Merge tag 'perf-tools-for-v6.1-1-2022-10-07' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools updates from Arnaldo Carvalho de Melo:

 - Add support for AMD on 'perf mem' and 'perf c2c', the kernel
   enablement patches went via tip.

   Example:

      $ sudo perf mem record -- -c 10000
      ^C[ perf record: Woken up 227 times to write data ]
      [ perf record: Captured and wrote 58.760 MB perf.data (836978 samples) ]

      $ sudo perf mem report -F mem,sample,snoop
      Samples: 836K of event 'ibs_op//', Event count (approx.): 8418762
      Memory access                  Samples  Snoop
      N/A                             700620  N/A
      L1 hit                          126675  N/A
      L2 hit                             424  N/A
      L3 hit                             664  HitM
      L3 hit                              10  N/A
      Local RAM hit                        2  N/A
      Remote RAM (1 hop) hit            8558  N/A
      Remote Cache (1 hop) hit             3  N/A
      Remote Cache (1 hop) hit             2  HitM
      Remote Cache (2 hops) hit           10  HitM
      Remote Cache (2 hops) hit            6  N/A
      Uncached hit                         4  N/A
      $

 - "perf lock" improvements:

     - Add -E/--entries option to limit the number of entries to
       display, say to ask for just the top 5 contended locks.

     - Add -q/--quiet option to suppress header and debug messages.

     - Add a 'perf test' kernel lock contention entry to test 'perf
       lock'.

 - "perf lock contention" improvements:

     - Ask BPF's bpf_get_stackid() to skip some callchain entries.

       The ones closer to the tooling are bpf related and not that
       interesting, the ones calling the locking function are the ones
       we're interested in, example of a full, unskipped callstack:

     - Allow changing the callstack depth and number of entries to skip.

           1     10.74 us     10.74 us     10.74 us     spinlock   __bpf_trace_contention_begin+0xb
                          0xffffffffc03b5c47  bpf_prog_bf07ae9e2cbd02c5_contention_begin+0x117
                          0xffffffffc03b5c47  bpf_prog_bf07ae9e2cbd02c5_contention_begin+0x117
                          0xffffffffbb8b8e75  bpf_trace_run2+0x35
                          0xffffffffbb7eab9b  __bpf_trace_contention_begin+0xb
                          0xffffffffbb7ebe75  queued_spin_lock_slowpath+0x1f5
                          0xffffffffbc1c26ff  _raw_spin_lock+0x1f
                          0xffffffffbb841015  tick_do_update_jiffies64+0x25
                          0xffffffffbb8409ee  tick_irq_enter+0x9e

     - Show full callstack in verbose mode (-v option), sometimes this
       is desirable instead of showing just one callstack entry.

 - Allow multiple time ranges in 'perf record --delay' to help in
   reducing the amount of data collected from hardware tracing (Intel
   PT, etc) when there is a rough idea of periods of time where events
   of interest take time.

 - Add Intel PT to record only decoder debug messages when error
   happens.

 - Improve layout of Intel PT man page.

 - Add new branch types: alignment, data and inst faults and arch
   specific ones, such as fiq, debug_halt, debug_exit, debug_inst and
   debug_data on arm64.

   Kernel enablement went thru the tip tree.

 - Fix 'perf probe' error log check in 'perf test' when no debuginfo is
   available.

 - Fix 'perf stat' aggregation mode logic, it should be looking at the
   CPU not at the core number.

 - Fix flags parsing in 'perf trace' filters.

 - Introduce compact encoding of CPU range encoding on perf.data, to
   avoid having a bitmap with all the CPUs.

 - Improvements to the 'perf stat' metrics, including adding
   "core_wide", and computing "smt" from the CPU topology.

 - Add support to the new PERF_FORMAT_LOST perf_event_attr.read_format,
   that allows tooling to ask for the precise number of lost samples for
   a given event.

 - Add 'addr' sort key to see just the address of sampled instructions:

      $ perf record -o- true | perf report -i- -s addr
      [ perf record: Woken up 1 times to write data ]
      [ perf record: Captured and wrote 0.000 MB - ]
      # Samples: 12  of event 'cycles:u'
      # Event count (approx.): 252512
      #
      # Overhead  Address
      # ........  ..................
          42.96%  0x7f96f08443d7
          29.55%  0x7f96f0859b50
          14.76%  0x7f96f0852e02
           8.30%  0x7f96f0855028
           4.43%  0xffffffff8de01087

      perf annotate: Toggle full address <-> offset display

 - Add 'f' hotkey to the 'perf annotate' TUI interface when in
   'disassembler output' mode ('o' hotkey) to toggle showing full
   virtual address or just the offset.

