summaryrefslogtreecommitdiff
path: root/tools/perf
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf')
-rw-r--r--tools/perf/builtin-inject.c6
-rw-r--r--tools/perf/builtin-stat.c2
-rw-r--r--tools/perf/builtin-trace.c2
-rw-r--r--tools/perf/tests/bp_account.c16
-rw-r--r--tools/perf/tests/expr.c2
-rw-r--r--tools/perf/tests/perf-time-to-tsc.c27
-rw-r--r--tools/perf/tests/shell/lib/perf_csv_output_lint.py48
-rwxr-xr-xtools/perf/tests/shell/stat+csv_output.sh69
-rwxr-xr-xtools/perf/tests/shell/test_arm_callgraph_fp.sh2
-rw-r--r--tools/perf/tests/topology.c2
-rwxr-xr-xtools/perf/trace/beauty/arch_errno_names.sh14
-rw-r--r--tools/perf/trace/beauty/include/linux/socket.h7
-rw-r--r--tools/perf/util/arm-spe.c22
-rw-r--r--tools/perf/util/bpf-utils.c5
-rw-r--r--tools/perf/util/bpf_off_cpu.c7
-rw-r--r--tools/perf/util/bpf_skel/off_cpu.bpf.c20
-rw-r--r--tools/perf/util/build-id.c28
-rw-r--r--tools/perf/util/evsel.c9
-rw-r--r--tools/perf/util/expr.l2
-rw-r--r--tools/perf/util/header.c14
-rw-r--r--tools/perf/util/header.h2
-rw-r--r--tools/perf/util/metricgroup.c9
-rw-r--r--tools/perf/util/off_cpu.h9
-rw-r--r--tools/perf/util/synthetic-events.c9
-rw-r--r--tools/perf/util/unwind-libunwind-local.c4
25 files changed, 198 insertions, 139 deletions
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index a75bf11585b5..54d4e508a092 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -891,7 +891,9 @@ static int copy_kcore_dir(struct perf_inject *inject)
if (ret < 0)
return ret;
pr_debug("%s\n", cmd);
- return system(cmd);
+ ret = system(cmd);
+ free(cmd);
+ return ret;
}
static int output_fd(struct perf_inject *inject)
@@ -916,7 +918,7 @@ static int __cmd_inject(struct perf_inject *inject)
inject->tool.tracing_data = perf_event__repipe_tracing_data;
}
- output_data_offset = session->header.data_offset;
+ output_data_offset = perf_session__data_offset(session->evlist);
if (inject->build_id_all) {
inject->tool.mmap = perf_event__repipe_buildid_mmap;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 4ce87a8eb7d7..d2ecd4d29624 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -2586,6 +2586,8 @@ int cmd_stat(int argc, const char **argv)
if (evlist__initialize_ctlfd(evsel_list, stat_config.ctl_fd, stat_config.ctl_fd_ack))
goto out;
+ /* Enable ignoring missing threads when -p option is defined. */
+ evlist__first(evsel_list)->ignore_missing_thread = target.pid;
status = 0;
for (run_idx = 0; forever || run_idx < stat_config.run_count; run_idx++) {
if (stat_config.run_count != 1 && verbose > 0)
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 897fc504918b..f075cf37a65e 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -4280,6 +4280,7 @@ static int trace__replay(struct trace *trace)
goto out;
evsel = evlist__find_tracepoint_by_name(session->evlist, "raw_syscalls:sys_enter");
+ trace->syscalls.events.sys_enter = evsel;
/* older kernels have syscalls tp versus raw_syscalls */
if (evsel == NULL)
evsel = evlist__find_tracepoint_by_name(session->evlist, "syscalls:sys_enter");
@@ -4292,6 +4293,7 @@ static int trace__replay(struct trace *trace)
}
evsel = evlist__find_tracepoint_by_name(session->evlist, "raw_syscalls:sys_exit");
+ trace->syscalls.events.sys_exit = evsel;
if (evsel == NULL)
evsel = evlist__find_tracepoint_by_name(session->evlist, "syscalls:sys_exit");
if (evsel &&
diff --git a/tools/perf/tests/bp_account.c b/tools/perf/tests/bp_account.c
