// SPDX-License-Identifier: GPL-2.0
/*
* NVM Express device driver
* Copyright (c) 2011-2014, Intel Corporation.
*/
#include <linux/blkdev.h>
#include <linux/blk-mq.h>
#include <linux/blk-integrity.h>
#include <linux/compat.h>
#include <linux/delay.h>
#include <linux/errno.h>
#include <linux/hdreg.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/backing-dev.h>
#include <linux/slab.h>
#include <linux/types.h>
#include <linux/pr.h>
#include <linux/ptrace.h>
#include <linux/nvme_ioctl.h>
#include <linux/pm_qos.h>
#include <asm/unaligned.h>
#include "nvme.h"
#include "fabrics.h"
#include <linux/nvme-auth.h>
#define CREATE_TRACE_POINTS
#include "trace.h"
#define NVME_MINORS (1U << MINORBITS)
struct nvme_ns_info {
struct nvme_ns_ids ids;
u32 nsid;
__le32 anagrpid;
bool is_shared;
bool is_readonly;
bool is_ready;
};
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 unsigned long apst_primary_timeout_ms = 100;
module_param(apst_primary_timeout_ms, ulong, 0644);
MODULE_PARM_DESC(apst_primary_timeout_ms,
"primary APST timeout in ms");
static unsigned long apst_secondary_timeout_ms = 2000;
module_param(apst_secondary_timeout_ms, ulong, 0644);
MODULE_PARM_DESC(apst_secondary_timeout_ms,
"secondary APST timeout in ms");
static unsigned long apst_primary_latency_tol_us = 15000;
module_param(apst_primary_latency_tol_us, ulong, 0644);
MODULE_PARM_DESC(apst_primary_latency_tol_us,
"primary APST latency tolerance in us");
static unsigned long apst_secondary_latency_tol_us = 100000;
module_param(apst_secondary_latency_tol_us, ulong, 0644);
MODULE_PARM_DESC(apst_secondary_latency_tol_us,
"secondary APST latency tolerance in us");
/*
* nvme_wq - hosts nvme related works that are not reset or delete
* nvme_reset_wq - hosts nvme reset works
* nvme_delete_wq - hosts nvme delete works
*
* nvme_wq will host works such as scan, aen handling, fw activation,
* keep-alive, periodic reconnects etc. nvme_reset_wq
* runs reset works which also flush works hosted on nvme_wq for
* serialization purposes. nvme_delete_wq host controller deletion
* works which flush reset works for serialization.
*/
struct workqueue_struct *nvme_wq;
EXPORT_SYMBOL_GPL(nvme_wq);
struct workqueue_struct *nvme_reset_wq;
EXPORT_SYMBOL_GPL(nvme_reset_wq);
struct workqueue_struct *nvme_delete_wq;
EXPORT_SYMBOL_GPL(nvme_delete_wq);
static LIST_HEAD(nvme_subsystems);
static DEFINE_MUTEX(nvme_subsystems_lock);
static DEFINE_IDA(nvme_instance_ida);
static dev_t nvme_ctrl_base_chr_devt;
static struct class *nvme_class;
static struct class *nvme_subsys_class;
static DEFINE_IDA(nvme_ns_chr_minor_ida);
static dev_t nvme_ns_chr_devt;
static struct class *nvme_ns_chr_class;
static void nvme_put_subsystem(struct nvme_subsystem *subsys);
static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
unsigned nsid);
static void nvme_update_keep_alive(struct nvme_ctrl *ctrl,
struct nvme_command *cmd);
void nvme_queue_scan(struct nvme_ctrl *ctrl)
{
/*
* Only new queue scan work when admin and IO queues are both alive
*/
if (ctrl->state == NVME_CTRL_LIVE && ctrl->tagset)
queue_work(nvme_wq, &ctrl->scan_work);
}
/*
* Use this function to proceed with scheduling reset_work for a controller
* that had previously been set to the resetting state. This is intended for
* code paths that can't be interrupted by other reset attempts. A hot removal
* may prevent this from succeeding.
*/
int nvme_try_sched_reset(struct nvme_ctrl *ctrl)
{
if (ctrl->state != NVME_CTRL_RESETTING)
return -EBUSY;
if (!queue_work(nvme_reset_wq, &ctrl->reset_work))
return -EBUSY;
return 0;
}
EXPORT_SYMBOL_GPL(nvme_try_sched_reset);
static void nvme_failfast_work(struct work_struct *work)
{
struct nvme_ctrl *ctrl = container_of(to_delayed_work(work),
struct nvme_ctrl, failfast_work);
if (ctrl->state != NVME_CTRL_CONNECTING)
return;
set_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags);
dev_info(ctrl->device, "failfast expired\n");
nvme_kick_requeue_lists(ctrl);
}
static inline void nvme_start_failfast_work(struct nvme_ctrl *ctrl)
{
if (!ctrl->opts || ctrl->opts->fast_io_fail_tmo == -1)
return;
schedule_delayed_work(&ctrl->failfast_work,
ctrl->opts->fast_io_fail_tmo * HZ);
}
static inline void nvme_stop_failfast_work(struct nvme_ctrl *ctrl)
{
if (!ctrl->opts)
return;
cancel_delayed_work_sync(&ctrl->failfast_work);
clear_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags);
}
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;
}
static void nvme_do_delete_ctrl(struct nvme_ctrl *ctrl)
{
dev_info(ctrl->device,
"Removing ctrl: NQN \"%s\"\n", nvmf_ctrl_subsysnqn(ctrl));
flush_work(&ctrl->reset_work);
nvme_stop_ctrl(ctrl);
nvme_remove_namespaces(ctrl);
ctrl->ops->delete_ctrl(ctrl);
nvme_uninit_ctrl(ctrl);
}
static void nvme_delete_ctrl_work(struct work_struct *work)
{
struct nvme_ctrl *ctrl =
container_of(work, struct nvme_ctrl, delete_work);
nvme_do_delete_ctrl(ctrl);
}
int nvme_delete_ctrl(struct nvme_ctrl *ctrl)
{
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);
static void nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl)
{
/*
* Keep a reference until nvme_do_delete_ctrl() complete,
* since ->delete_ctrl can free the controller.
