X-Git-Url: http://pileus.org/git/?a=blobdiff_plain;f=block%2Fll_rw_blk.c;h=5d472e47c125e5d1786ebdc2b107e1abc7928cc9;hb=9c9381f9425ab4d2f9f0458ae9525c18bc832f59;hp=9eaee66405353b6705c438c5aa8a5e9db7776f90;hpb=ced3985faebc232deec0dd9cc375cb5a43d18391;p=~andy%2Flinux diff --git a/block/ll_rw_blk.c b/block/ll_rw_blk.c index 9eaee664053..5d472e47c12 100644 --- a/block/ll_rw_blk.c +++ b/block/ll_rw_blk.c @@ -25,16 +25,18 @@ #include #include #include +#include #include #include #include +#include /* * for max sense size */ #include -static void blk_unplug_work(void *data); +static void blk_unplug_work(struct work_struct *work); static void blk_unplug_timeout(unsigned long data); static void drive_stat_acct(struct request *rq, int nr_sectors, int new_io); static void init_request_from_bio(struct request *req, struct bio *bio); @@ -44,17 +46,17 @@ static struct io_context *current_io_context(gfp_t gfp_flags, int node); /* * For the allocated request tables */ -static kmem_cache_t *request_cachep; +static struct kmem_cache *request_cachep; /* * For queue allocation */ -static kmem_cache_t *requestq_cachep; +static struct kmem_cache *requestq_cachep; /* * For io context allocations */ -static kmem_cache_t *iocontext_cachep; +static struct kmem_cache *iocontext_cachep; /* * Controlling structure to kblockd @@ -127,13 +129,6 @@ struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev) } EXPORT_SYMBOL(blk_get_backing_dev_info); -void blk_queue_activity_fn(request_queue_t *q, activity_fn *fn, void *data) -{ - q->activity_fn = fn; - q->activity_data = data; -} -EXPORT_SYMBOL(blk_queue_activity_fn); - /** * blk_queue_prep_rq - set a prepare_request function for queue * @q: queue @@ -227,7 +222,7 @@ void blk_queue_make_request(request_queue_t * q, make_request_fn * mfn) if (q->unplug_delay == 0) q->unplug_delay = 1; - INIT_WORK(&q->unplug_work, blk_unplug_work, q); + INIT_WORK(&q->unplug_work, blk_unplug_work); q->unplug_timer.function = blk_unplug_timeout; q->unplug_timer.data = (unsigned long)q; @@ -236,8 +231,6 @@ void blk_queue_make_request(request_queue_t * q, make_request_fn * mfn) * by default assume old behaviour and bounce for any highmem page */ blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH); - - blk_queue_activity_fn(q, NULL, NULL); } EXPORT_SYMBOL(blk_queue_make_request); @@ -1412,8 +1405,7 @@ static inline int ll_new_hw_segment(request_queue_t *q, return 1; } -static int ll_back_merge_fn(request_queue_t *q, struct request *req, - struct bio *bio) +int ll_back_merge_fn(request_queue_t *q, struct request *req, struct bio *bio) { unsigned short max_sectors; int len; @@ -1449,6 +1441,7 @@ static int ll_back_merge_fn(request_queue_t *q, struct request *req, return ll_new_hw_segment(q, req, bio); } +EXPORT_SYMBOL(ll_back_merge_fn); static int ll_front_merge_fn(request_queue_t *q, struct request *req, struct bio *bio) @@ -1631,9 +1624,9 @@ static void blk_backing_dev_unplug(struct backing_dev_info *bdi, } } -static void blk_unplug_work(void *data) +static void blk_unplug_work(struct work_struct *work) { - request_queue_t *q = data; + request_queue_t *q = container_of(work, request_queue_t, unplug_work); blk_add_trace_pdu_int(q, BLK_TA_UNPLUG_IO, NULL, q->rq.count[READ] + q->rq.count[WRITE]); @@ -1919,9 +1912,6 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id) } q->request_fn = rfn; - q->back_merge_fn = ll_back_merge_fn; - q->front_merge_fn = ll_front_merge_fn; - q->merge_requests_fn = ll_merge_requests_fn; q->prep_rq_fn = NULL; q->unplug_fn = generic_unplug_device; q->queue_flags = (1 << QUEUE_FLAG_CLUSTER); @@ -2065,15 +2055,16 @@ static void freed_request(request_queue_t *q, int rw, int priv) * Returns NULL on failure, with queue_lock held. * Returns !NULL on success, with queue_lock *not held*. */ -static struct request *get_request(request_queue_t *q, int rw, struct bio *bio, - gfp_t gfp_mask) +static struct request *get_request(request_queue_t *q, int rw_flags, + struct bio *bio, gfp_t gfp_mask) { struct request *rq = NULL; struct request_list *rl = &q->rq; struct io_context *ioc = NULL; + const int rw = rw_flags & 0x01; int may_queue, priv; - may_queue = elv_may_queue(q, rw); + may_queue = elv_may_queue(q, rw_flags); if (may_queue == ELV_MQUEUE_NO) goto rq_starved; @@ -2121,7 +2112,7 @@ static struct request *get_request(request_queue_t *q, int rw, struct bio *bio, spin_unlock_irq(q->queue_lock); - rq = blk_alloc_request(q, rw, priv, gfp_mask); + rq = blk_alloc_request(q, rw_flags, priv, gfp_mask); if (unlikely(!rq)) { /* * Allocation failed presumably due to memory. Undo anything @@ -2169,12 +2160,13 @@ out: * * Called with q->queue_lock held, and returns with it unlocked. */ -static struct request *get_request_wait(request_queue_t *q, int rw, +static struct request *get_request_wait(request_queue_t *q, int rw_flags, struct bio *bio) { + const int rw = rw_flags & 0x01; struct request *rq; - rq = get_request(q, rw, bio, GFP_NOIO); + rq = get_request(q, rw_flags, bio, GFP_NOIO); while (!rq) { DEFINE_WAIT(wait); struct request_list *rl = &q->rq; @@ -2182,7 +2174,7 @@ static struct request *get_request_wait(request_queue_t *q, int rw, prepare_to_wait_exclusive(&rl->wait[rw], &wait, TASK_UNINTERRUPTIBLE); - rq = get_request(q, rw, bio, GFP_NOIO); + rq = get_request(q, rw_flags, bio, GFP_NOIO); if (!rq) { struct io_context *ioc; @@ -2322,6 +2314,73 @@ void blk_insert_request(request_queue_t *q, struct request *rq, EXPORT_SYMBOL(blk_insert_request); +static int __blk_rq_unmap_user(struct bio *bio) +{ + int ret = 0; + + if (bio) { + if (bio_flagged(bio, BIO_USER_MAPPED)) + bio_unmap_user(bio); + else + ret = bio_uncopy_user(bio); + } + + return ret; +} + +static int __blk_rq_map_user(request_queue_t *q, struct request *rq, + void __user *ubuf, unsigned int len) +{ + unsigned long uaddr; + struct bio *bio, *orig_bio; + int reading, ret; + + reading = rq_data_dir(rq) == READ; + + /* + * if alignment requirement is satisfied, map in user pages for + * direct dma. else, set up kernel bounce buffers + */ + uaddr = (unsigned long) ubuf; + if (!(uaddr & queue_dma_alignment(q)) && !(len & queue_dma_alignment(q))) + bio = bio_map_user(q, NULL, uaddr, len, reading); + else + bio = bio_copy_user(q, uaddr, len, reading); + + if (IS_ERR(bio)) + return PTR_ERR(bio); + + orig_bio = bio; + blk_queue_bounce(q, &bio); + + /* + * We link the bounce buffer in and could have to traverse it + * later so we have to get a ref to prevent it from being freed + */ + bio_get(bio); + + if (!rq->bio) + blk_rq_bio_prep(q, rq, bio); + else if (!ll_back_merge_fn(q, rq, bio)) { + ret = -EINVAL; + goto unmap_bio; + } else { + rq->biotail->bi_next = bio; + rq->biotail = bio; + + rq->data_len += bio->bi_size; + } + + return bio->bi_size; + +unmap_bio: + /* if it was boucned we must call the end io function */ + bio_endio(bio, bio->bi_size, 0); + __blk_rq_unmap_user(orig_bio); + bio_put(bio); + return ret; +} + /** * blk_rq_map_user - map user data to a request, for REQ_BLOCK_PC usage * @q: request queue where request should be inserted @@ -2343,42 +2402,44 @@ EXPORT_SYMBOL(blk_insert_request); * unmapping. */ int blk_rq_map_user(request_queue_t *q, struct request *rq, void __user *ubuf, - unsigned int len) + unsigned long len) { - unsigned long uaddr; - struct bio *bio; - int reading; + unsigned long bytes_read = 0; + int ret; if (len > (q->max_hw_sectors << 9)) return -EINVAL; if (!len || !ubuf) return -EINVAL; - reading = rq_data_dir(rq) == READ; + while (bytes_read != len) { + unsigned long map_len, end, start; - /* - * if alignment requirement is satisfied, map in user pages for - * direct dma. else, set up kernel bounce buffers - */ - uaddr = (unsigned long) ubuf; - if (!