8694 Commits
| Author | SHA1 | Message | Date |
|---|---|---|---|
Yang Jihong
|
e024e98e81 |
perf evlist: Add evlist__findnew_tracking_event() helper
[ Upstream commit 9c95e4ef065723496442898614d09a9a916eab81 ] Currently, intel-bts, intel-pt, and arm-spe may add tracking event to the evlist. We may need to search for the tracking event for some settings. Therefore, add evlist__findnew_tracking_event() helper. If system_wide is true, evlist__findnew_tracking_event() set the cpu map of the evsel to all online CPUs. Signed-off-by: Yang Jihong <yangjihong1@huawei.com> Acked-by: Adrian Hunter <adrian.hunter@intel.com> Tested-by: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Richter <tmricht@linux.ibm.com> Link: https://lore.kernel.org/r/20230904023340.12707-3-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Stable-dep-of: 792bc998baf9 ("perf record: Fix debug message placement for test consumption") Signed-off-by: Sasha Levin <sashal@kernel.org> |
|
|
Namhyung Kim
|
73c6ddb499 |
perf annotate: Fix annotation_calc_lines() to pass correct address to get_srcline()
[ Upstream commit aaf494cf483a1a835c44e942861429b30a00cab0 ]
It should pass a proper address (i.e. suitable for objdump or addr2line)
to get_srcline() in order to work correctly. It used to pass an address
with map__rip_2objdump() as the second argument but later it's changed
to use notes->start. It's ok in normal cases but it can be changed when
annotate_opts.full_addr is set. So let's convert the address directly
instead of using the notes->start.
Also the last argument is an IP to print symbol offset if requested. So
it should pass symbol-relative address.
Fixes:
|
|
|
Namhyung Kim
|
80e06e547d |
perf annotate: Use global annotation_options
[ Upstream commit 41fd3cacd29f47f6b9c6474b27c5b0513786c4e9 ] Now it can directly use the global options and no need to pass it as an argument. Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20231128175441.721579-5-namhyung@kernel.org [ Fixup build with GTK2=1 ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Stable-dep-of: aaf494cf483a ("perf annotate: Fix annotation_calc_lines() to pass correct address to get_srcline()") Signed-off-by: Sasha Levin <sashal@kernel.org> |
|
|
Namhyung Kim
|
1157abdc2e |
perf top: Convert to the global annotation_options
[ Upstream commit c9a21a872c69032cb9a94ebc171649c0c28141d7 ] Use the global option and drop the local copy. Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20231128175441.721579-4-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Stable-dep-of: aaf494cf483a ("perf annotate: Fix annotation_calc_lines() to pass correct address to get_srcline()") Signed-off-by: Sasha Levin <sashal@kernel.org> |
|
|
Namhyung Kim
|
dfd02119ae |
perf annotate: Introduce global annotation_options
[ Upstream commit 9d03194a36345796d4f0f8d6b72eb770a45d614e ] The annotation options are to control the behavior of objdump and the output. It's basically used by 'perf annotate' but 'perf report' and 'perf top' can call it on TUI dynamically. But it doesn't need to have a copy of annotation options in many places. As most of the work is done in the util/annotate.c file, add a global variable and set/use it instead of having their own copies. Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20231128175441.721579-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Stable-dep-of: aaf494cf483a ("perf annotate: Fix annotation_calc_lines() to pass correct address to get_srcline()") Signed-off-by: Sasha Levin <sashal@kernel.org> |
|
|
Namhyung Kim
|
260de04387 |
perf annotate: Split branch stack cycles information out of 'struct annotation_line'
[ Upstream commit de2c7eb59c342d1a61124caaf2993e325a9becb7 ] The cycles info is used only when branch stack is provided. Separate them from 'struct annotation_line' into a separate struct and lazy allocate them to save some memory. Committer notes: Make annotation__compute_ipc() check if the lazy allocation works, bailing out if so, its callers already do error checking and propagation. Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Christophe JAILLET <christophe.jaillet@wanadoo.fr> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20231103191907.54531-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Stable-dep-of: aaf494cf483a ("perf annotate: Fix annotation_calc_lines() to pass correct address to get_srcline()") Signed-off-by: Sasha Levin <sashal@kernel.org> |
|
|
Ian Rogers
|
4ddf437cae |
perf machine thread: Remove exited threads by default
[ Upstream commit 9ffa6c7512ca7aaeb30e596e2c247cb1fae7123a ]
'struct thread' values hold onto references to mmaps, DSOs, etc. When a
thread exits it is necessary to clean all of this memory up by removing
the thread from the machine's threads. Some tools require this doesn't
happen, such as auxtrace events, 'perf report' if offcpu events exist or
if a task list is being generated, so add a 'struct symbol_conf' member
to make the behavior optional. When an exited thread is left in the
machine's threads, mark it as exited.
This change relates to commit
|
|
|
Ian Rogers
|
7adc363bc2 |
perf record: Lazy load kernel symbols
[ Upstream commit 1a27fc01700fbff2f205000edf0d1d315b5f85cc ]
Commit
|
|
|
Arnaldo Carvalho de Melo
|
5c53a28ab2 |
perf probe: Add missing libgen.h header needed for using basename()
[ Upstream commit 581037151910126a7934e369e4b6ac70eda9a703 ]
This prototype is obtained indirectly, by luck, from some other header
in probe-event.c in most systems, but recently exploded on alpine:edge:
8 13.39 alpine:edge : FAIL gcc version 13.2.1 20240309 (Alpine 13.2.1_git20240309)
util/probe-event.c: In function 'convert_exec_to_group':
util/probe-event.c:225:16: error: implicit declaration of function 'basename' [-Werror=implicit-function-declaration]
225 | ptr1 = basename(exec_copy);
| ^~~~~~~~
util/probe-event.c:225:14: error: assignment to 'char *' from 'int' makes pointer from integer without a cast [-Werror=int-conversion]
225 | ptr1 = basename(exec_copy);
| ^
cc1: all warnings being treated as errors
make[3]: *** [/git/perf-6.8.0/tools/build/Makefile.build:158: util] Error 2
Fix it by adding the libgen.h header where basename() is prototyped.
Fixes:
|
|
|
Namhyung Kim
|
c418d7a675 |
perf lock contention: Add a missing NULL check
[ Upstream commit f3408580bac8ce5cd76e7391e529c0a22e7c7eb2 ]
I got a report for a failure in BPF verifier on a recent kernel with
perf lock contention command. It checks task->sighand->siglock without
checking if sighand is NULL or not. Let's add one.
; if (&curr->sighand->siglock == (void *)lock)
265: (79) r1 = *(u64 *)(r0 +2624) ; frame1: R0_w=trusted_ptr_task_struct(off=0,imm=0)
; R1_w=rcu_ptr_or_null_sighand_struct(off=0,imm=0)
266: (b7) r2 = 0 ; frame1: R2_w=0
267: (0f) r1 += r2
R1 pointer arithmetic on rcu_ptr_or_null_ prohibited, null-check it first
processed 164 insns (limit 1000000) max_states_per_insn 1 total_states 15 peak_states 15 mark_read 5
-- END PROG LOAD LOG --
libbpf: prog 'contention_end': failed to load: -13
libbpf: failed to load object 'lock_contention_bpf'
libbpf: failed to load BPF skeleton 'lock_contention_bpf': -13
Failed to load lock-contention BPF skeleton
lock contention BPF setup failed
lock contention did not detect any lock contention
Fixes:
|
|
|
Christophe JAILLET
|
dfde5becad |
perf pmu: Fix a potential memory leak in perf_pmu__lookup()
[ Upstream commit ef5de1613d7d92bdc975e6beb34bb0fa94f34078 ]
The commit in Fixes has reordered some code, but missed an error handling
path.
'goto err' now, in order to avoid a memory leak in case of error.
