leandrof/linux
1
0
Fork 0
forked from Minki/linux
Code Issues Pull Requests Packages Projects Releases Wiki Activity
38dabe210f
linux/drivers/nvme/host/core.c
Keith Busch 38dabe210f nvme: centralize AEN defines 
All the transports were unnecessarilly duplicating the AEN request
accounting. This patch defines everything in one place.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Guan Junxiong <guanjunxiong@huawei.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-11-10 19:53:25 -07:00

3044 lines
76 KiB
C
Raw Blame History

/*
* 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>
#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");
struct workqueue_struct *nvme_wq;
EXPORT_SYMBOL_GPL(nvme_wq);
static DEFINE_IDA(nvme_instance_ida);
static dev_t nvme_chr_devt;
static struct class *nvme_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_wq, &ctrl->reset_work))
return -EBUSY;
return 0;
}
EXPORT_SYMBOL_GPL(nvme_reset_ctrl);
static int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl)
{
int ret;
ret = nvme_reset_ctrl(ctrl);
if (!ret)
flush_work(&ctrl->reset_work);
return ret;
}
static 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_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_ONCS_NOT_SUPPORTED:
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:
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;
if (blk_queue_dying(req->q))
return false;
return true;
}
void nvme_complete_rq(struct request *req)
{
if (unlikely(nvme_req(req)->status && nvme_req_needs_retry(req))) {
nvme_req(req)->retries++;
blk_mq_requeue_request(req, true);
return;
}
blk_mq_end_request(req, nvme_error_status(req));
}
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_LIVE:
switch (old_state) {
case NVME_CTRL_NEW:
case NVME_CTRL_RESETTING:
case NVME_CTRL_RECONNECTING:
changed = true;
/* FALLTHRU */
default:
break;
}
break;
case NVME_CTRL_RESETTING:
switch (old_state) {
case NVME_CTRL_NEW:
case NVME_CTRL_LIVE:
changed = true;
/* FALLTHRU */
default:
break;
}
break;
case NVME_CTRL_RECONNECTING:
switch (old_state) {
case NVME_CTRL_LIVE:
case NVME_CTRL_RESETTING:
changed = true;
/* FALLTHRU */
default:
break;
}
break;
case NVME_CTRL_DELETING:
switch (old_state) {
case NVME_CTRL_LIVE:
case NVME_CTRL_RESETTING:
case NVME_CTRL_RECONNECTING:
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);
return changed;
}
EXPORT_SYMBOL_GPL(nvme_change_ctrl_state);
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);
ida_simple_remove(&ns->ctrl->ns_ida, ns->instance);
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, unsigned int 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->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;
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->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->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;
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, int 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 nvme_command c;
struct request *rq;
memset(&c, 0, sizeof(c));
c.common.opcode = nvme_admin_keep_alive;
rq = nvme_alloc_request(ctrl->admin_q, &c, BLK_MQ_REQ_RESERVED,
NVME_QID_ANY);
if (IS_ERR(rq))
return PTR_ERR(rq);
rq->timeout = ctrl->kato * HZ;
rq->end_io_data = ctrl;
blk_execute_rq_nowait(rq->q, NULL, rq, 0, nvme_keep_alive_end_io);
return 0;
}
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);
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,
u8 *eui64, u8 *nguid, uuid_t *uuid)
{
struct nvme_command c = { };
int status;
void *data;
int pos;
int len;
