diff options
Diffstat (limited to 'block')
| -rw-r--r-- | block/bio-integrity-fs.c | 6 | ||||
| -rw-r--r-- | block/bio-integrity.c | 19 | ||||
| -rw-r--r-- | block/bio.c | 27 | ||||
| -rw-r--r-- | block/blk-cgroup.c | 2 | ||||
| -rw-r--r-- | block/blk-mq.c | 53 | ||||
| -rw-r--r-- | block/blk-zoned.c | 39 | ||||
| -rw-r--r-- | block/ioctl.c | 24 |
7 files changed, 112 insertions, 58 deletions
diff --git a/block/bio-integrity-fs.c b/block/bio-integrity-fs.c index acb1e5f270d2..0daa42d9ead7 100644 --- a/block/bio-integrity-fs.c +++ b/block/bio-integrity-fs.c @@ -55,6 +55,10 @@ int fs_bio_integrity_verify(struct bio *bio, sector_t sector, unsigned int size) { struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk); struct bio_integrity_payload *bip = bio_integrity(bio); + struct bvec_iter data_iter = { + .bi_sector = sector, + .bi_size = size, + }; /* * Reinitialize bip->bip_iter. @@ -65,7 +69,7 @@ int fs_bio_integrity_verify(struct bio *bio, sector_t sector, unsigned int size) memset(&bip->bip_iter, 0, sizeof(bip->bip_iter)); bip->bip_iter.bi_sector = sector; bip->bip_iter.bi_size = bio_integrity_bytes(bi, size >> SECTOR_SHIFT); - return blk_status_to_errno(bio_integrity_verify(bio, &bip->bip_iter)); + return blk_status_to_errno(bio_integrity_verify(bio, &data_iter)); } static int __init fs_bio_integrity_init(void) diff --git a/block/bio-integrity.c b/block/bio-integrity.c index e54c6e06e1cb..e796de1a749e 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -308,7 +308,6 @@ static int bio_integrity_copy_user(struct bio *bio, struct bio_vec *bvec, } bip->bip_flags |= BIP_COPY_USER; - bip->bip_vcnt = nr_vecs; return 0; free_bip: bio_integrity_free(bio); @@ -403,6 +402,24 @@ int bio_integrity_map_user(struct bio *bio, struct iov_iter *iter) if (unlikely(ret < 0)) goto free_bvec; + /* + * Handle partial pinning. This can happen when pin_user_pages_fast() + * returns fewer pages than requested. + */ + if (user_backed_iter(iter) && unlikely(ret != bytes)) { + if (ret > 0) { + int npinned = DIV_ROUND_UP(offset + ret, PAGE_SIZE); + int i; + + for (i = 0; i < npinned; i++) + unpin_user_page(pages[i]); + } + if (pages != stack_pages) + kvfree(pages); + ret = -EFAULT; + goto free_bvec; + } + nr_bvecs = bvec_from_pages(bvec, pages, nr_vecs, bytes, offset, &is_p2p); if (pages != stack_pages) diff --git a/block/bio.c b/block/bio.c index b8972dba68a0..5f10900b3f42 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1279,11 +1279,12 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter, return bio_iov_iter_align_down(bio, iter, len_align_mask); } -static struct folio *folio_alloc_greedy(gfp_t gfp, size_t *size) +static struct folio *folio_alloc_greedy(gfp_t gfp, size_t *size, + size_t minsize) { struct folio *folio; - while (*size > PAGE_SIZE) { + while (*size > minsize) { folio = folio_alloc(gfp | __GFP_NORETRY, get_order(*size)); if (folio) return folio; @@ -1307,7 +1308,7 @@ static void bio_free_folios(struct bio *bio) } static int bio_iov_iter_bounce_write(struct bio *bio, struct iov_iter *iter, - size_t maxlen) + size_t maxlen, size_t minsize) { size_t total_len = min(maxlen, iov_iter_count(iter)); @@ -1322,13 +1323,13 @@ static int bio_iov_iter_bounce_write(struct bio *bio, struct iov_iter *iter, size_t this_len = min(total_len, SZ_1M); struct folio *folio; - if (this_len > PAGE_SIZE * 2) + if (this_len > minsize * 2) this_len = rounddown_pow_of_two(this_len); if (bio->bi_iter.bi_size > BIO_MAX_SIZE - this_len) break; - folio = folio_alloc_greedy(GFP_KERNEL, &this_len); + folio = folio_alloc_greedy(GFP_KERNEL, &this_len, minsize); if (!folio) break; bio_add_folio_nofail(bio, folio, this_len, 0); @@ -1344,16 +1345,16 @@ static int bio_iov_iter_bounce_write(struct bio *bio, struct iov_iter *iter, if (!bio->bi_iter.bi_size) return -ENOMEM; - return 0; + return bio_iov_iter_align_down(bio, iter, minsize - 1); } static int bio_iov_iter_bounce_read(struct bio *bio, struct iov_iter *iter, - size_t maxlen) + size_t maxlen, size_t minsize) { size_t len = min3(iov_iter_count(iter), maxlen, SZ_1M); struct folio *folio; - folio = folio_alloc_greedy(GFP_KERNEL, &len); + folio = folio_alloc_greedy(GFP_KERNEL, &len, minsize); if (!folio) return -ENOMEM; @@ -1382,7 +1383,7 @@ static int bio_iov_iter_bounce_read(struct bio *bio, struct iov_iter *iter, bvec_set_folio(&bio->bi_io_vec[0], folio, bio->bi_iter.bi_size, 0); if (iov_iter_extract_will_pin(iter)) bio_set_flag(bio, BIO_PAGE_PINNED); - return 0; + return bio_iov_iter_align_down(bio, iter, minsize - 1); } /** @@ -1390,6 +1391,7 @@ static int bio_iov_iter_bounce_read(struct bio *bio, struct iov_iter *iter, * @bio: bio to send * @iter: iter to read from / write into * @maxlen: maximum size to bounce + * @minsize: minimum folio allocation size * * Helper for direct I/O implementations that need to bounce buffer because * we need to checksum the data or perform other operations that require @@ -1397,11 +1399,12 @@ static int bio_iov_iter_bounce_read(struct bio *bio, struct iov_iter *iter, * copies the data into it. Needs to be paired with bio_iov_iter_unbounce() * called on completion. */ -int bio_iov_iter_bounce(struct bio *bio, struct iov_iter *iter, size_t maxlen) +int bio_iov_iter_bounce(struct bio *bio, struct iov_iter *iter, size_t maxlen, + size_t minsize) { if (op_is_write(bio_op(bio))) - return bio_iov_iter_bounce_write(bio, iter, maxlen); - return bio_iov_iter_bounce_read(bio, iter, maxlen); + return bio_iov_iter_bounce_write(bio, iter, maxlen, minsize); + return bio_iov_iter_bounce_read(bio, iter, maxlen, minsize); } static void bvec_unpin(struct bio_vec *bv, bool mark_dirty) diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 554c87bb4a86..bc63bd220865 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -2241,7 +2241,7 @@ void blk_cgroup_bio_start(struct bio *bio) } u64_stats_update_end_irqrestore(&bis->sync, flags); - css_rstat_updated(&blkcg->css, cpu); + __css_rstat_updated(&blkcg->css, cpu); put_cpu(); } diff --git a/block/blk-mq.c b/block/blk-mq.c index 4c5c16cce4f8..28c2d931e75e 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -3077,7 +3077,7 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q, /* * Check if there is a suitable cached request and return it. */ -static struct request *blk_mq_peek_cached_request(struct blk_plug *plug, +static struct request *blk_mq_get_cached_request(struct blk_plug *plug, struct request_queue *q, blk_opf_t opf) { enum hctx_type type = blk_mq_get_hctx_type(opf); @@ -3093,27 +3093,10 @@ static struct request *blk_mq_peek_cached_request(struct blk_plug *plug, return NULL; if (op_is_flush(rq->cmd_flags) != op_is_flush(opf)) return NULL; + rq_list_pop(&plug->cached_rqs); return rq; } -static void blk_mq_use_cached_rq(struct request *rq, struct blk_plug *plug, - struct bio *bio) -{ - if (rq_list_pop(&plug->cached_rqs) != rq) - WARN_ON_ONCE(1); - - /* - * If any qos ->throttle() end up blocking, we will have flushed the - * plug and hence killed the cached_rq list as well. Pop this entry - * before we throttle. - */ - rq_qos_throttle(rq->q, bio); - - blk_mq_rq_time_init(rq, blk_time_get_ns()); - rq->cmd_flags = bio->bi_opf; - INIT_LIST_HEAD(&rq->queuelist); -} - static bool bio_unaligned(const struct bio *bio, struct request_queue *q) { unsigned int bs_mask = queue_logical_block_size(q) - 1; @@ -3152,7 +3135,7 @@ void blk_mq_submit_bio(struct bio *bio) /* * If the plug has a cached request for this queue, try to use it. */ - rq = blk_mq_peek_cached_request(plug, q, bio->bi_opf); + rq = blk_mq_get_cached_request(plug, q, bio->bi_opf); /* * A BIO that was released from a zone write plug has already been @@ -3211,7 +3194,10 @@ void blk_mq_submit_bio(struct bio *bio) new_request: if (rq) { - blk_mq_use_cached_rq(rq, plug, bio); + rq_qos_throttle(rq->q, bio); + blk_mq_rq_time_init(rq, blk_time_get_ns()); + rq->cmd_flags = bio->bi_opf; + INIT_LIST_HEAD(&rq->queuelist); } else { rq = blk_mq_get_new_requests(q, plug, bio); if (unlikely(!rq)) { @@ -3257,12 +3243,10 @@ new_request: return; queue_exit: - /* - * Don't drop the queue reference if we were trying to use a cached - * request and thus didn't acquire one. - */ if (!rq) blk_queue_exit(q); + else + blk_mq_free_request(rq); } #ifdef CONFIG_BLK_MQ_STACKING @@ -3307,6 +3291,25 @@ blk_status_t blk_insert_cloned_request(struct request *rq) return BLK_STS_IOERR; } + /* + * Integrity segment counting depends on the same queue limits + * (virt_boundary_mask, seg_boundary_mask, max_segment_size) that + * vary across stacked queues, so recompute against the bottom + * queue just like nr_phys_segments above. + */ + if (blk_integrity_rq(rq) && rq->bio) { + unsigned short max_int_segs = queue_max_integrity_segments(q); + + rq->nr_integrity_segments = + blk_rq_count_integrity_sg(rq->q, rq->bio); + if (rq->nr_integrity_segments > max_int_segs) { + printk(KERN_ERR "%s: over max integrity segments limit. (%u > %u)\n", + __func__, rq->nr_integrity_segments, + max_int_segs); + return BLK_STS_IOERR; + } + } + if (q->disk && should_fail_request(q->disk->part0, blk_rq_bytes(rq))) return BLK_STS_IOERR; diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 30cad2bb9291..6a221c180889 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -623,6 +623,28 @@ static void disk_mark_zone_wplug_dead(struct blk_zone_wplug *zwplug) } } +static inline bool disk_check_zone_wplug_dead(struct blk_zone_wplug *zwplug) +{ + if (!(zwplug->flags & BLK_ZONE_WPLUG_DEAD)) + return false; + + /* + * If a new write is received right after a zone reset completes and + * while the disk_zone_wplugs_worker() thread has not yet released the + * reference on the zone write plug after processing the last write to + * the zone, then the new write BIO will see the zone write plug marked + * as dead. This case is however a false positive and a perfectly valid + * pattern. In such case, restore the zone write plug to a live one. + */ + if (!zwplug->wp_offset && bio_list_empty(&zwplug->bio_list)) { + zwplug->flags &= ~BLK_ZONE_WPLUG_DEAD; + refcount_inc(&zwplug->ref); + return false; + } + + return true; +} + static bool disk_zone_wplug_submit_bio(struct gendisk *disk, struct blk_zone_wplug *zwplug); @@ -1444,12 +1466,12 @@ static bool blk_zone_wplug_handle_write(struct bio *bio, unsigned int nr_segs) spin_lock_irqsave(&zwplug->lock, flags); /* - * If we got a zone write plug marked as dead, then the user is issuing - * writes to a full zone, or without synchronizing with zone reset or - * zone finish operations. In such case, fail the BIO to signal this - * invalid usage. + * Check if we got a zone write plug marked as dead. If yes, then the + * user is likely issuing writes to a full zone, or without + * synchronizing with zone reset or zone finish operations. In such + * case, fail the BIO to signal this invalid usage. */ - if (zwplug->flags & BLK_ZONE_WPLUG_DEAD) { + if (disk_check_zone_wplug_dead(zwplug)) { spin_unlock_irqrestore(&zwplug->lock, flags); disk_put_zone_wplug(zwplug); bio_io_error(bio); @@ -1979,8 +2001,10 @@ static void disk_set_zones_cond_array(struct gendisk *disk, u8 *zones_cond) void disk_free_zone_resources(struct gendisk *disk) { - if (disk->zone_wplugs_worker) + if (disk->zone_wplugs_worker) { kthread_stop(disk->zone_wplugs_worker); + disk->zone_wplugs_worker = NULL; + } WARN_ON_ONCE(!list_empty(&disk->zone_wplugs_list)); if (disk->zone_wplugs_wq) { @@ -2113,9 +2137,6 @@ commit: ret = queue_limits_commit_update(q, &lim); unfreeze: - if (ret) - disk_free_zone_resources(disk); - blk_mq_unfreeze_queue(q, memflags); return ret; diff --git a/block/ioctl.c b/block/ioctl.c index fc3be0549aa7..ab2c9ed79946 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -857,6 +857,8 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) #endif struct blk_iou_cmd { + u64 start; + u64 len; int res; bool nowait; }; @@ -946,23 +948,27 @@ int blkdev_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) { struct block_device *bdev = I_BDEV(cmd->file->f_mapping->host); struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_cmd); - const struct io_uring_sqe *sqe = cmd->sqe; u32 cmd_op = cmd->cmd_op; - uint64_t start, len; - if (unlikely(sqe->ioprio || sqe->__pad1 || sqe->len || - sqe->rw_flags || sqe->file_index)) - return -EINVAL; + /* Read what we need from the SQE on the first issue */ + if (!(issue_flags & IORING_URING_CMD_REISSUE)) { + const struct io_uring_sqe *sqe = cmd->sqe; + + if (unlikely(sqe->ioprio || sqe->__pad1 || sqe->len || + sqe->rw_flags || sqe->file_index)) + return -EINVAL; + + bic->start = READ_ONCE(sqe->addr); + bic->len = READ_ONCE(sqe->addr3); + } bic->res = 0; bic->nowait = issue_flags & IO_URING_F_NONBLOCK; - start = READ_ONCE(sqe->addr); - len = READ_ONCE(sqe->addr3); - switch (cmd_op) { case BLOCK_URING_CMD_DISCARD: - return blkdev_cmd_discard(cmd, bdev, start, len, bic->nowait); + return blkdev_cmd_discard(cmd, bdev, bic->start, bic->len, + bic->nowait); } return -EINVAL; } |