Hi Song,
Song Liu <song@xxxxxxxxxx> 於 2023年8月28日 週一 下午1:21寫道：
>
> Hi AceLan,
>
> Thanks for running the experiments.
>
> On Fri, Aug 25, 2023 at 9:32 PM AceLan Kao <acelan@xxxxxxxxx> wrote:
> [...]
> > >
> > > Could you please run the follow two experiments?
> > >
> > > 1. Confirm 12a6caf273240a triggers this. Specifically:
> > > git checkout 12a6caf273240a => repros
> > > git checkout 12a6caf273240a~1 => cannot repro
> > Yes, I'm pretty sure about this, that's my bisect result and I just
> > confirmed it again.
> > I also tried reverting 12a6caf273240a and the issue is gone.
>
> The log doesn't match my guess. Specifically:
>
> [ 420.068142] systemd-shutdown[1]: Stopping MD /dev/md123 (9:123).
> [ 420.074718] md_open:md123 openers++ = 1 by systemd-shutdow
> [ 420.080787] systemd-shutdown[1]: Failed to sync MD block device
> /dev/md123, ignoring: Input/output error
> [ 420.090831] md: md123 stopped.
> [ 420.094465] systemd-shutdown[1]: Stopping MD /dev/md122 (9:122).
> [ 420.101045] systemd-shutdown[1]: Could not stop MD /dev/md122:
> Device or resource busy
>
> For a successful stop on md123, we reach the pr_info() in md_open().
> For a failed stop on md122, the kernel returns -EBUSY before that
> pr_info() in md_open(). There are some changes in md_open() in
> the past few release, so I am not quite sure we are looking at the
> same code.
>
> Therefore, could you please help clarify:
>
> 1. Which base kernel are you using?
>
> From the log, you are using 6.5-rc7-706a74159504. However,
> I think we cannot cleanly revert 12a6caf273240a on top of
> 6.5-rc7-706a74159504. Did you manually fix some issue in the
> revert? If so, could you please share the revert commit?
Yes, I'm basing 6.5.0-rc7 706a74159504 to apply your patch
706a74159504 Linux 6.5-rc7
Attached how I revert the commit.
>
> 2. If you are not using 6.5-rc7-706a74159504 as base kernel, which
> one are you using?
>
> Thanks,
> Song
>
> >
> > >
> > > 2. Try with the following change (add debug messages), which hopefully
> > > shows which command is holding a reference on mddev->openers.
> > >
> > > Thanks,
> > > Song
> > >
> > > diff --git i/drivers/md/md.c w/drivers/md/md.c
> > > index 78be7811a89f..3e9b718b32c1 100644
> > > --- i/drivers/md/md.c
> > > +++ w/drivers/md/md.c
> > > @@ -7574,11 +7574,15 @@ static int md_ioctl(struct block_device *bdev,
> > > blk_mode_t mode,
> > > if (mddev->pers && atomic_read(&mddev->openers) > 1) {
> > > mutex_unlock(&mddev->open_mutex);
> > > err = -EBUSY;
> > > + pr_warn("%s return -EBUSY for %s with
> > > mddev->openers = %d\n",
> > > + __func__, mdname(mddev),
> > > atomic_read(&mddev->openers));
> > > goto out;
> > > }
> > > if (test_and_set_bit(MD_CLOSING, &mddev->flags)) {
> > > mutex_unlock(&mddev->open_mutex);
> > > err = -EBUSY;
> > > + pr_warn("%s return -EBUSY for %s with
> > > MD_CLOSING bit set\n",
> > > + __func__, mdname(mddev));
> > > goto out;
> > > }
> > > did_set_md_closing = true;
> > > @@ -7789,6 +7793,8 @@ static int md_open(struct gendisk *disk, blk_mode_t mode)
> > > goto out_unlock;
> > >
> > > atomic_inc(&mddev->openers);
> > > + pr_info("%s:%s openers++ = %d by %s\n", __func__, mdname(mddev),
> > > + atomic_read(&mddev->openers), current->comm);
> > > mutex_unlock(&mddev->open_mutex);
> > >
> > > disk_check_media_change(disk);
> > > @@ -7807,6 +7813,8 @@ static void md_release(struct gendisk *disk)
> > >
> > > BUG_ON(!mddev);
> > > atomic_dec(&mddev->openers);
> > > + pr_info("%s:%s openers-- = %d by %s\n", __func__, mdname(mddev),
> > > + atomic_read(&mddev->openers), current->comm);
> > > mddev_put(mddev);
> > > }
> > It's pretty strange that I can't reproduce the issue after applied the patch.