 - Cache DSO build-ids when synthesizing PERF_RECORD_MMAP records for
   pre-existing threads, at the start of a 'perf record' session,
   speeding up that record startup phase.

 - Add a command line option to specify build ids in 'perf inject'.

 - Update JSON event files for the Intel alderlake, broadwell,
   broadwellde, broadwellx, cascadelakex, haswell, haswellx, icelake,
   icelakex, ivybridge, ivytown, jaketown, sandybridge, sapphirerapids,
   skylake, skylakex, and tigerlake processors.

 - Update vendor JSON event files for the ARM Neoverse V1 and E1
   platforms.

 - Add a 'perf test' entry for 'perf mem' where a struct has false
   sharing and this gets detected in the 'perf mem' output, tested with
   Intel, AMD and ARM64 systems.

 - Add a 'perf test' entry to test the resolution of java symbols, where
   an output like this is expected:

       8.18%  jshell    jitted-50116-29.so    [.] Interpreter
       0.75%  Thread-1  jitted-83602-1670.so  [.] jdk.internal.jimage.BasicImageReader.getString(int)

 - Add tests for the ARM64 CoreSight hardware tracing feature, with
   specially crafted pureloop, memcpy, thread loop and unroll tread that
   then gets traced and the output compared with expected output.

   Documentation explaining it is also included.

 - Add per thread Intel PT 'perf test' entry to check that
   PERF_RECORD_TEXT_POKE events are recorded per CPU, resulting in a
   mixture of per thread and per CPU events and mmaps, verify that this
   gets all recorded correctly.

 - Introduce pthread mutex wrappers to allow for building with clang's
   -Wthread-safety, i.e. using the "guarded_by" "pt_guarded_by"
   "lockable", "exclusive_lock_function", "exclusive_trylock_function",
   "exclusive_locks_required", and "no_thread_safety_analysis" compiler
   function attributes.

 - Fix empty version number when building outside of a git repo.

 - Improve feature detection display when multiple versions of a feature
   are present, such as for binutils libbfd, that has a mix of possible
   ways to detect according to the Linux distribution.

   Previously in some cases we had:

      Auto-detecting system features
      <SNIP>
      ...                                  libbfd: [ on  ]
      ...                          libbfd-liberty: [ on  ]
      ...                        libbfd-liberty-z: [ on  ]
      <SNIP>

   Now for this case we show just the main feature:

      Auto-detecting system features
      <SNIP>
      ...                                  libbfd: [ on  ]
      <SNIP>

 - Remove some unused structs, variables, macros, function prototypes
   and includes from various places.

* tag 'perf-tools-for-v6.1-1-2022-10-07' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (169 commits)
  perf script: Add missing fields in usage hint
  perf mem: Print "LFB/MAB" for PERF_MEM_LVLNUM_LFB
  perf mem/c2c: Avoid printing empty lines for unsupported events
  perf mem/c2c: Add load store event mappings for AMD
  perf mem/c2c: Set PERF_SAMPLE_WEIGHT for LOAD_STORE events
  perf mem: Add support for printing PERF_MEM_LVLNUM_{CXL|IO}
  perf amd ibs: Sync arch/x86/include/asm/amd-ibs.h header with the kernel
  tools headers UAPI: Sync include/uapi/linux/perf_event.h header with the kernel
  perf stat: Fix cpu check to use id.cpu.cpu in aggr_printout()
  perf test coresight: Add relevant documentation about ARM64 CoreSight testing
  perf test: Add git ignore for tmp and output files of ARM CoreSight tests
  perf test coresight: Add unroll thread test shell script
  perf test coresight: Add unroll thread test tool
  perf test coresight: Add thread loop test shell scripts
  perf test coresight: Add thread loop test tool
  perf test coresight: Add memcpy thread test shell script
  perf test coresight: Add memcpy thread test tool
  perf test: Add git ignore for perf data generated by the ARM CoreSight tests
  perf test: Add arm64 asm pureloop test shell script
  perf test: Add asm pureloop test tool
  ...

