summaryrefslogtreecommitdiff
path: root/tools/perf
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf')
-rw-r--r--tools/perf/arch/powerpc/entry/syscalls/syscall.tbl24
-rw-r--r--tools/perf/builtin-record.c2
-rw-r--r--tools/perf/tests/mmap-basic.c3
-rw-r--r--tools/perf/tests/perf-record.c2
-rwxr-xr-xtools/perf/tests/shell/record.sh2
-rwxr-xr-xtools/perf/tests/shell/stat_bpf_counters_cgrp.sh83
-rwxr-xr-xtools/perf/tests/shell/test_brstack.sh3
-rw-r--r--tools/perf/tests/vmlinux-kallsyms.c5
-rw-r--r--tools/perf/tests/wp.c10
-rw-r--r--tools/perf/util/Build2
-rw-r--r--tools/perf/util/arm-spe.c2
-rw-r--r--tools/perf/util/bpf_counter_cgroup.c10
-rw-r--r--tools/perf/util/bpf_skel/bperf_cgroup.bpf.c13
-rw-r--r--tools/perf/util/bpf_skel/off_cpu.bpf.c18
-rw-r--r--tools/perf/util/genelf.c14
-rw-r--r--tools/perf/util/genelf.h4
-rw-r--r--tools/perf/util/parse-events-hybrid.c21
-rw-r--r--tools/perf/util/parse-events.c39
-rw-r--r--tools/perf/util/parse-events.h1
-rw-r--r--tools/perf/util/print-events.c39
-rw-r--r--tools/perf/util/scripting-engines/Build2
-rw-r--r--tools/perf/util/symbol-elf.c7
-rw-r--r--tools/perf/util/synthetic-events.c17
23 files changed, 237 insertions, 86 deletions
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index 2600b4237292..2bca64f96164 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -110,7 +110,7 @@
79 common settimeofday sys_settimeofday compat_sys_settimeofday
80 common getgroups sys_getgroups
81 common setgroups sys_setgroups
-82 32 select ppc_select sys_ni_syscall
+82 32 select sys_old_select compat_sys_old_select
82 64 select sys_ni_syscall
82 spu select sys_ni_syscall
83 common symlink sys_symlink
@@ -178,9 +178,9 @@
133 common fchdir sys_fchdir
134 common bdflush sys_ni_syscall
135 common sysfs sys_sysfs
-136 32 personality sys_personality ppc64_personality
-136 64 personality ppc64_personality
-136 spu personality ppc64_personality
+136 32 personality sys_personality compat_sys_ppc64_personality
+136 64 personality sys_ppc64_personality
+136 spu personality sys_ppc64_personality
137 common afs_syscall sys_ni_syscall
138 common setfsuid sys_setfsuid
139 common setfsgid sys_setfsgid
@@ -228,8 +228,8 @@
176 64 rt_sigtimedwait sys_rt_sigtimedwait
177 nospu rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo
178 nospu rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend
-179 common pread64 sys_pread64 compat_sys_pread64
-180 common pwrite64 sys_pwrite64 compat_sys_pwrite64
+179 common pread64 sys_pread64 compat_sys_ppc_pread64
+180 common pwrite64 sys_pwrite64 compat_sys_ppc_pwrite64
181 common chown sys_chown
182 common getcwd sys_getcwd
183 common capget sys_capget
@@ -242,10 +242,10 @@
188 common putpmsg sys_ni_syscall
189 nospu vfork sys_vfork
190 common ugetrlimit sys_getrlimit compat_sys_getrlimit
-191 common readahead sys_readahead compat_sys_readahead
+191 common readahead sys_readahead compat_sys_ppc_readahead
192 32 mmap2 sys_mmap2 compat_sys_mmap2
-193 32 truncate64 sys_truncate64 compat_sys_truncate64
-194 32 ftruncate64 sys_ftruncate64 compat_sys_ftruncate64
+193 32 truncate64 sys_truncate64 compat_sys_ppc_truncate64
