2019-02-18 11:36:29 +03:00
|
|
|
// SPDX-License-Identifier: GPL-2.0
|
2017-11-02 14:59:30 +03:00
|
|
|
/*
|
2018-05-14 09:48:54 +03:00
|
|
|
* Copyright (c) 2017-2018 Christoph Hellwig.
|
2017-11-02 14:59:30 +03:00
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/moduleparam.h>
|
2018-06-07 11:38:47 +03:00
|
|
|
#include <trace/events/block.h>
|
2017-11-02 14:59:30 +03:00
|
|
|
#include "nvme.h"
|
|
|
|
|
|
|
|
static bool multipath = true;
|
2018-04-26 23:24:29 +03:00
|
|
|
module_param(multipath, bool, 0444);
|
2017-11-02 14:59:30 +03:00
|
|
|
MODULE_PARM_DESC(multipath,
|
|
|
|
"turn on native support for multiple controllers per subsystem");
|
|
|
|
|
2019-07-31 21:00:26 +03:00
|
|
|
void nvme_mpath_unfreeze(struct nvme_subsystem *subsys)
|
|
|
|
{
|
|
|
|
struct nvme_ns_head *h;
|
|
|
|
|
|
|
|
lockdep_assert_held(&subsys->lock);
|
|
|
|
list_for_each_entry(h, &subsys->nsheads, entry)
|
|
|
|
if (h->disk)
|
|
|
|
blk_mq_unfreeze_queue(h->disk->queue);
|
|
|
|
}
|
|
|
|
|
|
|
|
void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys)
|
|
|
|
{
|
|
|
|
struct nvme_ns_head *h;
|
|
|
|
|
|
|
|
lockdep_assert_held(&subsys->lock);
|
|
|
|
list_for_each_entry(h, &subsys->nsheads, entry)
|
|
|
|
if (h->disk)
|
|
|
|
blk_mq_freeze_queue_wait(h->disk->queue);
|
|
|
|
}
|
|
|
|
|
|
|
|
void nvme_mpath_start_freeze(struct nvme_subsystem *subsys)
|
|
|
|
{
|
|
|
|
struct nvme_ns_head *h;
|
|
|
|
|
|
|
|
lockdep_assert_held(&subsys->lock);
|
|
|
|
list_for_each_entry(h, &subsys->nsheads, entry)
|
|
|
|
if (h->disk)
|
|
|
|
blk_freeze_queue_start(h->disk->queue);
|
|
|
|
}
|
|
|
|
|
2018-04-26 23:22:41 +03:00
|
|
|
/*
|
|
|
|
* If multipathing is enabled we need to always use the subsystem instance
|
|
|
|
* number for numbering our devices to avoid conflicts between subsystems that
|
|
|
|
* have multiple controllers and thus use the multipath-aware subsystem node
|
|
|
|
* and those that have a single controller and use the controller node
|
|
|
|
* directly.
|
|
|
|
*/
|
|
|
|
void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
|
|
|
|
struct nvme_ctrl *ctrl, int *flags)
|
|
|
|
{
|
|
|
|
if (!multipath) {
|
|
|
|
sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->head->instance);
|
|
|
|
} else if (ns->head->disk) {
|
|
|
|
sprintf(disk_name, "nvme%dc%dn%d", ctrl->subsys->instance,
|
2019-05-03 16:37:35 +03:00
|
|
|
ctrl->instance, ns->head->instance);
|
2018-04-26 23:22:41 +03:00
|
|
|
*flags = GENHD_FL_HIDDEN;
|
|
|
|
} else {
|
|
|
|
sprintf(disk_name, "nvme%dn%d", ctrl->subsys->instance,
|
|
|
|
ns->head->instance);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2017-11-02 14:59:30 +03:00
|
|
|
void nvme_failover_req(struct request *req)
|
|
|
|
{
|
|
|
|
struct nvme_ns *ns = req->q->queuedata;
|
2018-05-14 09:48:54 +03:00
|
|
|
u16 status = nvme_req(req)->status;
|
2017-11-02 14:59:30 +03:00
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
spin_lock_irqsave(&ns->head->requeue_lock, flags);
|
|
|
|
blk_steal_bios(&ns->head->requeue_list, req);
|
|
|
|
spin_unlock_irqrestore(&ns->head->requeue_lock, flags);
|
|
|
|
blk_mq_end_request(req, 0);
|
|
|
|
|
2018-05-14 09:48:54 +03:00
|
|
|
switch (status & 0x7ff) {
|
|
|
|
case NVME_SC_ANA_TRANSITION:
|
|
|
|
case NVME_SC_ANA_INACCESSIBLE:
|
|
|
|
case NVME_SC_ANA_PERSISTENT_LOSS:
|
|
|
|
/*
|
|
|
|
* If we got back an ANA error we know the controller is alive,
|
|
|
|
* but not ready to serve this namespaces. The spec suggests
|
|
|
|
* we should update our general state here, but due to the fact
|
|
|
|
* that the admin and I/O queues are not serialized that is
|
|
|
|
* fundamentally racy. So instead just clear the current path,
|
|
|
|
* mark the the path as pending and kick of a re-read of the ANA
|
|
|
|
* log page ASAP.
|
|
|
|
*/
|
|
|
|
nvme_mpath_clear_current_path(ns);
|
|
|
|
if (ns->ctrl->ana_log_buf) {
|
|
|
|
set_bit(NVME_NS_ANA_PENDING, &ns->flags);
|
|
|
|
queue_work(nvme_wq, &ns->ctrl->ana_work);
|
|
|
|
}
|
|
|
|
break;
|
nvme: call nvme_complete_rq when nvmf_check_ready fails for mpath I/O
When an io is rejected by nvmf_check_ready() due to validation of the
controller state, the nvmf_fail_nonready_command() will normally return
BLK_STS_RESOURCE to requeue and retry. However, if the controller is
dying or the I/O is marked for NVMe multipath, the I/O is failed so that
the controller can terminate or so that the io can be issued on a
different path. Unfortunately, as this reject point is before the
transport has accepted the command, blk-mq ends up completing the I/O
and never calls nvme_complete_rq(), which is where multipath may preserve
or re-route the I/O. The end result is, the device user ends up seeing an
EIO error.
