Since generic_make_request() can now handle arbitrary size bios, all we have to do is make sure the bvec array doesn't overflow.
Signed-off-by: Kent Overstreet <k...@daterainc.com> --- drivers/scsi/osd/osd_initiator.c | 5 +- drivers/target/target_core_pscsi.c | 5 +- fs/bio.c | 158 +++++++------------------------------ fs/exofs/ore.c | 8 +- fs/exofs/ore_raid.c | 8 +- include/linux/bio.h | 2 - 6 files changed, 37 insertions(+), 149 deletions(-) diff --git a/drivers/scsi/osd/osd_initiator.c b/drivers/scsi/osd/osd_initiator.c index bac04c2..e52b30d 100644 --- a/drivers/scsi/osd/osd_initiator.c +++ b/drivers/scsi/osd/osd_initiator.c @@ -1043,7 +1043,6 @@ EXPORT_SYMBOL(osd_req_read_sg); static struct bio *_create_sg_bios(struct osd_request *or, void **buff, const struct osd_sg_entry *sglist, unsigned numentries) { - struct request_queue *q = osd_request_queue(or->osd_dev); struct bio *bio; unsigned i; @@ -1060,9 +1059,9 @@ static struct bio *_create_sg_bios(struct osd_request *or, unsigned added_len; BUG_ON(offset + len > PAGE_SIZE); - added_len = bio_add_pc_page(q, bio, page, len, offset); + added_len = bio_add_page(bio, page, len, offset); if (unlikely(len != added_len)) { - OSD_DEBUG("bio_add_pc_page len(%d) != added_len(%d)\n", + OSD_DEBUG("bio_add_page len(%d) != added_len(%d)\n", len, added_len); bio_put(bio); return ERR_PTR(-ENOMEM); diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index 551c96c..d65d512 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -922,12 +922,11 @@ pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, tbio = tbio->bi_next = bio; } - pr_debug("PSCSI: Calling bio_add_pc_page() i: %d" + pr_debug("PSCSI: Calling bio_add_page() i: %d" " bio: %p page: %p len: %d off: %d\n", i, bio, page, len, off); - rc = bio_add_pc_page(pdv->pdv_sd->request_queue, - bio, page, bytes, off); + rc = bio_add_page(bio, page, bytes, off); if (rc != bytes) goto fail; diff --git a/fs/bio.c b/fs/bio.c index 7d538a1..c60bfcb 100644 --- a/fs/bio.c +++ b/fs/bio.c @@ -665,12 +665,22 @@ int bio_get_nr_vecs(struct block_device *bdev) } EXPORT_SYMBOL(bio_get_nr_vecs); -static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page - *page, unsigned int len, unsigned int offset, - unsigned short max_sectors) +/** + * bio_add_page - attempt to add page to bio + * @bio: destination bio + * @page: page to add + * @len: vec entry length + * @offset: vec entry offset + * + * Attempt to add a page to the bio_vec maplist. This can fail for a + * number of reasons, such as the bio being full or target block device + * limitations. The target block device must allow bio's up to PAGE_SIZE, + * so it is always possible to add a single page to an empty bio. + */ +int bio_add_page(struct bio *bio, struct page *page, + unsigned int len, unsigned int offset) { - int retried_segments = 0; - struct bio_vec *bvec; + struct bio_vec *bv; /* * cloned bio must not modify vec list @@ -678,41 +688,17 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page if (unlikely(bio_flagged(bio, BIO_CLONED))) return 0; - if (((bio->bi_iter.bi_size + len) >> 9) > max_sectors) - return 0; - /* * For filesystems with a blocksize smaller than the pagesize * we will often be called with the same page as last time and * a consecutive offset. Optimize this special case. */ if (bio->bi_vcnt > 0) { - struct bio_vec *prev = &bio->bi_io_vec[bio->bi_vcnt - 1]; - - if (page == prev->bv_page && - offset == prev->bv_offset + prev->bv_len) { - unsigned int prev_bv_len = prev->bv_len; - prev->bv_len += len; - - if (q->merge_bvec_fn) { - struct bvec_merge_data bvm = { - /* prev_bvec is already charged in - bi_size, discharge it in order to - simulate merging updated prev_bvec - as new bvec. */ - .bi_bdev = bio->bi_bdev, - .bi_sector = bio->bi_iter.bi_sector, - .bi_size = bio->bi_iter.bi_size - - prev_bv_len, - .bi_rw = bio->bi_rw, - }; - - if (q->merge_bvec_fn(q, &bvm, prev) < prev->bv_len) { - prev->bv_len -= len; - return 0; - } - } + bv = &bio->bi_io_vec[bio->bi_vcnt - 1]; + if (page == bv->bv_page && + offset == bv->bv_offset + bv->bv_len) { + bv->bv_len += len; goto done; } } @@ -720,106 +706,16 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page if (bio->bi_vcnt >= bio->bi_max_vecs) return 0; - /* - * we might lose a segment or two here, but rather that than - * make this too complex. - */ - - while (bio->bi_phys_segments >= queue_max_segments(q)) { - - if (retried_segments) - return 0; - - retried_segments = 1; - blk_recount_segments(q, bio); - } - - /* - * setup the new entry, we might clear it again later if we - * cannot add the page - */ - bvec = &bio->bi_io_vec[bio->bi_vcnt]; - bvec->bv_page = page; - bvec->bv_len = len; - bvec->bv_offset = offset; - - /* - * if queue has other restrictions (eg varying max sector size - * depending on offset), it can specify a merge_bvec_fn in the - * queue to get further control - */ - if (q->merge_bvec_fn) { - struct bvec_merge_data bvm = { - .bi_bdev = bio->bi_bdev, - .bi_sector = bio->bi_iter.bi_sector, - .bi_size = bio->bi_iter.bi_size, - .bi_rw = bio->bi_rw, - }; - - /* - * merge_bvec_fn() returns number of bytes it can accept - * at this offset - */ - if (q->merge_bvec_fn(q, &bvm, bvec) < bvec->bv_len) { - bvec->bv_page = NULL; - bvec->bv_len = 0; - bvec->bv_offset = 0; - return 0; - } - } - - /* If we may be able to merge these biovecs, force a recount */ - if (bio->bi_vcnt && (BIOVEC_PHYS_MERGEABLE(bvec-1, bvec))) - bio->bi_flags &= ~(1 << BIO_SEG_VALID); + bv = &bio->bi_io_vec[bio->bi_vcnt]; + bv->bv_page = page; + bv->bv_len = len; + bv->bv_offset = offset; bio->bi_vcnt++; - bio->bi_phys_segments++; - done: +done: bio->bi_iter.bi_size += len; return len; } - -/** - * bio_add_pc_page - attempt to add page to bio - * @q: the target queue - * @bio: destination bio - * @page: page to add - * @len: vec entry length - * @offset: vec entry offset - * - * Attempt to add a page to the bio_vec maplist. This can fail for a - * number of reasons, such as the bio being full or target block device - * limitations. The target block device must allow bio's up to PAGE_SIZE, - * so it is always possible to add a single page to an empty bio. - * - * This should only be used by REQ_PC bios. - */ -int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page *page, - unsigned int len, unsigned int offset) -{ - return __bio_add_page(q, bio, page, len, offset, - queue_max_hw_sectors(q)); -} -EXPORT_SYMBOL(bio_add_pc_page); - -/** - * bio_add_page - attempt to add page to bio - * @bio: destination bio - * @page: page to add - * @len: vec entry length - * @offset: vec entry offset - * - * Attempt to add a page to the bio_vec maplist. This can fail for a - * number of reasons, such as the bio being full or target block device - * limitations. The target block device must