/*
 * 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/blkdev.h>
#include <linux/blk-mq.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/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>

#define CREATE_TRACE_POINTS
#include "trace.h"

#include "nvme.h"
#include "fabrics.h"

#define NVME_MINORS             (1U << MINORBITS)

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 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);

static unsigned char shutdown_timeout = 5;
module_param(shutdown_timeout, byte, 0644);
MODULE_PARM_DESC(shutdown_timeout, "timeout in seconds for controller shutdown");

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 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,
                 "max power saving latency for new devices; use PM QOS to change per device");

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");

/*
 * 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 are scan, aen handling, fw activation,
 * keep-alive error recovery, 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);

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 DEFINE_IDA(nvme_subsystems_ida);
static LIST_HEAD(nvme_subsystems);
static DEFINE_MUTEX(nvme_subsystems_lock);

static DEFINE_IDA(nvme_instance_ida);
static dev_t nvme_chr_devt;
static struct class *nvme_class;
static struct class *nvme_subsys_class;

static void nvme_ns_remove(struct nvme_ns *ns);
static int nvme_revalidate_disk(struct gendisk *disk);

static __le32 nvme_get_log_dw10(u8 lid, size_t size)
{
        return cpu_to_le32((((size / 4) - 1) << 16) | lid);
}

int nvme_reset_ctrl(struct nvme_ctrl *ctrl)
{
        if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING))
                return -EBUSY;
        if (!queue_work(nvme_reset_wq, &ctrl->reset_work))
                return -EBUSY;
        return 0;
}
EXPORT_SYMBOL_GPL(nvme_reset_ctrl);

int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl)
{
        int ret;

        ret = nvme_reset_ctrl(ctrl);
        if (!ret) {
                flush_work(&ctrl->reset_work);
                if (ctrl->state != NVME_CTRL_LIVE)
                        ret = -ENETRESET;
        }

        return ret;
}
EXPORT_SYMBOL_GPL(nvme_reset_ctrl_sync);

static void nvme_delete_ctrl_work(struct work_struct *work)
{
        struct nvme_ctrl *ctrl =
                container_of(work, struct nvme_ctrl, delete_work);

        flush_work(&ctrl->reset_work);
        nvme_stop_ctrl(ctrl);
        nvme_remove_namespaces(ctrl);
        ctrl->ops->delete_ctrl(ctrl);
        nvme_uninit_ctrl(ctrl);
        nvme_put_ctrl(ctrl);
}

int nvme_delete_ctrl(struct nvme_ctrl *ctrl)
{
        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);

int nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl)
{
        int ret = 0;

        /*
         * Keep a reference until the work is flushed since ->delete_ctrl
         * can free the controller.
         */
        nvme_get_ctrl(ctrl);
        ret = nvme_delete_ctrl(ctrl);
        if (!ret)
                flush_work(&ctrl->delete_work);
        nvme_put_ctrl(ctrl);
        return ret;
}
EXPORT_SYMBOL_GPL(nvme_delete_ctrl_sync);

static inline bool nvme_ns_has_pi(struct nvme_ns *ns)
{
        return ns->pi_type && ns->ms == sizeof(struct t10_pi_tuple);
}

static blk_status_t nvme_error_status(struct request *req)
{
        switch (nvme_req(req)->status & 0x7ff) {
        case NVME_SC_SUCCESS:
                return BLK_STS_OK;
        case NVME_SC_CAP_EXCEEDED:
                return BLK_STS_NOSPC;
        case NVME_SC_LBA_RANGE:
                return BLK_STS_TARGET;
        case NVME_SC_BAD_ATTRIBUTES:
        case NVME_SC_ONCS_NOT_SUPPORTED:
        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_NEXUS;
        default:
                return BLK_STS_IOERR;
        }
}

static inline bool nvme_req_needs_retry(struct request *req)
{
        if (blk_noretry_request(req))
                return false;
        if (nvme_req(req)->status & NVME_SC_DNR)
                return false;
        if (nvme_req(req)->retries >= nvme_max_retries)
                return false;
        return true;
}

void nvme_complete_rq(struct request *req)
{
        blk_status_t status = nvme_error_status(req);

        trace_nvme_complete_rq(req);

        if (unlikely(status != BLK_STS_OK && nvme_req_needs_retry(req))) {
                if (nvme_req_needs_failover(req, status)) {
                        nvme_failover_req(req);
                        return;
                }

                if (!blk_queue_dying(req->q)) {
                        nvme_req(req)->retries++;
                        blk_mq_requeue_request(req, true);
                        return;
                }
        }
        blk_mq_end_request(req, status);
}
EXPORT_SYMBOL_GPL(nvme_complete_rq);

void nvme_cancel_request(struct request *req, void *data, bool reserved)
{
        if (!blk_mq_request_started(req))
                return;

        dev_dbg_ratelimited(((struct nvme_ctrl *) data)->device,
                                "Cancelling I/O %d", req->tag);

        nvme_req(req)->status = NVME_SC_ABORT_REQ;
        blk_mq_complete_request(req);

}
EXPORT_SYMBOL_GPL(nvme_cancel_request);

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_irqsave(&ctrl->lock, flags);

        old_state = ctrl->state;
        switch (new_state) {
        case NVME_CTRL_ADMIN_ONLY:
                switch (old_state) {
                case NVME_CTRL_CONNECTING:
                        changed = true;
                        /* FALLTHRU */
                default:
                        break;
                }
                break;
        case NVME_CTRL_LIVE:
                switch (old_state) {
                case NVME_CTRL_NEW:
                case NVME_CTRL_RESETTING:
                case NVME_CTRL_CONNECTING:
                        changed = true;
                        /* FALLTHRU */
                default:
                        break;
                }
                break;
        case NVME_CTRL_RESETTING:
                switch (old_state) {
                case NVME_CTRL_NEW:
                case NVME_CTRL_LIVE:
                case NVME_CTRL_ADMIN_ONLY:
                        changed = true;
                        /* FALLTHRU */
                default:
                        break;
                }
                break;
        case NVME_CTRL_CONNECTING:
                switch (old_state) {
                case NVME_CTRL_NEW:
                case NVME_CTRL_RESETTING:
                        changed = true;
                        /* FALLTHRU */
                default:
                        break;
                }
                break;
        case NVME_CTRL_DELETING:
                switch (old_state) {
                case NVME_CTRL_LIVE:
                case NVME_CTRL_ADMIN_ONLY:
                case NVME_CTRL_RESETTING:
                case NVME_CTRL_CONNECTING:
                        changed = true;
                        /* FALLTHRU */
                default:
                        break;
                }
                break;
        case NVME_CTRL_DEAD:
                switch (old_state) {
                case NVME_CTRL_DELETING:
                        changed = true;
                        /* FALLTHRU */
                default:
                        break;
                }
                break;
        default:
                break;
        }

        if (changed)
                ctrl->state = new_state;

        spin_unlock_irqrestore(&ctrl->lock, flags);
        if (changed && ctrl->state == NVME_CTRL_LIVE)
                nvme_kick_requeue_lists(ctrl);
        return changed;
}
EXPORT_SYMBOL_GPL(nvme_change_ctrl_state);

static void nvme_free_ns_head(struct kref *ref)
{
        struct nvme_ns_head *head =
                container_of(ref, struct nvme_ns_head, ref);

        nvme_mpath_remove_disk(head);
        ida_simple_remove(&head->subsys->ns_ida, head->instance);
        list_del_init(&head->entry);
        cleanup_srcu_struct(&head->srcu);
        kfree(head);
}

static void nvme_put_ns_head(struct nvme_ns_head *head)
{
        kref_put(&head->ref, nvme_free_ns_head);
}

static void nvme_free_ns(struct kref *kref)
{
        struct nvme_ns *ns = container_of(kref, struct nvme_ns, kref);

        if (ns->ndev)
                nvme_nvm_unregister(ns);

        put_disk(ns->disk);
        nvme_put_ns_head(ns->head);
        nvme_put_ctrl(ns->ctrl);
        kfree(ns);
}

static void nvme_put_ns(struct nvme_ns *ns)
{
        kref_put(&ns->kref, nvme_free_ns);
}

struct request *nvme_alloc_request(struct request_queue *q,
                struct nvme_command *cmd, blk_mq_req_flags_t flags, int qid)
{
        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;
}
EXPORT_SYMBOL_GPL(nvme_alloc_request);

static int nvme_toggle_streams(struct nvme_ctrl *ctrl, bool enable)
{
        struct nvme_command c;

        memset(&c, 0, sizeof(c));

        c.directive.opcode = nvme_admin_directive_send;
        c.directive.nsid = cpu_to_le32(NVME_NSID_ALL);
        c.directive.doper = NVME_DIR_SND_ID_OP_ENABLE;
        c.directive.dtype = NVME_DIR_IDENTIFY;
        c.directive.tdtype = NVME_DIR_STREAMS;
        c.directive.endir = enable ? NVME_DIR_ENDIR : 0;

        return nvme_submit_sync_cmd(ctrl->admin_q, &c, NULL, 0);
}

static int nvme_disable_streams(struct nvme_ctrl *ctrl)
{
        return nvme_toggle_streams(ctrl, false);
}

