diff options
Diffstat (limited to 'block')
-rw-r--r-- | block/bio-integrity.c | 17 | ||||
-rw-r--r-- | block/bio.c | 26 | ||||
-rw-r--r-- | block/blk-cgroup.c | 1 | ||||
-rw-r--r-- | block/blk-core.c | 124 | ||||
-rw-r--r-- | block/blk-integrity.c | 192 | ||||
-rw-r--r-- | block/blk-ioc.c | 2 | ||||
-rw-r--r-- | block/blk-lib.c | 31 | ||||
-rw-r--r-- | block/blk-merge.c | 32 | ||||
-rw-r--r-- | block/blk-mq-sysfs.c | 6 | ||||
-rw-r--r-- | block/blk-mq-tag.c | 7 | ||||
-rw-r--r-- | block/blk-mq.c | 179 | ||||
-rw-r--r-- | block/blk-mq.h | 2 | ||||
-rw-r--r-- | block/blk-sysfs.c | 4 | ||||
-rw-r--r-- | block/blk-throttle.c | 2 | ||||
-rw-r--r-- | block/blk.h | 23 | ||||
-rw-r--r-- | block/cfq-iosched.c | 4 | ||||
-rw-r--r-- | block/elevator.c | 2 | ||||
-rw-r--r-- | block/genhd.c | 2 | ||||
-rw-r--r-- | block/ioctl.c | 330 | ||||
-rw-r--r-- | block/ioprio.c | 6 | ||||
-rw-r--r-- | block/partition-generic.c | 1 | ||||
-rw-r--r-- | block/scsi_ioctl.c | 6 | ||||
-rw-r--r-- | block/t10-pi.c | 16 |
23 files changed, 631 insertions, 384 deletions
diff --git a/block/bio-integrity.c b/block/bio-integrity.c index 14b8faf8b09d..f6325d573c10 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -32,6 +32,11 @@ static struct kmem_cache *bip_slab; static struct workqueue_struct *kintegrityd_wq; +void blk_flush_integrity(void) +{ + flush_workqueue(kintegrityd_wq); +} + /** * bio_integrity_alloc - Allocate integrity payload and attach it to bio * @bio: bio to attach integrity metadata to @@ -177,11 +182,11 @@ bool bio_integrity_enabled(struct bio *bio) if (bi == NULL) return false; - if (bio_data_dir(bio) == READ && bi->verify_fn != NULL && + if (bio_data_dir(bio) == READ && bi->profile->verify_fn != NULL && (bi->flags & BLK_INTEGRITY_VERIFY)) return true; - if (bio_data_dir(bio) == WRITE && bi->generate_fn != NULL && + if (bio_data_dir(bio) == WRITE && bi->profile->generate_fn != NULL && (bi->flags & BLK_INTEGRITY_GENERATE)) return true; @@ -202,7 +207,7 @@ EXPORT_SYMBOL(bio_integrity_enabled); static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, unsigned int sectors) { - return sectors >> (ilog2(bi->interval) - 9); + return sectors >> (bi->interval_exp - 9); } static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi, @@ -229,7 +234,7 @@ static int bio_integrity_process(struct bio *bio, bip->bip_vec->bv_offset; iter.disk_name = bio->bi_bdev->bd_disk->disk_name; - iter.interval = bi->interval; + iter.interval = 1 << bi->interval_exp; iter.seed = bip_get_seed(bip); iter.prot_buf = prot_buf; @@ -340,7 +345,7 @@ int bio_integrity_prep(struct bio *bio) /* Auto-generate integrity metadata if this is a write */ if (bio_data_dir(bio) == WRITE) - bio_integrity_process(bio, bi->generate_fn); + bio_integrity_process(bio, bi->profile->generate_fn); return 0; } @@ -361,7 +366,7 @@ static void bio_integrity_verify_fn(struct work_struct *work) struct bio *bio = bip->bip_bio; struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev); - bio->bi_error = bio_integrity_process(bio, bi->verify_fn); + bio->bi_error = bio_integrity_process(bio, bi->profile->verify_fn); /* Restore original bio completion handler */ bio->bi_end_io = bip->bip_end_io; diff --git a/block/bio.c b/block/bio.c index ad3f276d74bc..4f184d938942 100644 --- a/block/bio.c +++ b/block/bio.c @@ -211,7 +211,7 @@ fallback: bvl = mempool_alloc(pool, gfp_mask); } else { struct biovec_slab *bvs = bvec_slabs + *idx; - gfp_t __gfp_mask = gfp_mask & ~(__GFP_WAIT | __GFP_IO); + gfp_t __gfp_mask = gfp_mask & ~(__GFP_DIRECT_RECLAIM | __GFP_IO); /* * Make this allocation restricted and don't dump info on @@ -221,11 +221,11 @@ fallback: __gfp_mask |= __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN; /* - * Try a slab allocation. If this fails and __GFP_WAIT + * Try a slab allocation. If this fails and __GFP_DIRECT_RECLAIM * is set, retry with the 1-entry mempool */ bvl = kmem_cache_alloc(bvs->slab, __gfp_mask); - if (unlikely(!bvl && (gfp_mask & __GFP_WAIT))) { + if (unlikely(!bvl && (gfp_mask & __GFP_DIRECT_RECLAIM))) { *idx = BIOVEC_MAX_IDX; goto fallback; } @@ -395,12 +395,12 @@ static void punt_bios_to_rescuer(struct bio_set *bs) * If @bs is NULL, uses kmalloc() to allocate the bio; else the allocation is * backed by the @bs's mempool. * - * When @bs is not NULL, if %__GFP_WAIT is set then bio_alloc will always be - * able to allocate a bio. This is due to the mempool guarantees. To make this - * work, callers must never allocate more than 1 bio at a time from this pool. - * Callers that need to allocate more than 1 bio must always submit the - * previously allocated bio for IO before attempting to allocate a new one. - * Failure to do so can cause deadlocks under memory pressure. + * When @bs is not NULL, if %__GFP_DIRECT_RECLAIM is set then bio_alloc will + * always be able to allocate a bio. This is due to the mempool guarantees. + * To make this work, callers must never allocate more than 1 bio at a time + * from this pool. Callers that need to allocate more than 1 bio must always + * submit the previously allocated bio for IO before attempting to allocate + * a new one. Failure to do so can cause deadlocks under memory pressure. * * Note that when running under generic_make_request() (i.e. any block * driver), bios are not submitted until after you return - see the code in @@ -459,13 +459,13 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs) * We solve this, and guarantee forward progress, with a rescuer * workqueue per bio_set. If we go to allocate and there are * bios on current->bio_list, we first try the allocation - * without __GFP_WAIT; if that fails, we punt those bios we - * would be blocking to the rescuer workqueue before we retry - * with the original gfp_flags. + * without __GFP_DIRECT_RECLAIM; if that fails, we punt those + * bios we would be blocking to the rescuer workqueue before + * we retry with the original gfp_flags. */ if (current->bio_list && !bio_list_empty(current->bio_list)) - gfp_mask &= ~__GFP_WAIT; + gfp_mask &= ~__GFP_DIRECT_RECLAIM; p = mempool_alloc(bs->bio_pool, gfp_mask); if (!p && gfp_mask != saved_gfp) { diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 55512dd62633..5bcdfc10c23a 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -899,6 +899,7 @@ static int blkcg_print_stat(struct seq_file *sf, void *v) struct cftype blkcg_files[] = { { .name = "stat", + .flags = CFTYPE_NOT_ON_ROOT, .seq_show = blkcg_print_stat, }, { } /* terminate */ diff --git a/block/blk-core.c b/block/blk-core.c index 2eb722d48773..590cca21c24a 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -554,29 +554,30 @@ void blk_cleanup_queue(struct request_queue *q) * Drain all requests queued before DYING marking. Set DEAD flag to * prevent that q->request_fn() gets invoked after draining finished. */ - if (q->mq_ops) { - blk_mq_freeze_queue(q); - spin_lock_irq(lock); - } else { - spin_lock_irq(lock); + blk_freeze_queue(q); + spin_lock_irq(lock); + if (!q->mq_ops) __blk_drain_queue(q, true); - } queue_flag_set(QUEUE_FLAG_DEAD, q); spin_unlock_irq(lock); + /* for synchronous bio-based driver finish in-flight integrity i/o */ + blk_flush_integrity(); + /* @q won't process