRACE_ITER_FAILURES) && !(rec->flags & FTRACE_FL_FAILED)) || + ((iter->flags & FTRACE_ITER_FILTER) && + !(rec->flags & FTRACE_FL_FILTER)) || + ((iter->flags & FTRACE_ITER_NOTRACE) && !(rec->flags & FTRACE_FL_NOTRACE))) { rec = NULL; @@ -757,13 +748,11 @@ static void *t_start(struct seq_file *m, loff_t *pos) void *p = NULL; loff_t l = -1; - if (*pos != iter->pos) { - for (p = t_next(m, p, &l); p && l < *pos; p = t_next(m, p, &l)) - ; - } else { - l = *pos; - p = t_next(m, p, &l); - } + if (*pos > iter->pos) + *pos = iter->pos; + + l = *pos; + p = t_next(m, p, &l); return p; } @@ -774,15 +763,21 @@ static void t_stop(struct seq_file *m, void *p) static int t_show(struct seq_file *m, void *v) { + struct ftrace_iterator *iter = m->private; struct dyn_ftrace *rec = v; char str[KSYM_SYMBOL_LEN]; + int ret = 0; if (!rec) return 0; kallsyms_lookup(rec->ip, NULL, NULL, NULL, str); - seq_printf(m, "%s\n", str); + ret = seq_printf(m, "%s\n", str); + if (ret < 0) { + iter->pos--; + iter->idx--; + } return 0; } @@ -808,7 +803,7 @@ ftrace_avail_open(struct inode *inode, struct file *file) return -ENOMEM; iter->pg = ftrace_pages_start; - iter->pos = -1; + iter->pos = 0; ret = seq_open(file, &show_ftrace_seq_ops); if (!ret) { @@ -895,7 +890,7 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable) if (file->f_mode & FMODE_READ) { iter->pg = ftrace_pages_start; - iter->pos = -1; + iter->pos = 0; iter->flags = enable ? FTRACE_ITER_FILTER : FTRACE_ITER_NOTRACE; @@ -1186,7 +1181,7 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable) mutex_lock(&ftrace_sysctl_lock); mutex_lock(&ftrace_start_lock); - if (iter->filtered && ftrace_start && ftrace_enabled) + if (ftrace_start && ftrace_enabled) ftrace_run_update_code(FTRACE_ENABLE_CALLS); mutex_unlock(&ftrace_start_lock); mutex_unlock(&ftrace_sysctl_lock); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 2f76193c348..668bbb5ef2b 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -16,14 +16,49 @@ #include <linux/list.h> #include <linux/fs.h> +#include "trace.h" + +/* Global flag to disable all recording to ring buffers */ +static int ring_buffers_off __read_mostly; + +/** + * tracing_on - enable all tracing buffers + * + * This function enables all tracing buffers that may have been + * disabled with tracing_off. + */ +void tracing_on(void) +{ + ring_buffers_off = 0; +} + +/** + * tracing_off - turn off all tracing buffers + * + * This function stops all tracing buffers from recording data. + * It does not disable any overhead the tracers themselves may + * be causing. This function simply causes all recording to + * the ring buffers to fail. + */ +void tracing_off(void) +{ + ring_buffers_off = 1; +} + /* Up this if you want to test the TIME_EXTENTS and normalization */ #define DEBUG_SHIFT 0 /* FIXME!!! */ u64 ring_buffer_time_stamp(int cpu) { + u64 time; + + preempt_disable_notrace(); /* shift to debug/test normalization and TIME_EXTENTS */ - return sched_clock() << DEBUG_SHIFT; + time = sched_clock() << DEBUG_SHIFT; + preempt_enable_notrace(); + + return time; } void ring_buffer_normalize_time_stamp(int cpu, u64 *ts) @@ -503,6 +538,12 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size) LIST_HEAD(pages); int i, cpu; + /* + * Always succeed at resizing a non-existent buffer: + */ + if (!buffer) + return size; + size = DIV_ROUND_UP(size, BUF_PAGE_SIZE); size *= BUF_PAGE_SIZE; buffer_size = buffer->pages * BUF_PAGE_SIZE; @@ -576,6 +617,7 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size) list_del_init(&page->list); free_buffer_page(page); } + mutex_unlock(&buffer->mutex); return -ENOMEM; } @@ -1133,6 +1175,9 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, struct ring_buffer_event *event; int cpu, resched; + if (ring_buffers_off) + return NULL; + if (atomic_read(&buffer->record_disabled)) return NULL; @@ -1170,7 +1215,7 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, out: if (resched) - preempt_enable_notrace(); + preempt_enable_no_resched_notrace(); else preempt_enable_notrace(); return NULL; @@ -1249,6 +1294,9 @@ int ring_buffer_write(struct ring_buffer *buffer, int ret = -EBUSY; int cpu, resched; + if (ring_buffers_off) + return -EBUSY; + if (atomic_read(&buffer->record_disabled)) return -EBUSY; @@ -2070,3 +2118,69 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a, return 0; } +static ssize_t +rb_simple_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + int *p = filp->private_data; + char buf[64]; + int r; + + /* !ring_buffers_off == tracing_on */ + r = sprintf(buf, "%d\n", !