index d1ebb5561e5b..6f921db33cf9 100644
--- a/tools/perf/tests/bp_account.c
+++ b/tools/perf/tests/bp_account.c
@@ -151,11 +151,21 @@ static int detect_ioctl(void)
static int detect_share(int wp_cnt, int bp_cnt)
{
struct perf_event_attr attr;
- int i, fd[wp_cnt + bp_cnt], ret;
+ int i, *fd = NULL, ret = -1;
+
+ if (wp_cnt + bp_cnt == 0)
+ return 0;
+
+ fd = malloc(sizeof(int) * (wp_cnt + bp_cnt));
+ if (!fd)
+ return -1;
for (i = 0; i < wp_cnt; i++) {
fd[i] = wp_event((void *)&the_var, &attr);
- TEST_ASSERT_VAL("failed to create wp\n", fd[i] != -1);
+ if (fd[i] == -1) {
+ pr_err("failed to create wp\n");
+ goto out;
+ }
}
for (; i < (bp_cnt + wp_cnt); i++) {
@@ -166,9 +176,11 @@ static int detect_share(int wp_cnt, int bp_cnt)
ret = i != (bp_cnt + wp_cnt);
+out:
while (i--)
close(fd[i]);
+ free(fd);
return ret;
}
diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c
index d54c5371c6a6..5c0032fe93ae 100644
--- a/tools/perf/tests/expr.c
+++ b/tools/perf/tests/expr.c
@@ -97,6 +97,8 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u
ret |= test(ctx, "2.2 > 2.2", 0);
ret |= test(ctx, "2.2 < 1.1", 0);
ret |= test(ctx, "1.1 > 2.2", 0);
+ ret |= test(ctx, "1.1e10 < 1.1e100", 1);
+ ret |= test(ctx, "1.1e2 > 1.1e-2", 1);
if (ret) {
expr__ctx_free(ctx);
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index 4ad0dfbc8b21..7c7d20fc503a 100644
--- a/tools/perf/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -20,8 +20,6 @@
#include "tsc.h"
#include "mmap.h"
#include "tests.h"
-#include "pmu.h"
-#include "pmu-hybrid.h"
/*
* Except x86_64/i386 and Arm64, other archs don't support TSC in perf. Just
@@ -106,28 +104,21 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su
evlist__config(evlist, &opts, NULL);
- evsel = evlist__first(evlist);
-
- evsel->core.attr.comm = 1;
- evsel->core.attr.disabled = 1;
- evsel->core.attr.enable_on_exec = 0;
-
- /*
- * For hybrid "cycles:u", it creates two events.
- * Init the second evsel here.
- */
- if (perf_pmu__has_hybrid() && perf_pmu__hybrid_mounted("cpu_atom")) {
- evsel = evsel__next(evsel);
+ /* For hybrid "cycles:u", it creates two events */
+ evlist__for_each_entry(evlist, evsel) {
evsel->core.attr.comm = 1;
evsel->core.attr.disabled = 1;
evsel->core.attr.enable_on_exec = 0;
}
- if (evlist__open(evlist) == -ENOENT) {
- err = TEST_SKIP;
+ ret = evlist__open(evlist);
+ if (ret < 0) {
+ if (ret == -ENOENT)
+ err = TEST_SKIP;
+ else
+ pr_debug("evlist__open() failed\n");
goto out_err;
}
- CHECK__(evlist__open(evlist));
CHECK__(evlist__mmap(evlist, UINT_MAX));
@@ -167,10 +158,12 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su
goto next_event;
if (strcmp(event->comm.comm, comm1) == 0) {
+ CHECK_NOT_NULL__(evsel = evlist__event2evsel(evlist, event));
CHECK__(evsel__parse_sample(evsel, event, &sample));
comm1_time = sample.time;
}
if (strcmp(event->comm.comm, comm2) == 0) {
+ CHECK_NOT_NULL__(evsel = evlist__event2evsel(evlist, event));
CHECK__(evsel__parse_sample(evsel, event, &sample));
comm2_time = sample.time;
}
diff --git a/tools/perf/tests/shell/lib/perf_csv_output_lint.py b/tools/perf/tests/shell/lib/perf_csv_output_lint.py
deleted file mode 100644
index 714f283cfb1b..000000000000
--- a/tools/perf/tests/shell/lib/perf_csv_output_lint.py
+++ /dev/null
@@ -1,48 +0,0 @@
-#!/usr/bin/python
-# SPDX-License-Identifier: GPL-2.0
-
-import argparse
-import sys
-
-# Basic sanity check of perf CSV output as specified in the man page.
