X-Git-Url: http://ftp.safe.ca/?p=safe%2Fjmp%2Flinux-2.6;a=blobdiff_plain;f=block%2Fblk-core.c;h=ac0fa10f8fa55a2372aa7bae2e0a257fc064b193;hp=b84250d3019b717607531f01c0b2d1695ae31f45;hb=dc7a08166f3a5f23e79e839a8a88849bd3397c32;hpb=b243ddcbe9be146172baa544dadecebf156eda0e diff --git a/block/blk-core.c b/block/blk-core.c index b84250d..ac0fa10 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -26,24 +26,16 @@ #include #include #include -#include #include -#include + +#define CREATE_TRACE_POINTS +#include #include "blk.h" -DEFINE_TRACE(block_plug); -DEFINE_TRACE(block_unplug_io); -DEFINE_TRACE(block_unplug_timer); -DEFINE_TRACE(block_getrq); -DEFINE_TRACE(block_sleeprq); -DEFINE_TRACE(block_rq_requeue); -DEFINE_TRACE(block_bio_backmerge); -DEFINE_TRACE(block_bio_frontmerge); -DEFINE_TRACE(block_bio_queue); -DEFINE_TRACE(block_rq_complete); -DEFINE_TRACE(block_remap); /* Also used in drivers/md/dm.c */ EXPORT_TRACEPOINT_SYMBOL_GPL(block_remap); +EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap); +EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete); static int __make_request(struct request_queue *q, struct bio *bio); @@ -68,17 +60,17 @@ static void drive_stat_acct(struct request *rq, int new_io) int rw = rq_data_dir(rq); int cpu; - if (!blk_fs_request(rq) || !blk_do_io_stat(rq)) + if (!blk_do_io_stat(rq)) return; cpu = part_stat_lock(); - part = disk_map_sector_rcu(rq->rq_disk, rq->sector); + part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq)); if (!new_io) part_stat_inc(cpu, part, merges[rw]); else { part_round_stats(cpu, part); - part_inc_in_flight(part); + part_inc_in_flight(part, rw); } part_stat_unlock(); @@ -127,7 +119,7 @@ void blk_rq_init(struct request_queue *q, struct request *rq) INIT_LIST_HEAD(&rq->timeout_list); rq->cpu = -1; rq->q = q; - rq->sector = rq->hard_sector = (sector_t) -1; + rq->__sector = (sector_t) -1; INIT_HLIST_NODE(&rq->hash); RB_CLEAR_NODE(&rq->rb_node); rq->cmd = rq->__cmd; @@ -185,14 +177,11 @@ void blk_dump_rq_flags(struct request *rq, char *msg) rq->rq_disk ? rq->rq_disk->disk_name : "?", rq->cmd_type, rq->cmd_flags); - printk(KERN_INFO " sector %llu, nr/cnr %lu/%u\n", - (unsigned long long)rq->sector, - rq->nr_sectors, - rq->current_nr_sectors); - printk(KERN_INFO " bio %p, biotail %p, buffer %p, data %p, len %u\n", - rq->bio, rq->biotail, - rq->buffer, rq->data, - rq->data_len); + printk(KERN_INFO " sector %llu, nr/cnr %u/%u\n", + (unsigned long long)blk_rq_pos(rq), + blk_rq_sectors(rq), blk_rq_cur_sectors(rq)); + printk(KERN_INFO " bio %p, biotail %p, buffer %p, len %u\n", + rq->bio, rq->biotail, rq->buffer, blk_rq_bytes(rq)); if (blk_pc_request(rq)) { printk(KERN_INFO " cdb: "); @@ -509,6 +498,12 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) q->backing_dev_info.unplug_io_fn = blk_backing_dev_unplug; q->backing_dev_info.unplug_io_data = q; + q->backing_dev_info.ra_pages = + (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE; + q->backing_dev_info.state = 0; + q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY; + q->backing_dev_info.name = "block"; + err = bdi_init(&q->backing_dev_info); if (err) { kmem_cache_free(blk_requestq_cachep, q); @@ -582,13 +577,6 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id) return NULL; } - /* - * if caller didn't supply a lock, they get per-queue locking with - * our embedded lock - */ - if (!lock) - lock = &q->__queue_lock; - q->request_fn = rfn; q->prep_rq_fn = NULL; q->unplug_fn = generic_unplug_device; @@ -602,8 +590,6 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id) q->sg_reserved_size = INT_MAX; - blk_set_cmd_filter_defaults(&q->cmd_filter); - /* * all done */ @@ -894,6 +880,61 @@ struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask) EXPORT_SYMBOL(blk_get_request); /** + * blk_make_request - given a bio, allocate a corresponding struct request. + * @q: target request queue + * @bio: The bio describing the memory mappings that will be submitted for IO. + * It may be a chained-bio properly constructed by block/bio layer. + * @gfp_mask: gfp flags to be used for memory allocation + * + * blk_make_request is the parallel of generic_make_request for BLOCK_PC + * type commands. Where the struct request needs to be farther initialized by + * the caller. It is passed a &struct