patch, 9 partsTrace2 stopwatch timers and global counters

diff --git a/trace2/tr2_tls.h b/trace2/tr2_tls.h
index b1e327a928e..a90bd639d48 100644
--- a/trace2/tr2_tls.h
+++ b/trace2/tr2_tls.h
@@ -11,8 +11,8 @@
 struct tr2tls_thread_ctx {
 	struct strbuf thread_name;
 	uint64_t *array_us_start;
-	int alloc;
-	int nr_open_regions; /* plays role of "nr" in ALLOC_GROW */
+	size_t alloc;
+	size_t nr_open_regions; /* plays role of "nr" in ALLOC_GROW */
 	int thread_id;
 };
 

trace2/tr2_tgt_event.c, trace2/tr2_tgt_perf.c, trace2/tr2_tls.c, trace2/tr2_tls.h

diff --git a/trace2/tr2_tgt_event.c b/trace2/tr2_tgt_event.c
index 3a0014417cc..ca48d00aebc 100644
--- a/trace2/tr2_tgt_event.c
+++ b/trace2/tr2_tgt_event.c
@@ -88,7 +88,7 @@ static void event_fmt_prepare(const char *event_name, const char *file,
 
 	jw_object_string(jw, "event", event_name);
 	jw_object_string(jw, "sid", tr2_sid_get());
-	jw_object_string(jw, "thread", ctx->thread_name.buf);
+	jw_object_string(jw, "thread", ctx->thread_name);
 
 	/*
 	 * In brief mode, only emit <time> on these 2 event types.
diff --git a/trace2/tr2_tgt_perf.c b/trace2/tr2_tgt_perf.c
index e4acca13d64..c3e57fcb3c0 100644
--- a/trace2/tr2_tgt_perf.c
+++ b/trace2/tr2_tgt_perf.c
@@ -106,7 +106,7 @@ static void perf_fmt_prepare(const char *event_name,
 
 	strbuf_addf(buf, "d%d | ", tr2_sid_depth());
 	strbuf_addf(buf, "%-*s | %-*s | ", TR2_MAX_THREAD_NAME,
-		    ctx->thread_name.buf, TR2FMT_PERF_MAX_EVENT_NAME,
+		    ctx->thread_name, TR2FMT_PERF_MAX_EVENT_NAME,
 		    event_name);
 
 	len = buf->len + TR2FMT_PERF_REPO_WIDTH;
diff --git a/trace2/tr2_tls.c b/trace2/tr2_tls.c
index 7da94aba522..cd8b9f2f0a0 100644
--- a/trace2/tr2_tls.c
+++ b/trace2/tr2_tls.c
@@ -35,6 +35,7 @@ struct tr2tls_thread_ctx *tr2tls_create_self(const char *thread_name,
 					     uint64_t us_thread_start)
 {
 	struct tr2tls_thread_ctx *ctx = xcalloc(1, sizeof(*ctx));
+	struct strbuf buf_name = STRBUF_INIT;
 
 	/*
 	 * Implicitly "tr2tls_push_self()" to capture the thread's start
@@ -47,12 +48,13 @@ struct tr2tls_thread_ctx *tr2tls_create_self(const char *thread_name,
 
 	ctx->thread_id = tr2tls_locked_increment(&tr2_next_thread_id);
 
-	strbuf_init(&ctx->thread_name, 0);
 	if (ctx->thread_id)
-		strbuf_addf(&ctx->thread_name, "th%02d:", ctx->thread_id);
-	strbuf_addstr(&ctx->thread_name, thread_name);
-	if (ctx->thread_name.len > TR2_MAX_THREAD_NAME)
-		strbuf_setlen(&ctx->thread_name, TR2_MAX_THREAD_NAME);
+		strbuf_addf(&buf_name, "th%02d:", ctx->thread_id);
+	strbuf_addstr(&buf_name, thread_name);
+	if (buf_name.len > TR2_MAX_THREAD_NAME)
+		strbuf_setlen(&buf_name, TR2_MAX_THREAD_NAME);
+
+	ctx->thread_name = strbuf_detach(&buf_name, NULL);
 
 	pthread_setspecific(tr2tls_key, ctx);
 
@@ -95,7 +97,7 @@ void tr2tls_unset_self(void)
 
 	pthread_setspecific(tr2tls_key, NULL);
 
-	strbuf_release(&ctx->thread_name);
+	free(ctx->thread_name);
 	free(ctx->array_us_start);
 	free(ctx);
 }
@@ -113,7 +115,7 @@ void tr2tls_pop_self(void)
 	struct tr2tls_thread_ctx *ctx = tr2tls_get_self();
 
 	if (!ctx->nr_open_regions)
-		BUG("no open regions in thread '%s'", ctx->thread_name.buf);
+		BUG("no open regions in thread '%s'", ctx->thread_name);
 
 	ctx->nr_open_regions--;
 }
diff --git a/trace2/tr2_tls.h b/trace2/tr2_tls.h
index a90bd639d48..d968da6a679 100644
--- a/trace2/tr2_tls.h
+++ b/trace2/tr2_tls.h
@@ -9,7 +9,7 @@
 #define TR2_MAX_THREAD_NAME (24)
 
 struct tr2tls_thread_ctx {
-	struct strbuf thread_name;
+	char *thread_name;
 	uint64_t *array_us_start;
 	size_t alloc;
 	size_t nr_open_regions; /* plays role of "nr" in ALLOC_GROW */

trace2/tr2_tls.c, trace2/tr2_tls.h

diff --git a/trace2/tr2_tls.c b/trace2/tr2_tls.c
index cd8b9f2f0a0..b68d297bf51 100644
--- a/trace2/tr2_tls.c
+++ b/trace2/tr2_tls.c
@@ -15,7 +15,16 @@ static uint64_t tr2tls_us_start_process;
 static pthread_mutex_t tr2tls_mutex;
 static pthread_key_t tr2tls_key;
 
-static int tr2_next_thread_id; /* modify under lock */
+/*
+ * This list owns all of the thread-specific CTX data.
+ *
+ * While a thread is alive it is associated with a CTX (owned by this
+ * list) and that CTX is installed in the thread's TLS data area.
+ *
+ * Similarly, `tr2tls_thread_main` points to a CTX contained within
+ * this list.
+ */
+static struct tr2tls_thread_ctx *tr2tls_ctx_list; /* modify under lock */
 
 void tr2tls_start_process_clock(void)
 {
@@ -46,7 +55,12 @@ struct tr2tls_thread_ctx *tr2tls_create_self(const char *thread_name,
 	ctx->array_us_start = (uint64_t *)xcalloc(ctx->alloc, sizeof(uint64_t));
 	ctx->array_us_start[ctx->nr_open_regions++] = us_thread_start;
 
-	ctx->thread_id = tr2tls_locked_increment(&tr2_next_thread_id);
+	pthread_mutex_lock(&tr2tls_mutex);
+	if (tr2tls_ctx_list)
+		ctx->thread_id = tr2tls_ctx_list->thread_id + 1;
+	ctx->next_ctx = tr2tls_ctx_list;
+	tr2tls_ctx_list = ctx;
+	pthread_mutex_unlock(&tr2tls_mutex);
 
 	if (ctx->thread_id)
 		strbuf_addf(&buf_name, "th%02d:", ctx->thread_id);
@@ -91,15 +105,7 @@ int tr2tls_is_main_thread(void)
 
 void tr2tls_unset_self(void)
 {
-	struct tr2tls_thread_ctx *ctx;
-
-	ctx = tr2tls_get_self();
-
 	pthread_setspecific(tr2tls_key, NULL);
-
-	free(ctx->thread_name);
-	free(ctx->array_us_start);
-	free(ctx);
 }
 
 void tr2tls_push_self(uint64_t us_now)
@@ -163,11 +169,23 @@ void tr2tls_init(void)
 
 void tr2tls_release(void)
 {
+	struct tr2tls_thread_ctx *ctx = tr2tls_ctx_list;
+
 	tr2tls_unset_self();
 	tr2tls_thread_main = NULL;
 
 	pthread_mutex_destroy(&tr2tls_mutex);
 	pthread_key_delete(tr2tls_key);
+
+	while (ctx) {
+		struct tr2tls_thread_ctx *next = ctx->next_ctx;
+
+		free(ctx->thread_name);
+		free(ctx->array_us_start);
+		free(ctx);
+
+		ctx = next;
+	}
 }
 
 int tr2tls_locked_increment(int *p)
diff --git a/trace2/tr2_tls.h b/trace2/tr2_tls.h
index d968da6a679..c6b6c69b25a 100644
--- a/trace2/tr2_tls.h
+++ b/trace2/tr2_tls.h
@@ -9,6 +9,7 @@
 #define TR2_MAX_THREAD_NAME (24)
 
 struct tr2tls_thread_ctx {
+	struct tr2tls_thread_ctx *next_ctx;
 	char *thread_name;
 	uint64_t *array_us_start;
 	size_t alloc;
@@ -45,7 +46,7 @@ struct tr2tls_thread_ctx *tr2tls_get_self(void);
 int tr2tls_is_main_thread(void);
 
 /*
- * Free our TLS data.
+ * Disassociate thread's TLS CTX data from the thread.
  */
 void tr2tls_unset_self(void);
 

diff --git a/trace2/tr2_tgt_event.c b/trace2/tr2_tgt_event.c
index ca48d00aebc..4ce50944298 100644
--- a/trace2/tr2_tgt_event.c
+++ b/trace2/tr2_tgt_event.c
@@ -81,14 +81,17 @@ static void fn_term(void)
  */
 static void event_fmt_prepare(const char *event_name, const char *file,
 			      int line, const struct repository *repo,
-			      struct json_writer *jw)
+			      struct json_writer *jw,
+			      const char *thread_name_override)
 {
-	struct tr2tls_thread_ctx *ctx = tr2tls_get_self();
 	struct tr2_tbuf tb_now;
 
 	jw_object_string(jw, "event", event_name);
 	jw_object_string(jw, "sid", tr2_sid_get());
-	jw_object_string(jw, "thread", ctx->thread_name);
+	jw_object_string(jw, "thread",
+			 ((thread_name_override && *thread_name_override)
+			  ? thread_name_override
+			  : tr2tls_get_self()->thread_name));
 
 	/*
 	 * In brief mode, only emit <time> on these 2 event types.
@@ -114,7 +117,7 @@ static void fn_too_many_files_fl(const char *file, int line)
 	struct json_writer jw = JSON_WRITER_INIT;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_end(&jw);
 
 	tr2_dst_write_line(&tr2dst_event, &jw.json);
@@ -127,7 +130,7 @@ static void fn_version_fl(const char *file, int line)
 	struct json_writer jw = JSON_WRITER_INIT;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_object_string(&jw, "evt", TR2_EVENT_VERSION);
 	jw_object_string(&jw, "exe", git_version_string);
 	jw_end(&jw);
@@ -147,7 +150,7 @@ static void fn_start_fl(const char *file, int line,
 	double t_abs = (double)us_elapsed_absolute / 1000000.0;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_object_double(&jw, "t_abs", 6, t_abs);
 	jw_object_inline_begin_array(&jw, "argv");
 	jw_array_argv(&jw, argv);
@@ -166,7 +169,7 @@ static void fn_exit_fl(const char *file, int line, uint64_t us_elapsed_absolute,
 	double t_abs = (double)us_elapsed_absolute / 1000000.0;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_object_double(&jw, "t_abs", 6, t_abs);
 	jw_object_intmax(&jw, "code", code);
 	jw_end(&jw);
@@ -182,7 +185,7 @@ static void fn_signal(uint64_t us_elapsed_absolute, int signo)
 	double t_abs = (double)us_elapsed_absolute / 1000000.0;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, __FILE__, __LINE__, NULL, &jw);
+	event_fmt_prepare(event_name, __FILE__, __LINE__, NULL, &jw, NULL);
 	jw_object_double(&jw, "t_abs", 6, t_abs);
 	jw_object_intmax(&jw, "signo", signo);
 	jw_end(&jw);
@@ -198,7 +201,7 @@ static void fn_atexit(uint64_t us_elapsed_absolute, int code)
 	double t_abs = (double)us_elapsed_absolute / 1000000.0;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, __FILE__, __LINE__, NULL, &jw);
+	event_fmt_prepare(event_name, __FILE__, __LINE__, NULL, &jw, NULL);
 	jw_object_double(&jw, "t_abs", 6, t_abs);
 	jw_object_intmax(&jw, "code", code);
 	jw_end(&jw);
@@ -231,7 +234,7 @@ static void fn_error_va_fl(const char *file, int line, const char *fmt,
 	struct json_writer jw = JSON_WRITER_INIT;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	maybe_add_string_va(&jw, "msg", fmt, ap);
 	/*
 	 * Also emit the format string as a field in case
@@ -253,7 +256,7 @@ static void fn_command_path_fl(const char *file, int line, const char *pathname)
 	struct json_writer jw = JSON_WRITER_INIT;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_object_string(&jw, "path", pathname);
 	jw_end(&jw);
 
@@ -268,7 +271,7 @@ static void fn_command_ancestry_fl(const char *file, int line, const char **pare
 	struct json_writer jw = JSON_WRITER_INIT;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_object_inline_begin_array(&jw, "ancestry");
 
 	while ((parent_name = *parent_names++))
@@ -288,7 +291,7 @@ static void fn_command_name_fl(const char *file, int line, const char *name,
 	struct json_writer jw = JSON_WRITER_INIT;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_object_string(&jw, "name", name);
 	if (hierarchy && *hierarchy)
 		jw_object_string(&jw, "hierarchy", hierarchy);
@@ -304,7 +307,7 @@ static void fn_command_mode_fl(const char *file, int line, const char *mode)
 	struct json_writer jw = JSON_WRITER_INIT;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_object_string(&jw, "name", mode);
 	jw_end(&jw);
 
@@ -319,7 +322,7 @@ static void fn_alias_fl(const char *file, int line, const char *alias,
 	struct json_writer jw = JSON_WRITER_INIT;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_object_string(&jw, "alias", alias);
 	jw_object_inline_begin_array(&jw, "argv");
 	jw_array_argv(&jw, argv);
@@ -338,7 +341,7 @@ static void fn_child_start_fl(const char *file, int line,
 	struct json_writer jw = JSON_WRITER_INIT;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_object_intmax(&jw, "child_id", cmd->trace2_child_id);
 	if (cmd->trace2_hook_name) {
 		jw_object_string(&jw, "child_class", "hook");
@@ -371,7 +374,7 @@ static void fn_child_exit_fl(const char *file, int line,
 	double t_rel = (double)us_elapsed_child / 1000000.0;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_object_intmax(&jw, "child_id", cid);
 	jw_object_intmax(&jw, "pid", pid);
 	jw_object_intmax(&jw, "code", code);
@@ -392,7 +395,7 @@ static void fn_child_ready_fl(const char *file, int line,
 	double t_rel = (double)us_elapsed_child / 1000000.0;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_object_intmax(&jw, "child_id", cid);
 	jw_object_intmax(&jw, "pid", pid);
 	jw_object_string(&jw, "ready", ready);
@@ -411,7 +414,7 @@ static void fn_thread_start_fl(const char *file, int line,
 	struct json_writer jw = JSON_WRITER_INIT;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_end(&jw);
 
 	tr2_dst_write_line(&tr2dst_event, &jw.json);
@@ -427,7 +430,7 @@ static void fn_thread_exit_fl(const char *file, int line,
 	double t_rel = (double)us_elapsed_thread / 1000000.0;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_object_double(&jw, "t_rel", 6, t_rel);
 	jw_end(&jw);
 
@@ -442,7 +445,7 @@ static void fn_exec_fl(const char *file, int line, uint64_t us_elapsed_absolute,
 	struct json_writer jw = JSON_WRITER_INIT;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_object_intmax(&jw, "exec_id", exec_id);
 	if (exe)
 		jw_object_string(&jw, "exe", exe);
@@ -463,7 +466,7 @@ static void fn_exec_result_fl(const char *file, int line,
 	struct json_writer jw = JSON_WRITER_INIT;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_object_intmax(&jw, "exec_id", exec_id);
 	jw_object_intmax(&jw, "code", code);
 	jw_end(&jw);
@@ -479,7 +482,7 @@ static void fn_param_fl(const char *file, int line, const char *param,
 	struct json_writer jw = JSON_WRITER_INIT;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_object_string(&jw, "param", param);
 	jw_object_string(&jw, "value", value);
 	jw_end(&jw);
@@ -495,7 +498,7 @@ static void fn_repo_fl(const char *file, int line,
 	struct json_writer jw = JSON_WRITER_INIT;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, repo, &jw);
+	event_fmt_prepare(event_name, file, line, repo, &jw, NULL);
 	jw_object_string(&jw, "worktree", repo->worktree);
 	jw_end(&jw);
 
@@ -516,7 +519,7 @@ static void fn_region_enter_printf_va_fl(const char *file, int line,
 		struct json_writer jw = JSON_WRITER_INIT;
 
 		jw_object_begin(&jw, 0);
-		event_fmt_prepare(event_name, file, line, repo, &jw);
+		event_fmt_prepare(event_name, file, line, repo, &jw, NULL);
 		jw_object_intmax(&jw, "nesting", ctx->nr_open_regions);
 		if (category)
 			jw_object_string(&jw, "category", category);
@@ -542,7 +545,7 @@ static void fn_region_leave_printf_va_fl(
 		double t_rel = (double)us_elapsed_region / 1000000.0;
 
 		jw_object_begin(&jw, 0);
-		event_fmt_prepare(event_name, file, line, repo, &jw);
+		event_fmt_prepare(event_name, file, line, repo, &jw, NULL);
 		jw_object_double(&jw, "t_rel", 6, t_rel);
 		jw_object_intmax(&jw, "nesting", ctx->nr_open_regions);
 		if (category)
@@ -570,7 +573,7 @@ static void fn_data_fl(const char *file, int line, uint64_t us_elapsed_absolute,
 		double t_rel = (double)us_elapsed_region / 1000000.0;
 
 		jw_object_begin(&jw, 0);
-		event_fmt_prepare(event_name, file, line, repo, &jw);
+		event_fmt_prepare(event_name, file, line, repo, &jw, NULL);
 		jw_object_double(&jw, "t_abs", 6, t_abs);
 		jw_object_double(&jw, "t_rel", 6, t_rel);
 		jw_object_intmax(&jw, "nesting", ctx->nr_open_regions);
@@ -598,7 +601,7 @@ static void fn_data_json_fl(const char *file, int line,
 		double t_rel = (double)us_elapsed_region / 1000000.0;
 
 		jw_object_begin(&jw, 0);
-		event_fmt_prepare(event_name, file, line, repo, &jw);
+		event_fmt_prepare(event_name, file, line, repo, &jw, NULL);
 		jw_object_double(&jw, "t_abs", 6, t_abs);
 		jw_object_double(&jw, "t_rel", 6, t_rel);
 		jw_object_intmax(&jw, "nesting", ctx->nr_open_regions);

diff --git a/trace2/tr2_tgt_perf.c b/trace2/tr2_tgt_perf.c
index c3e57fcb3c0..47293e99d4b 100644
--- a/trace2/tr2_tgt_perf.c
+++ b/trace2/tr2_tgt_perf.c
@@ -64,9 +64,14 @@ static void perf_fmt_prepare(const char *event_name,
 			     int line, const struct repository *repo,
 			     uint64_t *p_us_elapsed_absolute,
 			     uint64_t *p_us_elapsed_relative,
-			     const char *category, struct strbuf *buf)
+			     const char *category, struct strbuf *buf,
+			     const char *thread_name_override)
 {
 	int len;
+	const char *thread_name =
+		((thread_name_override && *thread_name_override)
+		 ? thread_name_override
+		 : ctx->thread_name);
 
 	strbuf_setlen(buf, 0);
 
@@ -106,7 +111,7 @@ static void perf_fmt_prepare(const char *event_name,
 
 	strbuf_addf(buf, "d%d | ", tr2_sid_depth());
 	strbuf_addf(buf, "%-*s | %-*s | ", TR2_MAX_THREAD_NAME,
-		    ctx->thread_name, TR2FMT_PERF_MAX_EVENT_NAME,
+		    thread_name, TR2FMT_PERF_MAX_EVENT_NAME,
 		    event_name);
 
 	len = buf->len + TR2FMT_PERF_REPO_WIDTH;
@@ -140,14 +145,15 @@ static void perf_io_write_fl(const char *file, int line, const char *event_name,
 			     uint64_t *p_us_elapsed_absolute,
 			     uint64_t *p_us_elapsed_relative,
 			     const char *category,
-			     const struct strbuf *buf_payload)
+			     const struct strbuf *buf_payload,
+			     const char *thread_name_override)
 {
 	struct tr2tls_thread_ctx *ctx = tr2tls_get_self();
 	struct strbuf buf_line = STRBUF_INIT;
 
 	perf_fmt_prepare(event_name, ctx, file, line, repo,
 			 p_us_elapsed_absolute, p_us_elapsed_relative, category,
-			 &buf_line);
+			 &buf_line, thread_name_override);
 	strbuf_addbuf(&buf_line, buf_payload);
 	tr2_dst_write_line(&tr2dst_perf, &buf_line);
 	strbuf_release(&buf_line);
@@ -161,7 +167,7 @@ static void fn_version_fl(const char *file, int line)
 	strbuf_addstr(&buf_payload, git_version_string);
 
 	perf_io_write_fl(file, line, event_name, NULL, NULL, NULL, NULL,
-			 &buf_payload);
+			 &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -174,7 +180,7 @@ static void fn_start_fl(const char *file, int line,
 	sq_append_quote_argv_pretty(&buf_payload, argv);
 
 	perf_io_write_fl(file, line, event_name, NULL, &us_elapsed_absolute,
-			 NULL, NULL, &buf_payload);
+			 NULL, NULL, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -187,7 +193,7 @@ static void fn_exit_fl(const char *file, int line, uint64_t us_elapsed_absolute,
 	strbuf_addf(&buf_payload, "code:%d", code);
 
 	perf_io_write_fl(file, line, event_name, NULL, &us_elapsed_absolute,
-			 NULL, NULL, &buf_payload);
+			 NULL, NULL, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -199,7 +205,7 @@ static void fn_signal(uint64_t us_elapsed_absolute, int signo)
 	strbuf_addf(&buf_payload, "signo:%d", signo);
 
 	perf_io_write_fl(__FILE__, __LINE__, event_name, NULL,
-			 &us_elapsed_absolute, NULL, NULL, &buf_payload);
+			 &us_elapsed_absolute, NULL, NULL, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -211,7 +217,7 @@ static void fn_atexit(uint64_t us_elapsed_absolute, int code)
 	strbuf_addf(&buf_payload, "code:%d", code);
 
 	perf_io_write_fl(__FILE__, __LINE__, event_name, NULL,
-			 &us_elapsed_absolute, NULL, NULL, &buf_payload);
+			 &us_elapsed_absolute, NULL, NULL, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -237,7 +243,7 @@ static void fn_error_va_fl(const char *file, int line, const char *fmt,
 	maybe_append_string_va(&buf_payload, fmt, ap);
 
 	perf_io_write_fl(file, line, event_name, NULL, NULL, NULL, NULL,
-			 &buf_payload);
+			 &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -249,7 +255,7 @@ static void fn_command_path_fl(const char *file, int line, const char *pathname)
 	strbuf_addstr(&buf_payload, pathname);
 
 	perf_io_write_fl(file, line, event_name, NULL, NULL, NULL, NULL,
-			 &buf_payload);
+			 &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -264,7 +270,7 @@ static void fn_command_ancestry_fl(const char *file, int line, const char **pare
 	strbuf_addch(&buf_payload, ']');
 
 	perf_io_write_fl(file, line, event_name, NULL, NULL, NULL, NULL,
-			 &buf_payload);
+			 &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -279,7 +285,7 @@ static void fn_command_name_fl(const char *file, int line, const char *name,
 		strbuf_addf(&buf_payload, " (%s)", hierarchy);
 
 	perf_io_write_fl(file, line, event_name, NULL, NULL, NULL, NULL,
-			 &buf_payload);
+			 &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -291,7 +297,7 @@ static void fn_command_mode_fl(const char *file, int line, const char *mode)
 	strbuf_addstr(&buf_payload, mode);
 
 	perf_io_write_fl(file, line, event_name, NULL, NULL, NULL, NULL,
-			 &buf_payload);
+			 &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -306,7 +312,7 @@ static void fn_alias_fl(const char *file, int line, const char *alias,
 	strbuf_addch(&buf_payload, ']');
 
 	perf_io_write_fl(file, line, event_name, NULL, NULL, NULL, NULL,
-			 &buf_payload);
+			 &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -342,7 +348,7 @@ static void fn_child_start_fl(const char *file, int line,
 	strbuf_addch(&buf_payload, ']');
 
 	perf_io_write_fl(file, line, event_name, NULL, &us_elapsed_absolute,
-			 NULL, NULL, &buf_payload);
+			 NULL, NULL, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -356,7 +362,7 @@ static void fn_child_exit_fl(const char *file, int line,
 	strbuf_addf(&buf_payload, "[ch%d] pid:%d code:%d", cid, pid, code);
 
 	perf_io_write_fl(file, line, event_name, NULL, &us_elapsed_absolute,
-			 &us_elapsed_child, NULL, &buf_payload);
+			 &us_elapsed_child, NULL, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -370,7 +376,7 @@ static void fn_child_ready_fl(const char *file, int line,
 	strbuf_addf(&buf_payload, "[ch%d] pid:%d ready:%s", cid, pid, ready);
 
 	perf_io_write_fl(file, line, event_name, NULL, &us_elapsed_absolute,
-			 &us_elapsed_child, NULL, &buf_payload);
+			 &us_elapsed_child, NULL, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -381,7 +387,7 @@ static void fn_thread_start_fl(const char *file, int line,
 	struct strbuf buf_payload = STRBUF_INIT;
 
 	perf_io_write_fl(file, line, event_name, NULL, &us_elapsed_absolute,
-			 NULL, NULL, &buf_payload);
+			 NULL, NULL, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -393,7 +399,7 @@ static void fn_thread_exit_fl(const char *file, int line,
 	struct strbuf buf_payload = STRBUF_INIT;
 
 	perf_io_write_fl(file, line, event_name, NULL, &us_elapsed_absolute,
-			 &us_elapsed_thread, NULL, &buf_payload);
+			 &us_elapsed_thread, NULL, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -414,7 +420,7 @@ static void fn_exec_fl(const char *file, int line, uint64_t us_elapsed_absolute,
 	strbuf_addch(&buf_payload, ']');
 
 	perf_io_write_fl(file, line, event_name, NULL, &us_elapsed_absolute,
-			 NULL, NULL, &buf_payload);
+			 NULL, NULL, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -430,7 +436,7 @@ static void fn_exec_result_fl(const char *file, int line,
 		strbuf_addf(&buf_payload, " err:%s", strerror(code));
 
 	perf_io_write_fl(file, line, event_name, NULL, &us_elapsed_absolute,
-			 NULL, NULL, &buf_payload);
+			 NULL, NULL, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -443,7 +449,7 @@ static void fn_param_fl(const char *file, int line, const char *param,
 	strbuf_addf(&buf_payload, "%s:%s", param, value);
 
 	perf_io_write_fl(file, line, event_name, NULL, NULL, NULL, NULL,
-			 &buf_payload);
+			 &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -457,7 +463,7 @@ static void fn_repo_fl(const char *file, int line,
 	sq_quote_buf_pretty(&buf_payload, repo->worktree);
 
 	perf_io_write_fl(file, line, event_name, repo, NULL, NULL, NULL,
-			 &buf_payload);
+			 &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -479,7 +485,7 @@ static void fn_region_enter_printf_va_fl(const char *file, int line,
 	}
 
 	perf_io_write_fl(file, line, event_name, repo, &us_elapsed_absolute,
-			 NULL, category, &buf_payload);
+			 NULL, category, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -499,7 +505,7 @@ static void fn_region_leave_printf_va_fl(
 	}
 
 	perf_io_write_fl(file, line, event_name, repo, &us_elapsed_absolute,
-			 &us_elapsed_region, category, &buf_payload);
+			 &us_elapsed_region, category, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -514,7 +520,7 @@ static void fn_data_fl(const char *file, int line, uint64_t us_elapsed_absolute,
 	strbuf_addf(&buf_payload, "%s:%s", key, value);
 
 	perf_io_write_fl(file, line, event_name, repo, &us_elapsed_absolute,
-			 &us_elapsed_region, category, &buf_payload);
+			 &us_elapsed_region, category, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -530,7 +536,7 @@ static void fn_data_json_fl(const char *file, int line,
 	strbuf_addf(&buf_payload, "%s:%s", key, value->json.buf);
 
 	perf_io_write_fl(file, line, event_name, repo, &us_elapsed_absolute,
-			 &us_elapsed_region, category, &buf_payload);
+			 &us_elapsed_region, category, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -544,7 +550,7 @@ static void fn_printf_va_fl(const char *file, int line,
 	maybe_append_string_va(&buf_payload, fmt, ap);
 
 	perf_io_write_fl(file, line, event_name, NULL, &us_elapsed_absolute,
-			 NULL, NULL, &buf_payload);
+			 NULL, NULL, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 

