Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (106 commits)
  perf kvm: Fix copy & paste error in description
  perf script: Kill script_spec__delete
  perf top: Fix a memory leak
  perf stat: Introduce get_ratio_color() helper
  perf session: Remove impossible condition check
  perf tools: Fix feature-bits rework fallout, remove unused variable
  perf script: Add generic perl handler to process events
  perf tools: Use for_each_set_bit() to iterate over feature flags
  perf tools: Unify handling of features when writing feature section
  perf report: Accept fifos as input file
  perf tools: Moving code in some files
  perf tools: Fix out-of-bound access to struct perf_session
  perf tools: Continue processing header on unknown features
  perf tools: Improve macros for struct feature_ops
  perf: builtin-record: Document and check that mmap_pages must be a power of two.
  perf: builtin-record: Provide advice if mmap'ing fails with EPERM.
  perf tools: Fix truncated annotation
  perf script: look up thread using tid instead of pid
  perf tools: Look up thread names for system wide profiling
  perf tools: Fix comm for processes with named threads
  ...

12 files changed, 476 insertions, 306 deletions

diff --git a/kernel/events/Makefile b/kernel/events/Makefile
index 89e5e8aa4c36..22d901f9caf4 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 000000000000..057e24b665cf
--- /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 fc0e7ff11dda..890eb02c2f21 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_unlock(&callchain_mutex);
-
-        return err;
-}
-
-static void put_callchain_buffers(void)
-{
-        if (atomic_dec_and_mutex_lock(&nr_callchain_events, &callchain_mutex)) {
-                release_callchain_buffers();
-                mutex_unlock(&callchain_mutex);
-        }
-}
-
-static int get_recursion_context(int *recursion)
-{
-        int rctx;
-
-        if (in_nmi())
-                rctx = 3;
-        else if (in_irq())
-                rctx = 2;
-        else if (in_softirq())
-                rctx = 1;
-        else
-                rctx = 0;
-
-        if (recursion[rctx])
-                return -1;
-
-        recursion[rctx]++;
-        barrier();
-
-        return rctx;
-}
-
-static inline void put_recursion_context(int *recursion, int rctx)
-{
-        barrier();
-        recursion[rctx]--;
-}
-
-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);
-}
-
-static 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;
-}
-
-/*
  * Initialize the perf_event context in a task_struct:
  */
 static void __perf_event_init_context(struct perf_event_context *ctx)
@@ -2946,7 +2748,7 @@ static void free_event(struct perf_event *event)
 
         if (!event->parent) {
                 if (event->attach_state & PERF_ATTACH_TASK)
-                        jump_label_dec(&perf_sched_events);
+                        jump_label_dec_deferred(&perf_sched_events);
                 if (event->attr.mmap || event->attr.mmap_data)
                         atomic_dec(&nr_mmap_events);
                 if (event->attr.comm)
@@ -2957,7 +2759,7 @@ static void free_event(struct perf_event *event)
                         put_callchain_buffers();
                 if (is_cgroup_event(event)) {
                         atomic_dec(&per_cpu(perf_cgroup_events, event->cpu));
-                        jump_label_dec(&perf_sched_events);
+                        jump_label_dec_deferred(&perf_sched_events);
                 }
         }
 
@@ -4820,7 +4622,6 @@ static void perf_swevent_overflow(struct perf_event *event, u64 overflow,
         struct hw_perf_event *hwc = &event->hw;
         int throttle = 0;
 
-        data->period = event->hw.last_period;
         if (!overflow)
                 overflow = perf_swevent_set_period(event);
 
@@ -4854,6 +4655,12 @@ static void perf_swevent_event(struct perf_event *event, u64 nr,
         if (!is_sampling_event(event))
                 return;
 
