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, 190 insertions, 0 deletions

diff --git a/tools/perf/util/threads.c b/tools/perf/util/threads.c
new file mode 100644
index 000000000000..ff2b169e0085
--- /dev/null
+++ b/tools/perf/util/threads.c
@@ -0,0 +1,190 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "threads.h"
+#include "machine.h"
+#include "thread.h"
+
+static struct threads_table_entry *threads__table(struct threads *threads, pid_t tid)
+{
+	/* Cast it to handle tid == -1 */
+	return &threads->table[(unsigned int)tid % THREADS__TABLE_SIZE];
+}
+
+static size_t key_hash(long key, void *ctx __maybe_unused)
+{
+	/* The table lookup removes low bit entropy, but this is just ignored here. */
+	return key;
+}
+
+static bool key_equal(long key1, long key2, void *ctx __maybe_unused)
+{
+	return key1 == key2;
+}
+
+void threads__init(struct threads *threads)
+{
+	for (int i = 0; i < THREADS__TABLE_SIZE; i++) {
+		struct threads_table_entry *table = &threads->table[i];
+
+		hashmap__init(&table->shard, key_hash, key_equal, NULL);
+		init_rwsem(&table->lock);
+		table->last_match = NULL;
+	}
+}
+
+void threads__exit(struct threads *threads)
+{
+	threads__remove_all_threads(threads);
+	for (int i = 0; i < THREADS__TABLE_SIZE; i++) {
+		struct threads_table_entry *table = &threads->table[i];
+
+		hashmap__clear(&table->shard);
+		exit_rwsem(&table->lock);
+	}
+}
+
+size_t threads__nr(struct threads *threads)
+{
+	size_t nr = 0;
+
+	for (int i = 0; i < THREADS__TABLE_SIZE; i++) {
+		struct threads_table_entry *table = &threads->table[i];
+
+		down_read(&table->lock);
+		nr += hashmap__size(&table->shard);
+		up_read(&table->lock);
+	}
+	return nr;
+}
+
+/*
+ * 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_table_entry__get_last_match(struct threads_table_entry *table,
+							    pid_t tid)
+{
+	struct thread *th, *res = NULL;
+
+	th = table->last_match;
+	if (th != NULL) {
+		if (thread__tid(th) == tid)
+			res = thread__get(th);
+	}
+	return res;
+}
+
+static void __threads_table_entry__set_last_match(struct threads_table_entry *table,
+						  struct thread *th)
+{
+	thread__put(table->last_match);
+	table->last_match = thread__get(th);
+}
+
+static void threads_table_entry__set_last_match(struct threads_table_entry *table,
+						struct thread *th)
+{
+	down_write(&table->lock);
+	__threads_table_entry__set_last_match(table, th);
+	up_write(&table->lock);
+}
+
+struct thread *threads__find(struct threads *threads, pid_t tid)
+{
+	struct threads_table_entry *table  = threads__table(threads, tid);
+	struct thread *res;
+
+	down_read(&table->lock);
+	res = __threads_table_entry__get_last_match(table, tid);
+	if (!res) {
+		if (hashmap__find(&table->shard, tid, &res))
+			res = thread__get(res);
+	}
+	up_read(&table->lock);
+	if (res)
+		threads_table_entry__set_last_match(table, res);
+	return res;
+}
+
+struct thread *threads__findnew(struct threads *threads, pid_t pid, pid_t tid, bool *created)
+{
+	struct threads_table_entry *table  = threads__table(threads, tid);
+	struct thread *res = NULL;
+
+	*created = false;
+	down_write(&table->lock);
+	res = thread__new(pid, tid);
+	if (res) {
+		if (hashmap__add(&table->shard, tid, res)) {
+			/* Add failed. Assume a race so find other entry. */
+			thread__put(res);
+			res = NULL;
+			if (hashmap__find(&table->shard, tid, &res))
+				res = thread__get(res);
+		} else {
+			res = thread__get(res);
+			*created = true;
+		}
+		if (res)
+			__threads_table_entry__set_last_match(table, res);
+	}
+	up_write(&table->lock);
+	return res;
+}
+
+void threads__remove_all_threads(struct threads *threads)
+{
+	for (int i = 0; i < THREADS__TABLE_SIZE; i++) {
+		struct threads_table_entry *table = &threads->table[i];
+		struct hashmap_entry *cur, *tmp;
+		size_t bkt;
+
+		down_write(&table->lock);
+		__threads_table_entry__set_last_match(table, NULL);
+		hashmap__for_each_entry_safe((&table->shard), cur, tmp, bkt) {
+			struct thread *old_value;
+
+			hashmap__delete(&table->shard, cur->key, /*old_key=*/NULL, &old_value);
+			thread__put(old_value);
+		}
+		up_write(&table->lock);
+	}
+}
+
+void threads__remove(struct threads *threads, struct thread *thread)
+{
+	struct threads_table_entry *table  = threads__table(threads, thread__tid(thread));
+	struct thread *old_value;
+
+	down_write(&table->lock);
+	if (table->last_match && RC_CHK_EQUAL(table->last_match, thread))
+		__threads_table_entry__set_last_match(table, NULL);
+
+	hashmap__delete(&table->shard, thread__tid(thread), /*old_key=*/NULL, &old_value);
+	thread__put(old_value);
+	up_write(&table->lock);
+}
+
+int threads__for_each_thread(struct threads *threads,
+			     int (*fn)(struct thread *thread, void *data),
+			     void *data)
+{
+	for (int i = 0; i < THREADS__TABLE_SIZE; i++) {
+		struct threads_table_entry *table = &threads->table[i];
+		struct hashmap_entry *cur;
+		size_t bkt;
+
+		down_read(&table->lock);
+		hashmap__for_each_entry((&table->shard), cur, bkt) {
+			int rc = fn((struct thread *)cur->pvalue, data);
+
+			if (rc != 0) {
+				up_read(&table->lock);
+				return rc;
+			}
+		}
+		up_read(&table->lock);
+	}
+	return 0;
+
+}