diff options
Diffstat (limited to 'drivers/nvme/host/core.c')
| -rw-r--r-- | drivers/nvme/host/core.c | 5766 |
1 files changed, 4186 insertions, 1580 deletions
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index c49f1f8b2e57..7bf228df6001 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1,46 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 /* * NVM Express device driver * Copyright (c) 2011-2014, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. */ +#include <linux/async.h> #include <linux/blkdev.h> #include <linux/blk-mq.h> +#include <linux/blk-integrity.h> +#include <linux/compat.h> #include <linux/delay.h> #include <linux/errno.h> #include <linux/hdreg.h> #include <linux/kernel.h> #include <linux/module.h> -#include <linux/list_sort.h> +#include <linux/backing-dev.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/pr.h> #include <linux/ptrace.h> #include <linux/nvme_ioctl.h> -#include <linux/t10-pi.h> #include <linux/pm_qos.h> -#include <asm/unaligned.h> +#include <linux/ratelimit.h> +#include <linux/unaligned.h> #include "nvme.h" #include "fabrics.h" +#include <linux/nvme-auth.h> + +#define CREATE_TRACE_POINTS +#include "trace.h" #define NVME_MINORS (1U << MINORBITS) -unsigned char admin_timeout = 60; -module_param(admin_timeout, byte, 0644); +struct nvme_ns_info { + struct nvme_ns_ids ids; + u32 nsid; + __le32 anagrpid; + u8 pi_offset; + u16 endgid; + u64 runs; + bool is_shared; + bool is_readonly; + bool is_ready; + bool is_removed; + bool is_rotational; + bool no_vwc; +}; + +unsigned int admin_timeout = 60; +module_param(admin_timeout, uint, 0644); MODULE_PARM_DESC(admin_timeout, "timeout in seconds for admin commands"); EXPORT_SYMBOL_GPL(admin_timeout); -unsigned char nvme_io_timeout = 30; -module_param_named(io_timeout, nvme_io_timeout, byte, 0644); +unsigned int nvme_io_timeout = 30; +module_param_named(io_timeout, nvme_io_timeout, uint, 0644); MODULE_PARM_DESC(io_timeout, "timeout in seconds for I/O"); EXPORT_SYMBOL_GPL(nvme_io_timeout); @@ -52,9 +66,6 @@ static u8 nvme_max_retries = 5; module_param_named(max_retries, nvme_max_retries, byte, 0644); MODULE_PARM_DESC(max_retries, "max number of retries a command may have"); -static int nvme_char_major; -module_param(nvme_char_major, int, 0); - static unsigned long default_ps_max_latency_us = 100000; module_param(default_ps_max_latency_us, ulong, 0644); MODULE_PARM_DESC(default_ps_max_latency_us, @@ -64,117 +75,501 @@ 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"); +static unsigned long apst_primary_timeout_ms = 100; +module_param(apst_primary_timeout_ms, ulong, 0644); +MODULE_PARM_DESC(apst_primary_timeout_ms, + "primary APST timeout in ms"); + +static unsigned long apst_secondary_timeout_ms = 2000; +module_param(apst_secondary_timeout_ms, ulong, 0644); +MODULE_PARM_DESC(apst_secondary_timeout_ms, + "secondary APST timeout in ms"); +static unsigned long apst_primary_latency_tol_us = 15000; +module_param(apst_primary_latency_tol_us, ulong, 0644); +MODULE_PARM_DESC(apst_primary_latency_tol_us, + "primary APST latency tolerance in us"); + +static unsigned long apst_secondary_latency_tol_us = 100000; +module_param(apst_secondary_latency_tol_us, ulong, 0644); +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 + * + * nvme_wq will host works such as scan, aen handling, fw activation, + * keep-alive, periodic reconnects etc. nvme_reset_wq + * runs reset works which also flush works hosted on nvme_wq for + * serialization purposes. nvme_delete_wq host controller deletion + * works which flush reset works for serialization. + */ struct workqueue_struct *nvme_wq; EXPORT_SYMBOL_GPL(nvme_wq); -static LIST_HEAD(nvme_ctrl_list); -static DEFINE_SPINLOCK(dev_list_lock); +struct workqueue_struct *nvme_reset_wq; +EXPORT_SYMBOL_GPL(nvme_reset_wq); + +struct workqueue_struct *nvme_delete_wq; +EXPORT_SYMBOL_GPL(nvme_delete_wq); + +static LIST_HEAD(nvme_subsystems); +DEFINE_MUTEX(nvme_subsystems_lock); + +static DEFINE_IDA(nvme_instance_ida); +static dev_t nvme_ctrl_base_chr_devt; +static int nvme_class_uevent(const struct device *dev, struct kobj_uevent_env *env); +static const struct class nvme_class = { + .name = "nvme", + .dev_uevent = nvme_class_uevent, +}; + +static const struct class nvme_subsys_class = { + .name = "nvme-subsystem", +}; + +static DEFINE_IDA(nvme_ns_chr_minor_ida); +static dev_t nvme_ns_chr_devt; +static const struct class nvme_ns_chr_class = { + .name = "nvme-generic", +}; + +static void nvme_put_subsystem(struct nvme_subsystem *subsys); +static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl, + unsigned nsid); +static void nvme_update_keep_alive(struct nvme_ctrl *ctrl, + struct nvme_command *cmd); +static int nvme_get_log_lsi(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, + u8 lsp, u8 csi, void *log, size_t size, u64 offset, u16 lsi); + +void nvme_queue_scan(struct nvme_ctrl *ctrl) +{ + /* + * Only new queue scan work when admin and IO queues are both alive + */ + if (nvme_ctrl_state(ctrl) == NVME_CTRL_LIVE && ctrl->tagset) + queue_work(nvme_wq, &ctrl->scan_work); +} + +/* + * Use this function to proceed with scheduling reset_work for a controller + * that had previously been set to the resetting state. This is intended for + * code paths that can't be interrupted by other reset attempts. A hot removal + * may prevent this from succeeding. + */ +int nvme_try_sched_reset(struct nvme_ctrl *ctrl) +{ + if (nvme_ctrl_state(ctrl) != NVME_CTRL_RESETTING) + return -EBUSY; + if (!queue_work(nvme_reset_wq, &ctrl->reset_work)) + return -EBUSY; + return 0; +} +EXPORT_SYMBOL_GPL(nvme_try_sched_reset); + +static void nvme_failfast_work(struct work_struct *work) +{ + struct nvme_ctrl *ctrl = container_of(to_delayed_work(work), + struct nvme_ctrl, failfast_work); + + if (nvme_ctrl_state(ctrl) != NVME_CTRL_CONNECTING) + return; + + set_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags); + dev_info(ctrl->device, "failfast expired\n"); + nvme_kick_requeue_lists(ctrl); +} + +static inline void nvme_start_failfast_work(struct nvme_ctrl *ctrl) +{ + if (!ctrl->opts || ctrl->opts->fast_io_fail_tmo == -1) + return; + + schedule_delayed_work(&ctrl->failfast_work, + ctrl->opts->fast_io_fail_tmo * HZ); +} + +static inline void nvme_stop_failfast_work(struct nvme_ctrl *ctrl) +{ + if (!ctrl->opts) + return; + + cancel_delayed_work_sync(&ctrl->failfast_work); + clear_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags); +} -static struct class *nvme_class; 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)) + if (!queue_work(nvme_reset_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 nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl) { int ret; ret = nvme_reset_ctrl(ctrl); - if (!ret) + if (!ret) { flush_work(&ctrl->reset_work); + if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE) + ret = -ENETRESET; + } + return ret; } -static blk_status_t nvme_error_status(struct request *req) +static void nvme_do_delete_ctrl(struct nvme_ctrl *ctrl) +{ + dev_info(ctrl->device, + "Removing ctrl: NQN \"%s\"\n", nvmf_ctrl_subsysnqn(ctrl)); + + flush_work(&ctrl->reset_work); + nvme_stop_ctrl(ctrl); + nvme_remove_namespaces(ctrl); + ctrl->ops->delete_ctrl(ctrl); + nvme_uninit_ctrl(ctrl); +} + +static void nvme_delete_ctrl_work(struct work_struct *work) +{ + struct nvme_ctrl *ctrl = + container_of(work, struct nvme_ctrl, delete_work); + + nvme_do_delete_ctrl(ctrl); +} + +int nvme_delete_ctrl(struct nvme_ctrl *ctrl) { - switch (nvme_req(req)->status & 0x7ff) { + if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_DELETING)) + return -EBUSY; + if (!queue_work(nvme_delete_wq, &ctrl->delete_work)) + return -EBUSY; + return 0; +} +EXPORT_SYMBOL_GPL(nvme_delete_ctrl); + +void nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl) +{ + /* + * Keep a reference until nvme_do_delete_ctrl() complete, + * since ->delete_ctrl can free the controller. + */ + nvme_get_ctrl(ctrl); + if (nvme_change_ctrl_state(ctrl, NVME_CTRL_DELETING)) + nvme_do_delete_ctrl(ctrl); + nvme_put_ctrl(ctrl); +} + +static blk_status_t nvme_error_status(u16 status) +{ + switch (status & NVME_SCT_SC_MASK) { case NVME_SC_SUCCESS: return BLK_STS_OK; case NVME_SC_CAP_EXCEEDED: return BLK_STS_NOSPC; - case NVME_SC_ONCS_NOT_SUPPORTED: + case NVME_SC_LBA_RANGE: + case NVME_SC_CMD_INTERRUPTED: + case NVME_SC_NS_NOT_READY: + return BLK_STS_TARGET; + case NVME_SC_BAD_ATTRIBUTES: + case NVME_SC_INVALID_OPCODE: + case NVME_SC_INVALID_FIELD: + case NVME_SC_INVALID_NS: return BLK_STS_NOTSUPP; case NVME_SC_WRITE_FAULT: case NVME_SC_READ_ERROR: case NVME_SC_UNWRITTEN_BLOCK: + case NVME_SC_ACCESS_DENIED: + case NVME_SC_READ_ONLY: + case NVME_SC_COMPARE_FAILED: 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_RESV_CONFLICT; + case NVME_SC_HOST_PATH_ERROR: + return BLK_STS_TRANSPORT; + case NVME_SC_ZONE_TOO_MANY_ACTIVE: + return BLK_STS_ZONE_ACTIVE_RESOURCE; + case NVME_SC_ZONE_TOO_MANY_OPEN: + return BLK_STS_ZONE_OPEN_RESOURCE; default: return BLK_STS_IOERR; } } -static inline bool nvme_req_needs_retry(struct request *req) +static void nvme_retry_req(struct request *req) { - if (blk_noretry_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; + unsigned long delay = 0; + u16 crd; + + /* The mask and shift result must be <= 3 */ + crd = (nvme_req(req)->status & NVME_STATUS_CRD) >> 11; + if (crd) + delay = nvme_req(req)->ctrl->crdt[crd - 1] * 100; + + nvme_req(req)->retries++; + blk_mq_requeue_request(req, false); + blk_mq_delay_kick_requeue_list(req->q, delay); } -void nvme_complete_rq(struct request *req) +static void nvme_log_error(struct request *req) { - if (unlikely(nvme_req(req)->status && nvme_req_needs_retry(req))) { - nvme_req(req)->retries++; - blk_mq_requeue_request(req, true); + struct nvme_ns *ns = req->q->queuedata; + struct nvme_request *nr = nvme_req(req); + + if (ns) { + pr_err_ratelimited("%s: %s(0x%x) @ LBA %llu, %u blocks, %s (sct 0x%x / sc 0x%x) %s%s\n", + ns->disk ? ns->disk->disk_name : "?", + nvme_get_opcode_str(nr->cmd->common.opcode), + nr->cmd->common.opcode, + nvme_sect_to_lba(ns->head, blk_rq_pos(req)), + blk_rq_bytes(req) >> ns->head->lba_shift, + nvme_get_error_status_str(nr->status), + NVME_SCT(nr->status), /* Status Code Type */ + nr->status & NVME_SC_MASK, /* Status Code */ + nr->status & NVME_STATUS_MORE ? "MORE " : "", + nr->status & NVME_STATUS_DNR ? "DNR " : ""); return; } - blk_mq_end_request(req, nvme_error_status(req)); + pr_err_ratelimited("%s: %s(0x%x), %s (sct 0x%x / sc 0x%x) %s%s\n", + dev_name(nr->ctrl->device), + nvme_get_admin_opcode_str(nr->cmd->common.opcode), + nr->cmd->common.opcode, + nvme_get_error_status_str(nr->status), + NVME_SCT(nr->status), /* Status Code Type */ + nr->status & NVME_SC_MASK, /* Status Code */ + nr->status & NVME_STATUS_MORE ? "MORE " : "", + nr->status & NVME_STATUS_DNR ? "DNR " : ""); } -EXPORT_SYMBOL_GPL(nvme_complete_rq); -void nvme_cancel_request(struct request *req, void *data, bool reserved) +static void nvme_log_err_passthru(struct request *req) { - int status; + struct nvme_ns *ns = req->q->queuedata; + struct nvme_request *nr = nvme_req(req); + + pr_err_ratelimited("%s: %s(0x%x), %s (sct 0x%x / sc 0x%x) %s%s" + "cdw10=0x%x cdw11=0x%x cdw12=0x%x cdw13=0x%x cdw14=0x%x cdw15=0x%x\n", + ns ? ns->disk->disk_name : dev_name(nr->ctrl->device), + ns ? nvme_get_opcode_str(nr->cmd->common.opcode) : + nvme_get_admin_opcode_str(nr->cmd->common.opcode), + nr->cmd->common.opcode, + nvme_get_error_status_str(nr->status), + NVME_SCT(nr->status), /* Status Code Type */ + nr->status & NVME_SC_MASK, /* Status Code */ + nr->status & NVME_STATUS_MORE ? "MORE " : "", + nr->status & NVME_STATUS_DNR ? "DNR " : "", + le32_to_cpu(nr->cmd->common.cdw10), + le32_to_cpu(nr->cmd->common.cdw11), + le32_to_cpu(nr->cmd->common.cdw12), + le32_to_cpu(nr->cmd->common.cdw13), + le32_to_cpu(nr->cmd->common.cdw14), + le32_to_cpu(nr->cmd->common.cdw15)); +} + +enum nvme_disposition { + COMPLETE, + RETRY, + FAILOVER, + AUTHENTICATE, +}; + +static inline enum nvme_disposition nvme_decide_disposition(struct request *req) +{ + if (likely(nvme_req(req)->status == 0)) + return COMPLETE; + + if (blk_noretry_request(req) || + (nvme_req(req)->status & NVME_STATUS_DNR) || + nvme_req(req)->retries >= nvme_max_retries) + return COMPLETE; + + if ((nvme_req(req)->status & NVME_SCT_SC_MASK) == NVME_SC_AUTH_REQUIRED) + return AUTHENTICATE; + + if (req->cmd_flags & REQ_NVME_MPATH) { + if (nvme_is_path_error(nvme_req(req)->status) || + blk_queue_dying(req->q)) + return FAILOVER; + } else { + if (blk_queue_dying(req->q)) + return COMPLETE; + } + + return RETRY; +} + +static inline void nvme_end_req_zoned(struct request *req) +{ + if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && + req_op(req) == REQ_OP_ZONE_APPEND) { + struct nvme_ns *ns = req->q->queuedata; + + req->__sector = nvme_lba_to_sect(ns->head, + le64_to_cpu(nvme_req(req)->result.u64)); + } +} + +static inline void __nvme_end_req(struct request *req) +{ + if (unlikely(nvme_req(req)->status && !(req->rq_flags & RQF_QUIET))) { + if (blk_rq_is_passthrough(req)) + nvme_log_err_passthru(req); + else + nvme_log_error(req); + } + nvme_end_req_zoned(req); + nvme_trace_bio_complete(req); + if (req->cmd_flags & REQ_NVME_MPATH) + nvme_mpath_end_request(req); +} + +void nvme_end_req(struct request *req) +{ + blk_status_t status = nvme_error_status(nvme_req(req)->status); + + __nvme_end_req(req); + blk_mq_end_request(req, status); +} + +void nvme_complete_rq(struct request *req) +{ + struct nvme_ctrl *ctrl = nvme_req(req)->ctrl; + + trace_nvme_complete_rq(req); + nvme_cleanup_cmd(req); + + /* + * Completions of long-running commands should not be able to + * defer sending of periodic keep alives, since the controller + * may have completed processing such commands a long time ago + * (arbitrarily close to command submission time). + * req->deadline - req->timeout is the command submission time + * in jiffies. + */ + if (ctrl->kas && + req->deadline - req->timeout >= ctrl->ka_last_check_time) + ctrl->comp_seen = true; - if (!blk_mq_request_started(req)) + switch (nvme_decide_disposition(req)) { + case COMPLETE: + nvme_end_req(req); return; + case RETRY: + nvme_retry_req(req); + return; + case FAILOVER: + nvme_failover_req(req); + return; + case AUTHENTICATE: +#ifdef CONFIG_NVME_HOST_AUTH + queue_work(nvme_wq, &ctrl->dhchap_auth_work); + nvme_retry_req(req); +#else + nvme_end_req(req); +#endif + return; + } +} +EXPORT_SYMBOL_GPL(nvme_complete_rq); + +void nvme_complete_batch_req(struct request *req) +{ + trace_nvme_complete_rq(req); + nvme_cleanup_cmd(req); + __nvme_end_req(req); +} +EXPORT_SYMBOL_GPL(nvme_complete_batch_req); +/* + * Called to unwind from ->queue_rq on a failed command submission so that the + * multipathing code gets called to potentially failover to another path. + * The caller needs to unwind all transport specific resource allocations and + * must return propagate the return value. + */ +blk_status_t nvme_host_path_error(struct request *req) +{ + nvme_req(req)->status = NVME_SC_HOST_PATH_ERROR; + blk_mq_set_request_complete(req); + nvme_complete_rq(req); + return BLK_STS_OK; +} +EXPORT_SYMBOL_GPL(nvme_host_path_error); + +bool nvme_cancel_request(struct request *req, void *data) +{ dev_dbg_ratelimited(((struct nvme_ctrl *) data)->device, "Cancelling I/O %d", req->tag); - status = NVME_SC_ABORT_REQ; - if (blk_queue_dying(req->q)) - status |= NVME_SC_DNR; - nvme_req(req)->status = status; - blk_mq_complete_request(req); + /* don't abort one completed or idle request */ + if (blk_mq_rq_state(req) != MQ_RQ_IN_FLIGHT) + return true; + nvme_req(req)->status = NVME_SC_HOST_ABORTED_CMD; + nvme_req(req)->flags |= NVME_REQ_CANCELLED; + blk_mq_complete_request(req); + return true; } EXPORT_SYMBOL_GPL(nvme_cancel_request); +void nvme_cancel_tagset(struct nvme_ctrl *ctrl) +{ + if (ctrl->tagset) { + blk_mq_tagset_busy_iter(ctrl->tagset, + nvme_cancel_request, ctrl); + blk_mq_tagset_wait_completed_request(ctrl->tagset); + } +} +EXPORT_SYMBOL_GPL(nvme_cancel_tagset); + +void nvme_cancel_admin_tagset(struct nvme_ctrl *ctrl) +{ + if (ctrl->admin_tagset) { + blk_mq_tagset_busy_iter(ctrl->admin_tagset, + nvme_cancel_request, ctrl); + blk_mq_tagset_wait_completed_request(ctrl->admin_tagset); + } +} +EXPORT_SYMBOL_GPL(nvme_cancel_admin_tagset); + 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; + old_state = nvme_ctrl_state(ctrl); switch (new_state) { case NVME_CTRL_LIVE: switch (old_state) { - case NVME_CTRL_NEW: - case NVME_CTRL_RESETTING: - case NVME_CTRL_RECONNECTING: + case NVME_CTRL_CONNECTING: changed = true; - /* FALLTHRU */ + fallthrough; default: break; } @@ -184,16 +579,17 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, case NVME_CTRL_NEW: case NVME_CTRL_LIVE: changed = true; - /* FALLTHRU */ + fallthrough; default: break; } break; - case NVME_CTRL_RECONNECTING: + case NVME_CTRL_CONNECTING: switch (old_state) { - case NVME_CTRL_LIVE: + case NVME_CTRL_NEW: + case NVME_CTRL_RESETTING: changed = true; - /* FALLTHRU */ + fallthrough; default: break; } @@ -202,9 +598,19 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, switch (old_state) { case NVME_CTRL_LIVE: case NVME_CTRL_RESETTING: - case NVME_CTRL_RECONNECTING: + case NVME_CTRL_CONNECTING: + changed = true; + fallthrough; + default: + break; + } + break; + case NVME_CTRL_DELETING_NOIO: + switch (old_state) { + case NVME_CTRL_DELETING: + case NVME_CTRL_DEAD: changed = true; - /* FALLTHRU */ + fallthrough; default: break; } @@ -213,7 +619,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, switch (old_state) { case NVME_CTRL_DELETING: changed = true; - /* FALLTHRU */ + fallthrough; default: break; } @@ -222,189 +628,197 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, break; } - if (changed) - ctrl->state = new_state; + if (changed) { + WRITE_ONCE(ctrl->state, new_state); + wake_up_all(&ctrl->state_wq); + } - spin_unlock_irq(&ctrl->lock); + spin_unlock_irqrestore(&ctrl->lock, flags); + if (!changed) + return false; + if (new_state == NVME_CTRL_LIVE) { + if (old_state == NVME_CTRL_CONNECTING) + nvme_stop_failfast_work(ctrl); + nvme_kick_requeue_lists(ctrl); + } else if (new_state == NVME_CTRL_CONNECTING && + old_state == NVME_CTRL_RESETTING) { + nvme_start_failfast_work(ctrl); + } return changed; } EXPORT_SYMBOL_GPL(nvme_change_ctrl_state); -static void nvme_free_ns(struct kref *kref) +/* + * Waits for the controller state to be resetting, or returns false if it is + * not possible to ever transition to that state. + */ +bool nvme_wait_reset(struct nvme_ctrl *ctrl) { - struct nvme_ns *ns = container_of(kref, struct nvme_ns, kref); - - if (ns->ndev) - nvme_nvm_unregister(ns); - - if (ns->disk) { - spin_lock(&dev_list_lock); - ns->disk->private_data = NULL; - spin_unlock(&dev_list_lock); - } - - put_disk(ns->disk); - ida_simple_remove(&ns->ctrl->ns_ida, ns->instance); - nvme_put_ctrl(ns->ctrl); - kfree(ns); + wait_event(ctrl->state_wq, + nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING) || + nvme_state_terminal(ctrl)); + return nvme_ctrl_state(ctrl) == NVME_CTRL_RESETTING; } +EXPORT_SYMBOL_GPL(nvme_wait_reset); -static void nvme_put_ns(struct nvme_ns *ns) +static void nvme_free_ns_head(struct kref *ref) { - kref_put(&ns->kref, nvme_free_ns); + struct nvme_ns_head *head = + container_of(ref, struct nvme_ns_head, ref); + + nvme_mpath_put_disk(head); + ida_free(&head->subsys->ns_ida, head->instance); + cleanup_srcu_struct(&head->srcu); + nvme_put_subsystem(head->subsys); + kfree(head->plids); + kfree(head); } -static struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk) +bool nvme_tryget_ns_head(struct nvme_ns_head *head) { - struct nvme_ns *ns; - - spin_lock(&dev_list_lock); - ns = disk->private_data; - if (ns) { - if (!kref_get_unless_zero(&ns->kref)) - goto fail; - if (!try_module_get(ns->ctrl->ops->module)) - goto fail_put_ns; - } - spin_unlock(&dev_list_lock); - - return ns; - -fail_put_ns: - kref_put(&ns->kref, nvme_free_ns); -fail: - spin_unlock(&dev_list_lock); - return NULL; + return kref_get_unless_zero(&head->ref); } -struct request *nvme_alloc_request(struct request_queue *q, - struct nvme_command *cmd, unsigned int flags, int qid) +void nvme_put_ns_head(struct nvme_ns_head *head) { - unsigned op = nvme_is_write(cmd) ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN; - struct request *req; - - if (qid == NVME_QID_ANY) { - req = blk_mq_alloc_request(q, op, flags); - } else { - req = blk_mq_alloc_request_hctx(q, op, flags, - qid ? qid - 1 : 0); - } - if (IS_ERR(req)) - return req; - - req->cmd_flags |= REQ_FAILFAST_DRIVER; - nvme_req(req)->cmd = cmd; - - return req; + kref_put(&head->ref, nvme_free_ns_head); } -EXPORT_SYMBOL_GPL(nvme_alloc_request); -static int nvme_toggle_streams(struct nvme_ctrl *ctrl, bool enable) +static void nvme_free_ns(struct kref *kref) { - struct nvme_command c; - - memset(&c, 0, sizeof(c)); - - c.directive.opcode = nvme_admin_directive_send; - c.directive.nsid = cpu_to_le32(0xffffffff); - 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; + struct nvme_ns *ns = container_of(kref, struct nvme_ns, kref); - return nvme_submit_sync_cmd(ctrl->admin_q, &c, NULL, 0); + put_disk(ns->disk); + nvme_put_ns_head(ns->head); + nvme_put_ctrl(ns->ctrl); + kfree(ns); } -static int nvme_disable_streams(struct nvme_ctrl *ctrl) +bool nvme_get_ns(struct nvme_ns *ns) { - return nvme_toggle_streams(ctrl, false); + return kref_get_unless_zero(&ns->kref); } -static int nvme_enable_streams(struct nvme_ctrl *ctrl) +void nvme_put_ns(struct nvme_ns *ns) { - return nvme_toggle_streams(ctrl, true); + kref_put(&ns->kref, nvme_free_ns); } +EXPORT_SYMBOL_NS_GPL(nvme_put_ns, "NVME_TARGET_PASSTHRU"); -static int nvme_get_stream_params(struct nvme_ctrl *ctrl, - struct streams_directive_params *s, u32 nsid) +static inline void nvme_clear_nvme_request(struct request *req) { - 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)); - 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)); + nvme_req(req)->status = 0; + nvme_req(req)->retries = 0; + nvme_req(req)->flags = 0; + req->rq_flags |= RQF_DONTPREP; } -static int nvme_configure_directives(struct nvme_ctrl *ctrl) +/* initialize a passthrough request */ +void nvme_init_request(struct request *req, struct nvme_command *cmd) { - struct streams_directive_params s; - int ret; + struct nvme_request *nr = nvme_req(req); + bool logging_enabled; - if (!