+194 32 ftruncate64 sys_ftruncate64 compat_sys_ppc_ftruncate64
195 32 stat64 sys_stat64
196 32 lstat64 sys_lstat64
197 32 fstat64 sys_fstat64
@@ -288,7 +288,7 @@
230 common io_submit sys_io_submit compat_sys_io_submit
231 common io_cancel sys_io_cancel
232 nospu set_tid_address sys_set_tid_address
-233 common fadvise64 sys_fadvise64 ppc32_fadvise64
+233 common fadvise64 sys_fadvise64 compat_sys_ppc32_fadvise64
234 nospu exit_group sys_exit_group
235 nospu lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie
236 common epoll_create sys_epoll_create
@@ -323,7 +323,7 @@
251 spu utimes sys_utimes
252 common statfs64 sys_statfs64 compat_sys_statfs64
253 common fstatfs64 sys_fstatfs64 compat_sys_fstatfs64
-254 32 fadvise64_64 ppc_fadvise64_64
+254 32 fadvise64_64 sys_ppc_fadvise64_64
254 spu fadvise64_64 sys_ni_syscall
255 common rtas sys_rtas
256 32 sys_debug_setcontext sys_debug_setcontext sys_ni_syscall
@@ -390,7 +390,7 @@
305 common signalfd sys_signalfd compat_sys_signalfd
306 common timerfd_create sys_timerfd_create
307 common eventfd sys_eventfd
-308 common sync_file_range2 sys_sync_file_range2 compat_sys_sync_file_range2
+308 common sync_file_range2 sys_sync_file_range2 compat_sys_ppc_sync_file_range2
309 nospu fallocate sys_fallocate compat_sys_fallocate
310 nospu subpage_prot sys_subpage_prot
311 32 timerfd_settime sys_timerfd_settime32
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index f87ef43eb820..0f711f88894c 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -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;
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index dfb6173b2a82..9e9a2b67de19 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -114,8 +114,7 @@ static int test__basic_mmap(struct test_suite *test __maybe_unused, int subtest
for (i = 0; i < nsyscalls; ++i)
for (j = 0; j < expected_nr_events[i]; ++j) {
- int foo = syscalls[i]();
- ++foo;
+ syscalls[i]();
}
md = &evlist->mmap[0];
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 6a001fcfed68..4952abe716f3 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -332,7 +332,7 @@ out_delete_evlist:
out:
if (err == -EACCES)
return TEST_SKIP;
- if (err < 0)
+ if (err < 0 || errs != 0)
return TEST_FAIL;
return TEST_OK;
}
diff --git a/tools/perf/tests/shell/record.sh b/tools/perf/tests/shell/record.sh
index 00c7285ce1ac..301f95427159 100755
--- a/tools/perf/tests/shell/record.sh
+++ b/tools/perf/tests/shell/record.sh
@@ -61,7 +61,7 @@ test_register_capture() {
echo "Register capture test [Skipped missing registers]"
return
fi
- if ! perf record -o - --intr-regs=di,r8,dx,cx -e cpu/br_inst_retired.near_call/p \
+ if ! perf record -o - --intr-regs=di,r8,dx,cx -e br_inst_retired.near_call:p \
-c 1000 --per-thread true 2> /dev/null \
| perf script -F ip,sym,iregs -i - 2> /dev/null \
| egrep -q "DI:"
diff --git a/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh b/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh
new file mode 100755
index 000000000000..d724855d097c
--- /dev/null
+++ b/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh
@@ -0,0 +1,83 @@
