Merge branch 'perf/urgent' into perf/core

Pick up the latest fixes because upcoming uprobes changes will rely on it.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

14 files changed, 142 insertions, 78 deletions

diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 3a5ca582ba1e..ed206fd88cca 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -250,7 +250,6 @@ static void untag_chunk(struct node *p)
 		spin_unlock(&hash_lock);
 		spin_unlock(&entry->lock);
 		fsnotify_destroy_mark(entry);
-		fsnotify_put_mark(entry);
 		goto out;
 	}
 
@@ -259,7 +258,7 @@ static void untag_chunk(struct node *p)
 
 	fsnotify_duplicate_mark(&new->mark, entry);
 	if (fsnotify_add_mark(&new->mark, new->mark.group, new->mark.i.inode, NULL, 1)) {
-		free_chunk(new);
+		fsnotify_put_mark(&new->mark);
 		goto Fallback;
 	}
 
@@ -293,7 +292,7 @@ static void untag_chunk(struct node *p)
 	spin_unlock(&hash_lock);
 	spin_unlock(&entry->lock);
 	fsnotify_destroy_mark(entry);
-	fsnotify_put_mark(entry);
+	fsnotify_put_mark(&new->mark);	/* drop initial reference */
 	goto out;
 
 Fallback:
@@ -322,7 +321,7 @@ static int create_chunk(struct inode *inode, struct audit_tree *tree)
 
 	entry = &chunk->mark;
 	if (fsnotify_add_mark(entry, audit_tree_group, inode, NULL, 0)) {
-		free_chunk(chunk);
+		fsnotify_put_mark(entry);
 		return -ENOSPC;
 	}
 
@@ -347,6 +346,7 @@ static int create_chunk(struct inode *inode, struct audit_tree *tree)
 	insert_hash(chunk);
 	spin_unlock(&hash_lock);
 	spin_unlock(&entry->lock);
+	fsnotify_put_mark(entry);	/* drop initial reference */
 	return 0;
 }
 
@@ -396,7 +396,7 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree)
 	fsnotify_duplicate_mark(chunk_entry, old_entry);
 	if (fsnotify_add_mark(chunk_entry, chunk_entry->group, chunk_entry->i.inode, NULL, 1)) {
 		spin_unlock(&old_entry->lock);
-		free_chunk(chunk);
+		fsnotify_put_mark(chunk_entry);
 		fsnotify_put_mark(old_entry);
 		return -ENOSPC;
 	}
@@ -444,8 +444,8 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree)
 	spin_unlock(&chunk_entry->lock);
 	spin_unlock(&old_entry->lock);
 	fsnotify_destroy_mark(old_entry);
+	fsnotify_put_mark(chunk_entry);	/* drop initial reference */
 	fsnotify_put_mark(old_entry); /* pair to fsnotify_find mark_entry */
-	fsnotify_put_mark(old_entry); /* and kill it */
 	return 0;
 }
 
@@ -916,7 +916,12 @@ static void audit_tree_freeing_mark(struct fsnotify_mark *entry, struct fsnotify
 	struct audit_chunk *chunk = container_of(entry, struct audit_chunk, mark);
 
 	evict_chunk(chunk);
-	fsnotify_put_mark(entry);
+
+	/*
+	 * We are guaranteed to have at least one reference to the mark from
+	 * either the inode or the caller of fsnotify_destroy_mark().
+	 */
+	BUG_ON(atomic_read(&entry->refcnt) < 1);
 }
 
 static bool audit_tree_send_event(struct fsnotify_group *group, struct inode *inode,
diff --git a/kernel/fork.c b/kernel/fork.c
index 3bd2280d79f6..2c8857e12855 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -455,8 +455,8 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 		if (retval)
 			goto out;
 
-		if (file && uprobe_mmap(tmp))
-			goto out;
+		if (file)
+			uprobe_mmap(tmp);
 	}
 	/* a new mm has just been created */
 	arch_dup_mmap(oldmm, mm);
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 1da39ea248fd..c8b7446b27df 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -178,9 +178,6 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 	arch_suspend_enable_irqs();
 	BUG_ON(irqs_disabled());
 
