linux-toradex.git/tools/perf/util/callchain.h, branch v6.8

perf callchain: Minor layout changes to callchain_list

2023-10-25T20:39:32+00:00

Avoid 6 byte hole for padding. Place more frequently used fields
first in an attempt to use just 1 cacheline in the common case.

Before:
```
struct callchain_list {
        u64                        ip;                   /*     0     8 */
        struct map_symbol          ms;                   /*     8    24 */
        struct {
                _Bool              unfolded;             /*    32     1 */
                _Bool              has_children;         /*    33     1 */
        };                                               /*    32     2 */

        /* XXX 6 bytes hole, try to pack */

        u64                        branch_count;         /*    40     8 */
        u64                        from_count;           /*    48     8 */
        u64                        predicted_count;      /*    56     8 */
        /* --- cacheline 1 boundary (64 bytes) --- */
        u64                        abort_count;          /*    64     8 */
        u64                        cycles_count;         /*    72     8 */
        u64                        iter_count;           /*    80     8 */
        u64                        iter_cycles;          /*    88     8 */
        struct branch_type_stat *  brtype_stat;          /*    96     8 */
        const char  *              srcline;              /*   104     8 */
        struct list_head           list;                 /*   112    16 */

        /* size: 128, cachelines: 2, members: 13 */
        /* sum members: 122, holes: 1, sum holes: 6 */
};
```

After:
```
struct callchain_list {
        struct list_head           list;                 /*     0    16 */
        u64                        ip;                   /*    16     8 */
        struct map_symbol          ms;                   /*    24    24 */
        const char  *              srcline;              /*    48     8 */
        u64                        branch_count;         /*    56     8 */
        /* --- cacheline 1 boundary (64 bytes) --- */
        u64                        from_count;           /*    64     8 */
        u64                        cycles_count;         /*    72     8 */
        u64                        iter_count;           /*    80     8 */
        u64                        iter_cycles;          /*    88     8 */
        struct branch_type_stat *  brtype_stat;          /*    96     8 */
        u64                        predicted_count;      /*   104     8 */
        u64                        abort_count;          /*   112     8 */
        struct {
                _Bool              unfolded;             /*   120     1 */
                _Bool              has_children;         /*   121     1 */
        };                                               /*   120     2 */

        /* size: 128, cachelines: 2, members: 13 */
        /* padding: 6 */
};
```

Signed-off-by: Ian Rogers 
Cc: K Prateek Nayak 
Cc: Ravi Bangoria 
Cc: Sandipan Das 
Cc: Anshuman Khandual 
Cc: German Gomez 
Cc: James Clark 
Cc: Nick Terrell 
Cc: Sean Christopherson 
Cc: Changbin Du 
Cc: liuwenyu 
Cc: Yang Jihong 
Cc: Masami Hiramatsu 
Cc: Miguel Ojeda 
Cc: Song Liu 
Cc: Leo Yan 
Cc: Kajol Jain 
Cc: Andi Kleen 
Cc: Kan Liang 
Cc: Athira Rajeev 
Cc: Yanteng Si 
Cc: Liam Howlett 
Cc: Paolo Bonzini 
Link: https://lore.kernel.org/r/20231024222353.3024098-11-irogers@google.com
Signed-off-by: Namhyung Kim

perf callchain: Make brtype_stat in callchain_list optional

2023-10-25T20:39:08+00:00

struct callchain_list is 352bytes in size, 232 of which are
brtype_stat. brtype_stat is only used for certain callchain_list
items so make it optional, allocating when necessary. So that
printing doesn't need to deal with an optional brtype_stat, pass
an empty/zero version.