+        if ((event->attr.sample_type & PERF_SAMPLE_PERIOD) && !event->attr.freq) {
+                data->period = nr;
+                return perf_swevent_overflow(event, 1, data, regs);
+        } else
+                data->period = event->hw.last_period;
+
         if (nr == 1 && hwc->sample_period == 1 && !event->attr.freq)
                 return perf_swevent_overflow(event, 1, data, regs);
 
@@ -5981,7 +5788,7 @@ done:
 
         if (!event->parent) {
                 if (event->attach_state & PERF_ATTACH_TASK)
-                        jump_label_inc(&perf_sched_events);
+                        jump_label_inc(&perf_sched_events.key);
                 if (event->attr.mmap || event->attr.mmap_data)
                         atomic_inc(&nr_mmap_events);
                 if (event->attr.comm)
@@ -6219,7 +6026,7 @@ SYSCALL_DEFINE5(perf_event_open,
                  * - that may need work on context switch
                  */
                 atomic_inc(&per_cpu(perf_cgroup_events, event->cpu));
-                jump_label_inc(&perf_sched_events);
+                jump_label_inc(&perf_sched_events.key);
         }
 
         /*
@@ -7065,6 +6872,9 @@ void __init perf_event_init(void)
 
         ret = init_hw_breakpoint();
         WARN(ret, "hw_breakpoint initialization failed with: %d", ret);
+
+        /* do not patch jump label more than once per second */
+        jump_label_rate_limit(&perf_sched_events, HZ);
 }
 
 static int __init perf_event_sysfs_init(void)
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 64568a699375..b0b107f90afc 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -1,6 +1,10 @@
 #ifndef _KERNEL_EVENTS_INTERNAL_H
 #define _KERNEL_EVENTS_INTERNAL_H
 
+#include <linux/hardirq.h>
+
+/* Buffer handling */
+
 #define RING_BUFFER_WRITABLE            0x01
 
 struct ring_buffer {
@@ -67,7 +71,7 @@ static inline int page_order(struct ring_buffer *rb)
 }
 #endif
 
-static unsigned long perf_data_size(struct ring_buffer *rb)
+static inline unsigned long perf_data_size(struct ring_buffer *rb)
 {
         return rb->nr_pages << (PAGE_SHIFT + page_order(rb));
 }
@@ -96,4 +100,37 @@ __output_copy(struct perf_output_handle *handle,
         } while (len);
 }
 
+/* Callchain handling */
+extern struct perf_callchain_entry *perf_callchain(struct pt_regs *regs);
+extern int get_callchain_buffers(void);
+extern void put_callchain_buffers(void);
+
+static inline int get_recursion_context(int *recursion)
+{
+        int rctx;
+
+        if (in_nmi())
+                rctx = 3;
+        else if (in_irq())
+                rctx = 2;
+        else if (in_softirq())
+                rctx = 1;
+        else
+                rctx = 0;
+
+        if (recursion[rctx])
+                return -1;
+
+        recursion[rctx]++;
+        barrier();
+
+        return rctx;
+}
+
+static inline void put_recursion_context(int *recursion, int rctx)
+{
+        barrier();
+        recursion[rctx]--;
+}
+
 #endif /* _KERNEL_EVENTS_INTERNAL_H */
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 66ff7109f697..30c3c7708132 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -72,15 +72,46 @@ void jump_label_inc(struct jump_label_key *key)
         jump_label_unlock();
 }
 
-void jump_label_dec(struct jump_label_key *key)
+static void __jump_label_dec(struct jump_label_key *key,
+                unsigned long rate_limit, struct delayed_work *work)
 {
         if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex))
                 return;
 
-        jump_label_update(key, JUMP_LABEL_DISABLE);
+        if (rate_limit) {
+                atomic_inc(&key->enabled);
+                schedule_delayed_work(work, rate_limit);
+        } else
+                jump_label_update(key, JUMP_LABEL_DISABLE);
+
         jump_label_unlock();
 }
 
