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
  ...

1 files changed, 87 insertions, 468 deletions

diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index ad209c88a124..64fa568a5426 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -4,20 +4,15 @@
 #include <linux/string.h>
 #include <linux/zalloc.h>
 #include <linux/ctype.h>
-#include <subcmd/pager.h>
 #include <sys/types.h>
-#include <errno.h>
 #include <fcntl.h>
 #include <sys/stat.h>
 #include <unistd.h>
 #include <stdio.h>
 #include <stdbool.h>
-#include <stdarg.h>
 #include <dirent.h>
 #include <api/fs/fs.h>
 #include <locale.h>
-#include <regex.h>
-#include <perf/cpumap.h>
 #include <fnmatch.h>
 #include <math.h>
 #include "debug.h"
@@ -32,7 +27,6 @@
 #include "string2.h"
 #include "strbuf.h"
 #include "fncache.h"
-#include "pmu-hybrid.h"
 #include "util/evsel_config.h"
 
 struct perf_pmu perf_pmu__fake;
@@ -60,10 +54,6 @@ struct perf_pmu_format {
 	struct list_head list;
 };
 
-static bool hybrid_scanned;
-
-static struct perf_pmu *perf_pmu__find2(int dirfd, const char *name);
-
 /*
  * Parse & process all the sysfs attributes located under
  * the directory specified in 'dir' parameter.
@@ -557,36 +547,11 @@ static int pmu_alias_terms(struct perf_pmu_alias *alias,
 	return 0;
 }
 
-/* Add all pmus in sysfs to pmu list: */
-static void pmu_read_sysfs(void)
-{
-	int fd;
-	DIR *dir;
-	struct dirent *dent;
-
-	fd = perf_pmu__event_source_devices_fd();
-	if (fd < 0)
-		return;
-
-	dir = fdopendir(fd);
-	if (!dir)
-		return;
-
-	while ((dent = readdir(dir))) {
-		if (!strcmp(dent->d_name, ".") || !strcmp(dent->d_name, ".."))
-			continue;
-		/* add to static LIST_HEAD(pmus): */
-		perf_pmu__find2(fd, dent->d_name);
-	}
-
-	closedir(dir);
-}
-
 /*
  * Uncore PMUs have a "cpumask" file under sysfs. CPU PMUs (e.g. on arm/arm64)
  * may have a "cpus" file.
  */
-static struct perf_cpu_map *pmu_cpumask(int dirfd, const char *name)
+static struct perf_cpu_map *pmu_cpumask(int dirfd, const char *name, bool is_core)
 {
 	struct perf_cpu_map *cpus;
 	const char *templates[] = {
@@ -610,16 +575,14 @@ static struct perf_cpu_map *pmu_cpumask(int dirfd, const char *name)
 			return cpus;
 	}
 
-	return NULL;
+	/* Nothing found, for core PMUs assume this means all CPUs. */
+	return is_core ? perf_cpu_map__get(cpu_map__online()) : NULL;
 }
 
 static bool pmu_is_uncore(int dirfd, const char *name)
 {
 	int fd;
 
-	if (perf_pmu__hybrid_mounted(name))
-		return false;
-
 	fd = perf_pmu__pathname_fd(dirfd, name, "cpumask", O_PATH);
 	if (fd < 0)
 		return false;
@@ -643,12 +606,14 @@ static char *pmu_id(const char *name)
 	return str;
 }
 
-/*
- *  PMU CORE devices have different name other than cpu in sysfs on some
- *  platforms.
- *  Looking for possible sysfs files to identify the arm core device.
+/**
+ * is_sysfs_pmu_core() - PMU CORE devices have different name other than cpu in
+ *         sysfs on some platforms like ARM or Intel hybrid. Looking for
+ *         possible the cpus file in sysfs files to identify whether this is a
+ *         core device.
+ * @name: The PMU name such as "cpu_atom".
  */
-static int is_arm_pmu_core(const char *name)
+static int is_sysfs_pmu_core(const char *name)
 {
 	char path[PATH_MAX];
 
