diff --git a/.mailmap b/.mailmap index 81ac1e17ac3c..29a5fedee49c 100644 --- a/.mailmap +++ b/.mailmap @@ -690,6 +690,7 @@ Vivien Didelot Vlad Dogaru Vladimir Davydov Vladimir Davydov +Weiwen Hu WeiXiong Liao Wen Gong Wesley Cheng diff --git a/Documentation/ABI/stable/sysfs-block b/Documentation/ABI/stable/sysfs-block index 831f19a32e08..cea8856f798d 100644 --- a/Documentation/ABI/stable/sysfs-block +++ b/Documentation/ABI/stable/sysfs-block @@ -21,6 +21,59 @@ Description: device is offset from the internal allocation unit's natural alignment. +What: /sys/block//atomic_write_max_bytes +Date: February 2024 +Contact: Himanshu Madhani +Description: + [RO] This parameter specifies the maximum atomic write + size reported by the device. This parameter is relevant + for merging of writes, where a merged atomic write + operation must not exceed this number of bytes. + This parameter may be greater than the value in + atomic_write_unit_max_bytes as + atomic_write_unit_max_bytes will be rounded down to a + power-of-two and atomic_write_unit_max_bytes may also be + limited by some other queue limits, such as max_segments. + This parameter - along with atomic_write_unit_min_bytes + and atomic_write_unit_max_bytes - will not be larger than + max_hw_sectors_kb, but may be larger than max_sectors_kb. + + +What: /sys/block//atomic_write_unit_min_bytes +Date: February 2024 +Contact: Himanshu Madhani +Description: + [RO] This parameter specifies the smallest block which can + be written atomically with an atomic write operation. All + atomic write operations must begin at a + atomic_write_unit_min boundary and must be multiples of + atomic_write_unit_min. This value must be a power-of-two. + + +What: /sys/block//atomic_write_unit_max_bytes +Date: February 2024 +Contact: Himanshu Madhani +Description: + [RO] This parameter defines the largest block which can be + written atomically with an atomic write operation. This + value must be a multiple of atomic_write_unit_min and must + be a power-of-two. This value will not be larger than + atomic_write_max_bytes. + + +What: /sys/block//atomic_write_boundary_bytes +Date: February 2024 +Contact: Himanshu Madhani +Description: + [RO] A device may need to internally split an atomic write I/O + which straddles a given logical block address boundary. This + parameter specifies the size in bytes of the atomic boundary if + one is reported by the device. This value must be a + power-of-two and at least the size as in + atomic_write_unit_max_bytes. + Any attempt to merge atomic write I/Os must not result in a + merged I/O which crosses this boundary (if any). + What: /sys/block//diskseq Date: February 2021 diff --git a/Documentation/block/data-integrity.rst b/Documentation/block/data-integrity.rst index 6a760c0eb192..99905e880a0e 100644 --- a/Documentation/block/data-integrity.rst +++ b/Documentation/block/data-integrity.rst @@ -153,18 +153,11 @@ bio_free() will automatically free the bip. 4.2 Block Device ---------------- -Because the format of the protection data is tied to the physical -disk, each block device has been extended with a block integrity -profile (struct blk_integrity). This optional profile is registered -with the block layer using blk_integrity_register(). - -The profile contains callback functions for generating and verifying -the protection data, as well as getting and setting application tags. -The profile also contains a few constants to aid in completing, -merging and splitting the integrity metadata. +Block devices can set up the integrity information in the integrity +sub-struture of the queue_limits structure. Layered block devices will need to pick a profile that's appropriate -for all subdevices. blk_integrity_compare() can help with that. DM +for all subdevices. queue_limits_stack_integrity() can help with that. DM and MD linear, RAID0 and RAID1 are currently supported. RAID4/5/6 will require extra work due to the application tag. @@ -250,42 +243,6 @@ will require extra work due to the application tag. integrity upon completion. -5.4 Registering A Block Device As Capable Of Exchanging Integrity Metadata --------------------------------------------------------------------------- - - To enable integrity exchange on a block device the gendisk must be - registered as capable: - - `int blk_integrity_register(gendisk, blk_integrity);` - - The blk_integrity struct is a template and should contain the - following:: - - static struct blk_integrity my_profile = { - .name = "STANDARDSBODY-TYPE-VARIANT-CSUM", - .generate_fn = my_generate_fn, - .verify_fn = my_verify_fn, - .tuple_size = sizeof(struct my_tuple_size), - .tag_size = , - }; - - 'name' is a text string which will be visible in sysfs. This is - part of the userland API so chose it carefully and never change - it. The format is standards body-type-variant. - E.g. T10-DIF-TYPE1-IP or T13-EPP-0-CRC. - - 'generate_fn' generates appropriate integrity metadata (for WRITE). - - 'verify_fn' verifies that the data buffer matches the integrity - metadata. - - 'tuple_size' must be set to match the size of the integrity - metadata per sector. I.e. 8 for DIF and EPP. - - 'tag_size' must be set to identify how many bytes of tag space - are available per hardware sector. For DIF this is either 2 or - 0 depending on the value of the Control Mode Page ATO bit. - ---------------------------------------------------------------------- 2007-12-24 Martin K. Petersen diff --git a/Documentation/block/writeback_cache_control.rst b/Documentation/block/writeback_cache_control.rst index b208488d0aae..c3707d071780 100644 --- a/Documentation/block/writeback_cache_control.rst +++ b/Documentation/block/writeback_cache_control.rst @@ -46,41 +46,50 @@ worry if the underlying devices need any explicit cache flushing and how the Forced Unit Access is implemented. The REQ_PREFLUSH and REQ_FUA flags may both be set on a single bio. - -Implementation details for bio based block drivers --------------------------------------------------------------- - -These drivers will always see the REQ_PREFLUSH and REQ_FUA bits as they sit -directly below the submit_bio interface. For remapping drivers the REQ_FUA -bits need to be propagated to underlying devices, and a global flush needs -to be implemented for bios with the REQ_PREFLUSH bit set. For real device -drivers that do not have a volatile cache the REQ_PREFLUSH and REQ_FUA bits -on non-empty bios can simply be ignored, and REQ_PREFLUSH requests without -data can be completed successfully without doing any work. Drivers for -devices with volatile caches need to implement the support for these -flags themselves without any help from the block layer. - - -Implementation details for request_fn based block drivers ---------------------------------------------------------- +Feature settings for block drivers +---------------------------------- For devices that do not support volatile write caches there is no driver support required, the block layer completes empty REQ_PREFLUSH requests before entering the driver and strips off the REQ_PREFLUSH and REQ_FUA bits from -requests that have a payload. For devices with volatile write caches the -driver needs to tell the block layer that it supports flushing caches by -doing:: +requests that have a payload. - blk_queue_write_cache(sdkp->disk->queue, true, false); +For devices with volatile write caches the driver needs to tell the block layer +that it supports flushing caches by setting the -and handle empty REQ_OP_FLUSH requests in its prep_fn/request_fn. Note that -REQ_PREFLUSH requests with a payload are automatically turned into a sequence -of an empty REQ_OP_FLUSH request followed by the actual write by the block -layer. For devices that also support the FUA bit the block layer needs -to be told to pass through the REQ_FUA bit using:: + BLK_FEAT_WRITE_CACHE - blk_queue_write_cache(sdkp->disk->queue, true, true); +flag in the queue_limits feature field. For devices that also support the FUA +bit the block layer needs to be told to pass on the REQ_FUA bit by also setting +the -and the driver must handle write requests that have the REQ_FUA bit set -in prep_fn/request_fn. If the FUA bit is not natively supported the block -layer turns it into an empty REQ_OP_FLUSH request after the actual write. + BLK_FEAT_FUA + +flag in the features field of the queue_limits structure. + +Implementation details for bio based block drivers +-------------------------------------------------- + +For bio based drivers the REQ_PREFLUSH and REQ_FUA bit are simply passed on to +the driver if the driver sets the BLK_FEAT_WRITE_CACHE flag and the driver +needs to handle them. + +*NOTE*: The REQ_FUA bit also gets passed on when the BLK_FEAT_FUA flags is +_not_ set. Any bio based driver that sets BLK_FEAT_WRITE_CACHE also needs to +handle REQ_FUA. + +For remapping drivers the REQ_FUA bits need to be propagated to underlying +devices, and a global flush needs to be implemented for bios with the +REQ_PREFLUSH bit set. + +Implementation details for blk-mq drivers +----------------------------------------- + +When the BLK_FEAT_WRITE_CACHE flag is set, REQ_OP_WRITE | REQ_PREFLUSH requests +with a payload are automatically turned into a sequence of a REQ_OP_FLUSH +request followed by the actual write by the block layer. + +When the BLK_FEAT_FUA flags is set, the REQ_FUA bit is simply passed on for the +REQ_OP_WRITE request, else a REQ_OP_FLUSH request is sent by the block layer +after the completion of the write request for bio submissions with the REQ_FUA +bit set. diff --git a/MAINTAINERS b/MAINTAINERS index f6cc3af7b552..7507671fd4e9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3759,6 +3759,20 @@ F: include/linux/blk* F: kernel/trace/blktrace.c F: lib/sbitmap.c +BLOCK LAYER DEVICE DRIVER API [RUST] +M: Andreas Hindborg +R: Boqun Feng +L: linux-block@vger.kernel.org +L: rust-for-linux@vger.kernel.org +S: Supported +W: https://rust-for-linux.com +B: https://github.com/Rust-for-Linux/linux/issues +C: https://rust-for-linux.zulipchat.com/#narrow/stream/Block +T: git https://github.com/Rust-for-Linux/linux.git rust-block-next +F: drivers/block/rnull.rs +F: rust/kernel/block.rs +F: rust/kernel/block/ + BLOCK2MTD DRIVER M: Joern Engel L: linux-mtd@lists.infradead.org diff --git a/arch/m68k/emu/nfblock.c b/arch/m68k/emu/nfblock.c index 642fb80c5c4e..874fe9588773 100644 --- a/arch/m68k/emu/nfblock.c +++ b/arch/m68k/emu/nfblock.c @@ -71,7 +71,7 @@ static void nfhd_submit_bio(struct bio *bio) len = bvec.bv_len; len >>= 9; nfhd_read_write(dev->id, 0, dir, sec >> shift, len >> shift, - page_to_phys(bvec.bv_page) + bvec.bv_offset); + bvec_phys(&bvec)); sec += len; } bio_endio(bio); @@ -98,6 +98,7 @@ static int __init nfhd_init_one(int id, u32 blocks, u32 bsize) { struct queue_limits lim = { .logical_block_size = bsize, + .features = BLK_FEAT_ROTATIONAL, }; struct nfhd_device *dev; int dev_id = id - NFHD_DEV_OFFSET; diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index ef805eaa9e01..9f1e76ddda5a 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -447,43 +447,31 @@ static int bulk_req_safe_read( return n; } -/* Called without dev->lock held, and only in interrupt context. */ -static void ubd_handler(void) +static void ubd_end_request(struct io_thread_req *io_req) { - int n; - int count; - - while(1){ - n = bulk_req_safe_read( - thread_fd, - irq_req_buffer, - &irq_remainder, - &irq_remainder_size, - UBD_REQ_BUFFER_SIZE - ); - if (n < 0) { - if(n == -EAGAIN) - break; - printk(KERN_ERR "spurious interrupt in ubd_handler, " - "err = %d\n", -n); - return; - } - for (count = 0; count < n/sizeof(struct io_thread_req *); count++) { - struct io_thread_req *io_req = (*irq_req_buffer)[count]; - - if ((io_req->error == BLK_STS_NOTSUPP) && (req_op(io_req->req) == REQ_OP_DISCARD)) { - blk_queue_max_discard_sectors(io_req->req->q, 0); - blk_queue_max_write_zeroes_sectors(io_req->req->q, 0); - } - blk_mq_end_request(io_req->req, io_req->error); - kfree(io_req); - } + if (io_req->error == BLK_STS_NOTSUPP) { + if (req_op(io_req->req) == REQ_OP_DISCARD) + blk_queue_disable_discard(io_req->req->q); + else if (req_op(io_req->req) == REQ_OP_WRITE_ZEROES) + blk_queue_disable_write_zeroes(io_req->req->q); } + blk_mq_end_request(io_req->req, io_req->error); + kfree(io_req); } static irqreturn_t ubd_intr(int irq, void *dev) { - ubd_handler(); + int len, i; + + while ((len = bulk_req_safe_read(thread_fd, irq_req_buffer, + &irq_remainder, &irq_remainder_size, + UBD_REQ_BUFFER_SIZE)) >= 0) { + for (i = 0; i < len / sizeof(struct io_thread_req *); i++) + ubd_end_request((*irq_req_buffer)[i]); + } + + if (len < 0 && len != -EAGAIN) + pr_err("spurious interrupt in %s, err = %d\n", __func__, len); return IRQ_HANDLED; } @@ -847,6 +835,7 @@ static int ubd_add(int n, char **error_out) struct queue_limits lim = { .max_segments = MAX_SG, .seg_boundary_mask = PAGE_SIZE - 1, + .features = BLK_FEAT_WRITE_CACHE, }; struct gendisk *disk; int err = 0; @@ -893,8 +882,6 @@ static int ubd_add(int n, char **error_out) goto out_cleanup_tags; } - blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue); - blk_queue_write_cache(disk->queue, true, false); disk->major = UBD_MAJOR; disk->first_minor = n << UBD_SHIFT; disk->minors = 1 << UBD_SHIFT; diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c index defc67909a9c..d6d2b533a574 100644 --- a/arch/xtensa/platforms/iss/simdisk.c +++ b/arch/xtensa/platforms/iss/simdisk.c @@ -263,6 +263,9 @@ static const struct proc_ops simdisk_proc_ops = { static int __init simdisk_setup(struct simdisk *dev, int which, struct proc_dir_entry *procdir) { + struct queue_limits lim = { + .features = BLK_FEAT_ROTATIONAL, + }; char tmp[2] = { '0' + which, 0 }; int err; @@ -271,7 +274,7 @@ static int __init simdisk_setup(struct simdisk *dev, int which, spin_lock_init(&dev->lock); dev->users = 0; - dev->gd = blk_alloc_disk(NULL, NUMA_NO_NODE); + dev->gd = blk_alloc_disk(&lim, NUMA_NO_NODE); if (IS_ERR(dev->gd)) { err = PTR_ERR(dev->gd); goto out; diff --git a/block/Kconfig b/block/Kconfig index dc12af58dbae..5b623b876d3b 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -62,6 +62,8 @@ config BLK_DEV_BSGLIB config BLK_DEV_INTEGRITY bool "Block layer data integrity support" + select CRC_T10DIF + select CRC64_ROCKSOFT help Some storage devices allow extra information to be stored/retrieved to help protect the data. The block layer @@ -72,12 +74,6 @@ config BLK_DEV_INTEGRITY T10/SCSI Data Integrity Field or the T13/ATA External Path Protection. If in doubt, say N. -config BLK_DEV_INTEGRITY_T10 - tristate - depends on BLK_DEV_INTEGRITY - select CRC_T10DIF - select CRC64_ROCKSOFT - config BLK_DEV_WRITE_MOUNTED bool "Allow writing to mounted block devices" default y diff --git a/block/Makefile b/block/Makefile index 168150b9c510..ddfd21c1a9ff 100644 --- a/block/Makefile +++ b/block/Makefile @@ -26,8 +26,7 @@ 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-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o -obj-$(CONFIG_BLK_DEV_INTEGRITY_T10) += t10-pi.o +obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o t10-pi.o obj-$(CONFIG_BLK_MQ_PCI) += blk-mq-pci.o obj-$(CONFIG_BLK_MQ_VIRTIO) += blk-mq-virtio.o obj-$(CONFIG_BLK_DEV_ZONED) += blk-zoned.o diff --git a/block/bdev.c b/block/bdev.c index 353677ac49b3..c5507b6f63b8 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -385,7 +385,7 @@ static struct file_system_type bd_type = { }; struct super_block *blockdev_superblock __ro_after_init; -struct vfsmount *blockdev_mnt __ro_after_init; +static struct vfsmount *blockdev_mnt __ro_after_init; EXPORT_SYMBOL_GPL(blockdev_superblock); void __init bdev_cache_init(void) @@ -1260,23 +1260,42 @@ void sync_bdevs(bool wait) } /* - * Handle STATX_DIOALIGN for block devices. - * - * Note that the inode passed to this 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 instead. + * Handle STATX_{DIOALIGN, WRITE_ATOMIC} for block devices. */ -void bdev_statx_dioalign(struct inode *inode, struct kstat *stat) +void bdev_statx(struct path *path, struct kstat *stat, + u32 request_mask) { + struct inode *backing_inode; struct block_device *bdev; - bdev = blkdev_get_no_open(inode->i_rdev); + 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 + * instead. + */ + bdev = blkdev_get_no_open(backing_inode->i_rdev); if (!bdev) return; - stat->dio_mem_align = bdev_dma_alignment(bdev) + 1; - stat->dio_offset_align = bdev_logical_block_size(bdev); - stat->result_mask |= STATX_DIOALIGN; + if (request_mask & STATX_DIOALIGN) { + stat->dio_mem_align = bdev_dma_alignment(bdev) + 1; + stat->dio_offset_align = bdev_logical_block_size(bdev); + stat->result_mask |= STATX_DIOALIGN; + } + + if (request_mask & STATX_WRITE_ATOMIC && bdev_can_atomic_write(bdev)) { + struct request_queue *bd_queue = bdev->bd_queue; + + generic_fill_statx_atomic_writes(stat, + queue_atomic_write_unit_min_bytes(bd_queue), + queue_atomic_write_unit_max_bytes(bd_queue)); + } blkdev_put_no_open(bdev); } diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index d442ee358fc2..b758693697c0 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -797,57 +797,6 @@ void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio) */ bfq_link_bfqg(bfqd, bfqg); __bfq_bic_change_cgroup(bfqd, bic, bfqg); - /* - * Update blkg_path for bfq_log_* functions. We cache this - * path, and update it here, for the following - * reasons. Operations on blkg objects in blk-cgroup are - * protected with the request_queue lock, and not with the - * lock that protects the instances of this scheduler - * (bfqd->lock). This exposes BFQ to the following sort of - * race. - * - * The blkg_lookup performed in bfq_get_queue, protected - * through rcu, may happen to return the address of a copy of - * the original blkg. If this is the case, then the - * bfqg_and_blkg_get performed in bfq_get_queue, to pin down - * the blkg, is useless: it does not prevent blk-cgroup code - * from destroying both the original blkg and all objects - * directly or indirectly referred by the copy of the - * blkg. - * - * On the bright side, destroy operations on a blkg invoke, as - * a first step, hooks of the scheduler associated with the - * blkg. And these hooks are executed with bfqd->lock held for - * BFQ. As a consequence, for any blkg associated with the - * request queue this instance of the scheduler is attached - * to, we are guaranteed that such a blkg is not destroyed, and - * that all the pointers it contains are consistent, while we - * are holding bfqd->lock. A blkg_lookup performed with - * bfqd->lock held then returns a fully consistent blkg, which - * remains consistent until this lock is held. - * - * Thanks to the last fact, and to the fact that: (1) bfqg has - * been obtained through a blkg_lookup in the above - * assignment, and (2) bfqd->lock is being held, here we can - * safely use the policy data for the involved blkg (i.e., the - * field bfqg->pd) to get to the blkg associated with bfqg, - * and then we can safely use any field of blkg. After we - * release bfqd->lock, even just getting blkg through this - * bfqg may cause dangling references to be traversed, as - * bfqg->pd may not exist any more. - * - * In view of the above facts, here we cache, in the bfqg, any - * blkg data we may need for this bic, and for its associated - * bfq_queue. As of now, we need to cache only the path of the - * blkg, which is used in the bfq_log_* functions. - * - * Finally, note that bfqg itself needs to be protected from - * destruction on the blkg_free of the original blkg (which - * invokes bfq_pd_free). We use an additional private - * refcounter for bfqg, to let it disappear only after no - * bfq_queue refers to it any longer. - */ - blkg_path(bfqg_to_blkg(bfqg), bfqg->blkg_path, sizeof(bfqg->blkg_path)); bic->blkcg_serial_nr = serial_nr; } diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 4b88a54a9b76..36a4998c4b37 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -5463,29 +5463,10 @@ static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync, } } -static void bfq_exit_icq(struct io_cq *icq) +static void _bfq_exit_icq(struct bfq_io_cq *bic, unsigned int num_actuators) { - struct bfq_io_cq *bic = icq_to_bic(icq); - struct bfq_data *bfqd = bic_to_bfqd(bic); - unsigned long flags; - unsigned int act_idx; - /* - * If bfqd and thus bfqd->num_actuators is not available any - * longer, then cycle over all possible per-actuator bfqqs in - * next loop. We rely on bic being zeroed on creation, and - * therefore on its unused per-actuator fields being NULL. - */ - unsigned int num_actuators = BFQ_MAX_ACTUATORS; struct bfq_iocq_bfqq_data *bfqq_data = bic->bfqq_data; - - /* - * bfqd is NULL if scheduler already exited, and in that case - * this is the last time these queues are accessed. - */ - if (bfqd) { - spin_lock_irqsave(&bfqd->lock, flags); - num_actuators = bfqd->num_actuators; - } + unsigned int act_idx; for (act_idx = 0; act_idx < num_actuators; act_idx++) { if (bfqq_data[act_idx].stable_merge_bfqq) @@ -5494,9 +5475,30 @@ static void bfq_exit_icq(struct io_cq *icq) bfq_exit_icq_bfqq(bic, true, act_idx); bfq_exit_icq_bfqq(bic, false, act_idx); } +} - if (bfqd) +static void bfq_exit_icq(struct io_cq *icq) +{ + struct bfq_io_cq *bic = icq_to_bic(icq); + struct bfq_data *bfqd = bic_to_bfqd(bic); + unsigned long flags; + + /* + * If bfqd and thus bfqd->num_actuators is not available any + * longer, then cycle over all possible per-actuator bfqqs in + * next loop. We rely on bic being zeroed on creation, and + * therefore on its unused per-actuator fields being NULL. + * + * bfqd is NULL if scheduler already exited, and in that case + * this is the last time these queues are accessed. + */ + if (bfqd) { + spin_lock_irqsave(&bfqd->lock, flags); + _bfq_exit_icq(bic, bfqd->num_actuators); spin_unlock_irqrestore(&bfqd->lock, flags); + } else { + _bfq_exit_icq(bic, BFQ_MAX_ACTUATORS); + } } /* diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h index 467e8cfc41a2..08ddf2cfae5b 100644 --- a/block/bfq-iosched.h +++ b/block/bfq-iosched.h @@ -1003,9 +1003,6 @@ struct bfq_group { /* must be the first member */ struct blkg_policy_data pd; - /* cached path for this blkg (see comments in bfq_bic_update_cgroup) */ - char blkg_path[128]; - /* reference counter (see comments in bfq_bic_update_cgroup) */ refcount_t ref; diff --git a/block/bio-integrity.c b/block/bio-integrity.c index 8b528e12136f..b78c145eb026 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -76,7 +76,7 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio, &bip->bip_max_vcnt, gfp_mask); if (!bip->bip_vec) goto err; - } else { + } else if (nr_vecs) { bip->bip_vec = bip->bip_inline_vecs; } @@ -276,6 +276,7 @@ static int bio_integrity_copy_user(struct bio *bio, struct bio_vec *bvec, bip->bip_flags |= BIP_INTEGRITY_USER | BIP_COPY_USER; bip->bip_iter.bi_sector = seed; + bip->bip_vcnt = nr_vecs; return 0; free_bip: bio_integrity_free(bio); @@ -297,6 +298,7 @@ static int bio_integrity_init_user(struct bio *bio, struct bio_vec *bvec, bip->bip_flags |= BIP_INTEGRITY_USER; bip->bip_iter.bi_sector = seed; bip->bip_iter.bi_size = len; + bip->bip_vcnt = nr_vecs; return 0; } @@ -334,7 +336,7 @@ int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t bytes, u32 seed) { struct request_queue *q = bdev_get_queue(bio->bi_bdev); - unsigned int align = q->dma_pad_mask | queue_dma_alignment(q); + unsigned int align = blk_lim_dma_alignment_and_pad(&q->limits); struct page *stack_pages[UIO_FASTIOV], **pages = stack_pages; struct bio_vec stack_vec[UIO_FASTIOV], *bvec = stack_vec; unsigned int direction, nr_bvecs; @@ -396,44 +398,6 @@ free_bvec: } EXPORT_SYMBOL_GPL(bio_integrity_map_user); -/** - * bio_integrity_process - Process integrity metadata for a bio - * @bio: bio to generate/verify integrity metadata for - * @proc_iter: iterator to process - * @proc_fn: Pointer to the relevant processing function - */ -static blk_status_t bio_integrity_process(struct bio *bio, - struct bvec_iter *proc_iter, integrity_processing_fn *proc_fn) -{ - struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk); - struct blk_integrity_iter iter; - struct bvec_iter bviter; - struct bio_vec bv; - struct bio_integrity_payload *bip = bio_integrity(bio); - blk_status_t ret = BLK_STS_OK; - - iter.disk_name = bio->bi_bdev->bd_disk->disk_name; - iter.interval = 1 << bi->interval_exp; - iter.tuple_size = bi->tuple_size; - iter.seed = proc_iter->bi_sector; - iter.prot_buf = bvec_virt(bip->bip_vec); - iter.pi_offset = bi->pi_offset; - - __bio_for_each_segment(bv, bio, bviter, *proc_iter) { - void *kaddr = bvec_kmap_local(&bv); - - iter.data_buf = kaddr; - iter.data_size = bv.bv_len; - ret = proc_fn(&iter); - kunmap_local(kaddr); - - if (ret) - break; - - } - return ret; -} - /** * bio_integrity_prep - Prepare bio for integrity I/O * @bio: bio to prepare @@ -450,17 +414,13 @@ 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; - unsigned long start, end; - unsigned int len, nr_pages; - unsigned int bytes, offset, i; + gfp_t gfp = GFP_NOIO; if (!bi) return true; - if (bio_op(bio) != REQ_OP_READ && bio_op(bio) != REQ_OP_WRITE) - return true; - if (!bio_sectors(bio)) return true; @@ -468,32 +428,36 @@ bool bio_integrity_prep(struct bio *bio) if (bio_integrity(bio)) return true; - if (bio_data_dir(bio) == READ) { - if (!bi->profile->verify_fn || - !(bi->flags & BLK_INTEGRITY_VERIFY)) + switch (bio_op(bio)) { + case REQ_OP_READ: + if (bi->flags & BLK_INTEGRITY_NOVERIFY) return true; - } else { - if (!bi->profile->generate_fn || - !(bi->flags & BLK_INTEGRITY_GENERATE)) + 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_NOIO); + buf = kmalloc(len, gfp); if (unlikely(buf == NULL)) { - printk(KERN_ERR "could not allocate integrity buffer\n"); goto err_end_io; } - end = (((unsigned long) buf) + len + PAGE_SIZE - 1) >> PAGE_SHIFT; - start = ((unsigned long) buf) >> PAGE_SHIFT; - nr_pages = end - start; - - /* Allocate bio integrity payload and integrity vectors */ - bip = bio_integrity_alloc(bio, GFP_NOIO, nr_pages); + bip = bio_integrity_alloc(bio, GFP_NOIO, 1); if (IS_ERR(bip)) { - printk(KERN_ERR "could not allocate data integrity bioset\n"); kfree(buf); goto err_end_io; } @@ -501,35 +465,20 @@ bool bio_integrity_prep(struct bio *bio) bip->bip_flags |= BIP_BLOCK_INTEGRITY; bip_set_seed(bip, bio->bi_iter.bi_sector); - if (bi->flags & BLK_INTEGRITY_IP_CHECKSUM) + if (bi->csum_type == BLK_INTEGRITY_CSUM_IP) bip->bip_flags |= BIP_IP_CHECKSUM; - /* Map it */ - offset = offset_in_page(buf); - for (i = 0; i < nr_pages && len > 0; i++) { - bytes = PAGE_SIZE - offset; - - if (bytes > len) - bytes = len; - - if (bio_integrity_add_page(bio, virt_to_page(buf), - bytes, offset) < bytes) { - printk(KERN_ERR "could not attach integrity payload\n"); - goto err_end_io; - } - - buf += bytes; - len -= bytes; - offset = 0; + 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) { - bio_integrity_process(bio, &bio->bi_iter, - bi->profile->generate_fn); - } else { + if (bio_data_dir(bio) == WRITE) + blk_integrity_generate(bio); + else bip->bio_iter = bio->bi_iter; - } return true; err_end_io: @@ -552,15 +501,8 @@ 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; - struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk); - /* - * At the moment verify is called bio's iterator was advanced - * during split and completion, we need to rewind iterator to - * it's original position. - */ - bio->bi_status = bio_integrity_process(bio, &bip->bio_iter, - bi->profile->verify_fn); + blk_integrity_verify(bio); bio_integrity_free(bio); bio_endio(bio); } @@ -582,7 +524,7 @@ bool __bio_integrity_endio(struct bio *bio) struct bio_integrity_payload *bip = bio_integrity(bio); if (bio_op(bio) == REQ_OP_READ && !bio->bi_status && - (bip->bip_flags & BIP_BLOCK_INTEGRITY) && bi->profile->verify_fn) { + (bip->bip_flags & BIP_BLOCK_INTEGRITY) && bi->csum_type) { INIT_WORK(&bip->bip_work, bio_integrity_verify_fn); queue_work(kintegrityd_wq, &bip->bip_work); return false; @@ -642,14 +584,11 @@ int bio_integrity_clone(struct bio *bio, struct bio *bio_src, BUG_ON(bip_src == NULL); - bip = bio_integrity_alloc(bio, gfp_mask, bip_src->bip_vcnt); + bip = bio_integrity_alloc(bio, gfp_mask, 0); if (IS_ERR(bip)) return PTR_ERR(bip); - memcpy(bip->bip_vec, bip_src->bip_vec, - bip_src->bip_vcnt * sizeof(struct bio_vec)); - - bip->bip_vcnt = bip_src->bip_vcnt; + bip->bip_vec = bip_src->bip_vec; bip->bip_iter = bip_src->bip_iter; bip->bip_flags = bip_src->bip_flags & ~BIP_BLOCK_INTEGRITY; diff --git a/block/bio.c b/block/bio.c index e9e809a63c59..a3b1b2266c50 100644 --- a/block/bio.c +++ b/block/bio.c @@ -953,7 +953,7 @@ bool bvec_try_merge_hw_page(struct request_queue *q, struct bio_vec *bv, bool *same_page) { unsigned long mask = queue_segment_boundary(q); - phys_addr_t addr1 = page_to_phys(bv->bv_page) + bv->bv_offset; + phys_addr_t addr1 = bvec_phys(bv); phys_addr_t addr2 = page_to_phys(page) + offset + len - 1; if ((addr1 | mask) != (addr2 | mask)) diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h index 90b3959d88cf..bd472a30bc61 100644 --- a/block/blk-cgroup.h +++ b/block/blk-cgroup.h @@ -300,19 +300,6 @@ static inline struct blkcg *cpd_to_blkcg(struct blkcg_policy_data *cpd) return cpd ? cpd->blkcg : NULL; } -/** - * blkg_path - format cgroup path of blkg - * @blkg: blkg of interest - * @buf: target buffer - * @buflen: target buffer length - * - * Format the path of the cgroup of @blkg into @buf. - */ -static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen) -{ - return cgroup_path(blkg->blkcg->css.cgroup, buf, buflen); -} - /** * blkg_get - get a blkg reference * @blkg: blkg to get diff --git a/block/blk-core.c b/block/blk-core.c index 82c3ae22d76d..02bceeb36f2c 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -94,20 +94,6 @@ void blk_queue_flag_clear(unsigned int flag, struct request_queue *q) } EXPORT_SYMBOL(blk_queue_flag_clear); -/** - * blk_queue_flag_test_and_set - atomically test and set a queue flag - * @flag: flag to be set - * @q: request queue - * - * Returns the previous value of @flag - 0 if the flag was not set and 1 if - * the flag was already set. - */ -bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q) -{ - return test_and_set_bit(flag, &q->queue_flags); -} -EXPORT_SYMBOL_GPL(blk_queue_flag_test_and_set); - #define REQ_OP_NAME(name) [REQ_OP_##name] = #name static const char *const blk_op_name[] = { REQ_OP_NAME(READ), @@ -174,6 +160,8 @@ static const struct { /* Command duration limit device-side timeout */ [BLK_STS_DURATION_LIMIT] = { -ETIME, "duration limit exceeded" }, + [BLK_STS_INVAL] = { -EINVAL, "invalid" }, + /* everything else not covered above: */ [BLK_STS_IOERR] = { -EIO, "I/O" }, }; @@ -739,6 +727,18 @@ void submit_bio_noacct_nocheck(struct bio *bio) __submit_bio_noacct(bio); } +static blk_status_t blk_validate_atomic_write_op_size(struct request_queue *q, + struct bio *bio) +{ + if (bio->bi_iter.bi_size > queue_atomic_write_unit_max_bytes(q)) + return BLK_STS_INVAL; + + if (bio->bi_iter.bi_size % queue_atomic_write_unit_min_bytes(q)) + return BLK_STS_INVAL; + + return BLK_STS_OK; +} + /** * submit_bio_noacct - re-submit a bio to the block device layer for I/O * @bio: The bio describing the location in memory and on the device. @@ -782,7 +782,7 @@ void submit_bio_noacct(struct bio *bio) if (WARN_ON_ONCE(bio_op(bio) != REQ_OP_WRITE && bio_op(bio) != REQ_OP_ZONE_APPEND)) goto end_io; - if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags)) { + if (!bdev_write_cache(bdev)) { bio->bi_opf &= ~(REQ_PREFLUSH | REQ_FUA); if (!bio_sectors(bio)) { status = BLK_STS_OK; @@ -791,12 +791,17 @@ void submit_bio_noacct(struct bio *bio) } } - if (!test_bit(QUEUE_FLAG_POLL, &q->queue_flags)) + if (!(q->limits.features & BLK_FEAT_POLL)) bio_clear_polled(bio); switch (bio_op(bio)) { case REQ_OP_READ: case REQ_OP_WRITE: + if (bio->bi_opf & REQ_ATOMIC) { + status = blk_validate_atomic_write_op_size(q, bio); + if (status != BLK_STS_OK) + goto end_io; + } break; case REQ_OP_FLUSH: /* @@ -825,11 +830,8 @@ void submit_bio_noacct(struct bio *bio) case REQ_OP_ZONE_OPEN: case REQ_OP_ZONE_CLOSE: case REQ_OP_ZONE_FINISH: - if (!bdev_is_zoned(bio->bi_bdev)) - goto not_supported; - break; case REQ_OP_ZONE_RESET_ALL: - if (!bdev_is_zoned(bio->bi_bdev) || !blk_queue_zone_resetall(q)) + if (!bdev_is_zoned(bio->bi_bdev)) goto not_supported; break; case REQ_OP_DRV_IN: @@ -915,8 +917,7 @@ int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags) return 0; q = bdev_get_queue(bdev); - if (cookie == BLK_QC_T_NONE || - !test_bit(QUEUE_FLAG_POLL, &q->queue_flags)) + if (cookie == BLK_QC_T_NONE || !(q->limits.features & BLK_FEAT_POLL)) return 0; blk_flush_plug(current->plug, false); diff --git a/block/blk-flush.c b/block/blk-flush.c index cca4f9131f79..a72e2a83d075 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -100,23 +100,6 @@ blk_get_flush_queue(struct request_queue *q, struct blk_mq_ctx *ctx) return blk_mq_map_queue(q, REQ_OP_FLUSH, ctx)->fq; } -static unsigned int blk_flush_policy(unsigned long fflags, struct request *rq) -{ - unsigned int policy = 0; - - if (blk_rq_sectors(rq)) - policy |= REQ_FSEQ_DATA; - - if (fflags & (1UL << QUEUE_FLAG_WC)) { - if (rq->cmd_flags & REQ_PREFLUSH) - policy |= REQ_FSEQ_PREFLUSH; - if (!(fflags & (1UL << QUEUE_FLAG_FUA)) && - (rq->cmd_flags & REQ_FUA)) - policy |= REQ_FSEQ_POSTFLUSH; - } - return policy; -} - static unsigned int blk_flush_cur_seq(struct request *rq) { return 1 << ffz(rq->flush.seq); @@ -399,19 +382,32 @@ static void blk_rq_init_flush(struct request *rq) bool blk_insert_flush(struct request *rq) { struct request_queue *q = rq->q; - unsigned long fflags = q->queue_flags; /* may change, cache */ - unsigned int policy = blk_flush_policy(fflags, rq); struct blk_flush_queue *fq = blk_get_flush_queue(q, rq->mq_ctx); + bool supports_fua = q->limits.features & BLK_FEAT_FUA; + unsigned int policy = 0; /* FLUSH/FUA request must never be merged */ WARN_ON_ONCE(rq->bio != rq->biotail); + if (blk_rq_sectors(rq)) + policy |= REQ_FSEQ_DATA; + + /* + * Check which flushes we need to sequence for this operation. + */ + if (blk_queue_write_cache(q)) { + if (rq->cmd_flags & REQ_PREFLUSH) + policy |= REQ_FSEQ_PREFLUSH; + if ((rq->cmd_flags & REQ_FUA) && !supports_fua) + policy |= REQ_FSEQ_POSTFLUSH; + } + /* * @policy now records what operations need to be done. Adjust * REQ_PREFLUSH and FUA for the driver. */ rq->cmd_flags &= ~REQ_PREFLUSH; - if (!(fflags & (1UL << QUEUE_FLAG_FUA))) + if (!supports_fua) rq->cmd_flags &= ~REQ_FUA; /* diff --git a/block/blk-integrity.c b/block/blk-integrity.c index ccbeb6dfa87a..010decc892ea 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -107,60 +107,6 @@ new_segment: } EXPORT_SYMBOL(blk_rq_map_integrity_sg); -/** - * blk_integrity_compare - Compare integrity profile of two disks - * @gd1: Disk to compare - * @gd2: Disk to compare - * - * Description: Meta-devices like DM and MD need to verify that all - * sub-devices use the same integrity format before advertising to - * upper layers that they can send/receive integrity metadata. This - * function can be used to check whether two gendisk devices have - * compatible integrity formats. - */ -int blk_integrity_compare(struct gendisk *gd1, struct gendisk *gd2) -{ - struct blk_integrity *b1 = &gd1->queue->integrity; - struct blk_integrity *b2 = &gd2->queue->integrity; - - if (!b1->profile && !b2->profile) - return 0; - - if (!b1->profile || !b2->profile) - return -1; - - if (b1->interval_exp != b2->interval_exp) { - pr_err("%s: %s/%s protection interval %u != %u\n", - __func__, gd1->disk_name, gd2->disk_name, - 1 << b1->interval_exp, 1 << b2->interval_exp); - return -1; - } - - if (b1->tuple_size != b2->tuple_size) { - pr_err("%s: %s/%s tuple sz %u != %u\n", __func__, - gd1->disk_name, gd2->disk_name, - b1->tuple_size, b2->tuple_size); - return -1; - } - - if (b1->tag_size && b2->tag_size && (b1->tag_size != b2->tag_size)) { - pr_err("%s: %s/%s tag sz %u != %u\n", __func__, - gd1->disk_name, gd2->disk_name, - b1->tag_size, b2->tag_size); - return -1; - } - - if (b1->profile != b2->profile) { - pr_err("%s: %s/%s type %s != %s\n", __func__, - gd1->disk_name, gd2->disk_name, - b1->profile->name, b2->profile->name); - return -1; - } - - return 0; -} -EXPORT_SYMBOL(blk_integrity_compare); - bool blk_integrity_merge_rq(struct request_queue *q, struct request *req, struct request *next) { @@ -214,7 +160,64 @@ bool blk_integrity_merge_bio(struct request_queue *q, struct request *req, static inline struct blk_integrity *dev_to_bi(struct device *dev) { - return &dev_to_disk(dev)->queue->integrity; + return &dev_to_disk(dev)->queue->limits.integrity; +} + +const char *blk_integrity_profile_name(struct blk_integrity *bi) +{ + switch (bi->csum_type) { + case BLK_INTEGRITY_CSUM_IP: + if (bi->flags & BLK_INTEGRITY_REF_TAG) + return "T10-DIF-TYPE1-IP"; + return "T10-DIF-TYPE3-IP"; + case BLK_INTEGRITY_CSUM_CRC: + if (bi->flags & BLK_INTEGRITY_REF_TAG) + return "T10-DIF-TYPE1-CRC"; + return "T10-DIF-TYPE3-CRC"; + case BLK_INTEGRITY_CSUM_CRC64: + if (bi->flags & BLK_INTEGRITY_REF_TAG) + return "EXT-DIF-TYPE1-CRC64"; + return "EXT-DIF-TYPE3-CRC64"; + case BLK_INTEGRITY_CSUM_NONE: + break; + } + + return "nop"; +} +EXPORT_SYMBOL_GPL(blk_integrity_profile_name); + +static ssize_t flag_store(struct device *dev, const char *page, size_t count, + unsigned char flag) +{ + struct request_queue *q = dev_to_disk(dev)->queue; + struct queue_limits lim; + unsigned long val; + int err; + + err = kstrtoul(page, 10, &val); + if (err) + return err; + + /* note that the flags are inverted vs the values in the sysfs files */ + lim = queue_limits_start_update(q); + if (val) + lim.integrity.flags &= ~flag; + else + lim.integrity.flags |= flag; + + blk_mq_freeze_queue(q); + err = queue_limits_commit_update(q, &lim); + blk_mq_unfreeze_queue(q); + if (err) + return err; + return count; +} + +static ssize_t flag_show(struct device *dev, char *page, unsigned char flag) +{ + struct blk_integrity *bi = dev_to_bi(dev); + + return sysfs_emit(page, "%d\n", !(bi->flags & flag)); } static ssize_t format_show(struct device *dev, struct device_attribute *attr, @@ -222,9 +225,9 @@ static ssize_t format_show(struct device *dev, struct device_attribute *attr, { struct blk_integrity *bi = dev_to_bi(dev); - if (bi->profile && bi->profile->name) - return sysfs_emit(page, "%s\n", bi->profile->name); - return sysfs_emit(page, "none\n"); + if (!bi->tuple_size) + return sysfs_emit(page, "none\n"); + return sysfs_emit(page, "%s\n", blk_integrity_profile_name(bi)); } static ssize_t tag_size_show(struct device *dev, struct device_attribute *attr, @@ -249,49 +252,26 @@ static ssize_t read_verify_store(struct device *dev, struct device_attribute *attr, const char *page, size_t count) { - struct blk_integrity *bi = dev_to_bi(dev); - char *p = (char *) page; - unsigned long val = simple_strtoul(p, &p, 10); - - if (val) - bi->flags |= BLK_INTEGRITY_VERIFY; - else - bi->flags &= ~BLK_INTEGRITY_VERIFY; - - return count; + return flag_store(dev, page, count, BLK_INTEGRITY_NOVERIFY); } static ssize_t read_verify_show(struct device *dev, struct device_attribute *attr, char *page) { - struct blk_integrity *bi = dev_to_bi(dev); - - return sysfs_emit(page, "%d\n", !!(bi->flags & BLK_INTEGRITY_VERIFY)); + return flag_show(dev, page, BLK_INTEGRITY_NOVERIFY); } static ssize_t write_generate_store(struct device *dev, struct device_attribute *attr, const char *page, size_t count) { - struct blk_integrity *bi = dev_to_bi(dev); - - char *p = (char *) page; - unsigned long val = simple_strtoul(p, &p, 10); - - if (val) - bi->flags |= BLK_INTEGRITY_GENERATE; - else - bi->flags &= ~BLK_INTEGRITY_GENERATE; - - return count; + return flag_store(dev, page, count, BLK_INTEGRITY_NOGENERATE); } static ssize_t write_generate_show(struct device *dev, struct device_attribute *attr, char *page) { - struct blk_integrity *bi = dev_to_bi(dev); - - return sysfs_emit(page, "%d\n", !!(bi->flags & BLK_INTEGRITY_GENERATE)); + return flag_show(dev, page, BLK_INTEGRITY_NOGENERATE); } static ssize_t device_is_integrity_capable_show(struct device *dev, @@ -325,81 +305,3 @@ const struct attribute_group blk_integrity_attr_group = { .name = "integrity", .attrs = integrity_attrs, }; - -static blk_status_t blk_integrity_nop_fn(struct blk_integrity_iter *iter) -{ - return BLK_STS_OK; -} - -static void blk_integrity_nop_prepare(struct request *rq) -{ -} - -static void blk_integrity_nop_complete(struct request *rq, - unsigned int nr_bytes) -{ -} - -static const struct blk_integrity_profile nop_profile = { - .name = "nop", - .generate_fn = blk_integrity_nop_fn, - .verify_fn = blk_integrity_nop_fn, - .prepare_fn = blk_integrity_nop_prepare, - .complete_fn = blk_integrity_nop_complete, -}; - -/** - * blk_integrity_register - Register a gendisk as being integrity-capable - * @disk: struct gendisk pointer to make integrity-aware - * @template: block integrity profile to register - * - * Description: When a device needs to advertise itself as being able to - * send/receive integrity metadata it must use this function to register - * the capability with the block layer. The template is a blk_integrity - * struct with values appropriate for the underlying hardware. See - * Documentation/block/data-integrity.rst. - */ -void blk_integrity_register(struct gendisk *disk, struct blk_integrity *template) -{ - struct blk_integrity *bi = &disk->queue->integrity; - - bi->flags = BLK_INTEGRITY_VERIFY | BLK_INTEGRITY_GENERATE | - template->flags; - bi->interval_exp = template->interval_exp ? : - ilog2(queue_logical_block_size(disk->queue)); - bi->profile = template->profile ? template->profile : &nop_profile; - bi->tuple_size = template->tuple_size; - bi->tag_size = template->tag_size; - bi->pi_offset = template->pi_offset; - - blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, disk->queue); - -#ifdef CONFIG_BLK_INLINE_ENCRYPTION - if (disk->queue->crypto_profile) { - pr_warn("blk-integrity: Integrity and hardware inline encryption are not supported together. Disabling hardware inline encryption.\n"); - disk->queue->crypto_profile = NULL; - } -#endif -} -EXPORT_SYMBOL(blk_integrity_register); - -/** - * blk_integrity_unregister - Unregister block integrity profile - * @disk: disk whose integrity profile to unregister - * - * Description: This function unregisters the integrity capability from - * a block device. - */ -void blk_integrity_unregister(struct gendisk *disk) -{ - struct blk_integrity *bi = &disk->queue->integrity; - - if (!bi->profile) - return; - - /* ensure all bios are off the integrity workqueue */ - blk_flush_integrity(); - blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, disk->queue); - memset(bi, 0, sizeof(*bi)); -} -EXPORT_SYMBOL(blk_integrity_unregister); diff --git a/block/blk-lib.c b/block/blk-lib.c index 442da9dad042..9f735efa6c94 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -103,38 +103,71 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, } EXPORT_SYMBOL(blkdev_issue_discard); -static int __blkdev_issue_write_zeroes(struct block_device *bdev, +static sector_t bio_write_zeroes_limit(struct block_device *bdev) +{ + sector_t bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1; + + return min(bdev_write_zeroes_sectors(bdev), + (UINT_MAX >> SECTOR_SHIFT) & ~bs_mask); +} + +static void __blkdev_issue_write_zeroes(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct bio **biop, unsigned flags) { - struct bio *bio = *biop; - unsigned int max_sectors; - - if (bdev_read_only(bdev)) - return -EPERM; - - /* Ensure that max_sectors doesn't overflow bi_size */ - max_sectors = bdev_write_zeroes_sectors(bdev); - - if (max_sectors == 0) - return -EOPNOTSUPP; - while (nr_sects) { - unsigned int len = min_t(sector_t, nr_sects, max_sectors); + unsigned int len = min_t(sector_t, nr_sects, + bio_write_zeroes_limit(bdev)); + struct bio *bio; - bio = blk_next_bio(bio, bdev, 0, REQ_OP_WRITE_ZEROES, gfp_mask); + if ((flags & BLKDEV_ZERO_KILLABLE) && + fatal_signal_pending(current)) + break; + + bio = bio_alloc(bdev, 0, REQ_OP_WRITE_ZEROES, gfp_mask); bio->bi_iter.bi_sector = sector; if (flags & BLKDEV_ZERO_NOUNMAP) bio->bi_opf |= REQ_NOUNMAP; bio->bi_iter.bi_size = len << SECTOR_SHIFT; + *biop = bio_chain_and_submit(*biop, bio); + nr_sects -= len; sector += len; cond_resched(); } +} - *biop = bio; - return 0; +static int blkdev_issue_write_zeroes(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp, unsigned flags) +{ + struct bio *bio = NULL; + struct blk_plug plug; + int ret = 0; + + blk_start_plug(&plug); + __blkdev_issue_write_zeroes(bdev, sector, nr_sects, gfp, &bio, flags); + if (bio) { + if ((flags & BLKDEV_ZERO_KILLABLE) && + fatal_signal_pending(current)) { + bio_await_chain(bio); + blk_finish_plug(&plug); + return -EINTR; + } + ret = submit_bio_wait(bio); + bio_put(bio); + } + blk_finish_plug(&plug); + + /* + * For some devices there is no non-destructive way to verify whether + * WRITE ZEROES is actually supported. These will clear the capability + * on an I/O error, in which case we'll turn any error into + * "not supported" here. + */ + if (ret && !bdev_write_zeroes_sectors(bdev)) + return -EOPNOTSUPP; + return ret; } /* @@ -150,35 +183,63 @@ static unsigned int __blkdev_sectors_to_bio_pages(sector_t nr_sects) return min(pages, (sector_t)BIO_MAX_VECS); } -static int __blkdev_issue_zero_pages(struct block_device *bdev, +static void __blkdev_issue_zero_pages(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, - struct bio **biop) + struct bio **biop, unsigned int flags) { - struct bio *bio = *biop; - int bi_size = 0; - unsigned int sz; + while (nr_sects) { + unsigned int nr_vecs = __blkdev_sectors_to_bio_pages(nr_sects); + struct bio *bio; - if (bdev_read_only(bdev)) - return -EPERM; - - while (nr_sects != 0) { - bio = blk_next_bio(bio, bdev, __blkdev_sectors_to_bio_pages(nr_sects), - REQ_OP_WRITE, gfp_mask); + bio = bio_alloc(bdev, nr_vecs, REQ_OP_WRITE, gfp_mask); bio->bi_iter.bi_sector = sector; - while (nr_sects != 0) { - sz = min((sector_t) PAGE_SIZE, nr_sects << 9); - bi_size = bio_add_page(bio, ZERO_PAGE(0), sz, 0); - nr_sects -= bi_size >> 9; - sector += bi_size >> 9; - if (bi_size < sz) + if ((flags & BLKDEV_ZERO_KILLABLE) && + fatal_signal_pending(current)) + break; + + do { + unsigned int len, added; + + len = min_t(sector_t, + PAGE_SIZE, nr_sects << SECTOR_SHIFT); + added = bio_add_page(bio, ZERO_PAGE(0), len, 0); + if (added < len) break; - } + nr_sects -= added >> SECTOR_SHIFT; + sector += added >> SECTOR_SHIFT; + } while (nr_sects); + + *biop = bio_chain_and_submit(*biop, bio); cond_resched(); } +} - *biop = bio; - return 0; +static int blkdev_issue_zero_pages(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp, unsigned flags) +{ + struct bio *bio = NULL; + struct blk_plug plug; + int ret = 0; + + if (flags & BLKDEV_ZERO_NOFALLBACK) + return -EOPNOTSUPP; + + blk_start_plug(&plug); + __blkdev_issue_zero_pages(bdev, sector, nr_sects, gfp, &bio, flags); + if (bio) { + if ((flags & BLKDEV_ZERO_KILLABLE) && + fatal_signal_pending(current)) { + bio_await_chain(bio); + blk_finish_plug(&plug); + return -EINTR; + } + ret = submit_bio_wait(bio); + bio_put(bio); + } + blk_finish_plug(&plug); + + return ret; } /** @@ -204,20 +265,19 @@ int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct bio **biop, unsigned flags) { - int ret; - sector_t bs_mask; + if (bdev_read_only(bdev)) + return -EPERM; - bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1; - if ((sector | nr_sects) & bs_mask) - return -EINVAL; - - ret = __blkdev_issue_write_zeroes(bdev, sector, nr_sects, gfp_mask, - biop, flags); - if (ret != -EOPNOTSUPP || (flags & BLKDEV_ZERO_NOFALLBACK)) - return ret; - - return __blkdev_issue_zero_pages(bdev, sector, nr_sects, gfp_mask, - biop); + if (bdev_write_zeroes_sectors(bdev)) { + __blkdev_issue_write_zeroes(bdev, sector, nr_sects, + gfp_mask, biop, flags); + } else { + if (flags & BLKDEV_ZERO_NOFALLBACK) + return -EOPNOTSUPP; + __blkdev_issue_zero_pages(bdev, sector, nr_sects, gfp_mask, + biop, flags); + } + return 0; } EXPORT_SYMBOL(__blkdev_issue_zeroout); @@ -237,51 +297,21 @@ EXPORT_SYMBOL(__blkdev_issue_zeroout); int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, unsigned flags) { - int ret = 0; - sector_t bs_mask; - struct bio *bio; - struct blk_plug plug; - bool try_write_zeroes = !!bdev_write_zeroes_sectors(bdev); + int ret; - bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1; - if ((sector | nr_sects) & bs_mask) + if ((sector | nr_sects) & ((bdev_logical_block_size(bdev) >> 9) - 1)) return -EINVAL; + if (bdev_read_only(bdev)) + return -EPERM; -retry: - bio = NULL; - blk_start_plug(&plug); - if (try_write_zeroes) { - ret = __blkdev_issue_write_zeroes(bdev, sector, nr_sects, - gfp_mask, &bio, flags); - } else if (!(flags & BLKDEV_ZERO_NOFALLBACK)) { - ret = __blkdev_issue_zero_pages(bdev, sector, nr_sects, - gfp_mask, &bio); - } else { - /* No zeroing offload support */ - ret = -EOPNOTSUPP; - } - if (ret == 0 && bio) { - ret = submit_bio_wait(bio); - bio_put(bio); - } - blk_finish_plug(&plug); - if (ret && try_write_zeroes) { - if (!(flags & BLKDEV_ZERO_NOFALLBACK)) { - try_write_zeroes = false; - goto retry; - } - if (!bdev_write_zeroes_sectors(bdev)) { - /* - * Zeroing offload support was indicated, but the - * device reported ILLEGAL REQUEST (for some devices - * there is no non-destructive way to verify whether - * WRITE ZEROES is actually supported). - */ - ret = -EOPNOTSUPP; - } + if (bdev_write_zeroes_sectors(bdev)) { + ret = blkdev_issue_write_zeroes(bdev, sector, nr_sects, + gfp_mask, flags); + if (ret != -EOPNOTSUPP) + return ret; } - return ret; + return blkdev_issue_zero_pages(bdev, sector, nr_sects, gfp_mask, flags); } EXPORT_SYMBOL(blkdev_issue_zeroout); diff --git a/block/blk-map.c b/block/blk-map.c index 71210cdb3442..bce144091128 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -634,7 +634,7 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq, const struct iov_iter *iter, gfp_t gfp_mask) { bool copy = false, map_bvec = false; - unsigned long align = q->dma_pad_mask | queue_dma_alignment(q); + unsigned long align = blk_lim_dma_alignment_and_pad(&q->limits); struct bio *bio = NULL; struct iov_iter i; int ret = -EINVAL; diff --git a/block/blk-merge.c b/block/blk-merge.c index 8534c35e0497..de5281bcadc5 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -154,6 +154,19 @@ static struct bio *bio_split_write_zeroes(struct bio *bio, return bio_split(bio, lim->max_write_zeroes_sectors, GFP_NOIO, bs); } +static inline unsigned int blk_boundary_sectors(const struct queue_limits *lim, + bool is_atomic) +{ + /* + * chunk_sectors must be a multiple of atomic_write_boundary_sectors if + * both non-zero. + */ + if (is_atomic && lim->atomic_write_boundary_sectors) + return lim->atomic_write_boundary_sectors; + + return lim->chunk_sectors; +} + /* * Return the maximum number of sectors from the start of a bio that may be * submitted as a single request to a block device. If enough sectors remain, @@ -167,12 +180,23 @@ static inline unsigned get_max_io_size(struct bio *bio, { unsigned pbs = lim->physical_block_size >> SECTOR_SHIFT; unsigned lbs = lim->logical_block_size >> SECTOR_SHIFT; - unsigned max_sectors = lim->max_sectors, start, end; + bool is_atomic = bio->bi_opf & REQ_ATOMIC; + unsigned boundary_sectors = blk_boundary_sectors(lim, is_atomic); + unsigned max_sectors, start, end; - if (lim->chunk_sectors) { + /* + * We ignore lim->max_sectors for atomic writes because it may less + * than the actual bio size, which we cannot tolerate. + */ + if (is_atomic) + max_sectors = lim->atomic_write_max_sectors; + else + max_sectors = lim->max_sectors; + + if (boundary_sectors) { max_sectors = min(max_sectors, - blk_chunk_sectors_left(bio->bi_iter.bi_sector, - lim->chunk_sectors)); + blk_boundary_sectors_left(bio->bi_iter.bi_sector, + boundary_sectors)); } start = bio->bi_iter.bi_sector & (pbs - 1); @@ -185,23 +209,22 @@ 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. - * @start_page: See below. - * @offset: Offset from @start_page where to add a segment. + * @paddr: address of the range to add + * @len: maximum length available to add at @paddr * - * Returns the maximum number of bytes that can be added as a single segment. + * 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, - struct page *start_page, unsigned long offset) + phys_addr_t paddr, unsigned int len) { - unsigned long mask = lim->seg_boundary_mask; - - offset = mask & (page_to_phys(start_page) + offset); - /* * Prevent an overflow if mask = ULONG_MAX and offset = 0 by adding 1 * after having calculated the minimum. */ - return min(mask - offset, (unsigned long)lim->max_segment_size - 1) + 1; + return min_t(unsigned long, len, + min(lim->seg_boundary_mask - (lim->seg_boundary_mask & paddr), + (unsigned long)lim->max_segment_size - 1) + 1); } /** @@ -234,9 +257,7 @@ static bool bvec_split_segs(const struct queue_limits *lim, unsigned seg_size = 0; while (len && *nsegs < max_segs) { - seg_size = get_max_segment_size(lim, bv->bv_page, - bv->bv_offset + total_len); - seg_size = min(seg_size, len); + seg_size = get_max_segment_size(lim, bvec_phys(bv) + total_len, len); (*nsegs)++; total_len += seg_size; @@ -305,6 +326,11 @@ struct bio *bio_split_rw(struct bio *bio, const struct queue_limits *lim, *segs = nsegs; return NULL; split: + if (bio->bi_opf & REQ_ATOMIC) { + bio->bi_status = BLK_STS_INVAL; + bio_endio(bio); + return ERR_PTR(-EINVAL); + } /* * We can't sanely support splitting for a REQ_NOWAIT bio. End it * with EAGAIN if splitting is required and return an error pointer. @@ -465,8 +491,8 @@ static unsigned blk_bvec_map_sg(struct request_queue *q, while (nbytes > 0) { unsigned offset = bvec->bv_offset + total; - unsigned len = min(get_max_segment_size(&q->limits, - bvec->bv_page, offset), nbytes); + unsigned len = get_max_segment_size(&q->limits, + bvec_phys(bvec) + total, nbytes); struct page *page = bvec->bv_page; /* @@ -588,18 +614,22 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq, sector_t offset) { struct request_queue *q = rq->q; - unsigned int max_sectors; + struct queue_limits *lim = &q->limits; + unsigned int max_sectors, boundary_sectors; + bool is_atomic = rq->cmd_flags & REQ_ATOMIC; if (blk_rq_is_passthrough(rq)) return q->limits.max_hw_sectors; - max_sectors = blk_queue_get_max_sectors(q, req_op(rq)); - if (!q->limits.chunk_sectors || + boundary_sectors = blk_boundary_sectors(lim, is_atomic); + max_sectors = blk_queue_get_max_sectors(rq); + + if (!boundary_sectors || req_op(rq) == REQ_OP_DISCARD || req_op(rq) == REQ_OP_SECURE_ERASE) return max_sectors; return min(max_sectors, - blk_chunk_sectors_left(offset, q->limits.chunk_sectors)); + blk_boundary_sectors_left(offset, boundary_sectors)); } static inline int ll_new_hw_segment(struct request *req, struct bio *bio, @@ -797,6 +827,18 @@ static enum elv_merge blk_try_req_merge(struct request *req, return ELEVATOR_NO_MERGE; } +static bool blk_atomic_write_mergeable_rq_bio(struct request *rq, + struct bio *bio) +{ + return (rq->cmd_flags & REQ_ATOMIC) == (bio->bi_opf & REQ_ATOMIC); +} + +static bool blk_atomic_write_mergeable_rqs(struct request *rq, + struct request *next) +{ + return (rq->cmd_flags & REQ_ATOMIC) == (next->cmd_flags & REQ_ATOMIC); +} + /* * For non-mq, this has to be called with the request spinlock acquired. * For mq with scheduling, the appropriate queue wide lock should be held. @@ -820,6 +862,9 @@ static struct request *attempt_merge(struct request_queue *q, if (req->ioprio != next->ioprio) return NULL; + if (!blk_atomic_write_mergeable_rqs(req, next)) + return NULL; + /* * If we are allowed to merge, then append bio list * from next to rq and release next. merge_requests_fn @@ -951,6 +996,9 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio) if (rq->ioprio != bio_prio(bio)) return false; + if (blk_atomic_write_mergeable_rq_bio(rq, bio) == false) + return false; + return true; } diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 770c0c2b72fa..344f9e503bdb 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -84,28 +84,15 @@ static const char *const blk_queue_flag_name[] = { QUEUE_FLAG_NAME(NOMERGES), QUEUE_FLAG_NAME(SAME_COMP), QUEUE_FLAG_NAME(FAIL_IO), - QUEUE_FLAG_NAME(NONROT), - QUEUE_FLAG_NAME(IO_STAT), QUEUE_FLAG_NAME(NOXMERGES), - QUEUE_FLAG_NAME(ADD_RANDOM), - QUEUE_FLAG_NAME(SYNCHRONOUS), QUEUE_FLAG_NAME(SAME_FORCE), QUEUE_FLAG_NAME(INIT_DONE), - QUEUE_FLAG_NAME(STABLE_WRITES), - QUEUE_FLAG_NAME(POLL), - QUEUE_FLAG_NAME(WC), - QUEUE_FLAG_NAME(FUA), - QUEUE_FLAG_NAME(DAX), QUEUE_FLAG_NAME(STATS), QUEUE_FLAG_NAME(REGISTERED), QUEUE_FLAG_NAME(QUIESCED), - QUEUE_FLAG_NAME(PCI_P2PDMA), - QUEUE_FLAG_NAME(ZONE_RESETALL), QUEUE_FLAG_NAME(RQ_ALLOC_TIME), QUEUE_FLAG_NAME(HCTX_ACTIVE), - QUEUE_FLAG_NAME(NOWAIT), QUEUE_FLAG_NAME(SQ_SCHED), - QUEUE_FLAG_NAME(SKIP_TAGSET_QUIESCE), }; #undef QUEUE_FLAG_NAME diff --git a/block/blk-mq.c b/block/blk-mq.c index 3b4df8e5ac9e..e3c3c0c21b55 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -448,6 +448,10 @@ static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data) if (data->cmd_flags & REQ_NOWAIT) data->flags |= BLK_MQ_REQ_NOWAIT; +retry: + data->ctx = blk_mq_get_ctx(q); + data->hctx = blk_mq_map_queue(q, data->cmd_flags, data->ctx); + if (q->elevator) { /* * All requests use scheduler tags when an I/O scheduler is @@ -469,13 +473,9 @@ static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data) if (ops->limit_depth) ops->limit_depth(data->cmd_flags, data); } - } - -retry: - data->ctx = blk_mq_get_ctx(q); - data->hctx = blk_mq_map_queue(q, data->cmd_flags, data->ctx); - if (!(data->rq_flags & RQF_SCHED_TAGS)) + } else { blk_mq_tag_busy(data->hctx); + } if (data->flags & BLK_MQ_REQ_RESERVED) data->rq_flags |= RQF_RESV; @@ -804,10 +804,8 @@ static void blk_complete_request(struct request *req) if (!bio) return; -#ifdef CONFIG_BLK_DEV_INTEGRITY if (blk_integrity_rq(req) && req_op(req) == REQ_OP_READ) - req->q->integrity.profile->complete_fn(req, total_bytes); -#endif + blk_integrity_complete(req, total_bytes); /* * Upper layers may call blk_crypto_evict_key() anytime after the last @@ -875,11 +873,9 @@ bool blk_update_request(struct request *req, blk_status_t error, if (!req->bio) return false; -#ifdef CONFIG_BLK_DEV_INTEGRITY if (blk_integrity_rq(req) && req_op(req) == REQ_OP_READ && error == BLK_STS_OK) - req->q->integrity.profile->complete_fn(req, nr_bytes); -#endif + blk_integrity_complete(req, nr_bytes); /* * Upper layers may call blk_crypto_evict_key() anytime after the last @@ -1264,10 +1260,9 @@ void blk_mq_start_request(struct request *rq) WRITE_ONCE(rq->state, MQ_RQ_IN_FLIGHT); rq->mq_hctx->tags->rqs[rq->tag] = rq; -#ifdef CONFIG_BLK_DEV_INTEGRITY if (blk_integrity_rq(rq) && req_op(rq) == REQ_OP_WRITE) - q->integrity.profile->prepare_fn(rq); -#endif + blk_integrity_prepare(rq); + if (rq->bio && rq->bio->bi_opf & REQ_POLLED) WRITE_ONCE(rq->bio->bi_cookie, rq->mq_hctx->queue_num); } @@ -2914,6 +2909,17 @@ static void blk_mq_use_cached_rq(struct request *rq, struct blk_plug *plug, INIT_LIST_HEAD(&rq->queuelist); } +static bool bio_unaligned(const struct bio *bio, struct request_queue *q) +{ + unsigned int bs_mask = queue_logical_block_size(q) - 1; + + /* .bi_sector of any zero sized bio need to be initialized */ + if ((bio->bi_iter.bi_size & bs_mask) || + ((bio->bi_iter.bi_sector << SECTOR_SHIFT) & bs_mask)) + return true; + return false; +} + /** * blk_mq_submit_bio - Create and send a request to block device. * @bio: Bio pointer. @@ -2966,6 +2972,15 @@ void blk_mq_submit_bio(struct bio *bio) return; } + /* + * Device reconfiguration may change logical block size, so alignment + * check has to be done with queue usage counter held + */ + if (unlikely(bio_unaligned(bio, q))) { + bio_io_error(bio); + goto queue_exit; + } + if (unlikely(bio_may_exceed_limits(bio, &q->limits))) { bio = __bio_split_to_limits(bio, &q->limits, &nr_segs); if (!bio) @@ -3041,7 +3056,7 @@ queue_exit: blk_status_t blk_insert_cloned_request(struct request *rq) { struct request_queue *q = rq->q; - unsigned int max_sectors = blk_queue_get_max_sectors(q, req_op(rq)); + unsigned int max_sectors = blk_queue_get_max_sectors(rq); unsigned int max_segments = blk_rq_get_max_segments(rq); blk_status_t ret; @@ -4114,6 +4129,12 @@ void blk_mq_release(struct request_queue *q) blk_mq_sysfs_deinit(q); } +static bool blk_mq_can_poll(struct blk_mq_tag_set *set) +{ + return set->nr_maps > HCTX_TYPE_POLL && + set->map[HCTX_TYPE_POLL].nr_queues; +} + struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set, struct queue_limits *lim, void *queuedata) { @@ -4121,7 +4142,13 @@ struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set, struct request_queue *q; int ret; - q = blk_alloc_queue(lim ? lim : &default_lim, set->numa_node); + if (!lim) + lim = &default_lim; + lim->features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT; + if (blk_mq_can_poll(set)) + lim->features |= BLK_FEAT_POLL; + + q = blk_alloc_queue(lim, set->numa_node); if (IS_ERR(q)) return q; q->queuedata = queuedata; @@ -4274,17 +4301,6 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, mutex_unlock(&q->sysfs_lock); } -static void blk_mq_update_poll_flag(struct request_queue *q) -{ - struct blk_mq_tag_set *set = q->tag_set; - - if (set->nr_maps > HCTX_TYPE_POLL && - set->map[HCTX_TYPE_POLL].nr_queues) - blk_queue_flag_set(QUEUE_FLAG_POLL, q); - else - blk_queue_flag_clear(QUEUE_FLAG_POLL, q); -} - int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, struct request_queue *q) { @@ -4312,7 +4328,6 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, q->tag_set = set; q->queue_flags |= QUEUE_FLAG_MQ_DEFAULT; - blk_mq_update_poll_flag(q); INIT_DELAYED_WORK(&q->requeue_work, blk_mq_requeue_work); INIT_LIST_HEAD(&q->flush_list); @@ -4636,13 +4651,15 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr) int ret; unsigned long i; + if (WARN_ON_ONCE(!q->mq_freeze_depth)) + return -EINVAL; + if (!set) return -EINVAL; if (q->nr_requests == nr) return 0; - blk_mq_freeze_queue(q); blk_mq_quiesce_queue(q); ret = 0; @@ -4676,7 +4693,6 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr) } blk_mq_unquiesce_queue(q); - blk_mq_unfreeze_queue(q); return ret; } @@ -4798,8 +4814,10 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, fallback: blk_mq_update_queue_map(set); list_for_each_entry(q, &set->tag_list, tag_set_list) { + struct queue_limits lim; + blk_mq_realloc_hw_ctxs(set, q); - blk_mq_update_poll_flag(q); + if (q->nr_hw_queues != set->nr_hw_queues) { int i = prev_nr_hw_queues; @@ -4811,6 +4829,13 @@ fallback: set->nr_hw_queues = prev_nr_hw_queues; goto fallback; } + lim = queue_limits_start_update(q); + if (blk_mq_can_poll(set)) + lim.features |= BLK_FEAT_POLL; + else + lim.features &= ~BLK_FEAT_POLL; + if (queue_limits_commit_update(q, &lim) < 0) + pr_warn("updating the poll flag failed\n"); blk_mq_map_swqueue(q); } diff --git a/block/blk-settings.c b/block/blk-settings.c index effeb9a639bb..cd8a8eabc9a5 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -6,7 +6,7 @@ #include #include #include -#include +#include #include #include #include @@ -55,7 +55,7 @@ void blk_set_stacking_limits(struct queue_limits *lim) } EXPORT_SYMBOL(blk_set_stacking_limits); -static void blk_apply_bdi_limits(struct backing_dev_info *bdi, +void blk_apply_bdi_limits(struct backing_dev_info *bdi, struct queue_limits *lim) { /* @@ -68,7 +68,7 @@ static void blk_apply_bdi_limits(struct backing_dev_info *bdi, static int blk_validate_zoned_limits(struct queue_limits *lim) { - if (!lim->zoned) { + if (!(lim->features & BLK_FEAT_ZONED)) { if (WARN_ON_ONCE(lim->max_open_zones) || WARN_ON_ONCE(lim->max_active_zones) || WARN_ON_ONCE(lim->zone_write_granularity) || @@ -80,6 +80,14 @@ static int blk_validate_zoned_limits(struct queue_limits *lim) if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_BLK_DEV_ZONED))) return -EINVAL; + /* + * Given that active zones include open zones, the maximum number of + * open zones cannot be larger than the maximum number of active zones. + */ + if (lim->max_active_zones && + lim->max_open_zones > lim->max_active_zones) + return -EINVAL; + if (lim->zone_write_granularity < lim->logical_block_size) lim->zone_write_granularity = lim->logical_block_size; @@ -97,6 +105,120 @@ static int blk_validate_zoned_limits(struct queue_limits *lim) return 0; } +static int blk_validate_integrity_limits(struct queue_limits *lim) +{ + struct blk_integrity *bi = &lim->integrity; + + if (!bi->tuple_size) { + if (bi->csum_type != BLK_INTEGRITY_CSUM_NONE || + bi->tag_size || ((bi->flags & BLK_INTEGRITY_REF_TAG))) { + pr_warn("invalid PI settings.\n"); + return -EINVAL; + } + return 0; + } + + if (!IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY)) { + pr_warn("integrity support disabled.\n"); + return -EINVAL; + } + + if (bi->csum_type == BLK_INTEGRITY_CSUM_NONE && + (bi->flags & BLK_INTEGRITY_REF_TAG)) { + pr_warn("ref tag not support without checksum.\n"); + return -EINVAL; + } + + if (!bi->interval_exp) + bi->interval_exp = ilog2(lim->logical_block_size); + + return 0; +} + +/* + * Returns max guaranteed bytes which we can fit in a bio. + * + * We request that an atomic_write is ITER_UBUF iov_iter (so a single vector), + * so we assume that we can fit in at least PAGE_SIZE in a segment, apart from + * the first and last segments. + */ +static unsigned int blk_queue_max_guaranteed_bio(struct queue_limits *lim) +{ + unsigned int max_segments = min(BIO_MAX_VECS, lim->max_segments); + unsigned int length; + + length = min(max_segments, 2) * lim->logical_block_size; + if (max_segments > 2) + length += (max_segments - 2) * PAGE_SIZE; + + return length; +} + +static void blk_atomic_writes_update_limits(struct queue_limits *lim) +{ + unsigned int unit_limit = min(lim->max_hw_sectors << SECTOR_SHIFT, + blk_queue_max_guaranteed_bio(lim)); + + unit_limit = rounddown_pow_of_two(unit_limit); + + lim->atomic_write_max_sectors = + min(lim->atomic_write_hw_max >> SECTOR_SHIFT, + lim->max_hw_sectors); + lim->atomic_write_unit_min = + min(lim->atomic_write_hw_unit_min, unit_limit); + lim->atomic_write_unit_max = + min(lim->atomic_write_hw_unit_max, unit_limit); + lim->atomic_write_boundary_sectors = + lim->atomic_write_hw_boundary >> SECTOR_SHIFT; +} + +static void blk_validate_atomic_write_limits(struct queue_limits *lim) +{ + unsigned int boundary_sectors; + + if (!lim->atomic_write_hw_max) + goto unsupported; + + boundary_sectors = lim->atomic_write_hw_boundary >> SECTOR_SHIFT; + + if (boundary_sectors) { + /* + * A feature of boundary support is that it disallows bios to + * be merged which would result in a merged request which + * crosses either a chunk sector or atomic write HW boundary, + * even though chunk sectors may be just set for performance. + * For simplicity, disallow atomic writes for a chunk sector + * which is non-zero and smaller than atomic write HW boundary. + * Furthermore, chunk sectors must be a multiple of atomic + * write HW boundary. Otherwise boundary support becomes + * complicated. + * Devices which do not conform to these rules can be dealt + * with if and when they show up. + */ + if (WARN_ON_ONCE(lim->chunk_sectors % boundary_sectors)) + goto unsupported; + + /* + * The boundary size just needs to be a multiple of unit_max + * (and not necessarily a power-of-2), so this following check + * could be relaxed in future. + * Furthermore, if needed, unit_max could even be reduced so + * that it is compliant with a !power-of-2 boundary. + */ + if (!is_power_of_2(boundary_sectors)) + goto unsupported; + } + + blk_atomic_writes_update_limits(lim); + return; + +unsupported: + lim->atomic_write_max_sectors = 0; + lim->atomic_write_boundary_sectors = 0; + lim->atomic_write_unit_min = 0; + lim->atomic_write_unit_max = 0; +} + /* * Check that the limits in lim are valid, initialize defaults for unset * values, and cap values based on others where needed. @@ -105,6 +227,7 @@ static int blk_validate_limits(struct queue_limits *lim) { unsigned int max_hw_sectors; unsigned int logical_block_sectors; + int err; /* * Unless otherwise specified, default to 512 byte logical blocks and a @@ -112,6 +235,10 @@ static int blk_validate_limits(struct queue_limits *lim) */ if (!lim->logical_block_size) lim->logical_block_size = SECTOR_SIZE; + else if (blk_validate_block_size(lim->logical_block_size)) { + pr_warn("Invalid logical block size (%d)\n", lim->logical_block_size); + return -EINVAL; + } if (lim->physical_block_size < lim->logical_block_size) lim->physical_block_size = lim->logical_block_size; @@ -153,6 +280,12 @@ static int blk_validate_limits(struct queue_limits *lim) if (lim->max_user_sectors < PAGE_SIZE / SECTOR_SIZE) return -EINVAL; lim->max_sectors = min(max_hw_sectors, lim->max_user_sectors); + } else if (lim->io_opt > (BLK_DEF_MAX_SECTORS_CAP << SECTOR_SHIFT)) { + lim->max_sectors = + min(max_hw_sectors, lim->io_opt >> SECTOR_SHIFT); + } else if (lim->io_min > (BLK_DEF_MAX_SECTORS_CAP << SECTOR_SHIFT)) { + lim->max_sectors = + min(max_hw_sectors, lim->io_min >> SECTOR_SHIFT); } else { lim->max_sectors = min(max_hw_sectors, BLK_DEF_MAX_SECTORS_CAP); } @@ -220,9 +353,17 @@ static int blk_validate_limits(struct queue_limits *lim) if (lim->alignment_offset) { lim->alignment_offset &= (lim->physical_block_size - 1); - lim->misaligned = 0; + lim->flags &= ~BLK_FLAG_MISALIGNED; } + if (!