Documentation/technical/api-trace2.txt, trace2/tr2_tgt.h, trace2/tr2_tgt_event.c, trace2/tr2_tgt_normal.c, trace2/tr2_tgt_perf.c

diff --git a/Documentation/technical/api-trace2.txt b/Documentation/technical/api-trace2.txt
index bb13ca3db8b..e6ed94ba814 100644
--- a/Documentation/technical/api-trace2.txt
+++ b/Documentation/technical/api-trace2.txt
@@ -391,7 +391,7 @@ only present on the "start" and "atexit" events.
 {
 	"event":"version",
 	...
-	"evt":"3",		       # EVENT format version
+	"evt":"4",		       # EVENT format version
 	"exe":"2.20.1.155.g426c96fcdb" # git version
 }
 ------------
@@ -815,6 +815,29 @@ The "value" field may be an integer or a string.
 }
 ------------
 
+`"timer"`::
+	This event is generated at the end of the program and contains
+	statistics for a global stopwatch timer.
++
+------------
+{
+	"event":"timer",
+	...
+	"name":"test",      # timer name
+	"count":42,         # number of start+stop intervals
+	"t_total":1.234,    # sum of all intervals (by thread or globally)
+	"t_min":0.1,        # shortest interval
+	"t_max":0.9,        # longest interval
+}
+------------
++
+Stopwatch timer data is independently collected by each thread and then
+aggregated for the whole program, so the total time reported here
+may exceed the "atexit" elapsed time of the program.
++
+Timer events may represent an individual thread or a summation across
+the entire program.  Summation events will have a unique thread name.
+
 == Example Trace2 API Usage
 
 Here is a hypothetical usage of the Trace2 API showing the intended
diff --git a/trace2/tr2_tgt.h b/trace2/tr2_tgt.h
index 65f94e15748..1f548eb4b93 100644
--- a/trace2/tr2_tgt.h
+++ b/trace2/tr2_tgt.h
@@ -96,6 +96,30 @@ typedef void(tr2_tgt_evt_printf_va_fl_t)(const char *file, int line,
 					 uint64_t us_elapsed_absolute,
 					 const char *fmt, va_list ap);
 
+/*
+ * Stopwatch timer event.  This function writes the previously accumlated
+ * stopwatch timer values to the event streams.  Unlike other Trace2 API
+ * events, this is decoupled from the data collection.
+ *
+ * This does not take a (file,line) pair because a timer event reports
+ * the cummulative time spend in the timer over a series of intervals
+ * -- it does not represent a single usage (like region or data events
+ * do).
+ *
+ * The thread name is optional.  If non-null it will override the
+ * value inherited from the caller's TLS CTX.  This allows data
+ * for global timers to be reported without associating it with a
+ * single thread.
+ */
+typedef void(tr2_tgt_evt_timer_t)(uint64_t us_elapsed_absolute,
+				  const char *thread_name,
+				  const char *category,
+				  const char *timer_name,
+				  uint64_t interval_count,
+				  uint64_t us_total_time,
+				  uint64_t us_min_time,
+				  uint64_t us_max_time);
+
 /*
  * "vtable" for a TRACE2 target.  Use NULL if a target does not want
  * to emit that message.
@@ -132,6 +156,7 @@ struct tr2_tgt {
 	tr2_tgt_evt_data_fl_t                   *pfn_data_fl;
 	tr2_tgt_evt_data_json_fl_t              *pfn_data_json_fl;
 	tr2_tgt_evt_printf_va_fl_t              *pfn_printf_va_fl;
+	tr2_tgt_evt_timer_t                     *pfn_timer;
 };
 /* clang-format on */
 
diff --git a/trace2/tr2_tgt_event.c b/trace2/tr2_tgt_event.c
index 4ce50944298..9b3905b920c 100644
--- a/trace2/tr2_tgt_event.c
+++ b/trace2/tr2_tgt_event.c
@@ -19,8 +19,13 @@ static struct tr2_dst tr2dst_event = { TR2_SYSENV_EVENT, 0, 0, 0, 0 };
  * interpretation of existing events or fields. Smaller changes, such as adding
  * a new field to an existing event, do not require an increment to the EVENT
  * format version.
+ *
+ * Verison 1: original version
+ * Version 2: added "too_many_files" event
+ * Version 3: added "child_ready" event
+ * Version 4: added "timer" event
  */
-#define TR2_EVENT_VERSION "3"
+#define TR2_EVENT_VERSION "4"
 
 /*
  * Region nesting limit for messages written to the event target.
@@ -615,6 +620,38 @@ static void fn_data_json_fl(const char *file, int line,
 	}
 }
 
+static void fn_timer(uint64_t us_elapsed_absolute,
+		     const char *thread_name,
+		     const char *category,
+		     const char *timer_name,
+		     uint64_t interval_count,
+		     uint64_t us_total_time,
+		     uint64_t us_min_time,
+		     uint64_t us_max_time)
+{
+	const char *event_name = "timer";
+	struct json_writer jw = JSON_WRITER_INIT;
+	double t_abs = (double)us_elapsed_absolute / 1000000.0;
+
+	double t_total = (double)us_total_time / 1000000.0;
+	double t_min   = (double)us_min_time   / 1000000.0;
+	double t_max   = (double)us_max_time   / 1000000.0;
+
+	jw_object_begin(&jw, 0);
+	event_fmt_prepare(event_name, __FILE__, __LINE__, NULL, &jw, thread_name);
+	jw_object_double(&jw, "t_abs", 6, t_abs);
+	jw_object_string(&jw, "name", timer_name);
+	jw_object_intmax(&jw, "count", interval_count);
+	jw_object_double(&jw, "t_total", 6, t_total);
+	jw_object_double(&jw, "t_min", 6, t_min);
+	jw_object_double(&jw, "t_max", 6, t_max);
+
+	jw_end(&jw);
+
+	tr2_dst_write_line(&tr2dst_event, &jw.json);
+	jw_release(&jw);
+}
+
 struct tr2_tgt tr2_tgt_event = {
 	&tr2dst_event,
 
@@ -646,4 +683,5 @@ struct tr2_tgt tr2_tgt_event = {
 	fn_data_fl,
 	fn_data_json_fl,
 	NULL, /* printf */
+	fn_timer,
 };
diff --git a/trace2/tr2_tgt_normal.c b/trace2/tr2_tgt_normal.c
index 58d9e430f05..23a7e78dcaa 100644
--- a/trace2/tr2_tgt_normal.c
+++ b/trace2/tr2_tgt_normal.c
@@ -355,4 +355,5 @@ struct tr2_tgt tr2_tgt_normal = {
 	NULL, /* data */
 	NULL, /* data_json */
 	fn_printf_va_fl,
+	NULL, /* timer */
 };
diff --git a/trace2/tr2_tgt_perf.c b/trace2/tr2_tgt_perf.c
index 47293e99d4b..7597cb52ed5 100644
--- a/trace2/tr2_tgt_perf.c
+++ b/trace2/tr2_tgt_perf.c
@@ -554,6 +554,34 @@ static void fn_printf_va_fl(const char *file, int line,
 	strbuf_release(&buf_payload);
 }
 
+static void fn_timer(uint64_t us_elapsed_absolute,
+		     const char *thread_name,
+		     const char *category,
+		     const char *timer_name,
+		     uint64_t interval_count,
+		     uint64_t us_total_time,
+		     uint64_t us_min_time,
+		     uint64_t us_max_time)
+{
+	const char *event_name = "timer";
+	struct strbuf buf_payload = STRBUF_INIT;
+
+	double t_total = (double)us_total_time / 1000000.0;
+	double t_min   = (double)us_min_time   / 1000000.0;
+	double t_max   = (double)us_max_time   / 1000000.0;
+
+	strbuf_addf(&buf_payload, "name:%s", timer_name);
+	strbuf_addf(&buf_payload, " count:%"PRIu64, interval_count);
+	strbuf_addf(&buf_payload, " total:%9.6f", t_total);
+	strbuf_addf(&buf_payload, " min:%9.6f", t_min);
+	strbuf_addf(&buf_payload, " max:%9.6f", t_max);
+
+	perf_io_write_fl(__FILE__, __LINE__, event_name, NULL,
+			 &us_elapsed_absolute, NULL,
+			 category, &buf_payload, thread_name);
+	strbuf_release(&buf_payload);
+}
+
 struct tr2_tgt tr2_tgt_perf = {
 	&tr2dst_perf,
 
@@ -585,4 +613,5 @@ struct tr2_tgt tr2_tgt_perf = {
 	fn_data_fl,
 	fn_data_json_fl,
 	fn_printf_va_fl,
+	fn_timer,
 };

Documentation/technical/api-trace2.txt, trace2/tr2_tgt.h, trace2/tr2_tgt_event.c, trace2/tr2_tgt_normal.c, trace2/tr2_tgt_perf.c

diff --git a/Documentation/technical/api-trace2.txt b/Documentation/technical/api-trace2.txt
index 03a61332a2d..bb116dc85db 100644
--- a/Documentation/technical/api-trace2.txt
+++ b/Documentation/technical/api-trace2.txt
@@ -838,6 +838,25 @@ may exceed the "atexit" elapsed time of the program.
 Timer events may represent an individual thread or a summation across
 the entire program.  Summation events will have a unique thread name.
 
+`"counter"`::
+	This event is generated at the end of the program and contains
+	the value of a global counter.
++
+------------
+{
+	"event":"counter",
+	...
+	"name":"test",      # counter name
+	"value":42,         # value of the counter
+}
+------------
++
+A global counter can be incremented throughout the execution of the
+program.  It will be reported in a "counter" event just prior to exit.
++
+Counter events may represent an individual thread or a summation across
+the entire program.  Summation events will have a unique thread name.
+
 == Example Trace2 API Usage
 
 Here is a hypothetical usage of the Trace2 API showing the intended
diff --git a/trace2/tr2_tgt.h b/trace2/tr2_tgt.h
index 1f548eb4b93..33a2bb99199 100644
--- a/trace2/tr2_tgt.h
+++ b/trace2/tr2_tgt.h
@@ -120,6 +120,19 @@ typedef void(tr2_tgt_evt_timer_t)(uint64_t us_elapsed_absolute,
 				  uint64_t us_min_time,
 				  uint64_t us_max_time);
 
+/*
+ * Item counter event.
+ *
+ * This also does not take a (file,line) pair.
+ *
+ * The thread name is optional.
+ */
+typedef void(tr2_tgt_evt_counter_t)(uint64_t us_elapsed_absolute,
+				    const char *thread_name,
+				    const char *category,
+				    const char *counter_name,
+				    uint64_t value);
+
 /*
  * "vtable" for a TRACE2 target.  Use NULL if a target does not want
  * to emit that message.
@@ -157,6 +170,7 @@ struct tr2_tgt {
 	tr2_tgt_evt_data_json_fl_t              *pfn_data_json_fl;
 	tr2_tgt_evt_printf_va_fl_t              *pfn_printf_va_fl;
 	tr2_tgt_evt_timer_t                     *pfn_timer;
+	tr2_tgt_evt_counter_t                   *pfn_counter;
 };
 /* clang-format on */
 
diff --git a/trace2/tr2_tgt_event.c b/trace2/tr2_tgt_event.c
index 9b3905b920c..ca36d44dfd7 100644
--- a/trace2/tr2_tgt_event.c
+++ b/trace2/tr2_tgt_event.c
@@ -23,7 +23,7 @@ static struct tr2_dst tr2dst_event = { TR2_SYSENV_EVENT, 0, 0, 0, 0 };
  * Verison 1: original version
  * Version 2: added "too_many_files" event
  * Version 3: added "child_ready" event
- * Version 4: added "timer" event
+ * Version 4: added "timer" and "counter" events
  */
 #define TR2_EVENT_VERSION "4"
 
@@ -652,6 +652,28 @@ static void fn_timer(uint64_t us_elapsed_absolute,
 	jw_release(&jw);
 }
 
+static void fn_counter(uint64_t us_elapsed_absolute,
+		       const char *thread_name,
+		       const char *category,
+		       const char *counter_name,
+		       uint64_t value)
+{
+	const char *event_name = "counter";
+	struct json_writer jw = JSON_WRITER_INIT;
+	double t_abs = (double)us_elapsed_absolute / 1000000.0;
+
+	jw_object_begin(&jw, 0);
+	event_fmt_prepare(event_name, __FILE__, __LINE__, NULL, &jw, thread_name);
+	jw_object_double(&jw, "t_abs", 6, t_abs);
+	jw_object_string(&jw, "name", counter_name);
+	jw_object_intmax(&jw, "value", value);
+
+	jw_end(&jw);
+
+	tr2_dst_write_line(&tr2dst_event, &jw.json);
+	jw_release(&jw);
+}
+
 struct tr2_tgt tr2_tgt_event = {
 	&tr2dst_event,
 
@@ -684,4 +706,5 @@ struct tr2_tgt tr2_tgt_event = {
 	fn_data_json_fl,
 	NULL, /* printf */
 	fn_timer,
+	fn_counter,
 };
diff --git a/trace2/tr2_tgt_normal.c b/trace2/tr2_tgt_normal.c
index 23a7e78dcaa..1778232f6e9 100644
--- a/trace2/tr2_tgt_normal.c
+++ b/trace2/tr2_tgt_normal.c
@@ -356,4 +356,5 @@ struct tr2_tgt tr2_tgt_normal = {
 	NULL, /* data_json */
 	fn_printf_va_fl,
 	NULL, /* timer */
+	NULL, /* counter */
 };
diff --git a/trace2/tr2_tgt_perf.c b/trace2/tr2_tgt_perf.c
index 7597cb52ed5..eb4577ec40b 100644
--- a/trace2/tr2_tgt_perf.c
+++ b/trace2/tr2_tgt_perf.c
@@ -582,6 +582,24 @@ static void fn_timer(uint64_t us_elapsed_absolute,
 	strbuf_release(&buf_payload);
 }
 
+static void fn_counter(uint64_t us_elapsed_absolute,
+		       const char *thread_name,
+		       const char *category,
+		       const char *counter_name,
+		       uint64_t value)
+{
+	const char *event_name = "counter";
+	struct strbuf buf_payload = STRBUF_INIT;
+
+	strbuf_addf(&buf_payload, "name:%s", counter_name);
+	strbuf_addf(&buf_payload, " value:%"PRIu64, value);
+
+	perf_io_write_fl(__FILE__, __LINE__, event_name, NULL,
+			 &us_elapsed_absolute, NULL,
+			 category, &buf_payload, thread_name);
+	strbuf_release(&buf_payload);
+}
+
 struct tr2_tgt tr2_tgt_perf = {
 	&tr2dst_perf,
 
@@ -614,4 +632,5 @@ struct tr2_tgt tr2_tgt_perf = {
 	fn_data_json_fl,
 	fn_printf_va_fl,
 	fn_timer,
+	fn_counter,
 };

diff --git a/trace2/tr2_tgt_perf.c b/trace2/tr2_tgt_perf.c
index 2ff9cf70835..bcbb0d8a250 100644
--- a/trace2/tr2_tgt_perf.c
+++ b/trace2/tr2_tgt_perf.c
@@ -153,16 +153,33 @@ static void perf_io_write_fl(const char *file, int line, const char *event_name,
 	strbuf_release(&buf_line);
 }
 
+__attribute__((format (printf, 8, 9)))
+static void perf_io_write_fl_fmt(const char *file, int line, const char *event_name,
+				 const struct repository *repo,
+				 uint64_t *p_us_elapsed_absolute,
+				 uint64_t *p_us_elapsed_relative,
+				 const char *category,
+				 const char *fmt, ...)
+{
+	va_list ap;
+	struct strbuf sb = STRBUF_INIT;
+
+	va_start(ap, fmt);
+	strbuf_vaddf(&sb, fmt, ap);
+	va_end(ap);
+
+	perf_io_write_fl(file, line, event_name, repo, p_us_elapsed_absolute,
+			 p_us_elapsed_relative, category, &sb);
+
+	strbuf_release(&sb);
+}
+
 static void fn_version_fl(const char *file, int line)
 {
 	const char *event_name = "version";
-	struct strbuf buf_payload = STRBUF_INIT;
-
-	strbuf_addstr(&buf_payload, git_version_string);
 
-	perf_io_write_fl(file, line, event_name, NULL, NULL, NULL, NULL,
-			 &buf_payload);
-	strbuf_release(&buf_payload);
+	perf_io_write_fl_fmt(file, line, event_name, NULL, NULL, NULL, NULL,
+			     "%s", git_version_string);
 }
 
 static void fn_start_fl(const char *file, int line,
@@ -182,37 +199,25 @@ static void fn_exit_fl(const char *file, int line, uint64_t us_elapsed_absolute,
 		       int code)
 {
 	const char *event_name = "exit";
-	struct strbuf buf_payload = STRBUF_INIT;
 
-	strbuf_addf(&buf_payload, "code:%d", code);
-
-	perf_io_write_fl(file, line, event_name, NULL, &us_elapsed_absolute,
-			 NULL, NULL, &buf_payload);
-	strbuf_release(&buf_payload);
+	perf_io_write_fl_fmt(file, line, event_name, NULL, &us_elapsed_absolute,
+			     NULL, NULL, "code:%d", code);
 }
 
 static void fn_signal(uint64_t us_elapsed_absolute, int signo)
 {
 	const char *event_name = "signal";
-	struct strbuf buf_payload = STRBUF_INIT;
 
-	strbuf_addf(&buf_payload, "signo:%d", signo);
-
-	perf_io_write_fl(__FILE__, __LINE__, event_name, NULL,
-			 &us_elapsed_absolute, NULL, NULL, &buf_payload);
-	strbuf_release(&buf_payload);
+	perf_io_write_fl_fmt(__FILE__, __LINE__, event_name, NULL,
+			 &us_elapsed_absolute, NULL, NULL, "signo:%d", signo);
 }
 
 static void fn_atexit(uint64_t us_elapsed_absolute, int code)
 {
 	const char *event_name = "atexit";
-	struct strbuf buf_payload = STRBUF_INIT;
-
-	strbuf_addf(&buf_payload, "code:%d", code);
 
-	perf_io_write_fl(__FILE__, __LINE__, event_name, NULL,
-			 &us_elapsed_absolute, NULL, NULL, &buf_payload);
-	strbuf_release(&buf_payload);
+	perf_io_write_fl_fmt(__FILE__, __LINE__, event_name, NULL,
+			 &us_elapsed_absolute, NULL, NULL, "code:%d", code);
 }
 
 static void maybe_append_string_va(struct strbuf *buf, const char *fmt,
@@ -244,13 +249,9 @@ static void fn_error_va_fl(const char *file, int line, const char *fmt,
 static void fn_command_path_fl(const char *file, int line, const char *pathname)
 {
 	const char *event_name = "cmd_path";
-	struct strbuf buf_payload = STRBUF_INIT;
-
-	strbuf_addstr(&buf_payload, pathname);
 
-	perf_io_write_fl(file, line, event_name, NULL, NULL, NULL, NULL,
-			 &buf_payload);
-	strbuf_release(&buf_payload);
+	perf_io_write_fl_fmt(file, line, event_name, NULL, NULL, NULL, NULL,
+			     "%s", pathname);
 }
 
 static void fn_command_ancestry_fl(const char *file, int line, const char **parent_names)
@@ -286,13 +287,9 @@ static void fn_command_name_fl(const char *file, int line, const char *name,
 static void fn_command_mode_fl(const char *file, int line, const char *mode)
 {
 	const char *event_name = "cmd_mode";
-	struct strbuf buf_payload = STRBUF_INIT;
-
-	strbuf_addstr(&buf_payload, mode);
 
-	perf_io_write_fl(file, line, event_name, NULL, NULL, NULL, NULL,
-			 &buf_payload);
-	strbuf_release(&buf_payload);
+	perf_io_write_fl_fmt(file, line, event_name, NULL, NULL, NULL, NULL,
+			     "%s", mode);
 }
 
 static void fn_alias_fl(const char *file, int line, const char *alias,
@@ -351,13 +348,10 @@ static void fn_child_exit_fl(const char *file, int line,
 			     int code, uint64_t us_elapsed_child)
 {
 	const char *event_name = "child_exit";
-	struct strbuf buf_payload = STRBUF_INIT;
 
-	strbuf_addf(&buf_payload, "[ch%d] pid:%d code:%d", cid, pid, code);
-
-	perf_io_write_fl(file, line, event_name, NULL, &us_elapsed_absolute,
-			 &us_elapsed_child, NULL, &buf_payload);
-	strbuf_release(&buf_payload);
+	perf_io_write_fl_fmt(file, line, event_name, NULL, &us_elapsed_absolute,
+			     &us_elapsed_child, NULL, "[ch%d] pid:%d code:%d",
+			     cid, pid, code);
 }
 
 static void fn_child_ready_fl(const char *file, int line,
@@ -365,24 +359,19 @@ static void fn_child_ready_fl(const char *file, int line,
 			      const char *ready, uint64_t us_elapsed_child)
 {
 	const char *event_name = "child_ready";
-	struct strbuf buf_payload = STRBUF_INIT;
-
-	strbuf_addf(&buf_payload, "[ch%d] pid:%d ready:%s", cid, pid, ready);
 
-	perf_io_write_fl(file, line, event_name, NULL, &us_elapsed_absolute,
-			 &us_elapsed_child, NULL, &buf_payload);
-	strbuf_release(&buf_payload);
+	perf_io_write_fl_fmt(file, line, event_name, NULL, &us_elapsed_absolute,
+			     &us_elapsed_child, NULL,
+			     "[ch%d] pid:%d ready:%s", cid, pid, ready);
 }
 
 static void fn_thread_start_fl(const char *file, int line,
 			       uint64_t us_elapsed_absolute)
 {
 	const char *event_name = "thread_start";
-	struct strbuf buf_payload = STRBUF_INIT;
 
-	perf_io_write_fl(file, line, event_name, NULL, &us_elapsed_absolute,
-			 NULL, NULL, &buf_payload);
-	strbuf_release(&buf_payload);
+	perf_io_write_fl_fmt(file, line, event_name, NULL, &us_elapsed_absolute,
+			     NULL, NULL, "%s", ""); /* TODO: No payload, support NULL? */
 }
 
 static void fn_thread_exit_fl(const char *file, int line,
@@ -390,11 +379,9 @@ static void fn_thread_exit_fl(const char *file, int line,
 			      uint64_t us_elapsed_thread)
 {
 	const char *event_name = "thread_exit";
-	struct strbuf buf_payload = STRBUF_INIT;
 
-	perf_io_write_fl(file, line, event_name, NULL, &us_elapsed_absolute,
-			 &us_elapsed_thread, NULL, &buf_payload);
-	strbuf_release(&buf_payload);
+	perf_io_write_fl_fmt(file, line, event_name, NULL, &us_elapsed_absolute,
+			     &us_elapsed_thread, NULL, "%s", ""); /* TODO: No payload, support NULL ? */
 }
 
 static void fn_exec_fl(const char *file, int line, uint64_t us_elapsed_absolute,
@@ -438,13 +425,9 @@ static void fn_param_fl(const char *file, int line, const char *param,
 			const char *value)
 {
 	const char *event_name = "def_param";
-	struct strbuf buf_payload = STRBUF_INIT;
-
-	strbuf_addf(&buf_payload, "%s:%s", param, value);
 
-	perf_io_write_fl(file, line, event_name, NULL, NULL, NULL, NULL,
-			 &buf_payload);
-	strbuf_release(&buf_payload);
+	perf_io_write_fl_fmt(file, line, event_name, NULL, NULL, NULL, NULL,
+			     "%s:%s", param, value);
 }
 
 static void fn_repo_fl(const char *file, int line,
@@ -525,13 +508,10 @@ static void fn_data_json_fl(const char *file, int line,
 			    const struct json_writer *value)
 {
 	const char *event_name = "data_json";
-	struct strbuf buf_payload = STRBUF_INIT;
-
-	strbuf_addf(&buf_payload, "%s:%s", key, value->json.buf);
 
-	perf_io_write_fl(file, line, event_name, repo, &us_elapsed_absolute,
-			 &us_elapsed_region, category, &buf_payload);
-	strbuf_release(&buf_payload);
+	perf_io_write_fl_fmt(file, line, event_name, repo, &us_elapsed_absolute,
+			     &us_elapsed_region, category,
+			     "%s:%s", key, value->json.buf);
 }
 
 static void fn_printf_va_fl(const char *file, int line,

Documentation/technical/api-trace2.txt, Makefile, t/helper/test-trace2.c, t/t0211-trace2-perf.sh, t/t0212-trace2-event.sh, trace2.c, trace2.h, trace2/tr2_tls.c, trace2/tr2_tls.h, trace2/tr2_tmr.c, trace2/tr2_tmr.h

diff --git a/Documentation/technical/api-trace2.txt b/Documentation/technical/api-trace2.txt
index e6ed94ba814..03a61332a2d 100644
--- a/Documentation/technical/api-trace2.txt
+++ b/Documentation/technical/api-trace2.txt
@@ -1230,6 +1230,54 @@ at offset 508.
 This example also shows that thread names are assigned in a racy manner
 as each thread starts and allocates TLS storage.
 