*/
nvme_get_ctrl(ctrl);
if (nvme_change_ctrl_state(ctrl, NVME_CTRL_DELETING))
nvme_do_delete_ctrl(ctrl);
nvme_put_ctrl(ctrl);
}
static blk_status_t nvme_error_status(u16 status)
{
switch (status & 0x7ff) {
case NVME_SC_SUCCESS:
return BLK_STS_OK;
case NVME_SC_CAP_EXCEEDED:
return BLK_STS_NOSPC;
case NVME_SC_LBA_RANGE:
case NVME_SC_CMD_INTERRUPTED:
case NVME_SC_NS_NOT_READY:
return BLK_STS_TARGET;
case NVME_SC_BAD_ATTRIBUTES:
case NVME_SC_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;
case NVME_SC_HOST_PATH_ERROR:
return BLK_STS_TRANSPORT;
case NVME_SC_ZONE_TOO_MANY_ACTIVE:
return BLK_STS_ZONE_ACTIVE_RESOURCE;
case NVME_SC_ZONE_TOO_MANY_OPEN:
return BLK_STS_ZONE_OPEN_RESOURCE;
default:
return BLK_STS_IOERR;
}
}
static void nvme_retry_req(struct request *req)
{
unsigned long delay = 0;
u16 crd;
/* The mask and shift result must be <= 3 */
crd = (nvme_req(req)->status & NVME_SC_CRD) >> 11;
if (crd)
delay = nvme_req(req)->ctrl->crdt[crd - 1] * 100;
nvme_req(req)->retries++;
blk_mq_requeue_request(req, false);
blk_mq_delay_kick_requeue_list(req->q, delay);
}
static void nvme_log_error(struct request *req)
{
struct nvme_ns *ns = req->q->queuedata;
struct nvme_request *nr = nvme_req(req);
if (ns) {
pr_err_ratelimited("%s: %s(0x%x) @ LBA %llu, %llu blocks, %s (sct 0x%x / sc 0x%x) %s%s\n",
ns->disk ? ns->disk->disk_name : "?",
nvme_get_opcode_str(nr->cmd->common.opcode),
nr->cmd->common.opcode,
(unsigned long long)nvme_sect_to_lba(ns, blk_rq_pos(req)),
(unsigned long long)blk_rq_bytes(req) >> ns->lba_shift,
nvme_get_error_status_str(nr->status),
nr->status >> 8 & 7, /* Status Code Type */
nr->status & 0xff, /* Status Code */
nr->status & NVME_SC_MORE ? "MORE " : "",
nr->status & NVME_SC_DNR ? "DNR " : "");
return;
}
pr_err_ratelimited("%s: %s(0x%x), %s (sct 0x%x / sc 0x%x) %s%s\n",
dev_name(nr->ctrl->device),
nvme_get_admin_opcode_str(nr->cmd->common.opcode),
nr->cmd->common.opcode,
nvme_get_error_status_str(nr->status),
nr->status >> 8 & 7, /* Status Code Type */
nr->status & 0xff, /* Status Code */
nr->status & NVME_SC_MORE ? "MORE " : "",
nr->status & NVME_SC_DNR ? "DNR " : "");
}
enum nvme_disposition {
COMPLETE,
RETRY,
FAILOVER,
AUTHENTICATE,
};
static inline enum nvme_disposition nvme_decide_disposition(struct request *req)
{
if (likely(nvme_req(req)->status == 0))
return COMPLETE;
if ((nvme_req(req)->status & 0x7ff) == NVME_SC_AUTH_REQUIRED)
return AUTHENTICATE;
if (blk_noretry_request(req) ||
(nvme_req(req)->status & NVME_SC_DNR) ||
nvme_req(req)->retries >= nvme_max_retries)
return COMPLETE;
if (req->cmd_flags & REQ_NVME_MPATH) {
if (nvme_is_path_error(nvme_req(req)->status) ||
blk_queue_dying(req->q))
return FAILOVER;
} else {
if (blk_queue_dying(req->q))
return COMPLETE;
}
return RETRY;
}
static inline void nvme_end_req_zoned(struct request *req)
{
if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
req_op(req) == REQ_OP_ZONE_APPEND)
req->__sector = nvme_lba_to_sect(req->q->queuedata,
le64_to_cpu(nvme_req(req)->result.u64));
}
static inline void nvme_end_req(struct request *req)
{
blk_status_t status = nvme_error_status(nvme_req(req)->status);
if (unlikely(nvme_req(req)->status && !(req->rq_flags & RQF_QUIET)))
nvme_log_error(req);
nvme_end_req_zoned(req);
nvme_trace_bio_complete(req);
blk_mq_end_request(req, status);
}
void nvme_complete_rq(struct request *req)
{
struct nvme_ctrl *ctrl = nvme_req(req)->ctrl;
trace_nvme_complete_rq(req);
nvme_cleanup_cmd(req);
if (ctrl->kas)
ctrl->comp_seen = true;
switch (nvme_decide_disposition(req)) {
case COMPLETE:
nvme_end_req(req);
return;
case RETRY:
nvme_retry_req(req);
return;
case FAILOVER:
nvme_failover_req(req);
return;
case AUTHENTICATE:
#ifdef CONFIG_NVME_AUTH
queue_work(nvme_wq, &ctrl->dhchap_auth_work);
nvme_retry_req(req);
#else
nvme_end_req(req);
#endif
return;
}
}
EXPORT_SYMBOL_GPL(nvme_complete_rq);
void nvme_complete_batch_req(struct request *req)
{
trace_nvme_complete_rq(req);
nvme_cleanup_cmd(req);
nvme_end_req_zoned(req);
}
EXPORT_SYMBOL_GPL(nvme_complete_batch_req);
/*
* Called to unwind from ->queue_rq on a failed command submission so that the
* multipathing code gets called to potentially failover to another path.
* The caller needs to unwind all transport specific resource allocations and
* must return propagate the return value.
*/
blk_status_t nvme_host_path_error(struct request *req)
{
nvme_req(req)->status = NVME_SC_HOST_PATH_ERROR;
blk_mq_set_request_complete(req);
nvme_complete_rq(req);
return BLK_STS_OK;
}
EXPORT_SYMBOL_GPL(nvme_host_path_error);
bool nvme_cancel_request(struct request *req, void *data)
{
dev_dbg_ratelimited(((struct nvme_ctrl *) data)->device,
"Cancelling I/O %d", req->tag);
/* don't abort one completed request */
if (blk_mq_request_completed(req))
return true;
nvme_req(req)->status = NVME_SC_HOST_ABORTED_CMD;
nvme_req(req)->flags |= NVME_REQ_CANCELLED;
blk_mq_complete_request(req);
return true;
}
EXPORT_SYMBOL_GPL(nvme_cancel_request);
void nvme_cancel_tagset(struct nvme_ctrl *ctrl)
{
if (ctrl->tagset) {
blk_mq_tagset_busy_iter(ctrl->tagset,
nvme_cancel_request, ctrl);
blk_mq_tagset_wait_completed_request(ctrl->tagset);
}
}
EXPORT_SYMBOL_GPL(nvme_cancel_tagset);
void nvme_cancel_admin_tagset(struct nvme_ctrl *ctrl)
{
if (ctrl->admin_tagset) {
blk_mq_tagset_busy_iter(ctrl->admin_tagset,
nvme_cancel_request, ctrl);
blk_mq_tagset_wait_completed_request(ctrl->admin_tagset);
}
}
EXPORT_SYMBOL_GPL(nvme_cancel_admin_tagset);
bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
enum nvme_ctrl_state new_state)
{
enum nvme_ctrl_state old_state;
unsigned long flags;
bool changed = false;
spin_lock_irqsave(&ctrl->lock, flags);
old_state = ctrl->state;
switch (new_state) {
case NVME_CTRL_LIVE:
switch (old_state) {
case NVME_CTRL_NEW:
case NVME_CTRL_RESETTING:
case NVME_CTRL_CONNECTING:
changed = true;
fallthrough;
default:
break;
}
break;
case NVME_CTRL_RESETTING:
switch (old_state) {
case NVME_CTRL_NEW:
case NVME_CTRL_LIVE:
changed = true;
fallthrough;
default:
break;
}
break;
case NVME_CTRL_CONNECTING:
switch (old_state) {
case NVME_CTRL_NEW:
case NVME_CTRL_RESETTING:
changed = true;
fallthrough;
default:
break;
}
break;
case NVME_CTRL_DELETING:
switch (old_state) {
case NVME_CTRL_LIVE:
case NVME_CTRL_RESETTING:
case NVME_CTRL_CONNECTING:
changed = true;
fallthrough;
default:
break;
}
break;
case NVME_CTRL_DELETING_NOIO:
switch (old_state) {
case NVME_CTRL_DELETING:
case NVME_CTRL_DEAD:
changed = true;
fallthrough;
default:
break;
}
break;
case NVME_CTRL_DEAD:
switch (old_state) {
case NVME_CTRL_DELETING:
changed = true;
fallthrough;
default:
break;
}
break;
default:
break;
}
if (changed) {
ctrl->state = new_state;
wake_up_all(&ctrl->state_wq);
}
spin_unlock_irqrestore(&ctrl->lock, flags);
if (!changed)
return false;
if (ctrl->state == NVME_CTRL_LIVE) {
if (old_state == NVME_CTRL_CONNECTING)
nvme_stop_failfast_work(ctrl);
nvme_kick_requeue_lists(ctrl);
} else if (ctrl->state == NVME_CTRL_CONNECTING &&
old_state == NVME_CTRL_RESETTING) {
nvme_start_failfast_work(ctrl);
}
return changed;
}
EXPORT_SYMBOL_GPL(nvme_change_ctrl_state);
/*
* Returns true for sink states that can't ever transition back to live.
