diff mbox series

[RFC,V2,1/4] perf/core: Add aux_pause, aux_resume, aux_start_paused

Message ID 20231208172449.35444-2-adrian.hunter@intel.com
State New
Headers
Series perf/core: Add ability for an event to "pause" or "resume" AUX area tracing |

Commit Message

Adrian Hunter Dec. 8, 2023, 5:24 p.m. UTC 
  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@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(-)

Comments

Arnaldo Carvalho de Melo Dec. 19, 2023, 1:42 p.m. UTC | #1 
Em Fri, Dec 08, 2023 at 07:24:46PM +0200, Adrian Hunter escreveu:
> 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.

We need this as well for the usual ring buffer, 'perf report' has:

        --switch-off <event>
                          Stop considering events after the occurrence of this event
        --switch-on <event>
                          Consider events after the occurrence of this event

And 'perf record' has:

       --switch-output-event
           Events that will cause the switch of the perf.data file, auto-selecting --switch-output=signal, the results are similar as internally the side band thread will also send a
           SIGUSR2 to the main one.

But those are all in userspace, what you're doing is in the kernel, and
for the example you used synchronous, i.e. you're only interested in
what happens after you enter the syscall and then stop when the syscall
exits (but here you'll catch more stuff in the AUX trace, i.e. a "race"
from intel_pt inserting events in the AUX trace and then the syscall
exit switching it off).

Also being able to group the { resume, what-to-enable, pause } is
powerful, as we could have multiple such groups to record those
"slices", not just the --switch-off/--switch-on global ones.
 
> 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

User interface looks nice, asks for intel_pt to be armed but start
paused, collect just inside the kernel, then sets up another event to
enable the collection of whatever is using the aux area, intel_pt in
this case, and then one other event, sys_exit_newuname to pause it
again.

So this implicitely selects the CPU where the aux-resume took place and
in this specific case we ended up being lucky and that process wasn't
migrated to another CPU in the middle of the syscall...

Scratch that, you're not tracing system wide, but just the 'uname'
process being started from perf, perfect.