c.identify.opcode = nvme_admin_identify;
c.identify.nsid = cpu_to_le32(nsid);
c.identify.cns = NVME_ID_CNS_NS_DESC_LIST;
data = kzalloc(NVME_IDENTIFY_DATA_SIZE, GFP_KERNEL);
if (!data)
return -ENOMEM;
status = nvme_submit_sync_cmd(ctrl->admin_q, &c, data,
NVME_IDENTIFY_DATA_SIZE);
if (status)
goto free_data;
for (pos = 0; pos < NVME_IDENTIFY_DATA_SIZE; pos += len) {
struct nvme_ns_id_desc *cur = data + pos;
if (cur->nidl == 0)
break;
switch (cur->nidt) {
case NVME_NIDT_EUI64:
if (cur->nidl != NVME_NIDT_EUI64_LEN) {
dev_warn(ctrl->device,
"ctrl returned bogus length: %d for NVME_NIDT_EUI64\n",
cur->nidl);
goto free_data;
}
len = NVME_NIDT_EUI64_LEN;
memcpy(eui64, data + pos + sizeof(*cur), len);
break;
case NVME_NIDT_NGUID:
if (cur->nidl != NVME_NIDT_NGUID_LEN) {
dev_warn(ctrl->device,
"ctrl returned bogus length: %d for NVME_NIDT_NGUID\n",
cur->nidl);
goto free_data;
}
len = NVME_NIDT_NGUID_LEN;
memcpy(nguid, data + pos + sizeof(*cur), len);
break;
case NVME_NIDT_UUID:
if (cur->nidl != NVME_NIDT_UUID_LEN) {
dev_warn(ctrl->device,
"ctrl returned bogus length: %d for NVME_NIDT_UUID\n",
cur->nidl);
goto free_data;
}
len = NVME_NIDT_UUID_LEN;
uuid_copy(uuid, data + pos + sizeof(*cur));
break;
default:
/* Skip unnkown types */
len = cur->nidl;
break;
}
len += sizeof(*cur);
}
free_data:
kfree(data);
return status;
}
static int nvme_identify_ns_list(struct nvme_ctrl *dev, unsigned nsid, __le32 *ns_list)
{
struct nvme_command c = { };
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->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;
mutex_lock(&ctrl->namespaces_mutex);
list_for_each_entry(ns, &ctrl->namespaces, list) {
if (ns->disk && nvme_revalidate_disk(ns->disk))
nvme_ns_remove(ns);
}
mutex_unlock(&ctrl->namespaces_mutex);
}
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;
}
static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
unsigned int cmd, unsigned long arg)
{
struct nvme_ns *ns = bdev->bd_disk->private_data;
switch (cmd) {
case NVME_IOCTL_ID:
force_successful_syscall_return();
return ns->ns_id;
case NVME_IOCTL_ADMIN_CMD:
return nvme_user_cmd(ns->ctrl, NULL, (void __user *)arg);
case NVME_IOCTL_IO_CMD:
return nvme_user_cmd(ns->ctrl, ns, (void __user *)arg);
case NVME_IOCTL_SUBMIT_IO:
return nvme_submit_io(ns, (void __user *)arg);
default:
#ifdef CONFIG_NVM
if (ns->ndev)
return nvme_nvm_ioctl(ns, cmd, arg);
#endif
if (is_sed_ioctl(cmd))
return sed_ioctl(ns->ctrl->opal_dev, cmd,
(void __user *) arg);
return -ENOTTY;
}
}
static int nvme_open(struct block_device *bdev, fmode_t mode)
{
struct nvme_ns *ns = bdev->bd_disk->private_data;
if (!kref_get_unless_zero(&ns->kref))
return -ENXIO;
return 0;
}
static void nvme_release(struct gendisk *disk, fmode_t mode)
{
nvme_put_ns(disk->private_data);
}
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 = size;
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, u8 *eui64, u8 *nguid, uuid_t *uuid)
{
if (ctrl->vs >= NVME_VS(1, 1, 0))
memcpy(eui64, id->eui64, sizeof(id->eui64));
if (ctrl->vs >= NVME_VS(1, 2, 0))
memcpy(nguid, id->nguid, sizeof(id->nguid));
if (ctrl->vs >= NVME_VS(1, 3, 0)) {
/* Don't treat error as fatal we potentially
* already have a NGUID or EUI-64
*/
if (nvme_identify_ns_descs(ctrl, nsid, eui64, nguid, uuid))
dev_warn(ctrl->device,
"%s: Identify Descriptors failed\n", __func__);
}
}
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 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, 1 << ns->lba_shift);
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);
}
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;
