Merge branch 'linus' into sched/core

Merge reason: branch had an old upstream base (-rc1-ish), but also
              merge to avoid a conflict.

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

25 files changed, 426 insertions, 156 deletions

diff --git a/kernel/acct.c b/kernel/acct.c
index 7afa315..9f33910 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -215,6 +215,7 @@ static void acct_file_reopen(struct bsd_acct_struct *acct, struct file *file,
 static int acct_on(char *name)
 {
 	struct file *file;
+	struct vfsmount *mnt;
 	int error;
 	struct pid_namespace *ns;
 	struct bsd_acct_struct *acct = NULL;
@@ -256,11 +257,12 @@ static int acct_on(char *name)
 		acct = NULL;
 	}
 
-	mnt_pin(file->f_path.mnt);
+	mnt = file->f_path.mnt;
+	mnt_pin(mnt);
 	acct_file_reopen(ns->bacct, file, ns);
 	spin_unlock(&acct_lock);
 
-	mntput(file->f_path.mnt); /* it's pinned, now give up active reference */
+	mntput(mnt); /* it's pinned, now give up active reference */
 	kfree(acct);
 
 	return 0;
diff --git a/kernel/exit.c b/kernel/exit.c
index 628d41f..869dc22 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -12,7 +12,6 @@
 #include <linux/completion.h>
 #include <linux/personality.h>
 #include <linux/tty.h>
-#include <linux/mnt_namespace.h>
 #include <linux/iocontext.h>
 #include <linux/key.h>
 #include <linux/security.h>
diff --git a/kernel/fork.c b/kernel/fork.c
index 467746b..bd29592 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -17,7 +17,6 @@
 #include <linux/module.h>
 #include <linux/vmalloc.h>
 #include <linux/completion.h>
-#include <linux/mnt_namespace.h>
 #include <linux/personality.h>
 #include <linux/mempolicy.h>
 #include <linux/sem.h>
diff --git a/kernel/futex.c b/kernel/futex.c
index 794c862..0672ff8 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -247,6 +247,7 @@ again:
 	if (err < 0)
 		return err;
 
+	page = compound_head(page);
 	lock_page(page);
 	if (!page->mapping) {
 		unlock_page(page);
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 9002958..49da79a 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -191,6 +191,46 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
 	}
 }
 
+
+/*
+ * Get the preferred target CPU for NOHZ
+ */
+static int hrtimer_get_target(int this_cpu, int pinned)
+{
+#ifdef CONFIG_NO_HZ
+	if (!pinned && get_sysctl_timer_migration() && idle_cpu(this_cpu)) {
+		int preferred_cpu = get_nohz_load_balancer();
+
+		if (preferred_cpu >= 0)
+			return preferred_cpu;
+	}
+#endif
+	return this_cpu;
+}
+
+/*
+ * With HIGHRES=y we do not migrate the timer when it is expiring
+ * before the next event on the target cpu because we cannot reprogram
+ * the target cpu hardware and we would cause it to fire late.
+ *
+ * Called with cpu_base->lock of target cpu held.
+ */
+static int
+hrtimer_check_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base)
+{
+#ifdef CONFIG_HIGH_RES_TIMERS
+	ktime_t expires;
+
+	if (!new_base->cpu_base->hres_active)
+		return 0;
+
+	expires = ktime_sub(hrtimer_get_expires(timer), new_base->offset);
+	return expires.tv64 <= new_base->cpu_base->expires_next.tv64;
+#else
+	return 0;
+#endif
+}
+
 /*
  * Switch the timer base to the current CPU when possible.
  */
@@ -200,16 +240,8 @@ switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base,
 {
 	struct hrtimer_clock_base *new_base;
 	struct hrtimer_cpu_base *new_cpu_base;
-	int cpu, preferred_cpu = -1;
-
-	cpu = smp_processor_id();
-#if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP)
-	if (!pinned && get_sysctl_timer_migration() && idle_cpu(cpu)) {
-		preferred_cpu = get_nohz_load_balancer();
-		if (preferred_cpu >= 0)
-			cpu = preferred_cpu;
-	}
-#endif
+	int this_cpu = smp_processor_id();
+	int cpu = hrtimer_get_target(this_cpu, pinned);
 
 again:
 	new_cpu_base = &per_cpu(hrtimer_bases, cpu);
@@ -217,7 +249,7 @@ again:
 
 	if (base != new_base) {
 		/*
-		 * We are trying to schedule the timer on the local CPU.
+		 * We are trying to move timer to new_base.
 		 * However we can't change timer's base while it is running,
 		 * so we keep it on the same CPU. No hassle vs. reprogramming
 		 * the event source in the high resolution case. The softirq
@@ -233,38 +265,12 @@ again:
 		spin_unlock(&base->cpu_base->lock);
 		spin_lock(&new_base->cpu_base->lock);
 