+static void jump_label_update_timeout(struct work_struct *work)
+{
+        struct jump_label_key_deferred *key =
+                container_of(work, struct jump_label_key_deferred, work.work);
+        __jump_label_dec(&key->key, 0, NULL);
+}
+
+void jump_label_dec(struct jump_label_key *key)
+{
+        __jump_label_dec(key, 0, NULL);
+}
+
+void jump_label_dec_deferred(struct jump_label_key_deferred *key)
+{
+        __jump_label_dec(&key->key, key->timeout, &key->work);
+}
+
+
+void jump_label_rate_limit(struct jump_label_key_deferred *key,
+                unsigned long rl)
+{
+        key->timeout = rl;
+        INIT_DELAYED_WORK(&key->work, jump_label_update_timeout);
+}
+
 static int addr_conflict(struct jump_entry *entry, void *start, void *end)
 {
         if (entry->code <= (unsigned long)end &&
@@ -111,7 +142,7 @@ static int __jump_label_text_reserved(struct jump_entry *iter_start,
  * running code can override this to make the non-live update case
  * cheaper.
  */
-void __weak arch_jump_label_transform_static(struct jump_entry *entry,
+void __weak __init_or_module arch_jump_label_transform_static(struct jump_entry *entry,
                                             enum jump_label_type type)
 {
         arch_jump_label_transform(entry, type); 
@@ -217,8 +248,13 @@ void jump_label_apply_nops(struct module *mod)
         if (iter_start == iter_stop)
                 return;
 
-        for (iter = iter_start; iter < iter_stop; iter++)
-                arch_jump_label_transform_static(iter, JUMP_LABEL_DISABLE);
+        for (iter = iter_start; iter < iter_stop; iter++) {
+                struct jump_label_key *iterk;
+
+                iterk = (struct jump_label_key *)(unsigned long)iter->key;
+                arch_jump_label_transform_static(iter, jump_label_enabled(iterk) ?
+                                JUMP_LABEL_ENABLE : JUMP_LABEL_DISABLE);
+        }
 }
 
 static int jump_label_add_module(struct module *mod)
@@ -258,8 +294,7 @@ static int jump_label_add_module(struct module *mod)
                 key->next = jlm;
 
                 if (jump_label_enabled(key))
-                        __jump_label_update(key, iter, iter_stop,
-                                            JUMP_LABEL_ENABLE);
+                        __jump_label_update(key, iter, iter_stop, JUMP_LABEL_ENABLE);
         }
 
         return 0;
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 8fb755132322..8889f7dd7c46 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -500,36 +500,32 @@ void get_usage_chars(struct lock_class *class, char usage[LOCK_USAGE_CHARS])
         usage[i] = '\0';
 }
 
-static int __print_lock_name(struct lock_class *class)
+static void __print_lock_name(struct lock_class *class)
 {
         char str[KSYM_NAME_LEN];
         const char *name;
 
         name = class->name;
-        if (!name)
-                name = __get_key_name(class->key, str);
-
-        return printk("%s", name);
-}
-
-static void print_lock_name(struct lock_class *class)
-{
-        char str[KSYM_NAME_LEN], usage[LOCK_USAGE_CHARS];
-        const char *name;
-
-        get_usage_chars(class, usage);
-
-        name = class->name;
         if (!name) {
                 name = __get_key_name(class->key, str);
-                printk(" (%s", name);
+                printk("%s", name);
         } else {
-                printk(" (%s", name);
+                printk("%s", name);
                 if (class->name_version > 1)
                         printk("#%d", class->name_version);
                 if (class->subclass)
                         printk("/%d", class->subclass);
         }
+}
+
+static void print_lock_name(struct lock_class *class)
+{
+        char usage[LOCK_USAGE_CHARS];
+
+        get_usage_chars(class, usage);
+
+        printk(" (");
+        __print_lock_name(class);
         printk("){%s}", usage);
 }
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a043d224adf6..91dc4bc8bf72 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -338,7 +338,8 @@ static DECLARE_WAIT_QUEUE_HEAD(trace_wait);
 /* trace_flags holds trace_options default values */
 unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
         TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME |
-        TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE;
+        TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE |
+        TRACE_ITER_IRQ_INFO;
 
 static int trace_stop_count;
 static DEFINE_RAW_SPINLOCK(tracing_start_lock);
@@ -426,6 +427,7 @@ static const char *trace_options[] = {
         "record-cmd",
         "overwrite",
         "disable_on_free",
+        "irq-info",
         NULL
 };
 
