diff options
Diffstat (limited to 'kernel')
52 files changed, 291 insertions, 173 deletions
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index 37b2bea170c8..e99dda04b126 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -607,7 +607,7 @@ void audit_trim_trees(void) spin_lock(&hash_lock); list_for_each_entry(node, &tree->chunks, list) { struct audit_chunk *chunk = find_chunk(node); - /* this could be NULL if the watch is dieing else where... */ + /* this could be NULL if the watch is dying else where... */ struct inode *inode = chunk->mark.i.inode; node->index |= 1U<<31; if (iterate_mounts(compare_root, inode, root_mnt)) diff --git a/kernel/auditsc.c b/kernel/auditsc.c index f49a0318c2ed..b33513a08beb 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1011,7 +1011,7 @@ static int audit_log_pid_context(struct audit_context *context, pid_t pid, /* * to_send and len_sent accounting are very loose estimates. We aren't * really worried about a hard cap to MAX_EXECVE_AUDIT_LEN so much as being - * within about 500 bytes (next page boundry) + * within about 500 bytes (next page boundary) * * why snprintf? an int is up to 12 digits long. if we just assumed when * logging that a[%d]= was going to be 16 characters long we would be wasting diff --git a/kernel/cgroup.c b/kernel/cgroup.c index e31b220a743d..25c7eb52de1a 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -157,7 +157,7 @@ struct css_id { }; /* - * cgroup_event represents events which userspace want to recieve. + * cgroup_event represents events which userspace want to receive. */ struct cgroup_event { /* diff --git a/kernel/cpu.c b/kernel/cpu.c index c95fc4df0faa..12b7458f23b1 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -126,7 +126,7 @@ static void cpu_hotplug_done(void) #else /* #if CONFIG_HOTPLUG_CPU */ static void cpu_hotplug_begin(void) {} static void cpu_hotplug_done(void) {} -#endif /* #esle #if CONFIG_HOTPLUG_CPU */ +#endif /* #else #if CONFIG_HOTPLUG_CPU */ /* Need to know about CPUs going up/down? */ int __ref register_cpu_notifier(struct notifier_block *nb) diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index cefd4a11f6d9..bad6786dee88 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -538,7 +538,7 @@ return_normal: /* * For single stepping, try to only enter on the processor - * that was single stepping. To gaurd against a deadlock, the + * that was single stepping. To guard against a deadlock, the * kernel will only try for the value of sstep_tries before * giving up and continuing on. */ diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 6bc6e3bc4f9c..be14779bcef6 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -441,9 +441,9 @@ static int kdb_check_regs(void) * symbol name, and offset to the caller. * * The argument may consist of a numeric value (decimal or - * hexidecimal), a symbol name, a register name (preceeded by the + * hexidecimal), a symbol name, a register name (preceded by the * percent sign), an environment variable with a numeric value - * (preceeded by a dollar sign) or a simple arithmetic expression + * (preceded by a dollar sign) or a simple arithmetic expression * consisting of a symbol name, +/-, and a numeric constant value * (offset). * Parameters: @@ -1335,7 +1335,7 @@ void kdb_print_state(const char *text, int value) * error The hardware-defined error code * reason2 kdb's current reason code. * Initially error but can change - * acording to kdb state. + * according to kdb state. * db_result Result code from break or debug point. * regs The exception frame at time of fault/breakpoint. * should always be valid. diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c index 6b2485dcb050..5532dd37aa86 100644 --- a/kernel/debug/kdb/kdb_support.c +++ b/kernel/debug/kdb/kdb_support.c @@ -545,7 +545,7 @@ int kdb_putword(unsigned long addr, unsigned long word, size_t size) * Mask for process state. * Notes: * The mask folds data from several sources into a single long value, so - * be carefull not to overlap the bits. TASK_* bits are in the LSB, + * be careful not to overlap the bits. TASK_* bits are in the LSB, * special cases like UNRUNNABLE are in the MSB. As of 2.6.10-rc1 there * is no overlap between TASK_* and EXIT_* but that may not always be * true, so EXIT_* bits are shifted left 16 bits before being stored in diff --git a/kernel/exit.c b/kernel/exit.c index 6a488ad2dce5..f5d2f63bae0b 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -841,7 +841,7 @@ static void exit_notify(struct task_struct *tsk, int group_dead) /* Let father know we died * * Thread signals are configurable, but you aren't going to use - * that to send signals to arbitary processes. + * that to send signals to arbitrary processes. * That stops right now. * * If the parent exec id doesn't match the exec id we saved diff --git a/kernel/futex.c b/kernel/futex.c index dfb924ffe65b..fe28dc282eae 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1886,7 +1886,7 @@ retry: restart->futex.val = val; restart->futex.time = abs_time->tv64; restart->futex.bitset = bitset; - restart->futex.flags = flags; + restart->futex.flags = flags | FLAGS_HAS_TIMEOUT; ret = -ERESTART_RESTARTBLOCK; diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 9017478c5d4c..87fdb3f8db14 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -81,7 +81,11 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) = } }; -static int hrtimer_clock_to_base_table[MAX_CLOCKS]; +static int hrtimer_clock_to_base_table[MAX_CLOCKS] = { + [CLOCK_REALTIME] = HRTIMER_BASE_REALTIME, + [CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC, + [CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME, +}; static inline int hrtimer_clockid_to_base(clockid_t clock_id) { @@ -1722,10 +1726,6 @@ static struct notifier_block __cpuinitdata hrtimers_nb = { void __init hrtimers_init(void) { - hrtimer_clock_to_base_table[CLOCK_REALTIME] = HRTIMER_BASE_REALTIME; - hrtimer_clock_to_base_table[CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC; - hrtimer_clock_to_base_table[CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME; - hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE, (void *)(long)smp_processor_id()); register_cpu_notifier(&hrtimers_nb); diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 1dafc8652bd8..4af1e2b244cb 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -415,7 +415,7 @@ out: * @desc: the interrupt description structure for this irq * * Interrupt occures on the falling and/or rising edge of a hardware - * signal. The occurence is latched into the irq controller hardware + * signal. The occurrence is latched into the irq controller hardware * and must be acked in order to be reenabled. After the ack another * interrupt can happen on the same source even before the first one * is handled by the