提交 · d5c3a937e0b3ac16d0d7d152fab6768f765350ac · openanolis / cloud-kernel

08 2月, 2017 10 次提交

perf probe: Add option --symfs · d5c3a937

由 Uwe Kleine-König 提交于 7月 21, 2016

perf probe makes use of debug symbols, so add --symfs as the other
commands have.
Signed-off-by: NUwe Kleine-König <u.kleine-koenig@pengutronix.de>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: kernel@pengutronix.de
Link: http://lkml.kernel.org/r/1469094512-13440-2-git-send-email-u.kleine-koenig@pengutronix.deSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>

d5c3a937

perf symbols: Take into account symfs setting when reading file build ID · 9b200653

由 Victor Kamensky 提交于 2月 06, 2017

After commit 5baecbcd ("perf symbols: we can now read separate
debug-info files based on a build ID") and when --symfs option is used
perf failed to pick up symbols for file with the same name between host
and sysroot specified by --symfs option.  One can see message like this:

  bin/bash with build id 26f0062cb6950d4d1ab0fd9c43eae8b10ca42062 not found, continuing without symbols

It happens because code added by 5baecbcd opens files directly by
dso->long_name without symbol_conf.symfs consideration, which as result
picks one from the host. It reads its build ID and later even code finds
another proper file in directory pointed by --symfs perf ignores it
because build id mismatches.

Fix is to use __symbol__join_symfs to adjust file name according to
--symfs setting. If no --symfs passed the operation would noop and picks
the same host file as before.

Also note in latter tree after 5baecbcd commit additional check for
'!dso->has_build_id' was added, so to observe error condition 'perf
record' should run with --no-buildid, so perf.data itself would not have
build id for target binary in buildid perf section and 'perf report'
will pass '!dso->has_build_id' condition. Or target binary should not
have build id, but the same binary on host has build id, again
'!dso->has_build_id' will pass in this case and incorrect build id could
be read if --symfs is used.
Signed-off-by: NVictor Kamensky <kamensky@cisco.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Chris Phlipot <cphlipot0@gmail.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: He Kuang <hekuang@huawei.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: xe-linux-external@cisco.com
Fixes: 5baecbcd ("perf symbols: we can now read separate debug-info files based on a build ID")
Link: http://lkml.kernel.org/r/1486424908-17094-1-git-send-email-kamensky@cisco.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>

9b200653

perf sdt: Show proper hint when event not yet in place via 'perf probe' · 27cf5706

由 Ravi Bangoria 提交于 2月 03, 2017

All events from 'perf list', except SDT events, can be directly recorded
with 'perf record'. But, the flow is little different for SDT events.

Probe points for SDT event needs to be created using 'perf probe' before
recording it using 'perf record'.

Perf shows misleading hint when a user tries to record SDT event without
first creating a probe point. Show proper hint there.

Before patch:

  $ perf record -a -e sdt_glib:idle__add
    event syntax error: 'sdt_glib:idle__add'
                         \___ unknown tracepoint

    Error: File /sys/kernel/debug/tracing/events/sdt_glib/idle__add not found.
    Hint:  Perhaps this kernel misses some CONFIG_ setting to enable this feature?.
    ...

After patch:

  $ perf record -a -e sdt_glib:idle__add
    event syntax error: 'sdt_glib:idle__add'
                         \___ unknown tracepoint

    Error: File /sys/kernel/debug/tracing/events/sdt_glib/idle__add not found.
    Hint:  SDT event cannot be directly recorded on.
           Please first use 'perf probe sdt_glib:idle__add' before recording it.
    ...

  $ perf probe sdt_glib:idle__add
    Added new event:
      sdt_glib:idle__add   (on %idle__add in /usr/lib64/libglib-2.0.so.0.5000.2)

    You can now use it in all perf tools, such as:

        perf record -e sdt_glib:idle__add -aR sleep 1

  $ perf record -a -e sdt_glib:idle__add
    [ perf record: Woken up 1 times to write data ]
    [ perf record: Captured and wrote 0.175 MB perf.data ]
Suggested-and-Acked-by: NIngo Molnar <mingo@redhat.com>
Signed-off-by: NRavi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Tested-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: NMasami Hiramatsu <mhiramat@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexis Berlemont <alexis.berlemont@gmail.com>
Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20170203102642.17258-1-ravi.bangoria@linux.vnet.ibm.com
[ s/Please use/Please first use/ and break the Hint line in two ]
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>

27cf5706

perf list: Add debug support for outputing alias string · f2361024

由 Andi Kleen 提交于 1月 27, 2017

For debugging and testing it is useful to see the converted alias
string. Add support to perf stat/record and perf list to print the alias
conversion. The text string is saved in the alias structure.  For perf
stat/record it is folded into the normal -v. For perf list -v was taken,
so we use --debug.

