diff mbox series

[4/8] perf/core: Add perf_sample_save_brstack() helper

Message ID 20230118060559.615653-5-namhyung@kernel.org
State New
Headers
Series perf/core: Prepare sample data for BPF (v3) |

Commit Message

Namhyung Kim Jan. 18, 2023, 6:05 a.m. UTC 
  When it saves the branch stack to the perf sample data, it needs to
update the sample flags and the dynamic size.  To make sure this,
add the perf_sample_save_brstack() helper and convert all call sites.

Cc: linuxppc-dev@lists.ozlabs.org
Cc: x86@kernel.org
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 arch/powerpc/perf/core-book3s.c |  3 +-
 arch/x86/events/amd/core.c      |  6 +--
 arch/x86/events/intel/core.c    |  6 +--
 arch/x86/events/intel/ds.c      |  9 ++---
 include/linux/perf_event.h      | 66 ++++++++++++++++++++-------------
 kernel/events/core.c            | 16 +++-----
 6 files changed, 53 insertions(+), 53 deletions(-)

Comments

Athira Rajeev Jan. 18, 2023, 9:06 a.m. UTC | #1 
> On 18-Jan-2023, at 11:35 AM, Namhyung Kim <namhyung@kernel.org> wrote:
> 
> When it saves the branch stack to the perf sample data, it needs to
> update the sample flags and the dynamic size.  To make sure this,
> add the perf_sample_save_brstack() helper and convert all call sites.
> 
> Cc: linuxppc-dev@lists.ozlabs.org
> Cc: x86@kernel.org
> Suggested-by: Peter Zijlstra <peterz@infradead.org>
> Acked-by: Jiri Olsa <jolsa@kernel.org>
> Tested-by: Jiri Olsa <jolsa@kernel.org>
> Signed-off-by: Namhyung Kim <namhyung@kernel.org>

Hi Namhyung,

Changes looks good to me.