associated event handler. If this happens it diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 12a80fdae11c..07c1611f3899 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1051,6 +1051,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) register_irq_proc(irq, desc); new->dir = NULL; register_handler_proc(irq, new); + free_cpumask_var(mask); return 0; diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c index bc6194698dfd..47420908fba0 100644 --- a/kernel/irq/migration.c +++ b/kernel/irq/migration.c @@ -35,7 +35,7 @@ void irq_move_masked_irq(struct irq_data *idata) * do the disable, re-program, enable sequence. * This is *not* particularly important for level triggered * but in a edge trigger case, we might be setting rte - * when an active trigger is comming in. This could + * when an active trigger is coming in. This could * cause some ioapics to mal-function. * Being paranoid i guess! * diff --git a/kernel/kexec.c b/kernel/kexec.c index ec19b92c7ebd..87b77de03dd3 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -33,6 +33,7 @@ #include <linux/vmalloc.h> #include <linux/swap.h> #include <linux/kmsg_dump.h> +#include <linux/syscore_ops.h> #include <asm/page.h> #include <asm/uaccess.h> @@ -144,7 +145,7 @@ static int do_kimage_alloc(struct kimage **rimage, unsigned long entry, /* Initialize the list of destination pages */ INIT_LIST_HEAD(&image->dest_pages); - /* Initialize the list of unuseable pages */ + /* Initialize the list of unusable pages */ INIT_LIST_HEAD(&image->unuseable_pages); /* Read in the segments */ @@ -454,7 +455,7 @@ static struct page *kimage_alloc_normal_control_pages(struct kimage *image, /* Deal with the destination pages I have inadvertently allocated. * * Ideally I would convert multi-page allocations into single - * page allocations, and add everyting to image->dest_pages. + * page allocations, and add everything to image->dest_pages. * * For now it is simpler to just free the pages. */ @@ -602,7 +603,7 @@ static void kimage_free_extra_pages(struct kimage *image) /* Walk through and free any extra destination pages I may have */ kimage_free_page_list(&image->dest_pages); - /* Walk through and free any unuseable pages I have cached */ + /* Walk through and free any unusable pages I have cached */ kimage_free_page_list(&image->unuseable_pages); } @@ -1099,7 +1100,8 @@ size_t crash_get_memory_size(void) return size; } -static void free_reserved_phys_range(unsigned long begin, unsigned long end) +void __weak crash_free_reserved_phys_range(unsigned long begin, + unsigned long end) { unsigned long addr; @@ -1135,7 +1137,7 @@ int crash_shrink_memory(unsigned long new_size) start = roundup(start, PAGE_SIZE); end = roundup(start + new_size, PAGE_SIZE); - free_reserved_phys_range(end, crashk_res.end); + crash_free_reserved_phys_range(end, crashk_res.end); if ((start == end) && (crashk_res.parent != NULL)) release_resource(&crashk_res); @@ -1531,6 +1533,11 @@ int kernel_kexec(void) local_irq_disable(); /* Suspend system devices */ error = sysdev_suspend(PMSG_FREEZE); + if (!error) { + error = syscore_suspend(); + if (error) + sysdev_resume(); + } if (error) goto Enable_irqs; } else @@ -1545,6 +1552,7 @@ int kernel_kexec(void) #ifdef CONFIG_KEXEC_JUMP if (kexec_image->preserve_context) { + syscore_resume(); sysdev_resume(); Enable_irqs: local_irq_enable(); diff --git a/kernel/kthread.c b/kernel/kthread.c index 684ab3f7dd72..3b34d2732bce 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -139,7 +139,7 @@ static void create_kthread(struct kthread_create_info *create) * in @node, to get NUMA affinity for kthread stack, or else give -1. * When woken, the thread will run @threadfn() with @data as its * argument. @threadfn() can either call do_exit() directly if it is a - * standalone thread for which noone will call kthread_stop(), or + * standalone thread for which no one will call kthread_stop(), or * return when 'kthread_should_stop()' is true (which means * kthread_stop() has been called). The return value should be zero * or a negative error number; it will be passed to kthread_stop(). diff --git a/kernel/latencytop.c b/kernel/latencytop.c index ee74b35e528d..376066e10413 100644 --- a/kernel/latencytop.c +++ b/kernel/latencytop.c @@ -153,7 +153,7 @@ static inline void store_stacktrace(struct task_struct *tsk, } /** - * __account_scheduler_latency - record an occured latency + * __account_scheduler_latency - record an occurred latency * @tsk - the task struct of the task hitting the latency * @usecs - the duration of the latency in microseconds * @inter - 1 if the sleep was interruptible, 0 if uninterruptible diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 0d2058da80f5..53a68956f131 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -2309,7 +2309,7 @@ void trace_hardirqs_on_caller(unsigned long ip) if (unlikely(curr->hardirqs_enabled)) { /* * Neither irq nor preemption are disabled here - * so this is racy by nature but loosing one hit + * so this is racy by nature but losing one hit * in a stat is not a big deal. */ __debug_atomic_inc(redundant_hardirqs_on); @@ -2620,7 +2620,7 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this, if (!graph_lock()) return 0; /* - * Make sure we didnt race: + * Make sure we didn't race: */ if (unlikely(hlock_class(this)->usage_mask & new_mask)) { graph_unlock(); diff --git a/kernel/module.c b/kernel/module.c index 1f9f7bc56ca1..d5938a5c19c4 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -809,7 +809,7 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user, wait_for_zero_refcount(mod); mutex_unlock(&module_mutex); - /* Final destruction now noone is using it. */ + /* Final destruction now no one is using it. */ if (mod->exit != NULL) mod->exit(); blocking_notifier_call_chain(&module_notify_list, @@ -2777,7 +2777,7 @@ static struct module *load_module(void __user *umod, mod->state = MODULE_STATE_COMING; /* Now sew it into the lists so we can get lockdep and oops - * info during argument parsing. Noone should access us, since + * info during argument parsing. No one should access us, since * strong_try_module_get() will fail. * lockdep/oops can run asynchronous, so use the RCU list insertion * function to insert in a way safe to concurrent readers. @@ -2971,7 +2971,7 @@ static const char *get_ksymbol(struct module *mod, else nextval = (unsigned long)mod->module_core+mod->core_text_size; - /* Scan for closest preceeding symbol, and next symbol. (ELF + /* Scan for closest preceding symbol, and next symbol. (ELF starts real symbols at 1). */ for (i = 1; i < mod->num_symtab; i++) { if (mod->symtab[i].st_shndx == SHN_UNDEF) diff --git a/kernel/mutex.c b/kernel/mutex.c index a5889fb28ecf..c4195fa98900 100644 --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -245,7 +245,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, } __set_task_state(task, state); - /* didnt get the lock, go to sleep: */ + /* didn't get the lock, go to sleep: */ spin_unlock_mutex(&lock->wait_lock, flags); preempt_enable_no_resched(); schedule(); diff --git a/kernel/padata.c b/kernel/padata.c index 751019415d23..b91941df5e63 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -262,7 +262,7 @@ static void padata_reorder(struct parallel_data *pd) /* * This cpu has to do the parallel processing of the next * object. It's waiting in the cpu's parallelization queue, - * so exit imediately. + * so exit immediately. */ if (PTR_ERR(padata) == -ENODATA) { del_timer(&pd->timer); @@ -284,7 +284,7 @@ static void padata_reorder(struct parallel_data *pd) /* * The next object that needs serialization might have arrived to * the reorder queues in the meantime, we will be called again - * from the timer function if noone else cares for it. + * from the timer function if no one else cares for it. */ if (atomic_read(&pd->reorder_objects) && !(pinst->flags & PADATA_RESET)) @@ -515,7 +515,7 @@ static void __padata_stop(struct padata_instance *pinst) put_online_cpus(); } -/* Replace the internal control stucture with a new one. */ +/* Replace the internal control structure with a new one. */ static void padata_replace(struct padata_instance *pinst, struct parallel_data *pd_new) { @@ -768,7 +768,7 @@ static int __padata_remove_cpu(struct padata_instance *pinst, int cpu) } /** - * padata_remove_cpu - remove a cpu from the one or both(serial and paralell) + * padata_remove_cpu - remove a cpu from the one or both(serial and parallel) * padata cpumasks. * * @pinst: padata instance diff --git a/kernel/params.c b/kernel/params.c index 0da1411222b9..7ab388a48a2e 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -95,7 +95,7 @@ static int parse_one(char *param, /* Find parameter */ for (i = 0; i < num_params; i++) { if (parameq(param, params[i].name)) { - /* Noone handled NULL, so do it here. */ + /* No one handled NULL, so do it here. */ if (!val && params[i].ops->set != param_set_bool) return -EINVAL; DEBUGP("They are equal! Calling %p\n", diff --git a/kernel/perf_event.c b/kernel/perf_event.c index c75925c4d1e2..8e81a9860a0d 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -145,8 +145,8 @@ static struct srcu_struct pmus_srcu; */ int sysctl_perf_event_paranoid __read_mostly = 1; -/* Minimum for 128 pages + 1 for the user control page */ -int sysctl_perf_event_mlock __read_mostly = 516; /* 'free' kb per user */ +/* Minimum for 512 kiB + 1 user control page */ +int sysctl_perf_event_mlock __read_mostly = 512 + (PAGE_SIZE / 1024); /* 'free' kiB per user */ /* * max perf event sample rate @@ -364,6 +364,7 @@ void perf_cgroup_switch(struct task_struct *task, int mode) } if (mode & PERF_CGROUP_SWIN) { + WARN_ON_ONCE(cpuctx->cgrp); /* set cgrp before ctxsw in to * allow event_filter_match() to not * have to pass task around @@ -2423,6 +2424,14 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx) if (!ctx || !ctx->nr_events) goto out; + /* + * We must ctxsw out cgroup events to avoid conflict + * when invoking perf_task_event_sched_in() later on + * in this function. Otherwise we end up trying to + * ctxswin cgroup events which are already scheduled + * in. + */ + perf_cgroup_sched_out(current); task_ctx_sched_out(ctx, EVENT_ALL); raw_spin_lock(&ctx->lock); @@ -2447,6 +2456,9 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx) raw_spin_unlock(&ctx->lock); + /* + * Also calls ctxswin for cgroup events, if any: + */ perf_event_context_sched_in(ctx, ctx->task); out: local_irq_restore(flags); @@ -6531,6 +6543,11 @@ SYSCALL_DEFINE5(perf_event_open, goto err_alloc; } + if (task) { + put_task_struct(task); + task = NULL; + } + /* * Look up the group leader (we will attach this event to it): */ diff --git a/kernel/pid.c b/kernel/pid.c index 02f221274265..57a8346a270e 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -217,11 +217,14 @@ static int alloc_pidmap(struct pid_namespace *pid_ns) return -1; } -int next_pidmap(struct pid_namespace *pid_ns, int last) +int next_pidmap(struct pid_namespace *pid_ns, unsigned int last) { int offset; struct pidmap *map, *end; + if (last >= PID_MAX_LIMIT) + return -1; + offset = (last + 1) & BITS_PER_PAGE_MASK; map = &pid_ns->pidmap[(last + 1)/BITS_PER_PAGE]; end = &pid_ns->pidmap[PIDMAP_ENTRIES]; diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 67fea9d25d55..0791b13df7bf 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -1347,7 +1347,7 @@ void run_posix_cpu_timers(struct task_struct *tsk) /* * Now that all the timers on our list have the firing flag, - * noone will touch their list entries but us. We'll take + * no one will touch their list entries but us. We'll take * each timer's lock before clearing its firing flag, so no * timer call will interfere. */ diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index 4c0124919f9a..e5498d7405c3 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -313,7 +313,7 @@ static void schedule_next_timer(struct k_itimer *timr) * restarted (i.e. we have flagged this in the sys_private entry of the * info block). * - * To protect aginst the timer going away while the interrupt is queued, + * To protect against the timer going away while the interrupt is queued, * we require that the it_requeue_pending flag be set. */ void do_schedule_next_timer(struct siginfo *info) diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 4603f08dc47b..6de9a8fc3417 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -18,9 +18,13 @@ config SUSPEND_FREEZER Turning OFF this setting is NOT recommended! If in doubt, say Y. +config HIBERNATE_CALLBACKS + bool + config HIBERNATION bool "Hibernation (aka 'suspend to disk')" depends on SWAP && ARCH_HIBERNATION_POSSIBLE + select HIBERNATE_CALLBACKS select LZO_COMPRESS select LZO_DECOMPRESS ---help--- @@ -85,7 +89,7 @@ config PM_STD_PARTITION config PM_SLEEP def_bool y - depends on SUSPEND || HIBERNATION || XEN_SAVE_RESTORE + depends on SUSPEND || HIBERNATE_CALLBACKS config PM_SLEEP_SMP def_bool y diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index aeabd26e3342..50aae660174d 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -273,8 +273,11 @@ static int create_image(int platform_mode) local_irq_disable(); error = sysdev_suspend(PMSG_FREEZE); - if (!error) + if (!error) { error = syscore_suspend(); + if (error) + sysdev_resume(); + } if (error) { printk(KERN_ERR "PM: Some system devices failed to power down, " "aborting hibernation\n"); @@ -407,8 +410,11 @@ static int resume_target_kernel(bool platform_mode) local_irq_disable(); error = sysdev_suspend(PMSG_QUIESCE); - if (!error) + if (!error) { error = syscore_suspend(); + if (error) + sysdev_resume(); + } if (error) goto Enable_irqs; diff --git