diff options
Diffstat (limited to 'drivers/nvme/host')
| -rw-r--r-- | drivers/nvme/host/auth.c | 2 | ||||
| -rw-r--r-- | drivers/nvme/host/core.c | 99 | ||||
| -rw-r--r-- | drivers/nvme/host/hwmon.c | 2 | ||||
| -rw-r--r-- | drivers/nvme/host/ioctl.c | 7 | ||||
| -rw-r--r-- | drivers/nvme/host/multipath.c | 40 | ||||
| -rw-r--r-- | drivers/nvme/host/nvme.h | 1 | ||||
| -rw-r--r-- | drivers/nvme/host/pci.c | 19 | ||||
| -rw-r--r-- | drivers/nvme/host/pr.c | 2 | ||||
| -rw-r--r-- | drivers/nvme/host/rdma.c | 2 | ||||
| -rw-r--r-- | drivers/nvme/host/tcp.c | 7 | ||||
| -rw-r--r-- | drivers/nvme/host/trace.c | 2 |
11 files changed, 124 insertions, 59 deletions
diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c index 371e14f0a203..5ea0e21709da 100644 --- a/drivers/nvme/host/auth.c +++ b/drivers/nvme/host/auth.c @@ -6,7 +6,7 @@ #include <linux/crc32.h> #include <linux/base64.h> #include <linux/prandom.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/hash.h> #include <crypto/dh.h> #include "nvme.h" diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index ba6508455e18..b149b638453f 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -22,7 +22,7 @@ #include <linux/nvme_ioctl.h> #include <linux/pm_qos.h> #include <linux/ratelimit.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "nvme.h" #include "fabrics.h" @@ -92,6 +92,17 @@ MODULE_PARM_DESC(apst_secondary_latency_tol_us, "secondary APST latency tolerance in us"); /* + * Older kernels didn't enable protection information if it was at an offset. + * Newer kernels do, so it breaks reads on the upgrade if such formats were + * used in prior kernels since the metadata written did not contain a valid + * checksum. + */ +static bool disable_pi_offsets = false; +module_param(disable_pi_offsets, bool, 0444); +MODULE_PARM_DESC(disable_pi_offsets, + "disable protection information if it has an offset"); + +/* * nvme_wq - hosts nvme related works that are not reset or delete * nvme_reset_wq - hosts nvme reset works * nvme_delete_wq - hosts nvme delete works @@ -1292,14 +1303,12 @@ static void nvme_queue_keep_alive_work(struct nvme_ctrl *ctrl) queue_delayed_work(nvme_wq, &ctrl->ka_work, delay); } -static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq, - blk_status_t status) +static void nvme_keep_alive_finish(struct request *rq, + blk_status_t status, struct nvme_ctrl *ctrl) { - struct nvme_ctrl *ctrl = rq->end_io_data; - unsigned long flags; - bool startka = false; unsigned long rtt = jiffies - (rq->deadline - rq->timeout); unsigned long delay = nvme_keep_alive_work_period(ctrl); + enum nvme_ctrl_state state = nvme_ctrl_state(ctrl); /* * Subtract off the keepalive RTT so nvme_keep_alive_work runs @@ -1313,25 +1322,17 @@ static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq, delay = 0; } - blk_mq_free_request(rq); - if (status) { dev_err(ctrl->device, "failed nvme_keep_alive_end_io error=%d\n", status); - return RQ_END_IO_NONE; + return; } ctrl->ka_last_check_time = jiffies; ctrl->comp_seen = false; - spin_lock_irqsave(&ctrl->lock, flags); - if (ctrl->state == NVME_CTRL_LIVE || - ctrl->state == NVME_CTRL_CONNECTING) - startka = true; - spin_unlock_irqrestore(&ctrl->lock, flags); - if (startka) + if (state == NVME_CTRL_LIVE || state == NVME_CTRL_CONNECTING) queue_delayed_work(nvme_wq, &ctrl->ka_work, delay); - return RQ_END_IO_NONE; } static void nvme_keep_alive_work(struct work_struct *work) @@ -1340,6 +1341,7 @@ static void nvme_keep_alive_work(struct work_struct *work) struct nvme_ctrl, ka_work); bool comp_seen = ctrl->comp_seen; struct request *rq; + blk_status_t status; ctrl->ka_last_check_time = jiffies; @@ -1362,9 +1364,9 @@ static void nvme_keep_alive_work(struct work_struct *work) nvme_init_request(rq, &ctrl->ka_cmd); rq->timeout = ctrl->kato * HZ; - rq->end_io = nvme_keep_alive_end_io; - rq->end_io_data = ctrl; - blk_execute_rq_nowait(rq, false); + status = blk_execute_rq(rq, false); + nvme_keep_alive_finish(rq, status, ctrl); + blk_mq_free_request(rq); } static void nvme_start_keep_alive(struct nvme_ctrl *ctrl) @@ -1399,17 +1401,30 @@ static void nvme_update_keep_alive(struct nvme_ctrl *ctrl, nvme_start_keep_alive(ctrl); } -/* - * In NVMe 1.0 the CNS field was just a binary controller or namespace - * flag, thus sending any new CNS opcodes has a big chance of not working. - * Qemu unfortunately had that bug after reporting a 1.1 version compliance - * (but not for any later version). - */ -static bool nvme_ctrl_limited_cns(struct nvme_ctrl *ctrl) +static bool nvme_id_cns_ok(struct nvme_ctrl *ctrl, u8 cns) { - if (ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS) - return ctrl->vs < NVME_VS(1, 2, 0); - return ctrl->vs < NVME_VS(1, 1, 0); + /* + * The CNS field occupies a full byte starting with NVMe 1.2 + */ + if (ctrl->vs >= NVME_VS(1, 2, 0)) + return true; + + /* + * NVMe 1.1 expanded the CNS value to two bits, which means values + * larger than that could get truncated and treated as an incorrect + * value. + * + * Qemu implemented 1.0 behavior for controllers claiming 1.1 + * compliance, so they need to be quirked here. + */ + if (ctrl->vs >= NVME_VS(1, 1, 0) && + !(ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS)) + return cns <= 3; + + /* + * NVMe 1.0 used a single bit for the CNS value. + */ + return cns <= 1; } static int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id) @@ -1922,8 +1937,12 @@ static void nvme_configure_metadata(struct nvme_ctrl *ctrl, if (head->pi_size && head->ms >= head->pi_size) head->pi_type = id->dps & NVME_NS_DPS_PI_MASK; - if (!(id->dps & NVME_NS_DPS_PI_FIRST)) - info->pi_offset = head->ms - head->pi_size; + if (!(id->dps & NVME_NS_DPS_PI_FIRST)) { + if (disable_pi_offsets) + head->pi_type = 0; + else + info->pi_offset = head->ms - head->pi_size; + } if (ctrl->ops->flags & NVME_F_FABRICS) { /* @@ -2458,8 +2477,13 @@ int nvme_enable_ctrl(struct nvme_ctrl *ctrl) else ctrl->ctrl_config = NVME_CC_CSS_NVM; - if (ctrl->cap & NVME_CAP_CRMS_CRWMS && ctrl->cap & NVME_CAP_CRMS_CRIMS) - ctrl->ctrl_config |= NVME_CC_CRIME; + /* + * Setting CRIME results in CSTS.RDY before the media is ready. This + * makes it possible for media related commands to return the error + * NVME_SC_ADMIN_COMMAND_MEDIA_NOT_READY. Until the driver is + * restructured to handle retries, disable CC.CRIME. + */ + ctrl->ctrl_config &= ~NVME_CC_CRIME; ctrl->ctrl_config |= (NVME_CTRL_PAGE_SHIFT - 12) << NVME_CC_MPS_SHIFT; ctrl->ctrl_config |= NVME_CC_AMS_RR | NVME_CC_SHN_NONE; @@ -2489,10 +2513,7 @@ int nvme_enable_ctrl(struct nvme_ctrl *ctrl) * devices are known to get this wrong. Use the larger of the * two values. */ - if (ctrl->ctrl_config & NVME_CC_CRIME) - ready_timeout = NVME_CRTO_CRIMT(crto); - else - ready_timeout = NVME_CRTO_CRWMT(crto); + ready_timeout = NVME_CRTO_CRWMT(crto); if (ready_timeout < timeout) dev_warn_once(ctrl->device, "bad crto:%x cap:%llx\n", @@ -3111,7 +3132,7 @@ static int nvme_init_non_mdts_limits(struct nvme_ctrl *ctrl) ctrl->max_zeroes_sectors = 0; if (ctrl->subsys->subtype != NVME_NQN_NVME || - nvme_ctrl_limited_cns(ctrl) || + !nvme_id_cns_ok(ctrl, NVME_ID_CNS_CS_CTRL) || test_bit(NVME_CTRL_SKIP_ID_CNS_CS, &ctrl->flags)) return 0; @@ -4207,7 +4228,7 @@ static void nvme_scan_work(struct work_struct *work) } mutex_lock(&ctrl->scan_lock); - if (nvme_ctrl_limited_cns(ctrl)) { + if (!nvme_id_cns_ok(ctrl, NVME_ID_CNS_NS_ACTIVE_LIST)) { nvme_scan_ns_sequential(ctrl); } else { /* diff --git a/drivers/nvme/host/hwmon.c b/drivers/nvme/host/hwmon.c index 8df73a0b3980..89a1a1043d63 100644 --- a/drivers/nvme/host/hwmon.c +++ b/drivers/nvme/host/hwmon.c @@ -6,7 +6,7 @@ #include <linux/hwmon.h> #include <linux/units.