Example: single path connectivity, controller is under load, and a reset
is induced. An I/O is received:
a) while the reset state has been set but the queues have yet to be
stopped; or
b) after queues are started (at end of reset) but before the reconnect
has completed.
The I/O finishes with an EIO status.
This patch makes the following changes:
- Adds the HOST_PATH_ERROR pathing status from TP4028
- Modifies the reject point such that it appears to queue successfully,
but actually completes the io with the new pathing status and calls
nvme_complete_rq().
- nvme_complete_rq() recognizes the new status, avoids resetting the
controller (likely was already done in order to get this new status),
and calls the multipather to clear the current path that errored.
This allows the next command (retry or new command) to select a new
path if there is one.
Signed-off-by: James Smart <jsmart2021@gmail.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2018-09-28 02:58:54 +03:00
|
|
|
case NVME_SC_HOST_PATH_ERROR:
|
|
|
|
/*
|
|
|
|
* Temporary transport disruption in talking to the controller.
|
|
|
|
* Try to send on a new path.
|
|
|
|
*/
|
|
|
|
nvme_mpath_clear_current_path(ns);
|
|
|
|
break;
|
2018-05-14 09:48:54 +03:00
|
|
|
default:
|
|
|
|
/*
|
|
|
|
* Reset the controller for any non-ANA error as we don't know
|
|
|
|
* what caused the error.
|
|
|
|
*/
|
|
|
|
nvme_reset_ctrl(ns->ctrl);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
2017-11-02 14:59:30 +03:00
|
|
|
kblockd_schedule_work(&ns->head->requeue_work);
|
|
|
|
}
|
|
|
|
|
|
|
|
void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
|
|
|
|
{
|
|
|
|
struct nvme_ns *ns;
|
|
|
|
|
2018-02-12 15:54:46 +03:00
|
|
|
down_read(&ctrl->namespaces_rwsem);
|
2017-11-02 14:59:30 +03:00
|
|
|
list_for_each_entry(ns, &ctrl->namespaces, list) {
|
|
|
|
if (ns->head->disk)
|
|
|
|
kblockd_schedule_work(&ns->head->requeue_work);
|
|
|
|
}
|
2018-02-12 15:54:46 +03:00
|
|
|
up_read(&ctrl->namespaces_rwsem);
|
2017-11-02 14:59:30 +03:00
|
|
|
}
|
|
|
|
|
2018-05-14 09:48:54 +03:00
|
|
|
static const char *nvme_ana_state_names[] = {
|
|
|
|
[0] = "invalid state",
|
|
|
|
[NVME_ANA_OPTIMIZED] = "optimized",
|
|
|
|
[NVME_ANA_NONOPTIMIZED] = "non-optimized",
|
|
|
|
[NVME_ANA_INACCESSIBLE] = "inaccessible",
|
|
|
|
[NVME_ANA_PERSISTENT_LOSS] = "persistent-loss",
|
|
|
|
[NVME_ANA_CHANGE] = "change",
|
|
|
|
};
|
|
|
|
|
2019-07-25 21:56:57 +03:00
|
|
|
bool nvme_mpath_clear_current_path(struct nvme_ns *ns)
|
2017-11-02 14:59:30 +03:00
|
|
|
{
|
2018-09-11 10:51:29 +03:00
|
|
|
struct nvme_ns_head *head = ns->head;
|
2019-07-25 21:56:57 +03:00
|
|
|
bool changed = false;
|
2018-09-11 10:51:29 +03:00
|
|
|
int node;
|
|
|
|
|
|
|
|
if (!head)
|
2019-07-25 21:56:57 +03:00
|
|
|
goto out;
|
2018-09-11 10:51:29 +03:00
|
|
|
|
|
|
|
for_each_node(node) {
|
2019-07-25 21:56:57 +03:00
|
|
|
if (ns == rcu_access_pointer(head->current_path[node])) {
|
2018-09-11 10:51:29 +03:00
|
|
|
rcu_assign_pointer(head->current_path[node], NULL);
|
2019-07-25 21:56:57 +03:00
|
|
|
changed = true;
|
|
|
|
}
|
2018-09-11 10:51:29 +03:00
|
|
|
}
|
2019-07-25 21:56:57 +03:00
|
|
|
out:
|
|
|
|
return changed;
|
|
|
|
}
|
|
|
|
|
|
|
|
void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl)
|
|
|
|
{
|
|
|
|
struct nvme_ns *ns;
|
|
|
|
|
|
|
|
mutex_lock(&ctrl->scan_lock);
|
|
|
|
list_for_each_entry(ns, &ctrl->namespaces, list)
|
|
|
|
if (nvme_mpath_clear_current_path(ns))
|
|
|
|
kblockd_schedule_work(&ns->head->requeue_work);
|
|
|
|
mutex_unlock(&ctrl->scan_lock);
|
2018-09-11 10:51:29 +03:00
|
|
|
}
|
|
|
|
|
2019-07-04 09:10:46 +03:00
|
|
|
static bool nvme_path_is_disabled(struct nvme_ns *ns)
|
|
|
|
{
|
|
|
|
return ns->ctrl->state != NVME_CTRL_LIVE ||
|
2019-07-04 09:10:47 +03:00
|
|
|
test_bit(NVME_NS_ANA_PENDING, &ns->flags) ||
|
|
|
|
test_bit(NVME_NS_REMOVING, &ns->flags);
|
2019-07-04 09:10:46 +03:00
|
|
|
}
|
|
|
|
|
2018-09-11 10:51:29 +03:00
|
|
|
static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head, int node)
|
|
|
|
{
|
|
|
|
int found_distance = INT_MAX, fallback_distance = INT_MAX, distance;
|
|
|
|
struct nvme_ns *found = NULL, *fallback = NULL, *ns;
|
2017-11-02 14:59:30 +03:00
|
|
|
|
|
|
|
list_for_each_entry_rcu(ns, &head->list, siblings) {
|
2019-07-04 09:10:46 +03:00
|
|
|
if (nvme_path_is_disabled(ns))
|
2018-05-14 09:48:54 +03:00
|
|
|
continue;
|
2018-09-11 10:51:29 +03:00