Fixes:
|
|
|
Mark Rutland
|
f88698d645 |
perf print-events: make is_event_supported() more robust
[ Upstream commit 25412c0364f7110faa6053c73e3fd47ca956b8c3 ]
Currently the perf tool doesn't detect support for extended event types
on Apple M1/M2 systems, and will not auto-expand plain PERF_EVENT_TYPE
hardware events into per-PMU events. This is due to the detection of
extended event types not handling mandatory filters required by the
M1/M2 PMU driver.
PMU drivers and the core perf_events code can require that
perf_event_attr::exclude_* filters are configured in a specific way and
may reject certain configurations of filters, for example:
(a) Many PMUs lack support for any event filtering, and require all
perf_event_attr::exclude_* bits to be clear. This includes Alpha's
CPU PMU, and ARM CPU PMUs prior to the introduction of PMUv2 in
ARMv7,
(b) When /proc/sys/kernel/perf_event_paranoid >= 2, the perf core
requires that perf_event_attr::exclude_kernel is set.
(c) The Apple M1/M2 PMU requires that perf_event_attr::exclude_guest is
set as the hardware PMU does not count while a guest is running (but
might be extended in future to do so).
In is_event_supported(), we try to account for cases (a) and (b), first
attempting to open an event without any filters, and if this fails,
retrying with perf_event_attr::exclude_kernel set. We do not account for
case (c), or any other filters that drivers could theoretically require
to be set.
Thus is_event_supported() will fail to detect support for any events
targeting an Apple M1/M2 PMU, even where events would be supported with
perf_event_attr:::exclude_guest set.
Since commit:
|
|
|
Ian Rogers
|
0bbe598b58 |
perf metric: Don't remove scale from counts
[ Upstream commit 6d6be5eb45b423a37d746d3ee0fd0c78f76ead9f ]
Counts were switched from the scaled saved value form to the
aggregated count to avoid double accounting. When this happened the
removing of scaling for a count should have been removed, however, it
wasn't and this wasn't observed as it normally doesn't matter because
a counter's scale is 1. A problem was observed with RAPL events that
are scaled.
Fixes:
|
|
|
Ian Rogers
|
40ae9bb1dd |
perf stat: Avoid metric-only segv
[ Upstream commit 2543947c77e0e224bda86b4e7220c2f6714da463 ]
Cycles is recognized as part of a hard coded metric in stat-shadow.c,
it may call print_metric_only with a NULL fmt string leading to a
segfault. Handle the NULL fmt explicitly.
Fixes:
|
|
|
Ian Rogers
|
e40ef597e5 |
perf expr: Fix "has_event" function for metric style events
[ Upstream commit 6dd76680b925228312756c13b9b983661b552a64 ]
Events in metrics cannot use '/' as a separator, it would be
recognized as a divide, so they use '@'. The '@' is recognized in the
metricgroups code and changed to '/', do the same in the has_event
function so that the parsing is only tried without the @s.
Fixes:
|
|
|
Ian Rogers
|
149ad69e00 |
perf srcline: Add missed addr2line closes
[ Upstream commit c7ba9d18ae47924a6ea6a47ca139779f58eb83c0 ]
The child_process for addr2line sets in and out to -1 so that pipes
get created. It is the caller's responsibility to close the pipes,
finish_command doesn't do it. Add the missed closes.
Fixes:
|
|
|
Yang Jihong
|
3e72d9d980 |
perf thread_map: Free strlist on normal path in thread_map__new_by_tid_str()
[ Upstream commit 1eb3d924e3c0b8c27388b0583a989d757866efb6 ]
slist needs to be freed in both error path and normal path in
thread_map__new_by_tid_str().
Fixes:
|
|
|
Yang Jihong
|
cfd2417c3b |
perf evsel: Fix duplicate initialization of data->id in evsel__parse_sample()
[ Upstream commit 4962aec0d684c8edb14574ccd0da53e4926ff834 ]
data->id has been initialized at line 2362, remove duplicate initialization.
Fixes:
|
|
|
Ian Rogers
|
69a0a42bdf |
perf pmu: Treat the msr pmu as software
[ Upstream commit 24852ef2e2d5c555c2da05baff112ea414b6e0f5 ]
The msr PMU is a software one, meaning msr events may be grouped
with events in a hardware context. As the msr PMU isn't marked as a
software PMU by perf_pmu__is_software, groups with the msr PMU in
are broken and the msr events placed in a different group. This
may lead to multiplexing errors where a hardware event isn't
counted while the msr event, such as tsc, is. Fix all of this by
marking the msr PMU as software, which agrees with the driver.
Before:
```
$ perf stat -e '{slots,tsc}' -a true
WARNING: events were regrouped to match PMUs
Performance counter stats for 'system wide':
1,750,335 slots
4,243,557 tsc
0.001456717 seconds time elapsed
```
After:
```
$ perf stat -e '{slots,tsc}' -a true
Performance counter stats for 'system wide':
12,526,380 slots
3,415,163 tsc
0.001488360 seconds time elapsed
```
Fixes:
|
|
|
Yang Jihong
|
e55c8abaad |
perf record: Check conflict between '--timestamp-filename' option and pipe mode before recording
[ Upstream commit 02f9b50e04812782fd006ed21c6da1c5e3e373da ]
In pipe mode, no need to switch perf data output, therefore,
'--timestamp-filename' option should not take effect.
Check the conflict before recording and output WARNING.
In this case, the check pipe mode in perf_data__switch() can be removed.
Before:
# perf record --timestamp-filename -o- perf test -w noploop | perf report -i- --percent-limit=1
# To display the perf.data header info, please use --header/--header-only options.
#
[ perf record: Woken up 1 times to write data ]
[ perf record: Dump -.2024011812110182 ]
#
# Total Lost Samples: 0
#
# Samples: 4K of event 'cycles:P'
# Event count (approx.): 2176784359
#
# Overhead Command Shared Object Symbol
# ........ ....... .................... ......................................
#
97.83% perf perf [.] noploop
#
# (Tip: Print event counts in CSV format with: perf stat -x,)
#
After:
# perf record --timestamp-filename -o- perf test -w noploop | perf report -i- --percent-limit=1
WARNING: --timestamp-filename option is not available in pipe mode.
# To display the perf.data header info, please use --header/--header-only options.
#
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.000 MB - ]
#
# Total Lost Samples: 0
#
# Samples: 4K of event 'cycles:P'
# Event count (approx.): 2185575421
#
# Overhead Command Shared Object Symbol
# ........ ....... ..................... .............................................
#
97.75% perf perf [.] noploop
#
# (Tip: Profiling branch (mis)predictions with: perf record -b / perf report)
#
Fixes:
|
|
|
Kan Liang
|
1f7b3c801f |
perf top: Uniform the event name for the hybrid machine
[ Upstream commit a61f89bf76ef6f87ec48dd90dbc73a6cf9952edc ] It's hard to distinguish the default cycles events among hybrid PMUs. For example, $ perf top Available samples 385 cycles:P 903 cycles:P The other tool, e.g., perf record, uniforms the event name and adds the hybrid PMU name before opening the event. So the events can be easily distinguished. Apply the same methodology for the perf top as well. The evlist__uniquify_name() will be invoked by both record and top. Move it to util/evlist.c With the patch: $ perf top Available samples 148 cpu_atom/cycles:P/ 1K cpu_core/cycles:P/ Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Hector Martin <marcan@marcan.st> Cc: Marc Zyngier <maz@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/r/20231214144612.1092028-2-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Stable-dep-of: 02f9b50e0481 ("perf record: Check conflict between '--timestamp-filename' option and pipe mode before recording") Signed-off-by: Sasha Levin <sashal@kernel.org> |
|
|
James Clark
|
f7799ecf30 |
perf evlist: Fix evlist__new_default() for > 1 core PMU
[ Upstream commit 7814fe24a6211a610db0b408d87420403b5b7a36 ]
The 'Session topology' test currently fails with this message when
evlist__new_default() opens more than one event:
32: Session topology :
--- start ---
templ file: /tmp/perf-test-vv5YzZ
Using CPUID 0x00000000410fd070
Opening: unknown-hardware:HG
------------------------------------------------------------
perf_event_attr:
type 0 (PERF_TYPE_HARDWARE)
config 0xb00000000
disabled 1
------------------------------------------------------------
sys_perf_event_open: pid 0 cpu -1 group_fd -1 flags 0x8 = 4
Opening: unknown-hardware:HG
------------------------------------------------------------
perf_event_attr:
type 0 (PERF_TYPE_HARDWARE)
config 0xa00000000
disabled 1
------------------------------------------------------------
sys_perf_event_open: pid 0 cpu -1 group_fd -1 flags 0x8 = 5
non matching sample_type
FAILED tests/topology.c:73 can't get session
---- end ----
Session topology: FAILED!
