<feed xmlns='http://www.w3.org/2005/Atom'>
<title>kernel/tools/perf/util/annotate.h, branch linux-4.17.y</title>
<subtitle>Hosts the 0x221E linux distro kernel.</subtitle>
<id>https://universe.0xinfinity.dev/distro/kernel/atom?h=linux-4.17.y</id>
<link rel='self' href='https://universe.0xinfinity.dev/distro/kernel/atom?h=linux-4.17.y'/>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/'/>
<updated>2018-04-12T13:32:39Z</updated>
<entry>
<title>perf annotate: Allow showing offsets in more than just jump targets</title>
<updated>2018-04-12T13:32:39Z</updated>
<author>
<name>Arnaldo Carvalho de Melo</name>
<email>acme@redhat.com</email>
</author>
<published>2018-04-11T13:30:03Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=592c10e217f3edb35c7e0deba161fef69ad1a336'/>
<id>urn:sha1:592c10e217f3edb35c7e0deba161fef69ad1a336</id>
<content type='text'>
Jesper wanted to see offsets at callq sites when doing some performance
investigation related to retpolines, so save him some time by providing
an 'struct annotation_options' to control where offsets should appear:
just on jump targets? That + call instructions? All?

This puts in place the logic to show the offsets, now we need to wire
this up in the TUI browser (next patch) and on the 'perf annotate --stdio2"
interface, where we need a more general mechanism to setup the
'annotation_options' struct from the command line.

Suggested-by: Jesper Dangaard Brouer &lt;brouer@redhat.com&gt;
Cc: Adrian Hunter &lt;adrian.hunter@intel.com&gt;
Cc: Alexei Starovoitov &lt;alexei.starovoitov@gmail.com&gt;
Cc: Andi Kleen &lt;ak@linux.intel.com&gt;
Cc: Daniel Borkmann &lt;daniel@iogearbox.net&gt;
Cc: David Ahern &lt;dsahern@gmail.com&gt;
Cc: Jin Yao &lt;yao.jin@linux.intel.com&gt;
Cc: Jiri Olsa &lt;jolsa@kernel.org&gt;
Cc: Linus Torvalds &lt;torvalds@linux-foundation.org&gt;
Cc: Martin Liška &lt;mliska@suse.cz&gt;
Cc: Namhyung Kim &lt;namhyung@kernel.org&gt;
Cc: Ravi Bangoria &lt;ravi.bangoria@linux.vnet.ibm.com&gt;
Cc: Thomas Richter &lt;tmricht@linux.vnet.ibm.com&gt;
Cc: Wang Nan &lt;wangnan0@huawei.com&gt;
Link: https://lkml.kernel.org/n/tip-m3jc9c3swobye9tj08gnh5i7@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo &lt;acme@redhat.com&gt;
</content>
</entry>
<entry>
<title>perf annotate: Introduce annotation__scnprintf_samples_period() method</title>
<updated>2018-04-03T18:22:55Z</updated>
<author>
<name>Arnaldo Carvalho de Melo</name>
<email>acme@redhat.com</email>
</author>
<published>2018-04-03T18:19:47Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=b213eac245aa2d29a3b9dd90f3b96ab182337ee8'/>
<id>urn:sha1:b213eac245aa2d29a3b9dd90f3b96ab182337ee8</id>
<content type='text'>
To print a string using the total period (nr_events) and the number of
samples for a given annotation, i.e. for a given symbol, the counterpart
to hists__scnprintf_samples_period(), that is for all the samples in a
session (be it a live session, think 'perf top' or a perf.data file,
think 'perf report').

Cc: Adrian Hunter &lt;adrian.hunter@intel.com&gt;
Cc: David Ahern &lt;dsahern@gmail.com&gt;
Cc: Jiri Olsa &lt;jolsa@kernel.org&gt;
Cc: Martin Liška &lt;mliska@suse.cz&gt;
Cc: Namhyung Kim &lt;namhyung@kernel.org&gt;
Cc: Wang Nan &lt;wangnan0@huawei.com&gt;
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=196935
Link: https://lkml.kernel.org/n/tip-goj2wu4fxutc8vd46mw3yg14@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo &lt;acme@redhat.com&gt;
</content>
</entry>
<entry>
<title>perf annotate: Add "_local" to jump/offset validation routines</title>
<updated>2018-03-23T19:46:16Z</updated>
<author>
<name>Arnaldo Carvalho de Melo</name>
<email>acme@redhat.com</email>
</author>
<published>2018-03-23T13:12:33Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=2eff061162819e00ec6379874ceb47caef17bcba'/>
<id>urn:sha1:2eff061162819e00ec6379874ceb47caef17bcba</id>
<content type='text'>
Because they all really check if we can access data structures/visual
constructs where a "jump" instruction targets code in the same function,
i.e. things like:

