Merge tag 'perf-tools-for-v6.5-1-2023-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools-next

Pull perf tools updates from Namhyung Kim:
 "Internal cleanup:

   - Refactor PMU data management to handle hybrid systems in a generic
     way.

     Do more work in the lexer so that legacy event types parse more
     easily. A side-effect of this is that if a PMU is specified,
     scanning sysfs is avoided improving start-up time.

   - Fix hybrid metrics, for example, the TopdownL1 works for both
     performance and efficiency cores on Intel machines. To support
     this, sort and regroup events after parsing.

   - Add reference count checking for the 'thread' data structure.

   - Lots of fixes for memory leaks in various places thanks to the ASAN
     and Ian's refcount checker.

   - Reduce the binary size by replacing static variables with local or
     dynamically allocated memory.

   - Introduce shared_mutex for annotate data to reduce memory
     footprint.

   - Make filesystem access library functions more thread safe.

  Test:

   - Organize cpu_map tests into a single suite.

   - Add metric value validation test to check if the values are within
     correct value ranges.

   - Add perf stat stdio output test to check if event and metric names
     match.

   - Add perf data converter JSON output test.

   - Fix a lot of issues reported by shellcheck(1). This is a
     preparation to enable shellcheck by default.

   - Make the large x86 new instructions test optional at build time
     using EXTRA_TESTS=1.

   - Add a test for libpfm4 events.

  perf script:

   - Add 'dsoff' outpuf field to display offset from the DSO.

      $ perf script -F comm,pid,event,ip,dsoff
         ls 2695501 cycles:      152cc73ef4b5 (/usr/lib/x86_64-linux-gnu/ld-2.31.so+0x1c4b5)
         ls 2695501 cycles:  ffffffff99045b3e ([kernel.kallsyms])
         ls 2695501 cycles:  ffffffff9968e107 ([kernel.kallsyms])
         ls 2695501 cycles:  ffffffffc1f54afb ([kernel.kallsyms])
         ls 2695501 cycles:  ffffffff9968382f ([kernel.kallsyms])
         ls 2695501 cycles:  ffffffff99e00094 ([kernel.kallsyms])
         ls 2695501 cycles:      152cc718a8d0 (/usr/lib/x86_64-linux-gnu/libselinux.so.1+0x68d0)
         ls 2695501 cycles:  ffffffff992a6db0 ([kernel.kallsyms])

   - Adjust width for large PID/TID values.

  perf report:

   - Robustify reading addr2line output for srcline by checking sentinel
     output before the actual data and by using timeout of 1 second.

   - Allow config terms (like 'name=ABC') with breakpoint events.

      $ perf record -e mem:0x55feb98dd169:x/name=breakpoint/ -p 19646 -- sleep 1

  perf annotate:

   - Handle x86 instruction suffix like 'l' in 'movl' generally.

   - Parse instruction operands properly even with a whitespace. This is
     needed for llvm-objdump output.

   - Support RISC-V binutils lookup using the triplet prefixes.

   - Add '<' and '>' key to navigate to prev/next symbols in TUI.

   - Fix instruction association and parsing for LoongArch.

  perf stat:

   - Add --per-cache aggregation option, optionally specify a cache
     level like `--per-cache=L2`.

      $ sudo perf stat --per-cache -a -e ls_dmnd_fills_from_sys.ext_cache_remote --\
        taskset -c 0-15,64-79,128-143,192-207\
        perf bench sched messaging -p -t -l 100000 -g 8

        # Running 'sched/messaging' benchmark:
        # 20 sender and receiver threads per group
        # 8 groups == 320 threads run

        Total time: 7.648 [sec]

        Performance counter stats for 'system wide':

        S0-D0-L3-ID0             16         17,145,912      ls_dmnd_fills_from_sys.ext_cache_remote
        S0-D0-L3-ID8             16         14,977,628      ls_dmnd_fills_from_sys.ext_cache_remote
        S0-D0-L3-ID16            16            262,539      ls_dmnd_fills_from_sys.ext_cache_remote
        S0-D0-L3-ID24            16              3,140      ls_dmnd_fills_from_sys.ext_cache_remote
        S0-D0-L3-ID32            16             27,403      ls_dmnd_fills_from_sys.ext_cache_remote
        S0-D0-L3-ID40            16             17,026      ls_dmnd_fills_from_sys.ext_cache_remote
        S0-D0-L3-ID48            16              7,292      ls_dmnd_fills_from_sys.ext_cache_remote
        S0-D0-L3-ID56            16              2,464      ls_dmnd_fills_from_sys.ext_cache_remote
        S1-D1-L3-ID64            16         22,489,306      ls_dmnd_fills_from_sys.ext_cache_remote
        S1-D1-L3-ID72            16         21,455,257      ls_dmnd_fills_from_sys.ext_cache_remote
        S1-D1-L3-ID80            16             11,619      ls_dmnd_fills_from_sys.ext_cache_remote
        S1-D1-L3-ID88            16             30,978      ls_dmnd_fills_from_sys.ext_cache_remote
        S1-D1-L3-ID96            16             37,628      ls_dmnd_fills_from_sys.ext_cache_remote
        S1-D1-L3-ID104           16             13,594      ls_dmnd_fills_from_sys.ext_cache_remote
        S1-D1-L3-ID112           16             10,164      ls_dmnd_fills_from_sys.ext_cache_remote
        S1-D1-L3-ID120           16             11,259      ls_dmnd_fills_from_sys.ext_cache_remote

              7.779171484 seconds time elapsed

   - Change default (no event/metric) formatting for default metrics so
     that events are hidden and the metric and group appear.