-		/* Optimized away for NOHZ=n SMP=n */
-		if (cpu == preferred_cpu) {
-			/* Calculate clock monotonic expiry time */
-#ifdef CONFIG_HIGH_RES_TIMERS
-			ktime_t expires = ktime_sub(hrtimer_get_expires(timer),
-							new_base->offset);
-#else
-			ktime_t expires = hrtimer_get_expires(timer);
-#endif
-
-			/*
-			 * Get the next event on target cpu from the
-			 * clock events layer.
-			 * This covers the highres=off nohz=on case as well.
-			 */
-			ktime_t next = clockevents_get_next_event(cpu);
-
-			ktime_t delta = ktime_sub(expires, next);
-
-			/*
-			 * We do not migrate the timer when it is expiring
-			 * before the next event on the target cpu because
-			 * we cannot reprogram the target cpu hardware and
-			 * we would cause it to fire late.
-			 */
-			if (delta.tv64 < 0) {
-				cpu = smp_processor_id();
-				spin_unlock(&new_base->cpu_base->lock);
-				spin_lock(&base->cpu_base->lock);
-				timer->base = base;
-				goto again;
-			}
+		if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) {
+			cpu = this_cpu;
+			spin_unlock(&new_base->cpu_base->lock);
+			spin_lock(&base->cpu_base->lock);
+			timer->base = base;
+			goto again;
 		}
 		timer->base = new_base;
 	}
@@ -1276,14 +1282,22 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 
 	expires_next.tv64 = KTIME_MAX;
 
+	spin_lock(&cpu_base->lock);
+	/*
+	 * We set expires_next to KTIME_MAX here with cpu_base->lock
+	 * held to prevent that a timer is enqueued in our queue via
+	 * the migration code. This does not affect enqueueing of
+	 * timers which run their callback and need to be requeued on
+	 * this CPU.
+	 */
+	cpu_base->expires_next.tv64 = KTIME_MAX;
+
 	base = cpu_base->clock_base;
 
 	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
 		ktime_t basenow;
 		struct rb_node *node;
 
-		spin_lock(&cpu_base->lock);
-
 		basenow = ktime_add(now, base->offset);
 
 		while ((node = base->first)) {
@@ -1316,11 +1330,15 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 
 			__run_hrtimer(timer);
 		}
-		spin_unlock(&cpu_base->lock);
 		base++;
 	}
 
+	/*
+	 * Store the new expiry value so the migration code can verify
+	 * against it.
+	 */
 	cpu_base->expires_next = expires_next;
+	spin_unlock(&cpu_base->lock);
 
 	/* Reprogramming necessary ? */
 	if (expires_next.tv64 != KTIME_MAX) {
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 7e95bed..385c31a 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -24,7 +24,6 @@
 #include <linux/unistd.h>
 #include <linux/kmod.h>
 #include <linux/slab.h>
-#include <linux/mnt_namespace.h>
 #include <linux/completion.h>
 #include <linux/file.h>
 #include <linux/fdtable.h>
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index c0fa54b..16b5739 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -237,13 +237,9 @@ static int __kprobes collect_garbage_slots(void)
 {
 	struct kprobe_insn_page *kip;
 	struct hlist_node *pos, *next;
-	int safety;
 
 	/* Ensure no-one is preepmted on the garbages */
-	mutex_unlock(&kprobe_insn_mutex);
-	safety = check_safety();
-	mutex_lock(&kprobe_insn_mutex);
-	if (safety != 0)
+	if (check_safety())
 		return -EAGAIN;
 
 	hlist_for_each_entry_safe(kip, pos, next, &kprobe_insn_pages, hlist) {
diff --git a/kernel/module.c b/kernel/module.c
index 38928fc..0a04983 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2451,9 +2451,9 @@ SYSCALL_DEFINE3(init_module, void __user *, umod,
 		return ret;
 	}
 	if (ret > 0) {
-		printk(KERN_WARNING "%s: '%s'->init suspiciously returned %d, "
-				    "it should follow 0/-E convention\n"
-		       KERN_WARNING "%s: loading module anyway...\n",
+		printk(KERN_WARNING
+"%s: '%s'->init suspiciously returned %d, it should follow 0/-E convention\n"
+"%s: loading module anyway...\n",
 		       __func__, mod->name, ret,
 		       __func__);
 		dump_stack();
diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index 1a933a2..a641eb7 100644
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -236,6 +236,8 @@ list_add_counter(struct perf_counter *counter, struct perf_counter_context *ctx)
 
 	list_add_rcu(&counter->event_entry, &ctx->event_list);
 	ctx->nr_counters++;
+	if (counter->attr.inherit_stat)
+		ctx->nr_stat++;
 }
 
 /*
@@ -250,6 +252,8 @@ list_del_counter(struct perf_counter *counter, struct perf_counter_context *ctx)
 	if (list_empty(&counter->list_entry))
 		return;
 	ctx->nr_counters--;
+	if (counter->attr.inherit_stat)
+		ctx->nr_stat--;
 
 	list_del_init(&counter->list_entry);
 	list_del_rcu(&counter->event_entry);
@@ -1006,6 +1010,81 @@ static int context_equiv(struct perf_counter_context *ctx1,
 		&& !ctx1->pin_count && !ctx2->pin_count;
 }
 