Before:

% perf list
...
cache:
  l1d.replacement
       [L1D data line replacements]
  l1d_pend_miss.fb_full
       [Cycles a demand request was blocked due to Fill Buffers inavailability]

After

% perf list --debug
...
cache:
  l1d.replacement
       [L1D data line replacements]
        cpu/umask=0x1,period=2000003,event=0x51/
  l1d_pend_miss.fb_full
       [Cycles a demand request was blocked due to Fill Buffers inavailability]
        cpu/umask=0x2,period=2000003,cmask=1,event=0x48/
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Tested-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20170128020345.19007-6-andi@firstfloor.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>

f2361024

perf pmu: Support event aliases for non cpu// pmus · 231bb2aa

由 Andi Kleen 提交于 1月 27, 2017

The code for handling pmu aliases without specifying the PMU hardcoded
only supported the cpu PMU.

This patch extends it to work for all PMUs. We always duplicate the
event for all PMUs that have an matching alias. This allows to
automatically expand an alias for all instances of a PMU (so for example
you can monitor all cache boxes with a single event)
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Acked-by: NJiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20170128020345.19007-5-andi@firstfloor.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>

231bb2aa

perf pmu: Support per pmu json aliases · 15b22ed3

由 Andi Kleen 提交于 1月 27, 2017

Add support for registering json aliases per PMU. Any alias with an unit
matching the prefix is registered to the PMU.  Uncore has multiple
instances of most units, so all these aliases get registered for each
individual PMU (this is important later to run the event on every
instance of the PMU).

To avoid printing the events multiple times in perf list filter out
duplicated events during printing.

v2: Rely on uncore_ prefix already in unit
v3: Document why calls were reordered
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20170128020345.19007-4-andi@firstfloor.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>

15b22ed3

perf jevents: Add support for parsing uncore json files · fedb2b51

由 Andi Kleen 提交于 1月 27, 2017

Handle the "Unit" field, which is needed to find the right PMU for an
event. We call it "pmu" and convert it to the perf pmu name with an
uncore prefix.

Handle the "ExtSel" field, which just extends the event mask with an
additional bit.

Handle the "Filter" field which adds parameters to the main event
to configure filtering.

Handle the "Unit" field which declares the unit the values should be
scaled too (similar to what the kernel exports)

Set up the "perpkg" field for uncore events so that perf knows they are
per package (similar to what the kernel exports)

Then output the fields into the pmu-events data structures which are
compiled into perf.

Filter out zero fields, except for the event itself.

v2: Fix compilation. Add uncore_ prefix at pre-processing time.
    Move eventcode change to separate patch.

v3: Remove extra __maybe_unused

v4: dont duplicate aliases for cpu pmu events
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Acked-by: NJiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20170128020345.19007-3-andi@firstfloor.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>

fedb2b51

perf jevents: Parse eventcode as number · d5811419

由 Andi Kleen 提交于 1月 27, 2017

The next patch needs to modify event code. Previously eventcode was just
passed through as a string. Now parse it as a number.

v2: Don't special case 0
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Acked-by: NJiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20170128020345.19007-2-andi@firstfloor.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>

d5811419

perf bpf: Add missing newline in debug messages · 4d416436

由 He Kuang 提交于 2月 07, 2017

These two debug messages are missing the trailing newline.
Signed-off-by: NHe Kuang <hekuang@huawei.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Bintian Wang <bintian.wang@huawei.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Link: http://lkml.kernel.org/r/20170207073412.26983-2-hekuang@huawei.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>

4d416436

perf tools arm64: Add support for generating bpf prologue · 3bb53c9f

由 He Kuang 提交于 2月 07, 2017

Since HAVE_KPROBES can be enabled in arm64, this patch introduces
regs_query_register_offset() to convert register name to offset for
arm64, so the BPF prologue feature is ready to use.
Signed-off-by: NHe Kuang <hekuang@huawei.com>
Reviewed-by: NWill Deacon <will.deacon@arm.com>
Acked-by: NMasami Hiramatsu <mhiramat@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Bintian Wang <bintian.wang@huawei.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: linux-arm-kernel@lists.infradead.org
Link: http://lkml.kernel.org/r/20170207073412.26983-1-hekuang@huawei.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>

3bb53c9f

02 2月, 2017 3 次提交

perf callchain: Reference count maps · aa33b9b9

由 Krister Johansen 提交于 1月 05, 2017

If dso__load_kcore frees all of the existing maps, but one has already
been attached to a callchain cursor node, then we can get a SIGSEGV in
any function that happens to try to use this invalid cursor.  Use the
existing map refcount mechanism to forestall cleanup of a map until the
cursor iterates past the node.
Signed-off-by: NKrister Johansen <kjlx@templeofstupid.com>
Tested-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: stable@kernel.org
Fixes: 84c2cafa ("perf tools: Reference count struct map")
Link: http://lkml.kernel.org/r/20170106062331.GB2707@templeofstupid.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>

aa33b9b9

perf diff: Fix -o/--order option behavior (again) · a1c9f97f

由 Namhyung Kim 提交于 1月 18, 2017

Commit 21e6d842 ("perf diff: Use perf_hpp__register_sort_field
interface") changed list_add() to perf_hpp__register_sort_field().