-	/* Kick the lockup detector */
-	lockup_detector_bootcpu_resume();
-
  Enable_cpus:
 	enable_nonboot_cpus();
 
diff --git a/kernel/printk.c b/kernel/printk.c
index 6a76ab9d4476..66a2ea37b576 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -1034,6 +1034,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
 			struct log *msg = log_from_idx(idx);
 
 			len += msg_print_text(msg, prev, true, NULL, 0);
+			prev = msg->flags;
 			idx = log_next(idx);
 			seq++;
 		}
@@ -1046,6 +1047,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
 			struct log *msg = log_from_idx(idx);
 
 			len -= msg_print_text(msg, prev, true, NULL, 0);
+			prev = msg->flags;
 			idx = log_next(idx);
 			seq++;
 		}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 82ad284f823b..fbf1fd098dc6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3142,6 +3142,20 @@ void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
 # define nsecs_to_cputime(__nsecs)	nsecs_to_jiffies(__nsecs)
 #endif
 
+static cputime_t scale_utime(cputime_t utime, cputime_t rtime, cputime_t total)
+{
+	u64 temp = (__force u64) rtime;
+
+	temp *= (__force u64) utime;
+
+	if (sizeof(cputime_t) == 4)
+		temp = div_u64(temp, (__force u32) total);
+	else
+		temp = div64_u64(temp, (__force u64) total);
+
+	return (__force cputime_t) temp;
+}
+
 void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
 {
 	cputime_t rtime, utime = p->utime, total = utime + p->stime;
@@ -3151,13 +3165,9 @@ void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
 	 */
 	rtime = nsecs_to_cputime(p->se.sum_exec_runtime);
 
-	if (total) {
-		u64 temp = (__force u64) rtime;
-
-		temp *= (__force u64) utime;
-		do_div(temp, (__force u32) total);
-		utime = (__force cputime_t) temp;
-	} else
+	if (total)
+		utime = scale_utime(utime, rtime, total);
+	else
 		utime = rtime;
 
 	/*
@@ -3184,13 +3194,9 @@ void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
 	total = cputime.utime + cputime.stime;
 	rtime = nsecs_to_cputime(cputime.sum_exec_runtime);
 
-	if (total) {
-		u64 temp = (__force u64) rtime;
-
-		temp *= (__force u64) cputime.utime;
-		do_div(temp, (__force u32) total);
-		utime = (__force cputime_t) temp;
-	} else
+	if (total)
+		utime = scale_utime(cputime.utime, rtime, total);
+	else
 		utime = rtime;
 
 	sig->prev_utime = max(sig->prev_utime, utime);
@@ -7246,6 +7252,7 @@ int in_sched_functions(unsigned long addr)
 
 #ifdef CONFIG_CGROUP_SCHED
 struct task_group root_task_group;
+LIST_HEAD(task_groups);
 #endif
 
 DECLARE_PER_CPU(cpumask_var_t, load_balance_tmpmask);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d0cc03b3e70b..c219bf8d704c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3387,6 +3387,14 @@ static int tg_load_down(struct task_group *tg, void *data)
 
 static void update_h_load(long cpu)
 {
+	struct rq *rq = cpu_rq(cpu);
+	unsigned long now = jiffies;
+
+	if (rq->h_load_throttle == now)
+		return;
+
+	rq->h_load_throttle = now;
+
 	rcu_read_lock();
 	walk_tg_tree(tg_load_down, tg_nop, (void *)cpu);
 	rcu_read_unlock();
@@ -4293,11 +4301,10 @@ redo:
 		env.src_rq    = busiest;
 		env.loop_max  = min(sysctl_sched_nr_migrate, busiest->nr_running);
 
+		update_h_load(env.src_cpu);
 more_balance:
 		local_irq_save(flags);
 		double_rq_lock(this_rq, busiest);
-		if (!env.loop)
-			update_h_load(env.src_cpu);
 
