summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/cgroup.c8
-rw-r--r--kernel/exit.c4
-rw-r--r--kernel/fork.c2
-rw-r--r--kernel/futex.c20
-rw-r--r--kernel/irq/spurious.c2
-rw-r--r--kernel/kthread.c23
-rw-r--r--kernel/lockdep.c20
-rw-r--r--kernel/params.c17
-rw-r--r--kernel/perf_event.c68
-rw-r--r--kernel/power/hibernate.c11
-rw-r--r--kernel/power/suspend_test.c5
-rw-r--r--kernel/power/swap.c43
-rw-r--r--kernel/rcutree.c60
-rw-r--r--kernel/rcutree.h17
-rw-r--r--kernel/rcutree_plugin.h46
-rw-r--r--kernel/sched.c78
-rw-r--r--kernel/sched_fair.c74
-rw-r--r--kernel/sys.c25
-rw-r--r--kernel/sysctl_check.c2
-rw-r--r--kernel/trace/ftrace.c8
-rw-r--r--kernel/trace/ring_buffer.c14
-rw-r--r--kernel/trace/trace.c10
-rw-r--r--kernel/trace/trace_events_filter.c3
-rw-r--r--kernel/trace/trace_output.c5
-rw-r--r--kernel/user.c2
-rw-r--r--kernel/workqueue.c35
26 files changed, 399 insertions, 203 deletions
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index ca83b73fba19..0249f4be9b5c 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1710,14 +1710,13 @@ static ssize_t cgroup_write_X64(struct cgroup *cgrp, struct cftype *cft,
return -EFAULT;
buffer[nbytes] = 0; /* nul-terminate */
- strstrip(buffer);
if (cft->write_u64) {
- u64 val = simple_strtoull(buffer, &end, 0);
+ u64 val = simple_strtoull(strstrip(buffer), &end, 0);
if (*end)
return -EINVAL;
retval = cft->write_u64(cgrp, cft, val);
} else {
- s64 val = simple_strtoll(buffer, &end, 0);
+ s64 val = simple_strtoll(strstrip(buffer), &end, 0);
if (*end)
return -EINVAL;
retval = cft->write_s64(cgrp, cft, val);
@@ -1753,8 +1752,7 @@ static ssize_t cgroup_write_string(struct cgroup *cgrp, struct cftype *cft,
}
buffer[nbytes] = 0; /* nul-terminate */
- strstrip(buffer);
- retval = cft->write_string(cgrp, cft, buffer);
+ retval = cft->write_string(cgrp, cft, strstrip(buffer));
if (!retval)
retval = nbytes;
out:
diff --git a/kernel/exit.c b/kernel/exit.c
index e61891f80123..f7864ac2ecc1 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -359,10 +359,8 @@ void __set_special_pids(struct pid *pid)
{
struct task_struct *curr = current->group_leader;
- if (task_session(curr) != pid) {
+ if (task_session(curr) != pid)
change_pid(curr, PIDTYPE_SID, pid);
- proc_sid_connector(curr);
- }
if (task_pgrp(curr) != pid)
change_pid(curr, PIDTYPE_PGID, pid);
diff --git a/kernel/fork.c b/kernel/fork.c
index 4c20fff8c13a..166b8c49257c 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -91,7 +91,7 @@ int nr_processes(void)
int cpu;
int total = 0;
- for_each_online_cpu(cpu)
+ for_each_possible_cpu(cpu)
total += per_cpu(process_counts, cpu);
return total;
diff --git a/kernel/futex.c b/kernel/futex.c
index 4949d336d88d..fb65e822fc41 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -150,7 +150,8 @@ static struct futex_hash_bucket *hash_futex(union futex_key *key)
*/
static inline int match_futex(union futex_key *key1, union futex_key *key2)
{
- return (key1->both.word == key2->both.word
+ return (key1 && key2
+ && key1->both.word == key2->both.word
&& key1->both.ptr == key2->both.ptr
&& key1->both.offset == key2->both.offset);
}
@@ -1028,7 +1029,6 @@ static inline
void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
struct futex_hash_bucket *hb)
{
- drop_futex_key_refs(&q->key);
get_futex_key_refs(key);
q->key = *key;
@@ -1226,6 +1226,7 @@ retry_private:
*/
if (ret == 1) {
WARN_ON(pi_state);
+ drop_count++;
task_count++;
ret = get_futex_value_locked(&curval2, uaddr2);
if (!ret)
@@ -1304,6 +1305,7 @@ retry_private:
if (ret == 1) {
/* We got the lock. */
requeue_pi_wake_futex(this, &key2, hb2);
+ drop_count++;
continue;
} else if (ret) {
/* -EDEADLK */
@@ -1791,6 +1793,7 @@ static int futex_wait(u32 __user *uaddr, int fshared,
current->timer_slack_ns);
}
+retry:
/* Prepare to wait on uaddr. */
ret = futex_wait_setup(uaddr, val, fshared, &q, &hb);
if (ret)
@@ -1808,9 +1811,14 @@ static int futex_wait(u32 __user *uaddr, int fshared,
goto out_put_key;
/*
- * We expect signal_pending(current), but another thread may
- * have handled it for us already.
+ * We expect signal_pending(current), but we might be the
+ * victim of a spurious wakeup as well.
*/
+ if (!signal_pending(current)) {
+ put_futex_key(fshared, &q.key);
+ goto retry;
+ }
+
ret = -ERESTARTSYS;
if (!abs_time)
goto out_put_key;
@@ -2118,9 +2126,11 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
*/
plist_del(&q->list, &q->list.plist);
+ /* Handle spurious wakeups gracefully */
+ ret = -EWOULDBLOCK;
if (timeout && !timeout->task)
ret = -ETIMEDOUT;
- else
+ else if (signal_pending(current))
ret = -ERESTARTNOINTR;
}
return ret;
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 114e704760fe..bd7273e6282e 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -121,7 +121,9 @@ static void poll_all_shared_irqs(void)
if (!(status & IRQ_SPURIOUS_DISABLED))
continue;
+ local_irq_disable();
try_one_irq(i, desc);
+ local_irq_enable();
}
}
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 5fe709982caa..ab7ae57773e1 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -150,29 +150,6 @@ struct task_struct *kthread_create(int (*threadfn)(void *data),
EXPORT_SYMBOL(kthread_create);
/**
- * kthread_bind - bind a just-created kthread to a cpu.
- * @k: thread created by kthread_create().
- * @cpu: cpu (might not be online, must be possible) for @k to run on.
- *
- * Description: This function is equivalent to set_cpus_allowed(),
- * except that @cpu doesn't need to be online, and the thread must be
- * stopped (i.e., just returned from kthread_create()).
