| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <cgja46br2smmznxs7kbeabs6zgv3b4olfqgh2fdp5mxk2yom4v@w6jjgov6hdi6>
Date: Tue, 3 Feb 2026 12:37:28 -0500
From: Andres Freund <andres@...razel.de>
To: Ian Rogers <irogers@...gle.com>
Cc: Peter Zijlstra <peterz@...radead.org>, Ingo Molnar <mingo@...hat.com>,
Arnaldo Carvalho de Melo <acme@...nel.org>, Namhyung Kim <namhyung@...nel.org>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>, Jiri Olsa <jolsa@...nel.org>,
Adrian Hunter <adrian.hunter@...el.com>, "Dr. David Alan Gilbert" <linux@...blig.org>,
Yang Li <yang.lee@...ux.alibaba.com>, James Clark <james.clark@...aro.org>,
Thomas Falcon <thomas.falcon@...el.com>, Thomas Richter <tmricht@...ux.ibm.com>,
linux-perf-users@...r.kernel.org, linux-kernel@...r.kernel.org, Andi Kleen <ak@...ux.intel.com>,
Dapeng Mi <dapeng1.mi@...ux.intel.com>
Subject: Re: [PATCH v4 07/10] perf tool_pmu: More accurately set the cpus for
tool events
Hi,
On 2025-11-13 10:05:13 -0800, Ian Rogers wrote:
> The user and system time events can record on different CPUs, but for
> all other events a single CPU map of just CPU 0 makes sense. In
> parse-events detect a tool PMU and then pass the perf_event_attr so
> that the tool_pmu can return CPUs specific for the event. This avoids
> a CPU map of all online CPUs being used for events like
> duration_time. Avoiding this avoids the evlist CPUs containing CPUs
> for which duration_time just gives 0. Minimizing the evlist CPUs can
> remove unnecessary sched_setaffinity syscalls that delay metric
> calculations.
I was just testing v6.19-rc* and noticed that
perf stat -C $somecpu sleep 1
segfaults.
I bisected that down to this change (d8d8a0b3603a9a8fa207cf9e4f292e81dc5d1008).
$ git describe
v6.18-rc1-116-gd8d8a0b3603a9
$ gdb --args perf stat -C11 sleep 1
(gdb) r
Starting program: /home/andres/bin/bin/perf stat -C11 sleep 1
[Thread debugging using libthread_db enabled]
Using host libthread_db library "/usr/lib/x86_64-linux-gnu/libthread_db.so.1".
[Detaching after fork from child process 843870]
Performance counter stats for 'CPU(s) 11':
16 context-switches # 16.0 cs/sec cs_per_second
1,001.66 msec cpu-clock
Program received signal SIGSEGV, Segmentation fault.
prepare_metric (config=config@...ry=0x55555603bd80 <stat_config>, mexp=mexp@...ry=0x5555560a40f0, evsel=evsel@...ry=0x555556093e20,
pctx=pctx@...ry=0x5555560a7150, aggr_idx=aggr_idx@...ry=0) at util/stat-shadow.c:85
85 aggr = &ps->aggr[is_tool_time ? tool_aggr_idx : aggr_idx];
(gdb) bt
#0 prepare_metric (config=config@...ry=0x55555603bd80 <stat_config>, mexp=mexp@...ry=0x5555560a40f0, evsel=evsel@...ry=0x555556093e20,
pctx=pctx@...ry=0x5555560a7150, aggr_idx=aggr_idx@...ry=0) at util/stat-shadow.c:85
#1 0x00005555557be0eb in generic_metric (config=<optimized out>, mexp=0x5555560a40f0, evsel=<optimized out>, aggr_idx=<optimized out>, out=0x7fffffff76c0)
at util/stat-shadow.c:146
#2 perf_stat__print_shadow_stats_metricgroup (config=config@...ry=0x55555603bd80 <stat_config>, evsel=<optimized out>, aggr_idx=0,
num=num@...ry=0x7fffffff7604, from=from@...ry=0x0, out=0x7fffffff76c0) at util/stat-shadow.c:307
#3 0x00005555557be4c7 in perf_stat__print_shadow_stats (config=config@...ry=0x55555603bd80 <stat_config>, evsel=evsel@...ry=0x555556093e20,
aggr_idx=aggr_idx@...ry=0, out=out@...ry=0x7fffffff76c0) at util/stat-shadow.c:325
#4 0x00005555557c03a3 in printout (config=<optimized out>, os=0x7fffffff78b0, uval=<optimized out>, run=1001660763, ena=<optimized out>,
noise=<optimized out>, aggr_idx=0) at util/stat-display.c:874
#5 0x00005555557c1424 in print_counter_aggrdata (config=0x55555603bd80 <stat_config>, counter=0x555556093e20, aggr_idx=0, os=<optimized out>)
at util/stat-display.c:1013
#6 0x00005555557c3051 in print_counter (config=<optimized out>, counter=<optimized out>, os=<optimized out>) at util/stat-display.c:1127
#7 print_counter (config=<optimized out>, counter=<optimized out>, os=<optimized out>) at util/stat-display.c:1117
#8 evlist__print_counters (evlist=<optimized out>, config=config@...ry=0x55555603bd80 <stat_config>, _target=_target@...ry=0x5555560412e0 <target>,
ts=ts@...ry=0x0, argc=argc@...ry=2, argv=argv@...ry=0x7fffffffdb20) at util/stat-display.c:1600
