diff options
Diffstat (limited to 'drivers/nvme/host/core.c')
| -rw-r--r-- | drivers/nvme/host/core.c | 922 |
1 files changed, 667 insertions, 255 deletions
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 903d5813023a..5a14cc7f28ee 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -27,7 +27,6 @@ #include <linux/nvme_ioctl.h> #include <linux/t10-pi.h> #include <linux/pm_qos.h> -#include <scsi/sg.h> #include <asm/unaligned.h> #include "nvme.h" @@ -45,7 +44,7 @@ module_param_named(io_timeout, nvme_io_timeout, byte, 0644); MODULE_PARM_DESC(io_timeout, "timeout in seconds for I/O"); EXPORT_SYMBOL_GPL(nvme_io_timeout); -unsigned char shutdown_timeout = 5; +static unsigned char shutdown_timeout = 5; module_param(shutdown_timeout, byte, 0644); MODULE_PARM_DESC(shutdown_timeout, "timeout in seconds for controller shutdown"); @@ -65,34 +64,67 @@ static bool force_apst; module_param(force_apst, bool, 0644); MODULE_PARM_DESC(force_apst, "allow APST for newly enumerated devices even if quirked off"); +static bool streams; +module_param(streams, bool, 0644); +MODULE_PARM_DESC(streams, "turn on support for Streams write directives"); + +struct workqueue_struct *nvme_wq; +EXPORT_SYMBOL_GPL(nvme_wq); + static LIST_HEAD(nvme_ctrl_list); static DEFINE_SPINLOCK(dev_list_lock); static struct class *nvme_class; -static int nvme_error_status(struct request *req) +static __le32 nvme_get_log_dw10(u8 lid, size_t size) +{ + return cpu_to_le32((((size / 4) - 1) << 16) | lid); +} + +int nvme_reset_ctrl(struct nvme_ctrl *ctrl) +{ + if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) + return -EBUSY; + if (!queue_work(nvme_wq, &ctrl->reset_work)) + return -EBUSY; + return 0; +} +EXPORT_SYMBOL_GPL(nvme_reset_ctrl); + +static int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl) +{ + int ret; + + ret = nvme_reset_ctrl(ctrl); + if (!ret) + flush_work(&ctrl->reset_work); + return ret; +} + +static blk_status_t nvme_error_status(struct request *req) { switch (nvme_req(req)->status & 0x7ff) { case NVME_SC_SUCCESS: - return 0; + return BLK_STS_OK; case NVME_SC_CAP_EXCEEDED: - return -ENOSPC; - default: - return -EIO; - - /* - * XXX: these errors are a nasty side-band protocol to - * drivers/md/dm-mpath.c:noretry_error() that aren't documented - * anywhere.. - */ - case NVME_SC_CMD_SEQ_ERROR: - return -EILSEQ; + return BLK_STS_NOSPC; case NVME_SC_ONCS_NOT_SUPPORTED: - return -EOPNOTSUPP; + return BLK_STS_NOTSUPP; case NVME_SC_WRITE_FAULT: case NVME_SC_READ_ERROR: case NVME_SC_UNWRITTEN_BLOCK: - return -ENODATA; + case NVME_SC_ACCESS_DENIED: + case NVME_SC_READ_ONLY: + return BLK_STS_MEDIUM; + case NVME_SC_GUARD_CHECK: + case NVME_SC_APPTAG_CHECK: + case NVME_SC_REFTAG_CHECK: + case NVME_SC_INVALID_PI: + return BLK_STS_PROTECTION; + case NVME_SC_RESERVATION_CONFLICT: + return BLK_STS_NEXUS; + default: + return BLK_STS_IOERR; } } @@ -102,8 +134,6 @@ static inline bool nvme_req_needs_retry(struct request *req) return false; if (nvme_req(req)->status & NVME_SC_DNR) return false; - if (jiffies - req->start_time >= req->timeout) - return false; if (nvme_req(req)->retries >= nvme_max_retries) return false; return true; @@ -113,7 +143,7 @@ void nvme_complete_rq(struct request *req) { if (unlikely(nvme_req(req)->status && nvme_req_needs_retry(req))) { nvme_req(req)->retries++; - blk_mq_requeue_request(req, !blk_mq_queue_stopped(req->q)); + blk_mq_requeue_request(req, true); return; } @@ -144,9 +174,10 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, enum nvme_ctrl_state new_state) { enum nvme_ctrl_state old_state; + unsigned long flags; bool changed = false; - spin_lock_irq(&ctrl->lock); + spin_lock_irqsave(&ctrl->lock, flags); old_state = ctrl->state; switch (new_state) { @@ -165,7 +196,6 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, switch (old_state) { case NVME_CTRL_NEW: case NVME_CTRL_LIVE: - case NVME_CTRL_RECONNECTING: changed = true; /* FALLTHRU */ default: @@ -208,7 +238,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, if (changed) ctrl->state = new_state; - spin_unlock_irq(&ctrl->lock); + spin_unlock_irqrestore(&ctrl->lock, flags); return changed; } @@ -283,6 +313,105 @@ struct request *nvme_alloc_request(struct request_queue *q, } EXPORT_SYMBOL_GPL(nvme_alloc_request); +static int nvme_toggle_streams(struct nvme_ctrl *ctrl, bool enable) +{ + struct nvme_command c; + + memset(&c, 0, sizeof(c)); + + c.directive.opcode = nvme_admin_directive_send; + c.directive.nsid = cpu_to_le32(NVME_NSID_ALL); + c.directive.doper = NVME_DIR_SND_ID_OP_ENABLE; + c.directive.dtype = NVME_DIR_IDENTIFY; + c.directive.tdtype = NVME_DIR_STREAMS; + c.directive.endir = enable ? NVME_DIR_ENDIR : 0; + + return nvme_submit_sync_cmd(ctrl->admin_q, &c, NULL, 0); +} + +static int nvme_disable_streams(struct nvme_ctrl *ctrl) +{ + return nvme_toggle_streams(ctrl, false); +} + +static int nvme_enable_streams(struct nvme_ctrl *ctrl) +{ + return nvme_toggle_streams(ctrl, true); +} + +static int nvme_get_stream_params(struct nvme_ctrl *ctrl, + struct streams_directive_params *s, u32 nsid) +{ + struct nvme_command c; + + memset(&c, 0, sizeof(c)); + memset(s, 0, sizeof(*s)); + + c.directive.opcode = nvme_admin_directive_recv; + c.directive.nsid = cpu_to_le32(nsid); + c.directive.numd = cpu_to_le32((sizeof(*s) >> 2) - 1); + c.directive.doper = NVME_DIR_RCV_ST_OP_PARAM; + c.directive.dtype = NVME_DIR_STREAMS; + + return nvme_submit_sync_cmd(ctrl->admin_q, &c, s, sizeof(*s)); +} + +static int nvme_configure_directives(struct nvme_ctrl *ctrl) +{ + struct streams_directive_params s; + int ret; + + if (!