(uaddr & queue_dma_alignment(q)) && !(len & queue_dma_alignment(q))) - bio = bio_map_user(q, NULL, uaddr, len, reading); - else - bio = bio_copy_user(q, uaddr, len, reading); + map_len = min_t(unsigned long, len - bytes_read, BIO_MAX_SIZE); + end = ((unsigned long)ubuf + map_len + PAGE_SIZE - 1) + >> PAGE_SHIFT; + start = (unsigned long)ubuf >> PAGE_SHIFT; - if (!IS_ERR(bio)) { - rq->bio = rq->biotail = bio; - blk_rq_bio_prep(q, rq, bio); + /* + * A bad offset could cause us to require BIO_MAX_PAGES + 1 + * pages. If this happens we just lower the requested + * mapping len by a page so that we can fit + */ + if (end - start > BIO_MAX_PAGES) + map_len -= PAGE_SIZE; - rq->buffer = rq->data = NULL; - rq->data_len = len; - return 0; + ret = __blk_rq_map_user(q, rq, ubuf, map_len); + if (ret < 0) + goto unmap_rq; + bytes_read += ret; + ubuf += ret; } - /* - * bio is the err-ptr - */ - return PTR_ERR(bio); + rq->buffer = rq->data = NULL; + return 0; +unmap_rq: + blk_rq_unmap_user(rq); + return ret; } EXPORT_SYMBOL(blk_rq_map_user); @@ -2404,7 +2465,7 @@ EXPORT_SYMBOL(blk_rq_map_user); * unmapping. */ int blk_rq_map_user_iov(request_queue_t *q, struct request *rq, - struct sg_iovec *iov, int iov_count) + struct sg_iovec *iov, int iov_count, unsigned int len) { struct bio *bio; @@ -2418,10 +2479,15 @@ int blk_rq_map_user_iov(request_queue_t *q, struct request *rq, if (IS_ERR(bio)) return PTR_ERR(bio); - rq->bio = rq->biotail = bio; + if (bio->bi_size != len) { + bio_endio(bio, bio->bi_size, 0); + bio_unmap_user(bio); + return -EINVAL; + } + + bio_get(bio); blk_rq_bio_prep(q, rq, bio); rq->buffer = rq->data = NULL; - rq->data_len = bio->bi_size; return 0; } @@ -2429,23 +2495,26 @@ EXPORT_SYMBOL(blk_rq_map_user_iov); /** * blk_rq_unmap_user - unmap a request with user data - * @bio: bio to be unmapped - * @ulen: length of user buffer + * @rq: rq to be unmapped * * Description: - * Unmap a bio previously mapped by blk_rq_map_user(). + * Unmap a rq previously mapped by blk_rq_map_user(). + * rq->bio must be set to the original head of the request. */ -int blk_rq_unmap_user(struct bio *bio, unsigned int ulen) +int blk_rq_unmap_user(struct request *rq) { - int ret = 0; + struct bio *bio, *mapped_bio; - if (bio) { - if (bio_flagged(bio, BIO_USER_MAPPED)) - bio_unmap_user(bio); + while ((bio = rq->bio)) { + if (bio_flagged(bio, BIO_BOUNCED)) + mapped_bio = bio->bi_private; else - ret = bio_uncopy_user(bio); - } + mapped_bio = bio; + __blk_rq_unmap_user(mapped_bio); + rq->bio = bio->bi_next; + bio_put(bio); + } return 0; } @@ -2476,11 +2545,8 @@ int blk_rq_map_kern(request_queue_t *q, struct request *rq, void *kbuf, if (rq_data_dir(rq) == WRITE) bio->bi_rw |= (1 << BIO_RW); - rq->bio = rq->biotail = bio; blk_rq_bio_prep(q, rq, bio); - rq->buffer = rq->data = NULL; - rq->data_len = len; return 0; } @@ -2609,9 +2675,6 @@ static inline void add_request(request_queue_t * q, struct request * req) { drive_stat_acct(req, req->nr_sectors, 1); - if (q->activity_fn) - q->activity_fn(q->activity_data, rq_data_dir(req)); - /* * elevator indicated where it wants this request to be * inserted at elevator_merge time @@ -2745,7 +2808,7 @@ static int attempt_merge(request_queue_t *q, struct request *req, * will have updated segment counts, update sector * counts here. */ - if (!q->merge_requests_fn(q, req, next)) + if (!ll_merge_requests_fn(q, req, next)) return 0; /* @@ -2835,6 +2898,7 @@ static int __make_request(request_queue_t *q, struct bio *bio) int