When we parse an event we may get a value from the kernel in response to
PERF_SAMPLE_WEIGHT being set in perf_event_attr->sample_type, and if it
is not set, then perf_sample->weight will be set to zero, which should
be ok according to a discussion with Andi Kleen [1]:
1: https://lkml.kernel.org/r/20170724174637.GS3044@two.firstfloor.org
Acked-by: Andi Kleen <andi@firstfloor.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Taeung Song <treeze.taeung@gmail.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-8ev8ufk3lzmvgz37yg9nv3qz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Make perf stat use group read if there are groups defined. The group
read will get the values for all member of groups within a single
syscall instead of calling read syscall for every event.
We can see considerable less amount of kernel cycles spent on single
group read, than reading each event separately, like for following perf
stat command:
# perf stat -e {cycles,instructions} -I 10 -a sleep 1
Monitored with "perf stat -r 5 -e '{cycles:u,cycles:k}'"
Before:
24,325,676 cycles:u
297,040,775 cycles:k
1.038554134 seconds time elapsed
After:
25,034,418 cycles:u
158,256,395 cycles:k
1.036864497 seconds time elapsed
The perf_evsel__open fallback changes contributed by Andi Kleen.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20170726120206.9099-4-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Add perf_evsel__read_counter() to read single or group counter. After
calling this function the counter's evsel::counts struct is filled with
values for the counter and member of its group if there are any.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20170726120206.9099-3-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Currently we use the size of struct perf_counts_values to read the
event, which prevents us to put any new member to the struct.
Adding perf_evsel__read_size to return size of the buffer needed for
event read.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20170726120206.9099-2-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
New features:
- Filter out 'sshd' in the tracer ancestry in 'perf trace' syswide tracing,
to elliminate tracing loops (Arnaldo Carvalho de Melo)
- Support lookup of symbols in other mount namespaces in 'perf top' (Krister Johansen)
- Initial 'clone' syscall args beautifier in 'perf trace' (Arnaldo Carvalho de Melo)
User visible:
- Ignore 'fd' and 'offset' args for MAP_ANONYMOUS in 'perf trace'
(Arnaldo Carvalho de Melo)
- Process tracing data in 'perf annotate' pipe mode (David Carrillo-Cisneros)
- Make 'perf report --branch-history' work without callgraphs(-g) option
in perf record (Jin Yao)
- Tag branch type/flag on "to" and tag cycles on "from" in 'perf report' (Jin Yao)
Fixes:
- Fix jvmti linker error when libelf config is disabled (Sudeep Holla)
- Fix cgroups refcount usage (Arnaldo Carvalho de Melo)
- Fix kernel symbol adjustment for s390x (Thomas Richter)
- Fix 'perf report --stdio --show-total-period', it was showing the
number of samples, not the total period (Taeung Song)
Infrastructure:
- Add perf_sample dictionary to tracepoint handlers in 'perf script'
python, which were already present for other types of events
(hardware, etc) (Arun Kalyanasundaram)
- Make build fail on vendor events JSON parse error (Andi Kleen)
- Adopt strstarts() from the kernel (Arnaldo Carvalho de Melo)
Arch specific:
- Set no_aux_samples for the tracking event in Intel PT (Kan Liang)
- Always set no branch for Intel PT dummy event (Kan Liang)
Trivial:
- Simplify some error handlers in 'perf script' (Dan Carpenter)
- Add EXCLUDE_EXTLIBS and EXTRA_PERFLIBS to makefile (David Carrillo-Cisneros)
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2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=LBBF
-----END PGP SIGNATURE-----
Merge tag 'perf-core-for-mingo-4.14-20170725' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core
Pull perf/core improvemends and fixes for v4.14:
New features:
- Filter out 'sshd' in the tracer ancestry in 'perf trace' syswide tracing,
to elliminate tracing loops (Arnaldo Carvalho de Melo)
- Support lookup of symbols in other mount namespaces in 'perf top' (Krister Johansen)
- Initial 'clone' syscall args beautifier in 'perf trace' (Arnaldo Carvalho de Melo)
User visible changes:
- Ignore 'fd' and 'offset' args for MAP_ANONYMOUS in 'perf trace'
(Arnaldo Carvalho de Melo)
- Process tracing data in 'perf annotate' pipe mode (David Carrillo-Cisneros)
- Make 'perf report --branch-history' work without callgraphs(-g) option
in perf record (Jin Yao)