u8 eui64[8] = { 0 }, nguid[16] = { 0 };
uuid_t uuid = uuid_null;
int ret = 0;
if (test_bit(NVME_NS_DEAD, &ns->flags)) {
set_capacity(disk, 0);
return -ENODEV;
}
id = nvme_identify_ns(ctrl, ns->ns_id);
if (!id)
return -ENODEV;
if (id->ncap == 0) {
ret = -ENODEV;
goto out;
}
nvme_report_ns_ids(ctrl, ns->ns_id, id, eui64, nguid, &uuid);
if (!uuid_equal(&ns->uuid, &uuid) ||
memcmp(&ns->nguid, &nguid, sizeof(ns->nguid)) ||
memcmp(&ns->eui, &eui64, sizeof(ns->eui))) {
dev_err(ctrl->device,
"identifiers changed for nsid %d\n", ns->ns_id);
ret = -ENODEV;
}
out:
kfree(id);
return ret;
}
static char nvme_pr_type(enum pr_type type)
{
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 *ns = bdev->bd_disk->private_data;
struct nvme_command c;
u8 data[16] = { 0, };
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->ns_id);
c.common.cdw10[0] = cpu_to_le32(cdw10);
return nvme_submit_sync_cmd(ns->queue, &c, data, 16);
}
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,
};
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)
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_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(ctrl->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(ctrl->subnqn, NVMF_NQN_SIZE,
"nqn.2014.08.org.nvmexpress:%4x%4x",
le16_to_cpu(id->vid), le16_to_cpu(id->ssvid));
memcpy(ctrl->subnqn + off, id->sn, sizeof(id->sn));
off += sizeof(id->sn);
memcpy(ctrl->subnqn + off, id->mn, sizeof(id->mn));
off += sizeof(id->mn);
memset(ctrl->subnqn + off, 0, sizeof(ctrl->subnqn) - off);
}
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;
}
nvme_init_subnqn(ctrl, id);
if (!ctrl->identified) {
/*
* 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.
*/
int i;
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->vid = le16_to_cpu(id->vid);
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);
memcpy(ctrl->serial, id->sn, sizeof(id->sn));
memcpy(ctrl->model, id->mn, sizeof(id->mn));
memcpy(ctrl->firmware_rev, id->fr, sizeof(id->fr));
if (id->mdts)
max_hw_sectors = 1 << (id->mdts + page_shift - 9);
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_warn(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);
if (ctrl->state != NVME_CTRL_LIVE)
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 ssize_t wwid_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
struct nvme_ctrl *ctrl = ns->ctrl;
int serial_len = sizeof(ctrl->serial);
int model_len = sizeof(ctrl->model);
if (!uuid_is_null(&ns->uuid))
return sprintf(buf, "uuid.%pU\n", &ns->uuid);
if (memchr_inv(ns->nguid, 0, sizeof(ns->nguid)))
return sprintf(buf, "eui.%16phN\n", ns->nguid);
if (memchr_inv(ns->eui, 0, sizeof(ns->eui)))
return sprintf(buf, "eui.%8phN\n", ns->eui);
while (serial_len > 0 && (ctrl->serial[serial_len - 1] == ' ' ||
ctrl->serial[serial_len - 1] == '\0'))
serial_len--;
while (model_len > 0 && (ctrl->model[model_len - 1] == ' ' ||
ctrl->model[model_len - 1] == '\0'))
model_len--;
return sprintf(buf, "nvme.%04x-%*phN-%*phN-%08x\n", ctrl->vid,
serial_len, ctrl->serial, model_len, ctrl->model, ns->ns_id);
}
static DEVICE_ATTR(wwid, S_IRUGO, wwid_show, NULL);
static ssize_t nguid_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
return sprintf(buf, "%pU\n", ns->nguid);
}
static DEVICE_ATTR(nguid, S_IRUGO, nguid_show, NULL);
static ssize_t uuid_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
/* For backward compatibility expose the NGUID to userspace if
* we have no UUID set
*/
if (uuid_is_null(&ns->uuid)) {
printk_ratelimited(KERN_WARNING
"No UUID available providing old NGUID\n");