#9 0x00005555555d0d27 in print_counters (ts=0x0, argc=2, argv=0x7fffffffdb20) at builtin-stat.c:1070
#10 print_counters (ts=0x0, argc=2, argv=0x7fffffffdb20) at builtin-stat.c:1062
#11 cmd_stat (argc=2, argv=0x7fffffffdb20) at builtin-stat.c:2949
#12 0x000055555562fee2 in run_builtin (p=p@...ry=0x55555602df48 <commands+360>, argc=argc@...ry=4, argv=argv@...ry=0x7fffffffdb20) at perf.c:349
#13 0x00005555556301ce in handle_internal_command (argc=argc@...ry=4, argv=argv@...ry=0x7fffffffdb20) at perf.c:401
#14 0x00005555555a8d33 in run_argv (argcp=<synthetic pointer>, argv=<synthetic pointer>) at perf.c:445
#15 main (argc=<optimized out>, argv=0x7fffffffdb20) at perf.c:553
(gdb) bt full
#0 prepare_metric (config=config@...ry=0x55555603bd80 <stat_config>, mexp=mexp@...ry=0x5555560a40f0, evsel=evsel@...ry=0x555556093e20, pctx=pctx@...ry=0x5555560a7150, aggr_idx=aggr_idx@...ry=0) at util/stat-shadow.c:85
val = <optimized out>
source_count = 0
tool_aggr_idx = 0
is_tool_time = true
ps = 0x0
aggr = <optimized out>
n = <optimized out>
metric_events = <optimized out>
metric_refs = 0x0
i = 1
#1 0x00005555557be0eb in generic_metric (config=<optimized out>, mexp=0x5555560a40f0, evsel=<optimized out>, aggr_idx=<optimized out>, out=0x7fffffff76c0) at util/stat-shadow.c:146
print_metric = 0x5555557c1b70 <print_metric_std>
metric_name = 0x5555560ae550 "CPUs_utilized"
metric_expr = 0x555555ea5bb5 "(software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@...k\\-clock\\,name\\=task\\-clock@) / (duration_time * 1e9)"
metric_threshold = 0x0
metric_unit = 0x555555ea5c4d "1CPUs"
metric_events = 0x5555560ae490
runtime = 0
pctx = 0x5555560a7150
ratio = 15.973479072960373
scale = 1
threshold = 4.9406564584124654e-324
i = <optimized out>
ctxp = 0x7fffffff78b0
thresh = METRIC_THRESHOLD_UNKNOWN
#2 perf_stat__print_shadow_stats_metricgroup (config=config@...ry=0x55555603bd80 <stat_config>, evsel=<optimized out>, aggr_idx=0, num=num@...ry=0x7fffffff7604, from=from@...ry=0x0, out=0x7fffffff76c0) at util/stat-shadow.c:307
me = 0x5555560877d0
mexp = 0x5555560a40f0
ctxp = 0x7fffffff78b0
header_printed = false
name = 0x555555879b28 ""
metric_events = <optimized out>
#3 0x00005555557be4c7 in perf_stat__print_shadow_stats (config=config@...ry=0x55555603bd80 <stat_config>, evsel=evsel@...ry=0x555556093e20, aggr_idx=aggr_idx@...ry=0, out=out@...ry=0x7fffffff76c0) at util/stat-shadow.c:325
print_metric = 0x5555557c1b70 <print_metric_std>
ctxp = 0x7fffffff78b0
num = 1
#4 0x00005555557c03a3 in printout (config=<optimized out>, os=0x7fffffff78b0, uval=<optimized out>, run=1001660763, ena=<optimized out>, noise=<optimized out>, aggr_idx=0) at util/stat-display.c:874
out = {ctx = 0x7fffffff78b0, print_metric = 0x5555557c1b70 <print_metric_std>, new_line = 0x5555557be5a0 <new_line_std>, print_metricgroup_header = 0x5555557bea60 <print_metricgroup_header_std>, force_header = false}
pm = <optimized out>
nl = <optimized out>
pmh = <optimized out>
ok = <optimized out>
counter = 0x555556093e20
#5 0x00005555557c1424 in print_counter_aggrdata (config=0x55555603bd80 <stat_config>, counter=0x555556093e20, aggr_idx=0, os=<optimized out>) at util/stat-display.c:1013
output = 0x7ffff69f24e0 <_IO_2_1_stderr_>
ena = 1001660763
run = <optimized out>
val = <optimized out>
uval = <optimized out>
ps = <optimized out>
aggr = <optimized out>
id = {thread_idx = -1, node = -1, socket = -1, die = -1, cluster = -1, cache_lvl = -1, cache = -1, core = -1, cpu = {cpu = 0}}
avg = <optimized out>
metric_only = false
...
whereas on
$ git describe
v6.18-rc1-115-gd702c0f4af6e0
$ perf stat -C11 sleep 1
Performance counter stats for 'CPU(s) 11':
8 context-switches # 8.0 cs/sec cs_per_second
1,001.48 msec cpu-clock # 1.0 CPUs CPUs_utilized
0 cpu-migrations # 0.0 migrations/sec migrations_per_second
3 page-faults # 3.0 faults/sec page_faults_per_second
277,825 branch-misses # 0.3 % branch_miss_rate (33.11%)
102,546,153 branches # 102.4 M/sec branch_frequency (33.51%)
2,501,242,351 cpu-cycles # 2.5 GHz cycles_frequency (33.55%)
317,348,809 instructions # 0.1 instructions insn_per_cycle (33.55%)
1.001449562 seconds time elapsed
it works without a problem.
Greetings,
Andres Freund
Powered by blists - more mailing lists