This patch fixes the race in the beginning of benchmark run when some
threads hasn't got assigned curr_cpu yet so they don't occur in
nodes-of-process stats and benchmark concludes that all remaining
threads are converged already.
The race can be reproduced with small amount of threads and some bigger
amount of shared process memory, e.g. one process, two threads and 5GB
of process memory.
Signed-off-by: Petr Holasek <pholasek@redhat.com>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/1429198699-25039-4-git-send-email-pholasek@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The futex-requeue benchmark can hang because of missing wakeups once the
benchmark is done, ie:
[Run 1]: Requeued 1024 of 1024 threads in 0.3290 ms
perf: couldn't wakeup all tasks (135/1024)
This bug, while perhaps suggesting missing wakeups in kernel futex code,
is merely a consequence of the crappy FUTEX_CMP_REQUEUE man page,
incorrectly mentioning that the number of requeued tasks is in fact
returned, not the wakeups.
This patch acknowledges this and updates the corresponding futex_wake
code around it.
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Cc: Mel Gorman <mgorman@suse.de>
Link: http://lkml.kernel.org/r/1429894848.10273.44.camel@stgolabs.net
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
There are missing curly braces which causes find_variable() return wrong
value when probing with global variables.
This problem can be reproduced as following:
$ perf probe -v --add='generic_perform_write global_variable_for_test'
...
Try to find probe point from debuginfo.
Probe point found: generic_perform_write+0
Searching 'global_variable_for_test' variable in context.
An error occurred in debuginfo analysis (-2).
Error: Failed to add events. Reason: No such file or directory (Code: -2)
After this patch:
$ perf probe -v --add='generic_perform_write global_variable_for_test'
...
Converting variable global_variable_for_test into trace event.
global_variable_for_test type is int.
Found 1 probe_trace_events.
Opening /sys/kernel/debug/tracing/kprobe_events write=1
Added new event:
Writing event: p:probe/generic_perform_write _stext+1237464
global_variable_for_test=@global_variable_for_test+0:s32
probe:generic_perform_write (on generic_perform_write with
global_variable_for_test)
You can now use it in all perf tools, such as:
perf record -e probe:generic_perform_write -aR sleep 1
Signed-off-by: He Kuang <hekuang@huawei.com>
Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1429949338-18678-1-git-send-email-hekuang@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Perf top raise a warning if a kernel sample is collected but kernel map
is restricted. The warning message needs to dereference al.map->dso...
However, previous perf_event__preprocess_sample() doesn't always
guarantee al.map != NULL, for example, when kernel map is restricted.
This patch validates al.map before dereferencing, avoid the segfault.
Before this patch:
$ cat /proc/sys/kernel/kptr_restrict
1
$ perf top -p 120183
perf: Segmentation fault
-------- backtrace --------
/path/to/perf[0x509868]
/lib64/libc.so.6(+0x3545f)[0x7f9a1540045f]
/path/to/perf[0x448820]
/path/to/perf(cmd_top+0xe3c)[0x44a5dc]
/path/to/perf[0x4766a2]
/path/to/perf(main+0x5f5)[0x42e545]
/lib64/libc.so.6(__libc_start_main+0xf4)[0x7f9a153ecbd4]
/path/to/perf[0x42e674]
And gdb call trace:
Program received signal SIGSEGV, Segmentation fault.
perf_event__process_sample (machine=0xa44030, sample=0x7fffffffa4c0, evsel=0xa43b00, event=0x7ffff41c3000, tool=0x7fffffffa8a0)
at builtin-top.c:736
736 !RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION]) ?