*/
static bool nvme_state_terminal(struct nvme_ctrl *ctrl)
{
switch (ctrl->state) {
case NVME_CTRL_NEW:
case NVME_CTRL_LIVE:
case NVME_CTRL_RESETTING:
case NVME_CTRL_CONNECTING:
return false;
case NVME_CTRL_DELETING:
case NVME_CTRL_DELETING_NOIO:
case NVME_CTRL_DEAD:
return true;
default:
WARN_ONCE(1, "Unhandled ctrl state:%d", ctrl->state);
return true;
}
}
/*
* Waits for the controller state to be resetting, or returns false if it is
* not possible to ever transition to that state.
*/
bool nvme_wait_reset(struct nvme_ctrl *ctrl)
{
wait_event(ctrl->state_wq,
nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING) ||
nvme_state_terminal(ctrl));
return ctrl->state == NVME_CTRL_RESETTING;
}
EXPORT_SYMBOL_GPL(nvme_wait_reset);
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_free(&head->subsys->ns_ida, head->instance);
cleanup_srcu_struct(&head->srcu);
nvme_put_subsystem(head->subsys);
kfree(head);
}
bool nvme_tryget_ns_head(struct nvme_ns_head *head)
{
return kref_get_unless_zero(&head->ref);
}
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);
put_disk(ns->disk);
nvme_put_ns_head(ns->head);
nvme_put_ctrl(ns->ctrl);
kfree(ns);
}
static inline bool nvme_get_ns(struct nvme_ns *ns)
{
return kref_get_unless_zero(&ns->kref);
}
void nvme_put_ns(struct nvme_ns *ns)
{
kref_put(&ns->kref, nvme_free_ns);
}
EXPORT_SYMBOL_NS_GPL(nvme_put_ns, NVME_TARGET_PASSTHRU);
static inline void nvme_clear_nvme_request(struct request *req)
{
nvme_req(req)->status = 0;
nvme_req(req)->retries = 0;
nvme_req(req)->flags = 0;
req->rq_flags |= RQF_DONTPREP;
}
/* initialize a passthrough request */
void nvme_init_request(struct request *req, struct nvme_command *cmd)
{
if (req->q->queuedata)
req->timeout = NVME_IO_TIMEOUT;
else /* no queuedata implies admin queue */
req->timeout = NVME_ADMIN_TIMEOUT;
/* passthru commands should let the driver set the SGL flags */
cmd->common.flags &= ~NVME_CMD_SGL_ALL;
req->cmd_flags |= REQ_FAILFAST_DRIVER;
if (req->mq_hctx->type == HCTX_TYPE_POLL)
req->cmd_flags |= REQ_POLLED;
nvme_clear_nvme_request(req);
memcpy(nvme_req(req)->cmd, cmd, sizeof(*cmd));
}
EXPORT_SYMBOL_GPL(nvme_init_request);
/*
* For something we're not in a state to send to the device the default action
* is to busy it and retry it after the controller state is recovered. However,
* if the controller is deleting or if anything is marked for failfast or
* nvme multipath it is immediately failed.
*
* Note: commands used to initialize the controller will be marked for failfast.
* Note: nvme cli/ioctl commands are marked for failfast.
*/
blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl,
struct request *rq)
{
if (ctrl->state != NVME_CTRL_DELETING_NOIO &&
ctrl->state != NVME_CTRL_DELETING &&
ctrl->state != NVME_CTRL_DEAD &&
!test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags) &&
!blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
return BLK_STS_RESOURCE;
return nvme_host_path_error(rq);
}
EXPORT_SYMBOL_GPL(nvme_fail_nonready_command);
bool __nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
bool queue_live)
{
struct nvme_request *req = nvme_req(rq);
/*
* currently we have a problem sending passthru commands
* on the admin_q if the controller is not LIVE because we can't
* make sure that they are going out after the admin connect,
* controller enable and/or other commands in the initialization
* sequence. until the controller will be LIVE, fail with
* BLK_STS_RESOURCE so that they will be rescheduled.
*/
if (rq->q == ctrl->admin_q && (req->flags & NVME_REQ_USERCMD))
return false;
if (ctrl->ops->flags & NVME_F_FABRICS) {
/*
* Only allow commands on a live queue, except for the connect
* command, which is require to set the queue live in the
* appropinquate states.
*/
switch (ctrl->state) {
case NVME_CTRL_CONNECTING:
if (blk_rq_is_passthrough(rq) && nvme_is_fabrics(req->cmd) &&
(req->cmd->fabrics.fctype == nvme_fabrics_type_connect ||
req->cmd->fabrics.fctype == nvme_fabrics_type_auth_send ||
req->cmd->fabrics.fctype == nvme_fabrics_type_auth_receive))
return true;
break;
default:
break;
case NVME_CTRL_DEAD:
return false;
}
}
return queue_live;
}
EXPORT_SYMBOL_GPL(__nvme_check_ready);
static inline void nvme_setup_flush(struct nvme_ns *ns,
struct nvme_command *cmnd)
{
memset(cmnd, 0, sizeof(*cmnd));
cmnd->common.opcode = nvme_cmd_flush;
cmnd->common.nsid = cpu_to_le32(ns->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;
/*
* Some devices do not consider the DSM 'Number of Ranges' field when
* determining how much data to DMA. Always allocate memory for maximum
* number of segments to prevent device reading beyond end of buffer.
*/
static const size_t alloc_size = sizeof(*range) * NVME_DSM_MAX_RANGES;
range = kzalloc(alloc_size, GFP_ATOMIC | __GFP_NOWARN);
if (!range) {
/*
* If we fail allocation our range, fallback to the controller
* discard page. If that's also busy, it's safe to return
* busy, as we know we can make progress once that's freed.
