Merge tag 'perf-tools-for-v5.18-2022-03-26' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools updates from Arnaldo Carvalho de Melo:
 "New features:

  perf ftrace:

   - Add -n/--use-nsec option to the 'latency' subcommand.

     Default: usecs:

     $ sudo perf ftrace latency -T dput -a sleep 1
     #   DURATION     |      COUNT | GRAPH                          |
          0 - 1    us |    2098375 | #############################  |
          1 - 2    us |         61 |                                |
          2 - 4    us |         33 |                                |
          4 - 8    us |         13 |                                |
          8 - 16   us |        124 |                                |
         16 - 32   us |        123 |                                |
         32 - 64   us |          1 |                                |
         64 - 128  us |          0 |                                |
        128 - 256  us |          1 |                                |
        256 - 512  us |          0 |                                |

     Better granularity with nsec:

     $ sudo perf ftrace latency -T dput -a -n sleep 1
     #   DURATION     |      COUNT | GRAPH                          |
          0 - 1    us |          0 |                                |
          1 - 2    ns |          0 |                                |
          2 - 4    ns |          0 |                                |
          4 - 8    ns |          0 |                                |
          8 - 16   ns |          0 |                                |
         16 - 32   ns |          0 |                                |
         32 - 64   ns |          0 |                                |
         64 - 128  ns |    1163434 | ##############                 |
        128 - 256  ns |     914102 | #############                  |
        256 - 512  ns |        884 |                                |
        512 - 1024 ns |        613 |                                |
          1 - 2    us |         31 |                                |
          2 - 4    us |         17 |                                |
          4 - 8    us |          7 |                                |
          8 - 16   us |        123 |                                |
         16 - 32   us |         83 |                                |

  perf lock:

   - Add -c/--combine-locks option to merge lock instances in the same
     class into a single entry.

     # perf lock report -c
                    Name acquired contended avg wait(ns) total wait(ns) max wait(ns) min wait(ns)

           rcu_read_lock   251225         0            0              0            0            0
      hrtimer_bases.lock    39450         0            0              0            0            0
     &sb->s_type->i_l...    10301         1          662            662          662          662
        ptlock_ptr(page)    10173         2          701           1402          760          642
     &(ei->i_block_re...     8732         0            0              0            0            0
            &xa->xa_lock     8088         0            0              0            0            0
             &base->lock     6705         0            0              0            0            0
             &p->pi_lock     5549         0            0              0            0            0
     &dentry->d_lockr...     5010         4         1274           5097         1844          789
               &ep->lock     3958         0            0              0            0            0

      - Add -F/--field option to customize the list of fields to output:

     $ perf lock report -F contended,wait_max -k avg_wait
                     Name contended max wait(ns) avg wait(ns)

           slock-AF_INET6         1        23543        23543
        &lruvec->lru_lock         5        18317        11254
           slock-AF_INET6         1        10379        10379
               rcu_node_1         1         2104         2104
      &dentry->d_lockr...         1         1844         1844
      &dentry->d_lockr...         1         1672         1672
         &newf->file_lock        15         2279         1025
      &dentry->d_lockr...         1          792          792

   - Add --synth=no option for record, as there is no need to symbolize,
     lock names comes from the tracepoints.

  perf record:

   - Threaded recording, opt-in, via the new --threads command line
     option.

   - Improve AMD IBS (Instruction-Based Sampling) error handling
     messages.

  perf script:

   - Add 'brstackinsnlen' field (use it with -F) for branch stacks.

   - Output branch sample type in 'perf script'.

  perf report:

   - Add "addr_from" and "addr_to" sort dimensions.

   - Print branch stack entry type in 'perf report --dump-raw-trace'

   - Fix symbolization for chrooted workloads.

  Hardware tracing:

  Intel PT:

   - Add CFE (Control Flow Event) and EVD (Event Data) packets support.

   - Add MODE.Exec IFLAG bit support.