       Performance counter stats for 'ls /':

                    1.85 msec task-clock                       #    0.594 CPUs utilized
                       0      context-switches                 #    0.000 /sec
                       0      cpu-migrations                   #    0.000 /sec
                      97      page-faults                      #   52.517 K/sec
               2,187,173      cycles                           #    1.184 GHz
               2,474,459      instructions                     #    1.13  insn per cycle
                 531,584      branches                         #  287.805 M/sec
                  13,626      branch-misses                    #    2.56% of all branches
                              TopdownL1                 #     23.5 %  tma_backend_bound
                                                        #     11.5 %  tma_bad_speculation
                                                        #     39.1 %  tma_frontend_bound
                                                        #     25.9 %  tma_retiring

   - Allow --cputype option to have any PMU name (not just hybrid).

   - Fix output value not to added when it runs multiple times with -r
     option.

  perf list:

   - Show metricgroup description from JSON file called
     metricgroups.json.

   - Allow 'pfm' argument to list only libpfm4 events and check each
     event is supported before showing it.

  JSON vendor events:

   - Avoid event grouping using "NO_GROUP_EVENTS" constraints. The
     topdown events are correctly grouped even if no group exists.

   - Add "Default" metric group to print it in the default output. And
     use "DefaultMetricgroupName" to indicate the real metric group
     name.

   - Add AmpereOne core PMU events.

  Misc:

   - Define man page date correctly.

   - Track exception level properly on ARM CoreSight ETM.

   - Allow anonymous struct, union or enum when retrieving type names
     from DWARF.

   - Fix incorrect filename when calling `perf inject --jit`.

   - Handle PLT size correctly on LoongArch"

* tag 'perf-tools-for-v6.5-1-2023-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools-next: (269 commits)
  perf test: Skip metrics w/o event name in stat STD output linter
  perf test: Reorder event name checks in stat STD output linter
  perf pmu: Remove a hard coded cpu PMU assumption
  perf pmus: Add notion of default PMU for JSON events
  perf unwind: Fix map reference counts
  perf test: Set PERF_EXEC_PATH for script execution
  perf script: Initialize buffer for regs_map()
  perf tests: Fix test_arm_callgraph_fp variable expansion
  perf symbol: Add LoongArch case in get_plt_sizes()
  perf test: Remove x permission from lib/stat_output.sh
  perf test: Rerun failed metrics with longer workload
  perf test: Add skip list for metrics known would fail
  perf test: Add metric value validation test
  perf jit: Fix incorrect file name in DWARF line table
  perf annotate: Fix instruction association and parsing for LoongArch
  perf annotation: Switch lock from a mutex to a sharded_mutex
  perf sharded_mutex: Introduce sharded_mutex
  tools: Fix incorrect calculation of object size by sizeof
  perf subcmd: Fix missing check for return value of malloc() in add_cmdname()
  perf parse-events: Remove unneeded semicolon
  ...

11 files changed, 325 insertions, 195 deletions

diff --git a/tools/lib/api/fs/cgroup.c b/tools/lib/api/fs/cgroup.c
index 1573dae4259d97..250629a0942336 100644
--- a/tools/lib/api/fs/cgroup.c
+++ b/tools/lib/api/fs/cgroup.c
@@ -14,7 +14,7 @@ struct cgroupfs_cache_entry {
 };
 
 /* just cache last used one */
-static struct cgroupfs_cache_entry cached;
+static struct cgroupfs_cache_entry *cached;
 
 int cgroupfs_find_mountpoint(char *buf, size_t maxlen, const char *subsys)
 {
@@ -24,9 +24,9 @@ int cgroupfs_find_mountpoint(char *buf, size_t maxlen, const char *subsys)
 	char *p, *path;
 	char mountpoint[PATH_MAX];
 
-	if (!strcmp(cached.subsys, subsys)) {
-		if (strlen(cached.mountpoint) < maxlen) {
-			strcpy(buf, cached.mountpoint);
+	if (cached && !strcmp(cached->subsys, subsys)) {
+		if (strlen(cached->mountpoint) < maxlen) {
+			strcpy(buf, cached->mountpoint);
 			return 0;
 		}
 		return -1;
@@ -91,8 +91,13 @@ int cgroupfs_find_mountpoint(char *buf, size_t maxlen, const char *subsys)
 	free(line);
 	fclose(fp);
 
-	strncpy(cached.subsys, subsys, sizeof(cached.subsys) - 1);
-	strcpy(cached.mountpoint, mountpoint);
+	if (!cached)
+		cached = calloc(1, sizeof(*cached));
+
+	if (cached) {
+		strncpy(cached->subsys, subsys, sizeof(cached->subsys) - 1);
+		strcpy(cached->mountpoint, mountpoint);
+	}
 
 	if (mountpoint[0] && strlen(mountpoint) < maxlen) {
 		strcpy(buf, mountpoint);
diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
index 82f53d81a7a784..5cb0eeec2c8a6c 100644
--- a/tools/lib/api/fs/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <assert.h>
 #include <ctype.h>
 #include <errno.h>
 #include <limits.h>
@@ -10,6 +11,7 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
+#include <pthread.h>
 #include <unistd.h>
 #include <sys/mount.h>
 