static int nvme_enable_streams(struct nvme_ctrl *ctrl)
{
        return nvme_toggle_streams(ctrl, true);
}

static int nvme_get_stream_params(struct nvme_ctrl *ctrl,
                                  struct streams_directive_params *s, u32 nsid)
{
        struct nvme_command c;

        memset(&c, 0, sizeof(c));
        memset(s, 0, sizeof(*s));

        c.directive.opcode = nvme_admin_directive_recv;
        c.directive.nsid = cpu_to_le32(nsid);
        c.directive.numd = cpu_to_le32((sizeof(*s) >> 2) - 1);
        c.directive.doper = NVME_DIR_RCV_ST_OP_PARAM;
        c.directive.dtype = NVME_DIR_STREAMS;

        return nvme_submit_sync_cmd(ctrl->admin_q, &c, s, sizeof(*s));
}

static int nvme_configure_directives(struct nvme_ctrl *ctrl)
{
        struct streams_directive_params s;
        int ret;

        if (!(ctrl->oacs & NVME_CTRL_OACS_DIRECTIVES))
                return 0;
        if (!streams)
                return 0;

        ret = nvme_enable_streams(ctrl);
        if (ret)
                return ret;

        ret = nvme_get_stream_params(ctrl, &s, NVME_NSID_ALL);
        if (ret)
                return ret;

        ctrl->nssa = le16_to_cpu(s.nssa);
        if (ctrl->nssa < BLK_MAX_WRITE_HINTS - 1) {
                dev_info(ctrl->device, "too few streams (%u) available\n",
                                        ctrl->nssa);
                nvme_disable_streams(ctrl);
                return 0;
        }

        ctrl->nr_streams = min_t(unsigned, ctrl->nssa, BLK_MAX_WRITE_HINTS - 1);
        dev_info(ctrl->device, "Using %u streams\n", ctrl->nr_streams);
        return 0;
}

/*
 * Check if 'req' has a write hint associated with it. If it does, assign
 * a valid namespace stream to the write.
 */
static void nvme_assign_write_stream(struct nvme_ctrl *ctrl,
                                     struct request *req, u16 *control,
                                     u32 *dsmgmt)
{
        enum rw_hint streamid = req->write_hint;

        if (streamid == WRITE_LIFE_NOT_SET || streamid == WRITE_LIFE_NONE)
                streamid = 0;
        else {
                streamid--;
                if (WARN_ON_ONCE(streamid > ctrl->nr_streams))
                        return;

                *control |= NVME_RW_DTYPE_STREAMS;
                *dsmgmt |= streamid << 16;
        }

        if (streamid < ARRAY_SIZE(req->q->write_hints))
                req->q->write_hints[streamid] += blk_rq_bytes(req) >> 9;
}

static inline void nvme_setup_flush(struct nvme_ns *ns,
                struct nvme_command *cmnd)
{
        memset(cmnd, 0, sizeof(*cmnd));
        cmnd->common.opcode = nvme_cmd_flush;
        cmnd->common.nsid = cpu_to_le32(ns->head->ns_id);
}

static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
                struct nvme_command *cmnd)
{
        unsigned short segments = blk_rq_nr_discard_segments(req), n = 0;
        struct nvme_dsm_range *range;
        struct bio *bio;

        range = kmalloc_array(segments, sizeof(*range), GFP_ATOMIC);
        if (!range)
                return BLK_STS_RESOURCE;

        __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;

                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);
                return BLK_STS_IOERR;
        }

        memset(cmnd, 0, sizeof(*cmnd));
        cmnd->dsm.opcode = nvme_cmd_dsm;
        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;
        req->rq_flags |= RQF_SPECIAL_PAYLOAD;

        return BLK_STS_OK;
}

static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
                struct request *req, struct nvme_command *cmnd)
{
        struct nvme_ctrl *ctrl = ns->ctrl;
        u16 control = 0;
        u32 dsmgmt = 0;

        if (req->cmd_flags & REQ_FUA)
                control |= NVME_RW_FUA;
        if (req->cmd_flags & (REQ_FAILFAST_DEV | REQ_RAHEAD))
                control |= NVME_RW_LR;

        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->head->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 (req_op(req) == REQ_OP_WRITE && ctrl->nr_streams)
                nvme_assign_write_stream(ctrl, req, &control, &dsmgmt);

        if (ns->ms) {
                /*
                 * If formated 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)))
                                return BLK_STS_NOTSUPP;
                        control |= NVME_RW_PRINFO_PRACT;
                }

                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;
                }
        }

        cmnd->rw.control = cpu_to_le16(control);
        cmnd->rw.dsmgmt = cpu_to_le32(dsmgmt);
        return 0;
}

blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
                struct nvme_command *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;
        }

        switch (req_op(req)) {
        case REQ_OP_DRV_IN:
        case REQ_OP_DRV_OUT:
                memcpy(cmd, nvme_req(req)->cmd, sizeof(*cmd));
                break;
        case REQ_OP_FLUSH:
                nvme_setup_flush(ns, cmd);
                break;
        case REQ_OP_WRITE_ZEROES:
                /* currently only aliased to deallocate for a few ctrls: */
        case REQ_OP_DISCARD:
                ret = nvme_setup_discard(ns, req, cmd);
                break;
        case REQ_OP_READ:
        case REQ_OP_WRITE:
                ret = nvme_setup_rw(ns, req, cmd);
                break;
        default:
                WARN_ON_ONCE(1);
                return BLK_STS_IOERR;
        }

        cmd->common.command_id = req->tag;
        if (ns)
                trace_nvme_setup_nvm_cmd(req->q->id, cmd);
        else
                trace_nvme_setup_admin_cmd(cmd);
        return ret;
}
EXPORT_SYMBOL_GPL(nvme_setup_cmd);

/*
 * 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,
                blk_mq_req_flags_t flags)
{
        struct request *req;
        int ret;

        req = nvme_alloc_request(q, cmd, flags, qid);
        if (IS_ERR(req))
                return PTR_ERR(req);

        req->timeout = timeout ? timeout : ADMIN_TIMEOUT;

        if (buffer && bufflen) {
                ret = blk_rq_map_kern(q, req, buffer, bufflen, GFP_KERNEL);
                if (ret)
                        goto out;
        }

        blk_execute_rq(req->q, NULL, req, at_head);
        if (result)
                *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;
}
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);
}
EXPORT_SYMBOL_GPL(nvme_submit_sync_cmd);

static void *nvme_add_user_metadata(struct bio *bio, void __user *ubuf,
                unsigned len, u32 seed, bool write)
{
        struct bio_integrity_payload *bip;
        int ret = -ENOMEM;
        void *buf;

        buf = kmalloc(len, GFP_KERNEL);
        if (!buf)
                goto out;

        ret = -EFAULT;
        if (write && copy_from_user(buf, ubuf, len))
                goto out_free_meta;

        bip = bio_integrity_alloc(bio, GFP_KERNEL, 1);
        if (IS_ERR(bip)) {
                ret = PTR_ERR(bip);
                goto out_free_meta;
        }

        bip->bip_iter.bi_size = len;
        bip->bip_iter.bi_sector = seed;
        ret = bio_integrity_add_page(bio, virt_to_page(buf), len,
                        offset_in_page(buf));
        if (ret == len)
                return buf;
        ret = -ENOMEM;
out_free_meta:
        kfree(buf);
out:
        return ERR_PTR(ret);
}

static int nvme_submit_user_cmd(struct request_queue *q,
                struct nvme_command *cmd, void __user *ubuffer,
                unsigned bufflen, void __user *meta_buffer, unsigned meta_len,
                u32 meta_seed, u32 *result, unsigned timeout)
{
        bool write = nvme_is_write(cmd);
        struct nvme_ns *ns = q->queuedata;
        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;

        if (ubuffer && bufflen) {
                ret = blk_rq_map_user(q, req, NULL, ubuffer, bufflen,
                                GFP_KERNEL);
                if (ret)
                        goto out;
                bio = req->bio;
                bio->bi_disk = disk;
                if (disk && meta_buffer && meta_len) {
                        meta = nvme_add_user_metadata(bio, meta_buffer, meta_len,
                                        meta_seed, write);
                        if (IS_ERR(meta)) {
                                ret = PTR_ERR(meta);
                                goto out_unmap;
                        }
                }
        }

        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;
        }
        kfree(meta);
 out_unmap:
        if (bio)
                blk_rq_unmap_user(bio);
 out:
        blk_mq_free_request(req);
        return ret;
}

static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status)
{
        struct nvme_ctrl *ctrl = rq->end_io_data;

        blk_mq_free_request(rq);

        if (status) {
                dev_err(ctrl->device,
                        "failed nvme_keep_alive_end_io error=%d\n",
                                status);
                return;
        }

        schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
}

static int nvme_keep_alive(struct nvme_ctrl *ctrl)
{
        struct request *rq;

        rq = nvme_alloc_request(ctrl->admin_q, &ctrl->ka_cmd, 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;
}

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);

        if (nvme_keep_alive(ctrl)) {
                /* allocation failure, reset the controller */
                dev_err(ctrl->device, "keep-alive failed\n");
                nvme_reset_ctrl(ctrl);
                return;
        }
}

