| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
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 <irogers@google.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: James Clark <james.clark@arm.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: liuwenyu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Song Liu <song@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Yanteng Si <siyanteng@loongson.cn>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Link: https://lore.kernel.org/r/20231024222353.3024098-11-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
|
|
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 <irogers@google.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: James Clark <james.clark@arm.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: liuwenyu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Song Liu <song@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Yanteng Si <siyanteng@loongson.cn>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Link: https://lore.kernel.org/r/20231024222353.3024098-10-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
|
|
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 <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ali Saidi <alisaidi@amazon.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Brian Robbins <brianrob@linux.microsoft.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: Fangrui Song <maskray@google.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Ivan Babrou <ivan@cloudflare.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: Ye Xingchen <ye.xingchen@zte.com.cn>
Cc: Yuan Can <yuancan@huawei.com>
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 <acme@redhat.com>
|
|
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 <james.clark@arm.com>
Signed-off-by: Alexandre Truong <alexandre.truong@arm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Will Deacon <will@kernel.org>
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 <german.gomez@arm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
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 <james.clark@arm.com>
Signed-off-by: Alexandre Truong <alexandre.truong@arm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Will Deacon <will@kernel.org>
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 <german.gomez@arm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
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 <yao.jin@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20201009022845.13141-7-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
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 <yao.jin@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20201009022845.13141-6-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
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 <yao.jin@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20201009022845.13141-4-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
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 <pvk@pvk.ca>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20200507095024.2789147-5-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
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 '<stdlib.h>' or provide a declaration of 'free'
18 | #include "callchain.h"
+++ |+#include <stdlib.h>
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 '<stdlib.h>' or provide a declaration of 'free'
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Pavel Gerasimov <pavel.gerasimov@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Vitaly Slobodskoy <vitaly.slobodskoy@intel.com>
Link: http://lore.kernel.org/lkml/20200319202517.23423-13-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
The cursor nodes which generates from sample are eventually added into
callchain. To avoid generating cursor nodes from previous samples again,
the previous cursor nodes are also saved for LBR stitching approach.
Some option, e.g. hide-unresolved, may hide some LBRs. Add a variable
'valid' in struct callchain_cursor_node to indicate this case. The LBR
stitching approach will only append the valid cursor nodes from previous
samples later.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Pavel Gerasimov <pavel.gerasimov@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Vitaly Slobodskoy <vitaly.slobodskoy@intel.com>
Link: http://lore.kernel.org/lkml/20200319202517.23423-12-kan.liang@linux.intel.com
[ Use zfree() instead of open coded equivalent, and use it when freeing members of structs ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
To ease passing around map+symbol, just like done for other parts of the
tree recently.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
All we need is a bunch of struct forward declarations and then add
event.h to the only place that was getting it indirectly via
callchain.h.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-qq2xhyuxcvx5vmxha9otjd8d@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
bpf.h and build-id.h are not needed at all in event.h, remove them.
And fixup the fallout of files that were getting needed stuff from this
now pruned include.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-rdm3dgtlrndmmnlc4bafsg3b@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Rename struct perf_evsel to struct evsel, so we don't have a name clash
when we add struct perf_evsel in libperf.
Committer notes:
Added fixes for arm64, provided by Jiri.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20190721112506.12306-5-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
To allow headers just wanting this definition to be able to get it
without all the things in symbol.h, to reduce the include dep tree.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-l32z2qyhs6fe8unf4gk2ead2@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
That was the only thing that made including map.h in callchain.h a
requiriment, so uninline it and just add a 'struct map' forward
declaration.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-7fjz4hvv1bpzqaeriku44fn4@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
So ditch it.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-bodhwdvcds9ahk26dy4w8m71@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
By calculating the removed loops, we can get the iteration count.
But the iteration count could be reported incorrectly, reporting
impossibly high counts.
That's because previous code uses the number of removed LBR entries for
the iteration count. That's not good. Fix this by increasing the
iteration count when a loop is detected.