return sprintf(buf, "%pU\n", ns->nguid);
}
return sprintf(buf, "%pU\n", &ns->uuid);
}
static DEVICE_ATTR(uuid, S_IRUGO, uuid_show, NULL);
static ssize_t eui_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
return sprintf(buf, "%8ph\n", ns->eui);
}
static DEVICE_ATTR(eui, S_IRUGO, eui_show, NULL);
static ssize_t nsid_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
return sprintf(buf, "%d\n", ns->ns_id);
}
static DEVICE_ATTR(nsid, S_IRUGO, nsid_show, NULL);
static struct attribute *nvme_ns_attrs[] = {
&dev_attr_wwid.attr,
&dev_attr_uuid.attr,
&dev_attr_nguid.attr,
&dev_attr_eui.attr,
&dev_attr_nsid.attr,
NULL,
};
static umode_t nvme_ns_attrs_are_visible(struct kobject *kobj,
struct attribute *a, int n)
{
struct device *dev = container_of(kobj, struct device, kobj);
struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
if (a == &dev_attr_uuid.attr) {
if (uuid_is_null(&ns->uuid) ||
!memchr_inv(ns->nguid, 0, sizeof(ns->nguid)))
return 0;
}
if (a == &dev_attr_nguid.attr) {
if (!memchr_inv(ns->nguid, 0, sizeof(ns->nguid)))
return 0;
}
if (a == &dev_attr_eui.attr) {
if (!memchr_inv(ns->eui, 0, sizeof(ns->eui)))
return 0;
}
return a->mode;
}
static const struct attribute_group nvme_ns_attr_group = {
.attrs = nvme_ns_attrs,
.is_visible = nvme_ns_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->field), ctrl->field); \
} \
static DEVICE_ATTR(field, S_IRUGO, field##_show, NULL);
#define nvme_show_int_function(field) \
static ssize_t field##_show(struct device *dev, \
struct device_attribute *attr, char *buf) \
{ \
struct nvme_ctrl *ctrl = dev_get_drvdata(dev); \
return sprintf(buf, "%d\n", ctrl->field); \
} \
static DEVICE_ATTR(field, S_IRUGO, field##_show, NULL);
nvme_show_str_function(model);
nvme_show_str_function(serial);
nvme_show_str_function(firmware_rev);
nvme_show_int_function(cntlid);
static ssize_t nvme_sysfs_delete(struct device *dev,
struct device_attribute *attr, const char *buf,
size_t count)
{
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_RESETTING] = "resetting",
[NVME_CTRL_RECONNECTING]= "reconnecting",
[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->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 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->ns_id - nsb->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->ns_id == nsid) {
if (!kref_get_unless_zero(&ns->kref))
continue;
ret = ns;
break;
}
if (ns->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->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);
ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node);
if (!ns)
return;
ns->instance = ida_simple_get(&ctrl->ns_ida, 1, 0, GFP_KERNEL);
if (ns->instance < 0)
goto out_free_ns;
ns->queue = blk_mq_init_queue(ctrl->tagset);
if (IS_ERR(ns->queue))
goto out_release_instance;
queue_flag_set_unlocked(QUEUE_FLAG_NONROT, ns->queue);
ns->queue->queuedata = ns;
ns->ctrl = ctrl;
kref_init(&ns->kref);
ns->ns_id = nsid;
ns->lba_shift = 9; /* set to a default value for 512 until disk is validated */
blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift);
nvme_set_queue_limits(ctrl, ns->queue);
nvme_setup_streams_ns(ctrl, ns);
sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->instance);
id = nvme_identify_ns(ctrl, nsid);
if (!id)
goto out_free_queue;
if (id->ncap == 0)
goto out_free_id;
nvme_report_ns_ids(ctrl, ns->ns_id, id, ns->eui, ns->nguid, &ns->uuid);
if ((ctrl->quirks & NVME_QUIRK_LIGHTNVM) && id->vs[0] == 0x1) {
if (nvme_nvm_register(ns, disk_name, node)) {
dev_warn(ctrl->device, "LightNVM init failure\n");