(lim->features & BLK_FEAT_WRITE_CACHE)) + lim->features &= ~BLK_FEAT_FUA; + + blk_validate_atomic_write_limits(lim); + + err = blk_validate_integrity_limits(lim); + if (err) + return err; return blk_validate_zoned_limits(lim); } @@ -254,15 +395,25 @@ int blk_set_default_limits(struct queue_limits *lim) */ int queue_limits_commit_update(struct request_queue *q, struct queue_limits *lim) - __releases(q->limits_lock) { - int error = blk_validate_limits(lim); + int error; - if (!error) { - q->limits = *lim; - if (q->disk) - blk_apply_bdi_limits(q->disk->bdi, lim); + error = blk_validate_limits(lim); + if (error) + goto out_unlock; + +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + if (q->crypto_profile && lim->integrity.tag_size) { + pr_warn("blk-integrity: Integrity and hardware inline encryption are not supported together.\n"); + error = -EINVAL; + goto out_unlock; } +#endif + + q->limits = *lim; + if (q->disk) + blk_apply_bdi_limits(q->disk->bdi, lim); +out_unlock: mutex_unlock(&q->limits_lock); return error; } @@ -286,204 +437,6 @@ int queue_limits_set(struct request_queue *q, struct queue_limits *lim) } EXPORT_SYMBOL_GPL(queue_limits_set); -/** - * blk_queue_chunk_sectors - set size of the chunk for this queue - * @q: the request queue for the device - * @chunk_sectors: chunk sectors in the usual 512b unit - * - * Description: - * If a driver doesn't want IOs to cross a given chunk size, it can set - * this limit and prevent merging across chunks. Note that the block layer - * must accept a page worth of data at any offset. So if the crossing of - * chunks is a hard limitation in the driver, it must still be prepared - * to split single page bios. - **/ -void blk_queue_chunk_sectors(struct request_queue *q, unsigned int chunk_sectors) -{ - q->limits.chunk_sectors = chunk_sectors; -} -EXPORT_SYMBOL(blk_queue_chunk_sectors); - -/** - * blk_queue_max_discard_sectors - set max sectors for a single discard - * @q: the request queue for the device - * @max_discard_sectors: maximum number of sectors to discard - **/ -void blk_queue_max_discard_sectors(struct request_queue *q, - unsigned int max_discard_sectors) -{ - struct queue_limits *lim = &q->limits; - - lim->max_hw_discard_sectors = max_discard_sectors; - lim->max_discard_sectors = - min(max_discard_sectors, lim->max_user_discard_sectors); -} -EXPORT_SYMBOL(blk_queue_max_discard_sectors); - -/** - * blk_queue_max_secure_erase_sectors - set max sectors for a secure erase - * @q: the request queue for the device - * @max_sectors: maximum number of sectors to secure_erase - **/ -void blk_queue_max_secure_erase_sectors(struct request_queue *q, - unsigned int max_sectors) -{ - q->limits.max_secure_erase_sectors = max_sectors; -} -EXPORT_SYMBOL(blk_queue_max_secure_erase_sectors); - -/** - * blk_queue_max_write_zeroes_sectors - set max sectors for a single - * write zeroes - * @q: the request queue for the device - * @max_write_zeroes_sectors: maximum number of sectors to write per command - **/ -void blk_queue_max_write_zeroes_sectors(struct request_queue *q, - unsigned int max_write_zeroes_sectors) -{ - q->limits.max_write_zeroes_sectors = max_write_zeroes_sectors; -} -EXPORT_SYMBOL(blk_queue_max_write_zeroes_sectors); - -/** - * blk_queue_max_zone_append_sectors - set max sectors for a single zone append - * @q: the request queue for the device - * @max_zone_append_sectors: maximum number of sectors to write per command - * - * Sets the maximum number of sectors allowed for zone append commands. If - * Specifying 0 for @max_zone_append_sectors indicates that the queue does - * not natively support zone append operations and that the block layer must - * emulate these operations using regular writes. - **/ -void blk_queue_max_zone_append_sectors(struct request_queue *q, - unsigned int max_zone_append_sectors) -{ - unsigned int max_sectors = 0; - - if (WARN_ON(!blk_queue_is_zoned(q))) - return; - - if (max_zone_append_sectors) { - max_sectors = min(q->limits.max_hw_sectors, - max_zone_append_sectors); - max_sectors = min(q->limits.chunk_sectors, max_sectors); - - /* - * Signal eventual driver bugs resulting in the max_zone_append - * sectors limit being 0 due to the chunk_sectors limit (zone - * size) not set or the max_hw_sectors limit not set. - */ - WARN_ON_ONCE(!max_sectors); - } - - q->limits.max_zone_append_sectors = max_sectors; -} -EXPORT_SYMBOL_GPL(blk_queue_max_zone_append_sectors); - -/** - * blk_queue_logical_block_size - set logical block size for the queue - * @q: the request queue for the device - * @size: the logical block size, in bytes - * - * Description: - * This should be set to the lowest possible block size that the - * storage device can address. The default of 512 covers most - * hardware. - **/ -void blk_queue_logical_block_size(struct request_queue *q, unsigned int size) -{ - struct queue_limits *limits = &q->limits; - - limits->logical_block_size = size; - - if (limits->discard_granularity < limits->logical_block_size) - limits->discard_granularity = limits->logical_block_size; - - if (limits->physical_block_size < size) - limits->physical_block_size = size; - - if (limits->io_min < limits->physical_block_size) - limits->io_min = limits->physical_block_size; - - limits->max_hw_sectors = - round_down(limits->max_hw_sectors, size >> SECTOR_SHIFT); - limits->max_sectors = - round_down(limits->max_sectors, size >> SECTOR_SHIFT); -} -EXPORT_SYMBOL(blk_queue_logical_block_size); - -/** - * blk_queue_physical_block_size - set physical block size for the queue - * @q: the request queue for the device - * @size: the physical block size, in bytes - * - * Description: - * This should be set to the lowest possible sector size that the - * hardware can operate on without reverting to read-modify-write - * operations. - */ -void blk_queue_physical_block_size(struct request_queue *q, unsigned int size) -{ - q->limits.physical_block_size = size; - - if (q->limits.physical_block_size < q->limits.logical_block_size) - q->limits.physical_block_size = q->limits.logical_block_size; - - if (q->limits.discard_granularity < q->limits.physical_block_size) - q->limits.discard_granularity = q->limits.physical_block_size; - - if (q->limits.io_min < q->limits.physical_block_size) - q->limits.io_min = q->limits.physical_block_size; -} -EXPORT_SYMBOL(blk_queue_physical_block_size); - -/** - * blk_queue_zone_write_granularity - set zone write granularity for the queue - * @q: the request queue for the zoned device - * @size: the zone write granularity size, in bytes - * - * Description: - * This should be set to the lowest possible size allowing to write in - * sequential zones of a zoned block device. - */ -void blk_queue_zone_write_granularity(struct request_queue *q, - unsigned int size) -{ - if (WARN_ON_ONCE(!blk_queue_is_zoned(q))) - return; - - q->limits.zone_write_granularity = size; - - if (q->limits.zone_write_granularity < q->limits.logical_block_size) - q->limits.zone_write_granularity = q->limits.logical_block_size; -} -EXPORT_SYMBOL_GPL(blk_queue_zone_write_granularity); - -/** - * blk_queue_alignment_offset - set physical block alignment offset - * @q: the request queue for the device - * @offset: alignment offset in bytes - * - * Description: - * Some devices are naturally misaligned to compensate for things like - * the legacy DOS partition table 63-sector offset. Low-level drivers - * should call this function for devices whose first sector is not - * naturally aligned. - */ -void blk_queue_alignment_offset(struct request_queue *q, unsigned int offset) -{ - q->limits.alignment_offset = - offset & (q->limits.physical_block_size - 1); - q->limits.misaligned = 0; -} -EXPORT_SYMBOL(blk_queue_alignment_offset); - -void disk_update_readahead(struct gendisk *disk) -{ - blk_apply_bdi_limits(disk->bdi, &disk->queue->limits); -} -EXPORT_SYMBOL_GPL(disk_update_readahead); - /** * blk_limits_io_min - set minimum request size for a device * @limits: the queue limits @@ -507,26 +460,6 @@ void blk_limits_io_min(struct queue_limits *limits, unsigned int min) } EXPORT_SYMBOL(blk_limits_io_min); -/** - * blk_queue_io_min - set minimum request size for the queue - * @q: the request queue for the device - * @min: smallest I/O size in bytes - * - * Description: - * Storage devices may report a granularity or preferred minimum I/O - * size which is the smallest request the device can perform without - * incurring a performance penalty. For disk drives this is often the - * physical block size. For RAID arrays it is often the stripe chunk - * size. A properly aligned multiple of minimum_io_size is the - * preferred request size for workloads where a high number of I/O - * operations is desired. - */ -void blk_queue_io_min(struct request_queue *q, unsigned int min) -{ - blk_limits_io_min(&q->limits, min); -} -EXPORT_SYMBOL(blk_queue_io_min); - /** * blk_limits_io_opt - set optimal request size for a device * @limits: the queue limits @@ -614,6 +547,21 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, { unsigned int top, bottom, alignment, ret = 0; + t->features |= (b->features & BLK_FEAT_INHERIT_MASK); + + /* + * BLK_FEAT_NOWAIT and BLK_FEAT_POLL need to be supported both by the + * stacking driver and all underlying devices. The stacking driver sets + * the flags before stacking the limits, and this will clear the flags + * if any of the underlying devices does not support it. + */ + if (!(b->features & BLK_FEAT_NOWAIT)) + t->features &= ~BLK_FEAT_NOWAIT; + if (!(b->features & BLK_FEAT_POLL)) + t->features &= ~BLK_FEAT_POLL; + + t->flags |= (b->flags & BLK_FLAG_MISALIGNED); + t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors); t->max_user_sectors = min_not_zero(t->max_user_sectors, b->max_user_sectors); @@ -623,7 +571,6 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, b->max_write_zeroes_sectors); t->max_zone_append_sectors = min(queue_limits_max_zone_append_sectors(t), queue_limits_max_zone_append_sectors(b)); - t->bounce = max(t->bounce, b->bounce); t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask, b->seg_boundary_mask); @@ -639,8 +586,6 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, t->max_segment_size = min_not_zero(t->max_segment_size, b->max_segment_size); - t->misaligned |= b->misaligned; - alignment = queue_limit_alignment_offset(b, start); /* Bottom device has different alignment. Check that it is @@ -654,7 +599,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, /* Verify that top and bottom intervals line up */ if (max(top, bottom) % min(top, bottom)) { - t->misaligned = 1; + t->flags |= BLK_FLAG_MISALIGNED; ret = -1; } } @@ -676,42 +621,38 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, /* Physical block size a multiple of the logical block size? */ if (t->physical_block_size & (t->logical_block_size - 1)) { t->physical_block_size = t->logical_block_size; - t->misaligned = 1; + t->flags |= BLK_FLAG_MISALIGNED; ret = -1; } /* Minimum I/O a multiple of the physical block size? */ if (t->io_min & (t->physical_block_size - 1)) { t->io_min = t->physical_block_size; - t->misaligned = 1; + t->flags |= BLK_FLAG_MISALIGNED; ret = -1; } /* Optimal I/O a multiple of the physical block size? */ if (t->io_opt & (t->physical_block_size - 1)) { t->io_opt = 0; - t->misaligned = 1; + t->flags |= BLK_FLAG_MISALIGNED; ret = -1; } /* chunk_sectors a multiple of the physical block size? */ if ((t->chunk_sectors << 9) & (t->physical_block_size - 1)) { t->chunk_sectors = 0; - t->misaligned = 1; + t->flags |= BLK_FLAG_MISALIGNED; ret = -1; } - t->raid_partial_stripes_expensive = - max(t->raid_partial_stripes_expensive, - b->raid_partial_stripes_expensive); - /* Find lowest common alignment_offset */ t->alignment_offset = lcm_not_zero(t->alignment_offset, alignment) % max(t->physical_block_size, t->io_min); /* Verify that new alignment_offset is on a logical block boundary */ if (t->alignment_offset & (t->logical_block_size - 1)) { - t->misaligned = 1; + t->flags |= BLK_FLAG_MISALIGNED; ret = -1; } @@ -723,16 +664,6 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, if (b->discard_granularity) { alignment = queue_limit_discard_alignment(b, start); - if (t->discard_granularity != 0 && - t->discard_alignment != alignment) { - top = t->discard_granularity + t->discard_alignment; - bottom = b->discard_granularity + alignment; - - /* Verify that top and bottom intervals line up */ - if ((max(top, bottom) % min(top, bottom)) != 0) - t->discard_misaligned = 1; - } - t->max_discard_sectors = min_not_zero(t->max_discard_sectors, b->max_discard_sectors); t->max_hw_discard_sectors = min_not_zero(t->max_hw_discard_sectors, @@ -746,8 +677,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, b->max_secure_erase_sectors); t->zone_write_granularity = max(t->zone_write_granularity, b->zone_write_granularity); - t->zoned = max(t->zoned, b->zoned); - if (!t->zoned) { + if (!(t->features & BLK_FEAT_ZONED)) { t->zone_write_granularity = 0; t->max_zone_append_sectors = 0; } @@ -781,21 +711,65 @@ void queue_limits_stack_bdev(struct queue_limits *t, struct block_device *bdev, EXPORT_SYMBOL_GPL(queue_limits_stack_bdev); /** - * blk_queue_update_dma_pad - update pad mask - * @q: the request queue for the device - * @mask: pad mask + * queue_limits_stack_integrity - stack integrity profile + * @t: target queue limits + * @b: base queue limits * - * Update dma pad mask. + * Check if the integrity profile in the @b can be stacked into the + * target @t. Stacking is possible if either: * - * Appending pad buffer to a request modifies the last entry of a - * scatter list such that it includes the pad buffer. - **/ -void blk_queue_update_dma_pad(struct request_queue *q, unsigned int mask) + * a) does not have any integrity information stacked into it yet + * b) the integrity profile in @b is identical to the one in @t + * + * If @b can be stacked into @t, return %true. Else return %false and clear the + * integrity information in @t. + */ +bool queue_limits_stack_integrity(struct queue_limits *t, + struct queue_limits *b) { - if (mask > q->dma_pad_mask) - q->dma_pad_mask = mask; + struct blk_integrity *ti = &t->integrity; + struct blk_integrity *bi = &b->integrity; + + if (!IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY)) + return true; + + if (!ti->tuple_size) { + /* inherit the settings from the first underlying device */ + if (!(ti->flags & BLK_INTEGRITY_STACKED)) { + ti->flags = BLK_INTEGRITY_DEVICE_CAPABLE | + (bi->flags & BLK_INTEGRITY_REF_TAG); + ti->csum_type = bi->csum_type; + ti->tuple_size = bi->tuple_size; + ti->pi_offset = bi->pi_offset; + ti->interval_exp = bi->interval_exp; + ti->tag_size = bi->tag_size; + goto done; + } + if (!bi->tuple_size) + goto done; + } + + if (ti->tuple_size != bi->tuple_size) + goto incompatible; + if (ti->interval_exp != bi->interval_exp) + goto incompatible; + if (ti->tag_size != bi->tag_size) + goto incompatible; + if (ti->csum_type != bi->csum_type) + goto incompatible; + if ((ti->flags & BLK_INTEGRITY_REF_TAG) != + (bi->flags & BLK_INTEGRITY_REF_TAG)) + goto incompatible; + +done: + ti->flags |= BLK_INTEGRITY_STACKED; + return true; + +incompatible: + memset(ti, 0, sizeof(*ti)); + return false; } -EXPORT_SYMBOL(blk_queue_update_dma_pad); +EXPORT_SYMBOL_GPL(queue_limits_stack_integrity); /** * blk_set_queue_depth - tell the block layer about the device queue depth @@ -810,54 +784,11 @@ void blk_set_queue_depth(struct request_queue *q, unsigned int depth) } EXPORT_SYMBOL(blk_set_queue_depth); -/** - * blk_queue_write_cache - configure queue's write cache - * @q: the request queue for the device - * @wc: write back cache on or off - * @fua: device supports FUA writes, if true - * - * Tell the block layer about the write cache of @q. - */ -void blk_queue_write_cache(struct request_queue *q, bool wc, bool fua) -{ - if (wc) { - blk_queue_flag_set(QUEUE_FLAG_HW_WC, q); - blk_queue_flag_set(QUEUE_FLAG_WC, q); - } else { - blk_queue_flag_clear(QUEUE_FLAG_HW_WC, q); - blk_queue_flag_clear(QUEUE_FLAG_WC, q); - } - if (fua) - blk_queue_flag_set(QUEUE_FLAG_FUA, q); - else - blk_queue_flag_clear(QUEUE_FLAG_FUA, q); -} -EXPORT_SYMBOL_GPL(blk_queue_write_cache); - -/** - * disk_set_zoned - inidicate a zoned device - * @disk: gendisk to configure - */ -void disk_set_zoned(struct gendisk *disk) -{ - struct request_queue *q = disk->queue; - - WARN_ON_ONCE(!IS_ENABLED(CONFIG_BLK_DEV_ZONED)); - - /* - * Set the zone write granularity to the device logical block - * size by default. The driver can change this value if needed. - */ - q->limits.zoned = true; - blk_queue_zone_write_granularity(q, queue_logical_block_size(q)); -} -EXPORT_SYMBOL_GPL(disk_set_zoned); - int bdev_alignment_offset(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); - if (q->limits.misaligned) + if (q->limits.flags & BLK_FLAG_MISALIGNED) return -1; if (bdev_is_partition(bdev)) return queue_limit_alignment_offset(&q->limits, diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index f0f9314ab65c..60116d13cb80 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -22,8 +22,8 @@ struct queue_sysfs_entry { struct attribute attr; - ssize_t (*show)(struct request_queue *, char *); - ssize_t (*store)(struct request_queue *, const char *, size_t); + ssize_t (*show)(struct gendisk *disk, char *page); + ssize_t (*store)(struct gendisk *disk, const char *page, size_t count); }; static ssize_t @@ -47,18 +47,18 @@ queue_var_store(unsigned long *var, const char *page, size_t count) return count; } -static ssize_t queue_requests_show(struct request_queue *q, char *page) +static ssize_t queue_requests_show(struct gendisk *disk, char *page) { - return queue_var_show(q->nr_requests, page); + return queue_var_show(disk->queue->nr_requests, page); } static ssize_t -queue_requests_store(struct request_queue *q, const char *page, size_t count) +queue_requests_store(struct gendisk *disk, const char *page, size_t count) { unsigned long nr; int ret, err; - if (!queue_is_mq(q)) + if (!queue_is_mq(disk->queue)) return -EINVAL; ret = queue_var_store(&nr, page, count); @@ -68,111 +68,91 @@ queue_requests_store(struct request_queue *q, const char *page, size_t count) if (nr < BLKDEV_MIN_RQ) nr = BLKDEV_MIN_RQ; - err = blk_mq_update_nr_requests(q, nr); + err = blk_mq_update_nr_requests(disk->queue, nr); if (err) return err; return ret; } -static ssize_t queue_ra_show(struct request_queue *q, char *page) +static ssize_t queue_ra_show(struct gendisk *disk, char *page) { - unsigned long ra_kb; - - if (!q->disk) - return -EINVAL; - ra_kb = q->disk->bdi->ra_pages << (PAGE_SHIFT - 10); - return queue_var_show(ra_kb, page); + return queue_var_show(disk->bdi->ra_pages << (PAGE_SHIFT - 10), page); } static ssize_t -queue_ra_store(struct request_queue *q, const char *page, size_t count) +queue_ra_store(struct gendisk *disk, const char *page, size_t count) { unsigned long ra_kb; ssize_t ret; - if (!q->disk) - return -EINVAL; ret = queue_var_store(&ra_kb, page, count); if (ret < 0) return ret; - q->disk->bdi->ra_pages = ra_kb >> (PAGE_SHIFT - 10); + disk->bdi->ra_pages = ra_kb >> (PAGE_SHIFT - 10); return ret; } -static ssize_t queue_max_sectors_show(struct request_queue *q, char *page) -{ - int max_sectors_kb = queue_max_sectors(q) >> 1; - - return queue_var_show(max_sectors_kb, page); +#define QUEUE_SYSFS_LIMIT_SHOW(_field) \ +static ssize_t queue_##_field##_show(struct gendisk *disk, char *page) \ +{ \ + return queue_var_show(disk->queue->limits._field, page); \ } -static ssize_t queue_max_segments_show(struct request_queue *q, char *page) -{ - return queue_var_show(queue_max_segments(q), page); +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(logical_block_size) +QUEUE_SYSFS_LIMIT_SHOW(physical_block_size) +QUEUE_SYSFS_LIMIT_SHOW(chunk_sectors) +QUEUE_SYSFS_LIMIT_SHOW(io_min) +QUEUE_SYSFS_LIMIT_SHOW(io_opt) +QUEUE_SYSFS_LIMIT_SHOW(discard_granularity) +QUEUE_SYSFS_LIMIT_SHOW(zone_write_granularity) +QUEUE_SYSFS_LIMIT_SHOW(virt_boundary_mask) +QUEUE_SYSFS_LIMIT_SHOW(dma_alignment) +QUEUE_SYSFS_LIMIT_SHOW(max_open_zones) +QUEUE_SYSFS_LIMIT_SHOW(max_active_zones) +QUEUE_SYSFS_LIMIT_SHOW(atomic_write_unit_min) +QUEUE_SYSFS_LIMIT_SHOW(atomic_write_unit_max) + +#define QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(_field) \ +static ssize_t queue_##_field##_show(struct gendisk *disk, char *page) \ +{ \ + return sprintf(page, "%llu\n", \ + (unsigned long long)disk->queue->limits._field << \ + SECTOR_SHIFT); \ } -static ssize_t queue_max_discard_segments_show(struct request_queue *q, - char *page) -{ - return queue_var_show(queue_max_discard_segments(q), page); +QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(max_discard_sectors) +QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(max_hw_discard_sectors) +QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(max_write_zeroes_sectors) +QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(atomic_write_max_sectors) +QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(atomic_write_boundary_sectors) + +#define QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_KB(_field) \ +static ssize_t queue_##_field##_show(struct gendisk *disk, char *page) \ +{ \ + return queue_var_show(disk->queue->limits._field >> 1, page); \ } -static ssize_t queue_max_integrity_segments_show(struct request_queue *q, char *page) -{ - return queue_var_show(q->limits.max_integrity_segments, page); +QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_KB(max_sectors) +QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_KB(max_hw_sectors) + +#define QUEUE_SYSFS_SHOW_CONST(_name, _val) \ +static ssize_t queue_##_name##_show(struct gendisk *disk, char *page) \ +{ \ + return sprintf(page, "%d\n", _val); \ } -static ssize_t queue_max_segment_size_show(struct request_queue *q, char *page) -{ - return queue_var_show(queue_max_segment_size(q), page); -} +/* deprecated fields */ +QUEUE_SYSFS_SHOW_CONST(discard_zeroes_data, 0) +QUEUE_SYSFS_SHOW_CONST(write_same_max, 0) +QUEUE_SYSFS_SHOW_CONST(poll_delay, -1) -static ssize_t queue_logical_block_size_show(struct request_queue *q, char *page) -{ - return queue_var_show(queue_logical_block_size(q), page); -} - -static ssize_t queue_physical_block_size_show(struct request_queue *q, char *page) -{ - return queue_var_show(queue_physical_block_size(q), page); -} - -static ssize_t queue_chunk_sectors_show(struct request_queue *q, char *page) -{ - return queue_var_show(q->limits.chunk_sectors, page); -} - -static ssize_t queue_io_min_show(struct request_queue *q, char *page) -{ - return queue_var_show(queue_io_min(q), page); -} - -static ssize_t queue_io_opt_show(struct request_queue *q, char *page) -{ - return queue_var_show(queue_io_opt(q), page); -} - -static ssize_t queue_discard_granularity_show(struct request_queue *q, char *page) -{ - return queue_var_show(q->limits.discard_granularity, page); -} - -static ssize_t queue_discard_max_hw_show(struct request_queue *q, char *page) -{ - - return sprintf(page, "%llu\n", - (unsigned long long)q->limits.max_hw_discard_sectors << 9); -} - -static ssize_t queue_discard_max_show(struct request_queue *q, char *page) -{ - return sprintf(page, "%llu\n", - (unsigned long long)q->limits.max_discard_sectors << 9); -} - -static ssize_t queue_discard_max_store(struct request_queue *q, - const char *page, size_t count) +static ssize_t queue_max_discard_sectors_store(struct gendisk *disk, + const char *page, size_t count) { unsigned long max_discard_bytes; struct queue_limits lim; @@ -183,54 +163,34 @@ static ssize_t queue_discard_max_store(struct request_queue *q, if (ret < 0) return ret; - if (max_discard_bytes & (q->limits.discard_granularity - 1)) + if (max_discard_bytes & (disk->queue->limits.discard_granularity - 1)) return -EINVAL; if ((max_discard_bytes >> SECTOR_SHIFT) > UINT_MAX) return -EINVAL; - blk_mq_freeze_queue(q); - lim = queue_limits_start_update(q); + lim = queue_limits_start_update(disk->queue); lim.max_user_discard_sectors = max_discard_bytes >> SECTOR_SHIFT; - err = queue_limits_commit_update(q, &lim); - blk_mq_unfreeze_queue(q); - + err = queue_limits_commit_update(disk->queue, &lim); if (err) return err; return ret; } -static ssize_t queue_discard_zeroes_data_show(struct request_queue *q, char *page) -{ - return queue_var_show(0, page); -} - -static ssize_t queue_write_same_max_show(struct request_queue *q, char *page) -{ - return queue_var_show(0, page); -} - -static ssize_t queue_write_zeroes_max_show(struct request_queue *q, char *page) +/* + * For zone append queue_max_zone_append_sectors does not just return the + * underlying queue limits, but actually contains a calculation. Because of + * that we can't simply use QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES here. + */ +static ssize_t queue_zone_append_max_show(struct gendisk *disk, char *page) { return sprintf(page, "%llu\n", - (unsigned long long)q->limits.max_write_zeroes_sectors << 9); -} - -static ssize_t queue_zone_write_granularity_show(struct request_queue *q, - char *page) -{ - return queue_var_show(queue_zone_write_granularity(q), page); -} - -static ssize_t queue_zone_append_max_show(struct request_queue *q, char *page) -{ - unsigned long long max_sectors = queue_max_zone_append_sectors(q); - - return sprintf(page, "%llu\n", max_sectors << SECTOR_SHIFT); + (u64)queue_max_zone_append_sectors(disk->queue) << + SECTOR_SHIFT); } static ssize_t -queue_max_sectors_store(struct request_queue *q, const char *page, size_t count) +queue_max_sectors_store(struct gendisk *disk, const char *page, size_t count) { unsigned long max_sectors_kb; struct queue_limits lim; @@ -241,94 +201,83 @@ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count) if (ret < 0) return ret; - blk_mq_freeze_queue(q); - lim = queue_limits_start_update(q); + lim = queue_limits_start_update(disk->queue); lim.max_user_sectors = max_sectors_kb << 1; - err = queue_limits_commit_update(q, &lim); - blk_mq_unfreeze_queue(q); + err = queue_limits_commit_update(disk->queue, &lim); if (err) return err; return ret; } -static ssize_t queue_max_hw_sectors_show(struct request_queue *q, char *page) +static ssize_t queue_feature_store(struct gendisk *disk, const char *page, + size_t count, blk_features_t feature) { - int max_hw_sectors_kb = queue_max_hw_sectors(q) >> 1; + struct queue_limits lim; + unsigned long val; + ssize_t ret; - return queue_var_show(max_hw_sectors_kb, page); + ret = queue_var_store(&val, page, count); + if (ret < 0) + return ret; + + lim = queue_limits_start_update(disk->queue); + if (val) + lim.features |= feature; + else + lim.features &= ~feature; + ret = queue_limits_commit_update(disk->queue, &lim); + if (ret) + return ret; + return count; } -static ssize_t queue_virt_boundary_mask_show(struct request_queue *q, char *page) -{ - return queue_var_show(q->limits.virt_boundary_mask, page); -} - -static ssize_t queue_dma_alignment_show(struct request_queue *q, char *page) -{ - return queue_var_show(queue_dma_alignment(q), page); -} - -#define QUEUE_SYSFS_BIT_FNS(name, flag, neg) \ -static ssize_t \ -queue_##name##_show(struct request_queue *q, char *page) \ +#define QUEUE_SYSFS_FEATURE(_name, _feature) \ +static ssize_t queue_##_name##_show(struct gendisk *disk, char *page) \ { \ - int bit; \ - bit = test_bit(QUEUE_FLAG_##flag, &q->queue_flags); \ - return queue_var_show(neg ? !bit : bit, page); \ + return sprintf(page, "%u\n", \ + !!(disk->queue->limits.features & _feature)); \ } \ -static ssize_t \ -queue_##name##_store(struct request_queue *q, const char *page, size_t count) \ +static ssize_t queue_##_name##_store(struct gendisk *disk, \ + const char *page, size_t count) \ { \ - unsigned long val; \ - ssize_t ret; \ - ret = queue_var_store(&val, page, count); \ - if (ret < 0) \ - return ret; \ - if (neg) \ - val = !val; \ - \ - if (val) \ - blk_queue_flag_set(QUEUE_FLAG_##flag, q); \ - else \ - blk_queue_flag_clear(QUEUE_FLAG_##flag, q); \ - return ret; \ + return queue_feature_store(disk, page, count, _feature); \ } -QUEUE_SYSFS_BIT_FNS(nonrot, NONROT, 1); -QUEUE_SYSFS_BIT_FNS(random, ADD_RANDOM, 0); -QUEUE_SYSFS_BIT_FNS(iostats, IO_STAT, 0); -QUEUE_SYSFS_BIT_FNS(stable_writes, STABLE_WRITES, 0); -#undef QUEUE_SYSFS_BIT_FNS +QUEUE_SYSFS_FEATURE(rotational, BLK_FEAT_ROTATIONAL) +QUEUE_SYSFS_FEATURE(add_random, BLK_FEAT_ADD_RANDOM) +QUEUE_SYSFS_FEATURE(iostats, BLK_FEAT_IO_STAT) +QUEUE_SYSFS_FEATURE(stable_writes, BLK_FEAT_STABLE_WRITES); -static ssize_t queue_zoned_show(struct request_queue *q, char *page) +#define QUEUE_SYSFS_FEATURE_SHOW(_name, _feature) \ +static ssize_t queue_##_name##_show(struct gendisk *disk, char *page) \ +{ \ + return sprintf(page, "%u\n", \ + !!(disk->queue->limits.features & _feature)); \ +} + +QUEUE_SYSFS_FEATURE_SHOW(poll, BLK_FEAT_POLL); +QUEUE_SYSFS_FEATURE_SHOW(fua, BLK_FEAT_FUA); +QUEUE_SYSFS_FEATURE_SHOW(dax, BLK_FEAT_DAX); + +static ssize_t queue_zoned_show(struct gendisk *disk, char *page) { - if (blk_queue_is_zoned(q)) + if (blk_queue_is_zoned(disk->queue)) return sprintf(page, "host-managed\n"); return sprintf(page, "none\n"); } -static ssize_t queue_nr_zones_show(struct request_queue *q, char *page) +static ssize_t queue_nr_zones_show(struct gendisk *disk, char *page) { - return queue_var_show(disk_nr_zones(q->disk), page); + return queue_var_show(disk_nr_zones(disk), page); } -static ssize_t queue_max_open_zones_show(struct request_queue *q, char *page) +static ssize_t queue_nomerges_show(struct gendisk *disk, char *page) { - return queue_var_show(bdev_max_open_zones(q->disk->part0), page); + return queue_var_show((blk_queue_nomerges(disk->queue) << 1) | + blk_queue_noxmerges(disk->queue), page); } -static ssize_t queue_max_active_zones_show(struct request_queue *q, char *page) -{ - return queue_var_show(bdev_max_active_zones(q->disk->part0), page); -} - -static ssize_t queue_nomerges_show(struct request_queue *q, char *page) -{ - return queue_var_show((blk_queue_nomerges(q) << 1) | - blk_queue_noxmerges(q), page); -} - -static ssize_t queue_nomerges_store(struct request_queue *q, const char *page, +static ssize_t queue_nomerges_store(struct gendisk *disk, const char *page, size_t count) { unsigned long nm; @@ -337,29 +286,30 @@ static ssize_t queue_nomerges_store(struct request_queue *q, const char *page, if (ret < 0) return ret; - blk_queue_flag_clear(QUEUE_FLAG_NOMERGES, q); - blk_queue_flag_clear(QUEUE_FLAG_NOXMERGES, q); + blk_queue_flag_clear(QUEUE_FLAG_NOMERGES, disk->queue); + blk_queue_flag_clear(QUEUE_FLAG_NOXMERGES, disk->queue); if (nm == 2) - blk_queue_flag_set(QUEUE_FLAG_NOMERGES, q); + blk_queue_flag_set(QUEUE_FLAG_NOMERGES, disk->queue); else if (nm) - blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, q); + blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, disk->queue); return ret; } -static ssize_t queue_rq_affinity_show(struct request_queue *q, char *page) +static ssize_t queue_rq_affinity_show(struct gendisk *disk, char *page) { - bool set = test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags); - bool force = test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags); + bool set = test_bit(QUEUE_FLAG_SAME_COMP, &disk->queue->queue_flags); + bool force = test_bit(QUEUE_FLAG_SAME_FORCE, &disk->queue->queue_flags); return queue_var_show(set << force, page); } static ssize_t -queue_rq_affinity_store(struct request_queue *q, const char *page, size_t count) +queue_rq_affinity_store(struct gendisk *disk, const char *page, size_t count) { ssize_t ret = -EINVAL; #ifdef CONFIG_SMP + struct request_queue *q = disk->queue; unsigned long val; ret = queue_var_store(&val, page, count); @@ -380,38 +330,28 @@ queue_rq_affinity_store(struct request_queue *q, const char *page, size_t count) return ret; } -static ssize_t queue_poll_delay_show(struct request_queue *q, char *page) -{ - return sprintf(page, "%d\n", -1); -} - -static ssize_t queue_poll_delay_store(struct request_queue *q, const char *page, +static ssize_t queue_poll_delay_store(struct gendisk *disk, const char *page, size_t count) { return count; } -static ssize_t queue_poll_show(struct request_queue *q, char *page) -{ - return queue_var_show(test_bit(QUEUE_FLAG_POLL, &q->queue_flags), page); -} - -static ssize_t queue_poll_store(struct request_queue *q, const char *page, +static ssize_t queue_poll_store(struct gendisk *disk, const char *page, size_t count) { - if (!test_bit(QUEUE_FLAG_POLL, &q->queue_flags)) + if (!(disk->queue->limits.features & BLK_FEAT_POLL)) return -EINVAL; pr_info_ratelimited("writes to the poll attribute are ignored.\n"); pr_info_ratelimited("please use driver specific parameters instead.\n"); return count; } -static ssize_t queue_io_timeout_show(struct request_queue *q, char *page) +static ssize_t queue_io_timeout_show(struct gendisk *disk, char *page) { - return sprintf(page, "%u\n", jiffies_to_msecs(q->rq_timeout)); + return sprintf(page, "%u\n", jiffies_to_msecs(disk->queue->rq_timeout)); } -static ssize_t queue_io_timeout_store(struct request_queue *q, const char *page, +static ssize_t queue_io_timeout_store(struct gendisk *disk, const char *page, size_t count) { unsigned int val; @@ -421,46 +361,45 @@ static ssize_t queue_io_timeout_store(struct request_queue *q, const char *page, if (err || val == 0) return -EINVAL; - blk_queue_rq_timeout(q, msecs_to_jiffies(val)); + blk_queue_rq_timeout(disk->queue, msecs_to_jiffies(val)); return count; } -static ssize_t queue_wc_show(struct request_queue *q, char *page) +static ssize_t queue_wc_show(struct gendisk *disk, char *page) { - if (test_bit(QUEUE_FLAG_WC, &q->queue_flags)) + if (blk_queue_write_cache(disk->queue)) return sprintf(page, "write back\n"); - return sprintf(page, "write through\n"); } -static ssize_t queue_wc_store(struct request_queue *q, const char *page, +static ssize_t queue_wc_store(struct gendisk *disk, const char *page, size_t count) { + struct queue_limits lim; + bool disable; + int err; + if (!strncmp(page, "write back", 10)) { - if (!test_bit(QUEUE_FLAG_HW_WC, &q->queue_flags)) - return -EINVAL; - blk_queue_flag_set(QUEUE_FLAG_WC, q); + disable = false; } else if (!strncmp(page, "write through", 13) || - !strncmp(page, "none", 4)) { - blk_queue_flag_clear(QUEUE_FLAG_WC, q); + !strncmp(page, "none", 4)) { + disable = true; } else { return -EINVAL; } + lim = queue_limits_start_update(disk->queue); + if (disable) + lim.flags |= BLK_FLAG_WRITE_CACHE_DISABLED; + else + lim.flags &= ~BLK_FLAG_WRITE_CACHE_DISABLED; + err = queue_limits_commit_update(disk->queue, &lim); + if (err) + return err; return count; } -static ssize_t queue_fua_show(struct request_queue *q, char *page) -{ - return sprintf(page, "%u\n", test_bit(QUEUE_FLAG_FUA, &q->queue_flags)); -} - -static ssize_t queue_dax_show(struct request_queue *q, char *page) -{ - return queue_var_show(blk_queue_dax(q), page); -} - #define QUEUE_RO_ENTRY(_prefix, _name) \ static struct queue_sysfs_entry _prefix##_entry = { \ .attr = { .name = _name, .mode = 0444 }, \ @@ -491,12 +430,18 @@ 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_discard_max_hw, "discard_max_hw_bytes"); -QUEUE_RW_ENTRY(queue_discard_max, "discard_max_bytes"); +QUEUE_RO_ENTRY(queue_max_hw_discard_sectors, "discard_max_hw_bytes"); +QUEUE_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, + "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_RO_ENTRY(queue_write_same_max, "write_same_max_bytes"); -QUEUE_RO_ENTRY(queue_write_zeroes_max, "write_zeroes_max_bytes"); +QUEUE_RO_ENTRY(queue_max_write_zeroes_sectors, "write_zeroes_max_bytes"); QUEUE_RO_ENTRY(queue_zone_append_max, "zone_append_max_bytes"); QUEUE_RO_ENTRY(queue_zone_write_granularity, "zone_write_granularity"); @@ -522,9 +467,9 @@ static struct queue_sysfs_entry queue_hw_sector_size_entry = { .show = queue_logical_block_size_show, }; -QUEUE_RW_ENTRY(queue_nonrot, "rotational"); +QUEUE_RW_ENTRY(queue_rotational, "rotational"); QUEUE_RW_ENTRY(queue_iostats, "iostats"); -QUEUE_RW_ENTRY(queue_random, "add_random"); +QUEUE_RW_ENTRY(queue_add_random, "add_random"); QUEUE_RW_ENTRY(queue_stable_writes, "stable_writes"); #ifdef CONFIG_BLK_WBT @@ -541,20 +486,22 @@ static ssize_t queue_var_store64(s64 *var, const char *page) return 0; } -static ssize_t queue_wb_lat_show(struct request_queue *q, char *page) +static ssize_t queue_wb_lat_show(struct gendisk *disk, char *page) { - if (!wbt_rq_qos(q)) + if (!wbt_rq_qos(disk->queue)) return -EINVAL; - if (wbt_disabled(q)) + if (wbt_disabled(disk->queue)) return sprintf(page, "0\n"); - return sprintf(page, "%llu\n", div_u64(wbt_get_min_lat(q), 1000)); + return sprintf(page, "%llu\n", + div_u64(wbt_get_min_lat(disk->queue), 1000)); } -static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page, +static ssize_t queue_wb_lat_store(struct gendisk *disk, const char *page, size_t count) { + struct request_queue *q = disk->queue; struct rq_qos *rqos; ssize_t ret; s64 val; @@ -567,7 +514,7 @@ static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page, rqos = wbt_rq_qos(q); if (!rqos) { - ret = wbt_init(q->disk); + ret = wbt_init(disk); if (ret) return ret; } @@ -585,13 +532,11 @@ static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page, * ends up either enabling or disabling wbt completely. We can't * have IO inflight if that happens. */ - blk_mq_freeze_queue(q); blk_mq_quiesce_queue(q); wbt_set_min_lat(q, val); blk_mq_unquiesce_queue(q); - blk_mq_unfreeze_queue(q); return count; } @@ -615,14 +560,18 @@ static struct attribute *queue_attrs[] = { &queue_io_min_entry.attr, &queue_io_opt_entry.attr, &queue_discard_granularity_entry.attr, - &queue_discard_max_entry.attr, - &queue_discard_max_hw_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_write_zeroes_max_entry.attr, + &queue_max_write_zeroes_sectors_entry.attr, &queue_zone_append_max_entry.attr, &queue_zone_write_granularity_entry.attr, - &queue_nonrot_entry.attr, + &queue_rotational_entry.attr, &queue_zoned_entry.attr, &queue_nr_zones_entry.attr, &queue_max_open_zones_entry.attr, @@ -630,7 +579,7 @@ static struct attribute *queue_attrs[] = { &queue_nomerges_entry.attr, &queue_iostats_entry.attr, &queue_stable_writes_entry.attr, - &queue_random_entry.attr, + &queue_add_random_entry.attr, &queue_poll_entry.attr, &queue_wc_entry.attr, &queue_fua_entry.attr, @@ -699,14 +648,13 @@ 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); - struct request_queue *q = disk->queue; ssize_t res; if (!entry->show) return -EIO; - mutex_lock(&q->sysfs_lock); - res = entry->show(q, page); - mutex_unlock(&q->sysfs_lock); + mutex_lock(&disk->queue->sysfs_lock); + res = entry->show(disk, page); + mutex_unlock(&disk->queue->sysfs_lock); return res; } @@ -722,9 +670,11 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr, if (!entry->store) return -EIO; + blk_mq_freeze_queue(q); mutex_lock(&q->sysfs_lock); - res = entry->store(q, page, length); + res = entry->store(disk, page, length); mutex_unlock(&q->sysfs_lock); + blk_mq_unfreeze_queue(q); return res; } diff --git a/block/blk-throttle.c b/block/blk-throttle.c index c1bf73f8c75d..dc6140fa3de0 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -704,6 +704,9 @@ static unsigned long tg_within_iops_limit(struct throtl_grp *tg, struct bio *bio /* Calc approx time to dispatch */ jiffy_wait = jiffy_elapsed_rnd - jiffy_elapsed; + + /* make sure at least one io can be dispatched after waiting */ + jiffy_wait = max(jiffy_wait, HZ / iops_limit + 1); return jiffy_wait; } diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 64472134dd26..6dfc659d22e2 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_KSWAPD = 4, /* write, from kswapd */ + WBT_SWAP = 4, /* write, from swap_writepage() */ WBT_DISCARD = 8, /* discard */ WBT_NR_BITS = 4, /* number of bits */ @@ -45,7 +45,7 @@ enum wbt_flags { enum { WBT_RWQ_BG = 0, - WBT_RWQ_KSWAPD, + WBT_RWQ_SWAP, WBT_RWQ_DISCARD, WBT_NUM_RWQ, }; @@ -172,8 +172,8 @@ static bool wb_recent_wait(struct rq_wb *rwb) static inline struct rq_wait *get_rq_wait(struct rq_wb *rwb, enum wbt_flags wb_acct) { - if (wb_acct & WBT_KSWAPD) - return &rwb->rq_wait[WBT_RWQ_KSWAPD]; + if (wb_acct & WBT_SWAP) + return &rwb->rq_wait[WBT_RWQ_SWAP]; else if (wb_acct & WBT_DISCARD) return &rwb->rq_wait[WBT_RWQ_DISCARD]; @@ -206,8 +206,8 @@ static void wbt_rqw_done(struct rq_wb *rwb, struct rq_wait *rqw, */ if (wb_acct & WBT_DISCARD) limit = rwb->wb_background; - else if (test_bit(QUEUE_FLAG_WC, &rwb->rqos.disk->queue->queue_flags) && - !wb_recent_wait(rwb)) + else if (blk_queue_write_cache(rwb->rqos.disk->queue) && + !wb_recent_wait(rwb)) limit = 0; else limit = rwb->wb_normal; @@ -528,7 +528,7 @@ static bool close_io(struct rq_wb *rwb) time_before(now, rwb->last_comp + HZ / 10); } -#define REQ_HIPRIO (REQ_SYNC | REQ_META | REQ_PRIO) +#define REQ_HIPRIO (REQ_SYNC | REQ_META | REQ_PRIO | REQ_SWAP) static inline unsigned int get_limit(struct rq_wb *rwb, blk_opf_t opf) { @@ -539,13 +539,13 @@ static inline unsigned int get_limit(struct rq_wb *rwb, blk_opf_t opf) /* * At this point we know it's a buffered write. If this is - * kswapd trying to free memory, or REQ_SYNC is set, then + * swap trying to free memory, or REQ_SYNC is set, then * it's WB_SYNC_ALL writeback, and we'll use the max limit for * that. If the write is marked as a background write, then use * the idle limit, or go to normal if we haven't had competing * IO for a bit. */ - if ((opf & REQ_HIPRIO) || wb_recent_wait(rwb) || current_is_kswapd()) + if ((opf & REQ_HIPRIO) || wb_recent_wait(rwb)) limit = rwb->rq_depth.max_depth; else if ((opf & REQ_BACKGROUND) || close_io(rwb)) { /* @@ -622,8 +622,8 @@ static enum wbt_flags bio_to_wbt_flags(struct rq_wb *rwb, struct bio *bio) if (bio_op(bio) == REQ_OP_READ) { flags = WBT_READ; } else if (wbt_should_throttle(bio)) { - if (current_is_kswapd()) - flags |= WBT_KSWAPD; + if (bio->bi_opf & REQ_SWAP) + flags |= WBT_SWAP; if (bio_op(bio) == REQ_OP_DISCARD) flags |= WBT_DISCARD; flags |= WBT_TRACKED; diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 08d7dfe8bd93..af19296fa50d 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -115,24 +115,6 @@ const char *blk_zone_cond_str(enum blk_zone_cond zone_cond) } EXPORT_SYMBOL_GPL(blk_zone_cond_str); -/** - * bdev_nr_zones - Get number of zones - * @bdev: Target device - * - * Return the total number of zones of a zoned block device. For a block - * device without zone capabilities, the number of zones is always 0. - */ -unsigned int bdev_nr_zones(struct block_device *bdev) -{ - sector_t zone_sectors = bdev_zone_sectors(bdev); - - if (!bdev_is_zoned(bdev)) - return 0; - return (bdev_nr_sectors(bdev) + zone_sectors - 1) >> - ilog2(zone_sectors); -} -EXPORT_SYMBOL_GPL(bdev_nr_zones); - /** * blkdev_report_zones - Get zones information * @bdev: Target block device @@ -168,77 +150,6 @@ int blkdev_report_zones(struct block_device *bdev, sector_t sector, } EXPORT_SYMBOL_GPL(blkdev_report_zones); -static inline unsigned long *blk_alloc_zone_bitmap(int node, - unsigned int nr_zones) -{ - return kcalloc_node(BITS_TO_LONGS(nr_zones), sizeof(unsigned long), - GFP_NOIO, node); -} - -static int blk_zone_need_reset_cb(struct blk_zone *zone, unsigned int idx, - void *data) -{ - /* - * For an all-zones reset, ignore conventional, empty, read-only - * and offline zones. - */ - switch (zone->cond) { - case BLK_ZONE_COND_NOT_WP: - case BLK_ZONE_COND_EMPTY: - case BLK_ZONE_COND_READONLY: - case BLK_ZONE_COND_OFFLINE: - return 0; - default: - set_bit(idx, (unsigned long *)data); - return 0; - } -} - -static int blkdev_zone_reset_all_emulated(struct block_device *bdev) -{ - struct gendisk *disk = bdev->bd_disk; - sector_t capacity = bdev_nr_sectors(bdev); - sector_t zone_sectors = bdev_zone_sectors(bdev); - unsigned long *need_reset; - struct bio *bio = NULL; - sector_t sector = 0; - int ret; - - need_reset = blk_alloc_zone_bitmap(disk->queue->node, disk->nr_zones); - if (!need_reset) - return -ENOMEM; - - ret = disk->fops->report_zones(disk, 0, disk->nr_zones, - blk_zone_need_reset_cb, need_reset); - if (ret < 0) - goto out_free_need_reset; - - ret = 0; - while (sector < capacity) { - if (!test_bit(disk_zone_no(disk, sector), need_reset)) { - sector += zone_sectors; - continue; - } - - bio = blk_next_bio(bio, bdev, 0, REQ_OP_ZONE_RESET | REQ_SYNC, - GFP_KERNEL); - bio->bi_iter.bi_sector = sector; - sector += zone_sectors; - - /* This may take a while, so be nice to others */ - cond_resched(); - } - - if (bio) { - ret = submit_bio_wait(bio); - bio_put(bio); - } - -out_free_need_reset: - kfree(need_reset); - return ret; -} - static int blkdev_zone_reset_all(struct block_device *bdev) { struct bio bio; @@ -265,7 +176,6 @@ static int blkdev_zone_reset_all(struct block_device *bdev) int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op, sector_t sector, sector_t nr_sectors) { - struct request_queue *q = bdev_get_queue(bdev); sector_t zone_sectors = bdev_zone_sectors(bdev); sector_t capacity = bdev_nr_sectors(bdev); sector_t end_sector = sector + nr_sectors; @@ -293,16 +203,11 @@ int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op, return -EINVAL; /* - * In the case of a zone reset operation over all zones, - * REQ_OP_ZONE_RESET_ALL can be used with devices supporting this - * command. For other devices, we emulate this command behavior by - * identifying the zones needing a reset. + * In the case of a zone reset operation over all zones, use + * REQ_OP_ZONE_RESET_ALL. */ - if (op == REQ_OP_ZONE_RESET && sector == 0 && nr_sectors == capacity) { - if (!blk_queue_zone_resetall(q)) - return blkdev_zone_reset_all_emulated(bdev); + if (op == REQ_OP_ZONE_RESET && sector == 0 && nr_sectors == capacity) return blkdev_zone_reset_all(bdev); - } while (sector < end_sector) { bio = blk_next_bio(bio, bdev, 0, op | REQ_SYNC, GFP_KERNEL); @@ -1573,7 +1478,7 @@ void disk_free_zone_resources(struct gendisk *disk) mempool_destroy(disk->zone_wplugs_pool); disk->zone_wplugs_pool = NULL; - kfree(disk->conv_zones_bitmap); + bitmap_free(disk->conv_zones_bitmap); disk->conv_zones_bitmap = NULL; disk->zone_capacity = 0; disk->last_zone_capacity = 0; @@ -1650,8 +1555,22 @@ static int disk_update_zone_resources(struct gendisk *disk, return -ENODEV; } + lim = queue_limits_start_update(q); + + /* + * Some devices can advertize zone resource limits that are larger than + * the number of sequential zones of the zoned block device, e.g. a + * small ZNS namespace. For such case, assume that the zoned device has + * no zone resource limits. + */ + nr_seq_zones = disk->nr_zones - nr_conv_zones; + if (lim.max_open_zones >= nr_seq_zones) + lim.max_open_zones = 0; + if (lim.max_active_zones >= nr_seq_zones) + lim.max_active_zones = 0; + if (!disk->zone_wplugs_pool) - return 0; + goto commit; /* * If the device has no limit on the maximum number of open and active @@ -1660,9 +1579,6 @@ static int disk_update_zone_resources(struct gendisk *disk, * dynamic zone write plug allocation when simultaneously writing to * more zones than the size of the mempool. */ - lim = queue_limits_start_update(q); - - nr_seq_zones = disk->nr_zones - nr_conv_zones; pool_size = max(lim.max_open_zones, lim.max_active_zones); if (!pool_size) pool_size = min(BLK_ZONE_WPLUG_DEFAULT_POOL_SIZE, nr_seq_zones); @@ -1676,6 +1592,7 @@ static int disk_update_zone_resources(struct gendisk *disk, lim.max_open_zones = 0; } +commit: return queue_limits_commit_update(q, &lim); } @@ -1683,7 +1600,6 @@ static int blk_revalidate_conv_zone(struct blk_zone *zone, unsigned int idx, struct blk_revalidate_zone_args *args) { struct gendisk *disk = args->disk; - struct request_queue *q = disk->queue; if (zone->capacity != zone->len) { pr_warn("%s: Invalid conventional zone capacity\n", @@ -1699,7 +1615,7 @@ static int blk_revalidate_conv_zone(struct blk_zone *zone, unsigned int idx, if (!args->conv_zones_bitmap) { args->conv_zones_bitmap = - blk_alloc_zone_bitmap(q->node, args->nr_zones); + bitmap_zalloc(args->nr_zones, GFP_NOIO); if (!args->conv_zones_bitmap) return -ENOMEM; } diff --git a/block/blk.h b/block/blk.h index 189bc25beb50..8e8936e97307 100644 --- a/block/blk.h +++ b/block/blk.h @@ -98,8 +98,8 @@ static inline bool biovec_phys_mergeable(struct request_queue *q, struct bio_vec *vec1, struct bio_vec *vec2) { unsigned long mask = queue_segment_boundary(q); - phys_addr_t addr1 = page_to_phys(vec1->bv_page) + vec1->bv_offset; - phys_addr_t addr2 = page_to_phys(vec2->bv_page) + vec2->bv_offset; + phys_addr_t addr1 = bvec_phys(vec1); + phys_addr_t addr2 = bvec_phys(vec2); /* * Merging adjacent physical pages may not work correctly under KMSAN @@ -181,9 +181,11 @@ static inline unsigned int blk_rq_get_max_segments(struct request *rq) return queue_max_segments(rq->q); } -static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, - enum req_op op) +static inline unsigned int blk_queue_get_max_sectors(struct request *rq) { + struct request_queue *q = rq->q; + enum req_op op = req_op(rq); + if (unlikely(op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE)) return min(q->limits.max_discard_sectors, UINT_MAX >> SECTOR_SHIFT); @@ -191,6 +193,9 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, if (unlikely(op == REQ_OP_WRITE_ZEROES)) return q->limits.max_write_zeroes_sectors; + if (rq->cmd_flags & REQ_ATOMIC) + return q->limits.atomic_write_max_sectors; + return q->limits.max_sectors; } @@ -352,6 +357,8 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio); enum elv_merge blk_try_merge(struct request *rq, struct bio *bio); int blk_set_default_limits(struct queue_limits *lim); +void blk_apply_bdi_limits(struct backing_dev_info *bdi, + struct queue_limits *lim); int blk_dev_init(void); /* @@ -393,7 +400,7 @@ 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.bounce == BLK_BOUNCE_HIGH && + (q->limits.features & BLK_FEAT_BOUNCE_HIGH) && max_low_pfn >= max_pfn; } @@ -673,4 +680,9 @@ int bdev_open(struct block_device *bdev, blk_mode_t mode, void *holder, const struct blk_holder_ops *hops, struct file *bdev_file); 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_prepare(struct request *rq); +void blk_integrity_complete(struct request *rq, unsigned int nr_bytes); + #endif /* BLK_INTERNAL_H */ diff --git a/block/elevator.c b/block/elevator.c index f64ebd726e58..f13d552a32c8 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -709,24 +709,25 @@ static int elevator_change(struct request_queue *q, const char *elevator_name) return ret; } -ssize_t elv_iosched_store(struct request_queue *q, const char *buf, +ssize_t elv_iosched_store(struct gendisk *disk, const char *buf, size_t count) { char elevator_name[ELV_NAME_MAX]; int ret; - if (!elv_support_iosched(q)) + if (!elv_support_iosched(disk->queue)) return count; strscpy(elevator_name, buf, sizeof(elevator_name)); - ret = elevator_change(q, strstrip(elevator_name)); + ret = elevator_change(disk->queue, strstrip(elevator_name)); if (!ret) return count; return ret; } -ssize_t elv_iosched_show(struct request_queue *q, char *name) +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; diff --git a/block/elevator.h b/block/elevator.h index e9a050a96e53..3fe18e1a8692 100644 --- a/block/elevator.h +++ b/block/elevator.h @@ -147,8 +147,8 @@ extern void elv_unregister(struct elevator_type *); /* * io scheduler sysfs switching */ -extern ssize_t elv_iosched_show(struct request_queue *, char *); -extern ssize_t elv_iosched_store(struct request_queue *, const char *, size_t); +ssize_t elv_iosched_show(struct gendisk *disk, char *page); +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 *, diff --git a/block/fops.c b/block/fops.c index 376265935714..9825c1713a49 100644 --- a/block/fops.c +++ b/block/fops.c @@ -34,9 +34,12 @@ static blk_opf_t dio_bio_write_op(struct kiocb *iocb) return opf; } -static bool blkdev_dio_unaligned(struct block_device *bdev, loff_t pos, - struct iov_iter *iter) +static bool blkdev_dio_invalid(struct block_device *bdev, loff_t pos, + struct iov_iter *iter, bool is_atomic) { + if (is_atomic && !generic_atomic_write_valid(iter, pos)) + return true; + return pos & (bdev_logical_block_size(bdev) - 1) || !bdev_iter_is_aligned(bdev, iter); } @@ -72,6 +75,8 @@ 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_ioprio = iocb->ki_ioprio; + if (iocb->ki_flags & IOCB_ATOMIC) + bio.bi_opf |= REQ_ATOMIC; ret = bio_iov_iter_get_pages(&bio, iter); if (unlikely(ret)) @@ -343,6 +348,9 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb, task_io_account_write(bio->bi_iter.bi_size); } + if (iocb->ki_flags & IOCB_ATOMIC) + bio->bi_opf |= REQ_ATOMIC; + if (iocb->ki_flags & IOCB_NOWAIT) bio->bi_opf |= REQ_NOWAIT; @@ -359,12 +367,13 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb, static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host); + bool is_atomic = iocb->ki_flags & IOCB_ATOMIC; unsigned int nr_pages; if (!iov_iter_count(iter)) return 0; - if (blkdev_dio_unaligned(bdev, iocb->ki_pos, iter)) + if (blkdev_dio_invalid(bdev, iocb->ki_pos, iter, is_atomic)) return -EINVAL; nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS + 1); @@ -373,6 +382,8 @@ static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter) return __blkdev_direct_IO_simple(iocb, iter, bdev, nr_pages); return __blkdev_direct_IO_async(iocb, iter, bdev, nr_pages); + } else if (is_atomic) { + return -EINVAL; } return __blkdev_direct_IO(iocb, iter, bdev, bio_max_segs(nr_pages)); } @@ -383,10 +394,11 @@ static int blkdev_iomap_begin(struct inode *inode, loff_t offset, loff_t length, struct block_device *bdev = I_BDEV(inode); loff_t isize = i_size_read(inode); - iomap->bdev = bdev; - iomap->offset = ALIGN_DOWN(offset, bdev_logical_block_size(bdev)); if (offset >= isize) return -EIO; + + iomap->bdev = bdev; + iomap->offset = ALIGN_DOWN(offset, bdev_logical_block_size(bdev)); iomap->type = IOMAP_MAPPED; iomap->addr = iomap->offset; iomap->length = isize - iomap->offset; @@ -612,6 +624,9 @@ static int blkdev_open(struct inode *inode, struct file *filp) if (!bdev) return -ENXIO; + if (bdev_can_atomic_write(bdev) && filp->f_flags & O_DIRECT) + filp->f_mode |= FMODE_CAN_ATOMIC_WRITE; + ret = bdev_open(bdev, mode, filp->private_data, NULL, filp); if (ret) blkdev_put_no_open(bdev); diff --git a/block/genhd.c b/block/genhd.c index 8f1f3c6b4d67..4dc95a463505 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -524,7 +524,7 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk, disk->part0->bd_dev = MKDEV(disk->major, disk->first_minor); } - disk_update_readahead(disk); + blk_apply_bdi_limits(disk->bdi, &disk->queue->limits); disk_add_events(disk); set_bit(GD_ADDED, &disk->state); return 0; diff --git a/block/ioctl.c b/block/ioctl.c index d570e1695896..e8e4a4190f18 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -224,7 +224,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, blk_mode_t mode, goto fail; err = blkdev_issue_zeroout(bdev, start >> 9, len >> 9, GFP_KERNEL, - BLKDEV_ZERO_NOUNMAP); + BLKDEV_ZERO_NOUNMAP | BLKDEV_ZERO_KILLABLE); fail: filemap_invalidate_unlock(bdev->bd_mapping); diff --git a/block/mq-deadline.c b/block/mq-deadline.c index 94eede4fb9eb..acdc28756d9d 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -487,6 +487,20 @@ unlock: return rq; } +/* + * '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(). @@ -503,7 +517,7 @@ 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->async_depth; + data->shallow_depth = dd_to_word_depth(data->hctx, dd->async_depth); } /* Called by blk_mq_update_nr_requests(). */ @@ -513,9 +527,9 @@ static void dd_depth_updated(struct blk_mq_hw_ctx *hctx) struct deadline_data *dd = q->elevator->elevator_data; struct blk_mq_tags *tags = hctx->sched_tags; - dd->async_depth = max(1UL, 3 * q->nr_requests / 4); + dd->async_depth = q->nr_requests; - sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, dd->async_depth); + sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, 1); } /* Called by blk_mq_init_hctx() and blk_mq_init_sched(). */ diff --git a/block/t10-pi.c b/block/t10-pi.c index f4cc91156da1..425e2836f3e1 100644 --- a/block/t10-pi.c +++ b/block/t10-pi.c @@ -11,17 +11,23 @@ #include #include #include +#include "blk.h" -typedef __be16 (csum_fn) (__be16, void *, unsigned int); +struct blk_integrity_iter { + void *prot_buf; + void *data_buf; + sector_t seed; + unsigned int data_size; + unsigned short interval; + const char *disk_name; +}; -static __be16 t10_pi_crc_fn(__be16 crc, void *data, unsigned int len) +static __be16 t10_pi_csum(__be16 csum, void *data, unsigned int len, + unsigned char csum_type) { - return cpu_to_be16(crc_t10dif_update(be16_to_cpu(crc), data, len)); -} - -static __be16 t10_pi_ip_fn(__be16 csum, void *data, unsigned int len) -{ - return (__force __be16)ip_compute_csum(data, len); + if (csum_type == BLK_INTEGRITY_CSUM_IP) + return (__force __be16)ip_compute_csum(data, len); + return cpu_to_be16(crc_t10dif_update(be16_to_cpu(csum), data, len)); } /* @@ -29,48 +35,44 @@ static __be16 t10_pi_ip_fn(__be16 csum, void *data, unsigned int len) * 16 bit app tag, 32 bit reference tag. Type 3 does not define the ref * tag. */ -static blk_status_t t10_pi_generate(struct blk_integrity_iter *iter, - csum_fn *fn, enum t10_dif_type type) +static void t10_pi_generate(struct blk_integrity_iter *iter, + struct blk_integrity *bi) { - u8 offset = iter->pi_offset; + u8 offset = bi->pi_offset; unsigned int i; for (i = 0 ; i < iter->data_size ; i += iter->interval) { struct t10_pi_tuple *pi = iter->prot_buf + offset; - pi->guard_tag = fn(0, iter->data_buf, iter->interval); + pi->guard_tag = t10_pi_csum(0, iter->data_buf, iter->interval, + bi->csum_type); if (offset) - pi->guard_tag = fn(pi->guard_tag, iter->prot_buf, - offset); + pi->guard_tag = t10_pi_csum(pi->guard_tag, + iter->prot_buf, offset, bi->csum_type); pi->app_tag = 0; - if (type == T10_PI_TYPE1_PROTECTION) + if (bi->flags & BLK_INTEGRITY_REF_TAG) pi->ref_tag = cpu_to_be32(lower_32_bits(iter->seed)); else pi->ref_tag = 0; iter->data_buf += iter->interval; - iter->prot_buf += iter->tuple_size; + iter->prot_buf += bi->tuple_size; iter->seed++; } - - return BLK_STS_OK; } static blk_status_t t10_pi_verify(struct blk_integrity_iter *iter, - csum_fn *fn, enum t10_dif_type type) + struct blk_integrity *bi) { - u8 offset = iter->pi_offset; + u8 offset = bi->pi_offset; unsigned int i; - BUG_ON(type == T10_PI_TYPE0_PROTECTION); - for (i = 0 ; i < iter->data_size ; i += iter->interval) { struct t10_pi_tuple *pi = iter->prot_buf + offset; __be16 csum; - if (type == T10_PI_TYPE1_PROTECTION || - type == T10_PI_TYPE2_PROTECTION) { + if (bi->flags & BLK_INTEGRITY_REF_TAG) { if (pi->app_tag == T10_PI_APP_ESCAPE) goto next; @@ -82,15 +84,17 @@ static blk_status_t t10_pi_verify(struct blk_integrity_iter *iter, iter->seed, be32_to_cpu(pi->ref_tag)); return BLK_STS_PROTECTION; } - } else if (type == T10_PI_TYPE3_PROTECTION) { + } else { if (pi->app_tag == T10_PI_APP_ESCAPE && pi->ref_tag == T10_PI_REF_ESCAPE) goto next; } - csum = fn(0, iter->data_buf, iter->interval); + csum = t10_pi_csum(0, iter->data_buf, iter->interval, + bi->csum_type); if (offset) - csum = fn(csum, iter->prot_buf, offset); + csum = t10_pi_csum(csum, iter->prot_buf, offset, + bi->csum_type); if (pi->guard_tag != csum) { pr_err("%s: guard tag error at sector %llu " \ @@ -102,33 +106,13 @@ static blk_status_t t10_pi_verify(struct blk_integrity_iter *iter, next: iter->data_buf += iter->interval; - iter->prot_buf += iter->tuple_size; + iter->prot_buf += bi->tuple_size; iter->seed++; } return BLK_STS_OK; } -static blk_status_t t10_pi_type1_generate_crc(struct blk_integrity_iter *iter) -{ - return t10_pi_generate(iter, t10_pi_crc_fn, T10_PI_TYPE1_PROTECTION); -} - -static blk_status_t t10_pi_type1_generate_ip(struct blk_integrity_iter *iter) -{ - return t10_pi_generate(iter, t10_pi_ip_fn, T10_PI_TYPE1_PROTECTION); -} - -static blk_status_t t10_pi_type1_verify_crc(struct blk_integrity_iter *iter) -{ - return t10_pi_verify(iter, t10_pi_crc_fn, T10_PI_TYPE1_PROTECTION); -} - -static blk_status_t t10_pi_type1_verify_ip(struct blk_integrity_iter *iter) -{ - return t10_pi_verify(iter, t10_pi_ip_fn, T10_PI_TYPE1_PROTECTION); -} - /** * t10_pi_type1_prepare - prepare PI prior submitting request to device * @rq: request with PI that should be prepared @@ -141,7 +125,7 @@ static blk_status_t t10_pi_type1_verify_ip(struct blk_integrity_iter *iter) */ static void t10_pi_type1_prepare(struct request *rq) { - struct blk_integrity *bi = &rq->q->integrity; + struct blk_integrity *bi = &rq->q->limits.integrity; const int tuple_sz = bi->tuple_size; u32 ref_tag = t10_pi_ref_tag(rq); u8 offset = bi->pi_offset; @@ -192,7 +176,7 @@ static void t10_pi_type1_prepare(struct request *rq) */ static void t10_pi_type1_complete(struct request *rq, unsigned int nr_bytes) { - struct blk_integrity *bi = &rq->q->integrity; + struct blk_integrity *bi = &rq->q->limits.integrity; unsigned intervals = nr_bytes >> bi->interval_exp; const int tuple_sz = bi->tuple_size; u32 ref_tag = t10_pi_ref_tag(rq); @@ -225,81 +209,15 @@ static void t10_pi_type1_complete(struct request *rq, unsigned int nr_bytes) } } -static blk_status_t t10_pi_type3_generate_crc(struct blk_integrity_iter *iter) -{ - return t10_pi_generate(iter, t10_pi_crc_fn, T10_PI_TYPE3_PROTECTION); -} - -static blk_status_t t10_pi_type3_generate_ip(struct blk_integrity_iter *iter) -{ - return t10_pi_generate(iter, t10_pi_ip_fn, T10_PI_TYPE3_PROTECTION); -} - -static blk_status_t t10_pi_type3_verify_crc(struct blk_integrity_iter *iter) -{ - return t10_pi_verify(iter, t10_pi_crc_fn, T10_PI_TYPE3_PROTECTION); -} - -static blk_status_t t10_pi_type3_verify_ip(struct blk_integrity_iter *iter) -{ - return t10_pi_verify(iter, t10_pi_ip_fn, T10_PI_TYPE3_PROTECTION); -} - -/* Type 3 does not have a reference tag so no remapping is required. */ -static void t10_pi_type3_prepare(struct request *rq) -{ -} - -/* Type 3 does not have a reference tag so no remapping is required. */ -static void t10_pi_type3_complete(struct request *rq, unsigned int nr_bytes) -{ -} - -const struct blk_integrity_profile t10_pi_type1_crc = { - .name = "T10-DIF-TYPE1-CRC", - .generate_fn = t10_pi_type1_generate_crc, - .verify_fn = t10_pi_type1_verify_crc, - .prepare_fn = t10_pi_type1_prepare, - .complete_fn = t10_pi_type1_complete, -}; -EXPORT_SYMBOL(t10_pi_type1_crc); - -const struct blk_integrity_profile t10_pi_type1_ip = { - .name = "T10-DIF-TYPE1-IP", - .generate_fn = t10_pi_type1_generate_ip, - .verify_fn = t10_pi_type1_verify_ip, - .prepare_fn = t10_pi_type1_prepare, - .complete_fn = t10_pi_type1_complete, -}; -EXPORT_SYMBOL(t10_pi_type1_ip); - -const struct blk_integrity_profile t10_pi_type3_crc = { - .name = "T10-DIF-TYPE3-CRC", - .generate_fn = t10_pi_type3_generate_crc, - .verify_fn = t10_pi_type3_verify_crc, - .prepare_fn = t10_pi_type3_prepare, - .complete_fn = t10_pi_type3_complete, -}; -EXPORT_SYMBOL(t10_pi_type3_crc); - -const struct blk_integrity_profile t10_pi_type3_ip = { - .name = "T10-DIF-TYPE3-IP", - .generate_fn = t10_pi_type3_generate_ip, - .verify_fn = t10_pi_type3_verify_ip, - .prepare_fn = t10_pi_type3_prepare, - .complete_fn = t10_pi_type3_complete, -}; -EXPORT_SYMBOL(t10_pi_type3_ip); - static __be64 ext_pi_crc64(u64 crc, void *data, unsigned int len) { return cpu_to_be64(crc64_rocksoft_update(crc, data, len)); } -static blk_status_t ext_pi_crc64_generate(struct blk_integrity_iter *iter, - enum t10_dif_type type) +static void ext_pi_crc64_generate(struct blk_integrity_iter *iter, + struct blk_integrity *bi) { - u8 offset = iter->pi_offset; + u8 offset = bi->pi_offset; unsigned int i; for (i = 0 ; i < iter->data_size ; i += iter->interval) { @@ -311,17 +229,15 @@ static blk_status_t ext_pi_crc64_generate(struct blk_integrity_iter *iter, iter->prot_buf, offset); pi->app_tag = 0; - if (type == T10_PI_TYPE1_PROTECTION) + if (bi->flags & BLK_INTEGRITY_REF_TAG) put_unaligned_be48(iter->seed, pi->ref_tag); else put_unaligned_be48(0ULL, pi->ref_tag); iter->data_buf += iter->interval; - iter->prot_buf += iter->tuple_size; + iter->prot_buf += bi->tuple_size; iter->seed++; } - - return BLK_STS_OK; } static bool ext_pi_ref_escape(u8 *ref_tag) @@ -332,9 +248,9 @@ static bool ext_pi_ref_escape(u8 *ref_tag) } static blk_status_t ext_pi_crc64_verify(struct blk_integrity_iter *iter, - enum t10_dif_type type) + struct blk_integrity *bi) { - u8 offset = iter->pi_offset; + u8 offset = bi->pi_offset; unsigned int i; for (i = 0; i < iter->data_size; i += iter->interval) { @@ -342,7 +258,7 @@ static blk_status_t ext_pi_crc64_verify(struct blk_integrity_iter *iter, u64 ref, seed; __be64 csum; - if (type == T10_PI_TYPE1_PROTECTION) { + if (bi->flags & BLK_INTEGRITY_REF_TAG) { if (pi->app_tag == T10_PI_APP_ESCAPE) goto next; @@ -353,7 +269,7 @@ static blk_status_t ext_pi_crc64_verify(struct blk_integrity_iter *iter, iter->disk_name, seed, ref); return BLK_STS_PROTECTION; } - } else if (type == T10_PI_TYPE3_PROTECTION) { + } else { if (pi->app_tag == T10_PI_APP_ESCAPE && ext_pi_ref_escape(pi->ref_tag)) goto next; @@ -374,26 +290,16 @@ static blk_status_t ext_pi_crc64_verify(struct blk_integrity_iter *iter, next: iter->data_buf += iter->interval; - iter->prot_buf += iter->tuple_size; + iter->prot_buf += bi->tuple_size; iter->seed++; } return BLK_STS_OK; } -static blk_status_t ext_pi_type1_verify_crc64(struct blk_integrity_iter *iter) -{ - return ext_pi_crc64_verify(iter, T10_PI_TYPE1_PROTECTION); -} - -static blk_status_t ext_pi_type1_generate_crc64(struct blk_integrity_iter *iter) -{ - return ext_pi_crc64_generate(iter, T10_PI_TYPE1_PROTECTION); -} - static void ext_pi_type1_prepare(struct request *rq) { - struct blk_integrity *bi = &rq->q->integrity; + struct blk_integrity *bi = &rq->q->limits.integrity; const int tuple_sz = bi->tuple_size; u64 ref_tag = ext_pi_ref_tag(rq); u8 offset = bi->pi_offset; @@ -433,7 +339,7 @@ static void ext_pi_type1_prepare(struct request *rq) static void ext_pi_type1_complete(struct request *rq, unsigned int nr_bytes) { - struct blk_integrity *bi = &rq->q->integrity; + struct blk_integrity *bi = &rq->q->limits.integrity; unsigned intervals = nr_bytes >> bi->interval_exp; const int tuple_sz = bi->tuple_size; u64 ref_tag = ext_pi_ref_tag(rq); @@ -467,33 +373,105 @@ static void ext_pi_type1_complete(struct request *rq, unsigned int nr_bytes) } } -static blk_status_t ext_pi_type3_verify_crc64(struct blk_integrity_iter *iter) +void blk_integrity_generate(struct bio *bio) { - return ext_pi_crc64_verify(iter, T10_PI_TYPE3_PROTECTION); + struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk); + struct bio_integrity_payload *bip = bio_integrity(bio); + struct blk_integrity_iter iter; + struct bvec_iter bviter; + struct bio_vec bv; + + iter.disk_name = bio->bi_bdev->bd_disk->disk_name; + iter.interval = 1 << bi->interval_exp; + iter.seed = bio->bi_iter.bi_sector; + iter.prot_buf = bvec_virt(bip->bip_vec); + bio_for_each_segment(bv, bio, bviter) { + void *kaddr = bvec_kmap_local(&bv); + + iter.data_buf = kaddr; + iter.data_size = bv.bv_len; + switch (bi->csum_type) { + case BLK_INTEGRITY_CSUM_CRC64: + ext_pi_crc64_generate(&iter, bi); + break; + case BLK_INTEGRITY_CSUM_CRC: + case BLK_INTEGRITY_CSUM_IP: + t10_pi_generate(&iter, bi); + break; + default: + break; + } + kunmap_local(kaddr); + } } -static blk_status_t ext_pi_type3_generate_crc64(struct blk_integrity_iter *iter) +void blk_integrity_verify(struct bio *bio) { - return ext_pi_crc64_generate(iter, T10_PI_TYPE3_PROTECTION); + struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk); + struct bio_integrity_payload *bip = bio_integrity(bio); + struct blk_integrity_iter iter; + struct bvec_iter bviter; + struct bio_vec bv; + + /* + * At the moment verify is called bi_iter has been advanced during split + * and completion, so use the copy created during submission here. + */ + iter.disk_name = bio->bi_bdev->bd_disk->disk_name; + iter.interval = 1 << bi->interval_exp; + iter.seed = bip->bio_iter.bi_sector; + iter.prot_buf = bvec_virt(bip->bip_vec); + __bio_for_each_segment(bv, bio, bviter, bip->bio_iter) { + void *kaddr = bvec_kmap_local(&bv); + blk_status_t ret = BLK_STS_OK; + + iter.data_buf = kaddr; + iter.data_size = bv.bv_len; + switch (bi->csum_type) { + case BLK_INTEGRITY_CSUM_CRC64: + ret = ext_pi_crc64_verify(&iter, bi); + break; + case BLK_INTEGRITY_CSUM_CRC: + case BLK_INTEGRITY_CSUM_IP: + ret = t10_pi_verify(&iter, bi); + break; + default: + break; + } + kunmap_local(kaddr); + + if (ret) { + bio->bi_status = ret; + return; + } + } } -const struct blk_integrity_profile ext_pi_type1_crc64 = { - .name = "EXT-DIF-TYPE1-CRC64", - .generate_fn = ext_pi_type1_generate_crc64, - .verify_fn = ext_pi_type1_verify_crc64, - .prepare_fn = ext_pi_type1_prepare, - .complete_fn = ext_pi_type1_complete, -}; -EXPORT_SYMBOL_GPL(ext_pi_type1_crc64); +void blk_integrity_prepare(struct request *rq) +{ + struct blk_integrity *bi = &rq->q->limits.integrity; -const struct blk_integrity_profile ext_pi_type3_crc64 = { - .name = "EXT-DIF-TYPE3-CRC64", - .generate_fn = ext_pi_type3_generate_crc64, - .verify_fn = ext_pi_type3_verify_crc64, - .prepare_fn = t10_pi_type3_prepare, - .complete_fn = t10_pi_type3_complete, -}; -EXPORT_SYMBOL_GPL(ext_pi_type3_crc64); + if (!