[RFC PATCH 3/7] perf, core: replace flush_branch_stack with ctxsw callback

From: Yan, Zheng
Date: Thu Sep 26 2013 - 04:30:57 EST

From: "Yan, Zheng" <zheng.z.yan@xxxxxxxxx>

Replace the flush_branch_stack pmu callback with generic context
switch callback. x86 specific perf codes use the callback to
flush branch stack.

To avoid unnecessary overhead, the context switch callback can be
enabled/disabled.

Signed-off-by: Yan, Zheng <zheng.z.yan@xxxxxxxxx>
---
arch/x86/kernel/cpu/perf_event.c | 8 +-
arch/x86/kernel/cpu/perf_event.h | 6 +-
arch/x86/kernel/cpu/perf_event_intel.c | 14 +--
arch/x86/kernel/cpu/perf_event_intel_lbr.c | 32 ++++---
include/linux/perf_event.h | 7 +-
kernel/events/core.c | 135 ++++++++++++++---------------
6 files changed, 97 insertions(+), 105 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 8355c84..b96aea8 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1846,10 +1846,10 @@ static const struct attribute_group *x86_pmu_attr_groups[] = {
NULL,
};

-static void x86_pmu_flush_branch_stack(void)
+static void x86_pmu_sched_task(struct perf_event_context *ctx, bool sched_in)
{
- if (x86_pmu.flush_branch_stack)
- x86_pmu.flush_branch_stack();
+ if (x86_pmu.sched_task)
+ x86_pmu.sched_task(ctx, sched_in);
}

void perf_check_microcode(void)
@@ -1878,7 +1878,7 @@ static struct pmu pmu = {
.commit_txn = x86_pmu_commit_txn,

.event_idx = x86_pmu_event_idx,
- .flush_branch_stack = x86_pmu_flush_branch_stack,
+ .sched_task = x86_pmu_sched_task,
};

void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 9be984d..62f6ee8 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -150,7 +150,6 @@ struct cpu_hw_events {
* Intel LBR bits
*/
int lbr_users;
- void *lbr_context;
struct perf_branch_stack lbr_stack;
struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES];
struct er_account *lbr_sel;
@@ -416,7 +415,8 @@ struct x86_pmu {
void (*cpu_dead)(int cpu);

void (*check_microcode)(void);
- void (*flush_branch_stack)(void);
+ void (*sched_task)(struct perf_event_context *ctx,
+ bool sched_in);

/*
* Intel Arch Perfmon v2+
@@ -677,6 +677,8 @@ void intel_pmu_pebs_disable_all(void);

void intel_ds_init(void);

+void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in);
+
void intel_pmu_lbr_reset(void);

void intel_pmu_lbr_enable(struct perf_event *event);
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index b300594..92b132e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2038,18 +2038,6 @@ static void intel_pmu_cpu_dying(int cpu)
fini_debug_store_on_cpu(cpu);
}

-static void intel_pmu_flush_branch_stack(void)
-{
- /*
- * Intel LBR does not tag entries with the
- * PID of the current task, then we need to
- * flush it on ctxsw
- * For now, we simply reset it
- */
- if (x86_pmu.lbr_nr)
- intel_pmu_lbr_reset();
-}
-
PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");

PMU_FORMAT_ATTR(ldlat, "config1:0-15");
@@ -2101,7 +2089,7 @@ static __initconst const struct x86_pmu intel_pmu = {
.cpu_starting = intel_pmu_cpu_starting,
.cpu_dying = intel_pmu_cpu_dying,
.guest_get_msrs = intel_guest_get_msrs,
- .flush_branch_stack = intel_pmu_flush_branch_stack,
+ .sched_task = intel_pmu_lbr_sched_task,
};

static __init void intel_clovertown_quirk(void)
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 11911db..468ac1d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -187,24 +187,32 @@ void intel_pmu_lbr_reset(void)
intel_pmu_lbr_reset_64();
}

-void intel_pmu_lbr_enable(struct perf_event *event)
+void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-
if (!x86_pmu.lbr_nr)
return;

