Merge tag 'perf-tools-for-v6.4-3-2023-05-06' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tool updates from Arnaldo Carvalho de Melo:
 "Third version of perf tool updates, with the build problems with with
  using a 'vmlinux.h' generated from the main build fixed, and the bpf
  skeleton build disabled by default.

  Build:

   - Require libtraceevent to build, one can disable it using
     NO_LIBTRACEEVENT=1.

     It is required for tools like 'perf sched', 'perf kvm', 'perf
     trace', etc.

     libtraceevent is available in most distros so installing
     'libtraceevent-devel' should be a one-time event to continue
     building perf as usual.

     Using NO_LIBTRACEEVENT=1 produces tooling that is functional and
     sufficient for lots of users not interested in those libtraceevent
     dependent features.

   - Allow Python support in 'perf script' when libtraceevent isn't
     linked, as not all features requires it, for instance Intel PT does
     not use tracepoints.

   - Error if the python interpreter needed for jevents to work isn't
     available and NO_JEVENTS=1 isn't set, preventing a build without
     support for JSON vendor events, which is a rare but possible
     condition. The two check error messages:

        $(error ERROR: No python interpreter needed for jevents generation. Install python or build with NO_JEVENTS=1.)
        $(error ERROR: Python interpreter needed for jevents generation too old (older than 3.6). Install a newer python or build with NO_JEVENTS=1.)

   - Make libbpf 1.0 the minimum required when building with out of
     tree, distro provided libbpf.

   - Use libsdtc++'s and LLVM's libcxx's __cxa_demangle, a portable C++
     demangler, add 'perf test' entry for it.

   - Make binutils libraries opt in, as distros disable building with it
     due to licensing, they were used for C++ demangling, for instance.

   - Switch libpfm4 to opt-out rather than opt-in, if libpfm-devel (or
     equivalent) isn't installed, we'll just have a build warning:

       Makefile.config:1144: libpfm4 not found, disables libpfm4 support. Please install libpfm4-dev

   - Add a feature test for scandirat(), that is not implemented so far
     in musl and uclibc, disabling features that need it, such as
     scanning for tracepoints in /sys/kernel/tracing/events.

  perf BPF filters:

   - New feature where BPF can be used to filter samples, for instance:

      $ sudo ./perf record -e cycles --filter 'period > 1000' true
      $ sudo ./perf script
           perf-exec 2273949 546850.708501:       5029 cycles:  ffffffff826f9e25 finish_wait+0x5 ([kernel.kallsyms])
           perf-exec 2273949 546850.708508:      32409 cycles:  ffffffff826f9e25 finish_wait+0x5 ([kernel.kallsyms])
           perf-exec 2273949 546850.708526:     143369 cycles:  ffffffff82b4cdbf xas_start+0x5f ([kernel.kallsyms])
           perf-exec 2273949 546850.708600:     372650 cycles:  ffffffff8286b8f7 __pagevec_lru_add+0x117 ([kernel.kallsyms])
           perf-exec 2273949 546850.708791:     482953 cycles:  ffffffff829190de __mod_memcg_lruvec_state+0x4e ([kernel.kallsyms])
                true 2273949 546850.709036:     501985 cycles:  ffffffff828add7c tlb_gather_mmu+0x4c ([kernel.kallsyms])
                true 2273949 546850.709292:     503065 cycles:      7f2446d97c03 _dl_map_object_deps+0x973 (/usr/lib/x86_64-linux-gnu/ld-linux-x86-64.so.2)

   - In addition to 'period' (PERF_SAMPLE_PERIOD), the other
     PERF_SAMPLE_ can be used for filtering, and also some other sample
     accessible values, from tools/perf/Documentation/perf-record.txt:

        Essentially the BPF filter expression is:

        <term> <operator> <value> (("," | "||") <term> <operator> <value>)*

     The <term> can be one of:
        ip, id, tid, pid, cpu, time, addr, period, txn, weight, phys_addr,
        code_pgsz, data_pgsz, weight1, weight2, weight3, ins_lat, retire_lat,
        p_stage_cyc, mem_op, mem_lvl, mem_snoop, mem_remote, mem_lock,
        mem_dtlb, mem_blk, mem_hops

     The <operator> can be one of:
        ==, !=, >, >=, <, <=, &

     The <value> can be one of:
        <number> (for any term)
        na, load, store, pfetch, exec (for mem_op)
        l1, l2, l3, l4, cxl, io, any_cache, lfb, ram, pmem (for mem_lvl)
        na, none, hit, miss, hitm, fwd, peer (for mem_snoop)
        remote (for mem_remote)
        na, locked (for mem_locked)
        na, l1_hit, l1_miss, l2_hit, l2_miss, any_hit, any_miss, walk, fault (for mem_dtlb)
        na, by_data, by_addr (for mem_blk)
        hops0, hops1, hops2, hops3 (for mem_hops)

  perf lock contention:

   - Show lock type with address.