6 files changed, 46 insertions, 19 deletions

diff --git a/tools/lib/api/fd/array.h b/tools/lib/api/fd/array.h
index 60ad197c8ee9..5c01f7b05dfb 100644
--- a/tools/lib/api/fd/array.h
+++ b/tools/lib/api/fd/array.h
@@ -31,8 +31,9 @@ struct fdarray {
 };
 
 enum fdarray_flags {
-	fdarray_flag__default	    = 0x00000000,
-	fdarray_flag__nonfilterable = 0x00000001
+	fdarray_flag__default		= 0x00000000,
+	fdarray_flag__nonfilterable	= 0x00000001,
+	fdarray_flag__non_perf_event	= 0x00000002,
 };
 
 void fdarray__init(struct fdarray *fda, int nr_autogrow);
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index 8ec5b9f344e0..61b637f29b82 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -40,11 +40,11 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
 	 * We already have cpus for evsel (via PMU sysfs) so
 	 * keep it, if there's no target cpu list defined.
 	 */
-	if (!evsel->own_cpus ||
-	    (!evsel->system_wide && evlist->has_user_cpus) ||
-	    (!evsel->system_wide &&
-	     !evsel->requires_cpu &&
-	     perf_cpu_map__empty(evlist->user_requested_cpus))) {
+	if (evsel->system_wide) {
+		perf_cpu_map__put(evsel->cpus);
+		evsel->cpus = perf_cpu_map__new(NULL);
+	} else if (!evsel->own_cpus || evlist->has_user_cpus ||
+		   (!evsel->requires_cpu && perf_cpu_map__empty(evlist->user_requested_cpus))) {
 		perf_cpu_map__put(evsel->cpus);
 		evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus);
 	} else if (evsel->cpus != evsel->own_cpus) {
@@ -52,7 +52,10 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
 		evsel->cpus = perf_cpu_map__get(evsel->own_cpus);
 	}
 
-	if (!evsel->system_wide) {
+	if (evsel->system_wide) {
+		perf_thread_map__put(evsel->threads);
+		evsel->threads = perf_thread_map__new_dummy();
+	} else {
 		perf_thread_map__put(evsel->threads);
 		evsel->threads = perf_thread_map__get(evlist->threads);
 	}
@@ -64,9 +67,7 @@ static void perf_evlist__propagate_maps(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
 
-	/* Recomputing all_cpus, so start with a blank slate. */
-	perf_cpu_map__put(evlist->all_cpus);
-	evlist->all_cpus = NULL;
+	evlist->needs_map_propagation = true;
 
 	perf_evlist__for_each_evsel(evlist, evsel)
 		__perf_evlist__propagate_maps(evlist, evsel);
@@ -78,7 +79,9 @@ void perf_evlist__add(struct perf_evlist *evlist,
 	evsel->idx = evlist->nr_entries;
 	list_add_tail(&evsel->node, &evlist->entries);
 	evlist->nr_entries += 1;
-	__perf_evlist__propagate_maps(evlist, evsel);
+
+	if (evlist->needs_map_propagation)
+		__perf_evlist__propagate_maps(evlist, evsel);
 }
 
 void perf_evlist__remove(struct perf_evlist *evlist,
@@ -174,9 +177,6 @@ void perf_evlist__set_maps(struct perf_evlist *evlist,
 		evlist->threads = perf_thread_map__get(threads);
 	}
 
-	if (!evlist->all_cpus && cpus)
-		evlist->all_cpus = perf_cpu_map__get(cpus);
-
 	perf_evlist__propagate_maps(evlist);
 }
 
@@ -487,6 +487,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 			if (ops->idx)
 				ops->idx(evlist, evsel, mp, idx);
 
+			/* Debug message used by test scripts */
 			pr_debug("idx %d: mmapping fd %d\n", idx, *output);
 			if (ops->mmap(map, mp, *output, evlist_cpu) < 0)
 				return -1;
@@ -496,6 +497,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 			if (!idx)
 				perf_evlist__set_mmap_first(evlist, map, overwrite);
 		} else {
+			/* Debug message used by test scripts */
 			pr_debug("idx %d: set output fd %d -> %d\n", idx, fd, *output);
 			if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0)
 				return -1;
diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c
index 8ce5bbd09666..8b51b008a81f 100644
--- a/tools/lib/perf/evsel.c
+++ b/tools/lib/perf/evsel.c
@@ -515,9 +515,6 @@ int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
 	if (ncpus == 0 || nthreads == 0)
 		return 0;
 