  __pthread_mutex_lock  /usr/lib64/libpthread-2.26.so
  1.95 │       mov    __pthread_force_elision,%ecx
       │    ┌──test   %ecx,%ecx
  0.07 │    ├──je     60
       │    │  test   $0x300,%esi
       │    │↓ jne    60
       │    │  or     $0x100,%esi
       │    │  mov    %esi,0x10(%rdi)
       │ 42:│  mov    %esi,%edx
       │    │  lea    0x16(%r8),%rsi
       │    │  mov    %r8,%rdi
       │    │  and    $0x80,%edx
       │    │  add    $0x8,%rsp
       │    │→ jmpq   __lll_lock_elision
       │    │  nop
  0.29 │ 60:└─→and    $0x80,%esi
  0.07 │       mov    $0x1,%edi
  0.29 │       xor    %eax,%eax
  2.53 │       lock   cmpxchg %edi,(%r8)

And not things like that "jmpq __lll_lock_elision", that instead should behave
like a "call" instruction and "jump" to the disassembly of "___lll_lock_elision".

Cc: Adrian Hunter &lt;adrian.hunter@intel.com&gt;
Cc: Andi Kleen &lt;ak@linux.intel.com&gt;
Cc: David Ahern &lt;dsahern@gmail.com&gt;
Cc: Jin Yao &lt;yao.jin@linux.intel.com&gt;
Cc: Jiri Olsa &lt;jolsa@kernel.org&gt;
Cc: Namhyung Kim &lt;namhyung@kernel.org&gt;
Cc: Wang Nan &lt;wangnan0@huawei.com&gt;
Link: https://lkml.kernel.org/n/tip-3cwx39u3h66dfw9xjrlt7ca2@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo &lt;acme@redhat.com&gt;
</content>
</entry>
<entry>
<title>perf annotate: Mark jumps to outher functions with the call arrow</title>
<updated>2018-03-21T19:19:55Z</updated>
<author>
<name>Arnaldo Carvalho de Melo</name>
<email>acme@redhat.com</email>
</author>
<published>2018-03-20T20:20:43Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=751b1783da784299b0509adb6a9cd3024cc4f837'/>
<id>urn:sha1:751b1783da784299b0509adb6a9cd3024cc4f837</id>
<content type='text'>
Things like this in _cpp_lex_token (gcc's cc1 program):

     cpp_named_operator2name@@Base+0xa72

Point to a place that is after the cpp_named_operator2name boundaries,
i.e.  in the ELF symbol table for cc1 cpp_named_operator2name is marked
as being 32-bytes long, but it in fact is much larger than that, so we
seem to need a symbols__find() routine that looks for &gt;= current-&gt;start
and  &lt; next_symbol-&gt;start, possibly just for C++ objects?

For now lets just make some progress by marking jumps to outside the
current function as call like.

Actual navigation will come next, with further understanding of how the
symbol searching and disassembly should be done.

Cc: Adrian Hunter &lt;adrian.hunter@intel.com&gt;
Cc: Andi Kleen &lt;ak@linux.intel.com&gt;
Cc: David Ahern &lt;dsahern@gmail.com&gt;
Cc: Jin Yao &lt;yao.jin@linux.intel.com&gt;
Cc: Jiri Olsa &lt;jolsa@kernel.org&gt;
Cc: Namhyung Kim &lt;namhyung@kernel.org&gt;
Cc: Wang Nan &lt;wangnan0@huawei.com&gt;
Link: https://lkml.kernel.org/n/tip-aiys0a0bsgm3e00hbi6fg7yy@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo &lt;acme@redhat.com&gt;
</content>
</entry>
<entry>
<title>perf annotate: Pass function descriptor to its instruction parsing routines</title>
<updated>2018-03-21T19:19:41Z</updated>
<author>
<name>Arnaldo Carvalho de Melo</name>
<email>acme@redhat.com</email>
</author>
<published>2018-03-20T19:19:08Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=85a84e4f813912ab77d872ff6882dd7b435fbf4e'/>
<id>urn:sha1:85a84e4f813912ab77d872ff6882dd7b435fbf4e</id>
<content type='text'>
We need that to figure out if jumps have targets in a different
function.

