Merge tag 'perf-tools-for-v6.9-2024-03-13' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools

Pull perf tools updates from Namhyung Kim:
 "perf stat:

   - Support new 'cluster' aggregation mode for shared resources
     depending on the hardware configuration:

        $ sudo perf stat -a --per-cluster -e cycles,instructions sleep 1

         Performance counter stats for 'system wide':

        S0-D0-CLS0    2         85,051,822      cycles
        S0-D0-CLS0    2         73,909,908      instructions      #    0.87  insn per cycle
        S0-D0-CLS2    2         93,365,918      cycles
        S0-D0-CLS2    2         83,006,158      instructions      #    0.89  insn per cycle
        S0-D0-CLS4    2        104,157,523      cycles
        S0-D0-CLS4    2         53,234,396      instructions      #    0.51  insn per cycle
        S0-D0-CLS6    2         65,891,079      cycles
        S0-D0-CLS6    2         41,478,273      instructions      #    0.63  insn per cycle

               1.002407989 seconds time elapsed

   - Various fixes and cleanups for event metrics including NaN handling

  perf script:

   - Use libcapstone if available to disassemble the instructions. This
     enables 'perf script -F disasm' and 'perf script --insn-trace=disasm'
     (for Intel-PT):

        $ perf script -F event,ip,disasm
        cycles:P:  ffffffffa988d428             wrmsr
        cycles:P:  ffffffffa9839d25             movq %rax, %r14
        cycles:P:  ffffffffa9cdcaf0             endbr64
        cycles:P:  ffffffffa988d428             wrmsr
        cycles:P:  ffffffffa988d428             wrmsr
        cycles:P:  ffffffffaa401f86             iretq
        cycles:P:  ffffffffa99c4de5             movq 0x30(%rcx), %r8
        cycles:P:  ffffffffa988d428             wrmsr
        cycles:P:  ffffffffaa401f86             iretq
        cycles:P:  ffffffffa9907983             movl 0x68(%rbx), %eax
        cycles:P:  ffffffffa988d428             wrmsr

   - Expose sample ID / stream ID to python scripts

  perf test:

   - Add more perf test cases from Redhat internal test suites. This
     time it adds the base infra and a few perf probe tests. More to
     come. :)

   - Add 'perf test -p' for parallel execution and fix some issues found
     by the parallel test

   - Support symbol test to print symbols in given (active) module:

        $ perf test -F -v Symbols --dso /lib/modules/$(uname -r)/kernel/fs/ext4/ext4.ko
        --- start ---
        Testing /lib/modules/6.5.13-1rodete2-amd64/kernel/fs/ext4/ext4.ko
        Overlapping symbols:
         7a990-7a9a0 l __pfx_ext4_exit_fs
         7a990-7a9a0 g __pfx_cleanup_module
        Overlapping symbols:
         7a9a0-7aa1c l ext4_exit_fs
         7a9a0-7aa1c g cleanup_module
        ...

  JSON metric updates:

   - A new round of Intel metric updates

   - Support Power11 PVR (compatible to Power10)

   - Fix cache latency events on Zen 4 to set SliceId properly

  Internal:

   - Fix reference counting for 'map' data structure, tireless work from
     Ian!

   - More memory optimization for struct thread and annotate histogram.
     Now, 'perf report' (TUI) and 'perf annotate' should be much
     lighter-weight in terms of memory footprint

   - Support cross-arch perf register access. Clean up the build
     configuration so that it can detect arch-register support at
     runtime. This can allow to parse register data in sample which was
     recorded in a different arch

  Others:

   - Sync task state in 'perf sched' to kernel using trace event fields.
     The task states have been changed so tools cannot assume a fixed
     encoding

   - Clean up 'perf mem' to generalize the arch-specific events

   - Add support for local and global variables to data type profiling.
     This would increase the success rate of type resolution with DWARF