+Timer Events::
+
+	Trace2 also provides global stopwatch timers as an alternative
+	to regions.  These make it possible to measure the time spent
+	in a span of code or a library routine called from many places
+	and not	associated with a single phase of the overall command.
++
+At the end of the program, a single summary timer event is emitted; this
+aggregates timer usage across all threads.  These events have "summary"
+as their thread name.
++
+For some timers, individual (per-thread) timer events are also generated.
+These may be helpful in understanding how work is balanced between threads
+in some circumstances.
++
+Timers are defined in `enum trace2_timer_id` in trace2.h and in
+`trace2/tr2_tmr.c:tr2tmr_def_block[]`.
++
+----------------
+static void *unpack_compressed_entry(struct packed_git *p,
+				    struct pack_window **w_curs,
+				    off_t curpos,
+				    unsigned long size)
+{
+	...
+	trace2_timer_start(TRACE2_TIMER_ID__TEST1);
+	git_inflate_init(&stream);
+	...
+	git_inflate_end(&stream);
+	trace2_timer_stop(TRACE2_TIMER_ID__TEST1);
+	...
+}
+----------------
++
+----------------
+$ export GIT_TRACE2_PERF_BRIEF=1
+$ export GIT_TRACE2_PERF=~/log.perf
+$ git status
+...
+$ cat ~/log.perf
+...
+d0 | summary                  | timer        |     |  0.111026 |           | test         | name:test1 count:4 total: 0.000393 min: 0.000006 max: 0.000302
+d0 | main                     | atexit       |     |  0.111026 |           |              | code:0
+----------------
++
+In this example, the "test1" timer was started 4 times and ran for
+0.000393 seconds.
+
 == Future Work
 
 === Relationship to the Existing Trace Api (api-trace.txt)
diff --git a/Makefile b/Makefile
index ed75ed422b5..8b657f0162a 100644
--- a/Makefile
+++ b/Makefile
@@ -1022,6 +1022,7 @@ LIB_OBJS += trace2/tr2_cfg.o
 LIB_OBJS += trace2/tr2_cmd_name.o
 LIB_OBJS += trace2/tr2_dst.o
 LIB_OBJS += trace2/tr2_sid.o
+LIB_OBJS += trace2/tr2_tmr.o
 LIB_OBJS += trace2/tr2_sysenv.o
 LIB_OBJS += trace2/tr2_tbuf.o
 LIB_OBJS += trace2/tr2_tgt_event.o
diff --git a/t/helper/test-trace2.c b/t/helper/test-trace2.c
index f93633f895a..e98db5ba4c1 100644
--- a/t/helper/test-trace2.c
+++ b/t/helper/test-trace2.c
@@ -206,6 +206,102 @@ static int ut_007bug(int argc, const char **argv)
 	BUG("the bug message");
 }
 
+/*
+ * Single-threaded timer test.  Create several intervals using the
+ * TEST1 timer.  The test script can verify that an aggregate Trace2
+ * "timer" event is emitted indicating that we started+stopped the
+ * timer the requested number of times.
+ */
+static int ut_008timer(int argc, const char **argv)
+{
+	const char *usage_error =
+		"expect <count> <ms_delay>";
+
+	int count = 0;
+	int delay = 0;
+	int k;
+
+	if (argc != 2)
+		die("%s", usage_error);
+	if (get_i(&count, argv[0]))
+		die("%s", usage_error);
+	if (get_i(&delay, argv[1]))
+		die("%s", usage_error);
+
+	for (k = 0; k < count; k++) {
+		trace2_timer_start(TRACE2_TIMER_ID_TEST1);
+		sleep_millisec(delay);
+		trace2_timer_stop(TRACE2_TIMER_ID_TEST1);
+	}
+
+	return 0;
+}
+
+struct ut_009_data {
+	int count;
+	int delay;
+};
+
+static void *ut_009timer_thread_proc(void *_ut_009_data)
+{
+	struct ut_009_data *data = _ut_009_data;
+	int k;
+
+	trace2_thread_start("ut_009");
+
+	for (k = 0; k < data->count; k++) {
+		trace2_timer_start(TRACE2_TIMER_ID_TEST2);
+		sleep_millisec(data->delay);
+		trace2_timer_stop(TRACE2_TIMER_ID_TEST2);
+	}
+
+	trace2_thread_exit();
+	return NULL;
+}
+
+
+/*
+ * Multi-threaded timer test.  Create several threads that each create
+ * several intervals using the TEST2 timer.  The test script can verify
+ * that an individual Trace2 "timer" event for each thread and an
+ * aggregate "timer" event are generated.
+ */
+static int ut_009timer(int argc, const char **argv)
+{
+	const char *usage_error =
+		"expect <count> <ms_delay> <threads>";
+
+	struct ut_009_data data = { 0, 0 };
+	int nr_threads = 0;
+	int k;
+	pthread_t *pids = NULL;
+
+	if (argc != 3)
+		die("%s", usage_error);
+	if (get_i(&data.count, argv[0]))
+		die("%s", usage_error);
+	if (get_i(&data.delay, argv[1]))
+		die("%s", usage_error);
+	if (get_i(&nr_threads, argv[2]))
+		die("%s", usage_error);
+
+	CALLOC_ARRAY(pids, nr_threads);
+
+	for (k = 0; k < nr_threads; k++) {
+		if (pthread_create(&pids[k], NULL, ut_009timer_thread_proc, &data))
+			die("failed to create thread[%d]", k);
+	}
+
+	for (k = 0; k < nr_threads; k++) {
+		if (pthread_join(pids[k], NULL))
+			die("failed to join thread[%d]", k);
+	}
+
+	free(pids);
+
+	return 0;
+}
+
 /*
  * Usage:
  *     test-tool trace2 <ut_name_1> <ut_usage_1>
@@ -223,6 +319,8 @@ static struct unit_test ut_table[] = {
 	{ ut_005exec,     "005exec",   "<git_command_args>" },
 	{ ut_006data,     "006data",   "[<category> <key> <value>]+" },
 	{ ut_007bug,      "007bug",    "" },
+	{ ut_008timer,    "008timer",  "<count> <ms_delay>" },
+	{ ut_009timer,    "009timer",  "<count> <ms_delay> <threads>" },
 };
 /* clang-format on */
 
diff --git a/t/t0211-trace2-perf.sh b/t/t0211-trace2-perf.sh
index 22d0845544e..5c99d734ea2 100755
--- a/t/t0211-trace2-perf.sh
+++ b/t/t0211-trace2-perf.sh
@@ -173,4 +173,29 @@ test_expect_success 'using global config, perf stream, return code 0' '
 	test_cmp expect actual
 '
 
+# Exercise the stopwatch timer "test" in a loop and confirm that it was
+# we have as many start/stop intervals as expected.  We cannot really test
+# the (elapsed, min, max) timer values, so we assume they are good.
+#
+test_expect_success 'test stopwatch timers - summary only' '
+	test_when_finished "rm trace.perf actual" &&
+	test_config_global trace2.perfBrief 1 &&
+	test_config_global trace2.perfTarget "$(pwd)/trace.perf" &&
+	test-tool trace2 008timer 5 10 &&
+	perl "$TEST_DIRECTORY/t0211/scrub_perf.perl" <trace.perf >actual &&
+	grep "d0|summary|timer||_T_ABS_||test|name:test1 count:5" actual
+'
+
+test_expect_success 'test stopwatch timers - summary and threads' '
+	test_when_finished "rm trace.perf actual" &&
+	test_config_global trace2.perfBrief 1 &&
+	test_config_global trace2.perfTarget "$(pwd)/trace.perf" &&
+	test-tool trace2 009timer 5 10 3 &&
+	perl "$TEST_DIRECTORY/t0211/scrub_perf.perl" <trace.perf >actual &&
+	grep "d0|th01:ut_009|timer||_T_ABS_||test|name:test2 count:5" actual &&
+	grep "d0|th02:ut_009|timer||_T_ABS_||test|name:test2 count:5" actual &&
+	grep "d0|th02:ut_009|timer||_T_ABS_||test|name:test2 count:5" actual &&
+	grep "d0|summary|timer||_T_ABS_||test|name:test2 count:15" actual
+'
+
 test_done
diff --git a/t/t0212-trace2-event.sh b/t/t0212-trace2-event.sh
index 6d3374ff773..462c001deca 100755
--- a/t/t0212-trace2-event.sh
+++ b/t/t0212-trace2-event.sh
@@ -323,4 +323,39 @@ test_expect_success 'discard traces when there are too many files' '
 	head -n2 trace_target_dir/git-trace2-discard | tail -n1 | grep \"event\":\"too_many_files\"
 '
 
+# Exercise the stopwatch timer "test" in a loop and confirm that it was
+# we have as many start/stop intervals as expected.  We cannot really test
+# the (t_timer, t_min, t_max) timer values, so we assume they are good.
+#
+
+have_timer_event () {
+	thread=$1
+	name=$2
+	count=$3
+	file=$4
+
+	grep "\"event\":\"timer\".*\"thread\":\"${thread}\".*\"name\":\"${name}\".*\"count\":${count}" $file
+
+	return $?
+}
+
+test_expect_success 'test stopwatch timers - global, single-thread' '
+	test_when_finished "rm trace.event" &&
+	test_config_global trace2.eventBrief 1 &&
+	test_config_global trace2.eventTarget "$(pwd)/trace.event" &&
+	test-tool trace2 008timer 5 10 &&
+	have_timer_event "summary" "test1" 5 trace.event
+'
+
+test_expect_success 'test stopwatch timers - global+threads' '
+	test_when_finished "rm trace.event" &&
+	test_config_global trace2.eventBrief 1 &&
+	test_config_global trace2.eventTarget "$(pwd)/trace.event" &&
+	test-tool trace2 009timer 5 10 3 &&
+	have_timer_event "th01:ut_009" "test2" 5 trace.event &&
+	have_timer_event "th02:ut_009" "test2" 5 trace.event &&
+	have_timer_event "th03:ut_009" "test2" 5 trace.event &&
+	have_timer_event "summary" "test2" 15 trace.event
+'
+
 test_done
diff --git a/trace2.c b/trace2.c
index b2d471526fd..c073ffa836f 100644
--- a/trace2.c
+++ b/trace2.c
@@ -13,6 +13,7 @@
 #include "trace2/tr2_sysenv.h"
 #include "trace2/tr2_tgt.h"
 #include "trace2/tr2_tls.h"
+#include "trace2/tr2_tmr.h"
 
 static int trace2_enabled;
 
@@ -83,6 +84,42 @@ static void tr2_tgt_disable_builtins(void)
 		tgt_j->pfn_term();
 }
 
+static void tr2main_emit_summary_timers(uint64_t us_elapsed_absolute)
+{
+	struct tr2_tgt *tgt_j;
+	int j;
+	struct tr2tmr_block merged;
+
+	memset(&merged, 0, sizeof(merged));
+
+	/*
+	 * Sum across all of the per-thread stopwatch timer data into
+	 * a single composite block of timer values.
+	 */
+	tr2tls_aggregate_timer_blocks(&merged);
+
+	/*
+	 * Emit "summary" timer events for each composite timer value
+	 * that had activity.
+	 */
+	for_each_wanted_builtin (j, tgt_j)
+		if (tgt_j->pfn_timer)
+			tr2tmr_emit_block(tgt_j->pfn_timer,
+					  us_elapsed_absolute,
+					  &merged, "summary");
+}
+
+static void tr2main_emit_thread_timers(uint64_t us_elapsed_absolute)
+{
+	struct tr2_tgt *tgt_j;
+	int j;
+
+	for_each_wanted_builtin (j, tgt_j)
+		if (tgt_j->pfn_timer)
+			tr2tls_emit_timer_blocks_by_thread(tgt_j->pfn_timer,
+							   us_elapsed_absolute);
+}
+
 static int tr2main_exit_code;
 
 /*
@@ -110,6 +147,9 @@ static void tr2main_atexit_handler(void)
 	 */
 	tr2tls_pop_unwind_self();
 
+	tr2main_emit_thread_timers(us_elapsed_absolute);
+	tr2main_emit_summary_timers(us_elapsed_absolute);
+
 	for_each_wanted_builtin (j, tgt_j)
 		if (tgt_j->pfn_atexit)
 			tgt_j->pfn_atexit(us_elapsed_absolute,
@@ -841,3 +881,25 @@ const char *trace2_session_id(void)
 {
 	return tr2_sid_get();
 }
+
+void trace2_timer_start(enum trace2_timer_id tid)
+{
+	if (!trace2_enabled)
+		return;
+
+	if (tid < 0 || tid >= TRACE2_NUMBER_OF_TIMERS)
+		BUG("invalid timer id: %d", tid);
+
+	tr2tmr_start(tid);
+}
+
+void trace2_timer_stop(enum trace2_timer_id tid)
+{
+	if (!trace2_enabled)
+		return;
+
+	if (tid < 0 || tid >= TRACE2_NUMBER_OF_TIMERS)
+		BUG("invalid timer id: %d", tid);
+
+	tr2tmr_stop(tid);
+}
diff --git a/trace2.h b/trace2.h
index 0cc7b5f5312..32e2eaca7c8 100644
--- a/trace2.h
+++ b/trace2.h
@@ -51,6 +51,7 @@ struct json_writer;
  * [] trace2_region*    -- emit region nesting messages.
  * [] trace2_data*      -- emit region/thread/repo data messages.
  * [] trace2_printf*    -- legacy trace[1] messages.
+ * [] trace2_timer*     -- start/stop stopwatch timer (messages are deferred).
  */
 
 /*
@@ -531,4 +532,45 @@ void trace2_collect_process_info(enum trace2_process_info_reason reason);
 
 const char *trace2_session_id(void);
 
+/*
+ * Define the set of stopwatch timers.
+ *
+ * We can add more at any time, but they must be defined at compile
+ * time (to avoid the need to dynamically allocate and synchronize
+ * them between different threads).
+ *
+ * These must start at 0 and be contiguous (because we use them
+ * elsewhere as array indexes).
+ *
+ * Any values added to this enum must also be added to the timer definitions
+ * array.  See `trace2/tr2_tmr.c:tr2tmr_def_block[]`.
+ */
+enum trace2_timer_id {
+	/*
+	 * Define two timers for testing.  See `t/helper/test-trace2.c`.
+	 * These can be used for ad hoc testing, but should not be used
+	 * for permanent analysis code.
+	 */
+	TRACE2_TIMER_ID_TEST1 = 0, /* emits summary event only */
+	TRACE2_TIMER_ID_TEST2,     /* emits summary and thread events */
+
+
+	/* Add additional timer definitions before here. */
+	TRACE2_NUMBER_OF_TIMERS
+};
+
+/*
+ * Start/Stop a stopwatch timer in the current thread.
+ *
+ * The time spent in each start/stop interval will be accumulated and
+ * a "timer" event will be emitted when the program exits.
+ *
+ * Note: Since the stopwatch API routines do not generate individual
+ * events, they do not take (file, line) arguments.  Similarly, the
+ * category and timer name values are defined at compile-time in the
+ * timer definitions array, so they are not needed here in the API.
+ */
+void trace2_timer_start(enum trace2_timer_id tid);
+void trace2_timer_stop(enum trace2_timer_id tid);
+
 #endif /* TRACE2_H */
diff --git a/trace2/tr2_tls.c b/trace2/tr2_tls.c
index b68d297bf51..068938d334e 100644
--- a/trace2/tr2_tls.c
+++ b/trace2/tr2_tls.c
@@ -1,6 +1,7 @@
 #include "cache.h"
 #include "thread-utils.h"
 #include "trace2/tr2_tls.h"
+#include "trace2/tr2_tmr.h"
 
 /*
  * Initialize size of the thread stack for nested regions.
@@ -199,3 +200,31 @@ int tr2tls_locked_increment(int *p)
 
 	return current_value;
 }
+
+void tr2tls_aggregate_timer_blocks(struct tr2tmr_block *merged)
+{
+	struct tr2tls_thread_ctx *ctx = tr2tls_ctx_list;
+
+	while (ctx) {
+		struct tr2tls_thread_ctx *next = ctx->next_ctx;
+
+		tr2tmr_aggregate_timers(merged, &ctx->timers);
+
+		ctx = next;
+	}
+}
+
+void tr2tls_emit_timer_blocks_by_thread(tr2_tgt_evt_timer_t *pfn,
+					uint64_t us_elapsed_absolute)
+{
+	struct tr2tls_thread_ctx *ctx = tr2tls_ctx_list;
+
+	while (ctx) {
+		struct tr2tls_thread_ctx *next = ctx->next_ctx;
+
+		tr2tmr_emit_block(pfn, us_elapsed_absolute, &ctx->timers,
+				  ctx->thread_name);
+
+		ctx = next;
+	}
+}
diff --git a/trace2/tr2_tls.h b/trace2/tr2_tls.h
index c6b6c69b25a..10669f0d7b9 100644
--- a/trace2/tr2_tls.h
+++ b/trace2/tr2_tls.h
@@ -2,6 +2,7 @@
 #define TR2_TLS_H
 
 #include "strbuf.h"
+#include "trace2/tr2_tmr.h"
 
 /*
  * Arbitry limit for thread names for column alignment.
@@ -15,8 +16,24 @@ struct tr2tls_thread_ctx {
 	size_t alloc;
 	size_t nr_open_regions; /* plays role of "nr" in ALLOC_GROW */
 	int thread_id;
+
+	struct tr2tmr_block timers;
 };
 
+/*
+ * Iterate over the global list of TLS CTX data and aggregate the timer
+ * data into the given timer block.
+ */
+void tr2tls_aggregate_timer_blocks(struct tr2tmr_block *merged);
+
+/*
+ * Iterate over the global list of TLS CTX data (the complete set of
+ * threads that have used Trace2 resources) data and emit "per-thread"
+ * timer data for each.
+ */
+void tr2tls_emit_timer_blocks_by_thread(tr2_tgt_evt_timer_t *pfn,
+					uint64_t us_elapsed_absolute);
+
 /*
  * Create TLS data for the current thread.  This gives us a place to
  * put per-thread data, such as thread start time, function nesting
diff --git a/trace2/tr2_tmr.c b/trace2/tr2_tmr.c
new file mode 100644
index 00000000000..216cbd04cca
--- /dev/null
+++ b/trace2/tr2_tmr.c
@@ -0,0 +1,126 @@
+#include "cache.h"
+#include "thread-utils.h"
+#include "trace2/tr2_tls.h"
+#include "trace2/tr2_tmr.h"
+
+/*
+ * Define metadata for each stopwatch timer.  This list must match the
+ * set defined in "enum trace2_timer_id".
+ */
+struct tr2tmr_def {
+	const char *category;
+	const char *name;
+
+	unsigned int want_thread_events:1;
+};
+
+static struct tr2tmr_def tr2tmr_def_block[TRACE2_NUMBER_OF_TIMERS] = {
+	[TRACE2_TIMER_ID_TEST1] = { "test", "test1", 0 },
+	[TRACE2_TIMER_ID_TEST2] = { "test", "test2", 1 },
+};
+
+void tr2tmr_start(enum trace2_timer_id tid)
+{
+	struct tr2tls_thread_ctx *ctx = tr2tls_get_self();
+	struct tr2tmr_timer *t = &ctx->timers.timer[tid];
+
+	t->recursion_count++;
+	if (t->recursion_count > 1)
+		return; /* ignore recursive starts */
+
+	t->start_us = getnanotime() / 1000;
+}
+
+void tr2tmr_stop(enum trace2_timer_id tid)
+{
+	struct tr2tls_thread_ctx *ctx = tr2tls_get_self();
+	struct tr2tmr_timer *t = &ctx->timers.timer[tid];
+	uint64_t us_now;
+	uint64_t us_interval;
+
+	assert(t->recursion_count > 0);
+
+	t->recursion_count--;
+	if (t->recursion_count > 0)
+		return; /* still in recursive call */
+
+	us_now = getnanotime() / 1000;
+	us_interval = us_now - t->start_us;
+
+	t->total_us += us_interval;
+
+	if (!t->interval_count) {
+		t->min_us = us_interval;
+		t->max_us = us_interval;
+	} else {
+		if (us_interval < t->min_us)
+			t->min_us = us_interval;
+		if (us_interval > t->max_us)
+			t->max_us = us_interval;
+	}
+
+	t->interval_count++;
+}
+
+void tr2tmr_aggregate_timers(struct tr2tmr_block *merged,
+			     const struct tr2tmr_block *src)
+{
+	enum trace2_timer_id tid;
+
+	for (tid = 0; tid < TRACE2_NUMBER_OF_TIMERS; tid++) {
+		struct tr2tmr_timer *t_merged = &merged->timer[tid];
+		const struct tr2tmr_timer *t = &src->timer[tid];
+
+		t_merged->is_aggregate = 1;
+
+		if (t->recursion_count > 0) {
+			/*
+			 * A thread exited with a stopwatch running.
+			 *
+			 * NEEDSWORK: should we assert or throw a warning
+			 * for the open interval.  I'm going to ignore it
+			 * and keep going because we may have valid data
+			 * for previously closed intervals on this timer.
+			 */
+		}
+
+		if (!t->interval_count)
+			continue; /* this timer was not used by this thread. */
+
+		t_merged->total_us += t->total_us;
+
+		if (!t_merged->interval_count) {
+			t_merged->min_us = t->min_us;
+			t_merged->max_us = t->max_us;
+		} else {
+			if (t->min_us < t_merged->min_us)
+				t_merged->min_us = t->min_us;
+			if (t->max_us > t_merged->max_us)
+				t_merged->max_us = t->max_us;
+		}
+
+		t_merged->interval_count += t->interval_count;
+	}
+
+	merged->is_aggregate = 1;
+}
+
+void tr2tmr_emit_block(tr2_tgt_evt_timer_t *pfn, uint64_t us_elapsed_absolute,
+		       const struct tr2tmr_block *blk, const char *thread_name)
+{
+	enum trace2_timer_id tid;
+
+	for (tid = 0; tid < TRACE2_NUMBER_OF_TIMERS; tid++) {
+		const struct tr2tmr_timer *t = &blk->timer[tid];
+		const struct tr2tmr_def *d = &tr2tmr_def_block[tid];
+
+		if (!t->interval_count)
+			continue; /* timer was not used */
+
+		if (!d->want_thread_events && !t->is_aggregate)
+			continue; /* per-thread events not wanted */
+
+		pfn(us_elapsed_absolute, thread_name, d->category, d->name,
+		    t->interval_count, t->total_us, t->min_us, t->max_us);
+	}
+}
diff --git a/trace2/tr2_tmr.h b/trace2/tr2_tmr.h
new file mode 100644
index 00000000000..72f34f36d5f
--- /dev/null
+++ b/trace2/tr2_tmr.h
@@ -0,0 +1,120 @@
+#ifndef TR2_TM_H
+#define TR2_TM_H
+
+#include "trace2.h"
+#include "trace2/tr2_tgt.h"
+
+/*
+ * Define a mechanism to allow "stopwatch" timers.
+ *
+ * Timers can be used to measure "interesting" activity that does not
+ * fit the "region" model, such as code called from many different
+ * regions (like zlib) and/or where data for individual calls are not
+ * interesting or are too numerous to be efficiently logged.
+ *
+ * Timer values are accumulated during program execution and emitted
+ * to the Trace2 logs at program exit.
+ *
+ * To make this model efficient, we define a compile-time fixed set of
+ * timers and timer ids.  This lets us avoid the complexities of
+ * dynamically allocating a timer on demand and sharing that
+ * definition with other threads.
+ *
+ * Timer values are stored in a fixed size "timer block" inside the
+ * TLS CTX.  This allows data to be collected on a thread-by-thread
+ * basis without locking.
+ *
+ * We define (at compile time) a set of "timer ids" to access the
+ * various timers inside the fixed size "timer block".
+ *
+ * Timer definitions include the Trace2 "category" and similar fields.
+ * This eliminates the need to include those args on the various timer
+ * APIs.
+ *
+ * Timer results are summarized and emitted by the main thread at
+ * program exit by iterating over the global list of CTX data.
+ */
+
+/*
+ * The definition of an individual timer and used by an individual
+ * thread.
+ */
+struct tr2tmr_timer {
+	/*
+	 * Total elapsed time for this timer in this thread.
+	 */
+	uint64_t total_us;
+
+	/*
+	 * The maximum and minimum interval values observed for this
+	 * timer in this thread.
+	 */
+	uint64_t min_us;
+	uint64_t max_us;
+
+	/*
+	 * The value of the clock when this timer was started in this
+	 * thread.  (Undefined when the timer is not active in this
+	 * thread.)
+	 */
+	uint64_t start_us;
+
+	/*
+	 * Number of times that this timer has been started and stopped
+	 * in this thread.  (Recursive starts are ignored.)
+	 */
+	size_t interval_count;
+
+	/*
+	 * Number of nested starts on the stack in this thread.  (We
+	 * ignore recursive starts and use this to track the recursive
+	 * calls.)
+	 */
+	unsigned int recursion_count;
+
+	/*
+	 * Has data from multiple threads been combined into this object.
+	 */
+	unsigned int is_aggregate:1;
+};
+
+/*
+ * A compile-time fixed-size block of timers to insert into the TLS CTX.
+ *
+ * We use this simple wrapper around the array of timer instances to
+ * avoid C syntax quirks and the need to pass around an additional size_t
+ * argument.
+ */
+struct tr2tmr_block {
+	struct tr2tmr_timer timer[TRACE2_NUMBER_OF_TIMERS];
+
+	/*
+	 * Has data from multiple threads been combined into this block.
+	 */
+	unsigned int is_aggregate:1;
+};
+
+/*
+ * Private routines used by trace2.c to actually start/stop an individual
+ * timer in the current thread.
+ */
+void tr2tmr_start(enum trace2_timer_id tid);
+void tr2tmr_stop(enum trace2_timer_id tid);
+
+/*
+ * Accumulate timer data from source block into the merged block.
+ */
+void tr2tmr_aggregate_timers(struct tr2tmr_block *merged,
+			     const struct tr2tmr_block *src);
+
+/*
+ * Send stopwatch data for all of the timers in this block to the
+ * target.
+ *
+ * This will generate an event record for each timer that had activity
+ * during the program's execution.
+ */
+void tr2tmr_emit_block(tr2_tgt_evt_timer_t *pfn, uint64_t us_elapsed_absolute,
+		       const struct tr2tmr_block *blk, const char *thread_name);
+
+#endif /* TR2_TM_H */

Documentation/technical/api-trace2.txt, Makefile, t/helper/test-trace2.c, t/t0211-trace2-perf.sh, t/t0212-trace2-event.sh, trace2.c, trace2.h, trace2/tr2_ctr.c, trace2/tr2_ctr.h, trace2/tr2_tls.c, trace2/tr2_tls.h

diff --git a/Documentation/technical/api-trace2.txt b/Documentation/technical/api-trace2.txt
index bb116dc85db..14e6e50a2d6 100644
--- a/Documentation/technical/api-trace2.txt
+++ b/Documentation/technical/api-trace2.txt
@@ -1297,6 +1297,73 @@ d0 | main                     | atexit       |     |  0.111026 |           |
 In this example, the "test1" timer was started 4 times and ran for
 0.000393 seconds.
 