any more request, flush async actions */ del_timer_sync(&q->backing_dev_info.laptop_mode_wb_timer); blk_sync_queue(q); if (q->mq_ops) blk_mq_free_queue(q); + percpu_ref_exit(&q->q_usage_counter); spin_lock_irq(lock); if (q->queue_lock != &q->__queue_lock) q->queue_lock = &q->__queue_lock; spin_unlock_irq(lock); - bdi_destroy(&q->backing_dev_info); + bdi_unregister(&q->backing_dev_info); /* @q is and will stay empty, shutdown and put */ blk_put_queue(q); @@ -629,6 +630,40 @@ struct request_queue *blk_alloc_queue(gfp_t gfp_mask) } EXPORT_SYMBOL(blk_alloc_queue); +int blk_queue_enter(struct request_queue *q, gfp_t gfp) +{ + while (true) { + int ret; + + if (percpu_ref_tryget_live(&q->q_usage_counter)) + return 0; + + if (!gfpflags_allow_blocking(gfp)) + return -EBUSY; + + ret = wait_event_interruptible(q->mq_freeze_wq, + !atomic_read(&q->mq_freeze_depth) || + blk_queue_dying(q)); + if (blk_queue_dying(q)) + return -ENODEV; + if (ret) + return ret; + } +} + +void blk_queue_exit(struct request_queue *q) +{ + percpu_ref_put(&q->q_usage_counter); +} + +static void blk_queue_usage_counter_release(struct percpu_ref *ref) +{ + struct request_queue *q = + container_of(ref, struct request_queue, q_usage_counter); + + wake_up_all(&q->mq_freeze_wq); +} + struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) { struct request_queue *q; @@ -690,11 +725,22 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) init_waitqueue_head(&q->mq_freeze_wq); - if (blkcg_init_queue(q)) + /* + * Init percpu_ref in atomic mode so that it's faster to shutdown. + * See blk_register_queue() for details. + */ + if (percpu_ref_init(&q->q_usage_counter, + blk_queue_usage_counter_release, + PERCPU_REF_INIT_ATOMIC, GFP_KERNEL)) goto fail_bdi; + if (blkcg_init_queue(q)) + goto fail_ref; + return q; +fail_ref: + percpu_ref_exit(&q->q_usage_counter); fail_bdi: bdi_destroy(&q->backing_dev_info); fail_split: @@ -1160,8 +1206,8 @@ rq_starved: * @bio: bio to allocate request for (can be %NULL) * @gfp_mask: allocation mask * - * Get a free request from @q. If %__GFP_WAIT is set in @gfp_mask, this - * function keeps retrying under memory pressure and fails iff @q is dead. + * Get a free request from @q. If %__GFP_DIRECT_RECLAIM is set in @gfp_mask, + * this function keeps retrying under memory pressure and fails iff @q is dead. * * Must be called with @q->queue_lock held and, * Returns ERR_PTR on failure, with @q->queue_lock held. @@ -1181,7 +1227,7 @@ retry: if (!IS_ERR(rq)) return rq; - if (!(gfp_mask & __GFP_WAIT) || unlikely(blk_queue_dying(q))) { + if (!gfpflags_allow_blocking(gfp_mask) || unlikely(blk_queue_dying(q))) { blk_put_rl(rl); return rq; } @@ -1259,11 +1305,11 @@ EXPORT_SYMBOL(blk_get_request); * 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. + * given to how you allocate bios. In particular, you cannot use + * __GFP_DIRECT_RECLAIM 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. */ @@ -1594,6 +1640,30 @@ out: return ret; } +unsigned int blk_plug_queued_count(struct request_queue *q) +{ + struct blk_plug *plug; + struct request *rq; + struct list_head *plug_list; + unsigned int ret = 0; + + plug = current->plug; + if (!plug) + goto out; + + if (q->mq_ops) + plug_list = &plug->mq_list; + else + plug_list = &plug->list; + + list_for_each_entry(rq, plug_list, queuelist) { + if (rq->q == q) + ret++; + } +out: + return ret; +} + void init_request_from_bio(struct request *req, struct bio *bio) { req->cmd_type = REQ_TYPE_FS; @@ -1641,9 +1711,11 @@ static void blk_queue_bio(struct request_queue *q, struct bio *bio) * Check if we can merge with the plugged list before grabbing * any locks. */ - if (!blk_queue_nomerges(q) && - blk_attempt_plug_merge(q, bio, &request_count, NULL)) - return; + if (!blk_queue_nomerges(q)) { + if (blk_attempt_plug_merge(q, bio, &request_count, NULL)) + return; + } else + request_count = blk_plug_queued_count(q); spin_lock_irq(q->queue_lock); @@ -1966,9 +2038,19 @@ void generic_make_request(struct bio *bio) do { struct request_queue *q = bdev_get_queue(bio->bi_bdev); - q->make_request_fn(q, bio); + if (likely(blk_queue_enter(q, __GFP_DIRECT_RECLAIM) == 0)) { + + q->make_request_fn(q, bio); + + blk_queue_exit(q); - bio = bio_list_pop(current->bio_list); + bio = bio_list_pop(current->bio_list); + } else { + struct bio *bio_next = bio_list_pop(current->bio_list); + + bio_io_error(bio); + bio = bio_next; + } } while (bio); current->bio_list = NULL; /* deactivate */ } diff --git a/block/blk-integrity.c b/block/blk-integrity.c index 75f29cf70188..d69c5c79f98e 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -30,10 +30,6 @@ #include "blk.h" -static struct kmem_cache *integrity_cachep; - -static const char *bi_unsupported_name = "unsupported"; - /** * blk_rq_count_integrity_sg - Count number of integrity scatterlist elements * @q: request queue @@ -146,40 +142,40 @@ EXPORT_SYMBOL(blk_rq_map_integrity_sg); */ int blk_integrity_compare(struct gendisk *gd1, struct gendisk *gd2) { - struct blk_integrity *b1 = gd1->integrity; - struct blk_integrity *b2 = gd2->integrity; + struct blk_integrity *b1 = &gd1->queue->integrity; + struct blk_integrity *b2 = &gd2->queue->integrity; - if (!b1 && !b2) + if (!b1->profile && !b2->profile) return 0; - if (!b1 || !b2) + if (!b1->profile || !b2->profile) return -1; - if (b1->interval != b2->interval) { + if (b1->interval_exp != b2->interval_exp) { pr_err("%s: %s/%s protection interval %u != %u\n", __func__, gd1->disk_name, gd2->disk_name, - b1->interval, b2->interval); + 1 << b1->interval_exp, 1 << b2->interval_exp); return -1; } if (b1->tuple_size != b2->tuple_size) { - printk(KERN_ERR "%s: %s/%s tuple sz %u != %u\n", __func__, + pr_err("%s: %s/%s tuple sz %u != %u\n", __func__, gd1->disk_name, gd2->disk_name, b1->tuple_size, b2->tuple_size); return -1; } if (b1->tag_size && b2->tag_size && (b1->tag_size != b2->tag_size)) { - printk(KERN_ERR "%s: %s/%s tag sz %u != %u\n", __func__, + pr_err("%s: %s/%s tag sz %u != %u\n", __func__, gd1->disk_name, gd2->disk_name, b1->tag_size, b2->tag_size); return -1; } - if (strcmp(b1->name, b2->name)) { - printk(KERN_ERR "%s: %s/%s type %s != %s\n", __func__, + if (b1->profile != b2->profile) { + pr_err("%s: %s/%s type %s != %s\n", __func__, gd1->disk_name, gd2->disk_name, - b1->name, b2->name); + b1->profile->name, b2->profile->name); return -1; } @@ -249,8 +245,8 @@ struct integrity_sysfs_entry { static ssize_t integrity_attr_show(struct kobject *kobj, struct attribute *attr, char *page) { - struct blk_integrity *bi = - container_of(kobj, struct blk_integrity, kobj); + struct gendisk *disk = container_of(kobj, struct gendisk, integrity_kobj); + struct blk_integrity *bi = &disk->queue->integrity; struct integrity_sysfs_entry *entry = container_of(attr, struct integrity_sysfs_entry, attr); @@ -261,8 +257,8 @@ static ssize_t integrity_attr_store(struct kobject *kobj, struct attribute *attr, const char *page, size_t count) { - struct blk_integrity *bi = - container_of(kobj, struct blk_integrity, kobj); + struct gendisk *disk = container_of(kobj, struct gendisk, integrity_kobj); + struct blk_integrity *bi = &disk->queue->integrity; struct integrity_sysfs_entry *entry = container_of(attr, struct integrity_sysfs_entry, attr); ssize_t ret = 0; @@ -275,18 +271,21 @@ static ssize_t integrity_attr_store(struct kobject *kobj, static ssize_t integrity_format_show(struct blk_integrity *bi, char *page) { - if (bi != NULL && bi->name != NULL) - return sprintf(page, "%s\n", bi->name); + if (bi->profile && bi->profile->name) + return sprintf(page, "%s\n", bi->profile->name); else return sprintf(page, "none\n"); } static ssize_t integrity_tag_size_show(struct blk_integrity *bi, char *page) { - if (bi != NULL) - return sprintf(page, "%u\n", bi->tag_size); - else - return sprintf(page, "0\n"); + return sprintf(page, "%u\n", bi->tag_size); +} + +static ssize_t integrity_interval_show(struct blk_integrity *bi, char *page) +{ + return sprintf(page, "%u\n", + bi->interval_exp ? 