License cleanup: add SPDX GPL-2.0 license identifier to files with no license
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>
2017-11-01 22:07:57 +08:00
|
|
|
// SPDX-License-Identifier: GPL-2.0
|
2017-04-18 23:26:44 +08:00
|
|
|
#include <dirent.h>
|
2017-04-18 21:46:11 +08:00
|
|
|
#include <errno.h>
|
2017-09-11 21:50:26 +08:00
|
|
|
#include <fcntl.h>
|
2017-04-18 02:23:08 +08:00
|
|
|
#include <inttypes.h>
|
2017-04-17 22:39:06 +08:00
|
|
|
#include <linux/kernel.h>
|
2009-10-27 05:23:18 +08:00
|
|
|
#include <linux/types.h>
|
2017-04-20 07:57:47 +08:00
|
|
|
#include <sys/types.h>
|
|
|
|
#include <sys/stat.h>
|
|
|
|
#include <unistd.h>
|
2017-04-12 14:49:19 +08:00
|
|
|
#include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */
|
2016-09-06 12:58:29 +08:00
|
|
|
#include <api/fs/fs.h>
|
2017-04-26 02:30:47 +08:00
|
|
|
#include <linux/perf_event.h>
|
2019-07-04 22:32:27 +08:00
|
|
|
#include <linux/zalloc.h>
|
2009-10-27 05:23:18 +08:00
|
|
|
#include "event.h"
|
|
|
|
#include "debug.h"
|
2014-03-18 03:59:21 +08:00
|
|
|
#include "hist.h"
|
2012-10-07 02:44:59 +08:00
|
|
|
#include "machine.h"
|
2009-12-16 06:04:41 +08:00
|
|
|
#include "sort.h"
|
2017-04-18 03:51:59 +08:00
|
|
|
#include "string2.h"
|
2009-12-16 06:04:41 +08:00
|
|
|
#include "strlist.h"
|
2009-11-28 02:29:22 +08:00
|
|
|
#include "thread.h"
|
2011-02-11 21:45:54 +08:00
|
|
|
#include "thread_map.h"
|
tools perf: Move from sane_ctype.h obtained from git to the Linux's original
We got the sane_ctype.h headers from git and kept using it so far, but
since that code originally came from the kernel sources to the git
sources, perhaps its better to just use the one in the kernel, so that
we can leverage tools/perf/check_headers.sh to be notified when our copy
gets out of sync, i.e. when fixes or goodies are added to the code we've
copied.
This will help with things like tools/lib/string.c where we want to have
more things in common with the kernel, such as strim(), skip_spaces(),
etc so as to go on removing the things that we have in tools/perf/util/
and instead using the code in the kernel, indirectly and removing things
like EXPORT_SYMBOL(), etc, getting notified when fixes and improvements
are made to the original code.
Hopefully this also should help with reducing the difference of code
hosted in tools/ to the one in the kernel proper.
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-7k9868l713wqtgo01xxygn12@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-26 04:27:31 +08:00
|
|
|
#include <linux/ctype.h>
|
2019-01-27 20:42:37 +08:00
|
|
|
#include "map.h"
|
2019-01-28 07:03:34 +08:00
|
|
|
#include "symbol.h"
|
2013-12-11 20:15:00 +08:00
|
|
|
#include "symbol/kallsyms.h"
|
2015-10-25 22:51:28 +08:00
|
|
|
#include "asm/bug.h"
|
|
|
|
#include "stat.h"
|
2019-01-18 00:15:17 +08:00
|
|
|
#include "session.h"
|
perf tools: Handle PERF_RECORD_BPF_EVENT
This patch adds basic handling of PERF_RECORD_BPF_EVENT. Tracking of
PERF_RECORD_BPF_EVENT is OFF by default. Option --bpf-event is added to
turn it on.
Committer notes:
Add dummy machine__process_bpf_event() variant that returns zero for
systems without HAVE_LIBBPF_SUPPORT, such as Alpine Linux, unbreaking
the build in such systems.
Remove the needless include <machine.h> from bpf->event.h, provide just
forward declarations for the structs and unions in the parameters, to
reduce compilation time and needless rebuilds when machine.h gets
changed.
Committer testing:
When running with:
# perf record --bpf-event
On an older kernel where PERF_RECORD_BPF_EVENT and PERF_RECORD_KSYMBOL
is not present, we fallback to removing those two bits from
perf_event_attr, making the tool to continue to work on older kernels:
perf_event_attr:
size 112
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|PERIOD
read_format ID
disabled 1
inherit 1
mmap 1
comm 1
freq 1
enable_on_exec 1
task 1
precise_ip 3
sample_id_all 1
exclude_guest 1
mmap2 1
comm_exec 1
ksymbol 1
bpf_event 1
------------------------------------------------------------
sys_perf_event_open: pid 5779 cpu 0 group_fd -1 flags 0x8
sys_perf_event_open failed, error -22
switching off bpf_event
------------------------------------------------------------
perf_event_attr:
size 112
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|PERIOD
read_format ID
disabled 1
inherit 1
mmap 1
comm 1
freq 1
enable_on_exec 1
task 1
precise_ip 3
sample_id_all 1
exclude_guest 1
mmap2 1
comm_exec 1
ksymbol 1
------------------------------------------------------------
sys_perf_event_open: pid 5779 cpu 0 group_fd -1 flags 0x8
sys_perf_event_open failed, error -22
switching off ksymbol
------------------------------------------------------------
perf_event_attr:
size 112
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|PERIOD
read_format ID
disabled 1
inherit 1
mmap 1
comm 1
freq 1
enable_on_exec 1
task 1
precise_ip 3
sample_id_all 1
exclude_guest 1
mmap2 1
comm_exec 1
------------------------------------------------------------
And then proceeds to work without those two features.
As passing --bpf-event is an explicit action performed by the user, perhaps we
should emit a warning telling that the kernel has no such feature, but this can
be done on top of this patch.
Now with a kernel that supports these events, start the 'record --bpf-event -a'
and then run 'perf trace sleep 10000' that will use the BPF
augmented_raw_syscalls.o prebuilt (for another kernel version even) and thus
should generate PERF_RECORD_BPF_EVENT events:
[root@quaco ~]# perf record -e dummy -a --bpf-event
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.713 MB perf.data ]
[root@quaco ~]# bpftool prog
13: cgroup_skb tag 7be49e3934a125ba gpl
loaded_at 2019-01-19T09:09:43-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 13,14
14: cgroup_skb tag 2a142ef67aaad174 gpl
loaded_at 2019-01-19T09:09:43-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 13,14
15: cgroup_skb tag 7be49e3934a125ba gpl
loaded_at 2019-01-19T09:09:43-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 15,16
16: cgroup_skb tag 2a142ef67aaad174 gpl
loaded_at 2019-01-19T09:09:43-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 15,16
17: cgroup_skb tag 7be49e3934a125ba gpl
loaded_at 2019-01-19T09:09:44-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 17,18
18: cgroup_skb tag 2a142ef67aaad174 gpl
loaded_at 2019-01-19T09:09:44-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 17,18
21: cgroup_skb tag 7be49e3934a125ba gpl
loaded_at 2019-01-19T09:09:45-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 21,22
22: cgroup_skb tag 2a142ef67aaad174 gpl
loaded_at 2019-01-19T09:09:45-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 21,22
31: tracepoint name sys_enter tag 12504ba9402f952f gpl
loaded_at 2019-01-19T09:19:56-0300 uid 0
xlated 512B jited 374B memlock 4096B map_ids 30,29,28
32: tracepoint name sys_exit tag c1bd85c092d6e4aa gpl
loaded_at 2019-01-19T09:19:56-0300 uid 0
xlated 256B jited 191B memlock 4096B map_ids 30,29
# perf report -D | grep PERF_RECORD_BPF_EVENT | nl
1 0 55834574849 0x4fc8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 13
2 0 60129542145 0x5118 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 14
3 0 64424509441 0x5268 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 15
4 0 68719476737 0x53b8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 16
5 0 73014444033 0x5508 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 17
6 0 77309411329 0x5658 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 18
7 0 90194313217 0x57a8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 21
8 0 94489280513 0x58f8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 22
9 7 620922484360 0xb6390 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 29
10 7 620922486018 0xb6410 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 2, flags 0, id 29
11 7 620922579199 0xb6490 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 30
12 7 620922580240 0xb6510 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 2, flags 0, id 30
13 7 620922765207 0xb6598 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 31
14 7 620922874543 0xb6620 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 32
#
There, the 31 and 32 tracepoint BPF programs put in place by 'perf trace'.
Signed-off-by: Song Liu <songliubraving@fb.com>
Reviewed-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: kernel-team@fb.com
Cc: netdev@vger.kernel.org
Link: http://lkml.kernel.org/r/20190117161521.1341602-7-songliubraving@fb.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-01-18 00:15:18 +08:00
|
|
|
#include "bpf-event.h"
|
2009-10-27 05:23:18 +08:00
|
|
|
|
2018-12-05 04:34:20 +08:00
|
|
|
#define DEFAULT_PROC_MAP_PARSE_TIMEOUT 500
|
|
|
|
|
2011-01-30 00:01:45 +08:00
|
|
|
static const char *perf_event__names[] = {
|
2011-05-23 19:06:27 +08:00
|
|
|
[0] = "TOTAL",
|
|
|
|
[PERF_RECORD_MMAP] = "MMAP",
|
2013-08-21 18:10:25 +08:00
|
|
|
[PERF_RECORD_MMAP2] = "MMAP2",
|
2011-05-23 19:06:27 +08:00
|
|
|
[PERF_RECORD_LOST] = "LOST",
|
|
|
|
[PERF_RECORD_COMM] = "COMM",
|
|
|
|
[PERF_RECORD_EXIT] = "EXIT",
|
|
|
|
[PERF_RECORD_THROTTLE] = "THROTTLE",
|
|
|
|
[PERF_RECORD_UNTHROTTLE] = "UNTHROTTLE",
|
|
|
|
[PERF_RECORD_FORK] = "FORK",
|
|
|
|
[PERF_RECORD_READ] = "READ",
|
|
|
|
[PERF_RECORD_SAMPLE] = "SAMPLE",
|
2015-04-30 22:37:29 +08:00
|
|
|
[PERF_RECORD_AUX] = "AUX",
|
2015-04-30 22:37:30 +08:00
|
|
|
[PERF_RECORD_ITRACE_START] = "ITRACE_START",
|
2015-05-11 03:13:15 +08:00
|
|
|
[PERF_RECORD_LOST_SAMPLES] = "LOST_SAMPLES",
|
2015-07-21 17:44:03 +08:00
|
|
|
[PERF_RECORD_SWITCH] = "SWITCH",
|
|
|
|
[PERF_RECORD_SWITCH_CPU_WIDE] = "SWITCH_CPU_WIDE",
|
perf tools: Add PERF_RECORD_NAMESPACES to include namespaces related info
Introduce a new option to record PERF_RECORD_NAMESPACES events emitted
by the kernel when fork, clone, setns or unshare are invoked. And update
perf-record documentation with the new option to record namespace
events.
Committer notes:
Combined it with a later patch to allow printing it via 'perf report -D'
and be able to test the feature introduced in this patch. Had to move
here also perf_ns__name(), that was introduced in another later patch.
Also used PRIu64 and PRIx64 to fix the build in some enfironments wrt:
util/event.c:1129:39: error: format '%lx' expects argument of type 'long unsigned int', but argument 6 has type 'long long unsigned int' [-Werror=format=]
ret += fprintf(fp, "%u/%s: %lu/0x%lx%s", idx
^
Testing it:
# perf record --namespaces -a
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 1.083 MB perf.data (423 samples) ]
#
# perf report -D
<SNIP>
3 2028902078892 0x115140 [0xa0]: PERF_RECORD_NAMESPACES 14783/14783 - nr_namespaces: 7
[0/net: 3/0xf0000081, 1/uts: 3/0xeffffffe, 2/ipc: 3/0xefffffff, 3/pid: 3/0xeffffffc,
4/user: 3/0xeffffffd, 5/mnt: 3/0xf0000000, 6/cgroup: 3/0xeffffffb]
0x1151e0 [0x30]: event: 9
.
. ... raw event: size 48 bytes
. 0000: 09 00 00 00 02 00 30 00 c4 71 82 68 0c 7f 00 00 ......0..q.h....
. 0010: a9 39 00 00 a9 39 00 00 94 28 fe 63 d8 01 00 00 .9...9...(.c....
. 0020: 03 00 00 00 00 00 00 00 ce c4 02 00 00 00 00 00 ................
<SNIP>
NAMESPACES events: 1
<SNIP>
#
Signed-off-by: Hari Bathini <hbathini@linux.vnet.ibm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@fb.com>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Aravinda Prasad <aravinda@linux.vnet.ibm.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sargun Dhillon <sargun@sargun.me>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/148891930386.25309.18412039920746995488.stgit@hbathini.in.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-08 04:41:43 +08:00
|
|
|
[PERF_RECORD_NAMESPACES] = "NAMESPACES",
|
2019-01-18 00:15:17 +08:00
|
|
|
[PERF_RECORD_KSYMBOL] = "KSYMBOL",
|
perf tools: Handle PERF_RECORD_BPF_EVENT
This patch adds basic handling of PERF_RECORD_BPF_EVENT. Tracking of
PERF_RECORD_BPF_EVENT is OFF by default. Option --bpf-event is added to
turn it on.
Committer notes:
Add dummy machine__process_bpf_event() variant that returns zero for
systems without HAVE_LIBBPF_SUPPORT, such as Alpine Linux, unbreaking
the build in such systems.
Remove the needless include <machine.h> from bpf->event.h, provide just
forward declarations for the structs and unions in the parameters, to
reduce compilation time and needless rebuilds when machine.h gets
changed.
Committer testing:
When running with:
# perf record --bpf-event
On an older kernel where PERF_RECORD_BPF_EVENT and PERF_RECORD_KSYMBOL
is not present, we fallback to removing those two bits from
perf_event_attr, making the tool to continue to work on older kernels:
perf_event_attr:
size 112
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|PERIOD
read_format ID
disabled 1
inherit 1
mmap 1
comm 1
freq 1
enable_on_exec 1
task 1
precise_ip 3
sample_id_all 1
exclude_guest 1
mmap2 1
comm_exec 1
ksymbol 1
bpf_event 1
------------------------------------------------------------
sys_perf_event_open: pid 5779 cpu 0 group_fd -1 flags 0x8
sys_perf_event_open failed, error -22
switching off bpf_event
------------------------------------------------------------
perf_event_attr:
size 112
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|PERIOD
read_format ID
disabled 1
inherit 1
mmap 1
comm 1
freq 1
enable_on_exec 1
task 1
precise_ip 3
sample_id_all 1
exclude_guest 1
mmap2 1
comm_exec 1
ksymbol 1
------------------------------------------------------------
sys_perf_event_open: pid 5779 cpu 0 group_fd -1 flags 0x8
sys_perf_event_open failed, error -22
switching off ksymbol
------------------------------------------------------------
perf_event_attr:
size 112
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|PERIOD
read_format ID
disabled 1
inherit 1
mmap 1
comm 1
freq 1
enable_on_exec 1
task 1
precise_ip 3
sample_id_all 1
exclude_guest 1
mmap2 1
comm_exec 1
------------------------------------------------------------
And then proceeds to work without those two features.
As passing --bpf-event is an explicit action performed by the user, perhaps we
should emit a warning telling that the kernel has no such feature, but this can
be done on top of this patch.
Now with a kernel that supports these events, start the 'record --bpf-event -a'
and then run 'perf trace sleep 10000' that will use the BPF
augmented_raw_syscalls.o prebuilt (for another kernel version even) and thus
should generate PERF_RECORD_BPF_EVENT events:
[root@quaco ~]# perf record -e dummy -a --bpf-event
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.713 MB perf.data ]
[root@quaco ~]# bpftool prog
13: cgroup_skb tag 7be49e3934a125ba gpl
loaded_at 2019-01-19T09:09:43-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 13,14
14: cgroup_skb tag 2a142ef67aaad174 gpl
loaded_at 2019-01-19T09:09:43-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 13,14
15: cgroup_skb tag 7be49e3934a125ba gpl
loaded_at 2019-01-19T09:09:43-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 15,16
16: cgroup_skb tag 2a142ef67aaad174 gpl
loaded_at 2019-01-19T09:09:43-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 15,16
17: cgroup_skb tag 7be49e3934a125ba gpl
loaded_at 2019-01-19T09:09:44-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 17,18
18: cgroup_skb tag 2a142ef67aaad174 gpl
loaded_at 2019-01-19T09:09:44-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 17,18
21: cgroup_skb tag 7be49e3934a125ba gpl
loaded_at 2019-01-19T09:09:45-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 21,22
22: cgroup_skb tag 2a142ef67aaad174 gpl
loaded_at 2019-01-19T09:09:45-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 21,22
31: tracepoint name sys_enter tag 12504ba9402f952f gpl
loaded_at 2019-01-19T09:19:56-0300 uid 0
xlated 512B jited 374B memlock 4096B map_ids 30,29,28
32: tracepoint name sys_exit tag c1bd85c092d6e4aa gpl
loaded_at 2019-01-19T09:19:56-0300 uid 0
xlated 256B jited 191B memlock 4096B map_ids 30,29
# perf report -D | grep PERF_RECORD_BPF_EVENT | nl
1 0 55834574849 0x4fc8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 13
2 0 60129542145 0x5118 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 14
3 0 64424509441 0x5268 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 15
4 0 68719476737 0x53b8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 16
5 0 73014444033 0x5508 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 17
6 0 77309411329 0x5658 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 18
7 0 90194313217 0x57a8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 21
8 0 94489280513 0x58f8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 22
9 7 620922484360 0xb6390 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 29
10 7 620922486018 0xb6410 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 2, flags 0, id 29
11 7 620922579199 0xb6490 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 30
12 7 620922580240 0xb6510 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 2, flags 0, id 30
13 7 620922765207 0xb6598 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 31
14 7 620922874543 0xb6620 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 32
#
There, the 31 and 32 tracepoint BPF programs put in place by 'perf trace'.
Signed-off-by: Song Liu <songliubraving@fb.com>
Reviewed-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: kernel-team@fb.com
Cc: netdev@vger.kernel.org
Link: http://lkml.kernel.org/r/20190117161521.1341602-7-songliubraving@fb.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-01-18 00:15:18 +08:00
|
|
|
[PERF_RECORD_BPF_EVENT] = "BPF_EVENT",
|
2011-05-23 19:06:27 +08:00
|
|
|
[PERF_RECORD_HEADER_ATTR] = "ATTR",
|
|
|
|
[PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE",
|
|
|
|
[PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA",
|
|
|
|
[PERF_RECORD_HEADER_BUILD_ID] = "BUILD_ID",
|
|
|
|
[PERF_RECORD_FINISHED_ROUND] = "FINISHED_ROUND",
|
2014-10-27 21:49:22 +08:00
|
|
|
[PERF_RECORD_ID_INDEX] = "ID_INDEX",
|
2015-04-09 23:53:43 +08:00
|
|
|
[PERF_RECORD_AUXTRACE_INFO] = "AUXTRACE_INFO",
|
|
|
|
[PERF_RECORD_AUXTRACE] = "AUXTRACE",
|
2015-04-09 23:53:47 +08:00
|
|
|
[PERF_RECORD_AUXTRACE_ERROR] = "AUXTRACE_ERROR",
|
2015-10-25 22:51:19 +08:00
|
|
|
[PERF_RECORD_THREAD_MAP] = "THREAD_MAP",
|
2015-10-25 22:51:23 +08:00
|
|
|
[PERF_RECORD_CPU_MAP] = "CPU_MAP",
|
2015-10-25 22:51:27 +08:00
|
|
|
[PERF_RECORD_STAT_CONFIG] = "STAT_CONFIG",
|
2015-10-25 22:51:30 +08:00
|
|
|
[PERF_RECORD_STAT] = "STAT",
|
2015-10-25 22:51:33 +08:00
|
|
|
[PERF_RECORD_STAT_ROUND] = "STAT_ROUND",
|
2015-10-25 22:51:36 +08:00
|
|
|
[PERF_RECORD_EVENT_UPDATE] = "EVENT_UPDATE",
|
2016-03-08 16:38:44 +08:00
|
|
|
[PERF_RECORD_TIME_CONV] = "TIME_CONV",
|
perf tools: Add feature header record to pipe-mode
Add header record types to pipe-mode, reusing the functions
used in file-mode and leveraging the new struct feat_fd.
For alignment, check that synthesized events don't exceed
pagesize.
Add the perf_event__synthesize_feature event call back to
process the new header records.
Before this patch:
$ perf record -o - -e cycles sleep 1 | perf report --stdio --header
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.000 MB - ]
...
After this patch:
$ perf record -o - -e cycles sleep 1 | perf report --stdio --header
# ========
# captured on: Mon May 22 16:33:43 2017
# ========
#
# hostname : my_hostname
# os release : 4.11.0-dbx-up_perf
# perf version : 4.11.rc6.g6277c80
# arch : x86_64
# nrcpus online : 72
# nrcpus avail : 72
# cpudesc : Intel(R) Xeon(R) CPU E5-2696 v3 @ 2.30GHz
# cpuid : GenuineIntel,6,63,2
# total memory : 263457192 kB
# cmdline : /root/perf record -o - -e cycles -c 100000 sleep 1
# HEADER_CPU_TOPOLOGY info available, use -I to display
# HEADER_NUMA_TOPOLOGY info available, use -I to display
# pmu mappings: intel_bts = 6, uncore_imc_4 = 22, uncore_sbox_1 = 47, uncore_cbox_5 = 33, uncore_ha_0 = 16, uncore_cbox
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.000 MB - ]
...
Support added for the subcommands: report, inject, annotate and script.
Signed-off-by: David Carrillo-Cisneros <davidcc@google.com>
Acked-by: David Ahern <dsahern@gmail.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Turner <pjt@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Simon Que <sque@chromium.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/20170718042549.145161-16-davidcc@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-07-18 12:25:48 +08:00
|
|
|
[PERF_RECORD_HEADER_FEATURE] = "FEATURE",
|
2019-03-19 01:41:33 +08:00
|
|
|
[PERF_RECORD_COMPRESSED] = "COMPRESSED",
|
2010-05-14 21:36:42 +08:00
|
|
|
};
|
|
|
|
|
perf tools: Add PERF_RECORD_NAMESPACES to include namespaces related info
Introduce a new option to record PERF_RECORD_NAMESPACES events emitted
by the kernel when fork, clone, setns or unshare are invoked. And update
perf-record documentation with the new option to record namespace
events.
Committer notes:
Combined it with a later patch to allow printing it via 'perf report -D'
and be able to test the feature introduced in this patch. Had to move
here also perf_ns__name(), that was introduced in another later patch.
Also used PRIu64 and PRIx64 to fix the build in some enfironments wrt:
util/event.c:1129:39: error: format '%lx' expects argument of type 'long unsigned int', but argument 6 has type 'long long unsigned int' [-Werror=format=]
ret += fprintf(fp, "%u/%s: %lu/0x%lx%s", idx
^
Testing it:
# perf record --namespaces -a
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 1.083 MB perf.data (423 samples) ]
#
# perf report -D
<SNIP>
3 2028902078892 0x115140 [0xa0]: PERF_RECORD_NAMESPACES 14783/14783 - nr_namespaces: 7
[0/net: 3/0xf0000081, 1/uts: 3/0xeffffffe, 2/ipc: 3/0xefffffff, 3/pid: 3/0xeffffffc,
4/user: 3/0xeffffffd, 5/mnt: 3/0xf0000000, 6/cgroup: 3/0xeffffffb]
0x1151e0 [0x30]: event: 9
.
. ... raw event: size 48 bytes
. 0000: 09 00 00 00 02 00 30 00 c4 71 82 68 0c 7f 00 00 ......0..q.h....
. 0010: a9 39 00 00 a9 39 00 00 94 28 fe 63 d8 01 00 00 .9...9...(.c....
. 0020: 03 00 00 00 00 00 00 00 ce c4 02 00 00 00 00 00 ................
<SNIP>
NAMESPACES events: 1
<SNIP>
#
Signed-off-by: Hari Bathini <hbathini@linux.vnet.ibm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@fb.com>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Aravinda Prasad <aravinda@linux.vnet.ibm.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sargun Dhillon <sargun@sargun.me>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/148891930386.25309.18412039920746995488.stgit@hbathini.in.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-08 04:41:43 +08:00
|
|
|
static const char *perf_ns__names[] = {
|
|
|
|
[NET_NS_INDEX] = "net",
|
|
|
|
[UTS_NS_INDEX] = "uts",
|
|
|
|
[IPC_NS_INDEX] = "ipc",
|
|
|
|
[PID_NS_INDEX] = "pid",
|
|
|
|
[USER_NS_INDEX] = "user",
|
|
|
|
[MNT_NS_INDEX] = "mnt",
|
|
|
|
[CGROUP_NS_INDEX] = "cgroup",
|
|
|
|
};
|
|
|
|
|
2018-12-05 04:34:20 +08:00
|
|
|
unsigned int proc_map_timeout = DEFAULT_PROC_MAP_PARSE_TIMEOUT;
|
|
|
|
|
2011-01-30 00:01:45 +08:00
|
|
|
const char *perf_event__name(unsigned int id)
|
2010-12-07 20:48:42 +08:00
|
|
|
{
|
2011-01-30 00:01:45 +08:00
|
|
|
if (id >= ARRAY_SIZE(perf_event__names))
|
2010-12-07 20:48:42 +08:00
|
|
|
return "INVALID";
|
2011-01-30 00:01:45 +08:00
|
|
|
if (!perf_event__names[id])
|
2010-12-07 20:48:42 +08:00
|
|
|
return "UNKNOWN";
|
2011-01-30 00:01:45 +08:00
|
|
|
return perf_event__names[id];
|
2010-12-07 20:48:42 +08:00
|
|
|
}
|
|
|
|
|
perf tools: Add PERF_RECORD_NAMESPACES to include namespaces related info
Introduce a new option to record PERF_RECORD_NAMESPACES events emitted
by the kernel when fork, clone, setns or unshare are invoked. And update
perf-record documentation with the new option to record namespace
events.
Committer notes:
Combined it with a later patch to allow printing it via 'perf report -D'
and be able to test the feature introduced in this patch. Had to move
here also perf_ns__name(), that was introduced in another later patch.
Also used PRIu64 and PRIx64 to fix the build in some enfironments wrt:
util/event.c:1129:39: error: format '%lx' expects argument of type 'long unsigned int', but argument 6 has type 'long long unsigned int' [-Werror=format=]
ret += fprintf(fp, "%u/%s: %lu/0x%lx%s", idx
^
Testing it:
# perf record --namespaces -a
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 1.083 MB perf.data (423 samples) ]
#
# perf report -D
<SNIP>
3 2028902078892 0x115140 [0xa0]: PERF_RECORD_NAMESPACES 14783/14783 - nr_namespaces: 7
[0/net: 3/0xf0000081, 1/uts: 3/0xeffffffe, 2/ipc: 3/0xefffffff, 3/pid: 3/0xeffffffc,
4/user: 3/0xeffffffd, 5/mnt: 3/0xf0000000, 6/cgroup: 3/0xeffffffb]
0x1151e0 [0x30]: event: 9
.
. ... raw event: size 48 bytes
. 0000: 09 00 00 00 02 00 30 00 c4 71 82 68 0c 7f 00 00 ......0..q.h....
. 0010: a9 39 00 00 a9 39 00 00 94 28 fe 63 d8 01 00 00 .9...9...(.c....
. 0020: 03 00 00 00 00 00 00 00 ce c4 02 00 00 00 00 00 ................
<SNIP>
NAMESPACES events: 1
<SNIP>
#
Signed-off-by: Hari Bathini <hbathini@linux.vnet.ibm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@fb.com>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Aravinda Prasad <aravinda@linux.vnet.ibm.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sargun Dhillon <sargun@sargun.me>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/148891930386.25309.18412039920746995488.stgit@hbathini.in.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-08 04:41:43 +08:00
|
|
|
static const char *perf_ns__name(unsigned int id)
|
|
|
|
{
|
|
|
|
if (id >= ARRAY_SIZE(perf_ns__names))
|
|
|
|
return "UNKNOWN";
|
|
|
|
return perf_ns__names[id];
|
|
|
|
}
|
|
|
|
|
2018-05-22 18:54:37 +08:00
|
|
|
int perf_tool__process_synth_event(struct perf_tool *tool,
|
|
|
|
union perf_event *event,
|
|
|
|
struct machine *machine,
|
|
|
|
perf_event__handler_t process)
|
perf tools: Add missing initialization of perf_sample.cpumode in synthesized samples
In 473398a21d28 ("perf tools: Add cpumode to struct perf_sample"), I
missed some places where perf_sample fields are directly initialized in
addition to what is done in perf_evsel__parse_sample(), namely when
synthesizing PERF_RECORD_{MMAP*,COMM,FORK,EXIT} for pre-existing threads
and also in intel_pt and intel_bts when synthesizing events from
processor trace, the jitdump code also was affected, fix it.
The problem was noticed with running:
# perf record -e intel_pt//u true
# perf script
Where the samples wouldn't get resolved because perf_sample.cpumode
would be left as zero, i.e. PERF_RECORD_MISC_CPUMODE_UNKNOWN, not
resolving as kernel, hypervisor or user cpu modes.
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 473398a21d28 ("perf tools: Add cpumode to struct perf_sample")
Link: http://lkml.kernel.org/n/tip-n5sdauxgk24d5nun8kuuu2mh@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-03-30 05:46:04 +08:00
|
|
|
{
|
|
|
|
struct perf_sample synth_sample = {
|
perf session: Parse sample earlier
At perf_session__process_event, so that we reduce the number of lines in eache
tool sample processing routine that now receives a sample_data pointer already
parsed.
This will also be useful in the next patch, where we'll allow sample the
identity fields in MMAP, FORK, EXIT, etc, when it will be possible to see (cpu,
timestamp) just after before every event.
Also validate callchains in perf_session__process_event, i.e. as early as
possible, and keep a counter of the number of events discarded due to invalid
callchains, warning the user about it if it happens.
There is an assumption that was kept that all events have the same sample_type,
that will be dealt with in the future, when this preexisting limitation will be
removed.
Tested-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Ian Munsie <imunsie@au1.ibm.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: Ian Munsie <imunsie@au1.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Stephane Eranian <eranian@google.com>
LKML-Reference: <1291318772-30880-4-git-send-email-acme@infradead.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-03 00:10:21 +08:00
|
|
|
.pid = -1,
|
|
|
|
.tid = -1,
|
|
|
|
.time = -1,
|
|
|
|
.stream_id = -1,
|
|
|
|
.cpu = -1,
|
|
|
|
.period = 1,
|
perf tools: Add missing initialization of perf_sample.cpumode in synthesized samples
In 473398a21d28 ("perf tools: Add cpumode to struct perf_sample"), I
missed some places where perf_sample fields are directly initialized in
addition to what is done in perf_evsel__parse_sample(), namely when
synthesizing PERF_RECORD_{MMAP*,COMM,FORK,EXIT} for pre-existing threads
and also in intel_pt and intel_bts when synthesizing events from
processor trace, the jitdump code also was affected, fix it.
The problem was noticed with running:
# perf record -e intel_pt//u true
# perf script
Where the samples wouldn't get resolved because perf_sample.cpumode
would be left as zero, i.e. PERF_RECORD_MISC_CPUMODE_UNKNOWN, not
resolving as kernel, hypervisor or user cpu modes.
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 473398a21d28 ("perf tools: Add cpumode to struct perf_sample")
Link: http://lkml.kernel.org/n/tip-n5sdauxgk24d5nun8kuuu2mh@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-03-30 05:46:04 +08:00
|
|
|
.cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK,
|
|
|
|
};
|
|
|
|
|
|
|
|
return process(tool, event, &synth_sample, machine);
|
perf session: Parse sample earlier
At perf_session__process_event, so that we reduce the number of lines in eache
tool sample processing routine that now receives a sample_data pointer already
parsed.
This will also be useful in the next patch, where we'll allow sample the
identity fields in MMAP, FORK, EXIT, etc, when it will be possible to see (cpu,
timestamp) just after before every event.
Also validate callchains in perf_session__process_event, i.e. as early as
possible, and keep a counter of the number of events discarded due to invalid
callchains, warning the user about it if it happens.
There is an assumption that was kept that all events have the same sample_type,
that will be dealt with in the future, when this preexisting limitation will be
removed.