   - Add short option -H for --hierarchy in 'perf report' and 'perf top'"

* tag 'perf-tools-for-v6.9-2024-03-13' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (154 commits)
  perf annotate: Add comments in the data structures
  perf annotate: Remove sym_hist.addr[] array
  perf annotate: Calculate instruction overhead using hashmap
  perf annotate: Add a hashmap for symbol histogram
  perf threads: Reduce table size from 256 to 8
  perf threads: Switch from rbtree to hashmap
  perf threads: Move threads to its own files
  perf machine: Move machine's threads into its own abstraction
  perf machine: Move fprintf to for_each loop and a callback
  perf trace: Ignore thread hashing in summary
  perf report: Sort child tasks by tid
  perf vendor events amd: Fix Zen 4 cache latency events
  perf version: Display availability of OpenCSD support
  perf vendor events intel: Add umasks/occ_sel to PCU events.
  perf map: Fix map reference count issues
  libperf evlist: Avoid out-of-bounds access
  perf lock contention: Account contending locks too
  perf metrics: Fix segv for metrics with no events
  perf metrics: Fix metric matching
  perf pmu: Fix a potential memory leak in perf_pmu__lookup()
  ...

1 files changed, 102 insertions, 273 deletions

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index b397a769006f..527517db3182 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -43,9 +43,6 @@
 #include <linux/string.h>
 #include <linux/zalloc.h>
 
-static void __machine__remove_thread(struct machine *machine, struct thread_rb_node *nd,
-				     struct thread *th, bool lock);
-
 static struct dso *machine__kernel_dso(struct machine *machine)
 {
 	return map__dso(machine->vmlinux_map);
@@ -58,35 +55,6 @@ static void dsos__init(struct dsos *dsos)
 	init_rwsem(&dsos->lock);
 }
 
-static void machine__threads_init(struct machine *machine)
-{
-	int i;
-
-	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
-		struct threads *threads = &machine->threads[i];
-		threads->entries = RB_ROOT_CACHED;
-		init_rwsem(&threads->lock);
-		threads->nr = 0;
-		threads->last_match = NULL;
-	}
-}
-
-static int thread_rb_node__cmp_tid(const void *key, const struct rb_node *nd)
-{
-	int to_find = (int) *((pid_t *)key);
-
-	return to_find - (int)thread__tid(rb_entry(nd, struct thread_rb_node, rb_node)->thread);
-}
-
-static struct thread_rb_node *thread_rb_node__find(const struct thread *th,
-						   struct rb_root *tree)
-{
-	pid_t to_find = thread__tid(th);
-	struct rb_node *nd = rb_find(&to_find, tree, thread_rb_node__cmp_tid);
-
-	return rb_entry(nd, struct thread_rb_node, rb_node);
-}
-
 static int machine__set_mmap_name(struct machine *machine)
 {
 	if (machine__is_host(machine))
@@ -120,7 +88,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 	RB_CLEAR_NODE(&machine->rb_node);
 	dsos__init(&machine->dsos);
 
-	machine__threads_init(machine);
+	threads__init(&machine->threads);
 
 	machine->vdso_info = NULL;
 	machine->env = NULL;
@@ -221,27 +189,11 @@ static void dsos__exit(struct dsos *dsos)
 
 void machine__delete_threads(struct machine *machine)
 {
-	struct rb_node *nd;
-	int i;
-
-	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
-		struct threads *threads = &machine->threads[i];
-		down_write(&threads->lock);
-		nd = rb_first_cached(&threads->entries);
-		while (nd) {
-			struct thread_rb_node *trb = rb_entry(nd, struct thread_rb_node, rb_node);
-
-			nd = rb_next(nd);
-			__machine__remove_thread(machine, trb, trb->thread, false);
-		}
-		up_write(&threads->lock);
-	}
+	threads__remove_all_threads(&machine->threads);
 }
 
 void machine__exit(struct machine *machine)
 {
-	int i;
-
 	if (machine == NULL)
 		return;
 