- */
-void kthread_bind(struct task_struct *k, unsigned int cpu)
-{
- /* Must have done schedule() in kthread() before we set_task_cpu */
- if (!wait_task_inactive(k, TASK_UNINTERRUPTIBLE)) {
- WARN_ON(1);
- return;
- }
- set_task_cpu(k, cpu);
- k->cpus_allowed = cpumask_of_cpu(cpu);
- k->rt.nr_cpus_allowed = 1;
- k->flags |= PF_THREAD_BOUND;
-}
-EXPORT_SYMBOL(kthread_bind);
-
-/**
* kthread_stop - stop a thread created by kthread_create().
* @k: thread created by kthread_create().
*
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 3815ac1d58b2..9af56723c096 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -142,6 +142,11 @@ static inline struct lock_class *hlock_class(struct held_lock *hlock)
#ifdef CONFIG_LOCK_STAT
static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], lock_stats);
+static inline u64 lockstat_clock(void)
+{
+ return cpu_clock(smp_processor_id());
+}
+
static int lock_point(unsigned long points[], unsigned long ip)
{
int i;
@@ -158,7 +163,7 @@ static int lock_point(unsigned long points[], unsigned long ip)
return i;
}
-static void lock_time_inc(struct lock_time *lt, s64 time)
+static void lock_time_inc(struct lock_time *lt, u64 time)
{
if (time > lt->max)
lt->max = time;
@@ -234,12 +239,12 @@ static void put_lock_stats(struct lock_class_stats *stats)
static void lock_release_holdtime(struct held_lock *hlock)
{
struct lock_class_stats *stats;
- s64 holdtime;
+ u64 holdtime;
if (!lock_stat)
return;
- holdtime = sched_clock() - hlock->holdtime_stamp;
+ holdtime = lockstat_clock() - hlock->holdtime_stamp;
stats = get_lock_stats(hlock_class(hlock));
if (hlock->read)
@@ -2792,7 +2797,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
hlock->references = references;
#ifdef CONFIG_LOCK_STAT
hlock->waittime_stamp = 0;
- hlock->holdtime_stamp = sched_clock();
+ hlock->holdtime_stamp = lockstat_clock();
#endif
if (check == 2 && !mark_irqflags(curr, hlock))
@@ -3322,7 +3327,7 @@ found_it:
if (hlock->instance != lock)
return;
- hlock->waittime_stamp = sched_clock();
+ hlock->waittime_stamp = lockstat_clock();
contention_point = lock_point(hlock_class(hlock)->contention_point, ip);
contending_point = lock_point(hlock_class(hlock)->contending_point,
@@ -3345,8 +3350,7 @@ __lock_acquired(struct lockdep_map *lock, unsigned long ip)
struct held_lock *hlock, *prev_hlock;
struct lock_class_stats *stats;
unsigned int depth;
- u64 now;
- s64 waittime = 0;
+ u64 now, waittime = 0;
int i, cpu;
depth = curr->lockdep_depth;
@@ -3374,7 +3378,7 @@ found_it:
cpu = smp_processor_id();
if (hlock->waittime_stamp) {
- now = sched_clock();
+ now = lockstat_clock();
waittime = now - hlock->waittime_stamp;
hlock->holdtime_stamp = now;
}
diff --git a/kernel/params.c b/kernel/params.c
index 9da58eabdcb2..d656c276508d 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -218,15 +218,11 @@ int param_set_charp(const char *val, struct kernel_param *kp)
return -ENOSPC;
}
- if (kp->flags & KPARAM_KMALLOCED)
- kfree(*(char **)kp->arg);
-
/* This is a hack. We can't need to strdup in early boot, and we
* don't need to; this mangled commandline is preserved. */
if (slab_is_available()) {
- kp->flags |= KPARAM_KMALLOCED;
*(char **)kp->arg = kstrdup(val, GFP_KERNEL);
- if (!kp->arg)
+ if (!*(char **)kp->arg)
return -ENOMEM;
} else
*(const char **)kp->arg = val;
@@ -304,6 +300,7 @@ static int param_array(const char *name,
unsigned int min, unsigned int max,
void *elem, int elemsize,
int (*set)(const char *, struct kernel_param *kp),
+ u16 flags,
unsigned int *num)
{
int ret;
@@ -313,6 +310,7 @@ static int param_array(const char *name,
/* Get the name right for errors. */
kp.name = name;
kp.arg = elem;
+ kp.flags = flags;
/* No equals sign? */
if (!val) {
@@ -358,7 +356,8 @@ int param_array_set(const char *val, struct kernel_param *kp)
unsigned int temp_num;
return param_array(kp->name, val, 1, arr->max, arr->elem,
- arr->elemsize, arr->set, arr->num ?: &temp_num);
+ arr->elemsize, arr->set, kp->flags,
+ arr->num ?: &temp_num);
}
int param_array_get(char *buffer, struct kernel_param *kp)
@@ -605,11 +604,7 @@ void module_param_sysfs_remove(struct module *mod)
void destroy_params(const struct kernel_param *params, unsigned num)
{
- unsigned int i;
-
- for (i = 0; i < num; i++)
- if (params[i].flags & KPARAM_KMALLOCED)
- kfree(*(char **)params[i].arg);
+ /* FIXME: This should free kmalloced charp parameters. It doesn't. */
}
static void __init kernel_add_sysfs_param(const char *name,
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 9d0b5c665883..7f29643c8985 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -1355,7 +1355,7 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx)
u64 interrupts, freq;
spin_lock(&ctx->lock);
- list_for_each_entry(event, &ctx->group_list, group_entry) {
+ list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
if (event->state != PERF_EVENT_STATE_ACTIVE)
continue;
@@ -3959,8 +3959,9 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
regs = task_pt_regs(current);
if (regs) {
- if (perf_event_overflow(event, 0, &data, regs))
- ret = HRTIMER_NORESTART;
+ if (!(event->attr.exclude_idle && current->pid == 0))
+ if (perf_event_overflow(event, 0, &data, regs))
+ ret = HRTIMER_NORESTART;
}
period = max_t(u64, 10000, event->hw.sample_period);
@@ -3969,6 +3970,42 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
return ret;
}
+static void perf_swevent_start_hrtimer(struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ hwc->hrtimer.function = perf_swevent_hrtimer;
+ if (hwc->sample_period) {
+ u64 period;
+
+ if (hwc->remaining) {
+ if (hwc->remaining < 0)
+ period = 10000;
+ else
+ period = hwc->remaining;
+ hwc->remaining = 0;
+ } else {
+ period = max_t(u64, 10000, hwc->sample_period);
+ }
+ __hrtimer_start_range_ns(&hwc->hrtimer,
+ ns_to_ktime(period), 0,
+ HRTIMER_MODE_REL, 0);
+ }
+}
+
+static void perf_swevent_cancel_hrtimer(struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (hwc->sample_period) {
+ ktime_t remaining = hrtimer_get_remaining(&hwc->hrtimer);