- Tag branch type/flag on "to" and tag cycles on "from" in 'perf report' (Jin Yao)
Fixes:
- Fix jvmti linker error when libelf config is disabled (Sudeep Holla)
- Fix cgroups refcount usage (Arnaldo Carvalho de Melo)
- Fix kernel symbol adjustment for s390x (Thomas Richter)
- Fix 'perf report --stdio --show-total-period', it was showing the
number of samples, not the total period (Taeung Song)
Infrastructure changes:
- Add perf_sample dictionary to tracepoint handlers in 'perf script'
python, which were already present for other types of events
(hardware, etc) (Arun Kalyanasundaram)
- Make build fail on vendor events JSON parse error (Andi Kleen)
- Adopt strstarts() from the kernel (Arnaldo Carvalho de Melo)
Arch specific changes:
- Set no_aux_samples for the tracking event in Intel PT (Kan Liang)
- Always set no branch for Intel PT dummy event (Kan Liang)
Trivial changes:
- Simplify some error handlers in 'perf script' (Dan Carpenter)
- Add EXCLUDE_EXTLIBS and EXTRA_PERFLIBS to makefile (David Carrillo-Cisneros)
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This file was copied from the kernel so that we could build tools/perf/
on older systems where some newer defines, such as these are available:
CC trace/beauty/fcntl.o
trace/beauty/fcntl.c: In function ‘syscall_arg__scnprintf_fcntl_arg’:
trace/beauty/fcntl.c:93:13: error: ‘F_OFD_SETLK’ undeclared (first use in this function)
cmd == F_OFD_SETLK || cmd == F_OFD_SETLKW || cmd == F_OFD_GETLK ||
^
trace/beauty/fcntl.c:93:13: note: each undeclared identifier is reported only once for each function it appears in
trace/beauty/fcntl.c:93:35: error: ‘F_OFD_SETLKW’ undeclared (first use in this function)
cmd == F_OFD_SETLK || cmd == F_OFD_SETLKW || cmd == F_OFD_GETLK ||
^
trace/beauty/fcntl.c:93:58: error: ‘F_OFD_GETLK’ undeclared (first use in this function)
cmd == F_OFD_SETLK || cmd == F_OFD_SETLKW || cmd == F_OFD_GETLK ||
^
mv: cannot stat ‘trace/beauty/.fcntl.o.tmp’: No such file or directory
make[4]: *** [trace/beauty/fcntl.o] Error 1
make[3]: *** [trace/beauty] Error 2
make[3]: *** Waiting for unfinished jobs....
CC tests/llvm.o
But we need to make sure that it is also in the tools/perf/MANIFEST file, that
is used to build a tarball for detached (from the kernel sources) compilation,
which was failing, with the above message, on a RHEL7.4 system, fix it.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Fixes: 84d1d8a12d ("tools include uapi asm-generic: Grab a copy of fcntl.h")
Link: http://lkml.kernel.org/n/tip-2d5px7aq5stbwi24pgirwtlm@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Currently the first column header is always "Percent", fix it to show
correct column name based on given options, i.e. if using
--show-total-period, show "Event count" as a first column.
Reported-by: Milian Wolff <milian.wolff@kdab.com>
Signed-off-by: Taeung Song <treeze.taeung@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/c3c902e7-95bc-16d4-366f-12eb034c5c8d@gmail.com
[ Extracted from a larger patch ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Today, when a JSON file fails parsing the build continues, but there are
no json files built in, which is difficult to debug later. Make the
build stop on a parse error instead.
v2: Add fixes from Sukadev. Now we handle architectures
with no JSON events correctly. And fix some stale comments.
Committer note:
Tested by running the cross build container tests, that were all failing
for v1.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/20170725001638.19990-1-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Current --branch-history LBR annotation displays confused data. For
example, each cycles report is duplicated on both "from" and "to"
entries.
For example:
perf report --branch-history --no-children --stdio
--2.32%--main div.c:39 (COND_BWD CROSS_2M predicted:49.7% cycles:1)
main div.c:44 (predicted:49.7% cycles:1)
main div.c:42 (RET CROSS_2M cycles:2)
compute_flag div.c:28 (cycles:2)
compute_flag div.c:27 (RET CROSS_2M cycles:1)
rand rand.c:28 (cycles:1)
rand rand.c:28 (RET CROSS_2M cycles:1)
__random random.c:298 (cycles:1)
__random random.c:297 (COND_BWD CROSS_2M cycles:1)
__random random.c:295 (cycles:1)
__random random.c:295 (COND_BWD CROSS_2M cycles:1)
__random random.c:295 (cycles:1)
__random random.c:295 (RET CROSS_2M cycles:9)
The cycles should be tagged only on the "from". It's for the code block
that ends with "from", not for "to".
Another issue is the "predicted:49.7%" is duplicated too (tag on both
"from" and "to").
This patch tags the branch type/flag on "to" and tag the cycles on
"from".