@@ -1843,6 +1845,33 @@ static void s_stop(struct seq_file *m, void *p)
         trace_event_read_unlock();
 }
 
+static void
+get_total_entries(struct trace_array *tr, unsigned long *total, unsigned long *entries)
+{
+        unsigned long count;
+        int cpu;
+
+        *total = 0;
+        *entries = 0;
+
+        for_each_tracing_cpu(cpu) {
+                count = ring_buffer_entries_cpu(tr->buffer, cpu);
+                /*
+                 * If this buffer has skipped entries, then we hold all
+                 * entries for the trace and we need to ignore the
+                 * ones before the time stamp.
+                 */
+                if (tr->data[cpu]->skipped_entries) {
+                        count -= tr->data[cpu]->skipped_entries;
+                        /* total is the same as the entries */
+                        *total += count;
+                } else
+                        *total += count +
+                                ring_buffer_overrun_cpu(tr->buffer, cpu);
+                *entries += count;
+        }
+}
+
 static void print_lat_help_header(struct seq_file *m)
 {
         seq_puts(m, "#                  _------=> CPU#            \n");
@@ -1855,12 +1884,35 @@ static void print_lat_help_header(struct seq_file *m)
         seq_puts(m, "#     \\   /      |||||  \\    |   /           \n");
 }
 
-static void print_func_help_header(struct seq_file *m)
+static void print_event_info(struct trace_array *tr, struct seq_file *m)
+{
+        unsigned long total;
+        unsigned long entries;
+
+        get_total_entries(tr, &total, &entries);
+        seq_printf(m, "# entries-in-buffer/entries-written: %lu/%lu   #P:%d\n",
+                   entries, total, num_online_cpus());
+        seq_puts(m, "#\n");
+}
+
+static void print_func_help_header(struct trace_array *tr, struct seq_file *m)
 {
-        seq_puts(m, "#           TASK-PID    CPU#    TIMESTAMP  FUNCTION\n");
+        print_event_info(tr, m);
+        seq_puts(m, "#           TASK-PID   CPU#      TIMESTAMP  FUNCTION\n");
         seq_puts(m, "#              | |       |          |         |\n");
 }
 
+static void print_func_help_header_irq(struct trace_array *tr, struct seq_file *m)
+{
+        print_event_info(tr, m);
+        seq_puts(m, "#                              _-----=> irqs-off\n");
+        seq_puts(m, "#                             / _----=> need-resched\n");
+        seq_puts(m, "#                            | / _---=> hardirq/softirq\n");
+        seq_puts(m, "#                            || / _--=> preempt-depth\n");
+        seq_puts(m, "#                            ||| /     delay\n");
+        seq_puts(m, "#           TASK-PID   CPU#  ||||    TIMESTAMP  FUNCTION\n");
+        seq_puts(m, "#              | |       |   ||||       |         |\n");
+}
 
 void
 print_trace_header(struct seq_file *m, struct trace_iterator *iter)
@@ -1869,32 +1921,14 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter)
         struct trace_array *tr = iter->tr;
         struct trace_array_cpu *data = tr->data[tr->cpu];
         struct tracer *type = current_trace;
-        unsigned long entries = 0;
-        unsigned long total = 0;
-        unsigned long count;
+        unsigned long entries;
+        unsigned long total;
         const char *name = "preemption";
-        int cpu;
 
         if (type)
                 name = type->name;
 