Tested-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Ian Munsie <imunsie@au1.ibm.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: Ian Munsie <imunsie@au1.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Stephane Eranian <eranian@google.com>
LKML-Reference: <1291318772-30880-4-git-send-email-acme@infradead.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-03 00:10:21 +08:00
|
|
|
};
|
|
|
|
|
2015-03-31 04:35:57 +08:00
|
|
|
/*
|
|
|
|
* Assumes that the first 4095 bytes of /proc/pid/stat contains
|
2015-03-31 04:35:58 +08:00
|
|
|
* the comm, tgid and ppid.
|
2015-03-31 04:35:57 +08:00
|
|
|
*/
|
2015-03-31 04:35:58 +08:00
|
|
|
static int perf_event__get_comm_ids(pid_t pid, char *comm, size_t len,
|
|
|
|
pid_t *tgid, pid_t *ppid)
|
2009-10-27 05:23:18 +08:00
|
|
|
{
|
|
|
|
char filename[PATH_MAX];
|
2015-03-31 04:35:57 +08:00
|
|
|
char bf[4096];
|
|
|
|
int fd;
|
2015-10-06 17:00:17 +08:00
|
|
|
size_t size = 0;
|
|
|
|
ssize_t n;
|
2017-04-07 22:24:21 +08:00
|
|
|
char *name, *tgids, *ppids;
|
2015-03-31 04:35:58 +08:00
|
|
|
|
|
|
|
*tgid = -1;
|
|
|
|
*ppid = -1;
|
2009-10-27 05:23:18 +08:00
|
|
|
|
|
|
|
snprintf(filename, sizeof(filename), "/proc/%d/status", pid);
|
|
|
|
|
2015-03-31 04:35:57 +08:00
|
|
|
fd = open(filename, O_RDONLY);
|
|
|
|
if (fd < 0) {
|
2009-10-27 05:23:18 +08:00
|
|
|
pr_debug("couldn't open %s\n", filename);
|
2015-03-31 04:35:58 +08:00
|
|
|
return -1;
|
2009-10-27 05:23:18 +08:00
|
|
|
}
|
|
|
|
|
2015-03-31 04:35:57 +08:00
|
|
|
n = read(fd, bf, sizeof(bf) - 1);
|
|
|
|
close(fd);
|
|
|
|
if (n <= 0) {
|
2015-03-31 04:35:58 +08:00
|
|
|
pr_warning("Couldn't get COMM, tigd and ppid for pid %d\n",
|
2015-03-31 04:35:57 +08:00
|
|
|
pid);
|
|
|
|
return -1;
|
2009-10-27 05:23:18 +08:00
|
|
|
}
|
2015-03-31 04:35:57 +08:00
|
|
|
bf[n] = '\0';
|
2009-10-27 05:23:18 +08:00
|
|
|
|
2015-03-31 04:35:57 +08:00
|
|
|
name = strstr(bf, "Name:");
|
|
|
|
tgids = strstr(bf, "Tgid:");
|
2015-03-31 04:35:58 +08:00
|
|
|
ppids = strstr(bf, "PPid:");
|
2015-03-31 04:35:57 +08:00
|
|
|
|
|
|
|
if (name) {
|
2017-04-20 17:24:30 +08:00
|
|
|
char *nl;
|
|
|
|
|
2019-06-26 22:42:03 +08:00
|
|
|
name = skip_spaces(name + 5); /* strlen("Name:") */
|
2017-04-20 17:24:30 +08:00
|
|
|
nl = strchr(name, '\n');
|
|
|
|
if (nl)
|
|
|
|
*nl = '\0';
|
|
|
|
|
2015-03-31 04:35:57 +08:00
|
|
|
size = strlen(name);
|
|
|
|
if (size >= len)
|
|
|
|
size = len - 1;
|
|
|
|
memcpy(comm, name, size);
|
|
|
|
comm[size] = '\0';
|
|
|
|
} else {
|
|
|
|
pr_debug("Name: string not found for pid %d\n", pid);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (tgids) {
|
|
|
|
tgids += 5; /* strlen("Tgid:") */
|
2015-03-31 04:35:58 +08:00
|
|
|
*tgid = atoi(tgids);
|
2015-03-31 04:35:57 +08:00
|
|
|
} else {
|
|
|
|
pr_debug("Tgid: string not found for pid %d\n", pid);
|
|
|
|
}
|
2011-12-23 02:30:02 +08:00
|
|
|
|
2015-03-31 04:35:58 +08:00
|
|
|
if (ppids) {
|
|
|
|
ppids += 5; /* strlen("PPid:") */
|
|
|
|
*ppid = atoi(ppids);
|
|
|
|
} else {
|
|
|
|
pr_debug("PPid: string not found for pid %d\n", pid);
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
2011-12-23 02:30:02 +08:00
|
|
|
}
|
|
|
|
|
2015-03-31 04:35:58 +08:00
|
|
|
static int perf_event__prepare_comm(union perf_event *event, pid_t pid,
|
|
|
|
struct machine *machine,
|
|
|
|
pid_t *tgid, pid_t *ppid)
|
2011-12-23 02:30:02 +08:00
|
|
|
{
|
|
|
|
size_t size;
|
2015-03-31 04:35:58 +08:00
|
|
|
|
|
|
|
*ppid = -1;
|
2011-12-23 02:30:02 +08:00
|
|
|
|
|
|
|
memset(&event->comm, 0, sizeof(event->comm));
|
|
|
|
|
2015-03-31 04:35:58 +08:00
|
|
|
if (machine__is_host(machine)) {
|
|
|
|
if (perf_event__get_comm_ids(pid, event->comm.comm,
|
|
|
|
sizeof(event->comm.comm),
|
|
|
|
tgid, ppid) != 0) {
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
*tgid = machine->pid;
|
|
|
|
}
|
2013-12-21 04:52:59 +08:00
|
|
|
|
2015-03-31 04:35:58 +08:00
|
|
|
if (*tgid < 0)
|
|
|
|
return -1;
|
2011-12-23 02:30:02 +08:00
|
|
|
|
2015-03-31 04:35:58 +08:00
|
|
|
event->comm.pid = *tgid;
|
2010-12-02 20:25:28 +08:00
|
|
|
event->comm.header.type = PERF_RECORD_COMM;
|
2011-12-23 02:30:02 +08:00
|
|
|
|
|
|
|
size = strlen(event->comm.comm) + 1;
|
2012-09-11 06:15:01 +08:00
|
|
|
size = PERF_ALIGN(size, sizeof(u64));
|
2011-11-28 17:56:39 +08:00
|
|
|
memset(event->comm.comm + size, 0, machine->id_hdr_size);
|
2010-12-02 20:25:28 +08:00
|
|
|
event->comm.header.size = (sizeof(event->comm) -
|
|
|
|
(sizeof(event->comm.comm) - size) +
|
2011-11-28 17:56:39 +08:00
|
|
|
machine->id_hdr_size);
|
2014-02-26 23:45:26 +08:00
|
|
|
event->comm.tid = pid;
|
2015-03-31 04:35:58 +08:00
|
|
|
|
|
|
|
return 0;
|
perf tools: Fix FORK after COMM when synthesizing records for pre-existing threads
In this commit:
commit 363b785f3805a2632eb09a8b430842461c21a640
Author: Don Zickus <dzickus@redhat.com>
Date: Fri Mar 14 10:43:44 2014 -0400
perf tools: Speed up thread map generation
We ended up emitting PERF_RECORD_FORK events after their corresponding
PERF_RECORD_COMM, so the code below will remove the "existing thread"
and then recreates it, unnecessarily:
[root@ssdandy ~]# perf probe -x ~/bin/perf -L machine__process_fork_event
<machine__process_fork_event@/home/acme/git/linux/tools/perf/util/machine.c:0>
0 int machine__process_fork_event(struct machine *machine, union perf_event *event,
struct perf_sample *sample)
2 {
3 struct thread *thread = machine__find_thread(machine,
event->fork.pid,
event->fork.tid);
6 struct thread *parent = machine__findnew_thread(machine,
event->fork.ppid,
event->fork.ptid);
/* if a thread currently exists for the thread id remove it */
if (thread != NULL)
12 machine__remove_thread(machine, thread);
14 thread = machine__findnew_thread(machine, event->fork.pid,
event->fork.tid);
16 if (dump_trace)
17 perf_event__fprintf_task(event, stdout);
19 if (thread == NULL || parent == NULL ||
20 thread__fork(thread, parent, sample->time) < 0) {
21 dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n");
22 return -1;
}
25 return 0;
26 }
[root@ssdandy ~]# perf probe -x ~/bin/perf fork_after_comm=machine__process_fork_event:12
Added new event:
probe_perf:fork_after_comm (on machine__process_fork_event:12 in /home/acme/bin/perf)
You can now use it in all perf tools, such as:
perf record -e probe_perf:fork_after_comm -aR sleep 1
[root@ssdandy ~]#
[root@ssdandy ~]# perf record -g -e probe_perf:* trace -o /tmp/bla
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.021 MB perf.data (30 samples) ]
Terminated
[root@ssdandy ~]#
[root@ssdandy ~]# perf report --no-children --show-total-period --stdio
# To display the perf.data header info, please use --header/--header-only options.
#
# Samples: 30 of event 'probe_perf:fork_after_comm'
# Event count (approx.): 30
#
# Overhead Period Command Shared Object Symbol
# ........ ............ ....... ............. ...............................
#
100.00% 30 trace trace [.] machine__process_fork_event
|
---machine__process_fork_event
__event__synthesize_thread.part.2
perf_event__synthesize_threads
cmd_trace
main
__libc_start_main
[root@ssdandy ~]#
And Looking at 'perf report -D' output we see it:
0 0 0x8698 [0x30]: PERF_RECORD_COMM: auditd:703/707
0 0 0x86c8 [0x38]: PERF_RECORD_FORK(703:707):(703:703)
Fix it by more closely mimicking how the kernel generates those records
when a new fork happens, i.e. first a PERF_RECORD_FORK, then a
PERF_RECORD_COMM.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-h0emvymi2t3mw8dlqd6d6z73@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-28 06:52:10 +08:00
|
|
|
}
|
|
|
|
|
2015-09-22 08:24:55 +08:00
|
|
|
pid_t perf_event__synthesize_comm(struct perf_tool *tool,
|
perf tools: Fix FORK after COMM when synthesizing records for pre-existing threads
In this commit:
commit 363b785f3805a2632eb09a8b430842461c21a640
Author: Don Zickus <dzickus@redhat.com>
Date: Fri Mar 14 10:43:44 2014 -0400
perf tools: Speed up thread map generation
We ended up emitting PERF_RECORD_FORK events after their corresponding
PERF_RECORD_COMM, so the code below will remove the "existing thread"
and then recreates it, unnecessarily:
[root@ssdandy ~]# perf probe -x ~/bin/perf -L machine__process_fork_event
<machine__process_fork_event@/home/acme/git/linux/tools/perf/util/machine.c:0>
0 int machine__process_fork_event(struct machine *machine, union perf_event *event,
struct perf_sample *sample)
2 {
3 struct thread *thread = machine__find_thread(machine,
event->fork.pid,
event->fork.tid);
6 struct thread *parent = machine__findnew_thread(machine,
event->fork.ppid,
event->fork.ptid);
/* if a thread currently exists for the thread id remove it */
if (thread != NULL)
12 machine__remove_thread(machine, thread);
14 thread = machine__findnew_thread(machine, event->fork.pid,
event->fork.tid);
16 if (dump_trace)
17 perf_event__fprintf_task(event, stdout);
19 if (thread == NULL || parent == NULL ||
20 thread__fork(thread, parent, sample->time) < 0) {
21 dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n");
22 return -1;
}
25 return 0;
26 }
[root@ssdandy ~]# perf probe -x ~/bin/perf fork_after_comm=machine__process_fork_event:12
Added new event:
probe_perf:fork_after_comm (on machine__process_fork_event:12 in /home/acme/bin/perf)
You can now use it in all perf tools, such as:
perf record -e probe_perf:fork_after_comm -aR sleep 1
[root@ssdandy ~]#
[root@ssdandy ~]# perf record -g -e probe_perf:* trace -o /tmp/bla
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.021 MB perf.data (30 samples) ]
Terminated
[root@ssdandy ~]#
[root@ssdandy ~]# perf report --no-children --show-total-period --stdio
# To display the perf.data header info, please use --header/--header-only options.
#
# Samples: 30 of event 'probe_perf:fork_after_comm'
# Event count (approx.): 30
#
# Overhead Period Command Shared Object Symbol
# ........ ............ ....... ............. ...............................
#
100.00% 30 trace trace [.] machine__process_fork_event
|
---machine__process_fork_event
__event__synthesize_thread.part.2
perf_event__synthesize_threads
cmd_trace
main
__libc_start_main
[root@ssdandy ~]#
And Looking at 'perf report -D' output we see it:
0 0 0x8698 [0x30]: PERF_RECORD_COMM: auditd:703/707
0 0 0x86c8 [0x38]: PERF_RECORD_FORK(703:707):(703:703)
Fix it by more closely mimicking how the kernel generates those records
when a new fork happens, i.e. first a PERF_RECORD_FORK, then a
PERF_RECORD_COMM.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-h0emvymi2t3mw8dlqd6d6z73@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-28 06:52:10 +08:00
|
|
|
union perf_event *event, pid_t pid,
|
|
|
|
perf_event__handler_t process,
|
|
|
|
struct machine *machine)
|
|
|
|
{
|
2015-03-31 04:35:58 +08:00
|
|
|
pid_t tgid, ppid;
|
perf tools: Fix FORK after COMM when synthesizing records for pre-existing threads
In this commit:
commit 363b785f3805a2632eb09a8b430842461c21a640
Author: Don Zickus <dzickus@redhat.com>
Date: Fri Mar 14 10:43:44 2014 -0400
perf tools: Speed up thread map generation
We ended up emitting PERF_RECORD_FORK events after their corresponding
PERF_RECORD_COMM, so the code below will remove the "existing thread"
and then recreates it, unnecessarily:
[root@ssdandy ~]# perf probe -x ~/bin/perf -L machine__process_fork_event
<machine__process_fork_event@/home/acme/git/linux/tools/perf/util/machine.c:0>
0 int machine__process_fork_event(struct machine *machine, union perf_event *event,
struct perf_sample *sample)
2 {
3 struct thread *thread = machine__find_thread(machine,
event->fork.pid,
event->fork.tid);
6 struct thread *parent = machine__findnew_thread(machine,
event->fork.ppid,
event->fork.ptid);
/* if a thread currently exists for the thread id remove it */
if (thread != NULL)
12 machine__remove_thread(machine, thread);
14 thread = machine__findnew_thread(machine, event->fork.pid,
event->fork.tid);
16 if (dump_trace)
17 perf_event__fprintf_task(event, stdout);
19 if (thread == NULL || parent == NULL ||
20 thread__fork(thread, parent, sample->time) < 0) {
21 dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n");
22 return -1;
}
25 return 0;
26 }
[root@ssdandy ~]# perf probe -x ~/bin/perf fork_after_comm=machine__process_fork_event:12
Added new event:
probe_perf:fork_after_comm (on machine__process_fork_event:12 in /home/acme/bin/perf)
You can now use it in all perf tools, such as:
perf record -e probe_perf:fork_after_comm -aR sleep 1
[root@ssdandy ~]#
[root@ssdandy ~]# perf record -g -e probe_perf:* trace -o /tmp/bla
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.021 MB perf.data (30 samples) ]
Terminated
[root@ssdandy ~]#
[root@ssdandy ~]# perf report --no-children --show-total-period --stdio
# To display the perf.data header info, please use --header/--header-only options.
#
# Samples: 30 of event 'probe_perf:fork_after_comm'
# Event count (approx.): 30
#
# Overhead Period Command Shared Object Symbol
# ........ ............ ....... ............. ...............................
#
100.00% 30 trace trace [.] machine__process_fork_event
|
---machine__process_fork_event
__event__synthesize_thread.part.2
perf_event__synthesize_threads
cmd_trace
main
__libc_start_main
[root@ssdandy ~]#
And Looking at 'perf report -D' output we see it:
0 0 0x8698 [0x30]: PERF_RECORD_COMM: auditd:703/707
0 0 0x86c8 [0x38]: PERF_RECORD_FORK(703:707):(703:703)
Fix it by more closely mimicking how the kernel generates those records
when a new fork happens, i.e. first a PERF_RECORD_FORK, then a
PERF_RECORD_COMM.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-h0emvymi2t3mw8dlqd6d6z73@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-28 06:52:10 +08:00
|
|
|
|
2015-03-31 04:35:58 +08:00
|
|
|
if (perf_event__prepare_comm(event, pid, machine, &tgid, &ppid) != 0)
|
|
|
|
return -1;
|
2011-12-23 02:30:02 +08:00
|
|
|
|
perf tools: Add missing initialization of perf_sample.cpumode in synthesized samples
In 473398a21d28 ("perf tools: Add cpumode to struct perf_sample"), I
missed some places where perf_sample fields are directly initialized in
addition to what is done in perf_evsel__parse_sample(), namely when
synthesizing PERF_RECORD_{MMAP*,COMM,FORK,EXIT} for pre-existing threads
and also in intel_pt and intel_bts when synthesizing events from
processor trace, the jitdump code also was affected, fix it.
The problem was noticed with running:
# perf record -e intel_pt//u true
# perf script
Where the samples wouldn't get resolved because perf_sample.cpumode
would be left as zero, i.e. PERF_RECORD_MISC_CPUMODE_UNKNOWN, not
resolving as kernel, hypervisor or user cpu modes.
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 473398a21d28 ("perf tools: Add cpumode to struct perf_sample")
Link: http://lkml.kernel.org/n/tip-n5sdauxgk24d5nun8kuuu2mh@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-03-30 05:46:04 +08:00
|
|
|
if (perf_tool__process_synth_event(tool, event, machine, process) != 0)
|
2014-02-26 23:45:26 +08:00
|
|
|
return -1;
|
2009-10-27 05:23:18 +08:00
|
|
|
|
2010-12-02 20:25:28 +08:00
|
|
|
return tgid;
|
2009-10-27 05:23:18 +08:00
|
|
|
}
|
|
|
|
|
2017-03-08 04:41:51 +08:00
|
|
|
static void perf_event__get_ns_link_info(pid_t pid, const char *ns,
|
|
|
|
struct perf_ns_link_info *ns_link_info)
|
|
|
|
{
|
|
|
|
struct stat64 st;
|
|
|
|
char proc_ns[128];
|
|
|
|
|
|
|
|
sprintf(proc_ns, "/proc/%u/ns/%s", pid, ns);
|
|
|
|
if (stat64(proc_ns, &st) == 0) {
|
|
|
|
ns_link_info->dev = st.st_dev;
|
|
|
|
ns_link_info->ino = st.st_ino;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
int perf_event__synthesize_namespaces(struct perf_tool *tool,
|
|
|
|
union perf_event *event,
|
|
|
|
pid_t pid, pid_t tgid,
|
|
|
|
perf_event__handler_t process,
|
|
|
|
struct machine *machine)
|
|
|
|
{
|
|
|
|
u32 idx;
|
|
|
|
struct perf_ns_link_info *ns_link_info;
|
|
|
|
|
|
|
|
if (!tool || !tool->namespace_events)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
memset(&event->namespaces, 0, (sizeof(event->namespaces) +
|
|
|
|
(NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
|
|
|
|
machine->id_hdr_size));
|
|
|
|
|
|
|
|
event->namespaces.pid = tgid;
|
|
|
|
event->namespaces.tid = pid;
|
|
|
|
|
|
|
|
event->namespaces.nr_namespaces = NR_NAMESPACES;
|
|
|
|
|
|
|
|
ns_link_info = event->namespaces.link_info;
|
|
|
|
|
|
|
|
for (idx = 0; idx < event->namespaces.nr_namespaces; idx++)
|
|
|
|
perf_event__get_ns_link_info(pid, perf_ns__name(idx),
|
|
|
|
&ns_link_info[idx]);
|
|
|
|
|
|
|
|
event->namespaces.header.type = PERF_RECORD_NAMESPACES;
|
|
|
|
|
|
|
|
event->namespaces.header.size = (sizeof(event->namespaces) +
|
|
|
|
(NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
|
|
|
|
machine->id_hdr_size);
|
|
|
|
|
|
|
|
if (perf_tool__process_synth_event(tool, event, machine, process) != 0)
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2014-03-14 22:43:44 +08:00
|
|
|
static int perf_event__synthesize_fork(struct perf_tool *tool,
|
2015-03-31 04:35:58 +08:00
|
|
|
union perf_event *event,
|
|
|
|
pid_t pid, pid_t tgid, pid_t ppid,
|
|
|
|
perf_event__handler_t process,
|
2014-03-14 22:43:44 +08:00
|
|
|
struct machine *machine)
|
|
|
|
{
|
|
|
|
memset(&event->fork, 0, sizeof(event->fork) + machine->id_hdr_size);
|
|
|
|
|
2015-04-10 00:48:27 +08:00
|
|
|
/*
|
|
|
|
* for main thread set parent to ppid from status file. For other
|
|
|
|
* threads set parent pid to main thread. ie., assume main thread
|
|
|
|
* spawns all threads in a process
|
|
|
|
*/
|
|
|
|
if (tgid == pid) {
|
|
|
|
event->fork.ppid = ppid;
|
|
|
|
event->fork.ptid = ppid;
|
|
|
|
} else {
|
|
|
|
event->fork.ppid = tgid;
|
|
|
|
event->fork.ptid = tgid;
|
|
|
|
}
|
2014-03-14 22:43:44 +08:00
|
|
|
event->fork.pid = tgid;
|
|
|
|
event->fork.tid = pid;
|
|
|
|
event->fork.header.type = PERF_RECORD_FORK;
|
2018-10-31 13:24:04 +08:00
|
|
|
event->fork.header.misc = PERF_RECORD_MISC_FORK_EXEC;
|
2014-03-14 22:43:44 +08:00
|
|
|
|
|
|
|
event->fork.header.size = (sizeof(event->fork) + machine->id_hdr_size);
|
|
|
|
|
perf tools: Add missing initialization of perf_sample.cpumode in synthesized samples
In 473398a21d28 ("perf tools: Add cpumode to struct perf_sample"), I
missed some places where perf_sample fields are directly initialized in
addition to what is done in perf_evsel__parse_sample(), namely when
synthesizing PERF_RECORD_{MMAP*,COMM,FORK,EXIT} for pre-existing threads
and also in intel_pt and intel_bts when synthesizing events from
processor trace, the jitdump code also was affected, fix it.
The problem was noticed with running:
# perf record -e intel_pt//u true
# perf script
Where the samples wouldn't get resolved because perf_sample.cpumode
would be left as zero, i.e. PERF_RECORD_MISC_CPUMODE_UNKNOWN, not
resolving as kernel, hypervisor or user cpu modes.
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 473398a21d28 ("perf tools: Add cpumode to struct perf_sample")
Link: http://lkml.kernel.org/n/tip-n5sdauxgk24d5nun8kuuu2mh@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-03-30 05:46:04 +08:00
|
|
|
if (perf_tool__process_synth_event(tool, event, machine, process) != 0)
|
2014-03-14 22:43:44 +08:00
|
|
|
return -1;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2014-01-07 20:47:20 +08:00
|
|
|
int perf_event__synthesize_mmap_events(struct perf_tool *tool,
|
|
|
|
union perf_event *event,
|
|
|
|
pid_t pid, pid_t tgid,
|
|
|
|
perf_event__handler_t process,
|
|
|
|
struct machine *machine,
|
2018-12-05 04:34:20 +08:00
|
|
|
bool mmap_data)
|
2009-10-27 05:23:18 +08:00
|
|
|
{
|
|
|
|
char filename[PATH_MAX];
|
|
|
|
FILE *fp;
|
2015-06-17 21:51:10 +08:00
|
|
|
unsigned long long t;
|
|
|
|
bool truncation = false;
|
2015-06-17 21:51:11 +08:00
|
|
|
unsigned long long timeout = proc_map_timeout * 1000000ULL;
|
2012-08-27 02:24:42 +08:00
|
|
|
int rc = 0;
|
2016-09-06 12:58:29 +08:00
|
|
|
const char *hugetlbfs_mnt = hugetlbfs__mountpoint();
|
|
|
|
int hugetlbfs_mnt_len = hugetlbfs_mnt ? strlen(hugetlbfs_mnt) : 0;
|
2009-10-27 05:23:18 +08:00
|
|
|
|
2013-12-21 04:53:00 +08:00
|
|
|
if (machine__is_default_guest(machine))
|
|
|
|
return 0;
|
|
|
|
|
2017-03-16 01:17:13 +08:00
|
|
|
snprintf(filename, sizeof(filename), "%s/proc/%d/task/%d/maps",
|
|
|
|
machine->root_dir, pid, pid);
|
2009-10-27 05:23:18 +08:00
|
|
|
|
|
|
|
fp = fopen(filename, "r");
|
|
|
|
if (fp == NULL) {
|
|
|
|
/*
|
|
|
|
* We raced with a task exiting - just return:
|
|
|
|
*/
|
|
|
|
pr_debug("couldn't open %s\n", filename);
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
2014-05-30 22:49:42 +08:00
|
|
|
event->header.type = PERF_RECORD_MMAP2;
|
2015-06-17 21:51:10 +08:00
|
|
|
t = rdclock();
|
2010-12-02 20:25:28 +08:00
|
|
|
|
2009-10-27 05:23:18 +08:00
|
|
|
while (1) {
|
2012-11-11 22:20:50 +08:00
|
|
|
char bf[BUFSIZ];
|
|
|
|
char prot[5];
|
|
|
|
char execname[PATH_MAX];
|
|
|
|
char anonstr[] = "//anon";
|
2014-05-30 22:49:42 +08:00
|
|
|
unsigned int ino;
|
2009-10-27 05:23:18 +08:00
|
|
|
size_t size;
|
2013-08-21 18:10:25 +08:00
|
|
|
ssize_t n;
|
2012-11-11 22:20:50 +08:00
|
|
|
|
2009-10-27 05:23:18 +08:00
|
|
|
if (fgets(bf, sizeof(bf), fp) == NULL)
|
|
|
|
break;
|
|
|
|
|
2015-06-17 21:51:11 +08:00
|
|
|
if ((rdclock() - t) > timeout) {
|
|
|
|
pr_warning("Reading %s time out. "
|
|
|
|
"You may want to increase "
|
|
|
|
"the time limit by --proc-map-timeout\n",
|
|
|
|
filename);
|
2015-06-17 21:51:10 +08:00
|
|
|
truncation = true;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
2012-11-11 22:20:50 +08:00
|
|
|
/* ensure null termination since stack will be reused. */
|
|
|
|
strcpy(execname, "");
|
|
|
|
|
2009-10-27 05:23:18 +08:00
|
|
|
/* 00400000-0040c000 r-xp 00000000 fd:01 41038 /bin/cat */
|
2016-01-20 03:03:03 +08:00
|
|
|
n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %[^\n]\n",
|
2014-05-30 22:49:42 +08:00
|
|
|
&event->mmap2.start, &event->mmap2.len, prot,
|
|
|
|
&event->mmap2.pgoff, &event->mmap2.maj,
|
|
|
|
&event->mmap2.min,
|
|
|
|
&ino, execname);
|
|
|
|
|
2013-11-14 02:32:06 +08:00
|
|
|
/*
|
|
|
|
* Anon maps don't have the execname.
|
|
|
|
*/
|
2014-05-30 22:49:42 +08:00
|
|
|
if (n < 7)
|
2013-08-21 18:10:25 +08:00
|
|
|
continue;
|
2014-05-30 22:49:42 +08:00
|
|
|
|
|
|
|
event->mmap2.ino = (u64)ino;
|
|
|
|
|
2013-11-11 20:44:09 +08:00
|
|
|
/*
|
|
|
|
* Just like the kernel, see __perf_event_mmap in kernel/perf_event.c
|
|
|
|
*/
|
2013-12-21 04:52:58 +08:00
|
|
|
if (machine__is_host(machine))
|
|
|
|
event->header.misc = PERF_RECORD_MISC_USER;
|
|
|
|
else
|
|
|
|
event->header.misc = PERF_RECORD_MISC_GUEST_USER;
|
2012-11-11 22:20:50 +08:00
|
|
|
|
2014-05-20 03:13:49 +08:00
|
|
|
/* map protection and flags bits */
|
|
|
|
event->mmap2.prot = 0;
|
|
|
|
event->mmap2.flags = 0;
|
|
|
|
if (prot[0] == 'r')
|
|
|
|
event->mmap2.prot |= PROT_READ;
|
|
|
|
if (prot[1] == 'w')
|
|
|
|
event->mmap2.prot |= PROT_WRITE;
|
|
|
|
if (prot[2] == 'x')
|
|
|
|
event->mmap2.prot |= PROT_EXEC;
|
|
|
|
|
|
|
|
if (prot[3] == 's')
|
|
|
|
event->mmap2.flags |= MAP_SHARED;
|
|
|
|
else
|
|
|
|
event->mmap2.flags |= MAP_PRIVATE;
|
|
|
|
|
2013-11-11 20:44:09 +08:00
|
|
|
if (prot[2] != 'x') {
|
|
|
|
if (!mmap_data || prot[0] != 'r')
|
|
|
|
continue;
|
|
|
|
|
|
|
|
event->header.misc |= PERF_RECORD_MISC_MMAP_DATA;
|
|
|
|
}
|
2012-11-11 22:20:50 +08:00
|
|
|
|
2015-06-17 21:51:10 +08:00
|
|
|
out:
|
|
|
|
if (truncation)
|
|
|
|
event->header.misc |= PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT;
|
|
|
|
|
2012-11-11 22:20:50 +08:00
|
|
|
if (!strcmp(execname, ""))
|
|
|
|
strcpy(execname, anonstr);
|
2016-09-13 03:47:57 +08:00
|
|
|
|
2016-09-23 22:38:34 +08:00
|
|
|
if (hugetlbfs_mnt_len &&
|
|
|
|
!strncmp(execname, hugetlbfs_mnt, hugetlbfs_mnt_len)) {
|
2016-09-06 12:58:29 +08:00
|
|
|
strcpy(execname, anonstr);
|
|
|
|
event->mmap2.flags |= MAP_HUGETLB;
|
|
|
|
}
|
2012-11-11 22:20:50 +08:00
|
|
|
|
|
|
|
size = strlen(execname) + 1;
|
2014-05-30 22:49:42 +08:00
|
|
|
memcpy(event->mmap2.filename, execname, size);
|
2012-11-11 22:20:50 +08:00
|
|
|
size = PERF_ALIGN(size, sizeof(u64));
|
2014-05-30 22:49:42 +08:00
|
|
|
event->mmap2.len -= event->mmap.start;
|
|
|
|
event->mmap2.header.size = (sizeof(event->mmap2) -
|
|
|
|
(sizeof(event->mmap2.filename) - size));
|
|
|
|
memset(event->mmap2.filename + size, 0, machine->id_hdr_size);
|
|
|
|
event->mmap2.header.size += machine->id_hdr_size;
|
|
|
|
event->mmap2.pid = tgid;
|
|
|
|
event->mmap2.tid = pid;
|
2012-11-11 22:20:50 +08:00
|
|
|
|
perf tools: Add missing initialization of perf_sample.cpumode in synthesized samples
In 473398a21d28 ("perf tools: Add cpumode to struct perf_sample"), I
missed some places where perf_sample fields are directly initialized in
addition to what is done in perf_evsel__parse_sample(), namely when
synthesizing PERF_RECORD_{MMAP*,COMM,FORK,EXIT} for pre-existing threads
and also in intel_pt and intel_bts when synthesizing events from
processor trace, the jitdump code also was affected, fix it.
The problem was noticed with running:
# perf record -e intel_pt//u true
# perf script
Where the samples wouldn't get resolved because perf_sample.cpumode
would be left as zero, i.e. PERF_RECORD_MISC_CPUMODE_UNKNOWN, not
resolving as kernel, hypervisor or user cpu modes.
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 473398a21d28 ("perf tools: Add cpumode to struct perf_sample")
Link: http://lkml.kernel.org/n/tip-n5sdauxgk24d5nun8kuuu2mh@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-03-30 05:46:04 +08:00
|
|
|
if (perf_tool__process_synth_event(tool, event, machine, process) != 0) {
|
2012-11-11 22:20:50 +08:00
|
|
|
rc = -1;
|
|
|
|
break;
|
2009-10-27 05:23:18 +08:00
|
|
|
}
|
2015-06-17 21:51:10 +08:00
|
|
|
|
|
|
|
if (truncation)
|
|
|
|
break;
|
2009-10-27 05:23:18 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
fclose(fp);
|
2012-08-27 02:24:42 +08:00
|
|
|
return rc;
|
2009-10-27 05:23:18 +08:00
|
|
|
}
|
|
|
|
|
2011-11-28 18:30:20 +08:00
|
|
|
int perf_event__synthesize_modules(struct perf_tool *tool,
|
2011-11-25 18:19:45 +08:00
|
|
|
perf_event__handler_t process,
|
2011-01-30 00:01:45 +08:00
|
|
|
struct machine *machine)
|
perf tools: Encode kernel module mappings in perf.data
We were always looking at the running machine /proc/modules,
even when processing a perf.data file, which only makes sense
when we're doing 'perf record' and 'perf report' on the same
machine, and in close sucession, or if we don't use modules at
all, right Peter? ;-)
Now, at 'perf record' time we read /proc/modules, find the long
path for modules, and put them as PERF_MMAP events, just like we
did to encode the reloc reference symbol for vmlinux. Talking
about that now it is encoded in .pgoff, so that we can use
.{start,len} to store the address boundaries for the kernel so
that when we reconstruct the kmaps tree we can do lookups right
away, without having to fixup the end of the kernel maps like we
did in the past (and now only in perf record).
One more step in the 'perf archive' direction when we'll finally
be able to collect data in one machine and analyse in another.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1263396139-4798-1-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-13 23:22:17 +08:00
|
|
|
{
|
2012-08-27 02:24:42 +08:00
|
|
|
int rc = 0;
|
2015-05-22 22:52:22 +08:00
|
|
|
struct map *pos;
|
2018-04-25 04:06:25 +08:00
|
|
|
struct maps *maps = machine__kernel_maps(machine);
|
2011-01-30 00:01:45 +08:00
|
|
|
union perf_event *event = zalloc((sizeof(event->mmap) +
|
2011-11-28 17:56:39 +08:00
|
|
|
machine->id_hdr_size));
|
2010-12-02 20:25:28 +08:00
|
|
|
if (event == NULL) {
|
|
|
|
pr_debug("Not enough memory synthesizing mmap event "
|
|
|
|
"for kernel modules\n");
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
|
|
|
event->header.type = PERF_RECORD_MMAP;
|
perf tools: Encode kernel module mappings in perf.data
We were always looking at the running machine /proc/modules,
even when processing a perf.data file, which only makes sense
when we're doing 'perf record' and 'perf report' on the same
machine, and in close sucession, or if we don't use modules at
all, right Peter? ;-)
Now, at 'perf record' time we read /proc/modules, find the long
path for modules, and put them as PERF_MMAP events, just like we
did to encode the reloc reference symbol for vmlinux. Talking
about that now it is encoded in .pgoff, so that we can use
.{start,len} to store the address boundaries for the kernel so
that when we reconstruct the kmaps tree we can do lookups right
away, without having to fixup the end of the kernel maps like we
did in the past (and now only in perf record).