(bi->flags & BLK_INTEGRITY_REF_TAG)) + return; + + if (bi->csum_type == BLK_INTEGRITY_CSUM_CRC64) + ext_pi_type1_prepare(rq); + else + t10_pi_type1_prepare(rq); +} + +void blk_integrity_complete(struct request *rq, unsigned int nr_bytes) +{ + struct blk_integrity *bi = &rq->q->limits.integrity; + + if (!(bi->flags & BLK_INTEGRITY_REF_TAG)) + return; + + if (bi->csum_type == BLK_INTEGRITY_CSUM_CRC64) + ext_pi_type1_complete(rq, nr_bytes); + else + t10_pi_type1_complete(rq, nr_bytes); +} MODULE_DESCRIPTION("T10 Protection Information module"); MODULE_LICENSE("GPL"); diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index bb4d30d377ae..67ce756f8dfc 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1024,7 +1024,6 @@ EXPORT_SYMBOL_GPL(ata_scsi_dma_need_drain); int ata_scsi_dev_config(struct scsi_device *sdev, struct queue_limits *lim, struct ata_device *dev) { - struct request_queue *q = sdev->request_queue; int depth = 1; if (!ata_id_has_unload(dev->id)) @@ -1038,7 +1037,7 @@ int ata_scsi_dev_config(struct scsi_device *sdev, struct queue_limits *lim, sdev->sector_size = ATA_SECT_SIZE; /* set DMA padding */ - blk_queue_update_dma_pad(q, ATA_DMA_PAD_SZ - 1); + lim->dma_pad_mask = ATA_DMA_PAD_SZ - 1; /* make room for appending the drain */ lim->max_segments--; diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c index 3cb455a32d92..1b85e8bf4ef9 100644 --- a/drivers/ata/pata_macio.c +++ b/drivers/ata/pata_macio.c @@ -816,7 +816,7 @@ static int pata_macio_device_configure(struct scsi_device *sdev, /* OHare has issues with non cache aligned DMA on some chipsets */ if (priv->kind == controller_ohare) { lim->dma_alignment = 31; - blk_queue_update_dma_pad(sdev->request_queue, 31); + lim->dma_pad_mask = 31; /* Tell the world about it */ ata_dev_info(dev, "OHare alignment limits applied\n"); @@ -831,7 +831,7 @@ static int pata_macio_device_configure(struct scsi_device *sdev, if (priv->kind == controller_sh_ata6 || priv->kind == controller_k2_ata6) { /* Allright these are bad, apply restrictions */ lim->dma_alignment = 15; - blk_queue_update_dma_pad(sdev->request_queue, 15); + lim->dma_pad_mask = 15; /* We enable MWI and hack cache line size directly here, this * is specific to this chipset and not normal values, we happen diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index 5b9d4aaebb81..ed209f4f2798 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -354,6 +354,15 @@ config VIRTIO_BLK This is the virtual block driver for virtio. It can be used with QEMU based VMMs (like KVM or Xen). Say Y or M. +config BLK_DEV_RUST_NULL + tristate "Rust null block driver (Experimental)" + depends on RUST + help + This is the Rust implementation of the null block driver. For now it + is only a minimal stub. + + If unsure, say N. + config BLK_DEV_RBD tristate "Rados block device (RBD)" depends on INET && BLOCK diff --git a/drivers/block/Makefile b/drivers/block/Makefile index 101612cba303..1105a2d4fdcb 100644 --- a/drivers/block/Makefile +++ b/drivers/block/Makefile @@ -9,6 +9,9 @@ # needed for trace events ccflags-y += -I$(src) +obj-$(CONFIG_BLK_DEV_RUST_NULL) += rnull_mod.o +rnull_mod-y := rnull.o + obj-$(CONFIG_MAC_FLOPPY) += swim3.o obj-$(CONFIG_BLK_DEV_SWIM) += swim_mod.o obj-$(CONFIG_BLK_DEV_FD) += floppy.o diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c index a25414228e47..49ced65bef4c 100644 --- a/drivers/block/amiflop.c +++ b/drivers/block/amiflop.c @@ -232,6 +232,7 @@ static DEFINE_MUTEX(amiflop_mutex); static unsigned long int fd_def_df0 = FD_DD_3; /* default for df0 if it doesn't identify */ module_param(fd_def_df0, ulong, 0); +MODULE_DESCRIPTION("Amiga floppy driver"); MODULE_LICENSE("GPL"); /* @@ -1776,10 +1777,13 @@ static const struct blk_mq_ops amiflop_mq_ops = { static int fd_alloc_disk(int drive, int system) { + struct queue_limits lim = { + .features = BLK_FEAT_ROTATIONAL, + }; struct gendisk *disk; int err; - disk = blk_mq_alloc_disk(&unit[drive].tag_set, NULL, NULL); + disk = blk_mq_alloc_disk(&unit[drive].tag_set, &lim, NULL); if (IS_ERR(disk)) return PTR_ERR(disk); diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c index b6dac8cee70f..2028795ec61c 100644 --- a/drivers/block/aoe/aoeblk.c +++ b/drivers/block/aoe/aoeblk.c @@ -337,6 +337,7 @@ aoeblk_gdalloc(void *vp) struct queue_limits lim = { .max_hw_sectors = aoe_maxsectors, .io_opt = SZ_2M, + .features = BLK_FEAT_ROTATIONAL, }; ulong flags; int late = 0; diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c index cacc4ba942a8..4ba98c6654be 100644 --- a/drivers/block/ataflop.c +++ b/drivers/block/ataflop.c @@ -1992,9 +1992,12 @@ static const struct blk_mq_ops ataflop_mq_ops = { static int ataflop_alloc_disk(unsigned int drive, unsigned int type) { + struct queue_limits lim = { + .features = BLK_FEAT_ROTATIONAL, + }; struct gendisk *disk; - disk = blk_mq_alloc_disk(&unit[drive].tag_set, NULL, NULL); + disk = blk_mq_alloc_disk(&unit[drive].tag_set, &lim, NULL); if (IS_ERR(disk)) return PTR_ERR(disk); @@ -2197,4 +2200,5 @@ static void __exit atari_floppy_exit(void) module_init(atari_floppy_init) module_exit(atari_floppy_exit) +MODULE_DESCRIPTION("Atari floppy driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 558d8e670566..2fd1ed101748 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -296,6 +296,7 @@ static int max_part = 1; module_param(max_part, int, 0444); MODULE_PARM_DESC(max_part, "Num Minors to reserve between devices"); +MODULE_DESCRIPTION("Ram backed block device driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS_BLOCKDEV_MAJOR(RAMDISK_MAJOR); MODULE_ALIAS("rd"); @@ -335,6 +336,8 @@ static int brd_alloc(int i) .max_hw_discard_sectors = UINT_MAX, .max_discard_segments = 1, .discard_granularity = PAGE_SIZE, + .features = BLK_FEAT_SYNCHRONOUS | + BLK_FEAT_NOWAIT, }; list_for_each_entry(brd, &brd_devices, brd_list) @@ -366,10 +369,6 @@ static int brd_alloc(int i) strscpy(disk->disk_name, buf, DISK_NAME_LEN); set_capacity(disk, rd_size * 2); - /* Tell the block layer that this is not a rotational device */ - blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue); - blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, disk->queue); - blk_queue_flag_set(QUEUE_FLAG_NOWAIT, disk->queue); err = add_disk(disk); if (err) goto out_cleanup_disk; diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 113b441d4d36..f92673f05c7a 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -2697,6 +2697,9 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig * connect. */ .max_hw_sectors = DRBD_MAX_BIO_SIZE_SAFE >> 8, + .features = BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA | + BLK_FEAT_ROTATIONAL | + BLK_FEAT_STABLE_WRITES, }; device = minor_to_device(minor); @@ -2735,9 +2738,6 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig sprintf(disk->disk_name, "drbd%d", minor); disk->private_data = device; - blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, disk->queue); - blk_queue_write_cache(disk->queue, true, true); - device->md_io.page = alloc_page(GFP_KERNEL); if (!device->md_io.page) goto out_no_io_page; diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 25c9d85667f1..3affb538b989 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -4516,7 +4516,8 @@ static bool floppy_available(int drive) static int floppy_alloc_disk(unsigned int drive, unsigned int type) { struct queue_limits lim = { - .max_hw_sectors = 64, + .max_hw_sectors = 64, + .features = BLK_FEAT_ROTATIONAL, }; struct gendisk *disk; @@ -5016,6 +5017,7 @@ module_param(floppy, charp, 0); module_param(FLOPPY_IRQ, int, 0); module_param(FLOPPY_DMA, int, 0); MODULE_AUTHOR("Alain L. Knaff"); +MODULE_DESCRIPTION("Normal floppy disk support"); MODULE_LICENSE("GPL"); /* This doesn't actually get used other than for module information */ diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 1153721bc7c2..78a7bb28defe 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -211,13 +211,10 @@ static void __loop_update_dio(struct loop_device *lo, bool dio) if (lo->lo_state == Lo_bound) blk_mq_freeze_queue(lo->lo_queue); lo->use_dio = use_dio; - if (use_dio) { - blk_queue_flag_clear(QUEUE_FLAG_NOMERGES, lo->lo_queue); + if (use_dio) lo->lo_flags |= LO_FLAGS_DIRECT_IO; - } else { - blk_queue_flag_set(QUEUE_FLAG_NOMERGES, lo->lo_queue); + else lo->lo_flags &= ~LO_FLAGS_DIRECT_IO; - } if (lo->lo_state == Lo_bound) blk_mq_unfreeze_queue(lo->lo_queue); } @@ -939,24 +936,6 @@ static void loop_free_idle_workers_timer(struct timer_list *timer) return loop_free_idle_workers(lo, false); } -static void loop_update_rotational(struct loop_device *lo) -{ - struct file *file = lo->lo_backing_file; - struct inode *file_inode = file->f_mapping->host; - struct block_device *file_bdev = file_inode->i_sb->s_bdev; - struct request_queue *q = lo->lo_queue; - bool nonrot = true; - - /* not all filesystems (e.g. tmpfs) have a sb->s_bdev */ - if (file_bdev) - nonrot = bdev_nonrot(file_bdev); - - if (nonrot) - blk_queue_flag_set(QUEUE_FLAG_NONROT, q); - else - blk_queue_flag_clear(QUEUE_FLAG_NONROT, q); -} - /** * loop_set_status_from_info - configure device from loop_info * @lo: struct loop_device to configure @@ -998,17 +977,40 @@ loop_set_status_from_info(struct loop_device *lo, return 0; } -static int loop_reconfigure_limits(struct loop_device *lo, unsigned short bsize, - bool update_discard_settings) +static unsigned short loop_default_blocksize(struct loop_device *lo, + struct block_device *backing_bdev) { + /* In case of direct I/O, match underlying block size */ + if ((lo->lo_backing_file->f_flags & O_DIRECT) && backing_bdev) + return bdev_logical_block_size(backing_bdev); + return SECTOR_SIZE; +} + +static int loop_reconfigure_limits(struct loop_device *lo, unsigned short bsize) +{ + struct file *file = lo->lo_backing_file; + struct inode *inode = file->f_mapping->host; + struct block_device *backing_bdev = NULL; struct queue_limits lim; + if (S_ISBLK(inode->i_mode)) + backing_bdev = I_BDEV(inode); + else if (inode->i_sb->s_bdev) + backing_bdev = inode->i_sb->s_bdev; + + if (!bsize) + bsize = loop_default_blocksize(lo, backing_bdev); + lim = queue_limits_start_update(lo->lo_queue); lim.logical_block_size = bsize; lim.physical_block_size = bsize; lim.io_min = bsize; - if (update_discard_settings) - loop_config_discard(lo, &lim); + lim.features &= ~(BLK_FEAT_WRITE_CACHE | BLK_FEAT_ROTATIONAL); + if (file->f_op->fsync && !(lo->lo_flags & LO_FLAGS_READ_ONLY)) + lim.features |= BLK_FEAT_WRITE_CACHE; + if (backing_bdev && !bdev_nonrot(backing_bdev)) + lim.features |= BLK_FEAT_ROTATIONAL; + loop_config_discard(lo, &lim); return queue_limits_commit_update(lo->lo_queue, &lim); } @@ -1017,12 +1019,10 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode, const struct loop_config *config) { struct file *file = fget(config->fd); - struct inode *inode; struct address_space *mapping; int error; loff_t size; bool partscan; - unsigned short bsize; bool is_loop; if (!file) @@ -1055,19 +1055,12 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode, goto out_unlock; mapping = file->f_mapping; - inode = mapping->host; if ((config->info.lo_flags & ~LOOP_CONFIGURE_SETTABLE_FLAGS) != 0) { error = -EINVAL; goto out_unlock; } - if (config->block_size) { - error = blk_validate_block_size(config->block_size); - if (error) - goto out_unlock; - } - error = loop_set_status_from_info(lo, &config->info); if (error) goto out_unlock; @@ -1098,22 +1091,10 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode, lo->old_gfp_mask = mapping_gfp_mask(mapping); mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS)); - if (!(lo->lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync) - blk_queue_write_cache(lo->lo_queue, true, false); - - if (config->block_size) - bsize = config->block_size; - else if ((lo->lo_backing_file->f_flags & O_DIRECT) && inode->i_sb->s_bdev) - /* In case of direct I/O, match underlying block size */ - bsize = bdev_logical_block_size(inode->i_sb->s_bdev); - else - bsize = 512; - - error = loop_reconfigure_limits(lo, bsize, true); - if (WARN_ON_ONCE(error)) + error = loop_reconfigure_limits(lo, config->block_size); + if (error) goto out_unlock; - loop_update_rotational(lo); loop_update_dio(lo); loop_sysfs_init(lo); @@ -1154,22 +1135,12 @@ out_putf: return error; } -static void __loop_clr_fd(struct loop_device *lo, bool release) +static void __loop_clr_fd(struct loop_device *lo) { + struct queue_limits lim; struct file *filp; gfp_t gfp = lo->old_gfp_mask; - if (test_bit(QUEUE_FLAG_WC, &lo->lo_queue->queue_flags)) - blk_queue_write_cache(lo->lo_queue, false, false); - - /* - * Freeze the request queue when unbinding on a live file descriptor and - * thus an open device. When called from ->release we are guaranteed - * that there is no I/O in progress already. - */ - if (!release) - blk_mq_freeze_queue(lo->lo_queue); - spin_lock_irq(&lo->lo_lock); filp = lo->lo_backing_file; lo->lo_backing_file = NULL; @@ -1179,7 +1150,14 @@ static void __loop_clr_fd(struct loop_device *lo, bool release) lo->lo_offset = 0; lo->lo_sizelimit = 0; memset(lo->lo_file_name, 0, LO_NAME_SIZE); - loop_reconfigure_limits(lo, 512, false); + + /* reset the block size to the default */ + lim = queue_limits_start_update(lo->lo_queue); + lim.logical_block_size = SECTOR_SIZE; + lim.physical_block_size = SECTOR_SIZE; + lim.io_min = SECTOR_SIZE; + queue_limits_commit_update(lo->lo_queue, &lim); + invalidate_disk(lo->lo_disk); loop_sysfs_exit(lo); /* let user-space know about this change */ @@ -1187,8 +1165,6 @@ static void __loop_clr_fd(struct loop_device *lo, bool release) mapping_set_gfp_mask(filp->f_mapping, gfp); /* This is safe: open() is still holding a reference. */ module_put(THIS_MODULE); - if (!release) - blk_mq_unfreeze_queue(lo->lo_queue); disk_force_media_change(lo->lo_disk); @@ -1203,11 +1179,7 @@ static void __loop_clr_fd(struct loop_device *lo, bool release) * must be at least one and it can only become zero when the * current holder is released. */ - if (!release) - mutex_lock(&lo->lo_disk->open_mutex); err = bdev_disk_changed(lo->lo_disk, false); - if (!release) - mutex_unlock(&lo->lo_disk->open_mutex); if (err) pr_warn("%s: partition scan of loop%d failed (rc=%d)\n", __func__, lo->lo_number, err); @@ -1256,24 +1228,16 @@ static int loop_clr_fd(struct loop_device *lo) return -ENXIO; } /* - * If we've explicitly asked to tear down the loop device, - * and it has an elevated reference count, set it for auto-teardown when - * the last reference goes away. This stops $!~#$@ udev from - * preventing teardown because it decided that it needs to run blkid on - * the loopback device whenever they appear. xfstests is notorious for - * failing tests because blkid via udev races with a losetup - * /do something like mkfs/losetup -d causing the losetup -d - * command to fail with EBUSY. + * Mark the device for removing the backing device on last close. + * If we are the only opener, also switch the state to roundown here to + * prevent new openers from coming in. */ - if (disk_openers(lo->lo_disk) > 1) { - lo->lo_flags |= LO_FLAGS_AUTOCLEAR; - loop_global_unlock(lo, true); - return 0; - } - lo->lo_state = Lo_rundown; + + lo->lo_flags |= LO_FLAGS_AUTOCLEAR; + if (disk_openers(lo->lo_disk) == 1) + lo->lo_state = Lo_rundown; loop_global_unlock(lo, true); - __loop_clr_fd(lo, false); return 0; } @@ -1500,10 +1464,6 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg) if (lo->lo_state != Lo_bound) return -ENXIO; - err = blk_validate_block_size(arg); - if (err) - return err; - if (lo->lo_queue->limits.logical_block_size == arg) return 0; @@ -1511,7 +1471,7 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg) invalidate_bdev(lo->lo_device); blk_mq_freeze_queue(lo->lo_queue); - err = loop_reconfigure_limits(lo, arg, false); + err = loop_reconfigure_limits(lo, arg); loop_update_dio(lo); blk_mq_unfreeze_queue(lo->lo_queue); @@ -1740,25 +1700,43 @@ static int lo_compat_ioctl(struct block_device *bdev, blk_mode_t mode, } #endif +static int lo_open(struct gendisk *disk, blk_mode_t mode) +{ + struct loop_device *lo = disk->private_data; + int err; + + err = mutex_lock_killable(&lo->lo_mutex); + if (err) + return err; + + if (lo->lo_state == Lo_deleting || lo->lo_state == Lo_rundown) + err = -ENXIO; + mutex_unlock(&lo->lo_mutex); + return err; +} + static void lo_release(struct gendisk *disk) { struct loop_device *lo = disk->private_data; + bool need_clear = false; if (disk_openers(disk) > 0) return; + /* + * Clear the backing device information if this is the last close of + * a device that's been marked for auto clear, or on which LOOP_CLR_FD + * has been called. + */ mutex_lock(&lo->lo_mutex); - if (lo->lo_state == Lo_bound && (lo->lo_flags & LO_FLAGS_AUTOCLEAR)) { + if (lo->lo_state == Lo_bound && (lo->lo_flags & LO_FLAGS_AUTOCLEAR)) lo->lo_state = Lo_rundown; - mutex_unlock(&lo->lo_mutex); - /* - * In autoclear mode, stop the loop thread - * and remove configuration after last close. - */ - __loop_clr_fd(lo, true); - return; - } + + need_clear = (lo->lo_state == Lo_rundown); mutex_unlock(&lo->lo_mutex); + + if (need_clear) + __loop_clr_fd(lo); } static void lo_free_disk(struct gendisk *disk) @@ -1775,6 +1753,7 @@ static void lo_free_disk(struct gendisk *disk) static const struct block_device_operations lo_fops = { .owner = THIS_MODULE, + .open = lo_open, .release = lo_release, .ioctl = lo_ioctl, #ifdef CONFIG_COMPAT @@ -1853,6 +1832,7 @@ static const struct kernel_param_ops loop_hw_qdepth_param_ops = { device_param_cb(hw_queue_depth, &loop_hw_qdepth_param_ops, &hw_queue_depth, 0444); MODULE_PARM_DESC(hw_queue_depth, "Queue depth for each hardware queue. Default: " __stringify(LOOP_DEFAULT_HW_Q_DEPTH)); +MODULE_DESCRIPTION("Loopback device support"); MODULE_LICENSE("GPL"); MODULE_ALIAS_BLOCKDEV_MAJOR(LOOP_MAJOR); @@ -2059,14 +2039,6 @@ static int loop_add(int i) } lo->lo_queue = lo->lo_disk->queue; - /* - * By default, we do buffer IO, so it doesn't make sense to enable - * merge because the I/O submitted to backing file is handled page by - * page. For directio mode, merge does help to dispatch bigger request - * to underlayer disk. We will enable merge once directio is enabled. - */ - blk_queue_flag_set(QUEUE_FLAG_NOMERGES, lo->lo_queue); - /* * Disable partition scanning by default. The in-kernel partition * scanning can be requested individually per-device during its diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 43a187609ef7..c6ef0546ffc9 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -3485,8 +3485,6 @@ skip_create_disk: goto start_service_thread; /* Set device limits. */ - blk_queue_flag_set(QUEUE_FLAG_NONROT, dd->queue); - blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, dd->queue); dma_set_max_seg_size(&dd->pdev->dev, 0x400000); /* Set the capacity of the device in 512 byte sectors. */ diff --git a/drivers/block/n64cart.c b/drivers/block/n64cart.c index 27b2187e7a6d..b9fdeff31caf 100644 --- a/drivers/block/n64cart.c +++ b/drivers/block/n64cart.c @@ -150,8 +150,6 @@ static int __init n64cart_probe(struct platform_device *pdev) set_capacity(disk, size >> SECTOR_SHIFT); set_disk_ro(disk, 1); - blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue); - err = add_disk(disk); if (err) goto out_cleanup_disk; diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index b87aa80a46dd..41a90150b501 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -342,6 +342,14 @@ static int __nbd_set_size(struct nbd_device *nbd, loff_t bytesize, lim.max_hw_discard_sectors = UINT_MAX; else lim.max_hw_discard_sectors = 0; + if (!(nbd->config->flags & NBD_FLAG_SEND_FLUSH)) { + lim.features &= ~(BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA); + } else if (nbd->config->flags & NBD_FLAG_SEND_FUA) { + lim.features |= BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA; + } else { + lim.features |= BLK_FEAT_WRITE_CACHE; + lim.features &= ~BLK_FEAT_FUA; + } lim.logical_block_size = blksize; lim.physical_block_size = blksize; error = queue_limits_commit_update(nbd->disk->queue, &lim); @@ -1279,19 +1287,10 @@ static void nbd_bdev_reset(struct nbd_device *nbd) static void nbd_parse_flags(struct nbd_device *nbd) { - struct nbd_config *config = nbd->config; - if (config->flags & NBD_FLAG_READ_ONLY) + if (nbd->config->flags & NBD_FLAG_READ_ONLY) set_disk_ro(nbd->disk, true); else set_disk_ro(nbd->disk, false); - if (config->flags & NBD_FLAG_SEND_FLUSH) { - if (config->flags & NBD_FLAG_SEND_FUA) - blk_queue_write_cache(nbd->disk->queue, true, true); - else - blk_queue_write_cache(nbd->disk->queue, true, false); - } - else - blk_queue_write_cache(nbd->disk->queue, false, false); } static void send_disconnects(struct nbd_device *nbd) @@ -1801,7 +1800,7 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs) { struct queue_limits lim = { .max_hw_sectors = 65536, - .max_user_sectors = 256, + .io_opt = 256 << SECTOR_SHIFT, .max_segments = USHRT_MAX, .max_segment_size = UINT_MAX, }; @@ -1861,11 +1860,6 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs) goto out_err_disk; } - /* - * Tell the block layer that we are not a rotational device - */ - blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue); - mutex_init(&nbd->config_lock); refcount_set(&nbd->config_refs, 0); /* diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index 75f189e42f88..2f0431e42c49 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -77,7 +77,7 @@ enum { NULL_IRQ_TIMER = 2, }; -static bool g_virt_boundary = false; +static bool g_virt_boundary; module_param_named(virt_boundary, g_virt_boundary, bool, 0444); MODULE_PARM_DESC(virt_boundary, "Require a virtual boundary for the device. Default: False"); @@ -227,7 +227,7 @@ MODULE_PARM_DESC(mbps, "Cache size in MiB for memory-backed device. Default: 0 ( static bool g_fua = true; module_param_named(fua, g_fua, bool, 0444); -MODULE_PARM_DESC(zoned, "Enable/disable FUA support when cache_size is used. Default: true"); +MODULE_PARM_DESC(fua, "Enable/disable FUA support when cache_size is used. Default: true"); static unsigned int g_mbps; module_param_named(mbps, g_mbps, uint, 0444); @@ -262,6 +262,10 @@ module_param_named(zone_append_max_sectors, g_zone_append_max_sectors, int, 0444 MODULE_PARM_DESC(zone_append_max_sectors, "Maximum size of a zone append command (in 512B sectors). Specify 0 for zone append emulation"); +static bool g_zone_full; +module_param_named(zone_full, g_zone_full, bool, S_IRUGO); +MODULE_PARM_DESC(zone_full, "Initialize the sequential write required zones of a zoned device to be full. Default: false"); + static struct nullb_device *null_alloc_dev(void); static void null_free_dev(struct nullb_device *dev); static void null_del_dev(struct nullb *nullb); @@ -458,6 +462,7 @@ NULLB_DEVICE_ATTR(zone_nr_conv, uint, NULL); NULLB_DEVICE_ATTR(zone_max_open, uint, NULL); NULLB_DEVICE_ATTR(zone_max_active, uint, NULL); NULLB_DEVICE_ATTR(zone_append_max_sectors, uint, NULL); +NULLB_DEVICE_ATTR(zone_full, bool, NULL); NULLB_DEVICE_ATTR(virt_boundary, bool, NULL); NULLB_DEVICE_ATTR(no_sched, bool, NULL); NULLB_DEVICE_ATTR(shared_tags, bool, NULL); @@ -610,6 +615,7 @@ static struct configfs_attribute *nullb_device_attrs[] = { &nullb_device_attr_zone_append_max_sectors, &nullb_device_attr_zone_readonly, &nullb_device_attr_zone_offline, + &nullb_device_attr_zone_full, &nullb_device_attr_virt_boundary, &nullb_device_attr_no_sched, &nullb_device_attr_shared_tags, @@ -700,7 +706,7 @@ static ssize_t memb_group_features_show(struct config_item *item, char *page) "shared_tags,size,submit_queues,use_per_node_hctx," "virt_boundary,zoned,zone_capacity,zone_max_active," "zone_max_open,zone_nr_conv,zone_offline,zone_readonly," - "zone_size,zone_append_max_sectors\n"); + "zone_size,zone_append_max_sectors,zone_full\n"); } CONFIGFS_ATTR_RO(memb_group_, features); @@ -781,6 +787,7 @@ static struct nullb_device *null_alloc_dev(void) dev->zone_max_open = g_zone_max_open; dev->zone_max_active = g_zone_max_active; dev->zone_append_max_sectors = g_zone_append_max_sectors; + dev->zone_full = g_zone_full; dev->virt_boundary = g_virt_boundary; dev->no_sched = g_no_sched; dev->shared_tags = g_shared_tags; @@ -1824,9 +1831,6 @@ static int null_validate_conf(struct nullb_device *dev) dev->queue_mode = NULL_Q_MQ; } - if (blk_validate_block_size(dev->blocksize)) - return -EINVAL; - if (dev->use_per_node_hctx) { if (dev->submit_queues != nr_online_nodes) dev->submit_queues = nr_online_nodes; @@ -1928,6 +1932,13 @@ static int null_add_dev(struct nullb_device *dev) goto out_cleanup_tags; } + if (dev->cache_size > 0) { + set_bit(NULLB_DEV_FL_CACHE, &nullb->dev->flags); + lim.features |= BLK_FEAT_WRITE_CACHE; + if (dev->fua) + lim.features |= BLK_FEAT_FUA; + } + nullb->disk = blk_mq_alloc_disk(nullb->tag_set, &lim, nullb); if (IS_ERR(nullb->disk)) { rv = PTR_ERR(nullb->disk); @@ -1940,13 +1951,7 @@ static int null_add_dev(struct nullb_device *dev) nullb_setup_bwtimer(nullb); } - if (dev->cache_size > 0) { - set_bit(NULLB_DEV_FL_CACHE, &nullb->dev->flags); - blk_queue_write_cache(nullb->q, true, dev->fua); - } - nullb->q->queuedata = nullb; - blk_queue_flag_set(QUEUE_FLAG_NONROT, nullb->q); rv = ida_alloc(&nullb_indexes, GFP_KERNEL); if (rv < 0) diff --git a/drivers/block/null_blk/null_blk.h b/drivers/block/null_blk/null_blk.h index 3234e6c85eed..a7bb32f73ec3 100644 --- a/drivers/block/null_blk/null_blk.h +++ b/drivers/block/null_blk/null_blk.h @@ -101,6 +101,7 @@ struct nullb_device { bool memory_backed; /* if data is stored in memory */ bool discard; /* if support discard */ bool zoned; /* if device is zoned */ + bool zone_full; /* Initialize zones to be full */ bool virt_boundary; /* virtual boundary on/off for the device */ bool no_sched; /* no IO scheduler for the device */ bool shared_tags; /* share tag set between devices for blk-mq */ diff --git a/drivers/block/null_blk/zoned.c b/drivers/block/null_blk/zoned.c index f118d304f310..9bc768b2ca56 100644 --- a/drivers/block/null_blk/zoned.c +++ b/drivers/block/null_blk/zoned.c @@ -145,7 +145,7 @@ int null_init_zoned_dev(struct nullb_device *dev, zone = &dev->zones[i]; null_init_zone_lock(dev, zone); - zone->start = zone->wp = sector; + zone->start = sector; if (zone->start + dev->zone_size_sects > dev_capacity_sects) zone->len = dev_capacity_sects - zone->start; else @@ -153,12 +153,18 @@ int null_init_zoned_dev(struct nullb_device *dev, zone->capacity = min_t(sector_t, zone->len, zone_capacity_sects); zone->type = BLK_ZONE_TYPE_SEQWRITE_REQ; - zone->cond = BLK_ZONE_COND_EMPTY; + if (dev->zone_full) { + zone->cond = BLK_ZONE_COND_FULL; + zone->wp = zone->start + zone->capacity; + } else{ + zone->cond = BLK_ZONE_COND_EMPTY; + zone->wp = zone->start; + } sector += dev->zone_size_sects; } - lim->zoned = true; + lim->features |= BLK_FEAT_ZONED; lim->chunk_sectors = dev->zone_size_sects; lim->max_zone_append_sectors = dev->zone_append_max_sectors; lim->max_open_zones = dev->zone_max_open; @@ -171,9 +177,6 @@ int null_register_zoned_dev(struct nullb *nullb) struct request_queue *q = nullb->q; struct gendisk *disk = nullb->disk; - blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q); - disk->nr_zones = bdev_nr_zones(disk->part0); - pr_info("%s: using %s zone append\n", disk->disk_name, queue_emulates_zone_append(q) ? "emulated" : "native"); diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 8a2ce8070010..7cece5884b9c 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -2622,6 +2622,7 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev) struct queue_limits lim = { .max_hw_sectors = PACKET_MAX_SECTORS, .logical_block_size = CD_FRAMESIZE, + .features = BLK_FEAT_ROTATIONAL, }; int idx; int ret = -ENOMEM; diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c index b810ac0a5c4b..ff45ed766469 100644 --- a/drivers/block/ps3disk.c +++ b/drivers/block/ps3disk.c @@ -388,9 +388,9 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev) .max_segments = -1, .max_segment_size = dev->bounce_size, .dma_alignment = dev->blk_size - 1, + .features = BLK_FEAT_WRITE_CACHE | + BLK_FEAT_ROTATIONAL, }; - - struct request_queue *queue; struct gendisk *gendisk; if (dev->blk_size < 512) { @@ -447,10 +447,6 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev) goto fail_free_tag_set; } - queue = gendisk->queue; - - blk_queue_write_cache(queue, true, false); - priv->gendisk = gendisk; gendisk->major = ps3disk_major; gendisk->first_minor = devidx * PS3DISK_MINORS; diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 26ff5cd2bf0a..008e850555f4 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -4949,14 +4949,12 @@ static const struct blk_mq_ops rbd_mq_ops = { static int rbd_init_disk(struct rbd_device *rbd_dev) { struct gendisk *disk; - struct request_queue *q; unsigned int objset_bytes = rbd_dev->layout.object_size * rbd_dev->layout.stripe_count; struct queue_limits lim = { .max_hw_sectors = objset_bytes >> SECTOR_SHIFT, - .max_user_sectors = objset_bytes >> SECTOR_SHIFT, + .io_opt = objset_bytes, .io_min = rbd_dev->opts->alloc_size, - .io_opt = rbd_dev->opts->alloc_size, .max_segments = USHRT_MAX, .max_segment_size = UINT_MAX, }; @@ -4980,12 +4978,14 @@ static int rbd_init_disk(struct rbd_device *rbd_dev) lim.max_write_zeroes_sectors = objset_bytes >> SECTOR_SHIFT; } + if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC)) + lim.features |= BLK_FEAT_STABLE_WRITES; + disk = blk_mq_alloc_disk(&rbd_dev->tag_set, &lim, rbd_dev); if (IS_ERR(disk)) { err = PTR_ERR(disk); goto out_tag_set; } - q = disk->queue; snprintf(disk->disk_name, sizeof(disk->disk_name), RBD_DRV_NAME "%d", rbd_dev->dev_id); @@ -4997,13 +4997,6 @@ static int rbd_init_disk(struct rbd_device *rbd_dev) disk->minors = RBD_MINORS_PER_MAJOR; disk->fops = &rbd_bd_ops; disk->private_data = rbd_dev; - - blk_queue_flag_set(QUEUE_FLAG_NONROT, q); - /* QUEUE_FLAG_ADD_RANDOM is off by default for blk-mq */ - - if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC)) - blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q); - rbd_dev->disk = disk; return 0; diff --git a/drivers/block/rnbd/rnbd-clt-sysfs.c b/drivers/block/rnbd/rnbd-clt-sysfs.c index 39887556cf95..6ea7c12e3a87 100644 --- a/drivers/block/rnbd/rnbd-clt-sysfs.c +++ b/drivers/block/rnbd/rnbd-clt-sysfs.c @@ -475,7 +475,7 @@ void rnbd_clt_remove_dev_symlink(struct rnbd_clt_dev *dev) } } -static struct kobj_type rnbd_dev_ktype = { +static const struct kobj_type rnbd_dev_ktype = { .sysfs_ops = &kobj_sysfs_ops, .default_groups = rnbd_dev_groups, }; diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c index b7ffe03c6160..c34695d2eea7 100644 --- a/drivers/block/rnbd/rnbd-clt.c +++ b/drivers/block/rnbd/rnbd-clt.c @@ -1352,10 +1352,6 @@ static int rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev, if (dev->access_mode == RNBD_ACCESS_RO) set_disk_ro(dev->gd, true); - /* - * Network device does not need rotational - */ - blk_queue_flag_set(QUEUE_FLAG_NONROT, dev->queue); err = add_disk(dev->gd); if (err) put_disk(dev->gd); @@ -1389,18 +1385,18 @@ static int rnbd_client_setup_device(struct rnbd_clt_dev *dev, le32_to_cpu(rsp->max_discard_sectors); } + if (rsp->cache_policy & RNBD_WRITEBACK) { + lim.features |= BLK_FEAT_WRITE_CACHE; + if (rsp->cache_policy & RNBD_FUA) + lim.features |= BLK_FEAT_FUA; + } + dev->gd = blk_mq_alloc_disk(&dev->sess->tag_set, &lim, dev); if (IS_ERR(dev->gd)) return PTR_ERR(dev->gd); dev->queue = dev->gd->queue; rnbd_init_mq_hw_queues(dev); - blk_queue_flag_set(QUEUE_FLAG_SAME_COMP, dev->queue); - blk_queue_flag_set(QUEUE_FLAG_SAME_FORCE, dev->queue); - blk_queue_write_cache(dev->queue, - !!(rsp->cache_policy & RNBD_WRITEBACK), - !!(rsp->cache_policy & RNBD_FUA)); - return rnbd_clt_setup_gen_disk(dev, rsp, idx); } diff --git a/drivers/block/rnbd/rnbd-srv-sysfs.c b/drivers/block/rnbd/rnbd-srv-sysfs.c index cba6ba43c2c2..64780094442c 100644 --- a/drivers/block/rnbd/rnbd-srv-sysfs.c +++ b/drivers/block/rnbd/rnbd-srv-sysfs.c @@ -33,7 +33,7 @@ static void rnbd_srv_dev_release(struct kobject *kobj) kfree(dev); } -static struct kobj_type dev_ktype = { +static const struct kobj_type dev_ktype = { .sysfs_ops = &kobj_sysfs_ops, .release = rnbd_srv_dev_release }; @@ -184,7 +184,7 @@ static void rnbd_srv_sess_dev_release(struct kobject *kobj) rnbd_destroy_sess_dev(sess_dev, sess_dev->keep_id); } -static struct kobj_type rnbd_srv_sess_dev_ktype = { +static const struct kobj_type rnbd_srv_sess_dev_ktype = { .sysfs_ops = &kobj_sysfs_ops, .release = rnbd_srv_sess_dev_release, }; diff --git a/drivers/block/rnull.rs b/drivers/block/rnull.rs new file mode 100644 index 000000000000..b0227cf9ddd3 --- /dev/null +++ b/drivers/block/rnull.rs @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! This is a Rust implementation of the C null block driver. +//! +//! Supported features: +//! +//! - blk-mq interface +//! - direct completion +//! - block size 4k +//! +//! The driver is not configurable. + +use kernel::{ + alloc::flags, + block::mq::{ + self, + gen_disk::{self, GenDisk}, + Operations, TagSet, + }, + error::Result, + new_mutex, pr_info, + prelude::*, + sync::{Arc, Mutex}, + types::ARef, +}; + +module! { + type: NullBlkModule, + name: "rnull_mod", + author: "Andreas Hindborg", + license: "GPL v2", +} + +struct NullBlkModule { + _disk: Pin>>>, +} + +impl kernel::Module for NullBlkModule { + fn init(_module: &'static ThisModule) -> Result { + pr_info!("Rust null_blk loaded\n"); + let tagset = Arc::pin_init(TagSet::new(1, 256, 1), flags::GFP_KERNEL)?; + + let disk = gen_disk::GenDiskBuilder::new() + .capacity_sectors(4096 << 11) + .logical_block_size(4096)? + .physical_block_size(4096)? + .rotational(false) + .build(format_args!("rnullb{}", 0), tagset)?; + + let disk = Box::pin_init(new_mutex!(disk, "nullb:disk"), flags::GFP_KERNEL)?; + + Ok(Self { _disk: disk }) + } +} + +struct NullBlkDevice; + +#[vtable] +impl Operations for NullBlkDevice { + #[inline(always)] + fn queue_rq(rq: ARef>, _is_last: bool) -> Result { + mq::Request::end_ok(rq) + .map_err(|_e| kernel::error::code::EIO) + // We take no refcounts on the request, so we expect to be able to + // end the request. The request reference must be unique at this + // point, and so `end_ok` cannot fail. + .expect("Fatal error - expected to be able to end request"); + + Ok(()) + } + + fn commit_rqs() {} +} diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c index 5286cb8e0824..2d38331ee667 100644 --- a/drivers/block/sunvdc.c +++ b/drivers/block/sunvdc.c @@ -791,6 +791,7 @@ static int probe_disk(struct vdc_port *port) .seg_boundary_mask = PAGE_SIZE - 1, .max_segment_size = PAGE_SIZE, .max_segments = port->ring_cookies, + .features = BLK_FEAT_ROTATIONAL, }; struct request_queue *q; struct gendisk *g; diff --git a/drivers/block/swim.c b/drivers/block/swim.c index 6731678f3a41..126f151c4f2c 100644 --- a/drivers/block/swim.c +++ b/drivers/block/swim.c @@ -787,6 +787,9 @@ static void swim_cleanup_floppy_disk(struct floppy_state *fs) static int swim_floppy_init(struct swim_priv *swd) { + struct queue_limits lim = { + .features = BLK_FEAT_ROTATIONAL, + }; int err; int drive; struct swim __iomem *base = swd->base; @@ -820,7 +823,7 @@ static int swim_floppy_init(struct swim_priv *swd) goto exit_put_disks; swd->unit[drive].disk = - blk_mq_alloc_disk(&swd->unit[drive].tag_set, NULL, + blk_mq_alloc_disk(&swd->unit[drive].tag_set, &lim, &swd->unit[drive]); if (IS_ERR(swd->unit[drive].disk)) { blk_mq_free_tag_set(&swd->unit[drive].tag_set); diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c index a04756ac778e..90be1017f7bf 100644 --- a/drivers/block/swim3.c +++ b/drivers/block/swim3.c @@ -1189,6 +1189,9 @@ static int swim3_add_device(struct macio_dev *mdev, int index) static int swim3_attach(struct macio_dev *mdev, const struct of_device_id *match) { + struct queue_limits lim = { + .features = BLK_FEAT_ROTATIONAL, + }; struct floppy_state *fs; struct gendisk *disk; int rc; @@ -1210,7 +1213,7 @@ static int swim3_attach(struct macio_dev *mdev, if (rc) goto out_unregister; - disk = blk_mq_alloc_disk(&fs->tag_set, NULL, fs); + disk = blk_mq_alloc_disk(&fs->tag_set, &lim, fs); if (IS_ERR(disk)) { rc = PTR_ERR(disk); goto out_free_tag_set; diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 4e159948c912..6fb799ec0d88 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -248,8 +248,6 @@ static int ublk_dev_param_zoned_validate(const struct ublk_device *ub) static void ublk_dev_param_zoned_apply(struct ublk_device *ub) { - blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ub->ub_disk->queue); - ub->ub_disk->nr_zones = ublk_get_nr_zones(ub); } @@ -484,16 +482,8 @@ static inline unsigned ublk_pos_to_tag(loff_t pos) static void ublk_dev_param_basic_apply(struct ublk_device *ub) { - struct request_queue *q = ub->ub_disk->queue; const struct ublk_param_basic *p = &ub->params.basic; - blk_queue_write_cache(q, p->attrs & UBLK_ATTR_VOLATILE_CACHE, - p->attrs & UBLK_ATTR_FUA); - if (p->attrs & UBLK_ATTR_ROTATIONAL) - blk_queue_flag_clear(QUEUE_FLAG_NONROT, q); - else - blk_queue_flag_set(QUEUE_FLAG_NONROT, q); - if (p->attrs & UBLK_ATTR_READ_ONLY) set_disk_ro(ub->ub_disk, true); @@ -2204,12 +2194,21 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd) if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED)) return -EOPNOTSUPP; - lim.zoned = true; + lim.features |= BLK_FEAT_ZONED; lim.max_active_zones = p->max_active_zones; lim.max_open_zones = p->max_open_zones; lim.max_zone_append_sectors = p->max_zone_append_sectors; } + if (ub->params.basic.attrs & UBLK_ATTR_VOLATILE_CACHE) { + lim.features |= BLK_FEAT_WRITE_CACHE; + if (ub->params.basic.attrs & UBLK_ATTR_FUA) + lim.features |= BLK_FEAT_FUA; + } + + if (ub->params.basic.attrs & UBLK_ATTR_ROTATIONAL) + lim.features |= BLK_FEAT_ROTATIONAL; + if (wait_for_completion_interruptible(&ub->completion) != 0) return -EINTR; @@ -3017,4 +3016,5 @@ module_param_cb(ublks_max, &ublk_max_ublks_ops, &ublks_max, 0644); MODULE_PARM_DESC(ublks_max, "max number of ublk devices allowed to add(default: 64)"); MODULE_AUTHOR("Ming Lei "); +MODULE_DESCRIPTION("Userspace block device"); MODULE_LICENSE("GPL"); diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 2351f411fa46..e3147a611151 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -728,7 +728,7 @@ static int virtblk_read_zoned_limits(struct virtio_blk *vblk, dev_dbg(&vdev->dev, "probing host-managed zoned device\n"); - lim->zoned = true; + lim->features |= BLK_FEAT_ZONED; virtio_cread(vdev, struct virtio_blk_config, zoned.max_open_zones, &v); @@ -1089,14 +1089,6 @@ static int virtblk_get_cache_mode(struct virtio_device *vdev) return writeback; } -static void virtblk_update_cache_mode(struct virtio_device *vdev) -{ - u8 writeback = virtblk_get_cache_mode(vdev); - struct virtio_blk *vblk = vdev->priv; - - blk_queue_write_cache(vblk->disk->queue, writeback, false); -} - static const char *const virtblk_cache_types[] = { "write through", "write back" }; @@ -1108,6 +1100,7 @@ cache_type_store(struct device *dev, struct device_attribute *attr, struct gendisk *disk = dev_to_disk(dev); struct virtio_blk *vblk = disk->private_data; struct virtio_device *vdev = vblk->vdev; + struct queue_limits lim; int i; BUG_ON(!virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_CONFIG_WCE)); @@ -1116,7 +1109,17 @@ cache_type_store(struct device *dev, struct device_attribute *attr, return i; virtio_cwrite8(vdev, offsetof(struct virtio_blk_config, wce), i); - virtblk_update_cache_mode(vdev); + + lim = queue_limits_start_update(disk->queue); + if (virtblk_get_cache_mode(vdev)) + lim.features |= BLK_FEAT_WRITE_CACHE; + else + lim.features &= ~BLK_FEAT_WRITE_CACHE; + blk_mq_freeze_queue(disk->queue); + i = queue_limits_commit_update(disk->queue, &lim); + blk_mq_unfreeze_queue(disk->queue); + if (i) + return i; return count; } @@ -1247,7 +1250,7 @@ static int virtblk_read_limits(struct virtio_blk *vblk, struct queue_limits *lim) { struct virtio_device *vdev = vblk->vdev; - u32 v, blk_size, max_size, sg_elems, opt_io_size; + u32 v, max_size, sg_elems, opt_io_size; u32 max_discard_segs = 0; u32 discard_granularity = 0; u16 min_io_size; @@ -1286,46 +1289,36 @@ static int virtblk_read_limits(struct virtio_blk *vblk, lim->max_segment_size = max_size; /* Host can optionally specify the block size of the device */ - err = virtio_cread_feature(vdev, VIRTIO_BLK_F_BLK_SIZE, + virtio_cread_feature(vdev, VIRTIO_BLK_F_BLK_SIZE, struct virtio_blk_config, blk_size, - &blk_size); - if (!err) { - err = blk_validate_block_size(blk_size); - if (err) { - dev_err(&vdev->dev, - "virtio_blk: invalid block size: 0x%x\n", - blk_size); - return err; - } - - lim->logical_block_size = blk_size; - } else - blk_size = lim->logical_block_size; + &lim->logical_block_size); /* Use topology information if available */ err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY, struct virtio_blk_config, physical_block_exp, &physical_block_exp); if (!err && physical_block_exp) - lim->physical_block_size = blk_size * (1 << physical_block_exp); + lim->physical_block_size = + lim->logical_block_size * (1 << physical_block_exp); err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY, struct virtio_blk_config, alignment_offset, &alignment_offset); if (!err && alignment_offset) - lim->alignment_offset = blk_size * alignment_offset; + lim->alignment_offset = + lim->logical_block_size * alignment_offset; err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY, struct virtio_blk_config, min_io_size, &min_io_size); if (!err && min_io_size) - lim->io_min = blk_size * min_io_size; + lim->io_min = lim->logical_block_size * min_io_size; err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY, struct virtio_blk_config, opt_io_size, &opt_io_size); if (!err && opt_io_size) - lim->io_opt = blk_size * opt_io_size; + lim->io_opt = lim->logical_block_size * opt_io_size; if (virtio_has_feature(vdev, VIRTIO_BLK_F_DISCARD)) { virtio_cread(vdev, struct virtio_blk_config, @@ -1419,7 +1412,7 @@ static int virtblk_read_limits(struct virtio_blk *vblk, lim->discard_granularity = discard_granularity << SECTOR_SHIFT; else - lim->discard_granularity = blk_size; + lim->discard_granularity = lim->logical_block_size; } if (virtio_has_feature(vdev, VIRTIO_BLK_F_ZONED)) { @@ -1448,7 +1441,10 @@ static int virtblk_read_limits(struct virtio_blk *vblk, static int virtblk_probe(struct virtio_device *vdev) { struct virtio_blk *vblk; - struct queue_limits lim = { }; + struct queue_limits lim = { + .features = BLK_FEAT_ROTATIONAL, + .logical_block_size = SECTOR_SIZE, + }; int err, index; unsigned int queue_depth; @@ -1512,6 +1508,9 @@ static int virtblk_probe(struct virtio_device *vdev) if (err) goto out_free_tags; + if (virtblk_get_cache_mode(vdev)) + lim.features |= BLK_FEAT_WRITE_CACHE; + vblk->disk = blk_mq_alloc_disk(&vblk->tag_set, &lim, vblk); if (IS_ERR(vblk->disk)) { err = PTR_ERR(vblk->disk); @@ -1527,9 +1526,6 @@ static int virtblk_probe(struct virtio_device *vdev) vblk->disk->fops = &virtblk_fops; vblk->index = index; - /* configure queue flush support */ - virtblk_update_cache_mode(vdev); - /* If disk is read-only in the host, the guest should obey */ if (virtio_has_feature(vdev, VIRTIO_BLK_F_RO)) set_disk_ro(vblk->disk, 1); @@ -1541,8 +1537,8 @@ static int virtblk_probe(struct virtio_device *vdev) * All steps that follow use the VQs therefore they need to be * placed after the virtio_device_ready() call above. */ - if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && lim.zoned) { - blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, vblk->disk->queue); + if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && + (lim.features & BLK_FEAT_ZONED)) { err = blk_revalidate_disk_zones(vblk->disk); if (err) goto out_cleanup_disk; diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index 944576d582fb..838064593f62 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -1563,5 +1563,6 @@ static void __exit xen_blkif_fini(void) module_exit(xen_blkif_fini); +MODULE_DESCRIPTION("Virtual block device back-end driver"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_ALIAS("xen-backend:vbd"); diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index fd7c0ff2139c..59ce113b882a 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -788,6 +788,11 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri * A barrier request a superset of FUA, so we can * implement it the same way. (It's also a FLUSH+FUA, * since it is guaranteed ordered WRT previous writes.) + * + * Note that can end up here with a FUA write and the + * flags cleared. This happens when the flag was + * run-time disabled after a failing I/O, and we'll + * simplify submit it as a normal write. */ if (info->feature_flush && info->feature_fua) ring_req->operation = @@ -795,8 +800,6 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri else if (info->feature_flush) ring_req->operation = BLKIF_OP_FLUSH_DISKCACHE; - else - ring_req->operation = 0; } ring_req->u.rw.nr_segments = num_grant; if (unlikely(require_extra_req)) { @@ -887,16 +890,6 @@ static inline void flush_requests(struct blkfront_ring_info *rinfo) notify_remote_via_irq(rinfo->irq); } -static inline bool blkif_request_flush_invalid(struct request *req, - struct blkfront_info *info) -{ - return (blk_rq_is_passthrough(req) || - ((req_op(req) == REQ_OP_FLUSH) && - !info->feature_flush) || - ((req->cmd_flags & REQ_FUA) && - !info->feature_fua)); -} - static blk_status_t blkif_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *qd) { @@ -908,12 +901,22 @@ static blk_status_t blkif_queue_rq(struct blk_mq_hw_ctx *hctx, rinfo = get_rinfo(info, qid); blk_mq_start_request(qd->rq); spin_lock_irqsave(&rinfo->ring_lock, flags); + + /* + * Check if the backend actually supports flushes. + * + * While the block layer won't send us flushes if we don't claim to + * support them, the Xen protocol allows the backend to revoke support + * at any time. That is of course a really bad idea and dangerous, but + * has been allowed for 10+ years. In that case we simply clear the + * flags, and directly return here for an empty flush and ignore the + * FUA flag later on. + */ + if (unlikely(req_op(qd->rq) == REQ_OP_FLUSH && !info->feature_flush)) + goto complete; + if (RING_FULL(&rinfo->ring)) goto out_busy; - - if (blkif_request_flush_invalid(qd->rq, rinfo->dev_info)) - goto out_err; - if (blkif_queue_request(qd->rq, rinfo)) goto out_busy; @@ -921,14 +924,14 @@ static blk_status_t blkif_queue_rq(struct blk_mq_hw_ctx *hctx, spin_unlock_irqrestore(&rinfo->ring_lock, flags); return BLK_STS_OK; -out_err: - spin_unlock_irqrestore(&rinfo->ring_lock, flags); - return BLK_STS_IOERR; - out_busy: blk_mq_stop_hw_queue(hctx); spin_unlock_irqrestore(&rinfo->ring_lock, flags); return BLK_STS_DEV_RESOURCE; +complete: + spin_unlock_irqrestore(&rinfo->ring_lock, flags); + blk_mq_end_request(qd->rq, BLK_STS_OK); + return BLK_STS_OK; } static void blkif_complete_rq(struct request *rq) @@ -956,6 +959,12 @@ static void blkif_set_queue_limits(const struct blkfront_info *info, lim->max_secure_erase_sectors = UINT_MAX; } + if (info->feature_flush) { + lim->features |= BLK_FEAT_WRITE_CACHE; + if (info->feature_fua) + lim->features |= BLK_FEAT_FUA; + } + /* Hard sector size and max sectors impersonate the equiv. hardware. */ lim->logical_block_size = info->sector_size; lim->physical_block_size = info->physical_sector_size; @@ -984,8 +993,6 @@ static const char *flush_info(struct blkfront_info *info) static void xlvbd_flush(struct blkfront_info *info) { - blk_queue_write_cache(info->rq, info->feature_flush ? true : false, - info->feature_fua ? true : false); pr_info("blkfront: %s: %s %s %s %s %s %s %s\n", info->gd->disk_name, flush_info(info), "persistent grants:", info->feature_persistent ? @@ -1063,8 +1070,7 @@ static char *encode_disk_name(char *ptr, unsigned int n) } static int xlvbd_alloc_gendisk(blkif_sector_t capacity, - struct blkfront_info *info, u16 sector_size, - unsigned int physical_sector_size) + struct blkfront_info *info) { struct queue_limits lim = {}; struct gendisk *gd; @@ -1139,7 +1145,6 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity, err = PTR_ERR(gd); goto out_free_tag_set; } - blk_queue_flag_set(QUEUE_FLAG_VIRT, gd->queue); strcpy(gd->disk_name, DEV_NAME); ptr = encode_disk_name(gd->disk_name + sizeof(DEV_NAME) - 1, offset); @@ -1159,8 +1164,6 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity, info->rq = gd->queue; info->gd = gd; - info->sector_size = sector_size; - info->physical_sector_size = physical_sector_size; xlvbd_flush(info); @@ -1605,8 +1608,8 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) blkif_req(req)->error = BLK_STS_NOTSUPP; info->feature_discard = 0; info->feature_secdiscard = 0; - blk_queue_max_discard_sectors(rq, 0); - blk_queue_max_secure_erase_sectors(rq, 0); + blk_queue_disable_discard(rq); + blk_queue_disable_secure_erase(rq); } break; case BLKIF_OP_FLUSH_DISKCACHE: @@ -1627,7 +1630,6 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) blkif_req(req)->error = BLK_STS_OK; info->feature_fua = 0; info->feature_flush = 0; - xlvbd_flush(info); } fallthrough; case BLKIF_OP_READ: @@ -2315,8 +2317,6 @@ static void blkfront_gather_backend_features(struct blkfront_info *info) static void blkfront_connect(struct blkfront_info *info) { unsigned long long sectors; - unsigned long sector_size; - unsigned int physical_sector_size; int err, i; struct blkfront_ring_info *rinfo; @@ -2355,7 +2355,7 @@ static void blkfront_connect(struct blkfront_info *info) err = xenbus_gather(XBT_NIL, info->xbdev->otherend, "sectors", "%llu", §ors, "info", "%u", &info->vdisk_info, - "sector-size", "%lu", §or_size, + "sector-size", "%lu", &info->sector_size, NULL); if (err) { xenbus_dev_fatal(info->xbdev, err, @@ -2369,9 +2369,9 @@ static void blkfront_connect(struct blkfront_info *info) * provide this. Assume physical sector size to be the same as * sector_size in that case. */ - physical_sector_size = xenbus_read_unsigned(info->xbdev->otherend, + info->physical_sector_size = xenbus_read_unsigned(info->xbdev->otherend, "physical-sector-size", - sector_size); + info->sector_size); blkfront_gather_backend_features(info); for_each_rinfo(info, rinfo, i) { err = blkfront_setup_indirect(rinfo); @@ -2383,8 +2383,7 @@ static void blkfront_connect(struct blkfront_info *info) } } - err = xlvbd_alloc_gendisk(sectors, info, sector_size, - physical_sector_size); + err = xlvbd_alloc_gendisk(sectors, info); if (err) { xenbus_dev_fatal(info->xbdev, err, "xlvbd_add at %s", info->xbdev->otherend); diff --git a/drivers/block/z2ram.c b/drivers/block/z2ram.c index 7c5f4e4d9b50..4b7219be1bb8 100644 --- a/drivers/block/z2ram.c +++ b/drivers/block/z2ram.c @@ -409,4 +409,5 @@ static void __exit z2_exit(void) module_init(z2_init); module_exit(z2_exit); +MODULE_DESCRIPTION("Amiga Zorro II ramdisk driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 3acd7006ad2c..efcb8d9d274c 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -2208,6 +2208,8 @@ static int zram_add(void) #if ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE .max_write_zeroes_sectors = UINT_MAX, #endif + .features = BLK_FEAT_STABLE_WRITES | + BLK_FEAT_SYNCHRONOUS, }; struct zram *zram; int ret, device_id; @@ -2245,10 +2247,6 @@ static int zram_add(void) /* Actual capacity set using sysfs (/sys/block/zram/disksize */ set_capacity(zram->disk, 0); - /* zram devices sort of resembles non-rotational disks */ - blk_queue_flag_set(QUEUE_FLAG_NONROT, zram->disk->queue); - blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, zram->disk->queue); - blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, zram->disk->queue); ret = device_add_disk(NULL, zram->disk, zram_disk_groups); if (ret) goto out_cleanup_disk; diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 20c90ebb3a3f..49e4829b7264 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -3708,4 +3708,5 @@ static void __exit cdrom_exit(void) module_init(cdrom_init); module_exit(cdrom_exit); +MODULE_DESCRIPTION("Uniform CD-ROM driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c index eefdd422ad8e..71cfe7a85913 100644 --- a/drivers/cdrom/gdrom.c +++ b/drivers/cdrom/gdrom.c @@ -744,6 +744,7 @@ static int probe_gdrom(struct platform_device *devptr) .max_segments = 1, /* set a large max size to get most from DMA */ .max_segment_size = 0x40000, + .features = BLK_FEAT_ROTATIONAL, }; int err; diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 4d11fc664cb0..b5d6ef430b86 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -897,7 +897,6 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size, sector_t sectors, struct block_device *cached_bdev, const struct block_device_operations *ops) { - struct request_queue *q; const size_t max_stripes = min_t(size_t, INT_MAX, SIZE_MAX / sizeof(atomic_t)); struct queue_limits lim = { @@ -909,6 +908,7 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size, .io_min = block_size, .logical_block_size = block_size, .physical_block_size = block_size, + .features = BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA, }; uint64_t n; int idx; @@ -974,13 +974,6 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size, d->disk->minors = BCACHE_MINORS; d->disk->fops = ops; d->disk->private_data = d; - - q = d->disk->queue; - - blk_queue_flag_set(QUEUE_FLAG_NONROT, d->disk->queue); - - blk_queue_write_cache(q, true, true); - return 0; out_bioset_exit: @@ -1423,8 +1416,8 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size) } if (bdev_io_opt(dc->bdev)) - dc->partial_stripes_expensive = - q->limits.raid_partial_stripes_expensive; + dc->partial_stripes_expensive = !!(q->limits.features & + BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE); ret = bcache_device_init(&dc->disk, block_size, bdev_nr_sectors(dc->bdev) - dc->sb.data_offset, diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 16884b585053..2d8dd9283ff4 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -3403,7 +3403,6 @@ static void set_discard_limits(struct cache *cache, struct queue_limits *limits) limits->max_hw_discard_sectors = origin_limits->max_hw_discard_sectors; limits->discard_granularity = origin_limits->discard_granularity; limits->discard_alignment = origin_limits->discard_alignment; - limits->discard_misaligned = origin_limits->discard_misaligned; } static void cache_io_hints(struct dm_target *ti, struct queue_limits *limits) diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c index ad79b52ffc14..b4384a8b13e3 100644 --- a/drivers/md/dm-clone-target.c +++ b/drivers/md/dm-clone-target.c @@ -2059,7 +2059,6 @@ static void set_discard_limits(struct clone *clone, struct queue_limits *limits) limits->max_hw_discard_sectors = dest_limits->max_hw_discard_sectors; limits->discard_granularity = dest_limits->discard_granularity; limits->discard_alignment = dest_limits->discard_alignment; - limits->discard_misaligned = dest_limits->discard_misaligned; limits->max_discard_segments = dest_limits->max_discard_segments; } diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index 08700bfc3e23..14a44c0f8286 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -206,7 +206,6 @@ struct dm_table { bool integrity_supported:1; bool singleton:1; - unsigned integrity_added:1; /* * Indicates the rw permissions for the new logical device. This diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 1b7a97cc3779..6c013ceb0e5f 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1176,8 +1176,8 @@ static int crypt_integrity_ctr(struct crypt_config *cc, struct dm_target *ti) struct blk_integrity *bi = blk_get_integrity(cc->dev->bdev->bd_disk); struct mapped_device *md = dm_table_get_md(ti->table); - /* From now we require underlying device with our integrity profile */ - if (!bi || strcasecmp(bi->profile->name, "DM-DIF-EXT-TAG")) { + /* We require an underlying device with non-PI metadata */ + if (!bi || bi->csum_type != BLK_INTEGRITY_CSUM_NONE) { ti->error = "Integrity profile not supported."; return -EINVAL; } diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 417fddebe367..2a89f8eb4713 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -350,25 +350,6 @@ static struct kmem_cache *journal_io_cache; #define DEBUG_bytes(bytes, len, msg, ...) do { } while (0) #endif -static void dm_integrity_prepare(struct request *rq) -{ -} - -static void dm_integrity_complete(struct request *rq, unsigned int nr_bytes) -{ -} - -/* - * DM Integrity profile, protection is performed layer above (dm-crypt) - */ -static const struct blk_integrity_profile dm_integrity_profile = { - .name = "DM-DIF-EXT-TAG", - .generate_fn = NULL, - .verify_fn = NULL, - .prepare_fn = dm_integrity_prepare, - .complete_fn = dm_integrity_complete, -}; - static void dm_integrity_map_continue(struct dm_integrity_io *dio, bool from_map); static void integrity_bio_wait(struct work_struct *w); static void dm_integrity_dtr(struct dm_target *ti); @@ -3494,6 +3475,17 @@ static void dm_integrity_io_hints(struct dm_target *ti, struct queue_limits *lim limits->dma_alignment = limits->logical_block_size - 1; limits->discard_granularity = ic->sectors_per_block << SECTOR_SHIFT; } + + if (!ic->internal_hash) { + struct blk_integrity *bi = &limits->integrity; + + memset(bi, 0, sizeof(*bi)); + bi->tuple_size = ic->tag_size; + bi->tag_size = bi->tuple_size; + bi->interval_exp = + ic->sb->log2_sectors_per_block + SECTOR_SHIFT; + } + limits->max_integrity_segments = USHRT_MAX; } @@ -3650,20 +3642,6 @@ try_smaller_buffer: return 0; } -static void dm_integrity_set(struct dm_target *ti, struct dm_integrity_c *ic) -{ - struct gendisk *disk = dm_disk(dm_table_get_md(ti->table)); - struct blk_integrity bi; - - memset(&bi, 0, sizeof(bi)); - bi.profile = &dm_integrity_profile; - bi.tuple_size = ic->tag_size; - bi.tag_size = bi.tuple_size; - bi.interval_exp = ic->sb->log2_sectors_per_block + SECTOR_SHIFT; - - blk_integrity_register(disk, &bi); -} - static void dm_integrity_free_page_list(struct page_list *pl) { unsigned int i; @@ -4649,9 +4627,6 @@ try_smaller_buffer: } } - if (!ic->internal_hash) - dm_integrity_set(ti, ic); - ti->num_flush_bios = 1; ti->flush_supported = true; if (ic->discard) diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index abe88d1e6735..052c00c1eb15 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3542,7 +3542,7 @@ static void raid_status(struct dm_target *ti, status_type_t type, recovery = rs->md.recovery; state = decipher_sync_action(mddev, recovery); progress = rs_get_progress(rs, recovery, state, resync_max_sectors); - resync_mismatches = (mddev->last_sync_action && !strcasecmp(mddev->last_sync_action, "check")) ? + resync_mismatches = mddev->last_sync_action == ACTION_CHECK ? atomic64_read(&mddev->resync_mismatches) : 0; /* HM FIXME: do we want another state char for raid0? It shows 'D'/'A'/'-' now */ diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index b2d5246cff21..92d18dcdb3e9 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -425,6 +425,13 @@ static int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev, q->limits.logical_block_size, q->limits.alignment_offset, (unsigned long long) start << SECTOR_SHIFT); + + /* + * Only stack the integrity profile if the target doesn't have native + * integrity support. + */ + if (!dm_target_has_integrity(ti->type)) + queue_limits_stack_integrity_bdev(limits, bdev); return 0; } @@ -572,6 +579,12 @@ int dm_split_args(int *argc, char ***argvp, char *input) return 0; } +static void dm_set_stacking_limits(struct queue_limits *limits) +{ + blk_set_stacking_limits(limits); + limits->features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT | BLK_FEAT_POLL; +} + /* * Impose necessary and sufficient conditions on a devices's table such * that any incoming bio which respects its logical_block_size can be @@ -610,7 +623,7 @@ static int validate_hardware_logical_block_alignment(struct dm_table *t, for (i = 0; i < t->num_targets; i++) { ti = dm_table_get_target(t, i); - blk_set_stacking_limits(&ti_limits); + dm_set_stacking_limits(&ti_limits); /* combine all target devices' limits */ if (ti->type->iterate_devices) @@ -702,9 +715,6 @@ int dm_table_add_target(struct dm_table *t, const char *type, t->immutable_target_type = ti->type; } - if (dm_target_has_integrity(ti->type)) - t->integrity_added = 1; - ti->table = t; ti->begin = start; ti->len = len; @@ -1014,14 +1024,13 @@ bool dm_table_request_based(struct dm_table *t) return __table_type_request_based(dm_table_get_type(t)); } -static bool dm_table_supports_poll(struct dm_table *t); - static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *md) { enum dm_queue_mode type = dm_table_get_type(t); unsigned int per_io_data_size = 0, front_pad, io_front_pad; unsigned int min_pool_size = 0, pool_size; struct dm_md_mempools *pools; + unsigned int bioset_flags = 0; if (unlikely(type == DM_TYPE_NONE)) { DMERR("no table type is set, can't allocate mempools"); @@ -1038,6 +1047,9 @@ static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device * goto init_bs; } + if (md->queue->limits.features & BLK_FEAT_POLL) + bioset_flags |= BIOSET_PERCPU_CACHE; + for (unsigned int i = 0; i < t->num_targets; i++) { struct dm_target *ti = dm_table_get_target(t, i); @@ -1050,8 +1062,7 @@ static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device * io_front_pad = roundup(per_io_data_size, __alignof__(struct dm_io)) + DM_IO_BIO_OFFSET; - if (bioset_init(&pools->io_bs, pool_size, io_front_pad, - dm_table_supports_poll(t) ? BIOSET_PERCPU_CACHE : 0)) + if (bioset_init(&pools->io_bs, pool_size, io_front_pad, bioset_flags)) goto out_free_pools; if (t->integrity_supported && bioset_integrity_create(&pools->io_bs, pool_size)) @@ -1119,99 +1130,6 @@ static int dm_table_build_index(struct dm_table *t) return r; } -static bool integrity_profile_exists(struct gendisk *disk) -{ - return !!blk_get_integrity(disk); -} - -/* - * Get a disk whose integrity profile reflects the table's profile. - * Returns NULL if integrity support was inconsistent or unavailable. - */ -static struct gendisk *dm_table_get_integrity_disk(struct dm_table *t) -{ - struct list_head *devices = dm_table_get_devices(t); - struct dm_dev_internal *dd = NULL; - struct gendisk *prev_disk = NULL, *template_disk = NULL; - - for (unsigned int i = 0; i < t->num_targets; i++) { - struct dm_target *ti = dm_table_get_target(t, i); - - if (!dm_target_passes_integrity(ti->type)) - goto no_integrity; - } - - list_for_each_entry(dd, devices, list) { - template_disk = dd->dm_dev->bdev->bd_disk; - if (!integrity_profile_exists(template_disk)) - goto no_integrity; - else if (prev_disk && - blk_integrity_compare(prev_disk, template_disk) < 0) - goto no_integrity; - prev_disk = template_disk; - } - - return template_disk; - -no_integrity: - if (prev_disk) - DMWARN("%s: integrity not set: %s and %s profile mismatch", - dm_device_name(t->md), - prev_disk->disk_name, - template_disk->disk_name); - return NULL; -} - -/* - * Register the mapped device for blk_integrity support if the - * underlying devices have an integrity profile. But all devices may - * not have matching profiles (checking all devices isn't reliable - * during table load because this table may use other DM device(s) which - * must be resumed before they will have an initialized integity - * profile). Consequently, stacked DM devices force a 2 stage integrity - * profile validation: First pass during table load, final pass during - * resume. - */ -static int dm_table_register_integrity(struct dm_table *t) -{ - struct mapped_device *md = t->md; - struct gendisk *template_disk = NULL; - - /* If target handles integrity itself do not register it here. */ - if (t->integrity_added) - return 0; - - template_disk = dm_table_get_integrity_disk(t); - if (!template_disk) - return 0; - - if (!integrity_profile_exists(dm_disk(md))) { - t->integrity_supported = true; - /* - * Register integrity profile during table load; we can do - * this because the final profile must match during resume. - */ - blk_integrity_register(dm_disk(md), - blk_get_integrity(template_disk)); - return 0; - } - - /* - * If DM device already has an initialized integrity - * profile the new profile should not conflict. - */ - if (blk_integrity_compare(dm_disk(md), template_disk) < 0) { - DMERR("%s: conflict with existing integrity profile: %s profile mismatch", - dm_device_name(t->md), - template_disk->disk_name); - return 1; - } - - /* Preserve existing integrity profile */ - t->integrity_supported = true; - return 0; -} - #ifdef CONFIG_BLK_INLINE_ENCRYPTION struct dm_crypto_profile { @@ -1423,12 +1341,6 @@ int dm_table_complete(struct dm_table *t) return r; } - r = dm_table_register_integrity(t); - if (r) { - DMERR("could not register integrity profile."); - return r; - } - r = dm_table_construct_crypto_profile(t); if (r) { DMERR("could not construct crypto profile."); @@ -1493,14 +1405,6 @@ struct dm_target *dm_table_find_target(struct dm_table *t, sector_t sector) return &t->targets[(KEYS_PER_NODE * n) + k]; } -static int device_not_poll_capable(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data) -{ - struct request_queue *q = bdev_get_queue(dev->bdev); - - return !test_bit(QUEUE_FLAG_POLL, &q->queue_flags); -} - /* * type->iterate_devices() should be called when the sanity check needs to * iterate and check all underlying data devices. iterate_devices() will @@ -1548,19 +1452,6 @@ static int count_device(struct dm_target *ti, struct dm_dev *dev, return 0; } -static bool dm_table_supports_poll(struct dm_table *t) -{ - for (unsigned int i = 0; i < t->num_targets; i++) { - struct dm_target *ti = dm_table_get_target(t, i); - - if (!ti->type->iterate_devices || - ti->type->iterate_devices(ti, device_not_poll_capable, NULL)) - return false; - } - - return true; -} - /* * Check whether a table has no data devices attached using each * target's iterate_devices method. @@ -1686,12 +1577,20 @@ int dm_calculate_queue_limits(struct dm_table *t, unsigned int zone_sectors = 0; bool zoned = false; - blk_set_stacking_limits(limits); + dm_set_stacking_limits(limits); + + t->integrity_supported = true; + for (unsigned int i = 0; i < t->num_targets; i++) { + struct dm_target *ti = dm_table_get_target(t, i); + + if (!dm_target_passes_integrity(ti->type)) + t->integrity_supported = false; + } for (unsigned int i = 0; i < t->num_targets; i++) { struct dm_target *ti = dm_table_get_target(t, i); - blk_set_stacking_limits(&ti_limits); + dm_set_stacking_limits(&ti_limits); if (!ti->type->iterate_devices) { /* Set I/O hints portion of queue limits */ @@ -1706,12 +1605,12 @@ int dm_calculate_queue_limits(struct dm_table *t, ti->type->iterate_devices(ti, dm_set_device_limits, &ti_limits); - if (!zoned && ti_limits.zoned) { + if (!zoned && (ti_limits.features & BLK_FEAT_ZONED)) { /* * After stacking all limits, validate all devices * in table support this zoned model and zone sectors. */ - zoned = ti_limits.zoned; + zoned = (ti_limits.features & BLK_FEAT_ZONED); zone_sectors = ti_limits.chunk_sectors; } @@ -1738,6 +1637,18 @@ combine_limits: dm_device_name(t->md), (unsigned long long) ti->begin, (unsigned long long) ti->len); + + if (t->integrity_supported || + dm_target_has_integrity(ti->type)) { + if (!queue_limits_stack_integrity(limits, &ti_limits)) { + DMWARN("%s: adding target device (start sect %llu len %llu) " + "disabled integrity support due to incompatibility", + dm_device_name(t->md), + (unsigned long long) ti->begin, + (unsigned long long) ti->len); + t->integrity_supported = false; + } + } } /* @@ -1747,12 +1658,12 @@ combine_limits: * zoned model on host-managed zoned block devices. * BUT... */ - if (limits->zoned) { + if (limits->features & BLK_FEAT_ZONED) { /* * ...IF the above limits stacking determined a zoned model * validate that all of the table's devices conform to it. */ - zoned = limits->zoned; + zoned = limits->features & BLK_FEAT_ZONED; zone_sectors = limits->chunk_sectors; } if (validate_hardware_zoned(t, zoned, zone_sectors)) @@ -1762,63 +1673,15 @@ combine_limits: } /* - * Verify that all devices have an integrity profile that matches the - * DM device's registered integrity profile. If the profiles don't - * match then unregister the DM device's integrity profile. + * Check if a target requires flush support even if none of the underlying + * devices need it (e.g. to persist target-specific metadata). */ -static void dm_table_verify_integrity(struct dm_table *t) +static bool dm_table_supports_flush(struct dm_table *t) { - struct gendisk *template_disk = NULL; - - if (t->integrity_added) - return; - - if (t->integrity_supported) { - /* - * Verify that the original integrity profile - * matches all the devices in this table. - */ - template_disk = dm_table_get_integrity_disk(t); - if (template_disk && - blk_integrity_compare(dm_disk(t->md), template_disk) >= 0) - return; - } - - if (integrity_profile_exists(dm_disk(t->md))) { - DMWARN("%s: unable to establish an integrity profile", - dm_device_name(t->md)); - blk_integrity_unregister(dm_disk(t->md)); - } -} - -static int device_flush_capable(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data) -{ - unsigned long flush = (unsigned long) data; - struct request_queue *q = bdev_get_queue(dev->bdev); - - return (q->queue_flags & flush); -} - -static bool dm_table_supports_flush(struct dm_table *t, unsigned long flush) -{ - /* - * Require at least one underlying device to support flushes. - * t->devices includes internal dm devices such as mirror logs - * so we need to use iterate_devices here, which targets - * supporting flushes must provide. - */ for (unsigned int i = 0; i < t->num_targets; i++) { struct dm_target *ti = dm_table_get_target(t, i); - if (!ti->num_flush_bios) - continue; - - if (ti->flush_supported) - return true; - - if (ti->type->iterate_devices && - ti->type->iterate_devices(ti, device_flush_capable, (void *) flush)) + if (ti->num_flush_bios && ti->flush_supported) return true; } @@ -1839,20 +1702,6 @@ static int device_dax_write_cache_enabled(struct dm_target *ti, return false; } -static int device_is_rotational(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data) -{ - return !bdev_nonrot(dev->bdev); -} - -static int device_is_not_random(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data) -{ - struct request_queue *q = bdev_get_queue(dev->bdev); - - return !blk_queue_add_random(q); -} - static int device_not_write_zeroes_capable(struct dm_target *ti, struct dm_dev *dev, sector_t start, sector_t len, void *data) { @@ -1877,12 +1726,6 @@ static bool dm_table_supports_write_zeroes(struct dm_table *t) return true; } -static int device_not_nowait_capable(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data) -{ - return !bdev_nowait(dev->bdev); -} - static bool dm_table_supports_nowait(struct dm_table *t) { for (unsigned int i = 0; i < t->num_targets; i++) { @@ -1890,10 +1733,6 @@ static bool dm_table_supports_nowait(struct dm_table *t) if (!dm_target_supports_nowait(ti->type)) return false; - - if (!ti->type->iterate_devices || - ti->type->iterate_devices(ti, device_not_nowait_capable, NULL)) - return false; } return true; @@ -1950,29 +1789,25 @@ static bool dm_table_supports_secure_erase(struct dm_table *t) return true; } -static int device_requires_stable_pages(struct dm_target *ti, - struct dm_dev *dev, sector_t start, - sector_t len, void *data) -{ - return bdev_stable_writes(dev->bdev); -} - int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, struct queue_limits *limits) { - bool wc = false, fua = false; int r; - if (dm_table_supports_nowait(t)) - blk_queue_flag_set(QUEUE_FLAG_NOWAIT, q); - else - blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, q); + if (!dm_table_supports_nowait(t)) + limits->features &= ~BLK_FEAT_NOWAIT; + + /* + * The current polling impementation does not support request based + * stacking. + */ + if (!