+static void __perf_counter_read(void *counter);
+
+static void __perf_counter_sync_stat(struct perf_counter *counter,
+				     struct perf_counter *next_counter)
+{
+	u64 value;
+
+	if (!counter->attr.inherit_stat)
+		return;
+
+	/*
+	 * Update the counter value, we cannot use perf_counter_read()
+	 * because we're in the middle of a context switch and have IRQs
+	 * disabled, which upsets smp_call_function_single(), however
+	 * we know the counter must be on the current CPU, therefore we
+	 * don't need to use it.
+	 */
+	switch (counter->state) {
+	case PERF_COUNTER_STATE_ACTIVE:
+		__perf_counter_read(counter);
+		break;
+
+	case PERF_COUNTER_STATE_INACTIVE:
+		update_counter_times(counter);
+		break;
+
+	default:
+		break;
+	}
+
+	/*
+	 * In order to keep per-task stats reliable we need to flip the counter
+	 * values when we flip the contexts.
+	 */
+	value = atomic64_read(&next_counter->count);
+	value = atomic64_xchg(&counter->count, value);
+	atomic64_set(&next_counter->count, value);
+
+	swap(counter->total_time_enabled, next_counter->total_time_enabled);
+	swap(counter->total_time_running, next_counter->total_time_running);
+
+	/*
+	 * Since we swizzled the values, update the user visible data too.
+	 */
+	perf_counter_update_userpage(counter);
+	perf_counter_update_userpage(next_counter);
+}
+
+#define list_next_entry(pos, member) \
+	list_entry(pos->member.next, typeof(*pos), member)
+
+static void perf_counter_sync_stat(struct perf_counter_context *ctx,
+				   struct perf_counter_context *next_ctx)
+{
+	struct perf_counter *counter, *next_counter;
+
+	if (!ctx->nr_stat)
+		return;
+
+	counter = list_first_entry(&ctx->event_list,
+				   struct perf_counter, event_entry);
+
+	next_counter = list_first_entry(&next_ctx->event_list,
+					struct perf_counter, event_entry);
+
+	while (&counter->event_entry != &ctx->event_list &&
+	       &next_counter->event_entry != &next_ctx->event_list) {
+
+		__perf_counter_sync_stat(counter, next_counter);
+
+		counter = list_next_entry(counter, event_entry);
+		next_counter = list_next_entry(counter, event_entry);
+	}
+}
+
 /*
  * Called from scheduler to remove the counters of the current task,
  * with interrupts disabled.
@@ -1061,6 +1140,8 @@ void perf_counter_task_sched_out(struct task_struct *task,
 			ctx->task = next;
 			next_ctx->task = task;
 			do_switch = 0;
+
+			perf_counter_sync_stat(ctx, next_ctx);
 		}
 		spin_unlock(&next_ctx->lock);
 		spin_unlock(&ctx->lock);
@@ -1348,9 +1429,56 @@ void perf_counter_task_tick(struct task_struct *curr, int cpu)
 }
 
 /*
+ * Enable all of a task's counters that have been marked enable-on-exec.
+ * This expects task == current.
+ */
+static void perf_counter_enable_on_exec(struct task_struct *task)
+{
+	struct perf_counter_context *ctx;
+	struct perf_counter *counter;
+	unsigned long flags;
+	int enabled = 0;
+
+	local_irq_save(flags);
+	ctx = task->perf_counter_ctxp;
+	if (!ctx || !ctx->nr_counters)
+		goto out;
+
+	__perf_counter_task_sched_out(ctx);
+
+	spin_lock(&ctx->lock);
+
+	list_for_each_entry(counter, &ctx->counter_list, list_entry) {
+		if (!counter->attr.enable_on_exec)
+			continue;
+		counter->attr.enable_on_exec = 0;
+		if (counter->state >= PERF_COUNTER_STATE_INACTIVE)
+			continue;
+		counter->state = PERF_COUNTER_STATE_INACTIVE;
+		counter->tstamp_enabled =
+			ctx->time - counter->total_time_enabled;
+		enabled = 1;
+	}
+
+	/*
+	 * Unclone this context if we enabled any counter.
+	 */
+	if (enabled && ctx->parent_ctx) {
+		put_ctx(ctx->parent_ctx);
+		ctx->parent_ctx = NULL;
+	}
+
+	spin_unlock(&ctx->lock);
+
+	perf_counter_task_sched_in(task, smp_processor_id());
+ out:
+	local_irq_restore(flags);
+}
+
+/*
  * Cross CPU call to read the hardware counter
  */
-static void __read(void *info)
+static void __perf_counter_read(void *info)
 {
 	struct perf_counter *counter = info;
 	struct perf_counter_context *ctx = counter->ctx;
@@ -1372,7 +1500,7 @@ static u64 perf_counter_read(struct perf_counter *counter)
 	 */
 	if (counter->state == PERF_COUNTER_STATE_ACTIVE) {
 		smp_call_function_single(counter->oncpu,
-					 __read, counter, 1);
+					 __perf_counter_read, counter, 1);
 	} else if (counter->state == PERF_COUNTER_STATE_INACTIVE) {
 		update_counter_times(counter);
 	}
@@ -1508,11 +1636,13 @@ static void free_counter(struct perf_counter *counter)
 {
 	perf_pending_sync(counter);
 
-	atomic_dec(&nr_counters);
-	if (counter->attr.mmap)
-		atomic_dec(&nr_mmap_counters);
-	if (counter->attr.comm)
-		atomic_dec(&nr_comm_counters);
+	if (!counter->parent) {
+		atomic_dec(&nr_counters);
+		if (counter->attr.mmap)
+			atomic_dec(&nr_mmap_counters);
+		if (counter->attr.comm)
+			atomic_dec(&nr_comm_counters);
+	}
 
 	if (counter->destroy)
 		counter->destroy(counter);
@@ -1751,6 +1881,14 @@ int perf_counter_task_disable(void)
 	return 0;
 }
 