|
|
|
|
2019-02-18 13:43:26 +03:00
|
|
|
if (READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_NUMA)
|
|
|
|
distance = node_distance(node, ns->ctrl->numa_node);
|
|
|
|
else
|
|
|
|
distance = LOCAL_DISTANCE;
|
2018-09-11 10:51:29 +03:00
|
|
|
|
2018-05-14 09:48:54 +03:00
|
|
|
switch (ns->ana_state) {
|
|
|
|
case NVME_ANA_OPTIMIZED:
|
2018-09-11 10:51:29 +03:00
|
|
|
if (distance < found_distance) {
|
|
|
|
found_distance = distance;
|
|
|
|
found = ns;
|
|
|
|
}
|
|
|
|
break;
|
2018-05-14 09:48:54 +03:00
|
|
|
case NVME_ANA_NONOPTIMIZED:
|
2018-09-11 10:51:29 +03:00
|
|
|
if (distance < fallback_distance) {
|
|
|
|
fallback_distance = distance;
|
|
|
|
fallback = ns;
|
|
|
|
}
|
2018-05-14 09:48:54 +03:00
|
|
|
break;
|
|
|
|
default:
|
|
|
|
break;
|
2017-11-02 14:59:30 +03:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2018-09-11 10:51:29 +03:00
|
|
|
if (!found)
|
|
|
|
found = fallback;
|
|
|
|
if (found)
|
|
|
|
rcu_assign_pointer(head->current_path[node], found);
|
|
|
|
return found;
|
2018-05-14 09:48:54 +03:00
|
|
|
}
|
|
|
|
|
2019-02-18 13:43:26 +03:00
|
|
|
static struct nvme_ns *nvme_next_ns(struct nvme_ns_head *head,
|
|
|
|
struct nvme_ns *ns)
|
|
|
|
{
|
|
|
|
ns = list_next_or_null_rcu(&head->list, &ns->siblings, struct nvme_ns,
|
|
|
|
siblings);
|
|
|
|
if (ns)
|
|
|
|
return ns;
|
|
|
|
return list_first_or_null_rcu(&head->list, struct nvme_ns, siblings);
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head,
|
|
|
|
int node, struct nvme_ns *old)
|
|
|
|
{
|
|
|
|
struct nvme_ns *ns, *found, *fallback = NULL;
|
|
|
|
|
2019-07-04 09:10:46 +03:00
|
|
|
if (list_is_singular(&head->list)) {
|
|
|
|
if (nvme_path_is_disabled(old))
|
|
|
|
return NULL;
|
2019-02-18 13:43:26 +03:00
|
|
|
return old;
|
2019-07-04 09:10:46 +03:00
|
|
|
}
|
2019-02-18 13:43:26 +03:00
|
|
|
|
|
|
|
for (ns = nvme_next_ns(head, old);
|
|
|
|
ns != old;
|
|
|
|
ns = nvme_next_ns(head, ns)) {
|
2019-07-04 09:10:46 +03:00
|
|
|
if (nvme_path_is_disabled(ns))
|
2019-02-18 13:43:26 +03:00
|
|
|
continue;
|
|
|
|
|
|
|
|
if (ns->ana_state == NVME_ANA_OPTIMIZED) {
|
|
|
|
found = ns;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
if (ns->ana_state == NVME_ANA_NONOPTIMIZED)
|
|
|
|
fallback = ns;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!fallback)
|
|
|
|
return NULL;
|
|
|
|
found = fallback;
|
|
|
|
out:
|
|
|
|
rcu_assign_pointer(head->current_path[node], found);
|
|
|
|
return found;
|
|
|
|
}
|
|
|
|
|
2018-05-14 09:48:54 +03:00
|
|
|
static inline bool nvme_path_is_optimized(struct nvme_ns *ns)
|
|
|
|
{
|
|
|
|
return ns->ctrl->state == NVME_CTRL_LIVE &&
|
|
|
|
ns->ana_state == NVME_ANA_OPTIMIZED;
|
2017-11-02 14:59:30 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head)
|
|
|
|
{
|
2018-09-11 10:51:29 +03:00
|
|
|
int node = numa_node_id();
|
|
|
|
struct nvme_ns *ns;
|
2017-11-02 14:59:30 +03:00
|
|
|
|
2018-09-11 10:51:29 +03:00
|
|
|
ns = srcu_dereference(head->current_path[node], &head->srcu);
|
2019-02-18 13:43:26 +03:00
|
|
|
if (READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_RR && ns)
|
|
|
|
ns = nvme_round_robin_path(head, node, ns);
|
2018-05-14 09:48:54 +03:00
|
|
|
if (unlikely(!ns || !nvme_path_is_optimized(ns)))
|
2018-09-11 10:51:29 +03:00
|
|
|
ns = __nvme_find_path(head, node);
|
2017-11-02 14:59:30 +03:00
|
|
|
return ns;
|
|
|
|
}
|
|
|
|
|
2019-07-25 21:56:57 +03:00
|
|
|
static bool nvme_available_path(struct nvme_ns_head *head)
|
|
|
|
{
|
|
|
|
struct nvme_ns *ns;
|
|
|
|
|
|
|
|
list_for_each_entry_rcu(ns, &head->list, siblings) {
|
|
|
|
switch (ns->ctrl->state) {
|
|
|
|
case NVME_CTRL_LIVE:
|
|
|
|
case NVME_CTRL_RESETTING:
|
|
|
|
case NVME_CTRL_CONNECTING:
|
|
|
|
/* fallthru */
|
|
|
|
return true;
|
|
|
|
default:
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
2017-11-02 14:59:30 +03:00
|
|
|
static blk_qc_t nvme_ns_head_make_request(struct request_queue *q,
|
|
|
|
struct bio *bio)
|
|
|
|
{
|
|
|
|
struct nvme_ns_head *head = q->queuedata;
|
|
|
|
struct device *dev = disk_to_dev(head->disk);
|
|
|
|
struct nvme_ns *ns;
|
|
|
|
blk_qc_t ret = BLK_QC_T_NONE;
|
|
|
|
int srcu_idx;
|
|
|
|
|
2019-04-30 19:57:09 +03:00
|
|
|
/*
|
|
|
|
* The namespace might be going away and the bio might
|
|
|
|
* be moved to a different queue via blk_steal_bios(),
|
|
|
|
* so we need to use the bio_split pool from the original
|
|
|
|
* queue to allocate the bvecs from.