 		/*
 		 * cur_ld_moved - load moved in current iteration
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 573e1ca01102..944cb68420e9 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -788,6 +788,19 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 	const struct cpumask *span;
 
 	span = sched_rt_period_mask();
+#ifdef CONFIG_RT_GROUP_SCHED
+	/*
+	 * FIXME: isolated CPUs should really leave the root task group,
+	 * whether they are isolcpus or were isolated via cpusets, lest
+	 * the timer run on a CPU which does not service all runqueues,
+	 * potentially leaving other CPUs indefinitely throttled.  If
+	 * isolation is really required, the user will turn the throttle
+	 * off to kill the perturbations it causes anyway.  Meanwhile,
+	 * this maintains functionality for boot and/or troubleshooting.
+	 */
+	if (rt_b == &root_task_group.rt_bandwidth)
+		span = cpu_online_mask;
+#endif
 	for_each_cpu(i, span) {
 		int enqueue = 0;
 		struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c35a1a7dd4d6..f6714d009e77 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -80,7 +80,7 @@ extern struct mutex sched_domains_mutex;
 struct cfs_rq;
 struct rt_rq;
 
-static LIST_HEAD(task_groups);
+extern struct list_head task_groups;
 
 struct cfs_bandwidth {
 #ifdef CONFIG_CFS_BANDWIDTH
@@ -374,7 +374,11 @@ struct rq {
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	/* list of leaf cfs_rq on this cpu: */
 	struct list_head leaf_cfs_rq_list;
-#endif
+#ifdef CONFIG_SMP
+	unsigned long h_load_throttle;
+#endif /* CONFIG_SMP */
+#endif /* CONFIG_FAIR_GROUP_SCHED */
+
 #ifdef CONFIG_RT_GROUP_SCHED
 	struct list_head leaf_rt_rq_list;
 #endif
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 7b386e86fd23..da5eb5bed84a 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -27,8 +27,10 @@ static struct task_struct *pick_next_task_stop(struct rq *rq)
 {
 	struct task_struct *stop = rq->stop;
 
-	if (stop && stop->on_rq)
+	if (stop && stop->on_rq) {
+		stop->se.exec_start = rq->clock_task;
 		return stop;
+	}
 
 	return NULL;
 }
@@ -52,6 +54,21 @@ static void yield_task_stop(struct rq *rq)
 
 static void put_prev_task_stop(struct rq *rq, struct task_struct *prev)
 {
+	struct task_struct *curr = rq->curr;
+	u64 delta_exec;
+
+	delta_exec = rq->clock_task - curr->se.exec_start;
+	if (unlikely((s64)delta_exec < 0))
+		delta_exec = 0;
+
+	schedstat_set(curr->se.statistics.exec_max,
+			max(curr->se.statistics.exec_max, delta_exec));
+
+	curr->se.sum_exec_runtime += delta_exec;
+	account_group_exec_runtime(curr, delta_exec);
+
+	curr->se.exec_start = rq->clock_task;
+	cpuacct_charge(curr, delta_exec);
 }
 
 static void task_tick_stop(struct rq *rq, struct task_struct *curr, int queued)
@@ -60,6 +77,9 @@ static void task_tick_stop(struct rq *rq, struct task_struct *curr, int queued)
 
 static void set_curr_task_stop(struct rq *rq)
 {
+	struct task_struct *stop = rq->stop;
+
+	stop->se.exec_start = rq->clock_task;
 }
 
 static void switched_to_stop(struct rq *rq, struct task_struct *p)
diff --git a/kernel/task_work.c b/kernel/task_work.c
index 91d4e1742a0c..d320d44903bd 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -75,6 +75,7 @@ void task_work_run(void)
 			p = q->next;
 			q->func(q);
 			q = p;
+			cond_resched();
 		}
 	}
 }
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 2988bc819187..0c1485e42be6 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -115,6 +115,7 @@ static void tk_xtime_add(struct timekeeper *tk, const struct timespec *ts)
 {
 	tk->xtime_sec += ts->tv_sec;
 	tk->xtime_nsec += (u64)ts->tv_nsec << tk->shift;
+	tk_normalize_xtime(tk);
 }
 
 static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec wtm)
@@ -276,7 +277,7 @@ static void timekeeping_forward_now(struct timekeeper *tk)
 	tk->xtime_nsec += cycle_delta * tk->mult;
 