+ hwc->remaining = ktime_to_ns(remaining);
+
+ hrtimer_cancel(&hwc->hrtimer);
+ }
+}
+
/*
* Software event: cpu wall time clock
*/
@@ -3991,22 +4028,14 @@ static int cpu_clock_perf_event_enable(struct perf_event *event)
int cpu = raw_smp_processor_id();
atomic64_set(&hwc->prev_count, cpu_clock(cpu));
- hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
- hwc->hrtimer.function = perf_swevent_hrtimer;
- if (hwc->sample_period) {
- u64 period = max_t(u64, 10000, hwc->sample_period);
- __hrtimer_start_range_ns(&hwc->hrtimer,
- ns_to_ktime(period), 0,
- HRTIMER_MODE_REL, 0);
- }
+ perf_swevent_start_hrtimer(event);
return 0;
}
static void cpu_clock_perf_event_disable(struct perf_event *event)
{
- if (event->hw.sample_period)
- hrtimer_cancel(&event->hw.hrtimer);
+ perf_swevent_cancel_hrtimer(event);
cpu_clock_perf_event_update(event);
}
@@ -4043,22 +4072,15 @@ static int task_clock_perf_event_enable(struct perf_event *event)
now = event->ctx->time;
atomic64_set(&hwc->prev_count, now);
- hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
- hwc->hrtimer.function = perf_swevent_hrtimer;
- if (hwc->sample_period) {
- u64 period = max_t(u64, 10000, hwc->sample_period);
- __hrtimer_start_range_ns(&hwc->hrtimer,
- ns_to_ktime(period), 0,
- HRTIMER_MODE_REL, 0);
- }
+
+ perf_swevent_start_hrtimer(event);
return 0;
}
static void task_clock_perf_event_disable(struct perf_event *event)
{
- if (event->hw.sample_period)
- hrtimer_cancel(&event->hw.hrtimer);
+ perf_swevent_cancel_hrtimer(event);
task_clock_perf_event_update(event, event->ctx->time);
}
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 04b3a83d686f..04a9e90d248f 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -693,21 +693,22 @@ static int software_resume(void)
/* The snapshot device should not be opened while we're running */
if (!atomic_add_unless(&snapshot_device_available, -1, 0)) {
error = -EBUSY;
+ swsusp_close(FMODE_READ);
goto Unlock;
}
pm_prepare_console();
error = pm_notifier_call_chain(PM_RESTORE_PREPARE);
if (error)
- goto Finish;
+ goto close_finish;
error = usermodehelper_disable();
if (error)
- goto Finish;
+ goto close_finish;
error = create_basic_memory_bitmaps();
if (error)
- goto Finish;
+ goto close_finish;
pr_debug("PM: Preparing processes for restore.\n");
error = prepare_processes();
@@ -719,6 +720,7 @@ static int software_resume(void)
pr_debug("PM: Reading hibernation image.\n");
error = swsusp_read(&flags);
+ swsusp_close(FMODE_READ);
if (!error)
hibernation_restore(flags & SF_PLATFORM_MODE);
@@ -737,6 +739,9 @@ static int software_resume(void)
mutex_unlock(&pm_mutex);
pr_debug("PM: Resume from disk failed.\n");
return error;
+close_finish:
+ swsusp_close(FMODE_READ);
+ goto Finish;
}
late_initcall(software_resume);
diff --git a/kernel/power/suspend_test.c b/kernel/power/suspend_test.c
index 17d8bb1acf9c..25596e450ac7 100644
--- a/kernel/power/suspend_test.c
+++ b/kernel/power/suspend_test.c
@@ -19,7 +19,7 @@
* The time it takes is system-specific though, so when we test this
* during system bootup we allow a LOT of time.
*/
-#define TEST_SUSPEND_SECONDS 5
+#define TEST_SUSPEND_SECONDS 10
static unsigned long suspend_test_start_time;
@@ -49,7 +49,8 @@ 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(msec > (TEST_SUSPEND_SECONDS * 1000), "Component: %s\n", label);
+ WARN(msec > (TEST_SUSPEND_SECONDS * 1000),
+ "Component: %s, time: %u\n", label, msec);
}
/*
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index b101cdc4df3f..890f6b11b1d3 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -314,7 +314,6 @@ static int save_image(struct swap_map_handle *handle,
{
unsigned int m;
int ret;
- int error = 0;
int nr_pages;
int err2;
struct bio *bio;
@@ -329,26 +328,27 @@ static int save_image(struct swap_map_handle *handle,
nr_pages = 0;
bio = NULL;
do_gettimeofday(&start);
- do {
+ while (1) {
ret = snapshot_read_next(snapshot, PAGE_SIZE);
- if (ret > 0) {
- error = swap_write_page(handle, data_of(*snapshot),
- &bio);
- if (error)
- break;
- if (!(nr_pages % m))
- printk("\b\b\b\b%3d%%", nr_pages / m);
- nr_pages++;
- }
- } while (ret > 0);
+ if (ret <= 0)
+ break;
+ ret = swap_write_page(handle, data_of(*snapshot), &bio);
+ if (ret)
+ break;
+ if (!(nr_pages % m))
+ printk("\b\b\b\b%3d%%", nr_pages / m);
+ nr_pages++;
+ }
err2 = wait_on_bio_chain(&bio);
do_gettimeofday(&stop);
- if (!error)
- error = err2;
- if (!error)
+ if (!ret)
+ ret = err2;
+ if (!ret)
printk("\b\b\b\bdone\n");
+ else
+ printk("\n");
swsusp_show_speed(&start, &stop, nr_to_write, "Wrote");
- return error;
+ return ret;
}
/**
@@ -536,7 +536,8 @@ static int load_image(struct swap_map_handle *handle,
snapshot_write_finalize(snapshot);
if (!snapshot_image_loaded(snapshot))
error = -ENODATA;
- }
+ } else
+ printk("\n");
swsusp_show_speed(&start, &stop, nr_to_read, "Read");
return error;
}
@@ -572,8 +573,6 @@ int swsusp_read(unsigned int *flags_p)
error = load_image(&handle, &snapshot, header->pages - 1);
release_swap_reader(&handle);
- blkdev_put(resume_bdev, FMODE_READ);
-
if (!error)
pr_debug("PM: Image successfully loaded\n");
else
@@ -596,7 +595,7 @@ int swsusp_check(void)
error = bio_read_page(swsusp_resume_block,
swsusp_header, NULL);
if (error)
- return error;
+ goto put;
if (!memcmp(SWSUSP_SIG, swsusp_header->sig, 10)) {
memcpy(swsusp_header->sig, swsusp_header->orig_sig, 10);
@@ -604,8 +603,10 @@ int swsusp_check(void)
error = bio_write_page(swsusp_resume_block,
swsusp_header, NULL);
} else {
- return -EINVAL;
+ error = -EINVAL;
}
+
+put:
if (error)
blkdev_put(resume_bdev, FMODE_READ);
else
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 705f02ac7433..f3077c0ab181 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -59,7 +59,7 @@
NUM_RCU_LVL_2, \
NUM_RCU_LVL_3, /* == MAX_RCU_LVLS */ \
}, \
- .signaled = RCU_SIGNAL_INIT, \
+ .signaled = RCU_GP_IDLE, \
.gpnum = -300, \
.completed = -300, \
.onofflock = __SPIN_LOCK_UNLOCKED(&name.onofflock), \
@@ -657,14 +657,17 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
* irqs disabled.