   - Track and show mmap_lock, siglock and per-cpu rq_lock with address.
     This is done for mmap_lock by following the current->mm pointer:

      $ sudo ./perf lock con -abl -- sleep 10
       contended   total wait     max wait     avg wait            address   symbol
       ...
           16344    312.30 ms      2.22 ms     19.11 us   ffff8cc702595640
           17686    310.08 ms      1.49 ms     17.53 us   ffff8cc7025952c0
               3     84.14 ms     45.79 ms     28.05 ms   ffff8cc78114c478   mmap_lock
            3557     76.80 ms     68.75 us     21.59 us   ffff8cc77ca3af58
               1     68.27 ms     68.27 ms     68.27 ms   ffff8cda745dfd70
               9     54.53 ms      7.96 ms      6.06 ms   ffff8cc7642a48b8   mmap_lock
           14629     44.01 ms     60.00 us      3.01 us   ffff8cc7625f9ca0
            3481     42.63 ms    140.71 us     12.24 us   ffffffff937906ac   vmap_area_lock
           16194     38.73 ms     42.15 us      2.39 us   ffff8cd397cbc560
              11     38.44 ms     10.39 ms      3.49 ms   ffff8ccd6d12fbb8   mmap_lock
               1      5.43 ms      5.43 ms      5.43 ms   ffff8cd70018f0d8
            1674      5.38 ms    422.93 us      3.21 us   ffffffff92e06080   tasklist_lock
             581      4.51 ms    130.68 us      7.75 us   ffff8cc9b1259058
               5      3.52 ms      1.27 ms    703.23 us   ffff8cc754510070
             112      3.47 ms     56.47 us     31.02 us   ffff8ccee38b3120
             381      3.31 ms     73.44 us      8.69 us   ffffffff93790690   purge_vmap_area_lock
             255      3.19 ms     36.35 us     12.49 us   ffff8d053ce30c80

   - Update default map size to 16384.

   - Allocate single letter option -M for --map-nr-entries, as it is
     proving being frequently used.

   - Fix struct rq lock access for older kernels with BPF's CO-RE
     (Compile once, run everywhere).

   - Fix problems found with MSAn.

  perf report/top:

   - Add inline information when using --call-graph=fp or lbr, as was
     already done to the --call-graph=dwarf callchain mode.

   - Improve the 'srcfile' sort key performance by really using an
     optimization introduced in 6.2 for the 'srcline' sort key that
     avoids calling addr2line for comparision with each sample.

  perf sched:

   - Make 'perf sched latency/map/replay' to use "sched:sched_waking"
     instead of "sched:sched_waking", consistent with 'perf record'
     since d566a9c2d482 ("perf sched: Prefer sched_waking event when it
     exists").

  perf ftrace:

   - Make system wide the default target for latency subcommand, run the
     following command then generate some network traffic and press
     control+C:

       # perf ftrace latency -T __kfree_skb
     ^C
         DURATION     |      COUNT | GRAPH                                          |
          0 - 1    us |         27 | #############                                  |
          1 - 2    us |         22 | ###########                                    |
          2 - 4    us |          8 | ####                                           |
          4 - 8    us |          5 | ##                                             |
          8 - 16   us |         24 | ############                                   |
         16 - 32   us |          2 | #                                              |
         32 - 64   us |          1 |                                                |
         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 |                                                |
       #

  perf top:

   - Add --branch-history (LBR: Last Branch Record) option, just like
     already available for 'perf record'.

   - Fix segfault in thread__comm_len() where thread->comm was being
     used outside thread->comm_lock.

  perf annotate:

   - Allow configuring objdump and addr2line in ~/.perfconfig., so that
     you can use alternative binaries, such as llvm's.

  perf kvm:

   - Add TUI mode for 'perf kvm stat report'.

  Reference counting:

   - Add reference count checking infrastructure to check for use after
     free, done to the 'cpumap', 'namespaces', 'maps' and 'map' structs,
     more to come.