goto out_free_id;
}
}
disk = alloc_disk_node(0, node);
if (!disk)
goto out_free_id;
disk->fops = &nvme_fops;
disk->private_data = ns;
disk->queue = ns->queue;
disk->flags = GENHD_FL_EXT_DEVT;
memcpy(disk->disk_name, disk_name, DISK_NAME_LEN);
ns->disk = disk;
__nvme_revalidate_disk(disk, id);
mutex_lock(&ctrl->namespaces_mutex);
list_add_tail(&ns->list, &ctrl->namespaces);
mutex_unlock(&ctrl->namespaces_mutex);
nvme_get_ctrl(ctrl);
kfree(id);
device_add_disk(ctrl->device, ns->disk);
if (sysfs_create_group(&disk_to_dev(ns->disk)->kobj,
&nvme_ns_attr_group))
pr_warn("%s: failed to create sysfs group for identification\n",
ns->disk->disk_name);
if (ns->ndev && nvme_nvm_register_sysfs(ns))
pr_warn("%s: failed to register lightnvm sysfs group for identification\n",
ns->disk->disk_name);
return;
out_free_id:
kfree(id);
out_free_queue:
blk_cleanup_queue(ns->queue);
out_release_instance:
ida_simple_remove(&ctrl->ns_ida, ns->instance);
out_free_ns:
kfree(ns);
}
static void nvme_ns_remove(struct nvme_ns *ns)
{
if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags))
return;
if (ns->disk && ns->disk->flags & GENHD_FL_UP) {
if (blk_get_integrity(ns->disk))
blk_integrity_unregister(ns->disk);
sysfs_remove_group(&disk_to_dev(ns->disk)->kobj,
&nvme_ns_attr_group);
if (ns->ndev)
nvme_nvm_unregister_sysfs(ns);
del_gendisk(ns->disk);
blk_cleanup_queue(ns->queue);
}
mutex_lock(&ns->ctrl->namespaces_mutex);
list_del_init(&ns->list);
mutex_unlock(&ns->ctrl->namespaces_mutex);
nvme_put_ns(ns);
}
static void nvme_validate_ns(struct nvme_ctrl *ctrl, unsigned nsid)
{
struct nvme_ns *ns;
ns = nvme_find_get_ns(ctrl, nsid);
if (ns) {
if (ns->disk && revalidate_disk(ns->disk))
nvme_ns_remove(ns);
nvme_put_ns(ns);
} else
nvme_alloc_ns(ctrl, nsid);
}
static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
unsigned nsid)
{
struct nvme_ns *ns, *next;
list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) {
if (ns->ns_id > nsid)
nvme_ns_remove(ns);
}
}
static int nvme_scan_ns_list(struct nvme_ctrl *ctrl, unsigned nn)
{
struct nvme_ns *ns;
__le32 *ns_list;
unsigned i, j, nsid, prev = 0, num_lists = DIV_ROUND_UP(nn, 1024);
int ret = 0;
ns_list = kzalloc(0x1000, GFP_KERNEL);
if (!ns_list)
return -ENOMEM;
for (i = 0; i < num_lists; i++) {
ret = nvme_identify_ns_list(ctrl, prev, ns_list);
if (ret)
goto free;
for (j = 0; j < min(nn, 1024U); j++) {
nsid = le32_to_cpu(ns_list[j]);
if (!nsid)
goto out;
nvme_validate_ns(ctrl, nsid);
while (++prev < nsid) {
ns = nvme_find_get_ns(ctrl, prev);
if (ns) {
nvme_ns_remove(ns);
nvme_put_ns(ns);
}
}
}
nn -= j;
}
out:
nvme_remove_invalid_namespaces(ctrl, prev);
free:
kfree(ns_list);
return ret;
}
static void nvme_scan_ns_sequential(struct nvme_ctrl *ctrl, unsigned nn)
{
unsigned i;
for (i = 1; i <= nn; i++)
nvme_validate_ns(ctrl, i);
nvme_remove_invalid_namespaces(ctrl, nn);
}
static void nvme_scan_work(struct work_struct *work)
{
struct nvme_ctrl *ctrl =
container_of(work, struct nvme_ctrl, scan_work);
struct nvme_id_ctrl *id;
unsigned nn;
if (ctrl->state != NVME_CTRL_LIVE)
return;
if (nvme_identify_ctrl(ctrl, &id))
return;
nn = le32_to_cpu(id->nn);
if (ctrl->vs >= NVME_VS(1, 1, 0) &&
!(ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS)) {
if (!nvme_scan_ns_list(ctrl, nn))
goto done;
}
nvme_scan_ns_sequential(ctrl, nn);
done:
mutex_lock(&ctrl->namespaces_mutex);
list_sort(NULL, &ctrl->namespaces, ns_cmp);
mutex_unlock(&ctrl->namespaces_mutex);
kfree(id);
}
void nvme_queue_scan(struct nvme_ctrl *ctrl)
{
/*
* Do not queue new scan work when a controller is reset during
* removal.
