6 files changed, 145 insertions, 4 deletions

diff --git a/tools/lib/api/io.h b/tools/lib/api/io.h
index d3eb04d1bc89..1731996b2c32 100644
--- a/tools/lib/api/io.h
+++ b/tools/lib/api/io.h
@@ -189,6 +189,7 @@ static inline ssize_t io__getdelim(struct io *io, char **line_out, size_t *line_
 err_out:
 	free(line);
 	*line_out = NULL;
+	*line_len_out = 0;
 	return -ENOMEM;
 }
 
diff --git a/tools/lib/perf/Documentation/Makefile b/tools/lib/perf/Documentation/Makefile
index 972754082a85..573ca5b27556 100644
--- a/tools/lib/perf/Documentation/Makefile
+++ b/tools/lib/perf/Documentation/Makefile
@@ -121,7 +121,7 @@ install-man: all
 		$(INSTALL) -d -m 755 $(DESTDIR)$(man7dir); \
 		$(INSTALL) -m 644 $(MAN_7) $(DESTDIR)$(man7dir);
 
-install-html:
+install-html: $(MAN_HTML)
 	$(call QUIET_INSTALL, html) \
 		$(INSTALL) -d -m 755 $(DESTDIR)$(htmldir); \
 		$(INSTALL) -m 644 $(MAN_HTML) $(DESTDIR)$(htmldir); \
diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c
index c07160953224..c475319e2e41 100644
--- a/tools/lib/perf/evsel.c
+++ b/tools/lib/perf/evsel.c
@@ -5,6 +5,7 @@
 #include <perf/evsel.h>
 #include <perf/cpumap.h>
 #include <perf/threadmap.h>
+#include <linux/hash.h>
 #include <linux/list.h>
 #include <internal/evsel.h>
 #include <linux/zalloc.h>
@@ -23,6 +24,7 @@ void perf_evsel__init(struct perf_evsel *evsel, struct perf_event_attr *attr,
 		      int idx)
 {
 	INIT_LIST_HEAD(&evsel->node);
+	INIT_LIST_HEAD(&evsel->per_stream_periods);
 	evsel->attr = *attr;
 	evsel->idx  = idx;
 	evsel->leader = evsel;
@@ -531,10 +533,56 @@ int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
 
 void perf_evsel__free_id(struct perf_evsel *evsel)
 {
+	struct perf_sample_id_period *pos, *n;
+
 	xyarray__delete(evsel->sample_id);
 	evsel->sample_id = NULL;
 	zfree(&evsel->id);
 	evsel->ids = 0;
+
+	perf_evsel_for_each_per_thread_period_safe(evsel, n, pos) {
+		list_del_init(&pos->node);
+		free(pos);
+	}
+}
+
+bool perf_evsel__attr_has_per_thread_sample_period(struct perf_evsel *evsel)
+{
+	return (evsel->attr.sample_type & PERF_SAMPLE_READ) &&
+		(evsel->attr.sample_type & PERF_SAMPLE_TID) &&
+		evsel->attr.inherit;
+}
+
+u64 *perf_sample_id__get_period_storage(struct perf_sample_id *sid, u32 tid, bool per_thread)
+{
+	struct hlist_head *head;
+	struct perf_sample_id_period *res;
+	int hash;
+
+	if (!per_thread)
+		return &sid->period;
+
+	hash = hash_32(tid, PERF_SAMPLE_ID__HLIST_BITS);
+	head = &sid->periods[hash];
+
+	hlist_for_each_entry(res, head, hnode)
+		if (res->tid == tid)
+			return &res->period;
+
+	if (sid->evsel == NULL)
+		return NULL;
+
+	res = zalloc(sizeof(struct perf_sample_id_period));
+	if (res == NULL)
+		return NULL;
+
+	INIT_LIST_HEAD(&res->node);
+	res->tid = tid;
+
+	list_add_tail(&res->node, &sid->evsel->per_stream_periods);
+	hlist_add_head(&res->hnode, &sid->periods[hash]);
+
+	return &res->period;
 }
 
 void perf_counts_values__scale(struct perf_counts_values *count,
diff --git a/tools/lib/perf/include/internal/evsel.h b/tools/lib/perf/include/internal/evsel.h
index 5cd220a61962..ea78defa77d0 100644
--- a/tools/lib/perf/include/internal/evsel.h
+++ b/tools/lib/perf/include/internal/evsel.h
@@ -11,6 +11,32 @@
 struct perf_thread_map;
 struct xyarray;
 
+/**
+ * The per-thread accumulated period storage node.
+ */
+struct perf_sample_id_period {
+	struct list_head	node;
+	struct hlist_node	hnode;
+	/* Holds total ID period value for PERF_SAMPLE_READ processing. */
+	u64			period;
+	/* The TID that the values belongs to */
+	u32			tid;
+};
+
+/**
+ * perf_evsel_for_each_per_thread_period_safe - safely iterate thru all the
+ * per_stream_periods
+ * @evlist:perf_evsel instance to iterate
+ * @item: struct perf_sample_id_period iterator
+ * @tmp: struct perf_sample_id_period temp iterator
+ */
+#define perf_evsel_for_each_per_thread_period_safe(evsel, tmp, item) \
+	list_for_each_entry_safe(item, tmp, &(evsel)->per_stream_periods, node)
+
+
+#define PERF_SAMPLE_ID__HLIST_BITS 4
+#define PERF_SAMPLE_ID__HLIST_SIZE (1 << PERF_SAMPLE_ID__HLIST_BITS)
+
 /*
  * Per fd, to map back from PERF_SAMPLE_ID to evsel, only used when there are
  * more than one entry in the evlist.
@@ -34,8 +60,32 @@ struct perf_sample_id {
 	pid_t			 machine_pid;
 	struct perf_cpu		 vcpu;
 
-	/* Holds total ID period value for PERF_SAMPLE_READ processing. */
-	u64			 period;
+	/*
+	 * Per-thread, and global event counts are mutually exclusive:
+	 * Whilst it is possible to combine events into a group with differing
+	 * values of PERF_SAMPLE_READ, it is not valid to have inconsistent
+	 * values for `inherit`. Therefore it is not possible to have a
+	 * situation where a per-thread event is sampled as a global event;
+	 * all !inherit groups are global, and all groups where the sampling
+	 * event is inherit + PERF_SAMPLE_READ will be per-thread. Any event
+	 * that is part of such a group that is inherit but not PERF_SAMPLE_READ
+	 * will be read as per-thread. If such an event can also trigger a
+	 * sample (such as with sample_period > 0) then it will not cause
+	 * `read_format` to be included in its PERF_RECORD_SAMPLE, and
+	 * therefore will not expose the per-thread group members as global.
+	 */
+	union {
+		/*
+		 * Holds total ID period value for PERF_SAMPLE_READ processing
+		 * (when period is not per-thread).
+		 */
+		u64			period;
+		/*
+		 * Holds total ID period value for PERF_SAMPLE_READ processing
+		 * (when period is per-thread).
+		 */
+		struct hlist_head	periods[PERF_SAMPLE_ID__HLIST_SIZE];
+	};
 };
 
 struct perf_evsel {
@@ -58,6 +108,10 @@ struct perf_evsel {
 	u32			 ids;
 	struct perf_evsel	*leader;
 
+	/* For events where the read_format value is per-thread rather than
+	 * global, stores the per-thread cumulative period */
+	struct list_head	per_stream_periods;
+
 	/* parse modifier helper */
 	int			 nr_members;
 	/*
@@ -88,4 +142,9 @@ int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter);
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
 void perf_evsel__free_id(struct perf_evsel *evsel);
 
+bool perf_evsel__attr_has_per_thread_sample_period(struct perf_evsel *evsel);
+
+u64 *perf_sample_id__get_period_storage(struct perf_sample_id *sid, u32 tid,
+					bool per_thread);
+
 #endif /* __LIBPERF_INTERNAL_EVSEL_H */
diff --git a/tools/lib/subcmd/run-command.c b/tools/lib/subcmd/run-command.c
index 4e3a557a2f37..0a764c25c384 100644
--- a/tools/lib/subcmd/run-command.c
+++ b/tools/lib/subcmd/run-command.c
@@ -2,6 +2,7 @@
 #include <unistd.h>
 #include <sys/types.h>
 #include <sys/stat.h>
+#include <ctype.h>
 #include <fcntl.h>
 #include <string.h>
 #include <linux/string.h>
@@ -217,8 +218,40 @@ static int wait_or_whine(struct child_process *cmd, bool block)
 
 int check_if_command_finished(struct child_process *cmd)
 {
+#ifdef __linux__
+	char filename[FILENAME_MAX + 12];
+	char status_line[256];
+	FILE *status_file;
+
+	/*
+	 * Check by reading /proc/<pid>/status as calling waitpid causes
+	 * stdout/stderr to be closed and data lost.
+	 */
+	sprintf(filename, "/proc/%d/status", cmd->pid);
+	status_file = fopen(filename, "r");
+	if (status_file == NULL) {
+		/* Open failed assume finish_command was called. */
+		return true;
+	}
+	while (fgets(status_line, sizeof(status_line), status_file) != NULL) {
+		char *p;
+
+		if (strncmp(status_line, "State:", 6))
+			continue;
+
+		fclose(status_file);
+		p = status_line + 6;
+		while (isspace(*p))
+			p++;
+		return *p == 'Z' ? 1 : 0;
+	}
+	/* Read failed assume finish_command was called. */
+	fclose(status_file);
+	return 1;
+#else
 	wait_or_whine(cmd, /*block=*/false);
 	return cmd->finished;
+#endif
 }
 
 int finish_command(struct child_process *cmd)
diff --git a/tools/lib/subcmd/subcmd-util.h b/tools/lib/subcmd/subcmd-util.h
index dfac76e35ac7..c742b08815dc 100644
--- a/tools/lib/subcmd/subcmd-util.h
+++ b/tools/lib/subcmd/subcmd-util.h
@@ -20,8 +20,8 @@ static __noreturn inline void die(const char *err, ...)
 
 	va_start(params, err);
 	report(" Fatal: ", err, params);
-	exit(128);
 	va_end(params);
+	exit(128);
 }
 
 #define zfree(ptr) ({ free(*ptr); *ptr = NULL; })