(ctrl->oacs & NVME_CTRL_OACS_DIRECTIVES)) - return 0; - if (!streams) - return 0; + if (req->q->queuedata) { + struct nvme_ns *ns = req->q->disk->private_data; - ret = nvme_enable_streams(ctrl); - if (ret) - return ret; + logging_enabled = ns->head->passthru_err_log_enabled; + req->timeout = NVME_IO_TIMEOUT; + } else { /* no queuedata implies admin queue */ + logging_enabled = nr->ctrl->passthru_err_log_enabled; + req->timeout = NVME_ADMIN_TIMEOUT; + } - ret = nvme_get_stream_params(ctrl, &s, 0xffffffff); - if (ret) - return ret; + if (!logging_enabled) + req->rq_flags |= RQF_QUIET; - 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; - } + /* passthru commands should let the driver set the SGL flags */ + cmd->common.flags &= ~NVME_CMD_SGL_ALL; - 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; + req->cmd_flags |= REQ_FAILFAST_DRIVER; + if (req->mq_hctx->type == HCTX_TYPE_POLL) + req->cmd_flags |= REQ_POLLED; + nvme_clear_nvme_request(req); + memcpy(nr->cmd, cmd, sizeof(*cmd)); } +EXPORT_SYMBOL_GPL(nvme_init_request); /* - * Check if 'req' has a write hint associated with it. If it does, assign - * a valid namespace stream to the write. + * For something we're not in a state to send to the device the default action + * is to busy it and retry it after the controller state is recovered. However, + * if the controller is deleting or if anything is marked for failfast or + * nvme multipath it is immediately failed. + * + * Note: commands used to initialize the controller will be marked for failfast. + * Note: nvme cli/ioctl commands are marked for failfast. */ -static void nvme_assign_write_stream(struct nvme_ctrl *ctrl, - struct request *req, u16 *control, - u32 *dsmgmt) +blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl, + struct request *rq) { - enum rw_hint streamid = req->write_hint; + enum nvme_ctrl_state state = nvme_ctrl_state(ctrl); - if (streamid == WRITE_LIFE_NOT_SET || streamid == WRITE_LIFE_NONE) - streamid = 0; - else { - streamid--; - if (WARN_ON_ONCE(streamid > ctrl->nr_streams)) - return; + if (state != NVME_CTRL_DELETING_NOIO && + state != NVME_CTRL_DELETING && + state != NVME_CTRL_DEAD && + !test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags) && + !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH)) + return BLK_STS_RESOURCE; + + if (!(rq->rq_flags & RQF_DONTPREP)) + nvme_clear_nvme_request(rq); + + return nvme_host_path_error(rq); +} +EXPORT_SYMBOL_GPL(nvme_fail_nonready_command); + +bool __nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq, + bool queue_live, enum nvme_ctrl_state state) +{ + struct nvme_request *req = nvme_req(rq); + + /* + * currently we have a problem sending passthru commands + * on the admin_q if the controller is not LIVE because we can't + * make sure that they are going out after the admin connect, + * controller enable and/or other commands in the initialization + * sequence. until the controller will be LIVE, fail with + * BLK_STS_RESOURCE so that they will be rescheduled. + */ + if (rq->q == ctrl->admin_q && (req->flags & NVME_REQ_USERCMD)) + return false; - *control |= NVME_RW_DTYPE_STREAMS; - *dsmgmt |= streamid << 16; + if (ctrl->ops->flags & NVME_F_FABRICS) { + /* + * Only allow commands on a live queue, except for the connect + * command, which is require to set the queue live in the + * appropinquate states. + */ + switch (state) { + case NVME_CTRL_CONNECTING: + if (blk_rq_is_passthrough(rq) && nvme_is_fabrics(req->cmd) && + (req->cmd->fabrics.fctype == nvme_fabrics_type_connect || + req->cmd->fabrics.fctype == nvme_fabrics_type_auth_send || + req->cmd->fabrics.fctype == nvme_fabrics_type_auth_receive)) + return true; + break; + default: + break; + case NVME_CTRL_DEAD: + return false; + } } - if (streamid < ARRAY_SIZE(req->q->write_hints)) - req->q->write_hints[streamid] += blk_rq_bytes(req) >> 9; + return queue_live; } +EXPORT_SYMBOL_GPL(__nvme_check_ready); static inline void nvme_setup_flush(struct nvme_ns *ns, struct nvme_command *cmnd) { memset(cmnd, 0, sizeof(*cmnd)); cmnd->common.opcode = nvme_cmd_flush; - cmnd->common.nsid = cpu_to_le32(ns->ns_id); + cmnd->common.nsid = cpu_to_le32(ns->head->ns_id); } static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req, @@ -414,56 +828,172 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req, struct nvme_dsm_range *range; struct bio *bio; - range = kmalloc_array(segments, sizeof(*range), GFP_ATOMIC); - if (!range) - return BLK_STS_RESOURCE; + /* + * Some devices do not consider the DSM 'Number of Ranges' field when + * determining how much data to DMA. Always allocate memory for maximum + * number of segments to prevent device reading beyond end of buffer. + */ + static const size_t alloc_size = sizeof(*range) * NVME_DSM_MAX_RANGES; - __rq_for_each_bio(bio, req) { - u64 slba = nvme_block_nr(ns, bio->bi_iter.bi_sector); - u32 nlb = bio->bi_iter.bi_size >> ns->lba_shift; + range = kzalloc(alloc_size, GFP_ATOMIC | __GFP_NOWARN); + if (!range) { + /* + * If we fail allocation our range, fallback to the controller + * discard page. If that's also busy, it's safe to return + * busy, as we know we can make progress once that's freed. + */ + if (test_and_set_bit_lock(0, &ns->ctrl->discard_page_busy)) + return BLK_STS_RESOURCE; - range[n].cattr = cpu_to_le32(0); - range[n].nlb = cpu_to_le32(nlb); - range[n].slba = cpu_to_le64(slba); - n++; + range = page_address(ns->ctrl->discard_page); + } + + if (queue_max_discard_segments(req->q) == 1) { + u64 slba = nvme_sect_to_lba(ns->head, blk_rq_pos(req)); + u32 nlb = blk_rq_sectors(req) >> (ns->head->lba_shift - 9); + + range[0].cattr = cpu_to_le32(0); + range[0].nlb = cpu_to_le32(nlb); + range[0].slba = cpu_to_le64(slba); + n = 1; + } else { + __rq_for_each_bio(bio, req) { + u64 slba = nvme_sect_to_lba(ns->head, + bio->bi_iter.bi_sector); + u32 nlb = bio->bi_iter.bi_size >> ns->head->lba_shift; + + if (n < segments) { + range[n].cattr = cpu_to_le32(0); + range[n].nlb = cpu_to_le32(nlb); + range[n].slba = cpu_to_le64(slba); + } + n++; + } } if (WARN_ON_ONCE(n != segments)) { - kfree(range); + if (virt_to_page(range) == ns->ctrl->discard_page) + clear_bit_unlock(0, &ns->ctrl->discard_page_busy); + else + kfree(range); return BLK_STS_IOERR; } memset(cmnd, 0, sizeof(*cmnd)); cmnd->dsm.opcode = nvme_cmd_dsm; - cmnd->dsm.nsid = cpu_to_le32(ns->ns_id); + cmnd->dsm.nsid = cpu_to_le32(ns->head->ns_id); cmnd->dsm.nr = cpu_to_le32(segments - 1); cmnd->dsm.attributes = cpu_to_le32(NVME_DSMGMT_AD); - req->special_vec.bv_page = virt_to_page(range); - req->special_vec.bv_offset = offset_in_page(range); - req->special_vec.bv_len = sizeof(*range) * segments; + bvec_set_virt(&req->special_vec, range, alloc_size); req->rq_flags |= RQF_SPECIAL_PAYLOAD; return BLK_STS_OK; } -static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns, +static void nvme_set_app_tag(struct request *req, struct nvme_command *cmnd) +{ + cmnd->rw.lbat = cpu_to_le16(bio_integrity(req->bio)->app_tag); + cmnd->rw.lbatm = cpu_to_le16(0xffff); +} + +static void nvme_set_ref_tag(struct nvme_ns *ns, struct nvme_command *cmnd, + struct request *req) +{ + u32 upper, lower; + u64 ref48; + + /* only type1 and type 2 PI formats have a reftag */ + switch (ns->head->pi_type) { + case NVME_NS_DPS_PI_TYPE1: + case NVME_NS_DPS_PI_TYPE2: + break; + default: + return; + } + + /* both rw and write zeroes share the same reftag format */ + switch (ns->head->guard_type) { + case NVME_NVM_NS_16B_GUARD: + cmnd->rw.reftag = cpu_to_le32(t10_pi_ref_tag(req)); + break; + case NVME_NVM_NS_64B_GUARD: + ref48 = ext_pi_ref_tag(req); + lower = lower_32_bits(ref48); + upper = upper_32_bits(ref48); + + cmnd->rw.reftag = cpu_to_le32(lower); + cmnd->rw.cdw3 = cpu_to_le32(upper); + break; + default: + break; + } +} + +static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns, struct request *req, struct nvme_command *cmnd) { - struct nvme_ctrl *ctrl = ns->ctrl; + memset(cmnd, 0, sizeof(*cmnd)); + + if (ns->ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES) + return nvme_setup_discard(ns, req, cmnd); + + cmnd->write_zeroes.opcode = nvme_cmd_write_zeroes; + cmnd->write_zeroes.nsid = cpu_to_le32(ns->head->ns_id); + cmnd->write_zeroes.slba = + cpu_to_le64(nvme_sect_to_lba(ns->head, blk_rq_pos(req))); + cmnd->write_zeroes.length = + cpu_to_le16((blk_rq_bytes(req) >> ns->head->lba_shift) - 1); + + if (!(req->cmd_flags & REQ_NOUNMAP) && + (ns->head->features & NVME_NS_DEAC)) + cmnd->write_zeroes.control |= cpu_to_le16(NVME_WZ_DEAC); + + if (nvme_ns_has_pi(ns->head)) { + cmnd->write_zeroes.control |= cpu_to_le16(NVME_RW_PRINFO_PRACT); + nvme_set_ref_tag(ns, cmnd, req); + } + + return BLK_STS_OK; +} + +/* + * NVMe does not support a dedicated command to issue an atomic write. A write + * which does adhere to the device atomic limits will silently be executed + * non-atomically. The request issuer should ensure that the write is within + * the queue atomic writes limits, but just validate this in case it is not. + */ +static bool nvme_valid_atomic_write(struct request *req) +{ + struct request_queue *q = req->q; + u32 boundary_bytes = queue_atomic_write_boundary_bytes(q); + + if (blk_rq_bytes(req) > queue_atomic_write_unit_max_bytes(q)) + return false; + + if (boundary_bytes) { + u64 mask = boundary_bytes - 1, imask = ~mask; + u64 start = blk_rq_pos(req) << SECTOR_SHIFT; + u64 end = start + blk_rq_bytes(req) - 1; + + /* If greater then must be crossing a boundary */ + if (blk_rq_bytes(req) > boundary_bytes) + return false; + + if ((start & imask) != (end & imask)) + return false; + } + + return true; +} + +static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns, + struct request *req, struct nvme_command *cmnd, + enum nvme_opcode op) +{ 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)) @@ -472,30 +1002,61 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns, if (req->cmd_flags & REQ_RAHEAD) dsmgmt |= NVME_RW_DSM_FREQ_PREFETCH; - memset(cmnd, 0, sizeof(*cmnd)); - cmnd->rw.opcode = (rq_data_dir(req) ? nvme_cmd_write : nvme_cmd_read); - cmnd->rw.nsid = cpu_to_le32(ns->ns_id); - 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 (op == nvme_cmd_write && ns->head->nr_plids) { + u16 write_stream = req->bio->bi_write_stream; - if (req_op(req) == REQ_OP_WRITE && ctrl->nr_streams) - nvme_assign_write_stream(ctrl, req, &control, &dsmgmt); + if (WARN_ON_ONCE(write_stream > ns->head->nr_plids)) + return BLK_STS_INVAL; - if (ns->ms) { - switch (ns->pi_type) { - case NVME_NS_DPS_PI_TYPE3: - control |= NVME_RW_PRINFO_PRCHK_GUARD; - break; - case NVME_NS_DPS_PI_TYPE1: - case NVME_NS_DPS_PI_TYPE2: - control |= NVME_RW_PRINFO_PRCHK_GUARD | - NVME_RW_PRINFO_PRCHK_REF; - cmnd->rw.reftag = cpu_to_le32( - nvme_block_nr(ns, blk_rq_pos(req))); - break; + if (write_stream) { + dsmgmt |= ns->head->plids[write_stream - 1] << 16; + control |= NVME_RW_DTYPE_DPLCMT; } - if (!blk_integrity_rq(req)) + } + + if (req->cmd_flags & REQ_ATOMIC && !nvme_valid_atomic_write(req)) + return BLK_STS_INVAL; + + cmnd->rw.opcode = op; + cmnd->rw.flags = 0; + cmnd->rw.nsid = cpu_to_le32(ns->head->ns_id); + cmnd->rw.cdw2 = 0; + cmnd->rw.cdw3 = 0; + cmnd->rw.metadata = 0; + cmnd->rw.slba = + cpu_to_le64(nvme_sect_to_lba(ns->head, blk_rq_pos(req))); + cmnd->rw.length = + cpu_to_le16((blk_rq_bytes(req) >> ns->head->lba_shift) - 1); + cmnd->rw.reftag = 0; + cmnd->rw.lbat = 0; + cmnd->rw.lbatm = 0; + + if (ns->head->ms) { + /* + * If formatted with metadata, the block layer always provides a + * metadata buffer if CONFIG_BLK_DEV_INTEGRITY is enabled. Else + * we enable the PRACT bit for protection information or set the + * namespace capacity to zero to prevent any I/O. + */ + if (!blk_integrity_rq(req)) { + if (WARN_ON_ONCE(!nvme_ns_has_pi(ns->head))) + return BLK_STS_NOTSUPP; control |= NVME_RW_PRINFO_PRACT; + nvme_set_ref_tag(ns, cmnd, req); + } + + if (bio_integrity_flagged(req->bio, BIP_CHECK_GUARD)) + control |= NVME_RW_PRINFO_PRCHK_GUARD; + if (bio_integrity_flagged(req->bio, BIP_CHECK_REFTAG)) { + control |= NVME_RW_PRINFO_PRCHK_REF; + if (op == nvme_cmd_zone_append) + control |= NVME_RW_APPEND_PIREMAP; + nvme_set_ref_tag(ns, cmnd, req); + } + if (bio_integrity_flagged(req->bio, BIP_CHECK_APPTAG)) { + control |= NVME_RW_PRINFO_PRCHK_APP; + nvme_set_app_tag(req, cmnd); + } } cmnd->rw.control = cpu_to_le16(control); @@ -503,74 +1064,131 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns, return 0; } -blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req, - struct nvme_command *cmd) +void nvme_cleanup_cmd(struct request *req) { + if (req->rq_flags & RQF_SPECIAL_PAYLOAD) { + struct nvme_ctrl *ctrl = nvme_req(req)->ctrl; + + if (req->special_vec.bv_page == ctrl->discard_page) + clear_bit_unlock(0, &ctrl->discard_page_busy); + else + kfree(bvec_virt(&req->special_vec)); + req->rq_flags &= ~RQF_SPECIAL_PAYLOAD; + } +} +EXPORT_SYMBOL_GPL(nvme_cleanup_cmd); + +blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req) +{ + struct nvme_command *cmd = nvme_req(req)->cmd; blk_status_t ret = BLK_STS_OK; - if (!(req->rq_flags & RQF_DONTPREP)) { - nvme_req(req)->retries = 0; - nvme_req(req)->flags = 0; - req->rq_flags |= RQF_DONTPREP; - } + if (!(req->rq_flags & RQF_DONTPREP)) + nvme_clear_nvme_request(req); switch (req_op(req)) { case REQ_OP_DRV_IN: case REQ_OP_DRV_OUT: - memcpy(cmd, nvme_req(req)->cmd, sizeof(*cmd)); + /* these are setup prior to execution in nvme_init_request() */ break; case REQ_OP_FLUSH: nvme_setup_flush(ns, cmd); break; + case REQ_OP_ZONE_RESET_ALL: + case REQ_OP_ZONE_RESET: + ret = nvme_setup_zone_mgmt_send(ns, req, cmd, NVME_ZONE_RESET); + break; + case REQ_OP_ZONE_OPEN: + ret = nvme_setup_zone_mgmt_send(ns, req, cmd, NVME_ZONE_OPEN); + break; + case REQ_OP_ZONE_CLOSE: + ret = nvme_setup_zone_mgmt_send(ns, req, cmd, NVME_ZONE_CLOSE); + break; + case REQ_OP_ZONE_FINISH: + ret = nvme_setup_zone_mgmt_send(ns, req, cmd, NVME_ZONE_FINISH); + break; case REQ_OP_WRITE_ZEROES: - /* currently only aliased to deallocate for a few ctrls: */ + ret = nvme_setup_write_zeroes(ns, req, cmd); + break; case REQ_OP_DISCARD: ret = nvme_setup_discard(ns, req, cmd); break; case REQ_OP_READ: + ret = nvme_setup_rw(ns, req, cmd, nvme_cmd_read); + break; case REQ_OP_WRITE: - ret = nvme_setup_rw(ns, req, cmd); + ret = nvme_setup_rw(ns, req, cmd, nvme_cmd_write); + break; + case REQ_OP_ZONE_APPEND: + ret = nvme_setup_rw(ns, req, cmd, nvme_cmd_zone_append); break; default: WARN_ON_ONCE(1); return BLK_STS_IOERR; } - cmd->common.command_id = req->tag; + cmd->common.command_id = nvme_cid(req); + trace_nvme_setup_cmd(req, cmd); return ret; } EXPORT_SYMBOL_GPL(nvme_setup_cmd); /* + * Return values: + * 0: success + * >0: nvme controller's cqe status response + * <0: kernel error in lieu of controller response + */ +int nvme_execute_rq(struct request *rq, bool at_head) +{ + blk_status_t status; + + status = blk_execute_rq(rq, at_head); + if (nvme_req(rq)->flags & NVME_REQ_CANCELLED) + return -EINTR; + if (nvme_req(rq)->status) + return nvme_req(rq)->status; + return blk_status_to_errno(status); +} +EXPORT_SYMBOL_NS_GPL(nvme_execute_rq, "NVME_TARGET_PASSTHRU"); + +/* * 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 */ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, union nvme_result *result, void *buffer, unsigned bufflen, - unsigned timeout, int qid, int at_head, int flags) + int qid, nvme_submit_flags_t flags) { struct request *req; int ret; + blk_mq_req_flags_t blk_flags = 0; + + if (flags & NVME_SUBMIT_NOWAIT) + blk_flags |= BLK_MQ_REQ_NOWAIT; + if (flags & NVME_SUBMIT_RESERVED) + blk_flags |= BLK_MQ_REQ_RESERVED; + if (qid == NVME_QID_ANY) + req = blk_mq_alloc_request(q, nvme_req_op(cmd), blk_flags); + else + req = blk_mq_alloc_request_hctx(q, nvme_req_op(cmd), blk_flags, + qid - 1); - req = nvme_alloc_request(q, cmd, flags, qid); if (IS_ERR(req)) return PTR_ERR(req); - - req->timeout = timeout ? timeout : ADMIN_TIMEOUT; + nvme_init_request(req, cmd); + if (flags & NVME_SUBMIT_RETRY) + req->cmd_flags &= ~REQ_FAILFAST_DRIVER; if (buffer && bufflen) { - ret = blk_rq_map_kern(q, req, buffer, bufflen, GFP_KERNEL); + ret = blk_rq_map_kern(req, buffer, bufflen, GFP_KERNEL); if (ret) goto out; } - blk_execute_rq(req->q, NULL, req, at_head); - if (result) + ret = nvme_execute_rq(req, flags & NVME_SUBMIT_AT_HEAD); + if (result && ret >= 0) *result = nvme_req(req)->result; - if (nvme_req(req)->flags & NVME_REQ_CANCELLED) - ret = -EINTR; - else - ret = nvme_req(req)->status; out: blk_mq_free_request(req); return ret; @@ -580,115 +1198,159 @@ EXPORT_SYMBOL_GPL(__nvme_submit_sync_cmd); int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, void *buffer, unsigned bufflen) { - return __nvme_submit_sync_cmd(q, cmd, NULL, buffer, bufflen, 0, - NVME_QID_ANY, 0, 0); + return __nvme_submit_sync_cmd(q, cmd, NULL, buffer, bufflen, + NVME_QID_ANY, 0); } 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) +u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode) { - bool write = nvme_is_write(cmd); - struct nvme_ns *ns = q->queuedata; - struct gendisk *disk = ns ? ns->disk : NULL; - struct request *req; - struct bio *bio = NULL; - void *meta = NULL; - int ret; - - req = nvme_alloc_request(q, cmd, 0, NVME_QID_ANY); - if (IS_ERR(req)) - return PTR_ERR(req); - - req->timeout = timeout ? timeout : ADMIN_TIMEOUT; + u32 effects = 0; - if (ubuffer && bufflen) { - ret = blk_rq_map_user(q, req, NULL, ubuffer, bufflen, - GFP_KERNEL); - 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 (ns) { + effects = le32_to_cpu(ns->head->effects->iocs[opcode]); + if (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC)) + dev_warn_once(ctrl->device, + "IO command:%02x has unusual effects:%08x\n", + opcode, effects); - if (meta_buffer && meta_len) { - struct bio_integrity_payload *bip; + /* + * NVME_CMD_EFFECTS_CSE_MASK causes a freeze all I/O queues, + * which would deadlock when done on an I/O command. Note that + * We already warn about an unusual effect above. + */ + effects &= ~NVME_CMD_EFFECTS_CSE_MASK; + } else { + effects = le32_to_cpu(ctrl->effects->acs[opcode]); - meta = kmalloc(meta_len, GFP_KERNEL); - if (!meta) { - ret = -ENOMEM; - goto out_unmap; - } + /* Ignore execution restrictions if any relaxation bits are set */ + if (effects & NVME_CMD_EFFECTS_CSER_MASK) + effects &= ~NVME_CMD_EFFECTS_CSE_MASK; + } - if (write) { - if (copy_from_user(meta, meta_buffer, - meta_len)) { - ret = -EFAULT; - goto out_free_meta; - } - } + return effects; +} +EXPORT_SYMBOL_NS_GPL(nvme_command_effects, "NVME_TARGET_PASSTHRU"); - bip = bio_integrity_alloc(bio, GFP_KERNEL, 1); - if (IS_ERR(bip)) { - ret = PTR_ERR(bip); - goto out_free_meta; - } +u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode) +{ + u32 effects = nvme_command_effects(ctrl, ns, opcode); - bip->bip_iter.bi_size = meta_len; - bip->bip_iter.bi_sector = meta_seed; + /* + * For simplicity, IO to all namespaces is quiesced even if the command + * effects say only one namespace is affected. + */ + if (effects & NVME_CMD_EFFECTS_CSE_MASK) { + mutex_lock(&ctrl->scan_lock); + mutex_lock(&ctrl->subsys->lock); + nvme_mpath_start_freeze(ctrl->subsys); + nvme_mpath_wait_freeze(ctrl->subsys); + nvme_start_freeze(ctrl); + nvme_wait_freeze(ctrl); + } + return effects; +} +EXPORT_SYMBOL_NS_GPL(nvme_passthru_start, "NVME_TARGET_PASSTHRU"); - 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; - } +void nvme_passthru_end(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u32 effects, + struct nvme_command *cmd, int status) +{ + if (effects & NVME_CMD_EFFECTS_CSE_MASK) { + nvme_unfreeze(ctrl); + nvme_mpath_unfreeze(ctrl->subsys); + mutex_unlock(&ctrl->subsys->lock); + mutex_unlock(&ctrl->scan_lock); + } + if (effects & NVME_CMD_EFFECTS_CCC) { + if (!test_and_set_bit(NVME_CTRL_DIRTY_CAPABILITY, + &ctrl->flags)) { + dev_info(ctrl->device, +"controller capabilities changed, reset may be required to take effect.\n"); } } - submit: - blk_execute_rq(req->q, disk, req, 0); - if (nvme_req(req)->flags & NVME_REQ_CANCELLED) - ret = -EINTR; - else - ret = nvme_req(req)->status; - if (result) - *result = le32_to_cpu(nvme_req(req)->result.u32); - if (meta && !ret && !write) { - 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); - blk_rq_unmap_user(bio); + if (effects & (NVME_CMD_EFFECTS_NIC | NVME_CMD_EFFECTS_NCC)) { + nvme_queue_scan(ctrl); + flush_work(&ctrl->scan_work); + } + if (ns) + return; + + switch (cmd->common.opcode) { + case nvme_admin_set_features: + switch (le32_to_cpu(cmd->common.cdw10) & 0xFF) { + case NVME_FEAT_KATO: + /* + * Keep alive commands interval on the host should be + * updated when KATO is modified by Set Features + * commands. + */ + if (!status) + nvme_update_keep_alive(ctrl, cmd); + break; + default: + break; + } + break; + default: + break; } - out: - blk_mq_free_request(req); - return ret; } +EXPORT_SYMBOL_NS_GPL(nvme_passthru_end, "NVME_TARGET_PASSTHRU"); -int nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd, - void __user *ubuffer, unsigned bufflen, u32 *result, - unsigned timeout) +/* + * Recommended frequency for KATO commands per NVMe 1.4 section 7.12.1: + * + * The host should send Keep Alive commands at half of the Keep Alive Timeout + * accounting for transport roundtrip times [..]