diff options
Diffstat (limited to 'drivers')
45 files changed, 2382 insertions, 326 deletions
diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 2fd1ed101748..5a95671d8151 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -316,8 +316,40 @@ __setup("ramdisk_size=", ramdisk_size); * (should share code eventually). */ static LIST_HEAD(brd_devices); +static DEFINE_MUTEX(brd_devices_mutex); static struct dentry *brd_debugfs_dir; +static struct brd_device *brd_find_or_alloc_device(int i) +{ + struct brd_device *brd; + + mutex_lock(&brd_devices_mutex); + list_for_each_entry(brd, &brd_devices, brd_list) { + if (brd->brd_number == i) { + mutex_unlock(&brd_devices_mutex); + return ERR_PTR(-EEXIST); + } + } + + brd = kzalloc(sizeof(*brd), GFP_KERNEL); + if (!brd) { + mutex_unlock(&brd_devices_mutex); + return ERR_PTR(-ENOMEM); + } + brd->brd_number = i; + list_add_tail(&brd->brd_list, &brd_devices); + mutex_unlock(&brd_devices_mutex); + return brd; +} + +static void brd_free_device(struct brd_device *brd) +{ + mutex_lock(&brd_devices_mutex); + list_del(&brd->brd_list); + mutex_unlock(&brd_devices_mutex); + kfree(brd); +} + static int brd_alloc(int i) { struct brd_device *brd; @@ -340,14 +372,9 @@ static int brd_alloc(int i) BLK_FEAT_NOWAIT, }; - list_for_each_entry(brd, &brd_devices, brd_list) - if (brd->brd_number == i) - return -EEXIST; - brd = kzalloc(sizeof(*brd), GFP_KERNEL); - if (!brd) - return -ENOMEM; - brd->brd_number = i; - list_add_tail(&brd->brd_list, &brd_devices); + brd = brd_find_or_alloc_device(i); + if (IS_ERR(brd)) + return PTR_ERR(brd); xa_init(&brd->brd_pages); @@ -378,8 +405,7 @@ static int brd_alloc(int i) out_cleanup_disk: put_disk(disk); out_free_dev: - list_del(&brd->brd_list); - kfree(brd); + brd_free_device(brd); return err; } @@ -398,8 +424,7 @@ static void brd_cleanup(void) del_gendisk(brd->brd_disk); put_disk(brd->brd_disk); brd_free_pages(brd); - list_del(&brd->brd_list); - kfree(brd); + brd_free_device(brd); } } @@ -426,16 +451,6 @@ static int __init brd_init(void) { int err, i; - brd_check_and_reset_par(); - - brd_debugfs_dir = debugfs_create_dir("ramdisk_pages", NULL); - - for (i = 0; i < rd_nr; i++) { - err = brd_alloc(i); - if (err) - goto out_free; - } - /* * brd module now has a feature to instantiate underlying device * structure on-demand, provided that there is an access dev node. @@ -451,11 +466,18 @@ static int __init brd_init(void) * dynamically. */ + brd_check_and_reset_par(); + + brd_debugfs_dir = debugfs_create_dir("ramdisk_pages", NULL); + if (__register_blkdev(RAMDISK_MAJOR, "ramdisk", brd_probe)) { err = -EIO; goto out_free; } + for (i = 0; i < rd_nr; i++) + brd_alloc(i); + pr_info("brd: module loaded\n"); return 0; diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 78a7bb28defe..fe9bb4fb5f1b 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -173,7 +173,7 @@ static loff_t get_loop_size(struct loop_device *lo, struct file *file) static bool lo_bdev_can_use_dio(struct loop_device *lo, struct block_device *backing_bdev) { - unsigned short sb_bsize = bdev_logical_block_size(backing_bdev); + unsigned int sb_bsize = bdev_logical_block_size(backing_bdev); if (queue_logical_block_size(lo->lo_queue) < sb_bsize) return false; @@ -786,11 +786,10 @@ static void loop_config_discard(struct loop_device *lo, * file-backed loop devices: discarded regions read back as zero. */ if (S_ISBLK(inode->i_mode)) { - struct request_queue *backingq = bdev_get_queue(I_BDEV(inode)); + struct block_device *bdev = I_BDEV(inode); - max_discard_sectors = backingq->limits.max_write_zeroes_sectors; - granularity = bdev_discard_granularity(I_BDEV(inode)) ?: - queue_physical_block_size(backingq); + max_discard_sectors = bdev_write_zeroes_sectors(bdev); + granularity = bdev_discard_granularity(bdev); /* * We use punch hole to reclaim the free space used by the @@ -977,7 +976,7 @@ loop_set_status_from_info(struct loop_device *lo, return 0; } -static unsigned short loop_default_blocksize(struct loop_device *lo, +static unsigned int loop_default_blocksize(struct loop_device *lo, struct block_device *backing_bdev) { /* In case of direct I/O, match underlying block size */ @@ -986,7 +985,7 @@ static unsigned short loop_default_blocksize(struct loop_device *lo, return SECTOR_SIZE; } -static int loop_reconfigure_limits(struct loop_device *lo, unsigned short bsize) +static int loop_reconfigure_limits(struct loop_device *lo, unsigned int bsize) { struct file *file = lo->lo_backing_file; struct inode *inode = file->f_mapping->host; diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 223faa9d5ffd..43701b7b10a7 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -2701,7 +2701,12 @@ static int mtip_hw_init(struct driver_data *dd) int rv; unsigned long timeout, timetaken; - dd->mmio = pcim_iomap_table(dd->pdev)[MTIP_ABAR]; + dd->mmio = pcim_iomap_region(dd->pdev, MTIP_ABAR, MTIP_DRV_NAME); + if (IS_ERR(dd->mmio)) { + dev_err(&dd->pdev->dev, "Unable to request / ioremap PCI region\n"); + return PTR_ERR(dd->mmio); + } + mtip_detect_product(dd); if (dd->product_type == MTIP_PRODUCT_UNKNOWN) { @@ -3710,13 +3715,6 @@ static int mtip_pci_probe(struct pci_dev *pdev, goto iomap_err; } - /* Map BAR5 to memory. */ - rv = pcim_iomap_regions(pdev, 1 << MTIP_ABAR, MTIP_DRV_NAME); - if (rv < 0) { - dev_err(&pdev->dev, "Unable to map regions\n"); - goto iomap_err; - } - rv = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (rv) { dev_warn(&pdev->dev, "64-bit DMA enable failed\n"); diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index 2f0431e42c49..3c3d8d200abb 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -1638,10 +1638,9 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx, return BLK_STS_OK; } -static void null_queue_rqs(struct request **rqlist) +static void null_queue_rqs(struct rq_list *rqlist) { - struct request *requeue_list = NULL; - struct request **requeue_lastp = &requeue_list; + struct rq_list requeue_list = {}; struct blk_mq_queue_data bd = { }; blk_status_t ret; @@ -1651,8 +1650,8 @@ static void null_queue_rqs(struct request **rqlist) bd.rq = rq; ret = null_queue_rq(rq->mq_hctx, &bd); if (ret != BLK_STS_OK) - rq_list_add_tail(&requeue_lastp, rq); - } while (!rq_list_empty(*rqlist)); + rq_list_add_tail(&requeue_list, rq); + } while (!rq_list_empty(rqlist)); *rqlist = requeue_list; } diff --git a/drivers/block/null_blk/zoned.c b/drivers/block/null_blk/zoned.c index 9bc768b2ca56..0d5f9bf95229 100644 --- a/drivers/block/null_blk/zoned.c +++ b/drivers/block/null_blk/zoned.c @@ -166,7 +166,7 @@ int null_init_zoned_dev(struct nullb_device *dev, lim->features |= BLK_FEAT_ZONED; lim->chunk_sectors = dev->zone_size_sects; - lim->max_zone_append_sectors = dev->zone_append_max_sectors; + lim->max_hw_zone_append_sectors = dev->zone_append_max_sectors; lim->max_open_zones = dev->zone_max_open; lim->max_active_zones = dev->zone_max_active; return 0; diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 9c8b19a22c2a..ac421dbeeb11 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -7284,6 +7284,7 @@ static ssize_t do_rbd_remove(const char *buf, size_t count) */ blk_mq_freeze_queue(rbd_dev->disk->queue); blk_mark_disk_dead(rbd_dev->disk); + blk_mq_unfreeze_queue(rbd_dev->disk->queue); } del_gendisk(rbd_dev->disk); diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 6ba2c1dd1d87..c6d18cd8af44 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -60,7 +60,12 @@ | UBLK_F_UNPRIVILEGED_DEV \ | UBLK_F_CMD_IOCTL_ENCODE \ | UBLK_F_USER_COPY \ - | UBLK_F_ZONED) + | UBLK_F_ZONED \ + | UBLK_F_USER_RECOVERY_FAIL_IO) + +#define UBLK_F_ALL_RECOVERY_FLAGS (UBLK_F_USER_RECOVERY \ + | UBLK_F_USER_RECOVERY_REISSUE \ + | UBLK_F_USER_RECOVERY_FAIL_IO) /* All UBLK_PARAM_TYPE_* should be included here */ #define UBLK_PARAM_TYPE_ALL \ @@ -143,6 +148,7 @@ struct ublk_queue { bool force_abort; bool timeout; bool canceling; + bool fail_io; /* copy of dev->state == UBLK_S_DEV_FAIL_IO */ unsigned short nr_io_ready; /* how many ios setup */ spinlock_t cancel_lock; struct ublk_device *dev; @@ -179,8 +185,7 @@ struct ublk_device { unsigned int nr_queues_ready; unsigned int nr_privileged_daemon; - struct work_struct quiesce_work; - struct work_struct stop_work; + struct work_struct nosrv_work; }; /* header of ublk_params */ @@ -664,30 +669,69 @@ static inline char *ublk_queue_cmd_buf(struct ublk_device *ub, int q_id) return ublk_get_queue(ub, q_id)->io_cmd_buf; } +static inline int __ublk_queue_cmd_buf_size(int depth) +{ + return round_up(depth * sizeof(struct ublksrv_io_desc), PAGE_SIZE); +} + static inline int ublk_queue_cmd_buf_size(struct ublk_device *ub, int q_id) { struct ublk_queue *ubq = ublk_get_queue(ub, q_id); - return round_up(ubq->q_depth * sizeof(struct ublksrv_io_desc), - PAGE_SIZE); + return __ublk_queue_cmd_buf_size(ubq->q_depth); +} + +static int ublk_max_cmd_buf_size(void) +{ + return __ublk_queue_cmd_buf_size(UBLK_MAX_QUEUE_DEPTH); +} + +/* + * Should I/O outstanding to the ublk server when it exits be reissued? + * If not, outstanding I/O will get errors. + */ +static inline bool ublk_nosrv_should_reissue_outstanding(struct ublk_device *ub) +{ + return (ub->dev_info.flags & UBLK_F_USER_RECOVERY) && + (ub->dev_info.flags & UBLK_F_USER_RECOVERY_REISSUE); +} + +/* + * Should I/O issued while there is no ublk server queue? If not, I/O + * issued while there is no ublk server will get errors. + */ +static inline bool ublk_nosrv_dev_should_queue_io(struct ublk_device *ub) +{ + return (ub->dev_info.flags & UBLK_F_USER_RECOVERY) && + !(ub->dev_info.flags & UBLK_F_USER_RECOVERY_FAIL_IO); } -static inline bool ublk_queue_can_use_recovery_reissue( - struct ublk_queue *ubq) +/* + * Same as ublk_nosrv_dev_should_queue_io, but uses a queue-local copy + * of the device flags for smaller cache footprint - better for fast + * paths. + */ +static inline bool ublk_nosrv_should_queue_io(struct ublk_queue *ubq) { return (ubq->flags & UBLK_F_USER_RECOVERY) && - (ubq->flags & UBLK_F_USER_RECOVERY_REISSUE); + !(ubq->flags & UBLK_F_USER_RECOVERY_FAIL_IO); } -static inline bool ublk_queue_can_use_recovery( - struct ublk_queue *ubq) +/* + * Should ublk devices be stopped (i.e. no recovery possible) when the + * ublk server exits? If not, devices can be used again by a future + * incarnation of a ublk server via the start_recovery/end_recovery + * commands. + */ +static inline bool ublk_nosrv_should_stop_dev(struct ublk_device *ub) { - return ubq->flags & UBLK_F_USER_RECOVERY; + return !(ub->dev_info.flags & UBLK_F_USER_RECOVERY); } -static inline bool ublk_can_use_recovery(struct ublk_device *ub) +static inline bool ublk_dev_in_recoverable_state(struct ublk_device *ub) { - return ub->dev_info.flags & UBLK_F_USER_RECOVERY; + return ub->dev_info.state == UBLK_S_DEV_QUIESCED || + ub->dev_info.state == UBLK_S_DEV_FAIL_IO; } static void ublk_free_disk(struct gendisk *disk) @@ -1063,7 +1107,7 @@ static void __ublk_fail_req(struct ublk_queue *ubq, struct ublk_io *io, { WARN_ON_ONCE(io->flags & UBLK_IO_FLAG_ACTIVE); - if (ublk_queue_can_use_recovery_reissue(ubq)) + if (ublk_nosrv_should_reissue_outstanding(ubq->dev)) blk_mq_requeue_request(req, false); else ublk_put_req_ref(ubq, req); @@ -1091,7 +1135,7 @@ static inline void __ublk_abort_rq(struct ublk_queue *ubq, struct request *rq) { /* We cannot process this rq so just requeue it. */ - if (ublk_queue_can_use_recovery(ubq)) + if (ublk_nosrv_dev_should_queue_io(ubq->dev)) blk_mq_requeue_request(rq, false); else blk_mq_end_request(rq, BLK_STS_IOERR); @@ -1236,10 +1280,7 @@ static enum blk_eh_timer_return ublk_timeout(struct request *rq) struct ublk_device *ub = ubq->dev; if (ublk_abort_requests(ub, ubq)) { - if (ublk_can_use_recovery(ub)) - schedule_work(&ub->quiesce_work); - else - schedule_work(&ub->stop_work); + schedule_work(&ub->nosrv_work); } return BLK_EH_DONE; } @@ -1254,6 +1295,10 @@ static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *rq = bd->rq; blk_status_t res; + if (unlikely(ubq->fail_io)) { + return BLK_STS_TARGET; + } + /* fill iod to slot in io cmd buffer */ res = ublk_setup_iod(ubq, rq); if (unlikely(res != BLK_STS_OK)) @@ -1268,7 +1313,7 @@ static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx, * Note: force_abort is guaranteed to be seen because it is set * before request queue is unqiuesced. */ - if (ublk_queue_can_use_recovery(ubq) && unlikely(ubq->force_abort)) + if (ublk_nosrv_should_queue_io(ubq) && unlikely(ubq->force_abort)) return BLK_STS_IOERR; if (unlikely(ubq->canceling)) { @@ -1322,7 +1367,7 @@ static int ublk_ch_mmap(struct file *filp, struct vm_area_struct *vma) { struct ublk_device *ub = filp->private_data; size_t sz = vma->vm_end - vma->vm_start; - unsigned max_sz = UBLK_MAX_QUEUE_DEPTH * sizeof(struct ublksrv_io_desc); + unsigned max_sz = ublk_max_cmd_buf_size(); unsigned long pfn, end, phys_off = vma->vm_pgoff << PAGE_SHIFT; int q_id, ret = 0; @@ -1489,10 +1534,7 @@ static void ublk_uring_cmd_cancel_fn(struct io_uring_cmd *cmd, ublk_cancel_cmd(ubq, io, issue_flags); if (need_schedule) { - if (ublk_can_use_recovery(ub)) - schedule_work(&ub->quiesce_work); - else - schedule_work(&ub->stop_work); + schedule_work(&ub->nosrv_work); } } @@ -1555,20 +1597,6 @@ static void __ublk_quiesce_dev(struct ublk_device *ub) ub->dev_info.state = UBLK_S_DEV_QUIESCED; } -static void ublk_quiesce_work_fn(struct work_struct *work) -{ - struct ublk_device *ub = - container_of(work, struct ublk_device, quiesce_work); - - mutex_lock(&ub->mutex); - if (ub->dev_info.state != UBLK_S_DEV_LIVE) - goto unlock; - __ublk_quiesce_dev(ub); - unlock: - mutex_unlock(&ub->mutex); - ublk_cancel_dev(ub); -} - static void ublk_unquiesce_dev(struct ublk_device *ub) { int i; @@ -1597,7 +1625,7 @@ static void ublk_stop_dev(struct ublk_device *ub) mutex_lock(&ub->mutex); if (ub->dev_info.state == UBLK_S_DEV_DEAD) goto unlock; - if (ublk_can_use_recovery(ub)) { + if (ublk_nosrv_dev_should_queue_io(ub)) { if (ub->dev_info.state == UBLK_S_DEV_LIVE) __ublk_quiesce_dev(ub); ublk_unquiesce_dev(ub); @@ -1617,6 +1645,37 @@ static void ublk_stop_dev(struct ublk_device *ub) ublk_cancel_dev(ub); } +static void ublk_nosrv_work(struct work_struct *work) +{ + struct ublk_device *ub = + container_of(work, struct ublk_device, nosrv_work); + int i; + + if (ublk_nosrv_should_stop_dev(ub)) { + ublk_stop_dev(ub); + return; + } + + mutex_lock(&ub->mutex); + if (ub->dev_info.state != UBLK_S_DEV_LIVE) + goto unlock; + + if (ublk_nosrv_dev_should_queue_io(ub)) { + __ublk_quiesce_dev(ub); + } else { + blk_mq_quiesce_queue(ub->ub_disk->queue); + ub->dev_info.state = UBLK_S_DEV_FAIL_IO; + for (i = 0; i < ub->dev_info.nr_hw_queues; i++) { + ublk_get_queue(ub, i)->fail_io = true; + } + blk_mq_unquiesce_queue(ub->ub_disk->queue); + } + + unlock: + mutex_unlock(&ub->mutex); + ublk_cancel_dev(ub); +} + /* device can only be started after all IOs are ready */ static void ublk_mark_io_ready(struct ublk_device *ub, struct ublk_queue *ubq) { @@ -2130,14 +2189,6 @@ static int ublk_add_chdev(struct ublk_device *ub) return ret; } -static void ublk_stop_work_fn(struct work_struct *work) -{ - struct ublk_device *ub = - container_of(work, struct ublk_device, stop_work); - - ublk_stop_dev(ub); -} - /* align max io buffer size with PAGE_SIZE */ static void ublk_align_max_io_size(struct ublk_device *ub) { @@ -2162,8 +2213,7 @@ static int ublk_add_tag_set(struct ublk_device *ub) static void ublk_remove(struct ublk_device *ub) { ublk_stop_dev(ub); - cancel_work_sync(&ub->stop_work); - cancel_work_sync(&ub->quiesce_work); + cancel_work_sync(&ub->nosrv_work); cdev_device_del(&ub->cdev, &ub->cdev_dev); ublk_put_device(ub); ublks_added--; @@ -2229,7 +2279,7 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd) 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; + lim.max_hw_zone_append_sectors = p->max_zone_append_sectors; } if (ub->params.basic.attrs & UBLK_ATTR_VOLATILE_CACHE) { @@ -2372,6 +2422,19 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd) else if (!