Skip to content

Commit

Permalink
Merge tag 'block-6.7-2023-12-08' of git://git.kernel.dk/linux
Browse files Browse the repository at this point in the history 
Pull block fixes from Jens Axboe:
 "Nothing major in here, just miscellanous fixes for MD and NVMe:

   - NVMe pull request via Keith:
      - Proper nvme ctrl state setting (Keith)
      - Passthrough command optimization (Keith)
      - Spectre fix (Nitesh)
      - Kconfig clarifications (Shin'ichiro)
      - Frozen state deadlock fix (Bitao)
      - Power setting quirk (Georg)

   - MD pull requests via Song:
      - 6.7 regresisons with recovery/sync (Yu)
      - Reshape fix (David)"

* tag 'block-6.7-2023-12-08' of git://git.kernel.dk/linux:
  md: split MD_RECOVERY_NEEDED out of mddev_resume
  nvme-pci: Add sleep quirk for Kingston drives
  md: fix stopping sync thread
  md: don't leave 'MD_RECOVERY_FROZEN' in error path of md_set_readonly()
  md: fix missing flush of sync_work
  nvme: fix deadlock between reset and scan
  nvme: prevent potential spectre v1 gadget
  nvme: improve NVME_HOST_AUTH and NVME_TARGET_AUTH config descriptions
  nvme-ioctl: move capable() admin check to the end
  nvme: ensure reset state check ordering
  nvme: introduce helper function to get ctrl state
  md/raid6: use valid sector values to determine if an I/O should wait on the reshape
  • Loading branch information
@torvalds
torvalds committed Dec 8, 2023
2 parents 689659c + c6d3ab9 commit d71369d
Show file tree
Hide file tree
Showing 12 changed files with 197 additions and 134 deletions.
144 changes: 76 additions & 68 deletions drivers/md/md.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -490,7 +490,7 @@ int mddev_suspend(struct mddev *mddev, bool interruptible)
}
EXPORT_SYMBOL_GPL(mddev_suspend);

void mddev_resume(struct mddev *mddev)
static void __mddev_resume(struct mddev *mddev, bool recovery_needed)
{
lockdep_assert_not_held(&mddev->reconfig_mutex);

Expand All @@ -507,12 +507,18 @@ void mddev_resume(struct mddev *mddev)
percpu_ref_resurrect(&mddev->active_io);
wake_up(&mddev->sb_wait);

set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
if (recovery_needed)
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */

mutex_unlock(&mddev->suspend_mutex);
}

void mddev_resume(struct mddev *mddev)
{
return __mddev_resume(mddev, true);
}
EXPORT_SYMBOL_GPL(mddev_resume);

/*
Expand Down Expand Up @@ -4840,59 +4846,72 @@ action_show(struct mddev *mddev, char *page)
return sprintf(page, "%s\n", type);
}

static void stop_sync_thread(struct mddev *mddev)
/**
* stop_sync_thread() - wait for sync_thread to stop if it's running.
* @mddev: the array.
* @locked: if set, reconfig_mutex will still be held after this function
* return; if not set, reconfig_mutex will be released after this
* function return.
* @check_seq: if set, only wait for curent running sync_thread to stop, noted
* that new sync_thread can still start.
*/
static void stop_sync_thread(struct mddev *mddev, bool locked, bool check_seq)
{
if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
return;
int sync_seq;

if (mddev_lock(mddev))
return;
if (check_seq)
sync_seq = atomic_read(&mddev->sync_seq);

/*
* Check again in case MD_RECOVERY_RUNNING is cleared before lock is
* held.
*/
if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
mddev_unlock(mddev);
if (!locked)
mddev_unlock(mddev);
return;
}

if (work_pending(&mddev->del_work))
flush_workqueue(md_misc_wq);
mddev_unlock(mddev);

set_bit(MD_RECOVERY_INTR, &mddev->recovery);
/*
* Thread might be blocked waiting for metadata update which will now
* never happen
*/
md_wakeup_thread_directly(mddev->sync_thread);
if (work_pending(&mddev->sync_work))
flush_work(&mddev->sync_work);

mddev_unlock(mddev);
wait_event(resync_wait,
!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
(check_seq && sync_seq != atomic_read(&mddev->sync_seq)));

if (locked)
mddev_lock_nointr(mddev);
}

static void idle_sync_thread(struct mddev *mddev)
{
int sync_seq = atomic_read(&mddev->sync_seq);

mutex_lock(&mddev->sync_mutex);
clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
stop_sync_thread(mddev);

wait_event(resync_wait, sync_seq != atomic_read(&mddev->sync_seq) ||
!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery));
if (mddev_lock(mddev)) {
mutex_unlock(&mddev->sync_mutex);
return;
}

stop_sync_thread(mddev, false, true);
mutex_unlock(&mddev->sync_mutex);
}

static void frozen_sync_thread(struct mddev *mddev)
{
mutex_lock(&mddev->sync_mutex);
set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
stop_sync_thread(mddev);

wait_event(resync_wait, mddev->sync_thread == NULL &&
!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery));
if (mddev_lock(mddev)) {
mutex_unlock(&mddev->sync_mutex);
return;
}

stop_sync_thread(mddev, false, false);
mutex_unlock(&mddev->sync_mutex);
}

Expand Down Expand Up @@ -6264,14 +6283,7 @@ static void md_clean(struct mddev *mddev)

static void __md_stop_writes(struct mddev *mddev)
{
set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
if (work_pending(&mddev->del_work))
flush_workqueue(md_misc_wq);
if (mddev->sync_thread) {
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
md_reap_sync_thread(mddev);
}

stop_sync_thread(mddev, true, false);
del_timer_sync(&mddev->safemode_timer);

if (mddev->pers && mddev->pers->quiesce) {
Expand Down Expand Up @@ -6355,25 +6367,16 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
int err = 0;
int did_freeze = 0;

if (mddev->external && test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags))
return -EBUSY;

if (!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)) {
did_freeze = 1;
set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
md_wakeup_thread(mddev->thread);
}
if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
set_bit(MD_RECOVERY_INTR, &mddev->recovery);

