diff options
author | Christoph Hellwig <hch@lst.de> | 2016-12-08 15:20:32 -0700 |
---|---|---|
committer | Jens Axboe <axboe@fb.com> | 2016-12-09 08:30:51 -0700 |
commit | f9d03f96b988002027d4b28ea1b7a24729a4c9b5 (patch) | |
tree | e4995a30bbe58290594e2ef29de5ae2785c6c9db /block/blk-merge.c | |
parent | be07e14f96e3121483339a64d917fddb3b86ba98 (diff) | |
download | linux-f9d03f96b988002027d4b28ea1b7a24729a4c9b5.tar.gz linux-f9d03f96b988002027d4b28ea1b7a24729a4c9b5.tar.bz2 linux-f9d03f96b988002027d4b28ea1b7a24729a4c9b5.zip |
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>
Diffstat (limited to 'block/blk-merge.c')
-rw-r--r-- | block/blk-merge.c | 53 |
1 files changed, 17 insertions, 36 deletions
diff --git a/block/blk-merge.c b/block/blk-merge.c index 1002afdfee99..182398cb1524 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -241,18 +241,13 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q, if (!bio) return 0; - /* - * This should probably be returning 0, but blk_add_request_payload() - * (Christoph!!!!) - */ 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; } fbio = bio; @@ -410,39 +405,21 @@ new_segment: *bvprv = *bvec; } +static inline int __blk_bvec_map_sg(struct request_queue *q, struct bio_vec bv, + struct scatterlist *sglist, struct scatterlist **sg) +{ + *sg = sglist; + sg_set_page(*sg, bv.bv_page, bv.bv_len, bv.bv_offset); + return 1; +} + static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio, struct scatterlist *sglist, struct scatterlist **sg) { struct bio_vec bvec, bvprv = { NULL }; struct bvec_iter iter; - int nsegs, cluster; - - nsegs = 0; - cluster = blk_queue_cluster(q); - - switch (bio_op(bio)) { - case REQ_OP_DISCARD: - case REQ_OP_SECURE_ERASE: - case REQ_OP_WRITE_ZEROES: - /* - * This is a hack - drivers should be neither modifying the - * biovec, nor relying on bi_vcnt - but because of - * blk_add_request_payload(), a discard bio may or may not have - * a payload we need to set up here (thank you Christoph) and - * bi_vcnt is really the only way of telling if we need to. - */ - if (!bio->bi_vcnt) - return 0; - /* Fall through */ - case REQ_OP_WRITE_SAME: - *sg = sglist; - bvec = bio_iovec(bio); - sg_set_page(*sg, bvec.bv_page, bvec.bv_len, bvec.bv_offset); - return 1; - default: - break; - } + int cluster = blk_queue_cluster(q), nsegs = 0; for_each_bio(bio) bio_for_each_segment(bvec, bio, iter) @@ -462,7 +439,11 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq, struct scatterlist *sg = NULL; int nsegs = 0; - if (rq->bio) + if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) + nsegs = __blk_bvec_map_sg(q, rq->special_vec, sglist, &sg); + else if (rq->bio && bio_op(rq->bio) == REQ_OP_WRITE_SAME) + nsegs = __blk_bvec_map_sg(q, bio_iovec(rq->bio), sglist, &sg); + else if (rq->bio) nsegs = __blk_bios_map_sg(q, rq->bio, sglist, &sg); if (unlikely(rq->rq_flags & RQF_COPY_USER) && @@ -495,7 +476,7 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq, * Something must have been wrong if the figured number of * segment is bigger than number of req's physical segments */ - WARN_ON(nsegs > rq->nr_phys_segments); + WARN_ON(nsegs > blk_rq_nr_phys_segments(rq)); return nsegs; } |