diff options
Diffstat (limited to 'block')
56 files changed, 2724 insertions, 1977 deletions
diff --git a/block/Kconfig b/block/Kconfig index 5b623b876d3b..15027963472d 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -63,7 +63,7 @@ config BLK_DEV_BSGLIB config BLK_DEV_INTEGRITY bool "Block layer data integrity support" select CRC_T10DIF - select CRC64_ROCKSOFT + select CRC64 help Some storage devices allow extra information to be stored/retrieved to help protect the data. The block layer @@ -211,14 +211,6 @@ config BLK_INLINE_ENCRYPTION_FALLBACK source "block/partitions/Kconfig" -config BLK_MQ_PCI - def_bool PCI - -config BLK_MQ_VIRTIO - bool - depends on VIRTIO - default y - config BLK_PM def_bool PM diff --git a/block/Makefile b/block/Makefile index 33748123710b..c65f4da93702 100644 --- a/block/Makefile +++ b/block/Makefile @@ -5,13 +5,12 @@ obj-y := bdev.o fops.o bio.o elevator.o blk-core.o blk-sysfs.o \ blk-flush.o blk-settings.o blk-ioc.o blk-map.o \ - blk-merge.o blk-timeout.o \ - blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \ + blk-merge.o blk-timeout.o blk-lib.o blk-mq.o \ + blk-mq-tag.o blk-mq-dma.o blk-stat.o \ blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \ genhd.o ioprio.o badblocks.o partitions/ blk-rq-qos.o \ disk-events.o blk-ia-ranges.o early-lookup.o -obj-$(CONFIG_BOUNCE) += bounce.o obj-$(CONFIG_BLK_DEV_BSG_COMMON) += bsg.o obj-$(CONFIG_BLK_DEV_BSGLIB) += bsg-lib.o obj-$(CONFIG_BLK_CGROUP) += blk-cgroup.o @@ -26,7 +25,8 @@ obj-$(CONFIG_MQ_IOSCHED_KYBER) += kyber-iosched.o bfq-y := bfq-iosched.o bfq-wf2q.o bfq-cgroup.o obj-$(CONFIG_IOSCHED_BFQ) += bfq.o -obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o t10-pi.o +obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o t10-pi.o \ + bio-integrity-auto.o obj-$(CONFIG_BLK_DEV_ZONED) += blk-zoned.o obj-$(CONFIG_BLK_WBT) += blk-wbt.o obj-$(CONFIG_BLK_DEBUG_FS) += blk-mq-debugfs.o diff --git a/block/badblocks.c b/block/badblocks.c index dc147c017961..ece64e76fe8f 100644 --- a/block/badblocks.c +++ b/block/badblocks.c @@ -905,39 +905,35 @@ re_insert: goto update_sectors; } + if (can_merge_front(bb, prev, &bad)) { + len = front_merge(bb, prev, &bad); + added++; + hint = prev; + goto update_sectors; + } + if (overlap_front(bb, prev, &bad)) { - if (can_merge_front(bb, prev, &bad)) { - len = front_merge(bb, prev, &bad); - added++; - } else { - int extra = 0; + int extra = 0; - if (!can_front_overwrite(bb, prev, &bad, &extra)) { - if (extra > 0) - goto out; + if (!can_front_overwrite(bb, prev, &bad, &extra)) { + if (extra > 0) + goto out; - len = min_t(sector_t, - BB_END(p[prev]) - s, sectors); - hint = prev; - goto update_sectors; - } + len = min_t(sector_t, + BB_END(p[prev]) - s, sectors); + hint = prev; + goto update_sectors; + } - len = front_overwrite(bb, prev, &bad, extra); - added++; - bb->count += extra; + len = front_overwrite(bb, prev, &bad, extra); + added++; + bb->count += extra; - if (can_combine_front(bb, prev, &bad)) { - front_combine(bb, prev); - bb->count--; - } + if (can_combine_front(bb, prev, &bad)) { + front_combine(bb, prev); + bb->count--; } - hint = prev; - goto update_sectors; - } - if (can_merge_front(bb, prev, &bad)) { - len = front_merge(bb, prev, &bad); - added++; hint = prev; goto update_sectors; } @@ -1246,14 +1242,15 @@ re_check: len = sectors; update_sectors: + /* This situation should never happen */ + WARN_ON(sectors < len); + s += len; sectors -= len; if (sectors > 0) goto re_check; - WARN_ON(sectors < 0); - if (unacked_badblocks > 0) rv = -1; else if (acked_badblocks > 0) diff --git a/block/bdev.c b/block/bdev.c index 9d73a8fbf7f9..b77ddd12dc06 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -148,28 +148,69 @@ static void set_init_blocksize(struct block_device *bdev) bsize <<= 1; } BD_INODE(bdev)->i_blkbits = blksize_bits(bsize); + mapping_set_folio_min_order(BD_INODE(bdev)->i_mapping, + get_order(bsize)); } -int set_blocksize(struct file *file, int size) +/** + * bdev_validate_blocksize - check that this block size is acceptable + * @bdev: blockdevice to check + * @block_size: block size to check + * + * For block device users that do not use buffer heads or the block device + * page cache, make sure that this block size can be used with the device. + * + * Return: On success zero is returned, negative error code on failure. + */ +int bdev_validate_blocksize(struct block_device *bdev, int block_size) { - struct inode *inode = file->f_mapping->host; - struct block_device *bdev = I_BDEV(inode); - - if (blk_validate_block_size(size)) + if (blk_validate_block_size(block_size)) return -EINVAL; /* Size cannot be smaller than the size supported by the device */ - if (size < bdev_logical_block_size(bdev)) + if (block_size < bdev_logical_block_size(bdev)) return -EINVAL; + return 0; +} +EXPORT_SYMBOL_GPL(bdev_validate_blocksize); + +int set_blocksize(struct file *file, int size) +{ + struct inode *inode = file->f_mapping->host; + struct block_device *bdev = I_BDEV(inode); + int ret; + + ret = bdev_validate_blocksize(bdev, size); + if (ret) + return ret; + if (!file->private_data) return -EINVAL; /* Don't change the size if it is same as current */ if (inode->i_blkbits != blksize_bits(size)) { + /* + * Flush and truncate the pagecache before we reconfigure the + * mapping geometry because folio sizes are variable now. If a + * reader has already allocated a folio whose size is smaller + * than the new min_order but invokes readahead after the new + * min_order becomes visible, readahead will think there are + * "zero" blocks per folio and crash. Take the inode and + * invalidation locks to avoid racing with + * read/write/fallocate. + */ + inode_lock(inode); + filemap_invalidate_lock(inode->i_mapping); + sync_blockdev(bdev); + kill_bdev(bdev); + inode->i_blkbits = blksize_bits(size); + mapping_set_folio_min_order(inode->i_mapping, get_order(size)); kill_bdev(bdev); + filemap_invalidate_unlock(inode->i_mapping); + inode_unlock(inode); } return 0; } @@ -178,10 +219,11 @@ EXPORT_SYMBOL(set_blocksize); int sb_set_blocksize(struct super_block *sb, int size) { + if (!(sb->s_type->fs_flags & FS_LBS) && size > PAGE_SIZE) + return 0; if (set_blocksize(sb->s_bdev_file, size)) return 0; - /* If we get here, we know size is power of two - * and it's value is between 512 and PAGE_SIZE */ + /* If we get here, we know size is validated */ sb->s_blocksize = size; sb->s_blocksize_bits = blksize_bits(size); return sb->s_blocksize; @@ -773,13 +815,13 @@ static void blkdev_put_part(struct block_device *part) blkdev_put_whole(whole); } -struct block_device *blkdev_get_no_open(dev_t dev) +struct block_device *blkdev_get_no_open(dev_t dev, bool autoload) { struct block_device *bdev; struct inode *inode; inode = ilookup(blockdev_superblock, dev); - if (!inode && IS_ENABLED(CONFIG_BLOCK_LEGACY_AUTOLOAD)) { + if (!inode && autoload && IS_ENABLED(CONFIG_BLOCK_LEGACY_AUTOLOAD)) { blk_request_module(dev); inode = ilookup(blockdev_superblock, dev); if (inode) @@ -1001,7 +1043,7 @@ struct file *bdev_file_open_by_dev(dev_t dev, blk_mode_t mode, void *holder, if (ret) return ERR_PTR(ret); - bdev = blkdev_get_no_open(dev); + bdev = blkdev_get_no_open(dev, true); if (!bdev) return ERR_PTR(-ENXIO); @@ -1268,24 +1310,17 @@ void sync_bdevs(bool wait) /* * Handle STATX_{DIOALIGN, WRITE_ATOMIC} for block devices. */ -void bdev_statx(struct path *path, struct kstat *stat, - u32 request_mask) +void bdev_statx(const struct path *path, struct kstat *stat, u32 request_mask) { - struct inode *backing_inode; struct block_device *bdev; - if (!(request_mask & (STATX_DIOALIGN | STATX_WRITE_ATOMIC))) - return; - - backing_inode = d_backing_inode(path->dentry); - /* - * Note that backing_inode is the inode of a block device node file, - * not the block device's internal inode. Therefore it is *not* valid - * to use I_BDEV() here; the block device has to be looked up by i_rdev + * Note that d_backing_inode() returns the block device node inode, not + * the block device's internal inode. Therefore it is *not* valid to + * use I_BDEV() here; the block device has to be looked up by i_rdev * instead. */ - bdev = blkdev_get_no_open(backing_inode->i_rdev); + bdev = blkdev_get_no_open(d_backing_inode(path->dentry)->i_rdev, false); if (!bdev) return; @@ -1300,9 +1335,12 @@ void bdev_statx(struct path *path, struct kstat *stat, generic_fill_statx_atomic_writes(stat, queue_atomic_write_unit_min_bytes(bd_queue), - queue_atomic_write_unit_max_bytes(bd_queue)); + queue_atomic_write_unit_max_bytes(bd_queue), + 0); } + stat->blksize = bdev_io_min(bdev); + blkdev_put_no_open(bdev); } diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 167542201603..9483c529c958 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -701,17 +701,13 @@ static void bfq_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data) { struct bfq_data *bfqd = data->q->elevator->elevator_data; struct bfq_io_cq *bic = bfq_bic_lookup(data->q); - int depth; - unsigned limit = data->q->nr_requests; - unsigned int act_idx; + unsigned int limit, act_idx; /* Sync reads have full depth available */ - if (op_is_sync(opf) && !op_is_write(opf)) { - depth = 0; - } else { - depth = bfqd->word_depths[!!bfqd->wr_busy_queues][op_is_sync(opf)]; - limit = (limit * depth) >> bfqd->full_depth_shift; - } + if (op_is_sync(opf) && !op_is_write(opf)) + limit = data->q->nr_requests; + else + limit = bfqd->async_depths[!!bfqd->wr_busy_queues][op_is_sync(opf)]; for (act_idx = 0; bic && act_idx < bfqd->num_actuators; act_idx++) { /* Fast path to check if bfqq is already allocated. */ @@ -725,14 +721,16 @@ static void bfq_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data) * available requests and thus starve other entities. */ if (bfqq_request_over_limit(bfqd, bic, opf, act_idx, limit)) { - depth = 1; + limit = 1; break; } } + bfq_log(bfqd, "[%s] wr_busy %d sync %d depth %u", - __func__, bfqd->wr_busy_queues, op_is_sync(opf), depth); - if (depth) - data->shallow_depth = depth; + __func__, bfqd->wr_busy_queues, op_is_sync(opf), limit); + + if (limit < data->q->nr_requests) + data->shallow_depth = limit; } static struct bfq_queue * @@ -7128,9 +7126,8 @@ void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg) */ static void bfq_update_depths(struct bfq_data *bfqd, struct sbitmap_queue *bt) { - unsigned int depth = 1U << bt->sb.shift; + unsigned int nr_requests = bfqd->queue->nr_requests; - bfqd->full_depth_shift = bt->sb.shift; /* * In-word depths if no bfq_queue is being weight-raised: * leaving 25% of tags only for sync reads. @@ -7142,13 +7139,13 @@ static void bfq_update_depths(struct bfq_data *bfqd, struct sbitmap_queue *bt) * limit 'something'. */ /* no more than 50% of tags for async I/O */ - bfqd->word_depths[0][0] = max(depth >> 1, 1U); + bfqd->async_depths[0][0] = max(nr_requests >> 1, 1U); /* * no more than 75% of tags for sync writes (25% extra tags * w.r.t. async I/O, to prevent async I/O from starving sync * writes) */ - bfqd->word_depths[0][1] = max((depth * 3) >> 2, 1U); + bfqd->async_depths[0][1] = max((nr_requests * 3) >> 2, 1U); /* * In-word depths in case some bfq_queue is being weight- @@ -7158,9 +7155,9 @@ static void bfq_update_depths(struct bfq_data *bfqd, struct sbitmap_queue *bt) * shortage. */ /* no more than ~18% of tags for async I/O */ - bfqd->word_depths[1][0] = max((depth * 3) >> 4, 1U); + bfqd->async_depths[1][0] = max((nr_requests * 3) >> 4, 1U); /* no more than ~37% of tags for sync writes (~20% extra tags) */ - bfqd->word_depths[1][1] = max((depth * 6) >> 4, 1U); + bfqd->async_depths[1][1] = max((nr_requests * 6) >> 4, 1U); } static void bfq_depth_updated(struct blk_mq_hw_ctx *hctx) @@ -7210,8 +7207,8 @@ static void bfq_exit_queue(struct elevator_queue *e) #endif blk_stat_disable_accounting(bfqd->queue); - clear_bit(ELEVATOR_FLAG_DISABLE_WBT, &e->flags); - wbt_enable_default(bfqd->queue->disk); + blk_queue_flag_clear(QUEUE_FLAG_DISABLE_WBT_DEF, bfqd->queue); + set_bit(ELEVATOR_FLAG_ENABLE_WBT_ON_EXIT, &e->flags); kfree(bfqd); } @@ -7232,22 +7229,16 @@ static void bfq_init_root_group(struct bfq_group *root_group, root_group->sched_data.bfq_class_idle_last_service = jiffies; } -static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) +static int bfq_init_queue(struct request_queue *q, struct elevator_queue *eq) { struct bfq_data *bfqd; - struct elevator_queue *eq; unsigned int i; struct blk_independent_access_ranges *ia_ranges = q->disk->ia_ranges; - eq = elevator_alloc(q, e); - if (!eq) - return -ENOMEM; - bfqd = kzalloc_node(sizeof(*bfqd), GFP_KERNEL, q->node); - if (!bfqd) { - kobject_put(&eq->kobj); + if (!bfqd) return -ENOMEM; - } + eq->elevator_data = bfqd; spin_lock_irq(&q->queue_lock); @@ -7315,9 +7306,8 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) INIT_LIST_HEAD(&bfqd->dispatch); - hrtimer_init(&bfqd->idle_slice_timer, CLOCK_MONOTONIC, - HRTIMER_MODE_REL); - bfqd->idle_slice_timer.function = bfq_idle_slice_timer; + hrtimer_setup(&bfqd->idle_slice_timer, bfq_idle_slice_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL); bfqd->queue_weights_tree = RB_ROOT_CACHED; #ifdef CONFIG_BFQ_GROUP_IOSCHED @@ -7398,7 +7388,7 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) /* We dispatch from request queue wide instead of hw queue */ blk_queue_flag_set(QUEUE_FLAG_SQ_SCHED, q); - set_bit(ELEVATOR_FLAG_DISABLE_WBT, &eq->flags); + blk_queue_flag_set(QUEUE_FLAG_DISABLE_WBT_DEF, q); wbt_disable_default(q->disk); blk_stat_enable_accounting(q); @@ -7406,7 +7396,6 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) out_free: kfree(bfqd); - kobject_put(&eq->kobj); return -ENOMEM; } diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h index 687a3a7ba784..31217f196f4f 100644 --- a/block/bfq-iosched.h +++ b/block/bfq-iosched.h @@ -813,8 +813,7 @@ struct bfq_data { * Depth limits used in bfq_limit_depth (see comments on the * function) */ - unsigned int word_depths[2][2]; - unsigned int full_depth_shift; + unsigned int async_depths[2][2]; /* * Number of independent actuators. This is equal to 1 in diff --git a/block/bio-integrity-auto.c b/block/bio-integrity-auto.c new file mode 100644 index 000000000000..9c6657664792 --- /dev/null +++ b/block/bio-integrity-auto.c @@ -0,0 +1,223 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2007, 2008, 2009 Oracle Corporation + * Written by: Martin K. Petersen <martin.petersen@oracle.com> + * + * Automatically generate and verify integrity data on PI capable devices if the + * bio submitter didn't provide PI itself. This ensures that kernel verifies + * data integrity even if the file system (or other user of the block device) is + * not aware of PI. + */ +#include <linux/blk-integrity.h> +#include <linux/t10-pi.h> +#include <linux/workqueue.h> +#include "blk.h" + +struct bio_integrity_data { + struct bio *bio; + struct bvec_iter saved_bio_iter; + struct work_struct work; + struct bio_integrity_payload bip; + struct bio_vec bvec; +}; + +static struct kmem_cache *bid_slab; +static mempool_t bid_pool; +static struct workqueue_struct *kintegrityd_wq; + +static void bio_integrity_finish(struct bio_integrity_data *bid) +{ + bid->bio->bi_integrity = NULL; + bid->bio->bi_opf &= ~REQ_INTEGRITY; + kfree(bvec_virt(bid->bip.bip_vec)); + mempool_free(bid, &bid_pool); +} + +static void bio_integrity_verify_fn(struct work_struct *work) +{ + struct bio_integrity_data *bid = + container_of(work, struct bio_integrity_data, work); + struct bio *bio = bid->bio; + + blk_integrity_verify_iter(bio, &bid->saved_bio_iter); + bio_integrity_finish(bid); + bio_endio(bio); +} + +#define BIP_CHECK_FLAGS (BIP_CHECK_GUARD | BIP_CHECK_REFTAG | BIP_CHECK_APPTAG) +static bool bip_should_check(struct bio_integrity_payload *bip) +{ + return bip->bip_flags & BIP_CHECK_FLAGS; +} + +static bool bi_offload_capable(struct blk_integrity *bi) +{ + switch (bi->csum_type) { + case BLK_INTEGRITY_CSUM_CRC64: + return bi->tuple_size == sizeof(struct crc64_pi_tuple); + case BLK_INTEGRITY_CSUM_CRC: + case BLK_INTEGRITY_CSUM_IP: + return bi->tuple_size == sizeof(struct t10_pi_tuple); + default: + pr_warn_once("%s: unknown integrity checksum type:%d\n", + __func__, bi->csum_type); + fallthrough; + case BLK_INTEGRITY_CSUM_NONE: + return false; + } +} + +/** + * __bio_integrity_endio - Integrity I/O completion function + * @bio: Protected bio + * + * Normally I/O completion is done in interrupt context. However, verifying I/O + * integrity is a time-consuming task which must be run in process context. + * + * This function postpones completion accordingly. + */ +bool __bio_integrity_endio(struct bio *bio) +{ + struct bio_integrity_payload *bip = bio_integrity(bio); + struct bio_integrity_data *bid = + container_of(bip, struct bio_integrity_data, bip); + + if (bio_op(bio) == REQ_OP_READ && !bio->bi_status && + bip_should_check(bip)) { + INIT_WORK(&bid->work, bio_integrity_verify_fn); + queue_work(kintegrityd_wq, &bid->work); + return false; + } + + bio_integrity_finish(bid); + return true; +} + +/** + * bio_integrity_prep - Prepare bio for integrity I/O + * @bio: bio to prepare + * + * Checks if the bio already has an integrity payload attached. If it does, the + * payload has been generated by another kernel subsystem, and we just pass it + * through. + * Otherwise allocates integrity payload and for writes the integrity metadata + * will be generated. For reads, the completion handler will verify the + * metadata. + */ +bool bio_integrity_prep(struct bio *bio) +{ + struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk); + struct bio_integrity_data *bid; + bool set_flags = true; + gfp_t gfp = GFP_NOIO; + unsigned int len; + void *buf; + + if (!bi) + return true; + + if (!bio_sectors(bio)) + return true; + + /* Already protected? */ + if (bio_integrity(bio)) + return true; + + switch (bio_op(bio)) { + case REQ_OP_READ: + if (bi->flags & BLK_INTEGRITY_NOVERIFY) { + if (bi_offload_capable(bi)) + return true; + set_flags = false; + } + break; + case REQ_OP_WRITE: + /* + * Zero the memory allocated to not leak uninitialized kernel + * memory to disk for non-integrity metadata where nothing else + * initializes the memory. + */ + if (bi->flags & BLK_INTEGRITY_NOGENERATE) { + if (bi_offload_capable(bi)) + return true; + set_flags = false; + gfp |= __GFP_ZERO; + } else if (bi->csum_type == BLK_INTEGRITY_CSUM_NONE) + gfp |= __GFP_ZERO; + break; + default: + return true; + } + + if (WARN_ON_ONCE(bio_has_crypt_ctx(bio))) + return true; + + /* Allocate kernel buffer for protection data */ + len = bio_integrity_bytes(bi, bio_sectors(bio)); + buf = kmalloc(len, gfp); + if (!buf) + goto err_end_io; + bid = mempool_alloc(&bid_pool, GFP_NOIO); + if (!bid) + goto err_free_buf; + bio_integrity_init(bio, &bid->bip, &bid->bvec, 1); + + bid->bio = bio; + + bid->bip.bip_flags |= BIP_BLOCK_INTEGRITY; + bip_set_seed(&bid->bip, bio->bi_iter.bi_sector); + + if (set_flags) { + if (bi->csum_type == BLK_INTEGRITY_CSUM_IP) + bid->bip.bip_flags |= BIP_IP_CHECKSUM; + if (bi->csum_type) + bid->bip.bip_flags |= BIP_CHECK_GUARD; + if (bi->flags & BLK_INTEGRITY_REF_TAG) + bid->bip.bip_flags |= BIP_CHECK_REFTAG; + } + + if (bio_integrity_add_page(bio, virt_to_page(buf), len, + offset_in_page(buf)) < len) + goto err_end_io; + + /* Auto-generate integrity metadata if this is a write */ + if (bio_data_dir(bio) == WRITE && bip_should_check(&bid->bip)) + blk_integrity_generate(bio); + else + bid->saved_bio_iter = bio->bi_iter; + return true; + +err_free_buf: + kfree(buf); +err_end_io: + bio->bi_status = BLK_STS_RESOURCE; + bio_endio(bio); + return false; +} +EXPORT_SYMBOL(bio_integrity_prep); + +void blk_flush_integrity(void) +{ + flush_workqueue(kintegrityd_wq); +} + +static int __init blk_integrity_auto_init(void) +{ + bid_slab = kmem_cache_create("bio_integrity_data", + sizeof(struct bio_integrity_data), 0, + SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); + + if (mempool_init_slab_pool(&bid_pool, BIO_POOL_SIZE, bid_slab)) + panic("bio: can't create integrity pool\n"); + + /* + * kintegrityd won't block much but may burn a lot of CPU cycles. + * Make it highpri CPU intensive wq with max concurrency of 1. + */ + kintegrityd_wq = alloc_workqueue("kintegrityd", WQ_MEM_RECLAIM | + WQ_HIGHPRI | WQ_CPU_INTENSIVE, 1); + if (!kintegrityd_wq) + panic("Failed to create kintegrityd\n"); + return 0; +} +subsys_initcall(blk_integrity_auto_init); diff --git a/block/bio-integrity.c b/block/bio-integrity.c index 03e8fae17393..10912988c8f5 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -7,20 +7,12 @@ */ #include <linux/blk-integrity.h> -#include <linux/mempool.h> -#include <linux/export.h> -#include <linux/bio.h> -#include <linux/workqueue.h> -#include <linux/slab.h> #include "blk.h" -static struct kmem_cache *bip_slab; -static struct workqueue_struct *kintegrityd_wq; - -void blk_flush_integrity(void) -{ - flush_workqueue(kintegrityd_wq); -} +struct bio_integrity_alloc { + struct bio_integrity_payload bip; + struct bio_vec bvecs[]; +}; /** * bio_integrity_free - Free bio integrity payload @@ -30,21 +22,23 @@ void blk_flush_integrity(void) */ void bio_integrity_free(struct bio *bio) { - struct bio_integrity_payload *bip = bio_integrity(bio); - struct bio_set *bs = bio->bi_pool; - - if (bs && mempool_initialized(&bs->bio_integrity_pool)) { - if (bip->bip_vec) - bvec_free(&bs->bvec_integrity_pool, bip->bip_vec, - bip->bip_max_vcnt); - mempool_free(bip, &bs->bio_integrity_pool); - } else { - kfree(bip); - } + kfree(bio_integrity(bio)); bio->bi_integrity = NULL; bio->bi_opf &= ~REQ_INTEGRITY; } +void bio_integrity_init(struct bio *bio, struct bio_integrity_payload *bip, + struct bio_vec *bvecs, unsigned int nr_vecs) +{ + memset(bip, 0, sizeof(*bip)); + bip->bip_max_vcnt = nr_vecs; + if (nr_vecs) + bip->bip_vec = bvecs; + + bio->bi_integrity = bip; + bio->bi_opf |= REQ_INTEGRITY; +} + /** * bio_integrity_alloc - Allocate integrity payload and attach it to bio * @bio: bio to attach integrity metadata to @@ -59,48 +53,16 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio, gfp_t gfp_mask, unsigned int nr_vecs) { - struct bio_integrity_payload *bip; - struct bio_set *bs = bio->bi_pool; - unsigned inline_vecs; + struct bio_integrity_alloc *bia; if (WARN_ON_ONCE(bio_has_crypt_ctx(bio))) return ERR_PTR(-EOPNOTSUPP); - if (!bs || !mempool_initialized(&bs->bio_integrity_pool)) { - bip = kmalloc(struct_size(bip, bip_inline_vecs, nr_vecs), gfp_mask); - inline_vecs = nr_vecs; - } else { - bip = mempool_alloc(&bs->bio_integrity_pool, gfp_mask); - inline_vecs = BIO_INLINE_VECS; - } - - if (unlikely(!bip)) + bia = kmalloc(struct_size(bia, bvecs, nr_vecs), gfp_mask); + if (unlikely(!bia)) return ERR_PTR(-ENOMEM); - - memset(bip, 0, sizeof(*bip)); - - /* always report as many vecs as asked explicitly, not inline vecs */ - bip->bip_max_vcnt = nr_vecs; - if (nr_vecs > inline_vecs) { - bip->bip_vec = bvec_alloc(&bs->bvec_integrity_pool, - &bip->bip_max_vcnt, gfp_mask); - if (!bip->bip_vec) - goto err; - } else if (nr_vecs) { - bip->bip_vec = bip->bip_inline_vecs; - } - - bip->bip_bio = bio; - bio->bi_integrity = bip; - bio->bi_opf |= REQ_INTEGRITY; - - return bip; -err: - if (bs && mempool_initialized(&bs->bio_integrity_pool)) - mempool_free(bip, &bs->bio_integrity_pool); - else - kfree(bip); - return ERR_PTR(-ENOMEM); + bio_integrity_init(bio, &bia->bip, bia->bvecs, nr_vecs); + return &bia->bip; } EXPORT_SYMBOL(bio_integrity_alloc); @@ -165,10 +127,8 @@ int bio_integrity_add_page(struct bio *bio, struct page *page, if (bip->bip_vcnt > 0) { struct bio_vec *bv = &bip->bip_vec[bip->bip_vcnt - 1]; - bool same_page = false; - if (bvec_try_merge_hw_page(q, bv, page, len, offset, - &same_page)) { + if (bvec_try_merge_hw_page(q, bv, page, len, offset)) { bip->bip_iter.bi_size += len; return len; } @@ -194,10 +154,9 @@ int bio_integrity_add_page(struct bio *bio, struct page *page, EXPORT_SYMBOL(bio_integrity_add_page); static int bio_integrity_copy_user(struct bio *bio, struct bio_vec *bvec, - int nr_vecs, unsigned int len, - unsigned int direction) + int nr_vecs, unsigned int len) { - bool write = direction == ITER_SOURCE; + bool write = op_is_write(bio_op(bio)); struct bio_integrity_payload *bip; struct iov_iter iter; void *buf; @@ -208,7 +167,7 @@ static int bio_integrity_copy_user(struct bio *bio, struct bio_vec *bvec, return -ENOMEM; if (write) { - iov_iter_bvec(&iter, direction, bvec, nr_vecs, len); + iov_iter_bvec(&iter, ITER_SOURCE, bvec, nr_vecs, len); if (!copy_from_iter_full(buf, len, &iter)) { ret = -EFAULT; goto free_buf; @@ -304,7 +263,7 @@ int bio_integrity_map_user(struct bio *bio, struct iov_iter *iter) struct page *stack_pages[UIO_FASTIOV], **pages = stack_pages; struct bio_vec stack_vec[UIO_FASTIOV], *bvec = stack_vec; size_t offset, bytes = iter->count; - unsigned int direction, nr_bvecs; + unsigned int nr_bvecs; int ret, nr_vecs; bool copy; @@ -313,11 +272,6 @@ int bio_integrity_map_user(struct bio *bio, struct iov_iter *iter) if (bytes >> SECTOR_SHIFT > queue_max_hw_sectors(q)) return -E2BIG; - if (bio_data_dir(bio) == READ) - direction = ITER_DEST; - else - direction = ITER_SOURCE; - nr_vecs = iov_iter_npages(iter, BIO_MAX_VECS + 1); if (nr_vecs > BIO_MAX_VECS) return -E2BIG; @@ -340,8 +294,7 @@ int bio_integrity_map_user(struct bio *bio, struct iov_iter *iter) copy = true; if (copy) - ret = bio_integrity_copy_user(bio, bvec, nr_bvecs, bytes, - direction); + ret = bio_integrity_copy_user(bio, bvec, nr_bvecs, bytes); else ret = bio_integrity_init_user(bio, bvec, nr_bvecs, bytes); if (ret) @@ -409,149 +362,6 @@ int bio_integrity_map_iter(struct bio *bio, struct uio_meta *meta) } /** - * bio_integrity_prep - Prepare bio for integrity I/O - * @bio: bio to prepare - * - * Description: Checks if the bio already has an integrity payload attached. - * If it does, the payload has been generated by another kernel subsystem, - * and we just pass it through. Otherwise allocates integrity payload. - * The bio must have data direction, target device and start sector set priot - * to calling. In the WRITE case, integrity metadata will be generated using - * the block device's integrity function. In the READ case, the buffer - * will be prepared for DMA and a suitable end_io handler set up. - */ -bool bio_integrity_prep(struct bio *bio) -{ - struct bio_integrity_payload *bip; - struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk); - unsigned int len; - void *buf; - gfp_t gfp = GFP_NOIO; - - if (!bi) - return true; - - if (!bio_sectors(bio)) - return true; - - /* Already protected? */ - if (bio_integrity(bio)) - return true; - - switch (bio_op(bio)) { - case REQ_OP_READ: - if (bi->flags & BLK_INTEGRITY_NOVERIFY) - return true; - break; - case REQ_OP_WRITE: - if (bi->flags & BLK_INTEGRITY_NOGENERATE) - return true; - - /* - * Zero the memory allocated to not leak uninitialized kernel - * memory to disk for non-integrity metadata where nothing else - * initializes the memory. - */ - if (bi->csum_type == BLK_INTEGRITY_CSUM_NONE) - gfp |= __GFP_ZERO; - break; - default: - return true; - } - - /* Allocate kernel buffer for protection data */ - len = bio_integrity_bytes(bi, bio_sectors(bio)); - buf = kmalloc(len, gfp); - if (unlikely(buf == NULL)) { - goto err_end_io; - } - - bip = bio_integrity_alloc(bio, GFP_NOIO, 1); - if (IS_ERR(bip)) { - kfree(buf); - goto err_end_io; - } - - bip->bip_flags |= BIP_BLOCK_INTEGRITY; - bip_set_seed(bip, bio->bi_iter.bi_sector); - - if (bi->csum_type == BLK_INTEGRITY_CSUM_IP) - bip->bip_flags |= BIP_IP_CHECKSUM; - - /* describe what tags to check in payload */ - if (bi->csum_type) - bip->bip_flags |= BIP_CHECK_GUARD; - if (bi->flags & BLK_INTEGRITY_REF_TAG) - bip->bip_flags |= BIP_CHECK_REFTAG; - if (bio_integrity_add_page(bio, virt_to_page(buf), len, - offset_in_page(buf)) < len) { - printk(KERN_ERR "could not attach integrity payload\n"); - goto err_end_io; - } - - /* Auto-generate integrity metadata if this is a write */ - if (bio_data_dir(bio) == WRITE) - blk_integrity_generate(bio); - else - bip->bio_iter = bio->bi_iter; - return true; - -err_end_io: - bio->bi_status = BLK_STS_RESOURCE; - bio_endio(bio); - return false; -} -EXPORT_SYMBOL(bio_integrity_prep); - -/** - * bio_integrity_verify_fn - Integrity I/O completion worker - * @work: Work struct stored in bio to be verified - * - * Description: This workqueue function is called to complete a READ - * request. The function verifies the transferred integrity metadata - * and then calls the original bio end_io function. - */ -static void bio_integrity_verify_fn(struct work_struct *work) -{ - struct bio_integrity_payload *bip = - container_of(work, struct bio_integrity_payload, bip_work); - struct bio *bio = bip->bip_bio; - - blk_integrity_verify(bio); - - kfree(bvec_virt(bip->bip_vec)); - bio_integrity_free(bio); - bio_endio(bio); -} - -/** - * __bio_integrity_endio - Integrity I/O completion function - * @bio: Protected bio - * - * Description: Completion for integrity I/O - * - * Normally I/O completion is done in interrupt context. However, - * verifying I/O integrity is a time-consuming task which must be run - * in process context. This function postpones completion - * accordingly. - */ -bool __bio_integrity_endio(struct bio *bio) -{ - struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk); - struct bio_integrity_payload *bip = bio_integrity(bio); - - if (bio_op(bio) == REQ_OP_READ && !bio->bi_status && bi->csum_type) { - INIT_WORK(&bip->bip_work, bio_integrity_verify_fn); - queue_work(kintegrityd_wq, &bip->bip_work); - return false; - } - - kfree(bvec_virt(bip->bip_vec)); - bio_integrity_free(bio); - return true; -} - -/** * bio_integrity_advance - Advance integrity vector * @bio: bio whose integrity vector to update * @bytes_done: number of data bytes that have been completed @@ -612,44 +422,3 @@ int bio_integrity_clone(struct bio *bio, struct bio *bio_src, return 0; } - -int bioset_integrity_create(struct bio_set *bs, int pool_size) -{ - if (mempool_initialized(&bs->bio_integrity_pool)) - return 0; - - if (mempool_init_slab_pool(&bs->bio_integrity_pool, - pool_size, bip_slab)) - return -1; - - if (biovec_init_pool(&bs->bvec_integrity_pool, pool_size)) { - mempool_exit(&bs->bio_integrity_pool); - return -1; - } - - return 0; -} -EXPORT_SYMBOL(bioset_integrity_create); - -void bioset_integrity_free(struct bio_set *bs) -{ - mempool_exit(&bs->bio_integrity_pool); - mempool_exit(&bs->bvec_integrity_pool); -} - -void __init bio_integrity_init(void) -{ - /* - * kintegrityd won't block much but may burn a lot of CPU cycles. - * Make it highpri CPU intensive wq with max concurrency of 1. - */ - kintegrityd_wq = alloc_workqueue("kintegrityd", WQ_MEM_RECLAIM | - WQ_HIGHPRI | WQ_CPU_INTENSIVE, 1); - if (!kintegrityd_wq) - panic("Failed to create kintegrityd\n"); - - bip_slab = kmem_cache_create("bio_integrity_payload", - sizeof(struct bio_integrity_payload) + - sizeof(struct bio_vec) * BIO_INLINE_VECS, - 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); -} diff --git a/block/bio.c b/block/bio.c index 6deea10b2cd3..3c0a558c90f5 100644 --- a/block/bio.c +++ b/block/bio.c @@ -251,6 +251,7 @@ void bio_init(struct bio *bio, struct block_device *bdev, struct bio_vec *table, bio->bi_flags = 0; bio->bi_ioprio = 0; bio->bi_write_hint = 0; + bio->bi_write_stream = 0; bio->bi_status = 0; bio->bi_iter.bi_sector = 0; bio->bi_iter.bi_size = 0; @@ -611,7 +612,7 @@ struct bio *bio_kmalloc(unsigned short nr_vecs, gfp_t gfp_mask) { struct bio *bio; - if (nr_vecs > UIO_MAXIOV) + if (nr_vecs > BIO_MAX_INLINE_VECS) return NULL; return kmalloc(struct_size(bio, bi_inline_vecs, nr_vecs), gfp_mask); } @@ -827,6 +828,7 @@ static int __bio_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp) bio_set_flag(bio, BIO_CLONED); bio->bi_ioprio = bio_src->bi_ioprio; bio->bi_write_hint = bio_src->bi_write_hint; + bio->bi_write_stream = bio_src->bi_write_stream; bio->bi_iter = bio_src->bi_iter; if (bio->bi_bdev) { @@ -918,7 +920,7 @@ static inline bool bio_full(struct bio *bio, unsigned len) } static bool bvec_try_merge_page(struct bio_vec *bv, struct page *page, - unsigned int len, unsigned int off, bool *same_page) + unsigned int len, unsigned int off) { size_t bv_end = bv->bv_offset + bv->bv_len; phys_addr_t vec_end_addr = page_to_phys(bv->bv_page) + bv_end - 1; @@ -931,9 +933,7 @@ static bool bvec_try_merge_page(struct bio_vec *bv, struct page *page, if (!zone_device_pages_have_same_pgmap(bv->bv_page, page)) return false; - *same_page = ((vec_end_addr & PAGE_MASK) == ((page_addr + off) & - PAGE_MASK)); - if (!