E.g. _cpp_lex_token(), in /usr/libexec/gcc/x86_64-redhat-linux/5.3.1/cc1
has a line like this:

  jne    c469be &lt;cpp_named_operator2name@@Base+0xa72&gt;

Cc: Adrian Hunter &lt;adrian.hunter@intel.com&gt;
Cc: David Ahern &lt;dsahern@gmail.com&gt;
Cc: Jiri Olsa &lt;jolsa@kernel.org&gt;
Cc: Namhyung Kim &lt;namhyung@kernel.org&gt;
Cc: Wang Nan &lt;wangnan0@huawei.com&gt;
Link: https://lkml.kernel.org/n/tip-ris0ioziyp469pofpzix2atb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo &lt;acme@redhat.com&gt;
</content>
</entry>
<entry>
<title>perf annotate browser: Add 'P' hotkey to dump annotation to file</title>
<updated>2018-03-21T15:53:43Z</updated>
<author>
<name>Arnaldo Carvalho de Melo</name>
<email>acme@redhat.com</email>
</author>
<published>2018-03-16T19:57:47Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=d9bd766584491dbb6f96c85a27562eb1289b2ca9'/>
<id>urn:sha1:d9bd766584491dbb6f96c85a27562eb1289b2ca9</id>
<content type='text'>
Just like we have in the histograms browser used as the main screen for
'perf top --tui' and 'perf report --tui', to print the current
annotation to a file with a named composed by the symbol name and the
".annotation" suffix.

Here is one example of pressing 'A' on 'perf top' to live annotate a
kernel function and then press 'P' to dump that annotation, the
resulting file:

  # cat _raw_spin_lock_irqsave.annotation
  _raw_spin_lock_irqsave() /proc/kcore
  Event: cycles:ppp

    7.14        nop
   21.43        push   %rbx
    7.14        pushfq
                pop    %rax
                nop
                mov    %rax,%rbx
                cli
                nop
                xor    %eax,%eax
                mov    $0x1,%edx
   64.29        lock   cmpxchg %edx,(%rdi)
                test   %eax,%eax
              ↓ jne    2b
                mov    %rbx,%rax
                pop    %rbx
              ← retq
          2b:   mov    %eax,%esi
              → callq  queued_spin_lock_slowpath
                mov    %rbx,%rax
                pop    %rbx
              ← retq
  #

Cc: Adrian Hunter &lt;adrian.hunter@intel.com&gt;
Cc: Andi Kleen &lt;ak@linux.intel.com&gt;
Cc: David Ahern &lt;dsahern@gmail.com&gt;
Cc: Jin Yao &lt;yao.jin@linux.intel.com&gt;
Cc: Jiri Olsa &lt;jolsa@kernel.org&gt;
Cc: Namhyung Kim &lt;namhyung@kernel.org&gt;
Cc: Wang Nan &lt;wangnan0@huawei.com&gt;
Link: https://lkml.kernel.org/n/tip-zzmnrwugb5vtk7bvg0rbx150@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo &lt;acme@redhat.com&gt;
</content>
</entry>
<entry>
<title>perf annotate: Move the default annotate options to the library</title>
<updated>2018-03-21T15:53:40Z</updated>
<author>
<name>Arnaldo Carvalho de Melo</name>
<email>acme@redhat.com</email>
</author>
<published>2018-03-16T17:33:38Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=7f0b6fde3111aec82487662ccef5a4ebecb93381'/>
<id>urn:sha1:7f0b6fde3111aec82487662ccef5a4ebecb93381</id>
<content type='text'>
One more thing that goes from the TUI code to be used more widely,
for instance it'll affect the default options used by:

  perf annotate --stdio2

Cc: Adrian Hunter &lt;adrian.hunter@intel.com&gt;
Cc: Andi Kleen &lt;ak@linux.intel.com&gt;
Cc: David Ahern &lt;dsahern@gmail.com&gt;
Cc: Jin Yao &lt;yao.jin@linux.intel.com&gt;
Cc: Jiri Olsa &lt;jolsa@kernel.org&gt;
Cc: Namhyung Kim &lt;namhyung@kernel.org&gt;
Cc: Wang Nan &lt;wangnan0@huawei.com&gt;
Link: https://lkml.kernel.org/n/tip-0nsz0dm0akdbo30vgja2a10e@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo &lt;acme@redhat.com&gt;
</content>
</entry>
<entry>
<title>perf annotate: Introduce the --stdio2 output mode</title>
<updated>2018-03-21T15:53:26Z</updated>
<author>
<name>Arnaldo Carvalho de Melo</name>
<email>acme@redhat.com</email>
</author>
<published>2018-03-16T02:44:34Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=befd2a38a632b1f27ad652fea67c8cf97ce59409'/>
<id>urn:sha1:befd2a38a632b1f27ad652fea67c8cf97ce59409</id>
<content type='text'>
This uses the TUI augmented formatting routines, modulo interactivity.