a/kernel/power/main.c b/kernel/power/main.c index 8eaba5f27b10..de9aef8742f4 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -224,7 +224,7 @@ power_attr(state); * writing to 'state'. It first should read from 'wakeup_count' and store * the read value. Then, after carrying out its own preparations for the system * transition to a sleep state, it should write the stored value to - * 'wakeup_count'. If that fails, at least one wakeup event has occured since + * 'wakeup_count'. If that fails, at least one wakeup event has occurred since * 'wakeup_count' was read and 'state' should not be written to. Otherwise, it * is allowed to write to 'state', but the transition will be aborted if there * are any wakeup events detected after 'wakeup_count' was written to. diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 2814c32aed51..8935369d503a 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -164,8 +164,11 @@ static int suspend_enter(suspend_state_t state) BUG_ON(!irqs_disabled()); error = sysdev_suspend(PMSG_SUSPEND); - if (!error) + if (!error) { error = syscore_suspend(); + if (error) + sysdev_resume(); + } if (!error) { if (!(suspend_test(TEST_CORE) || pm_wakeup_pending())) { error = suspend_ops->enter(state); diff --git a/kernel/sched.c b/kernel/sched.c index f592ce6f8616..312f8b95c2d4 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2309,7 +2309,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) * Cause a process which is running on another CPU to enter * kernel-mode, without any delay. (to get signals handled.) * - * NOTE: this function doesnt have to take the runqueue lock, + * NOTE: this function doesn't have to take the runqueue lock, * because all it wants to ensure is that the remote task enters * the kernel. If the IPI races and the task has been migrated * to another CPU then no harm is done and the purpose has been @@ -4111,20 +4111,20 @@ need_resched: try_to_wake_up_local(to_wakeup); } deactivate_task(rq, prev, DEQUEUE_SLEEP); + + /* + * If we are going to sleep and we have plugged IO queued, make + * sure to submit it to avoid deadlocks. + */ + if (blk_needs_flush_plug(prev)) { + raw_spin_unlock(&rq->lock); + blk_schedule_flush_plug(prev); + raw_spin_lock(&rq->lock); + } } switch_count = &prev->nvcsw; } - /* - * If we are going to sleep and we have plugged IO queued, make - * sure to submit it to avoid deadlocks. - */ - if (prev->state != TASK_RUNNING && blk_needs_flush_plug(prev)) { - raw_spin_unlock(&rq->lock); - blk_flush_plug(prev); - raw_spin_lock(&rq->lock); - } - pre_schedule(rq, prev); if (unlikely(!rq->nr_running)) @@ -4997,7 +4997,7 @@ recheck: */ raw_spin_lock_irqsave(&p->pi_lock, flags); /* - * To be able to change p->policy safely, the apropriate + * To be able to change p->policy safely, the appropriate * runqueue lock must be held. */ rq = __task_rq_lock(p); @@ -5011,6 +5011,17 @@ recheck: return -EINVAL; } + /* + * If not changing anything there's no need to proceed further: + */ + if (unlikely(policy == p->policy && (!rt_policy(policy) || + param->sched_priority == p->rt_priority))) { + + __task_rq_unlock(rq); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + return 0; + } + #ifdef CONFIG_RT_GROUP_SCHED if (user) { /* @@ -5705,7 +5716,7 @@ void show_state_filter(unsigned long state_filter) do_each_thread(g, p) { /* * reset the NMI-timeout, listing all files on a slow - * console might take alot of time: + * console might take a lot of time: */ touch_nmi_watchdog(); if (!state_filter || (p->state & state_filter)) @@ -6320,6 +6331,9 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) break; #endif } + + update_max_interval(); + return NOTIFY_OK; } diff --git a/kernel/sched_autogroup.c b/kernel/sched_autogroup.c index 5946ac515602..429242f3c484 100644 --- a/kernel/sched_autogroup.c +++ b/kernel/sched_autogroup.c @@ -179,7 +179,7 @@ void sched_autogroup_create_attach(struct task_struct *p) struct autogroup *ag = autogroup_create(); autogroup_move_group(p, ag); - /* drop extra refrence added by autogroup_create() */ + /* drop extra reference added by autogroup_create() */ autogroup_kref_put(ag); } EXPORT_SYMBOL(sched_autogroup_create_attach); diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 3f7ec9e27ee1..6fa833ab2cb8 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -22,6 +22,7 @@ #include <linux/latencytop.h> #include <linux/sched.h> +#include <linux/cpumask.h> /* * Targeted preemption latency for CPU-bound tasks: @@ -2103,21 +2104,20 @@ balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, enum cpu_idle_type idle, int *all_pinned, int *this_best_prio, struct cfs_rq *busiest_cfs_rq) { - int loops = 0, pulled = 0, pinned = 0; + int loops = 0, pulled = 0; long rem_load_move = max_load_move; struct task_struct *p, *n; if (max_load_move == 0) goto out; - pinned = 1; - list_for_each_entry_safe(p, n, &busiest_cfs_rq->tasks, se.group_node) { if (loops++ > sysctl_sched_nr_migrate) break; if ((p->se.load.weight >> 1) > rem_load_move || - !can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) + !can_migrate_task(p, busiest, this_cpu, sd, idle, + all_pinned)) continue; pull_task(busiest, p, this_rq, this_cpu); @@ -2152,9 +2152,6 @@ out: */ schedstat_add(sd, lb_gained[idle], pulled); - if (all_pinned) - *all_pinned = pinned; - return max_load_move - rem_load_move; } @@ -3061,7 +3058,7 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu, /* * if *imbalance is less than the average load per runnable task - * there is no gaurantee that any tasks will be moved so we'll have + * there is no guarantee that any tasks will be moved so we'll have * a think about bumping its value to force at least one task to be * moved */ @@ -3126,6 +3123,8 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, if (!sds.busiest || sds.busiest_nr_running == 0) goto out_balanced; + sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr; + /* * If the busiest group is imbalanced the below checks don't * work because they assumes all things are equal, which typically @@ -3150,7 +3149,6 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, * Don't pull any tasks if this group is already above the domain * average load. */ - sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr; if (sds.this_load >= sds.avg_load) goto out_balanced; @@ -3339,6 +3337,7 @@ redo: * still unbalanced. ld_moved simply stays zero, so it is * correctly treated as an imbalance. */ + all_pinned = 1; local_irq_save(flags); double_rq_lock(this_rq, busiest); ld_moved = move_tasks(this_rq, this_cpu, busiest, @@ -3819,6 +3818,17 @@ void select_nohz_load_balancer(int stop_tick) static DEFINE_SPINLOCK(balancing); +static unsigned long __read_mostly max_load_balance_interval = HZ/10; + +/* + * Scale the max load_balance interval with the number of CPUs in the system. + * This trades