perf: Reduce perf_disable() usage

Since the current perf_disable() usage is only an optimization,
remove it for now. This eases the removal of the __weak
hw_perf_enable() interface.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus <paulus@samba.org>
Cc: stephane eranian <eranian@googlemail.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Lin Ming <ming.m.lin@intel.com>
Cc: Yanmin <yanmin_zhang@linux.intel.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: David Miller <davem@davemloft.net>
Cc: Michael Cree <mcree@orcon.net.nz>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

8 files changed, 48 insertions, 59 deletions

diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index f62f9db35db3..afc92c580d18 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -277,6 +277,8 @@ armpmu_enable(struct perf_event *event)
         int idx;
         int err = 0;
 
+        perf_disable();
+
         /* If we don't have a space for the counter then finish early. */
         idx = armpmu->get_event_idx(cpuc, hwc);
         if (idx < 0) {
@@ -303,6 +305,7 @@ armpmu_enable(struct perf_event *event)
         perf_event_update_userpage(event);
 
 out:
+        perf_enable();
         return err;
 }
 
diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c
index 19131b2614b9..c1408821dbc2 100644
--- a/arch/powerpc/kernel/perf_event.c
+++ b/arch/powerpc/kernel/perf_event.c
@@ -861,6 +861,7 @@ void power_pmu_start_txn(struct pmu *pmu)
 {
         struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
+        perf_disable();
         cpuhw->group_flag |= PERF_EVENT_TXN;
         cpuhw->n_txn_start = cpuhw->n_events;
 }
@@ -875,6 +876,7 @@ void power_pmu_cancel_txn(struct pmu *pmu)
         struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
         cpuhw->group_flag &= ~PERF_EVENT_TXN;
+        perf_enable();
 }
 
 /*
@@ -901,6 +903,7 @@ int power_pmu_commit_txn(struct pmu *pmu)
                 cpuhw->event[i]->hw.config = cpuhw->events[i];
 
         cpuhw->group_flag &= ~PERF_EVENT_TXN;
+        perf_enable();
         return 0;
 }
 
diff --git a/arch/powerpc/kernel/perf_event_fsl_emb.c b/arch/powerpc/kernel/perf_event_fsl_emb.c
index ea6a804e43fd..9bc84a7fd901 100644
--- a/arch/powerpc/kernel/perf_event_fsl_emb.c
+++ b/arch/powerpc/kernel/perf_event_fsl_emb.c
@@ -262,7 +262,7 @@ static int collect_events(struct perf_event *group, int max_count,
         return n;
 }
 
-/* perf must be disabled, context locked on entry */
+/* context locked on entry */
 static int fsl_emb_pmu_enable(struct perf_event *event)
 {
         struct cpu_hw_events *cpuhw;
@@ -271,6 +271,7 @@ static int fsl_emb_pmu_enable(struct perf_event *event)
         u64 val;
         int i;
 
+        perf_disable();
         cpuhw = &get_cpu_var(cpu_hw_events);
 
         if (event->hw.config & FSL_EMB_EVENT_RESTRICTED)
@@ -310,15 +311,17 @@ static int fsl_emb_pmu_enable(struct perf_event *event)
         ret = 0;
  out:
         put_cpu_var(cpu_hw_events);
+        perf_enable();
         return ret;
 }
 
-/* perf must be disabled, context locked on entry */
+/* context locked on entry */
 static void fsl_emb_pmu_disable(struct perf_event *event)
 {
         struct cpu_hw_events *cpuhw;
         int i = event->hw.idx;
 
+        perf_disable();
         if (i < 0)
                 goto out;
 
@@ -346,6 +349,7 @@ static void fsl_emb_pmu_disable(struct perf_event *event)
         cpuhw->n_events--;
 
  out:
+        perf_enable();
         put_cpu_var(cpu_hw_events);
 }
 
diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c
index 8cb206597e0c..d042989ceb45 100644
--- a/arch/sh/kernel/perf_event.c
+++ b/arch/sh/kernel/perf_event.c
@@ -230,11 +230,14 @@ static int sh_pmu_enable(struct perf_event *event)
         struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
         struct hw_perf_event *hwc = &event->hw;
         int idx = hwc->idx;
+        int ret = -EAGAIN;
+
+        perf_disable();
 
         if (test_and_set_bit(idx, cpuc->used_mask)) {
                 idx = find_first_zero_bit(cpuc->used_mask, sh_pmu->num_events);
                 if (idx == sh_pmu->num_events)
-                        return -EAGAIN;
+                        goto out;
 
                 set_bit(idx, cpuc->used_mask);
                 hwc->idx = idx;
@@ -248,8 +251,10 @@ static int sh_pmu_enable(struct perf_event *event)
         sh_pmu->enable(hwc, idx);
 
         perf_event_update_userpage(event);
-
-        return 0;
+        ret = 0;
+out:
+        perf_enable();
+        return ret;
 }
 
 static void sh_pmu_read(struct perf_event *event)
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index bed4327f5a7a..d0131deeeaf6 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1113,6 +1113,7 @@ static void sparc_pmu_start_txn(struct pmu *pmu)
 {
         struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
+        perf_disable();
         cpuhw->group_flag |= PERF_EVENT_TXN;
 }
 