|
|
|
|
*/
|
|
|
|
blk_queue_split(q, &bio);
|
|
|
|
|
2017-11-02 14:59:30 +03:00
|
|
|
srcu_idx = srcu_read_lock(&head->srcu);
|
|
|
|
ns = nvme_find_path(head);
|
|
|
|
if (likely(ns)) {
|
|
|
|
bio->bi_disk = ns->disk;
|
|
|
|
bio->bi_opf |= REQ_NVME_MPATH;
|
2018-06-07 11:38:47 +03:00
|
|
|
trace_block_bio_remap(bio->bi_disk->queue, bio,
|
|
|
|
disk_devt(ns->head->disk),
|
|
|
|
bio->bi_iter.bi_sector);
|
2017-11-02 14:59:30 +03:00
|
|
|
ret = direct_make_request(bio);
|
2019-07-25 21:56:57 +03:00
|
|
|
} else if (nvme_available_path(head)) {
|
|
|
|
dev_warn_ratelimited(dev, "no usable path - requeuing I/O\n");
|
2017-11-02 14:59:30 +03:00
|
|
|
|
|
|
|
spin_lock_irq(&head->requeue_lock);
|
|
|
|
bio_list_add(&head->requeue_list, bio);
|
|
|
|
spin_unlock_irq(&head->requeue_lock);
|
|
|
|
} else {
|
2019-07-25 21:56:57 +03:00
|
|
|
dev_warn_ratelimited(dev, "no available path - failing I/O\n");
|
2017-11-02 14:59:30 +03:00
|
|
|
|
|
|
|
bio->bi_status = BLK_STS_IOERR;
|
|
|
|
bio_endio(bio);
|
|
|
|
}
|
|
|
|
|
|
|
|
srcu_read_unlock(&head->srcu, srcu_idx);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void nvme_requeue_work(struct work_struct *work)
|
|
|
|
{
|
|
|
|
struct nvme_ns_head *head =
|
|
|
|
container_of(work, struct nvme_ns_head, requeue_work);
|
|
|
|
struct bio *bio, *next;
|
|
|
|
|
|
|
|
spin_lock_irq(&head->requeue_lock);
|
|
|
|
next = bio_list_get(&head->requeue_list);
|
|
|
|
spin_unlock_irq(&head->requeue_lock);
|
|
|
|
|
|
|
|
while ((bio = next) != NULL) {
|
|
|
|
next = bio->bi_next;
|
|
|
|
bio->bi_next = NULL;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Reset disk to the mpath node and resubmit to select a new
|
|
|
|
* path.
|
|
|
|
*/
|
|
|
|
bio->bi_disk = head->disk;
|
|
|
|
generic_make_request(bio);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
|
|
|
|
{
|
|
|
|
struct request_queue *q;
|
|
|
|
bool vwc = false;
|
|
|
|
|
2018-05-14 09:48:54 +03:00
|
|
|
mutex_init(&head->lock);
|
2017-11-02 14:59:30 +03:00
|
|
|
bio_list_init(&head->requeue_list);
|
|
|
|
spin_lock_init(&head->requeue_lock);
|
|
|
|
INIT_WORK(&head->requeue_work, nvme_requeue_work);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Add a multipath node if the subsystems supports multiple controllers.
|
|
|
|
* We also do this for private namespaces as the namespace sharing data could
|
|
|
|
* change after a rescan.