*/
if (test_and_set_bit_lock(0, &ns->ctrl->discard_page_busy))
return BLK_STS_RESOURCE;
range = page_address(ns->ctrl->discard_page);
}
__rq_for_each_bio(bio, req) {
u64 slba = nvme_sect_to_lba(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)) {
if (virt_to_page(range) == ns->ctrl->discard_page)
clear_bit_unlock(0, &ns->ctrl->discard_page_busy);
else
kfree(range);
return BLK_STS_IOERR;
}
memset(cmnd, 0, sizeof(*cmnd));
cmnd->dsm.opcode = nvme_cmd_dsm;
cmnd->dsm.nsid = cpu_to_le32(ns->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 = alloc_size;
req->rq_flags |= RQF_SPECIAL_PAYLOAD;
return BLK_STS_OK;
}
static void nvme_set_ref_tag(struct nvme_ns *ns, struct nvme_command *cmnd,
struct request *req)
{
u32 upper, lower;
u64 ref48;
/* both rw and write zeroes share the same reftag format */
switch (ns->guard_type) {
case NVME_NVM_NS_16B_GUARD:
cmnd->rw.reftag = cpu_to_le32(t10_pi_ref_tag(req));
break;
case NVME_NVM_NS_64B_GUARD:
ref48 = ext_pi_ref_tag(req);
lower = lower_32_bits(ref48);
upper = upper_32_bits(ref48);
cmnd->rw.reftag = cpu_to_le32(lower);
cmnd->rw.cdw3 = cpu_to_le32(upper);
break;
default:
break;
}
}
static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns,
struct request *req, struct nvme_command *cmnd)
{
memset(cmnd, 0, sizeof(*cmnd));
if (ns->ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES)
return nvme_setup_discard(ns, req, cmnd);
cmnd->write_zeroes.opcode = nvme_cmd_write_zeroes;
cmnd->write_zeroes.nsid = cpu_to_le32(ns->head->ns_id);
cmnd->write_zeroes.slba =
cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req)));
cmnd->write_zeroes.length =
cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
if (nvme_ns_has_pi(ns)) {
cmnd->write_zeroes.control = cpu_to_le16(NVME_RW_PRINFO_PRACT);
switch (ns->pi_type) {
case NVME_NS_DPS_PI_TYPE1:
case NVME_NS_DPS_PI_TYPE2:
nvme_set_ref_tag(ns, cmnd, req);
break;
}
}
return BLK_STS_OK;
}
static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
struct request *req, struct nvme_command *cmnd,
enum nvme_opcode op)
{
u16 control = 0;
u32 dsmgmt = 0;
if (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;
cmnd->rw.opcode = op;
cmnd->rw.flags = 0;
cmnd->rw.nsid = cpu_to_le32(ns->head->ns_id);
cmnd->rw.cdw2 = 0;
cmnd->rw.cdw3 = 0;
cmnd->rw.metadata = 0;
cmnd->rw.slba = cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req)));
cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
cmnd->rw.reftag = 0;
cmnd->rw.apptag = 0;
cmnd->rw.appmask = 0;
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;
if (op == nvme_cmd_zone_append)
control |= NVME_RW_APPEND_PIREMAP;
nvme_set_ref_tag(ns, cmnd, req);
break;
}
}
cmnd->rw.control = cpu_to_le16(control);
cmnd->rw.dsmgmt = cpu_to_le32(dsmgmt);
return 0;
}
void nvme_cleanup_cmd(struct request *req)
{
if (req->rq_flags & RQF_SPECIAL_PAYLOAD) {
struct nvme_ctrl *ctrl = nvme_req(req)->ctrl;
if (req->special_vec.bv_page == ctrl->discard_page)
clear_bit_unlock(0, &ctrl->discard_page_busy);
else
kfree(bvec_virt(&req->special_vec));
}
}
EXPORT_SYMBOL_GPL(nvme_cleanup_cmd);
blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req)
{
struct nvme_command *cmd = nvme_req(req)->cmd;
blk_status_t ret = BLK_STS_OK;
if (!(req->rq_flags & RQF_DONTPREP))
nvme_clear_nvme_request(req);
switch (req_op(req)) {
case REQ_OP_DRV_IN:
case REQ_OP_DRV_OUT:
/* these are setup prior to execution in nvme_init_request() */
break;
case REQ_OP_FLUSH:
nvme_setup_flush(ns, cmd);
break;
case REQ_OP_ZONE_RESET_ALL:
case REQ_OP_ZONE_RESET:
ret = nvme_setup_zone_mgmt_send(ns, req, cmd, NVME_ZONE_RESET);
break;
case REQ_OP_ZONE_OPEN:
ret = nvme_setup_zone_mgmt_send(ns, req, cmd, NVME_ZONE_OPEN);
break;
case REQ_OP_ZONE_CLOSE:
ret = nvme_setup_zone_mgmt_send(ns, req, cmd, NVME_ZONE_CLOSE);
break;
case REQ_OP_ZONE_FINISH:
ret = nvme_setup_zone_mgmt_send(ns, req, cmd, NVME_ZONE_FINISH);
break;
case REQ_OP_WRITE_ZEROES:
ret = nvme_setup_write_zeroes(ns, req, cmd);
break;
case REQ_OP_DISCARD:
ret = nvme_setup_discard(ns, req, cmd);
break;
case REQ_OP_READ:
ret = nvme_setup_rw(ns, req, cmd, nvme_cmd_read);
break;
case REQ_OP_WRITE:
ret = nvme_setup_rw(ns, req, cmd, nvme_cmd_write);
break;
case REQ_OP_ZONE_APPEND:
ret = nvme_setup_rw(ns, req, cmd, nvme_cmd_zone_append);
break;
default:
WARN_ON_ONCE(1);
return BLK_STS_IOERR;
}
cmd->common.command_id = nvme_cid(req);
trace_nvme_setup_cmd(req, cmd);
return ret;
}
EXPORT_SYMBOL_GPL(nvme_setup_cmd);
/*
* Return values:
* 0: success
* >0: nvme controller's cqe status response
* <0: kernel error in lieu of controller response
*/
static int nvme_execute_rq(struct request *rq, bool at_head)
{
blk_status_t status;
status = blk_execute_rq(rq, at_head);
if (nvme_req(rq)->flags & NVME_REQ_CANCELLED)
return -EINTR;
if (nvme_req(rq)->status)
return nvme_req(rq)->status;
return blk_status_to_errno(status);
}
/*
* 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,
int qid, int at_head, blk_mq_req_flags_t flags)
{
struct request *req;
int ret;
if (qid == NVME_QID_ANY)
req = blk_mq_alloc_request(q, nvme_req_op(cmd), flags);
else
req = blk_mq_alloc_request_hctx(q, nvme_req_op(cmd), flags,
qid - 1);
if (IS_ERR(req))
return PTR_ERR(req);
nvme_init_request(req, cmd);
if (buffer && bufflen) {
ret = blk_rq_map_kern(q, req, buffer, bufflen, GFP_KERNEL);
if (ret)
goto out;
}
req->rq_flags |= RQF_QUIET;
ret = nvme_execute_rq(req, at_head);
if (result && ret >= 0)
*result = nvme_req(req)->result;
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,
NVME_QID_ANY, 0, 0);
}
EXPORT_SYMBOL_GPL(nvme_submit_sync_cmd);
static u32 nvme_known_admin_effects(u8 opcode)
{
switch (opcode) {
case nvme_admin_format_nvm:
return NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_NCC |
NVME_CMD_EFFECTS_CSE_MASK;
case nvme_admin_sanitize_nvm:
return NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK;
default:
break;
}
return 0;
}
u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode)
{
u32 effects = 0;
if (ns) {
if (ns->head->effects)
effects = le32_to_cpu(ns->head->effects->iocs[opcode]);
if (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC))
dev_warn_once(ctrl->device,
"IO command:%02x has unhandled effects:%08x\n",
opcode, effects);
return 0;
}
if (ctrl->effects)
effects = le32_to_cpu(ctrl->effects->acs[opcode]);
effects |= nvme_known_admin_effects(opcode);
return effects;
}
EXPORT_SYMBOL_NS_GPL(nvme_command_effects, NVME_TARGET_PASSTHRU);
static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
u8 opcode)
{
u32 effects = nvme_command_effects(ctrl, ns, 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_CSE_MASK) {
mutex_lock(&ctrl->scan_lock);
mutex_lock(&ctrl->subsys->lock);
nvme_mpath_start_freeze(ctrl->subsys);
nvme_mpath_wait_freeze(ctrl->subsys);
nvme_start_freeze(ctrl);
nvme_wait_freeze(ctrl);
}
return effects;
}
static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects,
struct nvme_command *cmd, int status)
{
if (effects & NVME_CMD_EFFECTS_CSE_MASK) {
nvme_unfreeze(ctrl);
nvme_mpath_unfreeze(ctrl->subsys);
mutex_unlock(&ctrl->subsys->lock);
nvme_remove_invalid_namespaces(ctrl, NVME_NSID_ALL);
mutex_unlock(&ctrl->scan_lock);
}
if (effects & NVME_CMD_EFFECTS_CCC)
nvme_init_ctrl_finish(ctrl);
if (effects & (NVME_CMD_EFFECTS_NIC | NVME_CMD_EFFECTS_NCC)) {
nvme_queue_scan(ctrl);
flush_work(&ctrl->scan_work);
}
switch (cmd->common.opcode) {
case nvme_admin_set_features:
switch (le32_to_cpu(cmd->common.cdw10) & 0xFF) {
case NVME_FEAT_KATO:
/*
* Keep alive commands interval on the host should be
* updated when KATO is modified by Set Features
* commands.