-# Currently just checks the number of fields per line in output.
-
-ap = argparse.ArgumentParser()
-ap.add_argument('--no-args', action='store_true')
-ap.add_argument('--interval', action='store_true')
-ap.add_argument('--system-wide-no-aggr', action='store_true')
-ap.add_argument('--system-wide', action='store_true')
-ap.add_argument('--event', action='store_true')
-ap.add_argument('--per-core', action='store_true')
-ap.add_argument('--per-thread', action='store_true')
-ap.add_argument('--per-die', action='store_true')
-ap.add_argument('--per-node', action='store_true')
-ap.add_argument('--per-socket', action='store_true')
-ap.add_argument('--separator', default=',', nargs='?')
-args = ap.parse_args()
-
-Lines = sys.stdin.readlines()
-
-def check_csv_output(exp):
- for line in Lines:
- if 'failed' not in line:
- count = line.count(args.separator)
- if count != exp:
- sys.stdout.write(''.join(Lines))
- raise RuntimeError(f'wrong number of fields. expected {exp} in {line}')
-
-try:
- if args.no_args or args.system_wide or args.event:
- expected_items = 6
- elif args.interval or args.per_thread or args.system_wide_no_aggr:
- expected_items = 7
- elif args.per_core or args.per_socket or args.per_node or args.per_die:
- expected_items = 8
- else:
- ap.print_help()
- raise RuntimeError('No checking option specified')
- check_csv_output(expected_items)
-
-except:
- sys.stdout.write('Test failed for input: ' + ''.join(Lines))
- raise
diff --git a/tools/perf/tests/shell/stat+csv_output.sh b/tools/perf/tests/shell/stat+csv_output.sh
index 983220ef3cb4..38c26f3ef4c1 100755
--- a/tools/perf/tests/shell/stat+csv_output.sh
+++ b/tools/perf/tests/shell/stat+csv_output.sh
@@ -6,20 +6,41 @@
set -e
-pythonchecker=$(dirname $0)/lib/perf_csv_output_lint.py
-if [ "x$PYTHON" == "x" ]
-then
- if which python3 > /dev/null
- then
- PYTHON=python3
- elif which python > /dev/null
- then
- PYTHON=python
- else
- echo Skipping test, python not detected please set environment variable PYTHON.
- exit 2
- fi
-fi
+function commachecker()
+{
+ local -i cnt=0 exp=0
+
+ case "$1"
+ in "--no-args") exp=6
+ ;; "--system-wide") exp=6
+ ;; "--event") exp=6
+ ;; "--interval") exp=7
+ ;; "--per-thread") exp=7
+ ;; "--system-wide-no-aggr") exp=7
+ [ $(uname -m) = "s390x" ] && exp=6
+ ;; "--per-core") exp=8
+ ;; "--per-socket") exp=8
+ ;; "--per-node") exp=8
+ ;; "--per-die") exp=8
+ esac
+
+ while read line
+ do
+ # Check for lines beginning with Failed
+ x=${line:0:6}
+ [ "$x" = "Failed" ] && continue
+
+ # Count the number of commas
+ x=$(echo $line | tr -d -c ',')
+ cnt="${#x}"
+ # echo $line $cnt
+ [ "$cnt" -ne "$exp" ] && {
+ echo "wrong number of fields. expected $exp in $line" 1>&2
+ exit 1;