-
-        for_each_tracing_cpu(cpu) {
-                count = ring_buffer_entries_cpu(tr->buffer, cpu);
-                /*
-                 * If this buffer has skipped entries, then we hold all
-                 * entries for the trace and we need to ignore the
-                 * ones before the time stamp.
-                 */
-                if (tr->data[cpu]->skipped_entries) {
-                        count -= tr->data[cpu]->skipped_entries;
-                        /* total is the same as the entries */
-                        total += count;
-                } else
-                        total += count +
-                                ring_buffer_overrun_cpu(tr->buffer, cpu);
-                entries += count;
-        }
+        get_total_entries(tr, &total, &entries);
 
         seq_printf(m, "# %s latency trace v1.1.5 on %s\n",
                    name, UTS_RELEASE);
@@ -2140,6 +2174,21 @@ enum print_line_t print_trace_line(struct trace_iterator *iter)
         return print_trace_fmt(iter);
 }
 
+void trace_latency_header(struct seq_file *m)
+{
+        struct trace_iterator *iter = m->private;
+
+        /* print nothing if the buffers are empty */
+        if (trace_empty(iter))
+                return;
+
+        if (iter->iter_flags & TRACE_FILE_LAT_FMT)
+                print_trace_header(m, iter);
+
+        if (!(trace_flags & TRACE_ITER_VERBOSE))
+                print_lat_help_header(m);
+}
+
 void trace_default_header(struct seq_file *m)
 {
         struct trace_iterator *iter = m->private;
@@ -2155,8 +2204,12 @@ void trace_default_header(struct seq_file *m)
                 if (!(trace_flags & TRACE_ITER_VERBOSE))
                         print_lat_help_header(m);
         } else {
-                if (!(trace_flags & TRACE_ITER_VERBOSE))
-                        print_func_help_header(m);
+                if (!(trace_flags & TRACE_ITER_VERBOSE)) {
+                        if (trace_flags & TRACE_ITER_IRQ_INFO)
+                                print_func_help_header_irq(iter->tr, m);
+                        else
+                                print_func_help_header(iter->tr, m);
+                }
         }
 }
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 092e1f8d18dc..2c2657462ac3 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -370,6 +370,7 @@ void trace_graph_function(struct trace_array *tr,
                     unsigned long ip,
                     unsigned long parent_ip,
                     unsigned long flags, int pc);
+void trace_latency_header(struct seq_file *m);
 void trace_default_header(struct seq_file *m);
 void print_trace_header(struct seq_file *m, struct trace_iterator *iter);
 int trace_empty(struct trace_iterator *iter);
@@ -654,6 +655,7 @@ enum trace_iterator_flags {
         TRACE_ITER_RECORD_CMD           = 0x100000,
         TRACE_ITER_OVERWRITE            = 0x200000,
         TRACE_ITER_STOP_ON_FREE         = 0x400000,
+        TRACE_ITER_IRQ_INFO             = 0x800000,
 };
 
 /*
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 95dc31efd6dd..f04cc3136bd3 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -27,6 +27,12 @@
 #include "trace.h"
 #include "trace_output.h"
 
+#define DEFAULT_SYS_FILTER_MESSAGE                                      \
+        "### global filter ###\n"                                       \
+        "# Use this to set filters for multiple events.\n"              \
+        "# Only events with the given fields will be affected.\n"       \
+        "# If no events are modified, an error message will be displayed here"
+
 enum filter_op_ids
 {
         OP_OR,
@@ -646,7 +652,7 @@ void print_subsystem_event_filter(struct event_subsystem *system,
         if (filter && filter->filter_string)
                 trace_seq_printf(s, "%s\n", filter->filter_string);
         else
-                trace_seq_printf(s, "none\n");
+                trace_seq_printf(s, DEFAULT_SYS_FILTER_MESSAGE "\n");
         mutex_unlock(&event_mutex);
 }
 
