diff options
Diffstat (limited to '')
| -rw-r--r-- | drivers/nvme/host/pci.c (renamed from drivers/block/nvme-core.c) | 497 |
1 files changed, 300 insertions, 197 deletions
diff --git a/drivers/block/nvme-core.c b/drivers/nvme/host/pci.c index 6f04771f1019..f3b53af789ef 100644 --- a/drivers/block/nvme-core.c +++ b/drivers/nvme/host/pci.c @@ -12,7 +12,6 @@ * more details. */ -#include <linux/nvme.h> #include <linux/bitops.h> #include <linux/blkdev.h> #include <linux/blk-mq.h> @@ -40,8 +39,13 @@ #include <linux/slab.h> #include <linux/t10-pi.h> #include <linux/types.h> +#include <linux/pr.h> #include <scsi/sg.h> -#include <asm-generic/io-64-nonatomic-lo-hi.h> +#include <linux/io-64-nonatomic-lo-hi.h> +#include <asm/unaligned.h> + +#include <uapi/linux/nvme_ioctl.h> +#include "nvme.h" #define NVME_MINORS (1U << MINORBITS) #define NVME_Q_DEPTH 1024 @@ -84,9 +88,10 @@ static wait_queue_head_t nvme_kthread_wait; static struct class *nvme_class; -static void nvme_reset_failed_dev(struct work_struct *ws); +static int __nvme_reset(struct nvme_dev *dev); static int nvme_reset(struct nvme_dev *dev); -static int nvme_process_cq(struct nvme_queue *nvmeq); +static void nvme_process_cq(struct nvme_queue *nvmeq); +static void nvme_dead_ctrl(struct nvme_dev *dev); struct async_cmd_info { struct kthread_work work; @@ -535,7 +540,7 @@ static void nvme_dif_remap(struct request *req, virt = bip_get_seed(bip); phys = nvme_block_nr(ns, blk_rq_pos(req)); nlb = (blk_rq_bytes(req) >> ns->lba_shift); - ts = ns->disk->integrity->tuple_size; + ts = ns->disk->queue->integrity.tuple_size; for (i = 0; i < nlb; i++, virt++, phys++) { pi = (struct t10_pi_tuple *)p; @@ -545,36 +550,20 @@ static void nvme_dif_remap(struct request *req, kunmap_atomic(pmap); } -static int nvme_noop_verify(struct blk_integrity_iter *iter) -{ - return 0; -} - -static int nvme_noop_generate(struct blk_integrity_iter *iter) -{ - return 0; -} - -struct blk_integrity nvme_meta_noop = { - .name = "NVME_META_NOOP", - .generate_fn = nvme_noop_generate, - .verify_fn = nvme_noop_verify, -}; - static void nvme_init_integrity(struct nvme_ns *ns) { struct blk_integrity integrity; switch (ns->pi_type) { case NVME_NS_DPS_PI_TYPE3: - integrity = t10_pi_type3_crc; + integrity.profile = &t10_pi_type3_crc; break; case NVME_NS_DPS_PI_TYPE1: case NVME_NS_DPS_PI_TYPE2: - integrity = t10_pi_type1_crc; + integrity.profile = &t10_pi_type1_crc; break; default: - integrity = nvme_meta_noop; + integrity.profile = NULL; break; } integrity.tuple_size = ns->ms; @@ -603,27 +592,31 @@ static void req_completion(struct nvme_queue *nvmeq, void *ctx, struct nvme_iod *iod = ctx; struct request *req = iod_get_private(iod); struct nvme_cmd_info *cmd_rq = blk_mq_rq_to_pdu(req); - u16 status = le16_to_cpup(&cqe->status) >> 1; + bool requeue = false; + int error = 0; if (unlikely(status)) { if (!(status & NVME_SC_DNR || blk_noretry_request(req)) && (jiffies - req->start_time) < req->timeout) { unsigned long flags; + requeue = true; blk_mq_requeue_request(req); spin_lock_irqsave(req->q->queue_lock, flags); if (!blk_queue_stopped(req->q)) blk_mq_kick_requeue_list(req->q); spin_unlock_irqrestore(req->q->queue_lock, flags); - return; + goto release_iod; } if (req->cmd_type == REQ_TYPE_DRV_PRIV) { if (cmd_rq->ctx == CMD_CTX_CANCELLED) - status = -EINTR; + error = -EINTR; + else + error = status; } else { - status = nvme_error_status(status); + error = nvme_error_status(status); } } @@ -635,8 +628,9 @@ static void req_completion(struct nvme_queue *nvmeq, void *ctx, if (cmd_rq->aborted) dev_warn(nvmeq->dev->dev, "completing aborted command with status:%04x\n", - status); + error); +release_iod: if (iod->nents) { dma_unmap_sg(nvmeq->dev->dev, iod->sg, iod->nents, rq_data_dir(req) ? DMA_TO_DEVICE : DMA_FROM_DEVICE); @@ -649,7 +643,8 @@ static void req_completion(struct nvme_queue *nvmeq, void *ctx, } nvme_free_iod(nvmeq->dev, iod); - blk_mq_complete_request(req, status); + if (likely(!requeue)) + blk_mq_complete_request(req, error); } /* length is in bytes. gfp flags indicates whether we may sleep. */ @@ -901,19 +896,28 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx, goto retry_cmd; } if (blk_integrity_rq(req)) { - if (blk_rq_count_integrity_sg(req->q, req->bio) != 1) + if (blk_rq_count_integrity_sg(req->q, req->bio) != 1) { + dma_unmap_sg(dev->dev, iod->sg, iod->nents, + dma_dir); goto error_cmd; + } sg_init_table(iod->meta_sg, 1); if (blk_rq_map_integrity_sg( - req->q, req->bio, iod->meta_sg) != 1) + req->q, req->bio, iod->meta_sg) != 1) { + dma_unmap_sg(dev->dev, iod->sg, iod->nents, + dma_dir); goto error_cmd; + } if (rq_data_dir(req)) nvme_dif_remap(req, nvme_dif_prep); - if (!dma_map_sg(nvmeq->q_dmadev, iod->meta_sg, 1, dma_dir)) + if (!dma_map_sg(nvmeq->q_dmadev, iod->meta_sg, 1, dma_dir)) { + dma_unmap_sg(dev->dev, iod->sg, iod->nents, + dma_dir); goto error_cmd; + } } } @@ -940,7 +944,7 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx, return BLK_MQ_RQ_QUEUE_BUSY; } -static int nvme_process_cq(struct nvme_queue *nvmeq) +static void __nvme_process_cq(struct nvme_queue *nvmeq, unsigned int *tag) { u16 head, phase; @@ -958,6 +962,8 @@ static int nvme_process_cq(struct nvme_queue *nvmeq) head = 0; phase = !phase; } + if (tag && *tag == cqe.command_id) + *tag = -1; ctx = nvme_finish_cmd(nvmeq, cqe.command_id, &fn); fn(nvmeq, ctx, &cqe); } @@ -969,14 +975,19 @@ static int nvme_process_cq(struct nvme_queue *nvmeq) * a big problem. */ if (head == nvmeq->cq_head && phase == nvmeq->cq_phase) - return 0; + return; - writel(head, nvmeq->q_db + nvmeq->dev->db_stride); + if (likely(nvmeq->cq_vector >= 0)) + writel(head, nvmeq->q_db + nvmeq->dev->db_stride); nvmeq->cq_head = head; nvmeq->cq_phase = phase; nvmeq->cqe_seen = 1; - return 1; +} + +static void nvme_process_cq(struct nvme_queue *nvmeq) +{ + __nvme_process_cq(nvmeq, NULL); } static irqreturn_t nvme_irq(int irq, void *data) @@ -1000,6 +1011,23 @@ static irqreturn_t nvme_irq_check(int irq, void *data) return IRQ_WAKE_THREAD; } +static int nvme_poll(struct blk_mq_hw_ctx *hctx, unsigned int tag) +{ + struct nvme_queue *nvmeq = hctx->driver_data; + + if ((le16_to_cpu(nvmeq->cqes[nvmeq->cq_head].status) & 1) == + nvmeq->cq_phase) { + spin_lock_irq(&nvmeq->q_lock); + __nvme_process_cq(nvmeq, &tag); + spin_unlock_irq(&nvmeq->q_lock); + + if (tag == -1) + return 1; + } + + return 0; +} + /* * Returns 0 on success. If the result is negative, it's a Linux error code; * if the result is positive, it's an NVM Express status code @@ -1030,11 +1058,13 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, req->special = (void *)0; if (buffer && bufflen) { - ret = blk_rq_map_kern(q, req, buffer, bufflen, __GFP_WAIT); + ret = blk_rq_map_kern(q, req, buffer, bufflen, + __GFP_DIRECT_RECLAIM); if (ret) goto out; } else if (ubuffer && bufflen) { - ret = blk_rq_map_user(q, req, NULL, ubuffer, bufflen, __GFP_WAIT); + ret = blk_rq_map_user(q, req, NULL, ubuffer, bufflen, + __GFP_DIRECT_RECLAIM); if (ret) goto out; bio = req->bio; @@ -1277,18 +1307,13 @@ static void nvme_abort_req(struct request *req) struct nvme_command cmd; if (!nvmeq->qid || cmd_rq->aborted) { - unsigned long flags; - - spin_lock_irqsave(&dev_list_lock, flags); - if (work_busy(&dev->reset_work)) - goto out; - list_del_init(&dev->node); - dev_warn(dev->dev, "I/O %d QID %d timeout, reset controller\n", - req->tag, nvmeq->qid); - dev->reset_workfn = nvme_reset_failed_dev; - queue_work(nvme_workq, &dev->reset_work); - out: - spin_unlock_irqrestore(&dev_list_lock, flags); + spin_lock(&dev_list_lock); + if (!