Ian Rogers 7b6dd7a923 perf pmu: Assume sysfs events are always the same case ... Perf event names aren't case sensitive. For sysfs events the entire directory of events is read then iterated comparing names in a case insensitive way, most often to see if an event is present. Consider: $ perf stat -e inst_retired.any true The event inst_retired.any may be present in any PMU, so every PMU's sysfs events are loaded and then searched with strcasecmp to see if any match. This event is only present on the cpu PMU as a JSON event so a lot of events were loaded from sysfs unnecessarily just to prove an event didn't exist there. This change avoids loading all the events by assuming sysfs event names are always either lower or uppercase. It uses file exists and only loads the events when the desired event is present. For the example above, the number of openat calls measured by 'perf trace' on a tigerlake laptop goes from 325 down to 255. The reduction will be larger for machines with many PMUs, particularly replicated uncore PMUs. Ensure pmu_aliases_parse() is called before all uses of the aliases list, but remove some "pmu->sysfs_aliases_loaded" tests as they are now part of the function. Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Link: https://lore.kernel.org/r/20240502213507.2339733-7-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>		2024-05-03 17:08:20 -03:00
..
arm-spe-decoder
bpf_skel	Merge remote-tracking branch 'torvalds/master' into perf-tools-next	2024-04-22 13:35:18 -03:00
cs-etm-decoder
hisi-ptt-decoder
include	tools headers: Update the copy of x86's mem{cpy,set}_64.S used in 'perf bench'	2024-01-30 11:31:15 -03:00
intel-pt-decoder	perf intel-pt: Fix unassigned instruction op (discovered by MemorySanitizer)	2024-04-26 22:13:10 -03:00
libunwind
perf-regs-arch	perf parse-regs: Always build perf register functions	2024-02-15 13:48:20 -08:00
scripting-engines	perf cpumap: Use perf_cpu_map__for_each_cpu when possible	2024-03-21 10:41:28 -03:00
addr_location.c
addr_location.h
affinity.c
affinity.h
amd-sample-raw.c
annotate-data.c	perf annotate-data: Check kind of stack variables	2024-05-02 11:06:23 -03:00
annotate-data.h	perf annotate-data: Add hist_entry__annotate_data_tui()	2024-04-12 12:02:06 -03:00
annotate.c	perf annotate-data: Check if 'struct annotation_source' was allocated on 'perf report' TUI	2024-04-26 22:07:21 -03:00
annotate.h	perf annotate: Move 'start' field struct to 'struct annotated_source'	2024-04-08 17:43:20 -03:00
archinsn.h
arm-spe.c
arm-spe.h
arm64-frame-pointer-unwind-support.c
arm64-frame-pointer-unwind-support.h
auxtrace.c	perf cpumap: Clean up use of perf_cpu_map__has_any_cpu_or_is_empty	2024-03-21 10:41:28 -03:00
auxtrace.h
block-info.c
block-info.h
block-range.c
block-range.h
bpf-event.c	perf maps: Get map before returning in maps__find	2024-02-12 12:35:26 -08:00
bpf-event.h	perf env: Avoid recursively taking env->bpf_progs.lock	2024-01-03 17:54:54 -03:00
bpf-filter.c
bpf-filter.h
bpf-filter.l
bpf-filter.y
bpf-prologue.h
bpf-utils.c
bpf-utils.h
bpf_counter.c
bpf_counter.h
bpf_counter_cgroup.c
bpf_ftrace.c
bpf_kwork.c	perf cpumap: Use perf_cpu_map__for_each_cpu when possible	2024-03-21 10:41:28 -03:00
bpf_kwork_top.c	perf cpumap: Use perf_cpu_map__for_each_cpu when possible	2024-03-21 10:41:28 -03:00
bpf_lock_contention.c	perf machine: Move machine's threads into its own abstraction	2024-03-03 22:51:44 -08:00
bpf_map.c
bpf_map.h
bpf_off_cpu.c
branch.c
branch.h
Build	perf util: Add shellcheck to generate-cmdlist.sh	2024-04-12 17:54:02 -03:00
build-id.c	perf dsos: Switch more loops to dsos__for_each_dso()	2024-04-12 12:04:13 -03:00
