summaryrefslogtreecommitdiffstats
path: root/block
diff options
context:
space:
mode:
authorFUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>2008-04-11 12:56:52 +0200
committerJens Axboe <jens.axboe@oracle.com>2008-04-21 09:50:08 +0200
commitf18573abcc57844a7c3c12699d40eead8728cd8a (patch)
tree99d5dcfdfe29578bb23900e63f226022f5e87281 /block
parentafdc1a780ef84a54b613dae6f971407748aab61c (diff)
downloadlinux-f18573abcc57844a7c3c12699d40eead8728cd8a.tar.gz
linux-f18573abcc57844a7c3c12699d40eead8728cd8a.tar.bz2
linux-f18573abcc57844a7c3c12699d40eead8728cd8a.zip
block: move the padding adjustment to blk_rq_map_sg
blk_rq_map_user adjusts bi_size of the last bio. It breaks the rule that req->data_len (the true data length) is equal to sum(bio). It broke the scsi command completion code. commit e97a294ef6938512b655b1abf17656cf2b26f709 was introduced to fix the above issue. However, the partial completion code doesn't work with it. The commit is also a layer violation (scsi mid-layer should not know about the block layer's padding). This patch moves the padding adjustment to blk_rq_map_sg (suggested by James). The padding works like the drain buffer. This patch breaks the rule that req->data_len is equal to sum(sg), however, the drain buffer already broke it. So this patch just restores the rule that req->data_len is equal to sub(bio) without breaking anything new. Now when a low level driver needs padding, blk_rq_map_user and blk_rq_map_user_iov guarantee there's enough room for padding. blk_rq_map_sg can safely extend the last entry of a scatter list. blk_rq_map_sg must extend the last entry of a scatter list only for a request that got through bio_copy_user_iov. This patches introduces new REQ_COPY_USER flag. Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Tejun Heo <htejun@gmail.com> Cc: Mike Christie <michaelc@cs.wisc.edu> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Diffstat (limited to 'block')
-rw-r--r--block/blk-map.c24
-rw-r--r--block/blk-merge.c9
2 files changed, 14 insertions, 19 deletions
diff --git a/block/blk-map.c b/block/blk-map.c
index ab43533ba641..3c942bd6422a 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -141,25 +141,8 @@ int blk_rq_map_user(struct request_queue *q, struct request *rq,
ubuf += ret;
}
- /*
- * __blk_rq_map_user() copies the buffers if starting address
- * or length isn't aligned to dma_pad_mask. As the copied
- * buffer is always page aligned, we know that there's enough
- * room for padding. Extend the last bio and update
- * rq->data_len accordingly.
- *
- * On unmap, bio_uncopy_user() will use unmodified
- * bio_map_data pointed to by bio->bi_private.
- */
- if (len & q->dma_pad_mask) {
- unsigned int pad_len = (q->dma_pad_mask & ~len) + 1;
- struct bio *tail = rq->biotail;
-
- tail->bi_io_vec[tail->bi_vcnt - 1].bv_len += pad_len;
- tail->bi_size += pad_len;
-
- rq->extra_len += pad_len;
- }
+ if (!bio_flagged(bio, BIO_USER_MAPPED))
+ rq->cmd_flags |= REQ_COPY_USER;
rq->buffer = rq->data = NULL;
return 0;
@@ -224,6 +207,9 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
return -EINVAL;
}
+ if (!bio_flagged(bio, BIO_USER_MAPPED))
+ rq->cmd_flags |= REQ_COPY_USER;
+
bio_get(bio);
blk_rq_bio_prep(q, rq, bio);
rq->buffer = rq->data = NULL;
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 0f58616bcd7f..b5c5c4a9e3f0 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -220,6 +220,15 @@ new_segment:
bvprv = bvec;
} /* segments in rq */
+
+ if (unlikely(rq->cmd_flags & REQ_COPY_USER) &&
+ (rq->data_len & q->dma_pad_mask)) {
+ unsigned int pad_len = (q->dma_pad_mask & ~rq->data_len) + 1;
+
+ sg->length += pad_len;
+ rq->extra_len += pad_len;
+ }
+
if (q->dma_drain_size && q->dma_drain_needed(rq)) {
if (rq->cmd_flags & REQ_RW)
memset(q->dma_drain_buffer, 0, q->dma_drain_size);