allow bio's up to PAGE_SIZE, - * so it is always possible to add a single page to an empty bio. - */ -int bio_add_page(struct bio *bio, struct page *page, unsigned int len, - unsigned int offset) -{ - struct request_queue *q = bdev_get_queue(bio->bi_bdev); - return __bio_add_page(q, bio, page, len, offset, queue_max_sectors(q)); -} EXPORT_SYMBOL(bio_add_page); struct submit_bio_ret { @@ -1169,7 +1065,7 @@ struct bio *bio_copy_user_iov(struct request_queue *q, } } - if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes) + if (bio_add_page(bio, page, bytes, offset) < bytes) break; len -= bytes; @@ -1462,8 +1358,8 @@ static struct bio *__bio_map_kern(struct request_queue *q, void *data, if (bytes > len) bytes = len; - if (bio_add_pc_page(q, bio, virt_to_page(data), bytes, - offset) < bytes) + if (bio_add_page(bio, virt_to_page(data), bytes, + offset) < bytes) break; data += bytes; diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c index b744228..c694d6d 100644 --- a/fs/exofs/ore.c +++ b/fs/exofs/ore.c @@ -577,8 +577,6 @@ int _ore_add_stripe_unit(struct ore_io_state *ios, unsigned *cur_pg, struct ore_per_dev_state *per_dev, int cur_len) { unsigned pg = *cur_pg; - struct request_queue *q = - osd_request_queue(_ios_od(ios, per_dev->dev)); unsigned len = cur_len; int ret; @@ -606,10 +604,10 @@ int _ore_add_stripe_unit(struct ore_io_state *ios, unsigned *cur_pg, cur_len -= pglen; - added_len = bio_add_pc_page(q, per_dev->bio, pages[pg], - pglen, pgbase); + added_len = bio_add_page(per_dev->bio, pages[pg], + pglen, pgbase); if (unlikely(pglen != added_len)) { - ORE_DBGMSG("Failed bio_add_pc_page bi_vcnt=%u\n", + ORE_DBGMSG("Failed bio_add_page bi_vcnt=%u\n", per_dev->bio->bi_vcnt); ret = -ENOMEM; goto out; diff --git a/fs/exofs/ore_raid.c b/fs/exofs/ore_raid.c index 7682b97..bbd627f 100644 --- a/fs/exofs/ore_raid.c +++ b/fs/exofs/ore_raid.c @@ -331,7 +331,6 @@ static int _alloc_read_4_write(struct ore_io_state *ios) static int _add_to_r4w(struct ore_io_state *ios, struct ore_striping_info *si, struct page *page, unsigned pg_len) { - struct request_queue *q; struct ore_per_dev_state *per_dev; struct ore_io_state *read_ios; unsigned first_dev = si->dev - (si->dev % @@ -365,11 +364,10 @@ static int _add_to_r4w(struct ore_io_state *ios, struct ore_striping_info *si, _ore_add_sg_seg(per_dev, gap, true); } - q = osd_request_queue(ore_comp_dev(read_ios->oc, per_dev->dev)); - added_len = bio_add_pc_page(q, per_dev->bio, page, pg_len, - si->obj_offset % PAGE_SIZE); + added_len = bio_add_page(per_dev->bio, page, pg_len, + si->obj_offset % PAGE_SIZE); if (unlikely(added_len != pg_len)) { - ORE_DBGMSG("Failed to bio_add_pc_page bi_vcnt=%d\n", + ORE_DBGMSG("Failed to bio_add_page bi_vcnt=%d\n", per_dev->bio->bi_vcnt); return -ENOMEM; } diff --git a/include/linux/bio.h b/include/linux/bio.h index 204489e..a293b78 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -367,8 +367,6 @@ extern void bio_reset(struct bio *); void bio_chain(struct bio *, struct bio *); extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int); -extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *, - unsigned int, unsigned int); extern int bio_get_nr_vecs(struct block_device *); extern struct bio *bio_map_user(struct request_queue *, struct block_device *, unsigned long, unsigned int, int, gfp_t); -- 1.8.4.rc3 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/