@@ -43,7 +45,7 @@
 #define BPF_FS_MAGIC           0xcafe4a11
 #endif
 
-static const char * const sysfs__fs_known_mountpoints[] = {
+static const char * const sysfs__known_mountpoints[] = {
 	"/sys",
 	0,
 };
@@ -86,87 +88,89 @@ static const char * const bpf_fs__known_mountpoints[] = {
 };
 
 struct fs {
-	const char		*name;
-	const char * const	*mounts;
-	char			 path[PATH_MAX];
-	bool			 found;
-	bool			 checked;
-	long			 magic;
-};
-
-enum {
-	FS__SYSFS   = 0,
-	FS__PROCFS  = 1,
-	FS__DEBUGFS = 2,
-	FS__TRACEFS = 3,
-	FS__HUGETLBFS = 4,
-	FS__BPF_FS = 5,
+	const char *		 const name;
+	const char * const *	 const mounts;
+	char			*path;
+	pthread_mutex_t		 mount_mutex;
+	const long		 magic;
 };
 
 #ifndef TRACEFS_MAGIC
 #define TRACEFS_MAGIC 0x74726163
 #endif
 
-static struct fs fs__entries[] = {
-	[FS__SYSFS] = {
-		.name	= "sysfs",
-		.mounts	= sysfs__fs_known_mountpoints,
-		.magic	= SYSFS_MAGIC,
-		.checked = false,
-	},
-	[FS__PROCFS] = {
-		.name	= "proc",
-		.mounts	= procfs__known_mountpoints,
-		.magic	= PROC_SUPER_MAGIC,
-		.checked = false,
-	},
-	[FS__DEBUGFS] = {
-		.name	= "debugfs",
-		.mounts	= debugfs__known_mountpoints,
-		.magic	= DEBUGFS_MAGIC,
-		.checked = false,
-	},
-	[FS__TRACEFS] = {
-		.name	= "tracefs",
-		.mounts	= tracefs__known_mountpoints,
-		.magic	= TRACEFS_MAGIC,
-		.checked = false,
-	},
-	[FS__HUGETLBFS] = {
-		.name	= "hugetlbfs",
-		.mounts = hugetlbfs__known_mountpoints,
-		.magic	= HUGETLBFS_MAGIC,
-		.checked = false,
-	},
-	[FS__BPF_FS] = {
-		.name	= "bpf",
-		.mounts = bpf_fs__known_mountpoints,
-		.magic	= BPF_FS_MAGIC,
-		.checked = false,
-	},
-};
+static void fs__init_once(struct fs *fs);
+static const char *fs__mountpoint(const struct fs *fs);
+static const char *fs__mount(struct fs *fs);
+
+#define FS(lower_name, fs_name, upper_name)		\
+static struct fs fs__##lower_name = {			\
+	.name = #fs_name,				\
+	.mounts = lower_name##__known_mountpoints,	\
+	.magic = upper_name##_MAGIC,			\
+	.mount_mutex = PTHREAD_MUTEX_INITIALIZER,	\
+};							\
+							\
+static void lower_name##_init_once(void)		\
+{							\
+	struct fs *fs = &fs__##lower_name;		\
+							\
+	fs__init_once(fs);				\
+}							\
+							\
+const char *lower_name##__mountpoint(void)		\
+{							\
+	static pthread_once_t init_once = PTHREAD_ONCE_INIT;	\
+	struct fs *fs = &fs__##lower_name;		\
+							\
+	pthread_once(&init_once, lower_name##_init_once);	\
+	return fs__mountpoint(fs);			\
+}							\
+							\
+const char *lower_name##__mount(void)			\
+{							\
+	const char *mountpoint = lower_name##__mountpoint();	\
+	struct fs *fs = &fs__##lower_name;		\
+							\
+	if (mountpoint)					\
+		return mountpoint;			\
+							\
+	return fs__mount(fs);				\
+}							\
+							\
+bool lower_name##__configured(void)			\
+{							\
+	return lower_name##__mountpoint() != NULL;	\
+}
+
+FS(sysfs, sysfs, SYSFS);
+FS(procfs, procfs, PROC_SUPER);
+FS(debugfs, debugfs, DEBUGFS);
+FS(tracefs, tracefs, TRACEFS);
+FS(hugetlbfs, hugetlbfs, HUGETLBFS);
+FS(bpf_fs, bpf, BPF_FS);
 
 static bool fs__read_mounts(struct fs *fs)
 {
-	bool found = false;
 	char type[100];
 	FILE *fp;
+	char path[PATH_MAX + 1];
 
 	fp = fopen("/proc/mounts", "r");
 	if (fp == NULL)
-		return NULL;
+		return false;
 
-	while (!found &&
-	       fscanf(fp, "%*s %" STR(PATH_MAX) "s %99s %*s %*d %*d\n",
-		      fs->path, type) == 2) {
+	while (fscanf(fp, "%*s %" STR(PATH_MAX) "s %99s %*s %*d %*d\n",
+		      path, type) == 2) {
 
-		if (strcmp(type, fs->name) == 0)
-			found = true;
+		if (strcmp(type, fs->name) == 0) {
+			fs->path = strdup(path);
+			fclose(fp);
+			return fs->path != NULL;
+		}
 	}
-
 	fclose(fp);
-	fs->checked = true;
-	return fs->found = found;
+	return false;
 }
 
 static int fs__valid_mount(const char *fs, long magic)
@@ -188,8 +192,9 @@ static bool fs__check_mounts(struct fs *fs)
 	ptr = fs->mounts;
 	while (*ptr) {
 		if (fs__valid_mount(*ptr, fs->magic) == 0) {
-			fs->found = true;
-			strcpy(fs->path, *ptr);
+			fs->path = strdup(*ptr);
+			if (!fs->path)
+				return false;
 			return true;
 		}
 		ptr++;
@@ -227,43 +232,26 @@ static bool fs__env_override(struct fs *fs)
 	if (!override_path)
 		return false;
 