1 << bi->interval_exp : 0); } static ssize_t integrity_verify_store(struct blk_integrity *bi, @@ -343,6 +342,11 @@ static struct integrity_sysfs_entry integrity_tag_size_entry = { .show = integrity_tag_size_show, }; +static struct integrity_sysfs_entry integrity_interval_entry = { + .attr = { .name = "protection_interval_bytes", .mode = S_IRUGO }, + .show = integrity_interval_show, +}; + static struct integrity_sysfs_entry integrity_verify_entry = { .attr = { .name = "read_verify", .mode = S_IRUGO | S_IWUSR }, .show = integrity_verify_show, @@ -363,6 +367,7 @@ static struct integrity_sysfs_entry integrity_device_entry = { static struct attribute *integrity_attrs[] = { &integrity_format_entry.attr, &integrity_tag_size_entry.attr, + &integrity_interval_entry.attr, &integrity_verify_entry.attr, &integrity_generate_entry.attr, &integrity_device_entry.attr, @@ -374,114 +379,89 @@ static const struct sysfs_ops integrity_ops = { .store = &integrity_attr_store, }; -static int __init blk_dev_integrity_init(void) -{ - integrity_cachep = kmem_cache_create("blkdev_integrity", - sizeof(struct blk_integrity), - 0, SLAB_PANIC, NULL); - return 0; -} -subsys_initcall(blk_dev_integrity_init); - -static void blk_integrity_release(struct kobject *kobj) -{ - struct blk_integrity *bi = - container_of(kobj, struct blk_integrity, kobj); - - kmem_cache_free(integrity_cachep, bi); -} - static struct kobj_type integrity_ktype = { .default_attrs = integrity_attrs, .sysfs_ops = &integrity_ops, - .release = blk_integrity_release, }; -bool blk_integrity_is_initialized(struct gendisk *disk) +static int blk_integrity_nop_fn(struct blk_integrity_iter *iter) { - struct blk_integrity *bi = blk_get_integrity(disk); - - return (bi && bi->name && strcmp(bi->name, bi_unsupported_name) != 0); + return 0; } -EXPORT_SYMBOL(blk_integrity_is_initialized); + +static struct blk_integrity_profile nop_profile = { + .name = "nop", + .generate_fn = blk_integrity_nop_fn, + .verify_fn = blk_integrity_nop_fn, +}; /** * blk_integrity_register - Register a gendisk as being integrity-capable * @disk: struct gendisk pointer to make integrity-aware - * @template: optional integrity profile to register + * @template: block integrity profile to register * - * Description: When a device needs to advertise itself as being able - * to send/receive integrity metadata it must use this function to - * register the capability with the block layer. The template is a - * blk_integrity struct with values appropriate for the underlying - * hardware. If template is NULL the new profile is allocated but - * not filled out. See Documentation/block/data-integrity.txt. + * Description: When a device needs to advertise itself as being able to + * send/receive integrity metadata it must use this function to register + * the capability with the block layer. The template is a blk_integrity + * struct with values appropriate for the underlying hardware. See + * Documentation/block/data-integrity.txt. */ -int blk_integrity_register(struct gendisk *disk, struct blk_integrity *template) +void blk_integrity_register(struct gendisk *disk, struct blk_integrity *template) { - struct blk_integrity *bi; + struct blk_integrity *bi = &disk->queue->integrity; - BUG_ON(disk == NULL); + bi->flags = BLK_INTEGRITY_VERIFY | BLK_INTEGRITY_GENERATE | + template->flags; + bi->interval_exp = ilog2(queue_logical_block_size(disk->queue)); + bi->profile = template->profile ? template->profile : &nop_profile; + bi->tuple_size = template->tuple_size; + bi->tag_size = template->tag_size; - if (disk->integrity == NULL) { - bi = kmem_cache_alloc(integrity_cachep, - GFP_KERNEL | __GFP_ZERO); - if (!bi) - return -1; - - if (kobject_init_and_add(&bi->kobj, &integrity_ktype, - &disk_to_dev(disk)->kobj, - "%s", "integrity")) { - kmem_cache_free(integrity_cachep, bi); - return -1; - } - - kobject_uevent(&bi->kobj, KOBJ_ADD); - - bi->flags |= BLK_INTEGRITY_VERIFY | BLK_INTEGRITY_GENERATE; - bi->interval = queue_logical_block_size(disk->queue); - disk->integrity = bi; - } else - bi = disk->integrity; - - /* Use the provided profile as template */ - if (template != NULL) { - bi->name = template->name; - bi->generate_fn = template->generate_fn; - bi->verify_fn = template->verify_fn; - bi->tuple_size = template->tuple_size; - bi->tag_size = template->tag_size; - bi->flags |= template->flags; - } else - bi->name = bi_unsupported_name; - - disk->queue->backing_dev_info.capabilities |= BDI_CAP_STABLE_WRITES; - - return 0; + blk_integrity_revalidate(disk); } EXPORT_SYMBOL(blk_integrity_register); /** - * blk_integrity_unregister - Remove block integrity profile - * @disk: disk whose integrity profile to deallocate + * blk_integrity_unregister - Unregister block integrity profile + * @disk: disk whose integrity profile to unregister * - * Description: This function frees all memory used by the block - * integrity profile. To be called at device teardown. + * Description: This function unregisters the integrity capability from + * a block device. */ void blk_integrity_unregister(struct gendisk *disk) { - struct blk_integrity *bi; + blk_integrity_revalidate(disk); + memset(&disk->queue->integrity, 0, sizeof(struct blk_integrity)); +} +EXPORT_SYMBOL(blk_integrity_unregister); + +void blk_integrity_revalidate(struct gendisk *disk) +{ + struct blk_integrity *bi = &disk->queue->integrity; - if (!disk || !disk->integrity) + if (!