|
|
|
|
*/
|
|
|
|
if (!(ctrl->subsys->cmic & (1 << 1)) || !multipath)
|
|
|
|
return 0;
|
|
|
|
|
2018-11-16 11:22:29 +03:00
|
|
|
q = blk_alloc_queue_node(GFP_KERNEL, ctrl->numa_node);
|
2017-11-02 14:59:30 +03:00
|
|
|
if (!q)
|
|
|
|
goto out;
|
|
|
|
q->queuedata = head;
|
|
|
|
blk_queue_make_request(q, nvme_ns_head_make_request);
|
2018-03-08 04:10:10 +03:00
|
|
|
blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
|
2017-11-02 14:59:30 +03:00
|
|
|
/* set to a default value for 512 until disk is validated */
|
|
|
|
blk_queue_logical_block_size(q, 512);
|
2018-11-02 21:22:13 +03:00
|
|
|
blk_set_stacking_limits(&q->limits);
|
2017-11-02 14:59:30 +03:00
|
|
|
|
|
|
|
/* we need to propagate up the VMC settings */
|
|
|
|
if (ctrl->vwc & NVME_CTRL_VWC_PRESENT)
|
|
|
|
vwc = true;
|
|
|
|
blk_queue_write_cache(q, vwc, vwc);
|
|
|
|
|
|
|
|
head->disk = alloc_disk(0);
|
|
|
|
if (!head->disk)
|
|
|
|
goto out_cleanup_queue;
|
|
|
|
head->disk->fops = &nvme_ns_head_ops;
|
|
|
|
head->disk->private_data = head;
|
|
|
|
head->disk->queue = q;
|
|
|
|
head->disk->flags = GENHD_FL_EXT_DEVT;
|
|
|
|
sprintf(head->disk->disk_name, "nvme%dn%d",
|
|
|
|
ctrl->subsys->instance, head->instance);
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
out_cleanup_queue:
|
|
|
|
blk_cleanup_queue(q);
|
|
|
|
out:
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
|
2018-05-14 09:48:54 +03:00
|
|
|
static void nvme_mpath_set_live(struct nvme_ns *ns)
|
2017-11-02 14:59:30 +03:00
|
|
|
{
|
2018-05-14 09:48:54 +03:00
|
|
|
struct nvme_ns_head *head = ns->head;
|
|
|
|
|
|
|
|
lockdep_assert_held(&ns->head->lock);
|
|
|
|
|
2017-11-02 14:59:30 +03:00
|
|
|
if (!head->disk)
|
|
|
|
return;
|
2018-02-28 10:06:04 +03:00
|
|
|
|
2018-09-28 09:17:20 +03:00
|
|
|
if (!(head->disk->flags & GENHD_FL_UP))
|
|
|
|
device_add_disk(&head->subsys->dev, head->disk,
|
|
|
|
nvme_ns_id_attr_groups);
|
2018-05-14 09:48:54 +03:00
|
|
|
|
2018-10-05 18:49:37 +03:00
|
|
|
if (nvme_path_is_optimized(ns)) {
|
|
|
|
int node, srcu_idx;
|
|
|
|
|
|
|
|
srcu_idx = srcu_read_lock(&head->srcu);
|
|
|
|
for_each_node(node)
|
|
|
|
__nvme_find_path(head, node);
|
|
|
|
srcu_read_unlock(&head->srcu, srcu_idx);
|
|
|
|
}
|
|
|
|
|
2019-08-12 23:00:36 +03:00
|
|
|
synchronize_srcu(&ns->head->srcu);
|
2018-05-14 09:48:54 +03:00
|
|
|
kblockd_schedule_work(&ns->head->requeue_work);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int nvme_parse_ana_log(struct nvme_ctrl *ctrl, void *data,
|
|
|
|
int (*cb)(struct nvme_ctrl *ctrl, struct nvme_ana_group_desc *,
|
|
|
|
void *))
|
|
|
|
{
|
|
|
|
void *base = ctrl->ana_log_buf;
|
|
|
|
size_t offset = sizeof(struct nvme_ana_rsp_hdr);
|
|
|
|
int error, i;
|
|
|
|
|
|
|
|
lockdep_assert_held(&ctrl->ana_lock);
|
|
|
|
|
|
|
|
for (i = 0; i < le16_to_cpu(ctrl->ana_log_buf->ngrps); i++) {
|
|
|
|
struct nvme_ana_group_desc *desc = base + offset;
|
|
|
|
u32 nr_nsids = le32_to_cpu(desc->nnsids);
|
|
|
|
size_t nsid_buf_size = nr_nsids * sizeof(__le32);
|
|
|
|
|
|
|
|
if (WARN_ON_ONCE(desc->grpid == 0))
|
|
|
|
return -EINVAL;
|
|
|
|
if (WARN_ON_ONCE(le32_to_cpu(desc->grpid) > ctrl->anagrpmax))
|
|
|
|
return -EINVAL;
|
|
|
|
if (WARN_ON_ONCE(desc->state == 0))
|
|
|
|
return -EINVAL;
|
|
|
|
if (WARN_ON_ONCE(desc->state > NVME_ANA_CHANGE))
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
offset += sizeof(*desc);
|
|
|
|
if (WARN_ON_ONCE(offset > ctrl->ana_log_size - nsid_buf_size))
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
error = cb(ctrl, desc, data);
|
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
|
|
|
|
offset += nsid_buf_size;
|
|
|
|
if (WARN_ON_ONCE(offset > ctrl->ana_log_size - sizeof(*desc)))
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline bool nvme_state_is_live(enum nvme_ana_state state)
|
|
|
|
{
|
|
|
|
return state == NVME_ANA_OPTIMIZED || state == NVME_ANA_NONOPTIMIZED;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc,
|
|
|
|
struct nvme_ns *ns)
|
|
|
|
{
|
|
|
|
mutex_lock(&ns->head->lock);
|
|
|
|
ns->ana_grpid = le32_to_cpu(desc->grpid);
|
|
|
|
ns->ana_state = desc->state;
|
|
|
|
clear_bit(NVME_NS_ANA_PENDING, &ns->flags);
|
|
|
|
|
2019-03-27 11:52:56 +03:00
|
|
|
if (nvme_state_is_live(ns->ana_state))
|
2018-05-14 09:48:54 +03:00
|
|
|
nvme_mpath_set_live(ns);
|
|
|
|
mutex_unlock(&ns->head->lock);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
|
|
|
|
struct nvme_ana_group_desc *desc, void *data)
|
|
|
|
{
|
|
|
|
u32 nr_nsids = le32_to_cpu(desc->nnsids), n = 0;
|
|
|
|
unsigned *nr_change_groups = data;
|
|
|
|
struct nvme_ns *ns;
|
|
|
|
|
2019-04-29 06:24:42 +03:00
|
|
|
dev_dbg(ctrl->device, "ANA group %d: %s.\n",
|
2018-05-14 09:48:54 +03:00
|
|
|
le32_to_cpu(desc->grpid),
|
|
|
|
nvme_ana_state_names[desc->state]);
|
|
|
|
|
|
|
|
if (desc->state == NVME_ANA_CHANGE)
|
|
|
|
(*nr_change_groups)++;
|
|
|
|
|
|
|
|
if (!nr_nsids)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
down_write(&ctrl->namespaces_rwsem);
|
|
|
|
list_for_each_entry(ns, &ctrl->namespaces, list) {
|
nvme-multipath: fix ana log nsid lookup when nsid is not found
ANA log parsing invokes nvme_update_ana_state() per ANA group desc.