bio, which describes the memory info of + * the I/O transfer. + * + * The caller of blk_make_request must make sure that bi_io_vec + * are set to describe the memory buffers. That bio_data_dir() will return + * the needed direction of the request. (And all bio's in the passed bio-chain + * are properly set accordingly) + * + * If called under none-sleepable conditions, mapped bio buffers must not + * need bouncing, by calling the appropriate masked or flagged allocator, + * suitable for the target device. Otherwise the call to blk_queue_bounce will + * BUG. + * + * WARNING: When allocating/cloning a bio-chain, careful consideration should be + * given to how you allocate bios. In particular, you cannot use __GFP_WAIT for + * anything but the first bio in the chain. Otherwise you risk waiting for IO + * completion of a bio that hasn't been submitted yet, thus resulting in a + * deadlock. Alternatively bios should be allocated using bio_kmalloc() instead + * of bio_alloc(), as that avoids the mempool deadlock. + * If possible a big IO should be split into smaller parts when allocation + * fails. Partial allocation should not be an error, or you risk a live-lock. + */ +struct request *blk_make_request(struct request_queue *q, struct bio *bio, + gfp_t gfp_mask) +{ + struct request *rq = blk_get_request(q, bio_data_dir(bio), gfp_mask); + + if (unlikely(!rq)) + return ERR_PTR(-ENOMEM); + + for_each_bio(bio) { + struct bio *bounce_bio = bio; + int ret; + + blk_queue_bounce(q, &bounce_bio); + ret = blk_rq_append_bio(q, rq, bounce_bio); + if (unlikely(ret)) { + blk_put_request(rq); + return ERR_PTR(ret); + } + } + + return rq; +} +EXPORT_SYMBOL(blk_make_request); + +/** * blk_requeue_request - put a request back on queue * @q: request queue where request should be inserted * @rq: request to be inserted @@ -912,6 +953,8 @@ void blk_requeue_request(struct request_queue *q, struct request *rq) if (blk_rq_tagged(rq)) blk_queue_end_tag(q, rq); + BUG_ON(blk_queued_rq(rq)); + elv_requeue_request(q, rq); } EXPORT_SYMBOL(blk_requeue_request); @@ -987,9 +1030,9 @@ static void part_round_stats_single(int cpu, struct hd_struct *part, if (now == part->stamp) return; - if (part->in_flight) { + if (part_in_flight(part)) { __part_stat_add(cpu, part, time_in_queue, - part->in_flight * (now - part->stamp)); + part_in_flight(part) * (now - part->stamp)); __part_stat_add(cpu, part, io_ticks, (now - part->stamp)); } part->stamp = now; @@ -1070,35 +1113,30 @@ void init_request_from_bio(struct request *req, struct bio *bio) req->cmd_type = REQ_TYPE_FS; /* - * inherit FAILFAST from bio (for read-ahead, and explicit FAILFAST) + * Inherit FAILFAST from bio (for read-ahead, and explicit + * FAILFAST). FAILFAST flags are identical for req and bio. */ - if (bio_rw_ahead(bio)) - req->cmd_flags |= (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | - REQ_FAILFAST_DRIVER); - if (bio_failfast_dev(bio)) - req->cmd_flags |= REQ_FAILFAST_DEV; - if (bio_failfast_transport(bio)) - req->cmd_flags |= REQ_FAILFAST_TRANSPORT; - if (bio_failfast_driver(bio)) - req->cmd_flags |= REQ_FAILFAST_DRIVER; - - if (unlikely(bio_discard(bio))) { + if (bio_rw_flagged(bio, BIO_RW_AHEAD)) + req->cmd_flags |= REQ_FAILFAST_MASK; + else + req->cmd_flags |= bio->bi_rw & REQ_FAILFAST_MASK; + + if (unlikely(bio_rw_flagged(bio, BIO_RW_DISCARD))) { req->cmd_flags |= REQ_DISCARD; - if (bio_barrier(bio)) + if (bio_rw_flagged(bio, BIO_RW_BARRIER)) req->cmd_flags |= REQ_SOFTBARRIER; - req->q->prepare_discard_fn(req->q, req); - } else if (unlikely(bio_barrier(bio))) + } else if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) req->cmd_flags |= REQ_HARDBARRIER; - if (bio_sync(bio)) + if (bio_rw_flagged(bio, BIO_RW_SYNCIO)) req->cmd_flags |= REQ_RW_SYNC; - if (bio_rw_meta(bio)) + if (bio_rw_flagged(bio, BIO_RW_META)) req->cmd_flags |= REQ_RW_META; - if (bio_noidle(bio)) + if (bio_rw_flagged(bio, BIO_RW_NOIDLE)) req->cmd_flags |= REQ_NOIDLE; req->errors = 0; - req->hard_sector = req->sector = bio->bi_sector; + req->__sector = bio->bi_sector; req->ioprio = bio_prio(bio); blk_rq_bio_prep(req->q, req, bio); } @@ -1109,20 +1147,25 @@ void init_request_from_bio(struct request *req, struct bio *bio) */ static inline bool queue_should_plug(struct request_queue *q) { - return !