When matching the chain, the iteration count would be added up, finally we need
to compute the average value when printing out.
For example,
$ perf report --branch-history --stdio --no-children
Before:
---f2 +0
|
|--33.62%--f1 +9 (cycles:1)
| f1 +0
| main +22 (cycles:1)
| main +17
| main +38 (cycles:1)
| main +27
| f1 +26 (cycles:1)
| f1 +24
| f2 +27 (cycles:7)
| f2 +0
| f1 +19 (cycles:1)
| f1 +14
| f2 +27 (cycles:11)
| f2 +0
| f1 +9 (cycles:1 iter:2968 avg_cycles:3)
| f1 +0
| main +22 (cycles:1 iter:2968 avg_cycles:3)
| main +17
| main +38 (cycles:1 iter:2968 avg_cycles:3)
2968 is an impossible high iteration count and avg_cycles is too small.
After:
---f2 +0
|
|--33.62%--f1 +9 (cycles:1)
| f1 +0
| main +22 (cycles:1)
| main +17
| main +38 (cycles:1)
| main +27
| f1 +26 (cycles:1)
| f1 +24
| f2 +27 (cycles:7)
| f2 +0
| f1 +19 (cycles:1)
| f1 +14
| f2 +27 (cycles:11)
| f2 +0
| f1 +9 (cycles:1 iter:1 avg_cycles:23)
| f1 +0
| main +22 (cycles:1 iter:1 avg_cycles:23)
| main +17
| main +38 (cycles:1 iter:1 avg_cycles:23)
avg_cycles:23 is the average cycles of this iteration.
Fixes: c4ee06251d42 ("perf report: Calculate the average cycles of iterations")
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1546582230-17507-1-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
When setting up DWARF callchains on specific events, without using
'record' or 'trace' --call-graph, but instead doing it like:
perf trace -e cycles/call-graph=dwarf/
The unwind__prepare_access() call in thread__insert_map() when we
process PERF_RECORD_MMAP(2) metadata events were not being performed,
precluding us from using per-event DWARF callchains, handling them just
when we asked for all events to be DWARF, using "--call-graph dwarf".
We do it in the PERF_RECORD_MMAP because we have to look at one of the
executable maps to figure out the executable type (64-bit, 32-bit) of
the DSO laid out in that mmap. Also to look at the architecture where
the perf.data file was recorded.
All this probably should be deferred to when we process a sample for
some thread that has callchains, so that we do this processing only for
the threads with samples, not for all of them.
For now, fix using DWARF on specific events.
Before:
# perf trace --no-syscalls -e probe_libc:inet_pton/call-graph=dwarf/ ping -6 -c 1 ::1
PING ::1(::1) 56 data bytes
64 bytes from ::1: icmp_seq=1 ttl=64 time=0.048 ms
--- ::1 ping statistics ---
1 packets transmitted, 1 received, 0% packet loss, time 0ms
rtt min/avg/max/mdev = 0.048/0.048/0.048/0.000 ms
0.000 probe_libc:inet_pton:(7fe9597bb350))
Problem processing probe_libc:inet_pton callchain, skipping...