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "nvme.h" diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index b9b79ccfabf8..a96976b22fa7 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -421,10 +421,13 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req, struct io_uring_cmd *ioucmd = req->end_io_data; struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd); - if (nvme_req(req)->flags & NVME_REQ_CANCELLED) + if (nvme_req(req)->flags & NVME_REQ_CANCELLED) { pdu->status = -EINTR; - else + } else { pdu->status = nvme_req(req)->status; + if (!pdu->status) + pdu->status = blk_status_to_errno(err); + } pdu->result = le64_to_cpu(nvme_req(req)->result.u64); /* diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 48e7a8906d01..6a15873055b9 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -431,7 +431,6 @@ static bool nvme_available_path(struct nvme_ns_head *head) case NVME_CTRL_LIVE: case NVME_CTRL_RESETTING: case NVME_CTRL_CONNECTING: - /* fallthru */ return true; default: break; @@ -580,6 +579,20 @@ static int nvme_add_ns_head_cdev(struct nvme_ns_head *head) return ret; } +static void nvme_partition_scan_work(struct work_struct *work) +{ + struct nvme_ns_head *head = + container_of(work, struct nvme_ns_head, partition_scan_work); + + if (WARN_ON_ONCE(!test_and_clear_bit(GD_SUPPRESS_PART_SCAN, + &head->disk->state))) + return; + + mutex_lock(&head->disk->open_mutex); + bdev_disk_changed(head->disk, false); + mutex_unlock(&head->disk->open_mutex); +} + static void nvme_requeue_work(struct work_struct *work) { struct nvme_ns_head *head = @@ -606,6 +619,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head) bio_list_init(&head->requeue_list); spin_lock_init(&head->requeue_lock); INIT_WORK(&head->requeue_work, nvme_requeue_work); + INIT_WORK(&head->partition_scan_work, nvme_partition_scan_work); /* * Add a multipath node if the subsystems supports multiple controllers. @@ -629,6 +643,16 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head) return PTR_ERR(head->disk); head->disk->fops = &nvme_ns_head_ops; head->disk->private_data = head; + + /* + * We need to suppress the partition scan from occuring within the + * controller's scan_work context. If a path error occurs here, the IO + * will wait until a path becomes available or all paths are torn down, + * but that action also occurs within scan_work, so it would deadlock. + * Defer the partion scan to a different context that does not block + * scan_work. + */ + set_bit(GD_SUPPRESS_PART_SCAN, &head->disk->state); sprintf(head->disk->disk_name, "nvme%dn%d", ctrl->subsys->instance, head->instance); return 0; @@ -655,6 +679,7 @@ static void nvme_mpath_set_live(struct nvme_ns *ns) return; } nvme_add_ns_head_cdev(head); + kblockd_schedule_work(&head->partition_scan_work); } mutex_lock(&head->lock); @@ -974,14 +999,14 @@ void nvme_mpath_shutdown_disk(struct nvme_ns_head *head) return; if (test_and_clear_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) { nvme_cdev_del(&head->cdev, &head->cdev_device); + /* + * requeue I/O after NVME_NSHEAD_DISK_LIVE has been cleared + * to allow multipath to fail all I/O. + */ + synchronize_srcu(&head->srcu); + kblockd_schedule_work(&head->requeue_work); del_gendisk(head->disk); } - /* - * requeue I/O after NVME_NSHEAD_DISK_LIVE has been cleared - * to allow multipath to fail all I/O. - */ - synchronize_srcu(&head->srcu); - kblockd_schedule_work(&head->requeue_work); } void nvme_mpath_remove_disk(struct nvme_ns_head *head) @@ -991,6 +1016,7 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head) /* make