*/
rcu_for_each_node_breadth_first(rsp, rnp) {
- spin_lock(&rnp->lock); /* irqs already disabled. */
+ spin_lock(&rnp->lock); /* irqs already disabled. */
rcu_preempt_check_blocked_tasks(rnp);
rnp->qsmask = rnp->qsmaskinit;
rnp->gpnum = rsp->gpnum;
- spin_unlock(&rnp->lock); /* irqs already disabled. */
+ spin_unlock(&rnp->lock); /* irqs remain disabled. */
}
+ rnp = rcu_get_root(rsp);
+ spin_lock(&rnp->lock); /* irqs already disabled. */
rsp->signaled = RCU_SIGNAL_INIT; /* force_quiescent_state now OK. */
+ spin_unlock(&rnp->lock); /* irqs remain disabled. */
spin_unlock_irqrestore(&rsp->onofflock, flags);
}
@@ -706,6 +709,7 @@ static void cpu_quiet_msk_finish(struct rcu_state *rsp, unsigned long flags)
{
WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
rsp->completed = rsp->gpnum;
+ rsp->signaled = RCU_GP_IDLE;
rcu_process_gp_end(rsp, rsp->rda[smp_processor_id()]);
rcu_start_gp(rsp, flags); /* releases root node's rnp->lock. */
}
@@ -913,7 +917,20 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp)
spin_unlock(&rnp->lock); /* irqs remain disabled. */
break;
}
- rcu_preempt_offline_tasks(rsp, rnp, rdp);
+
+ /*
+ * If there was a task blocking the current grace period,
+ * and if all CPUs have checked in, we need to propagate
+ * the quiescent state up the rcu_node hierarchy. But that
+ * is inconvenient at the moment due to deadlock issues if
+ * this should end the current grace period. So set the
+ * offlined CPU's bit in ->qsmask in order to force the
+ * next force_quiescent_state() invocation to clean up this
+ * mess in a deadlock-free manner.
+ */
+ if (rcu_preempt_offline_tasks(rsp, rnp, rdp) && !rnp->qsmask)
+ rnp->qsmask |= mask;
+
mask = rnp->grpmask;
spin_unlock(&rnp->lock); /* irqs remain disabled. */
rnp = rnp->parent;
@@ -958,7 +975,7 @@ static void rcu_offline_cpu(int cpu)
* Invoke any RCU callbacks that have made it to the end of their grace
* period. Thottle as specified by rdp->blimit.
*/
-static void rcu_do_batch(struct rcu_data *rdp)
+static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
{
unsigned long flags;
struct rcu_head *next, *list, **tail;
@@ -1011,6 +1028,13 @@ static void rcu_do_batch(struct rcu_data *rdp)
if (rdp->blimit == LONG_MAX && rdp->qlen <= qlowmark)
rdp->blimit = blimit;
+ /* Reset ->qlen_last_fqs_check trigger if enough CBs have drained. */
+ if (rdp->qlen == 0 && rdp->qlen_last_fqs_check != 0) {
+ rdp->qlen_last_fqs_check = 0;
+ rdp->n_force_qs_snap = rsp->n_force_qs;
+ } else if (rdp->qlen < rdp->qlen_last_fqs_check - qhimark)
+ rdp->qlen_last_fqs_check = rdp->qlen;
+
local_irq_restore(flags);
/* Re-raise the RCU softirq if there are callbacks remaining. */
@@ -1142,9 +1166,10 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
}
spin_unlock(&rnp->lock);
switch (signaled) {
+ case RCU_GP_IDLE:
case RCU_GP_INIT:
- break; /* grace period still initializing, ignore. */
+ break; /* grace period idle or initializing, ignore. */
case RCU_SAVE_DYNTICK:
@@ -1158,7 +1183,8 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
/* Update state, record completion counter. */
spin_lock(&rnp->lock);
- if (lastcomp == rsp->completed) {
+ if (lastcomp == rsp->completed &&
+ rsp->signaled == RCU_SAVE_DYNTICK) {
rsp->signaled = RCU_FORCE_QS;
dyntick_record_completed(rsp, lastcomp);
}
@@ -1224,7 +1250,7 @@ __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
}
/* If there are callbacks ready, invoke them. */
- rcu_do_batch(rdp);
+ rcu_do_batch(rsp, rdp);
}
/*
@@ -1288,10 +1314,20 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
rcu_start_gp(rsp, nestflag); /* releases rnp_root->lock. */
}
- /* Force the grace period if too many callbacks or too long waiting. */
- if (unlikely(++rdp->qlen > qhimark)) {
+ /*
+ * Force the grace period if too many callbacks or too long waiting.
+ * Enforce hysteresis, and don't invoke force_quiescent_state()
+ * if some other CPU has recently done so. Also, don't bother
+ * invoking force_quiescent_state() if the newly enqueued callback
+ * is the only one waiting for a grace period to complete.