+ }
+ done
+ return 0
+}
# Return true if perf_event_paranoid is > $1 and not running as root.
function ParanoidAndNotRoot()
@@ -30,7 +51,7 @@ function ParanoidAndNotRoot()
check_no_args()
{
echo -n "Checking CSV output: no args "
- perf stat -x, true 2>&1 | $PYTHON $pythonchecker --no-args
+ perf stat -x, true 2>&1 | commachecker --no-args
echo "[Success]"
}
@@ -42,7 +63,7 @@ check_system_wide()
echo "[Skip] paranoid and not root"
return
fi
- perf stat -x, -a true 2>&1 | $PYTHON $pythonchecker --system-wide
+ perf stat -x, -a true 2>&1 | commachecker --system-wide
echo "[Success]"
}
@@ -55,14 +76,14 @@ check_system_wide_no_aggr()
return
fi
echo -n "Checking CSV output: system wide no aggregation "
- perf stat -x, -A -a --no-merge true 2>&1 | $PYTHON $pythonchecker --system-wide-no-aggr
+ perf stat -x, -A -a --no-merge true 2>&1 | commachecker --system-wide-no-aggr
echo "[Success]"
}
check_interval()
{
echo -n "Checking CSV output: interval "
- perf stat -x, -I 1000 true 2>&1 | $PYTHON $pythonchecker --interval
+ perf stat -x, -I 1000 true 2>&1 | commachecker --interval
echo "[Success]"
}
@@ -70,7 +91,7 @@ check_interval()
check_event()
{
echo -n "Checking CSV output: event "
- perf stat -x, -e cpu-clock true 2>&1 | $PYTHON $pythonchecker --event
+ perf stat -x, -e cpu-clock true 2>&1 | commachecker --event
echo "[Success]"
}
@@ -82,7 +103,7 @@ check_per_core()
echo "[Skip] paranoid and not root"
return
fi
- perf stat -x, --per-core -a true 2>&1 | $PYTHON $pythonchecker --per-core
+ perf stat -x, --per-core -a true 2>&1 | commachecker --per-core
echo "[Success]"
}
@@ -94,7 +115,7 @@ check_per_thread()
echo "[Skip] paranoid and not root"
return
fi
- perf stat -x, --per-thread -a true 2>&1 | $PYTHON $pythonchecker --per-thread
+ perf stat -x, --per-thread -a true 2>&1 | commachecker --per-thread
echo "[Success]"
}
@@ -106,7 +127,7 @@ check_per_die()
echo "[Skip] paranoid and not root"
return
fi
- perf stat -x, --per-die -a true 2>&1 | $PYTHON $pythonchecker --per-die
+ perf stat -x, --per-die -a true 2>&1 | commachecker --per-die
echo "[Success]"
}
@@ -118,7 +139,7 @@ check_per_node()
echo "[Skip] paranoid and not root"
return
fi
- perf stat -x, --per-node -a true 2>&1 | $PYTHON $pythonchecker --per-node
+ perf stat -x, --per-node -a true 2>&1 | commachecker --per-node
echo "[Success]"
}
@@ -130,7 +151,7 @@ check_per_socket()
echo "[Skip] paranoid and not root"
return
fi
- perf stat -x, --per-socket -a true 2>&1 | $PYTHON $pythonchecker --per-socket
+ perf stat -x, --per-socket -a true 2>&1 | commachecker --per-socket
echo "[Success]"
}
diff --git a/tools/perf/tests/shell/test_arm_callgraph_fp.sh b/tools/perf/tests/shell/test_arm_callgraph_fp.sh
index 6ffbb27afaba..ec108d45d3c6 100755
--- a/tools/perf/tests/shell/test_arm_callgraph_fp.sh
+++ b/tools/perf/tests/shell/test_arm_callgraph_fp.sh
@@ -43,7 +43,7 @@ CFLAGS="-g -O0 -fno-inline -fno-omit-frame-pointer"
cc $CFLAGS $TEST_PROGRAM_SOURCE -o $TEST_PROGRAM || exit 1
# Add a 1 second delay to skip samples that are not in the leaf() function
-perf record -o $PERF_DATA --call-graph fp -e cycles//u -D 1000 -- $TEST_PROGRAM 2> /dev/null &
+perf record -o $PERF_DATA --call-graph fp -e cycles//u -D 1000 --user-callchains -- $TEST_PROGRAM 2> /dev/null &
PID=$!
echo " + Recording (PID=$PID)..."
