UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

perf/core: Introduce perf_prepare_header() 

Factor out perf_prepare_header() so that it can call
perf_prepare_sample() without a header if not needed.

Also it checks the filtered_sample_type to avoid duplicate
work when perf_prepare_sample() is called twice (or more).

Suggested-by: Peter Zijlstr <peterz@infradead.org>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Song Liu <song@kernel.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230118060559.615653-8-namhyung@kernel.org
This commit is contained in:
Namhyung Kim 2023-01-17 22:05:58 -08:00 committed by Ingo Molnar
parent a7c8d0daa8
commit f6e707156e
4 changed files with 43 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
arch/s390/kernel/perf_cpum_sf.c
View File

@ -672,7 +672,8 @@ static void cpumsf_output_event_pid(struct perf_event *event,
/* Protect callchain buffers, tasks */
rcu_read_lock();
perf_prepare_sample(&header, data, event, regs);
perf_prepare_sample(data, event, regs);
perf_prepare_header(&header, data, event, regs);
if (perf_output_begin(&handle, data, event, header.size))
goto out;

3
arch/x86/events/intel/ds.c
View File

@ -807,7 +807,8 @@ int intel_pmu_drain_bts_buffer(void)
* the sample.
*/
rcu_read_lock();
perf_prepare_sample(&header, &data, event, &regs);
perf_prepare_sample(&data, event, &regs);
perf_prepare_header(&header, &data, event, &regs);
if (perf_output_begin(&handle, &data, event,
header.size * (top - base - skip)))

16
include/linux/perf_event.h
View File

@ -1250,6 +1250,17 @@ static inline void perf_sample_save_brstack(struct perf_sample_data *data,
data->sample_flags |= PERF_SAMPLE_BRANCH_STACK;
}
static inline u32 perf_sample_data_size(struct perf_sample_data *data,
struct perf_event *event)
{
u32 size = sizeof(struct perf_event_header);
size += event->header_size + event->id_header_size;
size += data->dyn_size;
return size;
}
/*
* Clear all bitfields in the perf_branch_entry.
* The to and from fields are not cleared because they are
@ -1271,7 +1282,10 @@ extern void perf_output_sample(struct perf_output_handle *handle,
struct perf_event_header *header,
struct perf_sample_data *data,
struct perf_event *event);
extern void perf_prepare_sample(struct perf_event_header *header,
extern void perf_prepare_sample(struct perf_sample_data *data,
struct perf_event *event,
struct pt_regs *regs);
extern void perf_prepare_header(struct perf_event_header *header,
struct perf_sample_data *data,
struct perf_event *event,
struct pt_regs *regs);

38
kernel/events/core.c
View File

@ -7568,20 +7568,13 @@ static __always_inline u64 __cond_set(u64 flags, u64 s, u64 d)
return d * !!(flags & s);
}
void perf_prepare_sample(struct perf_event_header *header,
struct perf_sample_data *data,
void perf_prepare_sample(struct perf_sample_data *data,
struct perf_event *event,
struct pt_regs *regs)
{
u64 sample_type = event->attr.sample_type;
u64 filtered_sample_type;
header->type = PERF_RECORD_SAMPLE;
header->size = sizeof(*header) + event->header_size + event->id_header_size;
header->misc = 0;
header->misc |= perf_misc_flags(regs);
/*
* Add the sample flags that are dependent to others. And clear the
* sample flags that have already been done by the PMU driver.
@ -7595,6 +7588,12 @@ void perf_prepare_sample(struct perf_event_header *header,
PERF_SAMPLE_REGS_USER);
filtered_sample_type &= ~data->sample_flags;
if (filtered_sample_type == 0) {
/* Make sure it has the correct data->type for output */
data->type = event->attr.sample_type;
return;
}
__perf_event_header__init_id(data, event, filtered_sample_type);
if (filtered_sample_type & PERF_SAMPLE_IP) {
@ -7646,9 +7645,10 @@ void perf_prepare_sample(struct perf_event_header *header,
* up the rest of the sample size.
*/
u16 stack_size = event->attr.sample_stack_user;
u16 header_size = perf_sample_data_size(data, event);
u16 size = sizeof(u64);
stack_size = perf_sample_ustack_size(stack_size, header->size,
stack_size = perf_sample_ustack_size(stack_size, header_size,
data->regs_user.regs);
/*
@ -7733,8 +7733,9 @@ void perf_prepare_sample(struct perf_event_header *header,
if (filtered_sample_type & PERF_SAMPLE_AUX) {
u64 size;
u16 header_size = perf_sample_data_size(data, event);
header->size += sizeof(u64); /* size */
header_size += sizeof(u64); /* size */
/*
* Given the 16bit nature of header::size, an AUX sample can
@ -7742,17 +7743,25 @@ void perf_prepare_sample(struct perf_event_header *header,
* Make sure this doesn't happen by using up to U16_MAX bytes
* per sample in total (rounded down to 8 byte boundary).
*/
size = min_t(size_t, U16_MAX - header->size,
size = min_t(size_t, U16_MAX - header_size,
event->attr.aux_sample_size);
size = rounddown(size, 8);
size = perf_prepare_sample_aux(event, data, size);
WARN_ON_ONCE(size + header->size > U16_MAX);
WARN_ON_ONCE(size + header_size > U16_MAX);
data->dyn_size += size + sizeof(u64); /* size above */
data->sample_flags |= PERF_SAMPLE_AUX;
}
}
header->size += data->dyn_size;
void perf_prepare_header(struct perf_event_header *header,
struct perf_sample_data *data,
struct perf_event *event,
struct pt_regs *regs)
{
header->type = PERF_RECORD_SAMPLE;
header->size = perf_sample_data_size(data, event);
header->misc = perf_misc_flags(regs);
/*
* If you're adding more sample types here, you likely need to do
@ -7781,7 +7790,8 @@ __perf_event_output(struct perf_event *event,
/* protect the callchain buffers */
rcu_read_lock();
perf_prepare_sample(&header, data, event, regs);
perf_prepare_sample(data, event, regs);
perf_prepare_header(&header, data, event, regs);
err = output_begin(&handle, data, event, header.size);
if (err)