+static int perf_counter_index(struct perf_counter *counter)
+{
+	if (counter->state != PERF_COUNTER_STATE_ACTIVE)
+		return 0;
+
+	return counter->hw.idx + 1 - PERF_COUNTER_INDEX_OFFSET;
+}
+
 /*
  * Callers need to ensure there can be no nesting of this function, otherwise
  * the seqlock logic goes bad. We can not serialize this because the arch
@@ -1775,11 +1913,17 @@ void perf_counter_update_userpage(struct perf_counter *counter)
 	preempt_disable();
 	++userpg->lock;
 	barrier();
-	userpg->index = counter->hw.idx;
+	userpg->index = perf_counter_index(counter);
 	userpg->offset = atomic64_read(&counter->count);
 	if (counter->state == PERF_COUNTER_STATE_ACTIVE)
 		userpg->offset -= atomic64_read(&counter->hw.prev_count);
 
+	userpg->time_enabled = counter->total_time_enabled +
+			atomic64_read(&counter->child_total_time_enabled);
+
+	userpg->time_running = counter->total_time_running +
+			atomic64_read(&counter->child_total_time_running);
+
 	barrier();
 	++userpg->lock;
 	preempt_enable();
@@ -1876,7 +2020,7 @@ fail:
 
 static void perf_mmap_free_page(unsigned long addr)
 {
-	struct page *page = virt_to_page(addr);
+	struct page *page = virt_to_page((void *)addr);
 
 	page->mapping = NULL;
 	__free_page(page);
@@ -2483,15 +2627,14 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
 		u32 cpu, reserved;
 	} cpu_entry;
 
-	header.type = 0;
+	header.type = PERF_EVENT_SAMPLE;
 	header.size = sizeof(header);
 
-	header.misc = PERF_EVENT_MISC_OVERFLOW;
+	header.misc = 0;
 	header.misc |= perf_misc_flags(data->regs);
 
 	if (sample_type & PERF_SAMPLE_IP) {
 		ip = perf_instruction_pointer(data->regs);
-		header.type |= PERF_SAMPLE_IP;
 		header.size += sizeof(ip);
 	}
 
@@ -2500,7 +2643,6 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
 		tid_entry.pid = perf_counter_pid(counter, current);
 		tid_entry.tid = perf_counter_tid(counter, current);
 
-		header.type |= PERF_SAMPLE_TID;
 		header.size += sizeof(tid_entry);
 	}
 
@@ -2510,34 +2652,25 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
 		 */
 		time = sched_clock();
 
-		header.type |= PERF_SAMPLE_TIME;
 		header.size += sizeof(u64);
 	}
 
-	if (sample_type & PERF_SAMPLE_ADDR) {
-		header.type |= PERF_SAMPLE_ADDR;
+	if (sample_type & PERF_SAMPLE_ADDR)
 		header.size += sizeof(u64);
-	}
 
-	if (sample_type & PERF_SAMPLE_ID) {
-		header.type |= PERF_SAMPLE_ID;
+	if (sample_type & PERF_SAMPLE_ID)
 		header.size += sizeof(u64);
-	}
 
 	if (sample_type & PERF_SAMPLE_CPU) {
-		header.type |= PERF_SAMPLE_CPU;
 		header.size += sizeof(cpu_entry);
 
 		cpu_entry.cpu = raw_smp_processor_id();
 	}
 
-	if (sample_type & PERF_SAMPLE_PERIOD) {
-		header.type |= PERF_SAMPLE_PERIOD;
+	if (sample_type & PERF_SAMPLE_PERIOD)
 		header.size += sizeof(u64);
-	}
 
 	if (sample_type & PERF_SAMPLE_GROUP) {
-		header.type |= PERF_SAMPLE_GROUP;
 		header.size += sizeof(u64) +
 			counter->nr_siblings * sizeof(group_entry);
 	}
@@ -2547,10 +2680,9 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
 
 		if (callchain) {
 			callchain_size = (1 + callchain->nr) * sizeof(u64);
-
-			header.type |= PERF_SAMPLE_CALLCHAIN;
 			header.size += callchain_size;
-		}
+		} else
+			header.size += sizeof(u64);
 	}
 
 	ret = perf_output_begin(&handle, counter, header.size, nmi, 1);
@@ -2601,13 +2733,79 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
 		}
 	}
 
-	if (callchain)
-		perf_output_copy(&handle, callchain, callchain_size);
+	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
+		if (callchain)
+			perf_output_copy(&handle, callchain, callchain_size);
+		else {
+			u64 nr = 0;
+			perf_output_put(&handle, nr);
+		}
+	}
 
 	perf_output_end(&handle);
 }
 
 /*
+ * read event
+ */
+
+struct perf_read_event {
+	struct perf_event_header	header;
+
+	u32				pid;
+	u32				tid;
+	u64				value;
+	u64				format[3];
+};
+
+static void
+perf_counter_read_event(struct perf_counter *counter,
+			struct task_struct *task)
+{
+	struct perf_output_handle handle;
+	struct perf_read_event event = {
+		.header = {
+			.type = PERF_EVENT_READ,
+			.misc = 0,
+			.size = sizeof(event) - sizeof(event.format),
+		},
+		.pid = perf_counter_pid(counter, task),
+		.tid = perf_counter_tid(counter, task),
+		.value = atomic64_read(&counter->count),
+	};
+	int ret, i = 0;
+
+	if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
+		event.header.size += sizeof(u64);
+		event.format[i++] = counter->total_time_enabled;
+	}
+
+	if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
+		event.header.size += sizeof(u64);
+		event.format[i++] = counter->total_time_running;
+	}
+
+	if (counter->attr.read_format & PERF_FORMAT_ID) {
+		u64 id;
+
+		event.header.size += sizeof(u64);
+		if (counter->parent)
+			id = counter->parent->id;
+		else
+			id = counter->id;
+
+		event.format[i++] = id;
+	}
+
+	ret = perf_output_begin(&handle, counter, event.header.size, 0, 0);
+	if (ret)
+		return;
+
+	perf_output_copy(&handle, &event, event.header.size);
+	perf_output_end(&handle);
+}
+
+/*
  * fork tracking
  */
 