*p); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t +rb_simple_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + int *p = filp->private_data; + char buf[64]; + long val; + int ret; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + ret = strict_strtoul(buf, 10, &val); + if (ret < 0) + return ret; + + /* !ring_buffers_off == tracing_on */ + *p = !val; + + (*ppos)++; + + return cnt; +} + +static struct file_operations rb_simple_fops = { + .open = tracing_open_generic, + .read = rb_simple_read, + .write = rb_simple_write, +}; + + +static __init int rb_init_debugfs(void) +{ + struct dentry *d_tracer; + struct dentry *entry; + + d_tracer = tracing_init_dentry(); + + entry = debugfs_create_file("tracing_on", 0644, d_tracer, + &ring_buffers_off, &rb_simple_fops); + if (!entry) + pr_warning("Could not create debugfs 'tracing_on' entry\n"); + + return 0; +} + +fs_initcall(rb_init_debugfs); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 697eda36b86..d86e3252f30 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1936,6 +1936,7 @@ __tracing_open(struct inode *inode, struct file *file, int *ret) ring_buffer_read_finish(iter->buffer_iter[cpu]); } mutex_unlock(&trace_types_lock); + kfree(iter); return ERR_PTR(-ENOMEM); } diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index f28484618ff..e62cbf78eab 100644 --- a/kernel/trace/trace_mmiotrace.c +++ b/kernel/trace/trace_mmiotrace.c @@ -18,12 +18,14 @@ struct header_iter { static struct trace_array *mmio_trace_array; static bool overrun_detected; +static unsigned long prev_overruns; static void mmio_reset_data(struct trace_array *tr) { int cpu; overrun_detected = false; + prev_overruns = 0; tr->time_start = ftrace_now(tr->cpu); for_each_online_cpu(cpu) @@ -128,16 +130,12 @@ static void mmio_close(struct trace_iterator *iter) static unsigned long count_overruns(struct trace_iterator *iter) { - int cpu; unsigned long cnt = 0; -/* FIXME: */ -#if 0 - for_each_online_cpu(cpu) { - cnt += iter->overrun[cpu]; - iter->overrun[cpu] = 0; - } -#endif - (void)cpu; + unsigned long over = ring_buffer_overruns(iter->tr->buffer); + + if (over > prev_overruns) + cnt = over - prev_overruns; + prev_overruns = over; return cnt; } diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index be682b62fe5..3bdb44bde4b 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -184,11 +184,16 @@ static struct file_operations stack_max_size_fops = { static void * t_next(struct seq_file *m, void *v, loff_t *pos) { - long i = (long)m->private; + long i; (*pos)++; - i++; + if (v == SEQ_START_TOKEN) + i = 0; + else { + i = *(long *)v; + i++; + } if (i >= max_stack_trace.nr_entries || stack_dump_trace[i] == ULONG_MAX) @@ -201,12 +206,15 @@ t_next(struct seq_file *m, void *v, loff_t *pos) static void *t_start(struct seq_file *m, loff_t *pos) { - void *t = &m->private; + void *t = SEQ_START_TOKEN; loff_t l = 0; local_irq_disable(); __raw_spin_lock(&max_stack_lock); + if (*pos == 0) + return SEQ_START_TOKEN; + for (; t && l < *pos; t = t_next(m, t, &l)) ; @@ -235,10 +243,10 @@ static int trace_lookup_stack(struct seq_file *m, long i) static int t_show(struct seq_file *m, void *v) { - long i = *(long *)v; + long i; int size; - if (i < 0) { + if (v == SEQ_START_TOKEN) { seq_printf(m, " Depth Size Location" " (%d entries)\n" " ----- ---- --------\n", @@ -246,6 +254,8 @@ static int t_show(struct seq_file *m, void *v) return 0; } + i = *(long *)v; + if (i >= max_stack_trace.nr_entries || stack_dump_trace[i] == ULONG_MAX) return 0; @@ -275,10 +285,6 @@ static int stack_trace_open(struct inode *inode, struct file *file) int ret; ret = seq_open(file, &stack_trace_seq_ops); - if (!ret) { - struct seq_file *m = file->private_data; - m->private = (void *)-1; - } return ret; } |