-	fs->found = true;
-	fs->checked = true;
-	strncpy(fs->path, override_path, sizeof(fs->path) - 1);
-	fs->path[sizeof(fs->path) - 1] = '\0';
+	fs->path = strdup(override_path);
+	if (!fs->path)
+		return false;
 	return true;
 }
 
-static const char *fs__get_mountpoint(struct fs *fs)
+static void fs__init_once(struct fs *fs)
 {
-	if (fs__env_override(fs))
-		return fs->path;
-
-	if (fs__check_mounts(fs))
-		return fs->path;
-
-	if (fs__read_mounts(fs))
-		return fs->path;
-
-	return NULL;
+	if (!fs__env_override(fs) &&
+	    !fs__check_mounts(fs) &&
+	    !fs__read_mounts(fs)) {
+		assert(!fs->path);
+	} else {
+		assert(fs->path);
+	}
 }
 
-static const char *fs__mountpoint(int idx)
+static const char *fs__mountpoint(const struct fs *fs)
 {
-	struct fs *fs = &fs__entries[idx];
-
-	if (fs->found)
-		return (const char *)fs->path;
-
-	/* the mount point was already checked for the mount point
-	 * but and did not exist, so return NULL to avoid scanning again.
-	 * This makes the found and not found paths cost equivalent
-	 * in case of multiple calls.
-	 */
-	if (fs->checked)
-		return NULL;
-
-	return fs__get_mountpoint(fs);
+	return fs->path;
 }
 
 static const char *mount_overload(struct fs *fs)
@@ -278,45 +266,29 @@ static const char *mount_overload(struct fs *fs)
 	return getenv(upper_name) ?: *fs->mounts;
 }
 
-static const char *fs__mount(int idx)
+static const char *fs__mount(struct fs *fs)
 {
-	struct fs *fs = &fs__entries[idx];
 	const char *mountpoint;
 
-	if (fs__mountpoint(idx))
-		return (const char *)fs->path;
+	pthread_mutex_lock(&fs->mount_mutex);
 
-	mountpoint = mount_overload(fs);
+	/* Check if path found inside the mutex to avoid races with other callers of mount. */
+	mountpoint = fs__mountpoint(fs);
+	if (mountpoint)
+		goto out;
 
-	if (mount(NULL, mountpoint, fs->name, 0, NULL) < 0)
-		return NULL;
-
-	return fs__check_mounts(fs) ? fs->path : NULL;
-}
+	mountpoint = mount_overload(fs);
 
-#define FS(name, idx)				\
-const char *name##__mountpoint(void)		\
-{						\
-	return fs__mountpoint(idx);		\
-}						\
-						\
-const char *name##__mount(void)			\
-{						\
-	return fs__mount(idx);			\
-}						\
-						\
-bool name##__configured(void)			\
-{						\
-	return name##__mountpoint() != NULL;	\
+	if (mount(NULL, mountpoint, fs->name, 0, NULL) == 0 &&
+	    fs__valid_mount(mountpoint, fs->magic) == 0) {
+		fs->path = strdup(mountpoint);
+		mountpoint = fs->path;
+	}
+out:
+	pthread_mutex_unlock(&fs->mount_mutex);
+	return mountpoint;
 }
 
-FS(sysfs,   FS__SYSFS);
-FS(procfs,  FS__PROCFS);
-FS(debugfs, FS__DEBUGFS);
-FS(tracefs, FS__TRACEFS);
-FS(hugetlbfs, FS__HUGETLBFS);
-FS(bpf_fs, FS__BPF_FS);
-
 int filename__read_int(const char *filename, int *value)
 {
 	char line[64];
diff --git a/tools/lib/api/fs/tracing_path.c b/tools/lib/api/fs/tracing_path.c
index 7ba3e81274e85a..30745f35d0d2db 100644
--- a/tools/lib/api/fs/tracing_path.c
+++ b/tools/lib/api/fs/tracing_path.c
@@ -13,17 +13,12 @@
 
 #include "tracing_path.h"
 
-static char tracing_mnt[PATH_MAX]  = "/sys/kernel/debug";
 static char tracing_path[PATH_MAX]        = "/sys/kernel/tracing";
-static char tracing_events_path[PATH_MAX] = "/sys/kernel/tracing/events";
 
 static void __tracing_path_set(const char *tracing, const char *mountpoint)
 {
-	snprintf(tracing_mnt, sizeof(tracing_mnt), "%s", mountpoint);
 	snprintf(tracing_path, sizeof(tracing_path), "%s/%s",
 		 mountpoint, tracing);
-	snprintf(tracing_events_path, sizeof(tracing_events_path), "%s/%s%s",
-		 mountpoint, tracing, "events");
 }
 