     To build with it use -DREFCNT_CHECKING=1 in the make command line
     to build tools/perf. Documented at:

       https://perf.wiki.kernel.org/index.php/Reference_Count_Checking

   - The above caught, for instance, fix, present in this series:

        - Fix maps use after put in 'perf test "Share thread maps"':

          'maps' is copied from leader, but the leader is put on line 79
          and then 'maps' is used to read the reference count below - so
          a use after put, with the put of maps happening within
          thread__put.

     Fixed by reversing the order of puts so that the leader is put
     last.

   - Also several fixes were made to places where reference counts were
     not being held.

   - Make this one of the tests in 'make -C tools/perf build-test' to
     regularly build test it and to make sure no direct access to the
     reference counted structs are made, doing that via accessors to
     check the validity of the struct pointer.

  ARM64:

   - Fix 'perf report' segfault when filtering coresight traces by
     sparse lists of CPUs.

   - Add support for 'simd' as a sort field for 'perf report', to show
     ARM's NEON SIMD's predicate flags: "partial" and "empty".

  arm64 vendor events:

   - Add N1 metrics.

  Intel vendor events:

   - Add graniterapids, grandridge and sierraforrest events.

   - Refresh events for: alderlake, aldernaken, broadwell, broadwellde,
     broadwellx, cascadelakx, haswell, haswellx, icelake, icelakex,
     jaketown, meteorlake, knightslanding, sandybridge, sapphirerapids,
     silvermont, skylake, tigerlake and westmereep-dp

   - Refresh metrics for alderlake-n, broadwell, broadwellde,
     broadwellx, haswell, haswellx, icelakex, ivybridge, ivytown and
     skylakex.

  perf stat:

   - Implement --topdown using JSON metrics.

   - Add TopdownL1 JSON metric as a default if present, but disable it
     for now for some Intel hybrid architectures, a series of patches
     addressing this is being reviewed and will be submitted for v6.5.

   - Use metrics for --smi-cost.

   - Update topdown documentation.

  Vendor events (JSON) infrastructure:

   - Add support for computing and printing metric threshold values. For
     instance, here is one found in thesapphirerapids json file:

       {
           "BriefDescription": "Percentage of cycles spent in System Management Interrupts.",
           "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)",
           "MetricGroup": "smi",
           "MetricName": "smi_cycles",
           "MetricThreshold": "smi_cycles > 0.1",
           "ScaleUnit": "100%"
       },

   - Test parsing metric thresholds with the fake PMU in 'perf test
     pmu-events'.

   - Support for printing metric thresholds in 'perf list'.

   - Add --metric-no-threshold option to 'perf stat'.

   - Add rand (reverse and) and has_pmem (optane memory) support to
     metrics.

   - Sort list of input files to avoid depending on the order from
     readdir() helping in obtaining reproducible builds.

  S/390:

   - Add common metrics: - CPI (cycles per instruction), prbstate (ratio
     of instructions executed in problem state compared to total number
     of instructions), l1mp (Level one instruction and data cache misses
     per 100 instructions).

   - Add cache metrics for z13, z14, z15 and z16.

   - Add metric for TLB and cache.

  ARM:

   - Add raw decoding for SPE (Statistical Profiling Extension) v1.3 MTE
     (Memory Tagging Extension) and MOPS (Memory Operations) load/store.

  Intel PT hardware tracing:

   - Add event type names UINTR (User interrupt delivered) and UIRET
     (Exiting from user interrupt routine), documented in table 32-50
     "CFE Packet Type and Vector Fields Details" in the Intel Processor
     Trace chapter of The Intel SDM Volume 3 version 078.

   - Add support for new branch instructions ERETS and ERETU.

   - Fix CYC timestamps after standalone CBR

  ARM CoreSight hardware tracing:

   - Allow user to override timestamp and contextid settings.

   - Fix segfault in dso lookup.

   - Fix timeless decode mode detection.

   - Add separate decode paths for timeless and per-thread modes.

  auxtrace:

   - Fix address filter entire kernel size.

  Miscellaneous:

   - Fix use-after-free and unaligned bugs in the PLT handling routines.

   - Use zfree() to reduce chances of use after free.

   - Add missing 0x prefix for addresses printed in hexadecimal in 'perf
     probe'.

   - Suppress massive unsupported target platform errors in the unwind
     code.

   - Fix return incorrect build_id size in elf_read_build_id().

   - Fix 'perf scripts intel-pt-events.py' IPC output for Python 2 .

   - Add missing new parameter in kfree_skb tracepoint to the python
     scripts using it.

   - Add 'perf bench syscall fork' benchmark.

   - Add support for printing PERF_MEM_LVLNUM_UNC (Uncached access) in
     'perf mem'.