+ */
+ if (unlikely(++rdp->qlen > rdp->qlen_last_fqs_check + qhimark)) {
rdp->blimit = LONG_MAX;
- force_quiescent_state(rsp, 0);
+ if (rsp->n_force_qs == rdp->n_force_qs_snap &&
+ *rdp->nxttail[RCU_DONE_TAIL] != head)
+ force_quiescent_state(rsp, 0);
+ rdp->n_force_qs_snap = rsp->n_force_qs;
+ rdp->qlen_last_fqs_check = rdp->qlen;
} else if ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0)
force_quiescent_state(rsp, 1);
local_irq_restore(flags);
@@ -1523,6 +1559,8 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptable)
rdp->beenonline = 1; /* We have now been online. */
rdp->preemptable = preemptable;
rdp->passed_quiesc_completed = lastcomp - 1;
+ rdp->qlen_last_fqs_check = 0;
+ rdp->n_force_qs_snap = rsp->n_force_qs;
rdp->blimit = blimit;
spin_unlock(&rnp->lock); /* irqs remain disabled. */
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index b40ac5706040..1899023b0962 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -167,6 +167,10 @@ struct rcu_data {
struct rcu_head *nxtlist;
struct rcu_head **nxttail[RCU_NEXT_SIZE];
long qlen; /* # of queued callbacks */
+ long qlen_last_fqs_check;
+ /* qlen at last check for QS forcing */
+ unsigned long n_force_qs_snap;
+ /* did other CPU force QS recently? */
long blimit; /* Upper limit on a processed batch */
#ifdef CONFIG_NO_HZ
@@ -197,9 +201,10 @@ struct rcu_data {
};
/* Values for signaled field in struct rcu_state. */
-#define RCU_GP_INIT 0 /* Grace period being initialized. */
-#define RCU_SAVE_DYNTICK 1 /* Need to scan dyntick state. */
-#define RCU_FORCE_QS 2 /* Need to force quiescent state. */
+#define RCU_GP_IDLE 0 /* No grace period in progress. */
+#define RCU_GP_INIT 1 /* Grace period being initialized. */
+#define RCU_SAVE_DYNTICK 2 /* Need to scan dyntick state. */
+#define RCU_FORCE_QS 3 /* Need to force quiescent state. */
#ifdef CONFIG_NO_HZ
#define RCU_SIGNAL_INIT RCU_SAVE_DYNTICK
#else /* #ifdef CONFIG_NO_HZ */
@@ -302,9 +307,9 @@ static void rcu_print_task_stall(struct rcu_node *rnp);
#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
#ifdef CONFIG_HOTPLUG_CPU
-static void rcu_preempt_offline_tasks(struct rcu_state *rsp,
- struct rcu_node *rnp,
- struct rcu_data *rdp);
+static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
+ struct rcu_node *rnp,
+ struct rcu_data *rdp);
static void rcu_preempt_offline_cpu(int cpu);
#endif /* #ifdef CONFIG_HOTPLUG_CPU */
static void rcu_preempt_check_callbacks(int cpu);
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index c0cb783aa16a..ef2a58c2b9d5 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -304,21 +304,25 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
* parent is to remove the need for rcu_read_unlock_special() to
* make more than two attempts to acquire the target rcu_node's lock.
*
+ * Returns 1 if there was previously a task blocking the current grace
+ * period on the specified rcu_node structure.
+ *
* The caller must hold rnp->lock with irqs disabled.
*/
-static void rcu_preempt_offline_tasks(struct rcu_state *rsp,
- struct rcu_node *rnp,
- struct rcu_data *rdp)
+static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
+ struct rcu_node *rnp,
+ struct rcu_data *rdp)
{
int i;
struct list_head *lp;
struct list_head *lp_root;
+ int retval = rcu_preempted_readers(rnp);
struct rcu_node *rnp_root = rcu_get_root(rsp);
struct task_struct *tp;
if (rnp == rnp_root) {
WARN_ONCE(1, "Last CPU thought to be offlined?");
- return; /* Shouldn't happen: at least one CPU online. */
+ return 0; /* Shouldn't happen: at least one CPU online. */
}
WARN_ON_ONCE(rnp != rdp->mynode &&
(!list_empty(&rnp->blocked_tasks[0]) ||
@@ -342,6 +346,8 @@ static void rcu_preempt_offline_tasks(struct rcu_state *rsp,
spin_unlock(&rnp_root->lock); /* irqs remain disabled */
}
}
+
+ return retval;
}
/*
@@ -393,6 +399,17 @@ void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
EXPORT_SYMBOL_GPL(call_rcu);
/*
+ * Wait for an rcu-preempt grace period. We are supposed to expedite the
+ * grace period, but this is the crude slow compatability hack, so just
+ * invoke synchronize_rcu().
+ */
+void synchronize_rcu_expedited(void)
+{
+ synchronize_rcu();
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
+
+/*
* Check to see if there is any immediate preemptable-RCU-related work
* to be done.
*/
@@ -521,12 +538,15 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
/*
* Because preemptable RCU does not exist, it never needs to migrate
- * tasks that were blocked within RCU read-side critical sections.
+ * tasks that were blocked within RCU read-side critical sections, and
+ * such non-existent tasks cannot possibly have been blocking the current
+ * grace period.
*/
-static void rcu_preempt_offline_tasks(struct rcu_state *rsp,
- struct rcu_node *rnp,
- struct rcu_data *rdp)
+static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
+ struct rcu_node *rnp,
+ struct rcu_data *rdp)
{
+ return 0;
}
/*
@@ -565,6 +585,16 @@ void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
EXPORT_SYMBOL_GPL(call_rcu);
/*
+ * Wait for an rcu-preempt grace period, but make it happen quickly.
+ * But because preemptable RCU does not exist, map to rcu-sched.
+ */
+void synchronize_rcu_expedited(void)
+{
+ synchronize_sched_expedited();
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
+
+/*
* Because preemptable RCU does not exist, it never has any work to do.
*/
static int rcu_preempt_pending(int cpu)
diff --git a/kernel/sched.c b/kernel/sched.c
index 76c0e9691fc0..3c11ae0a948d 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -309,6 +309,8 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq);
*/
static DEFINE_SPINLOCK(task_group_lock);
+#ifdef CONFIG_FAIR_GROUP_SCHED
+
#ifdef CONFIG_SMP
static int root_task_group_empty(void)
{
@@ -316,7 +318,6 @@ static int root_task_group_empty(void)
}
#endif
-#ifdef CONFIG_FAIR_GROUP_SCHED
#ifdef CONFIG_USER_SCHED
# define INIT_TASK_GROUP_LOAD (2*NICE_0_LOAD)
#else /* !CONFIG_USER_SCHED */
@@ -676,6 +677,7 @@ inline void update_rq_clock(struct rq *rq)
/**
* runqueue_is_locked
+ * @cpu: the processor in question.
*
* Returns true if the current cpu runqueue is locked.
