Use total latency info in the SPE counter packet as sample weight so
that we can see it in local_weight and (global) weight sort keys.
Maybe we can use PERF_SAMPLE_WEIGHT_STRUCT to support ins_lat as well
but I'm not sure which latency it matches. So just adding total latency
first.
Reviewed-by: Leo Yan <leo.yan@linaro.org>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20211201220855.1260688-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The output of 'perf bench' gets buffered when I pipe it to a file or to
tee, in such a way that I can see it only at the end.
E.g.
$ perf bench internals synthesize -t
< output comes out fine after each test run >
$ perf bench internals synthesize -t | tee file.txt
< output comes out only at the end of all tests >
This patch resolves this issue for 'bench' and 'test' subcommands.
See, also:
$ perf bench mem all | tee file.txt
$ perf bench sched all | tee file.txt
$ perf bench internals all -t | tee file.txt
$ perf bench internals all | tee file.txt
Committer testing:
It really gets staggered, i.e. outputs in bursts, when the buffer fills
up and has to be drained to make up space for more output.
Suggested-by: Riccardo Mancini <rickyman7@gmail.com>
Signed-off-by: Sohaib Mohamed <sohaib.amhmd@gmail.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Fabian Hemmer <copy@copy.sh>
Cc: Ian Rogers <irogers@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20211119061409.78004-1-sohaib.amhmd@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The function trace_event__tp_format_id may return ERR_PTR(-ENOMEM). Use
IS_ERR_OR_NULL to check tp_format.
Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Song Liu <song@kernel.org>
Link: http://lore.kernel.org/lkml/20211211053856.19827-1-linmq006@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
An error timestamp shows the last known timestamp for the queue, but this
is not updated on the error path. Fix by setting it.
Fixes: f4aa081949 ("perf tools: Add Intel PT decoder")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: stable@vger.kernel.org # v5.15+
Link: https://lore.kernel.org/r/20211210162303.2288710-8-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
FUP packets contain IP information, which makes them also an 'instruction'
event in 'hop' mode i.e. the itrace 'q' option. That wasn't happening, so
restructure the logic so that FUP events are added along with appropriate
'instruction' and 'branch' events.
Fixes: 7c1b16ba0e ("perf intel-pt: Add support for decoding FUP/TIP only")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: stable@vger.kernel.org # v5.15+
Link: https://lore.kernel.org/r/20211210162303.2288710-7-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Code after label 'next:' in intel_pt_walk_trace() assumes 'err' is zero,
but it may not be, if arrived at via a 'goto'. Ensure it is zero.
Fixes: 7c1b16ba0e ("perf intel-pt: Add support for decoding FUP/TIP only")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: stable@vger.kernel.org # v5.15+
Link: https://lore.kernel.org/r/20211210162303.2288710-6-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
An overflow (OVF packet) is treated as an error because it represents a
loss of trace data, but there is no loss of synchronization, so the packet
state should be INTEL_PT_STATE_IN_SYNC not INTEL_PT_STATE_ERR_RESYNC.
To support that, some additional variables must be reset, and the FUP
packet that may follow OVF is treated as an FUP event.
Fixes: f4aa081949 ("perf tools: Add Intel PT decoder")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: stable@vger.kernel.org # v5.15+
Link: https://lore.kernel.org/r/20211210162303.2288710-5-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
intel_pt_fup_event() assumes it can overwrite the state type if there has
been an FUP event, but this is an unnecessary and unexpected constraint on
callers.
Fix by touching only the state type flags that are affected by an FUP
event.
Fixes: a472e65fc4 ("perf intel-pt: Add decoder support for ptwrite and power event packets")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: stable@vger.kernel.org # v5.15+
Link: https://lore.kernel.org/r/20211210162303.2288710-4-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
When syncing, it may be that branch packet generation is not enabled at
that point, in which case there will not immediately be a control-flow
packet, so some packets before a control flow packet turns up, get
ignored. However, the decoder is in sync as soon as a PSB is found, so
the state should be set accordingly.
Fixes: f4aa081949 ("perf tools: Add Intel PT decoder")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: stable@vger.kernel.org # v5.15+
Link: https://lore.kernel.org/r/20211210162303.2288710-3-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Packet generation enable (PGE) refers to whether control flow (COFI)
packets are being produced.
PGE may be false even when branch-tracing is enabled, due to being
out-of-context, or outside a filter address range. Fix some missing PGE
usage.
Fixes: 7c1b16ba0e ("perf intel-pt: Add support for decoding FUP/TIP only")
Fixes: 839598176b ("perf intel-pt: Allow decoding with branch tracing disabled")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: stable@vger.kernel.org # v5.15+
Link: https://lore.kernel.org/r/20211210162303.2288710-2-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The size of the cache of register values is arch-dependant
(PERF_REGS_MAX). This has the potential of causing an out-of-bounds
access in the function "perf_reg_value" if the local architecture
contains less registers than the one the perf.data file was recorded on.