This updates the state of namespaces with nsids in desc->nsids[].
Both ctrl->namespaces list and desc->nsids[] array are sorted by nsid.
Hence nvme_update_ana_state() performs a single walk over ctrl->namespaces:
- if current namespace matches the current desc->nsids[n],
this namespace is updated, and n is incremented.
- the process stops when it encounters the end of either
ctrl->namespaces end or desc->nsids[]
In case desc->nsids[n] does not match any of ctrl->namespaces,
the remaining nsids following desc->nsids[n] will not be updated.
Such situation was considered abnormal and generated WARN_ON_ONCE.
However ANA log MAY contain nsids not (yet) found in ctrl->namespaces.
For example, lets consider the following scenario:
- nvme0 exposes namespaces with nsids = [2, 3] to the host
- a new namespace nsid = 1 is added dynamically
- also, a ANA topology change is triggered
- NS_CHANGED aen is generated and triggers scan_work
- before scan_work discovers nsid=1 and creates a namespace, a NOTICE_ANA
aen was issues and ana_work receives ANA log with nsids=[1, 2, 3]
Result: ana_work fails to update ANA state on existing namespaces [2, 3]
Solution:
Change the way nvme_update_ana_state() namespace list walk
checks the current namespace against desc->nsids[n] as follows:
a) ns->head->ns_id < desc->nsids[n]: keep walking ctrl->namespaces.
b) ns->head->ns_id == desc->nsids[n]: match, update the namespace
c) ns->head->ns_id >= desc->nsids[n]: skip to desc->nsids[n+1]
This enables correct operation in the scenario described above.
This also allows ANA log to contain nsids currently invisible
to the host, i.e. inactive nsids.
Signed-off-by: Anton Eidelman <anton@lightbitslabs.com>
Reviewed-by: James Smart <james.smart@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
2019-08-16 23:00:10 +03:00
|
|
|
unsigned nsid = le32_to_cpu(desc->nsids[n]);
|
|
|
|
|
|
|
|
if (ns->head->ns_id < nsid)
|
2018-05-14 09:48:54 +03:00
|
|
|
continue;
|
nvme-multipath: fix ana log nsid lookup when nsid is not found
ANA log parsing invokes nvme_update_ana_state() per ANA group desc.
This updates the state of namespaces with nsids in desc->nsids[].
Both ctrl->namespaces list and desc->nsids[] array are sorted by nsid.
Hence nvme_update_ana_state() performs a single walk over ctrl->namespaces:
- if current namespace matches the current desc->nsids[n],
this namespace is updated, and n is incremented.
- the process stops when it encounters the end of either
ctrl->namespaces end or desc->nsids[]
In case desc->nsids[n] does not match any of ctrl->namespaces,
the remaining nsids following desc->nsids[n] will not be updated.
Such situation was considered abnormal and generated WARN_ON_ONCE.
However ANA log MAY contain nsids not (yet) found in ctrl->namespaces.
For example, lets consider the following scenario:
- nvme0 exposes namespaces with nsids = [2, 3] to the host
- a new namespace nsid = 1 is added dynamically
- also, a ANA topology change is triggered
- NS_CHANGED aen is generated and triggers scan_work
- before scan_work discovers nsid=1 and creates a namespace, a NOTICE_ANA
aen was issues and ana_work receives ANA log with nsids=[1, 2, 3]
Result: ana_work fails to update ANA state on existing namespaces [2, 3]
Solution:
Change the way nvme_update_ana_state() namespace list walk
checks the current namespace against desc->nsids[n] as follows:
a) ns->head->ns_id < desc->nsids[n]: keep walking ctrl->namespaces.
b) ns->head->ns_id == desc->nsids[n]: match, update the namespace
c) ns->head->ns_id >= desc->nsids[n]: skip to desc->nsids[n+1]
This enables correct operation in the scenario described above.
This also allows ANA log to contain nsids currently invisible
to the host, i.e. inactive nsids.
