blktrace: trace zone write plugging operations

Trace zone write plugging operations on block devices.

As tracing of zoned block commands needs the upper 32bit of the widened
64bit action, only add traces to blktrace if user-space has requested
version 2 of the blktrace protocol.

Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

2 files changed, 44 insertions, 0 deletions

diff --git a/include/uapi/linux/blktrace_api.h b/include/uapi/linux/blktrace_api.h
index 289872e51fc5..30f3d2589365 100644
--- a/include/uapi/linux/blktrace_api.h
+++ b/include/uapi/linux/blktrace_api.h
@@ -62,6 +62,8 @@ enum blktrace_act {
 	__BLK_TA_REMAP,			/* bio was remapped */
 	__BLK_TA_ABORT,			/* request aborted */
 	__BLK_TA_DRV_DATA,		/* driver-specific binary data */
+	__BLK_TA_ZONE_PLUG,		/* zone write plug was plugged */
+	__BLK_TA_ZONE_UNPLUG,		/* zone write plug was unplugged */
 	__BLK_TA_CGROUP = 1 << 8,	/* from a cgroup*/
 };
 
@@ -99,6 +101,9 @@ enum blktrace_notify {
 
 #define BLK_TA_ZONE_APPEND	(__BLK_TA_COMPLETE |\
 				 BLK_TC_ACT(BLK_TC_ZONE_APPEND))
+#define BLK_TA_ZONE_PLUG	(__BLK_TA_ZONE_PLUG | BLK_TC_ACT(BLK_TC_QUEUE))
+#define BLK_TA_ZONE_UNPLUG	(__BLK_TA_ZONE_UNPLUG |\
+				 BLK_TC_ACT(BLK_TC_QUEUE))
 
 #define BLK_TN_PROCESS		(__BLK_TN_PROCESS | BLK_TC_ACT(BLK_TC_NOTIFY))
 #define BLK_TN_TIMESTAMP	(__BLK_TN_TIMESTAMP | BLK_TC_ACT(BLK_TC_NOTIFY))
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index c83577096607..6bfe1b36a1d3 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -1084,6 +1084,37 @@ static void blk_add_trace_unplug(void *ignore, struct request_queue *q,
 	rcu_read_unlock();
 }
 
+static void blk_add_trace_zone_plug(void *ignore, struct request_queue *q,
+				    unsigned int zno, sector_t sector,
+				    unsigned int sectors)
+{
+	struct blk_trace *bt;
+
+	rcu_read_lock();
+	bt = rcu_dereference(q->blk_trace);
+	if (bt && bt->version >= 2)
+		__blk_add_trace(bt, sector, sectors << SECTOR_SHIFT, 0,
+				BLK_TA_ZONE_PLUG, 0, 0, NULL, 0);
+	rcu_read_unlock();
+
+	return;
+}
+
+static void blk_add_trace_zone_unplug(void *ignore, struct request_queue *q,
+				      unsigned int zno, sector_t sector,
+				      unsigned int sectors)
+{
+	struct blk_trace *bt;
+
+	rcu_read_lock();
+	bt = rcu_dereference(q->blk_trace);
+	if (bt && bt->version >= 2)
+		__blk_add_trace(bt, sector, sectors << SECTOR_SHIFT, 0,
+				BLK_TA_ZONE_UNPLUG, 0, 0, NULL, 0);
+	rcu_read_unlock();
+	return;
+}
+
 static void blk_add_trace_split(void *ignore, struct bio *bio, unsigned int pdu)
 {
 	struct request_queue *q = bio->bi_bdev->bd_disk->queue;
@@ -1227,6 +1258,12 @@ static void blk_register_tracepoints(void)
 	ret = register_trace_blk_zone_append_update_request_bio(
 		blk_add_trace_zone_update_request, NULL);
 	WARN_ON(ret);
+	ret = register_trace_disk_zone_wplug_add_bio(blk_add_trace_zone_plug,
+						     NULL);
+	WARN_ON(ret);
+	ret = register_trace_blk_zone_wplug_bio(blk_add_trace_zone_unplug,
+						NULL);
+	WARN_ON(ret);
 	ret = register_trace_block_plug(blk_add_trace_plug, NULL);
 	WARN_ON(ret);
 	ret = register_trace_block_unplug(blk_add_trace_unplug, NULL);
@@ -1246,6 +1283,8 @@ static void blk_unregister_tracepoints(void)
 	unregister_trace_block_split(blk_add_trace_split, NULL);
 	unregister_trace_block_unplug(blk_add_trace_unplug, NULL);
 	unregister_trace_block_plug(blk_add_trace_plug, NULL);
+	unregister_trace_blk_zone_wplug_bio(blk_add_trace_zone_unplug, NULL);
+	unregister_trace_disk_zone_wplug_add_bio(blk_add_trace_zone_plug, NULL);
 	unregister_trace_blk_zone_append_update_request_bio(
 		blk_add_trace_zone_update_request, NULL);
 	unregister_trace_block_getrq(blk_add_trace_getrq, NULL);