+Counter Events::
+
+	Trace2 also provides global counters as an alternative to regions
+	and data events.  These make it possible to count an activity of
+	interest, such a call to a library routine, during the program
+	and get a single counter event at the end.
++
+At the end of the program, a single summary event is emitted; this
+value is aggregated across all threads.  These events have "summary"
+as their thread name.
++
+For some counters, individual (per-thread) counter events are also
+generated.  This may be helpful in understanding how work is balanced
+between threads in some circumstances.
++
+----------------
+static void *load_cache_entries_thread(void *_data)
+{
+	struct load_cache_entries_thread_data *p = _data;
+	int i;
+
+	trace2_thread_start("load_cache_entries");
+	...
+	trace2_thread_exit();
+}
+
+static unsigned long load_cache_entry_block(struct index_state *istate,
+			struct mem_pool *ce_mem_pool, int offset, int nr, const char *mmap,
+			unsigned long start_offset, const struct cache_entry *previous_ce)
+{
+	int i;
+	unsigned long src_offset = start_offset;
+
+	trace2_counter_add(TRACE2_COUNTER_ID_TEST2, nr);
+
+	for (i = offset; i < offset + nr; i++) {
+		...
+	}
+}
+----------------
++
+----------------
+$ export GIT_TRACE2_PERF_BRIEF=1
+$ export GIT_TRACE2_PERF=~/log.perf
+$ git status
+...
+$ cat ~/log.perf
+...
+d0 | main                     | exit         |     | 53.977680 |           |              | code:0
+d0 | th12:load_cache_entries  | counter      |     | 53.977708 |           | test         | name:test2 value:193220
+d0 | th11:load_cache_entries  | counter      |     | 53.977708 |           | test         | name:test2 value:193221
+d0 | th10:load_cache_entries  | counter      |     | 53.977708 |           | test         | name:test2 value:193221
+d0 | th09:load_cache_entries  | counter      |     | 53.977708 |           | test         | name:test2 value:193221
+d0 | th08:load_cache_entries  | counter      |     | 53.977708 |           | test         | name:test2 value:193221
+d0 | th07:load_cache_entries  | counter      |     | 53.977708 |           | test         | name:test2 value:193221
+d0 | th06:load_cache_entries  | counter      |     | 53.977708 |           | test         | name:test2 value:193221
+d0 | th05:load_cache_entries  | counter      |     | 53.977708 |           | test         | name:test2 value:193221
+d0 | th04:load_cache_entries  | counter      |     | 53.977708 |           | test         | name:test2 value:193221
+d0 | th03:load_cache_entries  | counter      |     | 53.977708 |           | test         | name:test2 value:193221
+d0 | th02:load_cache_entries  | counter      |     | 53.977708 |           | test         | name:test2 value:193221
+d0 | summary                  | counter      |     | 53.977708 |           | test         | name:test2 value:2125430
+d0 | main                     | atexit       |     | 53.977708 |           |              | code:0
+----------------
++
+This example shows the value computed by each of the 11
+`load_cache_entries` threads and the total across all threads.
+
 == Future Work
 
 === Relationship to the Existing Trace Api (api-trace.txt)
diff --git a/Makefile b/Makefile
index 8b657f0162a..cc5bd8593f1 100644
--- a/Makefile
+++ b/Makefile
@@ -1020,6 +1020,7 @@ LIB_OBJS += trace.o
 LIB_OBJS += trace2.o
 LIB_OBJS += trace2/tr2_cfg.o
 LIB_OBJS += trace2/tr2_cmd_name.o
+LIB_OBJS += trace2/tr2_ctr.o
 LIB_OBJS += trace2/tr2_dst.o
 LIB_OBJS += trace2/tr2_sid.o
 LIB_OBJS += trace2/tr2_tmr.o
diff --git a/t/helper/test-trace2.c b/t/helper/test-trace2.c
index e98db5ba4c1..b64264cfed4 100644
--- a/t/helper/test-trace2.c
+++ b/t/helper/test-trace2.c
@@ -302,6 +302,90 @@ static int ut_009timer(int argc, const char **argv)
 	return 0;
 }
 
+/*
+ * Single-threaded counter test.  Add several values to the TEST1 counter.
+ * The test script can verify that an aggregate Trace2 "counter" event is
+ * emitted containing the sum of the values provided.
+ */
+static int ut_010counter(int argc, const char **argv)
+{
+	const char *usage_error =
+		"expect <v1> [<v2> [...]]";
+	int value;
+	int k;
+
+	if (argc < 1)
+		die("%s", usage_error);
+
+	for (k = 0; k < argc; k++) {
+		if (get_i(&value, argv[k]))
+			die("invalid value[%s] -- %s",
+			    argv[k], usage_error);
+		trace2_counter_add(TRACE2_COUNTER_ID_TEST1, value);
+	}
+
+	return 0;
+}
+
+struct ut_011_data {
+	int v1, v2;
+};
+
+static void *ut_011counter_thread_proc(void *_ut_011_data)
+{
+	struct ut_011_data *data = _ut_011_data;
+
+	trace2_thread_start("ut_011");
+
+	trace2_counter_add(TRACE2_COUNTER_ID_TEST2, data->v1);
+	trace2_counter_add(TRACE2_COUNTER_ID_TEST2, data->v2);
+
+	trace2_thread_exit();
+	return NULL;
+}
+
+/*
+ * Multi-threaded counter test.  Create several threads that each
+ * increment the TEST2 global counter.  The test script can verify
+ * that an individual Trace2 "counter" event for each thread and an
+ * aggregate "counter" event are generated.
+ */
+static int ut_011counter(int argc, const char **argv)
+{
+	const char *usage_error =
+		"expect <v1> <v2> <threads>";
+
+	struct ut_011_data data = { 0, 0 };
+	int nr_threads = 0;
+	int k;
+	pthread_t *pids = NULL;
+
+	if (argc != 3)
+		die("%s", usage_error);
+	if (get_i(&data.v1, argv[0]))
+		die("%s", usage_error);
+	if (get_i(&data.v2, argv[1]))
+		die("%s", usage_error);
+	if (get_i(&nr_threads, argv[2]))
+		die("%s", usage_error);
+
+	CALLOC_ARRAY(pids, nr_threads);
+
+	for (k = 0; k < nr_threads; k++) {
+		if (pthread_create(&pids[k], NULL, ut_011counter_thread_proc, &data))
+			die("failed to create thread[%d]", k);
+	}
+
+	for (k = 0; k < nr_threads; k++) {
+		if (pthread_join(pids[k], NULL))
+			die("failed to join thread[%d]", k);
+	}
+
+	free(pids);
+
+	return 0;
+}
+
 /*
  * Usage:
  *     test-tool trace2 <ut_name_1> <ut_usage_1>
@@ -321,6 +405,8 @@ static struct unit_test ut_table[] = {
 	{ ut_007bug,      "007bug",    "" },
 	{ ut_008timer,    "008timer",  "<count> <ms_delay>" },
 	{ ut_009timer,    "009timer",  "<count> <ms_delay> <threads>" },
+	{ ut_010counter,  "010counter","<v1> [<v2> [<v3> [...]]]" },
+	{ ut_011counter,  "011counter","<v1> <v2> <threads>" },
 };
 /* clang-format on */
 
diff --git a/t/t0211-trace2-perf.sh b/t/t0211-trace2-perf.sh
index 5c99d734ea2..498cbb7316b 100755
--- a/t/t0211-trace2-perf.sh
+++ b/t/t0211-trace2-perf.sh
@@ -198,4 +198,28 @@ test_expect_success 'test stopwatch timers - summary and threads' '
 	grep "d0|summary|timer||_T_ABS_||test|name:test2 count:15" actual
 '
 
+# Exercise the global counter "test" in a loop and confirm that we get an
+# event with the sum.
+#
+test_expect_success 'test global counters - global, single-thead' '
+	test_when_finished "rm trace.perf actual" &&
+	test_config_global trace2.perfBrief 1 &&
+	test_config_global trace2.perfTarget "$(pwd)/trace.perf" &&
+	test-tool trace2 010counter 2 3 5 7 11 13  &&
+	perl "$TEST_DIRECTORY/t0211/scrub_perf.perl" <trace.perf >actual &&
+	grep "d0|summary|counter||_T_ABS_||test|name:test1 value:41" actual
+'
+
+test_expect_success 'test global counters - global+threads' '
+	test_when_finished "rm trace.perf actual" &&
+	test_config_global trace2.perfBrief 1 &&
+	test_config_global trace2.perfTarget "$(pwd)/trace.perf" &&
+	test-tool trace2 011counter 5 10 3 &&
+	perl "$TEST_DIRECTORY/t0211/scrub_perf.perl" <trace.perf >actual &&
+	grep "d0|th01:ut_011|counter||_T_ABS_||test|name:test2 value:15" actual &&
+	grep "d0|th02:ut_011|counter||_T_ABS_||test|name:test2 value:15" actual &&
+	grep "d0|th02:ut_011|counter||_T_ABS_||test|name:test2 value:15" actual &&
+	grep "d0|summary|counter||_T_ABS_||test|name:test2 value:45" actual
+'
+
 test_done
diff --git a/t/t0212-trace2-event.sh b/t/t0212-trace2-event.sh
index 462c001deca..66a73243585 100755
--- a/t/t0212-trace2-event.sh
+++ b/t/t0212-trace2-event.sh
@@ -358,4 +358,38 @@ test_expect_success 'test stopwatch timers - global+threads' '
 	have_timer_event "summary" "test2" 15 trace.event
 '
 
+# Exercise the global counter in a loop and confirm that we get the
+# expected sum in an event record.
+#
+
+have_counter_event () {
+	thread=$1
+	name=$2
+	value=$3
+	file=$4
+
+	grep "\"event\":\"counter\".*\"thread\":\"${thread}\".*\"name\":\"${name}\".*\"value\":${value}" $file
+
+	return $?
+}
+
+test_expect_success 'test global counter - global, single-thread' '
+	test_when_finished "rm trace.event" &&
+	test_config_global trace2.eventBrief 1 &&
+	test_config_global trace2.eventTarget "$(pwd)/trace.event" &&
+	test-tool trace2 010counter 2 3 5 7 11 13 &&
+	have_counter_event "summary" "test1" 41 trace.event
+'
+
+test_expect_success 'test global counter - global+threads' '
+	test_when_finished "rm trace.event" &&
+	test_config_global trace2.eventBrief 1 &&
+	test_config_global trace2.eventTarget "$(pwd)/trace.event" &&
+	test-tool trace2 011counter 5 10 3 &&
+	have_counter_event "th01:ut_011" "test2" 15 trace.event &&
+	have_counter_event "th02:ut_011" "test2" 15 trace.event &&
+	have_counter_event "th03:ut_011" "test2" 15 trace.event &&
+	have_counter_event "summary" "test2" 45 trace.event
+'
+
 test_done
diff --git a/trace2.c b/trace2.c
index c073ffa836f..4c94c5cca68 100644
--- a/trace2.c
+++ b/trace2.c
@@ -8,6 +8,7 @@
 #include "version.h"
 #include "trace2/tr2_cfg.h"
 #include "trace2/tr2_cmd_name.h"
+#include "trace2/tr2_ctr.h"
 #include "trace2/tr2_dst.h"
 #include "trace2/tr2_sid.h"
 #include "trace2/tr2_sysenv.h"
@@ -120,6 +121,43 @@ static void tr2main_emit_thread_timers(uint64_t us_elapsed_absolute)
 							   us_elapsed_absolute);
 }
 
+static void tr2main_emit_summary_counters(uint64_t us_elapsed_absolute)
+{
+	struct tr2_tgt *tgt_j;
+	int j;
+	struct tr2ctr_block merged;
+
+	memset(&merged, 0, sizeof(merged));
+
+	/*
+	 * Sum across all of the per-thread counter data into
+	 * a single composite block of counter values.
+	 */
+	tr2tls_aggregate_counter_blocks(&merged);
+
+	/*
+	 * Emit "summary" counter events for each composite counter value
+	 * that had activity.
+	 */
+	for_each_wanted_builtin (j, tgt_j)
+		if (tgt_j->pfn_counter)
+			tr2ctr_emit_block(tgt_j->pfn_counter,
+					  us_elapsed_absolute,
+					  &merged, "summary");
+}
+
+static void tr2main_emit_thread_counters(uint64_t us_elapsed_absolute)
+{
+	struct tr2_tgt *tgt_j;
+	int j;
+
+	for_each_wanted_builtin (j, tgt_j)
+		if (tgt_j->pfn_counter)
+			tr2tls_emit_counter_blocks_by_thread(
+				tgt_j->pfn_counter,
+				us_elapsed_absolute);
+}
+
 static int tr2main_exit_code;
 
 /*
@@ -150,6 +188,9 @@ static void tr2main_atexit_handler(void)
 	tr2main_emit_thread_timers(us_elapsed_absolute);
 	tr2main_emit_summary_timers(us_elapsed_absolute);
 
+	tr2main_emit_thread_counters(us_elapsed_absolute);
+	tr2main_emit_summary_counters(us_elapsed_absolute);
+
 	for_each_wanted_builtin (j, tgt_j)
 		if (tgt_j->pfn_atexit)
 			tgt_j->pfn_atexit(us_elapsed_absolute,
@@ -903,3 +944,14 @@ void trace2_timer_stop(enum trace2_timer_id tid)
 
 	tr2tmr_stop(tid);
 }
+
+void trace2_counter_add(enum trace2_counter_id cid, uint64_t value)
+{
+	if (!trace2_enabled)
+		return;
+
+	if (cid < 0 || cid >= TRACE2_NUMBER_OF_COUNTERS)
+		BUG("invalid counter id: %d", cid);
+
+	tr2ctr_add(cid, value);
+}
diff --git a/trace2.h b/trace2.h
index 32e2eaca7c8..80c781f5a94 100644
--- a/trace2.h
+++ b/trace2.h
@@ -52,6 +52,7 @@ struct json_writer;
  * [] trace2_data*      -- emit region/thread/repo data messages.
  * [] trace2_printf*    -- legacy trace[1] messages.
  * [] trace2_timer*     -- start/stop stopwatch timer (messages are deferred).
+ * [] trace2_counter*   -- global counters (messages are deferrred).
  */
 
 /*
@@ -573,4 +574,36 @@ enum trace2_timer_id {
 void trace2_timer_start(enum trace2_timer_id tid);
 void trace2_timer_stop(enum trace2_timer_id tid);
 
+/*
+ * Define the set of global counters.
+ *
+ * We can add more at any time, but they must be defined at compile
+ * time (to avoid the need to dynamically allocate and synchronize
+ * them between different threads).
+ *
+ * These must start at 0 and be contiguous (because we them elsewhere
+ * as array indexes).
+ *
+ * Any value added to this enum must also be added to the counter
+ * definitions array.  See `trace2/tr2_ctr.c:tr2ctr_def_block[]`.
+ */
+enum trace2_counter_id {
+	/*
+	 * Define two counters for testing.  See `t/helper/test-trace2.c`.
+	 * These can be used for ad hoc testing, but should not be used
+	 * for permanent analysis code.
+	 */
+	TRACE2_COUNTER_ID_TEST1 = 0, /* emits summary event only */
+	TRACE2_COUNTER_ID_TEST2,     /* emits summary and thread events */
+
+
+	/* Add additional counter definitions before here. */
+	TRACE2_NUMBER_OF_COUNTERS
+};
+
+/*
+ * Increment global counter by value.
+ */
+void trace2_counter_add(enum trace2_counter_id cid, uint64_t value);
+
 #endif /* TRACE2_H */
diff --git a/trace2/tr2_ctr.c b/trace2/tr2_ctr.c
new file mode 100644
index 00000000000..bfc27005dca
--- /dev/null
+++ b/trace2/tr2_ctr.c
@@ -0,0 +1,65 @@
+#include "cache.h"
+#include "thread-utils.h"
+#include "trace2/tr2_tls.h"
+#include "trace2/tr2_ctr.h"
+
+/*
+ * Define metadata for each global counter.  This list must match the
+ * set defined in "enum trace2_counter_id".
+ */
+struct tr2ctr_def {
+	const char *category;
+	const char *name;
+
+	unsigned int want_thread_events:1;
+};
+
+static struct tr2ctr_def tr2ctr_def_block[TRACE2_NUMBER_OF_COUNTERS] = {
+	[TRACE2_COUNTER_ID_TEST1] = { "test", "test1", 0 },
+	[TRACE2_COUNTER_ID_TEST2] = { "test", "test2", 1 },
+};
+
+void tr2ctr_add(enum trace2_counter_id cid, uint64_t value)
+{
+	struct tr2tls_thread_ctx *ctx = tr2tls_get_self();
+	struct tr2ctr_counter *c = &ctx->counters.counter[cid];
+
+	c->value += value;
+}
+
+void tr2ctr_aggregate_counters(struct tr2ctr_block *merged,
+			       const struct tr2ctr_block *src)
+{
+	enum trace2_counter_id cid;
+
+	for (cid = 0; cid < TRACE2_NUMBER_OF_COUNTERS; cid++) {
+		struct tr2ctr_counter *c_merged = &merged->counter[cid];
+		const struct tr2ctr_counter *c = &src->counter[cid];
+
+		c_merged->is_aggregate = 1;
+
+		c_merged->value += c->value;
+	}
+
+	merged->is_aggregate = 1;
+}
+
+void tr2ctr_emit_block(tr2_tgt_evt_counter_t *pfn, uint64_t us_elapsed_absolute,
+		       const struct tr2ctr_block *blk, const char *thread_name)
+{
+	enum trace2_counter_id cid;
+
+	for (cid = 0; cid < TRACE2_NUMBER_OF_COUNTERS; cid++) {
+		const struct tr2ctr_counter *c = &blk->counter[cid];
+		const struct tr2ctr_def *d = &tr2ctr_def_block[cid];
+
+		if (!c->value)
+			continue; /* counter was not used */
+
+		if (!d->want_thread_events && !c->is_aggregate)
+			continue; /* per-thread events not wanted */
+
+		pfn(us_elapsed_absolute, thread_name, d->category, d->name,
+		    c->value);
+	}
+}
diff --git a/trace2/tr2_ctr.h b/trace2/tr2_ctr.h
new file mode 100644
index 00000000000..9a805062069
--- /dev/null
+++ b/trace2/tr2_ctr.h
@@ -0,0 +1,75 @@
+#ifndef TR2_CTR_H
+#define TR2_CTR_H
+
+#include "trace2.h"
+#include "trace2/tr2_tgt.h"
+
+/*
+ * Define a mechanism to allow global "counters".
+ *
+ * Counters can be used count interesting activity that does not fit
+ * the "region and data" model, such as code called from many
+ * different regions and/or where you want to count a number of items,
+ * but don't have control of when the last item will be processed,
+ * such as counter the number of calls to `lstat()`.
+ *
+ * Counters differ from Trace2 "data" events.  Data events are emitted
+ * immediately and are appropriate for documenting loop counters and
+ * etc.  Counter values are accumulated during the program and the final
+ * counter value event is emitted at program exit.
+ *
+ * To make this model efficient, we define a compile-time fixed set
+ * of counters and counter ids.  This lets us avoid the complexities
+ * of dynamically allocating a counter and sharing that definition
+ * with other threads.
+ *
+ * We define (at compile time) a set of "counter ids" to access the
+ * various counters inside of a fixed size "counter block".
+ *
+ * A counter defintion table provides the counter category and name
+ * so we can eliminate those arguments from the public counter API.
+ *
+ * Each active thread maintains a counter block in its TLS CTX and
+ * increments them without locking.  At program exit, the counter
+ * blocks from all of the individual CTXs are added together to give
+ * the final summary value for the each global counter.
+ */
+
+/*
+ * The definition of an individual counter.
+ */
+struct tr2ctr_counter {
+	uint64_t value;
+
+	unsigned int is_aggregate:1;
+};
+
+/*
+ * Compile time fixed block of all defined counters.
+ */
+struct tr2ctr_block {
+	struct tr2ctr_counter counter[TRACE2_NUMBER_OF_COUNTERS];
+
+	unsigned int is_aggregate:1;
+};
+
+/*
+ * Add "value" to the global counter.
+ */
+void tr2ctr_add(enum trace2_counter_id cid, uint64_t value);
+
+/*
+ * Accumulate counter data from the source block into the merged block.
+ */
+void tr2ctr_aggregate_counters(struct tr2ctr_block *merged,
+			       const struct tr2ctr_block *src);
+
+/*
+ * Send counter data for all counters in this block to the target.
+ *
+ * This will generate an event record for each counter that had activity.
+ */
+void tr2ctr_emit_block(tr2_tgt_evt_counter_t *pfn, uint64_t us_elapsed_absolute,
+		       const struct tr2ctr_block *blk, const char *thread_name);
+
+#endif /* TR2_CTR_H */
diff --git a/trace2/tr2_tls.c b/trace2/tr2_tls.c
index 068938d334e..ff795d104e6 100644
--- a/trace2/tr2_tls.c
+++ b/trace2/tr2_tls.c
@@ -1,5 +1,6 @@
 #include "cache.h"
 #include "thread-utils.h"
+#include "trace2/tr2_ctr.h"
 #include "trace2/tr2_tls.h"
 #include "trace2/tr2_tmr.h"
 
@@ -228,3 +229,31 @@ void tr2tls_emit_timer_blocks_by_thread(tr2_tgt_evt_timer_t *pfn,
 		ctx = next;
 	}
 }
+
+void tr2tls_aggregate_counter_blocks(struct tr2ctr_block *merged)
+{
+	struct tr2tls_thread_ctx *ctx = tr2tls_ctx_list;
+
+	while (ctx) {
+		struct tr2tls_thread_ctx *next = ctx->next_ctx;
+
+		tr2ctr_aggregate_counters(merged, &ctx->counters);
+
+		ctx = next;
+	}
+}
+
+void tr2tls_emit_counter_blocks_by_thread(tr2_tgt_evt_counter_t *pfn,
+					  uint64_t us_elapsed_absolute)
+{
+	struct tr2tls_thread_ctx *ctx = tr2tls_ctx_list;
+
+	while (ctx) {
+		struct tr2tls_thread_ctx *next = ctx->next_ctx;
+
+		tr2ctr_emit_block(pfn, us_elapsed_absolute, &ctx->counters,
+				  ctx->thread_name);
+
+		ctx = next;
+	}
+}
diff --git a/trace2/tr2_tls.h b/trace2/tr2_tls.h
index 10669f0d7b9..032b90fa46b 100644
--- a/trace2/tr2_tls.h
+++ b/trace2/tr2_tls.h
@@ -2,6 +2,7 @@
 #define TR2_TLS_H
 
 #include "strbuf.h"
+#include "trace2/tr2_ctr.h"
 #include "trace2/tr2_tmr.h"
 
 /*
@@ -17,9 +18,24 @@ struct tr2tls_thread_ctx {
 	size_t nr_open_regions; /* plays role of "nr" in ALLOC_GROW */
 	int thread_id;
 
+	struct tr2ctr_block counters;
 	struct tr2tmr_block timers;
 };
 
+/*
+ * Iterate over the global list of TLS CTX data and aggregate the
+ * counter data into the given counter block.
+ */
+void tr2tls_aggregate_counter_blocks(struct tr2ctr_block *merged);
+
+/*
+ * Iterate over the global list of TLS CTX data (the complete set of
+ * threads that have used Trace2 resources) data and emit "per-thread"
+ * counter data for each.
+ */
+void tr2tls_emit_counter_blocks_by_thread(tr2_tgt_evt_counter_t *pfn,
+					  uint64_t us_elapsed_absolute);
+
 /*
  * Iterate over the global list of TLS CTX data and aggregate the timer
  * data into the given timer block.