(disk->flags & GENHD_FL_UP)) return; - disk->queue->backing_dev_info.capabilities &= ~BDI_CAP_STABLE_WRITES; + if (bi->profile) + disk->queue->backing_dev_info.capabilities |= + BDI_CAP_STABLE_WRITES; + else + disk->queue->backing_dev_info.capabilities &= + ~BDI_CAP_STABLE_WRITES; +} + +void blk_integrity_add(struct gendisk *disk) +{ + if (kobject_init_and_add(&disk->integrity_kobj, &integrity_ktype, + &disk_to_dev(disk)->kobj, "%s", "integrity")) + return; - bi = disk->integrity; + kobject_uevent(&disk->integrity_kobj, KOBJ_ADD); +} - kobject_uevent(&bi->kobj, KOBJ_REMOVE); - kobject_del(&bi->kobj); - kobject_put(&bi->kobj); - disk->integrity = NULL; +void blk_integrity_del(struct gendisk *disk) +{ + kobject_uevent(&disk->integrity_kobj, KOBJ_REMOVE); + kobject_del(&disk->integrity_kobj); + kobject_put(&disk->integrity_kobj); } -EXPORT_SYMBOL(blk_integrity_unregister); diff --git a/block/blk-ioc.c b/block/blk-ioc.c index 1a27f45ec776..381cb50a673c 100644 --- a/block/blk-ioc.c +++ b/block/blk-ioc.c @@ -289,7 +289,7 @@ struct io_context *get_task_io_context(struct task_struct *task, { struct io_context *ioc; - might_sleep_if(gfp_flags & __GFP_WAIT); + might_sleep_if(gfpflags_allow_blocking(gfp_flags)); do { task_lock(task); diff --git a/block/blk-lib.c b/block/blk-lib.c index bd40292e5009..9ebf65379556 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -26,13 +26,6 @@ static void bio_batch_end_io(struct bio *bio) bio_put(bio); } -/* - * Ensure that max discard sectors doesn't overflow bi_size and hopefully - * it is of the proper granularity as long as the granularity is a power - * of two. - */ -#define MAX_BIO_SECTORS ((1U << 31) >> 9) - /** * blkdev_issue_discard - queue a discard * @bdev: blockdev to issue discard for @@ -50,6 +43,8 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, DECLARE_COMPLETION_ONSTACK(wait); struct request_queue *q = bdev_get_queue(bdev); int type = REQ_WRITE | REQ_DISCARD; + unsigned int granularity; + int alignment; struct bio_batch bb; struct bio *bio; int ret = 0; @@ -61,6 +56,10 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, if (!blk_queue_discard(q)) return -EOPNOTSUPP; + /* Zero-sector (unknown) and one-sector granularities are the same. */ + granularity = max(q->limits.discard_granularity >> 9, 1U); + alignment = (bdev_discard_alignment(bdev) >> 9) % granularity; + if (flags & BLKDEV_DISCARD_SECURE) { if (!blk_queue_secdiscard(q)) return -EOPNOTSUPP; @@ -74,7 +73,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, blk_start_plug(&plug); while (nr_sects) { unsigned int req_sects; - sector_t end_sect; + sector_t end_sect, tmp; bio = bio_alloc(gfp_mask, 1); if (!bio) { @@ -82,8 +81,22 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, break; } - req_sects = min_t(sector_t, nr_sects, MAX_BIO_SECTORS); + /* Make sure bi_size doesn't overflow */ + req_sects = min_t(sector_t, nr_sects, UINT_MAX >> 9); + + /* + * If splitting a request, and the next starting sector would be + * misaligned, stop the discard at the previous aligned sector. + */ end_sect = sector + req_sects; + tmp = end_sect; + if (req_sects < nr_sects && + sector_div(tmp, granularity) != alignment) { + end_sect = end_sect - alignment; + sector_div(end_sect, granularity); + end_sect = end_sect * granularity + alignment; + req_sects = end_sect - sector; + } bio->bi_iter.bi_sector = sector; bio->bi_end_io = bio_batch_end_io; diff --git a/block/blk-merge.c b/block/blk-merge.c index c4e9c37f3e38..de5716d8e525 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -11,13 +11,16 @@ static struct bio *blk_bio_discard_split(struct request_queue *q, struct bio *bio, - struct bio_set *bs) + struct bio_set *bs, + unsigned *nsegs) { unsigned int max_discard_sectors, granularity; int alignment; sector_t tmp; unsigned split_sectors; + *nsegs = 1; + /* Zero-sector (unknown) and one-sector granularities are the same. */ granularity = max(q->limits.discard_granularity >> 9, 1U); @@ -51,8 +54,11 @@ static struct bio *blk_bio_discard_split(struct request_queue *q, static struct bio *blk_bio_write_same_split(struct request_queue *q, struct bio *bio, - struct bio_set *bs) + struct bio_set *bs, + unsigned *nsegs) { + *nsegs = 1; + if (!q->limits.max_write_same_sectors) return NULL; @@ -64,7 +70,8 @@ static struct bio *blk_bio_write_same_split(struct request_queue *q, static struct bio *blk_bio_segment_split(struct request_queue *q, struct bio *bio, - struct bio_set *bs) + struct bio_set *bs, + unsigned *segs) { struct bio_vec bv, bvprv, *bvprvp = NULL; struct bvec_iter iter; @@ -106,24 +113,35 @@ new_segment: sectors += bv.bv_len >> 9; } + *segs = nsegs; return NULL; split: + *segs = nsegs; return bio_split(bio, sectors, GFP_NOIO, bs); } void blk_queue_split(struct request_queue *q, struct bio **bio, struct bio_set *bs) { - struct bio *split; + struct bio *split, *res; + unsigned nsegs; if ((*bio)->bi_rw & REQ_DISCARD) - split = blk_bio_discard_split(q, *bio, bs); + split = blk_bio_discard_split(q, *bio, bs, &nsegs); else if ((*bio)->bi_rw & REQ_WRITE_SAME) - split = blk_bio_write_same_split(q, *bio, bs); + split = blk_bio_write_same_split(q, *bio, bs, &nsegs); else - split = blk_bio_segment_split(q, *bio, q->bio_split); + split = blk_bio_segment_split(q, *bio, q->bio_split, &nsegs); + + /* physical segments can be figured out during splitting */ + res = split ? split : *bio; + res->bi_phys_segments = nsegs; + bio_set_flag(res, BIO_SEG_VALID); if (split) { + /* there isn't chance to merge the splitted bio */ + split->bi_rw |= REQ_NOMERGE; + bio_chain(split, *bio); generic_make_request(*bio); *bio = split; diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c index 788fffd9b409..6f57a110289c 100644 --- a/block/blk-mq-sysfs.c +++ b/block/blk-mq-sysfs.c @@ -413,12 +413,6 @@ static void blk_mq_sysfs_init(struct request_queue *q) kobject_init(&ctx->kobj, &blk_mq_ctx_ktype); } -/* see blk_register_queue() */ -void blk_mq_finish_init(struct request_queue *q) -{ - percpu_ref_switch_to_percpu(&q->mq_usage_counter); -} - int blk_mq_register_disk(struct gendisk *disk) { struct device *dev = disk_to_dev(disk); diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index ed96474d75cb..a07ca3488d96 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -75,6 +75,10 @@ void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool include_reserve) struct blk_mq_bitmap_tags *bt; int i, wake_index; + /* + * Make sure all changes prior to this are visible from other CPUs. + */ + smp_mb(); bt = &tags->bitmap_tags; wake_index = atomic_read(&bt->wake_index); for (i = 0; i < BT_WAIT_QUEUES; i++) { @@ -264,7 +268,7 @@ static int bt_get(struct blk_mq_alloc_data *data, if (tag != -1) return tag; - if (!(data->gfp & __GFP_WAIT)) + if (!gfpflags_allow_blocking(data->gfp)) return -1; bs = bt_wait_ptr(bt, hctx); @@ -641,6 +645,7 @@ void blk_mq_free_tags(struct blk_mq_tags *tags) { bt_free(&tags->bitmap_tags); bt_free(&tags->breserved_tags); + free_cpumask_var(tags->cpumask); kfree(tags); } diff --git a/block/blk-mq.c b/block/blk-mq.c index 7785ae96267a..694f8703f83c 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -9,6 +9,7 @@ #include <linux/backing-dev.h> #include <linux/bio.h> #include <linux/blkdev.h> +#include <linux/kmemleak.h> #include <linux/mm.h> #include <linux/init.h> #include <linux/slab.h> @@ -77,47 +78,13 @@ static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx, clear_bit(CTX_TO_BIT(hctx, ctx), &bm->word); } -static int blk_mq_queue_enter(struct request_queue *q, gfp_t gfp) -{ - while (true) { - int ret; - - if (percpu_ref_tryget_live(&q->mq_usage_counter)) - return 0; - - if (!