(ctrl->oacs & NVME_CTRL_OACS_DIRECTIVES)) + return 0; + if (!streams) + return 0; + + ret = nvme_enable_streams(ctrl); + if (ret) + return ret; + + ret = nvme_get_stream_params(ctrl, &s, NVME_NSID_ALL); + if (ret) + return ret; + + ctrl->nssa = le16_to_cpu(s.nssa); + if (ctrl->nssa < BLK_MAX_WRITE_HINTS - 1) { + dev_info(ctrl->device, "too few streams (%u) available\n", + ctrl->nssa); + nvme_disable_streams(ctrl); + return 0; + } + + ctrl->nr_streams = min_t(unsigned, ctrl->nssa, BLK_MAX_WRITE_HINTS - 1); + dev_info(ctrl->device, "Using %u streams\n", ctrl->nr_streams); + return 0; +} + +/* + * Check if 'req' has a write hint associated with it. If it does, assign + * a valid namespace stream to the write. + */ +static void nvme_assign_write_stream(struct nvme_ctrl *ctrl, + struct request *req, u16 *control, + u32 *dsmgmt) +{ + enum rw_hint streamid = req->write_hint; + + if (streamid == WRITE_LIFE_NOT_SET || streamid == WRITE_LIFE_NONE) + streamid = 0; + else { + streamid--; + if (WARN_ON_ONCE(streamid > ctrl->nr_streams)) + return; + + *control |= NVME_RW_DTYPE_STREAMS; + *dsmgmt |= streamid << 16; + } + + if (streamid < ARRAY_SIZE(req->q->write_hints)) + req->q->write_hints[streamid] += blk_rq_bytes(req) >> 9; +} + static inline void nvme_setup_flush(struct nvme_ns *ns, struct nvme_command *cmnd) { @@ -291,7 +420,7 @@ static inline void nvme_setup_flush(struct nvme_ns *ns, cmnd->common.nsid = cpu_to_le32(ns->ns_id); } -static inline int nvme_setup_discard(struct nvme_ns *ns, struct request *req, +static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req, struct nvme_command *cmnd) { unsigned short segments = blk_rq_nr_discard_segments(req), n = 0; @@ -300,7 +429,7 @@ static inline int nvme_setup_discard(struct nvme_ns *ns, struct request *req, range = kmalloc_array(segments, sizeof(*range), GFP_ATOMIC); if (!range) - return BLK_MQ_RQ_QUEUE_BUSY; + return BLK_STS_RESOURCE; __rq_for_each_bio(bio, req) { u64 slba = nvme_block_nr(ns, bio->bi_iter.bi_sector); @@ -314,7 +443,7 @@ static inline int nvme_setup_discard(struct nvme_ns *ns, struct request *req, if (WARN_ON_ONCE(n != segments)) { kfree(range); - return BLK_MQ_RQ_QUEUE_ERROR; + return BLK_STS_IOERR; } memset(cmnd, 0, sizeof(*cmnd)); @@ -328,15 +457,26 @@ static inline int nvme_setup_discard(struct nvme_ns *ns, struct request *req, req->special_vec.bv_len = sizeof(*range) * segments; req->rq_flags |= RQF_SPECIAL_PAYLOAD; - return BLK_MQ_RQ_QUEUE_OK; + return BLK_STS_OK; } -static inline void nvme_setup_rw(struct nvme_ns *ns, struct request *req, - struct nvme_command *cmnd) +static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns, + struct request *req, struct nvme_command *cmnd) { + struct nvme_ctrl *ctrl = ns->ctrl; u16 control = 0; u32 dsmgmt = 0; + /* + * If formated with metadata, require the block layer provide a buffer + * unless this namespace is formated such that the metadata can be + * stripped/generated by the controller with PRACT=1. + */ + if (ns && ns->ms && + (!ns->pi_type || ns->ms != sizeof(struct t10_pi_tuple)) && + !blk_integrity_rq(req) && !blk_rq_is_passthrough(req)) + return BLK_STS_NOTSUPP; + if (req->cmd_flags & REQ_FUA) control |= NVME_RW_FUA; if (req->cmd_flags & (REQ_FAILFAST_DEV | REQ_RAHEAD)) @@ -351,6 +491,9 @@ static inline void nvme_setup_rw(struct nvme_ns *ns, struct request *req, cmnd->rw.slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req))); cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1); + if (req_op(req) == REQ_OP_WRITE && ctrl->nr_streams) + nvme_assign_write_stream(ctrl, req, &control, &dsmgmt); + if (ns->ms) { switch (ns->pi_type) { case NVME_NS_DPS_PI_TYPE3: @@ -370,12 +513,13 @@ static inline void nvme_setup_rw(struct nvme_ns *ns, struct request *req, cmnd->rw.control = cpu_to_le16(control); cmnd->rw.dsmgmt = cpu_to_le32(dsmgmt); + return 0; } -int nvme_setup_cmd(struct nvme_ns *ns, struct request *req, +blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req, struct nvme_command *cmd) { - int ret = BLK_MQ_RQ_QUEUE_OK; + blk_status_t ret = BLK_STS_OK; if (!(req->rq_flags & RQF_DONTPREP)) { nvme_req(req)->retries = 0; @@ -398,11 +542,11 @@ int nvme_setup_cmd(struct nvme_ns *ns, struct request *req, break; case REQ_OP_READ: case REQ_OP_WRITE: - nvme_setup_rw(ns, req, cmd); + ret = nvme_setup_rw(ns, req, cmd); break; default: WARN_ON_ONCE(1); - return BLK_MQ_RQ_QUEUE_ERROR; + return BLK_STS_IOERR; } cmd->common.command_id = req->tag; @@ -454,10 +598,44 @@ int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, } EXPORT_SYMBOL_GPL(nvme_submit_sync_cmd); -int __nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd, - void __user *ubuffer, unsigned bufflen, - void __user *meta_buffer, unsigned meta_len, u32 meta_seed, - u32 *result, unsigned timeout) +static void *nvme_add_user_metadata(struct bio *bio, void __user *ubuf, + unsigned len, u32 seed, bool write) +{ + struct bio_integrity_payload *bip; + int ret = -ENOMEM; + void *buf; + + buf = kmalloc(len, GFP_KERNEL); + if (!buf) + goto out; + + ret = -EFAULT; + if (write && copy_from_user(buf, ubuf, len)) + goto out_free_meta; + + bip = bio_integrity_alloc(bio, GFP_KERNEL, 1); + if (IS_ERR(bip)) { + ret = PTR_ERR(bip); + goto out_free_meta; + } + + bip->bip_iter.bi_size = len; + bip->bip_iter.bi_sector = seed; + ret = bio_integrity_add_page(bio, virt_to_page(buf), len, + offset_in_page(buf)); + if (ret == len) + return buf; + ret = -ENOMEM; +out_free_meta: + kfree(buf); +out: + return ERR_PTR(ret); +} + +static int nvme_submit_user_cmd(struct request_queue *q, + struct nvme_command *cmd, void __user *ubuffer, + unsigned bufflen, void __user *meta_buffer, unsigned meta_len, + u32 meta_seed, u32 *result, unsigned timeout) { bool write = nvme_is_write(cmd); struct nvme_ns *ns = q->queuedata; @@ -479,50 +657,17 @@ int __nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd, if (ret) goto out; bio = req->bio; - - if (!disk) - goto submit; - bio->bi_bdev = bdget_disk(disk, 0); - if (!bio->bi_bdev) { - ret = -ENODEV; - goto out_unmap; - } - - if (meta_buffer && meta_len) { - struct bio_integrity_payload *bip; - - meta = kmalloc(meta_len, GFP_KERNEL); - if (!meta) { - ret = -ENOMEM; + bio->bi_disk = disk; + if (disk && meta_buffer && meta_len) { + meta = nvme_add_user_metadata(bio, meta_buffer, meta_len, + meta_seed, write); + if (IS_ERR(meta)) { + ret = PTR_ERR(meta); goto out_unmap; } - - if (write) { - if (copy_from_user(meta, meta_buffer, - meta_len)) { - ret = -EFAULT; - goto out_free_meta; - } - } - - bip = bio_integrity_alloc(bio, GFP_KERNEL, 1); - if (IS_ERR(bip)) { - ret = PTR_ERR(bip); - goto out_free_meta; - } - - bip->bip_iter.bi_size = meta_len; - bip->bip_iter.bi_sector = meta_seed; - - ret = bio_integrity_add_page(bio, virt_to_page(meta), - meta_len, offset_in_page(meta)); - if (ret != meta_len) { - ret = -ENOMEM; - goto out_free_meta; - } } } - submit: + blk_execute_rq(req->q, disk, req, 0); if (nvme_req(req)->flags & NVME_REQ_CANCELLED) ret = -EINTR; @@ -534,36 +679,25 @@ int __nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd, if (copy_to_user(meta_buffer, meta, meta_len)) ret = -EFAULT; } - out_free_meta: kfree(meta); out_unmap: - if (bio) { - if (disk && bio->bi_bdev) - bdput(bio->bi_bdev); + if (bio) blk_rq_unmap_user(bio); - } out: blk_mq_free_request(req); return ret; } -int nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd, - void __user *ubuffer, unsigned bufflen, u32 *result, - unsigned timeout) -{ - return __nvme_submit_user_cmd(q, cmd, ubuffer, bufflen, NULL, 0, 0, - result, timeout); -} - -static void nvme_keep_alive_end_io(struct request *rq, int error) +static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status) { struct nvme_ctrl *ctrl = rq->end_io_data; blk_mq_free_request(rq); - if (error) { + if (status) { dev_err(ctrl->device, - "failed nvme_keep_alive_end_io error=%d\n", error); + "failed nvme_keep_alive_end_io error=%d\n", + status); return; } @@ -599,7 +733,7 @@ static void nvme_keep_alive_work(struct work_struct *work) if (nvme_keep_alive(ctrl)) { /* allocation failure, reset the controller */ dev_err(ctrl->device, "keep-alive failed\n"); - ctrl->ops->reset_ctrl(ctrl); + nvme_reset_ctrl(ctrl); return; } } @@ -623,7 +757,7 @@ void nvme_stop_keep_alive(struct nvme_ctrl *ctrl) } EXPORT_SYMBOL_GPL(nvme_stop_keep_alive); -int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id) +static int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id) { struct nvme_command c = { }; int error; @@ -643,6 +777,78 @@ int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id) return error; } +static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid, + u8 *eui64, u8 *nguid, uuid_t *uuid) +{ + struct nvme_command c = { }; + int status; + void *data; + int pos; + int len; + + c.identify.opcode = nvme_admin_identify; + c.identify.nsid = cpu_to_le32(nsid); + c.identify.cns = NVME_ID_CNS_NS_DESC_LIST; + + data = kzalloc(NVME_IDENTIFY_DATA_SIZE, GFP_KERNEL); + if (!data) + return -ENOMEM; + + status = nvme_submit_sync_cmd(ctrl->admin_q, &c, data, + NVME_IDENTIFY_DATA_SIZE); + if (status) + goto free_data; + + for (pos = 0; pos < NVME_IDENTIFY_DATA_SIZE; pos += len) { + struct nvme_ns_id_desc *cur = data + pos; + + if (cur->nidl == 0) + break; + + switch (cur->nidt) { + case NVME_NIDT_EUI64: + if (cur->nidl != NVME_NIDT_EUI64_LEN) { + dev_warn(ctrl->device, + "ctrl returned bogus length: %d for NVME_NIDT_EUI64\n", + cur->nidl); + goto free_data; + } + len = NVME_NIDT_EUI64_LEN; + memcpy(eui64, data + pos + sizeof(*cur), len); + break; + case NVME_NIDT_NGUID: + if (cur->nidl != NVME_NIDT_NGUID_LEN) { + dev_warn(ctrl->device, + "ctrl returned bogus length: %d for NVME_NIDT_NGUID\n", + cur->nidl); + goto free_data; + } + len = NVME_NIDT_NGUID_LEN; + memcpy(nguid, data + pos + sizeof(*cur), len); + break; + case NVME_NIDT_UUID: + if (cur->nidl != NVME_NIDT_UUID_LEN) { + dev_warn(ctrl->device, + "ctrl returned bogus length: %d for NVME_NIDT_UUID\n", + cur->nidl); + goto free_data; + } + len = NVME_NIDT_UUID_LEN; + uuid_copy(uuid, data + pos + sizeof(*cur)); + break; + default: + /* Skip unnkown types */ + len = cur->nidl; + break; + } + + len += sizeof(*cur); + } +free_data: + kfree(data); + return status; +} + static int nvme_identify_ns_list(struct nvme_ctrl *dev, unsigned nsid, __le32 *ns_list) { struct nvme_command c = { }; @@ -653,9 +859,10 @@ static int nvme_identify_ns_list(struct nvme_ctrl *dev, unsigned nsid, __le32 *n return nvme_submit_sync_cmd(dev->admin_q, &c, ns_list, 0x1000); } -int nvme_identify_ns(struct nvme_ctrl *dev, unsigned nsid, - struct nvme_id_ns **id) +static struct nvme_id_ns *nvme_identify_ns(struct nvme_ctrl *ctrl, + unsigned nsid) { + struct nvme_id_ns *id; struct nvme_command c = { }; int error; @@ -664,37 +871,21 @@ int nvme_identify_ns(struct nvme_ctrl *dev, unsigned nsid, c.identify.nsid = cpu_to_le32(nsid); c.identify.cns = NVME_ID_CNS_NS; - *id = kmalloc(sizeof(struct nvme_id_ns), GFP_KERNEL); - if (!