block: add scalable completion tracking of requests

For legacy block, we simply track them in the request queue. For
blk-mq, we track them on a per-sw queue basis, which we can then
sum up through the hardware queues and finally to a per device
state.

The stats are tracked in, roughly, 0.1s interval windows.

Add sysfs files to display the stats.

The feature is off by default, to avoid any extra overhead. In-kernel
users of it can turn it on by setting QUEUE_FLAG_STATS in the queue
flags. We currently don't turn it on if someone just reads any of
the stats files, that is something we could add as well.

Signed-off-by: Jens Axboe <axboe@fb.com>
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 488c2e2..9cdb724 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -401,6 +401,26 @@
 	return queue_var_show(blk_queue_dax(q), page);
 }
 
+static ssize_t print_stat(char *page, struct blk_rq_stat *stat, const char *pre)
+{
+	return sprintf(page, "%s samples=%llu, mean=%lld, min=%lld, max=%lld\n",
+			pre, (long long) stat->nr_samples,
+			(long long) stat->mean, (long long) stat->min,
+			(long long) stat->max);
+}
+
+static ssize_t queue_stats_show(struct request_queue *q, char *page)
+{
+	struct blk_rq_stat stat[2];
+	ssize_t ret;
+
+	blk_queue_stat_get(q, stat);
+
+	ret = print_stat(page, &stat[BLK_STAT_READ], "read :");
+	ret += print_stat(page + ret, &stat[BLK_STAT_WRITE], "write:");
+	return ret;
+}
+
 static struct queue_sysfs_entry queue_requests_entry = {
 	.attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_requests_show,
@@ -553,6 +573,11 @@
 	.show = queue_dax_show,
 };
 
+static struct queue_sysfs_entry queue_stats_entry = {
+	.attr = {.name = "stats", .mode = S_IRUGO },
+	.show = queue_stats_show,
+};
+
 static struct attribute *default_attrs[] = {
 	&queue_requests_entry.attr,
 	&queue_ra_entry.attr,
@@ -582,6 +607,7 @@
 	&queue_poll_entry.attr,
 	&queue_wc_entry.attr,
 	&queue_dax_entry.attr,
+	&queue_stats_entry.attr,
 	NULL,
 };