@@ -2798,6 +2996,9 @@ void perf_counter_comm(struct task_struct *task)
 {
 	struct perf_comm_event comm_event;
 
+	if (task->perf_counter_ctxp)
+		perf_counter_enable_on_exec(task);
+
 	if (!atomic_read(&nr_comm_counters))
 		return;
 
@@ -3317,8 +3518,8 @@ out:
 	put_cpu_var(perf_cpu_context);
 }
 
-void
-perf_swcounter_event(u32 event, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
+void __perf_swcounter_event(u32 event, u64 nr, int nmi,
+			    struct pt_regs *regs, u64 addr)
 {
 	struct perf_sample_data data = {
 		.regs = regs,
@@ -3509,9 +3710,21 @@ static const struct pmu *tp_perf_counter_init(struct perf_counter *counter)
 }
 #endif
 
+atomic_t perf_swcounter_enabled[PERF_COUNT_SW_MAX];
+
+static void sw_perf_counter_destroy(struct perf_counter *counter)
+{
+	u64 event = counter->attr.config;
+
+	WARN_ON(counter->parent);
+
+	atomic_dec(&perf_swcounter_enabled[event]);
+}
+
 static const struct pmu *sw_perf_counter_init(struct perf_counter *counter)
 {
 	const struct pmu *pmu = NULL;
+	u64 event = counter->attr.config;
 
 	/*
 	 * Software counters (currently) can't in general distinguish
@@ -3520,7 +3733,7 @@ static const struct pmu *sw_perf_counter_init(struct perf_counter *counter)
 	 * to be kernel events, and page faults are never hypervisor
 	 * events.
 	 */
-	switch (counter->attr.config) {
+	switch (event) {
 	case PERF_COUNT_SW_CPU_CLOCK:
 		pmu = &perf_ops_cpu_clock;
 
@@ -3541,6 +3754,10 @@ static const struct pmu *sw_perf_counter_init(struct perf_counter *counter)
 	case PERF_COUNT_SW_PAGE_FAULTS_MAJ:
 	case PERF_COUNT_SW_CONTEXT_SWITCHES:
 	case PERF_COUNT_SW_CPU_MIGRATIONS:
+		if (!counter->parent) {
+			atomic_inc(&perf_swcounter_enabled[event]);
+			counter->destroy = sw_perf_counter_destroy;
+		}
 		pmu = &perf_ops_generic;
 		break;
 	}
@@ -3556,6 +3773,7 @@ perf_counter_alloc(struct perf_counter_attr *attr,
 		   int cpu,
 		   struct perf_counter_context *ctx,
 		   struct perf_counter *group_leader,
+		   struct perf_counter *parent_counter,
 		   gfp_t gfpflags)
 {
 	const struct pmu *pmu;
@@ -3591,6 +3809,8 @@ perf_counter_alloc(struct perf_counter_attr *attr,
 	counter->ctx		= ctx;
 	counter->oncpu		= -1;
 
+	counter->parent		= parent_counter;
+
 	counter->ns		= get_pid_ns(current->nsproxy->pid_ns);
 	counter->id		= atomic64_inc_return(&perf_counter_id);
 
@@ -3648,11 +3868,13 @@ done:
 
 	counter->pmu = pmu;
 
-	atomic_inc(&nr_counters);
-	if (counter->attr.mmap)
-		atomic_inc(&nr_mmap_counters);
-	if (counter->attr.comm)
-		atomic_inc(&nr_comm_counters);
+	if (!counter->parent) {
+		atomic_inc(&nr_counters);
+		if (counter->attr.mmap)
+			atomic_inc(&nr_mmap_counters);
+		if (counter->attr.comm)
+			atomic_inc(&nr_comm_counters);
+	}
 
 	return counter;
 }
@@ -3815,7 +4037,7 @@ SYSCALL_DEFINE5(perf_counter_open,
 	}
 
 	counter = perf_counter_alloc(&attr, cpu, ctx, group_leader,
-				     GFP_KERNEL);
+				     NULL, GFP_KERNEL);
 	ret = PTR_ERR(counter);
 	if (IS_ERR(counter))
 		goto err_put_context;
@@ -3881,7 +4103,8 @@ inherit_counter(struct perf_counter *parent_counter,
 
 	child_counter = perf_counter_alloc(&parent_counter->attr,
 					   parent_counter->cpu, child_ctx,
-					   group_leader, GFP_KERNEL);
+					   group_leader, parent_counter,
+					   GFP_KERNEL);
 	if (IS_ERR(child_counter))
 		return child_counter;
 	get_ctx(child_ctx);
@@ -3904,12 +4127,6 @@ inherit_counter(struct perf_counter *parent_counter,
 	 */
 	add_counter_to_ctx(child_counter, child_ctx);
 