     Explanation about these features from the "Intel® 64 and IA-32
     architectures software developer’s manual combined volumes: 1, 2A,
     2B, 2C, 2D, 3A, 3B, 3C, 3D, and 4" PDF at:

        https://cdrdv2.intel.com/v1/dl/getContent/671200

     At page 3951:
      "32.2.4

       Event Trace is a capability that exposes details about the
       asynchronous events, when they are generated, and when their
       corresponding software event handler completes execution. These
       include:

        o Interrupts, including NMI and SMI, including the interrupt
          vector when defined.

        o Faults, exceptions including the fault vector.

           - Page faults additionally include the page fault address,
             when in context.

        o Event handler returns, including IRET and RSM.

        o VM exits and VM entries.¹

           - VM exits include the values written to the “exit reason”
             and “exit qualification” VMCS fields. INIT and SIPI events.

        o TSX aborts, including the abort status returned for the RTM
          instructions.

        o Shutdown.

       Additionally, it provides indication of the status of the
       Interrupt Flag (IF), to indicate when interrupts are masked"

  ARM CoreSight:

   - Use advertised caps/min_interval as default sample_period on ARM
     spe.

   - Update deduction of TRCCONFIGR register for branch broadcast on
     ARM's CoreSight ETM.

  Vendor Events (JSON):

  Intel:

   - Update events and metrics for: Alderlake, Broadwell, Broadwell DE,
     BroadwellX, CascadelakeX, Elkhartlake, Bonnell, Goldmont,
     GoldmontPlus, Westmere EP-DP, Haswell, HaswellX, Icelake, IcelakeX,
     Ivybridge, Ivytown, Jaketown, Knights Landing, Nehalem EP,
     Sandybridge, Silvermont, Skylake, Skylake Server, SkylakeX,
     Tigerlake, TremontX, Westmere EP-SP, and Westmere EX.

  ARM:

   - Add support for HiSilicon CPA PMU aliasing.

  perf stat:

   - Fix forked applications enablement of counters.

   - The 'slots' should only be printed on a different order than the
     one specified on the command line when 'topdown' events are
     present, fix it.

  Miscellaneous:

   - Sync msr-index, cpufeatures header files with the kernel sources.

   - Stop using some deprecated libbpf APIs in 'perf trace'.

   - Fix some spelling mistakes.

   - Refactor the maps pointers usage to pave the way for using refcount
     debugging.

   - Only offer the --tui option on perf top, report and annotate when
     perf was built with libslang.

   - Don't mention --to-ctf in 'perf data --help' when not linking with
     the required library, libbabeltrace.

   - Use ARRAY_SIZE() instead of ad hoc equivalent, spotted by
     array_size.cocci.

   - Enhance the matching of sub-commands abbreviations:
	'perf c2c rec' -> 'perf c2c record'
	'perf c2c recport -> error

   - Set build-id using build-id header on new mmap records.

   - Fix generation of 'perf --version' string.

  perf test:

   - Add test for the arm_spe event.

   - Add test to check unwinding using fame-pointer (fp) mode on arm64.

   - Make metric testing more robust in 'perf test'.

   - Add error message for unsupported branch stack cases.

  libperf:

   - Add API for allocating new thread map array.

   - Fix typo in perf_evlist__open() failure error messages in libperf
     tests.

  perf c2c:

   - Replace bitmap_weight() with bitmap_empty() where appropriate"

* tag 'perf-tools-for-v5.18-2022-03-26' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (143 commits)
  perf evsel: Improve AMD IBS (Instruction-Based Sampling) error handling messages
  perf python: Add perf_env stubs that will be needed in evsel__open_strerror()
  perf tools: Enhance the matching of sub-commands abbreviations
  libperf tests: Fix typo in perf_evlist__open() failure error messages
  tools arm64: Import cputype.h
  perf lock: Add -F/--field option to control output
  perf lock: Extend struct lock_key to have print function
  perf lock: Add --synth=no option for record
  tools headers cpufeatures: Sync with the kernel sources
  tools headers cpufeatures: Sync with the kernel sources
  perf stat: Fix forked applications enablement of counters
  tools arch x86: Sync the msr-index.h copy with the kernel sources
  perf evsel: Make evsel__env() always return a valid env
  perf build-id: Fix spelling mistake "Cant" -> "Can't"
  perf header: Fix spelling mistake "could't" -> "couldn't"
  perf script: Add 'brstackinsnlen' for branch stacks
  perf parse-events: Move slots only with topdown
  perf ftrace latency: Update documentation
  perf ftrace latency: Add -n/--use-nsec option
  perf tools: Fix version kernel tag
  ...