Since the maximum number of registers is bound by the bitmask "u64
cache_mask", and the size of the cache when running under x86 systems is
64 already, fix the size to 64 and add a range-check to the function
"perf_reg_value" to prevent out-of-bounds access.
Reported-by: Alexandre Truong <alexandre.truong@arm.com>
Reviewed-by: Kajol Jain <kjain@linux.ibm.com>
Signed-off-by: German Gomez <german.gomez@arm.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-csky@vger.kernel.org
Cc: linux-riscv@lists.infradead.org
Link: https://lore.kernel.org/r/20211201123334.679131-2-german.gomez@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Correct indentation to 4 spaces, same as the other JSON files.
Reviewed-by: John Garry <john.garry@huawei.com>
Signed-off-by: Andrew Kilroy <andrew.kilroy@arm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Link: http://lore.kernel.org/lkml/20211203123525.31127-2-andrew.kilroy@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
In previous patch, we have supported the syntax which enables
the event on a specified pmu, such as:
cpu_core/<event>/
cpu_atom/<event>/
While this syntax is not very easy for applying on a set of
events or applying on a group. In following example, we have to
explicitly assign the pmu prefix.
# ./perf stat -e '{cpu_core/cycles/,cpu_core/instructions/}' -- sleep 1
Performance counter stats for 'sleep 1':
1,158,545 cpu_core/cycles/
1,003,113 cpu_core/instructions/
1.002428712 seconds time elapsed
A much easier way is:
# ./perf stat --cputype core -e '{cycles,instructions}' -- sleep 1
Performance counter stats for 'sleep 1':
1,101,071 cpu_core/cycles/
939,892 cpu_core/instructions/
1.002363142 seconds time elapsed
For this example, the '--cputype' enables the events from specified
pmu (cpu_core).
If '--cputype' conflicts with pmu prefix, '--cputype' is ignored.
# ./perf stat --cputype core -e cycles,cpu_atom/instructions/ -a -- sleep 1
Performance counter stats for 'system wide':
21,003,407 cpu_core/cycles/
367,886 cpu_atom/instructions/
1.002203520 seconds time elapsed
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20210909062215.10278-1-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
It's possible to link against libopencsd_c_api without having
libstdc++.so available, only libstdc++.so.6.0.28 (or whatever version is
in use) needs to be available. The same holds true for libopencsd.so.
When -lstdc++ (or -lopencsd) is explicitly passed to the linker however
the .so file must be available.
So wrap adding the dependencies into a check for static linking that
actually requires adding them all. The same construct is already used
for some other tests in the same file to reduce dependencies in the
dynamic linking case.
Fixes: 573cf5c9a1 ("perf build: Add missing -lstdc++ when linking with libopencsd")
Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: Uwe Kleine-König <uwe@kleine-koenig.org>
Cc: Adrian Bunk <bunk@debian.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Branislav Rankov <branislav.rankov@arm.com>
Cc: Diederik de Haas <didi.debian@cknow.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/all/20211203210544.1137935-1-uwe@kleine-koenig.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Currently topdown events must appear after a slots event:
$ perf stat -e '{slots,topdown-fe-bound}' /bin/true
Performance counter stats for '/bin/true':
3,183,090 slots
986,133 topdown-fe-bound
Reversing the events yields:
$ perf stat -e '{topdown-fe-bound,slots}' /bin/true
Error:
The sys_perf_event_open() syscall returned with 22 (Invalid argument) for event (topdown-fe-bound).
For metrics the order of events is determined by iterating over a
hashmap, and so slots isn't guaranteed to be first which can yield this
error.
Change the set_leader in parse-events, called when a group is closed, so
that rather than always making the first event the leader, if the slots
event exists then it is made the leader. It is then moved to the head of
the evlist otherwise it won't be opened in the correct order.
The result is:
$ perf stat -e '{topdown-fe-bound,slots}' /bin/true
Performance counter stats for '/bin/true':
3,274,795 slots
1,001,702 topdown-fe-bound
A problem with this approach is the slots event is identified by name,
names can be overwritten like 'cpu/slots,name=foo/' and this causes the
leader change to fail.
The change also modifies and fixes mixed groups like, with the change:
$ perf stat -e '{instructions,slots,topdown-fe-bound}' -a -- sleep 2
Performance counter stats for 'system wide':
5574985410 slots
971981616 instructions
1348461887 topdown-fe-bound
2.001263120 seconds time elapsed
Without the change:
$ perf stat -e '{instructions,slots,topdown-fe-bound}' -a -- sleep 2
Performance counter stats for 'system wide':
<not counted> instructions
<not counted> slots
<not supported> topdown-fe-bound
2.006247990 seconds time elapsed
Something that may be undesirable here is that the events are reordered
in the output.