@@ -254,12 +206,7 @@ void machine__exit(struct machine *machine)
 	zfree(&machine->current_tid);
 	zfree(&machine->kallsyms_filename);
 
-	machine__delete_threads(machine);
-	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
-		struct threads *threads = &machine->threads[i];
-
-		exit_rwsem(&threads->lock);
-	}
+	threads__exit(&machine->threads);
 }
 
 void machine__delete(struct machine *machine)
@@ -440,7 +387,7 @@ static struct thread *findnew_guest_code(struct machine *machine,
 		return NULL;
 
 	/* Assume maps are set up if there are any */
-	if (maps__nr_maps(thread__maps(thread)))
+	if (!maps__empty(thread__maps(thread)))
 		return thread;
 
 	host_thread = machine__find_thread(host_machine, -1, pid);
@@ -526,7 +473,7 @@ static void machine__update_thread_pid(struct machine *machine,
 	if (thread__pid(th) == thread__tid(th))
 		return;
 
-	leader = __machine__findnew_thread(machine, thread__pid(th), thread__pid(th));
+	leader = machine__findnew_thread(machine, thread__pid(th), thread__pid(th));
 	if (!leader)
 		goto out_err;
 
@@ -561,159 +508,55 @@ out_err:
 }
 
 /*
- * Front-end cache - TID lookups come in blocks,
- * so most of the time we dont have to look up
- * the full rbtree:
- */
-static struct thread*
-__threads__get_last_match(struct threads *threads, struct machine *machine,
-			  int pid, int tid)
-{
-	struct thread *th;
-
-	th = threads->last_match;
-	if (th != NULL) {
-		if (thread__tid(th) == tid) {
-			machine__update_thread_pid(machine, th, pid);
-			return thread__get(th);
-		}
-		thread__put(threads->last_match);
-		threads->last_match = NULL;
-	}
-
-	return NULL;
-}
-
-static struct thread*
-threads__get_last_match(struct threads *threads, struct machine *machine,
-			int pid, int tid)
-{
-	struct thread *th = NULL;
-
-	if (perf_singlethreaded)
-		th = __threads__get_last_match(threads, machine, pid, tid);
-
-	return th;
-}
-
-static void
-__threads__set_last_match(struct threads *threads, struct thread *th)
-{
-	thread__put(threads->last_match);
-	threads->last_match = thread__get(th);
-}
-
-static void
-threads__set_last_match(struct threads *threads, struct thread *th)
-{
-	if (perf_singlethreaded)
-		__threads__set_last_match(threads, th);
-}
-
-/*
  * Caller must eventually drop thread->refcnt returned with a successful
  * lookup/new thread inserted.
  */
-static struct thread *____machine__findnew_thread(struct machine *machine,
-						  struct threads *threads,
-						  pid_t pid, pid_t tid,
-						  bool create)
+static struct thread *__machine__findnew_thread(struct machine *machine,
+						pid_t pid,
+						pid_t tid,
+						bool create)
 {
-	struct rb_node **p = &threads->entries.rb_root.rb_node;
-	struct rb_node *parent = NULL;
-	struct thread *th;
-	struct thread_rb_node *nd;
-	bool leftmost = true;
+	struct thread *th = threads__find(&machine->threads, tid);
+	bool created;
 
-	th = threads__get_last_match(threads, machine, pid, tid);
-	if (th)
+	if (th) {
+		machine__update_thread_pid(machine, th, pid);
 		return th;
-
-	while (*p != NULL) {
-		parent = *p;
-		th = rb_entry(parent, struct thread_rb_node, rb_node)->thread;
-
-		if (thread__tid(th) == tid) {
-			threads__set_last_match(threads, th);
-			machine__update_thread_pid(machine, th, pid);
-			return thread__get(th);
-		}
-
-		if (tid < thread__tid(th))
-			p = &(*p)->rb_left;
-		else {
-			p = &(*p)->rb_right;
-			leftmost = false;
-		}
 	}
-
 	if (!create)
 		return NULL;
 
