summaryrefslogtreecommitdiff
path: root/tools/perf/util/smt.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-01-18 06:32:11 +0200
committerLinus Torvalds <torvalds@linux-foundation.org>2022-01-18 06:32:11 +0200
commit57d17378a4a042401b0c2fe211e5a0e3a276cb3d (patch)
treebe65e51a7b11cccb903b44708b98b3af47477304 /tools/perf/util/smt.c
parentf0033681f0fe8421baf8db125e57fa6157824c2d (diff)
parent9bce13ea88f85344b765abe5d3dabdd0f44dc177 (diff)
Merge tag 'perf-tools-for-v5.17-2022-01-16' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux
Pull perf tool updates from Arnaldo Carvalho de Melo: "New features: - Add 'trace' subcommand for 'perf ftrace', setting the stage for more 'perf ftrace' subcommands. Not using a subcommand yields the previous behaviour of 'perf ftrace'. - Add 'latency' subcommand to 'perf ftrace', that can use the function graph tracer or a BPF optimized one, via the -b/--use-bpf option. E.g.: $ sudo perf ftrace latency -a -T mutex_lock sleep 1 # DURATION | COUNT | GRAPH | 0 - 1 us | 4596 | ######################## | 1 - 2 us | 1680 | ######### | 2 - 4 us | 1106 | ##### | 4 - 8 us | 546 | ## | 8 - 16 us | 562 | ### | 16 - 32 us | 1 | | 32 - 64 us | 0 | | 64 - 128 us | 0 | | 128 - 256 us | 0 | | 256 - 512 us | 0 | | 512 - 1024 us | 0 | | 1 - 2 ms | 0 | | 2 - 4 ms | 0 | | 4 - 8 ms | 0 | | 8 - 16 ms | 0 | | 16 - 32 ms | 0 | | 32 - 64 ms | 0 | | 64 - 128 ms | 0 | | 128 - 256 ms | 0 | | 256 - 512 ms | 0 | | 512 - 1024 ms | 0 | | 1 - ... s | 0 | | The original implementation of this command was in the bcc tool. - Support --cputype option for hybrid events in 'perf stat'. Improvements: - Call chain improvements for ARM64. - No need to do any affinity setup when profiling pids. - Reduce multiplexing with duration_time in 'perf stat' metrics. - Improve error message for uncore events, stating that some event groups are can only be used in system wide (-a) mode. - perf stat metric group leader fixes/improvements, including arch specific changes to better support Intel topdown events. - Probe non-deprecated sysfs path first, i.e. try the path /sys/devices/system/cpu/cpuN/topology/thread_siblings first, then the old /sys/devices/system/cpu/cpuN/topology/core_cpus. - Disable debuginfod by default in 'perf record', to avoid stalls on distros such as Fedora 35. - Use unbuffered output in 'perf bench' when pipe/tee'ing to a file. - Enable ignore_missing_thread in 'perf trace' Fixes: - Avoid TUI crash when navigating in the annotation of recursive functions. - Fix hex dump character output in 'perf script'. - Fix JSON indentation to 4 spaces standard in the ARM vendor event files. - Fix use after free in metric__new(). - Fix IS_ERR_OR_NULL() usage in the perf BPF loader. - Fix up cross-arch register support, i.e. when printing register names take into account the architecture where the perf.data file was collected. - Fix SMT fallback with large core counts. - Don't lower case MetricExpr when parsing JSON files so as not to lose info such as the ":G" event modifier in metrics. perf test: - Add basic stress test for sigtrap handling to 'perf test'. - Fix 'perf test' failures on s/390 - Enable system wide for metricgroups test in 'perf test´. - Use 3 digits for test numbering now we can have more tests. Arch specific: - Add events for Arm Neoverse N2 in the ARM JSON vendor event files - Support PERF_MEM_LVLNUM encodings in powerpc, that came from a single patch series, where I incorrectly merged the kernel bits, that were then reverted after coordination with Michael Ellerman and Stephen Rothwell. - Add ARM SPE total latency as PERF_SAMPLE_WEIGHT. - Update AMD documentation, with info on raw event encoding. - Add support for global and local variants of the "p_stage_cyc" sort key, applicable to perf.data files collected on powerpc. - Remove duplicate and incorrect aux size checks in the ARM CoreSight