This is because when re-opening the file and parsing the header, Perf
expects that any file that has more than one event has the sample ID
flag set. Perf record already sets the flag in a similar way when there
is more than one event, so add the same logic to evlist__new_default().
evlist__new_default() is only currently used in tests, so I don't
expect this change to have any other side effects. The other tests that
use it don't save and re-open the file so don't hit this issue.
The session topology test has been failing on Arm big.LITTLE platforms
since commit
|
|
|
Ben Gainey
|
4e0d679193 |
perf db-export: Fix missing reference count get in call_path_from_sample()
[ Upstream commit 1e24ce402c97dc3c0ab050593f1d5f6fde524564 ]
The addr_location map and maps fields in the inner loop were missing
calls to map__get()/maps__get(). The subsequent addr_location__exit()
call in each loop puts the map/maps fields causing use-after-free
aborts.
This issue reproduces on at least arm64 and x86_64 with something
simple like `perf record -g ls` followed by `perf script -s script.py`
with the following script:
perf_db_export_mode = True
perf_db_export_calls = False
perf_db_export_callchains = True
def sample_table(*args):
print(f'sample_table({args})')
def call_path_table(*args):
print(f'call_path_table({args}')
Committer testing:
This test, just introduced by Ian Rogers, now passes, not segfaulting
anymore:
# perf test "perf script tests"
95: perf script tests : Ok
#
Fixes:
|
|
|
Ian Rogers
|
8fdeaf4008 |
perf stat: Fix hard coded LL miss units
[ Upstream commit f2567e12a090f0eb22553a4468d4c4fe04aad906 ]
Copy-paste error where LL cache misses are reported as l1i.
Fixes:
|
|
|
Ian Rogers
|
35bcf6bf32 |
perf env: Avoid recursively taking env->bpf_progs.lock
[ Upstream commit 9c51f8788b5d4e9f46afbcf563255cfd355690b3 ]
Add variants of perf_env__insert_bpf_prog_info(), perf_env__insert_btf()
and perf_env__find_btf prefixed with __ to indicate the
env->bpf_progs.lock is assumed held.
Call these variants when the lock is held to avoid recursively taking it
and potentially having a thread deadlock with itself.
Fixes:
|
|
|
Namhyung Kim
|
46bd939d85 |
perf unwind-libunwind: Fix base address for .eh_frame
[ Upstream commit 4fb54994b2360ab5029ee3a959161f6fe6bbb349 ]
The base address of a DSO mapping should start at the start of the file.
Usually DSOs are mapped from the pgoff 0 so it doesn't matter when it
uses the start of the map address.
But generated DSOs for JIT codes doesn't start from the 0 so it should
subtract the offset to calculate the .eh_frame table offsets correctly.
Fixes:
|
|
|
Namhyung Kim
|
c05c54f0cd |
perf unwind-libdw: Handle JIT-generated DSOs properly
[ Upstream commit c966d23a351a33f8a977fd7efbb6f467132f7383 ]
Usually DSOs are mapped from the beginning of the file, so the base
address of the DSO can be calculated by map->start - map->pgoff.
However, JIT DSOs which are generated by `perf inject -j`, are mapped
only the code segment. This makes unwind-libdw code confusing and
rejects processing unwinds in the JIT DSOs. It should use the map
start address as base for them to fix the confusion.
Fixes:
|
|
|
Namhyung Kim
|
c8d6d5d080 |
perf genelf: Set ELF program header addresses properly
[ Upstream commit 1af478903fc48c1409a8dd6b698383b62387adf1 ]
The text section starts after the ELF headers so PHDR.p_vaddr and
others should have the correct addresses.
Fixes:
|
|
|
Yicong Yang
|
2f4c1c3580 |
perf hisi-ptt: Fix one memory leakage in hisi_ptt_process_auxtrace_event()
[ Upstream commit 1bc479d665bc25a9a4e8168d5b400a47491511f9 ]
ASan complains a memory leakage in hisi_ptt_process_auxtrace_event()
that the data buffer is not freed. Since currently we only support the
raw dump trace mode, the data buffer is used only within this function.
So fix this by freeing the data buffer before going out.
Fixes:
|
|
|
Yicong Yang
|
f8d47ca678 |
perf header: Fix one memory leakage in perf_event__fprintf_event_update()
[ Upstream commit 813900d19b923fc1b241c1ce292472f68066092b ]
When dump the raw trace by `perf report -D` ASan reports a memory
leakage in perf_event__fprintf_event_update().
It shows that we allocated a temporary cpumap for dumping the CPUs but
doesn't release it and it's not used elsewhere. Fix this by free the
cpumap after the dumping.
Fixes:
|
|
|
Kan Liang
|
9cc93a61cd |
perf mem: Fix error on hybrid related to availability of mem event in a PMU
[ Upstream commit a4320085a6c694326dd8db46f563d52d1a826f07 ]
The below error can be triggered on a hybrid machine.
$ perf mem record -t load sleep 1
event syntax error: 'breakpoint/mem-loads,ldlat=30/P'
\___ Bad event or PMU
Unable to find PMU or event on a PMU of 'breakpoint'
In the perf_mem_events__record_args(), the current perf never checks the
availability of a mem event on a given PMU. All the PMUs will be added
to the perf mem event list. Perf errors out for the unsupported PMU.
Extend perf_mem_event__supported() and take a PMU into account. Check
the mem event for each PMU before adding it to the perf mem event list.
Optimize the perf_mem_events__init() a little bit. The function is to
check whether the mem events are supported in the system. It doesn't
need to scan all PMUs. Just return with the first supported PMU is good
enough.
Fixes:
|
|
|
Adrian Hunter
|
bee4ceb8ea |
perf header: Fix segfault on build_mem_topology() error path
[ Upstream commit 70df07838fc1c0acfab3325ae79014e241a88bdf ]
Do not increase the node count unless a node has been successfully read,
because it can lead to a segfault if an error occurs.
For example, if perf exceeds the open file limit in memory_node__read(),
which, on a test system, could be made to happen by setting the file limit
to exactly 32:
Before:
$ ulimit -n 32
$ perf mem record --all-user -- sleep 1
[ perf record: Woken up 1 times to write data ]
failed: can't open memory sysfs data
perf: Segmentation fault
Obtained 14 stack frames.
perf(sighandler_dump_stack+0x48) [0x55f4b1f59558]
/lib/x86_64-linux-gnu/libc.so.6(+0x42520) [0x7f4ba1c42520]
/lib/x86_64-linux-gnu/libc.so.6(free+0x1e) [0x7f4ba1ca53fe]
perf(+0x178ff4) [0x55f4b1f48ff4]
perf(+0x179a70) [0x55f4b1f49a70]
perf(+0x17ef5d) [0x55f4b1f4ef5d]
perf(+0x85c0b) [0x55f4b1e55c0b]
perf(cmd_record+0xe1d) [0x55f4b1e5920d]
perf(cmd_mem+0xc96) [0x55f4b1e80e56]
perf(+0x130460) [0x55f4b1f00460]
perf(main+0x689) [0x55f4b1e427d9]
/lib/x86_64-linux-gnu/libc.so.6(+0x29d90) [0x7f4ba1c29d90]
/lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0x80) [0x7f4ba1c29e40]
perf(_start+0x25) [0x55f4b1e42a25]
Segmentation fault (core dumped)
$
After:
$ ulimit -n 32
$ perf mem record --all-user -- sleep 1
[ perf record: Woken up 1 times to write data ]
failed: can't open memory sysfs data
[ perf record: Captured and wrote 0.005 MB perf.data (11 samples) ]
$
Fixes:
|
|
|
Ian Rogers
|
114d0e5b99 |
perf metrics: Avoid segv if default metricgroup isn't set
commit e2b005d6ec0e738df584190e21d2c7ada37266a0 upstream.