-	th = thread__new(pid, tid);
-	if (th == NULL)
-		return NULL;
-
-	nd = malloc(sizeof(*nd));
-	if (nd == NULL) {
-		thread__put(th);
-		return NULL;
-	}
-	nd->thread = th;
-
-	rb_link_node(&nd->rb_node, parent, p);
-	rb_insert_color_cached(&nd->rb_node, &threads->entries, leftmost);
-	/*
-	 * We have to initialize maps separately after rb tree is updated.
-	 *
-	 * The reason is that we call machine__findnew_thread within
-	 * thread__init_maps to find the thread leader and that would screwed
-	 * the rb tree.
-	 */
-	if (thread__init_maps(th, machine)) {
-		pr_err("Thread init failed thread %d\n", pid);
-		rb_erase_cached(&nd->rb_node, &threads->entries);
-		RB_CLEAR_NODE(&nd->rb_node);
-		free(nd);
-		thread__put(th);
-		return NULL;
-	}
-	/*
-	 * It is now in the rbtree, get a ref
-	 */
-	threads__set_last_match(threads, th);
-	++threads->nr;
-
-	return thread__get(th);
-}
+	th = threads__findnew(&machine->threads, pid, tid, &created);
+	if (created) {
+		/*
+		 * We have to initialize maps separately after rb tree is
+		 * updated.
+		 *
+		 * The reason is that we call machine__findnew_thread within
+		 * thread__init_maps to find the thread leader and that would
+		 * screwed the rb tree.
+		 */
+		if (thread__init_maps(th, machine)) {
+			pr_err("Thread init failed thread %d\n", pid);
+			threads__remove(&machine->threads, th);
+			thread__put(th);
+			return NULL;
+		}
+	} else
+		machine__update_thread_pid(machine, th, pid);
 
-struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid)
-{
-	return ____machine__findnew_thread(machine, machine__threads(machine, tid), pid, tid, true);
+	return th;
 }
 
-struct thread *machine__findnew_thread(struct machine *machine, pid_t pid,
-				       pid_t tid)
+struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid)
 {
-	struct threads *threads = machine__threads(machine, tid);
-	struct thread *th;
-
-	down_write(&threads->lock);
-	th = __machine__findnew_thread(machine, pid, tid);
-	up_write(&threads->lock);
-	return th;
+	return __machine__findnew_thread(machine, pid, tid, /*create=*/true);
 }
 
 struct thread *machine__find_thread(struct machine *machine, pid_t pid,
 				    pid_t tid)
 {
-	struct threads *threads = machine__threads(machine, tid);
-	struct thread *th;
-
-	down_read(&threads->lock);
-	th =  ____machine__findnew_thread(machine, threads, pid, tid, false);
-	up_read(&threads->lock);
-	return th;
+	return __machine__findnew_thread(machine, pid, tid, /*create=*/false);
 }
 
 /*
@@ -896,7 +739,6 @@ static int machine__process_ksymbol_register(struct machine *machine,
 	struct symbol *sym;
 	struct dso *dso;
 	struct map *map = maps__find(machine__kernel_maps(machine), event->ksymbol.addr);
-	bool put_map = false;
 	int err = 0;
 
 	if (!map) {
@@ -913,12 +755,6 @@ static int machine__process_ksymbol_register(struct machine *machine,
 			err = -ENOMEM;
 			goto out;
 		}
-		/*
-		 * The inserted map has a get on it, we need to put to release
-		 * the reference count here, but do it after all accesses are
-		 * done.
-		 */
-		put_map = true;
 		if (event->ksymbol.ksym_type == PERF_RECORD_KSYMBOL_TYPE_OOL) {
 			dso->binary_type = DSO_BINARY_TYPE__OOL;
 			dso->data.file_size = event->ksymbol.len;
@@ -952,8 +788,7 @@ static int machine__process_ksymbol_register(struct machine *machine,
 	}
 	dso__insert_symbol(dso, sym);
 out:
-	if (put_map)
-		map__put(map);
+	map__put(map);
 	return err;
 }
 