Before:
```
struct callchain_list {
        u64                        ip;                   /*     0     8 */
        struct map_symbol          ms;                   /*     8    24 */
        struct {
                _Bool              unfolded;             /*    32     1 */
                _Bool              has_children;         /*    33     1 */
        };                                               /*    32     2 */

        /* XXX 6 bytes hole, try to pack */

        u64                        branch_count;         /*    40     8 */
        u64                        from_count;           /*    48     8 */
        u64                        predicted_count;      /*    56     8 */
        /* --- cacheline 1 boundary (64 bytes) --- */
        u64                        abort_count;          /*    64     8 */
        u64                        cycles_count;         /*    72     8 */
        u64                        iter_count;           /*    80     8 */
        u64                        iter_cycles;          /*    88     8 */
        struct branch_type_stat    brtype_stat;          /*    96   232 */
        /* --- cacheline 5 boundary (320 bytes) was 8 bytes ago --- */
        const char  *              srcline;              /*   328     8 */
        struct list_head           list;                 /*   336    16 */

        /* size: 352, cachelines: 6, members: 13 */
        /* sum members: 346, holes: 1, sum holes: 6 */
        /* last cacheline: 32 bytes */
};
```

After:
```
struct callchain_list {
        u64                        ip;                   /*     0     8 */
        struct map_symbol          ms;                   /*     8    24 */
        struct {
                _Bool              unfolded;             /*    32     1 */
                _Bool              has_children;         /*    33     1 */
        };                                               /*    32     2 */

        /* XXX 6 bytes hole, try to pack */

        u64                        branch_count;         /*    40     8 */
        u64                        from_count;           /*    48     8 */
        u64                        predicted_count;      /*    56     8 */
        /* --- cacheline 1 boundary (64 bytes) --- */
        u64                        abort_count;          /*    64     8 */
        u64                        cycles_count;         /*    72     8 */
        u64                        iter_count;           /*    80     8 */
        u64                        iter_cycles;          /*    88     8 */
        struct branch_type_stat *  brtype_stat;          /*    96     8 */
        const char  *              srcline;              /*   104     8 */
        struct list_head           list;                 /*   112    16 */

        /* size: 128, cachelines: 2, members: 13 */
        /* sum members: 122, holes: 1, sum holes: 6 */
};
```

Signed-off-by: Ian Rogers 
Cc: K Prateek Nayak 
Cc: Ravi Bangoria 
Cc: Sandipan Das 
Cc: Anshuman Khandual 
Cc: German Gomez 
Cc: James Clark 
Cc: Nick Terrell 
Cc: Sean Christopherson 
Cc: Changbin Du 
Cc: liuwenyu 
Cc: Yang Jihong 
Cc: Masami Hiramatsu 
Cc: Miguel Ojeda 
Cc: Song Liu 
Cc: Leo Yan 
Cc: Kajol Jain 
Cc: Andi Kleen 
Cc: Kan Liang 
Cc: Athira Rajeev 
Cc: Yanteng Si 
Cc: Liam Howlett 
Cc: Paolo Bonzini 
Link: https://lore.kernel.org/r/20231024222353.3024098-10-irogers@google.com
Signed-off-by: Namhyung Kim

perf callchain: Use pthread keys for tls callchain_cursor

2023-06-12T18:57:54+00:00

Pthread keys are more portable than __thread and allow the association
of a destructor with the key. Use the destructor to clean up TLS
callchain cursors to aid understanding memory leaks.

Committer notes:

Had to fixup a series of unconverted places and also check for the
return of get_tls_callchain_cursor() as it may fail and return NULL.

In that unlikely case we now either print something to a file, if the
caller was expecting to print a callchain, or return an error code to
state that resolving the callchain isn't possible.

In some cases this was made easier because thread__resolve_callchain()
already can fail for other reasons, so this new one (cursor == NULL) can
be added and the callers don't have to explicitely check for this new
condition.

Signed-off-by: Ian Rogers 
Cc: Adrian Hunter 
Cc: Alexander Shishkin 
Cc: Ali Saidi 
Cc: Andi Kleen 
Cc: Athira Rajeev 
Cc: Brian Robbins 
Cc: Changbin Du 
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: Fangrui Song 
Cc: German Gomez 
Cc: Ingo Molnar 
Cc: Ivan Babrou 
Cc: James Clark 
Cc: Jing Zhang 
Cc: Jiri Olsa 
Cc: John Garry 
Cc: K Prateek Nayak 
Cc: Kan Liang 
Cc: Leo Yan 
Cc: Liam Howlett 
Cc: Mark Rutland 
Cc: Miguel Ojeda 
Cc: Mike Leach 
Cc: Namhyung Kim 
Cc: Naveen N. Rao 
Cc: Peter Zijlstra 
Cc: Ravi Bangoria 
Cc: Sean Christopherson 
Cc: Steinar H. Gunderson 
Cc: Suzuki Poulouse 
Cc: Wenyu Liu 
Cc: Will Deacon 
Cc: Yang Jihong 
Cc: Ye Xingchen 
Cc: Yuan Can 
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20230608232823.4027869-25-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo

perf callchain: Enable dwarf_callchain_users on arm64

2021-12-21T21:35:44+00:00

Enable dwarf_callchain_users on arm64 which will be needed to do a
DWARF unwind in order to get the caller of the leaf frame.