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index d23a9e322ff5..0b4f61b6cc6b 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -115,7 +115,7 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map)
* physical_package_id will be set to -1. Hence skip this
* test if physical_package_id returns -1 for cpu from perf_cpu_map.
*/
- if (strncmp(session->header.env.arch, "powerpc", 7)) {
+ if (!strncmp(session->header.env.arch, "ppc64le", 7)) {
if (cpu__get_socket_id(perf_cpu_map__cpu(map, 0)) == -1)
return TEST_SKIP;
}
diff --git a/tools/perf/trace/beauty/arch_errno_names.sh b/tools/perf/trace/beauty/arch_errno_names.sh
index 2c5f72fa8108..37c53bac5f56 100755
--- a/tools/perf/trace/beauty/arch_errno_names.sh
+++ b/tools/perf/trace/beauty/arch_errno_names.sh
@@ -33,23 +33,13 @@ create_errno_lookup_func()
local arch=$(arch_string "$1")
local nr name
- cat <<EoFuncBegin
-static const char *errno_to_name__$arch(int err)
-{
- switch (err) {
-EoFuncBegin
+ printf "static const char *errno_to_name__%s(int err)\n{\n\tswitch (err) {\n" $arch
while read name nr; do
printf '\tcase %d: return "%s";\n' $nr $name
done
- cat <<EoFuncEnd
- default:
- return "(unknown)";
- }
-}
-
-EoFuncEnd
+ printf '\tdefault: return "(unknown)";\n\t}\n}\n'
}
process_arch()
diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h
index 6f85f5d957ef..17311ad9f9af 100644
--- a/tools/perf/trace/beauty/include/linux/socket.h
+++ b/tools/perf/trace/beauty/include/linux/socket.h
@@ -50,6 +50,9 @@ struct linger {
struct msghdr {
void *msg_name; /* ptr to socket address structure */
int msg_namelen; /* size of socket address structure */
+
+ int msg_inq; /* output, data left in socket */
+
struct iov_iter msg_iter; /* data */
/*
@@ -62,8 +65,9 @@ struct msghdr {
void __user *msg_control_user;
};
bool msg_control_is_user : 1;
- __kernel_size_t msg_controllen; /* ancillary data buffer length */
+ bool msg_get_inq : 1;/* return INQ after receive */
unsigned int msg_flags; /* flags on received message */
+ __kernel_size_t msg_controllen; /* ancillary data buffer length */
struct kiocb *msg_iocb; /* ptr to iocb for async requests */
};
@@ -434,6 +438,7 @@ extern struct file *do_accept(struct file *file, unsigned file_flags,
extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
int __user *upeer_addrlen, int flags);
extern int __sys_socket(int family, int type, int protocol);
+extern struct file *__sys_socket_file(int family, int type, int protocol);
extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen);
extern int __sys_connect_file(struct file *file, struct sockaddr_storage *addr,
int addrlen, int file_flags);
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 1a80151baed9..d040406f3314 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -387,26 +387,16 @@ static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq,
return arm_spe_deliver_synth_event(spe, speq, event, &sample);
}
-#define SPE_MEM_TYPE (ARM_SPE_L1D_ACCESS | ARM_SPE_L1D_MISS | \
- ARM_SPE_LLC_ACCESS | ARM_SPE_LLC_MISS | \
- ARM_SPE_REMOTE_ACCESS)
-
-static bool arm_spe__is_memory_event(enum arm_spe_sample_type type)
-{
- if (type & SPE_MEM_TYPE)
- return true;
-
- return false;
-}
-
static u64 arm_spe__synth_data_source(const struct arm_spe_record *record)
{
union perf_mem_data_src data_src = { 0 };
if (record->op == ARM_SPE_LD)
data_src.mem_op = PERF_MEM_OP_LOAD;
- else
+ else if (record->op == ARM_SPE_ST)
data_src.mem_op = PERF_MEM_OP_STORE;
+ else
+ return 0;
if (record->type & (ARM_SPE_LLC_ACCESS | ARM_SPE_LLC_MISS)) {
data_src.mem_lvl = PERF_MEM_LVL_L3;
@@ -510,7 +500,11 @@ static int arm_spe_sample(struct arm_spe_queue *speq)
return err;
}
- if (spe->sample_memory && arm_spe__is_memory_event(record->type)) {
+ /*
+ * When data_src is zero it means the record is not a memory operation,
+ * skip to synthesize memory sample for this case.