__table_type_bio_based(t->type)) + limits->features &= ~BLK_FEAT_POLL; if (!dm_table_supports_discards(t)) { limits->max_hw_discard_sectors = 0; limits->discard_granularity = 0; limits->discard_alignment = 0; - limits->discard_misaligned = 0; } if (!dm_table_supports_write_zeroes(t)) @@ -1981,58 +1816,22 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, if (!dm_table_supports_secure_erase(t)) limits->max_secure_erase_sectors = 0; - if (dm_table_supports_flush(t, (1UL << QUEUE_FLAG_WC))) { - wc = true; - if (dm_table_supports_flush(t, (1UL << QUEUE_FLAG_FUA))) - fua = true; - } - blk_queue_write_cache(q, wc, fua); + if (dm_table_supports_flush(t)) + limits->features |= BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA; if (dm_table_supports_dax(t, device_not_dax_capable)) { - blk_queue_flag_set(QUEUE_FLAG_DAX, q); + limits->features |= BLK_FEAT_DAX; if (dm_table_supports_dax(t, device_not_dax_synchronous_capable)) set_dax_synchronous(t->md->dax_dev); } else - blk_queue_flag_clear(QUEUE_FLAG_DAX, q); + limits->features &= ~BLK_FEAT_DAX; if (dm_table_any_dev_attr(t, device_dax_write_cache_enabled, NULL)) dax_write_cache(t->md->dax_dev, true); - /* Ensure that all underlying devices are non-rotational. */ - if (dm_table_any_dev_attr(t, device_is_rotational, NULL)) - blk_queue_flag_clear(QUEUE_FLAG_NONROT, q); - else - blk_queue_flag_set(QUEUE_FLAG_NONROT, q); - - dm_table_verify_integrity(t); - - /* - * Some devices don't use blk_integrity but still want stable pages - * because they do their own checksumming. - * If any underlying device requires stable pages, a table must require - * them as well. Only targets that support iterate_devices are considered: - * don't want error, zero, etc to require stable pages. - */ - if (dm_table_any_dev_attr(t, device_requires_stable_pages, NULL)) - blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q); - else - blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, q); - - /* - * Determine whether or not this queue's I/O timings contribute - * to the entropy pool, Only request-based targets use this. - * Clear QUEUE_FLAG_ADD_RANDOM if any underlying device does not - * have it set. - */ - if (blk_queue_add_random(q) && - dm_table_any_dev_attr(t, device_is_not_random, NULL)) - blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, q); - - /* - * For a zoned target, setup the zones related queue attributes - * and resources necessary for zone append emulation if necessary. - */ - if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && limits->zoned) { + /* For a zoned table, setup the zone related queue attributes. */ + if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && + (limits->features & BLK_FEAT_ZONED)) { r = dm_set_zones_restrictions(t, q, limits); if (r) return r; @@ -2042,22 +1841,18 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, if (r) return r; - dm_update_crypto_profile(q, t); - /* - * Check for request-based device is left to - * dm_mq_init_request_queue()->blk_mq_init_allocated_queue(). - * - * For bio-based device, only set QUEUE_FLAG_POLL when all - * underlying devices supporting polling. + * Now that the limits are set, check the zones mapped by the table + * and setup the resources for zone append emulation if necessary. */ - if (__table_type_bio_based(t->type)) { - if (dm_table_supports_poll(t)) - blk_queue_flag_set(QUEUE_FLAG_POLL, q); - else - blk_queue_flag_clear(QUEUE_FLAG_POLL, q); + if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && + (limits->features & BLK_FEAT_ZONED)) { + r = dm_revalidate_zones(t, q); + if (r) + return r; } + dm_update_crypto_profile(q, t); return 0; } diff --git a/drivers/md/dm-zone.c b/drivers/md/dm-zone.c index 5d66d916730e..c0d41c36e06e 100644 --- a/drivers/md/dm-zone.c +++ b/drivers/md/dm-zone.c @@ -13,8 +13,6 @@ #define DM_MSG_PREFIX "zone" -#define DM_ZONE_INVALID_WP_OFST UINT_MAX - /* * For internal zone reports bypassing the top BIO submission path. */ @@ -145,35 +143,28 @@ bool dm_is_zone_write(struct mapped_device *md, struct bio *bio) } } -/* - * Count conventional zones of a mapped zoned device. If the device - * only has conventional zones, do not expose it as zoned. - */ -static int dm_check_zoned_cb(struct blk_zone *zone, unsigned int idx, - void *data) -{ - unsigned int *nr_conv_zones = data; - - if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL) - (*nr_conv_zones)++; - - return 0; -} - /* * Revalidate the zones of a mapped device to initialize resource necessary * for zone append emulation. Note that we cannot simply use the block layer * blk_revalidate_disk_zones() function here as the mapped device is suspended * (this is called from __bind() context). */ -static int dm_revalidate_zones(struct mapped_device *md, struct dm_table *t) +int dm_revalidate_zones(struct dm_table *t, struct request_queue *q) { + struct mapped_device *md = t->md; struct gendisk *disk = md->disk; int ret; + if (!get_capacity(disk)) + return 0; + /* Revalidate only if something changed. */ - if (!disk->nr_zones || disk->nr_zones != md->nr_zones) + if (!disk->nr_zones || disk->nr_zones != md->nr_zones) { + DMINFO("%s using %s zone append", + disk->disk_name, + queue_emulates_zone_append(q) ? "emulated" : "native"); md->nr_zones = 0; + } if (md->nr_zones) return 0; @@ -220,13 +211,129 @@ static bool dm_table_supports_zone_append(struct dm_table *t) return true; } +struct dm_device_zone_count { + sector_t start; + sector_t len; + unsigned int total_nr_seq_zones; + unsigned int target_nr_seq_zones; +}; + +/* + * Count the total number of and the number of mapped sequential zones of a + * target zoned device. + */ +static int dm_device_count_zones_cb(struct blk_zone *zone, + unsigned int idx, void *data) +{ + struct dm_device_zone_count *zc = data; + + if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL) { + zc->total_nr_seq_zones++; + if (zone->start >= zc->start && + zone->start < zc->start + zc->len) + zc->target_nr_seq_zones++; + } + + return 0; +} + +static int dm_device_count_zones(struct dm_dev *dev, + struct dm_device_zone_count *zc) +{ + int ret; + + ret = blkdev_report_zones(dev->bdev, 0, BLK_ALL_ZONES, + dm_device_count_zones_cb, zc); + if (ret < 0) + return ret; + if (!ret) + return -EIO; + return 0; +} + +struct dm_zone_resource_limits { + unsigned int mapped_nr_seq_zones; + struct queue_limits *lim; + bool reliable_limits; +}; + +static int device_get_zone_resource_limits(struct dm_target *ti, + struct dm_dev *dev, sector_t start, + sector_t len, void *data) +{ + struct dm_zone_resource_limits *zlim = data; + struct gendisk *disk = dev->bdev->bd_disk; + unsigned int max_open_zones, max_active_zones; + int ret; + struct dm_device_zone_count zc = { + .start = start, + .len = len, + }; + + /* + * If the target is not the whole device, the device zone resources may + * be shared between different targets. Check this by counting the + * number of mapped sequential zones: if this number is smaller than the + * total number of sequential zones of the target device, then resource + * sharing may happen and the zone limits will not be reliable. + */ + ret = dm_device_count_zones(dev, &zc); + if (ret) { + DMERR("Count %s zones failed %d", disk->disk_name, ret); + return ret; + } + + /* + * If the target does not map any sequential zones, then we do not need + * any zone resource limits. + */ + if (!zc.target_nr_seq_zones) + return 0; + + /* + * If the target does not map all sequential zones, the limits + * will not be reliable and we cannot use REQ_OP_ZONE_RESET_ALL. + */ + if (zc.target_nr_seq_zones < zc.total_nr_seq_zones) { + zlim->reliable_limits = false; + ti->zone_reset_all_supported = false; + } + + /* + * If the target maps less sequential zones than the limit values, then + * we do not have limits for this target. + */ + max_active_zones = disk->queue->limits.max_active_zones; + if (max_active_zones >= zc.target_nr_seq_zones) + max_active_zones = 0; + zlim->lim->max_active_zones = + min_not_zero(max_active_zones, zlim->lim->max_active_zones); + + max_open_zones = disk->queue->limits.max_open_zones; + if (max_open_zones >= zc.target_nr_seq_zones) + max_open_zones = 0; + zlim->lim->max_open_zones = + min_not_zero(max_open_zones, zlim->lim->max_open_zones); + + /* + * Also count the total number of sequential zones for the mapped + * device so that when we are done inspecting all its targets, we are + * able to check if the mapped device actually has any sequential zones. + */ + zlim->mapped_nr_seq_zones += zc.target_nr_seq_zones; + + return 0; +} + int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q, struct queue_limits *lim) { struct mapped_device *md = t->md; struct gendisk *disk = md->disk; - unsigned int nr_conv_zones = 0; - int ret; + struct dm_zone_resource_limits zlim = { + .reliable_limits = true, + .lim = lim, + }; /* * Check if zone append is natively supported, and if not, set the @@ -240,46 +347,63 @@ int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q, lim->max_zone_append_sectors = 0; } - if (!get_capacity(md->disk)) - return 0; - /* - * Count conventional zones to check that the mapped device will indeed - * have sequential write required zones. + * Determine the max open and max active zone limits for the mapped + * device by inspecting the zone resource limits and the zones mapped + * by each target. */ - md->zone_revalidate_map = t; - ret = dm_blk_report_zones(disk, 0, UINT_MAX, - dm_check_zoned_cb, &nr_conv_zones); - md->zone_revalidate_map = NULL; - if (ret < 0) { - DMERR("Check zoned failed %d", ret); - return ret; + for (unsigned int i = 0; i < t->num_targets; i++) { + struct dm_target *ti = dm_table_get_target(t, i); + + /* + * Assume that the target can accept REQ_OP_ZONE_RESET_ALL. + * device_get_zone_resource_limits() may adjust this if one of + * the device used by the target does not have all its + * sequential write required zones mapped. + */ + ti->zone_reset_all_supported = true; + + if (!ti->type->iterate_devices || + ti->type->iterate_devices(ti, + device_get_zone_resource_limits, &zlim)) { + DMERR("Could not determine %s zone resource limits", + disk->disk_name); + return -ENODEV; + } } /* - * If we only have conventional zones, expose the mapped device as - * a regular device. + * If we only have conventional zones mapped, expose the mapped device + + as a regular device. */ - if (nr_conv_zones >= ret) { + if (!zlim.mapped_nr_seq_zones) { lim->max_open_zones = 0; lim->max_active_zones = 0; - lim->zoned = false; + lim->max_zone_append_sectors = 0; + lim->zone_write_granularity = 0; + lim->chunk_sectors = 0; + lim->features &= ~BLK_FEAT_ZONED; clear_bit(DMF_EMULATE_ZONE_APPEND, &md->flags); + md->nr_zones = 0; disk->nr_zones = 0; return 0; } - if (!md->disk->nr_zones) { - DMINFO("%s using %s zone append", - md->disk->disk_name, - queue_emulates_zone_append(q) ? "emulated" : "native"); - } + /* + * Warn once (when the capacity is not yet set) if the mapped device is + * partially using zone resources of the target devices as that leads to + * unreliable limits, i.e. if another mapped device uses the same + * underlying devices, we cannot enforce zone limits to guarantee that + * writing will not lead to errors. Note that we really should return + * an error for such case but there is no easy way to find out if + * another mapped device uses the same underlying zoned devices. + */ + if (!get_capacity(disk) && !zlim.reliable_limits) + DMWARN("%s zone resource limits may be unreliable", + disk->disk_name); - ret = dm_revalidate_zones(md, t); - if (ret < 0) - return ret; - - if (!static_key_enabled(&zoned_enabled.key)) + if (lim->features & BLK_FEAT_ZONED && + !static_key_enabled(&zoned_enabled.key)) static_branch_enable(&zoned_enabled); return 0; } @@ -306,3 +430,39 @@ void dm_zone_endio(struct dm_io *io, struct bio *clone) return; } + +static int dm_zone_need_reset_cb(struct blk_zone *zone, unsigned int idx, + void *data) +{ + /* + * For an all-zones reset, ignore conventional, empty, read-only + * and offline zones. + */ + switch (zone->cond) { + case BLK_ZONE_COND_NOT_WP: + case BLK_ZONE_COND_EMPTY: + case BLK_ZONE_COND_READONLY: + case BLK_ZONE_COND_OFFLINE: + return 0; + default: + set_bit(idx, (unsigned long *)data); + return 0; + } +} + +int dm_zone_get_reset_bitmap(struct mapped_device *md, struct dm_table *t, + sector_t sector, unsigned int nr_zones, + unsigned long *need_reset) +{ + int ret; + + ret = dm_blk_do_report_zones(md, t, sector, nr_zones, + dm_zone_need_reset_cb, need_reset); + if (ret != nr_zones) { + DMERR("Get %s zone reset bitmap failed\n", + md->disk->disk_name); + return -EIO; + } + + return 0; +} diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index 12236e6f46f3..cd0ee144973f 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -1009,7 +1009,7 @@ static void dmz_io_hints(struct dm_target *ti, struct queue_limits *limits) limits->max_sectors = chunk_sectors; /* We are exposing a drive-managed zoned block device */ - limits->zoned = false; + limits->features &= ~BLK_FEAT_ZONED; } /* diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 13037d6a6f62..4b1b69e576a5 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1188,7 +1188,7 @@ static sector_t __max_io_len(struct dm_target *ti, sector_t sector, return len; return min_t(sector_t, len, min(max_sectors ? : queue_max_sectors(ti->table->md->queue), - blk_chunk_sectors_left(target_offset, max_granularity))); + blk_boundary_sectors_left(target_offset, max_granularity))); } static inline sector_t max_io_len(struct dm_target *ti, sector_t sector) @@ -1598,20 +1598,19 @@ static void __send_abnormal_io(struct clone_info *ci, struct dm_target *ti, static bool is_abnormal_io(struct bio *bio) { - enum req_op op = bio_op(bio); - - if (op != REQ_OP_READ && op != REQ_OP_WRITE && op != REQ_OP_FLUSH) { - switch (op) { - case REQ_OP_DISCARD: - case REQ_OP_SECURE_ERASE: - case REQ_OP_WRITE_ZEROES: - return true; - default: - break; - } + switch (bio_op(bio)) { + case REQ_OP_READ: + case REQ_OP_WRITE: + case REQ_OP_FLUSH: + return false; + case REQ_OP_DISCARD: + case REQ_OP_SECURE_ERASE: + case REQ_OP_WRITE_ZEROES: + case REQ_OP_ZONE_RESET_ALL: + return true; + default: + return false; } - - return false; } static blk_status_t __process_abnormal_io(struct clone_info *ci, @@ -1776,6 +1775,119 @@ static inline bool dm_zone_plug_bio(struct mapped_device *md, struct bio *bio) { return dm_emulate_zone_append(md) && blk_zone_plug_bio(bio, 0); } + +static blk_status_t __send_zone_reset_all_emulated(struct clone_info *ci, + struct dm_target *ti) +{ + struct bio_list blist = BIO_EMPTY_LIST; + struct mapped_device *md = ci->io->md; + unsigned int zone_sectors = md->disk->queue->limits.chunk_sectors; + unsigned long *need_reset; + unsigned int i, nr_zones, nr_reset; + unsigned int num_bios = 0; + blk_status_t sts = BLK_STS_OK; + sector_t sector = ti->begin; + struct bio *clone; + int ret; + + nr_zones = ti->len >> ilog2(zone_sectors); + need_reset = bitmap_zalloc(nr_zones, GFP_NOIO); + if (!need_reset) + return BLK_STS_RESOURCE; + + ret = dm_zone_get_reset_bitmap(md, ci->map, ti->begin, + nr_zones, need_reset); + if (ret) { + sts = BLK_STS_IOERR; + goto free_bitmap; + } + + /* If we have no zone to reset, we are done. */ + nr_reset = bitmap_weight(need_reset, nr_zones); + if (!nr_reset) + goto free_bitmap; + + atomic_add(nr_zones, &ci->io->io_count); + + for (i = 0; i < nr_zones; i++) { + + if (!test_bit(i, need_reset)) { + sector += zone_sectors; + continue; + } + + if (bio_list_empty(&blist)) { + /* This may take a while, so be nice to others */ + if (num_bios) + cond_resched(); + + /* + * We may need to reset thousands of zones, so let's + * not go crazy with the clone allocation. + */ + alloc_multiple_bios(&blist, ci, ti, min(nr_reset, 32), + NULL, GFP_NOIO); + } + + /* Get a clone and change it to a regular reset operation. */ + clone = bio_list_pop(&blist); + clone->bi_opf &= ~REQ_OP_MASK; + clone->bi_opf |= REQ_OP_ZONE_RESET | REQ_SYNC; + clone->bi_iter.bi_sector = sector; + clone->bi_iter.bi_size = 0; + __map_bio(clone); + + sector += zone_sectors; + num_bios++; + nr_reset--; + } + + WARN_ON_ONCE(!bio_list_empty(&blist)); + atomic_sub(nr_zones - num_bios, &ci->io->io_count); + ci->sector_count = 0; + +free_bitmap: + bitmap_free(need_reset); + + return sts; +} + +static void __send_zone_reset_all_native(struct clone_info *ci, + struct dm_target *ti) +{ + unsigned int bios; + + atomic_add(1, &ci->io->io_count); + bios = __send_duplicate_bios(ci, ti, 1, NULL, GFP_NOIO); + atomic_sub(1 - bios, &ci->io->io_count); + + ci->sector_count = 0; +} + +static blk_status_t __send_zone_reset_all(struct clone_info *ci) +{ + struct dm_table *t = ci->map; + blk_status_t sts = BLK_STS_OK; + + for (unsigned int i = 0; i < t->num_targets; i++) { + struct dm_target *ti = dm_table_get_target(t, i); + + if (ti->zone_reset_all_supported) { + __send_zone_reset_all_native(ci, ti); + continue; + } + + sts = __send_zone_reset_all_emulated(ci, ti); + if (sts != BLK_STS_OK) + break; + } + + /* Release the reference that alloc_io() took for submission. */ + atomic_sub(1, &ci->io->io_count); + + return sts; +} + #else static inline bool dm_zone_bio_needs_split(struct mapped_device *md, struct bio *bio) @@ -1786,6 +1898,10 @@ static inline bool dm_zone_plug_bio(struct mapped_device *md, struct bio *bio) { return false; } +static blk_status_t __send_zone_reset_all(struct clone_info *ci) +{ + return BLK_STS_NOTSUPP; +} #endif /* @@ -1799,9 +1915,14 @@ static void dm_split_and_process_bio(struct mapped_device *md, blk_status_t error = BLK_STS_OK; bool is_abnormal, need_split; - need_split = is_abnormal = is_abnormal_io(bio); - if (static_branch_unlikely(&zoned_enabled)) - need_split = is_abnormal || dm_zone_bio_needs_split(md, bio); + is_abnormal = is_abnormal_io(bio); + if (static_branch_unlikely(&zoned_enabled)) { + /* Special case REQ_OP_ZONE_RESET_ALL as it cannot be split. */ + need_split = (bio_op(bio) != REQ_OP_ZONE_RESET_ALL) && + (is_abnormal || dm_zone_bio_needs_split(md, bio)); + } else { + need_split = is_abnormal; + } if (unlikely(need_split)) { /* @@ -1842,6 +1963,12 @@ static void dm_split_and_process_bio(struct mapped_device *md, goto out; } + if (static_branch_unlikely(&zoned_enabled) && + (bio_op(bio) == REQ_OP_ZONE_RESET_ALL)) { + error = __send_zone_reset_all(&ci); + goto out; + } + error = __split_and_process_bio(&ci); if (error || !ci.sector_count) goto out; @@ -2386,22 +2513,15 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t) struct table_device *td; int r; - switch (type) { - case DM_TYPE_REQUEST_BASED: + WARN_ON_ONCE(type == DM_TYPE_NONE); + + if (type == DM_TYPE_REQUEST_BASED) { md->disk->fops = &dm_rq_blk_dops; r = dm_mq_init_request_queue(md, t); if (r) { DMERR("Cannot initialize queue for request-based dm mapped device"); return r; } - break; - case DM_TYPE_BIO_BASED: - case DM_TYPE_DAX_BIO_BASED: - blk_queue_flag_set(QUEUE_FLAG_IO_STAT, md->queue); - break; - case DM_TYPE_NONE: - WARN_ON_ONCE(true); - break; } r = dm_calculate_queue_limits(t, &limits); diff --git a/drivers/md/dm.h b/drivers/md/dm.h index 53ef8207fe2c..cc466ad5cb1d 100644 --- a/drivers/md/dm.h +++ b/drivers/md/dm.h @@ -103,12 +103,16 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t); */ int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q, struct queue_limits *lim); +int dm_revalidate_zones(struct dm_table *t, struct request_queue *q); void dm_zone_endio(struct dm_io *io, struct bio *clone); #ifdef CONFIG_BLK_DEV_ZONED int dm_blk_report_zones(struct gendisk *disk, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); bool dm_is_zone_write(struct mapped_device *md, struct bio *bio); int dm_zone_map_bio(struct dm_target_io *io); +int dm_zone_get_reset_bitmap(struct mapped_device *md, struct dm_table *t, + sector_t sector, unsigned int nr_zones, + unsigned long *need_reset); #else #define dm_blk_report_zones NULL static inline bool dm_is_zone_write(struct mapped_device *md, struct bio *bio) diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 0a2d37eb38ef..08232d8dc815 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -227,6 +227,8 @@ static int __write_sb_page(struct md_rdev *rdev, struct bitmap *bitmap, struct block_device *bdev; struct mddev *mddev = bitmap->mddev; struct bitmap_storage *store = &bitmap->storage; + unsigned int bitmap_limit = (bitmap->storage.file_pages - pg_index) << + PAGE_SHIFT; loff_t sboff, offset = mddev->bitmap_info.offset; sector_t ps = pg_index * PAGE_SIZE / SECTOR_SIZE; unsigned int size = PAGE_SIZE; @@ -269,11 +271,9 @@ static int __write_sb_page(struct md_rdev *rdev, struct bitmap *bitmap, if (size == 0) /* bitmap runs in to data */ return -EINVAL; - } else { - /* DATA METADATA BITMAP - no problems */ } - md_super_write(mddev, rdev, sboff + ps, (int) size, page); + md_super_write(mddev, rdev, sboff + ps, (int)min(size, bitmap_limit), page); return 0; } diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c index 8e36a0feec09..139fe2019c1d 100644 --- a/drivers/md/md-cluster.c +++ b/drivers/md/md-cluster.c @@ -1570,7 +1570,7 @@ out: return err; } -static struct md_cluster_operations cluster_ops = { +static const struct md_cluster_operations cluster_ops = { .join = join, .leave = leave, .slot_number = slot_number, diff --git a/drivers/md/md.c b/drivers/md/md.c index aff9118ff697..64693913ed18 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -69,13 +69,23 @@ #include "md-bitmap.h" #include "md-cluster.h" +static const char *action_name[NR_SYNC_ACTIONS] = { + [ACTION_RESYNC] = "resync", + [ACTION_RECOVER] = "recover", + [ACTION_CHECK] = "check", + [ACTION_REPAIR] = "repair", + [ACTION_RESHAPE] = "reshape", + [ACTION_FROZEN] = "frozen", + [ACTION_IDLE] = "idle", +}; + /* pers_list is a list of registered personalities protected by pers_lock. */ static LIST_HEAD(pers_list); static DEFINE_SPINLOCK(pers_lock); static const struct kobj_type md_ktype; -struct md_cluster_operations *md_cluster_ops; +const struct md_cluster_operations *md_cluster_ops; EXPORT_SYMBOL(md_cluster_ops); static struct module *md_cluster_mod; @@ -479,7 +489,6 @@ int mddev_suspend(struct mddev *mddev, bool interruptible) */ WRITE_ONCE(mddev->suspended, mddev->suspended + 1); - del_timer_sync(&mddev->safemode_timer); /* restrict memory reclaim I/O during raid array is suspend */ mddev->noio_flag = memalloc_noio_save(); @@ -550,13 +559,9 @@ static void md_end_flush(struct bio *bio) rdev_dec_pending(rdev, mddev); - if (atomic_dec_and_test(&mddev->flush_pending)) { - /* The pair is percpu_ref_get() from md_flush_request() */ - percpu_ref_put(&mddev->active_io); - + if (atomic_dec_and_test(&mddev->flush_pending)) /* The pre-request flush has finished */ queue_work(md_wq, &mddev->flush_work); - } } static void md_submit_flush_data(struct work_struct *ws); @@ -587,12 +592,8 @@ static void submit_flushes(struct work_struct *ws) rcu_read_lock(); } rcu_read_unlock(); - if (atomic_dec_and_test(&mddev->flush_pending)) { - /* The pair is percpu_ref_get() from md_flush_request() */ - percpu_ref_put(&mddev->active_io); - + if (atomic_dec_and_test(&mddev->flush_pending)) queue_work(md_wq, &mddev->flush_work); - } } static void md_submit_flush_data(struct work_struct *ws) @@ -617,8 +618,20 @@ static void md_submit_flush_data(struct work_struct *ws) bio_endio(bio); } else { bio->bi_opf &= ~REQ_PREFLUSH; - md_handle_request(mddev, bio); + + /* + * make_requst() will never return error here, it only + * returns error in raid5_make_request() by dm-raid. + * Since dm always splits data and flush operation into + * two separate io, io size of flush submitted by dm + * always is 0, make_request() will not be called here. + */ + if (WARN_ON_ONCE(!mddev->pers->make_request(mddev, bio))) + bio_io_error(bio); } + + /* The pair is percpu_ref_get() from md_flush_request() */ + percpu_ref_put(&mddev->active_io); } /* @@ -654,24 +667,22 @@ bool md_flush_request(struct mddev *mddev, struct bio *bio) WARN_ON(percpu_ref_is_zero(&mddev->active_io)); percpu_ref_get(&mddev->active_io); mddev->flush_bio = bio; - bio = NULL; - } - spin_unlock_irq(&mddev->lock); - - if (!bio) { + spin_unlock_irq(&mddev->lock); INIT_WORK(&mddev->flush_work, submit_flushes); queue_work(md_wq, &mddev->flush_work); - } else { - /* flush was performed for some other bio while we waited. */ - if (bio->bi_iter.bi_size == 0) - /* an empty barrier - all done */ - bio_endio(bio); - else { - bio->bi_opf &= ~REQ_PREFLUSH; - return false; - } + return true; } - return true; + + /* flush was performed for some other bio while we waited. */ + spin_unlock_irq(&mddev->lock); + if (bio->bi_iter.bi_size == 0) { + /* pure flush without data - all done */ + bio_endio(bio); + return true; + } + + bio->bi_opf &= ~REQ_PREFLUSH; + return false; } EXPORT_SYMBOL(md_flush_request); @@ -742,7 +753,6 @@ int mddev_init(struct mddev *mddev) mutex_init(&mddev->open_mutex); mutex_init(&mddev->reconfig_mutex); - mutex_init(&mddev->sync_mutex); mutex_init(&mddev->suspend_mutex); mutex_init(&mddev->bitmap_info.mutex); INIT_LIST_HEAD(&mddev->disks); @@ -758,7 +768,7 @@ int mddev_init(struct mddev *mddev) init_waitqueue_head(&mddev->recovery_wait); mddev->reshape_position = MaxSector; mddev->reshape_backwards = 0; - mddev->last_sync_action = "none"; + mddev->last_sync_action = ACTION_IDLE; mddev->resync_min = 0; mddev->resync_max = MaxSector; mddev->level = LEVEL_NONE; @@ -2410,36 +2420,10 @@ static LIST_HEAD(pending_raid_disks); */ int md_integrity_register(struct mddev *mddev) { - struct md_rdev *rdev, *reference = NULL; - if (list_empty(&mddev->disks)) return 0; /* nothing to do */ - if (mddev_is_dm(mddev) || blk_get_integrity(mddev->gendisk)) - return 0; /* shouldn't register, or already is */ - rdev_for_each(rdev, mddev) { - /* skip spares and non-functional disks */ - if (test_bit(Faulty, &rdev->flags)) - continue; - if (rdev->raid_disk < 0) - continue; - if (!reference) { - /* Use the first rdev as the reference */ - reference = rdev; - continue; - } - /* does this rdev's profile match the reference profile? */ - if (blk_integrity_compare(reference->bdev->bd_disk, - rdev->bdev->bd_disk) < 0) - return -EINVAL; - } - if (!reference || !bdev_get_integrity(reference->bdev)) - return 0; - /* - * All component devices are integrity capable and have matching - * profiles, register the common profile for the md device. - */ - blk_integrity_register(mddev->gendisk, - bdev_get_integrity(reference->bdev)); + if (mddev_is_dm(mddev) || !blk_get_integrity(mddev->gendisk)) + return 0; /* shouldn't register */ pr_debug("md: data integrity enabled on %s\n", mdname(mddev)); if (bioset_integrity_create(&mddev->bio_set, BIO_POOL_SIZE) || @@ -2459,32 +2443,6 @@ int md_integrity_register(struct mddev *mddev) } EXPORT_SYMBOL(md_integrity_register); -/* - * Attempt to add an rdev, but only if it is consistent with the current - * integrity profile - */ -int md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev) -{ - struct blk_integrity *bi_mddev; - - if (mddev_is_dm(mddev)) - return 0; - - bi_mddev = blk_get_integrity(mddev->gendisk); - - if (!bi_mddev) /* nothing to do */ - return 0; - - if (blk_integrity_compare(mddev->gendisk, rdev->bdev->bd_disk) != 0) { - pr_err("%s: incompatible integrity profile for %pg\n", - mdname(mddev), rdev->bdev); - return -ENXIO; - } - - return 0; -} -EXPORT_SYMBOL(md_integrity_add_rdev); - static bool rdev_read_only(struct md_rdev *rdev) { return bdev_read_only(rdev->bdev) || @@ -4867,30 +4825,81 @@ out_unlock: static struct md_sysfs_entry md_metadata = __ATTR_PREALLOC(metadata_version, S_IRUGO|S_IWUSR, metadata_show, metadata_store); +enum sync_action md_sync_action(struct mddev *mddev) +{ + unsigned long recovery = mddev->recovery; + + /* + * frozen has the highest priority, means running sync_thread will be + * stopped immediately, and no new sync_thread can start. + */ + if (test_bit(MD_RECOVERY_FROZEN, &recovery)) + return ACTION_FROZEN; + + /* + * read-only array can't register sync_thread, and it can only + * add/remove spares. + */ + if (!md_is_rdwr(mddev)) + return ACTION_IDLE; + + /* + * idle means no sync_thread is running, and no new sync_thread is + * requested. + */ + if (!test_bit(MD_RECOVERY_RUNNING, &recovery) && + !test_bit(MD_RECOVERY_NEEDED, &recovery)) + return ACTION_IDLE; + + if (test_bit(MD_RECOVERY_RESHAPE, &recovery) || + mddev->reshape_position != MaxSector) + return ACTION_RESHAPE; + + if (test_bit(MD_RECOVERY_RECOVER, &recovery)) + return ACTION_RECOVER; + + if (test_bit(MD_RECOVERY_SYNC, &recovery)) { + /* + * MD_RECOVERY_CHECK must be paired with + * MD_RECOVERY_REQUESTED. + */ + if (test_bit(MD_RECOVERY_CHECK, &recovery)) + return ACTION_CHECK; + if (test_bit(MD_RECOVERY_REQUESTED, &recovery)) + return ACTION_REPAIR; + return ACTION_RESYNC; + } + + /* + * MD_RECOVERY_NEEDED or MD_RECOVERY_RUNNING is set, however, no + * sync_action is specified. + */ + return ACTION_IDLE; +} + +enum sync_action md_sync_action_by_name(const char *page) +{ + enum sync_action action; + + for (action = 0; action < NR_SYNC_ACTIONS; ++action) { + if (cmd_match(page, action_name[action])) + return action; + } + + return NR_SYNC_ACTIONS; +} + +const char *md_sync_action_name(enum sync_action action) +{ + return action_name[action]; +} + static ssize_t action_show(struct mddev *mddev, char *page) { - char *type = "idle"; - unsigned long recovery = mddev->recovery; - if (test_bit(MD_RECOVERY_FROZEN, &recovery)) - type = "frozen"; - else if (test_bit(MD_RECOVERY_RUNNING, &recovery) || - (md_is_rdwr(mddev) && test_bit(MD_RECOVERY_NEEDED, &recovery))) { - if (test_bit(MD_RECOVERY_RESHAPE, &recovery)) - type = "reshape"; - else if (test_bit(MD_RECOVERY_SYNC, &recovery)) { - if (!test_bit(MD_RECOVERY_REQUESTED, &recovery)) - type = "resync"; - else if (test_bit(MD_RECOVERY_CHECK, &recovery)) - type = "check"; - else - type = "repair"; - } else if (test_bit(MD_RECOVERY_RECOVER, &recovery)) - type = "recover"; - else if (mddev->reshape_position != MaxSector) - type = "reshape"; - } - return sprintf(page, "%s\n", type); + enum sync_action action = md_sync_action(mddev); + + return sprintf(page, "%s\n", md_sync_action_name(action)); } /** @@ -4899,15 +4908,10 @@ action_show(struct mddev *mddev, char *page) * @locked: if set, reconfig_mutex will still be held after this function * return; if not set, reconfig_mutex will be released after this * function return. - * @check_seq: if set, only wait for curent running sync_thread to stop, noted - * that new sync_thread can still start. */ -static void stop_sync_thread(struct mddev *mddev, bool locked, bool check_seq) +static void stop_sync_thread(struct mddev *mddev, bool locked) { - int sync_seq; - - if (check_seq) - sync_seq = atomic_read(&mddev->sync_seq); + int sync_seq = atomic_read(&mddev->sync_seq); if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) { if (!locked) @@ -4928,7 +4932,8 @@ static void stop_sync_thread(struct mddev *mddev, bool locked, bool check_seq) wait_event(resync_wait, !test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) || - (check_seq && sync_seq != atomic_read(&mddev->sync_seq))); + (!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery) && + sync_seq != atomic_read(&mddev->sync_seq))); if (locked) mddev_lock_nointr(mddev); @@ -4939,7 +4944,7 @@ void md_idle_sync_thread(struct mddev *mddev) lockdep_assert_held(&mddev->reconfig_mutex); clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - stop_sync_thread(mddev, true, true); + stop_sync_thread(mddev, true); } EXPORT_SYMBOL_GPL(md_idle_sync_thread); @@ -4948,7 +4953,7 @@ void md_frozen_sync_thread(struct mddev *mddev) lockdep_assert_held(&mddev->reconfig_mutex); set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - stop_sync_thread(mddev, true, false); + stop_sync_thread(mddev, true); } EXPORT_SYMBOL_GPL(md_frozen_sync_thread); @@ -4963,100 +4968,127 @@ void md_unfrozen_sync_thread(struct mddev *mddev) } EXPORT_SYMBOL_GPL(md_unfrozen_sync_thread); -static void idle_sync_thread(struct mddev *mddev) +static int mddev_start_reshape(struct mddev *mddev) { - mutex_lock(&mddev->sync_mutex); - clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + int ret; - if (mddev_lock(mddev)) { - mutex_unlock(&mddev->sync_mutex); - return; + if (mddev->pers->start_reshape == NULL) + return -EINVAL; + + if (mddev->reshape_position == MaxSector || + mddev->pers->check_reshape == NULL || + mddev->pers->check_reshape(mddev)) { + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + ret = mddev->pers->start_reshape(mddev); + if (ret) + return ret; + } else { + /* + * If reshape is still in progress, and md_check_recovery() can + * continue to reshape, don't restart reshape because data can + * be corrupted for raid456. + */ + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); } - stop_sync_thread(mddev, false, true); - mutex_unlock(&mddev->sync_mutex); -} - -static void frozen_sync_thread(struct mddev *mddev) -{ - mutex_lock(&mddev->sync_mutex); - set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - - if (mddev_lock(mddev)) { - mutex_unlock(&mddev->sync_mutex); - return; - } - - stop_sync_thread(mddev, false, false); - mutex_unlock(&mddev->sync_mutex); + sysfs_notify_dirent_safe(mddev->sysfs_degraded); + return 0; } static ssize_t action_store(struct mddev *mddev, const char *page, size_t len) { + int ret; + enum sync_action action; + if (!mddev->pers || !mddev->pers->sync_request) return -EINVAL; +retry: + if (work_busy(&mddev->sync_work)) + flush_work(&mddev->sync_work); - if (cmd_match(page, "idle")) - idle_sync_thread(mddev); - else if (cmd_match(page, "frozen")) - frozen_sync_thread(mddev); - else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) - return -EBUSY; - else if (cmd_match(page, "resync")) - clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - else if (cmd_match(page, "recover")) { - clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); - } else if (cmd_match(page, "reshape")) { - int err; - if (mddev->pers->start_reshape == NULL) - return -EINVAL; - err = mddev_lock(mddev); - if (!err) { - if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) { - err = -EBUSY; - } else if (mddev->reshape_position == MaxSector || - mddev->pers->check_reshape == NULL || - mddev->pers->check_reshape(mddev)) { - clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - err = mddev->pers->start_reshape(mddev); - } else { - /* - * If reshape is still in progress, and - * md_check_recovery() can continue to reshape, - * don't restart reshape because data can be - * corrupted for raid456. - */ - clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - } - mddev_unlock(mddev); - } - if (err) - return err; - sysfs_notify_dirent_safe(mddev->sysfs_degraded); - } else { - if (cmd_match(page, "check")) - set_bit(MD_RECOVERY_CHECK, &mddev->recovery); - else if (!cmd_match(page, "repair")) - return -EINVAL; - clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery); - set_bit(MD_RECOVERY_SYNC, &mddev->recovery); + ret = mddev_lock(mddev); + if (ret) + return ret; + + if (work_busy(&mddev->sync_work)) { + mddev_unlock(mddev); + goto retry; } + + action = md_sync_action_by_name(page); + + /* TODO: mdadm rely on "idle" to start sync_thread. */ + if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) { + switch (action) { + case ACTION_FROZEN: + md_frozen_sync_thread(mddev); + ret = len; + goto out; + case ACTION_IDLE: + md_idle_sync_thread(mddev); + break; + case ACTION_RESHAPE: + case ACTION_RECOVER: + case ACTION_CHECK: + case ACTION_REPAIR: + case ACTION_RESYNC: + ret = -EBUSY; + goto out; + default: + ret = -EINVAL; + goto out; + } + } else { + switch (action) { + case ACTION_FROZEN: + set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + ret = len; + goto out; + case ACTION_RESHAPE: + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + ret = mddev_start_reshape(mddev); + if (ret) + goto out; + break; + case ACTION_RECOVER: + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); + break; + case ACTION_CHECK: + set_bit(MD_RECOVERY_CHECK, &mddev->recovery); + fallthrough; + case ACTION_REPAIR: + set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery); + set_bit(MD_RECOVERY_SYNC, &mddev->recovery); + fallthrough; + case ACTION_RESYNC: + case ACTION_IDLE: + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + break; + default: + ret = -EINVAL; + goto out; + } + } + if (mddev->ro == MD_AUTO_READ) { /* A write to sync_action is enough to justify * canceling read-auto mode */ - flush_work(&mddev->sync_work); mddev->ro = MD_RDWR; md_wakeup_thread(mddev->sync_thread); } + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); md_wakeup_thread(mddev->thread); sysfs_notify_dirent_safe(mddev->sysfs_action); - return len; + ret = len; + +out: + mddev_unlock(mddev); + return ret; } static struct md_sysfs_entry md_scan_mode = @@ -5065,7 +5097,8 @@ __ATTR_PREALLOC(sync_action, S_IRUGO|S_IWUSR, action_show, action_store); static ssize_t last_sync_action_show(struct mddev *mddev, char *page) { - return sprintf(page, "%s\n", mddev->last_sync_action); + return sprintf(page, "%s\n", + md_sync_action_name(mddev->last_sync_action)); } static struct md_sysfs_entry md_last_scan_mode = __ATTR_RO(last_sync_action); @@ -5755,14 +5788,20 @@ static const struct kobj_type md_ktype = { int mdp_major = 0; /* stack the limit for all rdevs into lim */ -void mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim) +int mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim, + unsigned int flags) { struct md_rdev *rdev; rdev_for_each(rdev, mddev) { queue_limits_stack_bdev(lim, rdev->bdev, rdev->data_offset, mddev->gendisk->disk_name); + if ((flags & MDDEV_STACK_INTEGRITY) && + !queue_limits_stack_integrity_bdev(lim, rdev->bdev)) + return -EINVAL; } + + return 0; } EXPORT_SYMBOL_GPL(mddev_stack_rdev_limits); @@ -5777,6 +5816,14 @@ int mddev_stack_new_rdev(struct mddev *mddev, struct md_rdev *rdev) lim = queue_limits_start_update(mddev->gendisk->queue); queue_limits_stack_bdev(&lim, rdev->bdev, rdev->data_offset, mddev->gendisk->disk_name); + + if (!queue_limits_stack_integrity_bdev(&lim, rdev->bdev)) { + pr_err("%s: incompatible integrity profile for %pg\n", + mdname(mddev), rdev->bdev); + queue_limits_cancel_update(mddev->gendisk->queue); + return -ENXIO; + } + return queue_limits_commit_update(mddev->gendisk->queue, &lim); } EXPORT_SYMBOL_GPL(mddev_stack_new_rdev); @@ -5806,6 +5853,14 @@ static void mddev_delayed_delete(struct work_struct *ws) kobject_put(&mddev->kobj); } +void md_init_stacking_limits(struct queue_limits *lim) +{ + blk_set_stacking_limits(lim); + lim->features = BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA | + BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT; +} +EXPORT_SYMBOL_GPL(md_init_stacking_limits); + struct mddev *md_alloc(dev_t dev, char *name) { /* @@ -5823,7 +5878,7 @@ struct mddev *md_alloc(dev_t dev, char *name) int partitioned; int shift; int unit; - int error ; + int error; /* * Wait for any previous instance of this device to be completely @@ -5881,7 +5936,6 @@ struct mddev *md_alloc(dev_t dev, char *name) disk->fops = &md_fops; disk->private_data = mddev; - blk_queue_write_cache(disk->queue, true, true); disk->events |= DISK_EVENT_MEDIA_CHANGE; mddev->gendisk = disk; error = add_disk(disk); @@ -6185,28 +6239,6 @@ int md_run(struct mddev *mddev) } } - if (!mddev_is_dm(mddev)) { - struct request_queue *q = mddev->gendisk->queue; - bool nonrot = true; - - rdev_for_each(rdev, mddev) { - if (rdev->raid_disk >= 0 && !bdev_nonrot(rdev->bdev)) { - nonrot = false; - break; - } - } - if (mddev->degraded) - nonrot = false; - if (nonrot) - blk_queue_flag_set(QUEUE_FLAG_NONROT, q); - else - blk_queue_flag_clear(QUEUE_FLAG_NONROT, q); - blk_queue_flag_set(QUEUE_FLAG_IO_STAT, q); - - /* Set the NOWAIT flags if all underlying devices support it */ - if (nowait) - blk_queue_flag_set(QUEUE_FLAG_NOWAIT, q); - } if (pers->sync_request) { if (mddev->kobj.sd && sysfs_create_group(&mddev->kobj, &md_redundancy_group)) @@ -6437,7 +6469,7 @@ void md_stop_writes(struct mddev *mddev) { mddev_lock_nointr(mddev); set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - stop_sync_thread(mddev, true, false); + stop_sync_thread(mddev, true); __md_stop_writes(mddev); mddev_unlock(mddev); } @@ -6505,7 +6537,7 @@ static int md_set_readonly(struct mddev *mddev) set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); } - stop_sync_thread(mddev, false, false); + stop_sync_thread(mddev, false); wait_event(mddev->sb_wait, !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)); mddev_lock_nointr(mddev); @@ -6551,7 +6583,7 @@ static int do_md_stop(struct mddev *mddev, int mode) set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); } - stop_sync_thread(mddev, true, false); + stop_sync_thread(mddev, true); if (mddev->sysfs_active || test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) { @@ -7165,15 +7197,6 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev) set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags); if (!mddev->thread) md_update_sb(mddev, 1); - /* - * If the new disk does not support REQ_NOWAIT, - * disable on the whole MD. - */ - if (!bdev_nowait(rdev->bdev)) { - pr_info("%s: Disabling nowait because %pg does not support nowait\n", - mdname(mddev), rdev->bdev); - blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, mddev->gendisk->queue); - } /* * Kick recovery, maybe this spare has to be added to the * array immediately. @@ -7742,12 +7765,6 @@ static int md_ioctl(struct block_device *bdev, blk_mode_t mode, return get_bitmap_file(mddev, argp); } - if (cmd == HOT_REMOVE_DISK) - /* need to ensure recovery thread has run */ - wait_event_interruptible_timeout(mddev->sb_wait, - !test_bit(MD_RECOVERY_NEEDED, - &mddev->recovery), - msecs_to_jiffies(5000)); if (cmd == STOP_ARRAY || cmd == STOP_ARRAY_RO) { /* Need to flush page cache, and ensure no-one else opens * and writes @@ -8520,7 +8537,7 @@ int unregister_md_personality(struct md_personality *p) } EXPORT_SYMBOL(unregister_md_personality); -int register_md_cluster_operations(struct md_cluster_operations *ops, +int register_md_cluster_operations(const struct md_cluster_operations *ops, struct module *module) { int ret = 0; @@ -8641,12 +8658,12 @@ EXPORT_SYMBOL(md_done_sync); * A return value of 'false' means that the write wasn't recorded * and cannot proceed as the array is being suspend. */ -bool md_write_start(struct mddev *mddev, struct bio *bi) +void md_write_start(struct mddev *mddev, struct bio *bi) { int did_change = 0; if (bio_data_dir(bi) != WRITE) - return true; + return; BUG_ON(mddev->ro == MD_RDONLY); if (mddev->ro == MD_AUTO_READ) { @@ -8679,15 +8696,9 @@ bool md_write_start(struct mddev *mddev, struct bio *bi) if (did_change) sysfs_notify_dirent_safe(mddev->sysfs_state); if (!mddev->has_superblocks) - return true; + return; wait_event(mddev->sb_wait, - !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags) || - is_md_suspended(mddev)); - if (test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) { - percpu_ref_put(&mddev->writes_pending); - return false; - } - return true; + !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)); } EXPORT_SYMBOL(md_write_start); @@ -8835,6 +8846,77 @@ void md_allow_write(struct mddev *mddev) } EXPORT_SYMBOL_GPL(md_allow_write); +static sector_t md_sync_max_sectors(struct mddev *mddev, + enum sync_action action) +{ + switch (action) { + case ACTION_RESYNC: + case ACTION_CHECK: + case ACTION_REPAIR: + atomic64_set(&mddev->resync_mismatches, 0); + fallthrough; + case ACTION_RESHAPE: + return mddev->resync_max_sectors; + case ACTION_RECOVER: + return mddev->dev_sectors; + default: + return 0; + } +} + +static sector_t md_sync_position(struct mddev *mddev, enum sync_action action) +{ + sector_t start = 0; + struct md_rdev *rdev; + + switch (action) { + case ACTION_CHECK: + case ACTION_REPAIR: + return mddev->resync_min; + case ACTION_RESYNC: + if (!mddev->bitmap) + return mddev->recovery_cp; + return 0; + case ACTION_RESHAPE: + /* + * If the original node aborts reshaping then we continue the + * reshaping, so set again to avoid restart reshape from the + * first beginning + */ + if (mddev_is_clustered(mddev) && + mddev->reshape_position != MaxSector) + return mddev->reshape_position; + return 0; + case ACTION_RECOVER: + start = MaxSector; + rcu_read_lock(); + rdev_for_each_rcu(rdev, mddev) + if (rdev->raid_disk >= 0 && + !test_bit(Journal, &rdev->flags) && + !test_bit(Faulty, &rdev->flags) && + !test_bit(In_sync, &rdev->flags) && + rdev->recovery_offset < start) + start = rdev->recovery_offset; + rcu_read_unlock(); + + /* If there is a bitmap, we need to make sure all + * writes that started before we added a spare + * complete before we start doing a recovery. + * Otherwise the write might complete and (via + * bitmap_endwrite) set a bit in the bitmap after the + * recovery has checked that bit and skipped that + * region. + */ + if (mddev->bitmap) { + mddev->pers->quiesce(mddev, 1); + mddev->pers->quiesce(mddev, 0); + } + return start; + default: + return MaxSector; + } +} + #define SYNC_MARKS 10 #define SYNC_MARK_STEP (3*HZ) #define UPDATE_FREQUENCY (5*60*HZ) @@ -8851,7 +8933,8 @@ void md_do_sync(struct md_thread *thread) sector_t last_check; int skipped = 0; struct md_rdev *rdev; - char *desc, *action = NULL; + enum sync_action action; + const char *desc; struct blk_plug plug; int ret; @@ -8882,21 +8965,9 @@ void md_do_sync(struct md_thread *thread) goto skip; } - if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) { - if (test_bit(MD_RECOVERY_CHECK, &mddev->recovery)) { - desc = "data-check"; - action = "check"; - } else if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) { - desc = "requested-resync"; - action = "repair"; - } else - desc = "resync"; - } else if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) - desc = "reshape"; - else - desc = "recovery"; - - mddev->last_sync_action = action ?: desc; + action = md_sync_action(mddev); + desc = md_sync_action_name(action); + mddev->last_sync_action = action; /* * Before starting a resync we must have set curr_resync to @@ -8964,56 +9035,8 @@ void md_do_sync(struct md_thread *thread) spin_unlock(&all_mddevs_lock); } while (mddev->curr_resync < MD_RESYNC_DELAYED); - j = 0; - if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) { - /* resync follows the size requested by the personality, - * which defaults to physical size, but can be virtual size - */ - max_sectors = mddev->resync_max_sectors; - atomic64_set(&mddev->resync_mismatches, 0); - /* we don't use the checkpoint if there's a bitmap */ - if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) - j = mddev->resync_min; - else if (!mddev->bitmap) - j = mddev->recovery_cp; - - } else if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) { - max_sectors = mddev->resync_max_sectors; - /* - * If the original node aborts reshaping then we continue the - * reshaping, so set j again to avoid restart reshape from the - * first beginning - */ - if (mddev_is_clustered(mddev) && - mddev->reshape_position != MaxSector) - j = mddev->reshape_position; - } else { - /* recovery follows the physical size of devices */ - max_sectors = mddev->dev_sectors; - j = MaxSector; - rcu_read_lock(); - rdev_for_each_rcu(rdev, mddev) - if (rdev->raid_disk >= 0 && - !test_bit(Journal, &rdev->flags) && - !test_bit(Faulty, &rdev->flags) && - !test_bit(In_sync, &rdev->flags) && - rdev->recovery_offset < j) - j = rdev->recovery_offset; - rcu_read_unlock(); - - /* If there is a bitmap, we need to make sure all - * writes that started before we added a spare - * complete before we start doing a recovery. - * Otherwise the write might complete and (via - * bitmap_endwrite) set a bit in the bitmap after the - * recovery has checked that bit and skipped that - * region. - */ - if (mddev->bitmap) { - mddev->pers->quiesce(mddev, 1); - mddev->pers->quiesce(mddev, 0); - } - } + max_sectors = md_sync_max_sectors(mddev, action); + j = md_sync_position(mddev, action); pr_info("md: %s of RAID array %s\n", desc, mdname(mddev)); pr_debug("md: minimum _guaranteed_ speed: %d KB/sec/disk.\n", speed_min(mddev)); @@ -9095,7 +9118,8 @@ void md_do_sync(struct md_thread *thread) if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) break; - sectors = mddev->pers->sync_request(mddev, j, &skipped); + sectors = mddev->pers->sync_request(mddev, j, max_sectors, + &skipped); if (sectors == 0) { set_bit(MD_RECOVERY_INTR, &mddev->recovery); break; @@ -9185,7 +9209,7 @@ void md_do_sync(struct md_thread *thread) mddev->curr_resync_completed = mddev->curr_resync; sysfs_notify_dirent_safe(mddev->sysfs_completed); } - mddev->pers->sync_request(mddev, max_sectors, &skipped); + mddev->pers->sync_request(mddev, max_sectors, max_sectors, &skipped); if (!test_bit(MD_RECOVERY_CHECK, &mddev->recovery) && mddev->curr_resync > MD_RESYNC_ACTIVE) { diff --git a/drivers/md/md.h b/drivers/md/md.h index ca085ecad504..a0d6827dced9 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -34,6 +34,61 @@ */ #define MD_FAILFAST (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT) +/* Status of sync thread. */ +enum sync_action { + /* + * Represent by MD_RECOVERY_SYNC, start when: + * 1) after assemble, sync data from first rdev to other copies, this + * must be done first before other sync actions and will only execute + * once; + * 2) resize the array(notice that this is not reshape), sync data for + * the new range; + */ + ACTION_RESYNC, + /* + * Represent by MD_RECOVERY_RECOVER, start when: + * 1) for new replacement, sync data based on the replace rdev or + * available copies from other rdev; + * 2) for new member disk while the array is degraded, sync data from + * other rdev; + * 3) reassemble after power failure or re-add a hot removed rdev, sync + * data from first rdev to other copies based on bitmap; + */ + ACTION_RECOVER, + /* + * Represent by MD_RECOVERY_SYNC | MD_RECOVERY_REQUESTED | + * MD_RECOVERY_CHECK, start when user echo "check" to sysfs api + * sync_action, used to check if data copies from differenct rdev are + * the same. The number of mismatch sectors will be exported to user + * by sysfs api mismatch_cnt; + */ + ACTION_CHECK, + /* + * Represent by MD_RECOVERY_SYNC | MD_RECOVERY_REQUESTED, start when + * user echo "repair" to sysfs api sync_action, usually paired with + * ACTION_CHECK, used to force syncing data once user found that there + * are inconsistent data, + */ + ACTION_REPAIR, + /* + * Represent by MD_RECOVERY_RESHAPE, start when new member disk is added + * to the conf, notice that this is different from spares or + * replacement; + */ + ACTION_RESHAPE, + /* + * Represent by MD_RECOVERY_FROZEN, can be set by sysfs api sync_action + * or internal usage like setting the array read-only, will forbid above + * actions. + */ + ACTION_FROZEN, + /* + * All above actions don't match. + */ + ACTION_IDLE, + NR_SYNC_ACTIONS, +}; + /* * The struct embedded in rdev is used to serialize IO. */ @@ -371,13 +426,12 @@ struct mddev { struct md_thread __rcu *thread; /* management thread */ struct md_thread __rcu *sync_thread; /* doing resync or reconstruct */ - /* 'last_sync_action' is initialized to "none". It is set when a - * sync operation (i.e "data-check", "requested-resync", "resync", - * "recovery", or "reshape") is started. It holds this value even + /* + * Set when a sync operation is started. It holds this value even * when the sync thread is "frozen" (interrupted) or "idle" (stopped - * or finished). It is overwritten when a new sync operation is begun. + * or finished). It is overwritten when a new sync operation is begun. */ - char *last_sync_action; + enum sync_action last_sync_action; sector_t curr_resync; /* last block scheduled */ /* As resync requests can complete out of order, we cannot easily track * how much resync has been completed. So we occasionally pause until @@ -540,8 +594,6 @@ struct mddev { */ struct list_head deleting; - /* Used to synchronize idle and frozen for action_store() */ - struct mutex sync_mutex; /* The sequence number for sync thread */ atomic_t sync_seq; @@ -551,22 +603,46 @@ struct mddev { }; enum recovery_flags { + /* flags for sync thread running status */ + /* - * If neither SYNC or RESHAPE are set, then it is a recovery. + * set when one of sync action is set and new sync thread need to be + * registered, or just add/remove spares from conf. */ - MD_RECOVERY_RUNNING, /* a thread is running, or about to be started */ - MD_RECOVERY_SYNC, /* actually doing a resync, not a recovery */ - MD_RECOVERY_RECOVER, /* doing recovery, or need to try it. */ - MD_RECOVERY_INTR, /* resync needs to be aborted for some reason */ - MD_RECOVERY_DONE, /* thread is done and is waiting to be reaped */ - MD_RECOVERY_NEEDED, /* we might need to start a resync/recover */ - MD_RECOVERY_REQUESTED, /* user-space has requested a sync (used with SYNC) */ - MD_RECOVERY_CHECK, /* user-space request for check-only, no repair */ - MD_RECOVERY_RESHAPE, /* A reshape is happening */ - MD_RECOVERY_FROZEN, /* User request to abort, and not restart, any action */ - MD_RECOVERY_ERROR, /* sync-action interrupted because io-error */ - MD_RECOVERY_WAIT, /* waiting for pers->start() to finish */ - MD_RESYNCING_REMOTE, /* remote node is running resync thread */ + MD_RECOVERY_NEEDED, + /* sync thread is running, or about to be started */ + MD_RECOVERY_RUNNING, + /* sync thread needs to be aborted for some reason */ + MD_RECOVERY_INTR, + /* sync thread is done and is waiting to be unregistered */ + MD_RECOVERY_DONE, + /* running sync thread must abort immediately, and not restart */ + MD_RECOVERY_FROZEN, + /* waiting for pers->start() to finish */ + MD_RECOVERY_WAIT, + /* interrupted because io-error */ + MD_RECOVERY_ERROR, + + /* flags determines sync action, see details in enum sync_action */ + + /* if just this flag is set, action is resync. */ + MD_RECOVERY_SYNC, + /* + * paired with MD_RECOVERY_SYNC, if MD_RECOVERY_CHECK is not set, + * action is repair, means user requested resync. + */ + MD_RECOVERY_REQUESTED, + /* + * paired with MD_RECOVERY_SYNC and MD_RECOVERY_REQUESTED, action is + * check. + */ + MD_RECOVERY_CHECK, + /* recovery, or need to try it */ + MD_RECOVERY_RECOVER, + /* reshape */ + MD_RECOVERY_RESHAPE, + /* remote node is running resync thread */ + MD_RESYNCING_REMOTE, }; enum md_ro_state { @@ -653,7 +729,8 @@ struct md_personality int (*hot_add_disk) (struct mddev *mddev, struct md_rdev *rdev); int (*hot_remove_disk) (struct mddev *mddev, struct md_rdev *rdev); int (*spare_active) (struct mddev *mddev); - sector_t (*sync_request)(struct mddev *mddev, sector_t sector_nr, int *skipped); + sector_t (*sync_request)(struct mddev *mddev, sector_t sector_nr, + sector_t max_sector, int *skipped); int (*resize) (struct mddev *mddev, sector_t sectors); sector_t (*size) (struct mddev *mddev, sector_t sectors, int raid_disks); int (*check_reshape) (struct mddev *mddev); @@ -772,7 +849,7 @@ static inline void safe_put_page(struct page *p) extern int register_md_personality(struct md_personality *p); extern int unregister_md_personality(struct md_personality *p); -extern int register_md_cluster_operations(struct md_cluster_operations *ops, +extern int register_md_cluster_operations(const struct md_cluster_operations *ops, struct module *module); extern int unregister_md_cluster_operations(void); extern int md_setup_cluster(struct mddev *mddev, int nodes); @@ -785,7 +862,10 @@ extern void md_unregister_thread(struct mddev *mddev, struct md_thread __rcu **t extern void md_wakeup_thread(struct md_thread __rcu *thread); extern void md_check_recovery(struct mddev *mddev); extern void md_reap_sync_thread(struct mddev *mddev); -extern bool md_write_start(struct mddev *mddev, struct bio *bi); +extern enum sync_action md_sync_action(struct mddev *mddev); +extern enum sync_action md_sync_action_by_name(const char *page); +extern const char *md_sync_action_name(enum sync_action action); +extern void md_write_start(struct mddev *mddev, struct bio *bi); extern void md_write_inc(struct mddev *mddev, struct bio *bi); extern void md_write_end(struct mddev *mddev); extern void md_done_sync(struct mddev *mddev, int blocks, int ok); @@ -809,11 +889,11 @@ extern void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev); extern void md_set_array_sectors(struct mddev *mddev, sector_t array_sectors); extern int md_check_no_bitmap(struct mddev *mddev); extern int md_integrity_register(struct mddev *mddev); -extern int md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev); extern int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale); extern int mddev_init(struct mddev *mddev); extern void mddev_destroy(struct mddev *mddev); +void md_init_stacking_limits(struct queue_limits *lim); struct mddev *md_alloc(dev_t dev, char *name); void mddev_put(struct mddev *mddev); extern int md_run(struct mddev *mddev); @@ -852,7 +932,7 @@ static inline void rdev_dec_pending(struct md_rdev *rdev, struct mddev *mddev) } } -extern struct md_cluster_operations *md_cluster_ops; +extern const struct md_cluster_operations *md_cluster_ops; static inline int mddev_is_clustered(struct mddev *mddev) { return mddev->cluster_info && mddev->bitmap_info.nodes > 1; @@ -908,7 +988,9 @@ void md_autostart_arrays(int part); int md_set_array_info(struct mddev *mddev, struct mdu_array_info_s *info); int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info); int do_md_run(struct mddev *mddev); -void mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim); +#define MDDEV_STACK_INTEGRITY (1u << 0) +int mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim, + unsigned int flags); int mddev_stack_new_rdev(struct mddev *mddev, struct md_rdev *rdev); void mddev_update_io_opt(struct mddev *mddev, unsigned int nr_stripes); diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index c5d4aeb68404..32d587524778 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -365,30 +365,30 @@ static sector_t raid0_size(struct mddev *mddev, sector_t sectors, int raid_disks return array_sectors; } -static void free_conf(struct mddev *mddev, struct r0conf *conf) +static void raid0_free(struct mddev *mddev, void *priv) { + struct r0conf *conf = priv; + kfree(conf->strip_zone); kfree(conf->devlist); kfree(conf); } -static void raid0_free(struct mddev *mddev, void *priv) -{ - struct r0conf *conf = priv; - - free_conf(mddev, conf); -} - static int raid0_set_limits(struct mddev *mddev) { struct queue_limits lim; + int err; - blk_set_stacking_limits(&lim); + md_init_stacking_limits(&lim); lim.max_hw_sectors = mddev->chunk_sectors; lim.max_write_zeroes_sectors = mddev->chunk_sectors; lim.io_min = mddev->chunk_sectors << 9; lim.io_opt = lim.io_min * mddev->raid_disks; - mddev_stack_rdev_limits(mddev, &lim); + err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY); + if (err) { + queue_limits_cancel_update(mddev->gendisk->queue); + return err; + } return queue_limits_set(mddev->gendisk->queue, &lim); } @@ -415,7 +415,7 @@ static int raid0_run(struct mddev *mddev) if (!mddev_is_dm(mddev)) { ret = raid0_set_limits(mddev); if (ret) - goto out_free_conf; + return ret; } /* calculate array device size */ @@ -427,13 +427,7 @@ static int raid0_run(struct mddev *mddev) dump_zones(mddev); - ret = md_integrity_register(mddev); - if (ret) - goto out_free_conf; - return 0; -out_free_conf: - free_conf(mddev, conf); - return ret; + return md_integrity_register(mddev); } /* diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 7b8a71ca66dd..04a0c2ca1732 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1687,8 +1687,7 @@ static bool raid1_make_request(struct mddev *mddev, struct bio *bio) if (bio_data_dir(bio) == READ) raid1_read_request(mddev, bio, sectors, NULL); else { - if (!md_write_start(mddev,bio)) - return false; + md_write_start(mddev,bio); raid1_write_request(mddev, bio, sectors); } return true; @@ -1907,9 +1906,6 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev) if (mddev->recovery_disabled == conf->recovery_disabled) return -EBUSY; - if (md_integrity_add_rdev(rdev, mddev)) - return -ENXIO; - if (rdev->raid_disk >= 0) first = last = rdev->raid_disk; @@ -2757,12 +2753,12 @@ static struct r1bio *raid1_alloc_init_r1buf(struct r1conf *conf) */ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr, - int *skipped) + sector_t max_sector, int *skipped) { struct r1conf *conf = mddev->private; struct r1bio *r1_bio; struct bio *bio; - sector_t max_sector, nr_sectors; + sector_t nr_sectors; int disk = -1; int i; int wonly = -1; @@ -2778,7 +2774,6 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr, if (init_resync(conf)) return 0; - max_sector = mddev->dev_sectors; if (sector_nr >= max_sector) { /* If we aborted, we need to abort the * sync on the 'current' bitmap chunk (there will @@ -3197,14 +3192,18 @@ static struct r1conf *setup_conf(struct mddev *mddev) static int raid1_set_limits(struct mddev *mddev) { struct queue_limits lim; + int err; - blk_set_stacking_limits(&lim); + md_init_stacking_limits(&lim); lim.max_write_zeroes_sectors = 0; - mddev_stack_rdev_limits(mddev, &lim); + err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY); + if (err) { + queue_limits_cancel_update(mddev->gendisk->queue); + return err; + } return queue_limits_set(mddev->gendisk->queue, &lim); } -static void raid1_free(struct mddev *mddev, void *priv); static int raid1_run(struct mddev *mddev) { struct r1conf *conf; @@ -3238,7 +3237,7 @@ static int raid1_run(struct mddev *mddev) if (!mddev_is_dm(mddev)) { ret = raid1_set_limits(mddev); if (ret) - goto abort; + return ret; } mddev->degraded = 0; @@ -3252,8 +3251,7 @@ static int raid1_run(struct mddev *mddev) */ if (conf->raid_disks - mddev->degraded < 1) { md_unregister_thread(mddev, &conf->thread); - ret = -EINVAL; - goto abort; + return -EINVAL; } if (conf->raid_disks - mddev->degraded == 1) @@ -3277,14 +3275,8 @@ static int raid1_run(struct mddev *mddev) md_set_array_sectors(mddev, raid1_size(mddev, 0, 0)); ret = md_integrity_register(mddev); - if (ret) { + if (ret) md_unregister_thread(mddev, &mddev->thread); - goto abort; - } - return 0; - -abort: - raid1_free(mddev, conf); return ret; } diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index a4556d2e46bf..2a9c4ee982e0 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1836,8 +1836,7 @@ static bool raid10_make_request(struct mddev *mddev, struct bio *bio) && md_flush_request(mddev, bio)) return true; - if (!md_write_start(mddev, bio)) - return false; + md_write_start(mddev, bio); if (unlikely(bio_op(bio) == REQ_OP_DISCARD)) if (!raid10_handle_discard(mddev, bio)) @@ -2083,9 +2082,6 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev) if (rdev->saved_raid_disk < 0 && !