/*
- * Reset the LBR stack if we changed task context to
- * avoid data leaks.
+ * It is necessary to flush the stack on context switch. This happens
+ * when the branch stack does not tag its entries with the pid of the
+ * current task.
*/
- if (event->ctx->task && cpuc->lbr_context != event->ctx) {
+ if (sched_in)
intel_pmu_lbr_reset();
- cpuc->lbr_context = event->ctx;
- }
+}
+
+void intel_pmu_lbr_enable(struct perf_event *event)
+{
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+ if (!x86_pmu.lbr_nr)
+ return;
+
cpuc->br_sel = event->hw.branch_reg.reg;

cpuc->lbr_users++;
+ if (cpuc->lbr_users == 1)
+ perf_sched_cb_enable(event->ctx->pmu);
}

void intel_pmu_lbr_disable(struct perf_event *event)
@@ -217,10 +225,10 @@ void intel_pmu_lbr_disable(struct perf_event *event)
cpuc->lbr_users--;
WARN_ON_ONCE(cpuc->lbr_users < 0);

- if (cpuc->enabled && !cpuc->lbr_users) {
- __intel_pmu_lbr_disable();
- /* avoid stale pointer */
- cpuc->lbr_context = NULL;
+ if (!cpuc->lbr_users) {
+ perf_sched_cb_disable(event->ctx->pmu);
+ if (cpuc->enabled)
+ __intel_pmu_lbr_disable();
}
}

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 866e85c..991bcf5 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -248,9 +248,10 @@ struct pmu {
int (*event_idx) (struct perf_event *event); /*optional */

/*
- * flush branch stack on context-switches (needed in cpu-wide mode)
+ * PMU callback for context-switches. optional
*/
- void (*flush_branch_stack) (void);
+ void (*sched_task) (struct perf_event_context *ctx,
+ bool sched_in); /*optional */
};

/**
@@ -521,6 +522,8 @@ extern void perf_event_delayed_put(struct task_struct *task);
extern void perf_event_print_debug(void);
extern void perf_pmu_disable(struct pmu *pmu);
extern void perf_pmu_enable(struct pmu *pmu);
+extern void perf_sched_cb_disable(struct pmu *pmu);
+extern void perf_sched_cb_enable(struct pmu *pmu);
extern int perf_event_task_disable(void);
extern int perf_event_task_enable(void);
extern int perf_event_refresh(struct perf_event *event, int refresh);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index dd236b6..a6e11fd 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -140,7 +140,7 @@ enum event_type_t {
*/
struct static_key_deferred perf_sched_events __read_mostly;
static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
-static DEFINE_PER_CPU(atomic_t, perf_branch_stack_events);
+static DEFINE_PER_CPU(int, perf_sched_cb_usages);

static atomic_t nr_mmap_events __read_mostly;
static atomic_t nr_comm_events __read_mostly;
@@ -2297,6 +2297,62 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
}
}

+void perf_sched_cb_disable(struct pmu *pmu)
+{
+ __get_cpu_var(perf_sched_cb_usages)--;
+}
+
+void perf_sched_cb_enable(struct pmu *pmu)
+{
+ __get_cpu_var(perf_sched_cb_usages)++;
+}
+
+/*
+ * This function provides the context switch callback to the lower code
+ * layer. It is invoked ONLY when the context switch callback is enabled.
+ */
+static void perf_pmu_sched_task(struct task_struct *prev,
+ struct task_struct *next,
+ bool sched_in)
+{
+ struct perf_cpu_context *cpuctx;
+ struct pmu *pmu;
+ unsigned long flags;
+ int count = 0;
+
+ if (prev == next)
+ return;
+
+ local_irq_save(flags);
+
+ rcu_read_lock();
+
+ list_for_each_entry_rcu(pmu, &pmus, entry) {
+ if (!pmu->sched_task)
+ continue;
+
+ cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+ pmu = cpuctx->ctx.pmu;
+
+ perf_ctx_lock(cpuctx, cpuctx->task_ctx);
+
+ perf_pmu_disable(pmu);
+
+ pmu->sched_task(cpuctx->task_ctx, sched_in);
+
+ perf_pmu_enable(pmu);
+
+ perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
+
+ if (++count >= __get_cpu_var(perf_sched_cb_usages))
+ break;
+ }
+
+ rcu_read_unlock();
+
+ local_irq_restore(flags);
+}
+
#define for_each_task_context_nr(ctxn) \
for ((ctxn) = 0; (ctxn) < perf_nr_task_contexts; (ctxn)++)