@@ -777,9 +742,11 @@ out:
 }
 
 struct pmu_add_cpu_aliases_map_data {
+	/* List being added to. */
 	struct list_head *head;
-	const char *name;
-	const char *cpu_name;
+	/* If a pmu_event lacks a given PMU the default used. */
+	char *default_pmu_name;
+	/* The PMU that we're searching for events for. */
 	struct perf_pmu *pmu;
 };
 
@@ -788,37 +755,32 @@ static int pmu_add_cpu_aliases_map_callback(const struct pmu_event *pe,
 					void *vdata)
 {
 	struct pmu_add_cpu_aliases_map_data *data = vdata;
-	const char *pname = pe->pmu ? pe->pmu : data->cpu_name;
-
-	if (data->pmu->is_uncore && pmu_uncore_alias_match(pname, data->name))
-		goto new_alias;
-
-	if (strcmp(pname, data->name))
-		return 0;
+	const char *pname = pe->pmu ?: data->default_pmu_name;
 
-new_alias:
-	/* need type casts to override 'const' */
-	__perf_pmu__new_alias(data->head, -1, (char *)pe->name, (char *)pe->desc,
-			      (char *)pe->event, pe);
+	if (!strcmp(pname, data->pmu->name) ||
+	    (data->pmu->is_uncore && pmu_uncore_alias_match(pname, data->pmu->name))) {
+		/* need type casts to override 'const' */
+		__perf_pmu__new_alias(data->head, -1, (char *)pe->name, (char *)pe->desc,
+				      (char *)pe->event, pe);
+	}
 	return 0;
 }
 
 /*
- * From the pmu_events_map, find the table of PMU events that corresponds
- * to the current running CPU. Then, add all PMU events from that table
- * as aliases.
+ * From the pmu_events_table, find the events that correspond to the given
+ * PMU and add them to the list 'head'.
  */
 void pmu_add_cpu_aliases_table(struct list_head *head, struct perf_pmu *pmu,
-			       const struct pmu_events_table *table)
+			const struct pmu_events_table *table)
 {
 	struct pmu_add_cpu_aliases_map_data data = {
 		.head = head,
-		.name = pmu->name,
-		.cpu_name = is_arm_pmu_core(pmu->name) ? pmu->name : "cpu",
+		.default_pmu_name = perf_pmus__default_pmu_name(),
 		.pmu = pmu,
 	};
 
 	pmu_events_table_for_each_event(table, pmu_add_cpu_aliases_map_callback, &data);
+	free(data.default_pmu_name);
 }
 
 static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu)
@@ -898,23 +860,16 @@ static int pmu_max_precise(int dirfd, struct perf_pmu *pmu)
 	return max_precise;
 }
 
-static struct perf_pmu *pmu_lookup(int dirfd, const char *lookup_name)
+struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char *lookup_name)
 {
 	struct perf_pmu *pmu;
 	LIST_HEAD(format);
 	LIST_HEAD(aliases);
 	__u32 type;
 	char *name = pmu_find_real_name(lookup_name);
-	bool is_hybrid = perf_pmu__hybrid_mounted(name);
 	char *alias_name;
 
 	/*
-	 * Check pmu name for hybrid and the pmu may be invalid in sysfs
-	 */
-	if (!strncmp(name, "cpu_", 4) && !is_hybrid)
-		return NULL;
-
-	/*
 	 * The pmu data we store & need consists of the pmu
 	 * type value and format definitions. Load both right
 	 * now.
@@ -932,9 +887,9 @@ static struct perf_pmu *pmu_lookup(int dirfd, const char *lookup_name)
 	if (!pmu)
 		return NULL;
 
