diff options
Diffstat (limited to 'block')
| -rw-r--r-- | block/Kconfig | 6 | ||||
| -rw-r--r-- | block/Makefile | 3 | ||||
| -rw-r--r-- | block/bfq-iosched.c | 1 | ||||
| -rw-r--r-- | block/bfq-wf2q.c | 5 | ||||
| -rw-r--r-- | block/bio.c | 49 | ||||
| -rw-r--r-- | block/blk-merge.c | 23 | ||||
| -rw-r--r-- | block/blk-mq.c | 154 | ||||
| -rw-r--r-- | block/blk-settings.c | 2 | ||||
| -rw-r--r-- | block/blk-zoned.c | 2 | ||||
| -rw-r--r-- | block/partition-generic.c | 26 | ||||
| -rw-r--r-- | block/partitions/ldm.c | 2 | ||||
| -rw-r--r-- | block/t10-pi.c | 3 |
12 files changed, 205 insertions, 71 deletions
diff --git a/block/Kconfig b/block/Kconfig index c23094a14a2b..3bc76bb113a0 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -66,7 +66,6 @@ config BLK_DEV_BSGLIB config BLK_DEV_INTEGRITY bool "Block layer data integrity support" - select CRC_T10DIF if BLK_DEV_INTEGRITY ---help--- Some storage devices allow extra information to be stored/retrieved to help protect the data. The block layer @@ -77,6 +76,11 @@ config BLK_DEV_INTEGRITY T10/SCSI Data Integrity Field or the T13/ATA External Path Protection. If in doubt, say N. +config BLK_DEV_INTEGRITY_T10 + tristate + depends on BLK_DEV_INTEGRITY + select CRC_T10DIF + config BLK_DEV_ZONED bool "Zoned block device support" select MQ_IOSCHED_DEADLINE diff --git a/block/Makefile b/block/Makefile index 1f70c73ea83d..1a43750f4b01 100644 --- a/block/Makefile +++ b/block/Makefile @@ -26,7 +26,8 @@ bfq-y := bfq-iosched.o bfq-wf2q.o bfq-cgroup.o obj-$(CONFIG_IOSCHED_BFQ) += bfq.o obj-$(CONFIG_BLK_CMDLINE_PARSER) += cmdline-parser.o -obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o t10-pi.o +obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o +obj-$(CONFIG_BLK_DEV_INTEGRITY_T10) += t10-pi.o obj-$(CONFIG_BLK_MQ_PCI) += blk-mq-pci.o obj-$(CONFIG_BLK_MQ_VIRTIO) += blk-mq-virtio.o obj-$(CONFIG_BLK_MQ_RDMA) += blk-mq-rdma.o diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index ad4af4aaf2ce..4686b68b48b4 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -427,7 +427,6 @@ void bfq_schedule_dispatch(struct bfq_data *bfqd) } #define bfq_class_idle(bfqq) ((bfqq)->ioprio_class == IOPRIO_CLASS_IDLE) -#define bfq_class_rt(bfqq) ((bfqq)->ioprio_class == IOPRIO_CLASS_RT) #define bfq_sample_valid(samples) ((samples) > 80) diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c index 05f0bf4a1144..ffe9ce9faa89 100644 --- a/block/bfq-wf2q.c +++ b/block/bfq-wf2q.c @@ -277,10 +277,7 @@ struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity) */ static u64 bfq_delta(unsigned long service, unsigned long weight) { - u64 d = (u64)service << WFQ_SERVICE_SHIFT; - - do_div(d, weight); - return d; + return div64_ul((u64)service << WFQ_SERVICE_SHIFT, weight); } /** diff --git a/block/bio.c b/block/bio.c index a5d75f6bf4c7..94d697217887 100644 --- a/block/bio.c +++ b/block/bio.c @@ -539,6 +539,55 @@ void zero_fill_bio_iter(struct bio *bio, struct bvec_iter start) EXPORT_SYMBOL(zero_fill_bio_iter); /** + * bio_truncate - truncate the bio to small size of @new_size + * @bio: the bio to be truncated + * @new_size: new size for truncating the bio + * + * Description: + * Truncate the bio to new size of @new_size. If bio_op(bio) is + * REQ_OP_READ, zero the truncated part. This function should only + * be used for handling corner cases, such as bio eod. + */ +void bio_truncate(struct bio *bio, unsigned new_size) +{ + struct bio_vec bv; + struct bvec_iter iter; + unsigned int done = 0; + bool truncated = false; + + if (new_size >= bio->bi_iter.bi_size) + return; + + if (bio_op(bio) != REQ_OP_READ) + goto exit; + + bio_for_each_segment(bv, bio, iter) { + if (done + bv.bv_len > new_size) { + unsigned offset; + + if (!truncated) + offset = new_size - done; + else + offset = 0; + zero_user(bv.bv_page, offset, bv.bv_len - offset); + truncated = true; + } + done += bv.bv_len; + } + + exit: + /* + * Don't touch bvec table here and make it really immutable, since + * fs bio user has to retrieve all pages via bio_for_each_segment_all + * in its .end_bio() callback. + * + * It is enough to truncate bio by updating .bi_size since we can make + * correct bvec with the updated .bi_size for drivers. + */ + bio->bi_iter.bi_size = new_size; +} + +/** * bio_put - release a reference to a bio * @bio: bio to release reference to * diff --git a/block/blk-merge.c b/block/blk-merge.c index d783bdc4559b..1534ed736363 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -157,17 +157,20 @@ static inline unsigned get_max_io_size(struct request_queue *q, return sectors & (lbs - 1); } -static unsigned get_max_segment_size(const struct request_queue *q, - unsigned offset) +static inline unsigned get_max_segment_size(const struct request_queue *q, + struct page *start_page, + unsigned long offset) { unsigned long mask = queue_segment_boundary(q); - /* default segment boundary mask means no boundary limit */ - if (mask == BLK_SEG_BOUNDARY_MASK) - return queue_max_segment_size(q); + offset = mask & (page_to_phys(start_page) + offset); - return min_t(unsigned long, mask - (mask & offset) + 1, - queue_max_segment_size(q)); + /* + * overflow may be triggered in case of zero page physical address + * on 32bit arch, use queue's max segment size when that happens. + */ + return min_not_zero(mask - offset + 1, + (unsigned long)queue_max_segment_size(q)); } /** @@ -201,7 +204,8 @@ static bool bvec_split_segs(const struct request_queue *q, unsigned seg_size = 0; while (len && *nsegs < max_segs) { - seg_size = get_max_segment_size(q, bv->bv_offset + total_len); + seg_size = get_max_segment_size(q, bv->bv_page, + bv->bv_offset + total_len); seg_size = min(seg_size, len); (*nsegs)++; @@ -419,7 +423,8 @@ static unsigned blk_bvec_map_sg(struct request_queue *q, while (nbytes > 0) { unsigned offset = bvec->bv_offset + total; - unsigned len = min(get_max_segment_size(q, offset), nbytes); + unsigned len = min(get_max_segment_size(q, bvec->bv_page, + offset), nbytes); struct page *page = bvec->bv_page; /* diff --git a/block/blk-mq.c b/block/blk-mq.c index 323c9cb28066..a12b1763508d 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -641,6 +641,14 @@ bool blk_mq_complete_request(struct request *rq) } EXPORT_SYMBOL(blk_mq_complete_request); +/** + * blk_mq_start_request - Start processing a request + * @rq: Pointer to request to be started + * + * Function used by device drivers to notify the block layer that a request + * is going to be processed now, so blk layer can do proper initializations + * such as starting the timeout timer. + */ void blk_mq_start_request(struct request *rq) { struct request_queue *q = rq->q; @@ -1327,6 +1335,12 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list, return (queued + errors) != 0; } +/** + * __blk_mq_run_hw_queue - Run a hardware queue. + * @hctx: Pointer to the hardware queue to run. + * + * Send pending requests to the hardware. + */ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx) { int srcu_idx; @@ -1424,6 +1438,15 @@ select_cpu: return next_cpu; } +/** + * __blk_mq_delay_run_hw_queue - Run (or schedule to run) a hardware queue. + * @hctx: Pointer to the hardware queue to run. + * @async: If we want to run the queue asynchronously. + * @msecs: Microseconds of delay to wait before running the queue. + * + * If !