+ */
+ if (spe->sample_memory && data_src) {
err = arm_spe__synth_mem_sample(speq, spe->memory_id, data_src);
if (err)
return err;
diff --git a/tools/perf/util/bpf-utils.c b/tools/perf/util/bpf-utils.c
index e271e05e51bc..80b1d2b3729b 100644
--- a/tools/perf/util/bpf-utils.c
+++ b/tools/perf/util/bpf-utils.c
@@ -149,11 +149,10 @@ get_bpf_prog_info_linear(int fd, __u64 arrays)
count = bpf_prog_info_read_offset_u32(&info, desc->count_offset);
size = bpf_prog_info_read_offset_u32(&info, desc->size_offset);
- data_len += count * size;
+ data_len += roundup(count * size, sizeof(__u64));
}
/* step 3: allocate continuous memory */
- data_len = roundup(data_len, sizeof(__u64));
info_linear = malloc(sizeof(struct perf_bpil) + data_len);
if (!info_linear)
return ERR_PTR(-ENOMEM);
@@ -180,7 +179,7 @@ get_bpf_prog_info_linear(int fd, __u64 arrays)
bpf_prog_info_set_offset_u64(&info_linear->info,
desc->array_offset,
ptr_to_u64(ptr));
- ptr += count * size;
+ ptr += roundup(count * size, sizeof(__u64));
}
/* step 5: call syscall again to get required arrays */
diff --git a/tools/perf/util/bpf_off_cpu.c b/tools/perf/util/bpf_off_cpu.c
index b73e84a02264..f289b7713598 100644
--- a/tools/perf/util/bpf_off_cpu.c
+++ b/tools/perf/util/bpf_off_cpu.c
@@ -265,6 +265,12 @@ int off_cpu_write(struct perf_session *session)
sample_type = evsel->core.attr.sample_type;
+ if (sample_type & ~OFFCPU_SAMPLE_TYPES) {
+ pr_err("not supported sample type: %llx\n",
+ (unsigned long long)sample_type);
+ return -1;
+ }
+
if (sample_type & (PERF_SAMPLE_ID | PERF_SAMPLE_IDENTIFIER)) {
if (evsel->core.id)
sid = evsel->core.id[0];
@@ -319,7 +325,6 @@ int off_cpu_write(struct perf_session *session)
}
if (sample_type & PERF_SAMPLE_CGROUP)
data.array[n++] = key.cgroup_id;
- /* TODO: handle more sample types */
size = n * sizeof(u64);
data.hdr.size = size;
diff --git a/tools/perf/util/bpf_skel/off_cpu.bpf.c b/tools/perf/util/bpf_skel/off_cpu.bpf.c
index 792ae2847080..cc6d7fd55118 100644
--- a/tools/perf/util/bpf_skel/off_cpu.bpf.c
+++ b/tools/perf/util/bpf_skel/off_cpu.bpf.c
@@ -71,6 +71,11 @@ struct {
__uint(max_entries, 1);
} cgroup_filter SEC(".maps");
+/* new kernel task_struct definition */
+struct task_struct___new {
+ long __state;
+} __attribute__((preserve_access_index));
+
/* old kernel task_struct definition */
struct task_struct___old {
long state;
@@ -93,14 +98,17 @@ const volatile bool uses_cgroup_v1 = false;
*/
static inline int get_task_state(struct task_struct *t)
{
- if (bpf_core_field_exists(t->__state))
- return BPF_CORE_READ(t, __state);
+ /* recast pointer to capture new type for compiler */
+ struct task_struct___new *t_new = (void *)t;
- /* recast pointer to capture task_struct___old type for compiler */