Signed-off-by: Anton Eidelman <anton@lightbitslabs.com>
Reviewed-by: James Smart <james.smart@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
2019-08-16 23:00:10 +03:00
|
|
|
if (ns->head->ns_id == nsid)
|
|
|
|
nvme_update_ns_ana_state(desc, ns);
|
2018-05-14 09:48:54 +03:00
|
|
|
if (++n == nr_nsids)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
up_write(&ctrl->namespaces_rwsem);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int nvme_read_ana_log(struct nvme_ctrl *ctrl, bool groups_only)
|
|
|
|
{
|
|
|
|
u32 nr_change_groups = 0;
|
|
|
|
int error;
|
|
|
|
|
|
|
|
mutex_lock(&ctrl->ana_lock);
|
|
|
|
error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_ANA,
|
|
|
|
groups_only ? NVME_ANA_LOG_RGO : 0,
|
|
|
|
ctrl->ana_log_buf, ctrl->ana_log_size, 0);
|
|
|
|
if (error) {
|
|
|
|
dev_warn(ctrl->device, "Failed to get ANA log: %d\n", error);
|
|
|
|
goto out_unlock;
|
|
|
|
}
|
|
|
|
|
|
|
|
error = nvme_parse_ana_log(ctrl, &nr_change_groups,
|
|
|
|
nvme_update_ana_state);
|
|
|
|
if (error)
|
|
|
|
goto out_unlock;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* In theory we should have an ANATT timer per group as they might enter
|
|
|
|
* the change state at different times. But that is a lot of overhead
|
|
|
|
* just to protect against a target that keeps entering new changes
|
|
|
|
* states while never finishing previous ones. But we'll still
|
|
|
|
* eventually time out once all groups are in change state, so this
|
|
|
|
* isn't a big deal.
|
|
|
|
*
|
|
|
|
* We also double the ANATT value to provide some slack for transports
|
|
|
|
* or AEN processing overhead.
|
|
|
|
*/
|
|
|
|
if (nr_change_groups)
|
|
|
|
mod_timer(&ctrl->anatt_timer, ctrl->anatt * HZ * 2 + jiffies);
|
|
|
|
else
|
|
|
|
del_timer_sync(&ctrl->anatt_timer);
|
|
|
|
out_unlock:
|
|
|
|
mutex_unlock(&ctrl->ana_lock);
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void nvme_ana_work(struct work_struct *work)
|
|
|
|
{
|
|
|
|
struct nvme_ctrl *ctrl = container_of(work, struct nvme_ctrl, ana_work);
|
|
|
|
|
|
|
|
nvme_read_ana_log(ctrl, false);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void nvme_anatt_timeout(struct timer_list *t)
|
|
|
|
{
|
|
|
|
struct nvme_ctrl *ctrl = from_timer(ctrl, t, anatt_timer);
|
|
|
|
|
|
|
|
dev_info(ctrl->device, "ANATT timeout, resetting controller.\n");
|
|
|
|
nvme_reset_ctrl(ctrl);
|
|
|
|
}
|
|
|
|
|
|
|
|
void nvme_mpath_stop(struct nvme_ctrl *ctrl)
|
|
|
|
{
|
|
|
|
if (!nvme_ctrl_use_ana(ctrl))
|
|
|
|
return;
|
|
|
|
del_timer_sync(&ctrl->anatt_timer);
|
|
|
|
cancel_work_sync(&ctrl->ana_work);
|
|
|
|
}
|
|
|
|
|
2019-02-18 13:43:26 +03:00
|
|
|
#define SUBSYS_ATTR_RW(_name, _mode, _show, _store) \
|
|
|
|
struct device_attribute subsys_attr_##_name = \
|
|
|
|
__ATTR(_name, _mode, _show, _store)
|
|
|
|
|
|
|
|
static const char *nvme_iopolicy_names[] = {
|
|
|
|
[NVME_IOPOLICY_NUMA] = "numa",
|
|
|
|
[NVME_IOPOLICY_RR] = "round-robin",
|
|
|
|
};
|
|
|
|
|
|
|
|
static ssize_t nvme_subsys_iopolicy_show(struct device *dev,
|
|
|
|
struct device_attribute *attr, char *buf)
|
|
|
|
{
|
|
|
|
struct nvme_subsystem *subsys =
|
|
|
|
container_of(dev, struct nvme_subsystem, dev);
|
|
|
|
|
|
|
|
return sprintf(buf, "%s\n",
|
|
|
|
nvme_iopolicy_names[READ_ONCE(subsys->iopolicy)]);
|
|
|
|
}
|
|
|
|
|
|
|
|
static ssize_t nvme_subsys_iopolicy_store(struct device *dev,
|
|
|
|
struct device_attribute *attr, const char *buf, size_t count)
|
|
|
|
{
|
|
|
|
struct nvme_subsystem *subsys =
|
|
|
|
container_of(dev, struct nvme_subsystem, dev);
|
|
|
|
int i;
|
|
|
|
|
|
|
|
for (i = 0; i < ARRAY_SIZE(nvme_iopolicy_names); i++) {
|
|
|
|
if (sysfs_streq(buf, nvme_iopolicy_names[i])) {
|
|
|
|
WRITE_ONCE(subsys->iopolicy, i);
|
|
|
|
return count;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
SUBSYS_ATTR_RW(iopolicy, S_IRUGO | S_IWUSR,
|
|
|
|
nvme_subsys_iopolicy_show, nvme_subsys_iopolicy_store);
|
|
|
|
|
2018-05-14 09:48:54 +03:00
|
|
|
static ssize_t ana_grpid_show(struct device *dev, struct device_attribute *attr,
|
|
|
|
char *buf)
|
|
|
|
{
|
|
|
|