   - Fix wrong size expectation for perf test 'Setup struct
     perf_event_attr' caused by the patch adding
     perf_event_attr::config3.

   - Fix some spelling mistakes"

* tag 'perf-tools-for-v6.4-3-2023-05-06' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (365 commits)
  Revert "perf build: Make BUILD_BPF_SKEL default, rename to NO_BPF_SKEL"
  Revert "perf build: Warn for BPF skeletons if endian mismatches"
  perf metrics: Fix SEGV with --for-each-cgroup
  perf bpf skels: Stop using vmlinux.h generated from BTF, use subset of used structs + CO-RE
  perf stat: Separate bperf from bpf_profiler
  perf test record+probe_libc_inet_pton: Fix call chain match on x86_64
  perf test record+probe_libc_inet_pton: Fix call chain match on s390
  perf tracepoint: Fix memory leak in is_valid_tracepoint()
  perf cs-etm: Add fix for coresight trace for any range of CPUs
  perf build: Fix unescaped # in perf build-test
  perf unwind: Suppress massive unsupported target platform errors
  perf script: Add new parameter in kfree_skb tracepoint to the python scripts using it
  perf script: Print raw ip instead of binary offset for callchain
  perf symbols: Fix return incorrect build_id size in elf_read_build_id()
  perf list: Modify the warning message about scandirat(3)
  perf list: Fix memory leaks in print_tracepoint_events()
  perf lock contention: Rework offset calculation with BPF CO-RE
  perf lock contention: Fix struct rq lock access
  perf stat: Disable TopdownL1 on hybrid
  perf stat: Avoid SEGV on counter->name
  ...

9 files changed, 236 insertions, 52 deletions

diff --git a/tools/lib/api/io.h b/tools/lib/api/io.h
index 777c20f6b604..d5e8cf0dada0 100644
--- a/tools/lib/api/io.h
+++ b/tools/lib/api/io.h
@@ -7,7 +7,9 @@
 #ifndef __API_IO__
 #define __API_IO__
 
+#include <errno.h>
 #include <stdlib.h>
+#include <string.h>
 #include <unistd.h>
 
 struct io {
@@ -112,4 +114,47 @@ static inline int io__get_dec(struct io *io, __u64 *dec)
 	}
 }
 
+/* Read up to and including the first newline following the pattern of getline. */
+static inline ssize_t io__getline(struct io *io, char **line_out, size_t *line_len_out)
+{
+	char buf[128];
+	int buf_pos = 0;
+	char *line = NULL, *temp;
+	size_t line_len = 0;
+	int ch = 0;
+
+	/* TODO: reuse previously allocated memory. */
+	free(*line_out);
+	while (ch != '\n') {
+		ch = io__get_char(io);
+
+		if (ch < 0)
+			break;
+
+		if (buf_pos == sizeof(buf)) {
+			temp = realloc(line, line_len + sizeof(buf));
+			if (!temp)
+				goto err_out;
+			line = temp;
+			memcpy(&line[line_len], buf, sizeof(buf));
+			line_len += sizeof(buf);
+			buf_pos = 0;
+		}
+		buf[buf_pos++] = (char)ch;
+	}
+	temp = realloc(line, line_len + buf_pos + 1);
+	if (!temp)
+		goto err_out;
+	line = temp;
+	memcpy(&line[line_len], buf, buf_pos);
+	line[line_len + buf_pos] = '\0';
+	line_len += buf_pos;
+	*line_out = line;
+	*line_len_out = line_len;
+	return line_len;
+err_out:
+	free(line);
+	return -ENOMEM;
+}
+
 #endif /* __API_IO__ */
diff --git a/tools/lib/perf/Makefile b/tools/lib/perf/Makefile
index d8cad124e4c5..3a9b2140aa04 100644
--- a/tools/lib/perf/Makefile
+++ b/tools/lib/perf/Makefile
@@ -188,7 +188,7 @@ install_lib: libs
 		cp -fpR $(LIBPERF_ALL) $(DESTDIR)$(libdir_SQ)
 
 HDRS := bpf_perf.h core.h cpumap.h threadmap.h evlist.h evsel.h event.h mmap.h
-INTERNAL_HDRS := cpumap.h evlist.h evsel.h lib.h mmap.h threadmap.h xyarray.h
+INTERNAL_HDRS := cpumap.h evlist.h evsel.h lib.h mmap.h rc_check.h threadmap.h xyarray.h
 