+#!/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 ${output}
+ fi
+ exit 1
+ fi
+}
+
+check_bpf_counter
+find_cgroups
+
+check_system_wide_counted
+check_cpu_list_counted
+
+exit 0
diff --git a/tools/perf/tests/shell/test_brstack.sh b/tools/perf/tests/shell/test_brstack.sh
index c644f94a6500..ec801cffae6b 100755
--- a/tools/perf/tests/shell/test_brstack.sh
+++ b/tools/perf/tests/shell/test_brstack.sh
@@ -12,7 +12,8 @@ if ! [ -x "$(command -v cc)" ]; then
fi
# skip the test if the hardware doesn't support branch stack sampling
-perf record -b -o- -B true > /dev/null 2>&1 || exit 2
+# and if the architecture doesn't support filter types: any,save_type,u
+perf record -b -o- -B --branch-filter any,save_type,u true > /dev/null 2>&1 || exit 2
TMPDIR=$(mktemp -d /tmp/__perf_test.program.XXXXX)
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index 4fd8d703ff19..8ab035b55875 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -43,10 +43,11 @@ static bool is_ignored_symbol(const char *name, char type)
/* Symbol names that begin with the following are ignored.*/
static const char * const ignored_prefixes[] = {
"$", /* local symbols for ARM, MIPS, etc. */
- ".LASANPC", /* s390 kasan local symbols */
+ ".L", /* local labels, .LBB,.Ltmpxxx,.L__unnamed_xx,.LASANPC, etc. */
"__crc_", /* modversions */
"__efistub_", /* arm64 EFI stub namespace */
- "__kvm_nvhe_", /* arm64 non-VHE KVM namespace */
+ "__kvm_nvhe_$", /* arm64 local symbols in non-VHE KVM namespace */
+ "__kvm_nvhe_.L", /* arm64 local symbols in non-VHE KVM namespace */
"__AArch64ADRPThunk_", /* arm64 lld */
"__ARMV5PILongThunk_", /* arm lld */
"__ARMV7PILongThunk_",
diff --git a/tools/perf/tests/wp.c b/tools/perf/tests/wp.c
index 9d4c45184e71..56455da30341 100644
--- a/tools/perf/tests/wp.c
+++ b/tools/perf/tests/wp.c
@@ -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;
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 9dfae1bda9cc..485e1a343165 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -269,7 +269,7 @@ CFLAGS_expr-flex.o += $(flex_flags)
bison_flags := -DYYENABLE_NLS=0
BISON_GE_35 := $(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\)/\1\2/g') \>\= 35)
ifeq ($(BISON_GE_35),1)
- bison_flags += -Wno-unused-parameter -Wno-nested-externs -Wno-implicit-function-declaration -Wno-switch-enum
+ bison_flags += -Wno-unused-parameter -Wno-nested-externs -Wno-implicit-function-declaration -Wno-switch-enum -Wno-unused-but-set-variable -Wno-unknown-warning-option
else
bison_flags += -w
endif
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 22dcfe07e886..906476a839e1 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -498,7 +498,7 @@ static void arm_spe__synth_data_source_generic(const struct arm_spe_record *reco
static u64 arm_spe__synth_data_source(const struct arm_spe_record *record, u64 midr)
{
union perf_mem_data_src data_src = { 0 };
- bool is_neoverse = is_midr_in_range(midr, neoverse_spe);
+ bool is_neoverse = is_midr_in_range_list(midr, neoverse_spe);
if (record->op == ARM_SPE_LD)
data_src.mem_op = PERF_MEM_OP_LOAD;
diff --git a/tools/perf/util/bpf_counter_cgroup.c b/tools/perf/util/bpf_counter_cgroup.c