#
After:
# perf trace --no-syscalls -e probe_libc:inet_pton/call-graph=dwarf/ ping -6 -c 1 ::1
PING ::1(::1) 56 data bytes
64 bytes from ::1: icmp_seq=1 ttl=64 time=0.060 ms
--- ::1 ping statistics ---
1 packets transmitted, 1 received, 0% packet loss, time 0ms
rtt min/avg/max/mdev = 0.060/0.060/0.060/0.000 ms
0.000 probe_libc:inet_pton:(7fd4aa930350))
__inet_pton (inlined)
gaih_inet.constprop.7 (/usr/lib64/libc-2.26.so)
__GI_getaddrinfo (inlined)
[0xffffaa804e51af3f] (/usr/bin/ping)
__libc_start_main (/usr/lib64/libc-2.26.so)
[0xffffaa804e51b379] (/usr/bin/ping)
#
# perf trace --call-graph=dwarf --no-syscalls -e probe_libc:inet_pton/call-graph=dwarf/ ping -6 -c 1 ::1
PING ::1(::1) 56 data bytes
64 bytes from ::1: icmp_seq=1 ttl=64 time=0.057 ms
--- ::1 ping statistics ---
1 packets transmitted, 1 received, 0% packet loss, time 0ms
rtt min/avg/max/mdev = 0.057/0.057/0.057/0.000 ms
0.000 probe_libc:inet_pton:(7f9363b9e350))
__inet_pton (inlined)
gaih_inet.constprop.7 (/usr/lib64/libc-2.26.so)
__GI_getaddrinfo (inlined)
[0xffffa9e8a14e0f3f] (/usr/bin/ping)
__libc_start_main (/usr/lib64/libc-2.26.so)
[0xffffa9e8a14e1379] (/usr/bin/ping)
#
# perf trace --call-graph=fp --no-syscalls -e probe_libc:inet_pton/call-graph=dwarf/ ping -6 -c 1 ::1
PING ::1(::1) 56 data bytes
64 bytes from ::1: icmp_seq=1 ttl=64 time=0.077 ms
--- ::1 ping statistics ---
1 packets transmitted, 1 received, 0% packet loss, time 0ms
rtt min/avg/max/mdev = 0.077/0.077/0.077/0.000 ms
0.000 probe_libc:inet_pton:(7f4947e1c350))
__inet_pton (inlined)
gaih_inet.constprop.7 (/usr/lib64/libc-2.26.so)
__GI_getaddrinfo (inlined)
[0xffffaa716d88ef3f] (/usr/bin/ping)
__libc_start_main (/usr/lib64/libc-2.26.so)
[0xffffaa716d88f379] (/usr/bin/ping)
#
# perf trace --no-syscalls -e probe_libc:inet_pton/call-graph=fp/ ping -6 -c 1 ::1
PING ::1(::1) 56 data bytes
64 bytes from ::1: icmp_seq=1 ttl=64 time=0.078 ms
--- ::1 ping statistics ---
1 packets transmitted, 1 received, 0% packet loss, time 0ms
rtt min/avg/max/mdev = 0.078/0.078/0.078/0.000 ms
0.000 probe_libc:inet_pton:(7fa157696350))
__GI___inet_pton (/usr/lib64/libc-2.26.so)
getaddrinfo (/usr/lib64/libc-2.26.so)
[0xffffa9ba39c74f40] (/usr/bin/ping)
#
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Hendrick Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/r/20180116182650.GE16107@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Conflicts:
tools/perf/arch/arm/annotate/instructions.c
tools/perf/arch/arm64/annotate/instructions.c
tools/perf/arch/powerpc/annotate/instructions.c
tools/perf/arch/s390/annotate/instructions.c
tools/perf/arch/x86/tests/intel-cqm.c
tools/perf/ui/tui/progress.c
tools/perf/util/zlib.c
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
|
Many source files in the tree are missing licensing information, which
makes it harder for compliance tools to determine the correct license.
By default all files without license information are under the default
license of the kernel, which is GPL version 2.
Update the files which contain no license information with the 'GPL-2.0'
SPDX license identifier. The SPDX identifier is a legally binding
shorthand, which can be used instead of the full boiler plate text.
This patch is based on work done by Thomas Gleixner and Kate Stewart and
Philippe Ombredanne.
How this work was done:
Patches were generated and checked against linux-4.14-rc6 for a subset of
the use cases:
- file had no licensing information it it.
- file was a */uapi/* one with no licensing information in it,
- file was a */uapi/* one with existing licensing information,
Further patches will be generated in subsequent months to fix up cases
where non-standard license headers were used, and references to license
had to be inferred by heuristics based on keywords.
The analysis to determine which SPDX License Identifier to be applied to
a file was done in a spreadsheet of side by side results from of the
output of two independent scanners (ScanCode & Windriver) producing SPDX
tag:value files created by Philippe Ombredanne. Philippe prepared the
base worksheet, and did an initial spot review of a few 1000 files.