One more step in the 'perf archive' direction when we'll finally
be able to collect data in one machine and analyse in another.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1263396139-4798-1-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-13 23:22:17 +08:00
|
|
|
|
2010-04-19 13:32:50 +08:00
|
|
|
/*
|
|
|
|
* kernel uses 0 for user space maps, see kernel/perf_event.c
|
|
|
|
* __perf_event_mmap
|
|
|
|
*/
|
2010-04-28 08:17:50 +08:00
|
|
|
if (machine__is_host(machine))
|
2010-12-02 20:25:28 +08:00
|
|
|
event->header.misc = PERF_RECORD_MISC_KERNEL;
|
2010-04-19 13:32:50 +08:00
|
|
|
else
|
2010-12-02 20:25:28 +08:00
|
|
|
event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
|
2010-04-19 13:32:50 +08:00
|
|
|
|
2015-05-22 22:52:22 +08:00
|
|
|
for (pos = maps__first(maps); pos; pos = map__next(pos)) {
|
perf tools: Encode kernel module mappings in perf.data
We were always looking at the running machine /proc/modules,
even when processing a perf.data file, which only makes sense
when we're doing 'perf record' and 'perf report' on the same
machine, and in close sucession, or if we don't use modules at
all, right Peter? ;-)
Now, at 'perf record' time we read /proc/modules, find the long
path for modules, and put them as PERF_MMAP events, just like we
did to encode the reloc reference symbol for vmlinux. Talking
about that now it is encoded in .pgoff, so that we can use
.{start,len} to store the address boundaries for the kernel so
that when we reconstruct the kmaps tree we can do lookups right
away, without having to fixup the end of the kernel maps like we
did in the past (and now only in perf record).
One more step in the 'perf archive' direction when we'll finally
be able to collect data in one machine and analyse in another.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1263396139-4798-1-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-13 23:22:17 +08:00
|
|
|
size_t size;
|
|
|
|
|
2018-05-22 18:54:35 +08:00
|
|
|
if (!__map__is_kmodule(pos))
|
perf tools: Encode kernel module mappings in perf.data
We were always looking at the running machine /proc/modules,
even when processing a perf.data file, which only makes sense
when we're doing 'perf record' and 'perf report' on the same
machine, and in close sucession, or if we don't use modules at
all, right Peter? ;-)
Now, at 'perf record' time we read /proc/modules, find the long
path for modules, and put them as PERF_MMAP events, just like we
did to encode the reloc reference symbol for vmlinux. Talking
about that now it is encoded in .pgoff, so that we can use
.{start,len} to store the address boundaries for the kernel so
that when we reconstruct the kmaps tree we can do lookups right
away, without having to fixup the end of the kernel maps like we
did in the past (and now only in perf record).
One more step in the 'perf archive' direction when we'll finally
be able to collect data in one machine and analyse in another.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1263396139-4798-1-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-13 23:22:17 +08:00
|
|
|
continue;
|
|
|
|
|
2012-09-11 06:15:01 +08:00
|
|
|
size = PERF_ALIGN(pos->dso->long_name_len + 1, sizeof(u64));
|
2010-12-02 20:25:28 +08:00
|
|
|
event->mmap.header.type = PERF_RECORD_MMAP;
|
|
|
|
event->mmap.header.size = (sizeof(event->mmap) -
|
|
|
|
(sizeof(event->mmap.filename) - size));
|
2011-11-28 17:56:39 +08:00
|
|
|
memset(event->mmap.filename + size, 0, machine->id_hdr_size);
|
|
|
|
event->mmap.header.size += machine->id_hdr_size;
|
2010-12-02 20:25:28 +08:00
|
|
|
event->mmap.start = pos->start;
|
|
|
|
event->mmap.len = pos->end - pos->start;
|
|
|
|
event->mmap.pid = machine->pid;
|
|
|
|
|
|
|
|
memcpy(event->mmap.filename, pos->dso->long_name,
|
perf tools: Encode kernel module mappings in perf.data
We were always looking at the running machine /proc/modules,
even when processing a perf.data file, which only makes sense
when we're doing 'perf record' and 'perf report' on the same
machine, and in close sucession, or if we don't use modules at
all, right Peter? ;-)
Now, at 'perf record' time we read /proc/modules, find the long
path for modules, and put them as PERF_MMAP events, just like we
did to encode the reloc reference symbol for vmlinux. Talking
about that now it is encoded in .pgoff, so that we can use
.{start,len} to store the address boundaries for the kernel so
that when we reconstruct the kmaps tree we can do lookups right
away, without having to fixup the end of the kernel maps like we
did in the past (and now only in perf record).
One more step in the 'perf archive' direction when we'll finally
be able to collect data in one machine and analyse in another.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1263396139-4798-1-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-13 23:22:17 +08:00
|
|
|
pos->dso->long_name_len + 1);
|
perf tools: Add missing initialization of perf_sample.cpumode in synthesized samples
In 473398a21d28 ("perf tools: Add cpumode to struct perf_sample"), I
missed some places where perf_sample fields are directly initialized in
addition to what is done in perf_evsel__parse_sample(), namely when
synthesizing PERF_RECORD_{MMAP*,COMM,FORK,EXIT} for pre-existing threads
and also in intel_pt and intel_bts when synthesizing events from
processor trace, the jitdump code also was affected, fix it.
The problem was noticed with running:
# perf record -e intel_pt//u true
# perf script
Where the samples wouldn't get resolved because perf_sample.cpumode
would be left as zero, i.e. PERF_RECORD_MISC_CPUMODE_UNKNOWN, not
resolving as kernel, hypervisor or user cpu modes.
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 473398a21d28 ("perf tools: Add cpumode to struct perf_sample")
Link: http://lkml.kernel.org/n/tip-n5sdauxgk24d5nun8kuuu2mh@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-03-30 05:46:04 +08:00
|
|
|
if (perf_tool__process_synth_event(tool, event, machine, process) != 0) {
|
2012-08-27 02:24:42 +08:00
|
|
|
rc = -1;
|
|
|
|
break;
|
|
|
|
}
|
perf tools: Encode kernel module mappings in perf.data
We were always looking at the running machine /proc/modules,
even when processing a perf.data file, which only makes sense
when we're doing 'perf record' and 'perf report' on the same
machine, and in close sucession, or if we don't use modules at
all, right Peter? ;-)
Now, at 'perf record' time we read /proc/modules, find the long
path for modules, and put them as PERF_MMAP events, just like we
did to encode the reloc reference symbol for vmlinux. Talking
about that now it is encoded in .pgoff, so that we can use
.{start,len} to store the address boundaries for the kernel so
that when we reconstruct the kmaps tree we can do lookups right
away, without having to fixup the end of the kernel maps like we
did in the past (and now only in perf record).
One more step in the 'perf archive' direction when we'll finally
be able to collect data in one machine and analyse in another.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1263396139-4798-1-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-13 23:22:17 +08:00
|
|
|
}
|
|
|
|
|
2010-12-02 20:25:28 +08:00
|
|
|
free(event);
|
2012-08-27 02:24:42 +08:00
|
|
|
return rc;
|
perf tools: Encode kernel module mappings in perf.data
We were always looking at the running machine /proc/modules,
even when processing a perf.data file, which only makes sense
when we're doing 'perf record' and 'perf report' on the same
machine, and in close sucession, or if we don't use modules at
all, right Peter? ;-)
Now, at 'perf record' time we read /proc/modules, find the long
path for modules, and put them as PERF_MMAP events, just like we
did to encode the reloc reference symbol for vmlinux. Talking
about that now it is encoded in .pgoff, so that we can use
.{start,len} to store the address boundaries for the kernel so
that when we reconstruct the kmaps tree we can do lookups right
away, without having to fixup the end of the kernel maps like we
did in the past (and now only in perf record).
One more step in the 'perf archive' direction when we'll finally
be able to collect data in one machine and analyse in another.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1263396139-4798-1-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-13 23:22:17 +08:00
|
|
|
}
|
|
|
|
|
2011-01-30 00:01:45 +08:00
|
|
|
static int __event__synthesize_thread(union perf_event *comm_event,
|
|
|
|
union perf_event *mmap_event,
|
2014-03-14 22:43:44 +08:00
|
|
|
union perf_event *fork_event,
|
2017-03-08 04:41:51 +08:00
|
|
|
union perf_event *namespaces_event,
|
2011-12-23 02:30:01 +08:00
|
|
|
pid_t pid, int full,
|
2017-03-08 04:41:51 +08:00
|
|
|
perf_event__handler_t process,
|
2011-11-28 18:30:20 +08:00
|
|
|
struct perf_tool *tool,
|
2015-06-17 21:51:11 +08:00
|
|
|
struct machine *machine,
|
2018-12-05 04:34:20 +08:00
|
|
|
bool mmap_data)
|
2009-10-27 05:23:18 +08:00
|
|
|
{
|
2014-02-26 23:45:26 +08:00
|
|
|
char filename[PATH_MAX];
|
|
|
|
DIR *tasks;
|
perf tools: Use readdir() instead of deprecated readdir_r()
The readdir() function is thread safe as long as just one thread uses a
DIR, which is the case when synthesizing events for pre-existing threads
by traversing /proc, so, to avoid breaking the build with glibc-2.23.90
(upcoming 2.24), use it instead of readdir_r().
See: http://man7.org/linux/man-pages/man3/readdir.3.html
"However, in modern implementations (including the glibc implementation),
concurrent calls to readdir() that specify different directory streams
are thread-safe. In cases where multiple threads must read from the
same directory stream, using readdir() with external synchronization is
still preferable to the use of the deprecated readdir_r(3) function."
Noticed while building on a Fedora Rawhide docker container.
CC /tmp/build/perf/util/event.o
util/event.c: In function '__event__synthesize_thread':
util/event.c:466:2: error: 'readdir_r' is deprecated [-Werror=deprecated-declarations]
while (!readdir_r(tasks, &dirent, &next) && next) {
^~~~~
In file included from /usr/include/features.h:368:0,
from /usr/include/stdint.h:25,
from /usr/lib/gcc/x86_64-redhat-linux/6.0.0/include/stdint.h:9,
from /git/linux/tools/include/linux/types.h:6,
from util/event.c:1:
/usr/include/dirent.h:189:12: note: declared here
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-i1vj7nyjp2p750rirxgrfd3c@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-08 22:32:15 +08:00
|
|
|
struct dirent *dirent;
|
2015-03-31 04:35:58 +08:00
|
|
|
pid_t tgid, ppid;
|
2015-04-08 22:57:03 +08:00
|
|
|
int rc = 0;
|
2014-02-26 23:45:26 +08:00
|
|
|
|
|
|
|
/* special case: only send one comm event using passed in pid */
|
|
|
|
if (!full) {
|
|
|
|
tgid = perf_event__synthesize_comm(tool, comm_event, pid,
|
|
|
|
process, machine);
|
|
|
|
|
|
|
|
if (tgid == -1)
|
|
|
|
return -1;
|
|
|
|
|
2017-03-08 04:41:51 +08:00
|
|
|
if (perf_event__synthesize_namespaces(tool, namespaces_event, pid,
|
|
|
|
tgid, process, machine) < 0)
|
|
|
|
return -1;
|
|
|
|
|
perf map: Synthesize maps only for thread group leader
Threads share map_groups, all map events are merged into it.
Thus we could send mmaps only for thread group leader. Otherwise it
took ages to attach and record something from processes with many vmas
and threads.
Thread group leader could be already dead, but it seems perf cannot
handle this case anyway.
Testing dummy:
#include <stdio.h>
#include <stdlib.h>
#include <sys/mman.h>
#include <pthread.h>
#include <unistd.h>
void *thread(void *arg) {
pause();
}
int main(int argc, char **argv) {
int threads = 10000;
int vmas = 50000;
pthread_t th;
for (int i = 0; i < threads; i++)
pthread_create(&th, NULL, thread, NULL);
for (int i = 0; i < vmas; i++)
mmap(NULL, 4096, (i & 1) ? PROT_READ : PROT_WRITE,
MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE, -1, 0);
sleep(60);
return 0;
}
Comment by Jiri Olsa:
We actualy synthesize the group leader (if we found one) for the thread
even if it's not present in the thread_map, so the process maps are
always in data.
Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/153363294102.396323.6277944760215058174.stgit@buzz
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-07 17:09:01 +08:00
|
|
|
/*
|
|
|
|
* send mmap only for thread group leader
|
|
|
|
* see thread__init_map_groups
|
|
|
|
*/
|
|
|
|
if (pid == tgid &&
|
|
|
|
perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
|
2018-12-05 04:34:20 +08:00
|
|
|
process, machine, mmap_data))
|
perf map: Synthesize maps only for thread group leader
Threads share map_groups, all map events are merged into it.
Thus we could send mmaps only for thread group leader. Otherwise it
took ages to attach and record something from processes with many vmas
and threads.
Thread group leader could be already dead, but it seems perf cannot
handle this case anyway.
Testing dummy:
#include <stdio.h>
#include <stdlib.h>
#include <sys/mman.h>
#include <pthread.h>
#include <unistd.h>
void *thread(void *arg) {
pause();
}
int main(int argc, char **argv) {
int threads = 10000;
int vmas = 50000;
pthread_t th;
for (int i = 0; i < threads; i++)
pthread_create(&th, NULL, thread, NULL);
for (int i = 0; i < vmas; i++)
mmap(NULL, 4096, (i & 1) ? PROT_READ : PROT_WRITE,
MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE, -1, 0);
sleep(60);
return 0;
}
Comment by Jiri Olsa:
We actualy synthesize the group leader (if we found one) for the thread
even if it's not present in the thread_map, so the process maps are
always in data.
Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/153363294102.396323.6277944760215058174.stgit@buzz
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-07 17:09:01 +08:00
|
|
|
return -1;
|
2017-03-08 04:41:51 +08:00
|
|
|
|
perf map: Synthesize maps only for thread group leader
Threads share map_groups, all map events are merged into it.
Thus we could send mmaps only for thread group leader. Otherwise it
took ages to attach and record something from processes with many vmas
and threads.
Thread group leader could be already dead, but it seems perf cannot
handle this case anyway.
Testing dummy:
#include <stdio.h>
#include <stdlib.h>
#include <sys/mman.h>
#include <pthread.h>
#include <unistd.h>
void *thread(void *arg) {
pause();
}
int main(int argc, char **argv) {
int threads = 10000;
int vmas = 50000;
pthread_t th;
for (int i = 0; i < threads; i++)
pthread_create(&th, NULL, thread, NULL);
for (int i = 0; i < vmas; i++)
mmap(NULL, 4096, (i & 1) ? PROT_READ : PROT_WRITE,
MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE, -1, 0);
sleep(60);
return 0;
}
Comment by Jiri Olsa:
We actualy synthesize the group leader (if we found one) for the thread
even if it's not present in the thread_map, so the process maps are
always in data.
Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/153363294102.396323.6277944760215058174.stgit@buzz
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-07 17:09:01 +08:00
|
|
|
return 0;
|
2014-02-26 23:45:26 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
if (machine__is_default_guest(machine))
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
snprintf(filename, sizeof(filename), "%s/proc/%d/task",
|
|
|
|
machine->root_dir, pid);
|
|
|
|
|
|
|
|
tasks = opendir(filename);
|
|
|
|
if (tasks == NULL) {
|
|
|
|
pr_debug("couldn't open %s\n", filename);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
perf tools: Use readdir() instead of deprecated readdir_r()
The readdir() function is thread safe as long as just one thread uses a
DIR, which is the case when synthesizing events for pre-existing threads
by traversing /proc, so, to avoid breaking the build with glibc-2.23.90
(upcoming 2.24), use it instead of readdir_r().
See: http://man7.org/linux/man-pages/man3/readdir.3.html
"However, in modern implementations (including the glibc implementation),
concurrent calls to readdir() that specify different directory streams
are thread-safe. In cases where multiple threads must read from the
same directory stream, using readdir() with external synchronization is
still preferable to the use of the deprecated readdir_r(3) function."
Noticed while building on a Fedora Rawhide docker container.
CC /tmp/build/perf/util/event.o
util/event.c: In function '__event__synthesize_thread':
util/event.c:466:2: error: 'readdir_r' is deprecated [-Werror=deprecated-declarations]
while (!readdir_r(tasks, &dirent, &next) && next) {
^~~~~
In file included from /usr/include/features.h:368:0,
from /usr/include/stdint.h:25,
from /usr/lib/gcc/x86_64-redhat-linux/6.0.0/include/stdint.h:9,
from /git/linux/tools/include/linux/types.h:6,
from util/event.c:1:
/usr/include/dirent.h:189:12: note: declared here
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-i1vj7nyjp2p750rirxgrfd3c@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-08 22:32:15 +08:00
|
|
|
while ((dirent = readdir(tasks)) != NULL) {
|
2014-02-26 23:45:26 +08:00
|
|
|
char *end;
|
|
|
|
pid_t _pid;
|
|
|
|
|
perf tools: Use readdir() instead of deprecated readdir_r()
The readdir() function is thread safe as long as just one thread uses a
DIR, which is the case when synthesizing events for pre-existing threads
by traversing /proc, so, to avoid breaking the build with glibc-2.23.90
(upcoming 2.24), use it instead of readdir_r().
See: http://man7.org/linux/man-pages/man3/readdir.3.html
"However, in modern implementations (including the glibc implementation),
concurrent calls to readdir() that specify different directory streams
are thread-safe. In cases where multiple threads must read from the
same directory stream, using readdir() with external synchronization is
still preferable to the use of the deprecated readdir_r(3) function."
Noticed while building on a Fedora Rawhide docker container.
CC /tmp/build/perf/util/event.o
util/event.c: In function '__event__synthesize_thread':
util/event.c:466:2: error: 'readdir_r' is deprecated [-Werror=deprecated-declarations]
while (!readdir_r(tasks, &dirent, &next) && next) {
^~~~~
In file included from /usr/include/features.h:368:0,
from /usr/include/stdint.h:25,
from /usr/lib/gcc/x86_64-redhat-linux/6.0.0/include/stdint.h:9,
from /git/linux/tools/include/linux/types.h:6,
from util/event.c:1:
/usr/include/dirent.h:189:12: note: declared here
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-i1vj7nyjp2p750rirxgrfd3c@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-08 22:32:15 +08:00
|
|
|
_pid = strtol(dirent->d_name, &end, 10);
|
2014-02-26 23:45:26 +08:00
|
|
|
if (*end)
|
|
|
|
continue;
|
|
|
|
|
2015-04-08 22:57:03 +08:00
|
|
|
rc = -1;
|
2015-03-31 04:35:58 +08:00
|
|
|
if (perf_event__prepare_comm(comm_event, _pid, machine,
|
|
|
|
&tgid, &ppid) != 0)
|
2015-04-08 22:57:03 +08:00
|
|
|
break;
|
2014-02-26 23:45:26 +08:00
|
|
|
|
perf tools: Fix FORK after COMM when synthesizing records for pre-existing threads
In this commit:
commit 363b785f3805a2632eb09a8b430842461c21a640
Author: Don Zickus <dzickus@redhat.com>
Date: Fri Mar 14 10:43:44 2014 -0400
perf tools: Speed up thread map generation
We ended up emitting PERF_RECORD_FORK events after their corresponding
PERF_RECORD_COMM, so the code below will remove the "existing thread"
and then recreates it, unnecessarily:
[root@ssdandy ~]# perf probe -x ~/bin/perf -L machine__process_fork_event
<machine__process_fork_event@/home/acme/git/linux/tools/perf/util/machine.c:0>
0 int machine__process_fork_event(struct machine *machine, union perf_event *event,
struct perf_sample *sample)
2 {
3 struct thread *thread = machine__find_thread(machine,
event->fork.pid,
event->fork.tid);
6 struct thread *parent = machine__findnew_thread(machine,
event->fork.ppid,
event->fork.ptid);
/* if a thread currently exists for the thread id remove it */
if (thread != NULL)
12 machine__remove_thread(machine, thread);
14 thread = machine__findnew_thread(machine, event->fork.pid,
event->fork.tid);
16 if (dump_trace)
17 perf_event__fprintf_task(event, stdout);
19 if (thread == NULL || parent == NULL ||
20 thread__fork(thread, parent, sample->time) < 0) {
21 dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n");
22 return -1;
}
25 return 0;
26 }
[root@ssdandy ~]# perf probe -x ~/bin/perf fork_after_comm=machine__process_fork_event:12
Added new event:
probe_perf:fork_after_comm (on machine__process_fork_event:12 in /home/acme/bin/perf)
You can now use it in all perf tools, such as:
perf record -e probe_perf:fork_after_comm -aR sleep 1
[root@ssdandy ~]#
[root@ssdandy ~]# perf record -g -e probe_perf:* trace -o /tmp/bla
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.021 MB perf.data (30 samples) ]
Terminated
[root@ssdandy ~]#
[root@ssdandy ~]# perf report --no-children --show-total-period --stdio
# To display the perf.data header info, please use --header/--header-only options.
#
# Samples: 30 of event 'probe_perf:fork_after_comm'
# Event count (approx.): 30
#
# Overhead Period Command Shared Object Symbol
# ........ ............ ....... ............. ...............................
#
100.00% 30 trace trace [.] machine__process_fork_event
|
---machine__process_fork_event
__event__synthesize_thread.part.2
perf_event__synthesize_threads
cmd_trace
main
__libc_start_main
[root@ssdandy ~]#
And Looking at 'perf report -D' output we see it:
0 0 0x8698 [0x30]: PERF_RECORD_COMM: auditd:703/707
0 0 0x86c8 [0x38]: PERF_RECORD_FORK(703:707):(703:703)
Fix it by more closely mimicking how the kernel generates those records
when a new fork happens, i.e. first a PERF_RECORD_FORK, then a
PERF_RECORD_COMM.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-h0emvymi2t3mw8dlqd6d6z73@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-28 06:52:10 +08:00
|
|
|
if (perf_event__synthesize_fork(tool, fork_event, _pid, tgid,
|
2015-03-31 04:35:58 +08:00
|
|
|
ppid, process, machine) < 0)
|
2015-04-08 22:57:03 +08:00
|
|
|
break;
|
2017-03-08 04:41:51 +08:00
|
|
|
|
|
|
|
if (perf_event__synthesize_namespaces(tool, namespaces_event, _pid,
|
|
|
|
tgid, process, machine) < 0)
|
|
|
|
break;
|
|
|
|
|
perf tools: Fix FORK after COMM when synthesizing records for pre-existing threads
In this commit:
commit 363b785f3805a2632eb09a8b430842461c21a640
Author: Don Zickus <dzickus@redhat.com>
Date: Fri Mar 14 10:43:44 2014 -0400
perf tools: Speed up thread map generation
We ended up emitting PERF_RECORD_FORK events after their corresponding
PERF_RECORD_COMM, so the code below will remove the "existing thread"
and then recreates it, unnecessarily:
[root@ssdandy ~]# perf probe -x ~/bin/perf -L machine__process_fork_event
<machine__process_fork_event@/home/acme/git/linux/tools/perf/util/machine.c:0>
0 int machine__process_fork_event(struct machine *machine, union perf_event *event,
struct perf_sample *sample)
2 {
3 struct thread *thread = machine__find_thread(machine,
event->fork.pid,
event->fork.tid);
6 struct thread *parent = machine__findnew_thread(machine,
event->fork.ppid,
event->fork.ptid);
/* if a thread currently exists for the thread id remove it */
if (thread != NULL)
12 machine__remove_thread(machine, thread);
14 thread = machine__findnew_thread(machine, event->fork.pid,
event->fork.tid);
16 if (dump_trace)
17 perf_event__fprintf_task(event, stdout);
19 if (thread == NULL || parent == NULL ||
20 thread__fork(thread, parent, sample->time) < 0) {
21 dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n");
22 return -1;
}
25 return 0;
26 }
[root@ssdandy ~]# perf probe -x ~/bin/perf fork_after_comm=machine__process_fork_event:12
Added new event:
probe_perf:fork_after_comm (on machine__process_fork_event:12 in /home/acme/bin/perf)
You can now use it in all perf tools, such as:
perf record -e probe_perf:fork_after_comm -aR sleep 1
[root@ssdandy ~]#
[root@ssdandy ~]# perf record -g -e probe_perf:* trace -o /tmp/bla
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.021 MB perf.data (30 samples) ]
Terminated
[root@ssdandy ~]#
[root@ssdandy ~]# perf report --no-children --show-total-period --stdio
# To display the perf.data header info, please use --header/--header-only options.
#
# Samples: 30 of event 'probe_perf:fork_after_comm'
# Event count (approx.): 30
#
# Overhead Period Command Shared Object Symbol
# ........ ............ ....... ............. ...............................
#
100.00% 30 trace trace [.] machine__process_fork_event
|
---machine__process_fork_event
__event__synthesize_thread.part.2
perf_event__synthesize_threads
cmd_trace
main
__libc_start_main
[root@ssdandy ~]#
And Looking at 'perf report -D' output we see it:
0 0 0x8698 [0x30]: PERF_RECORD_COMM: auditd:703/707
0 0 0x86c8 [0x38]: PERF_RECORD_FORK(703:707):(703:703)
Fix it by more closely mimicking how the kernel generates those records
when a new fork happens, i.e. first a PERF_RECORD_FORK, then a
PERF_RECORD_COMM.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-h0emvymi2t3mw8dlqd6d6z73@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-28 06:52:10 +08:00
|
|
|
/*
|
|
|
|
* Send the prepared comm event
|
|
|
|
*/
|
perf tools: Add missing initialization of perf_sample.cpumode in synthesized samples
In 473398a21d28 ("perf tools: Add cpumode to struct perf_sample"), I
missed some places where perf_sample fields are directly initialized in
addition to what is done in perf_evsel__parse_sample(), namely when
synthesizing PERF_RECORD_{MMAP*,COMM,FORK,EXIT} for pre-existing threads
and also in intel_pt and intel_bts when synthesizing events from
processor trace, the jitdump code also was affected, fix it.
The problem was noticed with running:
# perf record -e intel_pt//u true
# perf script
Where the samples wouldn't get resolved because perf_sample.cpumode
would be left as zero, i.e. PERF_RECORD_MISC_CPUMODE_UNKNOWN, not
resolving as kernel, hypervisor or user cpu modes.
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 473398a21d28 ("perf tools: Add cpumode to struct perf_sample")
Link: http://lkml.kernel.org/n/tip-n5sdauxgk24d5nun8kuuu2mh@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-03-30 05:46:04 +08:00
|
|
|
if (perf_tool__process_synth_event(tool, comm_event, machine, process) != 0)
|
2015-04-08 22:57:03 +08:00
|
|
|
break;
|
perf tools: Fix FORK after COMM when synthesizing records for pre-existing threads
In this commit:
commit 363b785f3805a2632eb09a8b430842461c21a640
Author: Don Zickus <dzickus@redhat.com>
Date: Fri Mar 14 10:43:44 2014 -0400
perf tools: Speed up thread map generation
We ended up emitting PERF_RECORD_FORK events after their corresponding
PERF_RECORD_COMM, so the code below will remove the "existing thread"
and then recreates it, unnecessarily:
[root@ssdandy ~]# perf probe -x ~/bin/perf -L machine__process_fork_event
<machine__process_fork_event@/home/acme/git/linux/tools/perf/util/machine.c:0>
0 int machine__process_fork_event(struct machine *machine, union perf_event *event,
struct perf_sample *sample)
2 {
3 struct thread *thread = machine__find_thread(machine,
event->fork.pid,
event->fork.tid);
6 struct thread *parent = machine__findnew_thread(machine,
event->fork.ppid,
event->fork.ptid);
/* if a thread currently exists for the thread id remove it */
if (thread != NULL)
12 machine__remove_thread(machine, thread);
14 thread = machine__findnew_thread(machine, event->fork.pid,
event->fork.tid);
16 if (dump_trace)
17 perf_event__fprintf_task(event, stdout);
19 if (thread == NULL || parent == NULL ||
20 thread__fork(thread, parent, sample->time) < 0) {
21 dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n");
22 return -1;
}
25 return 0;
26 }
[root@ssdandy ~]# perf probe -x ~/bin/perf fork_after_comm=machine__process_fork_event:12
Added new event:
probe_perf:fork_after_comm (on machine__process_fork_event:12 in /home/acme/bin/perf)
You can now use it in all perf tools, such as:
perf record -e probe_perf:fork_after_comm -aR sleep 1
[root@ssdandy ~]#
[root@ssdandy ~]# perf record -g -e probe_perf:* trace -o /tmp/bla
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.021 MB perf.data (30 samples) ]
Terminated
[root@ssdandy ~]#
[root@ssdandy ~]# perf report --no-children --show-total-period --stdio
# To display the perf.data header info, please use --header/--header-only options.
#
# Samples: 30 of event 'probe_perf:fork_after_comm'
# Event count (approx.): 30
#
# Overhead Period Command Shared Object Symbol
# ........ ............ ....... ............. ...............................
#
100.00% 30 trace trace [.] machine__process_fork_event
|
---machine__process_fork_event
__event__synthesize_thread.part.2
perf_event__synthesize_threads
cmd_trace
main
__libc_start_main
[root@ssdandy ~]#
And Looking at 'perf report -D' output we see it:
0 0 0x8698 [0x30]: PERF_RECORD_COMM: auditd:703/707
0 0 0x86c8 [0x38]: PERF_RECORD_FORK(703:707):(703:703)
Fix it by more closely mimicking how the kernel generates those records
when a new fork happens, i.e. first a PERF_RECORD_FORK, then a
PERF_RECORD_COMM.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-h0emvymi2t3mw8dlqd6d6z73@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-28 06:52:10 +08:00
|
|
|
|
2015-04-08 22:57:03 +08:00
|
|
|
rc = 0;
|
2014-03-14 22:43:44 +08:00
|
|
|
if (_pid == pid) {
|
|
|
|
/* process the parent's maps too */
|
|
|
|
rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
|
2018-12-05 04:34:20 +08:00
|
|
|
process, machine, mmap_data);
|
2015-04-08 22:57:03 +08:00
|
|
|
if (rc)
|
|
|
|
break;
|
2014-03-14 22:43:44 +08:00
|
|
|
}
|
2014-02-26 23:45:26 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
closedir(tasks);
|
2015-04-08 22:57:03 +08:00
|
|
|
return rc;
|
2009-10-27 05:23:18 +08:00
|
|
|
}
|
|
|
|
|
2011-11-28 18:30:20 +08:00
|
|
|
int perf_event__synthesize_thread_map(struct perf_tool *tool,
|
2019-07-21 19:23:50 +08:00
|
|
|
struct perf_thread_map *threads,
|
2011-02-11 21:45:54 +08:00
|
|
|
perf_event__handler_t process,
|
2013-11-11 20:44:09 +08:00
|
|
|
struct machine *machine,
|
2018-12-05 04:34:20 +08:00
|
|
|
bool mmap_data)
|
2010-12-02 20:25:28 +08:00
|
|
|
{
|
2014-03-14 22:43:44 +08:00
|
|
|
union perf_event *comm_event, *mmap_event, *fork_event;
|
2017-03-08 04:41:51 +08:00
|
|
|
union perf_event *namespaces_event;
|
2011-12-23 02:30:01 +08:00
|
|
|
int err = -1, thread, j;
|
2010-12-02 20:25:28 +08:00
|
|
|
|
2011-11-28 17:56:39 +08:00
|
|
|
comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size);
|
2010-12-02 20:25:28 +08:00
|
|
|
if (comm_event == NULL)
|
|
|
|
goto out;
|
|
|
|
|
2016-01-12 18:12:04 +08:00
|
|
|
mmap_event = malloc(sizeof(mmap_event->mmap2) + machine->id_hdr_size);
|
2010-12-02 20:25:28 +08:00
|
|
|
if (mmap_event == NULL)
|
|
|
|
goto out_free_comm;
|
|
|
|
|
2014-03-14 22:43:44 +08:00
|
|
|
fork_event = malloc(sizeof(fork_event->fork) + machine->id_hdr_size);
|
|
|
|
if (fork_event == NULL)
|
|
|
|
goto out_free_mmap;
|
|
|
|
|
2017-03-08 04:41:51 +08:00
|
|
|
namespaces_event = malloc(sizeof(namespaces_event->namespaces) +
|
|
|
|
(NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
|
|
|
|
machine->id_hdr_size);
|
|
|
|
if (namespaces_event == NULL)
|
|
|
|
goto out_free_fork;
|
|
|
|
|
2011-02-10 22:52:47 +08:00
|
|
|
err = 0;
|
|
|
|
for (thread = 0; thread < threads->nr; ++thread) {
|
|
|
|
if (__event__synthesize_thread(comm_event, mmap_event,
|
2017-03-08 04:41:51 +08:00
|
|
|
fork_event, namespaces_event,
|
2015-06-23 06:36:02 +08:00
|
|
|
thread_map__pid(threads, thread), 0,
|
2013-11-11 20:44:09 +08:00
|
|
|
process, tool, machine,
|
2018-12-05 04:34:20 +08:00
|
|
|
mmap_data)) {
|
2011-02-10 22:52:47 +08:00
|
|
|
err = -1;
|
|
|
|
break;
|
|
|
|
}
|
2011-12-23 02:30:01 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* comm.pid is set to thread group id by
|
|
|
|
* perf_event__synthesize_comm
|
|
|
|
*/
|
2015-06-23 06:36:02 +08:00
|
|
|
if ((int) comm_event->comm.pid != thread_map__pid(threads, thread)) {
|
2011-12-23 02:30:01 +08:00
|
|
|
bool need_leader = true;
|
|
|
|
|
|
|
|
/* is thread group leader in thread_map? */
|
|
|
|
for (j = 0; j < threads->nr; ++j) {
|
2015-06-23 06:36:02 +08:00
|
|
|
if ((int) comm_event->comm.pid == thread_map__pid(threads, j)) {
|
2011-12-23 02:30:01 +08:00
|
|
|
need_leader = false;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/* if not, generate events for it */
|
|
|
|
if (need_leader &&
|
2013-11-11 20:44:09 +08:00
|
|
|
__event__synthesize_thread(comm_event, mmap_event,
|
2017-03-08 04:41:51 +08:00
|
|
|
fork_event, namespaces_event,
|
2013-11-11 20:44:09 +08:00
|
|
|
comm_event->comm.pid, 0,
|
|
|
|
process, tool, machine,
|
2018-12-05 04:34:20 +08:00
|
|
|
mmap_data)) {
|
2011-12-23 02:30:01 +08:00
|
|
|
err = -1;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
2011-02-10 22:52:47 +08:00
|
|
|
}
|
2017-03-08 04:41:51 +08:00
|
|
|
free(namespaces_event);
|
|
|
|
out_free_fork:
|
2014-03-14 22:43:44 +08:00
|
|
|
free(fork_event);
|
|
|
|
out_free_mmap:
|
2010-12-02 20:25:28 +08:00
|
|
|
free(mmap_event);
|
|
|
|
out_free_comm:
|
|
|
|
free(comm_event);
|
|
|
|
out:
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
perf top: Implement multithreading for perf_event__synthesize_threads
The proc files which is sorted with alphabetical order are evenly
assigned to several synthesize threads to be processed in parallel.