*same_page) { + if ((vec_end_addr & PAGE_MASK) != ((page_addr + off) & PAGE_MASK)) { if (IS_ENABLED(CONFIG_KMSAN)) return false; if (bv->bv_page + bv_end / PAGE_SIZE != page + off / PAGE_SIZE) @@ -953,8 +953,7 @@ static bool bvec_try_merge_page(struct bio_vec *bv, struct page *page, * helpers to split. Hopefully this will go away soon. */ bool bvec_try_merge_hw_page(struct request_queue *q, struct bio_vec *bv, - struct page *page, unsigned len, unsigned offset, - bool *same_page) + struct page *page, unsigned len, unsigned offset) { unsigned long mask = queue_segment_boundary(q); phys_addr_t addr1 = bvec_phys(bv); @@ -964,7 +963,7 @@ bool bvec_try_merge_hw_page(struct request_queue *q, struct bio_vec *bv, return false; if (len > queue_max_segment_size(q) - bv->bv_len) return false; - return bvec_try_merge_page(bv, page, len, offset, same_page); + return bvec_try_merge_page(bv, page, len, offset); } /** @@ -990,6 +989,22 @@ void __bio_add_page(struct bio *bio, struct page *page, EXPORT_SYMBOL_GPL(__bio_add_page); /** + * bio_add_virt_nofail - add data in the direct kernel mapping to a bio + * @bio: destination bio + * @vaddr: data to add + * @len: length of the data to add, may cross pages + * + * Add the data at @vaddr to @bio. The caller must have ensure a segment + * is available for the added data. No merging into an existing segment + * will be performed. + */ +void bio_add_virt_nofail(struct bio *bio, void *vaddr, unsigned len) +{ + __bio_add_page(bio, virt_to_page(vaddr), len, offset_in_page(vaddr)); +} +EXPORT_SYMBOL_GPL(bio_add_virt_nofail); + +/** * bio_add_page - attempt to add page(s) to bio * @bio: destination bio * @page: start page to add @@ -1002,8 +1017,6 @@ EXPORT_SYMBOL_GPL(__bio_add_page); int bio_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int offset) { - bool same_page = false; - if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED))) return 0; if (bio->bi_iter.bi_size > UINT_MAX - len) @@ -1011,7 +1024,7 @@ int bio_add_page(struct bio *bio, struct page *page, if (bio->bi_vcnt > 0 && bvec_try_merge_page(&bio->bi_io_vec[bio->bi_vcnt - 1], - page, len, offset, &same_page)) { + page, len, offset)) { bio->bi_iter.bi_size += len; return len; } @@ -1058,6 +1071,61 @@ bool bio_add_folio(struct bio *bio, struct folio *folio, size_t len, } EXPORT_SYMBOL(bio_add_folio); +/** + * bio_add_vmalloc_chunk - add a vmalloc chunk to a bio + * @bio: destination bio + * @vaddr: vmalloc address to add + * @len: total length in bytes of the data to add + * + * Add data starting at @vaddr to @bio and return how many bytes were added. + * This may be less than the amount originally asked. Returns 0 if no data + * could be added to @bio. + * + * This helper calls flush_kernel_vmap_range() for the range added. For reads + * the caller still needs to manually call invalidate_kernel_vmap_range() in + * the completion handler. + */ +unsigned int bio_add_vmalloc_chunk(struct bio *bio, void *vaddr, unsigned len) +{ + unsigned int offset = offset_in_page(vaddr); + + len = min(len, PAGE_SIZE - offset); + if (bio_add_page(bio, vmalloc_to_page(vaddr), len, offset) < len) + return 0; + if (op_is_write(bio_op(bio))) + flush_kernel_vmap_range(vaddr, len); + return len; +} +EXPORT_SYMBOL_GPL(bio_add_vmalloc_chunk); + +/** + * bio_add_vmalloc - add a vmalloc region to a bio + * @bio: destination bio + * @vaddr: vmalloc address to add + * @len: total length in bytes of the data to add + * + * Add data starting at @vaddr to @bio. Return %true on success or %false if + * @bio does not have enough space for the payload. + * + * This helper calls flush_kernel_vmap_range() for the range added. For reads + * the caller still needs to manually call invalidate_kernel_vmap_range() in + * the completion handler. + */ +bool bio_add_vmalloc(struct bio *bio, void *vaddr, unsigned int len) +{ + do { + unsigned int added = bio_add_vmalloc_chunk(bio, vaddr, len); + + if (!added) + return false; + vaddr += added; + len -= added; + } while (len); + + return true; +} +EXPORT_SYMBOL_GPL(bio_add_vmalloc); + void __bio_release_pages(struct bio *bio, bool mark_dirty) { struct folio_iter fi; @@ -1088,27 +1156,6 @@ void bio_iov_bvec_set(struct bio *bio, const struct iov_iter *iter) bio_set_flag(bio, BIO_CLONED); } -static int bio_iov_add_folio(struct bio *bio, struct folio *folio, size_t len, - size_t offset) -{ - bool same_page = false; - - if (WARN_ON_ONCE(bio->bi_iter.bi_size > UINT_MAX - len)) - return -EIO; - - if (bio->bi_vcnt > 0 && - bvec_try_merge_page(&bio->bi_io_vec[bio->bi_vcnt - 1], - folio_page(folio, 0), len, offset, - &same_page)) { - bio->bi_iter.bi_size += len; - if (same_page && bio_flagged(bio, BIO_PAGE_PINNED)) - unpin_user_folio(folio, 1); - return 0; - } - bio_add_folio_nofail(bio, folio, len, offset); - return 0; -} - static unsigned int get_contig_folio_len(unsigned int *num_pages, struct page **pages, unsigned int i, struct folio *folio, size_t left, @@ -1203,6 +1250,7 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) for (left = size, i = 0; left > 0; left -= len, i += num_pages) { struct page *page = pages[i]; struct folio *folio = page_folio(page); + unsigned int old_vcnt = bio->bi_vcnt; folio_offset = ((size_t)folio_page_idx(folio, page) << PAGE_SHIFT) + offset; @@ -1215,7 +1263,23 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) len = get_contig_folio_len(&num_pages, pages, i, folio, left, offset); - bio_iov_add_folio(bio, folio, len, folio_offset); + if (!bio_add_folio(bio, folio, len, folio_offset)) { + WARN_ON_ONCE(1); + ret = -EINVAL; + goto out; + } + + if (bio_flagged(bio, BIO_PAGE_PINNED)) { + /* + * We're adding another fragment of a page that already + * was part of the last segment. Undo our pin as the + * page was pinned when an earlier fragment of it was + * added to the bio and __bio_release_pages expects a + * single pin per page. + */ + if (offset && bio->bi_vcnt == old_vcnt) + unpin_user_folio(folio, 1); + } offset = 0; } @@ -1301,6 +1365,36 @@ int submit_bio_wait(struct bio *bio) } EXPORT_SYMBOL(submit_bio_wait); +/** + * bdev_rw_virt - synchronously read into / write from kernel mapping + * @bdev: block device to access + * @sector: sector to access + * @data: data to read/write + * @len: length in byte to read/write + * @op: operation (e.g. REQ_OP_READ/REQ_OP_WRITE) + * + * Performs synchronous I/O to @bdev for @data/@len. @data must be in + * the kernel direct mapping and not a vmalloc address. + */ +int bdev_rw_virt(struct block_device *bdev, sector_t sector, void *data, + size_t len, enum req_op op) +{ + struct bio_vec bv; + struct bio bio; + int error; + + if (WARN_ON_ONCE(is_vmalloc_addr(data))) + return -EIO; + + bio_init(&bio, bdev, &bv, 1, op); + bio.bi_iter.bi_sector = sector; + bio_add_virt_nofail(&bio, data, len); + error = submit_bio_wait(&bio); + bio_uninit(&bio); + return error; +} +EXPORT_SYMBOL_GPL(bdev_rw_virt); + static void bio_wait_end_io(struct bio *bio) { complete(bio->bi_private); @@ -1660,7 +1754,6 @@ void bioset_exit(struct bio_set *bs) mempool_exit(&bs->bio_pool); mempool_exit(&bs->bvec_pool); - bioset_integrity_free(bs); if (bs->bio_slab) bio_put_slab(bs); bs->bio_slab = NULL; @@ -1740,8 +1833,6 @@ static int __init init_bio(void) BUILD_BUG_ON(BIO_FLAG_LAST > 8 * sizeof_field(struct bio, bi_flags)); - bio_integrity_init(); - for (i = 0; i < ARRAY_SIZE(bvec_slabs); i++) { struct biovec_slab *bvs = bvec_slabs + i; @@ -1757,9 +1848,6 @@ static int __init init_bio(void) BIOSET_NEED_BVECS | BIOSET_PERCPU_CACHE)) panic("bio: can't allocate bios\n"); - if (bioset_integrity_create(&fs_bio_set, BIO_POOL_SIZE)) - panic("bio: can't create integrity pool\n"); - return 0; } subsys_initcall(init_bio); diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 9ed93d91d754..5936db7f8475 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -659,6 +659,7 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css, struct blkcg_gq *blkg; int i; + pr_info_once("blkio.%s is deprecated\n", cftype->name); mutex_lock(&blkcg_pol_mutex); spin_lock_irq(&blkcg->lock); @@ -796,7 +797,7 @@ int blkg_conf_open_bdev(struct blkg_conf_ctx *ctx) return -EINVAL; input = skip_spaces(input); - bdev = blkdev_get_no_open(MKDEV(major, minor)); + bdev = blkdev_get_no_open(MKDEV(major, minor), false); if (!bdev) return -ENODEV; if (bdev_is_partition(bdev)) { @@ -815,6 +816,41 @@ int blkg_conf_open_bdev(struct blkg_conf_ctx *ctx) ctx->bdev = bdev; return 0; } +/* + * Similar to blkg_conf_open_bdev, but additionally freezes the queue, + * acquires q->elevator_lock, and ensures the correct locking order + * between q->elevator_lock and q->rq_qos_mutex. + * + * This function returns negative error on failure. On success it returns + * memflags which must be saved and later passed to blkg_conf_exit_frozen + * for restoring the memalloc scope. + */ +unsigned long __must_check blkg_conf_open_bdev_frozen(struct blkg_conf_ctx *ctx) +{ + int ret; + unsigned long memflags; + + if (ctx->bdev) + return -EINVAL; + + ret = blkg_conf_open_bdev(ctx); + if (ret < 0) + return ret; + /* + * At this point, we haven’t started protecting anything related to QoS, + * so we release q->rq_qos_mutex here, which was first acquired in blkg_ + * conf_open_bdev. Later, we re-acquire q->rq_qos_mutex after freezing + * the queue and acquiring q->elevator_lock to maintain the correct + * locking order. + */ + mutex_unlock(&ctx->bdev->bd_queue->rq_qos_mutex); + + memflags = blk_mq_freeze_queue(ctx->bdev->bd_queue); + mutex_lock(&ctx->bdev->bd_queue->elevator_lock); + mutex_lock(&ctx->bdev->bd_queue->rq_qos_mutex); + + return memflags; +} /** * blkg_conf_prep - parse and prepare for per-blkg config update @@ -971,6 +1007,22 @@ void blkg_conf_exit(struct blkg_conf_ctx *ctx) } EXPORT_SYMBOL_GPL(blkg_conf_exit); +/* + * Similar to blkg_conf_exit, but also unfreezes the queue and releases + * q->elevator_lock. Should be used when blkg_conf_open_bdev_frozen + * is used to open the bdev. + */ +void blkg_conf_exit_frozen(struct blkg_conf_ctx *ctx, unsigned long memflags) +{ + if (ctx->bdev) { + struct request_queue *q = ctx->bdev->bd_queue; + + blkg_conf_exit(ctx); + mutex_unlock(&q->elevator_lock); + blk_mq_unfreeze_queue(q, memflags); + } +} + static void blkg_iostat_add(struct blkg_iostat *dst, struct blkg_iostat *src) { int i; @@ -1022,8 +1074,8 @@ static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu) /* * For covering concurrent parent blkg update from blkg_release(). * - * When flushing from cgroup, cgroup_rstat_lock is always held, so - * this lock won't cause contention most of time. + * When flushing from cgroup, the subsystem rstat lock is always held, + * so this lock won't cause contention most of time. */ raw_spin_lock_irqsave(&blkg_stat_lock, flags); @@ -1092,7 +1144,7 @@ static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu) /* * We source root cgroup stats from the system-wide stats to avoid * tracking the same information twice and incurring overhead when no - * cgroups are defined. For that reason, cgroup_rstat_flush in + * cgroups are defined. For that reason, css_rstat_flush in * blkcg_print_stat does not actually fill out the iostat in the root * cgroup's blkcg_gq. * @@ -1201,7 +1253,7 @@ static int blkcg_print_stat(struct seq_file *sf, void *v) if (!seq_css(sf)->parent) blkcg_fill_root_iostats(); else - cgroup_rstat_flush(blkcg->css.cgroup); + css_rstat_flush(&blkcg->css); rcu_read_lock(); hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { @@ -1727,27 +1779,27 @@ int blkcg_policy_register(struct blkcg_policy *pol) struct blkcg *blkcg; int i, ret; + /* + * Make sure cpd/pd_alloc_fn and cpd/pd_free_fn in pairs, and policy + * without pd_alloc_fn/pd_free_fn can't be activated. + */ + if ((!pol->cpd_alloc_fn ^ !pol->cpd_free_fn) || + (!pol->pd_alloc_fn ^ !pol->pd_free_fn)) + return -EINVAL; + mutex_lock(&blkcg_pol_register_mutex); mutex_lock(&blkcg_pol_mutex); /* find an empty slot */ - ret = -ENOSPC; for (i = 0; i < BLKCG_MAX_POLS; i++) if (!blkcg_policy[i]) break; if (i >= BLKCG_MAX_POLS) { pr_warn("blkcg_policy_register: BLKCG_MAX_POLS too small\n"); + ret = -ENOSPC; goto err_unlock; } - /* - * Make sure cpd/pd_alloc_fn and cpd/pd_free_fn in pairs, and policy - * without pd_alloc_fn/pd_free_fn can't be activated. - */ - if ((!pol->cpd_alloc_fn ^ !pol->cpd_free_fn) || - (!pol->pd_alloc_fn ^ !pol->pd_free_fn)) - goto err_unlock; - /* register @pol */ pol->plid = i; blkcg_policy[pol->plid] = pol; @@ -1758,8 +1810,10 @@ int blkcg_policy_register(struct blkcg_policy *pol) struct blkcg_policy_data *cpd; cpd = pol->cpd_alloc_fn(GFP_KERNEL); - if (!cpd) + if (!cpd) { + ret = -ENOMEM; goto err_free_cpds; + } blkcg->cpd[pol->plid] = cpd; cpd->blkcg = blkcg; @@ -1770,12 +1824,15 @@ int blkcg_policy_register(struct blkcg_policy *pol) mutex_unlock(&blkcg_pol_mutex); /* everything is in place, add intf files for the new policy */ - if (pol->dfl_cftypes) + if (pol->dfl_cftypes == pol->legacy_cftypes) { + WARN_ON(cgroup_add_cftypes(&io_cgrp_subsys, + pol->dfl_cftypes)); + } else { WARN_ON(cgroup_add_dfl_cftypes(&io_cgrp_subsys, pol->dfl_cftypes)); - if (pol->legacy_cftypes) WARN_ON(cgroup_add_legacy_cftypes(&io_cgrp_subsys, pol->legacy_cftypes)); + } mutex_unlock(&blkcg_pol_register_mutex); return 0; @@ -2186,7 +2243,7 @@ void blk_cgroup_bio_start(struct bio *bio) } u64_stats_update_end_irqrestore(&bis->sync, flags); - cgroup_rstat_updated(blkcg->css.cgroup, cpu); + css_rstat_updated(&blkcg->css, cpu); put_cpu(); } diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h index 2c4663bd993a..81868ad86330 100644 --- a/block/blk-cgroup.h +++ b/block/blk-cgroup.h @@ -219,9 +219,11 @@ struct blkg_conf_ctx { void blkg_conf_init(struct blkg_conf_ctx *ctx, char *input); int blkg_conf_open_bdev(struct blkg_conf_ctx *ctx); +unsigned long blkg_conf_open_bdev_frozen(struct blkg_conf_ctx *ctx); int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, struct blkg_conf_ctx *ctx); void blkg_conf_exit(struct blkg_conf_ctx *ctx); +void blkg_conf_exit_frozen(struct blkg_conf_ctx *ctx, unsigned long memflags); /** * bio_issue_as_root_blkg - see if this bio needs to be issued as root blkg diff --git a/block/blk-core.c b/block/blk-core.c index d6c4fa3943b5..fdac48aec5ef 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -219,7 +219,7 @@ EXPORT_SYMBOL_GPL(blk_status_to_str); */ void blk_sync_queue(struct request_queue *q) { - del_timer_sync(&q->timeout); + timer_delete_sync(&q->timeout); cancel_work_sync(&q->timeout_work); } EXPORT_SYMBOL(blk_sync_queue); @@ -381,7 +381,7 @@ static void blk_queue_usage_counter_release(struct percpu_ref *ref) static void blk_rq_timed_out_timer(struct timer_list *t) { - struct request_queue *q = from_timer(q, t, timeout); + struct request_queue *q = timer_container_of(q, t, timeout); kblockd_schedule_work(&q->timeout_work); } @@ -429,6 +429,7 @@ struct request_queue *blk_alloc_queue(struct queue_limits *lim, int node_id) refcount_set(&q->refs, 1); mutex_init(&q->debugfs_mutex); + mutex_init(&q->elevator_lock); mutex_init(&q->sysfs_lock); mutex_init(&q->limits_lock); mutex_init(&q->rq_qos_mutex); @@ -455,6 +456,12 @@ struct request_queue *blk_alloc_queue(struct queue_limits *lim, int node_id) lockdep_init_map(&q->q_lockdep_map, "&q->q_usage_counter(queue)", &q->q_lock_cls_key, 0); + /* Teach lockdep about lock ordering (reclaim WRT queue freeze lock). */ + fs_reclaim_acquire(GFP_KERNEL); + rwsem_acquire_read(&q->io_lockdep_map, 0, 0, _RET_IP_); + rwsem_release(&q->io_lockdep_map, _RET_IP_); + fs_reclaim_release(GFP_KERNEL); + q->nr_requests = BLKDEV_DEFAULT_RQ; return q; @@ -1011,7 +1018,7 @@ again: stamp = READ_ONCE(part->bd_stamp); if (unlikely(time_after(now, stamp)) && likely(try_cmpxchg(&part->bd_stamp, &stamp, now)) && - (end || part_in_flight(part))) + (end || bdev_count_inflight(part))) __part_stat_add(part, io_ticks, now - stamp); if (bdev_is_partition(part)) { diff --git a/block/blk-crypto-fallback.c b/block/blk-crypto-fallback.c index 29a205482617..005c9157ffb3 100644 --- a/block/blk-crypto-fallback.c +++ b/block/blk-crypto-fallback.c @@ -87,7 +87,7 @@ static struct bio_set crypto_bio_split; * This is the key we set when evicting a keyslot. This *should* be the all 0's * key, but AES-XTS rejects that key, so we use some random bytes instead. */ -static u8 blank_key[BLK_CRYPTO_MAX_KEY_SIZE]; +static u8 blank_key[BLK_CRYPTO_MAX_RAW_KEY_SIZE]; static void blk_crypto_fallback_evict_keyslot(unsigned int slot) { @@ -119,7 +119,7 @@ blk_crypto_fallback_keyslot_program(struct blk_crypto_profile *profile, blk_crypto_fallback_evict_keyslot(slot); slotp->crypto_mode = crypto_mode; - err = crypto_skcipher_setkey(slotp->tfms[crypto_mode], key->raw, + err = crypto_skcipher_setkey(slotp->tfms[crypto_mode], key->bytes, key->size); if (err) { blk_crypto_fallback_evict_keyslot(slot); @@ -173,6 +173,7 @@ static struct bio *blk_crypto_fallback_clone_bio(struct bio *bio_src) bio_set_flag(bio, BIO_REMAPPED); bio->bi_ioprio = bio_src->bi_ioprio; bio->bi_write_hint = bio_src->bi_write_hint; + bio->bi_write_stream = bio_src->bi_write_stream; bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector; bio->bi_iter.bi_size = bio_src->bi_iter.bi_size; @@ -539,7 +540,7 @@ static int blk_crypto_fallback_init(void) if (blk_crypto_fallback_inited) return 0; - get_random_bytes(blank_key, BLK_CRYPTO_MAX_KEY_SIZE); + get_random_bytes(blank_key, sizeof(blank_key)); err = bioset_init(&crypto_bio_split, 64, 0, 0); if (err) @@ -561,6 +562,7 @@ static int blk_crypto_fallback_init(void) blk_crypto_fallback_profile->ll_ops = blk_crypto_fallback_ll_ops; blk_crypto_fallback_profile->max_dun_bytes_supported = BLK_CRYPTO_MAX_IV_SIZE; + blk_crypto_fallback_profile->key_types_supported = BLK_CRYPTO_KEY_TYPE_RAW; /* All blk-crypto modes have a crypto API fallback. */ for (i = 0; i < BLK_ENCRYPTION_MODE_MAX; i++) diff --git a/block/blk-crypto-internal.h b/block/blk-crypto-internal.h index 93a141979694..ccf6dff6ff6b 100644 --- a/block/blk-crypto-internal.h +++ b/block/blk-crypto-internal.h @@ -14,6 +14,7 @@ struct blk_crypto_mode { const char *name; /* name of this mode, shown in sysfs */ const char *cipher_str; /* crypto API name (for fallback case) */ unsigned int keysize; /* key size in bytes */ + unsigned int security_strength; /* security strength in bytes */ unsigned int ivsize; /* iv size in bytes */ }; @@ -82,6 +83,9 @@ int __blk_crypto_evict_key(struct blk_crypto_profile *profile, bool __blk_crypto_cfg_supported(struct blk_crypto_profile *profile, const struct blk_crypto_config *cfg); +int blk_crypto_ioctl(struct block_device *bdev, unsigned int cmd, + void __user *argp); + #else /* CONFIG_BLK_INLINE_ENCRYPTION */ static inline int blk_crypto_sysfs_register(struct gendisk *disk) @@ -129,6 +133,12 @@ static inline bool blk_crypto_rq_has_keyslot(struct request *rq) return false; } +static inline int blk_crypto_ioctl(struct block_device *bdev, unsigned int cmd, + void __user *argp) +{ + return -ENOTTY; +} + #endif /* CONFIG_BLK_INLINE_ENCRYPTION */ void __bio_crypt_advance(struct bio *bio, unsigned int bytes); diff --git a/block/blk-crypto-profile.c b/block/blk-crypto-profile.c index 7fabc883e39f..81918f6e0cae 100644 --- a/block/blk-crypto-profile.c +++ b/block/blk-crypto-profile.c @@ -352,6 +352,8 @@ bool __blk_crypto_cfg_supported(struct blk_crypto_profile *profile, return false; if (profile->max_dun_bytes_supported < cfg->dun_bytes) return false; + if (!(profile->key_types_supported & cfg->key_type)) + return false; return true; } @@ -463,6 +465,103 @@ bool blk_crypto_register(struct blk_crypto_profile *profile, EXPORT_SYMBOL_GPL(blk_crypto_register); /** + * blk_crypto_derive_sw_secret() - Derive software secret from wrapped key + * @bdev: a block device that supports hardware-wrapped keys + * @eph_key: a hardware-wrapped key in ephemerally-wrapped form + * @eph_key_size: size of @eph_key in bytes + * @sw_secret: (output) the software secret + * + * Given a hardware-wrapped key in ephemerally-wrapped form (the same form that + * it is used for I/O), ask the hardware to derive the secret which software can + * use for cryptographic tasks other than inline encryption. This secret is + * guaranteed to be cryptographically isolated from the inline encryption key, + * i.e. derived with a different KDF context. + * + * Return: 0 on success, -EOPNOTSUPP if the block device doesn't support + * hardware-wrapped keys, -EBADMSG if the key isn't a valid + * ephemerally-wrapped key, or another -errno code. + */ +int blk_crypto_derive_sw_secret(struct block_device *bdev, + const u8 *eph_key, size_t eph_key_size, + u8 sw_secret[BLK_CRYPTO_SW_SECRET_SIZE]) +{ + struct blk_crypto_profile *profile = + bdev_get_queue(bdev)->crypto_profile; + int err; + + if (!profile) + return -EOPNOTSUPP; + if (!(profile->key_types_supported & BLK_CRYPTO_KEY_TYPE_HW_WRAPPED)) + return -EOPNOTSUPP; + if (!profile->ll_ops.derive_sw_secret) + return -EOPNOTSUPP; + blk_crypto_hw_enter(profile); + err = profile->ll_ops.derive_sw_secret(profile, eph_key, eph_key_size, + sw_secret); + blk_crypto_hw_exit(profile); + return err; +} +EXPORT_SYMBOL_GPL(blk_crypto_derive_sw_secret); + +int blk_crypto_import_key(struct blk_crypto_profile *profile, + const u8 *raw_key, size_t raw_key_size, + u8 lt_key[BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE]) +{ + int ret; + + if (!profile) + return -EOPNOTSUPP; + if (!(profile->key_types_supported & BLK_CRYPTO_KEY_TYPE_HW_WRAPPED)) + return -EOPNOTSUPP; + if (!profile->ll_ops.import_key) + return -EOPNOTSUPP; + blk_crypto_hw_enter(profile); + ret = profile->ll_ops.import_key(profile, raw_key, raw_key_size, + lt_key); + blk_crypto_hw_exit(profile); + return ret; +} +EXPORT_SYMBOL_GPL(blk_crypto_import_key); + +int blk_crypto_generate_key(struct blk_crypto_profile *profile, + u8 lt_key[BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE]) +{ + int ret; + + if (!profile) + return -EOPNOTSUPP; + if (!(profile->key_types_supported & BLK_CRYPTO_KEY_TYPE_HW_WRAPPED)) + return -EOPNOTSUPP; + if (!profile->ll_ops.generate_key) + return -EOPNOTSUPP; + blk_crypto_hw_enter(profile); + ret = profile->ll_ops.generate_key(profile, lt_key); + blk_crypto_hw_exit(profile); + return ret; +} +EXPORT_SYMBOL_GPL(blk_crypto_generate_key); + +int blk_crypto_prepare_key(struct blk_crypto_profile *profile, + const u8 *lt_key, size_t lt_key_size, + u8 eph_key[BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE]) +{ + int ret; + + if (!profile) + return -EOPNOTSUPP; + if (!(profile->key_types_supported & BLK_CRYPTO_KEY_TYPE_HW_WRAPPED)) + return -EOPNOTSUPP; + if (!profile->ll_ops.prepare_key) + return -EOPNOTSUPP; + blk_crypto_hw_enter(profile); + ret = profile->ll_ops.prepare_key(profile, lt_key, lt_key_size, + eph_key); + blk_crypto_hw_exit(profile); + return ret; +} +EXPORT_SYMBOL_GPL(blk_crypto_prepare_key); + +/** * blk_crypto_intersect_capabilities() - restrict supported crypto capabilities * by child device * @parent: the crypto profile for the parent device @@ -485,10 +584,12 @@ void blk_crypto_intersect_capabilities(struct blk_crypto_profile *parent, child->max_dun_bytes_supported); for (i = 0; i < ARRAY_SIZE(child->modes_supported); i++) parent->modes_supported[i] &= child->modes_supported[i]; + parent->key_types_supported &= child->key_types_supported; } else { parent->max_dun_bytes_supported = 0; memset(parent->modes_supported, 0, sizeof(parent->modes_supported)); + parent->key_types_supported = 0; } } EXPORT_SYMBOL_GPL(blk_crypto_intersect_capabilities); @@ -521,6 +622,9 @@ bool blk_crypto_has_capabilities(const struct blk_crypto_profile *target, target->max_dun_bytes_supported) return false; + if (reference->key_types_supported & ~target->key_types_supported) + return false; + return true; } EXPORT_SYMBOL_GPL(blk_crypto_has_capabilities); @@ -555,5 +659,6 @@ void blk_crypto_update_capabilities(struct blk_crypto_profile *dst, sizeof(dst->modes_supported)); dst->max_dun_bytes_supported = src->max_dun_bytes_supported; + dst->key_types_supported = src->key_types_supported; } EXPORT_SYMBOL_GPL(blk_crypto_update_capabilities); diff --git a/block/blk-crypto-sysfs.c b/block/blk-crypto-sysfs.c index a304434489ba..e832f403f200 100644 --- a/block/blk-crypto-sysfs.c +++ b/block/blk-crypto-sysfs.c @@ -31,6 +31,13 @@ static struct blk_crypto_attr *attr_to_crypto_attr(struct attribute *attr) return container_of(attr, struct blk_crypto_attr, attr); } +static ssize_t hw_wrapped_keys_show(struct blk_crypto_profile *profile, + struct blk_crypto_attr *attr, char *page) +{ + /* Always show supported, since the file doesn't exist otherwise. */ + return sysfs_emit(page, "supported\n"); +} + static ssize_t max_dun_bits_show(struct blk_crypto_profile *profile, struct blk_crypto_attr *attr, char *page) { @@ -43,20 +50,48 @@ static ssize_t num_keyslots_show(struct blk_crypto_profile *profile, return sysfs_emit(page, "%u\n", profile->num_slots); } +static ssize_t raw_keys_show(struct blk_crypto_profile *profile, + struct blk_crypto_attr *attr, char *page) +{ + /* Always show supported, since the file doesn't exist otherwise. */ + return sysfs_emit(page, "supported\n"); +} + #define BLK_CRYPTO_RO_ATTR(_name) \ static struct blk_crypto_attr _name##_attr = __ATTR_RO(_name) +BLK_CRYPTO_RO_ATTR(hw_wrapped_keys); BLK_CRYPTO_RO_ATTR(max_dun_bits); BLK_CRYPTO_RO_ATTR(num_keyslots); +BLK_CRYPTO_RO_ATTR(raw_keys); + +static umode_t blk_crypto_is_visible(struct kobject *kobj, + struct attribute *attr, int n) +{ + struct blk_crypto_profile *profile = kobj_to_crypto_profile(kobj); + struct blk_crypto_attr *a = attr_to_crypto_attr(attr); + + if (a == &hw_wrapped_keys_attr && + !(profile->key_types_supported & BLK_CRYPTO_KEY_TYPE_HW_WRAPPED)) + return 0; + if (a == &raw_keys_attr && + !