__nvme_reset(dev)) { + dev_warn(dev->dev, + "I/O %d QID %d timeout, reset controller\n", + req->tag, nvmeq->qid); + } + spin_unlock(&dev_list_lock); return; } @@ -1664,6 +1689,7 @@ static struct blk_mq_ops nvme_mq_ops = { .init_hctx = nvme_init_hctx, .init_request = nvme_init_request, .timeout = nvme_timeout, + .poll = nvme_poll, }; static void nvme_dev_remove_admin(struct nvme_dev *dev) @@ -1709,11 +1735,15 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev) { int result; u32 aqa; - u64 cap = readq(&dev->bar->cap); + u64 cap = lo_hi_readq(&dev->bar->cap); struct nvme_queue *nvmeq; - unsigned page_shift = PAGE_SHIFT; + /* + * default to a 4K page size, with the intention to update this + * path in the future to accomodate architectures with differing + * kernel and IO page sizes. + */ + unsigned page_shift = 12; unsigned dev_page_min = NVME_CAP_MPSMIN(cap) + 12; - unsigned dev_page_max = NVME_CAP_MPSMAX(cap) + 12; if (page_shift < dev_page_min) { dev_err(dev->dev, @@ -1722,13 +1752,6 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev) 1 << page_shift); return -ENODEV; } - if (page_shift > dev_page_max) { - dev_info(dev->dev, - "Device maximum page size (%u) smaller than " - "host (%u); enabling work-around\n", - 1 << dev_page_max, 1 << page_shift); - page_shift = dev_page_max; - } dev->subsystem = readl(&dev->bar->vs) >= NVME_VS(1, 1) ? NVME_CAP_NSSRC(cap) : 0; @@ -1758,8 +1781,8 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev) dev->ctrl_config |= NVME_CC_IOSQES | NVME_CC_IOCQES; writel(aqa, &dev->bar->aqa); - writeq(nvmeq->sq_dma_addr, &dev->bar->asq); - writeq(nvmeq->cq_dma_addr, &dev->bar->acq); + lo_hi_writeq(nvmeq->sq_dma_addr, &dev->bar->asq); + lo_hi_writeq(nvmeq->cq_dma_addr, &dev->bar->acq); result = nvme_enable_ctrl(dev, cap); if (result) @@ -1804,7 +1827,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) length = (io.nblocks + 1) << ns->lba_shift; meta_len = (io.nblocks + 1) * ns->ms; - metadata = (void __user *)(unsigned long)io.metadata; + metadata = (void __user *)(uintptr_t)io.metadata; write = io.opcode & 1; if (ns->ext) { @@ -1844,7 +1867,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) c.rw.metadata = cpu_to_le64(meta_dma); status = __nvme_submit_sync_cmd(ns->queue, &c, NULL, - (void __user *)io.addr, length, NULL, 0); + (void __user *)(uintptr_t)io.addr, length, NULL, 0); unmap: if (meta) { if (status == NVME_SC_SUCCESS && !write) { @@ -1886,7 +1909,7 @@ static int nvme_user_cmd(struct nvme_dev *dev, struct nvme_ns *ns, timeout = msecs_to_jiffies(cmd.timeout_ms); status = __nvme_submit_sync_cmd(ns ? ns->queue : dev->admin_q, &c, - NULL, (void __user *)cmd.addr, cmd.data_len, + NULL, (void __user *)(uintptr_t)cmd.addr, cmd.data_len, &cmd.result, timeout); if (status >= 0) { if (put_user(cmd.result, &ucmd->result)) @@ -1943,6 +1966,23 @@ static int nvme_compat_ioctl(struct block_device *bdev, fmode_t mode, #define nvme_compat_ioctl NULL #endif +static void nvme_free_dev(struct kref *kref); +static void nvme_free_ns(struct