62 files changed, 4286 insertions, 3112 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index e898c5b9d02..f70396e5a24 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -2,16 +2,15 @@
 # Makefile for the linux kernel.
 #
 
-obj-y     = sched.o fork.o exec_domain.o panic.o printk.o \
+obj-y     = fork.o exec_domain.o panic.o printk.o \
 	    cpu.o exit.o itimer.o time.o softirq.o resource.o \
 	    sysctl.o sysctl_binary.o capability.o ptrace.o timer.o user.o \
 	    signal.o sys.o kmod.o workqueue.o pid.o \
 	    rcupdate.o extable.o params.o posix-timers.o \
 	    kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
 	    hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
-	    notifier.o ksysfs.o sched_clock.o cred.o \
-	    async.o range.o
-obj-y += groups.o
+	    notifier.o ksysfs.o cred.o \
+	    async.o range.o groups.o
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not trace debug files and internal ftrace files
@@ -20,10 +19,11 @@ CFLAGS_REMOVE_lockdep_proc.o = -pg
 CFLAGS_REMOVE_mutex-debug.o = -pg
 CFLAGS_REMOVE_rtmutex-debug.o = -pg
 CFLAGS_REMOVE_cgroup-debug.o = -pg
-CFLAGS_REMOVE_sched_clock.o = -pg
 CFLAGS_REMOVE_irq_work.o = -pg
 endif
 
+obj-y += sched/
+
 obj-$(CONFIG_FREEZER) += freezer.o
 obj-$(CONFIG_PROFILING) += profile.o
 obj-$(CONFIG_SYSCTL_SYSCALL_CHECK) += sysctl_check.o
@@ -99,7 +99,6 @@ obj-$(CONFIG_TRACING) += trace/
 obj-$(CONFIG_X86_DS) += trace/
 obj-$(CONFIG_RING_BUFFER) += trace/
 obj-$(CONFIG_TRACEPOINTS) += trace/
-obj-$(CONFIG_SMP) += sched_cpupri.o
 obj-$(CONFIG_IRQ_WORK) += irq_work.o
 obj-$(CONFIG_CPU_PM) += cpu_pm.o
 
@@ -110,15 +109,6 @@ obj-$(CONFIG_PADATA) += padata.o
 obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
 obj-$(CONFIG_JUMP_LABEL) += jump_label.o
 
-ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
-# According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
-# needed for x86 only.  Why this used to be enabled for all architectures is beyond
-# me.  I suspect most platforms don't need this, but until we know that for sure
-# I turn this off for IA-64 only.  Andreas Schwab says it's also needed on m68k
-# to get a correct value for the wait-channel (WCHAN in ps). --davidm
-CFLAGS_sched.o := $(PROFILING) -fno-omit-frame-pointer
-endif
-
 $(obj)/configs.o: $(obj)/config_data.h
 
 # config_data.h contains the same information as ikconfig.h but gzipped.
diff --git a/kernel/acct.c b/kernel/acct.c
index 9663eb8058f..02e6167a53b 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -593,8 +593,8 @@ void acct_collect(long exitcode, int group_dead)
 		pacct->ac_flag |= ACORE;
 	if (current->flags & PF_SIGNALED)
 		pacct->ac_flag |= AXSIG;
-	pacct->ac_utime = cputime_add(pacct->ac_utime, current->utime);
-	pacct->ac_stime = cputime_add(pacct->ac_stime, current->stime);
+	pacct->ac_utime += current->utime;
+	pacct->ac_stime += current->stime;
 	pacct->ac_minflt += current->min_flt;
 	pacct->ac_majflt += current->maj_flt;
 	spin_unlock_irq(&current->sighand->siglock);
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 563f1360947..5ca38d5d238 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -178,8 +178,7 @@ static inline void check_for_tasks(int cpu)
 	write_lock_irq(&tasklist_lock);
 	for_each_process(p) {
 		if (task_cpu(p) == cpu && p->state == TASK_RUNNING &&
-		    (!cputime_eq(p->utime, cputime_zero) ||
-		     !cputime_eq(p->stime, cputime_zero)))
+		    (p->utime || p->stime))
 			printk(KERN_WARNING "Task %s (pid = %d) is on cpu %d "
 				"(state = %ld, flags = %x)\n",
 				p->comm, task_pid_nr(p), cpu,
@@ -380,6 +379,7 @@ out:
 	cpu_maps_update_done();
 	return err;
 }
+EXPORT_SYMBOL_GPL(cpu_up);
 