 static const char *tracing_path_tracefs_mount(void)
@@ -149,15 +144,15 @@ int tracing_path__strerror_open_tp(int err, char *buf, size_t size,
 			/* sdt markers */
 			if (!strncmp(filename, "sdt_", 4)) {
 				snprintf(buf, size,
-					"Error:\tFile %s/%s not found.\n"
+					"Error:\tFile %s/events/%s not found.\n"
 					"Hint:\tSDT event cannot be directly recorded on.\n"
 					"\tPlease first use 'perf probe %s:%s' before recording it.\n",
-					tracing_events_path, filename, sys, name);
+					tracing_path, filename, sys, name);
 			} else {
 				snprintf(buf, size,
-					 "Error:\tFile %s/%s not found.\n"
+					 "Error:\tFile %s/events/%s not found.\n"
 					 "Hint:\tPerhaps this kernel misses some CONFIG_ setting to enable this feature?.\n",
-					 tracing_events_path, filename);
+					 tracing_path, filename);
 			}
 			break;
 		}
@@ -169,9 +164,9 @@ int tracing_path__strerror_open_tp(int err, char *buf, size_t size,
 		break;
 	case EACCES: {
 		snprintf(buf, size,
-			 "Error:\tNo permissions to read %s/%s\n"
+			 "Error:\tNo permissions to read %s/events/%s\n"
 			 "Hint:\tTry 'sudo mount -o remount,mode=755 %s'\n",
-			 tracing_events_path, filename, tracing_path_mount());
+			 tracing_path, filename, tracing_path_mount());
 	}
 		break;
 	default:
diff --git a/tools/lib/api/io.h b/tools/lib/api/io.h
index d5e8cf0dada0de..9fc429d2852d78 100644
--- a/tools/lib/api/io.h
+++ b/tools/lib/api/io.h
@@ -8,6 +8,7 @@
 #define __API_IO__
 
 #include <errno.h>
+#include <poll.h>
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
@@ -23,6 +24,8 @@ struct io {
 	char *end;
 	/* Currently accessed data pointer. */
 	char *data;
+	/* Read timeout, 0 implies no timeout. */
+	int timeout_ms;
 	/* Set true on when the end of file on read error. */
 	bool eof;
 };
@@ -35,6 +38,7 @@ static inline void io__init(struct io *io, int fd,
 	io->buf = buf;
 	io->end = buf;
 	io->data = buf;
+	io->timeout_ms = 0;
 	io->eof = false;
 }
 
@@ -47,7 +51,29 @@ static inline int io__get_char(struct io *io)
 		return -1;
 
 	if (ptr == io->end) {
-		ssize_t n = read(io->fd, io->buf, io->buf_len);
+		ssize_t n;
+
+		if (io->timeout_ms != 0) {
+			struct pollfd pfds[] = {
+				{
+					.fd = io->fd,
+					.events = POLLIN,
+				},
+			};
+
+			n = poll(pfds, 1, io->timeout_ms);
+			if (n == 0)
+				errno = ETIMEDOUT;
+			if (n > 0 && !(pfds[0].revents & POLLIN)) {
+				errno = EIO;
+				n = -1;
+			}
+			if (n <= 0) {
+				io->eof = true;
+				return -1;
+			}
+		}
+		n = read(io->fd, io->buf, io->buf_len);
 
 		if (n <= 0) {
 			io->eof = true;
diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c
index 1229b18bcdb168..2a5a292173740b 100644
--- a/tools/lib/perf/cpumap.c
+++ b/tools/lib/perf/cpumap.c
@@ -99,6 +99,11 @@ static int cmp_cpu(const void *a, const void *b)
 	return cpu_a->cpu - cpu_b->cpu;
 }
 
+static struct perf_cpu __perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx)
+{
+	return RC_CHK_ACCESS(cpus)->map[idx];
+}
+
 static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, const struct perf_cpu *tmp_cpus)
 {
 	size_t payload_size = nr_cpus * sizeof(struct perf_cpu);
@@ -111,8 +116,12 @@ static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, const struct perf_cpu
 		/* Remove dups */
 		j = 0;
 		for (i = 0; i < nr_cpus; i++) {
-			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;
+			if (i == 0 ||
+			    __perf_cpu_map__cpu(cpus, i).cpu !=
+			    __perf_cpu_map__cpu(cpus, i - 1).cpu) {
+				RC_CHK_ACCESS(cpus)->map[j++].cpu =
+					__perf_cpu_map__cpu(cpus, i).cpu;
+			}
 		}
 		perf_cpu_map__set_nr(cpus, j);
 		assert(j <= nr_cpus);
@@ -269,26 +278,31 @@ out:
 	return cpus;
 }
 
+static int __perf_cpu_map__nr(const struct perf_cpu_map *cpus)
+{
+	return RC_CHK_ACCESS(cpus)->nr;
+}
+
 struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx)
 {
 	struct perf_cpu result = {
 		.cpu = -1
 	};
 
-	if (cpus && idx < RC_CHK_ACCESS(cpus)->nr)
-		return RC_CHK_ACCESS(cpus)->map[idx];
+	if (cpus && idx < __perf_cpu_map__nr(cpus))
+		return __perf_cpu_map__cpu(cpus, idx);
 
 	return result;
 }
 
 int perf_cpu_map__nr(const struct perf_cpu_map *cpus)
 {
-	return cpus ? RC_CHK_ACCESS(cpus)->nr : 1;
+	return cpus ? __perf_cpu_map__nr(cpus) : 1;
 }
 
 bool perf_cpu_map__empty(const struct perf_cpu_map *map)
 {
-	return map ? RC_CHK_ACCESS(map)->map[0].cpu == -1 : true;
+	return map ? __perf_cpu_map__cpu(map, 0).cpu == -1 : true;
 }
 
 int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu)
@@ -299,10 +313,10 @@ int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu)
 		return -1;
 
 	low = 0;
-	high = RC_CHK_ACCESS(cpus)->nr;
+	high = __perf_cpu_map__nr(cpus);
 	while (low < high) {
 		int idx = (low + high) / 2;
-		struct perf_cpu cpu_at_idx = RC_CHK_ACCESS(cpus)->map[idx];
+		struct perf_cpu cpu_at_idx = __perf_cpu_map__cpu(cpus, idx);
 
 		if (cpu_at_idx.cpu == cpu.cpu)
 			return idx;
@@ -321,6 +335,32 @@ bool perf_cpu_map__has(const struct perf_cpu_map *cpus, struct perf_cpu cpu)
 	return perf_cpu_map__idx(cpus, cpu) != -1;
 }
 