@@ -1126,6 +1127,7 @@ static void sparc_pmu_cancel_txn(struct pmu *pmu)
         struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
         cpuhw->group_flag &= ~PERF_EVENT_TXN;
+        perf_enable();
 }
 
 /*
@@ -1149,6 +1151,7 @@ static int sparc_pmu_commit_txn(struct pmu *pmu)
                 return -EAGAIN;
 
         cpuc->group_flag &= ~PERF_EVENT_TXN;
+        perf_enable();
         return 0;
 }
 
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 2c89264ee791..846070ce49c3 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -969,10 +969,11 @@ static int x86_pmu_enable(struct perf_event *event)
 
         hwc = &event->hw;
 
+        perf_disable();
         n0 = cpuc->n_events;
-        n = collect_events(cpuc, event, false);
-        if (n < 0)
-                return n;
+        ret = n = collect_events(cpuc, event, false);
+        if (ret < 0)
+                goto out;
 
         /*
          * If group events scheduling transaction was started,
@@ -980,23 +981,26 @@ static int x86_pmu_enable(struct perf_event *event)
          * at commit time(->commit_txn) as a whole
          */
         if (cpuc->group_flag & PERF_EVENT_TXN)
-                goto out;
+                goto done_collect;
 
         ret = x86_pmu.schedule_events(cpuc, n, assign);
         if (ret)
-                return ret;
+                goto out;
         /*
          * copy new assignment, now we know it is possible
          * will be used by hw_perf_enable()
          */
         memcpy(cpuc->assign, assign, n*sizeof(int));
 
-out:
+done_collect:
         cpuc->n_events = n;
         cpuc->n_added += n - n0;
         cpuc->n_txn += n - n0;
 
-        return 0;
+        ret = 0;
+out:
+        perf_enable();
+        return ret;
 }
 
 static int x86_pmu_start(struct perf_event *event)
@@ -1432,6 +1436,7 @@ static void x86_pmu_start_txn(struct pmu *pmu)
 {
         struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
+        perf_disable();
         cpuc->group_flag |= PERF_EVENT_TXN;
         cpuc->n_txn = 0;
 }
@@ -1451,6 +1456,7 @@ static void x86_pmu_cancel_txn(struct pmu *pmu)
          */
         cpuc->n_added -= cpuc->n_txn;
         cpuc->n_events -= cpuc->n_txn;
+        perf_enable();
 }
 
 /*
@@ -1480,7 +1486,7 @@ static int x86_pmu_commit_txn(struct pmu *pmu)
         memcpy(cpuc->assign, assign, n*sizeof(int));
 
         cpuc->group_flag &= ~PERF_EVENT_TXN;
-
+        perf_enable();
         return 0;
 }
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index ab72f56eb372..243286a8ded7 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -564,26 +564,26 @@ struct pmu {
         struct list_head                entry;
 
         /*
-         * Should return -ENOENT when the @event doesn't match this pmu
+         * Should return -ENOENT when the @event doesn't match this PMU.
          */
         int (*event_init)               (struct perf_event *event);
 
-        int (*enable)                   (struct perf_event *event);
+        int  (*enable)                  (struct perf_event *event);
         void (*disable)                 (struct perf_event *event);
-        int (*start)                    (struct perf_event *event);
+        int  (*start)                   (struct perf_event *event);
         void (*stop)                    (struct perf_event *event);
         void (*read)                    (struct perf_event *event);
         void (*unthrottle)              (struct perf_event *event);
 
         /*
-         * Group events scheduling is treated as a transaction, add group
-         * events as a whole and perform one schedulability test. If the test
-         * fails, roll back the whole group
+         * Group events scheduling is treated as a transaction, add
+         * group events as a whole and perform one schedulability test.
+         * If the test fails, roll back the whole group
          */
 
         /*
-         * Start the transaction, after this ->enable() doesn't need
-         * to do schedulability tests.
+         * Start the transaction, after this ->enable() doesn't need to
+         * do schedulability tests.
          */
         void (*start_txn)       (struct pmu *pmu);
         /*
@@ -594,8 +594,8 @@ struct pmu {
          */
         int  (*commit_txn)      (struct pmu *pmu);
         /*
-         * Will cancel the transaction, assumes ->disable() is called for
-         * each successfull ->enable() during the transaction.
+         * Will cancel the transaction, assumes ->disable() is called
+         * for each successfull ->enable() during the transaction.
          */
         void (*cancel_txn)      (struct pmu *pmu);
 };
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 149ca18371b7..9a98ce953561 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -478,11 +478,6 @@ static void __perf_event_remove_from_context(void *info)
                 return;
 
         raw_spin_lock(&ctx->lock);
-        /*
-         * Protect the list operation against NMI by disabling the
-         * events on a global level.
-         */
-        perf_disable();
 
         event_sched_out(event, cpuctx, ctx);
 