 INSTALL_HDRS_PFX := $(DESTDIR)$(prefix)/include/perf
 INSTALL_HDRS := $(addprefix $(INSTALL_HDRS_PFX)/, $(HDRS))
diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c
index 6cd0be7c1bb4..1229b18bcdb1 100644
--- a/tools/lib/perf/cpumap.c
+++ b/tools/lib/perf/cpumap.c
@@ -10,16 +10,21 @@
 #include <ctype.h>
 #include <limits.h>
 
-static struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus)
+void perf_cpu_map__set_nr(struct perf_cpu_map *map, int nr_cpus)
 {
-	struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(struct perf_cpu) * nr_cpus);
+	RC_CHK_ACCESS(map)->nr = nr_cpus;
+}
 
-	if (cpus != NULL) {
+struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus)
+{
+	RC_STRUCT(perf_cpu_map) *cpus = malloc(sizeof(*cpus) + sizeof(struct perf_cpu) * nr_cpus);
+	struct perf_cpu_map *result;
+
+	if (ADD_RC_CHK(result, cpus)) {
 		cpus->nr = nr_cpus;
 		refcount_set(&cpus->refcnt, 1);
-
 	}
-	return cpus;
+	return result;
 }
 
 struct perf_cpu_map *perf_cpu_map__dummy_new(void)
@@ -27,7 +32,7 @@ struct perf_cpu_map *perf_cpu_map__dummy_new(void)
 	struct perf_cpu_map *cpus = perf_cpu_map__alloc(1);
 
 	if (cpus)
-		cpus->map[0].cpu = -1;
+		RC_CHK_ACCESS(cpus)->map[0].cpu = -1;
 
 	return cpus;
 }
@@ -35,23 +40,30 @@ struct perf_cpu_map *perf_cpu_map__dummy_new(void)
 static void cpu_map__delete(struct perf_cpu_map *map)
 {
 	if (map) {
-		WARN_ONCE(refcount_read(&map->refcnt) != 0,
+		WARN_ONCE(refcount_read(perf_cpu_map__refcnt(map)) != 0,
 			  "cpu_map refcnt unbalanced\n");
-		free(map);
+		RC_CHK_FREE(map);
 	}
 }
 
 struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map)
 {
-	if (map)
-		refcount_inc(&map->refcnt);
-	return map;
+	struct perf_cpu_map *result;
+
+	if (RC_CHK_GET(result, map))
+		refcount_inc(perf_cpu_map__refcnt(map));
+
+	return result;
 }
 
 void perf_cpu_map__put(struct perf_cpu_map *map)
 {
-	if (map && refcount_dec_and_test(&map->refcnt))
-		cpu_map__delete(map);
+	if (map) {
+		if (refcount_dec_and_test(perf_cpu_map__refcnt(map)))
+			cpu_map__delete(map);
+		else
+			RC_CHK_PUT(map);
+	}
 }
 
 static struct perf_cpu_map *cpu_map__default_new(void)
@@ -68,7 +80,7 @@ static struct perf_cpu_map *cpu_map__default_new(void)
 		int i;
 
 		for (i = 0; i < nr_cpus; ++i)
-			cpus->map[i].cpu = i;
+			RC_CHK_ACCESS(cpus)->map[i].cpu = i;
 	}
 
 	return cpus;
@@ -94,15 +106,15 @@ static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, const struct perf_cpu
 	int i, j;
 
 	if (cpus != NULL) {
-		memcpy(cpus->map, tmp_cpus, payload_size);
-		qsort(cpus->map, nr_cpus, sizeof(struct perf_cpu), cmp_cpu);
+		memcpy(RC_CHK_ACCESS(cpus)->map, tmp_cpus, payload_size);
+		qsort(RC_CHK_ACCESS(cpus)->map, nr_cpus, sizeof(struct perf_cpu), cmp_cpu);
 		/* Remove dups */
 		j = 0;
 		for (i = 0; i < nr_cpus; i++) {
-			if (i == 0 || cpus->map[i].cpu != cpus->map[i - 1].cpu)
-				cpus->map[j++].cpu = cpus->map[i].cpu;
+			if (i == 0 || RC_CHK_ACCESS(cpus)->map[i].cpu != RC_CHK_ACCESS(cpus)->map[i - 1].cpu)
+				RC_CHK_ACCESS(cpus)->map[j++].cpu = RC_CHK_ACCESS(cpus)->map[i].cpu;
 		}
-		cpus->nr = j;
+		perf_cpu_map__set_nr(cpus, j);
 		assert(j <= nr_cpus);
 	}
 	return cpus;
@@ -263,20 +275,20 @@ struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx)
 		.cpu = -1
 	};
 