-	pmu->cpus = pmu_cpumask(dirfd, name);
+	pmu->is_core = is_pmu_core(name);
+	pmu->cpus = pmu_cpumask(dirfd, name, pmu->is_core);
 	pmu->name = strdup(name);
-
 	if (!pmu->name)
 		goto err;
 
@@ -962,12 +917,7 @@ static struct perf_pmu *pmu_lookup(int dirfd, const char *lookup_name)
 	INIT_LIST_HEAD(&pmu->caps);
 	list_splice(&format, &pmu->format);
 	list_splice(&aliases, &pmu->aliases);
-	list_add_tail(&pmu->list, &pmus);
-
-	if (is_hybrid)
-		list_add_tail(&pmu->hybrid_list, &perf_pmu__hybrid_pmus);
-	else
-		INIT_LIST_HEAD(&pmu->hybrid_list);
+	list_add_tail(&pmu->list, pmus);
 
 	pmu->default_config = perf_pmu__get_default_config(pmu);
 
@@ -982,6 +932,11 @@ void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu)
 {
 	struct perf_pmu_format *format;
 
+	if (pmu->formats_checked)
+		return;
+
+	pmu->formats_checked = true;
+
 	/* fake pmu doesn't have format list */
 	if (pmu == &perf_pmu__fake)
 		return;
@@ -995,61 +950,6 @@ void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu)
 		}
 }
 
-static struct perf_pmu *pmu_find(const char *name)
-{
-	struct perf_pmu *pmu;
-
-	list_for_each_entry(pmu, &pmus, list) {
-		if (!strcmp(pmu->name, name) ||
-		    (pmu->alias_name && !strcmp(pmu->alias_name, name)))
-			return pmu;
-	}
-
-	return NULL;
-}
-
-struct perf_pmu *perf_pmu__find_by_type(unsigned int type)
-{
-	struct perf_pmu *pmu;
-
-	list_for_each_entry(pmu, &pmus, list)
-		if (pmu->type == type)
-			return pmu;
-
-	return NULL;
-}
-
-struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu)
-{
-	/*
-	 * pmu iterator: If pmu is NULL, we start at the begin,
-	 * otherwise return the next pmu. Returns NULL on end.
-	 */
-	if (!pmu) {
-		pmu_read_sysfs();
-		pmu = list_prepare_entry(pmu, &pmus, list);
-	}
-	list_for_each_entry_continue(pmu, &pmus, list)
-		return pmu;
-	return NULL;
-}
-
-struct perf_pmu *evsel__find_pmu(const struct evsel *evsel)
-{
-	struct perf_pmu *pmu = NULL;
-
-	if (evsel->pmu)
-		return evsel->pmu;
-
-	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
-		if (pmu->type == evsel->core.attr.type)
-			break;
-	}
-
-	((struct evsel *)evsel)->pmu = pmu;
-	return pmu;
-}
-
 bool evsel__is_aux_event(const struct evsel *evsel)
 {
 	struct perf_pmu *pmu = evsel__find_pmu(evsel);
@@ -1086,43 +986,6 @@ void evsel__set_config_if_unset(struct perf_pmu *pmu, struct evsel *evsel,
 	evsel->core.attr.config |= field_prep(bits, val);
 }
 
-struct perf_pmu *perf_pmu__find(const char *name)
-{
-	struct perf_pmu *pmu;
-	int dirfd;
-
-	/*
-	 * Once PMU is loaded it stays in the list,
-	 * so we keep us from multiple reading/parsing
-	 * the pmu format definitions.
-	 */
-	pmu = pmu_find(name);
-	if (pmu)
-		return pmu;
-
-	dirfd = perf_pmu__event_source_devices_fd();
-	pmu = pmu_lookup(dirfd, name);
-	close(dirfd);
-
-	return pmu;
-}
-
-static struct perf_pmu *perf_pmu__find2(int dirfd, const char *name)
-{
-	struct perf_pmu *pmu;
-
-	/*
-	 * Once PMU is loaded it stays in the list,
-	 * so we keep us from multiple reading/parsing
-	 * the pmu format definitions.
-	 */
-	pmu = pmu_find(name);
-	if (pmu)
-		return pmu;
-
-	return pmu_lookup(dirfd, name);
-}
-
 static struct perf_pmu_format *
 pmu_find_format(struct list_head *formats, const char *name)
 {
@@ -1398,7 +1261,6 @@ int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 {
 	bool zero = !!pmu->default_config;
 