> >
> > I tried to figure out which part affect the issue and found when I
> > comment out the pr_info() In md_release(), the issue could be
> > reproduced.
> >
> > --
> > Chia-Lin Kao(AceLan)
> > http://blog.acelan.idv.tw/
> > E-Mail: acelan.kaoATcanonical.com (s/AT/@/)
--
Chia-Lin Kao(AceLan)
http://blog.acelan.idv.tw/
E-Mail: acelan.kaoATcanonical.com (s/AT/@/)
From 58dd106db88f00b08d20d4a949a001629238dbc0 Mon Sep 17 00:00:00 2001
From: "Chia-Lin Kao (AceLan)" <acelan.kao@xxxxxxxxxxxxx>
Date: Mon, 28 Aug 2023 02:34:08 -0400
Subject: [PATCH] Revert "md: only delete entries from all_mddevs when the disk
is freed"
This reverts commit 12a6caf273240ae42842de8cc05feaa86e582d61.
---
drivers/md/md.c | 52 ++++++++++++++++---------------------------------
drivers/md/md.h | 2 --
2 files changed, 17 insertions(+), 37 deletions(-)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 78be7811a89f..af5d379ad357 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -606,10 +606,6 @@ EXPORT_SYMBOL(md_flush_request);
static inline struct mddev *mddev_get(struct mddev *mddev)
{
- lockdep_assert_held(&all_mddevs_lock);
-
- if (test_bit(MD_DELETED, &mddev->flags))
- return NULL;
atomic_inc(&mddev->active);
return mddev;
}
@@ -624,7 +620,7 @@ void mddev_put(struct mddev *mddev)
mddev->ctime == 0 && !mddev->hold_active) {
/* Array is not configured at all, and not held active,
* so destroy it */
- set_bit(MD_DELETED, &mddev->flags);
+ list_del_init(&mddev->all_mddevs);
/*
* Call queue_work inside the spinlock so that
@@ -3285,8 +3281,6 @@ static bool md_rdev_overlaps(struct md_rdev *rdev)
spin_lock(&all_mddevs_lock);
list_for_each_entry(mddev, &all_mddevs, all_mddevs) {
- if (test_bit(MD_DELETED, &mddev->flags))
- continue;
rdev_for_each(rdev2, mddev) {
if (rdev != rdev2 && rdev->bdev == rdev2->bdev &&
md_rdevs_overlap(rdev, rdev2)) {
@@ -5488,10 +5482,11 @@ md_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
if (!entry->show)
return -EIO;
spin_lock(&all_mddevs_lock);
- if (!mddev_get(mddev)) {
+ if (list_empty(&mddev->all_mddevs)) {
spin_unlock(&all_mddevs_lock);
return -EBUSY;
}
+ mddev_get(mddev);
spin_unlock(&all_mddevs_lock);
rv = entry->show(mddev, page);
@@ -5512,10 +5507,11 @@ md_attr_store(struct kobject *kobj, struct attribute *attr,
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
spin_lock(&all_mddevs_lock);
- if (!mddev_get(mddev)) {
+ if (list_empty(&mddev->all_mddevs)) {
spin_unlock(&all_mddevs_lock);
return -EBUSY;
}
+ mddev_get(mddev);
spin_unlock(&all_mddevs_lock);
rv = entry->store(mddev, page, length);
mddev_put(mddev);
@@ -7826,6 +7822,7 @@ static void md_free_disk(struct gendisk *disk)
struct mddev *mddev = disk->private_data;