index 63b9db657442..3c2df7522f6f 100644
--- a/tools/perf/util/bpf_counter_cgroup.c
+++ b/tools/perf/util/bpf_counter_cgroup.c
@@ -95,7 +95,7 @@ static int bperf_load_program(struct evlist *evlist)
perf_cpu_map__for_each_cpu(cpu, i, evlist->core.all_cpus) {
link = bpf_program__attach_perf_event(skel->progs.on_cgrp_switch,
- FD(cgrp_switch, cpu.cpu));
+ FD(cgrp_switch, i));
if (IS_ERR(link)) {
pr_err("Failed to attach cgroup program\n");
err = PTR_ERR(link);
@@ -115,15 +115,15 @@ static int bperf_load_program(struct evlist *evlist)
evsel->cgrp = NULL;
/* open single copy of the events w/o cgroup */
- err = evsel__open_per_cpu(evsel, evlist->core.all_cpus, -1);
+ err = evsel__open_per_cpu(evsel, evsel->core.cpus, -1);
if (err) {
pr_err("Failed to open first cgroup events\n");
goto out;
}
map_fd = bpf_map__fd(skel->maps.events);
- perf_cpu_map__for_each_cpu(cpu, j, evlist->core.all_cpus) {
- int fd = FD(evsel, cpu.cpu);
+ perf_cpu_map__for_each_cpu(cpu, j, evsel->core.cpus) {
+ int fd = FD(evsel, j);
__u32 idx = evsel->core.idx * total_cpus + cpu.cpu;
err = bpf_map_update_elem(map_fd, &idx, &fd,
@@ -269,7 +269,7 @@ static int bperf_cgrp__read(struct evsel *evsel)
goto out;
}
- perf_cpu_map__for_each_cpu(cpu, i, evlist->core.all_cpus) {
+ perf_cpu_map__for_each_cpu(cpu, i, evsel->core.cpus) {
counts = perf_counts(evsel->counts, i, 0);
counts->val = values[cpu.cpu].counter;
counts->ena = values[cpu.cpu].enabled;
diff --git a/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c b/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c
index 292c430768b5..9aa8cdd93de4 100644
--- a/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c
+++ b/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c
@@ -48,6 +48,7 @@ const volatile __u32 num_cpus = 1;
int enabled = 0;
int use_cgroup_v2 = 0;
+int perf_subsys_id = -1;
static inline int get_cgroup_v1_idx(__u32 *cgrps, int size)
{
@@ -58,7 +59,15 @@ static inline int get_cgroup_v1_idx(__u32 *cgrps, int size)
int level;
int cnt;
- cgrp = BPF_CORE_READ(p, cgroups, subsys[perf_event_cgrp_id], cgroup);
+ if (perf_subsys_id == -1) {
+#if __has_builtin(__builtin_preserve_enum_value)
+ perf_subsys_id = bpf_core_enum_value(enum cgroup_subsys_id,
+ perf_event_cgrp_id);
+#else
+ perf_subsys_id = perf_event_cgrp_id;
+#endif
+ }
+ cgrp = BPF_CORE_READ(p, cgroups, subsys[perf_subsys_id], cgroup);
level = BPF_CORE_READ(cgrp, level);
for (cnt = 0; i < MAX_LEVELS; i++) {
@@ -176,7 +185,7 @@ static int bperf_cgroup_count(void)
}
// This will be attached to cgroup-switches event for each cpu
-SEC("perf_events")
+SEC("perf_event")
int BPF_PROG(on_cgrp_switch)
{
return bperf_cgroup_count();
diff --git a/tools/perf/util/bpf_skel/off_cpu.bpf.c b/tools/perf/util/bpf_skel/off_cpu.bpf.c
index c4ba2bcf179f..38e3b287dbb2 100644
--- a/tools/perf/util/bpf_skel/off_cpu.bpf.c
+++ b/tools/perf/util/bpf_skel/off_cpu.bpf.c
@@ -94,6 +94,8 @@ const volatile bool has_prev_state = false;
const volatile bool needs_cgroup = false;
const volatile bool uses_cgroup_v1 = false;
+int perf_subsys_id = -1;
+
/*
* Old kernel used to call it task_struct->state and now it's '__state'.