load-balance latency on larger machines for less cross talk. + */ +static void update_max_interval(void) +{ + max_load_balance_interval = HZ*num_online_cpus()/10; +} + /* * It checks each scheduling domain to see if it is due to be balanced, * and initiates a balancing operation if so. @@ -3848,10 +3858,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle) /* scale ms to jiffies */ interval = msecs_to_jiffies(interval); - if (unlikely(!interval)) - interval = 1; - if (interval > HZ*NR_CPUS/10) - interval = HZ*NR_CPUS/10; + interval = clamp(interval, 1UL, max_load_balance_interval); need_serialize = sd->flags & SD_SERIALIZE; diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index db308cb08b75..e7cebdc65f82 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -1378,7 +1378,7 @@ retry: task = pick_next_pushable_task(rq); if (task_cpu(next_task) == rq->cpu && task == next_task) { /* - * If we get here, the task hasnt moved at all, but + * If we get here, the task hasn't moved at all, but * it has failed to push. We will not try again, * since the other cpus will pull from us when they * are ready. @@ -1488,7 +1488,7 @@ static int pull_rt_task(struct rq *this_rq) /* * We continue with the search, just in * case there's an even higher prio task - * in another runqueue. (low likelyhood + * in another runqueue. (low likelihood * but possible) */ } diff --git a/kernel/signal.c b/kernel/signal.c index 1186cf7fac77..7165af5f1b11 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -226,7 +226,7 @@ static inline void print_dropped_signal(int sig) /* * allocate a new signal queue record * - this may be called without locks if and only if t == current, otherwise an - * appopriate lock must be held to stop the target task from exiting + * appropriate lock must be held to stop the target task from exiting */ static struct sigqueue * __sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimit) @@ -375,15 +375,15 @@ int unhandled_signal(struct task_struct *tsk, int sig) return !tracehook_consider_fatal_signal(tsk, sig); } - -/* Notify the system that a driver wants to block all signals for this +/* + * Notify the system that a driver wants to block all signals for this * process, and wants to be notified if any signals at all were to be * sent/acted upon. If the notifier routine returns non-zero, then the * signal will be acted upon after all. If the notifier routine returns 0, * then then signal will be blocked. Only one block per process is * allowed. priv is a pointer to private data that the notifier routine - * can use to determine if the signal should be blocked or not. */ - + * can use to determine if the signal should be blocked or not. + */ void block_all_signals(int (*notifier)(void *priv), void *priv, sigset_t *mask) { @@ -434,9 +434,10 @@ still_pending: copy_siginfo(info, &first->info); __sigqueue_free(first); } else { - /* Ok, it wasn't in the queue. This must be - a fast-pathed signal or we must have been - out of queue space. So zero out the info. + /* + * Ok, it wasn't in the queue. This must be + * a fast-pathed signal or we must have been + * out of queue space. So zero out the info. */ info->si_signo = sig; info->si_errno = 0; @@ -468,7 +469,7 @@ static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, } /* - * Dequeue a signal and return the element to the caller, which is + * Dequeue a signal and return the element to the caller, which is * expected to free it. * * All callers have to hold the siglock. @@ -490,7 +491,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) * itimers are process shared and we restart periodic * itimers in the signal delivery path to prevent DoS * attacks in the high resolution timer case. This is - * compliant with the old way of self restarting + * compliant with the old way of self-restarting * itimers, as the SIGALRM is a legacy signal and only * queued once. Changing the restart behaviour to * restart the timer in the signal dequeue path is @@ -923,14 +924,15 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t, if (info == SEND_SIG_FORCED) goto out_set; - /* Real-time signals must be queued if sent by sigqueue, or - some other real-time mechanism. It is implementation - defined whether kill() does so. We attempt to do so, on - the principle of least surprise, but since kill is not - allowed to fail with EAGAIN when low on memory we just - make sure at least one signal gets delivered and don't - pass on the info struct. */ - + /* + * Real-time signals must be queued if sent by sigqueue, or + * some other real-time mechanism. It is implementation + * defined whether kill() does so. We attempt to do so, on + * the principle of least surprise, but since kill is not + * allowed to fail with EAGAIN when low on memory we just + * make sure at least one signal gets delivered and don't + * pass on the info struct. + */ if (sig < SIGRTMIN) override_rlimit = (is_si_special(info) || info->si_code >= 0); else @@ -1201,8 +1203,7 @@ retry: return error; } -int -kill_proc_info(int sig, struct siginfo *info, pid_t pid) +int kill_proc_info(int sig, struct siginfo *info, pid_t pid) { int error; rcu_read_lock(); @@ -1299,8 +1300,7 @@ static int kill_something_info(int sig, struct siginfo *info, pid_t pid) * These are for backward compatibility with the rest of the kernel source. */ -int -send_sig_info(int sig, struct siginfo *info, struct task_struct *p) +int send_sig_info(int sig, struct siginfo *info, struct task_struct *p) { /* * Make sure legacy kernel users don't send in bad values @@ -1368,7 +1368,7 @@ EXPORT_SYMBOL(kill_pid); * These functions support sending signals using preallocated sigqueue * structures. This is needed "because realtime applications cannot * afford to lose notifications of asynchronous events, like timer - * expirations or I/O completions". In the case of Posix Timers + * expirations or I/O completions". In the case of POSIX Timers * we allocate the sigqueue structure from the timer_create. If this * allocation fails we are able to report the failure to the application * with an EAGAIN error. @@ -1553,7 +1553,7 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, int why) info.si_signo = SIGCHLD; info.si_errno = 0; /* - * see comment in do_notify_parent() abot the following 3 lines + * see comment in do_notify_parent() about the following 4 lines */ rcu_read_lock(); info.si_pid = task_pid_nr_ns(tsk, parent->nsproxy->pid_ns); @@ -1611,7 +1611,7 @@ static inline int may_ptrace_stop(void) } /* - * Return nonzero if there is a SIGKILL that should be waking us up. + * Return non-zero if there is a SIGKILL that should be waking us up. * Called with the siglock held. */ static int sigkill_pending(struct task_struct *tsk) @@ -1735,7 +1735,7 @@ void ptrace_notify(int exit_code) /* * This performs the stopping for SIGSTOP and