Reviewed-by: James Clark 
Signed-off-by: Alexandre Truong 
Acked-by: Jiri Olsa 
Cc: Alexander Shishkin 
Cc: John Garry 
Cc: Leo Yan 
Cc: Mark Rutland 
Cc: Mathieu Poirier 
Cc: Namhyung Kim 
Cc: Will Deacon 
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20211217154521.80603-5-german.gomez@arm.com
Signed-off-by: German Gomez 
Signed-off-by: Arnaldo Carvalho de Melo

perf tools: Record ARM64 LR register automatically

2021-12-21T21:35:23+00:00

On ARM64, automatically record the link register if the frame pointer
mode is on. It will be used to do a dwarf unwind to find the caller of
the leaf frame if the frame pointer was omitted.

Reviewed-by: James Clark 
Signed-off-by: Alexandre Truong 
Acked-by: Jiri Olsa 
Cc: Alexander Shishkin 
Cc: John Garry 
Cc: Leo Yan 
Cc: Mark Rutland 
Cc: Mathieu Poirier 
Cc: Namhyung Kim 
Cc: Will Deacon 
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20211217154521.80603-2-german.gomez@arm.com
Signed-off-by: German Gomez 
Signed-off-by: Arnaldo Carvalho de Melo

perf streams: Report hot streams

2020-10-14T16:34:26+00:00

We show the streams separately. They are divided into different sections.

1. "Matched hot streams"

2. "Hot streams in old perf data only"

3. "Hot streams in new perf data only".

For each stream, we report the cycles and hot percent (hits%).

For example,

     cycles: 2, hits: 4.08%
 --------------------------
              main div.c:42
      compute_flag div.c:28

Signed-off-by: Jin Yao 
Acked-by: Jiri Olsa 
Link: https://lore.kernel.org/r/20201009022845.13141-7-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo

perf streams: Calculate the sum of total streams hits

2020-10-14T16:34:06+00:00

We have used callchain_node->hit to measure the hot level of one stream.
This patch calculates the sum of hits of total streams.

Thus in next patch, we can use following formula to report hot percent
for one stream.

hot percent = callchain_node->hit / sum of total hits

Signed-off-by: Jin Yao 
Acked-by: Jiri Olsa 
Link: https://lore.kernel.org/r/20201009022845.13141-6-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo

perf streams: Compare two streams

2020-10-14T16:31:56+00:00

Stream is the branch history which is aggregated by the branch records
from perf samples. Now we support the callchain as stream.

If the callchain entries of one stream are fully matched with the
callchain entries of another stream, we think two streams are matched.

For example,

   cycles: 1, hits: 26.80%                 cycles: 1, hits: 27.30%
   -----------------------                 -----------------------
             main div.c:39                           main div.c:39
             main div.c:44                           main div.c:44

Above two streams are matched (we don't consider the case that source
code is changed).

The matching logic is, compare the chain string first. If it's not
matched, fallback to dso address comparison.

Signed-off-by: Jin Yao 
Acked-by: Jiri Olsa 
Link: https://lore.kernel.org/r/20201009022845.13141-4-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo

perf callchain: Setup callchain properly in pipe mode

2020-05-28T13:03:25+00:00

Callchains are automatically initialized by checking on event's
sample_type. For pipe mode we need to put this check into attr event
code.

Moving the callchains setup code into callchain_param_setup function and
calling it from attr event process code.

This enables pipe output having callchains, like:

  # perf record -g -e 'raw_syscalls:sys_enter' true | perf script
  # perf record -g -e 'raw_syscalls:sys_enter' true | perf report

Committer notes:

We still need the next patch for the above output to work.