build-id.h	perf dsos: Attempt to better abstract DSOs internals	2024-04-12 12:04:13 -03:00
cache.h
cacheline.c
cacheline.h
call-path.c
call-path.h
callchain.c	perf maps: Hide maps internals	2024-02-12 12:35:41 -08:00
callchain.h
cap.c
cap.h
cgroup.c
cgroup.h
clockid.c
clockid.h
cloexec.c
cloexec.h
color.c
color.h
color_config.c
comm.c
comm.h
compress.h
config.c
config.h
copyfile.c
copyfile.h
counts.c
counts.h
cpu-set-sched.h
cpumap.c	perf cpumap: Use perf_cpu_map__for_each_cpu when possible	2024-03-21 10:41:28 -03:00
cpumap.h	perf stat: Support per-cluster aggregation	2024-02-09 14:59:53 -08:00
cputopo.c
cputopo.h
cs-etm-base.c
cs-etm.c
cs-etm.h
data-convert-bt.c
data-convert-json.c	perf data convert: Fix segfault when converting to json when cpu_desc isn't set	2024-02-26 08:30:17 -08:00
data-convert.h
data.c	perf data: Minor code style alignment cleanup	2024-01-22 12:08:21 -08:00
data.h	perf data: Minor code style alignment cleanup	2024-01-22 12:08:21 -08:00
db-export.c	perf db-export: Fix missing reference count get in call_path_from_sample()	2024-01-04 18:29:17 -03:00
db-export.h
debug.c	perf annotate-data: Add debug messages	2024-03-21 10:41:28 -03:00
debug.h	perf annotate-data: Add debug messages	2024-03-21 10:41:28 -03:00
debuginfo.c
debuginfo.h
demangle-cxx.cpp
demangle-cxx.h
demangle-java.c
demangle-java.h
demangle-ocaml.c
demangle-ocaml.h
demangle-rust.c
demangle-rust.h
disasm.c	perf annotate: Update DSO binary type when trying build-id	2024-04-26 22:12:55 -03:00
disasm.h	perf annotate: Split out util/disasm.c	2024-04-03 11:48:57 -03:00
dlfilter.c
dlfilter.h
dso.c	perf dso: Move dso functions out of dsos.c	2024-04-12 12:04:13 -03:00
dso.h	perf dso: Move dso functions out of dsos.c	2024-04-12 12:04:13 -03:00
dsos.c	perf dsos: Switch more loops to dsos__for_each_dso()	2024-04-12 12:04:13 -03:00
dsos.h	perf dsos: Switch more loops to dsos__for_each_dso()	2024-04-12 12:04:13 -03:00
dump-insn.c
dump-insn.h	perf script: Add capstone support for '-F +brstackdisasm'	2024-04-05 10:43:07 -03:00
dwarf-aux.c	perf dwarf-aux: Add die_collect_global_vars()	2024-05-02 10:45:30 -03:00
dwarf-aux.h	perf dwarf-aux: Add die_collect_global_vars()	2024-05-02 10:45:30 -03:00
dwarf-regs.c	perf dwarf-regs: Add get_dwarf_regnum()	2023-12-23 10:56:05 -03:00
env.c	perf env: Avoid recursively taking env->bpf_progs.lock	2024-01-03 17:54:54 -03:00
env.h	perf stat: Support per-cluster aggregation	2024-02-09 14:59:53 -08:00
event.c	perf maps: Get map before returning in maps__find	2024-02-12 12:35:26 -08:00
event.h
events_stats.h
evlist.c	perf evlist: Fix evlist__new_default() for > 1 core PMU	2024-01-30 11:40:28 -03:00
evlist.h
evsel.c	perf evsel: Fix duplicate initialization of data->id in evsel__parse_sample()	2024-02-01 22:11:45 -08:00
evsel.h	perf util: Add evsel__taskstate() to parse the task state info instead	2024-01-22 23:02:37 -08:00
evsel_config.h
evsel_fprintf.c
evsel_fprintf.h
evswitch.c
evswitch.h
expr.c	perf expr: Fix "has_event" function for metric style events	2024-02-13 13:48:06 -08:00
expr.h
expr.l	perf expr: Allow NaN to be a valid number	2024-02-13 13:47:08 -08:00
expr.y
find-map.c
fncache.c
fncache.h
ftrace.h
genelf.c
genelf.h	perf genelf: Fix compiling with libelf on rv32	2024-04-18 22:22:51 -03:00
genelf_debug.c
generate-cmdlist.sh
get_current_dir_name.c
get_current_dir_name.h
hashmap.c
hashmap.h
header.c	perf env: Avoid recursively taking env->bpf_progs.lock	2024-01-03 17:54:54 -03:00
header.h
help-unknown-cmd.c	perf help: Lower levenshtein penality for deleting character	2024-03-21 13:54:40 -03:00
help-unknown-cmd.h
hisi-ptt.c
hisi-ptt.h
hist.c	perf hist: Add weight fields to hist entry stats	2024-04-17 12:21:39 -03:00
