Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 2a0ad3b3 authored by Yan, Zheng's avatar Yan, Zheng Committed by Ingo Molnar
Browse files

perf/x86/intel: Use context switch callback to flush LBR stack 



Previous commit introduces context switch callback, its function
overlaps with the flush branch stack callback. So we can use the
context switch callback to flush LBR stack.

This patch adds code that uses the flush branch callback to
flush the LBR stack when task is being scheduled in. The callback
is enabled only when there are events use the LBR hardware. This
patch also removes all old flush branch stack code.

Signed-off-by: default avatarYan, Zheng <zheng.z.yan@intel.com>
Signed-off-by: default avatarKan Liang <kan.liang@intel.com>
Signed-off-by: default avatarPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: eranian@google.com
Cc: jolsa@redhat.com
Link: http://lkml.kernel.org/r/1415156173-10035-4-git-send-email-kan.liang@intel.com


Signed-off-by: default avatarIngo Molnar <mingo@kernel.org>
parent ba532500

arch/x86/kernel/cpu/perf_event.c

+0 −7
Original line number Diff line number Diff line
@@ -1920,12 +1920,6 @@ static void x86_pmu_sched_task(struct perf_event_context *ctx, bool sched_in) 
		x86_pmu.sched_task(ctx, sched_in);

}



static void x86_pmu_flush_branch_stack(void)

{

	if (x86_pmu.flush_branch_stack)

		x86_pmu.flush_branch_stack();

}



void perf_check_microcode(void)

{

	if (x86_pmu.check_microcode)
@@ -1955,7 +1949,6 @@ 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,

};

arch/x86/kernel/cpu/perf_event.h

+2 −1
Original line number Diff line number Diff line
@@ -472,7 +472,6 @@ 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);
@@ -733,6 +732,8 @@ 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);

arch/x86/kernel/cpu/perf_event_intel.c

+1 −13
Original line number Diff line number Diff line
@@ -2044,18 +2044,6 @@ 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");
@@ -2107,7 +2095,7 @@ 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)

arch/x86/kernel/cpu/perf_event_intel_lbr.c

+27 −0
Original line number Diff line number Diff line
@@ -177,6 +177,31 @@ void intel_pmu_lbr_reset(void) 
		intel_pmu_lbr_reset_64();

}



void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)

{

	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);



	if (!x86_pmu.lbr_nr)

		return;



	/*

	 * 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.

 	 */

	if (sched_in) {

		intel_pmu_lbr_reset();

		cpuc->lbr_context = ctx;

	}

}



void intel_pmu_lbr_enable(struct perf_event *event)

{

	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -195,6 +220,7 @@ void intel_pmu_lbr_enable(struct perf_event *event) 
	cpuc->br_sel = event->hw.branch_reg.reg;



	cpuc->lbr_users++;

	perf_sched_cb_inc(event->ctx->pmu);

}



void intel_pmu_lbr_disable(struct perf_event *event)
@@ -206,6 +232,7 @@ void intel_pmu_lbr_disable(struct perf_event *event) 


	cpuc->lbr_users--;

	WARN_ON_ONCE(cpuc->lbr_users < 0);

	perf_sched_cb_dec(event->ctx->pmu);



	if (cpuc->enabled && !cpuc->lbr_users) {

		__intel_pmu_lbr_disable();

include/linux/perf_event.h

+0 −1
Original line number Diff line number Diff line
@@ -511,7 +511,6 @@ struct perf_event_context { 
	u64				generation;

	int				pin_count;

	int				nr_cgroups;	 /* cgroup evts */

	int				nr_branch_stack; /* branch_stack evt */

	struct rcu_head			rcu_head;



	struct delayed_work		orphans_remove;