kref *kref) +{ + struct nvme_ns *ns = container_of(kref, struct nvme_ns, kref); + + if (ns->type == NVME_NS_LIGHTNVM) + nvme_nvm_unregister(ns->queue, ns->disk->disk_name); + + spin_lock(&dev_list_lock); + ns->disk->private_data = NULL; + spin_unlock(&dev_list_lock); + + kref_put(&ns->dev->kref, nvme_free_dev); + put_disk(ns->disk); + kfree(ns); +} + static int nvme_open(struct block_device *bdev, fmode_t mode) { int ret = 0; @@ -1952,21 +1992,17 @@ static int nvme_open(struct block_device *bdev, fmode_t mode) ns = bdev->bd_disk->private_data; if (!ns) ret = -ENXIO; - else if (!kref_get_unless_zero(&ns->dev->kref)) + else if (!kref_get_unless_zero(&ns->kref)) ret = -ENXIO; spin_unlock(&dev_list_lock); return ret; } -static void nvme_free_dev(struct kref *kref); - static void nvme_release(struct gendisk *disk, fmode_t mode) { struct nvme_ns *ns = disk->private_data; - struct nvme_dev *dev = ns->dev; - - kref_put(&dev->kref, nvme_free_dev); + kref_put(&ns->kref, nvme_free_ns); } static int nvme_getgeo(struct block_device *bd, struct hd_geometry *geo) @@ -2007,6 +2043,16 @@ static int nvme_revalidate_disk(struct gendisk *disk) return -ENODEV; } + if (nvme_nvm_ns_supported(ns, id) && ns->type != NVME_NS_LIGHTNVM) { + if (nvme_nvm_register(ns->queue, disk->disk_name)) { + dev_warn(dev->dev, + "%s: LightNVM init failure\n", __func__); + kfree(id); + return -ENODEV; + } + ns->type = NVME_NS_LIGHTNVM; + } + old_ms = ns->ms; lbaf = id->flbas & NVME_NS_FLBAS_LBA_MASK; ns->lba_shift = id->lbaf[lbaf].ds; @@ -2025,6 +2071,7 @@ static int nvme_revalidate_disk(struct gendisk *disk) pi_type = ns->ms == sizeof(struct t10_pi_tuple) ? id->dps & NVME_NS_DPS_PI_MASK : 0; + blk_mq_freeze_queue(disk->queue); if (blk_get_integrity(disk) && (ns->pi_type != pi_type || ns->ms != old_ms || bs != queue_logical_block_size(disk->queue) || @@ -2034,22 +2081,116 @@ static int nvme_revalidate_disk(struct gendisk *disk) ns->pi_type = pi_type; blk_queue_logical_block_size(ns->queue, bs); - if (ns->ms && !blk_get_integrity(disk) && (disk->flags & GENHD_FL_UP) && - !ns->ext) + if (ns->ms && !ns->ext) nvme_init_integrity(ns); - if (ns->ms && !(ns->ms == 8 && ns->pi_type) && !blk_get_integrity(disk)) + if ((ns->ms && !(ns->ms == 8 && ns->pi_type) && + !blk_get_integrity(disk)) || + ns->type == NVME_NS_LIGHTNVM) set_capacity(disk, 0); else set_capacity(disk, le64_to_cpup(&id->nsze) << (ns->lba_shift - 9)); if (dev->oncs & NVME_CTRL_ONCS_DSM) nvme_config_discard(ns); + blk_mq_unfreeze_queue(disk->queue); kfree(id); return 0; } +static char nvme_pr_type(enum pr_type type) +{ + switch (type) { + case PR_WRITE_EXCLUSIVE: + return 1; + case PR_EXCLUSIVE_ACCESS: + return 2; + case PR_WRITE_EXCLUSIVE_REG_ONLY: + return 3; + case PR_EXCLUSIVE_ACCESS_REG_ONLY: + return 4; + case PR_WRITE_EXCLUSIVE_ALL_REGS: + return 5; + case PR_EXCLUSIVE_ACCESS_ALL_REGS: + return 6; + default: + return 0; + } +}; + +static int nvme_pr_command(struct block_device *bdev, u32 cdw10, + u64 key, u64 sa_key, u8 op) +{ + struct nvme_ns *ns = bdev->bd_disk->private_data; + struct nvme_command c; + u8 data[16] = { 0, }; + + put_unaligned_le64(key, &data[0]); + put_unaligned_le64(sa_key, &data[8]); + + memset(&c, 0, sizeof(c)); + c.common.opcode = op; + c.common.nsid = cpu_to_le32(ns->ns_id); + c.common.cdw10[0] = cpu_to_le32(cdw10); + + return nvme_submit_sync_cmd(ns->queue, &c, data, 16); +} + +static int nvme_pr_register(struct block_device *bdev, u64 old, + u64 new, unsigned flags) +{ + u32 cdw10; + + if (flags & ~PR_FL_IGNORE_KEY) + return -EOPNOTSUPP; + + cdw10 = old ? 