@@ -1838,7 +1844,10 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
         if (!filter)
                 goto out;
 
-        replace_filter_string(filter, filter_string);
+        /* System filters just show a default message */
+        kfree(filter->filter_string);
+        filter->filter_string = NULL;
+
         /*
          * No event actually uses the system filter
          * we can free it without synchronize_sched().
@@ -1848,14 +1857,12 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
 
         parse_init(ps, filter_ops, filter_string);
         err = filter_parse(ps);
-        if (err) {
-                append_filter_err(ps, system->filter);
-                goto out;
-        }
+        if (err)
+                goto err_filter;
 
         err = replace_system_preds(system, ps, filter_string);
         if (err)
-                append_filter_err(ps, system->filter);
+                goto err_filter;
 
 out:
         filter_opstack_clear(ps);
@@ -1865,6 +1872,11 @@ out_unlock:
         mutex_unlock(&event_mutex);
 
         return err;
+
+err_filter:
+        replace_filter_string(filter, filter_string);
+        append_filter_err(ps, system->filter);
+        goto out;
 }
 
 #ifdef CONFIG_PERF_EVENTS
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 20dad0d7a163..99d20e920368 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -280,9 +280,20 @@ static enum print_line_t irqsoff_print_line(struct trace_iterator *iter)
 }
 
 static void irqsoff_graph_return(struct ftrace_graph_ret *trace) { }
-static void irqsoff_print_header(struct seq_file *s) { }
 static void irqsoff_trace_open(struct trace_iterator *iter) { }
 static void irqsoff_trace_close(struct trace_iterator *iter) { }
+
+#ifdef CONFIG_FUNCTION_TRACER
+static void irqsoff_print_header(struct seq_file *s)
+{
+        trace_default_header(s);
+}
+#else
+static void irqsoff_print_header(struct seq_file *s)
+{
+        trace_latency_header(s);
+}
+#endif /* CONFIG_FUNCTION_TRACER */
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
 /*
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 51999309a6cf..0d6ff3555942 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -627,11 +627,23 @@ int trace_print_context(struct trace_iterator *iter)
         unsigned long usec_rem = do_div(t, USEC_PER_SEC);
         unsigned long secs = (unsigned long)t;
         char comm[TASK_COMM_LEN];
+        int ret;
 
         trace_find_cmdline(entry->pid, comm);
 
-        return trace_seq_printf(s, "%16s-%-5d [%03d] %5lu.%06lu: ",
-                                comm, entry->pid, iter->cpu, secs, usec_rem);
+        ret = trace_seq_printf(s, "%16s-%-5d [%03d] ",
+                               comm, entry->pid, iter->cpu);
+        if (!ret)
+                return 0;
+
+        if (trace_flags & TRACE_ITER_IRQ_INFO) {
+                ret = trace_print_lat_fmt(s, entry);
+                if (!ret)
+                        return 0;
+        }
+
+        return trace_seq_printf(s, " %5lu.%06lu: ",
+                                secs, usec_rem);
 }
 
 int trace_print_lat_context(struct trace_iterator *iter)
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index e4a70c0c71b6..ff791ea48b57 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -280,9 +280,20 @@ static enum print_line_t wakeup_print_line(struct trace_iterator *iter)
 }
 
 static void wakeup_graph_return(struct ftrace_graph_ret *trace) { }
-static void wakeup_print_header(struct seq_file *s) { }
 static void wakeup_trace_open(struct trace_iterator *iter) { }
 static void wakeup_trace_close(struct trace_iterator *iter) { }
+
+#ifdef CONFIG_FUNCTION_TRACER
+static void wakeup_print_header(struct seq_file *s)
+{
+        trace_default_header(s);
+}
+#else
+static void wakeup_print_header(struct seq_file *s)
+{
+        trace_latency_header(s);
+}
+#endif /* CONFIG_FUNCTION_TRACER */
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
 /*