For 'perf top', the threads number hard code to online CPU number. The
following patch will introduce an option to set it.
For other perf tools, the thread number is 1. Because the process
function is not ready for multithreading, e.g.
process_synthesized_event.
This patch series only support event synthesize multithreading for 'perf
top'. For other tools, it can be done separately later.
With multithread applied, the total processing time can get up to 1.56x
speedup on Knights Mill for 'perf top'.
For specific single event processing, the processing time could increase
because of the lock contention. So proc_map_timeout may need to be
increased. Otherwise some proc maps will be truncated.
Based on my test, increasing the proc_map_timeout has small impact
on the total processing time. The total processing time still get 1.49x
speedup on Knights Mill after increasing the proc_map_timeout.
The patch itself doesn't increase the proc_map_timeout.
Doesn't need to implement multithreading for per task monitoring,
perf_event__synthesize_thread_map. It doesn't have performance issue.
Committer testing:
# getconf _NPROCESSORS_ONLN
4
# perf trace --no-inherit -e clone -o /tmp/output perf top
# tail -4 /tmp/bla
0.124 ( 0.041 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3eb3a8f30, parent_tidptr: 0x7fc3eb3a99d0, child_tidptr: 0x7fc3eb3a99d0, tls: 0x7fc3eb3a9700) = 9548 (perf)
0.246 ( 0.023 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3eaba7f30, parent_tidptr: 0x7fc3eaba89d0, child_tidptr: 0x7fc3eaba89d0, tls: 0x7fc3eaba8700) = 9549 (perf)
0.286 ( 0.019 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3ea3a6f30, parent_tidptr: 0x7fc3ea3a79d0, child_tidptr: 0x7fc3ea3a79d0, tls: 0x7fc3ea3a7700) = 9550 (perf)
246.540 ( 0.047 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3ea3a6f30, parent_tidptr: 0x7fc3ea3a79d0, child_tidptr: 0x7fc3ea3a79d0, tls: 0x7fc3ea3a7700) = 9551 (perf)
#
Signed-off-by: Kan Liang <kan.liang@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Lukasz Odzioba <lukasz.odzioba@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1506696477-146932-4-git-send-email-kan.liang@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-09-29 22:47:54 +08:00
|
|
|
static int __perf_event__synthesize_threads(struct perf_tool *tool,
|
|
|
|
perf_event__handler_t process,
|
|
|
|
struct machine *machine,
|
|
|
|
bool mmap_data,
|
|
|
|
struct dirent **dirent,
|
|
|
|
int start,
|
|
|
|
int num)
|
2009-10-27 05:23:18 +08:00
|
|
|
{
|
2014-03-14 22:43:44 +08:00
|
|
|
union perf_event *comm_event, *mmap_event, *fork_event;
|
2017-03-08 04:41:51 +08:00
|
|
|
union perf_event *namespaces_event;
|
2010-12-02 20:25:28 +08:00
|
|
|
int err = -1;
|
2017-09-08 01:55:46 +08:00
|
|
|
char *end;
|
|
|
|
pid_t pid;
|
perf top: Implement multithreading for perf_event__synthesize_threads
The proc files which is sorted with alphabetical order are evenly
assigned to several synthesize threads to be processed in parallel.
For 'perf top', the threads number hard code to online CPU number. The
following patch will introduce an option to set it.
For other perf tools, the thread number is 1. Because the process
function is not ready for multithreading, e.g.
process_synthesized_event.
This patch series only support event synthesize multithreading for 'perf
top'. For other tools, it can be done separately later.
With multithread applied, the total processing time can get up to 1.56x
speedup on Knights Mill for 'perf top'.
For specific single event processing, the processing time could increase
because of the lock contention. So proc_map_timeout may need to be
increased. Otherwise some proc maps will be truncated.
Based on my test, increasing the proc_map_timeout has small impact
on the total processing time. The total processing time still get 1.49x
speedup on Knights Mill after increasing the proc_map_timeout.
The patch itself doesn't increase the proc_map_timeout.
Doesn't need to implement multithreading for per task monitoring,
perf_event__synthesize_thread_map. It doesn't have performance issue.
Committer testing:
# getconf _NPROCESSORS_ONLN
4
# perf trace --no-inherit -e clone -o /tmp/output perf top
# tail -4 /tmp/bla
0.124 ( 0.041 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3eb3a8f30, parent_tidptr: 0x7fc3eb3a99d0, child_tidptr: 0x7fc3eb3a99d0, tls: 0x7fc3eb3a9700) = 9548 (perf)
0.246 ( 0.023 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3eaba7f30, parent_tidptr: 0x7fc3eaba89d0, child_tidptr: 0x7fc3eaba89d0, tls: 0x7fc3eaba8700) = 9549 (perf)
0.286 ( 0.019 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3ea3a6f30, parent_tidptr: 0x7fc3ea3a79d0, child_tidptr: 0x7fc3ea3a79d0, tls: 0x7fc3ea3a7700) = 9550 (perf)
246.540 ( 0.047 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3ea3a6f30, parent_tidptr: 0x7fc3ea3a79d0, child_tidptr: 0x7fc3ea3a79d0, tls: 0x7fc3ea3a7700) = 9551 (perf)
#
Signed-off-by: Kan Liang <kan.liang@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Lukasz Odzioba <lukasz.odzioba@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1506696477-146932-4-git-send-email-kan.liang@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-09-29 22:47:54 +08:00
|
|
|
int i;
|
2014-03-17 09:45:49 +08:00
|
|
|
|
2011-11-28 17:56:39 +08:00
|
|
|
comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size);
|
2010-12-02 20:25:28 +08:00
|
|
|
if (comm_event == NULL)
|
|
|
|
goto out;
|
|
|
|
|
2016-01-12 18:12:04 +08:00
|
|
|
mmap_event = malloc(sizeof(mmap_event->mmap2) + machine->id_hdr_size);
|
2010-12-02 20:25:28 +08:00
|
|
|
if (mmap_event == NULL)
|
|
|
|
goto out_free_comm;
|
2009-10-27 05:23:18 +08:00
|
|
|
|
2014-03-14 22:43:44 +08:00
|
|
|
fork_event = malloc(sizeof(fork_event->fork) + machine->id_hdr_size);
|
|
|
|
if (fork_event == NULL)
|
|
|
|
goto out_free_mmap;
|
|
|
|
|
2017-03-08 04:41:51 +08:00
|
|
|
namespaces_event = malloc(sizeof(namespaces_event->namespaces) +
|
|
|
|
(NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
|
|
|
|
machine->id_hdr_size);
|
|
|
|
if (namespaces_event == NULL)
|
|
|
|
goto out_free_fork;
|
|
|
|
|
perf top: Implement multithreading for perf_event__synthesize_threads
The proc files which is sorted with alphabetical order are evenly
assigned to several synthesize threads to be processed in parallel.
For 'perf top', the threads number hard code to online CPU number. The
following patch will introduce an option to set it.
For other perf tools, the thread number is 1. Because the process
function is not ready for multithreading, e.g.
process_synthesized_event.
This patch series only support event synthesize multithreading for 'perf
top'. For other tools, it can be done separately later.
With multithread applied, the total processing time can get up to 1.56x
speedup on Knights Mill for 'perf top'.
For specific single event processing, the processing time could increase
because of the lock contention. So proc_map_timeout may need to be
increased. Otherwise some proc maps will be truncated.
Based on my test, increasing the proc_map_timeout has small impact
on the total processing time. The total processing time still get 1.49x
speedup on Knights Mill after increasing the proc_map_timeout.
The patch itself doesn't increase the proc_map_timeout.
Doesn't need to implement multithreading for per task monitoring,
perf_event__synthesize_thread_map. It doesn't have performance issue.
Committer testing:
# getconf _NPROCESSORS_ONLN
4
# perf trace --no-inherit -e clone -o /tmp/output perf top
# tail -4 /tmp/bla
0.124 ( 0.041 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3eb3a8f30, parent_tidptr: 0x7fc3eb3a99d0, child_tidptr: 0x7fc3eb3a99d0, tls: 0x7fc3eb3a9700) = 9548 (perf)
0.246 ( 0.023 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3eaba7f30, parent_tidptr: 0x7fc3eaba89d0, child_tidptr: 0x7fc3eaba89d0, tls: 0x7fc3eaba8700) = 9549 (perf)
0.286 ( 0.019 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3ea3a6f30, parent_tidptr: 0x7fc3ea3a79d0, child_tidptr: 0x7fc3ea3a79d0, tls: 0x7fc3ea3a7700) = 9550 (perf)
246.540 ( 0.047 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3ea3a6f30, parent_tidptr: 0x7fc3ea3a79d0, child_tidptr: 0x7fc3ea3a79d0, tls: 0x7fc3ea3a7700) = 9551 (perf)
#
Signed-off-by: Kan Liang <kan.liang@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Lukasz Odzioba <lukasz.odzioba@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1506696477-146932-4-git-send-email-kan.liang@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-09-29 22:47:54 +08:00
|
|
|
for (i = start; i < start + num; i++) {
|
2017-09-08 01:55:46 +08:00
|
|
|
if (!isdigit(dirent[i]->d_name[0]))
|
2009-10-27 05:23:18 +08:00
|
|
|
continue;
|
|
|
|
|
2017-09-08 01:55:46 +08:00
|
|
|
pid = (pid_t)strtol(dirent[i]->d_name, &end, 10);
|
|
|
|
/* only interested in proper numerical dirents */
|
perf top: Implement multithreading for perf_event__synthesize_threads
The proc files which is sorted with alphabetical order are evenly
assigned to several synthesize threads to be processed in parallel.
For 'perf top', the threads number hard code to online CPU number. The
following patch will introduce an option to set it.
For other perf tools, the thread number is 1. Because the process
function is not ready for multithreading, e.g.
process_synthesized_event.
This patch series only support event synthesize multithreading for 'perf
top'. For other tools, it can be done separately later.
With multithread applied, the total processing time can get up to 1.56x
speedup on Knights Mill for 'perf top'.
For specific single event processing, the processing time could increase
because of the lock contention. So proc_map_timeout may need to be
increased. Otherwise some proc maps will be truncated.
Based on my test, increasing the proc_map_timeout has small impact
on the total processing time. The total processing time still get 1.49x
speedup on Knights Mill after increasing the proc_map_timeout.
The patch itself doesn't increase the proc_map_timeout.
Doesn't need to implement multithreading for per task monitoring,
perf_event__synthesize_thread_map. It doesn't have performance issue.
Committer testing:
# getconf _NPROCESSORS_ONLN
4
# perf trace --no-inherit -e clone -o /tmp/output perf top
# tail -4 /tmp/bla
0.124 ( 0.041 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3eb3a8f30, parent_tidptr: 0x7fc3eb3a99d0, child_tidptr: 0x7fc3eb3a99d0, tls: 0x7fc3eb3a9700) = 9548 (perf)
0.246 ( 0.023 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3eaba7f30, parent_tidptr: 0x7fc3eaba89d0, child_tidptr: 0x7fc3eaba89d0, tls: 0x7fc3eaba8700) = 9549 (perf)
0.286 ( 0.019 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3ea3a6f30, parent_tidptr: 0x7fc3ea3a79d0, child_tidptr: 0x7fc3ea3a79d0, tls: 0x7fc3ea3a7700) = 9550 (perf)
246.540 ( 0.047 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3ea3a6f30, parent_tidptr: 0x7fc3ea3a79d0, child_tidptr: 0x7fc3ea3a79d0, tls: 0x7fc3ea3a7700) = 9551 (perf)
#
Signed-off-by: Kan Liang <kan.liang@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Lukasz Odzioba <lukasz.odzioba@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1506696477-146932-4-git-send-email-kan.liang@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-09-29 22:47:54 +08:00
|
|
|
if (*end)
|
|
|
|
continue;
|
|
|
|
/*
|
|
|
|
* We may race with exiting thread, so don't stop just because
|
|
|
|
* one thread couldn't be synthesized.
|
|
|
|
*/
|
|
|
|
__event__synthesize_thread(comm_event, mmap_event, fork_event,
|
|
|
|
namespaces_event, pid, 1, process,
|
2018-12-05 04:34:20 +08:00
|
|
|
tool, machine, mmap_data);
|
2017-09-08 01:55:46 +08:00
|
|
|
}
|
2010-12-02 20:25:28 +08:00
|
|
|
err = 0;
|
2017-09-08 01:55:46 +08:00
|
|
|
|
2017-03-08 04:41:51 +08:00
|
|
|
free(namespaces_event);
|
2014-03-14 22:43:44 +08:00
|
|
|
out_free_fork:
|
|
|
|
free(fork_event);
|
2010-12-02 20:25:28 +08:00
|
|
|
out_free_mmap:
|
|
|
|
free(mmap_event);
|
|
|
|
out_free_comm:
|
|
|
|
free(comm_event);
|
|
|
|
out:
|
|
|
|
return err;
|
2009-10-27 05:23:18 +08:00
|
|
|
}
|
2009-11-28 02:29:22 +08:00
|
|
|
|
perf top: Implement multithreading for perf_event__synthesize_threads
The proc files which is sorted with alphabetical order are evenly
assigned to several synthesize threads to be processed in parallel.
For 'perf top', the threads number hard code to online CPU number. The
following patch will introduce an option to set it.
For other perf tools, the thread number is 1. Because the process
function is not ready for multithreading, e.g.
process_synthesized_event.
This patch series only support event synthesize multithreading for 'perf
top'. For other tools, it can be done separately later.
With multithread applied, the total processing time can get up to 1.56x
speedup on Knights Mill for 'perf top'.
For specific single event processing, the processing time could increase
because of the lock contention. So proc_map_timeout may need to be
increased. Otherwise some proc maps will be truncated.
Based on my test, increasing the proc_map_timeout has small impact
on the total processing time. The total processing time still get 1.49x
speedup on Knights Mill after increasing the proc_map_timeout.
The patch itself doesn't increase the proc_map_timeout.
Doesn't need to implement multithreading for per task monitoring,
perf_event__synthesize_thread_map. It doesn't have performance issue.
Committer testing:
# getconf _NPROCESSORS_ONLN
4
# perf trace --no-inherit -e clone -o /tmp/output perf top
# tail -4 /tmp/bla
0.124 ( 0.041 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3eb3a8f30, parent_tidptr: 0x7fc3eb3a99d0, child_tidptr: 0x7fc3eb3a99d0, tls: 0x7fc3eb3a9700) = 9548 (perf)
0.246 ( 0.023 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3eaba7f30, parent_tidptr: 0x7fc3eaba89d0, child_tidptr: 0x7fc3eaba89d0, tls: 0x7fc3eaba8700) = 9549 (perf)
0.286 ( 0.019 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3ea3a6f30, parent_tidptr: 0x7fc3ea3a79d0, child_tidptr: 0x7fc3ea3a79d0, tls: 0x7fc3ea3a7700) = 9550 (perf)
246.540 ( 0.047 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3ea3a6f30, parent_tidptr: 0x7fc3ea3a79d0, child_tidptr: 0x7fc3ea3a79d0, tls: 0x7fc3ea3a7700) = 9551 (perf)
#
Signed-off-by: Kan Liang <kan.liang@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Lukasz Odzioba <lukasz.odzioba@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1506696477-146932-4-git-send-email-kan.liang@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-09-29 22:47:54 +08:00
|
|
|
struct synthesize_threads_arg {
|
|
|
|
struct perf_tool *tool;
|
|
|
|
perf_event__handler_t process;
|
|
|
|
struct machine *machine;
|
|
|
|
bool mmap_data;
|
|
|
|
struct dirent **dirent;
|
|
|
|
int num;
|
|
|
|
int start;
|
|
|
|
};
|
|
|
|
|
|
|
|
static void *synthesize_threads_worker(void *arg)
|
|
|
|
{
|
|
|
|
struct synthesize_threads_arg *args = arg;
|
|
|
|
|
|
|
|
__perf_event__synthesize_threads(args->tool, args->process,
|
|
|
|
args->machine, args->mmap_data,
|
2018-12-05 04:34:20 +08:00
|
|
|
args->dirent,
|
perf top: Implement multithreading for perf_event__synthesize_threads
The proc files which is sorted with alphabetical order are evenly
assigned to several synthesize threads to be processed in parallel.
For 'perf top', the threads number hard code to online CPU number. The
following patch will introduce an option to set it.
For other perf tools, the thread number is 1. Because the process
function is not ready for multithreading, e.g.
process_synthesized_event.
This patch series only support event synthesize multithreading for 'perf
top'. For other tools, it can be done separately later.
With multithread applied, the total processing time can get up to 1.56x
speedup on Knights Mill for 'perf top'.
For specific single event processing, the processing time could increase
because of the lock contention. So proc_map_timeout may need to be
increased. Otherwise some proc maps will be truncated.
Based on my test, increasing the proc_map_timeout has small impact
on the total processing time. The total processing time still get 1.49x
speedup on Knights Mill after increasing the proc_map_timeout.
The patch itself doesn't increase the proc_map_timeout.
Doesn't need to implement multithreading for per task monitoring,
perf_event__synthesize_thread_map. It doesn't have performance issue.
Committer testing:
# getconf _NPROCESSORS_ONLN
4
# perf trace --no-inherit -e clone -o /tmp/output perf top
# tail -4 /tmp/bla
0.124 ( 0.041 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3eb3a8f30, parent_tidptr: 0x7fc3eb3a99d0, child_tidptr: 0x7fc3eb3a99d0, tls: 0x7fc3eb3a9700) = 9548 (perf)
0.246 ( 0.023 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3eaba7f30, parent_tidptr: 0x7fc3eaba89d0, child_tidptr: 0x7fc3eaba89d0, tls: 0x7fc3eaba8700) = 9549 (perf)
0.286 ( 0.019 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3ea3a6f30, parent_tidptr: 0x7fc3ea3a79d0, child_tidptr: 0x7fc3ea3a79d0, tls: 0x7fc3ea3a7700) = 9550 (perf)
246.540 ( 0.047 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3ea3a6f30, parent_tidptr: 0x7fc3ea3a79d0, child_tidptr: 0x7fc3ea3a79d0, tls: 0x7fc3ea3a7700) = 9551 (perf)
#
Signed-off-by: Kan Liang <kan.liang@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Lukasz Odzioba <lukasz.odzioba@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1506696477-146932-4-git-send-email-kan.liang@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-09-29 22:47:54 +08:00
|
|
|
args->start, args->num);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
int perf_event__synthesize_threads(struct perf_tool *tool,
|
|
|
|
perf_event__handler_t process,
|
|
|
|
struct machine *machine,
|
|
|
|
bool mmap_data,
|
|
|
|
unsigned int nr_threads_synthesize)
|
|
|
|
{
|
|
|
|
struct synthesize_threads_arg *args = NULL;
|
|
|
|
pthread_t *synthesize_threads = NULL;
|
|
|
|
char proc_path[PATH_MAX];
|
|
|
|
struct dirent **dirent;
|
|
|
|
int num_per_thread;
|
|
|
|
int m, n, i, j;
|
|
|
|
int thread_nr;
|
|
|
|
int base = 0;
|
|
|
|
int err = -1;
|
|
|
|
|
|
|
|
|
|
|
|
if (machine__is_default_guest(machine))
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir);
|
|
|
|
n = scandir(proc_path, &dirent, 0, alphasort);
|
|
|
|
if (n < 0)
|
|
|
|
return err;
|
|
|
|
|
perf top: Add option to set the number of thread for event synthesize
Using UINT_MAX to indicate the default thread#, which is the max number
of online CPU.
Committer testing:
# perf trace --no-inherit -e clone -o /tmp/output perf top --num-thread-synthesize 9
# cat /tmp/output
? ( ? ): ... [continued]: clone()) = 26651 (perf)
0.059 ( 0.010 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7f5bfac44f30, parent_tidptr: 0x7f5bfac459d0, child_tidptr: 0x7f5bfac459d0, tls: 0x7f5bfac45700) = 26652 (perf)
0.116 ( 0.014 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7f5bfa443f30, parent_tidptr: 0x7f5bfa4449d0, child_tidptr: 0x7f5bfa4449d0, tls: 0x7f5bfa444700) = 26653 (perf)
0.141 ( 0.009 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7f5bf9c42f30, parent_tidptr: 0x7f5bf9c439d0, child_tidptr: 0x7f5bf9c439d0, tls: 0x7f5bf9c43700) = 26654 (perf)
0.160 ( 0.012 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7f5bf9441f30, parent_tidptr: 0x7f5bf94429d0, child_tidptr: 0x7f5bf94429d0, tls: 0x7f5bf9442700) = 26655 (perf)
0.232 ( 0.013 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7f5bf8c40f30, parent_tidptr: 0x7f5bf8c419d0, child_tidptr: 0x7f5bf8c419d0, tls: 0x7f5bf8c41700) = 26656 (perf)
0.393 ( 0.011 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7f5be3ffef30, parent_tidptr: 0x7f5be3fff9d0, child_tidptr: 0x7f5be3fff9d0, tls: 0x7f5be3fff700) = 26657 (perf)
0.802 ( 0.012 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7f5be37fdf30, parent_tidptr: 0x7f5be37fe9d0, child_tidptr: 0x7f5be37fe9d0, tls: 0x7f5be37fe700) = 26658 (perf)
1.411 ( 0.022 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7f5be2ffcf30, parent_tidptr: 0x7f5be2ffd9d0, child_tidptr: 0x7f5be2ffd9d0, tls: 0x7f5be2ffd700) = 26659 (perf)
246.422 ( 0.042 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7f5be2ffcf30, parent_tidptr: 0x7f5be2ffd9d0, child_tidptr: 0x7f5be2ffd9d0, tls: 0x7f5be2ffd700) = 26660 (perf)
#
Signed-off-by: Kan Liang <kan.liang@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Lukasz Odzioba <lukasz.odzioba@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1506696477-146932-5-git-send-email-kan.liang@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-09-29 22:47:55 +08:00
|
|
|
if (nr_threads_synthesize == UINT_MAX)
|
|
|
|
thread_nr = sysconf(_SC_NPROCESSORS_ONLN);
|
|
|
|
else
|
|
|
|
thread_nr = nr_threads_synthesize;
|
perf top: Implement multithreading for perf_event__synthesize_threads
The proc files which is sorted with alphabetical order are evenly
assigned to several synthesize threads to be processed in parallel.
For 'perf top', the threads number hard code to online CPU number. The
following patch will introduce an option to set it.
For other perf tools, the thread number is 1. Because the process
function is not ready for multithreading, e.g.
process_synthesized_event.
This patch series only support event synthesize multithreading for 'perf
top'. For other tools, it can be done separately later.
With multithread applied, the total processing time can get up to 1.56x
speedup on Knights Mill for 'perf top'.
For specific single event processing, the processing time could increase
because of the lock contention. So proc_map_timeout may need to be
increased. Otherwise some proc maps will be truncated.
Based on my test, increasing the proc_map_timeout has small impact
on the total processing time. The total processing time still get 1.49x
speedup on Knights Mill after increasing the proc_map_timeout.
The patch itself doesn't increase the proc_map_timeout.
Doesn't need to implement multithreading for per task monitoring,
perf_event__synthesize_thread_map. It doesn't have performance issue.
Committer testing:
# getconf _NPROCESSORS_ONLN
4
# perf trace --no-inherit -e clone -o /tmp/output perf top
# tail -4 /tmp/bla
0.124 ( 0.041 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3eb3a8f30, parent_tidptr: 0x7fc3eb3a99d0, child_tidptr: 0x7fc3eb3a99d0, tls: 0x7fc3eb3a9700) = 9548 (perf)
0.246 ( 0.023 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3eaba7f30, parent_tidptr: 0x7fc3eaba89d0, child_tidptr: 0x7fc3eaba89d0, tls: 0x7fc3eaba8700) = 9549 (perf)
0.286 ( 0.019 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3ea3a6f30, parent_tidptr: 0x7fc3ea3a79d0, child_tidptr: 0x7fc3ea3a79d0, tls: 0x7fc3ea3a7700) = 9550 (perf)
246.540 ( 0.047 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3ea3a6f30, parent_tidptr: 0x7fc3ea3a79d0, child_tidptr: 0x7fc3ea3a79d0, tls: 0x7fc3ea3a7700) = 9551 (perf)
#
Signed-off-by: Kan Liang <kan.liang@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Lukasz Odzioba <lukasz.odzioba@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1506696477-146932-4-git-send-email-kan.liang@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-09-29 22:47:54 +08:00
|
|
|
|
|
|
|
if (thread_nr <= 1) {
|
|
|
|
err = __perf_event__synthesize_threads(tool, process,
|
|
|
|
machine, mmap_data,
|
|
|
|
dirent, base, n);
|
|
|
|
goto free_dirent;
|
|
|
|
}
|
|
|
|
if (thread_nr > n)
|
|
|
|
thread_nr = n;
|
|
|
|
|
|
|
|
synthesize_threads = calloc(sizeof(pthread_t), thread_nr);
|
|
|
|
if (synthesize_threads == NULL)
|
|
|
|
goto free_dirent;
|
|
|
|
|
|
|
|
args = calloc(sizeof(*args), thread_nr);
|
|
|
|
if (args == NULL)
|
|
|
|
goto free_threads;
|
|
|
|
|
|
|
|
num_per_thread = n / thread_nr;
|
|
|
|
m = n % thread_nr;
|
|
|
|
for (i = 0; i < thread_nr; i++) {
|
|
|
|
args[i].tool = tool;
|
|
|
|
args[i].process = process;
|
|
|
|
args[i].machine = machine;
|
|
|
|
args[i].mmap_data = mmap_data;
|
|
|
|
args[i].dirent = dirent;
|
|
|
|
}
|
|
|
|
for (i = 0; i < m; i++) {
|
|
|
|
args[i].num = num_per_thread + 1;
|
|
|
|
args[i].start = i * args[i].num;
|
|
|
|
}
|
|
|
|
if (i != 0)
|
|
|
|
base = args[i-1].start + args[i-1].num;
|
|
|
|
for (j = i; j < thread_nr; j++) {
|
|
|
|
args[j].num = num_per_thread;
|
|
|
|
args[j].start = base + (j - i) * args[i].num;
|
|
|
|
}
|
|
|
|
|
|
|
|
for (i = 0; i < thread_nr; i++) {
|
|
|
|
if (pthread_create(&synthesize_threads[i], NULL,
|
|
|
|
synthesize_threads_worker, &args[i]))
|
|
|
|
goto out_join;
|
|
|
|
}
|
|
|
|
err = 0;
|
|
|
|
out_join:
|
|
|
|
for (i = 0; i < thread_nr; i++)
|
|
|
|
pthread_join(synthesize_threads[i], NULL);
|
|
|
|
free(args);
|
|
|
|
free_threads:
|
|
|
|
free(synthesize_threads);
|
|
|
|
free_dirent:
|
|
|
|
for (i = 0; i < n; i++)
|
2019-07-04 23:06:20 +08:00
|
|
|
zfree(&dirent[i]);
|
perf top: Implement multithreading for perf_event__synthesize_threads
The proc files which is sorted with alphabetical order are evenly
assigned to several synthesize threads to be processed in parallel.
For 'perf top', the threads number hard code to online CPU number. The
following patch will introduce an option to set it.
For other perf tools, the thread number is 1. Because the process
function is not ready for multithreading, e.g.
process_synthesized_event.
This patch series only support event synthesize multithreading for 'perf
top'. For other tools, it can be done separately later.
With multithread applied, the total processing time can get up to 1.56x
speedup on Knights Mill for 'perf top'.
For specific single event processing, the processing time could increase
because of the lock contention. So proc_map_timeout may need to be
increased. Otherwise some proc maps will be truncated.
Based on my test, increasing the proc_map_timeout has small impact
on the total processing time. The total processing time still get 1.49x
speedup on Knights Mill after increasing the proc_map_timeout.
The patch itself doesn't increase the proc_map_timeout.
Doesn't need to implement multithreading for per task monitoring,
perf_event__synthesize_thread_map. It doesn't have performance issue.
Committer testing:
# getconf _NPROCESSORS_ONLN
4
# perf trace --no-inherit -e clone -o /tmp/output perf top
# tail -4 /tmp/bla
0.124 ( 0.041 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3eb3a8f30, parent_tidptr: 0x7fc3eb3a99d0, child_tidptr: 0x7fc3eb3a99d0, tls: 0x7fc3eb3a9700) = 9548 (perf)
0.246 ( 0.023 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3eaba7f30, parent_tidptr: 0x7fc3eaba89d0, child_tidptr: 0x7fc3eaba89d0, tls: 0x7fc3eaba8700) = 9549 (perf)
0.286 ( 0.019 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3ea3a6f30, parent_tidptr: 0x7fc3ea3a79d0, child_tidptr: 0x7fc3ea3a79d0, tls: 0x7fc3ea3a7700) = 9550 (perf)
246.540 ( 0.047 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3ea3a6f30, parent_tidptr: 0x7fc3ea3a79d0, child_tidptr: 0x7fc3ea3a79d0, tls: 0x7fc3ea3a7700) = 9551 (perf)
#
Signed-off-by: Kan Liang <kan.liang@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Lukasz Odzioba <lukasz.odzioba@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1506696477-146932-4-git-send-email-kan.liang@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-09-29 22:47:54 +08:00
|
|
|
free(dirent);
|
|
|
|
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2010-01-06 02:50:31 +08:00
|
|
|
struct process_symbol_args {
|
|
|
|
const char *name;
|
|
|
|
u64 start;
|
|
|
|
};
|
|
|
|
|
2010-12-22 11:08:36 +08:00
|
|
|
static int find_symbol_cb(void *arg, const char *name, char type,
|
2012-08-11 06:22:48 +08:00
|
|
|
u64 start)
|
2010-01-06 02:50:31 +08:00
|
|
|
{
|
|
|
|
struct process_symbol_args *args = arg;
|
|
|
|
|
2010-01-16 04:08:27 +08:00
|
|
|
/*
|
|
|
|
* Must be a function or at least an alias, as in PARISC64, where "_text" is
|
|
|
|
* an 'A' to the same address as "_stext".
|
|
|
|
*/
|
2018-04-26 04:16:31 +08:00
|
|
|
if (!(kallsyms__is_function(type) ||
|
2010-01-16 04:08:27 +08:00
|
|
|
type == 'A') || strcmp(name, args->name))
|
2010-01-06 02:50:31 +08:00
|
|
|
return 0;
|
|
|
|
|
|
|
|
args->start = start;
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
perf symbols: Accept symbols starting at address 0
That is the case of _text on s390, and we have some functions that return an
address, using address zero to report problems, oops.
This would lead the symbol loading routines to not use "_text" as the reference
relocation symbol, or the first symbol for the kernel, but use instead
"_stext", that is at the same address on x86_64 and others, but not on s390:
[acme@localhost perf-4.11.0-rc6]$ head -15 /proc/kallsyms
0000000000000000 T _text
0000000000000418 t iplstart
0000000000000800 T start
000000000000080a t .base
000000000000082e t .sk8x8
0000000000000834 t .gotr
0000000000000842 t .cmd
0000000000000846 t .parm
000000000000084a t .lowcase
0000000000010000 T startup
0000000000010010 T startup_kdump
0000000000010214 t startup_kdump_relocated
0000000000011000 T startup_continue
00000000000112a0 T _ehead
0000000000100000 T _stext
[acme@localhost perf-4.11.0-rc6]$
Which in turn would make 'perf test vmlinux' to fail because it wouldn't find
the symbols before "_stext" in kallsyms.
Fix it by using the return value only for errors and storing the
address, when the symbol is successfully found, in a provided pointer
arg.
Before this patch:
After:
[acme@localhost perf-4.11.0-rc6]$ tools/perf/perf test -v 1
1: vmlinux symtab matches kallsyms :
--- start ---
test child forked, pid 40693
Looking at the vmlinux_path (8 entries long)
Using /usr/lib/debug/lib/modules/3.10.0-654.el7.s390x/vmlinux for symbols
ERR : 0: _text not on kallsyms
ERR : 0x418: iplstart not on kallsyms
ERR : 0x800: start not on kallsyms
ERR : 0x80a: .base not on kallsyms
ERR : 0x82e: .sk8x8 not on kallsyms
ERR : 0x834: .gotr not on kallsyms
ERR : 0x842: .cmd not on kallsyms
ERR : 0x846: .parm not on kallsyms
ERR : 0x84a: .lowcase not on kallsyms
ERR : 0x10000: startup not on kallsyms
ERR : 0x10010: startup_kdump not on kallsyms
ERR : 0x10214: startup_kdump_relocated not on kallsyms
ERR : 0x11000: startup_continue not on kallsyms
ERR : 0x112a0: _ehead not on kallsyms
<SNIP warnings>
test child finished with -1
---- end ----
vmlinux symtab matches kallsyms: FAILED!
[acme@localhost perf-4.11.0-rc6]$
After:
[acme@localhost perf-4.11.0-rc6]$ tools/perf/perf test -v 1
1: vmlinux symtab matches kallsyms :
--- start ---
test child forked, pid 47160
<SNIP warnings>
test child finished with 0
---- end ----
vmlinux symtab matches kallsyms: Ok
[acme@localhost perf-4.11.0-rc6]$
Reported-by: Michael Petlan <mpetlan@redhat.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/n/tip-9x9bwgd3btwdk1u51xie93fz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-04-28 08:21:09 +08:00
|
|
|
int kallsyms__get_function_start(const char *kallsyms_filename,
|
|
|
|
const char *symbol_name, u64 *addr)
|
2014-01-29 22:14:37 +08:00
|
|
|
{
|
|
|
|
struct process_symbol_args args = { .name = symbol_name, };
|
|
|
|
|
|
|
|
if (kallsyms__parse(kallsyms_filename, &args, find_symbol_cb) <= 0)
|
perf symbols: Accept symbols starting at address 0
That is the case of _text on s390, and we have some functions that return an
address, using address zero to report problems, oops.
This would lead the symbol loading routines to not use "_text" as the reference
relocation symbol, or the first symbol for the kernel, but use instead
"_stext", that is at the same address on x86_64 and others, but not on s390:
[acme@localhost perf-4.11.0-rc6]$ head -15 /proc/kallsyms
0000000000000000 T _text
0000000000000418 t iplstart
0000000000000800 T start
000000000000080a t .base
000000000000082e t .sk8x8
0000000000000834 t .gotr
0000000000000842 t .cmd
0000000000000846 t .parm
000000000000084a t .lowcase
0000000000010000 T startup
0000000000010010 T startup_kdump
0000000000010214 t startup_kdump_relocated
0000000000011000 T startup_continue
00000000000112a0 T _ehead
0000000000100000 T _stext
[acme@localhost perf-4.11.0-rc6]$
Which in turn would make 'perf test vmlinux' to fail because it wouldn't find
the symbols before "_stext" in kallsyms.
Fix it by using the return value only for errors and storing the
address, when the symbol is successfully found, in a provided pointer
arg.
Before this patch:
After:
[acme@localhost perf-4.11.0-rc6]$ tools/perf/perf test -v 1
1: vmlinux symtab matches kallsyms :
--- start ---
test child forked, pid 40693
Looking at the vmlinux_path (8 entries long)
Using /usr/lib/debug/lib/modules/3.10.0-654.el7.s390x/vmlinux for symbols
ERR : 0: _text not on kallsyms
ERR : 0x418: iplstart not on kallsyms
ERR : 0x800: start not on kallsyms
ERR : 0x80a: .base not on kallsyms
ERR : 0x82e: .sk8x8 not on kallsyms
ERR : 0x834: .gotr not on kallsyms
ERR : 0x842: .cmd not on kallsyms
ERR : 0x846: .parm not on kallsyms
ERR : 0x84a: .lowcase not on kallsyms
ERR : 0x10000: startup not on kallsyms
ERR : 0x10010: startup_kdump not on kallsyms
ERR : 0x10214: startup_kdump_relocated not on kallsyms
ERR : 0x11000: startup_continue not on kallsyms
ERR : 0x112a0: _ehead not on kallsyms
<SNIP warnings>
test child finished with -1
---- end ----
vmlinux symtab matches kallsyms: FAILED!
[acme@localhost perf-4.11.0-rc6]$
After:
[acme@localhost perf-4.11.0-rc6]$ tools/perf/perf test -v 1
1: vmlinux symtab matches kallsyms :
--- start ---
test child forked, pid 47160
<SNIP warnings>
test child finished with 0
---- end ----
vmlinux symtab matches kallsyms: Ok
[acme@localhost perf-4.11.0-rc6]$
Reported-by: Michael Petlan <mpetlan@redhat.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/n/tip-9x9bwgd3btwdk1u51xie93fz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-04-28 08:21:09 +08:00
|
|
|
return -1;
|
2014-01-29 22:14:37 +08:00
|
|
|
|
perf symbols: Accept symbols starting at address 0
That is the case of _text on s390, and we have some functions that return an
address, using address zero to report problems, oops.
This would lead the symbol loading routines to not use "_text" as the reference
relocation symbol, or the first symbol for the kernel, but use instead
"_stext", that is at the same address on x86_64 and others, but not on s390:
[acme@localhost perf-4.11.0-rc6]$ head -15 /proc/kallsyms
0000000000000000 T _text
0000000000000418 t iplstart
0000000000000800 T start
000000000000080a t .base
000000000000082e t .sk8x8
0000000000000834 t .gotr
0000000000000842 t .cmd
0000000000000846 t .parm
000000000000084a t .lowcase
0000000000010000 T startup
0000000000010010 T startup_kdump
0000000000010214 t startup_kdump_relocated
0000000000011000 T startup_continue
00000000000112a0 T _ehead
0000000000100000 T _stext
[acme@localhost perf-4.11.0-rc6]$
Which in turn would make 'perf test vmlinux' to fail because it wouldn't find
the symbols before "_stext" in kallsyms.
Fix it by using the return value only for errors and storing the
address, when the symbol is successfully found, in a provided pointer
arg.
Before this patch:
After:
[acme@localhost perf-4.11.0-rc6]$ tools/perf/perf test -v 1
1: vmlinux symtab matches kallsyms :
--- start ---
test child forked, pid 40693
Looking at the vmlinux_path (8 entries long)
Using /usr/lib/debug/lib/modules/3.10.0-654.el7.s390x/vmlinux for symbols
ERR : 0: _text not on kallsyms
ERR : 0x418: iplstart not on kallsyms
ERR : 0x800: start not on kallsyms
ERR : 0x80a: .base not on kallsyms
ERR : 0x82e: .sk8x8 not on kallsyms
ERR : 0x834: .gotr not on kallsyms
ERR : 0x842: .cmd not on kallsyms
ERR : 0x846: .parm not on kallsyms
ERR : 0x84a: .lowcase not on kallsyms
ERR : 0x10000: startup not on kallsyms
ERR : 0x10010: startup_kdump not on kallsyms
ERR : 0x10214: startup_kdump_relocated not on kallsyms
ERR : 0x11000: startup_continue not on kallsyms
ERR : 0x112a0: _ehead not on kallsyms
<SNIP warnings>
test child finished with -1
---- end ----
vmlinux symtab matches kallsyms: FAILED!
[acme@localhost perf-4.11.0-rc6]$
After:
[acme@localhost perf-4.11.0-rc6]$ tools/perf/perf test -v 1
1: vmlinux symtab matches kallsyms :
--- start ---
test child forked, pid 47160
<SNIP warnings>
test child finished with 0
---- end ----
vmlinux symtab matches kallsyms: Ok
[acme@localhost perf-4.11.0-rc6]$
Reported-by: Michael Petlan <mpetlan@redhat.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/n/tip-9x9bwgd3btwdk1u51xie93fz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-04-28 08:21:09 +08:00
|
|
|
*addr = args.start;
|
|
|
|
return 0;
|
2014-01-29 22:14:37 +08:00
|
|
|
}
|
|
|
|
|
2018-05-22 18:54:37 +08:00
|
|
|
int __weak perf_event__synthesize_extra_kmaps(struct perf_tool *tool __maybe_unused,
|
|
|
|
perf_event__handler_t process __maybe_unused,
|
|
|
|
struct machine *machine __maybe_unused)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int __perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
|
|
|
|
perf_event__handler_t process,
|
|
|
|
struct machine *machine)
|
2010-01-06 02:50:31 +08:00
|
|
|
{
|
|
|
|
size_t size;
|
2015-09-30 22:54:04 +08:00
|
|
|
struct map *map = machine__kernel_map(machine);
|
2014-01-29 22:14:40 +08:00
|
|
|
struct kmap *kmap;
|
2010-12-02 20:25:28 +08:00
|
|
|
int err;
|
2014-09-25 05:39:54 +08:00
|
|
|
union perf_event *event;
|
|
|
|
|
2016-05-24 17:21:28 +08:00
|
|
|
if (symbol_conf.kptr_restrict)
|
|
|
|
return -1;
|
2015-09-30 22:08:58 +08:00
|
|
|
if (map == NULL)
|
2014-09-25 05:39:54 +08:00
|
|
|
return -1;
|
|
|
|
|
2010-01-06 02:50:31 +08:00
|
|
|
/*
|
|
|
|
* We should get this from /sys/kernel/sections/.text, but till that is
|
|
|
|
* available use this, and after it is use this as a fallback for older
|
|
|
|
* kernels.
|
|
|
|
*/
|
2014-09-25 05:39:54 +08:00
|
|
|
event = zalloc((sizeof(event->mmap) + machine->id_hdr_size));
|
2010-12-02 20:25:28 +08:00
|
|
|
if (event == NULL) {
|
|
|
|
pr_debug("Not enough memory synthesizing mmap event "
|
|
|
|
"for kernel modules\n");
|
|
|
|
return -1;
|
|
|
|
}
|
2010-01-06 02:50:31 +08:00
|
|
|
|
2010-04-28 08:17:50 +08:00
|
|
|
if (machine__is_host(machine)) {
|
2010-04-19 13:32:50 +08:00
|
|
|
/*
|
|
|
|
* kernel uses PERF_RECORD_MISC_USER for user space maps,
|
|
|
|
* see kernel/perf_event.c __perf_event_mmap
|
|
|
|
*/
|
2010-12-02 20:25:28 +08:00
|
|
|
event->header.misc = PERF_RECORD_MISC_KERNEL;
|
2010-04-19 13:32:50 +08:00
|
|
|
} else {
|
2010-12-02 20:25:28 +08:00
|
|
|
event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
|
2013-01-25 18:20:47 +08:00
|
|
|
}
|
2010-01-06 02:50:31 +08:00
|
|
|
|
2014-01-29 22:14:40 +08:00
|
|
|
kmap = map__kmap(map);
|
2010-12-02 20:25:28 +08:00
|
|
|
size = snprintf(event->mmap.filename, sizeof(event->mmap.filename),
|
2018-02-15 20:26:30 +08:00
|
|
|
"%s%s", machine->mmap_name, kmap->ref_reloc_sym->name) + 1;
|
2012-09-11 06:15:01 +08:00
|
|
|
size = PERF_ALIGN(size, sizeof(u64));
|
2010-12-02 20:25:28 +08:00
|
|
|
event->mmap.header.type = PERF_RECORD_MMAP;
|
|
|
|
event->mmap.header.size = (sizeof(event->mmap) -
|
2011-11-28 17:56:39 +08:00
|
|
|
(sizeof(event->mmap.filename) - size) + machine->id_hdr_size);
|
2014-01-29 22:14:40 +08:00
|
|
|
event->mmap.pgoff = kmap->ref_reloc_sym->addr;
|
2010-12-02 20:25:28 +08:00
|
|
|
event->mmap.start = map->start;
|
|
|
|
event->mmap.len = map->end - event->mmap.start;
|
|
|
|
event->mmap.pid = machine->pid;
|
|
|
|
|
perf tools: Add missing initialization of perf_sample.cpumode in synthesized samples
In 473398a21d28 ("perf tools: Add cpumode to struct perf_sample"), I
missed some places where perf_sample fields are directly initialized in
addition to what is done in perf_evsel__parse_sample(), namely when
synthesizing PERF_RECORD_{MMAP*,COMM,FORK,EXIT} for pre-existing threads
and also in intel_pt and intel_bts when synthesizing events from
processor trace, the jitdump code also was affected, fix it.
The problem was noticed with running:
# perf record -e intel_pt//u true
# perf script
Where the samples wouldn't get resolved because perf_sample.cpumode
would be left as zero, i.e. PERF_RECORD_MISC_CPUMODE_UNKNOWN, not
resolving as kernel, hypervisor or user cpu modes.
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 473398a21d28 ("perf tools: Add cpumode to struct perf_sample")
Link: http://lkml.kernel.org/n/tip-n5sdauxgk24d5nun8kuuu2mh@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-03-30 05:46:04 +08:00
|
|
|
err = perf_tool__process_synth_event(tool, event, machine, process);
|
2010-12-02 20:25:28 +08:00
|
|
|
free(event);
|
|
|
|
|
|
|
|
return err;
|
2010-01-06 02:50:31 +08:00
|
|
|
}
|
|
|
|
|
2018-05-22 18:54:37 +08:00
|
|
|
int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
|
|
|
|
perf_event__handler_t process,
|
|
|
|
struct machine *machine)
|
|
|
|
{
|
|
|
|
int err;
|
|
|
|
|
|
|
|
err = __perf_event__synthesize_kernel_mmap(tool, process, machine);
|
|
|
|
if (err < 0)
|
|
|
|
return err;
|
|
|
|
|
|
|
|
return perf_event__synthesize_extra_kmaps(tool, process, machine);
|
|
|
|
}
|
|
|
|
|
2015-10-25 22:51:20 +08:00
|
|
|
int perf_event__synthesize_thread_map2(struct perf_tool *tool,
|
2019-07-21 19:23:50 +08:00
|
|
|
struct perf_thread_map *threads,
|
2015-10-25 22:51:20 +08:00
|
|
|
perf_event__handler_t process,
|
|
|
|
struct machine *machine)
|
|
|
|
{
|
|
|
|
union perf_event *event;
|
|
|
|
int i, err, size;
|
|
|
|
|
|
|
|
size = sizeof(event->thread_map);
|
|
|
|
size += threads->nr * sizeof(event->thread_map.entries[0]);
|
|
|
|
|
|
|
|
event = zalloc(size);
|
|
|
|
if (!event)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
event->header.type = PERF_RECORD_THREAD_MAP;
|
|
|
|
event->header.size = size;
|
|
|
|
event->thread_map.nr = threads->nr;
|
|
|
|
|
|
|
|
for (i = 0; i < threads->nr; i++) {
|
|
|
|
struct thread_map_event_entry *entry = &event->thread_map.entries[i];
|
|
|
|
char *comm = thread_map__comm(threads, i);
|
|
|
|
|
|
|
|
if (!comm)
|
|
|
|
comm = (char *) "";
|
|
|
|
|
|
|
|
entry->pid = thread_map__pid(threads, i);
|
|
|
|
strncpy((char *) &entry->comm, comm, sizeof(entry->comm));
|
|
|
|
}
|
|
|
|
|
|
|
|
err = process(tool, event, NULL, machine);
|
|
|
|
|
|
|
|
free(event);
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2015-10-25 22:51:24 +08:00
|
|
|
static void synthesize_cpus(struct cpu_map_entries *cpus,
|
2019-07-21 19:23:49 +08:00
|
|
|
struct perf_cpu_map *map)
|
2015-10-25 22:51:24 +08:00
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
cpus->nr = map->nr;
|
|
|
|
|
|
|
|
for (i = 0; i < map->nr; i++)
|
|
|
|
cpus->cpu[i] = map->map[i];
|
|
|
|
}
|
|
|
|
|
|
|
|
static void synthesize_mask(struct cpu_map_mask *mask,
|
2019-07-21 19:23:49 +08:00
|
|
|
struct perf_cpu_map *map, int max)
|
2015-10-25 22:51:24 +08:00
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
mask->nr = BITS_TO_LONGS(max);
|
|
|
|
mask->long_size = sizeof(long);
|
|
|
|
|
|
|
|
for (i = 0; i < map->nr; i++)
|
|
|
|
set_bit(map->map[i], mask->mask);
|
|
|
|
}
|
|
|
|
|
2019-07-21 19:23:49 +08:00
|
|
|
static size_t cpus_size(struct perf_cpu_map *map)
|
2015-10-25 22:51:24 +08:00
|
|
|
{
|
|
|
|
return sizeof(struct cpu_map_entries) + map->nr * sizeof(u16);
|
|
|
|
}
|
|
|
|
|
2019-07-21 19:23:49 +08:00
|
|
|
static size_t mask_size(struct perf_cpu_map *map, int *max)
|
2015-10-25 22:51:24 +08:00
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
*max = 0;
|
|
|
|
|
|
|
|
for (i = 0; i < map->nr; i++) {
|
|
|
|
/* bit possition of the cpu is + 1 */
|
|
|
|
int bit = map->map[i] + 1;
|
|
|
|
|
|
|
|
if (bit > *max)
|
|
|
|
*max = bit;
|
|
|
|
}
|
|
|
|
|
|
|
|
return sizeof(struct cpu_map_mask) + BITS_TO_LONGS(*max) * sizeof(long);
|
|
|
|
}
|
|
|
|
|
2019-07-21 19:23:49 +08:00
|
|
|
void *cpu_map_data__alloc(struct perf_cpu_map *map, size_t *size, u16 *type, int *max)
|
2015-10-25 22:51:24 +08:00
|
|
|
{
|
|
|
|
size_t size_cpus, size_mask;
|
|
|
|
bool is_dummy = cpu_map__empty(map);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Both array and mask data have variable size based
|
|
|
|
* on the number of cpus and their actual values.
|
|
|
|
* The size of the 'struct cpu_map_data' is:
|
|
|
|
*
|
|
|
|
* array = size of 'struct cpu_map_entries' +
|
|
|
|
* number of cpus * sizeof(u64)
|
|
|
|
*
|
|
|
|
* mask = size of 'struct cpu_map_mask' +
|
|
|
|
* maximum cpu bit converted to size of longs
|
|
|
|
*
|
|
|
|
* and finaly + the size of 'struct cpu_map_data'.
|
|
|
|
*/
|
|
|
|
size_cpus = cpus_size(map);
|
|
|
|
size_mask = mask_size(map, max);
|
|
|
|
|
|
|
|
if (is_dummy || (size_cpus < size_mask)) {
|
|
|
|
*size += size_cpus;
|
|
|
|
*type = PERF_CPU_MAP__CPUS;
|
|
|
|
} else {
|
|
|
|
*size += size_mask;
|
|
|
|
*type = PERF_CPU_MAP__MASK;
|
|
|
|
}
|
|
|
|
|
|
|
|
*size += sizeof(struct cpu_map_data);
|
2018-10-12 13:46:55 +08:00
|
|
|
*size = PERF_ALIGN(*size, sizeof(u64));
|
2015-10-25 22:51:24 +08:00
|
|
|
return zalloc(*size);
|
|
|
|
}
|
|
|
|
|
2019-07-21 19:23:49 +08:00
|
|
|
void cpu_map_data__synthesize(struct cpu_map_data *data, struct perf_cpu_map *map,
|
2015-10-25 22:51:24 +08:00
|
|
|
u16 type, int max)
|
|
|
|
{
|
|
|
|
data->type = type;
|
|
|
|
|
|
|
|
switch (type) {
|
|
|
|
case PERF_CPU_MAP__CPUS:
|
|
|
|
synthesize_cpus((struct cpu_map_entries *) data->data, map);
|
|
|
|
break;
|
|
|
|
case PERF_CPU_MAP__MASK:
|
|
|
|
synthesize_mask((struct cpu_map_mask *) data->data, map, max);
|
|
|
|
default:
|
|
|
|
break;
|
|
|
|
};
|
|
|
|
}
|
|
|
|
|
2019-07-21 19:23:49 +08:00
|
|
|
static struct cpu_map_event* cpu_map_event__new(struct perf_cpu_map *map)
|
2015-10-25 22:51:24 +08:00
|
|
|
{
|
|
|
|
size_t size = sizeof(struct cpu_map_event);
|
|
|
|
struct cpu_map_event *event;
|
|
|
|
int max;
|
|
|
|
u16 type;
|
|
|
|
|
|
|
|
event = cpu_map_data__alloc(map, &size, &type, &max);
|
|
|
|
if (!event)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
event->header.type = PERF_RECORD_CPU_MAP;
|
|
|
|
event->header.size = size;
|
|
|
|
event->data.type = type;
|
|
|
|
|
|
|
|
cpu_map_data__synthesize(&event->data, map, type, max);
|
|
|
|
return event;
|
|
|
|
}
|
|
|
|
|
|
|
|
int perf_event__synthesize_cpu_map(struct perf_tool *tool,
|
2019-07-21 19:23:49 +08:00
|
|
|
struct perf_cpu_map *map,
|
2015-10-25 22:51:24 +08:00
|
|
|
perf_event__handler_t process,
|
|
|
|
struct machine *machine)
|
|
|
|
{
|
|
|
|
struct cpu_map_event *event;
|
|
|
|
int err;
|
|
|
|
|
|
|
|
event = cpu_map_event__new(map);
|
|
|
|
if (!event)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
err = process(tool, (union perf_event *) event, NULL, machine);
|
|
|
|
|
|
|
|
free(event);
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2015-10-25 22:51:28 +08:00
|
|
|
int perf_event__synthesize_stat_config(struct perf_tool *tool,
|
|
|
|
struct perf_stat_config *config,
|
|
|
|
perf_event__handler_t process,
|
|
|
|
struct machine *machine)
|
|
|
|
{
|
|
|
|
struct stat_config_event *event;
|
|
|
|
int size, i = 0, err;
|
|
|
|
|
|
|
|
size = sizeof(*event);
|
|
|
|
size += (PERF_STAT_CONFIG_TERM__MAX * sizeof(event->data[0]));
|
|
|
|
|
|
|
|
event = zalloc(size);
|
|
|
|
if (!event)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
event->header.type = PERF_RECORD_STAT_CONFIG;
|
|
|
|
event->header.size = size;
|
|
|
|
event->nr = PERF_STAT_CONFIG_TERM__MAX;
|
|
|
|
|
|
|
|
#define ADD(__term, __val) \
|
|
|
|
event->data[i].tag = PERF_STAT_CONFIG_TERM__##__term; \
|
|
|
|
event->data[i].val = __val; \
|
|
|
|
i++;
|
|
|
|
|
|
|
|
ADD(AGGR_MODE, config->aggr_mode)
|
|
|
|
ADD(INTERVAL, config->interval)
|
|
|
|
ADD(SCALE, config->scale)
|
|
|
|
|
|
|
|
WARN_ONCE(i != PERF_STAT_CONFIG_TERM__MAX,
|
|
|
|
"stat config terms unbalanced\n");
|
|
|
|
#undef ADD
|
|
|
|
|
|
|
|
err = process(tool, (union perf_event *) event, NULL, machine);
|
|
|
|
|
|
|
|
free(event);
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2015-10-25 22:51:31 +08:00
|
|
|
int perf_event__synthesize_stat(struct perf_tool *tool,
|
|
|
|
u32 cpu, u32 thread, u64 id,
|
|
|
|
struct perf_counts_values *count,
|
|
|
|
perf_event__handler_t process,
|
|
|
|
struct machine *machine)
|
|
|
|
{
|
|
|
|
struct stat_event event;
|
|
|
|
|
|
|
|
event.header.type = PERF_RECORD_STAT;
|
|
|
|
event.header.size = sizeof(event);
|
|
|
|
event.header.misc = 0;
|
|
|
|
|
|
|
|
event.id = id;
|
|
|
|
event.cpu = cpu;
|
|
|
|
event.thread = thread;
|
|
|
|
event.val = count->val;
|
|
|
|
event.ena = count->ena;
|
|
|
|
event.run = count->run;
|
|
|
|
|
|
|
|
return process(tool, (union perf_event *) &event, NULL, machine);
|
|
|
|
}
|
|
|
|
|
2015-10-25 22:51:34 +08:00
|
|
|
int perf_event__synthesize_stat_round(struct perf_tool *tool,
|
|
|
|
u64 evtime, u64 type,
|
|
|
|
perf_event__handler_t process,
|
|
|
|
struct machine *machine)
|
|
|
|
{
|
|
|
|
struct stat_round_event event;
|
|
|
|
|
|
|
|
event.header.type = PERF_RECORD_STAT_ROUND;
|
|
|
|
event.header.size = sizeof(event);
|
|
|
|
event.header.misc = 0;
|
|
|
|
|
|
|
|
event.time = evtime;
|
|
|
|
event.type = type;
|
|
|
|
|
|
|
|
return process(tool, (union perf_event *) &event, NULL, machine);
|
|
|
|
}
|
|
|
|
|
2015-10-25 22:51:29 +08:00
|
|
|
void perf_event__read_stat_config(struct perf_stat_config *config,
|
|
|
|
struct stat_config_event *event)
|
|
|
|
{
|
|
|
|
unsigned i;
|
|
|
|
|
|
|
|
for (i = 0; i < event->nr; i++) {
|
|
|
|
|
|
|
|
switch (event->data[i].tag) {
|
|
|
|
#define CASE(__term, __val) \
|
|
|
|
case PERF_STAT_CONFIG_TERM__##__term: \
|
|
|
|
config->__val = event->data[i].val; \
|
|
|
|
break;
|
|
|
|
|
|
|
|
CASE(AGGR_MODE, aggr_mode)
|
|
|
|
CASE(SCALE, scale)
|
|
|
|
CASE(INTERVAL, interval)
|
|
|
|
#undef CASE
|
|
|
|
default:
|
|
|
|
pr_warning("unknown stat config term %" PRIu64 "\n",
|
|
|
|
event->data[i].tag);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2011-12-02 21:06:37 +08:00
|
|
|
size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp)
|
|
|
|
{
|
2014-07-14 18:02:27 +08:00
|
|
|
const char *s;
|
|
|
|
|
|
|
|
if (event->header.misc & PERF_RECORD_MISC_COMM_EXEC)
|
|
|
|
s = " exec";
|
|
|
|
else
|
|
|
|
s = "";
|
|
|
|
|
2015-02-25 04:20:31 +08:00
|
|
|
return fprintf(fp, "%s: %s:%d/%d\n", s, event->comm.comm, event->comm.pid, event->comm.tid);
|
2011-12-02 21:06:37 +08:00
|
|
|
}
|
|
|
|
|
perf tools: Add PERF_RECORD_NAMESPACES to include namespaces related info
Introduce a new option to record PERF_RECORD_NAMESPACES events emitted
by the kernel when fork, clone, setns or unshare are invoked. And update
perf-record documentation with the new option to record namespace
events.
Committer notes:
Combined it with a later patch to allow printing it via 'perf report -D'
and be able to test the feature introduced in this patch. Had to move
here also perf_ns__name(), that was introduced in another later patch.
Also used PRIu64 and PRIx64 to fix the build in some enfironments wrt:
util/event.c:1129:39: error: format '%lx' expects argument of type 'long unsigned int', but argument 6 has type 'long long unsigned int' [-Werror=format=]
ret += fprintf(fp, "%u/%s: %lu/0x%lx%s", idx
^
Testing it:
# perf record --namespaces -a
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 1.083 MB perf.data (423 samples) ]
#
# perf report -D
<SNIP>
3 2028902078892 0x115140 [0xa0]: PERF_RECORD_NAMESPACES 14783/14783 - nr_namespaces: 7
[0/net: 3/0xf0000081, 1/uts: 3/0xeffffffe, 2/ipc: 3/0xefffffff, 3/pid: 3/0xeffffffc,
4/user: 3/0xeffffffd, 5/mnt: 3/0xf0000000, 6/cgroup: 3/0xeffffffb]
0x1151e0 [0x30]: event: 9
.
. ... raw event: size 48 bytes
. 0000: 09 00 00 00 02 00 30 00 c4 71 82 68 0c 7f 00 00 ......0..q.h....
. 0010: a9 39 00 00 a9 39 00 00 94 28 fe 63 d8 01 00 00 .9...9...(.c....
. 0020: 03 00 00 00 00 00 00 00 ce c4 02 00 00 00 00 00 ................
<SNIP>
NAMESPACES events: 1
<SNIP>
#
Signed-off-by: Hari Bathini <hbathini@linux.vnet.ibm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@fb.com>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Aravinda Prasad <aravinda@linux.vnet.ibm.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sargun Dhillon <sargun@sargun.me>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/148891930386.25309.18412039920746995488.stgit@hbathini.in.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-08 04:41:43 +08:00
|
|
|
size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp)
|
|
|
|
{
|
|
|
|
size_t ret = 0;
|
|
|
|
struct perf_ns_link_info *ns_link_info;
|
|
|
|
u32 nr_namespaces, idx;
|
|
|
|
|
|
|
|
ns_link_info = event->namespaces.link_info;
|
|
|
|
nr_namespaces = event->namespaces.nr_namespaces;
|
|
|
|
|
|
|
|
ret += fprintf(fp, " %d/%d - nr_namespaces: %u\n\t\t[",
|
|
|
|
event->namespaces.pid,
|
|
|
|
event->namespaces.tid,
|
|
|
|
nr_namespaces);
|
|
|
|
|
|
|
|
for (idx = 0; idx < nr_namespaces; idx++) {
|
|
|
|
if (idx && (idx % 4 == 0))
|
|
|
|
ret += fprintf(fp, "\n\t\t ");
|
|
|
|
|
|
|
|
ret += fprintf(fp, "%u/%s: %" PRIu64 "/%#" PRIx64 "%s", idx,
|
|
|
|
perf_ns__name(idx), (u64)ns_link_info[idx].dev,
|
|
|
|
(u64)ns_link_info[idx].ino,
|
|
|
|
((idx + 1) != nr_namespaces) ? ", " : "]\n");
|
|
|
|
}
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2012-09-11 06:15:03 +08:00
|
|
|
int perf_event__process_comm(struct perf_tool *tool __maybe_unused,
|
2011-11-25 18:19:45 +08:00
|
|
|
union perf_event *event,
|
2013-09-11 22:18:24 +08:00
|
|
|
struct perf_sample *sample,
|
2011-11-28 17:56:39 +08:00
|
|
|
struct machine *machine)
|
2009-11-28 02:29:22 +08:00
|
|
|
{
|
2013-09-11 22:18:24 +08:00
|
|
|
return machine__process_comm_event(machine, event, sample);
|
2009-11-28 02:29:22 +08:00
|
|
|
}
|
|
|
|
|
perf tools: Add PERF_RECORD_NAMESPACES to include namespaces related info
Introduce a new option to record PERF_RECORD_NAMESPACES events emitted
by the kernel when fork, clone, setns or unshare are invoked. And update
perf-record documentation with the new option to record namespace
events.
Committer notes:
Combined it with a later patch to allow printing it via 'perf report -D'
and be able to test the feature introduced in this patch. Had to move
here also perf_ns__name(), that was introduced in another later patch.
Also used PRIu64 and PRIx64 to fix the build in some enfironments wrt:
util/event.c:1129:39: error: format '%lx' expects argument of type 'long unsigned int', but argument 6 has type 'long long unsigned int' [-Werror=format=]
ret += fprintf(fp, "%u/%s: %lu/0x%lx%s", idx
^
Testing it:
# perf record --namespaces -a
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 1.083 MB perf.data (423 samples) ]
#
# perf report -D
<SNIP>
3 2028902078892 0x115140 [0xa0]: PERF_RECORD_NAMESPACES 14783/14783 - nr_namespaces: 7
[0/net: 3/0xf0000081, 1/uts: 3/0xeffffffe, 2/ipc: 3/0xefffffff, 3/pid: 3/0xeffffffc,
4/user: 3/0xeffffffd, 5/mnt: 3/0xf0000000, 6/cgroup: 3/0xeffffffb]
0x1151e0 [0x30]: event: 9
.
. ... raw event: size 48 bytes
. 0000: 09 00 00 00 02 00 30 00 c4 71 82 68 0c 7f 00 00 ......0..q.h....
. 0010: a9 39 00 00 a9 39 00 00 94 28 fe 63 d8 01 00 00 .9...9...(.c....
. 0020: 03 00 00 00 00 00 00 00 ce c4 02 00 00 00 00 00 ................
<SNIP>
NAMESPACES events: 1
<SNIP>
#
Signed-off-by: Hari Bathini <hbathini@linux.vnet.ibm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@fb.com>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Aravinda Prasad <aravinda@linux.vnet.ibm.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sargun Dhillon <sargun@sargun.me>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/148891930386.25309.18412039920746995488.stgit@hbathini.in.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-08 04:41:43 +08:00
|
|
|
int perf_event__process_namespaces(struct perf_tool *tool __maybe_unused,
|
|
|
|
union perf_event *event,
|
|
|
|
struct perf_sample *sample,
|
|
|
|
struct machine *machine)
|
|
|
|
{
|
|
|
|
return machine__process_namespaces_event(machine, event, sample);
|
|
|
|
}
|
|
|
|
|
2012-09-11 06:15:03 +08:00
|
|
|
int perf_event__process_lost(struct perf_tool *tool __maybe_unused,
|
2011-11-25 18:19:45 +08:00
|
|
|
union perf_event *event,
|
2013-09-11 22:18:24 +08:00
|
|
|
struct perf_sample *sample,
|
2012-10-07 03:26:02 +08:00
|
|
|
struct machine *machine)
|
2009-11-28 02:29:22 +08:00
|
|
|
{
|
2013-09-11 22:18:24 +08:00
|
|
|
return machine__process_lost_event(machine, event, sample);
|
2010-04-19 13:32:50 +08:00
|
|
|
}
|
perf tools: Encode kernel module mappings in perf.data
We were always looking at the running machine /proc/modules,
even when processing a perf.data file, which only makes sense
when we're doing 'perf record' and 'perf report' on the same
machine, and in close sucession, or if we don't use modules at
all, right Peter? ;-)
Now, at 'perf record' time we read /proc/modules, find the long
path for modules, and put them as PERF_MMAP events, just like we
did to encode the reloc reference symbol for vmlinux. Talking
about that now it is encoded in .pgoff, so that we can use
.{start,len} to store the address boundaries for the kernel so
that when we reconstruct the kmaps tree we can do lookups right
away, without having to fixup the end of the kernel maps like we
did in the past (and now only in perf record).
One more step in the 'perf archive' direction when we'll finally
be able to collect data in one machine and analyse in another.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1263396139-4798-1-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-13 23:22:17 +08:00
|
|
|
|
2015-04-30 22:37:29 +08:00
|
|
|
int perf_event__process_aux(struct perf_tool *tool __maybe_unused,
|
|
|
|
union perf_event *event,
|
|
|
|
struct perf_sample *sample __maybe_unused,
|
|
|
|
struct machine *machine)
|
|
|
|
{
|
|
|
|
return machine__process_aux_event(machine, event);
|
|
|
|
}
|
|
|
|
|
2015-04-30 22:37:30 +08:00
|
|
|
int perf_event__process_itrace_start(struct perf_tool *tool __maybe_unused,
|
|
|
|
union perf_event *event,
|
|
|
|
struct perf_sample *sample __maybe_unused,
|
|
|
|
struct machine *machine)
|
|
|
|
{
|
|
|
|
return machine__process_itrace_start_event(machine, event);
|
|
|
|
}
|
|
|
|
|
2015-05-11 03:13:15 +08:00
|
|
|
int perf_event__process_lost_samples(struct perf_tool *tool __maybe_unused,
|
|
|
|
union perf_event *event,
|
|
|
|
struct perf_sample *sample,
|
|
|
|
struct machine *machine)
|
|
|
|
{
|
|
|
|
return machine__process_lost_samples_event(machine, event, sample);
|
|
|
|
}
|
|
|
|
|
2015-07-21 17:44:03 +08:00
|
|
|
int perf_event__process_switch(struct perf_tool *tool __maybe_unused,
|
|
|
|
union perf_event *event,
|
|
|
|
struct perf_sample *sample __maybe_unused,
|
|
|
|
struct machine *machine)
|
|
|
|
{
|
|
|
|
return machine__process_switch_event(machine, event);
|
|
|
|
}
|
|
|
|
|
2019-01-18 00:15:17 +08:00
|
|
|
int perf_event__process_ksymbol(struct perf_tool *tool __maybe_unused,
|
|
|
|
union perf_event *event,
|
|
|
|
struct perf_sample *sample __maybe_unused,
|
|
|
|
struct machine *machine)
|
|
|
|
{
|
|
|
|
return machine__process_ksymbol(machine, event, sample);
|
|
|
|
}
|
|
|
|
|
perf tools: Handle PERF_RECORD_BPF_EVENT
This patch adds basic handling of PERF_RECORD_BPF_EVENT. Tracking of
PERF_RECORD_BPF_EVENT is OFF by default. Option --bpf-event is added to
turn it on.
Committer notes:
Add dummy machine__process_bpf_event() variant that returns zero for
systems without HAVE_LIBBPF_SUPPORT, such as Alpine Linux, unbreaking
the build in such systems.
Remove the needless include <machine.h> from bpf->event.h, provide just
forward declarations for the structs and unions in the parameters, to
reduce compilation time and needless rebuilds when machine.h gets
changed.
Committer testing:
When running with:
# perf record --bpf-event
On an older kernel where PERF_RECORD_BPF_EVENT and PERF_RECORD_KSYMBOL
is not present, we fallback to removing those two bits from
perf_event_attr, making the tool to continue to work on older kernels:
perf_event_attr:
size 112
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|PERIOD
read_format ID
disabled 1
inherit 1
mmap 1
comm 1
freq 1
enable_on_exec 1
task 1
precise_ip 3
sample_id_all 1
exclude_guest 1
mmap2 1
comm_exec 1
ksymbol 1
bpf_event 1
------------------------------------------------------------
sys_perf_event_open: pid 5779 cpu 0 group_fd -1 flags 0x8
sys_perf_event_open failed, error -22
switching off bpf_event
------------------------------------------------------------
perf_event_attr:
size 112
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|PERIOD
read_format ID
disabled 1
inherit 1
mmap 1
comm 1
freq 1
enable_on_exec 1
task 1
precise_ip 3
sample_id_all 1
exclude_guest 1
mmap2 1
comm_exec 1
ksymbol 1
------------------------------------------------------------
sys_perf_event_open: pid 5779 cpu 0 group_fd -1 flags 0x8
sys_perf_event_open failed, error -22
switching off ksymbol
------------------------------------------------------------
perf_event_attr:
size 112
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|PERIOD
read_format ID
disabled 1
inherit 1
mmap 1
comm 1
freq 1
enable_on_exec 1
task 1
precise_ip 3
sample_id_all 1
exclude_guest 1
mmap2 1
comm_exec 1
------------------------------------------------------------
And then proceeds to work without those two features.
As passing --bpf-event is an explicit action performed by the user, perhaps we
should emit a warning telling that the kernel has no such feature, but this can
be done on top of this patch.
Now with a kernel that supports these events, start the 'record --bpf-event -a'
and then run 'perf trace sleep 10000' that will use the BPF
augmented_raw_syscalls.o prebuilt (for another kernel version even) and thus
should generate PERF_RECORD_BPF_EVENT events:
[root@quaco ~]# perf record -e dummy -a --bpf-event
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.713 MB perf.data ]
[root@quaco ~]# bpftool prog
13: cgroup_skb tag 7be49e3934a125ba gpl
loaded_at 2019-01-19T09:09:43-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 13,14
14: cgroup_skb tag 2a142ef67aaad174 gpl
loaded_at 2019-01-19T09:09:43-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 13,14
15: cgroup_skb tag 7be49e3934a125ba gpl
loaded_at 2019-01-19T09:09:43-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 15,16
16: cgroup_skb tag 2a142ef67aaad174 gpl
loaded_at 2019-01-19T09:09:43-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 15,16
17: cgroup_skb tag 7be49e3934a125ba gpl
loaded_at 2019-01-19T09:09:44-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 17,18
18: cgroup_skb tag 2a142ef67aaad174 gpl
loaded_at 2019-01-19T09:09:44-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 17,18
21: cgroup_skb tag 7be49e3934a125ba gpl
loaded_at 2019-01-19T09:09:45-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 21,22
22: cgroup_skb tag 2a142ef67aaad174 gpl
loaded_at 2019-01-19T09:09:45-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 21,22
31: tracepoint name sys_enter tag 12504ba9402f952f gpl
loaded_at 2019-01-19T09:19:56-0300 uid 0
xlated 512B jited 374B memlock 4096B map_ids 30,29,28
32: tracepoint name sys_exit tag c1bd85c092d6e4aa gpl
loaded_at 2019-01-19T09:19:56-0300 uid 0
xlated 256B jited 191B memlock 4096B map_ids 30,29
# perf report -D | grep PERF_RECORD_BPF_EVENT | nl
1 0 55834574849 0x4fc8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 13
2 0 60129542145 0x5118 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 14
3 0 64424509441 0x5268 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 15
4 0 68719476737 0x53b8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 16
5 0 73014444033 0x5508 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 17
6 0 77309411329 0x5658 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 18
7 0 90194313217 0x57a8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 21
8 0 94489280513 0x58f8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 22
9 7 620922484360 0xb6390 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 29
10 7 620922486018 0xb6410 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 2, flags 0, id 29
11 7 620922579199 0xb6490 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 30
12 7 620922580240 0xb6510 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 2, flags 0, id 30
13 7 620922765207 0xb6598 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 31
14 7 620922874543 0xb6620 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 32
#
There, the 31 and 32 tracepoint BPF programs put in place by 'perf trace'.
Signed-off-by: Song Liu <songliubraving@fb.com>
Reviewed-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: kernel-team@fb.com
Cc: netdev@vger.kernel.org
Link: http://lkml.kernel.org/r/20190117161521.1341602-7-songliubraving@fb.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-01-18 00:15:18 +08:00
|
|
|
int perf_event__process_bpf_event(struct perf_tool *tool __maybe_unused,
|
|
|
|
union perf_event *event,
|
|
|
|
struct perf_sample *sample __maybe_unused,
|
|
|
|
struct machine *machine)
|
|
|
|
{
|
|
|
|
return machine__process_bpf_event(machine, event, sample);
|
|
|
|
}
|
|
|
|
|
2011-12-02 21:06:37 +08:00
|
|
|
size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
|
|
|
|
{
|
2013-11-11 20:44:09 +08:00
|
|
|
return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %c %s\n",
|
2011-12-02 21:06:37 +08:00
|
|
|
event->mmap.pid, event->mmap.tid, event->mmap.start,
|
2013-11-11 20:44:09 +08:00
|
|
|
event->mmap.len, event->mmap.pgoff,
|
|
|
|
(event->header.misc & PERF_RECORD_MISC_MMAP_DATA) ? 'r' : 'x',
|
|
|
|
event->mmap.filename);
|
2011-12-02 21:06:37 +08:00
|
|
|
}
|
|
|
|
|
2013-08-21 18:10:25 +08:00
|
|
|
size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp)
|
|
|
|
{
|
|
|
|
return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64
|
2014-05-20 03:13:49 +08:00
|
|
|
" %02x:%02x %"PRIu64" %"PRIu64"]: %c%c%c%c %s\n",
|
2013-08-21 18:10:25 +08:00
|
|
|
event->mmap2.pid, event->mmap2.tid, event->mmap2.start,
|
|
|
|
event->mmap2.len, event->mmap2.pgoff, event->mmap2.maj,
|
|
|
|
event->mmap2.min, event->mmap2.ino,
|
|
|
|
event->mmap2.ino_generation,
|
2014-05-20 03:13:49 +08:00
|
|
|
(event->mmap2.prot & PROT_READ) ? 'r' : '-',
|
|
|
|
(event->mmap2.prot & PROT_WRITE) ? 'w' : '-',
|
|
|
|
(event->mmap2.prot & PROT_EXEC) ? 'x' : '-',
|
|
|
|
(event->mmap2.flags & MAP_SHARED) ? 's' : 'p',
|
2013-08-21 18:10:25 +08:00
|
|
|
event->mmap2.filename);
|
|
|
|
}
|
|
|
|
|
2015-10-25 22:51:22 +08:00
|
|
|
size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp)
|
|
|
|
{
|
2019-07-21 19:23:50 +08:00
|
|
|
struct perf_thread_map *threads = thread_map__new_event(&event->thread_map);
|
2015-10-25 22:51:22 +08:00
|
|
|
size_t ret;
|
|
|
|
|
|
|
|
ret = fprintf(fp, " nr: ");
|
|
|
|
|
|
|
|
if (threads)
|
|
|
|
ret += thread_map__fprintf(threads, fp);
|
|
|
|
else
|
|
|
|
ret += fprintf(fp, "failed to get threads from event\n");
|
|
|
|
|
|
|
|
thread_map__put(threads);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2015-10-25 22:51:26 +08:00
|
|
|
size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp)
|
|
|
|
{
|
2019-07-21 19:23:49 +08:00
|
|
|
struct perf_cpu_map *cpus = cpu_map__new_data(&event->cpu_map.data);
|
2015-10-25 22:51:26 +08:00
|
|
|
size_t ret;
|
|
|
|
|
2016-06-28 19:29:04 +08:00
|
|
|
ret = fprintf(fp, ": ");
|
2015-10-25 22:51:26 +08:00
|
|
|
|
|
|
|
if (cpus)
|
|
|
|
ret += cpu_map__fprintf(cpus, fp);
|
|
|
|
else
|
|
|
|
ret += fprintf(fp, "failed to get cpumap from event\n");
|
|
|
|
|
|
|
|
cpu_map__put(cpus);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2012-10-07 03:26:02 +08:00
|
|
|
int perf_event__process_mmap(struct perf_tool *tool __maybe_unused,
|
2011-11-25 18:19:45 +08:00
|
|
|
union perf_event *event,
|
2013-09-11 22:18:24 +08:00
|
|
|
struct perf_sample *sample,
|
2011-11-28 17:56:39 +08:00
|
|
|
struct machine *machine)
|
2010-04-19 13:32:50 +08:00
|
|
|
{
|
2013-09-11 22:18:24 +08:00
|
|
|
return machine__process_mmap_event(machine, event, sample);
|
2009-11-28 02:29:22 +08:00
|
|
|
}
|
|
|
|
|
2013-08-21 18:10:25 +08:00
|
|
|
int perf_event__process_mmap2(struct perf_tool *tool __maybe_unused,
|
|
|
|
union perf_event *event,
|
2013-09-11 22:18:24 +08:00
|
|
|
struct perf_sample *sample,
|
2013-08-21 18:10:25 +08:00
|
|
|
struct machine *machine)
|
|
|
|
{
|
2013-09-11 22:18:24 +08:00
|
|
|
return machine__process_mmap2_event(machine, event, sample);
|
2013-08-21 18:10:25 +08:00
|
|
|
}
|
|
|
|
|
2011-12-02 21:06:37 +08:00
|
|
|
size_t perf_event__fprintf_task(union perf_event *event, FILE *fp)
|
|
|
|
{
|
|
|
|
return fprintf(fp, "(%d:%d):(%d:%d)\n",
|
|
|
|
event->fork.pid, event->fork.tid,
|
|
|
|
event->fork.ppid, event->fork.ptid);
|
|
|
|
}
|
|
|
|
|
2012-10-07 02:44:59 +08:00
|
|
|
int perf_event__process_fork(struct perf_tool *tool __maybe_unused,
|
2011-11-25 18:19:45 +08:00
|
|
|
union perf_event *event,
|
2013-09-11 22:18:24 +08:00
|
|
|
struct perf_sample *sample,
|
2012-10-07 02:44:59 +08:00
|
|
|
struct machine *machine)
|
2009-11-28 02:29:22 +08:00
|
|
|
{
|
2013-09-11 22:18:24 +08:00
|
|
|
return machine__process_fork_event(machine, event, sample);
|
2009-11-28 02:29:22 +08:00
|
|
|
}
|
perf tools: Consolidate symbol resolving across all tools
Now we have a very high level routine for simple tools to
process IP sample events:
int event__preprocess_sample(const event_t *self,
struct addr_location *al,
symbol_filter_t filter)
It receives the event itself and will insert new threads in the
global threads list and resolve the map and symbol, filling all
this info into the new addr_location struct, so that tools like
annotate and report can further process the event by creating
hist_entries in their specific way (with or without callgraphs,
etc).
It in turn uses the new next layer function:
void thread__find_addr_location(struct thread *self, u8 cpumode,
enum map_type type, u64 addr,
struct addr_location *al,
symbol_filter_t filter)
This one will, given a thread (userspace or the kernel kthread
one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE
too in the near future) at the given cpumode, taking vdsos into
account (userspace hit, but kernel symbol) and will fill all
these details in the addr_location given.
Tools that need a more compact API for plain function
resolution, like 'kmem', can use this other one:
struct symbol *thread__find_function(struct thread *self, u64 addr,
symbol_filter_t filter)
So, to resolve a kernel symbol, that is all the 'kmem' tool
needs, its just a matter of calling:
sym = thread__find_function(kthread, addr, NULL);
The 'filter' parameter is needed because we do lazy
parsing/loading of ELF symtabs or /proc/kallsyms.
With this we remove more code duplication all around, which is
always good, huh? :-)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: John Kacur <jkacur@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
|
|
|
|
2012-10-07 02:44:59 +08:00
|
|
|
int perf_event__process_exit(struct perf_tool *tool __maybe_unused,
|
|
|
|
union perf_event *event,
|
2013-09-11 22:18:24 +08:00
|
|
|
struct perf_sample *sample,
|
2012-10-07 02:44:59 +08:00
|
|
|
struct machine *machine)
|
|
|
|
{
|
2013-09-11 22:18:24 +08:00
|
|
|
return machine__process_exit_event(machine, event, sample);
|
2012-10-07 02:44:59 +08:00
|
|
|
}
|
|
|
|
|
2015-04-30 22:37:29 +08:00
|
|
|
size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp)
|
|
|
|
{
|
2017-03-17 00:41:59 +08:00
|
|
|
return fprintf(fp, " offset: %#"PRIx64" size: %#"PRIx64" flags: %#"PRIx64" [%s%s%s]\n",
|
2015-04-30 22:37:29 +08:00
|
|
|
event->aux.aux_offset, event->aux.aux_size,
|
|
|
|
event->aux.flags,
|
|
|
|
event->aux.flags & PERF_AUX_FLAG_TRUNCATED ? "T" : "",
|
2017-03-17 00:41:59 +08:00
|
|
|
event->aux.flags & PERF_AUX_FLAG_OVERWRITE ? "O" : "",
|
|
|
|
event->aux.flags & PERF_AUX_FLAG_PARTIAL ? "P" : "");
|
2015-04-30 22:37:29 +08:00
|
|
|
}
|
|
|
|
|
2015-04-30 22:37:30 +08:00
|
|
|
size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp)
|
|
|
|
{
|
|
|
|
return fprintf(fp, " pid: %u tid: %u\n",
|
|
|
|
event->itrace_start.pid, event->itrace_start.tid);
|
|
|
|
}
|
|
|
|
|
2015-07-21 17:44:03 +08:00
|
|
|
size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp)
|
|
|
|
{
|
|
|
|
bool out = event->header.misc & PERF_RECORD_MISC_SWITCH_OUT;
|
2018-04-09 15:26:05 +08:00
|
|
|
const char *in_out = !out ? "IN " :
|
|
|
|
!(event->header.misc & PERF_RECORD_MISC_SWITCH_OUT_PREEMPT) ?
|
|
|
|
"OUT " : "OUT preempt";
|
2015-07-21 17:44:03 +08:00
|
|
|
|
|
|
|
if (event->header.type == PERF_RECORD_SWITCH)
|
|
|
|
return fprintf(fp, " %s\n", in_out);
|
|
|
|
|
|
|
|
return fprintf(fp, " %s %s pid/tid: %5u/%-5u\n",
|
|
|
|
in_out, out ? "next" : "prev",
|
|
|
|
event->context_switch.next_prev_pid,
|
|
|
|
event->context_switch.next_prev_tid);
|
|
|
|
}
|
|
|
|
|
2018-01-08 00:03:53 +08:00
|
|
|
static size_t perf_event__fprintf_lost(union perf_event *event, FILE *fp)
|
|
|
|
{
|
|
|
|
return fprintf(fp, " lost %" PRIu64 "\n", event->lost.lost);
|
|
|
|
}
|
|
|
|
|
2019-01-18 00:15:17 +08:00
|
|
|
size_t perf_event__fprintf_ksymbol(union perf_event *event, FILE *fp)
|
|
|
|
{
|
2019-05-08 21:20:09 +08:00
|
|
|
return fprintf(fp, " addr %" PRIx64 " len %u type %u flags 0x%x name %s\n",
|
2019-01-18 00:15:17 +08:00
|
|
|
event->ksymbol_event.addr, event->ksymbol_event.len,
|
|
|
|
event->ksymbol_event.ksym_type,
|
|
|
|
event->ksymbol_event.flags, event->ksymbol_event.name);
|
|
|
|
}
|
|
|
|
|
perf tools: Handle PERF_RECORD_BPF_EVENT
This patch adds basic handling of PERF_RECORD_BPF_EVENT. Tracking of
PERF_RECORD_BPF_EVENT is OFF by default. Option --bpf-event is added to
turn it on.
Committer notes:
Add dummy machine__process_bpf_event() variant that returns zero for
systems without HAVE_LIBBPF_SUPPORT, such as Alpine Linux, unbreaking
the build in such systems.
Remove the needless include <machine.h> from bpf->event.h, provide just
forward declarations for the structs and unions in the parameters, to
reduce compilation time and needless rebuilds when machine.h gets
changed.
Committer testing:
When running with:
# perf record --bpf-event
On an older kernel where PERF_RECORD_BPF_EVENT and PERF_RECORD_KSYMBOL
is not present, we fallback to removing those two bits from
perf_event_attr, making the tool to continue to work on older kernels:
perf_event_attr:
size 112
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|PERIOD
read_format ID
disabled 1
inherit 1
mmap 1
comm 1
freq 1
enable_on_exec 1
task 1
precise_ip 3
sample_id_all 1
exclude_guest 1
mmap2 1
comm_exec 1
ksymbol 1
bpf_event 1
------------------------------------------------------------
sys_perf_event_open: pid 5779 cpu 0 group_fd -1 flags 0x8
sys_perf_event_open failed, error -22
switching off bpf_event
------------------------------------------------------------
perf_event_attr:
size 112
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|PERIOD
read_format ID
disabled 1
inherit 1
mmap 1
comm 1
freq 1
enable_on_exec 1
task 1
precise_ip 3
sample_id_all 1
exclude_guest 1
mmap2 1
comm_exec 1
ksymbol 1
------------------------------------------------------------
sys_perf_event_open: pid 5779 cpu 0 group_fd -1 flags 0x8
sys_perf_event_open failed, error -22
switching off ksymbol
------------------------------------------------------------
perf_event_attr:
size 112
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|PERIOD
read_format ID
disabled 1
inherit 1
mmap 1
comm 1
freq 1
enable_on_exec 1
task 1
precise_ip 3
sample_id_all 1
exclude_guest 1
mmap2 1
comm_exec 1
------------------------------------------------------------
And then proceeds to work without those two features.
As passing --bpf-event is an explicit action performed by the user, perhaps we
should emit a warning telling that the kernel has no such feature, but this can
be done on top of this patch.
Now with a kernel that supports these events, start the 'record --bpf-event -a'
and then run 'perf trace sleep 10000' that will use the BPF
augmented_raw_syscalls.o prebuilt (for another kernel version even) and thus
should generate PERF_RECORD_BPF_EVENT events:
[root@quaco ~]# perf record -e dummy -a --bpf-event
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.713 MB perf.data ]
[root@quaco ~]# bpftool prog
13: cgroup_skb tag 7be49e3934a125ba gpl
loaded_at 2019-01-19T09:09:43-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 13,14
14: cgroup_skb tag 2a142ef67aaad174 gpl
loaded_at 2019-01-19T09:09:43-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 13,14
15: cgroup_skb tag 7be49e3934a125ba gpl
loaded_at 2019-01-19T09:09:43-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 15,16
16: cgroup_skb tag 2a142ef67aaad174 gpl
loaded_at 2019-01-19T09:09:43-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 15,16
17: cgroup_skb tag 7be49e3934a125ba gpl
loaded_at 2019-01-19T09:09:44-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 17,18
18: cgroup_skb tag 2a142ef67aaad174 gpl
loaded_at 2019-01-19T09:09:44-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 17,18
21: cgroup_skb tag 7be49e3934a125ba gpl
loaded_at 2019-01-19T09:09:45-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 21,22
22: cgroup_skb tag 2a142ef67aaad174 gpl
loaded_at 2019-01-19T09:09:45-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 21,22
31: tracepoint name sys_enter tag 12504ba9402f952f gpl
loaded_at 2019-01-19T09:19:56-0300 uid 0
xlated 512B jited 374B memlock 4096B map_ids 30,29,28
32: tracepoint name sys_exit tag c1bd85c092d6e4aa gpl
loaded_at 2019-01-19T09:19:56-0300 uid 0
xlated 256B jited 191B memlock 4096B map_ids 30,29
# perf report -D | grep PERF_RECORD_BPF_EVENT | nl
1 0 55834574849 0x4fc8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 13
2 0 60129542145 0x5118 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 14
3 0 64424509441 0x5268 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 15
4 0 68719476737 0x53b8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 16
5 0 73014444033 0x5508 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 17
6 0 77309411329 0x5658 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 18
7 0 90194313217 0x57a8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 21
8 0 94489280513 0x58f8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 22
9 7 620922484360 0xb6390 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 29
10 7 620922486018 0xb6410 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 2, flags 0, id 29
11 7 620922579199 0xb6490 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 30
12 7 620922580240 0xb6510 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 2, flags 0, id 30
13 7 620922765207 0xb6598 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 31
14 7 620922874543 0xb6620 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 32
#
There, the 31 and 32 tracepoint BPF programs put in place by 'perf trace'.
Signed-off-by: Song Liu <songliubraving@fb.com>
Reviewed-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: kernel-team@fb.com
Cc: netdev@vger.kernel.org
Link: http://lkml.kernel.org/r/20190117161521.1341602-7-songliubraving@fb.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-01-18 00:15:18 +08:00
|
|
|
size_t perf_event__fprintf_bpf_event(union perf_event *event, FILE *fp)
|
|
|
|
{
|
2019-05-08 21:20:09 +08:00
|
|
|
return fprintf(fp, " type %u, flags %u, id %u\n",
|
perf tools: Handle PERF_RECORD_BPF_EVENT
This patch adds basic handling of PERF_RECORD_BPF_EVENT. Tracking of
PERF_RECORD_BPF_EVENT is OFF by default. Option --bpf-event is added to
turn it on.
Committer notes:
Add dummy machine__process_bpf_event() variant that returns zero for
systems without HAVE_LIBBPF_SUPPORT, such as Alpine Linux, unbreaking
the build in such systems.
Remove the needless include <machine.h> from bpf->event.h, provide just
forward declarations for the structs and unions in the parameters, to
reduce compilation time and needless rebuilds when machine.h gets
changed.
Committer testing:
When running with:
# perf record --bpf-event
On an older kernel where PERF_RECORD_BPF_EVENT and PERF_RECORD_KSYMBOL
is not present, we fallback to removing those two bits from
perf_event_attr, making the tool to continue to work on older kernels:
perf_event_attr:
size 112
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|PERIOD
read_format ID
disabled 1
inherit 1
mmap 1
comm 1
freq 1
enable_on_exec 1
task 1
precise_ip 3
sample_id_all 1
exclude_guest 1
mmap2 1
comm_exec 1
ksymbol 1
bpf_event 1
------------------------------------------------------------
sys_perf_event_open: pid 5779 cpu 0 group_fd -1 flags 0x8
sys_perf_event_open failed, error -22
switching off bpf_event
------------------------------------------------------------
perf_event_attr:
size 112
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|PERIOD
read_format ID
disabled 1
inherit 1
mmap 1
comm 1
freq 1
enable_on_exec 1
task 1
precise_ip 3
sample_id_all 1
exclude_guest 1
mmap2 1
comm_exec 1
ksymbol 1
------------------------------------------------------------
sys_perf_event_open: pid 5779 cpu 0 group_fd -1 flags 0x8
sys_perf_event_open failed, error -22
switching off ksymbol
------------------------------------------------------------
perf_event_attr:
size 112
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|PERIOD
read_format ID
disabled 1
inherit 1
mmap 1
comm 1
freq 1
enable_on_exec 1
task 1
precise_ip 3
sample_id_all 1
exclude_guest 1
mmap2 1
comm_exec 1
------------------------------------------------------------
And then proceeds to work without those two features.
As passing --bpf-event is an explicit action performed by the user, perhaps we
should emit a warning telling that the kernel has no such feature, but this can
be done on top of this patch.
Now with a kernel that supports these events, start the 'record --bpf-event -a'
and then run 'perf trace sleep 10000' that will use the BPF
augmented_raw_syscalls.o prebuilt (for another kernel version even) and thus
should generate PERF_RECORD_BPF_EVENT events:
[root@quaco ~]# perf record -e dummy -a --bpf-event
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.713 MB perf.data ]
[root@quaco ~]# bpftool prog
13: cgroup_skb tag 7be49e3934a125ba gpl
loaded_at 2019-01-19T09:09:43-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 13,14
14: cgroup_skb tag 2a142ef67aaad174 gpl
loaded_at 2019-01-19T09:09:43-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 13,14
15: cgroup_skb tag 7be49e3934a125ba gpl
loaded_at 2019-01-19T09:09:43-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 15,16
16: cgroup_skb tag 2a142ef67aaad174 gpl
loaded_at 2019-01-19T09:09:43-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 15,16
17: cgroup_skb tag 7be49e3934a125ba gpl
loaded_at 2019-01-19T09:09:44-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 17,18
18: cgroup_skb tag 2a142ef67aaad174 gpl
loaded_at 2019-01-19T09:09:44-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 17,18
21: cgroup_skb tag 7be49e3934a125ba gpl
loaded_at 2019-01-19T09:09:45-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 21,22
22: cgroup_skb tag 2a142ef67aaad174 gpl
loaded_at 2019-01-19T09:09:45-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 21,22
31: tracepoint name sys_enter tag 12504ba9402f952f gpl
loaded_at 2019-01-19T09:19:56-0300 uid 0
xlated 512B jited 374B memlock 4096B map_ids 30,29,28
32: tracepoint name sys_exit tag c1bd85c092d6e4aa gpl
loaded_at 2019-01-19T09:19:56-0300 uid 0
xlated 256B jited 191B memlock 4096B map_ids 30,29
# perf report -D | grep PERF_RECORD_BPF_EVENT | nl
1 0 55834574849 0x4fc8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 13
2 0 60129542145 0x5118 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 14
3 0 64424509441 0x5268 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 15
4 0 68719476737 0x53b8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 16
5 0 73014444033 0x5508 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 17
6 0 77309411329 0x5658 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 18
7 0 90194313217 0x57a8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 21
8 0 94489280513 0x58f8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 22
9 7 620922484360 0xb6390 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 29
10 7 620922486018 0xb6410 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 2, flags 0, id 29
11 7 620922579199 0xb6490 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 30
12 7 620922580240 0xb6510 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 2, flags 0, id 30
13 7 620922765207 0xb6598 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 31
14 7 620922874543 0xb6620 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 32
#
There, the 31 and 32 tracepoint BPF programs put in place by 'perf trace'.
Signed-off-by: Song Liu <songliubraving@fb.com>
Reviewed-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: kernel-team@fb.com
Cc: netdev@vger.kernel.org
Link: http://lkml.kernel.org/r/20190117161521.1341602-7-songliubraving@fb.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-01-18 00:15:18 +08:00
|
|
|
event->bpf_event.type, event->bpf_event.flags,
|
|
|
|
event->bpf_event.id);
|
|
|
|
}
|
|
|
|
|
2011-12-02 21:06:37 +08:00
|
|
|
size_t perf_event__fprintf(union perf_event *event, FILE *fp)
|
|
|
|
{
|
|
|
|
size_t ret = fprintf(fp, "PERF_RECORD_%s",
|
|
|
|
perf_event__name(event->header.type));
|
|
|
|
|
|
|
|
switch (event->header.type) {
|
|
|
|
case PERF_RECORD_COMM:
|
|
|
|
ret += perf_event__fprintf_comm(event, fp);
|
|
|
|
break;
|
|
|
|
case PERF_RECORD_FORK:
|
|
|
|
case PERF_RECORD_EXIT:
|
|
|
|
ret += perf_event__fprintf_task(event, fp);
|
|
|
|
break;
|
|
|
|
case PERF_RECORD_MMAP:
|
|
|
|
ret += perf_event__fprintf_mmap(event, fp);
|
perf tools: Add PERF_RECORD_NAMESPACES to include namespaces related info
Introduce a new option to record PERF_RECORD_NAMESPACES events emitted
by the kernel when fork, clone, setns or unshare are invoked. And update
perf-record documentation with the new option to record namespace
events.
Committer notes:
Combined it with a later patch to allow printing it via 'perf report -D'
and be able to test the feature introduced in this patch. Had to move
here also perf_ns__name(), that was introduced in another later patch.
Also used PRIu64 and PRIx64 to fix the build in some enfironments wrt:
util/event.c:1129:39: error: format '%lx' expects argument of type 'long unsigned int', but argument 6 has type 'long long unsigned int' [-Werror=format=]
ret += fprintf(fp, "%u/%s: %lu/0x%lx%s", idx
^
Testing it:
# perf record --namespaces -a
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 1.083 MB perf.data (423 samples) ]
#
# perf report -D
<SNIP>
3 2028902078892 0x115140 [0xa0]: PERF_RECORD_NAMESPACES 14783/14783 - nr_namespaces: 7
[0/net: 3/0xf0000081, 1/uts: 3/0xeffffffe, 2/ipc: 3/0xefffffff, 3/pid: 3/0xeffffffc,
4/user: 3/0xeffffffd, 5/mnt: 3/0xf0000000, 6/cgroup: 3/0xeffffffb]
0x1151e0 [0x30]: event: 9
.
. ... raw event: size 48 bytes
. 0000: 09 00 00 00 02 00 30 00 c4 71 82 68 0c 7f 00 00 ......0..q.h....
. 0010: a9 39 00 00 a9 39 00 00 94 28 fe 63 d8 01 00 00 .9...9...(.c....
. 0020: 03 00 00 00 00 00 00 00 ce c4 02 00 00 00 00 00 ................
<SNIP>
NAMESPACES events: 1
<SNIP>
#
Signed-off-by: Hari Bathini <hbathini@linux.vnet.ibm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@fb.com>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Aravinda Prasad <aravinda@linux.vnet.ibm.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sargun Dhillon <sargun@sargun.me>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/148891930386.25309.18412039920746995488.stgit@hbathini.in.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-08 04:41:43 +08:00
|
|
|
break;
|
|
|
|
case PERF_RECORD_NAMESPACES:
|
|
|
|
ret += perf_event__fprintf_namespaces(event, fp);
|
2011-12-02 21:06:37 +08:00
|
|
|
break;
|
2013-08-21 18:10:25 +08:00
|
|
|
case PERF_RECORD_MMAP2:
|
|
|
|
ret += perf_event__fprintf_mmap2(event, fp);
|
|
|
|
break;
|
2015-04-30 22:37:29 +08:00
|
|
|
case PERF_RECORD_AUX:
|
|
|
|
ret += perf_event__fprintf_aux(event, fp);
|
|
|
|
break;
|
2015-04-30 22:37:30 +08:00
|
|
|
case PERF_RECORD_ITRACE_START:
|
|
|
|
ret += perf_event__fprintf_itrace_start(event, fp);
|
|
|
|
break;
|
2015-07-21 17:44:03 +08:00
|
|
|
case PERF_RECORD_SWITCH:
|
|
|
|
case PERF_RECORD_SWITCH_CPU_WIDE:
|
|
|
|
ret += perf_event__fprintf_switch(event, fp);
|
|
|
|
break;
|
2018-01-08 00:03:53 +08:00
|
|
|
case PERF_RECORD_LOST:
|
|
|
|
ret += perf_event__fprintf_lost(event, fp);
|
|
|
|
break;
|
2019-01-18 00:15:17 +08:00
|
|
|
case PERF_RECORD_KSYMBOL:
|
|
|
|
ret += perf_event__fprintf_ksymbol(event, fp);
|
|
|
|
break;
|
perf tools: Handle PERF_RECORD_BPF_EVENT
This patch adds basic handling of PERF_RECORD_BPF_EVENT. Tracking of
PERF_RECORD_BPF_EVENT is OFF by default. Option --bpf-event is added to
turn it on.
Committer notes:
Add dummy machine__process_bpf_event() variant that returns zero for
systems without HAVE_LIBBPF_SUPPORT, such as Alpine Linux, unbreaking
the build in such systems.
Remove the needless include <machine.h> from bpf->event.h, provide just
forward declarations for the structs and unions in the parameters, to
reduce compilation time and needless rebuilds when machine.h gets
changed.
Committer testing:
When running with:
# perf record --bpf-event
On an older kernel where PERF_RECORD_BPF_EVENT and PERF_RECORD_KSYMBOL
is not present, we fallback to removing those two bits from
perf_event_attr, making the tool to continue to work on older kernels:
perf_event_attr:
size 112
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|PERIOD
read_format ID
disabled 1
inherit 1
mmap 1
comm 1
freq 1
enable_on_exec 1
task 1
precise_ip 3
sample_id_all 1
exclude_guest 1
mmap2 1
comm_exec 1
ksymbol 1
bpf_event 1
------------------------------------------------------------
sys_perf_event_open: pid 5779 cpu 0 group_fd -1 flags 0x8
sys_perf_event_open failed, error -22
switching off bpf_event
------------------------------------------------------------
perf_event_attr:
size 112
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|PERIOD
read_format ID
disabled 1
inherit 1
mmap 1
comm 1
freq 1
enable_on_exec 1
task 1
precise_ip 3
sample_id_all 1
exclude_guest 1
mmap2 1
comm_exec 1
ksymbol 1
------------------------------------------------------------
sys_perf_event_open: pid 5779 cpu 0 group_fd -1 flags 0x8
sys_perf_event_open failed, error -22
switching off ksymbol
------------------------------------------------------------
perf_event_attr:
size 112
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|PERIOD
read_format ID
disabled 1
inherit 1
mmap 1
comm 1
freq 1
enable_on_exec 1
task 1
precise_ip 3
sample_id_all 1
exclude_guest 1
mmap2 1
comm_exec 1
------------------------------------------------------------
And then proceeds to work without those two features.
As passing --bpf-event is an explicit action performed by the user, perhaps we
should emit a warning telling that the kernel has no such feature, but this can
be done on top of this patch.
Now with a kernel that supports these events, start the 'record --bpf-event -a'
and then run 'perf trace sleep 10000' that will use the BPF
augmented_raw_syscalls.o prebuilt (for another kernel version even) and thus
should generate PERF_RECORD_BPF_EVENT events:
[root@quaco ~]# perf record -e dummy -a --bpf-event
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.713 MB perf.data ]
[root@quaco ~]# bpftool prog
13: cgroup_skb tag 7be49e3934a125ba gpl
loaded_at 2019-01-19T09:09:43-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 13,14
14: cgroup_skb tag 2a142ef67aaad174 gpl
loaded_at 2019-01-19T09:09:43-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 13,14
15: cgroup_skb tag 7be49e3934a125ba gpl
loaded_at 2019-01-19T09:09:43-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 15,16
16: cgroup_skb tag 2a142ef67aaad174 gpl
loaded_at 2019-01-19T09:09:43-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 15,16
17: cgroup_skb tag 7be49e3934a125ba gpl
loaded_at 2019-01-19T09:09:44-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 17,18
18: cgroup_skb tag 2a142ef67aaad174 gpl
loaded_at 2019-01-19T09:09:44-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 17,18
21: cgroup_skb tag 7be49e3934a125ba gpl
loaded_at 2019-01-19T09:09:45-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 21,22
22: cgroup_skb tag 2a142ef67aaad174 gpl
loaded_at 2019-01-19T09:09:45-0300 uid 0
xlated 296B jited 229B memlock 4096B map_ids 21,22
31: tracepoint name sys_enter tag 12504ba9402f952f gpl
loaded_at 2019-01-19T09:19:56-0300 uid 0
xlated 512B jited 374B memlock 4096B map_ids 30,29,28
32: tracepoint name sys_exit tag c1bd85c092d6e4aa gpl
loaded_at 2019-01-19T09:19:56-0300 uid 0
xlated 256B jited 191B memlock 4096B map_ids 30,29
# perf report -D | grep PERF_RECORD_BPF_EVENT | nl
1 0 55834574849 0x4fc8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 13
2 0 60129542145 0x5118 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 14
3 0 64424509441 0x5268 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 15
4 0 68719476737 0x53b8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 16
5 0 73014444033 0x5508 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 17
6 0 77309411329 0x5658 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 18
7 0 90194313217 0x57a8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 21
8 0 94489280513 0x58f8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 22
9 7 620922484360 0xb6390 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 29
10 7 620922486018 0xb6410 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 2, flags 0, id 29
11 7 620922579199 0xb6490 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 30
12 7 620922580240 0xb6510 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 2, flags 0, id 30
13 7 620922765207 0xb6598 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 31
14 7 620922874543 0xb6620 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 32
#
There, the 31 and 32 tracepoint BPF programs put in place by 'perf trace'.
Signed-off-by: Song Liu <songliubraving@fb.com>
Reviewed-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: kernel-team@fb.com
Cc: netdev@vger.kernel.org
Link: http://lkml.kernel.org/r/20190117161521.1341602-7-songliubraving@fb.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-01-18 00:15:18 +08:00
|
|
|
case PERF_RECORD_BPF_EVENT:
|
|
|
|
ret += perf_event__fprintf_bpf_event(event, fp);
|
|
|
|
break;
|
2011-12-02 21:06:37 +08:00
|
|
|
default:
|
|
|
|
ret += fprintf(fp, "\n");
|
|
|
|
}
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2012-10-07 03:26:02 +08:00
|
|
|
int perf_event__process(struct perf_tool *tool __maybe_unused,
|
|
|
|
union perf_event *event,
|
2013-09-11 22:18:24 +08:00
|
|
|
struct perf_sample *sample,
|
2012-10-07 03:26:02 +08:00
|
|
|
struct machine *machine)
|
2010-08-02 20:38:51 +08:00
|
|
|
{
|
2013-09-11 22:18:24 +08:00
|
|
|
return machine__process_event(machine, event, sample);
|
2010-08-02 20:38:51 +08:00
|
|
|
}
|
|
|
|
|
2018-04-27 03:52:34 +08:00
|
|
|
struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr,
|
|
|
|
struct addr_location *al)
|
perf tools: Consolidate symbol resolving across all tools
Now we have a very high level routine for simple tools to
process IP sample events:
int event__preprocess_sample(const event_t *self,
struct addr_location *al,
symbol_filter_t filter)
It receives the event itself and will insert new threads in the
global threads list and resolve the map and symbol, filling all
this info into the new addr_location struct, so that tools like
annotate and report can further process the event by creating
hist_entries in their specific way (with or without callgraphs,
etc).
It in turn uses the new next layer function:
void thread__find_addr_location(struct thread *self, u8 cpumode,
enum map_type type, u64 addr,
struct addr_location *al,
symbol_filter_t filter)
This one will, given a thread (userspace or the kernel kthread
one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE
too in the near future) at the given cpumode, taking vdsos into
account (userspace hit, but kernel symbol) and will fill all
these details in the addr_location given.
Tools that need a more compact API for plain function
resolution, like 'kmem', can use this other one:
struct symbol *thread__find_function(struct thread *self, u64 addr,
symbol_filter_t filter)
So, to resolve a kernel symbol, that is all the 'kmem' tool
needs, its just a matter of calling:
sym = thread__find_function(kthread, addr, NULL);
The 'filter' parameter is needed because we do lazy
parsing/loading of ELF symtabs or /proc/kallsyms.
With this we remove more code duplication all around, which is
always good, huh? :-)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: John Kacur <jkacur@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
|
|
|
{
|
2014-03-22 04:57:01 +08:00
|
|
|
struct map_groups *mg = thread->mg;
|
2014-10-23 23:50:25 +08:00
|
|
|
struct machine *machine = mg->machine;
|
2013-08-07 19:38:46 +08:00
|
|
|
bool load_map = false;
|
perf tools: Consolidate symbol resolving across all tools
Now we have a very high level routine for simple tools to
process IP sample events:
int event__preprocess_sample(const event_t *self,
struct addr_location *al,
symbol_filter_t filter)
It receives the event itself and will insert new threads in the
global threads list and resolve the map and symbol, filling all
this info into the new addr_location struct, so that tools like
annotate and report can further process the event by creating
hist_entries in their specific way (with or without callgraphs,
etc).
It in turn uses the new next layer function:
void thread__find_addr_location(struct thread *self, u8 cpumode,
enum map_type type, u64 addr,
struct addr_location *al,
symbol_filter_t filter)
This one will, given a thread (userspace or the kernel kthread
one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE
too in the near future) at the given cpumode, taking vdsos into
account (userspace hit, but kernel symbol) and will fill all
these details in the addr_location given.
Tools that need a more compact API for plain function
resolution, like 'kmem', can use this other one:
struct symbol *thread__find_function(struct thread *self, u64 addr,
symbol_filter_t filter)
So, to resolve a kernel symbol, that is all the 'kmem' tool
needs, its just a matter of calling:
sym = thread__find_function(kthread, addr, NULL);
The 'filter' parameter is needed because we do lazy
parsing/loading of ELF symtabs or /proc/kallsyms.
With this we remove more code duplication all around, which is
always good, huh? :-)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: John Kacur <jkacur@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
|
|
|
|
2013-12-20 04:20:06 +08:00
|
|
|
al->machine = machine;
|
2013-11-06 02:32:36 +08:00
|
|
|
al->thread = thread;
|
perf tools: Consolidate symbol resolving across all tools
Now we have a very high level routine for simple tools to
process IP sample events:
int event__preprocess_sample(const event_t *self,
struct addr_location *al,
symbol_filter_t filter)
It receives the event itself and will insert new threads in the
global threads list and resolve the map and symbol, filling all
this info into the new addr_location struct, so that tools like
annotate and report can further process the event by creating
hist_entries in their specific way (with or without callgraphs,
etc).
It in turn uses the new next layer function:
void thread__find_addr_location(struct thread *self, u8 cpumode,
enum map_type type, u64 addr,
struct addr_location *al,
symbol_filter_t filter)
This one will, given a thread (userspace or the kernel kthread
one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE
too in the near future) at the given cpumode, taking vdsos into
account (userspace hit, but kernel symbol) and will fill all
these details in the addr_location given.
Tools that need a more compact API for plain function
resolution, like 'kmem', can use this other one:
struct symbol *thread__find_function(struct thread *self, u64 addr,
symbol_filter_t filter)
So, to resolve a kernel symbol, that is all the 'kmem' tool
needs, its just a matter of calling:
sym = thread__find_function(kthread, addr, NULL);
The 'filter' parameter is needed because we do lazy
parsing/loading of ELF symtabs or /proc/kallsyms.
With this we remove more code duplication all around, which is
always good, huh? :-)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: John Kacur <jkacur@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
|
|
|
al->addr = addr;
|
2010-04-19 13:32:50 +08:00
|
|
|
al->cpumode = cpumode;
|
2014-03-18 03:59:21 +08:00
|
|
|
al->filtered = 0;
|
perf tools: Consolidate symbol resolving across all tools
Now we have a very high level routine for simple tools to
process IP sample events:
int event__preprocess_sample(const event_t *self,
struct addr_location *al,
symbol_filter_t filter)
It receives the event itself and will insert new threads in the
global threads list and resolve the map and symbol, filling all
this info into the new addr_location struct, so that tools like
annotate and report can further process the event by creating
hist_entries in their specific way (with or without callgraphs,
etc).
It in turn uses the new next layer function:
void thread__find_addr_location(struct thread *self, u8 cpumode,
enum map_type type, u64 addr,
struct addr_location *al,
symbol_filter_t filter)
This one will, given a thread (userspace or the kernel kthread
one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE
too in the near future) at the given cpumode, taking vdsos into
account (userspace hit, but kernel symbol) and will fill all
these details in the addr_location given.
Tools that need a more compact API for plain function
resolution, like 'kmem', can use this other one:
struct symbol *thread__find_function(struct thread *self, u64 addr,
symbol_filter_t filter)
So, to resolve a kernel symbol, that is all the 'kmem' tool
needs, its just a matter of calling:
sym = thread__find_function(kthread, addr, NULL);
The 'filter' parameter is needed because we do lazy
parsing/loading of ELF symtabs or /proc/kallsyms.
With this we remove more code duplication all around, which is
always good, huh? :-)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: John Kacur <jkacur@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
|
|
|
|
2011-11-28 17:56:39 +08:00
|
|
|
if (machine == NULL) {
|
|
|
|
al->map = NULL;
|
2018-04-24 22:58:56 +08:00
|
|
|
return NULL;
|
2011-11-28 17:56:39 +08:00
|
|
|
}
|
|
|
|
|
2010-04-19 13:32:50 +08:00
|
|
|
if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) {
|
perf tools: Consolidate symbol resolving across all tools
Now we have a very high level routine for simple tools to
process IP sample events:
int event__preprocess_sample(const event_t *self,
struct addr_location *al,
symbol_filter_t filter)
It receives the event itself and will insert new threads in the
global threads list and resolve the map and symbol, filling all
this info into the new addr_location struct, so that tools like
annotate and report can further process the event by creating
hist_entries in their specific way (with or without callgraphs,
etc).
It in turn uses the new next layer function:
void thread__find_addr_location(struct thread *self, u8 cpumode,
enum map_type type, u64 addr,
struct addr_location *al,
symbol_filter_t filter)
This one will, given a thread (userspace or the kernel kthread
one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE
too in the near future) at the given cpumode, taking vdsos into
account (userspace hit, but kernel symbol) and will fill all
these details in the addr_location given.
Tools that need a more compact API for plain function
resolution, like 'kmem', can use this other one:
struct symbol *thread__find_function(struct thread *self, u64 addr,
symbol_filter_t filter)
So, to resolve a kernel symbol, that is all the 'kmem' tool
needs, its just a matter of calling:
sym = thread__find_function(kthread, addr, NULL);
The 'filter' parameter is needed because we do lazy
parsing/loading of ELF symtabs or /proc/kallsyms.
With this we remove more code duplication all around, which is
always good, huh? :-)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: John Kacur <jkacur@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
|
|
|
al->level = 'k';
|
2010-04-28 08:17:50 +08:00
|
|
|
mg = &machine->kmaps;
|
2013-08-07 19:38:46 +08:00
|
|
|
load_map = true;
|
2010-04-19 13:32:50 +08:00
|
|
|
} else if (cpumode == PERF_RECORD_MISC_USER && perf_host) {
|
perf tools: Consolidate symbol resolving across all tools
Now we have a very high level routine for simple tools to
process IP sample events:
int event__preprocess_sample(const event_t *self,
struct addr_location *al,
symbol_filter_t filter)
It receives the event itself and will insert new threads in the
global threads list and resolve the map and symbol, filling all
this info into the new addr_location struct, so that tools like
annotate and report can further process the event by creating
hist_entries in their specific way (with or without callgraphs,
etc).
It in turn uses the new next layer function:
void thread__find_addr_location(struct thread *self, u8 cpumode,
enum map_type type, u64 addr,
struct addr_location *al,
symbol_filter_t filter)
This one will, given a thread (userspace or the kernel kthread
one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE
too in the near future) at the given cpumode, taking vdsos into
account (userspace hit, but kernel symbol) and will fill all
these details in the addr_location given.
Tools that need a more compact API for plain function
resolution, like 'kmem', can use this other one:
struct symbol *thread__find_function(struct thread *self, u64 addr,
symbol_filter_t filter)
So, to resolve a kernel symbol, that is all the 'kmem' tool
needs, its just a matter of calling:
sym = thread__find_function(kthread, addr, NULL);
The 'filter' parameter is needed because we do lazy
parsing/loading of ELF symtabs or /proc/kallsyms.
With this we remove more code duplication all around, which is
always good, huh? :-)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: John Kacur <jkacur@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
|
|
|
al->level = '.';
|
2010-04-19 13:32:50 +08:00
|
|
|
} else if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) {
|
|
|
|
al->level = 'g';
|
2010-04-28 08:17:50 +08:00
|
|
|
mg = &machine->kmaps;
|
2013-08-07 19:38:46 +08:00
|
|
|
load_map = true;
|
2013-12-21 04:52:56 +08:00
|
|
|
} else if (cpumode == PERF_RECORD_MISC_GUEST_USER && perf_guest) {
|
|
|
|
al->level = 'u';
|
2010-04-19 13:32:50 +08:00
|
|
|
} else {
|
2013-12-21 04:52:56 +08:00
|
|
|
al->level = 'H';
|
perf tools: Consolidate symbol resolving across all tools
Now we have a very high level routine for simple tools to
process IP sample events:
int event__preprocess_sample(const event_t *self,
struct addr_location *al,
symbol_filter_t filter)
It receives the event itself and will insert new threads in the
global threads list and resolve the map and symbol, filling all
this info into the new addr_location struct, so that tools like
annotate and report can further process the event by creating
hist_entries in their specific way (with or without callgraphs,
etc).
It in turn uses the new next layer function:
void thread__find_addr_location(struct thread *self, u8 cpumode,
enum map_type type, u64 addr,
struct addr_location *al,
symbol_filter_t filter)
This one will, given a thread (userspace or the kernel kthread
one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE
too in the near future) at the given cpumode, taking vdsos into
account (userspace hit, but kernel symbol) and will fill all
these details in the addr_location given.
Tools that need a more compact API for plain function
resolution, like 'kmem', can use this other one:
struct symbol *thread__find_function(struct thread *self, u64 addr,
symbol_filter_t filter)
So, to resolve a kernel symbol, that is all the 'kmem' tool
needs, its just a matter of calling:
sym = thread__find_function(kthread, addr, NULL);
The 'filter' parameter is needed because we do lazy
parsing/loading of ELF symtabs or /proc/kallsyms.
With this we remove more code duplication all around, which is
always good, huh? :-)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: John Kacur <jkacur@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
|
|
|
al->map = NULL;
|
2010-04-19 13:32:50 +08:00
|
|
|
|
|
|
|
if ((cpumode == PERF_RECORD_MISC_GUEST_USER ||
|
|
|
|
cpumode == PERF_RECORD_MISC_GUEST_KERNEL) &&
|
|
|
|
!perf_guest)
|
2014-03-18 03:59:21 +08:00
|
|
|
al->filtered |= (1 << HIST_FILTER__GUEST);
|
2010-04-19 13:32:50 +08:00
|
|
|
if ((cpumode == PERF_RECORD_MISC_USER ||
|
|
|
|
cpumode == PERF_RECORD_MISC_KERNEL) &&
|
|
|
|
!perf_host)
|
2014-03-18 03:59:21 +08:00
|
|
|
al->filtered |= (1 << HIST_FILTER__HOST);
|
2010-04-19 13:32:50 +08:00
|
|
|
|
2018-04-24 22:58:56 +08:00
|
|
|
return NULL;
|
perf tools: Consolidate symbol resolving across all tools
Now we have a very high level routine for simple tools to
process IP sample events:
int event__preprocess_sample(const event_t *self,
struct addr_location *al,
symbol_filter_t filter)
It receives the event itself and will insert new threads in the
global threads list and resolve the map and symbol, filling all
this info into the new addr_location struct, so that tools like
annotate and report can further process the event by creating
hist_entries in their specific way (with or without callgraphs,
etc).
It in turn uses the new next layer function:
void thread__find_addr_location(struct thread *self, u8 cpumode,
enum map_type type, u64 addr,
struct addr_location *al,
symbol_filter_t filter)
This one will, given a thread (userspace or the kernel kthread
one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE
too in the near future) at the given cpumode, taking vdsos into
account (userspace hit, but kernel symbol) and will fill all
these details in the addr_location given.
Tools that need a more compact API for plain function
resolution, like 'kmem', can use this other one:
struct symbol *thread__find_function(struct thread *self, u64 addr,
symbol_filter_t filter)
So, to resolve a kernel symbol, that is all the 'kmem' tool
needs, its just a matter of calling:
sym = thread__find_function(kthread, addr, NULL);
The 'filter' parameter is needed because we do lazy
parsing/loading of ELF symtabs or /proc/kallsyms.
With this we remove more code duplication all around, which is
always good, huh? :-)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: John Kacur <jkacur@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
|
|
|
}
|
perf tools: Stop fallbacking to kallsyms for vdso symbols lookup
David reports that:
<quote>
Perf has this hack where it uses the kernel symbol map as a backup when
a symbol can't be found in the user's symbol table(s).
This causes problems because the tests driving this code path use
machine__kernel_ip(), and that is completely meaningless on Sparc. On
sparc64 the kernel and user live in physically separate virtual address
spaces, rather than a shared one. And the kernel lives at a virtual
address that overlaps common userspace addresses. So this test passes
almost all the time when a user symbol lookup fails.
The consequence of this is that, if the unfound user virtual address in
the sample doesn't match up to a kernel symbol either, we trigger things
like this code in builtin-top.c:
if (al.sym == NULL && al.map != NULL) {
const char *msg = "Kernel samples will not be resolved.\n";
/*
* As we do lazy loading of symtabs we only will know if the
* specified vmlinux file is invalid when we actually have a
* hit in kernel space and then try to load it. So if we get
* here and there are _no_ symbols in the DSO backing the
* kernel map, bail out.
*
* We may never get here, for instance, if we use -K/
* --hide-kernel-symbols, even if the user specifies an
* invalid --vmlinux ;-)
*/
if (!machine->kptr_restrict_warned && !top->vmlinux_warned &&
__map__is_kernel(al.map) && map__has_symbols(al.map)) {
if (symbol_conf.vmlinux_name) {
char serr[256];
dso__strerror_load(al.map->dso, serr, sizeof(serr));
ui__warning("The %s file can't be used: %s\n%s",
symbol_conf.vmlinux_name, serr, msg);
} else {
ui__warning("A vmlinux file was not found.\n%s",
msg);
}
if (use_browser <= 0)
sleep(5);
top->vmlinux_warned = true;
}
}
When I fire up a compilation on sparc, this triggers immediately.
I'm trying to figure out what the "backup to kernel map" code is
accomplishing.
I see some language in the current code and in the changes that have
happened in this area talking about vdso. Does that really happen?
The vdso is mapped into userspace virtual addresses, not kernel ones.
More history. This didn't cause problems on sparc some time ago,
because the kernel IP check used to be "ip < 0" :-) Sparc kernel
addresses are not negative. But now with machine__kernel_ip(), which
works using the symbol table determined kernel address range, it does
trigger.
What it all boils down to is that on architectures like sparc,
machine__kernel_ip() should always return false in this scenerio, and
therefore this kind of logic:
if (cpumode == PERF_RECORD_MISC_USER && machine &&
mg != &machine->kmaps &&
machine__kernel_ip(machine, al->addr)) {
is basically invalid. PERF_RECORD_MISC_USER implies no kernel address
can possibly match for the sample/event in question (no matter how
hard you try!) :-)
</>
So, I thought something had changed and in the past we would somehow
find that address in the kallsyms, but I couldn't find anything to back
that up, the patch introducing this is over a decade old, lots of things
changed, so I was just thinking I was missing something.
I tried a gtod busy loop to generate vdso activity and added a 'perf
probe' at that branch, on x86_64 to see if it ever gets hit:
Made thread__find_map() noinline, as 'perf probe' in lines of inline
functions seems to not be working, only at function start. (Masami?)
# perf probe -x ~/bin/perf -L thread__find_map:57
<thread__find_map@/home/acme/git/perf/tools/perf/util/event.c:57>
57 if (cpumode == PERF_RECORD_MISC_USER && machine &&
58 mg != &machine->kmaps &&
59 machine__kernel_ip(machine, al->addr)) {
60 mg = &machine->kmaps;
61 load_map = true;
62 goto try_again;
}
} else {
/*
* Kernel maps might be changed when loading
* symbols so loading
* must be done prior to using kernel maps.
*/
69 if (load_map)
70 map__load(al->map);
71 al->addr = al->map->map_ip(al->map, al->addr);
# perf probe -x ~/bin/perf thread__find_map:60
Added new event:
probe_perf:thread__find_map (on thread__find_map:60 in /home/acme/bin/perf)
You can now use it in all perf tools, such as:
perf record -e probe_perf:thread__find_map -aR sleep 1
#
Then used this to see if, system wide, those probe points were being hit:
# perf trace -e *perf:thread*/max-stack=8/
^C[root@jouet ~]#
No hits when running 'perf top' and:
# cat gtod.c
#include <sys/time.h>
int main(void)
{
struct timeval tv;
while (1)
gettimeofday(&tv, 0);
return 0;
}
[root@jouet c]# ./gtod
^C
Pressed 'P' in 'perf top' and the [vdso] samples are there:
62.84% [vdso] [.] __vdso_gettimeofday
8.13% gtod [.] main
7.51% [vdso] [.] 0x0000000000000914
5.78% [vdso] [.] 0x0000000000000917
5.43% gtod [.] _init
2.71% [vdso] [.] 0x000000000000092d
0.35% [kernel] [k] native_io_delay
0.33% libc-2.26.so [.] __memmove_avx_unaligned_erms
0.20% [vdso] [.] 0x000000000000091d
0.17% [i2c_i801] [k] i801_access
0.06% firefox [.] free
0.06% libglib-2.0.so.0.5400.3 [.] g_source_iter_next
0.05% [vdso] [.] 0x0000000000000919
0.05% libpthread-2.26.so [.] __pthread_mutex_lock
0.05% libpixman-1.so.0.34.0 [.] 0x000000000006d3a7
0.04% [kernel] [k] entry_SYSCALL_64_trampoline
0.04% libxul.so [.] style::dom_apis::query_selector_slow
0.04% [kernel] [k] module_get_kallsym
0.04% firefox [.] malloc
0.04% [vdso] [.] 0x0000000000000910
I added a 'perf probe' to thread__find_map:69, and that surely got tons
of hits, i.e. for every map found, just to make sure the 'perf probe'
command was really working.
In the process I noticed a bug, we're only have records for '[vdso]' for
pre-existing commands, i.e. ones that are running when we start 'perf top',
when we will generate the PERF_RECORD_MMAP by looking at /perf/PID/maps.
I.e. like this, for preexisting processes with a vdso map, again,
tracing for all the system, only pre-existing processes get a [vdso] map
(when having one):
[root@jouet ~]# perf probe -x ~/bin/perf __machine__addnew_vdso
Added new event:
probe_perf:__machine__addnew_vdso (on __machine__addnew_vdso in /home/acme/bin/perf)
You can now use it in all perf tools, such as:
perf record -e probe_perf:__machine__addnew_vdso -aR sleep 1
[root@jouet ~]# perf trace -e probe_perf:__machine__addnew_vdso/max-stack=8/
0.000 probe_perf:__machine__addnew_vdso:(568eb3)
__machine__addnew_vdso (/home/acme/bin/perf)
map__new (/home/acme/bin/perf)
machine__process_mmap2_event (/home/acme/bin/perf)
machine__process_event (/home/acme/bin/perf)
perf_event__process (/home/acme/bin/perf)
perf_tool__process_synth_event (/home/acme/bin/perf)
perf_event__synthesize_mmap_events (/home/acme/bin/perf)
__event__synthesize_thread (/home/acme/bin/perf)
The kernel is generating a PERF_RECORD_MMAP for vDSOs, but somehow
'perf top' is not getting those records while 'perf record' is:
# perf record ~acme/c/gtod
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.076 MB perf.data (1499 samples) ]
# perf report -D | grep PERF_RECORD_MMAP2
71293612401913 0x11b48 [0x70]: PERF_RECORD_MMAP2 25484/25484: [0x400000(0x1000) @ 0 fd:02 1137 541179306]: r-xp /home/acme/c/gtod
71293612419012 0x11be0 [0x70]: PERF_RECORD_MMAP2 25484/25484: [0x7fa4a2783000(0x227000) @ 0 fd:00 3146370 854107250]: r-xp /usr/lib64/ld-2.26.so
71293612432110 0x11c50 [0x60]: PERF_RECORD_MMAP2 25484/25484: [0x7ffcdb53a000(0x2000) @ 0 00:00 0 0]: r-xp [vdso]
71293612509944 0x11cb0 [0x70]: PERF_RECORD_MMAP2 25484/25484: [0x7fa4a23cd000(0x3b6000) @ 0 fd:00 3149723 262067164]: r-xp /usr/lib64/libc-2.26.so
#
# perf script | grep vdso | head
gtod 25484 71293.612768: 2485554 cycles:ppp: 7ffcdb53a914 [unknown] ([vdso])
gtod 25484 71293.613576: 2149343 cycles:ppp: 7ffcdb53a917 [unknown] ([vdso])
gtod 25484 71293.614274: 1814652 cycles:ppp: 7ffcdb53aca8 __vdso_gettimeofday+0x98 ([vdso])
gtod 25484 71293.614862: 1669070 cycles:ppp: 7ffcdb53acc5 __vdso_gettimeofday+0xb5 ([vdso])
gtod 25484 71293.615404: 1451589 cycles:ppp: 7ffcdb53acc5 __vdso_gettimeofday+0xb5 ([vdso])
gtod 25484 71293.615999: 1269941 cycles:ppp: 7ffcdb53ace6 __vdso_gettimeofday+0xd6 ([vdso])
gtod 25484 71293.616405: 1177946 cycles:ppp: 7ffcdb53a914 [unknown] ([vdso])
gtod 25484 71293.616775: 1121290 cycles:ppp: 7ffcdb53ac47 __vdso_gettimeofday+0x37 ([vdso])
gtod 25484 71293.617150: 1037721 cycles:ppp: 7ffcdb53ace6 __vdso_gettimeofday+0xd6 ([vdso])
gtod 25484 71293.617478: 994526 cycles:ppp: 7ffcdb53ace6 __vdso_gettimeofday+0xd6 ([vdso])
#
The patch is the obvious one and with it we also continue to resolve
vdso symbols for pre-existing processes in 'perf top' and for all
processes in 'perf record' + 'perf report/script'.
Suggested-by: David Miller <davem@davemloft.net>
Acked-by: David Miller <davem@davemloft.net>
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: https://lkml.kernel.org/n/tip-cs7skq9pp0kjypiju6o7trse@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-10-17 04:08:29 +08:00
|
|
|
|
2018-04-27 03:52:34 +08:00
|
|
|
al->map = map_groups__find(mg, al->addr);
|
perf tools: Stop fallbacking to kallsyms for vdso symbols lookup
David reports that:
<quote>
Perf has this hack where it uses the kernel symbol map as a backup when
a symbol can't be found in the user's symbol table(s).
This causes problems because the tests driving this code path use
machine__kernel_ip(), and that is completely meaningless on Sparc. On
sparc64 the kernel and user live in physically separate virtual address
spaces, rather than a shared one. And the kernel lives at a virtual
address that overlaps common userspace addresses. So this test passes
almost all the time when a user symbol lookup fails.
The consequence of this is that, if the unfound user virtual address in
the sample doesn't match up to a kernel symbol either, we trigger things
like this code in builtin-top.c:
if (al.sym == NULL && al.map != NULL) {
const char *msg = "Kernel samples will not be resolved.\n";
/*
* As we do lazy loading of symtabs we only will know if the
* specified vmlinux file is invalid when we actually have a
* hit in kernel space and then try to load it. So if we get
* here and there are _no_ symbols in the DSO backing the
* kernel map, bail out.
*
* We may never get here, for instance, if we use -K/
* --hide-kernel-symbols, even if the user specifies an
* invalid --vmlinux ;-)
*/
if (!machine->kptr_restrict_warned && !top->vmlinux_warned &&
__map__is_kernel(al.map) && map__has_symbols(al.map)) {
if (symbol_conf.vmlinux_name) {
char serr[256];
dso__strerror_load(al.map->dso, serr, sizeof(serr));
ui__warning("The %s file can't be used: %s\n%s",
symbol_conf.vmlinux_name, serr, msg);
} else {
ui__warning("A vmlinux file was not found.\n%s",
msg);
}
if (use_browser <= 0)
sleep(5);
top->vmlinux_warned = true;
}
}
When I fire up a compilation on sparc, this triggers immediately.
I'm trying to figure out what the "backup to kernel map" code is
accomplishing.
I see some language in the current code and in the changes that have
happened in this area talking about vdso. Does that really happen?
The vdso is mapped into userspace virtual addresses, not kernel ones.
More history. This didn't cause problems on sparc some time ago,
because the kernel IP check used to be "ip < 0" :-) Sparc kernel
addresses are not negative. But now with machine__kernel_ip(), which
works using the symbol table determined kernel address range, it does
trigger.
What it all boils down to is that on architectures like sparc,
machine__kernel_ip() should always return false in this scenerio, and
therefore this kind of logic:
if (cpumode == PERF_RECORD_MISC_USER && machine &&
mg != &machine->kmaps &&
machine__kernel_ip(machine, al->addr)) {
is basically invalid. PERF_RECORD_MISC_USER implies no kernel address
can possibly match for the sample/event in question (no matter how
hard you try!) :-)
</>
So, I thought something had changed and in the past we would somehow
find that address in the kallsyms, but I couldn't find anything to back
that up, the patch introducing this is over a decade old, lots of things
changed, so I was just thinking I was missing something.
I tried a gtod busy loop to generate vdso activity and added a 'perf
probe' at that branch, on x86_64 to see if it ever gets hit:
Made thread__find_map() noinline, as 'perf probe' in lines of inline
functions seems to not be working, only at function start. (Masami?)
# perf probe -x ~/bin/perf -L thread__find_map:57
<thread__find_map@/home/acme/git/perf/tools/perf/util/event.c:57>
57 if (cpumode == PERF_RECORD_MISC_USER && machine &&
58 mg != &machine->kmaps &&
59 machine__kernel_ip(machine, al->addr)) {
60 mg = &machine->kmaps;
61 load_map = true;
62 goto try_again;
}
} else {
/*
* Kernel maps might be changed when loading
* symbols so loading
* must be done prior to using kernel maps.
*/
69 if (load_map)
70 map__load(al->map);
71 al->addr = al->map->map_ip(al->map, al->addr);
# perf probe -x ~/bin/perf thread__find_map:60
Added new event:
probe_perf:thread__find_map (on thread__find_map:60 in /home/acme/bin/perf)
You can now use it in all perf tools, such as:
perf record -e probe_perf:thread__find_map -aR sleep 1
#
Then used this to see if, system wide, those probe points were being hit:
# perf trace -e *perf:thread*/max-stack=8/
^C[root@jouet ~]#
No hits when running 'perf top' and:
# cat gtod.c
#include <sys/time.h>
int main(void)
{
struct timeval tv;
while (1)
gettimeofday(&tv, 0);
return 0;
}
[root@jouet c]# ./gtod
^C
Pressed 'P' in 'perf top' and the [vdso] samples are there:
62.84% [vdso] [.] __vdso_gettimeofday
8.13% gtod [.] main
7.51% [vdso] [.] 0x0000000000000914
5.78% [vdso] [.] 0x0000000000000917
5.43% gtod [.] _init
2.71% [vdso] [.] 0x000000000000092d
0.35% [kernel] [k] native_io_delay
0.33% libc-2.26.so [.] __memmove_avx_unaligned_erms
0.20% [vdso] [.] 0x000000000000091d
0.17% [i2c_i801] [k] i801_access
0.06% firefox [.] free
0.06% libglib-2.0.so.0.5400.3 [.] g_source_iter_next
0.05% [vdso] [.] 0x0000000000000919
0.05% libpthread-2.26.so [.] __pthread_mutex_lock
0.05% libpixman-1.so.0.34.0 [.] 0x000000000006d3a7
0.04% [kernel] [k] entry_SYSCALL_64_trampoline
0.04% libxul.so [.] style::dom_apis::query_selector_slow
0.04% [kernel] [k] module_get_kallsym
0.04% firefox [.] malloc
0.04% [vdso] [.] 0x0000000000000910
I added a 'perf probe' to thread__find_map:69, and that surely got tons
of hits, i.e. for every map found, just to make sure the 'perf probe'
command was really working.
In the process I noticed a bug, we're only have records for '[vdso]' for
pre-existing commands, i.e. ones that are running when we start 'perf top',
when we will generate the PERF_RECORD_MMAP by looking at /perf/PID/maps.
I.e. like this, for preexisting processes with a vdso map, again,
tracing for all the system, only pre-existing processes get a [vdso] map
(when having one):
[root@jouet ~]# perf probe -x ~/bin/perf __machine__addnew_vdso
Added new event:
probe_perf:__machine__addnew_vdso (on __machine__addnew_vdso in /home/acme/bin/perf)
You can now use it in all perf tools, such as:
perf record -e probe_perf:__machine__addnew_vdso -aR sleep 1
[root@jouet ~]# perf trace -e probe_perf:__machine__addnew_vdso/max-stack=8/
0.000 probe_perf:__machine__addnew_vdso:(568eb3)
__machine__addnew_vdso (/home/acme/bin/perf)
map__new (/home/acme/bin/perf)
machine__process_mmap2_event (/home/acme/bin/perf)
machine__process_event (/home/acme/bin/perf)
perf_event__process (/home/acme/bin/perf)
perf_tool__process_synth_event (/home/acme/bin/perf)
perf_event__synthesize_mmap_events (/home/acme/bin/perf)
__event__synthesize_thread (/home/acme/bin/perf)
The kernel is generating a PERF_RECORD_MMAP for vDSOs, but somehow
'perf top' is not getting those records while 'perf record' is:
# perf record ~acme/c/gtod
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.076 MB perf.data (1499 samples) ]
# perf report -D | grep PERF_RECORD_MMAP2
71293612401913 0x11b48 [0x70]: PERF_RECORD_MMAP2 25484/25484: [0x400000(0x1000) @ 0 fd:02 1137 541179306]: r-xp /home/acme/c/gtod
71293612419012 0x11be0 [0x70]: PERF_RECORD_MMAP2 25484/25484: [0x7fa4a2783000(0x227000) @ 0 fd:00 3146370 854107250]: r-xp /usr/lib64/ld-2.26.so
71293612432110 0x11c50 [0x60]: PERF_RECORD_MMAP2 25484/25484: [0x7ffcdb53a000(0x2000) @ 0 00:00 0 0]: r-xp [vdso]
71293612509944 0x11cb0 [0x70]: PERF_RECORD_MMAP2 25484/25484: [0x7fa4a23cd000(0x3b6000) @ 0 fd:00 3149723 262067164]: r-xp /usr/lib64/libc-2.26.so
#
# perf script | grep vdso | head
gtod 25484 71293.612768: 2485554 cycles:ppp: 7ffcdb53a914 [unknown] ([vdso])
gtod 25484 71293.613576: 2149343 cycles:ppp: 7ffcdb53a917 [unknown] ([vdso])
gtod 25484 71293.614274: 1814652 cycles:ppp: 7ffcdb53aca8 __vdso_gettimeofday+0x98 ([vdso])
gtod 25484 71293.614862: 1669070 cycles:ppp: 7ffcdb53acc5 __vdso_gettimeofday+0xb5 ([vdso])
gtod 25484 71293.615404: 1451589 cycles:ppp: 7ffcdb53acc5 __vdso_gettimeofday+0xb5 ([vdso])
gtod 25484 71293.615999: 1269941 cycles:ppp: 7ffcdb53ace6 __vdso_gettimeofday+0xd6 ([vdso])
gtod 25484 71293.616405: 1177946 cycles:ppp: 7ffcdb53a914 [unknown] ([vdso])
gtod 25484 71293.616775: 1121290 cycles:ppp: 7ffcdb53ac47 __vdso_gettimeofday+0x37 ([vdso])
gtod 25484 71293.617150: 1037721 cycles:ppp: 7ffcdb53ace6 __vdso_gettimeofday+0xd6 ([vdso])
gtod 25484 71293.617478: 994526 cycles:ppp: 7ffcdb53ace6 __vdso_gettimeofday+0xd6 ([vdso])
#
The patch is the obvious one and with it we also continue to resolve
vdso symbols for pre-existing processes in 'perf top' and for all
processes in 'perf record' + 'perf report/script'.
Suggested-by: David Miller <davem@davemloft.net>
Acked-by: David Miller <davem@davemloft.net>
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: https://lkml.kernel.org/n/tip-cs7skq9pp0kjypiju6o7trse@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-10-17 04:08:29 +08:00
|
|
|
if (al->map != NULL) {
|
2013-08-07 19:38:46 +08:00
|
|
|
/*
|
|
|
|
* Kernel maps might be changed when loading symbols so loading
|
|
|
|
* must be done prior to using kernel maps.
|
|
|
|
*/
|
|
|
|
if (load_map)
|
2016-09-02 06:25:52 +08:00
|
|
|
map__load(al->map);
|
perf tools: Consolidate symbol resolving across all tools
Now we have a very high level routine for simple tools to
process IP sample events:
int event__preprocess_sample(const event_t *self,
struct addr_location *al,
symbol_filter_t filter)
It receives the event itself and will insert new threads in the
global threads list and resolve the map and symbol, filling all
this info into the new addr_location struct, so that tools like
annotate and report can further process the event by creating
hist_entries in their specific way (with or without callgraphs,
etc).
It in turn uses the new next layer function:
void thread__find_addr_location(struct thread *self, u8 cpumode,
enum map_type type, u64 addr,
struct addr_location *al,
symbol_filter_t filter)
This one will, given a thread (userspace or the kernel kthread
one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE
too in the near future) at the given cpumode, taking vdsos into
account (userspace hit, but kernel symbol) and will fill all
these details in the addr_location given.
Tools that need a more compact API for plain function
resolution, like 'kmem', can use this other one:
struct symbol *thread__find_function(struct thread *self, u64 addr,
symbol_filter_t filter)
So, to resolve a kernel symbol, that is all the 'kmem' tool
needs, its just a matter of calling:
sym = thread__find_function(kthread, addr, NULL);
The 'filter' parameter is needed because we do lazy
parsing/loading of ELF symtabs or /proc/kallsyms.
With this we remove more code duplication all around, which is
always good, huh? :-)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: John Kacur <jkacur@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
|
|
|
al->addr = al->map->map_ip(al->map, al->addr);
|
2013-08-07 19:38:46 +08:00
|
|
|
}
|
2018-04-24 22:58:56 +08:00
|
|
|
|
|
|
|
return al->map;
|
2010-01-15 09:45:29 +08:00
|
|
|
}
|
|
|
|
|
2018-11-07 05:07:10 +08:00
|
|
|
/*
|
|
|
|
* For branch stacks or branch samples, the sample cpumode might not be correct
|
|
|
|
* because it applies only to the sample 'ip' and not necessary to 'addr' or
|
|
|
|
* branch stack addresses. If possible, use a fallback to deal with those cases.
|
|
|
|
*/
|
|
|
|
struct map *thread__find_map_fb(struct thread *thread, u8 cpumode, u64 addr,
|
|
|
|
struct addr_location *al)
|
|
|
|
{
|
|
|
|
struct map *map = thread__find_map(thread, cpumode, addr, al);
|
|
|
|
struct machine *machine = thread->mg->machine;
|
|
|
|
u8 addr_cpumode = machine__addr_cpumode(machine, cpumode, addr);
|
|
|
|
|
|
|
|
if (map || addr_cpumode == cpumode)
|
|
|
|
return map;
|
|
|
|
|
|
|
|
return thread__find_map(thread, addr_cpumode, addr, al);
|
|
|
|
}
|
|
|
|
|
2018-04-26 05:16:53 +08:00
|
|
|
struct symbol *thread__find_symbol(struct thread *thread, u8 cpumode,
|
|
|
|
u64 addr, struct addr_location *al)
|
2010-01-15 09:45:29 +08:00
|
|
|
{
|
2018-04-24 23:05:48 +08:00
|
|
|
al->sym = NULL;
|
2018-04-26 20:34:37 +08:00
|
|
|
if (thread__find_map(thread, cpumode, addr, al))
|
2016-09-02 06:25:52 +08:00
|
|
|
al->sym = map__find_symbol(al->map, al->addr);
|
2018-04-24 23:05:48 +08:00
|
|
|
return al->sym;
|
perf tools: Consolidate symbol resolving across all tools
Now we have a very high level routine for simple tools to
process IP sample events:
int event__preprocess_sample(const event_t *self,
struct addr_location *al,
symbol_filter_t filter)
It receives the event itself and will insert new threads in the
global threads list and resolve the map and symbol, filling all
this info into the new addr_location struct, so that tools like
annotate and report can further process the event by creating
hist_entries in their specific way (with or without callgraphs,
etc).
It in turn uses the new next layer function:
void thread__find_addr_location(struct thread *self, u8 cpumode,
enum map_type type, u64 addr,
struct addr_location *al,
symbol_filter_t filter)
This one will, given a thread (userspace or the kernel kthread
one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE
too in the near future) at the given cpumode, taking vdsos into
account (userspace hit, but kernel symbol) and will fill all
these details in the addr_location given.
Tools that need a more compact API for plain function
resolution, like 'kmem', can use this other one:
struct symbol *thread__find_function(struct thread *self, u64 addr,
symbol_filter_t filter)
So, to resolve a kernel symbol, that is all the 'kmem' tool
needs, its just a matter of calling:
sym = thread__find_function(kthread, addr, NULL);
The 'filter' parameter is needed because we do lazy
parsing/loading of ELF symtabs or /proc/kallsyms.
With this we remove more code duplication all around, which is
always good, huh? :-)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: John Kacur <jkacur@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
|
|
|
}
|
|
|
|
|
2018-11-07 05:07:10 +08:00
|
|
|
struct symbol *thread__find_symbol_fb(struct thread *thread, u8 cpumode,
|
|
|
|
u64 addr, struct addr_location *al)
|
|
|
|
{
|
|
|
|
al->sym = NULL;
|
|
|
|
if (thread__find_map_fb(thread, cpumode, addr, al))
|
|
|
|
al->sym = map__find_symbol(al->map, al->addr);
|
|
|
|
return al->sym;
|
|
|
|
}
|
|
|
|
|
perf machine: Protect the machine->threads with a rwlock
In addition to using refcounts for the struct thread lifetime
management, we need to protect access to machine->threads from
concurrent access.
That happens in 'perf top', where a thread processes events, inserting
and deleting entries from that rb_tree while another thread decays
hist_entries, that end up dropping references and ultimately deleting
threads from the rb_tree and releasing its resources when no further
hist_entry (or other data structures, like in 'perf sched') references
it.
So the rule is the same for refcounts + protected trees in the kernel,
get the tree lock, find object, bump the refcount, drop the tree lock,
return, use object, drop the refcount if no more use of it is needed,
keep it if storing it in some other data structure, drop when releasing
that data structure.
I.e. pair "t = machine__find(new)_thread()" with a "thread__put(t)", and
"perf_event__preprocess_sample(&al)" with "addr_location__put(&al)".
The addr_location__put() one is because as we return references to
several data structures, we may end up adding more reference counting
for the other data structures and then we'll drop it at
addr_location__put() time.
Acked-by: David Ahern <dsahern@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-bs9rt4n0jw3hi9f3zxyy3xln@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-07 07:43:22 +08:00
|
|
|
/*
|
|
|
|
* Callers need to drop the reference to al->thread, obtained in
|
|
|
|
* machine__findnew_thread()
|
|
|
|
*/
|
2016-03-23 05:39:09 +08:00
|
|
|
int machine__resolve(struct machine *machine, struct addr_location *al,
|
|
|
|
struct perf_sample *sample)
|
perf tools: Consolidate symbol resolving across all tools
Now we have a very high level routine for simple tools to
process IP sample events:
int event__preprocess_sample(const event_t *self,
struct addr_location *al,
symbol_filter_t filter)
It receives the event itself and will insert new threads in the
global threads list and resolve the map and symbol, filling all
this info into the new addr_location struct, so that tools like
annotate and report can further process the event by creating
hist_entries in their specific way (with or without callgraphs,
etc).
It in turn uses the new next layer function:
void thread__find_addr_location(struct thread *self, u8 cpumode,
enum map_type type, u64 addr,
struct addr_location *al,
symbol_filter_t filter)
This one will, given a thread (userspace or the kernel kthread
one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE
too in the near future) at the given cpumode, taking vdsos into
account (userspace hit, but kernel symbol) and will fill all
these details in the addr_location given.
Tools that need a more compact API for plain function
resolution, like 'kmem', can use this other one:
struct symbol *thread__find_function(struct thread *self, u64 addr,
symbol_filter_t filter)
So, to resolve a kernel symbol, that is all the 'kmem' tool
needs, its just a matter of calling:
sym = thread__find_function(kthread, addr, NULL);
The 'filter' parameter is needed because we do lazy
parsing/loading of ELF symtabs or /proc/kallsyms.
With this we remove more code duplication all around, which is
always good, huh? :-)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: John Kacur <jkacur@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
|
|
|
{
|
2013-08-27 16:23:06 +08:00
|
|
|
struct thread *thread = machine__findnew_thread(machine, sample->pid,
|
2014-05-12 08:56:42 +08:00
|
|
|
sample->tid);
|
2010-06-04 19:02:07 +08:00
|
|
|
|
perf tools: Consolidate symbol resolving across all tools
Now we have a very high level routine for simple tools to
process IP sample events:
int event__preprocess_sample(const event_t *self,
struct addr_location *al,
symbol_filter_t filter)
It receives the event itself and will insert new threads in the
global threads list and resolve the map and symbol, filling all
this info into the new addr_location struct, so that tools like
annotate and report can further process the event by creating
hist_entries in their specific way (with or without callgraphs,
etc).
It in turn uses the new next layer function:
void thread__find_addr_location(struct thread *self, u8 cpumode,
enum map_type type, u64 addr,
struct addr_location *al,
symbol_filter_t filter)
This one will, given a thread (userspace or the kernel kthread
one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE
too in the near future) at the given cpumode, taking vdsos into
account (userspace hit, but kernel symbol) and will fill all
these details in the addr_location given.
Tools that need a more compact API for plain function
resolution, like 'kmem', can use this other one:
struct symbol *thread__find_function(struct thread *self, u64 addr,
symbol_filter_t filter)
So, to resolve a kernel symbol, that is all the 'kmem' tool
needs, its just a matter of calling:
sym = thread__find_function(kthread, addr, NULL);
The 'filter' parameter is needed because we do lazy
parsing/loading of ELF symtabs or /proc/kallsyms.
With this we remove more code duplication all around, which is
always good, huh? :-)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: John Kacur <jkacur@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
|
|
|
if (thread == NULL)
|
|
|
|
return -1;
|
|
|
|
|
2013-09-11 20:46:56 +08:00
|
|
|
dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid);
|
2018-04-24 21:49:50 +08:00
|
|
|
thread__find_map(thread, sample->cpumode, sample->ip, al);
|
perf tools: Consolidate symbol resolving across all tools
Now we have a very high level routine for simple tools to
process IP sample events:
int event__preprocess_sample(const event_t *self,
struct addr_location *al,
symbol_filter_t filter)
It receives the event itself and will insert new threads in the
global threads list and resolve the map and symbol, filling all
this info into the new addr_location struct, so that tools like
annotate and report can further process the event by creating
hist_entries in their specific way (with or without callgraphs,
etc).
It in turn uses the new next layer function:
void thread__find_addr_location(struct thread *self, u8 cpumode,
enum map_type type, u64 addr,
struct addr_location *al,
symbol_filter_t filter)
This one will, given a thread (userspace or the kernel kthread
one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE
too in the near future) at the given cpumode, taking vdsos into
account (userspace hit, but kernel symbol) and will fill all
these details in the addr_location given.
Tools that need a more compact API for plain function
resolution, like 'kmem', can use this other one:
struct symbol *thread__find_function(struct thread *self, u64 addr,
symbol_filter_t filter)
So, to resolve a kernel symbol, that is all the 'kmem' tool
needs, its just a matter of calling:
sym = thread__find_function(kthread, addr, NULL);
The 'filter' parameter is needed because we do lazy
parsing/loading of ELF symtabs or /proc/kallsyms.
With this we remove more code duplication all around, which is
always good, huh? :-)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: John Kacur <jkacur@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
|
|
|
dump_printf(" ...... dso: %s\n",
|
|
|
|
al->map ? al->map->dso->long_name :
|
|
|
|
al->level == 'H' ? "[hypervisor]" : "<not found>");
|
2014-03-18 04:12:27 +08:00
|
|
|
|
|
|
|
if (thread__is_filtered(thread))
|
|
|
|
al->filtered |= (1 << HIST_FILTER__THREAD);
|
|
|
|
|
2010-03-25 03:40:15 +08:00
|
|
|
al->sym = NULL;
|
2011-01-29 23:02:00 +08:00
|
|
|
al->cpu = sample->cpu;
|
2015-09-04 22:45:42 +08:00
|
|
|
al->socket = -1;
|
perf report: Use srcline from callchain for hist entries
This also removes the symbol name from the srcline column, more on this
below.
This ensures we use the correct srcline, which could originate from a
potentially inlined function. The hist entries used to query for the
srcline based purely on the IP, which leads to wrong results for inlined
entries.
Before:
~~~~~
perf report --inline -s srcline -g none --stdio
...
# Children Self Source:Line
# ........ ........ ..................................................................................................................................
#
94.23% 0.00% __libc_start_main+18446603487898210537
94.23% 0.00% _start+41
44.58% 0.00% main+100
44.58% 0.00% std::_Norm_helper<true>::_S_do_it<double>+100
44.58% 0.00% std::__complex_abs+100
44.58% 0.00% std::abs<double>+100
44.58% 0.00% std::norm<double>+100
36.01% 0.00% hypot+18446603487892193300
25.81% 0.00% main+41
25.81% 0.00% std::__detail::_Adaptor<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul>, double>::operator()+41
25.81% 0.00% std::uniform_real_distribution<double>::operator()<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul> >+41
25.75% 25.75% random.h:143
18.39% 0.00% main+57
18.39% 0.00% std::__detail::_Adaptor<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul>, double>::operator()+57
18.39% 0.00% std::uniform_real_distribution<double>::operator()<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul> >+57
13.80% 13.80% random.tcc:3330
5.64% 0.00% ??:0
4.13% 4.13% __hypot_finite+163
4.13% 0.00% __hypot_finite+18446603487892193443
...
~~~~~
After:
~~~~~
perf report --inline -s srcline -g none --stdio
...
# Children Self Source:Line
# ........ ........ ...........................................
#
94.30% 1.19% main.cpp:39
94.23% 0.00% __libc_start_main+18446603487898210537
94.23% 0.00% _start+41
48.44% 1.70% random.h:1823
48.44% 0.00% random.h:1814
46.74% 2.53% random.h:185
44.68% 0.10% complex:589
44.68% 0.00% complex:597
44.68% 0.00% complex:654
44.68% 0.00% complex:664
40.61% 13.80% random.tcc:3330
36.01% 0.00% hypot+18446603487892193300
26.81% 0.00% random.h:151
26.81% 0.00% random.h:332
25.75% 25.75% random.h:143
5.64% 0.00% ??:0
4.13% 4.13% __hypot_finite+163
4.13% 0.00% __hypot_finite+18446603487892193443
...
~~~~~
Note that this change removes the symbol from the source:line hist
column. If this information is desired, users should explicitly query
for it if needed. I.e. run this command instead:
~~~~~
perf report --inline -s sym,srcline -g none --stdio
...
# To display the perf.data header info, please use --header/--header-only options.
#
#
# Total Lost Samples: 0
#
# Samples: 1K of event 'cycles:uppp'
# Event count (approx.): 1381229476
#
# Children Self Symbol Source:Line
# ........ ........ ................................................................................................................................... ...........................................
#
94.30% 1.19% [.] main main.cpp:39
94.23% 0.00% [.] __libc_start_main __libc_start_main+18446603487898210537
94.23% 0.00% [.] _start _start+41
48.44% 0.00% [.] std::uniform_real_distribution<double>::operator()<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul> > (inlined) random.h:1814
48.44% 0.00% [.] std::uniform_real_distribution<double>::operator()<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul> > (inlined) random.h:1823
46.74% 0.00% [.] std::__detail::_Adaptor<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul>, double>::operator() (inlined) random.h:185
44.68% 0.00% [.] std::_Norm_helper<true>::_S_do_it<double> (inlined) complex:654
44.68% 0.00% [.] std::__complex_abs (inlined) complex:589
44.68% 0.00% [.] std::abs<double> (inlined) complex:597
44.68% 0.00% [.] std::norm<double> (inlined) complex:664
39.80% 13.59% [.] std::generate_canonical<double, 53ul, std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul> > random.tcc:3330
36.01% 0.00% [.] hypot hypot+18446603487892193300
26.81% 0.00% [.] std::__detail::__mod<unsigned long, 2147483647ul, 16807ul, 0ul> (inlined) random.h:151
26.81% 0.00% [.] std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul>::operator() (inlined) random.h:332
25.75% 0.00% [.] std::__detail::_Mod<unsigned long, 2147483647ul, 16807ul, 0ul, true, true>::__calc (inlined) random.h:143
25.19% 25.19% [.] std::generate_canonical<double, 53ul, std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul> > random.h:143
4.13% 4.13% [.] __hypot_finite __hypot_finite+163
4.13% 0.00% [.] __hypot_finite __hypot_finite+18446603487892193443
...
~~~~~
Compared to the old behavior, this reduces duplication in the output.
Before we used to print the symbol name in the srcline column even
when the sym column was explicitly requested. I.e. the output was:
~~~~~
perf report --inline -s sym,srcline -g none --stdio
...
# To display the perf.data header info, please use --header/--header-only options.
#
#
# Total Lost Samples: 0
#
# Samples: 1K of event 'cycles:uppp'
# Event count (approx.): 1381229476
#
# Children Self Symbol Source:Line
# ........ ........ ................................................................................................................................... ..................................................................................................................................
#
94.23% 0.00% [.] __libc_start_main __libc_start_main+18446603487898210537
94.23% 0.00% [.] _start _start+41
44.58% 0.00% [.] main main+100
44.58% 0.00% [.] std::_Norm_helper<true>::_S_do_it<double> (inlined) std::_Norm_helper<true>::_S_do_it<double>+100
44.58% 0.00% [.] std::__complex_abs (inlined) std::__complex_abs+100
44.58% 0.00% [.] std::abs<double> (inlined) std::abs<double>+100
44.58% 0.00% [.] std::norm<double> (inlined) std::norm<double>+100
36.01% 0.00% [.] hypot hypot+18446603487892193300
25.81% 0.00% [.] main main+41
25.81% 0.00% [.] std::__detail::_Adaptor<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul>, double>::operator() (inlined) std::__detail::_Adaptor<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul>, double>::operator()+41
25.81% 0.00% [.] std::uniform_real_distribution<double>::operator()<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul> > (inlined) std::uniform_real_distribution<double>::operator()<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul> >+41
25.69% 25.69% [.] std::generate_canonical<double, 53ul, std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul> > random.h:143
18.39% 0.00% [.] main main+57
18.39% 0.00% [.] std::__detail::_Adaptor<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul>, double>::operator() (inlined) std::__detail::_Adaptor<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul>, double>::operator()+57
18.39% 0.00% [.] std::uniform_real_distribution<double>::operator()<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul> > (inlined) std::uniform_real_distribution<double>::operator()<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul> >+57
13.80% 13.80% [.] std::generate_canonical<double, 53ul, std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul> > random.tcc:3330
4.13% 4.13% [.] __hypot_finite __hypot_finite+163
4.13% 0.00% [.] __hypot_finite __hypot_finite+18446603487892193443
...
~~~~~
Signed-off-by: Milian Wolff <milian.wolff@kdab.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20171019113836.5548-5-milian.wolff@kdab.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-10-19 19:38:35 +08:00
|
|
|
al->srcline = NULL;
|
2015-09-04 22:45:42 +08:00
|
|
|
|
|
|
|
if (al->cpu >= 0) {
|
|
|
|
struct perf_env *env = machine->env;
|
|
|
|
|
|
|
|
if (env && env->cpu)
|
|
|
|
al->socket = env->cpu[al->cpu].socket_id;
|
|
|
|
}
|
2010-03-25 03:40:15 +08:00
|
|
|
|
|
|
|
if (al->map) {
|
2011-12-12 23:16:55 +08:00
|
|
|
struct dso *dso = al->map->dso;
|
|
|
|
|
2010-03-25 03:40:15 +08:00
|
|
|
if (symbol_conf.dso_list &&
|
2011-12-12 23:16:55 +08:00
|
|
|
(!dso || !(strlist__has_entry(symbol_conf.dso_list,
|
|
|
|
dso->short_name) ||
|
|
|
|
(dso->short_name != dso->long_name &&
|
|
|
|
strlist__has_entry(symbol_conf.dso_list,
|
2014-03-18 03:59:21 +08:00
|
|
|
dso->long_name))))) {
|
|
|
|
al->filtered |= (1 << HIST_FILTER__DSO);
|
|
|
|
}
|
2010-03-25 03:40:15 +08:00
|
|
|
|
2016-09-02 06:25:52 +08:00
|
|
|
al->sym = map__find_symbol(al->map, al->addr);
|
2010-03-25 03:40:15 +08:00
|
|
|
}
|
2009-12-16 06:04:41 +08:00
|
|
|
|
2012-09-07 16:42:23 +08:00
|
|
|
if (symbol_conf.sym_list &&
|
|
|
|
(!al->sym || !strlist__has_entry(symbol_conf.sym_list,
|
2014-03-18 03:59:21 +08:00
|
|
|
al->sym->name))) {
|
|
|
|
al->filtered |= (1 << HIST_FILTER__SYMBOL);
|
|
|
|
}
|
2009-12-16 06:04:41 +08:00
|
|
|
|
|
|
|
return 0;
|
perf tools: Consolidate symbol resolving across all tools
Now we have a very high level routine for simple tools to
process IP sample events:
int event__preprocess_sample(const event_t *self,
struct addr_location *al,
symbol_filter_t filter)
It receives the event itself and will insert new threads in the
global threads list and resolve the map and symbol, filling all
this info into the new addr_location struct, so that tools like
annotate and report can further process the event by creating
hist_entries in their specific way (with or without callgraphs,
etc).
It in turn uses the new next layer function:
void thread__find_addr_location(struct thread *self, u8 cpumode,
enum map_type type, u64 addr,
struct addr_location *al,
symbol_filter_t filter)
This one will, given a thread (userspace or the kernel kthread
one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE
too in the near future) at the given cpumode, taking vdsos into
account (userspace hit, but kernel symbol) and will fill all
these details in the addr_location given.
Tools that need a more compact API for plain function
resolution, like 'kmem', can use this other one:
struct symbol *thread__find_function(struct thread *self, u64 addr,
symbol_filter_t filter)
So, to resolve a kernel symbol, that is all the 'kmem' tool
needs, its just a matter of calling:
sym = thread__find_function(kthread, addr, NULL);
The 'filter' parameter is needed because we do lazy
parsing/loading of ELF symtabs or /proc/kallsyms.
With this we remove more code duplication all around, which is
always good, huh? :-)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: John Kacur <jkacur@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
|
|
|
}
|
2014-07-22 21:17:39 +08:00
|
|
|
|
perf machine: Protect the machine->threads with a rwlock
In addition to using refcounts for the struct thread lifetime
management, we need to protect access to machine->threads from
concurrent access.
That happens in 'perf top', where a thread processes events, inserting
and deleting entries from that rb_tree while another thread decays
hist_entries, that end up dropping references and ultimately deleting
threads from the rb_tree and releasing its resources when no further
hist_entry (or other data structures, like in 'perf sched') references
it.
So the rule is the same for refcounts + protected trees in the kernel,
get the tree lock, find object, bump the refcount, drop the tree lock,
return, use object, drop the refcount if no more use of it is needed,
keep it if storing it in some other data structure, drop when releasing
that data structure.
I.e. pair "t = machine__find(new)_thread()" with a "thread__put(t)", and
"perf_event__preprocess_sample(&al)" with "addr_location__put(&al)".
The addr_location__put() one is because as we return references to
several data structures, we may end up adding more reference counting
for the other data structures and then we'll drop it at
addr_location__put() time.
Acked-by: David Ahern <dsahern@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-bs9rt4n0jw3hi9f3zxyy3xln@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-07 07:43:22 +08:00
|
|
|
/*
|
|
|
|
* The preprocess_sample method will return with reference counts for the
|
|
|
|
* in it, when done using (and perhaps getting ref counts if needing to
|
|
|
|
* keep a pointer to one of those entries) it must be paired with
|
|
|
|
* addr_location__put(), so that the refcounts can be decremented.
|
|
|
|
*/
|
|
|
|
void addr_location__put(struct addr_location *al)
|
|
|
|
{
|
|
|
|
thread__zput(al->thread);
|
|
|
|
}
|
|
|
|
|
2014-07-22 21:17:39 +08:00
|
|
|
bool is_bts_event(struct perf_event_attr *attr)
|
|
|
|
{
|
|
|
|
return attr->type == PERF_TYPE_HARDWARE &&
|
|
|
|
(attr->config & PERF_COUNT_HW_BRANCH_INSTRUCTIONS) &&
|
|
|
|
attr->sample_period == 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
bool sample_addr_correlates_sym(struct perf_event_attr *attr)
|
|
|
|
{
|
|
|
|
if (attr->type == PERF_TYPE_SOFTWARE &&
|
|
|
|
(attr->config == PERF_COUNT_SW_PAGE_FAULTS ||
|
|
|
|
attr->config == PERF_COUNT_SW_PAGE_FAULTS_MIN ||
|
|
|
|
attr->config == PERF_COUNT_SW_PAGE_FAULTS_MAJ))
|
|
|
|
return true;
|
|
|
|
|
|
|
|
if (is_bts_event(attr))
|
|
|
|
return true;
|
|
|
|
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
2016-03-23 05:44:46 +08:00
|
|
|
void thread__resolve(struct thread *thread, struct addr_location *al,
|
|
|
|
struct perf_sample *sample)
|
2014-07-22 21:17:39 +08:00
|
|
|
{
|
2018-11-07 05:07:11 +08:00
|
|
|
thread__find_map_fb(thread, sample->cpumode, sample->addr, al);
|
2014-07-22 21:17:39 +08:00
|
|
|
|
|
|
|
al->cpu = sample->cpu;
|
|
|
|
al->sym = NULL;
|
|
|
|
|
|
|
|
if (al->map)
|
2016-09-02 06:25:52 +08:00
|
|
|
al->sym = map__find_symbol(al->map, al->addr);
|
2014-07-22 21:17:39 +08:00
|
|
|
}
|