Merge branch 'linus' into sched/core

Merge reason: pick up the latest fixes.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

kernel/irq/chip.c

@@ -178,7 +178,7 @@ void irq_shutdown(struct irq_desc *desc)
 	desc->depth = 1;
 	if (desc->irq_data.chip->irq_shutdown)
 		desc->irq_data.chip->irq_shutdown(&desc->irq_data);
-	if (desc->irq_data.chip->irq_disable)
+	else if (desc->irq_data.chip->irq_disable)
 		desc->irq_data.chip->irq_disable(&desc->irq_data);
 	else
 		desc->irq_data.chip->irq_mask(&desc->irq_data);

kernel/irq/irqdomain.c

@@ -29,7 +29,11 @@ void irq_domain_add(struct irq_domain *domain)
 	 */
 	for (hwirq = 0; hwirq < domain->nr_irq; hwirq++) {
 		d = irq_get_irq_data(irq_domain_to_irq(domain, hwirq));
-		if (d || d->domain) {
+		if (!d) {
+			WARN(1, "error: assigning domain to non existant irq_desc");
+			return;
+		}
+		if (d->domain) {
 			/* things are broken; just report, don't clean up */
 			WARN(1, "error: irq_desc already assigned to a domain");
 			return;

kernel/posix-cpu-timers.c

@@ -250,7 +250,7 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
 	do {
 		times->utime = cputime_add(times->utime, t->utime);
 		times->stime = cputime_add(times->stime, t->stime);
-		times->sum_exec_runtime += t->se.sum_exec_runtime;
+		times->sum_exec_runtime += task_sched_runtime(t);
 	} while_each_thread(tsk, t);
 out:
 	rcu_read_unlock();
@@ -312,7 +312,8 @@ static int cpu_clock_sample_group(const clockid_t which_clock,
 		cpu->cpu = cputime.utime;
 		break;
 	case CPUCLOCK_SCHED:
-		cpu->sched = thread_group_sched_runtime(p);
+		thread_group_cputime(p, &cputime);
+		cpu->sched = cputime.sum_exec_runtime;
 		break;
 	}
 	return 0;

kernel/ptrace.c

@@ -744,20 +744,17 @@ int ptrace_request(struct task_struct *child, long request,
 			break;
 
 		si = child->last_siginfo;
-		if (unlikely(!si || si->si_code >> 8 != PTRACE_EVENT_STOP))
-			break;
-
-		child->jobctl |= JOBCTL_LISTENING;
-
-		/*
-		 * If NOTIFY is set, it means event happened between start
-		 * of this trap and now.  Trigger re-trap immediately.
-		 */
-		if (child->jobctl & JOBCTL_TRAP_NOTIFY)
-			signal_wake_up(child, true);
-
+		if (likely(si && (si->si_code >> 8) == PTRACE_EVENT_STOP)) {
+			child->jobctl |= JOBCTL_LISTENING;
+			/*
+			 * If NOTIFY is set, it means event happened between
+			 * start of this trap and now.  Trigger re-trap.
+			 */
+			if (child->jobctl & JOBCTL_TRAP_NOTIFY)
+				signal_wake_up(child, true);
+			ret = 0;
+		}
 		unlock_task_sighand(child, &flags);
-		ret = 0;
 		break;
 
 	case PTRACE_DETACH:	 /* detach a process that was attached. */

kernel/resource.c

@@ -419,6 +419,9 @@ static int __find_resource(struct resource *root, struct resource *old,
 		else
 			tmp.end = root->end;
 
+		if (tmp.end < tmp.start)
+			goto next;
+
 		resource_clip(&tmp, constraint->min, constraint->max);
 		arch_remove_reservations(&tmp);
 
@@ -436,8 +439,10 @@ static int __find_resource(struct resource *root, struct resource *old,
 				return 0;
 			}
 		}
-		if (!this)
+
+next:		if (!this || this->end == root->end)
 			break;
+
 		if (this != old)
 			tmp.start = this->end + 1;
 		this = this->sibling;

kernel/sched.c

@@ -3865,30 +3865,6 @@ unsigned long long task_sched_runtime(struct task_struct *p)
 	return ns;
 }
 
