iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Browse Source 
Pull perf updates from Ingo Molnar:
 "The main kernel changes were:

   - add support for Intel's "adaptive PEBS v4" - which embedds LBS data
     in PEBS records and can thus batch up and reduce the IRQ (NMI) rate
     significantly - reducing overhead and making call-graph profiling
     less intrusive.

   - add Intel CPU core and uncore support updates for Tremont, Icelake,

   - extend the x86 PMU constraints scheduler with 'constraint ranges'
     to better support Icelake hw constraints,

   - make x86 call-chain support work better with CONFIG_FRAME_POINTER=y

   - misc other changes

  Tooling changes:

   - updates to the main tools: 'perf record', 'perf trace', 'perf
     stat'

   - updated Intel and S/390 vendor events

   - libtraceevent updates

   - misc other updates and fixes"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (69 commits)
  perf/x86: Make perf callchains work without CONFIG_FRAME_POINTER
  watchdog: Fix typo in comment
  perf/x86/intel: Add Tremont core PMU support
  perf/x86/intel/uncore: Add Intel Icelake uncore support
  perf/x86/msr: Add Icelake support
  perf/x86/intel/rapl: Add Icelake support
  perf/x86/intel/cstate: Add Icelake support
  perf/x86/intel: Add Icelake support
  perf/x86: Support constraint ranges
  perf/x86/lbr: Avoid reading the LBRs when adaptive PEBS handles them
  perf/x86/intel: Support adaptive PEBS v4
  perf/x86/intel/ds: Extract code of event update in short period
  perf/x86/intel: Extract memory code PEBS parser for reuse
  perf/x86: Support outputting XMM registers
  perf/x86/intel: Force resched when TFA sysctl is modified
  perf/core: Add perf_pmu_resched() as global function
  perf/headers: Fix stale comment for struct perf_addr_filter
  perf/core: Make perf_swevent_init_cpu() static
  perf/x86: Add sanity checks to x86_schedule_events()
  perf/x86: Optimize x86_schedule_events()
  ...
This commit is contained in:
Linus Torvalds
2019-05-06 14:16:36 -07:00
parent 007dc78fea d15d356887
commit 90489a72fb
140 changed files with 13693 additions and 8444 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
tools/perf/builtin-stat.c
View File

@ -244,11 +244,25 @@ perf_evsel__write_stat_event(struct perf_evsel *counter, u32 cpu, u32 thread,
process_synthesized_event, NULL);
}
static int read_single_counter(struct perf_evsel *counter, int cpu,
int thread, struct timespec *rs)
{
if (counter->tool_event == PERF_TOOL_DURATION_TIME) {
u64 val = rs->tv_nsec + rs->tv_sec*1000000000ULL;
struct perf_counts_values *count =
perf_counts(counter->counts, cpu, thread);
count->ena = count->run = val;
count->val = val;
return 0;
}
return perf_evsel__read_counter(counter, cpu, thread);
}
/*
* Read out the results of a single counter:
* do not aggregate counts across CPUs in system-wide mode
*/
static int read_counter(struct perf_evsel *counter)
static int read_counter(struct perf_evsel *counter, struct timespec *rs)
{
int nthreads = thread_map__nr(evsel_list->threads);
int ncpus, cpu, thread;
@ -275,7 +289,7 @@ static int read_counter(struct perf_evsel *counter)
* (via perf_evsel__read_counter) and sets threir count->loaded.
*/
if (!count->loaded &&
perf_evsel__read_counter(counter, cpu, thread)) {
read_single_counter(counter, cpu, thread, rs)) {
counter->counts->scaled = -1;
perf_counts(counter->counts, cpu, thread)->ena = 0;
perf_counts(counter->counts, cpu, thread)->run = 0;
@ -304,13 +318,13 @@ static int read_counter(struct perf_evsel *counter)
return 0;
}
static void read_counters(void)
static void read_counters(struct timespec *rs)
{
struct perf_evsel *counter;
int ret;
evlist__for_each_entry(evsel_list, counter) {
ret = read_counter(counter);
ret = read_counter(counter, rs);
if (ret)
pr_debug("failed to read counter %s\n", counter->name);
@ -323,11 +337,11 @@ static void process_interval(void)
{
struct timespec ts, rs;
read_counters();
clock_gettime(CLOCK_MONOTONIC, &ts);
diff_timespec(&rs, &ts, &ref_time);
read_counters(&rs);
if (STAT_RECORD) {
if (WRITE_STAT_ROUND_EVENT(rs.tv_sec * NSEC_PER_SEC + rs.tv_nsec, INTERVAL))
pr_err("failed to write stat round event\n");
@ -593,7 +607,7 @@ try_again:
* avoid arbitrary skew, we must read all counters before closing any
* group leaders.
*/
read_counters();
read_counters(&(struct timespec) { .tv_nsec = t1-t0 });
perf_evlist__close(evsel_list);
return WEXITSTATUS(status);