mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-05 10:29:37 +00:00
![Arnaldo Carvalho de Melo](/assets/img/avatar_default.png)
Since commit18e7a45af9
("perf/x86: Reject non sampling events with precise_ip") returns -EINVAL for sys_perf_event_open() with an attribute with (attr.precise_ip > 0 && attr.sample_period == 0), just like is done in the routine used to probe the max precise level when no events were passed to 'perf record' or 'perf top', i.e.: perf_evsel__new_cycles() perf_event_attr__set_max_precise_ip() The x86 code, in x86_pmu_hw_config(), which is called all the way from sys_perf_event_open() did, starting with the aforementioned commit: /* There's no sense in having PEBS for non sampling events: */ if (!is_sampling_event(event)) return -EINVAL; Which makes it fail for cycles:ppp, cycles:pp and cycles:p, always using just the non precise cycles variant. To make sure that this is the case, I tested it, before this patch, with: # perf probe -L x86_pmu_hw_config <x86_pmu_hw_config@/home/acme/git/linux/arch/x86/events/core.c:0> 0 int x86_pmu_hw_config(struct perf_event *event) 1 { 2 if (event->attr.precise_ip) { <SNIP> 17 if (event->attr.precise_ip > precise) 18 return -EOPNOTSUPP; /* There's no sense in having PEBS for non sampling events: */ 21 if (!is_sampling_event(event)) 22 return -EINVAL; } <SNIP> # perf probe x86_pmu_hw_config:22 Added new events: probe:x86_pmu_hw_config (on x86_pmu_hw_config:22) probe:x86_pmu_hw_config_1 (on x86_pmu_hw_config:22) You can now use it in all perf tools, such as: perf record -e probe:x86_pmu_hw_config_1 -aR sleep 1 # perf trace -e perf_event_open,probe:x86_pmu_hwconfig*/max-stack=16/ perf record usleep 1 0.000 ( 0.015 ms): perf/4150 perf_event_open(attr_uptr: 0x7ffebc8ba110, cpu: -1, group_fd: -1 ) ... 0.015 ( ): probe:x86_pmu_hw_config:(ffffffff9c0065e1)) x86_pmu_hw_config ([kernel.kallsyms]) hsw_hw_config ([kernel.kallsyms]) x86_pmu_event_init ([kernel.kallsyms]) perf_try_init_event ([kernel.kallsyms]) perf_event_alloc ([kernel.kallsyms]) SYSC_perf_event_open ([kernel.kallsyms]) sys_perf_event_open ([kernel.kallsyms]) do_syscall_64 ([kernel.kallsyms]) return_from_SYSCALL_64 ([kernel.kallsyms]) syscall (/usr/lib64/libc-2.24.so) perf_event_attr__set_max_precise_ip (/home/acme/bin/perf) perf_evsel__new_cycles (/home/acme/bin/perf) perf_evlist__add_default (/home/acme/bin/perf) cmd_record (/home/acme/bin/perf) run_builtin (/home/acme/bin/perf) handle_internal_command (/home/acme/bin/perf) 0.000 ( 0.021 ms): perf/4150 ... [continued]: perf_event_open()) = -1 EINVAL Invalid argument 0.023 ( 0.002 ms): perf/4150 perf_event_open(attr_uptr: 0x7ffebc8ba110, cpu: -1, group_fd: -1 ) ... 0.025 ( ): probe:x86_pmu_hw_config:(ffffffff9c0065e1)) x86_pmu_hw_config ([kernel.kallsyms]) hsw_hw_config ([kernel.kallsyms]) x86_pmu_event_init ([kernel.kallsyms]) perf_try_init_event ([kernel.kallsyms]) perf_event_alloc ([kernel.kallsyms]) SYSC_perf_event_open ([kernel.kallsyms]) sys_perf_event_open ([kernel.kallsyms]) do_syscall_64 ([kernel.kallsyms]) return_from_SYSCALL_64 ([kernel.kallsyms]) syscall (/usr/lib64/libc-2.24.so) perf_event_attr__set_max_precise_ip (/home/acme/bin/perf) perf_evsel__new_cycles (/home/acme/bin/perf) perf_evlist__add_default (/home/acme/bin/perf) cmd_record (/home/acme/bin/perf) run_builtin (/home/acme/bin/perf) handle_internal_command (/home/acme/bin/perf) 0.023 ( 0.004 ms): perf/4150 ... [continued]: perf_event_open()) = -1 EINVAL Invalid argument 0.028 ( 0.002 ms): perf/4150 perf_event_open(attr_uptr: 0x7ffebc8ba110, cpu: -1, group_fd: -1 ) ... 