(profile->key_types_supported & BLK_CRYPTO_KEY_TYPE_RAW)) + return 0; + + return 0444; +} static struct attribute *blk_crypto_attrs[] = { + &hw_wrapped_keys_attr.attr, &max_dun_bits_attr.attr, &num_keyslots_attr.attr, + &raw_keys_attr.attr, NULL, }; static const struct attribute_group blk_crypto_attr_group = { .attrs = blk_crypto_attrs, + .is_visible = blk_crypto_is_visible, }; /* diff --git a/block/blk-crypto.c b/block/blk-crypto.c index 4d760b092deb..4b1ad84d1b5a 100644 --- a/block/blk-crypto.c +++ b/block/blk-crypto.c @@ -23,24 +23,28 @@ const struct blk_crypto_mode blk_crypto_modes[] = { .name = "AES-256-XTS", .cipher_str = "xts(aes)", .keysize = 64, + .security_strength = 32, .ivsize = 16, }, [BLK_ENCRYPTION_MODE_AES_128_CBC_ESSIV] = { .name = "AES-128-CBC-ESSIV", .cipher_str = "essiv(cbc(aes),sha256)", .keysize = 16, + .security_strength = 16, .ivsize = 16, }, [BLK_ENCRYPTION_MODE_ADIANTUM] = { .name = "Adiantum", .cipher_str = "adiantum(xchacha12,aes)", .keysize = 32, + .security_strength = 32, .ivsize = 32, }, [BLK_ENCRYPTION_MODE_SM4_XTS] = { .name = "SM4-XTS", .cipher_str = "xts(sm4)", .keysize = 32, + .security_strength = 16, .ivsize = 16, }, }; @@ -76,9 +80,15 @@ static int __init bio_crypt_ctx_init(void) /* This is assumed in various places. */ BUILD_BUG_ON(BLK_ENCRYPTION_MODE_INVALID != 0); - /* Sanity check that no algorithm exceeds the defined limits. */ + /* + * Validate the crypto mode properties. This ideally would be done with + * static assertions, but boot-time checks are the next best thing. + */ for (i = 0; i < BLK_ENCRYPTION_MODE_MAX; i++) { - BUG_ON(blk_crypto_modes[i].keysize > BLK_CRYPTO_MAX_KEY_SIZE); + BUG_ON(blk_crypto_modes[i].keysize > + BLK_CRYPTO_MAX_RAW_KEY_SIZE); + BUG_ON(blk_crypto_modes[i].security_strength > + blk_crypto_modes[i].keysize); BUG_ON(blk_crypto_modes[i].ivsize > BLK_CRYPTO_MAX_IV_SIZE); } @@ -315,17 +325,20 @@ int __blk_crypto_rq_bio_prep(struct request *rq, struct bio *bio, /** * blk_crypto_init_key() - Prepare a key for use with blk-crypto * @blk_key: Pointer to the blk_crypto_key to initialize. - * @raw_key: Pointer to the raw key. Must be the correct length for the chosen - * @crypto_mode; see blk_crypto_modes[]. + * @key_bytes: the bytes of the key + * @key_size: size of the key in bytes + * @key_type: type of the key -- either raw or hardware-wrapped * @crypto_mode: identifier for the encryption algorithm to use * @dun_bytes: number of bytes that will be used to specify the DUN when this * key is used * @data_unit_size: the data unit size to use for en/decryption * * Return: 0 on success, -errno on failure. The caller is responsible for - * zeroizing both blk_key and raw_key when done with them. + * zeroizing both blk_key and key_bytes when done with them. */ -int blk_crypto_init_key(struct blk_crypto_key *blk_key, const u8 *raw_key, +int blk_crypto_init_key(struct blk_crypto_key *blk_key, + const u8 *key_bytes, size_t key_size, + enum blk_crypto_key_type key_type, enum blk_crypto_mode_num crypto_mode, unsigned int dun_bytes, unsigned int data_unit_size) @@ -338,8 +351,19 @@ int blk_crypto_init_key(struct blk_crypto_key *blk_key, const u8 *raw_key, return -EINVAL; mode = &blk_crypto_modes[crypto_mode]; - if (mode->keysize == 0) + switch (key_type) { + case BLK_CRYPTO_KEY_TYPE_RAW: + if (key_size != mode->keysize) + return -EINVAL; + break; + case BLK_CRYPTO_KEY_TYPE_HW_WRAPPED: + if (key_size < mode->security_strength || + key_size > BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE) + return -EINVAL; + break; + default: return -EINVAL; + } if (dun_bytes == 0 || dun_bytes > mode->ivsize) return -EINVAL; @@ -350,9 +374,10 @@ int blk_crypto_init_key(struct blk_crypto_key *blk_key, const u8 *raw_key, blk_key->crypto_cfg.crypto_mode = crypto_mode; blk_key->crypto_cfg.dun_bytes = dun_bytes; blk_key->crypto_cfg.data_unit_size = data_unit_size; + blk_key->crypto_cfg.key_type = key_type; blk_key->data_unit_size_bits = ilog2(data_unit_size); - blk_key->size = mode->keysize; - memcpy(blk_key->raw, raw_key, mode->keysize); + blk_key->size = key_size; + memcpy(blk_key->bytes, key_bytes, key_size); return 0; } @@ -372,8 +397,10 @@ bool blk_crypto_config_supported_natively(struct block_device *bdev, bool blk_crypto_config_supported(struct block_device *bdev, const struct blk_crypto_config *cfg) { - return IS_ENABLED(CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK) || - blk_crypto_config_supported_natively(bdev, cfg); + if (IS_ENABLED(CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK) && + cfg->key_type == BLK_CRYPTO_KEY_TYPE_RAW) + return true; + return blk_crypto_config_supported_natively(bdev, cfg); } /** @@ -387,15 +414,21 @@ bool blk_crypto_config_supported(struct block_device *bdev, * an skcipher, and *should not* be called from the data path, since that might * cause a deadlock * - * Return: 0 on success; -ENOPKG if the hardware doesn't support the key and - * blk-crypto-fallback is either disabled or the needed algorithm - * is disabled in the crypto API; or another -errno code. + * Return: 0 on success; -EOPNOTSUPP if the key is wrapped but the hardware does + * not support wrapped keys; -ENOPKG if the key is a raw key but the + * hardware does not support raw keys and blk-crypto-fallback is either + * disabled or the needed algorithm is disabled in the crypto API; or + * another -errno code if something else went wrong. */ int blk_crypto_start_using_key(struct block_device *bdev, const struct blk_crypto_key *key) { if (blk_crypto_config_supported_natively(bdev, &key->crypto_cfg)) return 0; + if (key->crypto_cfg.key_type != BLK_CRYPTO_KEY_TYPE_RAW) { + pr_warn_ratelimited("%pg: no support for wrapped keys\n", bdev); + return -EOPNOTSUPP; + } return blk_crypto_fallback_start_using_mode(key->crypto_cfg.crypto_mode); } @@ -436,3 +469,146 @@ void blk_crypto_evict_key(struct block_device *bdev, pr_warn_ratelimited("%pg: error %d evicting key\n", bdev, err); } EXPORT_SYMBOL_GPL(blk_crypto_evict_key); + +static int blk_crypto_ioctl_import_key(struct blk_crypto_profile *profile, + void __user *argp) +{ + struct blk_crypto_import_key_arg arg; + u8 raw_key[BLK_CRYPTO_MAX_RAW_KEY_SIZE]; + u8 lt_key[BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE]; + int ret; + + if (copy_from_user(&arg, argp, sizeof(arg))) + return -EFAULT; + + if (memchr_inv(arg.reserved, 0, sizeof(arg.reserved))) + return -EINVAL; + + if (arg.raw_key_size < 16 || arg.raw_key_size > sizeof(raw_key)) + return -EINVAL; + + if (copy_from_user(raw_key, u64_to_user_ptr(arg.raw_key_ptr), + arg.raw_key_size)) { + ret = -EFAULT; + goto out; + } + ret = blk_crypto_import_key(profile, raw_key, arg.raw_key_size, lt_key); + if (ret < 0) + goto out; + if (ret > arg.lt_key_size) { + ret = -EOVERFLOW; + goto out; + } + arg.lt_key_size = ret; + if (copy_to_user(u64_to_user_ptr(arg.lt_key_ptr), lt_key, + arg.lt_key_size) || + copy_to_user(argp, &arg, sizeof(arg))) { + ret = -EFAULT; + goto out; + } + ret = 0; + +out: + memzero_explicit(raw_key, sizeof(raw_key)); + memzero_explicit(lt_key, sizeof(lt_key)); + return ret; +} + +static int blk_crypto_ioctl_generate_key(struct blk_crypto_profile *profile, + void __user *argp) +{ + struct blk_crypto_generate_key_arg arg; + u8 lt_key[BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE]; + int ret; + + if (copy_from_user(&arg, argp, sizeof(arg))) + return -EFAULT; + + if (memchr_inv(arg.reserved, 0, sizeof(arg.reserved))) + return -EINVAL; + + ret = blk_crypto_generate_key(profile, lt_key); + if (ret < 0) + goto out; + if (ret > arg.lt_key_size) { + ret = -EOVERFLOW; + goto out; + } + arg.lt_key_size = ret; + if (copy_to_user(u64_to_user_ptr(arg.lt_key_ptr), lt_key, + arg.lt_key_size) || + copy_to_user(argp, &arg, sizeof(arg))) { + ret = -EFAULT; + goto out; + } + ret = 0; + +out: + memzero_explicit(lt_key, sizeof(lt_key)); + return ret; +} + +static int blk_crypto_ioctl_prepare_key(struct blk_crypto_profile *profile, + void __user *argp) +{ + struct blk_crypto_prepare_key_arg arg; + u8 lt_key[BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE]; + u8 eph_key[BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE]; + int ret; + + if (copy_from_user(&arg, argp, sizeof(arg))) + return -EFAULT; + + if (memchr_inv(arg.reserved, 0, sizeof(arg.reserved))) + return -EINVAL; + + if (arg.lt_key_size > sizeof(lt_key)) + return -EINVAL; + + if (copy_from_user(lt_key, u64_to_user_ptr(arg.lt_key_ptr), + arg.lt_key_size)) { + ret = -EFAULT; + goto out; + } + ret = blk_crypto_prepare_key(profile, lt_key, arg.lt_key_size, eph_key); + if (ret < 0) + goto out; + if (ret > arg.eph_key_size) { + ret = -EOVERFLOW; + goto out; + } + arg.eph_key_size = ret; + if (copy_to_user(u64_to_user_ptr(arg.eph_key_ptr), eph_key, + arg.eph_key_size) || + copy_to_user(argp, &arg, sizeof(arg))) { + ret = -EFAULT; + goto out; + } + ret = 0; + +out: + memzero_explicit(lt_key, sizeof(lt_key)); + memzero_explicit(eph_key, sizeof(eph_key)); + return ret; +} + +int blk_crypto_ioctl(struct block_device *bdev, unsigned int cmd, + void __user *argp) +{ + struct blk_crypto_profile *profile = + bdev_get_queue(bdev)->crypto_profile; + + if (!profile) + return -EOPNOTSUPP; + + switch (cmd) { + case BLKCRYPTOIMPORTKEY: + return blk_crypto_ioctl_import_key(profile, argp); + case BLKCRYPTOGENERATEKEY: + return blk_crypto_ioctl_generate_key(profile, argp); + case BLKCRYPTOPREPAREKEY: + return blk_crypto_ioctl_prepare_key(profile, argp); + default: + return -ENOTTY; + } +} diff --git a/block/blk-flush.c b/block/blk-flush.c index a72e2a83d075..43d6152897a4 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -95,9 +95,9 @@ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq, blk_opf_t flags); static inline struct blk_flush_queue * -blk_get_flush_queue(struct request_queue *q, struct blk_mq_ctx *ctx) +blk_get_flush_queue(struct blk_mq_ctx *ctx) { - return blk_mq_map_queue(q, REQ_OP_FLUSH, ctx)->fq; + return blk_mq_map_queue(REQ_OP_FLUSH, ctx)->fq; } static unsigned int blk_flush_cur_seq(struct request *rq) @@ -205,7 +205,7 @@ static enum rq_end_io_ret flush_end_io(struct request *flush_rq, struct list_head *running; struct request *rq, *n; unsigned long flags = 0; - struct blk_flush_queue *fq = blk_get_flush_queue(q, flush_rq->mq_ctx); + struct blk_flush_queue *fq = blk_get_flush_queue(flush_rq->mq_ctx); /* release the tag's ownership to the req cloned from */ spin_lock_irqsave(&fq->mq_flush_lock, flags); @@ -341,7 +341,7 @@ static enum rq_end_io_ret mq_flush_data_end_io(struct request *rq, struct blk_mq_hw_ctx *hctx = rq->mq_hctx; struct blk_mq_ctx *ctx = rq->mq_ctx; unsigned long flags; - struct blk_flush_queue *fq = blk_get_flush_queue(q, ctx); + struct blk_flush_queue *fq = blk_get_flush_queue(ctx); if (q->elevator) { WARN_ON(rq->tag < 0); @@ -382,7 +382,7 @@ static void blk_rq_init_flush(struct request *rq) bool blk_insert_flush(struct request *rq) { struct request_queue *q = rq->q; - struct blk_flush_queue *fq = blk_get_flush_queue(q, rq->mq_ctx); + struct blk_flush_queue *fq = blk_get_flush_queue(rq->mq_ctx); bool supports_fua = q->limits.features & BLK_FEAT_FUA; unsigned int policy = 0; diff --git a/block/blk-integrity.c b/block/blk-integrity.c index a1678f0a9f81..e4e2567061f9 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -117,13 +117,8 @@ int blk_rq_integrity_map_user(struct request *rq, void __user *ubuf, { int ret; struct iov_iter iter; - unsigned int direction; - if (op_is_write(req_op(rq))) - direction = ITER_DEST; - else - direction = ITER_SOURCE; - iov_iter_ubuf(&iter, direction, ubuf, bytes); + iov_iter_ubuf(&iter, rq_data_dir(rq), ubuf, bytes); ret = bio_integrity_map_user(rq->bio, &iter); if (ret) return ret; diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 65a1d4427ccf..5bfd70311359 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -2718,8 +2718,7 @@ retry_lock: * All waiters are on iocg->waitq and the wait states are * synchronized using waitq.lock. */ - init_waitqueue_func_entry(&wait.wait, iocg_wake_fn); - wait.wait.private = current; + init_wait_func(&wait.wait, iocg_wake_fn); wait.bio = bio; wait.abs_cost = abs_cost; wait.committed = false; /* will be set true by waker */ @@ -3004,8 +3003,7 @@ static void ioc_pd_init(struct blkg_policy_data *pd) iocg->hweight_inuse = WEIGHT_ONE; init_waitqueue_head(&iocg->waitq); - hrtimer_init(&iocg->waitq_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); - iocg->waitq_timer.function = iocg_waitq_timer_fn; + hrtimer_setup(&iocg->waitq_timer, iocg_waitq_timer_fn, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); iocg->level = blkg->blkcg->css.cgroup->level; @@ -3224,14 +3222,16 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input, u32 qos[NR_QOS_PARAMS]; bool enable, user; char *body, *p; - unsigned int memflags; + unsigned long memflags; int ret; blkg_conf_init(&ctx, input); - ret = blkg_conf_open_bdev(&ctx); - if (ret) + memflags = blkg_conf_open_bdev_frozen(&ctx); + if (IS_ERR_VALUE(memflags)) { + ret = memflags; goto err; + } body = ctx.body; disk = ctx.bdev->bd_disk; @@ -3248,7 +3248,6 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input, ioc = q_to_ioc(disk->queue); } - memflags = blk_mq_freeze_queue(disk->queue); blk_mq_quiesce_queue(disk->queue); spin_lock_irq(&ioc->lock); @@ -3348,19 +3347,15 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input, wbt_enable_default(disk); blk_mq_unquiesce_queue(disk->queue); - blk_mq_unfreeze_queue(disk->queue, memflags); - blkg_conf_exit(&ctx); + blkg_conf_exit_frozen(&ctx, memflags); return nbytes; einval: spin_unlock_irq(&ioc->lock); - blk_mq_unquiesce_queue(disk->queue); - blk_mq_unfreeze_queue(disk->queue, memflags); - ret = -EINVAL; err: - blkg_conf_exit(&ctx); + blkg_conf_exit_frozen(&ctx, memflags); return ret; } diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c index 42c1e0b9a68f..2f8fdecdd7a9 100644 --- a/block/blk-iolatency.c +++ b/block/blk-iolatency.c @@ -658,7 +658,8 @@ static const struct rq_qos_ops blkcg_iolatency_ops = { static void blkiolatency_timer_fn(struct timer_list *t) { - struct blk_iolatency *blkiolat = from_timer(blkiolat, t, timer); + struct blk_iolatency *blkiolat = timer_container_of(blkiolat, t, + timer); struct blkcg_gq *blkg; struct cgroup_subsys_state *pos_css; u64 now = blk_time_get_ns(); diff --git a/block/blk-ioprio.c b/block/blk-ioprio.c index 8fff7ccc0ac7..13659dc15c3f 100644 --- a/block/blk-ioprio.c +++ b/block/blk-ioprio.c @@ -113,27 +113,18 @@ static void ioprio_free_cpd(struct blkcg_policy_data *cpd) kfree(blkcg); } -#define IOPRIO_ATTRS \ - { \ - .name = "prio.class", \ - .seq_show = ioprio_show_prio_policy, \ - .write = ioprio_set_prio_policy, \ - }, \ - { } /* sentinel */ - -/* cgroup v2 attributes */ static struct cftype ioprio_files[] = { - IOPRIO_ATTRS -}; - -/* cgroup v1 attributes */ -static struct cftype ioprio_legacy_files[] = { - IOPRIO_ATTRS + { + .name = "prio.class", + .seq_show = ioprio_show_prio_policy, + .write = ioprio_set_prio_policy, + }, + { } /* sentinel */ }; static struct blkcg_policy ioprio_policy = { .dfl_cftypes = ioprio_files, - .legacy_cftypes = ioprio_legacy_files, + .legacy_cftypes = ioprio_files, .cpd_alloc_fn = ioprio_alloc_cpd, .cpd_free_fn = ioprio_free_cpd, diff --git a/block/blk-map.c b/block/blk-map.c index d2f22744b3d1..23e5d5ebe59e 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -317,64 +317,26 @@ static void bio_map_kern_endio(struct bio *bio) kfree(bio); } -/** - * bio_map_kern - map kernel address into bio - * @q: the struct request_queue for the bio - * @data: pointer to buffer to map - * @len: length in bytes - * @gfp_mask: allocation flags for bio allocation - * - * Map the kernel address into a bio suitable for io to a block - * device. Returns an error pointer in case of error. - */ -static struct bio *bio_map_kern(struct request_queue *q, void *data, - unsigned int len, gfp_t gfp_mask) +static struct bio *bio_map_kern(void *data, unsigned int len, enum req_op op, + gfp_t gfp_mask) { - unsigned long kaddr = (unsigned long)data; - unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT; - unsigned long start = kaddr >> PAGE_SHIFT; - const int nr_pages = end - start; - bool is_vmalloc = is_vmalloc_addr(data); - struct page *page; - int offset, i; + unsigned int nr_vecs = bio_add_max_vecs(data, len); struct bio *bio; - bio = bio_kmalloc(nr_pages, gfp_mask); + bio = bio_kmalloc(nr_vecs, gfp_mask); if (!bio) return ERR_PTR(-ENOMEM); - bio_init(bio, NULL, bio->bi_inline_vecs, nr_pages, 0); - - if (is_vmalloc) { - flush_kernel_vmap_range(data, len); + bio_init(bio, NULL, bio->bi_inline_vecs, nr_vecs, op); + if (is_vmalloc_addr(data)) { bio->bi_private = data; - } - - offset = offset_in_page(kaddr); - for (i = 0; i < nr_pages; i++) { - unsigned int bytes = PAGE_SIZE - offset; - - if (len <= 0) - break; - - if (bytes > len) - bytes = len; - - if (!is_vmalloc) - page = virt_to_page(data); - else - page = vmalloc_to_page(data); - if (bio_add_page(bio, page, bytes, offset) < bytes) { - /* we don't support partial mappings */ + if (!bio_add_vmalloc(bio, data, len)) { bio_uninit(bio); kfree(bio); return ERR_PTR(-EINVAL); } - - data += bytes; - len -= bytes; - offset = 0; + } else { + bio_add_virt_nofail(bio, data, len); } - bio->bi_end_io = bio_map_kern_endio; return bio; } @@ -402,17 +364,16 @@ static void bio_copy_kern_endio_read(struct bio *bio) /** * bio_copy_kern - copy kernel address into bio - * @q: the struct request_queue for the bio * @data: pointer to buffer to copy * @len: length in bytes + * @op: bio/request operation * @gfp_mask: allocation flags for bio and page allocation - * @reading: data direction is READ * * copy the kernel address into a bio suitable for io to a block * device. Returns an error pointer in case of error. */ -static struct bio *bio_copy_kern(struct request_queue *q, void *data, - unsigned int len, gfp_t gfp_mask, int reading) +static struct bio *bio_copy_kern(void *data, unsigned int len, enum req_op op, + gfp_t gfp_mask) { unsigned long kaddr = (unsigned long)data; unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT; @@ -431,7 +392,7 @@ static struct bio *bio_copy_kern(struct request_queue *q, void *data, bio = bio_kmalloc(nr_pages, gfp_mask); if (!bio) return ERR_PTR(-ENOMEM); - bio_init(bio, NULL, bio->bi_inline_vecs, nr_pages, 0); + bio_init(bio, NULL, bio->bi_inline_vecs, nr_pages, op); while (len) { struct page *page; @@ -444,7 +405,7 @@ static struct bio *bio_copy_kern(struct request_queue *q, void *data, if (!page) goto cleanup; - if (!reading) + if (op_is_write(op)) memcpy(page_address(page), p, bytes); if (bio_add_page(bio, page, bytes, 0) < bytes) @@ -454,11 +415,11 @@ static struct bio *bio_copy_kern(struct request_queue *q, void *data, p += bytes; } - if (reading) { + if (op_is_write(op)) { + bio->bi_end_io = bio_copy_kern_endio; + } else { bio->bi_end_io = bio_copy_kern_endio_read; bio->bi_private = data; - } else { - bio->bi_end_io = bio_copy_kern_endio; } return bio; @@ -556,8 +517,6 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq, if (map_data) copy = true; - else if (blk_queue_may_bounce(q)) - copy = true; else if (iov_iter_alignment(iter) & align) copy = true; else if (iov_iter_is_bvec(iter)) @@ -689,7 +648,6 @@ EXPORT_SYMBOL(blk_rq_unmap_user); /** * blk_rq_map_kern - map kernel data to a request, for passthrough requests - * @q: request queue where request should be inserted * @rq: request to fill * @kbuf: the kernel buffer * @len: length of user data @@ -700,31 +658,26 @@ EXPORT_SYMBOL(blk_rq_unmap_user); * buffer is used. Can be called multiple times to append multiple * buffers. */ -int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf, - unsigned int len, gfp_t gfp_mask) +int blk_rq_map_kern(struct request *rq, void *kbuf, unsigned int len, + gfp_t gfp_mask) { - int reading = rq_data_dir(rq) == READ; unsigned long addr = (unsigned long) kbuf; struct bio *bio; int ret; - if (len > (queue_max_hw_sectors(q) << 9)) + if (len > (queue_max_hw_sectors(rq->q) << SECTOR_SHIFT)) return -EINVAL; if (!len || !kbuf) return -EINVAL; - if (!blk_rq_aligned(q, addr, len) || object_is_on_stack(kbuf) || - blk_queue_may_bounce(q)) - bio = bio_copy_kern(q, kbuf, len, gfp_mask, reading); + if (!blk_rq_aligned(rq->q, addr, len) || object_is_on_stack(kbuf)) + bio = bio_copy_kern(kbuf, len, req_op(rq), gfp_mask); else - bio = bio_map_kern(q, kbuf, len, gfp_mask); + bio = bio_map_kern(kbuf, len, req_op(rq), gfp_mask); if (IS_ERR(bio)) return PTR_ERR(bio); - bio->bi_opf &= ~REQ_OP_MASK; - bio->bi_opf |= req_op(rq); - ret = blk_rq_append_bio(rq, bio); if (unlikely(ret)) { bio_uninit(bio); diff --git a/block/blk-merge.c b/block/blk-merge.c index 1d1589c35297..70d704615be5 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -7,7 +7,6 @@ #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/blk-integrity.h> -#include <linux/scatterlist.h> #include <linux/part_stat.h> #include <linux/blk-cgroup.h> @@ -226,27 +225,6 @@ static inline unsigned get_max_io_size(struct bio *bio, } /** - * get_max_segment_size() - maximum number of bytes to add as a single segment - * @lim: Request queue limits. - * @paddr: address of the range to add - * @len: maximum length available to add at @paddr - * - * Returns the maximum number of bytes of the range starting at @paddr that can - * be added to a single segment. - */ -static inline unsigned get_max_segment_size(const struct queue_limits *lim, - phys_addr_t paddr, unsigned int len) -{ - /* - * Prevent an overflow if mask = ULONG_MAX and offset = 0 by adding 1 - * after having calculated the minimum. - */ - return min_t(unsigned long, len, - min(lim->seg_boundary_mask - (lim->seg_boundary_mask & paddr), - (unsigned long)lim->max_segment_size - 1) + 1); -} - -/** * bvec_split_segs - verify whether or not a bvec should be split in the middle * @lim: [in] queue limits to split based on * @bv: [in] bvec to examine @@ -473,117 +451,6 @@ unsigned int blk_recalc_rq_segments(struct request *rq) return nr_phys_segs; } -struct phys_vec { - phys_addr_t paddr; - u32 len; -}; - -static bool blk_map_iter_next(struct request *req, - struct req_iterator *iter, struct phys_vec *vec) -{ - unsigned int max_size; - struct bio_vec bv; - - if (req->rq_flags & RQF_SPECIAL_PAYLOAD) { - if (!iter->bio) - return false; - vec->paddr = bvec_phys(&req->special_vec); - vec->len = req->special_vec.bv_len; - iter->bio = NULL; - return true; - } - - if (!iter->iter.bi_size) - return false; - - bv = mp_bvec_iter_bvec(iter->bio->bi_io_vec, iter->iter); - vec->paddr = bvec_phys(&bv); - max_size = get_max_segment_size(&req->q->limits, vec->paddr, UINT_MAX); - bv.bv_len = min(bv.bv_len, max_size); - bio_advance_iter_single(iter->bio, &iter->iter, bv.bv_len); - - /* - * If we are entirely done with this bi_io_vec entry, check if the next - * one could be merged into it. This typically happens when moving to - * the next bio, but some callers also don't pack bvecs tight. - */ - while (!iter->iter.bi_size || !iter->iter.bi_bvec_done) { - struct bio_vec next; - - if (!iter->iter.bi_size) { - if (!iter->bio->bi_next) - break; - iter->bio = iter->bio->bi_next; - iter->iter = iter->bio->bi_iter; - } - - next = mp_bvec_iter_bvec(iter->bio->bi_io_vec, iter->iter); - if (bv.bv_len + next.bv_len > max_size || - !biovec_phys_mergeable(req->q, &bv, &next)) - break; - - bv.bv_len += next.bv_len; - bio_advance_iter_single(iter->bio, &iter->iter, next.bv_len); - } - - vec->len = bv.bv_len; - return true; -} - -static inline struct scatterlist *blk_next_sg(struct scatterlist **sg, - struct scatterlist *sglist) -{ - if (!*sg) - return sglist; - - /* - * If the driver previously mapped a shorter list, we could see a - * termination bit prematurely unless it fully inits the sg table - * on each mapping. We KNOW that there must be more entries here - * or the driver would be buggy, so force clear the termination bit - * to avoid doing a full sg_init_table() in drivers for each command. - */ - sg_unmark_end(*sg); - return sg_next(*sg); -} - -/* - * Map a request to scatterlist, return number of sg entries setup. Caller - * must make sure sg can hold rq->nr_phys_segments entries. - */ -int __blk_rq_map_sg(struct request_queue *q, struct request *rq, - struct scatterlist *sglist, struct scatterlist **last_sg) -{ - struct req_iterator iter = { - .bio = rq->bio, - }; - struct phys_vec vec; - int nsegs = 0; - - /* the internal flush request may not have bio attached */ - if (iter.bio) - iter.iter = iter.bio->bi_iter; - - while (blk_map_iter_next(rq, &iter, &vec)) { - *last_sg = blk_next_sg(last_sg, sglist); - sg_set_page(*last_sg, phys_to_page(vec.paddr), vec.len, - offset_in_page(vec.paddr)); - nsegs++; - } - - if (*last_sg) - sg_mark_end(*last_sg); - - /* - * Something must have been wrong if the figured number of - * segment is bigger than number of req's physical segments - */ - WARN_ON(nsegs > blk_rq_nr_phys_segments(rq)); - - return nsegs; -} -EXPORT_SYMBOL(__blk_rq_map_sg); - static inline unsigned int blk_rq_get_max_sectors(struct request *rq, sector_t offset) { @@ -832,6 +699,8 @@ static struct request *attempt_merge(struct request_queue *q, if (req->bio->bi_write_hint != next->bio->bi_write_hint) return NULL; + if (req->bio->bi_write_stream != next->bio->bi_write_stream) + return NULL; if (req->bio->bi_ioprio != next->bio->bi_ioprio) return NULL; if (!blk_atomic_write_mergeable_rqs(req, next)) @@ -953,6 +822,8 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio) return false; if (rq->bio->bi_write_hint != bio->bi_write_hint) return false; + if (rq->bio->bi_write_stream != bio->bi_write_stream) + return false; if (rq->bio->bi_ioprio != bio->bi_ioprio) return false; if (blk_atomic_write_mergeable_rq_bio(rq, bio) == false) @@ -1127,20 +998,20 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio, if (!plug || rq_list_empty(&plug->mq_list)) return false; - rq_list_for_each(&plug->mq_list, rq) { - if (rq->q == q) { - if (blk_attempt_bio_merge(q, rq, bio, nr_segs, false) == - BIO_MERGE_OK) - return true; - break; - } + rq = plug->mq_list.tail; + if (rq->q == q) + return blk_attempt_bio_merge(q, rq, bio, nr_segs, false) == + BIO_MERGE_OK; + else if (!plug->multiple_queues) + return false; - /* - * Only keep iterating plug list for merges if we have multiple - * queues - */ - if (!plug->multiple_queues) - break; + rq_list_for_each(&plug->mq_list, rq) { + if (rq->q != q) + continue; + if (blk_attempt_bio_merge(q, rq, bio, nr_segs, false) == + BIO_MERGE_OK) + return true; + break; } return false; } diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index adf5f0697b6b..bdcb27ab5606 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -93,6 +93,9 @@ static const char *const blk_queue_flag_name[] = { QUEUE_FLAG_NAME(RQ_ALLOC_TIME), QUEUE_FLAG_NAME(HCTX_ACTIVE), QUEUE_FLAG_NAME(SQ_SCHED), + QUEUE_FLAG_NAME(DISABLE_WBT_DEF), + QUEUE_FLAG_NAME(NO_ELV_SWITCH), + QUEUE_FLAG_NAME(QOS_ENABLED), }; #undef QUEUE_FLAG_NAME @@ -347,9 +350,14 @@ static int hctx_busy_show(void *data, struct seq_file *m) { struct blk_mq_hw_ctx *hctx = data; struct show_busy_params params = { .m = m, .hctx = hctx }; + int res; + res = mutex_lock_interruptible(&hctx->queue->elevator_lock); + if (res) + return res; blk_mq_tagset_busy_iter(hctx->queue->tag_set, hctx_show_busy_rq, ¶ms); + mutex_unlock(&hctx->queue->elevator_lock); return 0; } @@ -400,15 +408,14 @@ static int hctx_tags_show(void *data, struct seq_file *m) struct request_queue *q = hctx->queue; int res; - res = mutex_lock_interruptible(&q->sysfs_lock); + res = mutex_lock_interruptible(&q->elevator_lock); if (res) - goto out; + return res; if (hctx->tags) blk_mq_debugfs_tags_show(m, hctx->tags); - mutex_unlock(&q->sysfs_lock); + mutex_unlock(&q->elevator_lock); -out: - return res; + return 0; } static int hctx_tags_bitmap_show(void *data, struct seq_file *m) @@ -417,15 +424,14 @@ static int hctx_tags_bitmap_show(void *data, struct seq_file *m) struct request_queue *q = hctx->queue; int res; - res = mutex_lock_interruptible(&q->sysfs_lock); + res = mutex_lock_interruptible(&q->elevator_lock); if (res) - goto out; + return res; if (hctx->tags) sbitmap_bitmap_show(&hctx->tags->bitmap_tags.sb, m); - mutex_unlock(&q->sysfs_lock); + mutex_unlock(&q->elevator_lock); -out: - return res; + return 0; } static int hctx_sched_tags_show(void *data, struct seq_file *m) @@ -434,15 +440,14 @@ static int hctx_sched_tags_show(void *data, struct seq_file *m) struct request_queue *q = hctx->queue; int res; - res = mutex_lock_interruptible(&q->sysfs_lock); + res = mutex_lock_interruptible(&q->elevator_lock); if (res) - goto out; + return res; if (hctx->sched_tags) blk_mq_debugfs_tags_show(m, hctx->sched_tags); - mutex_unlock(&q->sysfs_lock); + mutex_unlock(&q->elevator_lock); -out: - return res; + return 0; } static int hctx_sched_tags_bitmap_show(void *data, struct seq_file *m) @@ -451,15 +456,14 @@ static int hctx_sched_tags_bitmap_show(void *data, struct seq_file *m) struct request_queue *q = hctx->queue; int res; - res = mutex_lock_interruptible(&q->sysfs_lock); + res = mutex_lock_interruptible(&q->elevator_lock); if (res) - goto out; + return res; if (hctx->sched_tags) sbitmap_bitmap_show(&hctx->sched_tags->bitmap_tags.sb, m); - mutex_unlock(&q->sysfs_lock); + mutex_unlock(&q->elevator_lock); -out: - return res; + return 0; } static int hctx_active_show(void *data, struct seq_file *m) @@ -623,20 +627,9 @@ void blk_mq_debugfs_register(struct request_queue *q) debugfs_create_files(q->debugfs_dir, q, blk_mq_debugfs_queue_attrs); - /* - * blk_mq_init_sched() attempted to do this already, but q->debugfs_dir - * didn't exist yet (because we don't know what to name the directory - * until the queue is registered to a gendisk). - */ - if (q->elevator && !q->sched_debugfs_dir) - blk_mq_debugfs_register_sched(q); - - /* Similarly, blk_mq_init_hctx() couldn't do this previously. */ queue_for_each_hw_ctx(q, hctx, i) { if (!hctx->debugfs_dir) blk_mq_debugfs_register_hctx(q, hctx); - if (q->elevator && !hctx->sched_debugfs_dir) - blk_mq_debugfs_register_sched_hctx(q, hctx); } if (q->rq_qos) { diff --git a/block/blk-mq-dma.c b/block/blk-mq-dma.c new file mode 100644 index 000000000000..82bae475dfa4 --- /dev/null +++ b/block/blk-mq-dma.c @@ -0,0 +1,116 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2025 Christoph Hellwig + */ +#include "blk.h" + +struct phys_vec { + phys_addr_t paddr; + u32 len; +}; + +static bool blk_map_iter_next(struct request *req, struct req_iterator *iter, + struct phys_vec *vec) +{ + unsigned int max_size; + struct bio_vec bv; + + if (req->rq_flags & RQF_SPECIAL_PAYLOAD) { + if (!iter->bio) + return false; + vec->paddr = bvec_phys(&req->special_vec); + vec->len = req->special_vec.bv_len; + iter->bio = NULL; + return true; + } + + if (!iter->iter.bi_size) + return false; + + bv = mp_bvec_iter_bvec(iter->bio->bi_io_vec, iter->iter); + vec->paddr = bvec_phys(&bv); + max_size = get_max_segment_size(&req->q->limits, vec->paddr, UINT_MAX); + bv.bv_len = min(bv.bv_len, max_size); + bio_advance_iter_single(iter->bio, &iter->iter, bv.bv_len); + + /* + * If we are entirely done with this bi_io_vec entry, check if the next + * one could be merged into it. This typically happens when moving to + * the next bio, but some callers also don't pack bvecs tight. + */ + while (!iter->iter.bi_size || !iter->iter.bi_bvec_done) { + struct bio_vec next; + + if (!iter->iter.bi_size) { + if (!iter->bio->bi_next) + break; + iter->bio = iter->bio->bi_next; + iter->iter = iter->bio->bi_iter; + } + + next = mp_bvec_iter_bvec(iter->bio->bi_io_vec, iter->iter); + if (bv.bv_len + next.bv_len > max_size || + !biovec_phys_mergeable(req->q, &bv, &next)) + break; + + bv.bv_len += next.bv_len; + bio_advance_iter_single(iter->bio, &iter->iter, next.bv_len); + } + + vec->len = bv.bv_len; + return true; +} + +static inline struct scatterlist * +blk_next_sg(struct scatterlist **sg, struct scatterlist *sglist) +{ + if (!