  # perf annotate --ignore-vmlinux --stdio2 _raw_spin_lock_irqsave
  _raw_spin_lock_irqsave() /proc/kcore
  Event: cycles:ppp

  Percent

              Disassembly of section load0:

              ffffffff9a8734b0 &lt;load0&gt;:
                nop
                push   %rbx
   50.00        pushfq
                pop    %rax
                nop
                mov    %rax,%rbx
                cli
                nop
                xor    %eax,%eax
                mov    $0x1,%edx
   50.00        lock   cmpxchg %edx,(%rdi)
                test   %eax,%eax
              ↓ jne    2b
                mov    %rbx,%rax
                pop    %rbx
              ← retq
          2b:   mov    %eax,%esi
              → callq  queued_spin_lock_slowpath
                mov    %rbx,%rax
                pop    %rbx
              ← retq

Tested-by: Jin Yao &lt;yao.jin@linux.intel.com&gt;
Cc: Adrian Hunter &lt;adrian.hunter@intel.com&gt;
Cc: Andi Kleen &lt;ak@linux.intel.com&gt;
Cc: David Ahern &lt;dsahern@gmail.com&gt;
Cc: Jiri Olsa &lt;jolsa@kernel.org&gt;
Cc: Namhyung Kim &lt;namhyung@kernel.org&gt;
Cc: Wang Nan &lt;wangnan0@huawei.com&gt;
Link: https://lkml.kernel.org/n/tip-6cte5o8z84mbivbvqlg14uh1@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo &lt;acme@redhat.com&gt;
</content>
</entry>
<entry>
<title>perf annotate: Introduce annotation_line__filter()</title>
<updated>2018-03-20T18:36:22Z</updated>
<author>
<name>Arnaldo Carvalho de Melo</name>
<email>acme@redhat.com</email>
</author>
<published>2018-03-16T13:39:24Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=9b80d1f946ee40923f7bf51c69cb3a6ac6097e4a'/>
<id>urn:sha1:9b80d1f946ee40923f7bf51c69cb3a6ac6097e4a</id>
<content type='text'>
Out of the TUI logic that allows toggling the presentation of source
code lines.

Will be used in the upcoming --stdio2 mode.

Cc: Adrian Hunter &lt;adrian.hunter@intel.com&gt;
Cc: Andi Kleen &lt;ak@linux.intel.com&gt;
Cc: David Ahern &lt;dsahern@gmail.com&gt;
Cc: Jin Yao &lt;yao.jin@linux.intel.com&gt;
Cc: Jiri Olsa &lt;jolsa@kernel.org&gt;
Cc: Namhyung Kim &lt;namhyung@kernel.org&gt;
Cc: Wang Nan &lt;wangnan0@huawei.com&gt;
Link: https://lkml.kernel.org/n/tip-g0ckz9ajy6unswrv2iy39mxk@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo &lt;acme@redhat.com&gt;
</content>
</entry>
<entry>
<title>perf annotate: Use a ops table for annotation_line__write()</title>
<updated>2018-03-20T18:36:18Z</updated>
<author>
<name>Arnaldo Carvalho de Melo</name>
<email>acme@redhat.com</email>
</author>
<published>2018-03-16T02:14:51Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=c298304bd747d6a0b733f0becb470ff07ead0317'/>
<id>urn:sha1:c298304bd747d6a0b733f0becb470ff07ead0317</id>
<content type='text'>
To simplify the passing of arguments, the --stdio2 code will have to set
all the fields with operations printing to stdout.

Cc: Adrian Hunter &lt;adrian.hunter@intel.com&gt;
Cc: Andi Kleen &lt;ak@linux.intel.com&gt;
Cc: David Ahern &lt;dsahern@gmail.com&gt;
Cc: Jin Yao &lt;yao.jin@linux.intel.com&gt;
Cc: Jiri Olsa &lt;jolsa@kernel.org&gt;
Cc: Namhyung Kim &lt;namhyung@kernel.org&gt;
Cc: Wang Nan &lt;wangnan0@huawei.com&gt;
Link: https://lkml.kernel.org/n/tip-pcs3c7vdy9ucygxflo4nl1o7@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo &lt;acme@redhat.com&gt;
</content>
</entry>
</feed>