(gdb) bt
#0 perf_event__process_sample (machine=0xa44030, sample=0x7fffffffa4c0, evsel=0xa43b00, event=0x7ffff41c3000, tool=0x7fffffffa8a0)
at builtin-top.c:736
#1 perf_top__mmap_read_idx (top=top@entry=0x7fffffffa8a0, idx=idx@entry=0) at builtin-top.c:855
#2 0x000000000044a5dd in perf_top__mmap_read (top=0x7fffffffa8a0) at builtin-top.c:872
#3 __cmd_top (top=0x7fffffffa8a0) at builtin-top.c:997
#4 cmd_top (argc=<optimized out>, argv=<optimized out>, prefix=<optimized out>) at builtin-top.c:1267
#5 0x00000000004766a3 in run_builtin (p=p@entry=0x8a6ce8 <commands+264>, argc=argc@entry=3, argv=argv@entry=0x7fffffffdf70)
at perf.c:371
#6 0x000000000042e546 in handle_internal_command (argv=0x7fffffffdf70, argc=3) at perf.c:430
#7 run_argv (argv=0x7fffffffdcf0, argcp=0x7fffffffdcfc) at perf.c:474
#8 main (argc=3, argv=0x7fffffffdf70) at perf.c:589
(gdb)
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Zefan Li <lizefan@huawei.com>
Link: http://lkml.kernel.org/r/1429946703-80807-1-git-send-email-wangnan0@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
In my i386 build, it failed like this:
CC event-parse.o
event-parse.c: In function 'print_str_arg':
event-parse.c:3868:5: warning: format '%lu' expects argument of type 'long unsigned int',
but argument 3 has type 'uint64_t' [-Wformat]
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Javi Merino <javi.merino@arm.com>
Link: http://lkml.kernel.org/r/20150424020218.GF1905@sejong
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
0d68bc92c4 breaks compiles on RHEL6/OL6:
cc1: warnings being treated as errors
builtin-kmem.c: In function ‘search_page_alloc_stat’:
builtin-kmem.c:322: error: declaration of ‘stat’ shadows a global declaration
node = &parent->rb_left;
/usr/include/sys/stat.h:455: error: shadowed declaration is here
builtin-kmem.c: In function ‘perf_evsel__process_page_alloc_event’:
builtin-kmem.c:378: error: declaration of ‘stat’ shadows a global declaration
/usr/include/sys/stat.h:455: error: shadowed declaration is here
builtin-kmem.c: In function ‘perf_evsel__process_page_free_event’:
builtin-kmem.c:431: error: declaration of ‘stat’ shadows a global declaration
/usr/include/sys/stat.h:455: error: shadowed declaration is here
Rename local variable to pstat to avoid the name conflict.
Signed-off-by: David Ahern <david.ahern@oracle.com>
Link: http://lkml.kernel.org/r/1429033773-31383-1-git-send-email-david.ahern@oracle.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Building the perf tool for 32-bit ARM results in the following build
error due to a combination of an incorrect conversion specifier and
compiling with -Werror:
builtin-kmem.c: In function ‘print_page_summary’:
builtin-kmem.c:644:9: error: format ‘%lu’ expects argument of type ‘long unsigned int’, but argument 3 has type ‘u64’ [-Werror=format=]
nr_alloc_freed, (total_alloc_freed_bytes) / 1024);
^
builtin-kmem.c:647:9: error: format ‘%lu’ expects argument of type ‘long unsigned int’, but argument 3 has type ‘u64’ [-Werror=format=]
(total_page_alloc_bytes - total_alloc_freed_bytes) / 1024);
^
cc1: all warnings being treated as errors
This patch fixes the problem by consistently using PRIu64 for printing
out u64 values.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Joonsoo Kim <js1304@gmail.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1429796437-1790-1-git-send-email-will.deacon@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
We were not checking in the inner event processing loop if the forked workload
had finished, which, on a busy system, may make it take a long time trying to
drain events, entering a seemingly neverending loop, waiting for the system to
get idle enough to make it drain the buffers.
Fix it by disabling the events when 'done' is true, in the inner loop, to start
draining what is in the buffers.
Now:
[root@ssdandy ~]# time trace --filter-pids 14003 -a sleep 1 | tail
996.748 ( 0.002 ms): sh/30296 rt_sigprocmask(how: SETMASK, nset: 0x7ffc83418160, sigsetsize: 8) = 0
996.751 ( 0.002 ms): sh/30296 rt_sigprocmask(how: BLOCK, nset: 0x7ffc834181f0, oset: 0x7ffc83418270, sigsetsize: 8) = 0
996.755 ( 0.002 ms): sh/30296 rt_sigaction(sig: INT, act: 0x7ffc83417f50, oact: 0x7ffc83417ff0, sigsetsize: 8) = 0
1004.543 ( 0.362 ms): tail/30198 ... [continued]: read()) = 4096
1004.548 ( 7.791 ms): sh/30296 wait4(upid: -1, stat_addr: 0x7ffc834181a0) ...