* Use BPF CO-RE "ignored suffix rule" to deal with it like below:
@@ -119,11 +121,19 @@ static inline __u64 get_cgroup_id(struct task_struct *t)
{
struct cgroup *cgrp;
- if (uses_cgroup_v1)
- cgrp = BPF_CORE_READ(t, cgroups, subsys[perf_event_cgrp_id], cgroup);
- else
- cgrp = BPF_CORE_READ(t, cgroups, dfl_cgrp);
+ if (!uses_cgroup_v1)
+ return BPF_CORE_READ(t, cgroups, dfl_cgrp, kn, id);
+
+ if (perf_subsys_id == -1) {
+#if __has_builtin(__builtin_preserve_enum_value)
+ perf_subsys_id = bpf_core_enum_value(enum cgroup_subsys_id,
+ perf_event_cgrp_id);
+#else
+ perf_subsys_id = perf_event_cgrp_id;
+#endif
+ }
+ cgrp = BPF_CORE_READ(t, cgroups, subsys[perf_subsys_id], cgroup);
return BPF_CORE_READ(cgrp, kn, id);
}
diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c
index ed28a0dbcb7f..d81b54563e96 100644
--- a/tools/perf/util/genelf.c
+++ b/tools/perf/util/genelf.c
@@ -253,6 +253,7 @@ jit_write_elf(int fd, uint64_t load_addr, const char *sym,
Elf_Data *d;
Elf_Scn *scn;
Elf_Ehdr *ehdr;
+ Elf_Phdr *phdr;
Elf_Shdr *shdr;
uint64_t eh_frame_base_offset;
char *strsym = NULL;
@@ -288,6 +289,19 @@ jit_write_elf(int fd, uint64_t load_addr, const char *sym,
ehdr->e_shstrndx= unwinding ? 4 : 2; /* shdr index for section name */
/*
+ * setup program header
+ */
+ phdr = elf_newphdr(e, 1);
+ phdr[0].p_type = PT_LOAD;
+ phdr[0].p_offset = 0;
+ phdr[0].p_vaddr = 0;
+ phdr[0].p_paddr = 0;
+ phdr[0].p_filesz = csize;
+ phdr[0].p_memsz = csize;
+ phdr[0].p_flags = PF_X | PF_R;
+ phdr[0].p_align = 8;
+
+ /*
* setup text section
*/
scn = elf_newscn(e);
diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h
index ae138afe6c56..b5c909546e3f 100644
--- a/tools/perf/util/genelf.h
+++ b/tools/perf/util/genelf.h
@@ -53,8 +53,10 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent
#if GEN_ELF_CLASS == ELFCLASS64
#define elf_newehdr elf64_newehdr
+#define elf_newphdr elf64_newphdr
#define elf_getshdr elf64_getshdr
#define Elf_Ehdr Elf64_Ehdr
+#define Elf_Phdr Elf64_Phdr
#define Elf_Shdr Elf64_Shdr
#define Elf_Sym Elf64_Sym
#define ELF_ST_TYPE(a) ELF64_ST_TYPE(a)
@@ -62,8 +64,10 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent
#define ELF_ST_VIS(a) ELF64_ST_VISIBILITY(a)
#else
#define elf_newehdr elf32_newehdr
+#define elf_newphdr elf32_newphdr
#define elf_getshdr elf32_getshdr
#define Elf_Ehdr Elf32_Ehdr
+#define Elf_Phdr Elf32_Phdr
#define Elf_Shdr Elf32_Shdr
#define Elf_Sym Elf32_Sym
#define ELF_ST_TYPE(a) ELF32_ST_TYPE(a)
diff --git a/tools/perf/util/parse-events-hybrid.c b/tools/perf/util/parse-events-hybrid.c
index 284f8eabd3b9..7c9f9150bad5 100644
--- a/tools/perf/util/parse-events-hybrid.c
+++ b/tools/perf/util/parse-events-hybrid.c
@@ -33,7 +33,8 @@ static void config_hybrid_attr(struct perf_event_attr *attr,
* If the PMU type ID is 0, the PERF_TYPE_RAW will be applied.
