[PATCH RFC V2 1/4] perf/core: Add aux_pause, aux_resume, aux_start_paused
Adrian Hunter
adrian.hunter at intel.com
Fri Jan 5 04:57:42 PST 2024
On 20/12/23 19:41, Suzuki K Poulose wrote:
> On 08/12/2023 17:24, Adrian Hunter wrote:
>> Hardware traces, such as instruction traces, can produce a vast amount of
>> trace data, so being able to reduce tracing to more specific circumstances
>> can be useful.
>>
>> The ability to pause or resume tracing when another event happens, can do
>> that.
>>
>> Add ability for an event to "pause" or "resume" AUX area tracing.
>>
>> Add aux_pause bit to perf_event_attr to indicate that, if the event
>> happens, the associated AUX area tracing should be paused. Ditto
>> aux_resume. Do not allow aux_pause and aux_resume to be set together.
>>
>> Add aux_start_paused bit to perf_event_attr to indicate to an AUX area
>> event that it should start in a "paused" state.
>>
>> Add aux_paused to struct perf_event for AUX area events to keep track of
>> the "paused" state. aux_paused is initialized to aux_start_paused.
>>
>> Add PERF_EF_PAUSE and PERF_EF_RESUME modes for ->stop() and ->start()
>> callbacks. Call as needed, during __perf_event_output(). Add
>> aux_in_pause_resume to struct perf_buffer to prevent races with the NMI
>> handler. Pause/resume in NMI context will miss out if it coincides with
>> another pause/resume.
>>
>> To use aux_pause or aux_resume, an event must be in a group with the AUX
>> area event as the group leader.
>>
>> Example (requires Intel PT and tools patches also):
>>
>> $ perf record --kcore -e '{intel_pt/aux-start-paused/k,syscalls:sys_enter_newuname/aux-resume/,syscalls:sys_exit_newuname/aux-pause/}' uname
>> Linux
>> [ perf record: Woken up 1 times to write data ]
>> [ perf record: Captured and wrote 0.041 MB perf.data ]
>> $ perf script --call-trace
>> uname 5712 [007] 83.855580930: name: 0x7ffd9dcebec0
>> uname 5712 [007] 83.855582518: psb offs: 0
>> uname 5712 [007] 83.855582518: cbr: 42 freq: 4205 MHz (150%)
>> uname 5712 [007] 83.855582723: ([kernel.kallsyms]) debug_smp_processor_id
>> uname 5712 [007] 83.855582723: ([kernel.kallsyms]) __x64_sys_newuname
>> uname 5712 [007] 83.855582723: ([kernel.kallsyms]) down_read
>> uname 5712 [007] 83.855582723: ([kernel.kallsyms]) __cond_resched
>> uname 5712 [007] 83.855582932: ([kernel.kallsyms]) preempt_count_add
>> uname 5712 [007] 83.855582932: ([kernel.kallsyms]) in_lock_functions
>> uname 5712 [007] 83.855582932: ([kernel.kallsyms]) preempt_count_sub
>> uname 5712 [007] 83.855582932: ([kernel.kallsyms]) up_read
>> uname 5712 [007] 83.855582932: ([kernel.kallsyms]) preempt_count_add
>> uname 5712 [007] 83.855583348: ([kernel.kallsyms]) in_lock_functions
>> uname 5712 [007] 83.855583348: ([kernel.kallsyms]) preempt_count_sub
>> uname 5712 [007] 83.855583348: ([kernel.kallsyms]) _copy_to_user
>> uname 5712 [007] 83.855583557: ([kernel.kallsyms]) syscall_exit_to_user_mode
>> uname 5712 [007] 83.855583557: ([kernel.kallsyms]) syscall_exit_work
>> uname 5712 [007] 83.855583557: ([kernel.kallsyms]) perf_syscall_exit
>> uname 5712 [007] 83.855583557: ([kernel.kallsyms]) debug_smp_processor_id
>> uname 5712 [007] 83.855583557: ([kernel.kallsyms]) perf_trace_buf_alloc
>> uname 5712 [007] 83.855583557: ([kernel.kallsyms]) perf_swevent_get_recursion_context
>> uname 5712 [007] 83.855583557: ([kernel.kallsyms]) debug_smp_processor_id
>> uname 5712 [007] 83.855583557: ([kernel.kallsyms]) debug_smp_processor_id
>> uname 5712 [007] 83.855583557: ([kernel.kallsyms]) perf_tp_event
>> uname 5712 [007] 83.855583557: ([kernel.kallsyms]) perf_trace_buf_update
>> uname 5712 [007] 83.855583557: ([kernel.kallsyms]) tracing_gen_ctx_irq_test
