Commit 9597f088 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge tag 'perf-tools-fixes-for-v6.0-2022-09-21' of... 

Merge tag 'perf-tools-fixes-for-v6.0-2022-09-21' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Fix polling of system-wide events related to mixing per-cpu and
   per-thread events.

 - Do not check if /proc/modules is unchanged when copying /proc/kcore,
   that doesn't get in the way of post processing analysis.

 - Include program header in ELF files generated for JIT files, so that
   they can be opened by tools using elfutils libraries.

 - Enter namespaces when synthesizing build-ids.

 - Fix some bugs related to a recent cpu_map overhaul where we should be
   using an index and not the cpu number.

 - Fix BPF program ELF section name, using the naming expected by libbpf
   when using BPF counters in 'perf stat'.

 - Add a new test for perf stat cgroup BPF counter.

 - Adjust check on 'perf test wp' for older kernels, where the
   PERF_EVENT_IOC_MODIFY_ATTRIBUTES ioctl isn't supported.

 - Sync x86 cpufeatures with the kernel sources, no changes in tooling.

* tag 'perf-tools-fixes-for-v6.0-2022-09-21' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux:
  perf tools: Honor namespace when synthesizing build-ids
  tools headers cpufeatures: Sync with the kernel sources
  perf kcore_copy: Do not check /proc/modules is unchanged
  libperf evlist: Fix polling of system-wide events
  perf record: Fix cpu mask bit setting for mixed mmaps
  perf test: Skip wp modify test on old kernels
  perf jit: Include program header in ELF files
  perf test: Add a new test for perf stat cgroup BPF counter
  perf stat: Use evsel->core.cpus to iterate cpus in BPF cgroup counters
  perf stat: Fix cpu map index in bperf cgroup code
  perf stat: Fix BPF program section name
parents dc164f4f 999e4eaa

tools/arch/x86/include/asm/cpufeatures.h

+3 −2
Original line number Diff line number Diff line
@@ -457,7 +457,8 @@ 
#define X86_BUG_ITLB_MULTIHIT		X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */

#define X86_BUG_SRBDS			X86_BUG(24) /* CPU may leak RNG bits if not mitigated */

#define X86_BUG_MMIO_STALE_DATA		X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */

#define X86_BUG_RETBLEED		X86_BUG(26) /* CPU is affected by RETBleed */

#define X86_BUG_EIBRS_PBRSB		X86_BUG(27) /* EIBRS is vulnerable to Post Barrier RSB Predictions */

#define X86_BUG_MMIO_UNKNOWN		X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */

#define X86_BUG_RETBLEED		X86_BUG(27) /* CPU is affected by RETBleed */

#define X86_BUG_EIBRS_PBRSB		X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */



#endif /* _ASM_X86_CPUFEATURES_H */

tools/lib/perf/evlist.c

+3 −2
Original line number Diff line number Diff line
@@ -441,6 +441,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, 


	perf_evlist__for_each_entry(evlist, evsel) {

		bool overwrite = evsel->attr.write_backward;

		enum fdarray_flags flgs;

		struct perf_mmap *map;

		int *output, fd, cpu;
@@ -504,8 +505,8 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, 


		revent = !overwrite ? POLLIN : 0;



		if (!evsel->system_wide &&

		    perf_evlist__add_pollfd(evlist, fd, map, revent, fdarray_flag__default) < 0) {

		flgs = evsel->system_wide ? fdarray_flag__nonfilterable : fdarray_flag__default;

		if (perf_evlist__add_pollfd(evlist, fd, map, revent, flgs) < 0) {

			perf_mmap__put(map);

			return -1;

		}

tools/perf/builtin-record.c

+2 −0
Original line number Diff line number Diff line
@@ -3371,6 +3371,8 @@ static int record__mmap_cpu_mask_init(struct mmap_cpu_mask *mask, struct perf_cp 
		return 0;



	perf_cpu_map__for_each_cpu(cpu, idx, cpus) {

		if (cpu.cpu == -1)

			continue;