*sg) + return sglist; + + /* + * If the driver previously mapped a shorter list, we could see a + * termination bit prematurely unless it fully inits the sg table + * on each mapping. We KNOW that there must be more entries here + * or the driver would be buggy, so force clear the termination bit + * to avoid doing a full sg_init_table() in drivers for each command. + */ + sg_unmark_end(*sg); + return sg_next(*sg); +} + +/* + * Map a request to scatterlist, return number of sg entries setup. Caller + * must make sure sg can hold rq->nr_phys_segments entries. + */ +int __blk_rq_map_sg(struct request *rq, struct scatterlist *sglist, + struct scatterlist **last_sg) +{ + struct req_iterator iter = { + .bio = rq->bio, + }; + struct phys_vec vec; + int nsegs = 0; + + /* the internal flush request may not have bio attached */ + if (iter.bio) + iter.iter = iter.bio->bi_iter; + + while (blk_map_iter_next(rq, &iter, &vec)) { + *last_sg = blk_next_sg(last_sg, sglist); + sg_set_page(*last_sg, phys_to_page(vec.paddr), vec.len, + offset_in_page(vec.paddr)); + nsegs++; + } + + if (*last_sg) + sg_mark_end(*last_sg); + + /* + * Something must have been wrong if the figured number of + * segment is bigger than number of req's physical segments + */ + WARN_ON(nsegs > blk_rq_nr_phys_segments(rq)); + + return nsegs; +} +EXPORT_SYMBOL(__blk_rq_map_sg); diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 7442ca27c2bf..e2ce4a28e6c9 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -59,19 +59,17 @@ static bool blk_mq_dispatch_hctx_list(struct list_head *rq_list) list_first_entry(rq_list, struct request, queuelist)->mq_hctx; struct request *rq; LIST_HEAD(hctx_list); - unsigned int count = 0; list_for_each_entry(rq, rq_list, queuelist) { if (rq->mq_hctx != hctx) { list_cut_before(&hctx_list, rq_list, &rq->queuelist); goto dispatch; } - count++; } list_splice_tail_init(rq_list, &hctx_list); dispatch: - return blk_mq_dispatch_rq_list(hctx, &hctx_list, count); + return blk_mq_dispatch_rq_list(hctx, &hctx_list, false); } #define BLK_MQ_BUDGET_DELAY 3 /* ms units */ @@ -167,7 +165,7 @@ static int __blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx) dispatched |= blk_mq_dispatch_hctx_list(&rq_list); } while (!list_empty(&rq_list)); } else { - dispatched = blk_mq_dispatch_rq_list(hctx, &rq_list, count); + dispatched = blk_mq_dispatch_rq_list(hctx, &rq_list, false); } if (busy) @@ -261,7 +259,7 @@ static int blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx) /* round robin for fair dispatch */ ctx = blk_mq_next_ctx(hctx, rq->mq_ctx); - } while (blk_mq_dispatch_rq_list(rq->mq_hctx, &rq_list, 1)); + } while (blk_mq_dispatch_rq_list(rq->mq_hctx, &rq_list, false)); WRITE_ONCE(hctx->dispatch_from, ctx); return ret; @@ -298,7 +296,7 @@ static int __blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx) */ if (!list_empty(&rq_list)) { blk_mq_sched_mark_restart_hctx(hctx); - if (!blk_mq_dispatch_rq_list(hctx, &rq_list, 0)) + if (!blk_mq_dispatch_rq_list(hctx, &rq_list, true)) return 0; need_dispatch = true; } else { @@ -312,7 +310,7 @@ static int __blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx) if (need_dispatch) return blk_mq_do_dispatch_ctx(hctx); blk_mq_flush_busy_ctxs(hctx, &rq_list); - blk_mq_dispatch_rq_list(hctx, &rq_list, 0); + blk_mq_dispatch_rq_list(hctx, &rq_list, true); return 0; } @@ -349,7 +347,7 @@ bool blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio, } ctx = blk_mq_get_ctx(q); - hctx = blk_mq_map_queue(q, bio->bi_opf, ctx); + hctx = blk_mq_map_queue(bio->bi_opf, ctx); type = hctx->type; if (list_empty_careful(&ctx->rq_lists[type])) goto out_put; @@ -376,68 +374,177 @@ bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq, } EXPORT_SYMBOL_GPL(blk_mq_sched_try_insert_merge); -static int blk_mq_sched_alloc_map_and_rqs(struct request_queue *q, - struct blk_mq_hw_ctx *hctx, - unsigned int hctx_idx) +/* called in queue's release handler, tagset has gone away */ +static void blk_mq_sched_tags_teardown(struct request_queue *q, unsigned int flags) { - if (blk_mq_is_shared_tags(q->tag_set->flags)) { - hctx->sched_tags = q->sched_shared_tags; - return 0; - } + struct blk_mq_hw_ctx *hctx; + unsigned long i; - hctx->sched_tags = blk_mq_alloc_map_and_rqs(q->tag_set, hctx_idx, - q->nr_requests); + queue_for_each_hw_ctx(q, hctx, i) + hctx->sched_tags = NULL; - if (!hctx->sched_tags) - return -ENOMEM; - return 0; + if (blk_mq_is_shared_tags(flags)) + q->sched_shared_tags = NULL; } -static void blk_mq_exit_sched_shared_tags(struct request_queue *queue) +void blk_mq_sched_reg_debugfs(struct request_queue *q) { - blk_mq_free_rq_map(queue->sched_shared_tags); - queue->sched_shared_tags = NULL; + struct blk_mq_hw_ctx *hctx; + unsigned long i; + + mutex_lock(&q->debugfs_mutex); + blk_mq_debugfs_register_sched(q); + queue_for_each_hw_ctx(q, hctx, i) + blk_mq_debugfs_register_sched_hctx(q, hctx); + mutex_unlock(&q->debugfs_mutex); } -/* called in queue's release handler, tagset has gone away */ -static void blk_mq_sched_tags_teardown(struct request_queue *q, unsigned int flags) +void blk_mq_sched_unreg_debugfs(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned long i; - queue_for_each_hw_ctx(q, hctx, i) { - if (hctx->sched_tags) { - if (!blk_mq_is_shared_tags(flags)) - blk_mq_free_rq_map(hctx->sched_tags); - hctx->sched_tags = NULL; - } + mutex_lock(&q->debugfs_mutex); + queue_for_each_hw_ctx(q, hctx, i) + blk_mq_debugfs_unregister_sched_hctx(hctx); + blk_mq_debugfs_unregister_sched(q); + mutex_unlock(&q->debugfs_mutex); +} + +void blk_mq_free_sched_tags(struct elevator_tags *et, + struct blk_mq_tag_set *set) +{ + unsigned long i; + + /* Shared tags are stored at index 0 in @tags. */ + if (blk_mq_is_shared_tags(set->flags)) + blk_mq_free_map_and_rqs(set, et->tags[0], BLK_MQ_NO_HCTX_IDX); + else { + for (i = 0; i < et->nr_hw_queues; i++) + blk_mq_free_map_and_rqs(set, et->tags[i], i); } - if (blk_mq_is_shared_tags(flags)) - blk_mq_exit_sched_shared_tags(q); + kfree(et); } -static int blk_mq_init_sched_shared_tags(struct request_queue *queue) +void blk_mq_free_sched_tags_batch(struct xarray *et_table, + struct blk_mq_tag_set *set) { - struct blk_mq_tag_set *set = queue->tag_set; + struct request_queue *q; + struct elevator_tags *et; + lockdep_assert_held_write(&set->update_nr_hwq_lock); + + list_for_each_entry(q, &set->tag_list, tag_set_list) { + /* + * Accessing q->elevator without holding q->elevator_lock is + * safe because we're holding here set->update_nr_hwq_lock in + * the writer context. So, scheduler update/switch code (which + * acquires the same lock but in the reader context) can't run + * concurrently. + */ + if (q->elevator) { + et = xa_load(et_table, q->id); + if (unlikely(!et)) + WARN_ON_ONCE(1); + else + blk_mq_free_sched_tags(et, set); + } + } +} + +struct elevator_tags *blk_mq_alloc_sched_tags(struct blk_mq_tag_set *set, + unsigned int nr_hw_queues) +{ + unsigned int nr_tags; + int i; + struct elevator_tags *et; + gfp_t gfp = GFP_NOIO | __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY; + + if (blk_mq_is_shared_tags(set->flags)) + nr_tags = 1; + else + nr_tags = nr_hw_queues; + + et = kmalloc(sizeof(struct elevator_tags) + + nr_tags * sizeof(struct blk_mq_tags *), gfp); + if (!et) + return NULL; /* - * Set initial depth at max so that we don't need to reallocate for - * updating nr_requests. + * Default to double of smaller one between hw queue_depth and + * 128, since we don't split into sync/async like the old code + * did. Additionally, this is a per-hw queue depth. */ - queue->sched_shared_tags = blk_mq_alloc_map_and_rqs(set, - BLK_MQ_NO_HCTX_IDX, - MAX_SCHED_RQ); - if (!queue->sched_shared_tags) - return -ENOMEM; + et->nr_requests = 2 * min_t(unsigned int, set->queue_depth, + BLKDEV_DEFAULT_RQ); + et->nr_hw_queues = nr_hw_queues; + + if (blk_mq_is_shared_tags(set->flags)) { + /* Shared tags are stored at index 0 in @tags. */ + et->tags[0] = blk_mq_alloc_map_and_rqs(set, BLK_MQ_NO_HCTX_IDX, + MAX_SCHED_RQ); + if (!et->tags[0]) + goto out; + } else { + for (i = 0; i < et->nr_hw_queues; i++) { + et->tags[i] = blk_mq_alloc_map_and_rqs(set, i, + et->nr_requests); + if (!et->tags[i]) + goto out_unwind; + } + } - blk_mq_tag_update_sched_shared_tags(queue); + return et; +out_unwind: + while (--i >= 0) + blk_mq_free_map_and_rqs(set, et->tags[i], i); +out: + kfree(et); + return NULL; +} + +int blk_mq_alloc_sched_tags_batch(struct xarray *et_table, + struct blk_mq_tag_set *set, unsigned int nr_hw_queues) +{ + struct request_queue *q; + struct elevator_tags *et; + gfp_t gfp = GFP_NOIO | __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY; + lockdep_assert_held_write(&set->update_nr_hwq_lock); + + list_for_each_entry(q, &set->tag_list, tag_set_list) { + /* + * Accessing q->elevator without holding q->elevator_lock is + * safe because we're holding here set->update_nr_hwq_lock in + * the writer context. So, scheduler update/switch code (which + * acquires the same lock but in the reader context) can't run + * concurrently. + */ + if (q->elevator) { + et = blk_mq_alloc_sched_tags(set, nr_hw_queues); + if (!et) + goto out_unwind; + if (xa_insert(et_table, q->id, et, gfp)) + goto out_free_tags; + } + } return 0; +out_free_tags: + blk_mq_free_sched_tags(et, set); +out_unwind: + list_for_each_entry_continue_reverse(q, &set->tag_list, tag_set_list) { + if (q->elevator) { + et = xa_load(et_table, q->id); + if (et) + blk_mq_free_sched_tags(et, set); + } + } + return -ENOMEM; } /* caller must have a reference to @e, will grab another one if successful */ -int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e) +int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e, + struct elevator_tags *et) { unsigned int flags = q->tag_set->flags; struct blk_mq_hw_ctx *hctx; @@ -445,56 +552,44 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e) unsigned long i; int ret; - /* - * Default to double of smaller one between hw queue_depth and 128, - * since we don't split into sync/async like the old code did. - * Additionally, this is a per-hw queue depth. - */ - q->nr_requests = 2 * min_t(unsigned int, q->tag_set->queue_depth, - BLKDEV_DEFAULT_RQ); + eq = elevator_alloc(q, e, et); + if (!eq) + return -ENOMEM; + + q->nr_requests = et->nr_requests; if (blk_mq_is_shared_tags(flags)) { - ret = blk_mq_init_sched_shared_tags(q); - if (ret) - return ret; + /* Shared tags are stored at index 0 in @et->tags. */ + q->sched_shared_tags = et->tags[0]; + blk_mq_tag_update_sched_shared_tags(q); } queue_for_each_hw_ctx(q, hctx, i) { - ret = blk_mq_sched_alloc_map_and_rqs(q, hctx, i); - if (ret) - goto err_free_map_and_rqs; + if (blk_mq_is_shared_tags(flags)) + hctx->sched_tags = q->sched_shared_tags; + else + hctx->sched_tags = et->tags[i]; } - ret = e->ops.init_sched(q, e); + ret = e->ops.init_sched(q, eq); if (ret) - goto err_free_map_and_rqs; - - mutex_lock(&q->debugfs_mutex); - blk_mq_debugfs_register_sched(q); - mutex_unlock(&q->debugfs_mutex); + goto out; queue_for_each_hw_ctx(q, hctx, i) { if (e->ops.init_hctx) { ret = e->ops.init_hctx(hctx, i); if (ret) { - eq = q->elevator; - blk_mq_sched_free_rqs(q); blk_mq_exit_sched(q, eq); kobject_put(&eq->kobj); return ret; } } - mutex_lock(&q->debugfs_mutex); - blk_mq_debugfs_register_sched_hctx(q, hctx); - mutex_unlock(&q->debugfs_mutex); } - return 0; -err_free_map_and_rqs: - blk_mq_sched_free_rqs(q); +out: blk_mq_sched_tags_teardown(q, flags); - + kobject_put(&eq->kobj); q->elevator = NULL; return ret; } @@ -527,10 +622,6 @@ void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e) unsigned int flags = 0; queue_for_each_hw_ctx(q, hctx, i) { - mutex_lock(&q->debugfs_mutex); - blk_mq_debugfs_unregister_sched_hctx(hctx); - mutex_unlock(&q->debugfs_mutex); - if (e->type->ops.exit_hctx && hctx->sched_data) { e->type->ops.exit_hctx(hctx, i); hctx->sched_data = NULL; @@ -538,12 +629,9 @@ void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e) flags = hctx->flags; } - mutex_lock(&q->debugfs_mutex); - blk_mq_debugfs_unregister_sched(q); - mutex_unlock(&q->debugfs_mutex); - if (e->type->ops.exit_sched) e->type->ops.exit_sched(e); blk_mq_sched_tags_teardown(q, flags); + set_bit(ELEVATOR_FLAG_DYING, &q->elevator->flags); q->elevator = NULL; } diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h index 1326526bb733..b554e1d55950 100644 --- a/block/blk-mq-sched.h +++ b/block/blk-mq-sched.h @@ -18,10 +18,20 @@ void __blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx); void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx); -int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e); +int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e, + struct elevator_tags *et); void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e); void blk_mq_sched_free_rqs(struct request_queue *q); +struct elevator_tags *blk_mq_alloc_sched_tags(struct blk_mq_tag_set *set, + unsigned int nr_hw_queues); +int blk_mq_alloc_sched_tags_batch(struct xarray *et_table, + struct blk_mq_tag_set *set, unsigned int nr_hw_queues); +void blk_mq_free_sched_tags(struct elevator_tags *et, + struct blk_mq_tag_set *set); +void blk_mq_free_sched_tags_batch(struct xarray *et_table, + struct blk_mq_tag_set *set); + static inline void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx) { if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c index 3feeeccf8a99..24656980f443 100644 --- a/block/blk-mq-sysfs.c +++ b/block/blk-mq-sysfs.c @@ -61,9 +61,9 @@ static ssize_t blk_mq_hw_sysfs_show(struct kobject *kobj, if (!entry->show) return -EIO; - mutex_lock(&q->sysfs_lock); + mutex_lock(&q->elevator_lock); res = entry->show(hctx, page); - mutex_unlock(&q->sysfs_lock); + mutex_unlock(&q->elevator_lock); return res; } diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index b9f417d980b4..d880c50629d6 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -190,8 +190,7 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data) sbitmap_finish_wait(bt, ws, &wait); data->ctx = blk_mq_get_ctx(data->q); - data->hctx = blk_mq_map_queue(data->q, data->cmd_flags, - data->ctx); + data->hctx = blk_mq_map_queue(data->cmd_flags, data->ctx); tags = blk_mq_tags_from_data(data); if (data->flags & BLK_MQ_REQ_RESERVED) bt = &tags->breserved_tags; diff --git a/block/blk-mq.c b/block/blk-mq.c index 005c520d3498..355db0abe44b 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -89,7 +89,7 @@ struct mq_inflight { unsigned int inflight[2]; }; -static bool blk_mq_check_inflight(struct request *rq, void *priv) +static bool blk_mq_check_in_driver(struct request *rq, void *priv) { struct mq_inflight *mi = priv; @@ -101,24 +101,14 @@ static bool blk_mq_check_inflight(struct request *rq, void *priv) return true; } -unsigned int blk_mq_in_flight(struct request_queue *q, - struct block_device *part) +void blk_mq_in_driver_rw(struct block_device *part, unsigned int inflight[2]) { struct mq_inflight mi = { .part = part }; - blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi); - - return mi.inflight[0] + mi.inflight[1]; -} - -void blk_mq_in_flight_rw(struct request_queue *q, struct block_device *part, - unsigned int inflight[2]) -{ - struct mq_inflight mi = { .part = part }; - - blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi); - inflight[0] = mi.inflight[0]; - inflight[1] = mi.inflight[1]; + blk_mq_queue_tag_busy_iter(bdev_get_queue(part), blk_mq_check_in_driver, + &mi); + inflight[READ] = mi.inflight[READ]; + inflight[WRITE] = mi.inflight[WRITE]; } #ifdef CONFIG_LOCKDEP @@ -508,7 +498,7 @@ static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data) retry: data->ctx = blk_mq_get_ctx(q); - data->hctx = blk_mq_map_queue(q, data->cmd_flags, data->ctx); + data->hctx = blk_mq_map_queue(data->cmd_flags, data->ctx); if (q->elevator) { /* @@ -584,9 +574,13 @@ static struct request *blk_mq_rq_cache_fill(struct request_queue *q, struct blk_mq_alloc_data data = { .q = q, .flags = flags, + .shallow_depth = 0, .cmd_flags = opf, + .rq_flags = 0, .nr_tags = plug->nr_ios, .cached_rqs = &plug->cached_rqs, + .ctx = NULL, + .hctx = NULL }; struct request *rq; @@ -646,8 +640,13 @@ struct request *blk_mq_alloc_request(struct request_queue *q, blk_opf_t opf, struct blk_mq_alloc_data data = { .q = q, .flags = flags, + .shallow_depth = 0, .cmd_flags = opf, + .rq_flags = 0, .nr_tags = 1, + .cached_rqs = NULL, + .ctx = NULL, + .hctx = NULL }; int ret; @@ -675,8 +674,13 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, struct blk_mq_alloc_data data = { .q = q, .flags = flags, + .shallow_depth = 0, .cmd_flags = opf, + .rq_flags = 0, .nr_tags = 1, + .cached_rqs = NULL, + .ctx = NULL, + .hctx = NULL }; u64 alloc_time_ns = 0; struct request *rq; @@ -2080,7 +2084,7 @@ static void blk_mq_commit_rqs(struct blk_mq_hw_ctx *hctx, int queued, * Returns true if we did some work AND can potentially do more. */ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list, - unsigned int nr_budgets) + bool get_budget) { enum prep_dispatch prep; struct request_queue *q = hctx->queue; @@ -2102,7 +2106,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list, rq = list_first_entry(list, struct request, queuelist); WARN_ON_ONCE(hctx != rq->mq_hctx); - prep = blk_mq_prep_dispatch_rq(rq, !nr_budgets); + prep = blk_mq_prep_dispatch_rq(rq, get_budget); if (prep != PREP_DISPATCH_OK) break; @@ -2111,12 +2115,6 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list, bd.rq = rq; bd.last = list_empty(list); - /* - * once the request is queued to lld, no need to cover the - * budget any more - */ - if (nr_budgets) - nr_budgets--; ret = q->mq_ops->queue_rq(hctx, &bd); switch (ret) { case BLK_STS_OK: @@ -2150,7 +2148,11 @@ out: ((hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) || blk_mq_is_shared_tags(hctx->flags)); - if (nr_budgets) + /* + * If the caller allocated budgets, free the budgets of the + * requests that have not yet been passed to the block driver. + */ + if (!get_budget) blk_mq_release_budgets(q, list); spin_lock(&hctx->lock); @@ -2778,15 +2780,15 @@ static blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last) return __blk_mq_issue_directly(hctx, rq, last); } -static void blk_mq_plug_issue_direct(struct blk_plug *plug) +static void blk_mq_issue_direct(struct rq_list *rqs) { struct blk_mq_hw_ctx *hctx = NULL; struct request *rq; int queued = 0; blk_status_t ret = BLK_STS_OK; - while ((rq = rq_list_pop(&plug->mq_list))) { - bool last = rq_list_empty(&plug->mq_list); + while ((rq = rq_list_pop(rqs))) { + bool last = rq_list_empty(rqs); if (hctx != rq->mq_hctx) { if (hctx) { @@ -2817,15 +2819,64 @@ out: blk_mq_commit_rqs(hctx, queued, false); } -static void __blk_mq_flush_plug_list(struct request_queue *q, - struct blk_plug *plug) +static void __blk_mq_flush_list(struct request_queue *q, struct rq_list *rqs) { if (blk_queue_quiesced(q)) return; - q->mq_ops->queue_rqs(&plug->mq_list); + q->mq_ops->queue_rqs(rqs); +} + +static unsigned blk_mq_extract_queue_requests(struct rq_list *rqs, + struct rq_list *queue_rqs) +{ + struct request *rq = rq_list_pop(rqs); + struct request_queue *this_q = rq->q; + struct request **prev = &rqs->head; + struct rq_list matched_rqs = {}; + struct request *last = NULL; + unsigned depth = 1; + + rq_list_add_tail(&matched_rqs, rq); + while ((rq = *prev)) { + if (rq->q == this_q) { + /* move rq from rqs to matched_rqs */ + *prev = rq->rq_next; + rq_list_add_tail(&matched_rqs, rq); + depth++; + } else { + /* leave rq in rqs */ + prev = &rq->rq_next; + last = rq; + } + } + + rqs->tail = last; + *queue_rqs = matched_rqs; + return depth; } -static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched) +static void blk_mq_dispatch_queue_requests(struct rq_list *rqs, unsigned depth) +{ + struct request_queue *q = rq_list_peek(rqs)->q; + + trace_block_unplug(q, depth, true); + + /* + * Peek first request and see if we have a ->queue_rqs() hook. + * If we do, we can dispatch the whole list in one go. + * We already know at this point that all requests belong to the + * same queue, caller must ensure that's the case. + */ + if (q->mq_ops->queue_rqs) { + blk_mq_run_dispatch_ops(q, __blk_mq_flush_list(q, rqs)); + if (rq_list_empty(rqs)) + return; + } + + blk_mq_run_dispatch_ops(q, blk_mq_issue_direct(rqs)); +} + +static void blk_mq_dispatch_list(struct rq_list *rqs, bool from_sched) { struct blk_mq_hw_ctx *this_hctx = NULL; struct blk_mq_ctx *this_ctx = NULL; @@ -2835,7 +2886,7 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched) LIST_HEAD(list); do { - struct request *rq = rq_list_pop(&plug->mq_list); + struct request *rq = rq_list_pop(rqs); if (!this_hctx) { this_hctx = rq->mq_hctx; @@ -2848,9 +2899,9 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched) } list_add_tail(&rq->queuelist, &list); depth++; - } while (!rq_list_empty(&plug->mq_list)); + } while (!rq_list_empty(rqs)); - plug->mq_list = requeue_list; + *rqs = requeue_list; trace_block_unplug(this_hctx->queue, depth, !from_sched); percpu_ref_get(&this_hctx->queue->q_usage_counter); @@ -2870,9 +2921,21 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched) percpu_ref_put(&this_hctx->queue->q_usage_counter); } +static void blk_mq_dispatch_multiple_queue_requests(struct rq_list *rqs) +{ + do { + struct rq_list queue_rqs; + unsigned depth; + + depth = blk_mq_extract_queue_requests(rqs, &queue_rqs); + blk_mq_dispatch_queue_requests(&queue_rqs, depth); + while (!rq_list_empty(&queue_rqs)) + blk_mq_dispatch_list(&queue_rqs, false); + } while (!rq_list_empty(rqs)); +} + void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule) { - struct request *rq; unsigned int depth; /* @@ -2887,34 +2950,19 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule) depth = plug->rq_count; plug->rq_count = 0; - if (!plug->multiple_queues && !plug->has_elevator && !from_schedule) { - struct request_queue *q; - - rq = rq_list_peek(&plug->mq_list); - q = rq->q; - trace_block_unplug(q, depth, true); - - /* - * Peek first request and see if we have a ->queue_rqs() hook. - * If we do, we can dispatch the whole plug list in one go. We - * already know at this point that all requests belong to the - * same queue, caller must ensure that's the case. - */ - if (q->mq_ops->queue_rqs) { - blk_mq_run_dispatch_ops(q, - __blk_mq_flush_plug_list(q, plug)); - if (rq_list_empty(&plug->mq_list)) - return; + if (!plug->has_elevator && !from_schedule) { + if (plug->multiple_queues) { + blk_mq_dispatch_multiple_queue_requests(&plug->mq_list); + return; } - blk_mq_run_dispatch_ops(q, - blk_mq_plug_issue_direct(plug)); + blk_mq_dispatch_queue_requests(&plug->mq_list, depth); if (rq_list_empty(&plug->mq_list)) return; } do { - blk_mq_dispatch_plug_list(plug, from_schedule); + blk_mq_dispatch_list(&plug->mq_list, from_schedule); } while (!rq_list_empty(&plug->mq_list)); } @@ -2965,13 +3013,18 @@ static bool blk_mq_attempt_bio_merge(struct request_queue *q, static struct request *blk_mq_get_new_requests(struct request_queue *q, struct blk_plug *plug, - struct bio *bio, - unsigned int nsegs) + struct bio *bio) { struct blk_mq_alloc_data data = { .q = q, - .nr_tags = 1, + .flags = 0, + .shallow_depth = 0, .cmd_flags = bio->bi_opf, + .rq_flags = 0, + .nr_tags = 1, + .cached_rqs = NULL, + .ctx = NULL, + .hctx = NULL }; struct request *rq; @@ -3081,8 +3134,6 @@ void blk_mq_submit_bio(struct bio *bio) goto new_request; } - bio = blk_queue_bounce(bio, q); - /* * The cached request already holds a q_usage_counter reference and we * don't have to acquire a new one if we use it. @@ -3118,14 +3169,16 @@ void blk_mq_submit_bio(struct bio *bio) if (blk_mq_attempt_bio_merge(q, bio, nr_segs)) goto queue_exit; - if (blk_queue_is_zoned(q) && blk_zone_plug_bio(bio, nr_segs)) - goto queue_exit; + if (bio_needs_zone_write_plugging(bio)) { + if (blk_zone_plug_bio(bio, nr_segs)) + goto queue_exit; + } new_request: if (rq) { blk_mq_use_cached_rq(rq, plug, bio); } else { - rq = blk_mq_get_new_requests(q, plug, bio, nr_segs); + rq = blk_mq_get_new_requests(q, plug, bio); if (unlikely(!rq)) { if (bio->bi_opf & REQ_NOWAIT) bio_wouldblock_error(bio); @@ -4461,14 +4514,12 @@ static struct blk_mq_hw_ctx *blk_mq_alloc_and_init_hctx( return NULL; } -static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, - struct request_queue *q) +static void __blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, + struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned long i, j; - /* protect against switching io scheduler */ - mutex_lock(&q->sysfs_lock); for (i = 0; i < set->nr_hw_queues; i++) { int old_node; int node = blk_mq_get_hctx_node(set, i); @@ -4501,7 +4552,12 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, xa_for_each_start(&q->hctx_table, j, hctx, j) blk_mq_exit_hctx(q, set, hctx, j); - mutex_unlock(&q->sysfs_lock); +} + +static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, + struct request_queue *q) +{ + __blk_mq_realloc_hw_ctxs(set, q); /* unregister cpuhp callbacks for exited hctxs */ blk_mq_remove_hw_queues_cpuhp(q); @@ -4550,8 +4606,8 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, q->nr_requests = set->queue_depth; blk_mq_init_cpu_queues(q, set->nr_hw_queues); - blk_mq_add_queue_tag_set(set, q); blk_mq_map_swqueue(q); + blk_mq_add_queue_tag_set(set, q); return 0; err_hctxs: @@ -4771,6 +4827,8 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set) goto out_free_srcu; } + init_rwsem(&set->update_nr_hwq_lock); + ret = -ENOMEM; set->tags = kcalloc_node(set->nr_hw_queues, sizeof(struct blk_mq_tags *), GFP_KERNEL, @@ -4911,91 +4969,69 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr) } /* - * request_queue and elevator_type pair. - * It is just used by __blk_mq_update_nr_hw_queues to cache - * the elevator_type associated with a request_queue. + * Switch back to the elevator type stored in the xarray. */ -struct blk_mq_qe_pair { - struct list_head node; - struct request_queue *q; - struct elevator_type *type; -}; - -/* - * Cache the elevator_type in qe pair list and switch the - * io scheduler to 'none' - */ -static bool blk_mq_elv_switch_none(struct list_head *head, - struct request_queue *q) +static void blk_mq_elv_switch_back(struct request_queue *q, + struct xarray *elv_tbl, struct xarray *et_tbl) { - struct blk_mq_qe_pair *qe; + struct elevator_type *e = xa_load(elv_tbl, q->id); + struct elevator_tags *t = xa_load(et_tbl, q->id); - qe = kmalloc(sizeof(*qe), GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY); - if (!qe) - return false; + /* The elv_update_nr_hw_queues unfreezes the queue. */ + elv_update_nr_hw_queues(q, e, t); - /* q->elevator needs protection from ->sysfs_lock */ - mutex_lock(&q->sysfs_lock); - - /* the check has to be done with holding sysfs_lock */ - if (!q->elevator) { - kfree(qe); - goto unlock; - } - - INIT_LIST_HEAD(&qe->node); - qe->q = q; - qe->type = q->elevator->type; - /* keep a reference to the elevator module as we'll switch back */ - __elevator_get(qe->type); - list_add(&qe->node, head); - elevator_disable(q); -unlock: - mutex_unlock(&q->sysfs_lock); - - return true; + /* Drop the reference acquired in blk_mq_elv_switch_none. */ + if (e) + elevator_put(e); } -static struct blk_mq_qe_pair *blk_lookup_qe_pair(struct list_head *head, - struct request_queue *q) +/* + * Stores elevator type in xarray and set current elevator to none. It uses + * q->id as an index to store the elevator type into the xarray. + */ +static int blk_mq_elv_switch_none(struct request_queue *q, + struct xarray *elv_tbl) { - struct blk_mq_qe_pair *qe; + int ret = 0; - list_for_each_entry(qe, head, node) - if (qe->q == q) - return qe; + lockdep_assert_held_write(&q->tag_set->update_nr_hwq_lock); - return NULL; -} + /* + * Accessing q->elevator without holding q->elevator_lock is safe here + * because we're called from nr_hw_queue update which is protected by + * set->update_nr_hwq_lock in the writer context. So, scheduler update/ + * switch code (which acquires the same lock in the reader context) + * can't run concurrently. + */ + if (q->elevator) { -static void blk_mq_elv_switch_back(struct list_head *head, - struct request_queue *q) -{ - struct blk_mq_qe_pair *qe; - struct elevator_type *t; + ret = xa_insert(elv_tbl, q->id, q->elevator->type, GFP_KERNEL); + if (WARN_ON_ONCE(ret)) + return ret; - qe = blk_lookup_qe_pair(head, q); - if (!qe) - return; - t = qe->type; - list_del(&qe->node); - kfree(qe); + /* + * Before we switch elevator to 'none', take a reference to + * the elevator module so that while nr_hw_queue update is + * running, no one can remove elevator module. We'd put the + * reference to elevator module later when we switch back + * elevator. + */ + __elevator_get(q->elevator->type); - mutex_lock(&q->sysfs_lock); - elevator_switch(q, t); - /* drop the reference acquired in blk_mq_elv_switch_none */ - elevator_put(t); - mutex_unlock(&q->sysfs_lock); + elevator_set_none(q); + } + return ret; } static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues) { struct request_queue *q; - LIST_HEAD(head); int prev_nr_hw_queues = set->nr_hw_queues; unsigned int memflags; int i; + struct xarray elv_tbl, et_tbl; + bool queues_frozen = false; lockdep_assert_held(&set->tag_list_lock); @@ -5007,8 +5043,17 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, return; memflags = memalloc_noio_save(); - list_for_each_entry(q, &set->tag_list, tag_set_list) - blk_mq_freeze_queue_nomemsave(q); + + xa_init(&et_tbl); + if (blk_mq_alloc_sched_tags_batch(&et_tbl, set, nr_hw_queues) < 0) + goto out_memalloc_restore; + + xa_init(&elv_tbl); + + list_for_each_entry(q, &set->tag_list, tag_set_list) { + blk_mq_debugfs_unregister_hctxs(q); + blk_mq_sysfs_unregister_hctxs(q); + } /* * Switch IO scheduler to 'none', cleaning up the data associated @@ -5016,21 +5061,19 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, * updating the new sw to hw queue mappings. */ list_for_each_entry(q, &set->tag_list, tag_set_list) - if (!blk_mq_elv_switch_none(&head, q)) + if (blk_mq_elv_switch_none(q, &elv_tbl)) goto switch_back; - list_for_each_entry(q, &set->tag_list, tag_set_list) { - blk_mq_debugfs_unregister_hctxs(q); - blk_mq_sysfs_unregister_hctxs(q); - } - + list_for_each_entry(q, &set->tag_list, tag_set_list) + blk_mq_freeze_queue_nomemsave(q); + queues_frozen = true; if (blk_mq_realloc_tag_set_tags(set, nr_hw_queues) < 0) - goto reregister; + goto switch_back; fallback: blk_mq_update_queue_map(set); list_for_each_entry(q, &set->tag_list, tag_set_list) { - blk_mq_realloc_hw_ctxs(set, q); + __blk_mq_realloc_hw_ctxs(set, q); if (q->nr_hw_queues != set->nr_hw_queues) { int i = prev_nr_hw_queues; @@ -5045,19 +5088,26 @@ fallback: } blk_mq_map_swqueue(q); } +switch_back: + /* The blk_mq_elv_switch_back unfreezes queue for us. */ + list_for_each_entry(q, &set->tag_list, tag_set_list) { + /* switch_back expects queue to be frozen */ + if (!queues_frozen) + blk_mq_freeze_queue_nomemsave(q); + blk_mq_elv_switch_back(q, &elv_tbl, &et_tbl); + } -reregister: list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_sysfs_register_hctxs(q); blk_mq_debugfs_register_hctxs(q); - } -switch_back: - list_for_each_entry(q, &set->tag_list, tag_set_list) - blk_mq_elv_switch_back(&head, q); + blk_mq_remove_hw_queues_cpuhp(q); + blk_mq_add_hw_queues_cpuhp(q); + } - list_for_each_entry(q, &set->tag_list, tag_set_list) - blk_mq_unfreeze_queue_nomemrestore(q); + xa_destroy(&elv_tbl); + xa_destroy(&et_tbl); +out_memalloc_restore: memalloc_noio_restore(memflags); /* Free the excess tags when nr_hw_queues shrink. */ @@ -5067,9 +5117,11 @@ switch_back: void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues) { + down_write(&set->update_nr_hwq_lock); mutex_lock(&set->tag_list_lock); __blk_mq_update_nr_hw_queues(set, nr_hw_queues); mutex_unlock(&set->tag_list_lock); + up_write(&set->update_nr_hwq_lock); } EXPORT_SYMBOL_GPL(blk_mq_update_nr_hw_queues); diff --git a/block/blk-mq.h b/block/blk-mq.h index 44979e92b79f..affb2e14b56e 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -48,7 +48,7 @@ void blk_mq_exit_queue(struct request_queue *q); int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr); void blk_mq_wake_waiters(struct request_queue *q); bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *, - unsigned int); + bool); void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list); struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *start); @@ -100,12 +100,10 @@ static inline enum hctx_type blk_mq_get_hctx_type(blk_opf_t opf) /* * blk_mq_map_queue() - map (cmd_flags,type) to hardware queue - * @q: request queue * @opf: operation type (REQ_OP_*) and flags (e.g. REQ_POLLED). * @ctx: software queue cpu ctx */ -static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q, - blk_opf_t opf, +static inline struct blk_mq_hw_ctx *blk_mq_map_queue(blk_opf_t opf, struct blk_mq_ctx *ctx) { return ctx->hctxs[blk_mq_get_hctx_type(opf)]; @@ -248,10 +246,7 @@ static inline bool blk_mq_hw_queue_mapped(struct blk_mq_hw_ctx *hctx) return hctx->nr_ctx && hctx->tags; } -unsigned int blk_mq_in_flight(struct request_queue *q, - struct block_device *part); -void blk_mq_in_flight_rw(struct request_queue *q, struct block_device *part, - unsigned int inflight[2]); +void blk_mq_in_driver_rw(struct block_device *part, unsigned int inflight[2]); static inline void blk_mq_put_dispatch_budget(struct request_queue *q, int budget_token) diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c index d4d4f4dc0e23..654478dfbc20 100644 --- a/block/blk-rq-qos.c +++ b/block/blk-rq-qos.c @@ -196,7 +196,6 @@ bool rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle) struct rq_qos_wait_data { struct wait_queue_entry wq; - struct task_struct *task; struct rq_wait *rqw; acquire_inflight_cb_t *cb; void *private_data; @@ -218,7 +217,20 @@ static int rq_qos_wake_function(struct wait_queue_entry *curr, return -1; data->got_token = true; - wake_up_process(data->task); + /* + * autoremove_wake_function() removes the wait entry only when it + * actually changed the task state. We want the wait always removed. + * Remove explicitly and use default_wake_function(). + */ + default_wake_function(curr, mode, wake_flags, key); + /* + * Note that the order of operations is important as finish_wait() + * tests whether @curr is removed without grabbing the lock. This + * should be the last thing to do to make sure we will not have a + * UAF access to @data. And the semantics of memory barrier in it + * also make sure the waiter will see the latest @data->got_token + * once list_empty_careful() in finish_wait() returns true. + */ list_del_init_careful(&curr->entry); return 1; } @@ -244,41 +256,55 @@ void rq_qos_wait(struct rq_wait *rqw, void *private_data, cleanup_cb_t *cleanup_cb) { struct rq_qos_wait_data data = { - .wq = { - .func = rq_qos_wake_function, - .entry = LIST_HEAD_INIT(data.wq.entry), - }, - .task = current, - .rqw = rqw, - .cb = acquire_inflight_cb, - .private_data = private_data, + .rqw = rqw, + .cb = acquire_inflight_cb, + .private_data = private_data, + .got_token = false, }; - bool has_sleeper; + bool first_waiter; - has_sleeper = wq_has_sleeper(&rqw->wait); - if (!has_sleeper && acquire_inflight_cb(rqw, private_data)) + /* + * If there are no waiters in the waiting queue, try to increase the + * inflight counter if we can. Otherwise, prepare for adding ourselves + * to the waiting queue. + */ + if (!waitqueue_active(&rqw->wait) && acquire_inflight_cb(rqw, private_data)) return; - has_sleeper = !prepare_to_wait_exclusive(&rqw->wait, &data.wq, + init_wait_func(&data.wq, rq_qos_wake_function); + first_waiter = prepare_to_wait_exclusive(&rqw->wait, &data.wq, TASK_UNINTERRUPTIBLE); + /* + * Make sure there is at least one inflight process; otherwise, waiters + * will never be woken up. Since there may be no inflight process before + * adding ourselves to the waiting queue above, we need to try to + * increase the inflight counter for ourselves. And it is sufficient to + * guarantee that at least the first waiter to enter the waiting queue + * will re-check the waiting condition before going to sleep, thus + * ensuring forward progress. + */ + if (!data.got_token && first_waiter && acquire_inflight_cb(rqw, private_data)) { + finish_wait(&rqw->wait, &data.wq); + /* + * We raced with rq_qos_wake_function() getting a token, + * which means we now have two. Put our local token + * and wake anyone else potentially waiting for one. + * + * Enough memory barrier in list_empty_careful() in + * finish_wait() is paired with list_del_init_careful() + * in rq_qos_wake_function() to make sure we will see + * the latest @data->got_token. + */ + if (data.got_token) + cleanup_cb(rqw, private_data); + return; + } + + /* we are now relying on the waker to increase our inflight counter. */ do { - /* The memory barrier in set_current_state saves us here. */ if (data.got_token) break; - if (!has_sleeper && acquire_inflight_cb(rqw, private_data)) { - finish_wait(&rqw->wait, &data.wq); - - /* - * We raced with rq_qos_wake_function() getting a token, - * which means we now have two. Put our local token - * and wake anyone else potentially waiting for one. - */ - if (data.got_token) - cleanup_cb(rqw, private_data); - return; - } io_schedule(); - has_sleeper = true; set_current_state(TASK_UNINTERRUPTIBLE); } while (1); finish_wait(&rqw->wait, &data.wq); @@ -292,6 +318,7 @@ void rq_qos_exit(struct request_queue *q) q->rq_qos = rqos->next; rqos->ops->exit(rqos); } + blk_queue_flag_clear(QUEUE_FLAG_QOS_ENABLED, q); mutex_unlock(&q->rq_qos_mutex); } @@ -317,6 +344,7 @@ int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id, goto ebusy; rqos->next = q->rq_qos; q->rq_qos = rqos; + blk_queue_flag_set(QUEUE_FLAG_QOS_ENABLED, q); blk_mq_unfreeze_queue(q, memflags); @@ -347,6 +375,8 @@ void rq_qos_del(struct rq_qos *rqos) break; } } + if (!q->rq_qos) + blk_queue_flag_clear(QUEUE_FLAG_QOS_ENABLED, q); blk_mq_unfreeze_queue(q, memflags); mutex_lock(&q->debugfs_mutex); diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h index 37245c97ee61..b538f2c0febc 100644 --- a/block/blk-rq-qos.h +++ b/block/blk-rq-qos.h @@ -112,41 +112,58 @@ void __rq_qos_queue_depth_changed(struct rq_qos *rqos); static inline void rq_qos_cleanup(struct request_queue *q, struct bio *bio) { - if (q->rq_qos) + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos) __rq_qos_cleanup(q->rq_qos, bio); } static inline void rq_qos_done(struct request_queue *q, struct request *rq) { - if (q->rq_qos && !blk_rq_is_passthrough(rq)) + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos && !blk_rq_is_passthrough(rq)) __rq_qos_done(q->rq_qos, rq); } static inline void rq_qos_issue(struct request_queue *q, struct request *rq) { - if (q->rq_qos) + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos) __rq_qos_issue(q->rq_qos, rq); } static inline void rq_qos_requeue(struct request_queue *q, struct request *rq) { - if (q->rq_qos) + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos) __rq_qos_requeue(q->rq_qos, rq); } static inline void rq_qos_done_bio(struct bio *bio) { - if (bio->bi_bdev && (bio_flagged(bio, BIO_QOS_THROTTLED) || - bio_flagged(bio, BIO_QOS_MERGED))) { - struct request_queue *q = bdev_get_queue(bio->bi_bdev); - if (q->rq_qos) - __rq_qos_done_bio(q->rq_qos, bio); - } + struct request_queue *q; + + if (!bio->bi_bdev || (!bio_flagged(bio, BIO_QOS_THROTTLED) && + !bio_flagged(bio, BIO_QOS_MERGED))) + return; + + q = bdev_get_queue(bio->bi_bdev); + + /* + * A BIO may carry BIO_QOS_* flags even if the associated request_queue + * does not have rq_qos enabled. This can happen with stacked block + * devices — for example, NVMe multipath, where it's possible that the + * bottom device has QoS enabled but the top device does not. Therefore, + * always verify that q->rq_qos is present and QoS is enabled before + * calling __rq_qos_done_bio(). + */ + if (test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags) && q->rq_qos) + __rq_qos_done_bio(q->rq_qos, bio); } static inline void rq_qos_throttle(struct request_queue *q, struct bio *bio) { - if (q->rq_qos) { + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos) { bio_set_flag(bio, BIO_QOS_THROTTLED); __rq_qos_throttle(q->rq_qos, bio); } @@ -155,14 +172,16 @@ static inline void rq_qos_throttle(struct request_queue *q, struct bio *bio) static inline void rq_qos_track(struct request_queue *q, struct request *rq, struct bio *bio) { - if (q->rq_qos) + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos) __rq_qos_track(q->rq_qos, rq, bio); } static inline void rq_qos_merge(struct request_queue *q, struct request *rq, struct bio *bio) { - if (q->rq_qos) { + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos) { bio_set_flag(bio, BIO_QOS_MERGED); __rq_qos_merge(q->rq_qos, rq, bio); } @@ -170,7 +189,8 @@ static inline void rq_qos_merge(struct request_queue *q, struct request *rq, static inline void rq_qos_queue_depth_changed(struct request_queue *q) { - if (q->rq_qos) + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos) __rq_qos_queue_depth_changed(q->rq_qos); } diff --git a/block/blk-settings.c b/block/blk-settings.c index 66721afeea54..44dabc636a59 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -21,7 +21,7 @@ void blk_queue_rq_timeout(struct request_queue *q, unsigned int timeout) { - q->rq_timeout = timeout; + WRITE_ONCE(q->rq_timeout, timeout); } EXPORT_SYMBOL_GPL(blk_queue_rq_timeout); @@ -61,8 +61,14 @@ void blk_apply_bdi_limits(struct backing_dev_info *bdi, /* * For read-ahead of large files to be effective, we need to read ahead * at least twice the optimal I/O size. + * + * There is no hardware limitation for the read-ahead size and the user + * might have increased the read-ahead size through sysfs, so don't ever + * decrease it. */ - bdi->ra_pages = max(lim->io_opt * 2 / PAGE_SIZE, VM_READAHEAD_PAGES); + bdi->ra_pages = max3(bdi->ra_pages, + lim->io_opt * 2 / PAGE_SIZE, + VM_READAHEAD_PAGES); bdi->io_pages = lim->max_sectors >> PAGE_SECTORS_SHIFT; } @@ -175,6 +181,8 @@ static void blk_atomic_writes_update_limits(struct queue_limits *lim) static void blk_validate_atomic_write_limits(struct queue_limits *lim) { unsigned int boundary_sectors; + unsigned int atomic_write_hw_max_sectors = + lim->atomic_write_hw_max >> SECTOR_SHIFT; if (!(lim->features & BLK_FEAT_ATOMIC_WRITES)) goto unsupported; @@ -196,6 +204,10 @@ static void blk_validate_atomic_write_limits(struct queue_limits *lim) lim->atomic_write_hw_max)) goto unsupported; + if (WARN_ON_ONCE(lim->chunk_sectors && + atomic_write_hw_max_sectors > lim->chunk_sectors)) + goto unsupported; + boundary_sectors = lim->atomic_write_hw_boundary >> SECTOR_SHIFT; if (boundary_sectors) { @@ -330,12 +342,19 @@ int blk_validate_limits(struct queue_limits *lim) lim->max_discard_sectors = min(lim->max_hw_discard_sectors, lim->max_user_discard_sectors); + /* + * When discard is not supported, discard_granularity should be reported + * as 0 to userspace. + */ + if (lim->max_discard_sectors) + lim->discard_granularity = + max(lim->discard_granularity, lim->physical_block_size); + else + lim->discard_granularity = 0; + if (!lim->max_discard_segments) lim->max_discard_segments = 1; - if (lim->discard_granularity < lim->physical_block_size) - lim->discard_granularity = lim->physical_block_size; - /* * By default there is no limit on the segment boundary alignment, * but if there is one it can't be smaller than the page size as @@ -773,7 +792,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, } /* chunk_sectors a multiple of the physical block size? */ - if ((t->chunk_sectors << 9) & (t->physical_block_size - 1)) { + if (t->chunk_sectors % (t->physical_block_size >> SECTOR_SHIFT)) { t->chunk_sectors = 0; t->flags |= BLK_FLAG_MISALIGNED; ret = -1; diff --git a/block/blk-stat.c b/block/blk-stat.c index eaf60097bbe1..682a8ddb1173 100644 --- a/block/blk-stat.c +++ b/block/blk-stat.c @@ -76,7 +76,7 @@ void blk_stat_add(struct request *rq, u64 now) static void blk_stat_timer_fn(struct timer_list *t) { - struct blk_stat_callback *cb = from_timer(cb, t, timer); + struct blk_stat_callback *cb = timer_container_of(cb, t, timer); unsigned int bucket; int cpu; @@ -162,7 +162,7 @@ void blk_stat_remove_callback(struct request_queue *q, blk_queue_flag_clear(QUEUE_FLAG_STATS, q); spin_unlock_irqrestore(&q->stats->lock, flags); - del_timer_sync(&cb->timer); + timer_delete_sync(&cb->timer); } static void blk_stat_free_callback_rcu(struct rcu_head *head) diff --git a/block/blk-stat.h b/block/blk-stat.h index 5d7f18ba436d..9e05bf18d1be 100644 --- a/block/blk-stat.h +++ b/block/blk-stat.h @@ -148,7 +148,7 @@ static inline void blk_stat_activate_nsecs(struct blk_stat_callback *cb, static inline void blk_stat_deactivate(struct blk_stat_callback *cb) { - del_timer_sync(&cb->timer); + timer_delete_sync(&cb->timer); } /** diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 780218684907..7d1a03c36502 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -23,10 +23,11 @@ struct queue_sysfs_entry { struct attribute attr; ssize_t (*show)(struct gendisk *disk, char *page); + ssize_t (*show_limit)(struct gendisk *disk, char *page); + ssize_t (*store)(struct gendisk *disk, const char *page, size_t count); int (*store_limit)(struct gendisk *disk, const char *page, size_t count, struct queue_limits *lim); - void (*load_module)(struct gendisk *disk, const char *page, size_t count); }; static ssize_t @@ -52,7 +53,12 @@ queue_var_store(unsigned long *var, const char *page, size_t count) static ssize_t queue_requests_show(struct gendisk *disk, char *page) { - return queue_var_show(disk->queue->nr_requests, page); + ssize_t ret; + + mutex_lock(&disk->queue->elevator_lock); + ret = queue_var_show(disk->queue->nr_requests, page); + mutex_unlock(&disk->queue->elevator_lock); + return ret; } static ssize_t @@ -60,27 +66,38 @@ queue_requests_store(struct gendisk *disk, const char *page, size_t count) { unsigned long nr; int ret, err; + unsigned int memflags; + struct request_queue *q = disk->queue; - if (!queue_is_mq(disk->queue)) + if (!queue_is_mq(q)) return -EINVAL; ret = queue_var_store(&nr, page, count); if (ret < 0) return ret; + memflags = blk_mq_freeze_queue(q); + mutex_lock(&q->elevator_lock); if (nr < BLKDEV_MIN_RQ) nr = BLKDEV_MIN_RQ; err = blk_mq_update_nr_requests(disk->queue, nr); if (err) - return err; - + ret = err; + mutex_unlock(&q->elevator_lock); + blk_mq_unfreeze_queue(q, memflags); return ret; } static ssize_t queue_ra_show(struct gendisk *disk, char *page) { - return queue_var_show(disk->bdi->ra_pages << (PAGE_SHIFT - 10), page); + ssize_t ret; + + mutex_lock(&disk->queue->limits_lock); + ret = queue_var_show(disk->bdi->ra_pages << (PAGE_SHIFT - 10), page); + mutex_unlock(&disk->queue->limits_lock); + + return ret; } static ssize_t @@ -88,11 +105,22 @@ queue_ra_store(struct gendisk *disk, const char *page, size_t count) { unsigned long ra_kb; ssize_t ret; + unsigned int memflags; + struct request_queue *q = disk->queue; ret = queue_var_store(&ra_kb, page, count); if (ret < 0) return ret; + /* + * ->ra_pages is protected by ->limits_lock because it is usually + * calculated from the queue limits by queue_limits_commit_update. + */ + mutex_lock(&q->limits_lock); + memflags = blk_mq_freeze_queue(q); disk->bdi->ra_pages = ra_kb >> (PAGE_SHIFT - 10); + mutex_unlock(&q->limits_lock); + blk_mq_unfreeze_queue(q, memflags); + return ret; } @@ -106,6 +134,8 @@ QUEUE_SYSFS_LIMIT_SHOW(max_segments) QUEUE_SYSFS_LIMIT_SHOW(max_discard_segments) QUEUE_SYSFS_LIMIT_SHOW(max_integrity_segments) QUEUE_SYSFS_LIMIT_SHOW(max_segment_size) +QUEUE_SYSFS_LIMIT_SHOW(max_write_streams) +QUEUE_SYSFS_LIMIT_SHOW(write_stream_granularity) QUEUE_SYSFS_LIMIT_SHOW(logical_block_size) QUEUE_SYSFS_LIMIT_SHOW(physical_block_size) QUEUE_SYSFS_LIMIT_SHOW(chunk_sectors) @@ -238,8 +268,9 @@ static ssize_t queue_poll_show(struct gendisk *disk, char *page) { if (queue_is_mq(disk->queue)) return sysfs_emit(page, "%u\n", blk_mq_can_poll(disk->queue)); + return sysfs_emit(page, "%u\n", - !!(disk->queue->limits.features & BLK_FEAT_POLL)); + !!(disk->queue->limits.features & BLK_FEAT_POLL)); } static ssize_t queue_zoned_show(struct gendisk *disk, char *page) @@ -286,17 +317,21 @@ static ssize_t queue_nomerges_store(struct gendisk *disk, const char *page, size_t count) { unsigned long nm; + unsigned int memflags; + struct request_queue *q = disk->queue; ssize_t ret = queue_var_store(&nm, page, count); if (ret < 0) return ret; - blk_queue_flag_clear(QUEUE_FLAG_NOMERGES, disk->queue); - blk_queue_flag_clear(QUEUE_FLAG_NOXMERGES, disk->queue); + memflags = blk_mq_freeze_queue(q); + blk_queue_flag_clear(QUEUE_FLAG_NOMERGES, q); + blk_queue_flag_clear(QUEUE_FLAG_NOXMERGES, q); if (nm == 2) - blk_queue_flag_set(QUEUE_FLAG_NOMERGES, disk->queue); + blk_queue_flag_set(QUEUE_FLAG_NOMERGES, q); else if (nm) - blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, disk->queue); + blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, q); + blk_mq_unfreeze_queue(q, memflags); return ret; } @@ -316,11 +351,19 @@ queue_rq_affinity_store(struct gendisk *disk, const char *page, size_t count) #ifdef CONFIG_SMP struct request_queue *q = disk->queue; unsigned long val; + unsigned int memflags; ret = queue_var_store(&val, page, count); if (ret < 0) return ret; + /* + * Here we update two queue flags each using atomic bitops, although + * updating two flags isn't atomic it should be harmless as those flags + * are accessed individually using atomic test_bit operation. So we + * don't grab any lock while updating these flags. + */ + memflags = blk_mq_freeze_queue(q); if (val == 2) { blk_queue_flag_set(QUEUE_FLAG_SAME_COMP, q); blk_queue_flag_set(QUEUE_FLAG_SAME_FORCE, q); @@ -331,6 +374,7 @@ queue_rq_affinity_store(struct gendisk *disk, const char *page, size_t count) blk_queue_flag_clear(QUEUE_FLAG_SAME_COMP, q); blk_queue_flag_clear(QUEUE_FLAG_SAME_FORCE, q); } + blk_mq_unfreeze_queue(q, memflags); #endif return ret; } @@ -344,29 +388,43 @@ static ssize_t queue_poll_delay_store(struct gendisk *disk, const char *page, static ssize_t queue_poll_store(struct gendisk *disk, const char *page, size_t count) { - if (!(disk->queue->limits.features & BLK_FEAT_POLL)) - return -EINVAL; + unsigned int memflags; + ssize_t ret = count; + struct request_queue *q = disk->queue; + + memflags = blk_mq_freeze_queue(q); + if (!(q->limits.features & BLK_FEAT_POLL)) { + ret = -EINVAL; + goto out; + } + pr_info_ratelimited("writes to the poll attribute are ignored.\n"); pr_info_ratelimited("please use driver specific parameters instead.\n"); - return count; +out: + blk_mq_unfreeze_queue(q, memflags); + return ret; } static ssize_t queue_io_timeout_show(struct gendisk *disk, char *page) { - return sysfs_emit(page, "%u\n", jiffies_to_msecs(disk->queue->rq_timeout)); + return sysfs_emit(page, "%u\n", + jiffies_to_msecs(READ_ONCE(disk->queue->rq_timeout))); } static ssize_t queue_io_timeout_store(struct gendisk *disk, const char *page, size_t count) { - unsigned int val; + unsigned int val, memflags; int err; + struct request_queue *q = disk->queue; err = kstrtou32(page, 10, &val); if (err || val == 0) return -EINVAL; - blk_queue_rq_timeout(disk->queue, msecs_to_jiffies(val)); + memflags = blk_mq_freeze_queue(q); + blk_queue_rq_timeout(q, msecs_to_jiffies(val)); + blk_mq_unfreeze_queue(q, memflags); return count; } @@ -412,57 +470,57 @@ static struct queue_sysfs_entry _prefix##_entry = { \ .store = _prefix##_store, \ }; -#define QUEUE_LIM_RW_ENTRY(_prefix, _name) \ +#define QUEUE_LIM_RO_ENTRY(_prefix, _name) \ static struct queue_sysfs_entry _prefix##_entry = { \ - .attr = { .name = _name, .mode = 0644 }, \ - .show = _prefix##_show, \ - .store_limit = _prefix##_store, \ + .attr = { .name = _name, .mode = 0444 }, \ + .show_limit = _prefix##_show, \ } -#define QUEUE_RW_LOAD_MODULE_ENTRY(_prefix, _name) \ -static struct queue_sysfs_entry _prefix##_entry = { \ +#define QUEUE_LIM_RW_ENTRY(_prefix, _name) \ +static struct queue_sysfs_entry _prefix##_entry = { \ .attr = { .name = _name, .mode = 0644 }, \ - .show = _prefix##_show, \ - .load_module = _prefix##_load_module, \ - .store = _prefix##_store, \ + .show_limit = _prefix##_show, \ + .store_limit = _prefix##_store, \ } QUEUE_RW_ENTRY(queue_requests, "nr_requests"); QUEUE_RW_ENTRY(queue_ra, "read_ahead_kb"); QUEUE_LIM_RW_ENTRY(queue_max_sectors, "max_sectors_kb"); -QUEUE_RO_ENTRY(queue_max_hw_sectors, "max_hw_sectors_kb"); -QUEUE_RO_ENTRY(queue_max_segments, "max_segments"); -QUEUE_RO_ENTRY(queue_max_integrity_segments, "max_integrity_segments"); -QUEUE_RO_ENTRY(queue_max_segment_size, "max_segment_size"); -QUEUE_RW_LOAD_MODULE_ENTRY(elv_iosched, "scheduler"); - -QUEUE_RO_ENTRY(queue_logical_block_size, "logical_block_size"); -QUEUE_RO_ENTRY(queue_physical_block_size, "physical_block_size"); -QUEUE_RO_ENTRY(queue_chunk_sectors, "chunk_sectors"); -QUEUE_RO_ENTRY(queue_io_min, "minimum_io_size"); -QUEUE_RO_ENTRY(queue_io_opt, "optimal_io_size"); - -QUEUE_RO_ENTRY(queue_max_discard_segments, "max_discard_segments"); -QUEUE_RO_ENTRY(queue_discard_granularity, "discard_granularity"); -QUEUE_RO_ENTRY(queue_max_hw_discard_sectors, "discard_max_hw_bytes"); +QUEUE_LIM_RO_ENTRY(queue_max_hw_sectors, "max_hw_sectors_kb"); +QUEUE_LIM_RO_ENTRY(queue_max_segments, "max_segments"); +QUEUE_LIM_RO_ENTRY(queue_max_integrity_segments, "max_integrity_segments"); +QUEUE_LIM_RO_ENTRY(queue_max_segment_size, "max_segment_size"); +QUEUE_LIM_RO_ENTRY(queue_max_write_streams, "max_write_streams"); +QUEUE_LIM_RO_ENTRY(queue_write_stream_granularity, "write_stream_granularity"); +QUEUE_RW_ENTRY(elv_iosched, "scheduler"); + +QUEUE_LIM_RO_ENTRY(queue_logical_block_size, "logical_block_size"); +QUEUE_LIM_RO_ENTRY(queue_physical_block_size, "physical_block_size"); +QUEUE_LIM_RO_ENTRY(queue_chunk_sectors, "chunk_sectors"); +QUEUE_LIM_RO_ENTRY(queue_io_min, "minimum_io_size"); +QUEUE_LIM_RO_ENTRY(queue_io_opt, "optimal_io_size"); + +QUEUE_LIM_RO_ENTRY(queue_max_discard_segments, "max_discard_segments"); +QUEUE_LIM_RO_ENTRY(queue_discard_granularity, "discard_granularity"); +QUEUE_LIM_RO_ENTRY(queue_max_hw_discard_sectors, "discard_max_hw_bytes"); QUEUE_LIM_RW_ENTRY(queue_max_discard_sectors, "discard_max_bytes"); QUEUE_RO_ENTRY(queue_discard_zeroes_data, "discard_zeroes_data"); -QUEUE_RO_ENTRY(queue_atomic_write_max_sectors, "atomic_write_max_bytes"); -QUEUE_RO_ENTRY(queue_atomic_write_boundary_sectors, +QUEUE_LIM_RO_ENTRY(queue_atomic_write_max_sectors, "atomic_write_max_bytes"); +QUEUE_LIM_RO_ENTRY(queue_atomic_write_boundary_sectors, "atomic_write_boundary_bytes"); -QUEUE_RO_ENTRY(queue_atomic_write_unit_max, "atomic_write_unit_max_bytes"); -QUEUE_RO_ENTRY(queue_atomic_write_unit_min, "atomic_write_unit_min_bytes"); +QUEUE_LIM_RO_ENTRY(queue_atomic_write_unit_max, "atomic_write_unit_max_bytes"); +QUEUE_LIM_RO_ENTRY(queue_atomic_write_unit_min, "atomic_write_unit_min_bytes"); QUEUE_RO_ENTRY(queue_write_same_max, "write_same_max_bytes"); -QUEUE_RO_ENTRY(queue_max_write_zeroes_sectors, "write_zeroes_max_bytes"); -QUEUE_RO_ENTRY(queue_max_zone_append_sectors, "zone_append_max_bytes"); -QUEUE_RO_ENTRY(queue_zone_write_granularity, "zone_write_granularity"); +QUEUE_LIM_RO_ENTRY(queue_max_write_zeroes_sectors, "write_zeroes_max_bytes"); +QUEUE_LIM_RO_ENTRY(queue_max_zone_append_sectors, "zone_append_max_bytes"); +QUEUE_LIM_RO_ENTRY(queue_zone_write_granularity, "zone_write_granularity"); -QUEUE_RO_ENTRY(queue_zoned, "zoned"); +QUEUE_LIM_RO_ENTRY(queue_zoned, "zoned"); QUEUE_RO_ENTRY(queue_nr_zones, "nr_zones"); -QUEUE_RO_ENTRY(queue_max_open_zones, "max_open_zones"); -QUEUE_RO_ENTRY(queue_max_active_zones, "max_active_zones"); +QUEUE_LIM_RO_ENTRY(queue_max_open_zones, "max_open_zones"); +QUEUE_LIM_RO_ENTRY(queue_max_active_zones, "max_active_zones"); QUEUE_RW_ENTRY(queue_nomerges, "nomerges"); QUEUE_LIM_RW_ENTRY(queue_iostats_passthrough, "iostats_passthrough"); @@ -470,16 +528,16 @@ QUEUE_RW_ENTRY(queue_rq_affinity, "rq_affinity"); QUEUE_RW_ENTRY(queue_poll, "io_poll"); QUEUE_RW_ENTRY(queue_poll_delay, "io_poll_delay"); QUEUE_LIM_RW_ENTRY(queue_wc, "write_cache"); -QUEUE_RO_ENTRY(queue_fua, "fua"); -QUEUE_RO_ENTRY(queue_dax, "dax"); +QUEUE_LIM_RO_ENTRY(queue_fua, "fua"); +QUEUE_LIM_RO_ENTRY(queue_dax, "dax"); QUEUE_RW_ENTRY(queue_io_timeout, "io_timeout"); -QUEUE_RO_ENTRY(queue_virt_boundary_mask, "virt_boundary_mask"); -QUEUE_RO_ENTRY(queue_dma_alignment, "dma_alignment"); +QUEUE_LIM_RO_ENTRY(queue_virt_boundary_mask, "virt_boundary_mask"); +QUEUE_LIM_RO_ENTRY(queue_dma_alignment, "dma_alignment"); /* legacy alias for logical_block_size: */ static struct queue_sysfs_entry queue_hw_sector_size_entry = { - .attr = {.name = "hw_sector_size", .mode = 0444 }, - .show = queue_logical_block_size_show, + .attr = {.name = "hw_sector_size", .mode = 0444 }, + .show_limit = queue_logical_block_size_show, }; QUEUE_LIM_RW_ENTRY(queue_rotational, "rotational"); @@ -503,14 +561,24 @@ static ssize_t queue_var_store64(s64 *var, const char *page) static ssize_t queue_wb_lat_show(struct gendisk *disk, char *page) { - if (!wbt_rq_qos(disk->queue)) - return -EINVAL; + ssize_t ret; + struct request_queue *q = disk->queue; - if (wbt_disabled(disk->queue)) - return sysfs_emit(page, "0\n"); + mutex_lock(&disk->rqos_state_mutex); + if (!wbt_rq_qos(q)) { + ret = -EINVAL; + goto out; + } - return sysfs_emit(page, "%llu\n", - div_u64(wbt_get_min_lat(disk->queue), 1000)); + if (wbt_disabled(q)) { + ret = sysfs_emit(page, "0\n"); + goto out; + } + + ret = sysfs_emit(page, "%llu\n", div_u64(wbt_get_min_lat(q), 1000)); +out: + mutex_unlock(&disk->rqos_state_mutex); + return ret; } static ssize_t queue_wb_lat_store(struct gendisk *disk, const char *page, @@ -520,6 +588,7 @@ static ssize_t queue_wb_lat_store(struct gendisk *disk, const char *page, struct rq_qos *rqos; ssize_t ret; s64 val; + unsigned int memflags; ret = queue_var_store64(&val, page); if (ret < 0) @@ -527,20 +596,23 @@ static ssize_t queue_wb_lat_store(struct gendisk *disk, const char *page, if (val < -1) return -EINVAL; + memflags = blk_mq_freeze_queue(q); + rqos = wbt_rq_qos(q); if (!rqos) { ret = wbt_init(disk); if (ret) - return ret; + goto out; } + ret = count; if (val == -1) val = wbt_default_latency_nsec(q); else if (val >= 0) val *= 1000ULL; if (wbt_get_min_lat(q) == val) - return count; + goto out; /* * Ensure that the queue is idled, in case the latency update @@ -549,11 +621,15 @@ static ssize_t queue_wb_lat_store(struct gendisk *disk, const char *page, */ blk_mq_quiesce_queue(q); + mutex_lock(&disk->rqos_state_mutex); wbt_set_min_lat(q, val); + mutex_unlock(&disk->rqos_state_mutex); blk_mq_unquiesce_queue(q); +out: + blk_mq_unfreeze_queue(q, memflags); - return count; + return ret; } QUEUE_RW_ENTRY(queue_wb_lat, "wbt_lat_usec"); @@ -561,13 +637,17 @@ QUEUE_RW_ENTRY(queue_wb_lat, "wbt_lat_usec"); /* Common attributes for bio-based and request-based queues. */ static struct attribute *queue_attrs[] = { - &queue_ra_entry.attr, + /* + * Attributes which are protected with q->limits_lock. + */ &queue_max_hw_sectors_entry.attr, &queue_max_sectors_entry.attr, &queue_max_segments_entry.attr, &queue_max_discard_segments_entry.attr, &queue_max_integrity_segments_entry.attr, &queue_max_segment_size_entry.attr, + &queue_max_write_streams_entry.attr, + &queue_write_stream_granularity_entry.attr, &queue_hw_sector_size_entry.attr, &queue_logical_block_size_entry.attr, &queue_physical_block_size_entry.attr, @@ -577,44 +657,58 @@ static struct attribute *queue_attrs[] = { &queue_discard_granularity_entry.attr, &queue_max_discard_sectors_entry.attr, &queue_max_hw_discard_sectors_entry.attr, - &queue_discard_zeroes_data_entry.attr, &queue_atomic_write_max_sectors_entry.attr, &queue_atomic_write_boundary_sectors_entry.attr, &queue_atomic_write_unit_min_entry.attr, &queue_atomic_write_unit_max_entry.attr, - &queue_write_same_max_entry.attr, &queue_max_write_zeroes_sectors_entry.attr, &queue_max_zone_append_sectors_entry.attr, &queue_zone_write_granularity_entry.attr, &queue_rotational_entry.attr, &queue_zoned_entry.attr, - &queue_nr_zones_entry.attr, &queue_max_open_zones_entry.attr, &queue_max_active_zones_entry.attr, - &queue_nomerges_entry.attr, &queue_iostats_passthrough_entry.attr, &queue_iostats_entry.attr, &queue_stable_writes_entry.attr, &queue_add_random_entry.attr, - &queue_poll_entry.attr, &queue_wc_entry.attr, &queue_fua_entry.attr, &queue_dax_entry.attr, - &queue_poll_delay_entry.attr, &queue_virt_boundary_mask_entry.attr, &queue_dma_alignment_entry.attr, + &queue_ra_entry.attr, + + /* + * Attributes which don't require locking. + */ + &queue_discard_zeroes_data_entry.attr, + &queue_write_same_max_entry.attr, + &queue_nr_zones_entry.attr, + &queue_nomerges_entry.attr, + &queue_poll_entry.attr, + &queue_poll_delay_entry.attr, + NULL, }; /* Request-based queue attributes that are not relevant for bio-based queues. */ static struct attribute *blk_mq_queue_attrs[] = { - &queue_requests_entry.attr, + /* + * Attributes which require some form of locking other than + * q->sysfs_lock. + */ &elv_iosched_entry.attr, - &queue_rq_affinity_entry.attr, - &queue_io_timeout_entry.attr, + &queue_requests_entry.attr, #ifdef CONFIG_BLK_WBT &queue_wb_lat_entry.attr, #endif + /* + * Attributes which don't require locking. + */ + &queue_rq_affinity_entry.attr, + &queue_io_timeout_entry.attr, + NULL, }; @@ -664,14 +758,20 @@ queue_attr_show(struct kobject *kobj, struct attribute *attr, char *page) { struct queue_sysfs_entry *entry = to_queue(attr); struct gendisk *disk = container_of(kobj, struct gendisk, queue_kobj); - ssize_t res; - if (!entry->show) + if (!entry->show && !entry->show_limit) return -EIO; - mutex_lock(&disk->queue->sysfs_lock); - res = entry->show(disk, page); - mutex_unlock(&disk->queue->sysfs_lock); - return res; + + if (entry->show_limit) { + ssize_t res; + + mutex_lock(&disk->queue->limits_lock); + res = entry->show_limit(disk, page); + mutex_unlock(&disk->queue->limits_lock); + return res; + } + + return entry->show(disk, page); } static ssize_t @@ -681,21 +781,13 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr, struct queue_sysfs_entry *entry = to_queue(attr); struct gendisk *disk = container_of(kobj, struct gendisk, queue_kobj); struct request_queue *q = disk->queue; - unsigned int memflags; - ssize_t res; if (!entry->store_limit && !entry->store) return -EIO; - /* - * If the attribute needs to load a module, do it before freezing the - * queue to ensure that the module file can be read when the request - * queue is the one for the device storing the module file. - */ - if (entry->load_module) - entry->load_module(disk, page, length); - if (entry->store_limit) { + ssize_t res; + struct queue_limits lim = queue_limits_start_update(q); res = entry->store_limit(disk, page, length, &lim); @@ -710,12 +802,7 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr, return length; } - mutex_lock(&q->sysfs_lock); - memflags = blk_mq_freeze_queue(q); - res = entry->store(disk, page, length); - blk_mq_unfreeze_queue(q, memflags); - mutex_unlock(&q->sysfs_lock); - return res; + return entry->store(disk, page, length); } static const struct sysfs_ops queue_sysfs_ops = { @@ -734,7 +821,7 @@ static void blk_queue_release(struct kobject *kobj) /* nothing to do here, all data is associated with the parent gendisk */ } -static const struct kobj_type blk_queue_ktype = { +const struct kobj_type blk_queue_ktype = { .default_groups = blk_queue_attr_groups, .sysfs_ops = &queue_sysfs_ops, .release = blk_queue_release, @@ -762,15 +849,14 @@ int blk_register_queue(struct gendisk *disk) struct request_queue *q = disk->queue; int ret; - kobject_init(&disk->queue_kobj, &blk_queue_ktype); ret = kobject_add(&disk->queue_kobj, &disk_to_dev(disk)->kobj, "queue"); if (ret < 0) - goto out_put_queue_kobj; + return ret; if (queue_is_mq(q)) { ret = blk_mq_sysfs_register(disk); if (ret) - goto out_put_queue_kobj; + goto out_del_queue_kobj; } mutex_lock(&q->sysfs_lock); @@ -784,15 +870,12 @@ int blk_register_queue(struct gendisk *disk) if (ret) goto out_debugfs_remove; - if (q->elevator) { - ret = elv_register_queue(q, false); - if (ret) - goto out_unregister_ia_ranges; - } - ret = blk_crypto_sysfs_register(disk); if (ret) - goto out_elv_unregister; + goto out_unregister_ia_ranges; + + if (queue_is_mq(q)) + elevator_set_default(q); blk_queue_flag_set(QUEUE_FLAG_REGISTERED, q); wbt_enable_default(disk); @@ -817,8 +900,6 @@ int blk_register_queue(struct gendisk *disk) return ret; -out_elv_unregister: - elv_unregister_queue(q); out_unregister_ia_ranges: disk_unregister_independent_access_ranges(disk); out_debugfs_remove: @@ -826,8 +907,8 @@ out_debugfs_remove: mutex_unlock(&q->sysfs_lock); if (queue_is_mq(q)) blk_mq_sysfs_unregister(disk); -out_put_queue_kobj: - kobject_put(&disk->queue_kobj); +out_del_queue_kobj: + kobject_del(&disk->queue_kobj); return ret; } @@ -867,7 +948,6 @@ void blk_unregister_queue(struct gendisk *disk) blk_crypto_sysfs_unregister(disk); mutex_lock(&q->sysfs_lock); - elv_unregister_queue(q); disk_unregister_independent_access_ranges(disk); mutex_unlock(&q->sysfs_lock); @@ -875,5 +955,8 @@ void blk_unregister_queue(struct gendisk *disk) kobject_uevent(&disk->queue_kobj, KOBJ_REMOVE); kobject_del(&disk->queue_kobj); + if (queue_is_mq(q)) + elevator_set_none(q); + blk_debugfs_remove(disk); } diff --git a/block/blk-throttle.c b/block/blk-throttle.c index a52f0d6b40ad..397b6a410f9e 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -143,7 +143,8 @@ static inline unsigned int throtl_bio_data_size(struct bio *bio) static void throtl_qnode_init(struct throtl_qnode *qn, struct throtl_grp *tg) { INIT_LIST_HEAD(&qn->node); - bio_list_init(&qn->bios); + bio_list_init(&qn->bios_bps); + bio_list_init(&qn->bios_iops); qn->tg = tg; } @@ -151,18 +152,32 @@ static void throtl_qnode_init(struct throtl_qnode *qn, struct throtl_grp *tg) * throtl_qnode_add_bio - add a bio to a throtl_qnode and activate it * @bio: bio being added * @qn: qnode to add bio to - * @queued: the service_queue->queued[] list @qn belongs to + * @sq: the service_queue @qn belongs to * - * Add @bio to @qn and put @qn on @queued if it's not already on. + * Add @bio to @qn and put @qn on @sq->queued if it's not already on. * @qn->tg's reference count is bumped when @qn is activated. See the * comment on top of throtl_qnode definition for details. */ static void throtl_qnode_add_bio(struct bio *bio, struct throtl_qnode *qn, - struct list_head *queued) + struct throtl_service_queue *sq) { - bio_list_add(&qn->bios, bio); + bool rw = bio_data_dir(bio); + + /* + * Split bios have already been throttled by bps, so they are + * directly queued into the iops path. + */ + if (bio_flagged(bio, BIO_TG_BPS_THROTTLED) || + bio_flagged(bio, BIO_BPS_THROTTLED)) { + bio_list_add(&qn->bios_iops, bio); + sq->nr_queued_iops[rw]++; + } else { + bio_list_add(&qn->bios_bps, bio); + sq->nr_queued_bps[rw]++; + } + if (list_empty(&qn->node)) { - list_add_tail(&qn->node, queued); + list_add_tail(&qn->node, &sq->queued[rw]); blkg_get(tg_to_blkg(qn->tg)); } } @@ -170,6 +185,10 @@ static void throtl_qnode_add_bio(struct bio *bio, struct throtl_qnode *qn, /** * throtl_peek_queued - peek the first bio on a qnode list * @queued: the qnode list to peek + * + * Always take a bio from the head of the iops queue first. If the queue is + * empty, we then take it from the bps queue to maintain the overall idea of + * fetching bios from the head. */ static struct bio *throtl_peek_queued(struct list_head *queued) { @@ -180,28 +199,33 @@ static struct bio *throtl_peek_queued(struct list_head *queued) return NULL; qn = list_first_entry(queued, struct throtl_qnode, node); - bio = bio_list_peek(&qn->bios); + bio = bio_list_peek(&qn->bios_iops); + if (!bio) + bio = bio_list_peek(&qn->bios_bps); WARN_ON_ONCE(!bio); return bio; } /** * throtl_pop_queued - pop the first bio form a qnode list - * @queued: the qnode list to pop a bio from + * @sq: the service_queue to pop a bio from * @tg_to_put: optional out argument for throtl_grp to put + * @rw: read/write * - * Pop the first bio from the qnode list @queued. After popping, the first - * qnode is removed from @queued if empty or moved to the end of @queued so - * that the popping order is round-robin. + * Pop the first bio from the qnode list @sq->queued. Note that we firstly + * focus on the iops list because bios are ultimately dispatched from it. + * After popping, the first qnode is removed from @sq->queued if empty or moved + * to the end of @sq->queued so that the popping order is round-robin. * * When the first qnode is removed, its associated throtl_grp should be put * too. If @tg_to_put is NULL, this function automatically puts it; * otherwise, *@tg_to_put is set to the throtl_grp to put and the caller is * responsible for putting it. */ -static struct bio *throtl_pop_queued(struct list_head *queued, - struct throtl_grp **tg_to_put) +static struct bio *throtl_pop_queued(struct throtl_service_queue *sq, + struct throtl_grp **tg_to_put, bool rw) { + struct list_head *queued = &sq->queued[rw]; struct throtl_qnode *qn; struct bio *bio; @@ -209,10 +233,17 @@ static struct bio *throtl_pop_queued(struct list_head *queued, return NULL; qn = list_first_entry(queued, struct throtl_qnode, node); - bio = bio_list_pop(&qn->bios); + bio = bio_list_pop(&qn->bios_iops); + if (bio) { + sq->nr_queued_iops[rw]--; + } else { + bio = bio_list_pop(&qn->bios_bps); + if (bio) + sq->nr_queued_bps[rw]--; + } WARN_ON_ONCE(!bio); - if (bio_list_empty(&qn->bios)) { + if (bio_list_empty(&qn->bios_bps) && bio_list_empty(&qn->bios_iops)) { list_del_init(&qn->node); if (tg_to_put) *tg_to_put = qn->tg; @@ -333,7 +364,7 @@ static void throtl_pd_free(struct blkg_policy_data *pd) { struct throtl_grp *tg = pd_to_tg(pd); - del_timer_sync(&tg->service_queue.pending_timer); + timer_delete_sync(&tg->service_queue.pending_timer); blkg_rwstat_exit(&tg->stat_bytes); blkg_rwstat_exit(&tg->stat_ios); kfree(tg); @@ -478,8 +509,6 @@ static inline void throtl_start_new_slice_with_credit(struct throtl_grp *tg, { tg->bytes_disp[rw] = 0; tg->io_disp[rw] = 0; - tg->carryover_bytes[rw] = 0; - tg->carryover_ios[rw] = 0; /* * Previous slice has expired. We must have trimmed it after last @@ -498,16 +527,14 @@ static inline void throtl_start_new_slice_with_credit(struct throtl_grp *tg, } static inline void throtl_start_new_slice(struct throtl_grp *tg, bool rw, - bool clear_carryover) + bool clear) { - tg->bytes_disp[rw] = 0; - tg->io_disp[rw] = 0; + if (clear) { + tg->bytes_disp[rw] = 0; + tg->io_disp[rw] = 0; + } tg->slice_start[rw] = jiffies; tg->slice_end[rw] = jiffies + tg->td->throtl_slice; - if (clear_carryover) { - tg->carryover_bytes[rw] = 0; - tg->carryover_ios[rw] = 0; - } throtl_log(&tg->service_queue, "[%c] new slice start=%lu end=%lu jiffies=%lu", @@ -524,6 +551,9 @@ static inline void throtl_set_slice_end(struct throtl_grp *tg, bool rw, static inline void throtl_extend_slice(struct throtl_grp *tg, bool rw, unsigned long jiffy_end) { + if (!time_before(tg->slice_end[rw], jiffy_end)) + return; + throtl_set_slice_end(tg, rw, jiffy_end); throtl_log(&tg->service_queue, "[%c] extend slice start=%lu end=%lu jiffies=%lu", @@ -540,6 +570,11 @@ static bool throtl_slice_used(struct throtl_grp *tg, bool rw) return true; } +static unsigned int sq_queued(struct throtl_service_queue *sq, int type) +{ + return sq->nr_queued_bps[type] + sq->nr_queued_iops[type]; +} + static unsigned int calculate_io_allowed(u32 iops_limit, unsigned long jiffy_elapsed) { @@ -575,6 +610,48 @@ static u64 calculate_bytes_allowed(u64 bps_limit, unsigned long jiffy_elapsed) return mul_u64_u64_div_u64(bps_limit, (u64)jiffy_elapsed, (u64)HZ); } +static long long throtl_trim_bps(struct throtl_grp *tg, bool rw, + unsigned long time_elapsed) +{ + u64 bps_limit = tg_bps_limit(tg, rw); + long long bytes_trim; + + if (bps_limit == U64_MAX) + return 0; + + /* Need to consider the case of bytes_allowed overflow. */ + bytes_trim = calculate_bytes_allowed(bps_limit, time_elapsed); + if (bytes_trim <= 0 || tg->bytes_disp[rw] < bytes_trim) { + bytes_trim = tg->bytes_disp[rw]; + tg->bytes_disp[rw] = 0; + } else { + tg->bytes_disp[rw] -= bytes_trim; + } + + return bytes_trim; +} + +static int throtl_trim_iops(struct throtl_grp *tg, bool rw, + unsigned long time_elapsed) +{ + u32 iops_limit = tg_iops_limit(tg, rw); + int io_trim; + + if (iops_limit == UINT_MAX) + return 0; + + /* Need to consider the case of io_allowed overflow. */ + io_trim = calculate_io_allowed(iops_limit, time_elapsed); + if (io_trim <= 0 || tg->io_disp[rw] < io_trim) { + io_trim = tg->io_disp[rw]; + tg->io_disp[rw] = 0; + } else { + tg->io_disp[rw] -= io_trim; + } + + return io_trim; +} + /* Trim the used slices and adjust slice start accordingly */ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw) { @@ -616,26 +693,11 @@ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw) * one extra slice is preserved for deviation. */ time_elapsed -= tg->td->throtl_slice; - bytes_trim = calculate_bytes_allowed(tg_bps_limit(tg, rw), - time_elapsed) + - tg->carryover_bytes[rw]; - io_trim = calculate_io_allowed(tg_iops_limit(tg, rw), time_elapsed) + - tg->carryover_ios[rw]; - if (bytes_trim <= 0 && io_trim <= 0) + bytes_trim = throtl_trim_bps(tg, rw, time_elapsed); + io_trim = throtl_trim_iops(tg, rw, time_elapsed); + if (!bytes_trim && !io_trim) return; - tg->carryover_bytes[rw] = 0; - if ((long long)tg->bytes_disp[rw] >= bytes_trim) - tg->bytes_disp[rw] -= bytes_trim; - else - tg->bytes_disp[rw] = 0; - - tg->carryover_ios[rw] = 0; - if ((int)tg->io_disp[rw] >= io_trim) - tg->io_disp[rw] -= io_trim; - else - tg->io_disp[rw] = 0; - tg->slice_start[rw] += time_elapsed; throtl_log(&tg->service_queue, @@ -645,39 +707,60 @@ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw) jiffies); } -static void __tg_update_carryover(struct throtl_grp *tg, bool rw) +static void __tg_update_carryover(struct throtl_grp *tg, bool rw, + long long *bytes, int *ios) { unsigned long jiffy_elapsed = jiffies - tg->slice_start[rw]; u64 bps_limit = tg_bps_limit(tg, rw); u32 iops_limit = tg_iops_limit(tg, rw); + long long bytes_allowed; + int io_allowed; + + /* + * If the queue is empty, carryover handling is not needed. In such cases, + * tg->[bytes/io]_disp should be reset to 0 to avoid impacting the dispatch + * of subsequent bios. The same handling applies when the previous BPS/IOPS + * limit was set to max. + */ + if (sq_queued(&tg->service_queue, rw) == 0) { + tg->bytes_disp[rw] = 0; + tg->io_disp[rw] = 0; + return; + } /* * If config is updated while bios are still throttled, calculate and - * accumulate how many bytes/ios are waited across changes. And - * carryover_bytes/ios will be used to calculate new wait time under new - * configuration. + * accumulate how many bytes/ios are waited across changes. And use the + * calculated carryover (@bytes/@ios) to update [bytes/io]_disp, which + * will be used to calculate new wait time under new configuration. + * And we need to consider the case of bytes/io_allowed overflow. */ - if (bps_limit != U64_MAX) - tg->carryover_bytes[rw] += - calculate_bytes_allowed(bps_limit, jiffy_elapsed) - - tg->bytes_disp[rw]; - if (iops_limit != UINT_MAX) - tg->carryover_ios[rw] += - calculate_io_allowed(iops_limit, jiffy_elapsed) - - tg->io_disp[rw]; + if (bps_limit != U64_MAX) { + bytes_allowed = calculate_bytes_allowed(bps_limit, jiffy_elapsed); + if (bytes_allowed > 0) + *bytes = bytes_allowed - tg->bytes_disp[rw]; + } + if (iops_limit != UINT_MAX) { + io_allowed = calculate_io_allowed(iops_limit, jiffy_elapsed); + if (io_allowed > 0) + *ios = io_allowed - tg->io_disp[rw]; + } + + tg->bytes_disp[rw] = -*bytes; + tg->io_disp[rw] = -*ios; } static void tg_update_carryover(struct throtl_grp *tg) { - if (tg->service_queue.nr_queued[READ]) - __tg_update_carryover(tg, READ); - if (tg->service_queue.nr_queued[WRITE]) - __tg_update_carryover(tg, WRITE); + long long bytes[2] = {0}; + int ios[2] = {0}; + + __tg_update_carryover(tg, READ, &bytes[READ], &ios[READ]); + __tg_update_carryover(tg, WRITE, &bytes[WRITE], &ios[WRITE]); - /* see comments in struct throtl_grp for meaning of these fields. */ + /* see comments in struct throtl_grp for meaning of carryover. */ throtl_log(&tg->service_queue, "%s: %lld %lld %d %d\n", __func__, - tg->carryover_bytes[READ], tg->carryover_bytes[WRITE], - tg->carryover_ios[READ], tg->carryover_ios[WRITE]); + bytes[READ], bytes[WRITE], ios[READ], ios[WRITE]); } static unsigned long tg_within_iops_limit(struct throtl_grp *tg, struct bio *bio, @@ -687,16 +770,11 @@ static unsigned long tg_within_iops_limit(struct throtl_grp *tg, struct bio *bio int io_allowed; unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd; - if (iops_limit == UINT_MAX) { - return 0; - } - jiffy_elapsed = jiffies - tg->slice_start[rw]; /* Round up to the next throttle slice, wait time must be nonzero */ jiffy_elapsed_rnd = roundup(jiffy_elapsed + 1, tg->td->throtl_slice); - io_allowed = calculate_io_allowed(iops_limit, jiffy_elapsed_rnd) + - tg->carryover_ios[rw]; + io_allowed = calculate_io_allowed(iops_limit, jiffy_elapsed_rnd); if (io_allowed > 0 && tg->io_disp[rw] + 1 <= io_allowed) return 0; @@ -717,11 +795,6 @@ static unsigned long tg_within_bps_limit(struct throtl_grp *tg, struct bio *bio, unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd; unsigned int bio_size = throtl_bio_data_size(bio); - /* no need to throttle if this bio's bytes have been accounted */ - if (bps_limit == U64_MAX || bio_flagged(bio, BIO_BPS_THROTTLED)) { - return 0; - } - jiffy_elapsed = jiffy_elapsed_rnd = jiffies - tg->slice_start[rw]; /* Slice has just started. Consider one slice interval */ @@ -729,9 +802,10 @@ static unsigned long tg_within_bps_limit(struct throtl_grp *tg, struct bio *bio, jiffy_elapsed_rnd = tg->td->throtl_slice; jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, tg->td->throtl_slice); - bytes_allowed = calculate_bytes_allowed(bps_limit, jiffy_elapsed_rnd) + - tg->carryover_bytes[rw]; - if (bytes_allowed > 0 && tg->bytes_disp[rw] + bio_size <= bytes_allowed) + bytes_allowed = calculate_bytes_allowed(bps_limit, jiffy_elapsed_rnd); + /* Need to consider the case of bytes_allowed overflow. */ + if ((bytes_allowed > 0 && tg->bytes_disp[rw] + bio_size <= bytes_allowed) + || bytes_allowed < 0) return 0; /* Calc approx time to dispatch */ @@ -749,17 +823,82 @@ static unsigned long tg_within_bps_limit(struct throtl_grp *tg, struct bio *bio, return jiffy_wait; } +static void throtl_charge_bps_bio(struct throtl_grp *tg, struct bio *bio) +{ + unsigned int bio_size = throtl_bio_data_size(bio); + + /* Charge the bio to the group */ + if (!bio_flagged(bio, BIO_BPS_THROTTLED) && + !bio_flagged(bio, BIO_TG_BPS_THROTTLED)) { + bio_set_flag(bio, BIO_TG_BPS_THROTTLED); + tg->bytes_disp[bio_data_dir(bio)] += bio_size; + } +} + +static void throtl_charge_iops_bio(struct throtl_grp *tg, struct bio *bio) +{ + bio_clear_flag(bio, BIO_TG_BPS_THROTTLED); + tg->io_disp[bio_data_dir(bio)]++; +} + /* - * Returns whether one can dispatch a bio or not. Also returns approx number - * of jiffies to wait before this bio is with-in IO rate and can be dispatched + * If previous slice expired, start a new one otherwise renew/extend existing + * slice to make sure it is at least throtl_slice interval long since now. New + * slice is started only for empty throttle group. If there is queued bio, that + * means there should be an active slice and it should be extended instead. */ -static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio, - unsigned long *wait) +static void tg_update_slice(struct throtl_grp *tg, bool rw) +{ + if (throtl_slice_used(tg, rw) && + sq_queued(&tg->service_queue, rw) == 0) + throtl_start_new_slice(tg, rw, true); + else + throtl_extend_slice(tg, rw, jiffies + tg->td->throtl_slice); +} + +static unsigned long tg_dispatch_bps_time(struct throtl_grp *tg, struct bio *bio) { bool rw = bio_data_dir(bio); - unsigned long bps_wait = 0, iops_wait = 0, max_wait = 0; u64 bps_limit = tg_bps_limit(tg, rw); + unsigned long bps_wait; + + /* no need to throttle if this bio's bytes have been accounted */ + if (bps_limit == U64_MAX || tg->flags & THROTL_TG_CANCELING || + bio_flagged(bio, BIO_BPS_THROTTLED) || + bio_flagged(bio, BIO_TG_BPS_THROTTLED)) + return 0; + + tg_update_slice(tg, rw); + bps_wait = tg_within_bps_limit(tg, bio, bps_limit); + throtl_extend_slice(tg, rw, jiffies + bps_wait); + + return bps_wait; +} + +static unsigned long tg_dispatch_iops_time(struct throtl_grp *tg, struct bio *bio) +{ + bool rw = bio_data_dir(bio); u32 iops_limit = tg_iops_limit(tg, rw); + unsigned long iops_wait; + + if (iops_limit == UINT_MAX || tg->flags & THROTL_TG_CANCELING) + return 0; + + tg_update_slice(tg, rw); + iops_wait = tg_within_iops_limit(tg, bio, iops_limit); + throtl_extend_slice(tg, rw, jiffies + iops_wait); + + return iops_wait; +} + +/* + * Returns approx number of jiffies to wait before this bio is with-in IO rate + * and can be moved to other queue or dispatched. + */ +static unsigned long tg_dispatch_time(struct throtl_grp *tg, struct bio *bio) +{ + bool rw = bio_data_dir(bio); + unsigned long wait; /* * Currently whole state machine of group depends on first bio @@ -767,65 +906,20 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio, * this function with a different bio if there are other bios * queued. */ - BUG_ON(tg->service_queue.nr_queued[rw] && + BUG_ON(sq_queued(&tg->service_queue, rw) && bio != throtl_peek_queued(&tg->service_queue.queued[rw])); - /* If tg->bps = -1, then BW is unlimited */ - if ((bps_limit == U64_MAX && iops_limit == UINT_MAX) || - tg->flags & THROTL_TG_CANCELING) { - if (wait) - *wait = 0; - return true; - } + wait = tg_dispatch_bps_time(tg, bio); + if (wait != 0) + return wait; /* - * If previous slice expired, start a new one otherwise renew/extend - * existing slice to make sure it is at least throtl_slice interval - * long since now. New slice is started only for empty throttle group. - * If there is queued bio, that means there should be an active - * slice and it should be extended instead. + * Charge bps here because @bio will be directly placed into the + * iops queue afterward. */ - if (throtl_slice_used(tg, rw) && !(tg->service_queue.nr_queued[rw])) - throtl_start_new_slice(tg, rw, true); - else { - if (time_before(tg->slice_end[rw], - jiffies + tg->td->throtl_slice)) - throtl_extend_slice(tg, rw, - jiffies + tg->td->throtl_slice); - } - - bps_wait = tg_within_bps_limit(tg, bio, bps_limit); - iops_wait = tg_within_iops_limit(tg, bio, iops_limit); - if (bps_wait + iops_wait == 0) { - if (wait) - *wait = 0; - return true; - } - - max_wait = max(bps_wait, iops_wait); - - if (wait) - *wait = max_wait; - - if (time_before(tg->slice_end[rw], jiffies + max_wait)) - throtl_extend_slice(tg, rw, jiffies + max_wait); + throtl_charge_bps_bio(tg, bio); - return false; -} - -static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio) -{ - bool rw = bio_data_dir(bio); - unsigned int bio_size = throtl_bio_data_size(bio); - - /* Charge the bio to the group */ - if (!bio_flagged(bio, BIO_BPS_THROTTLED)) { - tg->bytes_disp[rw] += bio_size; - tg->last_bytes_disp[rw] += bio_size; - } - - tg->io_disp[rw]++; - tg->last_io_disp[rw]++; + return tg_dispatch_iops_time(tg, bio); } /** @@ -852,28 +946,36 @@ static void throtl_add_bio_tg(struct bio *bio, struct throtl_qnode *qn, * dispatched. Mark that @tg was empty. This is automatically * cleared on the next tg_update_disptime(). */ - if (!sq->nr_queued[rw]) + if (sq_queued(sq, rw) == 0) tg->flags |= THROTL_TG_WAS_EMPTY; - throtl_qnode_add_bio(bio, qn, &sq->queued[rw]); + throtl_qnode_add_bio(bio, qn, sq); + + /* + * Since we have split the queues, when the iops queue is + * previously empty and a new @bio is added into the first @qn, + * we also need to update the @tg->disptime. + */ + if (bio_flagged(bio, BIO_BPS_THROTTLED) && + bio == throtl_peek_queued(&sq->queued[rw])) + tg->flags |= THROTL_TG_IOPS_WAS_EMPTY; - sq->nr_queued[rw]++; throtl_enqueue_tg(tg); } static void tg_update_disptime(struct throtl_grp *tg) { struct throtl_service_queue *sq = &tg->service_queue; - unsigned long read_wait = -1, write_wait = -1, min_wait = -1, disptime; + unsigned long read_wait = -1, write_wait = -1, min_wait, disptime; struct bio *bio; bio = throtl_peek_queued(&sq->queued[READ]); if (bio) - tg_may_dispatch(tg, bio, &read_wait); + read_wait = tg_dispatch_time(tg, bio); bio = throtl_peek_queued(&sq->queued[WRITE]); if (bio) - tg_may_dispatch(tg, bio, &write_wait); + write_wait = tg_dispatch_time(tg, bio); min_wait = min(read_wait, write_wait); disptime = jiffies + min_wait; @@ -885,6 +987,7 @@ static void tg_update_disptime(struct throtl_grp *tg) /* see throtl_add_bio_tg() */ tg->flags &= ~THROTL_TG_WAS_EMPTY; + tg->flags &= ~THROTL_TG_IOPS_WAS_EMPTY; } static void start_parent_slice_with_credit(struct throtl_grp *child_tg, @@ -911,10 +1014,9 @@ static void tg_dispatch_one_bio(struct throtl_grp *tg, bool rw) * getting released prematurely. Remember the tg to put and put it * after @bio is transferred to @parent_sq. */ - bio = throtl_pop_queued(&sq->queued[rw], &tg_to_put); - sq->nr_queued[rw]--; + bio = throtl_pop_queued(sq, &tg_to_put, rw); - throtl_charge_bio(tg, bio); + throtl_charge_iops_bio(tg, bio); /* * If our parent is another tg, we just need to transfer @bio to @@ -929,7 +1031,7 @@ static void tg_dispatch_one_bio(struct throtl_grp *tg, bool rw) } else { bio_set_flag(bio, BIO_BPS_THROTTLED); throtl_qnode_add_bio(bio, &tg->qnode_on_parent[rw], - &parent_sq->queued[rw]); + parent_sq); BUG_ON(tg->td->nr_queued[rw] <= 0); tg->td->nr_queued[rw]--; } @@ -951,7 +1053,7 @@ static int throtl_dispatch_tg(struct throtl_grp *tg) /* Try to dispatch 75% READS and 25% WRITES */ while ((bio = throtl_peek_queued(&sq->queued[READ])) && - tg_may_dispatch(tg, bio, NULL)) { + tg_dispatch_time(tg, bio) == 0) { tg_dispatch_one_bio(tg, READ); nr_reads++; @@ -961,7 +1063,7 @@ static int throtl_dispatch_tg(struct throtl_grp *tg) } while ((bio = throtl_peek_queued(&sq->queued[WRITE])) && - tg_may_dispatch(tg, bio, NULL)) { + tg_dispatch_time(tg, bio) == 0) { tg_dispatch_one_bio(tg, WRITE); nr_writes++; @@ -994,7 +1096,7 @@ static int throtl_select_dispatch(struct throtl_service_queue *parent_sq) nr_disp += throtl_dispatch_tg(tg); sq = &tg->service_queue; - if (sq->nr_queued[READ] || sq->nr_queued[WRITE]) + if (sq_queued(sq, READ) || sq_queued(sq, WRITE)) tg_update_disptime(tg); else throtl_dequeue_tg(tg); @@ -1023,7 +1125,8 @@ static int throtl_select_dispatch(struct throtl_service_queue *parent_sq) */ static void throtl_pending_timer_fn(struct timer_list *t) { - struct throtl_service_queue *sq = from_timer(sq, t, pending_timer); + struct throtl_service_queue *sq = timer_container_of(sq, t, + pending_timer); struct throtl_grp *tg = sq_to_tg(sq); struct throtl_data *td = sq_to_td(sq); struct throtl_service_queue *parent_sq; @@ -1047,9 +1150,11 @@ again: dispatched = false; while (true) { + unsigned int __maybe_unused bio_cnt_r = sq_queued(sq, READ); + unsigned int __maybe_unused bio_cnt_w = sq_queued(sq, WRITE); + throtl_log(sq, "dispatch nr_queued=%u read=%u write=%u", - sq->nr_queued[READ] + sq->nr_queued[WRITE], - sq->nr_queued[READ], sq->nr_queued[WRITE]); + bio_cnt_r + bio_cnt_w, bio_cnt_r, bio_cnt_w); ret = throtl_select_dispatch(sq); if (ret) { @@ -1071,7 +1176,8 @@ again: if (parent_sq) { /* @parent_sq is another throl_grp, propagate dispatch */ - if (tg->flags & THROTL_TG_WAS_EMPTY) { + if (tg->flags & THROTL_TG_WAS_EMPTY || + tg->flags & THROTL_TG_IOPS_WAS_EMPTY) { tg_update_disptime(tg); if (!throtl_schedule_next_dispatch(parent_sq, false)) { /* window is already open, repeat dispatching */ @@ -1111,7 +1217,7 @@ static void blk_throtl_dispatch_work_fn(struct work_struct *work) spin_lock_irq(&q->queue_lock); for (rw = READ; rw <= WRITE; rw++) - while ((bio = throtl_pop_queued(&td_sq->queued[rw], NULL))) + while ((bio = throtl_pop_queued(td_sq, NULL, rw))) bio_list_add(&bio_list_on_stack, bio); spin_unlock_irq(&q->queue_lock); @@ -1616,18 +1722,30 @@ void blk_throtl_cancel_bios(struct gendisk *disk) static bool tg_within_limit(struct throtl_grp *tg, struct bio *bio, bool rw) { - /* throtl is FIFO - if bios are already queued, should queue */ - if (tg->service_queue.nr_queued[rw]) - return false; + struct throtl_service_queue *sq = &tg->service_queue; - return tg_may_dispatch(tg, bio, NULL); -} + /* + * For a split bio, we need to specifically distinguish whether the + * iops queue is empty. + */ + if (bio_flagged(bio, BIO_BPS_THROTTLED)) + return sq->nr_queued_iops[rw] == 0 && + tg_dispatch_iops_time(tg, bio) == 0; -static void tg_dispatch_in_debt(struct throtl_grp *tg, struct bio *bio, bool rw) -{ - if (!bio_flagged(bio, BIO_BPS_THROTTLED)) - tg->carryover_bytes[rw] -= throtl_bio_data_size(bio); - tg->carryover_ios[rw]--; + /* + * Throtl is FIFO - if bios are already queued, should queue. + * If the bps queue is empty and @bio is within the bps limit, charge + * bps here for direct placement into the iops queue. + */ + if (sq_queued(&tg->service_queue, rw)) { + if (sq->nr_queued_bps[rw] == 0 && + tg_dispatch_bps_time(tg, bio) == 0) + throtl_charge_bps_bio(tg, bio); + + return false; + } + + return tg_dispatch_time(tg, bio) == 0; } bool __blk_throtl_bio(struct bio *bio) @@ -1648,7 +1766,7 @@ bool __blk_throtl_bio(struct bio *bio) while (true) { if (tg_within_limit(tg, bio, rw)) { /* within limits, let's charge and dispatch directly */ - throtl_charge_bio(tg, bio); + throtl_charge_iops_bio(tg, bio); /* * We need to trim slice even when bios are not being @@ -1666,10 +1784,13 @@ bool __blk_throtl_bio(struct bio *bio) /* * IOs which may cause priority inversions are * dispatched directly, even if they're over limit. - * Debts are handled by carryover_bytes/ios while - * calculating wait time. + * + * Charge and dispatch directly, and our throttle + * control algorithm is adaptive, and extra IO bytes + * will be throttled for paying the debt */ - tg_dispatch_in_debt(tg, bio, rw); + throtl_charge_bps_bio(tg, bio); + throtl_charge_iops_bio(tg, bio); } else { /* if above limits, break to queue */ break; @@ -1695,7 +1816,7 @@ bool __blk_throtl_bio(struct bio *bio) tg->bytes_disp[rw], bio->bi_iter.bi_size, tg_bps_limit(tg, rw), tg->io_disp[rw], tg_iops_limit(tg, rw), - sq->nr_queued[READ], sq->nr_queued[WRITE]); + sq_queued(sq, READ), sq_queued(sq, WRITE)); td->nr_queued[rw]++; throtl_add_bio_tg(bio, qn, tg); @@ -1703,11 +1824,13 @@ bool __blk_throtl_bio(struct bio *bio) /* * Update @tg's dispatch time and force schedule dispatch if @tg - * was empty before @bio. The forced scheduling isn't likely to - * cause undue delay as @bio is likely to be dispatched directly if - * its @tg's disptime is not in the future. + * was empty before @bio, or the iops queue is empty and @bio will + * add to. The forced scheduling isn't likely to cause undue + * delay as @bio is likely to be dispatched directly if its @tg's + * disptime is not in the future. */ - if (tg->flags & THROTL_TG_WAS_EMPTY) { + if (tg->flags & THROTL_TG_WAS_EMPTY || + tg->flags & THROTL_TG_IOPS_WAS_EMPTY) { tg_update_disptime(tg); throtl_schedule_next_dispatch(tg->service_queue.parent_sq, true); } @@ -1726,7 +1849,7 @@ void blk_throtl_exit(struct gendisk *disk) if (!blk_throtl_activated(q)) return; - del_timer_sync(&q->td->service_queue.pending_timer); + timer_delete_sync(&q->td->service_queue.pending_timer); throtl_shutdown_wq(q); blkcg_deactivate_policy(disk, &blkcg_policy_throtl); kfree(q->td); diff --git a/block/blk-throttle.h b/block/blk-throttle.h index 1a36d1278eea..3b27755bfbff 100644 --- a/block/blk-throttle.h +++ b/block/blk-throttle.