/*
* Thread might be blocked waiting for metadata update which will now
* never happen
*/
md_wakeup_thread_directly(mddev->sync_thread);

if (mddev->external && test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags))
return -EBUSY;
mddev_unlock(mddev);
wait_event(resync_wait, !test_bit(MD_RECOVERY_RUNNING,
&mddev->recovery));
stop_sync_thread(mddev, false, false);
wait_event(mddev->sb_wait,
!test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
mddev_lock_nointr(mddev);
Expand All @@ -6383,29 +6386,30 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
mddev->sync_thread ||
test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
pr_warn("md: %s still in use.\n",mdname(mddev));
if (did_freeze) {
clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
}
err = -EBUSY;
goto out;
}

if (mddev->pers) {
__md_stop_writes(mddev);

err = -ENXIO;
if (mddev->ro == MD_RDONLY)
if (mddev->ro == MD_RDONLY) {
err = -ENXIO;
goto out;
}

mddev->ro = MD_RDONLY;
set_disk_ro(mddev->gendisk, 1);
}

out:
if ((mddev->pers && !err) || did_freeze) {
clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
sysfs_notify_dirent_safe(mddev->sysfs_state);
err = 0;
}
out:

mutex_unlock(&mddev->open_mutex);
return err;
}
Expand All @@ -6426,20 +6430,8 @@ static int do_md_stop(struct mddev *mddev, int mode,
set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
md_wakeup_thread(mddev->thread);
}
if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
set_bit(MD_RECOVERY_INTR, &mddev->recovery);

/*
* Thread might be blocked waiting for metadata update which will now
* never happen
*/
md_wakeup_thread_directly(mddev->sync_thread);

mddev_unlock(mddev);
wait_event(resync_wait, (mddev->sync_thread == NULL &&
!test_bit(MD_RECOVERY_RUNNING,
&mddev->recovery)));
mddev_lock_nointr(mddev);
stop_sync_thread(mddev, true, false);

mutex_lock(&mddev->open_mutex);
if ((mddev->pers && atomic_read(&mddev->openers) > !!bdev) ||
Expand Down Expand Up @@ -9403,7 +9395,15 @@ static void md_start_sync(struct work_struct *ws)
goto not_running;
}

suspend ? mddev_unlock_and_resume(mddev) : mddev_unlock(mddev);
mddev_unlock(mddev);
/*
* md_start_sync was triggered by MD_RECOVERY_NEEDED, so we should
* not set it again. Otherwise, we may cause issue like this one:
* https://bugzilla.kernel.org/show_bug.cgi?id=218200
* Therefore, use __mddev_resume(mddev, false).
*/
if (suspend)
__mddev_resume(mddev, false);
md_wakeup_thread(mddev->sync_thread);
sysfs_notify_dirent_safe(mddev->sysfs_action);
md_new_event();
Expand All @@ -9415,7 +9415,15 @@ static void md_start_sync(struct work_struct *ws)
clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
suspend ? mddev_unlock_and_resume(mddev) : mddev_unlock(mddev);
mddev_unlock(mddev);
/*
* md_start_sync was triggered by MD_RECOVERY_NEEDED, so we should
* not set it again. Otherwise, we may cause issue like this one:
* https://bugzilla.kernel.org/show_bug.cgi?id=218200
* Therefore, use __mddev_resume(mddev, false).
*/
if (suspend)
__mddev_resume(mddev, false);

wake_up(&resync_wait);
if (test_and_clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery) &&
Expand Down
4 changes: 2 additions & 2 deletions drivers/md/raid5.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -5892,11 +5892,11 @@ static bool stripe_ahead_of_reshape(struct mddev *mddev, struct r5conf *conf,
int dd_idx;

for (dd_idx = 0; dd_idx < sh->disks; dd_idx++) {
if (dd_idx == sh->pd_idx)
if (dd_idx == sh->pd_idx || dd_idx == sh->qd_idx)
continue;

min_sector = min(min_sector, sh->dev[dd_idx].sector);
max_sector = min(max_sector, sh->dev[dd_idx].sector);
max_sector = max(max_sector, sh->dev[dd_idx].sector);
}

spin_lock_irq(&conf->device_lock);
Expand Down
5 changes: 3 additions & 2 deletions drivers/nvme/host/Kconfig
View file
Original file line number Diff line number Diff line change
Expand Up @@ -107,11 +107,12 @@ config NVME_TCP_TLS
If unsure, say N.

config NVME_HOST_AUTH
bool "NVM Express over Fabrics In-Band Authentication"
bool "NVMe over Fabrics In-Band Authentication in host side"
depends on NVME_CORE
select NVME_AUTH
help
This provides support for NVMe over Fabrics In-Band Authentication.
This provides support for NVMe over Fabrics In-Band Authentication in
host side.

If unsure, say N.

Expand Down
Loading

0 comments on commit d71369d

Please sign in to comment.