ETM code. Refactorings: - Add a perf_cpu abstraction to disambiguate CPUs and CPU map indexes, fixing problems along the way. - Document CPU map methods. UAPI sync: - Update arch/x86/lib/mem{cpy,set}_64.S copies used in 'perf bench mem memcpy' - Sync UAPI files with the kernel sources: drm, msr-index, cpufeatures. Build system - Enable warnings through HOSTCFLAGS. - Drop requirement for libstdc++.so for libopencsd check libperf: - Make libperf adopt perf_counts_values__scale() from tools/perf/util/. - Add a stat multiplexing test to libperf" * tag 'perf-tools-for-v5.17-2022-01-16' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (115 commits) perf record: Disable debuginfod by default perf evlist: No need to do any affinity setup when profiling pids perf cpumap: Add is_dummy() method perf metric: Fix metric_leader perf cputopo: Fix CPU topology reading on s/390 perf metricgroup: Fix use after free in metric__new() libperf tests: Update a use of the new cpumap API perf arm: Fix off-by-one directory path tools arch x86: Sync the msr-index.h copy with the kernel sources tools headers cpufeatures: Sync with the kernel sources tools headers UAPI: Update tools's copy of drm.h header tools arch: Update arch/x86/lib/mem{cpy,set}_64.S copies used in 'perf bench mem memcpy' perf pmu-events: Don't lower case MetricExpr perf expr: Add debug logging for literals perf tools: Probe non-deprecated sysfs path 1st perf tools: Fix SMT fallback with large core counts perf cpumap: Give CPUs their own type perf stat: Correct first_shadow_cpu to return index perf script: Fix flipped index and cpu perf c2c: Use more intention revealing iterator ...
Diffstat (limited to 'tools/perf/util/smt.c')
-rw-r--r--tools/perf/util/smt.c73
1 files changed, 60 insertions, 13 deletions
diff --git a/tools/perf/util/smt.c b/tools/perf/util/smt.c
index 34f1b1b1176c..2b0a36ebf27a 100644
--- a/tools/perf/util/smt.c
+++ b/tools/perf/util/smt.c
@@ -5,6 +5,56 @@
#include "api/fs/fs.h"
#include "smt.h"
+/**
+ * hweight_str - Returns the number of bits set in str. Stops at first non-hex
+ * or ',' character.
+ */
+static int hweight_str(char *str)
+{
+ int result = 0;
+
+ while (*str) {
+ switch (*str++) {
+ case '0':
+ case ',':
+ break;
+ case '1':
+ case '2':
+ case '4':
+ case '8':
+ result++;
+ break;
+ case '3':
+ case '5':
+ case '6':
+ case '9':
+ case 'a':
+ case 'A':
+ case 'c':
+ case 'C':
+ result += 2;
+ break;
+ case '7':
+ case 'b':
+ case 'B':
+ case 'd':
+ case 'D':
+ case 'e':
+ case 'E':
+ result += 3;
+ break;
+ case 'f':
+ case 'F':
+ result += 4;
+ break;
+ default:
+ goto done;
+ }
+ }
+done:
+ return result;
+}
+
int smt_on(void)
{
static bool cached;
@@ -15,9 +65,12 @@ int smt_on(void)
if (cached)
return cached_result;
- if (sysfs__read_int("devices/system/cpu/smt/active", &cached_result) >= 0)
- goto done;
+ if (sysfs__read_int("devices/system/cpu/smt/active", &cached_result) >= 0) {
+ cached = true;
+ return cached_result;
+ }
+ cached_result = 0;
ncpu = sysconf(_SC_NPROCESSORS_CONF);
for (cpu = 0; cpu < ncpu; cpu++) {
unsigned long long siblings;
@@ -26,27 +79,21 @@ int smt_on(void)
char fn[256];
snprintf(fn, sizeof fn,
- "devices/system/cpu/cpu%d/topology/core_cpus", cpu);
+ "devices/system/cpu/cpu%d/topology/thread_siblings", cpu);
if (sysfs__read_str(fn, &str, &strlen) < 0) {
snprintf(fn, sizeof fn,
- "devices/system/cpu/cpu%d/topology/thread_siblings",
- cpu);
+ "devices/system/cpu/cpu%d/topology/core_cpus", cpu);
if (sysfs__read_str(fn, &str, &strlen) < 0)
continue;
}
/* Entry is hex, but does not have 0x, so need custom parser */
- siblings = strtoull(str, NULL, 16);
+ siblings = hweight_str(str);
free(str);
- if (hweight64(siblings) > 1) {
+ if (siblings > 1) {
cached_result = 1;
- cached = true;
break;
}
}
- if (!cached) {
- cached_result = 0;
-done:
- cached = true;
- }
+ cached = true;
return cached_result;
}