-	if (cpus && idx < cpus->nr)
-		return cpus->map[idx];
+	if (cpus && idx < RC_CHK_ACCESS(cpus)->nr)
+		return RC_CHK_ACCESS(cpus)->map[idx];
 
 	return result;
 }
 
 int perf_cpu_map__nr(const struct perf_cpu_map *cpus)
 {
-	return cpus ? cpus->nr : 1;
+	return cpus ? RC_CHK_ACCESS(cpus)->nr : 1;
 }
 
 bool perf_cpu_map__empty(const struct perf_cpu_map *map)
 {
-	return map ? map->map[0].cpu == -1 : true;
+	return map ? RC_CHK_ACCESS(map)->map[0].cpu == -1 : true;
 }
 
 int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu)
@@ -287,10 +299,10 @@ int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu)
 		return -1;
 
 	low = 0;
-	high = cpus->nr;
+	high = RC_CHK_ACCESS(cpus)->nr;
 	while (low < high) {
 		int idx = (low + high) / 2;
-		struct perf_cpu cpu_at_idx = cpus->map[idx];
+		struct perf_cpu cpu_at_idx = RC_CHK_ACCESS(cpus)->map[idx];
 
 		if (cpu_at_idx.cpu == cpu.cpu)
 			return idx;
@@ -316,7 +328,7 @@ struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map)
 	};
 
 	// cpu_map__trim_new() qsort()s it, cpu_map__default_new() sorts it as well.
-	return map->nr > 0 ? map->map[map->nr - 1] : result;
+	return RC_CHK_ACCESS(map)->nr > 0 ? RC_CHK_ACCESS(map)->map[RC_CHK_ACCESS(map)->nr - 1] : result;
 }
 
 /** Is 'b' a subset of 'a'. */
@@ -324,15 +336,15 @@ bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu
 {
 	if (a == b || !b)
 		return true;
-	if (!a || b->nr > a->nr)
+	if (!a || RC_CHK_ACCESS(b)->nr > RC_CHK_ACCESS(a)->nr)
 		return false;
 
-	for (int i = 0, j = 0; i < a->nr; i++) {
-		if (a->map[i].cpu > b->map[j].cpu)
+	for (int i = 0, j = 0; i < RC_CHK_ACCESS(a)->nr; i++) {
+		if (RC_CHK_ACCESS(a)->map[i].cpu > RC_CHK_ACCESS(b)->map[j].cpu)
 			return false;
-		if (a->map[i].cpu == b->map[j].cpu) {
+		if (RC_CHK_ACCESS(a)->map[i].cpu == RC_CHK_ACCESS(b)->map[j].cpu) {
 			j++;
-			if (j == b->nr)
+			if (j == RC_CHK_ACCESS(b)->nr)
 				return true;
 		}
 	}
@@ -362,27 +374,27 @@ struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
 		return perf_cpu_map__get(other);
 	}
 
-	tmp_len = orig->nr + other->nr;
+	tmp_len = RC_CHK_ACCESS(orig)->nr + RC_CHK_ACCESS(other)->nr;
 	tmp_cpus = malloc(tmp_len * sizeof(struct perf_cpu));
 	if (!tmp_cpus)
 		return NULL;
 
 	/* Standard merge algorithm from wikipedia */
 	i = j = k = 0;
-	while (i < orig->nr && j < other->nr) {
-		if (orig->map[i].cpu <= other->map[j].cpu) {
-			if (orig->map[i].cpu == other->map[j].cpu)
+	while (i < RC_CHK_ACCESS(orig)->nr && j < RC_CHK_ACCESS(other)->nr) {
+		if (RC_CHK_ACCESS(orig)->map[i].cpu <= RC_CHK_ACCESS(other)->map[j].cpu) {
+			if (RC_CHK_ACCESS(orig)->map[i].cpu == RC_CHK_ACCESS(other)->map[j].cpu)
 				j++;
-			tmp_cpus[k++] = orig->map[i++];
+			tmp_cpus[k++] = RC_CHK_ACCESS(orig)->map[i++];
 		} else
-			tmp_cpus[k++] = other->map[j++];
+			tmp_cpus[k++] = RC_CHK_ACCESS(other)->map[j++];
 	}
 
-	while (i < orig->nr)
-		tmp_cpus[k++] = orig->map[i++];
+	while (i < RC_CHK_ACCESS(orig)->nr)
+		tmp_cpus[k++] = RC_CHK_ACCESS(orig)->map[i++];
 