percpu_ref_exit(&mddev->writes_pending);
+
mddev_free(mddev);
}
@@ -8159,8 +8156,7 @@ static void *md_seq_start(struct seq_file *seq, loff_t *pos)
list_for_each(tmp,&all_mddevs)
if (!l--) {
mddev = list_entry(tmp, struct mddev, all_mddevs);
- if (!mddev_get(mddev))
- continue;
+ mddev_get(mddev);
spin_unlock(&all_mddevs_lock);
return mddev;
}
@@ -8174,35 +8170,25 @@ static void *md_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct list_head *tmp;
struct mddev *next_mddev, *mddev = v;
- struct mddev *to_put = NULL;
++*pos;
if (v == (void*)2)
return NULL;
spin_lock(&all_mddevs_lock);
- if (v == (void*)1) {
+ if (v == (void*)1)
tmp = all_mddevs.next;
- } else {
- to_put = mddev;
- tmp = mddev->all_mddevs.next;
- }
-
- for (;;) {
- if (tmp == &all_mddevs) {
- next_mddev = (void*)2;
- *pos = 0x10000;
- break;
- }
- next_mddev = list_entry(tmp, struct mddev, all_mddevs);
- if (mddev_get(next_mddev))
- break;
- mddev = next_mddev;
+ else
tmp = mddev->all_mddevs.next;
+ if (tmp != &all_mddevs)
+ next_mddev = mddev_get(list_entry(tmp,struct mddev,all_mddevs));
+ else {
+ next_mddev = (void*)2;
+ *pos = 0x10000;
}
spin_unlock(&all_mddevs_lock);
- if (to_put)
+ if (v != (void*)1)
mddev_put(mddev);
return next_mddev;
@@ -8772,8 +8758,6 @@ void md_do_sync(struct md_thread *thread)
goto skip;
spin_lock(&all_mddevs_lock);
list_for_each_entry(mddev2, &all_mddevs, all_mddevs) {
- if (test_bit(MD_DELETED, &mddev2->flags))
- continue;
if (mddev2 == mddev)
continue;
if (!mddev->parallel_resync
@@ -9577,8 +9561,7 @@ static int md_notify_reboot(struct notifier_block *this,
spin_lock(&all_mddevs_lock);
list_for_each_entry_safe(mddev, n, &all_mddevs, all_mddevs) {
- if (!mddev_get(mddev))
- continue;
+ mddev_get(mddev);
spin_unlock(&all_mddevs_lock);
if (mddev_trylock(mddev)) {
if (mddev->pers)
@@ -9934,8 +9917,7 @@ static __exit void md_exit(void)
spin_lock(&all_mddevs_lock);
list_for_each_entry_safe(mddev, n, &all_mddevs, all_mddevs) {
- if (!mddev_get(mddev))
- continue;
+ mddev_get(mddev);
spin_unlock(&all_mddevs_lock);
export_array(mddev);
mddev->ctime = 0;
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 1aef86bf3fc3..4e265e38c229 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -252,7 +252,6 @@ struct md_cluster_info;
* @MD_NOT_READY: do_md_run() is active, so 'array_state', ust not report that
* array is ready yet.
* @MD_BROKEN: This is used to stop writes and mark array as failed.
- * @MD_DELETED: This device is being deleted
*
* change UNSUPPORTED_MDDEV_FLAGS for each array type if new flag is added
*/
@@ -269,7 +268,6 @@ enum mddev_flags {
MD_UPDATING_SB,
MD_NOT_READY,
MD_BROKEN,
- MD_DELETED,
};
enum mddev_sb_flags {
--
2.37.2
