RAID5: check_reshape() shouldn't call mddev_suspend
check_reshape() is called from raid5d thread. raid5d thread shouldn't
call mddev_suspend(), because mddev_suspend() waits for all IO finish
but IO is handled in raid5d thread, we could easily deadlock here.
This issue is introduced by
738a273 ("md/raid5: fix allocation of 'scribble' array.")
Cc: stable@vger.kernel.org (v4.1+)
Reported-and-tested-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Reviewed-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 7f770b0..b628cd5 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2089,6 +2089,14 @@
unsigned long cpu;
int err = 0;
+ /*
+ * Never shrink. And mddev_suspend() could deadlock if this is called
+ * from raid5d. In that case, scribble_disks and scribble_sectors
+ * should equal to new_disks and new_sectors
+ */
+ if (conf->scribble_disks >= new_disks &&
+ conf->scribble_sectors >= new_sectors)
+ return 0;
mddev_suspend(conf->mddev);
get_online_cpus();
for_each_present_cpu(cpu) {
@@ -2110,6 +2118,10 @@
}
put_online_cpus();
mddev_resume(conf->mddev);
+ if (!err) {
+ conf->scribble_disks = new_disks;
+ conf->scribble_sectors = new_sectors;
+ }
return err;
}
@@ -6413,6 +6425,12 @@
}
put_online_cpus();
+ if (!err) {
+ conf->scribble_disks = max(conf->raid_disks,
+ conf->previous_raid_disks);
+ conf->scribble_sectors = max(conf->chunk_sectors,
+ conf->prev_chunk_sectors);
+ }
return err;
}
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index a415e1c..ae6068d 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -510,6 +510,8 @@
* conversions
*/
} __percpu *percpu;
+ int scribble_disks;
+ int scribble_sectors;
#ifdef CONFIG_HOTPLUG_CPU
struct notifier_block cpu_notify;
#endif