(info.flags & UBLK_F_UNPRIVILEGED_DEV)) return -EPERM; + /* forbid nonsense combinations of recovery flags */ + switch (info.flags & UBLK_F_ALL_RECOVERY_FLAGS) { + case 0: + case UBLK_F_USER_RECOVERY: + case (UBLK_F_USER_RECOVERY | UBLK_F_USER_RECOVERY_REISSUE): + case (UBLK_F_USER_RECOVERY | UBLK_F_USER_RECOVERY_FAIL_IO): + break; + default: + pr_warn("%s: invalid recovery flags %llx\n", __func__, + info.flags & UBLK_F_ALL_RECOVERY_FLAGS); + return -EINVAL; + } + /* * unprivileged device can't be trusted, but RECOVERY and * RECOVERY_REISSUE still may hang error handling, so can't @@ -2424,8 +2487,7 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd) goto out_unlock; mutex_init(&ub->mutex); spin_lock_init(&ub->lock); - INIT_WORK(&ub->quiesce_work, ublk_quiesce_work_fn); - INIT_WORK(&ub->stop_work, ublk_stop_work_fn); + INIT_WORK(&ub->nosrv_work, ublk_nosrv_work); ret = ublk_alloc_dev_number(ub, header->dev_id); if (ret < 0) @@ -2560,9 +2622,7 @@ static inline void ublk_ctrl_cmd_dump(struct io_uring_cmd *cmd) static int ublk_ctrl_stop_dev(struct ublk_device *ub) { ublk_stop_dev(ub); - cancel_work_sync(&ub->stop_work); - cancel_work_sync(&ub->quiesce_work); - + cancel_work_sync(&ub->nosrv_work); return 0; } @@ -2699,7 +2759,7 @@ static int ublk_ctrl_start_recovery(struct ublk_device *ub, int i; mutex_lock(&ub->mutex); - if (!ublk_can_use_recovery(ub)) + if (ublk_nosrv_should_stop_dev(ub)) goto out_unlock; if (!ub->nr_queues_ready) goto out_unlock; @@ -2710,14 +2770,18 @@ static int ublk_ctrl_start_recovery(struct ublk_device *ub, * and related io_uring ctx is freed so file struct of /dev/ublkcX is * released. * + * and one of the following holds + * * (2) UBLK_S_DEV_QUIESCED is set, which means the quiesce_work: * (a)has quiesced request queue * (b)has requeued every inflight rqs whose io_flags is ACTIVE * (c)has requeued/aborted every inflight rqs whose io_flags is NOT ACTIVE * (d)has completed/camceled all ioucmds owned by ther dying process + * + * (3) UBLK_S_DEV_FAIL_IO is set, which means the queue is not + * quiesced, but all I/O is being immediately errored */ - if (test_bit(UB_STATE_OPEN, &ub->state) || - ub->dev_info.state != UBLK_S_DEV_QUIESCED) { + if (test_bit(UB_STATE_OPEN, &ub->state) || !ublk_dev_in_recoverable_state(ub)) { ret = -EBUSY; goto out_unlock; } @@ -2741,6 +2805,7 @@ static int ublk_ctrl_end_recovery(struct ublk_device *ub, const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe); int ublksrv_pid = (int)header->data[0]; int ret = -EINVAL; + int i; pr_devel("%s: Waiting for new ubq_daemons(nr: %d) are ready, dev id %d...\n", __func__, ub->dev_info.nr_hw_queues, header->dev_id); @@ -2752,21 +2817,32 @@ static int ublk_ctrl_end_recovery(struct ublk_device *ub, __func__, ub->dev_info.nr_hw_queues, header->dev_id); mutex_lock(&ub->mutex); - if (!ublk_can_use_recovery(ub)) + if (ublk_nosrv_should_stop_dev(ub)) goto out_unlock; - if (ub->dev_info.state != UBLK_S_DEV_QUIESCED) { + if (!ublk_dev_in_recoverable_state(ub)) { ret = -EBUSY; goto out_unlock; } ub->dev_info.ublksrv_pid = ublksrv_pid; pr_devel("%s: new ublksrv_pid %d, dev id %d\n", __func__, ublksrv_pid, header->dev_id); - blk_mq_unquiesce_queue(ub->ub_disk->queue); - pr_devel("%s: queue unquiesced, dev id %d.\n", - __func__, header->dev_id); - blk_mq_kick_requeue_list(ub->ub_disk->queue); - ub->dev_info.state = UBLK_S_DEV_LIVE; + + if (ublk_nosrv_dev_should_queue_io(ub)) { + ub->dev_info.state = UBLK_S_DEV_LIVE; + blk_mq_unquiesce_queue(ub->ub_disk->queue); + pr_devel("%s: queue unquiesced, dev id %d.\n", + __func__, header->dev_id); + blk_mq_kick_requeue_list(ub->ub_disk->queue); + } else { + blk_mq_quiesce_queue(ub->ub_disk->queue); + ub->dev_info.state = UBLK_S_DEV_LIVE; + for (i = 0; i < ub->dev_info.nr_hw_queues; i++) { + ublk_get_queue(ub, i)->fail_io = false; + } + blk_mq_unquiesce_queue(ub->ub_disk->queue); + } + ret = 0; out_unlock: mutex_unlock(&ub->mutex); diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 194417abc105..c0cdba71f436 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -471,18 +471,18 @@ static bool virtblk_prep_rq_batch(struct request *req) return virtblk_prep_rq(req->mq_hctx, vblk, req, vbr) == BLK_STS_OK; } -static bool virtblk_add_req_batch(struct virtio_blk_vq *vq, - struct request **rqlist) +static void virtblk_add_req_batch(struct virtio_blk_vq *vq, + struct rq_list *rqlist) { + struct request *req; unsigned long flags; - int err; bool kick; spin_lock_irqsave(&vq->lock, flags); - while (!rq_list_empty(*rqlist)) { - struct request *req = rq_list_pop(rqlist); + while ((req = rq_list_pop(rqlist))) { struct virtblk_req *vbr = blk_mq_rq_to_pdu(req); + int err; err = virtblk_add_req(vq->vq, vbr); if (err) { @@ -495,37 +495,32 @@ static bool virtblk_add_req_batch(struct virtio_blk_vq *vq, kick = virtqueue_kick_prepare(vq->vq); spin_unlock_irqrestore(&vq->lock, flags); - return kick; + if (kick) + virtqueue_notify(vq->vq); } -static void virtio_queue_rqs(struct request **rqlist) +static void virtio_queue_rqs(struct rq_list *rqlist) { - struct request *req, *next, *prev = NULL; - struct request *requeue_list = NULL; - - rq_list_for_each_safe(rqlist, req, next) { - struct virtio_blk_vq *vq = get_virtio_blk_vq(req->mq_hctx); - bool kick; - - if (!virtblk_prep_rq_batch(req)) { - rq_list_move(rqlist, &requeue_list, req, prev); - req = prev; - if (!req) - continue; - } + struct rq_list submit_list = { }; + struct rq_list requeue_list = { }; + struct virtio_blk_vq *vq = NULL; + struct request *req; - if (!next || req->mq_hctx != next->mq_hctx) { - req->rq_next = NULL; - kick = virtblk_add_req_batch(vq, rqlist); - if (kick) - virtqueue_notify(vq->vq); + while ((req = rq_list_pop(rqlist))) { + struct virtio_blk_vq *this_vq = get_virtio_blk_vq(req->mq_hctx); - *rqlist = next; - prev = NULL; - } else - prev = req; + if (vq && vq != this_vq) + virtblk_add_req_batch(vq, &submit_list); + vq = this_vq; + + if (virtblk_prep_rq_batch(req)) + rq_list_add_tail(&submit_list, req); + else + rq_list_add_tail(&requeue_list, req); } + if (vq) + virtblk_add_req_batch(vq, &submit_list); *rqlist = requeue_list; } @@ -784,7 +779,7 @@ static int virtblk_read_zoned_limits(struct virtio_blk *vblk, wg, v); return -ENODEV; } - lim->max_zone_append_sectors = v; + lim->max_hw_zone_append_sectors = v; dev_dbg(&vdev->dev, "max append sectors = %u\n", v); return 0; diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 849eb6333e98..9cb797a561d6 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -3362,7 +3362,7 @@ static int cache_iterate_devices(struct dm_target *ti, static void disable_passdown_if_not_supported(struct cache *cache) { struct block_device *origin_bdev = cache->origin_dev->bdev; - struct queue_limits *origin_limits = &bdev_get_queue(origin_bdev)->limits; + struct queue_limits *origin_limits = bdev_limits(origin_bdev); const char *reason = NULL; if (!cache->features.discard_passdown) @@ -3384,7 +3384,7 @@ static void disable_passdown_if_not_supported(struct cache *cache) static void set_discard_limits(struct cache *cache, struct queue_limits *limits) { struct block_device *origin_bdev = cache->origin_dev->bdev; - struct queue_limits *origin_limits = &bdev_get_queue(origin_bdev)->limits; + struct queue_limits *origin_limits = bdev_limits(origin_bdev); if (!cache->features.discard_passdown) { /* No passdown is done so setting own virtual limits */ diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c index 12bbe487a4c8..e956d980672c 100644 --- a/drivers/md/dm-clone-target.c +++ b/drivers/md/dm-clone-target.c @@ -2020,7 +2020,7 @@ static void clone_resume(struct dm_target *ti) static void disable_passdown_if_not_supported(struct clone *clone) { struct block_device *dest_dev = clone->dest_dev->bdev; - struct queue_limits *dest_limits = &bdev_get_queue(dest_dev)->limits; + struct queue_limits *dest_limits = bdev_limits(dest_dev); const char *reason = NULL; if (!test_bit(DM_CLONE_DISCARD_PASSDOWN, &clone->flags)) @@ -2041,7 +2041,7 @@ static void disable_passdown_if_not_supported(struct clone *clone) static void set_discard_limits(struct clone *clone, struct queue_limits *limits) { struct block_device *dest_bdev = clone->dest_dev->bdev; - struct queue_limits *dest_limits = &bdev_get_queue(dest_bdev)->limits; + struct queue_limits *dest_limits = bdev_limits(dest_bdev); if (!test_bit(DM_CLONE_DISCARD_PASSDOWN, &clone->flags)) { /* No passdown is done so we set our own virtual limits */ diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 89632ce97760..9095f19a84f3 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -2842,7 +2842,7 @@ static void disable_discard_passdown_if_not_supported(struct pool_c *pt) { struct pool *pool = pt->pool; struct block_device *data_bdev = pt->data_dev->bdev; - struct queue_limits *data_limits = &bdev_get_queue(data_bdev)->limits; + struct queue_limits *data_limits = bdev_limits(data_bdev); const char *reason = NULL; if (!pt->adjusted_pf.discard_passdown) diff --git a/drivers/md/dm-zone.c b/drivers/md/dm-zone.c index c0d41c36e06e..20edd3fabbab 100644 --- a/drivers/md/dm-zone.c +++ b/drivers/md/dm-zone.c @@ -344,7 +344,7 @@ int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q, clear_bit(DMF_EMULATE_ZONE_APPEND, &md->flags); } else { set_bit(DMF_EMULATE_ZONE_APPEND, &md->flags); - lim->max_zone_append_sectors = 0; + lim->max_hw_zone_append_sectors = 0; } /* @@ -379,7 +379,7 @@ int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q, if (!zlim.mapped_nr_seq_zones) { lim->max_open_zones = 0; lim->max_active_zones = 0; - lim->max_zone_append_sectors = 0; + lim->max_hw_zone_append_sectors = 0; lim->zone_write_granularity = 0; lim->chunk_sectors = 0; lim->features &= ~BLK_FEAT_ZONED; diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 29da10e6f703..c3a42dd66ce5 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -1285,6 +1285,7 @@ static void bitmap_unplug_async(struct bitmap *bitmap) queue_work(md_bitmap_wq, &unplug_work.work); wait_for_completion(&done); + destroy_work_on_stack(&unplug_work.work); } static void bitmap_unplug(struct mddev *mddev, bool sync) diff --git a/drivers/md/md.c b/drivers/md/md.c index 67108c397c5a..aebe12b0ee27 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -9784,9 +9784,7 @@ EXPORT_SYMBOL(md_reap_sync_thread); void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev) { sysfs_notify_dirent_safe(rdev->sysfs_state); - wait_event_timeout(rdev->blocked_wait, - !test_bit(Blocked, &rdev->flags) && - !test_bit(BlockedBadBlocks, &rdev->flags), + wait_event_timeout(rdev->blocked_wait, !rdev_blocked(rdev), msecs_to_jiffies(5000)); rdev_dec_pending(rdev, mddev); } @@ -9815,6 +9813,17 @@ int rdev_set_badblocks(struct md_rdev *rdev, sector_t s, int sectors, { struct mddev *mddev = rdev->mddev; int rv; + + /* + * Recording new badblocks for faulty rdev will force unnecessary + * super block updating. This is fragile for external management because + * userspace daemon may trying to remove this device and deadlock may + * occur. This will be probably solved in the mdadm, but it is safer to + * avoid it. + */ + if (test_bit(Faulty, &rdev->flags)) + return 1; + if (is_new) s += rdev->new_data_offset; else diff --git a/drivers/md/md.h b/drivers/md/md.h index 5d2e6bd58e4d..4ba93af36126 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -1002,6 +1002,30 @@ static inline void mddev_trace_remap(struct mddev *mddev, struct bio *bio, trace_block_bio_remap(bio, disk_devt(mddev->gendisk), sector); } +static inline bool rdev_blocked(struct md_rdev *rdev) +{ + /* + * Blocked will be set by error handler and cleared by daemon after + * updating superblock, meanwhile write IO should be blocked to prevent + * reading old data after power failure. + */ + if (test_bit(Blocked, &rdev->flags)) + return true; + + /* + * Faulty device should not be accessed anymore, there is no need to + * wait for bad block to be acknowledged. + */ + if (test_bit(Faulty, &rdev->flags)) + return false; + + /* rdev is blocked by badblocks. */ + if (test_bit(BlockedBadBlocks, &rdev->flags)) + return true; + + return false; +} + #define mddev_add_trace_msg(mddev, fmt, args...) \ do { \ if (!mddev_is_dm(mddev)) \ diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 32d587524778..baaf5f8b80ae 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -466,6 +466,12 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio) struct bio *split = bio_split(bio, zone->zone_end - bio->bi_iter.bi_sector, GFP_NOIO, &mddev->bio_set); + + if (IS_ERR(split)) { + bio->bi_status = errno_to_blk_status(PTR_ERR(split)); + bio_endio(bio); + return; + } bio_chain(split, bio); submit_bio_noacct(bio); bio = split; @@ -608,6 +614,12 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio) if (sectors < bio_sectors(bio)) { struct bio *split = bio_split(bio, sectors, GFP_NOIO, &mddev->bio_set); + + if (IS_ERR(split)) { + bio->bi_status = errno_to_blk_status(PTR_ERR(split)); + bio_endio(bio); + return true; + } bio_chain(split, bio); raid0_map_submit_bio(mddev, bio); bio = split; diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 6c9d24203f39..a5adf08ee174 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1322,7 +1322,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio, const enum req_op op = bio_op(bio); const blk_opf_t do_sync = bio->bi_opf & REQ_SYNC; int max_sectors; - int rdisk; + int rdisk, error; bool r1bio_existed = !!r1_bio; /* @@ -1383,6 +1383,11 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio, if (max_sectors < bio_sectors(bio)) { struct bio *split = bio_split(bio, max_sectors, gfp, &conf->bio_split); + + if (IS_ERR(split)) { + error = PTR_ERR(split); + goto err_handle; + } bio_chain(split, bio); submit_bio_noacct(bio); bio = split; @@ -1410,6 +1415,47 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio, read_bio->bi_private = r1_bio; mddev_trace_remap(mddev, read_bio, r1_bio->sector); submit_bio_noacct(read_bio); + return; + +err_handle: + atomic_dec(&mirror->rdev->nr_pending); + bio->bi_status = errno_to_blk_status(error); + set_bit(R1BIO_Uptodate, &r1_bio->state); + raid_end_bio_io(r1_bio); +} + +static bool wait_blocked_rdev(struct mddev *mddev, struct bio *bio) +{ + struct r1conf *conf = mddev->private; + int disks = conf->raid_disks * 2; + int i; + +retry: + for (i = 0; i < disks; i++) { + struct md_rdev *rdev = conf->mirrors[i].rdev; + + if (!rdev) + continue; + + /* don't write here until the bad block is acknowledged */ + if (test_bit(WriteErrorSeen, &rdev->flags) && + rdev_has_badblock(rdev, bio->bi_iter.bi_sector, + bio_sectors(bio)) < 0) + set_bit(BlockedBadBlocks, &rdev->flags); + + if (rdev_blocked(rdev)) { + if (bio->bi_opf & REQ_NOWAIT) + return false; + + mddev_add_trace_msg(rdev->mddev, "raid1 wait rdev %d blocked", + rdev->raid_disk); + atomic_inc(&rdev->nr_pending); + md_wait_for_blocked_rdev(rdev, rdev->mddev); + goto retry; + } + } + + return true; } static void raid1_write_request(struct mddev *mddev, struct bio *bio, @@ -1417,9 +1463,8 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, { struct r1conf *conf = mddev->private; struct r1bio *r1_bio; - int i, disks; + int i, disks, k, error; unsigned long flags; - struct md_rdev *blocked_rdev; int first_clone; int max_sectors; bool write_behind = false; @@ -1457,7 +1502,11 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, return; } - retry_write: + if (!wait_blocked_rdev(mddev, bio)) { + bio_wouldblock_error(bio); + return; + } + r1_bio = alloc_r1bio(mddev, bio); r1_bio->sectors = max_write_sectors; @@ -1473,7 +1522,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, */ disks = conf->raid_disks * 2; - blocked_rdev = NULL; max_sectors = r1_bio->sectors; for (i = 0; i < disks; i++) { struct md_rdev *rdev = conf->mirrors[i].rdev; @@ -1486,11 +1534,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, if (!is_discard && rdev && test_bit(WriteMostly, &rdev->flags)) write_behind = true; - if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) { - atomic_inc(&rdev->nr_pending); - blocked_rdev = rdev; - break; - } r1_bio->bios[i] = NULL; if (!rdev || test_bit(Faulty, &rdev->flags)) { if (i < conf->raid_disks) @@ -1506,13 +1549,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, is_bad = is_badblock(rdev, r1_bio->sector, max_sectors, &first_bad, &bad_sectors); - if (is_bad < 0) { - /* mustn't write here until the bad block is - * acknowledged*/ - set_bit(BlockedBadBlocks, &rdev->flags); - blocked_rdev = rdev; - break; - } if (is_bad && first_bad <= r1_bio->sector) { /* Cannot write here at all */ bad_sectors -= (r1_bio->sector - first_bad); @@ -1543,27 +1579,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, r1_bio->bios[i] = bio; } - if (unlikely(blocked_rdev)) { - /* Wait for this device to become unblocked */ - int j; - - for (j = 0; j < i; j++) - if (r1_bio->bios[j]) - rdev_dec_pending(conf->mirrors[j].rdev, mddev); - mempool_free(r1_bio, &conf->r1bio_pool); - allow_barrier(conf, bio->bi_iter.bi_sector); - - if (bio->bi_opf & REQ_NOWAIT) { - bio_wouldblock_error(bio); - return; - } - mddev_add_trace_msg(mddev, "raid1 wait rdev %d blocked", - blocked_rdev->raid_disk); - md_wait_for_blocked_rdev(blocked_rdev, mddev); - wait_barrier(conf, bio->bi_iter.bi_sector, false); - goto retry_write; - } - /* * When using a bitmap, we may call alloc_behind_master_bio below. * alloc_behind_master_bio allocates a copy of the data payload a page @@ -1576,6 +1591,11 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, if (max_sectors < bio_sectors(bio)) { struct bio *split = bio_split(bio, max_sectors, GFP_NOIO, &conf->bio_split); + + if (IS_ERR(split)) { + error = PTR_ERR(split); + goto err_handle; + } bio_chain(split, bio); submit_bio_noacct(bio); bio = split; @@ -1660,6 +1680,18 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, /* In case raid1d snuck in to freeze_array */ wake_up_barrier(conf); + return; +err_handle: + for (k = 0; k < i; k++) { + if (r1_bio->bios[k]) { + rdev_dec_pending(conf->mirrors[k].rdev, mddev); + r1_bio->bios[k] = NULL; + } + } + + bio->bi_status = errno_to_blk_status(error); + set_bit(R1BIO_Uptodate, &r1_bio->state); + raid_end_bio_io(r1_bio); } static bool raid1_make_request(struct mddev *mddev, struct bio *bio) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 862b1fb71d86..18989231791a 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1159,6 +1159,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio, int slot = r10_bio->read_slot; struct md_rdev *err_rdev = NULL; gfp_t gfp = GFP_NOIO; + int error; if (slot >= 0 && r10_bio->devs[slot].rdev) { /* @@ -1206,6 +1207,10 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio, if (max_sectors < bio_sectors(bio)) { struct bio *split = bio_split(bio, max_sectors, gfp, &conf->bio_split); + if (IS_ERR(split)) { + error = PTR_ERR(split); + goto err_handle; + } bio_chain(split, bio); allow_barrier(conf); submit_bio_noacct(bio); @@ -1236,6 +1241,11 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio, mddev_trace_remap(mddev, read_bio, r10_bio->sector); submit_bio_noacct(read_bio); return; +err_handle: + atomic_dec(&rdev->nr_pending); + bio->bi_status = errno_to_blk_status(error); + set_bit(R10BIO_Uptodate, &r10_bio->state); + raid_end_bio_io(r10_bio); } static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio, @@ -1285,9 +1295,9 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio, static void wait_blocked_dev(struct mddev *mddev, struct r10bio *r10_bio) { - int i; struct r10conf *conf = mddev->private; struct md_rdev *blocked_rdev; + int i; retry_wait: blocked_rdev = NULL; @@ -1295,40 +1305,36 @@ retry_wait: struct md_rdev *rdev, *rrdev; rdev = conf->mirrors[i].rdev; - rrdev = conf->mirrors[i].replacement; - if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) { - atomic_inc(&rdev->nr_pending); - blocked_rdev = rdev; - break; - } - if (rrdev && unlikely(test_bit(Blocked, &rrdev->flags))) { - atomic_inc(&rrdev->nr_pending); - blocked_rdev = rrdev; - break; - } - - if (rdev && test_bit(WriteErrorSeen, &rdev->flags)) { + if (rdev) { sector_t dev_sector = r10_bio->devs[i].addr; /* * Discard request doesn't care the write result * so it doesn't need to wait blocked disk here. */ - if (!r10_bio->sectors) - continue; - - if (rdev_has_badblock(rdev, dev_sector, - r10_bio->sectors) < 0) { + if (test_bit(WriteErrorSeen, &rdev->flags) && + r10_bio->sectors && + rdev_has_badblock(rdev, dev_sector, + r10_bio->sectors) < 0) /* - * Mustn't write here until the bad block - * is acknowledged + * Mustn't write here until the bad + * block is acknowledged */ - atomic_inc(&rdev->nr_pending); set_bit(BlockedBadBlocks, &rdev->flags); + + if (rdev_blocked(rdev)) { blocked_rdev = rdev; + atomic_inc(&rdev->nr_pending); break; } } + + rrdev = conf->mirrors[i].replacement; + if (rrdev && rdev_blocked(rrdev)) { + atomic_inc(&rrdev->nr_pending); + blocked_rdev = rrdev; + break; + } } if (unlikely(blocked_rdev)) { @@ -1347,9 +1353,10 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, struct r10bio *r10_bio) { struct r10conf *conf = mddev->private; - int i; + int i, k; sector_t sectors; int max_sectors; + int error; if ((mddev_is_clustered(mddev) && md_cluster_ops->area_resyncing(mddev, WRITE, @@ -1482,6 +1489,10 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, if (r10_bio->sectors < bio_sectors(bio)) { struct bio *split = bio_split(bio, r10_bio->sectors, GFP_NOIO, &conf->bio_split); + if (IS_ERR(split)) { + error = PTR_ERR(split); + goto err_handle; + } bio_chain(split, bio); allow_barrier(conf); submit_bio_noacct(bio); @@ -1503,6 +1514,26 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, raid10_write_one_disk(mddev, r10_bio, bio, true, i); } one_write_done(r10_bio); + return; +err_handle: + for (k = 0; k < i; k++) { + int d = r10_bio->devs[k].devnum; + struct md_rdev *rdev = conf->mirrors[d].rdev; + struct md_rdev *rrdev = conf->mirrors[d].replacement; + + if (r10_bio->devs[k].bio) { + rdev_dec_pending(rdev, mddev); + r10_bio->devs[k].bio = NULL; + } + if (r10_bio->devs[k].repl_bio) { + rdev_dec_pending(rrdev, mddev); + r10_bio->devs[k].repl_bio = NULL; + } + } + + bio->bi_status = errno_to_blk_status(error); + set_bit(R10BIO_Uptodate, &r10_bio->state); + raid_end_bio_io(r10_bio); } static void __make_request(struct mddev *mddev, struct bio *bio, int sectors) @@ -1644,6 +1675,11 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio) if (remainder) { split_size = stripe_size - remainder; split = bio_split(bio, split_size, GFP_NOIO, &conf->bio_split); + if (IS_ERR(split)) { + bio->bi_status = errno_to_blk_status(PTR_ERR(split)); + bio_endio(bio); + return 0; + } bio_chain(split, bio); allow_barrier(conf); /* Resend the fist split part */ @@ -1654,6 +1690,11 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio) if (remainder) { split_size = bio_sectors(bio) - remainder; split = bio_split(bio, split_size, GFP_NOIO, &conf->bio_split); + if (IS_ERR(split)) { + bio->bi_status = errno_to_blk_status(PTR_ERR(split)); + bio_endio(bio); + return 0; + } bio_chain(split, bio); allow_barrier(conf); /* Resend the second split part */ diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c index a70cbec12ed0..37c4da5311ca 100644 --- a/drivers/md/raid5-ppl.c +++ b/drivers/md/raid5-ppl.c @@ -258,7 +258,7 @@ static struct ppl_io_unit *ppl_new_iounit(struct ppl_log *log, memset(pplhdr->reserved, 0xff, PPL_HDR_RESERVED); pplhdr->signature = cpu_to_le32(ppl_conf->signature); - io->seq = atomic64_add_return(1, &ppl_conf->seq); + io->seq = atomic64_inc_return(&ppl_conf->seq); pplhdr->generation = cpu_to_le64(io->seq); return io; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index dc2ea636d173..f09e7677ee9f 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -4724,14 +4724,13 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s) if (rdev) { is_bad = rdev_has_badblock(rdev, sh->sector, RAID5_STRIPE_SECTORS(conf)); - if (s->blocked_rdev == NULL - && (test_bit(Blocked, &rdev->flags) - || is_bad < 0)) { + if (s->blocked_rdev == NULL) { if (is_bad < 0) - set_bit(BlockedBadBlocks, - &rdev->flags); - s->blocked_rdev = rdev; - atomic_inc(&rdev->nr_pending); + set_bit(BlockedBadBlocks, &rdev->flags); + if (rdev_blocked(rdev)) { + s->blocked_rdev = rdev; + atomic_inc(&rdev->nr_pending); + } } } clear_bit(R5_Insync, &dev->flags); @@ -7177,6 +7176,8 @@ raid5_store_group_thread_cnt(struct mddev *mddev, const char *page, size_t len) err = mddev_suspend_and_lock(mddev); if (err) return err; + raid5_quiesce(mddev, true); + conf = mddev->private; if (!conf) err = -ENODEV; @@ -7198,6 +7199,8 @@ raid5_store_group_thread_cnt(struct mddev *mddev, const char *page, size_t len) kfree(old_groups); } } + + raid5_quiesce(mddev, false); mddev_unlock_and_resume(mddev); return err ?: len; diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index 896ecfc4afa6..d174e586698f 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -633,7 +633,7 @@ struct r5conf { * two caches. */ int active_name; - char cache_name[2][32]; + char cache_name[2][48]; struct kmem_cache *slab_cache; /* for allocating stripes */ struct mutex cache_size_mutex; /* Protect changes to cache size */ diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index ef06a4d5d65b..79f6fad97a80 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -2501,6 +2501,56 @@ static inline int mmc_blk_readonly(struct mmc_card *card) !(card->csd.cmdclass & CCC_BLOCK_WRITE); } +/* + * Search for a declared partitions node for the disk in mmc-card related node. + * + * This is to permit support for partition table defined in DT in special case + * where a partition table is not written in the disk and is expected to be + * passed from the running system. + * + * For the user disk, "partitions" node is searched. + * For the special HW disk, "partitions-" node with the appended name is used + * following this conversion table (to adhere to JEDEC naming) + * - boot0 -> partitions-boot1 + * - boot1 -> partitions-boot2 + * - gp0 -> partitions-gp1 + * - gp1 -> partitions-gp2 + * - gp2 -> partitions-gp3 + * - gp3 -> partitions-gp4 + */ +static struct fwnode_handle *mmc_blk_get_partitions_node(struct device *mmc_dev, + const char *subname) +{ + const char *node_name = "partitions"; + + if (subname) { + mmc_dev = mmc_dev->parent; + + /* + * Check if we are allocating a BOOT disk boot0/1 disk. + * In DT we use the JEDEC naming boot1/2. + */ + if (!strcmp(subname, "boot0")) + node_name = "partitions-boot1"; + if (!strcmp(subname, "boot1")) + node_name = "partitions-boot2"; + /* + * Check if we are allocating a GP disk gp0/1/2/3 disk. + * In DT we use the JEDEC naming gp1/2/3/4. + */ + if (!strcmp(subname, "gp0")) + node_name = "partitions-gp1"; + if (!strcmp(subname, "gp1")) + node_name = "partitions-gp2"; + if (!strcmp(subname, "gp2")) + node_name = "partitions-gp3"; + if (!strcmp(subname, "gp3")) + node_name = "partitions-gp4"; + } + + return device_get_named_child_node(mmc_dev, node_name); +} + static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card, struct device *parent, sector_t size, @@ -2509,6 +2559,7 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card, int area_type, unsigned int part_type) { + struct fwnode_handle *disk_fwnode; struct mmc_blk_data *md; int devidx, ret; char cap_str[10]; @@ -2610,7 +2661,9 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card, /* used in ->open, must be set before add_disk: */ if (area_type == MMC_BLK_DATA_AREA_MAIN) dev_set_drvdata(&card->dev, md); - ret = device_add_disk(md->parent, md->disk, mmc_disk_attr_groups); + disk_fwnode = mmc_blk_get_partitions_node(parent, subname); + ret = add_disk_fwnode(md->parent, md->disk, mmc_disk_attr_groups, + disk_fwnode); if (ret) goto err_put_disk; return md; diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c index b1387dc459a3..7cd1102a8d2c 100644 --- a/drivers/nvme/host/apple.c +++ b/drivers/nvme/host/apple.c @@ -649,7 +649,7 @@ static bool apple_nvme_handle_cq(struct apple_nvme_queue *q, bool force) found = apple_nvme_poll_cq(q, &iob); - if (!rq_list_empty(iob.req_list)) + if (!rq_list_empty(&iob.req_list)) apple_nvme_complete_batch(&iob); return found; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 855b42c92284..1a8d32a4a5c3 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -42,6 +42,8 @@ struct nvme_ns_info { bool is_readonly; bool is_ready; bool is_removed; + bool is_rotational; + bool no_vwc; }; unsigned int admin_timeout = 60; @@ -1639,6 +1641,8 @@ static int nvme_ns_info_from_id_cs_indep(struct nvme_ctrl *ctrl, info->is_shared = id->nmic & NVME_NS_NMIC_SHARED; info->is_readonly = id->nsattr & NVME_NS_ATTR_RO; info->is_ready = id->nstat & NVME_NSTAT_NRDY; + info->is_rotational = id->nsfeat & NVME_NS_ROTATIONAL; + info->no_vwc = id->nsfeat & NVME_NS_VWC_NOT_PRESENT; } kfree(id); return ret; @@ -2185,11 +2189,14 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, ns->head->ids.csi == NVME_CSI_ZNS) nvme_update_zone_info(ns, &lim, &zi); - if (ns->ctrl->vwc & NVME_CTRL_VWC_PRESENT) + if ((ns->ctrl->vwc & NVME_CTRL_VWC_PRESENT) && !info->no_vwc) lim.features |= BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA; else lim.features &= ~(BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA); + if (info->is_rotational) + lim.features |= BLK_FEAT_ROTATIONAL; + /* * Register a metadata profile for PI, or the plain non-integrity NVMe * metadata masquerading as Type 0 if supported, otherwise reject block @@ -3636,6 +3643,7 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl, head->ns_id = info->nsid; head->ids = info->ids; head->shared = info->is_shared; + head->rotational = info->is_rotational; ratelimit_state_init(&head->rs_nuse, 5 * HZ, 1); ratelimit_set_flags(&head->rs_nuse, RATELIMIT_MSG_ON_RELEASE); kref_init(&head->ref); @@ -4017,7 +4025,7 @@ static void nvme_scan_ns(struct nvme_ctrl *ctrl, unsigned nsid) { struct nvme_ns_info info = { .nsid = nsid }; struct nvme_ns *ns; - int ret; + int ret = 1; if (nvme_identify_ns_descs(ctrl, &info)) return; @@ -4034,9 +4042,10 @@ static void nvme_scan_ns(struct nvme_ctrl *ctrl, unsigned nsid) * set up a namespace. If not fall back to the legacy version. */ if ((ctrl->cap & NVME_CAP_CRMS_CRIMS) || - (info.ids.csi != NVME_CSI_NVM && info.ids.csi != NVME_CSI_ZNS)) + (info.ids.csi != NVME_CSI_NVM && info.ids.csi != NVME_CSI_ZNS) || + ctrl->vs >= NVME_VS(2, 0, 0)) ret = nvme_ns_info_from_id_cs_indep(ctrl, &info); - else + if (ret > 0) ret = nvme_ns_info_from_identify(ctrl, &info); if (info.is_removed) @@ -4895,7 +4904,7 @@ void nvme_unfreeze(struct nvme_ctrl *ctrl) srcu_idx = srcu_read_lock(&ctrl->srcu); list_for_each_entry_srcu(ns, &ctrl->namespaces, list, srcu_read_lock_held(&ctrl->srcu)) - blk_mq_unfreeze_queue(ns->queue); + blk_mq_unfreeze_queue_non_owner(ns->queue); srcu_read_unlock(&ctrl->srcu, srcu_idx); clear_bit(NVME_CTRL_FROZEN, &ctrl->flags); } @@ -4940,7 +4949,12 @@ void nvme_start_freeze(struct nvme_ctrl *ctrl) srcu_idx = srcu_read_lock(&ctrl->srcu); list_for_each_entry_srcu(ns, &ctrl->namespaces, list, srcu_read_lock_held(&ctrl->srcu)) - blk_freeze_queue_start(ns->queue); + /* + * Typical non_owner use case is from pci driver, in which + * start_freeze is called from timeout work function, but + * unfreeze is done in reset work context + */ + blk_freeze_queue_start_non_owner(ns->queue); srcu_read_unlock(&ctrl->srcu, srcu_idx); } EXPORT_SYMBOL_GPL(nvme_start_freeze); @@ -5036,6 +5050,8 @@ static inline void _nvme_check_size(void) BUILD_BUG_ON(sizeof(struct nvme_id_ctrl_nvm) != NVME_IDENTIFY_DATA_SIZE); BUILD_BUG_ON(sizeof(struct nvme_lba_range_type) != 64); BUILD_BUG_ON(sizeof(struct nvme_smart_log) != 512); + BUILD_BUG_ON(sizeof(struct nvme_endurance_group_log) != 512); + BUILD_BUG_ON(sizeof(struct nvme_rotational_media_log) != 512); BUILD_BUG_ON(sizeof(struct nvme_dbbuf) != 64); BUILD_BUG_ON(sizeof(struct nvme_directive_cmd) != 64); BUILD_BUG_ON(sizeof(struct nvme_feat_host_behavior) != 512); @@ -5044,22 +5060,20 @@ static inline void _nvme_check_size(void) static int __init nvme_core_init(void) { + unsigned int wq_flags = WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS; int result = -ENOMEM; _nvme_check_size(); - nvme_wq = alloc_workqueue("nvme-wq", - WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0); + nvme_wq = alloc_workqueue("nvme-wq", wq_flags, 0); if (!nvme_wq) goto out; - nvme_reset_wq = alloc_workqueue("nvme-reset-wq", - WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0); + nvme_reset_wq = alloc_workqueue("nvme-reset-wq", wq_flags, 0); if (!nvme_reset_wq) goto destroy_wq; - nvme_delete_wq = alloc_workqueue("nvme-delete-wq", - WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0); + nvme_delete_wq = alloc_workqueue("nvme-delete-wq", wq_flags, 0); if (!nvme_delete_wq) goto destroy_reset_wq; diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index a96976b22fa7..6522ae16531c 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -114,7 +114,7 @@ static struct request *nvme_alloc_user_request(struct request_queue *q, static int nvme_map_user_request(struct request *req, u64 ubuffer, unsigned bufflen, void __user *meta_buffer, unsigned meta_len, - u32 meta_seed, struct io_uring_cmd *ioucmd, unsigned int flags) + struct io_uring_cmd *ioucmd, unsigned int flags) { struct request_queue *q = req->q; struct nvme_ns *ns = q->queuedata; @@ -152,8 +152,7 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer, bio_set_dev(bio, bdev); if (has_metadata) { - ret = blk_rq_integrity_map_user(req, meta_buffer, meta_len, - meta_seed); + ret = blk_rq_integrity_map_user(req, meta_buffer, meta_len); if (ret) goto out_unmap; } @@ -170,7 +169,7 @@ out: static int nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd, u64 ubuffer, unsigned bufflen, - void __user *meta_buffer, unsigned meta_len, u32 meta_seed, + void __user *meta_buffer, unsigned meta_len, u64 *result, unsigned timeout, unsigned int flags) { struct nvme_ns *ns = q->queuedata; @@ -187,7 +186,7 @@ static int nvme_submit_user_cmd(struct request_queue *q, req->timeout = timeout; if (ubuffer && bufflen) { ret = nvme_map_user_request(req, ubuffer, bufflen, meta_buffer, - meta_len, meta_seed, NULL, flags); + meta_len, NULL, flags); if (ret) return ret; } @@ -268,7 +267,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) c.rw.lbatm = cpu_to_le16(io.appmask); return nvme_submit_user_cmd(ns->queue, &c, io.addr, length, metadata, - meta_len, lower_32_bits(io.slba), NULL, 0, 0); + meta_len, NULL, 0, 0); } static bool nvme_validate_passthru_nsid(struct nvme_ctrl *ctrl, @@ -323,7 +322,7 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns, status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c, cmd.addr, cmd.data_len, nvme_to_user_ptr(cmd.metadata), - cmd.metadata_len, 0, &result, timeout, 0); + cmd.metadata_len, &result, timeout, 0); if (status >= 0) { if (put_user(result, &ucmd->result)) @@ -370,7 +369,7 @@ static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns, status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c, cmd.addr, cmd.data_len, nvme_to_user_ptr(cmd.metadata), - cmd.metadata_len, 0, &cmd.result, timeout, flags); + cmd.metadata_len, &cmd.result, timeout, flags); if (status >= 0) { if (put_user(cmd.result, &ucmd->result)) @@ -402,7 +401,7 @@ struct nvme_uring_cmd_pdu { static inline struct nvme_uring_cmd_pdu *nvme_uring_cmd_pdu( struct io_uring_cmd *ioucmd) { - return (struct nvme_uring_cmd_pdu *)&ioucmd->pdu; + return io_uring_cmd_to_pdu(ioucmd, struct nvme_uring_cmd_pdu); } static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd, @@ -507,7 +506,7 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns, if (d.addr && d.data_len) { ret = nvme_map_user_request(req, d.addr, d.data_len, nvme_to_user_ptr(d.metadata), - d.metadata_len, 0, ioucmd, vec); + d.metadata_len, ioucmd, vec); if (ret) return ret; } @@ -635,8 +634,6 @@ static int nvme_ns_uring_cmd(struct nvme_ns *ns, struct io_uring_cmd *ioucmd, struct nvme_ctrl *ctrl = ns->ctrl; int ret; - BUILD_BUG_ON(sizeof(struct nvme_uring_cmd_pdu) > sizeof(ioucmd->pdu)); - ret = nvme_uring_cmd_checks(issue_flags); if (ret) return ret; diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 6a15873055b9..f04cfe3fb936 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -635,8 +635,6 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head) lim.features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT | BLK_FEAT_POLL; if (head->ids.csi == NVME_CSI_ZNS) lim.features |= BLK_FEAT_ZONED; - else - lim.max_zone_append_sectors = 0; head->disk = blk_alloc_disk(&lim, ctrl->numa_node); if (IS_ERR(head->disk)) diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 093cb423f536..900719c4c70c 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -474,6 +474,7 @@ struct nvme_ns_head { struct list_head entry; struct kref ref; bool shared; + bool rotational; bool passthru_err_log_enabled; struct nvme_effects_log *effects; u64 nuse; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 4b9fda0b1d9a..5f2e3ad2cc52 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -141,6 +141,7 @@ struct nvme_dev { struct nvme_ctrl ctrl; u32 last_ps; bool hmb; + struct sg_table *hmb_sgt; mempool_t *iod_mempool; @@ -153,6 +154,7 @@ struct nvme_dev { /* host memory buffer support: */ u64 host_mem_size; u32 nr_host_mem_descs; + u32 host_mem_descs_size; dma_addr_t host_mem_descs_dma; struct nvme_host_mem_buf_desc *host_mem_descs; void **host_mem_desc_bufs; @@ -902,11 +904,12 @@ static blk_status_t nvme_queue_rq(struct blk_mq_hw_ctx *hctx, return BLK_STS_OK; } -static void nvme_submit_cmds(struct nvme_queue *nvmeq, struct request **rqlist) +static void nvme_submit_cmds(struct nvme_queue *nvmeq, struct rq_list *rqlist) { + struct request *req; + spin_lock(&nvmeq->sq_lock); - while (!rq_list_empty(*rqlist)) { - struct request *req = rq_list_pop(rqlist); + while ((req = rq_list_pop(rqlist))) { struct nvme_iod *iod = blk_mq_rq_to_pdu(req); nvme_sq_copy_cmd(nvmeq, &iod->cmd); @@ -929,33 +932,26 @@ static bool nvme_prep_rq_batch(struct nvme_queue *nvmeq, struct request *req) return nvme_prep_rq(nvmeq->dev, req) == BLK_STS_OK; } -static void nvme_queue_rqs(struct request **rqlist) +static void nvme_queue_rqs(struct rq_list *rqlist) { - struct request *req, *next, *prev = NULL; - struct request *requeue_list = NULL; - - rq_list_for_each_safe(rqlist, req, next) { - struct nvme_queue *nvmeq = req->mq_hctx->driver_data; - - if (!nvme_prep_rq_batch(nvmeq, req)) { - /* detach 'req' and add to remainder list */ - rq_list_move(rqlist, &requeue_list, req, prev); + struct rq_list submit_list = { }; + struct rq_list requeue_list = { }; + struct nvme_queue *nvmeq = NULL; + struct request *req; - req = prev; - if (!req) - continue; - } + while ((req = rq_list_pop(rqlist))) { + if (nvmeq && nvmeq != req->mq_hctx->driver_data) + nvme_submit_cmds(nvmeq, &submit_list); + nvmeq = req->mq_hctx->driver_data; - if (!next || req->mq_hctx != next->mq_hctx) { - /* detach rest of list, and submit */ - req->rq_next = NULL; - nvme_submit_cmds(nvmeq, rqlist); - *rqlist = next; - prev = NULL; - } else - prev = req; + if (nvme_prep_rq_batch(nvmeq, req)) + rq_list_add_tail(&submit_list, req); + else + rq_list_add_tail(&requeue_list, req); } + if (nvmeq) + nvme_submit_cmds(nvmeq, &submit_list); *rqlist = requeue_list; } @@ -1083,7 +1079,7 @@ static irqreturn_t nvme_irq(int irq, void *data) DEFINE_IO_COMP_BATCH(iob); if (nvme_poll_cq(nvmeq, &iob)) { - if (!rq_list_empty(iob.req_list)) + if (!rq_list_empty(&iob.req_list)) nvme_pci_complete_batch(&iob); return IRQ_HANDLED; } @@ -1951,7 +1947,7 @@ static int nvme_set_host_mem(struct nvme_dev *dev, u32 bits) return ret; } -static void nvme_free_host_mem(struct nvme_dev *dev) +static void nvme_free_host_mem_multi(struct nvme_dev *dev) { int i; @@ -1966,18 +1962,54 @@ static void nvme_free_host_mem(struct nvme_dev *dev) kfree(dev->host_mem_desc_bufs); dev->host_mem_desc_bufs = NULL; - dma_free_coherent(dev->dev, - dev->nr_host_mem_descs * sizeof(*dev->host_mem_descs), +} + +static void nvme_free_host_mem(struct nvme_dev *dev) +{ + if (dev->hmb_sgt) + dma_free_noncontiguous(dev->dev, dev->host_mem_size, + dev->hmb_sgt, DMA_BIDIRECTIONAL); + else + nvme_free_host_mem_multi(dev); + + dma_free_coherent(dev->dev, dev->host_mem_descs_size, dev->host_mem_descs, dev->host_mem_descs_dma); dev->host_mem_descs = NULL; + dev->host_mem_descs_size = 0; dev->nr_host_mem_descs = 0; } -static int __nvme_alloc_host_mem(struct nvme_dev *dev, u64 preferred, +static int nvme_alloc_host_mem_single(struct nvme_dev *dev, u64 size) +{ + dev->hmb_sgt = dma_alloc_noncontiguous(dev->dev, size, + DMA_BIDIRECTIONAL, GFP_KERNEL, 0); + if (!dev->hmb_sgt) + return -ENOMEM; + + dev->host_mem_descs = dma_alloc_coherent(dev->dev, + sizeof(*dev->host_mem_descs), &dev->host_mem_descs_dma, + GFP_KERNEL); + if (!dev->host_mem_descs) { + dma_free_noncontiguous(dev->dev, dev->host_mem_size, + dev->hmb_sgt, DMA_BIDIRECTIONAL); + dev->hmb_sgt = NULL; + return -ENOMEM; + } + dev->host_mem_size = size; + dev->host_mem_descs_size = sizeof(*dev->host_mem_descs); + dev->nr_host_mem_descs = 1; + + dev->host_mem_descs[0].addr = + cpu_to_le64(dev->hmb_sgt->sgl->dma_address); + dev->host_mem_descs[0].size = cpu_to_le32(size / NVME_CTRL_PAGE_SIZE); + return 0; +} + +static int nvme_alloc_host_mem_multi(struct nvme_dev *dev, u64 preferred, u32 chunk_size) { struct nvme_host_mem_buf_desc *descs; - u32 max_entries, len; + u32 max_entries, len, descs_size; dma_addr_t descs_dma; int i = 0; void **bufs; @@ -1990,8 +2022,9 @@ static int __nvme_alloc_host_mem(struct nvme_dev *dev, u64 preferred, if (dev->ctrl.hmmaxd && dev->ctrl.hmmaxd < max_entries) max_entries = dev->ctrl.hmmaxd; - descs = dma_alloc_coherent(dev->dev, max_entries * sizeof(*descs), - &descs_dma, GFP_KERNEL); + descs_size = max_entries * sizeof(*descs); + descs = dma_alloc_coherent(dev->dev, descs_size, &descs_dma, + GFP_KERNEL); if (!descs) goto out; @@ -2020,6 +2053,7 @@ static int __nvme_alloc_host_mem(struct nvme_dev *dev, u64 preferred, dev->host_mem_size = size; dev->host_mem_descs = descs; dev->host_mem_descs_dma = descs_dma; + dev->host_mem_descs_size = descs_size; dev->host_mem_desc_bufs = bufs; return 0; @@ -2034,8 +2068,7 @@ out_free_bufs: kfree(bufs); out_free_descs: - dma_free_coherent(dev->dev, max_entries * sizeof(*descs), descs, - descs_dma); + dma_free_coherent(dev->dev, descs_size, descs, descs_dma); out: dev->host_mem_descs = NULL; return -ENOMEM; @@ -2047,9 +2080,18 @@ static int nvme_alloc_host_mem(struct nvme_dev *dev, u64 min, u64 preferred) u64 hmminds = max_t(u32, dev->ctrl.hmminds * 4096, PAGE_SIZE * 2); u64 chunk_size; + /* + * If there is an IOMMU that can merge pages, try a virtually + * non-contiguous allocation for a single segment first. + */ + if (!(PAGE_SIZE & dma_get_merge_boundary(dev->dev))) { + if (!nvme_alloc_host_mem_single(dev, preferred)) + return 0; + } + /* start big and work our way down */ for (chunk_size = min_chunk; chunk_size >= hmminds; chunk_size /= 2) { - if (!__nvme_alloc_host_mem(dev, preferred, chunk_size)) { + if (!nvme_alloc_host_mem_multi(dev, preferred, chunk_size)) { if (!min || dev->host_mem_size >= min) return 0; nvme_free_host_mem(dev); @@ -2097,8 +2139,10 @@ static int nvme_setup_host_mem(struct nvme_dev *dev) } dev_info(dev->ctrl.device, - "allocated %lld MiB host memory buffer.\n", - dev->host_mem_size >> ilog2(SZ_1M)); + "allocated %lld MiB host memory buffer (%u segment%s).\n", + dev->host_mem_size >> ilog2(SZ_1M), + dev->nr_host_mem_descs, + str_plural(dev->nr_host_mem_descs)); } ret = nvme_set_host_mem(dev, enable_bits); diff --git a/drivers/nvme/host/trace.c b/drivers/nvme/host/trace.c index 87c437fc070d..ad25ad1e4041 100644 --- a/drivers/nvme/host/trace.c +++ b/drivers/nvme/host/trace.c @@ -228,27 +228,61 @@ static const char *nvme_trace_zone_mgmt_recv(struct trace_seq *p, u8 *cdw10) static const char *nvme_trace_resv_reg(struct trace_seq *p, u8 *cdw10) { + static const char * const rrega_strs[] = { + [0x00] = "register", + [0x01] = "unregister", + [0x02] = "replace", + }; const char *ret = trace_seq_buffer_ptr(p); u8 rrega = cdw10[0] & 0x7; u8 iekey = (cdw10[0] >> 3) & 0x1; u8 ptpl = (cdw10[3] >> 6) & 0x3; + const char *rrega_str; + + if (rrega < ARRAY_SIZE(rrega_strs) && rrega_strs[rrega]) + rrega_str = rrega_strs[rrega]; + else + rrega_str = "reserved"; - trace_seq_printf(p, "rrega=%u, iekey=%u, ptpl=%u", - rrega, iekey, ptpl); + trace_seq_printf(p, "rrega=%u:%s, iekey=%u, ptpl=%u", + rrega, rrega_str, iekey, ptpl); trace_seq_putc(p, 0); return ret; } +static const char * const rtype_strs[] = { + [0x00] = "reserved", + [0x01] = "write exclusive", + [0x02] = "exclusive access", + [0x03] = "write exclusive registrants only", + [0x04] = "exclusive access registrants only", + [0x05] = "write exclusive all registrants", + [0x06] = "exclusive access all registrants", +}; + static const char *nvme_trace_resv_acq(struct trace_seq *p, u8 *cdw10) { + static const char * const racqa_strs[] = { + [0x00] = "acquire", + [0x01] = "preempt", + [0x02] = "preempt and abort", + }; const char *ret = trace_seq_buffer_ptr(p); u8 racqa = cdw10[0] & 0x7; u8 iekey = (cdw10[0] >> 3) & 0x1; u8 rtype = cdw10[1]; + const char *racqa_str = "reserved"; + const char *rtype_str = "reserved"; - trace_seq_printf(p, "racqa=%u, iekey=%u, rtype=%u", - racqa, iekey, rtype); + if (racqa < ARRAY_SIZE(racqa_strs) && racqa_strs[racqa]) + racqa_str = racqa_strs[racqa]; + + if (rtype < ARRAY_SIZE(rtype_strs) && rtype_strs[rtype]) + rtype_str = rtype_strs[rtype]; + + trace_seq_printf(p, "racqa=%u:%s, iekey=%u, rtype=%u:%s", + racqa, racqa_str, iekey, rtype, rtype_str); trace_seq_putc(p, 0); return ret; @@ -256,13 +290,25 @@ static const char *nvme_trace_resv_acq(struct trace_seq *p, u8 *cdw10) static const char *nvme_trace_resv_rel(struct trace_seq *p, u8 *cdw10) { + static const char * const rrela_strs[] = { + [0x00] = "release", + [0x01] = "clear", + }; const char *ret = trace_seq_buffer_ptr(p); u8 rrela = cdw10[0] & 0x7; u8 iekey = (cdw10[0] >> 3) & 0x1; u8 rtype = cdw10[1]; + const char *rrela_str = "reserved"; + const char *rtype_str = "reserved"; + + if (rrela < ARRAY_SIZE(rrela_strs) && rrela_strs[rrela]) + rrela_str = rrela_strs[rrela]; + + if (rtype < ARRAY_SIZE(rtype_strs) && rtype_strs[rtype]) + rtype_str = rtype_strs[rtype]; - trace_seq_printf(p, "rrela=%u, iekey=%u, rtype=%u", - rrela, iekey, rtype); + trace_seq_printf(p, "rrela=%u:%s, iekey=%u, rtype=%u:%s", + rrela, rrela_str, iekey, rtype, rtype_str); trace_seq_putc(p, 0); return ret; diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c index 9a06f9d98cd6..382949e18c6a 100644 --- a/drivers/nvme/host/zns.c +++ b/drivers/nvme/host/zns.c @@ -111,7 +111,7 @@ void nvme_update_zone_info(struct nvme_ns *ns, struct queue_limits *lim, 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->max_hw_zone_append_sectors = ns->ctrl->max_zone_append; lim->chunk_sectors = ns->head->zsze = nvme_lba_to_sect(ns->head, zi->zone_size); } diff --git a/drivers/nvme/target/Makefile b/drivers/nvme/target/Makefile index c402c44350b2..f2b025bbe10c 100644 --- a/drivers/nvme/target/Makefile +++ b/drivers/nvme/target/Makefile @@ -10,7 +10,7 @@ obj-$(CONFIG_NVME_TARGET_FCLOOP) += nvme-fcloop.o obj-$(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 + discovery.o io-cmd-file.o io-cmd-bdev.o pr.o nvmet-$(CONFIG_NVME_TARGET_DEBUGFS) += debugfs.o nvmet-$(CONFIG_NVME_TARGET_PASSTHRU) += passthru.o nvmet-$(CONFIG_BLK_DEV_ZONED) += zns.o diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index 081f0473cd9e..934b401fbc2f 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -71,6 +71,35 @@ static void nvmet_execute_get_log_page_error(struct nvmet_req *req) nvmet_req_complete(req, 0); } +static void nvmet_execute_get_supported_log_pages(struct nvmet_req *req) +{ + struct nvme_supported_log *logs; + u16 status; + + logs = kzalloc(sizeof(*logs), GFP_KERNEL); + if (!logs) { + status = NVME_SC_INTERNAL; + goto out; + } + + logs->lids[NVME_LOG_SUPPORTED] = cpu_to_le32(NVME_LIDS_LSUPP); + logs->lids[NVME_LOG_ERROR] = cpu_to_le32(NVME_LIDS_LSUPP); + logs->lids[NVME_LOG_SMART] = cpu_to_le32(NVME_LIDS_LSUPP); + logs->lids[NVME_LOG_FW_SLOT] = cpu_to_le32(NVME_LIDS_LSUPP); + logs->lids[NVME_LOG_CHANGED_NS] = cpu_to_le32(NVME_LIDS_LSUPP); + logs->lids[NVME_LOG_CMD_EFFECTS] = cpu_to_le32(NVME_LIDS_LSUPP); + logs->lids[NVME_LOG_ENDURANCE_GROUP] = cpu_to_le32(NVME_LIDS_LSUPP); + logs->lids[NVME_LOG_ANA] = cpu_to_le32(NVME_LIDS_LSUPP); + logs->lids[NVME_LOG_FEATURES] = cpu_to_le32(NVME_LIDS_LSUPP); + logs->lids[NVME_LOG_RMI] = cpu_to_le32(NVME_LIDS_LSUPP); + logs->lids[NVME_LOG_RESERVATION] = cpu_to_le32(NVME_LIDS_LSUPP); + + status = nvmet_copy_to_sgl(req, 0, logs, sizeof(*logs)); + kfree(logs); +out: + nvmet_req_complete(req, status); +} + static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req, struct nvme_smart_log *slog) { @@ -130,6 +159,45 @@ static u16 nvmet_get_smart_log_all(struct nvmet_req *req, return NVME_SC_SUCCESS; } +static void nvmet_execute_get_log_page_rmi(struct nvmet_req *req) +{ + struct nvme_rotational_media_log *log; + struct gendisk *disk; + u16 status; + + req->cmd->common.nsid = cpu_to_le32(le16_to_cpu( + req->cmd->get_log_page.lsi)); + status = nvmet_req_find_ns(req); + if (status) + goto out; + + if (!req->ns->bdev || bdev_nonrot(req->ns->bdev)) { + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; + goto out; + } + + if (req->transfer_len != sizeof(*log)) { + status = NVME_SC_SGL_INVALID_DATA | NVME_STATUS_DNR; + goto out; + } + + log = kzalloc(sizeof(*log), GFP_KERNEL); + if (!log) + goto out; + + log->endgid = req->cmd->get_log_page.lsi; + disk = req->ns->bdev->bd_disk; + if (disk && disk->ia_ranges) + log->numa = cpu_to_le16(disk->ia_ranges->nr_ia_ranges); + else + log->numa = cpu_to_le16(1); + + status = nvmet_copy_to_sgl(req, 0, log, sizeof(*log)); + kfree(log); +out: + nvmet_req_complete(req, status); +} + static void nvmet_execute_get_log_page_smart(struct nvmet_req *req) { struct nvme_smart_log *log; @@ -176,6 +244,10 @@ static void nvmet_get_cmd_effects_nvm(struct nvme_effects_log *log) log->iocs[nvme_cmd_read] = log->iocs[nvme_cmd_flush] = log->iocs[nvme_cmd_dsm] = + log->iocs[nvme_cmd_resv_acquire] = + log->iocs[nvme_cmd_resv_register] = + log->iocs[nvme_cmd_resv_release] = + log->iocs[nvme_cmd_resv_report] = cpu_to_le32(NVME_CMD_EFFECTS_CSUPP); log->iocs[nvme_cmd_write] = log->iocs[nvme_cmd_write_zeroes] = @@ -272,6 +344,49 @@ static u32 nvmet_format_ana_group(struct nvmet_req *req, u32 grpid, return struct_size(desc, nsids, count); } +static void nvmet_execute_get_log_page_endgrp(struct nvmet_req *req) +{ + u64 host_reads, host_writes, data_units_read, data_units_written; + struct nvme_endurance_group_log *log; + u16 status; + + /* + * The target driver emulates each endurance group as its own + * namespace, reusing the nsid as the endurance group identifier. + */ + req->cmd->common.nsid = cpu_to_le32(le16_to_cpu( + req->cmd->get_log_page.lsi)); + status = nvmet_req_find_ns(req); + if (status) + goto out; + + log = kzalloc(sizeof(*log), GFP_KERNEL); + if (!log) { + status = NVME_SC_INTERNAL; + goto out; + } + + if (!req->ns->bdev) + goto copy; + + host_reads = part_stat_read(req->ns->bdev, ios[READ]); + data_units_read = + DIV_ROUND_UP(part_stat_read(req->ns->bdev, sectors[READ]), 1000); + host_writes = part_stat_read(req->ns->bdev, ios[WRITE]); + data_units_written = + DIV_ROUND_UP(part_stat_read(req->ns->bdev, sectors[WRITE]), 1000); + + put_unaligned_le64(host_reads, &log->hrc[0]); + put_unaligned_le64(data_units_read, &log->dur[0]); + put_unaligned_le64(host_writes, &log->hwc[0]); + put_unaligned_le64(data_units_written, &log->duw[0]); +copy: + status = nvmet_copy_to_sgl(req, 0, log, sizeof(*log)); + kfree(log); +out: + nvmet_req_complete(req, status); +} + static void nvmet_execute_get_log_page_ana(struct nvmet_req *req) { struct nvme_ana_rsp_hdr hdr = { 0, }; @@ -317,12 +432,44 @@ out: nvmet_req_complete(req, status); } +static void nvmet_execute_get_log_page_features(struct nvmet_req *req) +{ + struct nvme_supported_features_log *features; + u16 status; + + features = kzalloc(sizeof(*features), GFP_KERNEL); + if (!features) { + status = NVME_SC_INTERNAL; + goto out; + } + + features->fis[NVME_FEAT_NUM_QUEUES] = + cpu_to_le32(NVME_FIS_FSUPP | NVME_FIS_CSCPE); + features->fis[NVME_FEAT_KATO] = + cpu_to_le32(NVME_FIS_FSUPP | NVME_FIS_CSCPE); + features->fis[NVME_FEAT_ASYNC_EVENT] = + cpu_to_le32(NVME_FIS_FSUPP | NVME_FIS_CSCPE); + features->fis[NVME_FEAT_HOST_ID] = + cpu_to_le32(NVME_FIS_FSUPP | NVME_FIS_CSCPE); + features->fis[NVME_FEAT_WRITE_PROTECT] = + cpu_to_le32(NVME_FIS_FSUPP | NVME_FIS_NSCPE); + features->fis[NVME_FEAT_RESV_MASK] = + cpu_to_le32(NVME_FIS_FSUPP | NVME_FIS_NSCPE); + + status = nvmet_copy_to_sgl(req, 0, features, sizeof(*features)); + kfree(features); +out: + nvmet_req_complete(req, status); +} + static void nvmet_execute_get_log_page(struct nvmet_req *req) { if (!nvmet_check_transfer_len(req, nvmet_get_log_page_len(req->cmd))) return; switch (req->cmd->get_log_page.lid) { + case NVME_LOG_SUPPORTED: + return nvmet_execute_get_supported_log_pages(req); case NVME_LOG_ERROR: return nvmet_execute_get_log_page_error(req); case NVME_LOG_SMART: @@ -338,8 +485,16 @@ static void nvmet_execute_get_log_page(struct nvmet_req *req) return nvmet_execute_get_log_changed_ns(req); case NVME_LOG_CMD_EFFECTS: return nvmet_execute_get_log_cmd_effects_ns(req); + case NVME_LOG_ENDURANCE_GROUP: + return nvmet_execute_get_log_page_endgrp(req); case NVME_LOG_ANA: return nvmet_execute_get_log_page_ana(req); + case NVME_LOG_FEATURES: + return nvmet_execute_get_log_page_features(req); + case NVME_LOG_RMI: + return nvmet_execute_get_log_page_rmi(req); + case NVME_LOG_RESERVATION: + return nvmet_execute_get_log_page_resv(req); } pr_debug("unhandled lid %d on qid %d\n", req->cmd->get_log_page.lid, req->sq->qid); @@ -433,7 +588,8 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req) id->nn = cpu_to_le32(NVMET_MAX_NAMESPACES); id->mnan = cpu_to_le32(NVMET_MAX_NAMESPACES); id->oncs = cpu_to_le16(NVME_CTRL_ONCS_DSM | - NVME_CTRL_ONCS_WRITE_ZEROES); + NVME_CTRL_ONCS_WRITE_ZEROES | + NVME_CTRL_ONCS_RESERVATIONS); /* XXX: don't report vwc if the underlying device is write through */ id->vwc = NVME_CTRL_VWC_PRESENT; @@ -467,6 +623,13 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req) id->msdbd = ctrl->ops->msdbd; + /* + * Endurance group identifier is 16 bits, so we can't let namespaces + * overflow that since we reuse the nsid + */ + BUILD_BUG_ON(NVMET_MAX_NAMESPACES > USHRT_MAX); + id->endgidmax = cpu_to_le16(NVMET_MAX_NAMESPACES); + id->anacap = (1 << 0) | (1 << 1) | (1 << 2) | (1 << 3) | (1 << 4); id->anatt = 10; /* random value */ id->anagrpmax = cpu_to_le32(NVMET_MAX_ANAGRPS); @@ -551,6 +714,21 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req) id->nmic = NVME_NS_NMIC_SHARED; id->anagrpid = cpu_to_le32(req->ns->anagrpid); + if (req->ns->pr.enable) + id->rescap = NVME_PR_SUPPORT_WRITE_EXCLUSIVE | + NVME_PR_SUPPORT_EXCLUSIVE_ACCESS | + NVME_PR_SUPPORT_WRITE_EXCLUSIVE_REG_ONLY | + NVME_PR_SUPPORT_EXCLUSIVE_ACCESS_REG_ONLY | + NVME_PR_SUPPORT_WRITE_EXCLUSIVE_ALL_REGS | + NVME_PR_SUPPORT_EXCLUSIVE_ACCESS_ALL_REGS | + NVME_PR_SUPPORT_IEKEY_VER_1_3_DEF; + + /* + * Since we don't know any better, every namespace is its own endurance + * group. + */ + id->endgid = cpu_to_le16(req->ns->nsid); + memcpy(&id->nguid, &req->ns->nguid, sizeof(id->nguid)); id->lbaf[0].ds = req->ns->blksize_shift; @@ -576,7 +754,40 @@ out: nvmet_req_complete(req, status); } -static void nvmet_execute_identify_nslist(struct nvmet_req *req) +static void nvmet_execute_identify_endgrp_list(struct nvmet_req *req) +{ + u16 min_endgid = le16_to_cpu(req->cmd->identify.cnssid); + static const int buf_size = NVME_IDENTIFY_DATA_SIZE; + struct nvmet_ctrl *ctrl = req->sq->ctrl; + struct nvmet_ns *ns; + unsigned long idx; + __le16 *list; + u16 status; + int i = 1; + + list = kzalloc(buf_size, GFP_KERNEL); + if (!list) { + status = NVME_SC_INTERNAL; + goto out; + } + + xa_for_each(&ctrl->subsys->namespaces, idx, ns) { + if (ns->nsid <= min_endgid) + continue; + + list[i++] = cpu_to_le16(ns->nsid); + if (i == buf_size / sizeof(__le16)) + break; + } + + list[0] = cpu_to_le16(i - 1); + status = nvmet_copy_to_sgl(req, 0, list, buf_size); + kfree(list); +out: + nvmet_req_complete(req, status); +} + +static void nvmet_execute_identify_nslist(struct nvmet_req *req, bool match_css) { static const int buf_size = NVME_IDENTIFY_DATA_SIZE; struct nvmet_ctrl *ctrl = req->sq->ctrl; @@ -606,6 +817,8 @@ static void nvmet_execute_identify_nslist(struct nvmet_req *req) xa_for_each(&ctrl->subsys->namespaces, idx, ns) { if (ns->nsid <= min_nsid) continue; + if (match_css && req->ns->csi != req->cmd->identify.csi) + continue; list[i++] = cpu_to_le32(ns->nsid); if (i == buf_size / sizeof(__le32)) break; @@ -685,6 +898,56 @@ static void nvmet_execute_identify_ctrl_nvm(struct nvmet_req *req) nvmet_zero_sgl(req, 0, sizeof(struct nvme_id_ctrl_nvm))); } +static void nvme_execute_identify_ns_nvm(struct nvmet_req *req) +{ + u16 status; + + status = nvmet_req_find_ns(req); + if (status) + goto out; + + status = nvmet_copy_to_sgl(req, 0, ZERO_PAGE(0), + NVME_IDENTIFY_DATA_SIZE); +out: + nvmet_req_complete(req, status); +} + +static void nvmet_execute_id_cs_indep(struct nvmet_req *req) +{ + struct nvme_id_ns_cs_indep *id; + u16 status; + + status = nvmet_req_find_ns(req); + if (status) + goto out; + + id = kzalloc(sizeof(*id), GFP_KERNEL); + if (!id) { + status = NVME_SC_INTERNAL; + goto out; + } + + id->nstat = NVME_NSTAT_NRDY; + id->anagrpid = cpu_to_le32(req->ns->anagrpid); + id->nmic = NVME_NS_NMIC_SHARED; + if (req->ns->readonly) + id->nsattr |= NVME_NS_ATTR_RO; + if (req->ns->bdev && !bdev_nonrot(req->ns->bdev)) + id->nsfeat |= NVME_NS_ROTATIONAL; + /* + * We need flush command to flush the file's metadata, + * so report supporting vwc if backend is file, even + * though buffered_io is disable. + */ + if (req->ns->bdev && !bdev_write_cache(req->ns->bdev)) + id->nsfeat |= NVME_NS_VWC_NOT_PRESENT; + + status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id)); + kfree(id); +out: + nvmet_req_complete(req, status); +} + static void nvmet_execute_identify(struct nvmet_req *req) { if (!nvmet_check_transfer_len(req, NVME_IDENTIFY_DATA_SIZE)) @@ -698,7 +961,7 @@ static void nvmet_execute_identify(struct nvmet_req *req) nvmet_execute_identify_ctrl(req); return; case NVME_ID_CNS_NS_ACTIVE_LIST: - nvmet_execute_identify_nslist(req); + nvmet_execute_identify_nslist(req, false); return; case NVME_ID_CNS_NS_DESC_LIST: nvmet_execute_identify_desclist(req); @@ -706,8 +969,8 @@ static void nvmet_execute_identify(struct nvmet_req *req) case NVME_ID_CNS_CS_NS: switch (req->cmd->identify.csi) { case NVME_CSI_NVM: - /* Not supported */ - break; + nvme_execute_identify_ns_nvm(req); + return; case NVME_CSI_ZNS: if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) { nvmet_execute_identify_ns_zns(req); @@ -729,6 +992,15 @@ static void nvmet_execute_identify(struct nvmet_req *req) break; } break; + case NVME_ID_CNS_NS_ACTIVE_LIST_CS: + nvmet_execute_identify_nslist(req, true); + return; + case NVME_ID_CNS_NS_CS_INDEP: + nvmet_execute_id_cs_indep(req); + return; + case NVME_ID_CNS_ENDGRP_LIST: + nvmet_execute_identify_endgrp_list(req); + return; } pr_debug("unhandled identify cns %d on qid %d\n", @@ -861,6 +1133,9 @@ void nvmet_execute_set_features(struct nvmet_req *req) case NVME_FEAT_WRITE_PROTECT: status = nvmet_set_feat_write_protect(req); break; + case NVME_FEAT_RESV_MASK: + status = nvmet_set_feat_resv_notif_mask(req, cdw11); + break; default: req->error_loc = offsetof(struct nvme_common_command, cdw10); status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; @@ -959,6 +1234,9 @@ void nvmet_execute_get_features(struct nvmet_req *req) case NVME_FEAT_WRITE_PROTECT: status = nvmet_get_feat_write_protect(req); break; + case NVME_FEAT_RESV_MASK: + status = nvmet_get_feat_resv_notif_mask(req); + break; default: req->error_loc = offsetof(struct nvme_common_command, cdw10); diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index 685e89b35d33..eeee9e9b854c 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -769,6 +769,32 @@ static ssize_t nvmet_ns_revalidate_size_store(struct config_item *item, CONFIGFS_ATTR_WO(nvmet_ns_, revalidate_size); +static ssize_t nvmet_ns_resv_enable_show(struct config_item *item, char *page) +{ + return sysfs_emit(page, "%d\n", to_nvmet_ns(item)->pr.enable); +} + +static ssize_t nvmet_ns_resv_enable_store(struct config_item *item, + const char *page, size_t count) +{ + struct nvmet_ns *ns = to_nvmet_ns(item); + bool val; + + if (kstrtobool(page, &val)) + return -EINVAL; + + mutex_lock(&ns->subsys->lock); + if (ns->enabled) { + pr_err("the ns:%d is already enabled.