For example:
--2.32%--main div.c:39 (COND_BWD CROSS_2M predicted:49.7%)
main div.c:44 (cycles:1)
main div.c:42 (RET CROSS_2M)
compute_flag div.c:28 (cycles:2)
compute_flag div.c:27 (RET CROSS_2M)
rand rand.c:28 (cycles:1)
rand rand.c:28 (RET CROSS_2M)
__random random.c:298 (cycles:1)
__random random.c:297 (COND_BWD CROSS_2M)
__random random.c:295 (cycles:1)
__random random.c:295 (COND_BWD CROSS_2M)
__random random.c:295 (cycles:1)
__random random.c:295 (RET CROSS_2M)
|
--2.23%--__random_r random_r.c:392 (cycles:9)
In this example, The "main div.c:39 (COND_BWD CROSS_2M predicted:49.7%)"
is "to" of branch and "main div.c:44 (cycles:1)" is "from" of branch.
It should be easier for understanding than before.
Signed-off-by: Yao Jin <yao.jin@linux.intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1500894547-18411-1-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
perf record -b -g <command>
perf report --branch-history
This merges the LBRs with the callgraphs.
However it would be nice if it also works without callgraphs (-g) set in
perf record, so that only the LBRs are displayed. But currently perf
report errors in this case. For example,
perf record -b <command>
perf report --branch-history
Error:
Selected -g or --branch-history but no callchain data. Did
you call 'perf record' without -g?
This patch displays the LBRs only even if callgraphs(-g) is not enabled
in perf record.
Change log:
v2: According to Milian Wolff's comment, change the obsolete error
message. Now the error message is:
┌─Error:─────────────────────────────────────┐
│Selected -g or --branch-history. │
│But no callchain or branch data. │
│Did you call 'perf record' without -g or -b?│
│ │
│ │
│Press any key... │
└────────────────────────────────────────────┘
When passing the last parameter to hists__fprintf,
changes "|" to "||".
hists__fprintf(hists, !quiet, 0, 0, rep->min_percent, stdout,
symbol_conf.use_callchain || symbol_conf.show_branchflag_count);
Signed-off-by: Yao Jin <yao.jin@linux.intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1494240182-28899-1-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Modify the signature of tracepoint specific and trace_unhandled hooks to
add the perf_sample dict as a new argument.
Create a python helper function to print a dictionary.
Signed-off-by: Arun Kalyanasundaram <arunkaly@google.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Carrillo-Cisneros <davidcc@google.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Seongjae Park <sj38.park@gmail.com>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/20170721220422.63962-6-arunkaly@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The process_event python hook receives a dict with all perf_sample
entries, but the tracepoint specific and trace_unhandled hooks predate
the introduction of this dict, and do not receive it.
Add the aforementioned dict as an additional argument to the affected
handlers. To keep backwards compatibility (and avoid unnecessary work),
do not pass the dict if the number of arguments signals that handler
version predates this change.
Signed-off-by: Arun Kalyanasundaram <arunkaly@google.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Carrillo-Cisneros <davidcc@google.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Seongjae Park <sj38.park@gmail.com>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/20170721220422.63962-5-arunkaly@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Provide time_enabled, time_running and counter value in the perf_sample
dict.
Signed-off-by: Arun Kalyanasundaram <arunkaly@google.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Carrillo-Cisneros <davidcc@google.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Seongjae Park <sj38.park@gmail.com>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/20170721220422.63962-4-arunkaly@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Move the creation of the dict containing perf_sample entries into a
helper function to enable its reuse in other sample processing routines.
Signed-off-by: Arun Kalyanasundaram <arunkaly@google.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Carrillo-Cisneros <davidcc@google.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Seongjae Park <sj38.park@gmail.com>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/20170721220422.63962-3-arunkaly@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Avoid allocating memory if hook handler is not available. This saves
unused memory allocation and simplifies error path.
Let handler in python_process_tracepoint point to either tracepoint
specific or trace_unhandled hook. Use dict to check if handler points to
trace_unhandled.
Remove the exit label in python_process_general_event and return when no
handler is available.
Signed-off-by: Arun Kalyanasundaram <arunkaly@google.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Carrillo-Cisneros <davidcc@google.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Seongjae Park <sj38.park@gmail.com>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/20170721220422.63962-2-arunkaly@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
If script_desc__new() fails then the current code has a NULL
dereference. We don't actually need to do any cleanup, we can just
return NULL.
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: kernel-janitors@vger.kernel.org
Link: http://lkml.kernel.org/r/20170722073610.nnsyiwdcfl6bhn4t@mwanda
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The perf top command needs to unshare its fs from the helper threads in
order to successfully setns(2) during its symbol lookup. It also needs
to impelement a force flag to ignore ownership of perf-<pid>.map files.
Signed-off-by: Krister Johansen <kjlx@templeofstupid.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas-Mich Richter <tmricht@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/1499305693-1599-6-git-send-email-kjlx@templeofstupid.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
When libelf is disabled in the configuration, we get the following
linker error:
LINK libperf-jvmti.so
ld: cannot find -lelf
Makefile.perf:515: recipe for target 'libperf-jvmti.so' failed
Jiri pointed out that both librt and libelf are not really required. So
this patch fixes the linker error by getting rid of unwanted libraries
in the linker stage.