(gfp & __GFP_WAIT)) - return -EBUSY; - - ret = wait_event_interruptible(q->mq_freeze_wq, - !atomic_read(&q->mq_freeze_depth) || - blk_queue_dying(q)); - if (blk_queue_dying(q)) - return -ENODEV; - if (ret) - return ret; - } -} - -static void blk_mq_queue_exit(struct request_queue *q) -{ - percpu_ref_put(&q->mq_usage_counter); -} - -static void blk_mq_usage_counter_release(struct percpu_ref *ref) -{ - struct request_queue *q = - container_of(ref, struct request_queue, mq_usage_counter); - - wake_up_all(&q->mq_freeze_wq); -} - void blk_mq_freeze_queue_start(struct request_queue *q) { int freeze_depth; freeze_depth = atomic_inc_return(&q->mq_freeze_depth); if (freeze_depth == 1) { - percpu_ref_kill(&q->mq_usage_counter); + percpu_ref_kill(&q->q_usage_counter); blk_mq_run_hw_queues(q, false); } } @@ -125,18 +92,34 @@ EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_start); static void blk_mq_freeze_queue_wait(struct request_queue *q) { - wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->mq_usage_counter)); + wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter)); } /* * Guarantee no request is in use, so we can change any data structure of * the queue afterward. */ -void blk_mq_freeze_queue(struct request_queue *q) +void blk_freeze_queue(struct request_queue *q) { + /* + * In the !blk_mq case we are only calling this to kill the + * q_usage_counter, otherwise this increases the freeze depth + * and waits for it to return to zero. For this reason there is + * no blk_unfreeze_queue(), and blk_freeze_queue() is not + * exported to drivers as the only user for unfreeze is blk_mq. + */ blk_mq_freeze_queue_start(q); blk_mq_freeze_queue_wait(q); } + +void blk_mq_freeze_queue(struct request_queue *q) +{ + /* + * ...just an alias to keep freeze and unfreeze actions balanced + * in the blk_mq_* namespace + */ + blk_freeze_queue(q); +} EXPORT_SYMBOL_GPL(blk_mq_freeze_queue); void blk_mq_unfreeze_queue(struct request_queue *q) @@ -146,7 +129,7 @@ void blk_mq_unfreeze_queue(struct request_queue *q) freeze_depth = atomic_dec_return(&q->mq_freeze_depth); WARN_ON_ONCE(freeze_depth < 0); if (!freeze_depth) { - percpu_ref_reinit(&q->mq_usage_counter); + percpu_ref_reinit(&q->q_usage_counter); wake_up_all(&q->mq_freeze_wq); } } @@ -255,17 +238,17 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp, struct blk_mq_alloc_data alloc_data; int ret; - ret = blk_mq_queue_enter(q, gfp); + ret = blk_queue_enter(q, gfp); if (ret) return ERR_PTR(ret); ctx = blk_mq_get_ctx(q); hctx = q->mq_ops->map_queue(q, ctx->cpu); - blk_mq_set_alloc_data(&alloc_data, q, gfp & ~__GFP_WAIT, + blk_mq_set_alloc_data(&alloc_data, q, gfp & ~__GFP_DIRECT_RECLAIM, reserved, ctx, hctx); rq = __blk_mq_alloc_request(&alloc_data, rw); - if (!rq && (gfp & __GFP_WAIT)) { + if (!rq && (gfp & __GFP_DIRECT_RECLAIM)) { __blk_mq_run_hw_queue(hctx); blk_mq_put_ctx(ctx); @@ -278,7 +261,7 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp, } blk_mq_put_ctx(ctx); if (!rq) { - blk_mq_queue_exit(q); + blk_queue_exit(q); return ERR_PTR(-EWOULDBLOCK); } return rq; @@ -297,7 +280,7 @@ static void __blk_mq_free_request(struct blk_mq_hw_ctx *hctx, clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags); blk_mq_put_tag(hctx, tag, &ctx->last_tag); - blk_mq_queue_exit(q); + blk_queue_exit(q); } void blk_mq_free_hctx_request(struct blk_mq_hw_ctx *hctx, struct request *rq) @@ -989,18 +972,25 @@ void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs) } EXPORT_SYMBOL(blk_mq_delay_queue); -static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, - struct request *rq, bool at_head) +static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx, + struct blk_mq_ctx *ctx, + struct request *rq, + bool at_head) { - struct blk_mq_ctx *ctx = rq->mq_ctx; - trace_block_rq_insert(hctx->queue, rq); if (at_head) list_add(&rq->queuelist, &ctx->rq_list); else list_add_tail(&rq->queuelist, &ctx->rq_list); +} + +static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, + struct request *rq, bool at_head) +{ + struct blk_mq_ctx *ctx = rq->mq_ctx; + __blk_mq_insert_req_list(hctx, ctx, rq, at_head); blk_mq_hctx_mark_pending(hctx, ctx); } @@ -1056,8 +1046,9 @@ static void blk_mq_insert_requests(struct request_queue *q, rq = list_first_entry(list, struct request, queuelist); list_del_init(&rq->queuelist); rq->mq_ctx = ctx; - __blk_mq_insert_request(hctx, rq, false); + __blk_mq_insert_req_list(hctx, ctx, rq, false); } + blk_mq_hctx_mark_pending(hctx, ctx); spin_unlock(&ctx->lock); blk_mq_run_hw_queue(hctx, from_schedule); @@ -1139,7 +1130,7 @@ static inline bool blk_mq_merge_queue_io(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx, struct request *rq, struct bio *bio) { - if (!hctx_allow_merges(hctx)) { + if (!hctx_allow_merges(hctx) || !bio_mergeable(bio)) { blk_mq_bio_to_request(rq, bio); spin_lock(&ctx->lock); insert_rq: @@ -1176,11 +1167,7 @@ static struct request *blk_mq_map_request(struct request_queue *q, int rw = bio_data_dir(bio); struct blk_mq_alloc_data alloc_data; - if (unlikely(blk_mq_queue_enter(q, GFP_KERNEL))) { - bio_io_error(bio); - return NULL; - } - + blk_queue_enter_live(q); ctx = blk_mq_get_ctx(q); hctx = q->mq_ops->map_queue(q, ctx->cpu); @@ -1199,7 +1186,7 @@ static struct request *blk_mq_map_request(struct request_queue *q, ctx = blk_mq_get_ctx(q); hctx = q->mq_ops->map_queue(q, ctx->cpu); blk_mq_set_alloc_data(&alloc_data, q, - __GFP_WAIT|GFP_ATOMIC, false, ctx, hctx); + __GFP_RECLAIM|__GFP_HIGH, false, ctx, hctx); rq = __blk_mq_alloc_request(&alloc_data, rw); ctx = alloc_data.ctx; hctx = alloc_data.hctx; @@ -1267,9 +1254,12 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio) blk_queue_split(q, &bio, q->bio_split); - if (!is_flush_fua && !blk_queue_nomerges(q) && - blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq)) - return; + if (!is_flush_fua && !blk_queue_nomerges(q)) { + if (blk_attempt_plug_merge(q, bio, &request_count, + &same_queue_rq)) + return; + } else + request_count = blk_plug_queued_count(q); rq = blk_mq_map_request(q, bio, &data); if (unlikely(!rq)) @@ -1376,7 +1366,7 @@ static void blk_sq_make_request(struct request_queue *q, struct bio *bio) plug = current->plug; if (plug) { blk_mq_bio_to_request(rq, bio); - if (list_empty(&plug->mq_list)) + if (!request_count) trace_block_plug(q); else if (request_count >= BLK_MAX_REQUEST_COUNT) { blk_flush_plug_list(plug, false); @@ -1430,6 +1420,11 @@ static void blk_mq_free_rq_map(struct blk_mq_tag_set *set, while (!list_empty(&tags->page_list)) { page = list_first_entry(&tags->page_list, struct page, lru); list_del_init(&page->lru); + /* + * Remove kmemleak object previously allocated in + * blk_mq_init_rq_map(). + */ + kmemleak_free(page_address(page)); __free_pages(page, page->private); } @@ -1502,6 +1497,11 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set, list_add_tail(&page->lru, &tags->page_list); p = page_address(page); + /* + * Allow kmemleak to scan these pages as they contain pointers + * to additional allocations like via ops->init_request(). + */ + kmemleak_alloc(p, order_to_size(this_order), 1, GFP_KERNEL); entries_per_page = order_to_size(this_order) / rq_size; to_do = min(entries_per_page, set->queue_depth - i); left -= to_do * rq_size; @@ -1673,7 +1673,7 @@ static int blk_mq_init_hctx(struct request_queue *q, INIT_LIST_HEAD(&hctx->dispatch); hctx->queue = q; hctx->queue_num = hctx_idx; - hctx->flags = set->flags; + hctx->flags = set->flags & ~BLK_MQ_F_TAG_SHARED; blk_mq_init_cpu_notifier(&hctx->cpu_notifier, blk_mq_hctx_notify, hctx); @@ -1860,27 +1860,26 @@ static void blk_mq_map_swqueue(struct request_queue *q, } } -static void blk_mq_update_tag_set_depth(struct blk_mq_tag_set *set) +static void