(blk_queue_nonrot(q) && blk_queue_tagged(q)); + return !(blk_queue_nonrot(q) && blk_queue_queuing(q)); } static int __make_request(struct request_queue *q, struct bio *bio) { struct request *req; - int el_ret, nr_sectors; + int el_ret; + unsigned int bytes = bio->bi_size; const unsigned short prio = bio_prio(bio); - const int sync = bio_sync(bio); - const int unplug = bio_unplug(bio); + const bool sync = bio_rw_flagged(bio, BIO_RW_SYNCIO); + const bool unplug = bio_rw_flagged(bio, BIO_RW_UNPLUG); + const unsigned int ff = bio->bi_rw & REQ_FAILFAST_MASK; int rw_flags; - nr_sectors = bio_sectors(bio); - + if (bio_rw_flagged(bio, BIO_RW_BARRIER) && bio_has_data(bio) && + (q->next_ordered == QUEUE_ORDERED_NONE)) { + bio_endio(bio, -EOPNOTSUPP); + return 0; + } /* * low level driver can indicate that it wants pages above a * certain limit bounced to low memory (ie for highmem, or even @@ -1132,7 +1175,7 @@ static int __make_request(struct request_queue *q, struct bio *bio) spin_lock_irq(q->queue_lock); - if (unlikely(bio_barrier(bio)) || elv_queue_empty(q)) + if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER)) || elv_queue_empty(q)) goto get_rq; el_ret = elv_merge(q, &req, bio); @@ -1145,9 +1188,12 @@ static int __make_request(struct request_queue *q, struct bio *bio) trace_block_bio_backmerge(q, bio); + if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) + blk_rq_set_mixed_merge(req); + req->biotail->bi_next = bio; req->biotail = bio; - req->nr_sectors = req->hard_nr_sectors += nr_sectors; + req->__data_len += bytes; req->ioprio = ioprio_best(req->ioprio, prio); if (!blk_rq_cpu_valid(req)) req->cpu = bio->bi_comp_cpu; @@ -1164,6 +1210,12 @@ static int __make_request(struct request_queue *q, struct bio *bio) trace_block_bio_frontmerge(q, bio); + if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) { + blk_rq_set_mixed_merge(req); + req->cmd_flags &= ~REQ_FAILFAST_MASK; + req->cmd_flags |= ff; + } + bio->bi_next = req->bio; req->bio = bio; @@ -1173,10 +1225,8 @@ static int __make_request(struct request_queue *q, struct bio *bio) * not touch req->buffer either... */ req->buffer = bio_data(bio); - req->current_nr_sectors = bio_cur_sectors(bio); - req->hard_cur_sectors = req->current_nr_sectors; - req->sector = req->hard_sector = bio->bi_sector; - req->nr_sectors = req->hard_nr_sectors += nr_sectors; + req->__sector = bio->bi_sector; + req->__data_len += bytes; req->ioprio = ioprio_best(req->ioprio, prio); if (!blk_rq_cpu_valid(req)) req->cpu = bio->bi_comp_cpu; @@ -1242,7 +1292,7 @@ static inline void blk_partition_remap(struct bio *bio) bio->bi_bdev = bdev->bd_contains; trace_block_remap(bdev_get_queue(bio->bi_bdev), bio, - bdev->bd_dev, bio->bi_sector, + bdev->bd_dev, bio->bi_sector - p->start_sect); } } @@ -1387,11 +1437,12 @@ static inline void __generic_make_request(struct bio *bio) goto end_io; } - if (unlikely(nr_sectors > q->max_hw_sectors)) { + if (unlikely(!bio_rw_flagged(bio, BIO_RW_DISCARD) && + nr_sectors > queue_max_hw_sectors(q))) { printk(KERN_ERR "bio too big device %s (%u > %u)\n", - bdevname(bio->bi_bdev, b), - bio_sectors(bio), - q->max_hw_sectors); + bdevname(bio->bi_bdev, b), + bio_sectors(bio), + queue_max_hw_sectors(q)); goto end_io; } @@ -1411,10 +1462,7 @@ static inline void __generic_make_request(struct bio *bio) goto end_io; if (old_sector != -1) - trace_block_remap(q, bio, old_dev, bio->bi_sector, - old_sector); - - trace_block_bio_queue(q, bio); + trace_block_remap(q, bio, old_dev, old_sector); old_sector = bio->bi_sector; old_dev = bio->bi_bdev->bd_dev; @@ -1422,16 +1470,14 @@ static inline void __generic_make_request(struct bio *bio) if (bio_check_eod(bio, nr_sectors)) goto end_io; - if (bio_discard(bio) && !q->prepare_discard_fn) { - err = -EOPNOTSUPP; - goto end_io; - } - if (bio_barrier(bio) && bio_has_data(bio) && - (q->next_ordered == QUEUE_ORDERED_NONE)) { + if (bio_rw_flagged(bio, BIO_RW_DISCARD) && + !blk_queue_discard(q)) { err = -EOPNOTSUPP; goto end_io; } + trace_block_bio_queue(q, bio); + ret = q->make_request_fn(q, bio); } while (ret); @@ -1558,8 +1604,8 @@ EXPORT_SYMBOL(submit_bio); */ int blk_rq_check_limits(struct request_queue *q, struct request *rq) { - if (rq->nr_sectors > q->max_sectors || - rq->data_len > q->max_hw_sectors << 9) { + if (blk_rq_sectors(rq) > queue_max_sectors(q) || + blk_rq_bytes(rq) > queue_max_hw_sectors(q) << 9) { printk(KERN_ERR "%s: over max size limit.