Linux 3.0.44
diff --git a/kernel/async.c b/kernel/async.c
index cd9dbb9..04f66e3 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -87,6 +87,13 @@
{
struct async_entry *entry;
+ if (!running) { /* just check the entry count */
+ if (atomic_read(&entry_count))
+ return 0; /* smaller than any cookie */
+ else
+ return next_cookie;
+ }
+
if (!list_empty(running)) {
entry = list_first_entry(running,
struct async_entry, list);
@@ -236,9 +243,7 @@
*/
void async_synchronize_full(void)
{
- do {
- async_synchronize_cookie(next_cookie);
- } while (!list_empty(&async_running) || !list_empty(&async_pending));
+ async_synchronize_cookie_domain(next_cookie, NULL);
}
EXPORT_SYMBOL_GPL(async_synchronize_full);
@@ -258,7 +263,7 @@
/**
* async_synchronize_cookie_domain - synchronize asynchronous function calls within a certain domain with cookie checkpointing
* @cookie: async_cookie_t to use as checkpoint
- * @running: running list to synchronize on
+ * @running: running list to synchronize on, NULL indicates all lists
*
* This function waits until all asynchronous function calls for the
* synchronization domain specified by the running list @list submitted
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 32a6151..7b344be 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2969,12 +2969,12 @@
/*
* Called when the last reference to the file is gone.
*/
-static int perf_release(struct inode *inode, struct file *file)
+static void put_event(struct perf_event *event)
{
- struct perf_event *event = file->private_data;
struct task_struct *owner;
- file->private_data = NULL;
+ if (!atomic_long_dec_and_test(&event->refcount))
+ return;
rcu_read_lock();
owner = ACCESS_ONCE(event->owner);
@@ -3009,7 +3009,13 @@
put_task_struct(owner);
}
- return perf_event_release_kernel(event);
+ perf_event_release_kernel(event);
+}
+
+static int perf_release(struct inode *inode, struct file *file)
+{
+ put_event(file->private_data);
+ return 0;
}
u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running)
@@ -3241,7 +3247,7 @@
static const struct file_operations perf_fops;
-static struct perf_event *perf_fget_light(int fd, int *fput_needed)
+static struct file *perf_fget_light(int fd, int *fput_needed)
{
struct file *file;
@@ -3255,7 +3261,7 @@
return ERR_PTR(-EBADF);
}
- return file->private_data;
+ return file;
}
static int perf_event_set_output(struct perf_event *event,
@@ -3287,19 +3293,21 @@
case PERF_EVENT_IOC_SET_OUTPUT:
{
+ struct file *output_file = NULL;
struct perf_event *output_event = NULL;
int fput_needed = 0;
int ret;
if (arg != -1) {
- output_event = perf_fget_light(arg, &fput_needed);
- if (IS_ERR(output_event))
- return PTR_ERR(output_event);
+ output_file = perf_fget_light(arg, &fput_needed);
+ if (IS_ERR(output_file))
+ return PTR_ERR(output_file);
+ output_event = output_file->private_data;
}
ret = perf_event_set_output(event, output_event);
if (output_event)
- fput_light(output_event->filp, fput_needed);
+ fput_light(output_file, fput_needed);
return ret;
}
@@ -6181,6 +6189,7 @@
mutex_init(&event->mmap_mutex);
+ atomic_long_set(&event->refcount, 1);
event->cpu = cpu;
event->attr = *attr;
event->group_leader = group_leader;
@@ -6455,12 +6464,12 @@
return event_fd;
if (group_fd != -1) {
- group_leader = perf_fget_light(group_fd, &fput_needed);
- if (IS_ERR(group_leader)) {
- err = PTR_ERR(group_leader);
+ group_file = perf_fget_light(group_fd, &fput_needed);
+ if (IS_ERR(group_file)) {
+ err = PTR_ERR(group_file);
goto err_fd;
}
- group_file = group_leader->filp;
+ group_leader = group_file->private_data;
if (flags & PERF_FLAG_FD_OUTPUT)
output_event = group_leader;
if (flags & PERF_FLAG_FD_NO_GROUP)
@@ -6594,7 +6603,6 @@
put_ctx(gctx);
}
- event->filp = event_file;
WARN_ON_ONCE(ctx->parent_ctx);
mutex_lock(&ctx->mutex);
@@ -6682,7 +6690,6 @@
goto err_free;
}
- event->filp = NULL;
WARN_ON_ONCE(ctx->parent_ctx);
mutex_lock(&ctx->mutex);
perf_install_in_context(ctx, event, cpu);
@@ -6731,7 +6738,7 @@
* Release the parent event, if this was the last
* reference to it.