2 : 0; + cdw10 |= (flags & PR_FL_IGNORE_KEY) ? 1 << 3 : 0; + cdw10 |= (1 << 30) | (1 << 31); /* PTPL=1 */ + return nvme_pr_command(bdev, cdw10, old, new, nvme_cmd_resv_register); +} + +static int nvme_pr_reserve(struct block_device *bdev, u64 key, + enum pr_type type, unsigned flags) +{ + u32 cdw10; + + if (flags & ~PR_FL_IGNORE_KEY) + return -EOPNOTSUPP; + + cdw10 = nvme_pr_type(type) << 8; + cdw10 |= ((flags & PR_FL_IGNORE_KEY) ? 1 << 3 : 0); + return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_acquire); +} + +static int nvme_pr_preempt(struct block_device *bdev, u64 old, u64 new, + enum pr_type type, bool abort) +{ + u32 cdw10 = nvme_pr_type(type) << 8 | abort ? 2 : 1; + return nvme_pr_command(bdev, cdw10, old, new, nvme_cmd_resv_acquire); +} + +static int nvme_pr_clear(struct block_device *bdev, u64 key) +{ + u32 cdw10 = 1 | (key ? 1 << 3 : 0); + return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_register); +} + +static int nvme_pr_release(struct block_device *bdev, u64 key, enum pr_type type) +{ + u32 cdw10 = nvme_pr_type(type) << 8 | key ? 1 << 3 : 0; + return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_release); +} + +static const struct pr_ops nvme_pr_ops = { + .pr_register = nvme_pr_register, + .pr_reserve = nvme_pr_reserve, + .pr_release = nvme_pr_release, + .pr_preempt = nvme_pr_preempt, + .pr_clear = nvme_pr_clear, +}; + static const struct block_device_operations nvme_fops = { .owner = THIS_MODULE, .ioctl = nvme_ioctl, @@ -2058,6 +2199,7 @@ static const struct block_device_operations nvme_fops = { .release = nvme_release, .getgeo = nvme_getgeo, .revalidate_disk= nvme_revalidate_disk, + .pr_ops = &nvme_pr_ops, }; static int nvme_kthread(void *data) @@ -2073,14 +2215,11 @@ static int nvme_kthread(void *data) if ((dev->subsystem && (csts & NVME_CSTS_NSSRO)) || csts & NVME_CSTS_CFS) { - if (work_busy(&dev->reset_work)) - continue; - list_del_init(&dev->node); - dev_warn(dev->dev, - "Failed status: %x, reset controller\n", - readl(&dev->bar->csts)); - dev->reset_workfn = nvme_reset_failed_dev; - queue_work(nvme_workq, &dev->reset_work); + if (!__nvme_reset(dev)) { + dev_warn(dev->dev, + "Failed status: %x, reset controller\n", + readl(&dev->bar->csts)); + } continue; } for (i = 0; i < dev->queue_count; i++) { @@ -2126,6 +2265,7 @@ static void nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid) if (!disk) goto out_free_queue; + kref_init(&ns->kref); ns->ns_id = nsid; ns->disk = disk; ns->lba_shift = 9; /* set to a default value for 512 until disk is validated */ @@ -2135,7 +2275,7 @@ static void nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid) if (dev->max_hw_sectors) { blk_queue_max_hw_sectors(ns->queue, dev->max_hw_sectors); blk_queue_max_segments(ns->queue, - ((dev->max_hw_sectors << 9) / dev->page_size) + 1); + (dev->max_hw_sectors / (dev->page_size >> 9)) + 1); } if (dev->stripe_size) blk_queue_chunk_sectors(ns->queue, dev->stripe_size >> 9); @@ -2162,17 +2302,20 @@ static void nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid) if (nvme_revalidate_disk(ns->disk)) goto out_free_disk; - add_disk(ns->disk); - if (ns->ms) { - struct block_device *bd = bdget_disk(ns->disk, 0); - if (!bd) - return; - if (blkdev_get(bd, FMODE_READ, NULL)) { - bdput(bd); - return; + kref_get(&dev->kref); + if (ns->type != NVME_NS_LIGHTNVM) { + add_disk(ns->disk); + if (ns->ms) { + struct block_device *bd = bdget_disk(ns->disk, 0); + if (!bd) + return; + if (blkdev_get(bd, FMODE_READ, NULL)) { + bdput(bd); + return; + } + blkdev_reread_part(bd); + blkdev_put(bd, FMODE_READ); } - blkdev_reread_part(bd); - blkdev_put(bd, FMODE_READ); } return; out_free_disk: @@ -2184,6 +2327,13 @@ static void nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid) kfree(ns); } +/* + * Create I/O queues. Failing to create an I/O queue is not an issue, + * we can continue with less than the desired amount of queues, and + * even a controller without I/O queues an still be used to issue + * admin commands. This might be useful to upgrade a buggy firmware + * for example. + */ static void nvme_create_io_queues(struct nvme_dev *dev) { unsigned i; @@ -2193,8 +2343,10 @@ static void nvme_create_io_queues(struct nvme_dev *dev) break; for (i = dev->online_queues; i <= dev->queue_count - 1; i++) - if (nvme_create_queue(dev->queues[i], i)) + if (nvme_create_queue(dev->queues[i], i)) { + nvme_free_queues(dev, i); break; + } } static int set_queue_count(struct nvme_dev *dev, int count) @@ -2357,18 +2509,6 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) return result; } -static void nvme_free_namespace(struct nvme_ns *ns) -{ - list_del(&ns->list); - - spin_lock(&dev_list_lock); - ns->disk->private_data = NULL; - spin_unlock(&dev_list_lock); - - put_disk(ns->disk); - kfree(ns); -} - static int ns_cmp(void *priv, struct list_head *a, struct list_head *b) { struct nvme_ns *nsa = container_of(a, struct nvme_ns, list); @@ -2402,15 +2542,14 @@ static void nvme_ns_remove(struct nvme_ns *ns) if (kill) blk_set_queue_dying(ns->queue); - if (ns->disk->flags & GENHD_FL_UP) { - if (blk_get_integrity(ns->disk)) - blk_integrity_unregister(ns->disk); + if (ns->disk->flags & GENHD_FL_UP) del_gendisk(ns->disk); - } if (kill || !blk_queue_dying(ns->queue)) { blk_mq_abort_requeue_list(ns->queue); blk_cleanup_queue(ns->queue); - } + } + list_del_init(&ns->list); + kref_put(&ns->kref, nvme_free_ns); } static void nvme_scan_namespaces(struct nvme_dev *dev, unsigned nn) @@ -2421,18 +2560,14 @@ static void nvme_scan_namespaces(struct nvme_dev *dev, unsigned nn) for (i = 1; i <= nn; i++) { ns = nvme_find_ns(dev, i); if (ns) { - if (revalidate_disk(ns->disk)) { + if (revalidate_disk(ns->disk)) nvme_ns_remove(ns); - nvme_free_namespace(ns); - } } else nvme_alloc_ns(dev, i); } list_for_each_entry_safe(ns, next, &dev->namespaces, list) { - if (ns->ns_id > nn) { + if (ns->ns_id > nn) nvme_ns_remove(ns); - nvme_free_namespace(ns); - } } list_sort(NULL, &dev->namespaces, ns_cmp); } @@ -2478,7 +2613,7 @@ static int nvme_dev_add(struct nvme_dev *dev) struct pci_dev *pdev = to_pci_dev(dev->dev); int res; struct nvme_id_ctrl *ctrl; - int shift = NVME_CAP_MPSMIN(readq(&dev->bar->cap)) + 12; + int shift = NVME_CAP_MPSMIN(lo_hi_readq(&dev->bar->cap)) + 12; res = nvme_identify_ctrl(dev, &ctrl); if (res) { @@ -2494,6 +2629,8 @@ static int nvme_dev_add(struct nvme_dev *dev) memcpy(dev->firmware_rev, ctrl->fr, sizeof(ctrl->fr)); if (ctrl->mdts) dev->max_hw_sectors = 1 << (ctrl->mdts + shift - 9); + else + dev->max_hw_sectors = UINT_MAX; if ((pdev->vendor == PCI_VENDOR_ID_INTEL) && (pdev->device == 0x0953) && ctrl->vs[3]) { unsigned int max_hw_sectors; @@ -2567,7 +2704,7 @@ static int nvme_dev_map(struct nvme_dev *dev) goto unmap; } - cap = readq(&dev->bar->cap); + cap = lo_hi_readq(&dev->bar->cap); dev->q_depth = min_t(int, NVME_CAP_MQES(cap) + 1, NVME_Q_DEPTH); dev->db_stride = 1 << NVME_CAP_STRIDE(cap); dev->dbs = ((void __iomem *)dev->bar) + 4096; @@ -2630,7 +2767,7 @@ static void