Reported-by: Paul Khuong 
Signed-off-by: Jiri Olsa 
Tested-by: Arnaldo Carvalho de Melo 
Cc: Alexander Shishkin 
Cc: Ian Rogers 
Cc: Michael Petlan 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Link: http://lore.kernel.org/lkml/20200507095024.2789147-5-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo

perf callchain: Stitch LBR call stack

2020-04-18T12:05:01+00:00

In LBR call stack mode, the depth of reconstructed LBR call stack limits
to the number of LBR registers.

  For example, on skylake, the depth of reconstructed LBR call stack is
  always <= 32.

  # To display the perf.data header info, please use
  # --header/--header-only options.
  #
  #
  # Total Lost Samples: 0
  #
  # Samples: 6K of event 'cycles'
  # Event count (approx.): 6487119731
  #
  # Children      Self  Command          Shared Object       Symbol
  # ........  ........  ...............  ..................
  # ................................

    99.97%    99.97%  tchain_edit      tchain_edit        [.] f43
            |
             --99.64%--f11
                       f12
                       f13
                       f14
                       f15
                       f16
                       f17
                       f18
                       f19
                       f20
                       f21
                       f22
                       f23
                       f24
                       f25
                       f26
                       f27
                       f28
                       f29
                       f30
                       f31
                       f32
                       f33
                       f34
                       f35
                       f36
                       f37
                       f38
                       f39
                       f40
                       f41
                       f42
                       f43

For a call stack which is deeper than LBR limit, HW will overwrite the
LBR register with oldest branch. Only partial call stacks can be
reconstructed.

However, the overwritten LBRs may still be retrieved from previous
sample. At that moment, HW hasn't overwritten the LBR registers yet.
Perf tools can stitch those overwritten LBRs on current call stacks to
get a more complete call stack.

To determine if LBRs can be stitched, perf tools need to compare current
sample with previous sample.

- They should have identical LBR records (Same from, to and flags
  values, and the same physical index of LBR registers).

- The searching starts from the base-of-stack of current sample.

Once perf determines to stitch the previous LBRs, the corresponding LBR
cursor nodes will be copied to 'lists'.  The 'lists' is to track the LBR
cursor nodes which are going to be stitched.

When the stitching is over, the nodes will not be freed immediately.
They will be moved to 'free_lists'. Next stitching may reuse the space.
Both 'lists' and 'free_lists' will be freed when all samples are
processed.

Committer notes:

Fix the intel-pt.c initialization of the union with 'struct
branch_flags', that breaks the build with its unnamed union on older gcc
versions.

Uninline thread__free_stitch_list(), as it grew big and started dragging
includes to thread.h, so move it to thread.c where what it needs in
terms of headers are already there.

This fixes the build in several systems such as debian:experimental when
cross building to the MIPS32 architecture, i.e. in the other cases what
was needed was being included by sheer luck.

  In file included from builtin-sched.c:11:
  util/thread.h: In function 'thread__free_stitch_list':
  util/thread.h:169:3: error: implicit declaration of function 'free' [-Werror=implicit-function-declaration]
    169 |   free(pos);
        |   ^~~~
  util/thread.h:169:3: error: incompatible implicit declaration of built-in function 'free' [-Werror]
  util/thread.h:19:1: note: include '' or provide a declaration of 'free'
     18 | #include "callchain.h"
    +++ |+#include 
     19 |
  util/thread.h:174:3: error: incompatible implicit declaration of built-in function 'free' [-Werror]
    174 |   free(pos);
        |   ^~~~
  util/thread.h:174:3: note: include '' or provide a declaration of 'free'

Signed-off-by: Kan Liang 
Reviewed-by: Andi Kleen 
Acked-by: Jiri Olsa 
Cc: Adrian Hunter 
Cc: Alexey Budankov 
Cc: Mathieu Poirier 
Cc: Michael Ellerman 
Cc: Namhyung Kim 
Cc: Pavel Gerasimov 
Cc: Peter Zijlstra 
Cc: Ravi Bangoria 
Cc: Stephane Eranian 
Cc: Vitaly Slobodskoy 
Link: http://lore.kernel.org/lkml/20200319202517.23423-13-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo