| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
For some kind of analysis a deltatime output is more human friendly and
reduce the cognitive load for further analysis.
The following output demonstrate the new option "deltatime": calculate
the time difference in relation to the previous event.
$ perf script --deltatime
test 2525 [001] 0.000000: sdt_libev:ev_add: (5635e72a5ebd)
test 2525 [001] 0.000091: sdt_libev:epoll_wait_enter: (5635e72a76a9)
test 2525 [001] 1.000051: sdt_libev:epoll_wait_return: (5635e72a772e) arg1=1
test 2525 [001] 0.000685: sdt_libev:ev_add: (5635e72a5ebd)
test 2525 [001] 0.000048: sdt_libev:epoll_wait_enter: (5635e72a76a9)
test 2525 [001] 1.000104: sdt_libev:epoll_wait_return: (5635e72a772e) arg1=1
test 2525 [001] 0.003895: sdt_libev:epoll_wait_enter: (5635e72a76a9)
test 2525 [001] 0.996034: sdt_libev:epoll_wait_return: (5635e72a772e) arg1=1
test 2525 [001] 0.000058: sdt_libev:epoll_wait_enter: (5635e72a76a9)
test 2525 [001] 1.000004: sdt_libev:epoll_wait_return: (5635e72a772e) arg1=1
test 2525 [001] 0.000064: sdt_libev:epoll_wait_enter: (5635e72a76a9)
test 2525 [001] 0.999934: sdt_libev:epoll_wait_return: (5635e72a772e) arg1=1
test 2525 [001] 0.000056: sdt_libev:epoll_wait_enter: (5635e72a76a9)
test 2525 [001] 0.999930: sdt_libev:epoll_wait_return: (5635e72a772e) arg1=1
Committer testing:
So go from default output to --reltime and then this new --deltatime, to
contrast the various timestamp presentation modes for a random perf.data file I
had laying around:
[root@five ~]# perf script --reltime | head
perf 442394 [000] 0.000000: 16 cycles: ffffffff9706e544 native_write_msr+0x4 (/usr/lib/debug/lib/modules/5.5.10-200.fc31.x86_64/vmlinux)
perf 442394 [000] 0.000002: 16 cycles: ffffffff9706e544 native_write_msr+0x4 (/usr/lib/debug/lib/modules/5.5.10-200.fc31.x86_64/vmlinux)
perf 442394 [000] 0.000004: 16 cycles: ffffffff9706e544 native_write_msr+0x4 (/usr/lib/debug/lib/modules/5.5.10-200.fc31.x86_64/vmlinux)
perf 442394 [000] 0.000006: 128 cycles: ffffffff972415a1 perf_event_update_userpage+0x1 (/usr/lib/debug/lib/modules/5.5.10-200.fc31.x86_64/vmlinux)
perf 442394 [000] 0.000009: 2597 cycles: ffffffff97463785 cap_task_setscheduler+0x5 (/usr/lib/debug/lib/modules/5.5.10-200.fc31.x86_64/vmlinux)
perf 442394 [001] 0.000036: 16 cycles: ffffffff9706e544 native_write_msr+0x4 (/usr/lib/debug/lib/modules/5.5.10-200.fc31.x86_64/vmlinux)
perf 442394 [001] 0.000038: 16 cycles: ffffffff9706e544 native_write_msr+0x4 (/usr/lib/debug/lib/modules/5.5.10-200.fc31.x86_64/vmlinux)
perf 442394 [001] 0.000040: 16 cycles: ffffffff9706e544 native_write_msr+0x4 (/usr/lib/debug/lib/modules/5.5.10-200.fc31.x86_64/vmlinux)
perf 442394 [001] 0.000041: 224 cycles: ffffffff9700a53a perf_ibs_handle_irq+0x1da (/usr/lib/debug/lib/modules/5.5.10-200.fc31.x86_64/vmlinux)
perf 442394 [001] 0.000044: 4439 cycles: ffffffff97120d85 put_prev_entity+0x45 (/usr/lib/debug/lib/modules/5.5.10-200.fc31.x86_64/vmlinux)
[root@five ~]# perf script --deltatime | head
perf 442394 [000] 0.000000: 16 cycles: ffffffff9706e544 native_write_msr+0x4 (/usr/lib/debug/lib/modules/5.5.10-200.fc31.x86_64/vmlinux)
perf 442394 [000] 0.000002: 16 cycles: ffffffff9706e544 native_write_msr+0x4 (/usr/lib/debug/lib/modules/5.5.10-200.fc31.x86_64/vmlinux)
perf 442394 [000] 0.000001: 16 cycles: ffffffff9706e544 native_write_msr+0x4 (/usr/lib/debug/lib/modules/5.5.10-200.fc31.x86_64/vmlinux)
perf 442394 [000] 0.000001: 128 cycles: ffffffff972415a1 perf_event_update_userpage+0x1 (/usr/lib/debug/lib/modules/5.5.10-200.fc31.x86_64/vmlinux)
perf 442394 [000] 0.000002: 2597 cycles: ffffffff97463785 cap_task_setscheduler+0x5 (/usr/lib/debug/lib/modules/5.5.10-200.fc31.x86_64/vmlinux)
perf 442394 [001] 0.000027: 16 cycles: ffffffff9706e544 native_write_msr+0x4 (/usr/lib/debug/lib/modules/5.5.10-200.fc31.x86_64/vmlinux)
perf 442394 [001] 0.000002: 16 cycles: ffffffff9706e544 native_write_msr+0x4 (/usr/lib/debug/lib/modules/5.5.10-200.fc31.x86_64/vmlinux)
perf 442394 [001] 0.000001: 16 cycles: ffffffff9706e544 native_write_msr+0x4 (/usr/lib/debug/lib/modules/5.5.10-200.fc31.x86_64/vmlinux)
perf 442394 [001] 0.000001: 224 cycles: ffffffff9700a53a perf_ibs_handle_irq+0x1da (/usr/lib/debug/lib/modules/5.5.10-200.fc31.x86_64/vmlinux)
perf 442394 [001] 0.000002: 4439 cycles: ffffffff97120d85 put_prev_entity+0x45 (/usr/lib/debug/lib/modules/5.5.10-200.fc31.x86_64/vmlinux)
[root@five ~]# perf script | head
perf 442394 [000] 7600.157861: 16 cycles: ffffffff9706e544 native_write_msr+0x4 (/usr/lib/debug/lib/modules/5.5.10-200.fc31.x86_64/vmlinux)
perf 442394 [000] 7600.157864: 16 cycles: ffffffff9706e544 native_write_msr+0x4 (/usr/lib/debug/lib/modules/5.5.10-200.fc31.x86_64/vmlinux)
perf 442394 [000] 7600.157866: 16 cycles: ffffffff9706e544 native_write_msr+0x4 (/usr/lib/debug/lib/modules/5.5.10-200.fc31.x86_64/vmlinux)
perf 442394 [000] 7600.157867: 128 cycles: ffffffff972415a1 perf_event_update_userpage+0x1 (/usr/lib/debug/lib/modules/5.5.10-200.fc31.x86_64/vmlinux)
perf 442394 [000] 7600.157870: 2597 cycles: ffffffff97463785 cap_task_setscheduler+0x5 (/usr/lib/debug/lib/modules/5.5.10-200.fc31.x86_64/vmlinux)
perf 442394 [001] 7600.157897: 16 cycles: ffffffff9706e544 native_write_msr+0x4 (/usr/lib/debug/lib/modules/5.5.10-200.fc31.x86_64/vmlinux)
perf 442394 [001] 7600.157900: 16 cycles: ffffffff9706e544 native_write_msr+0x4 (/usr/lib/debug/lib/modules/5.5.10-200.fc31.x86_64/vmlinux)
perf 442394 [001] 7600.157901: 16 cycles: ffffffff9706e544 native_write_msr+0x4 (/usr/lib/debug/lib/modules/5.5.10-200.fc31.x86_64/vmlinux)
perf 442394 [001] 7600.157903: 224 cycles: ffffffff9700a53a perf_ibs_handle_irq+0x1da (/usr/lib/debug/lib/modules/5.5.10-200.fc31.x86_64/vmlinux)
perf 442394 [001] 7600.157906: 4439 cycles: ffffffff97120d85 put_prev_entity+0x45 (/usr/lib/debug/lib/modules/5.5.10-200.fc31.x86_64/vmlinux)
[root@five ~]#
Andi suggested we better implement it as a new field, i.e. -F deltatime, like:
[root@five ~]# perf script -F deltatime
Invalid field requested.
Usage: perf script [<options>]
or: perf script [<options>] record <script> [<record-options>] <command>
or: perf script [<options>] report <script> [script-args]
or: perf script [<options>] <script> [<record-options>] <command>
or: perf script [<options>] <top-script> [script-args]
-F, --fields <str> comma separated output fields prepend with 'type:'. +field to add and -field to remove.Valid types: hw,sw,trace,raw,synth. Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,addr,symoff,srcline,period,iregs,uregs,brstack,brstacksym,flags,bpf-output,brstackinsn,brstackoff,callindent,insn,insnlen,synth,phys_addr,metric,misc,ipc
[root@five ~]#
I.e. we have -F for maximum flexibility:
[root@five ~]# perf script -F comm,pid,cpu,time | head
perf 442394 [000] 7600.157861:
perf 442394 [000] 7600.157864:
perf 442394 [000] 7600.157866:
perf 442394 [000] 7600.157867:
perf 442394 [000] 7600.157870:
perf 442394 [001] 7600.157897:
perf 442394 [001] 7600.157900:
perf 442394 [001] 7600.157901:
perf 442394 [001] 7600.157903:
perf 442394 [001] 7600.157906:
[root@five ~]#
But since we already have --reltime, having --deltatime, documented one after
the other is sensible.
Signed-off-by: Hagen Paul Pfeifer <[email protected]>
Tested-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Adrian Hunter <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Jiri Olsa <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
[ Added 'perf script' man page entry for --deltatime ]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
Add to the "x86 instruction decoder - new instructions" test the
following instructions:
incsspd
incsspq
rdsspd
rdsspq
saveprevssp
rstorssp
wrssd
wrssq
wrussd
wrussq
setssbsy
clrssbsy
endbr32
endbr64
And the "notrack" prefix for indirect calls and jumps.
For information about the instructions, refer Intel Control-flow
Enforcement Technology Specification May 2019 (334525-003).
Committer testing:
$ perf test instr
67: x86 instruction decoder - new instructions : Ok
$
Then use verbose mode and check one of those new instructions:
$ perf test -v instr |& grep saveprevssp
Decoded ok: f3 0f 01 ea saveprevssp
Decoded ok: f3 0f 01 ea saveprevssp
$
Signed-off-by: Adrian Hunter <[email protected]>
Acked-by: Masami Hiramatsu <[email protected]>
Tested-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: H. Peter Anvin <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Masami Hiramatsu <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Ravi v. Shankar <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Tony Luck <[email protected]>
Cc: [email protected]
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Yu-cheng Yu <[email protected]>
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
The $(CC) passed to arch_errno_names.sh may include a series of parameters
along with gcc itself. To avoid overwriting the following parameters of
arch_errno_names.sh and break the build like below, we just pick up the
first word of the $(CC).
find: unknown predicate `-m64/arch'
x86_64-wrs-linux-gcc: warning: '-x c' after last input file has no effect
x86_64-wrs-linux-gcc: error: unrecognized command line option '-m64/include/uapi/asm-generic/errno.h'
x86_64-wrs-linux-gcc: fatal error: no input files
Signed-off-by: He Zhe <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
Terms may have a NULL config in which case a strcmp will SEGV. This can
be reproduced with:
perf stat -e '*/event=?,nr/' sleep 1
Add a NULL check to avoid this. This was caught by LLVM's libfuzzer.
Signed-off-by: Ian Rogers <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Jin Yao <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: John Garry <[email protected]>
Cc: Kan Liang <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Stephane Eranian <[email protected]>
Cc: [email protected]
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
Add to the "x86 instruction decoder - new instructions" test the following
instructions:
incsspd
incsspq
rdsspd
rdsspq
saveprevssp
rstorssp
wrssd
wrssq
wrussd
wrussq
setssbsy
clrssbsy
endbr32
endbr64
And the notrack prefix for indirect calls and jumps.
For information about the instructions, refer Intel Control-flow
Enforcement Technology Specification May 2019 (334525-003).
Signed-off-by: Adrian Hunter <[email protected]>
Signed-off-by: Yu-cheng Yu <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Acked-by: Masami Hiramatsu <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
|
|
The method of unwinding for kernel space is defined by the kernel
config, not by the value of --call-graph. Improve the documentation to
reflect this.
Signed-off-by: Tony Jones <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
Add SPDX License Identifier to all .gitignore files.
Signed-off-by: Masahiro Yamada <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[email protected]>
|
|
Perf gets dso details from two different sources. 1st, from builid
headers in perf.data and 2nd from MMAP2 samples. Dso from buildid
header does not have dso_id detail. And dso from MMAP2 samples does
not have buildid information. If detail of the same dso is present
at both the places, filename is common.
Previously, __dsos__findnew_link_by_longname_id() used to compare only
long or short names, but Commit 0e3149f86b99 ("perf dso: Move dso_id
from 'struct map' to 'struct dso'") also added a dso_id comparison.
Because of that, now perf is creating two different dso objects of the
same file, one from buildid header (with dso_id but without buildid)
and second from MMAP2 sample (with buildid but without dso_id).
This is causing issues with archive, buildid-list etc subcommands. Fix
this by comparing dso_id only when it's present. And incase dso is
present in 'dsos' list without dso_id, inject dso_id detail as well.
Before:
$ sudo ./perf buildid-list -H
0000000000000000000000000000000000000000 /usr/bin/ls
0000000000000000000000000000000000000000 /usr/lib64/ld-2.30.so
0000000000000000000000000000000000000000 /usr/lib64/libc-2.30.so
$ ./perf archive
perf archive: no build-ids found
After:
$ ./perf buildid-list -H
b6b1291d0cead046ed0fa5734037fa87a579adee /usr/bin/ls
641f0c90cfa15779352f12c0ec3c7a2b2b6f41e8 /usr/lib64/ld-2.30.so
675ace3ca07a0b863df01f461a7b0984c65c8b37 /usr/lib64/libc-2.30.so
$ ./perf archive
Now please run:
$ tar xvf perf.data.tar.bz2 -C ~/.debug
wherever you need to run 'perf report' on.
Committer notes:
Renamed is_empty_dso_id() to dso_id__empty() and inject_dso_id() to
dso__inject_id() to keep namespacing consistent.
Fixes: 0e3149f86b99 ("perf dso: Move dso_id from 'struct map' to 'struct dso'")
Reported-by: Naveen N. Rao <[email protected]>
Signed-off-by: Ravi Bangoria <[email protected]>
Tested-by: Arnaldo Carvalho de Melo <[email protected]>
Tested-by: Naveen N. Rao <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Namhyung Kim <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
'snprintf' returns the number of characters which would be generated for
the given input.
If the returned value is *greater than* or equal to the buffer size, it
means that the output has been truncated.
Fix the overflow test accordingly.
Fixes: 7780c25bae59f ("perf tools: Allow ability to map cpus to nodes easily")
Fixes: 92a7e1278005b ("perf cpumap: Add cpu__max_present_cpu()")
Signed-off-by: Christophe JAILLET <[email protected]>
Suggested-by: David Laight <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Don Zickus <[email protected]>
Cc: He Zhe <[email protected]>
Cc: Jan Stancek <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Kan Liang <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: [email protected]
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
Add creating event aliases to the pmu-events test.
So currently we verify that the generated pmu-events.c is as expected for
some test events. Now test that we generate aliases as expected for those
events during normal operation.
For that, we cycle through each HW PMU in the system, and use the test
events to create aliases, and verify those against known, expected values.
For core PMUs, we should create an alias for every event in
test_cpu_events[].
However, for uncore PMUs, they need to be matched by the pmu_event.pmu
member, so use test_uncore_events[]; so check the match beforehand with
pmu_uncore_alias_match().
A sample run is as follows for my x86 machine:
john@linux-3c19:~/linux> tools/perf/perf test -vv 10
10: PMU events :
--- start ---
...
testing PMU uncore_arb aliases: no events to match
testing PMU cstate_pkg aliases: no events to match
skipping testing PMU breakpoint
testing aliases PMU uncore_cbox_1: matched event unc_cbo_xsnp_response.miss_eviction
testing PMU uncore_cbox_1 aliases: pass
testing PMU power aliases: no events to match
testing aliases PMU cpu: matched event bp_l1_btb_correct
testing aliases PMU cpu: matched event bp_l2_btb_correct
testing aliases PMU cpu: matched event segment_reg_loads.any
testing aliases PMU cpu: matched event dispatch_blocked.any
testing aliases PMU cpu: matched event eist_trans
testing PMU cpu aliases: pass
testing PMU intel_pt aliases: no events to match
skipping testing PMU software
skipping testing PMU intel_bts
testing PMU uncore_imc aliases: no events to match
testing aliases PMU uncore_cbox_0: matched event unc_cbo_xsnp_response.miss_eviction
testing PMU uncore_cbox_0 aliases: pass
testing PMU cstate_core aliases: no events to match
skipping testing PMU tracepoint
testing PMU msr aliases: no events to match
test child finished with 0
Signed-off-by: John Garry <[email protected]>
Acked-by: Jiri Olsa <[email protected]>
Tested-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: James Clark <[email protected]>
Cc: Joakim Zhang <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Will Deacon <[email protected]>
Cc: [email protected]
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
The perf pmu-events test will want to use pmu_uncore_alias_match(), so
make it public.
Signed-off-by: John Garry <[email protected]>
Acked-by: Jiri Olsa <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: James Clark <[email protected]>
Cc: Joakim Zhang <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Will Deacon <[email protected]>
Cc: [email protected]
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
Add a function to decide whether a PMU is a core PMU.
Signed-off-by: John Garry <[email protected]>
Acked-by: Jiri Olsa <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: James Clark <[email protected]>
Cc: Joakim Zhang <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Will Deacon <[email protected]>
Cc: [email protected]
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
The initial test will verify that the test tables in generated pmu-events.c
match against known, expected values.
For known events added in pmu-events/arch/test, we need to add an entry
in test_cpu_aliases_events[] or test_uncore_events[].
A sample run is as follows for x86:
john@linux-3c19:~/linux> tools/perf/perf test -vv 10
10: PMU event aliases :
--- start ---
test child forked, pid 5316
testing event table bp_l1_btb_correct: pass
testing event table bp_l2_btb_correct: pass
testing event table segment_reg_loads.any: pass
testing event table dispatch_blocked.any: pass
testing event table eist_trans: pass
testing event table uncore_hisi_ddrc.flux_wcmd: pass
testing event table unc_cbo_xsnp_response.miss_eviction: pass
test child finished with 0
---- end ----
PMU event aliases: Ok
Signed-off-by: John Garry <[email protected]>
Tested-by: Arnaldo Carvalho de Melo <[email protected]>
Acked-by: Jiri Olsa <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: James Clark <[email protected]>
Cc: Joakim Zhang <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Will Deacon <[email protected]>
Cc: [email protected]
[ Fixup test_cpu_events[] and test_uncore_events[] sentinels to initialize one of its members to NULL, fixing the build in older compilers ]
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
Create pmu_add_cpu_aliases_map() from pmu_add_cpu_aliases(), so the caller
can pass the map; the pmu-events test would use this since there would
be no CPUID matching to a mapfile there.
Signed-off-by: John Garry <[email protected]>
Acked-by: Jiri Olsa <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: James Clark <[email protected]>
Cc: Joakim Zhang <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Will Deacon <[email protected]>
Cc: [email protected]
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
With the goal of supporting pmu-events test case, introduce support for
a test events folder.
These test events can be used for testing generation of pmu-event tables
and alias creation for any arch.
When running the pmu-events test case, these test events will be used as
the platform-agnostic events, so aliases can be created per-PMU and
validated against known expected values.
To support the test events, add a "testcpu" entry in pmu_events_map[].
The pmu-events test will be able to lookup the events map for "testcpu",
to verify the generated tables against expected values.
The resultant generated pmu-events.c will now look like the following:
struct pmu_event pme_ampere_emag[] = {
{
.name = "ldrex_spec",
.event = "event=0x6c",
.desc = "Exclusive operation spe...",
.topic = "intrinsic",
.long_desc = "Exclusive operation ...",
},
...
};
struct pmu_event pme_test_cpu[] = {
{
.name = "uncore_hisi_ddrc.flux_wcmd",
.event = "event=0x2",
.desc = "DDRC write commands. Unit: hisi_sccl,ddrc ",
.topic = "uncore",
.long_desc = "DDRC write commands",
.pmu = "hisi_sccl,ddrc",
},
{
.name = "unc_cbo_xsnp_response.miss_eviction",
.event = "umask=0x81,event=0x22",
.desc = "Unit: uncore_cbox A cross-core snoop resulted ...",
.topic = "uncore",
.long_desc = "A cross-core snoop resulted from L3 ...",
.pmu = "uncore_cbox",
},
{
.name = "eist_trans",
.event = "umask=0x0,period=200000,event=0x3a",
.desc = "Number of Enhanced Intel SpeedStep(R) ...",
.topic = "other",
},
{
.name = 0,
},
};
struct pmu_events_map pmu_events_map[] = {
...
{
.cpuid = "0x00000000500f0000",
.version = "v1",
.type = "core",
.table = pme_ampere_emag
},
...
{
.cpuid = "testcpu",
.version = "v1",
.type = "core",
.table = pme_test_cpu,
},
{
.cpuid = 0,
.version = 0,
.type = 0,
.table = 0,
},
};
Signed-off-by: John Garry <[email protected]>
Acked-by: Jiri Olsa <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: James Clark <[email protected]>
Cc: Joakim Zhang <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Will Deacon <[email protected]>
Cc: [email protected]
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
Add some test PMU events. The events are randomly chosen from x86 and
arm64 JSONs. The events include CPU and uncore events.
Signed-off-by: John Garry <[email protected]>
Acked-by: Jiri Olsa <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: James Clark <[email protected]>
Cc: Joakim Zhang <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Will Deacon <[email protected]>
Cc: [email protected]
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
Removing the extra 'SUBDIR' line from clean and doc build output.
Because it's annoying.. ;-)
Before:
$ make clean
...
SUBDIR Documentation
CLEAN Documentation
After:
$ make clean
...
CLEAN Documentation
Before:
$ make doc
BUILD: Doing 'make -j8' parallel build
SUBDIR Documentation
ASCIIDOC perf-stat.html
...
After:
$ make doc
BUILD: Doing 'make -j8' parallel build
ASCIIDOC perf-stat.html
...
Signed-off-by: Jiri Olsa <[email protected]>
Tested-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Michael Petlan <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
This patch updates the PMCs for AMD Zen1 core based processors (Family
17h; Models 0 through 2F) to be in accordance with PMCs as
documented in the latest versions of the AMD Processor Programming
Reference [1], [2] and [3]. Note that some events, such as FPU pipe
assignment are missing in [1], and therefore [3] is included for full
coverage of events.
PMCs added:
fpu_pipe_assignment.dual{0|1|2|3}
fpu_pipe_assignment.total{0|1|2|3}
ls_mab_alloc.dc_prefetcher
ls_mab_alloc.stores
ls_mab_alloc.loads
bp_dyn_ind_pred
bp_de_redirect
PMC removed:
ex_ret_cond_misp
Cumulative counts, fpu_pipe_assignment.total and
fpu_pipe_assignment.dual, existed in v1, but did expose port-level
counters.
ex_ret_cond_misp has been removed as it has been removed from the latest
versions of the PPR, and when tested, always seems to sample zero as
tested on a Ryzen 3400G system.
[1]: Processor Programming Reference (PPR) for AMD Family 17h Models
01h,08h, Revision B2 Processors, 54945 Rev 3.03 - Jun 14, 2019.
[2]: Processor Programming Reference (PPR) for AMD Family 17h Model 18h,
Revision B1 Processors, 55570-B1 Rev 3.14 - Sep 26, 2019.
[3]: OSRR for AMD Family 17h processors, Models 00h-2Fh, 56255 Rev 3.03 - July, 2018
All of the PPRs can be found at:
https://bugzilla.kernel.org/show_bug.cgi?id=206537
Signed-off-by: Vijay Thakkar <[email protected]>
Acked-by: Kim Phillips <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Jon Grimm <[email protected]>
Cc: Martin Liška <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: vijay thakkar <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
This patch adds PMU events for AMD Zen2 core based processors, namely,
Matisse (model 71h), Castle Peak (model 31h) and Rome (model 2xh), as
documented in the AMD Processor Programming Reference for Matisse [1].
The model number regex has been set to detect all the models under
family 17 that do not match those of Zen1, as the range is larger for
zen2.
Zen2 adds some additional counters that are not present in Zen1 and
events for them have been added in this patch. Some counters have also
been removed for Zen2 thatwere previously present in Zen1 and have been
confirmed to always sample zero on zen2. These added/removed counters
have been omitted for brevity but can be found here:
https://gist.github.com/thakkarV/5b12ca5fd7488eb2c42e451e40bdd5f3
Note that PPR for Zen2 [1] does not include some counters that were
documented in the PPR for Zen1 based processors [2]. After having tested
these counters, some of them that still work for zen2 systems have been
preserved in the events for zen2. The counters that are omitted in [1]
but are still measurable and non-zero on zen2 (tested on a Ryzen 3900X
system) are the following:
PMC 0x000 fpu_pipe_assignment.{total|total0|total1|total2|total3}
PMC 0x004 fp_num_mov_elim_scal_op.*
PMC 0x046 ls_tablewalker.*
PMC 0x062 l2_latency.l2_cycles_waiting_on_fills
PMC 0x063 l2_wcb_req.*
PMC 0x06D l2_fill_pending.l2_fill_busy
PMC 0x080 ic_fw32
PMC 0x081 ic_fw32_miss
PMC 0x086 bp_snp_re_sync
PMC 0x087 ic_fetch_stall.*
PMC 0x08C ic_cache_inval.*
PMC 0x099 bp_tlb_rel
PMC 0x0C7 ex_ret_brn_resync
PMC 0x28A ic_oc_mode_switch.*
L3PMC 0x001 l3_request_g1.*
L3PMC 0x006 l3_comb_clstr_state.*
[1]: Processor Programming Reference (PPR) for AMD Family 17h Model 71h,
Revision B0 Processors, 56176 Rev 3.06 - Jul 17, 2019
[2]: Processor Programming Reference (PPR) for AMD Family 17h Models
01h,08h, Revision B2 Processors, 54945 Rev 3.03 - Jun 14, 2019
All of the PPRs can be found at:
https://bugzilla.kernel.org/show_bug.cgi?id=206537
Here are the results of running "fpu_pipe_assignment.total" events on my
Ryzen 3900X family 17h model 71h system:
Before this patch:
$> perf list *fpu_pipe_assignment*
List of pre-defined events (to be used in -e):
After:
$> perf list *fpu_pipe_assignment*
floating point:
fpu_pipe_assignment.total
[Total number of fp uOps]
fpu_pipe_assignment.total0
[Total number uOps assigned to pipe 0]
fpu_pipe_assignment.total1
[Total number uOps assigned to pipe 1]
fpu_pipe_assignment.total2
[Total number uOps assigned to pipe 2]
fpu_pipe_assignment.total3
[Total number uOps assigned to pipe 3]
Metric Groups:
$> perf stat -e fpu_pipe_assignment.total sleep 1
Performance counter stats for 'sleep 1':
25,883 fpu_pipe_assignment.total
1.004145868 seconds time elapsed
0.001805000 seconds user
0.000000000 seconds sys
Usage tests while running Linpackin the background:
$> perf stat -I1000 -e fpu_pipe_assignment.total
1.000266796 79,313,191,516 fpu_pipe_assignment.total
2.000809630 68,091,474,430 fpu_pipe_assignment.total
3.001028115 52,925,023,174 fpu_pipe_assignment.total
$> perf record -e fpu_pipe_assignment.total,fpu_pipe_assignment.total0 -a sleep 1
[ perf record: Woken up 9 times to write data ]
[ perf record: Captured and wrote 4.031 MB perf.data (64764 samples) ]
$> perf report --stdio --no-header | head -30
98.33% xhpl xhpl [.] dgemm_kernel
0.28% xhpl xhpl [.] dtrsm_kernel_LT
0.10% xhpl [kernel.kallsyms] [k] entry_SYSCALL_64
0.08% xhpl xhpl [.] idamax_k
0.07% baloo_file_extr liblmdb.so [.] mdb_mid2l_insert
0.06% xhpl xhpl [.] dgemm_itcopy
0.06% xhpl xhpl [.] dgemm_oncopy
0.06% xhpl [kernel.kallsyms] [k] __schedule
0.06% xhpl [kernel.kallsyms] [k] syscall_trace_enter
0.06% xhpl [kernel.kallsyms] [k] native_sched_clock
0.06% xhpl [kernel.kallsyms] [k] pick_next_task_fair
0.05% xhpl xhpl [.] blas_thread_server.llvm.15009391670273914865
0.04% xhpl [kernel.kallsyms] [k] do_syscall_64
0.04% xhpl [kernel.kallsyms] [k] yield_task_fair
0.04% xhpl libpthread-2.31.so [.] __pthread_mutex_unlock_usercnt
0.03% xhpl [kernel.kallsyms] [k] cpuacct_charge
0.03% xhpl [kernel.kallsyms] [k] syscall_return_via_sysret
0.03% xhpl libc-2.31.so [.] __sched_yield
0.03% xhpl [kernel.kallsyms] [k] __calc_delta
$> perf annotate --stdio2 dgemm_kernel | egrep '^ {0,2}[0-9]+' -B2 -A2
sub $0x60,%rsp
mov %rbx,(%rsp)
0.00 mov %rbp,0x8(%rsp)
mov %r12,0x10(%rsp)
0.00 mov %r13,0x18(%rsp)
mov %r14,0x20(%rsp)
mov %r15,0x28(%rsp)
--
mov %rdi,%r13
mov %rsi,0x28(%rsp)
0.00 mov %rdx,%r12
vmovsd %xmm0,0x30(%rsp)
shl $0x3,%r10
mov 0x28(%rsp),%rax
0.00 xor %rdx,%rdx
mov $0x18,%rdi
div %rdi
--
nop
a0: mov %r12,%rax
0.00 shl $0x3,%rax
mov %r8,%rdi
lea (%r8,%rax,8),%r15
--
mov %r12,%rax
nop
0.00 c0: vmovups (%rdi),%ymm1
0.09 vmovups 0x20(%rdi),%ymm2
0.02 vmovups (%r15),%ymm3
0.10 vmovups %ymm1,(%rsi)
0.07 vmovups %ymm2,0x20(%rsi)
0.07 vmovups %ymm3,0x40(%rsi)
0.06 add $0x40,%rdi
add $0x40,%r15
add $0x60,%rsi
0.00 dec %rax
↑ jne c0
mov %r9,%r15
--
nop
110: lea 0x80(%rsp),%rsi
0.01 add $0x60,%rsi
0.03 mov %r12,%rax
0.00 sar $0x3,%rax
cmp $0x2,%rax
↓ jl d26
prefetcht0 0x200(%rdi)
0.01 vmovups -0x60(%rsi),%ymm1
0.02 prefetcht0 0xa0(%rsi)
0.00 vbroadcastsd -0x80(%rdi),%ymm0
0.00 prefetcht0 0xe0(%rsi)
0.03 vmovups -0x40(%rsi),%ymm2
0.00 prefetcht0 0x120(%rsi)
vmovups -0x20(%rsi),%ymm3
vmulpd %ymm0,%ymm1,%ymm4
0.01 prefetcht0 0x160(%rsi)
vmulpd %ymm0,%ymm2,%ymm8
0.01 vmulpd %ymm0,%ymm3,%ymm12
0.02 prefetcht0 0x1a0(%rsi)
0.01 vbroadcastsd -0x78(%rdi),%ymm0
vmulpd %ymm0,%ymm1,%ymm5
0.01 vmulpd %ymm0,%ymm2,%ymm9
vmulpd %ymm0,%ymm3,%ymm13
0.01 vbroadcastsd -0x70(%rdi),%ymm0
vmulpd %ymm0,%ymm1,%ymm6
0.00 vmulpd %ymm0,%ymm2,%ymm10
0.00 add $0x60,%rsi
... snip ...
nop
65e0: vmovddup -0x60(%rsi),%xmm2
0.00 vmovups -0x80(%rdi),%xmm0
vmovups -0x70(%rdi),%xmm1
0.00 vmovddup -0x58(%rsi),%xmm3
vfmadd231pd %xmm0,%xmm2,%xmm4
0.00 vfmadd231pd %xmm1,%xmm2,%xmm5
0.00 vfmadd231pd %xmm0,%xmm3,%xmm6
0.00 vfmadd231pd %xmm1,%xmm3,%xmm7
0.00 add $0x10,%rsi
add $0x20,%rdi
0.00 dec %rax
↑ jne 65e0
nop
nop
6620: vmovddup 0x30(%rsp),%xmm0
0.00 vmulpd %xmm0,%xmm4,%xmm4
0.00 vmulpd %xmm0,%xmm5,%xmm5
vmulpd %xmm0,%xmm6,%xmm6
vmulpd %xmm0,%xmm7,%xmm7
vaddpd (%r15),%xmm4,%xmm4
vaddpd 0x10(%r15),%xmm5,%xmm5
0.00 vaddpd (%r15,%r10,1),%xmm6,%xmm6
0.00 vaddpd 0x10(%r15,%r10,1),%xmm7,%xmm7
0.00 vmovups %xmm4,(%r15)
vmovups %xmm5,0x10(%r15)
0.00 vmovups %xmm6,(%r15,%r10,1)
vmovups %xmm7,0x10(%r15,%r10,1)
add $0x20,%r15
--
lea (%r8,%rax,8),%r8
69d8: mov 0x20(%rsp),%r14
0.00 test $0x1,%r14
↓ je 6d84
mov %r9,%r15
--
vbroadcastsd -0x28(%rsi),%ymm3
vfmadd231pd (%rdi),%ymm0,%ymm4
0.00 vfmadd231pd 0x20(%rdi),%ymm1,%ymm5
vfmadd231pd 0x40(%rdi),%ymm2,%ymm6
vfmadd231pd 0x60(%rdi),%ymm3,%ymm7
--
vmulpd %ymm0,%ymm4,%ymm4
vaddpd (%r15),%ymm4,%ymm4
0.00 vmovups %ymm4,(%r15)
add $0x20,%r15
dec %r11
--
mov %rbx,%rsp
mov (%rsp),%rbx
0.01 mov 0x8(%rsp),%rbp
mov 0x10(%rsp),%r12
mov 0x18(%rsp),%r13
Signed-off-by: Vijay Thakkar <[email protected]>
Tested-by: Arnaldo Carvalho de Melo <[email protected]>
Acked-by: Kim Phillips <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Jon Grimm <[email protected]>
Cc: Martin Liška <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
This patch changes the previous blanket detection of AMD Family 17h
processors to be more specific to Zen1 core based products only by
replacing model detection regex pattern [[:xdigit:]]+ with
([12][0-9A-F]|[0-9A-F]), restricting to models 0 though 2f only.
This change is required to allow for the addition of separate PMU events
for Zen2 core based models in the following patches as those belong to
family 17h but have different PMCs. Current PMU events directory has
also been renamed to "amdzen1" from "amdfam17h" to reflect this
specificity.
Note that although this change does not break PMU counters for existing
zen1 based systems, it does disable the current set of counters for zen2
based systems. Counters for zen2 have been added in the following
patches in this patchset.
Signed-off-by: Vijay Thakkar <[email protected]>
Acked-by: Kim Phillips <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Jon Grimm <[email protected]>
Cc: Martin Liška <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
events incase of overlapping events
Commit f01642e4912b ("perf metricgroup: Support multiple events for
metricgroup") introduced support for multiple events in a metric group.
But with the current upstream, metric events names are not printed
properly incase we try to run multiple metric groups with overlapping
event.
With current upstream version, incase of overlapping metric events issue
is, we always start our comparision logic from start. So, the events
which already matched with some metric group also take part in
comparision logic. Because of that when we have overlapping events, we
end up matching current metric group event with already matched one.
For example, in skylake machine we have metric event CoreIPC and
Instructions. Both of them need 'inst_retired.any' event value. As
events in Instructions is subset of events in CoreIPC, they endup in
pointing to same 'inst_retired.any' value.
In skylake platform:
command:# ./perf stat -M CoreIPC,Instructions -C 0 sleep 1
Performance counter stats for 'CPU(s) 0':
1,254,992,790 inst_retired.any # 1254992790.0
Instructions
# 1.3 CoreIPC
977,172,805 cycles
1,254,992,756 inst_retired.any
1.000802596 seconds time elapsed
command:# sudo ./perf stat -M UPI,IPC sleep 1
Performance counter stats for 'sleep 1':
948,650 uops_retired.retire_slots
866,182 inst_retired.any # 0.7 IPC
866,182 inst_retired.any
1,175,671 cpu_clk_unhalted.thread
Patch fixes the issue by adding a new bool pointer 'evlist_used' to keep
track of events which already matched with some group by setting it
true. So, we skip all used events in list when we start comparision
logic. Patch also make some changes in comparision logic, incase we get
a match miss, we discard the whole match and start again with first
event id in metric event.
With this patch:
In skylake platform:
command:# ./perf stat -M CoreIPC,Instructions -C 0 sleep 1
Performance counter stats for 'CPU(s) 0':
3,348,415 inst_retired.any # 0.3 CoreIPC
11,779,026 cycles
3,348,381 inst_retired.any # 3348381.0
Instructions
1.001649056 seconds time elapsed
command:# ./perf stat -M UPI,IPC sleep 1
Performance counter stats for 'sleep 1':
1,023,148 uops_retired.retire_slots # 1.1 UPI
924,976 inst_retired.any
924,976 inst_retired.any # 0.6 IPC
1,489,414 cpu_clk_unhalted.thread
1.003064672 seconds time elapsed
Signed-off-by: Kajol Jain <[email protected]>
Acked-by: Jiri Olsa <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Anju T Sudhakar <[email protected]>
Cc: Jin Yao <[email protected]>
Cc: Kan Liang <[email protected]>
Cc: Madhavan Srinivasan <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Ravi Bangoria <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
There is a slight misalignment in -A -I output.
For example:
# perf stat -e cpu/event=cpu-cycles/ -a -A -I 1000
# time CPU counts unit events
1.000440863 CPU0 1,068,388 cpu/event=cpu-cycles/
1.000440863 CPU1 875,954 cpu/event=cpu-cycles/
1.000440863 CPU2 3,072,538 cpu/event=cpu-cycles/
1.000440863 CPU3 4,026,870 cpu/event=cpu-cycles/
1.000440863 CPU4 5,919,630 cpu/event=cpu-cycles/
1.000440863 CPU5 2,714,260 cpu/event=cpu-cycles/
1.000440863 CPU6 2,219,240 cpu/event=cpu-cycles/
1.000440863 CPU7 1,299,232 cpu/event=cpu-cycles/
The value of counts is not aligned with the column "counts" and
the event name is not aligned with the column "events".
With this patch, the output is,
# perf stat -e cpu/event=cpu-cycles/ -a -A -I 1000
# time CPU counts unit events
1.000423009 CPU0 997,421 cpu/event=cpu-cycles/
1.000423009 CPU1 1,422,042 cpu/event=cpu-cycles/
1.000423009 CPU2 484,651 cpu/event=cpu-cycles/
1.000423009 CPU3 525,791 cpu/event=cpu-cycles/
1.000423009 CPU4 1,370,100 cpu/event=cpu-cycles/
1.000423009 CPU5 442,072 cpu/event=cpu-cycles/
1.000423009 CPU6 205,643 cpu/event=cpu-cycles/
1.000423009 CPU7 1,302,250 cpu/event=cpu-cycles/
Now output is aligned.
Signed-off-by: Jin Yao <[email protected]>
Acked-by: Jiri Olsa <[email protected]>
Tested-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Kan Liang <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
When performing "perf report --group", it shows the event group information
together. In previous patch, we have supported a new option "--group-sort-idx"
to sort the output by the event at the index n in event group.
It would be nice if we can use a hotkey in browser to select a event
to sort.
For example,
# perf report --group
Samples: 12K of events 'cpu/instructions,period=2000003/, cpu/cpu-cycles,period=200003/, ...
Overhead Command Shared Object Symbol
92.19% 98.68% 0.00% 93.30% mgen mgen [.] LOOP1
3.12% 0.29% 0.00% 0.16% gsd-color libglib-2.0.so.0.5600.4 [.] 0x0000000000049515
1.56% 0.03% 0.00% 0.04% gsd-color libglib-2.0.so.0.5600.4 [.] 0x00000000000494b7
1.56% 0.01% 0.00% 0.00% gsd-color libglib-2.0.so.0.5600.4 [.] 0x00000000000494ce
1.56% 0.00% 0.00% 0.00% mgen [kernel.kallsyms] [k] task_tick_fair
0.00% 0.15% 0.00% 0.04% perf [kernel.kallsyms] [k] smp_call_function_single
0.00% 0.13% 0.00% 6.08% swapper [kernel.kallsyms] [k] intel_idle
0.00% 0.03% 0.00% 0.00% gsd-color libglib-2.0.so.0.5600.4 [.] g_main_context_check
0.00% 0.03% 0.00% 0.00% swapper [kernel.kallsyms] [k] apic_timer_interrupt
0.00% 0.03% 0.00% 0.00% swapper [kernel.kallsyms] [k] check_preempt_curr
When user press hotkey '3' (event index, starting from 0), it indicates
to sort output by the forth event in group.
Samples: 12K of events 'cpu/instructions,period=2000003/, cpu/cpu-cycles,period=200003/, ...
Overhead Command Shared Object Symbol
92.19% 98.68% 0.00% 93.30% mgen mgen [.] LOOP1
0.00% 0.13% 0.00% 6.08% swapper [kernel.kallsyms] [k] intel_idle
3.12% 0.29% 0.00% 0.16% gsd-color libglib-2.0.so.0.5600.4 [.] 0x0000000000049515
0.00% 0.00% 0.00% 0.06% swapper [kernel.kallsyms] [k] hrtimer_start_range_ns
1.56% 0.03% 0.00% 0.04% gsd-color libglib-2.0.so.0.5600.4 [.] 0x00000000000494b7
0.00% 0.15% 0.00% 0.04% perf [kernel.kallsyms] [k] smp_call_function_single
0.00% 0.00% 0.00% 0.02% mgen [kernel.kallsyms] [k] update_curr
0.00% 0.00% 0.00% 0.02% mgen [kernel.kallsyms] [k] apic_timer_interrupt
0.00% 0.00% 0.00% 0.02% mgen [kernel.kallsyms] [k] native_apic_msr_eoi_write
0.00% 0.00% 0.00% 0.02% mgen [kernel.kallsyms] [k] __update_load_avg_se
v6:
---
Jiri provided a good improvement to eliminate unneeded refresh.
This improvement is added to v6.
v2:
---
1. Report warning at helpline when index is invalid.
2. Report warning at helpline when it's not group event.
3. Use "case '0' ... '9'" to refine the code
4. Split K_RELOAD implementation to another patch.
Signed-off-by: Jin Yao <[email protected]>
Acked-by: Jiri Olsa <[email protected]>
Tested-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Kan Liang <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
Sometimes we may need to reload the browser to update the output since
some options are changed.
This patch creates a new key K_RELOAD. Once the __cmd_report() returns
K_RELOAD, it would repeat the whole process, such as, read samples from
data file, sort the data and display in the browser.
v5:
---
1. Fix the 'make NO_SLANG=1' error. Define K_RELOAD in util/hist.h.
2. Skip setup_sorting() in repeat path if last key is K_RELOAD.
v4:
---
Need to quit in perf_evsel_menu__run if key is K_RELOAD.
Signed-off-by: Jin Yao <[email protected]>
Tested-by: Arnaldo Carvalho de Melo <[email protected]>
Acked-by: Jiri Olsa <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Kan Liang <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
When performing "perf report --group", it shows the event group
information together. By default, the output is sorted by the first
event in group.
It would be nice for user to select any event for sorting. This patch
introduces a new option "--group-sort-idx" to sort the output by the
event at the index n in event group.
For example,
Before:
# perf report --group --stdio
# To display the perf.data header info, please use --header/--header-only options.
#
#
# Total Lost Samples: 0
#
# Samples: 12K of events 'cpu/instructions,period=2000003/, cpu/cpu-cycles,period=200003/, BR_MISP_RETIRED.ALL_BRANCHES:pp, cpu/event=0xc0,umask=1,cmask=1,
# Event count (approx.): 6451235635
#
# Overhead Command Shared Object Symbol
# ................................ ......... ....................... ...................................
#
92.19% 98.68% 0.00% 93.30% mgen mgen [.] LOOP1
3.12% 0.29% 0.00% 0.16% gsd-color libglib-2.0.so.0.5600.4 [.] 0x0000000000049515
1.56% 0.03% 0.00% 0.04% gsd-color libglib-2.0.so.0.5600.4 [.] 0x00000000000494b7
1.56% 0.01% 0.00% 0.00% gsd-color libglib-2.0.so.0.5600.4 [.] 0x00000000000494ce
1.56% 0.00% 0.00% 0.00% mgen [kernel.kallsyms] [k] task_tick_fair
0.00% 0.15% 0.00% 0.04% perf [kernel.kallsyms] [k] smp_call_function_single
0.00% 0.13% 0.00% 6.08% swapper [kernel.kallsyms] [k] intel_idle
0.00% 0.03% 0.00% 0.00% gsd-color libglib-2.0.so.0.5600.4 [.] g_main_context_check
0.00% 0.03% 0.00% 0.00% swapper [kernel.kallsyms] [k] apic_timer_interrupt
...
After:
# perf report --group --stdio --group-sort-idx 3
# To display the perf.data header info, please use --header/--header-only options.
#
#
# Total Lost Samples: 0
#
# Samples: 12K of events 'cpu/instructions,period=2000003/, cpu/cpu-cycles,period=200003/, BR_MISP_RETIRED.ALL_BRANCHES:pp, cpu/event=0xc0,umask=1,cmask=1,
# Event count (approx.): 6451235635
#
# Overhead Command Shared Object Symbol
# ................................ ......... ....................... ...................................
#
92.19% 98.68% 0.00% 93.30% mgen mgen [.] LOOP1
0.00% 0.13% 0.00% 6.08% swapper [kernel.kallsyms] [k] intel_idle
3.12% 0.29% 0.00% 0.16% gsd-color libglib-2.0.so.0.5600.4 [.] 0x0000000000049515
0.00% 0.00% 0.00% 0.06% swapper [kernel.kallsyms] [k] hrtimer_start_range_ns
1.56% 0.03% 0.00% 0.04% gsd-color libglib-2.0.so.0.5600.4 [.] 0x00000000000494b7
0.00% 0.15% 0.00% 0.04% perf [kernel.kallsyms] [k] smp_call_function_single
0.00% 0.00% 0.00% 0.02% mgen [kernel.kallsyms] [k] update_curr
0.00% 0.00% 0.00% 0.02% mgen [kernel.kallsyms] [k] apic_timer_interrupt
0.00% 0.00% 0.00% 0.02% mgen [kernel.kallsyms] [k] native_apic_msr_eoi_write
0.00% 0.00% 0.00% 0.02% mgen [kernel.kallsyms] [k] __update_load_avg_se
0.00% 0.00% 0.00% 0.02% mgen [kernel.kallsyms] [k] scheduler_tick
Now the output is sorted by the fourth event in group.
v7:
---
Rebase to latest perf/core, no other change.
v4:
---
1. Update Documentation/perf-report.txt to mention
'--group-sort-idx' support multiple groups with different
amount of events and it should be used on grouped events.
2. Update __hpp__group_sort_idx(), just return when the
idx is out of limit.
3. Return failure on symbol_conf.group_sort_idx && !session->evlist->nr_groups.
So now we don't need to use together with --group.
v3:
---
Refine the code in __hpp__group_sort_idx().
Before:
for (i = 1; i < nr_members; i++) {
if (i == idx) {
ret = field_cmp(fields_a[i], fields_b[i]);
if (ret)
goto out;
}
}
After:
if (idx >= 1 && idx < nr_members) {
ret = field_cmp(fields_a[idx], fields_b[idx]);
if (ret)
goto out;
}
Signed-off-by: Jin Yao <[email protected]>
Tested-by: Arnaldo Carvalho de Melo <[email protected]>
Acked-by: Jiri Olsa <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Kan Liang <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
[ Renamed pair_fields_alloc() to hist_entry__new_pair() and combined decl + assignment of vars ]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
In previous patch, we have supported the annotation functionality even
without symbols.
For this patch, it supports the hotkey 'a' on address in report view.
Note that, for branch mode, we only support the annotation for "branch
to" address.
Signed-off-by: Jin Yao <[email protected]>
Tested-by: Arnaldo Carvalho de Melo <[email protected]>
Acked-by: Jiri Olsa <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Kan Liang <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
For perf report on stripped binaries it is currently impossible to do
annotation. The annotation state is all tied to symbols, but there are
either no symbols, or symbols are not covering all the code.
We should support the annotation functionality even without symbols.
This patch fakes a symbol and the symbol name is the string of address.
After that, we just follow current annotation working flow.
For example,
1. perf report
Overhead Command Shared Object Symbol
20.67% div libc-2.27.so [.] __random_r
17.29% div libc-2.27.so [.] __random
10.59% div div [.] 0x0000000000000628
9.25% div div [.] 0x0000000000000612
6.11% div div [.] 0x0000000000000645
2. Select the line of "10.59% div div [.] 0x0000000000000628" and ENTER.
Annotate 0x0000000000000628
Zoom into div thread
Zoom into div DSO (use the 'k' hotkey to zoom directly into the kernel)
Browse map details
Run scripts for samples of symbol [0x0000000000000628]
Run scripts for all samples
Switch to another data file in PWD
Exit
3. Select the "Annotate 0x0000000000000628" and ENTER.
Percent│
│
│
│ Disassembly of section .text:
│
│ 0000000000000628 <.text+0x68>:
│ divsd %xmm4,%xmm0
│ divsd %xmm3,%xmm1
│ movsd (%rsp),%xmm2
│ addsd %xmm1,%xmm0
│ addsd %xmm2,%xmm0
│ movsd %xmm0,(%rsp)
Now we can see the dump of object starting from 0x628.
v5:
---
Remove the hotkey 'a' implementation from this patch. It
will be moved to a separate patch.
v4:
---
1. Support the hotkey 'a'. When we press 'a' on address,
now it supports the annotation.
2. Change the patch title from
"Support interactive annotation of code without symbols" to
"perf report: Support interactive annotation of code without symbols"
v3:
---
Keep just the ANNOTATION_DUMMY_LEN, and remove the
opts->annotate_dummy_len since it's the "maybe in future
we will provide" feature.
v2:
---
Fix a crash issue when annotating an address in "unknown" object.
The steps to reproduce this issue:
perf record -e cycles:u ls
perf report
75.29% ls ld-2.27.so [.] do_lookup_x
23.64% ls ld-2.27.so [.] __GI___tunables_init
1.04% ls [unknown] [k] 0xffffffff85c01210
0.03% ls ld-2.27.so [.] _start
When annotating 0xffffffff85c01210, the crash happens.
v2 adds checking for ms->map in add_annotate_opt(). If the object is
"unknown", ms->map is NULL.
Committer notes:
Renamed new_annotate_sym() to symbol__new_unresolved().
Use PRIx64 to fix this issue in some 32-bit arches:
ui/browsers/hists.c: In function 'symbol__new_unresolved':
ui/browsers/hists.c:2474:38: error: format '%lx' expects argument of type 'long unsigned int', but argument 5 has type 'u64' {aka 'long long unsigned int'} [-Werror=format=]
snprintf(name, sizeof(name), "%-#.*lx", BITS_PER_LONG / 4, addr);
~~~~~~^ ~~~~
%-#.*llx
Signed-off-by: Jin Yao <[email protected]>
Tested-by: Arnaldo Carvalho de Melo <[email protected]>
Tested-by: Ravi Bangoria <[email protected]>
Acked-by: Jiri Olsa <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Kan Liang <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
For branch mode, if the symbol is not found, it prints
the address.
For example, 0x0000555eee0365a0 in below output.
Overhead Command Source Shared Object Source Symbol Target Symbol
17.55% div libc-2.27.so [.] __random [.] __random
6.11% div div [.] 0x0000555eee0365a0 [.] rand
6.10% div libc-2.27.so [.] rand [.] 0x0000555eee036769
5.80% div libc-2.27.so [.] __random_r [.] __random
5.72% div libc-2.27.so [.] __random [.] __random_r
5.62% div libc-2.27.so [.] __random_r [.] __random_r
5.38% div libc-2.27.so [.] __random [.] rand
4.56% div libc-2.27.so [.] __random [.] __random
4.49% div div [.] 0x0000555eee036779 [.] 0x0000555eee0365ff
4.25% div div [.] 0x0000555eee0365fa [.] 0x0000555eee036760
But it's not very easy to understand what the instructions
are in the binary. So this patch uses the al_addr instead.
With this patch, the output is
Overhead Command Source Shared Object Source Symbol Target Symbol
17.55% div libc-2.27.so [.] __random [.] __random
6.11% div div [.] 0x00000000000005a0 [.] rand
6.10% div libc-2.27.so [.] rand [.] 0x0000000000000769
5.80% div libc-2.27.so [.] __random_r [.] __random
5.72% div libc-2.27.so [.] __random [.] __random_r
5.62% div libc-2.27.so [.] __random_r [.] __random_r
5.38% div libc-2.27.so [.] __random [.] rand
4.56% div libc-2.27.so [.] __random [.] __random
4.49% div div [.] 0x0000000000000779 [.] 0x00000000000005ff
4.25% div div [.] 0x00000000000005fa [.] 0x0000000000000760
Now we can use objdump to dump the object starting from 0x5a0.
For example,
objdump -d --start-address 0x5a0 div
00000000000005a0 <rand@plt>:
5a0: ff 25 2a 0a 20 00 jmpq *0x200a2a(%rip) # 200fd0 <__cxa_finalize@plt+0x200a20>
5a6: 68 02 00 00 00 pushq $0x2
5ab: e9 c0 ff ff ff jmpq 570 <srand@plt-0x10>
...
Committer testing:
[root@seventh ~]# perf record -a -b sleep 1
[root@seventh ~]# perf report --header-only | grep cpudesc
# cpudesc : Intel(R) Core(TM) i5-7500 CPU @ 3.40GHz
[root@seventh ~]# perf evlist -v
cycles: size: 120, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CPU|PERIOD|BRANCH_STACK, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, task: 1, precise_ip: 3, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, bpf_event: 1, branch_sample_type: ANY
[root@seventh ~]#
Before:
[root@seventh ~]# perf report --stdio --dso libsystemd-shared-241.so | head -20
# To display the perf.data header info, please use --header/--header-only options.
#
#
# Total Lost Samples: 0
#
# Samples: 2K of event 'cycles'
# Event count (approx.): 2240
#
# Overhead Command Source Shared Object Source Symbol Target Symbol Basic Block Cycles
# ........ ............... ........................ ...................... ...................... ..................
#
0.13% systemd-journal libc-2.29.so [.] cfree@GLIBC_2.2.5 [.] _int_free 1
0.09% systemd libsystemd-shared-241.so [.] 0x00007fe406465c82 [.] 0x00007fe406465d80 1
0.09% systemd libsystemd-shared-241.so [.] 0x00007fe406465ded [.] 0x00007fe406465c30 1
0.09% systemd libsystemd-shared-241.so [.] 0x00007fe406465e4e [.] 0x00007fe406465de0 1
0.09% systemd-journal systemd-journald [.] free@plt [.] cfree@GLIBC_2.2.5 1
0.09% systemd-journal libc-2.29.so [.] _int_free [.] _int_free 18
0.09% systemd-journal libc-2.29.so [.] _int_free [.] _int_free 2
0.04% systemd libsystemd-shared-241.so [.] bus_resolve@plt [.] bus_resolve 204
0.04% systemd libsystemd-shared-241.so [.] getpid_cached@plt [.] getpid_cached 7
[root@seventh ~]#
After:
[root@seventh ~]# perf report --stdio --dso libsystemd-shared-241.so | head -20
# To display the perf.data header info, please use --header/--header-only options.
#
#
# Total Lost Samples: 0
#
# Samples: 2K of event 'cycles'
# Event count (approx.): 2240
#
# Overhead Command Source Shared Object Source Symbol Target Symbol Basic Block Cycles
# ........ ............... ........................ ...................... ...................... ..................
#
0.13% systemd-journal libc-2.29.so [.] cfree@GLIBC_2.2.5 [.] _int_free 1
0.09% systemd libsystemd-shared-241.so [.] 0x00000000000f7c82 [.] 0x00000000000f7d80 1
0.09% systemd libsystemd-shared-241.so [.] 0x00000000000f7ded [.] 0x00000000000f7c30 1
0.09% systemd libsystemd-shared-241.so [.] 0x00000000000f7e4e [.] 0x00000000000f7de0 1
0.09% systemd-journal systemd-journald [.] free@plt [.] cfree@GLIBC_2.2.5 1
0.09% systemd-journal libc-2.29.so [.] _int_free [.] _int_free 18
0.09% systemd-journal libc-2.29.so [.] _int_free [.] _int_free 2
0.04% systemd libsystemd-shared-241.so [.] bus_resolve@plt [.] bus_resolve 204
0.04% systemd libsystemd-shared-241.so [.] getpid_cached@plt [.] getpid_cached 7
[root@seventh ~]#
Lets use -v to get full paths and then try objdump on the unresolved address:
[root@seventh ~]# perf report -v --stdio --dso libsystemd-shared-241.so |& grep libsystemd-shared-241.so | tail -1
0.04% systemd-journal /usr/lib/systemd/libsystemd-shared-241.so 0x80c1a B [.] 0x0000000000080c1a 0x80a95 B [.] 0x0000000000080a95 61
[root@seventh ~]#
[root@seventh ~]# objdump -d --start-address 0x00000000000f7d80 /usr/lib/systemd/libsystemd-shared-241.so | head -20
/usr/lib/systemd/libsystemd-shared-241.so: file format elf64-x86-64
Disassembly of section .text:
00000000000f7d80 <proc_cmdline_parse_given@@SD_SHARED+0x330>:
f7d80: 41 39 11 cmp %edx,(%r9)
f7d83: 0f 84 ff fe ff ff je f7c88 <proc_cmdline_parse_given@@SD_SHARED+0x238>
f7d89: 4c 8d 05 97 09 0c 00 lea 0xc0997(%rip),%r8 # 1b8727 <utf8_skip_data@@SD_SHARED+0x3147>
f7d90: b9 49 00 00 00 mov $0x49,%ecx
f7d95: 48 8d 15 c9 f5 0b 00 lea 0xbf5c9(%rip),%rdx # 1b7365 <utf8_skip_data@@SD_SHARED+0x1d85>
f7d9c: 31 ff xor %edi,%edi
f7d9e: 48 8d 35 9b ff 0b 00 lea 0xbff9b(%rip),%rsi # 1b7d40 <utf8_skip_data@@SD_SHARED+0x2760>
f7da5: e8 a6 d6 f4 ff callq 45450 <log_assert_failed_realm@plt>
f7daa: 66 0f 1f 44 00 00 nopw 0x0(%rax,%rax,1)
f7db0: 41 56 push %r14
f7db2: 41 55 push %r13
f7db4: 41 54 push %r12
f7db6: 55 push %rbp
[root@seventh ~]#
If we tried the the reported address before this patch:
[root@seventh ~]# objdump -d --start-address 0x00007fe406465d80 /usr/lib/systemd/libsystemd-shared-241.so | head -20
/usr/lib/systemd/libsystemd-shared-241.so: file format elf64-x86-64
[root@seventh ~]#
Signed-off-by: Jin Yao <[email protected]>
Tested-by: Arnaldo Carvalho de Melo <[email protected]>
Tested-by: Ravi Bangoria <[email protected]>
Acked-by: Jiri Olsa <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Kan Liang <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
After copying Arm64's perf archive with object files and perf.data file
to x86 laptop, the x86's perf kernel symbol resolution fails. It
outputs 'unknown' for all symbols parsing.
This issue is root caused by the function elf__needs_adjust_symbols(),
x86 perf tool uses one weak version, Arm64 (and powerpc) has rewritten
their own version. elf__needs_adjust_symbols() decides if need to parse
symbols with the relative offset address; but x86 building uses the weak
function which misses to check for the elf type 'ET_DYN', so that it
cannot parse symbols in Arm DSOs due to the wrong result from
elf__needs_adjust_symbols().
The DSO parsing should not depend on any specific architecture perf
building; e.g. x86 perf tool can parse Arm and Arm64 DSOs, vice versa.
And confirmed by Naveen N. Rao that powerpc64 kernels are not being
built as ET_DYN anymore and change to ET_EXEC.
This patch removes the arch specific functions for Arm64 and powerpc and
changes elf__needs_adjust_symbols() as a common function.
In the common elf__needs_adjust_symbols(), it checks an extra condition
'ET_DYN' for elf header type. With this fixing, the Arm64 DSO can be
parsed properly with x86's perf tool.
Before:
# perf script
main 3258 1 branches: 0 [unknown] ([unknown]) => ffff800010c4665c [unknown] ([kernel.kallsyms])
main 3258 1 branches: ffff800010c46670 [unknown] ([kernel.kallsyms]) => ffff800010c4eaec [unknown] ([kernel.kallsyms])
main 3258 1 branches: ffff800010c4eaec [unknown] ([kernel.kallsyms]) => ffff800010c4eb00 [unknown] ([kernel.kallsyms])
main 3258 1 branches: ffff800010c4eb08 [unknown] ([kernel.kallsyms]) => ffff800010c4e780 [unknown] ([kernel.kallsyms])
main 3258 1 branches: ffff800010c4e7a0 [unknown] ([kernel.kallsyms]) => ffff800010c4eeac [unknown] ([kernel.kallsyms])
main 3258 1 branches: ffff800010c4eebc [unknown] ([kernel.kallsyms]) => ffff800010c4ed80 [unknown] ([kernel.kallsyms])
After:
# perf script
main 3258 1 branches: 0 [unknown] ([unknown]) => ffff800010c4665c coresight_timeout+0x54 ([kernel.kallsyms])
main 3258 1 branches: ffff800010c46670 coresight_timeout+0x68 ([kernel.kallsyms]) => ffff800010c4eaec etm4_enable_hw+0x3cc ([kernel.kallsyms])
main 3258 1 branches: ffff800010c4eaec etm4_enable_hw+0x3cc ([kernel.kallsyms]) => ffff800010c4eb00 etm4_enable_hw+0x3e0 ([kernel.kallsyms])
main 3258 1 branches: ffff800010c4eb08 etm4_enable_hw+0x3e8 ([kernel.kallsyms]) => ffff800010c4e780 etm4_enable_hw+0x60 ([kernel.kallsyms])
main 3258 1 branches: ffff800010c4e7a0 etm4_enable_hw+0x80 ([kernel.kallsyms]) => ffff800010c4eeac etm4_enable+0x2d4 ([kernel.kallsyms])
main 3258 1 branches: ffff800010c4eebc etm4_enable+0x2e4 ([kernel.kallsyms]) => ffff800010c4ed80 etm4_enable+0x1a8 ([kernel.kallsyms])
v3: Changed to check for ET_DYN across all architectures.
v2: Fixed Arm64 and powerpc native building.
Reported-by: Mike Leach <[email protected]>
Signed-off-by: Leo Yan <[email protected]>
Reviewed-by: Naveen N. Rao <[email protected]>
Acked-by: Jiri Olsa <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Allison Randal <[email protected]>
Cc: Enrico Weigelt <[email protected]>
Cc: Greg Kroah-Hartman <[email protected]>
Cc: Hendrik Brueckner <[email protected]>
Cc: John Garry <[email protected]>
Cc: Kate Stewart <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Mathieu Poirier <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Thomas Richter <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
Reproducible with a clang asan build and then running perf test in
particular 'Parse event definition strings'.
Signed-off-by: Ian Rogers <[email protected]>
Acked-by: Jiri Olsa <[email protected]>
Cc: Adrian Hunter <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Leo Yan <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Stephane Eranian <[email protected]>
Cc: [email protected]
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core
Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:
perf record:
Alexey Budankov:
- Fix binding of AIO user space buffers to nodes
maps:
Dominik b. Czarnota:
- Fix off by one in strncpy() size argument.
Arnaldo Carvalho de Melo:
- Use strstarts() to look for Android libraries.
Ian Rogers:
- Give synthetic mmap events an inode generation.
man pages:
Ian Rogers:
- Set man page date to last git commit.
perf test:
Ian Rogers:
- Print if shell directory isn't present.
perf report:
Jin Yao:
- Fix no branch type statistics report issue.
perf expr:
Jiri Olsa:
- Fix copy/paste mistake
vendor events:
Kan Liang:
- Support metric constraints.
vendor events intel:
Kan Liang:
- Add NO_NMI_WATCHDOG metric constraint.
vendor events s390:
Thomas Richter:
- Add new deflate counters for IBM z15.
ARM cs-etm:
Leo Yan:
- Last branch improvements.
intel-pt:
Adrian Hunter:
- Update intel-pt.txt file with new location of the documentation.
- Add Intel PT man page references.
- Rename intel-pt.txt and put it in man page format.
perl scripting:
Michael Petlan:
- Add common_callchain to fix argument order.
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Conflicts:
tools/perf/util/map.c
|
|
Signed-off-by: Ingo Molnar <[email protected]>
|
|
Copy/paste leftover from recent refactor.
Fixes: 26226a97724d ("perf expr: Move expr lexer to flex")
Signed-off-by: Jiri Olsa <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Kajol Jain <[email protected]>
Cc: Michael Petlan <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
Previously we could get the report of branch type statistics.
For example:
# perf record -j any,save_type ...
# t perf report --stdio
#
# Branch Statistics:
#
COND_FWD: 40.6%
COND_BWD: 4.1%
CROSS_4K: 24.7%
CROSS_2M: 12.3%
COND: 44.7%
UNCOND: 0.0%
IND: 6.1%
CALL: 24.5%
RET: 24.7%
But now for the recent perf, it can't report the branch type statistics.
It's a regression issue caused by commit 40c39e304641 ("perf report: Fix
a no annotate browser displayed issue"), which only counts the branch
type statistics for browser mode.
This patch moves the branch_type_count() outside of ui__has_annotation()
checking, then branch type statistics can work for stdio mode.
Fixes: 40c39e304641 ("perf report: Fix a no annotate browser displayed issue")
Signed-off-by: Jin Yao <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Kan Liang <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
When mmap2 events are synthesized the ino_generation field isn't being
set leading to uninitialized memory being compared.