-	attr->type = pmu->type;
 	return perf_pmu__config_terms(pmu->name, &pmu->format, attr,
 				      head_terms, zero, err);
 }
@@ -1553,250 +1415,46 @@ void perf_pmu__del_formats(struct list_head *formats)
 	}
 }
 
-static int sub_non_neg(int a, int b)
-{
-	if (b > a)
-		return 0;
-	return a - b;
-}
-
-static char *format_alias(char *buf, int len, const struct perf_pmu *pmu,
-			  const struct perf_pmu_alias *alias)
-{
-	struct parse_events_term *term;
-	int used = snprintf(buf, len, "%s/%s", pmu->name, alias->name);
-
-	list_for_each_entry(term, &alias->terms, list) {
-		if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR)
-			used += snprintf(buf + used, sub_non_neg(len, used),
-					",%s=%s", term->config,
-					term->val.str);
-	}
-
-	if (sub_non_neg(len, used) > 0) {
-		buf[used] = '/';
-		used++;
-	}
-	if (sub_non_neg(len, used) > 0) {
-		buf[used] = '\0';
-		used++;
-	} else
-		buf[len - 1] = '\0';
-
-	return buf;
-}
-
-/** Struct for ordering events as output in perf list. */
-struct sevent {
-	/** PMU for event. */
-	const struct perf_pmu *pmu;
-	/**
-	 * Optional event for name, desc, etc. If not present then this is a
-	 * selectable PMU and the event name is shown as "//".
-	 */
-	const struct perf_pmu_alias *event;
-	/** Is the PMU for the CPU? */
-	bool is_cpu;
-};
-
-static int cmp_sevent(const void *a, const void *b)
+bool is_pmu_core(const char *name)
 {
-	const struct sevent *as = a;
-	const struct sevent *bs = b;
-	const char *a_pmu_name = NULL, *b_pmu_name = NULL;
-	const char *a_name = "//", *a_desc = NULL, *a_topic = "";
-	const char *b_name = "//", *b_desc = NULL, *b_topic = "";
-	int ret;
-
-	if (as->event) {
-		a_name = as->event->name;
-		a_desc = as->event->desc;
-		a_topic = as->event->topic ?: "";
-		a_pmu_name = as->event->pmu_name;
-	}
-	if (bs->event) {
-		b_name = bs->event->name;
-		b_desc = bs->event->desc;
-		b_topic = bs->event->topic ?: "";
-		b_pmu_name = bs->event->pmu_name;
-	}
-	/* Put extra events last. */
-	if (!!a_desc != !!b_desc)
-		return !!a_desc - !!b_desc;
-
-	/* Order by topics. */
-	ret = strcmp(a_topic, b_topic);
-	if (ret)
-		return ret;
-
-	/* Order CPU core events to be first */
-	if (as->is_cpu != bs->is_cpu)
-		return as->is_cpu ? -1 : 1;
-
-	/* Order by PMU name. */
-	if (as->pmu != bs->pmu) {
-		a_pmu_name = a_pmu_name ?: (as->pmu->name ?: "");
-		b_pmu_name = b_pmu_name ?: (bs->pmu->name ?: "");
-		ret = strcmp(a_pmu_name, b_pmu_name);
-		if (ret)
-			return ret;
-	}
-
-	/* Order by event name. */
-	return strcmp(a_name, b_name);
+	return !strcmp(name, "cpu") || !strcmp(name, "cpum_cf") || is_sysfs_pmu_core(name);
 }
 