0.030 ( ): probe:x86_pmu_hw_config:(ffffffff9c0065e1)) x86_pmu_hw_config ([kernel.kallsyms]) hsw_hw_config ([kernel.kallsyms]) x86_pmu_event_init ([kernel.kallsyms]) perf_try_init_event ([kernel.kallsyms]) perf_event_alloc ([kernel.kallsyms]) SYSC_perf_event_open ([kernel.kallsyms]) sys_perf_event_open ([kernel.kallsyms]) do_syscall_64 ([kernel.kallsyms]) return_from_SYSCALL_64 ([kernel.kallsyms]) syscall (/usr/lib64/libc-2.24.so) perf_event_attr__set_max_precise_ip (/home/acme/bin/perf) perf_evsel__new_cycles (/home/acme/bin/perf) perf_evlist__add_default (/home/acme/bin/perf) cmd_record (/home/acme/bin/perf) run_builtin (/home/acme/bin/perf) handle_internal_command (/home/acme/bin/perf) 0.028 ( 0.004 ms): perf/4150 ... [continued]: perf_event_open()) = -1 EINVAL Invalid argument 41.018 ( 0.012 ms): perf/4150 perf_event_open(attr_uptr: 0x7ffebc8b5dd0, pid: -1, group_fd: -1, flags: FD_CLOEXEC) = 4 41.065 ( 0.011 ms): perf/4150 perf_event_open(attr_uptr: 0x3c7db78, pid: -1, group_fd: -1, flags: FD_CLOEXEC) = 4 41.080 ( 0.006 ms): perf/4150 perf_event_open(attr_uptr: 0x3c7db78, pid: -1, group_fd: -1, flags: FD_CLOEXEC) = 4 41.103 ( 0.010 ms): perf/4150 perf_event_open(attr_uptr: 0x3c4e748, pid: 4151 (perf), group_fd: -1, flags: FD_CLOEXEC) = 4 41.115 ( 0.006 ms): perf/4150 perf_event_open(attr_uptr: 0x3c4e748, pid: 4151 (perf), cpu: 1, group_fd: -1, flags: FD_CLOEXEC) = 5 41.122 ( 0.004 ms): perf/4150 perf_event_open(attr_uptr: 0x3c4e748, pid: 4151 (perf), cpu: 2, group_fd: -1, flags: FD_CLOEXEC) = 6 41.128 ( 0.008 ms): perf/4150 perf_event_open(attr_uptr: 0x3c4e748, pid: 4151 (perf), cpu: 3, group_fd: -1, flags: FD_CLOEXEC) = 8 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.017 MB perf.data (2 samples) ] # I.e. that return -EINVAL in x86_pmu_hw_config() is hit three times. So fix it by just setting attr.sample_period Now, after this patch: # perf trace --max-stack=2 -e perf_event_open,probe:x86_pmu_hw_config* perf record usleep 1 [ perf record: Woken up 1 times to write data ] 0.000 ( 0.017 ms): perf/8469 perf_event_open(attr_uptr: 0x7ffe36c27d10, pid: -1, cpu: 3, group_fd: -1, flags: FD_CLOEXEC) = 4 syscall (/usr/lib64/libc-2.24.so) perf_event_open_cloexec_flag (/home/acme/bin/perf) 0.050 ( 0.031 ms): perf/8469 perf_event_open(attr_uptr: 0x24ebb78, pid: -1, group_fd: -1, flags: FD_CLOEXEC) = 4 syscall (/usr/lib64/libc-2.24.so) perf_evlist__config (/home/acme/bin/perf) 0.092 ( 0.040 ms): perf/8469 perf_event_open(attr_uptr: 0x24ebb78, pid: -1, group_fd: -1, flags: FD_CLOEXEC) = 4 syscall (/usr/lib64/libc-2.24.so) perf_evlist__config (/home/acme/bin/perf) 0.143 ( 0.007 ms): perf/8469 perf_event_open(attr_uptr: 0x24bc748, cpu: -1, group_fd: -1 ) = 4 syscall (/usr/lib64/libc-2.24.so) perf_event_attr__set_max_precise_ip (/home/acme/bin/perf) 0.161 ( 0.007 ms): perf/8469 perf_event_open(attr_uptr: 0x24bc748, pid: 8470 (perf), group_fd: -1, flags: FD_CLOEXEC) = 4 syscall (/usr/lib64/libc-2.24.so) perf_evsel__open (/home/acme/bin/perf) 0.171 ( 0.005 ms): perf/8469 perf_event_open(attr_uptr: 0x24bc748, pid: 8470 (perf), cpu: 1, group_fd: -1, flags: FD_CLOEXEC) = 5 syscall (/usr/lib64/libc-2.24.so) perf_evsel__open (/home/acme/bin/perf) 0.180 ( 0.007 ms): perf/8469 perf_event_open(attr_uptr: 0x24bc748, pid: 8470 (perf), cpu: 2, group_fd: -1, flags: FD_CLOEXEC) = 6 syscall (/usr/lib64/libc-2.24.so) perf_evsel__open (/home/acme/bin/perf) 0.190 ( 0.005 ms): perf/8469 perf_event_open(attr_uptr: 0x24bc748, pid: 8470 (perf), cpu: 3, group_fd: -1, flags: FD_CLOEXEC) = 8 syscall (/usr/lib64/libc-2.24.so) perf_evsel__open (/home/acme/bin/perf) [ perf record: Captured and wrote 0.017 MB perf.data (7 samples) ] # The probe one called from perf_event_attr__set_max_precise_ip() works the first time, with attr.precise_ip = 3, wit hthe next ones being the per cpu ones for the cycles:ppp event. And here is the text from a report and alternative proposed patch by Thomas-Mich Richter: --- On s390 the counter and sampling facility do not support a precise IP skid level and sometimes returns EOPNOTSUPP when structure member precise_ip in struct perf_event_attr is not set to zero. On s390 commnd 'perf record -- true' fails with error EOPNOTSUPP. This happens only when no events are specified on command line. The functions called are ... --> perf_evlist__add_default --> perf_evsel__new_cycles --> perf_event_attr__set_max_precise_ip The last function determines the value of structure member precise_ip by invoking the perf_event_open() system call and checking the return code. The first successful open is the value for precise_ip. However the value is determined without setting member sample_period and indicates no sampling. On s390 the counter facility and sampling facility are different. The above procedure determines a precise_ip value of 3 using the counter facility. Later it uses the sampling facility with a value of 3 and fails with EOPNOTSUPP. --- v2: Older compilers (e.g. gcc 4.4.7) don't support referencing members of unnamed union members in the container struct initialization, so move from: struct perf_event_attr attr = { ... .sample_period = 1, }; to right after it as: struct perf_event_attr attr = { ... }; attr.sample_period = 1; v3: We need to reset .sample_period to 0 to let the users of perf_evsel__new_cycles() to properly setup attr.sample_period or attr.sample_freq. Reported by Ingo Molnar. Reported-and-Acked-by: Thomas-Mich Richter <tmricht@linux.vnet.ibm.com> Acked-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Wang Nan <wangnan0@huawei.com> Fixes:18e7a45af9
("perf/x86: Reject non sampling events with precise_ip") Link: http://lkml.kernel.org/n/tip-yv6nnkl7tzqocrm0hl3x7vf1@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
131 lines
3 KiB
C
131 lines
3 KiB
C
#include "evlist.h"
|
|
#include "evsel.h"
|
|
#include "thread_map.h"
|
|
#include "cpumap.h"
|
|
#include "tests.h"
|
|
|
|
#include <errno.h>
|
|
#include <signal.h>
|
|
|
|
static int exited;
|
|
static int nr_exit;
|
|
|
|
static void sig_handler(int sig __maybe_unused)
|
|
{
|
|
exited = 1;
|
|
}
|
|
|
|
/*
|
|
* perf_evlist__prepare_workload will send a SIGUSR1 if the fork fails, since
|
|
* we asked by setting its exec_error to this handler.
