[GIT PULL] scheduler fixes

From: Ingo Molnar
Date: Sun Jan 11 2015 - 03:48:01 EST


Linus,

Please pull the latest sched-urgent-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched-urgent-for-linus

# HEAD: 7f1a169b88f513e32a432ca0f85bfd282d117bd6 sched/fair: Fix RCU stall upon -ENOMEM in sched_create_group()

[ Note: the fs/notify/fanotify/fanotify_user.c fix is an out of
tree fix, found by nested sleep debugging - I hope it's fine to
merge it this way, Al Cc:-ed. ]

Misc fixes: group scheduling corner case fix, two deadline
scheduler fixes, effective_load() overflow fix, nested sleep fix,
6144 CPUs system fix.

Thanks,

Ingo

------------------>
Alex Thorlton (1):
sched: Fix KMALLOC_MAX_SIZE overflow during cpumask allocation

Luca Abeni (2):
sched/deadline: Fix migration of SCHED_DEADLINE tasks
sched/deadline: Avoid double-accounting in case of missed deadlines

Peter Zijlstra (1):
sched, fanotify: Deal with nested sleeps

Tetsuo Handa (1):
sched/fair: Fix RCU stall upon -ENOMEM in sched_create_group()

Yuyang Du (1):
sched: Fix odd values in effective_load() calculations


fs/notify/fanotify/fanotify_user.c | 10 +++++-----
kernel/sched/core.c | 13 +++++--------
kernel/sched/deadline.c | 25 ++++---------------------
kernel/sched/fair.c | 6 +++++-
4 files changed, 19 insertions(+), 35 deletions(-)

diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index c991616acca9..bff8567aa42d 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -259,16 +259,15 @@ static ssize_t fanotify_read(struct file *file, char __user *buf,
struct fsnotify_event *kevent;
char __user *start;
int ret;
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);

start = buf;
group = file->private_data;

pr_debug("%s: group=%p\n", __func__, group);

+ add_wait_queue(&group->notification_waitq, &wait);
while (1) {
- prepare_to_wait(&group->notification_waitq, &wait, TASK_INTERRUPTIBLE);
-
mutex_lock(&group->notification_mutex);
kevent = get_one_event(group, count);
mutex_unlock(&group->notification_mutex);
@@ -289,7 +288,8 @@ static ssize_t fanotify_read(struct file *file, char __user *buf,

if (start != buf)
break;
- schedule();
+
+ wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
continue;
}

@@ -318,8 +318,8 @@ static ssize_t fanotify_read(struct file *file, char __user *buf,
buf += ret;
count -= ret;
}
+ remove_wait_queue(&group->notification_waitq, &wait);

- finish_wait(&group->notification_waitq, &wait);
if (start != buf && ret != -EFAULT)
ret = buf - start;
return ret;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b5797b78add6..c0accc00566e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7113,9 +7113,6 @@ void __init sched_init(void)
#ifdef CONFIG_RT_GROUP_SCHED
alloc_size += 2 * nr_cpu_ids * sizeof(void **);
#endif
-#ifdef CONFIG_CPUMASK_OFFSTACK
- alloc_size += num_possible_cpus() * cpumask_size();
-#endif
if (alloc_size) {
ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT);

@@ -7135,13 +7132,13 @@ void __init sched_init(void)
ptr += nr_cpu_ids * sizeof(void **);

#endif /* CONFIG_RT_GROUP_SCHED */
+ }
#ifdef CONFIG_CPUMASK_OFFSTACK
- for_each_possible_cpu(i) {
- per_cpu(load_balance_mask, i) = (void *)ptr;
- ptr += cpumask_size();
- }
-#endif /* CONFIG_CPUMASK_OFFSTACK */
+ for_each_possible_cpu(i) {
+ per_cpu(load_balance_mask, i) = (cpumask_var_t)kzalloc_node(
+ cpumask_size(), GFP_KERNEL, cpu_to_node(i));
}
+#endif /* CONFIG_CPUMASK_OFFSTACK */

init_rt_bandwidth(&def_rt_bandwidth,
global_rt_period(), global_rt_runtime());
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index e5db8c6feebd..b52092f2636d 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -570,24 +570,7 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se)
static
int dl_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se)
{
- int dmiss = dl_time_before(dl_se->deadline, rq_clock(rq));
- int rorun = dl_se->runtime <= 0;
-
- if (!rorun && !dmiss)
- return 0;
-
- /*
- * If we are beyond our current deadline and we are still
- * executing, then we have already used some of the runtime of
- * the next instance. Thus, if we do not account that, we are
- * stealing bandwidth from the system at each deadline miss!
- */
- if (dmiss) {
- dl_se->runtime = rorun ? dl_se->runtime : 0;
- dl_se->runtime -= rq_clock(rq) - dl_se->deadline;
- }
-
- return 1;
+ return (dl_se->runtime <= 0);
}

extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
@@ -826,10 +809,10 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se,
* parameters of the task might need updating. Otherwise,
* we want a replenishment of its runtime.
*/
- if (!dl_se->dl_new && flags & ENQUEUE_REPLENISH)
- replenish_dl_entity(dl_se, pi_se);
- else
+ if (dl_se->dl_new || flags & ENQUEUE_WAKEUP)
update_dl_entity(dl_se, pi_se);
+ else if (flags & ENQUEUE_REPLENISH)
+ replenish_dl_entity(dl_se, pi_se);

__enqueue_dl_entity(dl_se);
}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index df2cdf77f899..40667cbf371b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4005,6 +4005,10 @@ void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b, bool force)

static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
{
+ /* init_cfs_bandwidth() was not called */
+ if (!cfs_b->throttled_cfs_rq.next)
+ return;
+
hrtimer_cancel(&cfs_b->period_timer);
hrtimer_cancel(&cfs_b->slack_timer);
}
@@ -4424,7 +4428,7 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
* wl = S * s'_i; see (2)
*/
if (W > 0 && w < W)
- wl = (w * tg->shares) / W;
+ wl = (w * (long)tg->shares) / W;
else
wl = tg->shares;

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/