- Arnaldo

>  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@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 */
> +				aux_resume       :  1, /* on overflow, resume AUX area tracing */
> +				aux_start_paused :  1, /* start AUX area tracing paused */
> +				__reserved_3     : 29;
> +		};
> +	};
>  
>  	/*
>  	 * User provided data if sigtrap=1, passed back to user via
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index 4c72a41f11af..c1e11884d06e 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -2060,7 +2060,8 @@ static void perf_put_aux_event(struct perf_event *event)
>  
>  static bool perf_need_aux_event(struct perf_event *event)
>  {
> -	return !!event->attr.aux_output || !!event->attr.aux_sample_size;
> +	return event->attr.aux_output || event->attr.aux_sample_size ||
> +	       event->attr.aux_pause || event->attr.aux_resume;
>  }
>  
>  static int perf_get_aux_event(struct perf_event *event,
> @@ -2085,6 +2086,10 @@ static int perf_get_aux_event(struct perf_event *event,
>  	    !perf_aux_output_match(event, group_leader))
>  		return 0;
>  
> +	if ((event->attr.aux_pause || event->attr.aux_resume) &&
> +	    !(group_leader->pmu->capabilities & PERF_PMU_CAP_AUX_PAUSE))
> +		return 0;
> +
>  	if (event->attr.aux_sample_size && !group_leader->pmu->snapshot_aux)
>  		return 0;
>  
> @@ -7773,6 +7778,47 @@ void perf_prepare_header(struct perf_event_header *header,
>  	WARN_ON_ONCE(header->size & 7);
>  }
>  
> +static void __perf_event_aux_pause(struct perf_event *event, bool pause)
> +{
> +	if (pause) {
> +		if (!READ_ONCE(event->aux_paused)) {
> +			WRITE_ONCE(event->aux_paused, 1);
> +			event->pmu->stop(event, PERF_EF_PAUSE);
> +		}
> +	} else {
> +		if (READ_ONCE(event->aux_paused)) {
> +			WRITE_ONCE(event->aux_paused, 0);
> +			event->pmu->start(event, PERF_EF_RESUME);
> +		}
> +	}
> +}
> +
> +static void perf_event_aux_pause(struct perf_event *event, bool pause)
> +{
> +	struct perf_buffer *rb;
> +	unsigned long flags;
> +
> +	if (WARN_ON_ONCE(!event))
> +		return;
> +
> +	rb = ring_buffer_get(event);
> +	if (!rb)
> +		return;
> +
> +	local_irq_save(flags);
> +	/* Guard against NMI, NMI loses here */
> +	if (READ_ONCE(rb->aux_in_pause_resume))
> +		goto out_restore;
> +	WRITE_ONCE(rb->aux_in_pause_resume, 1);
> +	barrier();
> +	__perf_event_aux_pause(event, pause);
> +	barrier();
> +	WRITE_ONCE(rb->aux_in_pause_resume, 0);
> +out_restore:
> +	local_irq_restore(flags);
> +	ring_buffer_put(rb);
> +}
> +
>  static __always_inline int
>  __perf_event_output(struct perf_event *event,
>  		    struct perf_sample_data *data,
> @@ -7786,6 +7832,9 @@ __perf_event_output(struct perf_event *event,
>  	struct perf_event_header header;
>  	int err;
>  
> +	if (event->attr.aux_pause)
> +		perf_event_aux_pause(event->aux_event, true);
> +
>  	/* protect the callchain buffers */
>  	rcu_read_lock();
>  
> @@ -7802,6 +7851,10 @@ __perf_event_output(struct perf_event *event,
>  
>  exit:
>  	rcu_read_unlock();
> +
> +	if (event->attr.aux_resume)
> +		perf_event_aux_pause(event->aux_event, false);
> +
>  	return err;
>  }
>  
> @@ -11941,10 +11994,23 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
>  	}
>  
>  	if (event->attr.aux_output &&
> -	    !(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT)) {
> +	    (!(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT) ||
> +	     event->attr.aux_pause || event->attr.aux_resume)) {
> +		err = -EOPNOTSUPP;
> +		goto err_pmu;
> +	}
> +
> +	if (event->attr.aux_pause && event->attr.aux_resume) {
> +		err = -EINVAL;
> +		goto err_pmu;
> +	}
> +
> +	if (event->attr.aux_start_paused &&
> +	    !(pmu->capabilities & PERF_PMU_CAP_AUX_PAUSE)) {
>  		err = -EOPNOTSUPP;
>  		goto err_pmu;
>  	}
> +	event->aux_paused = event->attr.aux_start_paused;
>  
>  	if (cgroup_fd != -1) {
>  		err = perf_cgroup_connect(cgroup_fd, event, attr, group_leader);
> @@ -12741,7 +12807,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
>  	 * Grouping is not supported for kernel events, neither is 'AUX',
>  	 * make sure the caller's intentions are adjusted.
>  	 */
> -	if (attr->aux_output)
> +	if (attr->aux_output || attr->aux_output_cfg)
>  		return ERR_PTR(-EINVAL);
>  
>  	event = perf_event_alloc(attr, cpu, task, NULL, NULL,
> diff --git a/kernel/events/internal.h b/kernel/events/internal.h
> index 5150d5f84c03..3320f78117dc 100644
> --- a/kernel/events/internal.h
> +++ b/kernel/events/internal.h
> @@ -51,6 +51,7 @@ struct perf_buffer {
>  	void				(*free_aux)(void *);
>  	refcount_t			aux_refcount;
>  	int				aux_in_sampling;
> +	int				aux_in_pause_resume;
>  	void				**aux_pages;
>  	void				*aux_priv;
>  
> -- 
> 2.34.1
>
James Clark Dec. 20, 2023, 3:54 p.m. UTC | #2 
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

I think it might be useful to have an aux-toggle option as well, and
then you could do sampling if you put it on a PMU counter with an
interval. Unless you can make two events for the same counter with
different intervals, and one does resume and the other does pause? I'm
not sure if that would work?

Other than that it looks ok. I got Coresight working with a couple of
changes to what you posted on here, but that can always be done more
thoroughly later if we leave PERF_PMU_CAP_AUX_PAUSE off Coresight for now.

Thanks
James
Adrian Hunter Dec. 20, 2023, 4:16 p.m. UTC | #3 
On 20/12/23 17:54, James Clark 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
> 
> I think it might be useful to have an aux-toggle option as well, and
> then you could do sampling if you put it on a PMU counter with an
> interval. Unless you can make two events for the same counter with
> different intervals, and one does resume and the other does pause? I'm
> not sure if that would work?