|
|
*/
|
|
static void workload_exec_failed_signal(int signo __maybe_unused,
|
|
siginfo_t *info __maybe_unused,
|
|
void *ucontext __maybe_unused)
|
|
{
|
|
exited = 1;
|
|
nr_exit = -1;
|
|
}
|
|
|
|
/*
|
|
* This test will start a workload that does nothing then it checks
|
|
* if the number of exit event reported by the kernel is 1 or not
|
|
* in order to check the kernel returns correct number of event.
|
|
*/
|
|
int test__task_exit(int subtest __maybe_unused)
|
|
{
|
|
int err = -1;
|
|
union perf_event *event;
|
|
struct perf_evsel *evsel;
|
|
struct perf_evlist *evlist;
|
|
struct target target = {
|
|
.uid = UINT_MAX,
|
|
.uses_mmap = true,
|
|
};
|
|
const char *argv[] = { "true", NULL };
|
|
char sbuf[STRERR_BUFSIZE];
|
|
struct cpu_map *cpus;
|
|
struct thread_map *threads;
|
|
|
|
signal(SIGCHLD, sig_handler);
|
|
|
|
evlist = perf_evlist__new_default();
|
|
if (evlist == NULL) {
|
|
pr_debug("perf_evlist__new_default\n");
|
|
return -1;
|
|
}
|
|
|
|
/*
|
|
* Create maps of threads and cpus to monitor. In this case
|
|
* we start with all threads and cpus (-1, -1) but then in
|
|
* perf_evlist__prepare_workload we'll fill in the only thread
|
|
* we're monitoring, the one forked there.
|
|
*/
|
|
cpus = cpu_map__dummy_new();
|
|
threads = thread_map__new_by_tid(-1);
|
|
if (!cpus || !threads) {
|
|
err = -ENOMEM;
|
|
pr_debug("Not enough memory to create thread/cpu maps\n");
|
|
goto out_free_maps;
|
|
}
|
|
|
|
perf_evlist__set_maps(evlist, cpus, threads);
|
|
|
|
cpus = NULL;
|
|
threads = NULL;
|
|
|
|
err = perf_evlist__prepare_workload(evlist, &target, argv, false,
|
|
workload_exec_failed_signal);
|
|
if (err < 0) {
|
|
pr_debug("Couldn't run the workload!\n");
|
|
goto out_delete_evlist;
|
|
}
|
|
|
|
evsel = perf_evlist__first(evlist);
|
|
evsel->attr.task = 1;
|
|
evsel->attr.sample_freq = 1;
|
|
evsel->attr.inherit = 0;
|
|
evsel->attr.watermark = 0;
|
|
evsel->attr.wakeup_events = 1;
|
|
evsel->attr.exclude_kernel = 1;
|
|
|
|
err = perf_evlist__open(evlist);
|
|
if (err < 0) {
|
|
pr_debug("Couldn't open the evlist: %s\n",
|
|
str_error_r(-err, sbuf, sizeof(sbuf)));
|
|
goto out_delete_evlist;
|
|
}
|
|
|
|
if (perf_evlist__mmap(evlist, 128, true) < 0) {
|
|
pr_debug("failed to mmap events: %d (%s)\n", errno,
|
|
str_error_r(errno, sbuf, sizeof(sbuf)));
|
|
goto out_delete_evlist;
|
|
}
|
|
|
|
perf_evlist__start_workload(evlist);
|
|
|
|
retry:
|
|
while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) {
|
|
if (event->header.type == PERF_RECORD_EXIT)
|
|
nr_exit++;
|
|
|
|
perf_evlist__mmap_consume(evlist, 0);
|
|
}
|
|
|
|
if (!exited || !nr_exit) {
|
|
perf_evlist__poll(evlist, -1);
|
|
goto retry;
|
|
}
|
|
|
|
if (nr_exit != 1) {
|
|
pr_debug("received %d EXIT records\n", nr_exit);
|
|
err = -1;
|
|
}
|
|
|
|
out_free_maps:
|
|
cpu_map__put(cpus);
|
|
thread_map__put(threads);
|
|
out_delete_evlist:
|
|
perf_evlist__delete(evlist);
|
|
return err;
|
|
}
|