The 4.13 kernel was the starting point of the analysis with 60,537 files
assessed. Kate Stewart did a file by file comparison of the scanner
results in the spreadsheet to determine which SPDX license identifier(s)
to be applied to the file. She confirmed any determination that was not
immediately clear with lawyers working with the Linux Foundation.
Criteria used to select files for SPDX license identifier tagging was:
- Files considered eligible had to be source code files.
- Make and config files were included as candidates if they contained >5
lines of source
- File already had some variant of a license header in it (even if <5
lines).
All documentation files were explicitly excluded.
The following heuristics were used to determine which SPDX license
identifiers to apply.
- when both scanners couldn't find any license traces, file was
considered to have no license information in it, and the top level
COPYING file license applied.
For non */uapi/* files that summary was:
SPDX license identifier # files
---------------------------------------------------|-------
GPL-2.0 11139
and resulted in the first patch in this series.
If that file was a */uapi/* path one, it was "GPL-2.0 WITH
Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was:
SPDX license identifier # files
---------------------------------------------------|-------
GPL-2.0 WITH Linux-syscall-note 930
and resulted in the second patch in this series.
- if a file had some form of licensing information in it, and was one
of the */uapi/* ones, it was denoted with the Linux-syscall-note if
any GPL family license was found in the file or had no licensing in
it (per prior point). Results summary:
SPDX license identifier # files
---------------------------------------------------|------
GPL-2.0 WITH Linux-syscall-note 270
GPL-2.0+ WITH Linux-syscall-note 169
((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21
((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17
LGPL-2.1+ WITH Linux-syscall-note 15
GPL-1.0+ WITH Linux-syscall-note 14
((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5
LGPL-2.0+ WITH Linux-syscall-note 4
LGPL-2.1 WITH Linux-syscall-note 3
((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3
((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1
and that resulted in the third patch in this series.
- when the two scanners agreed on the detected license(s), that became
the concluded license(s).
- when there was disagreement between the two scanners (one detected a
license but the other didn't, or they both detected different
licenses) a manual inspection of the file occurred.
- In most cases a manual inspection of the information in the file
resulted in a clear resolution of the license that should apply (and
which scanner probably needed to revisit its heuristics).
- When it was not immediately clear, the license identifier was
confirmed with lawyers working with the Linux Foundation.
- If there was any question as to the appropriate license identifier,
the file was flagged for further research and to be revisited later
in time.
In total, over 70 hours of logged manual review was done on the
spreadsheet to determine the SPDX license identifiers to apply to the
source files by Kate, Philippe, Thomas and, in some cases, confirmation
by lawyers working with the Linux Foundation.
Kate also obtained a third independent scan of the 4.13 code base from
FOSSology, and compared selected files where the other two scanners
disagreed against that SPDX file, to see if there was new insights. The
Windriver scanner is based on an older version of FOSSology in part, so
they are related.
Thomas did random spot checks in about 500 files from the spreadsheets
for the uapi headers and agreed with SPDX license identifier in the
files he inspected. For the non-uapi files Thomas did random spot checks
in about 15000 files.
In initial set of patches against 4.14-rc6, 3 files were found to have
copy/paste license identifier errors, and have been fixed to reflect the
correct identifier.
Additionally Philippe spent 10 hours this week doing a detailed manual
inspection and review of the 12,461 patched files from the initial patch
version early this week with:
- a full scancode scan run, collecting the matched texts, detected
license ids and scores
- reviewing anything where there was a license detected (about 500+
files) to ensure that the applied SPDX license was correct
- reviewing anything where there was no detection but the patch license
was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied
SPDX license was correct
This produced a worksheet with 20 files needing minor correction. This
worksheet was then exported into 3 different .csv files for the
different types of files to be modified.