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef BLK_THROTTLE_H #define BLK_THROTTLE_H @@ -28,7 +29,8 @@ */ struct throtl_qnode { struct list_head node; /* service_queue->queued[] */ - struct bio_list bios; /* queued bios */ + struct bio_list bios_bps; /* queued bios for bps limit */ + struct bio_list bios_iops; /* queued bios for iops limit */ struct throtl_grp *tg; /* tg this qnode belongs to */ }; @@ -40,7 +42,8 @@ struct throtl_service_queue { * children throtl_grp's. */ struct list_head queued[2]; /* throtl_qnode [READ/WRITE] */ - unsigned int nr_queued[2]; /* number of queued bios */ + unsigned int nr_queued_bps[2]; /* number of queued bps bios */ + unsigned int nr_queued_iops[2]; /* number of queued iops bios */ /* * RB tree of active children throtl_grp's, which are sorted by @@ -53,9 +56,14 @@ struct throtl_service_queue { }; enum tg_state_flags { - THROTL_TG_PENDING = 1 << 0, /* on parent's pending tree */ - THROTL_TG_WAS_EMPTY = 1 << 1, /* bio_lists[] became non-empty */ - THROTL_TG_CANCELING = 1 << 2, /* starts to cancel bio */ + THROTL_TG_PENDING = 1 << 0, /* on parent's pending tree */ + THROTL_TG_WAS_EMPTY = 1 << 1, /* bio_lists[] became non-empty */ + /* + * The sq's iops queue is empty, and a bio is about to be enqueued + * to the first qnode's bios_iops list. + */ + THROTL_TG_IOPS_WAS_EMPTY = 1 << 2, + THROTL_TG_CANCELING = 1 << 3, /* starts to cancel bio */ }; struct throtl_grp { @@ -101,22 +109,16 @@ struct throtl_grp { /* IOPS limits */ unsigned int iops[2]; - /* Number of bytes dispatched in current slice */ - uint64_t bytes_disp[2]; - /* Number of bio's dispatched in current slice */ - unsigned int io_disp[2]; - - uint64_t last_bytes_disp[2]; - unsigned int last_io_disp[2]; - /* - * The following two fields are updated when new configuration is - * submitted while some bios are still throttled, they record how many - * bytes/ios are waited already in previous configuration, and they will - * be used to calculate wait time under new configuration. + * Number of bytes/bio's dispatched in current slice. + * When new configuration is submitted while some bios are still throttled, + * first calculate the carryover: the amount of bytes/IOs already waited + * under the previous configuration. Then, [bytes/io]_disp are represented + * as the negative of the carryover, and they will be used to calculate the + * wait time under the new configuration. */ - long long carryover_bytes[2]; - int carryover_ios[2]; + int64_t bytes_disp[2]; + int io_disp[2]; unsigned long last_check_time; diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 6dfc659d22e2..a50d4cd55f41 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -37,7 +37,7 @@ enum wbt_flags { WBT_TRACKED = 1, /* write, tracked for throttling */ WBT_READ = 2, /* read */ - WBT_SWAP = 4, /* write, from swap_writepage() */ + WBT_SWAP = 4, /* write, from swap_writeout() */ WBT_DISCARD = 8, /* discard */ WBT_NR_BITS = 4, /* number of bits */ @@ -136,8 +136,9 @@ enum { RWB_MIN_WRITE_SAMPLES = 3, /* - * If we have this number of consecutive windows with not enough - * information to scale up or down, scale up. + * If we have this number of consecutive windows without enough + * information to scale up or down, slowly return to center state + * (step == 0). */ RWB_UNKNOWN_BUMP = 5, }; @@ -446,9 +447,9 @@ static void wb_timer_fn(struct blk_stat_callback *cb) break; case LAT_UNKNOWN_WRITES: /* - * We started a the center step, but don't have a valid - * read/write sample, but we do have writes going on. - * Allow step to go negative, to increase write perf. + * We don't have a valid read/write sample, but we do have + * writes going on. Allow step to go negative, to increase + * write performance. */ scale_up(rwb); break; @@ -638,11 +639,7 @@ static void wbt_cleanup(struct rq_qos *rqos, struct bio *bio) __wbt_done(rqos, flags); } -/* - * May sleep, if we have exceeded the writeback limits. Caller can pass - * in an irq held spinlock, if it holds one when calling this function. - * If we do sleep, we'll release and re-grab it. - */ +/* May sleep, if we have exceeded the writeback limits. */ static void wbt_wait(struct rq_qos *rqos, struct bio *bio) { struct rq_wb *rwb = RQWB(rqos); @@ -707,8 +704,9 @@ void wbt_enable_default(struct gendisk *disk) struct rq_qos *rqos; bool enable = IS_ENABLED(CONFIG_BLK_WBT_MQ); - if (q->elevator && - test_bit(ELEVATOR_FLAG_DISABLE_WBT, &q->elevator->flags)) + mutex_lock(&disk->rqos_state_mutex); + + if (blk_queue_disable_wbt(q)) enable = false; /* Throttling already enabled? */ @@ -716,8 +714,10 @@ void wbt_enable_default(struct gendisk *disk) if (rqos) { if (enable && RQWB(rqos)->enable_state == WBT_STATE_OFF_DEFAULT) RQWB(rqos)->enable_state = WBT_STATE_ON_DEFAULT; + mutex_unlock(&disk->rqos_state_mutex); return; } + mutex_unlock(&disk->rqos_state_mutex); /* Queue not registered? Maybe shutting down... */ if (!blk_queue_registered(q)) @@ -777,11 +777,13 @@ void wbt_disable_default(struct gendisk *disk) struct rq_wb *rwb; if (!rqos) return; + mutex_lock(&disk->rqos_state_mutex); rwb = RQWB(rqos); if (rwb->enable_state == WBT_STATE_ON_DEFAULT) { blk_stat_deactivate(rwb->cb); rwb->enable_state = WBT_STATE_OFF_DEFAULT; } + mutex_unlock(&disk->rqos_state_mutex); } EXPORT_SYMBOL_GPL(wbt_disable_default); diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 0c77244a35c9..9104c3a34642 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -343,6 +343,7 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode, op = REQ_OP_ZONE_RESET; /* Invalidate the page cache, including dirty pages. */ + inode_lock(bdev->bd_mapping->host); filemap_invalidate_lock(bdev->bd_mapping); ret = blkdev_truncate_zone_range(bdev, mode, &zrange); if (ret) @@ -364,8 +365,10 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode, ret = blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors); fail: - if (cmd == BLKRESETZONE) + if (cmd == BLKRESETZONE) { filemap_invalidate_unlock(bdev->bd_mapping); + inode_unlock(bdev->bd_mapping->host); + } return ret; } @@ -1113,25 +1116,7 @@ bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs) { struct block_device *bdev = bio->bi_bdev; - if (!bdev->bd_disk->zone_wplugs_hash) - return false; - - /* - * If the BIO already has the plugging flag set, then it was already - * handled through this path and this is a submission from the zone - * plug bio submit work. - */ - if (bio_flagged(bio, BIO_ZONE_WRITE_PLUGGING)) - return false; - - /* - * We do not need to do anything special for empty flush BIOs, e.g - * BIOs such as issued by blkdev_issue_flush(). The is because it is - * the responsibility of the user to first wait for the completion of - * write operations for flush to have any effect on the persistence of - * the written data. - */ - if (op_is_flush(bio->bi_opf) && !bio_sectors(bio)) + if (WARN_ON_ONCE(!bdev->bd_disk->zone_wplugs_hash)) return false; /* @@ -1222,6 +1207,7 @@ void blk_zone_write_plug_bio_endio(struct bio *bio) if (bio_flagged(bio, BIO_EMULATES_ZONE_APPEND)) { bio->bi_opf &= ~REQ_OP_MASK; bio->bi_opf |= REQ_OP_ZONE_APPEND; + bio_clear_flag(bio, BIO_EMULATES_ZONE_APPEND); } /* @@ -1280,14 +1266,14 @@ static void blk_zone_wplug_bio_work(struct work_struct *work) struct block_device *bdev; unsigned long flags; struct bio *bio; + bool prepared; /* * Submit the next plugged BIO. If we do not have any, clear * the plugged flag. */ - spin_lock_irqsave(&zwplug->lock, flags); - again: + spin_lock_irqsave(&zwplug->lock, flags); bio = bio_list_pop(&zwplug->bio_list); if (!bio) { zwplug->flags &= ~BLK_ZONE_WPLUG_PLUGGED; @@ -1295,15 +1281,15 @@ again: goto put_zwplug; } - if (!blk_zone_wplug_prepare_bio(zwplug, bio)) { + prepared = blk_zone_wplug_prepare_bio(zwplug, bio); + spin_unlock_irqrestore(&zwplug->lock, flags); + + if (!prepared) { blk_zone_wplug_bio_io_error(zwplug, bio); goto again; } - spin_unlock_irqrestore(&zwplug->lock, flags); - bdev = bio->bi_bdev; - submit_bio_noacct_nocheck(bio); /* * blk-mq devices will reuse the extra reference on the request queue @@ -1311,8 +1297,12 @@ again: * path for BIO-based devices will not do that. So drop this extra * reference here. */ - if (bdev_test_flag(bdev, BD_HAS_SUBMIT_BIO)) + if (bdev_test_flag(bdev, BD_HAS_SUBMIT_BIO)) { + bdev->bd_disk->fops->submit_bio(bio); blk_queue_exit(bdev->bd_disk->queue); + } else { + blk_mq_submit_bio(bio); + } put_zwplug: /* Drop the reference we took in disk_zone_wplug_schedule_bio_work(). */ diff --git a/block/blk.h b/block/blk.h index 9cf9a0099416..5d9ca8c95193 100644 --- a/block/blk.h +++ b/block/blk.h @@ -12,6 +12,7 @@ #include "blk-crypto-internal.h" struct elevator_type; +struct elevator_tags; #define BLK_DEV_MAX_SECTORS (LLONG_MAX >> 9) #define BLK_MIN_SEGMENT_SIZE 4096 @@ -19,6 +20,7 @@ struct elevator_type; /* Max future timer expiry for timeouts */ #define BLK_MAX_TIMEOUT (5 * HZ) +extern const struct kobj_type blk_queue_ktype; extern struct dentry *blk_debugfs_root; struct blk_flush_queue { @@ -94,14 +96,16 @@ static inline void blk_wait_io(struct completion *done) wait_for_completion_io(done); } +struct block_device *blkdev_get_no_open(dev_t dev, bool autoload); +void blkdev_put_no_open(struct block_device *bdev); + #define BIO_INLINE_VECS 4 struct bio_vec *bvec_alloc(mempool_t *pool, unsigned short *nr_vecs, gfp_t gfp_mask); void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned short nr_vecs); bool bvec_try_merge_hw_page(struct request_queue *q, struct bio_vec *bv, - struct page *page, unsigned len, unsigned offset, - bool *same_page); + struct page *page, unsigned len, unsigned offset); static inline bool biovec_phys_mergeable(struct request_queue *q, struct bio_vec *vec1, struct bio_vec *vec2) @@ -319,11 +323,10 @@ bool blk_bio_list_merge(struct request_queue *q, struct list_head *list, bool blk_insert_flush(struct request *rq); -int elevator_switch(struct request_queue *q, struct elevator_type *new_e); -void elevator_disable(struct request_queue *q); -void elevator_exit(struct request_queue *q); -int elv_register_queue(struct request_queue *q, bool uevent); -void elv_unregister_queue(struct request_queue *q); +void elv_update_nr_hw_queues(struct request_queue *q, struct elevator_type *e, + struct elevator_tags *t); +void elevator_set_default(struct request_queue *q); +void elevator_set_none(struct request_queue *q); ssize_t part_size_show(struct device *dev, struct device_attribute *attr, char *buf); @@ -404,6 +407,27 @@ static inline struct bio *__bio_split_to_limits(struct bio *bio, } } +/** + * get_max_segment_size() - maximum number of bytes to add as a single segment + * @lim: Request queue limits. + * @paddr: address of the range to add + * @len: maximum length available to add at @paddr + * + * Returns the maximum number of bytes of the range starting at @paddr that can + * be added to a single segment. + */ +static inline unsigned get_max_segment_size(const struct queue_limits *lim, + phys_addr_t paddr, unsigned int len) +{ + /* + * Prevent an overflow if mask = ULONG_MAX and offset = 0 by adding 1 + * after having calculated the minimum. + */ + return min_t(unsigned long, len, + min(lim->seg_boundary_mask - (lim->seg_boundary_mask & paddr), + (unsigned long)lim->max_segment_size - 1) + 1); +} + int ll_back_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs); bool blk_attempt_req_merge(struct request_queue *q, struct request *rq, @@ -418,7 +442,6 @@ void blk_apply_bdi_limits(struct backing_dev_info *bdi, int blk_dev_init(void); void update_io_ticks(struct block_device *part, unsigned long now, bool end); -unsigned int part_in_flight(struct block_device *part); static inline void req_set_nomerge(struct request_queue *q, struct request *req) { @@ -440,23 +463,6 @@ static inline void ioc_clear_queue(struct request_queue *q) } #endif /* CONFIG_BLK_ICQ */ -struct bio *__blk_queue_bounce(struct bio *bio, struct request_queue *q); - -static inline bool blk_queue_may_bounce(struct request_queue *q) -{ - return IS_ENABLED(CONFIG_BOUNCE) && - (q->limits.features & BLK_FEAT_BOUNCE_HIGH) && - max_low_pfn >= max_pfn; -} - -static inline struct bio *blk_queue_bounce(struct bio *bio, - struct request_queue *q) -{ - if (unlikely(blk_queue_may_bounce(q) && bio_has_data(bio))) - return __blk_queue_bounce(bio, q); - return bio; -} - #ifdef CONFIG_BLK_DEV_ZONED void disk_init_zone_resources(struct gendisk *disk); void disk_free_zone_resources(struct gendisk *disk); @@ -477,7 +483,8 @@ static inline void blk_zone_update_request_bio(struct request *rq, * the original BIO sector so that blk_zone_write_plug_bio_endio() can * lookup the zone write plug. */ - if (req_op(rq) == REQ_OP_ZONE_APPEND || bio_zone_write_plugging(bio)) + if (req_op(rq) == REQ_OP_ZONE_APPEND || + bio_flagged(bio, BIO_EMULATES_ZONE_APPEND)) bio->bi_iter.bi_sector = rq->__sector; } void blk_zone_write_plug_bio_endio(struct bio *bio); @@ -715,7 +722,7 @@ int bdev_open(struct block_device *bdev, blk_mode_t mode, void *holder, int bdev_permission(dev_t dev, blk_mode_t mode, void *holder); void blk_integrity_generate(struct bio *bio); -void blk_integrity_verify(struct bio *bio); +void blk_integrity_verify_iter(struct bio *bio, struct bvec_iter *saved_iter); void blk_integrity_prepare(struct request *rq); void blk_integrity_complete(struct request *rq, unsigned int nr_bytes); diff --git a/block/bounce.c b/block/bounce.c deleted file mode 100644 index 0d898cd5ec49..000000000000 --- a/block/bounce.c +++ /dev/null @@ -1,269 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* bounce buffer handling for block devices - * - * - Split from highmem.c - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/mm.h> -#include <linux/export.h> -#include <linux/swap.h> -#include <linux/gfp.h> -#include <linux/bio-integrity.h> -#include <linux/pagemap.h> -#include <linux/mempool.h> -#include <linux/blkdev.h> -#include <linux/backing-dev.h> -#include <linux/init.h> -#include <linux/hash.h> -#include <linux/highmem.h> -#include <linux/printk.h> -#include <asm/tlbflush.h> - -#include <trace/events/block.h> -#include "blk.h" -#include "blk-cgroup.h" - -#define POOL_SIZE 64 -#define ISA_POOL_SIZE 16 - -static struct bio_set bounce_bio_set, bounce_bio_split; -static mempool_t page_pool; - -static void init_bounce_bioset(void) -{ - static bool bounce_bs_setup; - int ret; - - if (bounce_bs_setup) - return; - - ret = bioset_init(&bounce_bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); - BUG_ON(ret); - if (bioset_integrity_create(&bounce_bio_set, BIO_POOL_SIZE)) - BUG_ON(1); - - ret = bioset_init(&bounce_bio_split, BIO_POOL_SIZE, 0, 0); - BUG_ON(ret); - bounce_bs_setup = true; -} - -static __init int init_emergency_pool(void) -{ - int ret; - -#ifndef CONFIG_MEMORY_HOTPLUG - if (max_pfn <= max_low_pfn) - return 0; -#endif - - ret = mempool_init_page_pool(&page_pool, POOL_SIZE, 0); - BUG_ON(ret); - pr_info("pool size: %d pages\n", POOL_SIZE); - - init_bounce_bioset(); - return 0; -} - -__initcall(init_emergency_pool); - -/* - * Simple bounce buffer support for highmem pages. Depending on the - * queue gfp mask set, *to may or may not be a highmem page. kmap it - * always, it will do the Right Thing - */ -static void copy_to_high_bio_irq(struct bio *to, struct bio *from) -{ - struct bio_vec tovec, fromvec; - struct bvec_iter iter; - /* - * The bio of @from is created by bounce, so we can iterate - * its bvec from start to end, but the @from->bi_iter can't be - * trusted because it might be changed by splitting. - */ - struct bvec_iter from_iter = BVEC_ITER_ALL_INIT; - - bio_for_each_segment(tovec, to, iter) { - fromvec = bio_iter_iovec(from, from_iter); - if (tovec.bv_page != fromvec.bv_page) { - /* - * fromvec->bv_offset and fromvec->bv_len might have - * been modified by the block layer, so use the original - * copy, bounce_copy_vec already uses tovec->bv_len - */ - memcpy_to_bvec(&tovec, page_address(fromvec.bv_page) + - tovec.bv_offset); - } - bio_advance_iter(from, &from_iter, tovec.bv_len); - } -} - -static void bounce_end_io(struct bio *bio) -{ - struct bio *bio_orig = bio->bi_private; - struct bio_vec *bvec, orig_vec; - struct bvec_iter orig_iter = bio_orig->bi_iter; - struct bvec_iter_all iter_all; - - /* - * free up bounce indirect pages used - */ - bio_for_each_segment_all(bvec, bio, iter_all) { - orig_vec = bio_iter_iovec(bio_orig, orig_iter); - if (bvec->bv_page != orig_vec.bv_page) { - dec_zone_page_state(bvec->bv_page, NR_BOUNCE); - mempool_free(bvec->bv_page, &page_pool); - } - bio_advance_iter(bio_orig, &orig_iter, orig_vec.bv_len); - } - - bio_orig->bi_status = bio->bi_status; - bio_endio(bio_orig); - bio_put(bio); -} - -static void bounce_end_io_write(struct bio *bio) -{ - bounce_end_io(bio); -} - -static void bounce_end_io_read(struct bio *bio) -{ - struct bio *bio_orig = bio->bi_private; - - if (!bio->bi_status) - copy_to_high_bio_irq(bio_orig, bio); - - bounce_end_io(bio); -} - -static struct bio *bounce_clone_bio(struct bio *bio_src) -{ - struct bvec_iter iter; - struct bio_vec bv; - struct bio *bio; - - /* - * Pre immutable biovecs, __bio_clone() used to just do a memcpy from - * bio_src->bi_io_vec to bio->bi_io_vec. - * - * We can't do that anymore, because: - * - * - The point of cloning the biovec is to produce a bio with a biovec - * the caller can modify: bi_idx and bi_bvec_done should be 0. - * - * - The original bio could've had more than BIO_MAX_VECS biovecs; if - * we tried to clone the whole thing bio_alloc_bioset() would fail. - * But the clone should succeed as long as the number of biovecs we - * actually need to allocate is fewer than BIO_MAX_VECS. - * - * - Lastly, bi_vcnt should not be looked at or relied upon by code - * that does not own the bio - reason being drivers don't use it for - * iterating over the biovec anymore, so expecting it to be kept up - * to date (i.e. for clones that share the parent biovec) is just - * asking for trouble and would force extra work. - */ - bio = bio_alloc_bioset(bio_src->bi_bdev, bio_segments(bio_src), - bio_src->bi_opf, GFP_NOIO, &bounce_bio_set); - if (bio_flagged(bio_src, BIO_REMAPPED)) - bio_set_flag(bio, BIO_REMAPPED); - bio->bi_ioprio = bio_src->bi_ioprio; - bio->bi_write_hint = bio_src->bi_write_hint; - bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector; - bio->bi_iter.bi_size = bio_src->bi_iter.bi_size; - - switch (bio_op(bio)) { - case REQ_OP_DISCARD: - case REQ_OP_SECURE_ERASE: - case REQ_OP_WRITE_ZEROES: - break; - default: - bio_for_each_segment(bv, bio_src, iter) - bio->bi_io_vec[bio->bi_vcnt++] = bv; - break; - } - - if (bio_crypt_clone(bio, bio_src, GFP_NOIO) < 0) - goto err_put; - - if (bio_integrity(bio_src) && - bio_integrity_clone(bio, bio_src, GFP_NOIO) < 0) - goto err_put; - - bio_clone_blkg_association(bio, bio_src); - - return bio; - -err_put: - bio_put(bio); - return NULL; -} - -struct bio *__blk_queue_bounce(struct bio *bio_orig, struct request_queue *q) -{ - struct bio *bio; - int rw = bio_data_dir(bio_orig); - struct bio_vec *to, from; - struct bvec_iter iter; - unsigned i = 0, bytes = 0; - bool bounce = false; - int sectors; - - bio_for_each_segment(from, bio_orig, iter) { - if (i++ < BIO_MAX_VECS) - bytes += from.bv_len; - if (PageHighMem(from.bv_page)) - bounce = true; - } - if (!bounce) - return bio_orig; - - /* - * Individual bvecs might not be logical block aligned. Round down - * the split size so that each bio is properly block size aligned, - * even if we do not use the full hardware limits. - */ - sectors = ALIGN_DOWN(bytes, queue_logical_block_size(q)) >> - SECTOR_SHIFT; - if (sectors < bio_sectors(bio_orig)) { - bio = bio_split(bio_orig, sectors, GFP_NOIO, &bounce_bio_split); - bio_chain(bio, bio_orig); - submit_bio_noacct(bio_orig); - bio_orig = bio; - } - bio = bounce_clone_bio(bio_orig); - - /* - * Bvec table can't be updated by bio_for_each_segment_all(), - * so retrieve bvec from the table directly. This way is safe - * because the 'bio' is single-page bvec. - */ - for (i = 0, to = bio->bi_io_vec; i < bio->bi_vcnt; to++, i++) { - struct page *bounce_page; - - if (!PageHighMem(to->bv_page)) - continue; - - bounce_page = mempool_alloc(&page_pool, GFP_NOIO); - inc_zone_page_state(bounce_page, NR_BOUNCE); - - if (rw == WRITE) { - flush_dcache_page(to->bv_page); - memcpy_from_bvec(page_address(bounce_page), to); - } - to->bv_page = bounce_page; - } - - trace_block_bio_bounce(bio_orig); - - bio->bi_flags |= (1 << BIO_BOUNCED); - - if (rw == READ) - bio->bi_end_io = bounce_end_io_read; - else - bio->bi_end_io = bounce_end_io_write; - - bio->bi_private = bio_orig; - return bio; -} diff --git a/block/bsg-lib.c b/block/bsg-lib.c index 93523d8f8195..9ceb5d0832f5 100644 --- a/block/bsg-lib.c +++ b/block/bsg-lib.c @@ -219,7 +219,7 @@ static int bsg_map_buffer(struct bsg_buffer *buf, struct request *req) if (!buf->sg_list) return -ENOMEM; sg_init_table(buf->sg_list, req->nr_phys_segments); - buf->sg_cnt = blk_rq_map_sg(req->q, req, buf->sg_list); + buf->sg_cnt = blk_rq_map_sg(req, buf->sg_list); buf->payload_len = blk_rq_bytes(req); return 0; } diff --git a/block/elevator.c b/block/elevator.c index cd2ce4921601..fe96c6f4753c 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -45,6 +45,19 @@ #include "blk-wbt.h" #include "blk-cgroup.h" +/* Holding context data for changing elevator */ +struct elv_change_ctx { + const char *name; + bool no_uevent; + + /* for unregistering old elevator */ + struct elevator_queue *old; + /* for registering new elevator */ + struct elevator_queue *new; + /* holds sched tags data */ + struct elevator_tags *et; +}; + static DEFINE_SPINLOCK(elv_list_lock); static LIST_HEAD(elv_list); @@ -121,7 +134,7 @@ static struct elevator_type *elevator_find_get(const char *name) static const struct kobj_type elv_ktype; struct elevator_queue *elevator_alloc(struct request_queue *q, - struct elevator_type *e) + struct elevator_type *e, struct elevator_tags *et) { struct elevator_queue *eq; @@ -134,10 +147,10 @@ struct elevator_queue *elevator_alloc(struct request_queue *q, kobject_init(&eq->kobj, &elv_ktype); mutex_init(&eq->sysfs_lock); hash_init(eq->hash); + eq->et = et; return eq; } -EXPORT_SYMBOL(elevator_alloc); static void elevator_release(struct kobject *kobj) { @@ -148,18 +161,17 @@ static void elevator_release(struct kobject *kobj) kfree(e); } -void elevator_exit(struct request_queue *q) +static void elevator_exit(struct request_queue *q) { struct elevator_queue *e = q->elevator; + lockdep_assert_held(&q->elevator_lock); + ioc_clear_queue(q); - blk_mq_sched_free_rqs(q); mutex_lock(&e->sysfs_lock); blk_mq_exit_sched(q, e); mutex_unlock(&e->sysfs_lock); - - kobject_put(&e->kobj); } static inline void __elv_rqhash_del(struct request *rq) @@ -412,14 +424,15 @@ elv_attr_show(struct kobject *kobj, struct attribute *attr, char *page) { const struct elv_fs_entry *entry = to_elv(attr); struct elevator_queue *e; - ssize_t error; + ssize_t error = -ENODEV; if (!entry->show) return -EIO; e = container_of(kobj, struct elevator_queue, kobj); mutex_lock(&e->sysfs_lock); - error = e->type ? entry->show(e, page) : -ENOENT; + if (!test_bit(ELEVATOR_FLAG_DYING, &e->flags)) + error = entry->show(e, page); mutex_unlock(&e->sysfs_lock); return error; } @@ -430,14 +443,15 @@ elv_attr_store(struct kobject *kobj, struct attribute *attr, { const struct elv_fs_entry *entry = to_elv(attr); struct elevator_queue *e; - ssize_t error; + ssize_t error = -ENODEV; if (!entry->store) return -EIO; e = container_of(kobj, struct elevator_queue, kobj); mutex_lock(&e->sysfs_lock); - error = e->type ? entry->store(e, page, length) : -ENOENT; + if (!test_bit(ELEVATOR_FLAG_DYING, &e->flags)) + error = entry->store(e, page, length); mutex_unlock(&e->sysfs_lock); return error; } @@ -452,13 +466,12 @@ static const struct kobj_type elv_ktype = { .release = elevator_release, }; -int elv_register_queue(struct request_queue *q, bool uevent) +static int elv_register_queue(struct request_queue *q, + struct elevator_queue *e, + bool uevent) { - struct elevator_queue *e = q->elevator; int error; - lockdep_assert_held(&q->sysfs_lock); - error = kobject_add(&e->kobj, &q->disk->queue_kobj, "iosched"); if (!error) { const struct elv_fs_entry *attr = e->type->elevator_attrs; @@ -472,20 +485,25 @@ int elv_register_queue(struct request_queue *q, bool uevent) if (uevent) kobject_uevent(&e->kobj, KOBJ_ADD); + /* + * Sched is initialized, it is ready to export it via + * debugfs + */ + blk_mq_sched_reg_debugfs(q); set_bit(ELEVATOR_FLAG_REGISTERED, &e->flags); } return error; } -void elv_unregister_queue(struct request_queue *q) +static void elv_unregister_queue(struct request_queue *q, + struct elevator_queue *e) { - struct elevator_queue *e = q->elevator; - - lockdep_assert_held(&q->sysfs_lock); - if (e && test_and_clear_bit(ELEVATOR_FLAG_REGISTERED, &e->flags)) { kobject_uevent(&e->kobj, KOBJ_REMOVE); kobject_del(&e->kobj); + + /* unexport via debugfs before exiting sched */ + blk_mq_sched_unreg_debugfs(q); } } @@ -548,201 +566,282 @@ void elv_unregister(struct elevator_type *e) EXPORT_SYMBOL_GPL(elv_unregister); /* - * For single queue devices, default to using mq-deadline. If we have multiple - * queues or mq-deadline is not available, default to "none". - */ -static struct elevator_type *elevator_get_default(struct request_queue *q) -{ - if (q->tag_set->flags & BLK_MQ_F_NO_SCHED_BY_DEFAULT) - return NULL; - - if (q->nr_hw_queues != 1 && - !blk_mq_is_shared_tags(q->tag_set->flags)) - return NULL; - - return elevator_find_get("mq-deadline"); -} - -/* - * Use the default elevator settings. If the chosen elevator initialization - * fails, fall back to the "none" elevator (no elevator). - */ -void elevator_init_mq(struct request_queue *q) -{ - struct elevator_type *e; - unsigned int memflags; - int err; - - WARN_ON_ONCE(blk_queue_registered(q)); - - if (unlikely(q->elevator)) - return; - - e = elevator_get_default(q); - if (!e) - return; - - /* - * We are called before adding disk, when there isn't any FS I/O, - * so freezing queue plus canceling dispatch work is enough to - * drain any dispatch activities originated from passthrough - * requests, then no need to quiesce queue which may add long boot - * latency, especially when lots of disks are involved. - * - * Disk isn't added yet, so verifying queue lock only manually. - */ - memflags = blk_mq_freeze_queue(q); - - blk_mq_cancel_work_sync(q); - - err = blk_mq_init_sched(q, e); - - blk_mq_unfreeze_queue(q, memflags); - - if (err) { - pr_warn("\"%s\" elevator initialization failed, " - "falling back to \"none\"\n", e->elevator_name); - } - - elevator_put(e); -} - -/* * Switch to new_e io scheduler. * * If switching fails, we are most likely running out of memory and not able * to restore the old io scheduler, so leaving the io scheduler being none. */ -int elevator_switch(struct request_queue *q, struct elevator_type *new_e) +static int elevator_switch(struct request_queue *q, struct elv_change_ctx *ctx) { - unsigned int memflags; - int ret; + struct elevator_type *new_e = NULL; + int ret = 0; - lockdep_assert_held(&q->sysfs_lock); + WARN_ON_ONCE(q->mq_freeze_depth == 0); + lockdep_assert_held(&q->elevator_lock); + + if (strncmp(ctx->name, "none", 4)) { + new_e = elevator_find_get(ctx->name); + if (!new_e) + return -EINVAL; + } - memflags = blk_mq_freeze_queue(q); blk_mq_quiesce_queue(q); if (q->elevator) { - elv_unregister_queue(q); + ctx->old = q->elevator; elevator_exit(q); } - ret = blk_mq_init_sched(q, new_e); - if (ret) - goto out_unfreeze; - - ret = elv_register_queue(q, true); - if (ret) { - elevator_exit(q); - goto out_unfreeze; + if (new_e) { + ret = blk_mq_init_sched(q, new_e, ctx->et); + if (ret) + goto out_unfreeze; + ctx->new = q->elevator; + } else { + blk_queue_flag_clear(QUEUE_FLAG_SQ_SCHED, q); + q->elevator = NULL; + q->nr_requests = q->tag_set->queue_depth; } - blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name); + blk_add_trace_msg(q, "elv switch: %s", ctx->name); out_unfreeze: blk_mq_unquiesce_queue(q); - blk_mq_unfreeze_queue(q, memflags); if (ret) { pr_warn("elv: switch to \"%s\" failed, falling back to \"none\"\n", new_e->elevator_name); } + if (new_e) + elevator_put(new_e); return ret; } -void elevator_disable(struct request_queue *q) +static void elv_exit_and_release(struct request_queue *q) { - unsigned int memflags; - - lockdep_assert_held(&q->sysfs_lock); + struct elevator_queue *e; + unsigned memflags; memflags = blk_mq_freeze_queue(q); - blk_mq_quiesce_queue(q); - - elv_unregister_queue(q); + mutex_lock(&q->elevator_lock); + e = q->elevator; elevator_exit(q); - blk_queue_flag_clear(QUEUE_FLAG_SQ_SCHED, q); - q->elevator = NULL; - q->nr_requests = q->tag_set->queue_depth; - blk_add_trace_msg(q, "elv switch: none"); - - blk_mq_unquiesce_queue(q); + mutex_unlock(&q->elevator_lock); blk_mq_unfreeze_queue(q, memflags); + if (e) { + blk_mq_free_sched_tags(e->et, q->tag_set); + kobject_put(&e->kobj); + } +} + +static int elevator_change_done(struct request_queue *q, + struct elv_change_ctx *ctx) +{ + int ret = 0; + + if (ctx->old) { + bool enable_wbt = test_bit(ELEVATOR_FLAG_ENABLE_WBT_ON_EXIT, + &ctx->old->flags); + + elv_unregister_queue(q, ctx->old); + blk_mq_free_sched_tags(ctx->old->et, q->tag_set); + kobject_put(&ctx->old->kobj); + if (enable_wbt) + wbt_enable_default(q->disk); + } + if (ctx->new) { + ret = elv_register_queue(q, ctx->new, !ctx->no_uevent); + if (ret) + elv_exit_and_release(q); + } + return ret; } /* * Switch this queue to the given IO scheduler. */ -static int elevator_change(struct request_queue *q, const char *elevator_name) +static int elevator_change(struct request_queue *q, struct elv_change_ctx *ctx) { - struct elevator_type *e; - int ret; + unsigned int memflags; + struct blk_mq_tag_set *set = q->tag_set; + int ret = 0; - /* Make sure queue is not in the middle of being removed */ - if (!blk_queue_registered(q)) - return -ENOENT; + lockdep_assert_held(&set->update_nr_hwq_lock); + + if (strncmp(ctx->name, "none", 4)) { + ctx->et = blk_mq_alloc_sched_tags(set, set->nr_hw_queues); + if (!ctx->et) + return -ENOMEM; + } + + memflags = blk_mq_freeze_queue(q); + /* + * May be called before adding disk, when there isn't any FS I/O, + * so freezing queue plus canceling dispatch work is enough to + * drain any dispatch activities originated from passthrough + * requests, then no need to quiesce queue which may add long boot + * latency, especially when lots of disks are involved. + * + * Disk isn't added yet, so verifying queue lock only manually. + */ + blk_mq_cancel_work_sync(q); + mutex_lock(&q->elevator_lock); + if (!