 #ifdef CONFIG_PM_SLEEP_SMP
 static cpumask_var_t frozen_cpus;
diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c
index 5532dd37aa8..7d6fb40d218 100644
--- a/kernel/debug/kdb/kdb_support.c
+++ b/kernel/debug/kdb/kdb_support.c
@@ -636,7 +636,7 @@ char kdb_task_state_char (const struct task_struct *p)
 		(p->exit_state & EXIT_ZOMBIE) ? 'Z' :
 		(p->exit_state & EXIT_DEAD) ? 'E' :
 		(p->state & TASK_INTERRUPTIBLE) ? 'S' : '?';
-	if (p->pid == 0) {
+	if (is_idle_task(p)) {
 		/* Idle task.  Is it really idle, apart from the kdb
 		 * interrupt? */
 		if (!kdb_task_has_cpu(p) || kgdb_info[cpu].irq_depth == 1) {
diff --git a/kernel/events/Makefile b/kernel/events/Makefile
index 89e5e8aa4c3..22d901f9caf 100644
--- a/kernel/events/Makefile
+++ b/kernel/events/Makefile
@@ -2,5 +2,5 @@ ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_core.o = -pg
 endif
 
-obj-y := core.o ring_buffer.o
+obj-y := core.o ring_buffer.o callchain.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
new file mode 100644
index 00000000000..057e24b665c
--- /dev/null
+++ b/kernel/events/callchain.c
@@ -0,0 +1,191 @@
+/*
+ * Performance events callchain code, extracted from core.c:
+ *
+ *  Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
+ *  Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar
+ *  Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright  ©  2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
+ *
+ * For licensing details see kernel-base/COPYING
+ */
+
+#include <linux/perf_event.h>
+#include <linux/slab.h>
+#include "internal.h"
+
+struct callchain_cpus_entries {
+	struct rcu_head			rcu_head;
+	struct perf_callchain_entry	*cpu_entries[0];
+};
+
+static DEFINE_PER_CPU(int, callchain_recursion[PERF_NR_CONTEXTS]);
+static atomic_t nr_callchain_events;
+static DEFINE_MUTEX(callchain_mutex);
+static struct callchain_cpus_entries *callchain_cpus_entries;
+
+
+__weak void perf_callchain_kernel(struct perf_callchain_entry *entry,
+				  struct pt_regs *regs)
+{
+}
+
+__weak void perf_callchain_user(struct perf_callchain_entry *entry,
+				struct pt_regs *regs)
+{
+}
+
+static void release_callchain_buffers_rcu(struct rcu_head *head)
+{
+	struct callchain_cpus_entries *entries;
+	int cpu;
+
+	entries = container_of(head, struct callchain_cpus_entries, rcu_head);
+
+	for_each_possible_cpu(cpu)
+		kfree(entries->cpu_entries[cpu]);
+
+	kfree(entries);
+}
+
+static void release_callchain_buffers(void)
+{
+	struct callchain_cpus_entries *entries;
+
+	entries = callchain_cpus_entries;
+	rcu_assign_pointer(callchain_cpus_entries, NULL);
+	call_rcu(&entries->rcu_head, release_callchain_buffers_rcu);
+}
+
+static int alloc_callchain_buffers(void)
+{
+	int cpu;
+	int size;
+	struct callchain_cpus_entries *entries;
+
+	/*
+	 * We can't use the percpu allocation API for data that can be
+	 * accessed from NMI. Use a temporary manual per cpu allocation
+	 * until that gets sorted out.
+	 */
+	size = offsetof(struct callchain_cpus_entries, cpu_entries[nr_cpu_ids]);
+
+	entries = kzalloc(size, GFP_KERNEL);
+	if (!entries)
+		return -ENOMEM;
+
+	size = sizeof(struct perf_callchain_entry) * PERF_NR_CONTEXTS;
+
+	for_each_possible_cpu(cpu) {
+		entries->cpu_entries[cpu] = kmalloc_node(size, GFP_KERNEL,
+							 cpu_to_node(cpu));
+		if (!entries->cpu_entries[cpu])
+			goto fail;
+	}
+
+	rcu_assign_pointer(callchain_cpus_entries, entries);
+
+	return 0;
+
+fail:
+	for_each_possible_cpu(cpu)
+		kfree(entries->cpu_entries[cpu]);
+	kfree(entries);
+
+	return -ENOMEM;
+}
+
+int get_callchain_buffers(void)
+{
+	int err = 0;