*/
if (ctrl->state == NVME_CTRL_LIVE)
queue_work(nvme_wq, &ctrl->scan_work);
}
EXPORT_SYMBOL_GPL(nvme_queue_scan);
/*
* This function iterates the namespace list unlocked to allow recovery from
* controller failure. It is up to the caller to ensure the namespace list is
* not modified by scan work while this function is executing.
*/
void nvme_remove_namespaces(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns, *next;
/*
* The dead states indicates the controller was not gracefully
* disconnected. In that case, we won't be able to flush any data while
* removing the namespaces' disks; fail all the queues now to avoid
* potentially having to clean up the failed sync later.
*/
if (ctrl->state == NVME_CTRL_DEAD)
nvme_kill_queues(ctrl);
list_for_each_entry_safe(ns, next, &ctrl->namespaces, list)
nvme_ns_remove(ns);
}
EXPORT_SYMBOL_GPL(nvme_remove_namespaces);
static void nvme_async_event_work(struct work_struct *work)
{
struct nvme_ctrl *ctrl =
container_of(work, struct nvme_ctrl, async_event_work);
spin_lock_irq(&ctrl->lock);
while (ctrl->state == NVME_CTRL_LIVE && ctrl->event_limit > 0) {
int aer_idx = --ctrl->event_limit;
spin_unlock_irq(&ctrl->lock);
ctrl->ops->submit_async_event(ctrl, aer_idx);
spin_lock_irq(&ctrl->lock);
}
spin_unlock_irq(&ctrl->lock);
}
static bool nvme_ctrl_pp_status(struct nvme_ctrl *ctrl)
{
u32 csts;
if (ctrl->ops->reg_read32(ctrl, NVME_REG_CSTS, &csts))
return false;
if (csts == ~0)
return false;
return ((ctrl->ctrl_config & NVME_CC_ENABLE) && (csts & NVME_CSTS_PP));
}
static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl)
{
struct nvme_fw_slot_info_log *log;
log = kmalloc(sizeof(*log), GFP_KERNEL);
if (!log)
return;
if (nvme_get_log(ctrl, NVME_LOG_FW_SLOT, log, sizeof(*log)))
dev_warn(ctrl->device,
"Get FW SLOT INFO log error\n");
kfree(log);
}
static void nvme_fw_act_work(struct work_struct *work)
{
struct nvme_ctrl *ctrl = container_of(work,
struct nvme_ctrl, fw_act_work);
unsigned long fw_act_timeout;
if (ctrl->mtfa)
fw_act_timeout = jiffies +
msecs_to_jiffies(ctrl->mtfa * 100);
else
fw_act_timeout = jiffies +
msecs_to_jiffies(admin_timeout * 1000);
nvme_stop_queues(ctrl);
while (nvme_ctrl_pp_status(ctrl)) {
if (time_after(jiffies, fw_act_timeout)) {
dev_warn(ctrl->device,
"Fw activation timeout, reset controller\n");
nvme_reset_ctrl(ctrl);
break;
}
msleep(100);
}
if (ctrl->state != NVME_CTRL_LIVE)
return;
nvme_start_queues(ctrl);
/* read FW slot information to clear the AER */
nvme_get_fw_slot_info(ctrl);
}
void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
union nvme_result *res)
{
u32 result = le32_to_cpu(res->u32);
bool done = true;
switch (le16_to_cpu(status) >> 1) {
case NVME_SC_SUCCESS:
done = false;
/*FALLTHRU*/
case NVME_SC_ABORT_REQ:
++ctrl->event_limit;
if (ctrl->state == NVME_CTRL_LIVE)
queue_work(nvme_wq, &ctrl->async_event_work);
break;
default:
break;
}
if (done)
return;
switch (result & 0xff07) {
case NVME_AER_NOTICE_NS_CHANGED:
dev_info(ctrl->device, "rescanning\n");
nvme_queue_scan(ctrl);
break;
case NVME_AER_NOTICE_FW_ACT_STARTING:
queue_work(nvme_wq, &ctrl->fw_act_work);
break;
default:
dev_warn(ctrl->device, "async event result %08x\n", result);
}
}