Reviewed-by: Kajol Jain <kjain@linux.ibm.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Clarke <pc@us.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Riccardo Mancini <rickyman7@gmail.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Vineet Singh <vineet.singh@intel.com>
Link: http://lore.kernel.org/lkml/20211130174945.247604-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The leader of a group is the first, but allow it to be an arbitrary list
member so that for Intel topdown events slots may always be the group
leader.
Reviewed-by: Kajol Jain <kjain@linux.ibm.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Clarke <pc@us.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Riccardo Mancini <rickyman7@gmail.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Vineet Singh <vineet.singh@intel.com>
Link: http://lore.kernel.org/lkml/20211130174945.247604-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
It is common to use the same counters with and without duration_time.
The ID sharing code treats duration_time as if it were a hardware event
placed in the same group. This causes unnecessary multiplexing such as
in the following example where l3_cache_access isn't shared:
$ perf stat -M l3 -a sleep 1
Performance counter stats for 'system wide':
3,117,007 l3_cache_miss # 199.5 MB/s l3_rd_bw
# 43.6 % l3_hits
# 56.4 % l3_miss (50.00%)
5,526,447 l3_cache_access (50.00%)
5,392,435 l3_cache_access # 5389191.2 access/s l3_access_rate (50.00%)
1,000,601,901 ns duration_time
1.000601901 seconds time elapsed
Fix this by placing duration_time in all groups unless metric
sharing has been disabled on the command line:
$ perf stat -M l3 -a sleep 1
Performance counter stats for 'system wide':
3,597,972 l3_cache_miss # 230.3 MB/s l3_rd_bw
# 48.0 % l3_hits
# 52.0 % l3_miss
6,914,459 l3_cache_access # 6909935.9 access/s l3_access_rate
1,000,654,579 ns duration_time
1.000654579 seconds time elapsed
$ perf stat --metric-no-merge -M l3 -a sleep 1
Performance counter stats for 'system wide':
3,501,834 l3_cache_miss # 53.5 % l3_miss (24.99%)
6,548,173 l3_cache_access (24.99%)
3,417,622 l3_cache_miss # 45.7 % l3_hits (25.04%)
6,294,062 l3_cache_access (25.04%)
5,923,238 l3_cache_access # 5919688.1 access/s l3_access_rate (24.99%)
1,000,599,683 ns duration_time
3,607,486 l3_cache_miss # 230.9 MB/s l3_rd_bw (49.97%)
1.000599683 seconds time elapsed
v2. Doesn't count duration_time in the metric_list_cmp function that
sorts larger metrics first. Without this a metric with duration_time
and an event is sorted the same as a metric with two events,
possibly not allowing the first metric to share with the second.
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Clarke <pc@us.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20211124015226.3317994-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This updates the link to documentation on AMD processors. The new link
points to a page where users can find the Processor Programming
Reference (PPR) documents for the family and model codes corresponding
to processors they are using.
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Ananth Narayan <ananth.narayan@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kim Phillips <kim.phillips@amd.com>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Robert Richter <rrichter@amd.com>
Cc: Santosh Shukla <santosh.shukla@amd.com>
Link: https://lore.kernel.org/r/20211123084613.243792-2-sandipan.das@amd.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
AMD processors have events with event select codes and unit masks larger
than a byte. The core PMU, for example, uses 12-bit event select codes
split between bits 0-7 and 32-35 of the PERF_CTL MSRs as can be seen
from /sys/bus/event_sources/devices/cpu/format/*.
The Processor Programming Reference (PPR) lists the event codes as
unified 12-bit hexadecimal values instead and the split between the bits
is not apparent to someone who is not aware of the layout of the
PERF_CTL MSRs.
8-bit event select codes continue to work as the layout matches that of
the PERF_CTL MSRs i.e. bits 0-7 for event select and 8-15 for unit mask.
This adds more details in the perf man pages about using
/sys/bus/event_sources/devices/*/format/* for determining the correct
raw event encoding scheme.
E.g. the "op_cache_hit_miss.op_cache_hit" event with code 0x28f and
umask 0x03 can be programmed using its symbolic name as:
$ sudo perf --debug perf-event-open stat -e op_cache_hit_miss.op_cache_hit sleep 1
------------------------------------------------------------
perf_event_attr:
type 4
size 128
config 0x20000038f
sample_type IDENTIFIER
read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
disabled 1
inherit 1
enable_on_exec 1
exclude_guest 1
------------------------------------------------------------
[...]