\n", __func__); return -EIO; } @@ -1571,8 +1617,8 @@ int blk_rq_check_limits(struct request_queue *q, struct request *rq) * limitation. */ blk_recalc_rq_segments(rq); - if (rq->nr_phys_segments > q->max_phys_segments || - rq->nr_phys_segments > q->max_hw_segments) { + if (rq->nr_phys_segments > queue_max_phys_segments(q) || + rq->nr_phys_segments > queue_max_hw_segments(q)) { printk(KERN_ERR "%s: over max segments limit.\n", __func__); return -EIO; } @@ -1617,39 +1663,58 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq) EXPORT_SYMBOL_GPL(blk_insert_cloned_request); /** - * blkdev_dequeue_request - dequeue request and start timeout timer - * @req: request to dequeue + * blk_rq_err_bytes - determine number of bytes till the next failure boundary + * @rq: request to examine + * + * Description: + * A request could be merge of IOs which require different failure + * handling. This function determines the number of bytes which + * can be failed from the beginning of the request without + * crossing into area which need to be retried further. * - * Dequeue @req and start timeout timer on it. This hands off the - * request to the driver. + * Return: + * The number of bytes to fail. * - * Block internal functions which don't want to start timer should - * call elv_dequeue_request(). + * Context: + * queue_lock must be held. */ -void blkdev_dequeue_request(struct request *req) +unsigned int blk_rq_err_bytes(const struct request *rq) { - elv_dequeue_request(req->q, req); + unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK; + unsigned int bytes = 0; + struct bio *bio; + + if (!(rq->cmd_flags & REQ_MIXED_MERGE)) + return blk_rq_bytes(rq); /* - * We are now handing the request to the hardware, add the - * timeout handler. + * Currently the only 'mixing' which can happen is between + * different fastfail types. We can safely fail portions + * which have all the failfast bits that the first one has - + * the ones which are at least as eager to fail as the first + * one. */ - blk_add_timer(req); + for (bio = rq->bio; bio; bio = bio->bi_next) { + if ((bio->bi_rw & ff) != ff) + break; + bytes += bio->bi_size; + } + + /* this could lead to infinite loop */ + BUG_ON(blk_rq_bytes(rq) && !bytes); + return bytes; } -EXPORT_SYMBOL(blkdev_dequeue_request); +EXPORT_SYMBOL_GPL(blk_rq_err_bytes); static void blk_account_io_completion(struct request *req, unsigned int bytes) { - if (!blk_do_io_stat(req)) - return; - - if (blk_fs_request(req)) { + if (blk_do_io_stat(req)) { const int rw = rq_data_dir(req); struct hd_struct *part; int cpu; cpu = part_stat_lock(); - part = disk_map_sector_rcu(req->rq_disk, req->sector); + part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req)); part_stat_add(cpu, part, sectors[rw], bytes >> 9); part_stat_unlock(); } @@ -1657,62 +1722,46 @@ static void blk_account_io_completion(struct request *req, unsigned int bytes) static void blk_account_io_done(struct request *req) { - if (!blk_do_io_stat(req)) - return; - /* * Account IO completion. bar_rq isn't accounted as a normal * IO on queueing nor completion. Accounting the containing * request is enough. */ - if (blk_fs_request(req) && req != &req->q->bar_rq) { + if (blk_do_io_stat(req) && req != &req->q->bar_rq) { unsigned long duration = jiffies - req->start_time; const int rw = rq_data_dir(req); struct hd_struct *part; int cpu; cpu = part_stat_lock(); - part = disk_map_sector_rcu(req->rq_disk, req->sector); + part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req)); part_stat_inc(cpu, part, ios[rw]); part_stat_add(cpu, part, ticks[rw], duration); part_round_stats(cpu, part); - part_dec_in_flight(part); + part_dec_in_flight(part, rw); part_stat_unlock(); } } /** - * blk_rq_bytes - Returns bytes left to complete in the entire request - * @rq: the request being processed - **/ -unsigned int blk_rq_bytes(struct request *rq) -{ - if (blk_fs_request(rq)) - return rq->hard_nr_sectors << 9; - - return rq->data_len; -} -EXPORT_SYMBOL_GPL(blk_rq_bytes); - -/** - * blk_rq_cur_bytes - Returns bytes left to complete in the current segment - * @rq: the request being processed - **/ -unsigned int