Acked-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>

Thanks
Athira

> ---
> arch/powerpc/perf/core-book3s.c |  3 +-
> arch/x86/events/amd/core.c      |  6 +--
> arch/x86/events/intel/core.c    |  6 +--
> arch/x86/events/intel/ds.c      |  9 ++---
> include/linux/perf_event.h      | 66 ++++++++++++++++++++-------------
> kernel/events/core.c            | 16 +++-----
> 6 files changed, 53 insertions(+), 53 deletions(-)
> 
> diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
> index bf318dd9b709..8c1f7def596e 100644
> --- a/arch/powerpc/perf/core-book3s.c
> +++ b/arch/powerpc/perf/core-book3s.c
> @@ -2313,8 +2313,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
> 			struct cpu_hw_events *cpuhw;
> 			cpuhw = this_cpu_ptr(&cpu_hw_events);
> 			power_pmu_bhrb_read(event, cpuhw);
> -			data.br_stack = &cpuhw->bhrb_stack;
> -			data.sample_flags |= PERF_SAMPLE_BRANCH_STACK;
> +			perf_sample_save_brstack(&data, event, &cpuhw->bhrb_stack);
> 		}
> 
> 		if (event->attr.sample_type & PERF_SAMPLE_DATA_SRC &&
> diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
> index d6f3703e4119..463f3eb8bbd7 100644
> --- a/arch/x86/events/amd/core.c
> +++ b/arch/x86/events/amd/core.c
> @@ -928,10 +928,8 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
> 		if (!x86_perf_event_set_period(event))
> 			continue;
> 
> -		if (has_branch_stack(event)) {
> -			data.br_stack = &cpuc->lbr_stack;
> -			data.sample_flags |= PERF_SAMPLE_BRANCH_STACK;
> -		}
> +		if (has_branch_stack(event))
> +			perf_sample_save_brstack(&data, event, &cpuc->lbr_stack);
> 
> 		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 29d2d0411caf..14f0a746257d 100644
> --- a/arch/x86/events/intel/core.c
> +++ b/arch/x86/events/intel/core.c
> @@ -3036,10 +3036,8 @@ 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)) {
> -			data.br_stack = &cpuc->lbr_stack;
> -			data.sample_flags |= PERF_SAMPLE_BRANCH_STACK;
> -		}
> +		if (has_branch_stack(event))
> +			perf_sample_save_brstack(&data, event, &cpuc->lbr_stack);
> 
> 		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 158cf845fc80..07c8a2cdc3ee 100644
> --- a/arch/x86/events/intel/ds.c
> +++ b/arch/x86/events/intel/ds.c
> @@ -1720,10 +1720,8 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event,
> 		data->sample_flags |= PERF_SAMPLE_TIME;
> 	}
> 
> -	if (has_branch_stack(event)) {
> -		data->br_stack = &cpuc->lbr_stack;
> -		data->sample_flags |= PERF_SAMPLE_BRANCH_STACK;
> -	}
> +	if (has_branch_stack(event))
> +		perf_sample_save_brstack(data, event, &cpuc->lbr_stack);
> }
> 
> static void adaptive_pebs_save_regs(struct pt_regs *regs,
> @@ -1883,8 +1881,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
> 
> 		if (has_branch_stack(event)) {
> 			intel_pmu_store_pebs_lbrs(lbr);
> -			data->br_stack = &cpuc->lbr_stack;
> -			data->sample_flags |= PERF_SAMPLE_BRANCH_STACK;
> +			perf_sample_save_brstack(data, event, &cpuc->lbr_stack);
> 		}
> 	}
> 
> diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
> index 569dfac5887f..7db0e9cc2682 100644
> --- a/include/linux/perf_event.h
> +++ b/include/linux/perf_event.h
> @@ -1102,6 +1102,31 @@ extern u64 perf_event_read_value(struct perf_event *event,
> 
> extern struct perf_callchain_entry *perf_callchain(struct perf_event *event, struct pt_regs *regs);
> 
> +static inline bool branch_sample_no_flags(const struct perf_event *event)
> +{
> +	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_NO_FLAGS;
> +}
> +
> +static inline bool branch_sample_no_cycles(const struct perf_event *event)
> +{
> +	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_NO_CYCLES;
> +}
> +
> +static inline bool branch_sample_type(const struct perf_event *event)
> +{
> +	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_TYPE_SAVE;
> +}
> +
> +static inline bool branch_sample_hw_index(const struct perf_event *event)
> +{
> +	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX;
> +}
> +
> +static inline bool branch_sample_priv(const struct perf_event *event)
> +{
> +	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_PRIV_SAVE;
> +}
> +
> 
> struct perf_sample_data {
> 	/*
> @@ -1210,6 +1235,21 @@ static inline void perf_sample_save_raw_data(struct perf_sample_data *data,
> 	data->sample_flags |= PERF_SAMPLE_RAW;
> }
> 
> +static inline void perf_sample_save_brstack(struct perf_sample_data *data,
> +					    struct perf_event *event,
> +					    struct perf_branch_stack *brs)
> +{
> +	int size = sizeof(u64); /* nr */
> +
> +	if (branch_sample_hw_index(event))
> +		size += sizeof(u64);
> +	size += brs->nr * sizeof(struct perf_branch_entry);
> +
> +	data->br_stack = brs;
> +	data->dyn_size += size;
> +	data->sample_flags |= PERF_SAMPLE_BRANCH_STACK;
> +}
> +
> /*
>  * Clear all bitfields in the perf_branch_entry.
>  * The to and from fields are not cleared because they are
> @@ -1827,30 +1867,4 @@ static inline void perf_lopwr_cb(bool mode)
> }
> #endif
> 
> -#ifdef CONFIG_PERF_EVENTS
> -static inline bool branch_sample_no_flags(const struct perf_event *event)
> -{
> -	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_NO_FLAGS;
> -}
> -
> -static inline bool branch_sample_no_cycles(const struct perf_event *event)
> -{
> -	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_NO_CYCLES;
> -}
> -
> -static inline bool branch_sample_type(const struct perf_event *event)
> -{
> -	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_TYPE_SAVE;
> -}
> -
> -static inline bool branch_sample_hw_index(const struct perf_event *event)
> -{
> -	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX;
> -}
> -
> -static inline bool branch_sample_priv(const struct perf_event *event)
> -{
> -	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_PRIV_SAVE;
> -}
> -#endif /* CONFIG_PERF_EVENTS */
> #endif /* _LINUX_PERF_EVENT_H */
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index 133894ae5e30..0218b6ffaf36 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -7317,7 +7317,7 @@ void perf_output_sample(struct perf_output_handle *handle,
> 	}
> 
> 	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
> -		if (data->sample_flags & PERF_SAMPLE_BRANCH_STACK) {
> +		if (data->br_stack) {
> 			size_t size;
> 
> 			size = data->br_stack->nr
> @@ -7594,16 +7594,10 @@ void perf_prepare_sample(struct perf_event_header *header,
> 		data->sample_flags |= PERF_SAMPLE_RAW;
> 	}
> 
> -	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
> -		int size = sizeof(u64); /* nr */
> -		if (data->sample_flags & PERF_SAMPLE_BRANCH_STACK) {
> -			if (branch_sample_hw_index(event))
> -				size += sizeof(u64);
> -
> -			size += data->br_stack->nr
> -			      * sizeof(struct perf_branch_entry);
> -		}
> -		data->dyn_size += size;
> +	if (filtered_sample_type & PERF_SAMPLE_BRANCH_STACK) {
> +		data->br_stack = NULL;
> +		data->dyn_size += sizeof(u64);
> +		data->sample_flags |= PERF_SAMPLE_BRANCH_STACK;
> 	}
> 
> 	if (sample_type & (PERF_SAMPLE_REGS_USER | PERF_SAMPLE_STACK_USER))
> -- 
> 2.39.0.314.g84b9a713c41-goog
>
diff mbox series