-	child_counter->parent = parent_counter;
-	/*
-	 * inherit into child's child as well:
-	 */
-	child_counter->attr.inherit = 1;
-
 	/*
 	 * Get a reference to the parent filp - we will fput it
 	 * when the child counter exits. This is safe to do because
@@ -3953,10 +4170,14 @@ static int inherit_group(struct perf_counter *parent_counter,
 }
 
 static void sync_child_counter(struct perf_counter *child_counter,
-			       struct perf_counter *parent_counter)
+			       struct task_struct *child)
 {
+	struct perf_counter *parent_counter = child_counter->parent;
 	u64 child_val;
 
+	if (child_counter->attr.inherit_stat)
+		perf_counter_read_event(child_counter, child);
+
 	child_val = atomic64_read(&child_counter->count);
 
 	/*
@@ -3985,7 +4206,8 @@ static void sync_child_counter(struct perf_counter *child_counter,
 
 static void
 __perf_counter_exit_task(struct perf_counter *child_counter,
-			 struct perf_counter_context *child_ctx)
+			 struct perf_counter_context *child_ctx,
+			 struct task_struct *child)
 {
 	struct perf_counter *parent_counter;
 
@@ -3999,7 +4221,7 @@ __perf_counter_exit_task(struct perf_counter *child_counter,
 	 * counters need to be zapped - but otherwise linger.
 	 */
 	if (parent_counter) {
-		sync_child_counter(child_counter, parent_counter);
+		sync_child_counter(child_counter, child);
 		free_counter(child_counter);
 	}
 }
@@ -4061,7 +4283,7 @@ void perf_counter_exit_task(struct task_struct *child)
 again:
 	list_for_each_entry_safe(child_counter, tmp, &child_ctx->counter_list,
 				 list_entry)
-		__perf_counter_exit_task(child_counter, child_ctx);
+		__perf_counter_exit_task(child_counter, child_ctx, child);
 
 	/*
 	 * If the last counter was a group counter, it will have appended all
diff --git a/kernel/power/user.c b/kernel/power/user.c
index ed97375..bf0014d 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -23,7 +23,6 @@
 #include <linux/console.h>
 #include <linux/cpu.h>
 #include <linux/freezer.h>
-#include <linux/smp_lock.h>
 #include <scsi/scsi_scan.h>
 
 #include <asm/uaccess.h>
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 61c78b2..082c320 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -181,8 +181,8 @@ int ptrace_attach(struct task_struct *task)
 	 * interference; SUID, SGID and LSM creds get determined differently
 	 * under ptrace.
 	 */
-	retval = mutex_lock_interruptible(&task->cred_guard_mutex);
-	if (retval < 0)
+	retval = -ERESTARTNOINTR;
+	if (mutex_lock_interruptible(&task->cred_guard_mutex))
 		goto out;
 
 	task_lock(task);
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 0dccfbb..7717b95 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1533,7 +1533,7 @@ void __init __rcu_init(void)
 	int j;
 	struct rcu_node *rnp;
 
-	printk(KERN_WARNING "Experimental hierarchical RCU implementation.\n");
+	printk(KERN_INFO "Hierarchical RCU implementation.\n");
 #ifdef CONFIG_RCU_CPU_STALL_DETECTOR
 	printk(KERN_INFO "RCU-based detection of stalled CPUs is enabled.\n");
 #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
@@ -1546,7 +1546,6 @@ void __init __rcu_init(void)
 		rcu_cpu_notify(&rcu_nb, CPU_UP_PREPARE, (void *)(long)i);
 	/* Register notifier for non-boot CPUs */
 	register_cpu_notifier(&rcu_nb);
-	printk(KERN_WARNING "Experimental hierarchical RCU init done.\n");
 }
 
 module_param(blimit, int, 0);
diff --git a/kernel/resource.c b/kernel/resource.c
index ac5f3a3..78b0872 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -787,7 +787,7 @@ static int __init reserve_setup(char *str)
 	static struct resource reserve[MAXRESERVE];
 
 	for (;;) {
-		int io_start, io_num;
+		unsigned int io_start, io_num;
 		int x = reserved;
 
 		if (get_option (&str, &io_start) != 2)
diff --git a/kernel/sched.c b/kernel/sched.c
index ebc5151..03f7e3f 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -493,6 +493,7 @@ struct rt_rq {
 #endif
 #ifdef CONFIG_SMP
 	unsigned long rt_nr_migratory;
+	unsigned long rt_nr_total;
 	int overloaded;
 	struct plist_head pushable_tasks;
 #endif
@@ -2572,15 +2573,37 @@ static void __sched_fork(struct task_struct *p)
 	p->se.avg_wakeup		= sysctl_sched_wakeup_granularity;
 
 #ifdef CONFIG_SCHEDSTATS
-	p->se.wait_start		= 0;
-	p->se.sum_sleep_runtime		= 0;
-	p->se.sleep_start		= 0;
-	p->se.block_start		= 0;
-	p->se.sleep_max			= 0;
-	p->se.block_max			= 0;
-	p->se.exec_max			= 0;
-	p->se.slice_max			= 0;
-	p->se.wait_max			= 0;
+	p->se.wait_start			= 0;
+	p->se.wait_max				= 0;
+	p->se.wait_count			= 0;
+	p->se.wait_sum				= 0;
+
+	p->se.sleep_start			= 0;
+	p->se.sleep_max				= 0;
+	p->se.sum_sleep_runtime			= 0;
+
+	p->se.block_start			= 0;
+	p->se.block_max				= 0;
+	p->se.exec_max				= 0;
+	p->se.slice_max				= 0;
+
+	p->se.nr_migrations_cold		= 0;
+	p->se.nr_failed_migrations_affine	= 0;
+	p->se.nr_failed_migrations_running	= 0;
+	p->se.nr_failed_migrations_hot		= 0;
+	p->se.nr_forced_migrations		= 0;
+	p->se.nr_forced2_migrations		= 0;
+
+	p->se.nr_wakeups			= 0;
+	p->se.nr_wakeups_sync			= 0;
+	p->se.nr_wakeups_migrate		= 0;
+	p->se.nr_wakeups_local			= 0;
+	p->se.nr_wakeups_remote			= 0;
+	p->se.nr_wakeups_affine			= 0;
+	p->se.nr_wakeups_affine_attempts	= 0;
+	p->se.nr_wakeups_passive		= 0;
+	p->se.nr_wakeups_idle			= 0;
+
 #endif
 