@@ -498,7 +493,6 @@ static void __perf_event_remove_from_context(void *info)
                             perf_max_events - perf_reserved_percpu);
         }
 
-        perf_enable();
         raw_spin_unlock(&ctx->lock);
 }
 
@@ -803,12 +797,6 @@ static void __perf_install_in_context(void *info)
         ctx->is_active = 1;
         update_context_time(ctx);
 
-        /*
-         * Protect the list operation against NMI by disabling the
-         * events on a global level. NOP for non NMI based events.
-         */
-        perf_disable();
-
         add_event_to_ctx(event, ctx);
 
         if (event->cpu != -1 && event->cpu != smp_processor_id())
@@ -850,8 +838,6 @@ static void __perf_install_in_context(void *info)
                 cpuctx->max_pertask--;
 
 unlock:
-        perf_enable();
-
         raw_spin_unlock(&ctx->lock);
 }
 
@@ -972,12 +958,10 @@ static void __perf_event_enable(void *info)
         if (!group_can_go_on(event, cpuctx, 1)) {
                 err = -EEXIST;
         } else {
-                perf_disable();
                 if (event == leader)
                         err = group_sched_in(event, cpuctx, ctx);
                 else
                         err = event_sched_in(event, cpuctx, ctx);
-                perf_enable();
         }
 
         if (err) {
@@ -1090,9 +1074,8 @@ static void ctx_sched_out(struct perf_event_context *ctx,
                 goto out;
         update_context_time(ctx);
 
-        perf_disable();
         if (!ctx->nr_active)
-                goto out_enable;
+                goto out;
 
         if (event_type & EVENT_PINNED) {
                 list_for_each_entry(event, &ctx->pinned_groups, group_entry)
@@ -1103,9 +1086,6 @@ static void ctx_sched_out(struct perf_event_context *ctx,
                 list_for_each_entry(event, &ctx->flexible_groups, group_entry)
                         group_sched_out(event, cpuctx, ctx);
         }
-
- out_enable:
-        perf_enable();
 out:
         raw_spin_unlock(&ctx->lock);
 }
@@ -1364,8 +1344,6 @@ ctx_sched_in(struct perf_event_context *ctx,
 
         ctx->timestamp = perf_clock();
 
-        perf_disable();
-
         /*
          * First go through the list and put on any pinned groups
          * in order to give them the best chance of going on.
@@ -1377,7 +1355,6 @@ ctx_sched_in(struct perf_event_context *ctx,
         if (event_type & EVENT_FLEXIBLE)
                 ctx_flexible_sched_in(ctx, cpuctx);
 
-        perf_enable();
 out:
         raw_spin_unlock(&ctx->lock);
 }
@@ -1425,8 +1402,6 @@ void perf_event_task_sched_in(struct task_struct *task)
         if (cpuctx->task_ctx == ctx)
                 return;
 
-        perf_disable();
-
         /*
          * We want to keep the following priority order:
          * cpu pinned (that don't need to move), task pinned,
@@ -1439,8 +1414,6 @@ void perf_event_task_sched_in(struct task_struct *task)
         ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE);
 
         cpuctx->task_ctx = ctx;
-
-        perf_enable();
 }
 
 #define MAX_INTERRUPTS (~0ULL)
@@ -1555,11 +1528,9 @@ static void perf_adjust_period(struct perf_event *event, u64 nsec, u64 count)
         hwc->sample_period = sample_period;
 
         if (local64_read(&hwc->period_left) > 8*sample_period) {
-                perf_disable();
                 perf_event_stop(event);
                 local64_set(&hwc->period_left, 0);
                 perf_event_start(event);
-                perf_enable();
         }
 }
 
@@ -1588,15 +1559,12 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx)
                  */
                 if (interrupts == MAX_INTERRUPTS) {
                         perf_log_throttle(event, 1);
-                        perf_disable();
                         event->pmu->unthrottle(event);
-                        perf_enable();
                 }
 
                 if (!event->attr.freq || !event->attr.sample_freq)
                         continue;
 
-                perf_disable();
                 event->pmu->read(event);
                 now = local64_read(&event->count);
                 delta = now - hwc->freq_count_stamp;
@@ -1604,7 +1572,6 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx)
 
                 if (delta > 0)
                         perf_adjust_period(event, TICK_NSEC, delta);
-                perf_enable();
         }
         raw_spin_unlock(&ctx->lock);
 }
@@ -1647,7 +1614,6 @@ void perf_event_task_tick(struct task_struct *curr)
         if (!rotate)
                 return;
 
-        perf_disable();
         cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
         if (ctx)
                 task_ctx_sched_out(ctx, EVENT_FLEXIBLE);
@@ -1659,7 +1625,6 @@ void perf_event_task_tick(struct task_struct *curr)
         cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE);
         if (ctx)
                 task_ctx_sched_in(curr, EVENT_FLEXIBLE);
-        perf_enable();
 }
 
 static int event_enable_on_exec(struct perf_event *event,