Patch

diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index bf318dd9b709..8c1f7def596e 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -2313,8 +2313,7 @@  static void record_and_restart(struct perf_event *event, unsigned long val,
 			struct cpu_hw_events *cpuhw;
 			cpuhw = this_cpu_ptr(&cpu_hw_events);
 			power_pmu_bhrb_read(event, cpuhw);
-			data.br_stack = &cpuhw->bhrb_stack;
-			data.sample_flags |= PERF_SAMPLE_BRANCH_STACK;
+			perf_sample_save_brstack(&data, event, &cpuhw->bhrb_stack);
 		}
 
 		if (event->attr.sample_type & PERF_SAMPLE_DATA_SRC &&
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index d6f3703e4119..463f3eb8bbd7 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -928,10 +928,8 @@  static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
 		if (!x86_perf_event_set_period(event))
 			continue;
 
-		if (has_branch_stack(event)) {
-			data.br_stack = &cpuc->lbr_stack;
-			data.sample_flags |= PERF_SAMPLE_BRANCH_STACK;
-		}
+		if (has_branch_stack(event))
+			perf_sample_save_brstack(&data, event, &cpuc->lbr_stack);
 
 		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 29d2d0411caf..14f0a746257d 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3036,10 +3036,8 @@  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)) {
-			data.br_stack = &cpuc->lbr_stack;
-			data.sample_flags |= PERF_SAMPLE_BRANCH_STACK;
-		}
+		if (has_branch_stack(event))
+			perf_sample_save_brstack(&data, event, &cpuc->lbr_stack);
 
 		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 158cf845fc80..07c8a2cdc3ee 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1720,10 +1720,8 @@  static void setup_pebs_fixed_sample_data(struct perf_event *event,
 		data->sample_flags |= PERF_SAMPLE_TIME;
 	}
 
-	if (has_branch_stack(event)) {
-		data->br_stack = &cpuc->lbr_stack;
-		data->sample_flags |= PERF_SAMPLE_BRANCH_STACK;
-	}
+	if (has_branch_stack(event))
+		perf_sample_save_brstack(data, event, &cpuc->lbr_stack);
 }
 
 static void adaptive_pebs_save_regs(struct pt_regs *regs,
@@ -1883,8 +1881,7 @@  static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 
 		if (has_branch_stack(event)) {
 			intel_pmu_store_pebs_lbrs(lbr);
-			data->br_stack = &cpuc->lbr_stack;
-			data->sample_flags |= PERF_SAMPLE_BRANCH_STACK;
+			perf_sample_save_brstack(data, event, &cpuc->lbr_stack);
 		}
 	}
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 569dfac5887f..7db0e9cc2682 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1102,6 +1102,31 @@  extern u64 perf_event_read_value(struct perf_event *event,
 
 extern struct perf_callchain_entry *perf_callchain(struct perf_event *event, struct pt_regs *regs);
 