Caught with clang's -fsanitize=memory:
==124733==WARNING: MemorySanitizer: use-of-uninitialized-value
#0 0x55a96a6a65cc in __dso_id__cmp tools/perf/util/dsos.c:23:6
#1 0x55a96a6a81d5 in dso_id__cmp tools/perf/util/dsos.c:38:9
#2 0x55a96a6a717f in __dso__cmp_long_name tools/perf/util/dsos.c:74:15
#3 0x55a96a6a6c4c in __dsos__findnew_link_by_longname_id tools/perf/util/dsos.c:106:12
#4 0x55a96a6a851e in __dsos__findnew_by_longname_id tools/perf/util/dsos.c:178:9
#5 0x55a96a6a7798 in __dsos__find_id tools/perf/util/dsos.c:191:9
#6 0x55a96a6a7b57 in __dsos__findnew_id tools/perf/util/dsos.c:251:20
#7 0x55a96a6a7a57 in dsos__findnew_id tools/perf/util/dsos.c:259:17
#8 0x55a96a7776ae in machine__findnew_dso_id tools/perf/util/machine.c:2709:9
#9 0x55a96a77dfcf in map__new tools/perf/util/map.c:193:10
#10 0x55a96a77240a in machine__process_mmap2_event tools/perf/util/machine.c:1670:8
#11 0x55a96a7741a3 in machine__process_event tools/perf/util/machine.c:1882:9
#12 0x55a96a6aee39 in perf_event__process tools/perf/util/event.c:454:9
#13 0x55a96a87d633 in perf_tool__process_synth_event tools/perf/util/synthetic-events.c:63:9
#14 0x55a96a87f131 in perf_event__synthesize_mmap_events tools/perf/util/synthetic-events.c:403:7
#15 0x55a96a8815d6 in __event__synthesize_thread tools/perf/util/synthetic-events.c:548:9
#16 0x55a96a882bff in __perf_event__synthesize_threads tools/perf/util/synthetic-events.c:681:3
#17 0x55a96a881ec2 in perf_event__synthesize_threads tools/perf/util/synthetic-events.c:750:9
#18 0x55a96a562b26 in synth_all tools/perf/tests/mmap-thread-lookup.c:136:9
#19 0x55a96a5623b1 in mmap_events tools/perf/tests/mmap-thread-lookup.c:174:8
#20 0x55a96a561fa0 in test__mmap_thread_lookup tools/perf/tests/mmap-thread-lookup.c:230:2
#21 0x55a96a52c182 in run_test tools/perf/tests/builtin-test.c:378:9
#22 0x55a96a52afc1 in test_and_print tools/perf/tests/builtin-test.c:408:9
#23 0x55a96a52966e in __cmd_test tools/perf/tests/builtin-test.c:603:4
#24 0x55a96a52855d in cmd_test tools/perf/tests/builtin-test.c:747:9
#25 0x55a96a2844d4 in run_builtin tools/perf/perf.c:312:11
#26 0x55a96a282bd0 in handle_internal_command tools/perf/perf.c:364:8
#27 0x55a96a284097 in run_argv tools/perf/perf.c:408:2
#28 0x55a96a282223 in main tools/perf/perf.c:538:3
Uninitialized value was stored to memory at
#1 0x55a96a6a18f7 in dso__new_id tools/perf/util/dso.c:1230:14
#2 0x55a96a6a78ee in __dsos__addnew_id tools/perf/util/dsos.c:233:20
#3 0x55a96a6a7bcc in __dsos__findnew_id tools/perf/util/dsos.c:252:21
#4 0x55a96a6a7a57 in dsos__findnew_id tools/perf/util/dsos.c:259:17
#5 0x55a96a7776ae in machine__findnew_dso_id tools/perf/util/machine.c:2709:9
#6 0x55a96a77dfcf in map__new tools/perf/util/map.c:193:10
#7 0x55a96a77240a in machine__process_mmap2_event tools/perf/util/machine.c:1670:8
#8 0x55a96a7741a3 in machine__process_event tools/perf/util/machine.c:1882:9
#9 0x55a96a6aee39 in perf_event__process tools/perf/util/event.c:454:9
#10 0x55a96a87d633 in perf_tool__process_synth_event tools/perf/util/synthetic-events.c:63:9
#11 0x55a96a87f131 in perf_event__synthesize_mmap_events tools/perf/util/synthetic-events.c:403:7
#12 0x55a96a8815d6 in __event__synthesize_thread tools/perf/util/synthetic-events.c:548:9
#13 0x55a96a882bff in __perf_event__synthesize_threads tools/perf/util/synthetic-events.c:681:3
#14 0x55a96a881ec2 in perf_event__synthesize_threads tools/perf/util/synthetic-events.c:750:9
#15 0x55a96a562b26 in synth_all tools/perf/tests/mmap-thread-lookup.c:136:9
#16 0x55a96a5623b1 in mmap_events tools/perf/tests/mmap-thread-lookup.c:174:8
#17 0x55a96a561fa0 in test__mmap_thread_lookup tools/perf/tests/mmap-thread-lookup.c:230:2
#18 0x55a96a52c182 in run_test tools/perf/tests/builtin-test.c:378:9
#19 0x55a96a52afc1 in test_and_print tools/perf/tests/builtin-test.c:408:9
Uninitialized value was stored to memory at
#0 0x55a96a7725af in machine__process_mmap2_event tools/perf/util/machine.c:1646:25
#1 0x55a96a7741a3 in machine__process_event tools/perf/util/machine.c:1882:9
#2 0x55a96a6aee39 in perf_event__process tools/perf/util/event.c:454:9
#3 0x55a96a87d633 in perf_tool__process_synth_event tools/perf/util/synthetic-events.c:63:9
#4 0x55a96a87f131 in perf_event__synthesize_mmap_events tools/perf/util/synthetic-events.c:403:7
#5 0x55a96a8815d6 in __event__synthesize_thread tools/perf/util/synthetic-events.c:548:9
#6 0x55a96a882bff in __perf_event__synthesize_threads tools/perf/util/synthetic-events.c:681:3
#7 0x55a96a881ec2 in perf_event__synthesize_threads tools/perf/util/synthetic-events.c:750:9
#8 0x55a96a562b26 in synth_all tools/perf/tests/mmap-thread-lookup.c:136:9
#9 0x55a96a5623b1 in mmap_events tools/perf/tests/mmap-thread-lookup.c:174:8
#10 0x55a96a561fa0 in test__mmap_thread_lookup tools/perf/tests/mmap-thread-lookup.c:230:2
#11 0x55a96a52c182 in run_test tools/perf/tests/builtin-test.c:378:9
#12 0x55a96a52afc1 in test_and_print tools/perf/tests/builtin-test.c:408:9
#13 0x55a96a52966e in __cmd_test tools/perf/tests/builtin-test.c:603:4
#14 0x55a96a52855d in cmd_test tools/perf/tests/builtin-test.c:747:9
#15 0x55a96a2844d4 in run_builtin tools/perf/perf.c:312:11
#16 0x55a96a282bd0 in handle_internal_command tools/perf/perf.c:364:8
#17 0x55a96a284097 in run_argv tools/perf/perf.c:408:2
#18 0x55a96a282223 in main tools/perf/perf.c:538:3
Uninitialized value was created by a heap allocation
#0 0x55a96a22f60d in malloc llvm/llvm-project/compiler-rt/lib/msan/msan_interceptors.cpp:925:3
#1 0x55a96a882948 in __perf_event__synthesize_threads tools/perf/util/synthetic-events.c:655:15
#2 0x55a96a881ec2 in perf_event__synthesize_threads tools/perf/util/synthetic-events.c:750:9
#3 0x55a96a562b26 in synth_all tools/perf/tests/mmap-thread-lookup.c:136:9
#4 0x55a96a5623b1 in mmap_events tools/perf/tests/mmap-thread-lookup.c:174:8
#5 0x55a96a561fa0 in test__mmap_thread_lookup tools/perf/tests/mmap-thread-lookup.c:230:2
#6 0x55a96a52c182 in run_test tools/perf/tests/builtin-test.c:378:9
#7 0x55a96a52afc1 in test_and_print tools/perf/tests/builtin-test.c:408:9
#8 0x55a96a52966e in __cmd_test tools/perf/tests/builtin-test.c:603:4
#9 0x55a96a52855d in cmd_test tools/perf/tests/builtin-test.c:747:9
#10 0x55a96a2844d4 in run_builtin tools/perf/perf.c:312:11
#11 0x55a96a282bd0 in handle_internal_command tools/perf/perf.c:364:8
#12 0x55a96a284097 in run_argv tools/perf/perf.c:408:2
#13 0x55a96a282223 in main tools/perf/perf.c:538:3
SUMMARY: MemorySanitizer: use-of-uninitialized-value tools/perf/util/dsos.c:23:6 in __dso_id__cmp
Signed-off-by: Ian Rogers <[email protected]>
Acked-by: Jiri Olsa <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Stephane Eranian <[email protected]>
Cc: [email protected]
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
If the shell test directory isn't present the exit code will be 255 but
with no error messages printed. Add an error message.
Signed-off-by: Ian Rogers <[email protected]>
Acked-by: Jiri Olsa <[email protected]>
Cc: Adrian Hunter <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Leo Yan <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Stephane Eranian <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
Correct maxnode parameter value passed to mbind() syscall to be the
amount of node mask bits to analyze plus 1. Dynamically allocate node
mask memory depending on the index of node of cpu being profiled.
Fixes: c44a8b44ca9f ("perf record: Bind the AIO user space buffers to nodes")
Signed-off-by: Alexey Budankov <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
[ Remove leftover nr_bits + 1 comment in mbind() call ]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
Since common_callchain has been added to the argument array, we need to
reflect it in perl-based scripts, because otherwise the following args
would be shifted and thus incorrect. E.g. rw-by-pid and calculation of
read and written bytes:
Before:
read counts by pid:
pid comm # reads bytes_requested bytes_read
------ -------------------- ----------- ---------- ----------
19301 dd 4 424510450039736 0
After:
read counts by pid:
pid comm # reads bytes_requested bytes_read
------ -------------------- ----------- ---------- ----------
19301 dd 4 9536 4341
Committer testing:
To see before after first do:
# perf script record rw-by-pid
^C
Now you'll have a perf.data file to report on, then do before and after
using:
# perf script report rw-by-pid
Anbd notice the bytes_request/bytes_read, as above.
Signed-off-by: Michael Petlan <[email protected]>
Tested-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Benjamin Salon <[email protected]>
Cc: Jiri Olsa <[email protected]>
LPU-Reference: [email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
Make it easy for people looking in intel-pt.txt to find the new file.
Signed-off-by: Adrian Hunter <[email protected]>
Tested-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Jiri Olsa <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
Add references to Intel PT man page in man pages of associated tools.
Signed-off-by: Adrian Hunter <[email protected]>
Tested-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Jiri Olsa <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
Make the Intel PT documentation into a man page.
Signed-off-by: Adrian Hunter <[email protected]>
Tested-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Jiri Olsa <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
Currently the man page dates reflect the date the man pages were built.
This patch adjusts the date so that the date is when then man page
last had a commit against it. The date is generated using 'git log'.