_enough(conf, 1, -1)) return -EINVAL; - if (md_integrity_add_rdev(rdev, mddev)) - return -ENXIO; - if (rdev->raid_disk >= 0) first = last = rdev->raid_disk; @@ -3140,12 +3136,12 @@ static void raid10_set_cluster_sync_high(struct r10conf *conf) */ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, - int *skipped) + sector_t max_sector, int *skipped) { struct r10conf *conf = mddev->private; struct r10bio *r10_bio; struct bio *biolist = NULL, *bio; - sector_t max_sector, nr_sectors; + sector_t nr_sectors; int i; int max_sync; sector_t sync_blocks; @@ -3175,10 +3171,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, return 0; skipped: - max_sector = mddev->dev_sectors; - if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) || - test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) - max_sector = mddev->resync_max_sectors; if (sector_nr >= max_sector) { conf->cluster_sync_low = 0; conf->cluster_sync_high = 0; @@ -3980,12 +3972,17 @@ static int raid10_set_queue_limits(struct mddev *mddev) { struct r10conf *conf = mddev->private; struct queue_limits lim; + int err; - blk_set_stacking_limits(&lim); + md_init_stacking_limits(&lim); lim.max_write_zeroes_sectors = 0; lim.io_min = mddev->chunk_sectors << 9; lim.io_opt = lim.io_min * raid10_nr_stripes(conf); - mddev_stack_rdev_limits(mddev, &lim); + err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY); + if (err) { + queue_limits_cancel_update(mddev->gendisk->queue); + return err; + } return queue_limits_set(mddev->gendisk->queue, &lim); } diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 2bd1ce9b3922..c14cf2410365 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -155,7 +155,7 @@ static int raid6_idx_to_slot(int idx, struct stripe_head *sh, return slot; } -static void print_raid5_conf (struct r5conf *conf); +static void print_raid5_conf(struct r5conf *conf); static int stripe_operations_active(struct stripe_head *sh) { @@ -5899,6 +5899,39 @@ out: return ret; } +enum reshape_loc { + LOC_NO_RESHAPE, + LOC_AHEAD_OF_RESHAPE, + LOC_INSIDE_RESHAPE, + LOC_BEHIND_RESHAPE, +}; + +static enum reshape_loc get_reshape_loc(struct mddev *mddev, + struct r5conf *conf, sector_t logical_sector) +{ + sector_t reshape_progress, reshape_safe; + /* + * Spinlock is needed as reshape_progress may be + * 64bit on a 32bit platform, and so it might be + * possible to see a half-updated value + * Of course reshape_progress could change after + * the lock is dropped, so once we get a reference + * to the stripe that we think it is, we will have + * to check again. + */ + spin_lock_irq(&conf->device_lock); + reshape_progress = conf->reshape_progress; + reshape_safe = conf->reshape_safe; + spin_unlock_irq(&conf->device_lock); + if (reshape_progress == MaxSector) + return LOC_NO_RESHAPE; + if (ahead_of_reshape(mddev, logical_sector, reshape_progress)) + return LOC_AHEAD_OF_RESHAPE; + if (ahead_of_reshape(mddev, logical_sector, reshape_safe)) + return LOC_INSIDE_RESHAPE; + return LOC_BEHIND_RESHAPE; +} + static enum stripe_result make_stripe_request(struct mddev *mddev, struct r5conf *conf, struct stripe_request_ctx *ctx, sector_t logical_sector, struct bio *bi) @@ -5913,28 +5946,14 @@ static enum stripe_result make_stripe_request(struct mddev *mddev, seq = read_seqcount_begin(&conf->gen_lock); if (unlikely(conf->reshape_progress != MaxSector)) { - /* - * Spinlock is needed as reshape_progress may be - * 64bit on a 32bit platform, and so it might be - * possible to see a half-updated value - * Of course reshape_progress could change after - * the lock is dropped, so once we get a reference - * to the stripe that we think it is, we will have - * to check again. - */ - spin_lock_irq(&conf->device_lock); - if (ahead_of_reshape(mddev, logical_sector, - conf->reshape_progress)) { - previous = 1; - } else { - if (ahead_of_reshape(mddev, logical_sector, - conf->reshape_safe)) { - spin_unlock_irq(&conf->device_lock); - ret = STRIPE_SCHEDULE_AND_RETRY; - goto out; - } + enum reshape_loc loc = get_reshape_loc(mddev, conf, + logical_sector); + if (loc == LOC_INSIDE_RESHAPE) { + ret = STRIPE_SCHEDULE_AND_RETRY; + goto out; } - spin_unlock_irq(&conf->device_lock); + if (loc == LOC_AHEAD_OF_RESHAPE) + previous = 1; } new_sector = raid5_compute_sector(conf, logical_sector, previous, @@ -6078,8 +6097,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi) ctx.do_flush = bi->bi_opf & REQ_PREFLUSH; } - if (!md_write_start(mddev, bi)) - return false; + md_write_start(mddev, bi); /* * If array is degraded, better not do chunk aligned read because * later we might have to read it again in order to reconstruct @@ -6113,8 +6131,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi) /* Bail out if conflicts with reshape and REQ_NOWAIT is set */ if ((bi->bi_opf & REQ_NOWAIT) && (conf->reshape_progress != MaxSector) && - !ahead_of_reshape(mddev, logical_sector, conf->reshape_progress) && - ahead_of_reshape(mddev, logical_sector, conf->reshape_safe)) { + get_reshape_loc(mddev, conf, logical_sector) == LOC_INSIDE_RESHAPE) { bio_wouldblock_error(bi); if (rw == WRITE) md_write_end(mddev); @@ -6255,7 +6272,9 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk safepos = conf->reshape_safe; sector_div(safepos, data_disks); if (mddev->reshape_backwards) { - BUG_ON(writepos < reshape_sectors); + if (WARN_ON(writepos < reshape_sectors)) + return MaxSector; + writepos -= reshape_sectors; readpos += reshape_sectors; safepos += reshape_sectors; @@ -6273,14 +6292,18 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk * to set 'stripe_addr' which is where we will write to. */ if (mddev->reshape_backwards) { - BUG_ON(conf->reshape_progress == 0); + if (WARN_ON(conf->reshape_progress == 0)) + return MaxSector; + stripe_addr = writepos; - BUG_ON((mddev->dev_sectors & - ~((sector_t)reshape_sectors - 1)) - - reshape_sectors - stripe_addr - != sector_nr); + if (WARN_ON((mddev->dev_sectors & + ~((sector_t)reshape_sectors - 1)) - + reshape_sectors - stripe_addr != sector_nr)) + return MaxSector; } else { - BUG_ON(writepos != sector_nr + reshape_sectors); + if (WARN_ON(writepos != sector_nr + reshape_sectors)) + return MaxSector; + stripe_addr = sector_nr; } @@ -6458,11 +6481,10 @@ ret: } static inline sector_t raid5_sync_request(struct mddev *mddev, sector_t sector_nr, - int *skipped) + sector_t max_sector, int *skipped) { struct r5conf *conf = mddev->private; struct stripe_head *sh; - sector_t max_sector = mddev->dev_sectors; sector_t sync_blocks; int still_degraded = 0; int i; @@ -7082,12 +7104,14 @@ raid5_store_skip_copy(struct mddev *mddev, const char *page, size_t len) err = -ENODEV; else if (new != conf->skip_copy) { struct request_queue *q = mddev->gendisk->queue; + struct queue_limits lim = queue_limits_start_update(q); conf->skip_copy = new; if (new) - blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q); + lim.features |= BLK_FEAT_STABLE_WRITES; else - blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, q); + lim.features &= ~BLK_FEAT_STABLE_WRITES; + err = queue_limits_commit_update(q, &lim); } mddev_unlock_and_resume(mddev); return err ?: len; @@ -7562,11 +7586,11 @@ static struct r5conf *setup_conf(struct mddev *mddev) if (test_bit(Replacement, &rdev->flags)) { if (disk->replacement) goto abort; - RCU_INIT_POINTER(disk->replacement, rdev); + disk->replacement = rdev; } else { if (disk->rdev) goto abort; - RCU_INIT_POINTER(disk->rdev, rdev); + disk->rdev = rdev; } if (test_bit(In_sync, &rdev->flags)) { @@ -7702,13 +7726,13 @@ static int raid5_set_limits(struct mddev *mddev) */ stripe = roundup_pow_of_two(data_disks * (mddev->chunk_sectors << 9)); - blk_set_stacking_limits(&lim); + md_init_stacking_limits(&lim); lim.io_min = mddev->chunk_sectors << 9; lim.io_opt = lim.io_min * (conf->raid_disks - conf->max_degraded); - lim.raid_partial_stripes_expensive = 1; + lim.features |= BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE; lim.discard_granularity = stripe; lim.max_write_zeroes_sectors = 0; - mddev_stack_rdev_limits(mddev, &lim); + mddev_stack_rdev_limits(mddev, &lim, 0); rdev_for_each(rdev, mddev) queue_limits_stack_bdev(&lim, rdev->bdev, rdev->new_data_offset, mddev->gendisk->disk_name); @@ -8048,7 +8072,7 @@ static void raid5_status(struct seq_file *seq, struct mddev *mddev) seq_printf (seq, "]"); } -static void print_raid5_conf (struct r5conf *conf) +static void print_raid5_conf(struct r5conf *conf) { struct md_rdev *rdev; int i; @@ -8062,15 +8086,13 @@ static void print_raid5_conf (struct r5conf *conf) conf->raid_disks, conf->raid_disks - conf->mddev->degraded); - rcu_read_lock(); for (i = 0; i < conf->raid_disks; i++) { - rdev = rcu_dereference(conf->disks[i].rdev); + rdev = conf->disks[i].rdev; if (rdev) pr_debug(" disk %d, o:%d, dev:%pg\n", i, !test_bit(Faulty, &rdev->flags), rdev->bdev); } - rcu_read_unlock(); } static int raid5_spare_active(struct mddev *mddev) diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 367509b5b646..2c9963248fcb 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -2466,8 +2466,7 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card, struct mmc_blk_data *md; int devidx, ret; char cap_str[10]; - bool cache_enabled = false; - bool fua_enabled = false; + unsigned int features = 0; devidx = ida_alloc_max(&mmc_blk_ida, max_devices - 1, GFP_KERNEL); if (devidx < 0) { @@ -2499,7 +2498,24 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card, */ md->read_only = mmc_blk_readonly(card); - md->disk = mmc_init_queue(&md->queue, card); + if (mmc_host_cmd23(card->host)) { + if ((mmc_card_mmc(card) && + card->csd.mmca_vsn >= CSD_SPEC_VER_3) || + (mmc_card_sd(card) && + card->scr.cmds & SD_SCR_CMD23_SUPPORT)) + md->flags |= MMC_BLK_CMD23; + } + + if (md->flags & MMC_BLK_CMD23 && + ((card->ext_csd.rel_param & EXT_CSD_WR_REL_PARAM_EN) || + card->ext_csd.rel_sectors)) { + md->flags |= MMC_BLK_REL_WR; + features |= (BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA); + } else if (mmc_cache_enabled(card->host)) { + features |= BLK_FEAT_WRITE_CACHE; + } + + md->disk = mmc_init_queue(&md->queue, card, features); if (IS_ERR(md->disk)) { ret = PTR_ERR(md->disk); goto err_kfree; @@ -2539,26 +2555,6 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card, set_capacity(md->disk, size); - if (mmc_host_cmd23(card->host)) { - if ((mmc_card_mmc(card) && - card->csd.mmca_vsn >= CSD_SPEC_VER_3) || - (mmc_card_sd(card) && - card->scr.cmds & SD_SCR_CMD23_SUPPORT)) - md->flags |= MMC_BLK_CMD23; - } - - if (md->flags & MMC_BLK_CMD23 && - ((card->ext_csd.rel_param & EXT_CSD_WR_REL_PARAM_EN) || - card->ext_csd.rel_sectors)) { - md->flags |= MMC_BLK_REL_WR; - fua_enabled = true; - cache_enabled = true; - } - if (mmc_cache_enabled(card->host)) - cache_enabled = true; - - blk_queue_write_cache(md->queue.queue, cache_enabled, fua_enabled); - string_get_size((u64)size, 512, STRING_UNITS_2, cap_str, sizeof(cap_str)); pr_info("%s: %s %s %s%s\n", diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c index 241cdc2b2a2a..d0b3ca8a11f0 100644 --- a/drivers/mmc/core/queue.c +++ b/drivers/mmc/core/queue.c @@ -344,10 +344,12 @@ static const struct blk_mq_ops mmc_mq_ops = { }; static struct gendisk *mmc_alloc_disk(struct mmc_queue *mq, - struct mmc_card *card) + struct mmc_card *card, unsigned int features) { struct mmc_host *host = card->host; - struct queue_limits lim = { }; + struct queue_limits lim = { + .features = features, + }; struct gendisk *disk; if (mmc_can_erase(card)) @@ -376,18 +378,16 @@ static struct gendisk *mmc_alloc_disk(struct mmc_queue *mq, lim.max_segments = host->max_segs; } + if (mmc_host_is_spi(host) && host->use_spi_crc) + lim.features |= BLK_FEAT_STABLE_WRITES; + disk = blk_mq_alloc_disk(&mq->tag_set, &lim, mq); if (IS_ERR(disk)) return disk; mq->queue = disk->queue; - if (mmc_host_is_spi(host) && host->use_spi_crc) - blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, mq->queue); blk_queue_rq_timeout(mq->queue, 60 * HZ); - blk_queue_flag_set(QUEUE_FLAG_NONROT, mq->queue); - blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, mq->queue); - dma_set_max_seg_size(mmc_dev(host), queue_max_segment_size(mq->queue)); INIT_WORK(&mq->recovery_work, mmc_mq_recovery_handler); @@ -413,10 +413,12 @@ static inline bool mmc_merge_capable(struct mmc_host *host) * mmc_init_queue - initialise a queue structure. * @mq: mmc queue * @card: mmc card to attach this queue + * @features: block layer features (BLK_FEAT_*) * * Initialise a MMC card request queue. */ -struct gendisk *mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card) +struct gendisk *mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, + unsigned int features) { struct mmc_host *host = card->host; struct gendisk *disk; @@ -460,7 +462,7 @@ struct gendisk *mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card) return ERR_PTR(ret); - disk = mmc_alloc_disk(mq, card); + disk = mmc_alloc_disk(mq, card, features); if (IS_ERR(disk)) blk_mq_free_tag_set(&mq->tag_set); return disk; diff --git a/drivers/mmc/core/queue.h b/drivers/mmc/core/queue.h index 9ade3bcbb714..1498840a4ea0 100644 --- a/drivers/mmc/core/queue.h +++ b/drivers/mmc/core/queue.h @@ -94,7 +94,8 @@ struct mmc_queue { struct work_struct complete_work; }; -struct gendisk *mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card); +struct gendisk *mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, + unsigned int features); extern void mmc_cleanup_queue(struct mmc_queue *); extern void mmc_queue_suspend(struct mmc_queue *); extern void mmc_queue_resume(struct mmc_queue *); diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index 3caa0717d46c..47ead84407cd 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -336,6 +336,8 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new) lim.logical_block_size = tr->blksize; if (tr->discard) lim.max_hw_discard_sectors = UINT_MAX; + if (tr->flush) + lim.features |= BLK_FEAT_WRITE_CACHE; /* Create gendisk */ gd = blk_mq_alloc_disk(new->tag_set, &lim, new); @@ -372,13 +374,6 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new) /* Create the request queue */ spin_lock_init(&new->queue_lock); INIT_LIST_HEAD(&new->rq_list); - - if (tr->flush) - blk_queue_write_cache(new->rq, true, false); - - blk_queue_flag_set(QUEUE_FLAG_NONROT, new->rq); - blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, new->rq); - gd->queue = new->rq; if (new->readonly) diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c index 1e5aedaf8c7b..e79c06d65bb7 100644 --- a/drivers/nvdimm/btt.c +++ b/drivers/nvdimm/btt.c @@ -1501,9 +1501,15 @@ static int btt_blk_init(struct btt *btt) .logical_block_size = btt->sector_size, .max_hw_sectors = UINT_MAX, .max_integrity_segments = 1, + .features = BLK_FEAT_SYNCHRONOUS, }; int rc; + if (btt_meta_size(btt) && IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY)) { + lim.integrity.tuple_size = btt_meta_size(btt); + lim.integrity.tag_size = btt_meta_size(btt); + } + btt->btt_disk = blk_alloc_disk(&lim, NUMA_NO_NODE); if (IS_ERR(btt->btt_disk)) return PTR_ERR(btt->btt_disk); @@ -1513,17 +1519,6 @@ static int btt_blk_init(struct btt *btt) btt->btt_disk->fops = &btt_fops; btt->btt_disk->private_data = btt; - blk_queue_flag_set(QUEUE_FLAG_NONROT, btt->btt_disk->queue); - blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, btt->btt_disk->queue); - - if (btt_meta_size(btt) && IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY)) { - struct blk_integrity bi = { - .tuple_size = btt_meta_size(btt), - .tag_size = btt_meta_size(btt), - }; - blk_integrity_register(btt->btt_disk, &bi); - } - set_capacity(btt->btt_disk, btt->nlba * btt->sector_size >> 9); rc = device_add_disk(&btt->nd_btt->dev, btt->btt_disk, NULL); if (rc) diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 598fe2e89bda..1dd74c969d5a 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -455,6 +455,8 @@ static int pmem_attach_disk(struct device *dev, .logical_block_size = pmem_sector_size(ndns), .physical_block_size = PAGE_SIZE, .max_hw_sectors = UINT_MAX, + .features = BLK_FEAT_WRITE_CACHE | + BLK_FEAT_SYNCHRONOUS, }; int nid = dev_to_node(dev), fua; struct resource *res = &nsio->res; @@ -463,7 +465,6 @@ static int pmem_attach_disk(struct device *dev, struct dax_device *dax_dev; struct nd_pfn_sb *pfn_sb; struct pmem_device *pmem; - struct request_queue *q; struct gendisk *disk; void *addr; int rc; @@ -495,6 +496,10 @@ static int pmem_attach_disk(struct device *dev, dev_warn(dev, "unable to guarantee persistence of writes\n"); fua = 0; } + if (fua) + lim.features |= BLK_FEAT_FUA; + if (is_nd_pfn(dev)) + lim.features |= BLK_FEAT_DAX; if (!devm_request_mem_region(dev, res->start, resource_size(res), dev_name(&ndns->dev))) { @@ -505,7 +510,6 @@ static int pmem_attach_disk(struct device *dev, disk = blk_alloc_disk(&lim, nid); if (IS_ERR(disk)) return PTR_ERR(disk); - q = disk->queue; pmem->disk = disk; pmem->pgmap.owner = pmem; @@ -543,12 +547,6 @@ static int pmem_attach_disk(struct device *dev, } pmem->virt_addr = addr; - blk_queue_write_cache(q, true, fua); - blk_queue_flag_set(QUEUE_FLAG_NONROT, q); - blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, q); - if (pmem->pfn_flags & PFN_MAP) - blk_queue_flag_set(QUEUE_FLAG_DAX, q); - disk->fops = &pmem_fops; disk->private_data = pmem; nvdimm_namespace_disk_name(ndns, disk->disk_name); diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig index b309c8be720f..a3caef75aa0a 100644 --- a/drivers/nvme/host/Kconfig +++ b/drivers/nvme/host/Kconfig @@ -1,7 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only config NVME_CORE tristate - select BLK_DEV_INTEGRITY_T10 if BLK_DEV_INTEGRITY config BLK_DEV_NVME tristate "NVM Express block device" diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c index 0cfa39361d3b..b1387dc459a3 100644 --- a/drivers/nvme/host/apple.c +++ b/drivers/nvme/host/apple.c @@ -1388,7 +1388,7 @@ static void devm_apple_nvme_mempool_destroy(void *data) mempool_destroy(data); } -static int apple_nvme_probe(struct platform_device *pdev) +static struct apple_nvme *apple_nvme_alloc(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct apple_nvme *anv; @@ -1396,7 +1396,7 @@ static int apple_nvme_probe(struct platform_device *pdev) anv = devm_kzalloc(dev, sizeof(*anv), GFP_KERNEL); if (!anv) - return -ENOMEM; + return ERR_PTR(-ENOMEM); anv->dev = get_device(dev); anv->adminq.is_adminq = true; @@ -1516,10 +1516,30 @@ static int apple_nvme_probe(struct platform_device *pdev) goto put_dev; } + return anv; +put_dev: + put_device(anv->dev); + return ERR_PTR(ret); +} + +static int apple_nvme_probe(struct platform_device *pdev) +{ + struct apple_nvme *anv; + int ret; + + anv = apple_nvme_alloc(pdev); + if (IS_ERR(anv)) + return PTR_ERR(anv); + + ret = nvme_add_ctrl(&anv->ctrl); + if (ret) + goto out_put_ctrl; + anv->ctrl.admin_q = blk_mq_alloc_queue(&anv->admin_tagset, NULL, NULL); if (IS_ERR(anv->ctrl.admin_q)) { ret = -ENOMEM; - goto put_dev; + anv->ctrl.admin_q = NULL; + goto out_uninit_ctrl; } nvme_reset_ctrl(&anv->ctrl); @@ -1527,8 +1547,10 @@ static int apple_nvme_probe(struct platform_device *pdev) return 0; -put_dev: - put_device(anv->dev); +out_uninit_ctrl: + nvme_uninit_ctrl(&anv->ctrl); +out_put_ctrl: + nvme_put_ctrl(&anv->ctrl); return ret; } diff --git a/drivers/nvme/host/constants.c b/drivers/nvme/host/constants.c index 6f2ebb5fcdb0..2b9e6cfaf2a8 100644 --- a/drivers/nvme/host/constants.c +++ b/drivers/nvme/host/constants.c @@ -173,7 +173,7 @@ static const char * const nvme_statuses[] = { const char *nvme_get_error_status_str(u16 status) { - status &= 0x7ff; + status &= NVME_SCT_SC_MASK; if (status < ARRAY_SIZE(nvme_statuses) && nvme_statuses[status]) return nvme_statuses[status]; return "Unknown"; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 782090ce0bc1..19917253ba7b 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -110,7 +110,7 @@ struct workqueue_struct *nvme_delete_wq; EXPORT_SYMBOL_GPL(nvme_delete_wq); static LIST_HEAD(nvme_subsystems); -static DEFINE_MUTEX(nvme_subsystems_lock); +DEFINE_MUTEX(nvme_subsystems_lock); static DEFINE_IDA(nvme_instance_ida); static dev_t nvme_ctrl_base_chr_devt; @@ -261,7 +261,7 @@ void nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl) static blk_status_t nvme_error_status(u16 status) { - switch (status & 0x7ff) { + switch (status & NVME_SCT_SC_MASK) { case NVME_SC_SUCCESS: return BLK_STS_OK; case NVME_SC_CAP_EXCEEDED: @@ -307,7 +307,7 @@ static void nvme_retry_req(struct request *req) u16 crd; /* The mask and shift result must be <= 3 */ - crd = (nvme_req(req)->status & NVME_SC_CRD) >> 11; + crd = (nvme_req(req)->status & NVME_STATUS_CRD) >> 11; if (crd) delay = nvme_req(req)->ctrl->crdt[crd - 1] * 100; @@ -329,10 +329,10 @@ static void nvme_log_error(struct request *req) nvme_sect_to_lba(ns->head, blk_rq_pos(req)), blk_rq_bytes(req) >> ns->head->lba_shift, nvme_get_error_status_str(nr->status), - nr->status >> 8 & 7, /* Status Code Type */ - nr->status & 0xff, /* Status Code */ - nr->status & NVME_SC_MORE ? "MORE " : "", - nr->status & NVME_SC_DNR ? "DNR " : ""); + NVME_SCT(nr->status), /* Status Code Type */ + nr->status & NVME_SC_MASK, /* Status Code */ + nr->status & NVME_STATUS_MORE ? "MORE " : "", + nr->status & NVME_STATUS_DNR ? "DNR " : ""); return; } @@ -341,10 +341,10 @@ static void nvme_log_error(struct request *req) nvme_get_admin_opcode_str(nr->cmd->common.opcode), nr->cmd->common.opcode, nvme_get_error_status_str(nr->status), - nr->status >> 8 & 7, /* Status Code Type */ - nr->status & 0xff, /* Status Code */ - nr->status & NVME_SC_MORE ? "MORE " : "", - nr->status & NVME_SC_DNR ? "DNR " : ""); + NVME_SCT(nr->status), /* Status Code Type */ + nr->status & NVME_SC_MASK, /* Status Code */ + nr->status & NVME_STATUS_MORE ? "MORE " : "", + nr->status & NVME_STATUS_DNR ? "DNR " : ""); } static void nvme_log_err_passthru(struct request *req) @@ -359,10 +359,10 @@ static void nvme_log_err_passthru(struct request *req) nvme_get_admin_opcode_str(nr->cmd->common.opcode), nr->cmd->common.opcode, nvme_get_error_status_str(nr->status), - nr->status >> 8 & 7, /* Status Code Type */ - nr->status & 0xff, /* Status Code */ - nr->status & NVME_SC_MORE ? "MORE " : "", - nr->status & NVME_SC_DNR ? "DNR " : "", + NVME_SCT(nr->status), /* Status Code Type */ + nr->status & NVME_SC_MASK, /* Status Code */ + nr->status & NVME_STATUS_MORE ? "MORE " : "", + nr->status & NVME_STATUS_DNR ? "DNR " : "", nr->cmd->common.cdw10, nr->cmd->common.cdw11, nr->cmd->common.cdw12, @@ -384,11 +384,11 @@ static inline enum nvme_disposition nvme_decide_disposition(struct request *req) return COMPLETE; if (blk_noretry_request(req) || - (nvme_req(req)->status & NVME_SC_DNR) || + (nvme_req(req)->status & NVME_STATUS_DNR) || nvme_req(req)->retries >= nvme_max_retries) return COMPLETE; - if ((nvme_req(req)->status & 0x7ff) == NVME_SC_AUTH_REQUIRED) + if ((nvme_req(req)->status & NVME_SCT_SC_MASK) == NVME_SC_AUTH_REQUIRED) return AUTHENTICATE; if (req->cmd_flags & REQ_NVME_MPATH) { @@ -927,6 +927,36 @@ static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns, return BLK_STS_OK; } +/* + * NVMe does not support a dedicated command to issue an atomic write. A write + * which does adhere to the device atomic limits will silently be executed + * non-atomically. The request issuer should ensure that the write is within + * the queue atomic writes limits, but just validate this in case it is not. + */ +static bool nvme_valid_atomic_write(struct request *req) +{ + struct request_queue *q = req->q; + u32 boundary_bytes = queue_atomic_write_boundary_bytes(q); + + if (blk_rq_bytes(req) > queue_atomic_write_unit_max_bytes(q)) + return false; + + if (boundary_bytes) { + u64 mask = boundary_bytes - 1, imask = ~mask; + u64 start = blk_rq_pos(req) << SECTOR_SHIFT; + u64 end = start + blk_rq_bytes(req) - 1; + + /* If greater then must be crossing a boundary */ + if (blk_rq_bytes(req) > boundary_bytes) + return false; + + if ((start & imask) != (end & imask)) + return false; + } + + return true; +} + static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns, struct request *req, struct nvme_command *cmnd, enum nvme_opcode op) @@ -942,6 +972,9 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns, if (req->cmd_flags & REQ_RAHEAD) dsmgmt |= NVME_RW_DSM_FREQ_PREFETCH; + if (req->cmd_flags & REQ_ATOMIC && !nvme_valid_atomic_write(req)) + return BLK_STS_INVAL; + cmnd->rw.opcode = op; cmnd->rw.flags = 0; cmnd->rw.nsid = cpu_to_le32(ns->head->ns_id); @@ -1224,7 +1257,7 @@ EXPORT_SYMBOL_NS_GPL(nvme_passthru_end, NVME_TARGET_PASSTHRU); /* * Recommended frequency for KATO commands per NVMe 1.4 section 7.12.1: - * + * * The host should send Keep Alive commands at half of the Keep Alive Timeout * accounting for transport roundtrip times [..]. */ @@ -1724,11 +1757,12 @@ int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo) return 0; } -static bool nvme_init_integrity(struct gendisk *disk, struct nvme_ns_head *head) +static bool nvme_init_integrity(struct gendisk *disk, struct nvme_ns_head *head, + struct queue_limits *lim) { - struct blk_integrity integrity = { }; + struct blk_integrity *bi = &lim->integrity; - blk_integrity_unregister(disk); + memset(bi, 0, sizeof(*bi)); if (!head->ms) return true; @@ -1745,17 +1779,16 @@ static bool nvme_init_integrity(struct gendisk *disk, struct nvme_ns_head *head) case NVME_NS_DPS_PI_TYPE3: switch (head->guard_type) { case NVME_NVM_NS_16B_GUARD: - integrity.profile = &t10_pi_type3_crc; - integrity.tag_size = sizeof(u16) + sizeof(u32); - integrity.flags |= BLK_INTEGRITY_DEVICE_CAPABLE; + bi->csum_type = BLK_INTEGRITY_CSUM_CRC; + bi->tag_size = sizeof(u16) + sizeof(u32); + bi->flags |= BLK_INTEGRITY_DEVICE_CAPABLE; break; case NVME_NVM_NS_64B_GUARD: - integrity.profile = &ext_pi_type3_crc64; - integrity.tag_size = sizeof(u16) + 6; - integrity.flags |= BLK_INTEGRITY_DEVICE_CAPABLE; + bi->csum_type = BLK_INTEGRITY_CSUM_CRC64; + bi->tag_size = sizeof(u16) + 6; + bi->flags |= BLK_INTEGRITY_DEVICE_CAPABLE; break; default: - integrity.profile = NULL; break; } break; @@ -1763,28 +1796,27 @@ static bool nvme_init_integrity(struct gendisk *disk, struct nvme_ns_head *head) case NVME_NS_DPS_PI_TYPE2: switch (head->guard_type) { case NVME_NVM_NS_16B_GUARD: - integrity.profile = &t10_pi_type1_crc; - integrity.tag_size = sizeof(u16); - integrity.flags |= BLK_INTEGRITY_DEVICE_CAPABLE; + bi->csum_type = BLK_INTEGRITY_CSUM_CRC; + bi->tag_size = sizeof(u16); + bi->flags |= BLK_INTEGRITY_DEVICE_CAPABLE | + BLK_INTEGRITY_REF_TAG; break; case NVME_NVM_NS_64B_GUARD: - integrity.profile = &ext_pi_type1_crc64; - integrity.tag_size = sizeof(u16); - integrity.flags |= BLK_INTEGRITY_DEVICE_CAPABLE; + bi->csum_type = BLK_INTEGRITY_CSUM_CRC64; + bi->tag_size = sizeof(u16); + bi->flags |= BLK_INTEGRITY_DEVICE_CAPABLE | + BLK_INTEGRITY_REF_TAG; break; default: - integrity.profile = NULL; break; } break; default: - integrity.profile = NULL; break; } - integrity.tuple_size = head->ms; - integrity.pi_offset = head->pi_offset; - blk_integrity_register(disk, &integrity); + bi->tuple_size = head->ms; + bi->pi_offset = head->pi_offset; return true; } @@ -1922,6 +1954,23 @@ static void nvme_configure_metadata(struct nvme_ctrl *ctrl, } } + +static void nvme_update_atomic_write_disk_info(struct nvme_ns *ns, + struct nvme_id_ns *id, struct queue_limits *lim, + u32 bs, u32 atomic_bs) +{ + unsigned int boundary = 0; + + if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf) { + if (le16_to_cpu(id->nabspf)) + boundary = (le16_to_cpu(id->nabspf) + 1) * bs; + } + lim->atomic_write_hw_max = atomic_bs; + lim->atomic_write_hw_boundary = boundary; + lim->atomic_write_hw_unit_min = bs; + lim->atomic_write_hw_unit_max = rounddown_pow_of_two(atomic_bs); +} + static u32 nvme_max_drv_segments(struct nvme_ctrl *ctrl) { return ctrl->max_hw_sectors / (NVME_CTRL_PAGE_SIZE >> SECTOR_SHIFT) + 1; @@ -1968,13 +2017,16 @@ static bool nvme_update_disk_info(struct nvme_ns *ns, struct nvme_id_ns *id, atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs; else atomic_bs = (1 + ns->ctrl->subsys->awupf) * bs; + + nvme_update_atomic_write_disk_info(ns, id, lim, bs, atomic_bs); } if (id->nsfeat & NVME_NS_FEAT_IO_OPT) { /* NPWG = Namespace Preferred Write Granularity */ phys_bs = bs * (1 + le16_to_cpu(id->npwg)); /* NOWS = Namespace Optimal Write Size */ - io_opt = bs * (1 + le16_to_cpu(id->nows)); + if (id->nows) + io_opt = bs * (1 + le16_to_cpu(id->nows)); } /* @@ -2058,7 +2110,6 @@ static int nvme_update_ns_info_generic(struct nvme_ns *ns, static int nvme_update_ns_info_block(struct nvme_ns *ns, struct nvme_ns_info *info) { - bool vwc = ns->ctrl->vwc & NVME_CTRL_VWC_PRESENT; struct queue_limits lim; struct nvme_id_ns_nvm *nvm = NULL; struct nvme_zone_info zi = {}; @@ -2107,11 +2158,11 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && ns->head->ids.csi == NVME_CSI_ZNS) nvme_update_zone_info(ns, &lim, &zi); - ret = queue_limits_commit_update(ns->disk->queue, &lim); - if (ret) { - blk_mq_unfreeze_queue(ns->disk->queue); - goto out; - } + + if (ns->ctrl->vwc & NVME_CTRL_VWC_PRESENT) + lim.features |= BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA; + else + lim.features &= ~(BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA); /* * Register a metadata profile for PI, or the plain non-integrity NVMe @@ -2119,9 +2170,15 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, * I/O to namespaces with metadata except when the namespace supports * PI, as it can strip/insert in that case. */ - if (!nvme_init_integrity(ns->disk, ns->head)) + if (!nvme_init_integrity(ns->disk, ns->head, &lim)) capacity = 0; + ret = queue_limits_commit_update(ns->disk->queue, &lim); + if (ret) { + blk_mq_unfreeze_queue(ns->disk->queue); + goto out; + } + set_capacity_and_notify(ns->disk, capacity); /* @@ -2133,7 +2190,6 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, if ((id->dlfeat & 0x7) == 0x1 && (id->dlfeat & (1 << 3))) ns->head->features |= NVME_NS_DEAC; set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info)); - blk_queue_write_cache(ns->disk->queue, vwc, vwc); set_bit(NVME_NS_READY, &ns->flags); blk_mq_unfreeze_queue(ns->disk->queue); @@ -2193,14 +2249,6 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info) struct queue_limits lim; blk_mq_freeze_queue(ns->head->disk->queue); - if (unsupported) - ns->head->disk->flags |= GENHD_FL_HIDDEN; - else - nvme_init_integrity(ns->head->disk, ns->head); - set_capacity_and_notify(ns->head->disk, get_capacity(ns->disk)); - set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info)); - nvme_mpath_revalidate_paths(ns); - /* * queue_limits mixes values that are the hardware limitations * for bio splitting with what is the device configuration. @@ -2223,13 +2271,48 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info) lim.io_opt = ns_lim->io_opt; queue_limits_stack_bdev(&lim, ns->disk->part0, 0, ns->head->disk->disk_name); + if (unsupported) + ns->head->disk->flags |= GENHD_FL_HIDDEN; + else + nvme_init_integrity(ns->head->disk, ns->head, &lim); ret = queue_limits_commit_update(ns->head->disk->queue, &lim); + + set_capacity_and_notify(ns->head->disk, get_capacity(ns->disk)); + set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info)); + nvme_mpath_revalidate_paths(ns); + blk_mq_unfreeze_queue(ns->head->disk->queue); } return ret; } +int nvme_ns_get_unique_id(struct nvme_ns *ns, u8 id[16], + enum blk_unique_id type) +{ + struct nvme_ns_ids *ids = &ns->head->ids; + + if (type != BLK_UID_EUI64) + return -EINVAL; + + if (memchr_inv(ids->nguid, 0, sizeof(ids->nguid))) { + memcpy(id, &ids->nguid, sizeof(ids->nguid)); + return sizeof(ids->nguid); + } + if (memchr_inv(ids->eui64, 0, sizeof(ids->eui64))) { + memcpy(id, &ids->eui64, sizeof(ids->eui64)); + return sizeof(ids->eui64); + } + + return -EINVAL; +} + +static int nvme_get_unique_id(struct gendisk *disk, u8 id[16], + enum blk_unique_id type) +{ + return nvme_ns_get_unique_id(disk->private_data, id, type); +} + #ifdef CONFIG_BLK_SED_OPAL static int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len, bool send) @@ -2285,6 +2368,7 @@ const struct block_device_operations nvme_bdev_ops = { .open = nvme_open, .release = nvme_release, .getgeo = nvme_getgeo, + .get_unique_id = nvme_get_unique_id, .report_zones = nvme_report_zones, .pr_ops = &nvme_pr_ops, }; @@ -3721,6 +3805,7 @@ static void nvme_ns_add_to_ctrl_list(struct nvme_ns *ns) static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info) { + struct queue_limits lim = { }; struct nvme_ns *ns; struct gendisk *disk; int node = ctrl->numa_node; @@ -3729,7 +3814,13 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info) if (!ns) return; - disk = blk_mq_alloc_disk(ctrl->tagset, NULL, ns); + if (ctrl->opts && ctrl->opts->data_digest) + lim.features |= BLK_FEAT_STABLE_WRITES; + if (ctrl->ops->supports_pci_p2pdma && + ctrl->ops->supports_pci_p2pdma(ctrl)) + lim.features |= BLK_FEAT_PCI_P2PDMA; + + disk = blk_mq_alloc_disk(ctrl->tagset, &lim, ns); if (IS_ERR(disk)) goto out_free_ns; disk->fops = &nvme_bdev_ops; @@ -3737,15 +3828,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info) ns->disk = disk; ns->queue = disk->queue; - - if (ctrl->opts && ctrl->opts->data_digest) - blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, ns->queue); - - blk_queue_flag_set(QUEUE_FLAG_NONROT, ns->queue); - if (ctrl->ops->supports_pci_p2pdma && - ctrl->ops->supports_pci_p2pdma(ctrl)) - blk_queue_flag_set(QUEUE_FLAG_PCI_P2PDMA, ns->queue); - ns->ctrl = ctrl; kref_init(&ns->kref); @@ -3887,7 +3969,7 @@ static void nvme_ns_remove_by_nsid(struct nvme_ctrl *ctrl, u32 nsid) static void nvme_validate_ns(struct nvme_ns *ns, struct nvme_ns_info *info) { - int ret = NVME_SC_INVALID_NS | NVME_SC_DNR; + int ret = NVME_SC_INVALID_NS | NVME_STATUS_DNR; if (!nvme_ns_ids_equal(&ns->head->ids, &info->ids)) { dev_err(ns->ctrl->device, @@ -3903,7 +3985,7 @@ out: * * TODO: we should probably schedule a delayed retry here. */ - if (ret > 0 && (ret & NVME_SC_DNR)) + if (ret > 0 && (ret & NVME_STATUS_DNR)) nvme_ns_remove(ns); } @@ -4095,7 +4177,7 @@ static void nvme_scan_work(struct work_struct *work) * they report) but don't actually support it. */ ret = nvme_scan_ns_list(ctrl); - if (ret > 0 && ret & NVME_SC_DNR) + if (ret > 0 && ret & NVME_STATUS_DNR) nvme_scan_ns_sequential(ctrl); } mutex_unlock(&ctrl->scan_lock); @@ -4489,13 +4571,15 @@ int nvme_alloc_io_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set, return ret; if (ctrl->ops->flags & NVME_F_FABRICS) { - ctrl->connect_q = blk_mq_alloc_queue(set, NULL, NULL); + struct queue_limits lim = { + .features = BLK_FEAT_SKIP_TAGSET_QUIESCE, + }; + + ctrl->connect_q = blk_mq_alloc_queue(set, &lim, NULL); if (IS_ERR(ctrl->connect_q)) { ret = PTR_ERR(ctrl->connect_q); goto out_free_tag_set; } - blk_queue_flag_set(QUEUE_FLAG_SKIP_TAGSET_QUIESCE, - ctrl->connect_q); } ctrl->tagset = set; @@ -4613,6 +4697,9 @@ static void nvme_free_ctrl(struct device *dev) * Initialize a NVMe controller structures. This needs to be called during * earliest initialization so that we have the initialized structured around * during probing. + * + * On success, the caller must use the nvme_put_ctrl() to release this when + * needed, which also invokes the ops->free_ctrl() callback. */ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, const struct nvme_ctrl_ops *ops, unsigned long quirks) @@ -4661,6 +4748,12 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, goto out; ctrl->instance = ret; + ret = nvme_auth_init_ctrl(ctrl); + if (ret) + goto out_release_instance; + + nvme_mpath_init_ctrl(ctrl); + device_initialize(&ctrl->ctrl_device); ctrl->device = &ctrl->ctrl_device; ctrl->device->devt = MKDEV(MAJOR(nvme_ctrl_base_chr_devt), @@ -4673,16 +4766,36 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, ctrl->device->groups = nvme_dev_attr_groups; ctrl->device->release = nvme_free_ctrl; dev_set_drvdata(ctrl->device, ctrl); + + return ret; + +out_release_instance: + ida_free(&nvme_instance_ida, ctrl->instance); +out: + if (ctrl->discard_page) + __free_page(ctrl->discard_page); + cleanup_srcu_struct(&ctrl->srcu); + return ret; +} +EXPORT_SYMBOL_GPL(nvme_init_ctrl); + +/* + * On success, returns with an elevated controller reference and caller must + * use nvme_uninit_ctrl() to properly free resources associated with the ctrl. + */ +int nvme_add_ctrl(struct nvme_ctrl *ctrl) +{ + int ret; + ret = dev_set_name(ctrl->device, "nvme%d", ctrl->instance); if (ret) - goto out_release_instance; + return ret; - nvme_get_ctrl(ctrl); cdev_init(&ctrl->cdev, &nvme_dev_fops); - ctrl->cdev.owner = ops->module; + ctrl->cdev.owner = ctrl->ops->module; ret = cdev_device_add(&ctrl->cdev, ctrl->device); if (ret) - goto out_free_name; + return ret; /* * Initialize latency tolerance controls. The sysfs files won't @@ -4693,28 +4806,11 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, min(default_ps_max_latency_us, (unsigned long)S32_MAX)); nvme_fault_inject_init(&ctrl->fault_inject, dev_name(ctrl->device)); - nvme_mpath_init_ctrl(ctrl); - ret = nvme_auth_init_ctrl(ctrl); - if (ret) - goto out_free_cdev; + nvme_get_ctrl(ctrl); return 0; -out_free_cdev: - nvme_fault_inject_fini(&ctrl->fault_inject); - dev_pm_qos_hide_latency_tolerance(ctrl->device); - cdev_device_del(&ctrl->cdev, ctrl->device); -out_free_name: - nvme_put_ctrl(ctrl); - kfree_const(ctrl->device->kobj.name); -out_release_instance: - ida_free(&nvme_instance_ida, ctrl->instance); -out: - if (ctrl->discard_page) - __free_page(ctrl->discard_page); - cleanup_srcu_struct(&ctrl->srcu); - return ret; } -EXPORT_SYMBOL_GPL(nvme_init_ctrl); +EXPORT_SYMBOL_GPL(nvme_add_ctrl); /* let I/O to all namespaces fail in preparation for surprise removal */ void nvme_mark_namespaces_dead(struct nvme_ctrl *ctrl) diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index ceb9c0ed3120..44e342a46f39 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -187,7 +187,7 @@ int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val) if (unlikely(ret != 0)) dev_err(ctrl->device, "Property Get error: %d, offset %#x\n", - ret > 0 ? ret & ~NVME_SC_DNR : ret, off); + ret > 0 ? ret & ~NVME_STATUS_DNR : ret, off); return ret; } @@ -233,7 +233,7 @@ int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val) if (unlikely(ret != 0)) dev_err(ctrl->device, "Property Get error: %d, offset %#x\n", - ret > 0 ? ret & ~NVME_SC_DNR : ret, off); + ret > 0 ? ret & ~NVME_STATUS_DNR : ret, off); return ret; } EXPORT_SYMBOL_GPL(nvmf_reg_read64); @@ -275,11 +275,26 @@ int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val) if (unlikely(ret)) dev_err(ctrl->device, "Property Set error: %d, offset %#x\n", - ret > 0 ? ret & ~NVME_SC_DNR : ret, off); + ret > 0 ? ret & ~NVME_STATUS_DNR : ret, off); return ret; } EXPORT_SYMBOL_GPL(nvmf_reg_write32); +int nvmf_subsystem_reset(struct nvme_ctrl *ctrl) +{ + int ret; + + if (!nvme_wait_reset(ctrl)) + return -EBUSY; + + ret = ctrl->ops->reg_write32(ctrl, NVME_REG_NSSR, NVME_SUBSYS_RESET); + if (ret) + return ret; + + return nvme_try_sched_reset(ctrl); +} +EXPORT_SYMBOL_GPL(nvmf_subsystem_reset); + /** * nvmf_log_connect_error() - Error-parsing-diagnostic print out function for * connect() errors. @@ -295,7 +310,7 @@ static void nvmf_log_connect_error(struct nvme_ctrl *ctrl, int errval, int offset, struct nvme_command *cmd, struct nvmf_connect_data *data) { - int err_sctype = errval & ~NVME_SC_DNR; + int err_sctype = errval & ~NVME_STATUS_DNR; if (errval < 0) { dev_err(ctrl->device, @@ -573,7 +588,7 @@ EXPORT_SYMBOL_GPL(nvmf_connect_io_queue); */ bool nvmf_should_reconnect(struct nvme_ctrl *ctrl, int status) { - if (status > 0 && (status & NVME_SC_DNR)) + if (status > 0 && (status & NVME_STATUS_DNR)) return false; if (status == -EKEYREJECTED) diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index 602135910ae9..21d75dc4a3a0 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -217,6 +217,7 @@ static inline unsigned int nvmf_nr_io_queues(struct nvmf_ctrl_options *opts) int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val); int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val); int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val); +int nvmf_subsystem_reset(struct nvme_ctrl *ctrl); int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl); int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid); int nvmf_register_transport(struct nvmf_transport_ops *ops); diff --git a/drivers/nvme/host/fault_inject.c b/drivers/nvme/host/fault_inject.c index 1ba10a5c656d..1d1b6441a339 100644 --- a/drivers/nvme/host/fault_inject.c +++ b/drivers/nvme/host/fault_inject.c @@ -75,7 +75,7 @@ void nvme_should_fail(struct request *req) /* inject status code and DNR bit */ status = fault_inject->status; if (fault_inject->dont_retry) - status |= NVME_SC_DNR; + status |= NVME_STATUS_DNR; nvme_req(req)->status = status; } } diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index f0b081332749..b81af7919e94 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -3132,7 +3132,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) if (ctrl->ctrl.icdoff) { dev_err(ctrl->ctrl.device, "icdoff %d is not supported!\n", ctrl->ctrl.icdoff); - ret = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + ret = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; goto out_stop_keep_alive; } @@ -3140,7 +3140,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) if (!nvme_ctrl_sgl_supported(&ctrl->ctrl)) { dev_err(ctrl->ctrl.device, "Mandatory sgls are not supported!\n"); - ret = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + ret = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; goto out_stop_keep_alive; } @@ -3325,7 +3325,7 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status) queue_delayed_work(nvme_wq, &ctrl->connect_work, recon_delay); } else { if (portptr->port_state == FC_OBJSTATE_ONLINE) { - if (status > 0 && (status & NVME_SC_DNR)) + if (status > 0 && (status & NVME_STATUS_DNR)) dev_warn(ctrl->ctrl.device, "NVME-FC{%d}: reconnect failure\n", ctrl->cnum); @@ -3382,6 +3382,7 @@ static const struct nvme_ctrl_ops nvme_fc_ctrl_ops = { .reg_read32 = nvmf_reg_read32, .reg_read64 = nvmf_reg_read64, .reg_write32 = nvmf_reg_write32, + .subsystem_reset = nvmf_subsystem_reset, .free_ctrl = nvme_fc_free_ctrl, .submit_async_event = nvme_fc_submit_async_event, .delete_ctrl = nvme_fc_delete_ctrl, @@ -3444,12 +3445,11 @@ nvme_fc_existing_controller(struct nvme_fc_rport *rport, return found; } -static struct nvme_ctrl * -nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, +static struct nvme_fc_ctrl * +nvme_fc_alloc_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, struct nvme_fc_lport *lport, struct nvme_fc_rport *rport) { struct nvme_fc_ctrl *ctrl; - unsigned long flags; int ret, idx, ctrl_loss_tmo; if (!(rport->remoteport.port_role & @@ -3538,7 +3538,35 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, if (lport->dev) ctrl->ctrl.numa_node = dev_to_node(lport->dev); - /* at this point, teardown path changes to ref counting on nvme ctrl */ + return ctrl; + +out_free_queues: + kfree(ctrl->queues); +out_free_ida: + put_device(ctrl->dev); + ida_free(&nvme_fc_ctrl_cnt, ctrl->cnum); +out_free_ctrl: + kfree(ctrl); +out_fail: + /* exit via here doesn't follow ctlr ref points */ + return ERR_PTR(ret); +} + +static struct nvme_ctrl * +nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, + struct nvme_fc_lport *lport, struct nvme_fc_rport *rport) +{ + struct nvme_fc_ctrl *ctrl; + unsigned long flags; + int ret; + + ctrl = nvme_fc_alloc_ctrl(dev, opts, lport, rport); + if (IS_ERR(ctrl)) + return ERR_CAST(ctrl); + + ret = nvme_add_ctrl(&ctrl->ctrl); + if (ret) + goto out_put_ctrl; ret = nvme_alloc_admin_tag_set(&ctrl->ctrl, &ctrl->admin_tag_set, &nvme_fc_admin_mq_ops, @@ -3584,6 +3612,7 @@ fail_ctrl: /* initiate nvme ctrl ref counting teardown */ nvme_uninit_ctrl(&ctrl->ctrl); +out_put_ctrl: /* Remove core ctrl ref. */ nvme_put_ctrl(&ctrl->ctrl); @@ -3597,20 +3626,8 @@ fail_ctrl: nvme_fc_rport_get(rport); return ERR_PTR(-EIO); - -out_free_queues: - kfree(ctrl->queues); -out_free_ida: - put_device(ctrl->dev); - ida_free(&nvme_fc_ctrl_cnt, ctrl->cnum); -out_free_ctrl: - kfree(ctrl); -out_fail: - /* exit via here doesn't follow ctlr ref points */ - return ERR_PTR(ret); } - struct nvmet_fc_traddr { u64 nn; u64 pn; diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index d8b6b4648eaf..91d9eb3c22ef 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -17,6 +17,7 @@ MODULE_PARM_DESC(multipath, static const char *nvme_iopolicy_names[] = { [NVME_IOPOLICY_NUMA] = "numa", [NVME_IOPOLICY_RR] = "round-robin", + [NVME_IOPOLICY_QD] = "queue-depth", }; static int iopolicy = NVME_IOPOLICY_NUMA; @@ -29,6 +30,8 @@ static int nvme_set_iopolicy(const char *val, const struct kernel_param *kp) iopolicy = NVME_IOPOLICY_NUMA; else if (!strncmp(val, "round-robin", 11)) iopolicy = NVME_IOPOLICY_RR; + else if (!strncmp(val, "queue-depth", 11)) + iopolicy = NVME_IOPOLICY_QD; else return -EINVAL; @@ -43,7 +46,7 @@ static int nvme_get_iopolicy(char *buf, const struct kernel_param *kp) module_param_call(iopolicy, nvme_set_iopolicy, nvme_get_iopolicy, &iopolicy, 0644); MODULE_PARM_DESC(iopolicy, - "Default multipath I/O policy; 'numa' (default) or 'round-robin'"); + "Default multipath I/O policy; 'numa' (default), 'round-robin' or 'queue-depth'"); void nvme_mpath_default_iopolicy(struct nvme_subsystem *subsys) { @@ -83,7 +86,7 @@ void nvme_mpath_start_freeze(struct nvme_subsystem *subsys) void nvme_failover_req(struct request *req) { struct nvme_ns *ns = req->q->queuedata; - u16 status = nvme_req(req)->status & 0x7ff; + u16 status = nvme_req(req)->status & NVME_SCT_SC_MASK; unsigned long flags; struct bio *bio; @@ -128,6 +131,11 @@ void nvme_mpath_start_request(struct request *rq) struct nvme_ns *ns = rq->q->queuedata; struct gendisk *disk = ns->head->disk; + if (READ_ONCE(ns->head->subsys->iopolicy) == NVME_IOPOLICY_QD) { + atomic_inc(&ns->ctrl->nr_active); + nvme_req(rq)->flags |= NVME_MPATH_CNT_ACTIVE; + } + if (!blk_queue_io_stat(disk->queue) || blk_rq_is_passthrough(rq)) return; @@ -141,6 +149,9 @@ void nvme_mpath_end_request(struct request *rq) { struct nvme_ns *ns = rq->q->queuedata; + if (nvme_req(rq)->flags & NVME_MPATH_CNT_ACTIVE) + atomic_dec_if_positive(&ns->ctrl->nr_active); + if (!(nvme_req(rq)->flags & NVME_MPATH_IO_STATS)) return; bdev_end_io_acct(ns->head->disk->part0, req_op(rq), @@ -291,10 +302,15 @@ static struct nvme_ns *nvme_next_ns(struct nvme_ns_head *head, return list_first_or_null_rcu(&head->list, struct nvme_ns, siblings); } -static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head, - int node, struct nvme_ns *old) +static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head) { struct nvme_ns *ns, *found = NULL; + int node = numa_node_id(); + struct nvme_ns *old = srcu_dereference(head->current_path[node], + &head->srcu); + + if (unlikely(!old)) + return __nvme_find_path(head, node); if (list_is_singular(&head->list)) { if (nvme_path_is_disabled(old)) @@ -334,13 +350,49 @@ out: return found; } +static struct nvme_ns *nvme_queue_depth_path(struct nvme_ns_head *head) +{ + struct nvme_ns *best_opt = NULL, *best_nonopt = NULL, *ns; + unsigned int min_depth_opt = UINT_MAX, min_depth_nonopt = UINT_MAX; + unsigned int depth; + + list_for_each_entry_rcu(ns, &head->list, siblings) { + if (nvme_path_is_disabled(ns)) + continue; + + depth = atomic_read(&ns->ctrl->nr_active); + + switch (ns->ana_state) { + case NVME_ANA_OPTIMIZED: + if (depth < min_depth_opt) { + min_depth_opt = depth; + best_opt = ns; + } + break; + case NVME_ANA_NONOPTIMIZED: + if (depth < min_depth_nonopt) { + min_depth_nonopt = depth; + best_nonopt = ns; + } + break; + default: + break; + } + + if (min_depth_opt == 0) + return best_opt; + } + + return best_opt ? best_opt : best_nonopt; +} + static inline bool nvme_path_is_optimized(struct nvme_ns *ns) { return nvme_ctrl_state(ns->ctrl) == NVME_CTRL_LIVE && ns->ana_state == NVME_ANA_OPTIMIZED; } -inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head) +static struct nvme_ns *nvme_numa_path(struct nvme_ns_head *head) { int node = numa_node_id(); struct nvme_ns *ns; @@ -348,14 +400,23 @@ inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head) ns = srcu_dereference(head->current_path[node], &head->srcu); if (unlikely(!ns)) return __nvme_find_path(head, node); - - if (READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_RR) - return nvme_round_robin_path(head, node, ns); if (unlikely(!nvme_path_is_optimized(ns))) return __nvme_find_path(head, node); return ns; } +inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head) +{ + switch (READ_ONCE(head->subsys->iopolicy)) { + case NVME_IOPOLICY_QD: + return nvme_queue_depth_path(head); + case NVME_IOPOLICY_RR: + return nvme_round_robin_path(head); + default: + return nvme_numa_path(head); + } +} + static bool nvme_available_path(struct nvme_ns_head *head) { struct nvme_ns *ns; @@ -427,6 +488,21 @@ static void nvme_ns_head_release(struct gendisk *disk) nvme_put_ns_head(disk->private_data); } +static int nvme_ns_head_get_unique_id(struct gendisk *disk, u8 id[16], + enum blk_unique_id type) +{ + struct nvme_ns_head *head = disk->private_data; + struct nvme_ns *ns; + int srcu_idx, ret = -EWOULDBLOCK; + + srcu_idx = srcu_read_lock(&head->srcu); + ns = nvme_find_path(head); + if (ns) + ret = nvme_ns_get_unique_id(ns, id, type); + srcu_read_unlock(&head->srcu, srcu_idx); + return ret; +} + #ifdef CONFIG_BLK_DEV_ZONED static int nvme_ns_head_report_zones(struct gendisk *disk, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data) @@ -454,6 +530,7 @@ const struct block_device_operations nvme_ns_head_ops = { .ioctl = nvme_ns_head_ioctl, .compat_ioctl = blkdev_compat_ptr_ioctl, .getgeo = nvme_getgeo, + .get_unique_id = nvme_ns_head_get_unique_id, .report_zones = nvme_ns_head_report_zones, .pr_ops = &nvme_pr_ops, }; @@ -521,7 +598,6 @@ static void nvme_requeue_work(struct work_struct *work) int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head) { struct queue_limits lim; - bool vwc = false; mutex_init(&head->lock); bio_list_init(&head->requeue_list); @@ -539,6 +615,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head) blk_set_stacking_limits(&lim); lim.dma_alignment = 3; + lim.features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT | BLK_FEAT_POLL; if (head->ids.csi != NVME_CSI_ZNS) lim.max_zone_append_sectors = 0; @@ -549,24 +626,6 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head) head->disk->private_data = head; sprintf(head->disk->disk_name, "nvme%dn%d", ctrl->subsys->instance, head->instance); - - blk_queue_flag_set(QUEUE_FLAG_NONROT, head->disk->queue); - blk_queue_flag_set(QUEUE_FLAG_NOWAIT, head->disk->queue); - blk_queue_flag_set(QUEUE_FLAG_IO_STAT, head->disk->queue); - /* - * This assumes all controllers that refer to a namespace either - * support poll queues or not. That is not a strict guarantee, - * but if the assumption is wrong the effect is only suboptimal - * performance but not correctness problem. - */ - if (ctrl->tagset->nr_maps > HCTX_TYPE_POLL && - ctrl->tagset->map[HCTX_TYPE_POLL].nr_queues) - blk_queue_flag_set(QUEUE_FLAG_POLL, head->disk->queue); - - /* we need to propagate up the VMC settings */ - if (ctrl->vwc & NVME_CTRL_VWC_PRESENT) - vwc = true; - blk_queue_write_cache(head->disk->queue, vwc, vwc); return 0; } @@ -803,6 +862,29 @@ static ssize_t nvme_subsys_iopolicy_show(struct device *dev, nvme_iopolicy_names[READ_ONCE(subsys->iopolicy)]); } +static void nvme_subsys_iopolicy_update(struct nvme_subsystem *subsys, + int iopolicy) +{ + struct nvme_ctrl *ctrl; + int old_iopolicy = READ_ONCE(subsys->iopolicy); + + if (old_iopolicy == iopolicy) + return; + + WRITE_ONCE(subsys->iopolicy, iopolicy); + + /* iopolicy changes clear the mpath by design */ + mutex_lock(&nvme_subsystems_lock); + list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) + nvme_mpath_clear_ctrl_paths(ctrl); + mutex_unlock(&nvme_subsystems_lock); + + pr_notice("subsysnqn %s iopolicy changed from %s to %s\n", + subsys->subnqn, + nvme_iopolicy_names[old_iopolicy], + nvme_iopolicy_names[iopolicy]); +} + static ssize_t nvme_subsys_iopolicy_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { @@ -812,7 +894,7 @@ static ssize_t nvme_subsys_iopolicy_store(struct device *dev, for (i = 0; i < ARRAY_SIZE(nvme_iopolicy_names); i++) { if (sysfs_streq(buf, nvme_iopolicy_names[i])) { - WRITE_ONCE(subsys->iopolicy, i); + nvme_subsys_iopolicy_update(subsys, i); return count; } } @@ -875,9 +957,6 @@ void nvme_mpath_add_disk(struct nvme_ns *ns, __le32 anagrpid) nvme_mpath_set_live(ns); } - if (blk_queue_stable_writes(ns->queue) && ns->head->disk) - blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, - ns->head->disk->queue); #ifdef CONFIG_BLK_DEV_ZONED if (blk_queue_is_zoned(ns->queue) && ns->head->disk) ns->head->disk->nr_zones = ns->disk->nr_zones; @@ -923,6 +1002,9 @@ int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) !(ctrl->subsys->cmic & NVME_CTRL_CMIC_ANA)) return 0; + /* initialize this in the identify path to cover controller resets */ + atomic_set(&ctrl->nr_active, 0); + if (!ctrl->max_namespaces || ctrl->max_namespaces > le32_to_cpu(id->nn)) { dev_err(ctrl->device, diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 68b400f9c42d..f900e44243ae 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -49,6 +49,7 @@ extern unsigned int admin_timeout; extern struct workqueue_struct *nvme_wq; extern struct workqueue_struct *nvme_reset_wq; extern struct workqueue_struct *nvme_delete_wq; +extern struct mutex nvme_subsystems_lock; /* * List of workarounds for devices that required behavior not specified in @@ -195,6 +196,7 @@ enum { NVME_REQ_CANCELLED = (1 << 0), NVME_REQ_USERCMD = (1 << 1), NVME_MPATH_IO_STATS = (1 << 2), + NVME_MPATH_CNT_ACTIVE = (1 << 3), }; static inline struct nvme_request *nvme_req(struct request *req) @@ -360,6 +362,7 @@ struct nvme_ctrl { size_t ana_log_size; struct timer_list anatt_timer; struct work_struct ana_work; + atomic_t nr_active; #endif #ifdef CONFIG_NVME_HOST_AUTH @@ -408,6 +411,7 @@ static inline enum nvme_ctrl_state nvme_ctrl_state(struct nvme_ctrl *ctrl) enum nvme_iopolicy { NVME_IOPOLICY_NUMA, NVME_IOPOLICY_RR, + NVME_IOPOLICY_QD, }; struct nvme_subsystem { @@ -551,6 +555,7 @@ struct nvme_ctrl_ops { int (*reg_read64)(struct nvme_ctrl *ctrl, u32 off, u64 *val); void (*free_ctrl)(struct nvme_ctrl *ctrl); void (*submit_async_event)(struct nvme_ctrl *ctrl); + int (*subsystem_reset)(struct nvme_ctrl *ctrl); void (*delete_ctrl)(struct nvme_ctrl *ctrl); void (*stop_ctrl)(struct nvme_ctrl *ctrl); int (*get_address)(struct nvme_ctrl *ctrl, char *buf, int size); @@ -649,18 +654,9 @@ int nvme_try_sched_reset(struct nvme_ctrl *ctrl); static inline int nvme_reset_subsystem(struct nvme_ctrl *ctrl) { - int ret; - - if (!ctrl->subsystem) + if (!ctrl->subsystem || !ctrl->ops->subsystem_reset) return -ENOTTY; - if (!nvme_wait_reset(ctrl)) - return -EBUSY; - - ret = ctrl->ops->reg_write32(ctrl, NVME_REG_NSSR, 0x4E564D65); - if (ret) - return ret; - - return nvme_try_sched_reset(ctrl); + return ctrl->ops->subsystem_reset(ctrl); } /* @@ -689,7 +685,7 @@ static inline u32 nvme_bytes_to_numd(size_t len) static inline bool nvme_is_ana_error(u16 status) { - switch (status & 0x7ff) { + switch (status & NVME_SCT_SC_MASK) { case NVME_SC_ANA_TRANSITION: case NVME_SC_ANA_INACCESSIBLE: case NVME_SC_ANA_PERSISTENT_LOSS: @@ -702,7 +698,7 @@ static inline bool nvme_is_ana_error(u16 status) static inline bool nvme_is_path_error(u16 status) { /* check for a status code type of 'path related status' */ - return (status & 0x700) == 0x300; + return (status & NVME_SCT_MASK) == NVME_SCT_PATH; } /* @@ -792,6 +788,7 @@ int nvme_disable_ctrl(struct nvme_ctrl *ctrl, bool shutdown); int nvme_enable_ctrl(struct nvme_ctrl *ctrl); int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, const struct nvme_ctrl_ops *ops, unsigned long quirks); +int nvme_add_ctrl(struct nvme_ctrl *ctrl); void nvme_uninit_ctrl(struct nvme_ctrl *ctrl); void nvme_start_ctrl(struct nvme_ctrl *ctrl); void nvme_stop_ctrl(struct nvme_ctrl *ctrl); @@ -877,7 +874,7 @@ enum { NVME_SUBMIT_NOWAIT = (__force nvme_submit_flags_t)(1 << 1), /* Set BLK_MQ_REQ_RESERVED when allocating request */ NVME_SUBMIT_RESERVED = (__force nvme_submit_flags_t)(1 << 2), - /* Retry command when NVME_SC_DNR is not set in the result */ + /* Retry command when NVME_STATUS_DNR is not set in the result */ NVME_SUBMIT_RETRY = (__force nvme_submit_flags_t)(1 << 3), }; @@ -1062,6 +1059,9 @@ static inline bool nvme_disk_is_ns_head(struct gendisk *disk) } #endif /* CONFIG_NVME_MULTIPATH */ +int nvme_ns_get_unique_id(struct nvme_ns *ns, u8 id[16], + enum blk_unique_id type); + struct nvme_zone_info { u64 zone_size; unsigned int max_open_zones; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 102a9fb0c65f..21f8e1b9801f 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -826,9 +826,9 @@ static blk_status_t nvme_map_metadata(struct nvme_dev *dev, struct request *req, struct nvme_command *cmnd) { struct nvme_iod *iod = blk_mq_rq_to_pdu(req); + struct bio_vec bv = rq_integrity_vec(req); - iod->meta_dma = dma_map_bvec(dev->dev, rq_integrity_vec(req), - rq_dma_dir(req), 0); + iod->meta_dma = dma_map_bvec(dev->dev, &bv, rq_dma_dir(req), 0); if (dma_mapping_error(dev->dev, iod->meta_dma)) return BLK_STS_IOERR; cmnd->rw.metadata = cpu_to_le64(iod->meta_dma); @@ -967,7 +967,7 @@ static __always_inline void nvme_pci_unmap_rq(struct request *req) struct nvme_iod *iod = blk_mq_rq_to_pdu(req); dma_unmap_page(dev->dev, iod->meta_dma, - rq_integrity_vec(req)->bv_len, rq_dma_dir(req)); + rq_integrity_vec(req).bv_len, rq_dma_dir(req)); } if (blk_rq_nr_phys_segments(req)) @@ -1143,6 +1143,41 @@ static void nvme_pci_submit_async_event(struct nvme_ctrl *ctrl) spin_unlock(&nvmeq->sq_lock); } +static int nvme_pci_subsystem_reset(struct nvme_ctrl *ctrl) +{ + struct nvme_dev *dev = to_nvme_dev(ctrl); + int ret = 0; + + /* + * Taking the shutdown_lock ensures the BAR mapping is not being + * altered by reset_work. Holding this lock before the RESETTING state + * change, if successful, also ensures nvme_remove won't be able to + * proceed to iounmap until we're done. + */ + mutex_lock(&dev->shutdown_lock); + if (!dev->bar_mapped_size) { + ret = -ENODEV; + goto unlock; + } + + if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) { + ret = -EBUSY; + goto unlock; + } + + writel(NVME_SUBSYS_RESET, dev->bar + NVME_REG_NSSR); + nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE); + + /* + * Read controller status to flush the previous write and trigger a + * pcie read error. + */ + readl(dev->bar + NVME_REG_CSTS); +unlock: + mutex_unlock(&dev->shutdown_lock); + return ret; +} + static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id) { struct nvme_command c = { }; @@ -2859,6 +2894,7 @@ static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = { .reg_read64 = nvme_pci_reg_read64, .free_ctrl = nvme_pci_free_ctrl, .submit_async_event = nvme_pci_submit_async_event, + .subsystem_reset = nvme_pci_subsystem_reset, .get_address = nvme_pci_get_address, .print_device_info = nvme_pci_print_device_info, .supports_pci_p2pdma = nvme_pci_supports_pci_p2pdma, @@ -3015,6 +3051,10 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (IS_ERR(dev)) return PTR_ERR(dev); + result = nvme_add_ctrl(&dev->ctrl); + if (result) + goto out_put_ctrl; + result = nvme_dev_map(dev); if (result) goto out_uninit_ctrl; @@ -3101,6 +3141,7 @@ out_dev_unmap: nvme_dev_unmap(dev); out_uninit_ctrl: nvme_uninit_ctrl(&dev->ctrl); +out_put_ctrl: nvme_put_ctrl(&dev->ctrl); return result; } diff --git a/drivers/nvme/host/pr.c b/drivers/nvme/host/pr.c index 8fa1ffcdaed4..7347ddf85f00 100644 --- a/drivers/nvme/host/pr.c +++ b/drivers/nvme/host/pr.c @@ -72,12 +72,12 @@ static int nvme_send_ns_pr_command(struct nvme_ns *ns, struct nvme_command *c, return nvme_submit_sync_cmd(ns->queue, c, data, data_len); } -static int nvme_sc_to_pr_err(int nvme_sc) +static int nvme_status_to_pr_err(int status) { - if (nvme_is_path_error(nvme_sc)) + if (nvme_is_path_error(status)) return PR_STS_PATH_FAILED; - switch (nvme_sc & 0x7ff) { + switch (status & NVME_SCT_SC_MASK) { case NVME_SC_SUCCESS: return PR_STS_SUCCESS; case NVME_SC_RESERVATION_CONFLICT: @@ -121,7 +121,7 @@ static int nvme_pr_command(struct block_device *bdev, u32 cdw10, if (ret < 0) return ret; - return nvme_sc_to_pr_err(ret); + return nvme_status_to_pr_err(ret); } static int nvme_pr_register(struct block_device *bdev, u64 old, @@ -196,7 +196,7 @@ retry: if (ret < 0) return ret; - return nvme_sc_to_pr_err(ret); + return nvme_status_to_pr_err(ret); } static int nvme_pr_read_keys(struct block_device *bdev, diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 51a62b0c645a..2eb33842f971 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -2201,6 +2201,7 @@ static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = { .reg_read32 = nvmf_reg_read32, .reg_read64 = nvmf_reg_read64, .reg_write32 = nvmf_reg_write32, + .subsystem_reset = nvmf_subsystem_reset, .free_ctrl = nvme_rdma_free_ctrl, .submit_async_event = nvme_rdma_submit_async_event, .delete_ctrl = nvme_rdma_delete_ctrl, @@ -2237,12 +2238,11 @@ nvme_rdma_existing_controller(struct nvmf_ctrl_options *opts) return found; } -static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev, +static struct nvme_rdma_ctrl *nvme_rdma_alloc_ctrl(struct device *dev, struct nvmf_ctrl_options *opts) { struct nvme_rdma_ctrl *ctrl; int ret; - bool changed; ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL); if (!ctrl) @@ -2304,6 +2304,30 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev, if (ret) goto out_kfree_queues; + return ctrl; + +out_kfree_queues: + kfree(ctrl->queues); +out_free_ctrl: + kfree(ctrl); + return ERR_PTR(ret); +} + +static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev, + struct nvmf_ctrl_options *opts) +{ + struct nvme_rdma_ctrl *ctrl; + bool changed; + int ret; + + ctrl = nvme_rdma_alloc_ctrl(dev, opts); + if (IS_ERR(ctrl)) + return ERR_CAST(ctrl); + + ret = nvme_add_ctrl(&ctrl->ctrl); + if (ret) + goto out_put_ctrl; + changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING); WARN_ON_ONCE(!changed); @@ -2322,15 +2346,11 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev, out_uninit_ctrl: nvme_uninit_ctrl(&ctrl->ctrl); +out_put_ctrl: nvme_put_ctrl(&ctrl->ctrl); if (ret > 0) ret = -EIO; return ERR_PTR(ret); -out_kfree_queues: - kfree(ctrl->queues); -out_free_ctrl: - kfree(ctrl); - return ERR_PTR(ret); } static struct nvmf_transport_ops nvme_rdma_transport = { diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 8b5e4327fe83..a2a47d3ab99f 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -2662,6 +2662,7 @@ static const struct nvme_ctrl_ops nvme_tcp_ctrl_ops = { .reg_read32 = nvmf_reg_read32, .reg_read64 = nvmf_reg_read64, .reg_write32 = nvmf_reg_write32, + .subsystem_reset = nvmf_subsystem_reset, .free_ctrl = nvme_tcp_free_ctrl, .submit_async_event = nvme_tcp_submit_async_event, .delete_ctrl = nvme_tcp_delete_ctrl, @@ -2686,7 +2687,7 @@ nvme_tcp_existing_controller(struct nvmf_ctrl_options *opts) return found; } -static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev, +static struct nvme_tcp_ctrl *nvme_tcp_alloc_ctrl(struct device *dev, struct nvmf_ctrl_options *opts) { struct nvme_tcp_ctrl *ctrl; @@ -2761,6 +2762,28 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev, if (ret) goto out_kfree_queues; + return ctrl; +out_kfree_queues: + kfree(ctrl->queues); +out_free_ctrl: + kfree(ctrl); + return ERR_PTR(ret); +} + +static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev, + struct nvmf_ctrl_options *opts) +{ + struct nvme_tcp_ctrl *ctrl; + int ret; + + ctrl = nvme_tcp_alloc_ctrl(dev, opts); + if (IS_ERR(ctrl)) + return ERR_CAST(ctrl); + + ret = nvme_add_ctrl(&ctrl->ctrl); + if (ret) + goto out_put_ctrl; + if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) { WARN_ON_ONCE(1); ret = -EINTR; @@ -2782,15 +2805,11 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev, out_uninit_ctrl: nvme_uninit_ctrl(&ctrl->ctrl); +out_put_ctrl: nvme_put_ctrl(&ctrl->ctrl); if (ret > 0) ret = -EIO; return ERR_PTR(ret); -out_kfree_queues: - kfree(ctrl->queues); -out_free_ctrl: - kfree(ctrl); - return ERR_PTR(ret); } static struct nvmf_transport_ops nvme_tcp_transport = { diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c index 77aa0f440a6d..9a06f9d98cd6 100644 --- a/drivers/nvme/host/zns.c +++ b/drivers/nvme/host/zns.c @@ -108,13 +108,12 @@ free_data: void nvme_update_zone_info(struct nvme_ns *ns, struct queue_limits *lim, struct nvme_zone_info *zi) { - lim->zoned = 1; + lim->features |= BLK_FEAT_ZONED; lim->max_open_zones = zi->max_open_zones; lim->max_active_zones = zi->max_active_zones; lim->max_zone_append_sectors = ns->ctrl->max_zone_append; lim->chunk_sectors = ns->head->zsze = nvme_lba_to_sect(ns->head, zi->zone_size); - blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ns->queue); } static void *nvme_zns_alloc_report_buffer(struct nvme_ns *ns, diff --git a/drivers/nvme/target/Kconfig b/drivers/nvme/target/Kconfig index 872dd1a0acd8..46be031f91b4 100644 --- a/drivers/nvme/target/Kconfig +++ b/drivers/nvme/target/Kconfig @@ -6,7 +6,6 @@ config NVME_TARGET depends on CONFIGFS_FS select NVME_KEYRING if NVME_TARGET_TCP_TLS select KEYS if NVME_TARGET_TCP_TLS - select BLK_DEV_INTEGRITY_T10 if BLK_DEV_INTEGRITY select SGL_ALLOC help This enabled target side support for the NVMe protocol, that is @@ -18,6 +17,15 @@ config NVME_TARGET To configure the NVMe target you probably want to use the nvmetcli tool from http://git.infradead.org/users/hch/nvmetcli.git. +config NVME_TARGET_DEBUGFS + bool "NVMe Target debugfs support" + depends on NVME_TARGET + help + This enables debugfs support to display the connected controllers + to each subsystem + + If unsure, say N. + config NVME_TARGET_PASSTHRU bool "NVMe Target Passthrough support" depends on NVME_TARGET diff --git a/drivers/nvme/target/Makefile b/drivers/nvme/target/Makefile index c66820102493..c402c44350b2 100644 --- a/drivers/nvme/target/Makefile +++ b/drivers/nvme/target/Makefile @@ -11,6 +11,7 @@ obj-$(CONFIG_NVME_TARGET_TCP) += nvmet-tcp.o nvmet-y += core.o configfs.o admin-cmd.o fabrics-cmd.o \ discovery.o io-cmd-file.o io-cmd-bdev.o +nvmet-$(CONFIG_NVME_TARGET_DEBUGFS) += debugfs.o nvmet-$(CONFIG_NVME_TARGET_PASSTHRU) += passthru.o nvmet-$(CONFIG_BLK_DEV_ZONED) += zns.o nvmet-$(CONFIG_NVME_TARGET_AUTH) += fabrics-cmd-auth.o auth.o diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index f5b7054a4a05..f7e1156ac7ec 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -344,7 +344,7 @@ static void nvmet_execute_get_log_page(struct nvmet_req *req) pr_debug("unhandled lid %d on qid %d\n", req->cmd->get_log_page.lid, req->sq->qid); req->error_loc = offsetof(struct nvme_get_log_page_command, lid); - nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR); + nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_STATUS_DNR); } static void nvmet_execute_identify_ctrl(struct nvmet_req *req) @@ -496,7 +496,7 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req) if (le32_to_cpu(req->cmd->identify.nsid) == NVME_NSID_ALL) { req->error_loc = offsetof(struct nvme_identify, nsid); - status = NVME_SC_INVALID_NS | NVME_SC_DNR; + status = NVME_SC_INVALID_NS | NVME_STATUS_DNR; goto out; } @@ -662,7 +662,7 @@ static void nvmet_execute_identify_desclist(struct nvmet_req *req) if (sg_zero_buffer(req->sg, req->sg_cnt, NVME_IDENTIFY_DATA_SIZE - off, off) != NVME_IDENTIFY_DATA_SIZE - off) - status = NVME_SC_INTERNAL | NVME_SC_DNR; + status = NVME_SC_INTERNAL | NVME_STATUS_DNR; out: nvmet_req_complete(req, status); @@ -724,7 +724,7 @@ static void nvmet_execute_identify(struct nvmet_req *req) pr_debug("unhandled identify cns %d on qid %d\n", req->cmd->identify.cns, req->sq->qid); req->error_loc = offsetof(struct nvme_identify, cns); - nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR); + nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_STATUS_DNR); } /* @@ -807,7 +807,7 @@ u16 nvmet_set_feat_async_event(struct nvmet_req *req, u32 mask) if (val32 & ~mask) { req->error_loc = offsetof(struct nvme_common_command, cdw11); - return NVME_SC_INVALID_FIELD | NVME_SC_DNR; + return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; } WRITE_ONCE(req->sq->ctrl->aen_enabled, val32); @@ -833,7 +833,7 @@ void nvmet_execute_set_features(struct nvmet_req *req) ncqr = (cdw11 >> 16) & 0xffff; nsqr = cdw11 & 0xffff; if (ncqr == 0xffff || nsqr == 0xffff) { - status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; break; } nvmet_set_result(req, @@ -846,14 +846,14 @@ void nvmet_execute_set_features(struct nvmet_req *req) status = nvmet_set_feat_async_event(req, NVMET_AEN_CFG_ALL); break; case NVME_FEAT_HOST_ID: - status = NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR; + status = NVME_SC_CMD_SEQ_ERROR | NVME_STATUS_DNR; break; case NVME_FEAT_WRITE_PROTECT: status = nvmet_set_feat_write_protect(req); break; default: req->error_loc = offsetof(struct nvme_common_command, cdw10); - status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; break; } @@ -939,7 +939,7 @@ void nvmet_execute_get_features(struct nvmet_req *req) if (!