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Acked-by: David Carrillo-Cisneros <davidcc@google.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Elena Reshetova <elena.reshetova@intel.com>
Cc: Kees Kook <keescook@chromium.org>
Cc: Paul Turner <pjt@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Sudeep Holla <sudeep.holla@arm.com>
Cc: Wang Nan <wangnan0@huawei.com>
Fixes: 209045adc2 ("perf tools: add JVMTI agent library")
Link: http://lkml.kernel.org/r/20170719011839.99399-5-davidcc@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
'perf annotate' was missing the handler for tracing data records.
Prior to this patch we obtained "unhandled" records when piping trace
events to perf annotate (using -D option to show the dump_printf
messages in process_event_synth_tracing_data_stub):
$ perf record -o - -e block:bio_free sleep 2 | perf annotate -D --stdio
...
0x78 [0xc]: PERF_RECORD_TRACING_DATA: unhandled!
...
Signed-off-by: David Carrillo-Cisneros <davidcc@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Elena Reshetova <elena.reshetova@intel.com>
Cc: Kees Kook <keescook@chromium.org>
Cc: Paul Turner <pjt@google.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Sudeep Holla <sudeep.holla@arm.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/20170719011839.99399-4-davidcc@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The goal is to allow users to override linking of libraries that
were automatically added to PERFLIBS.
EXCLUDE_EXTLIBS contains linker flags to be removed from LIBS
while EXTRA_PERFLIBS contains linker flags to be added.
My use case is to force certain library to be build statically,
e.g. for libelf:
EXCLUDE_EXTLIBS=-lelf EXTRA_PERFLIBS=path/libelf.a
Signed-off-by: David Carrillo-Cisneros <davidcc@google.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Elena Reshetova <elena.reshetova@intel.com>
Cc: Kees Kook <keescook@chromium.org>
Cc: Paul Turner <pjt@google.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Sudeep Holla <sudeep.holla@arm.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/20170719011839.99399-3-davidcc@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
When converting from atomic_t to refcount_t we didn't follow the usual
step of initializing it to one before taking any new reference, which
trips over checking if taking a reference for a freed refcount_t, fix
it.
Brendan's report:
---
It's 4.12-rc7, with node v4.4.1. I'm building 4.13-rc1 now, as I hit
what I think is another unrelated perf bug and I'm starting to wonder
what else is broken on that version:
(root) /mnt/src/linux-4.12-rc7/tools/perf # ./perf record -F 99 -a -e
cpu-clock --cgroup=docker/f9e9d5df065b14646e8a11edc837a13877fd90c171137b2ba3feb67a0201cb65
-g
perf: /mnt/src/linux-4.12-rc7/tools/include/linux/refcount.h:108:
refcount_inc: Assertion `!(!refcount_inc_not_zero(r))' failed.
Aborted
that used to work...
---
Testing it:
Before:
# perf stat -e cycles -C 0 --cgroup /
perf: /home/acme/git/linux/tools/include/linux/refcount.h:108: refcount_inc: Assertion `!(!refcount_inc_not_zero(r))' failed.
Aborted (core dumped)
#
After:
# perf stat -e cycles -C 0 --cgroup /
^C
Performance counter stats for 'CPU(s) 0':
132,081,393 cycles /
2.492942763 seconds time elapsed
#
Reported-by: Brendan Gregg <brendan.d.gregg@gmail.com>
Acked-by: Elena Reshetova <elena.reshetova@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: David Carrillo-Cisneros <davidcc@google.com>
Cc: Kees Kook <keescook@chromium.org>
Cc: Krister Johansen <kjlx@templeofstupid.com>
Cc: Paul Turner <pjt@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Sudeep Holla <Sudeep.Holla@arm.com>
Cc: Thomas-Mich Richter <tmricht@linux.vnet.ibm.com>
Cc: Wang Nan <wangnan0@huawei.com>
Fixes: 79c5fe6db8 ("perf cgroup: Convert cgroup_sel.refcnt from atomic_t to refcount_t")
Link: http://lkml.kernel.org/n/tip-l7ovfblq14ip2i08m1g0fkhv@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
On s390x the kernel text segment starts at address 0x0. When perf
report reads kernel symbols from vmlinux file it adds an offset of
0x1000.
For example see symbol set_reset_devices:
[root@s8360047 linux-devel]# nm -A vmlinux| fgrep set_reset_devices
vmlinux:0000000001379000 t set_reset_devices
[root@s8360047 linux-devel]#
[root@s8360047 linux-devel]# fgrep set_reset_devices /proc/kallsyms
0000000001379000 t set_reset_devices
[root@s8360047 linux-devel]#
The kernel symbol table and the vmlinux file have the same address for
symbol set_reset_devices namely 1379000.