. + */ +static unsigned long nvme_keep_alive_work_period(struct nvme_ctrl *ctrl) +{ + unsigned long delay = ctrl->kato * HZ / 2; + + /* + * When using Traffic Based Keep Alive, we need to run + * nvme_keep_alive_work at twice the normal frequency, as one + * command completion can postpone sending a keep alive command + * by up to twice the delay between runs. + */ + if (ctrl->ctratt & NVME_CTRL_ATTR_TBKAS) + delay /= 2; + return delay; +} + +static void nvme_queue_keep_alive_work(struct nvme_ctrl *ctrl) { - return __nvme_submit_user_cmd(q, cmd, ubuffer, bufflen, NULL, 0, 0, - result, timeout); + unsigned long now = jiffies; + unsigned long delay = nvme_keep_alive_work_period(ctrl); + unsigned long ka_next_check_tm = ctrl->ka_last_check_time + delay; + + if (time_after(now, ka_next_check_tm)) + delay = 0; + else + delay = ka_next_check_tm - now; + + queue_delayed_work(nvme_wq, &ctrl->ka_work, delay); } -static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status) +static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq, + blk_status_t status) { struct nvme_ctrl *ctrl = rq->end_io_data; + 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 + * at the desired frequency. + */ + if (rtt <= delay) { + delay -= rtt; + } else { + dev_warn(ctrl->device, "long keepalive RTT (%u ms)\n", + jiffies_to_msecs(rtt)); + delay = 0; + } blk_mq_free_request(rq); @@ -696,55 +1358,56 @@ static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status) dev_err(ctrl->device, "failed nvme_keep_alive_end_io error=%d\n", status); - return; + return RQ_END_IO_NONE; } - schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ); -} - -static int nvme_keep_alive(struct nvme_ctrl *ctrl) -{ - struct nvme_command c; - struct request *rq; - - memset(&c, 0, sizeof(c)); - c.common.opcode = nvme_admin_keep_alive; - - rq = nvme_alloc_request(ctrl->admin_q, &c, BLK_MQ_REQ_RESERVED, - NVME_QID_ANY); - if (IS_ERR(rq)) - return PTR_ERR(rq); - - rq->timeout = ctrl->kato * HZ; - rq->end_io_data = ctrl; - - blk_execute_rq_nowait(rq->q, NULL, rq, 0, nvme_keep_alive_end_io); - - return 0; + ctrl->ka_last_check_time = jiffies; + ctrl->comp_seen = false; + 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) { struct nvme_ctrl *ctrl = container_of(to_delayed_work(work), struct nvme_ctrl, ka_work); + bool comp_seen = ctrl->comp_seen; + struct request *rq; + + ctrl->ka_last_check_time = jiffies; + + if ((ctrl->ctratt & NVME_CTRL_ATTR_TBKAS) && comp_seen) { + dev_dbg(ctrl->device, + "reschedule traffic based keep-alive timer\n"); + ctrl->comp_seen = false; + nvme_queue_keep_alive_work(ctrl); + return; + } - if (nvme_keep_alive(ctrl)) { + rq = blk_mq_alloc_request(ctrl->admin_q, nvme_req_op(&ctrl->ka_cmd), + BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT); + if (IS_ERR(rq)) { /* allocation failure, reset the controller */ - dev_err(ctrl->device, "keep-alive failed\n"); + dev_err(ctrl->device, "keep-alive failed: %ld\n", PTR_ERR(rq)); nvme_reset_ctrl(ctrl); return; } + 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); } -void nvme_start_keep_alive(struct nvme_ctrl *ctrl) +static void nvme_start_keep_alive(struct nvme_ctrl *ctrl) { if (unlikely(ctrl->kato == 0)) return; - INIT_DELAYED_WORK(&ctrl->ka_work, nvme_keep_alive_work); - schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ); + nvme_queue_keep_alive_work(ctrl); } -EXPORT_SYMBOL_GPL(nvme_start_keep_alive); void nvme_stop_keep_alive(struct nvme_ctrl *ctrl) { @@ -755,6 +1418,47 @@ void nvme_stop_keep_alive(struct nvme_ctrl *ctrl) } EXPORT_SYMBOL_GPL(nvme_stop_keep_alive); +static void nvme_update_keep_alive(struct nvme_ctrl *ctrl, + struct nvme_command *cmd) +{ + unsigned int new_kato = + DIV_ROUND_UP(le32_to_cpu(cmd->common.cdw11), 1000); + + dev_info(ctrl->device, + "keep alive interval updated from %u ms to %u ms\n", + ctrl->kato * 1000 / 2, new_kato * 1000 / 2); + + nvme_stop_keep_alive(ctrl); + ctrl->kato = new_kato; + nvme_start_keep_alive(ctrl); +} + +static bool nvme_id_cns_ok(struct nvme_ctrl *ctrl, u8 cns) +{ + /* + * 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) { struct nvme_command c = { }; @@ -770,31 +1474,94 @@ static int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id) error = nvme_submit_sync_cmd(dev->admin_q, &c, *id, sizeof(struct nvme_id_ctrl)); - if (error) + if (error) { kfree(*id); + *id = NULL; + } return error; } -static int nvme_identify_ns_descs(struct nvme_ns *ns, unsigned nsid) +static int nvme_process_ns_desc(struct nvme_ctrl *ctrl, struct nvme_ns_ids *ids, + struct nvme_ns_id_desc *cur, bool *csi_seen) +{ + const char *warn_str = "ctrl returned bogus length:"; + void *data = cur; + + switch (cur->nidt) { + case NVME_NIDT_EUI64: + if (cur->nidl != NVME_NIDT_EUI64_LEN) { + dev_warn(ctrl->device, "%s %d for NVME_NIDT_EUI64\n", + warn_str, cur->nidl); + return -1; + } + if (ctrl->quirks & NVME_QUIRK_BOGUS_NID) + return NVME_NIDT_EUI64_LEN; + memcpy(ids->eui64, data + sizeof(*cur), NVME_NIDT_EUI64_LEN); + return NVME_NIDT_EUI64_LEN; + case NVME_NIDT_NGUID: + if (cur->nidl != NVME_NIDT_NGUID_LEN) { + dev_warn(ctrl->device, "%s %d for NVME_NIDT_NGUID\n", + warn_str, cur->nidl); + return -1; + } + if (ctrl->quirks & NVME_QUIRK_BOGUS_NID) + return NVME_NIDT_NGUID_LEN; + memcpy(ids->nguid, data + sizeof(*cur), NVME_NIDT_NGUID_LEN); + return NVME_NIDT_NGUID_LEN; + case NVME_NIDT_UUID: + if (cur->nidl != NVME_NIDT_UUID_LEN) { + dev_warn(ctrl->device, "%s %d for NVME_NIDT_UUID\n", + warn_str, cur->nidl); + return -1; + } + if (ctrl->quirks & NVME_QUIRK_BOGUS_NID) + return NVME_NIDT_UUID_LEN; + uuid_copy(&ids->uuid, data + sizeof(*cur)); + return NVME_NIDT_UUID_LEN; + case NVME_NIDT_CSI: + if (cur->nidl != NVME_NIDT_CSI_LEN) { + dev_warn(ctrl->device, "%s %d for NVME_NIDT_CSI\n", + warn_str, cur->nidl); + return -1; + } + memcpy(&ids->csi, data + sizeof(*cur), NVME_NIDT_CSI_LEN); + *csi_seen = true; + return NVME_NIDT_CSI_LEN; + default: + /* Skip unknown types */ + return cur->nidl; + } +} + +static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, + struct nvme_ns_info *info) { struct nvme_command c = { }; - int status; + bool csi_seen = false; + int status, pos, len; void *data; - int pos; - int len; + + if (ctrl->vs < NVME_VS(1, 3, 0) && !nvme_multi_css(ctrl)) + return 0; + if (ctrl->quirks & NVME_QUIRK_NO_NS_DESC_LIST) + return 0; c.identify.opcode = nvme_admin_identify; - c.identify.nsid = cpu_to_le32(nsid); + c.identify.nsid = cpu_to_le32(info->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(ns->ctrl->admin_q, &c, data, + status = nvme_submit_sync_cmd(ctrl->admin_q, &c, data, NVME_IDENTIFY_DATA_SIZE); - if (status) + if (status) { + dev_warn(ctrl->device, + "Identify Descriptors failed (nsid=%u, status=0x%x)\n", + info->nsid, status); goto free_data; + } for (pos = 0; pos < NVME_IDENTIFY_DATA_SIZE; pos += len) { struct nvme_ns_id_desc *cur = data + pos; @@ -802,62 +1569,26 @@ static int nvme_identify_ns_descs(struct nvme_ns *ns, unsigned nsid) if (cur->nidl == 0) break; - switch (cur->nidt) { - case NVME_NIDT_EUI64: - if (cur->nidl != NVME_NIDT_EUI64_LEN) { - dev_warn(ns->ctrl->device, - "ctrl returned bogus length: %d for NVME_NIDT_EUI64\n", - cur->nidl); - goto free_data; - } - len = NVME_NIDT_EUI64_LEN; - memcpy(ns->eui, data + pos + sizeof(*cur), len); + len = nvme_process_ns_desc(ctrl, &info->ids, cur, &csi_seen); + if (len < 0) break; - case NVME_NIDT_NGUID: - if (cur->nidl != NVME_NIDT_NGUID_LEN) { - dev_warn(ns->ctrl->device, - "ctrl returned bogus length: %d for NVME_NIDT_NGUID\n", - cur->nidl); - goto free_data; - } - len = NVME_NIDT_NGUID_LEN; - memcpy(ns->nguid, data + pos + sizeof(*cur), len); - break; - case NVME_NIDT_UUID: - if (cur->nidl != NVME_NIDT_UUID_LEN) { - dev_warn(ns->ctrl->device, - "ctrl returned bogus length: %d for NVME_NIDT_UUID\n", - cur->nidl); - goto free_data; - } - len = NVME_NIDT_UUID_LEN; - uuid_copy(&ns->uuid, data + pos + sizeof(*cur)); - break; - default: - /* Skip unnkown types */ - len = cur->nidl; - break; - } len += sizeof(*cur); } + + if (nvme_multi_css(ctrl) && !csi_seen) { + dev_warn(ctrl->device, "Command set not reported for nsid:%d\n", + info->nsid); + status = -EINVAL; + } + 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 = { }; - - c.identify.opcode = nvme_admin_identify; - c.identify.cns = NVME_ID_CNS_NS_ACTIVE_LIST; - c.identify.nsid = cpu_to_le32(nsid); - return nvme_submit_sync_cmd(dev->admin_q, &c, ns_list, 0x1000); -} - -static int nvme_identify_ns(struct nvme_ctrl *dev, unsigned nsid, - struct nvme_id_ns **id) +int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid, + struct nvme_id_ns **id) { struct nvme_command c = { }; int error; @@ -867,36 +1598,124 @@ static 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); + *id = kmalloc(sizeof(**id), GFP_KERNEL); if (!*id) return -ENOMEM; - error = nvme_submit_sync_cmd(dev->admin_q, &c, *id, - sizeof(struct nvme_id_ns)); - if (error) + error = nvme_submit_sync_cmd(ctrl->admin_q, &c, *id, sizeof(**id)); + if (error) { + dev_warn(ctrl->device, "Identify namespace failed (%d)\n", error); kfree(*id); + *id = NULL; + } return error; } -static int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11, - void *buffer, size_t buflen, u32 *result) +static int nvme_ns_info_from_identify(struct nvme_ctrl *ctrl, + struct nvme_ns_info *info) +{ + struct nvme_ns_ids *ids = &info->ids; + struct nvme_id_ns *id; + int ret; + + ret = nvme_identify_ns(ctrl, info->nsid, &id); + if (ret) + return ret; + + if (id->ncap == 0) { + /* namespace not allocated or attached */ + info->is_removed = true; + ret = -ENODEV; + goto error; + } + + info->anagrpid = id->anagrpid; + info->is_shared = id->nmic & NVME_NS_NMIC_SHARED; + info->is_readonly = id->nsattr & NVME_NS_ATTR_RO; + info->is_ready = true; + info->endgid = le16_to_cpu(id->endgid); + if (ctrl->quirks & NVME_QUIRK_BOGUS_NID) { + dev_info(ctrl->device, + "Ignoring bogus Namespace Identifiers\n"); + } else { + if (ctrl->vs >= NVME_VS(1, 1, 0) && + !memchr_inv(ids->eui64, 0, sizeof(ids->eui64))) + memcpy(ids->eui64, id->eui64, sizeof(ids->eui64)); + if (ctrl->vs >= NVME_VS(1, 2, 0) && + !memchr_inv(ids->nguid, 0, sizeof(ids->nguid))) + memcpy(ids->nguid, id->nguid, sizeof(ids->nguid)); + } + +error: + kfree(id); + return ret; +} + +static int nvme_ns_info_from_id_cs_indep(struct nvme_ctrl *ctrl, + struct nvme_ns_info *info) +{ + struct nvme_id_ns_cs_indep *id; + struct nvme_command c = { + .identify.opcode = nvme_admin_identify, + .identify.nsid = cpu_to_le32(info->nsid), + .identify.cns = NVME_ID_CNS_NS_CS_INDEP, + }; + int ret; + + id = kmalloc(sizeof(*id), GFP_KERNEL); + if (!id) + return -ENOMEM; + + ret = nvme_submit_sync_cmd(ctrl->admin_q, &c, id, sizeof(*id)); + if (!ret) { + info->anagrpid = id->anagrpid; + 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; + info->endgid = le16_to_cpu(id->endgid); + } + kfree(id); + return ret; +} + +static int nvme_features(struct nvme_ctrl *dev, u8 op, unsigned int fid, + unsigned int dword11, void *buffer, size_t buflen, u32 *result) { - struct nvme_command c; - union nvme_result res; + union nvme_result res = { 0 }; + struct nvme_command c = { }; int ret; - memset(&c, 0, sizeof(c)); - c.features.opcode = nvme_admin_set_features; + c.features.opcode = op; c.features.fid = cpu_to_le32(fid); c.features.dword11 = cpu_to_le32(dword11); ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &res, - buffer, buflen, 0, NVME_QID_ANY, 0, 0); + buffer, buflen, NVME_QID_ANY, 0); if (ret >= 0 && result) *result = le32_to_cpu(res.u32); return ret; } +int nvme_set_features(struct nvme_ctrl *dev, unsigned int fid, + unsigned int dword11, void *buffer, size_t buflen, + void *result) +{ + return nvme_features(dev, nvme_admin_set_features, fid, dword11, buffer, + buflen, result); +} +EXPORT_SYMBOL_GPL(nvme_set_features); + +int nvme_get_features(struct nvme_ctrl *dev, unsigned int fid, + unsigned int dword11, void *buffer, size_t buflen, + void *result) +{ + return nvme_features(dev, nvme_admin_get_features, fid, dword11, buffer, + buflen, result); +} +EXPORT_SYMBOL_GPL(nvme_get_features); + int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count) { u32 q_count = (*count - 1) | ((*count - 1) << 16); @@ -905,7 +1724,13 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count) status = nvme_set_features(ctrl, NVME_FEAT_NUM_QUEUES, q_count, NULL, 0, &result); - if (status < 0) + + /* + * It's either a kernel error or the host observed a connection + * lost. In either case it's not possible communicate with the + * controller and thus enter the error code path. + */ + if (status < 0 || status == NVME_SC_HOST_PATH_ERROR) return status; /* @@ -925,476 +1750,895 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count) } EXPORT_SYMBOL_GPL(nvme_set_queue_count); -static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) -{ - struct nvme_user_io io; - struct nvme_command c; - unsigned length, meta_len; - void __user *metadata; +#define NVME_AEN_SUPPORTED \ + (NVME_AEN_CFG_NS_ATTR | NVME_AEN_CFG_FW_ACT | \ + NVME_AEN_CFG_ANA_CHANGE | NVME_AEN_CFG_DISC_CHANGE) - if (copy_from_user(&io, uio, sizeof(io))) - return -EFAULT; - if (io.flags) - return -EINVAL; - - switch (io.opcode) { - case nvme_cmd_write: - case nvme_cmd_read: - case nvme_cmd_compare: - break; - default: - return -EINVAL; - } - - length = (io.nblocks + 1) << ns->lba_shift; - meta_len = (io.nblocks + 1) * ns->ms; - metadata = (void __user *)(uintptr_t)io.metadata; +static void nvme_enable_aen(struct nvme_ctrl *ctrl) +{ + u32 result, supported_aens = ctrl->oaes & NVME_AEN_SUPPORTED; + int status; - if (ns->ext) { - length += meta_len; - meta_len = 0; - } else if (meta_len) { - if ((io.metadata & 3) || !io.metadata) - return -EINVAL; - } + if (!supported_aens) + return; - memset(&c, 0, sizeof(c)); - c.rw.opcode = io.opcode; - c.rw.flags = io.flags; - c.rw.nsid = cpu_to_le32(ns->ns_id); - c.rw.slba = cpu_to_le64(io.slba); - c.rw.length = cpu_to_le16(io.nblocks); - c.rw.control = cpu_to_le16(io.control); - c.rw.dsmgmt = cpu_to_le32(io.dsmgmt); - c.rw.reftag = cpu_to_le32(io.reftag); - c.rw.apptag = cpu_to_le16(io.apptag); - c.rw.appmask = cpu_to_le16(io.appmask); + status = nvme_set_features(ctrl, NVME_FEAT_ASYNC_EVENT, supported_aens, + NULL, 0, &result); + if (status) + dev_warn(ctrl->device, "Failed to configure AEN (cfg %x)\n", + supported_aens); - return __nvme_submit_user_cmd(ns->queue, &c, - (void __user *)(uintptr_t)io.addr, length, - metadata, meta_len, io.slba, NULL, 0); + queue_work(nvme_wq, &ctrl->async_event_work); } -static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns, - struct nvme_passthru_cmd __user *ucmd) +static int nvme_ns_open(struct nvme_ns *ns) { - struct nvme_passthru_cmd cmd; - struct nvme_command c; - unsigned timeout = 0; - int status; - if (!capable(CAP_SYS_ADMIN)) - return -EACCES; - if (copy_from_user(&cmd, ucmd, sizeof(cmd))) - return -EFAULT; - if (cmd.flags) - return -EINVAL; + /* should never be called due to GENHD_FL_HIDDEN */ + if (WARN_ON_ONCE(nvme_ns_head_multipath(ns->head))) + goto fail; + if (!nvme_get_ns(ns)) + goto fail; + if (!try_module_get(ns->ctrl->ops->module)) + goto fail_put_ns; - memset(&c, 0, sizeof(c)); - c.common.opcode = cmd.opcode; - c.common.flags = cmd.flags; - c.common.nsid = cpu_to_le32(cmd.nsid); - c.common.cdw2[0] = cpu_to_le32(cmd.cdw2); - c.common.cdw2[1] = cpu_to_le32(cmd.cdw3); - c.common.cdw10[0] = cpu_to_le32(cmd.cdw10); - c.common.cdw10[1] = cpu_to_le32(cmd.cdw11); - c.common.cdw10[2] = cpu_to_le32(cmd.cdw12); - c.common.cdw10[3] = cpu_to_le32(cmd.cdw13); - c.common.cdw10[4] = cpu_to_le32(cmd.cdw14); - c.common.cdw10[5] = cpu_to_le32(cmd.cdw15); - - if (cmd.timeout_ms) - timeout = msecs_to_jiffies(cmd.timeout_ms); - - status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c, - (void __user *)(uintptr_t)cmd.addr, cmd.data_len, - &cmd.result, timeout); - if (status >= 0) { - if (put_user(cmd.result, &ucmd->result)) - return -EFAULT; - } + return 0; - return status; +fail_put_ns: + nvme_put_ns(ns); +fail: + return -ENXIO; } -static int nvme_ioctl(struct block_device *bdev, fmode_t mode, - unsigned int cmd, unsigned long arg) +static void nvme_ns_release(struct nvme_ns *ns) { - struct nvme_ns *ns = bdev->bd_disk->private_data; - - switch (cmd) { - case NVME_IOCTL_ID: - force_successful_syscall_return(); - return ns->ns_id; - case NVME_IOCTL_ADMIN_CMD: - return nvme_user_cmd(ns->ctrl, NULL, (void __user *)arg); - case NVME_IOCTL_IO_CMD: - return nvme_user_cmd(ns->ctrl, ns, (void __user *)arg); - case NVME_IOCTL_SUBMIT_IO: - return nvme_submit_io(ns, (void __user *)arg); - default: -#ifdef CONFIG_NVM - if (ns->ndev) - return nvme_nvm_ioctl(ns, cmd, arg); -#endif - if (is_sed_ioctl(cmd)) - return sed_ioctl(ns->ctrl->opal_dev, cmd, - (void __user *) arg); - return -ENOTTY; - } -} -#ifdef CONFIG_COMPAT -static int nvme_compat_ioctl(struct block_device *bdev, fmode_t mode, - unsigned int cmd, unsigned long arg) -{ - return nvme_ioctl(bdev, mode, cmd, arg); + module_put(ns->ctrl->ops->module); + nvme_put_ns(ns); } -#else -#define nvme_compat_ioctl NULL -#endif -static int nvme_open(struct block_device *bdev, fmode_t mode) +static int nvme_open(struct gendisk *disk, blk_mode_t mode) { - return nvme_get_ns_from_disk(bdev->bd_disk) ? 0 : -ENXIO; + return nvme_ns_open(disk->private_data); } -static void nvme_release(struct gendisk *disk, fmode_t mode) +static void nvme_release(struct gendisk *disk) { - struct nvme_ns *ns = disk->private_data; - - module_put(ns->ctrl->ops->module); - nvme_put_ns(ns); + nvme_ns_release(disk->private_data); } -static int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo) +int nvme_getgeo(struct gendisk *disk, struct hd_geometry *geo) { /* some standard values */ geo->heads = 1 << 6; geo->sectors = 1 << 5; - geo->cylinders = get_capacity(bdev->bd_disk) >> 11; + geo->cylinders = get_capacity(disk) >> 11; return 0; } -#ifdef CONFIG_BLK_DEV_INTEGRITY -static void nvme_prep_integrity(struct gendisk *disk, struct nvme_id_ns *id, - u16 bs) +static bool nvme_init_integrity(struct nvme_ns_head *head, + struct queue_limits *lim, struct nvme_ns_info *info) { - struct nvme_ns *ns = disk->private_data; - u16 old_ms = ns->ms; - u8 pi_type = 0; - - ns->ms = le16_to_cpu(id->lbaf[id->flbas & NVME_NS_FLBAS_LBA_MASK].ms); - ns->ext = ns->ms && (id->flbas & NVME_NS_FLBAS_META_EXT); + struct blk_integrity *bi = &lim->integrity; - /* PI implementation requires metadata equal t10 pi tuple size */ - if (ns->ms == sizeof(struct t10_pi_tuple)) - pi_type = id->dps & NVME_NS_DPS_PI_MASK; + memset(bi, 0, sizeof(*bi)); - if (blk_get_integrity(disk) && - (ns->pi_type != pi_type || ns->ms != old_ms || - bs != queue_logical_block_size(disk->queue) || - (ns->ms && ns->ext))) - blk_integrity_unregister(disk); - - ns->pi_type = pi_type; -} + if (!head->ms) + return true; -static void nvme_init_integrity(struct nvme_ns *ns) -{ - struct blk_integrity integrity; + /* + * PI can always be supported as we can ask the controller to simply + * insert/strip it, which is not possible for other kinds of metadata. + */ + if (!IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) || + !(head->features & NVME_NS_METADATA_SUPPORTED)) + return nvme_ns_has_pi(head); - memset(&integrity, 0, sizeof(integrity)); - switch (ns->pi_type) { + switch (head->pi_type) { case NVME_NS_DPS_PI_TYPE3: - integrity.profile = &t10_pi_type3_crc; - integrity.tag_size = sizeof(u16) + sizeof(u32); - integrity.flags |= BLK_INTEGRITY_DEVICE_CAPABLE; + switch (head->guard_type) { + case NVME_NVM_NS_16B_GUARD: + bi->csum_type = BLK_INTEGRITY_CSUM_CRC; + bi->tag_size = sizeof(u16) + sizeof(u32); + bi->flags |= BLK_INTEGRITY_DEVICE_CAPABLE; + break; + case NVME_NVM_NS_64B_GUARD: + bi->csum_type = BLK_INTEGRITY_CSUM_CRC64; + bi->tag_size = sizeof(u16) + 6; + bi->flags |= BLK_INTEGRITY_DEVICE_CAPABLE; + break; + default: + break; + } break; case NVME_NS_DPS_PI_TYPE1: case NVME_NS_DPS_PI_TYPE2: - integrity.profile = &t10_pi_type1_crc; - integrity.tag_size = sizeof(u16); - integrity.flags |= BLK_INTEGRITY_DEVICE_CAPABLE; + switch (head->guard_type) { + case NVME_NVM_NS_16B_GUARD: + bi->csum_type = BLK_INTEGRITY_CSUM_CRC; + bi->tag_size = sizeof(u16); + bi->flags |= BLK_INTEGRITY_DEVICE_CAPABLE | + BLK_INTEGRITY_REF_TAG; + break; + case NVME_NVM_NS_64B_GUARD: + bi->csum_type = BLK_INTEGRITY_CSUM_CRC64; + bi->tag_size = sizeof(u16); + bi->flags |= BLK_INTEGRITY_DEVICE_CAPABLE | + BLK_INTEGRITY_REF_TAG; + break; + default: + break; + } break; default: - integrity.profile = NULL; break; } - integrity.tuple_size = ns->ms; - blk_integrity_register(ns->disk, &integrity); - blk_queue_max_integrity_segments(ns->queue, 1); + + bi->metadata_size = head->ms; + if (bi->csum_type) { + bi->pi_tuple_size = head->pi_size; + bi->pi_offset = info->pi_offset; + } + return true; } -#else -static void nvme_prep_integrity(struct gendisk *disk, struct nvme_id_ns *id, - u16 bs) + +static void nvme_config_discard(struct nvme_ns *ns, struct queue_limits *lim) { + struct nvme_ctrl *ctrl = ns->ctrl; + + if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(ns->head, UINT_MAX)) + lim->max_hw_discard_sectors = + nvme_lba_to_sect(ns->head, ctrl->dmrsl); + else if (ctrl->oncs & NVME_CTRL_ONCS_DSM) + lim->max_hw_discard_sectors = UINT_MAX; + else + lim->max_hw_discard_sectors = 0; + + lim->discard_granularity = lim->logical_block_size; + + if (ctrl->dmrl) + lim->max_discard_segments = ctrl->dmrl; + else + lim->max_discard_segments = NVME_DSM_MAX_RANGES; } -static void nvme_init_integrity(struct nvme_ns *ns) + +static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b) { + return uuid_equal(&a->uuid, &b->uuid) && + memcmp(&a->nguid, &b->nguid, sizeof(a->nguid)) == 0 && + memcmp(&a->eui64, &b->eui64, sizeof(a->eui64)) == 0 && + a->csi == b->csi; } -#endif /* CONFIG_BLK_DEV_INTEGRITY */ -static void nvme_set_chunk_size(struct nvme_ns *ns) +static int nvme_identify_ns_nvm(struct nvme_ctrl *ctrl, unsigned int nsid, + struct nvme_id_ns_nvm **nvmp) { - u32 chunk_size = (((u32)ns->noiob) << (ns->lba_shift - 9)); - blk_queue_chunk_sectors(ns->queue, rounddown_pow_of_two(chunk_size)); + struct nvme_command c = { + .identify.opcode = nvme_admin_identify, + .identify.nsid = cpu_to_le32(nsid), + .identify.cns = NVME_ID_CNS_CS_NS, + .identify.csi = NVME_CSI_NVM, + }; + struct nvme_id_ns_nvm *nvm; + int ret; + + nvm = kzalloc(sizeof(*nvm), GFP_KERNEL); + if (!nvm) + return -ENOMEM; + + ret = nvme_submit_sync_cmd(ctrl->admin_q, &c, nvm, sizeof(*nvm)); + if (ret) + kfree(nvm); + else + *nvmp = nvm; + return ret; } -static void nvme_config_discard(struct nvme_ns *ns) +static void nvme_configure_pi_elbas(struct nvme_ns_head *head, + struct nvme_id_ns *id, struct nvme_id_ns_nvm *nvm) { - struct nvme_ctrl *ctrl = ns->ctrl; - u32 logical_block_size = queue_logical_block_size(ns->queue); + u32 elbaf = le32_to_cpu(nvm->elbaf[nvme_lbaf_index(id->flbas)]); + u8 guard_type; - BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) < - NVME_DSM_MAX_RANGES); + /* no support for storage tag formats right now */ + if (nvme_elbaf_sts(elbaf)) + return; - if (ctrl->nr_streams && ns->sws && ns->sgs) { - unsigned int sz = logical_block_size * ns->sws * ns->sgs; + guard_type = nvme_elbaf_guard_type(elbaf); + if ((nvm->pic & NVME_ID_NS_NVM_QPIFS) && + guard_type == NVME_NVM_NS_QTYPE_GUARD) + guard_type = nvme_elbaf_qualified_guard_type(elbaf); - 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; + head->guard_type = guard_type; + switch (head->guard_type) { + case NVME_NVM_NS_64B_GUARD: + head->pi_size = sizeof(struct crc64_pi_tuple); + break; + case NVME_NVM_NS_16B_GUARD: + head->pi_size = sizeof(struct t10_pi_tuple); + break; + default: + break; } - 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); - - if (ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES) - 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_configure_metadata(struct nvme_ctrl *ctrl, + struct nvme_ns_head *head, struct nvme_id_ns *id, + struct nvme_id_ns_nvm *nvm, struct nvme_ns_info *info) { - if (nvme_identify_ns(ns->ctrl, ns->ns_id, id)) { - dev_warn(ns->ctrl->dev, "%s: Identify failure\n", __func__); - return -ENODEV; + head->features &= ~(NVME_NS_METADATA_SUPPORTED | NVME_NS_EXT_LBAS); + head->pi_type = 0; + head->pi_size = 0; + head->ms = le16_to_cpu(id->lbaf[nvme_lbaf_index(id->flbas)].ms); + if (!head->ms || !(ctrl->ops->flags & NVME_F_METADATA_SUPPORTED)) + return; + + if (nvm && (ctrl->ctratt & NVME_CTRL_ATTR_ELBAS)) { + nvme_configure_pi_elbas(head, id, nvm); + } else { + head->pi_size = sizeof(struct t10_pi_tuple); + head->guard_type = NVME_NVM_NS_16B_GUARD; } - if ((*id)->ncap == 0) { - kfree(*id); - return -ENODEV; + 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)) { + if (disable_pi_offsets) + head->pi_type = 0; + else + info->pi_offset = head->ms - head->pi_size; } - 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->nguid, (*id)->nguid, sizeof(ns->nguid)); - if (ns->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(ns, ns->ns_id)) - dev_warn(ns->ctrl->device, - "%s: Identify Descriptors failed\n", __func__); + if (ctrl->ops->flags & NVME_F_FABRICS) { + /* + * The NVMe over Fabrics specification only supports metadata as + * part of the extended data LBA. We rely on HCA/HBA support to + * remap the separate metadata buffer from the block layer. + */ + if (WARN_ON_ONCE(!