+	int count;
+
+	mutex_lock(&callchain_mutex);
+
+	count = atomic_inc_return(&nr_callchain_events);
+	if (WARN_ON_ONCE(count < 1)) {
+		err = -EINVAL;
+		goto exit;
+	}
+
+	if (count > 1) {
+		/* If the allocation failed, give up */
+		if (!callchain_cpus_entries)
+			err = -ENOMEM;
+		goto exit;
+	}
+
+	err = alloc_callchain_buffers();
+	if (err)
+		release_callchain_buffers();
+exit:
+	mutex_unlock(&callchain_mutex);
+
+	return err;
+}
+
+void put_callchain_buffers(void)
+{
+	if (atomic_dec_and_mutex_lock(&nr_callchain_events, &callchain_mutex)) {
+		release_callchain_buffers();
+		mutex_unlock(&callchain_mutex);
+	}
+}
+
+static struct perf_callchain_entry *get_callchain_entry(int *rctx)
+{
+	int cpu;
+	struct callchain_cpus_entries *entries;
+
+	*rctx = get_recursion_context(__get_cpu_var(callchain_recursion));
+	if (*rctx == -1)
+		return NULL;
+
+	entries = rcu_dereference(callchain_cpus_entries);
+	if (!entries)
+		return NULL;
+
+	cpu = smp_processor_id();
+
+	return &entries->cpu_entries[cpu][*rctx];
+}
+
+static void
+put_callchain_entry(int rctx)
+{
+	put_recursion_context(__get_cpu_var(callchain_recursion), rctx);
+}
+
+struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
+{
+	int rctx;
+	struct perf_callchain_entry *entry;
+
+
+	entry = get_callchain_entry(&rctx);
+	if (rctx == -1)
+		return NULL;
+
+	if (!entry)
+		goto exit_put;
+
+	entry->nr = 0;
+
+	if (!user_mode(regs)) {
+		perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
+		perf_callchain_kernel(entry, regs);
+		if (current->mm)
+			regs = task_pt_regs(current);
+		else
+			regs = NULL;
+	}
+
+	if (regs) {
+		perf_callchain_store(entry, PERF_CONTEXT_USER);
+		perf_callchain_user(entry, regs);
+	}
+
+exit_put:
+	put_callchain_entry(rctx);
+
+	return entry;
+}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 58690af323e..890eb02c2f2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -128,7 +128,7 @@ enum event_type_t {
  * perf_sched_events : >0 events exist
  * perf_cgroup_events: >0 per-cpu cgroup events exist on this cpu
  */
-struct jump_label_key perf_sched_events __read_mostly;
+struct jump_label_key_deferred perf_sched_events __read_mostly;
 static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
 
 static atomic_t nr_mmap_events __read_mostly;
@@ -1130,6 +1130,8 @@ event_sched_out(struct perf_event *event,
 	if (!is_software_event(event))
 		cpuctx->active_oncpu--;
 	ctx->nr_active--;
+	if (event->attr.freq && event->attr.sample_freq)
+		ctx->nr_freq--;
 	if (event->attr.exclusive || !cpuctx->active_oncpu)
 		cpuctx->exclusive = 0;
 }
@@ -1325,6 +1327,7 @@ retry:
 	}
 	raw_spin_unlock_irq(&ctx->lock);
 }
+EXPORT_SYMBOL_GPL(perf_event_disable);
 
 static void perf_set_shadow_time(struct perf_event *event,
 				 struct perf_event_context *ctx,
@@ -1406,6 +1409,8 @@ event_sched_in(struct perf_event *event,
 	if (!is_software_event(event))
 		cpuctx->active_oncpu++;
 	ctx->nr_active++;
+	if (event->attr.freq && event->attr.sample_freq)
+		ctx->nr_freq++;
 
 	if (event->attr.exclusive)
 		cpuctx->exclusive = 1;
@@ -1662,8 +1667,7 @@ retry:
  * Note: this works for group members as well as group leaders
  * since the non-leader members' sibling_lists will be empty.
  */
-static void __perf_event_mark_enabled(struct perf_event *event,
-					struct perf_event_context *ctx)
+static void __perf_event_mark_enabled(struct perf_event *event)
 {
 	struct perf_event *sub;
 	u64 tstamp = perf_event_time(event);
@@ -1701,7 +1705,7 @@ static int __perf_event_enable(void *info)
 	 */
 	perf_cgroup_set_timestamp(current, ctx);
 
