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
...
This commit is contained in:
Linus Torvalds
@ -36,6 +36,7 @@
|
||||
#include "../debug.h"
|
||||
#include "../dso.h"
|
||||
#include "../callchain.h"
|
||||
#include "../env.h"
|
||||
#include "../evsel.h"
|
||||
#include "../event.h"
|
||||
#include "../thread.h"
|
||||
@ -687,7 +688,7 @@ static void set_sample_datasrc_in_dict(PyObject *dict,
|
||||
_PyUnicode_FromString(decode));
|
||||
}
|
||||
|
||||
static void regs_map(struct regs_dump *regs, uint64_t mask, char *bf, int size)
|
||||
static void regs_map(struct regs_dump *regs, uint64_t mask, const char *arch, char *bf, int size)
|
||||
{
|
||||
unsigned int i = 0, r;
|
||||
int printed = 0;
|
||||
@ -702,7 +703,7 @@ static void regs_map(struct regs_dump *regs, uint64_t mask, char *bf, int size)
|
||||
|
||||
printed += scnprintf(bf + printed, size - printed,
|
||||
"%5s:0x%" PRIx64 " ",
|
||||
perf_reg_name(r), val);
|
||||
perf_reg_name(r, arch), val);
|
||||
}
|
||||
}
|
||||
|
||||
@ -711,6 +712,7 @@ static void set_regs_in_dict(PyObject *dict,
|
||||
struct evsel *evsel)
|
||||
{
|
||||
struct perf_event_attr *attr = &evsel->core.attr;
|
||||
const char *arch = perf_env__arch(evsel__env(evsel));
|
||||
|
||||
/*
|
||||
* Here value 28 is a constant size which can be used to print
|
||||
@ -722,12 +724,12 @@ static void set_regs_in_dict(PyObject *dict,
|
||||
int size = __sw_hweight64(attr->sample_regs_intr) * 28;
|
||||
char bf[size];
|
||||
|
||||
regs_map(&sample->intr_regs, attr->sample_regs_intr, bf, sizeof(bf));
|
||||
regs_map(&sample->intr_regs, attr->sample_regs_intr, arch, bf, sizeof(bf));
|
||||
|
||||
pydict_set_item_string_decref(dict, "iregs",
|
||||
_PyUnicode_FromString(bf));
|
||||
|
||||
regs_map(&sample->user_regs, attr->sample_regs_user, bf, sizeof(bf));
|
||||
regs_map(&sample->user_regs, attr->sample_regs_user, arch, bf, sizeof(bf));
|
||||
|
||||
pydict_set_item_string_decref(dict, "uregs",
|
||||
_PyUnicode_FromString(bf));
|
||||
@ -1555,7 +1557,7 @@ static void get_handler_name(char *str, size_t size,
|
||||
}
|
||||
|
||||
static void
|
||||
process_stat(struct evsel *counter, int cpu, int thread, u64 tstamp,
|
||||
process_stat(struct evsel *counter, struct perf_cpu cpu, int thread, u64 tstamp,
|
||||
struct perf_counts_values *count)
|
||||
{
|
||||
PyObject *handler, *t;
|
||||
@ -1575,7 +1577,7 @@ process_stat(struct evsel *counter, int cpu, int thread, u64 tstamp,
|
||||
return;
|
||||
}
|
||||
|
||||
PyTuple_SetItem(t, n++, _PyLong_FromLong(cpu));
|
||||
PyTuple_SetItem(t, n++, _PyLong_FromLong(cpu.cpu));
|
||||
PyTuple_SetItem(t, n++, _PyLong_FromLong(thread));
|
||||
|
||||
tuple_set_u64(t, n++, tstamp);
|
||||
@ -1599,7 +1601,7 @@ static void python_process_stat(struct perf_stat_config *config,
|
||||
int cpu, thread;
|
||||
|
||||
if (config->aggr_mode == AGGR_GLOBAL) {
|
||||
process_stat(counter, -1, -1, tstamp,
|
||||
process_stat(counter, (struct perf_cpu){ .cpu = -1 }, -1, tstamp,
|
||||
&counter->counts->aggr);
|
||||
return;
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user