- struct task_struct___old *t_old = (void *)t;
+ if (bpf_core_field_exists(t_new->__state)) {
+ return BPF_CORE_READ(t_new, __state);
+ } else {
+ /* recast pointer to capture old type for compiler */
+ struct task_struct___old *t_old = (void *)t;
- /* now use old "state" name of the field */
- return BPF_CORE_READ(t_old, state);
+ return BPF_CORE_READ(t_old, state);
+ }
}
static inline __u64 get_cgroup_id(struct task_struct *t)
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 82f3d46bea70..328668f38c69 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -872,6 +872,30 @@ out_free:
return err;
}
+static int filename__read_build_id_ns(const char *filename,
+ struct build_id *bid,
+ struct nsinfo *nsi)
+{
+ struct nscookie nsc;
+ int ret;
+
+ nsinfo__mountns_enter(nsi, &nsc);
+ ret = filename__read_build_id(filename, bid);
+ nsinfo__mountns_exit(&nsc);
+
+ return ret;
+}
+
+static bool dso__build_id_mismatch(struct dso *dso, const char *name)
+{
+ struct build_id bid;
+
+ if (filename__read_build_id_ns(name, &bid, dso->nsinfo) < 0)
+ return false;
+
+ return !dso__build_id_equal(dso, &bid);
+}
+
static int dso__cache_build_id(struct dso *dso, struct machine *machine,
void *priv __maybe_unused)
{
@@ -886,6 +910,10 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine,
is_kallsyms = true;
name = machine->mmap_name;
}
+
+ if (!is_kallsyms && dso__build_id_mismatch(dso, name))
+ return 0;
+
return build_id_cache__add_b(&dso->bid, name, dso->nsinfo,
is_kallsyms, is_vdso);
}
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index ce499c5da8d7..094b0a9c0bc0 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -48,6 +48,7 @@
#include "util.h"
#include "hashmap.h"
#include "pmu-hybrid.h"
+#include "off_cpu.h"
#include "../perf-sys.h"
#include "util/parse-branch-options.h"
#include <internal/xyarray.h>
@@ -1102,6 +1103,11 @@ static void evsel__set_default_freq_period(struct record_opts *opts,
}
}
+static bool evsel__is_offcpu_event(struct evsel *evsel)
+{
+ return evsel__is_bpf_output(evsel) && !strcmp(evsel->name, OFFCPU_EVENT);
+}
+
/*
* The enable_on_exec/disabled value strategy:
*
@@ -1366,6 +1372,9 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts,
*/
if (evsel__is_dummy_event(evsel))
evsel__reset_sample_bit(evsel, BRANCH_STACK);
+
+ if (evsel__is_offcpu_event(evsel))
+ evsel->core.attr.sample_type &= OFFCPU_SAMPLE_TYPES;
}
int evsel__set_filter(struct evsel *evsel, const char *filter)
diff --git a/tools/perf/util/expr.l b/tools/perf/util/expr.l
index 0a13eb20c814..4dc8edbfd9ce 100644
--- a/tools/perf/util/expr.l
+++ b/tools/perf/util/expr.l
@@ -91,7 +91,7 @@ static int literal(yyscan_t scanner)
}
%}
-number ([0-9]+\.?[0-9]*|[0-9]*\.?[0-9]+)
+number ([0-9]+\.?[0-9]*|[0-9]*\.?[0-9]+)(e-?[0-9]+)?