+bool perf_cpu_map__equal(const struct perf_cpu_map *lhs, const struct perf_cpu_map *rhs)
+{
+	int nr;
+
+	if (lhs == rhs)
+		return true;
+
+	if (!lhs || !rhs)
+		return false;
+
+	nr = __perf_cpu_map__nr(lhs);
+	if (nr != __perf_cpu_map__nr(rhs))
+		return false;
+
+	for (int idx = 0; idx < nr; idx++) {
+		if (__perf_cpu_map__cpu(lhs, idx).cpu != __perf_cpu_map__cpu(rhs, idx).cpu)
+			return false;
+	}
+	return true;
+}
+
+bool perf_cpu_map__has_any_cpu(const struct perf_cpu_map *map)
+{
+	return map && __perf_cpu_map__cpu(map, 0).cpu == -1;
+}
+
 struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map)
 {
 	struct perf_cpu result = {
@@ -328,7 +368,9 @@ 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 RC_CHK_ACCESS(map)->nr > 0 ? RC_CHK_ACCESS(map)->map[RC_CHK_ACCESS(map)->nr - 1] : result;
+	return __perf_cpu_map__nr(map) > 0
+		? __perf_cpu_map__cpu(map, __perf_cpu_map__nr(map) - 1)
+		: result;
 }
 
 /** Is 'b' a subset of 'a'. */
@@ -336,15 +378,15 @@ bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu
 {
 	if (a == b || !b)
 		return true;
-	if (!a || RC_CHK_ACCESS(b)->nr > RC_CHK_ACCESS(a)->nr)
+	if (!a || __perf_cpu_map__nr(b) > __perf_cpu_map__nr(a))
 		return false;
 
-	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)
+	for (int i = 0, j = 0; i < __perf_cpu_map__nr(a); i++) {
+		if (__perf_cpu_map__cpu(a, i).cpu > __perf_cpu_map__cpu(b, j).cpu)
 			return false;
-		if (RC_CHK_ACCESS(a)->map[i].cpu == RC_CHK_ACCESS(b)->map[j].cpu) {
+		if (__perf_cpu_map__cpu(a, i).cpu == __perf_cpu_map__cpu(b, j).cpu) {
 			j++;
-			if (j == RC_CHK_ACCESS(b)->nr)
+			if (j == __perf_cpu_map__nr(b))
 				return true;
 		}
 	}
@@ -374,27 +416,27 @@ struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
 		return perf_cpu_map__get(other);
 	}
 
-	tmp_len = RC_CHK_ACCESS(orig)->nr + RC_CHK_ACCESS(other)->nr;
+	tmp_len = __perf_cpu_map__nr(orig) + __perf_cpu_map__nr(other);
 	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 < 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)
+	while (i < __perf_cpu_map__nr(orig) && j < __perf_cpu_map__nr(other)) {
+		if (__perf_cpu_map__cpu(orig, i).cpu <= __perf_cpu_map__cpu(other, j).cpu) {
+			if (__perf_cpu_map__cpu(orig, i).cpu == __perf_cpu_map__cpu(other, j).cpu)
 				j++;
-			tmp_cpus[k++] = RC_CHK_ACCESS(orig)->map[i++];
+			tmp_cpus[k++] = __perf_cpu_map__cpu(orig, i++);
 		} else
-			tmp_cpus[k++] = RC_CHK_ACCESS(other)->map[j++];
+			tmp_cpus[k++] = __perf_cpu_map__cpu(other, j++);
 	}
 
-	while (i < RC_CHK_ACCESS(orig)->nr)
-		tmp_cpus[k++] = RC_CHK_ACCESS(orig)->map[i++];
+	while (i < __perf_cpu_map__nr(orig))
+		tmp_cpus[k++] = __perf_cpu_map__cpu(orig, i++);
 
-	while (j < RC_CHK_ACCESS(other)->nr)
-		tmp_cpus[k++] = RC_CHK_ACCESS(other)->map[j++];
+	while (j < __perf_cpu_map__nr(other))
+		tmp_cpus[k++] = __perf_cpu_map__cpu(other, j++);
 	assert(k <= tmp_len);
 