hist.h	perf report: Add weight[123] output fields	2024-04-17 12:21:39 -03:00
intel-bts.c
intel-bts.h
intel-pt.c	perf intel-pt: Fix unassigned instruction op (discovered by MemorySanitizer)	2024-04-26 22:13:10 -03:00
intel-pt.h
intlist.c
intlist.h
iostat.c
iostat.h
jit.h
jitdump.c
jitdump.h
kvm-stat.h
kwork.h
levenshtein.c
levenshtein.h
lock-contention.h
lzma.c
machine.c	perf dsos: Switch more loops to dsos__for_each_dso()	2024-04-12 12:04:13 -03:00
machine.h	perf dsos: Attempt to better abstract DSOs internals	2024-04-12 12:04:13 -03:00
map.c	perf dsos: Tidy reference counting and locking	2024-04-12 12:04:13 -03:00
map.h	perf map: Add map__objdump_2rip()	2024-03-21 10:41:28 -03:00
map_symbol.c
map_symbol.h
maps.c	perf maps: Remove check_invariants() from maps__lock()	2024-05-02 16:35:47 -03:00
maps.h	perf maps: Locking tidy up of nr_maps	2024-02-12 12:35:41 -08:00
mem-events.c	perf mem: Clean up perf_pmus__num_mem_pmus()	2024-01-24 14:05:22 -08:00
mem-events.h	perf mem: Clean up perf_pmus__num_mem_pmus()	2024-01-24 14:05:22 -08:00
mem2node.c
mem2node.h
memswap.c
memswap.h
metricgroup.c	perf stat: Add new field in stat_config to enable hardware aware grouping	2024-04-18 22:22:51 -03:00
metricgroup.h	perf stat: Add new field in stat_config to enable hardware aware grouping	2024-04-18 22:22:51 -03:00
mmap.c
mmap.h
mutex.c
mutex.h
namespaces.c
namespaces.h
off_cpu.h
ordered-events.c
ordered-events.h
parse-branch-options.c
parse-branch-options.h
parse-events.c	perf test pmu: Refactor format test and exposed test APIs	2024-05-03 17:08:20 -03:00
parse-events.h	perf test pmu: Refactor format test and exposed test APIs	2024-05-03 17:08:20 -03:00
parse-events.l	perf parse-events: Tidy the setting of the default event name	2024-04-26 22:07:21 -03:00
parse-events.y	perf parse-events: Tidy the setting of the default event name	2024-04-26 22:07:21 -03:00
parse-regs-options.c	perf parse-regs: Introduce a weak function arch__sample_reg_masks()	2024-02-15 13:48:36 -08:00
parse-regs-options.h
parse-sublevel-options.c
parse-sublevel-options.h
path.c
path.h
perf-hooks-list.h
perf-hooks.c
perf-hooks.h
PERF-VERSION-GEN
perf_api_probe.c
perf_api_probe.h
perf_event_attr_fprintf.c	perf tools: Add/use PMU reverse lookup from config to name	2024-03-21 13:53:45 -03:00
perf_regs.c	perf parse-regs: Introduce a weak function arch__sample_reg_masks()	2024-02-15 13:48:36 -08:00
perf_regs.h	perf parse-regs: Introduce a weak function arch__sample_reg_masks()	2024-02-15 13:48:36 -08:00
pfm.c
pfm.h
pmu.c	perf pmu: Assume sysfs events are always the same case	2024-05-03 17:08:20 -03:00
pmu.h	perf test pmu: Refactor format test and exposed test APIs	2024-05-03 17:08:20 -03:00
pmu.l
pmu.y
pmus.c	perf test pmu: Refactor format test and exposed test APIs	2024-05-03 17:08:20 -03:00
pmus.h	perf test pmu: Refactor format test and exposed test APIs	2024-05-03 17:08:20 -03:00
print-events.c	perf list: Give more details about raw event encodings	2024-03-21 10:41:29 -03:00
print-events.h
print_binary.c
print_binary.h
print_insn.c	perf script: Consolidate capstone print functions	2024-04-08 17:42:27 -03:00
print_insn.h	perf script: Consolidate capstone print functions	2024-04-08 17:42:27 -03:00
probe-event.c	perf probe-event: Better error message for a too-long probe name	2024-04-18 22:22:51 -03:00
probe-event.h
probe-file.c
probe-file.h
probe-finder.c
probe-finder.h
pstack.c
pstack.h
python-ext-sources	perf evsel: Rename get_states() to parse_task_states() and make it public	2024-02-01 22:10:27 -08:00
python.c	perf tools: Add/use PMU reverse lookup from config to name	2024-03-21 13:53:45 -03:00