*id) - return -ENOMEM; - - error = nvme_submit_sync_cmd(dev->admin_q, &c, *id, - sizeof(struct nvme_id_ns)); - if (error) - kfree(*id); - return error; -} + id = kmalloc(sizeof(*id), GFP_KERNEL); + if (!id) + return NULL; -int nvme_get_features(struct nvme_ctrl *dev, unsigned fid, unsigned nsid, - void *buffer, size_t buflen, u32 *result) -{ - struct nvme_command c; - union nvme_result res; - int ret; - - memset(&c, 0, sizeof(c)); - c.features.opcode = nvme_admin_get_features; - c.features.nsid = cpu_to_le32(nsid); - c.features.fid = cpu_to_le32(fid); + error = nvme_submit_sync_cmd(ctrl->admin_q, &c, id, sizeof(*id)); + if (error) { + dev_warn(ctrl->device, "Identify namespace failed\n"); + kfree(id); + return NULL; + } - ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &res, buffer, buflen, 0, - NVME_QID_ANY, 0, 0); - if (ret >= 0 && result) - *result = le32_to_cpu(res.u32); - return ret; + return id; } -int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11, +static int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11, void *buffer, size_t buflen, u32 *result) { struct nvme_command c; @@ -713,28 +904,6 @@ int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11, return ret; } -int nvme_get_log_page(struct nvme_ctrl *dev, struct nvme_smart_log **log) -{ - struct nvme_command c = { }; - int error; - - c.common.opcode = nvme_admin_get_log_page, - c.common.nsid = cpu_to_le32(0xFFFFFFFF), - c.common.cdw10[0] = cpu_to_le32( - (((sizeof(struct nvme_smart_log) / 4) - 1) << 16) | - NVME_LOG_SMART), - - *log = kmalloc(sizeof(struct nvme_smart_log), GFP_KERNEL); - if (!*log) - return -ENOMEM; - - error = nvme_submit_sync_cmd(dev->admin_q, &c, *log, - sizeof(struct nvme_smart_log)); - if (error) - kfree(*log); - return error; -} - int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count) { u32 q_count = (*count - 1) | ((*count - 1) << 16); @@ -752,7 +921,7 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count) * access to the admin queue, as that might be only way to fix them up. */ if (status > 0) { - dev_err(ctrl->dev, "Could not set queue count (%d)\n", status); + dev_err(ctrl->device, "Could not set queue count (%d)\n", status); *count = 0; } else { nr_io_queues = min(result & 0xffff, result >> 16) + 1; @@ -808,7 +977,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) c.rw.apptag = cpu_to_le16(io.apptag); c.rw.appmask = cpu_to_le16(io.appmask); - return __nvme_submit_user_cmd(ns->queue, &c, + return nvme_submit_user_cmd(ns->queue, &c, (void __user *)(uintptr_t)io.addr, length, metadata, meta_len, io.slba, NULL, 0); } @@ -846,7 +1015,8 @@ 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, (void __user *)(uintptr_t)cmd.addr, cmd.data_len, - &cmd.result, timeout); + (void __user *)(uintptr_t)cmd.metadata, cmd.metadata, + 0, &cmd.result, timeout); if (status >= 0) { if (put_user(cmd.result, &ucmd->result)) return -EFAULT; @@ -870,12 +1040,6 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode, return nvme_user_cmd(ns->ctrl, ns, (void __user *)arg); case NVME_IOCTL_SUBMIT_IO: return nvme_submit_io(ns, (void __user *)arg); -#ifdef CONFIG_BLK_DEV_NVME_SCSI - case SG_GET_VERSION_NUM: - return nvme_sg_get_version_num((void __user *)arg); - case SG_IO: - return nvme_sg_io(ns, (void __user *)arg); -#endif default: #ifdef CONFIG_NVM if (ns->ndev) @@ -892,10 +1056,6 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode, static int nvme_compat_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { - switch (cmd) { - case SG_IO: - return -ENOIOCTLCMD; - } return nvme_ioctl(bdev, mode, cmd, arg); } #else @@ -983,6 +1143,12 @@ static void nvme_init_integrity(struct nvme_ns *ns) } #endif /* CONFIG_BLK_DEV_INTEGRITY */ +static void nvme_set_chunk_size(struct nvme_ns *ns) +{ + u32 chunk_size = (((u32)ns->noiob) << (ns->lba_shift - 9)); + blk_queue_chunk_sectors(ns->queue, rounddown_pow_of_two(chunk_size)); +} + static void nvme_config_discard(struct nvme_ns *ns) { struct nvme_ctrl *ctrl = ns->ctrl; @@ -991,8 +1157,15 @@ static void nvme_config_discard(struct nvme_ns *ns) BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) < NVME_DSM_MAX_RANGES); - ns->queue->limits.discard_alignment = logical_block_size; - ns->queue->limits.discard_granularity = logical_block_size; + if (ctrl->nr_streams && ns->sws && ns->sgs) { + unsigned int sz = logical_block_size * ns->sws * ns->sgs; + + ns->queue->limits.discard_alignment = sz; + ns->queue->limits.discard_granularity = sz; + } else { + ns->queue->limits.discard_alignment = logical_block_size; + ns->queue->limits.discard_granularity = logical_block_size; + } blk_queue_max_discard_sectors(ns->queue, UINT_MAX); blk_queue_max_discard_segments(ns->queue, NVME_DSM_MAX_RANGES); queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, ns->queue); @@ -1001,29 +1174,27 @@ static void nvme_config_discard(struct nvme_ns *ns) blk_queue_max_write_zeroes_sectors(ns->queue, UINT_MAX); } -static int nvme_revalidate_ns(struct nvme_ns *ns, struct nvme_id_ns **id) +static void nvme_report_ns_ids(struct nvme_ctrl *ctrl, unsigned int nsid, + struct nvme_id_ns *id, u8 *eui64, u8 *nguid, uuid_t *uuid) { - if (nvme_identify_ns(ns->ctrl, ns->ns_id, id)) { - dev_warn(ns->ctrl->dev, "%s: Identify failure\n", __func__); - return -ENODEV; - } - - if ((*id)->ncap == 0) { - kfree(*id); - return -ENODEV; + if (ctrl->vs >= NVME_VS(1, 1, 0)) + memcpy(eui64, id->eui64, sizeof(id->eui64)); + if (ctrl->vs >= NVME_VS(1, 2, 0)) + memcpy(nguid, id->nguid, sizeof(id->nguid)); + if (ctrl->vs >= NVME_VS(1, 3, 0)) { + /* Don't treat error as fatal we potentially + * already have a NGUID or EUI-64 + */ + if (nvme_identify_ns_descs(ctrl, nsid, eui64, nguid, uuid)) + dev_warn(ctrl->device, + "%s: Identify Descriptors failed\n", __func__); } - - if (ns->ctrl->vs >= NVME_VS(1, 1, 0)) - memcpy(ns->eui, (*id)->eui64, sizeof(ns->eui)); - if (ns->ctrl->vs >= NVME_VS(1, 2, 0)) - memcpy(ns->uuid, (*id)->nguid, sizeof(ns->uuid)); - - return 0; } static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id) { struct nvme_ns *ns = disk->private_data; + struct nvme_ctrl *ctrl = ns->ctrl; u16 bs; /* @@ -1034,12 +1205,15 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id) if (ns->lba_shift == 0) ns->lba_shift = 9; bs = 1 << ns->lba_shift; + ns->noiob = le16_to_cpu(id->noiob); blk_mq_freeze_queue(disk->queue); - if (ns->ctrl->ops->flags & NVME_F_METADATA_SUPPORTED) + if (ctrl->ops->flags & NVME_F_METADATA_SUPPORTED) nvme_prep_integrity(disk, id, bs); blk_queue_logical_block_size(ns->queue, bs); + if (ns->noiob) + nvme_set_chunk_size(ns); if (ns->ms && !blk_get_integrity(disk) && !ns->ext) nvme_init_integrity(ns); if (ns->ms && !(ns->ms == 8 && ns->pi_type) && !blk_get_integrity(disk)) @@ -1047,7 +1221,7 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id) else set_capacity(disk, le64_to_cpup(&id->nsze) << (ns->lba_shift - 9)); - if (ns->ctrl->oncs & NVME_CTRL_ONCS_DSM) + if (ctrl->oncs & NVME_CTRL_ONCS_DSM) nvme_config_discard(ns); blk_mq_unfreeze_queue(disk->queue); } @@ -1055,22 +1229,38 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id) static int nvme_revalidate_disk(struct gendisk *disk) { struct nvme_ns *ns = disk->private_data; - struct nvme_id_ns *id = NULL; - int ret; + struct nvme_ctrl *ctrl = ns->ctrl; + struct nvme_id_ns *id; + u8 eui64[8] = { 0 }, nguid[16] = { 0 }; + uuid_t uuid = uuid_null; + int ret = 0; if (test_bit(NVME_NS_DEAD, &ns->flags)) { set_capacity(disk, 0); return -ENODEV; } - ret = nvme_revalidate_ns(ns, &id); - if (ret) - return ret; + id = nvme_identify_ns(ctrl, ns->ns_id); + if (!id) + return -ENODEV; - __nvme_revalidate_disk(disk, id); - kfree(id); + if (id->ncap == 0) { + ret = -ENODEV; + goto out; + } - return 0; + nvme_report_ns_ids(ctrl, ns->ns_id, id, eui64, nguid, &uuid); + if (!uuid_equal(&ns->uuid, &uuid) || + memcmp(&ns->nguid, &nguid, sizeof(ns->nguid)) || + memcmp(&ns->eui, &eui64, sizeof(ns->eui))) { + dev_err(ctrl->device, + "identifiers changed for nsid %d\n", ns->ns_id); + ret = -ENODEV; + } + +out: + kfree(id); + return ret; } static char nvme_pr_type(enum pr_type type) @@ -1270,7 +1460,7 @@ int nvme_enable_ctrl(struct nvme_ctrl *ctrl, u64 cap) ctrl->ctrl_config = NVME_CC_CSS_NVM; ctrl->ctrl_config |= (page_shift - 12) << NVME_CC_MPS_SHIFT; - ctrl->ctrl_config |= NVME_CC_ARB_RR | NVME_CC_SHN_NONE; + ctrl->ctrl_config |= NVME_CC_AMS_RR | NVME_CC_SHN_NONE; ctrl->ctrl_config |= NVME_CC_IOSQES | NVME_CC_IOCQES; ctrl->ctrl_config |= NVME_CC_ENABLE; @@ -1283,7 +1473,7 @@ EXPORT_SYMBOL_GPL(nvme_enable_ctrl); int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl) { - unsigned long timeout = SHUTDOWN_TIMEOUT + jiffies; + unsigned long timeout = jiffies + (ctrl->shutdown_timeout * HZ); u32 csts; int ret; @@ -1332,7 +1522,24 @@ static void nvme_set_queue_limits(struct nvme_ctrl *ctrl, blk_queue_write_cache(q, vwc, vwc); } -static void nvme_configure_apst(struct nvme_ctrl *ctrl) +static int nvme_configure_timestamp(struct nvme_ctrl *ctrl) +{ + __le64 ts; + int ret; + + if (!(ctrl->oncs & NVME_CTRL_ONCS_TIMESTAMP)) + return 0; + + ts = cpu_to_le64(ktime_to_ms(ktime_get_real())); + ret = nvme_set_features(ctrl, NVME_FEAT_TIMESTAMP, 0, &ts, sizeof(ts), + NULL); + if (ret) + dev_warn_once(ctrl->device, + "could not set timestamp (%d)\n", ret); + return ret; +} + +static int nvme_configure_apst(struct nvme_ctrl *ctrl) { /* * APST (Autonomous Power State Transition) lets us program a @@ -1361,18 +1568,18 @@ static void nvme_configure_apst(struct nvme_ctrl *ctrl) * then don't do anything. */ if (!ctrl->apsta) - return; + return 0; if (ctrl->npss > 31) { dev_warn(ctrl->device, "NPSS is invalid; not using APST\n"); - return; + return 0; } table = kzalloc(sizeof(*table), GFP_KERNEL); if (!table) - return; + return 0; - if (ctrl->ps_max_latency_us == 0) { + if (!ctrl->apst_enabled || ctrl->ps_max_latency_us == 0) { /* Turn off APST. */ apste = 0; dev_dbg(ctrl->device, "APST disabled\n"); @@ -1452,6 +1659,7 @@ static void nvme_configure_apst(struct nvme_ctrl *ctrl) dev_err(ctrl->device, "failed to set APST feature (%d)\n", ret); kfree(table); + return ret; } static void nvme_set_latency_tolerance(struct device *dev, s32 val) @@ -1528,6 +1736,31 @@ static bool quirk_matches(const struct nvme_id_ctrl *id, string_matches(id->fr, q->fr, sizeof(id->fr)); } +static void nvme_init_subnqn(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) +{ + size_t nqnlen; + int off; + + nqnlen = strnlen(id->subnqn, NVMF_NQN_SIZE); + if (nqnlen > 0 && nqnlen < NVMF_NQN_SIZE) { + strcpy(ctrl->subnqn, id->subnqn); + return; + } + + if (ctrl->vs >= NVME_VS(1, 2, 1)) + dev_warn(ctrl->device, "missing or invalid SUBNQN field.