block: improve handling of the magic discard payload

Instead of allocating a single unused biovec for discard requests, send
them down without any payload.  Instead we allow the driver to add a
"special" payload using a biovec embedded into struct request (unioned
over other fields never used while in the driver), and overloading
the number of segments for this case.

This has a couple of advantages:

 - we don't have to allocate the bio_vec
 - the amount of special casing for discard requests in the block
   layer is significantly reduced
 - using this same scheme for other request types is trivial,
   which will be important for implementing the new WRITE_ZEROES
   op on devices where it actually requires a payload (e.g. SCSI)
 - we can get rid of playing games with the request length, as
   we'll never touch it and completions will work just fine
 - it will allow us to support ranged discard operations in the
   future by merging non-contiguous discard bios into a single
   request
 - last but not least it removes a lot of code

This patch is the common base for my WIP series for ranges discards and to
remove discard_zeroes_data in favor of always using REQ_OP_WRITE_ZEROES,
so it would be good to get it in quickly.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

2 files changed, 14 insertions, 4 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index b15323934a29..7cf8a6c70a3f 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -197,8 +197,9 @@ static inline unsigned bio_segments(struct bio *bio)
 	switch (bio_op(bio)) {
 	case REQ_OP_DISCARD:
 	case REQ_OP_SECURE_ERASE:
-	case REQ_OP_WRITE_SAME:
 	case REQ_OP_WRITE_ZEROES:
+		return 0;
+	case REQ_OP_WRITE_SAME:
 		return 1;
 	default:
 		break;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index ebeef2b79c5a..c5393766909d 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -120,10 +120,13 @@ typedef __u32 __bitwise req_flags_t;
 #define RQF_HASHED		((__force req_flags_t)(1 << 16))
 /* IO stats tracking on */
 #define RQF_STATS		((__force req_flags_t)(1 << 17))
+/* Look at ->special_vec for the actual data payload instead of the
+   bio chain. */
+#define RQF_SPECIAL_PAYLOAD	((__force req_flags_t)(1 << 18))
 
 /* flags that prevent us from merging requests: */
 #define RQF_NOMERGE_FLAGS \
-	(RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ)
+	(RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD)
 
 #define BLK_MAX_CDB	16
 
@@ -175,6 +178,7 @@ struct request {
 	 */
 	union {
 		struct rb_node rb_node;	/* sort/lookup */
+		struct bio_vec special_vec;
 		void *completion_data;
 	};
 
@@ -909,8 +913,6 @@ extern void __blk_put_request(struct request_queue *, struct request *);
 extern struct request *blk_get_request(struct request_queue *, int, gfp_t);
 extern void blk_rq_set_block_pc(struct request *);
 extern void blk_requeue_request(struct request_queue *, struct request *);
-extern void blk_add_request_payload(struct request *rq, struct page *page,
-		int offset, unsigned int len);
 extern int blk_lld_busy(struct request_queue *q);
 extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
 			     struct bio_set *bs, gfp_t gfp_mask,
@@ -1153,6 +1155,13 @@ extern void blk_queue_flush_queueable(struct request_queue *q, bool queueable);
 extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua);
 extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev);
 
+static inline unsigned short blk_rq_nr_phys_segments(struct request *rq)
+{
+	if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
+		return 1;
+	return rq->nr_phys_segments;
+}
+
 extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *);
 extern void blk_dump_rq_flags(struct request *, char *);
 extern long nr_blockdev_pages(void);