There is already ->snapshot_aux() for sampling. Is that what you mean?

> 
> Other than that it looks ok. I got Coresight working with a couple of
> changes to what you posted on here, but that can always be done more
> thoroughly later if we leave PERF_PMU_CAP_AUX_PAUSE off Coresight for now.

Thanks a lot for looking at this!
Suzuki K Poulose Dec. 20, 2023, 5:41 p.m. UTC | #4 
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@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.

Suzuki

> +				aux_resume       :  1, /* on overflow, resume AUX area tracing */
> +				aux_start_paused :  1, /* start AUX area tracing paused */
> +				__reserved_3     : 29;
> +		};
> +	};
>   
>   	/*
>   	 * User provided data if sigtrap=1, passed back to user via
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index 4c72a41f11af..c1e11884d06e 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -2060,7 +2060,8 @@ static void perf_put_aux_event(struct perf_event *event)
>   
>   static bool perf_need_aux_event(struct perf_event *event)
>   {
> -	return !!event->attr.aux_output || !!event->attr.aux_sample_size;
> +	return event->attr.aux_output || event->attr.aux_sample_size ||
> +	       event->attr.aux_pause || event->attr.aux_resume;
>   }
>   
>   static int perf_get_aux_event(struct perf_event *event,
> @@ -2085,6 +2086,10 @@ static int perf_get_aux_event(struct perf_event *event,
>   	    !perf_aux_output_match(event, group_leader))
>   		return 0;
>   
> +	if ((event->attr.aux_pause || event->attr.aux_resume) &&
> +	    !(group_leader->pmu->capabilities & PERF_PMU_CAP_AUX_PAUSE))
> +		return 0;
> +
>   	if (event->attr.aux_sample_size && !group_leader->pmu->snapshot_aux)
>   		return 0;
>   
> @@ -7773,6 +7778,47 @@ void perf_prepare_header(struct perf_event_header *header,
>   	WARN_ON_ONCE(header->size & 7);
>   }
>   
> +static void __perf_event_aux_pause(struct perf_event *event, bool pause)
> +{
> +	if (pause) {
> +		if (!READ_ONCE(event->aux_paused)) {
> +			WRITE_ONCE(event->aux_paused, 1);
> +			event->pmu->stop(event, PERF_EF_PAUSE);
> +		}
> +	} else {
> +		if (READ_ONCE(event->aux_paused)) {
> +			WRITE_ONCE(event->aux_paused, 0);
> +			event->pmu->start(event, PERF_EF_RESUME);
> +		}
> +	}
> +}
> +
> +static void perf_event_aux_pause(struct perf_event *event, bool pause)
> +{
> +	struct perf_buffer *rb;
> +	unsigned long flags;
> +
> +	if (WARN_ON_ONCE(!event))
> +		return;
> +
> +	rb = ring_buffer_get(event);
> +	if (!rb)
> +		return;
> +
> +	local_irq_save(flags);
> +	/* Guard against NMI, NMI loses here */
> +	if (READ_ONCE(rb->aux_in_pause_resume))
> +		goto out_restore;
> +	WRITE_ONCE(rb->aux_in_pause_resume, 1);
> +	barrier();
> +	__perf_event_aux_pause(event, pause);
> +	barrier();
> +	WRITE_ONCE(rb->aux_in_pause_resume, 0);
> +out_restore:
> +	local_irq_restore(flags);
> +	ring_buffer_put(rb);
> +}
> +
>   static __always_inline int
>   __perf_event_output(struct perf_event *event,
>   		    struct perf_sample_data *data,
> @@ -7786,6 +7832,9 @@ __perf_event_output(struct perf_event *event,
>   	struct perf_event_header header;
>   	int err;
>   
> +	if (event->attr.aux_pause)
> +		perf_event_aux_pause(event->aux_event, true);
> +
>   	/* protect the callchain buffers */
>   	rcu_read_lock();
>   
> @@ -7802,6 +7851,10 @@ __perf_event_output(struct perf_event *event,
>   
>   exit:
>   	rcu_read_unlock();
> +
> +	if (event->attr.aux_resume)
> +		perf_event_aux_pause(event->aux_event, false);
> +
>   	return err;
>   }
>   
> @@ -11941,10 +11994,23 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
>   	}
>   
>   	if (event->attr.aux_output &&
> -	    !(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT)) {
> +	    (!(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT) ||
> +	     event->attr.aux_pause || event->attr.aux_resume)) {
> +		err = -EOPNOTSUPP;
> +		goto err_pmu;
> +	}
> +
> +	if (event->attr.aux_pause && event->attr.aux_resume) {
> +		err = -EINVAL;
> +		goto err_pmu;
> +	}
> +
> +	if (event->attr.aux_start_paused &&
> +	    !(pmu->capabilities & PERF_PMU_CAP_AUX_PAUSE)) {
>   		err = -EOPNOTSUPP;
>   		goto err_pmu;
>   	}
> +	event->aux_paused = event->attr.aux_start_paused;
>   
>   	if (cgroup_fd != -1) {
>   		err = perf_cgroup_connect(cgroup_fd, event, attr, group_leader);
> @@ -12741,7 +12807,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
>   	 * Grouping is not supported for kernel events, neither is 'AUX',
>   	 * make sure the caller's intentions are adjusted.
>   	 */
> -	if (attr->aux_output)
> +	if (attr->aux_output || attr->aux_output_cfg)
>   		return ERR_PTR(-EINVAL);
>   
>   	event = perf_event_alloc(attr, cpu, task, NULL, NULL,
> diff --git a/kernel/events/internal.h b/kernel/events/internal.h
> index 5150d5f84c03..3320f78117dc 100644
> --- a/kernel/events/internal.h
> +++ b/kernel/events/internal.h
> @@ -51,6 +51,7 @@ struct perf_buffer {
>   	void				(*free_aux)(void *);
>   	refcount_t			aux_refcount;
>   	int				aux_in_sampling;
> +	int				aux_in_pause_resume;
>   	void				**aux_pages;
>   	void				*aux_priv;
>
James Clark Dec. 21, 2023, 10:05 a.m. UTC | #5 
On 20/12/2023 16:16, Adrian Hunter wrote:
> On 20/12/23 17:54, James Clark 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
>>
>> I think it might be useful to have an aux-toggle option as well, and
>> then you could do sampling if you put it on a PMU counter with an
>> interval. Unless you can make two events for the same counter with
>> different intervals, and one does resume and the other does pause? I'm
>> not sure if that would work?
> 
> There is already ->snapshot_aux() for sampling. Is that what you mean?
> 