One might use a simple eventsel+umask combination based on what the
current man pages say and incorrectly program the event as:
$ sudo perf --debug perf-event-open stat -e r0328f sleep 1
------------------------------------------------------------
perf_event_attr:
type 4
size 128
config 0x328f
sample_type IDENTIFIER
read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
disabled 1
inherit 1
enable_on_exec 1
exclude_guest 1
------------------------------------------------------------
[...]
When it should have been based on the format from sysfs:
$ cat /sys/bus/event_source/devices/cpu/format/event
config:0-7,32-35
$ sudo perf --debug perf-event-open stat -e r20000038f sleep 1
------------------------------------------------------------
perf_event_attr:
type 4
size 128
config 0x20000038f
sample_type IDENTIFIER
read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
disabled 1
inherit 1
enable_on_exec 1
exclude_guest 1
------------------------------------------------------------
[...]
Reviewed-by: Kajol Jain <kjain@linux.ibm.com>
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Ananth Narayan <ananth.narayan@amd.com>
Cc: Kim Phillips <kim.phillips@amd.com>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Robert Richter <rrichter@amd.com>
Cc: Santosh Shukla <santosh.shukla@amd.com>
Link: https://lore.kernel.org/r/20211123084613.243792-1-sandipan.das@amd.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Move perf_counts_values__scale() from tools/perf/util to tools/lib/perf
so that it can be used with libperf.
Committer notes:
As noted by Jiri, use __s8 instead of s8 on the exported function.
Signed-off-by: Shunsuke Nakamura <nakamura.shun@fujitsu.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20211109085831.3770594-2-nakamura.shun@fujitsu.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The tools build system uses KBUILD_HOSTCFLAGS symbol for obvious purposes.
However this is not set for anything under tools/
As such, host tools apps built have no compiler warnings enabled.
Declare HOSTCFLAGS for perf tools build, and also use that symbol in
declaration of host_c_flags. HOSTCFLAGS comes from EXTRA_WARNINGS, which
is independent of target platform/arch warning flags.
Suggested-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Laura Abbott <labbott@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/1635525041-151876-1-git-send-email-john.garry@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Helps a bit the user figuring out why it is failing:
Before:
$ perf test sigtrap
73: Sigtrap : FAILED!
$ perf test -v sigtrap
73: Sigtrap :
--- start ---
test child forked, pid 3816772
FAILED sys_perf_event_open()
test child finished with -1
---- end ----
Sigtrap: FAILED!
$
After:
$ perf test sigtrap
73: Sigtrap : FAILED!
$ perf test -v sigtrap
73: Sigtrap :
--- start ---
test child forked, pid 3816772
FAILED sys_perf_event_open(): Permission denied
test child finished with -1
---- end ----
Sigtrap: FAILED!
$
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Fabian Hemmer <copy@copy.sh>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Marco Elver <elver@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: kasan-dev@googlegroups.com
Link: http://lore.kernel.org/lkml/YZOpSVOCXe0zWeRs@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Add basic stress test for sigtrap handling as a perf tool built-in test.
This allows sanity checking the basic sigtrap functionality from within
the perf tool.
Committer notes:
Reported that !root was getting -EPERM, applied a fixup from Marco to
set .exclude_{hv,kernel} that made it work.
Signed-off-by: Marco Elver <elver@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Fabian Hemmer <copy@copy.sh>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: kasan-dev@googlegroups.com
Link: http://lore.kernel.org/lkml/20211115112822.4077224-1-elver@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
When building bpf_skel with clang-10, typedef causes confusions like:
libbpf: map 'prev_readings': unexpected def kind var.
Fix this by removing the typedef.
Fixes: 7fac83aaf2 ("perf stat: Introduce 'bperf' to share hardware PMCs with BPF")
Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Song Liu <songliubraving@fb.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lore.kernel.org/lkml/BEF5C312-4331-4A60-AEC0-AD7617CB2BC4@fb.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Arnaldo reported that building all his containers with BUILD_BPF_SKEL=1
to then make this the default he found problems in some distros where
the system linux/bpf.h file was being used and lacked this:
util/bpf_skel/bperf_leader.bpf.c:13:20: error: use of undeclared identifier 'BPF_F_PRESERVE_ELEMS'
__uint(map_flags, BPF_F_PRESERVE_ELEMS);
So use instead the vmlinux.h file generated by bpftool from BTF info.
This fixed these as well, getting the build back working on debian:11,
debian:experimental and ubuntu:21.10:
In file included from In file included from util/bpf_skel/bperf_leader.bpf.cutil/bpf_skel/bpf_prog_profiler.bpf.c::33:
:
In file included from In file included from /usr/include/linux/bpf.h/usr/include/linux/bpf.h::1111:
:
/usr/include/linux/types.h/usr/include/linux/types.h::55::1010:: In file included from util/bpf_skel/bperf_follower.bpf.c:3fatal errorfatal error:
: : In file included from /usr/include/linux/bpf.h:'asm/types.h' file not found11'asm/types.h' file not found:
/usr/include/linux/types.h:5:10: fatal error: 'asm/types.h' file not found
#include <asm/types.h>#include <asm/types.h>
^~~~~~~~~~~~~ ^~~~~~~~~~~~~
#include <asm/types.h>
^~~~~~~~~~~~~
1 error generated.
Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Song Liu <song@kernel.org>
Tested-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lore.kernel.org/lkml/CF175681-8101-43D1-ABDB-449E644BE986@fb.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
These leaks were found with leak sanitizer running "perf pipe recording
and injection test".
In pipe mode feat_fd may hold onto an events struct that needs freeing.
When string features are processed they may overwrite an already created
string, so free this before the overwrite.
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20211118201730.2302927-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Otherwise load counting is an average. Without this change
duration_time in test_memory_bandwidth will alter its value if an
earlier test contains duration_time.
This patch fixes an issue that's introduced in the proposed patch:
https://lore.kernel.org/lkml/20211124015226.3317994-1-irogers@google.com/
in perf test "Parse and process metrics".
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Clarke <pc@us.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20211128085810.4027314-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Some platforms do not have CPU die support, for example s390.
Commit
Cc: Ian Rogers <irogers@google.com>
Fixes: fdf1e29b61 ("perf expr: Add metric literals for topology.")
fails on s390:
# perf test -Fv 7
...
# FAILED tests/expr.c:173 #num_dies >= #num_packages
---- end ----
Simple expression parser: FAILED!
#
Investigating this issue leads to these functions:
build_cpu_topology()
+--> has_die_topology(void)
{
struct utsname uts;
if (uname(&uts) < 0)
return false;
if (strncmp(uts.machine, "x86_64", 6))
return false;
....
}
which always returns false on s390. The caller build_cpu_topology()
checks has_die_topology() return value. On false the the struct
cpu_topology::die_cpu_list is not contructed and has zero entries. This
leads to the failing comparison: #num_dies >= #num_packages. s390 of
course has a positive number of packages.
Fix this and check if the function build_cpu_topology() did build up
a die_cpus_list. The number of entries in this list should be larger
than 0. If the number of list element is zero, the die_cpus_list has
not been created and the check in function test__expr():
TEST_ASSERT_VAL("#num_dies >= #num_packages", \
num_dies >= num_packages)
always fails.
Output after:
# perf test -Fv 7
7: Simple expression parser :
--- start ---
division by zero
syntax error
---- end ----
Simple expression parser: Ok
#
Fixes: fdf1e29b61 ("perf expr: Add metric literals for topology.")
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Link: http://lore.kernel.org/lkml/20211129112339.3003036-1-tmricht@linux.ibm.com
[ Added comment in the added 'if (num_dies)' line about architectures not having die topology ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Since 66dfdff03d ("perf tools: Add Python 3 support") we don't use
the tools/build/feature/test-libpython-version.c version in any Makefile
feature check:
$ find tools/ -type f | xargs grep feature-libpython-version
$
The only place where this was used was removed in 66dfdff03d:
- ifneq ($(feature-libpython-version), 1)
- $(warning Python 3 is not yet supported; please set)
- $(warning PYTHON and/or PYTHON_CONFIG appropriately.)
- $(warning If you also have Python 2 installed, then)
- $(warning try something like:)
- $(warning $(and ,))
- $(warning $(and ,) make PYTHON=python2)
- $(warning $(and ,))
- $(warning Otherwise, disable Python support entirely:)
- $(warning $(and ,))
- $(warning $(and ,) make NO_LIBPYTHON=1)
- $(warning $(and ,))
- $(error $(and ,))
- else
- LDFLAGS += $(PYTHON_EMBED_LDFLAGS)
- EXTLIBS += $(PYTHON_EMBED_LIBADD)
- LANG_BINDINGS += $(obj-perf)python/perf.so
- $(call detected,CONFIG_LIBPYTHON)
- endif
And nowadays we either build with PYTHON=python3 or just install the
python3 devel packages and perf will build against it.
But the leftover feature-libpython-version check made the fast path
feature detection to break in all cases except when python2 devel files
were installed:
$ rpm -qa | grep python.*devel
python3-devel-3.9.7-1.fc34.x86_64
$ rm -rf /tmp/build/perf ; mkdir -p /tmp/build/perf ;
$ make -C tools/perf O=/tmp/build/perf install-bin
make: Entering directory '/var/home/acme/git/perf/tools/perf'
BUILD: Doing 'make -j32' parallel build
HOSTCC /tmp/build/perf/fixdep.o
<SNIP>
$ cat /tmp/build/perf/feature/test-all.make.output
In file included from test-all.c:18:
test-libpython-version.c:5:10: error: #error
5 | #error
| ^~~~~
$ ldd ~/bin/perf | grep python
libpython3.9.so.1.0 => /lib64/libpython3.9.so.1.0 (0x00007fda6dbcf000)
$
As python3 is the norm these days, fix this by just removing the unused
feature-libpython-version feature check, making the test-all fast path
to work with the common case.