-	__perf_event_mark_enabled(event, ctx);
+	__perf_event_mark_enabled(event);
 
 	if (!event_filter_match(event)) {
 		if (is_cgroup_event(event))
@@ -1782,7 +1786,7 @@ void perf_event_enable(struct perf_event *event)
 
 retry:
 	if (!ctx->is_active) {
-		__perf_event_mark_enabled(event, ctx);
+		__perf_event_mark_enabled(event);
 		goto out;
 	}
 
@@ -1809,6 +1813,7 @@ retry:
 out:
 	raw_spin_unlock_irq(&ctx->lock);
 }
+EXPORT_SYMBOL_GPL(perf_event_enable);
 
 int perf_event_refresh(struct perf_event *event, int refresh)
 {
@@ -2327,6 +2332,9 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx, u64 period)
 	u64 interrupts, now;
 	s64 delta;
 
+	if (!ctx->nr_freq)
+		return;
+
 	list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
 		if (event->state != PERF_EVENT_STATE_ACTIVE)
 			continue;
@@ -2382,12 +2390,14 @@ static void perf_rotate_context(struct perf_cpu_context *cpuctx)
 {
 	u64 interval = (u64)cpuctx->jiffies_interval * TICK_NSEC;
 	struct perf_event_context *ctx = NULL;
-	int rotate = 0, remove = 1;
+	int rotate = 0, remove = 1, freq = 0;
 
 	if (cpuctx->ctx.nr_events) {
 		remove = 0;
 		if (cpuctx->ctx.nr_events != cpuctx->ctx.nr_active)
 			rotate = 1;
+		if (cpuctx->ctx.nr_freq)
+			freq = 1;
 	}
 
 	ctx = cpuctx->task_ctx;
@@ -2395,33 +2405,40 @@ static void perf_rotate_context(struct perf_cpu_context *cpuctx)
 		remove = 0;
 		if (ctx->nr_events != ctx->nr_active)
 			rotate = 1;
+		if (ctx->nr_freq)
+			freq = 1;
 	}
 
+	if (!rotate && !freq)
+		goto done;
+
 	perf_ctx_lock(cpuctx, cpuctx->task_ctx);
 	perf_pmu_disable(cpuctx->ctx.pmu);
-	perf_ctx_adjust_freq(&cpuctx->ctx, interval);
-	if (ctx)
-		perf_ctx_adjust_freq(ctx, interval);
 
-	if (!rotate)
-		goto done;
+	if (freq) {
+		perf_ctx_adjust_freq(&cpuctx->ctx, interval);
+		if (ctx)
+			perf_ctx_adjust_freq(ctx, interval);
+	}
 
-	cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
-	if (ctx)
-		ctx_sched_out(ctx, cpuctx, EVENT_FLEXIBLE);
+	if (rotate) {
+		cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
+		if (ctx)
+			ctx_sched_out(ctx, cpuctx, EVENT_FLEXIBLE);
 
-	rotate_ctx(&cpuctx->ctx);
-	if (ctx)
-		rotate_ctx(ctx);
+		rotate_ctx(&cpuctx->ctx);
+		if (ctx)
+			rotate_ctx(ctx);
 
-	perf_event_sched_in(cpuctx, ctx, current);
+		perf_event_sched_in(cpuctx, ctx, current);
+	}
+
+	perf_pmu_enable(cpuctx->ctx.pmu);
+	perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
 
 done:
 	if (remove)
 		list_del_init(&cpuctx->rotation_list);
-
-	perf_pmu_enable(cpuctx->ctx.pmu);
-	perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
 }
 
 void perf_event_task_tick(void)
@@ -2448,7 +2465,7 @@ static int event_enable_on_exec(struct perf_event *event,
 	if (event->state >= PERF_EVENT_STATE_INACTIVE)
 		return 0;
 