(req->cmd->common.cdw11 & cpu_to_le32(1 << 0))) { req->error_loc = offsetof(struct nvme_common_command, cdw11); - status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; break; } @@ -952,7 +952,7 @@ void nvmet_execute_get_features(struct nvmet_req *req) default: req->error_loc = offsetof(struct nvme_common_command, cdw10); - status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; break; } @@ -969,7 +969,7 @@ void nvmet_execute_async_event(struct nvmet_req *req) mutex_lock(&ctrl->lock); if (ctrl->nr_async_event_cmds >= NVMET_ASYNC_EVENTS) { mutex_unlock(&ctrl->lock); - nvmet_req_complete(req, NVME_SC_ASYNC_LIMIT | NVME_SC_DNR); + nvmet_req_complete(req, NVME_SC_ASYNC_LIMIT | NVME_STATUS_DNR); return; } ctrl->async_event_cmds[ctrl->nr_async_event_cmds++] = req; @@ -1006,7 +1006,7 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req) if (nvme_is_fabrics(cmd)) return nvmet_parse_fabrics_admin_cmd(req); if (unlikely(!nvmet_check_auth_status(req))) - return NVME_SC_AUTH_REQUIRED | NVME_SC_DNR; + return NVME_SC_AUTH_REQUIRED | NVME_STATUS_DNR; if (nvmet_is_disc_subsys(nvmet_req_subsys(req))) return nvmet_parse_discovery_cmd(req); diff --git a/drivers/nvme/target/auth.c b/drivers/nvme/target/auth.c index 7d2633940f9b..8bc3f431c77f 100644 --- a/drivers/nvme/target/auth.c +++ b/drivers/nvme/target/auth.c @@ -314,7 +314,7 @@ int nvmet_auth_host_hash(struct nvmet_req *req, u8 *response, req->sq->dhchap_c1, challenge, shash_len); if (ret) - goto out_free_response; + goto out_free_challenge; } pr_debug("ctrl %d qid %d host response seq %u transaction %d\n", @@ -325,7 +325,7 @@ int nvmet_auth_host_hash(struct nvmet_req *req, u8 *response, GFP_KERNEL); if (!shash) { ret = -ENOMEM; - goto out_free_response; + goto out_free_challenge; } shash->tfm = shash_tfm; ret = crypto_shash_init(shash); @@ -361,9 +361,10 @@ int nvmet_auth_host_hash(struct nvmet_req *req, u8 *response, goto out; ret = crypto_shash_final(shash, response); out: + kfree(shash); +out_free_challenge: if (challenge != req->sq->dhchap_c1) kfree(challenge); - kfree(shash); out_free_response: nvme_auth_free_key(transformed_key); out_free_tfm: @@ -427,14 +428,14 @@ int nvmet_auth_ctrl_hash(struct nvmet_req *req, u8 *response, req->sq->dhchap_c2, challenge, shash_len); if (ret) - goto out_free_response; + goto out_free_challenge; } shash = kzalloc(sizeof(*shash) + crypto_shash_descsize(shash_tfm), GFP_KERNEL); if (!shash) { ret = -ENOMEM; - goto out_free_response; + goto out_free_challenge; } shash->tfm = shash_tfm; @@ -471,9 +472,10 @@ int nvmet_auth_ctrl_hash(struct nvmet_req *req, u8 *response, goto out; ret = crypto_shash_final(shash, response); out: + kfree(shash); +out_free_challenge: if (challenge != req->sq->dhchap_c2) kfree(challenge); - kfree(shash); out_free_response: nvme_auth_free_key(transformed_key); out_free_tfm: diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 4ff460ba2826..ed2424f8a396 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -16,6 +16,7 @@ #include "trace.h" #include "nvmet.h" +#include "debugfs.h" struct kmem_cache *nvmet_bvec_cache; struct workqueue_struct *buffered_io_wq; @@ -55,18 +56,18 @@ inline u16 errno_to_nvme_status(struct nvmet_req *req, int errno) return NVME_SC_SUCCESS; case -ENOSPC: req->error_loc = offsetof(struct nvme_rw_command, length); - return NVME_SC_CAP_EXCEEDED | NVME_SC_DNR; + return NVME_SC_CAP_EXCEEDED | NVME_STATUS_DNR; case -EREMOTEIO: req->error_loc = offsetof(struct nvme_rw_command, slba); - return NVME_SC_LBA_RANGE | NVME_SC_DNR; + return NVME_SC_LBA_RANGE | NVME_STATUS_DNR; case -EOPNOTSUPP: req->error_loc = offsetof(struct nvme_common_command, opcode); switch (req->cmd->common.opcode) { case nvme_cmd_dsm: case nvme_cmd_write_zeroes: - return NVME_SC_ONCS_NOT_SUPPORTED | NVME_SC_DNR; + return NVME_SC_ONCS_NOT_SUPPORTED | NVME_STATUS_DNR; default: - return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; + return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR; } break; case -ENODATA: @@ -76,7 +77,7 @@ inline u16 errno_to_nvme_status(struct nvmet_req *req, int errno) fallthrough; default: req->error_loc = offsetof(struct nvme_common_command, opcode); - return NVME_SC_INTERNAL | NVME_SC_DNR; + return NVME_SC_INTERNAL | NVME_STATUS_DNR; } } @@ -86,7 +87,7 @@ u16 nvmet_report_invalid_opcode(struct nvmet_req *req) req->sq->qid); req->error_loc = offsetof(struct nvme_common_command, opcode); - return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; + return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR; } static struct nvmet_subsys *nvmet_find_get_subsys(struct nvmet_port *port, @@ -97,7 +98,7 @@ u16 nvmet_copy_to_sgl(struct nvmet_req *req, off_t off, const void *buf, { if (sg_pcopy_from_buffer(req->sg, req->sg_cnt, buf, len, off) != len) { req->error_loc = offsetof(struct nvme_common_command, dptr); - return NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR; + return NVME_SC_SGL_INVALID_DATA | NVME_STATUS_DNR; } return 0; } @@ -106,7 +107,7 @@ u16 nvmet_copy_from_sgl(struct nvmet_req *req, off_t off, void *buf, size_t len) { if (sg_pcopy_to_buffer(req->sg, req->sg_cnt, buf, len, off) != len) { req->error_loc = offsetof(struct nvme_common_command, dptr); - return NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR; + return NVME_SC_SGL_INVALID_DATA | NVME_STATUS_DNR; } return 0; } @@ -115,7 +116,7 @@ u16 nvmet_zero_sgl(struct nvmet_req *req, off_t off, size_t len) { if (sg_zero_buffer(req->sg, req->sg_cnt, len, off) != len) { req->error_loc = offsetof(struct nvme_common_command, dptr); - return NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR; + return NVME_SC_SGL_INVALID_DATA | NVME_STATUS_DNR; } return 0; } @@ -145,7 +146,7 @@ static void nvmet_async_events_failall(struct nvmet_ctrl *ctrl) while (ctrl->nr_async_event_cmds) { req = ctrl->async_event_cmds[--ctrl->nr_async_event_cmds]; mutex_unlock(&ctrl->lock); - nvmet_req_complete(req, NVME_SC_INTERNAL | NVME_SC_DNR); + nvmet_req_complete(req, NVME_SC_INTERNAL | NVME_STATUS_DNR); mutex_lock(&ctrl->lock); } mutex_unlock(&ctrl->lock); @@ -444,7 +445,7 @@ u16 nvmet_req_find_ns(struct nvmet_req *req) req->error_loc = offsetof(struct nvme_common_command, nsid); if (nvmet_subsys_nsid_exists(subsys, nsid)) return NVME_SC_INTERNAL_PATH_ERROR; - return NVME_SC_INVALID_NS | NVME_SC_DNR; + return NVME_SC_INVALID_NS | NVME_STATUS_DNR; } percpu_ref_get(&req->ns->ref); @@ -904,7 +905,7 @@ static u16 nvmet_parse_io_cmd(struct nvmet_req *req) return nvmet_parse_fabrics_io_cmd(req); if (unlikely(!nvmet_check_auth_status(req))) - return NVME_SC_AUTH_REQUIRED | NVME_SC_DNR; + return NVME_SC_AUTH_REQUIRED | NVME_STATUS_DNR; ret = nvmet_check_ctrl_status(req); if (unlikely(ret)) @@ -967,7 +968,7 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, /* no support for fused commands yet */ if (unlikely(flags & (NVME_CMD_FUSE_FIRST | NVME_CMD_FUSE_SECOND))) { req->error_loc = offsetof(struct nvme_common_command, flags); - status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; goto fail; } @@ -978,7 +979,7 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, */ if (unlikely((flags & NVME_CMD_SGL_ALL) != NVME_CMD_SGL_METABUF)) { req->error_loc = offsetof(struct nvme_common_command, flags); - status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; goto fail; } @@ -996,7 +997,7 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, trace_nvmet_req_init(req, req->cmd); if (unlikely(!percpu_ref_tryget_live(&sq->ref))) { - status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; goto fail; } @@ -1023,7 +1024,7 @@ bool nvmet_check_transfer_len(struct nvmet_req *req, size_t len) { if (unlikely(len != req->transfer_len)) { req->error_loc = offsetof(struct nvme_common_command, dptr); - nvmet_req_complete(req, NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR); + nvmet_req_complete(req, NVME_SC_SGL_INVALID_DATA | NVME_STATUS_DNR); return false; } @@ -1035,7 +1036,7 @@ bool nvmet_check_data_len_lte(struct nvmet_req *req, size_t data_len) { if (unlikely(data_len > req->transfer_len)) { req->error_loc = offsetof(struct nvme_common_command, dptr); - nvmet_req_complete(req, NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR); + nvmet_req_complete(req, NVME_SC_SGL_INVALID_DATA | NVME_STATUS_DNR); return false; } @@ -1304,18 +1305,18 @@ u16 nvmet_check_ctrl_status(struct nvmet_req *req) if (unlikely(!(req->sq->ctrl->cc & NVME_CC_ENABLE))) { pr_err("got cmd %d while CC.EN == 0 on qid = %d\n", req->cmd->common.opcode, req->sq->qid); - return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR; + return NVME_SC_CMD_SEQ_ERROR | NVME_STATUS_DNR; } if (unlikely(!(req->sq->ctrl->csts & NVME_CSTS_RDY))) { pr_err("got cmd %d while CSTS.RDY == 0 on qid = %d\n", req->cmd->common.opcode, req->sq->qid); - return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR; + return NVME_SC_CMD_SEQ_ERROR | NVME_STATUS_DNR; } if (unlikely(!nvmet_check_auth_status(req))) { pr_warn("qid %d not authenticated\n", req->sq->qid); - return NVME_SC_AUTH_REQUIRED | NVME_SC_DNR; + return NVME_SC_AUTH_REQUIRED | NVME_STATUS_DNR; } return 0; } @@ -1389,7 +1390,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, int ret; u16 status; - status = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR; + status = NVME_SC_CONNECT_INVALID_PARAM | NVME_STATUS_DNR; subsys = nvmet_find_get_subsys(req->port, subsysnqn); if (!subsys) { pr_warn("connect request for invalid subsystem %s!\n", @@ -1405,7 +1406,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, hostnqn, subsysnqn); req->cqe->result.u32 = IPO_IATTR_CONNECT_DATA(hostnqn); up_read(&nvmet_config_sem); - status = NVME_SC_CONNECT_INVALID_HOST | NVME_SC_DNR; + status = NVME_SC_CONNECT_INVALID_HOST | NVME_STATUS_DNR; req->error_loc = offsetof(struct nvme_common_command, dptr); goto out_put_subsystem; } @@ -1456,7 +1457,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, subsys->cntlid_min, subsys->cntlid_max, GFP_KERNEL); if (ret < 0) { - status = NVME_SC_CONNECT_CTRL_BUSY | NVME_SC_DNR; + status = NVME_SC_CONNECT_CTRL_BUSY | NVME_STATUS_DNR; goto out_free_sqs; } ctrl->cntlid = ret; @@ -1479,6 +1480,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, mutex_lock(&subsys->lock); list_add_tail(&ctrl->subsys_entry, &subsys->ctrls); nvmet_setup_p2p_ns_map(ctrl, req); + nvmet_debugfs_ctrl_setup(ctrl); mutex_unlock(&subsys->lock); *ctrlp = ctrl; @@ -1513,6 +1515,8 @@ static void nvmet_ctrl_free(struct kref *ref) nvmet_destroy_auth(ctrl); + nvmet_debugfs_ctrl_free(ctrl); + ida_free(&cntlid_ida, ctrl->cntlid); nvmet_async_events_free(ctrl); @@ -1539,6 +1543,14 @@ void nvmet_ctrl_fatal_error(struct nvmet_ctrl *ctrl) } EXPORT_SYMBOL_GPL(nvmet_ctrl_fatal_error); +ssize_t nvmet_ctrl_host_traddr(struct nvmet_ctrl *ctrl, + char *traddr, size_t traddr_len) +{ + if (!ctrl->ops->host_traddr) + return -EOPNOTSUPP; + return ctrl->ops->host_traddr(ctrl, traddr, traddr_len); +} + static struct nvmet_subsys *nvmet_find_get_subsys(struct nvmet_port *port, const char *subsysnqn) { @@ -1633,8 +1645,14 @@ struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn, INIT_LIST_HEAD(&subsys->ctrls); INIT_LIST_HEAD(&subsys->hosts); + ret = nvmet_debugfs_subsys_setup(subsys); + if (ret) + goto free_subsysnqn; + return subsys; +free_subsysnqn: + kfree(subsys->subsysnqn); free_fr: kfree(subsys->firmware_rev); free_mn: @@ -1651,6 +1669,8 @@ static void nvmet_subsys_free(struct kref *ref) WARN_ON_ONCE(!xa_empty(&subsys->namespaces)); + nvmet_debugfs_subsys_free(subsys); + xa_destroy(&subsys->namespaces); nvmet_passthru_subsys_free(subsys); @@ -1705,11 +1725,18 @@ static int __init nvmet_init(void) if (error) goto out_free_nvmet_work_queue; - error = nvmet_init_configfs(); + error = nvmet_init_debugfs(); if (error) goto out_exit_discovery; + + error = nvmet_init_configfs(); + if (error) + goto out_exit_debugfs; + return 0; +out_exit_debugfs: + nvmet_exit_debugfs(); out_exit_discovery: nvmet_exit_discovery(); out_free_nvmet_work_queue: @@ -1726,6 +1753,7 @@ out_destroy_bvec_cache: static void __exit nvmet_exit(void) { nvmet_exit_configfs(); + nvmet_exit_debugfs(); nvmet_exit_discovery(); ida_destroy(&cntlid_ida); destroy_workqueue(nvmet_wq); diff --git a/drivers/nvme/target/debugfs.c b/drivers/nvme/target/debugfs.c new file mode 100644 index 000000000000..cb2befc8619e --- /dev/null +++ b/drivers/nvme/target/debugfs.c @@ -0,0 +1,202 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * DebugFS interface for the NVMe target. + * Copyright (c) 2022-2024 Shadow + * Copyright (c) 2024 SUSE LLC + */ + +#include +#include +#include +#include + +#include "nvmet.h" +#include "debugfs.h" + +struct dentry *nvmet_debugfs; + +#define NVMET_DEBUGFS_ATTR(field) \ + static int field##_open(struct inode *inode, struct file *file) \ + { return single_open(file, field##_show, inode->i_private); } \ + \ + static const struct file_operations field##_fops = { \ + .open = field##_open, \ + .read = seq_read, \ + .release = single_release, \ + } + +#define NVMET_DEBUGFS_RW_ATTR(field) \ + static int field##_open(struct inode *inode, struct file *file) \ + { return single_open(file, field##_show, inode->i_private); } \ + \ + static const struct file_operations field##_fops = { \ + .open = field##_open, \ + .read = seq_read, \ + .write = field##_write, \ + .release = single_release, \ + } + +static int nvmet_ctrl_hostnqn_show(struct seq_file *m, void *p) +{ + struct nvmet_ctrl *ctrl = m->private; + + seq_puts(m, ctrl->hostnqn); + return 0; +} +NVMET_DEBUGFS_ATTR(nvmet_ctrl_hostnqn); + +static int nvmet_ctrl_kato_show(struct seq_file *m, void *p) +{ + struct nvmet_ctrl *ctrl = m->private; + + seq_printf(m, "%d\n", ctrl->kato); + return 0; +} +NVMET_DEBUGFS_ATTR(nvmet_ctrl_kato); + +static int nvmet_ctrl_port_show(struct seq_file *m, void *p) +{ + struct nvmet_ctrl *ctrl = m->private; + + seq_printf(m, "%d\n", le16_to_cpu(ctrl->port->disc_addr.portid)); + return 0; +} +NVMET_DEBUGFS_ATTR(nvmet_ctrl_port); + +static const char *const csts_state_names[] = { + [NVME_CSTS_RDY] = "ready", + [NVME_CSTS_CFS] = "fatal", + [NVME_CSTS_NSSRO] = "reset", + [NVME_CSTS_SHST_OCCUR] = "shutdown", + [NVME_CSTS_SHST_CMPLT] = "completed", + [NVME_CSTS_PP] = "paused", +}; + +static int nvmet_ctrl_state_show(struct seq_file *m, void *p) +{ + struct nvmet_ctrl *ctrl = m->private; + bool sep = false; + int i; + + for (i = 0; i < 7; i++) { + int state = BIT(i); + + if (!(ctrl->csts & state)) + continue; + if (sep) + seq_puts(m, "|"); + sep = true; + if (csts_state_names[state]) + seq_puts(m, csts_state_names[state]); + else + seq_printf(m, "%d", state); + } + if (sep) + seq_printf(m, "\n"); + return 0; +} + +static ssize_t nvmet_ctrl_state_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct seq_file *m = file->private_data; + struct nvmet_ctrl *ctrl = m->private; + char reset[16]; + + if (count >= sizeof(reset)) + return -EINVAL; + if (copy_from_user(reset, buf, count)) + return -EFAULT; + if (!memcmp(reset, "fatal", 5)) + nvmet_ctrl_fatal_error(ctrl); + else + return -EINVAL; + return count; +} +NVMET_DEBUGFS_RW_ATTR(nvmet_ctrl_state); + +static int nvmet_ctrl_host_traddr_show(struct seq_file *m, void *p) +{ + struct nvmet_ctrl *ctrl = m->private; + ssize_t size; + char buf[NVMF_TRADDR_SIZE + 1]; + + size = nvmet_ctrl_host_traddr(ctrl, buf, NVMF_TRADDR_SIZE); + if (size < 0) { + buf[0] = '\0'; + size = 0; + } + buf[size] = '\0'; + seq_printf(m, "%s\n", buf); + return 0; +} +NVMET_DEBUGFS_ATTR(nvmet_ctrl_host_traddr); + +int nvmet_debugfs_ctrl_setup(struct nvmet_ctrl *ctrl) +{ + char name[32]; + struct dentry *parent = ctrl->subsys->debugfs_dir; + int ret; + + if (!parent) + return -ENODEV; + snprintf(name, sizeof(name), "ctrl%d", ctrl->cntlid); + ctrl->debugfs_dir = debugfs_create_dir(name, parent); + if (IS_ERR(ctrl->debugfs_dir)) { + ret = PTR_ERR(ctrl->debugfs_dir); + ctrl->debugfs_dir = NULL; + return ret; + } + debugfs_create_file("port", S_IRUSR, ctrl->debugfs_dir, ctrl, + &nvmet_ctrl_port_fops); + debugfs_create_file("hostnqn", S_IRUSR, ctrl->debugfs_dir, ctrl, + &nvmet_ctrl_hostnqn_fops); + debugfs_create_file("kato", S_IRUSR, ctrl->debugfs_dir, ctrl, + &nvmet_ctrl_kato_fops); + debugfs_create_file("state", S_IRUSR | S_IWUSR, ctrl->debugfs_dir, ctrl, + &nvmet_ctrl_state_fops); + debugfs_create_file("host_traddr", S_IRUSR, ctrl->debugfs_dir, ctrl, + &nvmet_ctrl_host_traddr_fops); + return 0; +} + +void nvmet_debugfs_ctrl_free(struct nvmet_ctrl *ctrl) +{ + debugfs_remove_recursive(ctrl->debugfs_dir); +} + +int nvmet_debugfs_subsys_setup(struct nvmet_subsys *subsys) +{ + int ret = 0; + + subsys->debugfs_dir = debugfs_create_dir(subsys->subsysnqn, + nvmet_debugfs); + if (IS_ERR(subsys->debugfs_dir)) { + ret = PTR_ERR(subsys->debugfs_dir); + subsys->debugfs_dir = NULL; + } + return ret; +} + +void nvmet_debugfs_subsys_free(struct nvmet_subsys *subsys) +{ + debugfs_remove_recursive(subsys->debugfs_dir); +} + +int __init nvmet_init_debugfs(void) +{ + struct dentry *parent; + + parent = debugfs_create_dir("nvmet", NULL); + if (IS_ERR(parent)) { + pr_warn("%s: failed to create debugfs directory\n", "nvmet"); + return PTR_ERR(parent); + } + nvmet_debugfs = parent; + return 0; +} + +void nvmet_exit_debugfs(void) +{ + debugfs_remove_recursive(nvmet_debugfs); +} diff --git a/drivers/nvme/target/debugfs.h b/drivers/nvme/target/debugfs.h new file mode 100644 index 000000000000..cfb8bbf6a297 --- /dev/null +++ b/drivers/nvme/target/debugfs.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * DebugFS interface for the NVMe target. + * Copyright (c) 2022-2024 Shadow + * Copyright (c) 2024 SUSE LLC + */ +#ifndef NVMET_DEBUGFS_H +#define NVMET_DEBUGFS_H + +#include + +#ifdef CONFIG_NVME_TARGET_DEBUGFS +int nvmet_debugfs_subsys_setup(struct nvmet_subsys *subsys); +void nvmet_debugfs_subsys_free(struct nvmet_subsys *subsys); +int nvmet_debugfs_ctrl_setup(struct nvmet_ctrl *ctrl); +void nvmet_debugfs_ctrl_free(struct nvmet_ctrl *ctrl); + +int __init nvmet_init_debugfs(void); +void nvmet_exit_debugfs(void); +#else +static inline int nvmet_debugfs_subsys_setup(struct nvmet_subsys *subsys) +{ + return 0; +} +static inline void nvmet_debugfs_subsys_free(struct nvmet_subsys *subsys){} + +static inline int nvmet_debugfs_ctrl_setup(struct nvmet_ctrl *ctrl) +{ + return 0; +} +static inline void nvmet_debugfs_ctrl_free(struct nvmet_ctrl *ctrl) {} + +static inline int __init nvmet_init_debugfs(void) +{ + return 0; +} + +static inline void nvmet_exit_debugfs(void) {} + +#endif + +#endif /* NVMET_DEBUGFS_H */ diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c index ce54da8c6b36..28843df5fa7c 100644 --- a/drivers/nvme/target/discovery.c +++ b/drivers/nvme/target/discovery.c @@ -179,7 +179,7 @@ static void nvmet_execute_disc_get_log_page(struct nvmet_req *req) if (req->cmd->get_log_page.lid != NVME_LOG_DISC) { req->error_loc = offsetof(struct nvme_get_log_page_command, lid); - status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; goto out; } @@ -187,7 +187,7 @@ static void nvmet_execute_disc_get_log_page(struct nvmet_req *req) if (offset & 0x3) { req->error_loc = offsetof(struct nvme_get_log_page_command, lpo); - status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; goto out; } @@ -256,7 +256,7 @@ static void nvmet_execute_disc_identify(struct nvmet_req *req) if (req->cmd->identify.cns != NVME_ID_CNS_CTRL) { req->error_loc = offsetof(struct nvme_identify, cns); - status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; goto out; } @@ -320,7 +320,7 @@ static void nvmet_execute_disc_set_features(struct nvmet_req *req) default: req->error_loc = offsetof(struct nvme_common_command, cdw10); - stat = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + stat = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; break; } @@ -345,7 +345,7 @@ static void nvmet_execute_disc_get_features(struct nvmet_req *req) default: req->error_loc = offsetof(struct nvme_common_command, cdw10); - stat = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + stat = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; break; } @@ -361,7 +361,7 @@ u16 nvmet_parse_discovery_cmd(struct nvmet_req *req) cmd->common.opcode); req->error_loc = offsetof(struct nvme_common_command, opcode); - return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; + return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR; } switch (cmd->common.opcode) { @@ -386,7 +386,7 @@ u16 nvmet_parse_discovery_cmd(struct nvmet_req *req) default: pr_debug("unhandled cmd %d\n", cmd->common.opcode); req->error_loc = offsetof(struct nvme_common_command, opcode); - return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; + return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR; } } diff --git a/drivers/nvme/target/fabrics-cmd-auth.c b/drivers/nvme/target/fabrics-cmd-auth.c index cb34d644ed08..3f2857c17d95 100644 --- a/drivers/nvme/target/fabrics-cmd-auth.c +++ b/drivers/nvme/target/fabrics-cmd-auth.c @@ -189,26 +189,26 @@ void nvmet_execute_auth_send(struct nvmet_req *req) u8 dhchap_status; if (req->cmd->auth_send.secp != NVME_AUTH_DHCHAP_PROTOCOL_IDENTIFIER) { - status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; req->error_loc = offsetof(struct nvmf_auth_send_command, secp); goto done; } if (req->cmd->auth_send.spsp0 != 0x01) { - status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; req->error_loc = offsetof(struct nvmf_auth_send_command, spsp0); goto done; } if (req->cmd->auth_send.spsp1 != 0x01) { - status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; req->error_loc = offsetof(struct nvmf_auth_send_command, spsp1); goto done; } tl = le32_to_cpu(req->cmd->auth_send.tl); if (!tl) { - status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; req->error_loc = offsetof(struct nvmf_auth_send_command, tl); goto done; @@ -437,26 +437,26 @@ void nvmet_execute_auth_receive(struct nvmet_req *req) u16 status = 0; if (req->cmd->auth_receive.secp != NVME_AUTH_DHCHAP_PROTOCOL_IDENTIFIER) { - status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; req->error_loc = offsetof(struct nvmf_auth_receive_command, secp); goto done; } if (req->cmd->auth_receive.spsp0 != 0x01) { - status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; req->error_loc = offsetof(struct nvmf_auth_receive_command, spsp0); goto done; } if (req->cmd->auth_receive.spsp1 != 0x01) { - status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; req->error_loc = offsetof(struct nvmf_auth_receive_command, spsp1); goto done; } al = le32_to_cpu(req->cmd->auth_receive.al); if (!al) { - status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; req->error_loc = offsetof(struct nvmf_auth_receive_command, al); goto done; diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c index 69d77d34bec1..c4b2eddd5666 100644 --- a/drivers/nvme/target/fabrics-cmd.c +++ b/drivers/nvme/target/fabrics-cmd.c @@ -18,7 +18,7 @@ static void nvmet_execute_prop_set(struct nvmet_req *req) if (req->cmd->prop_set.attrib & 1) { req->error_loc = offsetof(struct nvmf_property_set_command, attrib); - status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; goto out; } @@ -29,7 +29,7 @@ static void nvmet_execute_prop_set(struct nvmet_req *req) default: req->error_loc = offsetof(struct nvmf_property_set_command, offset); - status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; } out: nvmet_req_complete(req, status); @@ -50,7 +50,7 @@ static void nvmet_execute_prop_get(struct nvmet_req *req) val = ctrl->cap; break; default: - status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; break; } } else { @@ -65,7 +65,7 @@ static void nvmet_execute_prop_get(struct nvmet_req *req) val = ctrl->csts; break; default: - status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; break; } } @@ -105,7 +105,7 @@ u16 nvmet_parse_fabrics_admin_cmd(struct nvmet_req *req) pr_debug("received unknown capsule type 0x%x\n", cmd->fabrics.fctype); req->error_loc = offsetof(struct nvmf_common_command, fctype); - return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; + return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR; } return 0; @@ -128,7 +128,7 @@ u16 nvmet_parse_fabrics_io_cmd(struct nvmet_req *req) pr_debug("received unknown capsule type 0x%x\n", cmd->fabrics.fctype); req->error_loc = offsetof(struct nvmf_common_command, fctype); - return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; + return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR; } return 0; @@ -147,14 +147,14 @@ static u16 nvmet_install_queue(struct nvmet_ctrl *ctrl, struct nvmet_req *req) pr_warn("queue size zero!\n"); req->error_loc = offsetof(struct nvmf_connect_command, sqsize); req->cqe->result.u32 = IPO_IATTR_CONNECT_SQE(sqsize); - ret = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR; + ret = NVME_SC_CONNECT_INVALID_PARAM | NVME_STATUS_DNR; goto err; } if (ctrl->sqs[qid] != NULL) { pr_warn("qid %u has already been created\n", qid); req->error_loc = offsetof(struct nvmf_connect_command, qid); - return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR; + return NVME_SC_CMD_SEQ_ERROR | NVME_STATUS_DNR; } /* for fabrics, this value applies to only the I/O Submission Queues */ @@ -163,14 +163,14 @@ static u16 nvmet_install_queue(struct nvmet_ctrl *ctrl, struct nvmet_req *req) sqsize, mqes, ctrl->cntlid); req->error_loc = offsetof(struct nvmf_connect_command, sqsize); req->cqe->result.u32 = IPO_IATTR_CONNECT_SQE(sqsize); - return NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR; + return NVME_SC_CONNECT_INVALID_PARAM | NVME_STATUS_DNR; } old = cmpxchg(&req->sq->ctrl, NULL, ctrl); if (old) { pr_warn("queue already connected!\n"); req->error_loc = offsetof(struct nvmf_connect_command, opcode); - return NVME_SC_CONNECT_CTRL_BUSY | NVME_SC_DNR; + return NVME_SC_CONNECT_CTRL_BUSY | NVME_STATUS_DNR; } /* note: convert queue size from 0's-based value to 1's-based value */ @@ -230,14 +230,14 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req) pr_warn("invalid connect version (%d).\n", le16_to_cpu(c->recfmt)); req->error_loc = offsetof(struct nvmf_connect_command, recfmt); - status = NVME_SC_CONNECT_FORMAT | NVME_SC_DNR; + status = NVME_SC_CONNECT_FORMAT | NVME_STATUS_DNR; goto out; } if (unlikely(d->cntlid != cpu_to_le16(0xffff))) { pr_warn("connect attempt for invalid controller ID %#x\n", d->cntlid); - status = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR; + status = NVME_SC_CONNECT_INVALID_PARAM | NVME_STATUS_DNR; req->cqe->result.u32 = IPO_IATTR_CONNECT_DATA(cntlid); goto out; } @@ -257,7 +257,7 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req) dhchap_status); nvmet_ctrl_put(ctrl); if (dhchap_status == NVME_AUTH_DHCHAP_FAILURE_FAILED) - status = (NVME_SC_CONNECT_INVALID_HOST | NVME_SC_DNR); + status = (NVME_SC_CONNECT_INVALID_HOST | NVME_STATUS_DNR); else status = NVME_SC_INTERNAL; goto out; @@ -305,7 +305,7 @@ static void nvmet_execute_io_connect(struct nvmet_req *req) if (c->recfmt != 0) { pr_warn("invalid connect version (%d).\n", le16_to_cpu(c->recfmt)); - status = NVME_SC_CONNECT_FORMAT | NVME_SC_DNR; + status = NVME_SC_CONNECT_FORMAT | NVME_STATUS_DNR; goto out; } @@ -314,13 +314,13 @@ static void nvmet_execute_io_connect(struct nvmet_req *req) ctrl = nvmet_ctrl_find_get(d->subsysnqn, d->hostnqn, le16_to_cpu(d->cntlid), req); if (!ctrl) { - status = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR; + status = NVME_SC_CONNECT_INVALID_PARAM | NVME_STATUS_DNR; goto out; } if (unlikely(qid > ctrl->subsys->max_qid)) { pr_warn("invalid queue id (%d)\n", qid); - status = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR; + status = NVME_SC_CONNECT_INVALID_PARAM | NVME_STATUS_DNR; req->cqe->result.u32 = IPO_IATTR_CONNECT_SQE(qid); goto out_ctrl_put; } @@ -350,13 +350,13 @@ u16 nvmet_parse_connect_cmd(struct nvmet_req *req) pr_debug("invalid command 0x%x on unconnected queue.\n", cmd->fabrics.opcode); req->error_loc = offsetof(struct nvme_common_command, opcode); - return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; + return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR; } if (cmd->fabrics.fctype != nvme_fabrics_type_connect) { pr_debug("invalid capsule type 0x%x on unconnected queue.\n", cmd->fabrics.fctype); req->error_loc = offsetof(struct nvmf_common_command, fctype); - return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; + return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR; } if (cmd->connect.qid == 0) diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index 381b4394731f..3ef4beacde32 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -2934,6 +2934,38 @@ nvmet_fc_discovery_chg(struct nvmet_port *port) tgtport->ops->discovery_event(&tgtport->fc_target_port); } +static ssize_t +nvmet_fc_host_traddr(struct nvmet_ctrl *ctrl, + char *traddr, size_t traddr_size) +{ + struct nvmet_sq *sq = ctrl->sqs[0]; + struct nvmet_fc_tgt_queue *queue = + container_of(sq, struct nvmet_fc_tgt_queue, nvme_sq); + struct nvmet_fc_tgtport *tgtport = queue->assoc ? queue->assoc->tgtport : NULL; + struct nvmet_fc_hostport *hostport = queue->assoc ? queue->assoc->hostport : NULL; + u64 wwnn, wwpn; + ssize_t ret = 0; + + if (!tgtport || !nvmet_fc_tgtport_get(tgtport)) + return -ENODEV; + if (!hostport || !nvmet_fc_hostport_get(hostport)) { + ret = -ENODEV; + goto out_put; + } + + if (tgtport->ops->host_traddr) { + ret = tgtport->ops->host_traddr(hostport->hosthandle, &wwnn, &wwpn); + if (ret) + goto out_put_host; + ret = snprintf(traddr, traddr_size, "nn-0x%llx:pn-0x%llx", wwnn, wwpn); + } +out_put_host: + nvmet_fc_hostport_put(hostport); +out_put: + nvmet_fc_tgtport_put(tgtport); + return ret; +} + static const struct nvmet_fabrics_ops nvmet_fc_tgt_fcp_ops = { .owner = THIS_MODULE, .type = NVMF_TRTYPE_FC, @@ -2943,6 +2975,7 @@ static const struct nvmet_fabrics_ops nvmet_fc_tgt_fcp_ops = { .queue_response = nvmet_fc_fcp_nvme_cmd_done, .delete_ctrl = nvmet_fc_delete_ctrl, .discovery_chg = nvmet_fc_discovery_chg, + .host_traddr = nvmet_fc_host_traddr, }; static int __init nvmet_fc_init_module(void) diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index 913cd2ec7a6f..e1abb27927ff 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -492,6 +492,16 @@ fcloop_t2h_host_release(void *hosthandle) /* host handle ignored for now */ } +static int +fcloop_t2h_host_traddr(void *hosthandle, u64 *wwnn, u64 *wwpn) +{ + struct fcloop_rport *rport = hosthandle; + + *wwnn = rport->lport->localport->node_name; + *wwpn = rport->lport->localport->port_name; + return 0; +} + /* * Simulate reception of RSCN and converting it to a initiator transport * call to rescan a remote port. @@ -1074,6 +1084,7 @@ static struct nvmet_fc_target_template tgttemplate = { .ls_req = fcloop_t2h_ls_req, .ls_abort = fcloop_t2h_ls_abort, .host_release = fcloop_t2h_host_release, + .host_traddr = fcloop_t2h_host_traddr, .max_hw_queues = FCLOOP_HW_QUEUES, .max_sgl_segments = FCLOOP_SGL_SEGS, .max_dif_sgl_segments = FCLOOP_SGL_SEGS, diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index 6426aac2634a..0bda83d0fc3e 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -61,15 +61,17 @@ static void nvmet_bdev_ns_enable_integrity(struct nvmet_ns *ns) { struct blk_integrity *bi = bdev_get_integrity(ns->bdev); - if (bi) { + if (!bi) + return; + + if (bi->csum_type == BLK_INTEGRITY_CSUM_CRC) { ns->metadata_size = bi->tuple_size; - if (bi->profile == &t10_pi_type1_crc) + if (bi->flags & BLK_INTEGRITY_REF_TAG) ns->pi_type = NVME_NS_DPS_PI_TYPE1; - else if (bi->profile == &t10_pi_type3_crc) - ns->pi_type = NVME_NS_DPS_PI_TYPE3; else - /* Unsupported metadata type */ - ns->metadata_size = 0; + ns->pi_type = NVME_NS_DPS_PI_TYPE3; + } else { + ns->metadata_size = 0; } } @@ -102,7 +104,7 @@ int nvmet_bdev_ns_enable(struct nvmet_ns *ns) ns->pi_type = 0; ns->metadata_size = 0; - if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY_T10)) + if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY)) nvmet_bdev_ns_enable_integrity(ns); if (bdev_is_zoned(ns->bdev)) { @@ -135,11 +137,11 @@ u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts) */ switch (blk_sts) { case BLK_STS_NOSPC: - status = NVME_SC_CAP_EXCEEDED | NVME_SC_DNR; + status = NVME_SC_CAP_EXCEEDED | NVME_STATUS_DNR; req->error_loc = offsetof(struct nvme_rw_command, length); break; case BLK_STS_TARGET: - status = NVME_SC_LBA_RANGE | NVME_SC_DNR; + status = NVME_SC_LBA_RANGE | NVME_STATUS_DNR; req->error_loc = offsetof(struct nvme_rw_command, slba); break; case BLK_STS_NOTSUPP: @@ -147,10 +149,10 @@ u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts) switch (req->cmd->common.opcode) { case nvme_cmd_dsm: case nvme_cmd_write_zeroes: - status = NVME_SC_ONCS_NOT_SUPPORTED | NVME_SC_DNR; + status = NVME_SC_ONCS_NOT_SUPPORTED | NVME_STATUS_DNR; break; default: - status = NVME_SC_INVALID_OPCODE | NVME_SC_DNR; + status = NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR; } break; case BLK_STS_MEDIUM: @@ -159,7 +161,7 @@ u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts) break; case BLK_STS_IOERR: default: - status = NVME_SC_INTERNAL | NVME_SC_DNR; + status = NVME_SC_INTERNAL | NVME_STATUS_DNR; req->error_loc = offsetof(struct nvme_common_command, opcode); } @@ -356,7 +358,7 @@ u16 nvmet_bdev_flush(struct nvmet_req *req) return 0; if (blkdev_issue_flush(req->ns->bdev)) - return NVME_SC_INTERNAL | NVME_SC_DNR; + return NVME_SC_INTERNAL | NVME_STATUS_DNR; return 0; } diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index e589915ddef8..e32790d8fc26 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -555,6 +555,10 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev, goto out; } + ret = nvme_add_ctrl(&ctrl->ctrl); + if (ret) + goto out_put_ctrl; + if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) WARN_ON_ONCE(1); @@ -611,6 +615,7 @@ out_free_queues: kfree(ctrl->queues); out_uninit_ctrl: nvme_uninit_ctrl(&ctrl->ctrl); +out_put_ctrl: nvme_put_ctrl(&ctrl->ctrl); out: if (ret > 0) diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 2f22b07eab29..190f55e6d753 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -230,7 +230,9 @@ struct nvmet_ctrl { struct device *p2p_client; struct radix_tree_root p2p_ns_map; - +#ifdef CONFIG_NVME_TARGET_DEBUGFS + struct dentry *debugfs_dir; +#endif spinlock_t error_lock; u64 err_counter; struct nvme_error_slot slots[NVMET_ERROR_LOG_SLOTS]; @@ -262,7 +264,9 @@ struct nvmet_subsys { struct list_head hosts; bool allow_any_host; - +#ifdef CONFIG_NVME_TARGET_DEBUGFS + struct dentry *debugfs_dir; +#endif u16 max_qid; u64 ver; @@ -350,6 +354,8 @@ struct nvmet_fabrics_ops { void (*delete_ctrl)(struct nvmet_ctrl *ctrl); void (*disc_traddr)(struct nvmet_req *req, struct nvmet_port *port, char *traddr); + ssize_t (*host_traddr)(struct nvmet_ctrl *ctrl, + char *traddr, size_t traddr_len); u16 (*install_queue)(struct nvmet_sq *nvme_sq); void (*discovery_chg)(struct nvmet_port *port); u8 (*get_mdts)(const struct nvmet_ctrl *ctrl); @@ -498,6 +504,8 @@ struct nvmet_ctrl *nvmet_ctrl_find_get(const char *subsysnqn, struct nvmet_req *req); void nvmet_ctrl_put(struct nvmet_ctrl *ctrl); u16 nvmet_check_ctrl_status(struct nvmet_req *req); +ssize_t nvmet_ctrl_host_traddr(struct nvmet_ctrl *ctrl, + char *traddr, size_t traddr_len); struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn, enum nvme_subsys_type type); diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c index f003782d4ecf..24d0e2418d2e 100644 --- a/drivers/nvme/target/passthru.c +++ b/drivers/nvme/target/passthru.c @@ -306,7 +306,7 @@ static void nvmet_passthru_execute_cmd(struct nvmet_req *req) ns = nvme_find_get_ns(ctrl, nsid); if (unlikely(!ns)) { pr_err("failed to get passthru ns nsid:%u\n", nsid); - status = NVME_SC_INVALID_NS | NVME_SC_DNR; + status = NVME_SC_INVALID_NS | NVME_STATUS_DNR; goto out; } @@ -426,7 +426,7 @@ u16 nvmet_parse_passthru_io_cmd(struct nvmet_req *req) * emulated in the future if regular targets grow support for * this feature. */ - return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; + return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR; } return nvmet_setup_passthru_command(req); @@ -478,7 +478,7 @@ static u16 nvmet_passthru_get_set_features(struct nvmet_req *req) case NVME_FEAT_RESV_PERSIST: /* No reservations, see nvmet_parse_passthru_io_cmd() */ default: - return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; + return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR; } } @@ -546,7 +546,7 @@ u16 nvmet_parse_passthru_admin_cmd(struct nvmet_req *req) req->p.use_workqueue = true; return NVME_SC_SUCCESS; } - return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; + return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR; case NVME_ID_CNS_NS: req->execute = nvmet_passthru_execute_cmd; req->p.use_workqueue = true; @@ -558,7 +558,7 @@ u16 nvmet_parse_passthru_admin_cmd(struct nvmet_req *req) req->p.use_workqueue = true; return NVME_SC_SUCCESS; } - return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; + return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR; default: return nvmet_setup_passthru_command(req); } diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 689bb5d3cfdc..1eff8ca6a5f1 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -852,12 +852,12 @@ static u16 nvmet_rdma_map_sgl_inline(struct nvmet_rdma_rsp *rsp) if (!nvme_is_write(rsp->req.cmd)) { rsp->req.error_loc = offsetof(struct nvme_common_command, opcode); - return NVME_SC_INVALID_FIELD | NVME_SC_DNR; + return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; } if (off + len > rsp->queue->dev->inline_data_size) { pr_err("invalid inline data offset!\n"); - return NVME_SC_SGL_INVALID_OFFSET | NVME_SC_DNR; + return NVME_SC_SGL_INVALID_OFFSET | NVME_STATUS_DNR; } /* no data command? */ @@ -919,7 +919,7 @@ static u16 nvmet_rdma_map_sgl(struct nvmet_rdma_rsp *rsp) pr_err("invalid SGL subtype: %#x\n", sgl->type); rsp->req.error_loc = offsetof(struct nvme_common_command, dptr); - return NVME_SC_INVALID_FIELD | NVME_SC_DNR; + return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; } case NVME_KEY_SGL_FMT_DATA_DESC: switch (sgl->type & 0xf) { @@ -931,12 +931,12 @@ static u16 nvmet_rdma_map_sgl(struct nvmet_rdma_rsp *rsp) pr_err("invalid SGL subtype: %#x\n", sgl->type); rsp->req.error_loc = offsetof(struct nvme_common_command, dptr); - return NVME_SC_INVALID_FIELD | NVME_SC_DNR; + return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; } default: pr_err("invalid SGL type: %#x\n", sgl->type); rsp->req.error_loc = offsetof(struct nvme_common_command, dptr); - return NVME_SC_SGL_INVALID_TYPE | NVME_SC_DNR; + return NVME_SC_SGL_INVALID_TYPE | NVME_STATUS_DNR; } } @@ -2000,6 +2000,17 @@ static void nvmet_rdma_disc_port_addr(struct nvmet_req *req, } } +static ssize_t nvmet_rdma_host_port_addr(struct nvmet_ctrl *ctrl, + char *traddr, size_t traddr_len) +{ + struct nvmet_sq *nvme_sq = ctrl->sqs[0]; + struct nvmet_rdma_queue *queue = + container_of(nvme_sq, struct nvmet_rdma_queue, nvme_sq); + + return snprintf(traddr, traddr_len, "%pISc", + (struct sockaddr *)&queue->cm_id->route.addr.dst_addr); +} + static u8 nvmet_rdma_get_mdts(const struct nvmet_ctrl *ctrl) { if (ctrl->pi_support) @@ -2024,6 +2035,7 @@ static const struct nvmet_fabrics_ops nvmet_rdma_ops = { .queue_response = nvmet_rdma_queue_response, .delete_ctrl = nvmet_rdma_delete_ctrl, .disc_traddr = nvmet_rdma_disc_port_addr, + .host_traddr = nvmet_rdma_host_port_addr, .get_mdts = nvmet_rdma_get_mdts, .get_max_queue_size = nvmet_rdma_get_max_queue_size, }; diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 380f22ee3ebb..5bff0d5464d1 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -416,10 +416,10 @@ static int nvmet_tcp_map_data(struct nvmet_tcp_cmd *cmd) if (sgl->type == ((NVME_SGL_FMT_DATA_DESC << 4) | NVME_SGL_FMT_OFFSET)) { if (!nvme_is_write(cmd->req.cmd)) - return NVME_SC_INVALID_FIELD | NVME_SC_DNR; + return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; if (len > cmd->req.port->inline_data_size) - return NVME_SC_SGL_INVALID_OFFSET | NVME_SC_DNR; + return NVME_SC_SGL_INVALID_OFFSET | NVME_STATUS_DNR; cmd->pdu_len = len; } cmd->req.transfer_len += len; @@ -2167,6 +2167,19 @@ static void nvmet_tcp_disc_port_addr(struct nvmet_req *req, } } +static ssize_t nvmet_tcp_host_port_addr(struct nvmet_ctrl *ctrl, + char *traddr, size_t traddr_len) +{ + struct nvmet_sq *sq = ctrl->sqs[0]; + struct nvmet_tcp_queue *queue = + container_of(sq, struct nvmet_tcp_queue, nvme_sq); + + if (queue->sockaddr_peer.ss_family == AF_UNSPEC) + return -EINVAL; + return snprintf(traddr, traddr_len, "%pISc", + (struct sockaddr *)&queue->sockaddr_peer); +} + static const struct nvmet_fabrics_ops nvmet_tcp_ops = { .owner = THIS_MODULE, .type = NVMF_TRTYPE_TCP, @@ -2177,6 +2190,7 @@ static const struct nvmet_fabrics_ops nvmet_tcp_ops = { .delete_ctrl = nvmet_tcp_delete_ctrl, .install_queue = nvmet_tcp_install_queue, .disc_traddr = nvmet_tcp_disc_port_addr, + .host_traddr = nvmet_tcp_host_port_addr, }; static int __init nvmet_tcp_init(void) diff --git a/drivers/nvme/target/zns.c b/drivers/nvme/target/zns.c index 0021d06041c1..af9e13be7678 100644 --- a/drivers/nvme/target/zns.c +++ b/drivers/nvme/target/zns.c @@ -100,7 +100,7 @@ void nvmet_execute_identify_ns_zns(struct nvmet_req *req) if (le32_to_cpu(req->cmd->identify.nsid) == NVME_NSID_ALL) { req->error_loc = offsetof(struct nvme_identify, nsid); - status = NVME_SC_INVALID_NS | NVME_SC_DNR; + status = NVME_SC_INVALID_NS | NVME_STATUS_DNR; goto out; } @@ -121,7 +121,7 @@ void nvmet_execute_identify_ns_zns(struct nvmet_req *req) } if (!bdev_is_zoned(req->ns->bdev)) { - status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; req->error_loc = offsetof(struct nvme_identify, nsid); goto out; } @@ -158,17 +158,17 @@ static u16 nvmet_bdev_validate_zone_mgmt_recv(struct nvmet_req *req) if (sect >= get_capacity(req->ns->bdev->bd_disk)) { req->error_loc = offsetof(struct nvme_zone_mgmt_recv_cmd, slba); - return NVME_SC_LBA_RANGE | NVME_SC_DNR; + return NVME_SC_LBA_RANGE | NVME_STATUS_DNR; } if (out_bufsize < sizeof(struct nvme_zone_report)) { req->error_loc = offsetof(struct nvme_zone_mgmt_recv_cmd, numd); - return NVME_SC_INVALID_FIELD | NVME_SC_DNR; + return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; } if (req->cmd->zmr.zra != NVME_ZRA_ZONE_REPORT) { req->error_loc = offsetof(struct nvme_zone_mgmt_recv_cmd, zra); - return NVME_SC_INVALID_FIELD | NVME_SC_DNR; + return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; } switch (req->cmd->zmr.pr) { @@ -177,7 +177,7 @@ static u16 nvmet_bdev_validate_zone_mgmt_recv(struct nvmet_req *req) break; default: req->error_loc = offsetof(struct nvme_zone_mgmt_recv_cmd, pr); - return NVME_SC_INVALID_FIELD | NVME_SC_DNR; + return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; } switch (req->cmd->zmr.zrasf) { @@ -193,7 +193,7 @@ static u16 nvmet_bdev_validate_zone_mgmt_recv(struct nvmet_req *req) default: req->error_loc = offsetof(struct nvme_zone_mgmt_recv_cmd, zrasf); - return NVME_SC_INVALID_FIELD | NVME_SC_DNR; + return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; } return NVME_SC_SUCCESS; @@ -341,7 +341,7 @@ static u16 blkdev_zone_mgmt_errno_to_nvme_status(int ret) return NVME_SC_SUCCESS; case -EINVAL: case -EIO: - return NVME_SC_ZONE_INVALID_TRANSITION | NVME_SC_DNR; + return NVME_SC_ZONE_INVALID_TRANSITION | NVME_STATUS_DNR; default: return NVME_SC_INTERNAL; } @@ -463,7 +463,7 @@ static u16 nvmet_bdev_execute_zmgmt_send_all(struct nvmet_req *req) default: /* this is needed to quiet compiler warning */ req->error_loc = offsetof(struct nvme_zone_mgmt_send_cmd, zsa); - return NVME_SC_INVALID_FIELD | NVME_SC_DNR; + return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; } return NVME_SC_SUCCESS; @@ -481,7 +481,7 @@ static void nvmet_bdev_zmgmt_send_work(struct work_struct *w) if (op == REQ_OP_LAST) { req->error_loc = offsetof(struct nvme_zone_mgmt_send_cmd, zsa); - status = NVME_SC_ZONE_INVALID_TRANSITION | NVME_SC_DNR; + status = NVME_SC_ZONE_INVALID_TRANSITION | NVME_STATUS_DNR; goto out; } @@ -493,13 +493,13 @@ static void nvmet_bdev_zmgmt_send_work(struct work_struct *w) if (sect >= get_capacity(bdev->bd_disk)) { req->error_loc = offsetof(struct nvme_zone_mgmt_send_cmd, slba); - status = NVME_SC_LBA_RANGE | NVME_SC_DNR; + status = NVME_SC_LBA_RANGE | NVME_STATUS_DNR; goto out; } if (sect & (zone_sectors - 1)) { req->error_loc = offsetof(struct nvme_zone_mgmt_send_cmd, slba); - status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; goto out; } @@ -551,13 +551,13 @@ void nvmet_bdev_execute_zone_append(struct nvmet_req *req) if (sect >= get_capacity(req->ns->bdev->bd_disk)) { req->error_loc = offsetof(struct nvme_rw_command, slba); - status = NVME_SC_LBA_RANGE | NVME_SC_DNR; + status = NVME_SC_LBA_RANGE | NVME_STATUS_DNR; goto out; } if (sect & (bdev_zone_sectors(req->ns->bdev) - 1)) { req->error_loc = offsetof(struct nvme_rw_command, slba); - status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; goto out; } @@ -590,7 +590,7 @@ void nvmet_bdev_execute_zone_append(struct nvmet_req *req) } if (total_len != nvmet_rw_data_len(req)) { - status = NVME_SC_INTERNAL | NVME_SC_DNR; + status = NVME_SC_INTERNAL | NVME_STATUS_DNR; goto out_put_bio; } diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c index 4533dd055ca8..1aa426b1dedd 100644 --- a/drivers/s390/block/dasd_genhd.c +++ b/drivers/s390/block/dasd_genhd.c @@ -68,7 +68,6 @@ int dasd_gendisk_alloc(struct dasd_block *block) blk_mq_free_tag_set(&block->tag_set); return PTR_ERR(gdp); } - blk_queue_flag_set(QUEUE_FLAG_NONROT, gdp->queue); /* Initialize gendisk structure. */ gdp->major = DASD_MAJOR; diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index 6d1689a2717e..d5a5d11ae0dc 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -548,6 +548,7 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char { struct queue_limits lim = { .logical_block_size = 4096, + .features = BLK_FEAT_DAX, }; int rc, i, j, num_of_segments; struct dcssblk_dev_info *dev_info; @@ -643,7 +644,6 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char dev_info->gd->fops = &dcssblk_devops; dev_info->gd->private_data = dev_info; dev_info->gd->flags |= GENHD_FL_NO_PART; - blk_queue_flag_set(QUEUE_FLAG_DAX, dev_info->gd->queue); seg_byte_size = (dev_info->end - dev_info->start + 1); set_capacity(dev_info->gd, seg_byte_size >> 9); // size in sectors diff --git a/drivers/s390/block/scm_blk.c b/drivers/s390/block/scm_blk.c index 1d456a5a3bfb..3fcfe029db1b 100644 --- a/drivers/s390/block/scm_blk.c +++ b/drivers/s390/block/scm_blk.c @@ -439,7 +439,6 @@ int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev) .logical_block_size = 1 << 12, }; unsigned int devindex; - struct request_queue *rq; int len, ret; lim.max_segments = min(scmdev->nr_max_block, @@ -474,10 +473,6 @@ int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev) ret = PTR_ERR(bdev->gendisk); goto out_tag; } - rq = bdev->rq = bdev->gendisk->queue; - blk_queue_flag_set(QUEUE_FLAG_NONROT, rq); - blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, rq); - bdev->gendisk->private_data = scmdev; bdev->gendisk->fops = &scm_blk_devops; bdev->gendisk->major = scm_major; diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 065db86d6021..37c24ffea65c 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -82,7 +82,6 @@ comment "SCSI support type (disk, tape, CD-ROM)" config BLK_DEV_SD tristate "SCSI disk support" depends on SCSI - select BLK_DEV_INTEGRITY_T10 if BLK_DEV_INTEGRITY help If you want to use SCSI hard disks, Fibre Channel disks, Serial ATA (SATA) or Parallel ATA (PATA) hard disks, diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c index 60688f18fac6..c708e1059638 100644 --- a/drivers/scsi/iscsi_tcp.c +++ b/drivers/scsi/iscsi_tcp.c @@ -1057,15 +1057,15 @@ static umode_t iscsi_sw_tcp_attr_is_visible(int param_type, int param) return 0; } -static int iscsi_sw_tcp_slave_configure(struct scsi_device *sdev) +static int iscsi_sw_tcp_device_configure(struct scsi_device *sdev, + struct queue_limits *lim) { struct iscsi_sw_tcp_host *tcp_sw_host = iscsi_host_priv(sdev->host); struct iscsi_session *session = tcp_sw_host->session; struct iscsi_conn *conn = session->leadconn; if (conn->datadgst_en) - blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, - sdev->request_queue); + lim->features |= BLK_FEAT_STABLE_WRITES; return 0; } @@ -1083,7 +1083,7 @@ static const struct scsi_host_template iscsi_sw_tcp_sht = { .eh_device_reset_handler= iscsi_eh_device_reset, .eh_target_reset_handler = iscsi_eh_recover_target, .dma_boundary = PAGE_SIZE - 1, - .slave_configure = iscsi_sw_tcp_slave_configure, + .device_configure = iscsi_sw_tcp_device_configure, .proc_name = "iscsi_tcp", .this_id = -1, .track_queue_depth = 1, diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c index 5297cacc8beb..0cef5d089f34 100644 --- a/drivers/scsi/lpfc/lpfc_nvmet.c +++ b/drivers/scsi/lpfc/lpfc_nvmet.c @@ -1363,6 +1363,16 @@ lpfc_nvmet_ls_abort(struct nvmet_fc_target_port *targetport, atomic_inc(&lpfc_nvmet->xmt_ls_abort); } +static int +lpfc_nvmet_host_traddr(void *hosthandle, u64 *wwnn, u64 *wwpn) +{ + struct lpfc_nodelist *ndlp = hosthandle; + + *wwnn = wwn_to_u64(ndlp->nlp_nodename.u.wwn); + *wwpn = wwn_to_u64(ndlp->nlp_portname.u.wwn); + return 0; +} + static void lpfc_nvmet_host_release(void *hosthandle) { @@ -1413,6 +1423,7 @@ static struct nvmet_fc_target_template lpfc_tgttemplate = { .ls_req = lpfc_nvmet_ls_req, .ls_abort = lpfc_nvmet_ls_abort, .host_release = lpfc_nvmet_host_release, + .host_traddr = lpfc_nvmet_host_traddr, .max_hw_queues = 1, .max_sgl_segments = LPFC_NVMET_DEFAULT_SEGS, diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index 88acefbf9aea..6c79c350a4d5 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -1981,8 +1981,6 @@ megasas_set_nvme_device_properties(struct scsi_device *sdev, lim->max_hw_sectors = max_io_size / 512; lim->virt_boundary_mask = mr_nvme_pg_size - 1; - - blk_queue_flag_set(QUEUE_FLAG_NOMERGES, sdev->request_queue); } /* diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 870ec2cb4af4..97c2472cd434 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -2680,12 +2680,6 @@ scsih_device_configure(struct scsi_device *sdev, struct queue_limits *lim) pcie_device_put(pcie_device); spin_unlock_irqrestore(&ioc->pcie_device_lock, flags); mpt3sas_scsih_change_queue_depth(sdev, qdepth); - /* Enable QUEUE_FLAG_NOMERGES flag, so that IOs won't be - ** merged and can eliminate holes created during merging - ** operation. - **/ - blk_queue_flag_set(QUEUE_FLAG_NOMERGES, - sdev->request_queue); lim->virt_boundary_mask = ioc->page_size - 1; return 0; } diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 91f022fb8d0c..a9d8a9c62663 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -69,6 +69,8 @@ static const char *sdebug_version_date = "20210520"; /* Additional Sense Code (ASC) */ #define NO_ADDITIONAL_SENSE 0x0 +#define OVERLAP_ATOMIC_COMMAND_ASC 0x0 +#define OVERLAP_ATOMIC_COMMAND_ASCQ 0x23 #define LOGICAL_UNIT_NOT_READY 0x4 #define LOGICAL_UNIT_COMMUNICATION_FAILURE 0x8 #define UNRECOVERED_READ_ERR 0x11 @@ -103,6 +105,7 @@ static const char *sdebug_version_date = "20210520"; #define READ_BOUNDARY_ASCQ 0x7 #define ATTEMPT_ACCESS_GAP 0x9 #define INSUFF_ZONE_ASCQ 0xe +/* see drivers/scsi/sense_codes.h */ /* Additional Sense Code Qualifier (ASCQ) */ #define ACK_NAK_TO 0x3 @@ -152,6 +155,12 @@ static const char *sdebug_version_date = "20210520"; #define DEF_VIRTUAL_GB 0 #define DEF_VPD_USE_HOSTNO 1 #define DEF_WRITESAME_LENGTH 0xFFFF +#define DEF_ATOMIC_WR 0 +#define DEF_ATOMIC_WR_MAX_LENGTH 8192 +#define DEF_ATOMIC_WR_ALIGN 2 +#define DEF_ATOMIC_WR_GRAN 2 +#define DEF_ATOMIC_WR_MAX_LENGTH_BNDRY (DEF_ATOMIC_WR_MAX_LENGTH) +#define DEF_ATOMIC_WR_MAX_BNDRY 128 #define DEF_STRICT 0 #define DEF_STATISTICS false #define DEF_SUBMIT_QUEUES 1 @@ -374,7 +383,9 @@ struct sdebug_host_info { /* There is an xarray of pointers to this struct's objects, one per host */ struct sdeb_store_info { - rwlock_t macc_lck; /* for atomic media access on this store */ + rwlock_t macc_data_lck; /* for media data access on this store */ + rwlock_t macc_meta_lck; /* for atomic media meta access on this store */ + rwlock_t macc_sector_lck; /* per-sector media data access on this store */ u8 *storep; /* user data storage (ram) */ struct t10_pi_tuple *dif_storep; /* protection info */ void *map_storep; /* provisioning map */ @@ -398,12 +409,20 @@ struct sdebug_defer { enum sdeb_defer_type defer_t; }; +struct sdebug_device_access_info { + bool atomic_write; + u64 lba; + u32 num; + struct scsi_cmnd *self; +}; + struct sdebug_queued_cmd { /* corresponding bit set in in_use_bm[] in owning struct sdebug_queue * instance indicates this slot is in use. */ struct sdebug_defer sd_dp; struct scsi_cmnd *scmd; + struct sdebug_device_access_info *i; }; struct sdebug_scsi_cmd { @@ -463,7 +482,8 @@ enum sdeb_opcode_index { SDEB_I_PRE_FETCH = 29, /* 10, 16 */ SDEB_I_ZONE_OUT = 30, /* 0x94+SA; includes no data xfer */ SDEB_I_ZONE_IN = 31, /* 0x95+SA; all have data-in */ - SDEB_I_LAST_ELEM_P1 = 32, /* keep this last (previous + 1) */ + SDEB_I_ATOMIC_WRITE_16 = 32, + SDEB_I_LAST_ELEM_P1 = 33, /* keep this last (previous + 1) */ }; @@ -497,7 +517,8 @@ static const unsigned char opcode_ind_arr[256] = { 0, 0, 0, SDEB_I_VERIFY, SDEB_I_PRE_FETCH, SDEB_I_SYNC_CACHE, 0, SDEB_I_WRITE_SAME, SDEB_I_ZONE_OUT, SDEB_I_ZONE_IN, 0, 0, - 0, 0, 0, 0, 0, 0, SDEB_I_SERV_ACT_IN_16, SDEB_I_SERV_ACT_OUT_16, + 0, 0, 0, 0, + SDEB_I_ATOMIC_WRITE_16, 0, SDEB_I_SERV_ACT_IN_16, SDEB_I_SERV_ACT_OUT_16, /* 0xa0; 0xa0->0xbf: 12 byte cdbs */ SDEB_I_REPORT_LUNS, SDEB_I_ATA_PT, 0, SDEB_I_MAINT_IN, SDEB_I_MAINT_OUT, 0, 0, 0, @@ -547,6 +568,7 @@ static int resp_write_buffer(struct scsi_cmnd *, struct sdebug_dev_info *); static int resp_sync_cache(struct scsi_cmnd *, struct sdebug_dev_info *); static int resp_pre_fetch(struct scsi_cmnd *, struct sdebug_dev_info *); static int resp_report_zones(struct scsi_cmnd *, struct sdebug_dev_info *); +static int resp_atomic_write(struct scsi_cmnd *, struct sdebug_dev_info *); static int resp_open_zone(struct scsi_cmnd *, struct sdebug_dev_info *); static int resp_close_zone(struct scsi_cmnd *, struct sdebug_dev_info *); static int resp_finish_zone(struct scsi_cmnd *, struct sdebug_dev_info *); @@ -788,6 +810,11 @@ static const struct opcode_info_t opcode_info_arr[SDEB_I_LAST_ELEM_P1 + 1] = { resp_report_zones, zone_in_iarr, /* ZONE_IN(16), REPORT ZONES) */ {16, 0x0 /* SA */, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xbf, 0xc7} }, +/* 31 */ + {0, 0x0, 0x0, F_D_OUT | FF_MEDIA_IO, + resp_atomic_write, NULL, /* ATOMIC WRITE 16 */ + {16, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff} }, /* sentinel */ {0xff, 0, 0, 0, NULL, NULL, /* terminating element */ {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} }, @@ -835,6 +862,13 @@ static unsigned int sdebug_unmap_granularity = DEF_UNMAP_GRANULARITY; static unsigned int sdebug_unmap_max_blocks = DEF_UNMAP_MAX_BLOCKS; static unsigned int sdebug_unmap_max_desc = DEF_UNMAP_MAX_DESC; static unsigned int sdebug_write_same_length = DEF_WRITESAME_LENGTH; +static unsigned int sdebug_atomic_wr = DEF_ATOMIC_WR; +static unsigned int sdebug_atomic_wr_max_length = DEF_ATOMIC_WR_MAX_LENGTH; +static unsigned int sdebug_atomic_wr_align = DEF_ATOMIC_WR_ALIGN; +static unsigned int sdebug_atomic_wr_gran = DEF_ATOMIC_WR_GRAN; +static unsigned int sdebug_atomic_wr_max_length_bndry = + DEF_ATOMIC_WR_MAX_LENGTH_BNDRY; +static unsigned int sdebug_atomic_wr_max_bndry = DEF_ATOMIC_WR_MAX_BNDRY; static int sdebug_uuid_ctl = DEF_UUID_CTL; static bool sdebug_random = DEF_RANDOM; static bool sdebug_per_host_store = DEF_PER_HOST_STORE; @@ -1192,6 +1226,11 @@ static inline bool scsi_debug_lbp(void) (sdebug_lbpu || sdebug_lbpws || sdebug_lbpws10); } +static inline bool scsi_debug_atomic_write(void) +{ + return sdebug_fake_rw == 0 && sdebug_atomic_wr; +} + static void *lba2fake_store(struct sdeb_store_info *sip, unsigned long long lba) { @@ -1819,6 +1858,14 @@ static int inquiry_vpd_b0(unsigned char *arr) /* Maximum WRITE SAME Length */ put_unaligned_be64(sdebug_write_same_length, &arr[32]); + if (sdebug_atomic_wr) { + put_unaligned_be32(sdebug_atomic_wr_max_length, &arr[40]); + put_unaligned_be32(sdebug_atomic_wr_align, &arr[44]); + put_unaligned_be32(sdebug_atomic_wr_gran, &arr[48]); + put_unaligned_be32(sdebug_atomic_wr_max_length_bndry, &arr[52]); + put_unaligned_be32(sdebug_atomic_wr_max_bndry, &arr[56]); + } + return 0x3c; /* Mandatory page length for Logical Block Provisioning */ } @@ -3381,16 +3428,238 @@ static inline struct sdeb_store_info *devip2sip(struct sdebug_dev_info *devip, return xa_load(per_store_ap, devip->sdbg_host->si_idx); } +static inline void +sdeb_read_lock(rwlock_t *lock) +{ + if (sdebug_no_rwlock) + __acquire(lock); + else + read_lock(lock); +} + +static inline void +sdeb_read_unlock(rwlock_t *lock) +{ + if (sdebug_no_rwlock) + __release(lock); + else + read_unlock(lock); +} + +static inline void +sdeb_write_lock(rwlock_t *lock) +{ + if (sdebug_no_rwlock) + __acquire(lock); + else + write_lock(lock); +} + +static inline void +sdeb_write_unlock(rwlock_t *lock) +{ + if (sdebug_no_rwlock) + __release(lock); + else + write_unlock(lock); +} + +static inline void +sdeb_data_read_lock(struct sdeb_store_info *sip) +{ + BUG_ON(!sip); + + sdeb_read_lock(&sip->macc_data_lck); +} + +static inline void +sdeb_data_read_unlock(struct sdeb_store_info *sip) +{ + BUG_ON(!sip); + + sdeb_read_unlock(&sip->macc_data_lck); +} + +static inline void +sdeb_data_write_lock(struct sdeb_store_info *sip) +{ + BUG_ON(!sip); + + sdeb_write_lock(&sip->macc_data_lck); +} + +static inline void +sdeb_data_write_unlock(struct sdeb_store_info *sip) +{ + BUG_ON(!sip); + + sdeb_write_unlock(&sip->macc_data_lck); +} + +static inline void +sdeb_data_sector_read_lock(struct sdeb_store_info *sip) +{ + BUG_ON(!sip); + + sdeb_read_lock(&sip->macc_sector_lck); +} + +static inline void +sdeb_data_sector_read_unlock(struct sdeb_store_info *sip) +{ + BUG_ON(!sip); + + sdeb_read_unlock(&sip->macc_sector_lck); +} + +static inline void +sdeb_data_sector_write_lock(struct sdeb_store_info *sip) +{ + BUG_ON(!sip); + + sdeb_write_lock(&sip->macc_sector_lck); +} + +static inline void +sdeb_data_sector_write_unlock(struct sdeb_store_info *sip) +{ + BUG_ON(!sip); + + sdeb_write_unlock(&sip->macc_sector_lck); +} + +/* + * Atomic locking: + * We simplify the atomic model to allow only 1x atomic write and many non- + * atomic reads or writes for all LBAs. + + * A RW lock has a similar bahaviour: + * Only 1x writer and many readers. + + * So use a RW lock for per-device read and write locking: + * An atomic access grabs the lock as a writer and non-atomic grabs the lock + * as a reader. + */ + +static inline void +sdeb_data_lock(struct sdeb_store_info *sip, bool atomic) +{ + if (atomic) + sdeb_data_write_lock(sip); + else + sdeb_data_read_lock(sip); +} + +static inline void +sdeb_data_unlock(struct sdeb_store_info *sip, bool atomic) +{ + if (atomic) + sdeb_data_write_unlock(sip); + else + sdeb_data_read_unlock(sip); +} + +/* Allow many reads but only 1x write per sector */ +static inline void +sdeb_data_sector_lock(struct sdeb_store_info *sip, bool do_write) +{ + if (do_write) + sdeb_data_sector_write_lock(sip); + else + sdeb_data_sector_read_lock(sip); +} + +static inline void +sdeb_data_sector_unlock(struct sdeb_store_info *sip, bool do_write) +{ + if (do_write) + sdeb_data_sector_write_unlock(sip); + else + sdeb_data_sector_read_unlock(sip); +} + +static inline void +sdeb_meta_read_lock(struct sdeb_store_info *sip) +{ + if (sdebug_no_rwlock) { + if (sip) + __acquire(&sip->macc_meta_lck); + else + __acquire(&sdeb_fake_rw_lck); + } else { + if (sip) + read_lock(&sip->macc_meta_lck); + else + read_lock(&sdeb_fake_rw_lck); + } +} + +static inline void +sdeb_meta_read_unlock(struct sdeb_store_info *sip) +{ + if (sdebug_no_rwlock) { + if (sip) + __release(&sip->macc_meta_lck); + else + __release(&sdeb_fake_rw_lck); + } else { + if (sip) + read_unlock(&sip->macc_meta_lck); + else + read_unlock(&sdeb_fake_rw_lck); + } +} + +static inline void +sdeb_meta_write_lock(struct sdeb_store_info *sip) +{ + if (sdebug_no_rwlock) { + if (sip) + __acquire(&sip->macc_meta_lck); + else + __acquire(&sdeb_fake_rw_lck); + } else { + if (sip) + write_lock(&sip->macc_meta_lck); + else + write_lock(&sdeb_fake_rw_lck); + } +} + +static inline void +sdeb_meta_write_unlock(struct sdeb_store_info *sip) +{ + if (sdebug_no_rwlock) { + if (sip) + __release(&sip->macc_meta_lck); + else + __release(&sdeb_fake_rw_lck); + } else { + if (sip) + write_unlock(&sip->macc_meta_lck); + else + write_unlock(&sdeb_fake_rw_lck); + } +} + /* Returns number of bytes copied or -1 if error. */ static int do_device_access(struct sdeb_store_info *sip, struct scsi_cmnd *scp, - u32 sg_skip, u64 lba, u32 num, bool do_write, - u8 group_number) + u32 sg_skip, u64 lba, u32 num, u8 group_number, + bool do_write, bool atomic) { int ret; - u64 block, rest = 0; + u64 block; enum dma_data_direction dir; struct scsi_data_buffer *sdb = &scp->sdb; u8 *fsp; + int i; + + /* + * Even though reads are inherently atomic (in this driver), we expect + * the atomic flag only for writes. + */ + if (!do_write && atomic) + return -1; if (do_write) { dir = DMA_TO_DEVICE; @@ -3410,21 +3679,26 @@ static int do_device_access(struct sdeb_store_info *sip, struct scsi_cmnd *scp, fsp = sip->storep; block = do_div(lba, sdebug_store_sectors); - if (block + num > sdebug_store_sectors) - rest = block + num - sdebug_store_sectors; - ret = sg_copy_buffer(sdb->table.sgl, sdb->table.nents, + /* Only allow 1x atomic write or multiple non-atomic writes at any given time */ + sdeb_data_lock(sip, atomic); + for (i = 0; i < num; i++) { + /* We shouldn't need to lock for atomic writes, but do it anyway */ + sdeb_data_sector_lock(sip, do_write); + ret = sg_copy_buffer(sdb->table.sgl, sdb->table.nents, fsp + (block * sdebug_sector_size), - (num - rest) * sdebug_sector_size, sg_skip, do_write); - if (ret != (num - rest) * sdebug_sector_size) - return ret; - - if (rest) { - ret += sg_copy_buffer(sdb->table.sgl, sdb->table.nents, - fsp, rest * sdebug_sector_size, - sg_skip + ((num - rest) * sdebug_sector_size), - do_write); + sdebug_sector_size, sg_skip, do_write); + sdeb_data_sector_unlock(sip, do_write); + if (ret != sdebug_sector_size) { + ret += (i * sdebug_sector_size); + break; + } + sg_skip += sdebug_sector_size; + if (++block >= sdebug_store_sectors) + block = 0; } + ret = num * sdebug_sector_size; + sdeb_data_unlock(sip, atomic); return ret; } @@ -3600,70 +3874,6 @@ static int prot_verify_read(struct scsi_cmnd *scp, sector_t start_sec, return ret; } -static inline void -sdeb_read_lock(struct sdeb_store_info *sip) -{ - if (sdebug_no_rwlock) { - if (sip) - __acquire(&sip->macc_lck); - else - __acquire(&sdeb_fake_rw_lck); - } else { - if (sip) - read_lock(&sip->macc_lck); - else - read_lock(&sdeb_fake_rw_lck); - } -} - -static inline void -sdeb_read_unlock(struct sdeb_store_info *sip) -{ - if (sdebug_no_rwlock) { - if (sip) - __release(&sip->macc_lck); - else - __release(&sdeb_fake_rw_lck); - } else { - if (sip) - read_unlock(&sip->macc_lck); - else - read_unlock(&sdeb_fake_rw_lck); - } -} - -static inline void -sdeb_write_lock(struct sdeb_store_info *sip) -{ - if (sdebug_no_rwlock) { - if (sip) - __acquire(&sip->macc_lck); - else - __acquire(&sdeb_fake_rw_lck); - } else { - if (sip) - write_lock(&sip->macc_lck); - else - write_lock(&sdeb_fake_rw_lck); - } -} - -static inline void -sdeb_write_unlock(struct sdeb_store_info *sip) -{ - if (sdebug_no_rwlock) { - if (sip) - __release(&sip->macc_lck); - else - __release(&sdeb_fake_rw_lck); - } else { - if (sip) - write_unlock(&sip->macc_lck); - else - write_unlock(&sdeb_fake_rw_lck); - } -} - static int resp_read_dt0(struct scsi_cmnd *scp, struct sdebug_dev_info *devip) { bool check_prot; @@ -3673,6 +3883,7 @@ static int resp_read_dt0(struct scsi_cmnd *scp, struct sdebug_dev_info *devip) u64 lba; struct sdeb_store_info *sip = devip2sip(devip, true); u8 *cmd = scp->cmnd; + bool meta_data_locked = false; switch (cmd[0]) { case READ_16: @@ -3731,6 +3942,10 @@ static int resp_read_dt0(struct scsi_cmnd *scp, struct sdebug_dev_info *devip) atomic_set(&sdeb_inject_pending, 0); } + /* + * When checking device access params, for reads we only check data + * versus what is set at init time, so no need to lock. + */ ret = check_device_access_params(scp, lba, num, false); if (ret) return ret; @@ -3750,29 +3965,33 @@ static int resp_read_dt0(struct scsi_cmnd *scp, struct sdebug_dev_info *devip) return check_condition_result; } - sdeb_read_lock(sip); + if (sdebug_dev_is_zoned(devip) || + (sdebug_dix && scsi_prot_sg_count(scp))) { + sdeb_meta_read_lock(sip); + meta_data_locked = true; + } /* DIX + T10 DIF */ if (unlikely(sdebug_dix && scsi_prot_sg_count(scp))) { switch (prot_verify_read(scp, lba, num, ei_lba)) { case 1: /* Guard tag error */ if (cmd[1] >> 5 != 3) { /* RDPROTECT != 3 */ - sdeb_read_unlock(sip); + sdeb_meta_read_unlock(sip); mk_sense_buffer(scp, ABORTED_COMMAND, 0x10, 1); return check_condition_result; } else if (scp->prot_flags & SCSI_PROT_GUARD_CHECK) { - sdeb_read_unlock(sip); + sdeb_meta_read_unlock(sip); mk_sense_buffer(scp, ILLEGAL_REQUEST, 0x10, 1); return illegal_condition_result; } break; case 3: /* Reference tag error */ if (cmd[1] >> 5 != 3) { /* RDPROTECT != 3 */ - sdeb_read_unlock(sip); + sdeb_meta_read_unlock(sip); mk_sense_buffer(scp, ABORTED_COMMAND, 0x10, 3); return check_condition_result; } else if (scp->prot_flags & SCSI_PROT_REF_CHECK) { - sdeb_read_unlock(sip); + sdeb_meta_read_unlock(sip); mk_sense_buffer(scp, ILLEGAL_REQUEST, 0x10, 3); return illegal_condition_result; } @@ -3780,8 +3999,9 @@ static int resp_read_dt0(struct scsi_cmnd *scp, struct sdebug_dev_info *devip) } } - ret = do_device_access(sip, scp, 0, lba, num, false, 0); - sdeb_read_unlock(sip); + ret = do_device_access(sip, scp, 0, lba, num, 0, false, false); + if (meta_data_locked) + sdeb_meta_read_unlock(sip); if (unlikely(ret == -1)) return DID_ERROR << 16; @@ -3971,6 +4191,7 @@ static int resp_write_dt0(struct scsi_cmnd *scp, struct sdebug_dev_info *devip) u64 lba; struct sdeb_store_info *sip = devip2sip(devip, true); u8 *cmd = scp->cmnd; + bool meta_data_locked = false; switch (cmd[0]) { case WRITE_16: @@ -4029,10 +4250,17 @@ static int resp_write_dt0(struct scsi_cmnd *scp, struct sdebug_dev_info *devip) "to DIF device\n"); } - sdeb_write_lock(sip); + if (sdebug_dev_is_zoned(devip) || + (sdebug_dix && scsi_prot_sg_count(scp)) || + scsi_debug_lbp()) { + sdeb_meta_write_lock(sip); + meta_data_locked = true; + } + ret = check_device_access_params(scp, lba, num, true); if (ret) { - sdeb_write_unlock(sip); + if (meta_data_locked) + sdeb_meta_write_unlock(sip); return ret; } @@ -4041,22 +4269,22 @@ static int resp_write_dt0(struct scsi_cmnd *scp, struct sdebug_dev_info *devip) switch (prot_verify_write(scp, lba, num, ei_lba)) { case 1: /* Guard tag error */ if (scp->prot_flags & SCSI_PROT_GUARD_CHECK) { - sdeb_write_unlock(sip); + sdeb_meta_write_unlock(sip); mk_sense_buffer(scp, ILLEGAL_REQUEST, 0x10, 1); return illegal_condition_result; } else if (scp->cmnd[1] >> 5 != 3) { /* WRPROTECT != 3 */ - sdeb_write_unlock(sip); + sdeb_meta_write_unlock(sip); mk_sense_buffer(scp, ABORTED_COMMAND, 0x10, 1); return check_condition_result; } break; case 3: /* Reference tag error */ if (scp->prot_flags & SCSI_PROT_REF_CHECK) { - sdeb_write_unlock(sip); + sdeb_meta_write_unlock(sip); mk_sense_buffer(scp, ILLEGAL_REQUEST, 0x10, 3); return illegal_condition_result; } else if (scp->cmnd[1] >> 5 != 3) { /* WRPROTECT != 3 */ - sdeb_write_unlock(sip); + sdeb_meta_write_unlock(sip); mk_sense_buffer(scp, ABORTED_COMMAND, 0x10, 3); return check_condition_result; } @@ -4064,13 +4292,16 @@ static int resp_write_dt0(struct scsi_cmnd *scp, struct sdebug_dev_info *devip) } } - ret = do_device_access(sip, scp, 0, lba, num, true, group); + ret = do_device_access(sip, scp, 0, lba, num, group, true, false); if (unlikely(scsi_debug_lbp())) map_region(sip, lba, num); + /* If ZBC zone then bump its write pointer */ if (sdebug_dev_is_zoned(devip)) zbc_inc_wp(devip, lba, num); - sdeb_write_unlock(sip); + if (meta_data_locked) + sdeb_meta_write_unlock(sip); + if (unlikely(-1 == ret)) return DID_ERROR << 16; else if (unlikely(sdebug_verbose && @@ -4180,7 +4411,8 @@ static int resp_write_scat(struct scsi_cmnd *scp, goto err_out; } - sdeb_write_lock(sip); + /* Just keep it simple and always lock for now */ + sdeb_meta_write_lock(sip); sg_off = lbdof_blen; /* Spec says Buffer xfer Length field in number of LBs in dout */ cum_lb = 0; @@ -4223,7 +4455,11 @@ static int resp_write_scat(struct scsi_cmnd *scp, } } - ret = do_device_access(sip, scp, sg_off, lba, num, true, group); + /* + * Write ranges atomically to keep as close to pre-atomic + * writes behaviour as possible. + */ + ret = do_device_access(sip, scp, sg_off, lba, num, group, true, true); /* If ZBC zone then bump its write pointer */ if (sdebug_dev_is_zoned(devip)) zbc_inc_wp(devip, lba, num); @@ -4262,7 +4498,7 @@ static int resp_write_scat(struct scsi_cmnd *scp, } ret = 0; err_out_unlock: - sdeb_write_unlock(sip); + sdeb_meta_write_unlock(sip); err_out: kfree(lrdp); return ret; @@ -4281,14 +4517,16 @@ static int resp_write_same(struct scsi_cmnd *scp, u64 lba, u32 num, scp->device->hostdata, true); u8 *fs1p; u8 *fsp; + bool meta_data_locked = false; - sdeb_write_lock(sip); + if (sdebug_dev_is_zoned(devip) || scsi_debug_lbp()) { + sdeb_meta_write_lock(sip); + meta_data_locked = true; + } ret = check_device_access_params(scp, lba, num, true); - if (ret) { - sdeb_write_unlock(sip); - return ret; - } + if (ret) + goto out; if (unmap && scsi_debug_lbp()) { unmap_region(sip, lba, num); @@ -4299,6 +4537,7 @@ static int resp_write_same(struct scsi_cmnd *scp, u64 lba, u32 num, /* if ndob then zero 1 logical block, else fetch 1 logical block */ fsp = sip->storep; fs1p = fsp + (block * lb_size); + sdeb_data_write_lock(sip); if (ndob) { memset(fs1p, 0, lb_size); ret = 0; @@ -4306,8 +4545,8 @@ static int resp_write_same(struct scsi_cmnd *scp, u64 lba, u32 num, ret = fetch_to_dev_buffer(scp, fs1p, lb_size); if (-1 == ret) { - sdeb_write_unlock(sip); - return DID_ERROR << 16; + ret = DID_ERROR << 16; + goto out; } else if (sdebug_verbose && !ndob && (ret < lb_size)) sdev_printk(KERN_INFO, scp->device, "%s: %s: lb size=%u, IO sent=%d bytes\n", @@ -4324,10 +4563,12 @@ static int resp_write_same(struct scsi_cmnd *scp, u64 lba, u32 num, /* If ZBC zone then bump its write pointer */ if (sdebug_dev_is_zoned(devip)) zbc_inc_wp(devip, lba, num); + sdeb_data_write_unlock(sip); + ret = 0; out: - sdeb_write_unlock(sip); - - return 0; + if (meta_data_locked) + sdeb_meta_write_unlock(sip); + return ret; } static int resp_write_same_10(struct scsi_cmnd *scp, @@ -4470,25 +4711,30 @@ static int resp_comp_write(struct scsi_cmnd *scp, return check_condition_result; } - sdeb_write_lock(sip); - ret = do_dout_fetch(scp, dnum, arr); if (ret == -1) { retval = DID_ERROR << 16; - goto cleanup; + goto cleanup_free; } else if (sdebug_verbose && (ret < (dnum * lb_size))) sdev_printk(KERN_INFO, scp->device, "%s: compare_write: cdb " "indicated=%u, IO sent=%d bytes\n", my_name, dnum * lb_size, ret); + + sdeb_data_write_lock(sip); + sdeb_meta_write_lock(sip); if (!comp_write_worker(sip, lba, num, arr, false)) { mk_sense_buffer(scp, MISCOMPARE, MISCOMPARE_VERIFY_ASC, 0); retval = check_condition_result; - goto cleanup; + goto cleanup_unlock; } + + /* Cover sip->map_storep (which map_region()) sets with data lock */ if (scsi_debug_lbp()) map_region(sip, lba, num); -cleanup: - sdeb_write_unlock(sip); +cleanup_unlock: + sdeb_meta_write_unlock(sip); + sdeb_data_write_unlock(sip); +cleanup_free: kfree(arr); return retval; } @@ -4532,7 +4778,7 @@ static int resp_unmap(struct scsi_cmnd *scp, struct sdebug_dev_info *devip) desc = (void *)&buf[8]; - sdeb_write_lock(sip); + sdeb_meta_write_lock(sip); for (i = 0 ; i < descriptors ; i++) { unsigned long long lba = get_unaligned_be64(&desc[i].lba); @@ -4548,7 +4794,7 @@ static int resp_unmap(struct scsi_cmnd *scp, struct sdebug_dev_info *devip) ret = 0; out: - sdeb_write_unlock(sip); + sdeb_meta_write_unlock(sip); kfree(buf); return ret; @@ -4706,12 +4952,13 @@ static int resp_pre_fetch(struct scsi_cmnd *scp, rest = block + nblks - sdebug_store_sectors; /* Try to bring the PRE-FETCH range into CPU's cache */ - sdeb_read_lock(sip); + sdeb_data_read_lock(sip); prefetch_range(fsp + (sdebug_sector_size * block), (nblks - rest) * sdebug_sector_size); if (rest) prefetch_range(fsp, rest * sdebug_sector_size); - sdeb_read_unlock(sip); + + sdeb_data_read_unlock(sip); fini: if (cmd[1] & 0x2) res = SDEG_RES_IMMED_MASK; @@ -4870,7 +5117,7 @@ static int resp_verify(struct scsi_cmnd *scp, struct sdebug_dev_info *devip) return check_condition_result; } /* Not changing store, so only need read access */ - sdeb_read_lock(sip); + sdeb_data_read_lock(sip); ret = do_dout_fetch(scp, a_num, arr); if (ret == -1) { @@ -4892,7 +5139,7 @@ static int resp_verify(struct scsi_cmnd *scp, struct sdebug_dev_info *devip) goto cleanup; } cleanup: - sdeb_read_unlock(sip); + sdeb_data_read_unlock(sip); kfree(arr); return ret; } @@ -4938,7 +5185,7 @@ static int resp_report_zones(struct scsi_cmnd *scp, return check_condition_result; } - sdeb_read_lock(sip); + sdeb_meta_read_lock(sip); desc = arr + 64; for (lba = zs_lba; lba < sdebug_capacity; @@ -5036,11 +5283,70 @@ static int resp_report_zones(struct scsi_cmnd *scp, ret = fill_from_dev_buffer(scp, arr, min_t(u32, alloc_len, rep_len)); fini: - sdeb_read_unlock(sip); + sdeb_meta_read_unlock(sip); kfree(arr); return ret; } +static int resp_atomic_write(struct scsi_cmnd *scp, + struct sdebug_dev_info *devip) +{ + struct sdeb_store_info *sip; + u8 *cmd = scp->cmnd; + u16 boundary, len; + u64 lba, lba_tmp; + int ret; + + if (!scsi_debug_atomic_write()) { + mk_sense_invalid_opcode(scp); + return check_condition_result; + } + + sip = devip2sip(devip, true); + + lba = get_unaligned_be64(cmd + 2); + boundary = get_unaligned_be16(cmd + 10); + len = get_unaligned_be16(cmd + 12); + + lba_tmp = lba; + if (sdebug_atomic_wr_align && + do_div(lba_tmp, sdebug_atomic_wr_align)) { + /* Does not meet alignment requirement */ + mk_sense_buffer(scp, ILLEGAL_REQUEST, INVALID_FIELD_IN_CDB, 0); + return check_condition_result; + } + + if (sdebug_atomic_wr_gran && len % sdebug_atomic_wr_gran) { + /* Does not meet alignment requirement */ + mk_sense_buffer(scp, ILLEGAL_REQUEST, INVALID_FIELD_IN_CDB, 0); + return check_condition_result; + } + + if (boundary > 0) { + if (boundary > sdebug_atomic_wr_max_bndry) { + mk_sense_invalid_fld(scp, SDEB_IN_CDB, 12, -1); + return check_condition_result; + } + + if (len > sdebug_atomic_wr_max_length_bndry) { + mk_sense_invalid_fld(scp, SDEB_IN_CDB, 12, -1); + return check_condition_result; + } + } else { + if (len > sdebug_atomic_wr_max_length) { + mk_sense_invalid_fld(scp, SDEB_IN_CDB, 12, -1); + return check_condition_result; + } + } + + ret = do_device_access(sip, scp, 0, lba, len, 0, true, true); + if (unlikely(ret == -1)) + return DID_ERROR << 16; + if (unlikely(ret != len * sdebug_sector_size)) + return DID_ERROR << 16; + return 0; +} + /* Logic transplanted from tcmu-runner, file_zbc.c */ static void zbc_open_all(struct sdebug_dev_info *devip) { @@ -5067,8 +5373,7 @@ static int resp_open_zone(struct scsi_cmnd *scp, struct sdebug_dev_info *devip) mk_sense_invalid_opcode(scp); return check_condition_result; } - - sdeb_write_lock(sip); + sdeb_meta_write_lock(sip); if (all) { /* Check if all closed zones can be open */ @@ -5117,7 +5422,7 @@ static int resp_open_zone(struct scsi_cmnd *scp, struct sdebug_dev_info *devip) zbc_open_zone(devip, zsp, true); fini: - sdeb_write_unlock(sip); + sdeb_meta_write_unlock(sip); return res; } @@ -5144,7 +5449,7 @@ static int resp_close_zone(struct scsi_cmnd *scp, return check_condition_result; } - sdeb_write_lock(sip); + sdeb_meta_write_lock(sip); if (all) { zbc_close_all(devip); @@ -5173,7 +5478,7 @@ static int resp_close_zone(struct scsi_cmnd *scp, zbc_close_zone(devip, zsp); fini: - sdeb_write_unlock(sip); + sdeb_meta_write_unlock(sip); return res; } @@ -5216,7 +5521,7 @@ static int resp_finish_zone(struct scsi_cmnd *scp, return check_condition_result; } - sdeb_write_lock(sip); + sdeb_meta_write_lock(sip); if (all) { zbc_finish_all(devip); @@ -5245,7 +5550,7 @@ static int resp_finish_zone(struct scsi_cmnd *scp, zbc_finish_zone(devip, zsp, true); fini: - sdeb_write_unlock(sip); + sdeb_meta_write_unlock(sip); return res; } @@ -5296,7 +5601,7 @@ static int resp_rwp_zone(struct scsi_cmnd *scp, struct sdebug_dev_info *devip) return check_condition_result; } - sdeb_write_lock(sip); + sdeb_meta_write_lock(sip); if (all) { zbc_rwp_all(devip); @@ -5324,7 +5629,7 @@ static int resp_rwp_zone(struct scsi_cmnd *scp, struct sdebug_dev_info *devip) zbc_rwp_zone(devip, zsp); fini: - sdeb_write_unlock(sip); + sdeb_meta_write_unlock(sip); return res; } @@ -6288,6 +6593,7 @@ module_param_named(lbprz, sdebug_lbprz, int, S_IRUGO); module_param_named(lbpu, sdebug_lbpu, int, S_IRUGO); module_param_named(lbpws, sdebug_lbpws, int, S_IRUGO); module_param_named(lbpws10, sdebug_lbpws10, int, S_IRUGO); +module_param_named(atomic_wr, sdebug_atomic_wr, int, S_IRUGO); module_param_named(lowest_aligned, sdebug_lowest_aligned, int, S_IRUGO); module_param_named(lun_format, sdebug_lun_am_i, int, S_IRUGO | S_IWUSR); module_param_named(max_luns, sdebug_max_luns, int, S_IRUGO | S_IWUSR); @@ -6322,6 +6628,11 @@ module_param_named(unmap_alignment, sdebug_unmap_alignment, int, S_IRUGO); module_param_named(unmap_granularity, sdebug_unmap_granularity, int, S_IRUGO); module_param_named(unmap_max_blocks, sdebug_unmap_max_blocks, int, S_IRUGO); module_param_named(unmap_max_desc, sdebug_unmap_max_desc, int, S_IRUGO); +module_param_named(atomic_wr_max_length, sdebug_atomic_wr_max_length, int, S_IRUGO); +module_param_named(atomic_wr_align, sdebug_atomic_wr_align, int, S_IRUGO); +module_param_named(atomic_wr_gran, sdebug_atomic_wr_gran, int, S_IRUGO); +module_param_named(atomic_wr_max_length_bndry, sdebug_atomic_wr_max_length_bndry, int, S_IRUGO); +module_param_named(atomic_wr_max_bndry, sdebug_atomic_wr_max_bndry, int, S_IRUGO); module_param_named(uuid_ctl, sdebug_uuid_ctl, int, S_IRUGO); module_param_named(virtual_gb, sdebug_virtual_gb, int, S_IRUGO | S_IWUSR); module_param_named(vpd_use_hostno, sdebug_vpd_use_hostno, int, @@ -6365,6 +6676,7 @@ MODULE_PARM_DESC(lbprz, MODULE_PARM_DESC(lbpu, "enable LBP, support UNMAP command (def=0)"); MODULE_PARM_DESC(lbpws, "enable LBP, support WRITE SAME(16) with UNMAP bit (def=0)"); MODULE_PARM_DESC(lbpws10, "enable LBP, support WRITE SAME(10) with UNMAP bit (def=0)"); +MODULE_PARM_DESC(atomic_write, "enable ATOMIC WRITE support, support WRITE ATOMIC(16) (def=0)"); MODULE_PARM_DESC(lowest_aligned, "lowest aligned lba (def=0)"); MODULE_PARM_DESC(lun_format, "LUN format: 0->peripheral (def); 1 --> flat address method"); MODULE_PARM_DESC(max_luns, "number of LUNs per target to simulate(def=1)"); @@ -6396,6 +6708,11 @@ MODULE_PARM_DESC(unmap_alignment, "lowest aligned thin provisioning lba (def=0)" MODULE_PARM_DESC(unmap_granularity, "thin provisioning granularity in blocks (def=1)"); MODULE_PARM_DESC(unmap_max_blocks, "max # of blocks can be unmapped in one cmd (def=0xffffffff)"); MODULE_PARM_DESC(unmap_max_desc, "max # of ranges that can be unmapped in one cmd (def=256)"); +MODULE_PARM_DESC(atomic_wr_max_length, "max # of blocks can be atomically written in one cmd (def=8192)"); +MODULE_PARM_DESC(atomic_wr_align, "minimum alignment of atomic write in blocks (def=2)"); +MODULE_PARM_DESC(atomic_wr_gran, "minimum granularity of atomic write in blocks (def=2)"); +MODULE_PARM_DESC(atomic_wr_max_length_bndry, "max # of blocks can be atomically written in one cmd with boundary set (def=8192)"); +MODULE_PARM_DESC(atomic_wr_max_bndry, "max # boundaries per atomic write (def=128)"); MODULE_PARM_DESC(uuid_ctl, "1->use uuid for lu name, 0->don't, 2->all use same (def=0)"); MODULE_PARM_DESC(virtual_gb, "virtual gigabyte (GiB) size (def=0 -> use dev_size_mb)"); @@ -7567,6 +7884,7 @@ static int __init scsi_debug_init(void) return -EINVAL; } } + xa_init_flags(per_store_ap, XA_FLAGS_ALLOC | XA_FLAGS_LOCK_IRQ); if (want_store) { idx = sdebug_add_store(); @@ -7774,7 +8092,9 @@ static int sdebug_add_store(void) map_region(sip, 0, 2); } - rwlock_init(&sip->macc_lck); + rwlock_init(&sip->macc_data_lck); + rwlock_init(&sip->macc_meta_lck); + rwlock_init(&sip->macc_sector_lck); return (int)n_idx; err: sdebug_erase_store((int)n_idx, sip); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index ec39acc986d6..3958a6d14bf4 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -631,8 +631,7 @@ static bool scsi_end_request(struct request *req, blk_status_t error, if (blk_update_request(req, error, bytes)) return true; - // XXX: - if (blk_queue_add_random(q)) + if (q->limits.features & BLK_FEAT_ADD_RANDOM) add_disk_randomness(req->q->disk); WARN_ON_ONCE(!blk_rq_is_passthrough(req) && @@ -1140,9 +1139,9 @@ blk_status_t scsi_alloc_sgtables(struct scsi_cmnd *cmd) */ count = __blk_rq_map_sg(rq->q, rq, cmd->sdb.table.sgl, &last_sg); - if (blk_rq_bytes(rq) & rq->q->dma_pad_mask) { + if (blk_rq_bytes(rq) & rq->q->limits.dma_pad_mask) { unsigned int pad_len = - (rq->q->dma_pad_mask & ~blk_rq_bytes(rq)) + 1; + (rq->q->limits.dma_pad_mask & ~blk_rq_bytes(rq)) + 1; last_sg->length += pad_len; cmd->extra_len += pad_len; @@ -1987,7 +1986,7 @@ void scsi_init_limits(struct Scsi_Host *shost, struct queue_limits *lim) shost->dma_alignment, dma_get_cache_alignment() - 1); if (shost->no_highmem) - lim->bounce = BLK_BOUNCE_HIGH; + lim->features |= BLK_FEAT_BOUNCE_HIGH; dma_set_seg_boundary(dev, shost->dma_boundary); dma_set_max_seg_size(dev, shost->max_segment_size); diff --git a/drivers/scsi/scsi_trace.c b/drivers/scsi/scsi_trace.c index 41a950075913..3e47c4472a80 100644 --- a/drivers/scsi/scsi_trace.c +++ b/drivers/scsi/scsi_trace.c @@ -325,6 +325,26 @@ out: return ret; } +static const char * +scsi_trace_atomic_write16_out(struct trace_seq *p, unsigned char *cdb, int len) +{ + const char *ret = trace_seq_buffer_ptr(p); + unsigned int boundary_size; + unsigned int nr_blocks; + sector_t lba; + + lba = get_unaligned_be64(&cdb[2]); + boundary_size = get_unaligned_be16(&cdb[10]); + nr_blocks = get_unaligned_be16(&cdb[12]); + + trace_seq_printf(p, "lba=%llu txlen=%u boundary_size=%u", + lba, nr_blocks, boundary_size); + + trace_seq_putc(p, 0); + + return ret; +} + static const char * scsi_trace_varlen(struct trace_seq *p, unsigned char *cdb, int len) { @@ -385,6 +405,8 @@ scsi_trace_parse_cdb(struct trace_seq *p, unsigned char *cdb, int len) return scsi_trace_zbc_in(p, cdb, len); case ZBC_OUT: return scsi_trace_zbc_out(p, cdb, len); + case WRITE_ATOMIC_16: + return scsi_trace_atomic_write16_out(p, cdb, len); default: return scsi_trace_misc(p, cdb, len); } diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 1b7561abe05d..2e933fd1de70 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -102,12 +102,13 @@ MODULE_ALIAS_SCSI_DEVICE(TYPE_ZBC); #define SD_MINORS 16 -static void sd_config_discard(struct scsi_disk *, unsigned int); -static void sd_config_write_same(struct scsi_disk *); +static void sd_config_discard(struct scsi_disk *sdkp, struct queue_limits *lim, + unsigned int mode); +static void sd_config_write_same(struct scsi_disk *sdkp, + struct queue_limits *lim); static int sd_revalidate_disk(struct gendisk *); static void sd_unlock_native_capacity(struct gendisk *disk); static void sd_shutdown(struct device *); -static void sd_read_capacity(struct scsi_disk *sdkp, unsigned char *buffer); static void scsi_disk_release(struct device *cdev); static DEFINE_IDA(sd_index_ida); @@ -120,17 +121,18 @@ static const char *sd_cache_types[] = { "write back, no read (daft)" }; -static void sd_set_flush_flag(struct scsi_disk *sdkp) +static void sd_set_flush_flag(struct scsi_disk *sdkp, + struct queue_limits *lim) { - bool wc = false, fua = false; - if (sdkp->WCE) { - wc = true; + lim->features |= BLK_FEAT_WRITE_CACHE; if (sdkp->DPOFUA) - fua = true; + lim->features |= BLK_FEAT_FUA; + else + lim->features &= ~BLK_FEAT_FUA; + } else { + lim->features &= ~(BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA); } - - blk_queue_write_cache(sdkp->disk->queue, wc, fua); } static ssize_t @@ -168,9 +170,18 @@ cache_type_store(struct device *dev, struct device_attribute *attr, wce = (ct & 0x02) && !sdkp->write_prot ? 1 : 0; if (sdkp->cache_override) { + struct queue_limits lim; + sdkp->WCE = wce; sdkp->RCD = rcd; - sd_set_flush_flag(sdkp); + + lim = queue_limits_start_update(sdkp->disk->queue); + sd_set_flush_flag(sdkp, &lim); + blk_mq_freeze_queue(sdkp->disk->queue); + ret = queue_limits_commit_update(sdkp->disk->queue, &lim); + blk_mq_unfreeze_queue(sdkp->disk->queue); + if (ret) + return ret; return count; } @@ -457,16 +468,12 @@ provisioning_mode_store(struct device *dev, struct device_attribute *attr, { struct scsi_disk *sdkp = to_scsi_disk(dev); struct scsi_device *sdp = sdkp->device; - int mode; + struct queue_limits lim; + int mode, err; if (!capable(CAP_SYS_ADMIN)) return -EACCES; - if (sd_is_zoned(sdkp)) { - sd_config_discard(sdkp, SD_LBP_DISABLE); - return count; - } - if (sdp->type != TYPE_DISK) return -EINVAL; @@ -474,8 +481,13 @@ provisioning_mode_store(struct device *dev, struct device_attribute *attr, if (mode < 0) return -EINVAL; - sd_config_discard(sdkp, mode); - + lim = queue_limits_start_update(sdkp->disk->queue); + sd_config_discard(sdkp, &lim, mode); + blk_mq_freeze_queue(sdkp->disk->queue); + err = queue_limits_commit_update(sdkp->disk->queue, &lim); + blk_mq_unfreeze_queue(sdkp->disk->queue); + if (err) + return err; return count; } static DEVICE_ATTR_RW(provisioning_mode); @@ -558,6 +570,7 @@ max_write_same_blocks_store(struct device *dev, struct device_attribute *attr, { struct scsi_disk *sdkp = to_scsi_disk(dev); struct scsi_device *sdp = sdkp->device; + struct queue_limits lim; unsigned long max; int err; @@ -579,8 +592,13 @@ max_write_same_blocks_store(struct device *dev, struct device_attribute *attr, sdkp->max_ws_blocks = max; } - sd_config_write_same(sdkp); - + lim = queue_limits_start_update(sdkp->disk->queue); + sd_config_write_same(sdkp, &lim); + blk_mq_freeze_queue(sdkp->disk->queue); + err = queue_limits_commit_update(sdkp->disk->queue, &lim); + blk_mq_unfreeze_queue(sdkp->disk->queue); + if (err) + return err; return count; } static DEVICE_ATTR_RW(max_write_same_blocks); @@ -823,25 +841,28 @@ static unsigned char sd_setup_protect_cmnd(struct scsi_cmnd *scmd, return protect; } -static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode) +static void sd_disable_discard(struct scsi_disk *sdkp) +{ + sdkp->provisioning_mode = SD_LBP_DISABLE; + blk_queue_disable_discard(sdkp->disk->queue); +} + +static void sd_config_discard(struct scsi_disk *sdkp, struct queue_limits *lim, + unsigned int mode) { - struct request_queue *q = sdkp->disk->queue; unsigned int logical_block_size = sdkp->device->sector_size; unsigned int max_blocks = 0; - q->limits.discard_alignment = - sdkp->unmap_alignment * logical_block_size; - q->limits.discard_granularity = - max(sdkp->physical_block_size, - sdkp->unmap_granularity * logical_block_size); + lim->discard_alignment = sdkp->unmap_alignment * logical_block_size; + lim->discard_granularity = max(sdkp->physical_block_size, + sdkp->unmap_granularity * logical_block_size); sdkp->provisioning_mode = mode; switch (mode) { case SD_LBP_FULL: case SD_LBP_DISABLE: - blk_queue_max_discard_sectors(q, 0); - return; + break; case SD_LBP_UNMAP: max_blocks = min_not_zero(sdkp->max_unmap_blocks, @@ -872,7 +893,8 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode) break; } - blk_queue_max_discard_sectors(q, max_blocks * (logical_block_size >> 9)); + lim->max_hw_discard_sectors = max_blocks * + (logical_block_size >> SECTOR_SHIFT); } static void *sd_set_special_bvec(struct request *rq, unsigned int data_len) @@ -918,6 +940,64 @@ static blk_status_t sd_setup_unmap_cmnd(struct scsi_cmnd *cmd) return scsi_alloc_sgtables(cmd); } +static void sd_config_atomic(struct scsi_disk *sdkp, struct queue_limits *lim) +{ + unsigned int logical_block_size = sdkp->device->sector_size, + physical_block_size_sectors, max_atomic, unit_min, unit_max; + + if ((!sdkp->max_atomic && !sdkp->max_atomic_with_boundary) || + sdkp->protection_type == T10_PI_TYPE2_PROTECTION) + return; + + physical_block_size_sectors = sdkp->physical_block_size / + sdkp->device->sector_size; + + unit_min = rounddown_pow_of_two(sdkp->atomic_granularity ? + sdkp->atomic_granularity : + physical_block_size_sectors); + + /* + * Only use atomic boundary when we have the odd scenario of + * sdkp->max_atomic == 0, which the spec does permit. + */ + if (sdkp->max_atomic) { + max_atomic = sdkp->max_atomic; + unit_max = rounddown_pow_of_two(sdkp->max_atomic); + sdkp->use_atomic_write_boundary = 0; + } else { + max_atomic = sdkp->max_atomic_with_boundary; + unit_max = rounddown_pow_of_two(sdkp->max_atomic_boundary); + sdkp->use_atomic_write_boundary = 1; + } + + /* + * Ensure compliance with granularity and alignment. For now, keep it + * simple and just don't support atomic writes for values mismatched + * with max_{boundary}atomic, physical block size, and + * atomic_granularity itself. + * + * We're really being distrustful by checking unit_max also... + */ + if (sdkp->atomic_granularity > 1) { + if (unit_min > 1 && unit_min % sdkp->atomic_granularity) + return; + if (unit_max > 1 && unit_max % sdkp->atomic_granularity) + return; + } + + if (sdkp->atomic_alignment > 1) { + if (unit_min > 1 && unit_min % sdkp->atomic_alignment) + return; + if (unit_max > 1 && unit_max % sdkp->atomic_alignment) + return; + } + + lim->atomic_write_hw_max = max_atomic * logical_block_size; + lim->atomic_write_hw_boundary = 0; + lim->atomic_write_hw_unit_min = unit_min * logical_block_size; + lim->atomic_write_hw_unit_max = unit_max * logical_block_size; +} + static blk_status_t sd_setup_write_same16_cmnd(struct scsi_cmnd *cmd, bool unmap) { @@ -1000,9 +1080,16 @@ static blk_status_t sd_setup_write_zeroes_cmnd(struct scsi_cmnd *cmd) return sd_setup_write_same10_cmnd(cmd, false); } -static void sd_config_write_same(struct scsi_disk *sdkp) +static void sd_disable_write_same(struct scsi_disk *sdkp) +{ + sdkp->device->no_write_same = 1; + sdkp->max_ws_blocks = 0; + blk_queue_disable_write_zeroes(sdkp->disk->queue); +} + +static void sd_config_write_same(struct scsi_disk *sdkp, + struct queue_limits *lim) { - struct request_queue *q = sdkp->disk->queue; unsigned int logical_block_size = sdkp->device->sector_size; if (sdkp->device->no_write_same) { @@ -1056,8 +1143,8 @@ static void sd_config_write_same(struct scsi_disk *sdkp) } out: - blk_queue_max_write_zeroes_sectors(q, sdkp->max_ws_blocks * - (logical_block_size >> 9)); + lim->max_write_zeroes_sectors = + sdkp->max_ws_blocks * (logical_block_size >> SECTOR_SHIFT); } static blk_status_t sd_setup_flush_cmnd(struct scsi_cmnd *cmd) @@ -1209,6 +1296,26 @@ static int sd_cdl_dld(struct scsi_disk *sdkp, struct scsi_cmnd *scmd) return (hint - IOPRIO_HINT_DEV_DURATION_LIMIT_1) + 1; } +static blk_status_t sd_setup_atomic_cmnd(struct scsi_cmnd *cmd, + sector_t lba, unsigned int nr_blocks, + bool boundary, unsigned char flags) +{ + cmd->cmd_len = 16; + cmd->cmnd[0] = WRITE_ATOMIC_16; + cmd->cmnd[1] = flags; + put_unaligned_be64(lba, &cmd->cmnd[2]); + put_unaligned_be16(nr_blocks, &cmd->cmnd[12]); + if (boundary) + put_unaligned_be16(nr_blocks, &cmd->cmnd[10]); + else + put_unaligned_be16(0, &cmd->cmnd[10]); + put_unaligned_be16(nr_blocks, &cmd->cmnd[12]); + cmd->cmnd[14] = 0; + cmd->cmnd[15] = 0; + + return BLK_STS_OK; +} + static blk_status_t sd_setup_read_write_cmnd(struct scsi_cmnd *cmd) { struct request *rq = scsi_cmd_to_rq(cmd); @@ -1274,6 +1381,10 @@ static blk_status_t sd_setup_read_write_cmnd(struct scsi_cmnd *cmd) if (protect && sdkp->protection_type == T10_PI_TYPE2_PROTECTION) { ret = sd_setup_rw32_cmnd(cmd, write, lba, nr_blocks, protect | fua, dld); + } else if (rq->cmd_flags & REQ_ATOMIC && write) { + ret = sd_setup_atomic_cmnd(cmd, lba, nr_blocks, + sdkp->use_atomic_write_boundary, + protect | fua); } else if (sdp->use_16_for_rw || (nr_blocks > 0xffff)) { ret = sd_setup_rw16_cmnd(cmd, write, lba, nr_blocks, protect | fua, dld); @@ -2247,15 +2358,14 @@ static int sd_done(struct scsi_cmnd *SCpnt) case 0x24: /* INVALID FIELD IN CDB */ switch (SCpnt->cmnd[0]) { case UNMAP: - sd_config_discard(sdkp, SD_LBP_DISABLE); + sd_disable_discard(sdkp); break; case WRITE_SAME_16: case WRITE_SAME: if (SCpnt->cmnd[1] & 8) { /* UNMAP */ - sd_config_discard(sdkp, SD_LBP_DISABLE); + sd_disable_discard(sdkp); } else { - sdkp->device->no_write_same = 1; - sd_config_write_same(sdkp); + sd_disable_write_same(sdkp); req->rq_flags |= RQF_QUIET; } break; @@ -2267,7 +2377,7 @@ static int sd_done(struct scsi_cmnd *SCpnt) } out: - if (sd_is_zoned(sdkp)) + if (sdkp->device->type == TYPE_ZBC) good_bytes = sd_zbc_complete(SCpnt, good_bytes, &sshdr); SCSI_LOG_HLCOMPLETE(1, scmd_printk(KERN_INFO, SCpnt, @@ -2461,11 +2571,13 @@ static int sd_read_protection_type(struct scsi_disk *sdkp, unsigned char *buffer return 0; } -static void sd_config_protection(struct scsi_disk *sdkp) +static void sd_config_protection(struct scsi_disk *sdkp, + struct queue_limits *lim) { struct scsi_device *sdp = sdkp->device; - sd_dif_config_host(sdkp); + if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY)) + sd_dif_config_host(sdkp, lim); if (!sdkp->protection_type) return; @@ -2514,7 +2626,7 @@ static void read_capacity_error(struct scsi_disk *sdkp, struct scsi_device *sdp, #define READ_CAPACITY_RETRIES_ON_RESET 10 static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp, - unsigned char *buffer) + struct queue_limits *lim, unsigned char *buffer) { unsigned char cmd[16]; struct scsi_sense_hdr sshdr; @@ -2588,7 +2700,7 @@ static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp, /* Lowest aligned logical block */ alignment = ((buffer[14] & 0x3f) << 8 | buffer[15]) * sector_size; - blk_queue_alignment_offset(sdp->request_queue, alignment); + lim->alignment_offset = alignment; if (alignment && sdkp->first_scan) sd_printk(KERN_NOTICE, sdkp, "physical block alignment offset: %u\n", alignment); @@ -2599,7 +2711,7 @@ static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp, if (buffer[14] & 0x40) /* LBPRZ */ sdkp->lbprz = 1; - sd_config_discard(sdkp, SD_LBP_WS16); + sd_config_discard(sdkp, lim, SD_LBP_WS16); } sdkp->capacity = lba + 1; @@ -2702,13 +2814,14 @@ static int sd_try_rc16_first(struct scsi_device *sdp) * read disk capacity */ static void -sd_read_capacity(struct scsi_disk *sdkp, unsigned char *buffer) +sd_read_capacity(struct scsi_disk *sdkp, struct queue_limits *lim, + unsigned char *buffer) { int sector_size; struct scsi_device *sdp = sdkp->device; if (sd_try_rc16_first(sdp)) { - sector_size = read_capacity_16(sdkp, sdp, buffer); + sector_size = read_capacity_16(sdkp, sdp, lim, buffer); if (sector_size == -EOVERFLOW) goto got_data; if (sector_size == -ENODEV) @@ -2728,7 +2841,7 @@ sd_read_capacity(struct scsi_disk *sdkp, unsigned char *buffer) int old_sector_size = sector_size; sd_printk(KERN_NOTICE, sdkp, "Very big device. " "Trying to use READ CAPACITY(16).\n"); - sector_size = read_capacity_16(sdkp, sdp, buffer); + sector_size = read_capacity_16(sdkp, sdp, lim, buffer); if (sector_size < 0) { sd_printk(KERN_NOTICE, sdkp, "Using 0xffffffff as device size\n"); @@ -2787,9 +2900,8 @@ got_data: */ sector_size = 512; } - blk_queue_logical_block_size(sdp->request_queue, sector_size); - blk_queue_physical_block_size(sdp->request_queue, - sdkp->physical_block_size); + lim->logical_block_size = sector_size; + lim->physical_block_size = sdkp->physical_block_size; sdkp->device->sector_size = sector_size; if (sdkp->capacity > 0xffffffff) @@ -3195,11 +3307,30 @@ static void sd_read_app_tag_own(struct scsi_disk *sdkp, unsigned char *buffer) return; } -/** - * sd_read_block_limits - Query disk device for preferred I/O sizes. - * @sdkp: disk to query +static unsigned int sd_discard_mode(struct scsi_disk *sdkp) +{ + if (!sdkp->lbpvpd) { + /* LBP VPD page not provided */ + if (sdkp->max_unmap_blocks) + return SD_LBP_UNMAP; + return SD_LBP_WS16; + } + + /* LBP VPD page tells us what to use */ + if (sdkp->lbpu && sdkp->max_unmap_blocks) + return SD_LBP_UNMAP; + if (sdkp->lbpws) + return SD_LBP_WS16; + if (sdkp->lbpws10) + return SD_LBP_WS10; + return SD_LBP_DISABLE; +} + +/* + * Query disk device for preferred I/O sizes. */ -static void sd_read_block_limits(struct scsi_disk *sdkp) +static void sd_read_block_limits(struct scsi_disk *sdkp, + struct queue_limits *lim) { struct scsi_vpd *vpd; @@ -3219,7 +3350,7 @@ static void sd_read_block_limits(struct scsi_disk *sdkp) sdkp->max_ws_blocks = (u32)get_unaligned_be64(&vpd->data[36]); if (!sdkp->lbpme) - goto out; + goto config_atomic; lba_count = get_unaligned_be32(&vpd->data[20]); desc_count = get_unaligned_be32(&vpd->data[24]); @@ -3233,23 +3364,16 @@ static void sd_read_block_limits(struct scsi_disk *sdkp) sdkp->unmap_alignment = get_unaligned_be32(&vpd->data[32]) & ~(1 << 31); - if (!sdkp->lbpvpd) { /* LBP VPD page not provided */ + sd_config_discard(sdkp, lim, sd_discard_mode(sdkp)); - if (sdkp->max_unmap_blocks) - sd_config_discard(sdkp, SD_LBP_UNMAP); - else - sd_config_discard(sdkp, SD_LBP_WS16); +config_atomic: + sdkp->max_atomic = get_unaligned_be32(&vpd->data[44]); + sdkp->atomic_alignment = get_unaligned_be32(&vpd->data[48]); + sdkp->atomic_granularity = get_unaligned_be32(&vpd->data[52]); + sdkp->max_atomic_with_boundary = get_unaligned_be32(&vpd->data[56]); + sdkp->max_atomic_boundary = get_unaligned_be32(&vpd->data[60]); - } else { /* LBP VPD page tells us what to use */ - if (sdkp->lbpu && sdkp->max_unmap_blocks) - sd_config_discard(sdkp, SD_LBP_UNMAP); - else if (sdkp->lbpws) - sd_config_discard(sdkp, SD_LBP_WS16); - else if (sdkp->lbpws10) - sd_config_discard(sdkp, SD_LBP_WS10); - else - sd_config_discard(sdkp, SD_LBP_DISABLE); - } + sd_config_atomic(sdkp, lim); } out: @@ -3268,13 +3392,10 @@ static void sd_read_block_limits_ext(struct scsi_disk *sdkp) rcu_read_unlock(); } -/** - * sd_read_block_characteristics - Query block dev. characteristics - * @sdkp: disk to query - */ -static void sd_read_block_characteristics(struct scsi_disk *sdkp) +/* Query block device characteristics */ +static void sd_read_block_characteristics(struct scsi_disk *sdkp, + struct queue_limits *lim) { - struct request_queue *q = sdkp->disk->queue; struct scsi_vpd *vpd; u16 rot; @@ -3290,37 +3411,13 @@ static void sd_read_block_characteristics(struct scsi_disk *sdkp) sdkp->zoned = (vpd->data[8] >> 4) & 3; rcu_read_unlock(); - if (rot == 1) { - blk_queue_flag_set(QUEUE_FLAG_NONROT, q); - blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, q); - } - - -#ifdef CONFIG_BLK_DEV_ZONED /* sd_probe rejects ZBD devices early otherwise */ - if (sdkp->device->type == TYPE_ZBC) { - /* - * Host-managed. - */ - disk_set_zoned(sdkp->disk); - - /* - * Per ZBC and ZAC specifications, writes in sequential write - * required zones of host-managed devices must be aligned to - * the device physical block size. - */ - blk_queue_zone_write_granularity(q, sdkp->physical_block_size); - } else { - /* - * Host-aware devices are treated as conventional. - */ - WARN_ON_ONCE(blk_queue_is_zoned(q)); - } -#endif /* CONFIG_BLK_DEV_ZONED */ + if (rot == 1) + lim->features &= ~(BLK_FEAT_ROTATIONAL | BLK_FEAT_ADD_RANDOM); if (!sdkp->first_scan) return; - if (blk_queue_is_zoned(q)) + if (sdkp->device->type == TYPE_ZBC) sd_printk(KERN_NOTICE, sdkp, "Host-managed zoned block device\n"); else if (sdkp->zoned == 1) sd_printk(KERN_NOTICE, sdkp, "Host-aware SMR disk used as regular disk\n"); @@ -3601,10 +3698,11 @@ static int sd_revalidate_disk(struct gendisk *disk) { struct scsi_disk *sdkp = scsi_disk(disk); struct scsi_device *sdp = sdkp->device; - struct request_queue *q = sdkp->disk->queue; sector_t old_capacity = sdkp->capacity; + struct queue_limits lim; unsigned char *buffer; - unsigned int dev_max, rw_max; + unsigned int dev_max; + int err; SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp, "sd_revalidate_disk\n")); @@ -3625,12 +3723,14 @@ static int sd_revalidate_disk(struct gendisk *disk) sd_spinup_disk(sdkp); + lim = queue_limits_start_update(sdkp->disk->queue); + /* * Without media there is no reason to ask; moreover, some devices * react badly if we do. */ if (sdkp->media_present) { - sd_read_capacity(sdkp, buffer); + sd_read_capacity(sdkp, &lim, buffer); /* * Some USB/UAS devices return generic values for mode pages * until the media has been accessed. Trigger a READ operation @@ -3644,15 +3744,14 @@ static int sd_revalidate_disk(struct gendisk *disk) * cause this to be updated correctly and any device which * doesn't support it should be treated as rotational. */ - blk_queue_flag_clear(QUEUE_FLAG_NONROT, q); - blk_queue_flag_set(QUEUE_FLAG_ADD_RANDOM, q); + lim.features |= (BLK_FEAT_ROTATIONAL | BLK_FEAT_ADD_RANDOM); if (scsi_device_supports_vpd(sdp)) { sd_read_block_provisioning(sdkp); - sd_read_block_limits(sdkp); + sd_read_block_limits(sdkp, &lim); sd_read_block_limits_ext(sdkp); - sd_read_block_characteristics(sdkp); - sd_zbc_read_zones(sdkp, buffer); + sd_read_block_characteristics(sdkp, &lim); + sd_zbc_read_zones(sdkp, &lim, buffer); sd_read_cpr(sdkp); } @@ -3664,64 +3763,50 @@ static int sd_revalidate_disk(struct gendisk *disk) sd_read_app_tag_own(sdkp, buffer); sd_read_write_same(sdkp, buffer); sd_read_security(sdkp, buffer); - sd_config_protection(sdkp); + sd_config_protection(sdkp, &lim); } /* * We now have all cache related info, determine how we deal * with flush requests. */ - sd_set_flush_flag(sdkp); + sd_set_flush_flag(sdkp, &lim); /* Initial block count limit based on CDB TRANSFER LENGTH field size. */ dev_max = sdp->use_16_for_rw ? SD_MAX_XFER_BLOCKS : SD_DEF_XFER_BLOCKS; /* Some devices report a maximum block count for READ/WRITE requests. */ dev_max = min_not_zero(dev_max, sdkp->max_xfer_blocks); - q->limits.max_dev_sectors = logical_to_sectors(sdp, dev_max); + lim.max_dev_sectors = logical_to_sectors(sdp, dev_max); if (sd_validate_min_xfer_size(sdkp)) - blk_queue_io_min(sdkp->disk->queue, - logical_to_bytes(sdp, sdkp->min_xfer_blocks)); + lim.io_min = logical_to_bytes(sdp, sdkp->min_xfer_blocks); else - blk_queue_io_min(sdkp->disk->queue, 0); - - if (sd_validate_opt_xfer_size(sdkp, dev_max)) { - q->limits.io_opt = logical_to_bytes(sdp, sdkp->opt_xfer_blocks); - rw_max = logical_to_sectors(sdp, sdkp->opt_xfer_blocks); - } else { - q->limits.io_opt = 0; - rw_max = min_not_zero(logical_to_sectors(sdp, dev_max), - (sector_t)BLK_DEF_MAX_SECTORS_CAP); - } + lim.io_min = 0; /* * Limit default to SCSI host optimal sector limit if set. There may be * an impact on performance for when the size of a request exceeds this * host limit. */ - rw_max = min_not_zero(rw_max, sdp->host->opt_sectors); - - /* Do not exceed controller limit */ - rw_max = min(rw_max, queue_max_hw_sectors(q)); - - /* - * Only update max_sectors if previously unset or if the current value - * exceeds the capabilities of the hardware. - */ - if (sdkp->first_scan || - q->limits.max_sectors > q->limits.max_dev_sectors || - q->limits.max_sectors > q->limits.max_hw_sectors) { - q->limits.max_sectors = rw_max; - q->limits.max_user_sectors = rw_max; + lim.io_opt = sdp->host->opt_sectors << SECTOR_SHIFT; + if (sd_validate_opt_xfer_size(sdkp, dev_max)) { + lim.io_opt = min_not_zero(lim.io_opt, + logical_to_bytes(sdp, sdkp->opt_xfer_blocks)); } sdkp->first_scan = 0; set_capacity_and_notify(disk, logical_to_sectors(sdp, sdkp->capacity)); - sd_config_write_same(sdkp); + sd_config_write_same(sdkp, &lim); kfree(buffer); + blk_mq_freeze_queue(sdkp->disk->queue); + err = queue_limits_commit_update(sdkp->disk->queue, &lim); + blk_mq_unfreeze_queue(sdkp->disk->queue); + if (err) + return err; + /* * For a zoned drive, revalidating the zones can be done only once * the gendisk capacity is set. So if this fails, set back the gendisk diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h index 49dd600bfa48..36382eca941c 100644 --- a/drivers/scsi/sd.h +++ b/drivers/scsi/sd.h @@ -115,6 +115,13 @@ struct scsi_disk { u32 max_unmap_blocks; u32 unmap_granularity; u32 unmap_alignment; + + u32 max_atomic; + u32 atomic_alignment; + u32 atomic_granularity; + u32 max_atomic_with_boundary; + u32 max_atomic_boundary; + u32 index; unsigned int physical_block_size; unsigned int max_medium_access_timeouts; @@ -148,6 +155,7 @@ struct scsi_disk { unsigned security : 1; unsigned ignore_medium_access_errors : 1; unsigned rscs : 1; /* reduced stream control support */ + unsigned use_atomic_write_boundary : 1; }; #define to_scsi_disk(obj) container_of(obj, struct scsi_disk, disk_dev) @@ -220,26 +228,12 @@ static inline sector_t sectors_to_logical(struct scsi_device *sdev, sector_t sec return sector >> (ilog2(sdev->sector_size) - 9); } -#ifdef CONFIG_BLK_DEV_INTEGRITY - -extern void sd_dif_config_host(struct scsi_disk *); - -#else /* CONFIG_BLK_DEV_INTEGRITY */ - -static inline void sd_dif_config_host(struct scsi_disk *disk) -{ -} - -#endif /* CONFIG_BLK_DEV_INTEGRITY */ - -static inline int sd_is_zoned(struct scsi_disk *sdkp) -{ - return sdkp->zoned == 1 || sdkp->device->type == TYPE_ZBC; -} +void sd_dif_config_host(struct scsi_disk *sdkp, struct queue_limits *lim); #ifdef CONFIG_BLK_DEV_ZONED -int sd_zbc_read_zones(struct scsi_disk *sdkp, u8 buf[SD_BUF_SIZE]); +int sd_zbc_read_zones(struct scsi_disk *sdkp, struct queue_limits *lim, + u8 buf[SD_BUF_SIZE]); int sd_zbc_revalidate_zones(struct scsi_disk *sdkp); blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd, unsigned char op, bool all); @@ -250,7 +244,8 @@ int sd_zbc_report_zones(struct gendisk *disk, sector_t sector, #else /* CONFIG_BLK_DEV_ZONED */ -static inline int sd_zbc_read_zones(struct scsi_disk *sdkp, u8 buf[SD_BUF_SIZE]) +static inline int sd_zbc_read_zones(struct scsi_disk *sdkp, + struct queue_limits *lim, u8 buf[SD_BUF_SIZE]) { return 0; } diff --git a/drivers/scsi/sd_dif.c b/drivers/scsi/sd_dif.c index 1df847b5f747..ae6ce6f5d622 100644 --- a/drivers/scsi/sd_dif.c +++ b/drivers/scsi/sd_dif.c @@ -24,14 +24,15 @@ /* * Configure exchange of protection information between OS and HBA. */ -void sd_dif_config_host(struct scsi_disk *sdkp) +void sd_dif_config_host(struct scsi_disk *sdkp, struct queue_limits *lim) { struct scsi_device *sdp = sdkp->device; - struct gendisk *disk = sdkp->disk; u8 type = sdkp->protection_type; - struct blk_integrity bi; + struct blk_integrity *bi = &lim->integrity; int dif, dix; + memset(bi, 0, sizeof(*bi)); + dif = scsi_host_dif_capable(sdp->host, type); dix = scsi_host_dix_capable(sdp->host, type); @@ -39,45 +40,33 @@ void sd_dif_config_host(struct scsi_disk *sdkp) dif = 0; dix = 1; } - if (!dix) { - blk_integrity_unregister(disk); + if (!dix) return; - } - - memset(&bi, 0, sizeof(bi)); /* Enable DMA of protection information */ - if (scsi_host_get_guard(sdkp->device->host) & SHOST_DIX_GUARD_IP) { - if (type == T10_PI_TYPE3_PROTECTION) - bi.profile = &t10_pi_type3_ip; - else - bi.profile = &t10_pi_type1_ip; + if (scsi_host_get_guard(sdkp->device->host) & SHOST_DIX_GUARD_IP) + bi->csum_type = BLK_INTEGRITY_CSUM_IP; + else + bi->csum_type = BLK_INTEGRITY_CSUM_CRC; - bi.flags |= BLK_INTEGRITY_IP_CHECKSUM; - } else - if (type == T10_PI_TYPE3_PROTECTION) - bi.profile = &t10_pi_type3_crc; - else - bi.profile = &t10_pi_type1_crc; + if (type != T10_PI_TYPE3_PROTECTION) + bi->flags |= BLK_INTEGRITY_REF_TAG; - bi.tuple_size = sizeof(struct t10_pi_tuple); + bi->tuple_size = sizeof(struct t10_pi_tuple); if (dif && type) { - bi.flags |= BLK_INTEGRITY_DEVICE_CAPABLE; + bi->flags |= BLK_INTEGRITY_DEVICE_CAPABLE; if (!sdkp->ATO) - goto out; + return; if (type == T10_PI_TYPE3_PROTECTION) - bi.tag_size = sizeof(u16) + sizeof(u32); + bi->tag_size = sizeof(u16) + sizeof(u32); else - bi.tag_size = sizeof(u16); + bi->tag_size = sizeof(u16); } sd_first_printk(KERN_NOTICE, sdkp, "Enabling DIX %s, application tag size %u bytes\n", - bi.profile->name, bi.tag_size); -out: - blk_integrity_register(disk, &bi); + blk_integrity_profile_name(bi), bi->tag_size); } - diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index 806036e48abe..c8b9654d30f0 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -232,7 +232,7 @@ int sd_zbc_report_zones(struct gendisk *disk, sector_t sector, int zone_idx = 0; int ret; - if (!sd_is_zoned(sdkp)) + if (sdkp->device->type != TYPE_ZBC) /* Not a zoned device */ return -EOPNOTSUPP; @@ -300,7 +300,7 @@ static blk_status_t sd_zbc_cmnd_checks(struct scsi_cmnd *cmd) struct scsi_disk *sdkp = scsi_disk(rq->q->disk); sector_t sector = blk_rq_pos(rq); - if (!sd_is_zoned(sdkp)) + if (sdkp->device->type != TYPE_ZBC) /* Not a zoned device */ return BLK_STS_IOERR; @@ -521,7 +521,7 @@ static int sd_zbc_check_capacity(struct scsi_disk *sdkp, unsigned char *buf, static void sd_zbc_print_zones(struct scsi_disk *sdkp) { - if (!sd_is_zoned(sdkp) || !sdkp->capacity) + if (sdkp->device->type != TYPE_ZBC || !sdkp->capacity) return; if (sdkp->capacity & (sdkp->zone_info.zone_blocks - 1)) @@ -565,12 +565,6 @@ int sd_zbc_revalidate_zones(struct scsi_disk *sdkp) sdkp->zone_info.zone_blocks = zone_blocks; sdkp->zone_info.nr_zones = nr_zones; - blk_queue_chunk_sectors(q, - logical_to_sectors(sdkp->device, zone_blocks)); - - /* Enable block layer zone append emulation */ - blk_queue_max_zone_append_sectors(q, 0); - flags = memalloc_noio_save(); ret = blk_revalidate_disk_zones(disk); memalloc_noio_restore(flags); @@ -588,27 +582,31 @@ int sd_zbc_revalidate_zones(struct scsi_disk *sdkp) /** * sd_zbc_read_zones - Read zone information and update the request queue * @sdkp: SCSI disk pointer. + * @lim: queue limits to read into * @buf: 512 byte buffer used for storing SCSI command output. * * Read zone information and update the request queue zone characteristics and * also the zoned device information in *sdkp. Called by sd_revalidate_disk() * before the gendisk capacity has been set. */ -int sd_zbc_read_zones(struct scsi_disk *sdkp, u8 buf[SD_BUF_SIZE]) +int sd_zbc_read_zones(struct scsi_disk *sdkp, struct queue_limits *lim, + u8 buf[SD_BUF_SIZE]) { - struct gendisk *disk = sdkp->disk; - struct request_queue *q = disk->queue; unsigned int nr_zones; u32 zone_blocks = 0; int ret; - if (!sd_is_zoned(sdkp)) { - /* - * Device managed or normal SCSI disk, no special handling - * required. - */ + if (sdkp->device->type != TYPE_ZBC) return 0; - } + + lim->features |= BLK_FEAT_ZONED; + + /* + * Per ZBC and ZAC specifications, writes in sequential write required + * zones of host-managed devices must be aligned to the device physical + * block size. + */ + lim->zone_write_granularity = sdkp->physical_block_size; /* READ16/WRITE16/SYNC16 is mandatory for ZBC devices */ sdkp->device->use_16_for_rw = 1; @@ -625,18 +623,20 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, u8 buf[SD_BUF_SIZE]) if (ret != 0) goto err; - /* The drive satisfies the kernel restrictions: set it up */ - blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q); - if (sdkp->zones_max_open == U32_MAX) - disk_set_max_open_zones(disk, 0); - else - disk_set_max_open_zones(disk, sdkp->zones_max_open); - disk_set_max_active_zones(disk, 0); nr_zones = round_up(sdkp->capacity, zone_blocks) >> ilog2(zone_blocks); - sdkp->early_zone_info.nr_zones = nr_zones; sdkp->early_zone_info.zone_blocks = zone_blocks; + /* The drive satisfies the kernel restrictions: set it up */ + if (sdkp->zones_max_open == U32_MAX) + lim->max_open_zones = 0; + else + lim->max_open_zones = sdkp->zones_max_open; + lim->max_active_zones = 0; + lim->chunk_sectors = logical_to_sectors(sdkp->device, zone_blocks); + /* Enable block layer zone append emulation */ + lim->max_zone_append_sectors = 0; + return 0; err: diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 7ab000942b97..3f491019103e 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -111,7 +111,7 @@ static struct lock_class_key sr_bio_compl_lkclass; static int sr_open(struct cdrom_device_info *, int); static void sr_release(struct cdrom_device_info *); -static void get_sectorsize(struct scsi_cd *); +static int get_sectorsize(struct scsi_cd *); static int get_capabilities(struct scsi_cd *); static unsigned int sr_check_events(struct cdrom_device_info *cdi, @@ -473,15 +473,15 @@ static blk_status_t sr_init_command(struct scsi_cmnd *SCpnt) return BLK_STS_IOERR; } -static void sr_revalidate_disk(struct scsi_cd *cd) +static int sr_revalidate_disk(struct scsi_cd *cd) { struct scsi_sense_hdr sshdr; /* if the unit is not ready, nothing more to do */ if (scsi_test_unit_ready(cd->device, SR_TIMEOUT, MAX_RETRIES, &sshdr)) - return; + return 0; sr_cd_check(&cd->cdi); - get_sectorsize(cd); + return get_sectorsize(cd); } static int sr_block_open(struct gendisk *disk, blk_mode_t mode) @@ -494,13 +494,16 @@ static int sr_block_open(struct gendisk *disk, blk_mode_t mode) return -ENXIO; scsi_autopm_get_device(sdev); - if (disk_check_media_change(disk)) - sr_revalidate_disk(cd); + if (disk_check_media_change(disk)) { + ret = sr_revalidate_disk(cd); + if (ret) + goto out; + } mutex_lock(&cd->lock); ret = cdrom_open(&cd->cdi, mode); mutex_unlock(&cd->lock); - +out: scsi_autopm_put_device(sdev); if (ret) scsi_device_put(cd->device); @@ -685,7 +688,9 @@ static int sr_probe(struct device *dev) blk_pm_runtime_init(sdev->request_queue, dev); dev_set_drvdata(dev, cd); - sr_revalidate_disk(cd); + error = sr_revalidate_disk(cd); + if (error) + goto unregister_cdrom; error = device_add_disk(&sdev->sdev_gendev, disk, NULL); if (error) @@ -714,13 +719,14 @@ fail: } -static void get_sectorsize(struct scsi_cd *cd) +static int get_sectorsize(struct scsi_cd *cd) { + struct request_queue *q = cd->device->request_queue; static const u8 cmd[10] = { READ_CAPACITY }; unsigned char buffer[8] = { }; - int the_result; + struct queue_limits lim; + int err; int sector_size; - struct request_queue *queue; struct scsi_failure failure_defs[] = { { .result = SCMD_FAILURE_RESULT_ANY, @@ -736,10 +742,10 @@ static void get_sectorsize(struct scsi_cd *cd) }; /* Do the command and wait.. */ - the_result = scsi_execute_cmd(cd->device, cmd, REQ_OP_DRV_IN, buffer, + err = scsi_execute_cmd(cd->device, cmd, REQ_OP_DRV_IN, buffer, sizeof(buffer), SR_TIMEOUT, MAX_RETRIES, &exec_args); - if (the_result) { + if (err) { cd->capacity = 0x1fffff; sector_size = 2048; /* A guess, just in case */ } else { @@ -789,10 +795,12 @@ static void get_sectorsize(struct scsi_cd *cd) set_capacity(cd->disk, cd->capacity); } - queue = cd->device->request_queue; - blk_queue_logical_block_size(queue, sector_size); - - return; + lim = queue_limits_start_update(q); + lim.logical_block_size = sector_size; + blk_mq_freeze_queue(q); + err = queue_limits_commit_update(q, &lim); + blk_mq_unfreeze_queue(q); + return err; } static int get_capabilities(struct scsi_cd *cd) diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index 7f6ca8177845..a3e09adc4e76 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -148,35 +148,38 @@ static int iblock_configure_device(struct se_device *dev) dev->dev_attrib.is_nonrot = 1; bi = bdev_get_integrity(bd); - if (bi) { - struct bio_set *bs = &ib_dev->ibd_bio_set; + if (!bi) + return 0; - if (!strcmp(bi->profile->name, "T10-DIF-TYPE3-IP") || - !strcmp(bi->profile->name, "T10-DIF-TYPE1-IP")) { - pr_err("IBLOCK export of blk_integrity: %s not" - " supported\n", bi->profile->name); - ret = -ENOSYS; - goto out_blkdev_put; - } - - if (!strcmp(bi->profile->name, "T10-DIF-TYPE3-CRC")) { - dev->dev_attrib.pi_prot_type = TARGET_DIF_TYPE3_PROT; - } else if (!strcmp(bi->profile->name, "T10-DIF-TYPE1-CRC")) { + switch (bi->csum_type) { + case BLK_INTEGRITY_CSUM_IP: + pr_err("IBLOCK export of blk_integrity: %s not supported\n", + blk_integrity_profile_name(bi)); + ret = -ENOSYS; + goto out_blkdev_put; + case BLK_INTEGRITY_CSUM_CRC: + if (bi->flags & BLK_INTEGRITY_REF_TAG) dev->dev_attrib.pi_prot_type = TARGET_DIF_TYPE1_PROT; - } - - if (dev->dev_attrib.pi_prot_type) { - if (bioset_integrity_create(bs, IBLOCK_BIO_POOL_SIZE) < 0) { - pr_err("Unable to allocate bioset for PI\n"); - ret = -ENOMEM; - goto out_blkdev_put; - } - pr_debug("IBLOCK setup BIP bs->bio_integrity_pool: %p\n", - &bs->bio_integrity_pool); - } - dev->dev_attrib.hw_pi_prot_type = dev->dev_attrib.pi_prot_type; + else + dev->dev_attrib.pi_prot_type = TARGET_DIF_TYPE3_PROT; + break; + default: + break; } + if (dev->dev_attrib.pi_prot_type) { + struct bio_set *bs = &ib_dev->ibd_bio_set; + + if (bioset_integrity_create(bs, IBLOCK_BIO_POOL_SIZE) < 0) { + pr_err("Unable to allocate bioset for PI\n"); + ret = -ENOMEM; + goto out_blkdev_put; + } + pr_debug("IBLOCK setup BIP bs->bio_integrity_pool: %p\n", + &bs->bio_integrity_pool); + } + + dev->dev_attrib.hw_pi_prot_type = dev->dev_attrib.pi_prot_type; return 0; out_blkdev_put: diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 46433ecf0c4d..702fa1996992 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -5193,17 +5193,19 @@ static int ufshcd_change_queue_depth(struct scsi_device *sdev, int depth) } /** - * ufshcd_slave_configure - adjust SCSI device configurations + * ufshcd_device_configure - adjust SCSI device configurations * @sdev: pointer to SCSI device + * @lim: queue limits * * Return: 0 (success). */ -static int ufshcd_slave_configure(struct scsi_device *sdev) +static int ufshcd_device_configure(struct scsi_device *sdev, + struct queue_limits *lim) { struct ufs_hba *hba = shost_priv(sdev->host); struct request_queue *q = sdev->request_queue; - blk_queue_update_dma_pad(q, PRDT_DATA_BYTE_COUNT_PAD - 1); + lim->dma_pad_mask = PRDT_DATA_BYTE_COUNT_PAD - 1; /* * Block runtime-pm until all consumers are added. @@ -8910,7 +8912,7 @@ static const struct scsi_host_template ufshcd_driver_template = { .queuecommand = ufshcd_queuecommand, .mq_poll = ufshcd_poll, .slave_alloc = ufshcd_slave_alloc, - .slave_configure = ufshcd_slave_configure, + .device_configure = ufshcd_device_configure, .slave_destroy = ufshcd_slave_destroy, .change_queue_depth = ufshcd_change_queue_depth, .eh_abort_handler = ufshcd_abort, diff --git a/fs/aio.c b/fs/aio.c index 57c9f7c077e6..93ef59d358b3 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -1516,7 +1516,7 @@ static void aio_complete_rw(struct kiocb *kiocb, long res) iocb_put(iocb); } -static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) +static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb, int rw_type) { int ret; @@ -1542,7 +1542,7 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) } else req->ki_ioprio = get_current_ioprio(); - ret = kiocb_set_rw_flags(req, iocb->aio_rw_flags); + ret = kiocb_set_rw_flags(req, iocb->aio_rw_flags, rw_type); if (unlikely(ret)) return ret; @@ -1594,7 +1594,7 @@ static int aio_read(struct kiocb *req, const struct iocb *iocb, struct file *file; int ret; - ret = aio_prep_rw(req, iocb); + ret = aio_prep_rw(req, iocb, READ); if (ret) return ret; file = req->ki_filp; @@ -1621,7 +1621,7 @@ static int aio_write(struct kiocb *req, const struct iocb *iocb, struct file *file; int ret; - ret = aio_prep_rw(req, iocb); + ret = aio_prep_rw(req, iocb, WRITE); if (ret) return ret; file = req->ki_filp; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index efd5d6e9589e..6ad524b894fc 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -4627,7 +4627,7 @@ static int btrfs_ioctl_encoded_write(struct file *file, void __user *argp, bool goto out_iov; init_sync_kiocb(&kiocb, file); - ret = kiocb_set_rw_flags(&kiocb, 0); + ret = kiocb_set_rw_flags(&kiocb, 0, WRITE); if (ret) goto out_iov; kiocb.ki_pos = pos; diff --git a/fs/read_write.c b/fs/read_write.c index ef6339391351..90e283b31ca1 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -730,7 +730,7 @@ static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, ssize_t ret; init_sync_kiocb(&kiocb, filp); - ret = kiocb_set_rw_flags(&kiocb, flags); + ret = kiocb_set_rw_flags(&kiocb, flags, type); if (ret) return ret; kiocb.ki_pos = (ppos ? *ppos : 0); @@ -1736,3 +1736,19 @@ int generic_file_rw_checks(struct file *file_in, struct file *file_out) return 0; } + +bool generic_atomic_write_valid(struct iov_iter *iter, loff_t pos) +{ + size_t len = iov_iter_count(iter); + + if (!iter_is_ubuf(iter)) + return false; + + if (!is_power_of_2(len)) + return false; + + if (!IS_ALIGNED(pos, len)) + return false; + + return true; +} diff --git a/fs/stat.c b/fs/stat.c index 6f65b3456cad..89ce1be56310 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -89,6 +89,37 @@ void generic_fill_statx_attr(struct inode *inode, struct kstat *stat) } EXPORT_SYMBOL(generic_fill_statx_attr); +/** + * generic_fill_statx_atomic_writes - Fill in atomic writes statx attributes + * @stat: Where to fill in the attribute flags + * @unit_min: Minimum supported atomic write length in bytes + * @unit_max: Maximum supported atomic write length in bytes + * + * Fill in the STATX{_ATTR}_WRITE_ATOMIC flags in the kstat structure from + * atomic write unit_min and unit_max values. + */ +void generic_fill_statx_atomic_writes(struct kstat *stat, + unsigned int unit_min, + unsigned int unit_max) +{ + /* Confirm that the request type is known */ + stat->result_mask |= STATX_WRITE_ATOMIC; + + /* Confirm that the file attribute type is known */ + stat->attributes_mask |= STATX_ATTR_WRITE_ATOMIC; + + if (unit_min) { + stat->atomic_write_unit_min = unit_min; + stat->atomic_write_unit_max = unit_max; + /* Initially only allow 1x segment */ + stat->atomic_write_segments_max = 1; + + /* Confirm atomic writes are actually supported */ + stat->attributes |= STATX_ATTR_WRITE_ATOMIC; + } +} +EXPORT_SYMBOL_GPL(generic_fill_statx_atomic_writes); + /** * vfs_getattr_nosec - getattr without security checks * @path: file to get attributes from @@ -231,13 +262,13 @@ static int vfs_statx_path(struct path *path, int flags, struct kstat *stat, stat->attributes |= STATX_ATTR_MOUNT_ROOT; stat->attributes_mask |= STATX_ATTR_MOUNT_ROOT; - /* Handle STATX_DIOALIGN for block devices. */ - if (request_mask & STATX_DIOALIGN) { - struct inode *inode = d_backing_inode(path->dentry); - - if (S_ISBLK(inode->i_mode)) - bdev_statx_dioalign(inode, stat); - } + /* + * If this is a block device inode, override the filesystem + * attributes with the block device specific parameters that need to be + * obtained from the bdev backing inode. + */ + if (S_ISBLK(stat->mode)) + bdev_statx(path, stat, request_mask); return error; } @@ -670,6 +701,9 @@ cp_statx(const struct kstat *stat, struct statx __user *buffer) tmp.stx_dio_mem_align = stat->dio_mem_align; tmp.stx_dio_offset_align = stat->dio_offset_align; tmp.stx_subvol = stat->subvol; + tmp.stx_atomic_write_unit_min = stat->atomic_write_unit_min; + tmp.stx_atomic_write_unit_max = stat->atomic_write_unit_max; + tmp.stx_atomic_write_segments_max = stat->atomic_write_segments_max; return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0; } diff --git a/include/linux/blk-integrity.h b/include/linux/blk-integrity.h index 7428cb43952d..804f856ed3e5 100644 --- a/include/linux/blk-integrity.h +++ b/include/linux/blk-integrity.h @@ -7,51 +7,38 @@ struct request; enum blk_integrity_flags { - BLK_INTEGRITY_VERIFY = 1 << 0, - BLK_INTEGRITY_GENERATE = 1 << 1, + BLK_INTEGRITY_NOVERIFY = 1 << 0, + BLK_INTEGRITY_NOGENERATE = 1 << 1, BLK_INTEGRITY_DEVICE_CAPABLE = 1 << 2, - BLK_INTEGRITY_IP_CHECKSUM = 1 << 3, + BLK_INTEGRITY_REF_TAG = 1 << 3, + BLK_INTEGRITY_STACKED = 1 << 4, }; -struct blk_integrity_iter { - void *prot_buf; - void *data_buf; - sector_t seed; - unsigned int data_size; - unsigned short interval; - unsigned char tuple_size; - unsigned char pi_offset; - const char *disk_name; -}; - -typedef blk_status_t (integrity_processing_fn) (struct blk_integrity_iter *); -typedef void (integrity_prepare_fn) (struct request *); -typedef void (integrity_complete_fn) (struct request *, unsigned int); - -struct blk_integrity_profile { - integrity_processing_fn *generate_fn; - integrity_processing_fn *verify_fn; - integrity_prepare_fn *prepare_fn; - integrity_complete_fn *complete_fn; - const char *name; -}; +const char *blk_integrity_profile_name(struct blk_integrity *bi); +bool queue_limits_stack_integrity(struct queue_limits *t, + struct queue_limits *b); +static inline bool queue_limits_stack_integrity_bdev(struct queue_limits *t, + struct block_device *bdev) +{ + return queue_limits_stack_integrity(t, &bdev->bd_disk->queue->limits); +} #ifdef CONFIG_BLK_DEV_INTEGRITY -void blk_integrity_register(struct gendisk *, struct blk_integrity *); -void blk_integrity_unregister(struct gendisk *); -int blk_integrity_compare(struct gendisk *, struct gendisk *); int blk_rq_map_integrity_sg(struct request_queue *, struct bio *, struct scatterlist *); int blk_rq_count_integrity_sg(struct request_queue *, struct bio *); +static inline bool +blk_integrity_queue_supports_integrity(struct request_queue *q) +{ + return q->limits.integrity.tuple_size; +} + static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) { - struct blk_integrity *bi = &disk->queue->integrity; - - if (!bi->profile) + if (!blk_integrity_queue_supports_integrity(disk->queue)) return NULL; - - return bi; + return &disk->queue->limits.integrity; } static inline struct blk_integrity * @@ -60,12 +47,6 @@ bdev_get_integrity(struct block_device *bdev) return blk_get_integrity(bdev->bd_disk); } -static inline bool -blk_integrity_queue_supports_integrity(struct request_queue *q) -{ - return q->integrity.profile; -} - static inline unsigned short queue_max_integrity_segments(const struct request_queue *q) { @@ -100,14 +81,13 @@ static inline bool blk_integrity_rq(struct request *rq) } /* - * Return the first bvec that contains integrity data. Only drivers that are - * limited to a single integrity segment should use this helper. + * Return the current bvec that contains the integrity data. bip_iter may be + * advanced to iterate over the integrity data. */ -static inline struct bio_vec *rq_integrity_vec(struct request *rq) +static inline struct bio_vec rq_integrity_vec(struct request *rq) { - if (WARN_ON_ONCE(queue_max_integrity_segments(rq->q) > 1)) - return NULL; - return rq->bio->bi_integrity->bip_vec; + return mp_bvec_iter_bvec(rq->bio->bi_integrity->bip_vec, + rq->bio->bi_integrity->bip_iter); } #else /* CONFIG_BLK_DEV_INTEGRITY */ static inline int blk_rq_count_integrity_sg(struct request_queue *q, @@ -134,17 +114,6 @@ blk_integrity_queue_supports_integrity(struct request_queue *q) { return false; } -static inline int blk_integrity_compare(struct gendisk *a, struct gendisk *b) -{ - return 0; -} -static inline void blk_integrity_register(struct gendisk *d, - struct blk_integrity *b) -{ -} -static inline void blk_integrity_unregister(struct gendisk *d) -{ -} static inline unsigned short queue_max_integrity_segments(const struct request_queue *q) { @@ -167,9 +136,11 @@ static inline int blk_integrity_rq(struct request *rq) return 0; } -static inline struct bio_vec *rq_integrity_vec(struct request *rq) +static inline struct bio_vec rq_integrity_vec(struct request *rq) { - return NULL; + /* the optimizer will remove all calls to this function */ + return (struct bio_vec){ }; } #endif /* CONFIG_BLK_DEV_INTEGRITY */ + #endif /* _LINUX_BLK_INTEGRITY_H */ diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 781c4500491b..632edd71f8c6 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -162,6 +162,11 @@ typedef u16 blk_short_t; */ #define BLK_STS_DURATION_LIMIT ((__force blk_status_t)17) +/* + * Invalid size or alignment. + */ +#define BLK_STS_INVAL ((__force blk_status_t)19) + /** * blk_path_error - returns true if error may be path related * @error: status the request was completed with @@ -370,7 +375,7 @@ enum req_flag_bits { __REQ_SWAP, /* swap I/O */ __REQ_DRV, /* for driver use */ __REQ_FS_PRIVATE, /* for file system (submitter) use */ - + __REQ_ATOMIC, /* for atomic write operations */ /* * Command specific flags, keep last: */ @@ -402,6 +407,7 @@ enum req_flag_bits { #define REQ_SWAP (__force blk_opf_t)(1ULL << __REQ_SWAP) #define REQ_DRV (__force blk_opf_t)(1ULL << __REQ_DRV) #define REQ_FS_PRIVATE (__force blk_opf_t)(1ULL << __REQ_FS_PRIVATE) +#define REQ_ATOMIC (__force blk_opf_t)(1ULL << __REQ_ATOMIC) #define REQ_NOUNMAP (__force blk_opf_t)(1ULL << __REQ_NOUNMAP) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 24c36929920b..b8196e219ac2 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -105,9 +105,16 @@ enum { struct disk_events; struct badblocks; +enum blk_integrity_checksum { + BLK_INTEGRITY_CSUM_NONE = 0, + BLK_INTEGRITY_CSUM_IP = 1, + BLK_INTEGRITY_CSUM_CRC = 2, + BLK_INTEGRITY_CSUM_CRC64 = 3, +} __packed ; + struct blk_integrity { - const struct blk_integrity_profile *profile; unsigned char flags; + enum blk_integrity_checksum csum_type; unsigned char tuple_size; unsigned char pi_offset; unsigned char interval_exp; @@ -261,6 +268,7 @@ static inline dev_t disk_devt(struct gendisk *disk) return MKDEV(disk->major, disk->first_minor); } +/* blk_validate_limits() validates bsize, so drivers don't usually need to */ static inline int blk_validate_block_size(unsigned long bsize) { if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize)) @@ -275,17 +283,75 @@ static inline bool blk_op_is_passthrough(blk_opf_t op) return op == REQ_OP_DRV_IN || op == REQ_OP_DRV_OUT; } +/* flags set by the driver in queue_limits.features */ +typedef unsigned int __bitwise blk_features_t; + +/* supports a volatile write cache */ +#define BLK_FEAT_WRITE_CACHE ((__force blk_features_t)(1u << 0)) + +/* supports passing on the FUA bit */ +#define BLK_FEAT_FUA ((__force blk_features_t)(1u << 1)) + +/* rotational device (hard drive or floppy) */ +#define BLK_FEAT_ROTATIONAL ((__force blk_features_t)(1u << 2)) + +/* contributes to the random number pool */ +#define BLK_FEAT_ADD_RANDOM ((__force blk_features_t)(1u << 3)) + +/* do disk/partitions IO accounting */ +#define BLK_FEAT_IO_STAT ((__force blk_features_t)(1u << 4)) + +/* don't modify data until writeback is done */ +#define BLK_FEAT_STABLE_WRITES ((__force blk_features_t)(1u << 5)) + +/* always completes in submit context */ +#define BLK_FEAT_SYNCHRONOUS ((__force blk_features_t)(1u << 6)) + +/* supports REQ_NOWAIT */ +#define BLK_FEAT_NOWAIT ((__force blk_features_t)(1u << 7)) + +/* supports DAX */ +#define BLK_FEAT_DAX ((__force blk_features_t)(1u << 8)) + +/* supports I/O polling */ +#define BLK_FEAT_POLL ((__force blk_features_t)(1u << 9)) + +/* is a zoned device */ +#define BLK_FEAT_ZONED ((__force blk_features_t)(1u << 10)) + +/* supports PCI(e) p2p requests */ +#define BLK_FEAT_PCI_P2PDMA ((__force blk_features_t)(1u << 12)) + +/* skip this queue in blk_mq_(un)quiesce_tagset */ +#define BLK_FEAT_SKIP_TAGSET_QUIESCE ((__force blk_features_t)(1u << 13)) + +/* bounce all highmem pages */ +#define BLK_FEAT_BOUNCE_HIGH ((__force blk_features_t)(1u << 14)) + +/* undocumented magic for bcache */ +#define BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE \ + ((__force blk_features_t)(1u << 15)) + /* - * BLK_BOUNCE_NONE: never bounce (default) - * BLK_BOUNCE_HIGH: bounce all highmem pages + * Flags automatically inherited when stacking limits. */ -enum blk_bounce { - BLK_BOUNCE_NONE, - BLK_BOUNCE_HIGH, -}; +#define BLK_FEAT_INHERIT_MASK \ + (BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA | BLK_FEAT_ROTATIONAL | \ + BLK_FEAT_STABLE_WRITES | BLK_FEAT_ZONED | BLK_FEAT_BOUNCE_HIGH | \ + BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE) + +/* internal flags in queue_limits.flags */ +typedef unsigned int __bitwise blk_flags_t; + +/* do not send FLUSH/FUA commands despite advertising a write cache */ +#define BLK_FLAG_WRITE_CACHE_DISABLED ((__force blk_flags_t)(1u << 0)) + +/* I/O topology is misaligned */ +#define BLK_FLAG_MISALIGNED ((__force blk_flags_t)(1u << 1)) struct queue_limits { - enum blk_bounce bounce; + blk_features_t features; + blk_flags_t flags; unsigned long seg_boundary_mask; unsigned long virt_boundary_mask; @@ -310,14 +376,20 @@ struct queue_limits { unsigned int discard_alignment; unsigned int zone_write_granularity; + /* atomic write limits */ + unsigned int atomic_write_hw_max; + unsigned int atomic_write_max_sectors; + unsigned int atomic_write_hw_boundary; + unsigned int atomic_write_boundary_sectors; + unsigned int atomic_write_hw_unit_min; + unsigned int atomic_write_unit_min; + unsigned int atomic_write_hw_unit_max; + unsigned int atomic_write_unit_max; + unsigned short max_segments; unsigned short max_integrity_segments; unsigned short max_discard_segments; - unsigned char misaligned; - unsigned char discard_misaligned; - unsigned char raid_partial_stripes_expensive; - bool zoned; unsigned int max_open_zones; unsigned int max_active_zones; @@ -327,13 +399,14 @@ struct queue_limits { * due to possible offsets. */ unsigned int dma_alignment; + unsigned int dma_pad_mask; + + struct blk_integrity integrity; }; typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx, void *data); -void disk_set_zoned(struct gendisk *disk); - #define BLK_ALL_ZONES ((unsigned int)-1) int blkdev_report_zones(struct block_device *bdev, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); @@ -414,10 +487,6 @@ struct request_queue { struct queue_limits limits; -#ifdef CONFIG_BLK_DEV_INTEGRITY - struct blk_integrity integrity; -#endif /* CONFIG_BLK_DEV_INTEGRITY */ - #ifdef CONFIG_PM struct device *dev; enum rpm_status rpm_status; @@ -439,8 +508,6 @@ struct request_queue { */ int id; - unsigned int dma_pad_mask; - /* * queue settings */ @@ -526,38 +593,20 @@ struct request_queue { #define QUEUE_FLAG_NOMERGES 3 /* disable merge attempts */ #define QUEUE_FLAG_SAME_COMP 4 /* complete on same CPU-group */ #define QUEUE_FLAG_FAIL_IO 5 /* fake timeout */ -#define QUEUE_FLAG_NONROT 6 /* non-rotational device (SSD) */ -#define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ -#define QUEUE_FLAG_IO_STAT 7 /* do disk/partitions IO accounting */ #define QUEUE_FLAG_NOXMERGES 9 /* No extended merges */ -#define QUEUE_FLAG_ADD_RANDOM 10 /* Contributes to random pool */ -#define QUEUE_FLAG_SYNCHRONOUS 11 /* always completes in submit context */ #define QUEUE_FLAG_SAME_FORCE 12 /* force complete on same CPU */ -#define QUEUE_FLAG_HW_WC 13 /* Write back caching supported */ #define QUEUE_FLAG_INIT_DONE 14 /* queue is initialized */ -#define QUEUE_FLAG_STABLE_WRITES 15 /* don't modify blks until WB is done */ -#define QUEUE_FLAG_POLL 16 /* IO polling enabled if set */ -#define QUEUE_FLAG_WC 17 /* Write back caching */ -#define QUEUE_FLAG_FUA 18 /* device supports FUA writes */ -#define QUEUE_FLAG_DAX 19 /* device supports DAX */ #define QUEUE_FLAG_STATS 20 /* track IO start and completion times */ #define QUEUE_FLAG_REGISTERED 22 /* queue has been registered to a disk */ #define QUEUE_FLAG_QUIESCED 24 /* queue has been quiesced */ -#define QUEUE_FLAG_PCI_P2PDMA 25 /* device supports PCI p2p requests */ -#define QUEUE_FLAG_ZONE_RESETALL 26 /* supports Zone Reset All */ #define QUEUE_FLAG_RQ_ALLOC_TIME 27 /* record rq->alloc_time_ns */ #define QUEUE_FLAG_HCTX_ACTIVE 28 /* at least one blk-mq hctx is active */ -#define QUEUE_FLAG_NOWAIT 29 /* device supports NOWAIT */ #define QUEUE_FLAG_SQ_SCHED 30 /* single queue style io dispatch */ -#define QUEUE_FLAG_SKIP_TAGSET_QUIESCE 31 /* quiesce_tagset skip the queue*/ -#define QUEUE_FLAG_MQ_DEFAULT ((1UL << QUEUE_FLAG_IO_STAT) | \ - (1UL << QUEUE_FLAG_SAME_COMP) | \ - (1UL << QUEUE_FLAG_NOWAIT)) +#define QUEUE_FLAG_MQ_DEFAULT (1UL << QUEUE_FLAG_SAME_COMP) void blk_queue_flag_set(unsigned int flag, struct request_queue *q); void blk_queue_flag_clear(unsigned int flag, struct request_queue *q); -bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); #define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags) #define blk_queue_dying(q) test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags) @@ -565,16 +614,10 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); #define blk_queue_nomerges(q) test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags) #define blk_queue_noxmerges(q) \ test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags) -#define blk_queue_nonrot(q) test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags) -#define blk_queue_stable_writes(q) \ - test_bit(QUEUE_FLAG_STABLE_WRITES, &(q)->queue_flags) -#define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags) -#define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags) -#define blk_queue_zone_resetall(q) \ - test_bit(QUEUE_FLAG_ZONE_RESETALL, &(q)->queue_flags) -#define blk_queue_dax(q) test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags) -#define blk_queue_pci_p2pdma(q) \ - test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags) +#define blk_queue_nonrot(q) (!