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);
        memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd));
        ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive;
        schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
}
EXPORT_SYMBOL_GPL(nvme_start_keep_alive);

void nvme_stop_keep_alive(struct nvme_ctrl *ctrl)
{
        if (unlikely(ctrl->kato == 0))
                return;

        cancel_delayed_work_sync(&ctrl->ka_work);
}
EXPORT_SYMBOL_GPL(nvme_stop_keep_alive);

static int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id)
{
        struct nvme_command c = { };
        int error;

        /* gcc-4.4.4 (at least) has issues with initializers and anon unions */
        c.identify.opcode = nvme_admin_identify;
        c.identify.cns = NVME_ID_CNS_CTRL;

        *id = kmalloc(sizeof(struct nvme_id_ctrl), GFP_KERNEL);
        if (!*id)
                return -ENOMEM;

        error = nvme_submit_sync_cmd(dev->admin_q, &c, *id,
                        sizeof(struct nvme_id_ctrl));
        if (error)
                kfree(*id);
        return error;
}

static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid,
                struct nvme_ns_ids *ids)
{
        struct nvme_command c = { };
        int status;
        void *data;
        int pos;
        int len;

        c.identify.opcode = nvme_admin_identify;
        c.identify.nsid = cpu_to_le32(nsid);
        c.identify.cns = NVME_ID_CNS_NS_DESC_LIST;

        data = kzalloc(NVME_IDENTIFY_DATA_SIZE, GFP_KERNEL);
        if (!data)
                return -ENOMEM;

        status = nvme_submit_sync_cmd(ctrl->admin_q, &c, data,
                                      NVME_IDENTIFY_DATA_SIZE);
        if (status)
                goto free_data;

        for (pos = 0; pos < NVME_IDENTIFY_DATA_SIZE; pos += len) {
                struct nvme_ns_id_desc *cur = data + pos;

                if (cur->nidl == 0)
                        break;

                switch (cur->nidt) {
                case NVME_NIDT_EUI64:
                        if (cur->nidl != NVME_NIDT_EUI64_LEN) {
                                dev_warn(ctrl->device,
                                         "ctrl returned bogus length: %d for NVME_NIDT_EUI64\n",
                                         cur->nidl);
                                goto free_data;
                        }
                        len = NVME_NIDT_EUI64_LEN;
                        memcpy(ids->eui64, data + pos + sizeof(*cur), len);
                        break;
                case NVME_NIDT_NGUID:
                        if (cur->nidl != NVME_NIDT_NGUID_LEN) {
                                dev_warn(ctrl->device,
                                         "ctrl returned bogus length: %d for NVME_NIDT_NGUID\n",
                                         cur->nidl);
                                goto free_data;
                        }
                        len = NVME_NIDT_NGUID_LEN;
                        memcpy(ids->nguid, data + pos + sizeof(*cur), len);
                        break;
                case NVME_NIDT_UUID:
                        if (cur->nidl != NVME_NIDT_UUID_LEN) {
                                dev_warn(ctrl->device,
                                         "ctrl returned bogus length: %d for NVME_NIDT_UUID\n",
                                         cur->nidl);
                                goto free_data;
                        }
                        len = NVME_NIDT_UUID_LEN;
                        uuid_copy(&ids->uuid, data + pos + sizeof(*cur));
                        break;
                default:
                        /* Skip unnkown types */
                        len = cur->nidl;
                        break;
                }

                len += sizeof(*cur);
        }
free_data:
        kfree(data);
        return status;
}

static int nvme_identify_ns_list(struct nvme_ctrl *dev, unsigned nsid, __le32 *ns_list)
{
        struct nvme_command c = { };

        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 struct nvme_id_ns *nvme_identify_ns(struct nvme_ctrl *ctrl,
                unsigned nsid)
{
        struct nvme_id_ns *id;
        struct nvme_command c = { };
        int error;

        /* gcc-4.4.4 (at least) has issues with initializers and anon unions */
        c.identify.opcode = nvme_admin_identify;
        c.identify.nsid = cpu_to_le32(nsid);
        c.identify.cns = NVME_ID_CNS_NS;

        id = kmalloc(sizeof(*id), GFP_KERNEL);
        if (!id)
                return NULL;

        error = nvme_submit_sync_cmd(ctrl->admin_q, &c, id, sizeof(*id));
        if (error) {
                dev_warn(ctrl->device, "Identify namespace failed\n");
                kfree(id);
                return NULL;
        }

        return id;
}

static int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11,
                      void *buffer, size_t buflen, u32 *result)
{
        struct nvme_command c;
        union nvme_result res;
        int ret;

        memset(&c, 0, sizeof(c));
        c.features.opcode = nvme_admin_set_features;
        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);
        if (ret >= 0 && result)
                *result = le32_to_cpu(res.u32);
        return ret;
}

int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count)
{

        u32 q_count = (*count - 1) | ((*count - 1) << 16);
        u32 result;
        int status, nr_io_queues;

        status = nvme_set_features(ctrl, NVME_FEAT_NUM_QUEUES, q_count, NULL, 0,
                        &result);
        if (status < 0)
                return status;

        /*
         * Degraded controllers might return an error when setting the queue
         * count.  We still want to be able to bring them online and offer
         * access to the admin queue, as that might be only way to fix them up.
         */
        if (status > 0) {
                dev_err(ctrl->device, "Could not set queue count (%d)\n", status);
                *count = 0;
        } else {
                nr_io_queues = min(result & 0xffff, result >> 16) + 1;
                *count = min(*count, nr_io_queues);
        }

        return 0;
}
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;

        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;

        if (ns->ext) {
                length += meta_len;
                meta_len = 0;
        } else if (meta_len) {
                if ((io.metadata & 3) || !io.metadata)
                        return -EINVAL;
        }

        memset(&c, 0, sizeof(c));
        c.rw.opcode = io.opcode;
        c.rw.flags = io.flags;
        c.rw.nsid = cpu_to_le32(ns->head->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);

        return nvme_submit_user_cmd(ns->queue, &c,
                        (void __user *)(uintptr_t)io.addr, length,
                        metadata, meta_len, io.slba, NULL, 0);
}

static u32 nvme_known_admin_effects(u8 opcode)
{
        switch (opcode) {
        case nvme_admin_format_nvm:
                return NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC |
                                        NVME_CMD_EFFECTS_CSE_MASK;
        case nvme_admin_sanitize_nvm:
                return NVME_CMD_EFFECTS_CSE_MASK;
        default:
                break;
        }
        return 0;
}

static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
                                                                u8 opcode)
{
        u32 effects = 0;

        if (ns) {
                if (ctrl->effects)
                        effects = le32_to_cpu(ctrl->effects->iocs[opcode]);
                if (effects & ~NVME_CMD_EFFECTS_CSUPP)
                        dev_warn(ctrl->device,
                                 "IO command:%02x has unhandled effects:%08x\n",
                                 opcode, effects);
                return 0;
        }

        if (ctrl->effects)
                effects = le32_to_cpu(ctrl->effects->iocs[opcode]);
        else
                effects = nvme_known_admin_effects(opcode);

        /*
         * For simplicity, IO to all namespaces is quiesced even if the command
         * effects say only one namespace is affected.
         */
        if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) {
                nvme_start_freeze(ctrl);
                nvme_wait_freeze(ctrl);
        }
        return effects;
}

static void nvme_update_formats(struct nvme_ctrl *ctrl)
{
        struct nvme_ns *ns, *next;
        LIST_HEAD(rm_list);

        mutex_lock(&ctrl->namespaces_mutex);
        list_for_each_entry(ns, &ctrl->namespaces, list) {
                if (ns->disk && nvme_revalidate_disk(ns->disk)) {
                        list_move_tail(&ns->list, &rm_list);
                }
        }
        mutex_unlock(&ctrl->namespaces_mutex);

        list_for_each_entry_safe(ns, next, &rm_list, list)
                nvme_ns_remove(ns);
}

static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
{
        /*
         * Revalidate LBA changes prior to unfreezing. This is necessary to
         * prevent memory corruption if a logical block size was changed by
         * this command.
         */
        if (effects & NVME_CMD_EFFECTS_LBCC)
                nvme_update_formats(ctrl);
        if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK))
                nvme_unfreeze(ctrl);
        if (effects & NVME_CMD_EFFECTS_CCC)
                nvme_init_identify(ctrl);
        if (effects & (NVME_CMD_EFFECTS_NIC | NVME_CMD_EFFECTS_NCC))
                nvme_queue_scan(ctrl);
}

static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
                        struct nvme_passthru_cmd __user *ucmd)
{
        struct nvme_passthru_cmd cmd;
        struct nvme_command c;
        unsigned timeout = 0;
        u32 effects;
        int status;

        if (!capable(CAP_SYS_ADMIN))
                return -EACCES;
        if (copy_from_user(&cmd, ucmd, sizeof(cmd)))
                return -EFAULT;
        if (cmd.flags)
                return -EINVAL;