A metric is default by having "Default" within its groups. The default
metricgroup name needn't be set and this can result in segv in
default_metricgroup_cmp and perf_stat__print_shadow_stats_metricgroup
that assume it has a value when there is a Default metric group. To
avoid the segv initialize the value to "".
Fixes:
|
|
|
Adrian Hunter
|
ee534525ba |
perf intel-pt: Fix async branch flags
commit f2d87895cbc4af80649850dcf5da36de6b2ed3dd upstream.
Ensure PERF_IP_FLAG_ASYNC is set always for asynchronous branches (i.e.
interrupts etc).
Fixes:
|
|
|
Ian Rogers
|
581570045a |
perf hist: Add missing puts to hist__account_cycles
[ Upstream commit c1149037f65bcf0334886180ebe3d5efcf214912 ]
Caught using reference count checking on perf top with
"--call-graph=lbr". After this no memory leaks were detected.
Fixes:
|
|
|
Ian Rogers
|
c139d4d928 |
perf machine: Avoid out of bounds LBR memory read
[ Upstream commit ab8ce150781d326c6bfbe1e09f175ffde1186f80 ]
Running perf top with address sanitizer and "--call-graph=lbr" fails
due to reading sample 0 when no samples exist. Add a guard to prevent
this.
Fixes:
|
|
|
Thomas Richter
|
b18be5a561 |
perf trace: Use the right bpf_probe_read(_str) variant for reading user data
[ Upstream commit 5069211e2f0b47e75119805e23ae6352d871e263 ]
Perf test case 111 Check open filename arg using perf trace + vfs_getname
fails on s390. This is caused by a failing function
bpf_probe_read() in file util/bpf_skel/augmented_raw_syscalls.bpf.c.
The root cause is the lookup by address. Function bpf_probe_read()
is used. This function works only for architectures
with ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE.
On s390 is not possible to determine from the address to which
address space the address belongs to (user or kernel space).
Replace bpf_probe_read() by bpf_probe_read_kernel()
and bpf_probe_read_str() by bpf_probe_read_user_str() to
explicity specify the address space the address refers to.
Output before:
# ./perf trace -eopen,openat -- touch /tmp/111
libbpf: prog 'sys_enter': BPF program load failed: Invalid argument
libbpf: prog 'sys_enter': -- BEGIN PROG LOAD LOG --
reg type unsupported for arg#0 function sys_enter#75
0: R1=ctx(off=0,imm=0) R10=fp0
; int sys_enter(struct syscall_enter_args *args)
0: (bf) r6 = r1 ; R1=ctx(off=0,imm=0) R6_w=ctx(off=0,imm=0)
; return bpf_get_current_pid_tgid();
1: (85) call bpf_get_current_pid_tgid#14 ; R0_w=scalar()
2: (63) *(u32 *)(r10 -8) = r0 ; R0_w=scalar() R10=fp0 fp-8=????mmmm
3: (bf) r2 = r10 ; R2_w=fp0 R10=fp0
;
.....
lines deleted here
.....
23: (bf) r3 = r6 ; R3_w=ctx(off=0,imm=0) R6=ctx(off=0,imm=0)
24: (85) call bpf_probe_read#4
unknown func bpf_probe_read#4
processed 23 insns (limit 1000000) max_states_per_insn 0 \
total_states 2 peak_states 2 mark_read 2
-- END PROG LOAD LOG --
libbpf: prog 'sys_enter': failed to load: -22
libbpf: failed to load object 'augmented_raw_syscalls_bpf'
libbpf: failed to load BPF skeleton 'augmented_raw_syscalls_bpf': -22
....
Output after:
# ./perf test -Fv 111
111: Check open filename arg using perf trace + vfs_getname :
--- start ---
1.085 ( 0.011 ms): touch/320753 openat(dfd: CWD, filename: \
"/tmp/temporary_file.SWH85", \
flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: IRUGO|IWUGO) = 3
---- end ----
Check open filename arg using perf trace + vfs_getname: Ok
#
Test with the sleep command shows:
Output before:
# ./perf trace -e *sleep sleep 1.234567890
0.000 (1234.681 ms): sleep/63114 clock_nanosleep(rqtp: \
{ .tv_sec: 0, .tv_nsec: 0 }, rmtp: 0x3ffe0979720) = 0
#
Output after:
# ./perf trace -e *sleep sleep 1.234567890
0.000 (1234.686 ms): sleep/64277 clock_nanosleep(rqtp: \
{ .tv_sec: 1, .tv_nsec: 234567890 }, rmtp: 0x3fff3df9ea0) = 0
#
Fixes:
|
|
|
Namhyung Kim
|
517310f7ce |
perf tools: Do not ignore the default vmlinux.h
[ Upstream commit 1f36b190ad2dea68e3a7e84b7b2f24ce8c4063ea ]
The recent change made it possible to generate vmlinux.h from BTF and
to ignore the file. But we also have a minimal vmlinux.h that will be
used by default. It should not be ignored by GIT.
Fixes:
|
|
|
Ian Rogers
|
650b41987a |
perf mem-events: Avoid uninitialized read
[ Upstream commit 85f73c377b2ac9988a204b119aebb33ca5c60083 ]
pmu should be initialized to NULL before perf_pmus__scan loop. Fix and
shrink the scope of pmu at the same time. Issue detected by clang-tidy.
Fixes:
|
|
|
Ian Rogers
|
4fa4152950 |
perf parse-events: Fix for term values that are raw events
[ Upstream commit b20576fd7fe39554b212095c3c0d7a3dff512515 ]
Raw events can be strings like 'r0xead' but the 0x is optional so they
can also be 'read'. On IcelakeX uncore_imc_free_running has an event
called 'read' which may be programmed as:
```
$ perf stat -e 'uncore_imc_free_running/event=read/' -a sleep 1
```
However, the PE_RAW type isn't allowed on the right of a term, even
though in this case we just want to interpret it as a string. This
leads to the following error on IcelakeX:
```
$ perf stat -e 'uncore_imc_free_running/event=read/' -a sleep 1
event syntax error: '..nning/event=read/'
\___ parser error
Run 'perf list' for a list of valid events
Usage: perf stat [<options>] [<command>]
-e, --event <event> event selector. use 'perf list' to list available events
```
Fix this by allowing raw types on the right of terms and treat them as
strings, just as is already done for PE_LEGACY_CACHE. Make this
consistent by just entirely removing name_or_legacy and always using
name_or_raw that covers all three cases.
Fixes:
|
|
|
Namhyung Kim
|
d9bd26de86 |
perf record: Fix BTF type checks in the off-cpu profiling
[ Upstream commit 0e501a65d35bf72414379fed0e31a0b6b81ab57d ]
The BTF func proto for a tracepoint has one more argument than the
actual tracepoint function since it has a context argument at the
begining. So it should compare to 5 when the tracepoint has 4
arguments.
typedef void (*btf_trace_sched_switch)(void *, bool, struct task_struct *, struct task_struct *, unsigned int);
Also, recent change in the perf tool would use a hand-written minimal
vmlinux.h to generate BTF in the skeleton. So it won't have the info
of the tracepoint. Anyway it should use the kernel's vmlinux BTF to
check the type in the kernel.