* This interface allows printk to be called with the runqueue lock
@@ -1563,11 +1565,7 @@ static unsigned long cpu_avg_load_per_task(int cpu)
#ifdef CONFIG_FAIR_GROUP_SCHED
-struct update_shares_data {
- unsigned long rq_weight[NR_CPUS];
-};
-
-static DEFINE_PER_CPU(struct update_shares_data, update_shares_data);
+static __read_mostly unsigned long *update_shares_data;
static void __set_se_shares(struct sched_entity *se, unsigned long shares);
@@ -1577,12 +1575,12 @@ static void __set_se_shares(struct sched_entity *se, unsigned long shares);
static void update_group_shares_cpu(struct task_group *tg, int cpu,
unsigned long sd_shares,
unsigned long sd_rq_weight,
- struct update_shares_data *usd)
+ unsigned long *usd_rq_weight)
{
unsigned long shares, rq_weight;
int boost = 0;
- rq_weight = usd->rq_weight[cpu];
+ rq_weight = usd_rq_weight[cpu];
if (!rq_weight) {
boost = 1;
rq_weight = NICE_0_LOAD;
@@ -1617,7 +1615,7 @@ static void update_group_shares_cpu(struct task_group *tg, int cpu,
static int tg_shares_up(struct task_group *tg, void *data)
{
unsigned long weight, rq_weight = 0, shares = 0;
- struct update_shares_data *usd;
+ unsigned long *usd_rq_weight;
struct sched_domain *sd = data;
unsigned long flags;
int i;
@@ -1626,11 +1624,11 @@ static int tg_shares_up(struct task_group *tg, void *data)
return 0;
local_irq_save(flags);
- usd = &__get_cpu_var(update_shares_data);
+ usd_rq_weight = per_cpu_ptr(update_shares_data, smp_processor_id());
for_each_cpu(i, sched_domain_span(sd)) {
weight = tg->cfs_rq[i]->load.weight;
- usd->rq_weight[i] = weight;
+ usd_rq_weight[i] = weight;
/*
* If there are currently no tasks on the cpu pretend there
@@ -1651,7 +1649,7 @@ static int tg_shares_up(struct task_group *tg, void *data)
shares = tg->shares;
for_each_cpu(i, sched_domain_span(sd))
- update_group_shares_cpu(tg, i, shares, rq_weight, usd);
+ update_group_shares_cpu(tg, i, shares, rq_weight, usd_rq_weight);
local_irq_restore(flags);
@@ -1995,6 +1993,38 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
p->sched_class->prio_changed(rq, p, oldprio, running);
}
+/**
+ * kthread_bind - bind a just-created kthread to a cpu.
+ * @p: thread created by kthread_create().
+ * @cpu: cpu (might not be online, must be possible) for @k to run on.
+ *
+ * Description: This function is equivalent to set_cpus_allowed(),
+ * except that @cpu doesn't need to be online, and the thread must be
+ * stopped (i.e., just returned from kthread_create()).
+ *
+ * Function lives here instead of kthread.c because it messes with
+ * scheduler internals which require locking.
+ */
+void kthread_bind(struct task_struct *p, unsigned int cpu)
+{
+ struct rq *rq = cpu_rq(cpu);
+ unsigned long flags;
+
+ /* Must have done schedule() in kthread() before we set_task_cpu */
+ if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE)) {
+ WARN_ON(1);
+ return;
+ }
+
+ spin_lock_irqsave(&rq->lock, flags);
+ set_task_cpu(p, cpu);
+ p->cpus_allowed = cpumask_of_cpu(cpu);
+ p->rt.nr_cpus_allowed = 1;
+ p->flags |= PF_THREAD_BOUND;
+ spin_unlock_irqrestore(&rq->lock, flags);
+}
+EXPORT_SYMBOL(kthread_bind);
+
#ifdef CONFIG_SMP
/*
* Is this task likely cache-hot:
@@ -2007,7 +2037,7 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
/*
* Buddy candidates are cache hot:
*/
- if (sched_feat(CACHE_HOT_BUDDY) &&
+ if (sched_feat(CACHE_HOT_BUDDY) && this_rq()->nr_running &&
(&p->se == cfs_rq_of(&p->se)->next ||
&p->se == cfs_rq_of(&p->se)->last))
return 1;
@@ -2311,7 +2341,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
{
int cpu, orig_cpu, this_cpu, success = 0;
unsigned long flags;
- struct rq *rq;
+ struct rq *rq, *orig_rq;
if (!sched_feat(SYNC_WAKEUPS))
wake_flags &= ~WF_SYNC;
@@ -2319,7 +2349,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
this_cpu = get_cpu();
smp_wmb();
- rq = task_rq_lock(p, &flags);
+ rq = orig_rq = task_rq_lock(p, &flags);
update_rq_clock(rq);
if (!(p->state & state))
goto out;
@@ -2350,6 +2380,10 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
set_task_cpu(p, cpu);
rq = task_rq_lock(p, &flags);
+
+ if (rq != orig_rq)
+ update_rq_clock(rq);
+
WARN_ON(p->state != TASK_WAKING);
cpu = task_cpu(p);
@@ -3656,6 +3690,7 @@ static void update_group_power(struct sched_domain *sd, int cpu)
/**
* update_sg_lb_stats - Update sched_group's statistics for load balancing.
+ * @sd: The sched_domain whose statistics are to be updated.
* @group: sched_group whose statistics are to be updated.
* @this_cpu: Cpu for which load balance is currently performed.
* @idle: Idle status of this_cpu
@@ -6718,9 +6753,6 @@ EXPORT_SYMBOL(yield);
/*
* This task is about to go to sleep on IO. Increment rq->nr_iowait so
* that process accounting knows that this is a task in IO wait state.
- *
- * But don't do that if it is a deliberate, throttling IO wait (this task
- * has set its backing_dev_info: the queue against which it should throttle)
*/
void __sched io_schedule(void)
{
@@ -9404,6 +9436,10 @@ void __init sched_init(void)
#endif /* CONFIG_USER_SCHED */
#endif /* CONFIG_GROUP_SCHED */
+#if defined CONFIG_FAIR_GROUP_SCHED && defined CONFIG_SMP
+ update_shares_data = __alloc_percpu(nr_cpu_ids * sizeof(unsigned long),
+ __alignof__(unsigned long));
+#endif
for_each_possible_cpu(i) {
struct rq *rq;
@@ -9529,13 +9565,13 @@ void __init sched_init(void)
current->sched_class = &fair_sched_class;
/* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */
- alloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT);
+ zalloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT);
#ifdef CONFIG_SMP
#ifdef CONFIG_NO_HZ
- alloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT);
+ zalloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT);
alloc_cpumask_var(&nohz.ilb_grp_nohz_mask, GFP_NOWAIT);
#endif
- alloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
+ zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
#endif /* SMP */
perf_event_init();
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 4e777b47eeda..37087a7fac22 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -822,6 +822,26 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
* re-elected due to buddy favours.
*/
clear_buddies(cfs_rq, curr);
+ return;
+ }
+
+ /*
+ * Ensure that a task that missed wakeup preemption by a
+ * narrow margin doesn't have to wait for a full slice.
+ * This also mitigates buddy induced latencies under load.
+ */
+ if (!sched_feat(WAKEUP_PREEMPT))
+ return;
+
+ if (delta_exec < sysctl_sched_min_granularity)
+ return;
+
+ if (cfs_rq->nr_running > 1) {
+ struct sched_entity *se = __pick_next_entity(cfs_rq);
+ s64 delta = curr->vruntime - se->vruntime;
+
+ if (delta > ideal_runtime)
+ resched_task(rq_of(cfs_rq)->curr);
}
}
@@ -861,12 +881,18 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
{
struct sched_entity *se = __pick_next_entity(cfs_rq);
+ struct sched_entity *left = se;
- if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, se) < 1)
- return cfs_rq->next;
+ if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
+ se = cfs_rq->next;
- if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, se) < 1)
- return cfs_rq->last;
+ /*
+ * Prefer last buddy, try to return the CPU to a preempted task.