*/
if (!status)
nvme_update_keep_alive(ctrl, cmd);
break;
default:
break;
}
break;
default:
break;
}
}
int nvme_execute_passthru_rq(struct request *rq)
{
struct nvme_command *cmd = nvme_req(rq)->cmd;
struct nvme_ctrl *ctrl = nvme_req(rq)->ctrl;
struct nvme_ns *ns = rq->q->queuedata;
u32 effects;
int ret;
effects = nvme_passthru_start(ctrl, ns, cmd->common.opcode);
ret = nvme_execute_rq(rq, false);
if (effects) /* nothing to be done for zero cmd effects */
nvme_passthru_end(ctrl, effects, cmd, ret);
return ret;
}
EXPORT_SYMBOL_NS_GPL(nvme_execute_passthru_rq, NVME_TARGET_PASSTHRU);
/*
* Recommended frequency for KATO commands per NVMe 1.4 section 7.12.1:
*
* The host should send Keep Alive commands at half of the Keep Alive Timeout
* accounting for transport roundtrip times [..].
*/
static void nvme_queue_keep_alive_work(struct nvme_ctrl *ctrl)
{
queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ / 2);
}
static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status)
{
struct nvme_ctrl *ctrl = rq->end_io_data;
unsigned long flags;
bool startka = false;
blk_mq_free_request(rq);
if (status) {
dev_err(ctrl->device,
"failed nvme_keep_alive_end_io error=%d\n",
status);
return;
}
ctrl->comp_seen = false;
spin_lock_irqsave(&ctrl->lock, flags);
if (ctrl->state == NVME_CTRL_LIVE ||
ctrl->state == NVME_CTRL_CONNECTING)
startka = true;
spin_unlock_irqrestore(&ctrl->lock, flags);
if (startka)
nvme_queue_keep_alive_work(ctrl);
}
static void nvme_keep_alive_work(struct work_struct *work)
{
struct nvme_ctrl *ctrl = container_of(to_delayed_work(work),
struct nvme_ctrl, ka_work);
bool comp_seen = ctrl->comp_seen;
struct request *rq;
if ((ctrl->ctratt & NVME_CTRL_ATTR_TBKAS) && comp_seen) {
dev_dbg(ctrl->device,
"reschedule traffic based keep-alive timer\n");
ctrl->comp_seen = false;
nvme_queue_keep_alive_work(ctrl);
return;
}
rq = blk_mq_alloc_request(ctrl->admin_q, nvme_req_op(&ctrl->ka_cmd),
BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT);
if (IS_ERR(rq)) {
/* allocation failure, reset the controller */
dev_err(ctrl->device, "keep-alive failed: %ld\n", PTR_ERR(rq));
nvme_reset_ctrl(ctrl);
return;
}
nvme_init_request(rq, &ctrl->ka_cmd);
rq->timeout = ctrl->kato * HZ;
rq->end_io = nvme_keep_alive_end_io;
rq->end_io_data = ctrl;
rq->rq_flags |= RQF_QUIET;
blk_execute_rq_nowait(rq, false);
}
static void nvme_start_keep_alive(struct nvme_ctrl *ctrl)
{
if (unlikely(ctrl->kato == 0))
return;
nvme_queue_keep_alive_work(ctrl);
}
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 void nvme_update_keep_alive(struct nvme_ctrl *ctrl,
struct nvme_command *cmd)
{
unsigned int new_kato =
DIV_ROUND_UP(le32_to_cpu(cmd->common.cdw11), 1000);
dev_info(ctrl->device,
"keep alive interval updated from %u ms to %u ms\n",
ctrl->kato * 1000 / 2, new_kato * 1000 / 2);
nvme_stop_keep_alive(ctrl);
ctrl->kato = new_kato;
nvme_start_keep_alive(ctrl);
}
/*
* In NVMe 1.0 the CNS field was just a binary controller or namespace
* flag, thus sending any new CNS opcodes has a big chance of not working.
* Qemu unfortunately had that bug after reporting a 1.1 version compliance
* (but not for any later version).
*/
static bool nvme_ctrl_limited_cns(struct nvme_ctrl *ctrl)
{
if (ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS)
return ctrl->vs < NVME_VS(1, 2, 0);
return ctrl->vs < NVME_VS(1, 1, 0);
}
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_process_ns_desc(struct nvme_ctrl *ctrl, struct nvme_ns_ids *ids,
struct nvme_ns_id_desc *cur, bool *csi_seen)
{
const char *warn_str = "ctrl returned bogus length:";
void *data = cur;
switch (cur->nidt) {
case NVME_NIDT_EUI64:
if (cur->nidl != NVME_NIDT_EUI64_LEN) {
dev_warn(ctrl->device, "%s %d for NVME_NIDT_EUI64\n",
warn_str, cur->nidl);
return -1;
}
if (ctrl->quirks & NVME_QUIRK_BOGUS_NID)
return NVME_NIDT_EUI64_LEN;
memcpy(ids->eui64, data + sizeof(*cur), NVME_NIDT_EUI64_LEN);
return NVME_NIDT_EUI64_LEN;
case NVME_NIDT_NGUID:
if (cur->nidl != NVME_NIDT_NGUID_LEN) {
dev_warn(ctrl->device, "%s %d for NVME_NIDT_NGUID\n",
warn_str, cur->nidl);
return -1;
}
if (ctrl->quirks & NVME_QUIRK_BOGUS_NID)
return NVME_NIDT_NGUID_LEN;
memcpy(ids->nguid, data + sizeof(*cur), NVME_NIDT_NGUID_LEN);
return NVME_NIDT_NGUID_LEN;
case NVME_NIDT_UUID:
if (cur->nidl != NVME_NIDT_UUID_LEN) {
dev_warn(ctrl->device, "%s %d for NVME_NIDT_UUID\n",
warn_str, cur->nidl);
return -1;
}
if (ctrl->quirks & NVME_QUIRK_BOGUS_NID)
return NVME_NIDT_UUID_LEN;
uuid_copy(&ids->uuid, data + sizeof(*cur));
return NVME_NIDT_UUID_LEN;
case NVME_NIDT_CSI:
if (cur->nidl != NVME_NIDT_CSI_LEN) {
dev_warn(ctrl->device, "%s %d for NVME_NIDT_CSI\n",
warn_str, cur->nidl);
return -1;
}
memcpy(&ids->csi, data + sizeof(*cur), NVME_NIDT_CSI_LEN);
*csi_seen = true;
return NVME_NIDT_CSI_LEN;
default:
/* Skip unknown types */
return cur->nidl;
}
}
static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl,
struct nvme_ns_info *info)
{
struct nvme_command c = { };
bool csi_seen = false;
int status, pos, len;
void *data;
if (ctrl->vs < NVME_VS(1, 3, 0) && !nvme_multi_css(ctrl))
return 0;
if (ctrl->quirks & NVME_QUIRK_NO_NS_DESC_LIST)
return 0;
c.identify.opcode = nvme_admin_identify;
c.identify.nsid = cpu_to_le32(info->nsid);
c.identify.cns = NVME_ID_CNS_NS_DESC_LIST;
data = kzalloc(NVME_IDENTIFY_DATA_SIZE, GFP_KERNEL);
if (!data)
return -ENOMEM;
status = nvme_submit_sync_cmd(ctrl->admin_q, &c, data,
NVME_IDENTIFY_DATA_SIZE);
if (status) {
dev_warn(ctrl->device,
"Identify Descriptors failed (nsid=%u, status=0x%x)\n",
info->nsid, status);
goto free_data;
}
for (pos = 0; pos < NVME_IDENTIFY_DATA_SIZE; pos += len) {
struct nvme_ns_id_desc *cur = data + pos;
if (cur->nidl == 0)
break;
len = nvme_process_ns_desc(ctrl, &info->ids, cur, &csi_seen);
if (len < 0)
break;
len += sizeof(*cur);
}
if (nvme_multi_css(ctrl) && !csi_seen) {
dev_warn(ctrl->device, "Command set not reported for nsid:%d\n",
info->nsid);
status = -EINVAL;
}
free_data:
kfree(data);