        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);

        effects = nvme_passthru_start(ctrl, ns, cmd.opcode);
        status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
                        (void __user *)(uintptr_t)cmd.addr, cmd.data_len,
                        (void __user *)(uintptr_t)cmd.metadata, cmd.metadata,
                        0, &cmd.result, timeout);
        nvme_passthru_end(ctrl, effects);

        if (status >= 0) {
                if (put_user(cmd.result, &ucmd->result))
                        return -EFAULT;
        }

        return status;
}

/*
 * Issue ioctl requests on the first available path.  Note that unlike normal
 * block layer requests we will not retry failed request on another controller.
 */
static struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk,
                struct nvme_ns_head **head, int *srcu_idx)
{
#ifdef CONFIG_NVME_MULTIPATH
        if (disk->fops == &nvme_ns_head_ops) {
                *head = disk->private_data;
                *srcu_idx = srcu_read_lock(&(*head)->srcu);
                return nvme_find_path(*head);
        }
#endif
        *head = NULL;
        *srcu_idx = -1;
        return disk->private_data;
}

static void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx)
{
        if (head)
                srcu_read_unlock(&head->srcu, idx);
}

static int nvme_ns_ioctl(struct nvme_ns *ns, unsigned cmd, unsigned long arg)
{
        switch (cmd) {
        case NVME_IOCTL_ID:
                force_successful_syscall_return();
                return ns->head->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;
        }
}

static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
                unsigned int cmd, unsigned long arg)
{
        struct nvme_ns_head *head = NULL;
        struct nvme_ns *ns;
        int srcu_idx, ret;

        ns = nvme_get_ns_from_disk(bdev->bd_disk, &head, &srcu_idx);
        if (unlikely(!ns))
                ret = -EWOULDBLOCK;
        else
                ret = nvme_ns_ioctl(ns, cmd, arg);
        nvme_put_ns_from_disk(head, srcu_idx);
        return ret;
}

static int nvme_open(struct block_device *bdev, fmode_t mode)
{
        struct nvme_ns *ns = bdev->bd_disk->private_data;

#ifdef CONFIG_NVME_MULTIPATH
        /* should never be called due to GENHD_FL_HIDDEN */
        if (WARN_ON_ONCE(ns->head->disk))
                goto fail;
#endif
        if (!kref_get_unless_zero(&ns->kref))
                goto fail;
        if (!try_module_get(ns->ctrl->ops->module))
                goto fail_put_ns;

        return 0;

fail_put_ns:
        nvme_put_ns(ns);
fail:
        return -ENXIO;
}

static void nvme_release(struct gendisk *disk, fmode_t mode)
{
        struct nvme_ns *ns = disk->private_data;

        module_put(ns->ctrl->ops->module);
        nvme_put_ns(ns);
}

static int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo)
{
        /* some standard values */
        geo->heads = 1 << 6;
        geo->sectors = 1 << 5;
        geo->cylinders = get_capacity(bdev->bd_disk) >> 11;
        return 0;
}

#ifdef CONFIG_BLK_DEV_INTEGRITY
static void nvme_init_integrity(struct gendisk *disk, u16 ms, u8 pi_type)
{
        struct blk_integrity integrity;

        memset(&integrity, 0, sizeof(integrity));
        switch (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;
                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;
                break;
        default:
                integrity.profile = NULL;
                break;
        }
        integrity.tuple_size = ms;
        blk_integrity_register(disk, &integrity);
        blk_queue_max_integrity_segments(disk->queue, 1);
}
#else
static void nvme_init_integrity(struct gendisk *disk, u16 ms, u8 pi_type)
{
}
#endif /* CONFIG_BLK_DEV_INTEGRITY */

static void nvme_set_chunk_size(struct nvme_ns *ns)
{
        u32 chunk_size = (((u32)ns->noiob) << (ns->lba_shift - 9));
        blk_queue_chunk_sectors(ns->queue, rounddown_pow_of_two(chunk_size));
}

static void nvme_config_discard(struct nvme_ctrl *ctrl,
                unsigned stream_alignment, struct request_queue *queue)
{
        u32 size = queue_logical_block_size(queue);

        if (stream_alignment)
                size *= stream_alignment;

        BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) <
                        NVME_DSM_MAX_RANGES);

        queue->limits.discard_alignment = 0;
        queue->limits.discard_granularity = size;

        blk_queue_max_discard_sectors(queue, UINT_MAX);
        blk_queue_max_discard_segments(queue, NVME_DSM_MAX_RANGES);
        queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, queue);

        if (ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES)
                blk_queue_max_write_zeroes_sectors(queue, UINT_MAX);
}

static void nvme_report_ns_ids(struct nvme_ctrl *ctrl, unsigned int nsid,
                struct nvme_id_ns *id, struct nvme_ns_ids *ids)
{
        memset(ids, 0, sizeof(*ids));

        if (ctrl->vs >= NVME_VS(1, 1, 0))
                memcpy(ids->eui64, id->eui64, sizeof(id->eui64));
        if (ctrl->vs >= NVME_VS(1, 2, 0))
                memcpy(ids->nguid, id->nguid, sizeof(id->nguid));
        if (ctrl->vs >= NVME_VS(1, 3, 0)) {
                 /* Don't treat error as fatal we potentially
                  * already have a NGUID or EUI-64
                  */
                if (nvme_identify_ns_descs(ctrl, nsid, ids))
                        dev_warn(ctrl->device,
                                 "%s: Identify Descriptors failed\n", __func__);
        }
}

static bool nvme_ns_ids_valid(struct nvme_ns_ids *ids)
{
        return !uuid_is_null(&ids->uuid) ||
                memchr_inv(ids->nguid, 0, sizeof(ids->nguid)) ||
                memchr_inv(ids->eui64, 0, sizeof(ids->eui64));
}

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;
}

static void nvme_update_disk_info(struct gendisk *disk,
                struct nvme_ns *ns, struct nvme_id_ns *id)
{
        sector_t capacity = le64_to_cpup(&id->nsze) << (ns->lba_shift - 9);
        unsigned short bs = 1 << ns->lba_shift;
        unsigned stream_alignment = 0;

        if (ns->ctrl->nr_streams && ns->sws && ns->sgs)
                stream_alignment = ns->sws * ns->sgs;

        blk_mq_freeze_queue(disk->queue);
        blk_integrity_unregister(disk);

        blk_queue_logical_block_size(disk->queue, bs);
        blk_queue_physical_block_size(disk->queue, bs);
        blk_queue_io_min(disk->queue, bs);

        if (ns->ms && !ns->ext &&
            (ns->ctrl->ops->flags & NVME_F_METADATA_SUPPORTED))
                nvme_init_integrity(disk, ns->ms, ns->pi_type);
        if (ns->ms && !nvme_ns_has_pi(ns) && !blk_get_integrity(disk))
                capacity = 0;
        set_capacity(disk, capacity);

        if (ns->ctrl->oncs & NVME_CTRL_ONCS_DSM)
                nvme_config_discard(ns->ctrl, stream_alignment, disk->queue);
        blk_mq_unfreeze_queue(disk->queue);
}

static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
{
        struct nvme_ns *ns = disk->private_data;

        /*
         * If identify namespace failed, use default 512 byte block size so
         * block layer can use before failing read/write for 0 capacity.
         */
        ns->lba_shift = id->lbaf[id->flbas & NVME_NS_FLBAS_LBA_MASK].ds;
        if (ns->lba_shift == 0)
                ns->lba_shift = 9;
        ns->noiob = le16_to_cpu(id->noiob);
        ns->ext = ns->ms && (id->flbas & NVME_NS_FLBAS_META_EXT);
        ns->ms = le16_to_cpu(id->lbaf[id->flbas & NVME_NS_FLBAS_LBA_MASK].ms);
        /* the PI implementation requires metadata equal t10 pi tuple size */
        if (ns->ms == sizeof(struct t10_pi_tuple))
                ns->pi_type = id->dps & NVME_NS_DPS_PI_MASK;
        else
                ns->pi_type = 0;

        if (ns->noiob)
                nvme_set_chunk_size(ns);
        nvme_update_disk_info(disk, ns, id);
#ifdef CONFIG_NVME_MULTIPATH
        if (ns->head->disk)
                nvme_update_disk_info(ns->head->disk, ns, id);
#endif
}

static int nvme_revalidate_disk(struct gendisk *disk)
{
        struct nvme_ns *ns = disk->private_data;
        struct nvme_ctrl *ctrl = ns->ctrl;
        struct nvme_id_ns *id;
        struct nvme_ns_ids ids;
        int ret = 0;

        if (test_bit(NVME_NS_DEAD, &ns->flags)) {
                set_capacity(disk, 0);
                return -ENODEV;
        }

        id = nvme_identify_ns(ctrl, ns->head->ns_id);
        if (!id)
                return -ENODEV;

        if (id->ncap == 0) {
                ret = -ENODEV;
                goto out;
        }