When perf report reads this symbols it displays it with address
symbol__new: set_reset_devices 0x137a000-0x137a018
There is a difference between perf report and vmlinux of 0x1000.
The reason for the difference is at kernel symbol load time in function
dso__load_sym(). The vmlinux file is investigated with its ELF header.
Command readelf shows this:
Section Headers:
[Nr] Name Type Address Offset
Size EntSize Flags Link Info Align
[ 0] NULL 0000000000000000 00000000
0000000000000000 0000000000000000 0 0 0
[ 1] .text PROGBITS 0000000000000000 00001000
0000000000b0e0c2 0000000000000000 AX 0 0 128
This leads to an invalid calculation of the symbol start address, see
file utit/symbol-elf.c line 974:
/* Adjust symbol to map to file offset */
if (adjust_kernel_syms)
sym.st_value -= shdr.sh_addr - shdr.sh_offset;
With shdr.sh_addr set to 0x0 and shdr.sh_offset set to 0x1000 as read
from the ELF .text section 0x1000 is added to the symbol address.
I would like to fix this by introducing an archticture specific function
named elf__needs_adjust_symbols(). This is the same approach as done by
PowerPC. The function currently does not exist for s390x and the
default weak one is used. The s390x specific one returns false when
symsrc_init() is invoked for kernel symbols and results in variable
adjust_kernel_syms being false. This omits the adjustment and the
correct address is displayed (when symbol resolvement does not work).
The s390x specific function returns false for kernel symbol adjustment
and returns true for kernel modules, processes and shared libraries.
Signed-off-by: Thomas-Mich Richter <tmricht@linux.vnet.ibm.com>
Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Thomas-Mich Richter <tmricht@linux.vnet.ibm.com>
LPU-Reference: 20170713130252.6167-1-tmricht@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
We were showing the total number of samples, not the total period as
asked by the user, fix it.
Reported-by: Namhyung Kim <namhyung@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Martin Liška <mliska@suse.cz>
Cc: Milian Wolff <milian.wolff@kdab.com>
Link: http://lkml.kernel.org/n/tip-lh2nh89rtqn5x5vbfthw6qml@git.kernel.org
Fixes: 0c4a5bcea4 ("perf annotate: Display total number of samples with --show-total-period")
[ split from a larger patch ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
In fixing the --show-total-period option it was noticed that the value
of sample->period was being overwritten, fix it.
Signed-off-by: Taeung Song <treeze.taeung@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Fixes: fd36f3dd79 ("perf hist: Pass struct sample to __hists__add_entry()")
Link: http://lkml.kernel.org/r/1500500215-16646-1-git-send-email-treeze.taeung@gmail.com
[ split from a larger patch, added the Fixes tag ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
We'll use it soon, when fixing --show-total-period.
Signed-off-by: Taeung Song <treeze.taeung@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1500500215-16646-1-git-send-email-treeze.taeung@gmail.com
[ split from a larger patch, do the math in __symbol__inc_addr_samples() ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
To pave the way to use perf_sample fields in the annotate code, storing
sample->period in sym_hist->addr->period and its sum in
sym_hist->period.
Signed-off-by: Taeung Song <treeze.taeung@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/1500500215-16646-1-git-send-email-treeze.taeung@gmail.com
[ split and adjusted from a larger patch ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
To make it more clear that it is the sum of all the nr_samples fields in the
addr[] entries, i.e.:
sym_hist->nr_samples = sum(sym_hist->addr[0 .. symbol__size(sym)]->nr_samples)
Committer notes:
Taeung had renamed it to total_samples, but using nr_samples, as in the
added explanation above, looks clearer and establishes the direct
connection, making clear it is about the _number_ of samples.
Signed-off-by: Taeung Song <treeze.taeung@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/1500500211-16599-1-git-send-email-treeze.taeung@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
struct sym_hist has addr[] but it should have not only number of samples
but also the sample period. So use new struct symhist_entry to pave the
way to have that.
Committer notes:
This initial patch will only introduce the struct sym_hist_entry and use
only the nr_samples member, which makes the code clearer and paves the
way to save the period as well.
Signed-off-by: Taeung Song <treeze.taeung@gmail.com>
Suggested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/1500500205-16553-1-git-send-email-treeze.taeung@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Getting support for "on", "off" introduced in a81a5a17d4 ("lib: add
"on"/"off" support to kstrtobool") and making it check for NULL,
introduced in ef95159907 ("lib: move strtobool() to kstrtobool()").
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Kees Cook <keescook@chromium.org>
Link: http://lkml.kernel.org/n/tip-mu8ghin4rklacmmubzwv8td7@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Replacing prefixcmp(), same purpose, inverted result, so standardize on
the kernel variant, to reduce silly differences among tools/ and the
kernel sources, making it easier for people to work in both codebases.