EXPORT_SYMBOL_GPL(nvme_complete_async_event);
void nvme_queue_async_events(struct nvme_ctrl *ctrl)
{
ctrl->event_limit = NVME_NR_AEN_COMMANDS;
queue_work(nvme_wq, &ctrl->async_event_work);
}
EXPORT_SYMBOL_GPL(nvme_queue_async_events);
void nvme_stop_ctrl(struct nvme_ctrl *ctrl)
{
nvme_stop_keep_alive(ctrl);
flush_work(&ctrl->async_event_work);
flush_work(&ctrl->scan_work);
cancel_work_sync(&ctrl->fw_act_work);
}
EXPORT_SYMBOL_GPL(nvme_stop_ctrl);
void nvme_start_ctrl(struct nvme_ctrl *ctrl)
{
if (ctrl->kato)
nvme_start_keep_alive(ctrl);
if (ctrl->queue_count > 1) {
nvme_queue_scan(ctrl);
nvme_queue_async_events(ctrl);
nvme_start_queues(ctrl);
}
}
EXPORT_SYMBOL_GPL(nvme_start_ctrl);
void nvme_uninit_ctrl(struct nvme_ctrl *ctrl)
{
cdev_device_del(&ctrl->cdev, ctrl->device);
}
EXPORT_SYMBOL_GPL(nvme_uninit_ctrl);
static void nvme_free_ctrl(struct device *dev)
{
struct nvme_ctrl *ctrl =
container_of(dev, struct nvme_ctrl, ctrl_device);
ida_simple_remove(&nvme_instance_ida, ctrl->instance);
ida_destroy(&ctrl->ns_ida);
kfree(ctrl->effects);
ctrl->ops->free_ctrl(ctrl);
}
/*
* Initialize a NVMe controller structures. This needs to be called during
* earliest initialization so that we have the initialized structured around
* during probing.
*/
int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
const struct nvme_ctrl_ops *ops, unsigned long quirks)
{
int ret;
ctrl->state = NVME_CTRL_NEW;
spin_lock_init(&ctrl->lock);
INIT_LIST_HEAD(&ctrl->namespaces);
mutex_init(&ctrl->namespaces_mutex);
ctrl->dev = dev;
ctrl->ops = ops;
ctrl->quirks = quirks;
INIT_WORK(&ctrl->scan_work, nvme_scan_work);
INIT_WORK(&ctrl->async_event_work, nvme_async_event_work);
INIT_WORK(&ctrl->fw_act_work, nvme_fw_act_work);
INIT_WORK(&ctrl->delete_work, nvme_delete_ctrl_work);
ret = ida_simple_get(&nvme_instance_ida, 0, 0, GFP_KERNEL);
if (ret < 0)
goto out;
ctrl->instance = ret;
device_initialize(&ctrl->ctrl_device);
ctrl->device = &ctrl->ctrl_device;
ctrl->device->devt = MKDEV(MAJOR(nvme_chr_devt), ctrl->instance);
ctrl->device->class = nvme_class;
ctrl->device->parent = ctrl->dev;
ctrl->device->groups = nvme_dev_attr_groups;
ctrl->device->release = nvme_free_ctrl;
dev_set_drvdata(ctrl->device, ctrl);
ret = dev_set_name(ctrl->device, "nvme%d", ctrl->instance);
if (ret)
goto out_release_instance;
cdev_init(&ctrl->cdev, &nvme_dev_fops);
ctrl->cdev.owner = ops->module;
ret = cdev_device_add(&ctrl->cdev, ctrl->device);
if (ret)
goto out_free_name;
ida_init(&ctrl->ns_ida);
/*
* Initialize latency tolerance controls. The sysfs files won't
* be visible to userspace unless the device actually supports APST.
*/
ctrl->device->power.set_latency_tolerance = nvme_set_latency_tolerance;
dev_pm_qos_update_user_latency_tolerance(ctrl->device,
min(default_ps_max_latency_us, (unsigned long)S32_MAX));
return 0;
out_free_name:
kfree_const(dev->kobj.name);
out_release_instance:
ida_simple_remove(&nvme_instance_ida, ctrl->instance);
out:
return ret;
}
EXPORT_SYMBOL_GPL(nvme_init_ctrl);
/**
* nvme_kill_queues(): Ends all namespace queues
* @ctrl: the dead controller that needs to end
*
* Call this function when the driver determines it is unable to get the
* controller in a state capable of servicing IO.