\n", ns->nsid); + mutex_unlock(&ns->subsys->lock); + return -EINVAL; + } + ns->pr.enable = val; + mutex_unlock(&ns->subsys->lock); + return count; +} +CONFIGFS_ATTR(nvmet_ns_, resv_enable); + static struct configfs_attribute *nvmet_ns_attrs[] = { &nvmet_ns_attr_device_path, &nvmet_ns_attr_device_nguid, @@ -777,6 +803,7 @@ static struct configfs_attribute *nvmet_ns_attrs[] = { &nvmet_ns_attr_enable, &nvmet_ns_attr_buffered_io, &nvmet_ns_attr_revalidate_size, + &nvmet_ns_attr_resv_enable, #ifdef CONFIG_PCI_P2PDMA &nvmet_ns_attr_p2pmem, #endif diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index ed2424f8a396..1f4e9989663b 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -611,6 +611,12 @@ int nvmet_ns_enable(struct nvmet_ns *ns) if (ret) goto out_restore_subsys_maxnsid; + if (ns->pr.enable) { + ret = nvmet_pr_init_ns(ns); + if (ret) + goto out_remove_from_subsys; + } + subsys->nr_namespaces++; nvmet_ns_changed(subsys, ns->nsid); @@ -620,6 +626,8 @@ out_unlock: mutex_unlock(&subsys->lock); return ret; +out_remove_from_subsys: + xa_erase(&subsys->namespaces, ns->nsid); out_restore_subsys_maxnsid: subsys->max_nsid = nvmet_max_nsid(subsys); percpu_ref_exit(&ns->ref); @@ -663,6 +671,9 @@ void nvmet_ns_disable(struct nvmet_ns *ns) wait_for_completion(&ns->disable_done); percpu_ref_exit(&ns->ref); + if (ns->pr.enable) + nvmet_pr_exit_ns(ns); + mutex_lock(&subsys->lock); subsys->nr_namespaces--; @@ -754,6 +765,7 @@ static void nvmet_set_error(struct nvmet_req *req, u16 status) static void __nvmet_req_complete(struct nvmet_req *req, u16 status) { struct nvmet_ns *ns = req->ns; + struct nvmet_pr_per_ctrl_ref *pc_ref = req->pc_ref; if (!req->sq->sqhd_disabled) nvmet_update_sq_head(req); @@ -766,6 +778,9 @@ static void __nvmet_req_complete(struct nvmet_req *req, u16 status) trace_nvmet_req_complete(req); req->ops->queue_response(req); + + if (pc_ref) + nvmet_pr_put_ns_pc_ref(pc_ref); if (ns) nvmet_put_namespace(ns); } @@ -929,18 +944,39 @@ static u16 nvmet_parse_io_cmd(struct nvmet_req *req) return ret; } + if (req->ns->pr.enable) { + ret = nvmet_parse_pr_cmd(req); + if (!ret) + return ret; + } + switch (req->ns->csi) { case NVME_CSI_NVM: if (req->ns->file) - return nvmet_file_parse_io_cmd(req); - return nvmet_bdev_parse_io_cmd(req); + ret = nvmet_file_parse_io_cmd(req); + else + ret = nvmet_bdev_parse_io_cmd(req); + break; case NVME_CSI_ZNS: if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) - return nvmet_bdev_zns_parse_io_cmd(req); - return NVME_SC_INVALID_IO_CMD_SET; + ret = nvmet_bdev_zns_parse_io_cmd(req); + else + ret = NVME_SC_INVALID_IO_CMD_SET; + break; default: - return NVME_SC_INVALID_IO_CMD_SET; + ret = NVME_SC_INVALID_IO_CMD_SET; } + if (ret) + return ret; + + if (req->ns->pr.enable) { + ret = nvmet_pr_check_cmd_access(req); + if (ret) + return ret; + + ret = nvmet_pr_get_ns_pc_ref(req); + } + return ret; } bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, @@ -964,6 +1000,7 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, req->ns = NULL; req->error_loc = NVMET_NO_ERROR_LOC; req->error_slba = 0; + req->pc_ref = NULL; /* no support for fused commands yet */ if (unlikely(flags & (NVME_CMD_FUSE_FIRST | NVME_CMD_FUSE_SECOND))) { @@ -1015,6 +1052,8 @@ EXPORT_SYMBOL_GPL(nvmet_req_init); void nvmet_req_uninit(struct nvmet_req *req) { percpu_ref_put(&req->sq->ref); + if (req->pc_ref) + nvmet_pr_put_ns_pc_ref(req->pc_ref); if (req->ns) nvmet_put_namespace(req->ns); } @@ -1383,7 +1422,8 @@ static void nvmet_fatal_error_handler(struct work_struct *work) } u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, - struct nvmet_req *req, u32 kato, struct nvmet_ctrl **ctrlp) + struct nvmet_req *req, u32 kato, struct nvmet_ctrl **ctrlp, + uuid_t *hostid) { struct nvmet_subsys *subsys; struct nvmet_ctrl *ctrl; @@ -1462,6 +1502,8 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, } ctrl->cntlid = ret; + uuid_copy(&ctrl->hostid, hostid); + /* * Discovery controllers may use some arbitrary high value * in order to cleanup stale discovery sessions @@ -1478,6 +1520,9 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, nvmet_start_keep_alive_timer(ctrl); mutex_lock(&subsys->lock); + ret = nvmet_ctrl_init_pr(ctrl); + if (ret) + goto init_pr_fail; list_add_tail(&ctrl->subsys_entry, &subsys->ctrls); nvmet_setup_p2p_ns_map(ctrl, req); nvmet_debugfs_ctrl_setup(ctrl); @@ -1486,6 +1531,10 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, *ctrlp = ctrl; return 0; +init_pr_fail: + mutex_unlock(&subsys->lock); + nvmet_stop_keep_alive_timer(ctrl); + ida_free(&cntlid_ida, ctrl->cntlid); out_free_sqs: kfree(ctrl->sqs); out_free_changed_ns_list: @@ -1504,6 +1553,7 @@ static void nvmet_ctrl_free(struct kref *ref) struct nvmet_subsys *subsys = ctrl->subsys; mutex_lock(&subsys->lock); + nvmet_ctrl_destroy_pr(ctrl); nvmet_release_p2p_ns_map(ctrl); list_del(&ctrl->subsys_entry); mutex_unlock(&subsys->lock); @@ -1717,7 +1767,7 @@ static int __init nvmet_init(void) goto out_free_zbd_work_queue; nvmet_wq = alloc_workqueue("nvmet-wq", - WQ_MEM_RECLAIM | WQ_UNBOUND, 0); + WQ_MEM_RECLAIM | WQ_UNBOUND | WQ_SYSFS, 0); if (!nvmet_wq) goto out_free_buffered_work_queue; diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c index c4b2eddd5666..c49904ebb6c2 100644 --- a/drivers/nvme/target/fabrics-cmd.c +++ b/drivers/nvme/target/fabrics-cmd.c @@ -64,6 +64,9 @@ static void nvmet_execute_prop_get(struct nvmet_req *req) case NVME_REG_CSTS: val = ctrl->csts; break; + case NVME_REG_CRTO: + val = NVME_CAP_TIMEOUT(ctrl->csts); + break; default: status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; break; @@ -245,12 +248,10 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req) d->subsysnqn[NVMF_NQN_FIELD_LEN - 1] = '\0'; d->hostnqn[NVMF_NQN_FIELD_LEN - 1] = '\0'; status = nvmet_alloc_ctrl(d->subsysnqn, d->hostnqn, req, - le32_to_cpu(c->kato), &ctrl); + le32_to_cpu(c->kato), &ctrl, &d->hostid); if (status) goto out; - uuid_copy(&ctrl->hostid, &d->hostid); - dhchap_status = nvmet_setup_auth(ctrl); if (dhchap_status) { pr_err("Failed to setup authentication, dhchap status %u\n", diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 190f55e6d753..58328b35dc96 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -20,8 +20,9 @@ #include <linux/blkdev.h> #include <linux/radix-tree.h> #include <linux/t10-pi.h> +#include <linux/kfifo.h> -#define NVMET_DEFAULT_VS NVME_VS(1, 3, 0) +#define NVMET_DEFAULT_VS NVME_VS(2, 1, 0) #define NVMET_ASYNC_EVENTS 4 #define NVMET_ERROR_LOG_SLOTS 128 @@ -30,6 +31,7 @@ #define NVMET_MN_MAX_SIZE 40 #define NVMET_SN_MAX_SIZE 20 #define NVMET_FR_MAX_SIZE 8 +#define NVMET_PR_LOG_QUEUE_SIZE 64 /* * Supported optional AENs: @@ -56,6 +58,38 @@ #define IPO_IATTR_CONNECT_SQE(x) \ (cpu_to_le32(offsetof(struct nvmf_connect_command, x))) +struct nvmet_pr_registrant { + u64 rkey; + uuid_t hostid; + enum nvme_pr_type rtype; + struct list_head entry; + struct rcu_head rcu; +}; + +struct nvmet_pr { + bool enable; + unsigned long notify_mask; + atomic_t generation; + struct nvmet_pr_registrant __rcu *holder; + /* + * During the execution of the reservation command, mutual + * exclusion is required throughout the process. However, + * while waiting asynchronously for the 'per controller + * percpu_ref' to complete before the 'preempt and abort' + * command finishes, a semaphore is needed to ensure mutual + * exclusion instead of a mutex. + */ + struct semaphore pr_sem; + struct list_head registrant_list; +}; + +struct nvmet_pr_per_ctrl_ref { + struct percpu_ref ref; + struct completion free_done; + struct completion confirm_done; + uuid_t hostid; +}; + struct nvmet_ns { struct percpu_ref ref; struct file *bdev_file; @@ -85,6 +119,8 @@ struct nvmet_ns { int pi_type; int metadata_size; u8 csi; + struct nvmet_pr pr; + struct xarray pr_per_ctrl_refs; }; static inline struct nvmet_ns *to_nvmet_ns(struct config_item *item) @@ -191,6 +227,13 @@ static inline bool nvmet_port_secure_channel_required(struct nvmet_port *port) return nvmet_port_disc_addr_treq_secure_channel(port) == NVMF_TREQ_REQUIRED; } +struct nvmet_pr_log_mgr { + struct mutex lock; + u64 lost_count; + u64 counter; + DECLARE_KFIFO(log_queue, struct nvme_pr_log, NVMET_PR_LOG_QUEUE_SIZE); +}; + struct nvmet_ctrl { struct nvmet_subsys *subsys; struct nvmet_sq **sqs; @@ -246,6 +289,7 @@ struct nvmet_ctrl { u8 *dh_key; size_t dh_keysize; #endif + struct nvmet_pr_log_mgr pr_log_mgr; }; struct nvmet_subsys { @@ -396,6 +440,9 @@ struct nvmet_req { struct work_struct zmgmt_work; } z; #endif /* CONFIG_BLK_DEV_ZONED */ + struct { + struct work_struct abort_work; + } r; }; int sg_cnt; int metadata_sg_cnt; @@ -412,6 +459,7 @@ struct nvmet_req { struct device *p2p_client; u16 error_loc; u64 error_slba; + struct nvmet_pr_per_ctrl_ref *pc_ref; }; #define NVMET_MAX_MPOOL_BVEC 16 @@ -498,7 +546,8 @@ void nvmet_ctrl_fatal_error(struct nvmet_ctrl *ctrl); void nvmet_update_cc(struct nvmet_ctrl *ctrl, u32 new); u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, - struct nvmet_req *req, u32 kato, struct nvmet_ctrl **ctrlp); + struct nvmet_req *req, u32 kato, struct nvmet_ctrl **ctrlp, + uuid_t *hostid); struct nvmet_ctrl *nvmet_ctrl_find_get(const char *subsysnqn, const char *hostnqn, u16 cntlid, struct nvmet_req *req); @@ -761,4 +810,18 @@ static inline bool nvmet_has_auth(struct nvmet_ctrl *ctrl) static inline const char *nvmet_dhchap_dhgroup_name(u8 dhgid) { return NULL; } #endif +int nvmet_pr_init_ns(struct nvmet_ns *ns); +u16 nvmet_parse_pr_cmd(struct nvmet_req *req); +u16 nvmet_pr_check_cmd_access(struct nvmet_req *req); +int nvmet_ctrl_init_pr(struct nvmet_ctrl *ctrl); +void nvmet_ctrl_destroy_pr(struct nvmet_ctrl *ctrl); +void nvmet_pr_exit_ns(struct nvmet_ns *ns); +void nvmet_execute_get_log_page_resv(struct nvmet_req *req); +u16 nvmet_set_feat_resv_notif_mask(struct nvmet_req *req, u32 mask); +u16 nvmet_get_feat_resv_notif_mask(struct nvmet_req *req); +u16 nvmet_pr_get_ns_pc_ref(struct nvmet_req *req); +static inline void nvmet_pr_put_ns_pc_ref(struct nvmet_pr_per_ctrl_ref *pc_ref) +{ + percpu_ref_put(&pc_ref->ref); +} #endif /* _NVMET_H */ diff --git a/drivers/nvme/target/pr.c b/drivers/nvme/target/pr.c new file mode 100644 index 000000000000..25a02b50d9f3 --- /dev/null +++ b/drivers/nvme/target/pr.c @@ -0,0 +1,1156 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * NVMe over Fabrics Persist Reservation. + * Copyright (c) 2024 Guixin Liu, Alibaba Group. + * All rights reserved. + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/unaligned.h> +#include "nvmet.h" + +#define NVMET_PR_NOTIFI_MASK_ALL \ + (1 << NVME_PR_NOTIFY_BIT_REG_PREEMPTED | \ + 1 << NVME_PR_NOTIFY_BIT_RESV_RELEASED | \ + 1 << NVME_PR_NOTIFY_BIT_RESV_PREEMPTED) + +static inline bool nvmet_pr_parse_ignore_key(u32 cdw10) +{ + /* Ignore existing key, bit 03. */ + return (cdw10 >> 3) & 1; +} + +static inline struct nvmet_ns *nvmet_pr_to_ns(struct nvmet_pr *pr) +{ + return container_of(pr, struct nvmet_ns, pr); +} + +static struct nvmet_pr_registrant * +nvmet_pr_find_registrant(struct nvmet_pr *pr, uuid_t *hostid) +{ + struct nvmet_pr_registrant *reg; + + list_for_each_entry_rcu(reg, &pr->registrant_list, entry) { + if (uuid_equal(®->hostid, hostid)) + return reg; + } + return NULL; +} + +u16 nvmet_set_feat_resv_notif_mask(struct nvmet_req *req, u32 mask) +{ + u32 nsid = le32_to_cpu(req->cmd->common.nsid); + struct nvmet_ctrl *ctrl = req->sq->ctrl; + struct nvmet_ns *ns; + unsigned long idx; + u16 status; + + if (mask & ~(NVMET_PR_NOTIFI_MASK_ALL)) { + req->error_loc = offsetof(struct nvme_common_command, cdw11); + return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; + } + + if (nsid != U32_MAX) { + status = nvmet_req_find_ns(req); + if (status) + return status; + if (!req->ns->pr.enable) + return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; + + WRITE_ONCE(req->ns->pr.notify_mask, mask); + goto success; + } + + xa_for_each(&ctrl->subsys->namespaces, idx, ns) { + if (ns->pr.enable) + WRITE_ONCE(ns->pr.notify_mask, mask); + } + +success: + nvmet_set_result(req, mask); + return NVME_SC_SUCCESS; +} + +u16 nvmet_get_feat_resv_notif_mask(struct nvmet_req *req) +{ + u16 status; + + status = nvmet_req_find_ns(req); + if (status) + return status; + + if (!req->ns->pr.enable) + return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; + + nvmet_set_result(req, READ_ONCE(req->ns->pr.notify_mask)); + return status; +} + +void nvmet_execute_get_log_page_resv(struct nvmet_req *req) +{ + struct nvmet_pr_log_mgr *log_mgr = &req->sq->ctrl->pr_log_mgr; + struct nvme_pr_log next_log = {0}; + struct nvme_pr_log log = {0}; + u16 status = NVME_SC_SUCCESS; + u64 lost_count; + u64 cur_count; + u64 next_count; + + mutex_lock(&log_mgr->lock); + if (!kfifo_get(&log_mgr->log_queue, &log)) + goto out; + + /* + * We can't get the last in kfifo. + * Utilize the current count and the count from the next log to + * calculate the number of lost logs, while also addressing cases + * of overflow. If there is no subsequent log, the number of lost + * logs is equal to the lost_count within the nvmet_pr_log_mgr. + */ + cur_count = le64_to_cpu(log.count); + if (kfifo_peek(&log_mgr->log_queue, &next_log)) { + next_count = le64_to_cpu(next_log.count); + if (next_count > cur_count) + lost_count = next_count - cur_count - 1; + else + lost_count = U64_MAX - cur_count + next_count - 1; + } else { + lost_count = log_mgr->lost_count; + } + + log.count = cpu_to_le64((cur_count + lost_count) == 0 ? + 1 : (cur_count + lost_count)); + log_mgr->lost_count -= lost_count; + + log.nr_pages = kfifo_len(&log_mgr->log_queue); + +out: + status = nvmet_copy_to_sgl(req, 0, &log, sizeof(log)); + mutex_unlock(&log_mgr->lock); + nvmet_req_complete(req, status); +} + +static void nvmet_pr_add_resv_log(struct nvmet_ctrl *ctrl, u8 log_type, + u32 nsid) +{ + struct nvmet_pr_log_mgr *log_mgr = &ctrl->pr_log_mgr; + struct nvme_pr_log log = {0}; + + mutex_lock(&log_mgr->lock); + log_mgr->counter++; + if (log_mgr->counter == 0) + log_mgr->counter = 1; + + log.count = cpu_to_le64(log_mgr->counter); + log.type = log_type; + log.nsid = cpu_to_le32(nsid); + + if (!kfifo_put(&log_mgr->log_queue, log)) { + pr_info("a reservation log lost, cntlid:%d, log_type:%d, nsid:%d\n", + ctrl->cntlid, log_type, nsid); + log_mgr->lost_count++; + } + + mutex_unlock(&log_mgr->lock); +} + +static void nvmet_pr_resv_released(struct nvmet_pr *pr, uuid_t *hostid) +{ + struct nvmet_ns *ns = nvmet_pr_to_ns(pr); + struct nvmet_subsys *subsys = ns->subsys; + struct nvmet_ctrl *ctrl; + + if (test_bit(NVME_PR_NOTIFY_BIT_RESV_RELEASED, &pr->notify_mask)) + return; + + mutex_lock(&subsys->lock); + list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) { + if (!uuid_equal(&ctrl->hostid, hostid) && + nvmet_pr_find_registrant(pr, &ctrl->hostid)) { + nvmet_pr_add_resv_log(ctrl, + NVME_PR_LOG_RESERVATION_RELEASED, ns->nsid); + nvmet_add_async_event(ctrl, NVME_AER_CSS, + NVME_AEN_RESV_LOG_PAGE_AVALIABLE, + NVME_LOG_RESERVATION); + } + } + mutex_unlock(&subsys->lock); +} + +static void nvmet_pr_send_event_to_host(struct nvmet_pr *pr, uuid_t *hostid, + u8 log_type) +{ + struct nvmet_ns *ns = nvmet_pr_to_ns(pr); + struct nvmet_subsys *subsys = ns->subsys; + struct nvmet_ctrl *ctrl; + + mutex_lock(&subsys->lock); + list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) { + if (uuid_equal(hostid, &ctrl->hostid)) { + nvmet_pr_add_resv_log(ctrl, log_type, ns->nsid); + nvmet_add_async_event(ctrl, NVME_AER_CSS, + NVME_AEN_RESV_LOG_PAGE_AVALIABLE, + NVME_LOG_RESERVATION); + } + } + mutex_unlock(&subsys->lock); +} + +static void nvmet_pr_resv_preempted(struct nvmet_pr *pr, uuid_t *hostid) +{ + if (test_bit(NVME_PR_NOTIFY_BIT_RESV_PREEMPTED, &pr->notify_mask)) + return; + + nvmet_pr_send_event_to_host(pr, hostid, + NVME_PR_LOG_RESERVATOIN_PREEMPTED); +} + +static void nvmet_pr_registration_preempted(struct nvmet_pr *pr, + uuid_t *hostid) +{ + if (test_bit(NVME_PR_NOTIFY_BIT_REG_PREEMPTED, &pr->notify_mask)) + return; + + nvmet_pr_send_event_to_host(pr, hostid, + NVME_PR_LOG_REGISTRATION_PREEMPTED); +} + +static inline void nvmet_pr_set_new_holder(struct nvmet_pr *pr, u8 new_rtype, + struct nvmet_pr_registrant *reg) +{ + reg->rtype = new_rtype; + rcu_assign_pointer(pr->holder, reg); +} + +static u16 nvmet_pr_register(struct nvmet_req *req, + struct nvmet_pr_register_data *d) +{ + struct nvmet_ctrl *ctrl = req->sq->ctrl; + struct nvmet_pr_registrant *new, *reg; + struct nvmet_pr *pr = &req->ns->pr; + u16 status = NVME_SC_SUCCESS; + u64 nrkey = le64_to_cpu(d->nrkey); + + new = kmalloc(sizeof(*new), GFP_KERNEL); + if (!new) + return NVME_SC_INTERNAL; + + down(&pr->pr_sem); + reg = nvmet_pr_find_registrant(pr, &ctrl->hostid); + if (reg) { + if (reg->rkey != nrkey) + status = NVME_SC_RESERVATION_CONFLICT | NVME_STATUS_DNR; + kfree(new); + goto out; + } + + memset(new, 0, sizeof(*new)); + INIT_LIST_HEAD(&new->entry); + new->rkey = nrkey; + uuid_copy(&new->hostid, &ctrl->hostid); + list_add_tail_rcu(&new->entry, &pr->registrant_list); + +out: + up(&pr->pr_sem); + return status; +} + +static void nvmet_pr_unregister_one(struct nvmet_pr *pr, + struct nvmet_pr_registrant *reg) +{ + struct nvmet_pr_registrant *first_reg; + struct nvmet_pr_registrant *holder; + u8 original_rtype; + + list_del_rcu(®->entry); + + holder = rcu_dereference_protected(pr->holder, 1); + if (reg != holder) + goto out; + + original_rtype = holder->rtype; + if (original_rtype == NVME_PR_WRITE_EXCLUSIVE_ALL_REGS || + original_rtype == NVME_PR_EXCLUSIVE_ACCESS_ALL_REGS) { + first_reg = list_first_or_null_rcu(&pr->registrant_list, + struct nvmet_pr_registrant, entry); + if (first_reg) + first_reg->rtype = original_rtype; + rcu_assign_pointer(pr->holder, first_reg); + } else { + rcu_assign_pointer(pr->holder, NULL); + + if (original_rtype == NVME_PR_WRITE_EXCLUSIVE_REG_ONLY || + original_rtype == NVME_PR_EXCLUSIVE_ACCESS_REG_ONLY) + nvmet_pr_resv_released(pr, ®->hostid); + } +out: + kfree_rcu(reg, rcu); +} + +static u16 nvmet_pr_unregister(struct nvmet_req *req, + struct nvmet_pr_register_data *d, + bool ignore_key) +{ + u16 status = NVME_SC_RESERVATION_CONFLICT | NVME_STATUS_DNR; + struct nvmet_ctrl *ctrl = req->sq->ctrl; + struct nvmet_pr *pr = &req->ns->pr; + struct nvmet_pr_registrant *reg; + + down(&pr->pr_sem); + list_for_each_entry_rcu(reg, &pr->registrant_list, entry) { + if (uuid_equal(®->hostid, &ctrl->hostid)) { + if (ignore_key || reg->rkey == le64_to_cpu(d->crkey)) { + status = NVME_SC_SUCCESS; + nvmet_pr_unregister_one(pr, reg); + } + break; + } + } + up(&pr->pr_sem); + + return status; +} + +static void nvmet_pr_update_reg_rkey(struct nvmet_pr_registrant *reg, + void *attr) +{ + reg->rkey = *(u64 *)attr; +} + +static u16 nvmet_pr_update_reg_attr(struct nvmet_pr *pr, + struct nvmet_pr_registrant *reg, + void (*change_attr)(struct nvmet_pr_registrant *reg, + void *attr), + void *attr) +{ + struct nvmet_pr_registrant *holder; + struct nvmet_pr_registrant *new; + + holder = rcu_dereference_protected(pr->holder, 1); + if (reg != holder) { + change_attr(reg, attr); + return NVME_SC_SUCCESS; + } + + new = kmalloc(sizeof(*new), GFP_ATOMIC); + if (!new) + return NVME_SC_INTERNAL; + + new->rkey = holder->rkey; + new->rtype = holder->rtype; + uuid_copy(&new->hostid, &holder->hostid); + INIT_LIST_HEAD(&new->entry); + + change_attr(new, attr); + list_replace_rcu(&holder->entry, &new->entry); + rcu_assign_pointer(pr->holder, new); + kfree_rcu(holder, rcu); + + return NVME_SC_SUCCESS; +} + +static u16 nvmet_pr_replace(struct nvmet_req *req, + struct nvmet_pr_register_data *d, + bool ignore_key) +{ + u16 status = NVME_SC_RESERVATION_CONFLICT | NVME_STATUS_DNR; + struct nvmet_ctrl *ctrl = req->sq->ctrl; + struct nvmet_pr *pr = &req->ns->pr; + struct nvmet_pr_registrant *reg; + u64 nrkey = le64_to_cpu(d->nrkey); + + down(&pr->pr_sem); + list_for_each_entry_rcu(reg, &pr->registrant_list, entry) { + if (uuid_equal(®->hostid, &ctrl->hostid)) { + if (ignore_key || reg->rkey == le64_to_cpu(d->crkey)) + status = nvmet_pr_update_reg_attr(pr, reg, + nvmet_pr_update_reg_rkey, + &nrkey); + break; + } + } + up(&pr->pr_sem); + return status; +} + +static void nvmet_execute_pr_register(struct nvmet_req *req) +{ + u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10); + bool ignore_key = nvmet_pr_parse_ignore_key(cdw10); + struct nvmet_pr_register_data *d; + u8 reg_act = cdw10 & 0x07; /* Reservation Register Action, bit 02:00 */ + u16 status; + + d = kmalloc(sizeof(*d), GFP_KERNEL); + if (!d) { + status = NVME_SC_INTERNAL; + goto out; + } + + status = nvmet_copy_from_sgl(req, 0, d, sizeof(*d)); + if (status) + goto free_data; + + switch (reg_act) { + case NVME_PR_REGISTER_ACT_REG: + status = nvmet_pr_register(req, d); + break; + case NVME_PR_REGISTER_ACT_UNREG: + status = nvmet_pr_unregister(req, d, ignore_key); + break; + case NVME_PR_REGISTER_ACT_REPLACE: + status = nvmet_pr_replace(req, d, ignore_key); + break; + default: + req->error_loc = offsetof(struct nvme_common_command, cdw10); + status = NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR; + break; + } +free_data: + kfree(d); +out: + if (!status) + atomic_inc(&req->ns->pr.generation); + nvmet_req_complete(req, status); +} + +static u16 nvmet_pr_acquire(struct nvmet_req *req, + struct nvmet_pr_registrant *reg, + u8 rtype) +{ + struct nvmet_pr *pr = &req->ns->pr; + struct nvmet_pr_registrant *holder; + + holder = rcu_dereference_protected(pr->holder, 1); + if (holder && reg != holder) + return NVME_SC_RESERVATION_CONFLICT | NVME_STATUS_DNR; + if (holder && reg == holder) { + if (holder->rtype == rtype) + return NVME_SC_SUCCESS; + return NVME_SC_RESERVATION_CONFLICT | NVME_STATUS_DNR; + } + + nvmet_pr_set_new_holder(pr, rtype, reg); + return NVME_SC_SUCCESS; +} + +static void nvmet_pr_confirm_ns_pc_ref(struct percpu_ref *ref) +{ + struct nvmet_pr_per_ctrl_ref *pc_ref = + container_of(ref, struct nvmet_pr_per_ctrl_ref, ref); + + complete(&pc_ref->confirm_done); +} + +static void nvmet_pr_set_ctrl_to_abort(struct nvmet_req *req, uuid_t *hostid) +{ + struct nvmet_pr_per_ctrl_ref *pc_ref; + struct nvmet_ns *ns = req->ns; + unsigned long idx; + + xa_for_each(&ns->pr_per_ctrl_refs, idx, pc_ref) { + if (uuid_equal(&pc_ref->hostid, hostid)) { + percpu_ref_kill_and_confirm(&pc_ref->ref, + nvmet_pr_confirm_ns_pc_ref); + wait_for_completion(&pc_ref->confirm_done); + } + } +} + +static u16 nvmet_pr_unreg_all_host_by_prkey(struct nvmet_req *req, u64 prkey, + uuid_t *send_hostid, + bool abort) +{ + u16 status = NVME_SC_RESERVATION_CONFLICT | NVME_STATUS_DNR; + struct nvmet_pr_registrant *reg, *tmp; + struct nvmet_pr *pr = &req->ns->pr; + uuid_t hostid; + + list_for_each_entry_safe(reg, tmp, &pr->registrant_list, entry) { + if (reg->rkey == prkey) { + status = NVME_SC_SUCCESS; + uuid_copy(&hostid, ®->hostid); + if (abort) + nvmet_pr_set_ctrl_to_abort(req, &hostid); + nvmet_pr_unregister_one(pr, reg); + if (!uuid_equal(&hostid, send_hostid)) + nvmet_pr_registration_preempted(pr, &hostid); + } + } + return status; +} + +static void nvmet_pr_unreg_all_others_by_prkey(struct nvmet_req *req, + u64 prkey, + uuid_t *send_hostid, + bool abort) +{ + struct nvmet_pr_registrant *reg, *tmp; + struct nvmet_pr *pr = &req->ns->pr; + uuid_t hostid; + + list_for_each_entry_safe(reg, tmp, &pr->registrant_list, entry) { + if (reg->rkey == prkey && + !uuid_equal(®->hostid, send_hostid)) { + uuid_copy(&hostid, ®->hostid); + if (abort) + nvmet_pr_set_ctrl_to_abort(req, &hostid); + nvmet_pr_unregister_one(pr, reg); + nvmet_pr_registration_preempted(pr, &hostid); + } + } +} + +static void nvmet_pr_unreg_all_others(struct nvmet_req *req, + uuid_t *send_hostid, + bool abort) +{ + struct nvmet_pr_registrant *reg, *tmp; + struct nvmet_pr *pr = &req->ns->pr; + uuid_t hostid; + + list_for_each_entry_safe(reg, tmp, &pr->registrant_list, entry) { + if (!uuid_equal(®->hostid, send_hostid)) { + uuid_copy(&hostid, ®->hostid); + if (abort) + nvmet_pr_set_ctrl_to_abort(req, &hostid); + nvmet_pr_unregister_one(pr, reg); + nvmet_pr_registration_preempted(pr, &hostid); + } + } +} + +static void nvmet_pr_update_holder_rtype(struct nvmet_pr_registrant *reg, + void *attr) +{ + u8 new_rtype = *(u8 *)attr; + + reg->rtype = new_rtype; +} + +static u16 nvmet_pr_preempt(struct nvmet_req *req, + struct nvmet_pr_registrant *reg, + u8 rtype, + struct nvmet_pr_acquire_data *d, + bool abort) +{ + struct nvmet_ctrl *ctrl = req->sq->ctrl; + struct nvmet_pr *pr = &req->ns->pr; + struct nvmet_pr_registrant *holder; + enum nvme_pr_type original_rtype; + u64 prkey = le64_to_cpu(d->prkey); + u16 status; + + holder = rcu_dereference_protected(pr->holder, 1); + if (!holder) + return nvmet_pr_unreg_all_host_by_prkey(req, prkey, + &ctrl->hostid, abort); + + original_rtype = holder->rtype; + if (original_rtype == NVME_PR_WRITE_EXCLUSIVE_ALL_REGS || + original_rtype == NVME_PR_EXCLUSIVE_ACCESS_ALL_REGS) { + if (!prkey) { + /* + * To prevent possible access from other hosts, and + * avoid terminate the holder, set the new holder + * first before unregistering. + */ + nvmet_pr_set_new_holder(pr, rtype, reg); + nvmet_pr_unreg_all_others(req, &ctrl->hostid, abort); + return NVME_SC_SUCCESS; + } + return nvmet_pr_unreg_all_host_by_prkey(req, prkey, + &ctrl->hostid, abort); + } + + if (holder == reg) { + status = nvmet_pr_update_reg_attr(pr, holder, + nvmet_pr_update_holder_rtype, &rtype); + if (!status && original_rtype != rtype) + nvmet_pr_resv_released(pr, ®->hostid); + return status; + } + + if (prkey == holder->rkey) { + /* + * Same as before, set the new holder first. + */ + nvmet_pr_set_new_holder(pr, rtype, reg); + nvmet_pr_unreg_all_others_by_prkey(req, prkey, &ctrl->hostid, + abort); + if (original_rtype != rtype) + nvmet_pr_resv_released(pr, ®->hostid); + return NVME_SC_SUCCESS; + } + + if (prkey) + return nvmet_pr_unreg_all_host_by_prkey(req, prkey, + &ctrl->hostid, abort); + return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; +} + +static void nvmet_pr_do_abort(struct work_struct *w) +{ + struct nvmet_req *req = container_of(w, struct nvmet_req, r.abort_work); + struct nvmet_pr_per_ctrl_ref *pc_ref; + struct nvmet_ns *ns = req->ns; + unsigned long idx; + + /* + * The target does not support abort, just wait per-controller ref to 0. + */ + xa_for_each(&ns->pr_per_ctrl_refs, idx, pc_ref) { + if (percpu_ref_is_dying(&pc_ref->ref)) { + wait_for_completion(&pc_ref->free_done); + reinit_completion(&pc_ref->confirm_done); + reinit_completion(&pc_ref->free_done); + percpu_ref_resurrect(&pc_ref->ref); + } + } + + up(&ns->pr.pr_sem); + nvmet_req_complete(req, NVME_SC_SUCCESS); +} + +static u16 __nvmet_execute_pr_acquire(struct nvmet_req *req, + struct nvmet_pr_registrant *reg, + u8 acquire_act, + u8 rtype, + struct nvmet_pr_acquire_data *d) +{ + u16 status; + + switch (acquire_act) { + case NVME_PR_ACQUIRE_ACT_ACQUIRE: + status = nvmet_pr_acquire(req, reg, rtype); + goto out; + case NVME_PR_ACQUIRE_ACT_PREEMPT: + status = nvmet_pr_preempt(req, reg, rtype, d, false); + goto inc_gen; + case NVME_PR_ACQUIRE_ACT_PREEMPT_AND_ABORT: + status = nvmet_pr_preempt(req, reg, rtype, d, true); + goto inc_gen; + default: + req->error_loc = offsetof(struct nvme_common_command, cdw10); + status = NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR; + goto out; + } +inc_gen: + if (!status) + atomic_inc(&req->ns->pr.generation); +out: + return status; +} + +static void nvmet_execute_pr_acquire(struct nvmet_req *req) +{ + u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10); + bool ignore_key = nvmet_pr_parse_ignore_key(cdw10); + /* Reservation type, bit 15:08 */ + u8 rtype = (u8)((cdw10 >> 8) & 0xff); + /* Reservation acquire action, bit 02:00 */ + u8 acquire_act = cdw10 & 0x07; + struct nvmet_ctrl *ctrl = req->sq->ctrl; + struct nvmet_pr_acquire_data *d = NULL; + struct nvmet_pr *pr = &req->ns->pr; + struct nvmet_pr_registrant *reg; + u16 status = NVME_SC_SUCCESS; + + if (ignore_key || + rtype < NVME_PR_WRITE_EXCLUSIVE || + rtype > NVME_PR_EXCLUSIVE_ACCESS_ALL_REGS) { + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; + goto out; + } + + d = kmalloc(sizeof(*d), GFP_KERNEL); + if (!d) { + status = NVME_SC_INTERNAL; + goto out; + } + + status = nvmet_copy_from_sgl(req, 0, d, sizeof(*d)); + if (status) + goto free_data; + + status = NVME_SC_RESERVATION_CONFLICT | NVME_STATUS_DNR; + down(&pr->pr_sem); + list_for_each_entry_rcu(reg, &pr->registrant_list, entry) { + if (uuid_equal(®->hostid, &ctrl->hostid) && + reg->rkey == le64_to_cpu(d->crkey)) { + status = __nvmet_execute_pr_acquire(req, reg, + acquire_act, rtype, d); + break; + } + } + + if (!status && acquire_act == NVME_PR_ACQUIRE_ACT_PREEMPT_AND_ABORT) { + kfree(d); + INIT_WORK(&req->r.abort_work, nvmet_pr_do_abort); + queue_work(nvmet_wq, &req->r.abort_work); + return; + } + + up(&pr->pr_sem); + +free_data: + kfree(d); +out: + nvmet_req_complete(req, status); +} + +static u16 nvmet_pr_release(struct nvmet_req *req, + struct nvmet_pr_registrant *reg, + u8 rtype) +{ + struct nvmet_pr *pr = &req->ns->pr; + struct nvmet_pr_registrant *holder; + u8 original_rtype; + + holder = rcu_dereference_protected(pr->holder, 1); + if (!holder || reg != holder) + return NVME_SC_SUCCESS; + + original_rtype = holder->rtype; + if (original_rtype != rtype) + return NVME_SC_RESERVATION_CONFLICT | NVME_STATUS_DNR; + + rcu_assign_pointer(pr->holder, NULL); + + if (original_rtype != NVME_PR_WRITE_EXCLUSIVE && + original_rtype != NVME_PR_EXCLUSIVE_ACCESS) + nvmet_pr_resv_released(pr, ®->hostid); + + return NVME_SC_SUCCESS; +} + +static void nvmet_pr_clear(struct nvmet_req *req) +{ + struct nvmet_pr_registrant *reg, *tmp; + struct nvmet_pr *pr = &req->ns->pr; + + rcu_assign_pointer(pr->holder, NULL); + + list_for_each_entry_safe(reg, tmp, &pr->registrant_list, entry) { + list_del_rcu(®->entry); + if (!uuid_equal(&req->sq->ctrl->hostid, ®->hostid)) + nvmet_pr_resv_preempted(pr, ®->hostid); + kfree_rcu(reg, rcu); + } + + atomic_inc(&pr->generation); +} + +static u16 __nvmet_execute_pr_release(struct nvmet_req *req, + struct nvmet_pr_registrant *reg, + u8 release_act, u8 rtype) +{ + switch (release_act) { + case NVME_PR_RELEASE_ACT_RELEASE: + return nvmet_pr_release(req, reg, rtype); + case NVME_PR_RELEASE_ACT_CLEAR: + nvmet_pr_clear(req); + return NVME_SC_SUCCESS; + default: + req->error_loc = offsetof(struct nvme_common_command, cdw10); + return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR; + } +} + +static void nvmet_execute_pr_release(struct nvmet_req *req) +{ + u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10); + bool ignore_key = nvmet_pr_parse_ignore_key(cdw10); + u8 rtype = (u8)((cdw10 >> 8) & 0xff); /* Reservation type, bit 15:08 */ + u8 release_act = cdw10 & 0x07; /* Reservation release action, bit 02:00 */ + struct nvmet_ctrl *ctrl = req->sq->ctrl; + struct nvmet_pr *pr = &req->ns->pr; + struct nvmet_pr_release_data *d; + struct nvmet_pr_registrant *reg; + u16 status; + + if (ignore_key) { + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; + goto out; + } + + d = kmalloc(sizeof(*d), GFP_KERNEL); + if (!d) { + status = NVME_SC_INTERNAL; + goto out; + } + + status = nvmet_copy_from_sgl(req, 0, d, sizeof(*d)); + if (status) + goto free_data; + + status = NVME_SC_RESERVATION_CONFLICT | NVME_STATUS_DNR; + down(&pr->pr_sem); + list_for_each_entry_rcu(reg, &pr->registrant_list, entry) { + if (uuid_equal(®->hostid, &ctrl->hostid) && + reg->rkey == le64_to_cpu(d->crkey)) { + status = __nvmet_execute_pr_release(req, reg, + release_act, rtype); + break; + } + } + up(&pr->pr_sem); +free_data: + kfree(d); +out: + nvmet_req_complete(req, status); +} + +static void nvmet_execute_pr_report(struct nvmet_req *req) +{ + u32 cdw11 = le32_to_cpu(req->cmd->common.cdw11); + u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10); + u32 num_bytes = 4 * (cdw10 + 1); /* cdw10 is number of dwords */ + u8 eds = cdw11 & 1; /* Extended data structure, bit 00 */ + struct nvme_registered_ctrl_ext *ctrl_eds; + struct nvme_reservation_status_ext *data; + struct nvmet_pr *pr = &req->ns->pr; + struct nvmet_pr_registrant *holder; + struct nvmet_pr_registrant *reg; + u16 num_ctrls = 0; + u16 status; + u8 rtype; + + /* nvmet hostid(uuid_t) is 128 bit. */ + if (!eds) { + req->error_loc = offsetof(struct nvme_common_command, cdw11); + status = NVME_SC_HOST_ID_INCONSIST | NVME_STATUS_DNR; + goto out; + } + + if (num_bytes < sizeof(struct nvme_reservation_status_ext)) { + req->error_loc = offsetof(struct nvme_common_command, cdw10); + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; + goto out; + } + + data = kmalloc(num_bytes, GFP_KERNEL); + if (!data) { + status = NVME_SC_INTERNAL; + goto out; + } + memset(data, 0, num_bytes); + data->gen = cpu_to_le32(atomic_read(&pr->generation)); + data->ptpls = 0; + ctrl_eds = data->regctl_eds; + + rcu_read_lock(); + holder = rcu_dereference(pr->holder); + rtype = holder ? holder->rtype : 0; + data->rtype = rtype; + + list_for_each_entry_rcu(reg, &pr->registrant_list, entry) { + num_ctrls++; + /* + * continue to get the number of all registrans. + */ + if (((void *)ctrl_eds + sizeof(*ctrl_eds)) > + ((void *)data + num_bytes)) + continue; + /* + * Dynamic controller, set cntlid to 0xffff. + */ + ctrl_eds->cntlid = cpu_to_le16(NVME_CNTLID_DYNAMIC); + if (rtype == NVME_PR_WRITE_EXCLUSIVE_ALL_REGS || + rtype == NVME_PR_EXCLUSIVE_ACCESS_ALL_REGS) + ctrl_eds->rcsts = 1; + if (reg == holder) + ctrl_eds->rcsts = 1; + uuid_copy((uuid_t *)&ctrl_eds->hostid, ®->hostid); + ctrl_eds->rkey = cpu_to_le64(reg->rkey); + ctrl_eds++; + } + rcu_read_unlock(); + + put_unaligned_le16(num_ctrls, data->regctl); + status = nvmet_copy_to_sgl(req, 0, data, num_bytes); + kfree(data); +out: + nvmet_req_complete(req, status); +} + +u16 nvmet_parse_pr_cmd(struct nvmet_req *req) +{ + struct nvme_command *cmd = req->cmd; + + switch (cmd->common.opcode) { + case nvme_cmd_resv_register: + req->execute = nvmet_execute_pr_register; + break; + case nvme_cmd_resv_acquire: + req->execute = nvmet_execute_pr_acquire; + break; + case nvme_cmd_resv_release: + req->execute = nvmet_execute_pr_release; + break; + case nvme_cmd_resv_report: + req->execute = nvmet_execute_pr_report; + break; + default: + return 1; + } + return NVME_SC_SUCCESS; +} + +static bool nvmet_is_req_write_cmd_group(struct nvmet_req *req) +{ + u8 opcode = req->cmd->common.opcode; + + if (req->sq->qid) { + switch (opcode) { + case nvme_cmd_flush: + case nvme_cmd_write: + case nvme_cmd_write_zeroes: + case nvme_cmd_dsm: + case nvme_cmd_zone_append: + case nvme_cmd_zone_mgmt_send: + return true; + default: + return false; + } + } + return false; +} + +static bool nvmet_is_req_read_cmd_group(struct nvmet_req *req) +{ + u8 opcode = req->cmd->common.opcode; + + if (req->sq->qid) { + switch (opcode) { + case nvme_cmd_read: + case nvme_cmd_zone_mgmt_recv: + return true; + default: + return false; + } + } + return false; +} + +u16 nvmet_pr_check_cmd_access(struct nvmet_req *req) +{ + struct nvmet_ctrl *ctrl = req->sq->ctrl; + struct nvmet_pr_registrant *holder; + struct nvmet_ns *ns = req->ns; + struct nvmet_pr *pr = &ns->pr; + u16 status = NVME_SC_SUCCESS; + + rcu_read_lock(); + holder = rcu_dereference(pr->holder); + if (!holder) + goto unlock; + if (uuid_equal(&ctrl->hostid, &holder->hostid)) + goto unlock; + + /* + * The Reservation command group is checked in executing, + * allow it here. + */ + switch (holder->rtype) { + case NVME_PR_WRITE_EXCLUSIVE: + if (nvmet_is_req_write_cmd_group(req)) + status = NVME_SC_RESERVATION_CONFLICT | NVME_STATUS_DNR; + break; + case NVME_PR_EXCLUSIVE_ACCESS: + if (nvmet_is_req_read_cmd_group(req) || + nvmet_is_req_write_cmd_group(req)) + status = NVME_SC_RESERVATION_CONFLICT | NVME_STATUS_DNR; + break; + case NVME_PR_WRITE_EXCLUSIVE_REG_ONLY: + case NVME_PR_WRITE_EXCLUSIVE_ALL_REGS: + if ((nvmet_is_req_write_cmd_group(req)) && + !nvmet_pr_find_registrant(pr, &ctrl->hostid)) + status = NVME_SC_RESERVATION_CONFLICT | NVME_STATUS_DNR; + break; + case NVME_PR_EXCLUSIVE_ACCESS_REG_ONLY: + case NVME_PR_EXCLUSIVE_ACCESS_ALL_REGS: + if ((nvmet_is_req_read_cmd_group(req) || + nvmet_is_req_write_cmd_group(req)) && + !nvmet_pr_find_registrant(pr, &ctrl->hostid)) + status = NVME_SC_RESERVATION_CONFLICT | NVME_STATUS_DNR; + break; + default: + pr_warn("the reservation type is set wrong, type:%d\n", + holder->rtype); + break; + } + +unlock: + rcu_read_unlock(); + if (status) + req->error_loc = offsetof(struct nvme_common_command, opcode); + return status; +} + +u16 nvmet_pr_get_ns_pc_ref(struct nvmet_req *req) +{ + struct nvmet_pr_per_ctrl_ref *pc_ref; + + pc_ref = xa_load(&req->ns->pr_per_ctrl_refs, + req->sq->ctrl->cntlid); + if (unlikely(!percpu_ref_tryget_live(&pc_ref->ref))) + return NVME_SC_INTERNAL; + req->pc_ref = pc_ref; + return NVME_SC_SUCCESS; +} + +static void nvmet_pr_ctrl_ns_all_cmds_done(struct percpu_ref *ref) +{ + struct nvmet_pr_per_ctrl_ref *pc_ref = + container_of(ref, struct nvmet_pr_per_ctrl_ref, ref); + + complete(&pc_ref->free_done); +} + +static int nvmet_pr_alloc_and_insert_pc_ref(struct nvmet_ns *ns, + unsigned long idx, + uuid_t *hostid) +{ + struct nvmet_pr_per_ctrl_ref *pc_ref; + int ret; + + pc_ref = kmalloc(sizeof(*pc_ref), GFP_ATOMIC); + if (!pc_ref) + return -ENOMEM; + + ret = percpu_ref_init(&pc_ref->ref, nvmet_pr_ctrl_ns_all_cmds_done, + PERCPU_REF_ALLOW_REINIT, GFP_KERNEL); + if (ret) + goto free; + + init_completion(&pc_ref->free_done); + init_completion(&pc_ref->confirm_done); + uuid_copy(&pc_ref->hostid, hostid); + + ret = xa_insert(&ns->pr_per_ctrl_refs, idx, pc_ref, GFP_KERNEL); + if (ret) + goto exit; + return ret; +exit: + percpu_ref_exit(&pc_ref->ref); +free: + kfree(pc_ref); + return ret; +} + +int nvmet_ctrl_init_pr(struct nvmet_ctrl *ctrl) +{ + struct nvmet_subsys *subsys = ctrl->subsys; + struct nvmet_pr_per_ctrl_ref *pc_ref; + struct nvmet_ns *ns = NULL; + unsigned long idx; + int ret; + + ctrl->pr_log_mgr.counter = 0; + ctrl->pr_log_mgr.lost_count = 0; + mutex_init(&ctrl->pr_log_mgr.lock); + INIT_KFIFO(ctrl->pr_log_mgr.log_queue); + + /* + * Here we are under subsys lock, if an ns not in subsys->namespaces, + * we can make sure that ns is not enabled, and not call + * nvmet_pr_init_ns(), see more details in nvmet_ns_enable(). + * So just check ns->pr.enable. + */ + xa_for_each(&subsys->namespaces, idx, ns) { + if (ns->pr.enable) { + ret = nvmet_pr_alloc_and_insert_pc_ref(ns, ctrl->cntlid, + &ctrl->hostid); + if (ret) + goto free_per_ctrl_refs; + } + } + return 0; + +free_per_ctrl_refs: + xa_for_each(&subsys->namespaces, idx, ns) { + if (ns->pr.enable) { + pc_ref = xa_erase(&ns->pr_per_ctrl_refs, ctrl->cntlid); + if (pc_ref) + percpu_ref_exit(&pc_ref->ref); + kfree(pc_ref); + } + } + return ret; +} + +void nvmet_ctrl_destroy_pr(struct nvmet_ctrl *ctrl) +{ + struct nvmet_pr_per_ctrl_ref *pc_ref; + struct nvmet_ns *ns; + unsigned long idx; + + kfifo_free(&ctrl->pr_log_mgr.log_queue); + mutex_destroy(&ctrl->pr_log_mgr.lock); + + xa_for_each(&ctrl->subsys->namespaces, idx, ns) { + if (ns->pr.enable) { + pc_ref = xa_erase(&ns->pr_per_ctrl_refs, ctrl->cntlid); + if (pc_ref) + percpu_ref_exit(&pc_ref->ref); + kfree(pc_ref); + } + } +} + +int nvmet_pr_init_ns(struct nvmet_ns *ns) +{ + struct nvmet_subsys *subsys = ns->subsys; + struct nvmet_pr_per_ctrl_ref *pc_ref; + struct nvmet_ctrl *ctrl = NULL; + unsigned long idx; + int ret; + + ns->pr.holder = NULL; + atomic_set(&ns->pr.generation, 0); + sema_init(&ns->pr.pr_sem, 1); + INIT_LIST_HEAD(&ns->pr.registrant_list); + ns->pr.notify_mask = 0; + + xa_init(&ns->pr_per_ctrl_refs); + + list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) { + ret = nvmet_pr_alloc_and_insert_pc_ref(ns, ctrl->cntlid, + &ctrl->hostid); + if (ret) + goto free_per_ctrl_refs; + } + return 0; + +free_per_ctrl_refs: + xa_for_each(&ns->pr_per_ctrl_refs, idx, pc_ref) { + xa_erase(&ns->pr_per_ctrl_refs, idx); + percpu_ref_exit(&pc_ref->ref); + kfree(pc_ref); + } + return ret; +} + +void nvmet_pr_exit_ns(struct nvmet_ns *ns) +{ + struct nvmet_pr_registrant *reg, *tmp; + struct nvmet_pr_per_ctrl_ref *pc_ref; + struct nvmet_pr *pr = &ns->pr; + unsigned long idx; + + list_for_each_entry_safe(reg, tmp, &pr->registrant_list, entry) { + list_del(®->entry); + kfree(reg); + } + + xa_for_each(&ns->pr_per_ctrl_refs, idx, pc_ref) { + /* + * No command on ns here, we can safely free pc_ref. + */ + pc_ref = xa_erase(&ns->pr_per_ctrl_refs, idx); + percpu_ref_exit(&pc_ref->ref); + kfree(pc_ref); + } + + xa_destroy(&ns->pr_per_ctrl_refs); +} diff --git a/drivers/nvme/target/trace.c b/drivers/nvme/target/trace.c index 9a3548179a8e..6dbc7036f2e4 100644 --- a/drivers/nvme/target/trace.c +++ b/drivers/nvme/target/trace.c @@ -180,6 +180,106 @@ static const char *nvmet_trace_zone_mgmt_recv(struct trace_seq *p, u8 *cdw10) return ret; } +static const char *nvmet_trace_resv_reg(struct trace_seq *p, u8 *cdw10) +{ + static const char * const rrega_strs[] = { + [0x00] = "register", + [0x01] = "unregister", + [0x02] = "replace", + }; + const char *ret = trace_seq_buffer_ptr(p); + u8 rrega = cdw10[0] & 0x7; + u8 iekey = (cdw10[0] >> 3) & 0x1; + u8 ptpl = (cdw10[3] >> 6) & 0x3; + const char *rrega_str; + + if (rrega < ARRAY_SIZE(rrega_strs) && rrega_strs[rrega]) + rrega_str = rrega_strs[rrega]; + else + rrega_str = "reserved"; + + trace_seq_printf(p, "rrega=%u:%s, iekey=%u, ptpl=%u", + rrega, rrega_str, iekey, ptpl); + trace_seq_putc(p, 0); + + return ret; +} + +static const char * const rtype_strs[] = { + [0x00] = "reserved", + [0x01] = "write exclusive", + [0x02] = "exclusive access", + [0x03] = "write exclusive registrants only", + [0x04] = "exclusive access registrants only", + [0x05] = "write exclusive all registrants", + [0x06] = "exclusive access all registrants", +}; + +static const char *nvmet_trace_resv_acq(struct trace_seq *p, u8 *cdw10) +{ + static const char * const racqa_strs[] = { + [0x00] = "acquire", + [0x01] = "preempt", + [0x02] = "preempt and abort", + }; + const char *ret = trace_seq_buffer_ptr(p); + u8 racqa = cdw10[0] & 0x7; + u8 iekey = (cdw10[0] >> 3) & 0x1; + u8 rtype = cdw10[1]; + const char *racqa_str = "reserved"; + const char *rtype_str = "reserved"; + + if (racqa < ARRAY_SIZE(racqa_strs) && racqa_strs[racqa]) + racqa_str = racqa_strs[racqa]; + + if (rtype < ARRAY_SIZE(rtype_strs) && rtype_strs[rtype]) + rtype_str = rtype_strs[rtype]; + + trace_seq_printf(p, "racqa=%u:%s, iekey=%u, rtype=%u:%s", + racqa, racqa_str, iekey, rtype, rtype_str); + trace_seq_putc(p, 0); + + return ret; +} + +static const char *nvmet_trace_resv_rel(struct trace_seq *p, u8 *cdw10) +{ + static const char * const rrela_strs[] = { + [0x00] = "release", + [0x01] = "clear", + }; + const char *ret = trace_seq_buffer_ptr(p); + u8 rrela = cdw10[0] & 0x7; + u8 iekey = (cdw10[0] >> 3) & 0x1; + u8 rtype = cdw10[1]; + const char *rrela_str = "reserved"; + const char *rtype_str = "reserved"; + + if (rrela < ARRAY_SIZE(rrela_strs) && rrela_strs[rrela]) + rrela_str = rrela_strs[rrela]; + + if (rtype < ARRAY_SIZE(rtype_strs) && rtype_strs[rtype]) + rtype_str = rtype_strs[rtype]; + + trace_seq_printf(p, "rrela=%u:%s, iekey=%u, rtype=%u:%s", + rrela, rrela_str, iekey, rtype, rtype_str); + trace_seq_putc(p, 0); + + return ret; +} + +static const char *nvmet_trace_resv_report(struct trace_seq *p, u8 *cdw10) +{ + const char *ret = trace_seq_buffer_ptr(p); + u32 numd = get_unaligned_le32(cdw10); + u8 eds = cdw10[4] & 0x1; + + trace_seq_printf(p, "numd=%u, eds=%u", numd, eds); + trace_seq_putc(p, 0); + + return ret; +} + const char *nvmet_trace_parse_nvm_cmd(struct trace_seq *p, u8 opcode, u8 *cdw10) { @@ -195,6 +295,14 @@ const char *nvmet_trace_parse_nvm_cmd(struct trace_seq *p, return nvmet_trace_zone_mgmt_send(p, cdw10); case nvme_cmd_zone_mgmt_recv: return nvmet_trace_zone_mgmt_recv(p, cdw10); + case nvme_cmd_resv_register: + return nvmet_trace_resv_reg(p, cdw10); + case nvme_cmd_resv_acquire: + return nvmet_trace_resv_acq(p, cdw10); + case nvme_cmd_resv_release: + return nvmet_trace_resv_rel(p, cdw10); + case nvme_cmd_resv_report: + return nvmet_trace_resv_report(p, cdw10); default: return nvmet_trace_common(p, cdw10); } diff --git a/drivers/nvme/target/zns.c b/drivers/nvme/target/zns.c index af9e13be7678..3aef35b05111 100644 --- a/drivers/nvme/target/zns.c +++ b/drivers/nvme/target/zns.c @@ -537,6 +537,7 @@ void nvmet_bdev_execute_zone_append(struct nvmet_req *req) u16 status = NVME_SC_SUCCESS; unsigned int total_len = 0; struct scatterlist *sg; + u32 data_len = nvmet_rw_data_len(req); struct bio *bio; int sg_cnt; @@ -544,6 +545,13 @@ void nvmet_bdev_execute_zone_append(struct nvmet_req *req) if (!nvmet_check_transfer_len(req, nvmet_rw_data_len(req))) return; + if (data_len > + bdev_max_zone_append_sectors(req->ns->bdev) << SECTOR_SHIFT) { + req->error_loc = offsetof(struct nvme_rw_command, length); + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; + goto out; + } + if (!req->sg_cnt) { nvmet_req_complete(req, 0); return; @@ -576,20 +584,17 @@ void nvmet_bdev_execute_zone_append(struct nvmet_req *req) bio->bi_opf |= REQ_FUA; for_each_sg(req->sg, sg, req->sg_cnt, sg_cnt) { - struct page *p = sg_page(sg); - unsigned int l = sg->length; - unsigned int o = sg->offset; - unsigned int ret; + unsigned int len = sg->length; - ret = bio_add_zone_append_page(bio, p, l, o); - if (ret != sg->length) { + if (bio_add_pc_page(bdev_get_queue(bio->bi_bdev), bio, + sg_page(sg), len, sg->offset) != len) { status = NVME_SC_INTERNAL; goto out_put_bio; } - total_len += sg->length; + total_len += len; } - if (total_len != nvmet_rw_data_len(req)) { + if (total_len != data_len) { status = NVME_SC_INTERNAL | NVME_STATUS_DNR; goto out_put_bio; } diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 42a4a996defb..3ed642f4f00d 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -2117,7 +2117,7 @@ int dasd_flush_device_queue(struct dasd_device *device) case DASD_CQR_IN_IO: rc = device->discipline->term_IO(cqr); if (rc) { - /* unable to terminate requeust */ + /* unable to terminate request */ dev_err(&device->cdev->dev, "Flushing the DASD request queue failed\n"); /* stop flush processing */ diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c index 6adaeb985dde..71d8fb86139d 100644 --- a/drivers/s390/block/dasd_devmap.c +++ b/drivers/s390/block/dasd_devmap.c @@ -855,7 +855,7 @@ dasd_delete_device(struct dasd_device *device) dev_set_drvdata(&device->cdev->dev, NULL); spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags); - /* Removve copy relation */ + /* Remove copy relation */ dasd_devmap_delete_copy_relation_device(device); /* * Drop ref_count by 3, one for the devmap reference, one for diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 90b106408992..1ebe589b5185 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -2405,7 +2405,7 @@ static int dasd_eckd_end_analysis(struct dasd_block *block) } if (count_area != NULL && count_area->kl == 0) { - /* we found notthing violating our disk layout */ + /* we found nothing violating our disk layout */ if (dasd_check_blocksize(count_area->dl) == 0) block->bp_block = count_area->dl; } diff --git a/drivers/s390/block/dasd_proc.c b/drivers/s390/block/dasd_proc.c index 0faaa437d9be..48e12e81df00 100644 --- a/drivers/s390/block/dasd_proc.c +++ b/drivers/s390/block/dasd_proc.c @@ -350,6 +350,7 @@ dasd_proc_init(void) remove_proc_entry("devices", dasd_proc_root_entry); out_nodevices: remove_proc_entry("dasd", NULL); + dasd_proc_root_entry = NULL; out_nodasd: return -ENOENT; } @@ -357,7 +358,11 @@ dasd_proc_init(void) void dasd_proc_exit(void) { + if (!dasd_proc_root_entry) + return; + remove_proc_entry("devices", dasd_proc_root_entry); remove_proc_entry("statistics", dasd_proc_root_entry); remove_proc_entry("dasd", NULL); + dasd_proc_root_entry = NULL; } diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index ca4bc0ac76ad..8947dab132d7 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1190,8 +1190,8 @@ static u8 sd_group_number(struct scsi_cmnd *cmd) if (!sdkp->rscs) return 0; - return min3((u32)rq->write_hint, (u32)sdkp->permanent_stream_count, - 0x3fu); + return min3((u32)rq->bio->bi_write_hint, + (u32)sdkp->permanent_stream_count, 0x3fu); } static blk_status_t sd_setup_rw32_cmnd(struct scsi_cmnd *cmd, bool write, @@ -1389,7 +1389,7 @@ static blk_status_t sd_setup_read_write_cmnd(struct scsi_cmnd *cmd) ret = sd_setup_rw16_cmnd(cmd, write, lba, nr_blocks, protect | fua, dld); } else if ((nr_blocks > 0xff) || (lba > 0x1fffff) || - sdp->use_10_for_rw || protect || rq->write_hint) { + sdp->use_10_for_rw || protect || rq->bio->bi_write_hint) { ret = sd_setup_rw10_cmnd(cmd, write, lba, nr_blocks, protect | fua); } else { diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index 6ab27f4f4878..7a447ff600d2 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -633,8 +633,6 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, struct queue_limits *lim, 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; |