8 files changed, 95 insertions, 23 deletions

diff --git a/tools/lib/api/fd/array.c b/tools/lib/api/fd/array.c
index 5e6cb9debe37..f0f195207fca 100644
--- a/tools/lib/api/fd/array.c
+++ b/tools/lib/api/fd/array.c
@@ -88,6 +88,23 @@ int fdarray__add(struct fdarray *fda, int fd, short revents, enum fdarray_flags
 	return pos;
 }
 
+int fdarray__dup_entry_from(struct fdarray *fda, int pos, struct fdarray *from)
+{
+	struct pollfd *entry;
+	int npos;
+
+	if (pos >= from->nr)
+		return -EINVAL;
+
+	entry = &from->entries[pos];
+
+	npos = fdarray__add(fda, entry->fd, entry->events, from->priv[pos].flags);
+	if (npos >= 0)
+		fda->priv[npos] = from->priv[pos];
+
+	return npos;
+}
+
 int fdarray__filter(struct fdarray *fda, short revents,
 		    void (*entry_destructor)(struct fdarray *fda, int fd, void *arg),
 		    void *arg)
diff --git a/tools/lib/api/fd/array.h b/tools/lib/api/fd/array.h
index 7fcf21a33c0c..60ad197c8ee9 100644
--- a/tools/lib/api/fd/array.h
+++ b/tools/lib/api/fd/array.h
@@ -42,6 +42,7 @@ struct fdarray *fdarray__new(int nr_alloc, int nr_autogrow);
 void fdarray__delete(struct fdarray *fda);
 
 int fdarray__add(struct fdarray *fda, int fd, short revents, enum fdarray_flags flags);
+int fdarray__dup_entry_from(struct fdarray *fda, int pos, struct fdarray *from);
 int fdarray__poll(struct fdarray *fda, int timeout);
 int fdarray__filter(struct fdarray *fda, short revents,
 		    void (*entry_destructor)(struct fdarray *fda, int fd, void *arg),
diff --git a/tools/lib/perf/Documentation/libperf.txt b/tools/lib/perf/Documentation/libperf.txt
index 32c5051c24eb..a8f1a237931b 100644
--- a/tools/lib/perf/Documentation/libperf.txt
+++ b/tools/lib/perf/Documentation/libperf.txt
@@ -62,11 +62,12 @@ SYNOPSIS
   struct perf_thread_map;
 
   struct perf_thread_map *perf_thread_map__new_dummy(void);
+  struct perf_thread_map *perf_thread_map__new_array(int nr_threads, pid_t *array);
 
-  void perf_thread_map__set_pid(struct perf_thread_map *map, int thread, pid_t pid);
-  char *perf_thread_map__comm(struct perf_thread_map *map, int thread);
+  void perf_thread_map__set_pid(struct perf_thread_map *map, int idx, pid_t pid);
+  char *perf_thread_map__comm(struct perf_thread_map *map, int idx);
   int perf_thread_map__nr(struct perf_thread_map *threads);
-  pid_t perf_thread_map__pid(struct perf_thread_map *map, int thread);
+  pid_t perf_thread_map__pid(struct perf_thread_map *map, int idx);
 
   struct perf_thread_map *perf_thread_map__get(struct perf_thread_map *map);
   void perf_thread_map__put(struct perf_thread_map *map);
diff --git a/tools/lib/perf/include/perf/threadmap.h b/tools/lib/perf/include/perf/threadmap.h
index a7c50de8d010..8b40e7777cea 100644
--- a/tools/lib/perf/include/perf/threadmap.h
+++ b/tools/lib/perf/include/perf/threadmap.h
@@ -8,11 +8,12 @@
 struct perf_thread_map;
 
 LIBPERF_API struct perf_thread_map *perf_thread_map__new_dummy(void);
+LIBPERF_API struct perf_thread_map *perf_thread_map__new_array(int nr_threads, pid_t *array);
 