(id->flbas & NVME_NS_FLBAS_META_EXT))) + return; + + head->features |= NVME_NS_EXT_LBAS; + + /* + * The current fabrics transport drivers support namespace + * metadata formats only if nvme_ns_has_pi() returns true. + * Suppress support for all other formats so the namespace will + * have a 0 capacity and not be usable through the block stack. + * + * Note, this check will need to be modified if any drivers + * gain the ability to use other metadata formats. + */ + if (ctrl->max_integrity_segments && nvme_ns_has_pi(head)) + head->features |= NVME_NS_METADATA_SUPPORTED; + } else { + /* + * For PCIe controllers, we can't easily remap the separate + * metadata buffer from the block layer and thus require a + * separate metadata buffer for block layer metadata/PI support. + * We allow extended LBAs for the passthrough interface, though. + */ + if (id->flbas & NVME_NS_FLBAS_META_EXT) + head->features |= NVME_NS_EXT_LBAS; + else + head->features |= NVME_NS_METADATA_SUPPORTED; } +} - return 0; + +static u32 nvme_configure_atomic_write(struct nvme_ns *ns, + struct nvme_id_ns *id, struct queue_limits *lim, u32 bs) +{ + u32 atomic_bs, boundary = 0; + + /* + * We do not support an offset for the atomic boundaries. + */ + if (id->nabo) + return bs; + + if ((id->nsfeat & NVME_NS_FEAT_ATOMICS) && id->nawupf) { + /* + * Use the per-namespace atomic write unit when available. + */ + atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs; + if (id->nabspf) + boundary = (le16_to_cpu(id->nabspf) + 1) * bs; + } else { + /* + * Use the controller wide atomic write unit. This sucks + * because the limit is defined in terms of logical blocks while + * namespaces can have different formats, and because there is + * no clear language in the specification prohibiting different + * values for different controllers in the subsystem. + */ + atomic_bs = (1 + ns->ctrl->subsys->awupf) * bs; + } + + lim->atomic_write_hw_max = atomic_bs; + lim->atomic_write_hw_boundary = boundary; + lim->atomic_write_hw_unit_min = bs; + lim->atomic_write_hw_unit_max = rounddown_pow_of_two(atomic_bs); + lim->features |= BLK_FEAT_ATOMIC_WRITES; + return atomic_bs; } -static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id) +static u32 nvme_max_drv_segments(struct nvme_ctrl *ctrl) { - struct nvme_ns *ns = disk->private_data; - struct nvme_ctrl *ctrl = ns->ctrl; - u16 bs; + return ctrl->max_hw_sectors / (NVME_CTRL_PAGE_SIZE >> SECTOR_SHIFT) + 1; +} + +static void nvme_set_ctrl_limits(struct nvme_ctrl *ctrl, + struct queue_limits *lim, bool is_admin) +{ + lim->max_hw_sectors = ctrl->max_hw_sectors; + lim->max_segments = min_t(u32, USHRT_MAX, + min_not_zero(nvme_max_drv_segments(ctrl), ctrl->max_segments)); + lim->max_integrity_segments = ctrl->max_integrity_segments; + lim->virt_boundary_mask = ctrl->ops->get_virt_boundary(ctrl, is_admin); + lim->max_segment_size = UINT_MAX; + lim->dma_alignment = 3; +} + +static bool nvme_update_disk_info(struct nvme_ns *ns, struct nvme_id_ns *id, + struct queue_limits *lim) +{ + struct nvme_ns_head *head = ns->head; + u32 bs = 1U << head->lba_shift; + u32 atomic_bs, phys_bs, io_opt = 0; + bool valid = true; /* - * If identify namespace failed, use default 512 byte block size so - * block layer can use before failing read/write for 0 capacity. + * The block layer can't support LBA sizes larger than the page size + * or smaller than a sector size yet, so catch this early and don't + * allow block I/O. */ - ns->lba_shift = id->lbaf[id->flbas & NVME_NS_FLBAS_LBA_MASK].ds; - 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 (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)) - set_capacity(disk, 0); + if (blk_validate_block_size(bs)) { + bs = (1 << 9); + valid = false; + } + + phys_bs = bs; + atomic_bs = nvme_configure_atomic_write(ns, id, lim, bs); + + if (id->nsfeat & NVME_NS_FEAT_IO_OPT) { + /* NPWG = Namespace Preferred Write Granularity */ + phys_bs = bs * (1 + le16_to_cpu(id->npwg)); + /* NOWS = Namespace Optimal Write Size */ + if (id->nows) + io_opt = bs * (1 + le16_to_cpu(id->nows)); + } + + /* + * Linux filesystems assume writing a single physical block is + * an atomic operation. Hence limit the physical block size to the + * value of the Atomic Write Unit Power Fail parameter. + */ + lim->logical_block_size = bs; + lim->physical_block_size = min(phys_bs, atomic_bs); + lim->io_min = phys_bs; + lim->io_opt = io_opt; + if ((ns->ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES) && + (ns->ctrl->oncs & NVME_CTRL_ONCS_DSM)) + lim->max_write_zeroes_sectors = UINT_MAX; else - set_capacity(disk, le64_to_cpup(&id->nsze) << (ns->lba_shift - 9)); + lim->max_write_zeroes_sectors = ns->ctrl->max_zeroes_sectors; + return valid; +} - if (ctrl->oncs & NVME_CTRL_ONCS_DSM) - nvme_config_discard(ns); - blk_mq_unfreeze_queue(disk->queue); +static bool nvme_ns_is_readonly(struct nvme_ns *ns, struct nvme_ns_info *info) +{ + return info->is_readonly || test_bit(NVME_NS_FORCE_RO, &ns->flags); } -static int nvme_revalidate_disk(struct gendisk *disk) +static inline bool nvme_first_scan(struct gendisk *disk) { - struct nvme_ns *ns = disk->private_data; - struct nvme_id_ns *id = NULL; - int ret; + /* nvme_alloc_ns() scans the disk prior to adding it */ + return !disk_live(disk); +} - if (test_bit(NVME_NS_DEAD, &ns->flags)) { - set_capacity(disk, 0); - return -ENODEV; +static void nvme_set_chunk_sectors(struct nvme_ns *ns, struct nvme_id_ns *id, + struct queue_limits *lim) +{ + struct nvme_ctrl *ctrl = ns->ctrl; + u32 iob; + + if ((ctrl->quirks & NVME_QUIRK_STRIPE_SIZE) && + is_power_of_2(ctrl->max_hw_sectors)) + iob = ctrl->max_hw_sectors; + else + iob = nvme_lba_to_sect(ns->head, le16_to_cpu(id->noiob)); + + if (!iob) + return; + + if (!is_power_of_2(iob)) { + if (nvme_first_scan(ns->disk)) + pr_warn("%s: ignoring unaligned IO boundary:%u\n", + ns->disk->disk_name, iob); + return; } - ret = nvme_revalidate_ns(ns, &id); - if (ret) - return ret; + if (blk_queue_is_zoned(ns->disk->queue)) { + if (nvme_first_scan(ns->disk)) + pr_warn("%s: ignoring zoned namespace IO boundary\n", + ns->disk->disk_name); + return; + } - __nvme_revalidate_disk(disk, id); - kfree(id); + lim->chunk_sectors = iob; +} - return 0; +static int nvme_update_ns_info_generic(struct nvme_ns *ns, + struct nvme_ns_info *info) +{ + struct queue_limits lim; + unsigned int memflags; + int ret; + + lim = queue_limits_start_update(ns->disk->queue); + nvme_set_ctrl_limits(ns->ctrl, &lim, false); + + memflags = blk_mq_freeze_queue(ns->disk->queue); + ret = queue_limits_commit_update(ns->disk->queue, &lim); + set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info)); + blk_mq_unfreeze_queue(ns->disk->queue, memflags); + + /* Hide the block-interface for these devices */ + if (!ret) + ret = -ENODEV; + return ret; } -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: +static int nvme_query_fdp_granularity(struct nvme_ctrl *ctrl, + struct nvme_ns_info *info, u8 fdp_idx) +{ + struct nvme_fdp_config_log hdr, *h; + struct nvme_fdp_config_desc *desc; + size_t size = sizeof(hdr); + void *log, *end; + int i, n, ret; + + ret = nvme_get_log_lsi(ctrl, 0, NVME_LOG_FDP_CONFIGS, 0, + NVME_CSI_NVM, &hdr, size, 0, info->endgid); + if (ret) { + dev_warn(ctrl->device, + "FDP configs log header status:0x%x endgid:%d\n", ret, + info->endgid); + return ret; + } + + size = le32_to_cpu(hdr.sze); + if (size > PAGE_SIZE * MAX_ORDER_NR_PAGES) { + dev_warn(ctrl->device, "FDP config size too large:%zu\n", + size); 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, }; + h = kvmalloc(size, GFP_KERNEL); + if (!h) + return -ENOMEM; - put_unaligned_le64(key, &data[0]); - put_unaligned_le64(sa_key, &data[8]); + ret = nvme_get_log_lsi(ctrl, 0, NVME_LOG_FDP_CONFIGS, 0, + NVME_CSI_NVM, h, size, 0, info->endgid); + if (ret) { + dev_warn(ctrl->device, + "FDP configs log status:0x%x endgid:%d\n", ret, + info->endgid); + goto out; + } + + n = le16_to_cpu(h->numfdpc) + 1; + if (fdp_idx > n) { + dev_warn(ctrl->device, "FDP index:%d out of range:%d\n", + fdp_idx, n); + /* Proceed without registering FDP streams */ + ret = 0; + goto out; + } + + log = h + 1; + desc = log; + end = log + size - sizeof(*h); + for (i = 0; i < fdp_idx; i++) { + log += le16_to_cpu(desc->dsze); + desc = log; + if (log >= end) { + dev_warn(ctrl->device, + "FDP invalid config descriptor list\n"); + ret = 0; + goto out; + } + } - 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); + if (le32_to_cpu(desc->nrg) > 1) { + dev_warn(ctrl->device, "FDP NRG > 1 not supported\n"); + ret = 0; + goto out; + } - return nvme_submit_sync_cmd(ns->queue, &c, data, 16); + info->runs = le64_to_cpu(desc->runs); +out: + kvfree(h); + return ret; } -static int nvme_pr_register(struct block_device *bdev, u64 old, - u64 new, unsigned flags) +static int nvme_query_fdp_info(struct nvme_ns *ns, struct nvme_ns_info *info) { - u32 cdw10; + struct nvme_ns_head *head = ns->head; + struct nvme_ctrl *ctrl = ns->ctrl; + struct nvme_fdp_ruh_status *ruhs; + struct nvme_fdp_config fdp; + struct nvme_command c = {}; + size_t size; + int i, ret; + + /* + * The FDP configuration is static for the lifetime of the namespace, + * so return immediately if we've already registered this namespace's + * streams. + */ + if (head->nr_plids) + return 0; + + ret = nvme_get_features(ctrl, NVME_FEAT_FDP, info->endgid, NULL, 0, + &fdp); + if (ret) { + dev_warn(ctrl->device, "FDP get feature status:0x%x\n", ret); + return ret; + } + + if (!(fdp.flags & FDPCFG_FDPE)) + return 0; + + ret = nvme_query_fdp_granularity(ctrl, info, fdp.fdpcidx); + if (!info->runs) + return ret; + + size = struct_size(ruhs, ruhsd, S8_MAX - 1); + ruhs = kzalloc(size, GFP_KERNEL); + if (!ruhs) + return -ENOMEM; + + c.imr.opcode = nvme_cmd_io_mgmt_recv; + c.imr.nsid = cpu_to_le32(head->ns_id); + c.imr.mo = NVME_IO_MGMT_RECV_MO_RUHS; + c.imr.numd = cpu_to_le32(nvme_bytes_to_numd(size)); + ret = nvme_submit_sync_cmd(ns->queue, &c, ruhs, size); + if (ret) { + dev_warn(ctrl->device, "FDP io-mgmt status:0x%x\n", ret); + goto free; + } + + head->nr_plids = le16_to_cpu(ruhs->nruhsd); + if (!head->nr_plids) + goto free; - if (flags & ~PR_FL_IGNORE_KEY) - return -EOPNOTSUPP; + head->plids = kcalloc(head->nr_plids, sizeof(*head->plids), + GFP_KERNEL); + if (!head->plids) { + dev_warn(ctrl->device, + "failed to allocate %u FDP placement IDs\n", + head->nr_plids); + head->nr_plids = 0; + ret = -ENOMEM; + goto free; + } - 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); + for (i = 0; i < head->nr_plids; i++) + head->plids[i] = le16_to_cpu(ruhs->ruhsd[i].pid); +free: + kfree(ruhs); + return ret; } -static int nvme_pr_reserve(struct block_device *bdev, u64 key, - enum pr_type type, unsigned flags) +static int nvme_update_ns_info_block(struct nvme_ns *ns, + struct nvme_ns_info *info) { - u32 cdw10; + struct queue_limits lim; + struct nvme_id_ns_nvm *nvm = NULL; + struct nvme_zone_info zi = {}; + struct nvme_id_ns *id; + unsigned int memflags; + sector_t capacity; + unsigned lbaf; + int ret; + + ret = nvme_identify_ns(ns->ctrl, info->nsid, &id); + if (ret) + return ret; + + if (id->ncap == 0) { + /* namespace not allocated or attached */ + info->is_removed = true; + ret = -ENXIO; + goto out; + } + lbaf = nvme_lbaf_index(id->flbas); + + if (ns->ctrl->ctratt & NVME_CTRL_ATTR_ELBAS) { + ret = nvme_identify_ns_nvm(ns->ctrl, info->nsid, &nvm); + if (ret < 0) + goto out; + } - if (flags & ~PR_FL_IGNORE_KEY) - return -EOPNOTSUPP; + if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && + ns->head->ids.csi == NVME_CSI_ZNS) { + ret = nvme_query_zone_info(ns, lbaf, &zi); + if (ret < 0) + goto out; + } + + if (ns->ctrl->ctratt & NVME_CTRL_ATTR_FDPS) { + ret = nvme_query_fdp_info(ns, info); + if (ret < 0) + goto out; + } + + lim = queue_limits_start_update(ns->disk->queue); + + memflags = blk_mq_freeze_queue(ns->disk->queue); + ns->head->lba_shift = id->lbaf[lbaf].ds; + ns->head->nuse = le64_to_cpu(id->nuse); + capacity = nvme_lba_to_sect(ns->head, le64_to_cpu(id->nsze)); + nvme_set_ctrl_limits(ns->ctrl, &lim, false); + nvme_configure_metadata(ns->ctrl, ns->head, id, nvm, info); + nvme_set_chunk_sectors(ns, id, &lim); + if (!nvme_update_disk_info(ns, id, &lim)) + capacity = 0; + + nvme_config_discard(ns, &lim); + if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && + ns->head->ids.csi == NVME_CSI_ZNS) + nvme_update_zone_info(ns, &lim, &zi); + + 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); - 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); + 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 + * I/O to namespaces with metadata except when the namespace supports + * PI, as it can strip/insert in that case. + */ + if (!nvme_init_integrity(ns->head, &lim, info)) + capacity = 0; + + lim.max_write_streams = ns->head->nr_plids; + if (lim.max_write_streams) + lim.write_stream_granularity = min(info->runs, U32_MAX); + else + lim.write_stream_granularity = 0; + + /* + * Only set the DEAC bit if the device guarantees that reads from + * deallocated data return zeroes. While the DEAC bit does not + * require that, it must be a no-op if reads from deallocated data + * do not return zeroes. + */ + if ((id->dlfeat & 0x7) == 0x1 && (id->dlfeat & (1 << 3))) { + ns->head->features |= NVME_NS_DEAC; + lim.max_hw_wzeroes_unmap_sectors = lim.max_write_zeroes_sectors; + } + + ret = queue_limits_commit_update(ns->disk->queue, &lim); + if (ret) { + blk_mq_unfreeze_queue(ns->disk->queue, memflags); + goto out; + } + + set_capacity_and_notify(ns->disk, capacity); + set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info)); + set_bit(NVME_NS_READY, &ns->flags); + blk_mq_unfreeze_queue(ns->disk->queue, memflags); + + if (blk_queue_is_zoned(ns->queue)) { + ret = blk_revalidate_disk_zones(ns->disk); + if (ret && !nvme_first_scan(ns->disk)) + goto out; + } + + ret = 0; +out: + kfree(nvm); + kfree(id); + return ret; } -static int nvme_pr_preempt(struct block_device *bdev, u64 old, u64 new, - enum pr_type type, bool abort) +static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info) { - u32 cdw10 = nvme_pr_type(type) << 8 | abort ? 2 : 1; - return nvme_pr_command(bdev, cdw10, old, new, nvme_cmd_resv_acquire); + bool unsupported = false; + int ret; + + switch (info->ids.csi) { + case NVME_CSI_ZNS: + if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED)) { + dev_info(ns->ctrl->device, + "block device for nsid %u not supported without CONFIG_BLK_DEV_ZONED\n", + info->nsid); + ret = nvme_update_ns_info_generic(ns, info); + break; + } + ret = nvme_update_ns_info_block(ns, info); + break; + case NVME_CSI_NVM: + ret = nvme_update_ns_info_block(ns, info); + break; + default: + dev_info(ns->ctrl->device, + "block device for nsid %u not supported (csi %u)\n", + info->nsid, info->ids.csi); + ret = nvme_update_ns_info_generic(ns, info); + break; + } + + /* + * If probing fails due an unsupported feature, hide the block device, + * but still allow other access. + */ + if (ret == -ENODEV) { + ns->disk->flags |= GENHD_FL_HIDDEN; + set_bit(NVME_NS_READY, &ns->flags); + unsupported = true; + ret = 0; + } + + if (!ret && nvme_ns_head_multipath(ns->head)) { + struct queue_limits *ns_lim = &ns->disk->queue->limits; + struct queue_limits lim; + unsigned int memflags; + + lim = queue_limits_start_update(ns->head->disk->queue); + memflags = blk_mq_freeze_queue(ns->head->disk->queue); + /* + * queue_limits mixes values that are the hardware limitations + * for bio splitting with what is the device configuration. + * + * For NVMe the device configuration can change after e.g. a + * Format command, and we really want to pick up the new format + * value here. But we must still stack the queue limits to the + * least common denominator for multipathing to split the bios + * properly. + * + * To work around this, we explicitly set the device + * configuration to those that we just queried, but only stack + * the splitting limits in to make sure we still obey possibly + * lower limitations of other controllers. + */ + lim.logical_block_size = ns_lim->logical_block_size; + lim.physical_block_size = ns_lim->physical_block_size; + lim.io_min = ns_lim->io_min; + lim.io_opt = ns_lim->io_opt; + queue_limits_stack_bdev(&lim, ns->disk->part0, 0, + ns->head->disk->disk_name); + if (unsupported) + ns->head->disk->flags |= GENHD_FL_HIDDEN; + else + nvme_init_integrity(ns->head, &lim, info); + lim.max_write_streams = ns_lim->max_write_streams; + lim.write_stream_granularity = ns_lim->write_stream_granularity; + ret = queue_limits_commit_update(ns->head->disk->queue, &lim); + + set_capacity_and_notify(ns->head->disk, get_capacity(ns->disk)); + set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info)); + nvme_mpath_revalidate_paths(ns); + + blk_mq_unfreeze_queue(ns->head->disk->queue, memflags); + } + + return ret; } -static int nvme_pr_clear(struct block_device *bdev, u64 key) +int nvme_ns_get_unique_id(struct nvme_ns *ns, u8 id[16], + enum blk_unique_id type) { - u32 cdw10 = 1 | (key ? 1 << 3 : 0); - return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_register); + struct nvme_ns_ids *ids = &ns->head->ids; + + if (type != BLK_UID_EUI64) + return -EINVAL; + + if (memchr_inv(ids->nguid, 0, sizeof(ids->nguid))) { + memcpy(id, &ids->nguid, sizeof(ids->nguid)); + return sizeof(ids->nguid); + } + if (memchr_inv(ids->eui64, 0, sizeof(ids->eui64))) { + memcpy(id, &ids->eui64, sizeof(ids->eui64)); + return sizeof(ids->eui64); + } + + return -EINVAL; } -static int nvme_pr_release(struct block_device *bdev, u64 key, enum pr_type type) +static int nvme_get_unique_id(struct gendisk *disk, u8 id[16], + enum blk_unique_id type) { - u32 cdw10 = nvme_pr_type(type) << 8 | key ? 1 << 3 : 0; - return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_release); + return nvme_ns_get_unique_id(disk->private_data, id, type); } -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, -}; - #ifdef CONFIG_BLK_SED_OPAL -int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len, +static int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len, bool send) { struct nvme_ctrl *ctrl = data; - struct nvme_command cmd; + struct nvme_command cmd = { }; - memset(&cmd, 0, sizeof(cmd)); if (send) cmd.common.opcode = nvme_admin_security_send; else cmd.common.opcode = nvme_admin_security_recv; cmd.common.nsid = 0; - cmd.common.cdw10[0] = cpu_to_le32(((u32)secp) << 24 | ((u32)spsp) << 8); - cmd.common.cdw10[1] = cpu_to_le32(len); + cmd.common.cdw10 = cpu_to_le32(((u32)secp) << 24 | ((u32)spsp) << 8); + cmd.common.cdw11 = cpu_to_le32(len); return __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, NULL, buffer, len, - ADMIN_TIMEOUT, NVME_QID_ANY, 1, 0); + NVME_QID_ANY, NVME_SUBMIT_AT_HEAD); +} + +static void nvme_configure_opal(struct nvme_ctrl *ctrl, bool was_suspended) +{ + if (ctrl->oacs & NVME_CTRL_OACS_SEC_SUPP) { + if (!ctrl->opal_dev) + ctrl->opal_dev = init_opal_dev(ctrl, &nvme_sec_submit); + else if (was_suspended) + opal_unlock_from_suspend(ctrl->opal_dev); + } else { + free_opal_dev(ctrl->opal_dev); + ctrl->opal_dev = NULL; + } +} +#else +static void nvme_configure_opal(struct nvme_ctrl *ctrl, bool was_suspended) +{ } -EXPORT_SYMBOL_GPL(nvme_sec_submit); #endif /* CONFIG_BLK_SED_OPAL */ -static const struct block_device_operations nvme_fops = { +#ifdef CONFIG_BLK_DEV_ZONED +static int nvme_report_zones(struct gendisk *disk, sector_t sector, + unsigned int nr_zones, struct blk_report_zones_args *args) +{ + return nvme_ns_report_zones(disk->private_data, sector, nr_zones, args); +} +#else +#define nvme_report_zones NULL +#endif /* CONFIG_BLK_DEV_ZONED */ + +const struct block_device_operations nvme_bdev_ops = { .owner = THIS_MODULE, .ioctl = nvme_ioctl, - .compat_ioctl = nvme_compat_ioctl, + .compat_ioctl = blkdev_compat_ptr_ioctl, .open = nvme_open, .release = nvme_release, .getgeo = nvme_getgeo, - .revalidate_disk= nvme_revalidate_disk, + .get_unique_id = nvme_get_unique_id, + .report_zones = nvme_report_zones, .pr_ops = &nvme_pr_ops, }; -static int nvme_wait_ready(struct nvme_ctrl *ctrl, u64 cap, bool enabled) +static int nvme_wait_ready(struct nvme_ctrl *ctrl, u32 mask, u32 val, + u32 timeout, const char *op) { - unsigned long timeout = - ((NVME_CAP_TIMEOUT(cap) + 1) * HZ / 2) + jiffies; - u32 csts, bit = enabled ? NVME_CSTS_RDY : 0; + unsigned long timeout_jiffies = jiffies + timeout * HZ; + u32 csts; int ret; while ((ret = ctrl->ops->reg_read32(ctrl, NVME_REG_CSTS, &csts)) == 0) { if (csts == ~0) return -ENODEV; - if ((csts & NVME_CSTS_RDY) == bit) + if ((csts & mask) == val) break; - msleep(100); + usleep_range(1000, 2000); if (fatal_signal_pending(current)) return -EINTR; - if (time_after(jiffies, timeout)) { + if (time_after(jiffies, timeout_jiffies)) { dev_err(ctrl->device, - "Device not ready; aborting %s\n", enabled ? - "initialisation" : "reset"); + "Device not ready; aborting %s, CSTS=0x%x\n", + op, csts); return -ENODEV; } } @@ -1402,233 +2646,312 @@ static int nvme_wait_ready(struct nvme_ctrl *ctrl, u64 cap, bool enabled) return ret; } -/* - * If the device has been passed off to us in an enabled state, just clear - * the enabled bit. The spec says we should set the 'shutdown notification - * bits', but doing so may cause the device to complete commands to the - * admin queue ... and we don't know what memory that might be pointing at! - */ -int nvme_disable_ctrl(struct nvme_ctrl *ctrl, u64 cap) +int nvme_disable_ctrl(struct nvme_ctrl *ctrl, bool shutdown) { int ret; ctrl->ctrl_config &= ~NVME_CC_SHN_MASK; - ctrl->ctrl_config &= ~NVME_CC_ENABLE; + if (shutdown) + ctrl->ctrl_config |= NVME_CC_SHN_NORMAL; + else + ctrl->ctrl_config &= ~NVME_CC_ENABLE; ret = ctrl->ops->reg_write32(ctrl, NVME_REG_CC, ctrl->ctrl_config); if (ret) return ret; + if (shutdown) { + return nvme_wait_ready(ctrl, NVME_CSTS_SHST_MASK, + NVME_CSTS_SHST_CMPLT, + ctrl->shutdown_timeout, "shutdown"); + } if (ctrl->quirks & NVME_QUIRK_DELAY_BEFORE_CHK_RDY) msleep(NVME_QUIRK_DELAY_AMOUNT); - - return nvme_wait_ready(ctrl, cap, false); + return nvme_wait_ready(ctrl, NVME_CSTS_RDY, 0, + (NVME_CAP_TIMEOUT(ctrl->cap) + 1) / 2, "reset"); } EXPORT_SYMBOL_GPL(nvme_disable_ctrl); -int nvme_enable_ctrl(struct nvme_ctrl *ctrl, u64 cap) +int nvme_enable_ctrl(struct nvme_ctrl *ctrl) { - /* - * 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 dev_page_min = NVME_CAP_MPSMIN(cap) + 12, page_shift = 12; + unsigned dev_page_min; + u32 timeout; int ret; - if (page_shift < dev_page_min) { + ret = ctrl->ops->reg_read64(ctrl, NVME_REG_CAP, &ctrl->cap); + if (ret) { + dev_err(ctrl->device, "Reading CAP failed (%d)\n", ret); + return ret; + } + dev_page_min = NVME_CAP_MPSMIN(ctrl->cap) + 12; + + if (NVME_CTRL_PAGE_SHIFT < dev_page_min) { dev_err(ctrl->device, "Minimum device page size %u too large for host (%u)\n", - 1 << dev_page_min, 1 << page_shift); + 1 << dev_page_min, 1 << NVME_CTRL_PAGE_SHIFT); return -ENODEV; } - ctrl->page_size = 1 << page_shift; + if (NVME_CAP_CSS(ctrl->cap) & NVME_CAP_CSS_CSI) + ctrl->ctrl_config = NVME_CC_CSS_CSI; + else + ctrl->ctrl_config = NVME_CC_CSS_NVM; + + /* + * 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_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_CTRL_PAGE_SHIFT - 12) << NVME_CC_MPS_SHIFT; + 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; + ret = ctrl->ops->reg_write32(ctrl, NVME_REG_CC, ctrl->ctrl_config); + if (ret) + return ret; + + /* CAP value may change after initial CC write */ + ret = ctrl->ops->reg_read64(ctrl, NVME_REG_CAP, &ctrl->cap); + if (ret) + return ret; + + timeout = NVME_CAP_TIMEOUT(ctrl->cap); + if (ctrl->cap & NVME_CAP_CRMS_CRWMS) { + u32 crto, ready_timeout; + + ret = ctrl->ops->reg_read32(ctrl, NVME_REG_CRTO, &crto); + if (ret) { + dev_err(ctrl->device, "Reading CRTO failed (%d)\n", + ret); + return ret; + } + + /* + * CRTO should always be greater or equal to CAP.TO, but some + * devices are known to get this wrong. Use the larger of the + * two values. + */ + ready_timeout = NVME_CRTO_CRWMT(crto); + if (ready_timeout < timeout) + dev_warn_once(ctrl->device, "bad crto:%x cap:%llx\n", + crto, ctrl->cap); + else + timeout = ready_timeout; + } + + ctrl->ctrl_config |= NVME_CC_ENABLE; ret = ctrl->ops->reg_write32(ctrl, NVME_REG_CC, ctrl->ctrl_config); if (ret) return ret; - return nvme_wait_ready(ctrl, cap, true); + return nvme_wait_ready(ctrl, NVME_CSTS_RDY, NVME_CSTS_RDY, + (timeout + 1) / 2, "initialisation"); } EXPORT_SYMBOL_GPL(nvme_enable_ctrl); -int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl) +static int nvme_configure_timestamp(struct nvme_ctrl *ctrl) { - unsigned long timeout = jiffies + (shutdown_timeout * HZ); - u32 csts; + __le64 ts; int ret; - ctrl->ctrl_config &= ~NVME_CC_SHN_MASK; - ctrl->ctrl_config |= NVME_CC_SHN_NORMAL; + if (!