Merge branch 'perf/fast' into perf/core

Merge reason: Lets ready it for v3.4

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

2 files changed, 47 insertions, 13 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 32b48c88971..de859fb4038 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3208,10 +3208,6 @@ int perf_event_task_disable(void)
         return 0;
 }
 
-#ifndef PERF_EVENT_INDEX_OFFSET
-# define PERF_EVENT_INDEX_OFFSET 0
-#endif
-
 static int perf_event_index(struct perf_event *event)
 {
         if (event->hw.state & PERF_HES_STOPPED)
@@ -3220,21 +3216,26 @@ static int perf_event_index(struct perf_event *event)
         if (event->state != PERF_EVENT_STATE_ACTIVE)
                 return 0;
 
-        return event->hw.idx + 1 - PERF_EVENT_INDEX_OFFSET;
+        return event->pmu->event_idx(event);
 }
 
 static void calc_timer_values(struct perf_event *event,
+                                u64 *now,
                                 u64 *enabled,
                                 u64 *running)
 {
-        u64 now, ctx_time;
+        u64 ctx_time;
 
-        now = perf_clock();
-        ctx_time = event->shadow_ctx_time + now;
+        *now = perf_clock();
+        ctx_time = event->shadow_ctx_time + *now;
         *enabled = ctx_time - event->tstamp_enabled;
         *running = ctx_time - event->tstamp_running;
 }
 
+void __weak perf_update_user_clock(struct perf_event_mmap_page *userpg, u64 now)
+{
+}
+
 /*
  * 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
@@ -3244,7 +3245,7 @@ void perf_event_update_userpage(struct perf_event *event)
 {
         struct perf_event_mmap_page *userpg;
         struct ring_buffer *rb;
-        u64 enabled, running;
+        u64 enabled, running, now;
 
         rcu_read_lock();
         /*
@@ -3256,7 +3257,7 @@ void perf_event_update_userpage(struct perf_event *event)
          * because of locking issue as we can be called in
          * NMI context
          */
-        calc_timer_values(event, &enabled, &running);
+        calc_timer_values(event, &now, &enabled, &running);
         rb = rcu_dereference(event->rb);
         if (!rb)
                 goto unlock;
@@ -3272,7 +3273,7 @@ void perf_event_update_userpage(struct perf_event *event)
         barrier();
         userpg->index = perf_event_index(event);
         userpg->offset = perf_event_count(event);
-        if (event->state == PERF_EVENT_STATE_ACTIVE)
+        if (userpg->index)
                 userpg->offset -= local64_read(&event->hw.prev_count);
 
         userpg->time_enabled = enabled +
@@ -3281,6 +3282,8 @@ void perf_event_update_userpage(struct perf_event *event)
         userpg->time_running = running +
                         atomic64_read(&event->child_total_time_running);
 
+        perf_update_user_clock(userpg, now);
+
         barrier();
         ++userpg->lock;
         preempt_enable();
@@ -3538,6 +3541,8 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
         event->mmap_user = get_current_user();
         vma->vm_mm->pinned_vm += event->mmap_locked;
 
+        perf_event_update_userpage(event);
+
 unlock:
         if (!ret)
                 atomic_inc(&event->mmap_count);
@@ -3769,7 +3774,7 @@ static void perf_output_read_group(struct perf_output_handle *handle,
 static void perf_output_read(struct perf_output_handle *handle,
                              struct perf_event *event)
 {
-        u64 enabled = 0, running = 0;
+        u64 enabled = 0, running = 0, now;
         u64 read_format = event->attr.read_format;
 
         /*
@@ -3782,7 +3787,7 @@ static void perf_output_read(struct perf_output_handle *handle,
          * NMI context
          */
         if (read_format & PERF_FORMAT_TOTAL_TIMES)
-                calc_timer_values(event, &enabled, &running);
+                calc_timer_values(event, &now, &enabled, &running);
 
         if (event->attr.read_format & PERF_FORMAT_GROUP)
                 perf_output_read_group(handle, event, enabled, running);
@@ -4994,6 +4999,11 @@ static int perf_swevent_init(struct perf_event *event)
         return 0;
 }
 
+static int perf_swevent_event_idx(struct perf_event *event)
+{
+        return 0;
+}
+
 static struct pmu perf_swevent = {
         .task_ctx_nr    = perf_sw_context,
 
@@ -5003,6 +5013,8 @@ static struct pmu perf_swevent = {
         .start          = perf_swevent_start,
         .stop           = perf_swevent_stop,
         .read           = perf_swevent_read,
+
+        .event_idx      = perf_swevent_event_idx,
 };
 
 #ifdef CONFIG_EVENT_TRACING
@@ -5089,6 +5101,8 @@ static struct pmu perf_tracepoint = {
         .start          = perf_swevent_start,
         .stop           = perf_swevent_stop,
         .read           = perf_swevent_read,
+
+        .event_idx      = perf_swevent_event_idx,
 };
 
 static inline void perf_tp_register(void)
@@ -5308,6 +5322,8 @@ static struct pmu perf_cpu_clock = {
         .start          = cpu_clock_event_start,
         .stop           = cpu_clock_event_stop,
         .read           = cpu_clock_event_read,
+
+        .event_idx      = perf_swevent_event_idx,
 };
 
 /*
@@ -5380,6 +5396,8 @@ static struct pmu perf_task_clock = {
         .start          = task_clock_event_start,
         .stop           = task_clock_event_stop,
         .read           = task_clock_event_read,
+
+        .event_idx      = perf_swevent_event_idx,
 };
 
 static void perf_pmu_nop_void(struct pmu *pmu)
@@ -5407,6 +5425,11 @@ static void perf_pmu_cancel_txn(struct pmu *pmu)
         perf_pmu_enable(pmu);
 }
 
+static int perf_event_idx_default(struct perf_event *event)
+{
+        return event->hw.idx + 1;
+}
+
 /*
  * Ensures all contexts with the same task_ctx_nr have the same
  * pmu_cpu_context too.
@@ -5493,6 +5516,7 @@ static int pmu_dev_alloc(struct pmu *pmu)
         if (!pmu->dev)
                 goto out;
 
+        pmu->dev->groups = pmu->attr_groups;
         device_initialize(pmu->dev);
         ret = dev_set_name(pmu->dev, "%s", pmu->name);
         if (ret)
@@ -5596,6 +5620,9 @@ got_cpu_context:
                 pmu->pmu_disable = perf_pmu_nop_void;
         }
 
+        if (!pmu->event_idx)
+                pmu->event_idx = perf_event_idx_default;
+
         list_add_rcu(&pmu->entry, &pmus);
         ret = 0;
 unlock:
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index b7971d6f38b..b0309f76d77 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -613,6 +613,11 @@ static void hw_breakpoint_stop(struct perf_event *bp, int flags)
         bp->hw.state = PERF_HES_STOPPED;
 }
 
+static int hw_breakpoint_event_idx(struct perf_event *bp)
+{
+        return 0;
+}
+
 static struct pmu perf_breakpoint = {
         .task_ctx_nr    = perf_sw_context, /* could eventually get its own */
 
@@ -622,6 +627,8 @@ static struct pmu perf_breakpoint = {
         .start          = hw_breakpoint_start,
         .stop           = hw_breakpoint_stop,
         .read           = hw_breakpoint_pmu_read,
+
+        .event_idx      = hw_breakpoint_event_idx,
 };
 
 int __init init_hw_breakpoint(void)