-bool is_pmu_core(const char *name)
+bool perf_pmu__supports_legacy_cache(const struct perf_pmu *pmu)
 {
-	return !strcmp(name, "cpu") || is_arm_pmu_core(name);
+	return pmu->is_core;
 }
 
-static bool pmu_alias_is_duplicate(struct sevent *alias_a,
-				   struct sevent *alias_b)
+bool perf_pmu__auto_merge_stats(const struct perf_pmu *pmu)
 {
-	const char *a_pmu_name = NULL, *b_pmu_name = NULL;
-	const char *a_name = "//", *b_name = "//";
-
-
-	if (alias_a->event) {
-		a_name = alias_a->event->name;
-		a_pmu_name = alias_a->event->pmu_name;
-	}
-	if (alias_b->event) {
-		b_name = alias_b->event->name;
-		b_pmu_name = alias_b->event->pmu_name;
-	}
-
-	/* Different names -> never duplicates */
-	if (strcmp(a_name, b_name))
-		return false;
-
-	/* Don't remove duplicates for different PMUs */
-	a_pmu_name = a_pmu_name ?: (alias_a->pmu->name ?: "");
-	b_pmu_name = b_pmu_name ?: (alias_b->pmu->name ?: "");
-	return strcmp(a_pmu_name, b_pmu_name) == 0;
+	return pmu->is_core && perf_pmus__num_core_pmus() == 1;
 }
 
-void print_pmu_events(const struct print_callbacks *print_cb, void *print_state)
+bool perf_pmu__have_event(const struct perf_pmu *pmu, const char *name)
 {
-	struct perf_pmu *pmu;
-	struct perf_pmu_alias *event;
-	char buf[1024];
-	int printed = 0;
-	int len, j;
-	struct sevent *aliases;
-
-	pmu = NULL;
-	len = 0;
-	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
-		list_for_each_entry(event, &pmu->aliases, list)
-			len++;
-		if (pmu->selectable)
-			len++;
-	}
-	aliases = zalloc(sizeof(struct sevent) * len);
-	if (!aliases) {
-		pr_err("FATAL: not enough memory to print PMU events\n");
-		return;
-	}
-	pmu = NULL;
-	j = 0;
-	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
-		bool is_cpu = is_pmu_core(pmu->name) || perf_pmu__is_hybrid(pmu->name);
-
-		list_for_each_entry(event, &pmu->aliases, list) {
-			aliases[j].event = event;
-			aliases[j].pmu = pmu;
-			aliases[j].is_cpu = is_cpu;
-			j++;
-		}
-		if (pmu->selectable) {
-			aliases[j].event = NULL;
-			aliases[j].pmu = pmu;
-			aliases[j].is_cpu = is_cpu;
-			j++;
-		}
-	}
-	len = j;
-	qsort(aliases, len, sizeof(struct sevent), cmp_sevent);
-	for (j = 0; j < len; j++) {
-		const char *name, *alias = NULL, *scale_unit = NULL,
-			*desc = NULL, *long_desc = NULL,
-			*encoding_desc = NULL, *topic = NULL,
-			*pmu_name = NULL;
-		bool deprecated = false;
-		size_t buf_used;
-
-		/* Skip duplicates */
-		if (j > 0 && pmu_alias_is_duplicate(&aliases[j], &aliases[j - 1]))
-			continue;
+	struct perf_pmu_alias *alias;
 