 	merged = cpu_map__trim_new(k, tmp_cpus);
@@ -402,3 +444,38 @@ struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
 	perf_cpu_map__put(orig);
 	return merged;
 }
+
+struct perf_cpu_map *perf_cpu_map__intersect(struct perf_cpu_map *orig,
+					     struct perf_cpu_map *other)
+{
+	struct perf_cpu *tmp_cpus;
+	int tmp_len;
+	int i, j, k;
+	struct perf_cpu_map *merged = NULL;
+
+	if (perf_cpu_map__is_subset(other, orig))
+		return perf_cpu_map__get(orig);
+	if (perf_cpu_map__is_subset(orig, other))
+		return perf_cpu_map__get(other);
+
+	tmp_len = max(__perf_cpu_map__nr(orig), __perf_cpu_map__nr(other));
+	tmp_cpus = malloc(tmp_len * sizeof(struct perf_cpu));
+	if (!tmp_cpus)
+		return NULL;
+
+	i = j = k = 0;
+	while (i < __perf_cpu_map__nr(orig) && j < __perf_cpu_map__nr(other)) {
+		if (__perf_cpu_map__cpu(orig, i).cpu < __perf_cpu_map__cpu(other, j).cpu)
+			i++;
+		else if (__perf_cpu_map__cpu(orig, i).cpu > __perf_cpu_map__cpu(other, j).cpu)
+			j++;
+		else {
+			j++;
+			tmp_cpus[k++] = __perf_cpu_map__cpu(orig, i++);
+		}
+	}
+	if (k)
+		merged = cpu_map__trim_new(k, tmp_cpus);
+	free(tmp_cpus);
+	return merged;
+}
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index 81e8b5fcd8bab4..b8b066d0dc5e45 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -36,18 +36,33 @@ void perf_evlist__init(struct perf_evlist *evlist)
 static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
 					  struct perf_evsel *evsel)
 {
-	/*
-	 * We already have cpus for evsel (via PMU sysfs) so
-	 * keep it, if there's no target cpu list defined.
-	 */
 	if (evsel->system_wide) {
+		/* System wide: set the cpu map of the evsel to all online CPUs. */
 		perf_cpu_map__put(evsel->cpus);
 		evsel->cpus = perf_cpu_map__new(NULL);
+	} else if (evlist->has_user_cpus && evsel->is_pmu_core) {
+		/*
+		 * User requested CPUs on a core PMU, ensure the requested CPUs
+		 * are valid by intersecting with those of the PMU.
+		 */
+		perf_cpu_map__put(evsel->cpus);
+		evsel->cpus = perf_cpu_map__intersect(evlist->user_requested_cpus, evsel->own_cpus);
 	} else if (!evsel->own_cpus || evlist->has_user_cpus ||
-		   (!evsel->requires_cpu && perf_cpu_map__empty(evlist->user_requested_cpus))) {
+		(!evsel->requires_cpu && perf_cpu_map__has_any_cpu(evlist->user_requested_cpus))) {
+		/*
+		 * The PMU didn't specify a default cpu map, this isn't a core
+		 * event and the user requested CPUs or the evlist user
+		 * requested CPUs have the "any CPU" (aka dummy) CPU value. In
+		 * which case use the user requested CPUs rather than the PMU
+		 * ones.
+		 */
 		perf_cpu_map__put(evsel->cpus);
 		evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus);
 	} else if (evsel->cpus != evsel->own_cpus) {
+		/*
+		 * No user requested cpu map but the PMU cpu map doesn't match
+		 * the evsel's. Reset it back to the PMU cpu map.
+		 */
 		perf_cpu_map__put(evsel->cpus);
 		evsel->cpus = perf_cpu_map__get(evsel->own_cpus);
 	}
diff --git a/tools/lib/perf/include/internal/evsel.h b/tools/lib/perf/include/internal/evsel.h
index a99a75d9e78f76..5cd220a61962e1 100644
--- a/tools/lib/perf/include/internal/evsel.h
+++ b/tools/lib/perf/include/internal/evsel.h
@@ -41,7 +41,14 @@ struct perf_sample_id {
 struct perf_evsel {
 	struct list_head	 node;
 	struct perf_event_attr	 attr;
+	/** The commonly used cpu map of CPUs the event should be opened upon, etc. */
 	struct perf_cpu_map	*cpus;
+	/**
+	 * The cpu map read from the PMU. For core PMUs this is the list of all
+	 * CPUs the event can be opened upon. For other PMUs this is the default
+	 * cpu map for opening the event on, for example, the first CPU on a
+	 * socket for an uncore event.
+	 */
 	struct perf_cpu_map	*own_cpus;
 	struct perf_thread_map	*threads;
 	struct xyarray		*fd;
@@ -55,9 +62,9 @@ struct perf_evsel {
 	int			 nr_members;
 	/*
 	 * system_wide is for events that need to be on every CPU, irrespective
-	 * of user requested CPUs or threads. Map propagation will set cpus to
-	 * this event's own_cpus, whereby they will contribute to evlist
-	 * all_cpus.
+	 * of user requested CPUs or threads. Tha main example of this is the
+	 * dummy event. Map propagation will set cpus for this event to all CPUs
+	 * as software PMU events like dummy, have a CPU map that is empty.
 	 */
 	bool			 system_wide;
 	/*
@@ -65,6 +72,8 @@ struct perf_evsel {
 	 * i.e. it cannot be the 'any CPU' value of -1.
 	 */
 	bool			 requires_cpu;
+	/** Is the PMU for the event a core one? Effects the handling of own_cpus. */
+	bool			 is_pmu_core;
 	int			 idx;
 };
 
diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h
index 3f43f770cdac58..e38d859a384d2c 100644
--- a/tools/lib/perf/include/perf/cpumap.h
+++ b/tools/lib/perf/include/perf/cpumap.h
@@ -11,8 +11,16 @@ struct perf_cpu {
 	int cpu;
 };
 
+struct perf_cache {
+	int cache_lvl;
+	int cache;
+};
+
 struct perf_cpu_map;
 
+/**
+ * perf_cpu_map__dummy_new - a map with a singular "any CPU"/dummy -1 value.
+ */
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__dummy_new(void);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__default_new(void);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list);
@@ -20,12 +28,23 @@ LIBPERF_API struct perf_cpu_map *perf_cpu_map__read(FILE *file);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
 						     struct perf_cpu_map *other);
+LIBPERF_API struct perf_cpu_map *perf_cpu_map__intersect(struct perf_cpu_map *orig,
+							 struct perf_cpu_map *other);
 LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map);
 LIBPERF_API struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx);
 LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
+/**
+ * perf_cpu_map__empty - is map either empty or the "any CPU"/dummy value.
+ */
 LIBPERF_API bool perf_cpu_map__empty(const struct perf_cpu_map *map);
 LIBPERF_API struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map);
 LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu);
+LIBPERF_API bool perf_cpu_map__equal(const struct perf_cpu_map *lhs,
+				     const struct perf_cpu_map *rhs);
+/**
+ * perf_cpu_map__any_cpu - Does the map contain the "any CPU"/dummy -1 value?
+ */
+LIBPERF_API bool perf_cpu_map__has_any_cpu(const struct perf_cpu_map *map);
 