*/
attr->type = type;
- attr->config = attr->config | ((__u64)pmu_type << PERF_PMU_TYPE_SHIFT);
+ attr->config = (attr->config & PERF_HW_EVENT_MASK) |
+ ((__u64)pmu_type << PERF_PMU_TYPE_SHIFT);
}
static int create_event_hybrid(__u32 config_type, int *idx,
@@ -48,13 +49,25 @@ static int create_event_hybrid(__u32 config_type, int *idx,
__u64 config = attr->config;
config_hybrid_attr(attr, config_type, pmu->type);
+
+ /*
+ * Some hybrid hardware cache events are only available on one CPU
+ * PMU. For example, the 'L1-dcache-load-misses' is only available
+ * on cpu_core, while the 'L1-icache-loads' is only available on
+ * cpu_atom. We need to remove "not supported" hybrid cache events.
+ */
+ if (attr->type == PERF_TYPE_HW_CACHE
+ && !is_event_supported(attr->type, attr->config))
+ return 0;
+
evsel = parse_events__add_event_hybrid(list, idx, attr, name, metric_id,
pmu, config_terms);
- if (evsel)
+ if (evsel) {
evsel->pmu_name = strdup(pmu->name);
- else
+ if (!evsel->pmu_name)
+ return -ENOMEM;
+ } else
return -ENOMEM;
-
attr->type = type;
attr->config = config;
return 0;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index f05e15acd33f..f3b2c2a87456 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -28,6 +28,7 @@
#include "util/parse-events-hybrid.h"
#include "util/pmu-hybrid.h"
#include "tracepoint.h"
+#include "thread_map.h"
#define MAX_NAME_LEN 100
@@ -157,6 +158,44 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = {
#define PERF_EVENT_TYPE(config) __PERF_EVENT_FIELD(config, TYPE)
#define PERF_EVENT_ID(config) __PERF_EVENT_FIELD(config, EVENT)
+bool is_event_supported(u8 type, u64 config)
+{
+ bool ret = true;
+ int open_return;
+ struct evsel *evsel;
+ struct perf_event_attr attr = {
+ .type = type,
+ .config = config,
+ .disabled = 1,
+ };
+ struct perf_thread_map *tmap = thread_map__new_by_tid(0);
+
+ if (tmap == NULL)
+ return false;
+
+ evsel = evsel__new(&attr);
+ if (evsel) {
+ open_return = evsel__open(evsel, NULL, tmap);
+ ret = open_return >= 0;
+
+ if (open_return == -EACCES) {
+ /*
+ * This happens if the paranoid value
+ * /proc/sys/kernel/perf_event_paranoid is set to 2
+ * Re-run with exclude_kernel set; we don't do that
+ * by default as some ARM machines do not support it.
+ *
+ */
+ evsel->core.attr.exclude_kernel = 1;
+ ret = evsel__open(evsel, NULL, tmap) >= 0;
+ }
+ evsel__delete(evsel);
+ }
+
+ perf_thread_map__put(tmap);
+ return ret;
+}
+
const char *event_type(int type)
{
switch (type) {
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 7e6a601d9cd0..07df7bb7b042 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -19,6 +19,7 @@ struct option;
struct perf_pmu;
bool have_tracepoints(struct list_head *evlist);
+bool is_event_supported(u8 type, u64 config);
const char *event_type(int type);
diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c
index ba1ab5134685..c4d5d87fae2f 100644
--- a/tools/perf/util/print-events.c
+++ b/tools/perf/util/print-events.c
@@ -22,7 +22,6 @@
#include "probe-file.h"
#include "string2.h"
#include "strlist.h"
-#include "thread_map.h"
#include "tracepoint.h"
#include "pfm.h"
#include "pmu-hybrid.h"
@@ -239,44 +238,6 @@ void print_sdt_events(const char *subsys_glob, const char *event_glob,
strlist__delete(sdtlist);
}
-static bool is_event_supported(u8 type, unsigned int config)
-{
- bool ret = true;
- int open_return;
- struct evsel *evsel;
- struct perf_event_attr attr = {
- .type = type,
- .config = config,
- .disabled = 1,
- };
- struct perf_thread_map *tmap = thread_map__new_by_tid(0);
-
- if (tmap == NULL)
- return false;
-
- evsel = evsel__new(&attr);
- if (evsel) {
- open_return = evsel__open(evsel, NULL, tmap);
- ret = open_return >= 0;
-
- if (open_return == -EACCES) {
- /*
- * This happens if the paranoid value
- * /proc/sys/kernel/perf_event_paranoid is set to 2
- * Re-run with exclude_kernel set; we don't do that
- * by default as some ARM machines do not support it.