+ */
+ if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1)
+ se = cfs_rq->last;
+
+ clear_buddies(cfs_rq, se);
return se;
}
@@ -1568,6 +1594,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
struct sched_entity *se = &curr->se, *pse = &p->se;
struct cfs_rq *cfs_rq = task_cfs_rq(curr);
int sync = wake_flags & WF_SYNC;
+ int scale = cfs_rq->nr_running >= sched_nr_latency;
update_curr(cfs_rq);
@@ -1582,18 +1609,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
if (unlikely(se == pse))
return;
- /*
- * Only set the backward buddy when the current task is still on the
- * rq. This can happen when a wakeup gets interleaved with schedule on
- * the ->pre_schedule() or idle_balance() point, either of which can
- * drop the rq lock.
- *
- * Also, during early boot the idle thread is in the fair class, for
- * obvious reasons its a bad idea to schedule back to the idle thread.
- */
- if (sched_feat(LAST_BUDDY) && likely(se->on_rq && curr != rq->idle))
- set_last_buddy(se);
- if (sched_feat(NEXT_BUDDY) && !(wake_flags & WF_FORK))
+ if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK))
set_next_buddy(pse);
/*
@@ -1639,8 +1655,22 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
BUG_ON(!pse);
- if (wakeup_preempt_entity(se, pse) == 1)
+ if (wakeup_preempt_entity(se, pse) == 1) {
resched_task(curr);
+ /*
+ * Only set the backward buddy when the current task is still
+ * on the rq. This can happen when a wakeup gets interleaved
+ * with schedule on the ->pre_schedule() or idle_balance()
+ * point, either of which can * drop the rq lock.
+ *
+ * Also, during early boot the idle thread is in the fair class,
+ * for obvious reasons its a bad idea to schedule back to it.
+ */
+ if (unlikely(!se->on_rq || curr == rq->idle))
+ return;
+ if (sched_feat(LAST_BUDDY) && scale && entity_is_task(se))
+ set_last_buddy(se);
+ }
}
static struct task_struct *pick_next_task_fair(struct rq *rq)
@@ -1654,16 +1684,6 @@ static struct task_struct *pick_next_task_fair(struct rq *rq)
do {
se = pick_next_entity(cfs_rq);
- /*
- * If se was a buddy, clear it so that it will have to earn
- * the favour again.
- *
- * If se was not a buddy, clear the buddies because neither
- * was elegible to run, let them earn it again.
- *
- * IOW. unconditionally clear buddies.
- */
- __clear_buddies(cfs_rq, NULL);
set_next_entity(cfs_rq, se);
cfs_rq = group_cfs_rq(se);
} while (cfs_rq);
diff --git a/kernel/sys.c b/kernel/sys.c
index 255475d163e0..ce17760d9c51 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1110,6 +1110,8 @@ SYSCALL_DEFINE0(setsid)
err = session;
out:
write_unlock_irq(&tasklist_lock);
+ if (err > 0)
+ proc_sid_connector(group_leader);
return err;
}
@@ -1546,24 +1548,37 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
if (arg4 | arg5)
return -EINVAL;
switch (arg2) {
- case 0:
+ case PR_MCE_KILL_CLEAR:
if (arg3 != 0)
return -EINVAL;
current->flags &= ~PF_MCE_PROCESS;
break;
- case 1:
+ case PR_MCE_KILL_SET:
current->flags |= PF_MCE_PROCESS;
- if (arg3 != 0)
+ if (arg3 == PR_MCE_KILL_EARLY)
current->flags |= PF_MCE_EARLY;
- else
+ else if (arg3 == PR_MCE_KILL_LATE)
current->flags &= ~PF_MCE_EARLY;
+ else if (arg3 == PR_MCE_KILL_DEFAULT)
+ current->flags &=
+ ~(PF_MCE_EARLY|PF_MCE_PROCESS);
+ else
+ return -EINVAL;
break;
default:
return -EINVAL;
}
error = 0;
break;
-
+ case PR_MCE_KILL_GET:
+ if (arg2 | arg3 | arg4 | arg5)
+ return -EINVAL;
+ if (current->flags & PF_MCE_PROCESS)
+ error = (current->flags & PF_MCE_EARLY) ?
+ PR_MCE_KILL_EARLY : PR_MCE_KILL_LATE;
+ else
+ error = PR_MCE_KILL_DEFAULT;
+ break;
default:
error = -EINVAL;
break;
diff --git a/kernel/sysctl_check.c b/kernel/sysctl_check.c
index b38423ca711a..b6e7aaea4604 100644
--- a/kernel/sysctl_check.c
+++ b/kernel/sysctl_check.c
@@ -1521,7 +1521,7 @@ int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table)
if (!table->ctl_name && table->strategy)
set_fail(&fail, table, "Strategy without ctl_name");
#endif
-#ifdef CONFIG_PROC_FS
+#ifdef CONFIG_PROC_SYSCTL
if (table->procname && !table->proc_handler)
set_fail(&fail, table, "No proc_handler");
#endif
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 37ba67e33265..6dc4e5ef7a01 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -740,7 +740,7 @@ ftrace_profile_write(struct file *filp, const char __user *ubuf,
out:
mutex_unlock(&ftrace_profile_lock);
- filp->f_pos += cnt;
+ *ppos += cnt;
return cnt;
}
@@ -2222,15 +2222,15 @@ ftrace_regex_write(struct file *file, const char __user *ubuf,
ret = ftrace_process_regex(parser->buffer,
parser->idx, enable);
if (ret)
- goto out;
+ goto out_unlock;
trace_parser_clear(parser);
}
ret = read;
-
+out_unlock:
mutex_unlock(&ftrace_regex_lock);
-out:
+
return ret;
}
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index d4ff01970547..5dd017fea6f5 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -483,7 +483,7 @@ struct ring_buffer_iter {
/* Up this if you want to test the TIME_EXTENTS and normalization */
#define DEBUG_SHIFT 0
-static inline u64 rb_time_stamp(struct ring_buffer *buffer, int cpu)
+static inline u64 rb_time_stamp(struct ring_buffer *buffer)
{
/* shift to debug/test normalization and TIME_EXTENTS */
return buffer->clock() << DEBUG_SHIFT;
@@ -494,7 +494,7 @@ u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu)
u64 time;
preempt_disable_notrace();
- time = rb_time_stamp(buffer, cpu);
+ time = rb_time_stamp(buffer);
preempt_enable_no_resched_notrace();
return time;
@@ -599,7 +599,7 @@ static struct list_head *rb_list_head(struct list_head *list)
}
/*
- * rb_is_head_page - test if the give page is the head page
+ * rb_is_head_page - test if the given page is the head page
*
* Because the reader may move the head_page pointer, we can
* not trust what the head page is (it may be pointing to
@@ -1193,6 +1193,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
atomic_inc(&cpu_buffer->record_disabled);
synchronize_sched();
+ spin_lock_irq(&cpu_buffer->reader_lock);
rb_head_page_deactivate(cpu_buffer);
for (i = 0; i < nr_pages; i++) {
@@ -1207,6 +1208,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
return;
rb_reset_cpu(cpu_buffer);
+ spin_unlock_irq(&cpu_buffer->reader_lock);
rb_check_pages(cpu_buffer);
@@ -1868,7 +1870,7 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
* Nested commits always have zero deltas, so
* just reread the time stamp
*/
- *ts = rb_time_stamp(buffer, cpu_buffer->cpu);
+ *ts = rb_time_stamp(buffer);
next_page->page->time_stamp = *ts;
}
@@ -2111,7 +2113,7 @@ rb_reserve_next_event(struct ring_buffer *buffer,
if (RB_WARN_ON(cpu_buffer, ++nr_loops > 1000))
goto out_fail;
- ts = rb_time_stamp(cpu_buffer->buffer, cpu_buffer->cpu);
+ ts = rb_time_stamp(cpu_buffer->buffer);
/*
* Only the first commit can update the timestamp.