nvme_wait_dq(struct nvme_delq_ctx *dq, struct nvme_dev *dev) * queues than admin tags. */ set_current_state(TASK_RUNNING); - nvme_disable_ctrl(dev, readq(&dev->bar->cap)); + nvme_disable_ctrl(dev, lo_hi_readq(&dev->bar->cap)); nvme_clear_queue(dev->queues[0]); flush_kthread_worker(dq->worker); nvme_disable_queue(dev, 0); @@ -2657,6 +2794,10 @@ static void nvme_del_queue_end(struct nvme_queue *nvmeq) { struct nvme_delq_ctx *dq = nvmeq->cmdinfo.ctx; nvme_put_dq(dq); + + spin_lock_irq(&nvmeq->q_lock); + nvme_process_cq(nvmeq); + spin_unlock_irq(&nvmeq->q_lock); } static int adapter_async_del_queue(struct nvme_queue *nvmeq, u8 opcode, @@ -2822,9 +2963,9 @@ static void nvme_dev_shutdown(struct nvme_dev *dev) static void nvme_dev_remove(struct nvme_dev *dev) { - struct nvme_ns *ns; + struct nvme_ns *ns, *next; - list_for_each_entry(ns, &dev->namespaces, list) + list_for_each_entry_safe(ns, next, &dev->namespaces, list) nvme_ns_remove(ns); } @@ -2880,21 +3021,12 @@ static void nvme_release_instance(struct nvme_dev *dev) spin_unlock(&dev_list_lock); } -static void nvme_free_namespaces(struct nvme_dev *dev) -{ - struct nvme_ns *ns, *next; - - list_for_each_entry_safe(ns, next, &dev->namespaces, list) - nvme_free_namespace(ns); -} - static void nvme_free_dev(struct kref *kref) { struct nvme_dev *dev = container_of(kref, struct nvme_dev, kref); put_device(dev->dev); put_device(dev->device); - nvme_free_namespaces(dev); nvme_release_instance(dev); if (dev->tagset.tags) blk_mq_free_tag_set(&dev->tagset); @@ -2968,14 +3100,15 @@ static const struct file_operations nvme_dev_fops = { .compat_ioctl = nvme_dev_ioctl, }; -static int nvme_dev_start(struct nvme_dev *dev) +static void nvme_probe_work(struct work_struct *work) { - int result; + struct nvme_dev *dev = container_of(work, struct nvme_dev, probe_work); bool start_thread = false; + int result; result = nvme_dev_map(dev); if (result) - return result; + goto out; result = nvme_configure_admin_queue(dev); if (result) @@ -3010,7 +3143,20 @@ static int nvme_dev_start(struct nvme_dev *dev) goto free_tags; dev->event_limit = 1; - return result; + + /* + * Keep the controller around but remove all namespaces if we don't have + * any working I/O queue. + */ + if (dev->online_queues < 2) { + dev_warn(dev->dev, "IO queues not created\n"); + nvme_dev_remove(dev); + } else { + nvme_unfreeze_queues(dev); + nvme_dev_add(dev); + } + + return; free_tags: nvme_dev_remove_admin(dev); @@ -3022,7 +3168,9 @@ static int nvme_dev_start(struct nvme_dev *dev) nvme_dev_list_remove(dev); unmap: nvme_dev_unmap(dev); - return result; + out: + if (!work_busy(&dev->reset_work)) + nvme_dead_ctrl(dev); } static int nvme_remove_dead_ctrl(void *arg) @@ -3036,33 +3184,6 @@ static int nvme_remove_dead_ctrl(void *arg) return 0; } -static void nvme_remove_disks(struct work_struct *ws) -{ - struct nvme_dev *dev = container_of(ws, struct nvme_dev, reset_work); - - nvme_free_queues(dev, 1); - nvme_dev_remove(dev); -} - -static int nvme_dev_resume(struct nvme_dev *dev) -{ - int ret; - - ret = nvme_dev_start(dev); - if (ret) - return ret; - if (dev->online_queues < 2) { - spin_lock(&dev_list_lock); - dev->reset_workfn = nvme_remove_disks; - queue_work(nvme_workq, &dev->reset_work); - spin_unlock(&dev_list_lock); - } else { - nvme_unfreeze_queues(dev); - nvme_dev_add(dev); - } - return 0; -} - static void nvme_dead_ctrl(struct nvme_dev *dev) { dev_warn(dev->dev, "Device failed to resume\n"); @@ -3075,8 +3196,9 @@ static void nvme_dead_ctrl(struct nvme_dev *dev) } } -static