diff --git a/trace2/tr2_tls.h b/trace2/tr2_tls.h
index b1e327a928e..a90bd639d48 100644
--- a/trace2/tr2_tls.h
+++ b/trace2/tr2_tls.h
@@ -11,8 +11,8 @@
 struct tr2tls_thread_ctx {
 	struct strbuf thread_name;
 	uint64_t *array_us_start;
-	int alloc;
-	int nr_open_regions; /* plays role of "nr" in ALLOC_GROW */
+	size_t alloc;
+	size_t nr_open_regions; /* plays role of "nr" in ALLOC_GROW */
 	int thread_id;
 };
 

trace2/tr2_tgt_event.c, trace2/tr2_tgt_perf.c, trace2/tr2_tls.c, trace2/tr2_tls.h

diff --git a/trace2/tr2_tgt_event.c b/trace2/tr2_tgt_event.c
index 3a0014417cc..ca48d00aebc 100644
--- a/trace2/tr2_tgt_event.c
+++ b/trace2/tr2_tgt_event.c
@@ -88,7 +88,7 @@ static void event_fmt_prepare(const char *event_name, const char *file,
 
 	jw_object_string(jw, "event", event_name);
 	jw_object_string(jw, "sid", tr2_sid_get());
-	jw_object_string(jw, "thread", ctx->thread_name.buf);
+	jw_object_string(jw, "thread", ctx->thread_name);
 
 	/*
 	 * In brief mode, only emit <time> on these 2 event types.
diff --git a/trace2/tr2_tgt_perf.c b/trace2/tr2_tgt_perf.c
index e4acca13d64..fd6cce3efe5 100644
--- a/trace2/tr2_tgt_perf.c
+++ b/trace2/tr2_tgt_perf.c
@@ -23,6 +23,7 @@ static int tr2env_perf_be_brief;
 
 #define TR2FMT_PERF_FL_WIDTH (28)
 #define TR2FMT_PERF_MAX_EVENT_NAME (12)
+#define TR2FMT_PERF_MAX_THREAD_NAME (24)
 #define TR2FMT_PERF_REPO_WIDTH (3)
 #define TR2FMT_PERF_CATEGORY_WIDTH (12)
 
@@ -105,9 +106,9 @@ static void perf_fmt_prepare(const char *event_name,
 	}
 
 	strbuf_addf(buf, "d%d | ", tr2_sid_depth());
-	strbuf_addf(buf, "%-*s | %-*s | ", TR2_MAX_THREAD_NAME,
-		    ctx->thread_name.buf, TR2FMT_PERF_MAX_EVENT_NAME,
-		    event_name);
+	strbuf_addf(buf, "%-*.*s | %-*s | ", TR2FMT_PERF_MAX_THREAD_NAME,
+		    TR2FMT_PERF_MAX_THREAD_NAME, ctx->thread_name,
+		    TR2FMT_PERF_MAX_EVENT_NAME, event_name);
 
 	len = buf->len + TR2FMT_PERF_REPO_WIDTH;
 	if (repo)
diff --git a/trace2/tr2_tls.c b/trace2/tr2_tls.c
index 7da94aba522..ed99a234b95 100644
--- a/trace2/tr2_tls.c
+++ b/trace2/tr2_tls.c
@@ -34,7 +34,18 @@ void tr2tls_start_process_clock(void)
 struct tr2tls_thread_ctx *tr2tls_create_self(const char *thread_name,
 					     uint64_t us_thread_start)
 {
-	struct tr2tls_thread_ctx *ctx = xcalloc(1, sizeof(*ctx));
+	struct tr2tls_thread_ctx *ctx;
+	struct strbuf buf_name = STRBUF_INIT;
+	int thread_id = tr2tls_locked_increment(&tr2_next_thread_id);
+
+	if (thread_id)
+		strbuf_addf(&buf_name, "th%02d:", thread_id);
+	strbuf_addstr(&buf_name, thread_name);
+
+	FLEX_ALLOC_MEM(ctx, thread_name, buf_name.buf, buf_name.len);
+	strbuf_release(&buf_name);
+
+	ctx->thread_id = thread_id;
 
 	/*
 	 * Implicitly "tr2tls_push_self()" to capture the thread's start
@@ -45,15 +56,6 @@ struct tr2tls_thread_ctx *tr2tls_create_self(const char *thread_name,
 	ctx->array_us_start = (uint64_t *)xcalloc(ctx->alloc, sizeof(uint64_t));
 	ctx->array_us_start[ctx->nr_open_regions++] = us_thread_start;
 
-	ctx->thread_id = tr2tls_locked_increment(&tr2_next_thread_id);
-
-	strbuf_init(&ctx->thread_name, 0);
-	if (ctx->thread_id)
-		strbuf_addf(&ctx->thread_name, "th%02d:", ctx->thread_id);
-	strbuf_addstr(&ctx->thread_name, thread_name);
-	if (ctx->thread_name.len > TR2_MAX_THREAD_NAME)
-		strbuf_setlen(&ctx->thread_name, TR2_MAX_THREAD_NAME);
-
 	pthread_setspecific(tr2tls_key, ctx);
 
 	return ctx;
@@ -95,7 +97,6 @@ void tr2tls_unset_self(void)
 
 	pthread_setspecific(tr2tls_key, NULL);
 
-	strbuf_release(&ctx->thread_name);
 	free(ctx->array_us_start);
 	free(ctx);
 }
@@ -113,7 +114,7 @@ void tr2tls_pop_self(void)
 	struct tr2tls_thread_ctx *ctx = tr2tls_get_self();
 
 	if (!ctx->nr_open_regions)
-		BUG("no open regions in thread '%s'", ctx->thread_name.buf);
+		BUG("no open regions in thread '%s'", ctx->thread_name);
 
 	ctx->nr_open_regions--;
 }
diff --git a/trace2/tr2_tls.h b/trace2/tr2_tls.h
index a90bd639d48..64d97c5ac03 100644
--- a/trace2/tr2_tls.h
+++ b/trace2/tr2_tls.h
@@ -3,17 +3,12 @@
 
 #include "strbuf.h"
 
-/*
- * Arbitry limit for thread names for column alignment.
- */
-#define TR2_MAX_THREAD_NAME (24)
-
 struct tr2tls_thread_ctx {
-	struct strbuf thread_name;
 	uint64_t *array_us_start;
 	size_t alloc;
 	size_t nr_open_regions; /* plays role of "nr" in ALLOC_GROW */
 	int thread_id;
+	char thread_name[FLEX_ARRAY];
 };
 
 /*
@@ -25,9 +20,6 @@ struct tr2tls_thread_ctx {
  * non-zero thread-ids to help distinguish messages from concurrent
  * threads.
  *
- * Truncate the thread name if necessary to help with column alignment
- * in printf-style messages.
- *
  * In this and all following functions the term "self" refers to the
  * current thread.
  */

trace2/tr2_tls.c, trace2/tr2_tls.h

diff --git a/trace2/tr2_tls.c b/trace2/tr2_tls.c
index 28ea55863d1..35d49b27b2e 100644
--- a/trace2/tr2_tls.c
+++ b/trace2/tr2_tls.c
@@ -48,7 +48,7 @@ void tr2tls_start_process_clock(void)
 struct tr2tls_thread_ctx *tr2tls_create_self(const char *thread_name,
 					     uint64_t us_thread_start)
 {
-	struct tr2tls_thread_ctx *ctx;
+	struct tr2tls_thread_ctx *ctx = xcalloc(1, sizeof(struct tr2tls_thread_ctx));
 	struct strbuf buf_name = STRBUF_INIT;
 	int thread_id = tr2tls_locked_increment(&tr2_next_thread_id);
 
@@ -56,8 +56,7 @@ struct tr2tls_thread_ctx *tr2tls_create_self(const char *thread_name,
 		strbuf_addf(&buf_name, "th%02d:", thread_id);
 	strbuf_addstr(&buf_name, thread_name);
 
-	FLEX_ALLOC_MEM(ctx, thread_name, buf_name.buf, buf_name.len);
-	strbuf_release(&buf_name);
+	ctx->thread_name = strbuf_detach(&buf_name, NULL);
 
 	ctx->thread_id = thread_id;
 
@@ -188,6 +187,7 @@ void tr2tls_release(void)
 	while (ctx) {
 		struct tr2tls_thread_ctx *next = ctx->next_ctx;
 
+		free((char *)ctx->thread_name);
 		free(ctx->array_us_start);
 		free(ctx);
 
diff --git a/trace2/tr2_tls.h b/trace2/tr2_tls.h
index 503829bbd44..bc6c6f12e38 100644
--- a/trace2/tr2_tls.h
+++ b/trace2/tr2_tls.h
@@ -6,6 +6,7 @@
 #include "trace2/tr2_tmr.h"
 
 struct tr2tls_thread_ctx {
+	const char *thread_name;
 	struct tr2tls_thread_ctx *next_ctx;
 	uint64_t *array_us_start;
 	size_t alloc;
@@ -14,8 +15,6 @@ struct tr2tls_thread_ctx {
 
 	struct tr2_timer_block timers;
 	struct tr2_counter_block counters;
-
-	char thread_name[FLEX_ARRAY];
 };
 
 /*

> [...]
> index 7da94aba522..ed99a234b95 100644
> --- a/trace2/tr2_tls.c
> +++ b/trace2/tr2_tls.c
> @@ -34,7 +34,18 @@ void tr2tls_start_process_clock(void)
>  struct tr2tls_thread_ctx *tr2tls_create_self(const char *thread_name,
>  					     uint64_t us_thread_start)
>  {
> -	struct tr2tls_thread_ctx *ctx = xcalloc(1, sizeof(*ctx));
> +	struct tr2tls_thread_ctx *ctx;
> +	struct strbuf buf_name = STRBUF_INIT;
> +	int thread_id = tr2tls_locked_increment(&tr2_next_thread_id);

Here's the looks-to-be-unrelated to this strbuf conversion code I
mentioned above.

> +
> +	if (thread_id)
> +		strbuf_addf(&buf_name, "th%02d:", thread_id);
> +	strbuf_addstr(&buf_name, thread_name);
> +
> +	FLEX_ALLOC_MEM(ctx, thread_name, buf_name.buf, buf_name.len);
> +	strbuf_release(&buf_name);
> +
> +	ctx->thread_id = thread_id;
>  
>  	/*
> [...]

trace2/tr2_tls.c, trace2/tr2_tls.h

diff --git a/trace2/tr2_tls.c b/trace2/tr2_tls.c
index ed99a234b95..78538d5e522 100644
--- a/trace2/tr2_tls.c
+++ b/trace2/tr2_tls.c
@@ -15,6 +15,18 @@ static uint64_t tr2tls_us_start_process;
 static pthread_mutex_t tr2tls_mutex;
 static pthread_key_t tr2tls_key;
 
+/*
+ * This list owns all of the thread-specific CTX data.
+ *
+ * While a thread is alive it is associated with a CTX (owned by this
+ * list) and that CTX is installed in the thread's TLS data area.
+ * When a thread exits, it is disassociated from its CTX, but the (now
+ * dormant) CTX is held in this list until program exit.
+ *
+ * Similarly, `tr2tls_thread_main` points to a CTX contained within
+ * this list.
+ */
+static struct tr2tls_thread_ctx *tr2tls_ctx_list; /* modify under lock */
 static int tr2_next_thread_id; /* modify under lock */
 
 void tr2tls_start_process_clock(void)
@@ -56,6 +68,14 @@ struct tr2tls_thread_ctx *tr2tls_create_self(const char *thread_name,
 	ctx->array_us_start = (uint64_t *)xcalloc(ctx->alloc, sizeof(uint64_t));
 	ctx->array_us_start[ctx->nr_open_regions++] = us_thread_start;
 
+	/*
+	 * Link this CTX into the CTX list and make it the head.
+	 */
+	pthread_mutex_lock(&tr2tls_mutex);
+	ctx->next_ctx = tr2tls_ctx_list;
+	tr2tls_ctx_list = ctx;
+	pthread_mutex_unlock(&tr2tls_mutex);
+
 	pthread_setspecific(tr2tls_key, ctx);
 
 	return ctx;
@@ -91,14 +111,7 @@ int tr2tls_is_main_thread(void)
 
 void tr2tls_unset_self(void)
 {
-	struct tr2tls_thread_ctx *ctx;
-
-	ctx = tr2tls_get_self();
-
 	pthread_setspecific(tr2tls_key, NULL);
-
-	free(ctx->array_us_start);
-	free(ctx);
 }
 
 void tr2tls_push_self(uint64_t us_now)
@@ -162,11 +175,22 @@ void tr2tls_init(void)
 
 void tr2tls_release(void)
 {
+	struct tr2tls_thread_ctx *ctx = tr2tls_ctx_list;
+
 	tr2tls_unset_self();
 	tr2tls_thread_main = NULL;
 
 	pthread_mutex_destroy(&tr2tls_mutex);
 	pthread_key_delete(tr2tls_key);
+
+	while (ctx) {
+		struct tr2tls_thread_ctx *next = ctx->next_ctx;
+
+		free(ctx->array_us_start);
+		free(ctx);
+
+		ctx = next;
+	}
 }
 
 int tr2tls_locked_increment(int *p)
diff --git a/trace2/tr2_tls.h b/trace2/tr2_tls.h
index 64d97c5ac03..889010ec1ff 100644
--- a/trace2/tr2_tls.h
+++ b/trace2/tr2_tls.h
@@ -4,6 +4,7 @@
 #include "strbuf.h"
 
 struct tr2tls_thread_ctx {
+	struct tr2tls_thread_ctx *next_ctx;
 	uint64_t *array_us_start;
 	size_t alloc;
 	size_t nr_open_regions; /* plays role of "nr" in ALLOC_GROW */
@@ -37,7 +38,7 @@ struct tr2tls_thread_ctx *tr2tls_get_self(void);
 int tr2tls_is_main_thread(void);
 
 /*
- * Free our TLS data.
+ * Disassociate thread's TLS CTX data from the thread.
  */
 void tr2tls_unset_self(void);
 

diff --git a/trace2/tr2_tgt_event.c b/trace2/tr2_tgt_event.c
index ca48d00aebc..4ce50944298 100644
--- a/trace2/tr2_tgt_event.c
+++ b/trace2/tr2_tgt_event.c
@@ -81,14 +81,17 @@ static void fn_term(void)
  */
 static void event_fmt_prepare(const char *event_name, const char *file,
 			      int line, const struct repository *repo,
-			      struct json_writer *jw)
+			      struct json_writer *jw,
+			      const char *thread_name_override)
 {
-	struct tr2tls_thread_ctx *ctx = tr2tls_get_self();
 	struct tr2_tbuf tb_now;
 
 	jw_object_string(jw, "event", event_name);
 	jw_object_string(jw, "sid", tr2_sid_get());
-	jw_object_string(jw, "thread", ctx->thread_name);
+	jw_object_string(jw, "thread",
+			 ((thread_name_override && *thread_name_override)
+			  ? thread_name_override
+			  : tr2tls_get_self()->thread_name));
 
 	/*
 	 * In brief mode, only emit <time> on these 2 event types.
@@ -114,7 +117,7 @@ static void fn_too_many_files_fl(const char *file, int line)
 	struct json_writer jw = JSON_WRITER_INIT;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_end(&jw);
 
 	tr2_dst_write_line(&tr2dst_event, &jw.json);
@@ -127,7 +130,7 @@ static void fn_version_fl(const char *file, int line)
 	struct json_writer jw = JSON_WRITER_INIT;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_object_string(&jw, "evt", TR2_EVENT_VERSION);
 	jw_object_string(&jw, "exe", git_version_string);
 	jw_end(&jw);
@@ -147,7 +150,7 @@ static void fn_start_fl(const char *file, int line,
 	double t_abs = (double)us_elapsed_absolute / 1000000.0;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_object_double(&jw, "t_abs", 6, t_abs);
 	jw_object_inline_begin_array(&jw, "argv");
 	jw_array_argv(&jw, argv);
@@ -166,7 +169,7 @@ static void fn_exit_fl(const char *file, int line, uint64_t us_elapsed_absolute,
 	double t_abs = (double)us_elapsed_absolute / 1000000.0;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_object_double(&jw, "t_abs", 6, t_abs);
 	jw_object_intmax(&jw, "code", code);
 	jw_end(&jw);
@@ -182,7 +185,7 @@ static void fn_signal(uint64_t us_elapsed_absolute, int signo)
 	double t_abs = (double)us_elapsed_absolute / 1000000.0;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, __FILE__, __LINE__, NULL, &jw);
+	event_fmt_prepare(event_name, __FILE__, __LINE__, NULL, &jw, NULL);
 	jw_object_double(&jw, "t_abs", 6, t_abs);
 	jw_object_intmax(&jw, "signo", signo);
 	jw_end(&jw);
@@ -198,7 +201,7 @@ static void fn_atexit(uint64_t us_elapsed_absolute, int code)
 	double t_abs = (double)us_elapsed_absolute / 1000000.0;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, __FILE__, __LINE__, NULL, &jw);
+	event_fmt_prepare(event_name, __FILE__, __LINE__, NULL, &jw, NULL);
 	jw_object_double(&jw, "t_abs", 6, t_abs);
 	jw_object_intmax(&jw, "code", code);
 	jw_end(&jw);
@@ -231,7 +234,7 @@ static void fn_error_va_fl(const char *file, int line, const char *fmt,
 	struct json_writer jw = JSON_WRITER_INIT;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	maybe_add_string_va(&jw, "msg", fmt, ap);
 	/*
 	 * Also emit the format string as a field in case
@@ -253,7 +256,7 @@ static void fn_command_path_fl(const char *file, int line, const char *pathname)
 	struct json_writer jw = JSON_WRITER_INIT;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_object_string(&jw, "path", pathname);
 	jw_end(&jw);
 
@@ -268,7 +271,7 @@ static void fn_command_ancestry_fl(const char *file, int line, const char **pare
 	struct json_writer jw = JSON_WRITER_INIT;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_object_inline_begin_array(&jw, "ancestry");
 
 	while ((parent_name = *parent_names++))
@@ -288,7 +291,7 @@ static void fn_command_name_fl(const char *file, int line, const char *name,
 	struct json_writer jw = JSON_WRITER_INIT;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_object_string(&jw, "name", name);
 	if (hierarchy && *hierarchy)
 		jw_object_string(&jw, "hierarchy", hierarchy);
@@ -304,7 +307,7 @@ static void fn_command_mode_fl(const char *file, int line, const char *mode)
 	struct json_writer jw = JSON_WRITER_INIT;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_object_string(&jw, "name", mode);
 	jw_end(&jw);
 
@@ -319,7 +322,7 @@ static void fn_alias_fl(const char *file, int line, const char *alias,
 	struct json_writer jw = JSON_WRITER_INIT;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_object_string(&jw, "alias", alias);
 	jw_object_inline_begin_array(&jw, "argv");
 	jw_array_argv(&jw, argv);
@@ -338,7 +341,7 @@ static void fn_child_start_fl(const char *file, int line,
 	struct json_writer jw = JSON_WRITER_INIT;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_object_intmax(&jw, "child_id", cmd->trace2_child_id);
 	if (cmd->trace2_hook_name) {
 		jw_object_string(&jw, "child_class", "hook");
@@ -371,7 +374,7 @@ static void fn_child_exit_fl(const char *file, int line,
 	double t_rel = (double)us_elapsed_child / 1000000.0;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_object_intmax(&jw, "child_id", cid);
 	jw_object_intmax(&jw, "pid", pid);
 	jw_object_intmax(&jw, "code", code);
@@ -392,7 +395,7 @@ static void fn_child_ready_fl(const char *file, int line,
 	double t_rel = (double)us_elapsed_child / 1000000.0;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_object_intmax(&jw, "child_id", cid);
 	jw_object_intmax(&jw, "pid", pid);
 	jw_object_string(&jw, "ready", ready);
@@ -411,7 +414,7 @@ static void fn_thread_start_fl(const char *file, int line,
 	struct json_writer jw = JSON_WRITER_INIT;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_end(&jw);
 
 	tr2_dst_write_line(&tr2dst_event, &jw.json);
@@ -427,7 +430,7 @@ static void fn_thread_exit_fl(const char *file, int line,
 	double t_rel = (double)us_elapsed_thread / 1000000.0;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_object_double(&jw, "t_rel", 6, t_rel);
 	jw_end(&jw);
 
@@ -442,7 +445,7 @@ static void fn_exec_fl(const char *file, int line, uint64_t us_elapsed_absolute,
 	struct json_writer jw = JSON_WRITER_INIT;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_object_intmax(&jw, "exec_id", exec_id);
 	if (exe)
 		jw_object_string(&jw, "exe", exe);
@@ -463,7 +466,7 @@ static void fn_exec_result_fl(const char *file, int line,
 	struct json_writer jw = JSON_WRITER_INIT;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_object_intmax(&jw, "exec_id", exec_id);
 	jw_object_intmax(&jw, "code", code);
 	jw_end(&jw);
@@ -479,7 +482,7 @@ static void fn_param_fl(const char *file, int line, const char *param,
 	struct json_writer jw = JSON_WRITER_INIT;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	event_fmt_prepare(event_name, file, line, NULL, &jw, NULL);
 	jw_object_string(&jw, "param", param);
 	jw_object_string(&jw, "value", value);
 	jw_end(&jw);
@@ -495,7 +498,7 @@ static void fn_repo_fl(const char *file, int line,
 	struct json_writer jw = JSON_WRITER_INIT;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, file, line, repo, &jw);
+	event_fmt_prepare(event_name, file, line, repo, &jw, NULL);
 	jw_object_string(&jw, "worktree", repo->worktree);
 	jw_end(&jw);
 
@@ -516,7 +519,7 @@ static void fn_region_enter_printf_va_fl(const char *file, int line,
 		struct json_writer jw = JSON_WRITER_INIT;
 
 		jw_object_begin(&jw, 0);
-		event_fmt_prepare(event_name, file, line, repo, &jw);
+		event_fmt_prepare(event_name, file, line, repo, &jw, NULL);
 		jw_object_intmax(&jw, "nesting", ctx->nr_open_regions);
 		if (category)
 			jw_object_string(&jw, "category", category);
@@ -542,7 +545,7 @@ static void fn_region_leave_printf_va_fl(
 		double t_rel = (double)us_elapsed_region / 1000000.0;
 
 		jw_object_begin(&jw, 0);
-		event_fmt_prepare(event_name, file, line, repo, &jw);
+		event_fmt_prepare(event_name, file, line, repo, &jw, NULL);
 		jw_object_double(&jw, "t_rel", 6, t_rel);
 		jw_object_intmax(&jw, "nesting", ctx->nr_open_regions);
 		if (category)
@@ -570,7 +573,7 @@ static void fn_data_fl(const char *file, int line, uint64_t us_elapsed_absolute,
 		double t_rel = (double)us_elapsed_region / 1000000.0;
 
 		jw_object_begin(&jw, 0);
-		event_fmt_prepare(event_name, file, line, repo, &jw);
+		event_fmt_prepare(event_name, file, line, repo, &jw, NULL);
 		jw_object_double(&jw, "t_abs", 6, t_abs);
 		jw_object_double(&jw, "t_rel", 6, t_rel);
 		jw_object_intmax(&jw, "nesting", ctx->nr_open_regions);
@@ -598,7 +601,7 @@ static void fn_data_json_fl(const char *file, int line,
 		double t_rel = (double)us_elapsed_region / 1000000.0;
 
 		jw_object_begin(&jw, 0);
-		event_fmt_prepare(event_name, file, line, repo, &jw);
+		event_fmt_prepare(event_name, file, line, repo, &jw, NULL);
 		jw_object_double(&jw, "t_abs", 6, t_abs);
 		jw_object_double(&jw, "t_rel", 6, t_rel);
 		jw_object_intmax(&jw, "nesting", ctx->nr_open_regions);

Documentation/technical/api-trace2.txt, Makefile, t/helper/test-trace2.c, t/t0211-trace2-perf.sh, t/t0212-trace2-event.sh, trace2.c, trace2.h, trace2/tr2_tls.c, trace2/tr2_tls.h, trace2/tr2_tmr.c, trace2/tr2_tmr.h

diff --git a/Documentation/technical/api-trace2.txt b/Documentation/technical/api-trace2.txt
index 351d140879e..616001bcbb0 100644
--- a/Documentation/technical/api-trace2.txt
+++ b/Documentation/technical/api-trace2.txt
@@ -1230,6 +1230,54 @@ at offset 508.
 This example also shows that thread names are assigned in a racy manner
 as each thread starts and allocates TLS storage.
 