 	/* If arch requires, add in gettimeoffset() */
-	tk->xtime_nsec += arch_gettimeoffset() << tk->shift;
+	tk->xtime_nsec += (u64)arch_gettimeoffset() << tk->shift;
 
 	tk_normalize_xtime(tk);
 
@@ -427,7 +428,7 @@ int do_settimeofday(const struct timespec *tv)
 	struct timespec ts_delta, xt;
 	unsigned long flags;
 
-	if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC)
+	if (!timespec_valid(tv))
 		return -EINVAL;
 
 	write_seqlock_irqsave(&tk->lock, flags);
@@ -463,6 +464,8 @@ int timekeeping_inject_offset(struct timespec *ts)
 {
 	struct timekeeper *tk = &timekeeper;
 	unsigned long flags;
+	struct timespec tmp;
+	int ret = 0;
 
 	if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC)
 		return -EINVAL;
@@ -471,10 +474,17 @@ int timekeeping_inject_offset(struct timespec *ts)
 
 	timekeeping_forward_now(tk);
 
+	/* Make sure the proposed value is valid */
+	tmp = timespec_add(tk_xtime(tk),  *ts);
+	if (!timespec_valid(&tmp)) {
+		ret = -EINVAL;
+		goto error;
+	}
 
 	tk_xtime_add(tk, ts);
 	tk_set_wall_to_mono(tk, timespec_sub(tk->wall_to_monotonic, *ts));
 
+error: /* even if we error out, we forwarded the time, so call update */
 	timekeeping_update(tk, true);
 
 	write_sequnlock_irqrestore(&tk->lock, flags);
@@ -482,7 +492,7 @@ int timekeeping_inject_offset(struct timespec *ts)
 	/* signal hrtimers about time change */
 	clock_was_set();
 
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL(timekeeping_inject_offset);
 
@@ -649,7 +659,20 @@ void __init timekeeping_init(void)
 	struct timespec now, boot, tmp;
 
 	read_persistent_clock(&now);
+	if (!timespec_valid(&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(&boot)) {
+		pr_warn("WARNING: Boot clock returned invalid value!\n"
+			"         Check your CMOS/BIOS settings.\n");
+		boot.tv_sec = 0;
+		boot.tv_nsec = 0;
+	}
 
 	seqlock_init(&tk->lock);
 
@@ -923,20 +946,22 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset)
 		if (likely(error <= interval))
 			adj = 1;
 		else
-			adj = timekeeping_bigadjust(tk, error, &interval,
-							&offset);
-	} else if (error < -interval) {
-		/* See comment above, this is just switched for the negative */
-		error >>= 2;
-		if (likely(error >= -interval)) {
-			adj = -1;
-			interval = -interval;
-			offset = -offset;
-		} else
-			adj = timekeeping_bigadjust(tk, error, &interval,
-							&offset);
-	} else
-		return;
+			adj = timekeeping_bigadjust(tk, error, &interval, &offset);
+	} else {
+		if (error < -interval) {
+			/* See comment above, this is just switched for the negative */
+			error >>= 2;
+			if (likely(error >= -interval)) {
+				adj = -1;
+				interval = -interval;
+				offset = -offset;
+			} else {
+				adj = timekeeping_bigadjust(tk, error, &interval, &offset);
+			}
+		} else {
+			goto out_adjust;
+		}
+	}
 
 	if (unlikely(tk->clock->maxadj &&
 		(tk->mult + adj > tk->clock->mult + tk->clock->maxadj))) {
@@ -999,6 +1024,7 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset)
 	tk->xtime_nsec -= offset;
 	tk->ntp_error -= (interval - offset) << tk->ntp_error_shift;
 