(ctrl->oncs & NVME_CTRL_ONCS_TIMESTAMP)) + return 0; - ret = ctrl->ops->reg_write32(ctrl, NVME_REG_CC, ctrl->ctrl_config); + 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) - return ret; + dev_warn_once(ctrl->device, + "could not set timestamp (%d)\n", ret); + return ret; +} - while ((ret = ctrl->ops->reg_read32(ctrl, NVME_REG_CSTS, &csts)) == 0) { - if ((csts & NVME_CSTS_SHST_MASK) == NVME_CSTS_SHST_CMPLT) - break; +static int nvme_configure_host_options(struct nvme_ctrl *ctrl) +{ + struct nvme_feat_host_behavior *host; + u8 acre = 0, lbafee = 0; + int ret; - msleep(100); - if (fatal_signal_pending(current)) - return -EINTR; - if (time_after(jiffies, timeout)) { - dev_err(ctrl->device, - "Device shutdown incomplete; abort shutdown\n"); - return -ENODEV; - } - } + /* Don't bother enabling the feature if retry delay is not reported */ + if (ctrl->crdt[0]) + acre = NVME_ENABLE_ACRE; + if (ctrl->ctratt & NVME_CTRL_ATTR_ELBAS) + lbafee = NVME_ENABLE_LBAFEE; + + if (!acre && !lbafee) + return 0; + host = kzalloc(sizeof(*host), GFP_KERNEL); + if (!host) + return 0; + + host->acre = acre; + host->lbafee = lbafee; + ret = nvme_set_features(ctrl, NVME_FEAT_HOST_BEHAVIOR, 0, + host, sizeof(*host), NULL); + kfree(host); return ret; } -EXPORT_SYMBOL_GPL(nvme_shutdown_ctrl); -static void nvme_set_queue_limits(struct nvme_ctrl *ctrl, - struct request_queue *q) +/* + * The function checks whether the given total (exlat + enlat) latency of + * a power state allows the latter to be used as an APST transition target. + * It does so by comparing the latency to the primary and secondary latency + * tolerances defined by module params. If there's a match, the corresponding + * timeout value is returned and the matching tolerance index (1 or 2) is + * reported. + */ +static bool nvme_apst_get_transition_time(u64 total_latency, + u64 *transition_time, unsigned *last_index) { - bool vwc = false; - - if (ctrl->max_hw_sectors) { - u32 max_segments = - (ctrl->max_hw_sectors / (ctrl->page_size >> 9)) + 1; - - blk_queue_max_hw_sectors(q, ctrl->max_hw_sectors); - blk_queue_max_segments(q, min_t(u32, max_segments, USHRT_MAX)); + if (total_latency <= apst_primary_latency_tol_us) { + if (*last_index == 1) + return false; + *last_index = 1; + *transition_time = apst_primary_timeout_ms; + return true; + } + if (apst_secondary_timeout_ms && + total_latency <= apst_secondary_latency_tol_us) { + if (*last_index <= 2) + return false; + *last_index = 2; + *transition_time = apst_secondary_timeout_ms; + return true; } - if (ctrl->quirks & NVME_QUIRK_STRIPE_SIZE) - blk_queue_chunk_sectors(q, ctrl->max_hw_sectors); - blk_queue_virt_boundary(q, ctrl->page_size - 1); - if (ctrl->vwc & NVME_CTRL_VWC_PRESENT) - vwc = true; - blk_queue_write_cache(q, vwc, vwc); + return false; } -static void nvme_configure_apst(struct nvme_ctrl *ctrl) +/* + * APST (Autonomous Power State Transition) lets us program a table of power + * state transitions that the controller will perform automatically. + * + * Depending on module params, one of the two supported techniques will be used: + * + * - If the parameters provide explicit timeouts and tolerances, they will be + * used to build a table with up to 2 non-operational states to transition to. + * The default parameter values were selected based on the values used by + * Microsoft's and Intel's NVMe drivers. Yet, since we don't implement dynamic + * regeneration of the APST table in the event of switching between external + * and battery power, the timeouts and tolerances reflect a compromise + * between values used by Microsoft for AC and battery scenarios. + * - If not, we'll configure the table with a simple heuristic: we are willing + * to spend at most 2% of the time transitioning between power states. + * Therefore, when running in any given state, we will enter the next + * lower-power non-operational state after waiting 50 * (enlat + exlat) + * microseconds, as long as that state's exit latency is under the requested + * maximum latency. + * + * We will not autonomously enter any non-operational state for which the total + * latency exceeds ps_max_latency_us. + * + * Users can set ps_max_latency_us to zero to turn off APST. + */ +static int nvme_configure_apst(struct nvme_ctrl *ctrl) { - /* - * APST (Autonomous Power State Transition) lets us program a - * table of power state transitions that the controller will - * perform automatically. We configure it with a simple - * heuristic: we are willing to spend at most 2% of the time - * transitioning between power states. Therefore, when running - * in any given state, we will enter the next lower-power - * non-operational state after waiting 50 * (enlat + exlat) - * microseconds, as long as that state's exit latency is under - * the requested maximum latency. - * - * We will not autonomously enter any non-operational state for - * which the total latency exceeds ps_max_latency_us. Users - * can set ps_max_latency_us to zero to turn off APST. - */ - - unsigned apste; struct nvme_feat_auto_pst *table; + unsigned apste = 0; u64 max_lat_us = 0; + __le64 target = 0; int max_ps = -1; + int state; int ret; + unsigned last_lt_index = UINT_MAX; /* * If APST isn't supported or if we haven't been initialized yet, * 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->apst_enabled || ctrl->ps_max_latency_us == 0) { /* Turn off APST. */ - apste = 0; dev_dbg(ctrl->device, "APST disabled\n"); - } else { - __le64 target = cpu_to_le64(0); - int state; + goto done; + } + + /* + * Walk through all states from lowest- to highest-power. + * According to the spec, lower-numbered states use more power. NPSS, + * despite the name, is the index of the lowest-power state, not the + * number of states. + */ + for (state = (int)ctrl->npss; state >= 0; state--) { + u64 total_latency_us, exit_latency_us, transition_ms; + + if (target) + table->entries[state] = target; /* - * Walk through all states from lowest- to highest-power. - * According to the spec, lower-numbered states use more - * power. NPSS, despite the name, is the index of the - * lowest-power state, not the number of states. + * Don't allow transitions to the deepest state if it's quirked + * off. */ - for (state = (int)ctrl->npss; state >= 0; state--) { - u64 total_latency_us, exit_latency_us, transition_ms; + if (state == ctrl->npss && + (ctrl->quirks & NVME_QUIRK_NO_DEEPEST_PS)) + continue; - if (target) - table->entries[state] = target; + /* + * Is this state a useful non-operational state for higher-power + * states to autonomously transition to? + */ + if (!(ctrl->psd[state].flags & NVME_PS_FLAGS_NON_OP_STATE)) + continue; - /* - * Don't allow transitions to the deepest state - * if it's quirked off. - */ - if (state == ctrl->npss && - (ctrl->quirks & NVME_QUIRK_NO_DEEPEST_PS)) - continue; + exit_latency_us = (u64)le32_to_cpu(ctrl->psd[state].exit_lat); + if (exit_latency_us > ctrl->ps_max_latency_us) + continue; - /* - * Is this state a useful non-operational state for - * higher-power states to autonomously transition to? - */ - if (!(ctrl->psd[state].flags & - NVME_PS_FLAGS_NON_OP_STATE)) - continue; + total_latency_us = exit_latency_us + + le32_to_cpu(ctrl->psd[state].entry_lat); - exit_latency_us = - (u64)le32_to_cpu(ctrl->psd[state].exit_lat); - if (exit_latency_us > ctrl->ps_max_latency_us) + /* + * This state is good. It can be used as the APST idle target + * for higher power states. + */ + if (apst_primary_timeout_ms && apst_primary_latency_tol_us) { + if (!nvme_apst_get_transition_time(total_latency_us, + &transition_ms, &last_lt_index)) continue; - - total_latency_us = - exit_latency_us + - le32_to_cpu(ctrl->psd[state].entry_lat); - - /* - * This state is good. Use it as the APST idle - * target for higher power states. - */ + } else { transition_ms = total_latency_us + 19; do_div(transition_ms, 20); if (transition_ms > (1 << 24) - 1) transition_ms = (1 << 24) - 1; - - target = cpu_to_le64((state << 3) | - (transition_ms << 8)); - - if (max_ps == -1) - max_ps = state; - - if (total_latency_us > max_lat_us) - max_lat_us = total_latency_us; } - apste = 1; - - if (max_ps == -1) { - dev_dbg(ctrl->device, "APST enabled but no non-operational states are available\n"); - } else { - dev_dbg(ctrl->device, "APST enabled: max PS = %d, max round-trip latency = %lluus, table = %*phN\n", - max_ps, max_lat_us, (int)sizeof(*table), table); - } + target = cpu_to_le64((state << 3) | (transition_ms << 8)); + if (max_ps == -1) + max_ps = state; + if (total_latency_us > max_lat_us) + max_lat_us = total_latency_us; } + if (max_ps == -1) + dev_dbg(ctrl->device, "APST enabled but no non-operational states are available\n"); + else + dev_dbg(ctrl->device, "APST enabled: max PS = %d, max round-trip latency = %lluus, table = %*phN\n", + max_ps, max_lat_us, (int)sizeof(*table), table); + apste = 1; + +done: ret = nvme_set_features(ctrl, NVME_FEAT_AUTO_PST, apste, table, sizeof(*table), NULL); if (ret) 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) @@ -1648,7 +2971,8 @@ static void nvme_set_latency_tolerance(struct device *dev, s32 val) if (ctrl->ps_max_latency_us != latency) { ctrl->ps_max_latency_us = latency; - nvme_configure_apst(ctrl); + if (nvme_ctrl_state(ctrl) == NVME_CTRL_LIVE) + nvme_configure_apst(ctrl); } } @@ -1673,6 +2997,44 @@ static const struct nvme_core_quirk_entry core_quirks[] = { .vid = 0x1179, .mn = "THNSF5256GPUK TOSHIBA", .quirks = NVME_QUIRK_NO_APST, + }, + { + /* + * This LiteON CL1-3D*-Q11 firmware version has a race + * condition associated with actions related to suspend to idle + * LiteON has resolved the problem in future firmware + */ + .vid = 0x14a4, + .fr = "22301111", + .quirks = NVME_QUIRK_SIMPLE_SUSPEND, + }, + { + /* + * This Kioxia CD6-V Series / HPE PE8030 device times out and + * aborts I/O during any load, but more easily reproducible + * with discards (fstrim). + * + * The device is left in a state where it is also not possible + * to use "nvme set-feature" to disable APST, but booting with + * nvme_core.default_ps_max_latency=0 works. + */ + .vid = 0x1e0f, + .mn = "KCD6XVUL6T40", + .quirks = NVME_QUIRK_NO_APST, + }, + { + /* + * The external Samsung X5 SSD fails initialization without a + * delay before checking if it is ready and has a whole set of + * other problems. To make this even more interesting, it + * shares the PCI ID with internal Samsung 970 Evo Plus that + * does not need or want these quirks. + */ + .vid = 0x144d, + .mn = "Samsung Portable SSD X5", + .quirks = NVME_QUIRK_DELAY_BEFORE_CHK_RDY | + NVME_QUIRK_NO_DEEPEST_PS | + NVME_QUIRK_IGNORE_DEV_SUBNQN, } }; @@ -1705,59 +3067,464 @@ 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) +static void nvme_init_subnqn(struct nvme_subsystem *subsys, 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->quirks & NVME_QUIRK_IGNORE_DEV_SUBNQN)) { + nqnlen = strnlen(id->subnqn, NVMF_NQN_SIZE); + if (nqnlen > 0 && nqnlen < NVMF_NQN_SIZE) { + strscpy(subsys->subnqn, id->subnqn, NVMF_NQN_SIZE); + return; + } - if (ctrl->vs >= NVME_VS(1, 2, 1)) - dev_warn(ctrl->device, "missing or invalid SUBNQN field.\n"); + 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", + /* + * Generate a "fake" NQN similar to the one in Section 4.5 of the NVMe + * Base Specification 2.0. It is slightly different from the format + * specified there due to historic reasons, and we can't change it now. + */ + off = snprintf(subsys->subnqn, NVMF_NQN_SIZE, + "nqn.2014.08.org.nvmexpress:%04x%04x", le16_to_cpu(id->vid), le16_to_cpu(id->ssvid)); - memcpy(ctrl->subnqn + off, id->sn, sizeof(id->sn)); + memcpy(subsys->subnqn + off, id->sn, sizeof(id->sn)); off += sizeof(id->sn); - memcpy(ctrl->subnqn + off, id->mn, sizeof(id->mn)); + memcpy(subsys->subnqn + off, id->mn, sizeof(id->mn)); off += sizeof(id->mn); - memset(ctrl->subnqn + off, 0, sizeof(ctrl->subnqn) - off); + memset(subsys->subnqn + off, 0, sizeof(subsys->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 - * the admin queue is fully up and running. - */ -int nvme_init_identify(struct nvme_ctrl *ctrl) +static void nvme_release_subsystem(struct device *dev) { - struct nvme_id_ctrl *id; - u64 cap; - int ret, page_shift; - u32 max_hw_sectors; - bool prev_apst_enabled; + struct nvme_subsystem *subsys = + container_of(dev, struct nvme_subsystem, dev); - ret = ctrl->ops->reg_read32(ctrl, NVME_REG_VS, &ctrl->vs); + if (subsys->instance >= 0) + ida_free(&nvme_instance_ida, subsys->instance); + kfree(subsys); +} + +static void nvme_destroy_subsystem(struct kref *ref) +{ + struct nvme_subsystem *subsys = + container_of(ref, struct nvme_subsystem, ref); + + mutex_lock(&nvme_subsystems_lock); + list_del(&subsys->entry); + mutex_unlock(&nvme_subsystems_lock); + + ida_destroy(&subsys->ns_ida); + device_del(&subsys->dev); + put_device(&subsys->dev); +} + +static void nvme_put_subsystem(struct nvme_subsystem *subsys) +{ + kref_put(&subsys->ref, nvme_destroy_subsystem); +} + +static struct nvme_subsystem *__nvme_find_get_subsystem(const char *subsysnqn) +{ + struct nvme_subsystem *subsys; + + lockdep_assert_held(&nvme_subsystems_lock); + + /* + * Fail matches for discovery subsystems. This results + * in each discovery controller bound to a unique subsystem. + * This avoids issues with validating controller values + * that can only be true when there is a single unique subsystem. + * There may be multiple and completely independent entities + * that provide discovery controllers. + */ + if (!strcmp(subsysnqn, NVME_DISC_SUBSYS_NAME)) + return NULL; + + list_for_each_entry(subsys, &nvme_subsystems, entry) { + if (strcmp(subsys->subnqn, subsysnqn)) + continue; + if (!kref_get_unless_zero(&subsys->ref)) + continue; + return subsys; + } + + return NULL; +} + +static inline bool nvme_discovery_ctrl(struct nvme_ctrl *ctrl) +{ + return ctrl->opts && ctrl->opts->discovery_nqn; +} + +static inline bool nvme_admin_ctrl(struct nvme_ctrl *ctrl) +{ + return ctrl->cntrltype == NVME_CTRL_ADMIN; +} + +static inline bool nvme_is_io_ctrl(struct nvme_ctrl *ctrl) +{ + return !nvme_discovery_ctrl(ctrl) && !nvme_admin_ctrl(ctrl); +} + +static bool nvme_validate_cntlid(struct nvme_subsystem *subsys, + struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) +{ + struct nvme_ctrl *tmp; + + lockdep_assert_held(&nvme_subsystems_lock); + + list_for_each_entry(tmp, &subsys->ctrls, subsys_entry) { + if (nvme_state_terminal(tmp)) + continue; + + if (tmp->cntlid == ctrl->cntlid) { + dev_err(ctrl->device, + "Duplicate cntlid %u with %s, subsys %s, rejecting\n", + ctrl->cntlid, dev_name(tmp->device), + subsys->subnqn); + return false; + } + + if ((id->cmic & NVME_CTRL_CMIC_MULTI_CTRL) || + nvme_discovery_ctrl(ctrl)) + continue; + + dev_err(ctrl->device, + "Subsystem does not support multiple controllers\n"); + return false; + } + + return true; +} + +static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) +{ + struct nvme_subsystem *subsys, *found; + int ret; + + subsys = kzalloc(sizeof(*subsys), GFP_KERNEL); + if (!subsys) + return -ENOMEM; + + subsys->instance = -1; + mutex_init(&subsys->lock); + kref_init(&subsys->ref); + INIT_LIST_HEAD(&subsys->ctrls); + INIT_LIST_HEAD(&subsys->nsheads); + nvme_init_subnqn(subsys, ctrl, id); + memcpy(subsys->serial, id->sn, sizeof(subsys->serial)); + memcpy(subsys->model, id->mn, sizeof(subsys->model)); + subsys->vendor_id = le16_to_cpu(id->vid); + subsys->cmic = id->cmic; + subsys->awupf = le16_to_cpu(id->awupf); + + /* Versions prior to 1.4 don't necessarily report a valid type */ + if (id->cntrltype == NVME_CTRL_DISC || + !strcmp(subsys->subnqn, NVME_DISC_SUBSYS_NAME)) + subsys->subtype = NVME_NQN_DISC; + else + subsys->subtype = NVME_NQN_NVME; + + if (nvme_discovery_ctrl(ctrl) && subsys->subtype != NVME_NQN_DISC) { + dev_err(ctrl->device, + "Subsystem %s is not a discovery controller", + subsys->subnqn); + kfree(subsys); + return -EINVAL; + } + nvme_mpath_default_iopolicy(subsys); + + subsys->dev.class = &nvme_subsys_class; + subsys->dev.release = nvme_release_subsystem; + subsys->dev.groups = nvme_subsys_attrs_groups; + dev_set_name(&subsys->dev, "nvme-subsys%d", ctrl->instance); + device_initialize(&subsys->dev); + + mutex_lock(&nvme_subsystems_lock); + found = __nvme_find_get_subsystem(subsys->subnqn); + if (found) { + put_device(&subsys->dev); + subsys = found; + + if (!nvme_validate_cntlid(subsys, ctrl, id)) { + ret = -EINVAL; + goto out_put_subsystem; + } + } else { + ret = device_add(&subsys->dev); + if (ret) { + dev_err(ctrl->device, + "failed to register subsystem device.\n"); + put_device(&subsys->dev); + goto out_unlock; + } + ida_init(&subsys->ns_ida); + list_add_tail(&subsys->entry, &nvme_subsystems); + } + + ret = sysfs_create_link(&subsys->dev.kobj, &ctrl->device->kobj, + dev_name(ctrl->device)); if (ret) { - dev_err(ctrl->device, "Reading VS failed (%d)\n", ret); - return ret; + dev_err(ctrl->device, + "failed to create sysfs link from subsystem.\n"); + goto out_put_subsystem; } - ret = ctrl->ops->reg_read64(ctrl, NVME_REG_CAP, &cap); + if (!found) + subsys->instance = ctrl->instance; + ctrl->subsys = subsys; + list_add_tail(&ctrl->subsys_entry, &subsys->ctrls); + mutex_unlock(&nvme_subsystems_lock); + return 0; + +out_put_subsystem: + nvme_put_subsystem(subsys); +out_unlock: + mutex_unlock(&nvme_subsystems_lock); + return ret; +} + +static int nvme_get_log_lsi(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, + u8 lsp, u8 csi, void *log, size_t size, u64 offset, u16 lsi) +{ + struct nvme_command c = { }; + u32 dwlen = nvme_bytes_to_numd(size); + + c.get_log_page.opcode = nvme_admin_get_log_page; + c.get_log_page.nsid = cpu_to_le32(nsid); + c.get_log_page.lid = log_page; + c.get_log_page.lsp = lsp; + c.get_log_page.numdl = cpu_to_le16(dwlen & ((1 << 16) - 1)); + c.get_log_page.numdu = cpu_to_le16(dwlen >> 16); + c.get_log_page.lpol = cpu_to_le32(lower_32_bits(offset)); + c.get_log_page.lpou = cpu_to_le32(upper_32_bits(offset)); + c.get_log_page.csi = csi; + c.get_log_page.lsi = cpu_to_le16(lsi); + + return nvme_submit_sync_cmd(ctrl->admin_q, &c, log, size); +} + +int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp, u8 csi, + void *log, size_t size, u64 offset) +{ + return nvme_get_log_lsi(ctrl, nsid, log_page, lsp, csi, log, size, + offset, 0); +} + +static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi, + struct nvme_effects_log **log) +{ + struct nvme_effects_log *old, *cel = xa_load(&ctrl->cels, csi); + int ret; + + if (cel) + goto out; + + cel = kzalloc(sizeof(*cel), GFP_KERNEL); + if (!cel) + return -ENOMEM; + + ret = nvme_get_log(ctrl, 0x00, NVME_LOG_CMD_EFFECTS, 0, csi, + cel, sizeof(*cel), 0); if (ret) { - dev_err(ctrl->device, "Reading CAP failed (%d)\n", ret); + kfree(cel); return ret; } - page_shift = NVME_CAP_MPSMIN(cap) + 12; - if (ctrl->vs >= NVME_VS(1, 1, 0)) - ctrl->subsystem = NVME_CAP_NSSRC(cap); + old = xa_store(&ctrl->cels, csi, cel, GFP_KERNEL); + if (xa_is_err(old)) { + kfree(cel); + return xa_err(old); + } +out: + *log = cel; + return 0; +} + +static inline u32 nvme_mps_to_sectors(struct nvme_ctrl *ctrl, u32 units) +{ + u32 page_shift = NVME_CAP_MPSMIN(ctrl->cap) + 12, val; + + if (check_shl_overflow(1U, units + page_shift - 9, &val)) + return UINT_MAX; + return val; +} + +static int nvme_init_non_mdts_limits(struct nvme_ctrl *ctrl) +{ + struct nvme_command c = { }; + struct nvme_id_ctrl_nvm *id; + int ret; + + /* + * Even though NVMe spec explicitly states that MDTS is not applicable + * to the write-zeroes, we are cautious and limit the size to the + * controllers max_hw_sectors value, which is based on the MDTS field + * and possibly other limiting factors. + */ + if ((ctrl->oncs & NVME_CTRL_ONCS_WRITE_ZEROES) && + !(ctrl->quirks & NVME_QUIRK_DISABLE_WRITE_ZEROES)) + ctrl->max_zeroes_sectors = ctrl->max_hw_sectors; + else + ctrl->max_zeroes_sectors = 0; + + if (!nvme_is_io_ctrl(ctrl) || + !nvme_id_cns_ok(ctrl, NVME_ID_CNS_CS_CTRL) || + test_bit(NVME_CTRL_SKIP_ID_CNS_CS, &ctrl->flags)) + return 0; + + id = kzalloc(sizeof(*id), GFP_KERNEL); + if (!id) + return -ENOMEM; + + c.identify.opcode = nvme_admin_identify; + c.identify.cns = NVME_ID_CNS_CS_CTRL; + c.identify.csi = NVME_CSI_NVM; + + ret = nvme_submit_sync_cmd(ctrl->admin_q, &c, id, sizeof(*id)); + if (ret) + goto free_data; + + ctrl->dmrl = id->dmrl; + ctrl->dmrsl = le32_to_cpu(id->dmrsl); + if (id->wzsl) + ctrl->max_zeroes_sectors = nvme_mps_to_sectors(ctrl, id->wzsl); + +free_data: + if (ret > 0) + set_bit(NVME_CTRL_SKIP_ID_CNS_CS, &ctrl->flags); + kfree(id); + return ret; +} + +static int nvme_init_effects_log(struct nvme_ctrl *ctrl, + u8 csi, struct nvme_effects_log **log) +{ + struct nvme_effects_log *effects, *old; + + effects = kzalloc(sizeof(*effects), GFP_KERNEL); + if (!effects) + return -ENOMEM; + + old = xa_store(&ctrl->cels, csi, effects, GFP_KERNEL); + if (xa_is_err(old)) { + kfree(effects); + return xa_err(old); + } + + *log = effects; + return 0; +} + +static void nvme_init_known_nvm_effects(struct nvme_ctrl *ctrl) +{ + struct nvme_effects_log *log = ctrl->effects; + + log->acs[nvme_admin_format_nvm] |= cpu_to_le32(NVME_CMD_EFFECTS_LBCC | + NVME_CMD_EFFECTS_NCC | + NVME_CMD_EFFECTS_CSE_MASK); + log->acs[nvme_admin_sanitize_nvm] |= cpu_to_le32(NVME_CMD_EFFECTS_LBCC | + NVME_CMD_EFFECTS_CSE_MASK); + + /* + * The spec says the result of a security receive command depends on + * the previous security send command. As such, many vendors log this + * command as one to submitted only when no other commands to the same + * namespace are outstanding. The intention is to tell the host to + * prevent mixing security send and receive. + * + * This driver can only enforce such exclusive access against IO + * queues, though. We are not readily able to enforce such a rule for + * two commands to the admin queue, which is the only queue that + * matters for this command. + * + * Rather than blindly freezing the IO queues for this effect that + * doesn't even apply to IO, mask it off. + */ + log->acs[nvme_admin_security_recv] &= cpu_to_le32(~NVME_CMD_EFFECTS_CSE_MASK); + + log->iocs[nvme_cmd_write] |= cpu_to_le32(NVME_CMD_EFFECTS_LBCC); + log->iocs[nvme_cmd_write_zeroes] |= cpu_to_le32(NVME_CMD_EFFECTS_LBCC); + log->iocs[nvme_cmd_write_uncor] |= cpu_to_le32(NVME_CMD_EFFECTS_LBCC); +} + +static int nvme_init_effects(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) +{ + int ret = 0; + + if (ctrl->effects) + return 0; + + if (id->lpa & NVME_CTRL_LPA_CMD_EFFECTS_LOG) { + ret = nvme_get_effects_log(ctrl, NVME_CSI_NVM, &ctrl->effects); + if (ret < 0) + return ret; + } + + if (!ctrl->effects) { + ret = nvme_init_effects_log(ctrl, NVME_CSI_NVM, &ctrl->effects); + if (ret < 0) + return ret; + } + + nvme_init_known_nvm_effects(ctrl); + return 0; +} + +static int nvme_check_ctrl_fabric_info(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) +{ + /* + * In fabrics we need to verify the cntlid matches the + * admin connect + */ + if (ctrl->cntlid != le16_to_cpu(id->cntlid)) { + dev_err(ctrl->device, + "Mismatching cntlid: Connect %u vs Identify %u, rejecting\n", + ctrl->cntlid, le16_to_cpu(id->cntlid)); + return -EINVAL; + } + + if (!nvme_discovery_ctrl(ctrl) && !ctrl->kas) { + dev_err(ctrl->device, + "keep-alive support is mandatory for fabrics\n"); + return -EINVAL; + } + + if (nvme_is_io_ctrl(ctrl) && ctrl->ioccsz < 4) { + dev_err(ctrl->device, + "I/O queue command capsule supported size %d < 4\n", + ctrl->ioccsz); + return -EINVAL; + } + + if (nvme_is_io_ctrl(ctrl) && ctrl->iorcsz < 1) { + dev_err(ctrl->device, + "I/O queue response capsule supported size %d < 1\n", + ctrl->iorcsz); + return -EINVAL; + } + + if (!ctrl->maxcmd) { + dev_warn(ctrl->device, + "Firmware bug: maximum outstanding commands is 0\n"); + ctrl->maxcmd = ctrl->sqsize + 1; + } + + return 0; +} + +static int nvme_init_identify(struct nvme_ctrl *ctrl) +{ + struct queue_limits lim; + struct nvme_id_ctrl *id; + u32 max_hw_sectors; + bool prev_apst_enabled; + int ret; ret = nvme_identify_ctrl(ctrl, &id); if (ret) { @@ -1765,9 +3532,12 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) return -EIO; } - nvme_init_subnqn(ctrl, id); + if (!