I suppose that mostly handles that use case yes. Although there are some
slight differences. It looks like for SAMPLE_AUX, the buffer size for
each sample is fixed and limited to 16 bits in size, whereas between
pause and resume you could potentially have multiple buffers delivered
to userspace of any size.

And it looks like SAMPLE_AUX would leave the trace running even when no
samples were being collected. I suppose you might not want to consume
the memory bandwidth and turn the trace off between samples, which
pause/resume does. Especially if you intend to have long periods between
the samples.

I think if it did turn out to be useful the toggle function can easily
be added later, so I don't intend this comment to be a blocking one.


>>
>> Other than that it looks ok. I got Coresight working with a couple of
>> changes to what you posted on here, but that can always be done more
>> thoroughly later if we leave PERF_PMU_CAP_AUX_PAUSE off Coresight for now.
> 
> Thanks a lot for looking at this!
>
Adrian Hunter Jan. 5, 2024, 12:57 p.m. UTC | #6 
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@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!
diff mbox series

Patch

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 */
+				aux_resume       :  1, /* on overflow, resume AUX area tracing */
+				aux_start_paused :  1, /* start AUX area tracing paused */
+				__reserved_3     : 29;
+		};
+	};
 
 	/*
 	 * User provided data if sigtrap=1, passed back to user via
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4c72a41f11af..c1e11884d06e 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2060,7 +2060,8 @@  static void perf_put_aux_event(struct perf_event *event)
 
 static bool perf_need_aux_event(struct perf_event *event)
 {
-	return !!event->attr.aux_output || !!event->attr.aux_sample_size;
+	return event->attr.aux_output || event->attr.aux_sample_size ||
+	       event->attr.aux_pause || event->attr.aux_resume;
 }
 
 static int perf_get_aux_event(struct perf_event *event,
@@ -2085,6 +2086,10 @@  static int perf_get_aux_event(struct perf_event *event,
 	    !perf_aux_output_match(event, group_leader))
 		return 0;
 