el_ret, nr_sectors, barrier, err; const unsigned short prio = bio_prio(bio); const int sync = bio_sync(bio); + int rw_flags; nr_sectors = bio_sectors(bio); @@ -2861,7 +2925,7 @@ static int __make_request(request_queue_t *q, struct bio *bio) case ELEVATOR_BACK_MERGE: BUG_ON(!rq_mergeable(req)); - if (!q->back_merge_fn(q, req, bio)) + if (!ll_back_merge_fn(q, req, bio)) break; blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE); @@ -2878,7 +2942,7 @@ static int __make_request(request_queue_t *q, struct bio *bio) case ELEVATOR_FRONT_MERGE: BUG_ON(!rq_mergeable(req)); - if (!q->front_merge_fn(q, req, bio)) + if (!ll_front_merge_fn(q, req, bio)) break; blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE); @@ -2908,11 +2972,20 @@ static int __make_request(request_queue_t *q, struct bio *bio) } get_rq: + /* + * This sync check and mask will be re-done in init_request_from_bio(), + * but we need to set it earlier to expose the sync flag to the + * rq allocator and io schedulers. + */ + rw_flags = bio_data_dir(bio); + if (sync) + rw_flags |= REQ_RW_SYNC; + /* * Grab a free request. This is might sleep but can not fail. * Returns with the queue unlocked. */ - req = get_request_wait(q, bio_data_dir(bio), bio); + req = get_request_wait(q, rw_flags, bio); /* * After dropping the lock and possibly sleeping here, our request @@ -2971,6 +3044,42 @@ static void handle_bad_sector(struct bio *bio) set_bit(BIO_EOF, &bio->bi_flags); } +#ifdef CONFIG_FAIL_MAKE_REQUEST + +static DECLARE_FAULT_ATTR(fail_make_request); + +static int __init setup_fail_make_request(char *str) +{ + return setup_fault_attr(&fail_make_request, str); +} +__setup("fail_make_request=", setup_fail_make_request); + +static int should_fail_request(struct bio *bio) +{ + if ((bio->bi_bdev->bd_disk->flags & GENHD_FL_FAIL) || + (bio->bi_bdev->bd_part && bio->bi_bdev->bd_part->make_it_fail)) + return should_fail(&fail_make_request, bio->bi_size); + + return 0; +} + +static int __init fail_make_request_debugfs(void) +{ + return init_fault_attr_dentries(&fail_make_request, + "fail_make_request"); +} + +late_initcall(fail_make_request_debugfs); + +#else /* CONFIG_FAIL_MAKE_REQUEST */ + +static inline int should_fail_request(struct bio *bio) +{ + return 0; +} + +#endif /* CONFIG_FAIL_MAKE_REQUEST */ + /** * generic_make_request: hand a buffer to its device driver for I/O * @bio: The bio describing the location in memory and on the device. @@ -3056,6 +3165,9 @@ end_io: if (unlikely(test_bit(QUEUE_FLAG_DEAD, &q->queue_flags))) goto end_io; + if (should_fail_request(bio)) + goto end_io; + /* * If this device has partitions, remap block n * of partition p to block n+start(p) of the disk. @@ -3110,10 +3222,12 @@ void submit_bio(int rw, struct bio *bio) BIO_BUG_ON(!bio->bi_size); BIO_BUG_ON(!bio->bi_io_vec); bio->bi_rw |= rw; - if (rw & WRITE) + if (rw & WRITE) { count_vm_events(PGPGOUT, count); - else + } else { + task_io_account_read(bio->bi_size); count_vm_events(PGPGIN, count); + } if (unlikely(block_dump)) { char b[BDEVNAME_SIZE]; @@ -3374,8 +3488,6 @@ static void blk_done_softirq(struct softirq_action *h) } } -#ifdef CONFIG_HOTPLUG_CPU - static int blk_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { @@ -3401,8 +3513,6 @@ static struct notifier_block __devinitdata blk_cpu_notifier = { .notifier_call = blk_cpu_notify, }; -#endif /* CONFIG_HOTPLUG_CPU */ - /** * blk_complete_request - end I/O on a request * @req: the request being processed @@ -3495,6 +3605,7 @@ void blk_rq_bio_prep(request_queue_t *q, struct request *rq, struct bio *bio) rq->hard_cur_sectors = rq->current_nr_sectors; rq->hard_nr_sectors = rq->nr_sectors = bio_sectors(bio); rq->buffer = bio_data(bio); + rq->data_len = bio->bi_size; rq->bio = rq->biotail = bio; }