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
  ...

1 files changed, 53 insertions, 243 deletions

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)