And then doing:
if (strstarts(option, "no-"))
Looks clearer than doing:
if (!prefixcmp(option, "no-"))
To figure out if option starts witn "no-".
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-kaei42gi7lpa8subwtv7eug8@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Avoiding a loop, so now its quite convenient to ssh to a machine and
then simply do:
# perf trace
To trace all syscalls without causing a loop.
This was possible using --filter-pids, i.e. once you noticed the loop,
get the sshd pid and add it to --filter-pids, restarting the 'perf
trace'.
Now to figure out how to do that in a X terminal, the other common
scenario, which is way more involved, as there are multiple processes
communicating to process terminal activity...
Using --filter-pids + '-e \!syscall,names,you,dont,need' may be a good
approximation when having to do syswide tracing on your workstation.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-68rjeao9wnpylla41htk7xps@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
No change in functionality, just to make clearer that what we want when
filtering the tracer pid in a system wide tracing session is to avoid a
feedback loop.
This also paves the way for a more interesting loop avoidance algorithm,
one that tries to figure out if we are in a ssh session, xterm, etc.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-5fcttc5kdjkcyp9404ezkuy9@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
So that we make sure we have recent enough defines for things
such as 'perf trace' system call argument beautifiers.
For instance, the 'clone' syscall argument 'flag' needs to use
CLONE_NEWCGROUP, and that is not available in RHEL7.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-81sln0ng4a2lcxrth14vcov4@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
For tracepointless syscalls, like clone, otherwise get them from the
tracepoint's /format file.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-ml5qvv1w5k96ghwhxpzzsmm3@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
When we don't have syscalls:sys_{enter,exit}_NAME, we had to resort to
dumping all the 6 syscall arguments, fix it by providing that info for
such syscalls, like 'clone'.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-dfq1jtrxj8dqvqoeqqpr3slu@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
All callers now can use syscall__arg_val(arg, idx), be it to iterate
thru the syscall arguments while taking into account alignment, or to
get values for other arguments that affect how the current argument
should be formatted (think of fcntl's 'cmd' and 'arg' arguments).
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-wm5b156d8kro1r4y3b33eyta@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Previously we only used the syscall_fmt when we had sc->tp_format set,
i.e. when we found the (enter, exit) pair in tracefs/events/syscalls/.
But we really only need to use what is in sc->arg_fmt to apply the arg
beautifiers to the syscall argument values, so do it.
With this we will be able to provide formatters to the "clone" syscall,
which doesn't have entries in tracefs/events/syscalls/.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-y41nl41jrayjo5ucnde2peix@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
At least "clone" doesn't have (enter, exit) entries tracefs/events/syscalls/,
but we can provide a syscall_fmt and use it instead, as will be done for
"clone" in the next cset.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-o12kejgcxddyovn2hlg4gbim@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Just suppress them, not used by the kernel.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-atpt07y2x9a8ttlwja94ow3j@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
An earlier kernel patch allowed enabling PT and LBR at the same time on
Goldmont.
commit ccbebba4c6 ("perf/x86/intel/pt: Bypass PT vs. LBR exclusivity
if the core supports it")
However, users still cannot use Intel PT and LBRs simultaneously. $
sudo perf record -e cycles,intel_pt//u -b -- sleep 1 Error: PMU
Hardware doesn't support sampling/overflow-interrupts.
PT implicitly adds dummy event in perf tool. dummy event is software
event which doesn't support LBR.
Always setting no branch for dummy event in Intel PT.
Signed-off-by: Kan Liang <kan.liang@intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20170630141656.1626-2-kan.liang@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The reason of introducing the tracking event (a dummy software event) is
to collect side-band information. Additional sampling is wasteful.
no_aux_samples should be set for tracking event.
Signed-off-by: Kan Liang <kan.liang@intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20170630141656.1626-1-kan.liang@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
User visible:
. Initial support for namespaces, using setns to access files in
namespaces, grabbing their build-ids, etc. We still need to work
more to deal with namespaces that vanish before we can get the
needed data to do analysis, but this should be as good as what is
in bcc now (Krister Johansen)
. Add header record types to pipe-mode, now this command:
$ perf record -o - -e cycles sleep 1 | perf report --stdio --header
Will show the same as in non-pipe mode, i.e. involving a perf.data
file (David Carrillo-Cisneros)
. Implement a visual marker for fused x86 instructions in the annotate
TUI browser, available now in 'perf report', more work needed to have
it available as well in 'perf top' (Jin Yao)
Further explanation from one of Jin's patches:
│ ┌──cmpl $0x0,argp_program_version_hook
81.93 │ ├──je 20
│ │ lock cmpxchg %esi,0x38a9a4(%rip)
│ │↓ jne 29
│ │↓ jmp 43
11.47 │20:└─→cmpxch %esi,0x38a999(%rip)
That means the cmpl+je is a fused instruction pair and they should be
considered together.