Fixes:
|
|
|
Ian Rogers
|
e3c2dc9d60 |
perf parse-events: Fix tracepoint name memory leak
[ Upstream commit ede72dca45b1893f3e9236b6ad6c4e790db232f6 ]
Fuzzing found that an invalid tracepoint name would create a memory
leak with an address sanitizer build:
```
$ perf stat -e '*:o/' true
event syntax error: '*:o/'
\___ parser error
Run 'perf list' for a list of valid events
Usage: perf stat [<options>] [<command>]
-e, --event <event> event selector. use 'perf list' to list available events
=================================================================
==59380==ERROR: LeakSanitizer: detected memory leaks
Direct leak of 4 byte(s) in 2 object(s) allocated from:
#0 0x7f38ac07077b in __interceptor_strdup ../../../../src/libsanitizer/asan/asan_interceptors.cpp:439
#1 0x55f2f41be73b in str util/parse-events.l:49
#2 0x55f2f41d08e8 in parse_events_lex util/parse-events.l:338
#3 0x55f2f41dc3b1 in parse_events_parse util/parse-events-bison.c:1464
#4 0x55f2f410b8b3 in parse_events__scanner util/parse-events.c:1822
#5 0x55f2f410d1b9 in __parse_events util/parse-events.c:2094
#6 0x55f2f410e57f in parse_events_option util/parse-events.c:2279
#7 0x55f2f4427b56 in get_value tools/lib/subcmd/parse-options.c:251
#8 0x55f2f4428d98 in parse_short_opt tools/lib/subcmd/parse-options.c:351
#9 0x55f2f4429d80 in parse_options_step tools/lib/subcmd/parse-options.c:539
#10 0x55f2f442acb9 in parse_options_subcommand tools/lib/subcmd/parse-options.c:654
#11 0x55f2f3ec99fc in cmd_stat tools/perf/builtin-stat.c:2501
#12 0x55f2f4093289 in run_builtin tools/perf/perf.c:322
#13 0x55f2f40937f5 in handle_internal_command tools/perf/perf.c:375
#14 0x55f2f4093bbd in run_argv tools/perf/perf.c:419
#15 0x55f2f409412b in main tools/perf/perf.c:535
SUMMARY: AddressSanitizer: 4 byte(s) leaked in 2 allocation(s).
```
Fix by adding the missing destructor.
Fixes:
|
|
|
Ian Rogers
|
67a21d9b93 |
perf evlist: Avoid frequency mode for the dummy event
[ Upstream commit f9cdeb58a9cf46c09b56f5f661ea8da24b6458c3 ]
Dummy events are created with an attribute where the period and freq
are zero. evsel__config will then see the uninitialized values and
initialize them in evsel__default_freq_period. As fequency mode is
used by default the dummy event would be set to use frequency
mode. However, this has no effect on the dummy event but does cause
unnecessary timers/interrupts. Avoid this overhead by setting the
period to 1 for dummy events.
evlist__add_aux_dummy calls evlist__add_dummy then sets freq=0 and
period=1. This isn't necessary after this change and so the setting is
removed.
From Stephane:
The dummy event is not counting anything. It is used to collect mmap
records and avoid a race condition during the synthesize mmap phase of
perf record. As such, it should not cause any overhead during active
profiling. Yet, it did. Because of a bug the dummy event was
programmed as a sampling event in frequency mode. Events in that mode
incur more kernel overheads because on timer tick, the kernel has to
look at the number of samples for each event and potentially adjust
the sampling period to achieve the desired frequency. The dummy event
was therefore adding a frequency event to task and ctx contexts we may
otherwise not have any, e.g.,
perf record -a -e cpu/event=0x3c,period=10000000/.
On each timer tick the perf_adjust_freq_unthr_context() is invoked and
if ctx->nr_freq is non-zero, then the kernel will loop over ALL the
events of the context looking for frequency mode ones. In doing, so it
locks the context, and enable/disable the PMU of each hw event. If all
the events of the context are in period mode, the kernel will have to
traverse the list for nothing incurring overhead. The overhead is
multiplied by a very large factor when this happens in a guest kernel.
There is no need for the dummy event to be in frequency mode, it does
not count anything and therefore should not cause extra overhead for
no reason.
Fixes:
|
|
|
Adrian Hunter
|
7a48b58eb5 |
perf dlfilter: Fix use of addr_location__exit() in dlfilter__object_code()
Stop calling addr_location__exit() when addr_location__init() was not
called.
Fixes:
|
|
|
Wyes Karny
|
48a3adcf47 |
perf pmu: Fix perf stat output with correct scale and unit
The perf_pmu__parse_* functions for the sysfs files of pmu event’s scale, unit, per-pkg and snapshot were updated in commit |
|
|
Ian Rogers
|
eaaebb01a7 |
perf pmu: Ensure all alias variables are initialized
Fix an error detected by memory sanitizer:
```
==4033==WARNING: MemorySanitizer: use-of-uninitialized-value
#0 0x55fb0fbedfc7 in read_alias_info tools/perf/util/pmu.c:457:6
#1 0x55fb0fbea339 in check_info_data tools/perf/util/pmu.c:1434:2
#2 0x55fb0fbea339 in perf_pmu__check_alias tools/perf/util/pmu.c:1504:9
#3 0x55fb0fbdca85 in parse_events_add_pmu tools/perf/util/parse-events.c:1429:32
#4 0x55fb0f965230 in parse_events_parse tools/perf/util/parse-events.y:299:6
#5 0x55fb0fbdf6b2 in parse_events__scanner tools/perf/util/parse-events.c:1822:8
#6 0x55fb0fbdf8c1 in __parse_events tools/perf/util/parse-events.c:2094:8
#7 0x55fb0fa8ffa9 in parse_events tools/perf/util/parse-events.h:41:9
#8 0x55fb0fa8ffa9 in test_event tools/perf/tests/parse-events.c:2393:8
#9 0x55fb0fa8f458 in test__pmu_events tools/perf/tests/parse-events.c:2551:15
#10 0x55fb0fa6d93f in run_test tools/perf/tests/builtin-test.c:242:9
#11 0x55fb0fa6d93f in test_and_print tools/perf/tests/builtin-test.c:271:8
#12 0x55fb0fa6d082 in __cmd_test tools/perf/tests/builtin-test.c:442:5
#13 0x55fb0fa6d082 in cmd_test tools/perf/tests/builtin-test.c:564:9
#14 0x55fb0f942720 in run_builtin tools/perf/perf.c:322:11
#15 0x55fb0f942486 in handle_internal_command tools/perf/perf.c:375:8
#16 0x55fb0f941dab in run_argv tools/perf/perf.c:419:2
#17 0x55fb0f941dab in main tools/perf/perf.c:535:3
```
Fixes:
|
|
|
Ian Rogers
|
33b725ce7b |
perf trace: Avoid compile error wrt redefining bool
Make part of an existing TODO conditional to avoid the following build
error:
```
tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c:26:14: error: cannot combine with previous 'char' declaration specifier
26 | typedef char bool;
| ^
include/stdbool.h:20:14: note: expanded from macro 'bool'
20 | #define bool _Bool
| ^
tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c:26:1: error: typedef requires a name [-Werror,-Wmissing-declarations]
26 | typedef char bool;
| ^~~~~~~~~~~~~~~~~
2 errors generated.
```
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20230913184957.230076-1-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
|
|
|
Ian Rogers
|
4a73fca226 |
perf bpf-prologue: Remove unused file
Commit |
|
|
Arnaldo Carvalho de Melo
|
a6e414a4cb |
perf tools: Update copy of libbpf's hashmap.c
To pick the changes in:
|
|
|
Linus Torvalds
|
535a265d7f |
perf tools changes for v6.6:
perf tools maintainership:
- Add git information for perf-tools and perf-tools-next trees/branches to the
MAINTAINERS file. That is where development now takes place and myself and
Namhyung Kim have write access, more people to come as we emulate other
maintainer groups.
perf record:
- Record kernel data maps when 'perf record --data' is used, so that global variables can
be resolved and used in tools that do data profiling.
perf trace:
- Remove the old, experimental support for BPF events in which a .c file was passed as
an event: "perf trace -e hello.c" to then get compiled and loaded.
The only known usage for that, that shipped with the kernel as an example for such events,
augmented the raw_syscalls tracepoints and was converted to a libbpf skeleton, reusing all
the user space components and the BPF code connected to the syscalls.