*/
void nvme_kill_queues(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
mutex_lock(&ctrl->namespaces_mutex);
/* Forcibly unquiesce queues to avoid blocking dispatch */
if (ctrl->admin_q)
blk_mq_unquiesce_queue(ctrl->admin_q);
list_for_each_entry(ns, &ctrl->namespaces, list) {
/*
* Revalidating a dead namespace sets capacity to 0. This will
* end buffered writers dirtying pages that can't be synced.
*/
if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags))
continue;
revalidate_disk(ns->disk);
blk_set_queue_dying(ns->queue);
/* Forcibly unquiesce queues to avoid blocking dispatch */
blk_mq_unquiesce_queue(ns->queue);
}
mutex_unlock(&ctrl->namespaces_mutex);
}
EXPORT_SYMBOL_GPL(nvme_kill_queues);
void nvme_unfreeze(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
mutex_lock(&ctrl->namespaces_mutex);
list_for_each_entry(ns, &ctrl->namespaces, list)
blk_mq_unfreeze_queue(ns->queue);
mutex_unlock(&ctrl->namespaces_mutex);
}
EXPORT_SYMBOL_GPL(nvme_unfreeze);
void nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout)
{
struct nvme_ns *ns;
mutex_lock(&ctrl->namespaces_mutex);
list_for_each_entry(ns, &ctrl->namespaces, list) {
timeout = blk_mq_freeze_queue_wait_timeout(ns->queue, timeout);
if (timeout <= 0)
break;
}
mutex_unlock(&ctrl->namespaces_mutex);
}
EXPORT_SYMBOL_GPL(nvme_wait_freeze_timeout);
void nvme_wait_freeze(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
mutex_lock(&ctrl->namespaces_mutex);
list_for_each_entry(ns, &ctrl->namespaces, list)
blk_mq_freeze_queue_wait(ns->queue);
mutex_unlock(&ctrl->namespaces_mutex);
}
EXPORT_SYMBOL_GPL(nvme_wait_freeze);
void nvme_start_freeze(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
mutex_lock(&ctrl->namespaces_mutex);
list_for_each_entry(ns, &ctrl->namespaces, list)
blk_freeze_queue_start(ns->queue);
mutex_unlock(&ctrl->namespaces_mutex);
}
EXPORT_SYMBOL_GPL(nvme_start_freeze);
void nvme_stop_queues(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
mutex_lock(&ctrl->namespaces_mutex);
list_for_each_entry(ns, &ctrl->namespaces, list)
blk_mq_quiesce_queue(ns->queue);
mutex_unlock(&ctrl->namespaces_mutex);
}
EXPORT_SYMBOL_GPL(nvme_stop_queues);
void nvme_start_queues(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
mutex_lock(&ctrl->namespaces_mutex);
list_for_each_entry(ns, &ctrl->namespaces, list)
blk_mq_unquiesce_queue(ns->queue);
mutex_unlock(&ctrl->namespaces_mutex);
}
EXPORT_SYMBOL_GPL(nvme_start_queues);
int nvme_reinit_tagset(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set)
{
if (!ctrl->ops->reinit_request)
return 0;
return blk_mq_tagset_iter(set, set->driver_data,
ctrl->ops->reinit_request);
}
EXPORT_SYMBOL_GPL(nvme_reinit_tagset);
int __init nvme_core_init(void)
{
int result;
nvme_wq = alloc_workqueue("nvme-wq",
WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0);
if (!nvme_wq)
return -ENOMEM;
result = alloc_chrdev_region(&nvme_chr_devt, 0, NVME_MINORS, "nvme");
if (result < 0)
goto destroy_wq;
nvme_class = class_create(THIS_MODULE, "nvme");
if (IS_ERR(nvme_class)) {
result = PTR_ERR(nvme_class);
goto unregister_chrdev;
}
return 0;
unregister_chrdev:
unregister_chrdev_region(nvme_chr_devt, NVME_MINORS);
destroy_wq:
destroy_workqueue(nvme_wq);
return result;
}
void nvme_core_exit(void)
{
class_destroy(nvme_class);
unregister_chrdev_region(nvme_chr_devt, NVME_MINORS);
destroy_workqueue(nvme_wq);
}
MODULE_LICENSE("GPL");
MODULE_VERSION("1.0");
module_init(nvme_core_init);
module_exit(nvme_core_exit);
Reference in New Issue View Git Blame Copy Permalink