return sprintf(buf, "%d\n", nvme_get_ns_from_dev(dev)->ana_grpid);
|
|
|
|
}
|
|
|
|
DEVICE_ATTR_RO(ana_grpid);
|
|
|
|
|
|
|
|
static ssize_t ana_state_show(struct device *dev, struct device_attribute *attr,
|
|
|
|
char *buf)
|
|
|
|
{
|
|
|
|
struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
|
|
|
|
|
|
|
|
return sprintf(buf, "%s\n", nvme_ana_state_names[ns->ana_state]);
|
|
|
|
}
|
|
|
|
DEVICE_ATTR_RO(ana_state);
|
|
|
|
|
|
|
|
static int nvme_set_ns_ana_state(struct nvme_ctrl *ctrl,
|
|
|
|
struct nvme_ana_group_desc *desc, void *data)
|
|
|
|
{
|
|
|
|
struct nvme_ns *ns = data;
|
|
|
|
|
|
|
|
if (ns->ana_grpid == le32_to_cpu(desc->grpid)) {
|
|
|
|
nvme_update_ns_ana_state(desc, ns);
|
|
|
|
return -ENXIO; /* just break out of the loop */
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id)
|
|
|
|
{
|
|
|
|
if (nvme_ctrl_use_ana(ns->ctrl)) {
|
|
|
|
mutex_lock(&ns->ctrl->ana_lock);
|
|
|
|
ns->ana_grpid = le32_to_cpu(id->anagrpid);
|
|
|
|
nvme_parse_ana_log(ns->ctrl, ns, nvme_set_ns_ana_state);
|
|
|
|
mutex_unlock(&ns->ctrl->ana_lock);
|
|
|
|
} else {
|
|
|
|
mutex_lock(&ns->head->lock);
|
|
|
|
ns->ana_state = NVME_ANA_OPTIMIZED;
|
|
|
|
nvme_mpath_set_live(ns);
|
|
|
|
mutex_unlock(&ns->head->lock);
|
2018-02-28 10:06:04 +03:00
|
|
|
}
|
2017-11-02 14:59:30 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
void nvme_mpath_remove_disk(struct nvme_ns_head *head)
|
|
|
|
{
|
|
|
|
if (!head->disk)
|
|
|
|
return;
|
2018-09-28 09:17:20 +03:00
|
|
|
if (head->disk->flags & GENHD_FL_UP)
|
2018-05-14 09:48:54 +03:00
|
|
|
del_gendisk(head->disk);
|
2017-11-02 14:59:30 +03:00
|
|
|
blk_set_queue_dying(head->disk->queue);
|
|
|
|
/* make sure all pending bios are cleaned up */
|
|
|
|
kblockd_schedule_work(&head->requeue_work);
|
|
|
|
flush_work(&head->requeue_work);
|
|
|
|
blk_cleanup_queue(head->disk->queue);
|
|
|
|
put_disk(head->disk);
|
|
|
|
}
|
2018-05-14 09:48:54 +03:00
|
|
|
|
|
|
|
int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
|
|
|
|
{
|
|
|
|
int error;
|
|
|
|
|
2019-07-23 08:41:20 +03:00
|
|
|
/* check if multipath is enabled and we have the capability */
|
|
|
|
if (!multipath || !ctrl->subsys || !(ctrl->subsys->cmic & (1 << 3)))
|
2018-05-14 09:48:54 +03:00
|
|
|
return 0;
|
|
|
|
|
|
|
|
ctrl->anacap = id->anacap;
|
|
|
|
ctrl->anatt = id->anatt;
|
|
|
|
ctrl->nanagrpid = le32_to_cpu(id->nanagrpid);
|
|
|
|
ctrl->anagrpmax = le32_to_cpu(id->anagrpmax);
|
|
|
|
|
|
|
|
mutex_init(&ctrl->ana_lock);
|
|
|
|
timer_setup(&ctrl->anatt_timer, nvme_anatt_timeout, 0);
|
|
|
|
ctrl->ana_log_size = sizeof(struct nvme_ana_rsp_hdr) +
|
|
|
|
ctrl->nanagrpid * sizeof(struct nvme_ana_group_desc);
|
2019-01-09 11:45:15 +03:00
|
|
|
ctrl->ana_log_size += ctrl->max_namespaces * sizeof(__le32);
|
2018-05-14 09:48:54 +03:00
|
|
|
|
|
|
|
if (ctrl->ana_log_size > ctrl->max_hw_sectors << SECTOR_SHIFT) {
|
|
|
|
dev_err(ctrl->device,
|
|
|
|
"ANA log page size (%zd) larger than MDTS (%d).\n",
|
|
|
|
ctrl->ana_log_size,
|
|
|
|
ctrl->max_hw_sectors << SECTOR_SHIFT);
|
|
|
|
dev_err(ctrl->device, "disabling ANA support.\n");
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
INIT_WORK(&ctrl->ana_work, nvme_ana_work);
|
|
|
|
ctrl->ana_log_buf = kmalloc(ctrl->ana_log_size, GFP_KERNEL);
|
2018-09-25 22:29:15 +03:00
|
|
|
if (!ctrl->ana_log_buf) {
|
|
|
|
error = -ENOMEM;
|
2018-05-14 09:48:54 +03:00
|
|
|
goto out;
|
2018-09-25 22:29:15 +03:00
|
|
|
}
|
2018-05-14 09:48:54 +03:00
|
|
|
|
2019-10-18 21:32:50 +03:00
|
|
|
error = nvme_read_ana_log(ctrl, false);
|
2018-05-14 09:48:54 +03:00
|
|
|
if (error)
|
|
|
|
goto out_free_ana_log_buf;
|
|
|
|
return 0;
|
|
|
|
out_free_ana_log_buf:
|
|
|
|
kfree(ctrl->ana_log_buf);
|
2019-01-08 14:46:58 +03:00
|
|
|
ctrl->ana_log_buf = NULL;
|
2018-05-14 09:48:54 +03:00
|
|
|
out:
|
2018-09-25 22:29:15 +03:00
|
|
|
return error;
|
2018-05-14 09:48:54 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
void nvme_mpath_uninit(struct nvme_ctrl *ctrl)
|
|
|
|
{
|
|
|
|
kfree(ctrl->ana_log_buf);
|
2019-01-08 14:46:58 +03:00
|
|
|
ctrl->ana_log_buf = NULL;
|
2018-05-14 09:48:54 +03:00
|
|
|
}
|
|
|
|
|