With this:
$ rm -rf /tmp/build/perf ; mkdir -p /tmp/build/perf ;
$ make -C tools/perf O=/tmp/build/perf install-bin |& head
make: Entering directory '/var/home/acme/git/perf/tools/perf'
BUILD: Doing 'make -j32' parallel build
HOSTCC /tmp/build/perf/fixdep.o
HOSTLD /tmp/build/perf/fixdep-in.o
LINK /tmp/build/perf/fixdep
Auto-detecting system features:
... dwarf: [ on ]
... dwarf_getlocations: [ on ]
... glibc: [ on ]
$ ldd ~/bin/perf | grep python
libpython3.9.so.1.0 => /lib64/libpython3.9.so.1.0 (0x00007f58800b0000)
$ cat /tmp/build/perf/feature/test-all.make.output
$
Reviewed-by: James Clark <james.clark@arm.com>
Fixes: 66dfdff03d ("perf tools: Add Python 3 support")
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jaroslav Škarvada <jskarvad@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/YaYmeeC6CS2b8OSz@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
sysfs__read_int() returns 0 on success, and so the fast read path was
always failing.
Fixes: bb629484d9 ("perf tools: Simplify checking if SMT is active.")
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Clarke <pc@us.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20211124001231.3277836-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The space allowed for new attributes can be too small if existing header
information is large. That can happen, for example, if there are very
many CPUs, due to having an event ID per CPU per event being stored in the
header information.
Fix by adding the existing header.data_offset. Also increase the extra
space allowed to 8KiB and align to a 4KiB boundary for neatness.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lore.kernel.org/lkml/20211125071457.2066863-1-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This: This reverts commit 92723ea0f1.
# perf test 91
91: perf stat --bpf-counters test :RRRRRRRRRRRRR FAILED!
# perf test 91
91: perf stat --bpf-counters test :RRRRRRRRRRRRR FAILED!
# perf test 91
91: perf stat --bpf-counters test :RRRRRRRRRRRR FAILED!
# perf test 91
91: perf stat --bpf-counters test :RRRRRRRRRRRRRRRRRR Ok
# perf test 91
91: perf stat --bpf-counters test :RRRRRRRRR FAILED!
# perf test 91
91: perf stat --bpf-counters test :RRRRRRRRRRR Ok
# perf test 91
91: perf stat --bpf-counters test :RRRRRRRRRRRRRRR Ok
yep, it seems the perf bench is broken so the counts won't correlated if
I revert this one:
92723ea0f1 perf bench: Fix two memory leaks detected with ASan
it works for me again.. it seems to break -t option
[root@dell-r440-01 perf]# ./perf bench sched messaging -g 1 -l 100 -t
# Running 'sched/messaging' benchmark:
RRRperf: CLIENT: ready write: Bad file descriptor
Rperf: SENDER: write: Bad file descriptor
Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Sohaib Mohamed <sohaib.amhmd@gmail.com>
Cc: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/lkml/YZev7KClb%2Fud43Lc@krava/
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
unit may have a strdup pointer or be to a literal, consequently memory
assocciated with it isn't freed. Change it so the unit is always strdup
and so the memory can be safely freed.
Fix related issue in perf_event__process_event_update() for name and
own_cpus. Leaks were spotted by leak sanitizer.
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20211118084749.2191447-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
perf_tip() may allocate memory or use a literal, this means memory
wasn't freed if allocated. Change the API so that literals aren't used.
At the same time add missing frees for system_path. These issues were
spotted using leak sanitizer.
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20211118073804.2149974-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
perf_hpp__column_unregister() removes an entry from a list but doesn't
free the memory causing a memory leak spotted by leak sanitizer.
Add the free while at the same time reducing the scope of the function
to static.
Signed-off-by: Ian Rogers <irogers@google.com>
Reviewed-by: Kajol Jain <kjain@linux.ibm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20211118071247.2140392-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
'perf inject' is currently not working for Arm SPE. When you try to run
'perf inject' and 'perf report' with a perf.data file that contains SPE
traces, the tool reports a "Bad address" error:
# ./perf record -e arm_spe_0/ts_enable=1,store_filter=1,branch_filter=1,load_filter=1/ -a -- sleep 1
# ./perf inject -i perf.data -o perf.inject.data --itrace
# ./perf report -i perf.inject.data --stdio
0x42c00 [0x8]: failed to process type: 9 [Bad address]
Error:
failed to process sample
As far as I know, the issue was first spotted in [1], but 'perf inject'
was not yet injecting the samples. This patch does something similar to
what cs_etm does for injecting the samples [2], but for SPE.