return status;
}
static int nvme_identify_ns(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 -ENOMEM;
error = nvme_submit_sync_cmd(ctrl->admin_q, &c, *id, sizeof(**id));
if (error) {
dev_warn(ctrl->device, "Identify namespace failed (%d)\n", error);
goto out_free_id;
}
error = NVME_SC_INVALID_NS | NVME_SC_DNR;
if ((*id)->ncap == 0) /* namespace not allocated or attached */
goto out_free_id;
return 0;
out_free_id:
kfree(*id);
return error;
}
static int nvme_ns_info_from_identify(struct nvme_ctrl *ctrl,
struct nvme_ns_info *info)
{
struct nvme_ns_ids *ids = &info->ids;
struct nvme_id_ns *id;
int ret;
ret = nvme_identify_ns(ctrl, info->nsid, &id);
if (ret)
return ret;
info->anagrpid = id->anagrpid;
info->is_shared = id->nmic & NVME_NS_NMIC_SHARED;
info->is_readonly = id->nsattr & NVME_NS_ATTR_RO;
info->is_ready = true;
if (ctrl->quirks & NVME_QUIRK_BOGUS_NID) {
dev_info(ctrl->device,
"Ignoring bogus Namespace Identifiers\n");
} else {
if (ctrl->vs >= NVME_VS(1, 1, 0) &&
!memchr_inv(ids->eui64, 0, sizeof(ids->eui64)))
memcpy(ids->eui64, id->eui64, sizeof(ids->eui64));
if (ctrl->vs >= NVME_VS(1, 2, 0) &&
!memchr_inv(ids->nguid, 0, sizeof(ids->nguid)))
memcpy(ids->nguid, id->nguid, sizeof(ids->nguid));
}
kfree(id);
return 0;
}
static int nvme_ns_info_from_id_cs_indep(struct nvme_ctrl *ctrl,
struct nvme_ns_info *info)
{
struct nvme_id_ns_cs_indep *id;
struct nvme_command c = {
.identify.opcode = nvme_admin_identify,
.identify.nsid = cpu_to_le32(info->nsid),
.identify.cns = NVME_ID_CNS_NS_CS_INDEP,
};
int ret;
id = kmalloc(sizeof(*id), GFP_KERNEL);
if (!id)
return -ENOMEM;
ret = nvme_submit_sync_cmd(ctrl->admin_q, &c, id, sizeof(*id));
if (!ret) {
info->anagrpid = id->anagrpid;
info->is_shared = id->nmic & NVME_NS_NMIC_SHARED;
info->is_readonly = id->nsattr & NVME_NS_ATTR_RO;
info->is_ready = id->nstat & NVME_NSTAT_NRDY;
}
kfree(id);
return ret;
}
static int nvme_features(struct nvme_ctrl *dev, u8 op, unsigned int fid,
unsigned int dword11, void *buffer, size_t buflen, u32 *result)
{
union nvme_result res = { 0 };
struct nvme_command c = { };
int ret;
c.features.opcode = op;
c.features.fid = cpu_to_le32(fid);
c.features.dword11 = cpu_to_le32(dword11);
ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &res,
buffer, buflen, NVME_QID_ANY, 0, 0);
if (ret >= 0 && result)
*result = le32_to_cpu(res.u32);
return ret;
}
int nvme_set_features(struct nvme_ctrl *dev, unsigned int fid,
unsigned int dword11, void *buffer, size_t buflen,
u32 *result)
{
return nvme_features(dev, nvme_admin_set_features, fid, dword11, buffer,
buflen, result);
}
EXPORT_SYMBOL_GPL(nvme_set_features);
int nvme_get_features(struct nvme_ctrl *dev, unsigned int fid,
unsigned int dword11, void *buffer, size_t buflen,
u32 *result)
{
return nvme_features(dev, nvme_admin_get_features, fid, dword11, buffer,
buflen, result);
}
EXPORT_SYMBOL_GPL(nvme_get_features);
int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count)
{
u32 q_count = (*count - 1) | ((*count - 1) << 16);
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);
#define NVME_AEN_SUPPORTED \
(NVME_AEN_CFG_NS_ATTR | NVME_AEN_CFG_FW_ACT | \
NVME_AEN_CFG_ANA_CHANGE | NVME_AEN_CFG_DISC_CHANGE)
static void nvme_enable_aen(struct nvme_ctrl *ctrl)
{
u32 result, supported_aens = ctrl->oaes & NVME_AEN_SUPPORTED;
int status;
if (!supported_aens)
return;
status = nvme_set_features(ctrl, NVME_FEAT_ASYNC_EVENT, supported_aens,
NULL, 0, &result);
if (status)
dev_warn(ctrl->device, "Failed to configure AEN (cfg %x)\n",
supported_aens);
queue_work(nvme_wq, &ctrl->async_event_work);
}
static int nvme_ns_open(struct nvme_ns *ns)
{
/* should never be called due to GENHD_FL_HIDDEN */
if (WARN_ON_ONCE(nvme_ns_head_multipath(ns->head)))
goto fail;
if (!nvme_get_ns(ns))
goto fail;
if (!try_module_get(ns->ctrl->ops->module))
goto fail_put_ns;
return 0;
fail_put_ns:
nvme_put_ns(ns);
fail:
return -ENXIO;
}
static void nvme_ns_release(struct nvme_ns *ns)
{
module_put(ns->ctrl->ops->module);
nvme_put_ns(ns);
}
static int nvme_open(struct block_device *bdev, fmode_t mode)
{
return nvme_ns_open(bdev->bd_disk->private_data);
}
static void nvme_release(struct gendisk *disk, fmode_t mode)
{
nvme_ns_release(disk->private_data);
}
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, struct nvme_ns *ns,
u32 max_integrity_segments)
{
struct blk_integrity integrity = { };
switch (ns->pi_type) {
case NVME_NS_DPS_PI_TYPE3:
switch (ns->guard_type) {
case NVME_NVM_NS_16B_GUARD:
integrity.profile = &t10_pi_type3_crc;
integrity.tag_size = sizeof(u16) + sizeof(u32);
integrity.flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
break;
case NVME_NVM_NS_64B_GUARD:
integrity.profile = &ext_pi_type3_crc64;
integrity.tag_size = sizeof(u16) + 6;
integrity.flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
break;
default:
integrity.profile = NULL;
break;
}
break;
case NVME_NS_DPS_PI_TYPE1:
case NVME_NS_DPS_PI_TYPE2:
switch (ns->guard_type) {
case NVME_NVM_NS_16B_GUARD:
integrity.profile = &t10_pi_type1_crc;
integrity.tag_size = sizeof(u16);
integrity.flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
break;
case NVME_NVM_NS_64B_GUARD:
integrity.profile = &ext_pi_type1_crc64;
integrity.tag_size = sizeof(u16);
integrity.flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
break;
default:
integrity.profile = NULL;
break;
}
break;
default:
integrity.profile = NULL;
break;
}
integrity.tuple_size = ns->ms;
blk_integrity_register(disk, &integrity);
blk_queue_max_integrity_segments(disk->queue, max_integrity_segments);
}
#else
static void nvme_init_integrity(struct gendisk *disk, struct nvme_ns *ns,
u32 max_integrity_segments)
{
}
#endif /* CONFIG_BLK_DEV_INTEGRITY */
static void nvme_config_discard(struct gendisk *disk, struct nvme_ns *ns)
{
struct nvme_ctrl *ctrl = ns->ctrl;
struct request_queue *queue = disk->queue;
u32 size = queue_logical_block_size(queue);
if (ctrl->max_discard_sectors == 0) {
blk_queue_max_discard_sectors(queue, 0);