(q->elevator && elevator_match(q->elevator->type, ctx->name))) + ret = elevator_switch(q, ctx); + mutex_unlock(&q->elevator_lock); + blk_mq_unfreeze_queue(q, memflags); + if (!ret) + ret = elevator_change_done(q, ctx); + /* + * Free sched tags if it's allocated but we couldn't switch elevator. + */ + if (ctx->et && !ctx->new) + blk_mq_free_sched_tags(ctx->et, set); + + return ret; +} - if (!strncmp(elevator_name, "none", 4)) { - if (q->elevator) - elevator_disable(q); - return 0; +/* + * The I/O scheduler depends on the number of hardware queues, this forces a + * reattachment when nr_hw_queues changes. + */ +void elv_update_nr_hw_queues(struct request_queue *q, struct elevator_type *e, + struct elevator_tags *t) +{ + struct blk_mq_tag_set *set = q->tag_set; + struct elv_change_ctx ctx = {}; + int ret = -ENODEV; + + WARN_ON_ONCE(q->mq_freeze_depth == 0); + + if (e && !blk_queue_dying(q) && blk_queue_registered(q)) { + ctx.name = e->elevator_name; + ctx.et = t; + + mutex_lock(&q->elevator_lock); + /* force to reattach elevator after nr_hw_queue is updated */ + ret = elevator_switch(q, &ctx); + mutex_unlock(&q->elevator_lock); } + blk_mq_unfreeze_queue_nomemrestore(q); + if (!ret) + WARN_ON_ONCE(elevator_change_done(q, &ctx)); + /* + * Free sched tags if it's allocated but we couldn't switch elevator. + */ + if (t && !ctx.new) + blk_mq_free_sched_tags(t, set); +} - if (q->elevator && elevator_match(q->elevator->type, elevator_name)) - return 0; +/* + * Use the default elevator settings. If the chosen elevator initialization + * fails, fall back to the "none" elevator (no elevator). + */ +void elevator_set_default(struct request_queue *q) +{ + struct elv_change_ctx ctx = { + .name = "mq-deadline", + .no_uevent = true, + }; + int err; + struct elevator_type *e; + + /* now we allow to switch elevator */ + blk_queue_flag_clear(QUEUE_FLAG_NO_ELV_SWITCH, q); + + if (q->tag_set->flags & BLK_MQ_F_NO_SCHED_BY_DEFAULT) + return; - e = elevator_find_get(elevator_name); + /* + * For single queue devices, default to using mq-deadline. If we + * have multiple queues or mq-deadline is not available, default + * to "none". + */ + e = elevator_find_get(ctx.name); if (!e) - return -EINVAL; - ret = elevator_switch(q, e); + return; + + if ((q->nr_hw_queues == 1 || + blk_mq_is_shared_tags(q->tag_set->flags))) { + err = elevator_change(q, &ctx); + if (err < 0) + pr_warn("\"%s\" elevator initialization, failed %d, falling back to \"none\"\n", + ctx.name, err); + } elevator_put(e); - return ret; } -void elv_iosched_load_module(struct gendisk *disk, const char *buf, - size_t count) +void elevator_set_none(struct request_queue *q) { - char elevator_name[ELV_NAME_MAX]; - struct elevator_type *found; - const char *name; + struct elv_change_ctx ctx = { + .name = "none", + }; + int err; - strscpy(elevator_name, buf, sizeof(elevator_name)); - name = strstrip(elevator_name); + err = elevator_change(q, &ctx); + if (err < 0) + pr_warn("%s: set none elevator failed %d\n", __func__, err); +} + +static void elv_iosched_load_module(const char *elevator_name) +{ + struct elevator_type *found; spin_lock(&elv_list_lock); - found = __elevator_find(name); + found = __elevator_find(elevator_name); spin_unlock(&elv_list_lock); if (!found) - request_module("%s-iosched", name); + request_module("%s-iosched", elevator_name); } ssize_t elv_iosched_store(struct gendisk *disk, const char *buf, size_t count) { char elevator_name[ELV_NAME_MAX]; + struct elv_change_ctx ctx = {}; int ret; + struct request_queue *q = disk->queue; + struct blk_mq_tag_set *set = q->tag_set; + + /* Make sure queue is not in the middle of being removed */ + if (!blk_queue_registered(q)) + return -ENOENT; + /* + * If the attribute needs to load a module, do it before freezing the + * queue to ensure that the module file can be read when the request + * queue is the one for the device storing the module file. + */ strscpy(elevator_name, buf, sizeof(elevator_name)); - ret = elevator_change(disk->queue, strstrip(elevator_name)); - if (!ret) - return count; + ctx.name = strstrip(elevator_name); + + elv_iosched_load_module(ctx.name); + + down_read(&set->update_nr_hwq_lock); + if (!blk_queue_no_elv_switch(q)) { + ret = elevator_change(q, &ctx); + if (!ret) + ret = count; + } else { + ret = -ENOENT; + } + up_read(&set->update_nr_hwq_lock); return ret; } ssize_t elv_iosched_show(struct gendisk *disk, char *name) { struct request_queue *q = disk->queue; - struct elevator_queue *eq = q->elevator; struct elevator_type *cur = NULL, *e; int len = 0; + mutex_lock(&q->elevator_lock); if (!q->elevator) { len += sprintf(name+len, "[none] "); } else { len += sprintf(name+len, "none "); - cur = eq->type; + cur = q->elevator->type; } spin_lock(&elv_list_lock); @@ -755,6 +854,8 @@ ssize_t elv_iosched_show(struct gendisk *disk, char *name) spin_unlock(&elv_list_lock); len += sprintf(name+len, "\n"); + mutex_unlock(&q->elevator_lock); + return len; } diff --git a/block/elevator.h b/block/elevator.h index e526662c5dbb..adc5c157e17e 100644 --- a/block/elevator.h +++ b/block/elevator.h @@ -23,8 +23,17 @@ enum elv_merge { struct blk_mq_alloc_data; struct blk_mq_hw_ctx; +struct elevator_tags { + /* num. of hardware queues for which tags are allocated */ + unsigned int nr_hw_queues; + /* depth used while allocating tags */ + unsigned int nr_requests; + /* shared tag is stored at index 0 */ + struct blk_mq_tags *tags[]; +}; + struct elevator_mq_ops { - int (*init_sched)(struct request_queue *, struct elevator_type *); + int (*init_sched)(struct request_queue *, struct elevator_queue *); void (*exit_sched)(struct elevator_queue *); int (*init_hctx)(struct blk_mq_hw_ctx *, unsigned int); void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int); @@ -113,6 +122,7 @@ struct request *elv_rqhash_find(struct request_queue *q, sector_t offset); struct elevator_queue { struct elevator_type *type; + struct elevator_tags *et; void *elevator_data; struct kobject kobj; struct mutex sysfs_lock; @@ -121,7 +131,8 @@ struct elevator_queue }; #define ELEVATOR_FLAG_REGISTERED 0 -#define ELEVATOR_FLAG_DISABLE_WBT 1 +#define ELEVATOR_FLAG_DYING 1 +#define ELEVATOR_FLAG_ENABLE_WBT_ON_EXIT 2 /* * block elevator interface @@ -148,13 +159,11 @@ extern void elv_unregister(struct elevator_type *); * io scheduler sysfs switching */ ssize_t elv_iosched_show(struct gendisk *disk, char *page); -void elv_iosched_load_module(struct gendisk *disk, const char *page, - size_t count); ssize_t elv_iosched_store(struct gendisk *disk, const char *page, size_t count); extern bool elv_bio_merge_ok(struct request *, struct bio *); -extern struct elevator_queue *elevator_alloc(struct request_queue *, - struct elevator_type *); +struct elevator_queue *elevator_alloc(struct request_queue *, + struct elevator_type *, struct elevator_tags *); /* * Helper functions. @@ -184,4 +193,7 @@ extern struct request *elv_rb_find(struct rb_root *, sector_t); #define rq_entry_fifo(ptr) list_entry((ptr), struct request, queuelist) #define rq_fifo_clear(rq) list_del_init(&(rq)->queuelist) +void blk_mq_sched_reg_debugfs(struct request_queue *q); +void blk_mq_sched_unreg_debugfs(struct request_queue *q); + #endif /* _ELEVATOR_H */ diff --git a/block/fops.c b/block/fops.c index be9f1dbea9ce..d62fbefb2e67 100644 --- a/block/fops.c +++ b/block/fops.c @@ -7,6 +7,7 @@ #include <linux/init.h> #include <linux/mm.h> #include <linux/blkdev.h> +#include <linux/blk-integrity.h> #include <linux/buffer_head.h> #include <linux/mpage.h> #include <linux/uio.h> @@ -54,7 +55,6 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb, struct bio bio; ssize_t ret; - WARN_ON_ONCE(iocb->ki_flags & IOCB_HAS_METADATA); if (nr_pages <= DIO_INLINE_BIO_VECS) vecs = inline_vecs; else { @@ -73,6 +73,7 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb, } bio.bi_iter.bi_sector = pos >> SECTOR_SHIFT; bio.bi_write_hint = file_inode(iocb->ki_filp)->i_write_hint; + bio.bi_write_stream = iocb->ki_write_stream; bio.bi_ioprio = iocb->ki_ioprio; if (iocb->ki_flags & IOCB_ATOMIC) bio.bi_opf |= REQ_ATOMIC; @@ -130,7 +131,7 @@ static void blkdev_bio_end_io(struct bio *bio) if (bio->bi_status && !dio->bio.bi_status) dio->bio.bi_status = bio->bi_status; - if (!is_sync && (dio->iocb->ki_flags & IOCB_HAS_METADATA)) + if (bio_integrity(bio)) bio_integrity_unmap_user(bio); if (atomic_dec_and_test(&dio->ref)) { @@ -206,6 +207,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, for (;;) { bio->bi_iter.bi_sector = pos >> SECTOR_SHIFT; bio->bi_write_hint = file_inode(iocb->ki_filp)->i_write_hint; + bio->bi_write_stream = iocb->ki_write_stream; bio->bi_private = dio; bio->bi_end_io = blkdev_bio_end_io; bio->bi_ioprio = iocb->ki_ioprio; @@ -231,7 +233,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, } bio->bi_opf |= REQ_NOWAIT; } - if (!is_sync && (iocb->ki_flags & IOCB_HAS_METADATA)) { + if (iocb->ki_flags & IOCB_HAS_METADATA) { ret = bio_integrity_map_iter(bio, iocb->private); if (unlikely(ret)) goto fail; @@ -299,7 +301,7 @@ static void blkdev_bio_end_io_async(struct bio *bio) ret = blk_status_to_errno(bio->bi_status); } - if (iocb->ki_flags & IOCB_HAS_METADATA) + if (bio_integrity(bio)) bio_integrity_unmap_user(bio); iocb->ki_complete(iocb, ret); @@ -333,6 +335,7 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb, dio->iocb = iocb; bio->bi_iter.bi_sector = pos >> SECTOR_SHIFT; bio->bi_write_hint = file_inode(iocb->ki_filp)->i_write_hint; + bio->bi_write_stream = iocb->ki_write_stream; bio->bi_end_io = blkdev_bio_end_io_async; bio->bi_ioprio = iocb->ki_ioprio; @@ -398,8 +401,29 @@ static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter) if (blkdev_dio_invalid(bdev, iocb, iter)) return -EINVAL; + if (iov_iter_rw(iter) == WRITE) { + u16 max_write_streams = bdev_max_write_streams(bdev); + + if (iocb->ki_write_stream) { + if (iocb->ki_write_stream > max_write_streams) + return -EINVAL; + } else if (max_write_streams) { + enum rw_hint write_hint = + file_inode(iocb->ki_filp)->i_write_hint; + + /* + * Just use the write hint as write stream for block + * device writes. This assumes no file system is + * mounted that would use the streams differently. + */ + if (write_hint <= max_write_streams) + iocb->ki_write_stream = write_hint; + } + } + nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS + 1); - if (likely(nr_pages <= BIO_MAX_VECS)) { + if (likely(nr_pages <= BIO_MAX_VECS && + !(iocb->ki_flags & IOCB_HAS_METADATA))) { if (is_sync_kiocb(iocb)) return __blkdev_direct_IO_simple(iocb, iter, bdev, nr_pages); @@ -451,12 +475,13 @@ static int blkdev_get_block(struct inode *inode, sector_t iblock, static int blkdev_writepages(struct address_space *mapping, struct writeback_control *wbc) { + struct folio *folio = NULL; struct blk_plug plug; int err; blk_start_plug(&plug); - err = write_cache_pages(mapping, wbc, block_write_full_folio, - blkdev_get_block); + while ((folio = writeback_iter(mapping, wbc, folio, &err))) + err = block_write_full_folio(folio, wbc, blkdev_get_block); blk_finish_plug(&plug); return err; @@ -642,12 +667,14 @@ static int blkdev_open(struct inode *inode, struct file *filp) if (ret) return ret; - bdev = blkdev_get_no_open(inode->i_rdev); + bdev = blkdev_get_no_open(inode->i_rdev, true); if (!bdev) return -ENXIO; if (bdev_can_atomic_write(bdev)) filp->f_mode |= FMODE_CAN_ATOMIC_WRITE; + if (blk_get_integrity(bdev->bd_disk)) + filp->f_mode |= FMODE_HAS_METADATA; ret = bdev_open(bdev, mode, filp->private_data, NULL, filp); if (ret) @@ -746,7 +773,14 @@ static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from) ret = direct_write_fallback(iocb, from, ret, blkdev_buffered_write(iocb, from)); } else { + /* + * Take i_rwsem and invalidate_lock to avoid racing with + * set_blocksize changing i_blkbits/folio order and punching + * out the pagecache. + */ + inode_lock_shared(bd_inode); ret = blkdev_buffered_write(iocb, from); + inode_unlock_shared(bd_inode); } if (ret > 0) @@ -757,6 +791,7 @@ static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from) static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to) { + struct inode *bd_inode = bdev_file_inode(iocb->ki_filp); struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host); loff_t size = bdev_nr_bytes(bdev); loff_t pos = iocb->ki_pos; @@ -793,7 +828,13 @@ static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to) goto reexpand; } + /* + * Take i_rwsem and invalidate_lock to avoid racing with set_blocksize + * changing i_blkbits/folio order and punching out the pagecache. + */ + inode_lock_shared(bd_inode); ret = filemap_read(iocb, to, ret); + inode_unlock_shared(bd_inode); reexpand: if (unlikely(shorted)) @@ -836,6 +877,7 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start, if ((start | len) & (bdev_logical_block_size(bdev) - 1)) return -EINVAL; + inode_lock(inode); filemap_invalidate_lock(inode->i_mapping); /* @@ -868,6 +910,7 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start, fail: filemap_invalidate_unlock(inode->i_mapping); + inode_unlock(inode); return error; } diff --git a/block/genhd.c b/block/genhd.c index e9375e20d866..9bbc38d12792 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -125,37 +125,50 @@ static void part_stat_read_all(struct block_device *part, } } -unsigned int part_in_flight(struct block_device *part) +static void bdev_count_inflight_rw(struct block_device *part, + unsigned int inflight[2], bool mq_driver) { - unsigned int inflight = 0; + int write = 0; + int read = 0; int cpu; + if (mq_driver) { + blk_mq_in_driver_rw(part, inflight); + return; + } + for_each_possible_cpu(cpu) { - inflight += part_stat_local_read_cpu(part, in_flight[0], cpu) + - part_stat_local_read_cpu(part, in_flight[1], cpu); + read += part_stat_local_read_cpu(part, in_flight[READ], cpu); + write += part_stat_local_read_cpu(part, in_flight[WRITE], cpu); } - if ((int)inflight < 0) - inflight = 0; - return inflight; + /* + * While iterating all CPUs, some IOs may be issued from a CPU already + * traversed and complete on a CPU that has not yet been traversed, + * causing the inflight number to be negative. + */ + inflight[READ] = read > 0 ? read : 0; + inflight[WRITE] = write > 0 ? write : 0; } -static void part_in_flight_rw(struct block_device *part, - unsigned int inflight[2]) +/** + * bdev_count_inflight - get the number of inflight IOs for a block device. + * + * @part: the block device. + * + * Inflight here means started IO accounting, from bdev_start_io_acct() for + * bio-based block device, and from blk_account_io_start() for rq-based block + * device. + */ +unsigned int bdev_count_inflight(struct block_device *part) { - int cpu; + unsigned int inflight[2] = {0}; - inflight[0] = 0; - inflight[1] = 0; - for_each_possible_cpu(cpu) { - inflight[0] += part_stat_local_read_cpu(part, in_flight[0], cpu); - inflight[1] += part_stat_local_read_cpu(part, in_flight[1], cpu); - } - if ((int)inflight[0] < 0) - inflight[0] = 0; - if ((int)inflight[1] < 0) - inflight[1] = 0; + bdev_count_inflight_rw(part, inflight, false); + + return inflight[READ] + inflight[WRITE]; } +EXPORT_SYMBOL_GPL(bdev_count_inflight); /* * Can be deleted altogether. Later. @@ -389,19 +402,35 @@ int disk_scan_partitions(struct gendisk *disk, blk_mode_t mode) return ret; } -/** - * add_disk_fwnode - add disk information to kernel list with fwnode - * @parent: parent device for the disk - * @disk: per-device partitioning information - * @groups: Additional per-device sysfs groups - * @fwnode: attached disk fwnode - * - * This function registers the partitioning information in @disk - * with the kernel. Also attach a fwnode to the disk device. - */ -int __must_check add_disk_fwnode(struct device *parent, struct gendisk *disk, - const struct attribute_group **groups, - struct fwnode_handle *fwnode) +static void add_disk_final(struct gendisk *disk) +{ + struct device *ddev = disk_to_dev(disk); + + if (!(disk->flags & GENHD_FL_HIDDEN)) { + /* Make sure the first partition scan will be proceed */ + if (get_capacity(disk) && disk_has_partscan(disk)) + set_bit(GD_NEED_PART_SCAN, &disk->state); + + bdev_add(disk->part0, ddev->devt); + if (get_capacity(disk)) + disk_scan_partitions(disk, BLK_OPEN_READ); + + /* + * Announce the disk and partitions after all partitions are + * created. (for hidden disks uevents remain suppressed forever) + */ + dev_set_uevent_suppress(ddev, 0); + disk_uevent(disk, KOBJ_ADD); + } + + blk_apply_bdi_limits(disk->bdi, &disk->queue->limits); + disk_add_events(disk); + set_bit(GD_ADDED, &disk->state); +} + +static int __add_disk(struct device *parent, struct gendisk *disk, + const struct attribute_group **groups, + struct fwnode_handle *fwnode) { struct device *ddev = disk_to_dev(disk); @@ -416,12 +445,6 @@ int __must_check add_disk_fwnode(struct device *parent, struct gendisk *disk, */ if (disk->fops->submit_bio || disk->fops->poll_bio) return -EINVAL; - - /* - * Initialize the I/O scheduler code and pick a default one if - * needed. - */ - elevator_init_mq(disk->queue); } else { if (!disk->fops->submit_bio) return -EINVAL; @@ -438,7 +461,7 @@ int __must_check add_disk_fwnode(struct device *parent, struct gendisk *disk, ret = -EINVAL; if (disk->major) { if (WARN_ON(!disk->minors)) - goto out_exit_elevator; + goto out; if (disk->minors > DISK_MAX_PARTS) { pr_err("block: can't allocate more than %d partitions\n", @@ -448,14 +471,14 @@ int __must_check add_disk_fwnode(struct device *parent, struct gendisk *disk, if (disk->first_minor > MINORMASK || disk->minors > MINORMASK + 1 || disk->first_minor + disk->minors > MINORMASK + 1) - goto out_exit_elevator; + goto out; } else { if (WARN_ON(disk->minors)) - goto out_exit_elevator; + goto out; ret = blk_alloc_ext_minor(); if (ret < 0) - goto out_exit_elevator; + goto out; disk->major = BLOCK_EXT_MAJOR; disk->first_minor = ret; } @@ -516,21 +539,6 @@ int __must_check add_disk_fwnode(struct device *parent, struct gendisk *disk, &disk->bdi->dev->kobj, "bdi"); if (ret) goto out_unregister_bdi; - - /* Make sure the first partition scan will be proceed */ - if (get_capacity(disk) && disk_has_partscan(disk)) - set_bit(GD_NEED_PART_SCAN, &disk->state); - - bdev_add(disk->part0, ddev->devt); - if (get_capacity(disk)) - disk_scan_partitions(disk, BLK_OPEN_READ); - - /* - * Announce the disk and partitions after all partitions are - * created. (for hidden disks uevents remain suppressed forever) - */ - dev_set_uevent_suppress(ddev, 0); - disk_uevent(disk, KOBJ_ADD); } else { /* * Even if the block_device for a hidden gendisk is not @@ -539,10 +547,6 @@ int __must_check add_disk_fwnode(struct device *parent, struct gendisk *disk, */ disk->part0->bd_dev = MKDEV(disk->major, disk->first_minor); } - - blk_apply_bdi_limits(disk->bdi, &disk->queue->limits); - disk_add_events(disk); - set_bit(GD_ADDED, &disk->state); return 0; out_unregister_bdi: @@ -564,9 +568,46 @@ out_device_del: out_free_ext_minor: if (disk->major == BLOCK_EXT_MAJOR) blk_free_ext_minor(disk->first_minor); -out_exit_elevator: - if (disk->queue->elevator) - elevator_exit(disk->queue); +out: + return ret; +} + +/** + * add_disk_fwnode - add disk information to kernel list with fwnode + * @parent: parent device for the disk + * @disk: per-device partitioning information + * @groups: Additional per-device sysfs groups + * @fwnode: attached disk fwnode + * + * This function registers the partitioning information in @disk + * with the kernel. Also attach a fwnode to the disk device. + */ +int __must_check add_disk_fwnode(struct device *parent, struct gendisk *disk, + const struct attribute_group **groups, + struct fwnode_handle *fwnode) +{ + struct blk_mq_tag_set *set; + unsigned int memflags; + int ret; + + if (queue_is_mq(disk->queue)) { + set = disk->queue->tag_set; + memflags = memalloc_noio_save(); + down_read(&set->update_nr_hwq_lock); + ret = __add_disk(parent, disk, groups, fwnode); + up_read(&set->update_nr_hwq_lock); + memalloc_noio_restore(memflags); + } else { + ret = __add_disk(parent, disk, groups, fwnode); + } + + /* + * add_disk_final() needn't to read `nr_hw_queues`, so move it out + * of read lock `set->update_nr_hwq_lock` for avoiding unnecessary + * lock dependency on `disk->open_mutex` from scanning partition. + */ + if (!ret) + add_disk_final(disk); return ret; } EXPORT_SYMBOL_GPL(add_disk_fwnode); @@ -649,26 +690,7 @@ void blk_mark_disk_dead(struct gendisk *disk) } EXPORT_SYMBOL_GPL(blk_mark_disk_dead); -/** - * del_gendisk - remove the gendisk - * @disk: the struct gendisk to remove - * - * Removes the gendisk and all its associated resources. This deletes the - * partitions associated with the gendisk, and unregisters the associated - * request_queue. - * - * This is the counter to the respective __device_add_disk() call. - * - * The final removal of the struct gendisk happens when its refcount reaches 0 - * with put_disk(), which should be called after del_gendisk(), if - * __device_add_disk() was used. - * - * Drivers exist which depend on the release of the gendisk to be synchronous, - * it should not be deferred. - * - * Context: can sleep - */ -void del_gendisk(struct gendisk *disk) +static void __del_gendisk(struct gendisk *disk) { struct request_queue *q = disk->queue; struct block_device *part; @@ -740,14 +762,7 @@ void del_gendisk(struct gendisk *disk) if (queue_is_mq(q)) blk_mq_cancel_work_sync(q); - blk_mq_quiesce_queue(q); - if (q->elevator) { - mutex_lock(&q->sysfs_lock); - elevator_exit(q); - mutex_unlock(&q->sysfs_lock); - } rq_qos_exit(q); - blk_mq_unquiesce_queue(q); /* * If the disk does not own the queue, allow using passthrough requests @@ -761,6 +776,55 @@ void del_gendisk(struct gendisk *disk) if (start_drain) blk_unfreeze_release_lock(q); } + +static void disable_elv_switch(struct request_queue *q) +{ + struct blk_mq_tag_set *set = q->tag_set; + WARN_ON_ONCE(!queue_is_mq(q)); + + down_write(&set->update_nr_hwq_lock); + blk_queue_flag_set(QUEUE_FLAG_NO_ELV_SWITCH, q); + up_write(&set->update_nr_hwq_lock); +} + +/** + * del_gendisk - remove the gendisk + * @disk: the struct gendisk to remove + * + * Removes the gendisk and all its associated resources. This deletes the + * partitions associated with the gendisk, and unregisters the associated + * request_queue. + * + * This is the counter to the respective __device_add_disk() call. + * + * The final removal of the struct gendisk happens when its refcount reaches 0 + * with put_disk(), which should be called after del_gendisk(), if + * __device_add_disk() was used. + * + * Drivers exist which depend on the release of the gendisk to be synchronous, + * it should not be deferred. + * + * Context: can sleep + */ +void del_gendisk(struct gendisk *disk) +{ + struct blk_mq_tag_set *set; + unsigned int memflags; + + if (!queue_is_mq(disk->queue)) { + __del_gendisk(disk); + } else { + set = disk->queue->tag_set; + + disable_elv_switch(disk->queue); + + memflags = memalloc_noio_save(); + down_read(&set->update_nr_hwq_lock); + __del_gendisk(disk); + up_read(&set->update_nr_hwq_lock); + memalloc_noio_restore(memflags); + } +} EXPORT_SYMBOL(del_gendisk); /** @@ -1002,7 +1066,7 @@ ssize_t part_stat_show(struct device *dev, struct disk_stats stat; unsigned int inflight; - inflight = part_in_flight(bdev); + inflight = bdev_count_inflight(bdev); if (inflight) { part_stat_lock(); update_io_ticks(bdev, jiffies, true); @@ -1039,19 +1103,21 @@ ssize_t part_stat_show(struct device *dev, (unsigned int)div_u64(stat.nsecs[STAT_FLUSH], NSEC_PER_MSEC)); } +/* + * Show the number of IOs issued to driver. + * For bio-based device, started from bdev_start_io_acct(); + * For rq-based device, started from blk_mq_start_request(); + */ ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr, char *buf) { struct block_device *bdev = dev_to_bdev(dev); struct request_queue *q = bdev_get_queue(bdev); - unsigned int inflight[2]; + unsigned int inflight[2] = {0}; - if (queue_is_mq(q)) - blk_mq_in_flight_rw(q, bdev, inflight); - else - part_in_flight_rw(bdev, inflight); + bdev_count_inflight_rw(bdev, inflight, queue_is_mq(q)); - return sysfs_emit(buf, "%8u %8u\n", inflight[0], inflight[1]); + return sysfs_emit(buf, "%8u %8u\n", inflight[READ], inflight[WRITE]); } static ssize_t disk_capability_show(struct device *dev, @@ -1237,6 +1303,7 @@ static void disk_release(struct device *dev) disk_free_zone_resources(disk); xa_destroy(&disk->part_tbl); + kobject_put(&disk->queue_kobj); disk->queue->disk = NULL; blk_put_queue(disk->queue); @@ -1304,7 +1371,7 @@ static int diskstats_show(struct seq_file *seqf, void *v) if (bdev_is_partition(hd) && !bdev_nr_sectors(hd)) continue; - inflight = part_in_flight(hd); + inflight = bdev_count_inflight(hd); if (inflight) { part_stat_lock(); update_io_ticks(hd, jiffies, true); @@ -1419,6 +1486,8 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, #ifdef CONFIG_BLOCK_HOLDER_DEPRECATED INIT_LIST_HEAD(&disk->slave_bdevs); #endif + mutex_init(&disk->rqos_state_mutex); + kobject_init(&disk->queue_kobj, &blk_queue_ktype); return disk; out_erase_part0: diff --git a/block/ioctl.c b/block/ioctl.c index 6554b728bae6..e472cc1030c6 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -15,6 +15,7 @@ #include <linux/io_uring/cmd.h> #include <uapi/linux/blkdev.h> #include "blk.h" +#include "blk-crypto-internal.h" static int blkpg_do_ioctl(struct block_device *bdev, struct blkpg_partition __user *upart, int op) @@ -141,6 +142,7 @@ static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode, if (err) return err; + inode_lock(bdev->bd_mapping->host); filemap_invalidate_lock(bdev->bd_mapping); err = truncate_bdev_range(bdev, mode, start, start + len - 1); if (err) @@ -173,6 +175,7 @@ out_unplug: blk_finish_plug(&plug); fail: filemap_invalidate_unlock(bdev->bd_mapping); + inode_unlock(bdev->bd_mapping->host); return err; } @@ -198,12 +201,14 @@ static int blk_ioctl_secure_erase(struct block_device *bdev, blk_mode_t mode, end > bdev_nr_bytes(bdev)) return -EINVAL; + inode_lock(bdev->bd_mapping->host); filemap_invalidate_lock(bdev->bd_mapping); err = truncate_bdev_range(bdev, mode, start, end - 1); if (!err) err = blkdev_issue_secure_erase(bdev, start >> 9, len >> 9, GFP_KERNEL); filemap_invalidate_unlock(bdev->bd_mapping); + inode_unlock(bdev->bd_mapping->host); return err; } @@ -235,6 +240,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, blk_mode_t mode, return -EINVAL; /* Invalidate the page cache, including dirty pages */ + inode_lock(bdev->bd_mapping->host); filemap_invalidate_lock(bdev->bd_mapping); err = truncate_bdev_range(bdev, mode, start, end); if (err) @@ -245,6 +251,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, blk_mode_t mode, fail: filemap_invalidate_unlock(bdev->bd_mapping); + inode_unlock(bdev->bd_mapping->host); return err; } @@ -620,6 +627,10 @@ static int blkdev_common_ioctl(struct block_device *bdev, blk_mode_t mode, case BLKTRACESTOP: case BLKTRACETEARDOWN: return blk_trace_ioctl(bdev, cmd, argp); + case BLKCRYPTOIMPORTKEY: + case BLKCRYPTOGENERATEKEY: + case BLKCRYPTOPREPAREKEY: + return blk_crypto_ioctl(bdev, cmd, argp); case IOC_PR_REGISTER: return blkdev_pr_register(bdev, mode, argp); case IOC_PR_RESERVE: diff --git a/block/ioprio.c b/block/ioprio.c index 73301a261429..f0ee2798539c 100644 --- a/block/ioprio.c +++ b/block/ioprio.c @@ -46,12 +46,8 @@ int ioprio_check_cap(int ioprio) */ if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_NICE)) return -EPERM; - fallthrough; - /* rt has prio field too */ - case IOPRIO_CLASS_BE: - if (level >= IOPRIO_NR_LEVELS) - return -EINVAL; break; + case IOPRIO_CLASS_BE: case IOPRIO_CLASS_IDLE: break; case IOPRIO_CLASS_NONE: diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c index dc31f2dfa414..70cbc7b2deb4 100644 --- a/block/kyber-iosched.c +++ b/block/kyber-iosched.c @@ -157,10 +157,7 @@ struct kyber_queue_data { */ struct sbitmap_queue domain_tokens[KYBER_NUM_DOMAINS]; - /* - * Async request percentage, converted to per-word depth for - * sbitmap_get_shallow(). - */ + /* Number of allowed async requests. */ unsigned int async_depth; struct kyber_cpu_latency __percpu *cpu_latency; @@ -276,7 +273,7 @@ static void kyber_resize_domain(struct kyber_queue_data *kqd, static void kyber_timer_fn(struct timer_list *t) { - struct kyber_queue_data *kqd = from_timer(kqd, t, timer); + struct kyber_queue_data *kqd = timer_container_of(kqd, t, timer); unsigned int sched_domain; int cpu; bool bad = false; @@ -402,20 +399,13 @@ err: return ERR_PTR(ret); } -static int kyber_init_sched(struct request_queue *q, struct elevator_type *e) +static int kyber_init_sched(struct request_queue *q, struct elevator_queue *eq) { struct kyber_queue_data *kqd; - struct elevator_queue *eq; - - eq = elevator_alloc(q, e); - if (!eq) - return -ENOMEM; kqd = kyber_queue_data_alloc(q); - if (IS_ERR(kqd)) { - kobject_put(&eq->kobj); + if (IS_ERR(kqd)) return PTR_ERR(kqd); - } blk_stat_enable_accounting(q); @@ -454,10 +444,8 @@ static void kyber_depth_updated(struct blk_mq_hw_ctx *hctx) { struct kyber_queue_data *kqd = hctx->queue->elevator->elevator_data; struct blk_mq_tags *tags = hctx->sched_tags; - unsigned int shift = tags->bitmap_tags.sb.shift; - - kqd->async_depth = (1U << shift) * KYBER_ASYNC_PERCENT / 100U; + kqd->async_depth = hctx->queue->nr_requests * KYBER_ASYNC_PERCENT / 100U; sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, kqd->async_depth); } @@ -568,7 +556,7 @@ static bool kyber_bio_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs) { struct blk_mq_ctx *ctx = blk_mq_get_ctx(q); - struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, bio->bi_opf, ctx); + struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(bio->bi_opf, ctx); struct kyber_hctx_data *khd = hctx->sched_data; struct kyber_ctx_queue *kcq = &khd->kcqs[ctx->index_hw[hctx->type]]; unsigned int sched_domain = kyber_sched_domain(bio->bi_opf); diff --git a/block/mq-deadline.c b/block/mq-deadline.c index 754f6b7415cd..b9b7cdf1d3c9 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -488,20 +488,6 @@ unlock: } /* - * 'depth' is a number in the range 1..INT_MAX representing a number of - * requests. Scale it with a factor (1 << bt->sb.shift) / q->nr_requests since - * 1..(1 << bt->sb.shift) is the range expected by sbitmap_get_shallow(). - * Values larger than q->nr_requests have the same effect as q->nr_requests. - */ -static int dd_to_word_depth(struct blk_mq_hw_ctx *hctx, unsigned int qdepth) -{ - struct sbitmap_queue *bt = &hctx->sched_tags->bitmap_tags; - const unsigned int nrr = hctx->queue->nr_requests; - - return ((qdepth << bt->sb.shift) + nrr - 1) / nrr; -} - -/* * Called by __blk_mq_alloc_request(). The shallow_depth value set by this * function is used by __blk_mq_get_tag(). */ @@ -517,7 +503,7 @@ static void dd_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data) * Throttle asynchronous requests and writes such that these requests * do not block the allocation of synchronous requests. */ - data->shallow_depth = dd_to_word_depth(data->hctx, dd->async_depth); + data->shallow_depth = dd->async_depth; } /* Called by blk_mq_update_nr_requests(). */ @@ -568,20 +554,14 @@ static void dd_exit_sched(struct elevator_queue *e) /* * initialize elevator private data (deadline_data). */ -static int dd_init_sched(struct request_queue *q, struct elevator_type *e) +static int dd_init_sched(struct request_queue *q, struct elevator_queue *eq) { struct deadline_data *dd; - struct elevator_queue *eq; enum dd_prio prio; - int ret = -ENOMEM; - - eq = elevator_alloc(q, e); - if (!eq) - return ret; dd = kzalloc_node(sizeof(*dd), GFP_KERNEL, q->node); if (!dd) - goto put_eq; + return -ENOMEM; eq->elevator_data = dd; @@ -608,10 +588,6 @@ static int dd_init_sched(struct request_queue *q, struct elevator_type *e) q->elevator = eq; return 0; - -put_eq: - kobject_put(&eq->kobj); - return ret; } /* @@ -715,7 +691,7 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, } /* - * Called from blk_mq_insert_request() or blk_mq_dispatch_plug_list(). + * Called from blk_mq_insert_request() or blk_mq_dispatch_list(). */ static void dd_insert_requests(struct blk_mq_hw_ctx *hctx, struct list_head *list, diff --git a/block/partitions/sgi.c b/block/partitions/sgi.c index 9cc6b8c1eea4..b5ecddd5181a 100644 --- a/block/partitions/sgi.c +++ b/block/partitions/sgi.c @@ -50,8 +50,6 @@ int sgi_partition(struct parsed_partitions *state) p = &label->partitions[0]; magic = label->magic_mushroom; if(be32_to_cpu(magic) != SGI_LABEL_MAGIC) { - /*printk("Dev %s SGI disklabel: bad magic %08x\n", - state->disk->disk_name, be32_to_cpu(magic));*/ put_dev_sector(sect); return 0; } diff --git a/block/partitions/sun.c b/block/partitions/sun.c index ddf9e6def4b2..2419af76120f 100644 --- a/block/partitions/sun.c +++ b/block/partitions/sun.c @@ -74,8 +74,6 @@ int sun_partition(struct parsed_partitions *state) p = label->partitions; if (be16_to_cpu(label->magic) != SUN_LABEL_MAGIC) { -/* printk(KERN_INFO "Dev %s Sun disklabel: bad magic %04x\n", - state->disk->disk_name, be16_to_cpu(label->magic)); */ put_dev_sector(sect); return 0; } diff --git a/block/t10-pi.c b/block/t10-pi.c index 2d05421f0fa5..851db518ee5e 100644 --- a/block/t10-pi.c +++ b/block/t10-pi.c @@ -210,7 +210,7 @@ static void t10_pi_type1_complete(struct request *rq, unsigned int nr_bytes) static __be64 ext_pi_crc64(u64 crc, void *data, unsigned int len) { - return cpu_to_be64(crc64_rocksoft_update(crc, data, len)); + return cpu_to_be64(crc64_nvme(crc, data, len)); } static void ext_pi_crc64_generate(struct blk_integrity_iter *iter, @@ -404,7 +404,7 @@ void blk_integrity_generate(struct bio *bio) } } -void blk_integrity_verify(struct bio *bio) +void blk_integrity_verify_iter(struct bio *bio, struct bvec_iter *saved_iter) { struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk); struct bio_integrity_payload *bip = bio_integrity(bio); @@ -418,9 +418,9 @@ void blk_integrity_verify(struct bio *bio) */ iter.disk_name = bio->bi_bdev->bd_disk->disk_name; iter.interval = 1 << bi->interval_exp; - iter.seed = bip->bio_iter.bi_sector; + iter.seed = saved_iter->bi_sector; iter.prot_buf = bvec_virt(bip->bip_vec); - __bio_for_each_segment(bv, bio, bviter, bip->bio_iter) { + __bio_for_each_segment(bv, bio, bviter, *saved_iter) { void *kaddr = bvec_kmap_local(&bv); blk_status_t ret = BLK_STS_OK; |