>> uname 5712 [007] 83.855583557: ([kernel.kallsyms]) perf_swevent_event
>> uname 5712 [007] 83.855583765: ([kernel.kallsyms]) __perf_event_account_interrupt
>> uname 5712 [007] 83.855583765: ([kernel.kallsyms]) __this_cpu_preempt_check
>> uname 5712 [007] 83.855583765: ([kernel.kallsyms]) perf_event_output_forward
>> uname 5712 [007] 83.855583765: ([kernel.kallsyms]) perf_event_aux_pause
>> uname 5712 [007] 83.855583765: ([kernel.kallsyms]) ring_buffer_get
>> uname 5712 [007] 83.855583765: ([kernel.kallsyms]) __rcu_read_lock
>> uname 5712 [007] 83.855583765: ([kernel.kallsyms]) __rcu_read_unlock
>> uname 5712 [007] 83.855583765: ([kernel.kallsyms]) pt_event_stop
>> uname 5712 [007] 83.855583765: ([kernel.kallsyms]) debug_smp_processor_id
>> uname 5712 [007] 83.855583765: ([kernel.kallsyms]) debug_smp_processor_id
>> uname 5712 [007] 83.855583973: ([kernel.kallsyms]) native_write_msr
>> uname 5712 [007] 83.855583973: ([kernel.kallsyms]) native_write_msr
>> uname 5712 [007] 83.855584175: 0x0
>>
>> Signed-off-by: Adrian Hunter <adrian.hunter at intel.com>
>> ---
>> include/linux/perf_event.h | 15 +++++++
>> include/uapi/linux/perf_event.h | 11 ++++-
>> kernel/events/core.c | 72 +++++++++++++++++++++++++++++++--
>> kernel/events/internal.h | 1 +
>> 4 files changed, 95 insertions(+), 4 deletions(-)
>>
>> diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
>> index e85cd1c0eaf3..252c4aac3b79 100644
>> --- a/include/linux/perf_event.h
>> +++ b/include/linux/perf_event.h
>> @@ -291,6 +291,7 @@ struct perf_event_pmu_context;
>> #define PERF_PMU_CAP_NO_EXCLUDE 0x0040
>> #define PERF_PMU_CAP_AUX_OUTPUT 0x0080
>> #define PERF_PMU_CAP_EXTENDED_HW_TYPE 0x0100
>> +#define PERF_PMU_CAP_AUX_PAUSE 0x0200
>> struct perf_output_handle;
>> @@ -363,6 +364,8 @@ struct pmu {
>> #define PERF_EF_START 0x01 /* start the counter when adding */
>> #define PERF_EF_RELOAD 0x02 /* reload the counter when starting */
>> #define PERF_EF_UPDATE 0x04 /* update the counter when stopping */
>> +#define PERF_EF_PAUSE 0x08 /* AUX area event, pause tracing */
>> +#define PERF_EF_RESUME 0x10 /* AUX area event, resume tracing */
>> /*
>> * Adds/Removes a counter to/from the PMU, can be done inside a
>> @@ -402,6 +405,15 @@ struct pmu {
>> *
>> * ->start() with PERF_EF_RELOAD will reprogram the counter
>> * value, must be preceded by a ->stop() with PERF_EF_UPDATE.
>> + *
>> + * ->stop() with PERF_EF_PAUSE will stop as simply as possible. Will not
>> + * overlap another ->stop() with PERF_EF_PAUSE nor ->start() with
>> + * PERF_EF_RESUME.
>> + *
>> + * ->start() with PERF_EF_RESUME will start as simply as possible but
>> + * only if the counter is not otherwise stopped. Will not overlap
>> + * another ->start() with PERF_EF_RESUME nor ->stop() with
>> + * PERF_EF_PAUSE.
>> */
>> void (*start) (struct perf_event *event, int flags);
>> void (*stop) (struct perf_event *event, int flags);
>> @@ -797,6 +809,9 @@ struct perf_event {
>> /* for aux_output events */
>> struct perf_event *aux_event;
>> + /* for AUX area events */
>> + unsigned int aux_paused;
>> +
>> void (*destroy)(struct perf_event *);
>> struct rcu_head rcu_head;
>> diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
>> index 39c6a250dd1b..437bc2a8d50c 100644
>> --- a/include/uapi/linux/perf_event.h
>> +++ b/include/uapi/linux/perf_event.h
>> @@ -507,7 +507,16 @@ struct perf_event_attr {
>> __u16 sample_max_stack;
>> __u16 __reserved_2;
>> __u32 aux_sample_size;
>> - __u32 __reserved_3;
>> +
>> + union {
>> + __u32 aux_output_cfg;
>> + struct {
>> + __u64 aux_pause : 1, /* on overflow, pause AUX area tracing */
>
> Did you mean __u32 ? Otherwise look good to me.
True, thanks!
More information about the linux-arm-kernel
mailing list