-		if (!aliases[j].event) {
-			/* A selectable event. */
-			pmu_name = aliases[j].pmu->name;
-			buf_used = snprintf(buf, sizeof(buf), "%s//", pmu_name) + 1;
-			name = buf;
-		} else {
-			if (aliases[j].event->desc) {
-				name = aliases[j].event->name;
-				buf_used = 0;
-			} else {
-				name = format_alias(buf, sizeof(buf), aliases[j].pmu,
-						    aliases[j].event);
-				if (aliases[j].is_cpu) {
-					alias = name;
-					name = aliases[j].event->name;
-				}
-				buf_used = strlen(buf) + 1;
-			}
-			pmu_name = aliases[j].event->pmu_name ?: (aliases[j].pmu->name ?: "");
-			if (strlen(aliases[j].event->unit) || aliases[j].event->scale != 1.0) {
-				scale_unit = buf + buf_used;
-				buf_used += snprintf(buf + buf_used, sizeof(buf) - buf_used,
-						"%G%s", aliases[j].event->scale,
-						aliases[j].event->unit) + 1;
-			}
-			desc = aliases[j].event->desc;
-			long_desc = aliases[j].event->long_desc;
-			topic = aliases[j].event->topic;
-			encoding_desc = buf + buf_used;
-			buf_used += snprintf(buf + buf_used, sizeof(buf) - buf_used,
-					"%s/%s/", pmu_name, aliases[j].event->str) + 1;
-			deprecated = aliases[j].event->deprecated;
-		}
-		print_cb->print_event(print_state,
-				pmu_name,
-				topic,
-				name,
-				alias,
-				scale_unit,
-				deprecated,
-				"Kernel PMU event",
-				desc,
-				long_desc,
-				encoding_desc);
+	list_for_each_entry(alias, &pmu->aliases, list) {
+		if (!strcmp(alias->name, name))
+			return true;
 	}
-	if (printed && pager_in_use())
-		printf("\n");
-
-	zfree(&aliases);
-	return;
+	return false;
 }
 
-bool pmu_have_event(const char *pname, const char *name)
+bool perf_pmu__is_software(const struct perf_pmu *pmu)
 {
-	struct perf_pmu *pmu;
-	struct perf_pmu_alias *alias;
-
-	pmu = NULL;
-	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
-		if (strcmp(pname, pmu->name))
-			continue;
-		list_for_each_entry(alias, &pmu->aliases, list)
-			if (!strcmp(alias->name, name))
-				return true;
+	if (pmu->is_core || pmu->is_uncore || pmu->auxtrace)
+		return false;
+	switch (pmu->type) {
+	case PERF_TYPE_HARDWARE:	return false;
+	case PERF_TYPE_SOFTWARE:	return true;
+	case PERF_TYPE_TRACEPOINT:	return true;
+	case PERF_TYPE_HW_CACHE:	return false;
+	case PERF_TYPE_RAW:		return false;
+	case PERF_TYPE_BREAKPOINT:	return true;
+	default: break;
 	}
-	return false;
+	return !strcmp(pmu->name, "kprobe") || !strcmp(pmu->name, "uprobe");
 }
 
 FILE *perf_pmu__open_file(struct perf_pmu *pmu, const char *name)
@@ -1967,47 +1625,53 @@ int perf_pmu__caps_parse(struct perf_pmu *pmu)
 	return pmu->nr_caps;
 }
 
-void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config,
-				   const char *name)
+static void perf_pmu__compute_config_masks(struct perf_pmu *pmu)
 {
 	struct perf_pmu_format *format;
-	__u64 masks = 0, bits;
-	char buf[100];
-	unsigned int i;
+
+	if (pmu->config_masks_computed)
+		return;
 
 	list_for_each_entry(format, &pmu->format, list)	{
-		if (format->value != PERF_PMU_FORMAT_VALUE_CONFIG)
+		unsigned int i;
+		__u64 *mask;
+
+		if (format->value >= PERF_PMU_FORMAT_VALUE_CONFIG_END)
 			continue;
 
+		pmu->config_masks_present = true;
+		mask = &pmu->config_masks[format->value];
+
 		for_each_set_bit(i, format->bits, PERF_PMU_FORMAT_BITS)
-			masks |= 1ULL << i;
+			*mask |= 1ULL << i;
 	}
+	pmu->config_masks_computed = true;
+}
+
+void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config,
+				   const char *name, int config_num,
+				   const char *config_name)
+{
+	__u64 bits;
+	char buf[100];
+
+	perf_pmu__compute_config_masks(pmu);
 