Committer testing:
$ git log -1 --pretty="format:%cd" --date=short tools/perf/Documentation/perf-top.txt
2020-01-14
Before:
rm -rf /tmp/build/perf
mkdir -p /tmp/build/perf
make -C tools/perf O=/tmp/build/perf/ install
$ date
Wed 11 Mar 2020 10:21:19 AM -03
$ man perf-top | tail -1
perf 03/11/2020 PERF-TOP(1)
$
After:
rm -rf /tmp/build/perf
mkdir -p /tmp/build/perf
make -C tools/perf O=/tmp/build/perf/ install
$ date
$ date
Wed 11 Mar 2020 10:24:06 AM -03
$ man perf-top | tail -1
perf 2020-01-14 PERF-TOP(1)
$
Signed-off-by: Ian Rogers <[email protected]>
Tested-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Greg Kroah-Hartman <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Masanari Iida <[email protected]>
Cc: Mukesh Ojha <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Stephane Eranian <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
The variable 'offset' in function cs_etm__sample() is u64 type, it's not
appropriate to check it with 'while (offset > 0)'; this patch changes to
'while (offset)'.
Signed-off-by: Leo Yan <[email protected]>
Reviewed-by: Mathieu Poirier <[email protected]>
Reviewed-by: Mike Leach <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Robert Walker <[email protected]>
Cc: Suzuki Poulouse <[email protected]>
Cc: coresight ml <[email protected]>
Cc: [email protected]
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
If an instruction range packet can generate multiple instruction
samples, these samples share the same last branches; it's not necessary
to copy the same last branches repeatedly for these samples within the
same packet.
This patch moves out the last branches copying from function
cs_etm__synth_instruction_sample(), and execute it prior to generating
instruction samples.
Signed-off-by: Leo Yan <[email protected]>
Reviewed-by: Mathieu Poirier <[email protected]>
Reviewed-by: Mike Leach <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Robert Walker <[email protected]>
Cc: Suzuki Poulouse <[email protected]>
Cc: coresight ml <[email protected]>
Cc: [email protected]
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
When 'etm->instructions_sample_period' is less than
'tidq->period_instructions', the function cs_etm__sample() cannot handle
this case properly with its logic.
Let's see below flow as an example:
- If we set itrace option '--itrace=i4', then function cs_etm__sample()
has variables with initialized values:
tidq->period_instructions = 0
etm->instructions_sample_period = 4
- When the first packet is coming:
packet->instr_count = 10; the number of instructions executed in this
packet is 10, thus update period_instructions as below:
tidq->period_instructions = 0 + 10 = 10
instrs_over = 10 - 4 = 6
offset = 10 - 6 - 1 = 3
tidq->period_instructions = instrs_over = 6
- When the second packet is coming:
packet->instr_count = 10; in the second pass, assume 10 instructions
in the trace sample again:
tidq->period_instructions = 6 + 10 = 16
instrs_over = 16 - 4 = 12
offset = 10 - 12 - 1 = -3 -> the negative value
tidq->period_instructions = instrs_over = 12
So after handle these two packets, there have below issues:
The first issue is that cs_etm__instr_addr() returns the address within
the current trace sample of the instruction related to offset, so the
offset is supposed to be always unsigned value. But in fact, function
cs_etm__sample() might calculate a negative offset value (in handling
the second packet, the offset is -3) and pass to cs_etm__instr_addr()
with u64 type with a big positive integer.
The second issue is it only synthesizes 2 samples for sample period = 4.
In theory, every packet has 10 instructions so the two packets have
total 20 instructions, 20 instructions should generate 5 samples
(4 x 5 = 20). This is because cs_etm__sample() only calls once
cs_etm__synth_instruction_sample() to generate instruction sample per
range packet.
This patch fixes the logic in function cs_etm__sample(); the basic
idea for handling coming packet is:
- To synthesize the first instruction sample, it combines the left
instructions from the previous packet and the head of the new
packet; then generate continuous samples with sample period;
- At the tail of the new packet, if it has the rest instructions,
these instructions will be left for the sequential sample.
Suggested-by: Mike Leach <[email protected]>
Signed-off-by: Leo Yan <[email protected]>
Reviewed-by: Mathieu Poirier <[email protected]>
Reviewed-by: Mike Leach <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Robert Walker <[email protected]>
Cc: Suzuki Poulouse <[email protected]>
Cc: coresight ml <[email protected]>
Cc: [email protected]
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
Every time synthesize instruction sample, the last branch recording will
be reset. This is fine if the instruction period is big enough, for
example if use the option '--itrace=i100000', the last branch array is
reset for every sample with 100000 instructions per period; before
generate the next instruction sample, there has the sufficient packets
coming to fill the last branch array.
On the other hand, if set a very small period, the packets will be
significantly reduced between two continuous instruction samples, thus
the last branch array is almost empty for new instruction sample by
frequently resetting.
To allow the last branches to work properly for any instruction periods,
this patch avoids to reset the last branch for every instruction sample
and only reset it when flush the trace data. The last branches will be
reset only for two cases, one is for trace starting, another case is for
discontinuous trace; other cases can keep recording last branches for
continuous instruction samples.
Signed-off-by: Leo Yan <[email protected]>
Reviewed-by: Mathieu Poirier <[email protected]>
Reviewed-by: Mike Leach <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Robert Walker <[email protected]>
Cc: Suzuki Poulouse <[email protected]>
Cc: coresight ml <[email protected]>
Cc: [email protected]
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
If use option '--itrace=iNNN' with Arm CoreSight trace data, perf tool
fails inject instruction samples; the root cause is the packets are only
swapped for branch samples and last branches but not for instruction
samples, so the new coming packets cannot be properly handled for only
synthesizing instruction samples.
To fix this issue, this patch refactors the code with a new function
cs_etm__packet_swap() which is used to swap packets and adds the
condition for instruction samples.
Signed-off-by: Leo Yan <[email protected]>
Reviewed-by: Mathieu Poirier <[email protected]>
Reviewed-by: Mike Leach <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Robert Walker <[email protected]>
Cc: Suzuki Poulouse <[email protected]>
Cc: coresight ml <[email protected]>
Cc: [email protected]
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
And add the '/' to avoid looking at things like "/system/libsomething",
when all we want to know if it is like "/system/lib/something", i.e. if
it is in that system library dir.
Using strstarts() avoids off-by-one errors like recently fixed in this
file.
Since this adds the '/' I separated this patch, another patch will make
this consistent by removing other strncmp(str, prefix, manually
calculated prefix length) usage.
Reported-by: Dominik Czarnota <[email protected]>
Acked-by: Dominik Czarnota <[email protected]>
Cc: Adrian Hunter <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Namhyung Kim <[email protected]>
Link: Link: http://lore.kernel.org/lkml/CABEVAa0_q-uC0vrrqpkqRHy_9RLOSXOJxizMLm1n5faHRy2AeA@mail.gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
This patch fixes an off-by-one error in strncpy size argument in
tools/perf/util/map.c. The issue is that in:
strncmp(filename, "/system/lib/", 11)
the passed string literal: "/system/lib/" has 12 bytes (without the NULL
byte) and the passed size argument is 11. As a result, the logic won't
match the ending "/" byte and will pass filepaths that are stored in
other directories e.g. "/system/libmalicious/bin" or just
"/system/libmalicious".
This functionality seems to be present only on Android. I assume the
/system/ directory is only writable by the root user, so I don't think
this bug has much (or any) security impact.
Fixes: eca818369996 ("perf tools: Add automatic remapping of Android libraries")
Signed-off-by: disconnect3d <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Changbin Du <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: John Keeping <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Michael Lentine <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Song Liu <[email protected]>
Cc: Stephane Eranian <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
Add NO_NMI_WATCHDOG metric constraint to Page_Walks_Utilization for Sky Lake
and Cascade Lake.
Committer testing:
On a Lenovo T480S, Intel(R) Core(TM) i7-8650U Kaby Lake, that looking at x86's
mapfile.csv file is a:
$ grep -w skylake tools/perf/pmu-events/arch/x86/mapfile.csv
GenuineIntel-6-[4589]E,v24,skylake,core
$
So uses the constraint added in this patch in this file:
tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
Before:
# perf stat -a -M Page_Walks_Utilization sleep 2
Performance counter stats for 'system wide':
<not counted> itlb_misses.walk_pending (0.00%)
<not counted> dtlb_load_misses.walk_pending (0.00%)
<not counted> dtlb_store_misses.walk_pending (0.00%)
<not counted> ept.walk_pending (0.00%)
<not counted> cycles (0.00%)
2.001750514 seconds time elapsed
Some events weren't counted. Try disabling the NMI watchdog:
echo 0 > /proc/sys/kernel/nmi_watchdog
perf stat ...
echo 1 > /proc/sys/kernel/nmi_watchdog
The events in group usually have to be from the same PMU. Try reorganizing the group.
#
After:
# perf stat -a -M Page_Walks_Utilization sleep 2
Splitting metric group Page_Walks_Utilization into standalone metrics.
Try disabling the NMI watchdog to comply NO_NMI_WATCHDOG metric constraint:
echo 0 > /proc/sys/kernel/nmi_watchdog
perf stat ...
echo 1 > /proc/sys/kernel/nmi_watchdog
,
Performance counter stats for 'system wide':
36,883,102 itlb_misses.walk_pending # 0.1 Page_Walks_Utilization (79.99%)
123,104,146 dtlb_load_misses.walk_pending (80.02%)
13,720,795 dtlb_store_misses.walk_pending (79.99%)
0 ept.walk_pending (79.99%)
1,519,948,400 cycles (80.01%)
2.002170780 seconds time elapsed
#
Before and after, if we disable the nmi_watchdog we get:
# echo 0 > /proc/sys/kernel/nmi_watchdog
# perf stat -a -M Page_Walks_Utilization sleep 2
Performance counter stats for 'system wide':
33,721,658 itlb_misses.walk_pending # 0.1 Page_Walks_Utilization
84,070,996 dtlb_load_misses.walk_pending
9,816,071 dtlb_store_misses.walk_pending
0 ept.walk_pending
704,920,899 cycles
2.002331670 seconds time elapsed
#
More information about the metric expressions:
# perf stat -v -a -M Page_Walks_Utilization sleep 2
Using CPUID GenuineIntel-6-8E-A
metric expr ( itlb_misses.walk_pending + dtlb_load_misses.walk_pending + dtlb_store_misses.walk_pending + ept.walk_pending ) / ( 2 * cycles ) for Page_Walks_Utilization
found event itlb_misses.walk_pending
found event dtlb_load_misses.walk_pending
found event dtlb_store_misses.walk_pending
found event ept.walk_pending
found event cycles
adding {itlb_misses.walk_pending,dtlb_load_misses.walk_pending,dtlb_store_misses.walk_pending,ept.walk_pending,cycles}:W
-> cpu/umask=0x10,(null)=0x186a3,event=0x85/
-> cpu/umask=0x10,(null)=0x1e8483,event=0x8/
-> cpu/umask=0x10,(null)=0x1e8483,event=0x49/
-> cpu/umask=0x10,(null)=0x1e8483,event=0x4f/
itlb_misses.walk_pending: 8085772 16010162799 16010162799
dtlb_load_misses.walk_pending: 28134579 16010162799 16010162799
dtlb_store_misses.walk_pending: 7276535 16010162799 16010162799
ept.walk_pending: 2 16010162799 16010162799
cycles: 315140605 16010162799 16010162799
Performance counter stats for 'system wide':
8,085,772 itlb_misses.walk_pending # 0.1 Page_Walks_Utilization
28,134,579 dtlb_load_misses.walk_pending
7,276,535 dtlb_store_misses.walk_pending
2 ept.walk_pending
315,140,605 cycles
2.002333181 seconds time elapsed
#
Signed-off-by: Kan Liang <[email protected]>
Acked-by: Jiri Olsa <[email protected]>
Tested-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Jin Yao <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Ravi Bangoria <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|