sch [-,=]
spec \\{sch}
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 53332da100e8..6ad629db63b7 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -3686,6 +3686,20 @@ int perf_session__write_header(struct perf_session *session,
return perf_session__do_write_header(session, evlist, fd, at_exit, NULL);
}
+size_t perf_session__data_offset(const struct evlist *evlist)
+{
+ struct evsel *evsel;
+ size_t data_offset;
+
+ data_offset = sizeof(struct perf_file_header);
+ evlist__for_each_entry(evlist, evsel) {
+ data_offset += evsel->core.ids * sizeof(u64);
+ }
+ data_offset += evlist->core.nr_entries * sizeof(struct perf_file_attr);
+
+ return data_offset;
+}
+
int perf_session__inject_header(struct perf_session *session,
struct evlist *evlist,
int fd,
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 08563c1f1bff..56916dabce7b 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -136,6 +136,8 @@ int perf_session__inject_header(struct perf_session *session,
int fd,
struct feat_copier *fc);
+size_t perf_session__data_offset(const struct evlist *evlist);
+
void perf_header__set_feat(struct perf_header *header, int feat);
void perf_header__clear_feat(struct perf_header *header, int feat);
bool perf_header__has_feat(const struct perf_header *header, int feat);
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index ee8fcfa115e5..8f7baeabc5cf 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -1372,6 +1372,7 @@ static int parse_ids(bool metric_no_merge, struct perf_pmu *fake_pmu,
*out_evlist = NULL;
if (!metric_no_merge || hashmap__size(ids->ids) == 0) {
+ bool added_event = false;
int i;
/*
* We may fail to share events between metrics because a tool
@@ -1393,8 +1394,16 @@ static int parse_ids(bool metric_no_merge, struct perf_pmu *fake_pmu,
if (!tmp)
return -ENOMEM;
ids__insert(ids->ids, tmp);
+ added_event = true;
}
}
+ if (!added_event && hashmap__size(ids->ids) == 0) {
+ char *tmp = strdup("duration_time");
+
+ if (!tmp)
+ return -ENOMEM;
+ ids__insert(ids->ids, tmp);
+ }
}
ret = metricgroup__build_event_string(&events, ids, modifier,
has_constraint);
diff --git a/tools/perf/util/off_cpu.h b/tools/perf/util/off_cpu.h
index 548008f74d42..2dd67c60f211 100644
--- a/tools/perf/util/off_cpu.h
+++ b/tools/perf/util/off_cpu.h
@@ -1,6 +1,8 @@
#ifndef PERF_UTIL_OFF_CPU_H
#define PERF_UTIL_OFF_CPU_H
+#include <linux/perf_event.h>
+
struct evlist;
struct target;
struct perf_session;
@@ -8,6 +10,13 @@ struct record_opts;
#define OFFCPU_EVENT "offcpu-time"
+#define OFFCPU_SAMPLE_TYPES (PERF_SAMPLE_IDENTIFIER | PERF_SAMPLE_IP | \
+ PERF_SAMPLE_TID | PERF_SAMPLE_TIME | \
+ PERF_SAMPLE_ID | PERF_SAMPLE_CPU | \
+ PERF_SAMPLE_PERIOD | PERF_SAMPLE_CALLCHAIN | \
+ PERF_SAMPLE_CGROUP)
+
+
#ifdef HAVE_BPF_SKEL
int off_cpu_prepare(struct evlist *evlist, struct target *target,
struct record_opts *opts);
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index 27acdc5e5723..84d17bd4efae 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -754,7 +754,7 @@ static int __event__synthesize_thread(union perf_event *comm_event,
snprintf(filename, sizeof(filename), "%s/proc/%d/task",
machine->root_dir, pid);
- n = scandir(filename, &dirent, filter_task, alphasort);
+ n = scandir(filename, &dirent, filter_task, NULL);
if (n < 0)
return n;
@@ -767,11 +767,12 @@ static int __event__synthesize_thread(union perf_event *comm_event,
if (*end)
continue;
- rc = -1;
+ /* some threads may exit just after scan, ignore it */
if (perf_event__prepare_comm(comm_event, pid, _pid, machine,
&tgid, &ppid, &kernel_thread) != 0)
- break;
+ continue;
+ rc = -1;
if (perf_event__synthesize_fork(tool, fork_event, _pid, tgid,
ppid, process, machine) < 0)
break;
@@ -987,7 +988,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
return 0;
snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir);
- n = scandir(proc_path, &dirent, filter_task, alphasort);
+ n = scandir(proc_path, &dirent, filter_task, NULL);
if (n < 0)
return err;
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 37622699c91a..81b6bd6e1536 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -174,7 +174,7 @@ static int elf_section_address_and_offset(int fd, const char *name, u64 *address
Elf *elf;
GElf_Ehdr ehdr;
GElf_Shdr shdr;
- int ret;
+ int ret = -1;
elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
if (elf == NULL)
@@ -197,7 +197,7 @@ out_err:
#ifndef NO_LIBUNWIND_DEBUG_FRAME
static u64 elf_section_offset(int fd, const char *name)
{
- u64 address, offset;
+ u64 address, offset = 0;
if (elf_section_address_and_offset(fd, name, &address, &offset))
return 0;