+Timer Events::
+
+	Trace2 also provides global stopwatch timers as an alternative
+	to regions.  These make it possible to measure the time spent
+	in a span of code or a library routine called from many places
+	and not	associated with a single phase of the overall command.
++
+At the end of the program, a single summary timer event is emitted; this
+aggregates timer usage across all threads.  These events have "summary"
+as their thread name.
++
+For some timers, individual (per-thread) timer events are also generated.
+These may be helpful in understanding how work is balanced between threads
+in some circumstances.
++
+Timers are defined in `enum trace2_timer_id` in trace2.h and in
+`trace2/tr2_tmr.c:tr2_timer_def_block[]`.
++
+----------------
+static void *unpack_compressed_entry(struct packed_git *p,
+				    struct pack_window **w_curs,
+				    off_t curpos,
+				    unsigned long size)
+{
+	...
+	trace2_timer_start(TRACE2_TIMER_ID__TEST1);
+	git_inflate_init(&stream);
+	...
+	git_inflate_end(&stream);
+	trace2_timer_stop(TRACE2_TIMER_ID__TEST1);
+	...
+}
+----------------
++
+----------------
+$ export GIT_TRACE2_PERF_BRIEF=1
+$ export GIT_TRACE2_PERF=~/log.perf
+$ git status
+...
+$ cat ~/log.perf
+...
+d0 | summary                  | timer        |     |  0.111026 |           | test         | name:test1 count:4 ns_total:393000 ns_min:6000 ns_max:302000
+d0 | main                     | atexit       |     |  0.111026 |           |              | code:0
+----------------
++
+In this example, the "test1" timer was started 4 times and ran for
+0.000393 seconds.
+
 == Future Work
 
 === Relationship to the Existing Trace Api (api-trace.txt)
diff --git a/Makefile b/Makefile
index ed75ed422b5..8b657f0162a 100644
--- a/Makefile
+++ b/Makefile
@@ -1022,6 +1022,7 @@ LIB_OBJS += trace2/tr2_cfg.o
 LIB_OBJS += trace2/tr2_cmd_name.o
 LIB_OBJS += trace2/tr2_dst.o
 LIB_OBJS += trace2/tr2_sid.o
+LIB_OBJS += trace2/tr2_tmr.o
 LIB_OBJS += trace2/tr2_sysenv.o
 LIB_OBJS += trace2/tr2_tbuf.o
 LIB_OBJS += trace2/tr2_tgt_event.o
diff --git a/t/helper/test-trace2.c b/t/helper/test-trace2.c
index f93633f895a..51d022422bf 100644
--- a/t/helper/test-trace2.c
+++ b/t/helper/test-trace2.c
@@ -206,6 +206,101 @@ static int ut_007bug(int argc, const char **argv)
 	BUG("the bug message");
 }
 
+/*
+ * Single-threaded timer test.  Create several intervals using the
+ * TEST1 timer.  The test script can verify that an aggregate Trace2
+ * "timer" event is emitted indicating that we started+stopped the
+ * timer the requested number of times.
+ */
+static int ut_008timer(int argc, const char **argv)
+{
+	const char *usage_error =
+		"expect <count> <ms_delay>";
+
+	int count = 0;
+	int delay = 0;
+	int k;
+
+	if (argc != 2)
+		die("%s", usage_error);
+	if (get_i(&count, argv[0]))
+		die("%s", usage_error);
+	if (get_i(&delay, argv[1]))
+		die("%s", usage_error);
+
+	for (k = 0; k < count; k++) {
+		trace2_timer_start(TRACE2_TIMER_ID_TEST1);
+		sleep_millisec(delay);
+		trace2_timer_stop(TRACE2_TIMER_ID_TEST1);
+	}
+
+	return 0;
+}
+
+struct ut_009_data {
+	int count;
+	int delay;
+};
+
+static void *ut_009timer_thread_proc(void *_ut_009_data)
+{
+	struct ut_009_data *data = _ut_009_data;
+	int k;
+
+	trace2_thread_start("ut_009");
+
+	for (k = 0; k < data->count; k++) {
+		trace2_timer_start(TRACE2_TIMER_ID_TEST2);
+		sleep_millisec(data->delay);
+		trace2_timer_stop(TRACE2_TIMER_ID_TEST2);
+	}
+
+	trace2_thread_exit();
+	return NULL;
+}
+
+/*
+ * Multi-threaded timer test.  Create several threads that each create
+ * several intervals using the TEST2 timer.  The test script can verify
+ * that an individual Trace2 "timer" event for each thread and an
+ * aggregate "timer" event are generated.
+ */
+static int ut_009timer(int argc, const char **argv)
+{
+	const char *usage_error =
+		"expect <count> <ms_delay> <threads>";
+
+	struct ut_009_data data = { 0, 0 };
+	int nr_threads = 0;
+	int k;
+	pthread_t *pids = NULL;
+
+	if (argc != 3)
+		die("%s", usage_error);
+	if (get_i(&data.count, argv[0]))
+		die("%s", usage_error);
+	if (get_i(&data.delay, argv[1]))
+		die("%s", usage_error);
+	if (get_i(&nr_threads, argv[2]))
+		die("%s", usage_error);
+
+	CALLOC_ARRAY(pids, nr_threads);
+
+	for (k = 0; k < nr_threads; k++) {
+		if (pthread_create(&pids[k], NULL, ut_009timer_thread_proc, &data))
+			die("failed to create thread[%d]", k);
+	}
+
+	for (k = 0; k < nr_threads; k++) {
+		if (pthread_join(pids[k], NULL))
+			die("failed to join thread[%d]", k);
+	}
+
+	free(pids);
+
+	return 0;
+}
+
 /*
  * Usage:
  *     test-tool trace2 <ut_name_1> <ut_usage_1>
@@ -223,6 +318,8 @@ static struct unit_test ut_table[] = {
 	{ ut_005exec,     "005exec",   "<git_command_args>" },
 	{ ut_006data,     "006data",   "[<category> <key> <value>]+" },
 	{ ut_007bug,      "007bug",    "" },
+	{ ut_008timer,    "008timer",  "<count> <ms_delay>" },
+	{ ut_009timer,    "009timer",  "<count> <ms_delay> <threads>" },
 };
 /* clang-format on */
 
diff --git a/t/t0211-trace2-perf.sh b/t/t0211-trace2-perf.sh
index 22d0845544e..381c3eea458 100755
--- a/t/t0211-trace2-perf.sh
+++ b/t/t0211-trace2-perf.sh
@@ -173,4 +173,50 @@ test_expect_success 'using global config, perf stream, return code 0' '
 	test_cmp expect actual
 '
 
+# Exercise the stopwatch timer "test" in a loop and confirm that it was
+# we have as many start/stop intervals as expected.  We cannot really test
+# the actual (total, min, max) timer values, so we assume they are good,
+# but we can test the keys for them.
+
+have_timer_event () {
+	thread=$1
+	name=$2
+	count=$3
+	file=$4
+
+	pattern="d0|${thread}|timer||_T_ABS_||test"
+	pattern="${pattern}|name:${name}"
+	pattern="${pattern} count:${count}"
+	pattern="${pattern} ns_total:.*"
+	pattern="${pattern} ns_min:.*"
+	pattern="${pattern} ns_max:.*"
+
+	grep "${pattern}" ${file}
+
+	return $?
+}
+
+test_expect_success 'test stopwatch timers - summary only' '
+	test_when_finished "rm trace.perf actual" &&
+	test_config_global trace2.perfBrief 1 &&
+	test_config_global trace2.perfTarget "$(pwd)/trace.perf" &&
+	test-tool trace2 008timer 5 10 &&
+	perl "$TEST_DIRECTORY/t0211/scrub_perf.perl" <trace.perf >actual &&
+
+	have_timer_event "summary" "test1" 5 actual
+'
+
+test_expect_success 'test stopwatch timers - summary and threads' '
+	test_when_finished "rm trace.perf actual" &&
+	test_config_global trace2.perfBrief 1 &&
+	test_config_global trace2.perfTarget "$(pwd)/trace.perf" &&
+	test-tool trace2 009timer 5 10 3 &&
+	perl "$TEST_DIRECTORY/t0211/scrub_perf.perl" <trace.perf >actual &&
+
+	have_timer_event "th01:ut_009" "test2" 5 actual &&
+	have_timer_event "th02:ut_009" "test2" 5 actual &&
+	have_timer_event "th03:ut_009" "test2" 5 actual &&
+	have_timer_event "summary" "test2" 15 actual
+'
+
 test_done
diff --git a/t/t0212-trace2-event.sh b/t/t0212-trace2-event.sh
index 6d3374ff773..277688fdbc4 100755
--- a/t/t0212-trace2-event.sh
+++ b/t/t0212-trace2-event.sh
@@ -323,4 +323,49 @@ test_expect_success 'discard traces when there are too many files' '
 	head -n2 trace_target_dir/git-trace2-discard | tail -n1 | grep \"event\":\"too_many_files\"
 '
 
+# Exercise the stopwatch timer "test" in a loop and confirm that it was
+# we have as many start/stop intervals as expected.  We cannot really test
+# the (t_timer, t_min, t_max) timer values, so we assume they are good.
+#
+
+have_timer_event () {
+	thread=$1
+	name=$2
+	count=$3
+	file=$4
+
+	pattern="\"event\":\"timer\""
+	pattern="${pattern}.*\"thread\":\"${thread}\""
+	pattern="${pattern}.*\"name\":\"${name}\""
+	pattern="${pattern}.*\"count\":${count}"
+	pattern="${pattern}.*\"ns_total\":[0-9]*"
+	pattern="${pattern}.*\"ns_min\":[0-9]*"
+	pattern="${pattern}.*\"ns_max\":[0-9]*"
+
+	grep "${pattern}" ${file}
+
+	return $?
+}
+
+test_expect_success 'test stopwatch timers - global, single-thread' '
+	test_when_finished "rm trace.event" &&
+	test_config_global trace2.eventBrief 1 &&
+	test_config_global trace2.eventTarget "$(pwd)/trace.event" &&
+	test-tool trace2 008timer 5 10 &&
+
+	have_timer_event "summary" "test1" 5 trace.event
+'
+
+test_expect_success 'test stopwatch timers - global+threads' '
+	test_when_finished "rm trace.event" &&
+	test_config_global trace2.eventBrief 1 &&
+	test_config_global trace2.eventTarget "$(pwd)/trace.event" &&
+	test-tool trace2 009timer 5 10 3 &&
+
+	have_timer_event "th01:ut_009" "test2" 5 trace.event &&
+	have_timer_event "th02:ut_009" "test2" 5 trace.event &&
+	have_timer_event "th03:ut_009" "test2" 5 trace.event &&
+	have_timer_event "summary" "test2" 15 trace.event
+'
+
 test_done
diff --git a/trace2.c b/trace2.c
index b2d471526fd..23289dd6eb4 100644
--- a/trace2.c
+++ b/trace2.c
@@ -13,6 +13,7 @@
 #include "trace2/tr2_sysenv.h"
 #include "trace2/tr2_tgt.h"
 #include "trace2/tr2_tls.h"
+#include "trace2/tr2_tmr.h"
 
 static int trace2_enabled;
 
@@ -83,6 +84,36 @@ static void tr2_tgt_disable_builtins(void)
 		tgt_j->pfn_term();
 }
 
+static void tr2main_emit_summary_timers(uint64_t us_elapsed_absolute)
+{
+	struct tr2_tgt *tgt_j;
+	int j;
+	struct tr2_timer_block merged = { { { 0 } } };
+
+	tr2_summarize_timers(&merged);
+
+	/*
+	 * Emit "summary" timer events for each composite timer value
+	 * that had activity.
+	 */
+	for_each_wanted_builtin (j, tgt_j)
+		if (tgt_j->pfn_timer)
+			tr2_emit_timer_block(tgt_j->pfn_timer,
+					     us_elapsed_absolute,
+					     &merged, "summary");
+}
+
+static void tr2main_emit_thread_timers(uint64_t us_elapsed_absolute)
+{
+	struct tr2_tgt *tgt_j;
+	int j;
+
+	for_each_wanted_builtin (j, tgt_j)
+		if (tgt_j->pfn_timer)
+			tr2_emit_timers_by_thread(tgt_j->pfn_timer,
+						  us_elapsed_absolute);
+}
+
 static int tr2main_exit_code;
 
 /*
@@ -110,6 +141,9 @@ static void tr2main_atexit_handler(void)
 	 */
 	tr2tls_pop_unwind_self();
 
+	tr2main_emit_thread_timers(us_elapsed_absolute);
+	tr2main_emit_summary_timers(us_elapsed_absolute);
+
 	for_each_wanted_builtin (j, tgt_j)
 		if (tgt_j->pfn_atexit)
 			tgt_j->pfn_atexit(us_elapsed_absolute,
@@ -841,3 +875,25 @@ const char *trace2_session_id(void)
 {
 	return tr2_sid_get();
 }
+
+void trace2_timer_start(enum trace2_timer_id tid)
+{
+	if (!trace2_enabled)
+		return;
+
+	if (tid < 0 || tid >= TRACE2_NUMBER_OF_TIMERS)
+		BUG("trace2_timer_start: invalid timer id: %d", tid);
+
+	tr2_start_timer(tid);
+}
+
+void trace2_timer_stop(enum trace2_timer_id tid)
+{
+	if (!trace2_enabled)
+		return;
+
+	if (tid < 0 || tid >= TRACE2_NUMBER_OF_TIMERS)
+		BUG("trace2_timer_stop: invalid timer id: %d", tid);
+
+	tr2_stop_timer(tid);
+}
diff --git a/trace2.h b/trace2.h
index 0cc7b5f5312..22da5c5516c 100644
--- a/trace2.h
+++ b/trace2.h
@@ -51,6 +51,7 @@ struct json_writer;
  * [] trace2_region*    -- emit region nesting messages.
  * [] trace2_data*      -- emit region/thread/repo data messages.
  * [] trace2_printf*    -- legacy trace[1] messages.
+ * [] trace2_timer*     -- start/stop stopwatch timer (messages are deferred).
  */
 
 /*
@@ -531,4 +532,45 @@ void trace2_collect_process_info(enum trace2_process_info_reason reason);
 
 const char *trace2_session_id(void);
 
+/*
+ * Define the set of stopwatch timers.
+ *
+ * We can add more at any time, but they must be defined at compile
+ * time (to avoid the need to dynamically allocate and synchronize
+ * them between different threads).
+ *
+ * These must start at 0 and be contiguous (because we use them
+ * elsewhere as array indexes).
+ *
+ * Any values added to this enum must also be added to the timer definitions
+ * array.  See `trace2/tr2_tmr.c:tr2_timer_def_block[]`.
+ */
+enum trace2_timer_id {
+	/*
+	 * Define two timers for testing.  See `t/helper/test-trace2.c`.
+	 * These can be used for ad hoc testing, but should not be used
+	 * for permanent analysis code.
+	 */
+	TRACE2_TIMER_ID_TEST1 = 0, /* emits summary event only */
+	TRACE2_TIMER_ID_TEST2,     /* emits summary and thread events */
+
+
+	/* Add additional timer definitions before here. */
+	TRACE2_NUMBER_OF_TIMERS
+};
+
+/*
+ * Start/Stop a stopwatch timer in the current thread.
+ *
+ * The time spent in each start/stop interval will be accumulated and
+ * a "timer" event will be emitted when the program exits.
+ *
+ * Note: Since the stopwatch API routines do not generate individual
+ * events, they do not take (file, line) arguments.  Similarly, the
+ * category and timer name values are defined at compile-time in the
+ * timer definitions array, so they are not needed here in the API.
+ */
+void trace2_timer_start(enum trace2_timer_id tid);
+void trace2_timer_stop(enum trace2_timer_id tid);
+
 #endif /* TRACE2_H */
diff --git a/trace2/tr2_tls.c b/trace2/tr2_tls.c
index 78538d5e522..675f6aeef31 100644
--- a/trace2/tr2_tls.c
+++ b/trace2/tr2_tls.c
@@ -1,6 +1,7 @@
 #include "cache.h"
 #include "thread-utils.h"
 #include "trace2/tr2_tls.h"
+#include "trace2/tr2_tmr.h"
 
 /*
  * Initialize size of the thread stack for nested regions.
@@ -204,3 +205,31 @@ int tr2tls_locked_increment(int *p)
 
 	return current_value;
 }
+
+void tr2_summarize_timers(struct tr2_timer_block *merged)
+{
+	struct tr2tls_thread_ctx *ctx = tr2tls_ctx_list;
+
+	while (ctx) {
+		struct tr2tls_thread_ctx *next = ctx->next_ctx;
+
+		tr2_merge_timer_block(merged, &ctx->timers);
+
+		ctx = next;
+	}
+}
+
+void tr2_emit_timers_by_thread(tr2_tgt_evt_timer_t *pfn,
+			       uint64_t us_elapsed_absolute)
+{
+	struct tr2tls_thread_ctx *ctx = tr2tls_ctx_list;
+
+	while (ctx) {
+		struct tr2tls_thread_ctx *next = ctx->next_ctx;
+
+		tr2_emit_timer_block(pfn, us_elapsed_absolute, &ctx->timers,
+				     ctx->thread_name);
+
+		ctx = next;
+	}
+}
diff --git a/trace2/tr2_tls.h b/trace2/tr2_tls.h
index 889010ec1ff..72e37beb1e7 100644
--- a/trace2/tr2_tls.h
+++ b/trace2/tr2_tls.h
@@ -2,6 +2,7 @@
 #define TR2_TLS_H
 
 #include "strbuf.h"
+#include "trace2/tr2_tmr.h"
 
 struct tr2tls_thread_ctx {
 	struct tr2tls_thread_ctx *next_ctx;
@@ -9,9 +10,26 @@ struct tr2tls_thread_ctx {
 	size_t alloc;
 	size_t nr_open_regions; /* plays role of "nr" in ALLOC_GROW */
 	int thread_id;
+
+	struct tr2_timer_block timers;
+
 	char thread_name[FLEX_ARRAY];
 };
 
+/*
+ * Iterate over the global list of threads and aggregate the timer
+ * data into the given timer block.  The resulting block will contain
+ * the global summary of timer usage.
+ */
+void tr2_summarize_timers(struct tr2_timer_block *merged);
+
+/*
+ * Iterate over the global list of threads and emit "per-thread"
+ * timer data.
+ */
+void tr2_emit_timers_by_thread(tr2_tgt_evt_timer_t *pfn,
+			       uint64_t us_elapsed_absolute);
+
 /*
  * Create TLS data for the current thread.  This gives us a place to
  * put per-thread data, such as thread start time, function nesting
diff --git a/trace2/tr2_tmr.c b/trace2/tr2_tmr.c
new file mode 100644
index 00000000000..c7edcfd55fb
--- /dev/null
+++ b/trace2/tr2_tmr.c
@@ -0,0 +1,136 @@
+#include "cache.h"
+#include "thread-utils.h"
+#include "trace2/tr2_tls.h"
+#include "trace2/tr2_tmr.h"
+
+#define MY_MAX(a, b) ((a) > (b) ? (a) : (b))
+#define MY_MIN(a, b) ((a) < (b) ? (a) : (b))
+
+/*
+ * Define metadata for each stopwatch timer.  This list must match the
+ * set defined in "enum trace2_timer_id".
+ */
+struct tr2_timer_def {
+	const char *category;
+	const char *name;
+
+	unsigned int want_thread_events:1;
+};
+
+static struct tr2_timer_def tr2_timer_def_block[TRACE2_NUMBER_OF_TIMERS] = {
+	[TRACE2_TIMER_ID_TEST1] = { "test", "test1", 0 },
+	[TRACE2_TIMER_ID_TEST2] = { "test", "test2", 1 },
+};
+
+void tr2_start_timer(enum trace2_timer_id tid)
+{
+	struct tr2tls_thread_ctx *ctx = tr2tls_get_self();
+	struct tr2_timer *t = &ctx->timers.timer[tid];
+
+	t->recursion_count++;
+	if (t->recursion_count > 1)
+		return; /* ignore recursive starts */
+
+	t->start_ns = getnanotime();
+}
+
+void tr2_stop_timer(enum trace2_timer_id tid)
+{
+	struct tr2tls_thread_ctx *ctx = tr2tls_get_self();
+	struct tr2_timer *t = &ctx->timers.timer[tid];
+	uint64_t ns_now;
+	uint64_t ns_interval;
+
+	assert(t->recursion_count > 0);
+
+	t->recursion_count--;
+	if (t->recursion_count)
+		return; /* still in recursive call(s) */
+
+	ns_now = getnanotime();
+	ns_interval = ns_now - t->start_ns;
+
+	t->total_ns += ns_interval;
+
+	/*
+	 * min_ns was initialized to zero (in the xcalloc()) rather
+	 * than "(unsigned)-1" when the block of timers was allocated,
+	 * so we should always set both the min_ns and max_ns values
+	 * the first time that the timer is used.
+	 */
+	if (!t->interval_count) {
+		t->min_ns = ns_interval;
+		t->max_ns = ns_interval;
+	} else {
+		t->min_ns = MY_MIN(ns_interval, t->min_ns);
+		t->max_ns = MY_MAX(ns_interval, t->max_ns);
+	}
+
+	t->interval_count++;
+}
+
+void tr2_merge_timer_block(struct tr2_timer_block *merged,
+			   const struct tr2_timer_block *src)
+{
+	enum trace2_timer_id tid;
+
+	for (tid = 0; tid < TRACE2_NUMBER_OF_TIMERS; tid++) {
+		struct tr2_timer *t_merged = &merged->timer[tid];
+		const struct tr2_timer *t = &src->timer[tid];
+
+		t_merged->is_aggregate = 1;
+
+		if (t->recursion_count) {
+			/*
+			 * A thread exited with a stopwatch running.
+			 *
+			 * NEEDSWORK: should we assert or throw a warning
+			 * for the open interval.  I'm going to ignore it
+			 * and keep going because we may have valid data
+			 * for previously closed intervals on this timer.
+			 *
+			 * That is, I'm going to ignore the value of
+			 * "now - start_ns".
+			 */
+		}
+
+		if (!t->interval_count)
+			continue; /* this timer was not used by this thread. */
+
+		t_merged->total_ns += t->total_ns;
+
+		if (!t_merged->interval_count) {
+			t_merged->min_ns = t->min_ns;
+			t_merged->max_ns = t->max_ns;
+		} else {
+			t_merged->min_ns = MY_MIN(t->min_ns, t_merged->min_ns);
+			t_merged->max_ns = MY_MAX(t->max_ns, t_merged->max_ns);
+		}
+
+		t_merged->interval_count += t->interval_count;
+	}
+
+	merged->is_aggregate = 1;
+}
+
+void tr2_emit_timer_block(tr2_tgt_evt_timer_t *pfn,
+			  uint64_t us_elapsed_absolute,
+			  const struct tr2_timer_block *blk,
+			  const char *thread_name)
+{
+	enum trace2_timer_id tid;
+
+	for (tid = 0; tid < TRACE2_NUMBER_OF_TIMERS; tid++) {
+		const struct tr2_timer *t = &blk->timer[tid];
+		const struct tr2_timer_def *d = &tr2_timer_def_block[tid];
+
+		if (!t->interval_count)
+			continue; /* timer was not used */
+
+		if (!d->want_thread_events && !t->is_aggregate)
+			continue; /* per-thread events not wanted */
+
+		pfn(us_elapsed_absolute, thread_name, d->category, d->name,
+		    t->interval_count, t->total_ns, t->min_ns, t->max_ns);
+	}
+}
diff --git a/trace2/tr2_tmr.h b/trace2/tr2_tmr.h
new file mode 100644
index 00000000000..1963e6ac475
--- /dev/null
+++ b/trace2/tr2_tmr.h
@@ -0,0 +1,139 @@
+#ifndef TR2_TM_H
+#define TR2_TM_H
+
+#include "trace2.h"
+#include "trace2/tr2_tgt.h"
+
+/*
+ * Define a mechanism to allow "stopwatch" timers.
+ *
+ * Timers can be used to measure "interesting" activity that does not
+ * fit the "region" model, such as code called from many different
+ * regions (like zlib) and/or where data for individual calls are not
+ * interesting or are too numerous to be efficiently logged.
+ *
+ * Timer values are accumulated during program execution and emitted
+ * to the Trace2 logs at program exit.
+ *
+ * To make this model efficient, we define a compile-time fixed set of
+ * timers and timer ids.  This lets us avoid the complexities of
+ * dynamically allocating a timer on demand and sharing that
+ * definition with other threads.
+ *
+ * Timer values are stored in a fixed size "timer block" inside thread
+ * local storage.  This allows data to be collected on a
+ * thread-by-thread basis without locking.
+ *
+ * Using this "timer block" model costs ~48 bytes per timer per thread
+ * (we have about six uint64 fields per timer).  This does increase
+ * the size of the thread local storage block, but it is allocated (at
+ * thread create time) and not on the thread stack, so I'm not worried
+ * about the size.  Using an array of timers in this block gives us
+ * constant time access to each timer within each thread, so we don't
+ * need to do expensive lookups (like hashmaps) to start/stop a timer.
+ *
+ * We define (at compile time) a set of "timer ids" to access the
+ * various timers inside the fixed size "timer block".  See
+ * `trace2_timer_id` in `trace2/trace2.h`.
+ *
+ * Timer definitions also include "category", "name", and similar
+ * fields.  These are defined in a parallel table in `tr2_tmr.c` and
+ * eliminate the need to include those args in the various timer APIs.
+ *
+ * Timer results are summarized and emitted by the main thread at
+ * program exit by iterating over the global list of thread local
+ * storage data blocks.
+ */
+
+/*
+ * The definition of an individual timer and used by an individual
+ * thread.
+ */
+struct tr2_timer {
+	/*
+	 * Total elapsed time for this timer in this thread in nanoseconds.
+	 */
+	uint64_t total_ns;
+
+	/*
+	 * The maximum and minimum interval values observed for this
+	 * timer in this thread.
+	 */
+	uint64_t min_ns;
+	uint64_t max_ns;
+
+	/*
+	 * The value of the clock when this timer was started in this
+	 * thread.  (Undefined when the timer is not active in this
+	 * thread.)
+	 */
+	uint64_t start_ns;
+
+	/*
+	 * Number of times that this timer has been started and stopped
+	 * in this thread.  (Recursive starts are ignored.)
+	 */
+	size_t interval_count;
+
+	/*
+	 * Number of nested starts on the stack in this thread.  (We
+	 * ignore recursive starts and use this to track the recursive
+	 * calls.)
+	 */
+	unsigned int recursion_count;
+
+	/*
+	 * Has data from multiple threads been combined into this object.
+	 */
+	unsigned int is_aggregate:1;
+};
+
+/*
+ * A compile-time fixed-size block of timers to insert into thread
+ * local storage.
+ *
+ * We use this simple wrapper around the array of timer instances to
+ * avoid C syntax quirks and the need to pass around an additional size_t
+ * argument.
+ */
+struct tr2_timer_block {
+	struct tr2_timer timer[TRACE2_NUMBER_OF_TIMERS];
+
+	/*
+	 * Has data from multiple threads been combined into this block.
+	 */
+	unsigned int is_aggregate:1;
+};
+
+/*
+ * Private routines used by trace2.c to actually start/stop an individual
+ * timer in the current thread.
+ */
+void tr2_start_timer(enum trace2_timer_id tid);
+void tr2_stop_timer(enum trace2_timer_id tid);
+
+/*
+ * Accumulate timer data for all of the individual timers in the source
+ * block into the corresponding timers in the merged block.
+ *
+ * This will aggregate data from one block (from an individual thread)
+ * into the merge block.
+ */
+void tr2_merge_timer_block(struct tr2_timer_block *merged,
+			   const struct tr2_timer_block *src);
+
+/*
+ * Send stopwatch data for all of the timers in this block to the
+ * trace target destination.
+ *
+ * This will generate an event record for each timer in the block that
+ * had activity during the program's execution.  (If this is called
+ * with a per-thread block, we emit the per-thread data; if called
+ * with a aggregate block, we emit summary data.)
+ */
+void tr2_emit_timer_block(tr2_tgt_evt_timer_t *pfn,
+			  uint64_t us_elapsed_absolute,
+			  const struct tr2_timer_block *blk,
+			  const char *thread_name);
+
+#endif /* TR2_TM_H */

diff --git a/trace2/tr2_tgt_perf.c b/trace2/tr2_tgt_perf.c
index fd6cce3efe5..c008fd08ae8 100644
--- a/trace2/tr2_tgt_perf.c
+++ b/trace2/tr2_tgt_perf.c
@@ -65,9 +65,14 @@ static void perf_fmt_prepare(const char *event_name,
 			     int line, const struct repository *repo,
 			     uint64_t *p_us_elapsed_absolute,
 			     uint64_t *p_us_elapsed_relative,
-			     const char *category, struct strbuf *buf)
+			     const char *category, struct strbuf *buf,
+			     const char *thread_name_override)
 {
 	int len;
+	const char *thread_name =
+		((thread_name_override && *thread_name_override)
+		 ? thread_name_override
+		 : ctx->thread_name);
 
 	strbuf_setlen(buf, 0);
 
