Merge branch 'sg_nents' into rdma.git for-next

From Maor Gottlieb
====================

Fix the use of nents and orig_nents in the sg table append helpers. The
nents should be used by the DMA layer to store the number of DMA mapped
sges, the orig_nents is the number of CPU sges.

Since the sg append logic doesn't always create a SGL with exactly
orig_nents entries store a total_nents as well to allow the table to be
properly free'd and reorganize the freeing logic to share across all the
use cases.

====================

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

* 'sg_nents':
  RDMA: Use the sg_table directly and remove the opencoded version from umem
  lib/scatterlist: Fix wrong update of orig_nents
  lib/scatterlist: Provide a dedicated function to support table append

1 files changed, 30 insertions, 5 deletions

diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 954ce2f594e9..1ff10d4bccf3 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -670,7 +670,7 @@ static void create_tasks(struct perf_sched *sched)
 	err = pthread_attr_init(&attr);
 	BUG_ON(err);
 	err = pthread_attr_setstacksize(&attr,
-			(size_t) max(16 * 1024, PTHREAD_STACK_MIN));
+			(size_t) max(16 * 1024, (int)PTHREAD_STACK_MIN));
 	BUG_ON(err);
 	err = pthread_mutex_lock(&sched->start_work_mutex);
 	BUG_ON(err);
@@ -3335,6 +3335,16 @@ static void setup_sorting(struct perf_sched *sched, const struct option *options
 	sort_dimension__add("pid", &sched->cmp_pid);
 }
 
+static bool schedstat_events_exposed(void)
+{
+	/*
+	 * Select "sched:sched_stat_wait" event to check
+	 * whether schedstat tracepoints are exposed.
+	 */
+	return IS_ERR(trace_event__tp_format("sched", "sched_stat_wait")) ?
+		false : true;
+}
+
 static int __cmd_record(int argc, const char **argv)
 {
 	unsigned int rec_argc, i, j;
@@ -3346,21 +3356,33 @@ static int __cmd_record(int argc, const char **argv)
 		"-m", "1024",
 		"-c", "1",
 		"-e", "sched:sched_switch",
-		"-e", "sched:sched_stat_wait",
-		"-e", "sched:sched_stat_sleep",
-		"-e", "sched:sched_stat_iowait",
 		"-e", "sched:sched_stat_runtime",
 		"-e", "sched:sched_process_fork",
 		"-e", "sched:sched_wakeup_new",
 		"-e", "sched:sched_migrate_task",
 	};
+
+	/*
+	 * The tracepoints trace_sched_stat_{wait, sleep, iowait}
+	 * are not exposed to user if CONFIG_SCHEDSTATS is not set,
+	 * to prevent "perf sched record" execution failure, determine
+	 * whether to record schedstat events according to actual situation.
+	 */
+	const char * const schedstat_args[] = {
+		"-e", "sched:sched_stat_wait",
+		"-e", "sched:sched_stat_sleep",
+		"-e", "sched:sched_stat_iowait",
+	};
+	unsigned int schedstat_argc = schedstat_events_exposed() ?
+		ARRAY_SIZE(schedstat_args) : 0;
+
 	struct tep_event *waking_event;
 
 	/*
 	 * +2 for either "-e", "sched:sched_wakeup" or
 	 * "-e", "sched:sched_waking"
 	 */
-	rec_argc = ARRAY_SIZE(record_args) + 2 + argc - 1;
+	rec_argc = ARRAY_SIZE(record_args) + 2 + schedstat_argc + argc - 1;
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
 	if (rec_argv == NULL)
@@ -3376,6 +3398,9 @@ static int __cmd_record(int argc, const char **argv)
 	else
 		rec_argv[i++] = strdup("sched:sched_wakeup");
 
+	for (j = 0; j < schedstat_argc; j++)
+		rec_argv[i++] = strdup(schedstat_args[j]);
+
 	for (j = 1; j < (unsigned int)argc; j++, i++)
 		rec_argv[i] = argv[j];