diff options
| author | Kan Liang <kan.liang@linux.intel.com> | 2023-10-25 23:16:19 +0300 |
|---|---|---|
| committer | Peter Zijlstra <peterz@infradead.org> | 2023-10-27 16:05:08 +0300 |
| commit | 571d91dcadfa3cef499010b4eddb9b58b0da4d24 (patch) | |
| tree | 1ae541b3ac838cf76949c40a9b41740a54d93740 /arch/x86/events | |
| parent | 744940f1921c8feb90e3c4bcc1e153fdd6e10fe2 (diff) | |
| download | linux-571d91dcadfa3cef499010b4eddb9b58b0da4d24.tar.xz | |
perf: Add branch stack counters
Currently, the additional information of a branch entry is stored in a
u64 space. With more and more information added, the space is running
out. For example, the information of occurrences of events will be added
for each branch.
Two places were suggested to append the counters.
https://lore.kernel.org/lkml/20230802215814.GH231007@hirez.programming.kicks-ass.net/
One place is right after the flags of each branch entry. It changes the
existing struct perf_branch_entry. The later ARCH specific
implementation has to be really careful to consistently pick
the right struct.
The other place is right after the entire struct perf_branch_stack.
The disadvantage is that the pointer of the extra space has to be
recorded. The common interface perf_sample_save_brstack() has to be
updated.
The latter is much straightforward, and should be easily understood and
maintained. It is implemented in the patch.
Add a new branch sample type, PERF_SAMPLE_BRANCH_COUNTERS, to indicate
the event which is recorded in the branch info.
The "u64 counters" may store the occurrences of several events. The
information regarding the number of events/counters and the width of
each counter should be exposed via sysfs as a reference for the perf
tool. Define the branch_counter_nr and branch_counter_width ABI here.
The support will be implemented later in the Intel-specific patch.
Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20231025201626.3000228-1-kan.liang@linux.intel.com
Diffstat (limited to 'arch/x86/events')
| -rw-r--r-- | arch/x86/events/amd/core.c | 2 | ||||
| -rw-r--r-- | arch/x86/events/core.c | 2 | ||||
| -rw-r--r-- | arch/x86/events/intel/core.c | 2 | ||||
| -rw-r--r-- | arch/x86/events/intel/ds.c | 4 |
4 files changed, 5 insertions, 5 deletions
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index e24976593a29..4ee6390b45c9 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -940,7 +940,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs) continue; if (has_branch_stack(event)) - perf_sample_save_brstack(&data, event, &cpuc->lbr_stack); + perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL); if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 40ad1425ffa2..40c9af124128 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1702,7 +1702,7 @@ int x86_pmu_handle_irq(struct pt_regs *regs) perf_sample_data_init(&data, 0, event->hw.last_period); if (has_branch_stack(event)) - perf_sample_save_brstack(&data, event, &cpuc->lbr_stack); + perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL); if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index a08f794a0e79..41a164764a84 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3047,7 +3047,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) perf_sample_data_init(&data, 0, event->hw.last_period); if (has_branch_stack(event)) - perf_sample_save_brstack(&data, event, &cpuc->lbr_stack); + perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL); if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index bf97ab904d40..cb3f329f8fa4 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1755,7 +1755,7 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event, setup_pebs_time(event, data, pebs->tsc); if (has_branch_stack(event)) - perf_sample_save_brstack(data, event, &cpuc->lbr_stack); + perf_sample_save_brstack(data, event, &cpuc->lbr_stack, NULL); } static void adaptive_pebs_save_regs(struct pt_regs *regs, @@ -1912,7 +1912,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, if (has_branch_stack(event)) { intel_pmu_store_pebs_lbrs(lbr); - perf_sample_save_brstack(data, event, &cpuc->lbr_stack); + perf_sample_save_brstack(data, event, &cpuc->lbr_stack, NULL); } } |