Commit 6cd70754 authored by Rob Herring's avatar Rob Herring Committed by Arnaldo Carvalho de Melo
Browse files

libperf: Add evsel mmap support 



In order to support usersapce access, an event must be mmapped. While
there's already mmap support for evlist, the usecase is a bit different
than the self monitoring with userspace access. So let's add new
perf_evsel__mmap()/perf_evsel_munmap() functions to mmap/munmap an
evsel. This allows implementing userspace access as a fastpath for
perf_evsel__read().

The mmapped address is returned by perf_evsel__mmap_base() which
primarily for users/tests to check if userspace access is enabled.

Signed-off-by: default avatarRob Herring <robh@kernel.org>
Acked-by: default avatarJiri Olsa <jolsa@redhat.com>
Acked-by: default avatarNamhyung Kim <namhyung@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Itaru Kitayama <itaru.kitayama@gmail.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will@kernel.org>
Link: http://lore.kernel.org/lkml/20210414155412.3697605-2-robh@kernel.org


Signed-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
parent 2fc83c2c

tools/lib/perf/Documentation/libperf.txt

+3 −0
Original line number Diff line number Diff line
@@ -136,6 +136,9 @@ SYNOPSIS 
                       struct perf_thread_map *threads);

  void perf_evsel__close(struct perf_evsel *evsel);

  void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu);

  int perf_evsel__mmap(struct perf_evsel *evsel, int pages);

  void perf_evsel__munmap(struct perf_evsel *evsel);

  void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread);

  int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,

                       struct perf_counts_values *count);

  int perf_evsel__enable(struct perf_evsel *evsel);

tools/lib/perf/evsel.c

+76 −0
Original line number Diff line number Diff line
@@ -11,10 +11,12 @@ 
#include <stdlib.h>

#include <internal/xyarray.h>

#include <internal/cpumap.h>

#include <internal/mmap.h>

#include <internal/threadmap.h>

#include <internal/lib.h>

#include <linux/string.h>

#include <sys/ioctl.h>

#include <sys/mman.h>



void perf_evsel__init(struct perf_evsel *evsel, struct perf_event_attr *attr)

{
@@ -38,6 +40,7 @@ void perf_evsel__delete(struct perf_evsel *evsel) 
}



#define FD(e, x, y) (*(int *) xyarray__entry(e->fd, x, y))

#define MMAP(e, x, y) (e->mmap ? ((struct perf_mmap *) xyarray__entry(e->mmap, x, y)) : NULL)



int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)

{
@@ -55,6 +58,13 @@ int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) 
	return evsel->fd != NULL ? 0 : -ENOMEM;

}



static int perf_evsel__alloc_mmap(struct perf_evsel *evsel, int ncpus, int nthreads)

{

	evsel->mmap = xyarray__new(ncpus, nthreads, sizeof(struct perf_mmap));



	return evsel->mmap != NULL ? 0 : -ENOMEM;

}



static int

sys_perf_event_open(struct perf_event_attr *attr,

		    pid_t pid, int cpu, int group_fd,
@@ -156,6 +166,72 @@ void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu) 
	perf_evsel__close_fd_cpu(evsel, cpu);

}



void perf_evsel__munmap(struct perf_evsel *evsel)

{

	int cpu, thread;



	if (evsel->fd == NULL || evsel->mmap == NULL)

		return;



	for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {

		for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {

			int fd = FD(evsel, cpu, thread);

			struct perf_mmap *map = MMAP(evsel, cpu, thread);



			if (fd < 0)

				continue;



			perf_mmap__munmap(map);

		}

	}



	xyarray__delete(evsel->mmap);

	evsel->mmap = NULL;

}



int perf_evsel__mmap(struct perf_evsel *evsel, int pages)

{

	int ret, cpu, thread;

	struct perf_mmap_param mp = {

		.prot = PROT_READ | PROT_WRITE,

		.mask = (pages * page_size) - 1,

	};



	if (evsel->fd == NULL || evsel->mmap)

		return -EINVAL;



	if (perf_evsel__alloc_mmap(evsel, xyarray__max_x(evsel->fd), xyarray__max_y(evsel->fd)) < 0)

		return -ENOMEM;



	for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {

		for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {

			int fd = FD(evsel, cpu, thread);

			struct perf_mmap *map = MMAP(evsel, cpu, thread);



			if (fd < 0)

				continue;



			perf_mmap__init(map, NULL, false, NULL);



			ret = perf_mmap__mmap(map, &mp, fd, cpu);

			if (ret) {

				perf_evsel__munmap(evsel);

				return ret;

			}

		}

	}



	return 0;

}



void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread)

{

	if (FD(evsel, cpu, thread) < 0 || MMAP(evsel, cpu, thread) == NULL)

		return NULL;



	return MMAP(evsel, cpu, thread)->base;

}



int perf_evsel__read_size(struct perf_evsel *evsel)

{

	u64 read_format = evsel->attr.read_format;

tools/lib/perf/include/internal/evsel.h

+1 −0
Original line number Diff line number Diff line
@@ -41,6 +41,7 @@ struct perf_evsel { 
	struct perf_cpu_map	*own_cpus;

	struct perf_thread_map	*threads;

	struct xyarray		*fd;

	struct xyarray		*mmap;

	struct xyarray		*sample_id;

	u64			*id;

	u32			 ids;

tools/lib/perf/include/perf/evsel.h

+3 −0
Original line number Diff line number Diff line
@@ -27,6 +27,9 @@ LIBPERF_API int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map * 
				 struct perf_thread_map *threads);

LIBPERF_API void perf_evsel__close(struct perf_evsel *evsel);

LIBPERF_API void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu);

LIBPERF_API int perf_evsel__mmap(struct perf_evsel *evsel, int pages);

LIBPERF_API void perf_evsel__munmap(struct perf_evsel *evsel);

LIBPERF_API void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread);

LIBPERF_API int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,

				 struct perf_counts_values *count);

LIBPERF_API int perf_evsel__enable(struct perf_evsel *evsel);

tools/lib/perf/libperf.map

+3 −0
Original line number Diff line number Diff line
@@ -23,6 +23,9 @@ LIBPERF_0.0.1 { 
		perf_evsel__disable;

		perf_evsel__open;

		perf_evsel__close;

		perf_evsel__mmap;

		perf_evsel__munmap;

		perf_evsel__mmap_base;

		perf_evsel__read;

		perf_evsel__cpus;

		perf_evsel__threads;