[1] https://patchwork.kernel.org/project/linux-arm-kernel/cover/20210412091006.468557-1-leo.yan@linaro.org/#24117339
[2] https://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git/tree/tools/perf/util/cs-etm.c?h=perf/core&id=133fe2e617e48ca0948983329f43877064ffda3e#n1196
Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: German Gomez <german.gomez@arm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20211105104130.28186-2-german.gomez@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
ASan reports memory leaks while running:
$ perf bench sched all
Fixes: e27454cc63 ("perf bench: Add sched-messaging.c: Benchmark for scheduler and IPC mechanisms based on hackbench")
Signed-off-by: Sohaib Mohamed <sohaib.amhmd@gmail.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Hitoshi Mitake <h.mitake@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Russel <rusty@rustcorp.com.au>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Pierre Gondois <pierre.gondois@arm.com>
Link: http://lore.kernel.org/lkml/20211110022012.16620-1-sohaib.amhmd@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Commit 10269a2ca2 ("perf test sample-parsing: Add endian test for
struct branch_flags") broke the test case 27 (Sample parsing) on s390 on
linux-next tree:
# perf test -Fv 27
27: Sample parsing
--- start ---
parsing failed for sample_type 0x800
---- end ----
Sample parsing: FAILED!
#
The cause of the failure is a wrong #define BS_EXPECTED_BE statement in
above commit. Correct this define and the test case runs fine.
Output After:
# perf test -Fv 27
27: Sample parsing :
--- start ---
---- end ----
Sample parsing: Ok
#
Fixes: 10269a2ca2 ("perf test sample-parsing: Add endian test for struct branch_flags")
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Tested-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Acked-by: Madhavan Srinivasan <maddy@linux.ibm.com>
CC: Sven Schnelle <svens@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Link: https://lore.kernel.org/r/54077e81-503e-3405-6cb0-6541eb5532cc@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
andle 'p_stage_cyc' (for pipeline stage cycles) sort key with the same
rationale as for the 'weight' and 'local_weight', see the fix in this
series for a full explanation.
Not sure it also needs the local and global variants.
But I couldn't test it actually because I don't have the machine.
Reviewed-by: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20211105225617.151364-3-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Handle 'ins_lat' (for instruction latency) and 'local_ins_lat' sort keys
with the same rationale as for the 'weight' and 'local_weight', see the
previous fix in this series for a full explanation.
But I couldn't test it actually, so only build tested.
Reviewed-by: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20211105225617.151364-2-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Currently, the 'weight' field in the perf sample has latency information
for some instructions like in memory accesses. And perf tool has 'weight'
and 'local_weight' sort keys to display the info.
But it's somewhat confusing what it shows exactly. In my understanding,
'local_weight' shows a weight in a single sample, and (global) 'weight'
shows a sum of the weights in the hist_entry.
For example:
$ perf mem record -t load dd if=/dev/zero of=/dev/null bs=4k count=1M
$ perf report --stdio -n -s +local_weight
...
#
# Overhead Samples Command Shared Object Symbol Local Weight
# ........ ....... ....... ................ ......................... ............
#
21.23% 313 dd [kernel.vmlinux] [k] lockref_get_not_zero 32
12.43% 183 dd [kernel.vmlinux] [k] lockref_get_not_zero 35
11.97% 159 dd [kernel.vmlinux] [k] lockref_get_not_zero 36
10.40% 141 dd [kernel.vmlinux] [k] lockref_put_return 32
7.63% 113 dd [kernel.vmlinux] [k] lockref_get_not_zero 33
6.37% 92 dd [kernel.vmlinux] [k] lockref_get_not_zero 34
6.15% 90 dd [kernel.vmlinux] [k] lockref_put_return 33
...
So let's look at the 'lockref_get_not_zero' symbols. The top entry
shows that 313 samples were captured with 'local_weight' 32, so the
total weight should be 313 x 32 = 10016. But it's not the case:
$ perf report --stdio -n -s +local_weight,weight -S lockref_get_not_zero
...
#
# Overhead Samples Command Shared Object Local Weight Weight
# ........ ....... ....... ................ ............ ......
#
1.36% 4 dd [kernel.vmlinux] 36 144
0.47% 4 dd [kernel.vmlinux] 37 148
0.42% 4 dd [kernel.vmlinux] 32 128
0.40% 4 dd [kernel.vmlinux] 34 136
0.35% 4 dd [kernel.vmlinux] 36 144
0.34% 4 dd [kernel.vmlinux] 35 140
0.30% 4 dd [kernel.vmlinux] 36 144
0.30% 4 dd [kernel.vmlinux] 34 136
0.30% 4 dd [kernel.vmlinux] 32 128
0.30% 4 dd [kernel.vmlinux] 32 128
...