-	__perf_event_mark_enabled(event, ctx);
+	__perf_event_mark_enabled(event);
 
 	return 1;
 }
@@ -2480,13 +2497,7 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx)
 	raw_spin_lock(&ctx->lock);
 	task_ctx_sched_out(ctx);
 
-	list_for_each_entry(event, &ctx->pinned_groups, group_entry) {
-		ret = event_enable_on_exec(event, ctx);
-		if (ret)
-			enabled = 1;
-	}
-
-	list_for_each_entry(event, &ctx->flexible_groups, group_entry) {
+	list_for_each_entry(event, &ctx->event_list, event_entry) {
 		ret = event_enable_on_exec(event, ctx);
 		if (ret)
 			enabled = 1;
@@ -2574,215 +2585,6 @@ static u64 perf_event_read(struct perf_event *event)
 }
 
 /*
- * Callchain support
- */
-
-struct callchain_cpus_entries {
-	struct rcu_head			rcu_head;
-	struct perf_callchain_entry	*cpu_entries[0];
-};
-
-static DEFINE_PER_CPU(int, callchain_recursion[PERF_NR_CONTEXTS]);
-static atomic_t nr_callchain_events;
-static DEFINE_MUTEX(callchain_mutex);
-struct callchain_cpus_entries *callchain_cpus_entries;
-
-
-__weak void perf_callchain_kernel(struct perf_callchain_entry *entry,
-				  struct pt_regs *regs)
-{
-}
-
-__weak void perf_callchain_user(struct perf_callchain_entry *entry,
-				struct pt_regs *regs)
-{
-}
-
-static void release_callchain_buffers_rcu(struct rcu_head *head)
-{
-	struct callchain_cpus_entries *entries;
-	int cpu;
-
-	entries = container_of(head, struct callchain_cpus_entries, rcu_head);
-
-	for_each_possible_cpu(cpu)
-		kfree(entries->cpu_entries[cpu]);
-
-	kfree(entries);
-}
-
-static void release_callchain_buffers(void)
-{
-	struct callchain_cpus_entries *entries;
-
-	entries = callchain_cpus_entries;
-	rcu_assign_pointer(callchain_cpus_entries, NULL);
-	call_rcu(&entries->rcu_head, release_callchain_buffers_rcu);
-}
-
-static int alloc_callchain_buffers(void)
-{
-	int cpu;
-	int size;
-	struct callchain_cpus_entries *entries;
-
-	/*
-	 * We can't use the percpu allocation API for data that can be
-	 * accessed from NMI. Use a temporary manual per cpu allocation
-	 * until that gets sorted out.
-	 */
-	size = offsetof(struct callchain_cpus_entries, cpu_entries[nr_cpu_ids]);
-
-	entries = kzalloc(size, GFP_KERNEL);
-	if (!entries)
-		return -ENOMEM;
-
-	size = sizeof(struct perf_callchain_entry) * PERF_NR_CONTEXTS;
-
-	for_each_possible_cpu(cpu) {
-		entries->cpu_entries[cpu] = kmalloc_node(size, GFP_KERNEL,
-							 cpu_to_node(cpu));
-		if (!entries->cpu_entries[cpu])
-			goto fail;
-	}
-
-	rcu_assign_pointer(callchain_cpus_entries, entries);
-
-	return 0;
-
-fail:
-	for_each_possible_cpu(cpu)
-		kfree(entries->cpu_entries[cpu]);
-	kfree(entries);
-
-	return -ENOMEM;
-}
-
-static int get_callchain_buffers(void)
-{
-	int err = 0;
-	int count;
-
-	mutex_lock(&callchain_mutex);
-
-	count = atomic_inc_return(&nr_callchain_events);
-	if (WARN_ON_ONCE(count < 1)) {
-		err = -EINVAL;
-		goto exit;
-	}
-
-	if (count > 1) {
-		/* If the allocation failed, give up */
-		if (!callchain_cpus_entries)
-			err = -ENOMEM;
-		goto exit;
-	}
-
-	err = alloc_callchain_buffers();
-	if (err)
-		release_callchain_buffers();
-exit:
-	mutex