(ctrl->ops->flags & NVME_F_FABRICS)) + ctrl->cntlid = le16_to_cpu(id->cntlid); if (!ctrl->identified) { + unsigned int i; + /* * Check for quirks. Quirk can depend on firmware version, * so, in principle, the set of quirks present can change @@ -1776,39 +3546,74 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) * the device, but we'd have to make sure that the driver * behaves intelligently if the quirks change. */ - - int i; - for (i = 0; i < ARRAY_SIZE(core_quirks); i++) { if (quirk_matches(id, &core_quirks[i])) ctrl->quirks |= core_quirks[i].quirks; } + + ret = nvme_init_subsystem(ctrl, id); + if (ret) + goto out_free; + + ret = nvme_init_effects(ctrl, id); + if (ret) + goto out_free; } + memcpy(ctrl->subsys->firmware_rev, id->fr, + sizeof(ctrl->subsys->firmware_rev)); if (force_apst && (ctrl->quirks & NVME_QUIRK_NO_DEEPEST_PS)) { 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; } + ctrl->crdt[0] = le16_to_cpu(id->crdt1); + ctrl->crdt[1] = le16_to_cpu(id->crdt2); + ctrl->crdt[2] = le16_to_cpu(id->crdt3); + ctrl->oacs = le16_to_cpu(id->oacs); - ctrl->vid = le16_to_cpu(id->vid); - ctrl->oncs = le16_to_cpup(&id->oncs); + ctrl->oncs = le16_to_cpu(id->oncs); + ctrl->mtfa = le16_to_cpu(id->mtfa); + ctrl->oaes = le32_to_cpu(id->oaes); + ctrl->wctemp = le16_to_cpu(id->wctemp); + ctrl->cctemp = le16_to_cpu(id->cctemp); + atomic_set(&ctrl->abort_limit, id->acl + 1); ctrl->vwc = id->vwc; - ctrl->cntlid = le16_to_cpup(&id->cntlid); - memcpy(ctrl->serial, id->sn, sizeof(id->sn)); - memcpy(ctrl->model, id->mn, sizeof(id->mn)); - memcpy(ctrl->firmware_rev, id->fr, sizeof(id->fr)); if (id->mdts) - max_hw_sectors = 1 << (id->mdts + page_shift - 9); + max_hw_sectors = nvme_mps_to_sectors(ctrl, id->mdts); else max_hw_sectors = UINT_MAX; ctrl->max_hw_sectors = min_not_zero(ctrl->max_hw_sectors, max_hw_sectors); - nvme_set_queue_limits(ctrl, ctrl->admin_q); + lim = queue_limits_start_update(ctrl->admin_q); + nvme_set_ctrl_limits(ctrl, &lim, true); + ret = queue_limits_commit_update(ctrl->admin_q, &lim); + if (ret) + goto out_free; + ctrl->sgls = le32_to_cpu(id->sgls); ctrl->kas = le16_to_cpu(id->kas); + ctrl->max_namespaces = le32_to_cpu(id->mnan); + ctrl->ctratt = le32_to_cpu(id->ctratt); + + ctrl->cntrltype = id->cntrltype; + ctrl->dctype = id->dctype; + + if (id->rtd3e) { + /* us -> s */ + u32 transition_time = le32_to_cpu(id->rtd3e) / USEC_PER_SEC; + + ctrl->shutdown_timeout = clamp_t(unsigned int, transition_time, + shutdown_timeout, 60); + + if (ctrl->shutdown_timeout != shutdown_timeout) + dev_info(ctrl->device, + "D3 entry latency set to %u seconds\n", + ctrl->shutdown_timeout); + } else + ctrl->shutdown_timeout = shutdown_timeout; ctrl->npss = id->npss; ctrl->apsta = id->apsta; @@ -1831,127 +3636,127 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) ctrl->iorcsz = le32_to_cpu(id->iorcsz); ctrl->maxcmd = le16_to_cpu(id->maxcmd); - /* - * In fabrics we need to verify the cntlid matches the - * admin connect - */ - if (ctrl->cntlid != le16_to_cpu(id->cntlid)) - ret = -EINVAL; - - if (!ctrl->opts->discovery_nqn && !ctrl->kas) { - dev_err(ctrl->device, - "keep-alive support is mandatory for fabrics\n"); - ret = -EINVAL; - } + ret = nvme_check_ctrl_fabric_info(ctrl, id); + if (ret) + 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); + ret = nvme_mpath_init_identify(ctrl, id); + if (ret < 0) + goto out_free; if (ctrl->apst_enabled && !prev_apst_enabled) dev_pm_qos_expose_latency_tolerance(ctrl->device); else if (!ctrl->apst_enabled && prev_apst_enabled) dev_pm_qos_hide_latency_tolerance(ctrl->device); - - nvme_configure_apst(ctrl); - nvme_configure_directives(ctrl); - - ctrl->identified = true; - +out_free: + kfree(id); return ret; } -EXPORT_SYMBOL_GPL(nvme_init_identify); -static int nvme_dev_open(struct inode *inode, struct file *file) +/* + * Initialize the cached copies of the Identify data and various controller + * register in our nvme_ctrl structure. This should be called as soon as + * the admin queue is fully up and running. + */ +int nvme_init_ctrl_finish(struct nvme_ctrl *ctrl, bool was_suspended) { - struct nvme_ctrl *ctrl; - int instance = iminor(inode); - int ret = -ENODEV; - - spin_lock(&dev_list_lock); - list_for_each_entry(ctrl, &nvme_ctrl_list, node) { - if (ctrl->instance != instance) - continue; + int ret; - if (!ctrl->admin_q) { - ret = -EWOULDBLOCK; - break; - } - if (!kref_get_unless_zero(&ctrl->kref)) - break; - file->private_data = ctrl; - ret = 0; - break; + ret = ctrl->ops->reg_read32(ctrl, NVME_REG_VS, &ctrl->vs); + if (ret) { + dev_err(ctrl->device, "Reading VS failed (%d)\n", ret); + return ret; } - spin_unlock(&dev_list_lock); - return ret; -} + ctrl->sqsize = min_t(u16, NVME_CAP_MQES(ctrl->cap), ctrl->sqsize); -static int nvme_dev_release(struct inode *inode, struct file *file) -{ - nvme_put_ctrl(file->private_data); - return 0; -} + if (ctrl->vs >= NVME_VS(1, 1, 0)) + ctrl->subsystem = NVME_CAP_NSSRC(ctrl->cap); -static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp) -{ - struct nvme_ns *ns; - int ret; + ret = nvme_init_identify(ctrl); + if (ret) + return ret; - mutex_lock(&ctrl->namespaces_mutex); - if (list_empty(&ctrl->namespaces)) { - ret = -ENOTTY; - goto out_unlock; + if (nvme_admin_ctrl(ctrl)) { + /* + * An admin controller has one admin queue, but no I/O queues. + * Override queue_count so it only creates an admin queue. + */ + dev_dbg(ctrl->device, + "Subsystem %s is an administrative controller", + ctrl->subsys->subnqn); + ctrl->queue_count = 1; } - ns = list_first_entry(&ctrl->namespaces, struct nvme_ns, list); - if (ns != list_last_entry(&ctrl->namespaces, struct nvme_ns, list)) { - dev_warn(ctrl->device, - "NVME_IOCTL_IO_CMD not supported when multiple namespaces present!\n"); - ret = -EINVAL; - goto out_unlock; + ret = nvme_configure_apst(ctrl); + if (ret < 0) + return ret; + + ret = nvme_configure_timestamp(ctrl); + if (ret < 0) + return ret; + + ret = nvme_configure_host_options(ctrl); + if (ret < 0) + return ret; + + nvme_configure_opal(ctrl, was_suspended); + + if (!ctrl->identified && !nvme_discovery_ctrl(ctrl)) { + /* + * Do not return errors unless we are in a controller reset, + * the controller works perfectly fine without hwmon. + */ + ret = nvme_hwmon_init(ctrl); + if (ret == -EINTR) + return ret; } - dev_warn(ctrl->device, - "using deprecated NVME_IOCTL_IO_CMD ioctl on the char device!\n"); - kref_get(&ns->kref); - mutex_unlock(&ctrl->namespaces_mutex); + clear_bit(NVME_CTRL_DIRTY_CAPABILITY, &ctrl->flags); + ctrl->identified = true; - ret = nvme_user_cmd(ctrl, ns, argp); - nvme_put_ns(ns); - return ret; + nvme_start_keep_alive(ctrl); -out_unlock: - mutex_unlock(&ctrl->namespaces_mutex); - return ret; + return 0; } +EXPORT_SYMBOL_GPL(nvme_init_ctrl_finish); -static long nvme_dev_ioctl(struct file *file, unsigned int cmd, - unsigned long arg) +static int nvme_dev_open(struct inode *inode, struct file *file) { - struct nvme_ctrl *ctrl = file->private_data; - void __user *argp = (void __user *)arg; + struct nvme_ctrl *ctrl = + container_of(inode->i_cdev, struct nvme_ctrl, cdev); - switch (cmd) { - case NVME_IOCTL_ADMIN_CMD: - return nvme_user_cmd(ctrl, NULL, argp); - case NVME_IOCTL_IO_CMD: - return nvme_dev_user_cmd(ctrl, argp); - case NVME_IOCTL_RESET: - dev_warn(ctrl->device, "resetting controller\n"); - return nvme_reset_ctrl_sync(ctrl); - case NVME_IOCTL_SUBSYS_RESET: - return nvme_reset_subsystem(ctrl); - case NVME_IOCTL_RESCAN: - nvme_queue_scan(ctrl); - return 0; + switch (nvme_ctrl_state(ctrl)) { + case NVME_CTRL_LIVE: + break; default: - return -ENOTTY; + return -EWOULDBLOCK; + } + + nvme_get_ctrl(ctrl); + if (!try_module_get(ctrl->ops->module)) { + nvme_put_ctrl(ctrl); + return -EINVAL; } + + file->private_data = ctrl; + return 0; +} + +static int nvme_dev_release(struct inode *inode, struct file *file) +{ + struct nvme_ctrl *ctrl = + container_of(inode->i_cdev, struct nvme_ctrl, cdev); + + module_put(ctrl->ops->module); + nvme_put_ctrl(ctrl); + return 0; } static const struct file_operations nvme_dev_fops = { @@ -1959,533 +3764,790 @@ static const struct file_operations nvme_dev_fops = { .open = nvme_dev_open, .release = nvme_dev_release, .unlocked_ioctl = nvme_dev_ioctl, - .compat_ioctl = nvme_dev_ioctl, + .compat_ioctl = compat_ptr_ioctl, + .uring_cmd = nvme_dev_uring_cmd, }; -static ssize_t nvme_sysfs_reset(struct device *dev, - struct device_attribute *attr, const char *buf, - size_t count) +static struct nvme_ns_head *nvme_find_ns_head(struct nvme_ctrl *ctrl, + unsigned nsid) { - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - int ret; + struct nvme_ns_head *h; - ret = nvme_reset_ctrl_sync(ctrl); - if (ret < 0) - return ret; - return count; -} -static DEVICE_ATTR(reset_controller, S_IWUSR, NULL, nvme_sysfs_reset); + lockdep_assert_held(&ctrl->subsys->lock); -static ssize_t nvme_sysfs_rescan(struct device *dev, - struct device_attribute *attr, const char *buf, - size_t count) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + list_for_each_entry(h, &ctrl->subsys->nsheads, entry) { + /* + * Private namespaces can share NSIDs under some conditions. + * In that case we can't use the same ns_head for namespaces + * with the same NSID. + */ + if (h->ns_id != nsid || !nvme_is_unique_nsid(ctrl, h)) + continue; + if (nvme_tryget_ns_head(h)) + return h; + } - nvme_queue_scan(ctrl); - return count; + return NULL; } -static DEVICE_ATTR(rescan_controller, S_IWUSR, NULL, nvme_sysfs_rescan); -static ssize_t wwid_show(struct device *dev, struct device_attribute *attr, - char *buf) +static int nvme_subsys_check_duplicate_ids(struct nvme_subsystem *subsys, + struct nvme_ns_ids *ids) { - struct nvme_ns *ns = nvme_get_ns_from_dev(dev); - struct nvme_ctrl *ctrl = ns->ctrl; - int serial_len = sizeof(ctrl->serial); - int model_len = sizeof(ctrl->model); - - if (!uuid_is_null(&ns->uuid)) - return sprintf(buf, "uuid.%pU\n", &ns->uuid); + bool has_uuid = !uuid_is_null(&ids->uuid); + bool has_nguid = memchr_inv(ids->nguid, 0, sizeof(ids->nguid)); + bool has_eui64 = memchr_inv(ids->eui64, 0, sizeof(ids->eui64)); + struct nvme_ns_head *h; - if (memchr_inv(ns->nguid, 0, sizeof(ns->nguid))) - return sprintf(buf, "eui.%16phN\n", ns->nguid); + lockdep_assert_held(&subsys->lock); - if (memchr_inv(ns->eui, 0, sizeof(ns->eui))) - return sprintf(buf, "eui.%8phN\n", ns->eui); + list_for_each_entry(h, &subsys->nsheads, entry) { + if (has_uuid && uuid_equal(&ids->uuid, &h->ids.uuid)) + return -EINVAL; + if (has_nguid && + memcmp(&ids->nguid, &h->ids.nguid, sizeof(ids->nguid)) == 0) + return -EINVAL; + if (has_eui64 && + memcmp(&ids->eui64, &h->ids.eui64, sizeof(ids->eui64)) == 0) + return -EINVAL; + } - while (ctrl->serial[serial_len - 1] == ' ') - serial_len--; - while (ctrl->model[model_len - 1] == ' ') - model_len--; + return 0; +} - return sprintf(buf, "nvme.%04x-%*phN-%*phN-%08x\n", ctrl->vid, - serial_len, ctrl->serial, model_len, ctrl->model, ns->ns_id); +static void nvme_cdev_rel(struct device *dev) +{ + ida_free(&nvme_ns_chr_minor_ida, MINOR(dev->devt)); } -static DEVICE_ATTR(wwid, S_IRUGO, wwid_show, NULL); -static ssize_t nguid_show(struct device *dev, struct device_attribute *attr, - char *buf) +void nvme_cdev_del(struct cdev *cdev, struct device *cdev_device) { - struct nvme_ns *ns = nvme_get_ns_from_dev(dev); - return sprintf(buf, "%pU\n", ns->nguid); + cdev_device_del(cdev, cdev_device); + put_device(cdev_device); } -static DEVICE_ATTR(nguid, S_IRUGO, nguid_show, NULL); -static ssize_t uuid_show(struct device *dev, struct device_attribute *attr, - char *buf) +int nvme_cdev_add(struct cdev *cdev, struct device *cdev_device, + const struct file_operations *fops, struct module *owner) { - struct nvme_ns *ns = nvme_get_ns_from_dev(dev); + int minor, ret; + + minor = ida_alloc(&nvme_ns_chr_minor_ida, GFP_KERNEL); + if (minor < 0) + return minor; + cdev_device->devt = MKDEV(MAJOR(nvme_ns_chr_devt), minor); + cdev_device->class = &nvme_ns_chr_class; + cdev_device->release = nvme_cdev_rel; + device_initialize(cdev_device); + cdev_init(cdev, fops); + cdev->owner = owner; + ret = cdev_device_add(cdev, cdev_device); + if (ret) + put_device(cdev_device); - /* 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); + return ret; } -static DEVICE_ATTR(uuid, S_IRUGO, uuid_show, NULL); -static ssize_t eui_show(struct device *dev, struct device_attribute *attr, - char *buf) +static int nvme_ns_chr_open(struct inode *inode, struct file *file) { - struct nvme_ns *ns = nvme_get_ns_from_dev(dev); - return sprintf(buf, "%8phd\n", ns->eui); + return nvme_ns_open(container_of(inode->i_cdev, struct nvme_ns, cdev)); } -static DEVICE_ATTR(eui, S_IRUGO, eui_show, NULL); -static ssize_t nsid_show(struct device *dev, struct device_attribute *attr, - char *buf) +static int nvme_ns_chr_release(struct inode *inode, struct file *file) { - struct nvme_ns *ns = nvme_get_ns_from_dev(dev); - return sprintf(buf, "%d\n", ns->ns_id); + nvme_ns_release(container_of(inode->i_cdev, struct nvme_ns, cdev)); + return 0; } -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, +static const struct file_operations nvme_ns_chr_fops = { + .owner = THIS_MODULE, + .open = nvme_ns_chr_open, + .release = nvme_ns_chr_release, + .unlocked_ioctl = nvme_ns_chr_ioctl, + .compat_ioctl = compat_ptr_ioctl, + .uring_cmd = nvme_ns_chr_uring_cmd, + .uring_cmd_iopoll = nvme_ns_chr_uring_cmd_iopoll, }; -static umode_t nvme_ns_attrs_are_visible(struct kobject *kobj, - struct attribute *a, int n) +static int nvme_add_ns_cdev(struct nvme_ns *ns) { - struct device *dev = container_of(kobj, struct device, kobj); - struct nvme_ns *ns = nvme_get_ns_from_dev(dev); + int ret; - if (a == &dev_attr_uuid.attr) { - 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) { - if (!memchr_inv(ns->eui, 0, sizeof(ns->eui))) - return 0; - } - return a->mode; -} + ns->cdev_device.parent = ns->ctrl->device; + ret = dev_set_name(&ns->cdev_device, "ng%dn%d", + ns->ctrl->instance, ns->head->instance); + if (ret) + return ret; -static const struct attribute_group nvme_ns_attr_group = { - .attrs = nvme_ns_attrs, - .is_visible = nvme_ns_attrs_are_visible, -}; + return nvme_cdev_add(&ns->cdev, &ns->cdev_device, &nvme_ns_chr_fops, + ns->ctrl->ops->module); +} -#define nvme_show_str_function(field) \ -static ssize_t field##_show(struct device *dev, \ - struct device_attribute *attr, char *buf) \ -{ \ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); \ - return sprintf(buf, "%.*s\n", (int)sizeof(ctrl->field), ctrl->field); \ -} \ -static DEVICE_ATTR(field, S_IRUGO, field##_show, NULL); - -#define nvme_show_int_function(field) \ -static ssize_t field##_show(struct device *dev, \ - struct device_attribute *attr, char *buf) \ -{ \ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); \ - return sprintf(buf, "%d\n", ctrl->field); \ -} \ -static DEVICE_ATTR(field, S_IRUGO, field##_show, NULL); - -nvme_show_str_function(model); -nvme_show_str_function(serial); -nvme_show_str_function(firmware_rev); -nvme_show_int_function(cntlid); - -static ssize_t nvme_sysfs_delete(struct device *dev, - struct device_attribute *attr, const char *buf, - size_t count) +static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl, + struct nvme_ns_info *info) { - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + struct nvme_ns_head *head; + size_t size = sizeof(*head); + int ret = -ENOMEM; - if (device_remove_file_self(dev, attr)) - ctrl->ops->delete_ctrl(ctrl); - return count; -} -static DEVICE_ATTR(delete_controller, S_IWUSR, NULL, nvme_sysfs_delete); +#ifdef CONFIG_NVME_MULTIPATH + size += num_possible_nodes() * sizeof(struct nvme_ns *); +#endif -static ssize_t nvme_sysfs_show_transport(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + head = kzalloc(size, GFP_KERNEL); + if (!head) + goto out; + ret = ida_alloc_min(&ctrl->subsys->ns_ida, 1, GFP_KERNEL); + if (ret < 0) + goto out_free_head; + head->instance = ret; + INIT_LIST_HEAD(&head->list); + ret = init_srcu_struct(&head->srcu); + if (ret) + goto out_ida_remove; + head->subsys = ctrl->subsys; + 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); + + if (head->ids.csi) { + ret = nvme_get_effects_log(ctrl, head->ids.csi, &head->effects); + if (ret) + goto out_cleanup_srcu; + } else + head->effects = ctrl->effects; - return snprintf(buf, PAGE_SIZE, "%s\n", ctrl->ops->name); -} -static DEVICE_ATTR(transport, S_IRUGO, nvme_sysfs_show_transport, NULL); + ret = nvme_mpath_alloc_disk(ctrl, head); + if (ret) + goto out_cleanup_srcu; -static ssize_t nvme_sysfs_show_state(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - static const char *const state_name[] = { - [NVME_CTRL_NEW] = "new", - [NVME_CTRL_LIVE] = "live", - [NVME_CTRL_RESETTING] = "resetting", - [NVME_CTRL_RECONNECTING]= "reconnecting", - [NVME_CTRL_DELETING] = "deleting", - [NVME_CTRL_DEAD] = "dead", - }; + list_add_tail(&head->entry, &ctrl->subsys->nsheads); - if ((unsigned)ctrl->state < ARRAY_SIZE(state_name) && - state_name[ctrl->state]) - return sprintf(buf, "%s\n", state_name[ctrl->state]); + kref_get(&ctrl->subsys->ref); - return sprintf(buf, "unknown state\n"); + return head; +out_cleanup_srcu: + cleanup_srcu_struct(&head->srcu); +out_ida_remove: + ida_free(&ctrl->subsys->ns_ida, head->instance); +out_free_head: + kfree(head); +out: + if (ret > 0) + ret = blk_status_to_errno(nvme_error_status(ret)); + return ERR_PTR(ret); } -static DEVICE_ATTR(state, S_IRUGO, nvme_sysfs_show_state, NULL); - -static ssize_t nvme_sysfs_show_subsysnqn(struct device *dev, - struct device_attribute *attr, - char *buf) +static int nvme_global_check_duplicate_ids(struct nvme_subsystem *this, + struct nvme_ns_ids *ids) { - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + struct nvme_subsystem *s; + int ret = 0; + + /* + * Note that this check is racy as we try to avoid holding the global + * lock over the whole ns_head creation. But it is only intended as + * a sanity check anyway. + */ + mutex_lock(&nvme_subsystems_lock); + list_for_each_entry(s, &nvme_subsystems, entry) { + if (s == this) + continue; + mutex_lock(&s->lock); + ret = nvme_subsys_check_duplicate_ids(s, ids); + mutex_unlock(&s->lock); + if (ret) + break; + } + mutex_unlock(&nvme_subsystems_lock); - return snprintf(buf, PAGE_SIZE, "%s\n", ctrl->subnqn); + return ret; } -static DEVICE_ATTR(subsysnqn, S_IRUGO, nvme_sysfs_show_subsysnqn, NULL); -static ssize_t nvme_sysfs_show_address(struct device *dev, - struct device_attribute *attr, - char *buf) +static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info) { - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - - return ctrl->ops->get_address(ctrl, buf, PAGE_SIZE); -} -static DEVICE_ATTR(address, S_IRUGO, nvme_sysfs_show_address, NULL); - -static struct attribute *nvme_dev_attrs[] = { - &dev_attr_reset_controller.attr, - &dev_attr_rescan_controller.attr, - &dev_attr_model.attr, - &dev_attr_serial.attr, - &dev_attr_firmware_rev.attr, - &dev_attr_cntlid.attr, - &dev_attr_delete_controller.attr, - &dev_attr_transport.attr, - &dev_attr_subsysnqn.attr, - &dev_attr_address.attr, - &dev_attr_state.attr, - NULL -}; + struct nvme_ctrl *ctrl = ns->ctrl; + struct nvme_ns_head *head = NULL; + int ret; -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); + ret = nvme_global_check_duplicate_ids(ctrl->subsys, &info->ids); + if (ret) { + /* + * We've found two different namespaces on two different + * subsystems that report the same ID. This is pretty nasty + * for anything that actually requires unique device + * identification. In the kernel we need this for multipathing, + * and in user space the /dev/disk/by-id/ links rely on it. + * + * If the device also claims to be multi-path capable back off + * here now and refuse the probe the second device as this is a + * recipe for data corruption. If not this is probably a + * cheap consumer device if on the PCIe bus, so let the user + * proceed and use the shiny toy, but warn that with changing + * probing order (which due to our async probing could just be + * device taking longer to startup) the other device could show + * up at any time. + */ + nvme_print_device_info(ctrl); + if ((ns->ctrl->ops->flags & NVME_F_FABRICS) || /* !PCIe */ + ((ns->ctrl->subsys->cmic & NVME_CTRL_CMIC_MULTI_CTRL) && + info->is_shared)) { + dev_err(ctrl->device, + "ignoring nsid %d because of duplicate IDs\n", + info->nsid); + return ret; + } - 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; + dev_err(ctrl->device, + "clearing duplicate IDs for nsid %d\n", info->nsid); + dev_err(ctrl->device, + "use of /dev/disk/by-id/ may cause data corruption\n"); + memset(&info->ids.nguid, 0, sizeof(info->ids.nguid)); + memset(&info->ids.uuid, 0, sizeof(info->ids.uuid)); + memset(&info->ids.eui64, 0, sizeof(info->ids.eui64)); + ctrl->quirks |= NVME_QUIRK_BOGUS_NID; + } - return a->mode; -} + mutex_lock(&ctrl->subsys->lock); + head = nvme_find_ns_head(ctrl, info->nsid); + if (!head) { + ret = nvme_subsys_check_duplicate_ids(ctrl->subsys, &info->ids); + if (ret) { + dev_err(ctrl->device, + "duplicate IDs in subsystem for nsid %d\n", + info->nsid); + goto out_unlock; + } + head = nvme_alloc_ns_head(ctrl, info); + if (IS_ERR(head)) { + ret = PTR_ERR(head); + goto out_unlock; + } + } else { + ret = -EINVAL; + if ((!info->is_shared || !head->shared) && + !list_empty(&head->list)) { + dev_err(ctrl->device, + "Duplicate unshared namespace %d\n", + info->nsid); + goto out_put_ns_head; + } + if (!nvme_ns_ids_equal(&head->ids, &info->ids)) { + dev_err(ctrl->device, + "IDs don't match for shared namespace %d\n", + info->nsid); + goto out_put_ns_head; + } -static struct attribute_group nvme_dev_attrs_group = { - .attrs = nvme_dev_attrs, - .is_visible = nvme_dev_attrs_are_visible, -}; + if (!multipath) { + dev_warn(ctrl->device, + "Found shared namespace %d, but multipathing not supported.\n", + info->nsid); + dev_warn_once(ctrl->device, + "Shared namespace support requires core_nvme.multipath=Y.