With the 'weight' sort key, it's divided to 4 samples even with the same
info ('comm', 'dso', 'sym' and 'local_weight'). I don't think this is
what we want.
I found this because of the way it aggregates the 'weight' value. Since
it's not a period, we should not add them in the he->stat. Otherwise,
two 32 'weight' entries will create a 64 'weight' entry.
After that, new 32 'weight' samples don't have a matching entry so it'd
create a new entry and make it a 64 'weight' entry again and again.
Later, they will be merged into 128 'weight' entries during the
hists__collapse_resort() with 4 samples, multiple times like above.
Let's keep the weight and display it differently. For 'local_weight',
it can show the weight as is, and for (global) 'weight' it can display
the number multiplied by the number of samples.
With this change, I can see the expected numbers.
$ perf report --stdio -n -s +local_weight,weight -S lockref_get_not_zero
...
#
# Overhead Samples Command Shared Object Local Weight Weight
# ........ ....... ....... ................ ............ .....
#
21.23% 313 dd [kernel.vmlinux] 32 10016
12.43% 183 dd [kernel.vmlinux] 35 6405
11.97% 159 dd [kernel.vmlinux] 36 5724
7.63% 113 dd [kernel.vmlinux] 33 3729
6.37% 92 dd [kernel.vmlinux] 34 3128
4.17% 59 dd [kernel.vmlinux] 37 2183
0.08% 1 dd [kernel.vmlinux] 269 269
0.08% 1 dd [kernel.vmlinux] 38 38
Reviewed-by: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20211105225617.151364-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
As it is being used in tools/perf/arch/arm64/util/arm-spe.c and the
COMPAT_NEED_REALLOCARRAY was only being set when CORESIGHT=1 is set.
Fixes: 56c31cdff7 ("perf arm-spe: Implement find_snapshot callback")
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/all/YZT63mIc7iY01er3@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Fixing these build problems:
tests/wp.c:24:12: error: 'wp_read' defined but not used [-Werror=unused-function]
static int wp_read(int fd, long long *count, int size)
^
tests/wp.c:35:13: error: 'get__perf_event_attr' defined but not used [-Werror=unused-function]
static void get__perf_event_attr(struct perf_event_attr *attr, int wp_type,
^
CC /tmp/build/perf/util/print_binary.o
Fixes: e47c6ecaae ("perf test: Convert watch point tests to test cases.")
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Brendan Higgins <brendanhiggins@google.com>
Cc: Daniel Latypov <dlatypov@google.com>
Cc: David Gow <davidgow@google.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Clarke <pc@us.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sohaib Mohamed <sohaib.amhmd@gmail.com>
Cc: Stephane Eranian <eranian@google.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The tests were passing but without testing and were printing the
following:
$ ./perf test -v 90
90: perf all PMU test :
--- start ---
test child forked, pid 51650
Testing cpu/branch-instructions/
./tests/shell/stat_all_pmu.sh: 10: [:
Performance counter stats for 'true':
137,307 cpu/branch-instructions/
0.001686672 seconds time elapsed
0.001376000 seconds user
0.000000000 seconds sys: unexpected operator
Changing the regexes to a grep works in sh and prints this:
$ ./perf test -v 90
90: perf all PMU test :
--- start ---
test child forked, pid 60186
[...]
Testing tlb_flush.stlb_any
test child finished with 0
---- end ----
perf all PMU test: Ok
Signed-off-by: James Clark <james.clark@arm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: KP Singh <kpsingh@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Yonghong Song <yhs@fb.com>
Cc: bpf@vger.kernel.org
Cc: netdev@vger.kernel.org
Link: https://lore.kernel.org/r/20211028134828.65774-4-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Commit 463538a383 ("perf tests: Fix test 68 zstd compression for
s390") inadvertently removed the -g flag from all platforms rather than
just s390, because the [[ ]] construct fails in sh. Changing to single
brackets restores testing of call graphs and removes the following error
from the output:
$ ./perf test -v 85
85: Zstd perf.data compression/decompression :
--- start ---
test child forked, pid 50643
Collecting compressed record file:
./tests/shell/record+zstd_comp_decomp.sh: 15: [[: not found
Fixes: 463538a383 ("perf tests: Fix test 68 zstd compression for s390")
Signed-off-by: James Clark <james.clark@arm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: KP Singh <kpsingh@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Yonghong Song <yhs@fb.com>
Cc: bpf@vger.kernel.org
Cc: netdev@vger.kernel.org
Link: https://lore.kernel.org/r/20211028134828.65774-3-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