@@ -2316,6 +2372,9 @@ void __perf_event_task_sched_out(struct task_struct *task,
{
int ctxn;

+ if (__get_cpu_var(perf_sched_cb_usages))
+ perf_pmu_sched_task(task, next, false);
+
for_each_task_context_nr(ctxn)
perf_event_context_sched_out(task, ctxn, next);

@@ -2480,65 +2539,6 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx,
perf_pmu_rotate_start(ctx->pmu);
}

-/*
- * When sampling the branck stack in system-wide, it may be necessary
- * to flush the stack on context switch. This happens when the branch
- * stack does not tag its entries with the pid of the current task.
- * Otherwise it becomes impossible to associate a branch entry with a
- * task. This ambiguity is more likely to appear when the branch stack
- * supports priv level filtering and the user sets it to monitor only
- * at the user level (which could be a useful measurement in system-wide
- * mode). In that case, the risk is high of having a branch stack with
- * branch from multiple tasks. Flushing may mean dropping the existing
- * entries or stashing them somewhere in the PMU specific code layer.
- *
- * This function provides the context switch callback to the lower code
- * layer. It is invoked ONLY when there is at least one system-wide context
- * with at least one active event using taken branch sampling.
- */
-static void perf_branch_stack_sched_in(struct task_struct *prev,
- struct task_struct *task)
-{
- struct perf_cpu_context *cpuctx;
- struct pmu *pmu;
- unsigned long flags;
-
- /* no need to flush branch stack if not changing task */
- if (prev == task)
- return;
-
- local_irq_save(flags);
-
- rcu_read_lock();
-
- list_for_each_entry_rcu(pmu, &pmus, entry) {
- cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
-
- /*
- * check if the context has at least one
- * event using PERF_SAMPLE_BRANCH_STACK
- */
- if (cpuctx->ctx.nr_branch_stack > 0
- && pmu->flush_branch_stack) {
-
- pmu = cpuctx->ctx.pmu;
-
- perf_ctx_lock(cpuctx, cpuctx->task_ctx);
-
- perf_pmu_disable(pmu);
-
- pmu->flush_branch_stack();
-
- perf_pmu_enable(pmu);
-
- perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
- }
- }
-
- rcu_read_unlock();
-
- local_irq_restore(flags);
-}

/*
* Called from scheduler to add the events of the current task
@@ -2572,9 +2572,8 @@ void __perf_event_task_sched_in(struct task_struct *prev,
if (atomic_read(&__get_cpu_var(perf_cgroup_events)))
perf_cgroup_sched_in(prev, task);

- /* check for system-wide branch_stack events */
- if (atomic_read(&__get_cpu_var(perf_branch_stack_events)))
- perf_branch_stack_sched_in(prev, task);
+ if (__get_cpu_var(perf_sched_cb_usages))
+ perf_pmu_sched_task(prev, task, true);
}

static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
@@ -3137,10 +3136,6 @@ static void unaccount_event_cpu(struct perf_event *event, int cpu)
if (event->parent)
return;

- if (has_branch_stack(event)) {
- if (!(event->attach_state & PERF_ATTACH_TASK))
- atomic_dec(&per_cpu(perf_branch_stack_events, cpu));
- }
if (is_cgroup_event(event))
atomic_dec(&per_cpu(perf_cgroup_events, cpu));
}
@@ -6447,7 +6442,7 @@ got_cpu_context:
if (!pmu->event_idx)
pmu->event_idx = perf_event_idx_default;

- list_add_rcu(&pmu->entry, &pmus);
+ list_add_tail_rcu(&pmu->entry, &pmus);
ret = 0;
unlock:
mutex_unlock(&pmus_lock);
@@ -6530,10 +6525,6 @@ static void account_event_cpu(struct perf_event *event, int cpu)
if (event->parent)
return;

- if (has_branch_stack(event)) {
- if (!(event->attach_state & PERF_ATTACH_TASK))
- atomic_inc(&per_cpu(perf_branch_stack_events, cpu));
- }
if (is_cgroup_event(event))
atomic_inc(&per_cpu(perf_cgroup_events, cpu));
}
--
1.8.1.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/