1004.975 ( 0.427 ms): tail/30198 read(buf: 0x7633f0, count: 8192) = 4096
1005.390 ( 0.410 ms): tail/30198 read(buf: 0x765410, count: 8192) = 4096
1005.743 ( 0.348 ms): tail/30198 read(buf: 0x7633f0, count: 8192) = 4096
1006.197 ( 0.449 ms): tail/30198 read(buf: 0x765410, count: 8192) = 4096
1006.492 ( 0.290 ms): tail/30198 read(buf: 0x7633f0, count: 8192) = 4096
real 0m1.219s
user 0m0.704s
sys 0m0.331s
[root@ssdandy ~]#
Reported-by: Michael Petlan <mpetlan@redhat.com>
Suggested-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-p6kpn1b26qcbe47pufpw0tex@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
commit f7aa222ff3
Author: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue Feb 3 13:25:39 2015 -0300
perf trace: No need to enable evsels for workload started from perf
The assumption was that whenever a workload is specified, the
attr.enable_on_exec evsel flag would be set, but that is not happening
when perf_record_opts.system_wide is set, for instance
That resulted in both perf_evlist__enable() and attr.enable_on_exec
being not called/set, which made the events to remain disabled while the
workload runs, producing no output.
Fix it, by calling perf_evlist__enable() in the 'trace' tool
when forking and not targetting a workload started from trace
v2: Test against !target__none(), as suggested by Namhyung Kim, that is
what is used in perf_evsel__config() when deciding if the
attr.enable_on_exec flag to be set. More work is needed to cover other
cases such as opts->initial_delay.
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-27z7169pvfxgj8upic636syv@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The core_pmu does not define cpu_* callbacks, which handles
allocation of 'struct cpu_hw_events::shared_regs' data,
initialization of debug store and PMU_FL_EXCL_CNTRS counters.
While this probably won't happen on bare metal, virtual CPU can
define x86_pmu.extra_regs together with PMU version 1 and thus
be using core_pmu -> using shared_regs data without it being
allocated. That could could leave to following panic:
BUG: unable to handle kernel NULL pointer dereference at (null)
IP: [<ffffffff8152cd4f>] _spin_lock_irqsave+0x1f/0x40
SNIP
[<ffffffff81024bd9>] __intel_shared_reg_get_constraints+0x69/0x1e0
[<ffffffff81024deb>] intel_get_event_constraints+0x9b/0x180
[<ffffffff8101e815>] x86_schedule_events+0x75/0x1d0
[<ffffffff810586dc>] ? check_preempt_curr+0x7c/0x90
[<ffffffff810649fe>] ? try_to_wake_up+0x24e/0x3e0
[<ffffffff81064ba2>] ? default_wake_function+0x12/0x20
[<ffffffff8109eb16>] ? autoremove_wake_function+0x16/0x40
[<ffffffff810577e9>] ? __wake_up_common+0x59/0x90
[<ffffffff811a9517>] ? __d_lookup+0xa7/0x150
[<ffffffff8119db5f>] ? do_lookup+0x9f/0x230
[<ffffffff811a993a>] ? dput+0x9a/0x150
[<ffffffff8119c8f5>] ? path_to_nameidata+0x25/0x60
[<ffffffff8119e90a>] ? __link_path_walk+0x7da/0x1000
[<ffffffff8101d8f9>] ? x86_pmu_add+0xb9/0x170
[<ffffffff8101d7a7>] x86_pmu_commit_txn+0x67/0xc0
[<ffffffff811b07b0>] ? mntput_no_expire+0x30/0x110
[<ffffffff8119c731>] ? path_put+0x31/0x40
[<ffffffff8107c297>] ? current_fs_time+0x27/0x30
[<ffffffff8117d170>] ? mem_cgroup_get_reclaim_stat_from_page+0x20/0x70
[<ffffffff8111b7aa>] group_sched_in+0x13a/0x170
[<ffffffff81014a29>] ? sched_clock+0x9/0x10
[<ffffffff8111bac8>] ctx_sched_in+0x2e8/0x330
[<ffffffff8111bb7b>] perf_event_sched_in+0x6b/0xb0
[<ffffffff8111bc36>] perf_event_context_sched_in+0x76/0xc0
[<ffffffff8111eb3b>] perf_event_comm+0x1bb/0x2e0
[<ffffffff81195ee9>] set_task_comm+0x69/0x80
[<ffffffff81195fe1>] setup_new_exec+0xe1/0x2e0
[<ffffffff811ea68e>] load_elf_binary+0x3ce/0x1ab0
Adding cpu_(prepare|starting|dying) for core_pmu to have
shared_regs data allocated for core_pmu. AFAICS there's no harm
to initialize debug store and PMU_FL_EXCL_CNTRS either for
core_pmu.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/20150421152623.GC13169@krava.redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Dan Carpenter reported that pt_event_add() has buggy
error handling logic: it returns 0 instead of -EBUSY when
it fails to start a newly added event.