void nvme_dev_reset(struct nvme_dev *dev) +static void nvme_reset_work(struct work_struct *ws) { + struct nvme_dev *dev = container_of(ws, struct nvme_dev, reset_work); bool in_probe = work_busy(&dev->probe_work); nvme_dev_shutdown(dev); @@ -3096,31 +3218,24 @@ static void nvme_dev_reset(struct nvme_dev *dev) schedule_work(&dev->probe_work); } -static void nvme_reset_failed_dev(struct work_struct *ws) -{ - struct nvme_dev *dev = container_of(ws, struct nvme_dev, reset_work); - nvme_dev_reset(dev); -} - -static void nvme_reset_workfn(struct work_struct *work) +static int __nvme_reset(struct nvme_dev *dev) { - struct nvme_dev *dev = container_of(work, struct nvme_dev, reset_work); - dev->reset_workfn(work); + if (work_pending(&dev->reset_work)) + return -EBUSY; + list_del_init(&dev->node); + queue_work(nvme_workq, &dev->reset_work); + return 0; } static int nvme_reset(struct nvme_dev *dev) { - int ret = -EBUSY; + int ret; if (!dev->admin_q || blk_queue_dying(dev->admin_q)) return -ENODEV; spin_lock(&dev_list_lock); - if (!work_pending(&dev->reset_work)) { - dev->reset_workfn = nvme_reset_failed_dev; - queue_work(nvme_workq, &dev->reset_work); - ret = 0; - } + ret = __nvme_reset(dev); spin_unlock(&dev_list_lock); if (!ret) { @@ -3147,7 +3262,6 @@ static ssize_t nvme_sysfs_reset(struct device *dev, } static DEVICE_ATTR(reset_controller, S_IWUSR, NULL, nvme_sysfs_reset); -static void nvme_async_probe(struct work_struct *work); static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) { int node, result = -ENOMEM; @@ -3170,8 +3284,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto free; INIT_LIST_HEAD(&dev->namespaces); - dev->reset_workfn = nvme_reset_failed_dev; - INIT_WORK(&dev->reset_work, nvme_reset_workfn); + INIT_WORK(&dev->reset_work, nvme_reset_work); dev->dev = get_device(&pdev->dev); pci_set_drvdata(pdev, dev); result = nvme_set_instance(dev); @@ -3199,7 +3312,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) INIT_LIST_HEAD(&dev->node); INIT_WORK(&dev->scan_work, nvme_dev_scan); - INIT_WORK(&dev->probe_work, nvme_async_probe); + INIT_WORK(&dev->probe_work, nvme_probe_work); schedule_work(&dev->probe_work); return 0; @@ -3219,14 +3332,6 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) return result; } -static void nvme_async_probe(struct work_struct *work) -{ - struct nvme_dev *dev = container_of(work, struct nvme_dev, probe_work); - - if (nvme_dev_resume(dev) && !work_busy(&dev->reset_work)) - nvme_dead_ctrl(dev); -} - static void nvme_reset_notify(struct pci_dev *pdev, bool prepare) { struct nvme_dev *dev = pci_get_drvdata(pdev); @@ -3234,7 +3339,7 @@ static void nvme_reset_notify(struct pci_dev *pdev, bool prepare) if (prepare) nvme_dev_shutdown(dev); else - nvme_dev_resume(dev); + schedule_work(&dev->probe_work); } static void nvme_shutdown(struct pci_dev *pdev) @@ -3288,10 +3393,7 @@ static int nvme_resume(struct device *dev) struct pci_dev *pdev = to_pci_dev(dev); struct nvme_dev *ndev = pci_get_drvdata(pdev); - if (nvme_dev_resume(ndev) && !work_busy(&ndev->reset_work)) { - ndev->reset_workfn = nvme_reset_failed_dev; - queue_work(nvme_workq, &ndev->reset_work); - } + schedule_work(&ndev->probe_work); return 0; } #endif @@ -3312,6 +3414,7 @@ static const struct pci_error_handlers nvme_err_handler = { static const struct pci_device_id nvme_id_table[] = { { PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) }, + { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) }, { 0, } }; MODULE_DEVICE_TABLE(pci, nvme_id_table); |