-	if (evsel->system_wide)
-		nthreads = 1;
-
 	evsel->sample_id = xyarray__new(ncpus, nthreads, sizeof(struct perf_sample_id));
 	if (evsel->sample_id == NULL)
 		return -ENOMEM;
diff --git a/tools/lib/perf/include/internal/evlist.h b/tools/lib/perf/include/internal/evlist.h
index 6f89aec3e608..850f07070036 100644
--- a/tools/lib/perf/include/internal/evlist.h
+++ b/tools/lib/perf/include/internal/evlist.h
@@ -19,6 +19,7 @@ struct perf_evlist {
 	int			 nr_entries;
 	int			 nr_groups;
 	bool			 has_user_cpus;
+	bool			 needs_map_propagation;
 	/**
 	 * The cpus passed from the command line or all online CPUs by
 	 * default.
diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h
index d8ae4e944467..e282faf8fd75 100644
--- a/tools/lib/perf/include/perf/event.h
+++ b/tools/lib/perf/include/perf/event.h
@@ -153,6 +153,7 @@ struct perf_record_header_attr {
 enum {
 	PERF_CPU_MAP__CPUS = 0,
 	PERF_CPU_MAP__MASK = 1,
+	PERF_CPU_MAP__RANGE_CPUS = 2,
 };
 
 /*
@@ -195,6 +196,17 @@ struct perf_record_mask_cpu_map64 {
 #pragma GCC diagnostic ignored "-Wpacked"
 #pragma GCC diagnostic ignored "-Wattributes"
 
+/*
+ * An encoding of a CPU map for a range starting at start_cpu through to
+ * end_cpu. If any_cpu is 1, an any CPU (-1) value (aka dummy value) is present.
+ */
+struct perf_record_range_cpu_map {
+	__u8 any_cpu;
+	__u8 __pad;
+	__u16 start_cpu;
+	__u16 end_cpu;
+};
+
 struct __packed perf_record_cpu_map_data {
 	__u16			 type;
 	union {
@@ -204,6 +216,8 @@ struct __packed perf_record_cpu_map_data {
 		struct perf_record_mask_cpu_map32 mask32_data;
 		/* Used when type == PERF_CPU_MAP__MASK and long_size == 8. */
 		struct perf_record_mask_cpu_map64 mask64_data;
+		/* Used when type == PERF_CPU_MAP__RANGE_CPUS. */
+		struct perf_record_range_cpu_map range_cpu_data;
 	};
 };
 
@@ -233,7 +247,16 @@ struct perf_record_event_update {
 	struct perf_event_header header;
 	__u64			 type;
 	__u64			 id;
-	char			 data[];
+	union {
+		/* Used when type == PERF_EVENT_UPDATE__SCALE. */
+		struct perf_record_event_update_scale scale;
+		/* Used when type == PERF_EVENT_UPDATE__UNIT. */
+		char unit[0];
+		/* Used when type == PERF_EVENT_UPDATE__NAME. */
+		char name[0];
+		/* Used when type == PERF_EVENT_UPDATE__CPUS. */
+		struct perf_record_event_update_cpus cpus;
+	};
 };
 
 #define MAX_EVENT_NAME 64
diff --git a/tools/lib/subcmd/exec-cmd.c b/tools/lib/subcmd/exec-cmd.c
index 33e94fb83986..5dbea456973e 100644
--- a/tools/lib/subcmd/exec-cmd.c
+++ b/tools/lib/subcmd/exec-cmd.c
@@ -24,6 +24,9 @@ void exec_cmd_init(const char *exec_name, const char *prefix,
 	subcmd_config.prefix		= prefix;
 	subcmd_config.exec_path		= exec_path;
 	subcmd_config.exec_path_env	= exec_path_env;
+
+	/* Setup environment variable for invoked shell script. */
+	setenv("PREFIX", prefix, 1);
 }
 
 #define is_dir_sep(c) ((c) == '/')