 	INIT_LIST_HEAD(&p->rt.run_list);
@@ -6580,6 +6603,11 @@ SYSCALL_DEFINE0(sched_yield)
 	return 0;
 }
 
+static inline int should_resched(void)
+{
+	return need_resched() && !(preempt_count() & PREEMPT_ACTIVE);
+}
+
 static void __cond_resched(void)
 {
 #ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
@@ -6599,8 +6627,7 @@ static void __cond_resched(void)
 
 int __sched _cond_resched(void)
 {
-	if (need_resched() && !(preempt_count() & PREEMPT_ACTIVE) &&
-					system_state == SYSTEM_RUNNING) {
+	if (should_resched()) {
 		__cond_resched();
 		return 1;
 	}
@@ -6618,12 +6645,12 @@ EXPORT_SYMBOL(_cond_resched);
  */
 int cond_resched_lock(spinlock_t *lock)
 {
-	int resched = need_resched() && system_state == SYSTEM_RUNNING;
+	int resched = should_resched();
 	int ret = 0;
 
 	if (spin_needbreak(lock) || resched) {
 		spin_unlock(lock);
-		if (resched && need_resched())
+		if (resched)
 			__cond_resched();
 		else
 			cpu_relax();
@@ -6638,7 +6665,7 @@ int __sched cond_resched_softirq(void)
 {
 	BUG_ON(!in_softirq());
 
-	if (need_resched() && system_state == SYSTEM_RUNNING) {
+	if (should_resched()) {
 		local_bh_enable();
 		__cond_resched();
 		local_bh_disable();
@@ -9109,7 +9136,7 @@ static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
 #ifdef CONFIG_SMP
 	rt_rq->rt_nr_migratory = 0;
 	rt_rq->overloaded = 0;
-	plist_head_init(&rq->rt.pushable_tasks, &rq->lock);
+	plist_head_init(&rt_rq->pushable_tasks, &rq->lock);
 #endif
 
 	rt_rq->rt_time = 0;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index ba7fd6e..7c248dc 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -687,7 +687,8 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 			 * all of which have the same weight.
 			 */
 			if (sched_feat(NORMALIZED_SLEEPER) &&
-					task_of(se)->policy != SCHED_IDLE)
+					(!entity_is_task(se) ||
+					 task_of(se)->policy != SCHED_IDLE))
 				thresh = calc_delta_fair(thresh, se);
 
 			vruntime -= thresh;
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 9bf0d2a..3918e01 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -10,6 +10,8 @@ static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
 
 #ifdef CONFIG_RT_GROUP_SCHED
 
+#define rt_entity_is_task(rt_se) (!(rt_se)->my_q)
+
 static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
 {
 	return rt_rq->rq;
@@ -22,6 +24,8 @@ static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
 
 #else /* CONFIG_RT_GROUP_SCHED */
 
+#define rt_entity_is_task(rt_se) (1)
+
 static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
 {
 	return container_of(rt_rq, struct rq, rt);
@@ -73,7 +77,7 @@ static inline void rt_clear_overload(struct rq *rq)
 
 static void update_rt_migration(struct rt_rq *rt_rq)
 {
-	if (rt_rq->rt_nr_migratory && (rt_rq->rt_nr_running > 1)) {
+	if (rt_rq->rt_nr_migratory && rt_rq->rt_nr_total > 1) {
 		if (!rt_rq->overloaded) {
 			rt_set_overload(rq_of_rt_rq(rt_rq));
 			rt_rq->overloaded = 1;
@@ -86,6 +90,12 @@ static void update_rt_migration(struct rt_rq *rt_rq)
 
 static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 {
+	if (!rt_entity_is_task(rt_se))
+		return;
+
+	rt_rq = &rq_of_rt_rq(rt_rq)->rt;
+
+	rt_rq->rt_nr_total++;
 	if (rt_se->nr_cpus_allowed > 1)
 		rt_rq->rt_nr_migratory++;
 
@@ -94,6 +104,12 @@ static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 
 static void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 {
+	if (!rt_entity_is_task(rt_se))
+		return;
+
+	rt_rq = &rq_of_rt_rq(rt_rq)->rt;
+
+	rt_rq->rt_nr_total--;
 	if (rt_se->nr_cpus_allowed > 1)
 		rt_rq->rt_nr_migratory--;
 
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 1ad6dd4..a6dcd67 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -254,15 +254,4 @@ void clockevents_notify(unsigned long reason, void *arg)
 	spin_unlock(&clockevents_lock);
 }
 EXPORT_SYMBOL_GPL(clockevents_notify);
-
-ktime_t clockevents_get_next_event(int cpu)
-{
-	struct tick_device *td;
-	struct clock_event_device *dev;
-
-	td = &per_cpu(tick_cpu_device, cpu);
-	dev = td->evtdev;
-
-	return dev->next_event;
-}
 #endif
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 1551f47..019f380 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -226,13 +226,13 @@ config BOOT_TRACER
 	  the timings of the initcalls and traces key events and the identity
 	  of tasks that can cause boot delays, such as context-switches.
 
