md: fix race when unfreezing sync_action
A recent change removed the need for locking around writing
to "sync_action" (and various other places), but introduced a
subtle race.
When e.g. setting 'reshape' on a 'frozen' array, the 'frozen'
flag is cleared before 'reshape' is set, so the md thread can
get in and start trying recovery - which isn't wanted.
So instead of clearing MD_RECOVERY_FROZEN for any command
except 'frozen', only clear it when each specific command
is parsed. This allows the handling of 'reshape' to clear
the bit while a lock is held.
Also remove some places where we set MD_RECOVERY_NEEDED,
as it is always set on non-error exit of the function.
Signed-off-by: NeilBrown <neilb@suse.de>
Fixes: 6791875e2e53 ("md: make reconfig_mutex optional for writes to md sysfs files.")
diff --git a/drivers/md/md.c b/drivers/md/md.c
index d4f31e1..8f10f4e 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -4211,12 +4211,12 @@
if (!mddev->pers || !mddev->pers->sync_request)
return -EINVAL;
- if (cmd_match(page, "frozen"))
- set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
- else
- clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
if (cmd_match(page, "idle") || cmd_match(page, "frozen")) {
+ if (cmd_match(page, "frozen"))
+ set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+ else
+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
flush_workqueue(md_misc_wq);
if (mddev->sync_thread) {
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
@@ -4229,16 +4229,17 @@
test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))
return -EBUSY;
else if (cmd_match(page, "resync"))
- set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
else if (cmd_match(page, "recover")) {
+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
- set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
} else if (cmd_match(page, "reshape")) {
int err;
if (mddev->pers->start_reshape == NULL)
return -EINVAL;
err = mddev_lock(mddev);
if (!err) {
+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
err = mddev->pers->start_reshape(mddev);
mddev_unlock(mddev);
}
@@ -4250,6 +4251,7 @@
set_bit(MD_RECOVERY_CHECK, &mddev->recovery);
else if (!cmd_match(page, "repair"))
return -EINVAL;
+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
}