-	while (j < other->nr)
-		tmp_cpus[k++] = other->map[j++];
+	while (j < RC_CHK_ACCESS(other)->nr)
+		tmp_cpus[k++] = RC_CHK_ACCESS(other)->map[j++];
 	assert(k <= tmp_len);
 
 	merged = cpu_map__trim_new(k, tmp_cpus);
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index 61b637f29b82..81e8b5fcd8ba 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -687,15 +687,14 @@ perf_evlist__next_mmap(struct perf_evlist *evlist, struct perf_mmap *map,
 
 void __perf_evlist__set_leader(struct list_head *list, struct perf_evsel *leader)
 {
-	struct perf_evsel *first, *last, *evsel;
-
-	first = list_first_entry(list, struct perf_evsel, node);
-	last = list_last_entry(list, struct perf_evsel, node);
-
-	leader->nr_members = last->idx - first->idx + 1;
+	struct perf_evsel *evsel;
+	int n = 0;
 
-	__perf_evlist__for_each_entry(list, evsel)
+	__perf_evlist__for_each_entry(list, evsel) {
 		evsel->leader = leader;
+		n++;
+	}
+	leader->nr_members = n;
 }
 
 void perf_evlist__set_leader(struct perf_evlist *evlist)
@@ -704,7 +703,23 @@ void perf_evlist__set_leader(struct perf_evlist *evlist)
 		struct perf_evsel *first = list_entry(evlist->entries.next,
 						struct perf_evsel, node);
 
-		evlist->nr_groups = evlist->nr_entries > 1 ? 1 : 0;
 		__perf_evlist__set_leader(&evlist->entries, first);
 	}
 }
+
+int perf_evlist__nr_groups(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+	int nr_groups = 0;
+
+	perf_evlist__for_each_evsel(evlist, evsel) {
+		/*
+		 * evsels by default have a nr_members of 1, and they are their
+		 * own leader. If the nr_members is >1 then this is an
+		 * indication of a group.
+		 */
+		if (evsel->leader == evsel && evsel->nr_members > 1)
+			nr_groups++;
+	}
+	return nr_groups;
+}
diff --git a/tools/lib/perf/include/internal/cpumap.h b/tools/lib/perf/include/internal/cpumap.h
index 35dd29642296..49649eb51ce4 100644
--- a/tools/lib/perf/include/internal/cpumap.h
+++ b/tools/lib/perf/include/internal/cpumap.h
@@ -4,6 +4,7 @@
 
 #include <linux/refcount.h>
 #include <perf/cpumap.h>
+#include <internal/rc_check.h>
 
 /**
  * A sized, reference counted, sorted array of integers representing CPU
@@ -12,7 +13,7 @@
  * gaps if CPU numbers were used. For events associated with a pid, rather than
  * a CPU, a single dummy map with an entry of -1 is used.
  */
-struct perf_cpu_map {
+DECLARE_RC_STRUCT(perf_cpu_map) {
 	refcount_t	refcnt;
 	/** Length of the map array. */
 	int		nr;
@@ -24,7 +25,14 @@ struct perf_cpu_map {
 #define MAX_NR_CPUS	2048
 #endif
 
+struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus);
 int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu);
 bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu_map *b);
 