@@ -107,7 +112,7 @@ static void perf_fmt_prepare(const char *event_name,
 
 	strbuf_addf(buf, "d%d | ", tr2_sid_depth());
 	strbuf_addf(buf, "%-*.*s | %-*s | ", TR2FMT_PERF_MAX_THREAD_NAME,
-		    TR2FMT_PERF_MAX_THREAD_NAME, ctx->thread_name,
+		    TR2FMT_PERF_MAX_THREAD_NAME, thread_name,
 		    TR2FMT_PERF_MAX_EVENT_NAME, event_name);
 
 	len = buf->len + TR2FMT_PERF_REPO_WIDTH;
@@ -141,14 +146,15 @@ static void perf_io_write_fl(const char *file, int line, const char *event_name,
 			     uint64_t *p_us_elapsed_absolute,
 			     uint64_t *p_us_elapsed_relative,
 			     const char *category,
-			     const struct strbuf *buf_payload)
+			     const struct strbuf *buf_payload,
+			     const char *thread_name_override)
 {
 	struct tr2tls_thread_ctx *ctx = tr2tls_get_self();
 	struct strbuf buf_line = STRBUF_INIT;
 
 	perf_fmt_prepare(event_name, ctx, file, line, repo,
 			 p_us_elapsed_absolute, p_us_elapsed_relative, category,
-			 &buf_line);
+			 &buf_line, thread_name_override);
 	strbuf_addbuf(&buf_line, buf_payload);
 	tr2_dst_write_line(&tr2dst_perf, &buf_line);
 	strbuf_release(&buf_line);
@@ -162,7 +168,7 @@ static void fn_version_fl(const char *file, int line)
 	strbuf_addstr(&buf_payload, git_version_string);
 
 	perf_io_write_fl(file, line, event_name, NULL, NULL, NULL, NULL,
-			 &buf_payload);
+			 &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -175,7 +181,7 @@ static void fn_start_fl(const char *file, int line,
 	sq_append_quote_argv_pretty(&buf_payload, argv);
 
 	perf_io_write_fl(file, line, event_name, NULL, &us_elapsed_absolute,
-			 NULL, NULL, &buf_payload);
+			 NULL, NULL, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -188,7 +194,7 @@ static void fn_exit_fl(const char *file, int line, uint64_t us_elapsed_absolute,
 	strbuf_addf(&buf_payload, "code:%d", code);
 
 	perf_io_write_fl(file, line, event_name, NULL, &us_elapsed_absolute,
-			 NULL, NULL, &buf_payload);
+			 NULL, NULL, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -200,7 +206,7 @@ static void fn_signal(uint64_t us_elapsed_absolute, int signo)
 	strbuf_addf(&buf_payload, "signo:%d", signo);
 
 	perf_io_write_fl(__FILE__, __LINE__, event_name, NULL,
-			 &us_elapsed_absolute, NULL, NULL, &buf_payload);
+			 &us_elapsed_absolute, NULL, NULL, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -212,7 +218,7 @@ static void fn_atexit(uint64_t us_elapsed_absolute, int code)
 	strbuf_addf(&buf_payload, "code:%d", code);
 
 	perf_io_write_fl(__FILE__, __LINE__, event_name, NULL,
-			 &us_elapsed_absolute, NULL, NULL, &buf_payload);
+			 &us_elapsed_absolute, NULL, NULL, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -238,7 +244,7 @@ static void fn_error_va_fl(const char *file, int line, const char *fmt,
 	maybe_append_string_va(&buf_payload, fmt, ap);
 
 	perf_io_write_fl(file, line, event_name, NULL, NULL, NULL, NULL,
-			 &buf_payload);
+			 &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -250,7 +256,7 @@ static void fn_command_path_fl(const char *file, int line, const char *pathname)
 	strbuf_addstr(&buf_payload, pathname);
 
 	perf_io_write_fl(file, line, event_name, NULL, NULL, NULL, NULL,
-			 &buf_payload);
+			 &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -265,7 +271,7 @@ static void fn_command_ancestry_fl(const char *file, int line, const char **pare
 	strbuf_addch(&buf_payload, ']');
 
 	perf_io_write_fl(file, line, event_name, NULL, NULL, NULL, NULL,
-			 &buf_payload);
+			 &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -280,7 +286,7 @@ static void fn_command_name_fl(const char *file, int line, const char *name,
 		strbuf_addf(&buf_payload, " (%s)", hierarchy);
 
 	perf_io_write_fl(file, line, event_name, NULL, NULL, NULL, NULL,
-			 &buf_payload);
+			 &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -292,7 +298,7 @@ static void fn_command_mode_fl(const char *file, int line, const char *mode)
 	strbuf_addstr(&buf_payload, mode);
 
 	perf_io_write_fl(file, line, event_name, NULL, NULL, NULL, NULL,
-			 &buf_payload);
+			 &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -307,7 +313,7 @@ static void fn_alias_fl(const char *file, int line, const char *alias,
 	strbuf_addch(&buf_payload, ']');
 
 	perf_io_write_fl(file, line, event_name, NULL, NULL, NULL, NULL,
-			 &buf_payload);
+			 &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -343,7 +349,7 @@ static void fn_child_start_fl(const char *file, int line,
 	strbuf_addch(&buf_payload, ']');
 
 	perf_io_write_fl(file, line, event_name, NULL, &us_elapsed_absolute,
-			 NULL, NULL, &buf_payload);
+			 NULL, NULL, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -357,7 +363,7 @@ static void fn_child_exit_fl(const char *file, int line,
 	strbuf_addf(&buf_payload, "[ch%d] pid:%d code:%d", cid, pid, code);
 
 	perf_io_write_fl(file, line, event_name, NULL, &us_elapsed_absolute,
-			 &us_elapsed_child, NULL, &buf_payload);
+			 &us_elapsed_child, NULL, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -371,7 +377,7 @@ static void fn_child_ready_fl(const char *file, int line,
 	strbuf_addf(&buf_payload, "[ch%d] pid:%d ready:%s", cid, pid, ready);
 
 	perf_io_write_fl(file, line, event_name, NULL, &us_elapsed_absolute,
-			 &us_elapsed_child, NULL, &buf_payload);
+			 &us_elapsed_child, NULL, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -382,7 +388,7 @@ static void fn_thread_start_fl(const char *file, int line,
 	struct strbuf buf_payload = STRBUF_INIT;
 
 	perf_io_write_fl(file, line, event_name, NULL, &us_elapsed_absolute,
-			 NULL, NULL, &buf_payload);
+			 NULL, NULL, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -394,7 +400,7 @@ static void fn_thread_exit_fl(const char *file, int line,
 	struct strbuf buf_payload = STRBUF_INIT;
 
 	perf_io_write_fl(file, line, event_name, NULL, &us_elapsed_absolute,
-			 &us_elapsed_thread, NULL, &buf_payload);
+			 &us_elapsed_thread, NULL, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -415,7 +421,7 @@ static void fn_exec_fl(const char *file, int line, uint64_t us_elapsed_absolute,
 	strbuf_addch(&buf_payload, ']');
 
 	perf_io_write_fl(file, line, event_name, NULL, &us_elapsed_absolute,
-			 NULL, NULL, &buf_payload);
+			 NULL, NULL, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -431,7 +437,7 @@ static void fn_exec_result_fl(const char *file, int line,
 		strbuf_addf(&buf_payload, " err:%s", strerror(code));
 
 	perf_io_write_fl(file, line, event_name, NULL, &us_elapsed_absolute,
-			 NULL, NULL, &buf_payload);
+			 NULL, NULL, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -444,7 +450,7 @@ static void fn_param_fl(const char *file, int line, const char *param,
 	strbuf_addf(&buf_payload, "%s:%s", param, value);
 
 	perf_io_write_fl(file, line, event_name, NULL, NULL, NULL, NULL,
-			 &buf_payload);
+			 &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -458,7 +464,7 @@ static void fn_repo_fl(const char *file, int line,
 	sq_quote_buf_pretty(&buf_payload, repo->worktree);
 
 	perf_io_write_fl(file, line, event_name, repo, NULL, NULL, NULL,
-			 &buf_payload);
+			 &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -480,7 +486,7 @@ static void fn_region_enter_printf_va_fl(const char *file, int line,
 	}
 
 	perf_io_write_fl(file, line, event_name, repo, &us_elapsed_absolute,
-			 NULL, category, &buf_payload);
+			 NULL, category, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -500,7 +506,7 @@ static void fn_region_leave_printf_va_fl(
 	}
 
 	perf_io_write_fl(file, line, event_name, repo, &us_elapsed_absolute,
-			 &us_elapsed_region, category, &buf_payload);
+			 &us_elapsed_region, category, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -515,7 +521,7 @@ static void fn_data_fl(const char *file, int line, uint64_t us_elapsed_absolute,
 	strbuf_addf(&buf_payload, "%s:%s", key, value);
 
 	perf_io_write_fl(file, line, event_name, repo, &us_elapsed_absolute,
-			 &us_elapsed_region, category, &buf_payload);
+			 &us_elapsed_region, category, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -531,7 +537,7 @@ static void fn_data_json_fl(const char *file, int line,
 	strbuf_addf(&buf_payload, "%s:%s", key, value->json.buf);
 
 	perf_io_write_fl(file, line, event_name, repo, &us_elapsed_absolute,
-			 &us_elapsed_region, category, &buf_payload);
+			 &us_elapsed_region, category, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 
@@ -545,7 +551,7 @@ static void fn_printf_va_fl(const char *file, int line,
 	maybe_append_string_va(&buf_payload, fmt, ap);
 
 	perf_io_write_fl(file, line, event_name, NULL, &us_elapsed_absolute,
-			 NULL, NULL, &buf_payload);
+			 NULL, NULL, &buf_payload, NULL);
 	strbuf_release(&buf_payload);
 }
 

diff --git a/trace2/tr2_tgt_event.c b/trace2/tr2_tgt_event.c
index b9eb2cdb77a..7aaec83dff7 100644
--- a/trace2/tr2_tgt_event.c
+++ b/trace2/tr2_tgt_event.c
@@ -82,16 +82,15 @@ static void fn_term(void)
 static void event_fmt_prepare(const char *event_name, const char *file,
 			      int line, const struct repository *repo,
 			      struct json_writer *jw,
-			      const char *thread_name_override)
+			      struct tr2tls_thread_ctx *ctx)
 {
 	struct tr2_tbuf tb_now;
+	if (!ctx)
+		ctx = tr2tls_get_self();
 
 	jw_object_string(jw, "event", event_name);
 	jw_object_string(jw, "sid", tr2_sid_get());
-	jw_object_string(jw, "thread",
-			 ((thread_name_override && *thread_name_override)
-			  ? thread_name_override
-			  : tr2tls_get_self()->thread_name));
+	jw_object_string(jw, "thread", ctx->thread_name);
 
 	/*
 	 * In brief mode, only emit <time> on these 2 event types.
@@ -111,6 +110,20 @@ static void event_fmt_prepare(const char *event_name, const char *file,
 		jw_object_intmax(jw, "repo", repo->trace2_repo_id);
 }
 
+static void event_fmt_prepare_tn(const char *event_name, const char *file,
+				 int line, const struct repository *repo,
+				 struct json_writer *jw,
+				 const char *thread_name)
+{
+	struct tr2tls_thread_ctx *ctx = tr2tls_get_self();
+	const char *tmp;
+
+	tmp = ctx->thread_name;
+	ctx->thread_name = thread_name;
+	event_fmt_prepare(event_name, __FILE__, __LINE__, NULL, jw, ctx);
+	ctx->thread_name = tmp;
+}
+
 static void fn_too_many_files_fl(const char *file, int line)
 {
 	const char *event_name = "too_many_files";
@@ -629,7 +642,7 @@ static void fn_timer(uint64_t us_elapsed_absolute,
 	double t_abs = (double)us_elapsed_absolute / 1000000.0;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, __FILE__, __LINE__, NULL, &jw, thread_name);
+	event_fmt_prepare_tn(event_name, __FILE__, __LINE__, NULL, &jw, thread_name);
 	jw_object_double(&jw, "t_abs", 6, t_abs);
 	jw_object_string(&jw, "name", timer_name);
 	jw_object_intmax(&jw, "count", interval_count);
@@ -654,7 +667,7 @@ static void fn_counter(uint64_t us_elapsed_absolute,
 	double t_abs = (double)us_elapsed_absolute / 1000000.0;
 
 	jw_object_begin(&jw, 0);
-	event_fmt_prepare(event_name, __FILE__, __LINE__, NULL, &jw, thread_name);
+	event_fmt_prepare_tn(event_name, __FILE__, __LINE__, NULL, &jw, thread_name);
 	jw_object_double(&jw, "t_abs", 6, t_abs);
 	jw_object_string(&jw, "name", counter_name);
 	jw_object_intmax(&jw, "value", value);

Documentation/technical/api-trace2.txt, trace2/tr2_tgt.h, trace2/tr2_tgt_event.c, trace2/tr2_tgt_normal.c, trace2/tr2_tgt_perf.c

diff --git a/Documentation/technical/api-trace2.txt b/Documentation/technical/api-trace2.txt
index bb13ca3db8b..351d140879e 100644
--- a/Documentation/technical/api-trace2.txt
+++ b/Documentation/technical/api-trace2.txt
@@ -815,6 +815,29 @@ The "value" field may be an integer or a string.
 }
 ------------
 
+`"timer"`::
+	This event is generated at the end of the program and contains
+	statistics for a global stopwatch timer.
++
+------------
+{
+	"event":"timer",
+	...
+	"name":"test",      # timer name
+	"count":42,         # number of start+stop intervals
+	"ns_total":1234,    # sum of all intervals in nanoseconds
+	"ns_min":11,        # shortest interval in nanoseconds
+	"ns_max":789,       # longest interval in nanoseconds
+}
+------------
++
+Stopwatch timer data is independently collected by each thread and then
+aggregated for the whole program, so the total time reported here
+may exceed the "atexit" elapsed time of the program.
++
+Timer events may represent an individual thread or a summation across
+the entire program.  Summation events will have a unique thread name.
+
 == Example Trace2 API Usage
 
 Here is a hypothetical usage of the Trace2 API showing the intended
diff --git a/trace2/tr2_tgt.h b/trace2/tr2_tgt.h
index 65f94e15748..a41f91d09b5 100644
--- a/trace2/tr2_tgt.h
+++ b/trace2/tr2_tgt.h
@@ -96,6 +96,30 @@ typedef void(tr2_tgt_evt_printf_va_fl_t)(const char *file, int line,
 					 uint64_t us_elapsed_absolute,
 					 const char *fmt, va_list ap);
 
+/*
+ * Stopwatch timer event.  This function writes the previously accumulated
+ * stopwatch timer values to the event streams.  Unlike other Trace2 API
+ * events, this is decoupled from the data collection.
+ *
+ * This does not take a (file,line) pair because a timer event reports
+ * the cumulative time spend in the timer over a series of intervals
+ * -- it does not represent a single usage (like region or data events
+ * do).
+ *
+ * The thread name is optional.  If non-null it will override the
+ * value inherited from the caller's thread local storage.  This
+ * allows timer data to be aggregated and reported without associating
+ * it to a specific thread.
+ */
+typedef void(tr2_tgt_evt_timer_t)(uint64_t us_elapsed_absolute,
+				  const char *thread_name,
+				  const char *category,
+				  const char *timer_name,
+				  uint64_t interval_count,
+				  uint64_t ns_total_time,
+				  uint64_t ns_min_time,
+				  uint64_t ns_max_time);
+
 /*
  * "vtable" for a TRACE2 target.  Use NULL if a target does not want
  * to emit that message.
@@ -132,6 +156,7 @@ struct tr2_tgt {
 	tr2_tgt_evt_data_fl_t                   *pfn_data_fl;
 	tr2_tgt_evt_data_json_fl_t              *pfn_data_json_fl;
 	tr2_tgt_evt_printf_va_fl_t              *pfn_printf_va_fl;
+	tr2_tgt_evt_timer_t                     *pfn_timer;
 };
 /* clang-format on */
 
diff --git a/trace2/tr2_tgt_event.c b/trace2/tr2_tgt_event.c
index 4ce50944298..fe89e80bb1a 100644
--- a/trace2/tr2_tgt_event.c
+++ b/trace2/tr2_tgt_event.c
@@ -615,6 +615,34 @@ static void fn_data_json_fl(const char *file, int line,
 	}
 }
 
+static void fn_timer(uint64_t us_elapsed_absolute,
+		     const char *thread_name,
+		     const char *category,
+		     const char *timer_name,
+		     uint64_t interval_count,
+		     uint64_t ns_total_time,
+		     uint64_t ns_min_time,
+		     uint64_t ns_max_time)
+{
+	const char *event_name = "timer";
+	struct json_writer jw = JSON_WRITER_INIT;
+	double t_abs = (double)us_elapsed_absolute / 1000000.0;
+
+	jw_object_begin(&jw, 0);
+	event_fmt_prepare(event_name, __FILE__, __LINE__, NULL, &jw, thread_name);
+	jw_object_double(&jw, "t_abs", 6, t_abs);
+	jw_object_string(&jw, "name", timer_name);
+	jw_object_intmax(&jw, "count", interval_count);
+	jw_object_intmax(&jw, "ns_total", ns_total_time);
+	jw_object_intmax(&jw, "ns_min", ns_min_time);
+	jw_object_intmax(&jw, "ns_max", ns_max_time);
+
+	jw_end(&jw);
+
+	tr2_dst_write_line(&tr2dst_event, &jw.json);
+	jw_release(&jw);
+}
+
 struct tr2_tgt tr2_tgt_event = {
 	&tr2dst_event,
 
@@ -646,4 +674,5 @@ struct tr2_tgt tr2_tgt_event = {
 	fn_data_fl,
 	fn_data_json_fl,
 	NULL, /* printf */
+	fn_timer,
 };
diff --git a/trace2/tr2_tgt_normal.c b/trace2/tr2_tgt_normal.c
index 58d9e430f05..23a7e78dcaa 100644
--- a/trace2/tr2_tgt_normal.c
+++ b/trace2/tr2_tgt_normal.c
@@ -355,4 +355,5 @@ struct tr2_tgt tr2_tgt_normal = {
 	NULL, /* data */
 	NULL, /* data_json */
 	fn_printf_va_fl,
+	NULL, /* timer */
 };
diff --git a/trace2/tr2_tgt_perf.c b/trace2/tr2_tgt_perf.c
index c008fd08ae8..c07ffad1a32 100644
--- a/trace2/tr2_tgt_perf.c
+++ b/trace2/tr2_tgt_perf.c
@@ -555,6 +555,32 @@ static void fn_printf_va_fl(const char *file, int line,
 	strbuf_release(&buf_payload);
 }
 
+static void fn_timer(uint64_t us_elapsed_absolute,
+		     const char *thread_name,
+		     const char *category,
+		     const char *timer_name,
+		     uint64_t interval_count,
+		     uint64_t ns_total_time,
+		     uint64_t ns_min_time,
+		     uint64_t ns_max_time)
+{
+	const char *event_name = "timer";
+	struct strbuf buf_payload = STRBUF_INIT;
+
+	strbuf_addf(&buf_payload, ("name:%s"
+				   " count:%"PRIu64
+				   " ns_total:%"PRIu64
+				   " ns_min:%"PRIu64
+				   " ns_max:%"PRIu64),
+		    timer_name, interval_count, ns_total_time, ns_min_time,
+		    ns_max_time);
+
+	perf_io_write_fl(__FILE__, __LINE__, event_name, NULL,
+			 &us_elapsed_absolute, NULL,
+			 category, &buf_payload, thread_name);
+	strbuf_release(&buf_payload);
+}
+
 struct tr2_tgt tr2_tgt_perf = {
 	&tr2dst_perf,
 
@@ -586,4 +612,5 @@ struct tr2_tgt tr2_tgt_perf = {
 	fn_data_fl,
 	fn_data_json_fl,
 	fn_printf_va_fl,
+	fn_timer,
 };

Documentation/technical/api-trace2.txt, trace2/tr2_tgt.h, trace2/tr2_tgt_event.c, trace2/tr2_tgt_normal.c, trace2/tr2_tgt_perf.c

diff --git a/Documentation/technical/api-trace2.txt b/Documentation/technical/api-trace2.txt
index 616001bcbb0..bdba0f92280 100644
--- a/Documentation/technical/api-trace2.txt
+++ b/Documentation/technical/api-trace2.txt
@@ -838,6 +838,25 @@ may exceed the "atexit" elapsed time of the program.
 Timer events may represent an individual thread or a summation across
 the entire program.  Summation events will have a unique thread name.
 
+`"counter"`::
+	This event is generated at the end of the program and contains
+	the value of a global counter.
++
+------------
+{
+	"event":"counter",
+	...
+	"name":"test",      # counter name
+	"value":42,         # value of the counter
+}
+------------
++
+A global counter can be incremented throughout the execution of the
+program.  It will be reported in a "counter" event just prior to exit.
++
+Counter events may represent an individual thread or a summation across
+the entire program.  Summation events will have a unique thread name.
+
 == Example Trace2 API Usage
 
 Here is a hypothetical usage of the Trace2 API showing the intended
diff --git a/trace2/tr2_tgt.h b/trace2/tr2_tgt.h
index a41f91d09b5..66f34b9258f 100644
--- a/trace2/tr2_tgt.h
+++ b/trace2/tr2_tgt.h
@@ -120,6 +120,19 @@ typedef void(tr2_tgt_evt_timer_t)(uint64_t us_elapsed_absolute,
 				  uint64_t ns_min_time,
 				  uint64_t ns_max_time);
 
+/*
+ * Item counter event.
+ *
+ * This also does not take a (file,line) pair.
+ *
+ * The thread name is optional.
+ */
+typedef void(tr2_tgt_evt_counter_t)(uint64_t us_elapsed_absolute,
+				    const char *thread_name,
+				    const char *category,
+				    const char *counter_name,
+				    uint64_t value);
+
 /*
  * "vtable" for a TRACE2 target.  Use NULL if a target does not want
  * to emit that message.
@@ -157,6 +170,7 @@ struct tr2_tgt {
 	tr2_tgt_evt_data_json_fl_t              *pfn_data_json_fl;
 	tr2_tgt_evt_printf_va_fl_t              *pfn_printf_va_fl;
 	tr2_tgt_evt_timer_t                     *pfn_timer;
+	tr2_tgt_evt_counter_t                   *pfn_counter;
 };
 /* clang-format on */
 
diff --git a/trace2/tr2_tgt_event.c b/trace2/tr2_tgt_event.c
index fe89e80bb1a..907bff80827 100644
--- a/trace2/tr2_tgt_event.c
+++ b/trace2/tr2_tgt_event.c
@@ -643,6 +643,28 @@ static void fn_timer(uint64_t us_elapsed_absolute,
 	jw_release(&jw);
 }
 
+static void fn_counter(uint64_t us_elapsed_absolute,
+		       const char *thread_name,
+		       const char *category,
+		       const char *counter_name,
+		       uint64_t value)
+{
+	const char *event_name = "counter";
+	struct json_writer jw = JSON_WRITER_INIT;
+	double t_abs = (double)us_elapsed_absolute / 1000000.0;
+
+	jw_object_begin(&jw, 0);
+	event_fmt_prepare(event_name, __FILE__, __LINE__, NULL, &jw, thread_name);
+	jw_object_double(&jw, "t_abs", 6, t_abs);
+	jw_object_string(&jw, "name", counter_name);
+	jw_object_intmax(&jw, "value", value);
+
+	jw_end(&jw);
+
+	tr2_dst_write_line(&tr2dst_event, &jw.json);
+	jw_release(&jw);
+}
+
 struct tr2_tgt tr2_tgt_event = {
 	&tr2dst_event,
 
@@ -675,4 +697,5 @@ struct tr2_tgt tr2_tgt_event = {
 	fn_data_json_fl,
 	NULL, /* printf */
 	fn_timer,
+	fn_counter,
 };
diff --git a/trace2/tr2_tgt_normal.c b/trace2/tr2_tgt_normal.c
index 23a7e78dcaa..1778232f6e9 100644
--- a/trace2/tr2_tgt_normal.c
+++ b/trace2/tr2_tgt_normal.c
@@ -356,4 +356,5 @@ struct tr2_tgt tr2_tgt_normal = {
 	NULL, /* data_json */
 	fn_printf_va_fl,
 	NULL, /* timer */
+	NULL, /* counter */
 };
diff --git a/trace2/tr2_tgt_perf.c b/trace2/tr2_tgt_perf.c
index c07ffad1a32..911cf6e6eab 100644
--- a/trace2/tr2_tgt_perf.c
+++ b/trace2/tr2_tgt_perf.c
@@ -581,6 +581,23 @@ static void fn_timer(uint64_t us_elapsed_absolute,
 	strbuf_release(&buf_payload);
 }
 
+static void fn_counter(uint64_t us_elapsed_absolute,
+		       const char *thread_name,
+		       const char *category,
+		       const char *counter_name,
+		       uint64_t value)
+{
+	const char *event_name = "counter";
+	struct strbuf buf_payload = STRBUF_INIT;
+
+	strbuf_addf(&buf_payload, "name:%s value:%"PRIu64, counter_name, value);
+
+	perf_io_write_fl(__FILE__, __LINE__, event_name, NULL,
+			 &us_elapsed_absolute, NULL,
+			 category, &buf_payload, thread_name);
+	strbuf_release(&buf_payload);
+}
+
 struct tr2_tgt tr2_tgt_perf = {
 	&tr2dst_perf,
 
@@ -613,4 +630,5 @@ struct tr2_tgt tr2_tgt_perf = {
 	fn_data_json_fl,
 	fn_printf_va_fl,
 	fn_timer,
+	fn_counter,
 };

Documentation/technical/api-trace2.txt, Makefile, t/helper/test-trace2.c, t/t0211-trace2-perf.sh, t/t0212-trace2-event.sh, trace2.c, trace2.h, trace2/tr2_ctr.c, trace2/tr2_ctr.h, trace2/tr2_tls.c, trace2/tr2_tls.h

diff --git a/Documentation/technical/api-trace2.txt b/Documentation/technical/api-trace2.txt
index bdba0f92280..a3ea867ff92 100644
--- a/Documentation/technical/api-trace2.txt
+++ b/Documentation/technical/api-trace2.txt
@@ -1297,6 +1297,73 @@ d0 | main                     | atexit       |     |  0.111026 |           |
 In this example, the "test1" timer was started 4 times and ran for
 0.000393 seconds.
 
