Commit a46a2300 authored by Yan, Zheng's avatar Yan, Zheng Committed by Ingo Molnar
Browse files

perf: Simplify the branch stack check 



Use event->attr.branch_sample_type to replace
intel_pmu_needs_lbr_smpl() for avoiding duplicated code that
implicitly enables the LBR.

Currently, branch stack can be enabled by user explicitly requesting
branch sampling or implicit branch sampling to correct PEBS skid.

For user explicitly requested branch sampling, the branch_sample_type
is explicitly set by user. For PEBS case, the branch_sample_type is also
implicitly set to PERF_SAMPLE_BRANCH_ANY in x86_pmu_hw_config.

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: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: eranian@google.com
Cc: jolsa@redhat.com
Link: http://lkml.kernel.org/r/1415156173-10035-11-git-send-email-kan.liang@intel.com


Signed-off-by: default avatarIngo Molnar <mingo@kernel.org>
parent 76cb2c61

arch/x86/kernel/cpu/perf_event_intel.c

+3 −17
Original line number Diff line number Diff line
@@ -1029,20 +1029,6 @@ static __initconst const u64 slm_hw_cache_event_ids 
 },

};



static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event)

{

	/* user explicitly requested branch sampling */

	if (has_branch_stack(event))

		return true;



	/* implicit branch sampling to correct PEBS skid */

	if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1 &&

	    x86_pmu.intel_cap.pebs_format < 2)

		return true;



	return false;

}



static void intel_pmu_disable_all(void)

{

	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -1207,7 +1193,7 @@ static void intel_pmu_disable_event(struct perf_event *event) 
	 * must disable before any actual event

	 * because any event may be combined with LBR

	 */

	if (intel_pmu_needs_lbr_smpl(event))

	if (needs_branch_stack(event))

		intel_pmu_lbr_disable(event);



	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
@@ -1268,7 +1254,7 @@ static void intel_pmu_enable_event(struct perf_event *event) 
	 * must enabled before any actual event

	 * because any event may be combined with LBR

	 */

	if (intel_pmu_needs_lbr_smpl(event))

	if (needs_branch_stack(event))

		intel_pmu_lbr_enable(event);



	if (event->attr.exclude_host)
@@ -1747,7 +1733,7 @@ static int intel_pmu_hw_config(struct perf_event *event) 
	if (event->attr.precise_ip && x86_pmu.pebs_aliases)

		x86_pmu.pebs_aliases(event);



	if (intel_pmu_needs_lbr_smpl(event)) {

	if (needs_branch_stack(event)) {

		ret = intel_pmu_setup_lbr_filter(event);

		if (ret)

			return ret;

include/linux/perf_event.h

+5 −0
Original line number Diff line number Diff line
@@ -814,6 +814,11 @@ static inline bool has_branch_stack(struct perf_event *event) 
	return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK;

}



static inline bool needs_branch_stack(struct perf_event *event)

{

	return event->attr.branch_sample_type != 0;

}



extern int perf_output_begin(struct perf_output_handle *handle,

			     struct perf_event *event, unsigned int size);

extern void perf_output_end(struct perf_output_handle *handle);

kernel/events/core.c

+3 −0
Original line number Diff line number Diff line
@@ -7232,6 +7232,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, 
	if (attr->inherit && (attr->read_format & PERF_FORMAT_GROUP))

		goto err_ns;



	if (!has_branch_stack(event))

		event->attr.branch_sample_type = 0;



	pmu = perf_init_event(event);

	if (!pmu)

		goto err_ns;

CRA Git | Maintained and supported by SUSTech CRA and CCSE