sure all pending bios are cleaned up */ kblockd_schedule_work(&head->requeue_work); flush_work(&head->requeue_work); + flush_work(&head->partition_scan_work); put_disk(head->disk); } diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 313a4f978a2c..093cb423f536 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -494,6 +494,7 @@ struct nvme_ns_head { struct bio_list requeue_list; spinlock_t requeue_lock; struct work_struct requeue_work; + struct work_struct partition_scan_work; struct mutex lock; unsigned long flags; #define NVME_NSHEAD_DISK_LIVE 0 diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 7990c3f22ecf..4b9fda0b1d9a 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2506,17 +2506,29 @@ static unsigned int nvme_pci_nr_maps(struct nvme_dev *dev) return 1; } -static void nvme_pci_update_nr_queues(struct nvme_dev *dev) +static bool nvme_pci_update_nr_queues(struct nvme_dev *dev) { if (!dev->ctrl.tagset) { nvme_alloc_io_tag_set(&dev->ctrl, &dev->tagset, &nvme_mq_ops, nvme_pci_nr_maps(dev), sizeof(struct nvme_iod)); - return; + return true; + } + + /* Give up if we are racing with nvme_dev_disable() */ + if (!mutex_trylock(&dev->shutdown_lock)) + return false; + + /* Check if nvme_dev_disable() has been executed already */ + if (!dev->online_queues) { + mutex_unlock(&dev->shutdown_lock); + return false; } blk_mq_update_nr_hw_queues(&dev->tagset, dev->online_queues - 1); /* free previously allocated queues that are no longer usable */ nvme_free_queues(dev, dev->online_queues); + mutex_unlock(&dev->shutdown_lock); + return true; } static int nvme_pci_enable(struct nvme_dev *dev) @@ -2797,7 +2809,8 @@ static void nvme_reset_work(struct work_struct *work) nvme_dbbuf_set(dev); nvme_unquiesce_io_queues(&dev->ctrl); nvme_wait_freeze(&dev->ctrl); - nvme_pci_update_nr_queues(dev); + if (!nvme_pci_update_nr_queues(dev)) + goto out; nvme_unfreeze(&dev->ctrl); } else { dev_warn(dev->ctrl.device, "IO queues lost\n"); diff --git a/drivers/nvme/host/pr.c b/drivers/nvme/host/pr.c index 7347ddf85f00..dc7922f22600 100644 --- a/drivers/nvme/host/pr.c +++ b/drivers/nvme/host/pr.c @@ -5,7 +5,7 @@ */ #include <linux/blkdev.h> #include <linux/pr.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "nvme.h" diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index c8fd0e8f0237..24a2759798d0 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -18,7 +18,7 @@ #include <linux/mutex.h> #include <linux/scatterlist.h> #include <linux/nvme.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <rdma/ib_verbs.h> #include <rdma/rdma_cm.h> diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 89c44413c593..3e416af2659f 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -2644,10 +2644,11 @@ static int nvme_tcp_get_address(struct nvme_ctrl *ctrl, char *buf, int size) len = nvmf_get_address(ctrl, buf, size); + if (!test_bit(NVME_TCP_Q_LIVE, &queue->flags)) + return len; + mutex_lock(&queue->queue_lock); - if (!test_bit(NVME_TCP_Q_LIVE, &queue->flags)) - goto done; ret = kernel_getsockname(queue->sock, (struct sockaddr *)&src_addr); if (ret > 0) { if (len > 0) @@ -2655,7 +2656,7 @@ static int nvme_tcp_get_address(struct nvme_ctrl *ctrl, char *buf, int size) len += scnprintf(buf + len, size - len, "%ssrc_addr=%pISc\n", (len) ? "," : "", &src_addr); } -done: + mutex_unlock(&queue->queue_lock); return len; diff --git a/drivers/nvme/host/trace.c b/drivers/nvme/host/trace.c index 0288315f0050..87c437fc070d 100644 --- a/drivers/nvme/host/trace.c +++ b/drivers/nvme/host/trace.c @@ -4,7 +4,7 @@ * Copyright (c) 2018 Johannes Thumshirn, SUSE Linux GmbH */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include "trace.h" static const char *nvme_trace_delete_sq(struct trace_seq *p, u8 *cdw10) |