These .csv files were then reviewed by Greg. Thomas wrote a script to
parse the csv files and add the proper SPDX tag to the file, in the
format that the file expected. This script was further refined by Greg
based on the output to detect more types of files automatically and to
distinguish between header and source .c files (which need different
comment types.) Finally Greg ran the script using the .csv files to
generate the patches.
Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org>
Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
This is mostly a preparation to enable the creation of full callchain
nodes for inline frames. Such frames will reference the IP of the
non-inlined frame, but hold the symbol and srcline for an inlined
location. As such, we won't be able to query the srcline on-demand based
on the IP alone. Instead, we will leverage the functionality provided by
this patch here, and store the srcline for the inlined nodes in the new
srcline member of callchain_cursor_node.
Note that this patch on its own leaks the srcline, as there is no
free_callchain_cursor_node or similar. A future patch will add caching
of the srcline and handle deletion properly.
Signed-off-by: Milian Wolff <milian.wolff@kdab.com>
Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Yao Jin <yao.jin@linux.intel.com>
Link: http://lkml.kernel.org/r/20171009203310.17362-3-milian.wolff@kdab.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
The branch history code has a loop detection function. With this, we can
get the number of iterations by calculating the removed loops.
While it would be nice for knowing the average cycles of iterations.
This patch adds up the cycles in branch entries of removed loops and
save the result to the next branch entry (e.g. branch entry A).
Finally it will display the iteration number and average cycles at the
"from" of branch entry A.
For example:
perf record -g -j any,save_type ./div
perf report --branch-history --no-children --stdio
--22.63%--main div.c:42 (RET CROSS_2M)
compute_flag div.c:28 (cycles:2 iter:173115 avg_cycles:2)
|
--10.73%--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)
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/1502111115-18305-1-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
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>
|
|
Often it is interesting to know how costly a given source line is in
total. Previously, one had to build these sums manually based on all
addresses that pointed to the same source line. This patch introduces
srcline as a sort key, which will do the aggregation for us.
Paired with the recent addition of showing inline frames, this makes
perf report much more useful for many C++ work loads.
The following shows the new feature in action. First, let's show the
status quo output when we sort by address. The result contains many hist
entries that generate the same output:
~~~~~~~~~~~~~~~~
$ perf report --stdio --inline -g address
# Children Self Command Shared Object Symbol
# ........ ........ ............ ................... .........................................
#
99.89% 35.34% cpp-inlining cpp-inlining [.] main
|
|--64.55%--main complex:655
| /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline)
| /usr/include/c++/6.3.1/complex:664 (inline)
| |
| |--60.31%--hypot +20
| | |
| | |--8.52%--__hypot_finite +273
| | |
| | |--7.32%--__hypot_finite +411
...
--35.34%--_start +4194346
__libc_start_main +241
|
|--6.65%--main random.tcc:3326
| /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline)
| /usr/include/c++/6.3.1/bits/random.h:1809 (inline)
| /usr/include/c++/6.3.1/bits/random.h:1818 (inline)
| /usr/include/c++/6.3.1/bits/random.h:185 (inline)
|
|--2.70%--main random.tcc:3326
| /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline)
| /usr/include/c++/6.3.1/bits/random.h:1809 (inline)
| /usr/include/c++/6.3.1/bits/random.h:1818 (inline)
| /usr/include/c++/6.3.1/bits/random.h:185 (inline)
|
|--1.69%--main random.tcc:3326
| /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline)
| /usr/include/c++/6.3.1/bits/random.h:1809 (inline)
| /usr/include/c++/6.3.1/bits/random.h:1818 (inline)
| /usr/include/c++/6.3.1/bits/random.h:185 (inline)
...
~~~~~~~~~~~~~~~~
With this patch and `-g srcline` we instead get the following output:
~~~~~~~~~~~~~~~~
$ perf report --stdio --inline -g srcline
# Children Self Command Shared Object Symbol
# ........ ........ ............ ................... .........................................
#
99.89% 35.34% cpp-inlining cpp-inlining [.] main
|
|--64.55%--main complex:655
| /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline)
| /usr/include/c++/6.3.1/complex:664 (inline)
| |
| |