blk_rq_cur_bytes(struct request *rq) -{ - if (blk_fs_request(rq)) - return rq->current_nr_sectors << 9; - - if (rq->bio) - return rq->bio->bi_size; - - return rq->data_len; -} -EXPORT_SYMBOL_GPL(blk_rq_cur_bytes); - -struct request *elv_next_request(struct request_queue *q) + * blk_peek_request - peek at the top of a request queue + * @q: request queue to peek at + * + * Description: + * Return the request at the top of @q. The returned request + * should be started using blk_start_request() before LLD starts + * processing it. + * + * Return: + * Pointer to the request at the top of @q if available. Null + * otherwise. + * + * Context: + * queue_lock must be held. + */ +struct request *blk_peek_request(struct request_queue *q) { struct request *rq; int ret; @@ -1744,7 +1793,7 @@ struct request *elv_next_request(struct request_queue *q) if (rq->cmd_flags & REQ_DONTPREP) break; - if (q->dma_drain_size && rq->data_len) { + if (q->dma_drain_size && blk_rq_bytes(rq)) { /* * make sure space for the drain appears we * know we can do this because max_hw_segments @@ -1767,7 +1816,7 @@ struct request *elv_next_request(struct request_queue *q) * avoid resource deadlock. REQ_STARTED will * prevent other fs requests from passing this one. */ - if (q->dma_drain_size && rq->data_len && + if (q->dma_drain_size && blk_rq_bytes(rq) && !(rq->cmd_flags & REQ_DONTPREP)) { /* * remove the space for the drain we added @@ -1780,7 +1829,12 @@ struct request *elv_next_request(struct request_queue *q) break; } else if (ret == BLKPREP_KILL) { rq->cmd_flags |= REQ_QUIET; - __blk_end_request(rq, -EIO, blk_rq_bytes(rq)); + /* + * Mark this request as started so we don't trigger + * any debug logic in the end I/O path. + */ + blk_start_request(rq); + __blk_end_request_all(rq, -EIO); } else { printk(KERN_ERR "%s: bad return=%d\n", __func__, ret); break; @@ -1789,10 +1843,12 @@ struct request *elv_next_request(struct request_queue *q) return rq; } -EXPORT_SYMBOL(elv_next_request); +EXPORT_SYMBOL(blk_peek_request); -void elv_dequeue_request(struct request_queue *q, struct request *rq) +void blk_dequeue_request(struct request *rq) { + struct request_queue *q = rq->q; + BUG_ON(list_empty(&rq->queuelist)); BUG_ON(ELV_ON_HASH(rq)); @@ -1803,20 +1859,83 @@ void elv_dequeue_request(struct request_queue *q, struct request *rq) * and to it is freed is accounted as io that is in progress at * the driver side. */ - if (blk_account_rq(rq)) - q->in_flight++; + if (blk_account_rq(rq)) { + q->in_flight[rq_is_sync(rq)]++; + /* + * Mark this device as supporting hardware queuing, if + * we have more IOs in flight than 4. + */ + if (!blk_queue_queuing(q) && queue_in_flight(q) > 4) + set_bit(QUEUE_FLAG_CQ, &q->queue_flags); + } +} + +/** + * blk_start_request - start request processing on the driver + * @req: request to dequeue + * + * Description: + * Dequeue @req and start timeout timer on it. This hands off the + * request to the driver. + * + * Block internal functions which don't want to start timer should + * call blk_dequeue_request(). + * + * Context: + * queue_lock must be held. + */ +void blk_start_request(struct request *req) +{ + blk_dequeue_request(req); + + /* + * We are now handing the request to the hardware, initialize + * resid_len to full count and add the timeout handler. + */ + req->resid_len = blk_rq_bytes(req); + if (unlikely(blk_bidi_rq(req))) + req->next_rq->resid_len = blk_rq_bytes(req->next_rq); + + blk_add_timer(req); +} +EXPORT_SYMBOL(blk_start_request); + +/** + * blk_fetch_request - fetch a request from a request queue + * @q: request queue to fetch a request from + * + * Description: + * Return the request at the top of @q. The request is started on + * return and LLD can start processing it immediately. + * + * Return: + * Pointer to the request at the top of @q if available. Null + * otherwise. + * + * Context: + * queue_lock must be held. + */ +struct request *blk_fetch_request(struct request_queue *q) +{ + struct request *rq; + + rq = blk_peek_request(q); + if (rq) + blk_start_request(rq); + return rq; } +EXPORT_SYMBOL(blk_fetch_request); /** * blk_update_request - Special helper function for request stacking drivers - * @rq: the request being processed + * @req: the request being processed * @error: %0 for success, < %0 