\n"); + + /* Generate a "fake" NQN per Figure 254 in NVMe 1.3 + ECN 001 */ + off = snprintf(ctrl->subnqn, NVMF_NQN_SIZE, + "nqn.2014.08.org.nvmexpress:%4x%4x", + le16_to_cpu(id->vid), le16_to_cpu(id->ssvid)); + memcpy(ctrl->subnqn + off, id->sn, sizeof(id->sn)); + off += sizeof(id->sn); + memcpy(ctrl->subnqn + off, id->mn, sizeof(id->mn)); + off += sizeof(id->mn); + memset(ctrl->subnqn + off, 0, sizeof(ctrl->subnqn) - off); +} + /* * Initialize the cached copies of the Identify data and various controller * register in our nvme_ctrl structure. This should be called as soon as @@ -1539,7 +1772,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) u64 cap; int ret, page_shift; u32 max_hw_sectors; - u8 prev_apsta; + bool prev_apst_enabled; ret = ctrl->ops->reg_read32(ctrl, NVME_REG_VS, &ctrl->vs); if (ret) { @@ -1563,6 +1796,8 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) return -EIO; } + nvme_init_subnqn(ctrl, id); + if (!ctrl->identified) { /* * Check for quirks. Quirk can depend on firmware version, @@ -1582,7 +1817,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) } if (force_apst && (ctrl->quirks & NVME_QUIRK_NO_DEEPEST_PS)) { - dev_warn(ctrl->dev, "forcibly allowing all power states due to nvme_core.force_apst -- use at your own risk\n"); + dev_warn(ctrl->device, "forcibly allowing all power states due to nvme_core.force_apst -- use at your own risk\n"); ctrl->quirks &= ~NVME_QUIRK_NO_DEEPEST_PS; } @@ -1606,17 +1841,32 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) ctrl->sgls = le32_to_cpu(id->sgls); ctrl->kas = le16_to_cpu(id->kas); + if (id->rtd3e) { + /* us -> s */ + u32 transition_time = le32_to_cpu(id->rtd3e) / 1000000; + + ctrl->shutdown_timeout = clamp_t(unsigned int, transition_time, + shutdown_timeout, 60); + + if (ctrl->shutdown_timeout != shutdown_timeout) + dev_warn(ctrl->device, + "Shutdown timeout set to %u seconds\n", + ctrl->shutdown_timeout); + } else + ctrl->shutdown_timeout = shutdown_timeout; + ctrl->npss = id->npss; - prev_apsta = ctrl->apsta; + ctrl->apsta = id->apsta; + prev_apst_enabled = ctrl->apst_enabled; if (ctrl->quirks & NVME_QUIRK_NO_APST) { if (force_apst && id->apsta) { - dev_warn(ctrl->dev, "forcibly allowing APST due to nvme_core.force_apst -- use at your own risk\n"); - ctrl->apsta = 1; + dev_warn(ctrl->device, "forcibly allowing APST due to nvme_core.force_apst -- use at your own risk\n"); + ctrl->apst_enabled = true; } else { - ctrl->apsta = 0; + ctrl->apst_enabled = false; } } else { - ctrl->apsta = id->apsta; + ctrl->apst_enabled = id->apsta; } memcpy(ctrl->psd, id->psd, sizeof(ctrl->psd)); @@ -1630,29 +1880,50 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) * In fabrics we need to verify the cntlid matches the * admin connect */ - if (ctrl->cntlid != le16_to_cpu(id->cntlid)) + if (ctrl->cntlid != le16_to_cpu(id->cntlid)) { ret = -EINVAL; + goto out_free; + } if (!ctrl->opts->discovery_nqn && !ctrl->kas) { - dev_err(ctrl->dev, + dev_err(ctrl->device, "keep-alive support is mandatory for fabrics\n"); ret = -EINVAL; + goto out_free; } } else { ctrl->cntlid = le16_to_cpu(id->cntlid); + ctrl->hmpre = le32_to_cpu(id->hmpre); + ctrl->hmmin = le32_to_cpu(id->hmmin); + ctrl->hmminds = le32_to_cpu(id->hmminds); + ctrl->hmmaxd = le16_to_cpu(id->hmmaxd); } kfree(id); - if (ctrl->apsta && !prev_apsta) + if (ctrl->apst_enabled && !prev_apst_enabled) dev_pm_qos_expose_latency_tolerance(ctrl->device); - else if (!ctrl->apsta && prev_apsta) + else if (!ctrl->apst_enabled && prev_apst_enabled) dev_pm_qos_hide_latency_tolerance(ctrl->device); - nvme_configure_apst(ctrl); + ret = nvme_configure_apst(ctrl); + if (ret < 0) + return ret; + + ret = nvme_configure_timestamp(ctrl); + if (ret < 0) + return ret; + + ret = nvme_configure_directives(ctrl); + if (ret < 0) + return ret; ctrl->identified = true; + return 0; + +out_free: + kfree(id); return ret; } EXPORT_SYMBOL_GPL(nvme_init_identify); @@ -1735,7 +2006,7 @@ static long nvme_dev_ioctl(struct file *file, unsigned int cmd, return nvme_dev_user_cmd(ctrl, argp); case NVME_IOCTL_RESET: dev_warn(ctrl->device, "resetting controller\n"); - return ctrl->ops->reset_ctrl(ctrl); + return nvme_reset_ctrl_sync(ctrl); case NVME_IOCTL_SUBSYS_RESET: return nvme_reset_subsystem(ctrl); case NVME_IOCTL_RESCAN: @@ -1761,7 +2032,7 @@ static ssize_t nvme_sysfs_reset(struct device *dev, struct nvme_ctrl *ctrl = dev_get_drvdata(dev); int ret; - ret = ctrl->ops->reset_ctrl(ctrl); + ret = nvme_reset_ctrl_sync(ctrl); if (ret < 0) return ret; return count; @@ -1787,15 +2058,20 @@ static ssize_t wwid_show(struct device *dev, struct device_attribute *attr, int serial_len = sizeof(ctrl->serial); int model_len = sizeof(ctrl->model); - if (memchr_inv(ns->uuid, 0, sizeof(ns->uuid))) - return sprintf(buf, "eui.%16phN\n", ns->uuid); + if (!uuid_is_null(&ns->uuid)) + return sprintf(buf, "uuid.%pU\n", &ns->uuid); + + if (memchr_inv(ns->nguid, 0, sizeof(ns->nguid))) + return sprintf(buf, "eui.%16phN\n", ns->nguid); if (memchr_inv(ns->eui, 0, sizeof(ns->eui))) return sprintf(buf, "eui.%8phN\n", ns->eui); - while (ctrl->serial[serial_len - 1] == ' ') + while (serial_len > 0 && (ctrl->serial[serial_len - 1] == ' ' || + ctrl->serial[serial_len - 1] == '\0')) serial_len--; - while (ctrl->model[model_len - 1] == ' ') + while (model_len > 0 && (ctrl->model[model_len - 1] == ' ' || + ctrl->model[model_len - 1] == '\0')) model_len--; return sprintf(buf, "nvme.