queue_set_hctx_shared(struct request_queue *q, bool shared) { struct blk_mq_hw_ctx *hctx; - struct request_queue *q; - bool shared; int i; - if (set->tag_list.next == set->tag_list.prev) - shared = false; - else - shared = true; + queue_for_each_hw_ctx(q, hctx, i) { + if (shared) + hctx->flags |= BLK_MQ_F_TAG_SHARED; + else + hctx->flags &= ~BLK_MQ_F_TAG_SHARED; + } +} + +static void blk_mq_update_tag_set_depth(struct blk_mq_tag_set *set, bool shared) +{ + struct request_queue *q; list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_freeze_queue(q); - - queue_for_each_hw_ctx(q, hctx, i) { - if (shared) - hctx->flags |= BLK_MQ_F_TAG_SHARED; - else - hctx->flags &= ~BLK_MQ_F_TAG_SHARED; - } + queue_set_hctx_shared(q, shared); blk_mq_unfreeze_queue(q); } } @@ -1891,7 +1890,12 @@ static void blk_mq_del_queue_tag_set(struct request_queue *q) mutex_lock(&set->tag_list_lock); list_del_init(&q->tag_set_list); - blk_mq_update_tag_set_depth(set); + if (list_is_singular(&set->tag_list)) { + /* just transitioned to unshared */ + set->flags &= ~BLK_MQ_F_TAG_SHARED; + /* update existing queue */ + blk_mq_update_tag_set_depth(set, false); + } mutex_unlock(&set->tag_list_lock); } @@ -1901,8 +1905,17 @@ static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set, q->tag_set = set; mutex_lock(&set->tag_list_lock); + + /* Check to see if we're transitioning to shared (from 1 to 2 queues). */ + if (!list_empty(&set->tag_list) && !(set->flags & BLK_MQ_F_TAG_SHARED)) { + set->flags |= BLK_MQ_F_TAG_SHARED; + /* update existing queue */ + blk_mq_update_tag_set_depth(set, true); + } + if (set->flags & BLK_MQ_F_TAG_SHARED) + queue_set_hctx_shared(q, true); list_add_tail(&q->tag_set_list, &set->tag_list); - blk_mq_update_tag_set_depth(set); + mutex_unlock(&set->tag_list_lock); } @@ -1989,14 +2002,6 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, hctxs[i]->queue_num = i; } - /* - * Init percpu_ref in atomic mode so that it's faster to shutdown. - * See blk_register_queue() for details. - */ - if (percpu_ref_init(&q->mq_usage_counter, blk_mq_usage_counter_release, - PERCPU_REF_INIT_ATOMIC, GFP_KERNEL)) - goto err_hctxs; - setup_timer(&q->timeout, blk_mq_rq_timer, (unsigned long) q); blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30 * HZ); @@ -2077,8 +2082,6 @@ void blk_mq_free_queue(struct request_queue *q) blk_mq_exit_hw_queues(q, set, set->nr_hw_queues); blk_mq_free_hw_queues(q, set); - - percpu_ref_exit(&q->mq_usage_counter); } /* Basically redo blk_mq_init_queue with queue frozen */ @@ -2296,10 +2299,8 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set) int i; for (i = 0; i < set->nr_hw_queues; i++) { - if (set->tags[i]) { + if (set->tags[i]) blk_mq_free_rq_map(set, set->tags[i], i); - free_cpumask_var(set->tags[i]->cpumask); - } } kfree(set->tags); diff --git a/block/blk-mq.h b/block/blk-mq.h index f4fea7964910..b44dce165761 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -29,8 +29,6 @@ void __blk_mq_complete_request(struct request *rq); void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_freeze_queue(struct request_queue *q); void blk_mq_free_queue(struct request_queue *q); -void blk_mq_clone_flush_request(struct request *flush_rq, - struct request *orig_rq); int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr); void blk_mq_wake_waiters(struct request_queue *q); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 3e44a9da2a13..31849e328b45 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -540,6 +540,7 @@ static void blk_release_queue(struct kobject *kobj) struct request_queue *q = container_of(kobj, struct request_queue, kobj); + bdi_exit(&q->backing_dev_info); blkcg_exit_queue(q); if (q->elevator) { @@ -599,9 +600,8 @@ int blk_register_queue(struct gendisk *disk) */ if (!blk_queue_init_done(q)) { queue_flag_set_unlocked(QUEUE_FLAG_INIT_DONE, q); + percpu_ref_switch_to_percpu(&q->q_usage_counter); blk_queue_bypass_end(q); - if (q->mq_ops) - blk_mq_finish_init(q); } ret = blk_trace_init_sysfs(dev); diff --git a/block/blk-throttle.c b/block/blk-throttle.c index c75a2636dd40..2149a1ddbacf 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -369,7 +369,7 @@ static void throtl_pd_init(struct blkg_policy_data *pd) * regardless of the position of the group in the hierarchy. */ sq->parent_sq = &td->service_queue; - if (cgroup_on_dfl(blkg->blkcg->css.cgroup) && blkg->parent) + if (cgroup_subsys_on_dfl(io_cgrp_subsys) && blkg->parent) sq->parent_sq = &blkg_to_tg(blkg->parent)->service_queue; tg->td = td; } diff --git a/block/blk.h b/block/blk.h index 98614ad37c81..da722eb786df 100644 --- a/block/blk.h +++ b/block/blk.h @@ -72,6 +72,28 @@ void blk_dequeue_request(struct request *rq); void __blk_queue_free_tags(struct request_queue *q); bool __blk_end_bidi_request(struct request *rq, int error, unsigned int nr_bytes, unsigned int bidi_bytes); +int blk_queue_enter(struct request_queue *q, gfp_t gfp); +void blk_queue_exit(struct request_queue *q); +void blk_freeze_queue(struct request_queue *q); + +static inline void blk_queue_enter_live(struct request_queue *q) +{ + /* + * Given that running in generic_make_request() context + * guarantees that a live reference against q_usage_counter has + * been established, further references under that same context + * need not check that the queue has been frozen (marked dead). + */ + percpu_ref_get(&q->q_usage_counter); +} + +#ifdef CONFIG_BLK_DEV_INTEGRITY +void blk_flush_integrity(void); +#else +static inline void blk_flush_integrity(void) +{ +} +#endif void blk_rq_timed_out_timer(unsigned long data); unsigned long blk_rq_timeout(unsigned long timeout); @@ -86,6 +108,7 @@ bool bio_attempt_back_merge(struct request_queue *q, struct request *req, bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio, unsigned int *request_count, struct request **same_queue_rq); +unsigned int blk_plug_queued_count(struct request_queue *q); void blk_account_io_start(struct request *req, bool new_io); void blk_account_io_completion(struct request *req, unsigned int bytes); diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 04de88463a98..1f9093e901da 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -1581,7 +1581,7 @@ static struct blkcg_policy_data *cfq_cpd_alloc(gfp_t gfp) static void cfq_cpd_init(struct blkcg_policy_data *cpd) { struct cfq_group_data *cgd = cpd_to_cfqgd(cpd); - unsigned int weight = cgroup_on_dfl(blkcg_root.css.cgroup) ? + unsigned int weight = cgroup_subsys_on_dfl(io_cgrp_subsys) ? CGROUP_WEIGHT_DFL : CFQ_WEIGHT_LEGACY_DFL; if (cpd_to_blkcg(cpd) == &blkcg_root) @@ -1599,7 +1599,7 @@ static void cfq_cpd_free(struct blkcg_policy_data *cpd) static void cfq_cpd_bind(struct blkcg_policy_data *cpd) { struct blkcg *blkcg = cpd_to_blkcg(cpd); - bool on_dfl = cgroup_on_dfl(blkcg_root.css.cgroup); + bool on_dfl = cgroup_subsys_on_dfl(io_cgrp_subsys); unsigned int weight = on_dfl ? CGROUP_WEIGHT_DFL : CFQ_WEIGHT_LEGACY_DFL; if (blkcg == &blkcg_root) diff --git a/block/elevator.c b/block/elevator.c index 84d63943f2de..c3555c9c672f 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -420,7 +420,7 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio) * noxmerges: Only simple