. Record the branch type and then show statistics and info about
in callchain entries (Jin Yao)
Example from one of Jin's patches:
# perf record -g -j any,save_type
# perf report --branch-history --stdio --no-children
38.50% div.c:45 [.] main div
|
---main div.c:42 (RET CROSS_2M cycles:2)
compute_flag div.c:28 (cycles:2)
compute_flag div.c:27 (RET CROSS_2M cycles:1)
rand rand.c:28 (cycles:1)
rand rand.c:28 (RET CROSS_2M cycles:1)
__random random.c:298 (cycles:1)
__random random.c:297 (COND_BWD CROSS_2M cycles:1)
__random random.c:295 (cycles:1)
__random random.c:295 (COND_BWD CROSS_2M cycles:1)
__random random.c:295 (cycles:1)
__random random.c:295 (RET CROSS_2M cycles:9)
. Beautify the fcntl syscall, which is an interesting one in the sense
that infrastructure had to be put in place to change the formatters of
some arguments according to the value in a previous one, i.e. cmd
dictates how arg and the syscall return will be formatted.
(Arnaldo Carvalho de Melo
Infrastructure:
. 'perf test attr' fixes (Jiri Olsa)
Vendor events:
- Add POWER9 PMU events Sukadev (Bhattiprolu)
- Support additional POWER8+ PVR in PMU mapfile (Shriya)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2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=eFUO
-----END PGP SIGNATURE-----
Merge tag 'perf-core-for-mingo-4.13-20170718' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core
Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:
User visible changes:
- Initial support for namespaces, using setns to access files in
namespaces, grabbing their build-ids, etc. We still need to work
more to deal with namespaces that vanish before we can get the
needed data to do analysis, but this should be as good as what is
in bcc now (Krister Johansen)
- Add header record types to pipe-mode, now this command:
$ perf record -o - -e cycles sleep 1 | perf report --stdio --header
Will show the same as in non-pipe mode, i.e. involving a perf.data
file (David Carrillo-Cisneros)
- Implement a visual marker for fused x86 instructions in the annotate
TUI browser, available now in 'perf report', more work needed to have
it available as well in 'perf top' (Jin Yao)
Further explanation from one of Jin's patches:
│ ┌──cmpl $0x0,argp_program_version_hook
81.93 │ ├──je 20
│ │ lock cmpxchg %esi,0x38a9a4(%rip)
│ │↓ jne 29
│ │↓ jmp 43
11.47 │20:└─→cmpxch %esi,0x38a999(%rip)
That means the cmpl+je is a fused instruction pair and they should be
considered together.
- Record the branch type and then show statistics and info about
in callchain entries (Jin Yao)
Example from one of Jin's patches:
# perf record -g -j any,save_type
# perf report --branch-history --stdio --no-children
38.50% div.c:45 [.] main div
|
---main div.c:42 (RET CROSS_2M cycles:2)
compute_flag div.c:28 (cycles:2)
compute_flag div.c:27 (RET CROSS_2M cycles:1)
rand rand.c:28 (cycles:1)
rand rand.c:28 (RET CROSS_2M cycles:1)
__random random.c:298 (cycles:1)
__random random.c:297 (COND_BWD CROSS_2M cycles:1)
__random random.c:295 (cycles:1)
__random random.c:295 (COND_BWD CROSS_2M cycles:1)
__random random.c:295 (cycles:1)
__random random.c:295 (RET CROSS_2M cycles:9)
- Beautify the fcntl syscall, which is an interesting one in the sense
that infrastructure had to be put in place to change the formatters of
some arguments according to the value in a previous one, i.e. cmd
dictates how arg and the syscall return will be formatted.
(Arnaldo Carvalho de Melo
Infrastructure changes:
- 'perf test attr' fixes (Jiri Olsa)
Vendor events changes:
- Add POWER9 PMU events Sukadev (Bhattiprolu)
- Support additional POWER8+ PVR in PMU mapfile (Shriya)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Vince Weaver reported:
> I was tracking down some regressions in my perf_event_test testsuite.
> Some of the tests broke in the 4.11-rc1 timeframe.
>
> I've bisected one of them, this report is about
> tests/overflow/simul_oneshot_group_overflow
> This test creates an event group containing two sampling events, set
> to overflow to a signal handler (which disables and then refreshes the
> event).