-/*
- * Return sum_exec_runtime for the thread group.
- * In case the task is currently running, return the sum plus current's
- * pending runtime that have not been accounted yet.
- *
- * Note that the thread group might have other running tasks as well,
- * so the return value not includes other pending runtime that other
- * running tasks might have.
- */
-unsigned long long thread_group_sched_runtime(struct task_struct *p)
-{
-	struct task_cputime totals;
-	unsigned long flags;
-	struct rq *rq;
-	u64 ns;
-
-	rq = task_rq_lock(p, &flags);
-	thread_group_cputime(p, &totals);
-	ns = totals.sum_exec_runtime + do_task_delta_exec(p, rq);
-	task_rq_unlock(rq, p, &flags);
-
-	return ns;
-}
-
 /*
  * Account user cpu time to a process.
  * @p: the process that the cpu time gets accounted to
@@ -4513,7 +4489,7 @@ static inline void sched_submit_work(struct task_struct *tsk)
 		blk_schedule_flush_plug(tsk);
 }
 
-asmlinkage void schedule(void)
+asmlinkage void __sched schedule(void)
 {
 	struct task_struct *tsk = current;
 

kernel/sched_rt.c

@@ -1031,7 +1031,7 @@ select_task_rq_rt(struct task_struct *p, int sd_flag, int flags)
 	 */
 	if (curr && unlikely(rt_task(curr)) &&
 	    (curr->rt.nr_cpus_allowed < 2 ||
-	     curr->prio < p->prio) &&
+	     curr->prio <= p->prio) &&
 	    (p->rt.nr_cpus_allowed > 1)) {
 		int target = find_lowest_rq(p);
 
@@ -1563,7 +1563,7 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p)
 	    p->rt.nr_cpus_allowed > 1 &&
 	    rt_task(rq->curr) &&
 	    (rq->curr->rt.nr_cpus_allowed < 2 ||
-	     rq->curr->prio < p->prio))
+	     rq->curr->prio <= p->prio))
 		push_rt_tasks(rq);
 }
 

kernel/taskstats.c

@@ -655,6 +655,7 @@ static struct genl_ops taskstats_ops = {
 	.cmd		= TASKSTATS_CMD_GET,
 	.doit		= taskstats_user_cmd,
 	.policy		= taskstats_cmd_get_policy,
+	.flags		= GENL_ADMIN_PERM,
 };
 
 static struct genl_ops cgroupstats_ops = {

kernel/tsacct.c

@@ -78,6 +78,7 @@ void bacct_add_tsk(struct taskstats *stats, struct task_struct *tsk)
 
 #define KB 1024
 #define MB (1024*KB)
+#define KB_MASK (~(KB-1))
 /*
  * fill in extended accounting fields
  */
@@ -95,14 +96,14 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p)
 		stats->hiwater_vm    = get_mm_hiwater_vm(mm)  * PAGE_SIZE / KB;
 		mmput(mm);
 	}
-	stats->read_char	= p->ioac.rchar;
-	stats->write_char	= p->ioac.wchar;
-	stats->read_syscalls	= p->ioac.syscr;
-	stats->write_syscalls	= p->ioac.syscw;
+	stats->read_char	= p->ioac.rchar & KB_MASK;
+	stats->write_char	= p->ioac.wchar & KB_MASK;
+	stats->read_syscalls	= p->ioac.syscr & KB_MASK;
+	stats->write_syscalls	= p->ioac.syscw & KB_MASK;
 #ifdef CONFIG_TASK_IO_ACCOUNTING
-	stats->read_bytes	= p->ioac.read_bytes;
-	stats->write_bytes	= p->ioac.write_bytes;
-	stats->cancelled_write_bytes = p->ioac.cancelled_write_bytes;
+	stats->read_bytes	= p->ioac.read_bytes & KB_MASK;
+	stats->write_bytes	= p->ioac.write_bytes & KB_MASK;
+	stats->cancelled_write_bytes = p->ioac.cancelled_write_bytes & KB_MASK;
 #else
 	stats->read_bytes	= 0;
 	stats->write_bytes	= 0;

kernel/workqueue.c

@@ -2412,8 +2412,13 @@ reflush:
 
 	for_each_cwq_cpu(cpu, wq) {
 		struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
+		bool drained;
 
-		if (!cwq->nr_active && list_empty(&cwq->delayed_works))
+		spin_lock_irq(&cwq->gcwq->lock);
+		drained = !cwq->nr_active && list_empty(&cwq->delayed_works);
+		spin_unlock_irq(&cwq->gcwq->lock);
+
+		if (drained)
 			continue;
 
 		if (++flush_cnt == 10 ||