        __nvme_revalidate_disk(disk, id);
        nvme_report_ns_ids(ctrl, ns->head->ns_id, id, &ids);
        if (!nvme_ns_ids_equal(&ns->head->ids, &ids)) {
                dev_err(ctrl->device,
                        "identifiers changed for nsid %d\n", ns->head->ns_id);
                ret = -ENODEV;
        }

out:
        kfree(id);
        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:
                return 0;
        }
};

static int nvme_pr_command(struct block_device *bdev, u32 cdw10,
                                u64 key, u64 sa_key, u8 op)
{
        struct nvme_ns_head *head = NULL;
        struct nvme_ns *ns;
        struct nvme_command c;
        int srcu_idx, ret;
        u8 data[16] = { 0, };

        ns = nvme_get_ns_from_disk(bdev->bd_disk, &head, &srcu_idx);
        if (unlikely(!ns))
                return -EWOULDBLOCK;

        put_unaligned_le64(key, &data[0]);
        put_unaligned_le64(sa_key, &data[8]);

        memset(&c, 0, sizeof(c));
        c.common.opcode = op;
        c.common.nsid = cpu_to_le32(ns->head->ns_id);
        c.common.cdw10[0] = cpu_to_le32(cdw10);

        ret = nvme_submit_sync_cmd(ns->queue, &c, data, 16);
        nvme_put_ns_from_disk(head, srcu_idx);
        return ret;
}

static int nvme_pr_register(struct block_device *bdev, u64 old,
                u64 new, unsigned flags)
{
        u32 cdw10;

        if (flags & ~PR_FL_IGNORE_KEY)
                return -EOPNOTSUPP;

        cdw10 = old ? 2 : 0;
        cdw10 |= (flags & PR_FL_IGNORE_KEY) ? 1 << 3 : 0;
        cdw10 |= (1 << 30) | (1 << 31); /* PTPL=1 */
        return nvme_pr_command(bdev, cdw10, old, new, nvme_cmd_resv_register);
}

static int nvme_pr_reserve(struct block_device *bdev, u64 key,
                enum pr_type type, unsigned flags)
{
        u32 cdw10;

        if (flags & ~PR_FL_IGNORE_KEY)
                return -EOPNOTSUPP;

        cdw10 = nvme_pr_type(type) << 8;
        cdw10 |= ((flags & PR_FL_IGNORE_KEY) ? 1 << 3 : 0);
        return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_acquire);
}

static int nvme_pr_preempt(struct block_device *bdev, u64 old, u64 new,
                enum pr_type type, bool abort)
{
        u32 cdw10 = nvme_pr_type(type) << 8 | abort ? 2 : 1;
        return nvme_pr_command(bdev, cdw10, old, new, nvme_cmd_resv_acquire);
}

static int nvme_pr_clear(struct block_device *bdev, u64 key)
{
        u32 cdw10 = 1 | (key ? 1 << 3 : 0);
        return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_register);
}

static int nvme_pr_release(struct block_device *bdev, u64 key, enum pr_type type)
{
        u32 cdw10 = nvme_pr_type(type) << 8 | key ? 1 << 3 : 0;
        return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_release);
}

static const struct pr_ops nvme_pr_ops = {
        .pr_register    = nvme_pr_register,
        .pr_reserve     = nvme_pr_reserve,
        .pr_release     = nvme_pr_release,
        .pr_preempt     = nvme_pr_preempt,
        .pr_clear       = nvme_pr_clear,
};

#ifdef CONFIG_BLK_SED_OPAL
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;

        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);

        return __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, NULL, buffer, len,
                                      ADMIN_TIMEOUT, NVME_QID_ANY, 1, 0);
}
EXPORT_SYMBOL_GPL(nvme_sec_submit);
#endif /* CONFIG_BLK_SED_OPAL */

static const struct block_device_operations nvme_fops = {
        .owner          = THIS_MODULE,
        .ioctl          = nvme_ioctl,
        .compat_ioctl   = nvme_ioctl,
        .open           = nvme_open,
        .release        = nvme_release,
        .getgeo         = nvme_getgeo,
        .revalidate_disk= nvme_revalidate_disk,
        .pr_ops         = &nvme_pr_ops,
};

#ifdef CONFIG_NVME_MULTIPATH
static int nvme_ns_head_open(struct block_device *bdev, fmode_t mode)
{
        struct nvme_ns_head *head = bdev->bd_disk->private_data;

        if (!kref_get_unless_zero(&head->ref))
                return -ENXIO;
        return 0;
}

static void nvme_ns_head_release(struct gendisk *disk, fmode_t mode)
{
        nvme_put_ns_head(disk->private_data);
}

const struct block_device_operations nvme_ns_head_ops = {
        .owner          = THIS_MODULE,
        .open           = nvme_ns_head_open,
        .release        = nvme_ns_head_release,
        .ioctl          = nvme_ioctl,
        .compat_ioctl   = nvme_ioctl,
        .getgeo         = nvme_getgeo,
        .pr_ops         = &nvme_pr_ops,
};
#endif /* CONFIG_NVME_MULTIPATH */

static int nvme_wait_ready(struct nvme_ctrl *ctrl, u64 cap, bool enabled)
{
        unsigned long timeout =
                ((NVME_CAP_TIMEOUT(cap) + 1) * HZ / 2) + jiffies;
        u32 csts, bit = enabled ? NVME_CSTS_RDY : 0;
        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)
                        break;

                msleep(100);
                if (fatal_signal_pending(current))
                        return -EINTR;
                if (time_after(jiffies, timeout)) {
                        dev_err(ctrl->device,
                                "Device not ready; aborting %s\n", enabled ?
                                                "initialisation" : "reset");
                        return -ENODEV;
                }
        }

        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 ret;

        ctrl->ctrl_config &= ~NVME_CC_SHN_MASK;
        ctrl->ctrl_config &= ~NVME_CC_ENABLE;

        ret = ctrl->ops->reg_write32(ctrl, NVME_REG_CC, ctrl->ctrl_config);
        if (ret)
                return ret;

        if (ctrl->quirks & NVME_QUIRK_DELAY_BEFORE_CHK_RDY)
                msleep(NVME_QUIRK_DELAY_AMOUNT);

        return nvme_wait_ready(ctrl, cap, false);
}
EXPORT_SYMBOL_GPL(nvme_disable_ctrl);

int nvme_enable_ctrl(struct nvme_ctrl *ctrl, u64 cap)
{
        /*
         * 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;
        int ret;

        if (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);
                return -ENODEV;
        }

        ctrl->page_size = 1 << page_shift;

        ctrl->ctrl_config = NVME_CC_CSS_NVM;
        ctrl->ctrl_config |= (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;
        return nvme_wait_ready(ctrl, cap, true);
}
EXPORT_SYMBOL_GPL(nvme_enable_ctrl);

int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl)
{
        unsigned long timeout = jiffies + (ctrl->shutdown_timeout * HZ);
        u32 csts;
        int ret;

        ctrl->ctrl_config &= ~NVME_CC_SHN_MASK;
        ctrl->ctrl_config |= NVME_CC_SHN_NORMAL;

        ret = ctrl->ops->reg_write32(ctrl, NVME_REG_CC, ctrl->ctrl_config);
        if (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;

                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;
                }
        }

        return ret;
}
EXPORT_SYMBOL_GPL(nvme_shutdown_ctrl);

static void nvme_set_queue_limits(struct nvme_ctrl *ctrl,
                struct request_queue *q)
{
        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 ((ctrl->quirks & NVME_QUIRK_STRIPE_SIZE) &&
            is_power_of_2(ctrl->max_hw_sectors))
                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);
}

static int nvme_configure_timestamp(struct nvme_ctrl *ctrl)
{
        __le64 ts;
        int ret;

        if (!(ctrl->oncs & NVME_CTRL_ONCS_TIMESTAMP))
                return 0;

        ts = cpu_to_le64(ktime_to_ms(ktime_get_real()));
        ret = nvme_set_features(ctrl, NVME_FEAT_TIMESTAMP, 0, &ts, sizeof(ts),
                        NULL);
        if (ret)
                dev_warn_once(ctrl->device,
                        "could not set timestamp (%d)\n", ret);
        return ret;
}

static int nvme_configure_apst(struct nvme_ctrl *ctrl)
{
        /*
         * APST (Autonomous Power State Transition) lets us program a
         * 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;
        u64 max_lat_us = 0;
        int max_ps = -1;
        int ret;

        /*
         * If APST isn't supported or if we haven't been initialized yet,
         * then don't do anything.
         */
        if (!ctrl->apsta)
                return 0;

        if (ctrl->npss > 31) {
                dev_warn(ctrl->device, "NPSS is invalid; not using APST\n");
                return 0;
        }

        table = kzalloc(sizeof(*table), GFP_KERNEL);
        if (!table)
                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;

                /*
                 * 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;

                        /*
                         * 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;

                        /*
                         * 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;

                        exit_latency_us =
                                (u64)le32_to_cpu(ctrl->psd[state].exit_lat);
                        if (exit_latency_us > ctrl->ps_max_latency_us)
                                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.
                         */
                        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);
                }
        }

        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)
{
        struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
        u64 latency;

        switch (val) {
        case PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT:
        case PM_QOS_LATENCY_ANY:
                latency = U64_MAX;
                break;

        default:
                latency = val;
        }

        if (ctrl->ps_max_latency_us != latency) {
                ctrl->ps_max_latency_us = latency;
                nvme_configure_apst(ctrl);
        }
}

struct nvme_core_quirk_entry {
        /*
         * NVMe model and firmware strings are padded with spaces.  For
         * simplicity, strings in the quirk table are padded with NULLs
         * instead.
         */
        u16 vid;
        const char *mn;
        const char *fr;
        unsigned long quirks;
};

static const struct nvme_core_quirk_entry core_quirks[] = {
        {
                /*
                 * This Toshiba device seems to die using any APST states.  See:
                 * https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1678184/comments/11
                 */
                .vid = 0x1179,
                .mn = "THNSF5256GPUK TOSHIBA",
                .quirks = NVME_QUIRK_NO_APST,
        }
};

