perf: Rework the PMU methods

Replace pmu::{enable,disable,start,stop,unthrottle} with
pmu::{add,del,start,stop}, all of which take a flags argument.

The new interface extends the capability to stop a counter while
keeping it scheduled on the PMU. We replace the throttled state with
the generic stopped state.

This also allows us to efficiently stop/start counters over certain
code paths (like IRQ handlers).

It also allows scheduling a counter without it starting, allowing for
a generic frozen state (useful for rotating stopped counters).

The stopped state is implemented in two different ways, depending on
how the architecture implemented the throttled state:

 1) We disable the counter:
    a) the pmu has per-counter enable bits, we flip that
    b) we program a NOP event, preserving the counter state

 2) We store the counter state and ignore all read/overflow events

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>

1 files changed, 51 insertions, 24 deletions

diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c
index 4bbe19058a5..cf39c487346 100644
--- a/arch/sh/kernel/perf_event.c
+++ b/arch/sh/kernel/perf_event.c
@@ -206,26 +206,52 @@ again:
         local64_add(delta, &event->count);
 }
 
-static void sh_pmu_disable(struct perf_event *event)
+static void sh_pmu_stop(struct perf_event *event, int flags)
 {
         struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
         struct hw_perf_event *hwc = &event->hw;
         int idx = hwc->idx;
 
-        clear_bit(idx, cpuc->active_mask);
-        sh_pmu->disable(hwc, idx);
+        if (!(event->hw.state & PERF_HES_STOPPED)) {
+                sh_pmu->disable(hwc, idx);
+                cpuc->events[idx] = NULL;
+                event->hw.state |= PERF_HES_STOPPED;
+        }
 
-        barrier();
+        if ((flags & PERF_EF_UPDATE) && !(event->hw.state & PERF_HES_UPTODATE)) {
+                sh_perf_event_update(event, &event->hw, idx);
+                event->hw.state |= PERF_HES_UPTODATE;
+        }
+}
 
-        sh_perf_event_update(event, &event->hw, idx);
+static void sh_pmu_start(struct perf_event *event, int flags)
+{
+        struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+        struct hw_perf_event *hwc = &event->hw;
+        int idx = hwc->idx;
 
-        cpuc->events[idx] = NULL;
-        clear_bit(idx, cpuc->used_mask);
+        if (WARN_ON_ONCE(idx == -1))
+                return;
+
+        if (flags & PERF_EF_RELOAD)
+                WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
+
+        cpuc->events[idx] = event;
+        event->hw.state = 0;
+        sh_pmu->enable(hwc, idx);
+}
+
+static void sh_pmu_del(struct perf_event *event, int flags)
+{
+        struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+        sh_pmu_stop(event, PERF_EF_UPDATE);
+        __clear_bit(event->hw.idx, cpuc->used_mask);
 
         perf_event_update_userpage(event);
 }
 
-static int sh_pmu_enable(struct perf_event *event)
+static int sh_pmu_add(struct perf_event *event, int flags)
 {
         struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
         struct hw_perf_event *hwc = &event->hw;
@@ -234,21 +260,20 @@ static int sh_pmu_enable(struct perf_event *event)
 
         perf_pmu_disable(event->pmu);
 
-        if (test_and_set_bit(idx, cpuc->used_mask)) {
+        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)
                         goto out;
 
-                set_bit(idx, cpuc->used_mask);
+                __set_bit(idx, cpuc->used_mask);
                 hwc->idx = idx;
         }
 
         sh_pmu->disable(hwc, idx);
 
-        cpuc->events[idx] = event;
-        set_bit(idx, cpuc->active_mask);
-
-        sh_pmu->enable(hwc, idx);
+        event->hw.state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+        if (flags & PERF_EF_START)
+                sh_pmu_start(event, PERF_EF_RELOAD);
 
         perf_event_update_userpage(event);
         ret = 0;
@@ -285,7 +310,7 @@ static int sh_pmu_event_init(struct perf_event *event)
         return err;
 }
 
-static void sh_pmu_pmu_enable(struct pmu *pmu)
+static void sh_pmu_enable(struct pmu *pmu)
 {
         if (!sh_pmu_initialized())
                 return;
@@ -293,7 +318,7 @@ static void sh_pmu_pmu_enable(struct pmu *pmu)
         sh_pmu->enable_all();
 }
 
-static void sh_pmu_pmu_disable(struct pmu *pmu)
+static void sh_pmu_disable(struct pmu *pmu)
 {
         if (!sh_pmu_initialized())
                 return;
@@ -302,11 +327,13 @@ static void sh_pmu_pmu_disable(struct pmu *pmu)
 }
 
 static struct pmu pmu = {
-        .pmu_enable     = sh_pmu_pmu_enable,
-        .pmu_disable    = sh_pmu_pmu_disable,
+        .pmu_enable     = sh_pmu_enable,
+        .pmu_disable    = sh_pmu_disable,
         .event_init     = sh_pmu_event_init,
-        .enable         = sh_pmu_enable,
-        .disable        = sh_pmu_disable,
+        .add            = sh_pmu_add,
+        .del            = sh_pmu_del,
+        .start          = sh_pmu_start,
+        .stop           = sh_pmu_stop,
         .read           = sh_pmu_read,
 };
 
@@ -334,15 +361,15 @@ sh_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
         return NOTIFY_OK;
 }
 
-int __cpuinit register_sh_pmu(struct sh_pmu *pmu)
+int __cpuinit register_sh_pmu(struct sh_pmu *_pmu)
 {
         if (sh_pmu)
                 return -EBUSY;
-        sh_pmu = pmu;
+        sh_pmu = _pmu;
 
-        pr_info("Performance Events: %s support registered\n", pmu->name);
+        pr_info("Performance Events: %s support registered\n", _pmu->name);
 
-        WARN_ON(pmu->num_events > MAX_HWEVENTS);
+        WARN_ON(_pmu->num_events > MAX_HWEVENTS);
 
         perf_pmu_register(&pmu);
         perf_cpu_notifier(sh_pmu_notifier);