+	if ((event->attr.aux_pause || event->attr.aux_resume) &&
+	    !(group_leader->pmu->capabilities & PERF_PMU_CAP_AUX_PAUSE))
+		return 0;
+
 	if (event->attr.aux_sample_size && !group_leader->pmu->snapshot_aux)
 		return 0;
 
@@ -7773,6 +7778,47 @@  void perf_prepare_header(struct perf_event_header *header,
 	WARN_ON_ONCE(header->size & 7);
 }
 
+static void __perf_event_aux_pause(struct perf_event *event, bool pause)
+{
+	if (pause) {
+		if (!READ_ONCE(event->aux_paused)) {
+			WRITE_ONCE(event->aux_paused, 1);
+			event->pmu->stop(event, PERF_EF_PAUSE);
+		}
+	} else {
+		if (READ_ONCE(event->aux_paused)) {
+			WRITE_ONCE(event->aux_paused, 0);
+			event->pmu->start(event, PERF_EF_RESUME);
+		}
+	}
+}
+
+static void perf_event_aux_pause(struct perf_event *event, bool pause)
+{
+	struct perf_buffer *rb;
+	unsigned long flags;
+
+	if (WARN_ON_ONCE(!event))
+		return;
+
+	rb = ring_buffer_get(event);
+	if (!rb)
+		return;
+
+	local_irq_save(flags);
+	/* Guard against NMI, NMI loses here */
+	if (READ_ONCE(rb->aux_in_pause_resume))
+		goto out_restore;
+	WRITE_ONCE(rb->aux_in_pause_resume, 1);
+	barrier();
+	__perf_event_aux_pause(event, pause);
+	barrier();
+	WRITE_ONCE(rb->aux_in_pause_resume, 0);
+out_restore:
+	local_irq_restore(flags);
+	ring_buffer_put(rb);
+}
+
 static __always_inline int
 __perf_event_output(struct perf_event *event,
 		    struct perf_sample_data *data,
@@ -7786,6 +7832,9 @@  __perf_event_output(struct perf_event *event,
 	struct perf_event_header header;
 	int err;
 
+	if (event->attr.aux_pause)
+		perf_event_aux_pause(event->aux_event, true);
+
 	/* protect the callchain buffers */
 	rcu_read_lock();
 
@@ -7802,6 +7851,10 @@  __perf_event_output(struct perf_event *event,
 
 exit:
 	rcu_read_unlock();
+
+	if (event->attr.aux_resume)
+		perf_event_aux_pause(event->aux_event, false);
+
 	return err;
 }
 
@@ -11941,10 +11994,23 @@  perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	}
 
 	if (event->attr.aux_output &&
-	    !(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT)) {
+	    (!(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT) ||
+	     event->attr.aux_pause || event->attr.aux_resume)) {
+		err = -EOPNOTSUPP;
+		goto err_pmu;
+	}
+
+	if (event->attr.aux_pause && event->attr.aux_resume) {
+		err = -EINVAL;
+		goto err_pmu;
+	}
+
+	if (event->attr.aux_start_paused &&
+	    !(pmu->capabilities & PERF_PMU_CAP_AUX_PAUSE)) {
 		err = -EOPNOTSUPP;
 		goto err_pmu;
 	}
+	event->aux_paused = event->attr.aux_start_paused;
 
 	if (cgroup_fd != -1) {
 		err = perf_cgroup_connect(cgroup_fd, event, attr, group_leader);
@@ -12741,7 +12807,7 @@  perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 	 * Grouping is not supported for kernel events, neither is 'AUX',
 	 * make sure the caller's intentions are adjusted.
 	 */
-	if (attr->aux_output)
+	if (attr->aux_output || attr->aux_output_cfg)
 		return ERR_PTR(-EINVAL);
 
 	event = perf_event_alloc(attr, cpu, task, NULL, NULL,
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 5150d5f84c03..3320f78117dc 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -51,6 +51,7 @@  struct perf_buffer {
 	void				(*free_aux)(void *);
 	refcount_t			aux_refcount;
 	int				aux_in_sampling;
+	int				aux_in_pause_resume;
 	void				**aux_pages;
 	void				*aux_priv;