@@ -977,7 +812,7 @@ static int machine__process_ksymbol_unregister(struct machine *machine,
 		if (sym)
 			dso__delete_symbol(dso, sym);
 	}
-
+	map__put(map);
 	return 0;
 }
 
@@ -1005,11 +840,11 @@ int machine__process_text_poke(struct machine *machine, union perf_event *event,
 		perf_event__fprintf_text_poke(event, machine, stdout);
 
 	if (!event->text_poke.new_len)
-		return 0;
+		goto out;
 
 	if (cpumode != PERF_RECORD_MISC_KERNEL) {
 		pr_debug("%s: unsupported cpumode - ignoring\n", __func__);
-		return 0;
+		goto out;
 	}
 
 	if (dso) {
@@ -1032,7 +867,8 @@ int machine__process_text_poke(struct machine *machine, union perf_event *event,
 		pr_debug("Failed to find kernel text poke address map for %#" PRI_lx64 "\n",
 			 event->text_poke.addr);
 	}
-
+out:
+	map__put(map);
 	return 0;
 }
 
@@ -1120,29 +956,30 @@ size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp)
 	return printed;
 }
 
-size_t machine__fprintf(struct machine *machine, FILE *fp)
-{
-	struct rb_node *nd;
-	size_t ret;
-	int i;
-
-	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
-		struct threads *threads = &machine->threads[i];
-
-		down_read(&threads->lock);
+struct machine_fprintf_cb_args {
+	FILE *fp;
+	size_t printed;
+};
 
-		ret = fprintf(fp, "Threads: %u\n", threads->nr);
+static int machine_fprintf_cb(struct thread *thread, void *data)
+{
+	struct machine_fprintf_cb_args *args = data;
 
-		for (nd = rb_first_cached(&threads->entries); nd;
-		     nd = rb_next(nd)) {
-			struct thread *pos = rb_entry(nd, struct thread_rb_node, rb_node)->thread;
+	/* TODO: handle fprintf errors. */
+	args->printed += thread__fprintf(thread, args->fp);
+	return 0;
+}
 
-			ret += thread__fprintf(pos, fp);
-		}
+size_t machine__fprintf(struct machine *machine, FILE *fp)
+{
+	struct machine_fprintf_cb_args args = {
+		.fp = fp,
+		.printed = 0,
+	};
+	size_t ret = fprintf(fp, "Threads: %zu\n", threads__nr(&machine->threads));
 
-		up_read(&threads->lock);
-	}
-	return ret;
+	machine__for_each_thread(machine, machine_fprintf_cb, &args);
+	return ret + args.printed;
 }
 
 static struct dso *machine__get_kernel(struct machine *machine)
@@ -1300,9 +1137,10 @@ static int machine__map_x86_64_entry_trampolines_cb(struct map *map, void *data)
 		return 0;
 
 	dest_map = maps__find(args->kmaps, map__pgoff(map));
-	if (dest_map != map)
+	if (RC_CHK_ACCESS(dest_map) != RC_CHK_ACCESS(map))
 		map__set_pgoff(map, map__map_ip(dest_map, map__pgoff(map)));
 
+	map__put(dest_map);
 	args->found = true;
 	return 0;
 }
@@ -1543,8 +1381,10 @@ static int maps__set_module_path(struct maps *maps, const char *path, struct kmo
 		return 0;
 
 	long_name = strdup(path);
-	if (long_name == NULL)
+	if (long_name == NULL) {
+		map__put(map);
 		return -ENOMEM;
+	}
 
 	dso = map__dso(map);
 	dso__set_long_name(dso, long_name, true);
@@ -1558,7 +1398,7 @@ static int maps__set_module_path(struct maps *maps, const char *path, struct kmo
 		dso->symtab_type++;
 		dso->comp = m->comp;
 	}
-
+	map__put(map);
 	return 0;
 }
 