-	  Its aim is to be parsed by the /scripts/bootgraph.pl tool to
+	  Its aim is to be parsed by the scripts/bootgraph.pl tool to
 	  produce pretty graphics about boot inefficiencies, giving a visual
 	  representation of the delays during initcalls - but the raw
 	  /debug/tracing/trace text output is readable too.
 
-	  You must pass in ftrace=initcall to the kernel command line
-	  to enable this on bootup.
+	  You must pass in initcall_debug and ftrace=initcall to the kernel
+	  command line to enable this on bootup.
 
 config TRACE_BRANCH_PROFILING
 	bool
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 39af8af..1090b0a 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -22,6 +22,7 @@
 #include <linux/init.h>
 #include <linux/mutex.h>
 #include <linux/debugfs.h>
+#include <linux/smp_lock.h>
 #include <linux/time.h>
 #include <linux/uaccess.h>
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index f3716bf..4521c77 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -768,7 +768,7 @@ static struct tracer_stat function_stats __initdata = {
 	.stat_show	= function_stat_show
 };
 
-static void ftrace_profile_debugfs(struct dentry *d_tracer)
+static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
 {
 	struct ftrace_profile_stat *stat;
 	struct dentry *entry;
@@ -786,7 +786,6 @@ static void ftrace_profile_debugfs(struct dentry *d_tracer)
 			 * The files created are permanent, if something happens
 			 * we still do not free memory.
 			 */
-			kfree(stat);
 			WARN(1,
 			     "Could not allocate stat file for cpu %d\n",
 			     cpu);
@@ -813,7 +812,7 @@ static void ftrace_profile_debugfs(struct dentry *d_tracer)
 }
 
 #else /* CONFIG_FUNCTION_PROFILER */
-static void ftrace_profile_debugfs(struct dentry *d_tracer)
+static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
 {
 }
 #endif /* CONFIG_FUNCTION_PROFILER */
@@ -3160,10 +3159,10 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 
 	ret  = proc_dointvec(table, write, file, buffer, lenp, ppos);
 
-	if (ret || !write || (last_ftrace_enabled == ftrace_enabled))
+	if (ret || !write || (last_ftrace_enabled == !!ftrace_enabled))
 		goto out;
 
-	last_ftrace_enabled = ftrace_enabled;
+	last_ftrace_enabled = !!ftrace_enabled;
 
 	if (ftrace_enabled) {
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 3aa0a0d..8bc8d8a 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -17,6 +17,7 @@
 #include <linux/writeback.h>
 #include <linux/kallsyms.h>
 #include <linux/seq_file.h>
+#include <linux/smp_lock.h>
 #include <linux/notifier.h>
 #include <linux/irqflags.h>
 #include <linux/debugfs.h>
diff --git a/kernel/trace/trace_event_types.h b/kernel/trace/trace_event_types.h
index 5e32e37..6db005e 100644
--- a/kernel/trace/trace_event_types.h
+++ b/kernel/trace/trace_event_types.h
@@ -26,6 +26,9 @@ TRACE_EVENT_FORMAT(funcgraph_exit, TRACE_GRAPH_RET,
 		   ftrace_graph_ret_entry, ignore,
 	TRACE_STRUCT(
 		TRACE_FIELD(unsigned long, ret.func, func)
+		TRACE_FIELD(unsigned long long, ret.calltime, calltime)
+		TRACE_FIELD(unsigned long long, ret.rettime, rettime)
+		TRACE_FIELD(unsigned long, ret.overrun, overrun)
 		TRACE_FIELD(int, ret.depth, depth)
 	),
 	TP_RAW_FMT("<-- %lx (%d)")
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 7402144..75ef000 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -363,7 +363,7 @@ ftrace_trace_onoff_callback(char *glob, char *cmd, char *param, int enable)
  out_reg:
 	ret = register_ftrace_function_probe(glob, ops, count);
 
-	return ret;
+	return ret < 0 ? ret : 0;
 }
 
 static struct ftrace_func_command ftrace_traceon_cmd = {
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 7938f3a..e0c2545 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -27,8 +27,7 @@ void trace_print_seq(struct seq_file *m, struct trace_seq *s)
 {
 	int len = s->len >= PAGE_SIZE ? PAGE_SIZE - 1 : s->len;
 
-	s->buffer[len] = 0;
-	seq_puts(m, s->buffer);
+	seq_write(m, s->buffer, len);
 
 	trace_seq_init(s);
 }
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 2d7aebd..e644af9 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -326,10 +326,10 @@ stack_trace_sysctl(struct ctl_table *table, int write,
 	ret = proc_dointvec(table, write, file, buffer, lenp, ppos);
 
 	if (ret || !write ||
-	    (last_stack_tracer_enabled == stack_tracer_enabled))
+	    (last_stack_tracer_enabled == !!stack_tracer_enabled))
 		goto out;
 
-	last_stack_tracer_enabled = stack_tracer_enabled;
+	last_stack_tracer_enabled = !!stack_tracer_enabled;
 
 	if (stack_tracer_enabled)
 		register_ftrace_function(&trace_ops);