+out_adjust:
 	/*
 	 * It may be possible that when we entered this function, xtime_nsec
 	 * was very small.  Further, if we're slightly speeding the clocksource
@@ -1126,6 +1152,10 @@ static void update_wall_time(void)
 	offset = (clock->read(clock) - clock->cycle_last) & clock->mask;
 #endif
 
+	/* Check if there's really nothing to do */
+	if (offset < tk->cycle_interval)
+		goto out;
+
 	/*
 	 * With NO_HZ we may have to accumulate many cycle_intervals
 	 * (think "ticks") worth of time at once. To do this efficiently,
@@ -1158,9 +1188,9 @@ static void update_wall_time(void)
 	* the vsyscall implementations are converted to use xtime_nsec
 	* (shifted nanoseconds), this can be killed.
 	*/
-	remainder = tk->xtime_nsec & ((1 << tk->shift) - 1);
+	remainder = tk->xtime_nsec & ((1ULL << tk->shift) - 1);
 	tk->xtime_nsec -= remainder;
-	tk->xtime_nsec += 1 << tk->shift;
+	tk->xtime_nsec += 1ULL << tk->shift;
 	tk->ntp_error += remainder << tk->ntp_error_shift;
 
 	/*
diff --git a/kernel/timer.c b/kernel/timer.c
index a61c09374eba..8c5e7b908c68 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1407,13 +1407,6 @@ SYSCALL_DEFINE1(alarm, unsigned int, seconds)
 
 #endif
 
-#ifndef __alpha__
-
-/*
- * The Alpha uses getxpid, getxuid, and getxgid instead.  Maybe this
- * should be moved into arch/i386 instead?
- */
-
 /**
  * sys_getpid - return the thread group id of the current process
  *
@@ -1469,8 +1462,6 @@ SYSCALL_DEFINE0(getegid)
 	return from_kgid_munged(current_user_ns(), current_egid());
 }
 
-#endif
-
 static void process_timeout(unsigned long __data)
 {
 	wake_up_process((struct task_struct *)__data);
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 60e4d7875672..6b245f64c8dd 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -506,6 +506,8 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	int size;
 
 	syscall_nr = syscall_get_nr(current, regs);
+	if (syscall_nr < 0)
+		return;
 	if (!test_bit(syscall_nr, enabled_perf_enter_syscalls))
 		return;
 
@@ -580,6 +582,8 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	int size;
 
 	syscall_nr = syscall_get_nr(current, regs);
+	if (syscall_nr < 0)
+		return;
 	if (!test_bit(syscall_nr, enabled_perf_exit_syscalls))
 		return;
 
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 69add8a9da68..4b1dfba70f7c 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -575,7 +575,7 @@ out:
 /*
  * Create/destroy watchdog threads as CPUs come and go:
  */
-static int
+static int __cpuinit
 cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 {
 	int hotcpu = (unsigned long)hcpu;
@@ -610,27 +610,10 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 	return NOTIFY_OK;
 }
 
-static struct notifier_block cpu_nfb = {
+static struct notifier_block __cpuinitdata cpu_nfb = {
 	.notifier_call = cpu_callback
 };
 
-#ifdef CONFIG_SUSPEND
-/*
- * On exit from suspend we force an offline->online transition on the boot CPU
- * so that the PMU state that was lost while in suspended state gets set up
- * properly for the boot CPU.  This information is required for restarting the
- * NMI watchdog.
- */
-void lockup_detector_bootcpu_resume(void)
-{
-	void *cpu = (void *)(long)smp_processor_id();
-
-	cpu_callback(&cpu_nfb, CPU_DEAD_FROZEN, cpu);
-	cpu_callback(&cpu_nfb, CPU_UP_PREPARE_FROZEN, cpu);
-	cpu_callback(&cpu_nfb, CPU_ONLINE_FROZEN, cpu);
-}
-#endif
-
 void __init lockup_detector_init(void)
 {
 	void *cpu = (void *)(long)smp_processor_id();