This resulted in a behavior change since the field was added to the tail
instead of the head. So the -o option is mostly ignored due to its
order in the list.

This patch fixes it by adding perf_hpp__prepend_sort_field().
Signed-off-by: NNamhyung Kim <namhyung@kernel.org>
Acked-by: NJiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Fixes: 21e6d842 ("perf diff: Use perf_hpp__register_sort_field interface")
Link: http://lkml.kernel.org/r/20170118051457.30946-2-namhyung@kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>

a1c9f97f

perf diff: Fix segfault on 'perf diff -o N' option · 8381cdd0

由 Namhyung Kim 提交于 1月 18, 2017

The -o/--order option is to select column number to sort a diff result.

It does the job by adding a hpp field at the beginning of the sort list.
But it should not be added to the output field list as it has no
callbacks required by a output field.

During the setup_sorting(), the perf_hpp__setup_output_field() appends
the given sort keys to the output field if it's not there already.

Originally it was checked by fmt->list being non-empty. But commit
3f931f2c ("perf hists: Make hpp setup function generic") changed it
to check the ->equal callback.

Anyways, we don't need to add the pseudo hpp field to the output field
list since it won't be used for output. So just skip fields if they
have no ->color or ->entry callbacks.
Signed-off-by: NNamhyung Kim <namhyung@kernel.org>
Acked-by: NJiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Fixes: 3f931f2c ("perf hists: Make hpp setup function generic")
Link: http://lkml.kernel.org/r/20170118051457.30946-1-namhyung@kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>

8381cdd0

01 2月, 2017 9 次提交

perf ftrace: Add ftrace.tracer config option · b05d1093

由 Taeung Song 提交于 1月 31, 2017

Currently 'perf ftrace' command allows selecting 'function_graph' or
'function', defaulting to 'function_graph'.

Add ftrace.tracer config option to select the default tracer:

    # cat ~/.perfconfig
    [ftrace]
        tracer = function

    # perf ftrace usleep 123456 | head -10
      <...>-14450 [002] d... 10089.284231: finish_task_switch <-__schedule
      <...>-14450 [002] .... 10089.284232: finish_wait <-pipe_wait
      <...>-14450 [002] .... 10089.284232: mutex_lock <-pipe_wait
      <...>-14450 [002] .... 10089.284232: _cond_resched <-mutex_lock

Committer notes:

Retesting it with invalid variables, invalid values for ftrace.tracer,
and a valid one:

  # cat ~/.perfconfig
  [ftrace]
        trace = function
  # perf ftrace usleep 1
  Error: wrong config key-value pair ftrace.trace=function
  # cat ~/.perfconfig
  [ftrace]
        tracer = functin
  # perf ftrace usleep 1
  Please select "function_graph" (default) or "function"
  Error: wrong config key-value pair ftrace.tracer=functin
  # cat ~/.perfconfig
  [ftrace]
        tracer = function
  # perf ftrace usleep 1 | head -5
          <idle>-0     [000] d...  3855.820847: switch_mm_irqs_off <-__schedule
           <...>-18550 [000] d...  3855.820849: finish_task_switch <-__schedule
           <...>-18550 [000] d...  3855.820851: smp_irq_work_interrupt <-irq_work_interrupt
           <...>-18550 [000] d...  3855.820851: irq_enter <-smp_irq_work_interrupt
           <...>-18550 [000] d...  3855.820851: rcu_irq_enter <-irq_enter
  #
Signed-off-by: NTaeung Song <treeze.taeung@gmail.com>
Tested-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1485862711-20216-3-git-send-email-treeze.taeung@gmail.com
[ Added missign space in error message, changed the logic to make it more compact and less error prone ]
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>

b05d1093

perf tools: Create for_each_event macro for tracepoints iteration · 43d41deb

由 Taeung Song 提交于 1月 31, 2017

Similar to for_each_subsystem and for_each_event in util/parse-events.c,
add new macro 'for_each_event' for easy iteration over the tracepoints
in order to be more compact and readable.
Signed-off-by: NTaeung Song <treeze.taeung@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1485862711-20216-2-git-send-email-treeze.taeung@gmail.com
[ Slight change to keep existing style for checking strcmp() return ]
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>

43d41deb

perf test: Add libbpf pinning test · a2630536