return;
}
BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) <
NVME_DSM_MAX_RANGES);
queue->limits.discard_granularity = size;
/* If discard is already enabled, don't reset queue limits */
if (queue->limits.max_discard_sectors)
return;
if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(ns, UINT_MAX))
ctrl->max_discard_sectors = nvme_lba_to_sect(ns, ctrl->dmrsl);
blk_queue_max_discard_sectors(queue, ctrl->max_discard_sectors);
blk_queue_max_discard_segments(queue, ctrl->max_discard_segments);
if (ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES)
blk_queue_max_write_zeroes_sectors(queue, UINT_MAX);
}
static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b)
{
return uuid_equal(&a->uuid, &b->uuid) &&
memcmp(&a->nguid, &b->nguid, sizeof(a->nguid)) == 0 &&
memcmp(&a->eui64, &b->eui64, sizeof(a->eui64)) == 0 &&
a->csi == b->csi;
}
static int nvme_init_ms(struct nvme_ns *ns, struct nvme_id_ns *id)
{
bool first = id->dps & NVME_NS_DPS_PI_FIRST;
unsigned lbaf = nvme_lbaf_index(id->flbas);
struct nvme_ctrl *ctrl = ns->ctrl;
struct nvme_command c = { };
struct nvme_id_ns_nvm *nvm;
int ret = 0;
u32 elbaf;
ns->pi_size = 0;
ns->ms = le16_to_cpu(id->lbaf[lbaf].ms);
if (!(ctrl->ctratt & NVME_CTRL_ATTR_ELBAS)) {
ns->pi_size = sizeof(struct t10_pi_tuple);
ns->guard_type = NVME_NVM_NS_16B_GUARD;
goto set_pi;
}
nvm = kzalloc(sizeof(*nvm), GFP_KERNEL);
if (!nvm)
return -ENOMEM;
c.identify.opcode = nvme_admin_identify;
c.identify.nsid = cpu_to_le32(ns->head->ns_id);
c.identify.cns = NVME_ID_CNS_CS_NS;
c.identify.csi = NVME_CSI_NVM;
ret = nvme_submit_sync_cmd(ns->ctrl->admin_q, &c, nvm, sizeof(*nvm));
if (ret)
goto free_data;
elbaf = le32_to_cpu(nvm->elbaf[lbaf]);
/* no support for storage tag formats right now */
if (nvme_elbaf_sts(elbaf))
goto free_data;
ns->guard_type = nvme_elbaf_guard_type(elbaf);
switch (ns->guard_type) {
case NVME_NVM_NS_64B_GUARD:
ns->pi_size = sizeof(struct crc64_pi_tuple);
break;
case NVME_NVM_NS_16B_GUARD:
ns->pi_size = sizeof(struct t10_pi_tuple);
break;
default:
break;
}
free_data:
kfree(nvm);
set_pi:
if (ns->pi_size && (first || ns->ms == ns->pi_size))
ns->pi_type = id->dps & NVME_NS_DPS_PI_MASK;
else
ns->pi_type = 0;
return ret;
}
static void nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id)
{
struct nvme_ctrl *ctrl = ns->ctrl;
if (nvme_init_ms(ns, id))
return;
ns->features &= ~(NVME_NS_METADATA_SUPPORTED | NVME_NS_EXT_LBAS);
if (!ns->ms || !(ctrl->ops->flags & NVME_F_METADATA_SUPPORTED))
return;
if (ctrl->ops->flags & NVME_F_FABRICS) {
/*
* The NVMe over Fabrics specification only supports metadata as
* part of the extended data LBA. We rely on HCA/HBA support to
* remap the separate metadata buffer from the block layer.
*/
if (WARN_ON_ONCE(!(id->flbas & NVME_NS_FLBAS_META_EXT)))
return;
ns->features |= NVME_NS_EXT_LBAS;
/*
* The current fabrics transport drivers support namespace
* metadata formats only if nvme_ns_has_pi() returns true.
* Suppress support for all other formats so the namespace will
* have a 0 capacity and not be usable through the block stack.
*
* Note, this check will need to be modified if any drivers
* gain the ability to use other metadata formats.
*/
if (ctrl->max_integrity_segments && nvme_ns_has_pi(ns))
ns->features |= NVME_NS_METADATA_SUPPORTED;
} else {
/*
* For PCIe controllers, we can't easily remap the separate
* metadata buffer from the block layer and thus require a
* separate metadata buffer for block layer metadata/PI support.
* We allow extended LBAs for the passthrough interface, though.
*/
if (id->flbas & NVME_NS_FLBAS_META_EXT)
ns->features |= NVME_NS_EXT_LBAS;
else
ns->features |= NVME_NS_METADATA_SUPPORTED;
}
}
static void nvme_set_queue_limits(struct nvme_ctrl *ctrl,
struct request_queue *q)
{
bool vwc = ctrl->vwc & NVME_CTRL_VWC_PRESENT;
if (ctrl->max_hw_sectors) {
u32 max_segments =
(ctrl->max_hw_sectors / (NVME_CTRL_PAGE_SIZE >> 9)) + 1;
max_segments = min_not_zero(max_segments, ctrl->max_segments);
blk_queue_max_hw_sectors(q, ctrl->max_hw_sectors);
blk_queue_max_segments(q, min_t(u32, max_segments, USHRT_MAX));
}
blk_queue_virt_boundary(q, NVME_CTRL_PAGE_SIZE - 1);
blk_queue_dma_alignment(q, 3);
blk_queue_write_cache(q, vwc, vwc);
}
static void nvme_update_disk_info(struct gendisk *disk,
struct nvme_ns *ns, struct nvme_id_ns *id)
{
sector_t capacity = nvme_lba_to_sect(ns, le64_to_cpu(id->nsze));
unsigned short bs = 1 << ns->lba_shift;
u32 atomic_bs, phys_bs, io_opt = 0;
/*
* The block layer can't support LBA sizes larger than the page size
* yet, so catch this early and don't allow block I/O.
*/
if (ns->lba_shift > PAGE_SHIFT) {
capacity = 0;
bs = (1 << 9);
}
blk_integrity_unregister(disk);
atomic_bs = phys_bs = bs;
if (id->nabo == 0) {
/*
* Bit 1 indicates whether NAWUPF is defined for this namespace
* and whether it should be used instead of AWUPF. If NAWUPF ==
* 0 then AWUPF must be used instead.
*/
if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf)
atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs;
else
atomic_bs = (1 + ns->ctrl->subsys->awupf) * bs;
}
if (id->nsfeat & NVME_NS_FEAT_IO_OPT) {
/* NPWG = Namespace Preferred Write Granularity */
phys_bs = bs * (1 + le16_to_cpu(id->npwg));
/* NOWS = Namespace Optimal Write Size */
io_opt = bs * (1 + le16_to_cpu(id->nows));
}
blk_queue_logical_block_size(disk->queue, bs);
/*
* Linux filesystems assume writing a single physical block is
* an atomic operation. Hence limit the physical block size to the
* value of the Atomic Write Unit Power Fail parameter.
*/
blk_queue_physical_block_size(disk->queue, min(phys_bs, atomic_bs));
blk_queue_io_min(disk->queue, phys_bs);
blk_queue_io_opt(disk->queue, io_opt);
/*
* Register a metadata profile for PI, or the plain non-integrity NVMe
* metadata masquerading as Type 0 if supported, otherwise reject block
* I/O to namespaces with metadata except when the namespace supports
* PI, as it can strip/insert in that case.
