It is more efficient to use bio_for_each_segment_mp() for mapping sg, meantime we have to consider splitting multipage bvec as done in blk_bio_segment_split(). Signed-off-by: Ming Lei <tom.leiming@xxxxxxxxx> --- block/blk-merge.c | 72 +++++++++++++++++++++++++++++++++++++++---------------- 1 file changed, 52 insertions(+), 20 deletions(-) diff --git a/block/blk-merge.c b/block/blk-merge.c index a0e97959db7b..55c5866ea77a 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -450,6 +450,56 @@ static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio, return 0; } +static inline struct scatterlist *blk_next_sg(struct scatterlist **sg, + struct scatterlist *sglist) +{ + if (!*sg) + return sglist; + else { + /* + * If the driver previously mapped a shorter + * list, we could see a termination bit + * prematurely unless it fully inits the sg + * table on each mapping. We KNOW that there + * must be more entries here or the driver + * would be buggy, so force clear the + * termination bit to avoid doing a full + * sg_init_table() in drivers for each command. + */ + sg_unmark_end(*sg); + return sg_next(*sg); + } +} + +static inline unsigned +blk_bvec_map_sg(struct request_queue *q, struct bio_vec *bvec, + struct scatterlist *sglist, struct scatterlist **sg) +{ + unsigned nbytes = bvec->bv_len; + unsigned nsegs = 0, total = 0; + + while (nbytes > 0) { + unsigned seg_size; + struct page *pg; + unsigned offset, idx; + + *sg = blk_next_sg(sg, sglist); + + seg_size = min(nbytes, queue_max_segment_size(q)); + offset = (total + bvec->bv_offset) % PAGE_SIZE; + idx = (total + bvec->bv_offset) / PAGE_SIZE; + pg = nth_page(bvec->bv_page, idx); + + sg_set_page(*sg, pg, seg_size, offset); + + total += seg_size; + nbytes -= seg_size; + nsegs++; + } + + return nsegs; +} + static inline void __blk_segment_map_sg(struct request_queue *q, struct bio_vec *bvec, struct scatterlist *sglist, struct bio_vec *bvprv, @@ -483,25 +533,7 @@ __blk_segment_map_sg(struct request_queue *q, struct bio_vec *bvec, (*sg)->length += nbytes; } else { new_segment: - if (!*sg) - *sg = sglist; - else { - /* - * If the driver previously mapped a shorter - * list, we could see a termination bit - * prematurely unless it fully inits the sg - * table on each mapping. We KNOW that there - * must be more entries here or the driver - * would be buggy, so force clear the - * termination bit to avoid doing a full - * sg_init_table() in drivers for each command. - */ - sg_unmark_end(*sg); - *sg = sg_next(*sg); - } - - sg_set_page(*sg, bvec->bv_page, nbytes, bvec->bv_offset); - (*nsegs)++; + (*nsegs) += blk_bvec_map_sg(q, bvec, sglist, sg); /* for making iterator happy */ bvec->bv_offset -= advance; @@ -527,7 +559,7 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio, int cluster = blk_queue_cluster(q), nsegs = 0; for_each_bio(bio) - bio_for_each_segment(bvec, bio, iter) + bio_for_each_segment_mp(bvec, bio, iter) __blk_segment_map_sg(q, &bvec, sglist, &bvprv, sg, &nsegs, &cluster); -- 2.7.4 -- To unsubscribe from this list: send the line "unsubscribe linux-block" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html