Re: [PATCH V8 03/14] perf, x86: use context switch callback to flush LBR stack

[Peter Zijlstra <peterz@infradead.org>]

On Thu, Nov 06, 2014 at 09:54:20AM -0500, Kan Liang wrote:
> --- a/kernel/events/core.c
> @@ -2673,64 +2666,6 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx,
>  }
>  
>  /*
> - * 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) {
> -
> -			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);
> -}

So while this patch removes almost everything flush_branch_stack related
it leaves a few rudiments and a broken architecture.

---
Subject: perf,powerpc: Fix up flush_branch_stack users
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed Jan 14 14:15:39 CET 2015

The recent LBR rework for x86 left a stray flush_branch_stack user in
the PowerPC code, fix that up.

Cc: Michael Neuling <mikey@neuling.org>
Cc: Anton Blanchard <anton@samba.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-q4y7je45jtnbp7nhu93by9gs@git.kernel.org
---
 arch/powerpc/perf/core-book3s.c |   13 +++++++++----
 include/linux/perf_event.h      |    5 -----
 2 files changed, 9 insertions(+), 9 deletions(-)

--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -124,7 +124,7 @@ static unsigned long ebb_switch_in(bool
 
 static inline void power_pmu_bhrb_enable(struct perf_event *event) {}
 static inline void power_pmu_bhrb_disable(struct perf_event *event) {}
-static void power_pmu_flush_branch_stack(void) {}
+static void power_pmu_sched_task(struct perf_event_context *ctx, bool sched_in) {}
 static inline void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) {}
 static void pmao_restore_workaround(bool ebb) { }
 #endif /* CONFIG_PPC32 */
@@ -350,6 +350,7 @@ static void power_pmu_bhrb_enable(struct
 		cpuhw->bhrb_context = event->ctx;
 	}
 	cpuhw->bhrb_users++;
+	perf_sched_cb_inc(event->ctx->pmu);
 }
 
 static void power_pmu_bhrb_disable(struct perf_event *event)
@@ -361,6 +362,7 @@ static void power_pmu_bhrb_disable(struc
 
 	cpuhw->bhrb_users--;
 	WARN_ON_ONCE(cpuhw->bhrb_users < 0);
+	perf_sched_cb_dec(event->ctx->pmu);
 
 	if (!cpuhw->disabled && !cpuhw->bhrb_users) {
 		/* BHRB cannot be turned off when other
@@ -375,9 +377,12 @@ static void power_pmu_bhrb_disable(struc
 /* Called from ctxsw to prevent one process's branch entries to
  * mingle with the other process's entries during context switch.
  */
-static void power_pmu_flush_branch_stack(void)
+static void power_pmu_sched_task(struct perf_event_context *ctx, bool sched_in)
 {
-	if (ppmu->bhrb_nr)
+	if (!ppmu->bhrb_nr)
+		return;
+
+	if (sched_in)
 		power_pmu_bhrb_reset();
 }
 /* Calculate the to address for a branch */
@@ -1901,7 +1906,7 @@ static struct pmu power_pmu = {
 	.cancel_txn	= power_pmu_cancel_txn,
 	.commit_txn	= power_pmu_commit_txn,
 	.event_idx	= power_pmu_event_idx,
-	.flush_branch_stack = power_pmu_flush_branch_stack,
+	.sched_task	= power_pmu_sched_task,
 };
 
 /*
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -255,11 +255,6 @@ struct pmu {
 	int (*event_idx)		(struct perf_event *event); /*optional */
 
 	/*
-	 * flush branch stack on context-switches (needed in cpu-wide mode)
-	 */
-	void (*flush_branch_stack)	(void);
-
-	/*
 	 * context-switches callback
 	 */
 	void (*sched_task)		(struct perf_event_context *ctx,