one-hit cache try * merges: All merge tries attempted */ - if (blk_queue_nomerges(q)) + if (blk_queue_nomerges(q) || !bio_mergeable(bio)) return ELEVATOR_NO_MERGE; /* diff --git a/block/genhd.c b/block/genhd.c index 0c706f33a599..e5cafa51567c 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -630,6 +630,7 @@ void add_disk(struct gendisk *disk) WARN_ON(retval); disk_add_events(disk); + blk_integrity_add(disk); } EXPORT_SYMBOL(add_disk); @@ -638,6 +639,7 @@ void del_gendisk(struct gendisk *disk) struct disk_part_iter piter; struct hd_struct *part; + blk_integrity_del(disk); disk_del_events(disk); /* invalidate stuff */ diff --git a/block/ioctl.c b/block/ioctl.c index 8061eba42887..0918aed2d847 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -7,6 +7,7 @@ #include <linux/backing-dev.h> #include <linux/fs.h> #include <linux/blktrace_api.h> +#include <linux/pr.h> #include <asm/uaccess.h> static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user *arg) @@ -193,10 +194,20 @@ int blkdev_reread_part(struct block_device *bdev) } EXPORT_SYMBOL(blkdev_reread_part); -static int blk_ioctl_discard(struct block_device *bdev, uint64_t start, - uint64_t len, int secure) +static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode, + unsigned long arg, unsigned long flags) { - unsigned long flags = 0; + uint64_t range[2]; + uint64_t start, len; + + if (!(mode & FMODE_WRITE)) + return -EBADF; + + if (copy_from_user(range, (void __user *)arg, sizeof(range))) + return -EFAULT; + + start = range[0]; + len = range[1]; if (start & 511) return -EINVAL; @@ -207,14 +218,24 @@ static int blk_ioctl_discard(struct block_device *bdev, uint64_t start, if (start + len > (i_size_read(bdev->bd_inode) >> 9)) return -EINVAL; - if (secure) - flags |= BLKDEV_DISCARD_SECURE; return blkdev_issue_discard(bdev, start, len, GFP_KERNEL, flags); } -static int blk_ioctl_zeroout(struct block_device *bdev, uint64_t start, - uint64_t len) +static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode, + unsigned long arg) { + uint64_t range[2]; + uint64_t start, len; + + if (!(mode & FMODE_WRITE)) + return -EBADF; + + if (copy_from_user(range, (void __user *)arg, sizeof(range))) + return -EFAULT; + + start = range[0]; + len = range[1]; + if (start & 511) return -EINVAL; if (len & 511) @@ -275,6 +296,96 @@ int __blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode, */ EXPORT_SYMBOL_GPL(__blkdev_driver_ioctl); +static int blkdev_pr_register(struct block_device *bdev, + struct pr_registration __user *arg) +{ + const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; + struct pr_registration reg; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + if (!ops || !ops->pr_register) + return -EOPNOTSUPP; + if (copy_from_user(®, arg, sizeof(reg))) + return -EFAULT; + + if (reg.flags & ~PR_FL_IGNORE_KEY) + return -EOPNOTSUPP; + return ops->pr_register(bdev, reg.old_key, reg.new_key, reg.flags); +} + +static int blkdev_pr_reserve(struct block_device *bdev, + struct pr_reservation __user *arg) +{ + const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; + struct pr_reservation rsv; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + if (!ops || !ops->pr_reserve) + return -EOPNOTSUPP; + if (copy_from_user(&rsv, arg, sizeof(rsv))) + return -EFAULT; + + if (rsv.flags & ~PR_FL_IGNORE_KEY) + return -EOPNOTSUPP; + return ops->pr_reserve(bdev, rsv.key, rsv.type, rsv.flags); +} + +static int blkdev_pr_release(struct block_device *bdev, + struct pr_reservation __user *arg) +{ + const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; + struct pr_reservation rsv; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + if (!ops || !ops->pr_release) + return -EOPNOTSUPP; + if (copy_from_user(&rsv, arg, sizeof(rsv))) + return -EFAULT; + + if (rsv.flags) + return -EOPNOTSUPP; + return ops->pr_release(bdev, rsv.key, rsv.type); +} + +static int blkdev_pr_preempt(struct block_device *bdev, + struct pr_preempt __user *arg, bool abort) +{ + const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; + struct pr_preempt p; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + if (!ops || !ops->pr_preempt) + return -EOPNOTSUPP; + if (copy_from_user(&p, arg, sizeof(p))) + return -EFAULT; + + if (p.flags) + return -EOPNOTSUPP; + return ops->pr_preempt(bdev, p.old_key, p.new_key, p.type, abort); +} + +static int blkdev_pr_clear(struct block_device *bdev, + struct pr_clear __user *arg) +{ + const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; + struct pr_clear c; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + if (!ops || !ops->pr_clear) + return -EOPNOTSUPP; + if (copy_from_user(&c, arg, sizeof(c))) + return -EFAULT; + + if (c.flags) + return -EOPNOTSUPP; + return ops->pr_clear(bdev, c.key); +} + /* * Is it an unrecognized ioctl? The correct returns are either * ENOTTY (final) or ENOIOCTLCMD ("I don't know this one, try a @@ -295,89 +406,115 @@ static inline int is_unrecognized_ioctl(int ret) ret == -ENOIOCTLCMD; } -/* - * always keep this in sync with compat_blkdev_ioctl() - */ -int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, - unsigned long arg) +static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode, + unsigned cmd, unsigned long arg) { - struct gendisk *disk = bdev->bd_disk; - struct backing_dev_info *bdi; - loff_t size; - int ret, n; - unsigned int max_sectors; + int ret; - switch(cmd) { - case BLKFLSBUF: - if (!capable(CAP_SYS_ADMIN)) - return -EACCES; - - ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg); - if (!is_unrecognized_ioctl(ret)) - return ret; + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; - fsync_bdev(bdev); - invalidate_bdev(bdev); - return 0; + ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg); + if (!is_unrecognized_ioctl(ret)) + return ret; - case BLKROSET: - ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg); - if (!is_unrecognized_ioctl(ret)) - return ret; - if (!capable(CAP_SYS_ADMIN)) - return -EACCES; - if (get_user(n, (int __user *)(arg))) - return -EFAULT; - set_device_ro(bdev, n); - return 0; + fsync_bdev(bdev); + invalidate_bdev(bdev); + return 0; +} - case BLKDISCARD: - case BLKSECDISCARD: { - uint64_t range[2]; +static int blkdev_roset(struct block_device *bdev, fmode_t mode, + unsigned cmd, unsigned long arg) +{ + int ret, n; - if (!(mode & FMODE_WRITE)) - return -EBADF; + ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg); + if (!is_unrecognized_ioctl(ret)) + return ret; + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + if (get_user(n, (int __user *)arg)) + return -EFAULT; + set_device_ro(bdev, n); + return 0; +} - if (copy_from_user(range, (void __user *)arg, sizeof(range))) - return -EFAULT; +static int blkdev_getgeo(struct block_device *bdev, + struct hd_geometry __user *argp) +{ + struct gendisk *disk = bdev->bd_disk; + struct hd_geometry geo; + int ret; - return blk_ioctl_discard(bdev, range[0], range[1], - cmd == BLKSECDISCARD); - } - case BLKZEROOUT: { - uint64_t range[2]; + if (!argp) + return -EINVAL; + if (!disk->fops->getgeo) + return -ENOTTY; + + /* + * We need to set the startsect first, the driver may + * want to override it. + */ + memset(&geo, 0, sizeof(geo)); + geo.start = get_start_sect(bdev); + ret = disk->fops->getgeo(bdev, &geo); + if (ret) + return ret; + if (copy_to_user(argp, &geo, sizeof(geo))) + return -EFAULT; + return 0; +} - if (!