@@ -2681,7 +2683,7 @@ unsigned long ring_buffer_entries(struct ring_buffer *buffer)
EXPORT_SYMBOL_GPL(ring_buffer_entries);
/**
- * ring_buffer_overrun_cpu - get the number of overruns in buffer
+ * ring_buffer_overruns - get the number of overruns in buffer
* @buffer: The ring buffer
*
* Returns the total number of overruns in the ring buffer
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 45068269ebb1..b20d3ec75de9 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1393,7 +1393,7 @@ int trace_array_vprintk(struct trace_array *tr,
int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
{
- return trace_array_printk(&global_trace, ip, fmt, args);
+ return trace_array_vprintk(&global_trace, ip, fmt, args);
}
EXPORT_SYMBOL_GPL(trace_vprintk);
@@ -2440,7 +2440,7 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf,
return ret;
}
- filp->f_pos += cnt;
+ *ppos += cnt;
return cnt;
}
@@ -2582,7 +2582,7 @@ tracing_ctrl_write(struct file *filp, const char __user *ubuf,
}
mutex_unlock(&trace_types_lock);
- filp->f_pos += cnt;
+ *ppos += cnt;
return cnt;
}
@@ -2764,7 +2764,7 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf,
if (err)
return err;
- filp->f_pos += ret;
+ *ppos += ret;
return ret;
}
@@ -3299,7 +3299,7 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
}
}
- filp->f_pos += cnt;
+ *ppos += cnt;
/* If check pages failed, return ENOMEM */
if (tracing_disabled)
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 23245785927f..98a6cc5c64ed 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -933,8 +933,9 @@ static void postfix_clear(struct filter_parse_state *ps)
while (!list_empty(&ps->postfix)) {
elt = list_first_entry(&ps->postfix, struct postfix_elt, list);
- kfree(elt->operand);
list_del(&elt->list);
+ kfree(elt->operand);
+ kfree(elt);
}
}
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index ed17565826b0..b6c12c6a1bcd 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -69,6 +69,9 @@ enum print_line_t trace_print_printk_msg_only(struct trace_iterator *iter)
* @s: trace sequence descriptor
* @fmt: printf format string
*
+ * It returns 0 if the trace oversizes the buffer's free
+ * space, 1 otherwise.
+ *
* The tracer may use either sequence operations or its own
* copy to user routines. To simplify formating of a trace
* trace_seq_printf is used to store strings into a special
@@ -95,7 +98,7 @@ trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
s->len += ret;
- return len;
+ return 1;
}
EXPORT_SYMBOL_GPL(trace_seq_printf);
diff --git a/kernel/user.c b/kernel/user.c
index 2c000e7132ac..46d0165ca70c 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -330,9 +330,9 @@ done:
*/
static void free_user(struct user_struct *up, unsigned long flags)
{
- spin_unlock_irqrestore(&uidhash_lock, flags);
INIT_DELAYED_WORK(&up->work, cleanup_user_struct);
schedule_delayed_work(&up->work, msecs_to_jiffies(1000));
+ spin_unlock_irqrestore(&uidhash_lock, flags);
}
#else /* CONFIG_USER_SCHED && CONFIG_SYSFS */
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index addfe2df93b1..67e526b6ae81 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -640,6 +640,24 @@ int schedule_delayed_work(struct delayed_work *dwork,
EXPORT_SYMBOL(schedule_delayed_work);
/**
+ * flush_delayed_work - block until a dwork_struct's callback has terminated
+ * @dwork: the delayed work which is to be flushed
+ *
+ * Any timeout is cancelled, and any pending work is run immediately.
+ */
+void flush_delayed_work(struct delayed_work *dwork)
+{
+ if (del_timer_sync(&dwork->timer)) {
+ struct cpu_workqueue_struct *cwq;
+ cwq = wq_per_cpu(keventd_wq, get_cpu());
+ __queue_work(cwq, &dwork->work);
+ put_cpu();
+ }
+ flush_work(&dwork->work);
+}
+EXPORT_SYMBOL(flush_delayed_work);
+
+/**
* schedule_delayed_work_on - queue work in global workqueue on CPU after delay
* @cpu: cpu to use
* @dwork: job to be done
@@ -667,6 +685,7 @@ EXPORT_SYMBOL(schedule_delayed_work_on);
int schedule_on_each_cpu(work_func_t func)
{
int cpu;
+ int orig = -1;
struct work_struct *works;
works = alloc_percpu(struct work_struct);
@@ -674,14 +693,28 @@ int schedule_on_each_cpu(work_func_t func)
return -ENOMEM;
get_online_cpus();
+
+ /*
+ * When running in keventd don't schedule a work item on
+ * itself. Can just call directly because the work queue is
+ * already bound. This also is faster.
+ */
+ if (current_is_keventd())
+ orig = raw_smp_processor_id();
+
for_each_online_cpu(cpu) {
struct work_struct *work = per_cpu_ptr(works, cpu);
INIT_WORK(work, func);
- schedule_work_on(cpu, work);
+ if (cpu != orig)
+ schedule_work_on(cpu, work);
}
+ if (orig >= 0)
+ func(per_cpu_ptr(works, orig));
+
for_each_online_cpu(cpu)
flush_work(per_cpu_ptr(works, cpu));
+
put_online_cpus();
free_percpu(works);
return 0;
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-10 07:28:55 +0000