+static inline bool branch_sample_no_flags(const struct perf_event *event)
+{
+	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_NO_FLAGS;
+}
+
+static inline bool branch_sample_no_cycles(const struct perf_event *event)
+{
+	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_NO_CYCLES;
+}
+
+static inline bool branch_sample_type(const struct perf_event *event)
+{
+	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_TYPE_SAVE;
+}
+
+static inline bool branch_sample_hw_index(const struct perf_event *event)
+{
+	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX;
+}
+
+static inline bool branch_sample_priv(const struct perf_event *event)
+{
+	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_PRIV_SAVE;
+}
+
 
 struct perf_sample_data {
 	/*
@@ -1210,6 +1235,21 @@  static inline void perf_sample_save_raw_data(struct perf_sample_data *data,
 	data->sample_flags |= PERF_SAMPLE_RAW;
 }
 
+static inline void perf_sample_save_brstack(struct perf_sample_data *data,
+					    struct perf_event *event,
+					    struct perf_branch_stack *brs)
+{
+	int size = sizeof(u64); /* nr */
+
+	if (branch_sample_hw_index(event))
+		size += sizeof(u64);
+	size += brs->nr * sizeof(struct perf_branch_entry);
+
+	data->br_stack = brs;
+	data->dyn_size += size;
+	data->sample_flags |= PERF_SAMPLE_BRANCH_STACK;
+}
+
 /*
  * Clear all bitfields in the perf_branch_entry.
  * The to and from fields are not cleared because they are
@@ -1827,30 +1867,4 @@  static inline void perf_lopwr_cb(bool mode)
 }
 #endif
 
-#ifdef CONFIG_PERF_EVENTS
-static inline bool branch_sample_no_flags(const struct perf_event *event)
-{
-	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_NO_FLAGS;
-}
-
-static inline bool branch_sample_no_cycles(const struct perf_event *event)
-{
-	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_NO_CYCLES;
-}
-
-static inline bool branch_sample_type(const struct perf_event *event)
-{
-	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_TYPE_SAVE;
-}
-
-static inline bool branch_sample_hw_index(const struct perf_event *event)
-{
-	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX;
-}
-
-static inline bool branch_sample_priv(const struct perf_event *event)
-{
-	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_PRIV_SAVE;
-}
-#endif /* CONFIG_PERF_EVENTS */
 #endif /* _LINUX_PERF_EVENT_H */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 133894ae5e30..0218b6ffaf36 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7317,7 +7317,7 @@  void perf_output_sample(struct perf_output_handle *handle,
 	}
 
 	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
-		if (data->sample_flags & PERF_SAMPLE_BRANCH_STACK) {
+		if (data->br_stack) {
 			size_t size;
 
 			size = data->br_stack->nr
@@ -7594,16 +7594,10 @@  void perf_prepare_sample(struct perf_event_header *header,
 		data->sample_flags |= PERF_SAMPLE_RAW;
 	}
 
-	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
-		int size = sizeof(u64); /* nr */
-		if (data->sample_flags & PERF_SAMPLE_BRANCH_STACK) {
-			if (branch_sample_hw_index(event))
-				size += sizeof(u64);
-
-			size += data->br_stack->nr
-			      * sizeof(struct perf_branch_entry);
-		}
-		data->dyn_size += size;
+	if (filtered_sample_type & PERF_SAMPLE_BRANCH_STACK) {
+		data->br_stack = NULL;
+		data->dyn_size += sizeof(u64);
+		data->sample_flags |= PERF_SAMPLE_BRANCH_STACK;
 	}
 
 	if (sample_type & (PERF_SAMPLE_REGS_USER | PERF_SAMPLE_STACK_USER))