/* match is null-terminated but idstr is space-padded. */
static bool string_matches(const char *idstr, const char *match, size_t len)
{
        size_t matchlen;

        if (!match)
                return true;

        matchlen = strlen(match);
        WARN_ON_ONCE(matchlen > len);

        if (memcmp(idstr, match, matchlen))
                return false;

        for (; matchlen < len; matchlen++)
                if (idstr[matchlen] != ' ')
                        return false;

        return true;
}

static bool quirk_matches(const struct nvme_id_ctrl *id,
                          const struct nvme_core_quirk_entry *q)
{
        return q->vid == le16_to_cpu(id->vid) &&
                string_matches(id->mn, q->mn, sizeof(id->mn)) &&
                string_matches(id->fr, q->fr, sizeof(id->fr));
}

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) {
                strncpy(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");

        /* Generate a "fake" NQN per Figure 254 in NVMe 1.3 + ECN 001 */
        off = snprintf(subsys->subnqn, NVMF_NQN_SIZE,
                        "nqn.2014.08.org.nvmexpress:%4x%4x",
                        le16_to_cpu(id->vid), le16_to_cpu(id->ssvid));
        memcpy(subsys->subnqn + off, id->sn, sizeof(id->sn));
        off += sizeof(id->sn);
        memcpy(subsys->subnqn + off, id->mn, sizeof(id->mn));
        off += sizeof(id->mn);
        memset(subsys->subnqn + off, 0, sizeof(subsys->subnqn) - off);
}

static void __nvme_release_subsystem(struct nvme_subsystem *subsys)
{
        ida_simple_remove(&nvme_subsystems_ida, subsys->instance);
        kfree(subsys);
}

static void nvme_release_subsystem(struct device *dev)
{
        __nvme_release_subsystem(container_of(dev, struct nvme_subsystem, dev));
}

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);

        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;
}

#define SUBSYS_ATTR_RO(_name, _mode, _show)                     \
        struct device_attribute subsys_attr_##_name = \
                __ATTR(_name, _mode, _show, NULL)

static ssize_t nvme_subsys_show_nqn(struct device *dev,
                                    struct device_attribute *attr,
                                    char *buf)
{
        struct nvme_subsystem *subsys =
                container_of(dev, struct nvme_subsystem, dev);

        return snprintf(buf, PAGE_SIZE, "%s\n", subsys->subnqn);
}
static SUBSYS_ATTR_RO(subsysnqn, S_IRUGO, nvme_subsys_show_nqn);

#define nvme_subsys_show_str_function(field)                            \
static ssize_t subsys_##field##_show(struct device *dev,                \
                            struct device_attribute *attr, char *buf)   \
{                                                                       \
        struct nvme_subsystem *subsys =                                 \
                container_of(dev, struct nvme_subsystem, dev);          \
        return sprintf(buf, "%.*s\n",                                   \
                       (int)sizeof(subsys->field), subsys->field);      \
}                                                                       \
static SUBSYS_ATTR_RO(field, S_IRUGO, subsys_##field##_show);

nvme_subsys_show_str_function(model);
nvme_subsys_show_str_function(serial);
nvme_subsys_show_str_function(firmware_rev);

static struct attribute *nvme_subsys_attrs[] = {
        &subsys_attr_model.attr,
        &subsys_attr_serial.attr,
        &subsys_attr_firmware_rev.attr,
        &subsys_attr_subsysnqn.attr,
        NULL,
};

static struct attribute_group nvme_subsys_attrs_group = {
        .attrs = nvme_subsys_attrs,
};

static const struct attribute_group *nvme_subsys_attrs_groups[] = {
        &nvme_subsys_attrs_group,
        NULL,
};

static int nvme_active_ctrls(struct nvme_subsystem *subsys)
{
        int count = 0;
        struct nvme_ctrl *ctrl;

        mutex_lock(&subsys->lock);
        list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
                if (ctrl->state != NVME_CTRL_DELETING &&
                    ctrl->state != NVME_CTRL_DEAD)
                        count++;
        }
        mutex_unlock(&subsys->lock);

        return count;
}

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;
        ret = ida_simple_get(&nvme_subsystems_ida, 0, 0, GFP_KERNEL);
        if (ret < 0) {
                kfree(subsys);
                return ret;
        }
        subsys->instance = ret;
        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));
        memcpy(subsys->firmware_rev, id->fr, sizeof(subsys->firmware_rev));
        subsys->vendor_id = le16_to_cpu(id->vid);
        subsys->cmic = id->cmic;

        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", subsys->instance);
        device_initialize(&subsys->dev);

        mutex_lock(&nvme_subsystems_lock);
        found = __nvme_find_get_subsystem(subsys->subnqn);
        if (found) {
                /*
                 * Verify that the subsystem actually supports multiple
                 * controllers, else bail out.
                 */
                if (nvme_active_ctrls(found) && !(id->cmic & (1 << 1))) {
                        dev_err(ctrl->device,
                                "ignoring ctrl due to duplicate subnqn (%s).\n",
                                found->subnqn);
                        nvme_put_subsystem(found);
                        ret = -EINVAL;
                        goto out_unlock;
                }

                __nvme_release_subsystem(subsys);
                subsys = found;
        } else {
                ret = device_add(&subsys->dev);
                if (ret) {
                        dev_err(ctrl->device,
                                "failed to register subsystem device.\n");
                        goto out_unlock;
                }
                ida_init(&subsys->ns_ida);
                list_add_tail(&subsys->entry, &nvme_subsystems);
        }

        ctrl->subsys = subsys;
        mutex_unlock(&nvme_subsystems_lock);

        if (sysfs_create_link(&subsys->dev.kobj, &ctrl->device->kobj,
                        dev_name(ctrl->device))) {
                dev_err(ctrl->device,
                        "failed to create sysfs link from subsystem.\n");
                /* the transport driver will eventually put the subsystem */
                return -EINVAL;
        }

        mutex_lock(&subsys->lock);
        list_add_tail(&ctrl->subsys_entry, &subsys->ctrls);
        mutex_unlock(&subsys->lock);

        return 0;

out_unlock:
        mutex_unlock(&nvme_subsystems_lock);
        put_device(&subsys->dev);
        return ret;
}

static int nvme_get_log(struct nvme_ctrl *ctrl, u8 log_page, void *log,
                        size_t size)
{
        struct nvme_command c = { };

        c.common.opcode = nvme_admin_get_log_page;
        c.common.nsid = cpu_to_le32(NVME_NSID_ALL);
        c.common.cdw10[0] = nvme_get_log_dw10(log_page, size);

        return nvme_submit_sync_cmd(ctrl->admin_q, &c, log, size);
}

static int nvme_get_effects_log(struct nvme_ctrl *ctrl)
{
        int ret;

        if (!ctrl->effects)
                ctrl->effects = kzalloc(sizeof(*ctrl->effects), GFP_KERNEL);

        if (!ctrl->effects)
                return 0;

        ret = nvme_get_log(ctrl, NVME_LOG_CMD_EFFECTS, ctrl->effects,
                                        sizeof(*ctrl->effects));
        if (ret) {
                kfree(ctrl->effects);
                ctrl->effects = NULL;
        }
        return ret;
}

/*
 * 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)
{
        struct nvme_id_ctrl *id;
        u64 cap;
        int ret, page_shift;
        u32 max_hw_sectors;
        bool prev_apst_enabled;

        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;
        }

        ret = ctrl->ops->reg_read64(ctrl, NVME_REG_CAP, &cap);
        if (ret) {
                dev_err(ctrl->device, "Reading CAP failed (%d)\n", ret);
                return ret;
        }
        page_shift = NVME_CAP_MPSMIN(cap) + 12;

        if (ctrl->vs >= NVME_VS(1, 1, 0))
                ctrl->subsystem = NVME_CAP_NSSRC(cap);

        ret = nvme_identify_ctrl(ctrl, &id);
        if (ret) {
                dev_err(ctrl->device, "Identify Controller failed (%d)\n", ret);
                return -EIO;
        }

        if (id->lpa & NVME_CTRL_LPA_CMD_EFFECTS_LOG) {
                ret = nvme_get_effects_log(ctrl);
                if (ret < 0)
                        return ret;
        }

        if (!ctrl->identified) {
                int i;

                ret = nvme_init_subsystem(ctrl, id);
                if (ret)
                        goto out_free;

                /*
                 * Check for quirks.  Quirk can depend on firmware version,
                 * so, in principle, the set of quirks present can change
                 * across a reset.  As a possible future enhancement, we
                 * could re-scan for quirks every time we reinitialize
                 * the device, but we'd have to make sure that the driver
                 * behaves intelligently if the quirks change.
                 */
                for (i = 0; i < ARRAY_SIZE(core_quirks); i++) {
                        if (quirk_matches(id, &core_quirks[i]))
                                ctrl->quirks |= core_quirks[i].quirks;
                }
        }