%04x-%*phN-%*phN-%08x\n", ctrl->vid, @@ -1803,11 +2079,28 @@ static ssize_t wwid_show(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR(wwid, S_IRUGO, wwid_show, NULL); +static ssize_t nguid_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct nvme_ns *ns = nvme_get_ns_from_dev(dev); + return sprintf(buf, "%pU\n", ns->nguid); +} +static DEVICE_ATTR(nguid, S_IRUGO, nguid_show, NULL); + static ssize_t uuid_show(struct device *dev, struct device_attribute *attr, char *buf) { struct nvme_ns *ns = nvme_get_ns_from_dev(dev); - return sprintf(buf, "%pU\n", ns->uuid); + + /* For backward compatibility expose the NGUID to userspace if + * we have no UUID set + */ + if (uuid_is_null(&ns->uuid)) { + printk_ratelimited(KERN_WARNING + "No UUID available providing old NGUID\n"); + return sprintf(buf, "%pU\n", ns->nguid); + } + return sprintf(buf, "%pU\n", &ns->uuid); } static DEVICE_ATTR(uuid, S_IRUGO, uuid_show, NULL); @@ -1830,6 +2123,7 @@ static DEVICE_ATTR(nsid, S_IRUGO, nsid_show, NULL); static struct attribute *nvme_ns_attrs[] = { &dev_attr_wwid.attr, &dev_attr_uuid.attr, + &dev_attr_nguid.attr, &dev_attr_eui.attr, &dev_attr_nsid.attr, NULL, @@ -1842,7 +2136,12 @@ static umode_t nvme_ns_attrs_are_visible(struct kobject *kobj, struct nvme_ns *ns = nvme_get_ns_from_dev(dev); if (a == &dev_attr_uuid.attr) { - if (!memchr_inv(ns->uuid, 0, sizeof(ns->uuid))) + if (uuid_is_null(&ns->uuid) && + !memchr_inv(ns->nguid, 0, sizeof(ns->nguid))) + return 0; + } + if (a == &dev_attr_nguid.attr) { + if (!memchr_inv(ns->nguid, 0, sizeof(ns->nguid))) return 0; } if (a == &dev_attr_eui.attr) { @@ -1931,8 +2230,7 @@ static ssize_t nvme_sysfs_show_subsysnqn(struct device *dev, { struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - return snprintf(buf, PAGE_SIZE, "%s\n", - ctrl->ops->get_subsysnqn(ctrl)); + return snprintf(buf, PAGE_SIZE, "%s\n", ctrl->subnqn); } static DEVICE_ATTR(subsysnqn, S_IRUGO, nvme_sysfs_show_subsysnqn, NULL); @@ -1961,24 +2259,16 @@ static struct attribute *nvme_dev_attrs[] = { NULL }; -#define CHECK_ATTR(ctrl, a, name) \ - if ((a) == &dev_attr_##name.attr && \ - !(ctrl)->ops->get_##name) \ - return 0 - static umode_t nvme_dev_attrs_are_visible(struct kobject *kobj, struct attribute *a, int n) { struct device *dev = container_of(kobj, struct device, kobj); struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - if (a == &dev_attr_delete_controller.attr) { - if (!ctrl->ops->delete_ctrl) - return 0; - } - - CHECK_ATTR(ctrl, a, subsysnqn); - CHECK_ATTR(ctrl, a, address); + if (a == &dev_attr_delete_controller.attr && !ctrl->ops->delete_ctrl) + return 0; + if (a == &dev_attr_address.attr && !ctrl->ops->get_address) + return 0; return a->mode; } @@ -2019,6 +2309,32 @@ static struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid) return ret; } +static int nvme_setup_streams_ns(struct nvme_ctrl *ctrl, struct nvme_ns *ns) +{ + struct streams_directive_params s; + int ret; + + if (!ctrl->nr_streams) + return 0; + + ret = nvme_get_stream_params(ctrl, &s, ns->ns_id); + if (ret) + return ret; + + ns->sws = le32_to_cpu(s.sws); + ns->sgs = le16_to_cpu(s.sgs); + + if (ns->sws) { + unsigned int bs = 1 << ns->lba_shift; + + blk_queue_io_min(ns->queue, bs * ns->sws); + if (ns->sgs) + blk_queue_io_opt(ns->queue, bs * ns->sws * ns->sgs); + } + + return 0; +} + static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) { struct nvme_ns *ns; @@ -2048,16 +2364,24 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift); nvme_set_queue_limits(ctrl, ns->queue); + nvme_setup_streams_ns(ctrl, ns); sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->instance); - if (nvme_revalidate_ns(ns, &id)) + id = nvme_identify_ns(ctrl, nsid); + if (!id) goto out_free_queue; - if (nvme_nvm_ns_supported(ns, id) && - nvme_nvm_register(ns, disk_name, node)) { - dev_warn(ctrl->dev, "%s: LightNVM init failure\n", __func__); + if (id->ncap == 0) goto out_free_id; + + nvme_report_ns_ids(ctrl, ns->ns_id, id, ns->eui, ns->nguid, &ns->uuid); + + if ((ctrl->quirks & NVME_QUIRK_LIGHTNVM) && id->vs[0] == 0x1) { + if (nvme_nvm_register(ns, disk_name, node)) { + dev_warn(ctrl->device, "LightNVM init failure\n"); + goto out_free_id; + } } disk = alloc_disk_node(0, node); @@ -2231,7 +2555,7 @@ void nvme_queue_scan(struct nvme_ctrl *ctrl) * removal. */ if (ctrl->state == NVME_CTRL_LIVE) - schedule_work(&ctrl->scan_work); + queue_work(nvme_wq, &ctrl->scan_work); } EXPORT_SYMBOL_GPL(nvme_queue_scan); @@ -2264,7 +2588,7 @@ static void nvme_async_event_work(struct work_struct *work) container_of(work, struct nvme_ctrl, async_event_work); spin_lock_irq(&ctrl->lock); - while (ctrl->event_limit > 0) { + while (ctrl->state == NVME_CTRL_LIVE && ctrl->event_limit > 0) { int aer_idx = --ctrl->event_limit; spin_unlock_irq(&ctrl->lock); @@ -2274,6 +2598,71 @@ static void nvme_async_event_work(struct work_struct *work) spin_unlock_irq(&ctrl->lock); } +static bool nvme_ctrl_pp_status(struct nvme_ctrl *ctrl) +{ + + u32 csts; + + if (ctrl->ops->reg_read32(ctrl, NVME_REG_CSTS, &csts)) + return false; + + if (csts == ~0) + return false; + + return ((ctrl->ctrl_config & NVME_CC_ENABLE) && (csts & NVME_CSTS_PP)); +} + +static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl) +{ + struct nvme_command c = { }; + struct nvme_fw_slot_info_log *log; + + log = kmalloc(sizeof(*log), GFP_KERNEL); + if (!log) + return; + + c.common.opcode = nvme_admin_get_log_page; + c.common.nsid = cpu_to_le32(NVME_NSID_ALL); + c.common.cdw10[0] = nvme_get_log_dw10(NVME_LOG_FW_SLOT, sizeof(*log)); + + if (!nvme_submit_sync_cmd(ctrl->admin_q, &c, log, sizeof(*log))) + dev_warn(ctrl->device, + "Get FW SLOT INFO log error\n"); + kfree(log); +} + +static void nvme_fw_act_work(struct work_struct *work) +{ + struct nvme_ctrl *ctrl = container_of(work, + struct nvme_ctrl, fw_act_work); + unsigned long fw_act_timeout; + + if (ctrl->mtfa) + fw_act_timeout = jiffies + + msecs_to_jiffies(ctrl->mtfa * 100); + else + fw_act_timeout = jiffies + + msecs_to_jiffies(admin_timeout * 1000); + + nvme_stop_queues(ctrl); + while (nvme_ctrl_pp_status(ctrl)) { + if (time_after(jiffies, fw_act_timeout)) { + dev_warn(ctrl->device, + "Fw activation timeout, reset controller\n"); + nvme_reset_ctrl(ctrl); + break; + } + msleep(100); + } + + if (ctrl->state != NVME_CTRL_LIVE) + return; + + nvme_start_queues(ctrl); + /* read FW slot informationi to clear the AER*/ + nvme_get_fw_slot_info(ctrl); +} + void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, union nvme_result *res) { @@ -2286,7 +2675,8 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, /*FALLTHRU*/ case NVME_SC_ABORT_REQ: ++ctrl->event_limit; - schedule_work(&ctrl->async_event_work); + if (ctrl->state == NVME_CTRL_LIVE) + queue_work(nvme_wq, &ctrl->async_event_work); break; default: break; @@ -2300,6 +2690,9 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, dev_info(ctrl->device, "rescanning\n"); nvme_queue_scan(ctrl); break; + case NVME_AER_NOTICE_FW_ACT_STARTING: + queue_work(nvme_wq, &ctrl->fw_act_work); + break; default: dev_warn(ctrl->device, "async event result %08x\n", result); } @@ -2309,7 +2702,7 @@ EXPORT_SYMBOL_GPL(nvme_complete_async_event); void nvme_queue_async_events(struct nvme_ctrl *ctrl) { ctrl->event_limit = NVME_NR_AERS; - schedule_work(&ctrl->async_event_work); + queue_work(nvme_wq, &ctrl->async_event_work); } EXPORT_SYMBOL_GPL(nvme_queue_async_events); @@ -2342,12 +2735,30 @@ static void nvme_release_instance(struct nvme_ctrl *ctrl) spin_unlock(&dev_list_lock); } -void nvme_uninit_ctrl(struct nvme_ctrl *ctrl) +void nvme_stop_ctrl(struct nvme_ctrl *ctrl) { + nvme_stop_keep_alive(ctrl); flush_work(&ctrl->async_event_work); flush_work(&ctrl->scan_work); - nvme_remove_namespaces(ctrl); + cancel_work_sync(&ctrl->fw_act_work); +} +EXPORT_SYMBOL_GPL(nvme_stop_ctrl); + +void nvme_start_ctrl(struct nvme_ctrl *ctrl) +{ + if (ctrl->kato) + nvme_start_keep_alive(ctrl); + + if (ctrl->queue_count > 1) { + nvme_queue_scan(ctrl); + nvme_queue_async_events(ctrl); + nvme_start_queues(ctrl); + } +} +EXPORT_SYMBOL_GPL(nvme_start_ctrl); +void nvme_uninit_ctrl(struct nvme_ctrl *ctrl) +{ device_destroy(nvme_class, MKDEV(nvme_char_major, ctrl->instance)); spin_lock(&dev_list_lock); @@ -2393,6 +2804,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, ctrl->quirks = quirks; INIT_WORK(&ctrl->scan_work, nvme_scan_work); INIT_WORK(&ctrl->async_event_work, nvme_async_event_work); + INIT_WORK(&ctrl->fw_act_work, nvme_fw_act_work); ret = nvme_set_instance(ctrl); if (ret) @@ -2442,8 +2854,9 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl) mutex_lock(&ctrl->namespaces_mutex); - /* Forcibly start all queues to avoid having stuck requests */ - blk_mq_start_hw_queues(ctrl->admin_q); + /* Forcibly unquiesce queues to avoid blocking dispatch */ + if (ctrl->admin_q) + blk_mq_unquiesce_queue(ctrl->admin_q); list_for_each_entry(ns, &ctrl->namespaces, list) { /* @@ -2455,15 +2868,8 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl) revalidate_disk(ns->disk); blk_set_queue_dying(ns->queue); - /* - * Forcibly start all queues to avoid having stuck requests. - * Note that we must ensure the queues are not stopped - * when the final removal happens. - */ - blk_mq_start_hw_queues(ns->queue); - - /* draining requests in requeue list */ - blk_mq_kick_requeue_list(ns->queue); + /* Forcibly unquiesce queues to avoid blocking dispatch */ + blk_mq_unquiesce_queue(ns->queue); } mutex_unlock(&ctrl->namespaces_mutex); } @@ -2532,10 +2938,8 @@ void nvme_start_queues(struct nvme_ctrl *ctrl) struct nvme_ns *ns; mutex_lock(&ctrl->namespaces_mutex); - list_for_each_entry(ns, &ctrl->namespaces, list) { - blk_mq_start_stopped_hw_queues(ns->queue, true); - blk_mq_kick_requeue_list(ns->queue); - } + list_for_each_entry(ns, &ctrl->namespaces, list) + blk_mq_unquiesce_queue(ns->queue); mutex_unlock(&ctrl->namespaces_mutex); } EXPORT_SYMBOL_GPL(nvme_start_queues); @@ -2544,10 +2948,15 @@ int __init nvme_core_init(void) { int result; + nvme_wq = alloc_workqueue("nvme-wq", + WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0); + if (!nvme_wq) + return -ENOMEM; + result = __register_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme", &nvme_dev_fops); if (result < 0) - return result; + goto destroy_wq; else if (result > 0) nvme_char_major = result; @@ -2559,8 +2968,10 @@ int __init nvme_core_init(void) return 0; - unregister_chrdev: +unregister_chrdev: __unregister_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme"); +destroy_wq: + destroy_workqueue(nvme_wq); return result; } @@ -2568,6 +2979,7 @@ void nvme_core_exit(void) { class_destroy(nvme_class); __unregister_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme"); + destroy_workqueue(nvme_wq); } MODULE_LICENSE("GPL"); |