rb_resort.h	perf trace: Ignore thread hashing in summary	2024-03-03 22:51:18 -08:00
rblist.c
rblist.h
record.c	perf cpumap: Clean up use of perf_cpu_map__has_any_cpu_or_is_empty	2024-03-21 10:41:28 -03:00
record.h
rlimit.c
rlimit.h
rwsem.c
rwsem.h
s390-cpumcf-kernel.h
s390-cpumsf-kernel.h
s390-cpumsf.c
s390-cpumsf.h
s390-sample-raw.c
sample-raw.c
sample-raw.h
sample.h
session.c	perf dsos: Attempt to better abstract DSOs internals	2024-04-12 12:04:13 -03:00
session.h	perf dsos: Attempt to better abstract DSOs internals	2024-04-12 12:04:13 -03:00
setns.c
setup.py	perf evsel: Rename get_states() to parse_task_states() and make it public	2024-02-01 22:10:27 -08:00
sharded_mutex.c
sharded_mutex.h
sideband_evlist.c
smt.c
smt.h
sort.c	perf report: Add weight[123] output fields	2024-04-17 12:21:39 -03:00
sort.h	perf report: Add weight[123] output fields	2024-04-17 12:21:39 -03:00
spark.c
spark.h
srccode.c
srccode.h
srcline.c	perf srcline: Add missed addr2line closes	2024-02-09 20:43:13 -08:00
srcline.h
stat-display.c	perf stat: Fix metric-only aggregation index	2024-02-22 08:57:29 -08:00
stat-shadow.c	perf metrics: Compute unmerged uncore metrics individually	2024-02-22 08:57:09 -08:00
stat.c	perf cpumap: Clean up use of perf_cpu_map__has_any_cpu_or_is_empty	2024-03-21 10:41:28 -03:00
stat.h	perf stat: Add new field in stat_config to enable hardware aware grouping	2024-04-18 22:22:51 -03:00
strbuf.c
strbuf.h
stream.c
stream.h
strfilter.c
strfilter.h
string.c
string2.h
strlist.c
strlist.h
svghelper.c	perf cpumap: Use perf_cpu_map__for_each_cpu when possible	2024-03-21 10:41:28 -03:00
svghelper.h
symbol-elf.c	perf maps: Get map before returning in maps__find_by_name	2024-02-12 12:35:33 -08:00
symbol-minimal.c
symbol.c	perf tools: Fixup module symbol end address properly	2024-02-16 16:07:28 -08:00
symbol.h
symbol_conf.h	perf annotate: Add --data-type option	2023-12-23 22:39:43 -03:00
symbol_fprintf.c
symsrc.h
synthetic-events.c	perf tools: Fix calloc() arguments to address error introduced in gcc-14	2024-01-26 12:56:01 -03:00
synthetic-events.h
syscalltbl.c
syscalltbl.h
target.c
target.h
term.c
term.h
thread-stack.c
thread-stack.h
thread.c	perf machine: Move machine's threads into its own abstraction	2024-03-03 22:51:44 -08:00
thread.h	perf machine: Move machine's threads into its own abstraction	2024-03-03 22:51:44 -08:00
thread_map.c	perf thread_map: Skip exited threads when scanning /proc	2024-02-22 09:11:03 -08:00
thread_map.h
threads.c	perf threads: Switch from rbtree to hashmap	2024-03-03 22:52:04 -08:00
threads.h	perf threads: Reduce table size from 256 to 8	2024-03-03 22:52:13 -08:00
time-utils.c
time-utils.h
tool.h
top.c
top.h
topdown.c
topdown.h
trace-event-info.c
trace-event-parse.c	perf evsel: Rename get_states() to parse_task_states() and make it public	2024-02-01 22:10:27 -08:00
trace-event-read.c
trace-event-scripting.c
trace-event.c
trace-event.h	perf evsel: Rename get_states() to parse_task_states() and make it public	2024-02-01 22:10:27 -08:00
tracepoint.c
tracepoint.h
trigger.h
tsc.c
tsc.h
units.c
units.h
unwind-libdw.c	perf maps: Hide maps internals	2024-02-12 12:35:41 -08:00
unwind-libdw.h
unwind-libunwind-local.c	perf maps: Hide maps internals	2024-02-12 12:35:41 -08:00
unwind-libunwind.c	perf maps: Hide maps internals	2024-02-12 12:35:41 -08:00
unwind.h
usage.c
util.c	perf list: Add scandirat compatibility function	2024-02-22 09:11:41 -08:00
util.h	perf list: Add scandirat compatibility function	2024-02-22 09:11:41 -08:00
values.c
values.h	perf hist: Move histogram related code to hist.h	2024-04-17 12:21:39 -03:00
vdso.c	perf dsos: Tidy reference counting and locking	2024-04-12 12:04:13 -03:00
vdso.h
zlib.c
zstd.c