 	/*
 	 * Kernel doesn't export any valid format bits.
 	 */
-	if (masks == 0)
+	if (!pmu->config_masks_present)
 		return;
 
-	bits = config & ~masks;
+	bits = config & ~pmu->config_masks[config_num];
 	if (bits == 0)
 		return;
 
 	bitmap_scnprintf((unsigned long *)&bits, sizeof(bits) * 8, buf, sizeof(buf));
 
-	pr_warning("WARNING: event '%s' not valid (bits %s of config "
+	pr_warning("WARNING: event '%s' not valid (bits %s of %s "
 		   "'%llx' not supported by kernel)!\n",
-		   name ?: "N/A", buf, config);
-}
-
-bool perf_pmu__has_hybrid(void)
-{
-	if (!hybrid_scanned) {
-		hybrid_scanned = true;
-		perf_pmu__scan(NULL);
-	}
-
-	return !list_empty(&perf_pmu__hybrid_pmus);
+		   name ?: "N/A", buf, config_name, config);
 }
 
 int perf_pmu__match(char *pattern, char *name, char *tok)
@@ -2024,39 +1688,6 @@ int perf_pmu__match(char *pattern, char *name, char *tok)
 	return 0;
 }
 
-int perf_pmu__cpus_match(struct perf_pmu *pmu, struct perf_cpu_map *cpus,
-			 struct perf_cpu_map **mcpus_ptr,
-			 struct perf_cpu_map **ucpus_ptr)
-{
-	struct perf_cpu_map *pmu_cpus = pmu->cpus;
-	struct perf_cpu_map *matched_cpus, *unmatched_cpus;
-	struct perf_cpu cpu;
-	int i, matched_nr = 0, unmatched_nr = 0;
-
-	matched_cpus = perf_cpu_map__default_new();
-	if (!matched_cpus)
-		return -1;
-
-	unmatched_cpus = perf_cpu_map__default_new();
-	if (!unmatched_cpus) {
-		perf_cpu_map__put(matched_cpus);
-		return -1;
-	}
-
-	perf_cpu_map__for_each_cpu(cpu, i, cpus) {
-		if (!perf_cpu_map__has(pmu_cpus, cpu))
-			RC_CHK_ACCESS(unmatched_cpus)->map[unmatched_nr++] = cpu;
-		else
-			RC_CHK_ACCESS(matched_cpus)->map[matched_nr++] = cpu;
-	}
-
-	perf_cpu_map__set_nr(unmatched_cpus, unmatched_nr);
-	perf_cpu_map__set_nr(matched_cpus, matched_nr);
-	*mcpus_ptr = matched_cpus;
-	*ucpus_ptr = unmatched_cpus;
-	return 0;
-}
-
 double __weak perf_pmu__cpu_slots_per_cycle(void)
 {
 	return NAN;
@@ -2110,7 +1741,7 @@ int perf_pmu__pathname_fd(int dirfd, const char *pmu_name, const char *filename,
 	return openat(dirfd, path, flags);
 }
 
-static void perf_pmu__delete(struct perf_pmu *pmu)
+void perf_pmu__delete(struct perf_pmu *pmu)
 {
 	perf_pmu__del_formats(&pmu->format);
 	perf_pmu__del_aliases(pmu);
@@ -2123,15 +1754,3 @@ static void perf_pmu__delete(struct perf_pmu *pmu)
 	zfree(&pmu->alias_name);
 	free(pmu);
 }
-
-void perf_pmu__destroy(void)
-{
-	struct perf_pmu *pmu, *tmp;
-
-	list_for_each_entry_safe(pmu, tmp, &pmus, list) {
-		list_del(&pmu->list);
-		list_del(&pmu->hybrid_list);
-
-		perf_pmu__delete(pmu);
-	}
-}