for error - * @nr_bytes: number of bytes to complete @rq + * @nr_bytes: number of bytes to complete @req * * Description: - * Ends I/O on a number of bytes attached to @rq, but doesn't complete - * the request structure even if @rq doesn't have leftover. - * If @rq has leftover, sets it up for the next range of segments. + * Ends I/O on a number of bytes attached to @req, but doesn't complete + * the request structure even if @req doesn't have leftover. + * If @req has leftover, sets it up for the next range of segments. * * This special helper function is only for request stacking drivers * (e.g. request-based dm) so that they can handle partial completion. @@ -1853,7 +1972,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes) if (error && (blk_fs_request(req) && !(req->cmd_flags & REQ_QUIET))) { printk(KERN_ERR "end_request: I/O error, dev %s, sector %llu\n", req->rq_disk ? req->rq_disk->disk_name : "?", - (unsigned long long)req->sector); + (unsigned long long)blk_rq_pos(req)); } blk_account_io_completion(req, nr_bytes); @@ -1871,10 +1990,10 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes) } else { int idx = bio->bi_idx + next_idx; - if (unlikely(bio->bi_idx >= bio->bi_vcnt)) { + if (unlikely(idx >= bio->bi_vcnt)) { blk_dump_rq_flags(req, "__end_that"); printk(KERN_ERR "%s: bio idx %d >= vcnt %d\n", - __func__, bio->bi_idx, bio->bi_vcnt); + __func__, idx, bio->bi_vcnt); break; } @@ -1919,8 +2038,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes) * can find how many bytes remain in the request * later. */ - req->nr_sectors = req->hard_nr_sectors = 0; - req->current_nr_sectors = req->hard_cur_sectors = 0; + req->__data_len = 0; return false; } @@ -1934,8 +2052,31 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes) bio_iovec(bio)->bv_len -= nr_bytes; } - blk_recalc_rq_sectors(req, total_bytes >> 9); + req->__data_len -= total_bytes; + req->buffer = bio_data(req->bio); + + /* update sector only for requests with clear definition of sector */ + if (blk_fs_request(req) || blk_discard_rq(req)) + req->__sector += total_bytes >> 9; + + /* mixed attributes always follow the first bio */ + if (req->cmd_flags & REQ_MIXED_MERGE) { + req->cmd_flags &= ~REQ_FAILFAST_MASK; + req->cmd_flags |= req->bio->bi_rw & REQ_FAILFAST_MASK; + } + + /* + * If total number of sectors is less than the first segment + * size, something has gone terribly wrong. + */ + if (blk_rq_bytes(req) < blk_rq_cur_bytes(req)) { + printk(KERN_ERR "blk: request botched\n"); + req->__data_len = blk_rq_cur_bytes(req); + } + + /* recalculate the number of segments */ blk_recalc_rq_segments(req); + return true; } EXPORT_SYMBOL_GPL(blk_update_request); @@ -1965,8 +2106,7 @@ static void blk_finish_request(struct request *req, int error) if (blk_rq_tagged(req)) blk_queue_end_tag(req->q, req); - if (blk_queued_rq(req)) - elv_dequeue_request(req->q, req); + BUG_ON(blk_queued_rq(req)); if (unlikely(laptop_mode) && blk_fs_request(req)) laptop_io_completion(); @@ -2002,8 +2142,8 @@ static void blk_finish_request(struct request *req, int error) * %false - we are done with this request * %true - still buffers pending for this request **/ -bool blk_end_bidi_request(struct request *rq, int error, - unsigned int nr_bytes, unsigned int bidi_bytes) +static bool blk_end_bidi_request(struct request *rq, int error, + unsigned int nr_bytes, unsigned int bidi_bytes) { struct request_queue *q = rq->q; unsigned long flags; @@ -2017,7 +2157,6 @@ bool blk_end_bidi_request(struct request *rq, int error, return false; } -EXPORT_SYMBOL_GPL(blk_end_bidi_request); /** * __blk_end_bidi_request - Complete a bidi request with queue lock held @@ -2034,8 +2173,8 @@ EXPORT_SYMBOL_GPL(blk_end_bidi_request); * %false - we are done with this request * %true - still buffers pending for this request **/ -bool __blk_end_bidi_request(struct request *rq, int error, - unsigned int nr_bytes, unsigned int bidi_bytes) +static bool __blk_end_bidi_request(struct request *rq, int error, + unsigned int nr_bytes, unsigned int bidi_bytes) { if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes)) return true; @@ -2044,24 +2183,175 @@ bool __blk_end_bidi_request(struct request *rq, int error, return false; } -EXPORT_SYMBOL_GPL(__blk_end_bidi_request); + +/** + * blk_end_request - Helper function for drivers to complete the request. + * @rq: the request being processed + * @error: %0 for success, < %0 for error + * @nr_bytes: number of bytes to complete + * + * Description: + * Ends I/O on a number of bytes attached to @rq. + * If @rq has leftover, sets it up for the next range of segments. + * + * Return: + * %false - we are done with this request + * %true - still buffers pending for this request + **/ +bool blk_end_request(struct request *rq, int error, unsigned int nr_bytes) +{ + return blk_end_bidi_request(rq, error, nr_bytes, 0); +} +EXPORT_SYMBOL(blk_end_request); + +/** + * blk_end_request_all - Helper function for drives to finish the request. + * @rq: the request to finish + * @error: %0 for success, < %0 for error + * + * Description: + * Completely finish @rq. + */ +void blk_end_request_all(struct request *rq, int error) +{ + bool pending; + unsigned int bidi_bytes = 0; + + if (unlikely(blk_bidi_rq(rq))) + bidi_bytes = blk_rq_bytes(rq->next_rq); + + pending = blk_end_bidi_request(rq, error, blk_rq_bytes(rq), bidi_bytes); + BUG_ON(pending); +} +EXPORT_SYMBOL(blk_end_request_all); + +/** + * blk_end_request_cur - Helper function to finish the current request chunk. + * @rq: the request to finish the current chunk for + * @error: %0 for success, < %0 for error + * + * Description: + * Complete the current consecutively mapped chunk from @rq. + * + * Return: + * %false - we are done with this request + * %true - still buffers pending for this request + */ +bool blk_end_request_cur(struct request *rq, int error) +{ + return blk_end_request(rq, error, blk_rq_cur_bytes(rq)); +} +EXPORT_SYMBOL(blk_end_request_cur); + +/** + * blk_end_request_err - Finish a request till the next failure boundary. + * @rq: the request to finish till the next failure boundary for + * @error: must be negative errno + * + * Description: + * Complete @rq till the next failure boundary. + * + * Return: + * %false - we are done with this request + * %true - still buffers pending for this request + */ +bool blk_end_request_err(struct request *rq, int error) +{ + WARN_ON(error >= 0); + return blk_end_request(rq, error, blk_rq_err_bytes(rq)); +} +EXPORT_SYMBOL_GPL(blk_end_request_err); + +/** + * __blk_end_request - Helper function for drivers to complete the request. + * @rq: the request being processed + * @error: %0 for success, < %0 for error + * @nr_bytes: number of bytes to complete + * + * Description: + * Must be called with queue lock held unlike blk_end_request(). + * + * Return: + * %false - we are done with this request + * %true - still buffers pending for this request + **/ +bool __blk_end_request(struct request *rq, int error, unsigned int nr_bytes) +{ + return __blk_end_bidi_request(rq, error, nr_bytes, 0); +} +EXPORT_SYMBOL(__blk_end_request); + +/** + * __blk_end_request_all - Helper function for drives to finish the request. + * @rq: the request to finish + * @error: %0 for success, < %0 for error + * + * Description: + * Completely finish @rq. Must be called with queue lock held. + */ +void __blk_end_request_all(struct request *rq, int error) +{ + bool pending; + unsigned int bidi_bytes = 0; + + if (unlikely(blk_bidi_rq(rq))) + bidi_bytes = blk_rq_bytes(rq->next_rq); + + pending = __blk_end_bidi_request(rq, error, blk_rq_bytes(rq), bidi_bytes); + BUG_ON(pending); +} +EXPORT_SYMBOL(__blk_end_request_all); + +/** + * __blk_end_request_cur - Helper function to finish the current request chunk. + * @rq: the request to finish the current chunk for + * @error: %0 for success, < %0 for error + * + * Description: + * Complete the current consecutively mapped chunk from @rq. Must + * be called with queue lock held. + * + * Return: + * %false - we are done with this request + * %true - still buffers pending for this request + */ +bool __blk_end_request_cur(struct request *rq, int error) +{ + return __blk_end_request(rq, error, blk_rq_cur_bytes(rq)); +} +EXPORT_SYMBOL(__blk_end_request_cur); + +/** + * __blk_end_request_err - Finish a request till the next failure boundary. + * @rq: the request to finish till the next failure boundary for + * @error: must be negative errno + * + * Description: + * Complete @rq till the next failure boundary. Must be called + * with queue lock