*/
- fput(parent_event->filp);
+ put_event(parent_event);
}
static void
@@ -6807,9 +6814,8 @@
*
* __perf_event_exit_task()
* sync_child_event()
- * fput(parent_event->filp)
- * perf_release()
- * mutex_lock(&ctx->mutex)
+ * put_event()
+ * mutex_lock(&ctx->mutex)
*
* But since its the parent context it won't be the same instance.
*/
@@ -6877,7 +6883,7 @@
list_del_init(&event->child_list);
mutex_unlock(&parent->child_mutex);
- fput(parent->filp);
+ put_event(parent);
perf_group_detach(event);
list_del_event(event, ctx);
@@ -6957,6 +6963,12 @@
NULL);
if (IS_ERR(child_event))
return child_event;
+
+ if (!atomic_long_inc_not_zero(&parent_event->refcount)) {
+ free_event(child_event);
+ return NULL;
+ }
+
get_ctx(child_ctx);
/*
@@ -6996,14 +7008,6 @@
raw_spin_unlock_irqrestore(&child_ctx->lock, flags);
/*
- * Get a reference to the parent filp - we will fput it
- * when the child event exits. This is safe to do because
- * we are in the parent and we know that the filp still
- * exists and has a nonzero count:
- */
- atomic_long_inc(&parent_event->filp->f_count);
-
- /*
* Link this into the parent event's child list
*/
WARN_ON_ONCE(parent_event->ctx->parent_ctx);
diff --git a/kernel/exit.c b/kernel/exit.c
index cadcc61..ee862e5 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1051,6 +1051,22 @@
preempt_disable();
exit_rcu();
+
+ /*
+ * The setting of TASK_RUNNING by try_to_wake_up() may be delayed
+ * when the following two conditions become true.
+ * - There is race condition of mmap_sem (It is acquired by
+ * exit_mm()), and
+ * - SMI occurs before setting TASK_RUNINNG.
+ * (or hypervisor of virtual machine switches to other guest)
+ * As a result, we may become TASK_RUNNING after becoming TASK_DEAD
+ *
+ * To avoid it, we have to wait for releasing tsk->pi_lock which
+ * is held by try_to_wake_up()
+ */
+ smp_mb();
+ raw_spin_unlock_wait(&tsk->pi_lock);
+
/* causes final put_task_struct in finish_task_switch(). */
tsk->state = TASK_DEAD;
schedule();
diff --git a/kernel/sched.c b/kernel/sched.c
index cf53b43..485caea 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -606,22 +606,19 @@
/*
* Return the group to which this tasks belongs.
*
- * We use task_subsys_state_check() and extend the RCU verification with
- * pi->lock and rq->lock because cpu_cgroup_attach() holds those locks for each
- * task it moves into the cgroup. Therefore by holding either of those locks,
- * we pin the task to the current cgroup.
+ * We cannot use task_subsys_state() and friends because the cgroup
+ * subsystem changes that value before the cgroup_subsys::attach() method
+ * is called, therefore we cannot pin it and might observe the wrong value.
+ *
+ * The same is true for autogroup's p->signal->autogroup->tg, the autogroup
+ * core changes this before calling sched_move_task().
+ *
+ * Instead we use a 'copy' which is updated from sched_move_task() while
+ * holding both task_struct::pi_lock and rq::lock.
*/
static inline struct task_group *task_group(struct task_struct *p)
{
- struct task_group *tg;
- struct cgroup_subsys_state *css;
-
- css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
- lockdep_is_held(&p->pi_lock) ||
- lockdep_is_held(&task_rq(p)->lock));
- tg = container_of(css, struct task_group, css);
-
- return autogroup_task_group(p, tg);
+ return p->sched_task_group;
}
/* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
@@ -2207,7 +2204,7 @@
* a task's CPU. ->pi_lock for waking tasks, rq->lock for runnable tasks.
*
* sched_move_task() holds both and thus holding either pins the cgroup,
- * see set_task_rq().
+ * see task_group().
*
* Furthermore, all task_rq users should acquire both locks, see
* task_rq_lock().