		/* Return ENODEV is input cpu is greater than max cpu */

		if ((unsigned long)cpu.cpu > mask->nbits)

			return -ENODEV;

tools/perf/tests/shell/stat_bpf_counters_cgrp.sh

0 → 100755
+83 −0
Original line number Diff line number Diff line 
#!/bin/sh

# perf stat --bpf-counters --for-each-cgroup test

# SPDX-License-Identifier: GPL-2.0



set -e



test_cgroups=

if [ "$1" = "-v" ]; then

	verbose="1"

fi



# skip if --bpf-counters --for-each-cgroup is not supported

check_bpf_counter()

{

	if ! perf stat -a --bpf-counters --for-each-cgroup / true > /dev/null 2>&1; then

		if [ "${verbose}" = "1" ]; then

			echo "Skipping: --bpf-counters --for-each-cgroup not supported"

			perf --no-pager stat -a --bpf-counters --for-each-cgroup / true || true

		fi

		exit 2

	fi

}



# find two cgroups to measure

find_cgroups()

{

	# try usual systemd slices first

	if [ -d /sys/fs/cgroup/system.slice -a -d /sys/fs/cgroup/user.slice ]; then

		test_cgroups="system.slice,user.slice"

		return

	fi



	# try root and self cgroups

	local self_cgrp=$(grep perf_event /proc/self/cgroup | cut -d: -f3)

	if [ -z ${self_cgrp} ]; then

		# cgroup v2 doesn't specify perf_event

		self_cgrp=$(grep ^0: /proc/self/cgroup | cut -d: -f3)

	fi



	if [ -z ${self_cgrp} ]; then

		test_cgroups="/"

	else

		test_cgroups="/,${self_cgrp}"

	fi

}



# As cgroup events are cpu-wide, we cannot simply compare the result.

# Just check if it runs without failure and has non-zero results.

check_system_wide_counted()

{

	local output



	output=$(perf stat -a --bpf-counters --for-each-cgroup ${test_cgroups} -e cpu-clock -x, sleep 1  2>&1)

	if echo ${output} | grep -q -F "<not "; then

		echo "Some system-wide events are not counted"

		if [ "${verbose}" = "1" ]; then

			echo ${output}

		fi

		exit 1

	fi

}



check_cpu_list_counted()

{

	local output



	output=$(perf stat -C 1 --bpf-counters --for-each-cgroup ${test_cgroups} -e cpu-clock -x, taskset -c 1 sleep 1  2>&1)

	if echo ${output} | grep -q -F "<not "; then

		echo "Some CPU events are not counted"

		if [ "${verbose}" = "1" ]; then

			echo ${output}

		fi

		exit 1

	fi

}



check_bpf_counter

find_cgroups



check_system_wide_counted

check_cpu_list_counted



exit 0

tools/perf/tests/wp.c

+8 −2
Original line number Diff line number Diff line
@@ -2,7 +2,9 @@ 
#include <stdlib.h>

#include <string.h>

#include <unistd.h>

#include <errno.h>

#include <sys/ioctl.h>

#include <linux/compiler.h>

#include <linux/hw_breakpoint.h>

#include <linux/kernel.h>

#include "tests.h"
@@ -137,8 +139,7 @@ static int test__wp_rw(struct test_suite *test __maybe_unused, 
#endif

}



static int test__wp_modify(struct test_suite *test __maybe_unused,

			   int subtest __maybe_unused)

static int test__wp_modify(struct test_suite *test __maybe_unused, int subtest __maybe_unused)

{

#if defined(__s390x__)

	return TEST_SKIP;
@@ -160,6 +161,11 @@ static int test__wp_modify(struct test_suite *test __maybe_unused, 
	new_attr.disabled = 1;

	ret = ioctl(fd, PERF_EVENT_IOC_MODIFY_ATTRIBUTES, &new_attr);

	if (ret < 0) {

		if (errno == ENOTTY) {

			test->test_cases[subtest].skip_reason = "missing kernel support";

			ret = TEST_SKIP;

		}



		pr_debug("ioctl(PERF_EVENT_IOC_MODIFY_ATTRIBUTES) failed\n");

		close(fd);

		return ret;