        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->oacs = le16_to_cpu(id->oacs);
        ctrl->oncs = le16_to_cpup(&id->oncs);
        atomic_set(&ctrl->abort_limit, id->acl + 1);
        ctrl->vwc = id->vwc;
        ctrl->cntlid = le16_to_cpup(&id->cntlid);
        if (id->mdts)
                max_hw_sectors = 1 << (id->mdts + page_shift - 9);
        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);
        ctrl->sgls = le32_to_cpu(id->sgls);
        ctrl->kas = le16_to_cpu(id->kas);

        if (id->rtd3e) {
                /* us -> s */
                u32 transition_time = le32_to_cpu(id->rtd3e) / 1000000;

                ctrl->shutdown_timeout = clamp_t(unsigned int, transition_time,
                                                 shutdown_timeout, 60);

                if (ctrl->shutdown_timeout != shutdown_timeout)
                        dev_info(ctrl->device,
                                 "Shutdown timeout set to %u seconds\n",
                                 ctrl->shutdown_timeout);
        } else
                ctrl->shutdown_timeout = shutdown_timeout;

        ctrl->npss = id->npss;
        ctrl->apsta = id->apsta;
        prev_apst_enabled = ctrl->apst_enabled;
        if (ctrl->quirks & NVME_QUIRK_NO_APST) {
                if (force_apst && id->apsta) {
                        dev_warn(ctrl->device, "forcibly allowing APST due to nvme_core.force_apst -- use at your own risk\n");
                        ctrl->apst_enabled = true;
                } else {
                        ctrl->apst_enabled = false;
                }
        } else {
                ctrl->apst_enabled = id->apsta;
        }
        memcpy(ctrl->psd, id->psd, sizeof(ctrl->psd));

        if (ctrl->ops->flags & NVME_F_FABRICS) {
                ctrl->icdoff = le16_to_cpu(id->icdoff);
                ctrl->ioccsz = le32_to_cpu(id->ioccsz);
                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;
                        goto out_free;
                }

                if (!ctrl->opts->discovery_nqn && !ctrl->kas) {
                        dev_err(ctrl->device,
                                "keep-alive support is mandatory for fabrics\n");
                        ret = -EINVAL;
                        goto out_free;
                }
        } else {
                ctrl->cntlid = le16_to_cpu(id->cntlid);
                ctrl->hmpre = le32_to_cpu(id->hmpre);
                ctrl->hmmin = le32_to_cpu(id->hmmin);
                ctrl->hmminds = le32_to_cpu(id->hmminds);
                ctrl->hmmaxd = le16_to_cpu(id->hmmaxd);
        }

        kfree(id);

        if (ctrl->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);

        ret = nvme_configure_apst(ctrl);
        if (ret < 0)
                return ret;
        
        ret = nvme_configure_timestamp(ctrl);
        if (ret < 0)
                return ret;

        ret = nvme_configure_directives(ctrl);
        if (ret < 0)
                return ret;

        ctrl->identified = true;

        return 0;

out_free:
        kfree(id);
        return ret;
}
EXPORT_SYMBOL_GPL(nvme_init_identify);

static int nvme_dev_open(struct inode *inode, struct file *file)
{
        struct nvme_ctrl *ctrl =
                container_of(inode->i_cdev, struct nvme_ctrl, cdev);

        switch (ctrl->state) {
        case NVME_CTRL_LIVE:
        case NVME_CTRL_ADMIN_ONLY:
                break;
        default:
                return -EWOULDBLOCK;
        }

        file->private_data = ctrl;
        return 0;
}

static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp)
{
        struct nvme_ns *ns;
        int ret;

        mutex_lock(&ctrl->namespaces_mutex);
        if (list_empty(&ctrl->namespaces)) {
                ret = -ENOTTY;
                goto out_unlock;
        }

        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;
        }

        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);

        ret = nvme_user_cmd(ctrl, ns, argp);
        nvme_put_ns(ns);
        return ret;

out_unlock:
        mutex_unlock(&ctrl->namespaces_mutex);
        return ret;
}

static long nvme_dev_ioctl(struct file *file, unsigned int cmd,
                unsigned long arg)
{
        struct nvme_ctrl *ctrl = file->private_data;
        void __user *argp = (void __user *)arg;

        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;
        default:
                return -ENOTTY;
        }
}

static const struct file_operations nvme_dev_fops = {
        .owner          = THIS_MODULE,
        .open           = nvme_dev_open,
        .unlocked_ioctl = nvme_dev_ioctl,
        .compat_ioctl   = nvme_dev_ioctl,
};

static ssize_t nvme_sysfs_reset(struct device *dev,
                                struct device_attribute *attr, const char *buf,
                                size_t count)
{
        struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
        int ret;

        ret = nvme_reset_ctrl_sync(ctrl);
        if (ret < 0)
                return ret;
        return count;
}
static DEVICE_ATTR(reset_controller, S_IWUSR, NULL, nvme_sysfs_reset);

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);

        nvme_queue_scan(ctrl);
        return count;
}
static DEVICE_ATTR(rescan_controller, S_IWUSR, NULL, nvme_sysfs_rescan);

static inline struct nvme_ns_head *dev_to_ns_head(struct device *dev)
{
        struct gendisk *disk = dev_to_disk(dev);

        if (disk->fops == &nvme_fops)
                return nvme_get_ns_from_dev(dev)->head;
        else
                return disk->private_data;
}

static ssize_t wwid_show(struct device *dev, struct device_attribute *attr,
                char *buf)
{
        struct nvme_ns_head *head = dev_to_ns_head(dev);
        struct nvme_ns_ids *ids = &head->ids;
        struct nvme_subsystem *subsys = head->subsys;
        int serial_len = sizeof(subsys->serial);
        int model_len = sizeof(subsys->model);

        if (!uuid_is_null(&ids->uuid))
                return sprintf(buf, "uuid.%pU\n", &ids->uuid);

        if (memchr_inv(ids->nguid, 0, sizeof(ids->nguid)))
                return sprintf(buf, "eui.%16phN\n", ids->nguid);

        if (memchr_inv(ids->eui64, 0, sizeof(ids->eui64)))
                return sprintf(buf, "eui.%8phN\n", ids->eui64);

        while (serial_len > 0 && (subsys->serial[serial_len - 1] == ' ' ||
                                  subsys->serial[serial_len - 1] == '\0'))
                serial_len--;
        while (model_len > 0 && (subsys->model[model_len - 1] == ' ' ||
                                 subsys->model[model_len - 1] == '\0'))
                model_len--;

        return sprintf(buf, "nvme.%04x-%*phN-%*phN-%08x\n", subsys->vendor_id,
                serial_len, subsys->serial, model_len, subsys->model,
                head->ns_id);
}
static DEVICE_ATTR_RO(wwid);

static ssize_t nguid_show(struct device *dev, struct device_attribute *attr,
                char *buf)
{
        return sprintf(buf, "%pU\n", dev_to_ns_head(dev)->ids.nguid);
}
static DEVICE_ATTR_RO(nguid);

static ssize_t uuid_show(struct device *dev, struct device_attribute *attr,
                char *buf)
{
        struct nvme_ns_ids *ids = &dev_to_ns_head(dev)->ids;

        /* For backward compatibility expose the NGUID to userspace if
         * we have no UUID set
         */
        if (uuid_is_null(&ids->uuid)) {
                printk_ratelimited(KERN_WARNING
                                   "No UUID available providing old NGUID\n");
                return sprintf(buf, "%pU\n", ids->nguid);
        }
        return sprintf(buf, "%pU\n", &ids->uuid);
}
static DEVICE_ATTR_RO(uuid);

static ssize_t eui_show(struct device *dev, struct device_attribute *attr,
                char *buf)
{
        return sprintf(buf, "%8ph\n", dev_to_ns_head(dev)->ids.eui64);
}
static DEVICE_ATTR_RO(eui);

static ssize_t nsid_show(struct device *dev, struct device_attribute *attr,
                char *buf)
{
        return sprintf(buf, "%d\n", dev_to_ns_head(dev)->ns_id);
}
static DEVICE_ATTR_RO(nsid);

static struct attribute *nvme_ns_id_attrs[] = {
        &dev_attr_wwid.attr,
        &dev_attr_uuid.attr,
        &dev_attr_nguid.attr,
        &dev_attr_eui.attr,
        &dev_attr_nsid.attr,
        NULL,
};

static umode_t nvme_ns_id_attrs_are_visible(struct kobject *kobj,
                struct attribute *a, int n)
{
        struct device *dev = container_of(kobj, struct device, kobj);
        struct nvme_ns_ids *ids = &dev_to_ns_head(dev)->ids;

        if (a == &dev_attr_uuid.attr) {
                if (uuid_is_null(&ids->uuid) &&
                    !memchr_inv(ids->nguid, 0, sizeof(ids->nguid)))
                        return 0;
        }
        if (a == &dev_attr_nguid.attr) {
                if (!memchr_inv(ids->nguid, 0, sizeof(ids->nguid)))
                        return 0;
        }
        if (a == &dev_attr_eui.attr) {
                if (!memchr_inv(ids->eui64, 0, sizeof(ids->eui64)))
                        return 0;
        }
        return a->mode;
}

const struct attribute_group nvme_ns_id_attr_group = {
        .attrs          = nvme_ns_id_attrs,
        .is_visible     = nvme_ns_id_attrs_are_visible,
};

#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->subsys->field), ctrl->subsys->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);