>
> On a good kernel you get the following:
> Event perf::instructions with period 1000000
> Event perf::instructions with period 2000000
> fd 3 overflows: 946 (perf::instructions/1000000)
> fd 4 overflows: 473 (perf::instructions/2000000)
> Ending counts:
> Count 0: 946379875
> Count 1: 946365218
>
> With the broken kernels you get:
> Event perf::instructions with period 1000000
> Event perf::instructions with period 2000000
> fd 3 overflows: 938 (perf::instructions/1000000)
> fd 4 overflows: 318 (perf::instructions/2000000)
> Ending counts:
> Count 0: 946373080
> Count 1: 653373058
The root cause of the bug is that the following commit:
487f05e18a ("perf/core: Optimize event rescheduling on active contexts")
erronously assumed that event's 'pinned' setting determines whether the
event belongs to a pinned group or not, but in fact, it's the group
leader's pinned state that matters.
This was discovered by Vince in the test case described above, where two instruction
counters are grouped, the group leader is pinned, but the other event is not;
in the regressed case the counters were off by 33% (the difference between events'
periods), but should be the same within the error margin.
Fix the problem by looking at the group leader's pinning.
Reported-by: Vince Weaver <vincent.weaver@maine.edu>
Tested-by: Vince Weaver <vincent.weaver@maine.edu>
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
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>
Cc: Stephane Eranian <eranian@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Fixes: 487f05e18a ("perf/core: Optimize event rescheduling on active contexts")
Link: http://lkml.kernel.org/r/87lgnmvw7h.fsf@ashishki-desk.ger.corp.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Show branch type in callchain entry. The branch type is printed
with other LBR information (such as cycles/abort/...).
For example:
perf record -g -j any,save_type
perf report --branch-history --stdio --no-children
38.50% div.c:45 [.] main div
|
---main div.c:42 (RET CROSS_2M cycles:2)
compute_flag div.c:28 (cycles:2)
compute_flag div.c:27 (RET CROSS_2M cycles:1)
rand rand.c:28 (cycles:1)
rand rand.c:28 (RET CROSS_2M cycles:1)
__random random.c:298 (cycles:1)
__random random.c:297 (COND_BWD CROSS_2M cycles:1)
__random random.c:295 (cycles:1)
__random random.c:295 (COND_BWD CROSS_2M cycles:1)
__random random.c:295 (cycles:1)
__random random.c:295 (RET CROSS_2M cycles:9)
Change log
v6: Remove the branch_type_str() since it's moved to branch.c.
v5: Rewrite the branch info print code in util/callchain.c.
v4: Comparing to previous version, the major changes are:
Signed-off-by: Yao Jin <yao.jin@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1500379995-6449-8-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Show the branch type statistics at the end of perf report --stdio.
For example:
perf report --stdio
COND_FWD: 28.5%
COND_BWD: 9.4%
CROSS_4K: 0.7%
CROSS_2M: 14.1%
COND: 37.9%
UNCOND: 0.2%
IND: 6.7%
CALL: 26.5%
RET: 28.7%
SYSRET: 0.0%
The branch types are:
COND_FWD: conditional forward
COND_BWD: conditional backward
COND: conditional branch
UNCOND: unconditional branch
IND: indirect
CALL: function call
IND_CALL: indirect function call
RET: function return
SYSCALL: syscall
SYSRET: syscall return
COND_CALL: conditional function call
COND_RET: conditional function return
CROSS_4K and CROSS_2M:
They are the metrics checking for branches cross 4K or 2MB pages.
It's an approximate computing. We don't know if the area is 4K or
2MB, so always compute both.
To make the output simple, if a branch crosses 2M area, CROSS_4K
will not be incremented.
Change log
v7: Since the common branch type definitions are changed, some
tags/strings are updated accordingly.
v6: Remove branch_type_stat_display() since it's moved to branch.c.
v5: Remove the unnecessary sort__mode checking in
hist_iter__branch_callback().
v4: Comparing to previous version, the major changes are:
Add the computing of JCC forward/JCC backward and cross page checking
by using the from and to addresses.
Signed-off-by: Yao Jin <yao.jin@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1500379995-6449-7-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Create new util/branch.c and util/branch.h to contain the common branch
functions. Such as:
branch_type_count(): Count the numbers of branch types
branch_type_name() : Return the name of branch type
branch_type_stat_display(): Display branch type statistics info
branch_type_str(): Construct the branch type string.
The branch type is saved in branch_flags.
Change log:
v8: Change PERF_BR_NONE to PERF_BR_UNKNOWN.
v7: Since the common branch type name is changed (e.g. JCC->COND),
this patch is performed the modification accordingly.
v6: Move that multiline conditional code inside {} brackets.
Move branch_type_stat_display() from builtin-report.c to
branch.c.
Move branch_type_str() from callchain.c to branch.c.
v5: It's a new patch in v5 patch series.
Signed-off-by: Yao Jin <yao.jin@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1500379995-6449-6-git-send-email-yao.jin@linux.intel.com
[ Don't use 'index' and 'stat' as names for variables, it shadows global decls in older distros ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Arnaldo Carvalho de Melo