*/
if (ns->ms) {
if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) &&
(ns->features & NVME_NS_METADATA_SUPPORTED))
nvme_init_integrity(disk, ns,
ns->ctrl->max_integrity_segments);
else if (!nvme_ns_has_pi(ns))
capacity = 0;
}
set_capacity_and_notify(disk, capacity);
nvme_config_discard(disk, ns);
blk_queue_max_write_zeroes_sectors(disk->queue,
ns->ctrl->max_zeroes_sectors);
}
static bool nvme_ns_is_readonly(struct nvme_ns *ns, struct nvme_ns_info *info)
{
return info->is_readonly || test_bit(NVME_NS_FORCE_RO, &ns->flags);
}
static inline bool nvme_first_scan(struct gendisk *disk)
{
/* nvme_alloc_ns() scans the disk prior to adding it */
return !disk_live(disk);
}
static void nvme_set_chunk_sectors(struct nvme_ns *ns, struct nvme_id_ns *id)
{
struct nvme_ctrl *ctrl = ns->ctrl;
u32 iob;
if ((ctrl->quirks & NVME_QUIRK_STRIPE_SIZE) &&
is_power_of_2(ctrl->max_hw_sectors))
iob = ctrl->max_hw_sectors;
else
iob = nvme_lba_to_sect(ns, le16_to_cpu(id->noiob));
if (!iob)
return;
if (!is_power_of_2(iob)) {
if (nvme_first_scan(ns->disk))
pr_warn("%s: ignoring unaligned IO boundary:%u\n",
ns->disk->disk_name, iob);
return;
}
if (blk_queue_is_zoned(ns->disk->queue)) {
if (nvme_first_scan(ns->disk))
pr_warn("%s: ignoring zoned namespace IO boundary\n",
ns->disk->disk_name);
return;
}
blk_queue_chunk_sectors(ns->queue, iob);
}
static int nvme_update_ns_info_generic(struct nvme_ns *ns,
struct nvme_ns_info *info)
{
blk_mq_freeze_queue(ns->disk->queue);
nvme_set_queue_limits(ns->ctrl, ns->queue);
set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info));
blk_mq_unfreeze_queue(ns->disk->queue);
if (nvme_ns_head_multipath(ns->head)) {
blk_mq_freeze_queue(ns->head->disk->queue);
set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info));
nvme_mpath_revalidate_paths(ns);
blk_stack_limits(&ns->head->disk->queue->limits,
&ns->queue->limits, 0);
ns->head->disk->flags |= GENHD_FL_HIDDEN;
blk_mq_unfreeze_queue(ns->head->disk->queue);
}
/* Hide the block-interface for these devices */
ns->disk->flags |= GENHD_FL_HIDDEN;
set_bit(NVME_NS_READY, &ns->flags);
return 0;
}
static int nvme_update_ns_info_block(struct nvme_ns *ns,
struct nvme_ns_info *info)
{
struct nvme_id_ns *id;
unsigned lbaf;
int ret;
ret = nvme_identify_ns(ns->ctrl, info->nsid, &id);
if (ret)
return ret;
blk_mq_freeze_queue(ns->disk->queue);
lbaf = nvme_lbaf_index(id->flbas);
ns->lba_shift = id->lbaf[lbaf].ds;
nvme_set_queue_limits(ns->ctrl, ns->queue);
nvme_configure_metadata(ns, id);
nvme_set_chunk_sectors(ns, id);
nvme_update_disk_info(ns->disk, ns, id);
if (ns->head->ids.csi == NVME_CSI_ZNS) {
ret = nvme_update_zone_info(ns, lbaf);
if (ret) {
blk_mq_unfreeze_queue(ns->disk->queue);
goto out;
}
}
set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info));
set_bit(NVME_NS_READY, &ns->flags);
blk_mq_unfreeze_queue(ns->disk->queue);
if (blk_queue_is_zoned(ns->queue)) {
ret = nvme_revalidate_zones(ns);
if (ret && !nvme_first_scan(ns->disk))
goto out;
}
if (nvme_ns_head_multipath(ns->head)) {
blk_mq_freeze_queue(ns->head->disk->queue);
nvme_update_disk_info(ns->head->disk, ns, id);
set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info));
nvme_mpath_revalidate_paths(ns);
blk_stack_limits(&ns->head->disk->queue->limits,
&ns->queue->limits, 0);
disk_update_readahead(ns->head->disk);
blk_mq_unfreeze_queue(ns->head->disk->queue);
}
ret = 0;
out:
/*
* If probing fails due an unsupported feature, hide the block device,
* but still allow other access.
*/
if (ret == -ENODEV) {
ns->disk->flags |= GENHD_FL_HIDDEN;
set_bit(NVME_NS_READY, &ns->flags);
ret = 0;
}
kfree(id);
return ret;
}
static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info)
{
switch (info->ids.csi) {
case NVME_CSI_ZNS:
if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED)) {
dev_info(ns->ctrl->device,
"block device for nsid %u not supported without CONFIG_BLK_DEV_ZONED\n",
info->nsid);
return nvme_update_ns_info_generic(ns, info);
}
return nvme_update_ns_info_block(ns, info);
case NVME_CSI_NVM:
return nvme_update_ns_info_block(ns, info);
default:
dev_info(ns->ctrl->device,
"block device for nsid %u not supported (csi %u)\n",
info->nsid, info->ids.csi);
return nvme_update_ns_info_generic(ns, info);
}
}
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_send_ns_head_pr_command(struct block_device *bdev,
struct nvme_command *c, u8 data[16])
{
struct nvme_ns_head *head = bdev->bd_disk->private_data;
int srcu_idx = srcu_read_lock(&head->srcu);
struct nvme_ns *ns = nvme_find_path(head);
int ret = -EWOULDBLOCK;
if (ns) {
c->common.nsid = cpu_to_le32(ns->head->ns_id);
ret = nvme_submit_sync_cmd(ns->queue, c, data, 16);
}
srcu_read_unlock(&head->srcu, srcu_idx);
return ret;
}
static int nvme_send_ns_pr_command(struct nvme_ns *ns, struct nvme_command *c,
u8 data[16])
{
c->common.nsid = cpu_to_le32(ns->head->ns_id);
return nvme_submit_sync_cmd(ns->queue, c, data, 16);
}
static int nvme_pr_command(struct block_device *bdev, u32 cdw10,
u64 key, u64 sa_key, u8 op)
{
struct nvme_command c = { };
u8 data[16] = { 0, };
put_unaligned_le64(key, &data[0]);
put_unaligned_le64(sa_key, &data[8]);
c.common.opcode = op;
c.common.cdw10 = cpu_to_le32(cdw10);
if (IS_ENABLED(CONFIG_NVME_MULTIPATH) &&
bdev->bd_disk->fops == &nvme_ns_head_ops)
return nvme_send_ns_head_pr_command(bdev, &c, data);
return nvme_send_ns_pr_command(bdev->bd_disk->private_data, &c, data);
}
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);
}
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 = { };
if (send)
cmd.common.opcode = nvme_admin_security_send;
else
cmd.common.opcode = nvme_admin_security_recv;
cmd.common.nsid = 0;
cmd.common.cdw10 = cpu_to_le32(((u32)secp) << 24 | ((u32)spsp) << 8);
cmd.common.cdw11 = cpu_to_le32(len);
return __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, NULL, buffer, len,
NVME_QID_ANY, 1, 0);
}
EXPORT_SYMBOL_GPL(nvme_sec_submit);
#endif /* CONFIG_BLK_SED_OPAL */
#ifdef CONFIG_BLK_DEV_ZONED
static int nvme_report_zones(struct gendisk *disk, sector_t sector,
unsigned int nr_zones, report_zones_cb cb, void *data)
{
return nvme_ns_report_zones(disk->private_data, sector, nr_zones, cb,
data);
}
#else
#define nvme_report_zones NULL
#endif /* CONFIG_BLK_DEV_ZONED */
static const struct block_device_operations nvme_bdev_ops = {
.owner = THIS_MODULE,
.ioctl = nvme_ioctl,
.compat_ioctl = blkdev_compat_ptr_ioctl,
.open = nvme_open,
.release = nvme_release,
.getgeo = nvme_getgeo,
.report_zones = nvme_report_zones,
.pr_ops = &nvme_pr_ops,
};
static int nvme_wait_ready(struct nvme_ctrl *ctrl, u32 timeout, bool enabled)
{
unsigned long timeout_jiffies = ((timeout + 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;
usleep_range(1000, 2000);
if (fatal_signal_pending(current))
return -EINTR;
if (time_after(jiffies, timeout_jiffies)) {
dev_err(ctrl->device,
"Device not ready; aborting %s, CSTS=0x%x<