In the end just the way to glue the BPF part and the user space type beautifiers changed,
now being performed by libbpf skeletons.
The next step is to use BTF to do pretty printing of all syscall types, as discussed with
Alan Maguire and others.
Now, on a perf built with BUILD_BPF_SKEL=1 we get most if not all path/filenames/strings,
some of the networking data structures, perf_event_attr, etc, i.e. systemwide tracing of
nanosleep calls and perf_event_open syscalls while 'perf stat' runs 'sleep' for 5 seconds:
# perf trace -a -e *nanosleep,perf* perf stat -e cycles,instructions sleep 5
0.000 ( 9.034 ms): perf/327641 perf_event_open(attr_uptr: { type: 0 (PERF_TYPE_HARDWARE), size: 136, config: 0 (PERF_COUNT_HW_CPU_CYCLES), sample_type: IDENTIFIER, read_format: TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING, disabled: 1, inherit: 1, enable_on_exec: 1, exclude_guest: 1 }, pid: 327642 (perf), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 3
9.039 ( 0.006 ms): perf/327641 perf_event_open(attr_uptr: { type: 0 (PERF_TYPE_HARDWARE), size: 136, config: 0x1 (PERF_COUNT_HW_INSTRUCTIONS), sample_type: IDENTIFIER, read_format: TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING, disabled: 1, inherit: 1, enable_on_exec: 1, exclude_guest: 1 }, pid: 327642 (perf-exec), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 4
? ( ): gpm/991 ... [continued]: clock_nanosleep()) = 0
10.133 ( ): sleep/327642 clock_nanosleep(rqtp: { .tv_sec: 5, .tv_nsec: 0 }, rmtp: 0x7ffd36f83ed0) ...
? ( ): pool-gsd-smart/3051 ... [continued]: clock_nanosleep()) = 0
30.276 ( ): gpm/991 clock_nanosleep(rqtp: { .tv_sec: 2, .tv_nsec: 0 }, rmtp: 0x7ffcc6f73710) ...
223.215 (1000.430 ms): pool-gsd-smart/3051 clock_nanosleep(rqtp: { .tv_sec: 1, .tv_nsec: 0 }, rmtp: 0x7f6e7fffec90) = 0
30.276 (2000.394 ms): gpm/991 ... [continued]: clock_nanosleep()) = 0
1230.814 ( ): pool-gsd-smart/3051 clock_nanosleep(rqtp: { .tv_sec: 1, .tv_nsec: 0 }, rmtp: 0x7f6e7fffec90) ...
1230.814 (1000.404 ms): pool-gsd-smart/3051 ... [continued]: clock_nanosleep()) = 0
2030.886 ( ): gpm/991 clock_nanosleep(rqtp: { .tv_sec: 2, .tv_nsec: 0 }, rmtp: 0x7ffcc6f73710) ...
2237.709 (1000.153 ms): pool-gsd-smart/3051 clock_nanosleep(rqtp: { .tv_sec: 1, .tv_nsec: 0 }, rmtp: 0x7f6e7fffec90) = 0
? ( ): crond/1172 ... [continued]: clock_nanosleep()) = 0
3242.699 ( ): pool-gsd-smart/3051 clock_nanosleep(rqtp: { .tv_sec: 1, .tv_nsec: 0 }, rmtp: 0x7f6e7fffec90) ...
2030.886 (2000.385 ms): gpm/991 ... [continued]: clock_nanosleep()) = 0
3728.078 ( ): crond/1172 clock_nanosleep(rqtp: { .tv_sec: 60, .tv_nsec: 0 }, rmtp: 0x7ffe0971dcf0) ...
3242.699 (1000.158 ms): pool-gsd-smart/3051 ... [continued]: clock_nanosleep()) = 0
4031.409 ( ): gpm/991 clock_nanosleep(rqtp: { .tv_sec: 2, .tv_nsec: 0 }, rmtp: 0x7ffcc6f73710) ...
10.133 (5000.375 ms): sleep/327642 ... [continued]: clock_nanosleep()) = 0
Performance counter stats for 'sleep 5':
2,617,347 cycles
1,855,997 instructions # 0.71 insn per cycle
5.002282128 seconds time elapsed
0.000855000 seconds user
0.000852000 seconds sys
#
perf annotate:
- Building with binutils' libopcode now is opt-in (BUILD_NONDISTRO=1) for
licensing reasons, and we missed a build test on tools/perf/tests makefile.
Since we now default to NDEBUG=1, we ended up segfaulting when building with
BUILD_NONDISTRO=1 because a needed initialization routine was being "error
checked" via an assert.
Fix it by explicitly checking the result and aborting instead if it fails.
We better back propagate the error, but at least 'perf annotate' on samples
collected for a BPF program is back working when perf is built with
BUILD_NONDISTRO=1.
perf report/top:
- Add back TUI hierarchy mode header, that is seen when using 'perf report/top --hierarchy'.
- Fix the number of entries for 'e' key in the TUI that was preventing navigation of
lines when expanding an entry.
perf report/script:
- Support cross platform register handling, allowing a perf.data file collected
on one architecture to have registers sampled correctly displayed when
analysis tools such as 'perf report' and 'perf script' are used on a different
architecture.
- Fix handling of event attributes in pipe mode, i.e. when one uses:
perf record -o - | perf report -i -
When no perf.data files are used.
- Handle files generated via pipe mode with a version of perf and then read
also via pipe mode with a different version of perf, where the event attr
record may have changed, use the record size field to properly support this
version mismatch.
perf probe:
- Accessing global variables from uprobes isn't supported, make the error
message state that instead of stating that some minimal kernel version is
needed to have that feature. This seems just a tool limitation, the kernel
probably has all that is needed.
perf tests:
- Fix a reference count related leak in the dlfilter v0 API where the result
of a thread__find_symbol_fb() is not matched with an addr_location__exit()
to drop the reference counts of the resolved components (machine, thread, map,
symbol, etc). Add a dlfilter test to make sure that doesn't regresses.
- Lots of fixes for the 'perf test' written in shell script related to problems
found with the shellcheck utility.
- Fixes for 'perf test' shell scripts testing features enabled when perf is
built with BUILD_BPF_SKEL=1, such as 'perf stat' bpf counters.
- Add perf record sample filtering test, things like the following example, that gets
implemented as a BPF filter attached to the event:
# perf record -e task-clock -c 10000 --filter 'ip < 0xffffffff00000000'
- Improve the way the task_analyzer test checks if libtraceevent is linked,
using 'perf version --build-options' instead of the more expensinve
'perf record -e "sched:sched_switch"'.
- Add support for riscv in the mmap-basic test. (This went as well via the RiscV tree, same contents).
libperf:
- Implement riscv mmap support (This went as well via the RiscV tree, same contents).
perf script:
- New tool that converts perf.data files to the firefox profiler format so that one can use
the visualizer at https://profiler.firefox.com/. Done by Anup Sharma as part of this year's
Google Summer of Code.
One can generate the output and upload it to the web interface but Anup also automated
everything:
perf script gecko -F 99 -a sleep 60
- Support syscall name parsing on arm64.
- Print "cgroup" field on the same line as "comm".
perf bench:
- Add new 'uprobe' benchmark to measure the overhead of uprobes with/without
BPF programs attached to it.
- breakpoints are not available on power9, skip that test.
perf stat:
- Add #num_cpus_online literal to be used in 'perf stat' metrics, and add this extra
'perf test' check that exemplifies its purpose:
TEST_ASSERT_VAL("#num_cpus_online",
expr__parse(&num_cpus_online, ctx, "#num_cpus_online") == 0);
TEST_ASSERT_VAL("#num_cpus", expr__parse(&num_cpus, ctx, "#num_cpus") == 0);
TEST_ASSERT_VAL("#num_cpus >= #num_cpus_online", num_cpus >= num_cpus_online);
Miscellaneous:
- Improve tool startup time by lazily reading PMU, JSON, sysfs data.