-LIBPERF_API void perf_thread_map__set_pid(struct perf_thread_map *map, int thread, pid_t pid);
-LIBPERF_API char *perf_thread_map__comm(struct perf_thread_map *map, int thread);
+LIBPERF_API void perf_thread_map__set_pid(struct perf_thread_map *map, int idx, pid_t pid);
+LIBPERF_API char *perf_thread_map__comm(struct perf_thread_map *map, int idx);
 LIBPERF_API int perf_thread_map__nr(struct perf_thread_map *threads);
-LIBPERF_API pid_t perf_thread_map__pid(struct perf_thread_map *map, int thread);
+LIBPERF_API pid_t perf_thread_map__pid(struct perf_thread_map *map, int idx);
 
 LIBPERF_API struct perf_thread_map *perf_thread_map__get(struct perf_thread_map *map);
 LIBPERF_API void perf_thread_map__put(struct perf_thread_map *map);
diff --git a/tools/lib/perf/libperf.map b/tools/lib/perf/libperf.map
index 6fa0d651576b..190b56ae923a 100644
--- a/tools/lib/perf/libperf.map
+++ b/tools/lib/perf/libperf.map
@@ -12,6 +12,7 @@ LIBPERF_0.0.1 {
 		perf_cpu_map__empty;
 		perf_cpu_map__max;
 		perf_cpu_map__has;
+		perf_thread_map__new_array;
 		perf_thread_map__new_dummy;
 		perf_thread_map__set_pid;
 		perf_thread_map__comm;
diff --git a/tools/lib/perf/tests/test-evlist.c b/tools/lib/perf/tests/test-evlist.c
index fa854c83b7e7..ed616fc19b4f 100644
--- a/tools/lib/perf/tests/test-evlist.c
+++ b/tools/lib/perf/tests/test-evlist.c
@@ -69,7 +69,7 @@ static int test_stat_cpu(void)
 	perf_evlist__set_maps(evlist, cpus, NULL);
 
 	err = perf_evlist__open(evlist);
-	__T("failed to open evsel", err == 0);
+	__T("failed to open evlist", err == 0);
 
 	perf_evlist__for_each_evsel(evlist, evsel) {
 		cpus = perf_evsel__cpus(evsel);
@@ -130,7 +130,7 @@ static int test_stat_thread(void)
 	perf_evlist__set_maps(evlist, NULL, threads);
 
 	err = perf_evlist__open(evlist);
-	__T("failed to open evsel", err == 0);
+	__T("failed to open evlist", err == 0);
 
 	perf_evlist__for_each_evsel(evlist, evsel) {
 		perf_evsel__read(evsel, 0, 0, &counts);
@@ -187,7 +187,7 @@ static int test_stat_thread_enable(void)
 	perf_evlist__set_maps(evlist, NULL, threads);
 
 	err = perf_evlist__open(evlist);
-	__T("failed to open evsel", err == 0);
+	__T("failed to open evlist", err == 0);
 
 	perf_evlist__for_each_evsel(evlist, evsel) {
 		perf_evsel__read(evsel, 0, 0, &counts);
@@ -507,7 +507,7 @@ static int test_stat_multiplexing(void)
 	perf_evlist__set_maps(evlist, NULL, threads);
 
 	err = perf_evlist__open(evlist);
-	__T("failed to open evsel", err == 0);
+	__T("failed to open evlist", err == 0);
 
 	perf_evlist__enable(evlist);
 
diff --git a/tools/lib/perf/tests/test-threadmap.c b/tools/lib/perf/tests/test-threadmap.c
index 5e2a0291e94c..f728ad7002bb 100644
--- a/tools/lib/perf/tests/test-threadmap.c
+++ b/tools/lib/perf/tests/test-threadmap.c
@@ -11,9 +11,43 @@ static int libperf_print(enum libperf_print_level level,
 	return vfprintf(stderr, fmt, ap);
 }
 