#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_int_function(cntlid);

static ssize_t nvme_sysfs_delete(struct device *dev,
                                struct device_attribute *attr, const char *buf,
                                size_t count)
{
        struct nvme_ctrl *ctrl = dev_get_drvdata(dev);

        if (device_remove_file_self(dev, attr))
                nvme_delete_ctrl_sync(ctrl);
        return count;
}
static DEVICE_ATTR(delete_controller, S_IWUSR, NULL, nvme_sysfs_delete);

static ssize_t nvme_sysfs_show_transport(struct device *dev,
                                         struct device_attribute *attr,
                                         char *buf)
{
        struct nvme_ctrl *ctrl = dev_get_drvdata(dev);

        return snprintf(buf, PAGE_SIZE, "%s\n", ctrl->ops->name);
}
static DEVICE_ATTR(transport, S_IRUGO, nvme_sysfs_show_transport, NULL);

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_ADMIN_ONLY]  = "only-admin",
                [NVME_CTRL_RESETTING]   = "resetting",
                [NVME_CTRL_CONNECTING]  = "connecting",
                [NVME_CTRL_DELETING]    = "deleting",
                [NVME_CTRL_DEAD]        = "dead",
        };

        if ((unsigned)ctrl->state < ARRAY_SIZE(state_name) &&
            state_name[ctrl->state])
                return sprintf(buf, "%s\n", state_name[ctrl->state]);

        return sprintf(buf, "unknown state\n");
}

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)
{
        struct nvme_ctrl *ctrl = dev_get_drvdata(dev);

        return snprintf(buf, PAGE_SIZE, "%s\n", ctrl->subsys->subnqn);
}
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)
{
        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
};

static umode_t nvme_dev_attrs_are_visible(struct kobject *kobj,
                struct attribute *a, int n)
{
        struct device *dev = container_of(kobj, struct device, kobj);
        struct nvme_ctrl *ctrl = dev_get_drvdata(dev);

        if (a == &dev_attr_delete_controller.attr && !ctrl->ops->delete_ctrl)
                return 0;
        if (a == &dev_attr_address.attr && !ctrl->ops->get_address)
                return 0;

        return a->mode;
}

static struct attribute_group nvme_dev_attrs_group = {
        .attrs          = nvme_dev_attrs,
        .is_visible     = nvme_dev_attrs_are_visible,
};

static const struct attribute_group *nvme_dev_attr_groups[] = {
        &nvme_dev_attrs_group,
        NULL,
};

static struct nvme_ns_head *__nvme_find_ns_head(struct nvme_subsystem *subsys,
                unsigned nsid)
{
        struct nvme_ns_head *h;

        lockdep_assert_held(&subsys->lock);

        list_for_each_entry(h, &subsys->nsheads, entry) {
                if (h->ns_id == nsid && kref_get_unless_zero(&h->ref))
                        return h;
        }

        return NULL;
}

static int __nvme_check_ids(struct nvme_subsystem *subsys,
                struct nvme_ns_head *new)
{
        struct nvme_ns_head *h;

        lockdep_assert_held(&subsys->lock);

        list_for_each_entry(h, &subsys->nsheads, entry) {
                if (nvme_ns_ids_valid(&new->ids) &&
                    nvme_ns_ids_equal(&new->ids, &h->ids))
                        return -EINVAL;
        }

        return 0;
}

static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
                unsigned nsid, struct nvme_id_ns *id)
{
        struct nvme_ns_head *head;
        int ret = -ENOMEM;

        head = kzalloc(sizeof(*head), GFP_KERNEL);
        if (!head)
                goto out;
        ret = ida_simple_get(&ctrl->subsys->ns_ida, 1, 0, GFP_KERNEL);
        if (ret < 0)
                goto out_free_head;
        head->instance = ret;
        INIT_LIST_HEAD(&head->list);
        init_srcu_struct(&head->srcu);
        head->subsys = ctrl->subsys;
        head->ns_id = nsid;
        kref_init(&head->ref);

        nvme_report_ns_ids(ctrl, nsid, id, &head->ids);

        ret = __nvme_check_ids(ctrl->subsys, head);
        if (ret) {
                dev_err(ctrl->device,
                        "duplicate IDs for nsid %d\n", nsid);
                goto out_cleanup_srcu;
        }

        ret = nvme_mpath_alloc_disk(ctrl, head);
        if (ret)
                goto out_cleanup_srcu;

        list_add_tail(&head->entry, &ctrl->subsys->nsheads);
        return head;
out_cleanup_srcu:
        cleanup_srcu_struct(&head->srcu);
        ida_simple_remove(&ctrl->subsys->ns_ida, head->instance);
out_free_head:
        kfree(head);
out:
        return ERR_PTR(ret);
}

static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid,
                struct nvme_id_ns *id)
{
        struct nvme_ctrl *ctrl = ns->ctrl;
        bool is_shared = id->nmic & (1 << 0);
        struct nvme_ns_head *head = NULL;
        int ret = 0;

        mutex_lock(&ctrl->subsys->lock);
        if (is_shared)
                head = __nvme_find_ns_head(ctrl->subsys, nsid);
        if (!head) {
                head = nvme_alloc_ns_head(ctrl, nsid, id);
                if (IS_ERR(head)) {
                        ret = PTR_ERR(head);
                        goto out_unlock;
                }
        } else {
                struct nvme_ns_ids ids;

                nvme_report_ns_ids(ctrl, nsid, id, &ids);
                if (!nvme_ns_ids_equal(&head->ids, &ids)) {
                        dev_err(ctrl->device,
                                "IDs don't match for shared namespace %d\n",
                                        nsid);
                        ret = -EINVAL;
                        goto out_unlock;
                }
        }

        list_add_tail(&ns->siblings, &head->list);
        ns->head = head;

out_unlock:
        mutex_unlock(&ctrl->subsys->lock);
        return ret;
}

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);

        return nsa->head->ns_id - nsb->head->ns_id;
}

static struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid)
{
        struct nvme_ns *ns, *ret = NULL;

        mutex_lock(&ctrl->namespaces_mutex);
        list_for_each_entry(ns, &ctrl->namespaces, list) {
                if (ns->head->ns_id == nsid) {
                        if (!kref_get_unless_zero(&ns->kref))
                                continue;
                        ret = ns;
                        break;
                }
                if (ns->head->ns_id > nsid)
                        break;
        }
        mutex_unlock(&ctrl->namespaces_mutex);
        return ret;
}

static int nvme_setup_streams_ns(struct nvme_ctrl *ctrl, struct nvme_ns *ns)
{
        struct streams_directive_params s;
        int ret;

        if (!ctrl->nr_streams)
                return 0;

        ret = nvme_get_stream_params(ctrl, &s, ns->head->ns_id);
        if (ret)
                return ret;

        ns->sws = le32_to_cpu(s.sws);
        ns->sgs = le16_to_cpu(s.sgs);

        if (ns->sws) {
                unsigned int bs = 1 << ns->lba_shift;

                blk_queue_io_min(ns->queue, bs * ns->sws);
                if (ns->sgs)
                        blk_queue_io_opt(ns->queue, bs * ns->sws * ns->sgs);
        }

        return 0;
}

static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
{
        struct nvme_ns *ns;
        struct gendisk *disk;
        struct nvme_id_ns *id;
        char disk_name[DISK_NAME_LEN];
        int node = dev_to_node(ctrl->dev), flags = GENHD_FL_EXT_DEVT;

        ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node);
        if (!ns)
                return;

        ns->queue = blk_mq_init_queue(ctrl->tagset);
        if (IS_ERR(ns->queue))
                goto out_free_ns;
        queue_flag_set_unlocked(QUEUE_FLAG_NONROT, ns->queue);
        ns->queue->queuedata = ns;
        ns->ctrl = ctrl;

        kref_init(&ns->kref);
        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);

        id = nvme_identify_ns(ctrl, nsid);
        if (!id)
                goto out_free_queue;

        if (id->ncap == 0)
                goto out_free_id;

        if (nvme_init_ns_head(ns, nsid, id))
                goto out_free_id;
        nvme_setup_streams_ns(ctrl, ns);
        
#ifdef CONFIG_NVME_MULTIPATH
        /*
         * If multipathing is enabled we need to always use the subsystem
         * instance number for numbering our devices to avoid conflicts
         * between subsystems that have multiple controllers and thus use
         * the multipath-aware subsystem node and those that have a single
         * controller and use the controller node directly.
         */
        if (ns->head->disk) {
                sprintf(disk_name, "nvme%dc%dn%d", ctrl->subsys->instance,
                                ctrl->cntlid, ns->head->instance);
                flags = GENHD_FL_HIDDEN;
        } else {
                sprintf(disk_name, "nvme%dn%d", ctrl->subsys->instance,
                                ns->head->instance);
        }
#else
        /*
         * But without the multipath code enabled, multiple controller per
         * subsystems are visible as devices and thus we cannot use the
         * subsystem instance.
         */
        sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->head->instance);
#endif

        if ((ctrl->quirks & NVME_QUIRK_LIGHTNVM) && id->vs[0] == 0x1) {
                if (nvme_nvm_register(ns, disk_name, node)) {
                        dev_warn(ctrl->device, "LightNVM init failure\n");