(mode & FMODE_WRITE)) - return -EBADF; +/* set the logical block size */ +static int blkdev_bszset(struct block_device *bdev, fmode_t mode, + int __user *argp) +{ + int ret, n; - if (copy_from_user(range, (void __user *)arg, sizeof(range))) - return -EFAULT; + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + if (!argp) + return -EINVAL; + if (get_user(n, argp)) + return -EFAULT; - return blk_ioctl_zeroout(bdev, range[0], range[1]); + if (!(mode & FMODE_EXCL)) { + bdgrab(bdev); + if (blkdev_get(bdev, mode | FMODE_EXCL, &bdev) < 0) + return -EBUSY; } - case HDIO_GETGEO: { - struct hd_geometry geo; + ret = set_blocksize(bdev, n); + if (!(mode & FMODE_EXCL)) + blkdev_put(bdev, mode | FMODE_EXCL); + return ret; +} - if (!arg) - return -EINVAL; - if (!disk->fops->getgeo) - return -ENOTTY; - - /* - * We need to set the startsect first, the driver may - * want to override it. - */ - memset(&geo, 0, sizeof(geo)); - geo.start = get_start_sect(bdev); - ret = disk->fops->getgeo(bdev, &geo); - if (ret) - return ret; - if (copy_to_user((struct hd_geometry __user *)arg, &geo, - sizeof(geo))) - return -EFAULT; - return 0; - } +/* + * always keep this in sync with compat_blkdev_ioctl() + */ +int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, + unsigned long arg) +{ + struct backing_dev_info *bdi; + void __user *argp = (void __user *)arg; + loff_t size; + unsigned int max_sectors; + + switch (cmd) { + case BLKFLSBUF: + return blkdev_flushbuf(bdev, mode, cmd, arg); + case BLKROSET: + return blkdev_roset(bdev, mode, cmd, arg); + case BLKDISCARD: + return blk_ioctl_discard(bdev, mode, arg, 0); + case BLKSECDISCARD: + return blk_ioctl_discard(bdev, mode, arg, + BLKDEV_DISCARD_SECURE); + case BLKZEROOUT: + return blk_ioctl_zeroout(bdev, mode, arg); + case HDIO_GETGEO: + return blkdev_getgeo(bdev, argp); case BLKRAGET: case BLKFRAGET: if (!arg) @@ -414,28 +551,11 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, bdi->ra_pages = (arg * 512) / PAGE_CACHE_SIZE; return 0; case BLKBSZSET: - /* set the logical block size */ - if (!capable(CAP_SYS_ADMIN)) - return -EACCES; - if (!arg) - return -EINVAL; - if (get_user(n, (int __user *) arg)) - return -EFAULT; - if (!(mode & FMODE_EXCL)) { - bdgrab(bdev); - if (blkdev_get(bdev, mode | FMODE_EXCL, &bdev) < 0) - return -EBUSY; - } - ret = set_blocksize(bdev, n); - if (!(mode & FMODE_EXCL)) - blkdev_put(bdev, mode | FMODE_EXCL); - return ret; + return blkdev_bszset(bdev, mode, argp); case BLKPG: - ret = blkpg_ioctl(bdev, (struct blkpg_ioctl_arg __user *) arg); - break; + return blkpg_ioctl(bdev, argp); case BLKRRPART: - ret = blkdev_reread_part(bdev); - break; + return blkdev_reread_part(bdev); case BLKGETSIZE: size = i_size_read(bdev->bd_inode); if ((size >> 9) > ~0UL) @@ -447,11 +567,21 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, case BLKTRACESTOP: case BLKTRACESETUP: case BLKTRACETEARDOWN: - ret = blk_trace_ioctl(bdev, cmd, (char __user *) arg); - break; + return blk_trace_ioctl(bdev, cmd, argp); + case IOC_PR_REGISTER: + return blkdev_pr_register(bdev, argp); + case IOC_PR_RESERVE: + return blkdev_pr_reserve(bdev, argp); + case IOC_PR_RELEASE: + return blkdev_pr_release(bdev, argp); + case IOC_PR_PREEMPT: + return blkdev_pr_preempt(bdev, argp, false); + case IOC_PR_PREEMPT_ABORT: + return blkdev_pr_preempt(bdev, argp, true); + case IOC_PR_CLEAR: + return blkdev_pr_clear(bdev, argp); default: - ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg); + return __blkdev_driver_ioctl(bdev, mode, cmd, arg); } - return ret; } EXPORT_SYMBOL_GPL(blkdev_ioctl); diff --git a/block/ioprio.c b/block/ioprio.c index 31666c92b46a..cc7800e9eb44 100644 --- a/block/ioprio.c +++ b/block/ioprio.c @@ -123,7 +123,8 @@ SYSCALL_DEFINE3(ioprio_set, int, which, int, who, int, ioprio) break; do_each_thread(g, p) { - if (!uid_eq(task_uid(p), uid)) + if (!uid_eq(task_uid(p), uid) || + !task_pid_vnr(p)) continue; ret = set_task_ioprio(p, ioprio); if (ret) @@ -220,7 +221,8 @@ SYSCALL_DEFINE2(ioprio_get, int, which, int, who) break; do_each_thread(g, p) { - if (!uid_eq(task_uid(p), user->uid)) + if (!uid_eq(task_uid(p), user->uid) || + !task_pid_vnr(p)) continue; tmpio = get_task_ioprio(p); if (tmpio < 0) diff --git a/block/partition-generic.c b/block/partition-generic.c index e7711133284e..3b030157ec85 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -428,6 +428,7 @@ rescan: if (disk->fops->revalidate_disk) disk->fops->revalidate_disk(disk); + blk_integrity_revalidate(disk); check_disk_size_change(disk, bdev); bdev->bd_invalidated = 0; if (!get_capacity(disk) || !(state = check_partition(disk, bdev))) diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index dda653ce7b24..0774799942e0 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -444,7 +444,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode, } - rq = blk_get_request(q, in_len ? WRITE : READ, __GFP_WAIT); + rq = blk_get_request(q, in_len ? WRITE : READ, __GFP_RECLAIM); if (IS_ERR(rq)) { err = PTR_ERR(rq); goto error_free_buffer; @@ -495,7 +495,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode, break; } - if (bytes && blk_rq_map_kern(q, rq, buffer, bytes, __GFP_WAIT)) { + if (bytes && blk_rq_map_kern(q, rq, buffer, bytes, __GFP_RECLAIM)) { err = DRIVER_ERROR << 24; goto error; } @@ -536,7 +536,7 @@ static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk, struct request *rq; int err; - rq = blk_get_request(q, WRITE, __GFP_WAIT); + rq = blk_get_request(q, WRITE, __GFP_RECLAIM); if (IS_ERR(rq)) return PTR_ERR(rq); blk_rq_set_block_pc(rq); diff --git a/block/t10-pi.c b/block/t10-pi.c index 24d6e9715318..2c97912335a9 100644 --- a/block/t10-pi.c +++ b/block/t10-pi.c @@ -160,38 +160,30 @@ static int t10_pi_type3_verify_ip(struct blk_integrity_iter *iter) return t10_pi_verify(iter, t10_pi_ip_fn, 3); } -struct blk_integrity t10_pi_type1_crc = { +struct blk_integrity_profile t10_pi_type1_crc = { .name = "T10-DIF-TYPE1-CRC", .generate_fn = t10_pi_type1_generate_crc, .verify_fn = t10_pi_type1_verify_crc, - .tuple_size = sizeof(struct t10_pi_tuple), - .tag_size = 0, }; EXPORT_SYMBOL(t10_pi_type1_crc); -struct blk_integrity t10_pi_type1_ip = { +struct blk_integrity_profile t10_pi_type1_ip = { .name = "T10-DIF-TYPE1-IP", .generate_fn = t10_pi_type1_generate_ip, .verify_fn = t10_pi_type1_verify_ip, - .tuple_size = sizeof(struct t10_pi_tuple), - .tag_size = 0, }; EXPORT_SYMBOL(t10_pi_type1_ip); -struct blk_integrity t10_pi_type3_crc = { +struct blk_integrity_profile t10_pi_type3_crc = { .name = "T10-DIF-TYPE3-CRC", .generate_fn = t10_pi_type3_generate_crc, .verify_fn = t10_pi_type3_verify_crc, - .tuple_size = sizeof(struct t10_pi_tuple), - .tag_size = 0, }; EXPORT_SYMBOL(t10_pi_type3_crc); -struct blk_integrity t10_pi_type3_ip = { +struct blk_integrity_profile t10_pi_type3_ip = { .name = "T10-DIF-TYPE3-IP", .generate_fn = t10_pi_type3_generate_ip, .verify_fn = t10_pi_type3_verify_ip, - .tuple_size = sizeof(struct t10_pi_tuple), - .tag_size = 0, }; EXPORT_SYMBOL(t10_pi_type3_ip); |