+static int test_threadmap_array(int nr, pid_t *array)
+{
+	struct perf_thread_map *threads;
+	int i;
+
+	threads = perf_thread_map__new_array(nr, array);
+	__T("Failed to allocate new thread map", threads);
+
+	__T("Unexpected number of threads", perf_thread_map__nr(threads) == nr);
+
+	for (i = 0; i < nr; i++) {
+		__T("Unexpected initial value of thread",
+		    perf_thread_map__pid(threads, i) == (array ? array[i] : -1));
+	}
+
+	for (i = 1; i < nr; i++)
+		perf_thread_map__set_pid(threads, i, i * 100);
+
+	__T("Unexpected value of thread 0",
+	    perf_thread_map__pid(threads, 0) == (array ? array[0] : -1));
+
+	for (i = 1; i < nr; i++) {
+		__T("Unexpected thread value",
+		    perf_thread_map__pid(threads, i) == i * 100);
+	}
+
+	perf_thread_map__put(threads);
+
+	return 0;
+}
+
+#define THREADS_NR	10
 int test_threadmap(int argc, char **argv)
 {
 	struct perf_thread_map *threads;
+	pid_t thr_array[THREADS_NR];
+	int i;
 
 	__T_START;
 
@@ -27,6 +61,13 @@ int test_threadmap(int argc, char **argv)
 	perf_thread_map__put(threads);
 	perf_thread_map__put(threads);
 
+	test_threadmap_array(THREADS_NR, NULL);
+
+	for (i = 0; i < THREADS_NR; i++)
+		thr_array[i] = i + 100;
+
+	test_threadmap_array(THREADS_NR, thr_array);
+
 	__T_END;
 	return tests_failed == 0 ? 0 : -1;
 }
diff --git a/tools/lib/perf/threadmap.c b/tools/lib/perf/threadmap.c
index e92c368b0a6c..07968f3ea093 100644
--- a/tools/lib/perf/threadmap.c
+++ b/tools/lib/perf/threadmap.c
@@ -32,28 +32,38 @@ struct perf_thread_map *perf_thread_map__realloc(struct perf_thread_map *map, in
 
 #define thread_map__alloc(__nr) perf_thread_map__realloc(NULL, __nr)
 
-void perf_thread_map__set_pid(struct perf_thread_map *map, int thread, pid_t pid)
+void perf_thread_map__set_pid(struct perf_thread_map *map, int idx, pid_t pid)
 {
-	map->map[thread].pid = pid;
+	map->map[idx].pid = pid;
 }
 
-char *perf_thread_map__comm(struct perf_thread_map *map, int thread)
+char *perf_thread_map__comm(struct perf_thread_map *map, int idx)
 {
-	return map->map[thread].comm;
+	return map->map[idx].comm;
 }
 
-struct perf_thread_map *perf_thread_map__new_dummy(void)
+struct perf_thread_map *perf_thread_map__new_array(int nr_threads, pid_t *array)
 {
-	struct perf_thread_map *threads = thread_map__alloc(1);
+	struct perf_thread_map *threads = thread_map__alloc(nr_threads);
+	int i;
+
+	if (!threads)
+		return NULL;
+
+	for (i = 0; i < nr_threads; i++)
+		perf_thread_map__set_pid(threads, i, array ? array[i] : -1);
+
+	threads->nr = nr_threads;
+	refcount_set(&threads->refcnt, 1);
 
-	if (threads != NULL) {
-		perf_thread_map__set_pid(threads, 0, -1);
-		threads->nr = 1;
-		refcount_set(&threads->refcnt, 1);
-	}
 	return threads;
 }
 
+struct perf_thread_map *perf_thread_map__new_dummy(void)
+{
+	return perf_thread_map__new_array(1, NULL);
+}
+
 static void perf_thread_map__delete(struct perf_thread_map *threads)
 {
 	if (threads) {
@@ -85,7 +95,7 @@ int perf_thread_map__nr(struct perf_thread_map *threads)
 	return threads ? threads->nr : 1;
 }
 
-pid_t perf_thread_map__pid(struct perf_thread_map *map, int thread)
+pid_t perf_thread_map__pid(struct perf_thread_map *map, int idx)
 {
-	return map->map[thread].pid;
+	return map->map[idx].pid;
 }