@@ -8582,6 +8579,7 @@
*/
void sched_move_task(struct task_struct *tsk)
{
+ struct task_group *tg;
int on_rq, running;
unsigned long flags;
struct rq *rq;
@@ -8596,6 +8594,12 @@
if (unlikely(running))
tsk->sched_class->put_prev_task(rq, tsk);
+ tg = container_of(task_subsys_state_check(tsk, cpu_cgroup_subsys_id,
+ lockdep_is_held(&tsk->sighand->siglock)),
+ struct task_group, css);
+ tg = autogroup_task_group(tsk, tg);
+ tsk->sched_task_group = tg;
+
#ifdef CONFIG_FAIR_GROUP_SCHED
if (tsk->sched_class->task_move_group)
tsk->sched_class->task_move_group(tsk, on_rq);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 9d6f66d..10033bc 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -382,7 +382,7 @@
struct timespec ts_delta;
unsigned long flags;
- if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC)
+ if (!timespec_valid_strict(tv))
return -EINVAL;
write_seqlock_irqsave(&xtime_lock, flags);
@@ -417,6 +417,8 @@
int timekeeping_inject_offset(struct timespec *ts)
{
unsigned long flags;
+ struct timespec tmp;
+ int ret = 0;
if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC)
return -EINVAL;
@@ -425,9 +427,16 @@
timekeeping_forward_now();
+ tmp = timespec_add(xtime, *ts);
+ if (!timespec_valid_strict(&tmp)) {
+ ret = -EINVAL;
+ goto error;
+ }
+
xtime = timespec_add(xtime, *ts);
wall_to_monotonic = timespec_sub(wall_to_monotonic, *ts);
+error: /* even if we error out, we forwarded the time, so call update */
timekeeping_update(true);
write_sequnlock_irqrestore(&xtime_lock, flags);
@@ -435,7 +444,7 @@
/* signal hrtimers about time change */
clock_was_set();
- return 0;
+ return ret;
}
EXPORT_SYMBOL(timekeeping_inject_offset);
@@ -582,7 +591,20 @@
struct timespec now, boot;
read_persistent_clock(&now);
+ if (!timespec_valid_strict(&now)) {
+ pr_warn("WARNING: Persistent clock returned invalid value!\n"
+ " Check your CMOS/BIOS settings.\n");
+ now.tv_sec = 0;
+ now.tv_nsec = 0;
+ }
+
read_boot_clock(&boot);
+ if (!timespec_valid_strict(&boot)) {
+ pr_warn("WARNING: Boot clock returned invalid value!\n"
+ " Check your CMOS/BIOS settings.\n");
+ boot.tv_sec = 0;
+ boot.tv_nsec = 0;
+ }
write_seqlock_irqsave(&xtime_lock, flags);
@@ -632,6 +654,7 @@
"sleep delta value!\n");
return;
}
+
xtime = timespec_add(xtime, *delta);
wall_to_monotonic = timespec_sub(wall_to_monotonic, *delta);
update_sleep_time(timespec_add(total_sleep_time, *delta));
@@ -902,6 +925,10 @@
#else
offset = (clock->read(clock) - clock->cycle_last) & clock->mask;
#endif
+ /* Check if there's really nothing to do */
+ if (offset < timekeeper.cycle_interval)
+ return;
+
timekeeper.xtime_nsec = (s64)xtime.tv_nsec << timekeeper.shift;
/*
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index e22a8a8..6029536 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3434,14 +3434,17 @@
for_each_busy_worker(worker, i, pos, gcwq) {
struct work_struct *rebind_work = &worker->rebind_work;
+ unsigned long worker_flags = worker->flags;
/*
* Rebind_work may race with future cpu hotplug
* operations. Use a separate flag to mark that
- * rebinding is scheduled.
+ * rebinding is scheduled. The morphing should
+ * be atomic.
*/
- worker->flags |= WORKER_REBIND;
- worker->flags &= ~WORKER_ROGUE;
+ worker_flags |= WORKER_REBIND;
+ worker_flags &= ~WORKER_ROGUE;
+ ACCESS_ONCE(worker->flags) = worker_flags;
/* queue rebind_work, wq doesn't matter, use the default one */
if (test_and_set_bit(WORK_STRUCT_PENDING_BIT,
@@ -3621,18 +3624,17 @@
#ifdef CONFIG_SMP
struct work_for_cpu {
- struct completion completion;
+ struct work_struct work;
long (*fn)(void *);
void *arg;
long ret;
};
-static int do_work_for_cpu(void *_wfc)
+static void work_for_cpu_fn(struct work_struct *work)
{
- struct work_for_cpu *wfc = _wfc;
+ struct work_for_cpu *wfc = container_of(work, struct work_for_cpu, work);
+
wfc->ret = wfc->fn(wfc->arg);
- complete(&wfc->completion);
- return 0;
}
/**
@@ -3647,19 +3649,11 @@
*/
long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
{
- struct task_struct *sub_thread;
- struct work_for_cpu wfc = {
- .completion = COMPLETION_INITIALIZER_ONSTACK(wfc.completion),
- .fn = fn,
- .arg = arg,
- };
+ struct work_for_cpu wfc = { .fn = fn, .arg = arg };
- sub_thread = kthread_create(do_work_for_cpu, &wfc, "work_for_cpu");
- if (IS_ERR(sub_thread))
- return PTR_ERR(sub_thread);
- kthread_bind(sub_thread, cpu);
- wake_up_process(sub_thread);
- wait_for_completion(&wfc.completion);
+ INIT_WORK_ONSTACK(&wfc.work, work_for_cpu_fn);
+ schedule_work_on(cpu, &wfc.work);
+ flush_work(&wfc.work);
return wfc.ret;
}
EXPORT_SYMBOL_GPL(work_on_cpu);