+void perf_cpu_map__set_nr(struct perf_cpu_map *map, int nr_cpus);
+
+static inline refcount_t *perf_cpu_map__refcnt(struct perf_cpu_map *map)
+{
+	return &RC_CHK_ACCESS(map)->refcnt;
+}
 #endif /* __LIBPERF_INTERNAL_CPUMAP_H */
diff --git a/tools/lib/perf/include/internal/evlist.h b/tools/lib/perf/include/internal/evlist.h
index 850f07070036..3339bc2f1765 100644
--- a/tools/lib/perf/include/internal/evlist.h
+++ b/tools/lib/perf/include/internal/evlist.h
@@ -17,7 +17,6 @@ struct perf_mmap_param;
 struct perf_evlist {
 	struct list_head	 entries;
 	int			 nr_entries;
-	int			 nr_groups;
 	bool			 has_user_cpus;
 	bool			 needs_map_propagation;
 	/**
diff --git a/tools/lib/perf/include/internal/rc_check.h b/tools/lib/perf/include/internal/rc_check.h
new file mode 100644
index 000000000000..d5d771ccdc7b
--- /dev/null
+++ b/tools/lib/perf/include/internal/rc_check.h
@@ -0,0 +1,102 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#ifndef __LIBPERF_INTERNAL_RC_CHECK_H
+#define __LIBPERF_INTERNAL_RC_CHECK_H
+
+#include <stdlib.h>
+#include <linux/zalloc.h>
+
+/*
+ * Enable reference count checking implicitly with leak checking, which is
+ * integrated into address sanitizer.
+ */
+#if defined(LEAK_SANITIZER) || defined(ADDRESS_SANITIZER)
+#define REFCNT_CHECKING 1
+#endif
+
+/*
+ * Shared reference count checking macros.
+ *
+ * Reference count checking is an approach to sanitizing the use of reference
+ * counted structs. It leverages address and leak sanitizers to make sure gets
+ * are paired with a put. Reference count checking adds a malloc-ed layer of
+ * indirection on a get, and frees it on a put. A missed put will be reported as
+ * a memory leak. A double put will be reported as a double free. Accessing
+ * after a put will cause a use-after-free and/or a segfault.
+ */
+
+#ifndef REFCNT_CHECKING
+/* Replaces "struct foo" so that the pointer may be interposed. */
+#define DECLARE_RC_STRUCT(struct_name)		\
+	struct struct_name
+
+/* Declare a reference counted struct variable. */
+#define RC_STRUCT(struct_name) struct struct_name
+
+/*
+ * Interpose the indirection. Result will hold the indirection and object is the
+ * reference counted struct.
+ */
+#define ADD_RC_CHK(result, object) (result = object, object)
+
+/* Strip the indirection layer. */
+#define RC_CHK_ACCESS(object) object
+
+/* Frees the object and the indirection layer. */
+#define RC_CHK_FREE(object) free(object)
+
+/* A get operation adding the indirection layer. */
+#define RC_CHK_GET(result, object) ADD_RC_CHK(result, object)
+
+/* A put operation removing the indirection layer. */
+#define RC_CHK_PUT(object) {}
+
+#else
+
+/* Replaces "struct foo" so that the pointer may be interposed. */
+#define DECLARE_RC_STRUCT(struct_name)			\
+	struct original_##struct_name;			\
+	struct struct_name {				\
+		struct original_##struct_name *orig;	\
+	};						\
+	struct original_##struct_name
+
+/* Declare a reference counted struct variable. */
+#define RC_STRUCT(struct_name) struct original_##struct_name
+
+/*
+ * Interpose the indirection. Result will hold the indirection and object is the
+ * reference counted struct.
+ */
+#define ADD_RC_CHK(result, object)					\
+	(								\
+		object ? (result = malloc(sizeof(*result)),		\
+			result ? (result->orig = object, result)	\
+			: (result = NULL, NULL))			\
+		: (result = NULL, NULL)					\
+		)
+
+/* Strip the indirection layer. */
+#define RC_CHK_ACCESS(object) object->orig
+
+/* Frees the object and the indirection layer. */
+#define RC_CHK_FREE(object)			\
+	do {					\
+		zfree(&object->orig);		\
+		free(object);			\
+	} while(0)
+
+/* A get operation adding the indirection layer. */
+#define RC_CHK_GET(result, object) ADD_RC_CHK(result, (object ? object->orig : NULL))
+
+/* A put operation removing the indirection layer. */
+#define RC_CHK_PUT(object)			\
+	do {					\
+		if (object) {			\
+			object->orig = NULL;	\
+			free(object);		\
+		}				\
+	} while(0)
+
+#endif
+
+#endif /* __LIBPERF_INTERNAL_RC_CHECK_H */
diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h
index ad47d7b31046..51b9338f4c11 100644
--- a/tools/lib/perf/include/perf/event.h
+++ b/tools/lib/perf/include/perf/event.h
@@ -70,6 +70,8 @@ struct perf_record_lost {
 	__u64			 lost;
 };
 
+#define PERF_RECORD_MISC_LOST_SAMPLES_BPF (1 << 15)
+
 struct perf_record_lost_samples {
 	struct perf_event_header header;
 	__u64			 lost;
diff --git a/tools/lib/perf/include/perf/evlist.h b/tools/lib/perf/include/perf/evlist.h
index 9ca399d49bb4..e894b770779e 100644
--- a/tools/lib/perf/include/perf/evlist.h
+++ b/tools/lib/perf/include/perf/evlist.h
@@ -47,4 +47,5 @@ LIBPERF_API struct perf_mmap *perf_evlist__next_mmap(struct perf_evlist *evlist,
 	     (pos) = perf_evlist__next_mmap((evlist), (pos), overwrite))
 
 LIBPERF_API void perf_evlist__set_leader(struct perf_evlist *evlist);
+LIBPERF_API int perf_evlist__nr_groups(struct perf_evlist *evlist);
 #endif /* __LIBPERF_EVLIST_H */