- *
- */
- evsel->core.attr.exclude_kernel = 1;
- ret = evsel__open(evsel, NULL, tmap) >= 0;
- }
- evsel__delete(evsel);
- }
-
- perf_thread_map__put(tmap);
- return ret;
-}
-
int print_hwcache_events(const char *event_glob, bool name_only)
{
unsigned int type, op, i, evt_i = 0, evt_num = 0, npmus = 0;
diff --git a/tools/perf/util/scripting-engines/Build b/tools/perf/util/scripting-engines/Build
index c92326c2233a..0f5ba28339cf 100644
--- a/tools/perf/util/scripting-engines/Build
+++ b/tools/perf/util/scripting-engines/Build
@@ -3,4 +3,4 @@ perf-$(CONFIG_LIBPYTHON) += trace-event-python.o
CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-nested-externs -Wno-undef -Wno-switch-default -Wno-bad-function-cast -Wno-declaration-after-statement -Wno-switch-enum
-CFLAGS_trace-event-python.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-error=deprecated-declarations
+CFLAGS_trace-event-python.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-deprecated-declarations
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 75bec32d4f57..647b7dff8ef3 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -2102,8 +2102,8 @@ static int kcore_copy__compare_file(const char *from_dir, const char *to_dir,
* unusual. One significant peculiarity is that the mapping (start -> pgoff)
* is not the same for the kernel map and the modules map. That happens because
* the data is copied adjacently whereas the original kcore has gaps. Finally,
- * kallsyms and modules files are compared with their copies to check that
- * modules have not been loaded or unloaded while the copies were taking place.
+ * kallsyms file is compared with its copy to check that modules have not been
+ * loaded or unloaded while the copies were taking place.
*
* Return: %0 on success, %-1 on failure.
*/
@@ -2166,9 +2166,6 @@ int kcore_copy(const char *from_dir, const char *to_dir)
goto out_extract_close;
}
- if (kcore_copy__compare_file(from_dir, to_dir, "modules"))
- goto out_extract_close;
-
if (kcore_copy__compare_file(from_dir, to_dir, "kallsyms"))
goto out_extract_close;
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index 812424dbf2d5..538790758e24 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -367,13 +367,24 @@ static void perf_record_mmap2__read_build_id(struct perf_record_mmap2 *event,
bool is_kernel)
{
struct build_id bid;
+ struct nsinfo *nsi;
+ struct nscookie nc;
int rc;
- if (is_kernel)
+ if (is_kernel) {
rc = sysfs__read_build_id("/sys/kernel/notes", &bid);
- else
- rc = filename__read_build_id(event->filename, &bid) > 0 ? 0 : -1;
+ goto out;
+ }
+
+ nsi = nsinfo__new(event->pid);
+ nsinfo__mountns_enter(nsi, &nc);
+ rc = filename__read_build_id(event->filename, &bid) > 0 ? 0 : -1;
+
+ nsinfo__mountns_exit(&nc);
+ nsinfo__put(nsi);
+
+out:
if (rc == 0) {
memcpy(event->build_id, bid.data, sizeof(bid.data));
event->build_id_size = (u8) bid.size;