held. + * + * Return: + * %false - we are done with this request + * %true - still buffers pending for this request + */ +bool __blk_end_request_err(struct request *rq, int error) +{ + WARN_ON(error >= 0); + return __blk_end_request(rq, error, blk_rq_err_bytes(rq)); +} +EXPORT_SYMBOL_GPL(__blk_end_request_err); void blk_rq_bio_prep(struct request_queue *q, struct request *rq, struct bio *bio) { - /* Bit 0 (R/W) is identical in rq->cmd_flags and bio->bi_rw, and - we want BIO_RW_AHEAD (bit 1) to imply REQ_FAILFAST (bit 1). */ - rq->cmd_flags |= (bio->bi_rw & 3); + /* Bit 0 (R/W) is identical in rq->cmd_flags and bio->bi_rw */ + rq->cmd_flags |= bio->bi_rw & REQ_RW; if (bio_has_data(bio)) { rq->nr_phys_segments = bio_phys_segments(q, bio); rq->buffer = bio_data(bio); } - rq->current_nr_sectors = bio_cur_sectors(bio); - rq->hard_cur_sectors = rq->current_nr_sectors; - rq->hard_nr_sectors = rq->nr_sectors = bio_sectors(bio); - rq->data_len = bio->bi_size; - + rq->__data_len = bio->bi_size; rq->bio = rq->biotail = bio; if (bio->bi_bdev) @@ -2096,6 +2386,106 @@ int blk_lld_busy(struct request_queue *q) } EXPORT_SYMBOL_GPL(blk_lld_busy); +/** + * blk_rq_unprep_clone - Helper function to free all bios in a cloned request + * @rq: the clone request to be cleaned up + * + * Description: + * Free all bios in @rq for a cloned request. + */ +void blk_rq_unprep_clone(struct request *rq) +{ + struct bio *bio; + + while ((bio = rq->bio) != NULL) { + rq->bio = bio->bi_next; + + bio_put(bio); + } +} +EXPORT_SYMBOL_GPL(blk_rq_unprep_clone); + +/* + * Copy attributes of the original request to the clone request. + * The actual data parts (e.g. ->cmd, ->buffer, ->sense) are not copied. + */ +static void __blk_rq_prep_clone(struct request *dst, struct request *src) +{ + dst->cpu = src->cpu; + dst->cmd_flags = (rq_data_dir(src) | REQ_NOMERGE); + dst->cmd_type = src->cmd_type; + dst->__sector = blk_rq_pos(src); + dst->__data_len = blk_rq_bytes(src); + dst->nr_phys_segments = src->nr_phys_segments; + dst->ioprio = src->ioprio; + dst->extra_len = src->extra_len; +} + +/** + * blk_rq_prep_clone - Helper function to setup clone request + * @rq: the request to be setup + * @rq_src: original request to be cloned + * @bs: bio_set that bios for clone are allocated from + * @gfp_mask: memory allocation mask for bio + * @bio_ctr: setup function to be called for each clone bio. + * Returns %0 for success, non %0 for failure. + * @data: private data to be passed to @bio_ctr + * + * Description: + * Clones bios in @rq_src to @rq, and copies attributes of @rq_src to @rq. + * The actual data parts of @rq_src (e.g. ->cmd, ->buffer, ->sense) + * are not copied, and copying such parts is the caller's responsibility. + * Also, pages which the original bios are pointing to are not copied + * and the cloned bios just point same pages. + * So cloned bios must be completed before original bios, which means + * the caller must complete @rq before @rq_src. + */ +int blk_rq_prep_clone(struct request *rq, struct request *rq_src, + struct bio_set *bs, gfp_t gfp_mask, + int (*bio_ctr)(struct bio *, struct bio *, void *), + void *data) +{ + struct bio *bio, *bio_src; + + if (!bs) + bs = fs_bio_set; + + blk_rq_init(NULL, rq); + + __rq_for_each_bio(bio_src, rq_src) { + bio = bio_alloc_bioset(gfp_mask, bio_src->bi_max_vecs, bs); + if (!bio) + goto free_and_out; + + __bio_clone(bio, bio_src); + + if (bio_integrity(bio_src) && + bio_integrity_clone(bio, bio_src, gfp_mask, bs)) + goto free_and_out; + + if (bio_ctr && bio_ctr(bio, bio_src, data)) + goto free_and_out; + + if (rq->bio) { + rq->biotail->bi_next = bio; + rq->biotail = bio; + } else + rq->bio = rq->biotail = bio; + } + + __blk_rq_prep_clone(rq, rq_src); + + return 0; + +free_and_out: + if (bio) + bio_free(bio, bs); + blk_rq_unprep_clone(rq); + + return -ENOMEM; +} +EXPORT_SYMBOL_GPL(blk_rq_prep_clone); + int kblockd_schedule_work(struct request_queue *q, struct work_struct *work) { return queue_work(kblockd_workqueue, work); @@ -2104,6 +2494,9 @@ EXPORT_SYMBOL(kblockd_schedule_work); int __init blk_dev_init(void) { + BUILD_BUG_ON(__REQ_NR_BITS > 8 * + sizeof(((struct request *)0)->cmd_flags)); + kblockd_workqueue = create_workqueue("kblockd"); if (!kblockd_workqueue) panic("Failed to create kblockd\n");