((q)->limits.features & BLK_FEAT_ROTATIONAL)) +#define blk_queue_io_stat(q) ((q)->limits.features & BLK_FEAT_IO_STAT) +#define blk_queue_dax(q) ((q)->limits.features & BLK_FEAT_DAX) +#define blk_queue_pci_p2pdma(q) ((q)->limits.features & BLK_FEAT_PCI_P2PDMA) #ifdef CONFIG_BLK_RQ_ALLOC_TIME #define blk_queue_rq_alloc_time(q) \ test_bit(QUEUE_FLAG_RQ_ALLOC_TIME, &(q)->queue_flags) @@ -590,7 +633,7 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); #define blk_queue_registered(q) test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags) #define blk_queue_sq_sched(q) test_bit(QUEUE_FLAG_SQ_SCHED, &(q)->queue_flags) #define blk_queue_skip_tagset_quiesce(q) \ - test_bit(QUEUE_FLAG_SKIP_TAGSET_QUIESCE, &(q)->queue_flags) + ((q)->limits.features & BLK_FEAT_SKIP_TAGSET_QUIESCE) extern void blk_set_pm_only(struct request_queue *q); extern void blk_clear_pm_only(struct request_queue *q); @@ -620,16 +663,26 @@ static inline enum rpm_status queue_rpm_status(struct request_queue *q) static inline bool blk_queue_is_zoned(struct request_queue *q) { - return IS_ENABLED(CONFIG_BLK_DEV_ZONED) && q->limits.zoned; + return IS_ENABLED(CONFIG_BLK_DEV_ZONED) && + (q->limits.features & BLK_FEAT_ZONED); } #ifdef CONFIG_BLK_DEV_ZONED -unsigned int bdev_nr_zones(struct block_device *bdev); - static inline unsigned int disk_nr_zones(struct gendisk *disk) { - return blk_queue_is_zoned(disk->queue) ? disk->nr_zones : 0; + return disk->nr_zones; } +bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs); +#else /* CONFIG_BLK_DEV_ZONED */ +static inline unsigned int disk_nr_zones(struct gendisk *disk) +{ + return 0; +} +static inline bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs) +{ + return false; +} +#endif /* CONFIG_BLK_DEV_ZONED */ static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector) { @@ -638,16 +691,9 @@ static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector) return sector >> ilog2(disk->queue->limits.chunk_sectors); } -static inline void disk_set_max_open_zones(struct gendisk *disk, - unsigned int max_open_zones) +static inline unsigned int bdev_nr_zones(struct block_device *bdev) { - disk->queue->limits.max_open_zones = max_open_zones; -} - -static inline void disk_set_max_active_zones(struct gendisk *disk, - unsigned int max_active_zones) -{ - disk->queue->limits.max_active_zones = max_active_zones; + return disk_nr_zones(bdev->bd_disk); } static inline unsigned int bdev_max_open_zones(struct block_device *bdev) @@ -660,36 +706,6 @@ static inline unsigned int bdev_max_active_zones(struct block_device *bdev) return bdev->bd_disk->queue->limits.max_active_zones; } -bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs); -#else /* CONFIG_BLK_DEV_ZONED */ -static inline unsigned int bdev_nr_zones(struct block_device *bdev) -{ - return 0; -} - -static inline unsigned int disk_nr_zones(struct gendisk *disk) -{ - return 0; -} -static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector) -{ - return 0; -} -static inline unsigned int bdev_max_open_zones(struct block_device *bdev) -{ - return 0; -} - -static inline unsigned int bdev_max_active_zones(struct block_device *bdev) -{ - return 0; -} -static inline bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs) -{ - return false; -} -#endif /* CONFIG_BLK_DEV_ZONED */ - static inline unsigned int blk_queue_depth(struct request_queue *q) { if (q->queue_depth) @@ -880,14 +896,15 @@ static inline bool bio_straddles_zones(struct bio *bio) } /* - * Return how much of the chunk is left to be used for I/O at a given offset. + * Return how much within the boundary is left to be used for I/O at a given + * offset. */ -static inline unsigned int blk_chunk_sectors_left(sector_t offset, - unsigned int chunk_sectors) +static inline unsigned int blk_boundary_sectors_left(sector_t offset, + unsigned int boundary_sectors) { - if (unlikely(!is_power_of_2(chunk_sectors))) - return chunk_sectors - sector_div(offset, chunk_sectors); - return chunk_sectors - (offset & (chunk_sectors - 1)); + if (unlikely(!is_power_of_2(boundary_sectors))) + return boundary_sectors - sector_div(offset, boundary_sectors); + return boundary_sectors - (offset & (boundary_sectors - 1)); } /** @@ -904,7 +921,6 @@ static inline unsigned int blk_chunk_sectors_left(sector_t offset, */ static inline struct queue_limits queue_limits_start_update(struct request_queue *q) - __acquires(q->limits_lock) { mutex_lock(&q->limits_lock); return q->limits; @@ -926,27 +942,32 @@ static inline void queue_limits_cancel_update(struct request_queue *q) mutex_unlock(&q->limits_lock); } +/* + * These helpers are for drivers that have sloppy feature negotiation and might + * have to disable DISCARD, WRITE_ZEROES or SECURE_DISCARD from the I/O + * completion handler when the device returned an indicator that the respective + * feature is not actually supported. They are racy and the driver needs to + * cope with that. Try to avoid this scheme if you can. + */ +static inline void blk_queue_disable_discard(struct request_queue *q) +{ + q->limits.max_discard_sectors = 0; +} + +static inline void blk_queue_disable_secure_erase(struct request_queue *q) +{ + q->limits.max_secure_erase_sectors = 0; +} + +static inline void blk_queue_disable_write_zeroes(struct request_queue *q) +{ + q->limits.max_write_zeroes_sectors = 0; +} + /* * Access functions for manipulating queue properties */ -extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int); -void blk_queue_max_secure_erase_sectors(struct request_queue *q, - unsigned int max_sectors); -extern void blk_queue_max_discard_sectors(struct request_queue *q, - unsigned int max_discard_sectors); -extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q, - unsigned int max_write_same_sectors); -extern void blk_queue_logical_block_size(struct request_queue *, unsigned int); -extern void blk_queue_max_zone_append_sectors(struct request_queue *q, - unsigned int max_zone_append_sectors); -extern void blk_queue_physical_block_size(struct request_queue *, unsigned int); -void blk_queue_zone_write_granularity(struct request_queue *q, - unsigned int size); -extern void blk_queue_alignment_offset(struct request_queue *q, - unsigned int alignment); -void disk_update_readahead(struct gendisk *disk); extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min); -extern void blk_queue_io_min(struct request_queue *q, unsigned int min); extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt); extern void blk_set_queue_depth(struct request_queue *q, unsigned int depth); extern void blk_set_stacking_limits(struct queue_limits *lim); @@ -954,9 +975,7 @@ extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, sector_t offset); void queue_limits_stack_bdev(struct queue_limits *t, struct block_device *bdev, sector_t offset, const char *pfx); -extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); -extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua); struct blk_independent_access_ranges * disk_alloc_independent_access_ranges(struct gendisk *disk, int nr_ia_ranges); @@ -1077,6 +1096,7 @@ int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector, #define BLKDEV_ZERO_NOUNMAP (1 << 0) /* do not free blocks */ #define BLKDEV_ZERO_NOFALLBACK (1 << 1) /* don't write explicit zeroes */ +#define BLKDEV_ZERO_KILLABLE (1 << 2) /* interruptible by fatal signals */ extern int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct bio **biop, @@ -1204,12 +1224,7 @@ static inline unsigned int bdev_max_segments(struct block_device *bdev) static inline unsigned queue_logical_block_size(const struct request_queue *q) { - int retval = 512; - - if (q && q->limits.logical_block_size) - retval = q->limits.logical_block_size; - - return retval; + return q->limits.logical_block_size; } static inline unsigned int bdev_logical_block_size(struct block_device *bdev) @@ -1295,29 +1310,38 @@ static inline bool bdev_nonrot(struct block_device *bdev) static inline bool bdev_synchronous(struct block_device *bdev) { - return test_bit(QUEUE_FLAG_SYNCHRONOUS, - &bdev_get_queue(bdev)->queue_flags); + return bdev->bd_disk->queue->limits.features & BLK_FEAT_SYNCHRONOUS; } static inline bool bdev_stable_writes(struct block_device *bdev) { - return test_bit(QUEUE_FLAG_STABLE_WRITES, - &bdev_get_queue(bdev)->queue_flags); + struct request_queue *q = bdev_get_queue(bdev); + + if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) && + q->limits.integrity.csum_type != BLK_INTEGRITY_CSUM_NONE) + return true; + return q->limits.features & BLK_FEAT_STABLE_WRITES; +} + +static inline bool blk_queue_write_cache(struct request_queue *q) +{ + return (q->limits.features & BLK_FEAT_WRITE_CACHE) && + !(q->limits.flags & BLK_FLAG_WRITE_CACHE_DISABLED); } static inline bool bdev_write_cache(struct block_device *bdev) { - return test_bit(QUEUE_FLAG_WC, &bdev_get_queue(bdev)->queue_flags); + return blk_queue_write_cache(bdev_get_queue(bdev)); } static inline bool bdev_fua(struct block_device *bdev) { - return test_bit(QUEUE_FLAG_FUA, &bdev_get_queue(bdev)->queue_flags); + return bdev_get_queue(bdev)->limits.features & BLK_FEAT_FUA; } static inline bool bdev_nowait(struct block_device *bdev) { - return test_bit(QUEUE_FLAG_NOWAIT, &bdev_get_queue(bdev)->queue_flags); + return bdev->bd_disk->queue->limits.features & BLK_FEAT_NOWAIT; } static inline bool bdev_is_zoned(struct block_device *bdev) @@ -1359,7 +1383,31 @@ static inline bool bdev_is_zone_start(struct block_device *bdev, static inline int queue_dma_alignment(const struct request_queue *q) { - return q ? q->limits.dma_alignment : 511; + return q->limits.dma_alignment; +} + +static inline unsigned int +queue_atomic_write_unit_max_bytes(const struct request_queue *q) +{ + return q->limits.atomic_write_unit_max; +} + +static inline unsigned int +queue_atomic_write_unit_min_bytes(const struct request_queue *q) +{ + return q->limits.atomic_write_unit_min; +} + +static inline unsigned int +queue_atomic_write_boundary_bytes(const struct request_queue *q) +{ + return q->limits.atomic_write_boundary_sectors << SECTOR_SHIFT; +} + +static inline unsigned int +queue_atomic_write_max_bytes(const struct request_queue *q) +{ + return q->limits.atomic_write_max_sectors << SECTOR_SHIFT; } static inline unsigned int bdev_dma_alignment(struct block_device *bdev) @@ -1374,10 +1422,16 @@ static inline bool bdev_iter_is_aligned(struct block_device *bdev, bdev_logical_block_size(bdev) - 1); } +static inline int blk_lim_dma_alignment_and_pad(struct queue_limits *lim) +{ + return lim->dma_alignment | lim->dma_pad_mask; +} + static inline int blk_rq_aligned(struct request_queue *q, unsigned long addr, unsigned int len) { - unsigned int alignment = queue_dma_alignment(q) | q->dma_pad_mask; + unsigned int alignment = blk_lim_dma_alignment_and_pad(&q->limits); + return !(addr & alignment) && !(len & alignment); } @@ -1563,7 +1617,7 @@ int sync_blockdev(struct block_device *bdev); int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend); int sync_blockdev_nowait(struct block_device *bdev); void sync_bdevs(bool wait); -void bdev_statx_dioalign(struct inode *inode, struct kstat *stat); +void bdev_statx(struct path *, struct kstat *, u32); void printk_all_partitions(void); int __init early_lookup_bdev(const char *pathname, dev_t *dev); #else @@ -1581,7 +1635,8 @@ static inline int sync_blockdev_nowait(struct block_device *bdev) static inline void sync_bdevs(bool wait) { } -static inline void bdev_statx_dioalign(struct inode *inode, struct kstat *stat) +static inline void bdev_statx(struct path *path, struct kstat *stat, + u32 request_mask) { } static inline void printk_all_partitions(void) @@ -1603,6 +1658,27 @@ struct io_comp_batch { void (*complete)(struct io_comp_batch *); }; +static inline bool bdev_can_atomic_write(struct block_device *bdev) +{ + struct request_queue *bd_queue = bdev->bd_queue; + struct queue_limits *limits = &bd_queue->limits; + + if (!limits->atomic_write_unit_min) + return false; + + if (bdev_is_partition(bdev)) { + sector_t bd_start_sect = bdev->bd_start_sect; + unsigned int alignment = + max(limits->atomic_write_unit_min, + limits->atomic_write_hw_boundary); + + if (!IS_ALIGNED(bd_start_sect, alignment >> SECTOR_SHIFT)) + return false; + } + + return true; +} + #define DEFINE_IO_COMP_BATCH(name) struct io_comp_batch name = { } #endif /* _LINUX_BLKDEV_H */ diff --git a/include/linux/bvec.h b/include/linux/bvec.h index bd1e361b351c..f41c7f0ef91e 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -280,4 +280,18 @@ static inline void *bvec_virt(struct bio_vec *bvec) return page_address(bvec->bv_page) + bvec->bv_offset; } +/** + * bvec_phys - return the physical address for a bvec + * @bvec: bvec to return the physical address for + */ +static inline phys_addr_t bvec_phys(const struct bio_vec *bvec) +{ + /* + * Note this open codes page_to_phys because page_to_phys is defined in + * , which we don't want to pull in here. If it ever moves to + * a sensible place we should start using it. + */ + return PFN_PHYS(page_to_pfn(bvec->bv_page)) + bvec->bv_offset; +} + #endif /* __LINUX_BVEC_H */ diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 82b2195efaca..15d28164bbbd 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -357,6 +357,13 @@ struct dm_target { */ bool discards_supported:1; + /* + * Automatically set by dm-core if this target supports + * REQ_OP_ZONE_RESET_ALL. Otherwise, this operation will be emulated + * using REQ_OP_ZONE_RESET. Target drivers must not set this manually. + */ + bool zone_reset_all_supported:1; + /* * Set if this target requires that discards be split on * 'max_discard_sectors' boundaries. diff --git a/include/linux/fs.h b/include/linux/fs.h index dc9f9c4b2572..fd34b5755c0b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -125,8 +125,10 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define FMODE_EXEC ((__force fmode_t)(1 << 5)) /* File writes are restricted (block device specific) */ #define FMODE_WRITE_RESTRICTED ((__force fmode_t)(1 << 6)) +/* File supports atomic writes */ +#define FMODE_CAN_ATOMIC_WRITE ((__force fmode_t)(1 << 7)) -/* FMODE_* bits 7 to 8 */ +/* FMODE_* bit 8 */ /* 32bit hashes as llseek() offset (for directories) */ #define FMODE_32BITHASH ((__force fmode_t)(1 << 9)) @@ -317,6 +319,7 @@ struct readahead_control; #define IOCB_SYNC (__force int) RWF_SYNC #define IOCB_NOWAIT (__force int) RWF_NOWAIT #define IOCB_APPEND (__force int) RWF_APPEND +#define IOCB_ATOMIC (__force int) RWF_ATOMIC /* non-RWF related bits - start at 16 */ #define IOCB_EVENTFD (1 << 16) @@ -351,6 +354,7 @@ struct readahead_control; { IOCB_SYNC, "SYNC" }, \ { IOCB_NOWAIT, "NOWAIT" }, \ { IOCB_APPEND, "APPEND" }, \ + { IOCB_ATOMIC, "ATOMIC"}, \ { IOCB_EVENTFD, "EVENTFD"}, \ { IOCB_DIRECT, "DIRECT" }, \ { IOCB_WRITE, "WRITE" }, \ @@ -3254,6 +3258,9 @@ extern const struct inode_operations page_symlink_inode_operations; extern void kfree_link(void *); void generic_fillattr(struct mnt_idmap *, u32, struct inode *, struct kstat *); void generic_fill_statx_attr(struct inode *inode, struct kstat *stat); +void generic_fill_statx_atomic_writes(struct kstat *stat, + unsigned int unit_min, + unsigned int unit_max); extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int); extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int); void __inode_add_bytes(struct inode *inode, loff_t bytes); @@ -3430,7 +3437,8 @@ static inline int iocb_flags(struct file *file) return res; } -static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) +static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags, + int rw_type) { int kiocb_flags = 0; @@ -3449,6 +3457,12 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) return -EOPNOTSUPP; kiocb_flags |= IOCB_NOIO; } + if (flags & RWF_ATOMIC) { + if (rw_type != WRITE) + return -EOPNOTSUPP; + if (!(ki->ki_filp->f_mode & FMODE_CAN_ATOMIC_WRITE)) + return -EOPNOTSUPP; + } kiocb_flags |= (__force int) (flags & RWF_SUPPORTED); if (flags & RWF_SYNC) kiocb_flags |= IOCB_DSYNC; @@ -3643,4 +3657,6 @@ static inline bool vfs_empty_path(int dfd, const char __user *path) return !c; } +bool generic_atomic_write_valid(struct iov_iter *iter, loff_t pos); + #endif /* _LINUX_FS_H */ diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index 4109f1bd6128..89ea1ebd975a 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -920,6 +920,9 @@ struct nvmet_fc_target_port { * further references to hosthandle. * Entrypoint is Mandatory if the lldd calls nvmet_fc_invalidate_host(). * + * @host_traddr: called by the transport to retrieve the node name and + * port name of the host port address. + * * @max_hw_queues: indicates the maximum number of hw queues the LLDD * supports for cpu affinitization. * Value is Mandatory. Must be at least 1. @@ -975,6 +978,7 @@ struct nvmet_fc_target_template { void (*ls_abort)(struct nvmet_fc_target_port *targetport, void *hosthandle, struct nvmefc_ls_req *lsreq); void (*host_release)(void *hosthandle); + int (*host_traddr)(void *hosthandle, u64 *wwnn, u64 *wwpn); u32 max_hw_queues; u16 max_sgl_segments; diff --git a/include/linux/nvme.h b/include/linux/nvme.h index c693ac344ec0..c12a329dd463 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -25,6 +25,9 @@ #define NVME_NSID_ALL 0xffffffff +/* Special NSSR value, 'NVMe' */ +#define NVME_SUBSYS_RESET 0x4E564D65 + enum nvme_subsys_type { /* Referral to another discovery type target subsystem */ NVME_NQN_DISC = 1, @@ -1848,6 +1851,7 @@ enum { /* * Generic Command Status: */ + NVME_SCT_GENERIC = 0x0, NVME_SC_SUCCESS = 0x0, NVME_SC_INVALID_OPCODE = 0x1, NVME_SC_INVALID_FIELD = 0x2, @@ -1895,6 +1899,7 @@ enum { /* * Command Specific Status: */ + NVME_SCT_COMMAND_SPECIFIC = 0x100, NVME_SC_CQ_INVALID = 0x100, NVME_SC_QID_INVALID = 0x101, NVME_SC_QUEUE_SIZE = 0x102, @@ -1968,6 +1973,7 @@ enum { /* * Media and Data Integrity Errors: */ + NVME_SCT_MEDIA_ERROR = 0x200, NVME_SC_WRITE_FAULT = 0x280, NVME_SC_READ_ERROR = 0x281, NVME_SC_GUARD_CHECK = 0x282, @@ -1980,6 +1986,7 @@ enum { /* * Path-related Errors: */ + NVME_SCT_PATH = 0x300, NVME_SC_INTERNAL_PATH_ERROR = 0x300, NVME_SC_ANA_PERSISTENT_LOSS = 0x301, NVME_SC_ANA_INACCESSIBLE = 0x302, @@ -1988,11 +1995,17 @@ enum { NVME_SC_HOST_PATH_ERROR = 0x370, NVME_SC_HOST_ABORTED_CMD = 0x371, - NVME_SC_CRD = 0x1800, - NVME_SC_MORE = 0x2000, - NVME_SC_DNR = 0x4000, + NVME_SC_MASK = 0x00ff, /* Status Code */ + NVME_SCT_MASK = 0x0700, /* Status Code Type */ + NVME_SCT_SC_MASK = NVME_SCT_MASK | NVME_SC_MASK, + + NVME_STATUS_CRD = 0x1800, /* Command Retry Delayed */ + NVME_STATUS_MORE = 0x2000, + NVME_STATUS_DNR = 0x4000, /* Do Not Retry */ }; +#define NVME_SCT(status) ((status) >> 8 & 7) + struct nvme_completion { /* * Used by Admin and Fabrics commands to return data: diff --git a/include/linux/stat.h b/include/linux/stat.h index bf92441dbad2..3d900c86981c 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -54,6 +54,9 @@ struct kstat { u32 dio_offset_align; u64 change_cookie; u64 subvol; + u32 atomic_write_unit_min; + u32 atomic_write_unit_max; + u32 atomic_write_segments_max; }; /* These definitions are internal to the kernel for now. Mainly used by nfsd. */ diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h index 248f4ac95642..2c59fe3efcd4 100644 --- a/include/linux/t10-pi.h +++ b/include/linux/t10-pi.h @@ -41,18 +41,12 @@ static inline u32 t10_pi_ref_tag(struct request *rq) { unsigned int shift = ilog2(queue_logical_block_size(rq->q)); -#ifdef CONFIG_BLK_DEV_INTEGRITY - if (rq->q->integrity.interval_exp) - shift = rq->q->integrity.interval_exp; -#endif + if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) && + rq->q->limits.integrity.interval_exp) + shift = rq->q->limits.integrity.interval_exp; return blk_rq_pos(rq) >> (shift - SECTOR_SHIFT) & 0xffffffff; } -extern const struct blk_integrity_profile t10_pi_type1_crc; -extern const struct blk_integrity_profile t10_pi_type1_ip; -extern const struct blk_integrity_profile t10_pi_type3_crc; -extern const struct blk_integrity_profile t10_pi_type3_ip; - struct crc64_pi_tuple { __be64 guard_tag; __be16 app_tag; @@ -72,14 +66,10 @@ static inline u64 ext_pi_ref_tag(struct request *rq) { unsigned int shift = ilog2(queue_logical_block_size(rq->q)); -#ifdef CONFIG_BLK_DEV_INTEGRITY - if (rq->q->integrity.interval_exp) - shift = rq->q->integrity.interval_exp; -#endif + if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) && + rq->q->limits.integrity.interval_exp) + shift = rq->q->limits.integrity.interval_exp; return lower_48_bits(blk_rq_pos(rq) >> (shift - SECTOR_SHIFT)); } -extern const struct blk_integrity_profile ext_pi_type1_crc64; -extern const struct blk_integrity_profile ext_pi_type3_crc64; - #endif diff --git a/include/scsi/scsi_proto.h b/include/scsi/scsi_proto.h index 843106e1109f..70e1262b2e20 100644 --- a/include/scsi/scsi_proto.h +++ b/include/scsi/scsi_proto.h @@ -120,6 +120,7 @@ #define WRITE_SAME_16 0x93 #define ZBC_OUT 0x94 #define ZBC_IN 0x95 +#define WRITE_ATOMIC_16 0x9c #define SERVICE_ACTION_BIDIRECTIONAL 0x9d #define SERVICE_ACTION_IN_16 0x9e #define SERVICE_ACTION_OUT_16 0x9f diff --git a/include/trace/events/block.h b/include/trace/events/block.h index 0e128ad51460..1527d5d45e01 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -9,9 +9,17 @@ #include #include #include +#include #define RWBS_LEN 8 +#define IOPRIO_CLASS_STRINGS \ + { IOPRIO_CLASS_NONE, "none" }, \ + { IOPRIO_CLASS_RT, "rt" }, \ + { IOPRIO_CLASS_BE, "be" }, \ + { IOPRIO_CLASS_IDLE, "idle" }, \ + { IOPRIO_CLASS_INVALID, "invalid"} + #ifdef CONFIG_BUFFER_HEAD DECLARE_EVENT_CLASS(block_buffer, @@ -82,6 +90,7 @@ TRACE_EVENT(block_rq_requeue, __field( dev_t, dev ) __field( sector_t, sector ) __field( unsigned int, nr_sector ) + __field( unsigned short, ioprio ) __array( char, rwbs, RWBS_LEN ) __dynamic_array( char, cmd, 1 ) ), @@ -90,16 +99,20 @@ TRACE_EVENT(block_rq_requeue, __entry->dev = rq->q->disk ? disk_devt(rq->q->disk) : 0; __entry->sector = blk_rq_trace_sector(rq); __entry->nr_sector = blk_rq_trace_nr_sectors(rq); + __entry->ioprio = rq->ioprio; blk_fill_rwbs(__entry->rwbs, rq->cmd_flags); __get_str(cmd)[0] = '\0'; ), - TP_printk("%d,%d %s (%s) %llu + %u [%d]", + TP_printk("%d,%d %s (%s) %llu + %u %s,%u,%u [%d]", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs, __get_str(cmd), - (unsigned long long)__entry->sector, - __entry->nr_sector, 0) + (unsigned long long)__entry->sector, __entry->nr_sector, + __print_symbolic(IOPRIO_PRIO_CLASS(__entry->ioprio), + IOPRIO_CLASS_STRINGS), + IOPRIO_PRIO_HINT(__entry->ioprio), + IOPRIO_PRIO_LEVEL(__entry->ioprio), 0) ); DECLARE_EVENT_CLASS(block_rq_completion, @@ -113,6 +126,7 @@ DECLARE_EVENT_CLASS(block_rq_completion, __field( sector_t, sector ) __field( unsigned int, nr_sector ) __field( int , error ) + __field( unsigned short, ioprio ) __array( char, rwbs, RWBS_LEN ) __dynamic_array( char, cmd, 1 ) ), @@ -122,16 +136,20 @@ DECLARE_EVENT_CLASS(block_rq_completion, __entry->sector = blk_rq_pos(rq); __entry->nr_sector = nr_bytes >> 9; __entry->error = blk_status_to_errno(error); + __entry->ioprio = rq->ioprio; blk_fill_rwbs(__entry->rwbs, rq->cmd_flags); __get_str(cmd)[0] = '\0'; ), - TP_printk("%d,%d %s (%s) %llu + %u [%d]", + TP_printk("%d,%d %s (%s) %llu + %u %s,%u,%u [%d]", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs, __get_str(cmd), - (unsigned long long)__entry->sector, - __entry->nr_sector, __entry->error) + (unsigned long long)__entry->sector, __entry->nr_sector, + __print_symbolic(IOPRIO_PRIO_CLASS(__entry->ioprio), + IOPRIO_CLASS_STRINGS), + IOPRIO_PRIO_HINT(__entry->ioprio), + IOPRIO_PRIO_LEVEL(__entry->ioprio), __entry->error) ); /** @@ -180,6 +198,7 @@ DECLARE_EVENT_CLASS(block_rq, __field( sector_t, sector ) __field( unsigned int, nr_sector ) __field( unsigned int, bytes ) + __field( unsigned short, ioprio ) __array( char, rwbs, RWBS_LEN ) __array( char, comm, TASK_COMM_LEN ) __dynamic_array( char, cmd, 1 ) @@ -190,17 +209,21 @@ DECLARE_EVENT_CLASS(block_rq, __entry->sector = blk_rq_trace_sector(rq); __entry->nr_sector = blk_rq_trace_nr_sectors(rq); __entry->bytes = blk_rq_bytes(rq); + __entry->ioprio = rq->ioprio; blk_fill_rwbs(__entry->rwbs, rq->cmd_flags); __get_str(cmd)[0] = '\0'; memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), - TP_printk("%d,%d %s %u (%s) %llu + %u [%s]", + TP_printk("%d,%d %s %u (%s) %llu + %u %s,%u,%u [%s]", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs, __entry->bytes, __get_str(cmd), - (unsigned long long)__entry->sector, - __entry->nr_sector, __entry->comm) + (unsigned long long)__entry->sector, __entry->nr_sector, + __print_symbolic(IOPRIO_PRIO_CLASS(__entry->ioprio), + IOPRIO_CLASS_STRINGS), + IOPRIO_PRIO_HINT(__entry->ioprio), + IOPRIO_PRIO_LEVEL(__entry->ioprio), __entry->comm) ); /** diff --git a/include/trace/events/scsi.h b/include/trace/events/scsi.h index 8e2d9b1b0e77..05f1945ed204 100644 --- a/include/trace/events/scsi.h +++ b/include/trace/events/scsi.h @@ -102,6 +102,7 @@ scsi_opcode_name(WRITE_32), \ scsi_opcode_name(WRITE_SAME_32), \ scsi_opcode_name(ATA_16), \ + scsi_opcode_name(WRITE_ATOMIC_16), \ scsi_opcode_name(ATA_12)) #define scsi_hostbyte_name(result) { result, #result } diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 45e4e64fd664..191a7e88a8ab 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -329,9 +329,12 @@ typedef int __bitwise __kernel_rwf_t; /* per-IO negation of O_APPEND */ #define RWF_NOAPPEND ((__force __kernel_rwf_t)0x00000020) +/* Atomic Write */ +#define RWF_ATOMIC ((__force __kernel_rwf_t)0x00000040) + /* mask of flags supported by the kernel */ #define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\ - RWF_APPEND | RWF_NOAPPEND) + RWF_APPEND | RWF_NOAPPEND | RWF_ATOMIC) /* Pagemap ioctl */ #define PAGEMAP_SCAN _IOWR('f', 16, struct pm_scan_arg) diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h index 95770941ee2c..887a25286441 100644 --- a/include/uapi/linux/stat.h +++ b/include/uapi/linux/stat.h @@ -128,7 +128,13 @@ struct statx { __u32 stx_dio_offset_align; /* File offset alignment for direct I/O */ /* 0xa0 */ __u64 stx_subvol; /* Subvolume identifier */ - __u64 __spare3[11]; /* Spare space for future expansion */ + __u32 stx_atomic_write_unit_min; /* Min atomic write unit in bytes */ + __u32 stx_atomic_write_unit_max; /* Max atomic write unit in bytes */ + /* 0xb0 */ + __u32 stx_atomic_write_segments_max; /* Max atomic write segment count */ + __u32 __spare1[1]; + /* 0xb8 */ + __u64 __spare3[9]; /* Spare space for future expansion */ /* 0x100 */ }; @@ -157,6 +163,7 @@ struct statx { #define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */ #define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */ #define STATX_SUBVOL 0x00008000U /* Want/got stx_subvol */ +#define STATX_WRITE_ATOMIC 0x00010000U /* Want/got atomic_write_* fields */ #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ @@ -192,6 +199,7 @@ struct statx { #define STATX_ATTR_MOUNT_ROOT 0x00002000 /* Root of a mount */ #define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */ #define STATX_ATTR_DAX 0x00200000 /* File is currently in DAX state */ +#define STATX_ATTR_WRITE_ATOMIC 0x00400000 /* File supports atomic write operations */ #endif /* _UAPI_LINUX_STAT_H */ diff --git a/io_uring/rw.c b/io_uring/rw.c index 1a2128459cb4..c004d21e2f12 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -772,7 +772,7 @@ static bool need_complete_io(struct io_kiocb *req) S_ISBLK(file_inode(req->file)->i_mode); } -static int io_rw_init_file(struct io_kiocb *req, fmode_t mode) +static int io_rw_init_file(struct io_kiocb *req, fmode_t mode, int rw_type) { struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw); struct kiocb *kiocb = &rw->kiocb; @@ -787,7 +787,7 @@ static int io_rw_init_file(struct io_kiocb *req, fmode_t mode) req->flags |= io_file_get_flags(file); kiocb->ki_flags = file->f_iocb_flags; - ret = kiocb_set_rw_flags(kiocb, rw->flags); + ret = kiocb_set_rw_flags(kiocb, rw->flags, rw_type); if (unlikely(ret)) return ret; kiocb->ki_flags |= IOCB_ALLOC_CACHE; @@ -832,8 +832,7 @@ static int __io_read(struct io_kiocb *req, unsigned int issue_flags) if (unlikely(ret < 0)) return ret; } - - ret = io_rw_init_file(req, FMODE_READ); + ret = io_rw_init_file(req, FMODE_READ, READ); if (unlikely(ret)) return ret; req->cqe.res = iov_iter_count(&io->iter); @@ -1013,7 +1012,7 @@ int io_write(struct io_kiocb *req, unsigned int issue_flags) ssize_t ret, ret2; loff_t *ppos; - ret = io_rw_init_file(req, FMODE_WRITE); + ret = io_rw_init_file(req, FMODE_WRITE, WRITE); if (unlikely(ret)) return ret; req->cqe.res = iov_iter_count(&io->iter); diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h index ddb5644d4fd9..6deee85a29c8 100644 --- a/rust/bindings/bindings_helper.h +++ b/rust/bindings/bindings_helper.h @@ -7,6 +7,9 @@ */ #include +#include +#include +#include #include #include #include @@ -20,8 +23,10 @@ /* `bindgen` gets confused at certain things. */ const size_t RUST_CONST_HELPER_ARCH_SLAB_MINALIGN = ARCH_SLAB_MINALIGN; +const size_t RUST_CONST_HELPER_PAGE_SIZE = PAGE_SIZE; const gfp_t RUST_CONST_HELPER_GFP_ATOMIC = GFP_ATOMIC; const gfp_t RUST_CONST_HELPER_GFP_KERNEL = GFP_KERNEL; const gfp_t RUST_CONST_HELPER_GFP_KERNEL_ACCOUNT = GFP_KERNEL_ACCOUNT; const gfp_t RUST_CONST_HELPER_GFP_NOWAIT = GFP_NOWAIT; const gfp_t RUST_CONST_HELPER___GFP_ZERO = __GFP_ZERO; +const blk_features_t RUST_CONST_HELPER_BLK_FEAT_ROTATIONAL = BLK_FEAT_ROTATIONAL; diff --git a/rust/helpers.c b/rust/helpers.c index 2c37a0f5d7a8..3df5217fb2ff 100644 --- a/rust/helpers.c +++ b/rust/helpers.c @@ -186,3 +186,19 @@ static_assert( __alignof__(size_t) == __alignof__(uintptr_t), "Rust code expects C `size_t` to match Rust `usize`" ); + +// This will soon be moved to a separate file, so no need to merge with above. +#include +#include + +void *rust_helper_blk_mq_rq_to_pdu(struct request *rq) +{ + return blk_mq_rq_to_pdu(rq); +} +EXPORT_SYMBOL_GPL(rust_helper_blk_mq_rq_to_pdu); + +struct request *rust_helper_blk_mq_rq_from_pdu(void *pdu) +{ + return blk_mq_rq_from_pdu(pdu); +} +EXPORT_SYMBOL_GPL(rust_helper_blk_mq_rq_from_pdu); diff --git a/rust/kernel/block.rs b/rust/kernel/block.rs new file mode 100644 index 000000000000..150f710efe5b --- /dev/null +++ b/rust/kernel/block.rs @@ -0,0 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Types for working with the block layer. + +pub mod mq; diff --git a/rust/kernel/block/mq.rs b/rust/kernel/block/mq.rs new file mode 100644 index 000000000000..fb0f393c1cea --- /dev/null +++ b/rust/kernel/block/mq.rs @@ -0,0 +1,98 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! This module provides types for implementing block drivers that interface the +//! blk-mq subsystem. +//! +//! To implement a block device driver, a Rust module must do the following: +//! +//! - Implement [`Operations`] for a type `T`. +//! - Create a [`TagSet`]. +//! - Create a [`GenDisk`], via the [`GenDiskBuilder`]. +//! - Add the disk to the system by calling [`GenDiskBuilder::build`] passing in +//! the `TagSet` reference. +//! +//! The types available in this module that have direct C counterparts are: +//! +//! - The [`TagSet`] type that abstracts the C type `struct tag_set`. +//! - The [`GenDisk`] type that abstracts the C type `struct gendisk`. +//! - The [`Request`] type that abstracts the C type `struct request`. +//! +//! The kernel will interface with the block device driver by calling the method +//! implementations of the `Operations` trait. +//! +//! IO requests are passed to the driver as [`kernel::types::ARef`] +//! instances. The `Request` type is a wrapper around the C `struct request`. +//! The driver must mark end of processing by calling one of the +//! `Request::end`, methods. Failure to do so can lead to deadlock or timeout +//! errors. Please note that the C function `blk_mq_start_request` is implicitly +//! called when the request is queued with the driver. +//! +//! The `TagSet` is responsible for creating and maintaining a mapping between +//! `Request`s and integer ids as well as carrying a pointer to the vtable +//! generated by `Operations`. This mapping is useful for associating +//! completions from hardware with the correct `Request` instance. The `TagSet` +//! determines the maximum queue depth by setting the number of `Request` +//! instances available to the driver, and it determines the number of queues to +//! instantiate for the driver. If possible, a driver should allocate one queue +//! per core, to keep queue data local to a core. +//! +//! One `TagSet` instance can be shared between multiple `GenDisk` instances. +//! This can be useful when implementing drivers where one piece of hardware +//! with one set of IO resources are represented to the user as multiple disks. +//! +//! One significant difference between block device drivers implemented with +//! these Rust abstractions and drivers implemented in C, is that the Rust +//! drivers have to own a reference count on the `Request` type when the IO is +//! in flight. This is to ensure that the C `struct request` instances backing +//! the Rust `Request` instances are live while the Rust driver holds a +//! reference to the `Request`. In addition, the conversion of an integer tag to +//! a `Request` via the `TagSet` would not be sound without this bookkeeping. +//! +//! [`GenDisk`]: gen_disk::GenDisk +//! [`GenDisk`]: gen_disk::GenDisk +//! [`GenDiskBuilder`]: gen_disk::GenDiskBuilder +//! [`GenDiskBuilder::build`]: gen_disk::GenDiskBuilder::build +//! +//! # Example +//! +//! ```rust +//! use kernel::{ +//! alloc::flags, +//! block::mq::*, +//! new_mutex, +//! prelude::*, +//! sync::{Arc, Mutex}, +//! types::{ARef, ForeignOwnable}, +//! }; +//! +//! struct MyBlkDevice; +//! +//! #[vtable] +//! impl Operations for MyBlkDevice { +//! +//! fn queue_rq(rq: ARef>, _is_last: bool) -> Result { +//! Request::end_ok(rq); +//! Ok(()) +//! } +//! +//! fn commit_rqs() {} +//! } +//! +//! let tagset: Arc> = +//! Arc::pin_init(TagSet::new(1, 256, 1), flags::GFP_KERNEL)?; +//! let mut disk = gen_disk::GenDiskBuilder::new() +//! .capacity_sectors(4096) +//! .build(format_args!("myblk"), tagset)?; +//! +//! # Ok::<(), kernel::error::Error>(()) +//! ``` + +pub mod gen_disk; +mod operations; +mod raw_writer; +mod request; +mod tag_set; + +pub use operations::Operations; +pub use request::Request; +pub use tag_set::TagSet; diff --git a/rust/kernel/block/mq/gen_disk.rs b/rust/kernel/block/mq/gen_disk.rs new file mode 100644 index 000000000000..f548a6199847 --- /dev/null +++ b/rust/kernel/block/mq/gen_disk.rs @@ -0,0 +1,198 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Generic disk abstraction. +//! +//! C header: [`include/linux/blkdev.h`](srctree/include/linux/blkdev.h) +//! C header: [`include/linux/blk_mq.h`](srctree/include/linux/blk_mq.h) + +use crate::block::mq::{raw_writer::RawWriter, Operations, TagSet}; +use crate::error; +use crate::{bindings, error::from_err_ptr, error::Result, sync::Arc}; +use core::fmt::{self, Write}; + +/// A builder for [`GenDisk`]. +/// +/// Use this struct to configure and add new [`GenDisk`] to the VFS. +pub struct GenDiskBuilder { + rotational: bool, + logical_block_size: u32, + physical_block_size: u32, + capacity_sectors: u64, +} + +impl Default for GenDiskBuilder { + fn default() -> Self { + Self { + rotational: false, + logical_block_size: bindings::PAGE_SIZE as u32, + physical_block_size: bindings::PAGE_SIZE as u32, + capacity_sectors: 0, + } + } +} + +impl GenDiskBuilder { + /// Create a new instance. + pub fn new() -> Self { + Self::default() + } + + /// Set the rotational media attribute for the device to be built. + pub fn rotational(mut self, rotational: bool) -> Self { + self.rotational = rotational; + self + } + + /// Validate block size by verifying that it is between 512 and `PAGE_SIZE`, + /// and that it is a power of two. + fn validate_block_size(size: u32) -> Result<()> { + if !(512..=bindings::PAGE_SIZE as u32).contains(&size) || !size.is_power_of_two() { + Err(error::code::EINVAL) + } else { + Ok(()) + } + } + + /// Set the logical block size of the device to be built. + /// + /// This method will check that block size is a power of two and between 512 + /// and 4096. If not, an error is returned and the block size is not set. + /// + /// This is the smallest unit the storage device can address. It is + /// typically 4096 bytes. + pub fn logical_block_size(mut self, block_size: u32) -> Result { + Self::validate_block_size(block_size)?; + self.logical_block_size = block_size; + Ok(self) + } + + /// Set the physical block size of the device to be built. + /// + /// This method will check that block size is a power of two and between 512 + /// and 4096. If not, an error is returned and the block size is not set. + /// + /// This is the smallest unit a physical storage device can write + /// atomically. It is usually the same as the logical block size but may be + /// bigger. One example is SATA drives with 4096 byte physical block size + /// that expose a 512 byte logical block size to the operating system. + pub fn physical_block_size(mut self, block_size: u32) -> Result { + Self::validate_block_size(block_size)?; + self.physical_block_size = block_size; + Ok(self) + } + + /// Set the capacity of the device to be built, in sectors (512 bytes). + pub fn capacity_sectors(mut self, capacity: u64) -> Self { + self.capacity_sectors = capacity; + self + } + + /// Build a new `GenDisk` and add it to the VFS. + pub fn build( + self, + name: fmt::Arguments<'_>, + tagset: Arc>, + ) -> Result> { + let lock_class_key = crate::sync::LockClassKey::new(); + + // SAFETY: `bindings::queue_limits` contain only fields that are valid when zeroed. + let mut lim: bindings::queue_limits = unsafe { core::mem::zeroed() }; + + lim.logical_block_size = self.logical_block_size; + lim.physical_block_size = self.physical_block_size; + if self.rotational { + lim.features = bindings::BLK_FEAT_ROTATIONAL; + } + + // SAFETY: `tagset.raw_tag_set()` points to a valid and initialized tag set + let gendisk = from_err_ptr(unsafe { + bindings::__blk_mq_alloc_disk( + tagset.raw_tag_set(), + &mut lim, + core::ptr::null_mut(), + lock_class_key.as_ptr(), + ) + })?; + + const TABLE: bindings::block_device_operations = bindings::block_device_operations { + submit_bio: None, + open: None, + release: None, + ioctl: None, + compat_ioctl: None, + check_events: None, + unlock_native_capacity: None, + getgeo: None, + set_read_only: None, + swap_slot_free_notify: None, + report_zones: None, + devnode: None, + alternative_gpt_sector: None, + get_unique_id: None, + // TODO: Set to THIS_MODULE. Waiting for const_refs_to_static feature to + // be merged (unstable in rustc 1.78 which is staged for linux 6.10) + // https://github.com/rust-lang/rust/issues/119618 + owner: core::ptr::null_mut(), + pr_ops: core::ptr::null_mut(), + free_disk: None, + poll_bio: None, + }; + + // SAFETY: `gendisk` is a valid pointer as we initialized it above + unsafe { (*gendisk).fops = &TABLE }; + + let mut raw_writer = RawWriter::from_array( + // SAFETY: `gendisk` points to a valid and initialized instance. We + // have exclusive access, since the disk is not added to the VFS + // yet. + unsafe { &mut (*gendisk).disk_name }, + )?; + raw_writer.write_fmt(name)?; + raw_writer.write_char('\0')?; + + // SAFETY: `gendisk` points to a valid and initialized instance of + // `struct gendisk`. `set_capacity` takes a lock to synchronize this + // operation, so we will not race. + unsafe { bindings::set_capacity(gendisk, self.capacity_sectors) }; + + crate::error::to_result( + // SAFETY: `gendisk` points to a valid and initialized instance of + // `struct gendisk`. + unsafe { + bindings::device_add_disk(core::ptr::null_mut(), gendisk, core::ptr::null_mut()) + }, + )?; + + // INVARIANT: `gendisk` was initialized above. + // INVARIANT: `gendisk` was added to the VFS via `device_add_disk` above. + Ok(GenDisk { + _tagset: tagset, + gendisk, + }) + } +} + +/// A generic block device. +/// +/// # Invariants +/// +/// - `gendisk` must always point to an initialized and valid `struct gendisk`. +/// - `gendisk` was added to the VFS through a call to +/// `bindings::device_add_disk`. +pub struct GenDisk { + _tagset: Arc>, + gendisk: *mut bindings::gendisk, +} + +// SAFETY: `GenDisk` is an owned pointer to a `struct gendisk` and an `Arc` to a +// `TagSet` It is safe to send this to other threads as long as T is Send. +unsafe impl Send for GenDisk {} + +impl Drop for GenDisk { + fn drop(&mut self) { + // SAFETY: By type invariant, `self.gendisk` points to a valid and + // initialized instance of `struct gendisk`, and it was previously added + // to the VFS. + unsafe { bindings::del_gendisk(self.gendisk) }; + } +} diff --git a/rust/kernel/block/mq/operations.rs b/rust/kernel/block/mq/operations.rs new file mode 100644 index 000000000000..9ba7fdfeb4b2 --- /dev/null +++ b/rust/kernel/block/mq/operations.rs @@ -0,0 +1,245 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! This module provides an interface for blk-mq drivers to implement. +//! +//! C header: [`include/linux/blk-mq.h`](srctree/include/linux/blk-mq.h) + +use crate::{ + bindings, + block::mq::request::RequestDataWrapper, + block::mq::Request, + error::{from_result, Result}, + types::ARef, +}; +use core::{marker::PhantomData, sync::atomic::AtomicU64, sync::atomic::Ordering}; + +/// Implement this trait to interface blk-mq as block devices. +/// +/// To implement a block device driver, implement this trait as described in the +/// [module level documentation]. The kernel will use the implementation of the +/// functions defined in this trait to interface a block device driver. Note: +/// There is no need for an exit_request() implementation, because the `drop` +/// implementation of the [`Request`] type will be invoked by automatically by +/// the C/Rust glue logic. +/// +/// [module level documentation]: kernel::block::mq +#[macros::vtable] +pub trait Operations: Sized { + /// Called by the kernel to queue a request with the driver. If `is_last` is + /// `false`, the driver is allowed to defer committing the request. + fn queue_rq(rq: ARef>, is_last: bool) -> Result; + + /// Called by the kernel to indicate that queued requests should be submitted. + fn commit_rqs(); + + /// Called by the kernel to poll the device for completed requests. Only + /// used for poll queues. + fn poll() -> bool { + crate::build_error(crate::error::VTABLE_DEFAULT_ERROR) + } +} + +/// A vtable for blk-mq to interact with a block device driver. +/// +/// A `bindings::blk_mq_ops` vtable is constructed from pointers to the `extern +/// "C"` functions of this struct, exposed through the `OperationsVTable::VTABLE`. +/// +/// For general documentation of these methods, see the kernel source +/// documentation related to `struct blk_mq_operations` in +/// [`include/linux/blk-mq.h`]. +/// +/// [`include/linux/blk-mq.h`]: srctree/include/linux/blk-mq.h +pub(crate) struct OperationsVTable(PhantomData); + +impl OperationsVTable { + /// This function is called by the C kernel. A pointer to this function is + /// installed in the `blk_mq_ops` vtable for the driver. + /// + /// # Safety + /// + /// - The caller of this function must ensure that the pointee of `bd` is + /// valid for reads for the duration of this function. + /// - This function must be called for an initialized and live `hctx`. That + /// is, `Self::init_hctx_callback` was called and + /// `Self::exit_hctx_callback()` was not yet called. + /// - `(*bd).rq` must point to an initialized and live `bindings:request`. + /// That is, `Self::init_request_callback` was called but + /// `Self::exit_request_callback` was not yet called for the request. + /// - `(*bd).rq` must be owned by the driver. That is, the block layer must + /// promise to not access the request until the driver calls + /// `bindings::blk_mq_end_request` for the request. + unsafe extern "C" fn queue_rq_callback( + _hctx: *mut bindings::blk_mq_hw_ctx, + bd: *const bindings::blk_mq_queue_data, + ) -> bindings::blk_status_t { + // SAFETY: `bd.rq` is valid as required by the safety requirement for + // this function. + let request = unsafe { &*(*bd).rq.cast::>() }; + + // One refcount for the ARef, one for being in flight + request.wrapper_ref().refcount().store(2, Ordering::Relaxed); + + // SAFETY: + // - We own a refcount that we took above. We pass that to `ARef`. + // - By the safety requirements of this function, `request` is a valid + // `struct request` and the private data is properly initialized. + // - `rq` will be alive until `blk_mq_end_request` is called and is + // reference counted by `ARef` until then. + let rq = unsafe { Request::aref_from_raw((*bd).rq) }; + + // SAFETY: We have exclusive access and we just set the refcount above. + unsafe { Request::start_unchecked(&rq) }; + + let ret = T::queue_rq( + rq, + // SAFETY: `bd` is valid as required by the safety requirement for + // this function. + unsafe { (*bd).last }, + ); + + if let Err(e) = ret { + e.to_blk_status() + } else { + bindings::BLK_STS_OK as _ + } + } + + /// This function is called by the C kernel. A pointer to this function is + /// installed in the `blk_mq_ops` vtable for the driver. + /// + /// # Safety + /// + /// This function may only be called by blk-mq C infrastructure. + unsafe extern "C" fn commit_rqs_callback(_hctx: *mut bindings::blk_mq_hw_ctx) { + T::commit_rqs() + } + + /// This function is called by the C kernel. It is not currently + /// implemented, and there is no way to exercise this code path. + /// + /// # Safety + /// + /// This function may only be called by blk-mq C infrastructure. + unsafe extern "C" fn complete_callback(_rq: *mut bindings::request) {} + + /// This function is called by the C kernel. A pointer to this function is + /// installed in the `blk_mq_ops` vtable for the driver. + /// + /// # Safety + /// + /// This function may only be called by blk-mq C infrastructure. + unsafe extern "C" fn poll_callback( + _hctx: *mut bindings::blk_mq_hw_ctx, + _iob: *mut bindings::io_comp_batch, + ) -> core::ffi::c_int { + T::poll().into() + } + + /// This function is called by the C kernel. A pointer to this function is + /// installed in the `blk_mq_ops` vtable for the driver. + /// + /// # Safety + /// + /// This function may only be called by blk-mq C infrastructure. This + /// function may only be called once before `exit_hctx_callback` is called + /// for the same context. + unsafe extern "C" fn init_hctx_callback( + _hctx: *mut bindings::blk_mq_hw_ctx, + _tagset_data: *mut core::ffi::c_void, + _hctx_idx: core::ffi::c_uint, + ) -> core::ffi::c_int { + from_result(|| Ok(0)) + } + + /// This function is called by the C kernel. A pointer to this function is + /// installed in the `blk_mq_ops` vtable for the driver. + /// + /// # Safety + /// + /// This function may only be called by blk-mq C infrastructure. + unsafe extern "C" fn exit_hctx_callback( + _hctx: *mut bindings::blk_mq_hw_ctx, + _hctx_idx: core::ffi::c_uint, + ) { + } + + /// This function is called by the C kernel. A pointer to this function is + /// installed in the `blk_mq_ops` vtable for the driver. + /// + /// # Safety + /// + /// - This function may only be called by blk-mq C infrastructure. + /// - `_set` must point to an initialized `TagSet`. + /// - `rq` must point to an initialized `bindings::request`. + /// - The allocation pointed to by `rq` must be at the size of `Request` + /// plus the size of `RequestDataWrapper`. + unsafe extern "C" fn init_request_callback( + _set: *mut bindings::blk_mq_tag_set, + rq: *mut bindings::request, + _hctx_idx: core::ffi::c_uint, + _numa_node: core::ffi::c_uint, + ) -> core::ffi::c_int { + from_result(|| { + // SAFETY: By the safety requirements of this function, `rq` points + // to a valid allocation. + let pdu = unsafe { Request::wrapper_ptr(rq.cast::>()) }; + + // SAFETY: The refcount field is allocated but not initialized, so + // it is valid for writes. + unsafe { RequestDataWrapper::refcount_ptr(pdu.as_ptr()).write(AtomicU64::new(0)) }; + + Ok(0) + }) + } + + /// This function is called by the C kernel. A pointer to this function is + /// installed in the `blk_mq_ops` vtable for the driver. + /// + /// # Safety + /// + /// - This function may only be called by blk-mq C infrastructure. + /// - `_set` must point to an initialized `TagSet`. + /// - `rq` must point to an initialized and valid `Request`. + unsafe extern "C" fn exit_request_callback( + _set: *mut bindings::blk_mq_tag_set, + rq: *mut bindings::request, + _hctx_idx: core::ffi::c_uint, + ) { + // SAFETY: The tagset invariants guarantee that all requests are allocated with extra memory + // for the request data. + let pdu = unsafe { bindings::blk_mq_rq_to_pdu(rq) }.cast::(); + + // SAFETY: `pdu` is valid for read and write and is properly initialised. + unsafe { core::ptr::drop_in_place(pdu) }; + } + + const VTABLE: bindings::blk_mq_ops = bindings::blk_mq_ops { + queue_rq: Some(Self::queue_rq_callback), + queue_rqs: None, + commit_rqs: Some(Self::commit_rqs_callback), + get_budget: None, + put_budget: None, + set_rq_budget_token: None, + get_rq_budget_token: None, + timeout: None, + poll: if T::HAS_POLL { + Some(Self::poll_callback) + } else { + None + }, + complete: Some(Self::complete_callback), + init_hctx: Some(Self::init_hctx_callback), + exit_hctx: Some(Self::exit_hctx_callback), + init_request: Some(Self::init_request_callback), + exit_request: Some(Self::exit_request_callback), + cleanup_rq: None, + busy: None, + map_queues: None, + #[cfg(CONFIG_BLK_DEBUG_FS)] + show_rq: None, + }; + + pub(crate) const fn build() -> &'static bindings::blk_mq_ops { + &Self::VTABLE + } +} diff --git a/rust/kernel/block/mq/raw_writer.rs b/rust/kernel/block/mq/raw_writer.rs new file mode 100644 index 000000000000..9222465d670b --- /dev/null +++ b/rust/kernel/block/mq/raw_writer.rs @@ -0,0 +1,55 @@ +// SPDX-License-Identifier: GPL-2.0 + +use core::fmt::{self, Write}; + +use crate::error::Result; +use crate::prelude::EINVAL; + +/// A mutable reference to a byte buffer where a string can be written into. +/// +/// # Invariants +/// +/// `buffer` is always null terminated. +pub(crate) struct RawWriter<'a> { + buffer: &'a mut [u8], + pos: usize, +} + +impl<'a> RawWriter<'a> { + /// Create a new `RawWriter` instance. + fn new(buffer: &'a mut [u8]) -> Result> { + *(buffer.last_mut().ok_or(EINVAL)?) = 0; + + // INVARIANT: We null terminated the buffer above. + Ok(Self { buffer, pos: 0 }) + } + + pub(crate) fn from_array( + a: &'a mut [core::ffi::c_char; N], + ) -> Result> { + Self::new( + // SAFETY: the buffer of `a` is valid for read and write as `u8` for + // at least `N` bytes. + unsafe { core::slice::from_raw_parts_mut(a.as_mut_ptr().cast::(), N) }, + ) + } +} + +impl Write for RawWriter<'_> { + fn write_str(&mut self, s: &str) -> fmt::Result { + let bytes = s.as_bytes(); + let len = bytes.len(); + + // We do not want to overwrite our null terminator + if self.pos + len > self.buffer.len() - 1 { + return Err(fmt::Error); + } + + // INVARIANT: We are not overwriting the last byte + self.buffer[self.pos..self.pos + len].copy_from_slice(bytes); + + self.pos += len; + + Ok(()) + } +} diff --git a/rust/kernel/block/mq/request.rs b/rust/kernel/block/mq/request.rs new file mode 100644 index 000000000000..a0e22827f3f4 --- /dev/null +++ b/rust/kernel/block/mq/request.rs @@ -0,0 +1,253 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! This module provides a wrapper for the C `struct request` type. +//! +//! C header: [`include/linux/blk-mq.h`](srctree/include/linux/blk-mq.h) + +use crate::{ + bindings, + block::mq::Operations, + error::Result, + types::{ARef, AlwaysRefCounted, Opaque}, +}; +use core::{ + marker::PhantomData, + ptr::{addr_of_mut, NonNull}, + sync::atomic::{AtomicU64, Ordering}, +}; + +/// A wrapper around a blk-mq `struct request`. This represents an IO request. +/// +/// # Implementation details +/// +/// There are four states for a request that the Rust bindings care about: +/// +/// A) Request is owned by block layer (refcount 0) +/// B) Request is owned by driver but with zero `ARef`s in existence +/// (refcount 1) +/// C) Request is owned by driver with exactly one `ARef` in existence +/// (refcount 2) +/// D) Request is owned by driver with more than one `ARef` in existence +/// (refcount > 2) +/// +/// +/// We need to track A and B to ensure we fail tag to request conversions for +/// requests that are not owned by the driver. +/// +/// We need to track C and D to ensure that it is safe to end the request and hand +/// back ownership to the block layer. +/// +/// The states are tracked through the private `refcount` field of +/// `RequestDataWrapper`. This structure lives in the private data area of the C +/// `struct request`. +/// +/// # Invariants +/// +/// * `self.0` is a valid `struct request` created by the C portion of the kernel. +/// * The private data area associated with this request must be an initialized +/// and valid `RequestDataWrapper`. +/// * `self` is reference counted by atomic modification of +/// self.wrapper_ref().refcount(). +/// +#[repr(transparent)] +pub struct Request(Opaque, PhantomData); + +impl Request { + /// Create an `ARef` from a `struct request` pointer. + /// + /// # Safety + /// + /// * The caller must own a refcount on `ptr` that is transferred to the + /// returned `ARef`. + /// * The type invariants for `Request` must hold for the pointee of `ptr`. + pub(crate) unsafe fn aref_from_raw(ptr: *mut bindings::request) -> ARef { + // INVARIANT: By the safety requirements of this function, invariants are upheld. + // SAFETY: By the safety requirement of this function, we own a + // reference count that we can pass to `ARef`. + unsafe { ARef::from_raw(NonNull::new_unchecked(ptr as *const Self as *mut Self)) } + } + + /// Notify the block layer that a request is going to be processed now. + /// + /// The block layer uses this hook to do proper initializations such as + /// starting the timeout timer. It is a requirement that block device + /// drivers call this function when starting to process a request. + /// + /// # Safety + /// + /// The caller must have exclusive ownership of `self`, that is + /// `self.wrapper_ref().refcount() == 2`. + pub(crate) unsafe fn start_unchecked(this: &ARef) { + // SAFETY: By type invariant, `self.0` is a valid `struct request` and + // we have exclusive access. + unsafe { bindings::blk_mq_start_request(this.0.get()) }; + } + + /// Try to take exclusive ownership of `this` by dropping the refcount to 0. + /// This fails if `this` is not the only `ARef` pointing to the underlying + /// `Request`. + /// + /// If the operation is successful, `Ok` is returned with a pointer to the + /// C `struct request`. If the operation fails, `this` is returned in the + /// `Err` variant. + fn try_set_end(this: ARef) -> Result<*mut bindings::request, ARef> { + // We can race with `TagSet::tag_to_rq` + if let Err(_old) = this.wrapper_ref().refcount().compare_exchange( + 2, + 0, + Ordering::Relaxed, + Ordering::Relaxed, + ) { + return Err(this); + } + + let request_ptr = this.0.get(); + core::mem::forget(this); + + Ok(request_ptr) + } + + /// Notify the block layer that the request has been completed without errors. + /// + /// This function will return `Err` if `this` is not the only `ARef` + /// referencing the request. + pub fn end_ok(this: ARef) -> Result<(), ARef> { + let request_ptr = Self::try_set_end(this)?; + + // SAFETY: By type invariant, `this.0` was a valid `struct request`. The + // success of the call to `try_set_end` guarantees that there are no + // `ARef`s pointing to this request. Therefore it is safe to hand it + // back to the block layer. + unsafe { bindings::blk_mq_end_request(request_ptr, bindings::BLK_STS_OK as _) }; + + Ok(()) + } + + /// Return a pointer to the `RequestDataWrapper` stored in the private area + /// of the request structure. + /// + /// # Safety + /// + /// - `this` must point to a valid allocation of size at least size of + /// `Self` plus size of `RequestDataWrapper`. + pub(crate) unsafe fn wrapper_ptr(this: *mut Self) -> NonNull { + let request_ptr = this.cast::(); + // SAFETY: By safety requirements for this function, `this` is a + // valid allocation. + let wrapper_ptr = + unsafe { bindings::blk_mq_rq_to_pdu(request_ptr).cast::() }; + // SAFETY: By C API contract, wrapper_ptr points to a valid allocation + // and is not null. + unsafe { NonNull::new_unchecked(wrapper_ptr) } + } + + /// Return a reference to the `RequestDataWrapper` stored in the private + /// area of the request structure. + pub(crate) fn wrapper_ref(&self) -> &RequestDataWrapper { + // SAFETY: By type invariant, `self.0` is a valid allocation. Further, + // the private data associated with this request is initialized and + // valid. The existence of `&self` guarantees that the private data is + // valid as a shared reference. + unsafe { Self::wrapper_ptr(self as *const Self as *mut Self).as_ref() } + } +} + +/// A wrapper around data stored in the private area of the C `struct request`. +pub(crate) struct RequestDataWrapper { + /// The Rust request refcount has the following states: + /// + /// - 0: The request is owned by C block layer. + /// - 1: The request is owned by Rust abstractions but there are no ARef references to it. + /// - 2+: There are `ARef` references to the request. + refcount: AtomicU64, +} + +impl RequestDataWrapper { + /// Return a reference to the refcount of the request that is embedding + /// `self`. + pub(crate) fn refcount(&self) -> &AtomicU64 { + &self.refcount + } + + /// Return a pointer to the refcount of the request that is embedding the + /// pointee of `this`. + /// + /// # Safety + /// + /// - `this` must point to a live allocation of at least the size of `Self`. + pub(crate) unsafe fn refcount_ptr(this: *mut Self) -> *mut AtomicU64 { + // SAFETY: Because of the safety requirements of this function, the + // field projection is safe. + unsafe { addr_of_mut!((*this).refcount) } + } +} + +// SAFETY: Exclusive access is thread-safe for `Request`. `Request` has no `&mut +// self` methods and `&self` methods that mutate `self` are internally +// synchronized. +unsafe impl Send for Request {} + +// SAFETY: Shared access is thread-safe for `Request`. `&self` methods that +// mutate `self` are internally synchronized` +unsafe impl Sync for Request {} + +/// Store the result of `op(target.load())` in target, returning new value of +/// target. +fn atomic_relaxed_op_return(target: &AtomicU64, op: impl Fn(u64) -> u64) -> u64 { + let old = target.fetch_update(Ordering::Relaxed, Ordering::Relaxed, |x| Some(op(x))); + + // SAFETY: Because the operation passed to `fetch_update` above always + // return `Some`, `old` will always be `Ok`. + let old = unsafe { old.unwrap_unchecked() }; + + op(old) +} + +/// Store the result of `op(target.load)` in `target` if `target.load() != +/// pred`, returning true if the target was updated. +fn atomic_relaxed_op_unless(target: &AtomicU64, op: impl Fn(u64) -> u64, pred: u64) -> bool { + target + .fetch_update(Ordering::Relaxed, Ordering::Relaxed, |x| { + if x == pred { + None + } else { + Some(op(x)) + } + }) + .is_ok() +} + +// SAFETY: All instances of `Request` are reference counted. This +// implementation of `AlwaysRefCounted` ensure that increments to the ref count +// keeps the object alive in memory at least until a matching reference count +// decrement is executed. +unsafe impl AlwaysRefCounted for Request { + fn inc_ref(&self) { + let refcount = &self.wrapper_ref().refcount(); + + #[cfg_attr(not(CONFIG_DEBUG_MISC), allow(unused_variables))] + let updated = atomic_relaxed_op_unless(refcount, |x| x + 1, 0); + + #[cfg(CONFIG_DEBUG_MISC)] + if !updated { + panic!("Request refcount zero on clone") + } + } + + unsafe fn dec_ref(obj: core::ptr::NonNull) { + // SAFETY: The type invariants of `ARef` guarantee that `obj` is valid + // for read. + let wrapper_ptr = unsafe { Self::wrapper_ptr(obj.as_ptr()).as_ptr() }; + // SAFETY: The type invariant of `Request` guarantees that the private + // data area is initialized and valid. + let refcount = unsafe { &*RequestDataWrapper::refcount_ptr(wrapper_ptr) }; + + #[cfg_attr(not(CONFIG_DEBUG_MISC), allow(unused_variables))] + let new_refcount = atomic_relaxed_op_return(refcount, |x| x - 1); + + #[cfg(CONFIG_DEBUG_MISC)] + if new_refcount == 0 { + panic!("Request reached refcount zero in Rust abstractions"); + } + } +} diff --git a/rust/kernel/block/mq/tag_set.rs b/rust/kernel/block/mq/tag_set.rs new file mode 100644 index 000000000000..f9a1ca655a35 --- /dev/null +++ b/rust/kernel/block/mq/tag_set.rs @@ -0,0 +1,86 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! This module provides the `TagSet` struct to wrap the C `struct blk_mq_tag_set`. +//! +//! C header: [`include/linux/blk-mq.h`](srctree/include/linux/blk-mq.h) + +use core::pin::Pin; + +use crate::{ + bindings, + block::mq::{operations::OperationsVTable, request::RequestDataWrapper, Operations}, + error, + prelude::PinInit, + try_pin_init, + types::Opaque, +}; +use core::{convert::TryInto, marker::PhantomData}; +use macros::{pin_data, pinned_drop}; + +/// A wrapper for the C `struct blk_mq_tag_set`. +/// +/// `struct blk_mq_tag_set` contains a `struct list_head` and so must be pinned. +/// +/// # Invariants +/// +/// - `inner` is initialized and valid. +#[pin_data(PinnedDrop)] +#[repr(transparent)] +pub struct TagSet { + #[pin] + inner: Opaque, + _p: PhantomData, +} + +impl TagSet { + /// Try to create a new tag set + pub fn new( + nr_hw_queues: u32, + num_tags: u32, + num_maps: u32, + ) -> impl PinInit { + // SAFETY: `blk_mq_tag_set` only contains integers and pointers, which + // all are allowed to be 0. + let tag_set: bindings::blk_mq_tag_set = unsafe { core::mem::zeroed() }; + let tag_set = core::mem::size_of::() + .try_into() + .map(|cmd_size| { + bindings::blk_mq_tag_set { + ops: OperationsVTable::::build(), + nr_hw_queues, + timeout: 0, // 0 means default which is 30Hz in C + numa_node: bindings::NUMA_NO_NODE, + queue_depth: num_tags, + cmd_size, + flags: bindings::BLK_MQ_F_SHOULD_MERGE, + driver_data: core::ptr::null_mut::(), + nr_maps: num_maps, + ..tag_set + } + }); + + try_pin_init!(TagSet { + inner <- PinInit::<_, error::Error>::pin_chain(Opaque::new(tag_set?), |tag_set| { + // SAFETY: we do not move out of `tag_set`. + let tag_set = unsafe { Pin::get_unchecked_mut(tag_set) }; + // SAFETY: `tag_set` is a reference to an initialized `blk_mq_tag_set`. + error::to_result( unsafe { bindings::blk_mq_alloc_tag_set(tag_set.get())}) + }), + _p: PhantomData, + }) + } + + /// Return the pointer to the wrapped `struct blk_mq_tag_set` + pub(crate) fn raw_tag_set(&self) -> *mut bindings::blk_mq_tag_set { + self.inner.get() + } +} + +#[pinned_drop] +impl PinnedDrop for TagSet { + fn drop(self: Pin<&mut Self>) { + // SAFETY: By type invariant `inner` is valid and has been properly + // initialized during construction. + unsafe { bindings::blk_mq_free_tag_set(self.inner.get()) }; + } +} diff --git a/rust/kernel/error.rs b/rust/kernel/error.rs index 55280ae9fe40..145f5c397009 100644 --- a/rust/kernel/error.rs +++ b/rust/kernel/error.rs @@ -126,6 +126,12 @@ impl Error { self.0 } + #[cfg(CONFIG_BLOCK)] + pub(crate) fn to_blk_status(self) -> bindings::blk_status_t { + // SAFETY: `self.0` is a valid error due to its invariant. + unsafe { bindings::errno_to_blk_status(self.0) } + } + /// Returns the error encoded as a pointer. #[allow(dead_code)] pub(crate) fn to_ptr(self) -> *mut T { diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index fbd91a48ff8b..2cf7c6b6f66b 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -27,6 +27,8 @@ compile_error!("Missing kernel configuration for conditional compilation"); extern crate self as kernel; pub mod alloc; +#[cfg(CONFIG_BLOCK)] +pub mod block; mod build_assert; pub mod error; pub mod init;