- Improve error reporting in the parsing of events, passing YYLTYPE to error routines,
so that the output can show were the parsing error was found.
- Add 'perf test' entries to check the parsing of events improvements.
- Fix various leak for things detected by -fsanitize=address, mostly things that would
be freed at tool exit, including:
- Free evsel->filter on the destructor.
- Allow tools to register a thread->priv destructor and use it in 'perf trace'.
- Free evsel->priv in 'perf trace'.
- Free string returned by synthesize_perf_probe_point() when the caller fails
to do all it needs.
- Adjust various compiler options to not consider errors some warnings when
building with broken headers found in things like python, flex, bison, as we
otherwise build with -Werror. Some for gcc, some for clang, some for some
specific version of those, some for some specific version of flex or bison, or
some specific combination of these components, bah.
- Allow customization of clang options for BPF target, this helps building on
gentoo where there are other oddities where BPF targets gets passed some compiler
options intended for the native build, so building with WERROR=0 helps while
these oddities are fixed.
- Dont pass ERR_PTR() values to perf_session__delete() in 'perf top' and 'perf lock',
fixing some segfaults when handling some odd failures.
- Add LTO build option.
- Fix format of unordered lists in the perf docs (tools/perf/Documentation).
- Overhaul the bison files, using constructs such as YYNOMEM.
- Remove unused tokens from the bison .y files.
- Add more comments to various structs.
- A few LoongArch enablement patches.
Vendor events (JSON):
- Add JSON metrics for Yitian 710 DDR (aarch64). Things like:
EventName, BriefDescription
visible_window_limit_reached_rd, "At least one entry in read queue reaches the visible window limit.",
visible_window_limit_reached_wr, "At least one entry in write queue reaches the visible window limit.",
op_is_dqsosc_mpc , "A DQS Oscillator MPC command to DRAM.",
op_is_dqsosc_mrr , "A DQS Oscillator MRR command to DRAM.",
op_is_tcr_mrr , "A Temperature Compensated Refresh(TCR) MRR command to DRAM.",
- Add AmpereOne metrics (aarch64).
- Update N2 and V2 metrics (aarch64) and events using Arm telemetry repo.
- Update scale units and descriptions of common topdown metrics on aarch64. Things like:
- "MetricExpr": "stall_slot_frontend / (#slots * cpu_cycles)",
- "BriefDescription": "Frontend bound L1 topdown metric",
+ "MetricExpr": "100 * (stall_slot_frontend / (#slots * cpu_cycles))",
+ "BriefDescription": "This metric is the percentage of total slots that were stalled due to resource constraints in the frontend of the processor.",
- Update events for intel: meteorlake to 1.04, sapphirerapids to 1.15, Icelake+ metric constraints.
- Update files for the power10 platform.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
-----BEGIN PGP SIGNATURE-----
iHUEABYKAB0WIQR2GiIUctdOfX2qHhGyPKLppCJ+JwUCZPfJZgAKCRCyPKLppCJ+
J1/eAP9lgtavD0V75wy1p5zyotkceOmPTkk1DYFVx2Euhxa/lAD/YW/JvuVSo0Gr
HqJP52XaV0tF8gG+YxL+Lay/Ke0P5AQ=
=d12c
-----END PGP SIGNATURE-----
Merge tag 'perf-tools-for-v6.6-1-2023-09-05' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools
Pull perf tools updates from Arnaldo Carvalho de Melo:
"perf tools maintainership:
- Add git information for perf-tools and perf-tools-next trees and
branches to the MAINTAINERS file. That is where development now
takes place and myself and Namhyung Kim have write access, more
people to come as we emulate other maintainer groups.
perf record:
- Record kernel data maps when 'perf record --data' is used, so that
global variables can be resolved and used in tools that do data
profiling.
perf trace:
- Remove the old, experimental support for BPF events in which a .c
file was passed as an event: "perf trace -e hello.c" to then get
compiled and loaded.
The only known usage for that, that shipped with the kernel as an
example for such events, augmented the raw_syscalls tracepoints and
was converted to a libbpf skeleton, reusing all the user space
components and the BPF code connected to the syscalls.
In the end just the way to glue the BPF part and the user space
type beautifiers changed, now being performed by libbpf skeletons.
The next step is to use BTF to do pretty printing of all syscall
types, as discussed with Alan Maguire and others.
Now, on a perf built with BUILD_BPF_SKEL=1 we get most if not all
path/filenames/strings, some of the networking data structures,
perf_event_attr, etc, i.e. systemwide tracing of nanosleep calls
and perf_event_open syscalls while 'perf stat' runs 'sleep' for 5
seconds:
# perf trace -a -e *nanosleep,perf* perf stat -e cycles,instructions sleep 5
0.000 ( 9.034 ms): perf/327641 perf_event_open(attr_uptr: { type: 0 (PERF_TYPE_HARDWARE), size: 136, config: 0 (PERF_COUNT_HW_CPU_CYCLES), sample_type: IDENTIFIER, read_format: TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING, disabled: 1, inherit: 1, enable_on_exec: 1, exclude_guest: 1 }, pid: 327642 (perf), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 3
9.039 ( 0.006 ms): perf/327641 perf_event_open(attr_uptr: { type: 0 (PERF_TYPE_HARDWARE), size: 136, config: 0x1 (PERF_COUNT_HW_INSTRUCTIONS), sample_type: IDENTIFIER, read_format: TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING, disabled: 1, inherit: 1, enable_on_exec: 1, exclude_guest: 1 }, pid: 327642 (perf-exec), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 4
? ( ): gpm/991 ... [continued]: clock_nanosleep()) = 0
10.133 ( ): sleep/327642 clock_nanosleep(rqtp: { .tv_sec: 5, .tv_nsec: 0 }, rmtp: 0x7ffd36f83ed0) ...
? ( ): pool-gsd-smart/3051 ... [continued]: clock_nanosleep()) = 0
30.276 ( ): gpm/991 clock_nanosleep(rqtp: { .tv_sec: 2, .tv_nsec: 0 }, rmtp: 0x7ffcc6f73710) ...
223.215 (1000.430 ms): pool-gsd-smart/3051 clock_nanosleep(rqtp: { .tv_sec: 1, .tv_nsec: 0 }, rmtp: 0x7f6e7fffec90) = 0
30.276 (2000.394 ms): gpm/991 ... [continued]: clock_nanosleep()) = 0
1230.814 ( ): pool-gsd-smart/3051 clock_nanosleep(rqtp: { .tv_sec: 1, .tv_nsec: 0 }, rmtp: 0x7f6e7fffec90) ...
1230.814 (1000.404 ms): pool-gsd-smart/3051 ... [continued]: clock_nanosleep()) = 0
2030.886 ( ): gpm/991 clock_nanosleep(rqtp: { .tv_sec: 2, .tv_nsec: 0 }, rmtp: 0x7ffcc6f73710) ...
2237.709 (1000.153 ms): pool-gsd-smart/3051 clock_nanosleep(rqtp: { .tv_sec: 1, .tv_nsec: 0 }, rmtp: 0x7f6e7fffec90) = 0
? ( ): crond/1172 ... [continued]: clock_nanosleep()) = 0
3242.699 ( ): pool-gsd-smart/3051 clock_nanosleep(rqtp: { .tv_sec: 1, .tv_nsec: 0 }, rmtp: 0x7f6e7fffec90) ...
2030.886 (2000.385 ms): gpm/991 ... [continued]: clock_nanosleep()) = 0
3728.078 ( ): crond/1172 clock_nanosleep(rqtp: { .tv_sec: 60, .tv_nsec: 0 }, rmtp: 0x7ffe0971dcf0) ...
3242.699 (1000.158 ms): pool-gsd-smart/3051 ... [continued]: clock_nanosleep()) = 0
4031.409 ( ): gpm/991 clock_nanosleep(rqtp: { .tv_sec: 2, .tv_nsec: 0 }, rmtp: 0x7ffcc6f73710) ...