Furthermore, the control flow in this function is messy,
with cleanup labels mixed with direct returns.
Fix the bug and clean up the code by converting it to
a straight fast path for the regular non-failing case,
plus a clear sequence of cascading goto labels to do
all cleanup.
NOTE: I materially changed the existing clean up logic in the
pt_event_start() failure case to use the direct
perf_aux_output_end() path, not pt_event_del(), because
perf_aux_output_end() is enough here.
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Julia Lawall <julia.lawall@lip6.fr>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20150416103830.GB7847@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
RAPL energy hardware unit can vary within a single CPU package, e.g.
HSW server DRAM has a fixed energy unit of 15.3 uJ (2^-16) whereas
the unit on other domains can be enumerated from power unit MSR.
There might be other variations in the future, this patch adds
per cpu model quirk to allow special handling of certain cpus.
hw_unit is also removed from per cpu data since it is not per cpu
and the sampling rate for energy counter is typically not high.
Without this patch, DRAM domain on HSW servers will be counted
4x higher than the real energy counter.
Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Stephane Eranian <eranian@google.com>
Cc: Andi Kleen <andi.kleen@intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Link: http://lkml.kernel.org/r/1427405325-780-1-git-send-email-jacob.jun.pan@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Ingo reported that cycles:pp didn't work for him on some machines.
It turns out that in this commit:
af4bdcf675 perf/x86/intel: Disallow flags for most Core2/Atom/Nehalem/Westmere events
Andi forgot to explicitly allow that event when he
disabled event flags for PEBS on those uarchs.
Reported-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Fixes: af4bdcf675 ("perf/x86/intel: Disallow flags for most Core2/Atom/Nehalem/Westmere events")
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:
New features:
- Analyze page allocator events in 'perf kmem' (Namhyung Kim)
User visible changes:
- Fix retprobe 'perf probe' handling when failing to find needed debuginfo (He Kuang)
- lazy_line probe fixes in 'perf probe' (Naohiro Aota, He Kuang)
Infrastructure changes:
- Record pfn instead of pointer to struct page in tracepoints (Namhyung Kim)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The first argument passed to find_probe_point_lazy() should be CU die,
which will be passed to die_walk_lines() when lazy_line matches.
Currently, when we probe with lazy_line pattern to file without function
name, NULL pointer is passed and causes a segment fault.
Can be reproduced as following:
$ perf probe -k vmlinux --add='fs/super.c;s->s_count=1;'
[ 1958.984658] perf[1020]: segfault at 10 ip 00007fc6e10d8c71 sp
00007ffcbfaaf900 error 4 in libdw-0.161.so[7fc6e10ce000+34000]
Segmentation fault
After this patch:
$ perf probe -k vmlinux --add='fs/super.c;s->s_count=1;'
Added new event:
probe:_stext (on @fs/super.c)
You can now use it in all perf tools, such as:
perf record -e probe:_stext -aR sleep 1
Signed-off-by: He Kuang <hekuang@huawei.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1428925290-5623-3-git-send-email-hekuang@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
When perf probe searched in a debuginfo file and failed, it tried with
an alternative, in function get_alternative_probe_event():
memcpy(tmp, &pev->point, sizeof(*tmp));
memset(&pev->point, 0, sizeof(pev->point));
In this case, it drops the retprobe flag and forgets to set it back in
find_alternative_probe_point(), so the problem occurs.
Can be reproduced as following:
$ perf probe -v -k vmlinux --add='sys_write%return'
...
Added new event:
Writing event: p:probe/sys_write _stext+1584952
probe:sys_write (on sys_write%return)
$ cat /sys/kernel/debug/tracing/kprobe_events
p:probe/sys_write _stext+1584952
After this patch:
$ perf probe -v -k vmlinux --add='sys_write%return'
Added new event:
Writing event: r:probe/sys_write SyS_write+0
probe:sys_write (on sys_write%return)
$ cat /sys/kernel/debug/tracing/kprobe_events
r:probe/sys_write SyS_write
Signed-off-by: He Kuang <hekuang@huawei.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1428925290-5623-1-git-send-email-hekuang@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Petr Holasek
Davidlohr Bueso
He Kuang
Wang Nan
Namhyung Kim
David Ahern
Bobby Powers
Will Deacon
Arnaldo Carvalho de Melo
Sonny Rao
Jiri Olsa
Ingo Molnar
Kan Liang
Jacob Pan
Peter Zijlstra
Naohiro Aota