\n"); + } + } -static const struct attribute_group *nvme_dev_attr_groups[] = { - &nvme_dev_attrs_group, - NULL, -}; + list_add_tail_rcu(&ns->siblings, &head->list); + ns->head = head; + mutex_unlock(&ctrl->subsys->lock); -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); - struct nvme_ns *nsb = container_of(b, struct nvme_ns, list); +#ifdef CONFIG_NVME_MULTIPATH + cancel_delayed_work(&head->remove_work); +#endif + return 0; - return nsa->ns_id - nsb->ns_id; +out_put_ns_head: + nvme_put_ns_head(head); +out_unlock: + mutex_unlock(&ctrl->subsys->lock); + return ret; } -static struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid) +struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid) { struct nvme_ns *ns, *ret = NULL; + int srcu_idx; - mutex_lock(&ctrl->namespaces_mutex); - list_for_each_entry(ns, &ctrl->namespaces, list) { - if (ns->ns_id == nsid) { - kref_get(&ns->kref); + srcu_idx = srcu_read_lock(&ctrl->srcu); + list_for_each_entry_srcu(ns, &ctrl->namespaces, list, + srcu_read_lock_held(&ctrl->srcu)) { + if (ns->head->ns_id == nsid) { + if (!nvme_get_ns(ns)) + continue; ret = ns; break; } - if (ns->ns_id > nsid) + if (ns->head->ns_id > nsid) break; } - mutex_unlock(&ctrl->namespaces_mutex); + srcu_read_unlock(&ctrl->srcu, srcu_idx); return ret; } +EXPORT_SYMBOL_NS_GPL(nvme_find_get_ns, "NVME_TARGET_PASSTHRU"); -static int nvme_setup_streams_ns(struct nvme_ctrl *ctrl, struct nvme_ns *ns) +/* + * Add the namespace to the controller list while keeping the list ordered. + */ +static void nvme_ns_add_to_ctrl_list(struct nvme_ns *ns) { - struct streams_directive_params s; - int ret; + struct nvme_ns *tmp; - 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); + list_for_each_entry_reverse(tmp, &ns->ctrl->namespaces, list) { + if (tmp->head->ns_id < ns->head->ns_id) { + list_add_rcu(&ns->list, &tmp->list); + return; + } } - - return 0; + list_add_rcu(&ns->list, &ns->ctrl->namespaces); } -static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) +static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info) { + struct queue_limits lim = { }; struct nvme_ns *ns; struct gendisk *disk; - struct nvme_id_ns *id; - char disk_name[DISK_NAME_LEN]; - int node = dev_to_node(ctrl->dev); + int node = ctrl->numa_node; + bool last_path = false; ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node); if (!ns) return; - ns->instance = ida_simple_get(&ctrl->ns_ida, 1, 0, GFP_KERNEL); - if (ns->instance < 0) + if (ctrl->opts && ctrl->opts->data_digest) + lim.features |= BLK_FEAT_STABLE_WRITES; + if (ctrl->ops->supports_pci_p2pdma && + ctrl->ops->supports_pci_p2pdma(ctrl)) + lim.features |= BLK_FEAT_PCI_P2PDMA; + + disk = blk_mq_alloc_disk(ctrl->tagset, &lim, ns); + if (IS_ERR(disk)) goto out_free_ns; + disk->fops = &nvme_bdev_ops; + disk->private_data = ns; - ns->queue = blk_mq_init_queue(ctrl->tagset); - if (IS_ERR(ns->queue)) - goto out_release_instance; - queue_flag_set_unlocked(QUEUE_FLAG_NONROT, ns->queue); - ns->queue->queuedata = ns; + ns->disk = disk; + ns->queue = disk->queue; ns->ctrl = ctrl; - kref_init(&ns->kref); - ns->ns_id = nsid; - ns->lba_shift = 9; /* set to a default value for 512 until disk is validated */ - - 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_init_ns_head(ns, info)) + goto out_cleanup_disk; - if (nvme_revalidate_ns(ns, &id)) - goto out_free_queue; - - if (nvme_nvm_ns_supported(ns, id) && - nvme_nvm_register(ns, disk_name, node)) { - dev_warn(ctrl->device, "%s: LightNVM init failure\n", __func__); - goto out_free_id; + /* + * If multipathing is enabled, the device name for all disks and not + * just those that represent shared namespaces needs to be based on the + * subsystem instance. Using the controller instance for private + * namespaces could lead to naming collisions between shared and private + * namespaces if they don't use a common numbering scheme. + * + * If multipathing is not enabled, disk names must use the controller + * instance as shared namespaces will show up as multiple block + * devices. + */ + if (nvme_ns_head_multipath(ns->head)) { + sprintf(disk->disk_name, "nvme%dc%dn%d", ctrl->subsys->instance, + ctrl->instance, ns->head->instance); + disk->flags |= GENHD_FL_HIDDEN; + } else if (multipath) { + sprintf(disk->disk_name, "nvme%dn%d", ctrl->subsys->instance, + ns->head->instance); + } else { + sprintf(disk->disk_name, "nvme%dn%d", ctrl->instance, + ns->head->instance); } - disk = alloc_disk_node(0, node); - if (!disk) - goto out_free_id; + if (nvme_update_ns_info(ns, info)) + goto out_unlink_ns; - disk->fops = &nvme_fops; - disk->private_data = ns; - disk->queue = ns->queue; - disk->flags = GENHD_FL_EXT_DEVT; - memcpy(disk->disk_name, disk_name, DISK_NAME_LEN); - ns->disk = disk; + mutex_lock(&ctrl->namespaces_lock); + /* + * Ensure that no namespaces are added to the ctrl list after the queues + * are frozen, thereby avoiding a deadlock between scan and reset. + */ + if (test_bit(NVME_CTRL_FROZEN, &ctrl->flags)) { + mutex_unlock(&ctrl->namespaces_lock); + goto out_unlink_ns; + } + nvme_ns_add_to_ctrl_list(ns); + mutex_unlock(&ctrl->namespaces_lock); + synchronize_srcu(&ctrl->srcu); + nvme_get_ctrl(ctrl); - __nvme_revalidate_disk(disk, id); + if (device_add_disk(ctrl->device, ns->disk, nvme_ns_attr_groups)) + goto out_cleanup_ns_from_list; - mutex_lock(&ctrl->namespaces_mutex); - list_add_tail(&ns->list, &ctrl->namespaces); - mutex_unlock(&ctrl->namespaces_mutex); + if (!nvme_ns_head_multipath(ns->head)) + nvme_add_ns_cdev(ns); - kref_get(&ctrl->kref); + nvme_mpath_add_disk(ns, info->anagrpid); + nvme_fault_inject_init(&ns->fault_inject, ns->disk->disk_name); - kfree(id); + /* + * Set ns->disk->device->driver_data to ns so we can access + * ns->head->passthru_err_log_enabled in + * nvme_io_passthru_err_log_enabled_[store | show](). + */ + dev_set_drvdata(disk_to_dev(ns->disk), ns); - device_add_disk(ctrl->device, ns->disk); - if (sysfs_create_group(&disk_to_dev(ns->disk)->kobj, - &nvme_ns_attr_group)) - pr_warn("%s: failed to create sysfs group for identification\n", - ns->disk->disk_name); - if (ns->ndev && nvme_nvm_register_sysfs(ns)) - pr_warn("%s: failed to register lightnvm sysfs group for identification\n", - ns->disk->disk_name); return; - out_free_id: - kfree(id); - out_free_queue: - blk_cleanup_queue(ns->queue); - out_release_instance: - ida_simple_remove(&ctrl->ns_ida, ns->instance); + + out_cleanup_ns_from_list: + nvme_put_ctrl(ctrl); + mutex_lock(&ctrl->namespaces_lock); + list_del_rcu(&ns->list); + mutex_unlock(&ctrl->namespaces_lock); + synchronize_srcu(&ctrl->srcu); + out_unlink_ns: + mutex_lock(&ctrl->subsys->lock); + list_del_rcu(&ns->siblings); + if (list_empty(&ns->head->list)) { + list_del_init(&ns->head->entry); + /* + * If multipath is not configured, we still create a namespace + * head (nshead), but head->disk is not initialized in that + * case. As a result, only a single reference to nshead is held + * (via kref_init()) when it is created. Therefore, ensure that + * we do not release the reference to nshead twice if head->disk + * is not present. + */ + if (ns->head->disk) + last_path = true; + } + mutex_unlock(&ctrl->subsys->lock); + if (last_path) + nvme_put_ns_head(ns->head); + nvme_put_ns_head(ns->head); + out_cleanup_disk: + put_disk(disk); out_free_ns: kfree(ns); } static void nvme_ns_remove(struct nvme_ns *ns) { + bool last_path = false; + if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags)) return; - if (ns->disk && ns->disk->flags & GENHD_FL_UP) { - if (blk_get_integrity(ns->disk)) - blk_integrity_unregister(ns->disk); - sysfs_remove_group(&disk_to_dev(ns->disk)->kobj, - &nvme_ns_attr_group); - if (ns->ndev) - nvme_nvm_unregister_sysfs(ns); - del_gendisk(ns->disk); - blk_cleanup_queue(ns->queue); + clear_bit(NVME_NS_READY, &ns->flags); + set_capacity(ns->disk, 0); + nvme_fault_inject_fini(&ns->fault_inject); + + /* + * Ensure that !NVME_NS_READY is seen by other threads to prevent + * this ns going back into current_path. + */ + synchronize_srcu(&ns->head->srcu); + + /* wait for concurrent submissions */ + if (nvme_mpath_clear_current_path(ns)) + synchronize_srcu(&ns->head->srcu); + + mutex_lock(&ns->ctrl->subsys->lock); + list_del_rcu(&ns->siblings); + if (list_empty(&ns->head->list)) { + if (!nvme_mpath_queue_if_no_path(ns->head)) + list_del_init(&ns->head->entry); + last_path = true; } + mutex_unlock(&ns->ctrl->subsys->lock); + + /* guarantee not available in head->list */ + synchronize_srcu(&ns->head->srcu); + + if (!nvme_ns_head_multipath(ns->head)) + nvme_cdev_del(&ns->cdev, &ns->cdev_device); - mutex_lock(&ns->ctrl->namespaces_mutex); - list_del_init(&ns->list); - mutex_unlock(&ns->ctrl->namespaces_mutex); + nvme_mpath_remove_sysfs_link(ns); + del_gendisk(ns->disk); + + mutex_lock(&ns->ctrl->namespaces_lock); + list_del_rcu(&ns->list); + mutex_unlock(&ns->ctrl->namespaces_lock); + synchronize_srcu(&ns->ctrl->srcu); + + if (last_path) + nvme_mpath_remove_disk(ns->head); nvme_put_ns(ns); } -static void nvme_validate_ns(struct nvme_ctrl *ctrl, unsigned nsid) +static void nvme_ns_remove_by_nsid(struct nvme_ctrl *ctrl, u32 nsid) +{ + struct nvme_ns *ns = nvme_find_get_ns(ctrl, nsid); + + if (ns) { + nvme_ns_remove(ns); + nvme_put_ns(ns); + } +} + +static void nvme_validate_ns(struct nvme_ns *ns, struct nvme_ns_info *info) { + int ret = NVME_SC_INVALID_NS | NVME_STATUS_DNR; + + if (!nvme_ns_ids_equal(&ns->head->ids, &info->ids)) { + dev_err(ns->ctrl->device, + "identifiers changed for nsid %d\n", ns->head->ns_id); + goto out; + } + + ret = nvme_update_ns_info(ns, info); +out: + /* + * Only remove the namespace if we got a fatal error back from the + * device, otherwise ignore the error and just move on. + * + * TODO: we should probably schedule a delayed retry here. + */ + if (ret > 0 && (ret & NVME_STATUS_DNR)) + nvme_ns_remove(ns); +} + +static void nvme_scan_ns(struct nvme_ctrl *ctrl, unsigned nsid) +{ + struct nvme_ns_info info = { .nsid = nsid }; struct nvme_ns *ns; + int ret = 1; + + if (nvme_identify_ns_descs(ctrl, &info)) + return; + + if (info.ids.csi != NVME_CSI_NVM && !nvme_multi_css(ctrl)) { + dev_warn(ctrl->device, + "command set not reported for nsid: %d\n", nsid); + return; + } + + /* + * If available try to use the Command Set Independent Identify Namespace + * data structure to find all the generic information that is needed to + * 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) || + ctrl->vs >= NVME_VS(2, 0, 0)) + ret = nvme_ns_info_from_id_cs_indep(ctrl, &info); + if (ret > 0) + ret = nvme_ns_info_from_identify(ctrl, &info); + + if (info.is_removed) + nvme_ns_remove_by_nsid(ctrl, nsid); + + /* + * Ignore the namespace if it is not ready. We will get an AEN once it + * becomes ready and restart the scan. + */ + if (ret || !info.is_ready) + return; ns = nvme_find_get_ns(ctrl, nsid); if (ns) { - if (ns->disk && revalidate_disk(ns->disk)) - nvme_ns_remove(ns); + nvme_validate_ns(ns, &info); nvme_put_ns(ns); - } else - nvme_alloc_ns(ctrl, nsid); + } else { + nvme_alloc_ns(ctrl, &info); + } +} + +/** + * struct async_scan_info - keeps track of controller & NSIDs to scan + * @ctrl: Controller on which namespaces are being scanned + * @next_nsid: Index of next NSID to scan in ns_list + * @ns_list: Pointer to list of NSIDs to scan + * + * Note: There is a single async_scan_info structure shared by all instances + * of nvme_scan_ns_async() scanning a given controller, so the atomic + * operations on next_nsid are critical to ensure each instance scans a unique + * NSID. + */ +struct async_scan_info { + struct nvme_ctrl *ctrl; + atomic_t next_nsid; + __le32 *ns_list; +}; + +static void nvme_scan_ns_async(void *data, async_cookie_t cookie) +{ + struct async_scan_info *scan_info = data; + int idx; + u32 nsid; + + idx = (u32)atomic_fetch_inc(&scan_info->next_nsid); + nsid = le32_to_cpu(scan_info->ns_list[idx]); + + nvme_scan_ns(scan_info->ctrl, nsid); } static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl, unsigned nsid) { struct nvme_ns *ns, *next; + LIST_HEAD(rm_list); + mutex_lock(&ctrl->namespaces_lock); list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) { - if (ns->ns_id > nsid) - nvme_ns_remove(ns); + if (ns->head->ns_id > nsid) { + list_del_rcu(&ns->list); + synchronize_srcu(&ctrl->srcu); + list_add_tail_rcu(&ns->list, &rm_list); + } } + mutex_unlock(&ctrl->namespaces_lock); + + list_for_each_entry_safe(ns, next, &rm_list, list) + nvme_ns_remove(ns); } -static int nvme_scan_ns_list(struct nvme_ctrl *ctrl, unsigned nn) +static int nvme_scan_ns_list(struct nvme_ctrl *ctrl) { - struct nvme_ns *ns; + const int nr_entries = NVME_IDENTIFY_DATA_SIZE / sizeof(__le32); __le32 *ns_list; - unsigned i, j, nsid, prev = 0, num_lists = DIV_ROUND_UP(nn, 1024); - int ret = 0; + u32 prev = 0; + int ret = 0, i; + ASYNC_DOMAIN(domain); + struct async_scan_info scan_info; - ns_list = kzalloc(0x1000, GFP_KERNEL); + ns_list = kzalloc(NVME_IDENTIFY_DATA_SIZE, GFP_KERNEL); if (!ns_list) return -ENOMEM; - for (i = 0; i < num_lists; i++) { - ret = nvme_identify_ns_list(ctrl, prev, ns_list); - if (ret) + scan_info.ctrl = ctrl; + scan_info.ns_list = ns_list; + for (;;) { + struct nvme_command cmd = { + .identify.opcode = nvme_admin_identify, + .identify.cns = NVME_ID_CNS_NS_ACTIVE_LIST, + .identify.nsid = cpu_to_le32(prev), + }; + + ret = nvme_submit_sync_cmd(ctrl->admin_q, &cmd, ns_list, + NVME_IDENTIFY_DATA_SIZE); + if (ret) { + dev_warn(ctrl->device, + "Identify NS List failed (status=0x%x)\n", ret); goto free; + } - for (j = 0; j < min(nn, 1024U); j++) { - nsid = le32_to_cpu(ns_list[j]); - if (!nsid) - goto out; - - nvme_validate_ns(ctrl, nsid); + atomic_set(&scan_info.next_nsid, 0); + for (i = 0; i < nr_entries; i++) { + u32 nsid = le32_to_cpu(ns_list[i]); - while (++prev < nsid) { - ns = nvme_find_get_ns(ctrl, prev); - if (ns) { - nvme_ns_remove(ns); - nvme_put_ns(ns); - } - } + if (!nsid) /* end of the list? */ + goto out; + async_schedule_domain(nvme_scan_ns_async, &scan_info, + &domain); + while (++prev < nsid) + nvme_ns_remove_by_nsid(ctrl, prev); } - nn -= j; + async_synchronize_full_domain(&domain); } out: nvme_remove_invalid_namespaces(ctrl, prev); free: + async_synchronize_full_domain(&domain); kfree(ns_list); return ret; } -static void nvme_scan_ns_sequential(struct nvme_ctrl *ctrl, unsigned nn) +static void nvme_scan_ns_sequential(struct nvme_ctrl *ctrl) { - unsigned i; + struct nvme_id_ctrl *id; + u32 nn, i; + + if (nvme_identify_ctrl(ctrl, &id)) + return; + nn = le32_to_cpu(id->nn); + kfree(id); for (i = 1; i <= nn; i++) - nvme_validate_ns(ctrl, i); + nvme_scan_ns(ctrl, i); nvme_remove_invalid_namespaces(ctrl, nn); } -static void nvme_scan_work(struct work_struct *work) +static void nvme_clear_changed_ns_log(struct nvme_ctrl *ctrl) { - struct nvme_ctrl *ctrl = - container_of(work, struct nvme_ctrl, scan_work); - struct nvme_id_ctrl *id; - unsigned nn; + size_t log_size = NVME_MAX_CHANGED_NAMESPACES * sizeof(__le32); + __le32 *log; + int error; - if (ctrl->state != NVME_CTRL_LIVE) + log = kzalloc(log_size, GFP_KERNEL); + if (!log) return; - if (nvme_identify_ctrl(ctrl, &id)) - return; + /* + * We need to read the log to clear the AEN, but we don't want to rely + * on it for the changed namespace information as userspace could have + * raced with us in reading the log page, which could cause us to miss + * updates. + */ + error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CHANGED_NS, 0, + NVME_CSI_NVM, log, log_size, 0); + if (error) + dev_warn(ctrl->device, + "reading changed ns log failed: %d\n", error); - nn = le32_to_cpu(id->nn); - if (ctrl->vs >= NVME_VS(1, 1, 0) && - !(ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS)) { - if (!nvme_scan_ns_list(ctrl, nn)) - goto done; - } - nvme_scan_ns_sequential(ctrl, nn); - done: - mutex_lock(&ctrl->namespaces_mutex); - list_sort(NULL, &ctrl->namespaces, ns_cmp); - mutex_unlock(&ctrl->namespaces_mutex); - kfree(id); + kfree(log); } -void nvme_queue_scan(struct nvme_ctrl *ctrl) +static void nvme_scan_work(struct work_struct *work) { + struct nvme_ctrl *ctrl = + container_of(work, struct nvme_ctrl, scan_work); + int ret; + + /* No tagset on a live ctrl means IO queues could not created */ + if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE || !ctrl->tagset) + return; + /* - * Do not queue new scan work when a controller is reset during - * removal. + * Identify controller limits can change at controller reset due to + * new firmware download, even though it is not common we cannot ignore + * such scenario. Controller's non-mdts limits are reported in the unit + * of logical blocks that is dependent on the format of attached + * namespace. Hence re-read the limits at the time of ns allocation. */ - if (ctrl->state == NVME_CTRL_LIVE) - queue_work(nvme_wq, &ctrl->scan_work); + ret = nvme_init_non_mdts_limits(ctrl); + if (ret < 0) { + dev_warn(ctrl->device, + "reading non-mdts-limits failed: %d\n", ret); + return; + } + + if (test_and_clear_bit(NVME_AER_NOTICE_NS_CHANGED, &ctrl->events)) { + dev_info(ctrl->device, "rescanning namespaces.\n"); + nvme_clear_changed_ns_log(ctrl); + } + + mutex_lock(&ctrl->scan_lock); + if (!nvme_id_cns_ok(ctrl, NVME_ID_CNS_NS_ACTIVE_LIST)) { + nvme_scan_ns_sequential(ctrl); + } else { + /* + * Fall back to sequential scan if DNR is set to handle broken + * devices which should support Identify NS List (as per the VS + * they report) but don't actually support it. + */ + ret = nvme_scan_ns_list(ctrl); + if (ret > 0 && ret & NVME_STATUS_DNR) + nvme_scan_ns_sequential(ctrl); + } + mutex_unlock(&ctrl->scan_lock); + + /* Requeue if we have missed AENs */ + if (test_bit(NVME_AER_NOTICE_NS_CHANGED, &ctrl->events)) + nvme_queue_scan(ctrl); +#ifdef CONFIG_NVME_MULTIPATH + else if (ctrl->ana_log_buf) + /* Re-read the ANA log page to not miss updates */ + queue_work(nvme_wq, &ctrl->ana_work); +#endif } -EXPORT_SYMBOL_GPL(nvme_queue_scan); /* * This function iterates the namespace list unlocked to allow recovery from @@ -2495,6 +4557,23 @@ EXPORT_SYMBOL_GPL(nvme_queue_scan); void nvme_remove_namespaces(struct nvme_ctrl *ctrl) { struct nvme_ns *ns, *next; + LIST_HEAD(ns_list); + + /* + * make sure to requeue I/O to all namespaces as these + * might result from the scan itself and must complete + * for the scan_work to make progress + */ + nvme_mpath_clear_ctrl_paths(ctrl); + + /* + * Unquiesce io queues so any pending IO won't hang, especially + * those submitted from scan work + */ + nvme_unquiesce_io_queues(ctrl); + + /* prevent racing with ns scanning */ + flush_work(&ctrl->scan_work); /* * The dead states indicates the controller was not gracefully @@ -2502,185 +4581,596 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl) * removing the namespaces' disks; fail all the queues now to avoid * potentially having to clean up the failed sync later. */ - if (ctrl->state == NVME_CTRL_DEAD) - nvme_kill_queues(ctrl); + if (nvme_ctrl_state(ctrl) == NVME_CTRL_DEAD) + nvme_mark_namespaces_dead(ctrl); + + /* this is a no-op when called from the controller reset handler */ + nvme_change_ctrl_state(ctrl, NVME_CTRL_DELETING_NOIO); - list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) + mutex_lock(&ctrl->namespaces_lock); + list_splice_init_rcu(&ctrl->namespaces, &ns_list, synchronize_rcu); + mutex_unlock(&ctrl->namespaces_lock); + synchronize_srcu(&ctrl->srcu); + + list_for_each_entry_safe(ns, next, &ns_list, list) nvme_ns_remove(ns); } EXPORT_SYMBOL_GPL(nvme_remove_namespaces); +static int nvme_class_uevent(const struct device *dev, struct kobj_uevent_env *env) +{ + const struct nvme_ctrl *ctrl = + container_of(dev, struct nvme_ctrl, ctrl_device); + struct nvmf_ctrl_options *opts = ctrl->opts; + int ret; + + ret = add_uevent_var(env, "NVME_TRTYPE=%s", ctrl->ops->name); + if (ret) + return ret; + + if (opts) { + ret = add_uevent_var(env, "NVME_TRADDR=%s", opts->traddr); + if (ret) + return ret; + + ret = add_uevent_var(env, "NVME_TRSVCID=%s", + opts->trsvcid ?: "none"); + if (ret) + return ret; + + ret = add_uevent_var(env, "NVME_HOST_TRADDR=%s", + opts->host_traddr ?: "none"); + if (ret) + return ret; + + ret = add_uevent_var(env, "NVME_HOST_IFACE=%s", + opts->host_iface ?: "none"); + } + return ret; +} + +static void nvme_change_uevent(struct nvme_ctrl *ctrl, char *envdata) +{ + char *envp[2] = { envdata, NULL }; + + kobject_uevent_env(&ctrl->device->kobj, KOBJ_CHANGE, envp); +} + +static void nvme_aen_uevent(struct nvme_ctrl *ctrl) +{ + char *envp[2] = { NULL, NULL }; + u32 aen_result = ctrl->aen_result; + + ctrl->aen_result = 0; + if (!aen_result) + return; + + envp[0] = kasprintf(GFP_KERNEL, "NVME_AEN=%#08x", aen_result); + if (!envp[0]) + return; + kobject_uevent_env(&ctrl->device->kobj, KOBJ_CHANGE, envp); + kfree(envp[0]); +} + static void nvme_async_event_work(struct work_struct *work) { struct nvme_ctrl *ctrl = container_of(work, struct nvme_ctrl, async_event_work); - spin_lock_irq(&ctrl->lock); - while (ctrl->event_limit > 0) { - int aer_idx = --ctrl->event_limit; + nvme_aen_uevent(ctrl); + + /* + * The transport drivers must guarantee AER submission here is safe by + * flushing ctrl async_event_work after changing the controller state + * from LIVE and before freeing the admin queue. + */ + if (nvme_ctrl_state(ctrl) == NVME_CTRL_LIVE) + ctrl->ops->submit_async_event(ctrl); +} + +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)); +} - spin_unlock_irq(&ctrl->lock); - ctrl->ops->submit_async_event(ctrl, aer_idx); - spin_lock_irq(&ctrl->lock); +static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl) +{ + struct nvme_fw_slot_info_log *log; + u8 next_fw_slot, cur_fw_slot; + + log = kmalloc(sizeof(*log), GFP_KERNEL); + if (!log) + return; + + if (nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_FW_SLOT, 0, NVME_CSI_NVM, + log, sizeof(*log), 0)) { + dev_warn(ctrl->device, "Get FW SLOT INFO log error\n"); + goto out_free_log; } - spin_unlock_irq(&ctrl->lock); + + cur_fw_slot = log->afi & 0x7; + next_fw_slot = (log->afi & 0x70) >> 4; + if (!cur_fw_slot || (next_fw_slot && (cur_fw_slot != next_fw_slot))) { + dev_info(ctrl->device, + "Firmware is activated after next Controller Level Reset\n"); + goto out_free_log; + } + + memcpy(ctrl->subsys->firmware_rev, &log->frs[cur_fw_slot - 1], + sizeof(ctrl->subsys->firmware_rev)); + +out_free_log: + kfree(log); } -void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, - union nvme_result *res) +static void nvme_fw_act_work(struct work_struct *work) { - u32 result = le32_to_cpu(res->u32); - bool done = true; + struct nvme_ctrl *ctrl = container_of(work, + struct nvme_ctrl, fw_act_work); + unsigned long fw_act_timeout; - switch (le16_to_cpu(status) >> 1) { - case NVME_SC_SUCCESS: - done = false; - /*FALLTHRU*/ - case NVME_SC_ABORT_REQ: - ++ctrl->event_limit; - queue_work(nvme_wq, &ctrl->async_event_work); - break; - default: - break; + nvme_auth_stop(ctrl); + + if (ctrl->mtfa) + fw_act_timeout = jiffies + msecs_to_jiffies(ctrl->mtfa * 100); + else + fw_act_timeout = jiffies + secs_to_jiffies(admin_timeout); + + nvme_quiesce_io_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_try_sched_reset(ctrl); + return; + } + msleep(100); } - if (done) + if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_CONNECTING) || + !nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE)) return; - switch (result & 0xff07) { + nvme_unquiesce_io_queues(ctrl); + /* read FW slot information to clear the AER */ + nvme_get_fw_slot_info(ctrl); + + queue_work(nvme_wq, &ctrl->async_event_work); +} + +static u32 nvme_aer_type(u32 result) +{ + return result & 0x7; +} + +static u32 nvme_aer_subtype(u32 result) +{ + return (result & 0xff00) >> 8; +} + +static bool nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result) +{ + u32 aer_notice_type = nvme_aer_subtype(result); + bool requeue = true; + + switch (aer_notice_type) { case NVME_AER_NOTICE_NS_CHANGED: - dev_info(ctrl->device, "rescanning\n"); + set_bit(NVME_AER_NOTICE_NS_CHANGED, &ctrl->events); nvme_queue_scan(ctrl); break; + case NVME_AER_NOTICE_FW_ACT_STARTING: + /* + * We are (ab)using the RESETTING state to prevent subsequent + * recovery actions from interfering with the controller's + * firmware activation. + */ + if (nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) { + requeue = false; + queue_work(nvme_wq, &ctrl->fw_act_work); + } + break; +#ifdef CONFIG_NVME_MULTIPATH + case NVME_AER_NOTICE_ANA: + if (!ctrl->ana_log_buf) + break; + queue_work(nvme_wq, &ctrl->ana_work); + break; +#endif + case NVME_AER_NOTICE_DISC_CHANGED: + ctrl->aen_result = result; + break; default: dev_warn(ctrl->device, "async event result %08x\n", result); } + return requeue; } -EXPORT_SYMBOL_GPL(nvme_complete_async_event); -void nvme_queue_async_events(struct nvme_ctrl *ctrl) +static void nvme_handle_aer_persistent_error(struct nvme_ctrl *ctrl) { - ctrl->event_limit = NVME_NR_AERS; - queue_work(nvme_wq, &ctrl->async_event_work); + dev_warn(ctrl->device, + "resetting controller due to persistent internal error\n"); + nvme_reset_ctrl(ctrl); } -EXPORT_SYMBOL_GPL(nvme_queue_async_events); -static DEFINE_IDA(nvme_instance_ida); +void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, + volatile union nvme_result *res) +{ + u32 result = le32_to_cpu(res->u32); + u32 aer_type = nvme_aer_type(result); + u32 aer_subtype = nvme_aer_subtype(result); + bool requeue = true; + + if (le16_to_cpu(status) >> 1 != NVME_SC_SUCCESS) + return; + + trace_nvme_async_event(ctrl, result); + switch (aer_type) { + case NVME_AER_NOTICE: + requeue = nvme_handle_aen_notice(ctrl, result); + break; + case NVME_AER_ERROR: + /* + * For a persistent internal error, don't run async_event_work + * to submit a new AER. The controller reset will do it. + */ + if (aer_subtype == NVME_AER_ERROR_PERSIST_INT_ERR) { + nvme_handle_aer_persistent_error(ctrl); + return; + } + fallthrough; + case NVME_AER_SMART: + case NVME_AER_CSS: + case NVME_AER_VS: + ctrl->aen_result = result; + break; + default: + break; + } + + if (requeue) + queue_work(nvme_wq, &ctrl->async_event_work); +} +EXPORT_SYMBOL_GPL(nvme_complete_async_event); -static int nvme_set_instance(struct nvme_ctrl *ctrl) +int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set, + const struct blk_mq_ops *ops, unsigned int cmd_size) { - int instance, error; + struct queue_limits lim = {}; + int ret; - do { - if (!ida_pre_get(&nvme_instance_ida, GFP_KERNEL)) - return -ENODEV; + memset(set, 0, sizeof(*set)); + set->ops = ops; + set->queue_depth = NVME_AQ_MQ_TAG_DEPTH; + if (ctrl->ops->flags & NVME_F_FABRICS) + /* Reserved for fabric connect and keep alive */ + set->reserved_tags = 2; + set->numa_node = ctrl->numa_node; + if (ctrl->ops->flags & NVME_F_BLOCKING) + set->flags |= BLK_MQ_F_BLOCKING; + set->cmd_size = cmd_size; + set->driver_data = ctrl; + set->nr_hw_queues = 1; + set->timeout = NVME_ADMIN_TIMEOUT; + ret = blk_mq_alloc_tag_set(set); + if (ret) + return ret; - spin_lock(&dev_list_lock); - error = ida_get_new(&nvme_instance_ida, &instance); - spin_unlock(&dev_list_lock); - } while (error == -EAGAIN); + ctrl->admin_q = blk_mq_alloc_queue(set, &lim, NULL); + if (IS_ERR(ctrl->admin_q)) { + ret = PTR_ERR(ctrl->admin_q); + goto out_free_tagset; + } - if (error) - return -ENODEV; + if (ctrl->ops->flags & NVME_F_FABRICS) { + ctrl->fabrics_q = blk_mq_alloc_queue(set, NULL, NULL); + if (IS_ERR(ctrl->fabrics_q)) { + ret = PTR_ERR(ctrl->fabrics_q); + goto out_cleanup_admin_q; + } + } - ctrl->instance = instance; + ctrl->admin_tagset = set; return 0; + +out_cleanup_admin_q: + blk_mq_destroy_queue(ctrl->admin_q); + blk_put_queue(ctrl->admin_q); +out_free_tagset: + blk_mq_free_tag_set(set); + ctrl->admin_q = NULL; + ctrl->fabrics_q = NULL; + return ret; } +EXPORT_SYMBOL_GPL(nvme_alloc_admin_tag_set); -static void nvme_release_instance(struct nvme_ctrl *ctrl) +void nvme_remove_admin_tag_set(struct nvme_ctrl *ctrl) { - spin_lock(&dev_list_lock); - ida_remove(&nvme_instance_ida, ctrl->instance); - spin_unlock(&dev_list_lock); + /* + * As we're about to destroy the queue and free tagset + * we can not have keep-alive work running. + */ + nvme_stop_keep_alive(ctrl); + blk_mq_destroy_queue(ctrl->admin_q); + if (ctrl->ops->flags & NVME_F_FABRICS) { + blk_mq_destroy_queue(ctrl->fabrics_q); + blk_put_queue(ctrl->fabrics_q); + } + blk_mq_free_tag_set(ctrl->admin_tagset); } +EXPORT_SYMBOL_GPL(nvme_remove_admin_tag_set); + +int nvme_alloc_io_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set, + const struct blk_mq_ops *ops, unsigned int nr_maps, + unsigned int cmd_size) +{ + int ret; + + memset(set, 0, sizeof(*set)); + set->ops = ops; + set->queue_depth = min_t(unsigned, ctrl->sqsize, BLK_MQ_MAX_DEPTH - 1); + /* + * Some Apple controllers requires tags to be unique across admin and + * the (only) I/O queue, so reserve the first 32 tags of the I/O queue. + */ + if (ctrl->quirks & NVME_QUIRK_SHARED_TAGS) + set->reserved_tags = NVME_AQ_DEPTH; + else if (ctrl->ops->flags & NVME_F_FABRICS) + /* Reserved for fabric connect */ + set->reserved_tags = 1; + set->numa_node = ctrl->numa_node; + if (ctrl->ops->flags & NVME_F_BLOCKING) + set->flags |= BLK_MQ_F_BLOCKING; + set->cmd_size = cmd_size; + set->driver_data = ctrl; + set->nr_hw_queues = ctrl->queue_count - 1; + set->timeout = NVME_IO_TIMEOUT; + set->nr_maps = nr_maps; + ret = blk_mq_alloc_tag_set(set); + if (ret) + return ret; + + if (ctrl->ops->flags & NVME_F_FABRICS) { + struct queue_limits lim = { + .features = BLK_FEAT_SKIP_TAGSET_QUIESCE, + }; + + ctrl->connect_q = blk_mq_alloc_queue(set, &lim, NULL); + if (IS_ERR(ctrl->connect_q)) { + ret = PTR_ERR(ctrl->connect_q); + goto out_free_tag_set; + } + } + + ctrl->tagset = set; + return 0; + +out_free_tag_set: + blk_mq_free_tag_set(set); + ctrl->connect_q = NULL; + return ret; +} +EXPORT_SYMBOL_GPL(nvme_alloc_io_tag_set); + +void nvme_remove_io_tag_set(struct nvme_ctrl *ctrl) +{ + if (ctrl->ops->flags & NVME_F_FABRICS) { + blk_mq_destroy_queue(ctrl->connect_q); + blk_put_queue(ctrl->connect_q); + } + blk_mq_free_tag_set(ctrl->tagset); +} +EXPORT_SYMBOL_GPL(nvme_remove_io_tag_set); void nvme_stop_ctrl(struct nvme_ctrl *ctrl) { - nvme_stop_keep_alive(ctrl); + nvme_mpath_stop(ctrl); + nvme_auth_stop(ctrl); + nvme_stop_failfast_work(ctrl); flush_work(&ctrl->async_event_work); - flush_work(&ctrl->scan_work); + cancel_work_sync(&ctrl->fw_act_work); + if (ctrl->ops->stop_ctrl) + ctrl->ops->stop_ctrl(ctrl); } EXPORT_SYMBOL_GPL(nvme_stop_ctrl); void nvme_start_ctrl(struct nvme_ctrl *ctrl) { - if (ctrl->kato) - nvme_start_keep_alive(ctrl); + nvme_enable_aen(ctrl); + + /* + * persistent discovery controllers need to send indication to userspace + * to re-read the discovery log page to learn about possible changes + * that were missed. We identify persistent discovery controllers by + * checking that they started once before, hence are reconnecting back. + */ + if (test_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags) && + nvme_discovery_ctrl(ctrl)) { + if (!ctrl->kato) { + nvme_stop_keep_alive(ctrl); + ctrl->kato = NVME_DEFAULT_KATO; + nvme_start_keep_alive(ctrl); + } + nvme_change_uevent(ctrl, "NVME_EVENT=rediscover"); + } if (ctrl->queue_count > 1) { nvme_queue_scan(ctrl); - nvme_queue_async_events(ctrl); - nvme_start_queues(ctrl); + nvme_unquiesce_io_queues(ctrl); + nvme_mpath_update(ctrl); } + + nvme_change_uevent(ctrl, "NVME_EVENT=connected"); + set_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags); } 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); - list_del(&ctrl->node); - spin_unlock(&dev_list_lock); + nvme_stop_keep_alive(ctrl); + nvme_hwmon_exit(ctrl); + nvme_fault_inject_fini(&ctrl->fault_inject); + dev_pm_qos_hide_latency_tolerance(ctrl->device); + cdev_device_del(&ctrl->cdev, ctrl->device); + nvme_put_ctrl(ctrl); } EXPORT_SYMBOL_GPL(nvme_uninit_ctrl); -static void nvme_free_ctrl(struct kref *kref) +static void nvme_free_cels(struct nvme_ctrl *ctrl) { - struct nvme_ctrl *ctrl = container_of(kref, struct nvme_ctrl, kref); + struct nvme_effects_log *cel; + unsigned long i; - put_device(ctrl->device); - nvme_release_instance(ctrl); - ida_destroy(&ctrl->ns_ida); + xa_for_each(&ctrl->cels, i, cel) { + xa_erase(&ctrl->cels, i); + kfree(cel); + } - ctrl->ops->free_ctrl(ctrl); + xa_destroy(&ctrl->cels); } -void nvme_put_ctrl(struct nvme_ctrl *ctrl) +static void nvme_free_ctrl(struct device *dev) { - kref_put(&ctrl->kref, nvme_free_ctrl); + struct nvme_ctrl *ctrl = + container_of(dev, struct nvme_ctrl, ctrl_device); + struct nvme_subsystem *subsys = ctrl->subsys; + + if (ctrl->admin_q) + blk_put_queue(ctrl->admin_q); + if (!subsys || ctrl->instance != subsys->instance) + ida_free(&nvme_instance_ida, ctrl->instance); + nvme_free_cels(ctrl); + nvme_mpath_uninit(ctrl); + cleanup_srcu_struct(&ctrl->srcu); + nvme_auth_stop(ctrl); + nvme_auth_free(ctrl); + __free_page(ctrl->discard_page); + free_opal_dev(ctrl->opal_dev); + + if (subsys) { + mutex_lock(&nvme_subsystems_lock); + list_del(&ctrl->subsys_entry); + sysfs_remove_link(&subsys->dev.kobj, dev_name(ctrl->device)); + mutex_unlock(&nvme_subsystems_lock); + } + + ctrl->ops->free_ctrl(ctrl); + + if (subsys) + nvme_put_subsystem(subsys); } -EXPORT_SYMBOL_GPL(nvme_put_ctrl); /* * Initialize a NVMe controller structures. This needs to be called during * earliest initialization so that we have the initialized structured around * during probing. + * + * On success, the caller must use the nvme_put_ctrl() to release this when + * needed, which also invokes the ops->free_ctrl() callback. */ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, const struct nvme_ctrl_ops *ops, unsigned long quirks) { int ret; - ctrl->state = NVME_CTRL_NEW; + WRITE_ONCE(ctrl->state, NVME_CTRL_NEW); + ctrl->passthru_err_log_enabled = false; + clear_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags); spin_lock_init(&ctrl->lock); + mutex_init(&ctrl->namespaces_lock); + + ret = init_srcu_struct(&ctrl->srcu); + if (ret) + return ret; + + mutex_init(&ctrl->scan_lock); INIT_LIST_HEAD(&ctrl->namespaces); - mutex_init(&ctrl->namespaces_mutex); - kref_init(&ctrl->kref); + xa_init(&ctrl->cels); ctrl->dev = dev; ctrl->ops = ops; ctrl->quirks = quirks; + ctrl->numa_node = NUMA_NO_NODE; 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); + INIT_WORK(&ctrl->delete_work, nvme_delete_ctrl_work); + init_waitqueue_head(&ctrl->state_wq); - ret = nvme_set_instance(ctrl); - if (ret) + INIT_DELAYED_WORK(&ctrl->ka_work, nvme_keep_alive_work); + INIT_DELAYED_WORK(&ctrl->failfast_work, nvme_failfast_work); + memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd)); + ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive; + ctrl->ka_last_check_time = jiffies; + + BUILD_BUG_ON(NVME_DSM_MAX_RANGES * sizeof(struct nvme_dsm_range) > + PAGE_SIZE); + ctrl->discard_page = alloc_page(GFP_KERNEL); + if (!ctrl->discard_page) { + ret = -ENOMEM; + goto out; + } + + ret = ida_alloc(&nvme_instance_ida, GFP_KERNEL); + if (ret < 0) goto out; + ctrl->instance = ret; - ctrl->device = device_create_with_groups(nvme_class, ctrl->dev, - MKDEV(nvme_char_major, ctrl->instance), - ctrl, nvme_dev_attr_groups, - "nvme%d", ctrl->instance); - if (IS_ERR(ctrl->device)) { - ret = PTR_ERR(ctrl->device); + ret = nvme_auth_init_ctrl(ctrl); + if (ret) goto out_release_instance; - } - get_device(ctrl->device); - ida_init(&ctrl->ns_ida); - spin_lock(&dev_list_lock); - list_add_tail(&ctrl->node, &nvme_ctrl_list); - spin_unlock(&dev_list_lock); + nvme_mpath_init_ctrl(ctrl); + + device_initialize(&ctrl->ctrl_device); + ctrl->device = &ctrl->ctrl_device; + ctrl->device->devt = MKDEV(MAJOR(nvme_ctrl_base_chr_devt), + ctrl->instance); + ctrl->device->class = &nvme_class; + ctrl->device->parent = ctrl->dev; + if (ops->dev_attr_groups) + ctrl->device->groups = ops->dev_attr_groups; + else + ctrl->device->groups = nvme_dev_attr_groups; + ctrl->device->release = nvme_free_ctrl; + dev_set_drvdata(ctrl->device, ctrl); + + return ret; + +out_release_instance: + ida_free(&nvme_instance_ida, ctrl->instance); +out: + if (ctrl->discard_page) + __free_page(ctrl->discard_page); + cleanup_srcu_struct(&ctrl->srcu); + return ret; +} +EXPORT_SYMBOL_GPL(nvme_init_ctrl); + +/* + * On success, returns with an elevated controller reference and caller must + * use nvme_uninit_ctrl() to properly free resources associated with the ctrl. + */ +int nvme_add_ctrl(struct nvme_ctrl *ctrl) +{ + int ret; + + ret = dev_set_name(ctrl->device, "nvme%d", ctrl->instance); + if (ret) + return ret; + + cdev_init(&ctrl->cdev, &nvme_dev_fops); + ctrl->cdev.owner = ctrl->ops->module; + ret = cdev_device_add(&ctrl->cdev, ctrl->device); + if (ret) + return ret; /* * Initialize latency tolerance controls. The sysfs files won't @@ -2690,156 +5180,272 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, dev_pm_qos_update_user_latency_tolerance(ctrl->device, min(default_ps_max_latency_us, (unsigned long)S32_MAX)); + nvme_fault_inject_init(&ctrl->fault_inject, dev_name(ctrl->device)); + nvme_get_ctrl(ctrl); + return 0; -out_release_instance: - nvme_release_instance(ctrl); -out: - return ret; } -EXPORT_SYMBOL_GPL(nvme_init_ctrl); +EXPORT_SYMBOL_GPL(nvme_add_ctrl); -/** - * nvme_kill_queues(): Ends all namespace queues - * @ctrl: the dead controller that needs to end - * - * Call this function when the driver determines it is unable to get the - * controller in a state capable of servicing IO. - */ -void nvme_kill_queues(struct nvme_ctrl *ctrl) +/* let I/O to all namespaces fail in preparation for surprise removal */ +void nvme_mark_namespaces_dead(struct nvme_ctrl *ctrl) { struct nvme_ns *ns; + int srcu_idx; - mutex_lock(&ctrl->namespaces_mutex); - - /* 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) { - /* - * Revalidating a dead namespace sets capacity to 0. This will - * end buffered writers dirtying pages that can't be synced. - */ - if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags)) - continue; - revalidate_disk(ns->disk); - blk_set_queue_dying(ns->queue); - - /* Forcibly unquiesce queues to avoid blocking dispatch */ - blk_mq_unquiesce_queue(ns->queue); - } - mutex_unlock(&ctrl->namespaces_mutex); + srcu_idx = srcu_read_lock(&ctrl->srcu); + list_for_each_entry_srcu(ns, &ctrl->namespaces, list, + srcu_read_lock_held(&ctrl->srcu)) + blk_mark_disk_dead(ns->disk); + srcu_read_unlock(&ctrl->srcu, srcu_idx); } -EXPORT_SYMBOL_GPL(nvme_kill_queues); +EXPORT_SYMBOL_GPL(nvme_mark_namespaces_dead); void nvme_unfreeze(struct nvme_ctrl *ctrl) { struct nvme_ns *ns; - - mutex_lock(&ctrl->namespaces_mutex); - list_for_each_entry(ns, &ctrl->namespaces, list) - blk_mq_unfreeze_queue(ns->queue); - mutex_unlock(&ctrl->namespaces_mutex); + int srcu_idx; + + 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_non_owner(ns->queue); + srcu_read_unlock(&ctrl->srcu, srcu_idx); + clear_bit(NVME_CTRL_FROZEN, &ctrl->flags); } EXPORT_SYMBOL_GPL(nvme_unfreeze); -void nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout) +int nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout) { struct nvme_ns *ns; + int srcu_idx; - mutex_lock(&ctrl->namespaces_mutex); - list_for_each_entry(ns, &ctrl->namespaces, list) { + srcu_idx = srcu_read_lock(&ctrl->srcu); + list_for_each_entry_srcu(ns, &ctrl->namespaces, list, + srcu_read_lock_held(&ctrl->srcu)) { timeout = blk_mq_freeze_queue_wait_timeout(ns->queue, timeout); if (timeout <= 0) break; } - mutex_unlock(&ctrl->namespaces_mutex); + srcu_read_unlock(&ctrl->srcu, srcu_idx); + return timeout; } EXPORT_SYMBOL_GPL(nvme_wait_freeze_timeout); void nvme_wait_freeze(struct nvme_ctrl *ctrl) { struct nvme_ns *ns; + int srcu_idx; - mutex_lock(&ctrl->namespaces_mutex); - list_for_each_entry(ns, &ctrl->namespaces, list) + srcu_idx = srcu_read_lock(&ctrl->srcu); + list_for_each_entry_srcu(ns, &ctrl->namespaces, list, + srcu_read_lock_held(&ctrl->srcu)) blk_mq_freeze_queue_wait(ns->queue); - mutex_unlock(&ctrl->namespaces_mutex); + srcu_read_unlock(&ctrl->srcu, srcu_idx); } EXPORT_SYMBOL_GPL(nvme_wait_freeze); void nvme_start_freeze(struct nvme_ctrl *ctrl) { struct nvme_ns *ns; + int srcu_idx; - mutex_lock(&ctrl->namespaces_mutex); - list_for_each_entry(ns, &ctrl->namespaces, list) - blk_freeze_queue_start(ns->queue); - mutex_unlock(&ctrl->namespaces_mutex); + set_bit(NVME_CTRL_FROZEN, &ctrl->flags); + srcu_idx = srcu_read_lock(&ctrl->srcu); + list_for_each_entry_srcu(ns, &ctrl->namespaces, list, + srcu_read_lock_held(&ctrl->srcu)) + /* + * 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); -void nvme_stop_queues(struct nvme_ctrl *ctrl) +void nvme_quiesce_io_queues(struct nvme_ctrl *ctrl) { - struct nvme_ns *ns; + if (!ctrl->tagset) + return; + if (!test_and_set_bit(NVME_CTRL_STOPPED, &ctrl->flags)) + blk_mq_quiesce_tagset(ctrl->tagset); + else + blk_mq_wait_quiesce_done(ctrl->tagset); +} +EXPORT_SYMBOL_GPL(nvme_quiesce_io_queues); - mutex_lock(&ctrl->namespaces_mutex); - list_for_each_entry(ns, &ctrl->namespaces, list) - blk_mq_quiesce_queue(ns->queue); - mutex_unlock(&ctrl->namespaces_mutex); +void nvme_unquiesce_io_queues(struct nvme_ctrl *ctrl) +{ + if (!ctrl->tagset) + return; + if (test_and_clear_bit(NVME_CTRL_STOPPED, &ctrl->flags)) + blk_mq_unquiesce_tagset(ctrl->tagset); } -EXPORT_SYMBOL_GPL(nvme_stop_queues); +EXPORT_SYMBOL_GPL(nvme_unquiesce_io_queues); -void nvme_start_queues(struct nvme_ctrl *ctrl) +void nvme_quiesce_admin_queue(struct nvme_ctrl *ctrl) +{ + if (!test_and_set_bit(NVME_CTRL_ADMIN_Q_STOPPED, &ctrl->flags)) + blk_mq_quiesce_queue(ctrl->admin_q); + else + blk_mq_wait_quiesce_done(ctrl->admin_q->tag_set); +} +EXPORT_SYMBOL_GPL(nvme_quiesce_admin_queue); + +void nvme_unquiesce_admin_queue(struct nvme_ctrl *ctrl) +{ + if (test_and_clear_bit(NVME_CTRL_ADMIN_Q_STOPPED, &ctrl->flags)) + blk_mq_unquiesce_queue(ctrl->admin_q); +} +EXPORT_SYMBOL_GPL(nvme_unquiesce_admin_queue); + +void nvme_sync_io_queues(struct nvme_ctrl *ctrl) { struct nvme_ns *ns; + int srcu_idx; + + srcu_idx = srcu_read_lock(&ctrl->srcu); + list_for_each_entry_srcu(ns, &ctrl->namespaces, list, + srcu_read_lock_held(&ctrl->srcu)) + blk_sync_queue(ns->queue); + srcu_read_unlock(&ctrl->srcu, srcu_idx); +} +EXPORT_SYMBOL_GPL(nvme_sync_io_queues); + +void nvme_sync_queues(struct nvme_ctrl *ctrl) +{ + nvme_sync_io_queues(ctrl); + if (ctrl->admin_q) + blk_sync_queue(ctrl->admin_q); +} +EXPORT_SYMBOL_GPL(nvme_sync_queues); - mutex_lock(&ctrl->namespaces_mutex); - list_for_each_entry(ns, &ctrl->namespaces, list) - blk_mq_unquiesce_queue(ns->queue); - mutex_unlock(&ctrl->namespaces_mutex); +struct nvme_ctrl *nvme_ctrl_from_file(struct file *file) +{ + if (file->f_op != &nvme_dev_fops) + return NULL; + return file->private_data; +} +EXPORT_SYMBOL_NS_GPL(nvme_ctrl_from_file, "NVME_TARGET_PASSTHRU"); + +/* + * Check we didn't inadvertently grow the command structure sizes: + */ +static inline void _nvme_check_size(void) +{ + BUILD_BUG_ON(sizeof(struct nvme_common_command) != 64); + BUILD_BUG_ON(sizeof(struct nvme_rw_command) != 64); + BUILD_BUG_ON(sizeof(struct nvme_identify) != 64); + BUILD_BUG_ON(sizeof(struct nvme_features) != 64); + BUILD_BUG_ON(sizeof(struct nvme_download_firmware) != 64); + BUILD_BUG_ON(sizeof(struct nvme_format_cmd) != 64); + BUILD_BUG_ON(sizeof(struct nvme_dsm_cmd) != 64); + BUILD_BUG_ON(sizeof(struct nvme_write_zeroes_cmd) != 64); + BUILD_BUG_ON(sizeof(struct nvme_abort_cmd) != 64); + BUILD_BUG_ON(sizeof(struct nvme_get_log_page_command) != 64); + BUILD_BUG_ON(sizeof(struct nvme_command) != 64); + BUILD_BUG_ON(sizeof(struct nvme_id_ctrl) != NVME_IDENTIFY_DATA_SIZE); + BUILD_BUG_ON(sizeof(struct nvme_id_ns) != NVME_IDENTIFY_DATA_SIZE); + BUILD_BUG_ON(sizeof(struct nvme_id_ns_cs_indep) != + NVME_IDENTIFY_DATA_SIZE); + BUILD_BUG_ON(sizeof(struct nvme_id_ns_zns) != NVME_IDENTIFY_DATA_SIZE); + BUILD_BUG_ON(sizeof(struct nvme_id_ns_nvm) != NVME_IDENTIFY_DATA_SIZE); + BUILD_BUG_ON(sizeof(struct nvme_id_ctrl_zns) != NVME_IDENTIFY_DATA_SIZE); + 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); } -EXPORT_SYMBOL_GPL(nvme_start_queues); -int __init nvme_core_init(void) + +static int __init nvme_core_init(void) { - int result; + 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) - return -ENOMEM; + goto out; - result = __register_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme", - &nvme_dev_fops); - if (result < 0) + nvme_reset_wq = alloc_workqueue("nvme-reset-wq", wq_flags, 0); + if (!nvme_reset_wq) goto destroy_wq; - else if (result > 0) - nvme_char_major = result; - nvme_class = class_create(THIS_MODULE, "nvme"); - if (IS_ERR(nvme_class)) { - result = PTR_ERR(nvme_class); + nvme_delete_wq = alloc_workqueue("nvme-delete-wq", wq_flags, 0); + if (!nvme_delete_wq) + goto destroy_reset_wq; + + result = alloc_chrdev_region(&nvme_ctrl_base_chr_devt, 0, + NVME_MINORS, "nvme"); + if (result < 0) + goto destroy_delete_wq; + + result = class_register(&nvme_class); + if (result) goto unregister_chrdev; - } + result = class_register(&nvme_subsys_class); + if (result) + goto destroy_class; + + result = alloc_chrdev_region(&nvme_ns_chr_devt, 0, NVME_MINORS, + "nvme-generic"); + if (result < 0) + goto destroy_subsys_class; + + result = class_register(&nvme_ns_chr_class); + if (result) + goto unregister_generic_ns; + + result = nvme_init_auth(); + if (result) + goto destroy_ns_chr; return 0; +destroy_ns_chr: + class_unregister(&nvme_ns_chr_class); +unregister_generic_ns: + unregister_chrdev_region(nvme_ns_chr_devt, NVME_MINORS); +destroy_subsys_class: + class_unregister(&nvme_subsys_class); +destroy_class: + class_unregister(&nvme_class); unregister_chrdev: - __unregister_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme"); + unregister_chrdev_region(nvme_ctrl_base_chr_devt, NVME_MINORS); +destroy_delete_wq: + destroy_workqueue(nvme_delete_wq); +destroy_reset_wq: + destroy_workqueue(nvme_reset_wq); destroy_wq: destroy_workqueue(nvme_wq); +out: return result; } -void nvme_core_exit(void) +static void __exit nvme_core_exit(void) { - class_destroy(nvme_class); - __unregister_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme"); + nvme_exit_auth(); + class_unregister(&nvme_ns_chr_class); + class_unregister(&nvme_subsys_class); + class_unregister(&nvme_class); + unregister_chrdev_region(nvme_ns_chr_devt, NVME_MINORS); + unregister_chrdev_region(nvme_ctrl_base_chr_devt, NVME_MINORS); + destroy_workqueue(nvme_delete_wq); + destroy_workqueue(nvme_reset_wq); destroy_workqueue(nvme_wq); + ida_destroy(&nvme_ns_chr_minor_ida); + ida_destroy(&nvme_instance_ida); } MODULE_LICENSE("GPL"); MODULE_VERSION("1.0"); +MODULE_DESCRIPTION("NVMe host core framework"); module_init(nvme_core_init); module_exit(nvme_core_exit); |