@@ -1765,8 +1605,10 @@ int machine__create_kernel_maps(struct machine *machine)
 		struct map *next = maps__find_next_entry(machine__kernel_maps(machine),
 							 machine__kernel_map(machine));
 
-		if (next)
+		if (next) {
 			machine__set_kernel_mmap(machine, start, map__start(next));
+			map__put(next);
+		}
 	}
 
 out_put:
@@ -2060,36 +1902,9 @@ out_problem:
 	return 0;
 }
 
-static void __machine__remove_thread(struct machine *machine, struct thread_rb_node *nd,
-				     struct thread *th, bool lock)
-{
-	struct threads *threads = machine__threads(machine, thread__tid(th));
-
-	if (!nd)
-		nd = thread_rb_node__find(th, &threads->entries.rb_root);
-
-	if (threads->last_match && RC_CHK_EQUAL(threads->last_match, th))
-		threads__set_last_match(threads, NULL);
-
-	if (lock)
-		down_write(&threads->lock);
-
-	BUG_ON(refcount_read(thread__refcnt(th)) == 0);
-
-	thread__put(nd->thread);
-	rb_erase_cached(&nd->rb_node, &threads->entries);
-	RB_CLEAR_NODE(&nd->rb_node);
-	--threads->nr;
-
-	free(nd);
-
-	if (lock)
-		up_write(&threads->lock);
-}
-
 void machine__remove_thread(struct machine *machine, struct thread *th)
 {
-	return __machine__remove_thread(machine, NULL, th, true);
+	return threads__remove(&machine->threads, th);
 }
 
 int machine__process_fork_event(struct machine *machine, union perf_event *event,
@@ -3223,23 +3038,7 @@ int machine__for_each_thread(struct machine *machine,
 			     int (*fn)(struct thread *thread, void *p),
 			     void *priv)
 {
-	struct threads *threads;
-	struct rb_node *nd;
-	int rc = 0;
-	int i;
-
-	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
-		threads = &machine->threads[i];
-		for (nd = rb_first_cached(&threads->entries); nd;
-		     nd = rb_next(nd)) {
-			struct thread_rb_node *trb = rb_entry(nd, struct thread_rb_node, rb_node);
-
-			rc = fn(trb->thread, priv);
-			if (rc != 0)
-				return rc;
-		}
-	}
-	return rc;
+	return threads__for_each_thread(&machine->threads, fn, priv);
 }
 
 int machines__for_each_thread(struct machines *machines,
@@ -3263,6 +3062,36 @@ int machines__for_each_thread(struct machines *machines,
 	return rc;
 }
 
+
+static int thread_list_cb(struct thread *thread, void *data)
+{
+	struct list_head *list = data;
+	struct thread_list *entry = malloc(sizeof(*entry));
+
+	if (!entry)
+		return -ENOMEM;
+
+	entry->thread = thread__get(thread);
+	list_add_tail(&entry->list, list);
+	return 0;
+}
+
+int machine__thread_list(struct machine *machine, struct list_head *list)
+{
+	return machine__for_each_thread(machine, thread_list_cb, list);
+}
+
+void thread_list__delete(struct list_head *list)
+{
+	struct thread_list *pos, *next;
+
+	list_for_each_entry_safe(pos, next, list, list) {
+		thread__zput(pos->thread);
+		list_del(&pos->list);
+		free(pos);
+	}
+}
+
 pid_t machine__get_current_tid(struct machine *machine, int cpu)
 {
 	if (cpu < 0 || (size_t)cpu >= machine->current_tid_sz)