@async, try to run the queue now. Else, run the queue asynchronously and + * with a delay of @msecs. + */ static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async, unsigned long msecs) { @@ -1445,12 +1468,28 @@ static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async, msecs_to_jiffies(msecs)); } +/** + * blk_mq_delay_run_hw_queue - Run a hardware queue asynchronously. + * @hctx: Pointer to the hardware queue to run. + * @msecs: Microseconds of delay to wait before running the queue. + * + * Run a hardware queue asynchronously with a delay of @msecs. + */ void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs) { __blk_mq_delay_run_hw_queue(hctx, true, msecs); } EXPORT_SYMBOL(blk_mq_delay_run_hw_queue); +/** + * blk_mq_run_hw_queue - Start to run a hardware queue. + * @hctx: Pointer to the hardware queue to run. + * @async: If we want to run the queue asynchronously. + * + * Check if the request queue is not in a quiesced state and if there are + * pending requests to be sent. If this is true, run the queue to send requests + * to hardware. + */ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async) { int srcu_idx; @@ -1474,6 +1513,11 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async) } EXPORT_SYMBOL(blk_mq_run_hw_queue); +/** + * blk_mq_run_hw_queue - Run all hardware queues in a request queue. + * @q: Pointer to the request queue to run. + * @async: If we want to run the queue asynchronously. + */ void blk_mq_run_hw_queues(struct request_queue *q, bool async) { struct blk_mq_hw_ctx *hctx; @@ -1625,7 +1669,11 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, blk_mq_hctx_mark_pending(hctx, ctx); } -/* +/** + * blk_mq_request_bypass_insert - Insert a request at dispatch list. + * @rq: Pointer to request to be inserted. + * @run_queue: If we should run the hardware queue after inserting the request. + * * Should only be used carefully, when the caller knows we want to * bypass a potential IO scheduler on the target device. */ @@ -1668,28 +1716,20 @@ static int plug_rq_cmp(void *priv, struct list_head *a, struct list_head *b) struct request *rqa = container_of(a, struct request, queuelist); struct request *rqb = container_of(b, struct request, queuelist); - if (rqa->mq_ctx < rqb->mq_ctx) - return -1; - else if (rqa->mq_ctx > rqb->mq_ctx) - return 1; - else if (rqa->mq_hctx < rqb->mq_hctx) - return -1; - else if (rqa->mq_hctx > rqb->mq_hctx) - return 1; + if (rqa->mq_ctx != rqb->mq_ctx) + return rqa->mq_ctx > rqb->mq_ctx; + if (rqa->mq_hctx != rqb->mq_hctx) + return rqa->mq_hctx > rqb->mq_hctx; return blk_rq_pos(rqa) > blk_rq_pos(rqb); } void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule) { - struct blk_mq_hw_ctx *this_hctx; - struct blk_mq_ctx *this_ctx; - struct request_queue *this_q; - struct request *rq; LIST_HEAD(list); - LIST_HEAD(rq_list); - unsigned int depth; + if (list_empty(&plug->mq_list)) + return; list_splice_init(&plug->mq_list, &list); if (plug->rq_count > 2 && plug->multiple_queues) @@ -1697,42 +1737,27 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule) plug->rq_count = 0; - this_q = NULL; - this_hctx = NULL; - this_ctx = NULL; - depth = 0; - - while (!list_empty(&list)) { - rq = list_entry_rq(list.next); - list_del_init(&rq->queuelist); - BUG_ON(!rq->q); - if (rq->mq_hctx != this_hctx || rq->mq_ctx != this_ctx) { - if (this_hctx) { - trace_block_unplug(this_q, depth, !from_schedule); - blk_mq_sched_insert_requests(this_hctx, this_ctx, - &rq_list, - from_schedule); - } - - this_q = rq->q; - this_ctx = rq->mq_ctx; - this_hctx = rq->mq_hctx; - depth = 0; + do { + struct list_head rq_list; + struct request *rq, *head_rq = list_entry_rq(list.next); + struct list_head *pos = &head_rq->queuelist; /* skip first */ + struct blk_mq_hw_ctx *this_hctx = head_rq->mq_hctx; + struct blk_mq_ctx *this_ctx = head_rq->mq_ctx; + unsigned int depth = 1; + + list_for_each_continue(pos, &list) { + rq = list_entry_rq(pos); + BUG_ON(!rq->q); + if (rq->mq_hctx != this_hctx || rq->mq_ctx != this_ctx) + break; + depth++; } - depth++; - list_add_tail(&rq->queuelist, &rq_list); - } - - /* - * If 'this_hctx' is set, we know we have entries to complete - * on 'rq_list'. Do those. - */ - if (this_hctx) { - trace_block_unplug(this_q, depth, !from_schedule); + list_cut_before(&rq_list, &list, pos); + trace_block_unplug(head_rq->q, depth, !from_schedule); blk_mq_sched_insert_requests(this_hctx, this_ctx, &rq_list, from_schedule); - } + } while(!list_empty(&list)); } static void blk_mq_bio_to_request(struct request *rq, struct bio *bio, @@ -1828,6 +1853,17 @@ insert: return BLK_STS_OK; } +/** + * blk_mq_try_issue_directly - Try to send a request directly to device driver. + * @hctx: Pointer of the associated hardware queue. + * @rq: Pointer to request to be sent. + * @cookie: Request queue cookie. + * + * If the device has enough resources to accept a new request now, send the + * request directly to device driver. Else, insert at hctx->dispatch queue, so + * we can try send it another time in the future. Requests inserted at this + * queue have higher priority. + */ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, struct request *rq, blk_qc_t *cookie) { @@ -1905,6 +1941,22 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq) } } +/** + * blk_mq_make_request - Create and send a request to block device. + * @q: Request queue pointer. + * @bio: Bio pointer. + * + * Builds up a request structure from @q and @bio and send to the device. The + * request may not be queued directly to hardware if: + * * This request can be merged with another one + * * We want to place request at plug queue for possible future merging + * * There is an IO scheduler active at this queue + * + * It will not queue the request if there is an error with the bio, or at the + * request creation. + * + * Returns: Request queue cookie. + */ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) { const int is_sync = op_is_sync(bio->bi_opf); @@ -1950,7 +2002,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) plug = blk_mq_plug(q, bio); if (unlikely(is_flush_fua)) { - /* bypass scheduler for flush rq */ + /* Bypass scheduler for flush requests */ blk_insert_flush(rq); blk_mq_run_hw_queue(data.hctx, true); } else if (plug && (q->nr_hw_queues == 1 || q->mq_ops->commit_rqs || @@ -1978,6 +2030,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) blk_add_rq_to_plug(plug, rq); } else if (q->elevator) { + /* Insert the request at the IO scheduler queue */ blk_mq_sched_insert_request(rq, false, true, true); } else if (plug && !blk_queue_nomerges(q)) { /* @@ -2004,8 +2057,13 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) } } else if ((q->nr_hw_queues > 1 && is_sync) || !data.hctx->dispatch_busy) { + /* + * There is no scheduler and we can try to send directly + * to the hardware. + */ blk_mq_try_issue_directly(data.hctx, rq, &cookie); } else { + /* Default case. */ blk_mq_sched_insert_request(rq, false, true, true); } diff --git a/block/blk-settings.c b/block/blk-settings.c index 5f6dcc7a47bd..c8eda2e7b91e 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -328,7 +328,7 @@ EXPORT_SYMBOL(blk_queue_max_segment_size); * storage device can address. The default of 512 covers most * hardware. **/ -void blk_queue_logical_block_size(struct request_queue *q, unsigned short size) +void blk_queue_logical_block_size(struct request_queue *q, unsigned int size) { q->limits.logical_block_size = size; diff --git a/block/blk-zoned.c b/block/blk-zoned.c index d00fcfd71dfe..05741c6f618b 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -198,7 +198,7 @@ int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op, break; } - bio->bi_opf = op; + bio->bi_opf = op | REQ_SYNC; bio->bi_iter.bi_sector = sector; sector += zone_sectors; diff --git a/block/partition-generic.c b/block/partition-generic.c index 1d20c9cf213f..564fae77711d 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -321,6 +321,24 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno, const char *dname; int err; + /* + * Partitions are not supported on zoned block devices that are used as + * such. + */ + switch (disk->queue->limits.zoned) { + case BLK_ZONED_HM: + pr_warn("%s: partitions not supported on host managed zoned block device\n", + disk->disk_name); + return ERR_PTR(-ENXIO); + case BLK_ZONED_HA: + pr_info("%s: disabling host aware zoned block device support due to partitions\n", + disk->disk_name); + disk->queue->limits.zoned = BLK_ZONED_NONE; + break; + case BLK_ZONED_NONE: + break; + } + err = disk_expand_part_tbl(disk, partno); if (err) return ERR_PTR(err); @@ -501,7 +519,7 @@ static bool blk_add_partition(struct gendisk *disk, struct block_device *bdev, part = add_partition(disk, p, from, size, state->parts[p].flags, &state->parts[p].info); - if (IS_ERR(part)) { + if (IS_ERR(part) && PTR_ERR(part) != -ENXIO) { printk(KERN_ERR " %s: p%d could not be added: %ld\n", disk->disk_name, p, -PTR_ERR(part)); return true; @@ -540,10 +558,10 @@ int blk_add_partitions(struct gendisk *disk, struct block_device *bdev) } /* - * Partitions are not supported on zoned block devices. + * Partitions are not supported on host managed zoned block devices. */ - if (bdev_is_zoned(bdev)) { - pr_warn("%s: ignoring partition table on zoned block device\n", + if (disk->queue->limits.zoned == BLK_ZONED_HM) { + pr_warn("%s: ignoring partition table on host managed zoned block device\n", disk->disk_name); ret = 0; goto out_free_state; diff --git a/block/partitions/ldm.c b/block/partitions/ldm.c index fe5d970e2e60..a2d97ee1908c 100644 --- a/block/partitions/ldm.c +++ b/block/partitions/ldm.c @@ -1233,7 +1233,7 @@ static bool ldm_frag_add (const u8 *data, int size, struct list_head *frags) BUG_ON (!data || !frags); if (size < 2 * VBLK_SIZE_HEAD) { - ldm_error("Value of size is to small."); + ldm_error("Value of size is too small."); return false; } diff --git a/block/t10-pi.c b/block/t10-pi.c index f4907d941f03..d910534b3a41 100644 --- a/block/t10-pi.c +++ b/block/t10-pi.c @@ -7,6 +7,7 @@ #include <linux/t10-pi.h> #include <linux/blkdev.h> #include <linux/crc-t10dif.h> +#include <linux/module.h> #include <net/checksum.h> typedef __be16 (csum_fn) (void *, unsigned int); @@ -280,3 +281,5 @@ const struct blk_integrity_profile t10_pi_type3_ip = { .complete_fn = t10_pi_type3_complete, }; EXPORT_SYMBOL(t10_pi_type3_ip); + +MODULE_LICENSE("GPL"); |