+Counter Events::
+
+	Trace2 also provides global counters as an alternative to regions
+	and data events.  These make it possible to count an activity of
+	interest, such a call to a library routine, during the program
+	and get a single counter event at the end.
++
+At the end of the program, a single summary event is emitted; this
+value is aggregated across all threads.  These events have "summary"
+as their thread name.
++
+For some counters, individual (per-thread) counter events are also
+generated.  This may be helpful in understanding how work is balanced
+between threads in some circumstances.
++
+----------------
+static void *load_cache_entries_thread(void *_data)
+{
+	struct load_cache_entries_thread_data *p = _data;
+	int i;
+
+	trace2_thread_start("load_cache_entries");
+	...
+	trace2_thread_exit();
+}
+
+static unsigned long load_cache_entry_block(struct index_state *istate,
+			struct mem_pool *ce_mem_pool, int offset, int nr, const char *mmap,
+			unsigned long start_offset, const struct cache_entry *previous_ce)
+{
+	int i;
+	unsigned long src_offset = start_offset;
+
+	trace2_counter_increment(TRACE2_COUNTER_ID_TEST2, nr);
+
+	for (i = offset; i < offset + nr; i++) {
+		...
+	}
+}
+----------------
++
+----------------
+$ export GIT_TRACE2_PERF_BRIEF=1
+$ export GIT_TRACE2_PERF=~/log.perf
+$ git status
+...
+$ cat ~/log.perf
+...
+d0 | main                     | exit         |     | 53.977680 |           |              | code:0
+d0 | th12:load_cache_entries  | counter      |     | 53.977708 |           | test         | name:test2 value:193220
+d0 | th11:load_cache_entries  | counter      |     | 53.977708 |           | test         | name:test2 value:193221
+d0 | th10:load_cache_entries  | counter      |     | 53.977708 |           | test         | name:test2 value:193221
+d0 | th09:load_cache_entries  | counter      |     | 53.977708 |           | test         | name:test2 value:193221
+d0 | th08:load_cache_entries  | counter      |     | 53.977708 |           | test         | name:test2 value:193221
+d0 | th07:load_cache_entries  | counter      |     | 53.977708 |           | test         | name:test2 value:193221
+d0 | th06:load_cache_entries  | counter      |     | 53.977708 |           | test         | name:test2 value:193221
+d0 | th05:load_cache_entries  | counter      |     | 53.977708 |           | test         | name:test2 value:193221
+d0 | th04:load_cache_entries  | counter      |     | 53.977708 |           | test         | name:test2 value:193221
+d0 | th03:load_cache_entries  | counter      |     | 53.977708 |           | test         | name:test2 value:193221
+d0 | th02:load_cache_entries  | counter      |     | 53.977708 |           | test         | name:test2 value:193221
+d0 | summary                  | counter      |     | 53.977708 |           | test         | name:test2 value:2125430
+d0 | main                     | atexit       |     | 53.977708 |           |              | code:0
+----------------
++
+This example shows the value computed by each of the 11
+`load_cache_entries` threads and the total across all threads.
+
 == Future Work
 
 === Relationship to the Existing Trace Api (api-trace.txt)
diff --git a/Makefile b/Makefile
index 8b657f0162a..cc5bd8593f1 100644
--- a/Makefile
+++ b/Makefile
@@ -1020,6 +1020,7 @@ LIB_OBJS += trace.o
 LIB_OBJS += trace2.o
 LIB_OBJS += trace2/tr2_cfg.o
 LIB_OBJS += trace2/tr2_cmd_name.o
+LIB_OBJS += trace2/tr2_ctr.o
 LIB_OBJS += trace2/tr2_dst.o
 LIB_OBJS += trace2/tr2_sid.o
 LIB_OBJS += trace2/tr2_tmr.o
diff --git a/t/helper/test-trace2.c b/t/helper/test-trace2.c
index 51d022422bf..a7dbecfda9a 100644
--- a/t/helper/test-trace2.c
+++ b/t/helper/test-trace2.c
@@ -270,7 +270,7 @@ static int ut_009timer(int argc, const char **argv)
 	const char *usage_error =
 		"expect <count> <ms_delay> <threads>";
 
-	struct ut_009_data data = { 0, 0 };
+	struct ut_009_data data = { 0 };
 	int nr_threads = 0;
 	int k;
 	pthread_t *pids = NULL;
@@ -301,6 +301,90 @@ static int ut_009timer(int argc, const char **argv)
 	return 0;
 }
 
+/*
+ * Single-threaded counter test.  Add several values to the TEST1 counter.
+ * The test script can verify that an aggregate Trace2 "counter" event is
+ * emitted containing the sum of the values provided.
+ */
+static int ut_010counter(int argc, const char **argv)
+{
+	const char *usage_error =
+		"expect <v1> [<v2> [...]]";
+	int value;
+	int k;
+
+	if (argc < 1)
+		die("%s", usage_error);
+
+	for (k = 0; k < argc; k++) {
+		if (get_i(&value, argv[k]))
+			die("invalid value[%s] -- %s",
+			    argv[k], usage_error);
+		trace2_counter_add(TRACE2_COUNTER_ID_TEST1, value);
+	}
+
+	return 0;
+}
+
+struct ut_011_data {
+	int v1, v2;
+};
+
+static void *ut_011counter_thread_proc(void *_ut_011_data)
+{
+	struct ut_011_data *data = _ut_011_data;
+
+	trace2_thread_start("ut_011");
+
+	trace2_counter_add(TRACE2_COUNTER_ID_TEST2, data->v1);
+	trace2_counter_add(TRACE2_COUNTER_ID_TEST2, data->v2);
+
+	trace2_thread_exit();
+	return NULL;
+}
+
+/*
+ * Multi-threaded counter test.  Create several threads that each
+ * increment the TEST2 global counter.  The test script can verify
+ * that an individual Trace2 "counter" event for each thread and an
+ * aggregate "counter" event are generated.
+ */
+static int ut_011counter(int argc, const char **argv)
+{
+	const char *usage_error =
+		"expect <v1> <v2> <threads>";
+
+	struct ut_011_data data = { 0, 0 };
+	int nr_threads = 0;
+	int k;
+	pthread_t *pids = NULL;
+
+	if (argc != 3)
+		die("%s", usage_error);
+	if (get_i(&data.v1, argv[0]))
+		die("%s", usage_error);
+	if (get_i(&data.v2, argv[1]))
+		die("%s", usage_error);
+	if (get_i(&nr_threads, argv[2]))
+		die("%s", usage_error);
+
+	CALLOC_ARRAY(pids, nr_threads);
+
+	for (k = 0; k < nr_threads; k++) {
+		if (pthread_create(&pids[k], NULL, ut_011counter_thread_proc, &data))
+			die("failed to create thread[%d]", k);
+	}
+
+	for (k = 0; k < nr_threads; k++) {
+		if (pthread_join(pids[k], NULL))
+			die("failed to join thread[%d]", k);
+	}
+
+	free(pids);
+
+	return 0;
+}
+
 /*
  * Usage:
  *     test-tool trace2 <ut_name_1> <ut_usage_1>
@@ -320,6 +404,8 @@ static struct unit_test ut_table[] = {
 	{ ut_007bug,      "007bug",    "" },
 	{ ut_008timer,    "008timer",  "<count> <ms_delay>" },
 	{ ut_009timer,    "009timer",  "<count> <ms_delay> <threads>" },
+	{ ut_010counter,  "010counter","<v1> [<v2> [<v3> [...]]]" },
+	{ ut_011counter,  "011counter","<v1> <v2> <threads>" },
 };
 /* clang-format on */
 
diff --git a/t/t0211-trace2-perf.sh b/t/t0211-trace2-perf.sh
index 381c3eea458..5f9a3533ce4 100755
--- a/t/t0211-trace2-perf.sh
+++ b/t/t0211-trace2-perf.sh
@@ -219,4 +219,46 @@ test_expect_success 'test stopwatch timers - summary and threads' '
 	have_timer_event "summary" "test2" 15 actual
 '
 
+# Exercise the global counter "test" in a loop and confirm that we get an
+# event with the sum.
+#
+
+have_counter_event () {
+	thread=$1
+	name=$2
+	value=$3
+	file=$4
+
+	pattern="d0|${thread}|counter||_T_ABS_||test"
+	pattern="${pattern}|name:${name}"
+	pattern="${pattern} value:${value}"
+
+	grep "${pattern}" ${file}
+
+	return $?
+}
+
+test_expect_success 'test global counters - global, single-thead' '
+	test_when_finished "rm trace.perf actual" &&
+	test_config_global trace2.perfBrief 1 &&
+	test_config_global trace2.perfTarget "$(pwd)/trace.perf" &&
+	test-tool trace2 010counter 2 3 5 7 11 13  &&
+	perl "$TEST_DIRECTORY/t0211/scrub_perf.perl" <trace.perf >actual &&
+
+	have_counter_event "summary" "test1" 41 actual
+'
+
+test_expect_success 'test global counters - global+threads' '
+	test_when_finished "rm trace.perf actual" &&
+	test_config_global trace2.perfBrief 1 &&
+	test_config_global trace2.perfTarget "$(pwd)/trace.perf" &&
+	test-tool trace2 011counter 5 10 3 &&
+	perl "$TEST_DIRECTORY/t0211/scrub_perf.perl" <trace.perf >actual &&
+
+	have_counter_event "th01:ut_011" "test2" 15 actual &&
+	have_counter_event "th02:ut_011" "test2" 15 actual &&
+	have_counter_event "th03:ut_011" "test2" 15 actual &&
+	have_counter_event "summary" "test2" 45 actual
+'
+
 test_done
diff --git a/t/t0212-trace2-event.sh b/t/t0212-trace2-event.sh
index 277688fdbc4..9e76ef5caa7 100755
--- a/t/t0212-trace2-event.sh
+++ b/t/t0212-trace2-event.sh
@@ -368,4 +368,45 @@ test_expect_success 'test stopwatch timers - global+threads' '
 	have_timer_event "summary" "test2" 15 trace.event
 '
 
+# Exercise the global counter in a loop and confirm that we get the
+# expected sum in an event record.
+#
+
+have_counter_event () {
+	thread=$1
+	name=$2
+	value=$3
+	file=$4
+
+	pattern="\"event\":\"counter\""
+	pattern="${pattern}.*\"thread\":\"${thread}\""
+	pattern="${pattern}.*\"name\":\"${name}\""
+	pattern="${pattern}.*\"value\":${value}"
+
+	grep "${pattern}" ${file}
+
+	return $?
+}
+
+test_expect_success 'test global counter - global, single-thread' '
+	test_when_finished "rm trace.event" &&
+	test_config_global trace2.eventBrief 1 &&
+	test_config_global trace2.eventTarget "$(pwd)/trace.event" &&
+	test-tool trace2 010counter 2 3 5 7 11 13 &&
+
+	have_counter_event "summary" "test1" 41 trace.event
+'
+
+test_expect_success 'test global counter - global+threads' '
+	test_when_finished "rm trace.event" &&
+	test_config_global trace2.eventBrief 1 &&
+	test_config_global trace2.eventTarget "$(pwd)/trace.event" &&
+	test-tool trace2 011counter 5 10 3 &&
+
+	have_counter_event "th01:ut_011" "test2" 15 trace.event &&
+	have_counter_event "th02:ut_011" "test2" 15 trace.event &&
+	have_counter_event "th03:ut_011" "test2" 15 trace.event &&
+	have_counter_event "summary" "test2" 45 trace.event
+'
+
 test_done
diff --git a/trace2.c b/trace2.c
index 23289dd6eb4..aa6ed6dd3ee 100644
--- a/trace2.c
+++ b/trace2.c
@@ -8,6 +8,7 @@
 #include "version.h"
 #include "trace2/tr2_cfg.h"
 #include "trace2/tr2_cmd_name.h"
+#include "trace2/tr2_ctr.h"
 #include "trace2/tr2_dst.h"
 #include "trace2/tr2_sid.h"
 #include "trace2/tr2_sysenv.h"
@@ -114,6 +115,41 @@ static void tr2main_emit_thread_timers(uint64_t us_elapsed_absolute)
 						  us_elapsed_absolute);
 }
 
+static void tr2main_emit_summary_counters(uint64_t us_elapsed_absolute)
+{
+	struct tr2_tgt *tgt_j;
+	int j;
+	struct tr2_counter_block merged = { { { 0 } } };
+
+	/*
+	 * Sum across all of the per-thread counter data into
+	 * a single composite block of counter values.
+	 */
+	tr2tls_aggregate_counter_blocks(&merged);
+
+	/*
+	 * Emit "summary" counter events for each composite counter value
+	 * that had activity.
+	 */
+	for_each_wanted_builtin (j, tgt_j)
+		if (tgt_j->pfn_counter)
+			tr2_emit_counter_block(tgt_j->pfn_counter,
+					       us_elapsed_absolute,
+					       &merged, "summary");
+}
+
+static void tr2main_emit_thread_counters(uint64_t us_elapsed_absolute)
+{
+	struct tr2_tgt *tgt_j;
+	int j;
+
+	for_each_wanted_builtin (j, tgt_j)
+		if (tgt_j->pfn_counter)
+			tr2tls_emit_counter_blocks_by_thread(
+				tgt_j->pfn_counter,
+				us_elapsed_absolute);
+}
+
 static int tr2main_exit_code;
 
 /*
@@ -144,6 +180,9 @@ static void tr2main_atexit_handler(void)
 	tr2main_emit_thread_timers(us_elapsed_absolute);
 	tr2main_emit_summary_timers(us_elapsed_absolute);
 
+	tr2main_emit_thread_counters(us_elapsed_absolute);
+	tr2main_emit_summary_counters(us_elapsed_absolute);
+
 	for_each_wanted_builtin (j, tgt_j)
 		if (tgt_j->pfn_atexit)
 			tgt_j->pfn_atexit(us_elapsed_absolute,
@@ -897,3 +936,14 @@ void trace2_timer_stop(enum trace2_timer_id tid)
 
 	tr2_stop_timer(tid);
 }
+
+void trace2_counter_add(enum trace2_counter_id cid, uint64_t value)
+{
+	if (!trace2_enabled)
+		return;
+
+	if (cid < 0 || cid >= TRACE2_NUMBER_OF_COUNTERS)
+		BUG("invalid counter id: %d", cid);
+
+	tr2_counter_increment(cid, value);
+}
diff --git a/trace2.h b/trace2.h
index 22da5c5516c..d4ed602c19a 100644
--- a/trace2.h
+++ b/trace2.h
@@ -52,6 +52,7 @@ struct json_writer;
  * [] trace2_data*      -- emit region/thread/repo data messages.
  * [] trace2_printf*    -- legacy trace[1] messages.
  * [] trace2_timer*     -- start/stop stopwatch timer (messages are deferred).
+ * [] trace2_counter*   -- global counters (messages are deferrred).
  */
 
 /*
@@ -573,4 +574,36 @@ enum trace2_timer_id {
 void trace2_timer_start(enum trace2_timer_id tid);
 void trace2_timer_stop(enum trace2_timer_id tid);
 
+/*
+ * Define the set of global counters.
+ *
+ * We can add more at any time, but they must be defined at compile
+ * time (to avoid the need to dynamically allocate and synchronize
+ * them between different threads).
+ *
+ * These must start at 0 and be contiguous (because we them elsewhere
+ * as array indexes).
+ *
+ * Any value added to this enum must also be added to the counter
+ * definitions array.  See `trace2/tr2_ctr.c:tr2_counter_def_block[]`.
+ */
+enum trace2_counter_id {
+	/*
+	 * Define two counters for testing.  See `t/helper/test-trace2.c`.
+	 * These can be used for ad hoc testing, but should not be used
+	 * for permanent analysis code.
+	 */
+	TRACE2_COUNTER_ID_TEST1 = 0, /* emits summary event only */
+	TRACE2_COUNTER_ID_TEST2,     /* emits summary and thread events */
+
+
+	/* Add additional counter definitions before here. */
+	TRACE2_NUMBER_OF_COUNTERS
+};
+
+/*
+ * Increment global counter by value.
+ */
+void trace2_counter_add(enum trace2_counter_id cid, uint64_t value);
+
 #endif /* TRACE2_H */
diff --git a/trace2/tr2_ctr.c b/trace2/tr2_ctr.c
new file mode 100644
index 00000000000..ce80ceb5476
--- /dev/null
+++ b/trace2/tr2_ctr.c
@@ -0,0 +1,67 @@
+#include "cache.h"
+#include "thread-utils.h"
+#include "trace2/tr2_tls.h"
+#include "trace2/tr2_ctr.h"
+
+/*
+ * Define metadata for each global counter.  This list must match the
+ * set defined in "enum trace2_counter_id".
+ */
+struct tr2_counter_def {
+	const char *category;
+	const char *name;
+
+	unsigned int want_thread_events:1;
+};
+
+static struct tr2_counter_def tr2_counter_def_block[TRACE2_NUMBER_OF_COUNTERS] = {
+	[TRACE2_COUNTER_ID_TEST1] = { "test", "test1", 0 },
+	[TRACE2_COUNTER_ID_TEST2] = { "test", "test2", 1 },
+};
+
+void tr2_counter_increment(enum trace2_counter_id cid, uint64_t value)
+{
+	struct tr2tls_thread_ctx *ctx = tr2tls_get_self();
+	struct tr2_counter *c = &ctx->counters.counter[cid];
+
+	c->value += value;
+}
+
+void tr2_merge_counter_block(struct tr2_counter_block *merged,
+			     const struct tr2_counter_block *src)
+{
+	enum trace2_counter_id cid;
+
+	for (cid = 0; cid < TRACE2_NUMBER_OF_COUNTERS; cid++) {
+		struct tr2_counter *c_merged = &merged->counter[cid];
+		const struct tr2_counter *c = &src->counter[cid];
+
+		c_merged->is_aggregate = 1;
+
+		c_merged->value += c->value;
+	}
+
+	merged->is_aggregate = 1;
+}
+
+void tr2_emit_counter_block(tr2_tgt_evt_counter_t *pfn,
+			    uint64_t us_elapsed_absolute,
+			    const struct tr2_counter_block *blk,
+			    const char *thread_name)
+{
+	enum trace2_counter_id cid;
+
+	for (cid = 0; cid < TRACE2_NUMBER_OF_COUNTERS; cid++) {
+		const struct tr2_counter *c = &blk->counter[cid];
+		const struct tr2_counter_def *d = &tr2_counter_def_block[cid];
+
+		if (!c->value)
+			continue; /* counter was not used */
+
+		if (!d->want_thread_events && !c->is_aggregate)
+			continue; /* per-thread events not wanted */
+
+		pfn(us_elapsed_absolute, thread_name, d->category, d->name,
+		    c->value);
+	}
+}
diff --git a/trace2/tr2_ctr.h b/trace2/tr2_ctr.h
new file mode 100644
index 00000000000..fd6fbef89a2
--- /dev/null
+++ b/trace2/tr2_ctr.h
@@ -0,0 +1,79 @@
+#ifndef TR2_CTR_H
+#define TR2_CTR_H
+
+#include "trace2.h"
+#include "trace2/tr2_tgt.h"
+
+/*
+ * Define a mechanism to allow global "counters".
+ *
+ * Counters can be used count interesting activity that does not fit
+ * the "region and data" model, such as code called from many
+ * different regions and/or where you want to count a number of items,
+ * but don't have control of when the last item will be processed,
+ * such as counter the number of calls to `lstat()`.
+ *
+ * Counters differ from Trace2 "data" events.  Data events are emitted
+ * immediately and are appropriate for documenting loop counters and
+ * etc.  Counter values are accumulated during the program and the final
+ * counter value event is emitted at program exit.
+ *
+ * To make this model efficient, we define a compile-time fixed set
+ * of counters and counter ids.  This lets us avoid the complexities
+ * of dynamically allocating a counter and sharing that definition
+ * with other threads.
+ *
+ * We define (at compile time) a set of "counter ids" to access the
+ * various counters inside of a fixed size "counter block".
+ *
+ * A counter defintion table provides the counter category and name
+ * so we can eliminate those arguments from the public counter API.
+ * These are defined in a parallel tabel in `tr2_ctr.c`.
+ *
+ * Each thread has a private block of counters in its thread local
+ * storage data so no locks are required for a thread to increment
+ * it's version of the counter.  At program exit, the counter blocks
+ * from all of the per-thread counters are added together to give the
+ * final summary value for the each global counter.
+ */
+
+/*
+ * The definition of an individual counter.
+ */
+struct tr2_counter {
+	uint64_t value;
+
+	unsigned int is_aggregate:1;
+};
+
+/*
+ * Compile time fixed block of all defined counters.
+ */
+struct tr2_counter_block {
+	struct tr2_counter counter[TRACE2_NUMBER_OF_COUNTERS];
+
+	unsigned int is_aggregate:1;
+};
+
+/*
+ * Add "value" to the global counter.
+ */
+void tr2_counter_increment(enum trace2_counter_id cid, uint64_t value);
+
+/*
+ * Accumulate counter data from the source block into the merged block.
+ */
+void tr2_merge_counter_block(struct tr2_counter_block *merged,
+			       const struct tr2_counter_block *src);
+
+/*
+ * Send counter data for all counters in this block to the target.
+ *
+ * This will generate an event record for each counter that had activity.
+ */
+void tr2_emit_counter_block(tr2_tgt_evt_counter_t *pfn,
+			    uint64_t us_elapsed_absolute,
+			    const struct tr2_counter_block *blk,
+			    const char *thread_name);
+
+#endif /* TR2_CTR_H */
diff --git a/trace2/tr2_tls.c b/trace2/tr2_tls.c
index 675f6aeef31..28ea55863d1 100644
--- a/trace2/tr2_tls.c
+++ b/trace2/tr2_tls.c
@@ -1,5 +1,6 @@
 #include "cache.h"
 #include "thread-utils.h"
+#include "trace2/tr2_ctr.h"
 #include "trace2/tr2_tls.h"
 #include "trace2/tr2_tmr.h"
 
@@ -233,3 +234,31 @@ void tr2_emit_timers_by_thread(tr2_tgt_evt_timer_t *pfn,
 		ctx = next;
 	}
 }
+
+void tr2tls_aggregate_counter_blocks(struct tr2_counter_block *merged)
+{
+	struct tr2tls_thread_ctx *ctx = tr2tls_ctx_list;
+
+	while (ctx) {
+		struct tr2tls_thread_ctx *next = ctx->next_ctx;
+
+		tr2_merge_counter_block(merged, &ctx->counters);
+
+		ctx = next;
+	}
+}
+
+void tr2tls_emit_counter_blocks_by_thread(tr2_tgt_evt_counter_t *pfn,
+					  uint64_t us_elapsed_absolute)
+{
+	struct tr2tls_thread_ctx *ctx = tr2tls_ctx_list;
+
+	while (ctx) {
+		struct tr2tls_thread_ctx *next = ctx->next_ctx;
+
+		tr2_emit_counter_block(pfn, us_elapsed_absolute, &ctx->counters,
+				       ctx->thread_name);
+
+		ctx = next;
+	}
+}
diff --git a/trace2/tr2_tls.h b/trace2/tr2_tls.h
index 72e37beb1e7..503829bbd44 100644
--- a/trace2/tr2_tls.h
+++ b/trace2/tr2_tls.h
@@ -2,6 +2,7 @@
 #define TR2_TLS_H
 
 #include "strbuf.h"
+#include "trace2/tr2_ctr.h"
 #include "trace2/tr2_tmr.h"
 
 struct tr2tls_thread_ctx {
@@ -12,10 +13,25 @@ struct tr2tls_thread_ctx {
 	int thread_id;
 
 	struct tr2_timer_block timers;
+	struct tr2_counter_block counters;
 
 	char thread_name[FLEX_ARRAY];
 };
 
+/*
+ * Iterate over the global list of threads and aggregate the
+ * counter data into the given counter block.  The resulting block
+ * will contain the global counter sums.
+ */
+void tr2tls_aggregate_counter_blocks(struct tr2_counter_block *merged);
+
+/*
+ * Iterate over the global list of threads and emit "per-thread"
+ * counter data for each.
+ */
+void tr2tls_emit_counter_blocks_by_thread(tr2_tgt_evt_counter_t *pfn,
+					  uint64_t us_elapsed_absolute);
+
 /*
  * Iterate over the global list of threads and aggregate the timer
  * data into the given timer block.  The resulting block will contain