other stop signals. * We have to stop all threads in the thread group. - * Returns nonzero if we've actually stopped and released the siglock. + * Returns non-zero if we've actually stopped and released the siglock. * Returns zero if we didn't stop and still hold the siglock. */ static int do_signal_stop(int signr) @@ -1823,10 +1823,12 @@ static int ptrace_signal(int signr, siginfo_t *info, current->exit_code = 0; - /* Update the siginfo structure if the signal has - changed. If the debugger wanted something - specific in the siginfo structure then it should - have updated *info via PTRACE_SETSIGINFO. */ + /* + * Update the siginfo structure if the signal has + * changed. If the debugger wanted something + * specific in the siginfo structure then it should + * have updated *info via PTRACE_SETSIGINFO. + */ if (signr != info->si_signo) { info->si_signo = signr; info->si_errno = 0; @@ -1885,7 +1887,7 @@ relock: for (;;) { struct k_sigaction *ka; /* - * Tracing can induce an artifical signal and choose sigaction. + * Tracing can induce an artificial signal and choose sigaction. * The return value in @signr determines the default action, * but @info->si_signo is the signal number we will report. */ @@ -2034,7 +2036,8 @@ void exit_signals(struct task_struct *tsk) if (!signal_pending(tsk)) goto out; - /* It could be that __group_complete_signal() choose us to + /* + * It could be that __group_complete_signal() choose us to * notify about group-wide signal. Another thread should be * woken now to take the signal since we will not. */ @@ -2072,6 +2075,9 @@ EXPORT_SYMBOL(unblock_all_signals); * System call entry points. */ +/** + * sys_restart_syscall - restart a system call + */ SYSCALL_DEFINE0(restart_syscall) { struct restart_block *restart = ¤t_thread_info()->restart_block; @@ -2125,6 +2131,13 @@ int sigprocmask(int how, sigset_t *set, sigset_t *oldset) return error; } +/** + * sys_rt_sigprocmask - change the list of currently blocked signals + * @how: whether to add, remove, or set signals + * @set: stores pending signals + * @oset: previous value of signal mask if non-null + * @sigsetsize: size of sigset_t type + */ SYSCALL_DEFINE4(rt_sigprocmask, int, how, sigset_t __user *, set, sigset_t __user *, oset, size_t, sigsetsize) { @@ -2183,8 +2196,14 @@ long do_sigpending(void __user *set, unsigned long sigsetsize) out: return error; -} +} +/** + * sys_rt_sigpending - examine a pending signal that has been raised + * while blocked + * @set: stores pending signals + * @sigsetsize: size of sigset_t type or larger + */ SYSCALL_DEFINE2(rt_sigpending, sigset_t __user *, set, size_t, sigsetsize) { return do_sigpending(set, sigsetsize); @@ -2233,9 +2252,9 @@ int copy_siginfo_to_user(siginfo_t __user *to, siginfo_t *from) err |= __put_user(from->si_trapno, &to->si_trapno); #endif #ifdef BUS_MCEERR_AO - /* + /* * Other callers might not initialize the si_lsb field, - * so check explicitely for the right codes here. + * so check explicitly for the right codes here. */ if (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO) err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb); @@ -2264,6 +2283,14 @@ int copy_siginfo_to_user(siginfo_t __user *to, siginfo_t *from) #endif +/** + * sys_rt_sigtimedwait - synchronously wait for queued signals specified + * in @uthese + * @uthese: queued signals to wait for + * @uinfo: if non-null, the signal's siginfo is returned here + * @uts: upper bound on process time suspension + * @sigsetsize: size of sigset_t type + */ SYSCALL_DEFINE4(rt_sigtimedwait, const sigset_t __user *, uthese, siginfo_t __user *, uinfo, const struct timespec __user *, uts, size_t, sigsetsize) @@ -2280,7 +2307,7 @@ SYSCALL_DEFINE4(rt_sigtimedwait, const sigset_t __user *, uthese, if (copy_from_user(&these, uthese, sizeof(these))) return -EFAULT; - + /* * Invert the set of allowed signals to get those we * want to block. @@ -2305,9 +2332,11 @@ SYSCALL_DEFINE4(rt_sigtimedwait, const sigset_t __user *, uthese, + (ts.tv_sec || ts.tv_nsec)); if (timeout) { - /* None ready -- temporarily unblock those we're + /* + * None ready -- temporarily unblock those we're * interested while we are sleeping in so that we'll - * be awakened when they arrive. */ + * be awakened when they arrive. + */ current->real_blocked = current->blocked; sigandsets(¤t->blocked, ¤t->blocked, &these); recalc_sigpending(); @@ -2339,6 +2368,11 @@ SYSCALL_DEFINE4(rt_sigtimedwait, const sigset_t __user *, uthese, return ret; } +/** + * sys_kill - send a signal to a process + * @pid: the PID of the process + * @sig: signal to be sent + */ SYSCALL_DEFINE2(kill, pid_t, pid, int, sig) { struct siginfo info; @@ -2414,7 +2448,11 @@ SYSCALL_DEFINE3(tgkill, pid_t, tgid, pid_t, pid, int, sig) return do_tkill(tgid, pid, sig); } -/* +/** + * sys_tkill - send signal to one specific task + * @pid: the PID of the task + * @sig: signal to be sent + * * Send a signal to only one task, even if it's a CLONE_THREAD task. */ SYSCALL_DEFINE2(tkill, pid_t, pid, int, sig) @@ -2426,6 +2464,12 @@ SYSCALL_DEFINE2(tkill, pid_t, pid, int, sig) return do_tkill(0, pid, sig); } +/** + * sys_rt_sigqueueinfo - send signal information to a signal + * @pid: the PID of the thread + * @sig: signal to be sent + * @uinfo: signal info to be sent + */ SYSCALL_DEFINE3(rt_sigqueueinfo, pid_t, pid, int, sig, siginfo_t __user *, uinfo) { @@ -2553,12 +2597,11 @@ do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long s error = -EINVAL; /* - * - * Note - this code used to test ss_flags incorrectly + * Note - this code used to test ss_flags incorrectly: * old code may have been written using ss_flags==0 * to mean ss_flags==SS_ONSTACK (as this was the only * way that worked) - this fix preserves that older - * mechanism + * mechanism. */ if (ss_flags != SS_DISABLE && ss_flags != SS_ONSTACK && ss_flags != 0) goto out; @@ -2592,6 +2635,10 @@ out: #ifdef __ARCH_WANT_SYS_SIGPENDING +/** + * sys_sigpending - examine pending signals + * @set: where mask of pending signal is returned + */ SYSCALL_DEFINE1(sigpending, old_sigset_t __user *, set) { return do_sigpending(set, sizeof(*set)); @@ -2600,8 +2647,15 @@ SYSCALL_DEFINE1(sigpending, old_sigset_t __user *, set) #endif #ifdef __ARCH_WANT_SYS_SIGPROCMASK -/* Some platforms have their own version with special arguments others - support only sys_rt_sigprocmask. */ +/** + * sys_sigprocmask - examine and change blocked signals + * @how: whether to add, remove, or set signals + * @set: signals to add or remove (if non-null) + * @oset: previous value of signal mask if non-null + * + * Some platforms have their own version with special arguments; + * others support only sys_rt_sigprocmask. + */ SYSCALL_DEFINE3(sigprocmask, int, how, old_sigset_t __user *, set, old_sigset_t __user *, oset) @@ -2654,6 +2708,13 @@ out: #endif /* __ARCH_WANT_SYS_SIGPROCMASK */ #ifdef __ARCH_WANT_SYS_RT_SIGACTION +/** + * sys_rt_sigaction - alter an action taken by a process + * @sig: signal to be sent + * @act: new sigaction + * @oact: used to save the previous sigaction + * @sigsetsize: size of sigset_t type + */ SYSCALL_DEFINE4(rt_sigaction, int, sig, const struct sigaction __user *, act, struct sigaction __user *, oact, @@ -2740,6 +2801,12 @@ SYSCALL_DEFINE0(pause) #endif #ifdef __ARCH_WANT_SYS_RT_SIGSUSPEND +/** + * sys_rt_sigsuspend - replace the signal mask for a value with the + * @unewset value until a signal is received + * @unewset: new signal mask value + * @sigsetsize: size of sigset_t type + */ SYSCALL_DEFINE2(rt_sigsuspend, sigset_t __user *, unewset, size_t, sigsetsize) { sigset_t newset; diff --git a/kernel/softirq.c b/kernel/softirq.c index 735d87095172..174f976c2874 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -567,7 +567,7 @@ static void __tasklet_hrtimer_trampoline(unsigned long data) /** * tasklet_hrtimer_init - Init a tasklet/hrtimer combo for softirq callbacks * @ttimer: tasklet_hrtimer which is initialized - * @function: hrtimer callback funtion which gets called from softirq context + * @function: hrtimer callback function which gets called from softirq context * @which_clock: clock id (CLOCK_MONOTONIC/CLOCK_REALTIME) * @mode: hrtimer mode (HRTIMER_MODE_ABS/HRTIMER_MODE_REL) */ diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index b2fa506667c0..a470154e0408 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -34,7 +34,7 @@ * inaccuracies caused by missed or lost timer * interrupts and the inability for the timer * interrupt hardware to accuratly tick at the - * requested HZ value. It is also not reccomended + * requested HZ value. It is also not recommended * for "tick-less" systems. */ #define NSEC_PER_JIFFY ((u32)((((u64)NSEC_PER_SEC)<<8)/ACTHZ)) diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 5f1bb8e2008f..f6117a4c7cb8 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -652,6 +652,8 @@ int do_adjtimex(struct timex *txc) struct timespec delta; delta.tv_sec = txc->time.tv_sec; delta.tv_nsec = txc->time.tv_usec; + if (!capable(CAP_SYS_TIME)) + return -EPERM; if (!(txc->modes & ADJ_NANO)) delta.tv_nsec *= 1000; result = timekeeping_inject_offset(&delta); diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c index 25028dd4fa18..c340ca658f37 100644 --- a/kernel/time/posix-clock.c +++ b/kernel/time/posix-clock.c @@ -19,7 +19,6 @@ */ #include <linux/device.h> #include <linux/file.h> -#include <linux/mutex.h> #include <linux/posix-clock.h> #include <linux/slab.h> #include <linux/syscalls.h> @@ -34,19 +33,19 @@ static struct posix_clock *get_posix_clock(struct file *fp) { struct posix_clock *clk = fp->private_data; - mutex_lock(&clk->mutex); + down_read(&clk->rwsem); if (!clk->zombie) return clk; - mutex_unlock(&clk->mutex); + up_read(&clk->rwsem); return NULL; } static void put_posix_clock(struct posix_clock *clk) { - mutex_unlock(&clk->mutex); + up_read(&clk->rwsem); } static ssize_t posix_clock_read(struct file *fp, char __user *buf, @@ -156,7 +155,7 @@ static int posix_clock_open(struct inode *inode, struct file *fp) struct posix_clock *clk = container_of(inode->i_cdev, struct posix_clock, cdev); - mutex_lock(&clk->mutex); + down_read(&clk->rwsem); if (clk->zombie) { err = -ENODEV; @@ -172,7 +171,7 @@ static int posix_clock_open(struct inode *inode, struct file *fp) fp->private_data = clk; } out: - mutex_unlock(&clk->mutex); + up_read(&clk->rwsem); return err; } @@ -211,25 +210,20 @@ int posix_clock_register(struct posix_clock *clk, dev_t devid) int err; kref_init(&clk->kref); - mutex_init(&clk->mutex); + init_rwsem(&clk->rwsem); cdev_init(&clk->cdev, &posix_clock_file_operations); clk->cdev.owner = clk->ops.owner; err = cdev_add(&clk->cdev, devid, 1); - if (err) - goto no_cdev; return err; -no_cdev: - mutex_destroy(&clk->mutex); - return err; } EXPORT_SYMBOL_GPL(posix_clock_register); static void delete_clock(struct kref *kref) { struct posix_clock *clk = container_of(kref, struct posix_clock, kref); - mutex_destroy(&clk->mutex); + if (clk->release) clk->release(clk); } @@ -238,9 +232,9 @@ void posix_clock_unregister(struct posix_clock *clk) { cdev_del(&clk->cdev); - mutex_lock(&clk->mutex); + down_write(&clk->rwsem); clk->zombie = true; - mutex_unlock(&clk->mutex); + up_write(&clk->rwsem); kref_put(&clk->kref, delete_clock); } diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c index 2f3b585b8d7d..a5d0a3a85dd8 100644 --- a/kernel/time/timer_stats.c +++ b/kernel/time/timer_stats.c @@ -236,7 +236,7 @@ void timer_stats_update_stats(void *timer, pid_t pid, void *startf, unsigned int timer_flag) { /* - * It doesnt matter which lock we take: + * It doesn't matter which lock we take: */ raw_spinlock_t *lock; struct entry *entry, input; diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 61d7d59f4a1a..2ad39e556cb4 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -141,7 +141,7 @@ if FTRACE config FUNCTION_TRACER bool "Kernel Function Tracer" depends on HAVE_FUNCTION_TRACER - select FRAME_POINTER if !ARM_UNWIND && !S390 + select FRAME_POINTER if !ARM_UNWIND && !S390 && !MICROBLAZE select KALLSYMS select GENERIC_TRACER select CONTEXT_SWITCH_TRACER diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 7aa40f8e182d..6957aa298dfa 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -850,29 +850,21 @@ static void blk_add_trace_plug(void *ignore, struct request_queue *q) __blk_add_trace(bt, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL); } -static void blk_add_trace_unplug_io(void *ignore, struct request_queue *q) +static void blk_add_trace_unplug(void *ignore, struct request_queue *q, + unsigned int depth, bool explicit) { struct blk_trace *bt = q->blk_trace; if (bt) { - unsigned int pdu = q->rq.count[READ] + q->rq.count[WRITE]; - __be64 rpdu = cpu_to_be64(pdu); + __be64 rpdu = cpu_to_be64(depth); + u32 what; - __blk_add_trace(bt, 0, 0, 0, BLK_TA_UNPLUG_IO, 0, - sizeof(rpdu), &rpdu); - } -} - -static void blk_add_trace_unplug_timer(void *ignore, struct request_queue *q) -{ - struct blk_trace *bt = q->blk_trace; - - if (bt) { - unsigned int pdu = q->rq.count[READ] + q->rq.count[WRITE]; - __be64 rpdu = cpu_to_be64(pdu); + if (explicit) + what = BLK_TA_UNPLUG_IO; + else + what = BLK_TA_UNPLUG_TIMER; - __blk_add_trace(bt, 0, 0, 0, BLK_TA_UNPLUG_TIMER, 0, - sizeof(rpdu), &rpdu); + __blk_add_trace(bt, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu); } } @@ -1015,9 +1007,7 @@ static void blk_register_tracepoints(void) WARN_ON(ret); ret = register_trace_block_plug(blk_add_trace_plug, NULL); WARN_ON(ret); - ret = register_trace_block_unplug_timer(blk_add_trace_unplug_timer, NULL); - WARN_ON(ret); - ret = register_trace_block_unplug_io(blk_add_trace_unplug_io, NULL); + ret = register_trace_block_unplug(blk_add_trace_unplug, NULL); WARN_ON(ret); ret = register_trace_block_split(blk_add_trace_split, NULL); WARN_ON(ret); @@ -1032,8 +1022,7 @@ static void blk_unregister_tracepoints(void) unregister_trace_block_rq_remap(blk_add_trace_rq_remap, NULL); unregister_trace_block_bio_remap(blk_add_trace_bio_remap, NULL); unregister_trace_block_split(blk_add_trace_split, NULL); - unregister_trace_block_unplug_io(blk_add_trace_unplug_io, NULL); - unregister_trace_block_unplug_timer(blk_add_trace_unplug_timer, NULL); + unregister_trace_block_unplug(blk_add_trace_unplug, NULL); unregister_trace_block_plug(blk_add_trace_plug, NULL); unregister_trace_block_sleeprq(blk_add_trace_sleeprq, NULL); unregister_trace_block_getrq(blk_add_trace_getrq, NULL); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index c075f4ea6b94..ee24fa1935ac 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1268,7 +1268,7 @@ static int ftrace_update_code(struct module *mod) p->flags = 0L; /* - * Do the initial record convertion from mcount jump + * Do the initial record conversion from mcount jump * to the NOP instructions. */ if (!ftrace_code_disable(mod, p)) { @@ -3425,7 +3425,7 @@ graph_init_task(struct task_struct *t, struct ftrace_ret_stack *ret_stack) atomic_set(&t->tracing_graph_pause, 0); atomic_set(&t->trace_overrun, 0); t->ftrace_timestamp = 0; - /* make curr_ret_stack visable before we add the ret_stack */ + /* make curr_ret_stack visible before we add the ret_stack */ smp_wmb(); t->ret_stack = ret_stack; } diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index d9c8bcafb120..0ef7b4b2a1f7 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1478,7 +1478,7 @@ static inline unsigned long rb_page_entries(struct buffer_page *bpage) return local_read(&bpage->entries) & RB_WRITE_MASK; } -/* Size is determined by what has been commited */ +/* Size is determined by what has been committed */ static inline unsigned rb_page_size(struct buffer_page *bpage) { return rb_page_commit(bpage); @@ -2932,7 +2932,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) /* * cpu_buffer->pages just needs to point to the buffer, it * has no specific buffer page to point to. Lets move it out - * of our way so we don't accidently swap it. + * of our way so we don't accidentally swap it. */ cpu_buffer->pages = reader->list.prev; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 9541c27c1cf2..d38c16a06a6f 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3239,7 +3239,7 @@ waitagain: trace_seq_init(&iter->seq); /* - * If there was nothing to send to user, inspite of consuming trace + * If there was nothing to send to user, in spite of consuming trace * entries, go back to wait for more entries. */ if (sret == -EBUSY) diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c index 685a67d55db0..6302747a1398 100644 --- a/kernel/trace/trace_clock.c +++ b/kernel/trace/trace_clock.c @@ -46,7 +46,7 @@ u64 notrace trace_clock_local(void) } /* - * trace_clock(): 'inbetween' trace clock. Not completely serialized, + * trace_clock(): 'between' trace clock. Not completely serialized, * but not completely incorrect when crossing CPUs either. * * This is based on cpu_clock(), which will allow at most ~1 jiffy of diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index 1516cb3ec549..e32744c84d94 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -27,7 +27,7 @@ * in the structure. * * * for structures within structures, the format of the internal - * structure is layed out. This allows the internal structure + * structure is laid out. This allows the internal structure * to be deciphered for the format file. Although these macros * may become out of sync with the internal structure, they * will create a compile error if it happens. Since the diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 76b05980225c..962cdb24ed81 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -905,7 +905,7 @@ print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s, * * returns 1 if * - we are inside irq code - * - we just extered irq code + * - we just entered irq code * * retunns 0 if * - funcgraph-interrupts option is set diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 92b6e1e12d98..a4969b47afc1 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -80,7 +80,7 @@ static struct tracer_flags tracer_flags = { * skip the latency if the sequence has changed - some other section * did a maximum and could disturb our measurement with serial console * printouts, etc. Truly coinciding maximum latencies should be rare - * and what happens together happens separately as well, so this doesnt + * and what happens together happens separately as well, so this doesn't * decrease the validity of the maximum found: */ static __cacheline_aligned_in_smp unsigned long max_sequence; diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 8435b43b1782..35d55a386145 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1839,7 +1839,7 @@ static void unregister_probe_event(struct trace_probe *tp) kfree(tp->call.print_fmt); } -/* Make a debugfs interface for controling probe points */ +/* Make a debugfs interface for controlling probe points */ static __init int init_kprobe_trace(void) { struct dentry *d_tracer; diff --git a/kernel/user-return-notifier.c b/kernel/user-return-notifier.c index eb27fd3430a2..92cb706c7fc8 100644 --- a/kernel/user-return-notifier.c +++ b/kernel/user-return-notifier.c @@ -20,7 +20,7 @@ EXPORT_SYMBOL_GPL(user_return_notifier_register); /* * Removes a registered user return notifier. Must be called from atomic - * context, and from the same cpu registration occured in. + * context, and from the same cpu registration occurred in. */ void user_return_notifier_unregister(struct user_return_notifier *urn) { diff --git a/kernel/wait.c b/kernel/wait.c index b0310eb6cc1e..f45ea8d2a1ce 100644 --- a/kernel/wait.c +++ b/kernel/wait.c @@ -142,7 +142,7 @@ EXPORT_SYMBOL(finish_wait); * woken up through the queue. * * This prevents waiter starvation where an exclusive waiter - * aborts and is woken up concurrently and noone wakes up + * aborts and is woken up concurrently and no one wakes up * the next waiter. */ void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait, diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 140dce750450..14733d4d156b 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -430,9 +430,12 @@ static int watchdog_enable(int cpu) p = kthread_create(watchdog, (void *)(unsigned long)cpu, "watchdog/%d", cpu); if (IS_ERR(p)) { printk(KERN_ERR "softlockup watchdog for %i failed\n", cpu); - if (!err) + if (!err) { /* if hardlockup hasn't already set this */ err = PTR_ERR(p); + /* and disable the perf event */ + watchdog_nmi_disable(cpu); + } goto out; } kthread_bind(p, cpu); |