10.133 (5000.375 ms): sleep/327642 ... [continued]: clock_nanosleep()) = 0
Performance counter stats for 'sleep 5':
2,617,347 cycles
1,855,997 instructions # 0.71 insn per cycle
5.002282128 seconds time elapsed
0.000855000 seconds user
0.000852000 seconds sys
perf annotate:
- Building with binutils' libopcode now is opt-in (BUILD_NONDISTRO=1)
for licensing reasons, and we missed a build test on
tools/perf/tests makefile.
Since we now default to NDEBUG=1, we ended up segfaulting when
building with BUILD_NONDISTRO=1 because a needed initialization
routine was being "error checked" via an assert.
Fix it by explicitly checking the result and aborting instead if it
fails.
We better back propagate the error, but at least 'perf annotate' on
samples collected for a BPF program is back working when perf is
built with BUILD_NONDISTRO=1.
perf report/top:
- Add back TUI hierarchy mode header, that is seen when using 'perf
report/top --hierarchy'.
- Fix the number of entries for 'e' key in the TUI that was
preventing navigation of lines when expanding an entry.
perf report/script:
- Support cross platform register handling, allowing a perf.data file
collected on one architecture to have registers sampled correctly
displayed when analysis tools such as 'perf report' and 'perf
script' are used on a different architecture.
- Fix handling of event attributes in pipe mode, i.e. when one uses:
perf record -o - | perf report -i -
When no perf.data files are used.
- Handle files generated via pipe mode with a version of perf and
then read also via pipe mode with a different version of perf,
where the event attr record may have changed, use the record size
field to properly support this version mismatch.
perf probe:
- Accessing global variables from uprobes isn't supported, make the
error message state that instead of stating that some minimal
kernel version is needed to have that feature. This seems just a
tool limitation, the kernel probably has all that is needed.
perf tests:
- Fix a reference count related leak in the dlfilter v0 API where the
result of a thread__find_symbol_fb() is not matched with an
addr_location__exit() to drop the reference counts of the resolved
components (machine, thread, map, symbol, etc). Add a dlfilter test
to make sure that doesn't regresses.
- Lots of fixes for the 'perf test' written in shell script related
to problems found with the shellcheck utility.
- Fixes for 'perf test' shell scripts testing features enabled when
perf is built with BUILD_BPF_SKEL=1, such as 'perf stat' bpf
counters.
- Add perf record sample filtering test, things like the following
example, that gets implemented as a BPF filter attached to the
event:
# perf record -e task-clock -c 10000 --filter 'ip < 0xffffffff00000000'
- Improve the way the task_analyzer test checks if libtraceevent is
linked, using 'perf version --build-options' instead of the more
expensinve 'perf record -e "sched:sched_switch"'.
- Add support for riscv in the mmap-basic test. (This went as well
via the RiscV tree, same contents).
libperf:
- Implement riscv mmap support (This went as well via the RiscV tree,
same contents).
perf script:
- New tool that converts perf.data files to the firefox profiler
format so that one can use the visualizer at
https://profiler.firefox.com/. Done by Anup Sharma as part of this
year's Google Summer of Code.
One can generate the output and upload it to the web interface but
Anup also automated everything:
perf script gecko -F 99 -a sleep 60
- Support syscall name parsing on arm64.
- Print "cgroup" field on the same line as "comm".
perf bench:
- Add new 'uprobe' benchmark to measure the overhead of uprobes
with/without BPF programs attached to it.
- breakpoints are not available on power9, skip that test.
perf stat:
- Add #num_cpus_online literal to be used in 'perf stat' metrics, and
add this extra 'perf test' check that exemplifies its purpose:
TEST_ASSERT_VAL("#num_cpus_online",
expr__parse(&num_cpus_online, ctx, "#num_cpus_online") == 0);
TEST_ASSERT_VAL("#num_cpus", expr__parse(&num_cpus, ctx, "#num_cpus") == 0);
TEST_ASSERT_VAL("#num_cpus >= #num_cpus_online", num_cpus >= num_cpus_online);
Miscellaneous:
- Improve tool startup time by lazily reading PMU, JSON, sysfs data.
- Improve error reporting in the parsing of events, passing YYLTYPE
to error routines, so that the output can show were the parsing
error was found.
- Add 'perf test' entries to check the parsing of events
improvements.
- Fix various leak for things detected by -fsanitize=address, mostly
things that would be freed at tool exit, including:
- Free evsel->filter on the destructor.
- Allow tools to register a thread->priv destructor and use it in
'perf trace'.
- Free evsel->priv in 'perf trace'.
- Free string returned by synthesize_perf_probe_point() when the
caller fails to do all it needs.
- Adjust various compiler options to not consider errors some
warnings when building with broken headers found in things like
python, flex, bison, as we otherwise build with -Werror. Some for
gcc, some for clang, some for some specific version of those, some
for some specific version of flex or bison, or some specific
combination of these components, bah.
- Allow customization of clang options for BPF target, this helps
building on gentoo where there are other oddities where BPF targets
gets passed some compiler options intended for the native build, so
building with WERROR=0 helps while these oddities are fixed.
- Dont pass ERR_PTR() values to perf_session__delete() in 'perf top'
and 'perf lock', fixing some segfaults when handling some odd
failures.
- Add LTO build option.
- Fix format of unordered lists in the perf docs
(tools/perf/Documentation)
- Overhaul the bison files, using constructs such as YYNOMEM.
- Remove unused tokens from the bison .y files.
- Add more comments to various structs.
- A few LoongArch enablement patches.
Vendor events (JSON):
- Add JSON metrics for Yitian 710 DDR (aarch64). Things like:
EventName, BriefDescription
visible_window_limit_reached_rd, "At least one entry in read queue reaches the visible window limit.",
visible_window_limit_reached_wr, "At least one entry in write queue reaches the visible window limit.",
op_is_dqsosc_mpc , "A DQS Oscillator MPC command to DRAM.",
op_is_dqsosc_mrr , "A DQS Oscillator MRR command to DRAM.",
op_is_tcr_mrr , "A Temperature Compensated Refresh(TCR) MRR command to DRAM.",
- Add AmpereOne metrics (aarch64).
- Update N2 and V2 metrics (aarch64) and events using Arm telemetry
repo.
- Update scale units and descriptions of common topdown metrics on
aarch64. Things like:
- "MetricExpr": "stall_slot_frontend / (#slots * cpu_cycles)",
- "BriefDescription": "Frontend bound L1 topdown metric",
+ "MetricExpr": "100 * (stall_slot_frontend / (#slots * cpu_cycles))",
+ "BriefDescription": "This metric is the percentage of total slots that were stalled due to resource constraints in the frontend of the processor.",
- Update events for intel: meteorlake to 1.04, sapphirerapids to
1.15, Icelake+ metric constraints.
- Update files for the power10 platform"
* tag 'perf-tools-for-v6.6-1-2023-09-05' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (217 commits)
perf parse-events: Fix driver config term
perf parse-events: Fixes relating to no_value terms
perf parse-events: Fix propagation of term's no_value when cloning
perf parse-events: Name the two term enums
perf list: Don't print Unit for "default_core"
perf vendor events intel: Fix modifier in tma_info_system_mem_parallel_reads for skylake
perf dlfilter: Avoid leak in v0 API test use of resolve_address()
perf metric: Add #num_cpus_online literal
perf pmu: Remove str from perf_pmu_alias
perf parse-events: Make common term list to strbuf helper
perf parse-events: Minor help message improvements
perf pmu: Avoid uninitialized use of alias->str
perf jevents: Use "default_core" for events with no Unit
perf test stat_bpf_counters_cgrp: Enhance perf stat cgroup BPF counter test
perf test shell stat_bpf_counters: Fix test on Intel
perf test shell record_bpf_filter: Skip 6.2 kernel
libperf: Get rid of attr.id field
perf tools: Convert to perf_record_header_attr_id()
libperf: Add perf_record_header_attr_id()
perf tools: Handle old data in PERF_RECORD_ATTR
...
|