[v9,03/10] md: Neither resync nor reshape while the system is frozen

Commit Message

Bart Van Assche Oct. 16, 2017, 11:28 p.m. UTC

Some people use the md driver on laptops and use the suspend and
resume functionality. Since it is essential that submitting of
new I/O requests stops before a hibernation image is created,
interrupt the md resync and reshape actions if the system is
being frozen. Note: the resync and reshape will restart after
the system is resumed and a message similar to the following
will appear in the system log:

md: md0: data-check interrupted.

Signed-off-by: Bart Van Assche <[e-mail]>
Reviewed-by: Shaohua Li <[e-mail]>
Tested-by: Martin Steigerwald <[e-mail]>
Cc: [e-mail]
Cc: Ming Lei <[e-mail]>
Cc: Christoph Hellwig <[e-mail]>
Cc: Hannes Reinecke <[e-mail]>
Cc: Johannes Thumshirn <[e-mail]>
---
 drivers/md/md.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++++-
 drivers/md/md.h |  8 ++++++++
 2 files changed, 57 insertions(+), 1 deletion(-)

Comments

Hannes Reinecke Oct. 17, 2017, 6:24 a.m. UTC | #1

On 10/17/2017 01:28 AM, Bart Van Assche wrote:
> Some people use the md driver on laptops and use the suspend and
> resume functionality. Since it is essential that submitting of
> new I/O requests stops before a hibernation image is created,
> interrupt the md resync and reshape actions if the system is
> being frozen. Note: the resync and reshape will restart after
> the system is resumed and a message similar to the following
> will appear in the system log:
> 
> md: md0: data-check interrupted.
> 
> Signed-off-by: Bart Van Assche <[e-mail]>
> Reviewed-by: Shaohua Li <[e-mail]>
> Tested-by: Martin Steigerwald <[e-mail]>
> Cc: [e-mail]
> Cc: Ming Lei <[e-mail]>
> Cc: Christoph Hellwig <[e-mail]>
> Cc: Hannes Reinecke <[e-mail]>
> Cc: Johannes Thumshirn <[e-mail]>
> ---
>  drivers/md/md.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++++-
>  drivers/md/md.h |  8 ++++++++
>  2 files changed, 57 insertions(+), 1 deletion(-)
> 
Reviewed-by: Hannes Reinecke <[e-mail]>

Cheers,

Hannes

Patch

diff --git a/drivers/md/md.c b/drivers/md/md.c
index b99584e5d6b1..8b2fc750f97f 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -66,6 +66,8 @@ 
 #include <linux/raid/md_u.h>
 #include <linux/slab.h>
 #include <linux/percpu-refcount.h>
+#include <linux/freezer.h>
+#include <linux/suspend.h>
 
 #include <trace/events/block.h>
 #include "md.h"
@@ -7439,6 +7441,7 @@  static int md_thread(void *arg)
 	 */
 
 	allow_signal(SIGKILL);
+	set_freezable();
 	while (!kthread_should_stop()) {
 
 		/* We need to wait INTERRUPTIBLE so that
@@ -7449,7 +7452,7 @@  static int md_thread(void *arg)
 		if (signal_pending(current))
 			flush_signals(current);
 
-		wait_event_interruptible_timeout
+		wait_event_freezable_timeout
 			(thread->wqueue,
 			 test_bit(THREAD_WAKEUP, &thread->flags)
 			 || kthread_should_stop() || kthread_should_park(),
@@ -8944,6 +8947,8 @@  static void md_stop_all_writes(void)
 	int need_delay = 0;
 
 	for_each_mddev(mddev, tmp) {
+		mddev->frozen_before_suspend =
+			test_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 		if (mddev_trylock(mddev)) {
 			if (mddev->pers)
 				__md_stop_writes(mddev);
@@ -8963,6 +8968,47 @@  static void md_stop_all_writes(void)
 		mdelay(1000*1);
 }
 
+static void md_restore_frozen_flag(void)
+{
+	struct list_head *tmp;
+	struct mddev *mddev;
+
+	for_each_mddev(mddev, tmp) {
+		if (mddev->frozen_before_suspend)
+			set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+		else
+			clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	}
+}
+
+/*
+ * Ensure that neither resyncing nor reshaping occurs while the system is
+ * frozen.
+ */
+static int md_notify_pm(struct notifier_block *bl, unsigned long state,
+			void *unused)
+{
+	pr_debug("%s: state = %ld\n", __func__, state);
+
+	switch (state) {
+	case PM_HIBERNATION_PREPARE:
+	case PM_SUSPEND_PREPARE:
+	case PM_RESTORE_PREPARE:
+		md_stop_all_writes();
+		break;
+	case PM_POST_HIBERNATION:
+	case PM_POST_SUSPEND:
+	case PM_POST_RESTORE:
+		md_restore_frozen_flag();
+		break;
+	}
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block md_pm_notifier = {
+	.notifier_call	= md_notify_pm,
+};
+
 static int md_notify_reboot(struct notifier_block *this,
 			    unsigned long code, void *x)
 {
@@ -9009,6 +9055,7 @@  static int __init md_init(void)
 			    md_probe, NULL, NULL);
 
 	register_reboot_notifier(&md_reboot_notifier);
+	register_pm_notifier(&md_pm_notifier);
 	raid_table_header = register_sysctl_table(raid_root_table);
 
 	md_geninit();
@@ -9248,6 +9295,7 @@  static __exit void md_exit(void)
 
 	unregister_blkdev(MD_MAJOR,"md");
 	unregister_blkdev(mdp_major, "mdp");
+	unregister_pm_notifier(&md_pm_notifier);
 	unregister_reboot_notifier(&md_reboot_notifier);
 	unregister_sysctl_table(raid_table_header);
 
diff --git a/drivers/md/md.h b/drivers/md/md.h
index d8287d3cd1bf..727b3aef4d26 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -356,6 +356,14 @@  struct mddev {
 	 */
 	int				recovery_disabled;
 
+	/* Writes are stopped before hibernation, suspend and restore by
+	 * calling md_stop_all_writes(). That function sets the
+	 * MD_RECOVERY_FROZEN flag. The value of that flag is saved before
+	 * writes are stopped such that it can be restored after hibernation,
+	 * suspend or restore have finished.
+	 */
+	bool				frozen_before_suspend;
+
 	int				in_sync;	/* know to not need resync */
 	/* 'open_mutex' avoids races between 'md_open' and 'do_md_stop', so
 	 * that we are never stopping an array while it is open.