 #define perf_cpu_map__for_each_cpu(cpu, idx, cpus)		\
 	for ((idx) = 0, (cpu) = perf_cpu_map__cpu(cpus, idx);	\
diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h
index 51b9338f4c117c..ba2dcf64f4e639 100644
--- a/tools/lib/perf/include/perf/event.h
+++ b/tools/lib/perf/include/perf/event.h
@@ -380,7 +380,8 @@ enum {
 	PERF_STAT_CONFIG_TERM__AGGR_MODE	= 0,
 	PERF_STAT_CONFIG_TERM__INTERVAL		= 1,
 	PERF_STAT_CONFIG_TERM__SCALE		= 2,
-	PERF_STAT_CONFIG_TERM__MAX		= 3,
+	PERF_STAT_CONFIG_TERM__AGGR_LEVEL	= 3,
+	PERF_STAT_CONFIG_TERM__MAX		= 4,
 };
 
 struct perf_record_stat_config_entry {
diff --git a/tools/lib/subcmd/exec-cmd.c b/tools/lib/subcmd/exec-cmd.c
index 5dbea456973e1e..7739b5217cf656 100644
--- a/tools/lib/subcmd/exec-cmd.c
+++ b/tools/lib/subcmd/exec-cmd.c
@@ -36,38 +36,40 @@ static int is_absolute_path(const char *path)
 	return path[0] == '/';
 }
 
-static const char *get_pwd_cwd(void)
+static const char *get_pwd_cwd(char *buf, size_t sz)
 {
-	static char cwd[PATH_MAX + 1];
 	char *pwd;
 	struct stat cwd_stat, pwd_stat;
-	if (getcwd(cwd, PATH_MAX) == NULL)
+	if (getcwd(buf, sz) == NULL)
 		return NULL;
 	pwd = getenv("PWD");
-	if (pwd && strcmp(pwd, cwd)) {
-		stat(cwd, &cwd_stat);
+	if (pwd && strcmp(pwd, buf)) {
+		stat(buf, &cwd_stat);
 		if (!stat(pwd, &pwd_stat) &&
 		    pwd_stat.st_dev == cwd_stat.st_dev &&
 		    pwd_stat.st_ino == cwd_stat.st_ino) {
-			strlcpy(cwd, pwd, PATH_MAX);
+			strlcpy(buf, pwd, sz);
 		}
 	}
-	return cwd;
+	return buf;
 }
 
-static const char *make_nonrelative_path(const char *path)
+static const char *make_nonrelative_path(char *buf, size_t sz, const char *path)
 {
-	static char buf[PATH_MAX + 1];
-
 	if (is_absolute_path(path)) {
-		if (strlcpy(buf, path, PATH_MAX) >= PATH_MAX)
+		if (strlcpy(buf, path, sz) >= sz)
 			die("Too long path: %.*s", 60, path);
 	} else {
-		const char *cwd = get_pwd_cwd();
+		const char *cwd = get_pwd_cwd(buf, sz);
+
 		if (!cwd)
 			die("Cannot determine the current working directory");
-		if (snprintf(buf, PATH_MAX, "%s/%s", cwd, path) >= PATH_MAX)
+
+		if (strlen(cwd) + strlen(path) + 2 >= sz)
 			die("Too long path: %.*s", 60, path);
+
+		strcat(buf, "/");
+		strcat(buf, path);
 	}
 	return buf;
 }
@@ -133,8 +135,11 @@ static void add_path(char **out, const char *path)
 	if (path && *path) {
 		if (is_absolute_path(path))
 			astrcat(out, path);
-		else
-			astrcat(out, make_nonrelative_path(path));
+		else {
+			char buf[PATH_MAX];
+
+			astrcat(out, make_nonrelative_path(buf, sizeof(buf), path));
+		}
 
 		astrcat(out, ":");
 	}
diff --git a/tools/lib/subcmd/help.c b/tools/lib/subcmd/help.c
index bf02d62a3b2b53..67a8d6b740eadf 100644
--- a/tools/lib/subcmd/help.c
+++ b/tools/lib/subcmd/help.c
@@ -16,6 +16,8 @@
 void add_cmdname(struct cmdnames *cmds, const char *name, size_t len)
 {
 	struct cmdname *ent = malloc(sizeof(*ent) + len + 1);
+	if (!ent)
+		return;
 
 	ent->len = len;
 	memcpy(ent->name, name, len);
@@ -66,6 +68,7 @@ void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes)
 	while (ci < cmds->cnt && ei < excludes->cnt) {
 		cmp = strcmp(cmds->names[ci]->name, excludes->names[ei]->name);
 		if (cmp < 0) {
+			zfree(&cmds->names[cj]);
 			cmds->names[cj++] = cmds->names[ci++];
 		} else if (cmp == 0) {
 			ci++;
@@ -75,9 +78,12 @@ void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes)
 		}
 	}
 
-	while (ci < cmds->cnt)
+	while (ci < cmds->cnt) {
+		zfree(&cmds->names[cj]);
 		cmds->names[cj++] = cmds->names[ci++];
-
+	}
+	for (ci = cj; ci < cmds->cnt; ci++)
+		zfree(&cmds->names[ci]);
 	cmds->cnt = cj;
 }